3096 files changed, 99802 insertions, 46593 deletions

diff --git a/.clang-format b/.clang-format
index fe1aa1a30d40..86c20ee744de 100644
--- a/.clang-format
+++ b/.clang-format
@@ -92,6 +92,7 @@ ForEachMacros:
   - '__rq_for_each_bio'
   - '__shost_for_each_device'
   - '__sym_for_each'
+  - '_for_each_counter'
   - 'apei_estatus_for_each_section'
   - 'ata_for_each_dev'
   - 'ata_for_each_link'
@@ -141,11 +142,14 @@ ForEachMacros:
   - 'damon_for_each_target_safe'
   - 'damos_for_each_filter'
   - 'damos_for_each_filter_safe'
+  - 'damos_for_each_ops_filter'
+  - 'damos_for_each_ops_filter_safe'
   - 'damos_for_each_quota_goal'
   - 'damos_for_each_quota_goal_safe'
   - 'data__for_each_file'
   - 'data__for_each_file_new'
   - 'data__for_each_file_start'
+  - 'def_for_each_cpu'
   - 'device_for_each_child_node'
   - 'device_for_each_child_node_scoped'
   - 'dma_fence_array_for_each'
@@ -176,6 +180,7 @@ ForEachMacros:
   - 'drm_for_each_privobj'
   - 'drm_gem_for_each_gpuvm_bo'
   - 'drm_gem_for_each_gpuvm_bo_safe'
+  - 'drm_gpusvm_for_each_range'
   - 'drm_gpuva_for_each_op'
   - 'drm_gpuva_for_each_op_from_reverse'
   - 'drm_gpuva_for_each_op_reverse'
@@ -216,8 +221,10 @@ ForEachMacros:
   - 'for_each_active_dev_scope'
   - 'for_each_active_drhd_unit'
   - 'for_each_active_iommu'
+  - 'for_each_active_irq'
   - 'for_each_active_route'
   - 'for_each_aggr_pgid'
+  - 'for_each_alloc_capable_rdt_resource'
   - 'for_each_and_bit'
   - 'for_each_andnot_bit'
   - 'for_each_available_child_of_node'
@@ -228,6 +235,7 @@ ForEachMacros:
   - 'for_each_btf_ext_rec'
   - 'for_each_btf_ext_sec'
   - 'for_each_bvec'
+  - 'for_each_capable_rdt_resource'
   - 'for_each_card_auxs'
   - 'for_each_card_auxs_safe'
   - 'for_each_card_components'
@@ -241,6 +249,7 @@ ForEachMacros:
   - 'for_each_cgroup_storage_type'
   - 'for_each_child_of_node'
   - 'for_each_child_of_node_scoped'
+  - 'for_each_child_of_node_with_prefix'
   - 'for_each_clear_bit'
   - 'for_each_clear_bit_from'
   - 'for_each_clear_bitrange'
@@ -296,6 +305,7 @@ ForEachMacros:
   - 'for_each_group_member_head'
   - 'for_each_hstate'
   - 'for_each_hwgpio'
+  - 'for_each_hwgpio_in_range'
   - 'for_each_if'
   - 'for_each_inject_fn'
   - 'for_each_insn'
@@ -304,6 +314,7 @@ ForEachMacros:
   - 'for_each_intid'
   - 'for_each_iommu'
   - 'for_each_ip_tunnel_rcu'
+  - 'for_each_irq_desc'
   - 'for_each_irq_nr'
   - 'for_each_lang'
   - 'for_each_link_ch_maps'
@@ -324,6 +335,8 @@ ForEachMacros:
   - 'for_each_missing_reg'
   - 'for_each_mle_subelement'
   - 'for_each_mod_mem_type'
+  - 'for_each_mon_capable_rdt_resource'
+  - 'for_each_mp_bvec'
   - 'for_each_net'
   - 'for_each_net_continue_reverse'
   - 'for_each_net_rcu'
@@ -351,6 +364,7 @@ ForEachMacros:
   - 'for_each_node_by_name'
   - 'for_each_node_by_type'
   - 'for_each_node_mask'
+  - 'for_each_node_numadist'
   - 'for_each_node_state'
   - 'for_each_node_with_cpus'
   - 'for_each_node_with_property'
@@ -359,6 +373,8 @@ ForEachMacros:
   - 'for_each_of_allnodes'
   - 'for_each_of_allnodes_from'
   - 'for_each_of_cpu_node'
+  - 'for_each_of_graph_port'
+  - 'for_each_of_graph_port_endpoint'
   - 'for_each_of_pci_range'
   - 'for_each_old_connector_in_state'
   - 'for_each_old_crtc_in_state'
@@ -372,9 +388,11 @@ ForEachMacros:
   - 'for_each_oldnew_plane_in_state_reverse'
   - 'for_each_oldnew_private_obj_in_state'
   - 'for_each_online_cpu'
+  - 'for_each_online_cpu_wrap'
   - 'for_each_online_node'
   - 'for_each_online_pgdat'
   - 'for_each_or_bit'
+  - 'for_each_page_ext'
   - 'for_each_path'
   - 'for_each_pci_bridge'
   - 'for_each_pci_dev'
@@ -382,8 +400,10 @@ ForEachMacros:
   - 'for_each_physmem_range'
   - 'for_each_populated_zone'
   - 'for_each_possible_cpu'
+  - 'for_each_possible_cpu_wrap'
   - 'for_each_present_blessed_reg'
   - 'for_each_present_cpu'
+  - 'for_each_present_section_nr'
   - 'for_each_prime_number'
   - 'for_each_prime_number_from'
   - 'for_each_probe_cache_entry'
@@ -396,6 +416,7 @@ ForEachMacros:
   - 'for_each_prop_dlc_cpus'
   - 'for_each_prop_dlc_platforms'
   - 'for_each_property_of_node'
+  - 'for_each_rdt_resource'
   - 'for_each_reg'
   - 'for_each_reg_filtered'
   - 'for_each_reloc'
@@ -434,10 +455,10 @@ ForEachMacros:
   - 'for_each_subelement_id'
   - 'for_each_sublist'
   - 'for_each_subsystem'
+  - 'for_each_suite'
   - 'for_each_supported_activate_fn'
   - 'for_each_supported_inject_fn'
   - 'for_each_sym'
-  - 'for_each_test'
   - 'for_each_thread'
   - 'for_each_token'
   - 'for_each_unicast_dest_pgid'
@@ -499,8 +520,10 @@ ForEachMacros:
   - 'idr_for_each_entry_continue'
   - 'idr_for_each_entry_continue_ul'
   - 'idr_for_each_entry_ul'
+  - 'iio_for_each_active_channel'
   - 'in_dev_for_each_ifa_rcu'
   - 'in_dev_for_each_ifa_rtnl'
+  - 'in_dev_for_each_ifa_rtnl_net'
   - 'inet_bind_bucket_for_each'
   - 'interval_tree_for_each_span'
   - 'intlist__for_each_entry'
@@ -542,7 +565,6 @@ ForEachMacros:
   - 'list_for_each_prev'
   - 'list_for_each_prev_safe'
   - 'list_for_each_rcu'
-  - 'list_for_each_reverse'
   - 'list_for_each_safe'
   - 'llist_for_each'
   - 'llist_for_each_entry'
@@ -552,6 +574,7 @@ ForEachMacros:
   - 'map__for_each_symbol'
   - 'map__for_each_symbol_by_name'
   - 'mas_for_each'
+  - 'mas_for_each_rev'
   - 'mci_for_each_dimm'
   - 'media_device_for_each_entity'
   - 'media_device_for_each_intf'
@@ -561,10 +584,15 @@ ForEachMacros:
   - 'media_pipeline_for_each_entity'
   - 'media_pipeline_for_each_pad'
   - 'mlx5_lag_for_each_peer_mdev'
+  - 'mptcp_for_each_subflow'
   - 'msi_domain_for_each_desc'
   - 'msi_for_each_desc'
   - 'mt_for_each'
+  - 'nanddev_io_for_each_block'
   - 'nanddev_io_for_each_page'
+  - 'neigh_for_each_in_bucket'
+  - 'neigh_for_each_in_bucket_rcu'
+  - 'neigh_for_each_in_bucket_safe'
   - 'netdev_for_each_lower_dev'
   - 'netdev_for_each_lower_private'
   - 'netdev_for_each_lower_private_rcu'
@@ -604,11 +632,11 @@ ForEachMacros:
   - 'perf_evlist__for_each_entry_safe'
   - 'perf_evlist__for_each_evsel'
   - 'perf_evlist__for_each_mmap'
+  - 'perf_evsel_for_each_per_thread_period_safe'
   - 'perf_hpp_list__for_each_format'
   - 'perf_hpp_list__for_each_format_safe'
   - 'perf_hpp_list__for_each_sort_list'
   - 'perf_hpp_list__for_each_sort_list_safe'
-  - 'perf_tool_event__for_each_event'
   - 'plist_for_each'
   - 'plist_for_each_continue'
   - 'plist_for_each_entry'
@@ -627,7 +655,6 @@ ForEachMacros:
   - 'rdma_for_each_block'
   - 'rdma_for_each_port'
   - 'rdma_umem_for_each_dma_block'
-  - 'resort_rb__for_each_entry'
   - 'resource_list_for_each_entry'
   - 'resource_list_for_each_entry_safe'
   - 'rhl_for_each_entry_rcu'
@@ -658,6 +685,7 @@ ForEachMacros:
   - 'shost_for_each_device'
   - 'sk_for_each'
   - 'sk_for_each_bound'
+  - 'sk_for_each_bound_safe'
   - 'sk_for_each_entry_offset_rcu'
   - 'sk_for_each_from'
   - 'sk_for_each_rcu'
@@ -680,7 +708,11 @@ ForEachMacros:
   - 'tb_property_for_each'
   - 'tcf_act_for_each_action'
   - 'tcf_exts_for_each_action'
+  - 'test_suite__for_each_test_case'
+  - 'tool_pmu__for_each_event'
+  - 'ttm_bo_lru_for_each_reserved_guarded'
   - 'ttm_resource_manager_for_each_res'
+  - 'udp_lrpa_for_each_entry_rcu'
   - 'udp_portaddr_for_each_entry'
   - 'udp_portaddr_for_each_entry_rcu'
   - 'usb_hub_for_each_child'
@@ -691,6 +723,7 @@ ForEachMacros:
   - 'v4l2_m2m_for_each_src_buf_safe'
   - 'virtio_device_for_each_vq'
   - 'while_for_each_ftrace_op'
+  - 'workloads__for_each'
   - 'xa_for_each'
   - 'xa_for_each_marked'
   - 'xa_for_each_range'
diff --git a/.clippy.toml b/.clippy.toml
index 815c94732ed7..137f41d203de 100644
--- a/.clippy.toml
+++ b/.clippy.toml
@@ -7,5 +7,5 @@ check-private-items = true
 disallowed-macros = [
     # The `clippy::dbg_macro` lint only works with `std::dbg!`, thus we simulate
     # it here, see: https://github.com/rust-lang/rust-clippy/issues/11303.
-    { path = "kernel::dbg", reason = "the `dbg!` macro is intended as a debugging tool" },
+    { path = "kernel::dbg", reason = "the `dbg!` macro is intended as a debugging tool", allow-invalid = true },
 ]
diff --git a/.mailmap b/.mailmap
index 4f7cd8e23177..9531546fcac9 100644
--- a/.mailmap
+++ b/.mailmap
@@ -102,6 +102,7 @@ Ard Biesheuvel <ardb@kernel.org> <ard.biesheuvel@linaro.org>
 Arnaud Patard <arnaud.patard@rtp-net.org>
 Arnd Bergmann <arnd@arndb.de>
 Arun Kumar Neelakantam <quic_aneela@quicinc.com> <aneela@codeaurora.org>
+Asahi Lina <lina+kernel@asahilina.net> <lina@asahilina.net>
 Ashok Raj Nagarajan <quic_arnagara@quicinc.com> <arnagara@codeaurora.org>
 Ashwin Chaugule <quic_ashwinc@quicinc.com> <ashwinc@codeaurora.org>
 Asutosh Das <quic_asutoshd@quicinc.com> <asutoshd@codeaurora.org>
@@ -322,6 +323,7 @@ Jayachandran C <c.jayachandran@gmail.com> <jchandra@broadcom.com>
 Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com>
 Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com>
 <jean-philippe@linaro.org> <jean-philippe.brucker@arm.com>
+Jean-Michel Hautbois <jeanmichel.hautbois@yoseli.org> <jeanmichel.hautbois@ideasonboard.com>
 Jean Tourrilhes <jt@hpl.hp.com>
 Jeevan Shriram <quic_jshriram@quicinc.com> <jshriram@codeaurora.org>
 Jeff Garzik <jgarzik@pretzel.yyz.us>
@@ -438,12 +440,16 @@ Linus Lüssing <linus.luessing@c0d3.blue> <ll@simonwunderlich.de>
 Li Yang <leoyang.li@nxp.com> <leoli@freescale.com>
 Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
 Lior David <quic_liord@quicinc.com> <liord@codeaurora.org>
+Loic Poulain <loic.poulain@oss.qualcomm.com> <loic.poulain@linaro.org>
+Loic Poulain <loic.poulain@oss.qualcomm.com> <loic.poulain@intel.com>
 Lorenzo Pieralisi <lpieralisi@kernel.org> <lorenzo.pieralisi@arm.com>
 Lorenzo Stoakes <lorenzo.stoakes@oracle.com> <lstoakes@gmail.com>
 Luca Ceresoli <luca.ceresoli@bootlin.com> <luca@lucaceresoli.net>
 Luca Weiss <luca@lucaweiss.eu> <luca@z3ntu.xyz>
 Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com>
 Luo Jie <quic_luoj@quicinc.com> <luoj@codeaurora.org>
+Lance Yang <lance.yang@linux.dev> <ioworker0@gmail.com>
+Lance Yang <lance.yang@linux.dev> <mingzhe.yang@ly.com>
 Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
 Maciej W. Rozycki <macro@orcam.me.uk> <macro@linux-mips.org>
 Maharaja Kennadyrajan <quic_mkenna@quicinc.com> <mkenna@codeaurora.org>
@@ -480,6 +486,7 @@ Matthias Fuchs <socketcan@esd.eu> <matthias.fuchs@esd.eu>
 Matthieu Baerts <matttbe@kernel.org> <matthieu.baerts@tessares.net>
 Matthieu CASTET <castet.matthieu@free.fr>
 Matti Vaittinen <mazziesaccount@gmail.com> <matti.vaittinen@fi.rohmeurope.com>
+Mattijs Korpershoek <mkorpershoek@kernel.org> <mkorpershoek@baylibre.com>
 Matt Ranostay <matt@ranostay.sg> <matt.ranostay@konsulko.com>
 Matt Ranostay <matt@ranostay.sg> <matt@ranostay.consulting>
 Matt Ranostay <matt@ranostay.sg> Matthew Ranostay <mranostay@embeddedalley.com>
@@ -685,6 +692,8 @@ Simon Wunderlich <sw@simonwunderlich.de> <simon.wunderlich@saxnet.de>
 Simon Wunderlich <sw@simonwunderlich.de> <simon@open-mesh.com>
 Simon Wunderlich <sw@simonwunderlich.de> <siwu@hrz.tu-chemnitz.de>
 Sricharan Ramabadhran <quic_srichara@quicinc.com> <sricharan@codeaurora.org>
+Srinivas Kandagatla <srini@kernel.org> <srinivas.kandagatla@st.com>
+Srinivas Kandagatla <srini@kernel.org> <srinivas.kandagatla@linaro.org>
 Srinivas Ramana <quic_sramana@quicinc.com> <sramana@codeaurora.org>
 Sriram R <quic_srirrama@quicinc.com> <srirrama@codeaurora.org>
 Sriram Yagnaraman <sriram.yagnaraman@ericsson.com> <sriram.yagnaraman@est.tech>
@@ -744,6 +753,7 @@ Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko@ursulin.net>
 Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
 Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
+Uwe Kleine-König <u.kleine-koenig@baylibre.com> <ukleinek@baylibre.com>
 Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
 Uwe Kleine-König <ukleinek@strlen.de>
 Uwe Kleine-König <ukl@pengutronix.de>
diff --git a/CREDITS b/CREDITS
index 1b77fba6c27e..f74d230992d6 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2071,6 +2071,10 @@ S: 660 Harvard Ave. #7
 S: Santa Clara, CA 95051
 S: USA
 
+N: Joonsoo Kim
+E: iamjoonsoo.kim@lge.com
+D: Slab allocators
+
 N: Kukjin Kim
 E: kgene@kernel.org
 D: Samsung S3C, S5P and Exynos ARM architectures
diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block
index 3879963f0f01..11545c9e2e93 100644
--- a/Documentation/ABI/stable/sysfs-block
+++ b/Documentation/ABI/stable/sysfs-block
@@ -77,7 +77,7 @@ Description:
 
 What:		/sys/block/<disk>/diskseq
 Date:		February 2021
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:
 		The /sys/block/<disk>/diskseq files reports the disk
 		sequence number, which is a monotonically increasing
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 206079d3bd5b..6a1acabb29d8 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -511,6 +511,7 @@ Description:	information about CPUs heterogeneity.
 
 What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/gather_data_sampling
+		/sys/devices/system/cpu/vulnerabilities/indirect_target_selection
 		/sys/devices/system/cpu/vulnerabilities/itlb_multihit
 		/sys/devices/system/cpu/vulnerabilities/l1tf
 		/sys/devices/system/cpu/vulnerabilities/mds
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd b/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd
index 2a19584d091e..8c9718d83e9d 100644
--- a/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd
+++ b/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd
@@ -1,6 +1,6 @@
 What:		/sys/bus/hid/drivers/hid-appletb-kbd/<dev>/mode
-Date:		September, 2023
-KernelVersion:	6.5
+Date:		March, 2025
+KernelVersion:	6.15
 Contact:	linux-input@vger.kernel.org
 Description:
 		The set of keys displayed on the Touch Bar.
diff --git a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
index 9bce281314df..cb207c79680d 100644
--- a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
+++ b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
@@ -111,7 +111,7 @@ Description:	RO. Package current voltage in millivolt.
 
 What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/temp2_input
 Date:		March 2025
-KernelVersion:	6.14
+KernelVersion:	6.15
 Contact:	intel-xe@lists.freedesktop.org
 Description:	RO. Package temperature in millidegree Celsius.
 
@@ -119,7 +119,7 @@ Description:	RO. Package temperature in millidegree Celsius.
 
 What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/temp3_input
 Date:		March 2025
-KernelVersion:	6.14
+KernelVersion:	6.15
 Contact:	intel-xe@lists.freedesktop.org
 Description:	RO. VRAM temperature in millidegree Celsius.
 
diff --git a/Documentation/ABI/testing/sysfs-driver-ufs b/Documentation/ABI/testing/sysfs-driver-ufs
index ae0191295d29..e36d2de16cbd 100644
--- a/Documentation/ABI/testing/sysfs-driver-ufs
+++ b/Documentation/ABI/testing/sysfs-driver-ufs
@@ -1604,3 +1604,35 @@ Description:
 		prevent the UFS from frequently performing clock gating/ungating.
 
 		The attribute is read/write.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/device_lvl_exception_count
+What:		/sys/bus/platform/devices/*.ufs/device_lvl_exception_count
+Date:		March 2025
+Contact:	Bao D. Nguyen <quic_nguyenb@quicinc.com>
+Description:
+		This attribute is applicable to ufs devices compliant to the
+		JEDEC specifications version 4.1 or later. The
+		device_lvl_exception_count is a counter indicating the number of
+		times the device level exceptions have occurred since the last
+		time this variable is reset.  Writing a 0 value to this
+		attribute will reset the device_lvl_exception_count.  If the
+		device_lvl_exception_count reads a positive value, the user
+		application should read the device_lvl_exception_id attribute to
+		know more information about the exception.
+
+		The attribute is read/write.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/device_lvl_exception_id
+What:		/sys/bus/platform/devices/*.ufs/device_lvl_exception_id
+Date:		March 2025
+Contact:	Bao D. Nguyen <quic_nguyenb@quicinc.com>
+Description:
+		Reading the device_lvl_exception_id returns the
+		qDeviceLevelExceptionID attribute of the ufs device JEDEC
+		specification version 4.1. The definition of the
+		qDeviceLevelExceptionID is the ufs device vendor specific
+		implementation.  Refer to the device manufacturer datasheet for
+		more information on the meaning of the qDeviceLevelExceptionID
+		attribute value.
+
+		The attribute is read only.
diff --git a/Documentation/ABI/testing/sysfs-kernel-reboot b/Documentation/ABI/testing/sysfs-kernel-reboot
index e117aba46be0..52571fd5ddba 100644
--- a/Documentation/ABI/testing/sysfs-kernel-reboot
+++ b/Documentation/ABI/testing/sysfs-kernel-reboot
@@ -1,7 +1,7 @@
 What:		/sys/kernel/reboot
 Date:		November 2020
 KernelVersion:	5.11
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:	Interface to set the kernel reboot behavior, similarly to
 		what can be done via the reboot= cmdline option.
 		(see Documentation/admin-guide/kernel-parameters.txt)
@@ -9,25 +9,25 @@ Description:	Interface to set the kernel reboot behavior, similarly to
 What:		/sys/kernel/reboot/mode
 Date:		November 2020
 KernelVersion:	5.11
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:	Reboot mode. Valid values are: cold warm hard soft gpio
 
 What:		/sys/kernel/reboot/type
 Date:		November 2020
 KernelVersion:	5.11
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:	Reboot type. Valid values are: bios acpi kbd triple efi pci
 
 What:		/sys/kernel/reboot/cpu
 Date:		November 2020
 KernelVersion:	5.11
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:	CPU number to use to reboot.
 
 What:		/sys/kernel/reboot/force
 Date:		November 2020
 KernelVersion:	5.11
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:	Don't wait for any other CPUs on reboot and
 		avoid anything that could hang.
 
diff --git a/Documentation/admin-guide/bug-hunting.rst b/Documentation/admin-guide/bug-hunting.rst
index ce6f4e8ca487..30858757c9f2 100644
--- a/Documentation/admin-guide/bug-hunting.rst
+++ b/Documentation/admin-guide/bug-hunting.rst
@@ -196,7 +196,7 @@ will see the assembler code for the routine shown, but if your kernel has
 debug symbols the C code will also be available. (Debug symbols can be enabled
 in the kernel hacking menu of the menu configuration.) For example::
 
-    $ objdump -r -S -l --disassemble net/dccp/ipv4.o
+    $ objdump -r -S -l --disassemble net/ipv4/tcp.o
 
 .. note::
 
diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst
index ff0b440ef2dc..ce296b8430fc 100644
--- a/Documentation/admin-guide/hw-vuln/index.rst
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@@ -22,3 +22,5 @@ are configurable at compile, boot or run time.
    srso
    gather_data_sampling
    reg-file-data-sampling
+   rsb
+   indirect-target-selection
diff --git a/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst b/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst
new file mode 100644
index 000000000000..d9ca64108d23
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst
@@ -0,0 +1,168 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Indirect Target Selection (ITS)
+===============================
+
+ITS is a vulnerability in some Intel CPUs that support Enhanced IBRS and were
+released before Alder Lake. ITS may allow an attacker to control the prediction
+of indirect branches and RETs located in the lower half of a cacheline.
+
+ITS is assigned CVE-2024-28956 with a CVSS score of 4.7 (Medium).
+
+Scope of Impact
+---------------
+- **eIBRS Guest/Host Isolation**: Indirect branches in KVM/kernel may still be
+  predicted with unintended target corresponding to a branch in the guest.
+
+- **Intra-Mode BTI**: In-kernel training such as through cBPF or other native
+  gadgets.
+
+- **Indirect Branch Prediction Barrier (IBPB)**: After an IBPB, indirect
+  branches may still be predicted with targets corresponding to direct branches
+  executed prior to the IBPB. This is fixed by the IPU 2025.1 microcode, which
+  should be available via distro updates. Alternatively microcode can be
+  obtained from Intel's github repository [#f1]_.
+
+Affected CPUs
+-------------
+Below is the list of ITS affected CPUs [#f2]_ [#f3]_:
+
+   ========================  ============  ====================  ===============
+   Common name               Family_Model  eIBRS                 Intra-mode BTI
+                                           Guest/Host Isolation
+   ========================  ============  ====================  ===============
+   SKYLAKE_X (step >= 6)     06_55H        Affected              Affected
+   ICELAKE_X                 06_6AH        Not affected          Affected
+   ICELAKE_D                 06_6CH        Not affected          Affected
+   ICELAKE_L                 06_7EH        Not affected          Affected
+   TIGERLAKE_L               06_8CH        Not affected          Affected
+   TIGERLAKE                 06_8DH        Not affected          Affected
+   KABYLAKE_L (step >= 12)   06_8EH        Affected              Affected
+   KABYLAKE (step >= 13)     06_9EH        Affected              Affected
+   COMETLAKE                 06_A5H        Affected              Affected
+   COMETLAKE_L               06_A6H        Affected              Affected
+   ROCKETLAKE                06_A7H        Not affected          Affected
+   ========================  ============  ====================  ===============
+
+- All affected CPUs enumerate Enhanced IBRS feature.
+- IBPB isolation is affected on all ITS affected CPUs, and need a microcode
+  update for mitigation.
+- None of the affected CPUs enumerate BHI_CTRL which was introduced in Golden
+  Cove (Alder Lake and Sapphire Rapids). This can help guests to determine the
+  host's affected status.
+- Intel Atom CPUs are not affected by ITS.
+
+Mitigation
+----------
+As only the indirect branches and RETs that have their last byte of instruction
+in the lower half of the cacheline are vulnerable to ITS, the basic idea behind
+the mitigation is to not allow indirect branches in the lower half.
+
+This is achieved by relying on existing retpoline support in the kernel, and in
+compilers. ITS-vulnerable retpoline sites are runtime patched to point to newly
+added ITS-safe thunks. These safe thunks consists of indirect branch in the
+second half of the cacheline. Not all retpoline sites are patched to thunks, if
+a retpoline site is evaluated to be ITS-safe, it is replaced with an inline
+indirect branch.
+
+Dynamic thunks
+~~~~~~~~~~~~~~
+From a dynamically allocated pool of safe-thunks, each vulnerable site is
+replaced with a new thunk, such that they get a unique address. This could
+improve the branch prediction accuracy. Also, it is a defense-in-depth measure
+against aliasing.
+
+Note, for simplicity, indirect branches in eBPF programs are always replaced
+with a jump to a static thunk in __x86_indirect_its_thunk_array. If required,
+in future this can be changed to use dynamic thunks.
+
+All vulnerable RETs are replaced with a static thunk, they do not use dynamic
+thunks. This is because RETs get their prediction from RSB mostly that does not
+depend on source address. RETs that underflow RSB may benefit from dynamic
+thunks. But, RETs significantly outnumber indirect branches, and any benefit
+from a unique source address could be outweighed by the increased icache
+footprint and iTLB pressure.
+
+Retpoline
+~~~~~~~~~
+Retpoline sequence also mitigates ITS-unsafe indirect branches. For this
+reason, when retpoline is enabled, ITS mitigation only relocates the RETs to
+safe thunks. Unless user requested the RSB-stuffing mitigation.
+
+RSB Stuffing
+~~~~~~~~~~~~
+RSB-stuffing via Call Depth Tracking is a mitigation for Retbleed RSB-underflow
+attacks. And it also mitigates RETs that are vulnerable to ITS.
+
+Mitigation in guests
+^^^^^^^^^^^^^^^^^^^^
+All guests deploy ITS mitigation by default, irrespective of eIBRS enumeration
+and Family/Model of the guest. This is because eIBRS feature could be hidden
+from a guest. One exception to this is when a guest enumerates BHI_DIS_S, which
+indicates that the guest is running on an unaffected host.
+
+To prevent guests from unnecessarily deploying the mitigation on unaffected
+platforms, Intel has defined ITS_NO bit(62) in MSR IA32_ARCH_CAPABILITIES. When
+a guest sees this bit set, it should not enumerate the ITS bug. Note, this bit
+is not set by any hardware, but is **intended for VMMs to synthesize** it for
+guests as per the host's affected status.
+
+Mitigation options
+^^^^^^^^^^^^^^^^^^
+The ITS mitigation can be controlled using the "indirect_target_selection"
+kernel parameter. The available options are:
+
+   ======== ===================================================================
+   on       (default)  Deploy the "Aligned branch/return thunks" mitigation.
+	    If spectre_v2 mitigation enables retpoline, aligned-thunks are only
+	    deployed for the affected RET instructions. Retpoline mitigates
+	    indirect branches.
+
+   off      Disable ITS mitigation.
+
+   vmexit   Equivalent to "=on" if the CPU is affected by guest/host isolation
+	    part of ITS. Otherwise, mitigation is not deployed. This option is
+	    useful when host userspace is not in the threat model, and only
+	    attacks from guest to host are considered.
+
+   stuff    Deploy RSB-fill mitigation when retpoline is also deployed.
+	    Otherwise, deploy the default mitigation. When retpoline mitigation
+	    is enabled, RSB-stuffing via Call-Depth-Tracking also mitigates
+	    ITS.
+
+   force    Force the ITS bug and deploy the default mitigation.
+   ======== ===================================================================
+
+Sysfs reporting
+---------------
+
+The sysfs file showing ITS mitigation status is:
+
+  /sys/devices/system/cpu/vulnerabilities/indirect_target_selection
+
+Note, microcode mitigation status is not reported in this file.
+
+The possible values in this file are:
+
+.. list-table::
+
+   * - Not affected
+     - The processor is not vulnerable.
+   * - Vulnerable
+     - System is vulnerable and no mitigation has been applied.
+   * - Vulnerable, KVM: Not affected
+     - System is vulnerable to intra-mode BTI, but not affected by eIBRS
+       guest/host isolation.
+   * - Mitigation: Aligned branch/return thunks
+     - The mitigation is enabled, affected indirect branches and RETs are
+       relocated to safe thunks.
+   * - Mitigation: Retpolines, Stuffing RSB
+     - The mitigation is enabled using retpoline and RSB stuffing.
+
+References
+----------
+.. [#f1] Microcode repository - https://github.com/intel/Intel-Linux-Processor-Microcode-Data-Files
+
+.. [#f2] Affected Processors list - https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html
+
+.. [#f3] Affected Processors list (machine readable) - https://github.com/intel/Intel-affected-processor-list
diff --git a/Documentation/admin-guide/hw-vuln/rsb.rst b/Documentation/admin-guide/hw-vuln/rsb.rst
new file mode 100644
index 000000000000..21dbf9cf25f8
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/rsb.rst
@@ -0,0 +1,268 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================
+RSB-related mitigations
+=======================
+
+.. warning::
+   Please keep this document up-to-date, otherwise you will be
+   volunteered to update it and convert it to a very long comment in
+   bugs.c!
+
+Since 2018 there have been many Spectre CVEs related to the Return Stack
+Buffer (RSB) (sometimes referred to as the Return Address Stack (RAS) or
+Return Address Predictor (RAP) on AMD).
+
+Information about these CVEs and how to mitigate them is scattered
+amongst a myriad of microarchitecture-specific documents.
+
+This document attempts to consolidate all the relevant information in
+once place and clarify the reasoning behind the current RSB-related
+mitigations.  It's meant to be as concise as possible, focused only on
+the current kernel mitigations: what are the RSB-related attack vectors
+and how are they currently being mitigated?
+
+It's *not* meant to describe how the RSB mechanism operates or how the
+exploits work.  More details about those can be found in the references
+below.
+
+Rather, this is basically a glorified comment, but too long to actually
+be one.  So when the next CVE comes along, a kernel developer can
+quickly refer to this as a refresher to see what we're actually doing
+and why.
+
+At a high level, there are two classes of RSB attacks: RSB poisoning
+(Intel and AMD) and RSB underflow (Intel only).  They must each be
+considered individually for each attack vector (and microarchitecture
+where applicable).
+
+----
+
+RSB poisoning (Intel and AMD)
+=============================
+
+SpectreRSB
+~~~~~~~~~~
+
+RSB poisoning is a technique used by SpectreRSB [#spectre-rsb]_ where
+an attacker poisons an RSB entry to cause a victim's return instruction
+to speculate to an attacker-controlled address.  This can happen when
+there are unbalanced CALLs/RETs after a context switch or VMEXIT.
+
+* All attack vectors can potentially be mitigated by flushing out any
+  poisoned RSB entries using an RSB filling sequence
+  [#intel-rsb-filling]_ [#amd-rsb-filling]_ when transitioning between
+  untrusted and trusted domains.  But this has a performance impact and
+  should be avoided whenever possible.
+
+  .. DANGER::
+     **FIXME**: Currently we're flushing 32 entries.  However, some CPU
+     models have more than 32 entries.  The loop count needs to be
+     increased for those.  More detailed information is needed about RSB
+     sizes.
+
+* On context switch, the user->user mitigation requires ensuring the
+  RSB gets filled or cleared whenever IBPB gets written [#cond-ibpb]_
+  during a context switch:
+
+  * AMD:
+	On Zen 4+, IBPB (or SBPB [#amd-sbpb]_ if used) clears the RSB.
+	This is indicated by IBPB_RET in CPUID [#amd-ibpb-rsb]_.
+
+	On Zen < 4, the RSB filling sequence [#amd-rsb-filling]_ must be
+	always be done in addition to IBPB [#amd-ibpb-no-rsb]_.  This is
+	indicated by X86_BUG_IBPB_NO_RET.
+
+  * Intel:
+	IBPB always clears the RSB:
+
+	"Software that executed before the IBPB command cannot control
+	the predicted targets of indirect branches executed after the
+	command on the same logical processor. The term indirect branch
+	in this context includes near return instructions, so these
+	predicted targets may come from the RSB." [#intel-ibpb-rsb]_
+
+* On context switch, user->kernel attacks are prevented by SMEP.  User
+  space can only insert user space addresses into the RSB.  Even
+  non-canonical addresses can't be inserted due to the page gap at the
+  end of the user canonical address space reserved by TASK_SIZE_MAX.
+  A SMEP #PF at instruction fetch prevents the kernel from speculatively
+  executing user space.
+
+  * AMD:
+	"Finally, branches that are predicted as 'ret' instructions get
+	their predicted targets from the Return Address Predictor (RAP).
+	AMD recommends software use a RAP stuffing sequence (mitigation
+	V2-3 in [2]) and/or Supervisor Mode Execution Protection (SMEP)
+	to ensure that the addresses in the RAP are safe for
+	speculation. Collectively, we refer to these mitigations as "RAP
+	Protection"." [#amd-smep-rsb]_
+
+  * Intel:
+	"On processors with enhanced IBRS, an RSB overwrite sequence may
+	not suffice to prevent the predicted target of a near return
+	from using an RSB entry created in a less privileged predictor
+	mode.  Software can prevent this by enabling SMEP (for
+	transitions from user mode to supervisor mode) and by having
+	IA32_SPEC_CTRL.IBRS set during VM exits." [#intel-smep-rsb]_
+
+* On VMEXIT, guest->host attacks are mitigated by eIBRS (and PBRSB
+  mitigation if needed):
+
+  * AMD:
+	"When Automatic IBRS is enabled, the internal return address
+	stack used for return address predictions is cleared on VMEXIT."
+	[#amd-eibrs-vmexit]_
+
+  * Intel:
+	"On processors with enhanced IBRS, an RSB overwrite sequence may
+	not suffice to prevent the predicted target of a near return
+	from using an RSB entry created in a less privileged predictor
+	mode.  Software can prevent this by enabling SMEP (for
+	transitions from user mode to supervisor mode) and by having
+	IA32_SPEC_CTRL.IBRS set during VM exits. Processors with
+	enhanced IBRS still support the usage model where IBRS is set
+	only in the OS/VMM for OSes that enable SMEP. To do this, such
+	processors will ensure that guest behavior cannot control the
+	RSB after a VM exit once IBRS is set, even if IBRS was not set
+	at the time of the VM exit." [#intel-eibrs-vmexit]_
+
+    Note that some Intel CPUs are susceptible to Post-barrier Return
+    Stack Buffer Predictions (PBRSB) [#intel-pbrsb]_, where the last
+    CALL from the guest can be used to predict the first unbalanced RET.
+    In this case the PBRSB mitigation is needed in addition to eIBRS.
+
+AMD RETBleed / SRSO / Branch Type Confusion
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+On AMD, poisoned RSB entries can also be created by the AMD RETBleed
+variant [#retbleed-paper]_ [#amd-btc]_ or by Speculative Return Stack
+Overflow [#amd-srso]_ (Inception [#inception-paper]_).  The kernel
+protects itself by replacing every RET in the kernel with a branch to a
+single safe RET.
+
+----
+
+RSB underflow (Intel only)
+==========================
+
+RSB Alternate (RSBA) ("Intel Retbleed")
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Some Intel Skylake-generation CPUs are susceptible to the Intel variant
+of RETBleed [#retbleed-paper]_ (Return Stack Buffer Underflow
+[#intel-rsbu]_).  If a RET is executed when the RSB buffer is empty due
+to mismatched CALLs/RETs or returning from a deep call stack, the branch
+predictor can fall back to using the Branch Target Buffer (BTB).  If a
+user forces a BTB collision then the RET can speculatively branch to a
+user-controlled address.
+
+* Note that RSB filling doesn't fully mitigate this issue.  If there
+  are enough unbalanced RETs, the RSB may still underflow and fall back
+  to using a poisoned BTB entry.
+
+* On context switch, user->user underflow attacks are mitigated by the
+  conditional IBPB [#cond-ibpb]_ on context switch which effectively
+  clears the BTB:
+
+  * "The indirect branch predictor barrier (IBPB) is an indirect branch
+    control mechanism that establishes a barrier, preventing software
+    that executed before the barrier from controlling the predicted
+    targets of indirect branches executed after the barrier on the same
+    logical processor." [#intel-ibpb-btb]_
+
+* On context switch and VMEXIT, user->kernel and guest->host RSB
+  underflows are mitigated by IBRS or eIBRS:
+
+  * "Enabling IBRS (including enhanced IBRS) will mitigate the "RSBU"
+    attack demonstrated by the researchers. As previously documented,
+    Intel recommends the use of enhanced IBRS, where supported. This
+    includes any processor that enumerates RRSBA but not RRSBA_DIS_S."
+    [#intel-rsbu]_
+
+  However, note that eIBRS and IBRS do not mitigate intra-mode attacks.
+  Like RRSBA below, this is mitigated by clearing the BHB on kernel
+  entry.
+
+  As an alternative to classic IBRS, call depth tracking (combined with
+  retpolines) can be used to track kernel returns and fill the RSB when
+  it gets close to being empty.
+
+Restricted RSB Alternate (RRSBA)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Some newer Intel CPUs have Restricted RSB Alternate (RRSBA) behavior,
+which, similar to RSBA described above, also falls back to using the BTB
+on RSB underflow.  The only difference is that the predicted targets are
+restricted to the current domain when eIBRS is enabled:
+
+* "Restricted RSB Alternate (RRSBA) behavior allows alternate branch
+  predictors to be used by near RET instructions when the RSB is
+  empty.  When eIBRS is enabled, the predicted targets of these
+  alternate predictors are restricted to those belonging to the
+  indirect branch predictor entries of the current prediction domain.
+  [#intel-eibrs-rrsba]_
+
+When a CPU with RRSBA is vulnerable to Branch History Injection
+[#bhi-paper]_ [#intel-bhi]_, an RSB underflow could be used for an
+intra-mode BTI attack.  This is mitigated by clearing the BHB on
+kernel entry.
+
+However if the kernel uses retpolines instead of eIBRS, it needs to
+disable RRSBA:
+
+* "Where software is using retpoline as a mitigation for BHI or
+  intra-mode BTI, and the processor both enumerates RRSBA and
+  enumerates RRSBA_DIS controls, it should disable this behavior."
+  [#intel-retpoline-rrsba]_
+
+----
+
+References
+==========
+
+.. [#spectre-rsb] `Spectre Returns! Speculation Attacks using the Return Stack Buffer <https://arxiv.org/pdf/1807.07940.pdf>`_
+
+.. [#intel-rsb-filling] "Empty RSB Mitigation on Skylake-generation" in `Retpoline: A Branch Target Injection Mitigation <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/retpoline-branch-target-injection-mitigation.html#inpage-nav-5-1>`_
+
+.. [#amd-rsb-filling] "Mitigation V2-3" in `Software Techniques for Managing Speculation <https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/software-techniques-for-managing-speculation.pdf>`_
+
+.. [#cond-ibpb] Whether IBPB is written depends on whether the prev and/or next task is protected from Spectre attacks.  It typically requires opting in per task or system-wide.  For more details see the documentation for the ``spectre_v2_user`` cmdline option in Documentation/admin-guide/kernel-parameters.txt.
+
+.. [#amd-sbpb] IBPB without flushing of branch type predictions.  Only exists for AMD.
+
+.. [#amd-ibpb-rsb] "Function 8000_0008h -- Processor Capacity Parameters and Extended Feature Identification" in `AMD64 Architecture Programmer's Manual Volume 3: General-Purpose and System Instructions <https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/24594.pdf>`_.  SBPB behaves the same way according to `this email <https://lore.kernel.org/5175b163a3736ca5fd01cedf406735636c99a>`_.
+
+.. [#amd-ibpb-no-rsb] `Spectre Attacks: Exploiting Speculative Execution <https://comsec.ethz.ch/wp-content/files/ibpb_sp25.pdf>`_
+
+.. [#intel-ibpb-rsb] "Introduction" in `Post-barrier Return Stack Buffer Predictions / CVE-2022-26373 / INTEL-SA-00706 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/advisory-guidance/post-barrier-return-stack-buffer-predictions.html>`_
+
+.. [#amd-smep-rsb] "Existing Mitigations" in `Technical Guidance for Mitigating Branch Type Confusion <https://www.amd.com/content/dam/amd/en/documents/resources/technical-guidance-for-mitigating-branch-type-confusion.pdf>`_
+
+.. [#intel-smep-rsb] "Enhanced IBRS" in `Indirect Branch Restricted Speculation <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/indirect-branch-restricted-speculation.html>`_
+
+.. [#amd-eibrs-vmexit] "Extended Feature Enable Register (EFER)" in `AMD64 Architecture Programmer's Manual Volume 2: System Programming <https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/24593.pdf>`_
+
+.. [#intel-eibrs-vmexit] "Enhanced IBRS" in `Indirect Branch Restricted Speculation <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/indirect-branch-restricted-speculation.html>`_
+
+.. [#intel-pbrsb] `Post-barrier Return Stack Buffer Predictions / CVE-2022-26373 / INTEL-SA-00706 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/advisory-guidance/post-barrier-return-stack-buffer-predictions.html>`_
+
+.. [#retbleed-paper] `RETBleed: Arbitrary Speculative Code Execution with Return Instruction <https://comsec.ethz.ch/wp-content/files/retbleed_sec22.pdf>`_
+
+.. [#amd-btc] `Technical Guidance for Mitigating Branch Type Confusion <https://www.amd.com/content/dam/amd/en/documents/resources/technical-guidance-for-mitigating-branch-type-confusion.pdf>`_
+
+.. [#amd-srso] `Technical Update Regarding Speculative Return Stack Overflow <https://www.amd.com/content/dam/amd/en/documents/corporate/cr/speculative-return-stack-overflow-whitepaper.pdf>`_
+
+.. [#inception-paper] `Inception: Exposing New Attack Surfaces with Training in Transient Execution <https://comsec.ethz.ch/wp-content/files/inception_sec23.pdf>`_
+
+.. [#intel-rsbu] `Return Stack Buffer Underflow / Return Stack Buffer Underflow / CVE-2022-29901, CVE-2022-28693 / INTEL-SA-00702 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/advisory-guidance/return-stack-buffer-underflow.html>`_
+
+.. [#intel-ibpb-btb] `Indirect Branch Predictor Barrier' <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/indirect-branch-predictor-barrier.html>`_
+
+.. [#intel-eibrs-rrsba] "Guidance for RSBU" in `Return Stack Buffer Underflow / Return Stack Buffer Underflow / CVE-2022-29901, CVE-2022-28693 / INTEL-SA-00702 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/advisory-guidance/return-stack-buffer-underflow.html>`_
+
+.. [#bhi-paper] `Branch History Injection: On the Effectiveness of Hardware Mitigations Against Cross-Privilege Spectre-v2 Attacks <http://download.vusec.net/papers/bhi-spectre-bhb_sec22.pdf>`_
+
+.. [#intel-bhi] `Branch History Injection and Intra-mode Branch Target Injection / CVE-2022-0001, CVE-2022-0002 / INTEL-SA-00598 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/branch-history-injection.html>`_
+
+.. [#intel-retpoline-rrsba] "Retpoline" in `Branch History Injection and Intra-mode Branch Target Injection / CVE-2022-0001, CVE-2022-0002 / INTEL-SA-00598 <https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/branch-history-injection.html>`_
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 76e538c77e31..8f75ec177399 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1407,18 +1407,15 @@
 			earlyprintk=serial[,0x...[,baudrate]]
 			earlyprintk=ttySn[,baudrate]
 			earlyprintk=dbgp[debugController#]
+			earlyprintk=mmio32,membase[,{nocfg|baudrate}]
 			earlyprintk=pciserial[,force],bus:device.function[,{nocfg|baudrate}]
 			earlyprintk=xdbc[xhciController#]
 			earlyprintk=bios
-			earlyprintk=mmio,membase[,{nocfg|baudrate}]
 
 			earlyprintk is useful when the kernel crashes before
 			the normal console is initialized. It is not enabled by
 			default because it has some cosmetic problems.
 
-			Only 32-bit memory addresses are supported for "mmio"
-			and "pciserial" devices.
-
 			Use "nocfg" to skip UART configuration, assume
 			BIOS/firmware has configured UART correctly.
 
@@ -2205,6 +2202,23 @@
 			different crypto accelerators. This option can be used
 			to achieve best performance for particular HW.
 
+	indirect_target_selection= [X86,Intel] Mitigation control for Indirect
+			Target Selection(ITS) bug in Intel CPUs. Updated
+			microcode is also required for a fix in IBPB.
+
+			on:     Enable mitigation (default).
+			off:    Disable mitigation.
+			force:	Force the ITS bug and deploy default
+				mitigation.
+			vmexit: Only deploy mitigation if CPU is affected by
+				guest/host isolation part of ITS.
+			stuff:	Deploy RSB-fill mitigation when retpoline is
+				also deployed. Otherwise, deploy the default
+				mitigation.
+
+			For details see:
+			Documentation/admin-guide/hw-vuln/indirect-target-selection.rst
+
 	init=		[KNL]
 			Format: <full_path>
 			Run specified binary instead of /sbin/init as init
@@ -3696,6 +3710,7 @@
 				expose users to several CPU vulnerabilities.
 				Equivalent to: if nokaslr then kpti=0 [ARM64]
 					       gather_data_sampling=off [X86]
+					       indirect_target_selection=off [X86]
 					       kvm.nx_huge_pages=off [X86]
 					       l1tf=off [X86]
 					       mds=off [X86]
diff --git a/Documentation/admin-guide/xfs.rst b/Documentation/admin-guide/xfs.rst
index b67772cf36d6..5becb441c3cb 100644
--- a/Documentation/admin-guide/xfs.rst
+++ b/Documentation/admin-guide/xfs.rst
@@ -124,6 +124,14 @@ When mounting an XFS filesystem, the following options are accepted.
 	controls the size of each buffer and so is also relevant to
 	this case.
 
+  lifetime (default) or nolifetime
+	Enable data placement based on write life time hints provided
+	by the user. This turns on co-allocation of data of similar
+	life times when statistically favorable to reduce garbage
+	collection cost.
+
+	These options are only available for zoned rt file systems.
+
   logbsize=value
 	Set the size of each in-memory log buffer.  The size may be
 	specified in bytes, or in kilobytes with a "k" suffix.
@@ -143,6 +151,14 @@ When mounting an XFS filesystem, the following options are accepted.
 	optional, and the log section can be separate from the data
 	section or contained within it.
 
+  max_open_zones=value
+	Specify the max number of zones to keep open for writing on a
+	zoned rt device. Many open zones aids file data separation
+	but may impact performance on HDDs.
+
+	If ``max_open_zones`` is not specified, the value is determined
+	by the capabilities and the size of the zoned rt device.
+
   noalign
 	Data allocations will not be aligned at stripe unit
 	boundaries. This is only relevant to filesystems created
@@ -542,3 +558,24 @@ The interesting knobs for XFS workqueues are as follows:
   nice           Relative priority of scheduling the threads.  These are the
                  same nice levels that can be applied to userspace processes.
 ============     ===========
+
+Zoned Filesystems
+=================
+
+For zoned file systems, the following attributes are exposed in:
+
+  /sys/fs/xfs/<dev>/zoned/
+
+  max_open_zones		(Min:  1  Default:  Varies  Max:  UINTMAX)
+	This read-only attribute exposes the maximum number of open zones
+	available for data placement. The value is determined at mount time and
+	is limited by the capabilities of the backing zoned device, file system
+	size and the max_open_zones mount option.
+
+  zonegc_low_space		(Min:  0  Default:  0  Max:  100)
+	Define a percentage for how much of the unused space that GC should keep
+	available for writing. A high value will reclaim more of the space
+	occupied by unused blocks, creating a larger buffer against write
+	bursts at the cost of increased write amplification.  Regardless
+	of this value, garbage collection will always aim to free a minimum
+	amount of blocks to keep max_open_zones open for data placement purposes.
diff --git a/Documentation/arch/openrisc/openrisc_port.rst b/Documentation/arch/openrisc/openrisc_port.rst
index 1565b9546e38..a8f307a3b499 100644
--- a/Documentation/arch/openrisc/openrisc_port.rst
+++ b/Documentation/arch/openrisc/openrisc_port.rst
@@ -7,10 +7,10 @@ target architecture, specifically, is the 32-bit OpenRISC 1000 family (or1k).
 
 For information about OpenRISC processors and ongoing development:
 
-	=======		=============================
+	=======		==============================
 	website		https://openrisc.io
-	email		openrisc@lists.librecores.org
-	=======		=============================
+	email		linux-openrisc@vger.kernel.org
+	=======		==============================
 
 ---------------------------------------------------------------------
 
@@ -27,11 +27,11 @@ Toolchain binaries can be obtained from openrisc.io or our github releases page.
 Instructions for building the different toolchains can be found on openrisc.io
 or Stafford's toolchain build and release scripts.
 
-	==========	=================================================
-	binaries	https://github.com/openrisc/or1k-gcc/releases
+	==========	==========================================================
+	binaries	https://github.com/stffrdhrn/or1k-toolchain-build/releases
 	toolchains	https://openrisc.io/software
 	building	https://github.com/stffrdhrn/or1k-toolchain-build
-	==========	=================================================
+	==========	==========================================================
 
 2) Building
 
diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 53607d962653..f60bf5991755 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -51,7 +51,7 @@ The following keys are defined:
 * :c:macro:`RISCV_HWPROBE_KEY_MARCHID`: Contains the value of ``marchid``, as
   defined by the RISC-V privileged architecture specification.
 
-* :c:macro:`RISCV_HWPROBE_KEY_MIMPLID`: Contains the value of ``mimplid``, as
+* :c:macro:`RISCV_HWPROBE_KEY_MIMPID`: Contains the value of ``mimpid``, as
   defined by the RISC-V privileged architecture specification.
 
 * :c:macro:`RISCV_HWPROBE_KEY_BASE_BEHAVIOR`: A bitmask containing the base
diff --git a/Documentation/arch/x86/cpuinfo.rst b/Documentation/arch/x86/cpuinfo.rst
index 6ef426a52cdc..f80e2a558d2a 100644
--- a/Documentation/arch/x86/cpuinfo.rst
+++ b/Documentation/arch/x86/cpuinfo.rst
@@ -79,8 +79,9 @@ feature flags.
 How are feature flags created?
 ==============================
 
-a: Feature flags can be derived from the contents of CPUID leaves.
-------------------------------------------------------------------
+Feature flags can be derived from the contents of CPUID leaves
+--------------------------------------------------------------
+
 These feature definitions are organized mirroring the layout of CPUID
 leaves and grouped in words with offsets as mapped in enum cpuid_leafs
 in cpufeatures.h (see arch/x86/include/asm/cpufeatures.h for details).
@@ -89,8 +90,9 @@ cpufeatures.h, and if it is detected at run time, the flags will be
 displayed accordingly in /proc/cpuinfo. For example, the flag "avx2"
 comes from X86_FEATURE_AVX2 in cpufeatures.h.
 
-b: Flags can be from scattered CPUID-based features.
-----------------------------------------------------
+Flags can be from scattered CPUID-based features
+------------------------------------------------
+
 Hardware features enumerated in sparsely populated CPUID leaves get
 software-defined values. Still, CPUID needs to be queried to determine
 if a given feature is present. This is done in init_scattered_cpuid_features().
@@ -104,8 +106,9 @@ has only one feature and would waste 31 bits of space in the x86_capability[]
 array. Since there is a struct cpuinfo_x86 for each possible CPU, the wasted
 memory is not trivial.
 
-c: Flags can be created synthetically under certain conditions for hardware features.
--------------------------------------------------------------------------------------
+Flags can be created synthetically under certain conditions for hardware features
+---------------------------------------------------------------------------------
+
 Examples of conditions include whether certain features are present in
 MSR_IA32_CORE_CAPS or specific CPU models are identified. If the needed
 conditions are met, the features are enabled by the set_cpu_cap or
@@ -114,8 +117,8 @@ the feature X86_FEATURE_SPLIT_LOCK_DETECT will be enabled and
 "split_lock_detect" will be displayed. The flag "ring3mwait" will be
 displayed only when running on INTEL_XEON_PHI_[KNL|KNM] processors.
 
-d: Flags can represent purely software features.
-------------------------------------------------
+Flags can represent purely software features
+--------------------------------------------
 These flags do not represent hardware features. Instead, they represent a
 software feature implemented in the kernel. For example, Kernel Page Table
 Isolation is purely software feature and its feature flag X86_FEATURE_PTI is
@@ -130,14 +133,18 @@ x86_cap/bug_flags[] arrays in kernel/cpu/capflags.c. The names in the
 resulting x86_cap/bug_flags[] are used to populate /proc/cpuinfo. The naming
 of flags in the x86_cap/bug_flags[] are as follows:
 
-a: The name of the flag is from the string in X86_FEATURE_<name> by default.
-----------------------------------------------------------------------------
-By default, the flag <name> in /proc/cpuinfo is extracted from the respective
-X86_FEATURE_<name> in cpufeatures.h. For example, the flag "avx2" is from
-X86_FEATURE_AVX2.
+Flags do not appear by default in /proc/cpuinfo
+-----------------------------------------------
+
+Feature flags are omitted by default from /proc/cpuinfo as it does not make
+sense for the feature to be exposed to userspace in most cases. For example,
+X86_FEATURE_ALWAYS is defined in cpufeatures.h but that flag is an internal
+kernel feature used in the alternative runtime patching functionality. So the
+flag does not appear in /proc/cpuinfo.
+
+Specify a flag name if absolutely needed
+----------------------------------------
 
-b: The naming can be overridden.
---------------------------------
 If the comment on the line for the #define X86_FEATURE_* starts with a
 double-quote character (""), the string inside the double-quote characters
 will be the name of the flags. For example, the flag "sse4_1" comes from
@@ -148,36 +155,31 @@ needed. For instance, /proc/cpuinfo is a userspace interface and must remain
 constant. If, for some reason, the naming of X86_FEATURE_<name> changes, one
 shall override the new naming with the name already used in /proc/cpuinfo.
 
-c: The naming override can be "", which means it will not appear in /proc/cpuinfo.
-----------------------------------------------------------------------------------
-The feature shall be omitted from /proc/cpuinfo if it does not make sense for
-the feature to be exposed to userspace. For example, X86_FEATURE_ALWAYS is
-defined in cpufeatures.h but that flag is an internal kernel feature used
-in the alternative runtime patching functionality. So, its name is overridden
-with "". Its flag will not appear in /proc/cpuinfo.
-
 Flags are missing when one or more of these happen
 ==================================================
 
-a: The hardware does not enumerate support for it.
---------------------------------------------------
+The hardware does not enumerate support for it
+----------------------------------------------
+
 For example, when a new kernel is running on old hardware or the feature is
 not enabled by boot firmware. Even if the hardware is new, there might be a
 problem enabling the feature at run time, the flag will not be displayed.
 
-b: The kernel does not know about the flag.
--------------------------------------------
+The kernel does not know about the flag
+---------------------------------------
+
 For example, when an old kernel is running on new hardware.
 
-c: The kernel disabled support for it at compile-time.
-------------------------------------------------------
+The kernel disabled support for it at compile-time
+--------------------------------------------------
+
 For example, if 5-level-paging is not enabled when building (i.e.,
 CONFIG_X86_5LEVEL is not selected) the flag "la57" will not show up [#f1]_.
 Even though the feature will still be detected via CPUID, the kernel disables
 it by clearing via setup_clear_cpu_cap(X86_FEATURE_LA57).
 
-d: The feature is disabled at boot-time.
-----------------------------------------
+The feature is disabled at boot-time
+------------------------------------
 A feature can be disabled either using a command-line parameter or because
 it failed to be enabled. The command-line parameter clearcpuid= can be used
 to disable features using the feature number as defined in
@@ -190,8 +192,9 @@ disable specific features. The list of parameters includes, but is not limited
 to, nofsgsbase, nosgx, noxsave, etc. 5-level paging can also be disabled using
 "no5lvl".
 
-e: The feature was known to be non-functional.
-----------------------------------------------
+The feature was known to be non-functional
+------------------------------------------
+
 The feature was known to be non-functional because a dependency was
 missing at runtime. For example, AVX flags will not show up if XSAVE feature
 is disabled since they depend on XSAVE feature. Another example would be broken
diff --git a/Documentation/bpf/bpf_devel_QA.rst b/Documentation/bpf/bpf_devel_QA.rst
index de27e1620821..0acb4c9b8d90 100644
--- a/Documentation/bpf/bpf_devel_QA.rst
+++ b/Documentation/bpf/bpf_devel_QA.rst
@@ -382,6 +382,14 @@ In case of new BPF instructions, once the changes have been accepted
 into the Linux kernel, please implement support into LLVM's BPF back
 end. See LLVM_ section below for further information.
 
+Q: What "BPF_INTERNAL" symbol namespace is for?
+-----------------------------------------------
+A: Symbols exported as BPF_INTERNAL can only be used by BPF infrastructure
+like preload kernel modules with light skeleton. Most symbols outside
+of BPF_INTERNAL are not expected to be used by code outside of BPF either.
+Symbols may lack the designation because they predate the namespaces,
+or due to an oversight.
+
 Stable submission
 =================
 
diff --git a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
index 6ad78429dc74..c92341888a28 100644
--- a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
+++ b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
@@ -7,7 +7,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Ceva AHCI SATA Controller
 
 maintainers:
-  - Mubin Sayyed <mubin.sayyed@amd.com>
   - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 description: |
diff --git a/Documentation/devicetree/bindings/display/bridge/nwl-dsi.yaml b/Documentation/devicetree/bindings/display/bridge/nwl-dsi.yaml
index 350fb8f400f0..5952e6448ed4 100644
--- a/Documentation/devicetree/bindings/display/bridge/nwl-dsi.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/nwl-dsi.yaml
@@ -111,11 +111,27 @@ properties:
         unevaluatedProperties: false
 
       port@1:
-        $ref: /schemas/graph.yaml#/properties/port
+        $ref: /schemas/graph.yaml#/$defs/port-base
+        unevaluatedProperties: false
         description:
           DSI output port node to the panel or the next bridge
           in the chain
 
+        properties:
+          endpoint:
+            $ref: /schemas/media/video-interfaces.yaml#
+            unevaluatedProperties: false
+
+            properties:
+              data-lanes:
+                description: array of physical DSI data lane indexes.
+                minItems: 1
+                items:
+                  - const: 1
+                  - const: 2
+                  - const: 3
+                  - const: 4
+
     required:
       - port@0
       - port@1
diff --git a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
index bb93baa88879..e13e9d6dd148 100644
--- a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
+++ b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
@@ -12,7 +12,6 @@ description:
   PS_MODE). Every pin can be configured as input/output.
 
 maintainers:
-  - Mubin Sayyed <mubin.sayyed@amd.com>
   - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
diff --git a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
index 517a4ac1bea3..e365413732e7 100644
--- a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
+++ b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Mediatek's Keypad Controller
 
 maintainers:
-  - Mattijs Korpershoek <mkorpershoek@baylibre.com>
+  - Mattijs Korpershoek <mkorpershoek@kernel.org>
 
 allOf:
   - $ref: /schemas/input/matrix-keymap.yaml#
diff --git a/Documentation/devicetree/bindings/interrupt-controller/fsl,irqsteer.yaml b/Documentation/devicetree/bindings/interrupt-controller/fsl,irqsteer.yaml
index 6076ddf56bb5..c49688be1058 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/fsl,irqsteer.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/fsl,irqsteer.yaml
@@ -19,6 +19,7 @@ properties:
               - fsl,imx8mp-irqsteer
               - fsl,imx8qm-irqsteer
               - fsl,imx8qxp-irqsteer
+              - fsl,imx94-irqsteer
           - const: fsl,imx-irqsteer
 
   reg:
diff --git a/Documentation/devicetree/bindings/net/aeonsemi,as21xxx.yaml b/Documentation/devicetree/bindings/net/aeonsemi,as21xxx.yaml
new file mode 100644
index 000000000000..69eb29dc4d7b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/aeonsemi,as21xxx.yaml
@@ -0,0 +1,122 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/aeonsemi,as21xxx.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Aeonsemi AS21XXX Ethernet PHY
+
+maintainers:
+  - Christian Marangi <ansuelsmth@gmail.com>
+
+description: |
+  Aeonsemi AS21xxx Ethernet PHYs requires a firmware to be loaded to actually
+  work. The same firmware is compatible with various PHYs of the same family.
+
+  A PHY with not firmware loaded will be exposed on the MDIO bus with ID
+  0x7500 0x7500 or 0x7500 0x9410 on C45 registers.
+
+  This can be done and is implemented by OEM in 2 different way:
+    - Attached SPI flash directly to the PHY with the firmware. The PHY
+      will self load the firmware in the presence of this configuration.
+    - Manually provided firmware loaded from a file in the filesystem.
+
+  Each PHY can support up to 5 LEDs.
+
+  AS2xxx PHY Name logic:
+
+  AS21x1xxB1
+      ^ ^^
+      | |J: Supports SyncE/PTP
+      | |P: No SyncE/PTP support
+      | 1: Supports 2nd Serdes
+      | 2: Not 2nd Serdes support
+      0: 10G, 5G, 2.5G
+      5: 5G, 2.5G
+      2: 2.5G
+
+allOf:
+  - $ref: ethernet-phy.yaml#
+
+select:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - ethernet-phy-id7500.9410
+          - ethernet-phy-id7500.9402
+          - ethernet-phy-id7500.9412
+          - ethernet-phy-id7500.9422
+          - ethernet-phy-id7500.9432
+          - ethernet-phy-id7500.9442
+          - ethernet-phy-id7500.9452
+          - ethernet-phy-id7500.9462
+          - ethernet-phy-id7500.9472
+          - ethernet-phy-id7500.9482
+          - ethernet-phy-id7500.9492
+  required:
+    - compatible
+
+properties:
+  reg:
+    maxItems: 1
+
+  firmware-name:
+    description: specify the name of PHY firmware to load
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: ethernet-phy-id7500.9410
+then:
+  required:
+    - firmware-name
+else:
+  properties:
+    firmware-name: false
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/leds/common.h>
+
+    mdio {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        ethernet-phy@1f {
+            compatible = "ethernet-phy-id7500.9410",
+                         "ethernet-phy-ieee802.3-c45";
+
+            reg = <31>;
+            firmware-name = "as21x1x_fw.bin";
+
+            leds {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                led@0 {
+                    reg = <0>;
+                    color = <LED_COLOR_ID_GREEN>;
+                    function = LED_FUNCTION_LAN;
+                    function-enumerator = <0>;
+                    default-state = "keep";
+                };
+
+                led@1 {
+                    reg = <1>;
+                    color = <LED_COLOR_ID_GREEN>;
+                    function = LED_FUNCTION_LAN;
+                    function-enumerator = <1>;
+                    default-state = "keep";
+                };
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml b/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml
index 0fdd11265417..6d22131ac2f9 100644
--- a/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml
+++ b/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml
@@ -57,6 +57,16 @@ properties:
       - const: hsi-mac
       - const: xfp-mac
 
+  memory-region:
+    items:
+      - description: QDMA0 buffer memory
+      - description: QDMA1 buffer memory
+
+  memory-region-names:
+    items:
+      - const: qdma0-buf
+      - const: qdma1-buf
+
   "#address-cells":
     const: 1
 
@@ -140,6 +150,9 @@ examples:
                      <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
                      <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
 
+        memory-region = <&qdma0_buf>, <&qdma1_buf>;
+        memory-region-names = "qdma0-buf", "qdma1-buf";
+
         airoha,npu = <&npu>;
 
         #address-cells = <1>;
diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
index 7fe0352dff0f..7b6a2fde8175 100644
--- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
+++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
@@ -23,6 +23,7 @@ properties:
               - allwinner,sun20i-d1-emac
               - allwinner,sun50i-h6-emac
               - allwinner,sun50i-h616-emac0
+              - allwinner,sun55i-a523-emac0
           - const: allwinner,sun50i-a64-emac
 
   reg:
diff --git a/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml b/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml
index d02e9dd847ef..3ab60c70286f 100644
--- a/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml
+++ b/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml
@@ -48,6 +48,18 @@ properties:
     description:
       The GPIO number of the NXP chipset used for BT_WAKE_IN.
 
+  interrupts:
+    maxItems: 1
+    description:
+      Host wakeup by falling edge interrupt on this pin which is
+      connected to BT_WAKE_OUT pin of the NXP chipset.
+
+  interrupt-names:
+    items:
+      - const: wakeup
+
+  wakeup-source: true
+
   nxp,wakeout-pin:
     $ref: /schemas/types.yaml#/definitions/uint8
     description:
@@ -61,6 +73,7 @@ unevaluatedProperties: false
 examples:
   - |
     #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
     serial {
         bluetooth {
             compatible = "nxp,88w8987-bt";
@@ -70,5 +83,9 @@ examples:
             nxp,wakein-pin = /bits/ 8 <18>;
             nxp,wakeout-pin = /bits/ 8 <19>;
             local-bd-address = [66 55 44 33 22 11];
+            interrupt-parent = <&gpio>;
+            interrupts = <8 IRQ_TYPE_EDGE_FALLING>;
+            interrupt-names = "wakeup";
+            wakeup-source;
         };
     };
diff --git a/Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml b/Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml
index 660e2ca42daf..a3db6d594c8c 100644
--- a/Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml
+++ b/Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml
@@ -4,7 +4,7 @@
 $id: http://devicetree.org/schemas/net/brcm,asp-v2.0.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Broadcom ASP 2.0 Ethernet controller
+title: Broadcom ASP Ethernet controller
 
 maintainers:
   - Justin Chen <justin.chen@broadcom.com>
@@ -17,16 +17,16 @@ properties:
     oneOf:
       - items:
           - enum:
+              - brcm,bcm74110-asp
+          - const: brcm,asp-v3.0
+      - items:
+          - enum:
               - brcm,bcm74165b0-asp
           - const: brcm,asp-v2.2
       - items:
           - enum:
               - brcm,bcm74165-asp
           - const: brcm,asp-v2.1
-      - items:
-          - enum:
-              - brcm,bcm72165-asp
-          - const: brcm,asp-v2.0
 
   "#address-cells":
     const: 1
@@ -39,11 +39,9 @@ properties:
   ranges: true
 
   interrupts:
-    minItems: 1
     items:
       - description: RX/TX interrupt
-      - description: Port 0 Wake-on-LAN
-      - description: Port 1 Wake-on-LAN
+      - description: Wake-on-LAN interrupt
 
   clocks:
     maxItems: 1
@@ -106,16 +104,17 @@ examples:
     #include <dt-bindings/interrupt-controller/arm-gic.h>
 
     ethernet@9c00000 {
-        compatible = "brcm,bcm72165-asp", "brcm,asp-v2.0";
+        compatible = "brcm,bcm74165-asp", "brcm,asp-v2.1";
         reg = <0x9c00000 0x1fff14>;
-        interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>;
+        interrupts-extended = <&intc GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>,
+                              <&aon_pm_l2_intc 14>;
         ranges = <0x0 0x9c00000 0x1fff14>;
         clocks = <&scmi 14>;
         #address-cells = <1>;
         #size-cells = <1>;
 
         mdio@c614 {
-            compatible = "brcm,asp-v2.0-mdio";
+            compatible = "brcm,asp-v2.1-mdio";
             reg = <0xc614 0x8>;
             reg-names = "mdio";
             #address-cells = <1>;
@@ -127,7 +126,7 @@ examples:
        };
 
         mdio@ce14 {
-            compatible = "brcm,asp-v2.0-mdio";
+            compatible = "brcm,asp-v2.1-mdio";
             reg = <0xce14 0x8>;
             reg-names = "mdio";
             #address-cells = <1>;
diff --git a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml
index 63bee5b542f5..43516dd357b8 100644
--- a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml
+++ b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml
@@ -22,9 +22,9 @@ properties:
       - brcm,genet-mdio-v3
       - brcm,genet-mdio-v4
       - brcm,genet-mdio-v5
-      - brcm,asp-v2.0-mdio
       - brcm,asp-v2.1-mdio
       - brcm,asp-v2.2-mdio
+      - brcm,asp-v3.0-mdio
       - brcm,unimac-mdio
       - brcm,bcm6846-mdio
 
diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml b/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml
index e0ec53bc10c6..1525a50ded47 100644
--- a/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml
+++ b/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/can/microchip,mcp2510.yaml#
+$id: http://devicetree.org/schemas/net/can/microchip,mcp2510.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Microchip MCP251X stand-alone CAN controller
diff --git a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml
index f6884f6e59e7..f4ac21c68427 100644
--- a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml
+++ b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml
@@ -42,19 +42,80 @@ properties:
               - renesas,r9a07g054-canfd    # RZ/V2L
           - const: renesas,rzg2l-canfd     # RZ/G2L family
 
+      - const: renesas,r9a09g047-canfd     # RZ/G3E
+
   reg:
     maxItems: 1
 
-  interrupts: true
+  interrupts:
+    oneOf:
+      - items:
+          - description: Channel interrupt
+          - description: Global interrupt
+      - items:
+          - description: CAN global error interrupt
+          - description: CAN receive FIFO interrupt
+          - description: CAN0 error interrupt
+          - description: CAN0 transmit interrupt
+          - description: CAN0 transmit/receive FIFO receive completion interrupt
+          - description: CAN1 error interrupt
+          - description: CAN1 transmit interrupt
+          - description: CAN1 transmit/receive FIFO receive completion interrupt
+          - description: CAN2 error interrupt
+          - description: CAN2 transmit interrupt
+          - description: CAN2 transmit/receive FIFO receive completion interrupt
+          - description: CAN3 error interrupt
+          - description: CAN3 transmit interrupt
+          - description: CAN3 transmit/receive FIFO receive completion interrupt
+          - description: CAN4 error interrupt
+          - description: CAN4 transmit interrupt
+          - description: CAN4 transmit/receive FIFO receive completion interrupt
+          - description: CAN5 error interrupt
+          - description: CAN5 transmit interrupt
+          - description: CAN5 transmit/receive FIFO receive completion interrupt
+        minItems: 8
+
+  interrupt-names:
+    oneOf:
+      - items:
+          - const: ch_int
+          - const: g_int
+      - items:
+          - const: g_err
+          - const: g_recc
+          - const: ch0_err
+          - const: ch0_rec
+          - const: ch0_trx
+          - const: ch1_err
+          - const: ch1_rec
+          - const: ch1_trx
+          - const: ch2_err
+          - const: ch2_rec
+          - const: ch2_trx
+          - const: ch3_err
+          - const: ch3_rec
+          - const: ch3_trx
+          - const: ch4_err
+          - const: ch4_rec
+          - const: ch4_trx
+          - const: ch5_err
+          - const: ch5_rec
+          - const: ch5_trx
+        minItems: 8
 
   clocks:
     maxItems: 3
 
   clock-names:
-    items:
-      - const: fck
-      - const: canfd
-      - const: can_clk
+    oneOf:
+      - items:
+          - const: fck
+          - const: canfd
+          - const: can_clk
+      - items:
+          - const: fck
+          - const: ram_clk
+          - const: can_clk
 
   power-domains:
     maxItems: 1
@@ -117,48 +178,38 @@ allOf:
     then:
       properties:
         interrupts:
-          items:
-            - description: CAN global error interrupt
-            - description: CAN receive FIFO interrupt
-            - description: CAN0 error interrupt
-            - description: CAN0 transmit interrupt
-            - description: CAN0 transmit/receive FIFO receive completion interrupt
-            - description: CAN1 error interrupt
-            - description: CAN1 transmit interrupt
-            - description: CAN1 transmit/receive FIFO receive completion interrupt
+          maxItems: 8
 
         interrupt-names:
-          items:
-            - const: g_err
-            - const: g_recc
-            - const: ch0_err
-            - const: ch0_rec
-            - const: ch0_trx
-            - const: ch1_err
-            - const: ch1_rec
-            - const: ch1_trx
+          maxItems: 8
 
         resets:
+          minItems: 2
           maxItems: 2
 
         reset-names:
-          items:
-            - const: rstp_n
-            - const: rstc_n
+          minItems: 2
+          maxItems: 2
 
       required:
         - reset-names
-    else:
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,rcar-gen3-canfd
+              - renesas,rcar-gen4-canfd
+    then:
       properties:
         interrupts:
-          items:
-            - description: Channel interrupt
-            - description: Global interrupt
+          minItems: 2
+          maxItems: 2
 
         interrupt-names:
-          items:
-            - const: ch_int
-            - const: g_int
+          minItems: 2
+          maxItems: 2
 
         resets:
           maxItems: 1
@@ -167,20 +218,54 @@ allOf:
       properties:
         compatible:
           contains:
+            const: renesas,r9a09g047-canfd
+    then:
+      properties:
+        interrupts:
+          minItems: 20
+
+        interrupt-names:
+          minItems: 20
+
+        resets:
+          minItems: 2
+          maxItems: 2
+
+        reset-names:
+          minItems: 2
+          maxItems: 2
+
+      required:
+        - reset-names
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,rcar-gen3-canfd
+              - renesas,rzg2l-canfd
+    then:
+      patternProperties:
+        "^channel[2-7]$": false
+
+  - if:
+      properties:
+        compatible:
+          contains:
             const: renesas,r8a779h0-canfd
     then:
       patternProperties:
         "^channel[4-7]$": false
-    else:
-      if:
-        not:
-          properties:
-            compatible:
-              contains:
-                const: renesas,rcar-gen4-canfd
-      then:
-        patternProperties:
-          "^channel[2-7]$": false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: renesas,r9a09g047-canfd
+    then:
+      patternProperties:
+        "^channel[6-7]$": false
 
 unevaluatedProperties: false
 
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 45819b235800..7cbf11bbe99c 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -16,30 +16,6 @@ properties:
   label:
     description: Human readable label on a port of a box.
 
-  local-mac-address:
-    description:
-      Specifies the MAC address that was assigned to the network device.
-    $ref: /schemas/types.yaml#/definitions/uint8-array
-    minItems: 6
-    maxItems: 6
-
-  mac-address:
-    description:
-      Specifies the MAC address that was last used by the boot
-      program; should be used in cases where the MAC address assigned
-      to the device by the boot program is different from the
-      local-mac-address property.
-    $ref: /schemas/types.yaml#/definitions/uint8-array
-    minItems: 6
-    maxItems: 6
-
-  max-frame-size:
-    $ref: /schemas/types.yaml#/definitions/uint32
-    description:
-      Maximum transfer unit (IEEE defined MTU), rather than the
-      maximum frame size (there\'s contradiction in the Devicetree
-      Specification).
-
   max-speed:
     $ref: /schemas/types.yaml#/definitions/uint32
     description:
@@ -74,19 +50,17 @@ properties:
       - rev-rmii
       - moca
 
-      # RX and TX delays are added by the MAC when required
+      # RX and TX delays are provided by the PCB. See below
       - rgmii
 
-      # RGMII with internal RX and TX delays provided by the PHY,
-      # the MAC should not add the RX or TX delays in this case
+      # RX and TX delays are not provided by the PCB. This is the most
+      # frequent case. See below
       - rgmii-id
 
-      # RGMII with internal RX delay provided by the PHY, the MAC
-      # should not add an RX delay in this case
+      # TX delay is provided by the PCB. See below
       - rgmii-rxid
 
-      # RGMII with internal TX delay provided by the PHY, the MAC
-      # should not add an TX delay in this case
+      # RX delay is provided by the PCB. See below
       - rgmii-txid
       - rtbi
       - smii
@@ -197,7 +171,7 @@ properties:
             description:
               Link speed.
             $ref: /schemas/types.yaml#/definitions/uint32
-            enum: [10, 100, 1000, 2500, 10000]
+            enum: [10, 100, 1000, 2500, 5000, 10000]
 
           full-duplex:
             $ref: /schemas/types.yaml#/definitions/flag
@@ -262,6 +236,7 @@ dependencies:
   pcs-handle-names: [pcs-handle]
 
 allOf:
+  - $ref: /schemas/net/network-class.yaml#
   - if:
       properties:
         phy-mode:
@@ -286,4 +261,89 @@ allOf:
 
 additionalProperties: true
 
+# Informative
+# ===========
+#
+# 'phy-modes' & 'phy-connection-type' properties 'rgmii', 'rgmii-id',
+# 'rgmii-rxid', and 'rgmii-txid' are frequently used wrongly by
+# developers. This informative section clarifies their usage.
+#
+# The RGMII specification requires a 2ns delay between the data and
+# clock signals on the RGMII bus. How this delay is implemented is not
+# specified.
+#
+# One option is to make the clock traces on the PCB longer than the
+# data traces. A sufficiently difference in length can provide the 2ns
+# delay. If both the RX and TX delays are implemented in this manner,
+# 'rgmii' should be used, so indicating the PCB adds the delays.
+#
+# If the PCB does not add these delays via extra long traces,
+# 'rgmii-id' should be used. Here, 'id' refers to 'internal delay',
+# where either the MAC or PHY adds the delay.
+#
+# If only one of the two delays are implemented via extra long clock
+# lines, either 'rgmii-rxid' or 'rgmii-txid' should be used,
+# indicating the MAC or PHY should implement one of the delays
+# internally, while the PCB implements the other delay.
+#
+# Device Tree describes hardware, and in this case, it describes the
+# PCB between the MAC and the PHY, if the PCB implements delays or
+# not.
+#
+# In practice, very few PCBs make use of extra long clock lines. Hence
+# any RGMII phy mode other than 'rgmii-id' is probably wrong, and is
+# unlikely to be accepted during review without details provided in
+# the commit description and comments in the .dts file.
+#
+# When the PCB does not implement the delays, the MAC or PHY must.  As
+# such, this is software configuration, and so not described in Device
+# Tree.
+#
+# The following describes how Linux implements the configuration of
+# the MAC and PHY to add these delays when the PCB does not. As stated
+# above, developers often get this wrong, and the aim of this section
+# is reduce the frequency of these errors by Linux developers. Other
+# users of the Device Tree may implement it differently, and still be
+# consistent with both the normative and informative description
+# above.
+#
+# By default in Linux, when using phylib/phylink, the MAC is expected
+# to read the 'phy-mode' from Device Tree, not implement any delays,
+# and pass the value to the PHY. The PHY will then implement delays as
+# specified by the 'phy-mode'. The PHY should always be reconfigured
+# to implement the needed delays, replacing any setting performed by
+# strapping or the bootloader, etc.
+#
+# Experience to date is that all PHYs which implement RGMII also
+# implement the ability to add or not add the needed delays. Hence
+# this default is expected to work in all cases. Ignoring this default
+# is likely to be questioned by Reviews, and require a strong argument
+# to be accepted.
+#
+# There are a small number of cases where the MAC has hard coded
+# delays which cannot be disabled. The 'phy-mode' only describes the
+# PCB.  The inability to disable the delays in the MAC does not change
+# the meaning of 'phy-mode'. It does however mean that a 'phy-mode' of
+# 'rgmii' is now invalid, it cannot be supported, since both the PCB
+# and the MAC and PHY adding delays cannot result in a functional
+# link. Thus the MAC should report a fatal error for any modes which
+# cannot be supported. When the MAC implements the delay, it must
+# ensure that the PHY does not also implement the same delay. So it
+# must modify the phy-mode it passes to the PHY, removing the delay it
+# has added. Failure to remove the delay will result in a
+# non-functioning link.
+#
+# Sometimes there is a need to fine tune the delays. Often the MAC or
+# PHY can perform this fine tuning. In the MAC node, the Device Tree
+# properties 'rx-internal-delay-ps' and 'tx-internal-delay-ps' should
+# be used to indicate fine tuning performed by the MAC. The values
+# expected here are small. A value of 2000ps, i.e 2ns, and a phy-mode
+# of 'rgmii' will not be accepted by Reviewers.
+#
+# If the PHY is to perform fine tuning, the properties
+# 'rx-internal-delay-ps' and 'tx-internal-delay-ps' in the PHY node
+# should be used. When the PHY is implementing delays, e.g. 'rgmii-id'
+# these properties should have a value near to 2000ps. If the PCB is
+# implementing delays, e.g. 'rgmii', a small value can be used to fine
+# tune the delay added by the PCB.
 ...
diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
index 824bbe4333b7..71e2cd32580f 100644
--- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
@@ -238,6 +238,16 @@ properties:
       peak-to-peak specified in ANSI X3.263. When omitted, the PHYs default
       will be left as is.
 
+  mac-termination-ohms:
+    maximum: 200
+    description:
+      The xMII signals need series termination on the driver side to match both
+      the output driver impedance and the line characteristic impedance, to
+      prevent reflections and EMI problems. Select a resistance value which is
+      supported by the builtin resistors of the PHY, otherwise the resistors may
+      have to be placed on board. When omitted, the PHYs default will be left as
+      is.
+
   leds:
     type: object
 
diff --git a/Documentation/devicetree/bindings/net/network-class.yaml b/Documentation/devicetree/bindings/net/network-class.yaml
new file mode 100644
index 000000000000..06461fb92eb8
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/network-class.yaml
@@ -0,0 +1,46 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/network-class.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Network Class Common Properties
+
+maintainers:
+  - Devicetree Specification Mailing List <devicetree-spec@vger.kernel.org>
+
+properties:
+  address-bits:
+    description:
+      Specifies number of address bits required to address the device
+      described by this node, e.g. size of the MAC address.
+    default: 48
+    const: 48
+
+  local-mac-address:
+    description:
+      Specifies MAC address that was assigned to the network device described by
+      the node containing this property.
+    $ref: /schemas/types.yaml#/definitions/uint8-array
+    minItems: 6
+    maxItems: 6
+
+  mac-address:
+    description:
+      Specifies the MAC address that was last used by the boot program. This
+      property should be used in cases where the MAC address assigned to the
+      device by the boot program is different from the
+      local-mac-address property. This property shall be used only if the value
+      differs from local-mac-address property value.
+    $ref: /schemas/types.yaml#/definitions/uint8-array
+    minItems: 6
+    maxItems: 6
+
+  max-frame-size:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      Maximum transfer unit (IEEE defined MTU), rather than the
+      maximum frame size (there\'s contradiction in the Devicetree
+      Specification).
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/net/renesas,r9a09g057-gbeth.yaml b/Documentation/devicetree/bindings/net/renesas,r9a09g057-gbeth.yaml
new file mode 100644
index 000000000000..c498a9999289
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/renesas,r9a09g057-gbeth.yaml
@@ -0,0 +1,203 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/renesas,r9a09g057-gbeth.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: GBETH glue layer for Renesas RZ/V2H(P) (and similar SoCs)
+
+maintainers:
+  - Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
+
+select:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - renesas,r9a09g056-gbeth
+          - renesas,r9a09g057-gbeth
+          - renesas,rzv2h-gbeth
+  required:
+    - compatible
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - renesas,r9a09g056-gbeth # RZ/V2N
+          - renesas,r9a09g057-gbeth # RZ/V2H(P)
+      - const: renesas,rzv2h-gbeth
+      - const: snps,dwmac-5.20
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: CSR clock
+      - description: AXI system clock
+      - description: PTP clock
+      - description: TX clock
+      - description: RX clock
+      - description: TX clock phase-shifted by 180 degrees
+      - description: RX clock phase-shifted by 180 degrees
+
+  clock-names:
+    items:
+      - const: stmmaceth
+      - const: pclk
+      - const: ptp_ref
+      - const: tx
+      - const: rx
+      - const: tx-180
+      - const: rx-180
+
+  interrupts:
+    minItems: 11
+
+  interrupt-names:
+    items:
+      - const: macirq
+      - const: eth_wake_irq
+      - const: eth_lpi
+      - const: rx-queue-0
+      - const: rx-queue-1
+      - const: rx-queue-2
+      - const: rx-queue-3
+      - const: tx-queue-0
+      - const: tx-queue-1
+      - const: tx-queue-2
+      - const: tx-queue-3
+
+  resets:
+    items:
+      - description: AXI power-on system reset
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - interrupts
+  - interrupt-names
+  - resets
+
+allOf:
+  - $ref: snps,dwmac.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/renesas-cpg-mssr.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    ethernet@15c30000 {
+        compatible = "renesas,r9a09g057-gbeth", "renesas,rzv2h-gbeth", "snps,dwmac-5.20";
+        reg = <0x15c30000 0x10000>;
+        clocks =  <&cpg CPG_MOD 0xbd>, <&cpg CPG_MOD 0xbc>,
+                  <&ptp_clock>, <&cpg CPG_MOD 0xb8>,
+                  <&cpg CPG_MOD 0xb9>, <&cpg CPG_MOD 0xba>,
+                  <&cpg CPG_MOD 0xbb>;
+        clock-names = "stmmaceth", "pclk", "ptp_ref",
+                      "tx", "rx", "tx-180", "rx-180";
+        resets = <&cpg 0xb0>;
+        interrupts = <GIC_SPI 765 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 767 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 766 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 772 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 773 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 774 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 745 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 768 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 769 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 770 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 771 IRQ_TYPE_LEVEL_HIGH>;
+        interrupt-names = "macirq", "eth_wake_irq", "eth_lpi",
+                          "rx-queue-0", "rx-queue-1", "rx-queue-2",
+                          "rx-queue-3", "tx-queue-0", "tx-queue-1",
+                          "tx-queue-2", "tx-queue-3";
+        phy-mode = "rgmii-id";
+        snps,multicast-filter-bins = <256>;
+        snps,perfect-filter-entries = <128>;
+        rx-fifo-depth = <8192>;
+        tx-fifo-depth = <8192>;
+        snps,fixed-burst;
+        snps,force_thresh_dma_mode;
+        snps,axi-config = <&stmmac_axi_setup>;
+        snps,mtl-rx-config = <&mtl_rx_setup>;
+        snps,mtl-tx-config = <&mtl_tx_setup>;
+        snps,txpbl = <32>;
+        snps,rxpbl = <32>;
+        phy-handle = <&phy0>;
+
+        stmmac_axi_setup: stmmac-axi-config {
+            snps,lpi_en;
+            snps,wr_osr_lmt = <0xf>;
+            snps,rd_osr_lmt = <0xf>;
+            snps,blen = <16 8 4 0 0 0 0>;
+        };
+
+        mtl_rx_setup: rx-queues-config {
+            snps,rx-queues-to-use = <4>;
+            snps,rx-sched-sp;
+
+            queue0 {
+                snps,dcb-algorithm;
+                snps,priority = <0x1>;
+                snps,map-to-dma-channel = <0>;
+            };
+
+            queue1 {
+                snps,dcb-algorithm;
+                snps,priority = <0x2>;
+                snps,map-to-dma-channel = <1>;
+            };
+
+            queue2 {
+                snps,dcb-algorithm;
+                snps,priority = <0x4>;
+                snps,map-to-dma-channel = <2>;
+            };
+
+            queue3 {
+                snps,dcb-algorithm;
+                snps,priority = <0x8>;
+                snps,map-to-dma-channel = <3>;
+            };
+        };
+
+        mtl_tx_setup: tx-queues-config {
+            snps,tx-queues-to-use = <4>;
+
+            queue0 {
+                snps,dcb-algorithm;
+                snps,priority = <0x1>;
+            };
+
+            queue1 {
+                snps,dcb-algorithm;
+                snps,priority = <0x2>;
+            };
+
+            queue2 {
+                snps,dcb-algorithm;
+                snps,priority = <0x4>;
+            };
+
+            queue3 {
+                snps,dcb-algorithm;
+                snps,priority = <0x1>;
+            };
+        };
+
+        mdio {
+            #address-cells = <1>;
+            #size-cells = <0>;
+            compatible = "snps,dwmac-mdio";
+
+            phy0: ethernet-phy@0 {
+                reg = <0>;
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
index 78b3030dc56d..90b79283e228 100644
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@@ -75,6 +75,7 @@ properties:
         - qcom,sm8150-ethqos
         - renesas,r9a06g032-gmac
         - renesas,rzn1-gmac
+        - renesas,rzv2h-gbeth
         - rockchip,px30-gmac
         - rockchip,rk3128-gmac
         - rockchip,rk3228-gmac
@@ -114,19 +115,25 @@ properties:
 
   interrupts:
     minItems: 1
-    items:
-      - description: Combined signal for various interrupt events
-      - description: The interrupt to manage the remote wake-up packet detection
-      - description: The interrupt that occurs when Rx exits the LPI state
-      - description: The interrupt that occurs when HW safety error triggered
+    maxItems: 11
 
   interrupt-names:
     minItems: 1
+    maxItems: 11
     items:
-      - const: macirq
-      - enum: [eth_wake_irq, eth_lpi, sfty]
-      - enum: [eth_wake_irq, eth_lpi, sfty]
-      - enum: [eth_wake_irq, eth_lpi, sfty]
+      oneOf:
+        - description: Combined signal for various interrupt events
+          const: macirq
+        - description: The interrupt to manage the remote wake-up packet detection
+          const: eth_wake_irq
+        - description: The interrupt that occurs when Rx exits the LPI state
+          const: eth_lpi
+        - description: The interrupt that occurs when HW safety error triggered
+          const: sfty
+        - description: Per channel receive completion interrupt
+          pattern: '^rx-queue-[0-3]$'
+        - description: Per channel transmit completion interrupt
+          pattern: '^tx-queue-[0-3]$'
 
   clocks:
     minItems: 1
@@ -703,7 +710,7 @@ examples:
             };
         };
 
-        mdio0 {
+        mdio {
             #address-cells = <1>;
             #size-cells = <0>;
             compatible = "snps,dwmac-mdio";
diff --git a/Documentation/devicetree/bindings/net/ti,dp83822.yaml b/Documentation/devicetree/bindings/net/ti,dp83822.yaml
index 50c24248df26..28a0bddb9af9 100644
--- a/Documentation/devicetree/bindings/net/ti,dp83822.yaml
+++ b/Documentation/devicetree/bindings/net/ti,dp83822.yaml
@@ -122,6 +122,9 @@ properties:
       - free-running
       - recovered
 
+  mac-termination-ohms:
+    enum: [43, 44, 46, 48, 50, 53, 55, 58, 61, 65, 69, 73, 78, 84, 91, 99]
+
 required:
   - reg
 
@@ -137,6 +140,7 @@ examples:
         rx-internal-delay-ps = <1>;
         tx-internal-delay-ps = <1>;
         ti,gpio2-clk-out = "xi";
+        mac-termination-ohms = <43>;
       };
     };
 
diff --git a/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml b/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml
index b11894fbaec4..7b3d948f187d 100644
--- a/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml
+++ b/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml
@@ -143,6 +143,8 @@ properties:
           label:
             description: label associated with this port
 
+          fixed-link: true
+
           ti,mac-only:
             $ref: /schemas/types.yaml#/definitions/flag
             description:
diff --git a/Documentation/devicetree/bindings/net/vertexcom-mse102x.yaml b/Documentation/devicetree/bindings/net/vertexcom-mse102x.yaml
index 4158673f723c..8359de7ad272 100644
--- a/Documentation/devicetree/bindings/net/vertexcom-mse102x.yaml
+++ b/Documentation/devicetree/bindings/net/vertexcom-mse102x.yaml
@@ -63,7 +63,7 @@ examples:
             compatible = "vertexcom,mse1021";
             reg = <0>;
             interrupt-parent = <&gpio>;
-            interrupts = <23 IRQ_TYPE_EDGE_RISING>;
+            interrupts = <23 IRQ_TYPE_LEVEL_HIGH>;
             spi-cpha;
             spi-cpol;
             spi-max-frequency = <7142857>;
diff --git a/Documentation/devicetree/bindings/net/via,vt8500-rhine.yaml b/Documentation/devicetree/bindings/net/via,vt8500-rhine.yaml
new file mode 100644
index 000000000000..e663d5a2f014
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/via,vt8500-rhine.yaml
@@ -0,0 +1,41 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/via,vt8500-rhine.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: VIA Rhine 10/100 Network Controller
+
+description:
+  VIA's Ethernet controller integrated into VIA VT8500,
+  WonderMedia WM8950 and related SoCs
+
+maintainers:
+  - Alexey Charkov <alchark@gmail.com>
+
+allOf:
+  - $ref: ethernet-controller.yaml#
+
+properties:
+  compatible:
+    const: via,vt8500-rhine
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+required:
+  - reg
+  - interrupts
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    ethernet@d8004000 {
+        compatible = "via,vt8500-rhine";
+        reg = <0xd8004000 0x100>;
+        interrupts = <10>;
+    };
diff --git a/Documentation/devicetree/bindings/net/via-rhine.txt b/Documentation/devicetree/bindings/net/via-rhine.txt
deleted file mode 100644
index 334eca2bf937..000000000000
--- a/Documentation/devicetree/bindings/net/via-rhine.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-* VIA Rhine 10/100 Network Controller
-
-Required properties:
-- compatible : Should be "via,vt8500-rhine" for integrated
-	Rhine controllers found in VIA VT8500, WonderMedia WM8950
-	and similar. These are listed as 1106:3106 rev. 0x84 on the
-	virtual PCI bus under vendor-provided kernels
-- reg : Address and length of the io space
-- interrupts : Should contain the controller interrupt line
-
-Examples:
-
-ethernet@d8004000 {
-	compatible = "via,vt8500-rhine";
-	reg = <0xd8004000 0x100>;
-	interrupts = <10>;
-};
diff --git a/Documentation/devicetree/bindings/net/wireless/brcm,bcm4329-fmac.yaml b/Documentation/devicetree/bindings/net/wireless/brcm,bcm4329-fmac.yaml
index a3607d55ef36..7c8100e59a6c 100644
--- a/Documentation/devicetree/bindings/net/wireless/brcm,bcm4329-fmac.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/brcm,bcm4329-fmac.yaml
@@ -16,7 +16,7 @@ description:
   binding.
 
 allOf:
-  - $ref: ieee80211.yaml#
+  - $ref: /schemas/net/wireless/wireless-controller.yaml#
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath12k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath12k.yaml
index 9e557cb838c7..dc68dd59988f 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath12k.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath12k.yaml
@@ -21,6 +21,12 @@ properties:
   reg:
     maxItems: 1
 
+  firmware-name:
+    maxItems: 1
+    description:
+      If present, a board or platform specific string used to lookup
+      usecase-specific firmware files for the device.
+
   vddaon-supply:
     description: VDD_AON supply regulator handle
 
diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ipq5332-wifi.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ipq5332-wifi.yaml
new file mode 100644
index 000000000000..363a0ecb6ad9
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ipq5332-wifi.yaml
@@ -0,0 +1,315 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (c) 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/wireless/qcom,ipq5332-wifi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies ath12k wireless devices (AHB)
+
+maintainers:
+  - Jeff Johnson <jjohnson@kernel.org>
+
+description:
+  Qualcomm Technologies IEEE 802.11be AHB devices.
+
+properties:
+  compatible:
+    enum:
+      - qcom,ipq5332-wifi
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: XO clock used for copy engine
+
+  clock-names:
+    items:
+      - const: xo
+
+  interrupts:
+    items:
+      - description: Fatal interrupt
+      - description: Ready interrupt
+      - description: Spawn acknowledge interrupt
+      - description: Stop acknowledge interrupt
+      - description: misc-pulse1 interrupt events
+      - description: misc-latch interrupt events
+      - description: sw exception interrupt events
+      - description: interrupt event for ring CE0
+      - description: interrupt event for ring CE1
+      - description: interrupt event for ring CE2
+      - description: interrupt event for ring CE3
+      - description: interrupt event for ring CE4
+      - description: interrupt event for ring CE5
+      - description: interrupt event for ring CE6
+      - description: interrupt event for ring CE7
+      - description: interrupt event for ring CE8
+      - description: interrupt event for ring CE9
+      - description: interrupt event for ring CE10
+      - description: interrupt event for ring CE11
+      - description: interrupt event for ring host2wbm-desc-feed
+      - description: interrupt event for ring host2reo-re-injection
+      - description: interrupt event for ring host2reo-command
+      - description: interrupt event for ring host2rxdma-monitor-ring1
+      - description: interrupt event for ring reo2ost-exception
+      - description: interrupt event for ring wbm2host-rx-release
+      - description: interrupt event for ring reo2host-status
+      - description: interrupt event for ring reo2host-destination-ring4
+      - description: interrupt event for ring reo2host-destination-ring3
+      - description: interrupt event for ring reo2host-destination-ring2
+      - description: interrupt event for ring reo2host-destination-ring1
+      - description: interrupt event for ring rxdma2host-monitor-destination-mac3
+      - description: interrupt event for ring rxdma2host-monitor-destination-mac2
+      - description: interrupt event for ring rxdma2host-monitor-destination-mac1
+      - description: interrupt event for ring host2rxdma-host-buf-ring-mac3
+      - description: interrupt event for ring host2rxdma-host-buf-ring-mac2
+      - description: interrupt event for ring host2rxdma-host-buf-ring-mac1
+      - description: interrupt event for ring host2tcl-input-ring4
+      - description: interrupt event for ring host2tcl-input-ring3
+      - description: interrupt event for ring host2tcl-input-ring2
+      - description: interrupt event for ring host2tcl-input-ring1
+      - description: interrupt event for ring wbm2host-tx-completions-ring4
+      - description: interrupt event for ring wbm2host-tx-completions-ring3
+      - description: interrupt event for ring wbm2host-tx-completions-ring2
+      - description: interrupt event for ring wbm2host-tx-completions-ring1
+      - description: interrupt event for ring host2tx-monitor-ring1
+      - description: interrupt event for ring txmon2host-monitor-destination-mac3
+      - description: interrupt event for ring txmon2host-monitor-destination-mac2
+      - description: interrupt event for ring txmon2host-monitor-destination-mac1
+      - description: interrupt event for umac-reset
+
+  interrupt-names:
+    items:
+      - const: fatal
+      - const: ready
+      - const: spawn
+      - const: stop-ack
+      - const: misc-pulse1
+      - const: misc-latch
+      - const: sw-exception
+      - const: ce0
+      - const: ce1
+      - const: ce2
+      - const: ce3
+      - const: ce4
+      - const: ce5
+      - const: ce6
+      - const: ce7
+      - const: ce8
+      - const: ce9
+      - const: ce10
+      - const: ce11
+      - const: host2wbm-desc-feed
+      - const: host2reo-re-injection
+      - const: host2reo-command
+      - const: host2rxdma-monitor-ring1
+      - const: reo2ost-exception
+      - const: wbm2host-rx-release
+      - const: reo2host-status
+      - const: reo2host-destination-ring4
+      - const: reo2host-destination-ring3
+      - const: reo2host-destination-ring2
+      - const: reo2host-destination-ring1
+      - const: rxdma2host-monitor-destination-mac3
+      - const: rxdma2host-monitor-destination-mac2
+      - const: rxdma2host-monitor-destination-mac1
+      - const: host2rxdma-host-buf-ring-mac3
+      - const: host2rxdma-host-buf-ring-mac2
+      - const: host2rxdma-host-buf-ring-mac1
+      - const: host2tcl-input-ring4
+      - const: host2tcl-input-ring3
+      - const: host2tcl-input-ring2
+      - const: host2tcl-input-ring1
+      - const: wbm2host-tx-completions-ring4
+      - const: wbm2host-tx-completions-ring3
+      - const: wbm2host-tx-completions-ring2
+      - const: wbm2host-tx-completions-ring1
+      - const: host2tx-monitor-ring1
+      - const: txmon2host-monitor-destination-mac3
+      - const: txmon2host-monitor-destination-mac2
+      - const: txmon2host-monitor-destination-mac1
+      - const: umac-reset
+
+  memory-region:
+    description:
+      Memory regions used by the ath12k firmware.
+    items:
+      - description: Q6 memory region
+      - description: m3 dump memory region
+      - description: Q6 caldata memory region
+      - description: Multi Link Operation (MLO) Global memory region
+
+  memory-region-names:
+    items:
+      - const: q6-region
+      - const: m3-dump
+      - const: q6-caldb
+      - const: mlo-global-mem
+
+  qcom,calibration-variant:
+    $ref: /schemas/types.yaml#/definitions/string
+    description:
+      String to uniquely identify variant of the calibration data for designs
+      with colliding bus and device ids
+
+  qcom,rproc:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      Phandle to the Qualcomm Hexagon DSP(q6 remote processor), which is utilized
+      for offloading WiFi processing tasks, this q6 remote processor operates in
+      conjunction with WiFi.
+
+  qcom,smem-states:
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    description: States used by the AP to signal the remote processor
+    items:
+      - description: Shutdown WCSS pd
+      - description: Stop WCSS pd
+      - description: Spawn WCSS pd
+
+  qcom,smem-state-names:
+    description:
+      Names of the states used by the AP to signal the remote processor
+    items:
+      - const: shutdown
+      - const: stop
+      - const: spawn
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - interrupts
+  - interrupt-names
+  - memory-region
+  - memory-region-names
+  - qcom,rproc
+  - qcom,smem-states
+  - qcom,smem-state-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/qcom,ipq5332-gcc.h>
+
+    wifi0: wifi@c000000 {
+        compatible = "qcom,ipq5332-wifi";
+        reg = <0x0c000000 0x1000000>;
+        clocks = <&gcc GCC_XO_CLK>;
+        clock-names = "xo";
+        interrupts-extended = <&wcss_smp2p_in 8 IRQ_TYPE_NONE>,
+                              <&wcss_smp2p_in 9 IRQ_TYPE_NONE>,
+                              <&wcss_smp2p_in 12 IRQ_TYPE_NONE>,
+                              <&wcss_smp2p_in 11 IRQ_TYPE_NONE>,
+                              <&intc GIC_SPI 559 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 560 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 561 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 422 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 423 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 424 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 425 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 426 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 427 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 428 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 429 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 430 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 431 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 432 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 433 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 491 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 495 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 493 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 544 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 457 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 466 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 497 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 454 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 453 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 452 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 451 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 488 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 488 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 484 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 554 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 554 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 549 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 507 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 500 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 499 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 498 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 450 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 449 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 448 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 447 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 543 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 486 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 486 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 482 IRQ_TYPE_EDGE_RISING>,
+                              <&intc GIC_SPI 419 IRQ_TYPE_EDGE_RISING>;
+        interrupt-names = "fatal",
+                          "ready",
+                          "spawn",
+                          "stop-ack",
+                          "misc-pulse1",
+                          "misc-latch",
+                          "sw-exception",
+                          "ce0",
+                          "ce1",
+                          "ce2",
+                          "ce3",
+                          "ce4",
+                          "ce5",
+                          "ce6",
+                          "ce7",
+                          "ce8",
+                          "ce9",
+                          "ce10",
+                          "ce11",
+                          "host2wbm-desc-feed",
+                          "host2reo-re-injection",
+                          "host2reo-command",
+                          "host2rxdma-monitor-ring1",
+                          "reo2ost-exception",
+                          "wbm2host-rx-release",
+                          "reo2host-status",
+                          "reo2host-destination-ring4",
+                          "reo2host-destination-ring3",
+                          "reo2host-destination-ring2",
+                          "reo2host-destination-ring1",
+                          "rxdma2host-monitor-destination-mac3",
+                          "rxdma2host-monitor-destination-mac2",
+                          "rxdma2host-monitor-destination-mac1",
+                          "host2rxdma-host-buf-ring-mac3",
+                          "host2rxdma-host-buf-ring-mac2",
+                          "host2rxdma-host-buf-ring-mac1",
+                          "host2tcl-input-ring4",
+                          "host2tcl-input-ring3",
+                          "host2tcl-input-ring2",
+                          "host2tcl-input-ring1",
+                          "wbm2host-tx-completions-ring4",
+                          "wbm2host-tx-completions-ring3",
+                          "wbm2host-tx-completions-ring2",
+                          "wbm2host-tx-completions-ring1",
+                          "host2tx-monitor-ring1",
+                          "txmon2host-monitor-destination-mac3",
+                          "txmon2host-monitor-destination-mac2",
+                          "txmon2host-monitor-destination-mac1",
+                          "umac-reset";
+
+        memory-region = <&q6_region>, <&m3_dump>, <&q6_caldb>, <&mlo_mem>;
+        memory-region-names = "q6-region", "m3-dump", "q6-caldb", "mlo-global-mem";
+        qcom,calibration-variant = "RDP441_1";
+        qcom,rproc = <&q6v5_wcss>;
+        qcom,smem-states = <&wcss_smp2p_out 8>,
+                           <&wcss_smp2p_out 9>,
+                           <&wcss_smp2p_out 10>;
+        qcom,smem-state-names = "shutdown",
+                                "stop",
+                                "spawn";
+    };
diff --git a/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml b/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
index 84e5659e50ef..6c0888ae4c4e 100644
--- a/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
@@ -71,15 +71,12 @@ properties:
       "Platform Data Set" in Silabs jargon). Default depends of "compatible"
       string. For "silabs,wf200", the default is 'wf200.pds'.
 
-  local-mac-address: true
-
-  mac-address: true
-
 required:
   - compatible
   - reg
 
 allOf:
+  - $ref: /schemas/net/wireless/wireless-controller.yaml#
   - $ref: /schemas/spi/spi-peripheral-props.yaml#
 
 unevaluatedProperties: false
diff --git a/Documentation/devicetree/bindings/net/wireless/wireless-controller.yaml b/Documentation/devicetree/bindings/net/wireless/wireless-controller.yaml
new file mode 100644
index 000000000000..7379f6c1aa05
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/wireless/wireless-controller.yaml
@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/wireless/wireless-controller.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Wireless Controller Common Properties
+
+maintainers:
+  - Lorenzo Bianconi <lorenzo@kernel.org>
+
+properties:
+  $nodename:
+    pattern: "^wifi(@.*)?$"
+
+allOf:
+  - $ref: ieee80211.yaml#
+  - $ref: /schemas/net/network-class.yaml#
+
+additionalProperties: true
+
+...
+
diff --git a/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml b/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml
index 8b3826243ddd..38e3ad50ff4f 100644
--- a/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml
+++ b/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml
@@ -27,7 +27,7 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32-array
     items:
       - minimum: 0
-        maximum: 7
+        maximum: 31
         description:
           Offset in bit within the address range specified by reg.
       - minimum: 1
diff --git a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
index 39c209249c9c..3f6dc6a3a9f1 100644
--- a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
+++ b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
@@ -19,6 +19,7 @@ properties:
       - enum:
           - qcom,apq8064-qfprom
           - qcom,apq8084-qfprom
+          - qcom,ipq5018-qfprom
           - qcom,ipq5332-qfprom
           - qcom,ipq5424-qfprom
           - qcom,ipq6018-qfprom
@@ -28,6 +29,8 @@ properties:
           - qcom,msm8226-qfprom
           - qcom,msm8916-qfprom
           - qcom,msm8917-qfprom
+          - qcom,msm8937-qfprom
+          - qcom,msm8960-qfprom
           - qcom,msm8974-qfprom
           - qcom,msm8976-qfprom
           - qcom,msm8996-qfprom
@@ -51,6 +54,7 @@ properties:
           - qcom,sm8450-qfprom
           - qcom,sm8550-qfprom
           - qcom,sm8650-qfprom
+          - qcom,x1e80100-qfprom
       - const: qcom,qfprom
 
   reg:
diff --git a/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml b/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml
index a44d44b32809..dc89020b0950 100644
--- a/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml
+++ b/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml
@@ -14,6 +14,7 @@ properties:
     enum:
       - rockchip,px30-otp
       - rockchip,rk3308-otp
+      - rockchip,rk3576-otp
       - rockchip,rk3588-otp
 
   reg:
@@ -62,6 +63,8 @@ allOf:
       properties:
         clocks:
           maxItems: 3
+        clock-names:
+          maxItems: 3
         resets:
           maxItems: 1
         reset-names:
@@ -73,11 +76,33 @@ allOf:
         compatible:
           contains:
             enum:
+              - rockchip,rk3576-otp
+    then:
+      properties:
+        clocks:
+          maxItems: 3
+        clock-names:
+          maxItems: 3
+        resets:
+          minItems: 2
+          maxItems: 2
+        reset-names:
+          items:
+            - const: otp
+            - const: apb
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
               - rockchip,rk3588-otp
     then:
       properties:
         clocks:
           minItems: 4
+        clock-names:
+          minItems: 4
         resets:
           minItems: 3
         reset-names:
diff --git a/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml b/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml
index a4dfa09344dd..f85ee5d20ccb 100644
--- a/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml
+++ b/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.yaml
@@ -9,15 +9,6 @@ title: Renesas R-Car Timer Pulse Unit PWM Controller
 maintainers:
   - Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
 
-select:
-  properties:
-    compatible:
-      contains:
-        const: renesas,tpu
-  required:
-    - compatible
-    - '#pwm-cells'
-
 properties:
   compatible:
     items:
diff --git a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
index 1f1b42dde94d..1db85fc9966f 100644
--- a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
+++ b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
@@ -7,7 +7,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Zynq UltraScale+ MPSoC and Versal reset
 
 maintainers:
-  - Mubin Sayyed <mubin.sayyed@amd.com>
   - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 description: |
diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml
index 31295be91013..234089b5954d 100644
--- a/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml
+++ b/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Freescale Layerscape Reset Registers Module
 
 maintainers:
-  - Frank Li
+  - Frank Li <Frank.Li@nxp.com>
 
 description:
   Reset Module includes chip reset, service processor control and Reset Control
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,wcnss.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,wcnss.yaml
index fd6db0ca98eb..4fcae6bedfff 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,wcnss.yaml
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,wcnss.yaml
@@ -54,7 +54,7 @@ properties:
       - compatible
 
   wifi:
-    additionalProperties: false
+    unevaluatedProperties: false
     type: object
     properties:
       compatible:
@@ -88,6 +88,9 @@ properties:
       - qcom,smem-states
       - qcom,smem-state-names
 
+    allOf:
+      - $ref: /schemas/net/wireless/wireless-controller.yaml#
+
 required:
   - compatible
   - qcom,mmio
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
index bccd00a1ddd0..53d00ca643b3 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
@@ -56,19 +56,18 @@ properties:
         enum:
           - snps,dw-apb-ssi
           - snps,dwc-ssi-1.01a
-      - description: Microsemi Ocelot/Jaguar2 SoC SPI Controller
-        items:
-          - enum:
-              - mscc,ocelot-spi
-              - mscc,jaguar2-spi
-          - const: snps,dw-apb-ssi
       - description: Microchip Sparx5 SoC SPI Controller
         const: microchip,sparx5-spi
       - description: Amazon Alpine SPI Controller
         const: amazon,alpine-dw-apb-ssi
-      - description: Renesas RZ/N1 SPI Controller
+      - description: Vendor controllers which use snps,dw-apb-ssi as fallback
         items:
-          - const: renesas,rzn1-spi
+          - enum:
+              - mscc,ocelot-spi
+              - mscc,jaguar2-spi
+              - renesas,rzn1-spi
+              - sophgo,sg2042-spi
+              - thead,th1520-spi
           - const: snps,dw-apb-ssi
       - description: Intel Keem Bay SPI Controller
         const: intel,keembay-ssi
@@ -88,10 +87,6 @@ properties:
               - renesas,r9a06g032-spi # RZ/N1D
               - renesas,r9a06g033-spi # RZ/N1S
           - const: renesas,rzn1-spi   # RZ/N1
-      - description: T-HEAD TH1520 SoC SPI Controller
-        items:
-          - const: thead,th1520-spi
-          - const: snps,dw-apb-ssi
 
   reg:
     minItems: 1
diff --git a/Documentation/devicetree/bindings/timer/nxp,sysctr-timer.yaml b/Documentation/devicetree/bindings/timer/nxp,sysctr-timer.yaml
index 891cca009528..6b80b060672e 100644
--- a/Documentation/devicetree/bindings/timer/nxp,sysctr-timer.yaml
+++ b/Documentation/devicetree/bindings/timer/nxp,sysctr-timer.yaml
@@ -18,9 +18,14 @@ description: |
 
 properties:
   compatible:
-    enum:
-      - nxp,imx95-sysctr-timer
-      - nxp,sysctr-timer
+    oneOf:
+      - enum:
+          - nxp,imx95-sysctr-timer
+          - nxp,sysctr-timer
+      - items:
+          - enum:
+              - nxp,imx94-sysctr-timer
+          - const: nxp,imx95-sysctr-timer
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/timer/renesas,tpu.yaml b/Documentation/devicetree/bindings/timer/renesas,tpu.yaml
deleted file mode 100644
index 7a473b302775..000000000000
--- a/Documentation/devicetree/bindings/timer/renesas,tpu.yaml
+++ /dev/null
@@ -1,56 +0,0 @@
-# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-%YAML 1.2
----
-$id: http://devicetree.org/schemas/timer/renesas,tpu.yaml#
-$schema: http://devicetree.org/meta-schemas/core.yaml#
-
-title: Renesas H8/300 Timer Pulse Unit
-
-maintainers:
-  - Yoshinori Sato <ysato@users.sourceforge.jp>
-
-description:
-  The TPU is a 16bit timer/counter with configurable clock inputs and
-  programmable compare match.
-  This implementation supports only cascade mode.
-
-select:
-  properties:
-    compatible:
-      contains:
-        const: renesas,tpu
-    '#pwm-cells': false
-  required:
-    - compatible
-
-properties:
-  compatible:
-    const: renesas,tpu
-
-  reg:
-    items:
-      - description: First channel
-      - description: Second channel
-
-  clocks:
-    maxItems: 1
-
-  clock-names:
-    const: fck
-
-required:
-  - compatible
-  - reg
-  - clocks
-  - clock-names
-
-additionalProperties: false
-
-examples:
-  - |
-    tpu: tpu@ffffe0 {
-        compatible = "renesas,tpu";
-        reg = <0xffffe0 16>, <0xfffff0 12>;
-        clocks = <&pclk>;
-        clock-names = "fck";
-    };
diff --git a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
index b5843f4d17d8..379dacacb526 100644
--- a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
+++ b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
@@ -7,7 +7,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Xilinx SuperSpeed DWC3 USB SoC controller
 
 maintainers:
-  - Mubin Sayyed <mubin.sayyed@amd.com>
   - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
diff --git a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
index e2a72deae776..c68c04da3399 100644
--- a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
+++ b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
@@ -17,7 +17,6 @@ description:
 
 maintainers:
   - Michal Simek <michal.simek@amd.com>
-  - Mubin Sayyed <mubin.sayyed@amd.com>
   - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
diff --git a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
index a7f75fe36665..f295aa9d9ee7 100644
--- a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
+++ b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
@@ -7,7 +7,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Xilinx udc controller
 
 maintainers:
-  - Mubin Sayyed <mubin.sayyed@amd.com>
   - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
diff --git a/Documentation/filesystems/ext4/super.rst b/Documentation/filesystems/ext4/super.rst
index a1eb4a11a1d0..1b240661bfa3 100644
--- a/Documentation/filesystems/ext4/super.rst
+++ b/Documentation/filesystems/ext4/super.rst
@@ -328,9 +328,13 @@ The ext4 superblock is laid out as follows in
      - s_checksum_type
      - Metadata checksum algorithm type. The only valid value is 1 (crc32c).
    * - 0x176
-     - __le16
-     - s_reserved_pad
-     -
+     - \_\_u8
+     - s\_encryption\_level
+     - Versioning level for encryption.
+   * - 0x177
+     - \_\_u8
+     - s\_reserved\_pad
+     - Padding to next 32bits.
    * - 0x178
      - __le64
      - s_kbytes_written
@@ -466,9 +470,13 @@ The ext4 superblock is laid out as follows in
      - s_last_error_time_hi
      - Upper 8 bits of the s_last_error_time field.
    * - 0x27A
-     - __u8
-     - s_pad[2]
-     - Zero padding.
+     - \_\_u8
+     - s\_first\_error\_errcode
+     -
+   * - 0x27B
+     - \_\_u8
+     - s\_last\_error\_errcode
+     -
    * - 0x27C
      - __le16
      - s_encoding
diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst
index a7762486c93f..f2dcc39044e6 100644
--- a/Documentation/kbuild/reproducible-builds.rst
+++ b/Documentation/kbuild/reproducible-builds.rst
@@ -46,6 +46,21 @@ The kernel embeds the building user and host names in
 `KBUILD_BUILD_USER and KBUILD_BUILD_HOST`_ variables.  If you are
 building from a git commit, you could use its committer address.
 
+Absolute filenames
+------------------
+
+When the kernel is built out-of-tree, debug information may include
+absolute filenames for the source files.  This must be overridden by
+including the ``-fdebug-prefix-map`` option in the `KCFLAGS`_ variable.
+
+Depending on the compiler used, the ``__FILE__`` macro may also expand
+to an absolute filename in an out-of-tree build.  Kbuild automatically
+uses the ``-fmacro-prefix-map`` option to prevent this, if it is
+supported.
+
+The Reproducible Builds web site has more information about these
+`prefix-map options`_.
+
 Generated files in source packages
 ----------------------------------
 
@@ -116,5 +131,7 @@ See ``scripts/setlocalversion`` for details.
 
 .. _KBUILD_BUILD_TIMESTAMP: kbuild.html#kbuild-build-timestamp
 .. _KBUILD_BUILD_USER and KBUILD_BUILD_HOST: kbuild.html#kbuild-build-user-kbuild-build-host
+.. _KCFLAGS: kbuild.html#kcflags
+.. _prefix-map options: https://reproducible-builds.org/docs/build-path/
 .. _Reproducible Builds project: https://reproducible-builds.org/
 .. _SOURCE_DATE_EPOCH: https://reproducible-builds.org/docs/source-date-epoch/
diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml
index 96fa1f1522ed..5a234e9b5fa2 100644
--- a/Documentation/netlink/genetlink-c.yaml
+++ b/Documentation/netlink/genetlink-c.yaml
@@ -148,6 +148,9 @@ properties:
         attr-max-name:
           description: The explicit name for last member of attribute enum.
           type: string
+        header:
+          description: For C-compatible languages, header which already defines this attribute set.
+          type: string
         # End genetlink-c
         attributes:
           description: List of attributes in the space.
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index a8c5b521937d..4cbfe666e6f5 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -193,6 +193,9 @@ properties:
         attr-max-name:
           description: The explicit name for last member of attribute enum.
           type: string
+        header:
+          description: For C-compatible languages, header which already defines this attribute set.
+          type: string
         # End genetlink-c
         attributes:
           description: List of attributes in the space.
diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml
index 1b0772c8e333..e34bf23897fa 100644
--- a/Documentation/netlink/netlink-raw.yaml
+++ b/Documentation/netlink/netlink-raw.yaml
@@ -207,6 +207,9 @@ properties:
         attr-max-name:
           description: The explicit name for last member of attribute enum.
           type: string
+        header:
+          description: For C-compatible languages, header which already defines this attribute set.
+          type: string
         # End genetlink-c
         attributes:
           description: List of attributes in the space.
diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index bd9726269b4f..05fee1b7fe19 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -202,6 +202,28 @@ definitions:
         name: exception
       -
         name: control
+  -
+    type: enum
+    name: var-attr-type
+    entries:
+      -
+        name: u8
+        value: 1
+      -
+        name: u16
+      -
+        name: u32
+      -
+        name: u64
+      -
+        name: string
+      -
+        name: flag
+      -
+        name: nul_string
+        value: 10
+      -
+        name: binary
 
 attribute-sets:
   -
@@ -498,6 +520,7 @@ attribute-sets:
       -
         name: param-type
         type: u8
+        enum: var-attr-type
 
       # TODO: fill in the attributes in between
 
@@ -592,6 +615,7 @@ attribute-sets:
       -
         name: fmsg-obj-value-type
         type: u8
+        enum: var-attr-type
 
       # TODO: fill in the attributes in between
 
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 655d8d10fe24..9f98715a6512 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -89,13 +89,33 @@ definitions:
           doc: Group of short_detected states
   -
     name: phy-upstream-type
-    enum-name:
+    enum-name: phy-upstream
+    header: linux/ethtool.h
     type: enum
+    name-prefix: phy-upstream
     entries: [ mac, phy ]
   -
     name: tcp-data-split
     type: enum
     entries: [ unknown, disabled, enabled ]
+  -
+    name: hwtstamp-source
+    doc: Source of the hardware timestamp
+    enum-name: hwtstamp-source
+    name-prefix: hwtstamp-source-
+    type: enum
+    entries:
+      -
+        name: netdev
+        doc: |
+          Hardware timestamp comes from a MAC or a device
+          which has MAC and PHY integrated
+        value: 1
+      -
+        name: phylib
+        doc: |
+          Hardware timestamp comes from one PHY device
+          of the network topology
 
 attribute-sets:
   -
@@ -894,6 +914,13 @@ attribute-sets:
         name: hwtstamp-provider
         type: nest
         nested-attributes: ts-hwtstamp-provider
+      -
+        name: hwtstamp-source
+        type: u32
+        enum: hwtstamp-source
+      -
+        name: hwtstamp-phyindex
+        type: u32
   -
     name: cable-result
     attr-cnt-name: __ethtool-a-cable-result-cnt
@@ -1979,6 +2006,8 @@ operations:
             - phc-index
             - stats
             - hwtstamp-provider
+            - hwtstamp-source
+            - hwtstamp-phyindex
       dump: *tsinfo-get-op
     -
       name: cable-test-act
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index f5e0750ab71d..c0ef6d0d7786 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -743,6 +743,18 @@ operations:
             - defer-hard-irqs
             - gro-flush-timeout
             - irq-suspend-timeout
+    -
+      name: bind-tx
+      doc: Bind dmabuf to netdev for TX
+      attribute-set: dmabuf
+      do:
+        request:
+          attributes:
+            - ifindex
+            - fd
+        reply:
+          attributes:
+            - id
 
 kernel-family:
   headers: [ "net/netdev_netlink.h"]
diff --git a/Documentation/netlink/specs/nl80211.yaml b/Documentation/netlink/specs/nl80211.yaml
index 1ec49c3562cd..3611b11a7d8f 100644
--- a/Documentation/netlink/specs/nl80211.yaml
+++ b/Documentation/netlink/specs/nl80211.yaml
@@ -204,71 +204,6 @@ definitions:
       - sched-scan-random-mac-addr
       - no-random-mac-addr
   -
-    name: ieee80211-mcs-info
-    type: struct
-    members:
-      -
-        name: rx-mask
-        type: binary
-        len: 10
-      -
-        name: rx-highest
-        type: u16
-        byte-order: little-endian
-      -
-        name: tx-params
-        type: u8
-      -
-        name: reserved
-        type: binary
-        len: 3
-  -
-    name: ieee80211-vht-mcs-info
-    type: struct
-    members:
-      -
-        name: rx-mcs-map
-        type: u16
-        byte-order: little-endian
-      -
-        name: rx-highest
-        type: u16
-        byte-order: little-endian
-      -
-        name: tx-mcs-map
-        type: u16
-        byte-order: little-endian
-      -
-        name: tx-highest
-        type: u16
-        byte-order: little-endian
-  -
-    name: ieee80211-ht-cap
-    type: struct
-    members:
-      -
-        name: cap-info
-        type: u16
-        byte-order: little-endian
-      -
-        name: ampdu-params-info
-        type: u8
-      -
-        name: mcs
-        type: binary
-        struct: ieee80211-mcs-info
-      -
-        name: extended-ht-cap-info
-        type: u16
-        byte-order: little-endian
-      -
-        name: tx-bf-cap-info
-        type: u32
-        byte-order: little-endian
-      -
-        name: antenna-selection-info
-        type: u8
-  -
     name: channel-type
     type: enum
     entries:
@@ -761,7 +696,6 @@ attribute-sets:
       -
         name: ht-capability-mask
         type: binary
-        struct: ieee80211-ht-cap
       -
         name: noack-map
         type: u16
@@ -1382,7 +1316,6 @@ attribute-sets:
       -
         name: ht-mcs-set
         type: binary
-        struct: ieee80211-mcs-info
       -
         name: ht-capa
         type: u16
@@ -1395,7 +1328,6 @@ attribute-sets:
       -
         name: vht-mcs-set
         type: binary
-        struct: ieee80211-vht-mcs-info
       -
         name: vht-capa
         type: u32
diff --git a/Documentation/netlink/specs/ovpn.yaml b/Documentation/netlink/specs/ovpn.yaml
new file mode 100644
index 000000000000..096c51f0c69a
--- /dev/null
+++ b/Documentation/netlink/specs/ovpn.yaml
@@ -0,0 +1,367 @@
+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+#
+# Author: Antonio Quartulli <antonio@openvpn.net>
+#
+# Copyright (c) 2024-2025, OpenVPN Inc.
+#
+
+name: ovpn
+
+protocol: genetlink
+
+doc: Netlink protocol to control OpenVPN network devices
+
+definitions:
+  -
+    type: const
+    name: nonce-tail-size
+    value: 8
+  -
+    type: enum
+    name: cipher-alg
+    entries: [ none, aes-gcm, chacha20-poly1305 ]
+  -
+    type: enum
+    name: del-peer-reason
+    entries:
+      - teardown
+      - userspace
+      - expired
+      - transport-error
+      - transport-disconnect
+  -
+    type: enum
+    name: key-slot
+    entries: [ primary, secondary ]
+
+attribute-sets:
+  -
+    name: peer
+    attributes:
+      -
+        name: id
+        type: u32
+        doc: >-
+          The unique ID of the peer in the device context. To be used to identify
+          peers during operations for a specific device
+        checks:
+          max: 0xFFFFFF
+      -
+        name: remote-ipv4
+        type: u32
+        doc: The remote IPv4 address of the peer
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: remote-ipv6
+        type: binary
+        doc: The remote IPv6 address of the peer
+        display-hint: ipv6
+        checks:
+          exact-len: 16
+      -
+        name: remote-ipv6-scope-id
+        type: u32
+        doc: The scope id of the remote IPv6 address of the peer (RFC2553)
+      -
+        name: remote-port
+        type: u16
+        doc: The remote port of the peer
+        byte-order: big-endian
+        checks:
+          min: 1
+      -
+        name: socket
+        type: u32
+        doc: The socket to be used to communicate with the peer
+      -
+        name: socket-netnsid
+        type: s32
+        doc: The ID of the netns the socket assigned to this peer lives in
+      -
+        name: vpn-ipv4
+        type: u32
+        doc: The IPv4 address assigned to the peer by the server
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: vpn-ipv6
+        type: binary
+        doc: The IPv6 address assigned to the peer by the server
+        display-hint: ipv6
+        checks:
+          exact-len: 16
+      -
+        name: local-ipv4
+        type: u32
+        doc: The local IPv4 to be used to send packets to the peer (UDP only)
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: local-ipv6
+        type: binary
+        doc: The local IPv6 to be used to send packets to the peer (UDP only)
+        display-hint: ipv6
+        checks:
+          exact-len: 16
+      -
+        name: local-port
+        type: u16
+        doc: The local port to be used to send packets to the peer (UDP only)
+        byte-order: big-endian
+        checks:
+          min: 1
+      -
+        name: keepalive-interval
+        type: u32
+        doc: >-
+          The number of seconds after which a keep alive message is sent to the
+          peer
+      -
+        name: keepalive-timeout
+        type: u32
+        doc: >-
+          The number of seconds from the last activity after which the peer is
+          assumed dead
+      -
+        name: del-reason
+        type: u32
+        doc: The reason why a peer was deleted
+        enum: del-peer-reason
+      -
+        name: vpn-rx-bytes
+        type: uint
+        doc: Number of bytes received over the tunnel
+      -
+        name: vpn-tx-bytes
+        type: uint
+        doc: Number of bytes transmitted over the tunnel
+      -
+        name: vpn-rx-packets
+        type: uint
+        doc: Number of packets received over the tunnel
+      -
+        name: vpn-tx-packets
+        type: uint
+        doc: Number of packets transmitted over the tunnel
+      -
+        name: link-rx-bytes
+        type: uint
+        doc: Number of bytes received at the transport level
+      -
+        name: link-tx-bytes
+        type: uint
+        doc: Number of bytes transmitted at the transport level
+      -
+        name: link-rx-packets
+        type: uint
+        doc: Number of packets received at the transport level
+      -
+        name: link-tx-packets
+        type: uint
+        doc: Number of packets transmitted at the transport level
+  -
+    name: keyconf
+    attributes:
+      -
+        name: peer-id
+        type: u32
+        doc: >-
+          The unique ID of the peer in the device context. To be used to
+          identify peers during key operations
+        checks:
+          max: 0xFFFFFF
+      -
+        name: slot
+        type: u32
+        doc: The slot where the key should be stored
+        enum: key-slot
+      -
+        name: key-id
+        doc: >-
+          The unique ID of the key in the peer context. Used to fetch the
+          correct key upon decryption
+        type: u32
+        checks:
+          max: 7
+      -
+        name: cipher-alg
+        type: u32
+        doc: The cipher to be used when communicating with the peer
+        enum: cipher-alg
+      -
+        name: encrypt-dir
+        type: nest
+        doc: Key material for encrypt direction
+        nested-attributes: keydir
+      -
+        name: decrypt-dir
+        type: nest
+        doc: Key material for decrypt direction
+        nested-attributes: keydir
+  -
+    name: keydir
+    attributes:
+      -
+        name: cipher-key
+        type: binary
+        doc: The actual key to be used by the cipher
+        checks:
+          max-len: 256
+      -
+        name: nonce-tail
+        type: binary
+        doc: >-
+          Random nonce to be concatenated to the packet ID, in order to
+          obtain the actual cipher IV
+        checks:
+          exact-len: nonce-tail-size
+  -
+    name: ovpn
+    attributes:
+      -
+        name: ifindex
+        type: u32
+        doc: Index of the ovpn interface to operate on
+      -
+        name: peer
+        type: nest
+        doc: >-
+          The peer object containing the attributed of interest for the specific
+          operation
+        nested-attributes: peer
+      -
+        name: keyconf
+        type: nest
+        doc: Peer specific cipher configuration
+        nested-attributes: keyconf
+
+operations:
+  list:
+    -
+      name: peer-new
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Add a remote peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - peer
+    -
+      name: peer-set
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: modify a remote peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - peer
+    -
+      name: peer-get
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Retrieve data about existing remote peers (or a specific one)
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - peer
+        reply:
+          attributes:
+            - peer
+      dump:
+        request:
+          attributes:
+            - ifindex
+        reply:
+          attributes:
+            - peer
+    -
+      name: peer-del
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Delete existing remote peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - peer
+    -
+      name: peer-del-ntf
+      doc: Notification about a peer being deleted
+      notify: peer-get
+      mcgrp: peers
+
+    -
+      name: key-new
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Add a cipher key for a specific peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - keyconf
+    -
+      name: key-get
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Retrieve non-sensitive data about peer key and cipher
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - keyconf
+        reply:
+          attributes:
+            - keyconf
+    -
+      name: key-swap
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Swap primary and secondary session keys for a specific peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - keyconf
+    -
+      name: key-swap-ntf
+      notify: key-get
+      doc: >-
+        Notification about key having exhausted its IV space and requiring
+        renegotiation
+      mcgrp: peers
+    -
+      name: key-del
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Delete cipher key for a specific peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - keyconf
+
+mcast-groups:
+  list:
+    -
+      name: peers
diff --git a/Documentation/netlink/specs/ovs_datapath.yaml b/Documentation/netlink/specs/ovs_datapath.yaml
index edc8c95ca6f5..df6a8f94975e 100644
--- a/Documentation/netlink/specs/ovs_datapath.yaml
+++ b/Documentation/netlink/specs/ovs_datapath.yaml
@@ -35,8 +35,7 @@ definitions:
         name: dispatch-upcall-per-cpu
         doc: Allow per-cpu dispatch of upcalls
   -
-    name: datapath-stats
-    enum-name: ovs-dp-stats
+    name: ovs-dp-stats
     type: struct
     members:
       -
@@ -52,8 +51,7 @@ definitions:
         name: n-flows
         type: u64
   -
-    name: megaflow-stats
-    enum-name: ovs-dp-megaflow-stats
+    name: ovs-dp-megaflow-stats
     type: struct
     members:
       -
@@ -88,11 +86,11 @@ attribute-sets:
       -
         name: stats
         type: binary
-        struct: datapath-stats
+        struct: ovs-dp-stats
       -
         name: megaflow-stats
         type: binary
-        struct: megaflow-stats
+        struct: ovs-dp-megaflow-stats
       -
         name: user-features
         type: u32
diff --git a/Documentation/netlink/specs/ovs_vport.yaml b/Documentation/netlink/specs/ovs_vport.yaml
index 86ba9ac2a521..306da6bb842d 100644
--- a/Documentation/netlink/specs/ovs_vport.yaml
+++ b/Documentation/netlink/specs/ovs_vport.yaml
@@ -23,9 +23,8 @@ definitions:
     name-prefix: ovs-vport-type-
     entries: [ unspec, netdev, internal, gre, vxlan, geneve ]
   -
-    name: vport-stats
+    name: ovs-vport-stats
     type: struct
-    enum-name: ovs-vport-stats
     members:
       -
         name: rx-packets
@@ -106,7 +105,7 @@ attribute-sets:
       -
         name: stats
         type: binary
-        struct: vport-stats
+        struct: ovs-vport-stats
       -
         name: pad
         type: unused
@@ -123,12 +122,12 @@ attribute-sets:
 
 operations:
   name-prefix: ovs-vport-cmd-
+  fixed-header: ovs-header
   list:
     -
       name: new
       doc: Create a new OVS vport
       attribute-set: vport
-      fixed-header: ovs-header
       do:
         request:
           attributes:
@@ -141,7 +140,6 @@ operations:
       name: del
       doc: Delete existing OVS vport from a data path
       attribute-set: vport
-      fixed-header: ovs-header
       do:
         request:
           attributes:
@@ -152,7 +150,6 @@ operations:
       name: get
       doc: Get / dump OVS vport configuration and state
       attribute-set: vport
-      fixed-header: ovs-header
       do: &vport-get-op
         request:
           attributes:
diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml
index 31238455f8e9..5ec3d35b7a38 100644
--- a/Documentation/netlink/specs/rt-link.yaml
+++ b/Documentation/netlink/specs/rt-link.yaml
@@ -2,6 +2,7 @@
 
 name: rt-link
 protocol: netlink-raw
+uapi-header: linux/rtnetlink.h
 protonum: 0
 
 doc:
@@ -11,6 +12,9 @@ definitions:
   -
     name: ifinfo-flags
     type: flags
+    header: linux/if.h
+    enum-name: net-device-flags
+    name-prefix: iff-
     entries:
       -
         name: up
@@ -53,6 +57,7 @@ definitions:
   -
     name: vlan-protocols
     type: enum
+    enum-name:
     entries:
       -
         name: 8021q
@@ -299,421 +304,297 @@ definitions:
         type: u8
   -
     name: ipv4-devconf
-    type: struct
-    members:
+    enum-name:
+    type: enum
+    entries:
       -
         name: forwarding
-        type: u32
       -
         name: mc-forwarding
-        type: u32
       -
         name: proxy-arp
-        type: u32
       -
         name: accept-redirects
-        type: u32
       -
         name: secure-redirects
-        type: u32
       -
         name: send-redirects
-        type: u32
       -
         name: shared-media
-        type: u32
       -
         name: rp-filter
-        type: u32
       -
         name: accept-source-route
-        type: u32
       -
         name: bootp-relay
-        type: u32
       -
         name: log-martians
-        type: u32
       -
         name: tag
-        type: u32
       -
         name: arpfilter
-        type: u32
       -
         name: medium-id
-        type: u32
       -
         name: noxfrm
-        type: u32
       -
         name: nopolicy
-        type: u32
       -
         name: force-igmp-version
-        type: u32
       -
         name: arp-announce
-        type: u32
       -
         name: arp-ignore
-        type: u32
       -
         name: promote-secondaries
-        type: u32
       -
         name: arp-accept
-        type: u32
       -
         name: arp-notify
-        type: u32
       -
         name: accept-local
-        type: u32
       -
         name: src-vmark
-        type: u32
       -
         name: proxy-arp-pvlan
-        type: u32
       -
         name: route-localnet
-        type: u32
       -
         name: igmpv2-unsolicited-report-interval
-        type: u32
       -
         name: igmpv3-unsolicited-report-interval
-        type: u32
       -
         name: ignore-routes-with-linkdown
-        type: u32
       -
         name: drop-unicast-in-l2-multicast
-        type: u32
       -
         name: drop-gratuitous-arp
-        type: u32
       -
         name: bc-forwarding
-        type: u32
       -
         name: arp-evict-nocarrier
-        type: u32
   -
     name: ipv6-devconf
-    type: struct
-    members:
+    enum-name:
+    type: enum
+    entries:
       -
         name: forwarding
-        type: u32
       -
         name: hoplimit
-        type: u32
       -
         name: mtu6
-        type: u32
       -
         name: accept-ra
-        type: u32
       -
         name: accept-redirects
-        type: u32
       -
         name: autoconf
-        type: u32
       -
         name: dad-transmits
-        type: u32
       -
         name: rtr-solicits
-        type: u32
       -
         name: rtr-solicit-interval
-        type: u32
       -
         name: rtr-solicit-delay
-        type: u32
       -
         name: use-tempaddr
-        type: u32
       -
         name: temp-valid-lft
-        type: u32
       -
         name: temp-prefered-lft
-        type: u32
       -
         name: regen-max-retry
-        type: u32
       -
         name: max-desync-factor
-        type: u32
       -
         name: max-addresses
-        type: u32
       -
         name: force-mld-version
-        type: u32
       -
         name: accept-ra-defrtr
-        type: u32
       -
         name: accept-ra-pinfo
-        type: u32
       -
         name: accept-ra-rtr-pref
-        type: u32
       -
         name: rtr-probe-interval
-        type: u32
       -
         name: accept-ra-rt-info-max-plen
-        type: u32
       -
         name: proxy-ndp
-        type: u32
       -
         name: optimistic-dad
-        type: u32
       -
         name: accept-source-route
-        type: u32
       -
         name: mc-forwarding
-        type: u32
       -
         name: disable-ipv6
-        type: u32
       -
         name: accept-dad
-        type: u32
       -
         name: force-tllao
-        type: u32
       -
         name: ndisc-notify
-        type: u32
       -
         name: mldv1-unsolicited-report-interval
-        type: u32
       -
         name: mldv2-unsolicited-report-interval
-        type: u32
       -
         name: suppress-frag-ndisc
-        type: u32
       -
         name: accept-ra-from-local
-        type: u32
       -
         name: use-optimistic
-        type: u32
       -
         name: accept-ra-mtu
-        type: u32
       -
         name: stable-secret
-        type: u32
       -
         name: use-oif-addrs-only
-        type: u32
       -
         name: accept-ra-min-hop-limit
-        type: u32
       -
         name: ignore-routes-with-linkdown
-        type: u32
       -
         name: drop-unicast-in-l2-multicast
-        type: u32
       -
         name: drop-unsolicited-na
-        type: u32
       -
         name: keep-addr-on-down
-        type: u32
       -
         name: rtr-solicit-max-interval
-        type: u32
       -
         name: seg6-enabled
-        type: u32
       -
         name: seg6-require-hmac
-        type: u32
       -
         name: enhanced-dad
-        type: u32
       -
         name: addr-gen-mode
-        type: u8
       -
         name: disable-policy
-        type: u32
       -
         name: accept-ra-rt-info-min-plen
-        type: u32
       -
         name: ndisc-tclass
-        type: u32
       -
         name: rpl-seg-enabled
-        type: u32
       -
         name: ra-defrtr-metric
-        type: u32
       -
         name: ioam6-enabled
-        type: u32
       -
         name: ioam6-id
-        type: u32
       -
         name: ioam6-id-wide
-        type: u32
       -
         name: ndisc-evict-nocarrier
-        type: u32
       -
         name: accept-untracked-na
-        type: u32
   -
     name: ifla-icmp6-stats
-    type: struct
-    members:
+    enum-name:
+    type: enum
+    entries:
+      -
+        name: num
       -
         name: inmsgs
-        type: u64
       -
         name: inerrors
-        type: u64
       -
         name: outmsgs
-        type: u64
       -
         name: outerrors
-        type: u64
       -
         name: csumerrors
-        type: u64
       -
         name: ratelimithost
-        type: u64
   -
     name: ifla-inet6-stats
-    type: struct
-    members:
+    enum-name:
+    type: enum
+    entries:
+      -
+        name: num
       -
         name: inpkts
-        type: u64
       -
         name: inoctets
-        type: u64
       -
         name: indelivers
-        type: u64
       -
         name: outforwdatagrams
-        type: u64
       -
         name: outpkts
-        type: u64
       -
         name: outoctets
-        type: u64
       -
         name: inhdrerrors
-        type: u64
       -
         name: intoobigerrors
-        type: u64
       -
         name: innoroutes
-        type: u64
       -
         name: inaddrerrors
-        type: u64
       -
         name: inunknownprotos
-        type: u64
       -
         name: intruncatedpkts
-        type: u64
       -
         name: indiscards
-        type: u64
       -
         name: outdiscards
-        type: u64
       -
         name: outnoroutes
-        type: u64
       -
         name: reasmtimeout
-        type: u64
       -
         name: reasmreqds
-        type: u64
       -
         name: reasmoks
-        type: u64
       -
         name: reasmfails
-        type: u64
       -
         name: fragoks
-        type: u64
       -
         name: fragfails
-        type: u64
       -
         name: fragcreates
-        type: u64
       -
         name: inmcastpkts
-        type: u64
       -
         name: outmcastpkts
-        type: u64
       -
         name: inbcastpkts
-        type: u64
       -
         name: outbcastpkts
-        type: u64
       -
         name: inmcastoctets
-        type: u64
       -
         name: outmcastoctets
-        type: u64
       -
         name: inbcastoctets
-        type: u64
       -
         name: outbcastoctets
-        type: u64
       -
         name: csumerrors
-        type: u64
       -
         name: noectpkts
-        type: u64
       -
         name: ect1-pkts
-        type: u64
       -
         name: ect0-pkts
-        type: u64
       -
         name: cepkts
-        type: u64
       -
         name: reasm-overlaps
-        type: u64
   - name: br-boolopt-multi
     type: struct
+    header: linux/if_bridge.h
     members:
       -
         name: optval
@@ -754,6 +635,7 @@ definitions:
   -
     name: vlan-flags
     type: flags
+    enum-name:
     entries:
       - reorder-hdr
       - gvrp
@@ -840,6 +722,7 @@ definitions:
   -
     name: ifla-vf-link-state-enum
     type: enum
+    enum-name:
     entries:
       - auto
       - enable
@@ -906,6 +789,7 @@ definitions:
   -
     name: rtext-filter
     type: flags
+    enum-name:
     entries:
       - vf
       - brvlan
@@ -918,6 +802,7 @@ definitions:
   -
     name: netkit-policy
     type: enum
+    enum-name:
     entries:
       -
         name: forward
@@ -928,6 +813,7 @@ definitions:
   -
     name: netkit-mode
     type: enum
+    enum-name: netkit-mode
     entries:
       - name: l2
       - name: l3
@@ -935,9 +821,18 @@ definitions:
   -
     name: netkit-scrub
     type: enum
+    enum-name:
     entries:
       - name: none
       - name: default
+  -
+    name: ovpn-mode
+    enum-name: ovpn-mode
+    name-prefix: ovpn-mode
+    type: enum
+    entries:
+      - p2p
+      - mp
 
 attribute-sets:
   -
@@ -1113,11 +1008,10 @@ attribute-sets:
       -
         name: prop-list
         type: nest
-        nested-attributes: link-attrs
+        nested-attributes: prop-list-link-attrs
       -
         name: alt-ifname
         type: string
-        multi-attr: true
       -
         name: perm-address
         type: binary
@@ -1164,25 +1058,35 @@ attribute-sets:
         name: netns-immutable
         type: u8
   -
+    name: prop-list-link-attrs
+    subset-of: link-attrs
+    attributes:
+      -
+        name: alt-ifname
+        multi-attr: true
+  -
     name: af-spec-attrs
+    name-prefix: af-
+    attr-max-name: af-max
     attributes:
       -
-        name: "inet"
+        name: inet
         type: nest
         value: 2
         nested-attributes: ifla-attrs
       -
-        name: "inet6"
+        name: inet6
         type: nest
         value: 10
         nested-attributes: ifla6-attrs
       -
-        name: "mctp"
+        name: mctp
         type: nest
         value: 45
         nested-attributes: mctp-attrs
   -
     name: vfinfo-list-attrs
+    name-prefix: ifla-vf-
     attributes:
       -
         name: info
@@ -1191,6 +1095,7 @@ attribute-sets:
         multi-attr: true
   -
     name: vfinfo-attrs
+    name-prefix: ifla-vf-
     attributes:
       -
         name: mac
@@ -1245,6 +1150,7 @@ attribute-sets:
         type: binary
   -
     name: vf-stats-attrs
+    name-prefix: ifla-vf-stats-
     attributes:
       -
         name: rx-packets
@@ -1276,6 +1182,8 @@ attribute-sets:
         type: u64
   -
     name: vf-vlan-attrs
+    name-prefix: ifla-vf-vlan-
+    attr-max-name: ifla-vf-vlan-info-max
     attributes:
       -
         name: info
@@ -1284,12 +1192,15 @@ attribute-sets:
         multi-attr: true
   -
     name: vf-ports-attrs
+    name-prefix: ifla-
     attributes: []
   -
     name: port-self-attrs
+    name-prefix: ifla-
     attributes: []
   -
     name: linkinfo-attrs
+    name-prefix: ifla-info-
     attributes:
       -
         name: kind
@@ -1414,6 +1325,8 @@ attribute-sets:
         type: indexed-array
         sub-type: binary
         display-hint: ipv6
+        checks:
+          exact-len: 16
       -
         name: coupled-control
         type: u8
@@ -1585,7 +1498,7 @@ attribute-sets:
         name: nf-call-iptables
         type: u8
       -
-        name: nf-call-ip6-tables
+        name: nf-call-ip6tables
         type: u8
       -
         name: nf-call-arptables
@@ -1843,6 +1756,7 @@ attribute-sets:
   -
     name: linkinfo-vti-attrs
     name-prefix: ifla-vti-
+    header: linux/if_tunnel.h
     attributes:
       -
         name: link
@@ -2077,7 +1991,7 @@ attribute-sets:
         name: id
         type: u16
       -
-        name: flag
+        name: flags
         type: binary
         struct: ifla-vlan-flags
       -
@@ -2095,7 +2009,7 @@ attribute-sets:
         byte-order: big-endian
   -
     name: ifla-vlan-qos
-    name-prefix: ifla-vlan-qos
+    name-prefix: ifla-vlan-qos-
     attributes:
       -
         name: mapping
@@ -2111,6 +2025,7 @@ attribute-sets:
         type: u32
   -
     name: xdp-attrs
+    name-prefix: ifla-xdp-
     attributes:
       -
         name: fd
@@ -2138,13 +2053,16 @@ attribute-sets:
         type: s32
   -
     name: ifla-attrs
+    name-prefix: ifla-inet-
     attributes:
       -
         name: conf
         type: binary
-        struct: ipv4-devconf
+        sub-type: u32
+        doc: u32 indexed by ipv4-devconf - 1 on output, on input it's a nest
   -
     name: ifla6-attrs
+    name-prefix: ifla-inet6-
     attributes:
       -
         name: flags
@@ -2152,11 +2070,12 @@ attribute-sets:
       -
         name: conf
         type: binary
-        struct: ipv6-devconf
+        sub-type: u32
+        doc: u32 indexed by ipv6-devconf - 1 on output, on input it's a nest
       -
         name: stats
         type: binary
-        struct: ifla-inet6-stats
+        sub-type: u64
       -
         name: mcast
         type: binary
@@ -2165,9 +2084,9 @@ attribute-sets:
         type: binary
         struct: ifla-cacheinfo
       -
-        name: icmp6-stats
+        name: icmp6stats
         type: binary
-        struct: ifla-icmp6-stats
+        sub-type: u64
       -
         name: token
         type: binary
@@ -2179,9 +2098,10 @@ attribute-sets:
         type: u32
   -
     name: mctp-attrs
+    name-prefix: ifla-mctp-
     attributes:
       -
-        name: mctp-net
+        name: net
         type: u32
       -
         name: phys-binding
@@ -2209,6 +2129,7 @@ attribute-sets:
         type: binary
   -
     name: link-offload-xstats
+    name-prefix: ifla-offload-xstats-
     attributes:
       -
         name: cpu-hit
@@ -2223,6 +2144,7 @@ attribute-sets:
         type: binary
   -
     name: hw-s-info-one
+    name-prefix: ifla-offload-xstats-hw-s-info-
     attributes:
       -
         name: request
@@ -2232,6 +2154,8 @@ attribute-sets:
         type: u8
   -
     name: link-dpll-pin-attrs
+    name-prefix: dpll-a-
+    header: linux/dpll.h
     attributes:
       -
         name: id
@@ -2272,6 +2196,14 @@ attribute-sets:
       -
         name: tailroom
         type: u16
+  -
+    name: linkinfo-ovpn-attrs
+    name-prefix: ifla-ovpn-
+    attributes:
+      -
+        name: mode
+        type: u8
+        enum: ovpn-mode
 
 sub-messages:
   -
@@ -2322,6 +2254,9 @@ sub-messages:
       -
         value: netkit
         attribute-set: linkinfo-netkit-attrs
+      -
+        value: ovpn
+        attribute-set: linkinfo-ovpn-attrs
   -
     name: linkinfo-member-data-msg
     formats:
@@ -2334,6 +2269,7 @@ sub-messages:
 
 operations:
   enum-model: directional
+  name-prefix: rtm-
   list:
     -
       name: newlink
@@ -2344,7 +2280,6 @@ operations:
         request:
           value: 16
           attributes: &link-new-attrs
-            - ifi-index
             - ifname
             - net-ns-pid
             - net-ns-fd
@@ -2360,7 +2295,6 @@ operations:
             - txqlen
             - operstate
             - linkmode
-            - group
             - gso-max-size
             - gso-max-segs
             - gro-max-size
@@ -2368,6 +2302,12 @@ operations:
             - gro-ipv4-max-size
             - af-spec
     -
+      name: newlink-ntf
+      doc: Notify that a link has been created
+      value: 16
+      notify: getlink
+      fixed-header: ifinfomsg
+    -
       name: dellink
       doc: Delete an existing link.
       attribute-set: link-attrs
@@ -2376,7 +2316,6 @@ operations:
         request:
           value: 17
           attributes:
-            - ifi-index
             - ifname
     -
       name: getlink
@@ -2387,7 +2326,6 @@ operations:
         request:
           value: 18
           attributes:
-            - ifi-index
             - ifname
             - alt-ifname
             - ext-mask
@@ -2395,11 +2333,6 @@ operations:
         reply:
           value: 16
           attributes: &link-all-attrs
-            - ifi-family
-            - ifi-type
-            - ifi-index
-            - ifi-flags
-            - ifi-change
             - address
             - broadcast
             - ifname
@@ -2445,7 +2378,6 @@ operations:
             - xdp
             - event
             - new-netnsid
-            - if-netnsid
             - target-netnsid
             - carrier-up-count
             - carrier-down-count
@@ -2453,7 +2385,6 @@ operations:
             - min-mtu
             - max-mtu
             - prop-list
-            - alt-ifname
             - perm-address
             - proto-down-reason
             - parent-dev-name
@@ -2493,14 +2424,9 @@ operations:
       do:
         request:
           value: 94
-          attributes:
-            - ifindex
         reply:
           value: 92
           attributes: &link-stats-attrs
-            - family
-            - ifindex
-            - filter-mask
             - link-64
             - link-xstats
             - link-xstats-slave
diff --git a/Documentation/netlink/specs/rt-neigh.yaml b/Documentation/netlink/specs/rt-neigh.yaml
index e670b6dc07be..e9cba164e3d1 100644
--- a/Documentation/netlink/specs/rt-neigh.yaml
+++ b/Documentation/netlink/specs/rt-neigh.yaml
@@ -2,6 +2,7 @@
 
 name: rt-neigh
 protocol: netlink-raw
+uapi-header: linux/rtnetlink.h
 protonum: 0
 
 doc:
@@ -13,25 +14,25 @@ definitions:
     type: struct
     members:
       -
-        name: family
+        name: ndm-family
         type: u8
       -
-        name: pad
+        name: ndm-pad
         type: pad
         len: 3
       -
-        name: ifindex
+        name: ndm-ifindex
         type: s32
       -
-        name: state
+        name: ndm-state
         type: u16
         enum: nud-state
       -
-        name: flags
+        name: ndm-flags
         type: u8
         enum: ntf-flags
       -
-        name: type
+        name: ndm-type
         type: u8
         enum: rtm-type
   -
@@ -48,6 +49,7 @@ definitions:
   -
     name: nud-state
     type: flags
+    enum-name:
     entries:
       - incomplete
       - reachable
@@ -60,6 +62,7 @@ definitions:
   -
     name: ntf-flags
     type: flags
+    enum-name:
     entries:
       - use
       - self
@@ -72,12 +75,14 @@ definitions:
   -
     name: ntf-ext-flags
     type: flags
+    enum-name:
     entries:
       - managed
       - locked
   -
     name: rtm-type
     type: enum
+    enum-name:
     entries:
       - unspec
       - unicast
@@ -179,6 +184,7 @@ definitions:
 attribute-sets:
   -
     name: neighbour-attrs
+    name-prefix: nda-
     attributes:
       -
         name: unspec
@@ -189,7 +195,7 @@ attribute-sets:
         type: binary
         display-hint: ipv4
       -
-        name: lladr
+        name: lladdr
         type: binary
         display-hint: mac
       -
@@ -241,6 +247,7 @@ attribute-sets:
         type: u8
   -
     name: ndt-attrs
+    name-prefix: ndta-
     attributes:
       -
         name: name
@@ -274,6 +281,7 @@ attribute-sets:
         type: pad
   -
     name: ndtpa-attrs
+    name-prefix: ndtpa-
     attributes:
       -
         name: ifindex
@@ -335,6 +343,7 @@ attribute-sets:
 
 operations:
   enum-model: directional
+  name-prefix: rtm-
   list:
     -
       name: newneigh
@@ -372,7 +381,7 @@ operations:
       name: delneigh-ntf
       doc: Notify a neighbour deletion
       value: 29
-      notify: delneigh
+      notify: getneigh
       fixed-header: ndmsg
     -
       name: getneigh
@@ -393,6 +402,7 @@ operations:
             - ifindex
             - master
         reply:
+          value: 28
           attributes: *neighbour-all
     -
       name: newneigh-ntf
diff --git a/Documentation/netlink/specs/rt-rule.yaml b/Documentation/netlink/specs/rt-rule.yaml
index de0938d36541..003707ca4a3e 100644
--- a/Documentation/netlink/specs/rt-rule.yaml
+++ b/Documentation/netlink/specs/rt-rule.yaml
@@ -2,6 +2,7 @@
 
 name: rt-rule
 protocol: netlink-raw
+uapi-header: linux/fib_rules.h
 protonum: 0
 
 doc:
@@ -56,6 +57,7 @@ definitions:
   -
     name: fr-act
     type: enum
+    enum-name:
     entries:
       - unspec
       - to-tbl
@@ -90,6 +92,7 @@ definitions:
 attribute-sets:
   -
     name: fib-rule-attrs
+    name-prefix: fra-
     attributes:
       -
         name: dst
@@ -198,6 +201,7 @@ attribute-sets:
 operations:
   enum-model: directional
   fixed-header: fib-rule-hdr
+  name-prefix: rtm-
   list:
     -
       name: newrule
@@ -234,7 +238,7 @@ operations:
       name: newrule-ntf
       doc: Notify a rule creation
       value: 32
-      notify: newrule
+      notify: getrule
     -
       name: delrule
       doc: Remove an existing FIB rule
@@ -247,7 +251,7 @@ operations:
       name: delrule-ntf
       doc: Notify a rule deletion
       value: 33
-      notify: delrule
+      notify: getrule
     -
       name: getrule
       doc: Dump all FIB rules
diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml
index aacccea5dfe4..cb7ea7d62e56 100644
--- a/Documentation/netlink/specs/tc.yaml
+++ b/Documentation/netlink/specs/tc.yaml
@@ -2,6 +2,7 @@
 
 name: tc
 protocol: netlink-raw
+uapi-header: linux/pkt_cls.h
 protonum: 0
 
 doc:
@@ -12,6 +13,7 @@ definitions:
   -
     name: tcmsg
     type: struct
+    header: linux/rtnetlink.h
     members:
       -
         name: family
@@ -33,7 +35,8 @@ definitions:
         name: info
         type: u32
   -
-    name: tc-cls-flags
+    name: cls-flags
+    enum-name:
     type: flags
     entries:
       - skip-hw
@@ -42,7 +45,9 @@ definitions:
       - not-in-nw
       - verbose
   -
-    name: tc-flower-key-ctrl-flags
+    name: flower-key-ctrl-flags
+    name-prefix: tca-flower-key-flags-
+    enum-name:
     type: flags
     entries:
       - frag
@@ -630,6 +635,7 @@ definitions:
   -
     name: tc-ratespec
     type: struct
+    header: linux/pkt_sched.h
     members:
       -
         name: cell-log
@@ -1186,7 +1192,7 @@ definitions:
         name: firstuse
         type: u64
   -
-    name: tc-gen
+    name: tc-gact
     type: struct
     members:
       -
@@ -1377,7 +1383,8 @@ definitions:
         type: s32
 attribute-sets:
   -
-    name: tc-attrs
+    name: attrs
+    name-prefix: tca-
     attributes:
       -
         name: kind
@@ -1385,7 +1392,7 @@ attribute-sets:
       -
         name: options
         type: sub-message
-        sub-message: tc-options-msg
+        sub-message: options-msg
         selector: kind
       -
         name: stats
@@ -1436,7 +1443,8 @@ attribute-sets:
         name: ext-warn-msg
         type: string
   -
-    name: tc-act-attrs
+    name: act-attrs
+    name-prefix: tca-act-
     attributes:
       -
         name: kind
@@ -1444,7 +1452,7 @@ attribute-sets:
       -
         name: options
         type: sub-message
-        sub-message: tc-act-options-msg
+        sub-message: act-options-msg
         selector: kind
       -
         name: index
@@ -1452,7 +1460,7 @@ attribute-sets:
       -
         name: stats
         type: nest
-        nested-attributes: tc-act-stats-attrs
+        nested-attributes: tca-stats-attrs
       -
         name: pad
         type: pad
@@ -1472,39 +1480,9 @@ attribute-sets:
         name: in-hw-count
         type: u32
   -
-    name: tc-act-stats-attrs
-    attributes:
-      -
-        name: basic
-        type: binary
-        struct: gnet-stats-basic
-      -
-        name: rate-est
-        type: binary
-        struct: gnet-stats-rate-est
-      -
-        name: queue
-        type: binary
-        struct: gnet-stats-queue
-      -
-        name: app
-        type: binary
-      -
-        name: rate-est64
-        type: binary
-        struct: gnet-stats-rate-est64
-      -
-        name: pad
-        type: pad
-      -
-        name: basic-hw
-        type: binary
-        struct: gnet-stats-basic
-      -
-        name: pkt64
-        type: u64
-  -
-    name: tc-act-bpf-attrs
+    name: act-bpf-attrs
+    name-prefix: tca-act-bpf-
+    header: linux/tc_act/tc_bpf.h
     attributes:
       -
         name: tm
@@ -1535,7 +1513,9 @@ attribute-sets:
         name: id
         type: binary
   -
-    name: tc-act-connmark-attrs
+    name: act-connmark-attrs
+    name-prefix: tca-connmark-
+    header: linux/tc_act/tc_connmark.h
     attributes:
       -
         name: parms
@@ -1548,7 +1528,9 @@ attribute-sets:
         name: pad
         type: pad
   -
-    name: tc-act-csum-attrs
+    name: act-csum-attrs
+    name-prefix: tca-csum-
+    header: linux/tc_act/tc_csum.h
     attributes:
       -
         name: parms
@@ -1561,7 +1543,9 @@ attribute-sets:
         name: pad
         type: pad
   -
-    name: tc-act-ct-attrs
+    name: act-ct-attrs
+    name-prefix: tca-ct-
+    header: linux/tc_act/tc_ct.h
     attributes:
       -
         name: parms
@@ -1623,7 +1607,9 @@ attribute-sets:
         name: helper-proto
         type: u8
   -
-    name: tc-act-ctinfo-attrs
+    name: act-ctinfo-attrs
+    name-prefix: tca-ctinfo-
+    header: linux/tc_act/tc_ctinfo.h
     attributes:
       -
         name: pad
@@ -1657,7 +1643,9 @@ attribute-sets:
         name: stats-cpmark-set
         type: u64
   -
-    name: tc-act-gate-attrs
+    name: act-gate-attrs
+    name-prefix: tca-gate-
+    header: linux/tc_act/tc_gate.h
     attributes:
       -
         name: tm
@@ -1691,7 +1679,9 @@ attribute-sets:
         name: clockid
         type: s32
   -
-    name: tc-act-ife-attrs
+    name: act-ife-attrs
+    name-prefix: tca-ife-
+    header: linux/tc_act/tc_ife.h
     attributes:
       -
         name: parms
@@ -1716,7 +1706,9 @@ attribute-sets:
         name: pad
         type: pad
   -
-    name: tc-act-mirred-attrs
+    name: act-mirred-attrs
+    name-prefix: tca-mirred-
+    header: linux/tc_act/tc_mirred.h
     attributes:
       -
         name: tm
@@ -1732,7 +1724,9 @@ attribute-sets:
         name: blockid
         type: binary
   -
-    name: tc-act-mpls-attrs
+    name: act-mpls-attrs
+    name-prefix: tca-mpls-
+    header: linux/tc_act/tc_mpls.h
     attributes:
       -
         name: tm
@@ -1762,7 +1756,9 @@ attribute-sets:
         name: bos
         type: u8
   -
-    name: tc-act-nat-attrs
+    name: act-nat-attrs
+    name-prefix: tca-nat-
+    header: linux/tc_act/tc_nat.h
     attributes:
       -
         name: parms
@@ -1775,7 +1771,9 @@ attribute-sets:
         name: pad
         type: pad
   -
-    name: tc-act-pedit-attrs
+    name: act-pedit-attrs
+    name-prefix: tca-pedit-
+    header: linux/tc_act/tc_pedit.h
     attributes:
       -
         name: tm
@@ -1798,45 +1796,9 @@ attribute-sets:
         name: key-ex
         type: binary
   -
-    name: tc-act-police-attrs
-    attributes:
-      -
-        name: tbf
-        type: binary
-        struct: tc-police
-      -
-        name: rate
-        type: binary # TODO
-      -
-        name: peakrate
-        type: binary # TODO
-      -
-        name: avrate
-        type: u32
-      -
-        name: result
-        type: u32
-      -
-        name: tm
-        type: binary
-        struct: tcf-t
-      -
-        name: pad
-        type: pad
-      -
-        name: rate64
-        type: u64
-      -
-        name: peakrate64
-        type: u64
-      -
-        name: pktrate64
-        type: u64
-      -
-        name: pktburst64
-        type: u64
-  -
-    name: tc-act-simple-attrs
+    name: act-simple-attrs
+    name-prefix: tca-def-
+    header: linux/tc_act/tc_defact.h
     attributes:
       -
         name: tm
@@ -1852,7 +1814,9 @@ attribute-sets:
         name: pad
         type: pad
   -
-    name: tc-act-skbedit-attrs
+    name: act-skbedit-attrs
+    name-prefix: tca-skbedit-
+    header: linux/tc_act/tc_skbedit.h
     attributes:
       -
         name: tm
@@ -1886,7 +1850,9 @@ attribute-sets:
         name: queue-mapping-max
         type: u16
   -
-    name: tc-act-skbmod-attrs
+    name: act-skbmod-attrs
+    name-prefix: tca-skbmod-
+    header: linux/tc_act/tc_skbmod.h
     attributes:
       -
         name: tm
@@ -1908,7 +1874,9 @@ attribute-sets:
         name: pad
         type: pad
   -
-    name: tc-act-tunnel-key-attrs
+    name: act-tunnel-key-attrs
+    name-prefix: tca-tunnel-key-
+    header: linux/tc_act/tc_tunnel_key.h
     attributes:
       -
         name: tm
@@ -1958,7 +1926,9 @@ attribute-sets:
         name: no-frag
         type: flag
   -
-    name: tc-act-vlan-attrs
+    name: act-vlan-attrs
+    name-prefix: tca-vlan-
+    header: linux/tc_act/tc_vlan.h
     attributes:
       -
         name: tm
@@ -1987,7 +1957,8 @@ attribute-sets:
         name: push-eth-src
         type: binary
   -
-    name: tc-basic-attrs
+    name: basic-attrs
+    name-prefix: tca-basic-
     attributes:
       -
         name: classid
@@ -1995,16 +1966,16 @@ attribute-sets:
       -
         name: ematches
         type: nest
-        nested-attributes: tc-ematch-attrs
+        nested-attributes: ematch-attrs
       -
         name: act
         type: indexed-array
         sub-type: nest
-        nested-attributes: tc-act-attrs
+        nested-attributes: act-attrs
       -
         name: police
         type: nest
-        nested-attributes: tc-police-attrs
+        nested-attributes: police-attrs
       -
         name: pcnt
         type: binary
@@ -2013,16 +1984,18 @@ attribute-sets:
         name: pad
         type: pad
   -
-    name: tc-bpf-attrs
+    name: bpf-attrs
+    name-prefix: tca-bpf-
     attributes:
       -
         name: act
-        type: nest
-        nested-attributes: tc-act-attrs
+        type: indexed-array
+        sub-type: nest
+        nested-attributes: act-attrs
       -
         name: police
         type: nest
-        nested-attributes: tc-police-attrs
+        nested-attributes: police-attrs
       -
         name: classid
         type: u32
@@ -2051,7 +2024,8 @@ attribute-sets:
         name: id
         type: u32
   -
-    name: tc-cake-attrs
+    name: cake-attrs
+    name-prefix: tca-cake-
     attributes:
       -
         name: pad
@@ -2108,7 +2082,8 @@ attribute-sets:
         name: fwmark
         type: u32
   -
-    name: tc-cake-stats-attrs
+    name: cake-stats-attrs
+    name-prefix: tca-cake-stats-
     attributes:
       -
         name: pad
@@ -2141,7 +2116,7 @@ attribute-sets:
         name: tin-stats
         type: indexed-array
         sub-type: nest
-        nested-attributes: tc-cake-tin-stats-attrs
+        nested-attributes: cake-tin-stats-attrs
       -
         name: deficit
         type: s32
@@ -2161,7 +2136,8 @@ attribute-sets:
         name: blue-timer-us
         type: s32
   -
-    name: tc-cake-tin-stats-attrs
+    name: cake-tin-stats-attrs
+    name-prefix: tca-cake-tin-stats-
     attributes:
       -
         name: pad
@@ -2239,28 +2215,32 @@ attribute-sets:
         name: flow-quantum
         type: u32
   -
-    name: tc-cbs-attrs
+    name: cbs-attrs
+    name-prefix: tca-cbs-
     attributes:
       -
         name: parms
         type: binary
         struct: tc-cbs-qopt
   -
-    name: tc-cgroup-attrs
+    name: cgroup-attrs
+    name-prefix: tca-cgroup-
     attributes:
       -
         name: act
-        type: nest
-        nested-attributes: tc-act-attrs
+        type: indexed-array
+        sub-type: nest
+        nested-attributes: act-attrs
       -
         name: police
         type: nest
-        nested-attributes: tc-police-attrs
+        nested-attributes: police-attrs
       -
         name: ematches
         type: binary
   -
-    name: tc-choke-attrs
+    name: choke-attrs
+    name-prefix: tca-choke-
     attributes:
       -
         name: parms
@@ -2276,7 +2256,8 @@ attribute-sets:
         name: max-p
         type: u32
   -
-    name: tc-codel-attrs
+    name: codel-attrs
+    name-prefix: tca-codel-
     attributes:
       -
         name: target
@@ -2294,13 +2275,16 @@ attribute-sets:
         name: ce-threshold
         type: u32
   -
-    name: tc-drr-attrs
+    name: drr-attrs
+    name-prefix: tca-drr-
     attributes:
       -
         name: quantum
         type: u32
   -
-    name: tc-ematch-attrs
+    name: ematch-attrs
+    name-prefix: tca-ematch-
+    attr-max-name: tca-ematch-tree-max
     attributes:
       -
         name: tree-hdr
@@ -2310,7 +2294,8 @@ attribute-sets:
         name: tree-list
         type: binary
   -
-    name: tc-flow-attrs
+    name: flow-attrs
+    name-prefix: tca-flow-
     attributes:
       -
         name: keys
@@ -2342,7 +2327,7 @@ attribute-sets:
       -
         name: police
         type: nest
-        nested-attributes: tc-police-attrs
+        nested-attributes: police-attrs
       -
         name: ematches
         type: binary
@@ -2350,7 +2335,8 @@ attribute-sets:
         name: perturb
         type: u32
   -
-    name: tc-flower-attrs
+    name: flower-attrs
+    name-prefix: tca-flower-
     attributes:
       -
         name: classid
@@ -2362,7 +2348,7 @@ attribute-sets:
         name: act
         type: indexed-array
         sub-type: nest
-        nested-attributes: tc-act-attrs
+        nested-attributes: act-attrs
       -
         name: key-eth-dst
         type: binary
@@ -2441,7 +2427,7 @@ attribute-sets:
       -
         name: flags
         type: u32
-        enum: tc-cls-flags
+        enum: cls-flags
         enum-as-flags: true
       -
         name: key-vlan-id
@@ -2546,13 +2532,13 @@ attribute-sets:
         name: key-flags
         type: u32
         byte-order: big-endian
-        enum: tc-flower-key-ctrl-flags
+        enum: flower-key-ctrl-flags
         enum-as-flags: true
       -
         name: key-flags-mask
         type: u32
         byte-order: big-endian
-        enum: tc-flower-key-ctrl-flags
+        enum: flower-key-ctrl-flags
         enum-as-flags: true
       -
         name: key-icmpv4-code
@@ -2675,11 +2661,11 @@ attribute-sets:
       -
         name: key-enc-opts
         type: nest
-        nested-attributes: tc-flower-key-enc-opts-attrs
+        nested-attributes: flower-key-enc-opts-attrs
       -
         name: key-enc-opts-mask
         type: nest
-        nested-attributes: tc-flower-key-enc-opts-attrs
+        nested-attributes: flower-key-enc-opts-attrs
       -
         name: in-hw-count
         type: u32
@@ -2726,7 +2712,7 @@ attribute-sets:
       -
         name: key-mpls-opts
         type: nest
-        nested-attributes: tc-flower-key-mpls-opt-attrs
+        nested-attributes: flower-key-mpls-opt-attrs
       -
         name: key-hash
         type: u32
@@ -2745,7 +2731,7 @@ attribute-sets:
         type: u16
         byte-order: big-endian
       -
-        name: key-l2-tpv3-sid
+        name: key-l2tpv3-sid
         type: u32
         byte-order: big-endian
       -
@@ -2754,7 +2740,7 @@ attribute-sets:
       -
         name: key-cfm
         type: nest
-        nested-attributes: tc-flower-key-cfm-attrs
+        nested-attributes: flower-key-cfm-attrs
       -
         name: key-spi
         type: u32
@@ -2767,35 +2753,37 @@ attribute-sets:
         name: key-enc-flags
         type: u32
         byte-order: big-endian
-        enum: tc-flower-key-ctrl-flags
+        enum: flower-key-ctrl-flags
         enum-as-flags: true
       -
         name: key-enc-flags-mask
         type: u32
         byte-order: big-endian
-        enum: tc-flower-key-ctrl-flags
+        enum: flower-key-ctrl-flags
         enum-as-flags: true
   -
-    name: tc-flower-key-enc-opts-attrs
+    name: flower-key-enc-opts-attrs
+    name-prefix: tca-flower-key-enc-opts-
     attributes:
       -
         name: geneve
         type: nest
-        nested-attributes: tc-flower-key-enc-opt-geneve-attrs
+        nested-attributes: flower-key-enc-opt-geneve-attrs
       -
         name: vxlan
         type: nest
-        nested-attributes: tc-flower-key-enc-opt-vxlan-attrs
+        nested-attributes: flower-key-enc-opt-vxlan-attrs
       -
         name: erspan
         type: nest
-        nested-attributes: tc-flower-key-enc-opt-erspan-attrs
+        nested-attributes: flower-key-enc-opt-erspan-attrs
       -
         name: gtp
         type: nest
-        nested-attributes: tc-flower-key-enc-opt-gtp-attrs
+        nested-attributes: flower-key-enc-opt-gtp-attrs
   -
-    name: tc-flower-key-enc-opt-geneve-attrs
+    name: flower-key-enc-opt-geneve-attrs
+    name-prefix: tca-flower-key-enc-opt-geneve-
     attributes:
       -
         name: class
@@ -2807,13 +2795,15 @@ attribute-sets:
         name: data
         type: binary
   -
-    name: tc-flower-key-enc-opt-vxlan-attrs
+    name: flower-key-enc-opt-vxlan-attrs
+    name-prefix: tca-flower-key-enc-opt-vxlan-
     attributes:
       -
         name: gbp
         type: u32
   -
-    name: tc-flower-key-enc-opt-erspan-attrs
+    name: flower-key-enc-opt-erspan-attrs
+    name-prefix: tca-flower-key-enc-opt-erspan-
     attributes:
       -
         name: ver
@@ -2828,7 +2818,8 @@ attribute-sets:
         name: hwid
         type: u8
   -
-    name: tc-flower-key-enc-opt-gtp-attrs
+    name: flower-key-enc-opt-gtp-attrs
+    name-prefix: tca-flower-key-enc-opt-gtp-
     attributes:
       -
         name: pdu-type
@@ -2837,7 +2828,9 @@ attribute-sets:
         name: qfi
         type: u8
   -
-    name: tc-flower-key-mpls-opt-attrs
+    name: flower-key-mpls-opt-attrs
+    name-prefix: tca-flower-key-mpls-opt-
+    attr-max-name: tca-flower-key-mpls-opt-lse-max
     attributes:
       -
         name: lse-depth
@@ -2855,7 +2848,8 @@ attribute-sets:
         name: lse-label
         type: u32
   -
-    name: tc-flower-key-cfm-attrs
+    name: flower-key-cfm-attrs
+    name-prefix: tca-flower-key-cfm-
     attributes:
       -
         name: md-level
@@ -2864,7 +2858,8 @@ attribute-sets:
         name: opcode
         type: u8
   -
-    name: tc-fw-attrs
+    name: fw-attrs
+    name-prefix: tca-fw-
     attributes:
       -
         name: classid
@@ -2872,7 +2867,7 @@ attribute-sets:
       -
         name: police
         type: nest
-        nested-attributes: tc-police-attrs
+        nested-attributes: police-attrs
       -
         name: indev
         type: string
@@ -2880,12 +2875,13 @@ attribute-sets:
         name: act
         type: indexed-array
         sub-type: nest
-        nested-attributes: tc-act-attrs
+        nested-attributes: act-attrs
       -
         name: mask
         type: u32
   -
-    name: tc-gred-attrs
+    name: gred-attrs
+    name-prefix: tca-gred-
     attributes:
       -
         name: parms
@@ -2911,6 +2907,7 @@ attribute-sets:
         nested-attributes: tca-gred-vq-list-attrs
   -
     name: tca-gred-vq-list-attrs
+    name-prefix: tca-gred-vq-
     attributes:
       -
         name: entry
@@ -2919,6 +2916,7 @@ attribute-sets:
         multi-attr: true
   -
     name: tca-gred-vq-entry-attrs
+    name-prefix: tca-gred-vq-
     attributes:
       -
         name: pad
@@ -2957,7 +2955,7 @@ attribute-sets:
         name: flags
         type: u32
   -
-    name: tc-hfsc-attrs
+    name: hfsc-attrs
     attributes:
       -
         name: rsc
@@ -2969,7 +2967,8 @@ attribute-sets:
         name: usc
         type: binary
   -
-    name: tc-hhf-attrs
+    name: hhf-attrs
+    name-prefix: tca-hhf-
     attributes:
       -
         name: backlog-limit
@@ -2993,7 +2992,8 @@ attribute-sets:
         name: non-hh-weight
         type: u32
   -
-    name: tc-htb-attrs
+    name: htb-attrs
+    name-prefix: tca-htb-
     attributes:
       -
         name: parms
@@ -3025,7 +3025,8 @@ attribute-sets:
         name: offload
         type: flag
   -
-    name: tc-matchall-attrs
+    name: matchall-attrs
+    name-prefix: tca-matchall-
     attributes:
       -
         name: classid
@@ -3034,7 +3035,7 @@ attribute-sets:
         name: act
         type: indexed-array
         sub-type: nest
-        nested-attributes: tc-act-attrs
+        nested-attributes: act-attrs
       -
         name: flags
         type: u32
@@ -3046,14 +3047,16 @@ attribute-sets:
         name: pad
         type: pad
   -
-    name: tc-etf-attrs
+    name: etf-attrs
+    name-prefix: tca-etf-
     attributes:
       -
         name: parms
         type: binary
         struct: tc-etf-qopt
   -
-    name: tc-ets-attrs
+    name: ets-attrs
+    name-prefix: tca-ets-
     attributes:
       -
         name: nbands
@@ -3064,7 +3067,7 @@ attribute-sets:
       -
         name: quanta
         type: nest
-        nested-attributes: tc-ets-attrs
+        nested-attributes: ets-attrs
       -
         name: quanta-band
         type: u32
@@ -3072,13 +3075,14 @@ attribute-sets:
       -
         name: priomap
         type: nest
-        nested-attributes: tc-ets-attrs
+        nested-attributes: ets-attrs
       -
         name: priomap-band
         type: u8
         multi-attr: true
   -
-    name: tc-fq-attrs
+    name: fq-attrs
+    name-prefix: tca-fq-
     attributes:
       -
         name: plimit
@@ -3149,7 +3153,8 @@ attribute-sets:
         sub-type: s32
         doc: Weights for each band
   -
-    name: tc-fq-codel-attrs
+    name: fq-codel-attrs
+    name-prefix: tca-fq-codel-
     attributes:
       -
         name: target
@@ -3185,7 +3190,8 @@ attribute-sets:
         name: ce-threshold-mask
         type: u8
   -
-    name: tc-fq-pie-attrs
+    name: fq-pie-attrs
+    name-prefix: tca-fq-pie-
     attributes:
       -
         name: limit
@@ -3224,7 +3230,8 @@ attribute-sets:
         name: dq-rate-estimator
         type: u32
   -
-    name: tc-netem-attrs
+    name: netem-attrs
+    name-prefix: tca-netem-
     attributes:
       -
         name: corr
@@ -3245,7 +3252,7 @@ attribute-sets:
       -
         name: loss
         type: nest
-        nested-attributes: tc-netem-loss-attrs
+        nested-attributes: netem-loss-attrs
       -
         name: rate
         type: binary
@@ -3277,7 +3284,8 @@ attribute-sets:
         name: prng-seed
         type: u64
   -
-    name: tc-netem-loss-attrs
+    name: netem-loss-attrs
+    name-prefix: netem-loss-
     attributes:
       -
         name: gi
@@ -3290,7 +3298,8 @@ attribute-sets:
         doc: Gilbert Elliot models
         struct: tc-netem-gemodel
   -
-    name: tc-pie-attrs
+    name: pie-attrs
+    name-prefix: tca-pie-
     attributes:
       -
         name: target
@@ -3317,7 +3326,8 @@ attribute-sets:
         name: dq-rate-estimator
         type: u32
   -
-    name: tc-police-attrs
+    name: police-attrs
+    name-prefix: tca-police-
     attributes:
       -
         name: tbf
@@ -3325,10 +3335,10 @@ attribute-sets:
         struct: tc-police
       -
         name: rate
-        type: binary
+        type: binary # TODO
       -
         name: peakrate
-        type: binary
+        type: binary # TODO
       -
         name: avrate
         type: u32
@@ -3355,7 +3365,8 @@ attribute-sets:
         name: pktburst64
         type: u64
   -
-    name: tc-qfq-attrs
+    name: qfq-attrs
+    name-prefix: tca-qfq-
     attributes:
       -
         name: weight
@@ -3364,7 +3375,8 @@ attribute-sets:
         name: lmax
         type: u32
   -
-    name: tc-red-attrs
+    name: red-attrs
+    name-prefix: tca-red-
     attributes:
       -
         name: parms
@@ -3386,7 +3398,8 @@ attribute-sets:
         name: mark-block
         type: u32
   -
-    name: tc-route-attrs
+    name: route-attrs
+    name-prefix: tca-route4-
     attributes:
       -
         name: classid
@@ -3403,14 +3416,15 @@ attribute-sets:
       -
         name: police
         type: nest
-        nested-attributes: tc-police-attrs
+        nested-attributes: police-attrs
       -
         name: act
         type: indexed-array
         sub-type: nest
-        nested-attributes: tc-act-attrs
+        nested-attributes: act-attrs
   -
-    name: tc-taprio-attrs
+    name: taprio-attrs
+    name-prefix: tca-taprio-attr-
     attributes:
       -
         name: priomap
@@ -3419,14 +3433,14 @@ attribute-sets:
       -
         name: sched-entry-list
         type: nest
-        nested-attributes: tc-taprio-sched-entry-list
+        nested-attributes: taprio-sched-entry-list
       -
         name: sched-base-time
         type: s64
       -
         name: sched-single-entry
         type: nest
-        nested-attributes: tc-taprio-sched-entry
+        nested-attributes: taprio-sched-entry
       -
         name: sched-clockid
         type: s32
@@ -3451,17 +3465,19 @@ attribute-sets:
       -
         name: tc-entry
         type: nest
-        nested-attributes: tc-taprio-tc-entry-attrs
+        nested-attributes: taprio-tc-entry-attrs
   -
-    name: tc-taprio-sched-entry-list
+    name: taprio-sched-entry-list
+    name-prefix: tca-taprio-sched-
     attributes:
       -
         name: entry
         type: nest
-        nested-attributes: tc-taprio-sched-entry
+        nested-attributes: taprio-sched-entry
         multi-attr: true
   -
-    name: tc-taprio-sched-entry
+    name: taprio-sched-entry
+    name-prefix: tca-taprio-sched-entry-
     attributes:
       -
         name: index
@@ -3476,7 +3492,8 @@ attribute-sets:
         name: interval
         type: u32
   -
-    name: tc-taprio-tc-entry-attrs
+    name: taprio-tc-entry-attrs
+    name-prefix: tca-taprio-tc-entry-
     attributes:
       -
         name: index
@@ -3488,7 +3505,8 @@ attribute-sets:
         name: fp
         type: u32
   -
-    name: tc-tbf-attrs
+    name: tbf-attrs
+    name-prefix: tca-tbf-
     attributes:
       -
         name: parms
@@ -3504,7 +3522,7 @@ attribute-sets:
         name: rate64
         type: u64
       -
-        name: prate4
+        name: prate64
         type: u64
       -
         name: burst
@@ -3516,7 +3534,9 @@ attribute-sets:
         name: pad
         type: pad
   -
-    name: tc-act-sample-attrs
+    name: act-sample-attrs
+    name-prefix: tca-sample-
+    header: linux/tc_act/tc_sample.h
     attributes:
       -
         name: tm
@@ -3525,7 +3545,7 @@ attribute-sets:
       -
         name: parms
         type: binary
-        struct: tc-gen
+        struct: tc-gact
       -
         name: rate
         type: u32
@@ -3539,7 +3559,9 @@ attribute-sets:
         name: pad
         type: pad
   -
-    name: tc-act-gact-attrs
+    name: act-gact-attrs
+    name-prefix: tca-gact-
+    header: linux/tc_act/tc_gact.h
     attributes:
       -
         name: tm
@@ -3548,7 +3570,7 @@ attribute-sets:
       -
         name: parms
         type: binary
-        struct: tc-gen
+        struct: tc-gact
       -
         name: prob
         type: binary
@@ -3558,6 +3580,7 @@ attribute-sets:
         type: pad
   -
     name: tca-stab-attrs
+    name-prefix: tca-stab-
     attributes:
       -
         name: base
@@ -3568,6 +3591,8 @@ attribute-sets:
         type: binary
   -
     name: tca-stats-attrs
+    name-prefix: tca-stats-
+    header: linux/gen_stats.h
     attributes:
       -
         name: basic
@@ -3601,7 +3626,8 @@ attribute-sets:
         name: pkt64
         type: u64
   -
-    name: tc-u32-attrs
+    name: u32-attrs
+    name-prefix: tca-u32-
     attributes:
       -
         name: classid
@@ -3622,12 +3648,12 @@ attribute-sets:
       -
         name: police
         type: nest
-        nested-attributes: tc-police-attrs
+        nested-attributes: police-attrs
       -
         name: act
         type: indexed-array
         sub-type: nest
-        nested-attributes: tc-act-attrs
+        nested-attributes: act-attrs
       -
         name: indev
         type: string
@@ -3648,78 +3674,78 @@ attribute-sets:
 
 sub-messages:
   -
-    name: tc-options-msg
+    name: options-msg
     formats:
       -
         value: basic
-        attribute-set: tc-basic-attrs
+        attribute-set: basic-attrs
       -
         value: bpf
-        attribute-set: tc-bpf-attrs
+        attribute-set: bpf-attrs
       -
         value: bfifo
         fixed-header: tc-fifo-qopt
       -
         value: cake
-        attribute-set: tc-cake-attrs
+        attribute-set: cake-attrs
       -
         value: cbs
-        attribute-set: tc-cbs-attrs
+        attribute-set: cbs-attrs
       -
         value: cgroup
-        attribute-set: tc-cgroup-attrs
+        attribute-set: cgroup-attrs
       -
         value: choke
-        attribute-set: tc-choke-attrs
+        attribute-set: choke-attrs
       -
         value: clsact # no content
       -
         value: codel
-        attribute-set: tc-codel-attrs
+        attribute-set: codel-attrs
       -
         value: drr
-        attribute-set: tc-drr-attrs
+        attribute-set: drr-attrs
       -
         value: etf
-        attribute-set: tc-etf-attrs
+        attribute-set: etf-attrs
       -
         value: ets
-        attribute-set: tc-ets-attrs
+        attribute-set: ets-attrs
       -
         value: flow
-        attribute-set: tc-flow-attrs
+        attribute-set: flow-attrs
       -
         value: flower
-        attribute-set: tc-flower-attrs
+        attribute-set: flower-attrs
       -
         value: fq
-        attribute-set: tc-fq-attrs
+        attribute-set: fq-attrs
       -
         value: fq_codel
-        attribute-set: tc-fq-codel-attrs
+        attribute-set: fq-codel-attrs
       -
         value: fq_pie
-        attribute-set: tc-fq-pie-attrs
+        attribute-set: fq-pie-attrs
       -
         value: fw
-        attribute-set: tc-fw-attrs
+        attribute-set: fw-attrs
       -
         value: gred
-        attribute-set: tc-gred-attrs
+        attribute-set: gred-attrs
       -
         value: hfsc
         fixed-header: tc-hfsc-qopt
       -
         value: hhf
-        attribute-set: tc-hhf-attrs
+        attribute-set: hhf-attrs
       -
         value: htb
-        attribute-set: tc-htb-attrs
+        attribute-set: htb-attrs
       -
         value: ingress # no content
       -
         value: matchall
-        attribute-set: tc-matchall-attrs
+        attribute-set: matchall-attrs
       -
         value: mq # no content
       -
@@ -3731,7 +3757,7 @@ sub-messages:
       -
         value: netem
         fixed-header: tc-netem-qopt
-        attribute-set: tc-netem-attrs
+        attribute-set: netem-attrs
       -
         value: pfifo
         fixed-header: tc-fifo-qopt
@@ -3743,7 +3769,7 @@ sub-messages:
         fixed-header: tc-fifo-qopt
       -
         value: pie
-        attribute-set: tc-pie-attrs
+        attribute-set: pie-attrs
       -
         value: plug
         fixed-header: tc-plug-qopt
@@ -3752,13 +3778,13 @@ sub-messages:
         fixed-header: tc-prio-qopt
       -
         value: qfq
-        attribute-set: tc-qfq-attrs
+        attribute-set: qfq-attrs
       -
         value: red
-        attribute-set: tc-red-attrs
+        attribute-set: red-attrs
       -
         value: route
-        attribute-set: tc-route-attrs
+        attribute-set: route-attrs
       -
         value: sfb
         fixed-header: tc-sfb-qopt
@@ -3767,79 +3793,79 @@ sub-messages:
         fixed-header: tc-sfq-qopt-v1
       -
         value: taprio
-        attribute-set: tc-taprio-attrs
+        attribute-set: taprio-attrs
       -
         value: tbf
-        attribute-set: tc-tbf-attrs
+        attribute-set: tbf-attrs
       -
         value: u32
-        attribute-set: tc-u32-attrs
+        attribute-set: u32-attrs
   -
-    name: tc-act-options-msg
+    name: act-options-msg
     formats:
       -
         value: bpf
-        attribute-set: tc-act-bpf-attrs
+        attribute-set: act-bpf-attrs
       -
         value: connmark
-        attribute-set: tc-act-connmark-attrs
+        attribute-set: act-connmark-attrs
       -
         value: csum
-        attribute-set: tc-act-csum-attrs
+        attribute-set: act-csum-attrs
       -
         value: ct
-        attribute-set: tc-act-ct-attrs
+        attribute-set: act-ct-attrs
       -
         value: ctinfo
-        attribute-set: tc-act-ctinfo-attrs
+        attribute-set: act-ctinfo-attrs
       -
         value: gact
-        attribute-set: tc-act-gact-attrs
+        attribute-set: act-gact-attrs
       -
         value: gate
-        attribute-set: tc-act-gate-attrs
+        attribute-set: act-gate-attrs
       -
         value: ife
-        attribute-set: tc-act-ife-attrs
+        attribute-set: act-ife-attrs
       -
         value: mirred
-        attribute-set: tc-act-mirred-attrs
+        attribute-set: act-mirred-attrs
       -
         value: mpls
-        attribute-set: tc-act-mpls-attrs
+        attribute-set: act-mpls-attrs
       -
         value: nat
-        attribute-set: tc-act-nat-attrs
+        attribute-set: act-nat-attrs
       -
         value: pedit
-        attribute-set: tc-act-pedit-attrs
+        attribute-set: act-pedit-attrs
       -
         value: police
-        attribute-set: tc-act-police-attrs
+        attribute-set: police-attrs
       -
         value: sample
-        attribute-set: tc-act-sample-attrs
+        attribute-set: act-sample-attrs
       -
         value: simple
-        attribute-set: tc-act-simple-attrs
+        attribute-set: act-simple-attrs
       -
         value: skbedit
-        attribute-set: tc-act-skbedit-attrs
+        attribute-set: act-skbedit-attrs
       -
         value: skbmod
-        attribute-set: tc-act-skbmod-attrs
+        attribute-set: act-skbmod-attrs
       -
         value: tunnel_key
-        attribute-set: tc-act-tunnel-key-attrs
+        attribute-set: act-tunnel-key-attrs
       -
         value: vlan
-        attribute-set: tc-act-vlan-attrs
+        attribute-set: act-vlan-attrs
   -
     name: tca-stats-app-msg
     formats:
       -
         value: cake
-        attribute-set: tc-cake-stats-attrs
+        attribute-set: cake-stats-attrs
       -
         value: choke
         fixed-header: tc-choke-xstats
@@ -3873,11 +3899,12 @@ sub-messages:
 
 operations:
   enum-model: directional
+  name-prefix: rtm-
   list:
     -
       name: newqdisc
       doc: Create new tc qdisc.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
       do:
         request:
@@ -3892,7 +3919,7 @@ operations:
     -
       name: delqdisc
       doc: Delete existing tc qdisc.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
       do:
         request:
@@ -3900,9 +3927,9 @@ operations:
     -
       name: getqdisc
       doc: Get / dump tc qdisc information.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
-      do:
+      do: &getqdisc-do
         request:
           value: 38
           attributes:
@@ -3921,10 +3948,11 @@ operations:
             - chain
             - ingress-block
             - egress-block
+      dump: *getqdisc-do
     -
       name: newtclass
       doc: Get / dump tc traffic class information.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
       do:
         request:
@@ -3933,7 +3961,7 @@ operations:
     -
       name: deltclass
       doc: Get / dump tc traffic class information.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
       do:
         request:
@@ -3941,7 +3969,7 @@ operations:
     -
       name: gettclass
       doc: Get / dump tc traffic class information.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
       do:
         request:
@@ -3952,7 +3980,7 @@ operations:
     -
       name: newtfilter
       doc: Get / dump tc filter information.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
       do:
         request:
@@ -3961,7 +3989,7 @@ operations:
     -
       name: deltfilter
       doc: Get / dump tc filter information.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
       do:
         request:
@@ -3972,7 +4000,7 @@ operations:
     -
       name: gettfilter
       doc: Get / dump tc filter information.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
       do:
         request:
@@ -3995,7 +4023,7 @@ operations:
     -
       name: newchain
       doc: Get / dump tc chain information.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
       do:
         request:
@@ -4004,7 +4032,7 @@ operations:
     -
       name: delchain
       doc: Get / dump tc chain information.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
       do:
         request:
@@ -4014,7 +4042,7 @@ operations:
     -
       name: getchain
       doc: Get / dump tc chain information.
-      attribute-set: tc-attrs
+      attribute-set: attrs
       fixed-header: tcmsg
       do:
         request:
diff --git a/Documentation/networking/dccp.rst b/Documentation/networking/dccp.rst
deleted file mode 100644
index 91e5c33ba3ff..000000000000
--- a/Documentation/networking/dccp.rst
+++ /dev/null
@@ -1,219 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-=============
-DCCP protocol
-=============
-
-
-.. Contents
-   - Introduction
-   - Missing features
-   - Socket options
-   - Sysctl variables
-   - IOCTLs
-   - Other tunables
-   - Notes
-
-
-Introduction
-============
-Datagram Congestion Control Protocol (DCCP) is an unreliable, connection
-oriented protocol designed to solve issues present in UDP and TCP, particularly
-for real-time and multimedia (streaming) traffic.
-It divides into a base protocol (RFC 4340) and pluggable congestion control
-modules called CCIDs. Like pluggable TCP congestion control, at least one CCID
-needs to be enabled in order for the protocol to function properly. In the Linux
-implementation, this is the TCP-like CCID2 (RFC 4341). Additional CCIDs, such as
-the TCP-friendly CCID3 (RFC 4342), are optional.
-For a brief introduction to CCIDs and suggestions for choosing a CCID to match
-given applications, see section 10 of RFC 4340.
-
-It has a base protocol and pluggable congestion control IDs (CCIDs).
-
-DCCP is a Proposed Standard (RFC 2026), and the homepage for DCCP as a protocol
-is at http://www.ietf.org/html.charters/dccp-charter.html
-
-
-Missing features
-================
-The Linux DCCP implementation does not currently support all the features that are
-specified in RFCs 4340...42.
-
-The known bugs are at:
-
-	http://www.linuxfoundation.org/collaborate/workgroups/networking/todo#DCCP
-
-For more up-to-date versions of the DCCP implementation, please consider using
-the experimental DCCP test tree; instructions for checking this out are on:
-http://www.linuxfoundation.org/collaborate/workgroups/networking/dccp_testing#Experimental_DCCP_source_tree
-
-
-Socket options
-==============
-DCCP_SOCKOPT_QPOLICY_ID sets the dequeuing policy for outgoing packets. It takes
-a policy ID as argument and can only be set before the connection (i.e. changes
-during an established connection are not supported). Currently, two policies are
-defined: the "simple" policy (DCCPQ_POLICY_SIMPLE), which does nothing special,
-and a priority-based variant (DCCPQ_POLICY_PRIO). The latter allows to pass an
-u32 priority value as ancillary data to sendmsg(), where higher numbers indicate
-a higher packet priority (similar to SO_PRIORITY). This ancillary data needs to
-be formatted using a cmsg(3) message header filled in as follows::
-
-	cmsg->cmsg_level = SOL_DCCP;
-	cmsg->cmsg_type	 = DCCP_SCM_PRIORITY;
-	cmsg->cmsg_len	 = CMSG_LEN(sizeof(uint32_t));	/* or CMSG_LEN(4) */
-
-DCCP_SOCKOPT_QPOLICY_TXQLEN sets the maximum length of the output queue. A zero
-value is always interpreted as unbounded queue length. If different from zero,
-the interpretation of this parameter depends on the current dequeuing policy
-(see above): the "simple" policy will enforce a fixed queue size by returning
-EAGAIN, whereas the "prio" policy enforces a fixed queue length by dropping the
-lowest-priority packet first. The default value for this parameter is
-initialised from /proc/sys/net/dccp/default/tx_qlen.
-
-DCCP_SOCKOPT_SERVICE sets the service. The specification mandates use of
-service codes (RFC 4340, sec. 8.1.2); if this socket option is not set,
-the socket will fall back to 0 (which means that no meaningful service code
-is present). On active sockets this is set before connect(); specifying more
-than one code has no effect (all subsequent service codes are ignored). The
-case is different for passive sockets, where multiple service codes (up to 32)
-can be set before calling bind().
-
-DCCP_SOCKOPT_GET_CUR_MPS is read-only and retrieves the current maximum packet
-size (application payload size) in bytes, see RFC 4340, section 14.
-
-DCCP_SOCKOPT_AVAILABLE_CCIDS is also read-only and returns the list of CCIDs
-supported by the endpoint. The option value is an array of type uint8_t whose
-size is passed as option length. The minimum array size is 4 elements, the
-value returned in the optlen argument always reflects the true number of
-built-in CCIDs.
-
-DCCP_SOCKOPT_CCID is write-only and sets both the TX and RX CCIDs at the same
-time, combining the operation of the next two socket options. This option is
-preferable over the latter two, since often applications will use the same
-type of CCID for both directions; and mixed use of CCIDs is not currently well
-understood. This socket option takes as argument at least one uint8_t value, or
-an array of uint8_t values, which must match available CCIDS (see above). CCIDs
-must be registered on the socket before calling connect() or listen().
-
-DCCP_SOCKOPT_TX_CCID is read/write. It returns the current CCID (if set) or sets
-the preference list for the TX CCID, using the same format as DCCP_SOCKOPT_CCID.
-Please note that the getsockopt argument type here is ``int``, not uint8_t.
-
-DCCP_SOCKOPT_RX_CCID is analogous to DCCP_SOCKOPT_TX_CCID, but for the RX CCID.
-
-DCCP_SOCKOPT_SERVER_TIMEWAIT enables the server (listening socket) to hold
-timewait state when closing the connection (RFC 4340, 8.3). The usual case is
-that the closing server sends a CloseReq, whereupon the client holds timewait
-state. When this boolean socket option is on, the server sends a Close instead
-and will enter TIMEWAIT. This option must be set after accept() returns.
-
-DCCP_SOCKOPT_SEND_CSCOV and DCCP_SOCKOPT_RECV_CSCOV are used for setting the
-partial checksum coverage (RFC 4340, sec. 9.2). The default is that checksums
-always cover the entire packet and that only fully covered application data is
-accepted by the receiver. Hence, when using this feature on the sender, it must
-be enabled at the receiver, too with suitable choice of CsCov.
-
-DCCP_SOCKOPT_SEND_CSCOV sets the sender checksum coverage. Values in the
-	range 0..15 are acceptable. The default setting is 0 (full coverage),
-	values between 1..15 indicate partial coverage.
-
-DCCP_SOCKOPT_RECV_CSCOV is for the receiver and has a different meaning: it
-	sets a threshold, where again values 0..15 are acceptable. The default
-	of 0 means that all packets with a partial coverage will be discarded.
-	Values in the range 1..15 indicate that packets with minimally such a
-	coverage value are also acceptable. The higher the number, the more
-	restrictive this setting (see [RFC 4340, sec. 9.2.1]). Partial coverage
-	settings are inherited to the child socket after accept().
-
-The following two options apply to CCID 3 exclusively and are getsockopt()-only.
-In either case, a TFRC info struct (defined in <linux/tfrc.h>) is returned.
-
-DCCP_SOCKOPT_CCID_RX_INFO
-	Returns a ``struct tfrc_rx_info`` in optval; the buffer for optval and
-	optlen must be set to at least sizeof(struct tfrc_rx_info).
-
-DCCP_SOCKOPT_CCID_TX_INFO
-	Returns a ``struct tfrc_tx_info`` in optval; the buffer for optval and
-	optlen must be set to at least sizeof(struct tfrc_tx_info).
-
-On unidirectional connections it is useful to close the unused half-connection
-via shutdown (SHUT_WR or SHUT_RD): this will reduce per-packet processing costs.
-
-
-Sysctl variables
-================
-Several DCCP default parameters can be managed by the following sysctls
-(sysctl net.dccp.default or /proc/sys/net/dccp/default):
-
-request_retries
-	The number of active connection initiation retries (the number of
-	Requests minus one) before timing out. In addition, it also governs
-	the behaviour of the other, passive side: this variable also sets
-	the number of times DCCP repeats sending a Response when the initial
-	handshake does not progress from RESPOND to OPEN (i.e. when no Ack
-	is received after the initial Request).  This value should be greater
-	than 0, suggested is less than 10. Analogue of tcp_syn_retries.
-
-retries1
-	How often a DCCP Response is retransmitted until the listening DCCP
-	side considers its connecting peer dead. Analogue of tcp_retries1.
-
-retries2
-	The number of times a general DCCP packet is retransmitted. This has
-	importance for retransmitted acknowledgments and feature negotiation,
-	data packets are never retransmitted. Analogue of tcp_retries2.
-
-tx_ccid = 2
-	Default CCID for the sender-receiver half-connection. Depending on the
-	choice of CCID, the Send Ack Vector feature is enabled automatically.
-
-rx_ccid = 2
-	Default CCID for the receiver-sender half-connection; see tx_ccid.
-
-seq_window = 100
-	The initial sequence window (sec. 7.5.2) of the sender. This influences
-	the local ackno validity and the remote seqno validity windows (7.5.1).
-	Values in the range Wmin = 32 (RFC 4340, 7.5.2) up to 2^32-1 can be set.
-
-tx_qlen = 5
-	The size of the transmit buffer in packets. A value of 0 corresponds
-	to an unbounded transmit buffer.
-
-sync_ratelimit = 125 ms
-	The timeout between subsequent DCCP-Sync packets sent in response to
-	sequence-invalid packets on the same socket (RFC 4340, 7.5.4). The unit
-	of this parameter is milliseconds; a value of 0 disables rate-limiting.
-
-
-IOCTLS
-======
-FIONREAD
-	Works as in udp(7): returns in the ``int`` argument pointer the size of
-	the next pending datagram in bytes, or 0 when no datagram is pending.
-
-SIOCOUTQ
-	Returns the number of unsent data bytes in the socket send queue as ``int``
-	into the buffer specified by the argument pointer.
-
-Other tunables
-==============
-Per-route rto_min support
-	CCID-2 supports the RTAX_RTO_MIN per-route setting for the minimum value
-	of the RTO timer. This setting can be modified via the 'rto_min' option
-	of iproute2; for example::
-
-		> ip route change 10.0.0.0/24   rto_min 250j dev wlan0
-		> ip route add    10.0.0.254/32 rto_min 800j dev wlan0
-		> ip route show dev wlan0
-
-	CCID-3 also supports the rto_min setting: it is used to define the lower
-	bound for the expiry of the nofeedback timer. This can be useful on LANs
-	with very low RTTs (e.g., loopback, Gbit ethernet).
-
-
-Notes
-=====
-DCCP does not travel through NAT successfully at present on many boxes. This is
-because the checksum covers the pseudo-header as per TCP and UDP. Linux NAT
-support for DCCP has been added.
diff --git a/Documentation/networking/device_drivers/ethernet/huawei/hinic3.rst b/Documentation/networking/device_drivers/ethernet/huawei/hinic3.rst
new file mode 100644
index 000000000000..e3dfd083fa52
--- /dev/null
+++ b/Documentation/networking/device_drivers/ethernet/huawei/hinic3.rst
@@ -0,0 +1,137 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================================================================
+Linux kernel driver for Huawei Ethernet Device Driver (hinic3) family
+=====================================================================
+
+Overview
+========
+
+The hinic3 is a network interface card (NIC) for Data Center. It supports
+a range of link-speed devices (10GE, 25GE, 100GE, etc.). The hinic3
+devices can have multiple physical forms: LOM (Lan on Motherboard) NIC,
+PCIe standard NIC, OCP (Open Compute Project) NIC, etc.
+
+The hinic3 driver supports the following features:
+- IPv4/IPv6 TCP/UDP checksum offload
+- TSO (TCP Segmentation Offload), LRO (Large Receive Offload)
+- RSS (Receive Side Scaling)
+- MSI-X interrupt aggregation configuration and interrupt adaptation.
+- SR-IOV (Single Root I/O Virtualization).
+
+Content
+=======
+
+- Supported PCI vendor ID/device IDs
+- Source Code Structure of Hinic3 Driver
+- Management Interface
+
+Supported PCI vendor ID/device IDs
+==================================
+
+19e5:0222 - hinic3 PF/PPF
+19e5:375F - hinic3 VF
+
+Prime Physical Function (PPF) is responsible for the management of the
+whole NIC card. For example, clock synchronization between the NIC and
+the host. Any PF may serve as a PPF. The PPF is selected dynamically.
+
+Source Code Structure of Hinic3 Driver
+======================================
+
+========================  ================================================
+hinic3_pci_id_tbl.h       Supported device IDs
+hinic3_hw_intf.h          Interface between HW and driver
+hinic3_queue_common.[ch]  Common structures and methods for NIC queues
+hinic3_common.[ch]        Encapsulation of memory operations in Linux
+hinic3_csr.h              Register definitions in the BAR
+hinic3_hwif.[ch]          Interface for BAR
+hinic3_eqs.[ch]           Interface for AEQs and CEQs
+hinic3_mbox.[ch]          Interface for mailbox
+hinic3_mgmt.[ch]          Management interface based on mailbox and AEQ
+hinic3_wq.[ch]            Work queue data structures and interface
+hinic3_cmdq.[ch]          Command queue is used to post command to HW
+hinic3_hwdev.[ch]         HW structures and methods abstractions
+hinic3_lld.[ch]           Auxiliary driver adaptation layer
+hinic3_hw_comm.[ch]       Interface for common HW operations
+hinic3_mgmt_interface.h   Interface between firmware and driver
+hinic3_hw_cfg.[ch]        Interface for HW configuration
+hinic3_irq.c              Interrupt request
+hinic3_netdev_ops.c       Operations registered to Linux kernel stack
+hinic3_nic_dev.h          NIC structures and methods abstractions
+hinic3_main.c             Main Linux kernel driver
+hinic3_nic_cfg.[ch]       NIC service configuration
+hinic3_nic_io.[ch]        Management plane interface for TX and RX
+hinic3_rss.[ch]           Interface for Receive Side Scaling (RSS)
+hinic3_rx.[ch]            Interface for transmit
+hinic3_tx.[ch]            Interface for receive
+hinic3_ethtool.c          Interface for ethtool operations (ops)
+hinic3_filter.c           Interface for MAC address
+========================  ================================================
+
+Management Interface
+====================
+
+Asynchronous Event Queue (AEQ)
+------------------------------
+
+AEQ receives high priority events from the HW over a descriptor queue.
+Every descriptor is a fixed size of 64 bytes. AEQ can receive solicited or
+unsolicited events. Every device, VF or PF, can have up to 4 AEQs.
+Every AEQ is associated to a dedicated IRQ. AEQ can receive multiple types
+of events, but in practice the hinic3 driver ignores all events except for
+2 mailbox related events.
+
+Mailbox
+-------
+
+Mailbox is a communication mechanism between the hinic3 driver and the HW.
+Each device has an independent mailbox. Driver can use the mailbox to send
+requests to management. Driver receives mailbox messages, such as responses
+to requests, over the AEQ (using event HINIC3_AEQ_FOR_MBOX). Due to the
+limited size of mailbox data register, mailbox messages are sent
+segment-by-segment.
+
+Every device can use its mailbox to post request to firmware. The mailbox
+can also be used to post requests and responses between the PF and its VFs.
+
+Completion Event Queue (CEQ)
+----------------------------
+
+The implementation of CEQ is the same as AEQ. It receives completion events
+from HW over a fixed size descriptor of 32 bits. Every device can have up
+to 32 CEQs. Every CEQ has a dedicated IRQ. CEQ only receives solicited
+events that are responses to requests from the driver. CEQ can receive
+multiple types of events, but in practice the hinic3 driver ignores all
+events except for HINIC3_CMDQ that represents completion of previously
+posted commands on a cmdq.
+
+Command Queue (cmdq)
+--------------------
+
+Every cmdq has a dedicated work queue on which commands are posted.
+Commands on the work queue are fixed size descriptor of size 64 bytes.
+Completion of a command will be indicated using ctrl bits in the
+descriptor that carried the command. Notification of command completions
+will also be provided via event on CEQ. Every device has 4 command queues
+that are initialized as a set (called cmdqs), each with its own type.
+Hinic3 driver only uses type HINIC3_CMDQ_SYNC.
+
+Work Queues(WQ)
+---------------
+
+Work queues are logical arrays of fixed size WQEs. The array may be spread
+over multiple non-contiguous pages using indirection table. Work queues are
+used by I/O queues and command queues.
+
+Global function ID
+------------------
+
+Every function, PF or VF, has a unique ordinal identification within the device.
+Many management commands (mbox or cmdq) contain this ID so HW can apply the
+command effect to the right function.
+
+PF is allowed to post management commands to a subordinate VF by specifying the
+VFs ID. A VF must provide its own ID. Anti-spoofing in the HW will cause
+command from a VF to fail if it contains the wrong ID.
+
diff --git a/Documentation/networking/device_drivers/ethernet/index.rst b/Documentation/networking/device_drivers/ethernet/index.rst
index 05d822b904b4..139b4c75a191 100644
--- a/Documentation/networking/device_drivers/ethernet/index.rst
+++ b/Documentation/networking/device_drivers/ethernet/index.rst
@@ -28,6 +28,7 @@ Contents:
    freescale/gianfar
    google/gve
    huawei/hinic
+   huawei/hinic3
    intel/e100
    intel/e1000
    intel/e1000e
@@ -55,6 +56,7 @@ Contents:
    ti/cpsw_switchdev
    ti/am65_nuss_cpsw_switchdev
    ti/tlan
+   ti/icssg_prueth
    wangxun/txgbe
    wangxun/ngbe
 
diff --git a/Documentation/networking/device_drivers/ethernet/meta/fbnic.rst b/Documentation/networking/device_drivers/ethernet/meta/fbnic.rst
index 04e0595bb0a7..f8592dec8851 100644
--- a/Documentation/networking/device_drivers/ethernet/meta/fbnic.rst
+++ b/Documentation/networking/device_drivers/ethernet/meta/fbnic.rst
@@ -28,9 +28,60 @@ devlink dev info provides version information for all three components. In
 addition to the version the hg commit hash of the build is included as a
 separate entry.
 
+Upgrading Firmware
+------------------
+
+fbnic supports updating firmware using signed PLDM images with devlink dev
+flash. PLDM images are written into the flash. Flashing does not interrupt
+the operation of the device.
+
+On host boot the latest UEFI driver is always used, no explicit activation
+is required. Firmware activation is required to run new control firmware. cmrt
+firmware can only be activated by power cycling the NIC.
+
 Statistics
 ----------
 
+TX MAC Interface
+~~~~~~~~~~~~~~~~
+
+ - ``ptp_illegal_req``: packets sent to the NIC with PTP request bit set but routed to BMC/FW
+ - ``ptp_good_ts``: packets successfully routed to MAC with PTP request bit set
+ - ``ptp_bad_ts``: packets destined for MAC with PTP request bit set but aborted because of some error (e.g., DMA read error)
+
+TX Extension (TEI) Interface (TTI)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+ - ``tti_cm_drop``: control messages dropped at the TX Extension (TEI) Interface because of credit starvation
+ - ``tti_frame_drop``: packets dropped at the TX Extension (TEI) Interface because of credit starvation
+ - ``tti_tbi_drop``: packets dropped at the TX BMC Interface (TBI) because of credit starvation
+
+RXB (RX Buffer) Enqueue
+~~~~~~~~~~~~~~~~~~~~~~~
+
+ - ``rxb_integrity_err[i]``: frames enqueued with integrity errors (e.g., multi-bit ECC errors) on RXB input i
+ - ``rxb_mac_err[i]``: frames enqueued with MAC end-of-frame errors (e.g., bad FCS) on RXB input i
+ - ``rxb_parser_err[i]``: frames experienced RPC parser errors
+ - ``rxb_frm_err[i]``: frames experienced signaling errors (e.g., missing end-of-packet/start-of-packet) on RXB input i
+ - ``rxb_drbo[i]_frames``: frames received at RXB input i
+ - ``rxb_drbo[i]_bytes``: bytes received at RXB input i
+
+RXB (RX Buffer) FIFO
+~~~~~~~~~~~~~~~~~~~~
+
+ - ``rxb_fifo[i]_drop``: transitions into the drop state on RXB pool i
+ - ``rxb_fifo[i]_dropped_frames``: frames dropped on RXB pool i
+ - ``rxb_fifo[i]_ecn``: transitions into the ECN mark state on RXB pool i
+ - ``rxb_fifo[i]_level``: current occupancy of RXB pool i
+
+RXB (RX Buffer) Dequeue
+~~~~~~~~~~~~~~~~~~~~~~~
+
+   - ``rxb_intf[i]_frames``: frames sent to the output i
+   - ``rxb_intf[i]_bytes``: bytes sent to the output i
+   - ``rxb_pbuf[i]_frames``: frames sent to output i from the perspective of internal packet buffer
+   - ``rxb_pbuf[i]_bytes``: bytes sent to output i from the perspective of internal packet buffer
+
 RPC (Rx parser)
 ~~~~~~~~~~~~~~~
 
@@ -44,6 +95,15 @@ RPC (Rx parser)
  - ``rpc_out_of_hdr_err``: frames where header was larger than parsable region
  - ``ovr_size_err``: oversized frames
 
+Hardware Queues
+~~~~~~~~~~~~~~~
+
+1. RX DMA Engine:
+
+ - ``rde_[i]_pkt_err``: packets with MAC EOP, RPC parser, RXB truncation, or RDE frame truncation errors. These error are flagged in the packet metadata because of cut-through support but the actual drop happens once PCIE/RDE is reached.
+ - ``rde_[i]_pkt_cq_drop``: packets dropped because RCQ is full
+ - ``rde_[i]_pkt_bdq_drop``: packets dropped because HPQ or PPQ ran out of host buffer
+
 PCIe
 ~~~~
 
diff --git a/Documentation/networking/device_drivers/ethernet/ti/icssg_prueth.rst b/Documentation/networking/device_drivers/ethernet/ti/icssg_prueth.rst
new file mode 100644
index 000000000000..da21ddf431bb
--- /dev/null
+++ b/Documentation/networking/device_drivers/ethernet/ti/icssg_prueth.rst
@@ -0,0 +1,56 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================================
+Texas Instruments ICSSG PRUETH ethernet driver
+==============================================
+
+:Version: 1.0
+
+ICSSG Firmware
+==============
+
+Every ICSSG core has two Programmable Real-Time Unit(PRUs), two auxiliary
+Real-Time Transfer Unit (RTUs), and two Transmit Real-Time Transfer Units
+(TX_PRUs). Each one of these runs its own firmware. The firmwares combnined are
+referred as ICSSG Firmware.
+
+Firmware Statistics
+===================
+
+The ICSSG firmware maintains certain statistics which are dumped by the driver
+via ``ethtool -S <interface>``
+
+These statistics are as follows,
+
+ - ``FW_RTU_PKT_DROP``: Diagnostic error counter which increments when RTU drops a locally injected packet due to port being disabled or rule violation.
+ - ``FW_Q0_OVERFLOW``: TX overflow counter for queue0
+ - ``FW_Q1_OVERFLOW``: TX overflow counter for queue1
+ - ``FW_Q2_OVERFLOW``: TX overflow counter for queue2
+ - ``FW_Q3_OVERFLOW``: TX overflow counter for queue3
+ - ``FW_Q4_OVERFLOW``: TX overflow counter for queue4
+ - ``FW_Q5_OVERFLOW``: TX overflow counter for queue5
+ - ``FW_Q6_OVERFLOW``: TX overflow counter for queue6
+ - ``FW_Q7_OVERFLOW``: TX overflow counter for queue7
+ - ``FW_DROPPED_PKT``: This counter is incremented when a packet is dropped at PRU because of rule violation.
+ - ``FW_RX_ERROR``: Incremented if there was a CRC error or Min/Max frame error at PRU
+ - ``FW_RX_DS_INVALID``: Incremented when RTU detects Data Status invalid condition
+ - ``FW_TX_DROPPED_PACKET``: Counter for packets dropped via TX Port
+ - ``FW_TX_TS_DROPPED_PACKET``: Counter for packets with TS flag dropped via TX Port
+ - ``FW_INF_PORT_DISABLED``: Incremented when RX frame is dropped due to port being disabled
+ - ``FW_INF_SAV``: Incremented when RX frame is dropped due to Source Address violation
+ - ``FW_INF_SA_DL``: Incremented when RX frame is dropped due to Source Address being in the denylist
+ - ``FW_INF_PORT_BLOCKED``: Incremented when RX frame is dropped due to port being blocked and frame being a special frame
+ - ``FW_INF_DROP_TAGGED`` : Incremented when RX frame is dropped for being tagged
+ - ``FW_INF_DROP_PRIOTAGGED``: Incremented when RX frame is dropped for being priority tagged
+ - ``FW_INF_DROP_NOTAG``: Incremented when RX frame is dropped for being untagged
+ - ``FW_INF_DROP_NOTMEMBER``: Incremented when RX frame is dropped for port not being member of VLAN
+ - ``FW_RX_EOF_SHORT_FRMERR``: Incremented if End Of Frame (EOF) task is scheduled without seeing RX_B1
+ - ``FW_RX_B0_DROP_EARLY_EOF``: Incremented when frame is dropped due to Early EOF
+ - ``FW_TX_JUMBO_FRM_CUTOFF``: Incremented when frame is cut off to prevent packet size > 2000 Bytes
+ - ``FW_RX_EXP_FRAG_Q_DROP``: Incremented when express frame is received in the same queue as the previous fragment
+ - ``FW_RX_FIFO_OVERRUN``: RX fifo overrun counter
+ - ``FW_CUT_THR_PKT``: Incremented when a packet is forwarded using Cut-Through forwarding method
+ - ``FW_HOST_RX_PKT_CNT``: Number of valid packets sent by Rx PRU to Host on PSI
+ - ``FW_HOST_TX_PKT_CNT``: Number of valid packets copied by RTU0 to Tx queues
+ - ``FW_HOST_EGRESS_Q_PRE_OVERFLOW``: Host Egress Q (Pre-emptible) Overflow Counter
+ - ``FW_HOST_EGRESS_Q_EXP_OVERFLOW``: Host Egress Q (Pre-emptible) Overflow Counter
diff --git a/Documentation/networking/devlink/devlink-info.rst b/Documentation/networking/devlink/devlink-info.rst
index 23073bc219d8..dd6adc4d0559 100644
--- a/Documentation/networking/devlink/devlink-info.rst
+++ b/Documentation/networking/devlink/devlink-info.rst
@@ -86,6 +86,10 @@ In case software/firmware components are loaded from the disk (e.g.
 ``/lib/firmware``) only the running version should be reported via
 the kernel API.
 
+Please note that any security versions reported via devlink are purely
+informational. Devlink does not use a secure channel to communicate with
+the device.
+
 Generic Versions
 ================
 
diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst
index 2c14dfe69b3a..5885e21e2212 100644
--- a/Documentation/networking/devlink/devlink-trap.rst
+++ b/Documentation/networking/devlink/devlink-trap.rst
@@ -451,7 +451,7 @@ be added to the following table:
    * - ``udp_parsing``
      - ``drop``
      - Traps packets dropped due to an error in the UDP header parsing.
-       This packet trap could include checksum errorrs, an improper UDP
+       This packet trap could include checksum errors, an improper UDP
        length detected (smaller than 8 bytes) or detection of header
        truncation.
    * - ``tcp_parsing``
diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst
index 948c8c44e233..8319f43b5933 100644
--- a/Documentation/networking/devlink/index.rst
+++ b/Documentation/networking/devlink/index.rst
@@ -84,6 +84,7 @@ parameters, info versions, and other features it supports.
    i40e
    ionic
    ice
+   ixgbe
    mlx4
    mlx5
    mlxsw
diff --git a/Documentation/networking/devlink/ixgbe.rst b/Documentation/networking/devlink/ixgbe.rst
new file mode 100644
index 000000000000..c27d1436c70e
--- /dev/null
+++ b/Documentation/networking/devlink/ixgbe.rst
@@ -0,0 +1,171 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+ixgbe devlink support
+=====================
+
+This document describes the devlink features implemented by the ``ixgbe``
+device driver.
+
+Info versions
+=============
+
+Any of the versions dealing with the security presented by ``devlink-info``
+is purely informational. Devlink does not use a secure channel to communicate
+with the device.
+
+The ``ixgbe`` driver reports the following versions
+
+.. list-table:: devlink info versions implemented
+    :widths: 5 5 5 90
+
+    * - Name
+      - Type
+      - Example
+      - Description
+    * - ``board.id``
+      - fixed
+      - H49289-000
+      - The Product Board Assembly (PBA) identifier of the board.
+    * - ``fw.undi``
+      - running
+      - 1.1937.0
+      - Version of the Option ROM containing the UEFI driver. The version is
+        reported in ``major.minor.patch`` format. The major version is
+        incremented whenever a major breaking change occurs, or when the
+        minor version would overflow. The minor version is incremented for
+        non-breaking changes and reset to 1 when the major version is
+        incremented. The patch version is normally 0 but is incremented when
+        a fix is delivered as a patch against an older base Option ROM.
+    * - ``fw.undi.srev``
+      - running
+      - 4
+      - Number indicating the security revision of the Option ROM.
+    * - ``fw.bundle_id``
+      - running
+      - 0x80000d0d
+      - Unique identifier of the firmware image file that was loaded onto
+        the device. Also referred to as the EETRACK identifier of the NVM.
+    * - ``fw.mgmt.api``
+      - running
+      - 1.5.1
+      - 3-digit version number (major.minor.patch) of the API exported over
+        the AdminQ by the management firmware. Used by the driver to
+        identify what commands are supported. Historical versions of the
+        kernel only displayed a 2-digit version number (major.minor).
+    * - ``fw.mgmt.build``
+      - running
+      - 0x305d955f
+      - Unique identifier of the source for the management firmware.
+    * - ``fw.mgmt.srev``
+      - running
+      - 3
+      - Number indicating the security revision of the firmware.
+    * - ``fw.psid.api``
+      - running
+      - 0.80
+      - Version defining the format of the flash contents.
+    * - ``fw.netlist``
+      - running
+      - 1.1.2000-6.7.0
+      - The version of the netlist module. This module defines the device's
+        Ethernet capabilities and default settings, and is used by the
+        management firmware as part of managing link and device
+        connectivity.
+    * - ``fw.netlist.build``
+      - running
+      - 0xee16ced7
+      - The first 4 bytes of the hash of the netlist module contents.
+
+Flash Update
+============
+
+The ``ixgbe`` driver implements support for flash update using the
+``devlink-flash`` interface. It supports updating the device flash using a
+combined flash image that contains the ``fw.mgmt``, ``fw.undi``, and
+``fw.netlist`` components.
+
+.. list-table:: List of supported overwrite modes
+   :widths: 5 95
+
+   * - Bits
+     - Behavior
+   * - ``DEVLINK_FLASH_OVERWRITE_SETTINGS``
+     - Do not preserve settings stored in the flash components being
+       updated. This includes overwriting the port configuration that
+       determines the number of physical functions the device will
+       initialize with.
+   * - ``DEVLINK_FLASH_OVERWRITE_SETTINGS`` and ``DEVLINK_FLASH_OVERWRITE_IDENTIFIERS``
+     - Do not preserve either settings or identifiers. Overwrite everything
+       in the flash with the contents from the provided image, without
+       performing any preservation. This includes overwriting device
+       identifying fields such as the MAC address, Vital product Data (VPD) area,
+       and device serial number. It is expected that this combination be used with an
+       image customized for the specific device.
+
+Reload
+======
+
+The ``ixgbe`` driver supports activating new firmware after a flash update
+using ``DEVLINK_CMD_RELOAD`` with the ``DEVLINK_RELOAD_ACTION_FW_ACTIVATE``
+action.
+
+.. code:: shell
+
+    $ devlink dev reload pci/0000:01:00.0 reload action fw_activate
+
+The new firmware is activated by issuing a device specific Embedded
+Management Processor reset which requests the device to reset and reload the
+EMP firmware image.
+
+The driver does not currently support reloading the driver via
+``DEVLINK_RELOAD_ACTION_DRIVER_REINIT``.
+
+Regions
+=======
+
+The ``ixgbe`` driver implements the following regions for accessing internal
+device data.
+
+.. list-table:: regions implemented
+    :widths: 15 85
+
+    * - Name
+      - Description
+    * - ``nvm-flash``
+      - The contents of the entire flash chip, sometimes referred to as
+        the device's Non Volatile Memory.
+    * - ``shadow-ram``
+      - The contents of the Shadow RAM, which is loaded from the beginning
+        of the flash. Although the contents are primarily from the flash,
+        this area also contains data generated during device boot which is
+        not stored in flash.
+    * - ``device-caps``
+      - The contents of the device firmware's capabilities buffer. Useful to
+        determine the current state and configuration of the device.
+
+Both the ``nvm-flash`` and ``shadow-ram`` regions can be accessed without a
+snapshot. The ``device-caps`` region requires a snapshot as the contents are
+sent by firmware and can't be split into separate reads.
+
+Users can request an immediate capture of a snapshot for all three regions
+via the ``DEVLINK_CMD_REGION_NEW`` command.
+
+.. code:: shell
+
+    $ devlink region show
+    pci/0000:01:00.0/nvm-flash: size 10485760 snapshot [] max 1
+    pci/0000:01:00.0/device-caps: size 4096 snapshot [] max 10
+
+    $ devlink region new pci/0000:01:00.0/nvm-flash snapshot 1
+
+    $ devlink region dump pci/0000:01:00.0/nvm-flash snapshot 1
+    0000000000000000 0014 95dc 0014 9514 0035 1670 0034 db30
+    0000000000000010 0000 0000 ffff ff04 0029 8c00 0028 8cc8
+    0000000000000020 0016 0bb8 0016 1720 0000 0000 c00f 3ffc
+    0000000000000030 bada cce5 bada cce5 bada cce5 bada cce5
+
+    $ devlink region read pci/0000:01:00.0/nvm-flash snapshot 1 address 0 length 16
+    0000000000000000 0014 95dc 0014 9514 0035 1670 0034 db30
+
+    $ devlink region delete pci/0000:01:00.0/device-caps snapshot 1
diff --git a/Documentation/networking/devmem.rst b/Documentation/networking/devmem.rst
index eb678ca45496..a6cd7236bfbd 100644
--- a/Documentation/networking/devmem.rst
+++ b/Documentation/networking/devmem.rst
@@ -62,15 +62,15 @@ More Info
     https://lore.kernel.org/netdev/20240831004313.3713467-1-almasrymina@google.com/
 
 
-Interface
-=========
+RX Interface
+============
 
 
 Example
 -------
 
-tools/testing/selftests/net/ncdevmem.c:do_server shows an example of setting up
-the RX path of this API.
+./tools/testing/selftests/drivers/net/hw/ncdevmem:do_server shows an example of
+setting up the RX path of this API.
 
 
 NIC Setup
@@ -235,6 +235,148 @@ can be less than the tokens provided by the user in case of:
 (a) an internal kernel leak bug.
 (b) the user passed more than 1024 frags.
 
+TX Interface
+============
+
+
+Example
+-------
+
+./tools/testing/selftests/drivers/net/hw/ncdevmem:do_client shows an example of
+setting up the TX path of this API.
+
+
+NIC Setup
+---------
+
+The user must bind a TX dmabuf to a given NIC using the netlink API::
+
+        struct netdev_bind_tx_req *req = NULL;
+        struct netdev_bind_tx_rsp *rsp = NULL;
+        struct ynl_error yerr;
+
+        *ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+
+        req = netdev_bind_tx_req_alloc();
+        netdev_bind_tx_req_set_ifindex(req, ifindex);
+        netdev_bind_tx_req_set_fd(req, dmabuf_fd);
+
+        rsp = netdev_bind_tx(*ys, req);
+
+        tx_dmabuf_id = rsp->id;
+
+
+The netlink API returns a dmabuf_id: a unique ID that refers to this dmabuf
+that has been bound.
+
+The user can unbind the dmabuf from the netdevice by closing the netlink socket
+that established the binding. We do this so that the binding is automatically
+unbound even if the userspace process crashes.
+
+Note that any reasonably well-behaved dmabuf from any exporter should work with
+devmem TCP, even if the dmabuf is not actually backed by devmem. An example of
+this is udmabuf, which wraps user memory (non-devmem) in a dmabuf.
+
+Socket Setup
+------------
+
+The user application must use MSG_ZEROCOPY flag when sending devmem TCP. Devmem
+cannot be copied by the kernel, so the semantics of the devmem TX are similar
+to the semantics of MSG_ZEROCOPY::
+
+	setsockopt(socket_fd, SOL_SOCKET, SO_ZEROCOPY, &opt, sizeof(opt));
+
+It is also recommended that the user binds the TX socket to the same interface
+the dma-buf has been bound to via SO_BINDTODEVICE::
+
+	setsockopt(socket_fd, SOL_SOCKET, SO_BINDTODEVICE, ifname, strlen(ifname) + 1);
+
+
+Sending data
+------------
+
+Devmem data is sent using the SCM_DEVMEM_DMABUF cmsg.
+
+The user should create a msghdr where,
+
+* iov_base is set to the offset into the dmabuf to start sending from
+* iov_len is set to the number of bytes to be sent from the dmabuf
+
+The user passes the dma-buf id to send from via the dmabuf_tx_cmsg.dmabuf_id.
+
+The example below sends 1024 bytes from offset 100 into the dmabuf, and 2048
+from offset 2000 into the dmabuf. The dmabuf to send from is tx_dmabuf_id::
+
+       char ctrl_data[CMSG_SPACE(sizeof(struct dmabuf_tx_cmsg))];
+       struct dmabuf_tx_cmsg ddmabuf;
+       struct msghdr msg = {};
+       struct cmsghdr *cmsg;
+       struct iovec iov[2];
+
+       iov[0].iov_base = (void*)100;
+       iov[0].iov_len = 1024;
+       iov[1].iov_base = (void*)2000;
+       iov[1].iov_len = 2048;
+
+       msg.msg_iov = iov;
+       msg.msg_iovlen = 2;
+
+       msg.msg_control = ctrl_data;
+       msg.msg_controllen = sizeof(ctrl_data);
+
+       cmsg = CMSG_FIRSTHDR(&msg);
+       cmsg->cmsg_level = SOL_SOCKET;
+       cmsg->cmsg_type = SCM_DEVMEM_DMABUF;
+       cmsg->cmsg_len = CMSG_LEN(sizeof(struct dmabuf_tx_cmsg));
+
+       ddmabuf.dmabuf_id = tx_dmabuf_id;
+
+       *((struct dmabuf_tx_cmsg *)CMSG_DATA(cmsg)) = ddmabuf;
+
+       sendmsg(socket_fd, &msg, MSG_ZEROCOPY);
+
+
+Reusing TX dmabufs
+------------------
+
+Similar to MSG_ZEROCOPY with regular memory, the user should not modify the
+contents of the dma-buf while a send operation is in progress. This is because
+the kernel does not keep a copy of the dmabuf contents. Instead, the kernel
+will pin and send data from the buffer available to the userspace.
+
+Just as in MSG_ZEROCOPY, the kernel notifies the userspace of send completions
+using MSG_ERRQUEUE::
+
+        int64_t tstop = gettimeofday_ms() + waittime_ms;
+        char control[CMSG_SPACE(100)] = {};
+        struct sock_extended_err *serr;
+        struct msghdr msg = {};
+        struct cmsghdr *cm;
+        int retries = 10;
+        __u32 hi, lo;
+
+        msg.msg_control = control;
+        msg.msg_controllen = sizeof(control);
+
+        while (gettimeofday_ms() < tstop) {
+                if (!do_poll(fd)) continue;
+
+                ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+
+                for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+                        serr = (void *)CMSG_DATA(cm);
+
+                        hi = serr->ee_data;
+                        lo = serr->ee_info;
+
+                        fprintf(stdout, "tx complete [%d,%d]\n", lo, hi);
+                }
+        }
+
+After the associated sendmsg has been completed, the dmabuf can be reused by
+the userspace.
+
+
 Implementation & Caveats
 ========================
 
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index c64133d309bf..ac90b82f3ce9 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -48,7 +48,6 @@ Contents:
    ax25
    bonding
    cdc_mbim
-   dccp
    dctcp
    devmem
    dns_resolver
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 5c63ab928b97..0f1251cce314 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -37,8 +37,8 @@ ip_no_pmtu_disc - INTEGER
 	Mode 3 is a hardened pmtu discover mode. The kernel will only
 	accept fragmentation-needed errors if the underlying protocol
 	can verify them besides a plain socket lookup. Current
-	protocols for which pmtu events will be honored are TCP, SCTP
-	and DCCP as they verify e.g. the sequence number or the
+	protocols for which pmtu events will be honored are TCP and
+	SCTP as they verify e.g. the sequence number or the
 	association. This mode should not be enabled globally but is
 	only intended to secure e.g. name servers in namespaces where
 	TCP path mtu must still work but path MTU information of other
@@ -735,7 +735,7 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
 	net.core.rmem_max.  Calling setsockopt() with SO_RCVBUF disables
 	automatic tuning of that socket's receive buffer size, in which
 	case this value is ignored.
-	Default: between 131072 and 6MB, depending on RAM size.
+	Default: between 131072 and 32MB, depending on RAM size.
 
 tcp_sack - BOOLEAN
 	Enable select acknowledgments (SACKS).
@@ -1099,7 +1099,7 @@ tcp_limit_output_bytes - INTEGER
 	limits the number of bytes on qdisc or device to reduce artificial
 	RTT/cwnd and reduce bufferbloat.
 
-	Default: 1048576 (16 * 65536)
+	Default: 4194304 (4 MB)
 
 tcp_challenge_ack_limit - INTEGER
 	Limits number of Challenge ACK sent per second, as recommended
diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 6327e689e8a8..c69cc89c958e 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -10,6 +10,7 @@ Type                                Name                        fastpath_tx_acce
 =================================== =========================== =================== =================== ===================================================================================
 unsigned_long:32                    priv_flags                  read_mostly                             __dev_queue_xmit(tx)
 unsigned_long:1                     lltx                        read_mostly                             HARD_TX_LOCK,HARD_TX_TRYLOCK,HARD_TX_UNLOCK(tx)
+unsigned long:1                     netmem_tx:1;                read_mostly
 char                                name[16]
 struct netdev_name_node*            name_node
 struct dev_ifalias*                 ifalias
@@ -131,7 +132,7 @@ struct ref_tracker_dir              refcnt_tracker
 struct list_head                    link_watch_list
 enum:8                              reg_state
 bool                                dismantle
-enum:16                             rtnl_link_state
+bool                                rtnl_link_initilizing
 bool                                needs_free_netdev
 void*priv_destructor                struct net_device
 struct netpoll_info*                npinfo                                          read_mostly         napi_poll/napi_poll_lock
diff --git a/Documentation/networking/netdev-features.rst b/Documentation/networking/netdev-features.rst
index 5014f7cc1398..02bd7536fc0c 100644
--- a/Documentation/networking/netdev-features.rst
+++ b/Documentation/networking/netdev-features.rst
@@ -188,3 +188,8 @@ Redundancy) frames from one port to another in hardware.
 This should be set for devices which duplicate outgoing HSR (High-availability
 Seamless Redundancy) or PRP (Parallel Redundancy Protocol) tags automatically
 frames in hardware.
+
+* netmem-tx
+
+This should be set for devices which support netmem TX. See
+Documentation/networking/netmem.rst
diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst
index f87bb55b4afe..7ebb6c36482d 100644
--- a/Documentation/networking/netdevices.rst
+++ b/Documentation/networking/netdevices.rst
@@ -8,7 +8,7 @@ Network Devices, the Kernel, and You!
 Introduction
 ============
 The following is a random collection of documentation regarding
-network devices.
+network devices. It is intended for driver developers.
 
 struct net_device lifetime rules
 ================================
@@ -387,12 +387,14 @@ For device drivers that implement shaping or queue management APIs,
 some of the notifiers (``enum netdev_cmd``) are running under the netdev
 instance lock.
 
+The following netdev notifiers are always run under the instance lock:
+* ``NETDEV_XDP_FEAT_CHANGE``
+
 For devices with locked ops, currently only the following notifiers are
 running under the lock:
 * ``NETDEV_CHANGE``
 * ``NETDEV_REGISTER``
 * ``NETDEV_UP``
-* ``NETDEV_XDP_FEAT_CHANGE``
 
 The following notifiers are running without the lock:
 * ``NETDEV_UNREGISTER``
diff --git a/Documentation/networking/netmem.rst b/Documentation/networking/netmem.rst
index 7de21ddb5412..b63aded46337 100644
--- a/Documentation/networking/netmem.rst
+++ b/Documentation/networking/netmem.rst
@@ -19,8 +19,8 @@ Benefits of Netmem :
 * Simplified Development: Drivers interact with a consistent API,
   regardless of the underlying memory implementation.
 
-Driver Requirements
-===================
+Driver RX Requirements
+======================
 
 1. The driver must support page_pool.
 
@@ -77,3 +77,22 @@ Driver Requirements
    that purpose, but be mindful that some netmem types might have longer
    circulation times, such as when userspace holds a reference in zerocopy
    scenarios.
+
+Driver TX Requirements
+======================
+
+1. The Driver must not pass the netmem dma_addr to any of the dma-mapping APIs
+   directly. This is because netmem dma_addrs may come from a source like
+   dma-buf that is not compatible with the dma-mapping APIs.
+
+   Helpers like netmem_dma_unmap_page_attrs() & netmem_dma_unmap_addr_set()
+   should be used in lieu of dma_unmap_page[_attrs](), dma_unmap_addr_set().
+   The netmem variants will handle netmem dma_addrs correctly regardless of the
+   source, delegating to the dma-mapping APIs when appropriate.
+
+   Not all dma-mapping APIs have netmem equivalents at the moment. If your
+   driver relies on a missing netmem API, feel free to add and propose to
+   netdev@, or reach out to the maintainers and/or almasrymina@google.com for
+   help adding the netmem API.
+
+2. Driver should declare support by setting `netdev->netmem_tx = true`
diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst
index e807e18ba32a..d63e3e27dd06 100644
--- a/Documentation/networking/rxrpc.rst
+++ b/Documentation/networking/rxrpc.rst
@@ -1062,30 +1062,6 @@ The kernel interface functions are as follows:
      first function to change.  Note that this must be called in TASK_RUNNING
      state.
 
- (#) Get remote client epoch::
-
-	u32 rxrpc_kernel_get_epoch(struct socket *sock,
-				   struct rxrpc_call *call)
-
-     This allows the epoch that's contained in packets of an incoming client
-     call to be queried.  This value is returned.  The function always
-     successful if the call is still in progress.  It shouldn't be called once
-     the call has expired.  Note that calling this on a local client call only
-     returns the local epoch.
-
-     This value can be used to determine if the remote client has been
-     restarted as it shouldn't change otherwise.
-
- (#) Set the maximum lifespan on a call::
-
-	void rxrpc_kernel_set_max_life(struct socket *sock,
-				       struct rxrpc_call *call,
-				       unsigned long hard_timeout)
-
-     This sets the maximum lifespan on a call to hard_timeout (which is in
-     jiffies).  In the event of the timeout occurring, the call will be
-     aborted and -ETIME or -ETIMEDOUT will be returned.
-
  (#) Apply the RXRPC_MIN_SECURITY_LEVEL sockopt to a socket from within in the
      kernel::
 
@@ -1172,3 +1148,18 @@ adjusted through sysctls in /proc/net/rxrpc/:
      header plus exactly 1412 bytes of data.  The terminal packet must contain
      a four byte header plus any amount of data.  In any event, a jumbo packet
      may not exceed rxrpc_rx_mtu in size.
+
+
+API Function Reference
+======================
+
+.. kernel-doc:: net/rxrpc/af_rxrpc.c
+.. kernel-doc:: net/rxrpc/call_object.c
+.. kernel-doc:: net/rxrpc/key.c
+.. kernel-doc:: net/rxrpc/oob.c
+.. kernel-doc:: net/rxrpc/peer_object.c
+.. kernel-doc:: net/rxrpc/recvmsg.c
+.. kernel-doc:: net/rxrpc/rxgk.c
+.. kernel-doc:: net/rxrpc/rxkad.c
+.. kernel-doc:: net/rxrpc/sendmsg.c
+.. kernel-doc:: net/rxrpc/server_key.c
diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst
index b8fef8101176..7aabead90648 100644
--- a/Documentation/networking/timestamping.rst
+++ b/Documentation/networking/timestamping.rst
@@ -811,11 +811,9 @@ Documentation/devicetree/bindings/ptp/timestamper.txt for more details.
 3.2.4 Other caveats for MAC drivers
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-Stacked PHCs, especially DSA (but not only) - since that doesn't require any
-modification to MAC drivers, so it is more difficult to ensure correctness of
-all possible code paths - is that they uncover bugs which were impossible to
-trigger before the existence of stacked PTP clocks.  One example has to do with
-this line of code, already presented earlier::
+The use of stacked PHCs may uncover MAC driver bugs which were impossible to
+trigger without them. One example has to do with this line of code, already
+presented earlier::
 
       skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 
diff --git a/Documentation/networking/tproxy.rst b/Documentation/networking/tproxy.rst
index 7f7c1ff6f159..75e4990cc3db 100644
--- a/Documentation/networking/tproxy.rst
+++ b/Documentation/networking/tproxy.rst
@@ -69,9 +69,9 @@ add rules like this to the iptables ruleset above::
     # iptables -t mangle -A PREROUTING -p tcp --dport 80 -j TPROXY \
       --tproxy-mark 0x1/0x1 --on-port 50080
 
-Or the following rule to nft:
+Or the following rule to nft::
 
-# nft add rule filter divert tcp dport 80 tproxy to :50080 meta mark set 1 accept
+    # nft add rule filter divert tcp dport 80 tproxy to :50080 meta mark set 1 accept
 
 Note that for this to work you'll have to modify the proxy to enable (SOL_IP,
 IP_TRANSPARENT) for the listening socket.
diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst
index 12f429359a82..63344bea8393 100644
--- a/Documentation/power/runtime_pm.rst
+++ b/Documentation/power/runtime_pm.rst
@@ -154,7 +154,7 @@ suspending the device are satisfied) and to queue up a suspend request for the
 device in that case.  If there is no idle callback, or if the callback returns
 0, then the PM core will attempt to carry out a runtime suspend of the device,
 also respecting devices configured for autosuspend.  In essence this means a
-call to __pm_runtime_autosuspend() (do note that drivers needs to update the
+call to pm_runtime_autosuspend() (do note that drivers needs to update the
 device last busy mark, pm_runtime_mark_last_busy(), to control the delay under
 this circumstance).  To prevent this (for example, if the callback routine has
 started a delayed suspend), the routine must return a non-zero value.  Negative
diff --git a/Documentation/translations/zh_CN/admin-guide/bug-hunting.rst b/Documentation/translations/zh_CN/admin-guide/bug-hunting.rst
index c3f6a83294dc..4b3432753eb9 100644
--- a/Documentation/translations/zh_CN/admin-guide/bug-hunting.rst
+++ b/Documentation/translations/zh_CN/admin-guide/bug-hunting.rst
@@ -188,7 +188,7 @@ objdump
 编行。如果没有调试符号，您将看到所示例程的汇编程序代码，但是如果内核有调试
 符号，C代码也将可见（调试符号可以在内核配置菜单的hacking项中启用）。例如::
 
-    $ objdump -r -S -l --disassemble net/dccp/ipv4.o
+    $ objdump -r -S -l --disassemble net/ipv4/tcp.o
 
 .. note::
 
diff --git a/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst b/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst
index cadc580fa23b..d728e4db0b85 100644
--- a/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst
+++ b/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst
@@ -17,10 +17,10 @@ OpenRISC 1000系列（或1k）。
 
 关于OpenRISC处理器和正在进行中的开发的信息:
 
-	=======		=============================
+	=======		==============================
 	网站		https://openrisc.io
-	邮箱		openrisc@lists.librecores.org
-	=======		=============================
+	邮箱		linux-openrisc@vger.kernel.org
+	=======		==============================
 
 ---------------------------------------------------------------------
 
@@ -36,11 +36,11 @@ OpenRISC工具链和Linux的构建指南
 工具链的构建指南可以在openrisc.io或Stafford的工具链构建和发布脚本
 中找到。
 
-	======      =================================================
-	二进制      https://github.com/openrisc/or1k-gcc/releases
+	======      ==========================================================
+	二进制      https://github.com/stffrdhrn/or1k-toolchain-build/releases
 	工具链      https://openrisc.io/software
 	构建        https://github.com/stffrdhrn/or1k-toolchain-build
-	======      =================================================
+	======      ==========================================================
 
 2) 构建
 
diff --git a/Documentation/translations/zh_TW/admin-guide/bug-hunting.rst b/Documentation/translations/zh_TW/admin-guide/bug-hunting.rst
index b25ecc44d735..80ea5677ee52 100644
--- a/Documentation/translations/zh_TW/admin-guide/bug-hunting.rst
+++ b/Documentation/translations/zh_TW/admin-guide/bug-hunting.rst
@@ -191,7 +191,7 @@ objdump
 編行。如果沒有調試符號，您將看到所示例程的彙編程序代碼，但是如果內核有調試
 符號，C代碼也將可見（調試符號可以在內核配置菜單的hacking項中啓用）。例如::
 
-    $ objdump -r -S -l --disassemble net/dccp/ipv4.o
+    $ objdump -r -S -l --disassemble net/ipv4/tcp.o
 
 .. note::
 
diff --git a/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst b/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst
index 422fe9f7a3f2..a1e4517dc601 100644
--- a/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst
+++ b/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst
@@ -17,10 +17,10 @@ OpenRISC 1000系列（或1k）。
 
 關於OpenRISC處理器和正在進行中的開發的信息:
 
-	=======		=============================
+	=======		==============================
 	網站		https://openrisc.io
-	郵箱		openrisc@lists.librecores.org
-	=======		=============================
+	郵箱		linux-openrisc@vger.kernel.org
+	=======		==============================
 
 ---------------------------------------------------------------------
 
@@ -36,11 +36,11 @@ OpenRISC工具鏈和Linux的構建指南
 工具鏈的構建指南可以在openrisc.io或Stafford的工具鏈構建和發佈腳本
 中找到。
 
-	======      =================================================
-	二進制      https://github.com/openrisc/or1k-gcc/releases
+	======      ==========================================================
+	二進制      https://github.com/stffrdhrn/or1k-toolchain-build/releases
 	工具鏈      https://openrisc.io/software
 	構建        https://github.com/stffrdhrn/or1k-toolchain-build
-	======      =================================================
+	======      ==========================================================
 
 2) 構建
 
diff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst
index 1dabfc29be0d..7195a7f91107 100644
--- a/Documentation/userspace-api/mseal.rst
+++ b/Documentation/userspace-api/mseal.rst
@@ -27,7 +27,7 @@ SYSCALL
 =======
 mseal syscall signature
 -----------------------
-   ``int mseal(void \* addr, size_t len, unsigned long flags)``
+   ``int mseal(void *addr, size_t len, unsigned long flags)``
 
    **addr**/**len**: virtual memory address range.
       The address range set by **addr**/**len** must meet:
diff --git a/Documentation/wmi/devices/msi-wmi-platform.rst b/Documentation/wmi/devices/msi-wmi-platform.rst
index 31a136942892..73197b31926a 100644
--- a/Documentation/wmi/devices/msi-wmi-platform.rst
+++ b/Documentation/wmi/devices/msi-wmi-platform.rst
@@ -138,6 +138,10 @@ input data, the meaning of which depends on the subfeature being accessed.
 The output buffer contains a single byte which signals success or failure (``0x00`` on failure)
 and 31 bytes of output data, the meaning if which depends on the subfeature being accessed.
 
+.. note::
+   The ACPI control method responsible for handling the WMI method calls is not thread-safe.
+   This is a firmware bug that needs to be handled inside the driver itself.
+
 WMI method Get_EC()
 -------------------
 
diff --git a/MAINTAINERS b/MAINTAINERS
index c59316109e3f..b0a3860dd44a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -646,6 +646,13 @@ F:	drivers/iio/accel/adxl380.h
 F:	drivers/iio/accel/adxl380_i2c.c
 F:	drivers/iio/accel/adxl380_spi.c
 
+AEONSEMI PHY DRIVER
+M:	Christian Marangi <ansuelsmth@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/aeonsemi,as21xxx.yaml
+F:	drivers/net/phy/as21xxx.c
+
 AF8133J THREE-AXIS MAGNETOMETER DRIVER
 M:	Ondřej Jirman <megi@xff.cz>
 S:	Maintained
@@ -2519,6 +2526,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
 F:	arch/arm/boot/dts/nxp/imx/
 F:	arch/arm/boot/dts/nxp/mxs/
 F:	arch/arm64/boot/dts/freescale/
+X:	Documentation/devicetree/bindings/media/i2c/
 X:	arch/arm64/boot/dts/freescale/fsl-*
 X:	arch/arm64/boot/dts/freescale/qoriq-*
 X:	drivers/media/i2c/
@@ -3191,6 +3199,12 @@ M:	Dinh Nguyen <dinguyen@kernel.org>
 S:	Maintained
 F:	drivers/clk/socfpga/
 
+ARM/SOCFPGA DWMAC GLUE LAYER
+M:	Maxime Chevallier <maxime.chevallier@bootlin.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/socfpga-dwmac.txt
+F:	drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+
 ARM/SOCFPGA EDAC BINDINGS
 M:	Matthew Gerlach <matthew.gerlach@altera.com>
 S:	Maintained
@@ -3867,8 +3881,9 @@ AUXILIARY BUS DRIVER
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 R:	Dave Ertman <david.m.ertman@intel.com>
 R:	Ira Weiny <ira.weiny@intel.com>
+R:	Leon Romanovsky <leon@kernel.org>
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
 F:	Documentation/driver-api/auxiliary_bus.rst
 F:	drivers/base/auxiliary.c
 F:	include/linux/auxiliary_bus.h
@@ -5259,6 +5274,7 @@ F:	include/uapi/linux/can/isotp.h
 F:	include/uapi/linux/can/raw.h
 F:	net/can/
 F:	net/sched/em_canid.c
+F:	tools/testing/selftests/net/can/
 
 CAN-J1939 NETWORK LAYER
 M:	Robin van der Gracht <robin@protonic.nl>
@@ -6335,6 +6351,7 @@ F:	Documentation/process/cve.rst
 
 CW1200 WLAN driver
 S:	Orphan
+L:	linux-wireless@vger.kernel.org
 F:	drivers/net/wireless/st/
 F:	include/linux/platform_data/net-cw1200.h
 
@@ -6546,15 +6563,6 @@ S:	Maintained
 F:	Documentation/scsi/dc395x.rst
 F:	drivers/scsi/dc395x.*
 
-DCCP PROTOCOL
-L:	dccp@vger.kernel.org
-S:	Orphan
-W:	http://www.linuxfoundation.org/collaborate/workgroups/networking/dccp
-F:	include/linux/dccp.h
-F:	include/linux/tfrc.h
-F:	include/uapi/linux/dccp.h
-F:	net/dccp/
-
 DEBUGOBJECTS:
 M:	Thomas Gleixner <tglx@linutronix.de>
 L:	linux-kernel@vger.kernel.org
@@ -7020,6 +7028,7 @@ L:	rust-for-linux@vger.kernel.org
 S:	Supported
 W:	https://rust-for-linux.com
 T:	git https://github.com/Rust-for-Linux/linux.git alloc-next
+F:	rust/helpers/dma.c
 F:	rust/kernel/dma.rs
 F:	samples/rust/rust_dma.rs
 
@@ -7225,7 +7234,7 @@ M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Danilo Krummrich <dakr@kernel.org>
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
 F:	Documentation/core-api/kobject.rst
 F:	drivers/base/
 F:	fs/debugfs/
@@ -8717,6 +8726,7 @@ M:	Chao Yu <chao@kernel.org>
 R:	Yue Hu <zbestahu@gmail.com>
 R:	Jeffle Xu <jefflexu@linux.alibaba.com>
 R:	Sandeep Dhavale <dhavale@google.com>
+R:	Hongbo Li <lihongbo22@huawei.com>
 L:	linux-erofs@lists.ozlabs.org
 S:	Maintained
 W:	https://erofs.docs.kernel.org
@@ -9376,6 +9386,7 @@ F:	Documentation/devicetree/bindings/net/nxp,netc-blk-ctrl.yaml
 F:	drivers/net/ethernet/freescale/enetc/
 F:	include/linux/fsl/enetc_mdio.h
 F:	include/linux/fsl/netc_global.h
+F:	include/linux/fsl/ntmp.h
 
 FREESCALE eTSEC ETHERNET DRIVER (GIANFAR)
 M:	Claudiu Manoil <claudiu.manoil@nxp.com>
@@ -10136,6 +10147,13 @@ F:	drivers/gpio/gpio-regmap.c
 F:	include/linux/gpio/regmap.h
 K:	(devm_)?gpio_regmap_(un)?register
 
+GPIO SLOPPY LOGIC ANALYZER
+M:	Wolfram Sang <wsa+renesas@sang-engineering.com>
+S:	Supported
+F:	Documentation/dev-tools/gpio-sloppy-logic-analyzer.rst
+F:	drivers/gpio/gpio-sloppy-logic-analyzer.c
+F:	tools/gpio/gpio-sloppy-logic-analyzer.sh
+
 GPIO SUBSYSTEM
 M:	Linus Walleij <linus.walleij@linaro.org>
 M:	Bartosz Golaszewski <brgl@bgdev.pl>
@@ -10455,14 +10473,20 @@ S:	Supported
 F:	drivers/infiniband/hw/hfi1
 
 HFS FILESYSTEM
+M:	Viacheslav Dubeyko <slava@dubeyko.com>
+M:	John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
+M:	Yangtao Li <frank.li@vivo.com>
 L:	linux-fsdevel@vger.kernel.org
-S:	Orphan
+S:	Maintained
 F:	Documentation/filesystems/hfs.rst
 F:	fs/hfs/
 
 HFSPLUS FILESYSTEM
+M:	Viacheslav Dubeyko <slava@dubeyko.com>
+M:	John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
+M:	Yangtao Li <frank.li@vivo.com>
 L:	linux-fsdevel@vger.kernel.org
-S:	Orphan
+S:	Maintained
 F:	Documentation/filesystems/hfsplus.rst
 F:	fs/hfsplus/
 
@@ -10947,6 +10971,13 @@ S:	Maintained
 F:	Documentation/networking/device_drivers/ethernet/huawei/hinic.rst
 F:	drivers/net/ethernet/huawei/hinic/
 
+HUAWEI 3RD GEN ETHERNET DRIVER
+M:	Fan Gong <gongfan1@huawei.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	Documentation/networking/device_drivers/ethernet/huawei/hinic3.rst
+F:	drivers/net/ethernet/huawei/hinic3/
+
 HUAWEI MATEBOOK E GO EMBEDDED CONTROLLER DRIVER
 M:	Pengyu Luo <mitltlatltl@gmail.com>
 S:	Maintained
@@ -10956,6 +10987,7 @@ F:	include/linux/platform_data/huawei-gaokun-ec.h
 
 HUGETLB SUBSYSTEM
 M:	Muchun Song <muchun.song@linux.dev>
+R:	Oscar Salvador <osalvador@suse.de>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-kernel-mm-hugepages
@@ -11219,7 +11251,6 @@ S:	Maintained
 F:	drivers/i2c/busses/i2c-cht-wc.c
 
 I2C/SMBUS ISMT DRIVER
-M:	Seth Heasley <seth.heasley@intel.com>
 M:	Neil Horman <nhorman@tuxdriver.com>
 L:	linux-i2c@vger.kernel.org
 F:	Documentation/i2c/busses/i2c-ismt.rst
@@ -11892,7 +11923,7 @@ F:	Documentation/networking/device_drivers/ethernet/intel/
 F:	drivers/net/ethernet/intel/
 F:	drivers/net/ethernet/intel/*/
 F:	include/linux/avf/virtchnl.h
-F:	include/linux/net/intel/iidc.h
+F:	include/linux/net/intel/*/
 
 INTEL ETHERNET PROTOCOL DRIVER FOR RDMA
 M:	Mustafa Ismail <mustafa.ismail@intel.com>
@@ -12812,6 +12843,7 @@ F:	lib/Kconfig.kcsan
 F:	scripts/Makefile.kcsan
 
 KDUMP
+M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Baoquan He <bhe@redhat.com>
 R:	Vivek Goyal <vgoyal@redhat.com>
 R:	Dave Young <dyoung@redhat.com>
@@ -13108,11 +13140,13 @@ KERNFS
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 M:	Tejun Heo <tj@kernel.org>
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
 F:	fs/kernfs/
 F:	include/linux/kernfs.h
 
 KEXEC
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	Baoquan He <bhe@redhat.com>
 L:	kexec@lists.infradead.org
 W:	http://kernel.org/pub/linux/utils/kernel/kexec/
 F:	include/linux/kexec.h
@@ -14285,6 +14319,7 @@ S:	Odd fixes
 F:	drivers/net/ethernet/marvell/sk*
 
 MARVELL LIBERTAS WIRELESS DRIVER
+L:	linux-wireless@vger.kernel.org
 L:	libertas-dev@lists.infradead.org
 S:	Orphan
 F:	drivers/net/wireless/marvell/libertas/
@@ -15021,6 +15056,7 @@ M:	Qingfang Deng <dqfext@gmail.com>
 M:	SkyLake Huang <SkyLake.Huang@mediatek.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
+F:	drivers/net/phy/mediatek/mtk-2p5ge.c
 F:	drivers/net/phy/mediatek/mtk-ge-soc.c
 F:	drivers/net/phy/mediatek/mtk-phy-lib.c
 F:	drivers/net/phy/mediatek/mtk-ge.c
@@ -15051,7 +15087,7 @@ F:	Documentation/devicetree/bindings/media/mediatek-jpeg-*.yaml
 F:	drivers/media/platform/mediatek/jpeg/
 
 MEDIATEK KEYPAD DRIVER
-M:	Mattijs Korpershoek <mkorpershoek@baylibre.com>
+M:	Mattijs Korpershoek <mkorpershoek@kernel.org>
 S:	Supported
 F:	Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
 F:	drivers/input/keyboard/mt6779-keypad.c
@@ -15474,24 +15510,45 @@ F:	Documentation/mm/
 F:	include/linux/gfp.h
 F:	include/linux/gfp_types.h
 F:	include/linux/memfd.h
-F:	include/linux/memory.h
 F:	include/linux/memory_hotplug.h
 F:	include/linux/memory-tiers.h
 F:	include/linux/mempolicy.h
 F:	include/linux/mempool.h
 F:	include/linux/memremap.h
-F:	include/linux/mm.h
-F:	include/linux/mm_*.h
 F:	include/linux/mmzone.h
 F:	include/linux/mmu_notifier.h
 F:	include/linux/pagewalk.h
-F:	include/linux/rmap.h
 F:	include/trace/events/ksm.h
 F:	mm/
 F:	tools/mm/
 F:	tools/testing/selftests/mm/
 N:	include/linux/page[-_]*
 
+MEMORY MANAGEMENT - CORE
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	David Hildenbrand <david@redhat.com>
+R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Liam R. Howlett <Liam.Howlett@oracle.com>
+R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Mike Rapoport <rppt@kernel.org>
+R:	Suren Baghdasaryan <surenb@google.com>
+R:	Michal Hocko <mhocko@suse.com>
+L:	linux-mm@kvack.org
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	include/linux/memory.h
+F:	include/linux/mm.h
+F:	include/linux/mm_*.h
+F:	include/linux/mmdebug.h
+F:	include/linux/pagewalk.h
+F:	mm/Kconfig
+F:	mm/debug.c
+F:	mm/init-mm.c
+F:	mm/memory.c
+F:	mm/pagewalk.c
+F:	mm/util.c
+
 MEMORY MANAGEMENT - EXECMEM
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Mike Rapoport <rppt@kernel.org>
@@ -15500,6 +15557,18 @@ S:	Maintained
 F:	include/linux/execmem.h
 F:	mm/execmem.c
 
+MEMORY MANAGEMENT - GUP (GET USER PAGES)
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	David Hildenbrand <david@redhat.com>
+R:	Jason Gunthorpe <jgg@nvidia.com>
+R:	John Hubbard <jhubbard@nvidia.com>
+R:	Peter Xu <peterx@redhat.com>
+L:	linux-mm@kvack.org
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	mm/gup.c
+
 MEMORY MANAGEMENT - NUMA MEMBLOCKS AND NUMA EMULATION
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Mike Rapoport <rppt@kernel.org>
@@ -15510,6 +15579,34 @@ F:	mm/numa.c
 F:	mm/numa_emulation.c
 F:	mm/numa_memblks.c
 
+MEMORY MANAGEMENT - PAGE ALLOCATOR
+M:	Andrew Morton <akpm@linux-foundation.org>
+R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Suren Baghdasaryan <surenb@google.com>
+R:	Michal Hocko <mhocko@suse.com>
+R:	Brendan Jackman <jackmanb@google.com>
+R:	Johannes Weiner <hannes@cmpxchg.org>
+R:	Zi Yan <ziy@nvidia.com>
+L:	linux-mm@kvack.org
+S:	Maintained
+F:	mm/compaction.c
+F:	mm/page_alloc.c
+F:	include/linux/gfp.h
+F:	include/linux/compaction.h
+
+MEMORY MANAGEMENT - RMAP (REVERSE MAPPING)
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	David Hildenbrand <david@redhat.com>
+M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Rik van Riel <riel@surriel.com>
+R:	Liam R. Howlett <Liam.Howlett@oracle.com>
+R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Harry Yoo <harry.yoo@oracle.com>
+L:	linux-mm@kvack.org
+S:	Maintained
+F:	include/linux/rmap.h
+F:	mm/rmap.c
+
 MEMORY MANAGEMENT - SECRETMEM
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Mike Rapoport <rppt@kernel.org>
@@ -15518,6 +15615,30 @@ S:	Maintained
 F:	include/linux/secretmem.h
 F:	mm/secretmem.c
 
+MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	David Hildenbrand <david@redhat.com>
+R:	Zi Yan <ziy@nvidia.com>
+R:	Baolin Wang <baolin.wang@linux.alibaba.com>
+R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Liam R. Howlett <Liam.Howlett@oracle.com>
+R:	Nico Pache <npache@redhat.com>
+R:	Ryan Roberts <ryan.roberts@arm.com>
+R:	Dev Jain <dev.jain@arm.com>
+L:	linux-mm@kvack.org
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	Documentation/admin-guide/mm/transhuge.rst
+F:	include/linux/huge_mm.h
+F:	include/linux/khugepaged.h
+F:	include/trace/events/huge_memory.h
+F:	mm/huge_memory.c
+F:	mm/khugepaged.c
+F:	tools/testing/selftests/mm/khugepaged.c
+F:	tools/testing/selftests/mm/split_huge_page_test.c
+F:	tools/testing/selftests/mm/transhuge-stress.c
+
 MEMORY MANAGEMENT - USERFAULTFD
 M:	Andrew Morton <akpm@linux-foundation.org>
 R:	Peter Xu <peterx@redhat.com>
@@ -15537,10 +15658,12 @@ M:	Liam R. Howlett <Liam.Howlett@oracle.com>
 M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 R:	Vlastimil Babka <vbabka@suse.cz>
 R:	Jann Horn <jannh@google.com>
+R:	Pedro Falcato <pfalcato@suse.de>
 L:	linux-mm@kvack.org
 S:	Maintained
 W:	http://www.linux-mm.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	include/trace/events/mmap.h
 F:	mm/mlock.c
 F:	mm/mmap.c
 F:	mm/mprotect.c
@@ -15551,6 +15674,36 @@ F:	mm/vma.h
 F:	mm/vma_internal.h
 F:	tools/testing/vma/
 
+MEMORY MAPPING - LOCKING
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	Suren Baghdasaryan <surenb@google.com>
+M:	Liam R. Howlett <Liam.Howlett@oracle.com>
+M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Shakeel Butt <shakeel.butt@linux.dev>
+L:	linux-mm@kvack.org
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	Documentation/mm/process_addrs.rst
+F:	include/linux/mmap_lock.h
+F:	include/trace/events/mmap_lock.h
+F:	mm/mmap_lock.c
+
+MEMORY MAPPING - MADVISE (MEMORY ADVICE)
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	Liam R. Howlett <Liam.Howlett@oracle.com>
+M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M:	David Hildenbrand <david@redhat.com>
+R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Jann Horn <jannh@google.com>
+L:	linux-mm@kvack.org
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	include/uapi/asm-generic/mman-common.h
+F:	mm/madvise.c
+
 MEMORY TECHNOLOGY DEVICES (MTD)
 M:	Miquel Raynal <miquel.raynal@bootlin.com>
 M:	Richard Weinberger <richard@nod.at>
@@ -16758,6 +16911,7 @@ F:	Documentation/networking/net_cachelines/net_device.rst
 F:	drivers/connector/
 F:	drivers/net/
 F:	drivers/ptp/
+F:	drivers/s390/net/
 F:	include/dt-bindings/net/
 F:	include/linux/cn_proc.h
 F:	include/linux/etherdevice.h
@@ -16767,6 +16921,7 @@ F:	include/linux/fddidevice.h
 F:	include/linux/hippidevice.h
 F:	include/linux/if_*
 F:	include/linux/inetdevice.h
+F:	include/linux/ism.h
 F:	include/linux/netdev*
 F:	include/linux/platform_data/wiznet.h
 F:	include/uapi/linux/cn_proc.h
@@ -16922,6 +17077,7 @@ X:	net/ceph/
 X:	net/mac80211/
 X:	net/rfkill/
 X:	net/wireless/
+X:	tools/testing/selftests/net/can/
 
 NETWORKING [IPSEC]
 M:	Steffen Klassert <steffen.klassert@secunet.com>
@@ -17370,7 +17526,7 @@ T:	git git://git.infradead.org/nvme.git
 F:	drivers/nvme/target/
 
 NVMEM FRAMEWORK
-M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+M:	Srinivas Kandagatla <srini@kernel.org>
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/srini/nvmem.git
 F:	Documentation/ABI/stable/sysfs-bus-nvmem
@@ -18134,6 +18290,18 @@ F:	arch/openrisc/
 F:	drivers/irqchip/irq-ompic.c
 F:	drivers/irqchip/irq-or1k-*
 
+OPENVPN DATA CHANNEL OFFLOAD
+M:	Antonio Quartulli <antonio@openvpn.net>
+R:	Sabrina Dubroca <sd@queasysnail.net>
+L:	openvpn-devel@lists.sourceforge.net (subscribers-only)
+L:	netdev@vger.kernel.org
+S:	Supported
+T:	git https://github.com/OpenVPN/ovpn-net-next.git
+F:	Documentation/netlink/specs/ovpn.yaml
+F:	drivers/net/ovpn/
+F:	include/uapi/linux/ovpn.h
+F:	tools/testing/selftests/net/ovpn/
+
 OPENVSWITCH
 M:	Aaron Conole <aconole@redhat.com>
 M:	Eelco Chaudron <echaudro@redhat.com>
@@ -18304,7 +18472,7 @@ F:	include/uapi/linux/ppdev.h
 PARAVIRT_OPS INTERFACE
 M:	Juergen Gross <jgross@suse.com>
 R:	Ajay Kaher <ajay.kaher@broadcom.com>
-R:	Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R:	Alexey Makhalov <alexey.makhalov@broadcom.com>
 R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	virtualization@lists.linux.dev
 L:	x86@kernel.org
@@ -18635,7 +18803,7 @@ F:	drivers/pci/controller/pci-xgene-msi.c
 PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS
 M:	Lorenzo Pieralisi <lpieralisi@kernel.org>
 M:	Krzysztof Wilczyński <kw@linux.com>
-R:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
 R:	Rob Herring <robh@kernel.org>
 L:	linux-pci@vger.kernel.org
 S:	Supported
@@ -18688,6 +18856,16 @@ F:	include/asm-generic/pci*
 F:	include/linux/of_pci.h
 F:	include/linux/pci*
 F:	include/uapi/linux/pci*
+
+PCI SUBSYSTEM [RUST]
+M:	Danilo Krummrich <dakr@kernel.org>
+R:	Bjorn Helgaas <bhelgaas@google.com>
+R:	Krzysztof Wilczyński <kwilczynski@kernel.org>
+L:	linux-pci@vger.kernel.org
+S:	Maintained
+C:	irc://irc.oftc.net/linux-pci
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git
+F:	rust/helpers/pci.c
 F:	rust/kernel/pci.rs
 F:	samples/rust/rust_driver_pci.rs
 
@@ -19575,7 +19753,7 @@ S:	Supported
 F:	drivers/crypto/intel/qat/
 
 QCOM AUDIO (ASoC) DRIVERS
-M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+M:	Srinivas Kandagatla <srini@kernel.org>
 L:	linux-sound@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Supported
@@ -19748,6 +19926,7 @@ F:	drivers/media/tuners/qt1010*
 
 QUALCOMM ATH12K WIRELESS DRIVER
 M:	Jeff Johnson <jjohnson@kernel.org>
+L:	linux-wireless@vger.kernel.org
 L:	ath12k@lists.infradead.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath12k
@@ -19757,6 +19936,7 @@ N:	ath12k
 
 QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
 M:	Jeff Johnson <jjohnson@kernel.org>
+L:	linux-wireless@vger.kernel.org
 L:	ath10k@lists.infradead.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath10k
@@ -19766,6 +19946,7 @@ N:	ath10k
 
 QUALCOMM ATHEROS ATH11K WIRELESS DRIVER
 M:	Jeff Johnson <jjohnson@kernel.org>
+L:	linux-wireless@vger.kernel.org
 L:	ath11k@lists.infradead.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath11k
@@ -19875,7 +20056,7 @@ F:	Documentation/devicetree/bindings/net/qcom,ethqos.yaml
 F:	drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
 
 QUALCOMM FASTRPC DRIVER
-M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+M:	Srinivas Kandagatla <srini@kernel.org>
 M:	Amol Maheshwari <amahesh@qti.qualcomm.com>
 L:	linux-arm-msm@vger.kernel.org
 L:	dri-devel@lists.freedesktop.org
@@ -20453,8 +20634,8 @@ F:	Documentation/devicetree/bindings/i2c/renesas,iic-emev2.yaml
 F:	drivers/i2c/busses/i2c-emev2.c
 
 RENESAS ETHERNET AVB DRIVER
-M:	Paul Barker <paul.barker.ct@bp.renesas.com>
 M:	Niklas Söderlund <niklas.soderlund@ragnatech.se>
+R:	Paul Barker <paul@pbarker.dev>
 L:	netdev@vger.kernel.org
 L:	linux-renesas-soc@vger.kernel.org
 S:	Maintained
@@ -20615,6 +20796,14 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/usb/renesas,rzn1-usbf.yaml
 F:	drivers/usb/gadget/udc/renesas_usbf.c
 
+RENESAS RZ/V2H(P) DWMAC GBETH GLUE LAYER DRIVER
+M:	Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
+L:	netdev@vger.kernel.org
+L:	linux-renesas-soc@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/renesas,r9a09g057-gbeth.yaml
+F:	drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c
+
 RENESAS RZ/V2M I2C DRIVER
 M:	Fabrizio Castro <fabrizio.castro.jz@renesas.com>
 L:	linux-i2c@vger.kernel.org
@@ -21255,6 +21444,7 @@ L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/s390/net/
+F:	include/linux/ism.h
 
 S390 PCI SUBSYSTEM
 M:	Niklas Schnelle <schnelle@linux.ibm.com>
@@ -21923,7 +22113,7 @@ S:	Maintained
 F:	drivers/media/rc/serial_ir.c
 
 SERIAL LOW-POWER INTER-CHIP MEDIA BUS (SLIMbus)
-M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+M:	Srinivas Kandagatla <srini@kernel.org>
 L:	linux-sound@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/slimbus/
@@ -22139,6 +22329,7 @@ F:	drivers/platform/x86/touchscreen_dmi.c
 
 SILICON LABS WIRELESS DRIVERS (for WFxxx series)
 M:	Jérôme Pouiller <jerome.pouiller@silabs.com>
+L:	linux-wireless@vger.kernel.org
 S:	Supported
 F:	Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
 F:	drivers/net/wireless/silabs/
@@ -22239,9 +22430,7 @@ F:	drivers/nvmem/layouts/sl28vpd.c
 
 SLAB ALLOCATOR
 M:	Christoph Lameter <cl@linux.com>
-M:	Pekka Enberg <penberg@kernel.org>
 M:	David Rientjes <rientjes@google.com>
-M:	Joonsoo Kim <iamjoonsoo.kim@lge.com>
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Vlastimil Babka <vbabka@suse.cz>
 R:	Roman Gushchin <roman.gushchin@linux.dev>
@@ -22656,9 +22845,15 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git
 F:	Documentation/devicetree/bindings/sound/
 F:	Documentation/sound/soc/
 F:	include/dt-bindings/sound/
+F:	include/sound/cs-amp-lib.h
+F:	include/sound/cs35l*
+F:	include/sound/cs4271.h
+F:	include/sound/cs42l*
+F:	include/sound/madera-pdata.h
 F:	include/sound/soc*
 F:	include/sound/sof.h
 F:	include/sound/sof/
+F:	include/sound/wm*.h
 F:	include/trace/events/sof*.h
 F:	include/uapi/sound/asoc.h
 F:	sound/soc/
@@ -22769,7 +22964,6 @@ F:	drivers/accessibility/speakup/
 
 SPEAR PLATFORM/CLOCK/PINCTRL SUPPORT
 M:	Viresh Kumar <vireshk@kernel.org>
-M:	Shiraz Hashim <shiraz.linux.kernel@gmail.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	soc@lists.linux.dev
 S:	Maintained
@@ -25128,9 +25322,13 @@ S:	Maintained
 F:	drivers/usb/typec/mux/pi3usb30532.c
 
 USB TYPEC PORT CONTROLLER DRIVERS
+M:	Badhri Jagan Sridharan <badhri@google.com>
 L:	linux-usb@vger.kernel.org
-S:	Orphan
-F:	drivers/usb/typec/tcpm/
+S:	Maintained
+F:	drivers/usb/typec/tcpm/tcpci.c
+F:	drivers/usb/typec/tcpm/tcpm.c
+F:	include/linux/usb/tcpci.h
+F:	include/linux/usb/tcpm.h
 
 USB TYPEC TUSB1046 MUX DRIVER
 M:	Romain Gantois <romain.gantois@bootlin.com>
@@ -25767,7 +25965,7 @@ F:	drivers/misc/vmw_balloon.c
 
 VMWARE HYPERVISOR INTERFACE
 M:	Ajay Kaher <ajay.kaher@broadcom.com>
-M:	Alexey Makhalov <alexey.amakhalov@broadcom.com>
+M:	Alexey Makhalov <alexey.makhalov@broadcom.com>
 R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	virtualization@lists.linux.dev
 L:	x86@kernel.org
@@ -25795,7 +25993,7 @@ F:	drivers/scsi/vmw_pvscsi.h
 VMWARE VIRTUAL PTP CLOCK DRIVER
 M:	Nick Shi <nick.shi@broadcom.com>
 R:	Ajay Kaher <ajay.kaher@broadcom.com>
-R:	Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R:	Alexey Makhalov <alexey.makhalov@broadcom.com>
 R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	netdev@vger.kernel.org
 S:	Supported
diff --git a/Makefile b/Makefile
index f42418556507..a9edd0303653 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc7
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
@@ -477,7 +477,6 @@ export rust_common_flags := --edition=2021 \
 			    -Wclippy::ignored_unit_patterns \
 			    -Wclippy::mut_mut \
 			    -Wclippy::needless_bitwise_bool \
-			    -Wclippy::needless_continue \
 			    -Aclippy::needless_lifetimes \
 			    -Wclippy::no_mangle_with_rust_abi \
 			    -Wclippy::undocumented_unsafe_blocks \
@@ -1053,10 +1052,6 @@ NOSTDINC_FLAGS += -nostdinc
 # perform bounds checking.
 KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3)
 
-#Currently, disable -Wstringop-overflow for GCC 11, globally.
-KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow)
-KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
-
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= -fno-strict-overflow
 
@@ -1073,8 +1068,7 @@ KBUILD_CFLAGS += -fno-builtin-wcslen
 
 # change __FILE__ to the relative path to the source directory
 ifdef building_out_of_srctree
-KBUILD_CPPFLAGS += $(call cc-option,-ffile-prefix-map=$(srcroot)/=)
-KBUILD_RUSTFLAGS += --remap-path-prefix=$(srcroot)/=
+KBUILD_CPPFLAGS += $(call cc-option,-fmacro-prefix-map=$(srcroot)/=)
 endif
 
 # include additional Makefiles when needed
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 3df5f2dd4c0f..8f1f18adcdb5 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -150,6 +150,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/arm/boot/dts/amlogic/meson8.dtsi b/arch/arm/boot/dts/amlogic/meson8.dtsi
index 847f7b1f1e96..f785e0de0847 100644
--- a/arch/arm/boot/dts/amlogic/meson8.dtsi
+++ b/arch/arm/boot/dts/amlogic/meson8.dtsi
@@ -451,7 +451,7 @@
 	pwm_ef: pwm@86c0 {
 		compatible = "amlogic,meson8-pwm-v2";
 		clocks = <&xtal>,
-			 <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+			 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
 			 <&clkc CLKID_FCLK_DIV4>,
 			 <&clkc CLKID_FCLK_DIV3>;
 		reg = <0x86c0 0x10>;
@@ -705,7 +705,7 @@
 &pwm_ab {
 	compatible = "amlogic,meson8-pwm-v2";
 	clocks = <&xtal>,
-		 <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+		 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
 		 <&clkc CLKID_FCLK_DIV4>,
 		 <&clkc CLKID_FCLK_DIV3>;
 };
@@ -713,7 +713,7 @@
 &pwm_cd {
 	compatible = "amlogic,meson8-pwm-v2";
 	clocks = <&xtal>,
-		 <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+		 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
 		 <&clkc CLKID_FCLK_DIV4>,
 		 <&clkc CLKID_FCLK_DIV3>;
 };
diff --git a/arch/arm/boot/dts/amlogic/meson8b.dtsi b/arch/arm/boot/dts/amlogic/meson8b.dtsi
index 0876611ce26a..fdb0abe23a0c 100644
--- a/arch/arm/boot/dts/amlogic/meson8b.dtsi
+++ b/arch/arm/boot/dts/amlogic/meson8b.dtsi
@@ -406,7 +406,7 @@
 		compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2";
 		reg = <0x86c0 0x10>;
 		clocks = <&xtal>,
-			 <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+			 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
 			 <&clkc CLKID_FCLK_DIV4>,
 			 <&clkc CLKID_FCLK_DIV3>;
 		#pwm-cells = <3>;
@@ -680,7 +680,7 @@
 &pwm_ab {
 	compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2";
 	clocks = <&xtal>,
-		 <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+		 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
 		 <&clkc CLKID_FCLK_DIV4>,
 		 <&clkc CLKID_FCLK_DIV3>;
 };
@@ -688,7 +688,7 @@
 &pwm_cd {
 	compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2";
 	clocks = <&xtal>,
-		 <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+		 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
 		 <&clkc CLKID_FCLK_DIV4>,
 		 <&clkc CLKID_FCLK_DIV3>;
 };
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
index f2386dcb9ff2..dda4fa91b2f2 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
@@ -40,6 +40,9 @@
 			reg = <1>;
 			interrupt-parent = <&gpio4>;
 			interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
+			micrel,led-mode = <1>;
+			clocks = <&clks IMX6UL_CLK_ENET_REF>;
+			clock-names = "rmii-ref";
 			status = "okay";
 		};
 	};
diff --git a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
index da9de4986660..5a72f0b64247 100644
--- a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
+++ b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
@@ -151,7 +151,7 @@
 			al,msi-num-spis = <160>;
 		};
 
-		io-fabric@fc000000 {
+		io-bus@fc000000 {
 			compatible = "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
index 8b6156b5af65..dea60d136c2e 100644
--- a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
+++ b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
@@ -361,7 +361,7 @@
 			interrupt-parent = <&gic>;
 		};
 
-		io-fabric@fc000000 {
+		io-bus@fc000000 {
 			compatible = "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
index ab2b3f15ef19..69834b49673d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
@@ -2313,7 +2313,7 @@
 					     "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x19000 0x0 0x20>;
 				clocks = <&xtal>,
-					 <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+					 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
 					 <&clkc CLKID_FCLK_DIV4>,
 					 <&clkc CLKID_FCLK_DIV3>;
 				#pwm-cells = <3>;
@@ -2325,7 +2325,7 @@
 					     "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x1a000 0x0 0x20>;
 				clocks = <&xtal>,
-					 <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+					 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
 					 <&clkc CLKID_FCLK_DIV4>,
 					 <&clkc CLKID_FCLK_DIV3>;
 				#pwm-cells = <3>;
@@ -2337,7 +2337,7 @@
 					     "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x1b000 0x0 0x20>;
 				clocks = <&xtal>,
-					 <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+					 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
 					 <&clkc CLKID_FCLK_DIV4>,
 					 <&clkc CLKID_FCLK_DIV3>;
 				#pwm-cells = <3>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi
index de35fa2d7a6d..8e3e3354ed67 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi
@@ -116,6 +116,10 @@
 	status = "okay";
 };
 
+&clkc_audio {
+	status = "okay";
+};
+
 &frddr_a {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 8ebce7114a60..6c134592c7bb 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -741,7 +741,7 @@
 
 &pwm_ab {
 	clocks = <&xtal>,
-		 <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
 		 <&clkc CLKID_FCLK_DIV4>,
 		 <&clkc CLKID_FCLK_DIV3>;
 };
@@ -752,14 +752,14 @@
 
 &pwm_cd {
 	clocks = <&xtal>,
-		 <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
 		 <&clkc CLKID_FCLK_DIV4>,
 		 <&clkc CLKID_FCLK_DIV3>;
 };
 
 &pwm_ef {
 	clocks = <&xtal>,
-		 <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
 		 <&clkc CLKID_FCLK_DIV4>,
 		 <&clkc CLKID_FCLK_DIV3>;
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 2dc2fdaecf9f..19b8a39de6a0 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -811,7 +811,7 @@
 
 &pwm_ab {
 	clocks = <&xtal>,
-		 <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
 		 <&clkc CLKID_FCLK_DIV4>,
 		 <&clkc CLKID_FCLK_DIV3>;
 };
@@ -822,14 +822,14 @@
 
 &pwm_cd {
 	clocks = <&xtal>,
-		 <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
 		 <&clkc CLKID_FCLK_DIV4>,
 		 <&clkc CLKID_FCLK_DIV3>;
 };
 
 &pwm_ef {
 	clocks = <&xtal>,
-		 <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
 		 <&clkc CLKID_FCLK_DIV4>,
 		 <&clkc CLKID_FCLK_DIV3>;
 };
diff --git a/arch/arm64/boot/dts/apple/t8103-j293.dts b/arch/arm64/boot/dts/apple/t8103-j293.dts
index 2dfe7b895b2b..e2d9439397f7 100644
--- a/arch/arm64/boot/dts/apple/t8103-j293.dts
+++ b/arch/arm64/boot/dts/apple/t8103-j293.dts
@@ -77,6 +77,16 @@
 	};
 };
 
+/*
+ * The driver depends on boot loader initialized state which resets when this
+ * power-domain is powered off. This happens on suspend or when the driver is
+ * missing during boot. Mark the domain as always on until the driver can
+ * handle this.
+ */
+&ps_dispdfr_be {
+	apple,always-on;
+};
+
 &display_dfr {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/apple/t8112-j493.dts b/arch/arm64/boot/dts/apple/t8112-j493.dts
index 3d73f9ee2f46..be86d34c6696 100644
--- a/arch/arm64/boot/dts/apple/t8112-j493.dts
+++ b/arch/arm64/boot/dts/apple/t8112-j493.dts
@@ -40,6 +40,16 @@
 	};
 };
 
+/*
+ * The driver depends on boot loader initialized state which resets when this
+ * power-domain is powered off. This happens on suspend or when the driver is
+ * missing during boot. Mark the domain as always on until the driver can
+ * handle this.
+ */
+&ps_dispdfr_be {
+	apple,always-on;
+};
+
 &display_dfr {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/arm/morello.dtsi b/arch/arm64/boot/dts/arm/morello.dtsi
index 0bab0b3ea969..5bc1c725dc86 100644
--- a/arch/arm64/boot/dts/arm/morello.dtsi
+++ b/arch/arm64/boot/dts/arm/morello.dtsi
@@ -44,7 +44,7 @@
 			next-level-cache = <&l2_0>;
 			clocks = <&scmi_dvfs 0>;
 
-			l2_0: l2-cache-0 {
+			l2_0: l2-cache {
 				compatible = "cache";
 				cache-level = <2>;
 				/* 8 ways set associative */
@@ -53,13 +53,6 @@
 				cache-sets = <2048>;
 				cache-unified;
 				next-level-cache = <&l3_0>;
-
-				l3_0: l3-cache {
-					compatible = "cache";
-					cache-level = <3>;
-					cache-size = <0x100000>;
-					cache-unified;
-				};
 			};
 		};
 
@@ -78,7 +71,7 @@
 			next-level-cache = <&l2_1>;
 			clocks = <&scmi_dvfs 0>;
 
-			l2_1: l2-cache-1 {
+			l2_1: l2-cache {
 				compatible = "cache";
 				cache-level = <2>;
 				/* 8 ways set associative */
@@ -105,7 +98,7 @@
 			next-level-cache = <&l2_2>;
 			clocks = <&scmi_dvfs 1>;
 
-			l2_2: l2-cache-2 {
+			l2_2: l2-cache {
 				compatible = "cache";
 				cache-level = <2>;
 				/* 8 ways set associative */
@@ -132,7 +125,7 @@
 			next-level-cache = <&l2_3>;
 			clocks = <&scmi_dvfs 1>;
 
-			l2_3: l2-cache-3 {
+			l2_3: l2-cache {
 				compatible = "cache";
 				cache-level = <2>;
 				/* 8 ways set associative */
@@ -143,6 +136,13 @@
 				next-level-cache = <&l3_0>;
 			};
 		};
+
+		l3_0: l3-cache {
+			compatible = "cache";
+			cache-level = <3>;
+			cache-size = <0x100000>;
+			cache-unified;
+		};
 	};
 
 	firmware {
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
index 7251ad3a0017..b46566f3ce20 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
@@ -144,6 +144,19 @@
 		startup-delay-us = <20000>;
 	};
 
+	reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc {
+		compatible = "regulator-gpio";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usdhc2_vsel>;
+		gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <1800000>;
+		states = <1800000 0x1>,
+			 <3300000 0x0>;
+		regulator-name = "PMIC_USDHC_VSELECT";
+		vin-supply = <&reg_nvcc_sd>;
+	};
+
 	reserved-memory {
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -269,7 +282,7 @@
 			  "SODIMM_19",
 			  "",
 			  "",
-			  "",
+			  "PMIC_USDHC_VSELECT",
 			  "",
 			  "",
 			  "",
@@ -785,6 +798,7 @@
 	pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_cd>;
 	pinctrl-3 = <&pinctrl_usdhc2_sleep>, <&pinctrl_usdhc2_cd_sleep>;
 	vmmc-supply = <&reg_usdhc2_vmmc>;
+	vqmmc-supply = <&reg_usdhc2_vqmmc>;
 };
 
 &wdog1 {
@@ -1206,13 +1220,17 @@
 			<MX8MM_IOMUXC_NAND_CLE_GPIO3_IO5		0x6>;	/* SODIMM 76 */
 	};
 
+	pinctrl_usdhc2_vsel: usdhc2vselgrp {
+		fsl,pins =
+			<MX8MM_IOMUXC_GPIO1_IO04_GPIO1_IO4	0x10>; /* PMIC_USDHC_VSELECT */
+	};
+
 	/*
 	 * Note: Due to ERR050080 we use discrete external on-module resistors pulling-up to the
 	 * on-module +V3.3_1.8_SD (LDO5) rail and explicitly disable the internal pull-ups here.
 	 */
 	pinctrl_usdhc2: usdhc2grp {
 		fsl,pins =
-			<MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x10>,
 			<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK		0x90>,	/* SODIMM 78 */
 			<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD		0x90>,	/* SODIMM 74 */
 			<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x90>,	/* SODIMM 80 */
@@ -1223,7 +1241,6 @@
 
 	pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
 		fsl,pins =
-			<MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x10>,
 			<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK		0x94>,
 			<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD		0x94>,
 			<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x94>,
@@ -1234,7 +1251,6 @@
 
 	pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
 		fsl,pins =
-			<MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x10>,
 			<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK		0x96>,
 			<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD		0x96>,
 			<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x96>,
@@ -1246,7 +1262,6 @@
 	/* Avoid backfeeding with removed card power */
 	pinctrl_usdhc2_sleep: usdhc2slpgrp {
 		fsl,pins =
-			<MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x0>,
 			<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK		0x0>,
 			<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD		0x0>,
 			<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x0>,
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi
index a1b75c9068b2..2ce1860b244d 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi
@@ -24,6 +24,20 @@
 	fsl,operating-mode = "nominal";
 };
 
+&gpu2d {
+	assigned-clocks = <&clk IMX8MP_CLK_GPU2D_CORE>;
+	assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>;
+	assigned-clock-rates = <800000000>;
+};
+
+&gpu3d {
+	assigned-clocks = <&clk IMX8MP_CLK_GPU3D_CORE>,
+			  <&clk IMX8MP_CLK_GPU3D_SHADER_CORE>;
+	assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+				 <&clk IMX8MP_SYS_PLL1_800M>;
+	assigned-clock-rates = <800000000>, <800000000>;
+};
+
 &pgc_hdmimix {
 	assigned-clocks = <&clk IMX8MP_CLK_HDMI_AXI>,
 			  <&clk IMX8MP_CLK_HDMI_APB>;
@@ -46,6 +60,18 @@
 	assigned-clock-rates = <600000000>, <300000000>;
 };
 
+&pgc_mlmix {
+	assigned-clocks = <&clk IMX8MP_CLK_ML_CORE>,
+			  <&clk IMX8MP_CLK_ML_AXI>,
+			  <&clk IMX8MP_CLK_ML_AHB>;
+	assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+				 <&clk IMX8MP_SYS_PLL1_800M>,
+				 <&clk IMX8MP_SYS_PLL1_800M>;
+	assigned-clock-rates = <800000000>,
+			       <800000000>,
+			       <300000000>;
+};
+
 &media_blk_ctrl {
 	assigned-clocks = <&clk IMX8MP_CLK_MEDIA_AXI>,
 			  <&clk IMX8MP_CLK_MEDIA_APB>,
@@ -62,3 +88,5 @@
 			       <0>, <0>, <400000000>,
 			       <1039500000>;
 };
+
+/delete-node/ &{noc_opp_table/opp-1000000000};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi
index b2ac2583a592..b59da91fdd04 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi
@@ -35,7 +35,6 @@
 		      <0x1 0x00000000 0 0xc0000000>;
 	};
 
-
 	reg_usdhc2_vmmc: regulator-usdhc2-vmmc {
 	        compatible = "regulator-fixed";
 	        regulator-name = "VSD_3V3";
@@ -46,6 +45,16 @@
 	        startup-delay-us = <100>;
 	        off-on-delay-us = <12000>;
 	};
+
+	reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc {
+		compatible = "regulator-gpio";
+		regulator-name = "VSD_VSEL";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <3300000>;
+		gpios = <&gpio2 12 GPIO_ACTIVE_HIGH>;
+		states = <3300000 0x0 1800000 0x1>;
+		vin-supply = <&ldo5>;
+	};
 };
 
 &A53_0 {
@@ -205,6 +214,7 @@
         pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>;
         cd-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>;
         vmmc-supply = <&reg_usdhc2_vmmc>;
+	vqmmc-supply = <&reg_usdhc2_vqmmc>;
         bus-width = <4>;
         status = "okay";
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index ce6793b2d57e..7c1c87eab54c 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -1645,6 +1645,12 @@
 					opp-hz = /bits/ 64 <200000000>;
 				};
 
+				/* Nominal drive mode maximum */
+				opp-800000000 {
+					opp-hz = /bits/ 64 <800000000>;
+				};
+
+				/* Overdrive mode maximum */
 				opp-1000000000 {
 					opp-hz = /bits/ 64 <1000000000>;
 				};
diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi
index 9bb26b466a06..59f057ba6fa7 100644
--- a/arch/arm64/boot/dts/freescale/imx95.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx95.dtsi
@@ -1626,7 +1626,7 @@
 			reg = <0 0x4c300000 0 0x10000>,
 			      <0 0x60100000 0 0xfe00000>,
 			      <0 0x4c360000 0 0x10000>,
-			      <0 0x4c340000 0 0x2000>;
+			      <0 0x4c340000 0 0x4000>;
 			reg-names = "dbi", "config", "atu", "app";
 			ranges = <0x81000000 0x0 0x00000000 0x0 0x6ff00000 0 0x00100000>,
 				 <0x82000000 0x0 0x10000000 0x9 0x10000000 0 0x10000000>;
@@ -1673,7 +1673,7 @@
 			reg = <0 0x4c300000 0 0x10000>,
 			      <0 0x4c360000 0 0x1000>,
 			      <0 0x4c320000 0 0x1000>,
-			      <0 0x4c340000 0 0x2000>,
+			      <0 0x4c340000 0 0x4000>,
 			      <0 0x4c370000 0 0x10000>,
 			      <0x9 0 1 0>;
 			reg-names = "dbi","atu", "dbi2", "app", "dma", "addr_space";
@@ -1700,7 +1700,7 @@
 			reg = <0 0x4c380000 0 0x10000>,
 			      <8 0x80100000 0 0xfe00000>,
 			      <0 0x4c3e0000 0 0x10000>,
-			      <0 0x4c3c0000 0 0x2000>;
+			      <0 0x4c3c0000 0 0x4000>;
 			reg-names = "dbi", "config", "atu", "app";
 			ranges = <0x81000000 0 0x00000000 0x8 0x8ff00000 0 0x00100000>,
 				 <0x82000000 0 0x10000000 0xa 0x10000000 0 0x10000000>;
@@ -1749,7 +1749,7 @@
 			reg = <0 0x4c380000 0 0x10000>,
 			      <0 0x4c3e0000 0 0x1000>,
 			      <0 0x4c3a0000 0 0x1000>,
-			      <0 0x4c3c0000 0 0x2000>,
+			      <0 0x4c3c0000 0 0x4000>,
 			      <0 0x4c3f0000 0 0x10000>,
 			      <0xa 0 1 0>;
 			reg-names = "dbi", "atu", "dbi2", "app", "dma", "addr_space";
diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi b/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
index 1edfd643b25a..a334ef0629d1 100644
--- a/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
@@ -31,7 +31,7 @@
 	};
 
 	vcc3v3_btreg: vcc3v3-btreg {
-		compatible = "regulator-gpio";
+		compatible = "regulator-fixed";
 		enable-active-high;
 		pinctrl-names = "default";
 		pinctrl-0 = <&bt_enable_h>;
@@ -39,7 +39,6 @@
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 		regulator-always-on;
-		states = <3300000 0x0>;
 	};
 
 	vcc3v3_rf_aux_mod: regulator-vcc3v3-rf-aux-mod {
diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi b/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi
index 80db778c9684..b60e68faa83a 100644
--- a/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi
@@ -26,5 +26,5 @@
 };
 
 &vcc3v3_btreg {
-	enable-gpios = <&gpio1 RK_PC3 GPIO_ACTIVE_HIGH>;
+	gpios = <&gpio1 RK_PC3 GPIO_ACTIVE_HIGH>;
 };
diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts
index 165d09ccb942..5886b802c520 100644
--- a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts
@@ -39,5 +39,5 @@
 };
 
 &vcc3v3_btreg {
-	enable-gpios = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>;
+	gpios = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>;
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
index 541dca12bf1a..046dbe329017 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
@@ -43,7 +43,7 @@
 	sdio_pwrseq: sdio-pwrseq {
 		compatible = "mmc-pwrseq-simple";
 		clocks = <&rk808 1>;
-		clock-names = "lpo";
+		clock-names = "ext_clock";
 		pinctrl-names = "default";
 		pinctrl-0 = <&wifi_enable_h>;
 		reset-gpios = <&gpio0 RK_PB2 GPIO_ACTIVE_LOW>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
index a48351471764..e7ba477e75f9 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
@@ -775,7 +775,7 @@
 	rockchip,default-sample-phase = <90>;
 	status = "okay";
 
-	sdio-wifi@1 {
+	wifi@1 {
 		compatible = "brcm,bcm4329-fmac";
 		reg = <1>;
 		interrupt-parent = <&gpio2>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts
index 7bd32d230ad2..b80d628c426b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts
@@ -619,6 +619,8 @@
 	bus-width = <8>;
 	max-frequency = <200000000>;
 	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd &emmc_datastrobe>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
index 828bde7fab68..314067ba6f3c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
@@ -610,7 +610,7 @@
 		reg = <0x51>;
 		clock-output-names = "hym8563";
 		interrupt-parent = <&gpio0>;
-		interrupts = <RK_PB0 IRQ_TYPE_LEVEL_LOW>;
+		interrupts = <RK_PA0 IRQ_TYPE_LEVEL_LOW>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&hym8563_int>;
 		wakeup-source;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi
index 1af0a30866f6..af431fdcbea7 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi
@@ -222,6 +222,10 @@
 		compatible = "realtek,rt5616";
 		reg = <0x1b>;
 		#sound-dai-cells = <0>;
+		assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
+		assigned-clock-rates = <12288000>;
+		clocks = <&cru I2S0_8CH_MCLKOUT>;
+		clock-names = "mclk";
 	};
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
index 711ac4f2c7cb..60ad272982ad 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
@@ -214,6 +214,8 @@
 };
 
 &package_thermal {
+	polling-delay = <1000>;
+
 	trips {
 		package_active1: trip-active1 {
 			temperature = <45000>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
index bce72bac4503..3045cb3bd68c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
@@ -11,20 +11,15 @@
 		compatible = "operating-points-v2";
 		opp-shared;
 
-		opp-1416000000 {
-			opp-hz = /bits/ 64 <1416000000>;
+		opp-1200000000 {
+			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <750000 750000 950000>;
 			clock-latency-ns = <40000>;
 			opp-suspend;
 		};
-		opp-1608000000 {
-			opp-hz = /bits/ 64 <1608000000>;
-			opp-microvolt = <887500 887500 950000>;
-			clock-latency-ns = <40000>;
-		};
-		opp-1704000000 {
-			opp-hz = /bits/ 64 <1704000000>;
-			opp-microvolt = <937500 937500 950000>;
+		opp-1296000000 {
+			opp-hz = /bits/ 64 <1296000000>;
+			opp-microvolt = <775000 775000 950000>;
 			clock-latency-ns = <40000>;
 		};
 	};
@@ -33,9 +28,14 @@
 		compatible = "operating-points-v2";
 		opp-shared;
 
+		opp-1200000000{
+			opp-hz = /bits/ 64 <1200000000>;
+			opp-microvolt = <750000 750000 950000>;
+			clock-latency-ns = <40000>;
+		};
 		opp-1416000000 {
 			opp-hz = /bits/ 64 <1416000000>;
-			opp-microvolt = <750000 750000 950000>;
+			opp-microvolt = <762500 762500 950000>;
 			clock-latency-ns = <40000>;
 		};
 		opp-1608000000 {
@@ -43,25 +43,20 @@
 			opp-microvolt = <787500 787500 950000>;
 			clock-latency-ns = <40000>;
 		};
-		opp-1800000000 {
-			opp-hz = /bits/ 64 <1800000000>;
-			opp-microvolt = <875000 875000 950000>;
-			clock-latency-ns = <40000>;
-		};
-		opp-2016000000 {
-			opp-hz = /bits/ 64 <2016000000>;
-			opp-microvolt = <950000 950000 950000>;
-			clock-latency-ns = <40000>;
-		};
 	};
 
 	cluster2_opp_table: opp-table-cluster2 {
 		compatible = "operating-points-v2";
 		opp-shared;
 
+		opp-1200000000{
+			opp-hz = /bits/ 64 <1200000000>;
+			opp-microvolt = <750000 750000 950000>;
+			clock-latency-ns = <40000>;
+		};
 		opp-1416000000 {
 			opp-hz = /bits/ 64 <1416000000>;
-			opp-microvolt = <750000 750000 950000>;
+			opp-microvolt = <762500 762500 950000>;
 			clock-latency-ns = <40000>;
 		};
 		opp-1608000000 {
@@ -69,16 +64,6 @@
 			opp-microvolt = <787500 787500 950000>;
 			clock-latency-ns = <40000>;
 		};
-		opp-1800000000 {
-			opp-hz = /bits/ 64 <1800000000>;
-			opp-microvolt = <875000 875000 950000>;
-			clock-latency-ns = <40000>;
-		};
-		opp-2016000000 {
-			opp-hz = /bits/ 64 <2016000000>;
-			opp-microvolt = <950000 950000 950000>;
-			clock-latency-ns = <40000>;
-		};
 	};
 
 	gpu_opp_table: opp-table {
@@ -104,10 +89,6 @@
 			opp-hz = /bits/ 64 <700000000>;
 			opp-microvolt = <750000 750000 850000>;
 		};
-		opp-850000000 {
-			opp-hz = /bits/ 64 <800000000>;
-			opp-microvolt = <787500 787500 850000>;
-		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/st/stm32mp211.dtsi b/arch/arm64/boot/dts/st/stm32mp211.dtsi
index 6dd1377f3e1d..bf888d60cd4f 100644
--- a/arch/arm64/boot/dts/st/stm32mp211.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp211.dtsi
@@ -116,11 +116,11 @@
 		};
 
 		intc: interrupt-controller@4ac10000 {
-			compatible = "arm,cortex-a7-gic";
+			compatible = "arm,gic-400";
 			reg = <0x4ac10000 0x0 0x1000>,
-			      <0x4ac20000 0x0 0x2000>,
-			      <0x4ac40000 0x0 0x2000>,
-			      <0x4ac60000 0x0 0x2000>;
+			      <0x4ac20000 0x0 0x20000>,
+			      <0x4ac40000 0x0 0x20000>,
+			      <0x4ac60000 0x0 0x20000>;
 			      #interrupt-cells = <3>;
 			      interrupt-controller;
 		};
diff --git a/arch/arm64/boot/dts/st/stm32mp231.dtsi b/arch/arm64/boot/dts/st/stm32mp231.dtsi
index 8820d219a33e..75697acd1345 100644
--- a/arch/arm64/boot/dts/st/stm32mp231.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp231.dtsi
@@ -1201,13 +1201,12 @@
 		};
 
 		intc: interrupt-controller@4ac10000 {
-			compatible = "arm,cortex-a7-gic";
+			compatible = "arm,gic-400";
 			reg = <0x4ac10000 0x1000>,
-			      <0x4ac20000 0x2000>,
-			      <0x4ac40000 0x2000>,
-			      <0x4ac60000 0x2000>;
+			      <0x4ac20000 0x20000>,
+			      <0x4ac40000 0x20000>,
+			      <0x4ac60000 0x20000>;
 			#interrupt-cells = <3>;
-			#address-cells = <1>;
 			interrupt-controller;
 		};
 	};
diff --git a/arch/arm64/boot/dts/st/stm32mp251.dtsi b/arch/arm64/boot/dts/st/stm32mp251.dtsi
index f3c6cdfd7008..87110f91e489 100644
--- a/arch/arm64/boot/dts/st/stm32mp251.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp251.dtsi
@@ -115,14 +115,13 @@
 	};
 
 	intc: interrupt-controller@4ac00000 {
-		compatible = "arm,cortex-a7-gic";
+		compatible = "arm,gic-400";
 		#interrupt-cells = <3>;
-		#address-cells = <1>;
 		interrupt-controller;
 		reg = <0x0 0x4ac10000 0x0 0x1000>,
-		      <0x0 0x4ac20000 0x0 0x2000>,
-		      <0x0 0x4ac40000 0x0 0x2000>,
-		      <0x0 0x4ac60000 0x0 0x2000>;
+		      <0x0 0x4ac20000 0x0 0x20000>,
+		      <0x0 0x4ac40000 0x0 0x20000>,
+		      <0x0 0x4ac60000 0x0 0x20000>;
 	};
 
 	psci {
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index d1cc0571798b..dffff6763812 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -81,6 +81,7 @@
 #define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
+#define ARM_CPU_PART_CORTEX_X1C		0xD4C
 #define ARM_CPU_PART_CORTEX_A520	0xD80
 #define ARM_CPU_PART_CORTEX_A710	0xD47
 #define ARM_CPU_PART_CORTEX_A715	0xD4D
@@ -168,6 +169,7 @@
 #define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C)
 #define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
 #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index ebceaae3c749..d40e427ddad9 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -52,7 +52,7 @@
 	mrs	x0, id_aa64mmfr1_el1
 	ubfx	x0, x0, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4
 	cbz	x0, .Lskip_hcrx_\@
-	mov_q	x0, HCRX_HOST_FLAGS
+	mov_q	x0, (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM)
 
         /* Enable GCS if supported */
 	mrs_s	x1, SYS_ID_AA64PFR1_EL1
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 39577f1d079a..18c7811774d3 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -706,6 +706,7 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result,
 }
 #endif
 u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type);
+u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type);
 u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result,
 			 enum aarch64_insn_system_register sysreg);
 
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 974d72b5905b..e9c8a581e16f 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -100,9 +100,8 @@
 			 HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 | HCR_TID1)
 #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
 #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
-#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
+#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H | HCR_AMO | HCR_IMO | HCR_FMO)
 
-#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM)
 #define MPAMHCR_HOST_FLAGS	0
 
 /* TCR_EL2 Registers bits */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e98cfe7855a6..08ba91e6fb03 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1588,4 +1588,9 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
 #define kvm_has_s1poe(k)				\
 	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
 
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+	return true;
+}
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 30a29e88994b..6e8aa8e72601 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -94,17 +94,6 @@ static inline bool kaslr_requires_kpti(void)
 			return false;
 	}
 
-	/*
-	 * Systems affected by Cavium erratum 24756 are incompatible
-	 * with KPTI.
-	 */
-	if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) {
-		extern const struct midr_range cavium_erratum_27456_cpus[];
-
-		if (is_midr_in_range_list(cavium_erratum_27456_cpus))
-			return false;
-	}
-
 	return true;
 }
 
diff --git a/arch/arm64/include/asm/rqspinlock.h b/arch/arm64/include/asm/rqspinlock.h
index 5b80785324b6..9ea0a74e5892 100644
--- a/arch/arm64/include/asm/rqspinlock.h
+++ b/arch/arm64/include/asm/rqspinlock.h
@@ -86,7 +86,7 @@
 
 #endif
 
-#define res_smp_cond_load_acquire_timewait(v, c) smp_cond_load_acquire_timewait(v, c, 0, 1)
+#define res_smp_cond_load_acquire(v, c) smp_cond_load_acquire_timewait(v, c, 0, 1)
 
 #include <asm-generic/rqspinlock.h>
 
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index f1524cdeacf1..8fef12626090 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -97,6 +97,9 @@ enum mitigation_state arm64_get_meltdown_state(void);
 
 enum mitigation_state arm64_get_spectre_bhb_state(void);
 bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope);
+extern bool __nospectre_bhb;
+u8 get_spectre_bhb_loop_value(void);
+bool is_spectre_bhb_fw_mitigated(void);
 void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
 bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr);
 
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
index 92a2b59a9f3d..3322c7047d84 100644
--- a/arch/arm64/include/asm/vdso/gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -99,6 +99,19 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return res;
 }
 
+#if IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB)
+static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
+{
+	const struct vdso_time_data *ret = &vdso_u_time_data;
+
+	/* Work around invalid absolute relocations */
+	OPTIMIZER_HIDE_VAR(ret);
+
+	return ret;
+}
+#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
+#endif /* IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB) */
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index b55f5f705750..6b0ad5070d3e 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -335,7 +335,7 @@ static const struct midr_range cavium_erratum_23154_cpus[] = {
 #endif
 
 #ifdef CONFIG_CAVIUM_ERRATUM_27456
-const struct midr_range cavium_erratum_27456_cpus[] = {
+static const struct midr_range cavium_erratum_27456_cpus[] = {
 	/* Cavium ThunderX, T88 pass 1.x - 2.1 */
 	MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
 	/* Cavium ThunderX, T81 pass 1.0 */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 9c4d6d552b25..4c46d80aa64b 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -114,7 +114,14 @@ static struct arm64_cpu_capabilities const __ro_after_init *cpucap_ptrs[ARM64_NC
 
 DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS);
 
-bool arm64_use_ng_mappings = false;
+/*
+ * arm64_use_ng_mappings must be placed in the .data section, otherwise it
+ * ends up in the .bss section where it is initialized in early_map_kernel()
+ * after the MMU (with the idmap) was enabled. create_init_idmap() - which
+ * runs before early_map_kernel() and reads the variable via PTE_MAYBE_NG -
+ * may end up generating an incorrect idmap page table attributes.
+ */
+bool arm64_use_ng_mappings __read_mostly = false;
 EXPORT_SYMBOL(arm64_use_ng_mappings);
 
 DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors;
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 5e3c4b58f279..2004b4f41ade 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -47,10 +47,6 @@ PROVIDE(__pi_id_aa64smfr0_override	= id_aa64smfr0_override);
 PROVIDE(__pi_id_aa64zfr0_override	= id_aa64zfr0_override);
 PROVIDE(__pi_arm64_sw_feature_override	= arm64_sw_feature_override);
 PROVIDE(__pi_arm64_use_ng_mappings	= arm64_use_ng_mappings);
-#ifdef CONFIG_CAVIUM_ERRATUM_27456
-PROVIDE(__pi_cavium_erratum_27456_cpus	= cavium_erratum_27456_cpus);
-PROVIDE(__pi_is_midr_in_range_list	= is_midr_in_range_list);
-#endif
 PROVIDE(__pi__ctype			= _ctype);
 PROVIDE(__pi_memstart_offset_seed	= memstart_offset_seed);
 
diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c
index e57b043f324b..c6650cfe706c 100644
--- a/arch/arm64/kernel/pi/map_kernel.c
+++ b/arch/arm64/kernel/pi/map_kernel.c
@@ -207,6 +207,29 @@ static void __init map_fdt(u64 fdt)
 	dsb(ishst);
 }
 
+/*
+ * PI version of the Cavium Eratum 27456 detection, which makes it
+ * impossible to use non-global mappings.
+ */
+static bool __init ng_mappings_allowed(void)
+{
+	static const struct midr_range cavium_erratum_27456_cpus[] __initconst = {
+		/* Cavium ThunderX, T88 pass 1.x - 2.1 */
+		MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
+		/* Cavium ThunderX, T81 pass 1.0 */
+		MIDR_REV(MIDR_THUNDERX_81XX, 0, 0),
+		{},
+	};
+
+	for (const struct midr_range *r = cavium_erratum_27456_cpus; r->model; r++) {
+		if (midr_is_cpu_model_range(read_cpuid_id(), r->model,
+					    r->rv_min, r->rv_max))
+			return false;
+	}
+
+	return true;
+}
+
 asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 {
 	static char const chosen_str[] __initconst = "/chosen";
@@ -246,7 +269,7 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 		u64 kaslr_seed = kaslr_early_init(fdt, chosen);
 
 		if (kaslr_seed && kaslr_requires_kpti())
-			arm64_use_ng_mappings = true;
+			arm64_use_ng_mappings = ng_mappings_allowed();
 
 		kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1);
 	}
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index b198dde79e59..edf1783ffc81 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -879,16 +879,19 @@ static u8 spectre_bhb_loop_affected(void)
 	static const struct midr_range spectre_bhb_k132_list[] = {
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_X3),
 		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2),
+		{},
 	};
 	static const struct midr_range spectre_bhb_k38_list[] = {
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A715),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A720),
+		{},
 	};
 	static const struct midr_range spectre_bhb_k32_list[] = {
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
 		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
@@ -997,6 +1000,11 @@ bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry,
 	return true;
 }
 
+u8 get_spectre_bhb_loop_value(void)
+{
+	return max_bhb_k;
+}
+
 static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
 {
 	const char *v = arm64_get_bp_hardening_vector(slot);
@@ -1014,7 +1022,7 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
 	isb();
 }
 
-static bool __read_mostly __nospectre_bhb;
+bool __read_mostly __nospectre_bhb;
 static int __init parse_spectre_bhb_param(char *str)
 {
 	__nospectre_bhb = true;
@@ -1092,6 +1100,11 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 	update_mitigation_state(&spectre_bhb_state, state);
 }
 
+bool is_spectre_bhb_fw_mitigated(void)
+{
+	return test_bit(BHB_FW, &system_bhb_mitigations);
+}
+
 /* Patched to NOP when enabled */
 void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt,
 						     __le32 *origptr,
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 68fec8c95fee..19ca57def629 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2743,11 +2743,6 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
 	return irqchip_in_kernel(kvm);
 }
 
-bool kvm_arch_has_irq_bypass(void)
-{
-	return true;
-}
-
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 				      struct irq_bypass_producer *prod)
 {
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index b741ea6aefa5..96f625dc7256 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -235,6 +235,8 @@ static inline void __deactivate_traps_mpam(void)
 
 static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 {
+	struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
+
 	/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
 
@@ -245,11 +247,8 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 	 * EL1 instead of being trapped to EL2.
 	 */
 	if (system_supports_pmuv3()) {
-		struct kvm_cpu_context *hctxt;
-
 		write_sysreg(0, pmselr_el0);
 
-		hctxt = host_data_ptr(host_ctxt);
 		ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0);
 		write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
 		vcpu_set_flag(vcpu, PMUSERENR_ON_CPU);
@@ -269,6 +268,7 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 			hcrx &= ~clr;
 		}
 
+		ctxt_sys_reg(hctxt, HCRX_EL2) = read_sysreg_s(SYS_HCRX_EL2);
 		write_sysreg_s(hcrx, SYS_HCRX_EL2);
 	}
 
@@ -278,19 +278,18 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 
 static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
 {
+	struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
+
 	write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2);
 
 	write_sysreg(0, hstr_el2);
 	if (system_supports_pmuv3()) {
-		struct kvm_cpu_context *hctxt;
-
-		hctxt = host_data_ptr(host_ctxt);
 		write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0);
 		vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU);
 	}
 
 	if (cpus_have_final_cap(ARM64_HAS_HCX))
-		write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2);
+		write_sysreg_s(ctxt_sys_reg(hctxt, HCRX_EL2), SYS_HCRX_EL2);
 
 	__deactivate_traps_hfgxtr(vcpu);
 	__deactivate_traps_mpam();
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 2a5284f749b4..e80f3ebd3e2a 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -503,7 +503,7 @@ int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
 {
 	int ret;
 
-	if (!addr_is_memory(addr))
+	if (!range_is_memory(addr, addr + size))
 		return -EPERM;
 
 	ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index ed363aa3027e..50aa8dbcae75 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -429,23 +429,27 @@ u64 __vgic_v3_get_gic_config(void)
 	/*
 	 * To check whether we have a MMIO-based (GICv2 compatible)
 	 * CPU interface, we need to disable the system register
-	 * view. To do that safely, we have to prevent any interrupt
-	 * from firing (which would be deadly).
+	 * view.
 	 *
-	 * Note that this only makes sense on VHE, as interrupts are
-	 * already masked for nVHE as part of the exception entry to
-	 * EL2.
-	 */
-	if (has_vhe())
-		flags = local_daif_save();
-
-	/*
 	 * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates
 	 * that to be able to set ICC_SRE_EL1.SRE to 0, all the
 	 * interrupt overrides must be set. You've got to love this.
+	 *
+	 * As we always run VHE with HCR_xMO set, no extra xMO
+	 * manipulation is required in that case.
+	 *
+	 * To safely disable SRE, we have to prevent any interrupt
+	 * from firing (which would be deadly). This only makes sense
+	 * on VHE, as interrupts are already masked for nVHE as part
+	 * of the exception entry to EL2.
 	 */
-	sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
-	isb();
+	if (has_vhe()) {
+		flags = local_daif_save();
+	} else {
+		sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
+		isb();
+	}
+
 	write_gicreg(0, ICC_SRE_EL1);
 	isb();
 
@@ -453,11 +457,13 @@ u64 __vgic_v3_get_gic_config(void)
 
 	write_gicreg(sre, ICC_SRE_EL1);
 	isb();
-	sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
-	isb();
 
-	if (has_vhe())
+	if (has_vhe()) {
 		local_daif_restore(flags);
+	} else {
+		sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
+		isb();
+	}
 
 	val  = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
 	val |= read_gicreg(ICH_VTR_EL2);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 754f2fe0cc67..eeda92330ade 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1501,6 +1501,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
+	if (!is_protected_kvm_enabled())
+		memcache = &vcpu->arch.mmu_page_cache;
+	else
+		memcache = &vcpu->arch.pkvm_memcache;
+
 	/*
 	 * Permission faults just need to update the existing leaf entry,
 	 * and so normally don't require allocations from the memcache. The
@@ -1510,13 +1515,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (!fault_is_perm || (logging_active && write_fault)) {
 		int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
 
-		if (!is_protected_kvm_enabled()) {
-			memcache = &vcpu->arch.mmu_page_cache;
+		if (!is_protected_kvm_enabled())
 			ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
-		} else {
-			memcache = &vcpu->arch.pkvm_memcache;
+		else
 			ret = topup_hyp_memcache(memcache, min_pages);
-		}
+
 		if (ret)
 			return ret;
 	}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 005ad28f7306..5dde9285afc8 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1945,6 +1945,12 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
 	if ((hw_val & mpam_mask) == (user_val & mpam_mask))
 		user_val &= ~ID_AA64PFR0_EL1_MPAM_MASK;
 
+	/* Fail the guest's request to disable the AA64 ISA at EL{0,1,2} */
+	if (!FIELD_GET(ID_AA64PFR0_EL1_EL0, user_val) ||
+	    !FIELD_GET(ID_AA64PFR0_EL1_EL1, user_val) ||
+	    (vcpu_has_nv(vcpu) && !FIELD_GET(ID_AA64PFR0_EL1_EL2, user_val)))
+		return -EINVAL;
+
 	return set_id_reg(vcpu, rd, user_val);
 }
 
diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c
index 9bef696e2230..4e298baddc2e 100644
--- a/arch/arm64/lib/insn.c
+++ b/arch/arm64/lib/insn.c
@@ -5,6 +5,7 @@
  *
  * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.com>
  */
+#include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/bug.h>
 #include <linux/printk.h>
@@ -1500,43 +1501,41 @@ u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant,
 	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, Rm);
 }
 
-u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type)
+static u32 __get_barrier_crm_val(enum aarch64_insn_mb_type type)
 {
-	u32 opt;
-	u32 insn;
-
 	switch (type) {
 	case AARCH64_INSN_MB_SY:
-		opt = 0xf;
-		break;
+		return 0xf;
 	case AARCH64_INSN_MB_ST:
-		opt = 0xe;
-		break;
+		return 0xe;
 	case AARCH64_INSN_MB_LD:
-		opt = 0xd;
-		break;
+		return 0xd;
 	case AARCH64_INSN_MB_ISH:
-		opt = 0xb;
-		break;
+		return 0xb;
 	case AARCH64_INSN_MB_ISHST:
-		opt = 0xa;
-		break;
+		return 0xa;
 	case AARCH64_INSN_MB_ISHLD:
-		opt = 0x9;
-		break;
+		return 0x9;
 	case AARCH64_INSN_MB_NSH:
-		opt = 0x7;
-		break;
+		return 0x7;
 	case AARCH64_INSN_MB_NSHST:
-		opt = 0x6;
-		break;
+		return 0x6;
 	case AARCH64_INSN_MB_NSHLD:
-		opt = 0x5;
-		break;
+		return 0x5;
 	default:
-		pr_err("%s: unknown dmb type %d\n", __func__, type);
+		pr_err("%s: unknown barrier type %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
+}
+
+u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type)
+{
+	u32 opt;
+	u32 insn;
+
+	opt = __get_barrier_crm_val(type);
+	if (opt == AARCH64_BREAK_FAULT)
+		return AARCH64_BREAK_FAULT;
 
 	insn = aarch64_insn_get_dmb_value();
 	insn &= ~GENMASK(11, 8);
@@ -1545,6 +1544,21 @@ u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type)
 	return insn;
 }
 
+u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type)
+{
+	u32 opt, insn;
+
+	opt = __get_barrier_crm_val(type);
+	if (opt == AARCH64_BREAK_FAULT)
+		return AARCH64_BREAK_FAULT;
+
+	insn = aarch64_insn_get_dsb_base_value();
+	insn &= ~GENMASK(11, 8);
+	insn |= (opt << 8);
+
+	return insn;
+}
+
 u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result,
 			 enum aarch64_insn_system_register sysreg)
 {
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 70d7c89d3ac9..634d78422adb 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -7,6 +7,7 @@
 
 #define pr_fmt(fmt) "bpf_jit: " fmt
 
+#include <linux/arm-smccc.h>
 #include <linux/bitfield.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
@@ -17,6 +18,7 @@
 #include <asm/asm-extable.h>
 #include <asm/byteorder.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/insn.h>
 #include <asm/text-patching.h>
@@ -939,7 +941,51 @@ static void build_plt(struct jit_ctx *ctx)
 		plt->target = (u64)&dummy_tramp;
 }
 
-static void build_epilogue(struct jit_ctx *ctx)
+/* Clobbers BPF registers 1-4, aka x0-x3 */
+static void __maybe_unused build_bhb_mitigation(struct jit_ctx *ctx)
+{
+	const u8 r1 = bpf2a64[BPF_REG_1]; /* aka x0 */
+	u8 k = get_spectre_bhb_loop_value();
+
+	if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY) ||
+	    cpu_mitigations_off() || __nospectre_bhb ||
+	    arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE)
+		return;
+
+	if (capable(CAP_SYS_ADMIN))
+		return;
+
+	if (supports_clearbhb(SCOPE_SYSTEM)) {
+		emit(aarch64_insn_gen_hint(AARCH64_INSN_HINT_CLEARBHB), ctx);
+		return;
+	}
+
+	if (k) {
+		emit_a64_mov_i64(r1, k, ctx);
+		emit(A64_B(1), ctx);
+		emit(A64_SUBS_I(true, r1, r1, 1), ctx);
+		emit(A64_B_(A64_COND_NE, -2), ctx);
+		emit(aarch64_insn_gen_dsb(AARCH64_INSN_MB_ISH), ctx);
+		emit(aarch64_insn_get_isb_value(), ctx);
+	}
+
+	if (is_spectre_bhb_fw_mitigated()) {
+		emit(A64_ORR_I(false, r1, AARCH64_INSN_REG_ZR,
+			       ARM_SMCCC_ARCH_WORKAROUND_3), ctx);
+		switch (arm_smccc_1_1_get_conduit()) {
+		case SMCCC_CONDUIT_HVC:
+			emit(aarch64_insn_get_hvc_value(), ctx);
+			break;
+		case SMCCC_CONDUIT_SMC:
+			emit(aarch64_insn_get_smc_value(), ctx);
+			break;
+		default:
+			pr_err_once("Firmware mitigation enabled with unknown conduit\n");
+		}
+	}
+}
+
+static void build_epilogue(struct jit_ctx *ctx, bool was_classic)
 {
 	const u8 r0 = bpf2a64[BPF_REG_0];
 	const u8 ptr = bpf2a64[TCCNT_PTR];
@@ -952,10 +998,13 @@ static void build_epilogue(struct jit_ctx *ctx)
 
 	emit(A64_POP(A64_ZR, ptr, A64_SP), ctx);
 
+	if (was_classic)
+		build_bhb_mitigation(ctx);
+
 	/* Restore FP/LR registers */
 	emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
 
-	/* Set return value */
+	/* Move the return value from bpf:r0 (aka x7) to x0 */
 	emit(A64_MOV(1, A64_R(0), r0), ctx);
 
 	/* Authenticate lr */
@@ -1898,7 +1947,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 
 	ctx.epilogue_offset = ctx.idx;
-	build_epilogue(&ctx);
+	build_epilogue(&ctx, was_classic);
 	build_plt(&ctx);
 
 	extable_align = __alignof__(struct exception_table_entry);
@@ -1961,7 +2010,7 @@ skip_init_ctx:
 		goto out_free_hdr;
 	}
 
-	build_epilogue(&ctx);
+	build_epilogue(&ctx, was_classic);
 	build_plt(&ctx);
 
 	/* Extra pass to validate JITed code. */
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 067c0b994648..1a2cf012b8f2 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -73,6 +73,7 @@ config LOONGARCH
 	select ARCH_SUPPORTS_RT
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_DEFAULT_BPF_JIT
diff --git a/arch/loongarch/include/asm/fpu.h b/arch/loongarch/include/asm/fpu.h
index 3177674228f8..45514f314664 100644
--- a/arch/loongarch/include/asm/fpu.h
+++ b/arch/loongarch/include/asm/fpu.h
@@ -22,22 +22,29 @@
 struct sigcontext;
 
 #define kernel_fpu_available() cpu_has_fpu
-extern void kernel_fpu_begin(void);
-extern void kernel_fpu_end(void);
-
-extern void _init_fpu(unsigned int);
-extern void _save_fp(struct loongarch_fpu *);
-extern void _restore_fp(struct loongarch_fpu *);
-
-extern void _save_lsx(struct loongarch_fpu *fpu);
-extern void _restore_lsx(struct loongarch_fpu *fpu);
-extern void _init_lsx_upper(void);
-extern void _restore_lsx_upper(struct loongarch_fpu *fpu);
-
-extern void _save_lasx(struct loongarch_fpu *fpu);
-extern void _restore_lasx(struct loongarch_fpu *fpu);
-extern void _init_lasx_upper(void);
-extern void _restore_lasx_upper(struct loongarch_fpu *fpu);
+
+void kernel_fpu_begin(void);
+void kernel_fpu_end(void);
+
+asmlinkage void _init_fpu(unsigned int);
+asmlinkage void _save_fp(struct loongarch_fpu *);
+asmlinkage void _restore_fp(struct loongarch_fpu *);
+asmlinkage int _save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
+asmlinkage int _restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
+
+asmlinkage void _save_lsx(struct loongarch_fpu *fpu);
+asmlinkage void _restore_lsx(struct loongarch_fpu *fpu);
+asmlinkage void _init_lsx_upper(void);
+asmlinkage void _restore_lsx_upper(struct loongarch_fpu *fpu);
+asmlinkage int _save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+asmlinkage int _restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+
+asmlinkage void _save_lasx(struct loongarch_fpu *fpu);
+asmlinkage void _restore_lasx(struct loongarch_fpu *fpu);
+asmlinkage void _init_lasx_upper(void);
+asmlinkage void _restore_lasx_upper(struct loongarch_fpu *fpu);
+asmlinkage int _save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+asmlinkage int _restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
 
 static inline void enable_lsx(void);
 static inline void disable_lsx(void);
diff --git a/arch/loongarch/include/asm/lbt.h b/arch/loongarch/include/asm/lbt.h
index e671978bf552..38566574e562 100644
--- a/arch/loongarch/include/asm/lbt.h
+++ b/arch/loongarch/include/asm/lbt.h
@@ -12,9 +12,13 @@
 #include <asm/loongarch.h>
 #include <asm/processor.h>
 
-extern void _init_lbt(void);
-extern void _save_lbt(struct loongarch_lbt *);
-extern void _restore_lbt(struct loongarch_lbt *);
+asmlinkage void _init_lbt(void);
+asmlinkage void _save_lbt(struct loongarch_lbt *);
+asmlinkage void _restore_lbt(struct loongarch_lbt *);
+asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
+asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
+asmlinkage int _save_ftop_context(void __user *ftop);
+asmlinkage int _restore_ftop_context(void __user *ftop);
 
 static inline int is_lbt_enabled(void)
 {
diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h
index f3ddaed9ef7f..e5d21e836d99 100644
--- a/arch/loongarch/include/asm/ptrace.h
+++ b/arch/loongarch/include/asm/ptrace.h
@@ -33,9 +33,9 @@ struct pt_regs {
 	unsigned long __last[];
 } __aligned(8);
 
-static inline int regs_irqs_disabled(struct pt_regs *regs)
+static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
 {
-	return arch_irqs_disabled_flags(regs->csr_prmd);
+	return !(regs->csr_prmd & CSR_PRMD_PIE);
 }
 
 static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
@@ -55,7 +55,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long v
 
 /* Query offset/name of register from its name/offset */
 extern int regs_query_register_offset(const char *name);
-#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last))
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last) - sizeof(unsigned long))
 
 /**
  * regs_get_register() - get register value from its offset
diff --git a/arch/loongarch/include/asm/uprobes.h b/arch/loongarch/include/asm/uprobes.h
index 99a0d198927f..025fc3f0a102 100644
--- a/arch/loongarch/include/asm/uprobes.h
+++ b/arch/loongarch/include/asm/uprobes.h
@@ -15,7 +15,6 @@ typedef u32 uprobe_opcode_t;
 #define UPROBE_XOLBP_INSN	__emit_break(BRK_UPROBE_XOLBP)
 
 struct arch_uprobe {
-	unsigned long	resume_era;
 	u32	insn[2];
 	u32	ixol[2];
 	bool	simulate;
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 4853e8b04c6f..f9dcaa60033d 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -21,10 +21,10 @@ obj-$(CONFIG_CPU_HAS_LBT)	+= lbt.o
 
 obj-$(CONFIG_ARCH_STRICT_ALIGN)	+= unaligned.o
 
-CFLAGS_module.o		+= $(call cc-option,-Wno-override-init,)
-CFLAGS_syscall.o	+= $(call cc-option,-Wno-override-init,)
-CFLAGS_traps.o		+= $(call cc-option,-Wno-override-init,)
-CFLAGS_perf_event.o	+= $(call cc-option,-Wno-override-init,)
+CFLAGS_module.o		+= $(call cc-disable-warning, override-init)
+CFLAGS_syscall.o	+= $(call cc-disable-warning, override-init)
+CFLAGS_traps.o		+= $(call cc-disable-warning, override-init)
+CFLAGS_perf_event.o	+= $(call cc-disable-warning, override-init)
 
 ifdef CONFIG_FUNCTION_TRACER
   ifndef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index 6ab640101457..28caf416ae36 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -458,6 +458,7 @@ SYM_FUNC_START(_save_fp_context)
 	li.w		a0, 0				# success
 	jr		ra
 SYM_FUNC_END(_save_fp_context)
+EXPORT_SYMBOL_GPL(_save_fp_context)
 
 /*
  * a0: fpregs
@@ -471,6 +472,7 @@ SYM_FUNC_START(_restore_fp_context)
 	li.w		a0, 0				# success
 	jr		ra
 SYM_FUNC_END(_restore_fp_context)
+EXPORT_SYMBOL_GPL(_restore_fp_context)
 
 /*
  * a0: fpregs
@@ -484,6 +486,7 @@ SYM_FUNC_START(_save_lsx_context)
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_save_lsx_context)
+EXPORT_SYMBOL_GPL(_save_lsx_context)
 
 /*
  * a0: fpregs
@@ -497,6 +500,7 @@ SYM_FUNC_START(_restore_lsx_context)
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_restore_lsx_context)
+EXPORT_SYMBOL_GPL(_restore_lsx_context)
 
 /*
  * a0: fpregs
@@ -510,6 +514,7 @@ SYM_FUNC_START(_save_lasx_context)
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_save_lasx_context)
+EXPORT_SYMBOL_GPL(_save_lasx_context)
 
 /*
  * a0: fpregs
@@ -523,6 +528,7 @@ SYM_FUNC_START(_restore_lasx_context)
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_restore_lasx_context)
+EXPORT_SYMBOL_GPL(_restore_lasx_context)
 
 .L_fpu_fault:
 	li.w	a0, -EFAULT				# failure
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 4f0912141781..733a7665e434 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -16,6 +16,7 @@
 #include <asm/stackframe.h>
 #include <asm/thread_info.h>
 
+	.section .cpuidle.text, "ax"
 	.align	5
 SYM_FUNC_START(__arch_cpu_idle)
 	/* start of idle interrupt region */
@@ -31,14 +32,16 @@ SYM_FUNC_START(__arch_cpu_idle)
 	 */
 	idle	0
 	/* end of idle interrupt region */
-1:	jr	ra
+idle_exit:
+	jr	ra
 SYM_FUNC_END(__arch_cpu_idle)
+	.previous
 
 SYM_CODE_START(handle_vint)
 	UNWIND_HINT_UNDEFINED
 	BACKUP_T0T1
 	SAVE_ALL
-	la_abs	t1, 1b
+	la_abs	t1, idle_exit
 	LONG_L	t0, sp, PT_ERA
 	/* 3 instructions idle interrupt region */
 	ori	t0, t0, 0b1100
diff --git a/arch/loongarch/kernel/kfpu.c b/arch/loongarch/kernel/kfpu.c
index ec5b28e570c9..4c476904227f 100644
--- a/arch/loongarch/kernel/kfpu.c
+++ b/arch/loongarch/kernel/kfpu.c
@@ -18,11 +18,28 @@ static unsigned int euen_mask = CSR_EUEN_FPEN;
 static DEFINE_PER_CPU(bool, in_kernel_fpu);
 static DEFINE_PER_CPU(unsigned int, euen_current);
 
+static inline void fpregs_lock(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_disable();
+	else
+		local_bh_disable();
+}
+
+static inline void fpregs_unlock(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_enable();
+	else
+		local_bh_enable();
+}
+
 void kernel_fpu_begin(void)
 {
 	unsigned int *euen_curr;
 
-	preempt_disable();
+	if (!irqs_disabled())
+		fpregs_lock();
 
 	WARN_ON(this_cpu_read(in_kernel_fpu));
 
@@ -73,7 +90,8 @@ void kernel_fpu_end(void)
 
 	this_cpu_write(in_kernel_fpu, false);
 
-	preempt_enable();
+	if (!irqs_disabled())
+		fpregs_unlock();
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 
diff --git a/arch/loongarch/kernel/lbt.S b/arch/loongarch/kernel/lbt.S
index 001f061d226a..71678912d24c 100644
--- a/arch/loongarch/kernel/lbt.S
+++ b/arch/loongarch/kernel/lbt.S
@@ -90,6 +90,7 @@ SYM_FUNC_START(_save_lbt_context)
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_save_lbt_context)
+EXPORT_SYMBOL_GPL(_save_lbt_context)
 
 /*
  * a0: scr
@@ -110,6 +111,7 @@ SYM_FUNC_START(_restore_lbt_context)
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_restore_lbt_context)
+EXPORT_SYMBOL_GPL(_restore_lbt_context)
 
 /*
  * a0: ftop
@@ -120,6 +122,7 @@ SYM_FUNC_START(_save_ftop_context)
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_save_ftop_context)
+EXPORT_SYMBOL_GPL(_save_ftop_context)
 
 /*
  * a0: ftop
@@ -150,6 +153,7 @@ SYM_FUNC_START(_restore_ftop_context)
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_restore_ftop_context)
+EXPORT_SYMBOL_GPL(_restore_ftop_context)
 
 .L_lbt_fault:
 	li.w		a0, -EFAULT		# failure
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index 7a555b600171..4740cb5b2388 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -51,27 +51,6 @@
 #define lock_lbt_owner()	({ preempt_disable(); pagefault_disable(); })
 #define unlock_lbt_owner()	({ pagefault_enable(); preempt_enable(); })
 
-/* Assembly functions to move context to/from the FPU */
-extern asmlinkage int
-_save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern asmlinkage int
-_restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern asmlinkage int
-_save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-
-#ifdef CONFIG_CPU_HAS_LBT
-extern asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
-extern asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
-extern asmlinkage int _save_ftop_context(void __user *ftop);
-extern asmlinkage int _restore_ftop_context(void __user *ftop);
-#endif
-
 struct rt_sigframe {
 	struct siginfo rs_info;
 	struct ucontext rs_uctx;
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index e2d3bfeb6366..bc75a3a69fc8 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -111,7 +111,7 @@ static unsigned long __init get_loops_per_jiffy(void)
 	return lpj;
 }
 
-static long init_offset __nosavedata;
+static long init_offset;
 
 void save_counter(void)
 {
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 2ec3106c0da3..47fc2de6d150 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -553,9 +553,10 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
 	die_if_kernel("Kernel ale access", regs);
 	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
 #else
+	bool pie = regs_irqs_disabled(regs);
 	unsigned int *pc;
 
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr);
@@ -582,7 +583,7 @@ sigbus:
 	die_if_kernel("Kernel ale access", regs);
 	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 #endif
 	irqentry_exit(regs, state);
@@ -621,12 +622,13 @@ static void bug_handler(struct pt_regs *regs)
 asmlinkage void noinstr do_bce(struct pt_regs *regs)
 {
 	bool user = user_mode(regs);
+	bool pie = regs_irqs_disabled(regs);
 	unsigned long era = exception_era(regs);
 	u64 badv = 0, lower = 0, upper = ULONG_MAX;
 	union loongarch_instruction insn;
 	irqentry_state_t state = irqentry_enter(regs);
 
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	current->thread.trap_nr = read_csr_excode();
@@ -692,7 +694,7 @@ asmlinkage void noinstr do_bce(struct pt_regs *regs)
 	force_sig_bnderr((void __user *)badv, (void __user *)lower, (void __user *)upper);
 
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 
 	irqentry_exit(regs, state);
@@ -710,11 +712,12 @@ bad_era:
 asmlinkage void noinstr do_bp(struct pt_regs *regs)
 {
 	bool user = user_mode(regs);
+	bool pie = regs_irqs_disabled(regs);
 	unsigned int opcode, bcode;
 	unsigned long era = exception_era(regs);
 	irqentry_state_t state = irqentry_enter(regs);
 
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	if (__get_inst(&opcode, (u32 *)era, user))
@@ -780,7 +783,7 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs)
 	}
 
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 
 	irqentry_exit(regs, state);
@@ -1015,6 +1018,7 @@ static void init_restore_lbt(void)
 
 asmlinkage void noinstr do_lbt(struct pt_regs *regs)
 {
+	bool pie = regs_irqs_disabled(regs);
 	irqentry_state_t state = irqentry_enter(regs);
 
 	/*
@@ -1024,7 +1028,7 @@ asmlinkage void noinstr do_lbt(struct pt_regs *regs)
 	 * (including the user using 'MOVGR2GCSR' to turn on TM, which
 	 * will not trigger the BTE), we need to check PRMD first.
 	 */
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	if (!cpu_has_lbt) {
@@ -1038,7 +1042,7 @@ asmlinkage void noinstr do_lbt(struct pt_regs *regs)
 	preempt_enable();
 
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 
 	irqentry_exit(regs, state);
diff --git a/arch/loongarch/kernel/uprobes.c b/arch/loongarch/kernel/uprobes.c
index 87abc7137b73..6022eb0f71db 100644
--- a/arch/loongarch/kernel/uprobes.c
+++ b/arch/loongarch/kernel/uprobes.c
@@ -42,7 +42,6 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	utask->autask.saved_trap_nr = current->thread.trap_nr;
 	current->thread.trap_nr = UPROBE_TRAP_NR;
 	instruction_pointer_set(regs, utask->xol_vaddr);
-	user_enable_single_step(current);
 
 	return 0;
 }
@@ -53,13 +52,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR);
 	current->thread.trap_nr = utask->autask.saved_trap_nr;
-
-	if (auprobe->simulate)
-		instruction_pointer_set(regs, auprobe->resume_era);
-	else
-		instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE);
-
-	user_disable_single_step(current);
+	instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE);
 
 	return 0;
 }
@@ -70,7 +63,6 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	current->thread.trap_nr = utask->autask.saved_trap_nr;
 	instruction_pointer_set(regs, utask->vaddr);
-	user_disable_single_step(current);
 }
 
 bool arch_uprobe_xol_was_trapped(struct task_struct *t)
@@ -90,7 +82,6 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	insn.word = auprobe->insn[0];
 	arch_simulate_insn(insn, regs);
-	auprobe->resume_era = regs->csr_era;
 
 	return true;
 }
diff --git a/arch/loongarch/kvm/Makefile b/arch/loongarch/kvm/Makefile
index f4c8e35c216a..cb41d9265662 100644
--- a/arch/loongarch/kvm/Makefile
+++ b/arch/loongarch/kvm/Makefile
@@ -21,4 +21,4 @@ kvm-y += intc/eiointc.o
 kvm-y += intc/pch_pic.o
 kvm-y += irqfd.o
 
-CFLAGS_exit.o	+= $(call cc-option,-Wno-override-init,)
+CFLAGS_exit.o	+= $(call cc-disable-warning, override-init)
diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c
index 93f4acd44523..fe734dc062ed 100644
--- a/arch/loongarch/kvm/intc/ipi.c
+++ b/arch/loongarch/kvm/intc/ipi.c
@@ -111,7 +111,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 		ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		if (unlikely(ret)) {
-			kvm_err("%s: : read date from addr %llx failed\n", __func__, addr);
+			kvm_err("%s: : read data from addr %llx failed\n", __func__, addr);
 			return ret;
 		}
 		/* Construct the mask by scanning the bit 27-30 */
@@ -127,7 +127,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 	ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	if (unlikely(ret))
-		kvm_err("%s: : write date to addr %llx failed\n", __func__, addr);
+		kvm_err("%s: : write data to addr %llx failed\n", __func__, addr);
 
 	return ret;
 }
diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index d165cd38c6bb..80ea63d465b8 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -296,10 +296,10 @@ int kvm_arch_enable_virtualization_cpu(void)
 	/*
 	 * Enable virtualization features granting guest direct control of
 	 * certain features:
-	 * GCI=2:       Trap on init or unimplement cache instruction.
+	 * GCI=2:       Trap on init or unimplemented cache instruction.
 	 * TORU=0:      Trap on Root Unimplement.
 	 * CACTRL=1:    Root control cache.
-	 * TOP=0:       Trap on Previlege.
+	 * TOP=0:       Trap on Privilege.
 	 * TOE=0:       Trap on Exception.
 	 * TIT=0:       Trap on Timer.
 	 */
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 8e427b379661..5af32ec62cb1 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -294,6 +294,7 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu)
 		vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST;
 
 		if (kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending()) {
+			kvm_lose_pmu(vcpu);
 			/* make sure the vcpu mode has been written */
 			smp_store_mb(vcpu->mode, OUTSIDE_GUEST_MODE);
 			local_irq_enable();
@@ -902,6 +903,13 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu,
 			vcpu->arch.st.guest_addr = 0;
 			memset(&vcpu->arch.irq_pending, 0, sizeof(vcpu->arch.irq_pending));
 			memset(&vcpu->arch.irq_clear, 0, sizeof(vcpu->arch.irq_clear));
+
+			/*
+			 * When vCPU reset, clear the ESTAT and GINTC registers
+			 * Other CSR registers are cleared with function _kvm_setcsr().
+			 */
+			kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_GINTC, 0);
+			kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_ESTAT, 0);
 			break;
 		default:
 			ret = -EINVAL;
diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c
index e4068906143b..cea84d7f2b91 100644
--- a/arch/loongarch/mm/hugetlbpage.c
+++ b/arch/loongarch/mm/hugetlbpage.c
@@ -47,7 +47,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
 				pmd = pmd_offset(pud, addr);
 		}
 	}
-	return (pte_t *) pmd;
+	return pmd_none(pmdp_get(pmd)) ? NULL : (pte_t *) pmd;
 }
 
 uint64_t pmd_to_entrylo(unsigned long pmd_val)
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index fdb7f73ad160..06f11d9e4ec1 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -65,9 +65,6 @@ void __init paging_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
 
-#ifdef CONFIG_ZONE_DMA
-	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
-#endif
 #ifdef CONFIG_ZONE_DMA32
 	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
 #endif
diff --git a/arch/loongarch/power/hibernate.c b/arch/loongarch/power/hibernate.c
index 1e0590542f98..e7b7346592cb 100644
--- a/arch/loongarch/power/hibernate.c
+++ b/arch/loongarch/power/hibernate.c
@@ -2,6 +2,7 @@
 #include <asm/fpu.h>
 #include <asm/loongson.h>
 #include <asm/sections.h>
+#include <asm/time.h>
 #include <asm/tlbflush.h>
 #include <linux/suspend.h>
 
@@ -14,6 +15,7 @@ struct pt_regs saved_regs;
 
 void save_processor_state(void)
 {
+	save_counter();
 	saved_crmd = csr_read32(LOONGARCH_CSR_CRMD);
 	saved_prmd = csr_read32(LOONGARCH_CSR_PRMD);
 	saved_euen = csr_read32(LOONGARCH_CSR_EUEN);
@@ -26,6 +28,7 @@ void save_processor_state(void)
 
 void restore_processor_state(void)
 {
+	sync_counter();
 	csr_write32(saved_crmd, LOONGARCH_CSR_CRMD);
 	csr_write32(saved_prmd, LOONGARCH_CSR_PRMD);
 	csr_write32(saved_euen, LOONGARCH_CSR_EUEN);
diff --git a/arch/m68k/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c
index 734dab657fe3..5b70dfdab368 100644
--- a/arch/m68k/coldfire/m5272.c
+++ b/arch/m68k/coldfire/m5272.c
@@ -119,7 +119,7 @@ static struct fixed_phy_status nettel_fixed_phy_status __initdata = {
 static int __init init_BSP(void)
 {
 	m5272_uarts_init();
-	fixed_phy_add(PHY_POLL, 0, &nettel_fixed_phy_status);
+	fixed_phy_add(0, &nettel_fixed_phy_status);
 	clkdev_add_table(m5272_clk_lookup, ARRAY_SIZE(m5272_clk_lookup));
 	return 0;
 }
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 31ecb8b7b9f1..85bd696b0e90 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -267,8 +267,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 1f57514624d5..93003ceb51bb 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -263,8 +263,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 02db7a48e57e..fa6ed1bb01e3 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -270,8 +270,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index f0e673cb17eb..80ca001d5eab 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -260,8 +260,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index e8ca5a50b86d..5e35e4b1fe16 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -262,8 +262,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index b3a270441bb1..11bc3f3c7576 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -261,8 +261,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index d215dba006ce..343f702210df 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -281,8 +281,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index a888ed93ff82..6104a5a24594 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -259,8 +259,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index b481782375f6..a99dd6c7c9c8 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -260,8 +260,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 6eba743d8eb5..0d87c119d4c4 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -261,8 +261,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 9bdbb418ffa8..841f9615b6ab 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -256,8 +256,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index e1cf20fa5343..12c5dc92ea4c 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -257,8 +257,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index 247be207f293..de426a474b5b 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -282,7 +282,7 @@ static int __init bcm47xx_register_bus_complete(void)
 	bcm47xx_leds_register();
 	bcm47xx_workarounds();
 
-	fixed_phy_add(PHY_POLL, 0, &bcm47xx_fixed_phy_status);
+	fixed_phy_add(0, &bcm47xx_fixed_phy_status);
 	return 0;
 }
 device_initcall(bcm47xx_register_bus_complete);
diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig
index 8f7c36868204..97d2cd997285 100644
--- a/arch/mips/configs/bigsur_defconfig
+++ b/arch/mips/configs/bigsur_defconfig
@@ -81,7 +81,6 @@ CONFIG_IP_VS_SH=m
 CONFIG_IP_VS_SED=m
 CONFIG_IP_VS_NQ=m
 CONFIG_IP_VS_FTP=m
-CONFIG_IP_DCCP=m
 CONFIG_BRIDGE=m
 CONFIG_VLAN_8021Q=m
 CONFIG_VLAN_8021Q_GVRP=y
diff --git a/arch/mips/configs/gpr_defconfig b/arch/mips/configs/gpr_defconfig
index 12f3eed8a946..df55fe6df8ba 100644
--- a/arch/mips/configs/gpr_defconfig
+++ b/arch/mips/configs/gpr_defconfig
@@ -84,7 +84,6 @@ CONFIG_BRIDGE_EBT_MARK_T=m
 CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
-CONFIG_IP_DCCP=m
 CONFIG_IP_SCTP=m
 CONFIG_TIPC=m
 CONFIG_ATM=y
diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig
index 06b7a0b97eca..487bd84043f7 100644
--- a/arch/mips/configs/mtx1_defconfig
+++ b/arch/mips/configs/mtx1_defconfig
@@ -130,7 +130,6 @@ CONFIG_BRIDGE_EBT_MARK_T=m
 CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
-CONFIG_IP_DCCP=m
 CONFIG_IP_SCTP=m
 CONFIG_TIPC=m
 CONFIG_ATM=y
diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h
index 0992cad9c632..c7d75807d13f 100644
--- a/arch/mips/include/asm/idle.h
+++ b/arch/mips/include/asm/idle.h
@@ -6,11 +6,10 @@
 #include <linux/linkage.h>
 
 extern void (*cpu_wait)(void);
-extern void r4k_wait(void);
-extern asmlinkage void __r4k_wait(void);
+extern asmlinkage void r4k_wait(void);
 extern void r4k_wait_irqoff(void);
 
-static inline int using_rollback_handler(void)
+static inline int using_skipover_handler(void)
 {
 	return cpu_wait == r4k_wait;
 }
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 85fa9962266a..ef72c46b5568 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -65,7 +65,8 @@ static inline void instruction_pointer_set(struct pt_regs *regs,
 
 /* Query offset/name of register from its name/offset */
 extern int regs_query_register_offset(const char *name);
-#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last))
+#define MAX_REG_OFFSET \
+	(offsetof(struct pt_regs, __last) - sizeof(unsigned long))
 
 /**
  * regs_get_register() - get register value from its offset
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 22fa8f19924a..31ac655b7837 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -161,6 +161,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index a572ce36a24f..08c0a01d9a29 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -104,48 +104,59 @@ handle_vcei:
 
 	__FINIT
 
-	.align	5	/* 32 byte rollback region */
-LEAF(__r4k_wait)
-	.set	push
-	.set	noreorder
-	/* start of rollback region */
-	LONG_L	t0, TI_FLAGS($28)
-	nop
-	andi	t0, _TIF_NEED_RESCHED
-	bnez	t0, 1f
-	 nop
-	nop
-	nop
-#ifdef CONFIG_CPU_MICROMIPS
-	nop
-	nop
-	nop
-	nop
-#endif
+	.section .cpuidle.text,"ax"
+	/* Align to 32 bytes for the maximum idle interrupt region size. */
+	.align	5
+LEAF(r4k_wait)
+	/* Keep the ISA bit clear for calculations on local labels here. */
+0:	.fill 	0
+	/* Start of idle interrupt region. */
+	local_irq_enable
+	/*
+	 * If an interrupt lands here, before going idle on the next
+	 * instruction, we must *NOT* go idle since the interrupt could
+	 * have set TIF_NEED_RESCHED or caused a timer to need resched.
+	 * Fall through -- see skipover_handler below -- and have the
+	 * idle loop take care of things.
+	 */
+1:	.fill	0
+	/* The R2 EI/EHB sequence takes 8 bytes, otherwise pad up.  */
+	.if		1b - 0b > 32
+	.error	"overlong idle interrupt region"
+	.elseif	1b - 0b > 8
+	.align	4
+	.endif
+2:	.fill	0
+	.equ	r4k_wait_idle_size, 2b - 0b
+	/* End of idle interrupt region; size has to be a power of 2. */
 	.set	MIPS_ISA_ARCH_LEVEL_RAW
+r4k_wait_insn:
 	wait
-	/* end of rollback region (the region size must be power of two) */
-1:
+r4k_wait_exit:
+	.set	mips0
+	local_irq_disable
 	jr	ra
-	 nop
-	.set	pop
-	END(__r4k_wait)
+	END(r4k_wait)
+	.previous
 
-	.macro	BUILD_ROLLBACK_PROLOGUE handler
-	FEXPORT(rollback_\handler)
+	.macro	BUILD_SKIPOVER_PROLOGUE handler
+	FEXPORT(skipover_\handler)
 	.set	push
 	.set	noat
 	MFC0	k0, CP0_EPC
-	PTR_LA	k1, __r4k_wait
-	ori	k0, 0x1f	/* 32 byte rollback region */
-	xori	k0, 0x1f
+	/* Subtract/add 2 to let the ISA bit propagate through the mask.  */
+	PTR_LA	k1, r4k_wait_insn - 2
+	ori 	k0, r4k_wait_idle_size - 2
+	.set	noreorder
 	bne	k0, k1, \handler
+	PTR_ADDIU 	k0, r4k_wait_exit - r4k_wait_insn + 2
+	.set	reorder
 	MTC0	k0, CP0_EPC
 	.set pop
 	.endm
 
 	.align	5
-BUILD_ROLLBACK_PROLOGUE handle_int
+BUILD_SKIPOVER_PROLOGUE handle_int
 NESTED(handle_int, PT_SIZE, sp)
 	.cfi_signal_frame
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -265,7 +276,7 @@ NESTED(except_vec_ejtag_debug, 0, sp)
  * This prototype is copied to ebase + n*IntCtl.VS and patched
  * to invoke the handler
  */
-BUILD_ROLLBACK_PROLOGUE except_vec_vi
+BUILD_SKIPOVER_PROLOGUE except_vec_vi
 NESTED(except_vec_vi, 0, sp)
 	SAVE_SOME docfi=1
 	SAVE_AT docfi=1
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 5abc8b7340f8..80e8a04a642e 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -35,13 +35,6 @@ static void __cpuidle r3081_wait(void)
 	write_c0_conf(cfg | R30XX_CONF_HALT);
 }
 
-void __cpuidle r4k_wait(void)
-{
-	raw_local_irq_enable();
-	__r4k_wait();
-	raw_local_irq_disable();
-}
-
 /*
  * This variant is preferable as it allows testing need_resched and going to
  * sleep depending on the outcome atomically.  Unfortunately the "It is
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index e85bd087467e..cc26d56f3ab6 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -332,6 +332,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus)
 	mips_cps_cluster_bootcfg = kcalloc(nclusters,
 					   sizeof(*mips_cps_cluster_bootcfg),
 					   GFP_KERNEL);
+	if (!mips_cps_cluster_bootcfg)
+		goto err_out;
 
 	if (nclusters > 1)
 		mips_cm_update_property();
@@ -348,6 +350,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus)
 		mips_cps_cluster_bootcfg[cl].core_power =
 			kcalloc(BITS_TO_LONGS(ncores), sizeof(unsigned long),
 				GFP_KERNEL);
+		if (!mips_cps_cluster_bootcfg[cl].core_power)
+			goto err_out;
 
 		/* Allocate VPE boot configuration structs */
 		for (c = 0; c < ncores; c++) {
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 39e248d0ed59..8ec1e185b35c 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -77,7 +77,7 @@
 #include "access-helper.h"
 
 extern void check_wait(void);
-extern asmlinkage void rollback_handle_int(void);
+extern asmlinkage void skipover_handle_int(void);
 extern asmlinkage void handle_int(void);
 extern asmlinkage void handle_adel(void);
 extern asmlinkage void handle_ades(void);
@@ -2066,7 +2066,7 @@ void *set_vi_handler(int n, vi_handler_t addr)
 {
 	extern const u8 except_vec_vi[];
 	extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
-	extern const u8 rollback_except_vec_vi[];
+	extern const u8 skipover_except_vec_vi[];
 	unsigned long handler;
 	unsigned long old_handler = vi_handlers[n];
 	int srssets = current_cpu_data.srsets;
@@ -2095,7 +2095,7 @@ void *set_vi_handler(int n, vi_handler_t addr)
 			change_c0_srsmap(0xf << n*4, 0 << n*4);
 	}
 
-	vec_start = using_rollback_handler() ? rollback_except_vec_vi :
+	vec_start = using_skipover_handler() ? skipover_except_vec_vi :
 					       except_vec_vi;
 #if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
 	ori_offset = except_vec_vi_ori - vec_start + 2;
@@ -2426,8 +2426,8 @@ void __init trap_init(void)
 	if (board_be_init)
 		board_be_init();
 
-	set_except_vector(EXCCODE_INT, using_rollback_handler() ?
-					rollback_handle_int : handle_int);
+	set_except_vector(EXCCODE_INT, using_skipover_handler() ?
+					skipover_handle_int : handle_int);
 	set_except_vector(EXCCODE_MOD, handle_tlbm);
 	set_except_vector(EXCCODE_TLBL, handle_tlbl);
 	set_except_vector(EXCCODE_TLBS, handle_tlbs);
diff --git a/arch/openrisc/include/asm/cacheflush.h b/arch/openrisc/include/asm/cacheflush.h
index 984c331ff5f4..0e60af486ec1 100644
--- a/arch/openrisc/include/asm/cacheflush.h
+++ b/arch/openrisc/include/asm/cacheflush.h
@@ -23,6 +23,9 @@
  */
 extern void local_dcache_page_flush(struct page *page);
 extern void local_icache_page_inv(struct page *page);
+extern void local_dcache_range_flush(unsigned long start, unsigned long end);
+extern void local_dcache_range_inv(unsigned long start, unsigned long end);
+extern void local_icache_range_inv(unsigned long start, unsigned long end);
 
 /*
  * Data cache flushing always happen on the local cpu. Instruction cache
@@ -39,6 +42,20 @@ extern void smp_icache_page_inv(struct page *page);
 #endif /* CONFIG_SMP */
 
 /*
+ * Even if the actual block size is larger than L1_CACHE_BYTES, paddr
+ * can be incremented by L1_CACHE_BYTES. When paddr is written to the
+ * invalidate register, the entire cache line encompassing this address
+ * is invalidated. Each subsequent reference to the same cache line will
+ * not affect the invalidation process.
+ */
+#define local_dcache_block_flush(addr) \
+	local_dcache_range_flush(addr, addr + L1_CACHE_BYTES)
+#define local_dcache_block_inv(addr) \
+	local_dcache_range_inv(addr, addr + L1_CACHE_BYTES)
+#define local_icache_block_inv(addr) \
+	local_icache_range_inv(addr, addr + L1_CACHE_BYTES)
+
+/*
  * Synchronizes caches. Whenever a cpu writes executable code to memory, this
  * should be called to make sure the processor sees the newly written code.
  */
diff --git a/arch/openrisc/include/asm/cpuinfo.h b/arch/openrisc/include/asm/cpuinfo.h
index 5e4744153d0e..3cfc4cf0b019 100644
--- a/arch/openrisc/include/asm/cpuinfo.h
+++ b/arch/openrisc/include/asm/cpuinfo.h
@@ -15,16 +15,21 @@
 #ifndef __ASM_OPENRISC_CPUINFO_H
 #define __ASM_OPENRISC_CPUINFO_H
 
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
+struct cache_desc {
+	u32 size;
+	u32 sets;
+	u32 block_size;
+	u32 ways;
+};
+
 struct cpuinfo_or1k {
 	u32 clock_frequency;
 
-	u32 icache_size;
-	u32 icache_block_size;
-	u32 icache_ways;
-
-	u32 dcache_size;
-	u32 dcache_block_size;
-	u32 dcache_ways;
+	struct cache_desc icache;
+	struct cache_desc dcache;
 
 	u16 coreid;
 };
@@ -32,4 +37,9 @@ struct cpuinfo_or1k {
 extern struct cpuinfo_or1k cpuinfo_or1k[NR_CPUS];
 extern void setup_cpuinfo(void);
 
+/*
+ * Check if the cache component exists.
+ */
+extern bool cpu_cache_is_present(const unsigned int cache_type);
+
 #endif /* __ASM_OPENRISC_CPUINFO_H */
diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile
index 79129161f3e0..e4c7d9bdd598 100644
--- a/arch/openrisc/kernel/Makefile
+++ b/arch/openrisc/kernel/Makefile
@@ -7,7 +7,7 @@ extra-y	:= vmlinux.lds
 
 obj-y	:= head.o setup.o or32_ksyms.o process.o dma.o \
 	   traps.o time.o irq.o entry.o ptrace.o signal.o \
-	   sys_call_table.o unwinder.o
+	   sys_call_table.o unwinder.o cacheinfo.o
 
 obj-$(CONFIG_SMP)		+= smp.o sync-timer.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
diff --git a/arch/openrisc/kernel/cacheinfo.c b/arch/openrisc/kernel/cacheinfo.c
new file mode 100644
index 000000000000..61230545e4ff
--- /dev/null
+++ b/arch/openrisc/kernel/cacheinfo.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * OpenRISC cacheinfo support
+ *
+ * Based on work done for MIPS and LoongArch. All original copyrights
+ * apply as per the original source declaration.
+ *
+ * OpenRISC implementation:
+ * Copyright (C) 2025 Sahil Siddiq <sahilcdq@proton.me>
+ */
+
+#include <linux/cacheinfo.h>
+#include <asm/cpuinfo.h>
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
+static inline void ci_leaf_init(struct cacheinfo *this_leaf, enum cache_type type,
+				unsigned int level, struct cache_desc *cache, int cpu)
+{
+	this_leaf->type = type;
+	this_leaf->level = level;
+	this_leaf->coherency_line_size = cache->block_size;
+	this_leaf->number_of_sets = cache->sets;
+	this_leaf->ways_of_associativity = cache->ways;
+	this_leaf->size = cache->size;
+	cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+}
+
+int init_cache_level(unsigned int cpu)
+{
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	int leaves = 0, levels = 0;
+	unsigned long upr = mfspr(SPR_UPR);
+	unsigned long iccfgr, dccfgr;
+
+	if (!(upr & SPR_UPR_UP)) {
+		printk(KERN_INFO
+		       "-- no UPR register... unable to detect configuration\n");
+		return -ENOENT;
+	}
+
+	if (cpu_cache_is_present(SPR_UPR_DCP)) {
+		dccfgr = mfspr(SPR_DCCFGR);
+		cpuinfo->dcache.ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
+		cpuinfo->dcache.sets = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
+		cpuinfo->dcache.block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
+		cpuinfo->dcache.size =
+		    cpuinfo->dcache.sets * cpuinfo->dcache.ways * cpuinfo->dcache.block_size;
+		leaves += 1;
+		printk(KERN_INFO
+		       "-- dcache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n",
+		       cpuinfo->dcache.size, cpuinfo->dcache.block_size,
+		       cpuinfo->dcache.sets, cpuinfo->dcache.ways);
+	} else
+		printk(KERN_INFO "-- dcache disabled\n");
+
+	if (cpu_cache_is_present(SPR_UPR_ICP)) {
+		iccfgr = mfspr(SPR_ICCFGR);
+		cpuinfo->icache.ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
+		cpuinfo->icache.sets = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
+		cpuinfo->icache.block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
+		cpuinfo->icache.size =
+		    cpuinfo->icache.sets * cpuinfo->icache.ways * cpuinfo->icache.block_size;
+		leaves += 1;
+		printk(KERN_INFO
+		       "-- icache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n",
+		       cpuinfo->icache.size, cpuinfo->icache.block_size,
+		       cpuinfo->icache.sets, cpuinfo->icache.ways);
+	} else
+		printk(KERN_INFO "-- icache disabled\n");
+
+	if (!leaves)
+		return -ENOENT;
+
+	levels = 1;
+
+	this_cpu_ci->num_leaves = leaves;
+	this_cpu_ci->num_levels = levels;
+
+	return 0;
+}
+
+int populate_cache_leaves(unsigned int cpu)
+{
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+	int level = 1;
+
+	if (cpu_cache_is_present(SPR_UPR_DCP)) {
+		ci_leaf_init(this_leaf, CACHE_TYPE_DATA, level, &cpuinfo->dcache, cpu);
+		this_leaf->attributes = ((mfspr(SPR_DCCFGR) & SPR_DCCFGR_CWS) >> 8) ?
+					CACHE_WRITE_BACK : CACHE_WRITE_THROUGH;
+		this_leaf++;
+	}
+
+	if (cpu_cache_is_present(SPR_UPR_ICP))
+		ci_leaf_init(this_leaf, CACHE_TYPE_INST, level, &cpuinfo->icache, cpu);
+
+	this_cpu_ci->cpu_map_populated = true;
+
+	return 0;
+}
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index b3edbb33b621..3a7b5baaa450 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -17,6 +17,7 @@
 #include <linux/pagewalk.h>
 
 #include <asm/cpuinfo.h>
+#include <asm/cacheflush.h>
 #include <asm/spr_defs.h>
 #include <asm/tlbflush.h>
 
@@ -24,9 +25,6 @@ static int
 page_set_nocache(pte_t *pte, unsigned long addr,
 		 unsigned long next, struct mm_walk *walk)
 {
-	unsigned long cl;
-	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
 	pte_val(*pte) |= _PAGE_CI;
 
 	/*
@@ -36,8 +34,7 @@ page_set_nocache(pte_t *pte, unsigned long addr,
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 
 	/* Flush page out of dcache */
-	for (cl = __pa(addr); cl < __pa(next); cl += cpuinfo->dcache_block_size)
-		mtspr(SPR_DCBFR, cl);
+	local_dcache_range_flush(__pa(addr), __pa(next));
 
 	return 0;
 }
@@ -98,21 +95,14 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size)
 void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
 		enum dma_data_direction dir)
 {
-	unsigned long cl;
-	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
 	switch (dir) {
 	case DMA_TO_DEVICE:
 		/* Flush the dcache for the requested range */
-		for (cl = addr; cl < addr + size;
-		     cl += cpuinfo->dcache_block_size)
-			mtspr(SPR_DCBFR, cl);
+		local_dcache_range_flush(addr, addr + size);
 		break;
 	case DMA_FROM_DEVICE:
 		/* Invalidate the dcache for the requested range */
-		for (cl = addr; cl < addr + size;
-		     cl += cpuinfo->dcache_block_size)
-			mtspr(SPR_DCBIR, cl);
+		local_dcache_range_inv(addr, addr + size);
 		break;
 	default:
 		/*
diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c
index be56eaafc8b9..a9fb9cc6779e 100644
--- a/arch/openrisc/kernel/setup.c
+++ b/arch/openrisc/kernel/setup.c
@@ -113,21 +113,6 @@ static void print_cpuinfo(void)
 		return;
 	}
 
-	if (upr & SPR_UPR_DCP)
-		printk(KERN_INFO
-		       "-- dcache: %4d bytes total, %2d bytes/line, %d way(s)\n",
-		       cpuinfo->dcache_size, cpuinfo->dcache_block_size,
-		       cpuinfo->dcache_ways);
-	else
-		printk(KERN_INFO "-- dcache disabled\n");
-	if (upr & SPR_UPR_ICP)
-		printk(KERN_INFO
-		       "-- icache: %4d bytes total, %2d bytes/line, %d way(s)\n",
-		       cpuinfo->icache_size, cpuinfo->icache_block_size,
-		       cpuinfo->icache_ways);
-	else
-		printk(KERN_INFO "-- icache disabled\n");
-
 	if (upr & SPR_UPR_DMP)
 		printk(KERN_INFO "-- dmmu: %4d entries, %lu way(s)\n",
 		       1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
@@ -155,8 +140,6 @@ static void print_cpuinfo(void)
 void __init setup_cpuinfo(void)
 {
 	struct device_node *cpu;
-	unsigned long iccfgr, dccfgr;
-	unsigned long cache_set_size;
 	int cpu_id = smp_processor_id();
 	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[cpu_id];
 
@@ -164,20 +147,6 @@ void __init setup_cpuinfo(void)
 	if (!cpu)
 		panic("Couldn't find CPU%d in device tree...\n", cpu_id);
 
-	iccfgr = mfspr(SPR_ICCFGR);
-	cpuinfo->icache_ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
-	cache_set_size = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
-	cpuinfo->icache_block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
-	cpuinfo->icache_size =
-	    cache_set_size * cpuinfo->icache_ways * cpuinfo->icache_block_size;
-
-	dccfgr = mfspr(SPR_DCCFGR);
-	cpuinfo->dcache_ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
-	cache_set_size = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
-	cpuinfo->dcache_block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
-	cpuinfo->dcache_size =
-	    cache_set_size * cpuinfo->dcache_ways * cpuinfo->dcache_block_size;
-
 	if (of_property_read_u32(cpu, "clock-frequency",
 				 &cpuinfo->clock_frequency)) {
 		printk(KERN_WARNING
@@ -294,14 +263,14 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	unsigned int vr, cpucfgr;
 	unsigned int avr;
 	unsigned int version;
+#ifdef CONFIG_SMP
 	struct cpuinfo_or1k *cpuinfo = v;
+	seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
+#endif
 
 	vr = mfspr(SPR_VR);
 	cpucfgr = mfspr(SPR_CPUCFGR);
 
-#ifdef CONFIG_SMP
-	seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
-#endif
 	if (vr & SPR_VR_UVRP) {
 		vr = mfspr(SPR_VR2);
 		version = vr & SPR_VR2_VER;
@@ -320,14 +289,6 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "revision\t\t: %d\n", vr & SPR_VR_REV);
 	}
 	seq_printf(m, "frequency\t\t: %ld\n", loops_per_jiffy * HZ);
-	seq_printf(m, "dcache size\t\t: %d bytes\n", cpuinfo->dcache_size);
-	seq_printf(m, "dcache block size\t: %d bytes\n",
-		   cpuinfo->dcache_block_size);
-	seq_printf(m, "dcache ways\t\t: %d\n", cpuinfo->dcache_ways);
-	seq_printf(m, "icache size\t\t: %d bytes\n", cpuinfo->icache_size);
-	seq_printf(m, "icache block size\t: %d bytes\n",
-		   cpuinfo->icache_block_size);
-	seq_printf(m, "icache ways\t\t: %d\n", cpuinfo->icache_ways);
 	seq_printf(m, "immu\t\t\t: %d entries, %lu ways\n",
 		   1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
 		   1 + (mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTW));
diff --git a/arch/openrisc/mm/cache.c b/arch/openrisc/mm/cache.c
index eb43b73f3855..0f265b8e73ec 100644
--- a/arch/openrisc/mm/cache.c
+++ b/arch/openrisc/mm/cache.c
@@ -14,31 +14,70 @@
 #include <asm/spr_defs.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
+#include <asm/cpuinfo.h>
 #include <asm/tlbflush.h>
 
-static __always_inline void cache_loop(struct page *page, const unsigned int reg)
+/*
+ * Check if the cache component exists.
+ */
+bool cpu_cache_is_present(const unsigned int cache_type)
 {
-	unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
-	unsigned long line = paddr & ~(L1_CACHE_BYTES - 1);
+	unsigned long upr = mfspr(SPR_UPR);
+	unsigned long mask = SPR_UPR_UP | cache_type;
+
+	return !((upr & mask) ^ mask);
+}
+
+static __always_inline void cache_loop(unsigned long paddr, unsigned long end,
+				       const unsigned short reg, const unsigned int cache_type)
+{
+	if (!cpu_cache_is_present(cache_type))
+		return;
 
-	while (line < paddr + PAGE_SIZE) {
-		mtspr(reg, line);
-		line += L1_CACHE_BYTES;
+	while (paddr < end) {
+		mtspr(reg, paddr);
+		paddr += L1_CACHE_BYTES;
 	}
 }
 
+static __always_inline void cache_loop_page(struct page *page, const unsigned short reg,
+					    const unsigned int cache_type)
+{
+	unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
+	unsigned long end = paddr + PAGE_SIZE;
+
+	paddr &= ~(L1_CACHE_BYTES - 1);
+
+	cache_loop(paddr, end, reg, cache_type);
+}
+
 void local_dcache_page_flush(struct page *page)
 {
-	cache_loop(page, SPR_DCBFR);
+	cache_loop_page(page, SPR_DCBFR, SPR_UPR_DCP);
 }
 EXPORT_SYMBOL(local_dcache_page_flush);
 
 void local_icache_page_inv(struct page *page)
 {
-	cache_loop(page, SPR_ICBIR);
+	cache_loop_page(page, SPR_ICBIR, SPR_UPR_ICP);
 }
 EXPORT_SYMBOL(local_icache_page_inv);
 
+void local_dcache_range_flush(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_DCBFR, SPR_UPR_DCP);
+}
+
+void local_dcache_range_inv(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_DCBIR, SPR_UPR_DCP);
+}
+
+void local_icache_range_inv(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_ICBIR, SPR_UPR_ICP);
+}
+
 void update_cache(struct vm_area_struct *vma, unsigned long address,
 	pte_t *pte)
 {
@@ -58,4 +97,3 @@ void update_cache(struct vm_area_struct *vma, unsigned long address,
 			sync_icache_dcache(folio_page(folio, nr));
 	}
 }
-
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index be1c2eb8bb94..e4904ca6f0a0 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -35,6 +35,7 @@
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
+#include <asm/cacheflush.h>
 
 int mem_init_done;
 
@@ -176,8 +177,8 @@ void __init paging_init(void)
 	barrier();
 
 	/* Invalidate instruction caches after code modification */
-	mtspr(SPR_ICBIR, 0x900);
-	mtspr(SPR_ICBIR, 0xa00);
+	local_icache_block_inv(0x900);
+	local_icache_block_inv(0xa00);
 
 	/* New TLB miss handlers and kernel page tables are in now place.
 	 * Make sure that page flags get updated for all pages in TLB by
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 96831c988606..1f2d5b7a7f5d 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -142,6 +142,8 @@
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
 #define SO_DEVMEM_DONTNEED	0x4050
 
+#define SO_PASSRIGHTS		0x4051
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/parisc/math-emu/driver.c b/arch/parisc/math-emu/driver.c
index 34495446e051..71829cb7bc81 100644
--- a/arch/parisc/math-emu/driver.c
+++ b/arch/parisc/math-emu/driver.c
@@ -97,9 +97,19 @@ handle_fpe(struct pt_regs *regs)
 
 	memcpy(regs->fr, frcopy, sizeof regs->fr);
 	if (signalcode != 0) {
-	    force_sig_fault(signalcode >> 24, signalcode & 0xffffff,
-			    (void __user *) regs->iaoq[0]);
-	    return -1;
+		int sig = signalcode >> 24;
+
+		if (sig == SIGFPE) {
+			/*
+			 * Clear floating point trap bit to avoid trapping
+			 * again on the first floating-point instruction in
+			 * the userspace signal handler.
+			 */
+			regs->fr[0] &= ~(1ULL << 38);
+		}
+		force_sig_fault(sig, signalcode & 0xffffff,
+				(void __user *) regs->iaoq[0]);
+		return -1;
 	}
 
 	return signalcode ? -1 : 0;
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 1db60fe13802..3d8dc822282a 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -234,10 +234,8 @@ fi
 
 # suppress some warnings in recent ld versions
 nowarn="-z noexecstack"
-if ! ld_is_lld; then
-	if [ "$LD_VERSION" -ge "$(echo 2.39 | ld_version)" ]; then
-		nowarn="$nowarn --no-warn-rwx-segments"
-	fi
+if "${CROSS}ld" -v --no-warn-rwx-segments >/dev/null 2>&1; then
+	nowarn="$nowarn --no-warn-rwx-segments"
 fi
 
 platformo=$object/"$platform".o
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig
index 1bc3466bc909..ae45f70b29f0 100644
--- a/arch/powerpc/configs/pmac32_defconfig
+++ b/arch/powerpc/configs/pmac32_defconfig
@@ -87,7 +87,6 @@ CONFIG_IP_NF_RAW=m
 CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_IP_DCCP=m
 CONFIG_BT=m
 CONFIG_BT_RFCOMM=m
 CONFIG_BT_RFCOMM_TTY=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index a91a766b71a4..5e0f2cd7e62b 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -225,7 +225,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
 CONFIG_TIPC=m
 CONFIG_ATM=m
 CONFIG_ATM_CLIP=m
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 34a5aec4908f..126bf3b06ab7 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -258,10 +258,6 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 			break;
 		}
 	}
-	if (i == hdr->e_shnum) {
-		pr_err("%s: doesn't contain __patchable_function_entries.\n", me->name);
-		return -ENOEXEC;
-	}
 #endif
 
 	pr_debug("Looks like a total of %lu stubs, max\n", relocs);
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 311e2112d782..9f764bc42b8c 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -976,7 +976,7 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start,
 	return 0;
 }
 
-
+#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
 bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
 {
 	if (radix_enabled())
@@ -984,6 +984,7 @@ bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
 
 	return false;
 }
+#endif
 
 int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
 				unsigned long addr, unsigned long next)
@@ -1120,6 +1121,19 @@ int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, in
 	pmd_t *pmd;
 	pte_t *pte;
 
+	/*
+	 * Make sure we align the start vmemmap addr so that we calculate
+	 * the correct start_pfn in altmap boundary check to decided whether
+	 * we should use altmap or RAM based backing memory allocation. Also
+	 * the address need to be aligned for set_pte operation.
+
+	 * If the start addr is already PMD_SIZE aligned we will try to use
+	 * a pmd mapping. We don't want to be too aggressive here beacause
+	 * that will cause more allocations in RAM. So only if the namespace
+	 * vmemmap start addr is PMD_SIZE aligned we will use PMD mapping.
+	 */
+
+	start = ALIGN_DOWN(start, PAGE_SIZE);
 	for (addr = start; addr < end; addr = next) {
 		next = pmd_addr_end(addr, end);
 
@@ -1145,8 +1159,8 @@ int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, in
 			 * in altmap block allocation failures, in which case
 			 * we fallback to RAM for vmemmap allocation.
 			 */
-			if (altmap && (!IS_ALIGNED(addr, PMD_SIZE) ||
-				       altmap_cross_boundary(altmap, addr, PMD_SIZE))) {
+			if (!IS_ALIGNED(addr, PMD_SIZE) || (altmap &&
+			    altmap_cross_boundary(altmap, addr, PMD_SIZE))) {
 				/*
 				 * make sure we don't create altmap mappings
 				 * covering things outside the device.
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 3fbe0295ce14..95d7ba73d43d 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -17,7 +17,7 @@ config PPC_POWERNV
 	select MMU_NOTIFIER
 	select FORCE_SMP
 	select ARCH_SUPPORTS_PER_VMA_LOCK
-	select PPC_RADIX_BROADCAST_TLBIE
+	select PPC_RADIX_BROADCAST_TLBIE if PPC_RADIX_MMU
 	default y
 
 config OPAL_PRD
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index a934c2a262f6..fa3c2fff082a 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -23,7 +23,7 @@ config PPC_PSERIES
 	select FORCE_SMP
 	select SWIOTLB
 	select ARCH_SUPPORTS_PER_VMA_LOCK
-	select PPC_RADIX_BROADCAST_TLBIE
+	select PPC_RADIX_BROADCAST_TLBIE if PPC_RADIX_MMU
 	default y
 
 config PARAVIRT
diff --git a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
index c18822ec849f..58cd546392e0 100644
--- a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
+++ b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
@@ -341,7 +341,7 @@
 					   1024 1024 1024 1024>;
 			snps,priority = <0 1 2 3 4 5 6 7>;
 			snps,dma-masters = <2>;
-			snps,data-width = <4>;
+			snps,data-width = <2>;
 			status = "disabled";
 		};
 
diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h
index 721ec275ce57..231d777d936c 100644
--- a/arch/riscv/include/asm/alternative-macros.h
+++ b/arch/riscv/include/asm/alternative-macros.h
@@ -115,24 +115,19 @@
 	\old_c
 .endm
 
-#define _ALTERNATIVE_CFG(old_c, ...)	\
-	ALTERNATIVE_CFG old_c
-
-#define _ALTERNATIVE_CFG_2(old_c, ...)	\
-	ALTERNATIVE_CFG old_c
+#define __ALTERNATIVE_CFG(old_c, ...)		ALTERNATIVE_CFG old_c
+#define __ALTERNATIVE_CFG_2(old_c, ...)		ALTERNATIVE_CFG old_c
 
 #else /* !__ASSEMBLY__ */
 
-#define __ALTERNATIVE_CFG(old_c)	\
-	old_c "\n"
+#define __ALTERNATIVE_CFG(old_c, ...)		old_c "\n"
+#define __ALTERNATIVE_CFG_2(old_c, ...)		old_c "\n"
 
-#define _ALTERNATIVE_CFG(old_c, ...)	\
-	__ALTERNATIVE_CFG(old_c)
+#endif /* __ASSEMBLY__ */
 
-#define _ALTERNATIVE_CFG_2(old_c, ...)	\
-	__ALTERNATIVE_CFG(old_c)
+#define _ALTERNATIVE_CFG(old_c, ...)		__ALTERNATIVE_CFG(old_c)
+#define _ALTERNATIVE_CFG_2(old_c, ...)		__ALTERNATIVE_CFG_2(old_c)
 
-#endif /* __ASSEMBLY__ */
 #endif /* CONFIG_RISCV_ALTERNATIVE */
 
 /*
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 8de73f91bfa3..b59ffeb668d6 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -34,11 +34,6 @@ static inline void flush_dcache_page(struct page *page)
 	flush_dcache_folio(page_folio(page));
 }
 
-/*
- * RISC-V doesn't have an instruction to flush parts of the instruction cache,
- * so instead we just flush the whole thing.
- */
-#define flush_icache_range(start, end) flush_icache_all()
 #define flush_icache_user_page(vma, pg, addr, len)	\
 do {							\
 	if (vma->vm_flags & VM_EXEC)			\
@@ -78,6 +73,16 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
 
 #endif /* CONFIG_SMP */
 
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range flush_icache_range
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+	flush_icache_all();
+}
+
 extern unsigned int riscv_cbom_block_size;
 extern unsigned int riscv_cboz_block_size;
 void riscv_init_cbo_blocksizes(void);
diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h
index 46677daf708b..cc11c4544cff 100644
--- a/arch/riscv/include/asm/kgdb.h
+++ b/arch/riscv/include/asm/kgdb.h
@@ -19,16 +19,9 @@
 
 #ifndef	__ASSEMBLY__
 
+void arch_kgdb_breakpoint(void);
 extern unsigned long kgdb_compiled_break;
 
-static inline void arch_kgdb_breakpoint(void)
-{
-	asm(".global kgdb_compiled_break\n"
-	    ".option norvc\n"
-	    "kgdb_compiled_break: ebreak\n"
-	    ".option rvc\n");
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #define DBG_REG_ZERO "zero"
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index 121fff429dce..eceabf59ae48 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -62,8 +62,11 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned long *args)
 {
 	args[0] = regs->orig_a0;
-	args++;
-	memcpy(args, &regs->a1, 5 * sizeof(args[0]));
+	args[1] = regs->a1;
+	args[2] = regs->a2;
+	args[3] = regs->a3;
+	args[4] = regs->a4;
+	args[5] = regs->a5;
 }
 
 static inline int syscall_get_arch(struct task_struct *task)
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 8d186bfced45..f7480c9c6f8d 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -9,8 +9,8 @@ CFLAGS_REMOVE_patch.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_return_address.o	= $(CC_FLAGS_FTRACE)
 endif
-CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
-CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_table.o	+= $(call cc-disable-warning, override-init)
+CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init)
 
 ifdef CONFIG_KEXEC_CORE
 AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
index 2e0266ae6bd7..9f3db3503dab 100644
--- a/arch/riscv/kernel/kgdb.c
+++ b/arch/riscv/kernel/kgdb.c
@@ -254,6 +254,12 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
 	regs->epc = pc;
 }
 
+noinline void arch_kgdb_breakpoint(void)
+{
+	asm(".global kgdb_compiled_break\n"
+	    "kgdb_compiled_break: ebreak\n");
+}
+
 void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer,
 				char *remcom_out_buffer)
 {
diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c
index e264e59e596e..91d0b355ceef 100644
--- a/arch/riscv/kernel/module-sections.c
+++ b/arch/riscv/kernel/module-sections.c
@@ -73,16 +73,17 @@ static bool duplicate_rela(const Elf_Rela *rela, int idx)
 static void count_max_entries(Elf_Rela *relas, int num,
 			      unsigned int *plts, unsigned int *gots)
 {
-	unsigned int type, i;
-
-	for (i = 0; i < num; i++) {
-		type = ELF_RISCV_R_TYPE(relas[i].r_info);
-		if (type == R_RISCV_CALL_PLT) {
+	for (int i = 0; i < num; i++) {
+		switch (ELF_R_TYPE(relas[i].r_info)) {
+		case R_RISCV_CALL_PLT:
+		case R_RISCV_PLT32:
 			if (!duplicate_rela(relas, i))
 				(*plts)++;
-		} else if (type == R_RISCV_GOT_HI20) {
+			break;
+		case R_RISCV_GOT_HI20:
 			if (!duplicate_rela(relas, i))
 				(*gots)++;
+			break;
 		}
 	}
 }
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 47d0ebeec93c..7f6147c18033 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -648,7 +648,7 @@ process_accumulated_relocations(struct module *me,
 		kfree(bucket_iter);
 	}
 
-	kfree(*relocation_hashtable);
+	kvfree(*relocation_hashtable);
 }
 
 static int add_relocation_to_accumulate(struct module *me, int type,
@@ -752,9 +752,10 @@ initialize_relocation_hashtable(unsigned int num_relocations,
 
 	hashtable_size <<= should_double_size;
 
-	*relocation_hashtable = kmalloc_array(hashtable_size,
-					      sizeof(**relocation_hashtable),
-					      GFP_KERNEL);
+	/* Number of relocations may be large, so kvmalloc it */
+	*relocation_hashtable = kvmalloc_array(hashtable_size,
+					       sizeof(**relocation_hashtable),
+					       GFP_KERNEL);
 	if (!*relocation_hashtable)
 		return 0;
 
@@ -859,7 +860,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 				}
 
 				j++;
-				if (j > sechdrs[relsec].sh_size / sizeof(*rel))
+				if (j == num_relocations)
 					j = 0;
 
 			} while (j_idx != j);
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
index 4b3dc8beaf77..cc15f7ca6cc1 100644
--- a/arch/riscv/kernel/probes/uprobes.c
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -167,6 +167,7 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 	/* Initialize the slot */
 	void *kaddr = kmap_atomic(page);
 	void *dst = kaddr + (vaddr & ~PAGE_MASK);
+	unsigned long start = (unsigned long)dst;
 
 	memcpy(dst, src, len);
 
@@ -176,13 +177,6 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 		*(uprobe_opcode_t *)dst = __BUG_INSN_32;
 	}
 
+	flush_icache_range(start, start + len);
 	kunmap_atomic(kaddr);
-
-	/*
-	 * We probably need flush_icache_user_page() but it needs vma.
-	 * This should work on most of architectures by default. If
-	 * architecture needs to do something different it can define
-	 * its own version of the function.
-	 */
-	flush_dcache_page(page);
 }
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 7c244de77180..15d8f75902f8 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -275,6 +275,9 @@ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
 	unsigned long pmm;
 	u8 pmlen;
 
+	if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+		return -EINVAL;
+
 	if (is_compat_thread(ti))
 		return -EINVAL;
 
@@ -330,6 +333,9 @@ long get_tagged_addr_ctrl(struct task_struct *task)
 	struct thread_info *ti = task_thread_info(task);
 	long ret = 0;
 
+	if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+		return -EINVAL;
+
 	if (is_compat_thread(ti))
 		return -EINVAL;
 
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index c174544eefc8..f7c9a1caa83e 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -66,6 +66,9 @@ static struct resource bss_res = { .name = "Kernel bss", };
 static struct resource elfcorehdr_res = { .name = "ELF Core hdr", };
 #endif
 
+static int num_standard_resources;
+static struct resource *standard_resources;
+
 static int __init add_resource(struct resource *parent,
 				struct resource *res)
 {
@@ -139,7 +142,7 @@ static void __init init_resources(void)
 	struct resource *res = NULL;
 	struct resource *mem_res = NULL;
 	size_t mem_res_sz = 0;
-	int num_resources = 0, res_idx = 0;
+	int num_resources = 0, res_idx = 0, non_resv_res = 0;
 	int ret = 0;
 
 	/* + 1 as memblock_alloc() might increase memblock.reserved.cnt */
@@ -193,6 +196,7 @@ static void __init init_resources(void)
 	/* Add /memory regions to the resource tree */
 	for_each_mem_region(region) {
 		res = &mem_res[res_idx--];
+		non_resv_res++;
 
 		if (unlikely(memblock_is_nomap(region))) {
 			res->name = "Reserved";
@@ -210,6 +214,9 @@ static void __init init_resources(void)
 			goto error;
 	}
 
+	num_standard_resources = non_resv_res;
+	standard_resources = &mem_res[res_idx + 1];
+
 	/* Clean-up any unused pre-allocated resources */
 	if (res_idx >= 0)
 		memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res));
@@ -221,6 +228,33 @@ static void __init init_resources(void)
 	memblock_free(mem_res, mem_res_sz);
 }
 
+static int __init reserve_memblock_reserved_regions(void)
+{
+	u64 i, j;
+
+	for (i = 0; i < num_standard_resources; i++) {
+		struct resource *mem = &standard_resources[i];
+		phys_addr_t r_start, r_end, mem_size = resource_size(mem);
+
+		if (!memblock_is_region_reserved(mem->start, mem_size))
+			continue;
+
+		for_each_reserved_mem_range(j, &r_start, &r_end) {
+			resource_size_t start, end;
+
+			start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);
+			end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end);
+
+			if (start > mem->end || end < mem->start)
+				continue;
+
+			reserve_region_with_split(mem, start, end, "Reserved");
+		}
+	}
+
+	return 0;
+}
+arch_initcall(reserve_memblock_reserved_regions);
 
 static void __init parse_dtb(void)
 {
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 8ff8e8b36524..9c83848797a7 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -198,47 +198,57 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re
 DO_ERROR_INFO(do_trap_load_fault,
 	SIGSEGV, SEGV_ACCERR, "load access fault");
 
-asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs)
+enum misaligned_access_type {
+	MISALIGNED_STORE,
+	MISALIGNED_LOAD,
+};
+static const struct {
+	const char *type_str;
+	int (*handler)(struct pt_regs *regs);
+} misaligned_handler[] = {
+	[MISALIGNED_STORE] = {
+		.type_str = "Oops - store (or AMO) address misaligned",
+		.handler = handle_misaligned_store,
+	},
+	[MISALIGNED_LOAD] = {
+		.type_str = "Oops - load address misaligned",
+		.handler = handle_misaligned_load,
+	},
+};
+
+static void do_trap_misaligned(struct pt_regs *regs, enum misaligned_access_type type)
 {
+	irqentry_state_t state;
+
 	if (user_mode(regs)) {
 		irqentry_enter_from_user_mode(regs);
+		local_irq_enable();
+	} else {
+		state = irqentry_nmi_enter(regs);
+	}
 
-		if (handle_misaligned_load(regs))
-			do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
-			      "Oops - load address misaligned");
+	if (misaligned_handler[type].handler(regs))
+		do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+			      misaligned_handler[type].type_str);
 
+	if (user_mode(regs)) {
+		local_irq_disable();
 		irqentry_exit_to_user_mode(regs);
 	} else {
-		irqentry_state_t state = irqentry_nmi_enter(regs);
-
-		if (handle_misaligned_load(regs))
-			do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
-			      "Oops - load address misaligned");
-
 		irqentry_nmi_exit(regs, state);
 	}
 }
 
-asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs)
+asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs)
 {
-	if (user_mode(regs)) {
-		irqentry_enter_from_user_mode(regs);
-
-		if (handle_misaligned_store(regs))
-			do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
-				"Oops - store (or AMO) address misaligned");
-
-		irqentry_exit_to_user_mode(regs);
-	} else {
-		irqentry_state_t state = irqentry_nmi_enter(regs);
-
-		if (handle_misaligned_store(regs))
-			do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
-				"Oops - store (or AMO) address misaligned");
+	do_trap_misaligned(regs, MISALIGNED_LOAD);
+}
 
-		irqentry_nmi_exit(regs, state);
-	}
+asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs)
+{
+	do_trap_misaligned(regs, MISALIGNED_STORE);
 }
+
 DO_ERROR_INFO(do_trap_store_fault,
 	SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
 DO_ERROR_INFO(do_trap_ecall_s,
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 4354c87c0376..77c788660223 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -88,6 +88,13 @@
 #define INSN_MATCH_C_FSWSP		0xe002
 #define INSN_MASK_C_FSWSP		0xe003
 
+#define INSN_MATCH_C_LHU		0x8400
+#define INSN_MASK_C_LHU			0xfc43
+#define INSN_MATCH_C_LH			0x8440
+#define INSN_MASK_C_LH			0xfc43
+#define INSN_MATCH_C_SH			0x8c00
+#define INSN_MASK_C_SH			0xfc43
+
 #define INSN_LEN(insn)			((((insn) & 0x3) < 0x3) ? 2 : 4)
 
 #if defined(CONFIG_64BIT)
@@ -268,7 +275,7 @@ static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset,
 	int __ret;					\
 							\
 	if (user_mode(regs)) {				\
-		__ret = __get_user(insn, (type __user *) insn_addr); \
+		__ret = get_user(insn, (type __user *) insn_addr); \
 	} else {					\
 		insn = *(type *)insn_addr;		\
 		__ret = 0;				\
@@ -431,6 +438,13 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs)
 		fp = 1;
 		len = 4;
 #endif
+	} else if ((insn & INSN_MASK_C_LHU) == INSN_MATCH_C_LHU) {
+		len = 2;
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_LH) == INSN_MATCH_C_LH) {
+		len = 2;
+		shift = 8 * (sizeof(ulong) - len);
+		insn = RVC_RS2S(insn) << SH_RD;
 	} else {
 		regs->epc = epc;
 		return -1;
@@ -530,6 +544,9 @@ static int handle_scalar_misaligned_store(struct pt_regs *regs)
 		len = 4;
 		val.data_ulong = GET_F32_RS2C(insn, regs);
 #endif
+	} else if ((insn & INSN_MASK_C_SH) == INSN_MATCH_C_SH) {
+		len = 2;
+		val.data_ulong = GET_RS2S(insn, regs);
 	} else {
 		regs->epc = epc;
 		return -1;
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index 585d2dcf2dab..b8ba13819d05 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -439,29 +439,36 @@ static int __init check_unaligned_access_all_cpus(void)
 {
 	int cpu;
 
-	if (unaligned_scalar_speed_param == RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN &&
-	    !check_unaligned_access_emulated_all_cpus()) {
-		check_unaligned_access_speed_all_cpus();
-	} else {
-		pr_info("scalar unaligned access speed set to '%s' by command line\n",
-			speed_str[unaligned_scalar_speed_param]);
+	if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) {
+		pr_info("scalar unaligned access speed set to '%s' (%lu) by command line\n",
+			speed_str[unaligned_scalar_speed_param], unaligned_scalar_speed_param);
 		for_each_online_cpu(cpu)
 			per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param;
+	} else if (!check_unaligned_access_emulated_all_cpus()) {
+		check_unaligned_access_speed_all_cpus();
+	}
+
+	if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
+		if (!has_vector() &&
+		    unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED) {
+			pr_warn("vector support is not available, ignoring unaligned_vector_speed=%s\n",
+				speed_str[unaligned_vector_speed_param]);
+		} else {
+			pr_info("vector unaligned access speed set to '%s' (%lu) by command line\n",
+				speed_str[unaligned_vector_speed_param], unaligned_vector_speed_param);
+		}
 	}
 
 	if (!has_vector())
 		unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
 
-	if (unaligned_vector_speed_param == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN &&
-	    !check_vector_unaligned_access_emulated_all_cpus() &&
-	    IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) {
-		kthread_run(vec_check_unaligned_access_speed_all_cpus,
-			    NULL, "vec_check_unaligned_access_speed_all_cpus");
-	} else {
-		pr_info("vector unaligned access speed set to '%s' by command line\n",
-			speed_str[unaligned_vector_speed_param]);
+	if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
 		for_each_online_cpu(cpu)
 			per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param;
+	} else if (!check_vector_unaligned_access_emulated_all_cpus() &&
+		   IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) {
+		kthread_run(vec_check_unaligned_access_speed_all_cpus,
+			    NULL, "vec_check_unaligned_access_speed_all_cpus");
 	}
 
 	/*
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 60d684c76c58..02635bac91f1 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -77,6 +77,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 	memcpy(cntx, reset_cntx, sizeof(*cntx));
 	spin_unlock(&vcpu->arch.reset_cntx_lock);
 
+	memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr));
+
 	kvm_riscv_vcpu_fp_reset(vcpu);
 
 	kvm_riscv_vcpu_vector_reset(vcpu);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index db8161ebb43c..99fb986fca6e 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -332,6 +332,10 @@ config HAVE_MARCH_Z16_FEATURES
 	def_bool n
 	select HAVE_MARCH_Z15_FEATURES
 
+config HAVE_MARCH_Z17_FEATURES
+	def_bool n
+	select HAVE_MARCH_Z16_FEATURES
+
 choice
 	prompt "Processor type"
 	default MARCH_Z196
@@ -397,6 +401,14 @@ config MARCH_Z16
 	  Select this to enable optimizations for IBM z16 (3931 and
 	  3932 series).
 
+config MARCH_Z17
+	bool "IBM z17"
+	select HAVE_MARCH_Z17_FEATURES
+	depends on $(cc-option,-march=z17)
+	help
+	  Select this to enable optimizations for IBM z17 (9175 and
+	  9176 series).
+
 endchoice
 
 config MARCH_Z10_TUNE
@@ -420,6 +432,9 @@ config MARCH_Z15_TUNE
 config MARCH_Z16_TUNE
 	def_bool TUNE_Z16 || MARCH_Z16 && TUNE_DEFAULT
 
+config MARCH_Z17_TUNE
+	def_bool TUNE_Z17 || MARCH_Z17 && TUNE_DEFAULT
+
 choice
 	prompt "Tune code generation"
 	default TUNE_DEFAULT
@@ -464,6 +479,10 @@ config TUNE_Z16
 	bool "IBM z16"
 	depends on $(cc-option,-mtune=z16)
 
+config TUNE_Z17
+	bool "IBM z17"
+	depends on $(cc-option,-mtune=z17)
+
 endchoice
 
 config 64BIT
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index b06dc53bfed5..7679bc16b692 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -48,6 +48,7 @@ mflags-$(CONFIG_MARCH_Z13)    := -march=z13
 mflags-$(CONFIG_MARCH_Z14)    := -march=z14
 mflags-$(CONFIG_MARCH_Z15)    := -march=z15
 mflags-$(CONFIG_MARCH_Z16)    := -march=z16
+mflags-$(CONFIG_MARCH_Z17)    := -march=z17
 
 export CC_FLAGS_MARCH := $(mflags-y)
 
@@ -61,6 +62,7 @@ cflags-$(CONFIG_MARCH_Z13_TUNE)		+= -mtune=z13
 cflags-$(CONFIG_MARCH_Z14_TUNE)		+= -mtune=z14
 cflags-$(CONFIG_MARCH_Z15_TUNE)		+= -mtune=z15
 cflags-$(CONFIG_MARCH_Z16_TUNE)		+= -mtune=z16
+cflags-$(CONFIG_MARCH_Z17_TUNE)		+= -mtune=z17
 
 cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include
 
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 6f2c9ce1b154..24b22f6a9e99 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -38,7 +38,6 @@ CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
 CONFIG_PROFILING=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
@@ -92,7 +91,6 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BINFMT_MISC=m
 CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=y
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_SLAB_BUCKETS=y
 CONFIG_SLUB_STATS=y
@@ -395,6 +393,9 @@ CONFIG_CLS_U32_MARK=y
 CONFIG_NET_CLS_FLOW=m
 CONFIG_NET_CLS_CGROUP=y
 CONFIG_NET_CLS_BPF=m
+CONFIG_NET_CLS_FLOWER=m
+CONFIG_NET_CLS_MATCHALL=m
+CONFIG_NET_EMATCH=y
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
@@ -405,6 +406,9 @@ CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_VLAN=m
+CONFIG_NET_ACT_TUNNEL_KEY=m
+CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_GATE=m
 CONFIG_NET_TC_SKB_EXT=y
 CONFIG_DNS_RESOLVER=y
@@ -628,8 +632,16 @@ CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_MEM=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_VDPA=m
+CONFIG_VDPA_SIM=m
+CONFIG_VDPA_SIM_NET=m
+CONFIG_VDPA_SIM_BLOCK=m
+CONFIG_VDPA_USER=m
+CONFIG_MLX5_VDPA_NET=m
+CONFIG_VP_VDPA=m
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
+CONFIG_VHOST_VDPA=m
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -654,7 +666,6 @@ CONFIG_NILFS2_FS=m
 CONFIG_BCACHEFS_FS=y
 CONFIG_BCACHEFS_QUOTA=y
 CONFIG_BCACHEFS_POSIX_ACL=y
-CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
 CONFIG_FS_VERITY=y
@@ -724,11 +735,10 @@ CONFIG_NLS_UTF8=m
 CONFIG_DLM=m
 CONFIG_UNICODE=y
 CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
-CONFIG_HARDENED_USERCOPY=y
-CONFIG_FORTIFY_SOURCE=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_LOCKDOWN_LSM=y
@@ -741,6 +751,8 @@ CONFIG_IMA=y
 CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
+CONFIG_FORTIFY_SOURCE=y
+CONFIG_HARDENED_USERCOPY=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_CRYPTO_USER=m
 # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
@@ -756,7 +768,6 @@ CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_DES=m
@@ -801,7 +812,6 @@ CONFIG_CRYPTO_SHA3_512_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_CHACHA_S390=m
 CONFIG_CRYPTO_HMAC_S390=m
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
@@ -812,9 +822,9 @@ CONFIG_PKEY_UV=m
 CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_SYSTEM_BLACKLIST_KEYRING=y
+CONFIG_CRYPTO_KRB5=m
+CONFIG_CRYPTO_KRB5_SELFTESTS=y
 CONFIG_CORDIC=m
-CONFIG_CRYPTO_LIB_CURVE25519=m
-CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
 CONFIG_RANDOM32_SELFTEST=y
 CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_DMA_CMA=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index f18a7d97ac21..2b8b42d569bc 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -36,7 +36,6 @@ CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
 CONFIG_PROFILING=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
@@ -86,7 +85,6 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BINFMT_MISC=m
 CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=y
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_SLAB_BUCKETS=y
 # CONFIG_COMPAT_BRK is not set
@@ -385,6 +383,9 @@ CONFIG_CLS_U32_MARK=y
 CONFIG_NET_CLS_FLOW=m
 CONFIG_NET_CLS_CGROUP=y
 CONFIG_NET_CLS_BPF=m
+CONFIG_NET_CLS_FLOWER=m
+CONFIG_NET_CLS_MATCHALL=m
+CONFIG_NET_EMATCH=y
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
@@ -395,6 +396,9 @@ CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_VLAN=m
+CONFIG_NET_ACT_TUNNEL_KEY=m
+CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_GATE=m
 CONFIG_NET_TC_SKB_EXT=y
 CONFIG_DNS_RESOLVER=y
@@ -618,8 +622,16 @@ CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_MEM=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_VDPA=m
+CONFIG_VDPA_SIM=m
+CONFIG_VDPA_SIM_NET=m
+CONFIG_VDPA_SIM_BLOCK=m
+CONFIG_VDPA_USER=m
+CONFIG_MLX5_VDPA_NET=m
+CONFIG_VP_VDPA=m
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
+CONFIG_VHOST_VDPA=m
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -641,7 +653,6 @@ CONFIG_NILFS2_FS=m
 CONFIG_BCACHEFS_FS=m
 CONFIG_BCACHEFS_QUOTA=y
 CONFIG_BCACHEFS_POSIX_ACL=y
-CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
 CONFIG_FS_VERITY=y
@@ -711,6 +722,7 @@ CONFIG_NLS_UTF8=m
 CONFIG_DLM=m
 CONFIG_UNICODE=y
 CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
@@ -742,7 +754,6 @@ CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_DES=m
@@ -788,7 +799,6 @@ CONFIG_CRYPTO_SHA3_512_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_CHACHA_S390=m
 CONFIG_CRYPTO_HMAC_S390=m
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
@@ -799,10 +809,10 @@ CONFIG_PKEY_UV=m
 CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_SYSTEM_BLACKLIST_KEYRING=y
+CONFIG_CRYPTO_KRB5=m
+CONFIG_CRYPTO_KRB5_SELFTESTS=y
 CONFIG_CORDIC=m
 CONFIG_PRIME_NUMBERS=m
-CONFIG_CRYPTO_LIB_CURVE25519=m
-CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
 CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=0
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 853b2326a171..8163c1702720 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -70,7 +70,6 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO_DWARF4=y
 CONFIG_DEBUG_FS=y
 CONFIG_PANIC_ON_OOPS=y
-# CONFIG_SCHED_DEBUG is not set
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
 # CONFIG_RCU_TRACE is not set
 # CONFIG_FTRACE is not set
diff --git a/arch/s390/include/asm/march.h b/arch/s390/include/asm/march.h
index fd9eef3be44c..11a71bd14954 100644
--- a/arch/s390/include/asm/march.h
+++ b/arch/s390/include/asm/march.h
@@ -33,6 +33,10 @@
 #define MARCH_HAS_Z16_FEATURES 1
 #endif
 
+#ifdef CONFIG_HAVE_MARCH_Z17_FEATURES
+#define MARCH_HAS_Z17_FEATURES 1
+#endif
+
 #endif /* __DECOMPRESSOR */
 
 #endif /* __ASM_S390_MARCH_H */
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index dd291c9ad6a6..9980c17ba22d 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -602,7 +602,8 @@ SYM_CODE_START(stack_invalid)
 	stmg	%r0,%r7,__PT_R0(%r11)
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	mvc	__PT_R8(64,%r11),0(%r14)
-	stg	%r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2
+	GET_LC	%r2
+	mvc	__PT_ORIG_GPR2(8,%r11),__LC_PGM_LAST_BREAK(%r2)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	jg	kernel_stack_invalid
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 33205dd410e4..e657fad7e376 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -442,7 +442,7 @@ static void cpum_cf_make_setsize(enum cpumf_ctr_set ctrset)
 			ctrset_size = 48;
 		else if (cpumf_ctr_info.csvn >= 3 && cpumf_ctr_info.csvn <= 5)
 			ctrset_size = 128;
-		else if (cpumf_ctr_info.csvn == 6 || cpumf_ctr_info.csvn == 7)
+		else if (cpumf_ctr_info.csvn >= 6 && cpumf_ctr_info.csvn <= 8)
 			ctrset_size = 160;
 		break;
 	case CPUMF_CTR_SET_MT_DIAG:
@@ -858,18 +858,13 @@ static int cpumf_pmu_event_type(struct perf_event *event)
 static int cpumf_pmu_event_init(struct perf_event *event)
 {
 	unsigned int type = event->attr.type;
-	int err;
+	int err = -ENOENT;
 
 	if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
 		err = __hw_perf_event_init(event, type);
 	else if (event->pmu->type == type)
 		/* Registered as unknown PMU */
 		err = __hw_perf_event_init(event, cpumf_pmu_event_type(event));
-	else
-		return -ENOENT;
-
-	if (unlikely(err) && event->destroy)
-		event->destroy(event);
 
 	return err;
 }
@@ -1819,8 +1814,6 @@ static int cfdiag_event_init(struct perf_event *event)
 	event->destroy = hw_perf_event_destroy;
 
 	err = cfdiag_event_init2(event);
-	if (unlikely(err))
-		event->destroy(event);
 out:
 	return err;
 }
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index e4a6bfc91080..690a293eb10d 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -237,7 +237,6 @@ CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_NO_SPECIAL, 0x00f4);
 CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_SPECIAL, 0x00f5);
 CPUMF_EVENT_ATTR(cf_z14, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
 CPUMF_EVENT_ATTR(cf_z14, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
-
 CPUMF_EVENT_ATTR(cf_z15, L1D_RO_EXCL_WRITES, 0x0080);
 CPUMF_EVENT_ATTR(cf_z15, DTLB2_WRITES, 0x0081);
 CPUMF_EVENT_ATTR(cf_z15, DTLB2_MISSES, 0x0082);
@@ -365,6 +364,83 @@ CPUMF_EVENT_ATTR(cf_z16, NNPA_WAIT_LOCK, 0x010d);
 CPUMF_EVENT_ATTR(cf_z16, NNPA_HOLD_LOCK, 0x010e);
 CPUMF_EVENT_ATTR(cf_z16, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
 CPUMF_EVENT_ATTR(cf_z16, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
+CPUMF_EVENT_ATTR(cf_z17, L1D_RO_EXCL_WRITES, 0x0080);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_WRITES, 0x0081);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_MISSES, 0x0082);
+CPUMF_EVENT_ATTR(cf_z17, CRSTE_1MB_WRITES, 0x0083);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_GPAGE_WRITES, 0x0084);
+CPUMF_EVENT_ATTR(cf_z17, ITLB2_WRITES, 0x0086);
+CPUMF_EVENT_ATTR(cf_z17, ITLB2_MISSES, 0x0087);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_PTE_WRITES, 0x0089);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_CRSTE_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_ENGINES_BUSY, 0x008b);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TEND, 0x008c);
+CPUMF_EVENT_ATTR(cf_z17, TX_NC_TEND, 0x008d);
+CPUMF_EVENT_ATTR(cf_z17, L1C_TLB2_MISSES, 0x008f);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ, 0x0091);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_IV, 0x0092);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_CHIP_HIT, 0x0093);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_DRAWER_HIT, 0x0094);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP, 0x0095);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_IV, 0x0096);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_CHIP_HIT, 0x0097);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_DRAWER_HIT, 0x0098);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_MODULE, 0x0099);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_DRAWER, 0x009a);
+CPUMF_EVENT_ATTR(cf_z17, DCW_OFF_DRAWER, 0x009b);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_MEMORY, 0x009c);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_MODULE_MEMORY, 0x009d);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_DRAWER_MEMORY, 0x009e);
+CPUMF_EVENT_ATTR(cf_z17, DCW_OFF_DRAWER_MEMORY, 0x009f);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_IV, 0x00a0);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_CHIP_HIT, 0x00a1);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_DRAWER_HIT, 0x00a2);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_IV, 0x00a3);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_CHIP_HIT, 0x00a4);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_DRAWER_HIT, 0x00a5);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_IV, 0x00a6);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_CHIP_HIT, 0x00a7);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_DRAWER_HIT, 0x00a8);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ, 0x00a9);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_IV, 0x00aa);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_CHIP_HIT, 0x00ab);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_DRAWER_HIT, 0x00ac);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP, 0x00ad);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_IV, 0x00ae);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_CHIP_HIT, 0x00af);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_DRAWER_HIT, 0x00b0);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_MODULE, 0x00b1);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_DRAWER, 0x00b2);
+CPUMF_EVENT_ATTR(cf_z17, ICW_OFF_DRAWER, 0x00b3);
+CPUMF_EVENT_ATTR(cf_z17, CYCLES_SAMETHRD, 0x00ca);
+CPUMF_EVENT_ATTR(cf_z17, CYCLES_DIFFTHRD, 0x00cb);
+CPUMF_EVENT_ATTR(cf_z17, INST_SAMETHRD, 0x00cc);
+CPUMF_EVENT_ATTR(cf_z17, INST_DIFFTHRD, 0x00cd);
+CPUMF_EVENT_ATTR(cf_z17, WRONG_BRANCH_PREDICTION, 0x00ce);
+CPUMF_EVENT_ATTR(cf_z17, VX_BCD_EXECUTION_SLOTS, 0x00e1);
+CPUMF_EVENT_ATTR(cf_z17, DECIMAL_INSTRUCTIONS, 0x00e2);
+CPUMF_EVENT_ATTR(cf_z17, LAST_HOST_TRANSLATIONS, 0x00e8);
+CPUMF_EVENT_ATTR(cf_z17, TX_NC_TABORT, 0x00f4);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TABORT_NO_SPECIAL, 0x00f5);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TABORT_SPECIAL, 0x00f6);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_ACCESS, 0x00f8);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CYCLES, 0x00fd);
+CPUMF_EVENT_ATTR(cf_z17, SORTL, 0x0100);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CC, 0x0109);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CCFINISH, 0x010a);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INVOCATIONS, 0x010b);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_COMPLETIONS, 0x010c);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_WAIT_LOCK, 0x010d);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_HOLD_LOCK, 0x010e);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_ONCHIP, 0x0110);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_OFFCHIP, 0x0111);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_DIFF, 0x0112);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_4K_PREFETCH, 0x0114);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_COMPL_LOCK, 0x0115);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_RETRY_LOCK, 0x0116);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_RETRY_LOCK_WITH_PLO, 0x0117);
+CPUMF_EVENT_ATTR(cf_z17, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
+CPUMF_EVENT_ATTR(cf_z17, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
 
 static struct attribute *cpumcf_fvn1_pmu_event_attr[] __initdata = {
 	CPUMF_EVENT_PTR(cf_fvn1, CPU_CYCLES),
@@ -414,7 +490,7 @@ static struct attribute *cpumcf_svn_12345_pmu_event_attr[] __initdata = {
 	NULL,
 };
 
-static struct attribute *cpumcf_svn_67_pmu_event_attr[] __initdata = {
+static struct attribute *cpumcf_svn_678_pmu_event_attr[] __initdata = {
 	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_FUNCTIONS),
 	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_CYCLES),
 	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS),
@@ -779,6 +855,87 @@ static struct attribute *cpumcf_z16_pmu_event_attr[] __initdata = {
 	NULL,
 };
 
+static struct attribute *cpumcf_z17_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_z17, L1D_RO_EXCL_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, DTLB2_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, DTLB2_MISSES),
+	CPUMF_EVENT_PTR(cf_z17, CRSTE_1MB_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, DTLB2_GPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, ITLB2_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, ITLB2_MISSES),
+	CPUMF_EVENT_PTR(cf_z17, TLB2_PTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, TLB2_CRSTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, TLB2_ENGINES_BUSY),
+	CPUMF_EVENT_PTR(cf_z17, TX_C_TEND),
+	CPUMF_EVENT_PTR(cf_z17, TX_NC_TEND),
+	CPUMF_EVENT_PTR(cf_z17, L1C_TLB2_MISSES),
+	CPUMF_EVENT_PTR(cf_z17, DCW_REQ),
+	CPUMF_EVENT_PTR(cf_z17, DCW_REQ_IV),
+	CPUMF_EVENT_PTR(cf_z17, DCW_REQ_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, DCW_REQ_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_IV),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_MODULE),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_DRAWER),
+	CPUMF_EVENT_PTR(cf_z17, DCW_OFF_DRAWER),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_MEMORY),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_MODULE_MEMORY),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_DRAWER_MEMORY),
+	CPUMF_EVENT_PTR(cf_z17, DCW_OFF_DRAWER_MEMORY),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_IV),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_IV),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_IV),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, ICW_REQ),
+	CPUMF_EVENT_PTR(cf_z17, ICW_REQ_IV),
+	CPUMF_EVENT_PTR(cf_z17, ICW_REQ_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, ICW_REQ_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_IV),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_MODULE),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_DRAWER),
+	CPUMF_EVENT_PTR(cf_z17, ICW_OFF_DRAWER),
+	CPUMF_EVENT_PTR(cf_z17, CYCLES_SAMETHRD),
+	CPUMF_EVENT_PTR(cf_z17, CYCLES_DIFFTHRD),
+	CPUMF_EVENT_PTR(cf_z17, INST_SAMETHRD),
+	CPUMF_EVENT_PTR(cf_z17, INST_DIFFTHRD),
+	CPUMF_EVENT_PTR(cf_z17, WRONG_BRANCH_PREDICTION),
+	CPUMF_EVENT_PTR(cf_z17, VX_BCD_EXECUTION_SLOTS),
+	CPUMF_EVENT_PTR(cf_z17, DECIMAL_INSTRUCTIONS),
+	CPUMF_EVENT_PTR(cf_z17, LAST_HOST_TRANSLATIONS),
+	CPUMF_EVENT_PTR(cf_z17, TX_NC_TABORT),
+	CPUMF_EVENT_PTR(cf_z17, TX_C_TABORT_NO_SPECIAL),
+	CPUMF_EVENT_PTR(cf_z17, TX_C_TABORT_SPECIAL),
+	CPUMF_EVENT_PTR(cf_z17, DFLT_ACCESS),
+	CPUMF_EVENT_PTR(cf_z17, DFLT_CYCLES),
+	CPUMF_EVENT_PTR(cf_z17, SORTL),
+	CPUMF_EVENT_PTR(cf_z17, DFLT_CC),
+	CPUMF_EVENT_PTR(cf_z17, DFLT_CCFINISH),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_INVOCATIONS),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_COMPLETIONS),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_WAIT_LOCK),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_HOLD_LOCK),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_INST_ONCHIP),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_INST_OFFCHIP),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_INST_DIFF),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_4K_PREFETCH),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_COMPL_LOCK),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_RETRY_LOCK),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_RETRY_LOCK_WITH_PLO),
+	CPUMF_EVENT_PTR(cf_z17, MT_DIAG_CYCLES_ONE_THR_ACTIVE),
+	CPUMF_EVENT_PTR(cf_z17, MT_DIAG_CYCLES_TWO_THR_ACTIVE),
+	NULL,
+};
+
 /* END: CPUM_CF COUNTER DEFINITIONS ===================================== */
 
 static struct attribute_group cpumcf_pmu_events_group = {
@@ -859,7 +1016,7 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
 	if (ci.csvn >= 1 && ci.csvn <= 5)
 		csvn = cpumcf_svn_12345_pmu_event_attr;
 	else if (ci.csvn >= 6)
-		csvn = cpumcf_svn_67_pmu_event_attr;
+		csvn = cpumcf_svn_678_pmu_event_attr;
 
 	/* Determine model-specific counter set(s) */
 	get_cpu_id(&cpu_id);
@@ -892,6 +1049,10 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
 	case 0x3932:
 		model = cpumcf_z16_pmu_event_attr;
 		break;
+	case 0x9175:
+	case 0x9176:
+		model = cpumcf_z17_pmu_event_attr;
+		break;
 	default:
 		model = none;
 		break;
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 5f60248cb468..ad22799d8a7d 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -885,9 +885,6 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 		event->attr.exclude_idle = 0;
 
 	err = __hw_perf_event_init(event);
-	if (unlikely(err))
-		if (event->destroy)
-			event->destroy(event);
 	return err;
 }
 
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 54e281436a28..80b1f7a29f11 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -294,6 +294,10 @@ static int __init setup_elf_platform(void)
 	case 0x3932:
 		strcpy(elf_platform, "z16");
 		break;
+	case 0x9175:
+	case 0x9176:
+		strcpy(elf_platform, "z17");
+		break;
 	}
 	return 0;
 }
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 9a929bbcc397..241f7251c873 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -428,6 +428,8 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data)
 		return;
 	}
 	zdev = zpci_create_device(entry->fid, entry->fh, entry->config_state);
+	if (IS_ERR(zdev))
+		return;
 	list_add_tail(&zdev->entry, scan_list);
 }
 
diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c
index 855f818deb98..d5c68ade71ab 100644
--- a/arch/s390/tools/gen_facilities.c
+++ b/arch/s390/tools/gen_facilities.c
@@ -54,6 +54,9 @@ static struct facility_def facility_defs[] = {
 #ifdef CONFIG_HAVE_MARCH_Z15_FEATURES
 			61, /* miscellaneous-instruction-extension 3 */
 #endif
+#ifdef CONFIG_HAVE_MARCH_Z17_FEATURES
+			84, /* miscellaneous-instruction-extension 4 */
+#endif
 			-1 /* END */
 		}
 	},
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 5b464a568664..adcba7329386 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -143,6 +143,8 @@
 
 #define SO_RCVPRIORITY           0x005b
 
+#define SO_PASSRIGHTS            0x005c
+
 #if !defined(__KERNEL__)
 
 
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 1d36a613aad8..9ed792e565c9 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -154,5 +154,6 @@ MRPROPER_FILES += $(HOST_DIR)/include/generated
 archclean:
 	@find . \( -name '*.bb' -o -name '*.bbg' -o -name '*.da' \
 		-o -name '*.gcov' \) -type f -print | xargs rm -f
+	$(Q)$(MAKE) -f $(srctree)/Makefile ARCH=$(HEADER_ARCH) clean
 
 export HEADER_ARCH SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING DEV_NULL_PATH
diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h
index 3a08f9029a3f..1c6e0ae41b0c 100644
--- a/arch/um/include/asm/uaccess.h
+++ b/arch/um/include/asm/uaccess.h
@@ -55,6 +55,7 @@ do {									\
 		goto err_label;						\
 	}								\
 	*((type *)dst) = get_unaligned((type *)(src));			\
+	barrier();							\
 	current->thread.segv_continue = NULL;				\
 } while (0)
 
@@ -66,6 +67,7 @@ do {									\
 	if (__faulted)							\
 		goto err_label;						\
 	put_unaligned(*((type *)src), (type *)(dst));			\
+	barrier();							\
 	current->thread.segv_continue = NULL;				\
 } while (0)
 
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index ce073150dc20..ef2272e92a43 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -225,20 +225,20 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
 			panic("Failed to sync kernel TLBs: %d", err);
 		goto out;
 	}
-	else if (current->mm == NULL) {
-		if (current->pagefault_disabled) {
-			if (!mc) {
-				show_regs(container_of(regs, struct pt_regs, regs));
-				panic("Segfault with pagefaults disabled but no mcontext");
-			}
-			if (!current->thread.segv_continue) {
-				show_regs(container_of(regs, struct pt_regs, regs));
-				panic("Segfault without recovery target");
-			}
-			mc_set_rip(mc, current->thread.segv_continue);
-			current->thread.segv_continue = NULL;
-			goto out;
+	else if (current->pagefault_disabled) {
+		if (!mc) {
+			show_regs(container_of(regs, struct pt_regs, regs));
+			panic("Segfault with pagefaults disabled but no mcontext");
 		}
+		if (!current->thread.segv_continue) {
+			show_regs(container_of(regs, struct pt_regs, regs));
+			panic("Segfault without recovery target");
+		}
+		mc_set_rip(mc, current->thread.segv_continue);
+		current->thread.segv_continue = NULL;
+		goto out;
+	}
+	else if (current->mm == NULL) {
 		show_regs(container_of(regs, struct pt_regs, regs));
 		panic("Segfault with no mm");
 	}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4b9f378e05f6..e21cca404943 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2368,6 +2368,7 @@ config STRICT_SIGALTSTACK_SIZE
 config CFI_AUTO_DEFAULT
 	bool "Attempt to use FineIBT by default at boot time"
 	depends on FINEIBT
+	depends on !RUST || RUSTC_VERSION >= 108800
 	default y
 	help
 	  Attempt to use FineIBT by default at boot time. If enabled,
@@ -2710,6 +2711,18 @@ config MITIGATION_SSB
 	  of speculative execution in a similar way to the Meltdown and Spectre
 	  security vulnerabilities.
 
+config MITIGATION_ITS
+	bool "Enable Indirect Target Selection mitigation"
+	depends on CPU_SUP_INTEL && X86_64
+	depends on MITIGATION_RETPOLINE && MITIGATION_RETHUNK
+	select EXECMEM
+	default y
+	help
+	  Enable Indirect Target Selection (ITS) mitigation. ITS is a bug in
+	  BPU on some Intel CPUs that may allow Spectre V2 style attacks. If
+	  disabled, mitigation cannot be enabled via cmdline.
+	  See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst>
+
 endif
 
 config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 81f55da81967..640fcac3af74 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -59,7 +59,7 @@ KBUILD_CFLAGS	+= $(CONFIG_CC_IMPLICIT_FALLTHROUGH)
 $(obj)/bzImage: asflags-y  := $(SVGA_MODE)
 
 quiet_cmd_image = BUILD   $@
-      cmd_image = cp $< $@; truncate -s %4K $@; cat $(obj)/vmlinux.bin >>$@
+      cmd_image = (dd if=$< bs=4k conv=sync status=none; cat $(filter-out $<,$(real-prereqs))) >$@
 
 $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin FORCE
 	$(call if_changed,image)
diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c
index dbba332e4a12..0e9f84ab4bdc 100644
--- a/arch/x86/boot/compressed/mem.c
+++ b/arch/x86/boot/compressed/mem.c
@@ -38,7 +38,7 @@ void arch_accept_memory(phys_addr_t start, phys_addr_t end)
 	if (early_is_tdx_guest()) {
 		if (!tdx_accept_memory(start, end))
 			panic("TDX: Failed to accept memory\n");
-	} else if (sev_snp_enabled()) {
+	} else if (early_is_sevsnp_guest()) {
 		snp_accept_memory(start, end);
 	} else {
 		error("Cannot accept memory: unknown platform\n");
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index bb55934c1cee..0003e4416efd 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -164,10 +164,7 @@ bool sev_snp_enabled(void)
 
 static void __page_state_change(unsigned long paddr, enum psc_op op)
 {
-	u64 val;
-
-	if (!sev_snp_enabled())
-		return;
+	u64 val, msr;
 
 	/*
 	 * If private -> shared then invalidate the page before requesting the
@@ -176,6 +173,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
 	if (op == SNP_PAGE_STATE_SHARED)
 		pvalidate_4k_page(paddr, paddr, false);
 
+	/* Save the current GHCB MSR value */
+	msr = sev_es_rd_ghcb_msr();
+
 	/* Issue VMGEXIT to change the page state in RMP table. */
 	sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
 	VMGEXIT();
@@ -185,6 +185,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
 	if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val))
 		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
 
+	/* Restore the GHCB MSR value */
+	sev_es_wr_ghcb_msr(msr);
+
 	/*
 	 * Now that page state is changed in the RMP table, validate it so that it is
 	 * consistent with the RMP entry.
@@ -195,11 +198,17 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
 
 void snp_set_page_private(unsigned long paddr)
 {
+	if (!sev_snp_enabled())
+		return;
+
 	__page_state_change(paddr, SNP_PAGE_STATE_PRIVATE);
 }
 
 void snp_set_page_shared(unsigned long paddr)
 {
+	if (!sev_snp_enabled())
+		return;
+
 	__page_state_change(paddr, SNP_PAGE_STATE_SHARED);
 }
 
@@ -223,56 +232,10 @@ static bool early_setup_ghcb(void)
 	return true;
 }
 
-static phys_addr_t __snp_accept_memory(struct snp_psc_desc *desc,
-				       phys_addr_t pa, phys_addr_t pa_end)
-{
-	struct psc_hdr *hdr;
-	struct psc_entry *e;
-	unsigned int i;
-
-	hdr = &desc->hdr;
-	memset(hdr, 0, sizeof(*hdr));
-
-	e = desc->entries;
-
-	i = 0;
-	while (pa < pa_end && i < VMGEXIT_PSC_MAX_ENTRY) {
-		hdr->end_entry = i;
-
-		e->gfn = pa >> PAGE_SHIFT;
-		e->operation = SNP_PAGE_STATE_PRIVATE;
-		if (IS_ALIGNED(pa, PMD_SIZE) && (pa_end - pa) >= PMD_SIZE) {
-			e->pagesize = RMP_PG_SIZE_2M;
-			pa += PMD_SIZE;
-		} else {
-			e->pagesize = RMP_PG_SIZE_4K;
-			pa += PAGE_SIZE;
-		}
-
-		e++;
-		i++;
-	}
-
-	if (vmgexit_psc(boot_ghcb, desc))
-		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
-
-	pvalidate_pages(desc);
-
-	return pa;
-}
-
 void snp_accept_memory(phys_addr_t start, phys_addr_t end)
 {
-	struct snp_psc_desc desc = {};
-	unsigned int i;
-	phys_addr_t pa;
-
-	if (!boot_ghcb && !early_setup_ghcb())
-		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
-
-	pa = start;
-	while (pa < end)
-		pa = __snp_accept_memory(&desc, pa, end);
+	for (phys_addr_t pa = start; pa < end; pa += PAGE_SIZE)
+		__page_state_change(pa, SNP_PAGE_STATE_PRIVATE);
 }
 
 void sev_es_shutdown_ghcb(void)
@@ -682,3 +645,43 @@ void sev_prep_identity_maps(unsigned long top_level_pgt)
 
 	sev_verify_cbit(top_level_pgt);
 }
+
+bool early_is_sevsnp_guest(void)
+{
+	static bool sevsnp;
+
+	if (sevsnp)
+		return true;
+
+	if (!(sev_get_status() & MSR_AMD64_SEV_SNP_ENABLED))
+		return false;
+
+	sevsnp = true;
+
+	if (!snp_vmpl) {
+		unsigned int eax, ebx, ecx, edx;
+
+		/*
+		 * CPUID Fn8000_001F_EAX[28] - SVSM support
+		 */
+		eax = 0x8000001f;
+		ecx = 0;
+		native_cpuid(&eax, &ebx, &ecx, &edx);
+		if (eax & BIT(28)) {
+			struct msr m;
+
+			/* Obtain the address of the calling area to use */
+			boot_rdmsr(MSR_SVSM_CAA, &m);
+			boot_svsm_caa = (void *)m.q;
+			boot_svsm_caa_pa = m.q;
+
+			/*
+			 * The real VMPL level cannot be discovered, but the
+			 * memory acceptance routines make no use of that so
+			 * any non-zero value suffices here.
+			 */
+			snp_vmpl = U8_MAX;
+		}
+	}
+	return true;
+}
diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h
index fc725a981b09..d3900384b8ab 100644
--- a/arch/x86/boot/compressed/sev.h
+++ b/arch/x86/boot/compressed/sev.h
@@ -12,11 +12,15 @@
 
 bool sev_snp_enabled(void);
 void snp_accept_memory(phys_addr_t start, phys_addr_t end);
+u64 sev_get_status(void);
+bool early_is_sevsnp_guest(void);
 
 #else
 
 static inline bool sev_snp_enabled(void) { return false; }
 static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
+static inline u64 sev_get_status(void) { return 0; }
+static inline bool early_is_sevsnp_guest(void) { return false; }
 
 #endif
 
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index b0c1a7a57497..36beaac713c1 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -959,6 +959,102 @@ void snp_accept_memory(phys_addr_t start, phys_addr_t end)
 	set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE);
 }
 
+static int vmgexit_ap_control(u64 event, struct sev_es_save_area *vmsa, u32 apic_id)
+{
+	bool create = event != SVM_VMGEXIT_AP_DESTROY;
+	struct ghcb_state state;
+	unsigned long flags;
+	struct ghcb *ghcb;
+	int ret = 0;
+
+	local_irq_save(flags);
+
+	ghcb = __sev_get_ghcb(&state);
+
+	vc_ghcb_invalidate(ghcb);
+
+	if (create)
+		ghcb_set_rax(ghcb, vmsa->sev_features);
+
+	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
+	ghcb_set_sw_exit_info_1(ghcb,
+				((u64)apic_id << 32)	|
+				((u64)snp_vmpl << 16)	|
+				event);
+	ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));
+
+	sev_es_wr_ghcb_msr(__pa(ghcb));
+	VMGEXIT();
+
+	if (!ghcb_sw_exit_info_1_is_valid(ghcb) ||
+	    lower_32_bits(ghcb->save.sw_exit_info_1)) {
+		pr_err("SNP AP %s error\n", (create ? "CREATE" : "DESTROY"));
+		ret = -EINVAL;
+	}
+
+	__sev_put_ghcb(&state);
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa)
+{
+	int ret;
+
+	if (snp_vmpl) {
+		struct svsm_call call = {};
+		unsigned long flags;
+
+		local_irq_save(flags);
+
+		call.caa = this_cpu_read(svsm_caa);
+		call.rcx = __pa(va);
+
+		if (make_vmsa) {
+			/* Protocol 0, Call ID 2 */
+			call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU);
+			call.rdx = __pa(caa);
+			call.r8  = apic_id;
+		} else {
+			/* Protocol 0, Call ID 3 */
+			call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU);
+		}
+
+		ret = svsm_perform_call_protocol(&call);
+
+		local_irq_restore(flags);
+	} else {
+		/*
+		 * If the kernel runs at VMPL0, it can change the VMSA
+		 * bit for a page using the RMPADJUST instruction.
+		 * However, for the instruction to succeed it must
+		 * target the permissions of a lesser privileged (higher
+		 * numbered) VMPL level, so use VMPL1.
+		 */
+		u64 attrs = 1;
+
+		if (make_vmsa)
+			attrs |= RMPADJUST_VMSA_PAGE_BIT;
+
+		ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+	}
+
+	return ret;
+}
+
+static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id)
+{
+	int err;
+
+	err = snp_set_vmsa(vmsa, NULL, apic_id, false);
+	if (err)
+		pr_err("clear VMSA page failed (%u), leaking page\n", err);
+	else
+		free_page((unsigned long)vmsa);
+}
+
 static void set_pte_enc(pte_t *kpte, int level, void *va)
 {
 	struct pte_enc_desc d = {
@@ -1005,7 +1101,8 @@ static void unshare_all_memory(void)
 			data = per_cpu(runtime_data, cpu);
 			ghcb = (unsigned long)&data->ghcb_page;
 
-			if (addr <= ghcb && ghcb <= addr + size) {
+			/* Handle the case of a huge page containing the GHCB page */
+			if (addr <= ghcb && ghcb < addr + size) {
 				skipped_addr = true;
 				break;
 			}
@@ -1055,11 +1152,70 @@ void snp_kexec_begin(void)
 		pr_warn("Failed to stop shared<->private conversions\n");
 }
 
+/*
+ * Shutdown all APs except the one handling kexec/kdump and clearing
+ * the VMSA tag on AP's VMSA pages as they are not being used as
+ * VMSA page anymore.
+ */
+static void shutdown_all_aps(void)
+{
+	struct sev_es_save_area *vmsa;
+	int apic_id, this_cpu, cpu;
+
+	this_cpu = get_cpu();
+
+	/*
+	 * APs are already in HLT loop when enc_kexec_finish() callback
+	 * is invoked.
+	 */
+	for_each_present_cpu(cpu) {
+		vmsa = per_cpu(sev_vmsa, cpu);
+
+		/*
+		 * The BSP or offlined APs do not have guest allocated VMSA
+		 * and there is no need  to clear the VMSA tag for this page.
+		 */
+		if (!vmsa)
+			continue;
+
+		/*
+		 * Cannot clear the VMSA tag for the currently running vCPU.
+		 */
+		if (this_cpu == cpu) {
+			unsigned long pa;
+			struct page *p;
+
+			pa = __pa(vmsa);
+			/*
+			 * Mark the VMSA page of the running vCPU as offline
+			 * so that is excluded and not touched by makedumpfile
+			 * while generating vmcore during kdump.
+			 */
+			p = pfn_to_online_page(pa >> PAGE_SHIFT);
+			if (p)
+				__SetPageOffline(p);
+			continue;
+		}
+
+		apic_id = cpuid_to_apicid[cpu];
+
+		/*
+		 * Issue AP destroy to ensure AP gets kicked out of guest mode
+		 * to allow using RMPADJUST to remove the VMSA tag on it's
+		 * VMSA page.
+		 */
+		vmgexit_ap_control(SVM_VMGEXIT_AP_DESTROY, vmsa, apic_id);
+		snp_cleanup_vmsa(vmsa, apic_id);
+	}
+
+	put_cpu();
+}
+
 void snp_kexec_finish(void)
 {
 	struct sev_es_runtime_data *data;
+	unsigned long size, addr;
 	unsigned int level, cpu;
-	unsigned long size;
 	struct ghcb *ghcb;
 	pte_t *pte;
 
@@ -1069,6 +1225,8 @@ void snp_kexec_finish(void)
 	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
 		return;
 
+	shutdown_all_aps();
+
 	unshare_all_memory();
 
 	/*
@@ -1085,54 +1243,11 @@ void snp_kexec_finish(void)
 		ghcb = &data->ghcb_page;
 		pte = lookup_address((unsigned long)ghcb, &level);
 		size = page_level_size(level);
-		set_pte_enc(pte, level, (void *)ghcb);
-		snp_set_memory_private((unsigned long)ghcb, (size / PAGE_SIZE));
-	}
-}
-
-static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa)
-{
-	int ret;
-
-	if (snp_vmpl) {
-		struct svsm_call call = {};
-		unsigned long flags;
-
-		local_irq_save(flags);
-
-		call.caa = this_cpu_read(svsm_caa);
-		call.rcx = __pa(va);
-
-		if (make_vmsa) {
-			/* Protocol 0, Call ID 2 */
-			call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU);
-			call.rdx = __pa(caa);
-			call.r8  = apic_id;
-		} else {
-			/* Protocol 0, Call ID 3 */
-			call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU);
-		}
-
-		ret = svsm_perform_call_protocol(&call);
-
-		local_irq_restore(flags);
-	} else {
-		/*
-		 * If the kernel runs at VMPL0, it can change the VMSA
-		 * bit for a page using the RMPADJUST instruction.
-		 * However, for the instruction to succeed it must
-		 * target the permissions of a lesser privileged (higher
-		 * numbered) VMPL level, so use VMPL1.
-		 */
-		u64 attrs = 1;
-
-		if (make_vmsa)
-			attrs |= RMPADJUST_VMSA_PAGE_BIT;
-
-		ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+		/* Handle the case of a huge page containing the GHCB page */
+		addr = (unsigned long)ghcb & page_level_mask(level);
+		set_pte_enc(pte, level, (void *)addr);
+		snp_set_memory_private(addr, (size / PAGE_SIZE));
 	}
-
-	return ret;
 }
 
 #define __ATTR_BASE		(SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK)
@@ -1166,24 +1281,10 @@ static void *snp_alloc_vmsa_page(int cpu)
 	return page_address(p + 1);
 }
 
-static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id)
-{
-	int err;
-
-	err = snp_set_vmsa(vmsa, NULL, apic_id, false);
-	if (err)
-		pr_err("clear VMSA page failed (%u), leaking page\n", err);
-	else
-		free_page((unsigned long)vmsa);
-}
-
 static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 {
 	struct sev_es_save_area *cur_vmsa, *vmsa;
-	struct ghcb_state state;
 	struct svsm_ca *caa;
-	unsigned long flags;
-	struct ghcb *ghcb;
 	u8 sipi_vector;
 	int cpu, ret;
 	u64 cr4;
@@ -1297,33 +1398,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 	}
 
 	/* Issue VMGEXIT AP Creation NAE event */
-	local_irq_save(flags);
-
-	ghcb = __sev_get_ghcb(&state);
-
-	vc_ghcb_invalidate(ghcb);
-	ghcb_set_rax(ghcb, vmsa->sev_features);
-	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
-	ghcb_set_sw_exit_info_1(ghcb,
-				((u64)apic_id << 32)	|
-				((u64)snp_vmpl << 16)	|
-				SVM_VMGEXIT_AP_CREATE);
-	ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));
-
-	sev_es_wr_ghcb_msr(__pa(ghcb));
-	VMGEXIT();
-
-	if (!ghcb_sw_exit_info_1_is_valid(ghcb) ||
-	    lower_32_bits(ghcb->save.sw_exit_info_1)) {
-		pr_err("SNP AP Creation error\n");
-		ret = -EINVAL;
-	}
-
-	__sev_put_ghcb(&state);
-
-	local_irq_restore(flags);
-
-	/* Perform cleanup if there was an error */
+	ret = vmgexit_ap_control(SVM_VMGEXIT_AP_CREATE, vmsa, apic_id);
 	if (ret) {
 		snp_cleanup_vmsa(vmsa, apic_id);
 		vmsa = NULL;
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index d3caa31240ed..175958b02f2b 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -17,19 +17,20 @@
 
 .pushsection .noinstr.text, "ax"
 
-SYM_FUNC_START(entry_ibpb)
+/* Clobbers AX, CX, DX */
+SYM_FUNC_START(write_ibpb)
 	ANNOTATE_NOENDBR
 	movl	$MSR_IA32_PRED_CMD, %ecx
-	movl	$PRED_CMD_IBPB, %eax
+	movl	_ASM_RIP(x86_pred_cmd), %eax
 	xorl	%edx, %edx
 	wrmsr
 
 	/* Make sure IBPB clears return stack preductions too. */
 	FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_BUG_IBPB_NO_RET
 	RET
-SYM_FUNC_END(entry_ibpb)
+SYM_FUNC_END(write_ibpb)
 /* For KVM */
-EXPORT_SYMBOL_GPL(entry_ibpb);
+EXPORT_SYMBOL_GPL(write_ibpb);
 
 .popsection
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f40bdf97d390..ed04a968cc7d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1525,7 +1525,9 @@ SYM_CODE_END(rewind_stack_and_make_dead)
  * ORC to unwind properly.
  *
  * The alignment is for performance and not for safety, and may be safely
- * refactored in the future if needed.
+ * refactored in the future if needed. The .skips are for safety, to ensure
+ * that all RETs are in the second half of a cacheline to mitigate Indirect
+ * Target Selection, rather than taking the slowpath via its_return_thunk.
  */
 SYM_FUNC_START(clear_bhb_loop)
 	ANNOTATE_NOENDBR
@@ -1536,10 +1538,22 @@ SYM_FUNC_START(clear_bhb_loop)
 	call	1f
 	jmp	5f
 	.align 64, 0xcc
+	/*
+	 * Shift instructions so that the RET is in the upper half of the
+	 * cacheline and don't take the slowpath to its_return_thunk.
+	 */
+	.skip 32 - (.Lret1 - 1f), 0xcc
 	ANNOTATE_INTRA_FUNCTION_CALL
 1:	call	2f
-	RET
+.Lret1:	RET
 	.align 64, 0xcc
+	/*
+	 * As above shift instructions for RET at .Lret2 as well.
+	 *
+	 * This should be ideally be: .skip 32 - (.Lret2 - 2f), 0xcc
+	 * but some Clang versions (e.g. 18) don't like this.
+	 */
+	.skip 32 - 18, 0xcc
 2:	movl	$5, %eax
 3:	jmp	4f
 	nop
@@ -1547,7 +1561,7 @@ SYM_FUNC_START(clear_bhb_loop)
 	jnz	3b
 	sub	$1, %ecx
 	jnz	1b
-	RET
+.Lret2:	RET
 5:	lfence
 	pop	%rbp
 	RET
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 6866cc5acb0b..139ad80d1df3 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -629,7 +629,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == event->pmu->type)
 		event->hw.config |= x86_pmu_get_event_config(event);
 
-	if (!event->attr.freq && x86_pmu.limit_period) {
+	if (is_sampling_event(event) && !event->attr.freq && x86_pmu.limit_period) {
 		s64 left = event->attr.sample_period;
 		x86_pmu.limit_period(event, &left);
 		if (left > event->attr.sample_period)
@@ -754,7 +754,7 @@ void x86_pmu_enable_all(int added)
 	}
 }
 
-static inline int is_x86_event(struct perf_event *event)
+int is_x86_event(struct perf_event *event)
 {
 	int i;
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 09d2d66c9f21..c5f385413392 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3049,7 +3049,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int bit;
 	int handled = 0;
-	u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
 
 	inc_irq_stat(apic_perf_irqs);
 
@@ -3093,7 +3092,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		handled++;
 		x86_pmu_handle_guest_pebs(regs, &data);
 		static_call(x86_pmu_drain_pebs)(regs, &data);
-		status &= intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
 
 		/*
 		 * PMI throttle may be triggered, which stops the PEBS event.
@@ -3104,6 +3102,15 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		 */
 		if (pebs_enabled != cpuc->pebs_enabled)
 			wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+
+		/*
+		 * Above PEBS handler (PEBS counters snapshotting) has updated fixed
+		 * counter 3 and perf metrics counts if they are in counter group,
+		 * unnecessary to update again.
+		 */
+		if (cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS] &&
+		    is_pebs_counter_event_group(cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS]))
+			status &= ~GLOBAL_STATUS_PERF_METRICS_OVF_BIT;
 	}
 
 	/*
@@ -3123,6 +3130,8 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		static_call(intel_pmu_update_topdown_event)(NULL, NULL);
 	}
 
+	status &= hybrid(cpuc->pmu, intel_ctrl);
+
 	/*
 	 * Checkpointed counters can lead to 'spurious' PMIs because the
 	 * rollback caused by the PMI will have cleared the overflow status
@@ -4386,7 +4395,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 	arr[pebs_enable] = (struct perf_guest_switch_msr){
 		.msr = MSR_IA32_PEBS_ENABLE,
 		.host = cpuc->pebs_enabled & ~cpuc->intel_ctrl_guest_mask,
-		.guest = pebs_mask & ~cpuc->intel_ctrl_host_mask,
+		.guest = pebs_mask & ~cpuc->intel_ctrl_host_mask & kvm_pmu->pebs_enable,
 	};
 
 	if (arr[pebs_enable].host) {
@@ -7305,8 +7314,17 @@ __init int intel_pmu_init(void)
 		name = "meteorlake_hybrid";
 		break;
 
+	case INTEL_PANTHERLAKE_L:
+		pr_cont("Pantherlake Hybrid events, ");
+		name = "pantherlake_hybrid";
+		goto lnl_common;
+
 	case INTEL_LUNARLAKE_M:
 	case INTEL_ARROWLAKE:
+		pr_cont("Lunarlake Hybrid events, ");
+		name = "lunarlake_hybrid";
+
+	lnl_common:
 		intel_pmu_init_hybrid(hybrid_big_small);
 
 		x86_pmu.pebs_latency_data = lnl_latency_data;
@@ -7328,8 +7346,6 @@ __init int intel_pmu_init(void)
 		intel_pmu_init_skt(&pmu->pmu);
 
 		intel_pmu_pebs_data_source_lnl();
-		pr_cont("Lunarlake Hybrid events, ");
-		name = "lunarlake_hybrid";
 		break;
 
 	case INTEL_ARROWLAKE_H:
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 1f7e1a692a7a..8d86e91bd5e5 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1399,8 +1399,10 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
 	 * + precise_ip < 2 for the non event IP
 	 * + For RTM TSX weight we need GPRs for the abort code.
 	 */
-	gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
-	       (attr->sample_regs_intr & PEBS_GP_REGS);
+	gprs = ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+		(attr->sample_regs_intr & PEBS_GP_REGS)) ||
+	       ((sample_type & PERF_SAMPLE_REGS_USER) &&
+		(attr->sample_regs_user & PEBS_GP_REGS));
 
 	tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) &&
 		     ((attr->config & INTEL_ARCH_EVENT_MASK) ==
@@ -2123,7 +2125,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 			regs->flags &= ~PERF_EFLAGS_EXACT;
 		}
 
-		if (sample_type & PERF_SAMPLE_REGS_INTR)
+		if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER))
 			adaptive_pebs_save_regs(regs, gprs);
 	}
 
@@ -2377,8 +2379,25 @@ __intel_pmu_pebs_last_event(struct perf_event *event,
 			 */
 			intel_pmu_save_and_restart_reload(event, count);
 		}
-	} else
-		intel_pmu_save_and_restart(event);
+	} else {
+		/*
+		 * For a non-precise event, it's possible the
+		 * counters-snapshotting records a positive value for the
+		 * overflowed event. Then the HW auto-reload mechanism
+		 * reset the counter to 0 immediately, because the
+		 * pebs_event_reset is cleared if the PERF_X86_EVENT_AUTO_RELOAD
+		 * is not set. The counter backwards may be observed in a
+		 * PMI handler.
+		 *
+		 * Since the event value has been updated when processing the
+		 * counters-snapshotting record, only needs to set the new
+		 * period for the counter.
+		 */
+		if (is_pebs_counter_event_group(event))
+			static_call(x86_pmu_set_period)(event);
+		else
+			intel_pmu_save_and_restart(event);
+	}
 }
 
 static __always_inline void
@@ -2446,8 +2465,9 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_
 				setup_pebs_fixed_sample_data);
 }
 
-static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, u64 mask)
 {
+	u64 pebs_enabled = cpuc->pebs_enabled & mask;
 	struct perf_event *event;
 	int bit;
 
@@ -2458,7 +2478,7 @@ static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int
 	 * It needs to call intel_pmu_save_and_restart_reload() to
 	 * update the event->count for this case.
 	 */
-	for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
+	for_each_set_bit(bit, (unsigned long *)&pebs_enabled, X86_PMC_IDX_MAX) {
 		event = cpuc->events[bit];
 		if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
 			intel_pmu_save_and_restart_reload(event, 0);
@@ -2493,7 +2513,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 	}
 
 	if (unlikely(base >= top)) {
-		intel_pmu_pebs_event_update_no_drain(cpuc, size);
+		intel_pmu_pebs_event_update_no_drain(cpuc, mask);
 		return;
 	}
 
@@ -2607,7 +2627,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 	       (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED);
 
 	if (unlikely(base >= top)) {
-		intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX);
+		intel_pmu_pebs_event_update_no_drain(cpuc, mask);
 		return;
 	}
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 60973c209c0e..76d96df1475a 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -4891,28 +4891,28 @@ static struct uncore_event_desc snr_uncore_iio_freerunning_events[] = {
 	INTEL_UNCORE_EVENT_DESC(ioclk,			"event=0xff,umask=0x10"),
 	/* Free-Running IIO BANDWIDTH IN Counters */
 	INTEL_UNCORE_EVENT_DESC(bw_in_port0,		"event=0xff,umask=0x20"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port1,		"event=0xff,umask=0x21"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port2,		"event=0xff,umask=0x22"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port3,		"event=0xff,umask=0x23"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port4,		"event=0xff,umask=0x24"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port5,		"event=0xff,umask=0x25"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port6,		"event=0xff,umask=0x26"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port7,		"event=0xff,umask=0x27"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit,	"MiB"),
 	{ /* end: all zeroes */ },
 };
@@ -5485,37 +5485,6 @@ static struct freerunning_counters icx_iio_freerunning[] = {
 	[ICX_IIO_MSR_BW_IN]	= { 0xaa0, 0x1, 0x10, 8, 48, icx_iio_bw_freerunning_box_offsets },
 };
 
-static struct uncore_event_desc icx_uncore_iio_freerunning_events[] = {
-	/* Free-Running IIO CLOCKS Counter */
-	INTEL_UNCORE_EVENT_DESC(ioclk,			"event=0xff,umask=0x10"),
-	/* Free-Running IIO BANDWIDTH IN Counters */
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0,		"event=0xff,umask=0x20"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1,		"event=0xff,umask=0x21"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2,		"event=0xff,umask=0x22"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3,		"event=0xff,umask=0x23"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4,		"event=0xff,umask=0x24"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5,		"event=0xff,umask=0x25"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6,		"event=0xff,umask=0x26"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7,		"event=0xff,umask=0x27"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit,	"MiB"),
-	{ /* end: all zeroes */ },
-};
-
 static struct intel_uncore_type icx_uncore_iio_free_running = {
 	.name			= "iio_free_running",
 	.num_counters		= 9,
@@ -5523,7 +5492,7 @@ static struct intel_uncore_type icx_uncore_iio_free_running = {
 	.num_freerunning_types	= ICX_IIO_FREERUNNING_TYPE_MAX,
 	.freerunning		= icx_iio_freerunning,
 	.ops			= &skx_uncore_iio_freerunning_ops,
-	.event_descs		= icx_uncore_iio_freerunning_events,
+	.event_descs		= snr_uncore_iio_freerunning_events,
 	.format_group		= &skx_uncore_iio_freerunning_format_group,
 };
 
@@ -6320,69 +6289,13 @@ static struct freerunning_counters spr_iio_freerunning[] = {
 	[SPR_IIO_MSR_BW_OUT]	= { 0x3808, 0x1, 0x10, 8, 48 },
 };
 
-static struct uncore_event_desc spr_uncore_iio_freerunning_events[] = {
-	/* Free-Running IIO CLOCKS Counter */
-	INTEL_UNCORE_EVENT_DESC(ioclk,			"event=0xff,umask=0x10"),
-	/* Free-Running IIO BANDWIDTH IN Counters */
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0,		"event=0xff,umask=0x20"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1,		"event=0xff,umask=0x21"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2,		"event=0xff,umask=0x22"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3,		"event=0xff,umask=0x23"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4,		"event=0xff,umask=0x24"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5,		"event=0xff,umask=0x25"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6,		"event=0xff,umask=0x26"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7,		"event=0xff,umask=0x27"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit,	"MiB"),
-	/* Free-Running IIO BANDWIDTH OUT Counters */
-	INTEL_UNCORE_EVENT_DESC(bw_out_port0,		"event=0xff,umask=0x30"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port0.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port0.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port1,		"event=0xff,umask=0x31"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port1.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port1.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port2,		"event=0xff,umask=0x32"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port2.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port2.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port3,		"event=0xff,umask=0x33"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port3.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port3.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port4,		"event=0xff,umask=0x34"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port4.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port4.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port5,		"event=0xff,umask=0x35"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port5.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port5.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port6,		"event=0xff,umask=0x36"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port6.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port6.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port7,		"event=0xff,umask=0x37"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port7.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port7.unit,	"MiB"),
-	{ /* end: all zeroes */ },
-};
-
 static struct intel_uncore_type spr_uncore_iio_free_running = {
 	.name			= "iio_free_running",
 	.num_counters		= 17,
 	.num_freerunning_types	= SPR_IIO_FREERUNNING_TYPE_MAX,
 	.freerunning		= spr_iio_freerunning,
 	.ops			= &skx_uncore_iio_freerunning_ops,
-	.event_descs		= spr_uncore_iio_freerunning_events,
+	.event_descs		= snr_uncore_iio_freerunning_events,
 	.format_group		= &skx_uncore_iio_freerunning_format_group,
 };
 
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 2c0ce0e9545e..46d120597bab 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -110,14 +110,21 @@ static inline bool is_topdown_event(struct perf_event *event)
 	return is_metric_event(event) || is_slots_event(event);
 }
 
+int is_x86_event(struct perf_event *event);
+
+static inline bool check_leader_group(struct perf_event *leader, int flags)
+{
+	return is_x86_event(leader) ? !!(leader->hw.flags & flags) : false;
+}
+
 static inline bool is_branch_counters_group(struct perf_event *event)
 {
-	return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS;
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_BRANCH_COUNTERS);
 }
 
 static inline bool is_pebs_counter_event_group(struct perf_event *event)
 {
-	return event->group_leader->hw.flags & PERF_X86_EVENT_PEBS_CNTR;
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_PEBS_CNTR);
 }
 
 struct amd_nb {
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 4a37a8bd87fd..f2294784babc 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -6,6 +6,7 @@
 #include <linux/stringify.h>
 #include <linux/objtool.h>
 #include <asm/asm.h>
+#include <asm/bug.h>
 
 #define ALT_FLAGS_SHIFT		16
 
@@ -124,6 +125,37 @@ static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
 }
 #endif
 
+#ifdef CONFIG_MITIGATION_ITS
+extern void its_init_mod(struct module *mod);
+extern void its_fini_mod(struct module *mod);
+extern void its_free_mod(struct module *mod);
+extern u8 *its_static_thunk(int reg);
+#else /* CONFIG_MITIGATION_ITS */
+static inline void its_init_mod(struct module *mod) { }
+static inline void its_fini_mod(struct module *mod) { }
+static inline void its_free_mod(struct module *mod) { }
+static inline u8 *its_static_thunk(int reg)
+{
+	WARN_ONCE(1, "ITS not compiled in");
+
+	return NULL;
+}
+#endif
+
+#if defined(CONFIG_MITIGATION_RETHUNK) && defined(CONFIG_OBJTOOL)
+extern bool cpu_wants_rethunk(void);
+extern bool cpu_wants_rethunk_at(void *addr);
+#else
+static __always_inline bool cpu_wants_rethunk(void)
+{
+	return false;
+}
+static __always_inline bool cpu_wants_rethunk_at(void *addr)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_SMP
 extern void alternatives_smp_module_add(struct module *mod, char *name,
 					void *locks, void *locks_end,
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 6c2c152d8a67..30144ef9ef02 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -75,7 +75,7 @@
 #define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */
 #define X86_FEATURE_K8			( 3*32+ 4) /* Opteron, Athlon64 */
 #define X86_FEATURE_ZEN5		( 3*32+ 5) /* CPU based on Zen5 microarchitecture */
-/* Free                                 ( 3*32+ 6) */
+#define X86_FEATURE_ZEN6		( 3*32+ 6) /* CPU based on Zen6 microarchitecture */
 /* Free                                 ( 3*32+ 7) */
 #define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */
 #define X86_FEATURE_UP			( 3*32+ 9) /* "up" SMP kernel running on UP */
@@ -481,6 +481,7 @@
 #define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */
 #define X86_FEATURE_AMD_WORKLOAD_CLASS	(21*32 + 7) /* Workload Classification */
 #define X86_FEATURE_PREFER_YMM		(21*32 + 8) /* Avoid ZMM registers due to downclocking */
+#define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32 + 9) /* Use thunk for indirect branches in lower half of cacheline */
 
 /*
  * BUG word(s)
@@ -533,4 +534,6 @@
 #define X86_BUG_BHI			X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
 #define X86_BUG_IBPB_NO_RET	   	X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
 #define X86_BUG_SPECTRE_V2_USER		X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
+#define X86_BUG_ITS			X86_BUG(1*32 + 6) /* "its" CPU is affected by Indirect Target Selection */
+#define X86_BUG_ITS_NATIVE_ONLY		X86_BUG(1*32 + 7) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 3a97a7eefb51..be10c188614f 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -126,6 +126,8 @@
 #define INTEL_GRANITERAPIDS_X		IFM(6, 0xAD) /* Redwood Cove */
 #define INTEL_GRANITERAPIDS_D		IFM(6, 0xAE)
 
+#define INTEL_BARTLETTLAKE		IFM(6, 0xD7) /* Raptor Cove */
+
 /* "Hybrid" Processors (P-Core/E-Core) */
 
 #define INTEL_LAKEFIELD			IFM(6, 0x8A) /* Sunny Cove / Tremont */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3bdae454a959..7bc174a1f1cb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -35,6 +35,7 @@
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
 #include <asm/asm.h>
+#include <asm/irq_remapping.h>
 #include <asm/kvm_page_track.h>
 #include <asm/kvm_vcpu_regs.h>
 #include <asm/reboot.h>
@@ -2423,4 +2424,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
  */
 #define KVM_EXIT_HYPERCALL_MBZ		GENMASK_ULL(31, 1)
 
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+	return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 695e569159c1..be7cddc414e4 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -17,10 +17,12 @@ struct ucode_cpu_info {
 void load_ucode_bsp(void);
 void load_ucode_ap(void);
 void microcode_bsp_resume(void);
+bool __init microcode_loader_disabled(void);
 #else
 static inline void load_ucode_bsp(void)	{ }
 static inline void load_ucode_ap(void) { }
 static inline void microcode_bsp_resume(void) { }
+static inline bool __init microcode_loader_disabled(void) { return false; }
 #endif
 
 extern unsigned long initrd_start_early;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e6134ef2263d..e7d2f460fcc6 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -211,6 +211,14 @@
 						 * VERW clears CPU Register
 						 * File.
 						 */
+#define ARCH_CAP_ITS_NO			BIT_ULL(62) /*
+						     * Not susceptible to
+						     * Indirect Target Selection.
+						     * This bit is not set by
+						     * HW, but is synthesized by
+						     * VMMs for guests to know
+						     * their affected status.
+						     */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 8a5cc8e70439..7d04ade33541 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -269,7 +269,7 @@
  * typically has NO_MELTDOWN).
  *
  * While retbleed_untrain_ret() doesn't clobber anything but requires stack,
- * entry_ibpb() will clobber AX, CX, DX.
+ * write_ibpb() will clobber AX, CX, DX.
  *
  * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point
  * where we have a stack but before any RET instruction.
@@ -279,7 +279,7 @@
 	VALIDATE_UNRET_END
 	CALL_UNTRAIN_RET
 	ALTERNATIVE_2 "",						\
-		      "call entry_ibpb", \ibpb_feature,			\
+		      "call write_ibpb", \ibpb_feature,			\
 		     __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH
 #endif
 .endm
@@ -336,10 +336,14 @@
 
 #else /* __ASSEMBLER__ */
 
+#define ITS_THUNK_SIZE	64
+
 typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
+typedef u8 its_thunk_t[ITS_THUNK_SIZE];
 extern retpoline_thunk_t __x86_indirect_thunk_array[];
 extern retpoline_thunk_t __x86_indirect_call_thunk_array[];
 extern retpoline_thunk_t __x86_indirect_jump_thunk_array[];
+extern its_thunk_t	 __x86_indirect_its_thunk_array[];
 
 #ifdef CONFIG_MITIGATION_RETHUNK
 extern void __x86_return_thunk(void);
@@ -363,12 +367,18 @@ static inline void srso_return_thunk(void) {}
 static inline void srso_alias_return_thunk(void) {}
 #endif
 
+#ifdef CONFIG_MITIGATION_ITS
+extern void its_return_thunk(void);
+#else
+static inline void its_return_thunk(void) {}
+#endif
+
 extern void retbleed_return_thunk(void);
 extern void srso_return_thunk(void);
 extern void srso_alias_return_thunk(void);
 
 extern void entry_untrain_ret(void);
-extern void entry_ibpb(void);
+extern void write_ibpb(void);
 
 #ifdef CONFIG_X86_64
 extern void clear_bhb_loop(void);
@@ -514,11 +524,11 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
 		: "memory");
 }
 
-extern u64 x86_pred_cmd;
-
 static inline void indirect_branch_prediction_barrier(void)
 {
-	alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_IBPB);
+	asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB)
+			    : ASM_CALL_CONSTRAINT
+			    :: "rax", "rcx", "rdx", "memory");
 }
 
 /* The Intel SPEC CTRL MSR base value cache */
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index a33147520044..c88691b15f3c 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -6,6 +6,8 @@
 #include <linux/mm.h>		/* for struct page */
 #include <linux/pagemap.h>
 
+#include <asm/cpufeature.h>
+
 #define __HAVE_ARCH_PTE_ALLOC_ONE
 #define __HAVE_ARCH_PGD_FREE
 #include <asm-generic/pgalloc.h>
@@ -29,16 +31,17 @@ static inline void paravirt_release_pud(unsigned long pfn) {}
 static inline void paravirt_release_p4d(unsigned long pfn) {}
 #endif
 
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
- * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
- * both 8k in size and 8k-aligned.  That lets us just flip bit 12
- * in a pointer to swap between the two 4k halves.
+ * In case of Page Table Isolation active, we acquire two PGDs instead of one.
+ * Being order-1, it is both 8k in size and 8k-aligned.  That lets us just
+ * flip bit 12 in a pointer to swap between the two 4k halves.
  */
-#define PGD_ALLOCATION_ORDER 1
-#else
-#define PGD_ALLOCATION_ORDER 0
-#endif
+static inline unsigned int pgd_allocation_order(void)
+{
+	if (cpu_feature_enabled(X86_FEATURE_PTI))
+		return 1;
+	return 0;
+}
 
 /*
  * Allocate and free page tables.
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index acb85b9346d8..0020d77a0800 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -116,7 +116,7 @@ enum psc_op {
 #define GHCB_MSR_VMPL_REQ		0x016
 #define GHCB_MSR_VMPL_REQ_LEVEL(v)			\
 	/* GHCBData[39:32] */				\
-	(((u64)(v) & GENMASK_ULL(7, 0) << 32) |		\
+	((((u64)(v) & GENMASK_ULL(7, 0)) << 32) |	\
 	/* GHCBDdata[11:0] */				\
 	GHCB_MSR_VMPL_REQ)
 
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 55a5e656e4b9..4f84d421d1cf 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -16,23 +16,23 @@
 #ifdef __ASSEMBLER__
 
 #define ASM_CLAC \
-	ALTERNATIVE __stringify(ANNOTATE_IGNORE_ALTERNATIVE), "clac", X86_FEATURE_SMAP
+	ALTERNATIVE "", "clac", X86_FEATURE_SMAP
 
 #define ASM_STAC \
-	ALTERNATIVE __stringify(ANNOTATE_IGNORE_ALTERNATIVE), "stac", X86_FEATURE_SMAP
+	ALTERNATIVE "", "stac", X86_FEATURE_SMAP
 
 #else /* __ASSEMBLER__ */
 
 static __always_inline void clac(void)
 {
 	/* Note: a barrier is implicit in alternative() */
-	alternative(ANNOTATE_IGNORE_ALTERNATIVE "", "clac", X86_FEATURE_SMAP);
+	alternative("", "clac", X86_FEATURE_SMAP);
 }
 
 static __always_inline void stac(void)
 {
 	/* Note: a barrier is implicit in alternative() */
-	alternative(ANNOTATE_IGNORE_ALTERNATIVE "", "stac", X86_FEATURE_SMAP);
+	alternative("", "stac", X86_FEATURE_SMAP);
 }
 
 static __always_inline unsigned long smap_save(void)
@@ -59,9 +59,9 @@ static __always_inline void smap_restore(unsigned long flags)
 
 /* These macros can be used in asm() statements */
 #define ASM_CLAC \
-	ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE "", "clac", X86_FEATURE_SMAP)
+	ALTERNATIVE("", "clac", X86_FEATURE_SMAP)
 #define ASM_STAC \
-	ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE "", "stac", X86_FEATURE_SMAP)
+	ALTERNATIVE("", "stac", X86_FEATURE_SMAP)
 
 #define ASM_CLAC_UNSAFE \
 	ALTERNATIVE("", ANNOTATE_IGNORE_ALTERNATIVE "clac", X86_FEATURE_SMAP)
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index dae6a73be40e..9fa321a95eb3 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -23,6 +23,8 @@
 #include <linux/serial_core.h>
 #include <linux/pgtable.h>
 
+#include <xen/xen.h>
+
 #include <asm/e820/api.h>
 #include <asm/irqdomain.h>
 #include <asm/pci_x86.h>
@@ -1729,6 +1731,15 @@ int __init acpi_mps_check(void)
 {
 #if defined(CONFIG_X86_LOCAL_APIC) && !defined(CONFIG_X86_MPPARSE)
 /* mptable code is not built-in*/
+
+	/*
+	 * Xen disables ACPI in PV DomU guests but it still emulates APIC and
+	 * supports SMP. Returning early here ensures that APIC is not disabled
+	 * unnecessarily and the guest is not limited to a single vCPU.
+	 */
+	if (xen_pv_domain() && !xen_initial_domain())
+		return 0;
+
 	if (acpi_disabled || acpi_noirq) {
 		pr_warn("MPS support code is not built-in, using acpi=off or acpi=noirq or pci=noacpi may have problem\n");
 		return 1;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index bf82c6f7d690..45bcff181cba 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -18,6 +18,7 @@
 #include <linux/mmu_context.h>
 #include <linux/bsearch.h>
 #include <linux/sync_core.h>
+#include <linux/execmem.h>
 #include <asm/text-patching.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
@@ -31,6 +32,8 @@
 #include <asm/paravirt.h>
 #include <asm/asm-prototypes.h>
 #include <asm/cfi.h>
+#include <asm/ibt.h>
+#include <asm/set_memory.h>
 
 int __read_mostly alternatives_patched;
 
@@ -124,6 +127,171 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
 #endif
 };
 
+#ifdef CONFIG_FINEIBT
+static bool cfi_paranoid __ro_after_init;
+#endif
+
+#ifdef CONFIG_MITIGATION_ITS
+
+#ifdef CONFIG_MODULES
+static struct module *its_mod;
+#endif
+static void *its_page;
+static unsigned int its_offset;
+
+/* Initialize a thunk with the "jmp *reg; int3" instructions. */
+static void *its_init_thunk(void *thunk, int reg)
+{
+	u8 *bytes = thunk;
+	int offset = 0;
+	int i = 0;
+
+#ifdef CONFIG_FINEIBT
+	if (cfi_paranoid) {
+		/*
+		 * When ITS uses indirect branch thunk the fineibt_paranoid
+		 * caller sequence doesn't fit in the caller site. So put the
+		 * remaining part of the sequence (<ea> + JNE) into the ITS
+		 * thunk.
+		 */
+		bytes[i++] = 0xea; /* invalid instruction */
+		bytes[i++] = 0x75; /* JNE */
+		bytes[i++] = 0xfd;
+
+		offset = 1;
+	}
+#endif
+
+	if (reg >= 8) {
+		bytes[i++] = 0x41; /* REX.B prefix */
+		reg -= 8;
+	}
+	bytes[i++] = 0xff;
+	bytes[i++] = 0xe0 + reg; /* jmp *reg */
+	bytes[i++] = 0xcc;
+
+	return thunk + offset;
+}
+
+#ifdef CONFIG_MODULES
+void its_init_mod(struct module *mod)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+		return;
+
+	mutex_lock(&text_mutex);
+	its_mod = mod;
+	its_page = NULL;
+}
+
+void its_fini_mod(struct module *mod)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+		return;
+
+	WARN_ON_ONCE(its_mod != mod);
+
+	its_mod = NULL;
+	its_page = NULL;
+	mutex_unlock(&text_mutex);
+
+	for (int i = 0; i < mod->its_num_pages; i++) {
+		void *page = mod->its_page_array[i];
+		execmem_restore_rox(page, PAGE_SIZE);
+	}
+}
+
+void its_free_mod(struct module *mod)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+		return;
+
+	for (int i = 0; i < mod->its_num_pages; i++) {
+		void *page = mod->its_page_array[i];
+		execmem_free(page);
+	}
+	kfree(mod->its_page_array);
+}
+#endif /* CONFIG_MODULES */
+
+static void *its_alloc(void)
+{
+	void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+
+	if (!page)
+		return NULL;
+
+#ifdef CONFIG_MODULES
+	if (its_mod) {
+		void *tmp = krealloc(its_mod->its_page_array,
+				     (its_mod->its_num_pages+1) * sizeof(void *),
+				     GFP_KERNEL);
+		if (!tmp)
+			return NULL;
+
+		its_mod->its_page_array = tmp;
+		its_mod->its_page_array[its_mod->its_num_pages++] = page;
+
+		execmem_make_temp_rw(page, PAGE_SIZE);
+	}
+#endif /* CONFIG_MODULES */
+
+	return no_free_ptr(page);
+}
+
+static void *its_allocate_thunk(int reg)
+{
+	int size = 3 + (reg / 8);
+	void *thunk;
+
+#ifdef CONFIG_FINEIBT
+	/*
+	 * The ITS thunk contains an indirect jump and an int3 instruction so
+	 * its size is 3 or 4 bytes depending on the register used. If CFI
+	 * paranoid is used then 3 extra bytes are added in the ITS thunk to
+	 * complete the fineibt_paranoid caller sequence.
+	 */
+	if (cfi_paranoid)
+		size += 3;
+#endif
+
+	if (!its_page || (its_offset + size - 1) >= PAGE_SIZE) {
+		its_page = its_alloc();
+		if (!its_page) {
+			pr_err("ITS page allocation failed\n");
+			return NULL;
+		}
+		memset(its_page, INT3_INSN_OPCODE, PAGE_SIZE);
+		its_offset = 32;
+	}
+
+	/*
+	 * If the indirect branch instruction will be in the lower half
+	 * of a cacheline, then update the offset to reach the upper half.
+	 */
+	if ((its_offset + size - 1) % 64 < 32)
+		its_offset = ((its_offset - 1) | 0x3F) + 33;
+
+	thunk = its_page + its_offset;
+	its_offset += size;
+
+	return its_init_thunk(thunk, reg);
+}
+
+u8 *its_static_thunk(int reg)
+{
+	u8 *thunk = __x86_indirect_its_thunk_array[reg];
+
+#ifdef CONFIG_FINEIBT
+	/* Paranoid thunk starts 2 bytes before */
+	if (cfi_paranoid)
+		return thunk - 2;
+#endif
+	return thunk;
+}
+
+#endif
+
 /*
  * Nomenclature for variable names to simplify and clarify this code and ease
  * any potential staring at it:
@@ -581,7 +749,8 @@ static int emit_indirect(int op, int reg, u8 *bytes)
 	return i;
 }
 
-static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+static int __emit_trampoline(void *addr, struct insn *insn, u8 *bytes,
+			     void *call_dest, void *jmp_dest)
 {
 	u8 op = insn->opcode.bytes[0];
 	int i = 0;
@@ -602,7 +771,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8
 	switch (op) {
 	case CALL_INSN_OPCODE:
 		__text_gen_insn(bytes+i, op, addr+i,
-				__x86_indirect_call_thunk_array[reg],
+				call_dest,
 				CALL_INSN_SIZE);
 		i += CALL_INSN_SIZE;
 		break;
@@ -610,7 +779,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8
 	case JMP32_INSN_OPCODE:
 clang_jcc:
 		__text_gen_insn(bytes+i, op, addr+i,
-				__x86_indirect_jump_thunk_array[reg],
+				jmp_dest,
 				JMP32_INSN_SIZE);
 		i += JMP32_INSN_SIZE;
 		break;
@@ -625,6 +794,48 @@ clang_jcc:
 	return i;
 }
 
+static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+	return __emit_trampoline(addr, insn, bytes,
+				 __x86_indirect_call_thunk_array[reg],
+				 __x86_indirect_jump_thunk_array[reg]);
+}
+
+#ifdef CONFIG_MITIGATION_ITS
+static int emit_its_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+	u8 *thunk = __x86_indirect_its_thunk_array[reg];
+	u8 *tmp = its_allocate_thunk(reg);
+
+	if (tmp)
+		thunk = tmp;
+
+	return __emit_trampoline(addr, insn, bytes, thunk, thunk);
+}
+
+/* Check if an indirect branch is at ITS-unsafe address */
+static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+		return false;
+
+	/* Indirect branch opcode is 2 or 3 bytes depending on reg */
+	addr += 1 + reg / 8;
+
+	/* Lower-half of the cacheline? */
+	return !(addr & 0x20);
+}
+#else /* CONFIG_MITIGATION_ITS */
+
+#ifdef CONFIG_FINEIBT
+static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg)
+{
+	return false;
+}
+#endif
+
+#endif /* CONFIG_MITIGATION_ITS */
+
 /*
  * Rewrite the compiler generated retpoline thunk calls.
  *
@@ -699,6 +910,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 		bytes[i++] = 0xe8; /* LFENCE */
 	}
 
+#ifdef CONFIG_MITIGATION_ITS
+	/*
+	 * Check if the address of last byte of emitted-indirect is in
+	 * lower-half of the cacheline. Such branches need ITS mitigation.
+	 */
+	if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + i, reg))
+		return emit_its_trampoline(addr, insn, reg, bytes);
+#endif
+
 	ret = emit_indirect(op, reg, bytes + i);
 	if (ret < 0)
 		return ret;
@@ -732,6 +952,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 		int len, ret;
 		u8 bytes[16];
 		u8 op1, op2;
+		u8 *dest;
 
 		ret = insn_decode_kernel(&insn, addr);
 		if (WARN_ON_ONCE(ret < 0))
@@ -748,6 +969,12 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 
 		case CALL_INSN_OPCODE:
 		case JMP32_INSN_OPCODE:
+			/* Check for cfi_paranoid + ITS */
+			dest = addr + insn.length + insn.immediate.value;
+			if (dest[-1] == 0xea && (dest[0] & 0xf0) == 0x70) {
+				WARN_ON_ONCE(cfi_mode != CFI_FINEIBT);
+				continue;
+			}
 			break;
 
 		case 0x0f: /* escape */
@@ -775,6 +1002,21 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 
 #ifdef CONFIG_MITIGATION_RETHUNK
 
+bool cpu_wants_rethunk(void)
+{
+	return cpu_feature_enabled(X86_FEATURE_RETHUNK);
+}
+
+bool cpu_wants_rethunk_at(void *addr)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		return false;
+	if (x86_return_thunk != its_return_thunk)
+		return true;
+
+	return !((unsigned long)addr & 0x20);
+}
+
 /*
  * Rewrite the compiler generated return thunk tail-calls.
  *
@@ -791,7 +1033,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
 	int i = 0;
 
 	/* Patch the custom return thunks... */
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+	if (cpu_wants_rethunk_at(addr)) {
 		i = JMP32_INSN_SIZE;
 		__text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i);
 	} else {
@@ -808,7 +1050,7 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 {
 	s32 *s;
 
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+	if (cpu_wants_rethunk())
 		static_call_force_reinit();
 
 	for (s = start; s < end; s++) {
@@ -1022,8 +1264,6 @@ int cfi_get_func_arity(void *func)
 static bool cfi_rand __ro_after_init = true;
 static u32  cfi_seed __ro_after_init;
 
-static bool cfi_paranoid __ro_after_init = false;
-
 /*
  * Re-hash the CFI hash with a boot-time seed while making sure the result is
  * not a valid ENDBR instruction.
@@ -1436,6 +1676,19 @@ static int cfi_rand_callers(s32 *start, s32 *end)
 	return 0;
 }
 
+static int emit_paranoid_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+	u8 *thunk = (void *)__x86_indirect_its_thunk_array[reg] - 2;
+
+#ifdef CONFIG_MITIGATION_ITS
+	u8 *tmp = its_allocate_thunk(reg);
+	if (tmp)
+		thunk = tmp;
+#endif
+
+	return __emit_trampoline(addr, insn, bytes, thunk, thunk);
+}
+
 static int cfi_rewrite_callers(s32 *start, s32 *end)
 {
 	s32 *s;
@@ -1477,9 +1730,14 @@ static int cfi_rewrite_callers(s32 *start, s32 *end)
 		memcpy(bytes, fineibt_paranoid_start, fineibt_paranoid_size);
 		memcpy(bytes + fineibt_caller_hash, &hash, 4);
 
-		ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind);
-		if (WARN_ON_ONCE(ret != 3))
-			continue;
+		if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + fineibt_paranoid_ind, 11)) {
+			emit_paranoid_trampoline(addr + fineibt_caller_size,
+						 &insn, 11, bytes + fineibt_caller_size);
+		} else {
+			ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind);
+			if (WARN_ON_ONCE(ret != 3))
+				continue;
+		}
 
 		text_poke_early(addr, bytes, fineibt_paranoid_size);
 	}
@@ -1706,29 +1964,66 @@ Efault:
 	return false;
 }
 
+static bool is_paranoid_thunk(unsigned long addr)
+{
+	u32 thunk;
+
+	__get_kernel_nofault(&thunk, (u32 *)addr, u32, Efault);
+	return (thunk & 0x00FFFFFF) == 0xfd75ea;
+
+Efault:
+	return false;
+}
+
 /*
  * regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[]
- * sequence.
+ * sequence, or to an invalid instruction (0xea) + Jcc.d8 for cfi_paranoid + ITS
+ * thunk.
  */
 static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, u32 *type)
 {
 	unsigned long addr = regs->ip - fineibt_paranoid_ud;
-	u32 hash;
 
-	if (!cfi_paranoid || !is_cfi_trap(addr + fineibt_caller_size - LEN_UD2))
+	if (!cfi_paranoid)
 		return false;
 
-	__get_kernel_nofault(&hash, addr + fineibt_caller_hash, u32, Efault);
-	*target = regs->r11 + fineibt_preamble_size;
-	*type = regs->r10;
+	if (is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) {
+		*target = regs->r11 + fineibt_preamble_size;
+		*type = regs->r10;
+
+		/*
+		 * Since the trapping instruction is the exact, but LOCK prefixed,
+		 * Jcc.d8 that got us here, the normal fixup will work.
+		 */
+		return true;
+	}
 
 	/*
-	 * Since the trapping instruction is the exact, but LOCK prefixed,
-	 * Jcc.d8 that got us here, the normal fixup will work.
+	 * The cfi_paranoid + ITS thunk combination results in:
+	 *
+	 *  0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
+	 *  6:   45 3b 53 f7             cmp    -0x9(%r11), %r10d
+	 *  a:   4d 8d 5b f0             lea    -0x10(%r11), %r11
+	 *  e:   2e e8 XX XX XX XX	 cs call __x86_indirect_paranoid_thunk_r11
+	 *
+	 * Where the paranoid_thunk looks like:
+	 *
+	 *  1d:  <ea>                    (bad)
+	 *  __x86_indirect_paranoid_thunk_r11:
+	 *  1e:  75 fd                   jne 1d
+	 *  __x86_indirect_its_thunk_r11:
+	 *  20:  41 ff eb                jmp *%r11
+	 *  23:  cc                      int3
+	 *
 	 */
-	return true;
+	if (is_paranoid_thunk(regs->ip)) {
+		*target = regs->r11 + fineibt_preamble_size;
+		*type = regs->r10;
+
+		regs->ip = *target;
+		return true;
+	}
 
-Efault:
 	return false;
 }
 
@@ -2031,6 +2326,8 @@ static noinline void __init alt_reloc_selftest(void)
 
 void __init alternative_instructions(void)
 {
+	u64 ibt;
+
 	int3_selftest();
 
 	/*
@@ -2057,6 +2354,9 @@ void __init alternative_instructions(void)
 	 */
 	paravirt_set_cap();
 
+	/* Keep CET-IBT disabled until caller/callee are patched */
+	ibt = ibt_save(/*disable*/ true);
+
 	__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
 			__cfi_sites, __cfi_sites_end, true);
 
@@ -2080,6 +2380,8 @@ void __init alternative_instructions(void)
 	 */
 	apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
 
+	ibt_restore(ibt);
+
 #ifdef CONFIG_SMP
 	/* Patch to UP if other cpus not imminent. */
 	if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 79569f72b8ee..4e06baab40bb 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -472,6 +472,11 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		case 0x60 ... 0x7f:
 			setup_force_cpu_cap(X86_FEATURE_ZEN5);
 			break;
+		case 0x50 ... 0x5f:
+		case 0x90 ... 0xaf:
+		case 0xc0 ... 0xcf:
+			setup_force_cpu_cap(X86_FEATURE_ZEN6);
+			break;
 		default:
 			goto warn;
 		}
@@ -805,6 +810,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 static const struct x86_cpu_id erratum_1386_microcode[] = {
 	X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x01), 0x2, 0x2, 0x0800126e),
 	X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x31), 0x0, 0x0, 0x08301052),
+	{}
 };
 
 static void fix_erratum_1386(struct cpuinfo_x86 *c)
@@ -868,6 +874,16 @@ static void init_amd_zen1(struct cpuinfo_x86 *c)
 
 	pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
 	setup_force_cpu_bug(X86_BUG_DIV0);
+
+	/*
+	 * Turn off the Instructions Retired free counter on machines that are
+	 * susceptible to erratum #1054 "Instructions Retired Performance
+	 * Counter May Be Inaccurate".
+	 */
+	if (c->x86_model < 0x30) {
+		msr_clear_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
+		clear_cpu_cap(c, X86_FEATURE_IRPERF);
+	}
 }
 
 static bool cpu_has_zenbleed_microcode(void)
@@ -1051,13 +1067,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 	if (!cpu_feature_enabled(X86_FEATURE_XENPV))
 		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
 
-	/*
-	 * Turn on the Instructions Retired free counter on machines not
-	 * susceptible to erratum #1054 "Instructions Retired Performance
-	 * Counter May Be Inaccurate".
-	 */
-	if (cpu_has(c, X86_FEATURE_IRPERF) &&
-	    (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f))
+	/* Enable the Instructions Retired free counter */
+	if (cpu_has(c, X86_FEATURE_IRPERF))
 		msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
 
 	check_null_seg_clears_base(c);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 4386aa6c69e1..8596ce85026c 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -49,6 +49,7 @@ static void __init srbds_select_mitigation(void);
 static void __init l1d_flush_select_mitigation(void);
 static void __init srso_select_mitigation(void);
 static void __init gds_select_mitigation(void);
+static void __init its_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR without task-specific bits set */
 u64 x86_spec_ctrl_base;
@@ -59,7 +60,6 @@ DEFINE_PER_CPU(u64, x86_spec_ctrl_current);
 EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current);
 
 u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB;
-EXPORT_SYMBOL_GPL(x86_pred_cmd);
 
 static u64 __ro_after_init x86_arch_cap_msr;
 
@@ -67,6 +67,14 @@ static DEFINE_MUTEX(spec_ctrl_mutex);
 
 void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk;
 
+static void __init set_return_thunk(void *thunk)
+{
+	if (x86_return_thunk != __x86_return_thunk)
+		pr_warn("x86/bugs: return thunk changed\n");
+
+	x86_return_thunk = thunk;
+}
+
 /* Update SPEC_CTRL MSR and its cached copy unconditionally */
 static void update_spec_ctrl(u64 val)
 {
@@ -179,6 +187,7 @@ void __init cpu_select_mitigations(void)
 	 */
 	srso_select_mitigation();
 	gds_select_mitigation();
+	its_select_mitigation();
 }
 
 /*
@@ -1119,7 +1128,7 @@ do_cmd_auto:
 		setup_force_cpu_cap(X86_FEATURE_RETHUNK);
 		setup_force_cpu_cap(X86_FEATURE_UNRET);
 
-		x86_return_thunk = retbleed_return_thunk;
+		set_return_thunk(retbleed_return_thunk);
 
 		if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
 		    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
@@ -1142,7 +1151,7 @@ do_cmd_auto:
 		setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
 
 		/*
-		 * There is no need for RSB filling: entry_ibpb() ensures
+		 * There is no need for RSB filling: write_ibpb() ensures
 		 * all predictions, including the RSB, are invalidated,
 		 * regardless of IBPB implementation.
 		 */
@@ -1154,7 +1163,7 @@ do_cmd_auto:
 		setup_force_cpu_cap(X86_FEATURE_RETHUNK);
 		setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
 
-		x86_return_thunk = call_depth_return_thunk;
+		set_return_thunk(call_depth_return_thunk);
 		break;
 
 	default:
@@ -1189,6 +1198,145 @@ do_cmd_auto:
 }
 
 #undef pr_fmt
+#define pr_fmt(fmt)     "ITS: " fmt
+
+enum its_mitigation_cmd {
+	ITS_CMD_OFF,
+	ITS_CMD_ON,
+	ITS_CMD_VMEXIT,
+	ITS_CMD_RSB_STUFF,
+};
+
+enum its_mitigation {
+	ITS_MITIGATION_OFF,
+	ITS_MITIGATION_VMEXIT_ONLY,
+	ITS_MITIGATION_ALIGNED_THUNKS,
+	ITS_MITIGATION_RETPOLINE_STUFF,
+};
+
+static const char * const its_strings[] = {
+	[ITS_MITIGATION_OFF]			= "Vulnerable",
+	[ITS_MITIGATION_VMEXIT_ONLY]		= "Mitigation: Vulnerable, KVM: Not affected",
+	[ITS_MITIGATION_ALIGNED_THUNKS]		= "Mitigation: Aligned branch/return thunks",
+	[ITS_MITIGATION_RETPOLINE_STUFF]	= "Mitigation: Retpolines, Stuffing RSB",
+};
+
+static enum its_mitigation its_mitigation __ro_after_init = ITS_MITIGATION_ALIGNED_THUNKS;
+
+static enum its_mitigation_cmd its_cmd __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_ITS) ? ITS_CMD_ON : ITS_CMD_OFF;
+
+static int __init its_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!IS_ENABLED(CONFIG_MITIGATION_ITS)) {
+		pr_err("Mitigation disabled at compile time, ignoring option (%s)", str);
+		return 0;
+	}
+
+	if (!strcmp(str, "off")) {
+		its_cmd = ITS_CMD_OFF;
+	} else if (!strcmp(str, "on")) {
+		its_cmd = ITS_CMD_ON;
+	} else if (!strcmp(str, "force")) {
+		its_cmd = ITS_CMD_ON;
+		setup_force_cpu_bug(X86_BUG_ITS);
+	} else if (!strcmp(str, "vmexit")) {
+		its_cmd = ITS_CMD_VMEXIT;
+	} else if (!strcmp(str, "stuff")) {
+		its_cmd = ITS_CMD_RSB_STUFF;
+	} else {
+		pr_err("Ignoring unknown indirect_target_selection option (%s).", str);
+	}
+
+	return 0;
+}
+early_param("indirect_target_selection", its_parse_cmdline);
+
+static void __init its_select_mitigation(void)
+{
+	enum its_mitigation_cmd cmd = its_cmd;
+
+	if (!boot_cpu_has_bug(X86_BUG_ITS) || cpu_mitigations_off()) {
+		its_mitigation = ITS_MITIGATION_OFF;
+		return;
+	}
+
+	/* Retpoline+CDT mitigates ITS, bail out */
+	if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
+	    boot_cpu_has(X86_FEATURE_CALL_DEPTH)) {
+		its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
+		goto out;
+	}
+
+	/* Exit early to avoid irrelevant warnings */
+	if (cmd == ITS_CMD_OFF) {
+		its_mitigation = ITS_MITIGATION_OFF;
+		goto out;
+	}
+	if (spectre_v2_enabled == SPECTRE_V2_NONE) {
+		pr_err("WARNING: Spectre-v2 mitigation is off, disabling ITS\n");
+		its_mitigation = ITS_MITIGATION_OFF;
+		goto out;
+	}
+	if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) ||
+	    !IS_ENABLED(CONFIG_MITIGATION_RETHUNK)) {
+		pr_err("WARNING: ITS mitigation depends on retpoline and rethunk support\n");
+		its_mitigation = ITS_MITIGATION_OFF;
+		goto out;
+	}
+	if (IS_ENABLED(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)) {
+		pr_err("WARNING: ITS mitigation is not compatible with CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B\n");
+		its_mitigation = ITS_MITIGATION_OFF;
+		goto out;
+	}
+	if (boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) {
+		pr_err("WARNING: ITS mitigation is not compatible with lfence mitigation\n");
+		its_mitigation = ITS_MITIGATION_OFF;
+		goto out;
+	}
+
+	if (cmd == ITS_CMD_RSB_STUFF &&
+	    (!boot_cpu_has(X86_FEATURE_RETPOLINE) || !IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING))) {
+		pr_err("RSB stuff mitigation not supported, using default\n");
+		cmd = ITS_CMD_ON;
+	}
+
+	switch (cmd) {
+	case ITS_CMD_OFF:
+		its_mitigation = ITS_MITIGATION_OFF;
+		break;
+	case ITS_CMD_VMEXIT:
+		if (boot_cpu_has_bug(X86_BUG_ITS_NATIVE_ONLY)) {
+			its_mitigation = ITS_MITIGATION_VMEXIT_ONLY;
+			goto out;
+		}
+		fallthrough;
+	case ITS_CMD_ON:
+		its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
+		if (!boot_cpu_has(X86_FEATURE_RETPOLINE))
+			setup_force_cpu_cap(X86_FEATURE_INDIRECT_THUNK_ITS);
+		setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+		set_return_thunk(its_return_thunk);
+		break;
+	case ITS_CMD_RSB_STUFF:
+		its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
+		setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+		setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
+		set_return_thunk(call_depth_return_thunk);
+		if (retbleed_mitigation == RETBLEED_MITIGATION_NONE) {
+			retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
+			pr_info("Retbleed mitigation updated to stuffing\n");
+		}
+		break;
+	}
+out:
+	pr_info("%s\n", its_strings[its_mitigation]);
+}
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V2 : " fmt
 
 static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init =
@@ -1592,51 +1740,54 @@ static void __init spec_ctrl_disable_kernel_rrsba(void)
 	rrsba_disabled = true;
 }
 
-static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode)
+static void __init spectre_v2_select_rsb_mitigation(enum spectre_v2_mitigation mode)
 {
 	/*
-	 * Similar to context switches, there are two types of RSB attacks
-	 * after VM exit:
+	 * WARNING! There are many subtleties to consider when changing *any*
+	 * code related to RSB-related mitigations.  Before doing so, carefully
+	 * read the following document, and update if necessary:
 	 *
-	 * 1) RSB underflow
+	 *   Documentation/admin-guide/hw-vuln/rsb.rst
 	 *
-	 * 2) Poisoned RSB entry
+	 * In an overly simplified nutshell:
 	 *
-	 * When retpoline is enabled, both are mitigated by filling/clearing
-	 * the RSB.
+	 *   - User->user RSB attacks are conditionally mitigated during
+	 *     context switches by cond_mitigation -> write_ibpb().
 	 *
-	 * When IBRS is enabled, while #1 would be mitigated by the IBRS branch
-	 * prediction isolation protections, RSB still needs to be cleared
-	 * because of #2.  Note that SMEP provides no protection here, unlike
-	 * user-space-poisoned RSB entries.
+	 *   - User->kernel and guest->host attacks are mitigated by eIBRS or
+	 *     RSB filling.
 	 *
-	 * eIBRS should protect against RSB poisoning, but if the EIBRS_PBRSB
-	 * bug is present then a LITE version of RSB protection is required,
-	 * just a single call needs to retire before a RET is executed.
+	 *     Though, depending on config, note that other alternative
+	 *     mitigations may end up getting used instead, e.g., IBPB on
+	 *     entry/vmexit, call depth tracking, or return thunks.
 	 */
+
 	switch (mode) {
 	case SPECTRE_V2_NONE:
-		return;
+		break;
 
-	case SPECTRE_V2_EIBRS_LFENCE:
 	case SPECTRE_V2_EIBRS:
+	case SPECTRE_V2_EIBRS_LFENCE:
+	case SPECTRE_V2_EIBRS_RETPOLINE:
 		if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
-			setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE);
 			pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n");
+			setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE);
 		}
-		return;
+		break;
 
-	case SPECTRE_V2_EIBRS_RETPOLINE:
 	case SPECTRE_V2_RETPOLINE:
 	case SPECTRE_V2_LFENCE:
 	case SPECTRE_V2_IBRS:
+		pr_info("Spectre v2 / SpectreRSB: Filling RSB on context switch and VMEXIT\n");
+		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
 		setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT);
-		pr_info("Spectre v2 / SpectreRSB : Filling RSB on VMEXIT\n");
-		return;
-	}
+		break;
 
-	pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation at VM exit");
-	dump_stack();
+	default:
+		pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation\n");
+		dump_stack();
+		break;
+	}
 }
 
 /*
@@ -1695,11 +1846,11 @@ static void __init bhi_select_mitigation(void)
 			return;
 	}
 
-	/* Mitigate in hardware if supported */
-	if (spec_ctrl_bhi_dis())
+	if (!IS_ENABLED(CONFIG_X86_64))
 		return;
 
-	if (!IS_ENABLED(CONFIG_X86_64))
+	/* Mitigate in hardware if supported */
+	if (spec_ctrl_bhi_dis())
 		return;
 
 	if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) {
@@ -1830,48 +1981,7 @@ static void __init spectre_v2_select_mitigation(void)
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
-	/*
-	 * If Spectre v2 protection has been enabled, fill the RSB during a
-	 * context switch.  In general there are two types of RSB attacks
-	 * across context switches, for which the CALLs/RETs may be unbalanced.
-	 *
-	 * 1) RSB underflow
-	 *
-	 *    Some Intel parts have "bottomless RSB".  When the RSB is empty,
-	 *    speculated return targets may come from the branch predictor,
-	 *    which could have a user-poisoned BTB or BHB entry.
-	 *
-	 *    AMD has it even worse: *all* returns are speculated from the BTB,
-	 *    regardless of the state of the RSB.
-	 *
-	 *    When IBRS or eIBRS is enabled, the "user -> kernel" attack
-	 *    scenario is mitigated by the IBRS branch prediction isolation
-	 *    properties, so the RSB buffer filling wouldn't be necessary to
-	 *    protect against this type of attack.
-	 *
-	 *    The "user -> user" attack scenario is mitigated by RSB filling.
-	 *
-	 * 2) Poisoned RSB entry
-	 *
-	 *    If the 'next' in-kernel return stack is shorter than 'prev',
-	 *    'next' could be tricked into speculating with a user-poisoned RSB
-	 *    entry.
-	 *
-	 *    The "user -> kernel" attack scenario is mitigated by SMEP and
-	 *    eIBRS.
-	 *
-	 *    The "user -> user" scenario, also known as SpectreBHB, requires
-	 *    RSB clearing.
-	 *
-	 * So to mitigate all cases, unconditionally fill RSB on context
-	 * switches.
-	 *
-	 * FIXME: Is this pointless for retbleed-affected AMD?
-	 */
-	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
-	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
-
-	spectre_v2_determine_rsb_fill_type_at_vmexit(mode);
+	spectre_v2_select_rsb_mitigation(mode);
 
 	/*
 	 * Retpoline protects the kernel, but doesn't protect firmware.  IBRS
@@ -2646,10 +2756,10 @@ static void __init srso_select_mitigation(void)
 
 			if (boot_cpu_data.x86 == 0x19) {
 				setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS);
-				x86_return_thunk = srso_alias_return_thunk;
+				set_return_thunk(srso_alias_return_thunk);
 			} else {
 				setup_force_cpu_cap(X86_FEATURE_SRSO);
-				x86_return_thunk = srso_return_thunk;
+				set_return_thunk(srso_return_thunk);
 			}
 			if (has_microcode)
 				srso_mitigation = SRSO_MITIGATION_SAFE_RET;
@@ -2676,7 +2786,7 @@ static void __init srso_select_mitigation(void)
 				setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
 
 				/*
-				 * There is no need for RSB filling: entry_ibpb() ensures
+				 * There is no need for RSB filling: write_ibpb() ensures
 				 * all predictions, including the RSB, are invalidated,
 				 * regardless of IBPB implementation.
 				 */
@@ -2701,7 +2811,7 @@ ibpb_on_vmexit:
 				srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
 
 				/*
-				 * There is no need for RSB filling: entry_ibpb() ensures
+				 * There is no need for RSB filling: write_ibpb() ensures
 				 * all predictions, including the RSB, are invalidated,
 				 * regardless of IBPB implementation.
 				 */
@@ -2839,6 +2949,11 @@ static ssize_t rfds_show_state(char *buf)
 	return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]);
 }
 
+static ssize_t its_show_state(char *buf)
+{
+	return sysfs_emit(buf, "%s\n", its_strings[its_mitigation]);
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
@@ -3021,6 +3136,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_RFDS:
 		return rfds_show_state(buf);
 
+	case X86_BUG_ITS:
+		return its_show_state(buf);
+
 	default:
 		break;
 	}
@@ -3100,6 +3218,11 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_RFDS);
 }
+
+ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_ITS);
+}
 #endif
 
 void __warn_thunk(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 12126adbc3a9..0ff057ff11ce 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1227,6 +1227,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define GDS		BIT(6)
 /* CPU is affected by Register File Data Sampling */
 #define RFDS		BIT(7)
+/* CPU is affected by Indirect Target Selection */
+#define ITS		BIT(8)
+/* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */
+#define ITS_NATIVE_ONLY	BIT(9)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE,	     X86_STEP_MAX,	SRBDS),
@@ -1238,22 +1242,25 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPS(INTEL_BROADWELL_G,	     X86_STEP_MAX,	SRBDS),
 	VULNBL_INTEL_STEPS(INTEL_BROADWELL_X,	     X86_STEP_MAX,	MMIO),
 	VULNBL_INTEL_STEPS(INTEL_BROADWELL,	     X86_STEP_MAX,	SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS),
+	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,		      0x5,	MMIO | RETBLEED | GDS),
+	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | ITS),
 	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS),
 	VULNBL_INTEL_STEPS(INTEL_SKYLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_KABYLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L,		      0xb,	MMIO | RETBLEED | GDS | SRBDS),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS | ITS),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE,		      0xc,	MMIO | RETBLEED | GDS | SRBDS),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS | ITS),
 	VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L,	     X86_STEP_MAX,	RETBLEED),
-	VULNBL_INTEL_STEPS(INTEL_ICELAKE_L,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS),
-	VULNBL_INTEL_STEPS(INTEL_ICELAKE_D,	     X86_STEP_MAX,	MMIO | GDS),
-	VULNBL_INTEL_STEPS(INTEL_ICELAKE_X,	     X86_STEP_MAX,	MMIO | GDS),
-	VULNBL_INTEL_STEPS(INTEL_COMETLAKE,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS),
-	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,		      0x0,	MMIO | RETBLEED),
-	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS),
-	VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L,	     X86_STEP_MAX,	GDS),
-	VULNBL_INTEL_STEPS(INTEL_TIGERLAKE,	     X86_STEP_MAX,	GDS),
+	VULNBL_INTEL_STEPS(INTEL_ICELAKE_L,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
+	VULNBL_INTEL_STEPS(INTEL_ICELAKE_D,	     X86_STEP_MAX,	MMIO | GDS | ITS | ITS_NATIVE_ONLY),
+	VULNBL_INTEL_STEPS(INTEL_ICELAKE_X,	     X86_STEP_MAX,	MMIO | GDS | ITS | ITS_NATIVE_ONLY),
+	VULNBL_INTEL_STEPS(INTEL_COMETLAKE,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
+	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,		      0x0,	MMIO | RETBLEED | ITS),
+	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
+	VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L,	     X86_STEP_MAX,	GDS | ITS | ITS_NATIVE_ONLY),
+	VULNBL_INTEL_STEPS(INTEL_TIGERLAKE,	     X86_STEP_MAX,	GDS | ITS | ITS_NATIVE_ONLY),
 	VULNBL_INTEL_STEPS(INTEL_LAKEFIELD,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED),
-	VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS),
+	VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
 	VULNBL_INTEL_TYPE(INTEL_ALDERLAKE,		     ATOM,	RFDS),
 	VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L,	     X86_STEP_MAX,	RFDS),
 	VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE,		     ATOM,	RFDS),
@@ -1318,6 +1325,32 @@ static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr)
 	return cpu_matches(cpu_vuln_blacklist, RFDS);
 }
 
+static bool __init vulnerable_to_its(u64 x86_arch_cap_msr)
+{
+	/* The "immunity" bit trumps everything else: */
+	if (x86_arch_cap_msr & ARCH_CAP_ITS_NO)
+		return false;
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return false;
+
+	/* None of the affected CPUs have BHI_CTRL */
+	if (boot_cpu_has(X86_FEATURE_BHI_CTRL))
+		return false;
+
+	/*
+	 * If a VMM did not expose ITS_NO, assume that a guest could
+	 * be running on a vulnerable hardware or may migrate to such
+	 * hardware.
+	 */
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return true;
+
+	if (cpu_matches(cpu_vuln_blacklist, ITS))
+		return true;
+
+	return false;
+}
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 x86_arch_cap_msr = x86_read_arch_cap_msr();
@@ -1439,9 +1472,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (vulnerable_to_rfds(x86_arch_cap_msr))
 		setup_force_cpu_bug(X86_BUG_RFDS);
 
-	/* When virtualized, eIBRS could be hidden, assume vulnerable */
-	if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) &&
-	    !cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
+	/*
+	 * Intel parts with eIBRS are vulnerable to BHI attacks. Parts with
+	 * BHI_NO still need to use the BHI mitigation to prevent Intra-mode
+	 * attacks.  When virtualized, eIBRS could be hidden, assume vulnerable.
+	 */
+	if (!cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
 	    (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) ||
 	     boot_cpu_has(X86_FEATURE_HYPERVISOR)))
 		setup_force_cpu_bug(X86_BUG_BHI);
@@ -1449,6 +1485,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET))
 		setup_force_cpu_bug(X86_BUG_IBPB_NO_RET);
 
+	if (vulnerable_to_its(x86_arch_cap_msr)) {
+		setup_force_cpu_bug(X86_BUG_ITS);
+		if (cpu_matches(cpu_vuln_blacklist, ITS_NATIVE_ONLY))
+			setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY);
+	}
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index b61028cf5c8a..96cb992d50ef 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -199,6 +199,12 @@ static bool need_sha_check(u32 cur_rev)
 	case 0xa70c0: return cur_rev <= 0xa70C009; break;
 	case 0xaa001: return cur_rev <= 0xaa00116; break;
 	case 0xaa002: return cur_rev <= 0xaa00218; break;
+	case 0xb0021: return cur_rev <= 0xb002146; break;
+	case 0xb1010: return cur_rev <= 0xb101046; break;
+	case 0xb2040: return cur_rev <= 0xb204031; break;
+	case 0xb4040: return cur_rev <= 0xb404031; break;
+	case 0xb6000: return cur_rev <= 0xb600031; break;
+	case 0xb7000: return cur_rev <= 0xb700031; break;
 	default: break;
 	}
 
@@ -214,8 +220,7 @@ static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsi
 	struct sha256_state s;
 	int i;
 
-	if (x86_family(bsp_cpuid_1_eax) < 0x17 ||
-	    x86_family(bsp_cpuid_1_eax) > 0x19)
+	if (x86_family(bsp_cpuid_1_eax) < 0x17)
 		return true;
 
 	if (!need_sha_check(cur_rev))
@@ -1093,15 +1098,17 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
 
 static int __init save_microcode_in_initrd(void)
 {
-	unsigned int cpuid_1_eax = native_cpuid_eax(1);
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 	struct cont_desc desc = { 0 };
+	unsigned int cpuid_1_eax;
 	enum ucode_state ret;
 	struct cpio_data cp;
 
-	if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+	if (microcode_loader_disabled() || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
 		return 0;
 
+	cpuid_1_eax = native_cpuid_eax(1);
+
 	if (!find_blobs_in_containers(&cp))
 		return -EINVAL;
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index b3658d11e7b6..079f046ee26d 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -41,8 +41,8 @@
 
 #include "internal.h"
 
-static struct microcode_ops	*microcode_ops;
-bool dis_ucode_ldr = true;
+static struct microcode_ops *microcode_ops;
+static bool dis_ucode_ldr = false;
 
 bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV);
 module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
@@ -84,6 +84,9 @@ static bool amd_check_current_patch_level(void)
 	u32 lvl, dummy, i;
 	u32 *levels;
 
+	if (x86_cpuid_vendor() != X86_VENDOR_AMD)
+		return false;
+
 	native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
 
 	levels = final_levels;
@@ -95,27 +98,29 @@ static bool amd_check_current_patch_level(void)
 	return false;
 }
 
-static bool __init check_loader_disabled_bsp(void)
+bool __init microcode_loader_disabled(void)
 {
-	static const char *__dis_opt_str = "dis_ucode_ldr";
-	const char *cmdline = boot_command_line;
-	const char *option  = __dis_opt_str;
+	if (dis_ucode_ldr)
+		return true;
 
 	/*
-	 * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
-	 * completely accurate as xen pv guests don't see that CPUID bit set but
-	 * that's good enough as they don't land on the BSP path anyway.
+	 * Disable when:
+	 *
+	 * 1) The CPU does not support CPUID.
+	 *
+	 * 2) Bit 31 in CPUID[1]:ECX is clear
+	 *    The bit is reserved for hypervisor use. This is still not
+	 *    completely accurate as XEN PV guests don't see that CPUID bit
+	 *    set, but that's good enough as they don't land on the BSP
+	 *    path anyway.
+	 *
+	 * 3) Certain AMD patch levels are not allowed to be
+	 *    overwritten.
 	 */
-	if (native_cpuid_ecx(1) & BIT(31))
-		return true;
-
-	if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
-		if (amd_check_current_patch_level())
-			return true;
-	}
-
-	if (cmdline_find_option_bool(cmdline, option) <= 0)
-		dis_ucode_ldr = false;
+	if (!have_cpuid_p() ||
+	    native_cpuid_ecx(1) & BIT(31) ||
+	    amd_check_current_patch_level())
+		dis_ucode_ldr = true;
 
 	return dis_ucode_ldr;
 }
@@ -125,7 +130,10 @@ void __init load_ucode_bsp(void)
 	unsigned int cpuid_1_eax;
 	bool intel = true;
 
-	if (!have_cpuid_p())
+	if (cmdline_find_option_bool(boot_command_line, "dis_ucode_ldr") > 0)
+		dis_ucode_ldr = true;
+
+	if (microcode_loader_disabled())
 		return;
 
 	cpuid_1_eax = native_cpuid_eax(1);
@@ -146,9 +154,6 @@ void __init load_ucode_bsp(void)
 		return;
 	}
 
-	if (check_loader_disabled_bsp())
-		return;
-
 	if (intel)
 		load_ucode_intel_bsp(&early_data);
 	else
@@ -159,6 +164,11 @@ void load_ucode_ap(void)
 {
 	unsigned int cpuid_1_eax;
 
+	/*
+	 * Can't use microcode_loader_disabled() here - .init section
+	 * hell. It doesn't have to either - the BSP variant must've
+	 * parsed cmdline already anyway.
+	 */
 	if (dis_ucode_ldr)
 		return;
 
@@ -810,7 +820,7 @@ static int __init microcode_init(void)
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 	int error;
 
-	if (dis_ucode_ldr)
+	if (microcode_loader_disabled())
 		return -EINVAL;
 
 	if (c->x86_vendor == X86_VENDOR_INTEL)
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 819199bc0119..2a397da43923 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -389,7 +389,7 @@ static int __init save_builtin_microcode(void)
 	if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED)
 		return 0;
 
-	if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	if (microcode_loader_disabled() || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return 0;
 
 	uci.mc = get_microcode_blob(&uci, true);
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index 5df621752fef..50a9702ae4e2 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -94,7 +94,6 @@ static inline unsigned int x86_cpuid_family(void)
 	return x86_family(eax);
 }
 
-extern bool dis_ucode_ldr;
 extern bool force_minrev;
 
 #ifdef CONFIG_CPU_SUP_AMD
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 93ec829015f1..cc4a54145c83 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -3553,6 +3553,22 @@ static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp)
 		free_rmid(rgrp->closid, rgrp->mon.rmid);
 }
 
+/*
+ * We allow creating mon groups only with in a directory called "mon_groups"
+ * which is present in every ctrl_mon group. Check if this is a valid
+ * "mon_groups" directory.
+ *
+ * 1. The directory should be named "mon_groups".
+ * 2. The mon group itself should "not" be named "mon_groups".
+ *   This makes sure "mon_groups" directory always has a ctrl_mon group
+ *   as parent.
+ */
+static bool is_mon_groups(struct kernfs_node *kn, const char *name)
+{
+	return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
+		strcmp(name, "mon_groups"));
+}
+
 static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 			     const char *name, umode_t mode,
 			     enum rdt_group_type rtype, struct rdtgroup **r)
@@ -3568,6 +3584,15 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 		goto out_unlock;
 	}
 
+	/*
+	 * Check that the parent directory for a monitor group is a "mon_groups"
+	 * directory.
+	 */
+	if (rtype == RDTMON_GROUP && !is_mon_groups(parent_kn, name)) {
+		ret = -EPERM;
+		goto out_unlock;
+	}
+
 	if (rtype == RDTMON_GROUP &&
 	    (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
 	     prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
@@ -3751,22 +3776,6 @@ out_unlock:
 	return ret;
 }
 
-/*
- * We allow creating mon groups only with in a directory called "mon_groups"
- * which is present in every ctrl_mon group. Check if this is a valid
- * "mon_groups" directory.
- *
- * 1. The directory should be named "mon_groups".
- * 2. The mon group itself should "not" be named "mon_groups".
- *   This makes sure "mon_groups" directory always has a ctrl_mon group
- *   as parent.
- */
-static bool is_mon_groups(struct kernfs_node *kn, const char *name)
-{
-	return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
-		strcmp(name, "mon_groups"));
-}
-
 static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 			  umode_t mode)
 {
@@ -3782,11 +3791,8 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 	if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn)
 		return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode);
 
-	/*
-	 * If RDT monitoring is supported and the parent directory is a valid
-	 * "mon_groups" directory, add a monitoring subdirectory.
-	 */
-	if (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name))
+	/* Else, attempt to add a monitoring subdirectory. */
+	if (resctrl_arch_mon_capable())
 		return rdtgroup_mkdir_mon(parent_kn, name, mode);
 
 	return -EPERM;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 57120f0749cc..9920122018a0 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -753,22 +753,21 @@ void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len)
 void __init e820__register_nosave_regions(unsigned long limit_pfn)
 {
 	int i;
-	unsigned long pfn = 0;
+	u64 last_addr = 0;
 
 	for (i = 0; i < e820_table->nr_entries; i++) {
 		struct e820_entry *entry = &e820_table->entries[i];
 
-		if (pfn < PFN_UP(entry->addr))
-			register_nosave_region(pfn, PFN_UP(entry->addr));
-
-		pfn = PFN_DOWN(entry->addr + entry->size);
-
 		if (entry->type != E820_TYPE_RAM)
-			register_nosave_region(PFN_UP(entry->addr), pfn);
+			continue;
 
-		if (pfn >= limit_pfn)
-			break;
+		if (last_addr < entry->addr)
+			register_nosave_region(PFN_DOWN(last_addr), PFN_UP(entry->addr));
+
+		last_addr = entry->addr + entry->size;
 	}
+
+	register_nosave_region(PFN_DOWN(last_addr), limit_pfn);
 }
 
 #ifdef CONFIG_ACPI
@@ -1300,6 +1299,14 @@ void __init e820__memblock_setup(void)
 		memblock_add(entry->addr, entry->size);
 	}
 
+	/*
+	 * 32-bit systems are limited to 4BG of memory even with HIGHMEM and
+	 * to even less without it.
+	 * Discard memory after max_pfn - the actual limit detected at runtime.
+	 */
+	if (IS_ENABLED(CONFIG_X86_32))
+		memblock_remove(PFN_PHYS(max_pfn), -1);
+
 	/* Throw away partial pages: */
 	memblock_trim_memory(PAGE_SIZE);
 
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 611f27e3890c..3aad78bfcb26 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -389,10 +389,10 @@ static int __init setup_early_printk(char *buf)
 	keep = (strstr(buf, "keep") != NULL);
 
 	while (*buf != '\0') {
-		if (!strncmp(buf, "mmio", 4)) {
-			early_mmio_serial_init(buf + 4);
+		if (!strncmp(buf, "mmio32", 6)) {
+			buf += 6;
+			early_mmio_serial_init(buf);
 			early_console_register(&early_serial_console, keep);
-			buf += 4;
 		}
 		if (!strncmp(buf, "serial", 6)) {
 			buf += 6;
@@ -407,9 +407,9 @@ static int __init setup_early_printk(char *buf)
 		}
 #ifdef CONFIG_PCI
 		if (!strncmp(buf, "pciserial", 9)) {
-			early_pci_serial_init(buf + 9);
+			buf += 9; /* Keep from match the above "pciserial" */
+			early_pci_serial_init(buf);
 			early_console_register(&early_serial_console, keep);
-			buf += 9; /* Keep from match the above "serial" */
 		}
 #endif
 		if (!strncmp(buf, "vga", 3) &&
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index cace6e8d7cc7..5eb1514af559 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -354,7 +354,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		goto fail;
 
 	ip = trampoline + size;
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+	if (cpu_wants_rethunk_at(ip))
 		__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
 	else
 		memcpy(ip, retq, sizeof(retq));
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index de001b2146ab..375f2d7f1762 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -145,10 +145,6 @@ void __init __no_stack_protector mk_early_pgtbl_32(void)
 	*ptr = (unsigned long)ptep + PAGE_OFFSET;
 
 #ifdef CONFIG_MICROCODE_INITRD32
-	/* Running on a hypervisor? */
-	if (native_cpuid_ecx(1) & BIT(31))
-		return;
-
 	params = (struct boot_params *)__pa_nodebug(&boot_params);
 	if (!params->hdr.ramdisk_size || !params->hdr.ramdisk_image)
 		return;
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 80e262bb627f..cb9852ad6098 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -46,7 +46,8 @@ bool __init pit_timer_init(void)
 		 * VMMs otherwise steal CPU time just to pointlessly waggle
 		 * the (masked) IRQ.
 		 */
-		clockevent_i8253_disable();
+		scoped_guard(irq)
+			clockevent_i8253_disable();
 		return false;
 	}
 	clockevent_i8253_init(true);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 80265162aeff..1f325304c4a8 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -42,7 +42,7 @@ static void load_segments(void)
 
 static void machine_kexec_free_page_tables(struct kimage *image)
 {
-	free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
+	free_pages((unsigned long)image->arch.pgd, pgd_allocation_order());
 	image->arch.pgd = NULL;
 #ifdef CONFIG_X86_PAE
 	free_page((unsigned long)image->arch.pmd0);
@@ -59,7 +59,7 @@ static void machine_kexec_free_page_tables(struct kimage *image)
 static int machine_kexec_alloc_page_tables(struct kimage *image)
 {
 	image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-						    PGD_ALLOCATION_ORDER);
+						    pgd_allocation_order());
 #ifdef CONFIG_X86_PAE
 	image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
 	image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index a7998f351701..ff07558b7ebc 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -266,6 +266,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 			ibt_endbr = s;
 	}
 
+	its_init_mod(me);
+
 	if (retpolines || cfi) {
 		void *rseg = NULL, *cseg = NULL;
 		unsigned int rsize = 0, csize = 0;
@@ -286,6 +288,9 @@ int module_finalize(const Elf_Ehdr *hdr,
 		void *rseg = (void *)retpolines->sh_addr;
 		apply_retpolines(rseg, rseg + retpolines->sh_size);
 	}
+
+	its_fini_mod(me);
+
 	if (returns) {
 		void *rseg = (void *)returns->sh_addr;
 		apply_returns(rseg, rseg + returns->sh_size);
@@ -326,4 +331,5 @@ int module_finalize(const Elf_Ehdr *hdr,
 void module_arch_cleanup(struct module *mod)
 {
 	alternatives_smp_module_del(mod);
+	its_free_mod(mod);
 }
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index a59c72e77645..c3d7ff44b29a 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -81,7 +81,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 		break;
 
 	case RET:
-		if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		if (cpu_wants_rethunk_at(insn))
 			code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk);
 		else
 			code = &retinsn;
@@ -90,7 +90,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 	case JCC:
 		if (!func) {
 			func = __static_call_return;
-			if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+			if (cpu_wants_rethunk())
 				func = x86_return_thunk;
 		}
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index ccdc45e5b759..cda5f8362e9d 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -466,10 +466,18 @@ SECTIONS
 }
 
 /*
- * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+ * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause
+ * this.  Let's assume that nobody will be running a COMPILE_TEST kernel and
+ * let's assert that fuller build coverage is more valuable than being able to
+ * run a COMPILE_TEST kernel.
+ */
+#ifndef CONFIG_COMPILE_TEST
+/*
+ * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility:
  */
 . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
 	   "kernel image bigger than KERNEL_IMAGE_SIZE");
+#endif
 
 /* needed for Clang - see arch/x86/entry/entry.S */
 PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
@@ -497,6 +505,16 @@ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
 		"SRSO function pair won't alias");
 #endif
 
+#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)
+. = ASSERT(__x86_indirect_its_thunk_rax & 0x20, "__x86_indirect_thunk_rax not in second half of cacheline");
+. = ASSERT(((__x86_indirect_its_thunk_rcx - __x86_indirect_its_thunk_rax) % 64) == 0, "Indirect thunks are not cacheline apart");
+. = ASSERT(__x86_indirect_its_thunk_array == __x86_indirect_its_thunk_rax, "Gap in ITS thunk array");
+#endif
+
+#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)
+. = ASSERT(its_return_thunk & 0x20, "its_return_thunk not in second half of cacheline");
+#endif
+
 #endif /* CONFIG_X86_64 */
 
 /*
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 050a0e229a4d..f2b36d32ef40 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -104,6 +104,9 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 
 static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
 {
+	if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
+		kvm_mmu_free_obsolete_roots(vcpu);
+
 	/*
 	 * Checking root.hpa is sufficient even when KVM has mirror root.
 	 * We can have either:
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 63bb77ee1bb1..8d1b632e33d2 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5974,6 +5974,7 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu)
 	__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu);
 	__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu);
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_free_obsolete_roots);
 
 static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
 				    int *bytes)
@@ -7669,9 +7670,30 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 }
 
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+				int level)
+{
+	return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+				 int level)
+{
+	lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+			       int level)
+{
+	lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
+}
+
 bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 					struct kvm_gfn_range *range)
 {
+	struct kvm_memory_slot *slot = range->slot;
+	int level;
+
 	/*
 	 * Zap SPTEs even if the slot can't be mapped PRIVATE.  KVM x86 only
 	 * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
@@ -7686,6 +7708,38 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 	if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
 		return false;
 
+	if (WARN_ON_ONCE(range->end <= range->start))
+		return false;
+
+	/*
+	 * If the head and tail pages of the range currently allow a hugepage,
+	 * i.e. reside fully in the slot and don't have mixed attributes, then
+	 * add each corresponding hugepage range to the ongoing invalidation,
+	 * e.g. to prevent KVM from creating a hugepage in response to a fault
+	 * for a gfn whose attributes aren't changing.  Note, only the range
+	 * of gfns whose attributes are being modified needs to be explicitly
+	 * unmapped, as that will unmap any existing hugepages.
+	 */
+	for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+		gfn_t start = gfn_round_for_level(range->start, level);
+		gfn_t end = gfn_round_for_level(range->end - 1, level);
+		gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
+
+		if ((start != range->start || start + nr_pages > range->end) &&
+		    start >= slot->base_gfn &&
+		    start + nr_pages <= slot->base_gfn + slot->npages &&
+		    !hugepage_test_mixed(slot, start, level))
+			kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages);
+
+		if (end == start)
+			continue;
+
+		if ((end + nr_pages) > range->end &&
+		    (end + nr_pages) <= (slot->base_gfn + slot->npages) &&
+		    !hugepage_test_mixed(slot, end, level))
+			kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages);
+	}
+
 	/* Unmap the old attribute page. */
 	if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE)
 		range->attr_filter = KVM_FILTER_SHARED;
@@ -7695,23 +7749,7 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 	return kvm_unmap_gfn_range(kvm, range);
 }
 
-static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
-				int level)
-{
-	return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
-}
-
-static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
-				 int level)
-{
-	lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
-}
 
-static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
-			       int level)
-{
-	lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
-}
 
 static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
 			       gfn_t gfn, int level, unsigned long attrs)
diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c
index 699e551ec93b..9864c057187d 100644
--- a/arch/x86/kvm/smm.c
+++ b/arch/x86/kvm/smm.c
@@ -131,6 +131,7 @@ void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
 
 	kvm_mmu_reset_context(vcpu);
 }
+EXPORT_SYMBOL_GPL(kvm_smm_changed);
 
 void process_smi(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 65fd245a9953..7338879d1c0c 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -796,12 +796,15 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 	struct amd_svm_iommu_ir *ir;
 	u64 entry;
 
+	if (WARN_ON_ONCE(!pi->ir_data))
+		return -EINVAL;
+
 	/**
 	 * In some cases, the existing irte is updated and re-set,
 	 * so we need to check here if it's already been * added
 	 * to the ir_list.
 	 */
-	if (pi->ir_data && (pi->prev_ga_tag != 0)) {
+	if (pi->prev_ga_tag) {
 		struct kvm *kvm = svm->vcpu.kvm;
 		u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
 		struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
@@ -820,7 +823,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 	 * Allocating new amd_iommu_pi_data, which will get
 	 * add to the per-vcpu ir_list.
 	 */
-	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT);
+	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT);
 	if (!ir) {
 		ret = -ENOMEM;
 		goto out;
@@ -896,10 +899,10 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
+	bool enable_remapped_mode = true;
 	int idx, ret = 0;
 
-	if (!kvm_arch_has_assigned_device(kvm) ||
-	    !irq_remapping_cap(IRQ_POSTING_CAP))
+	if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
 		return 0;
 
 	pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
@@ -933,6 +936,8 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 		    kvm_vcpu_apicv_active(&svm->vcpu)) {
 			struct amd_iommu_pi_data pi;
 
+			enable_remapped_mode = false;
+
 			/* Try to enable guest_mode in IRTE */
 			pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
 					    AVIC_HPA_MASK);
@@ -951,33 +956,6 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 			 */
 			if (!ret && pi.is_guest_mode)
 				svm_ir_list_add(svm, &pi);
-		} else {
-			/* Use legacy mode in IRTE */
-			struct amd_iommu_pi_data pi;
-
-			/**
-			 * Here, pi is used to:
-			 * - Tell IOMMU to use legacy mode for this interrupt.
-			 * - Retrieve ga_tag of prior interrupt remapping data.
-			 */
-			pi.prev_ga_tag = 0;
-			pi.is_guest_mode = false;
-			ret = irq_set_vcpu_affinity(host_irq, &pi);
-
-			/**
-			 * Check if the posted interrupt was previously
-			 * setup with the guest_mode by checking if the ga_tag
-			 * was cached. If so, we need to clean up the per-vcpu
-			 * ir_list.
-			 */
-			if (!ret && pi.prev_ga_tag) {
-				int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
-				struct kvm_vcpu *vcpu;
-
-				vcpu = kvm_get_vcpu_by_id(kvm, id);
-				if (vcpu)
-					svm_ir_list_del(to_svm(vcpu), &pi);
-			}
 		}
 
 		if (!ret && svm) {
@@ -993,6 +971,34 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 	}
 
 	ret = 0;
+	if (enable_remapped_mode) {
+		/* Use legacy mode in IRTE */
+		struct amd_iommu_pi_data pi;
+
+		/**
+		 * Here, pi is used to:
+		 * - Tell IOMMU to use legacy mode for this interrupt.
+		 * - Retrieve ga_tag of prior interrupt remapping data.
+		 */
+		pi.prev_ga_tag = 0;
+		pi.is_guest_mode = false;
+		ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+		/**
+		 * Check if the posted interrupt was previously
+		 * setup with the guest_mode by checking if the ga_tag
+		 * was cached. If so, we need to clean up the per-vcpu
+		 * ir_list.
+		 */
+		if (!ret && pi.prev_ga_tag) {
+			int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+			struct kvm_vcpu *vcpu;
+
+			vcpu = kvm_get_vcpu_by_id(kvm, id);
+			if (vcpu)
+				svm_ir_list_del(to_svm(vcpu), &pi);
+		}
+	}
 out:
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 	return ret;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0bc708ee2788..a7a7dc507336 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3173,9 +3173,14 @@ skip_vmsa_free:
 		kvfree(svm->sev_es.ghcb_sa);
 }
 
+static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
+{
+	return (((u64)control->exit_code_hi) << 32) | control->exit_code;
+}
+
 static void dump_ghcb(struct vcpu_svm *svm)
 {
-	struct ghcb *ghcb = svm->sev_es.ghcb;
+	struct vmcb_control_area *control = &svm->vmcb->control;
 	unsigned int nbits;
 
 	/* Re-use the dump_invalid_vmcb module parameter */
@@ -3184,18 +3189,24 @@ static void dump_ghcb(struct vcpu_svm *svm)
 		return;
 	}
 
-	nbits = sizeof(ghcb->save.valid_bitmap) * 8;
+	nbits = sizeof(svm->sev_es.valid_bitmap) * 8;
 
-	pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa);
+	/*
+	 * Print KVM's snapshot of the GHCB values that were (unsuccessfully)
+	 * used to handle the exit.  If the guest has since modified the GHCB
+	 * itself, dumping the raw GHCB won't help debug why KVM was unable to
+	 * handle the VMGEXIT that KVM observed.
+	 */
+	pr_err("GHCB (GPA=%016llx) snapshot:\n", svm->vmcb->control.ghcb_gpa);
 	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code",
-	       ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb));
+	       kvm_ghcb_get_sw_exit_code(control), kvm_ghcb_sw_exit_code_is_valid(svm));
 	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1",
-	       ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb));
+	       control->exit_info_1, kvm_ghcb_sw_exit_info_1_is_valid(svm));
 	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2",
-	       ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb));
+	       control->exit_info_2, kvm_ghcb_sw_exit_info_2_is_valid(svm));
 	pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch",
-	       ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb));
-	pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap);
+	       svm->sev_es.sw_scratch, kvm_ghcb_sw_scratch_is_valid(svm));
+	pr_err("%-20s%*pb\n", "valid_bitmap", nbits, svm->sev_es.valid_bitmap);
 }
 
 static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
@@ -3266,11 +3277,6 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
 }
 
-static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
-{
-	return (((u64)control->exit_code_hi) << 32) | control->exit_code;
-}
-
 static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d5d0c5c3300b..a89c271a1951 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -607,9 +607,6 @@ static void svm_disable_virtualization_cpu(void)
 	kvm_cpu_svm_disable();
 
 	amd_pmu_disable_virt();
-
-	if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
-		msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
 }
 
 static int svm_enable_virtualization_cpu(void)
@@ -687,9 +684,6 @@ static int svm_enable_virtualization_cpu(void)
 		rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi);
 	}
 
-	if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
-		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
-
 	return 0;
 }
 
@@ -1518,6 +1512,63 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
 	__free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
 }
 
+#ifdef CONFIG_CPU_MITIGATIONS
+static DEFINE_SPINLOCK(srso_lock);
+static atomic_t srso_nr_vms;
+
+static void svm_srso_clear_bp_spec_reduce(void *ign)
+{
+	struct svm_cpu_data *sd = this_cpu_ptr(&svm_data);
+
+	if (!sd->bp_spec_reduce_set)
+		return;
+
+	msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+	sd->bp_spec_reduce_set = false;
+}
+
+static void svm_srso_vm_destroy(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		return;
+
+	if (atomic_dec_return(&srso_nr_vms))
+		return;
+
+	guard(spinlock)(&srso_lock);
+
+	/*
+	 * Verify a new VM didn't come along, acquire the lock, and increment
+	 * the count before this task acquired the lock.
+	 */
+	if (atomic_read(&srso_nr_vms))
+		return;
+
+	on_each_cpu(svm_srso_clear_bp_spec_reduce, NULL, 1);
+}
+
+static void svm_srso_vm_init(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		return;
+
+	/*
+	 * Acquire the lock on 0 => 1 transitions to ensure a potential 1 => 0
+	 * transition, i.e. destroying the last VM, is fully complete, e.g. so
+	 * that a delayed IPI doesn't clear BP_SPEC_REDUCE after a vCPU runs.
+	 */
+	if (atomic_inc_not_zero(&srso_nr_vms))
+		return;
+
+	guard(spinlock)(&srso_lock);
+
+	atomic_inc(&srso_nr_vms);
+}
+#else
+static void svm_srso_vm_init(void) { }
+static void svm_srso_vm_destroy(void) { }
+#endif
+
 static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -1550,6 +1601,11 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	    (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
 		kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
 
+	if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE) &&
+	    !sd->bp_spec_reduce_set) {
+		sd->bp_spec_reduce_set = true;
+		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+	}
 	svm->guest_state_loaded = true;
 }
 
@@ -2231,6 +2287,10 @@ static int shutdown_interception(struct kvm_vcpu *vcpu)
 	 */
 	if (!sev_es_guest(vcpu->kvm)) {
 		clear_page(svm->vmcb);
+#ifdef CONFIG_KVM_SMM
+		if (is_smm(vcpu))
+			kvm_smm_changed(vcpu, false);
+#endif
 		kvm_vcpu_reset(vcpu, true);
 	}
 
@@ -5036,6 +5096,8 @@ static void svm_vm_destroy(struct kvm *kvm)
 {
 	avic_vm_destroy(kvm);
 	sev_vm_destroy(kvm);
+
+	svm_srso_vm_destroy();
 }
 
 static int svm_vm_init(struct kvm *kvm)
@@ -5061,6 +5123,7 @@ static int svm_vm_init(struct kvm *kvm)
 			return ret;
 	}
 
+	svm_srso_vm_init();
 	return 0;
 }
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index d4490eaed55d..f16b068c4228 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -335,6 +335,8 @@ struct svm_cpu_data {
 	u32 next_asid;
 	u32 min_asid;
 
+	bool bp_spec_reduce_set;
+
 	struct vmcb *save_area;
 	unsigned long save_area_pa;
 
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index ccda95e53f62..ba736cbb0587 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -11,6 +11,13 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
 
+#ifdef CREATE_TRACE_POINTS
+#define tracing_kvm_rip_read(vcpu) ({					\
+	typeof(vcpu) __vcpu = vcpu;					\
+	__vcpu->arch.guest_state_protected ? 0 : kvm_rip_read(__vcpu);	\
+	})
+#endif
+
 /*
  * Tracepoint for guest mode entry.
  */
@@ -28,7 +35,7 @@ TRACE_EVENT(kvm_entry,
 
 	TP_fast_assign(
 		__entry->vcpu_id        = vcpu->vcpu_id;
-		__entry->rip		= kvm_rip_read(vcpu);
+		__entry->rip		= tracing_kvm_rip_read(vcpu);
 		__entry->immediate_exit	= force_immediate_exit;
 
 		kvm_x86_call(get_entry_info)(vcpu, &__entry->intr_info,
@@ -319,7 +326,7 @@ TRACE_EVENT(name,							     \
 	),								     \
 									     \
 	TP_fast_assign(							     \
-		__entry->guest_rip	= kvm_rip_read(vcpu);		     \
+		__entry->guest_rip	= tracing_kvm_rip_read(vcpu);		     \
 		__entry->isa            = isa;				     \
 		__entry->vcpu_id        = vcpu->vcpu_id;		     \
 		__entry->requests       = READ_ONCE(vcpu->requests);	     \
@@ -423,7 +430,7 @@ TRACE_EVENT(kvm_page_fault,
 
 	TP_fast_assign(
 		__entry->vcpu_id	= vcpu->vcpu_id;
-		__entry->guest_rip	= kvm_rip_read(vcpu);
+		__entry->guest_rip	= tracing_kvm_rip_read(vcpu);
 		__entry->fault_address	= fault_address;
 		__entry->error_code	= error_code;
 	),
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 51116fe69a50..d70e5b90087d 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -297,6 +297,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
+	bool enable_remapped_mode = true;
 	struct kvm_lapic_irq irq;
 	struct kvm_vcpu *vcpu;
 	struct vcpu_data vcpu_info;
@@ -335,21 +336,8 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 
 		kvm_set_msi_irq(kvm, e, &irq);
 		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
-		    !kvm_irq_is_postable(&irq)) {
-			/*
-			 * Make sure the IRTE is in remapped mode if
-			 * we don't handle it in posted mode.
-			 */
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
-			if (ret < 0) {
-				printk(KERN_INFO
-				   "failed to back to remapped mode, irq: %u\n",
-				   host_irq);
-				goto out;
-			}
-
+		    !kvm_irq_is_postable(&irq))
 			continue;
-		}
 
 		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
 		vcpu_info.vector = irq.vector;
@@ -357,11 +345,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
 				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
 
-		if (set)
-			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
-		else
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
+		if (!set)
+			continue;
 
+		enable_remapped_mode = false;
+
+		ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
 		if (ret < 0) {
 			printk(KERN_INFO "%s: failed to update PI IRTE\n",
 					__func__);
@@ -369,6 +358,9 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 		}
 	}
 
+	if (enable_remapped_mode)
+		ret = irq_set_vcpu_affinity(host_irq, NULL);
+
 	ret = 0;
 out:
 	srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3712dde0bf9d..be7bb6d20129 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1584,7 +1584,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc);
 	 ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
 	 ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
 	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
-	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO)
+	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO)
 
 static u64 kvm_get_arch_capabilities(void)
 {
@@ -1618,6 +1618,8 @@ static u64 kvm_get_arch_capabilities(void)
 		data |= ARCH_CAP_MDS_NO;
 	if (!boot_cpu_has_bug(X86_BUG_RFDS))
 		data |= ARCH_CAP_RFDS_NO;
+	if (!boot_cpu_has_bug(X86_BUG_ITS))
+		data |= ARCH_CAP_ITS_NO;
 
 	if (!boot_cpu_has(X86_FEATURE_RTM)) {
 		/*
@@ -4597,7 +4599,7 @@ static bool kvm_is_vm_type_supported(unsigned long type)
 	return type < 32 && (kvm_caps.supported_vm_types & BIT(type));
 }
 
-static inline u32 kvm_sync_valid_fields(struct kvm *kvm)
+static inline u64 kvm_sync_valid_fields(struct kvm *kvm)
 {
 	return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS;
 }
@@ -11098,7 +11100,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	/*
 	 * Profile KVM exit RIPs:
 	 */
-	if (unlikely(prof_on == KVM_PROFILING)) {
+	if (unlikely(prof_on == KVM_PROFILING &&
+		     !vcpu->arch.guest_state_protected)) {
 		unsigned long rip = kvm_rip_read(vcpu);
 		profile_hit(KVM_PROFILING, (void *)rip);
 	}
@@ -11492,7 +11495,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_queued_exception *ex = &vcpu->arch.exception;
 	struct kvm_run *kvm_run = vcpu->run;
-	u32 sync_valid_fields;
+	u64 sync_valid_fields;
 	int r;
 
 	r = kvm_mmu_post_init_vm(vcpu->kvm);
@@ -13556,25 +13559,27 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
 
-bool kvm_arch_has_irq_bypass(void)
-{
-	return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
-}
-
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 				      struct irq_bypass_producer *prod)
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	struct kvm *kvm = irqfd->kvm;
 	int ret;
 
-	irqfd->producer = prod;
 	kvm_arch_start_assignment(irqfd->kvm);
+
+	spin_lock_irq(&kvm->irqfds.lock);
+	irqfd->producer = prod;
+
 	ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
 					   prod->irq, irqfd->gsi, 1);
 	if (ret)
 		kvm_arch_end_assignment(irqfd->kvm);
 
+	spin_unlock_irq(&kvm->irqfds.lock);
+
+
 	return ret;
 }
 
@@ -13584,9 +13589,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	int ret;
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	struct kvm *kvm = irqfd->kvm;
 
 	WARN_ON(irqfd->producer != prod);
-	irqfd->producer = NULL;
 
 	/*
 	 * When producer of consumer is unregistered, we change back to
@@ -13594,12 +13599,18 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	 * when the irq is masked/disabled or the consumer side (KVM
 	 * int this case doesn't want to receive the interrupts.
 	*/
+	spin_lock_irq(&kvm->irqfds.lock);
+	irqfd->producer = NULL;
+
 	ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
 					   prod->irq, irqfd->gsi, 0);
 	if (ret)
 		printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
 		       " fails: %d\n", irqfd->consumer.token, ret);
 
+	spin_unlock_irq(&kvm->irqfds.lock);
+
+
 	kvm_arch_end_assignment(irqfd->kvm);
 }
 
@@ -13612,7 +13623,8 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
 bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
 				  struct kvm_kernel_irq_routing_entry *new)
 {
-	if (new->type != KVM_IRQ_ROUTING_MSI)
+	if (old->type != KVM_IRQ_ROUTING_MSI ||
+	    new->type != KVM_IRQ_ROUTING_MSI)
 		return true;
 
 	return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index a26c43abd47d..39374949daa2 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -367,6 +367,54 @@ SYM_FUNC_END(call_depth_return_thunk)
 
 #endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
 
+#ifdef CONFIG_MITIGATION_ITS
+
+.macro ITS_THUNK reg
+
+/*
+ * If CFI paranoid is used then the ITS thunk starts with opcodes (0xea; jne 1b)
+ * that complete the fineibt_paranoid caller sequence.
+ */
+1:	.byte 0xea
+SYM_INNER_LABEL(__x86_indirect_paranoid_thunk_\reg, SYM_L_GLOBAL)
+	UNWIND_HINT_UNDEFINED
+	ANNOTATE_NOENDBR
+	jne 1b
+SYM_INNER_LABEL(__x86_indirect_its_thunk_\reg, SYM_L_GLOBAL)
+	UNWIND_HINT_UNDEFINED
+	ANNOTATE_NOENDBR
+	ANNOTATE_RETPOLINE_SAFE
+	jmp *%\reg
+	int3
+	.align 32, 0xcc		/* fill to the end of the line */
+	.skip  32 - (__x86_indirect_its_thunk_\reg - 1b), 0xcc /* skip to the next upper half */
+.endm
+
+/* ITS mitigation requires thunks be aligned to upper half of cacheline */
+.align 64, 0xcc
+.skip 29, 0xcc
+
+#define GEN(reg) ITS_THUNK reg
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+	.align 64, 0xcc
+SYM_FUNC_ALIAS(__x86_indirect_its_thunk_array, __x86_indirect_its_thunk_rax)
+SYM_CODE_END(__x86_indirect_its_thunk_array)
+
+.align 64, 0xcc
+.skip 32, 0xcc
+SYM_CODE_START(its_return_thunk)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+SYM_CODE_END(its_return_thunk)
+EXPORT_SYMBOL(its_return_thunk)
+
+#endif /* CONFIG_MITIGATION_ITS */
+
 /*
  * This function name is magical and is used by -mfunction-return=thunk-extern
  * for the compiler to generate JMPs to it.
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index caedb3ef6688..f5dd84eb55dc 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -996,8 +996,8 @@ AVXcode: 4
 83: Grp1 Ev,Ib (1A),(es)
 # CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
 #			     CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
 88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
 8f: POP2 Bq,Rq (000),(11B),(ev)
 a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index ad662cc4605c..bb8d99e717b9 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -30,6 +30,7 @@
 #include <linux/initrd.h>
 #include <linux/cpumask.h>
 #include <linux/gfp.h>
+#include <linux/execmem.h>
 
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
@@ -565,7 +566,7 @@ static void __init lowmem_pfn_init(void)
 	"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"
 
 #define MSG_HIGHMEM_TRIMMED \
-	"Warning: only 4GB will be used. Support for for CONFIG_HIGHMEM64G was removed!\n"
+	"Warning: only 4GB will be used. Support for CONFIG_HIGHMEM64G was removed!\n"
 /*
  * We have more RAM than fits into lowmem - we try to put it into
  * highmem, also taking the highmem=x boot parameter into account:
@@ -755,6 +756,8 @@ void mark_rodata_ro(void)
 	pr_info("Write protecting kernel text and read-only data: %luk\n",
 		size >> 10);
 
+	execmem_cache_make_ro();
+
 	kernel_set_to_readonly = 1;
 
 #ifdef CONFIG_CPA_DEBUG
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 7c4f6f591f2b..949a447f75ec 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -34,6 +34,7 @@
 #include <linux/gfp.h>
 #include <linux/kcore.h>
 #include <linux/bootmem_info.h>
+#include <linux/execmem.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
@@ -1391,6 +1392,8 @@ void mark_rodata_ro(void)
 	       (end - start) >> 10);
 	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
 
+	execmem_cache_make_ro();
+
 	kernel_set_to_readonly = 1;
 
 	/*
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index a05fcddfc811..f7ae44d3dd9e 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -360,7 +360,7 @@ static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
 	 * We allocate one page for pgd.
 	 */
 	if (!SHARED_KERNEL_PMD)
-		return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+		return __pgd_alloc(mm, pgd_allocation_order());
 
 	/*
 	 * Now PAE kernel is not running as a Xen domain. We can allocate
@@ -380,7 +380,7 @@ static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
 {
-	return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+	return __pgd_alloc(mm, pgd_allocation_order());
 }
 
 static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index e459d97ef397..b6d6750e4bd1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -667,9 +667,9 @@ static void cond_mitigation(struct task_struct *next)
 	prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_spec);
 
 	/*
-	 * Avoid user/user BTB poisoning by flushing the branch predictor
-	 * when switching between processes. This stops one process from
-	 * doing Spectre-v2 attacks on another.
+	 * Avoid user->user BTB/RSB poisoning by flushing them when switching
+	 * between processes. This stops one process from doing Spectre-v2
+	 * attacks on another.
 	 *
 	 * Both, the conditional and the always IBPB mode use the mm
 	 * pointer to avoid the IBPB when switching between tasks of the
@@ -899,8 +899,9 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		cond_mitigation(tsk);
 
 		/*
-		 * Let nmi_uaccess_okay() and finish_asid_transition()
-		 * know that CR3 is changing.
+		 * Indicate that CR3 is about to change. nmi_uaccess_okay()
+		 * and others are sensitive to the window where mm_cpumask(),
+		 * CR3 and cpu_tlbstate.loaded_mm are not all in sync.
 		 */
 		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
 		barrier();
@@ -1204,8 +1205,16 @@ done:
 
 static bool should_flush_tlb(int cpu, void *data)
 {
+	struct mm_struct *loaded_mm = per_cpu(cpu_tlbstate.loaded_mm, cpu);
 	struct flush_tlb_info *info = data;
 
+	/*
+	 * Order the 'loaded_mm' and 'is_lazy' against their
+	 * write ordering in switch_mm_irqs_off(). Ensure
+	 * 'is_lazy' is at least as new as 'loaded_mm'.
+	 */
+	smp_rmb();
+
 	/* Lazy TLB will get flushed at the next context switch. */
 	if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
 		return false;
@@ -1214,8 +1223,15 @@ static bool should_flush_tlb(int cpu, void *data)
 	if (!info->mm)
 		return true;
 
+	/*
+	 * While switching, the remote CPU could have state from
+	 * either the prev or next mm. Assume the worst and flush.
+	 */
+	if (loaded_mm == LOADED_MM_SWITCHING)
+		return true;
+
 	/* The target mm is loaded, and the CPU is not lazy. */
-	if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm)
+	if (loaded_mm == info->mm)
 		return true;
 
 	/* In cpumask, but not the loaded mm? Periodically remove by flushing. */
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 9e5fe2ba858f..ea4dd5b393aa 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -41,6 +41,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 #define EMIT2(b1, b2)		EMIT((b1) + ((b2) << 8), 2)
 #define EMIT3(b1, b2, b3)	EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
 #define EMIT4(b1, b2, b3, b4)   EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+#define EMIT5(b1, b2, b3, b4, b5) \
+	do { EMIT1(b1); EMIT4(b2, b3, b4, b5); } while (0)
 
 #define EMIT1_off32(b1, off) \
 	do { EMIT1(b1); EMIT(off, 4); } while (0)
@@ -661,7 +663,10 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
 {
 	u8 *prog = *pprog;
 
-	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
+	if (cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) {
+		OPTIMIZER_HIDE_VAR(reg);
+		emit_jump(&prog, its_static_thunk(reg), ip);
+	} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
 		EMIT_LFENCE();
 		EMIT2(0xFF, 0xE0 + reg);
 	} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
@@ -683,7 +688,7 @@ static void emit_return(u8 **pprog, u8 *ip)
 {
 	u8 *prog = *pprog;
 
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+	if (cpu_wants_rethunk()) {
 		emit_jump(&prog, x86_return_thunk, ip);
 	} else {
 		EMIT1(0xC3);		/* ret */
@@ -1502,6 +1507,48 @@ static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr)
 #define PRIV_STACK_GUARD_SZ    8
 #define PRIV_STACK_GUARD_VAL   0xEB9F12345678eb9fULL
 
+static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip,
+				    struct bpf_prog *bpf_prog)
+{
+	u8 *prog = *pprog;
+	u8 *func;
+
+	if (cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP)) {
+		/* The clearing sequence clobbers eax and ecx. */
+		EMIT1(0x50); /* push rax */
+		EMIT1(0x51); /* push rcx */
+		ip += 2;
+
+		func = (u8 *)clear_bhb_loop;
+		ip += x86_call_depth_emit_accounting(&prog, func, ip);
+
+		if (emit_call(&prog, func, ip))
+			return -EINVAL;
+		EMIT1(0x59); /* pop rcx */
+		EMIT1(0x58); /* pop rax */
+	}
+	/* Insert IBHF instruction */
+	if ((cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP) &&
+	     cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) ||
+	    cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_HW)) {
+		/*
+		 * Add an Indirect Branch History Fence (IBHF). IBHF acts as a
+		 * fence preventing branch history from before the fence from
+		 * affecting indirect branches after the fence. This is
+		 * specifically used in cBPF jitted code to prevent Intra-mode
+		 * BHI attacks. The IBHF instruction is designed to be a NOP on
+		 * hardware that doesn't need or support it.  The REP and REX.W
+		 * prefixes are required by the microcode, and they also ensure
+		 * that the NOP is unlikely to be used in existing code.
+		 *
+		 * IBHF is not a valid instruction in 32-bit mode.
+		 */
+		EMIT5(0xF3, 0x48, 0x0F, 0x1E, 0xF8); /* ibhf */
+	}
+	*pprog = prog;
+	return 0;
+}
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
 		  int oldproglen, struct jit_context *ctx, bool jmp_padding)
 {
@@ -2544,6 +2591,13 @@ emit_jmp:
 			seen_exit = true;
 			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
+			if (bpf_prog_was_classic(bpf_prog) &&
+			    !capable(CAP_SYS_ADMIN)) {
+				u8 *ip = image + addrs[i - 1];
+
+				if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog))
+					return -EINVAL;
+			}
 			if (bpf_prog->aux->exception_boundary) {
 				pop_callee_regs(&prog, all_callee_regs_used);
 				pop_r12(&prog);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac57259a432b..a4b4ebd41b8f 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -73,7 +73,7 @@ int __init efi_alloc_page_tables(void)
 	gfp_t gfp_mask;
 
 	gfp_mask = GFP_KERNEL | __GFP_ZERO;
-	efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
+	efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, pgd_allocation_order());
 	if (!efi_pgd)
 		goto fail;
 
@@ -96,7 +96,7 @@ free_p4d:
 	if (pgtable_l5_enabled())
 		free_page((unsigned long)pgd_page_vaddr(*pgd));
 free_pgd:
-	free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
+	free_pages((unsigned long)efi_pgd, pgd_allocation_order());
 fail:
 	return -ENOMEM;
 }
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 8c534c36adfa..66f066b8feda 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -26,7 +26,7 @@
 	 /* code below belongs to the image kernel */
 	.align PAGE_SIZE
 SYM_FUNC_START(restore_registers)
-	ANNOTATE_NOENDBR
+	ENDBR
 	/* go back to the original page tables */
 	movq    %r9, %cr3
 
@@ -120,7 +120,7 @@ SYM_FUNC_END(restore_image)
 
 	/* code below has been relocated to a safe page */
 SYM_FUNC_START(core_restore_code)
-	ANNOTATE_NOENDBR
+	ENDBR
 	/* switch to temporary page tables */
 	movq	%rax, %cr3
 	/* flush TLB */
diff --git a/arch/x86/um/shared/sysdep/faultinfo_32.h b/arch/x86/um/shared/sysdep/faultinfo_32.h
index ab5c8e47049c..9193a7790a71 100644
--- a/arch/x86/um/shared/sysdep/faultinfo_32.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_32.h
@@ -31,8 +31,8 @@ struct faultinfo {
 
 #define ___backtrack_faulted(_faulted)					\
 	asm volatile (							\
-		"mov $0, %0\n"						\
 		"movl $__get_kernel_nofault_faulted_%=,%1\n"		\
+		"mov $0, %0\n"						\
 		"jmp _end_%=\n"						\
 		"__get_kernel_nofault_faulted_%=:\n"			\
 		"mov $1, %0;"						\
diff --git a/arch/x86/um/shared/sysdep/faultinfo_64.h b/arch/x86/um/shared/sysdep/faultinfo_64.h
index 26fb4835d3e9..61e4ca1e0ab5 100644
--- a/arch/x86/um/shared/sysdep/faultinfo_64.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_64.h
@@ -31,8 +31,8 @@ struct faultinfo {
 
 #define ___backtrack_faulted(_faulted)					\
 	asm volatile (							\
-		"mov $0, %0\n"						\
 		"movq $__get_kernel_nofault_faulted_%=,%1\n"		\
+		"mov $0, %0\n"						\
 		"jmp _end_%=\n"						\
 		"__get_kernel_nofault_faulted_%=:\n"			\
 		"mov $1, %0;"						\
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 1b7710bd0d05..53282dc7d5ac 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -103,10 +103,6 @@ noinstr void *__xen_hypercall_setfunc(void)
 	void (*func)(void);
 
 	/*
-	 * Xen is supported only on CPUs with CPUID, so testing for
-	 * X86_FEATURE_CPUID is a test for early_cpu_init() having been
-	 * run.
-	 *
 	 * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty
 	 * dependency chain: it is being called via the xen_hypercall static
 	 * call when running as a PVH or HVM guest. Hypercalls need to be
@@ -118,8 +114,7 @@ noinstr void *__xen_hypercall_setfunc(void)
 	 */
 	instrumentation_begin();
 
-	if (!boot_cpu_has(X86_FEATURE_CPUID))
-		xen_get_vendor();
+	xen_get_vendor();
 
 	if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
 	     boot_cpu_data.x86_vendor == X86_VENDOR_HYGON))
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 10c660fae8b3..7237d56a9d3f 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -54,14 +54,20 @@ struct mc_debug_data {
 
 static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
 static struct mc_debug_data mc_debug_data_early __initdata;
-static DEFINE_PER_CPU(struct mc_debug_data *, mc_debug_data) =
-	&mc_debug_data_early;
 static struct mc_debug_data __percpu *mc_debug_data_ptr;
 DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
 
 static struct static_key mc_debug __ro_after_init;
 static bool mc_debug_enabled __initdata;
 
+static struct mc_debug_data * __ref get_mc_debug(void)
+{
+	if (!mc_debug_data_ptr)
+		return &mc_debug_data_early;
+
+	return this_cpu_ptr(mc_debug_data_ptr);
+}
+
 static int __init xen_parse_mc_debug(char *arg)
 {
 	mc_debug_enabled = true;
@@ -71,20 +77,16 @@ static int __init xen_parse_mc_debug(char *arg)
 }
 early_param("xen_mc_debug", xen_parse_mc_debug);
 
-void mc_percpu_init(unsigned int cpu)
-{
-	per_cpu(mc_debug_data, cpu) = per_cpu_ptr(mc_debug_data_ptr, cpu);
-}
-
 static int __init mc_debug_enable(void)
 {
 	unsigned long flags;
+	struct mc_debug_data __percpu *mcdb;
 
 	if (!mc_debug_enabled)
 		return 0;
 
-	mc_debug_data_ptr = alloc_percpu(struct mc_debug_data);
-	if (!mc_debug_data_ptr) {
+	mcdb = alloc_percpu(struct mc_debug_data);
+	if (!mcdb) {
 		pr_err("xen_mc_debug inactive\n");
 		static_key_slow_dec(&mc_debug);
 		return -ENOMEM;
@@ -93,7 +95,7 @@ static int __init mc_debug_enable(void)
 	/* Be careful when switching to percpu debug data. */
 	local_irq_save(flags);
 	xen_mc_flush();
-	mc_percpu_init(0);
+	mc_debug_data_ptr = mcdb;
 	local_irq_restore(flags);
 
 	pr_info("xen_mc_debug active\n");
@@ -155,7 +157,7 @@ void xen_mc_flush(void)
 	trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx);
 
 	if (static_key_false(&mc_debug)) {
-		mcdb = __this_cpu_read(mc_debug_data);
+		mcdb = get_mc_debug();
 		memcpy(mcdb->entries, b->entries,
 		       b->mcidx * sizeof(struct multicall_entry));
 	}
@@ -235,7 +237,7 @@ struct multicall_space __xen_mc_entry(size_t args)
 
 	ret.mc = &b->entries[b->mcidx];
 	if (static_key_false(&mc_debug)) {
-		struct mc_debug_data *mcdb = __this_cpu_read(mc_debug_data);
+		struct mc_debug_data *mcdb = get_mc_debug();
 
 		mcdb->caller[b->mcidx] = __builtin_return_address(0);
 		mcdb->argsz[b->mcidx] = args;
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 688ff59318ae..9bb8ff8bff30 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -305,7 +305,6 @@ static int xen_pv_kick_ap(unsigned int cpu, struct task_struct *idle)
 		return rc;
 
 	xen_pmu_init(cpu);
-	mc_percpu_init(cpu);
 
 	/*
 	 * Why is this a BUG? If the hypercall fails then everything can be
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 109af12f7647..461bb1526502 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -226,9 +226,7 @@ SYM_CODE_END(xen_early_idt_handler_array)
 	push %rax
 	mov  $__HYPERVISOR_iret, %eax
 	syscall		/* Do the IRET. */
-#ifdef CONFIG_MITIGATION_SLS
-	int3
-#endif
+	ud2		/* The SYSCALL should never return. */
 .endm
 
 SYM_CODE_START(xen_iret)
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 63c13a2ccf55..25e318ef27d6 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -261,9 +261,6 @@ void xen_mc_callback(void (*fn)(void *), void *data);
  */
 struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size);
 
-/* Do percpu data initialization for multicalls. */
-void mc_percpu_init(unsigned int cpu);
-
 extern bool is_xen_pmu;
 
 irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);
diff --git a/block/bdev.c b/block/bdev.c
index 4844d1e27b6f..889ec6e002d7 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -152,27 +152,65 @@ static void set_init_blocksize(struct block_device *bdev)
 				    get_order(bsize));
 }
 
-int set_blocksize(struct file *file, int size)
+/**
+ * bdev_validate_blocksize - check that this block size is acceptable
+ * @bdev:	blockdevice to check
+ * @block_size:	block size to check
+ *
+ * For block device users that do not use buffer heads or the block device
+ * page cache, make sure that this block size can be used with the device.
+ *
+ * Return: On success zero is returned, negative error code on failure.
+ */
+int bdev_validate_blocksize(struct block_device *bdev, int block_size)
 {
-	struct inode *inode = file->f_mapping->host;
-	struct block_device *bdev = I_BDEV(inode);
-
-	if (blk_validate_block_size(size))
+	if (blk_validate_block_size(block_size))
 		return -EINVAL;
 
 	/* Size cannot be smaller than the size supported by the device */
-	if (size < bdev_logical_block_size(bdev))
+	if (block_size < bdev_logical_block_size(bdev))
 		return -EINVAL;
 
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bdev_validate_blocksize);
+
+int set_blocksize(struct file *file, int size)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct block_device *bdev = I_BDEV(inode);
+	int ret;
+
+	ret = bdev_validate_blocksize(bdev, size);
+	if (ret)
+		return ret;
+
 	if (!file->private_data)
 		return -EINVAL;
 
 	/* Don't change the size if it is same as current */
 	if (inode->i_blkbits != blksize_bits(size)) {
+		/*
+		 * Flush and truncate the pagecache before we reconfigure the
+		 * mapping geometry because folio sizes are variable now.  If a
+		 * reader has already allocated a folio whose size is smaller
+		 * than the new min_order but invokes readahead after the new
+		 * min_order becomes visible, readahead will think there are
+		 * "zero" blocks per folio and crash.  Take the inode and
+		 * invalidation locks to avoid racing with
+		 * read/write/fallocate.
+		 */
+		inode_lock(inode);
+		filemap_invalidate_lock(inode->i_mapping);
+
 		sync_blockdev(bdev);
+		kill_bdev(bdev);
+
 		inode->i_blkbits = blksize_bits(size);
 		mapping_set_folio_min_order(inode->i_mapping, get_order(size));
 		kill_bdev(bdev);
+		filemap_invalidate_unlock(inode->i_mapping);
+		inode_unlock(inode);
 	}
 	return 0;
 }
@@ -777,13 +815,13 @@ static void blkdev_put_part(struct block_device *part)
 	blkdev_put_whole(whole);
 }
 
-struct block_device *blkdev_get_no_open(dev_t dev)
+struct block_device *blkdev_get_no_open(dev_t dev, bool autoload)
 {
 	struct block_device *bdev;
 	struct inode *inode;
 
 	inode = ilookup(blockdev_superblock, dev);
-	if (!inode && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) {
+	if (!inode && autoload && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) {
 		blk_request_module(dev);
 		inode = ilookup(blockdev_superblock, dev);
 		if (inode)
@@ -1005,7 +1043,7 @@ struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 	if (ret)
 		return ERR_PTR(ret);
 
-	bdev = blkdev_get_no_open(dev);
+	bdev = blkdev_get_no_open(dev, true);
 	if (!bdev)
 		return ERR_PTR(-ENXIO);
 
@@ -1272,21 +1310,17 @@ void sync_bdevs(bool wait)
 /*
  * Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices.
  */
-void bdev_statx(struct path *path, struct kstat *stat,
-		u32 request_mask)
+void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask)
 {
-	struct inode *backing_inode;
 	struct block_device *bdev;
 
-	backing_inode = d_backing_inode(path->dentry);
-
 	/*
-	 * Note that backing_inode is the inode of a block device node file,
-	 * not the block device's internal inode.  Therefore it is *not* valid
-	 * to use I_BDEV() here; the block device has to be looked up by i_rdev
+	 * Note that d_backing_inode() returns the block device node inode, not
+	 * the block device's internal inode.  Therefore it is *not* valid to
+	 * use I_BDEV() here; the block device has to be looked up by i_rdev
 	 * instead.
 	 */
-	bdev = blkdev_get_no_open(backing_inode->i_rdev);
+	bdev = blkdev_get_no_open(d_backing_inode(path->dentry)->i_rdev, false);
 	if (!bdev)
 		return;
 
diff --git a/block/bio-integrity-auto.c b/block/bio-integrity-auto.c
index e524c609be50..9c6657664792 100644
--- a/block/bio-integrity-auto.c
+++ b/block/bio-integrity-auto.c
@@ -9,6 +9,7 @@
  * not aware of PI.
  */
 #include <linux/blk-integrity.h>
+#include <linux/t10-pi.h>
 #include <linux/workqueue.h>
 #include "blk.h"
 
@@ -43,6 +44,29 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	bio_endio(bio);
 }
 
+#define BIP_CHECK_FLAGS (BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG)
+static bool bip_should_check(struct bio_integrity_payload *bip)
+{
+	return bip->bip_flags & BIP_CHECK_FLAGS;
+}
+
+static bool bi_offload_capable(struct blk_integrity *bi)
+{
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_CRC64:
+		return bi->tuple_size == sizeof(struct crc64_pi_tuple);
+	case BLK_INTEGRITY_CSUM_CRC:
+	case BLK_INTEGRITY_CSUM_IP:
+		return bi->tuple_size == sizeof(struct t10_pi_tuple);
+	default:
+		pr_warn_once("%s: unknown integrity checksum type:%d\n",
+			__func__, bi->csum_type);
+		fallthrough;
+	case BLK_INTEGRITY_CSUM_NONE:
+		return false;
+	}
+}
+
 /**
  * __bio_integrity_endio - Integrity I/O completion function
  * @bio:	Protected bio
@@ -54,12 +78,12 @@ static void bio_integrity_verify_fn(struct work_struct *work)
  */
 bool __bio_integrity_endio(struct bio *bio)
 {
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_integrity_data *bid =
 		container_of(bip, struct bio_integrity_data, bip);
 
-	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && bi->csum_type) {
+	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status &&
+	    bip_should_check(bip)) {
 		INIT_WORK(&bid->work, bio_integrity_verify_fn);
 		queue_work(kintegrityd_wq, &bid->work);
 		return false;
@@ -84,6 +108,7 @@ bool bio_integrity_prep(struct bio *bio)
 {
 	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	struct bio_integrity_data *bid;
+	bool set_flags = true;
 	gfp_t gfp = GFP_NOIO;
 	unsigned int len;
 	void *buf;
@@ -100,19 +125,24 @@ bool bio_integrity_prep(struct bio *bio)
 
 	switch (bio_op(bio)) {
 	case REQ_OP_READ:
-		if (bi->flags & BLK_INTEGRITY_NOVERIFY)
-			return true;
+		if (bi->flags & BLK_INTEGRITY_NOVERIFY) {
+			if (bi_offload_capable(bi))
+				return true;
+			set_flags = false;
+		}
 		break;
 	case REQ_OP_WRITE:
-		if (bi->flags & BLK_INTEGRITY_NOGENERATE)
-			return true;
-
 		/*
 		 * Zero the memory allocated to not leak uninitialized kernel
 		 * memory to disk for non-integrity metadata where nothing else
 		 * initializes the memory.
 		 */
-		if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
+		if (bi->flags & BLK_INTEGRITY_NOGENERATE) {
+			if (bi_offload_capable(bi))
+				return true;
+			set_flags = false;
+			gfp |= __GFP_ZERO;
+		} else if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
 			gfp |= __GFP_ZERO;
 		break;
 	default:
@@ -137,19 +167,21 @@ bool bio_integrity_prep(struct bio *bio)
 	bid->bip.bip_flags |= BIP_BLOCK_INTEGRITY;
 	bip_set_seed(&bid->bip, bio->bi_iter.bi_sector);
 
-	if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
-		bid->bip.bip_flags |= BIP_IP_CHECKSUM;
-	if (bi->csum_type)
-		bid->bip.bip_flags |= BIP_CHECK_GUARD;
-	if (bi->flags & BLK_INTEGRITY_REF_TAG)
-		bid->bip.bip_flags |= BIP_CHECK_REFTAG;
+	if (set_flags) {
+		if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
+			bid->bip.bip_flags |= BIP_IP_CHECKSUM;
+		if (bi->csum_type)
+			bid->bip.bip_flags |= BIP_CHECK_GUARD;
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			bid->bip.bip_flags |= BIP_CHECK_REFTAG;
+	}
 
 	if (bio_integrity_add_page(bio, virt_to_page(buf), len,
 			offset_in_page(buf)) < len)
 		goto err_end_io;
 
 	/* Auto-generate integrity metadata if this is a write */
-	if (bio_data_dir(bio) == WRITE)
+	if (bio_data_dir(bio) == WRITE && bip_should_check(&bid->bip))
 		blk_integrity_generate(bio);
 	else
 		bid->saved_bio_iter = bio->bi_iter;
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 608594a154a5..43ef6bd06c85 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -66,16 +66,12 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
 
-static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs,
-				     bool dirty)
+static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs)
 {
 	int i;
 
-	for (i = 0; i < nr_vecs; i++) {
-		if (dirty && !PageCompound(bv[i].bv_page))
-			set_page_dirty_lock(bv[i].bv_page);
+	for (i = 0; i < nr_vecs; i++)
 		unpin_user_page(bv[i].bv_page);
-	}
 }
 
 static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
@@ -91,7 +87,7 @@ static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
 	ret = copy_to_iter(bvec_virt(bounce_bvec), bytes, &orig_iter);
 	WARN_ON_ONCE(ret != bytes);
 
-	bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs, true);
+	bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs);
 }
 
 /**
@@ -111,8 +107,7 @@ void bio_integrity_unmap_user(struct bio *bio)
 		return;
 	}
 
-	bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt,
-			bio_data_dir(bio) == READ);
+	bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt);
 }
 
 /**
@@ -198,7 +193,7 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
 	}
 
 	if (write)
-		bio_integrity_unpin_bvec(bvec, nr_vecs, false);
+		bio_integrity_unpin_bvec(bvec, nr_vecs);
 	else
 		memcpy(&bip->bip_vec[1], bvec, nr_vecs * sizeof(*bvec));
 
@@ -319,7 +314,7 @@ int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter)
 	return 0;
 
 release_pages:
-	bio_integrity_unpin_bvec(bvec, nr_bvecs, false);
+	bio_integrity_unpin_bvec(bvec, nr_bvecs);
 free_bvec:
 	if (bvec != stack_vec)
 		kfree(bvec);
diff --git a/block/bio.c b/block/bio.c
index 4e6c85a33d74..4be592d37fb6 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -611,7 +611,7 @@ struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask)
 {
 	struct bio *bio;
 
-	if (nr_vecs > UIO_MAXIOV)
+	if (nr_vecs > BIO_MAX_INLINE_VECS)
 		return NULL;
 	return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask);
 }
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5905f277057b..ce93706555c5 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -797,7 +797,7 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx)
 		return -EINVAL;
 	input = skip_spaces(input);
 
-	bdev = blkdev_get_no_open(MKDEV(major, minor));
+	bdev = blkdev_get_no_open(MKDEV(major, minor), false);
 	if (!bdev)
 		return -ENODEV;
 	if (bdev_is_partition(bdev)) {
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 6b2dbe645d23..4817e7ca03f8 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -61,8 +61,14 @@ void blk_apply_bdi_limits(struct backing_dev_info *bdi,
 	/*
 	 * For read-ahead of large files to be effective, we need to read ahead
 	 * at least twice the optimal I/O size.
+	 *
+	 * There is no hardware limitation for the read-ahead size and the user
+	 * might have increased the read-ahead size through sysfs, so don't ever
+	 * decrease it.
 	 */
-	bdi->ra_pages = max(lim->io_opt * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+	bdi->ra_pages = max3(bdi->ra_pages,
+				lim->io_opt * 2 / PAGE_SIZE,
+				VM_READAHEAD_PAGES);
 	bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
 }
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index a2882751f0d2..1f9b45b0b9ee 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -909,6 +909,8 @@ out_unregister_ia_ranges:
 out_debugfs_remove:
 	blk_debugfs_remove(disk);
 	mutex_unlock(&q->sysfs_lock);
+	if (queue_is_mq(q))
+		blk_mq_sysfs_unregister(disk);
 out_put_queue_kobj:
 	kobject_put(&disk->queue_kobj);
 	return ret;
diff --git a/block/blk-throttle.h b/block/blk-throttle.h
index 7964cc041e06..f9f8666891ab 100644
--- a/block/blk-throttle.h
+++ b/block/blk-throttle.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef BLK_THROTTLE_H
 #define BLK_THROTTLE_H
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 0c77244a35c9..8f15d1aa6eb8 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -343,6 +343,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		op = REQ_OP_ZONE_RESET;
 
 		/* Invalidate the page cache, including dirty pages. */
+		inode_lock(bdev->bd_mapping->host);
 		filemap_invalidate_lock(bdev->bd_mapping);
 		ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
 		if (ret)
@@ -364,8 +365,10 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors);
 
 fail:
-	if (cmd == BLKRESETZONE)
+	if (cmd == BLKRESETZONE) {
 		filemap_invalidate_unlock(bdev->bd_mapping);
+		inode_unlock(bdev->bd_mapping->host);
+	}
 
 	return ret;
 }
diff --git a/block/blk.h b/block/blk.h
index 006e3be433d2..594eeba7b949 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -94,6 +94,9 @@ static inline void blk_wait_io(struct completion *done)
 		wait_for_completion_io(done);
 }
 
+struct block_device *blkdev_get_no_open(dev_t dev, bool autoload);
+void blkdev_put_no_open(struct block_device *bdev);
+
 #define BIO_INLINE_VECS 4
 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
 		gfp_t gfp_mask);
@@ -477,7 +480,8 @@ static inline void blk_zone_update_request_bio(struct request *rq,
 	 * the original BIO sector so that blk_zone_write_plug_bio_endio() can
 	 * lookup the zone write plug.
 	 */
-	if (req_op(rq) == REQ_OP_ZONE_APPEND || bio_zone_write_plugging(bio))
+	if (req_op(rq) == REQ_OP_ZONE_APPEND ||
+	    bio_flagged(bio, BIO_EMULATES_ZONE_APPEND))
 		bio->bi_iter.bi_sector = rq->__sector;
 }
 void blk_zone_write_plug_bio_endio(struct bio *bio);
diff --git a/block/fops.c b/block/fops.c
index be9f1dbea9ce..82b672d15ea4 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -642,7 +642,7 @@ static int blkdev_open(struct inode *inode, struct file *filp)
 	if (ret)
 		return ret;
 
-	bdev = blkdev_get_no_open(inode->i_rdev);
+	bdev = blkdev_get_no_open(inode->i_rdev, true);
 	if (!bdev)
 		return -ENXIO;
 
@@ -746,7 +746,14 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			ret = direct_write_fallback(iocb, from, ret,
 					blkdev_buffered_write(iocb, from));
 	} else {
+		/*
+		 * Take i_rwsem and invalidate_lock to avoid racing with
+		 * set_blocksize changing i_blkbits/folio order and punching
+		 * out the pagecache.
+		 */
+		inode_lock_shared(bd_inode);
 		ret = blkdev_buffered_write(iocb, from);
+		inode_unlock_shared(bd_inode);
 	}
 
 	if (ret > 0)
@@ -757,6 +764,7 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	struct inode *bd_inode = bdev_file_inode(iocb->ki_filp);
 	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	loff_t size = bdev_nr_bytes(bdev);
 	loff_t pos = iocb->ki_pos;
@@ -793,7 +801,13 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			goto reexpand;
 	}
 
+	/*
+	 * Take i_rwsem and invalidate_lock to avoid racing with set_blocksize
+	 * changing i_blkbits/folio order and punching out the pagecache.
+	 */
+	inode_lock_shared(bd_inode);
 	ret = filemap_read(iocb, to, ret);
+	inode_unlock_shared(bd_inode);
 
 reexpand:
 	if (unlikely(shorted))
@@ -836,6 +850,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	if ((start | len) & (bdev_logical_block_size(bdev) - 1))
 		return -EINVAL;
 
+	inode_lock(inode);
 	filemap_invalidate_lock(inode->i_mapping);
 
 	/*
@@ -868,6 +883,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 
  fail:
 	filemap_invalidate_unlock(inode->i_mapping);
+	inode_unlock(inode);
 	return error;
 }
 
diff --git a/block/ioctl.c b/block/ioctl.c
index faa40f383e27..e472cc1030c6 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -142,6 +142,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 	if (err)
 		return err;
 
+	inode_lock(bdev->bd_mapping->host);
 	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
 	if (err)
@@ -174,6 +175,7 @@ out_unplug:
 	blk_finish_plug(&plug);
 fail:
 	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
 	return err;
 }
 
@@ -199,12 +201,14 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode,
 	    end > bdev_nr_bytes(bdev))
 		return -EINVAL;
 
+	inode_lock(bdev->bd_mapping->host);
 	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, end - 1);
 	if (!err)
 		err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9,
 						GFP_KERNEL);
 	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
 	return err;
 }
 
@@ -236,6 +240,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages */
+	inode_lock(bdev->bd_mapping->host);
 	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, end);
 	if (err)
@@ -246,6 +251,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 
 fail:
 	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
 	return err;
 }
 
diff --git a/block/ioprio.c b/block/ioprio.c
index 73301a261429..f0ee2798539c 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -46,12 +46,8 @@ int ioprio_check_cap(int ioprio)
 			 */
 			if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE))
 				return -EPERM;
-			fallthrough;
-			/* rt has prio field too */
-		case IOPRIO_CLASS_BE:
-			if (level >= IOPRIO_NR_LEVELS)
-				return -EINVAL;
 			break;
+		case IOPRIO_CLASS_BE:
 		case IOPRIO_CLASS_IDLE:
 			break;
 		case IOPRIO_CLASS_NONE:
diff --git a/crypto/ahash.c b/crypto/ahash.c
index 9f57b925b116..2d9eec2b2b1c 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -315,16 +315,7 @@ EXPORT_SYMBOL_GPL(crypto_ahash_setkey);
 
 static bool ahash_request_hasvirt(struct ahash_request *req)
 {
-	struct ahash_request *r2;
-
-	if (ahash_request_isvirt(req))
-		return true;
-
-	list_for_each_entry(r2, &req->base.list, base.list)
-		if (ahash_request_isvirt(r2))
-			return true;
-
-	return false;
+	return ahash_request_isvirt(req);
 }
 
 static int ahash_reqchain_virt(struct ahash_save_req_state *state,
@@ -472,7 +463,6 @@ static int ahash_do_req_chain(struct ahash_request *req,
 	bool update = op == crypto_ahash_alg(tfm)->update;
 	struct ahash_save_req_state *state;
 	struct ahash_save_req_state state0;
-	struct ahash_request *r2;
 	u8 *page = NULL;
 	int err;
 
@@ -509,7 +499,6 @@ static int ahash_do_req_chain(struct ahash_request *req,
 	state->offset = 0;
 	state->nbytes = 0;
 	INIT_LIST_HEAD(&state->head);
-	list_splice_init(&req->base.list, &state->head);
 
 	if (page)
 		sg_init_one(&state->sg, page, PAGE_SIZE);
@@ -540,9 +529,6 @@ out_free_page:
 
 out_set_chain:
 	req->base.err = err;
-	list_for_each_entry(r2, &req->base.list, base.list)
-		r2->base.err = err;
-
 	return err;
 }
 
@@ -551,19 +537,10 @@ int crypto_ahash_init(struct ahash_request *req)
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 
 	if (likely(tfm->using_shash)) {
-		struct ahash_request *r2;
 		int err;
 
 		err = crypto_shash_init(prepare_shash_desc(req, tfm));
 		req->base.err = err;
-
-		list_for_each_entry(r2, &req->base.list, base.list) {
-			struct shash_desc *desc;
-
-			desc = prepare_shash_desc(r2, tfm);
-			r2->base.err = crypto_shash_init(desc);
-		}
-
 		return err;
 	}
 
@@ -620,19 +597,10 @@ int crypto_ahash_update(struct ahash_request *req)
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 
 	if (likely(tfm->using_shash)) {
-		struct ahash_request *r2;
 		int err;
 
 		err = shash_ahash_update(req, ahash_request_ctx(req));
 		req->base.err = err;
-
-		list_for_each_entry(r2, &req->base.list, base.list) {
-			struct shash_desc *desc;
-
-			desc = ahash_request_ctx(r2);
-			r2->base.err = shash_ahash_update(r2, desc);
-		}
-
 		return err;
 	}
 
@@ -645,19 +613,10 @@ int crypto_ahash_final(struct ahash_request *req)
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 
 	if (likely(tfm->using_shash)) {
-		struct ahash_request *r2;
 		int err;
 
 		err = crypto_shash_final(ahash_request_ctx(req), req->result);
 		req->base.err = err;
-
-		list_for_each_entry(r2, &req->base.list, base.list) {
-			struct shash_desc *desc;
-
-			desc = ahash_request_ctx(r2);
-			r2->base.err = crypto_shash_final(desc, r2->result);
-		}
-
 		return err;
 	}
 
@@ -670,19 +629,10 @@ int crypto_ahash_finup(struct ahash_request *req)
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 
 	if (likely(tfm->using_shash)) {
-		struct ahash_request *r2;
 		int err;
 
 		err = shash_ahash_finup(req, ahash_request_ctx(req));
 		req->base.err = err;
-
-		list_for_each_entry(r2, &req->base.list, base.list) {
-			struct shash_desc *desc;
-
-			desc = ahash_request_ctx(r2);
-			r2->base.err = shash_ahash_finup(r2, desc);
-		}
-
 		return err;
 	}
 
@@ -757,19 +707,10 @@ int crypto_ahash_digest(struct ahash_request *req)
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 
 	if (likely(tfm->using_shash)) {
-		struct ahash_request *r2;
 		int err;
 
 		err = shash_ahash_digest(req, prepare_shash_desc(req, tfm));
 		req->base.err = err;
-
-		list_for_each_entry(r2, &req->base.list, base.list) {
-			struct shash_desc *desc;
-
-			desc = prepare_shash_desc(r2, tfm);
-			r2->base.err = shash_ahash_digest(r2, desc);
-		}
-
 		return err;
 	}
 
@@ -1133,20 +1074,5 @@ int ahash_register_instance(struct crypto_template *tmpl,
 }
 EXPORT_SYMBOL_GPL(ahash_register_instance);
 
-void ahash_request_free(struct ahash_request *req)
-{
-	struct ahash_request *tmp;
-	struct ahash_request *r2;
-
-	if (unlikely(!req))
-		return;
-
-	list_for_each_entry_safe(r2, tmp, &req->base.list, base.list)
-		kfree_sensitive(r2);
-
-	kfree_sensitive(req);
-}
-EXPORT_SYMBOL_GPL(ahash_request_free);
-
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Asynchronous cryptographic hash type");
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 5498a87249d3..e3f1a4852737 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -265,10 +265,6 @@ static int hash_accept(struct socket *sock, struct socket *newsock,
 		goto out_free_state;
 
 	err = crypto_ahash_import(&ctx2->req, state);
-	if (err) {
-		sock_orphan(sk2);
-		sock_put(sk2);
-	}
 
 out_free_state:
 	kfree_sensitive(state);
diff --git a/crypto/krb5/rfc3961_simplified.c b/crypto/krb5/rfc3961_simplified.c
index 79180d28baa9..e49cbdec7c40 100644
--- a/crypto/krb5/rfc3961_simplified.c
+++ b/crypto/krb5/rfc3961_simplified.c
@@ -89,6 +89,7 @@ int crypto_shash_update_sg(struct shash_desc *desc, struct scatterlist *sg,
 
 	sg_miter_start(&miter, sg, sg_nents(sg),
 		       SG_MITER_FROM_SG | SG_MITER_LOCAL);
+	sg_miter_skip(&miter, offset);
 	for (i = 0; i < len; i += n) {
 		sg_miter_next(&miter);
 		n = min(miter.length, len - i);
diff --git a/crypto/scompress.c b/crypto/scompress.c
index d435d4b24469..ffeedcf20b0f 100644
--- a/crypto/scompress.c
+++ b/crypto/scompress.c
@@ -111,10 +111,14 @@ static void scomp_free_streams(struct scomp_alg *alg)
 	struct crypto_acomp_stream __percpu *stream = alg->stream;
 	int i;
 
+	alg->stream = NULL;
+	if (!stream)
+		return;
+
 	for_each_possible_cpu(i) {
 		struct crypto_acomp_stream *ps = per_cpu_ptr(stream, i);
 
-		if (!ps->ctx)
+		if (IS_ERR_OR_NULL(ps->ctx))
 			break;
 
 		alg->free_ctx(ps->ctx);
@@ -132,6 +136,8 @@ static int scomp_alloc_streams(struct scomp_alg *alg)
 	if (!stream)
 		return -ENOMEM;
 
+	alg->stream = stream;
+
 	for_each_possible_cpu(i) {
 		struct crypto_acomp_stream *ps = per_cpu_ptr(stream, i);
 
@@ -143,8 +149,6 @@ static int scomp_alloc_streams(struct scomp_alg *alg)
 
 		spin_lock_init(&ps->lock);
 	}
-
-	alg->stream = stream;
 	return 0;
 }
 
@@ -159,11 +163,10 @@ static int crypto_scomp_init_tfm(struct crypto_tfm *tfm)
 		if (ret)
 			goto unlock;
 	}
-	if (!scomp_scratch_users) {
+	if (!scomp_scratch_users++) {
 		ret = crypto_scomp_alloc_scratches();
 		if (ret)
-			goto unlock;
-		scomp_scratch_users++;
+			scomp_scratch_users--;
 	}
 unlock:
 	mutex_unlock(&scomp_lock);
@@ -211,8 +214,8 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
 			spage = nth_page(spage, soff / PAGE_SIZE);
 			soff = offset_in_page(soff);
 
-			n = slen / PAGE_SIZE;
-			n += (offset_in_page(slen) + soff - 1) / PAGE_SIZE;
+			n = (slen - 1) / PAGE_SIZE;
+			n += (offset_in_page(slen - 1) + soff) / PAGE_SIZE;
 			if (PageHighMem(nth_page(spage, n)) &&
 			    size_add(soff, slen) > PAGE_SIZE)
 				break;
@@ -239,9 +242,9 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
 			dpage = nth_page(dpage, doff / PAGE_SIZE);
 			doff = offset_in_page(doff);
 
-			n = dlen / PAGE_SIZE;
-			n += (offset_in_page(dlen) + doff - 1) / PAGE_SIZE;
-			if (PageHighMem(dpage + n) &&
+			n = (dlen - 1) / PAGE_SIZE;
+			n += (offset_in_page(dlen - 1) + doff) / PAGE_SIZE;
+			if (PageHighMem(nth_page(dpage, n)) &&
 			    size_add(doff, dlen) > PAGE_SIZE)
 				break;
 			dst = kmap_local_page(dpage) + doff;
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index abd609d4c8ef..82977ea25db3 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -58,9 +58,6 @@ module_param(fuzz_iterations, uint, 0644);
 MODULE_PARM_DESC(fuzz_iterations, "number of fuzz test iterations");
 #endif
 
-/* Multibuffer is unlimited.  Set arbitrary limit for testing. */
-#define MAX_MB_MSGS	16
-
 #ifdef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS
 
 /* a perfect nop */
@@ -3329,48 +3326,27 @@ static int test_acomp(struct crypto_acomp *tfm,
 		      int ctcount, int dtcount)
 {
 	const char *algo = crypto_tfm_alg_driver_name(crypto_acomp_tfm(tfm));
-	struct scatterlist *src = NULL, *dst = NULL;
-	struct acomp_req *reqs[MAX_MB_MSGS] = {};
-	char *decomp_out[MAX_MB_MSGS] = {};
-	char *output[MAX_MB_MSGS] = {};
-	struct crypto_wait wait;
-	struct acomp_req *req;
-	int ret = -ENOMEM;
 	unsigned int i;
+	char *output, *decomp_out;
+	int ret;
+	struct scatterlist src, dst;
+	struct acomp_req *req;
+	struct crypto_wait wait;
 
-	src = kmalloc_array(MAX_MB_MSGS, sizeof(*src), GFP_KERNEL);
-	if (!src)
-		goto out;
-	dst = kmalloc_array(MAX_MB_MSGS, sizeof(*dst), GFP_KERNEL);
-	if (!dst)
-		goto out;
-
-	for (i = 0; i < MAX_MB_MSGS; i++) {
-		reqs[i] = acomp_request_alloc(tfm);
-		if (!reqs[i])
-			goto out;
-
-		acomp_request_set_callback(reqs[i],
-					   CRYPTO_TFM_REQ_MAY_SLEEP |
-					   CRYPTO_TFM_REQ_MAY_BACKLOG,
-					   crypto_req_done, &wait);
-		if (i)
-			acomp_request_chain(reqs[i], reqs[0]);
-
-		output[i] = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
-		if (!output[i])
-			goto out;
+	output = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
+	if (!output)
+		return -ENOMEM;
 
-		decomp_out[i] = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
-		if (!decomp_out[i])
-			goto out;
+	decomp_out = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
+	if (!decomp_out) {
+		kfree(output);
+		return -ENOMEM;
 	}
 
 	for (i = 0; i < ctcount; i++) {
 		unsigned int dlen = COMP_BUF_SIZE;
 		int ilen = ctemplate[i].inlen;
 		void *input_vec;
-		int j;
 
 		input_vec = kmemdup(ctemplate[i].input, ilen, GFP_KERNEL);
 		if (!input_vec) {
@@ -3378,61 +3354,70 @@ static int test_acomp(struct crypto_acomp *tfm,
 			goto out;
 		}
 
+		memset(output, 0, dlen);
 		crypto_init_wait(&wait);
-		sg_init_one(src, input_vec, ilen);
+		sg_init_one(&src, input_vec, ilen);
+		sg_init_one(&dst, output, dlen);
 
-		for (j = 0; j < MAX_MB_MSGS; j++) {
-			sg_init_one(dst + j, output[j], dlen);
-			acomp_request_set_params(reqs[j], src, dst + j, ilen, dlen);
+		req = acomp_request_alloc(tfm);
+		if (!req) {
+			pr_err("alg: acomp: request alloc failed for %s\n",
+			       algo);
+			kfree(input_vec);
+			ret = -ENOMEM;
+			goto out;
 		}
 
-		req = reqs[0];
+		acomp_request_set_params(req, &src, &dst, ilen, dlen);
+		acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					   crypto_req_done, &wait);
+
 		ret = crypto_wait_req(crypto_acomp_compress(req), &wait);
 		if (ret) {
 			pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
 			       i + 1, algo, -ret);
 			kfree(input_vec);
+			acomp_request_free(req);
 			goto out;
 		}
 
 		ilen = req->dlen;
 		dlen = COMP_BUF_SIZE;
+		sg_init_one(&src, output, ilen);
+		sg_init_one(&dst, decomp_out, dlen);
 		crypto_init_wait(&wait);
-		for (j = 0; j < MAX_MB_MSGS; j++) {
-			sg_init_one(src + j, output[j], ilen);
-			sg_init_one(dst + j, decomp_out[j], dlen);
-			acomp_request_set_params(reqs[j], src + j, dst + j, ilen, dlen);
-		}
-
-		crypto_wait_req(crypto_acomp_decompress(req), &wait);
-		for (j = 0; j < MAX_MB_MSGS; j++) {
-			ret = reqs[j]->base.err;
-			if (ret) {
-				pr_err("alg: acomp: compression failed on test %d (%d) for %s: ret=%d\n",
-				       i + 1, j, algo, -ret);
-				kfree(input_vec);
-				goto out;
-			}
+		acomp_request_set_params(req, &src, &dst, ilen, dlen);
 
-			if (reqs[j]->dlen != ctemplate[i].inlen) {
-				pr_err("alg: acomp: Compression test %d (%d) failed for %s: output len = %d\n",
-				       i + 1, j, algo, reqs[j]->dlen);
-				ret = -EINVAL;
-				kfree(input_vec);
-				goto out;
-			}
+		ret = crypto_wait_req(crypto_acomp_decompress(req), &wait);
+		if (ret) {
+			pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
+			       i + 1, algo, -ret);
+			kfree(input_vec);
+			acomp_request_free(req);
+			goto out;
+		}
 
-			if (memcmp(input_vec, decomp_out[j], reqs[j]->dlen)) {
-				pr_err("alg: acomp: Compression test %d (%d) failed for %s\n",
-				       i + 1, j, algo);
-				hexdump(output[j], reqs[j]->dlen);
-				ret = -EINVAL;
-				kfree(input_vec);
-				goto out;
-			}
+		if (req->dlen != ctemplate[i].inlen) {
+			pr_err("alg: acomp: Compression test %d failed for %s: output len = %d\n",
+			       i + 1, algo, req->dlen);
+			ret = -EINVAL;
+			kfree(input_vec);
+			acomp_request_free(req);
+			goto out;
+		}
+
+		if (memcmp(input_vec, decomp_out, req->dlen)) {
+			pr_err("alg: acomp: Compression test %d failed for %s\n",
+			       i + 1, algo);
+			hexdump(output, req->dlen);
+			ret = -EINVAL;
+			kfree(input_vec);
+			acomp_request_free(req);
+			goto out;
 		}
 
 		kfree(input_vec);
+		acomp_request_free(req);
 	}
 
 	for (i = 0; i < dtcount; i++) {
@@ -3446,9 +3431,10 @@ static int test_acomp(struct crypto_acomp *tfm,
 			goto out;
 		}
 
+		memset(output, 0, dlen);
 		crypto_init_wait(&wait);
-		sg_init_one(src, input_vec, ilen);
-		sg_init_one(dst, output[0], dlen);
+		sg_init_one(&src, input_vec, ilen);
+		sg_init_one(&dst, output, dlen);
 
 		req = acomp_request_alloc(tfm);
 		if (!req) {
@@ -3459,7 +3445,7 @@ static int test_acomp(struct crypto_acomp *tfm,
 			goto out;
 		}
 
-		acomp_request_set_params(req, src, dst, ilen, dlen);
+		acomp_request_set_params(req, &src, &dst, ilen, dlen);
 		acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 					   crypto_req_done, &wait);
 
@@ -3481,10 +3467,10 @@ static int test_acomp(struct crypto_acomp *tfm,
 			goto out;
 		}
 
-		if (memcmp(output[0], dtemplate[i].output, req->dlen)) {
+		if (memcmp(output, dtemplate[i].output, req->dlen)) {
 			pr_err("alg: acomp: Decompression test %d failed for %s\n",
 			       i + 1, algo);
-			hexdump(output[0], req->dlen);
+			hexdump(output, req->dlen);
 			ret = -EINVAL;
 			kfree(input_vec);
 			acomp_request_free(req);
@@ -3498,13 +3484,8 @@ static int test_acomp(struct crypto_acomp *tfm,
 	ret = 0;
 
 out:
-	acomp_request_free(reqs[0]);
-	for (i = 0; i < MAX_MB_MSGS; i++) {
-		kfree(output[i]);
-		kfree(decomp_out[i]);
-	}
-	kfree(dst);
-	kfree(src);
+	kfree(decomp_out);
+	kfree(output);
 	return ret;
 }
 
diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c
index 0825851656a2..cd24ccd20ba6 100644
--- a/drivers/accel/ivpu/ivpu_debugfs.c
+++ b/drivers/accel/ivpu/ivpu_debugfs.c
@@ -332,7 +332,7 @@ ivpu_force_recovery_fn(struct file *file, const char __user *user_buf, size_t si
 		return -EINVAL;
 
 	ret = ivpu_rpm_get(vdev);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	ivpu_pm_trigger_recovery(vdev, "debugfs");
@@ -383,7 +383,7 @@ static int dct_active_set(void *data, u64 active_percent)
 		return -EINVAL;
 
 	ret = ivpu_rpm_get(vdev);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	if (active_percent)
@@ -455,7 +455,7 @@ priority_bands_fops_write(struct file *file, const char __user *user_buf, size_t
 	if (ret < 0)
 		return ret;
 
-	buf[size] = '\0';
+	buf[ret] = '\0';
 	ret = sscanf(buf, "%u %u %u %u", &band, &grace_period, &process_grace_period,
 		     &process_quantum);
 	if (ret != 4)
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 4fa73189502e..eff1d3ca075f 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #include <linux/firmware.h>
@@ -164,7 +164,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 		args->value = vdev->platform;
 		break;
 	case DRM_IVPU_PARAM_CORE_CLOCK_RATE:
-		args->value = ivpu_hw_ratio_to_freq(vdev, vdev->hw->pll.max_ratio);
+		args->value = ivpu_hw_dpu_max_freq_get(vdev);
 		break;
 	case DRM_IVPU_PARAM_NUM_CONTEXTS:
 		args->value = ivpu_get_context_count(vdev);
@@ -421,9 +421,9 @@ void ivpu_prepare_for_reset(struct ivpu_device *vdev)
 {
 	ivpu_hw_irq_disable(vdev);
 	disable_irq(vdev->irq);
-	cancel_work_sync(&vdev->irq_ipc_work);
-	cancel_work_sync(&vdev->irq_dct_work);
-	cancel_work_sync(&vdev->context_abort_work);
+	flush_work(&vdev->irq_ipc_work);
+	flush_work(&vdev->irq_dct_work);
+	flush_work(&vdev->context_abort_work);
 	ivpu_ipc_disable(vdev);
 	ivpu_mmu_disable(vdev);
 }
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 7a1bb92d8c81..ccaaf6c100c0 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #include <linux/firmware.h>
@@ -233,10 +233,20 @@ static int ivpu_fw_parse(struct ivpu_device *vdev)
 	fw->dvfs_mode = 0;
 
 	fw->sched_mode = ivpu_fw_sched_mode_select(vdev, fw_hdr);
-	fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size;
-	fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size;
 	ivpu_info(vdev, "Scheduler mode: %s\n", fw->sched_mode ? "HW" : "OS");
 
+	if (fw_hdr->preemption_buffer_1_max_size)
+		fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_max_size;
+	else
+		fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size;
+
+	if (fw_hdr->preemption_buffer_2_max_size)
+		fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_max_size;
+	else
+		fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size;
+	ivpu_dbg(vdev, FW_BOOT, "Preemption buffer sizes: primary %u, secondary %u\n",
+		 fw->primary_preempt_buf_size, fw->secondary_preempt_buf_size);
+
 	if (fw_hdr->ro_section_start_address && !is_within_range(fw_hdr->ro_section_start_address,
 								 fw_hdr->ro_section_size,
 								 fw_hdr->image_load_address,
@@ -534,7 +544,7 @@ static void ivpu_fw_boot_params_print(struct ivpu_device *vdev, struct vpu_boot_
 		 boot_params->d0i3_entry_vpu_ts);
 	ivpu_dbg(vdev, FW_BOOT, "boot_params.system_time_us = %llu\n",
 		 boot_params->system_time_us);
-	ivpu_dbg(vdev, FW_BOOT, "boot_params.power_profile = %u\n",
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.power_profile = 0x%x\n",
 		 boot_params->power_profile);
 }
 
@@ -566,7 +576,6 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 
 	boot_params->magic = VPU_BOOT_PARAMS_MAGIC;
 	boot_params->vpu_id = to_pci_dev(vdev->drm.dev)->bus->number;
-	boot_params->frequency = ivpu_hw_pll_freq_get(vdev);
 
 	/*
 	 * This param is a debug firmware feature.  It switches default clock
@@ -637,7 +646,7 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	boot_params->d0i3_residency_time_us = 0;
 	boot_params->d0i3_entry_vpu_ts = 0;
 	if (IVPU_WA(disable_d0i2))
-		boot_params->power_profile = 1;
+		boot_params->power_profile |= BIT(1);
 
 	boot_params->system_time_us = ktime_to_us(ktime_get_real());
 	wmb(); /* Flush WC buffers after writing bootparams */
diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c
index ec9a3629da3a..633160470c93 100644
--- a/drivers/accel/ivpu/ivpu_hw.c
+++ b/drivers/accel/ivpu/ivpu_hw.c
@@ -119,7 +119,7 @@ static void timeouts_init(struct ivpu_device *vdev)
 		else
 			vdev->timeout.autosuspend = 100;
 		vdev->timeout.d0i3_entry_msg = 5;
-		vdev->timeout.state_dump_msg = 10;
+		vdev->timeout.state_dump_msg = 100;
 	}
 }
 
diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h
index 16435f2756d0..d79668fe1609 100644
--- a/drivers/accel/ivpu/ivpu_hw.h
+++ b/drivers/accel/ivpu/ivpu_hw.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #ifndef __IVPU_HW_H__
@@ -82,19 +82,19 @@ static inline u64 ivpu_hw_range_size(const struct ivpu_addr_range *range)
 	return range->end - range->start;
 }
 
-static inline u32 ivpu_hw_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
+static inline u32 ivpu_hw_dpu_max_freq_get(struct ivpu_device *vdev)
 {
-	return ivpu_hw_btrs_ratio_to_freq(vdev, ratio);
+	return ivpu_hw_btrs_dpu_max_freq_get(vdev);
 }
 
-static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev)
+static inline u32 ivpu_hw_dpu_freq_get(struct ivpu_device *vdev)
 {
-	ivpu_hw_ip_irq_clear(vdev);
+	return ivpu_hw_btrs_dpu_freq_get(vdev);
 }
 
-static inline u32 ivpu_hw_pll_freq_get(struct ivpu_device *vdev)
+static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev)
 {
-	return ivpu_hw_btrs_pll_freq_get(vdev);
+	ivpu_hw_ip_irq_clear(vdev);
 }
 
 static inline u32 ivpu_hw_profiling_freq_get(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.c b/drivers/accel/ivpu/ivpu_hw_btrs.c
index 56c56012b980..b236c7234daa 100644
--- a/drivers/accel/ivpu/ivpu_hw_btrs.c
+++ b/drivers/accel/ivpu/ivpu_hw_btrs.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
+#include <linux/units.h>
+
 #include "ivpu_drv.h"
 #include "ivpu_hw.h"
 #include "ivpu_hw_btrs.h"
@@ -28,17 +30,13 @@
 
 #define BTRS_LNL_ALL_IRQ_MASK ((u32)-1)
 
-#define BTRS_MTL_WP_CONFIG_1_TILE_5_3_RATIO WP_CONFIG(MTL_CONFIG_1_TILE, MTL_PLL_RATIO_5_3)
-#define BTRS_MTL_WP_CONFIG_1_TILE_4_3_RATIO WP_CONFIG(MTL_CONFIG_1_TILE, MTL_PLL_RATIO_4_3)
-#define BTRS_MTL_WP_CONFIG_2_TILE_5_3_RATIO WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_5_3)
-#define BTRS_MTL_WP_CONFIG_2_TILE_4_3_RATIO WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3)
-#define BTRS_MTL_WP_CONFIG_0_TILE_PLL_OFF   WP_CONFIG(0, 0)
 
 #define PLL_CDYN_DEFAULT               0x80
 #define PLL_EPP_DEFAULT                0x80
 #define PLL_CONFIG_DEFAULT             0x0
-#define PLL_SIMULATION_FREQ            10000000
-#define PLL_REF_CLK_FREQ               50000000
+#define PLL_REF_CLK_FREQ               50000000ull
+#define PLL_RATIO_TO_FREQ(x)           ((x) * PLL_REF_CLK_FREQ)
+
 #define PLL_TIMEOUT_US		       (1500 * USEC_PER_MSEC)
 #define IDLE_TIMEOUT_US		       (5 * USEC_PER_MSEC)
 #define TIMEOUT_US                     (150 * USEC_PER_MSEC)
@@ -62,6 +60,8 @@
 #define DCT_ENABLE                     0x1
 #define DCT_DISABLE                    0x0
 
+static u32 pll_ratio_to_dpu_freq(struct ivpu_device *vdev, u32 ratio);
+
 int ivpu_hw_btrs_irqs_clear_with_0_mtl(struct ivpu_device *vdev)
 {
 	REGB_WR32(VPU_HW_BTRS_MTL_INTERRUPT_STAT, BTRS_MTL_ALL_IRQ_MASK);
@@ -156,7 +156,7 @@ static int info_init_mtl(struct ivpu_device *vdev)
 
 	hw->tile_fuse = BTRS_MTL_TILE_FUSE_ENABLE_BOTH;
 	hw->sku = BTRS_MTL_TILE_SKU_BOTH;
-	hw->config = BTRS_MTL_WP_CONFIG_2_TILE_4_3_RATIO;
+	hw->config = WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3);
 
 	return 0;
 }
@@ -334,8 +334,8 @@ int ivpu_hw_btrs_wp_drive(struct ivpu_device *vdev, bool enable)
 
 	prepare_wp_request(vdev, &wp, enable);
 
-	ivpu_dbg(vdev, PM, "PLL workpoint request: %u Hz, config: 0x%x, epp: 0x%x, cdyn: 0x%x\n",
-		 PLL_RATIO_TO_FREQ(wp.target), wp.cfg, wp.epp, wp.cdyn);
+	ivpu_dbg(vdev, PM, "PLL workpoint request: %lu MHz, config: 0x%x, epp: 0x%x, cdyn: 0x%x\n",
+		 pll_ratio_to_dpu_freq(vdev, wp.target) / HZ_PER_MHZ, wp.cfg, wp.epp, wp.cdyn);
 
 	ret = wp_request_send(vdev, &wp);
 	if (ret) {
@@ -573,6 +573,47 @@ int ivpu_hw_btrs_wait_for_idle(struct ivpu_device *vdev)
 		return REGB_POLL_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, IDLE, 0x1, IDLE_TIMEOUT_US);
 }
 
+static u32 pll_config_get_mtl(struct ivpu_device *vdev)
+{
+	return REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL);
+}
+
+static u32 pll_config_get_lnl(struct ivpu_device *vdev)
+{
+	return REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ);
+}
+
+static u32 pll_ratio_to_dpu_freq_mtl(u16 ratio)
+{
+	return (PLL_RATIO_TO_FREQ(ratio) * 2) / 3;
+}
+
+static u32 pll_ratio_to_dpu_freq_lnl(u16 ratio)
+{
+	return PLL_RATIO_TO_FREQ(ratio) / 2;
+}
+
+static u32 pll_ratio_to_dpu_freq(struct ivpu_device *vdev, u32 ratio)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return pll_ratio_to_dpu_freq_mtl(ratio);
+	else
+		return pll_ratio_to_dpu_freq_lnl(ratio);
+}
+
+u32 ivpu_hw_btrs_dpu_max_freq_get(struct ivpu_device *vdev)
+{
+	return pll_ratio_to_dpu_freq(vdev, vdev->hw->pll.max_ratio);
+}
+
+u32 ivpu_hw_btrs_dpu_freq_get(struct ivpu_device *vdev)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return pll_ratio_to_dpu_freq_mtl(pll_config_get_mtl(vdev));
+	else
+		return pll_ratio_to_dpu_freq_lnl(pll_config_get_lnl(vdev));
+}
+
 /* Handler for IRQs from Buttress core (irqB) */
 bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq)
 {
@@ -582,9 +623,12 @@ bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq)
 	if (!status)
 		return false;
 
-	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, FREQ_CHANGE, status))
-		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x",
-			 REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL));
+	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, FREQ_CHANGE, status)) {
+		u32 pll = pll_config_get_mtl(vdev);
+
+		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq, wp %08x, %lu MHz",
+			 pll, pll_ratio_to_dpu_freq_mtl(pll) / HZ_PER_MHZ);
+	}
 
 	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, ATS_ERR, status)) {
 		ivpu_err(vdev, "ATS_ERR irq 0x%016llx", REGB_RD64(VPU_HW_BTRS_MTL_ATS_ERR_LOG_0));
@@ -633,8 +677,12 @@ bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq)
 		queue_work(system_wq, &vdev->irq_dct_work);
 	}
 
-	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, FREQ_CHANGE, status))
-		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x", REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ));
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, FREQ_CHANGE, status)) {
+		u32 pll = pll_config_get_lnl(vdev);
+
+		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq, wp %08x, %lu MHz",
+			 pll, pll_ratio_to_dpu_freq_lnl(pll) / HZ_PER_MHZ);
+	}
 
 	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, ATS_ERR, status)) {
 		ivpu_err(vdev, "ATS_ERR LOG1 0x%08x ATS_ERR_LOG2 0x%08x\n",
@@ -717,60 +765,6 @@ void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 acti
 	REGB_WR32(VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS, val);
 }
 
-static u32 pll_ratio_to_freq_mtl(u32 ratio, u32 config)
-{
-	u32 pll_clock = PLL_REF_CLK_FREQ * ratio;
-	u32 cpu_clock;
-
-	if ((config & 0xff) == MTL_PLL_RATIO_4_3)
-		cpu_clock = pll_clock * 2 / 4;
-	else
-		cpu_clock = pll_clock * 2 / 5;
-
-	return cpu_clock;
-}
-
-u32 ivpu_hw_btrs_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
-{
-	struct ivpu_hw_info *hw = vdev->hw;
-
-	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
-		return pll_ratio_to_freq_mtl(ratio, hw->config);
-	else
-		return PLL_RATIO_TO_FREQ(ratio);
-}
-
-static u32 pll_freq_get_mtl(struct ivpu_device *vdev)
-{
-	u32 pll_curr_ratio;
-
-	pll_curr_ratio = REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL);
-	pll_curr_ratio &= VPU_HW_BTRS_MTL_CURRENT_PLL_RATIO_MASK;
-
-	if (!ivpu_is_silicon(vdev))
-		return PLL_SIMULATION_FREQ;
-
-	return pll_ratio_to_freq_mtl(pll_curr_ratio, vdev->hw->config);
-}
-
-static u32 pll_freq_get_lnl(struct ivpu_device *vdev)
-{
-	u32 pll_curr_ratio;
-
-	pll_curr_ratio = REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ);
-	pll_curr_ratio &= VPU_HW_BTRS_LNL_PLL_FREQ_RATIO_MASK;
-
-	return PLL_RATIO_TO_FREQ(pll_curr_ratio);
-}
-
-u32 ivpu_hw_btrs_pll_freq_get(struct ivpu_device *vdev)
-{
-	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
-		return pll_freq_get_mtl(vdev);
-	else
-		return pll_freq_get_lnl(vdev);
-}
-
 u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev)
 {
 	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.h b/drivers/accel/ivpu/ivpu_hw_btrs.h
index 1fd71b4d4ab0..d2d82651976d 100644
--- a/drivers/accel/ivpu/ivpu_hw_btrs.h
+++ b/drivers/accel/ivpu/ivpu_hw_btrs.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #ifndef __IVPU_HW_BTRS_H__
@@ -13,9 +13,8 @@
 
 #define PLL_PROFILING_FREQ_DEFAULT   38400000
 #define PLL_PROFILING_FREQ_HIGH      400000000
-#define PLL_RATIO_TO_FREQ(x)         ((x) * PLL_REF_CLK_FREQ)
 
-#define DCT_DEFAULT_ACTIVE_PERCENT 15u
+#define DCT_DEFAULT_ACTIVE_PERCENT 30u
 #define DCT_PERIOD_US		   35300u
 
 int ivpu_hw_btrs_info_init(struct ivpu_device *vdev);
@@ -32,12 +31,12 @@ int ivpu_hw_btrs_ip_reset(struct ivpu_device *vdev);
 void ivpu_hw_btrs_profiling_freq_reg_set_lnl(struct ivpu_device *vdev);
 void ivpu_hw_btrs_ats_print_lnl(struct ivpu_device *vdev);
 void ivpu_hw_btrs_clock_relinquish_disable_lnl(struct ivpu_device *vdev);
+u32 ivpu_hw_btrs_dpu_max_freq_get(struct ivpu_device *vdev);
+u32 ivpu_hw_btrs_dpu_freq_get(struct ivpu_device *vdev);
 bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq);
 bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq);
 int ivpu_hw_btrs_dct_get_request(struct ivpu_device *vdev, bool *enable);
 void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 dct_percent);
-u32 ivpu_hw_btrs_pll_freq_get(struct ivpu_device *vdev);
-u32 ivpu_hw_btrs_ratio_to_freq(struct ivpu_device *vdev, u32 ratio);
 u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev);
 u32 ivpu_hw_btrs_telemetry_size_get(struct ivpu_device *vdev);
 u32 ivpu_hw_btrs_telemetry_enable_get(struct ivpu_device *vdev);
diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index 0e096fd9b95d..39f83225c181 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -302,7 +302,8 @@ ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg *req
 	struct ivpu_ipc_consumer cons;
 	int ret;
 
-	drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev));
+	drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev) &&
+		    pm_runtime_enabled(vdev->drm.dev));
 
 	ivpu_ipc_consumer_add(vdev, &cons, channel, NULL);
 
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 004059e4f1e8..b28da35c30b6 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -470,8 +470,8 @@ static void ivpu_job_destroy(struct ivpu_job *job)
 	struct ivpu_device *vdev = job->vdev;
 	u32 i;
 
-	ivpu_dbg(vdev, JOB, "Job destroyed: id %3u ctx %2d engine %d",
-		 job->job_id, job->file_priv->ctx.id, job->engine_idx);
+	ivpu_dbg(vdev, JOB, "Job destroyed: id %3u ctx %2d cmdq_id %u engine %d",
+		 job->job_id, job->file_priv->ctx.id, job->cmdq_id, job->engine_idx);
 
 	for (i = 0; i < job->bo_count; i++)
 		if (job->bos[i])
@@ -564,8 +564,8 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
 	dma_fence_signal(job->done_fence);
 
 	trace_job("done", job);
-	ivpu_dbg(vdev, JOB, "Job complete:  id %3u ctx %2d engine %d status 0x%x\n",
-		 job->job_id, job->file_priv->ctx.id, job->engine_idx, job_status);
+	ivpu_dbg(vdev, JOB, "Job complete:  id %3u ctx %2d cmdq_id %u engine %d status 0x%x\n",
+		 job->job_id, job->file_priv->ctx.id, job->cmdq_id, job->engine_idx, job_status);
 
 	ivpu_job_destroy(job);
 	ivpu_stop_job_timeout_detection(vdev);
@@ -664,8 +664,8 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority, u32 cmdq_id)
 	}
 
 	trace_job("submit", job);
-	ivpu_dbg(vdev, JOB, "Job submitted: id %3u ctx %2d engine %d prio %d addr 0x%llx next %d\n",
-		 job->job_id, file_priv->ctx.id, job->engine_idx, cmdq->priority,
+	ivpu_dbg(vdev, JOB, "Job submitted: id %3u ctx %2d cmdq_id %u engine %d prio %d addr 0x%llx next %d\n",
+		 job->job_id, file_priv->ctx.id, cmdq->id, job->engine_idx, cmdq->priority,
 		 job->cmd_buf_vpu_addr, cmdq->jobq->header.tail);
 
 	mutex_unlock(&file_priv->lock);
@@ -681,8 +681,8 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority, u32 cmdq_id)
 err_erase_xa:
 	xa_erase(&vdev->submitted_jobs_xa, job->job_id);
 err_unlock:
-	mutex_unlock(&vdev->submitted_jobs_lock);
 	mutex_unlock(&file_priv->lock);
+	mutex_unlock(&vdev->submitted_jobs_lock);
 	ivpu_rpm_put(vdev);
 	return ret;
 }
@@ -777,7 +777,8 @@ static int ivpu_submit(struct drm_file *file, struct ivpu_file_priv *file_priv,
 		goto err_free_handles;
 	}
 
-	ivpu_dbg(vdev, JOB, "Submit ioctl: ctx %u buf_count %u\n", file_priv->ctx.id, buffer_count);
+	ivpu_dbg(vdev, JOB, "Submit ioctl: ctx %u cmdq_id %u buf_count %u\n",
+		 file_priv->ctx.id, cmdq_id, buffer_count);
 
 	job = ivpu_job_create(file_priv, engine, buffer_count);
 	if (!job) {
@@ -873,15 +874,21 @@ int ivpu_cmdq_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *
 int ivpu_cmdq_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
 	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct ivpu_device *vdev = file_priv->vdev;
 	struct drm_ivpu_cmdq_create *args = data;
 	struct ivpu_cmdq *cmdq;
+	int ret;
 
-	if (!ivpu_is_capable(file_priv->vdev, DRM_IVPU_CAP_MANAGE_CMDQ))
+	if (!ivpu_is_capable(vdev, DRM_IVPU_CAP_MANAGE_CMDQ))
 		return -ENODEV;
 
 	if (args->priority > DRM_IVPU_JOB_PRIORITY_REALTIME)
 		return -EINVAL;
 
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
 	mutex_lock(&file_priv->lock);
 
 	cmdq = ivpu_cmdq_create(file_priv, ivpu_job_to_jsm_priority(args->priority), false);
@@ -890,6 +897,8 @@ int ivpu_cmdq_create_ioctl(struct drm_device *dev, void *data, struct drm_file *
 
 	mutex_unlock(&file_priv->lock);
 
+	ivpu_rpm_put(vdev);
+
 	return cmdq ? 0 : -ENOMEM;
 }
 
@@ -899,28 +908,35 @@ int ivpu_cmdq_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file
 	struct ivpu_device *vdev = file_priv->vdev;
 	struct drm_ivpu_cmdq_destroy *args = data;
 	struct ivpu_cmdq *cmdq;
-	u32 cmdq_id;
+	u32 cmdq_id = 0;
 	int ret;
 
 	if (!ivpu_is_capable(vdev, DRM_IVPU_CAP_MANAGE_CMDQ))
 		return -ENODEV;
 
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
 	mutex_lock(&file_priv->lock);
 
 	cmdq = xa_load(&file_priv->cmdq_xa, args->cmdq_id);
 	if (!cmdq || cmdq->is_legacy) {
 		ret = -ENOENT;
-		goto err_unlock;
+	} else {
+		cmdq_id = cmdq->id;
+		ivpu_cmdq_destroy(file_priv, cmdq);
+		ret = 0;
 	}
 
-	cmdq_id = cmdq->id;
-	ivpu_cmdq_destroy(file_priv, cmdq);
 	mutex_unlock(&file_priv->lock);
-	ivpu_cmdq_abort_all_jobs(vdev, file_priv->ctx.id, cmdq_id);
-	return 0;
 
-err_unlock:
-	mutex_unlock(&file_priv->lock);
+	/* Abort any pending jobs only if cmdq was destroyed */
+	if (!ret)
+		ivpu_cmdq_abort_all_jobs(vdev, file_priv->ctx.id, cmdq_id);
+
+	ivpu_rpm_put(vdev);
+
 	return ret;
 }
 
diff --git a/drivers/accel/ivpu/ivpu_ms.c b/drivers/accel/ivpu/ivpu_ms.c
index ffe7b10f8a76..2a043baf10ca 100644
--- a/drivers/accel/ivpu/ivpu_ms.c
+++ b/drivers/accel/ivpu/ivpu_ms.c
@@ -4,6 +4,7 @@
  */
 
 #include <drm/drm_file.h>
+#include <linux/pm_runtime.h>
 
 #include "ivpu_drv.h"
 #include "ivpu_gem.h"
@@ -44,6 +45,10 @@ int ivpu_ms_start_ioctl(struct drm_device *dev, void *data, struct drm_file *fil
 	    args->sampling_period_ns < MS_MIN_SAMPLE_PERIOD_NS)
 		return -EINVAL;
 
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
 	mutex_lock(&file_priv->ms_lock);
 
 	if (get_instance_by_mask(file_priv, args->metric_group_mask)) {
@@ -96,6 +101,8 @@ err_free_ms:
 	kfree(ms);
 unlock:
 	mutex_unlock(&file_priv->ms_lock);
+
+	ivpu_rpm_put(vdev);
 	return ret;
 }
 
@@ -160,6 +167,10 @@ int ivpu_ms_get_data_ioctl(struct drm_device *dev, void *data, struct drm_file *
 	if (!args->metric_group_mask)
 		return -EINVAL;
 
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
 	mutex_lock(&file_priv->ms_lock);
 
 	ms = get_instance_by_mask(file_priv, args->metric_group_mask);
@@ -187,6 +198,7 @@ int ivpu_ms_get_data_ioctl(struct drm_device *dev, void *data, struct drm_file *
 unlock:
 	mutex_unlock(&file_priv->ms_lock);
 
+	ivpu_rpm_put(vdev);
 	return ret;
 }
 
@@ -204,11 +216,17 @@ int ivpu_ms_stop_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 {
 	struct ivpu_file_priv *file_priv = file->driver_priv;
 	struct drm_ivpu_metric_streamer_stop *args = data;
+	struct ivpu_device *vdev = file_priv->vdev;
 	struct ivpu_ms_instance *ms;
+	int ret;
 
 	if (!args->metric_group_mask)
 		return -EINVAL;
 
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
 	mutex_lock(&file_priv->ms_lock);
 
 	ms = get_instance_by_mask(file_priv, args->metric_group_mask);
@@ -217,6 +235,7 @@ int ivpu_ms_stop_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 	mutex_unlock(&file_priv->ms_lock);
 
+	ivpu_rpm_put(vdev);
 	return ms ? 0 : -EINVAL;
 }
 
@@ -281,6 +300,9 @@ unlock:
 void ivpu_ms_cleanup(struct ivpu_file_priv *file_priv)
 {
 	struct ivpu_ms_instance *ms, *tmp;
+	struct ivpu_device *vdev = file_priv->vdev;
+
+	pm_runtime_get_sync(vdev->drm.dev);
 
 	mutex_lock(&file_priv->ms_lock);
 
@@ -293,6 +315,8 @@ void ivpu_ms_cleanup(struct ivpu_file_priv *file_priv)
 		free_instance(file_priv, ms);
 
 	mutex_unlock(&file_priv->ms_lock);
+
+	pm_runtime_put_autosuspend(vdev->drm.dev);
 }
 
 void ivpu_ms_cleanup_all(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index b5891e91f7ab..ac0e22454596 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -428,16 +428,17 @@ int ivpu_pm_dct_enable(struct ivpu_device *vdev, u8 active_percent)
 	active_us = (DCT_PERIOD_US * active_percent) / 100;
 	inactive_us = DCT_PERIOD_US - active_us;
 
+	vdev->pm->dct_active_percent = active_percent;
+
+	ivpu_dbg(vdev, PM, "DCT requested %u%% (D0: %uus, D0i2: %uus)\n",
+		 active_percent, active_us, inactive_us);
+
 	ret = ivpu_jsm_dct_enable(vdev, active_us, inactive_us);
 	if (ret) {
 		ivpu_err_ratelimited(vdev, "Failed to enable DCT: %d\n", ret);
 		return ret;
 	}
 
-	vdev->pm->dct_active_percent = active_percent;
-
-	ivpu_dbg(vdev, PM, "DCT set to %u%% (D0: %uus, D0i2: %uus)\n",
-		 active_percent, active_us, inactive_us);
 	return 0;
 }
 
@@ -445,15 +446,16 @@ int ivpu_pm_dct_disable(struct ivpu_device *vdev)
 {
 	int ret;
 
+	vdev->pm->dct_active_percent = 0;
+
+	ivpu_dbg(vdev, PM, "DCT requested to be disabled\n");
+
 	ret = ivpu_jsm_dct_disable(vdev);
 	if (ret) {
 		ivpu_err_ratelimited(vdev, "Failed to disable DCT: %d\n", ret);
 		return ret;
 	}
 
-	vdev->pm->dct_active_percent = 0;
-
-	ivpu_dbg(vdev, PM, "DCT disabled\n");
 	return 0;
 }
 
@@ -466,7 +468,7 @@ void ivpu_pm_irq_dct_work_fn(struct work_struct *work)
 	if (ivpu_hw_btrs_dct_get_request(vdev, &enable))
 		return;
 
-	if (vdev->pm->dct_active_percent)
+	if (enable)
 		ret = ivpu_pm_dct_enable(vdev, DCT_DEFAULT_ACTIVE_PERCENT);
 	else
 		ret = ivpu_pm_dct_disable(vdev);
diff --git a/drivers/accel/ivpu/ivpu_sysfs.c b/drivers/accel/ivpu/ivpu_sysfs.c
index 97102feaf8dd..268ab7744a8b 100644
--- a/drivers/accel/ivpu/ivpu_sysfs.c
+++ b/drivers/accel/ivpu/ivpu_sysfs.c
@@ -1,10 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  */
 
 #include <linux/device.h>
 #include <linux/err.h>
+#include <linux/pm_runtime.h>
+#include <linux/units.h>
 
 #include "ivpu_drv.h"
 #include "ivpu_gem.h"
@@ -90,10 +92,55 @@ sched_mode_show(struct device *dev, struct device_attribute *attr, char *buf)
 
 static DEVICE_ATTR_RO(sched_mode);
 
+/**
+ * DOC: npu_max_frequency
+ *
+ * The npu_max_frequency shows maximum frequency in MHz of the NPU's data
+ * processing unit
+ */
+static ssize_t
+npu_max_frequency_mhz_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct ivpu_device *vdev = to_ivpu_device(drm);
+	u32 freq = ivpu_hw_dpu_max_freq_get(vdev);
+
+	return sysfs_emit(buf, "%lu\n", freq / HZ_PER_MHZ);
+}
+
+static DEVICE_ATTR_RO(npu_max_frequency_mhz);
+
+/**
+ * DOC: npu_current_frequency_mhz
+ *
+ * The npu_current_frequency_mhz shows current frequency in MHz of the NPU's
+ * data processing unit
+ */
+static ssize_t
+npu_current_frequency_mhz_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct ivpu_device *vdev = to_ivpu_device(drm);
+	u32 freq = 0;
+
+	/* Read frequency only if device is active, otherwise frequency is 0 */
+	if (pm_runtime_get_if_active(vdev->drm.dev) > 0) {
+		freq = ivpu_hw_dpu_freq_get(vdev);
+
+		pm_runtime_put_autosuspend(vdev->drm.dev);
+	}
+
+	return sysfs_emit(buf, "%lu\n", freq / HZ_PER_MHZ);
+}
+
+static DEVICE_ATTR_RO(npu_current_frequency_mhz);
+
 static struct attribute *ivpu_dev_attrs[] = {
 	&dev_attr_npu_busy_time_us.attr,
 	&dev_attr_npu_memory_utilization.attr,
 	&dev_attr_sched_mode.attr,
+	&dev_attr_npu_max_frequency_mhz.attr,
+	&dev_attr_npu_current_frequency_mhz.attr,
 	NULL,
 };
 
diff --git a/drivers/accel/ivpu/vpu_boot_api.h b/drivers/accel/ivpu/vpu_boot_api.h
index 908e68ea1c39..218468bbbcad 100644
--- a/drivers/accel/ivpu/vpu_boot_api.h
+++ b/drivers/accel/ivpu/vpu_boot_api.h
@@ -26,7 +26,7 @@
  * Minor version changes when API backward compatibility is preserved.
  * Resets to 0 if Major version is incremented.
  */
-#define VPU_BOOT_API_VER_MINOR 26
+#define VPU_BOOT_API_VER_MINOR 28
 
 /*
  * API header changed (field names, documentation, formatting) but API itself has not been changed
@@ -76,8 +76,15 @@ struct vpu_firmware_header {
 	 * submission queue size and device capabilities.
 	 */
 	u32 preemption_buffer_2_size;
+	/*
+	 * Maximum preemption buffer size that the FW can use: no need for the host
+	 * driver to allocate more space than that specified by these fields.
+	 * A value of 0 means no declared limit.
+	 */
+	u32 preemption_buffer_1_max_size;
+	u32 preemption_buffer_2_max_size;
 	/* Space reserved for future preemption-related fields. */
-	u32 preemption_reserved[6];
+	u32 preemption_reserved[4];
 	/* FW image read only section start address, 4KB aligned */
 	u64 ro_section_start_address;
 	/* FW image read only section size, 4KB aligned */
@@ -134,7 +141,7 @@ enum vpu_trace_destination {
 /*
  * Processor bit shifts (for loggable HW components).
  */
-#define VPU_TRACE_PROC_BIT_ARM	     0
+#define VPU_TRACE_PROC_BIT_RESERVED  0
 #define VPU_TRACE_PROC_BIT_LRT	     1
 #define VPU_TRACE_PROC_BIT_LNN	     2
 #define VPU_TRACE_PROC_BIT_SHV_0     3
diff --git a/drivers/accel/ivpu/vpu_jsm_api.h b/drivers/accel/ivpu/vpu_jsm_api.h
index 7215c144158c..4b6b2b3d2583 100644
--- a/drivers/accel/ivpu/vpu_jsm_api.h
+++ b/drivers/accel/ivpu/vpu_jsm_api.h
@@ -22,7 +22,7 @@
 /*
  * Minor version changes when API backward compatibility is preserved.
  */
-#define VPU_JSM_API_VER_MINOR 25
+#define VPU_JSM_API_VER_MINOR 29
 
 /*
  * API header changed (field names, documentation, formatting) but API itself has not been changed
@@ -53,8 +53,7 @@
  * Engine indexes.
  */
 #define VPU_ENGINE_COMPUTE 0
-#define VPU_ENGINE_COPY	   1
-#define VPU_ENGINE_NB	   2
+#define VPU_ENGINE_NB	   1
 
 /*
  * VPU status values.
@@ -126,11 +125,13 @@ enum {
 	 * When set, indicates that job queue uses native fences (as inline commands
 	 * in job queue). Such queues may also use legacy fences (as commands in batch buffers).
 	 * When cleared, indicates the job queue only uses legacy fences.
-	 * NOTE: For queues using native fences, VPU expects that all jobs in the queue
-	 * are immediately followed by an inline command object. This object is expected
-	 * to be a fence signal command in most cases, but can also be a NOP in case the host
-	 * does not need per-job fence signalling. Other inline commands objects can be
-	 * inserted between "job and inline command" pairs.
+	 * NOTES:
+	 *   1. For queues using native fences, VPU expects that all jobs in the queue
+	 *      are immediately followed by an inline command object. This object is expected
+	 *      to be a fence signal command in most cases, but can also be a NOP in case the host
+	 *      does not need per-job fence signalling. Other inline commands objects can be
+	 *      inserted between "job and inline command" pairs.
+	 *  2. Native fence queues are only supported on VPU 40xx onwards.
 	 */
 	VPU_JOB_QUEUE_FLAGS_USE_NATIVE_FENCE_MASK = (1 << 1U),
 
@@ -275,6 +276,8 @@ struct vpu_inline_cmd {
 			u64 value;
 			/* User VA of the log buffer in which to add log entry on completion. */
 			u64 log_buffer_va;
+			/* NPU private data. */
+			u64 npu_private_data;
 		} fence;
 		/* Other commands do not have a payload. */
 		/* Payload definition for future inline commands can be inserted here. */
@@ -791,12 +794,22 @@ struct vpu_jsm_metric_streamer_update {
 	/** Metric group mask that identifies metric streamer instance. */
 	u64 metric_group_mask;
 	/**
-	 * Address and size of the buffer where the VPU will write metric data. If
-	 * the buffer address is 0 or same as the currently used buffer the VPU will
-	 * continue writing metric data to the current buffer. In this case the
-	 * buffer size is ignored and the size of the current buffer is unchanged.
-	 * If the address is non-zero and differs from the current buffer address the
-	 * VPU will immediately switch data collection to the new buffer.
+	 * Address and size of the buffer where the VPU will write metric data.
+	 * This member dictates how the update operation should perform:
+	 * 1. client needs information about the number of collected samples and the
+	 *   amount of data written to the current buffer
+	 * 2. client wants to switch to a new buffer
+	 *
+	 * Case 1. is identified by the buffer address being 0 or the same as the
+	 * currently used buffer address. In this case the buffer size is ignored and
+	 * the size of the current buffer is unchanged. The VPU will return an update
+	 * in the vpu_jsm_metric_streamer_done structure. The internal writing position
+	 * into the buffer is not changed.
+	 *
+	 * Case 2. is identified by the address being non-zero and differs from the
+	 * current buffer address. The VPU will immediately switch data collection to
+	 * the new buffer. Then the VPU will return an update in the
+	 * vpu_jsm_metric_streamer_done structure.
 	 */
 	u64 buffer_addr;
 	u64 buffer_size;
@@ -934,6 +947,7 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup {
 	/*
 	 * Default quantum in 100ns units for scheduling across processes
 	 * within a priority band
+	 * Minimum value supported by NPU is 1ms (10000 in 100ns units).
 	 */
 	u32 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS];
 	/*
@@ -946,8 +960,10 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup {
 	 * in situations when it's starved by the focus band.
 	 */
 	u32 normal_band_percentage;
-	/* Reserved */
-	u32 reserved_0;
+	/*
+	 * TDR timeout value in milliseconds. Default value of 0 meaning no timeout.
+	 */
+	u32 tdr_timeout;
 };
 
 /*
@@ -1024,7 +1040,10 @@ struct vpu_ipc_msg_payload_hws_set_context_sched_properties {
 	s32 in_process_priority;
 	/* Zero padding / Reserved */
 	u32 reserved_1;
-	/* Context quantum relative to other contexts of same priority in the same process */
+	/*
+	 * Context quantum relative to other contexts of same priority in the same process
+	 * Minimum value supported by NPU is 1ms (10000 in 100ns units).
+	 */
 	u64 context_quantum;
 	/* Grace period when preempting context of the same priority within the same process */
 	u64 grace_period_same_priority;
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 6f4fe47c955b..6481c48c22bb 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -293,7 +293,7 @@ acpi_status (*acpi_internal_method) (struct acpi_walk_state * walk_state);
  * expected_return_btypes - Allowed type(s) for the return value
  */
 struct acpi_name_info {
-	char name[ACPI_NAMESEG_SIZE];
+	char name[ACPI_NAMESEG_SIZE] __nonstring;
 	u16 argument_list;
 	u8 expected_btypes;
 };
@@ -370,7 +370,7 @@ typedef acpi_status (*acpi_object_converter) (struct acpi_namespace_node *
 					      converted_object);
 
 struct acpi_simple_repair_info {
-	char name[ACPI_NAMESEG_SIZE];
+	char name[ACPI_NAMESEG_SIZE] __nonstring;
 	u32 unexpected_btypes;
 	u32 package_index;
 	acpi_object_converter object_converter;
diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c
index 1bb7b71f07f1..330b5e4711da 100644
--- a/drivers/acpi/acpica/nsrepair2.c
+++ b/drivers/acpi/acpica/nsrepair2.c
@@ -25,7 +25,7 @@ acpi_status (*acpi_repair_function) (struct acpi_evaluate_info * info,
 				     return_object_ptr);
 
 typedef struct acpi_repair_info {
-	char name[ACPI_NAMESEG_SIZE];
+	char name[ACPI_NAMESEG_SIZE] __nonstring;
 	acpi_repair_function repair_function;
 
 } acpi_repair_info;
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 90b09840536d..0a7026040188 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -458,7 +458,7 @@ static void acpi_button_notify(acpi_handle handle, u32 event, void *data)
 	acpi_pm_wakeup_event(&device->dev);
 
 	button = acpi_driver_data(device);
-	if (button->suspended)
+	if (button->suspended || event == ACPI_BUTTON_NOTIFY_WAKE)
 		return;
 
 	input = button->input;
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 8db09d81918f..3c5f34892734 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -2301,6 +2301,34 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = {
 			DMI_MATCH(DMI_PRODUCT_FAMILY, "103C_5336AN HP ZHAN 66 Pro"),
 		},
 	},
+	/*
+	 * Lenovo Legion Go S; touchscreen blocks HW sleep when woken up from EC
+	 * https://gitlab.freedesktop.org/drm/amd/-/issues/3929
+	 */
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83L3"),
+		}
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83N6"),
+		}
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83Q2"),
+		}
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83Q3"),
+		}
+	},
 	{ },
 };
 
diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
index a35dd0e41c27..54676e3d82dd 100644
--- a/drivers/acpi/pptt.c
+++ b/drivers/acpi/pptt.c
@@ -229,18 +229,20 @@ static int acpi_pptt_leaf_node(struct acpi_table_header *table_hdr,
 	node_entry = ACPI_PTR_DIFF(node, table_hdr);
 	entry = ACPI_ADD_PTR(struct acpi_subtable_header, table_hdr,
 			     sizeof(struct acpi_table_pptt));
-	proc_sz = sizeof(struct acpi_pptt_processor *);
+	proc_sz = sizeof(struct acpi_pptt_processor);
 
-	while ((unsigned long)entry + proc_sz < table_end) {
+	/* ignore subtable types that are smaller than a processor node */
+	while ((unsigned long)entry + proc_sz <= table_end) {
 		cpu_node = (struct acpi_pptt_processor *)entry;
+
 		if (entry->type == ACPI_PPTT_TYPE_PROCESSOR &&
 		    cpu_node->parent == node_entry)
 			return 0;
 		if (entry->length == 0)
 			return 0;
+
 		entry = ACPI_ADD_PTR(struct acpi_subtable_header, entry,
 				     entry->length);
-
 	}
 	return 1;
 }
@@ -270,18 +272,21 @@ static struct acpi_pptt_processor *acpi_find_processor_node(struct acpi_table_he
 	table_end = (unsigned long)table_hdr + table_hdr->length;
 	entry = ACPI_ADD_PTR(struct acpi_subtable_header, table_hdr,
 			     sizeof(struct acpi_table_pptt));
-	proc_sz = sizeof(struct acpi_pptt_processor *);
+	proc_sz = sizeof(struct acpi_pptt_processor);
 
 	/* find the processor structure associated with this cpuid */
-	while ((unsigned long)entry + proc_sz < table_end) {
+	while ((unsigned long)entry + proc_sz <= table_end) {
 		cpu_node = (struct acpi_pptt_processor *)entry;
 
 		if (entry->length == 0) {
 			pr_warn("Invalid zero length subtable\n");
 			break;
 		}
+		/* entry->length may not equal proc_sz, revalidate the processor structure length */
 		if (entry->type == ACPI_PPTT_TYPE_PROCESSOR &&
 		    acpi_cpu_id == cpu_node->acpi_processor_id &&
+		    (unsigned long)entry + entry->length <= table_end &&
+		    entry->length == proc_sz + cpu_node->number_of_priv_resources * sizeof(u32) &&
 		     acpi_pptt_leaf_node(table_hdr, cpu_node)) {
 			return (struct acpi_pptt_processor *)entry;
 		}
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 76052006bd87..5fc2c8ee61b1 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -6373,7 +6373,7 @@ static void print_binder_transaction_ilocked(struct seq_file *m,
 		seq_printf(m, " node %d", buffer->target_node->debug_id);
 	seq_printf(m, " size %zd:%zd offset %lx\n",
 		   buffer->data_size, buffer->offsets_size,
-		   proc->alloc.vm_start - buffer->user_data);
+		   buffer->user_data - proc->alloc.vm_start);
 }
 
 static void print_binder_work_ilocked(struct seq_file *m,
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index ba300cc0a3a3..2e4463d3a356 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -1510,6 +1510,8 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
 	unsigned int err_mask, tag;
 	u8 *sense, sk = 0, asc = 0, ascq = 0;
 	u64 sense_valid, val;
+	u16 extended_sense;
+	bool aux_icc_valid;
 	int ret = 0;
 
 	err_mask = ata_read_log_page(dev, ATA_LOG_SENSE_NCQ, 0, buf, 2);
@@ -1529,6 +1531,8 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
 
 	sense_valid = (u64)buf[8] | ((u64)buf[9] << 8) |
 		((u64)buf[10] << 16) | ((u64)buf[11] << 24);
+	extended_sense = get_unaligned_le16(&buf[14]);
+	aux_icc_valid = extended_sense & BIT(15);
 
 	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_EH) ||
@@ -1556,6 +1560,17 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
 			continue;
 		}
 
+		qc->result_tf.nsect = sense[6];
+		qc->result_tf.hob_nsect = sense[7];
+		qc->result_tf.lbal = sense[8];
+		qc->result_tf.lbam = sense[9];
+		qc->result_tf.lbah = sense[10];
+		qc->result_tf.hob_lbal = sense[11];
+		qc->result_tf.hob_lbam = sense[12];
+		qc->result_tf.hob_lbah = sense[13];
+		if (aux_icc_valid)
+			qc->result_tf.auxiliary = get_unaligned_le32(&sense[16]);
+
 		/* Set sense without also setting scsicmd->result */
 		scsi_build_sense_buffer(dev->flags & ATA_DFLAG_D_SENSE,
 					qc->scsicmd->sense_buffer, sk,
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 2796c0da8257..c0eb8c67a9ff 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2453,8 +2453,8 @@ static unsigned int ata_msense_control_ata_feature(struct ata_device *dev,
 	 */
 	put_unaligned_be16(ATA_FEATURE_SUB_MPAGE_LEN - 4, &buf[2]);
 
-	if (dev->flags & ATA_DFLAG_CDL)
-		buf[4] = 0x02; /* Support T2A and T2B pages */
+	if (dev->flags & ATA_DFLAG_CDL_ENABLED)
+		buf[4] = 0x02; /* T2A and T2B pages enabled */
 	else
 		buf[4] = 0;
 
@@ -3886,12 +3886,11 @@ static int ata_mselect_control_spg0(struct ata_queued_cmd *qc,
 }
 
 /*
- * Translate MODE SELECT control mode page, sub-pages f2h (ATA feature mode
+ * Translate MODE SELECT control mode page, sub-page f2h (ATA feature mode
  * page) into a SET FEATURES command.
  */
-static unsigned int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
-						    const u8 *buf, int len,
-						    u16 *fp)
+static int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
+					   const u8 *buf, int len, u16 *fp)
 {
 	struct ata_device *dev = qc->dev;
 	struct ata_taskfile *tf = &qc->tf;
@@ -3909,17 +3908,27 @@ static unsigned int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
 	/* Check cdl_ctrl */
 	switch (buf[0] & 0x03) {
 	case 0:
-		/* Disable CDL */
+		/* Disable CDL if it is enabled */
+		if (!(dev->flags & ATA_DFLAG_CDL_ENABLED))
+			return 0;
+		ata_dev_dbg(dev, "Disabling CDL\n");
 		cdl_action = 0;
 		dev->flags &= ~ATA_DFLAG_CDL_ENABLED;
 		break;
 	case 0x02:
-		/* Enable CDL T2A/T2B: NCQ priority must be disabled */
+		/*
+		 * Enable CDL if not already enabled. Since this is mutually
+		 * exclusive with NCQ priority, allow this only if NCQ priority
+		 * is disabled.
+		 */
+		if (dev->flags & ATA_DFLAG_CDL_ENABLED)
+			return 0;
 		if (dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLED) {
 			ata_dev_err(dev,
 				"NCQ priority must be disabled to enable CDL\n");
 			return -EINVAL;
 		}
+		ata_dev_dbg(dev, "Enabling CDL\n");
 		cdl_action = 1;
 		dev->flags |= ATA_DFLAG_CDL_ENABLED;
 		break;
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index 434f380114af..03dbaf4a13a7 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -223,10 +223,16 @@ static int pxa_ata_probe(struct platform_device *pdev)
 
 	ap->ioaddr.cmd_addr	= devm_ioremap(&pdev->dev, cmd_res->start,
 						resource_size(cmd_res));
+	if (!ap->ioaddr.cmd_addr)
+		return -ENOMEM;
 	ap->ioaddr.ctl_addr	= devm_ioremap(&pdev->dev, ctl_res->start,
 						resource_size(ctl_res));
+	if (!ap->ioaddr.ctl_addr)
+		return -ENOMEM;
 	ap->ioaddr.bmdma_addr	= devm_ioremap(&pdev->dev, dma_res->start,
 						resource_size(dma_res));
+	if (!ap->ioaddr.bmdma_addr)
+		return -ENOMEM;
 
 	/*
 	 * Adjust register offsets
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index a482741eb181..c3042eca6332 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -1117,9 +1117,14 @@ static int pdc20621_prog_dimm0(struct ata_host *host)
 	mmio += PDC_CHIP0_OFS;
 
 	for (i = 0; i < ARRAY_SIZE(pdc_i2c_read_data); i++)
-		pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
-				  pdc_i2c_read_data[i].reg,
-				  &spd0[pdc_i2c_read_data[i].ofs]);
+		if (!pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
+				       pdc_i2c_read_data[i].reg,
+				       &spd0[pdc_i2c_read_data[i].ofs])) {
+			dev_err(host->dev,
+				"Failed in i2c read at index %d: device=%#x, reg=%#x\n",
+				i, PDC_DIMM0_SPD_DEV_ADDRESS, pdc_i2c_read_data[i].reg);
+			return -EIO;
+		}
 
 	data |= (spd0[4] - 8) | ((spd0[21] != 0) << 3) | ((spd0[3]-11) << 4);
 	data |= ((spd0[17] / 4) << 6) | ((spd0[5] / 2) << 7) |
@@ -1284,6 +1289,8 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
 
 	/* Programming DIMM0 Module Control Register (index_CID0:80h) */
 	size = pdc20621_prog_dimm0(host);
+	if (size < 0)
+		return size;
 	dev_dbg(host->dev, "Local DIMM Size = %dMB\n", size);
 
 	/* Programming DIMM Module Global Control Register (index_CID0:88h) */
diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index afa4df4c5a3f..95717d509ca9 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -156,6 +156,16 @@
  *		},
  *		.ops = my_custom_ops,
  *	};
+ *
+ * Please note that such custom ops approach is valid, but it is hard to implement
+ * it right without global locks per-device to protect from auxiliary_drv removal
+ * during call to that ops. In addition, this implementation lacks proper module
+ * dependency, which causes to load/unload races between auxiliary parent and devices
+ * modules.
+ *
+ * The most easiest way to provide these ops reliably without needing to
+ * have a lock is to EXPORT_SYMBOL*() them and rely on already existing
+ * modules infrastructure for validity and correct dependencies chains.
  */
 
 static const struct auxiliary_device_id *auxiliary_match_id(const struct auxiliary_device_id *id,
diff --git a/drivers/base/base.h b/drivers/base/base.h
index 0042e4774b0c..123031a757d9 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -73,6 +73,7 @@ static inline void subsys_put(struct subsys_private *sp)
 		kset_put(&sp->subsys);
 }
 
+struct subsys_private *bus_to_subsys(const struct bus_type *bus);
 struct subsys_private *class_to_subsys(const struct class *class);
 
 struct driver_private {
@@ -180,6 +181,22 @@ int driver_add_groups(const struct device_driver *drv, const struct attribute_gr
 void driver_remove_groups(const struct device_driver *drv, const struct attribute_group **groups);
 void device_driver_detach(struct device *dev);
 
+static inline void device_set_driver(struct device *dev, const struct device_driver *drv)
+{
+	/*
+	 * Majority (all?) read accesses to dev->driver happens either
+	 * while holding device lock or in bus/driver code that is only
+	 * invoked when the device is bound to a driver and there is no
+	 * concern of the pointer being changed while it is being read.
+	 * However when reading device's uevent file we read driver pointer
+	 * without taking device lock (so we do not block there for
+	 * arbitrary amount of time). We use WRITE_ONCE() here to prevent
+	 * tearing so that READ_ONCE() can safely be used in uevent code.
+	 */
+	// FIXME - this cast should not be needed "soon"
+	WRITE_ONCE(dev->driver, (struct device_driver *)drv);
+}
+
 int devres_release_all(struct device *dev);
 void device_block_probing(void);
 void device_unblock_probing(void);
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 5ea3b03af9ba..5e75e1bce551 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -57,7 +57,7 @@ static int __must_check bus_rescan_devices_helper(struct device *dev,
  * NULL.  A call to subsys_put() must be done when finished with the pointer in
  * order for it to be properly freed.
  */
-static struct subsys_private *bus_to_subsys(const struct bus_type *bus)
+struct subsys_private *bus_to_subsys(const struct bus_type *bus)
 {
 	struct subsys_private *sp = NULL;
 	struct kobject *kobj;
diff --git a/drivers/base/core.c b/drivers/base/core.c
index d2f9d3a59d6b..cbc0099d8ef2 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2624,6 +2624,35 @@ static const char *dev_uevent_name(const struct kobject *kobj)
 	return NULL;
 }
 
+/*
+ * Try filling "DRIVER=<name>" uevent variable for a device. Because this
+ * function may race with binding and unbinding the device from a driver,
+ * we need to be careful. Binding is generally safe, at worst we miss the
+ * fact that the device is already bound to a driver (but the driver
+ * information that is delivered through uevents is best-effort, it may
+ * become obsolete as soon as it is generated anyways). Unbinding is more
+ * risky as driver pointer is transitioning to NULL, so READ_ONCE() should
+ * be used to make sure we are dealing with the same pointer, and to
+ * ensure that driver structure is not going to disappear from under us
+ * we take bus' drivers klist lock. The assumption that only registered
+ * driver can be bound to a device, and to unregister a driver bus code
+ * will take the same lock.
+ */
+static void dev_driver_uevent(const struct device *dev, struct kobj_uevent_env *env)
+{
+	struct subsys_private *sp = bus_to_subsys(dev->bus);
+
+	if (sp) {
+		scoped_guard(spinlock, &sp->klist_drivers.k_lock) {
+			struct device_driver *drv = READ_ONCE(dev->driver);
+			if (drv)
+				add_uevent_var(env, "DRIVER=%s", drv->name);
+		}
+
+		subsys_put(sp);
+	}
+}
+
 static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
 {
 	const struct device *dev = kobj_to_dev(kobj);
@@ -2655,8 +2684,8 @@ static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
 	if (dev->type && dev->type->name)
 		add_uevent_var(env, "DEVTYPE=%s", dev->type->name);
 
-	if (dev->driver)
-		add_uevent_var(env, "DRIVER=%s", dev->driver->name);
+	/* Add "DRIVER=%s" variable if the device is bound to a driver */
+	dev_driver_uevent(dev, env);
 
 	/* Add common DT information about the device */
 	of_device_uevent(dev, env);
@@ -2726,11 +2755,8 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr,
 	if (!env)
 		return -ENOMEM;
 
-	/* Synchronize with really_probe() */
-	device_lock(dev);
 	/* let the kset specific function add its keys */
 	retval = kset->uevent_ops->uevent(&dev->kobj, env);
-	device_unlock(dev);
 	if (retval)
 		goto out;
 
@@ -3700,7 +3726,7 @@ done:
 	device_pm_remove(dev);
 	dpm_sysfs_remove(dev);
  DPMError:
-	dev->driver = NULL;
+	device_set_driver(dev, NULL);
 	bus_remove_device(dev);
  BusError:
 	device_remove_attrs(dev);
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index a7e511849875..50651435577c 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -600,6 +600,7 @@ CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow);
 CPU_SHOW_VULN_FALLBACK(gds);
 CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling);
 CPU_SHOW_VULN_FALLBACK(ghostwrite);
+CPU_SHOW_VULN_FALLBACK(indirect_target_selection);
 
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
@@ -616,6 +617,7 @@ static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NU
 static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL);
 static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL);
 static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL);
+static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -633,6 +635,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_gather_data_sampling.attr,
 	&dev_attr_reg_file_data_sampling.attr,
 	&dev_attr_ghostwrite.attr,
+	&dev_attr_indirect_target_selection.attr,
 	NULL
 };
 
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index f0e4b4aba885..b526e0e0f52d 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -550,7 +550,7 @@ static void device_unbind_cleanup(struct device *dev)
 	arch_teardown_dma_ops(dev);
 	kfree(dev->dma_range_map);
 	dev->dma_range_map = NULL;
-	dev->driver = NULL;
+	device_set_driver(dev, NULL);
 	dev_set_drvdata(dev, NULL);
 	if (dev->pm_domain && dev->pm_domain->dismiss)
 		dev->pm_domain->dismiss(dev);
@@ -629,8 +629,7 @@ static int really_probe(struct device *dev, const struct device_driver *drv)
 	}
 
 re_probe:
-	// FIXME - this cast should not be needed "soon"
-	dev->driver = (struct device_driver *)drv;
+	device_set_driver(dev, drv);
 
 	/* If using pinctrl, bind pins now before probing */
 	ret = pinctrl_bind_pins(dev);
@@ -1014,7 +1013,7 @@ static int __device_attach(struct device *dev, bool allow_async)
 		if (ret == 0)
 			ret = 1;
 		else {
-			dev->driver = NULL;
+			device_set_driver(dev, NULL);
 			ret = 0;
 		}
 	} else {
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 6dd1a8860f1c..31bfb3194b4c 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -296,7 +296,7 @@ static int delete_path(const char *nodepath)
 	return err;
 }
 
-static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *stat)
+static int dev_mynode(struct device *dev, struct inode *inode)
 {
 	/* did we create it */
 	if (inode->i_private != &thread)
@@ -304,13 +304,13 @@ static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *sta
 
 	/* does the dev_t match */
 	if (is_blockdev(dev)) {
-		if (!S_ISBLK(stat->mode))
+		if (!S_ISBLK(inode->i_mode))
 			return 0;
 	} else {
-		if (!S_ISCHR(stat->mode))
+		if (!S_ISCHR(inode->i_mode))
 			return 0;
 	}
-	if (stat->rdev != dev->devt)
+	if (inode->i_rdev != dev->devt)
 		return 0;
 
 	/* ours */
@@ -321,20 +321,16 @@ static int handle_remove(const char *nodename, struct device *dev)
 {
 	struct path parent;
 	struct dentry *dentry;
-	struct kstat stat;
-	struct path p;
+	struct inode *inode;
 	int deleted = 0;
-	int err;
+	int err = 0;
 
 	dentry = kern_path_locked(nodename, &parent);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	p.mnt = parent.mnt;
-	p.dentry = dentry;
-	err = vfs_getattr(&p, &stat, STATX_TYPE | STATX_MODE,
-			  AT_STATX_SYNC_AS_STAT);
-	if (!err && dev_mynode(dev, d_inode(dentry), &stat)) {
+	inode = d_inode(dentry);
+	if (dev_mynode(dev, inode)) {
 		struct iattr newattrs;
 		/*
 		 * before unlinking this node, reset permissions
@@ -342,7 +338,7 @@ static int handle_remove(const char *nodename, struct device *dev)
 		 */
 		newattrs.ia_uid = GLOBAL_ROOT_UID;
 		newattrs.ia_gid = GLOBAL_ROOT_GID;
-		newattrs.ia_mode = stat.mode & ~0777;
+		newattrs.ia_mode = inode->i_mode & ~0777;
 		newattrs.ia_valid =
 			ATTR_UID|ATTR_GID|ATTR_MODE;
 		inode_lock(d_inode(dentry));
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 8f3a41d9bfaa..19469e7f88c2 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -816,21 +816,6 @@ static int add_memory_block(unsigned long block_id, unsigned long state,
 	return 0;
 }
 
-static int __init add_boot_memory_block(unsigned long base_section_nr)
-{
-	unsigned long nr;
-
-	for_each_present_section_nr(base_section_nr, nr) {
-		if (nr >= (base_section_nr + sections_per_block))
-			break;
-
-		return add_memory_block(memory_block_id(base_section_nr),
-					MEM_ONLINE, NULL, NULL);
-	}
-
-	return 0;
-}
-
 static int add_hotplug_memory_block(unsigned long block_id,
 				    struct vmem_altmap *altmap,
 				    struct memory_group *group)
@@ -957,7 +942,7 @@ static const struct attribute_group *memory_root_attr_groups[] = {
 void __init memory_dev_init(void)
 {
 	int ret;
-	unsigned long block_sz, nr;
+	unsigned long block_sz, block_id, nr;
 
 	/* Validate the configured memory block size */
 	block_sz = memory_block_size_bytes();
@@ -970,15 +955,23 @@ void __init memory_dev_init(void)
 		panic("%s() failed to register subsystem: %d\n", __func__, ret);
 
 	/*
-	 * Create entries for memory sections that were found
-	 * during boot and have been initialized
+	 * Create entries for memory sections that were found during boot
+	 * and have been initialized. Use @block_id to track the last
+	 * handled block and initialize it to an invalid value (ULONG_MAX)
+	 * to bypass the block ID matching check for the first present
+	 * block so that it can be covered.
 	 */
-	for (nr = 0; nr <= __highest_present_section_nr;
-	     nr += sections_per_block) {
-		ret = add_boot_memory_block(nr);
-		if (ret)
-			panic("%s() failed to add memory block: %d\n", __func__,
-			      ret);
+	block_id = ULONG_MAX;
+	for_each_present_section_nr(0, nr) {
+		if (block_id != ULONG_MAX && memory_block_id(nr) == block_id)
+			continue;
+
+		block_id = memory_block_id(nr);
+		ret = add_memory_block(block_id, MEM_ONLINE, NULL, NULL);
+		if (ret) {
+			panic("%s() failed to add memory block: %d\n",
+			      __func__, ret);
+		}
 	}
 }
 
diff --git a/drivers/base/module.c b/drivers/base/module.c
index 5bc71bea883a..218aaa096455 100644
--- a/drivers/base/module.c
+++ b/drivers/base/module.c
@@ -42,16 +42,13 @@ int module_add_driver(struct module *mod, const struct device_driver *drv)
 	if (mod)
 		mk = &mod->mkobj;
 	else if (drv->mod_name) {
-		struct kobject *mkobj;
-
-		/* Lookup built-in module entry in /sys/modules */
-		mkobj = kset_find_obj(module_kset, drv->mod_name);
-		if (mkobj) {
-			mk = container_of(mkobj, struct module_kobject, kobj);
+		/* Lookup or create built-in module entry in /sys/modules */
+		mk = lookup_or_create_module_kobject(drv->mod_name);
+		if (mk) {
 			/* remember our module structure */
 			drv->p->mkobj = mk;
-			/* kset_find_obj took a reference */
-			kobject_put(mkobj);
+			/* lookup_or_create_module_kobject took a reference */
+			kobject_put(&mk->kobj);
 		}
 	}
 
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 1813cfd0c4bd..cfccf3ff36e7 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1440,7 +1440,7 @@ static void platform_shutdown(struct device *_dev)
 
 static int platform_dma_configure(struct device *dev)
 {
-	struct platform_driver *drv = to_platform_driver(dev->driver);
+	struct device_driver *drv = READ_ONCE(dev->driver);
 	struct fwnode_handle *fwnode = dev_fwnode(dev);
 	enum dev_dma_attr attr;
 	int ret = 0;
@@ -1451,8 +1451,8 @@ static int platform_dma_configure(struct device *dev)
 		attr = acpi_get_dma_attr(to_acpi_device_node(fwnode));
 		ret = acpi_dma_configure(dev, attr);
 	}
-	/* @drv may not be valid when we're called from the IOMMU layer */
-	if (ret || !dev->driver || drv->driver_managed_dma)
+	/* @dev->driver may not be valid when we're called from the IOMMU layer */
+	if (ret || !drv || to_platform_driver(drv)->driver_managed_dma)
 		return ret;
 
 	ret = iommu_device_use_default_domain(dev);
diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index b1726a3515f6..5c78fa6ae772 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -1080,6 +1080,7 @@ void software_node_notify(struct device *dev)
 	if (!swnode)
 		return;
 
+	kobject_get(&swnode->kobj);
 	ret = sysfs_create_link(&dev->kobj, &swnode->kobj, "software_node");
 	if (ret)
 		return;
@@ -1089,8 +1090,6 @@ void software_node_notify(struct device *dev)
 		sysfs_remove_link(&dev->kobj, "software_node");
 		return;
 	}
-
-	kobject_get(&swnode->kobj);
 }
 
 void software_node_notify_remove(struct device *dev)
diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c
index 5f90bac6bb09..f021e27644e0 100644
--- a/drivers/bcma/driver_gpio.c
+++ b/drivers/bcma/driver_gpio.c
@@ -26,12 +26,14 @@ static int bcma_gpio_get_value(struct gpio_chip *chip, unsigned gpio)
 	return !!bcma_chipco_gpio_in(cc, 1 << gpio);
 }
 
-static void bcma_gpio_set_value(struct gpio_chip *chip, unsigned gpio,
-				int value)
+static int bcma_gpio_set_value(struct gpio_chip *chip, unsigned int gpio,
+			       int value)
 {
 	struct bcma_drv_cc *cc = gpiochip_get_data(chip);
 
 	bcma_chipco_gpio_out(cc, 1 << gpio, value ? 1 << gpio : 0);
+
+	return 0;
 }
 
 static int bcma_gpio_direction_input(struct gpio_chip *chip, unsigned gpio)
@@ -184,7 +186,7 @@ int bcma_gpio_init(struct bcma_drv_cc *cc)
 	chip->request		= bcma_gpio_request;
 	chip->free		= bcma_gpio_free;
 	chip->get		= bcma_gpio_get_value;
-	chip->set		= bcma_gpio_set_value;
+	chip->set_rv		= bcma_gpio_set_value;
 	chip->direction_input	= bcma_gpio_direction_input;
 	chip->direction_output	= bcma_gpio_direction_output;
 	chip->parent		= bus->dev;
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 2551ebf88dda..e48b24be45ee 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -388,12 +388,6 @@ config BLK_DEV_UBLK
 	  definition isn't finalized yet, and might change according to future
 	  requirement, so mark is as experimental now.
 
-	  Say Y if you want to get better performance because task_work_add()
-	  can be used in IO path for replacing io_uring cmd, which will become
-	  shared between IO tasks and ubq daemon, meantime task_work_add() can
-	  can handle batch more effectively, but task_work_add() isn't exported
-	  for module, so ublk has to be built to kernel.
-
 config BLKDEV_UBLK_LEGACY_OPCODES
 	bool "Support legacy command opcode"
 	depends on BLK_DEV_UBLK
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 674527d770dc..b8ba7de08753 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -211,72 +211,6 @@ static void loop_set_size(struct loop_device *lo, loff_t size)
 		kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 }
 
-static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
-{
-	struct iov_iter i;
-	ssize_t bw;
-
-	iov_iter_bvec(&i, ITER_SOURCE, bvec, 1, bvec->bv_len);
-
-	bw = vfs_iter_write(file, &i, ppos, 0);
-
-	if (likely(bw ==  bvec->bv_len))
-		return 0;
-
-	printk_ratelimited(KERN_ERR
-		"loop: Write error at byte offset %llu, length %i.\n",
-		(unsigned long long)*ppos, bvec->bv_len);
-	if (bw >= 0)
-		bw = -EIO;
-	return bw;
-}
-
-static int lo_write_simple(struct loop_device *lo, struct request *rq,
-		loff_t pos)
-{
-	struct bio_vec bvec;
-	struct req_iterator iter;
-	int ret = 0;
-
-	rq_for_each_segment(bvec, rq, iter) {
-		ret = lo_write_bvec(lo->lo_backing_file, &bvec, &pos);
-		if (ret < 0)
-			break;
-		cond_resched();
-	}
-
-	return ret;
-}
-
-static int lo_read_simple(struct loop_device *lo, struct request *rq,
-		loff_t pos)
-{
-	struct bio_vec bvec;
-	struct req_iterator iter;
-	struct iov_iter i;
-	ssize_t len;
-
-	rq_for_each_segment(bvec, rq, iter) {
-		iov_iter_bvec(&i, ITER_DEST, &bvec, 1, bvec.bv_len);
-		len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
-		if (len < 0)
-			return len;
-
-		flush_dcache_page(bvec.bv_page);
-
-		if (len != bvec.bv_len) {
-			struct bio *bio;
-
-			__rq_for_each_bio(bio, rq)
-				zero_fill_bio(bio);
-			break;
-		}
-		cond_resched();
-	}
-
-	return 0;
-}
-
 static void loop_clear_limits(struct loop_device *lo, int mode)
 {
 	struct queue_limits lim = queue_limits_start_update(lo->lo_queue);
@@ -342,7 +276,7 @@ static void lo_complete_rq(struct request *rq)
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	blk_status_t ret = BLK_STS_OK;
 
-	if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
+	if (cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
 	    req_op(rq) != REQ_OP_READ) {
 		if (cmd->ret < 0)
 			ret = errno_to_blk_status(cmd->ret);
@@ -358,14 +292,13 @@ static void lo_complete_rq(struct request *rq)
 		cmd->ret = 0;
 		blk_mq_requeue_request(rq, true);
 	} else {
-		if (cmd->use_aio) {
-			struct bio *bio = rq->bio;
+		struct bio *bio = rq->bio;
 
-			while (bio) {
-				zero_fill_bio(bio);
-				bio = bio->bi_next;
-			}
+		while (bio) {
+			zero_fill_bio(bio);
+			bio = bio->bi_next;
 		}
+
 		ret = BLK_STS_IOERR;
 end_io:
 		blk_mq_end_request(rq, ret);
@@ -445,9 +378,14 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 
 	cmd->iocb.ki_pos = pos;
 	cmd->iocb.ki_filp = file;
-	cmd->iocb.ki_complete = lo_rw_aio_complete;
-	cmd->iocb.ki_flags = IOCB_DIRECT;
-	cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
+	cmd->iocb.ki_ioprio = req_get_ioprio(rq);
+	if (cmd->use_aio) {
+		cmd->iocb.ki_complete = lo_rw_aio_complete;
+		cmd->iocb.ki_flags = IOCB_DIRECT;
+	} else {
+		cmd->iocb.ki_complete = NULL;
+		cmd->iocb.ki_flags = 0;
+	}
 
 	if (rw == ITER_SOURCE)
 		ret = file->f_op->write_iter(&cmd->iocb, &iter);
@@ -458,7 +396,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 
 	if (ret != -EIOCBQUEUED)
 		lo_rw_aio_complete(&cmd->iocb, ret);
-	return 0;
+	return -EIOCBQUEUED;
 }
 
 static int do_req_filebacked(struct loop_device *lo, struct request *rq)
@@ -466,15 +404,6 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset;
 
-	/*
-	 * lo_write_simple and lo_read_simple should have been covered
-	 * by io submit style function like lo_rw_aio(), one blocker
-	 * is that lo_read_simple() need to call flush_dcache_page after
-	 * the page is written from kernel, and it isn't easy to handle
-	 * this in io submit style function which submits all segments
-	 * of the req at one time. And direct read IO doesn't need to
-	 * run flush_dcache_page().
-	 */
 	switch (req_op(rq)) {
 	case REQ_OP_FLUSH:
 		return lo_req_flush(lo, rq);
@@ -490,15 +419,9 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	case REQ_OP_DISCARD:
 		return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
 	case REQ_OP_WRITE:
-		if (cmd->use_aio)
-			return lo_rw_aio(lo, cmd, pos, ITER_SOURCE);
-		else
-			return lo_write_simple(lo, rq, pos);
+		return lo_rw_aio(lo, cmd, pos, ITER_SOURCE);
 	case REQ_OP_READ:
-		if (cmd->use_aio)
-			return lo_rw_aio(lo, cmd, pos, ITER_DEST);
-		else
-			return lo_read_simple(lo, rq, pos);
+		return lo_rw_aio(lo, cmd, pos, ITER_DEST);
 	default:
 		WARN_ON_ONCE(1);
 		return -EIO;
@@ -582,6 +505,17 @@ static void loop_assign_backing_file(struct loop_device *lo, struct file *file)
 	lo->lo_min_dio_size = loop_query_min_dio_size(lo);
 }
 
+static int loop_check_backing_file(struct file *file)
+{
+	if (!file->f_op->read_iter)
+		return -EINVAL;
+
+	if ((file->f_mode & FMODE_WRITE) && !file->f_op->write_iter)
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * loop_change_fd switched the backing store of a loopback device to
  * a new file. This is useful for operating system installers to free up
@@ -603,6 +537,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (!file)
 		return -EBADF;
 
+	error = loop_check_backing_file(file);
+	if (error)
+		return error;
+
 	/* suppress uevents while reconfiguring the device */
 	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1);
 
@@ -662,19 +600,20 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	 * dependency.
 	 */
 	fput(old_file);
+	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
 	if (partscan)
 		loop_reread_partitions(lo);
 
 	error = 0;
 done:
-	/* enable and uncork uevent now that we are done */
-	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
+	kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 	return error;
 
 out_err:
 	loop_global_unlock(lo, is_loop);
 out_putf:
 	fput(file);
+	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
 	goto done;
 }
 
@@ -1039,6 +978,14 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 
 	if (!file)
 		return -EBADF;
+
+	if ((mode & BLK_OPEN_WRITE) && !file->f_op->write_iter)
+		return -EINVAL;
+
+	error = loop_check_backing_file(file);
+	if (error)
+		return error;
+
 	is_loop = is_loop_device(file);
 
 	/* This is safe, since we have a reference from open(). */
@@ -1129,8 +1076,8 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	if (partscan)
 		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 
-	/* enable and uncork uevent now that we are done */
 	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
+	kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 
 	loop_global_unlock(lo, is_loop);
 	if (partscan)
@@ -1921,7 +1868,6 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 	struct loop_device *lo = rq->q->queuedata;
 	int ret = 0;
 	struct mem_cgroup *old_memcg = NULL;
-	const bool use_aio = cmd->use_aio;
 
 	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
 		ret = -EIO;
@@ -1951,7 +1897,7 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 	}
  failed:
 	/* complete non-aio request */
-	if (!use_aio || ret) {
+	if (ret != -EIOCBQUEUED) {
 		if (ret == -EOPNOTSUPP)
 			cmd->ret = ret;
 		else
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 3bb9cee0a9b5..aa163ae9b2aa 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -2031,7 +2031,7 @@ static int null_add_dev(struct nullb_device *dev)
 	nullb->disk->minors = 1;
 	nullb->disk->fops = &null_ops;
 	nullb->disk->private_data = nullb;
-	strscpy_pad(nullb->disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+	strscpy(nullb->disk->disk_name, nullb->disk_name);
 
 	if (nullb->dev->zoned) {
 		rv = null_register_zoned_dev(nullb);
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index cdb1543fa4a9..dc104c025cd5 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -123,15 +123,6 @@ struct ublk_uring_cmd_pdu {
 #define UBLK_IO_FLAG_OWNED_BY_SRV 0x02
 
 /*
- * IO command is aborted, so this flag is set in case of
- * !UBLK_IO_FLAG_ACTIVE.
- *
- * After this flag is observed, any pending or new incoming request
- * associated with this io command will be failed immediately
- */
-#define UBLK_IO_FLAG_ABORTED 0x04
-
-/*
  * UBLK_IO_FLAG_NEED_GET_DATA is set because IO command requires
  * get data buffer address from ublksrv.
  *
@@ -199,8 +190,6 @@ struct ublk_device {
 	struct completion	completion;
 	unsigned int		nr_queues_ready;
 	unsigned int		nr_privileged_daemon;
-
-	struct work_struct	nosrv_work;
 };
 
 /* header of ublk_params */
@@ -209,18 +198,13 @@ struct ublk_params_header {
 	__u32	types;
 };
 
-static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq);
-
+static void ublk_stop_dev_unlocked(struct ublk_device *ub);
+static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq);
 static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
-		struct ublk_queue *ubq, int tag, size_t offset);
+		const struct ublk_queue *ubq, int tag, size_t offset);
 static inline unsigned int ublk_req_build_flags(struct request *req);
 static inline struct ublksrv_io_desc *ublk_get_iod(struct ublk_queue *ubq,
 						   int tag);
-static inline bool ublk_dev_is_user_copy(const struct ublk_device *ub)
-{
-	return ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY);
-}
-
 static inline bool ublk_dev_is_zoned(const struct ublk_device *ub)
 {
 	return ub->dev_info.flags & UBLK_F_ZONED;
@@ -620,14 +604,19 @@ static void ublk_apply_params(struct ublk_device *ub)
 		ublk_dev_param_zoned_apply(ub);
 }
 
+static inline bool ublk_support_zero_copy(const struct ublk_queue *ubq)
+{
+	return ubq->flags & UBLK_F_SUPPORT_ZERO_COPY;
+}
+
 static inline bool ublk_support_user_copy(const struct ublk_queue *ubq)
 {
-	return ubq->flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY);
+	return ubq->flags & UBLK_F_USER_COPY;
 }
 
 static inline bool ublk_need_map_io(const struct ublk_queue *ubq)
 {
-	return !ublk_support_user_copy(ubq);
+	return !ublk_support_user_copy(ubq) && !ublk_support_zero_copy(ubq);
 }
 
 static inline bool ublk_need_req_ref(const struct ublk_queue *ubq)
@@ -635,8 +624,11 @@ static inline bool ublk_need_req_ref(const struct ublk_queue *ubq)
 	/*
 	 * read()/write() is involved in user copy, so request reference
 	 * has to be grabbed
+	 *
+	 * for zero copy, request buffer need to be registered to io_uring
+	 * buffer table, so reference is needed
 	 */
-	return ublk_support_user_copy(ubq);
+	return ublk_support_user_copy(ubq) || ublk_support_zero_copy(ubq);
 }
 
 static inline void ublk_init_req_ref(const struct ublk_queue *ubq,
@@ -1074,7 +1066,7 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu(
 
 static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq)
 {
-	return ubq->ubq_daemon->flags & PF_EXITING;
+	return !ubq->ubq_daemon || ubq->ubq_daemon->flags & PF_EXITING;
 }
 
 /* todo: handle partial completion */
@@ -1085,12 +1077,6 @@ static inline void __ublk_complete_rq(struct request *req)
 	unsigned int unmapped_bytes;
 	blk_status_t res = BLK_STS_OK;
 
-	/* called from ublk_abort_queue() code path */
-	if (io->flags & UBLK_IO_FLAG_ABORTED) {
-		res = BLK_STS_IOERR;
-		goto exit;
-	}
-
 	/* failed read IO if nothing is read */
 	if (!io->res && req_op(req) == REQ_OP_READ)
 		io->res = -EIO;
@@ -1140,47 +1126,6 @@ static void ublk_complete_rq(struct kref *ref)
 	__ublk_complete_rq(req);
 }
 
-static void ublk_do_fail_rq(struct request *req)
-{
-	struct ublk_queue *ubq = req->mq_hctx->driver_data;
-
-	if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
-		blk_mq_requeue_request(req, false);
-	else
-		__ublk_complete_rq(req);
-}
-
-static void ublk_fail_rq_fn(struct kref *ref)
-{
-	struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data,
-			ref);
-	struct request *req = blk_mq_rq_from_pdu(data);
-
-	ublk_do_fail_rq(req);
-}
-
-/*
- * Since ublk_rq_task_work_cb always fails requests immediately during
- * exiting, __ublk_fail_req() is only called from abort context during
- * exiting. So lock is unnecessary.
- *
- * Also aborting may not be started yet, keep in mind that one failed
- * request may be issued by block layer again.
- */
-static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
-		struct request *req)
-{
-	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
-
-	if (ublk_need_req_ref(ubq)) {
-		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
-
-		kref_put(&data->ref, ublk_fail_rq_fn);
-	} else {
-		ublk_do_fail_rq(req);
-	}
-}
-
 static void ubq_complete_io_cmd(struct ublk_io *io, int res,
 				unsigned issue_flags)
 {
@@ -1336,8 +1281,6 @@ static void ublk_queue_cmd_list(struct ublk_queue *ubq, struct rq_list *l)
 static enum blk_eh_timer_return ublk_timeout(struct request *rq)
 {
 	struct ublk_queue *ubq = rq->mq_hctx->driver_data;
-	unsigned int nr_inflight = 0;
-	int i;
 
 	if (ubq->flags & UBLK_F_UNPRIVILEGED_DEV) {
 		if (!ubq->timeout) {
@@ -1348,26 +1291,6 @@ static enum blk_eh_timer_return ublk_timeout(struct request *rq)
 		return BLK_EH_DONE;
 	}
 
-	if (!ubq_daemon_is_dying(ubq))
-		return BLK_EH_RESET_TIMER;
-
-	for (i = 0; i < ubq->q_depth; i++) {
-		struct ublk_io *io = &ubq->ios[i];
-
-		if (!(io->flags & UBLK_IO_FLAG_ACTIVE))
-			nr_inflight++;
-	}
-
-	/* cancelable uring_cmd can't help us if all commands are in-flight */
-	if (nr_inflight == ubq->q_depth) {
-		struct ublk_device *ub = ubq->dev;
-
-		if (ublk_abort_requests(ub, ubq)) {
-			schedule_work(&ub->nosrv_work);
-		}
-		return BLK_EH_DONE;
-	}
-
 	return BLK_EH_RESET_TIMER;
 }
 
@@ -1470,6 +1393,37 @@ static const struct blk_mq_ops ublk_mq_ops = {
 	.timeout	= ublk_timeout,
 };
 
+static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
+{
+	int i;
+
+	/* All old ioucmds have to be completed */
+	ubq->nr_io_ready = 0;
+
+	/*
+	 * old daemon is PF_EXITING, put it now
+	 *
+	 * It could be NULL in case of closing one quisced device.
+	 */
+	if (ubq->ubq_daemon)
+		put_task_struct(ubq->ubq_daemon);
+	/* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */
+	ubq->ubq_daemon = NULL;
+	ubq->timeout = false;
+
+	for (i = 0; i < ubq->q_depth; i++) {
+		struct ublk_io *io = &ubq->ios[i];
+
+		/*
+		 * UBLK_IO_FLAG_CANCELED is kept for avoiding to touch
+		 * io->cmd
+		 */
+		io->flags &= UBLK_IO_FLAG_CANCELED;
+		io->cmd = NULL;
+		io->addr = 0;
+	}
+}
+
 static int ublk_ch_open(struct inode *inode, struct file *filp)
 {
 	struct ublk_device *ub = container_of(inode->i_cdev,
@@ -1481,10 +1435,119 @@ static int ublk_ch_open(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static void ublk_reset_ch_dev(struct ublk_device *ub)
+{
+	int i;
+
+	for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
+		ublk_queue_reinit(ub, ublk_get_queue(ub, i));
+
+	/* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */
+	ub->mm = NULL;
+	ub->nr_queues_ready = 0;
+	ub->nr_privileged_daemon = 0;
+}
+
+static struct gendisk *ublk_get_disk(struct ublk_device *ub)
+{
+	struct gendisk *disk;
+
+	spin_lock(&ub->lock);
+	disk = ub->ub_disk;
+	if (disk)
+		get_device(disk_to_dev(disk));
+	spin_unlock(&ub->lock);
+
+	return disk;
+}
+
+static void ublk_put_disk(struct gendisk *disk)
+{
+	if (disk)
+		put_device(disk_to_dev(disk));
+}
+
 static int ublk_ch_release(struct inode *inode, struct file *filp)
 {
 	struct ublk_device *ub = filp->private_data;
+	struct gendisk *disk;
+	int i;
+
+	/*
+	 * disk isn't attached yet, either device isn't live, or it has
+	 * been removed already, so we needn't to do anything
+	 */
+	disk = ublk_get_disk(ub);
+	if (!disk)
+		goto out;
+
+	/*
+	 * All uring_cmd are done now, so abort any request outstanding to
+	 * the ublk server
+	 *
+	 * This can be done in lockless way because ublk server has been
+	 * gone
+	 *
+	 * More importantly, we have to provide forward progress guarantee
+	 * without holding ub->mutex, otherwise control task grabbing
+	 * ub->mutex triggers deadlock
+	 *
+	 * All requests may be inflight, so ->canceling may not be set, set
+	 * it now.
+	 */
+	for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
+		struct ublk_queue *ubq = ublk_get_queue(ub, i);
 
+		ubq->canceling = true;
+		ublk_abort_queue(ub, ubq);
+	}
+	blk_mq_kick_requeue_list(disk->queue);
+
+	/*
+	 * All infligh requests have been completed or requeued and any new
+	 * request will be failed or requeued via `->canceling` now, so it is
+	 * fine to grab ub->mutex now.
+	 */
+	mutex_lock(&ub->mutex);
+
+	/* double check after grabbing lock */
+	if (!ub->ub_disk)
+		goto unlock;
+
+	/*
+	 * Transition the device to the nosrv state. What exactly this
+	 * means depends on the recovery flags
+	 */
+	blk_mq_quiesce_queue(disk->queue);
+	if (ublk_nosrv_should_stop_dev(ub)) {
+		/*
+		 * Allow any pending/future I/O to pass through quickly
+		 * with an error. This is needed because del_gendisk
+		 * waits for all pending I/O to complete
+		 */
+		for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
+			ublk_get_queue(ub, i)->force_abort = true;
+		blk_mq_unquiesce_queue(disk->queue);
+
+		ublk_stop_dev_unlocked(ub);
+	} else {
+		if (ublk_nosrv_dev_should_queue_io(ub)) {
+			/* ->canceling is set and all requests are aborted */
+			ub->dev_info.state = UBLK_S_DEV_QUIESCED;
+		} else {
+			ub->dev_info.state = UBLK_S_DEV_FAIL_IO;
+			for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
+				ublk_get_queue(ub, i)->fail_io = true;
+		}
+		blk_mq_unquiesce_queue(disk->queue);
+	}
+unlock:
+	mutex_unlock(&ub->mutex);
+	ublk_put_disk(disk);
+
+	/* all uring_cmd has been done now, reset device & ubq */
+	ublk_reset_ch_dev(ub);
+out:
 	clear_bit(UB_STATE_OPEN, &ub->state);
 	return 0;
 }
@@ -1551,10 +1614,26 @@ static void ublk_commit_completion(struct ublk_device *ub,
 		ublk_put_req_ref(ubq, req);
 }
 
+static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
+		struct request *req)
+{
+	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
+
+	if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
+		blk_mq_requeue_request(req, false);
+	else {
+		io->res = -EIO;
+		__ublk_complete_rq(req);
+	}
+}
+
 /*
- * Called from ubq_daemon context via cancel fn, meantime quiesce ublk
- * blk-mq queue, so we are called exclusively with blk-mq and ubq_daemon
- * context, so everything is serialized.
+ * Called from ublk char device release handler, when any uring_cmd is
+ * done, meantime request queue is "quiesced" since all inflight requests
+ * can't be completed because ublk server is dead.
+ *
+ * So no one can hold our request IO reference any more, simply ignore the
+ * reference, and complete the request immediately
  */
 static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
 {
@@ -1571,46 +1650,29 @@ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
 			 * will do it
 			 */
 			rq = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], i);
-			if (rq && blk_mq_request_started(rq)) {
-				io->flags |= UBLK_IO_FLAG_ABORTED;
+			if (rq && blk_mq_request_started(rq))
 				__ublk_fail_req(ubq, io, rq);
-			}
 		}
 	}
 }
 
 /* Must be called when queue is frozen */
-static bool ublk_mark_queue_canceling(struct ublk_queue *ubq)
+static void ublk_mark_queue_canceling(struct ublk_queue *ubq)
 {
-	bool canceled;
-
 	spin_lock(&ubq->cancel_lock);
-	canceled = ubq->canceling;
-	if (!canceled)
+	if (!ubq->canceling)
 		ubq->canceling = true;
 	spin_unlock(&ubq->cancel_lock);
-
-	return canceled;
 }
 
-static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq)
+static void ublk_start_cancel(struct ublk_queue *ubq)
 {
-	bool was_canceled = ubq->canceling;
-	struct gendisk *disk;
-
-	if (was_canceled)
-		return false;
-
-	spin_lock(&ub->lock);
-	disk = ub->ub_disk;
-	if (disk)
-		get_device(disk_to_dev(disk));
-	spin_unlock(&ub->lock);
+	struct ublk_device *ub = ubq->dev;
+	struct gendisk *disk = ublk_get_disk(ub);
 
 	/* Our disk has been dead */
 	if (!disk)
-		return false;
-
+		return;
 	/*
 	 * Now we are serialized with ublk_queue_rq()
 	 *
@@ -1619,25 +1681,36 @@ static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq)
 	 * touch completed uring_cmd
 	 */
 	blk_mq_quiesce_queue(disk->queue);
-	was_canceled = ublk_mark_queue_canceling(ubq);
-	if (!was_canceled) {
-		/* abort queue is for making forward progress */
-		ublk_abort_queue(ub, ubq);
-	}
+	ublk_mark_queue_canceling(ubq);
 	blk_mq_unquiesce_queue(disk->queue);
-	put_device(disk_to_dev(disk));
-
-	return !was_canceled;
+	ublk_put_disk(disk);
 }
 
-static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io,
+static void ublk_cancel_cmd(struct ublk_queue *ubq, unsigned tag,
 		unsigned int issue_flags)
 {
+	struct ublk_io *io = &ubq->ios[tag];
+	struct ublk_device *ub = ubq->dev;
+	struct request *req;
 	bool done;
 
 	if (!(io->flags & UBLK_IO_FLAG_ACTIVE))
 		return;
 
+	/*
+	 * Don't try to cancel this command if the request is started for
+	 * avoiding race between io_uring_cmd_done() and
+	 * io_uring_cmd_complete_in_task().
+	 *
+	 * Either the started request will be aborted via __ublk_abort_rq(),
+	 * then this uring_cmd is canceled next time, or it will be done in
+	 * task work function ublk_dispatch_req() because io_uring guarantees
+	 * that ublk_dispatch_req() is always called
+	 */
+	req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
+	if (req && blk_mq_request_started(req) && req->tag == tag)
+		return;
+
 	spin_lock(&ubq->cancel_lock);
 	done = !!(io->flags & UBLK_IO_FLAG_CANCELED);
 	if (!done)
@@ -1651,6 +1724,17 @@ static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io,
 /*
  * The ublk char device won't be closed when calling cancel fn, so both
  * ublk device and queue are guaranteed to be live
+ *
+ * Two-stage cancel:
+ *
+ * - make every active uring_cmd done in ->cancel_fn()
+ *
+ * - aborting inflight ublk IO requests in ublk char device release handler,
+ *   which depends on 1st stage because device can only be closed iff all
+ *   uring_cmd are done
+ *
+ * Do _not_ try to acquire ub->mutex before all inflight requests are
+ * aborted, otherwise deadlock may be caused.
  */
 static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
 		unsigned int issue_flags)
@@ -1658,9 +1742,6 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
 	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
 	struct ublk_queue *ubq = pdu->ubq;
 	struct task_struct *task;
-	struct ublk_device *ub;
-	bool need_schedule;
-	struct ublk_io *io;
 
 	if (WARN_ON_ONCE(!ubq))
 		return;
@@ -1672,16 +1753,11 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
 	if (WARN_ON_ONCE(task && task != ubq->ubq_daemon))
 		return;
 
-	ub = ubq->dev;
-	need_schedule = ublk_abort_requests(ub, ubq);
-
-	io = &ubq->ios[pdu->tag];
-	WARN_ON_ONCE(io->cmd != cmd);
-	ublk_cancel_cmd(ubq, io, issue_flags);
+	if (!ubq->canceling)
+		ublk_start_cancel(ubq);
 
-	if (need_schedule) {
-		schedule_work(&ub->nosrv_work);
-	}
+	WARN_ON_ONCE(ubq->ios[pdu->tag].cmd != cmd);
+	ublk_cancel_cmd(ubq, pdu->tag, issue_flags);
 }
 
 static inline bool ublk_queue_ready(struct ublk_queue *ubq)
@@ -1694,7 +1770,7 @@ static void ublk_cancel_queue(struct ublk_queue *ubq)
 	int i;
 
 	for (i = 0; i < ubq->q_depth; i++)
-		ublk_cancel_cmd(ubq, &ubq->ios[i], IO_URING_F_UNLOCKED);
+		ublk_cancel_cmd(ubq, i, IO_URING_F_UNLOCKED);
 }
 
 /* Cancel all pending commands, must be called after del_gendisk() returns */
@@ -1732,33 +1808,20 @@ static void ublk_wait_tagset_rqs_idle(struct ublk_device *ub)
 	}
 }
 
-static void __ublk_quiesce_dev(struct ublk_device *ub)
-{
-	pr_devel("%s: quiesce ub: dev_id %d state %s\n",
-			__func__, ub->dev_info.dev_id,
-			ub->dev_info.state == UBLK_S_DEV_LIVE ?
-			"LIVE" : "QUIESCED");
-	blk_mq_quiesce_queue(ub->ub_disk->queue);
-	ublk_wait_tagset_rqs_idle(ub);
-	ub->dev_info.state = UBLK_S_DEV_QUIESCED;
-}
-
-static void ublk_unquiesce_dev(struct ublk_device *ub)
+static void ublk_force_abort_dev(struct ublk_device *ub)
 {
 	int i;
 
-	pr_devel("%s: unquiesce ub: dev_id %d state %s\n",
+	pr_devel("%s: force abort ub: dev_id %d state %s\n",
 			__func__, ub->dev_info.dev_id,
 			ub->dev_info.state == UBLK_S_DEV_LIVE ?
 			"LIVE" : "QUIESCED");
-	/* quiesce_work has run. We let requeued rqs be aborted
-	 * before running fallback_wq. "force_abort" must be seen
-	 * after request queue is unqiuesced. Then del_gendisk()
-	 * can move on.
-	 */
+	blk_mq_quiesce_queue(ub->ub_disk->queue);
+	if (ub->dev_info.state == UBLK_S_DEV_LIVE)
+		ublk_wait_tagset_rqs_idle(ub);
+
 	for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
 		ublk_get_queue(ub, i)->force_abort = true;
-
 	blk_mq_unquiesce_queue(ub->ub_disk->queue);
 	/* We may have requeued some rqs in ublk_quiesce_queue() */
 	blk_mq_kick_requeue_list(ub->ub_disk->queue);
@@ -1779,61 +1842,51 @@ static struct gendisk *ublk_detach_disk(struct ublk_device *ub)
 	return disk;
 }
 
-static void ublk_stop_dev(struct ublk_device *ub)
+static void ublk_stop_dev_unlocked(struct ublk_device *ub)
+	__must_hold(&ub->mutex)
 {
 	struct gendisk *disk;
 
-	mutex_lock(&ub->mutex);
 	if (ub->dev_info.state == UBLK_S_DEV_DEAD)
-		goto unlock;
-	if (ublk_nosrv_dev_should_queue_io(ub)) {
-		if (ub->dev_info.state == UBLK_S_DEV_LIVE)
-			__ublk_quiesce_dev(ub);
-		ublk_unquiesce_dev(ub);
-	}
+		return;
+
+	if (ublk_nosrv_dev_should_queue_io(ub))
+		ublk_force_abort_dev(ub);
 	del_gendisk(ub->ub_disk);
 	disk = ublk_detach_disk(ub);
 	put_disk(disk);
- unlock:
+}
+
+static void ublk_stop_dev(struct ublk_device *ub)
+{
+	mutex_lock(&ub->mutex);
+	ublk_stop_dev_unlocked(ub);
 	mutex_unlock(&ub->mutex);
 	ublk_cancel_dev(ub);
 }
 
-static void ublk_nosrv_work(struct work_struct *work)
+/* reset ublk io_uring queue & io flags */
+static void ublk_reset_io_flags(struct ublk_device *ub)
 {
-	struct ublk_device *ub =
-		container_of(work, struct ublk_device, nosrv_work);
-	int i;
+	int i, j;
 
-	if (ublk_nosrv_should_stop_dev(ub)) {
-		ublk_stop_dev(ub);
-		return;
-	}
+	for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
+		struct ublk_queue *ubq = ublk_get_queue(ub, i);
 
-	mutex_lock(&ub->mutex);
-	if (ub->dev_info.state != UBLK_S_DEV_LIVE)
-		goto unlock;
-
-	if (ublk_nosrv_dev_should_queue_io(ub)) {
-		__ublk_quiesce_dev(ub);
-	} else {
-		blk_mq_quiesce_queue(ub->ub_disk->queue);
-		ub->dev_info.state = UBLK_S_DEV_FAIL_IO;
-		for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
-			ublk_get_queue(ub, i)->fail_io = true;
-		}
-		blk_mq_unquiesce_queue(ub->ub_disk->queue);
+		/* UBLK_IO_FLAG_CANCELED can be cleared now */
+		spin_lock(&ubq->cancel_lock);
+		for (j = 0; j < ubq->q_depth; j++)
+			ubq->ios[j].flags &= ~UBLK_IO_FLAG_CANCELED;
+		spin_unlock(&ubq->cancel_lock);
+		ubq->canceling = false;
+		ubq->fail_io = false;
 	}
-
- unlock:
-	mutex_unlock(&ub->mutex);
-	ublk_cancel_dev(ub);
 }
 
 /* device can only be started after all IOs are ready */
 static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
+	__must_hold(&ub->mutex)
 {
-	mutex_lock(&ub->mutex);
 	ubq->nr_io_ready++;
 	if (ublk_queue_ready(ubq)) {
 		ubq->ubq_daemon = current;
@@ -1843,18 +1896,12 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
 		if (capable(CAP_SYS_ADMIN))
 			ub->nr_privileged_daemon++;
 	}
-	if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues)
-		complete_all(&ub->completion);
-	mutex_unlock(&ub->mutex);
-}
-
-static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id,
-		int tag)
-{
-	struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
-	struct request *req = blk_mq_tag_to_rq(ub->tag_set.tags[q_id], tag);
 
-	ublk_queue_cmd(ubq, req);
+	if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues) {
+		/* now we are ready for handling ublk io request */
+		ublk_reset_io_flags(ub);
+		complete_all(&ub->completion);
+	}
 }
 
 static inline int ublk_check_cmd_op(u32 cmd_op)
@@ -1902,13 +1949,20 @@ static void ublk_io_release(void *priv)
 }
 
 static int ublk_register_io_buf(struct io_uring_cmd *cmd,
-				struct ublk_queue *ubq, unsigned int tag,
+				const struct ublk_queue *ubq, unsigned int tag,
 				unsigned int index, unsigned int issue_flags)
 {
 	struct ublk_device *ub = cmd->file->private_data;
+	const struct ublk_io *io = &ubq->ios[tag];
 	struct request *req;
 	int ret;
 
+	if (!ublk_support_zero_copy(ubq))
+		return -EINVAL;
+
+	if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
+		return -EINVAL;
+
 	req = __ublk_check_and_get_req(ub, ubq, tag, 0);
 	if (!req)
 		return -EINVAL;
@@ -1924,11 +1978,66 @@ static int ublk_register_io_buf(struct io_uring_cmd *cmd,
 }
 
 static int ublk_unregister_io_buf(struct io_uring_cmd *cmd,
+				  const struct ublk_queue *ubq, unsigned int tag,
 				  unsigned int index, unsigned int issue_flags)
 {
+	const struct ublk_io *io = &ubq->ios[tag];
+
+	if (!ublk_support_zero_copy(ubq))
+		return -EINVAL;
+
+	if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
+		return -EINVAL;
+
 	return io_buffer_unregister_bvec(cmd, index, issue_flags);
 }
 
+static int ublk_fetch(struct io_uring_cmd *cmd, struct ublk_queue *ubq,
+		      struct ublk_io *io, __u64 buf_addr)
+{
+	struct ublk_device *ub = ubq->dev;
+	int ret = 0;
+
+	/*
+	 * When handling FETCH command for setting up ublk uring queue,
+	 * ub->mutex is the innermost lock, and we won't block for handling
+	 * FETCH, so it is fine even for IO_URING_F_NONBLOCK.
+	 */
+	mutex_lock(&ub->mutex);
+	/* UBLK_IO_FETCH_REQ is only allowed before queue is setup */
+	if (ublk_queue_ready(ubq)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/* allow each command to be FETCHed at most once */
+	if (io->flags & UBLK_IO_FLAG_ACTIVE) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV);
+
+	if (ublk_need_map_io(ubq)) {
+		/*
+		 * FETCH_RQ has to provide IO buffer if NEED GET
+		 * DATA is not enabled
+		 */
+		if (!buf_addr && !ublk_need_get_data(ubq))
+			goto out;
+	} else if (buf_addr) {
+		/* User copy requires addr to be unset */
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ublk_fill_io_cmd(io, cmd, buf_addr);
+	ublk_mark_io_ready(ub, ubq);
+out:
+	mutex_unlock(&ub->mutex);
+	return ret;
+}
+
 static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			       unsigned int issue_flags,
 			       const struct ublksrv_io_cmd *ub_cmd)
@@ -1983,35 +2092,11 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 	case UBLK_IO_REGISTER_IO_BUF:
 		return ublk_register_io_buf(cmd, ubq, tag, ub_cmd->addr, issue_flags);
 	case UBLK_IO_UNREGISTER_IO_BUF:
-		return ublk_unregister_io_buf(cmd, ub_cmd->addr, issue_flags);
+		return ublk_unregister_io_buf(cmd, ubq, tag, ub_cmd->addr, issue_flags);
 	case UBLK_IO_FETCH_REQ:
-		/* UBLK_IO_FETCH_REQ is only allowed before queue is setup */
-		if (ublk_queue_ready(ubq)) {
-			ret = -EBUSY;
-			goto out;
-		}
-		/*
-		 * The io is being handled by server, so COMMIT_RQ is expected
-		 * instead of FETCH_REQ
-		 */
-		if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)
-			goto out;
-
-		if (ublk_need_map_io(ubq)) {
-			/*
-			 * FETCH_RQ has to provide IO buffer if NEED GET
-			 * DATA is not enabled
-			 */
-			if (!ub_cmd->addr && !ublk_need_get_data(ubq))
-				goto out;
-		} else if (ub_cmd->addr) {
-			/* User copy requires addr to be unset */
-			ret = -EINVAL;
+		ret = ublk_fetch(cmd, ubq, io, ub_cmd->addr);
+		if (ret)
 			goto out;
-		}
-
-		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
-		ublk_mark_io_ready(ub, ubq);
 		break;
 	case UBLK_IO_COMMIT_AND_FETCH_REQ:
 		req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag);
@@ -2043,8 +2128,9 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 		if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
 			goto out;
 		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
-		ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag);
-		break;
+		req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag);
+		ublk_dispatch_req(ubq, req, issue_flags);
+		return -EIOCBQUEUED;
 	default:
 		goto out;
 	}
@@ -2058,13 +2144,10 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 }
 
 static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
-		struct ublk_queue *ubq, int tag, size_t offset)
+		const struct ublk_queue *ubq, int tag, size_t offset)
 {
 	struct request *req;
 
-	if (!ublk_need_req_ref(ubq))
-		return NULL;
-
 	req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
 	if (!req)
 		return NULL;
@@ -2178,6 +2261,9 @@ static struct request *ublk_check_and_get_req(struct kiocb *iocb,
 	if (!ubq)
 		return ERR_PTR(-EINVAL);
 
+	if (!ublk_support_user_copy(ubq))
+		return ERR_PTR(-EACCES);
+
 	if (tag >= ubq->q_depth)
 		return ERR_PTR(-EINVAL);
 
@@ -2411,7 +2497,6 @@ static void ublk_remove(struct ublk_device *ub)
 	bool unprivileged;
 
 	ublk_stop_dev(ub);
-	cancel_work_sync(&ub->nosrv_work);
 	cdev_device_del(&ub->cdev, &ub->cdev_dev);
 	unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV;
 	ublk_put_device(ub);
@@ -2696,7 +2781,6 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
 		goto out_unlock;
 	mutex_init(&ub->mutex);
 	spin_lock_init(&ub->lock);
-	INIT_WORK(&ub->nosrv_work, ublk_nosrv_work);
 
 	ret = ublk_alloc_dev_number(ub, header->dev_id);
 	if (ret < 0)
@@ -2718,13 +2802,18 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
 	ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE |
 		UBLK_F_URING_CMD_COMP_IN_TASK;
 
-	/* GET_DATA isn't needed any more with USER_COPY */
-	if (ublk_dev_is_user_copy(ub))
+	/* GET_DATA isn't needed any more with USER_COPY or ZERO COPY */
+	if (ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY))
 		ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA;
 
-	/* Zoned storage support requires user copy feature */
+	/*
+	 * Zoned storage support requires reuse `ublksrv_io_cmd->addr` for
+	 * returning write_append_lba, which is only allowed in case of
+	 * user copy or zero copy
+	 */
 	if (ublk_dev_is_zoned(ub) &&
-	    (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || !ublk_dev_is_user_copy(ub))) {
+	    (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || !(ub->dev_info.flags &
+	     (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY)))) {
 		ret = -EINVAL;
 		goto out_free_dev_number;
 	}
@@ -2828,7 +2917,6 @@ static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd)
 static int ublk_ctrl_stop_dev(struct ublk_device *ub)
 {
 	ublk_stop_dev(ub);
-	cancel_work_sync(&ub->nosrv_work);
 	return 0;
 }
 
@@ -2932,42 +3020,14 @@ static int ublk_ctrl_set_params(struct ublk_device *ub,
 	return ret;
 }
 
-static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
-{
-	int i;
-
-	WARN_ON_ONCE(!(ubq->ubq_daemon && ubq_daemon_is_dying(ubq)));
-
-	/* All old ioucmds have to be completed */
-	ubq->nr_io_ready = 0;
-	/* old daemon is PF_EXITING, put it now */
-	put_task_struct(ubq->ubq_daemon);
-	/* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */
-	ubq->ubq_daemon = NULL;
-	ubq->timeout = false;
-	ubq->canceling = false;
-
-	for (i = 0; i < ubq->q_depth; i++) {
-		struct ublk_io *io = &ubq->ios[i];
-
-		/* forget everything now and be ready for new FETCH_REQ */
-		io->flags = 0;
-		io->cmd = NULL;
-		io->addr = 0;
-	}
-}
-
 static int ublk_ctrl_start_recovery(struct ublk_device *ub,
 		const struct ublksrv_ctrl_cmd *header)
 {
 	int ret = -EINVAL;
-	int i;
 
 	mutex_lock(&ub->mutex);
 	if (ublk_nosrv_should_stop_dev(ub))
 		goto out_unlock;
-	if (!ub->nr_queues_ready)
-		goto out_unlock;
 	/*
 	 * START_RECOVERY is only allowd after:
 	 *
@@ -2991,12 +3051,6 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub,
 		goto out_unlock;
 	}
 	pr_devel("%s: start recovery for dev id %d.\n", __func__, header->dev_id);
-	for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
-		ublk_queue_reinit(ub, ublk_get_queue(ub, i));
-	/* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */
-	ub->mm = NULL;
-	ub->nr_queues_ready = 0;
-	ub->nr_privileged_daemon = 0;
 	init_completion(&ub->completion);
 	ret = 0;
  out_unlock:
@@ -3009,7 +3063,6 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 {
 	int ublksrv_pid = (int)header->data[0];
 	int ret = -EINVAL;
-	int i;
 
 	pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n",
 			__func__, ub->dev_info.nr_hw_queues, header->dev_id);
@@ -3029,24 +3082,10 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 		goto out_unlock;
 	}
 	ub->dev_info.ublksrv_pid = ublksrv_pid;
+	ub->dev_info.state = UBLK_S_DEV_LIVE;
 	pr_devel("%s: new ublksrv_pid %d, dev id %d\n",
 			__func__, ublksrv_pid, header->dev_id);
-
-	if (ublk_nosrv_dev_should_queue_io(ub)) {
-		ub->dev_info.state = UBLK_S_DEV_LIVE;
-		blk_mq_unquiesce_queue(ub->ub_disk->queue);
-		pr_devel("%s: queue unquiesced, dev id %d.\n",
-				__func__, header->dev_id);
-		blk_mq_kick_requeue_list(ub->ub_disk->queue);
-	} else {
-		blk_mq_quiesce_queue(ub->ub_disk->queue);
-		ub->dev_info.state = UBLK_S_DEV_LIVE;
-		for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
-			ublk_get_queue(ub, i)->fail_io = false;
-		}
-		blk_mq_unquiesce_queue(ub->ub_disk->queue);
-	}
-
+	blk_mq_kick_requeue_list(ub->ub_disk->queue);
 	ret = 0;
  out_unlock:
 	mutex_unlock(&ub->mutex);
diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 7771edf54fb3..4ab32abf0f48 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -56,18 +56,6 @@ config BT_HCIBTUSB_POLL_SYNC
 	  Say Y here to enable USB poll_sync for Bluetooth USB devices by
 	  default.
 
-config BT_HCIBTUSB_AUTO_ISOC_ALT
-	bool "Automatically adjust alternate setting for Isoc endpoints"
-	depends on BT_HCIBTUSB
-	default y if CHROME_PLATFORMS
-	help
-	  Say Y here to automatically adjusting the alternate setting for
-	  HCI_USER_CHANNEL whenever a SCO link is established.
-
-	  When enabled, btusb intercepts the HCI_EV_SYNC_CONN_COMPLETE packets
-	  and configures isoc endpoint alternate setting automatically when
-	  HCI_USER_CHANNEL is in use.
-
 config BT_HCIBTUSB_BCM
 	bool "Broadcom protocol support"
 	depends on BT_HCIBTUSB
diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 48e2f400957b..55cc1652bfe4 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -2719,7 +2719,7 @@ static int btintel_uefi_get_dsbr(u32 *dsbr_var)
 	} __packed data;
 
 	efi_status_t status;
-	unsigned long data_size = 0;
+	unsigned long data_size = sizeof(data);
 	efi_guid_t guid = EFI_GUID(0xe65d8884, 0xd4af, 0x4b20, 0x8d, 0x03,
 				   0x77, 0x2e, 0xcc, 0x3d, 0xa5, 0x31);
 
@@ -2730,15 +2730,9 @@ static int btintel_uefi_get_dsbr(u32 *dsbr_var)
 		return -EOPNOTSUPP;
 
 	status = efi.get_variable(BTINTEL_EFI_DSBR, &guid, NULL, &data_size,
-				  NULL);
-
-	if (status != EFI_BUFFER_TOO_SMALL || !data_size)
-		return -EIO;
-
-	status = efi.get_variable(BTINTEL_EFI_DSBR, &guid, NULL, &data_size,
 				  &data);
 
-	if (status != EFI_SUCCESS)
+	if (status != EFI_SUCCESS || data_size != sizeof(data))
 		return -ENXIO;
 
 	*dsbr_var = data.dsbr;
@@ -3688,7 +3682,7 @@ int btintel_configure_setup(struct hci_dev *hdev, const char *driver_name)
 }
 EXPORT_SYMBOL_GPL(btintel_configure_setup);
 
-int btintel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb)
+static int btintel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct intel_tlv *tlv = (void *)&skb->data[5];
 
@@ -3716,7 +3710,6 @@ int btintel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb)
 recv_frame:
 	return hci_recv_frame(hdev, skb);
 }
-EXPORT_SYMBOL_GPL(btintel_diagnostics);
 
 int btintel_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
 {
diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index 2aece3effa4e..1d12c4113c66 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -277,7 +277,6 @@ int btintel_bootloader_setup_tlv(struct hci_dev *hdev,
 int btintel_shutdown_combined(struct hci_dev *hdev);
 void btintel_hw_error(struct hci_dev *hdev, u8 code);
 void btintel_print_fseq_info(struct hci_dev *hdev);
-int btintel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb);
 #else
 
 static inline int btintel_check_bdaddr(struct hci_dev *hdev)
@@ -411,9 +410,4 @@ static inline void btintel_hw_error(struct hci_dev *hdev, u8 code)
 static inline void btintel_print_fseq_info(struct hci_dev *hdev)
 {
 }
-
-static inline int btintel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb)
-{
-	return -EOPNOTSUPP;
-}
 #endif
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index c1e69fcc9c4f..50fe17f1e1d1 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -208,6 +208,96 @@ static void btintel_pcie_prepare_tx(struct txq *txq, u16 tfd_index,
 	memcpy(buf->data, skb->data, tfd->size);
 }
 
+static inline void btintel_pcie_dump_debug_registers(struct hci_dev *hdev)
+{
+	struct btintel_pcie_data *data = hci_get_drvdata(hdev);
+	u16 cr_hia, cr_tia;
+	u32 reg, mbox_reg;
+	struct sk_buff *skb;
+	u8 buf[80];
+
+	skb = alloc_skb(1024, GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	snprintf(buf, sizeof(buf), "%s", "---- Dump of debug registers ---");
+	bt_dev_dbg(hdev, "%s", buf);
+	skb_put_data(skb, buf, strlen(buf));
+
+	reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_BOOT_STAGE_REG);
+	snprintf(buf, sizeof(buf), "boot stage: 0x%8.8x", reg);
+	bt_dev_dbg(hdev, "%s", buf);
+	skb_put_data(skb, buf, strlen(buf));
+	data->boot_stage_cache = reg;
+
+	reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_IPC_STATUS_REG);
+	snprintf(buf, sizeof(buf), "ipc status: 0x%8.8x", reg);
+	skb_put_data(skb, buf, strlen(buf));
+	bt_dev_dbg(hdev, "%s", buf);
+
+	reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_IPC_CONTROL_REG);
+	snprintf(buf, sizeof(buf), "ipc control: 0x%8.8x", reg);
+	skb_put_data(skb, buf, strlen(buf));
+	bt_dev_dbg(hdev, "%s", buf);
+
+	reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_IPC_SLEEP_CTL_REG);
+	snprintf(buf, sizeof(buf), "ipc sleep control: 0x%8.8x", reg);
+	skb_put_data(skb, buf, strlen(buf));
+	bt_dev_dbg(hdev, "%s", buf);
+
+	/*Read the Mail box status and registers*/
+	reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_MBOX_STATUS_REG);
+	snprintf(buf, sizeof(buf), "mbox status: 0x%8.8x", reg);
+	skb_put_data(skb, buf, strlen(buf));
+	if (reg & BTINTEL_PCIE_CSR_MBOX_STATUS_MBOX1) {
+		mbox_reg = btintel_pcie_rd_reg32(data,
+						 BTINTEL_PCIE_CSR_MBOX_1_REG);
+		snprintf(buf, sizeof(buf), "mbox_1: 0x%8.8x", mbox_reg);
+		skb_put_data(skb, buf, strlen(buf));
+		bt_dev_dbg(hdev, "%s", buf);
+	}
+
+	if (reg & BTINTEL_PCIE_CSR_MBOX_STATUS_MBOX2) {
+		mbox_reg = btintel_pcie_rd_reg32(data,
+						 BTINTEL_PCIE_CSR_MBOX_2_REG);
+		snprintf(buf, sizeof(buf), "mbox_2: 0x%8.8x", mbox_reg);
+		skb_put_data(skb, buf, strlen(buf));
+		bt_dev_dbg(hdev, "%s", buf);
+	}
+
+	if (reg & BTINTEL_PCIE_CSR_MBOX_STATUS_MBOX3) {
+		mbox_reg = btintel_pcie_rd_reg32(data,
+						 BTINTEL_PCIE_CSR_MBOX_3_REG);
+		snprintf(buf, sizeof(buf), "mbox_3: 0x%8.8x", mbox_reg);
+		skb_put_data(skb, buf, strlen(buf));
+		bt_dev_dbg(hdev, "%s", buf);
+	}
+
+	if (reg & BTINTEL_PCIE_CSR_MBOX_STATUS_MBOX4) {
+		mbox_reg = btintel_pcie_rd_reg32(data,
+						 BTINTEL_PCIE_CSR_MBOX_4_REG);
+		snprintf(buf, sizeof(buf), "mbox_4: 0x%8.8x", mbox_reg);
+		skb_put_data(skb, buf, strlen(buf));
+		bt_dev_dbg(hdev, "%s", buf);
+	}
+
+	cr_hia = data->ia.cr_hia[BTINTEL_PCIE_RXQ_NUM];
+	cr_tia = data->ia.cr_tia[BTINTEL_PCIE_RXQ_NUM];
+	snprintf(buf, sizeof(buf), "rxq: cr_tia: %u cr_hia: %u", cr_tia, cr_hia);
+	skb_put_data(skb, buf, strlen(buf));
+	bt_dev_dbg(hdev, "%s", buf);
+
+	cr_hia = data->ia.cr_hia[BTINTEL_PCIE_TXQ_NUM];
+	cr_tia = data->ia.cr_tia[BTINTEL_PCIE_TXQ_NUM];
+	snprintf(buf, sizeof(buf), "txq: cr_tia: %u cr_hia: %u", cr_tia, cr_hia);
+	skb_put_data(skb, buf, strlen(buf));
+	bt_dev_dbg(hdev, "%s", buf);
+	snprintf(buf, sizeof(buf), "--------------------------------");
+	bt_dev_dbg(hdev, "%s", buf);
+
+	hci_recv_diag(hdev, skb);
+}
+
 static int btintel_pcie_send_sync(struct btintel_pcie_data *data,
 				  struct sk_buff *skb)
 {
@@ -237,8 +327,11 @@ static int btintel_pcie_send_sync(struct btintel_pcie_data *data,
 	/* Wait for the complete interrupt - URBD0 */
 	ret = wait_event_timeout(data->tx_wait_q, data->tx_wait_done,
 				 msecs_to_jiffies(BTINTEL_PCIE_TX_WAIT_TIMEOUT_MS));
-	if (!ret)
+	if (!ret) {
+		bt_dev_err(data->hdev, "tx completion timeout");
+		btintel_pcie_dump_debug_registers(data->hdev);
 		return -ETIME;
+	}
 
 	return 0;
 }
@@ -756,6 +849,26 @@ static int btintel_pcie_read_device_mem(struct btintel_pcie_data *data,
 	return 0;
 }
 
+static inline bool btintel_pcie_in_lockdown(struct btintel_pcie_data *data)
+{
+	return (data->boot_stage_cache &
+		BTINTEL_PCIE_CSR_BOOT_STAGE_ROM_LOCKDOWN) ||
+		(data->boot_stage_cache &
+		 BTINTEL_PCIE_CSR_BOOT_STAGE_IML_LOCKDOWN);
+}
+
+static inline bool btintel_pcie_in_error(struct btintel_pcie_data *data)
+{
+	return (data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_DEVICE_ERR) ||
+		(data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_ABORT_HANDLER);
+}
+
+static void btintel_pcie_msix_gp1_handler(struct btintel_pcie_data *data)
+{
+	bt_dev_err(data->hdev, "Received gp1 mailbox interrupt");
+	btintel_pcie_dump_debug_registers(data->hdev);
+}
+
 /* This function handles the MSI-X interrupt for gp0 cause (bit 0 in
  * BTINTEL_PCIE_CSR_MSIX_HW_INT_CAUSES) which is sent for boot stage and image response.
  */
@@ -779,6 +892,18 @@ static void btintel_pcie_msix_gp0_handler(struct btintel_pcie_data *data)
 	if (reg != data->img_resp_cache)
 		data->img_resp_cache = reg;
 
+	if (btintel_pcie_in_error(data)) {
+		bt_dev_err(data->hdev, "Controller in error state");
+		btintel_pcie_dump_debug_registers(data->hdev);
+		return;
+	}
+
+	if (btintel_pcie_in_lockdown(data)) {
+		bt_dev_err(data->hdev, "Controller in lockdown state");
+		btintel_pcie_dump_debug_registers(data->hdev);
+		return;
+	}
+
 	data->gp0_received = true;
 
 	old_ctxt = data->alive_intr_ctxt;
@@ -889,7 +1014,6 @@ static void btintel_pcie_msix_tx_handle(struct btintel_pcie_data *data)
 static int btintel_pcie_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_event_hdr *hdr = (void *)skb->data;
-	const char diagnostics_hdr[] = { 0x87, 0x80, 0x03 };
 	struct btintel_pcie_data *data = hci_get_drvdata(hdev);
 
 	if (skb->len > HCI_EVENT_HDR_SIZE && hdr->evt == 0xff &&
@@ -945,20 +1069,13 @@ static int btintel_pcie_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
 			}
 		}
 
-		/* Handle all diagnostics events separately. May still call
-		 * hci_recv_frame.
-		 */
-		if (len >= sizeof(diagnostics_hdr) &&
-		    memcmp(&skb->data[2], diagnostics_hdr,
-			   sizeof(diagnostics_hdr)) == 0) {
-			return btintel_diagnostics(hdev, skb);
-		}
-
 		/* This is a debug event that comes from IML and OP image when it
 		 * starts execution. There is no need pass this event to stack.
 		 */
-		if (skb->data[2] == 0x97)
+		if (skb->data[2] == 0x97) {
+			hci_recv_diag(hdev, skb);
 			return 0;
+		}
 	}
 
 	return hci_recv_frame(hdev, skb);
@@ -974,7 +1091,6 @@ static int btintel_pcie_recv_frame(struct btintel_pcie_data *data,
 	u8 pkt_type;
 	u16 plen;
 	u32 pcie_pkt_type;
-	struct sk_buff *new_skb;
 	void *pdata;
 	struct hci_dev *hdev = data->hdev;
 
@@ -1051,24 +1167,20 @@ static int btintel_pcie_recv_frame(struct btintel_pcie_data *data,
 
 	bt_dev_dbg(hdev, "pkt_type: 0x%2.2x len: %u", pkt_type, plen);
 
-	new_skb = bt_skb_alloc(plen, GFP_ATOMIC);
-	if (!new_skb) {
-		bt_dev_err(hdev, "Failed to allocate memory for skb of len: %u",
-			   skb->len);
-		ret = -ENOMEM;
-		goto exit_error;
-	}
-
-	hci_skb_pkt_type(new_skb) = pkt_type;
-	skb_put_data(new_skb, skb->data, plen);
+	hci_skb_pkt_type(skb) = pkt_type;
 	hdev->stat.byte_rx += plen;
+	skb_trim(skb, plen);
 
 	if (pcie_pkt_type == BTINTEL_PCIE_HCI_EVT_PKT)
-		ret = btintel_pcie_recv_event(hdev, new_skb);
+		ret = btintel_pcie_recv_event(hdev, skb);
 	else
-		ret = hci_recv_frame(hdev, new_skb);
+		ret = hci_recv_frame(hdev, skb);
+	skb = NULL; /* skb is freed in the callee  */
 
 exit_error:
+	if (skb)
+		kfree_skb(skb);
+
 	if (ret)
 		hdev->stat.err_rx++;
 
@@ -1202,8 +1314,6 @@ static void btintel_pcie_rx_work(struct work_struct *work)
 	struct btintel_pcie_data *data = container_of(work,
 					struct btintel_pcie_data, rx_work);
 	struct sk_buff *skb;
-	int err;
-	struct hci_dev *hdev = data->hdev;
 
 	if (test_bit(BTINTEL_PCIE_HWEXP_INPROGRESS, &data->flags)) {
 		/* Unlike usb products, controller will not send hardware
@@ -1224,11 +1334,7 @@ static void btintel_pcie_rx_work(struct work_struct *work)
 
 	/* Process the sk_buf in queue and send to the HCI layer */
 	while ((skb = skb_dequeue(&data->rx_skb_q))) {
-		err = btintel_pcie_recv_frame(data, skb);
-		if (err)
-			bt_dev_err(hdev, "Failed to send received frame: %d",
-				   err);
-		kfree_skb(skb);
+		btintel_pcie_recv_frame(data, skb);
 	}
 }
 
@@ -1281,10 +1387,8 @@ static void btintel_pcie_msix_rx_handle(struct btintel_pcie_data *data)
 	bt_dev_dbg(hdev, "RXQ: cr_hia: %u  cr_tia: %u", cr_hia, cr_tia);
 
 	/* Check CR_TIA and CR_HIA for change */
-	if (cr_tia == cr_hia) {
-		bt_dev_warn(hdev, "RXQ: no new CD found");
+	if (cr_tia == cr_hia)
 		return;
-	}
 
 	rxq = &data->rxq;
 
@@ -1320,6 +1424,16 @@ static irqreturn_t btintel_pcie_msix_isr(int irq, void *data)
 	return IRQ_WAKE_THREAD;
 }
 
+static inline bool btintel_pcie_is_rxq_empty(struct btintel_pcie_data *data)
+{
+	return data->ia.cr_hia[BTINTEL_PCIE_RXQ_NUM] == data->ia.cr_tia[BTINTEL_PCIE_RXQ_NUM];
+}
+
+static inline bool btintel_pcie_is_txackq_empty(struct btintel_pcie_data *data)
+{
+	return data->ia.cr_tia[BTINTEL_PCIE_TXQ_NUM] == data->ia.cr_hia[BTINTEL_PCIE_TXQ_NUM];
+}
+
 static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id)
 {
 	struct msix_entry *entry = dev_id;
@@ -1344,6 +1458,9 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id)
 	if (intr_hw & BTINTEL_PCIE_MSIX_HW_INT_CAUSES_HWEXP)
 		btintel_pcie_msix_hw_exp_handler(data);
 
+	if (intr_hw & BTINTEL_PCIE_MSIX_HW_INT_CAUSES_GP1)
+		btintel_pcie_msix_gp1_handler(data);
+
 	/* This interrupt is triggered by the firmware after updating
 	 * boot_stage register and image_response register
 	 */
@@ -1351,12 +1468,18 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id)
 		btintel_pcie_msix_gp0_handler(data);
 
 	/* For TX */
-	if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_0)
+	if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_0) {
 		btintel_pcie_msix_tx_handle(data);
+		if (!btintel_pcie_is_rxq_empty(data))
+			btintel_pcie_msix_rx_handle(data);
+	}
 
 	/* For RX */
-	if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_1)
+	if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_1) {
 		btintel_pcie_msix_rx_handle(data);
+		if (!btintel_pcie_is_txackq_empty(data))
+			btintel_pcie_msix_tx_handle(data);
+	}
 
 	/*
 	 * Before sending the interrupt the HW disables it to prevent a nested
@@ -2023,6 +2146,7 @@ static int btintel_pcie_setup(struct hci_dev *hdev)
 	while ((err = btintel_pcie_setup_internal(hdev)) && fw_dl_retry++ < 1) {
 		bt_dev_err(hdev, "Firmware download retry count: %d",
 			   fw_dl_retry);
+		btintel_pcie_dump_debug_registers(hdev);
 		err = btintel_pcie_reset_bt(data);
 		if (err) {
 			bt_dev_err(hdev, "Failed to do shr reset: %d", err);
diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h
index 873178019cad..21b964b15c1c 100644
--- a/drivers/bluetooth/btintel_pcie.h
+++ b/drivers/bluetooth/btintel_pcie.h
@@ -12,10 +12,17 @@
 #define BTINTEL_PCIE_CSR_HW_REV_REG		(BTINTEL_PCIE_CSR_BASE + 0x028)
 #define BTINTEL_PCIE_CSR_RF_ID_REG		(BTINTEL_PCIE_CSR_BASE + 0x09C)
 #define BTINTEL_PCIE_CSR_BOOT_STAGE_REG		(BTINTEL_PCIE_CSR_BASE + 0x108)
+#define BTINTEL_PCIE_CSR_IPC_CONTROL_REG	(BTINTEL_PCIE_CSR_BASE + 0x10C)
+#define BTINTEL_PCIE_CSR_IPC_STATUS_REG		(BTINTEL_PCIE_CSR_BASE + 0x110)
 #define BTINTEL_PCIE_CSR_IPC_SLEEP_CTL_REG	(BTINTEL_PCIE_CSR_BASE + 0x114)
 #define BTINTEL_PCIE_CSR_CI_ADDR_LSB_REG	(BTINTEL_PCIE_CSR_BASE + 0x118)
 #define BTINTEL_PCIE_CSR_CI_ADDR_MSB_REG	(BTINTEL_PCIE_CSR_BASE + 0x11C)
 #define BTINTEL_PCIE_CSR_IMG_RESPONSE_REG	(BTINTEL_PCIE_CSR_BASE + 0x12C)
+#define BTINTEL_PCIE_CSR_MBOX_1_REG		(BTINTEL_PCIE_CSR_BASE + 0x170)
+#define BTINTEL_PCIE_CSR_MBOX_2_REG		(BTINTEL_PCIE_CSR_BASE + 0x174)
+#define BTINTEL_PCIE_CSR_MBOX_3_REG		(BTINTEL_PCIE_CSR_BASE + 0x178)
+#define BTINTEL_PCIE_CSR_MBOX_4_REG		(BTINTEL_PCIE_CSR_BASE + 0x17C)
+#define BTINTEL_PCIE_CSR_MBOX_STATUS_REG	(BTINTEL_PCIE_CSR_BASE + 0x180)
 #define BTINTEL_PCIE_PRPH_DEV_ADDR_REG		(BTINTEL_PCIE_CSR_BASE + 0x440)
 #define BTINTEL_PCIE_PRPH_DEV_RD_REG		(BTINTEL_PCIE_CSR_BASE + 0x458)
 #define BTINTEL_PCIE_CSR_HBUS_TARG_WRPTR	(BTINTEL_PCIE_CSR_BASE + 0x460)
@@ -41,6 +48,9 @@
 #define BTINTEL_PCIE_CSR_BOOT_STAGE_OPFW		(BIT(2))
 #define BTINTEL_PCIE_CSR_BOOT_STAGE_ROM_LOCKDOWN	(BIT(10))
 #define BTINTEL_PCIE_CSR_BOOT_STAGE_IML_LOCKDOWN	(BIT(11))
+#define BTINTEL_PCIE_CSR_BOOT_STAGE_DEVICE_ERR		(BIT(12))
+#define BTINTEL_PCIE_CSR_BOOT_STAGE_ABORT_HANDLER	(BIT(13))
+#define BTINTEL_PCIE_CSR_BOOT_STAGE_DEVICE_HALTED	(BIT(14))
 #define BTINTEL_PCIE_CSR_BOOT_STAGE_MAC_ACCESS_ON	(BIT(16))
 #define BTINTEL_PCIE_CSR_BOOT_STAGE_ALIVE		(BIT(23))
 #define BTINTEL_PCIE_CSR_BOOT_STAGE_D3_STATE_READY	(BIT(24))
@@ -89,6 +99,7 @@ enum msix_fh_int_causes {
 /* Causes for the HW register interrupts */
 enum msix_hw_int_causes {
 	BTINTEL_PCIE_MSIX_HW_INT_CAUSES_GP0	= BIT(0),	/* cause 32 */
+	BTINTEL_PCIE_MSIX_HW_INT_CAUSES_GP1	= BIT(1),	/* cause 33 */
 	BTINTEL_PCIE_MSIX_HW_INT_CAUSES_HWEXP	= BIT(3),	/* cause 35 */
 };
 
@@ -121,6 +132,14 @@ enum btintel_pcie_tlv_type {
 	BTINTEL_FW_BUILD,
 };
 
+/* causes for the MBOX interrupts */
+enum msix_mbox_int_causes {
+	BTINTEL_PCIE_CSR_MBOX_STATUS_MBOX1 = BIT(0), /* cause MBOX1 */
+	BTINTEL_PCIE_CSR_MBOX_STATUS_MBOX2 = BIT(1), /* cause MBOX2 */
+	BTINTEL_PCIE_CSR_MBOX_STATUS_MBOX3 = BIT(2), /* cause MBOX3 */
+	BTINTEL_PCIE_CSR_MBOX_STATUS_MBOX4 = BIT(3), /* cause MBOX4 */
+};
+
 #define BTINTEL_PCIE_MSIX_NON_AUTO_CLEAR_CAUSE	BIT(7)
 
 /* Minimum and Maximum number of MSI-X Vector
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index 07cd308f7abf..93932a0d8625 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -100,7 +100,9 @@ static int btmrvl_sdio_probe_of(struct device *dev,
 			}
 
 			/* Configure wakeup (enabled by default) */
-			device_init_wakeup(dev, true);
+			ret = devm_device_init_wakeup(dev);
+			if (ret)
+				return dev_err_probe(dev, ret, "Failed to init wakeup\n");
 		}
 	}
 
diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
index edd5eead1e93..c16a3518b8ff 100644
--- a/drivers/bluetooth/btmtksdio.c
+++ b/drivers/bluetooth/btmtksdio.c
@@ -723,6 +723,10 @@ static int btmtksdio_close(struct hci_dev *hdev)
 {
 	struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
 
+	/* Skip btmtksdio_close if BTMTKSDIO_FUNC_ENABLED isn't set */
+	if (!test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state))
+		return 0;
+
 	sdio_claim_host(bdev->func);
 
 	/* Disable interrupt */
@@ -1410,7 +1414,7 @@ static int btmtksdio_probe(struct sdio_func *func,
 	 */
 	pm_runtime_put_noidle(bdev->dev);
 
-	err = device_init_wakeup(bdev->dev, true);
+	err = devm_device_init_wakeup(bdev->dev);
 	if (err)
 		bt_dev_err(hdev, "failed to initialize device wakeup");
 
@@ -1443,11 +1447,15 @@ static void btmtksdio_remove(struct sdio_func *func)
 	if (!bdev)
 		return;
 
+	hdev = bdev->hdev;
+
+	/* Make sure to call btmtksdio_close before removing sdio card */
+	if (test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state))
+		btmtksdio_close(hdev);
+
 	/* Be consistent the state in btmtksdio_probe */
 	pm_runtime_get_noresume(bdev->dev);
 
-	hdev = bdev->hdev;
-
 	sdio_set_drvdata(func, NULL);
 	hci_unregister_dev(hdev);
 	hci_free_dev(hdev);
diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index 5091dea762a0..b34623a69b8a 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -17,6 +17,7 @@
 #include <linux/crc32.h>
 #include <linux/string_helpers.h>
 #include <linux/gpio/consumer.h>
+#include <linux/of_irq.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -143,7 +144,9 @@ struct ps_data {
 	bool  driver_sent_cmd;
 	u16   h2c_ps_interval;
 	u16   c2h_ps_interval;
+	bool  wakeup_source;
 	struct gpio_desc *h2c_ps_gpio;
+	s32 irq_handler;
 	struct hci_dev *hdev;
 	struct work_struct work;
 	struct timer_list ps_timer;
@@ -476,12 +479,21 @@ static void ps_timeout_func(struct timer_list *t)
 	}
 }
 
+static irqreturn_t ps_host_wakeup_irq_handler(int irq, void *priv)
+{
+	struct btnxpuart_dev *nxpdev = (struct btnxpuart_dev *)priv;
+
+	bt_dev_dbg(nxpdev->hdev, "Host wakeup interrupt");
+	return IRQ_HANDLED;
+}
 static int ps_setup(struct hci_dev *hdev)
 {
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
 	struct serdev_device *serdev = nxpdev->serdev;
 	struct ps_data *psdata = &nxpdev->psdata;
+	int ret;
 
+	/* Out-Of-Band Device Wakeup */
 	psdata->h2c_ps_gpio = devm_gpiod_get_optional(&serdev->dev, "device-wakeup",
 						      GPIOD_OUT_LOW);
 	if (IS_ERR(psdata->h2c_ps_gpio)) {
@@ -493,11 +505,37 @@ static int ps_setup(struct hci_dev *hdev)
 	if (device_property_read_u8(&serdev->dev, "nxp,wakein-pin", &psdata->h2c_wakeup_gpio)) {
 		psdata->h2c_wakeup_gpio = 0xff; /* 0xff: use default pin/gpio */
 	} else if (!psdata->h2c_ps_gpio) {
-		bt_dev_warn(hdev, "nxp,wakein-pin property without device-wakeup GPIO");
+		bt_dev_warn(hdev, "nxp,wakein-pin property without device-wakeup-gpios");
 		psdata->h2c_wakeup_gpio = 0xff;
 	}
 
-	device_property_read_u8(&serdev->dev, "nxp,wakeout-pin", &psdata->c2h_wakeup_gpio);
+	/* Out-Of-Band Host Wakeup */
+	if (of_property_read_bool(serdev->dev.of_node, "wakeup-source")) {
+		psdata->irq_handler = of_irq_get_byname(serdev->dev.of_node, "wakeup");
+		bt_dev_info(nxpdev->hdev, "irq_handler: %d", psdata->irq_handler);
+		if (psdata->irq_handler > 0)
+			psdata->wakeup_source = true;
+	}
+
+	if (device_property_read_u8(&serdev->dev, "nxp,wakeout-pin", &psdata->c2h_wakeup_gpio)) {
+		psdata->c2h_wakeup_gpio = 0xff;
+		if (psdata->wakeup_source) {
+			bt_dev_warn(hdev, "host wakeup interrupt without nxp,wakeout-pin");
+			psdata->wakeup_source = false;
+		}
+	} else if (!psdata->wakeup_source) {
+		bt_dev_warn(hdev, "nxp,wakeout-pin property without host wakeup interrupt");
+		psdata->c2h_wakeup_gpio = 0xff;
+	}
+
+	if (psdata->wakeup_source) {
+		ret = devm_request_irq(&serdev->dev, psdata->irq_handler,
+					ps_host_wakeup_irq_handler,
+					IRQF_ONESHOT | IRQF_TRIGGER_FALLING,
+					dev_name(&serdev->dev), nxpdev);
+		disable_irq(psdata->irq_handler);
+		device_init_wakeup(&serdev->dev, true);
+	}
 
 	psdata->hdev = hdev;
 	INIT_WORK(&psdata->work, ps_work_func);
@@ -637,12 +675,10 @@ static void ps_init(struct hci_dev *hdev)
 
 	psdata->ps_state = PS_STATE_AWAKE;
 
-	if (psdata->c2h_wakeup_gpio) {
+	if (psdata->c2h_wakeup_gpio != 0xff)
 		psdata->c2h_wakeupmode = BT_HOST_WAKEUP_METHOD_GPIO;
-	} else {
+	else
 		psdata->c2h_wakeupmode = BT_HOST_WAKEUP_METHOD_NONE;
-		psdata->c2h_wakeup_gpio = 0xff;
-	}
 
 	psdata->cur_h2c_wakeupmode = WAKEUP_METHOD_INVALID;
 	if (psdata->h2c_ps_gpio)
@@ -1286,7 +1322,9 @@ static void nxp_coredump(struct hci_dev *hdev)
 	u8 pcmd = 2;
 
 	skb = nxp_drv_send_cmd(hdev, HCI_NXP_TRIGGER_DUMP, 1, &pcmd);
-	if (!IS_ERR(skb))
+	if (IS_ERR(skb))
+		bt_dev_err(hdev, "Failed to trigger FW Dump. (%ld)", PTR_ERR(skb));
+	else
 		kfree_skb(skb);
 }
 
@@ -1445,9 +1483,6 @@ static int nxp_shutdown(struct hci_dev *hdev)
 		/* HCI_NXP_IND_RESET command may not returns any response */
 		if (!IS_ERR(skb))
 			kfree_skb(skb);
-	} else if (nxpdev->current_baudrate != nxpdev->fw_init_baudrate) {
-		nxpdev->new_baudrate = nxpdev->fw_init_baudrate;
-		nxp_set_baudrate_cmd(hdev, NULL);
 	}
 
 	return 0;
@@ -1799,13 +1834,15 @@ static void nxp_serdev_remove(struct serdev_device *serdev)
 		clear_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
 		wake_up_interruptible(&nxpdev->check_boot_sign_wait_q);
 		wake_up_interruptible(&nxpdev->fw_dnld_done_wait_q);
-	}
-
-	if (test_bit(HCI_RUNNING, &hdev->flags)) {
-		/* Ensure shutdown callback is executed before unregistering, so
-		 * that baudrate is reset to initial value.
+	} else {
+		/* Restore FW baudrate to fw_init_baudrate if changed.
+		 * This will ensure FW baudrate is in sync with
+		 * driver baudrate in case this driver is re-inserted.
 		 */
-		nxp_shutdown(hdev);
+		if (nxpdev->current_baudrate != nxpdev->fw_init_baudrate) {
+			nxpdev->new_baudrate = nxpdev->fw_init_baudrate;
+			nxp_set_baudrate_cmd(hdev, NULL);
+		}
 	}
 
 	ps_cleanup(nxpdev);
@@ -1820,6 +1857,11 @@ static int nxp_serdev_suspend(struct device *dev)
 	struct ps_data *psdata = &nxpdev->psdata;
 
 	ps_control(psdata->hdev, PS_STATE_SLEEP);
+
+	if (psdata->wakeup_source) {
+		enable_irq_wake(psdata->irq_handler);
+		enable_irq(psdata->irq_handler);
+	}
 	return 0;
 }
 
@@ -1828,6 +1870,11 @@ static int nxp_serdev_resume(struct device *dev)
 	struct btnxpuart_dev *nxpdev = dev_get_drvdata(dev);
 	struct ps_data *psdata = &nxpdev->psdata;
 
+	if (psdata->wakeup_source) {
+		disable_irq(psdata->irq_handler);
+		disable_irq_wake(psdata->irq_handler);
+	}
+
 	ps_control(psdata->hdev, PS_STATE_AWAKE);
 	return 0;
 }
diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index 3d6778b95e00..edefb9dc76aa 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -889,7 +889,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 			if (le32_to_cpu(ver.soc_id) == QCA_WCN3950_SOC_ID_T)
 				variant = "t";
 			else if (le32_to_cpu(ver.soc_id) == QCA_WCN3950_SOC_ID_S)
-				variant = "u";
+				variant = "s";
 
 			snprintf(config.fwname, sizeof(config.fwname),
 				 "qca/cmnv%02x%s.bin", rom_ver, variant);
diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index d3eba0d4a57d..7838c89e529e 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -1215,6 +1215,8 @@ next:
 			rtl_dev_err(hdev, "mandatory config file %s not found",
 				    btrtl_dev->ic_info->cfg_name);
 			ret = btrtl_dev->cfg_len;
+			if (!ret)
+				ret = -EINVAL;
 			goto err_free;
 		}
 	}
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 5012b5ff92c8..9ab661d2d1e6 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -21,6 +21,7 @@
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/hci_drv.h>
 
 #include "btintel.h"
 #include "btbcm.h"
@@ -34,7 +35,6 @@ static bool force_scofix;
 static bool enable_autosuspend = IS_ENABLED(CONFIG_BT_HCIBTUSB_AUTOSUSPEND);
 static bool enable_poll_sync = IS_ENABLED(CONFIG_BT_HCIBTUSB_POLL_SYNC);
 static bool reset = true;
-static bool auto_isoc_alt = IS_ENABLED(CONFIG_BT_HCIBTUSB_AUTO_ISOC_ALT);
 
 static struct usb_driver btusb_driver;
 
@@ -513,6 +513,7 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Realtek 8851BE Bluetooth devices */
+	{ USB_DEVICE(0x0bda, 0xb850), .driver_info = BTUSB_REALTEK },
 	{ USB_DEVICE(0x13d3, 0x3600), .driver_info = BTUSB_REALTEK },
 
 	/* Realtek 8852AE Bluetooth devices */
@@ -678,6 +679,8 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3568), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3584), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3605), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3607), .driver_info = BTUSB_MEDIATEK |
@@ -716,8 +719,12 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3608), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3613), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3628), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3630), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Additional Realtek 8723AE Bluetooth devices */
 	{ USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
@@ -1118,42 +1125,6 @@ static inline void btusb_free_frags(struct btusb_data *data)
 	spin_unlock_irqrestore(&data->rxlock, flags);
 }
 
-static void btusb_sco_connected(struct btusb_data *data, struct sk_buff *skb)
-{
-	struct hci_event_hdr *hdr = (void *) skb->data;
-	struct hci_ev_sync_conn_complete *ev =
-		(void *) skb->data + sizeof(*hdr);
-	struct hci_dev *hdev = data->hdev;
-	unsigned int notify_air_mode;
-
-	if (hci_skb_pkt_type(skb) != HCI_EVENT_PKT)
-		return;
-
-	if (skb->len < sizeof(*hdr) || hdr->evt != HCI_EV_SYNC_CONN_COMPLETE)
-		return;
-
-	if (skb->len != sizeof(*hdr) + sizeof(*ev) || ev->status)
-		return;
-
-	switch (ev->air_mode) {
-	case BT_CODEC_CVSD:
-		notify_air_mode = HCI_NOTIFY_ENABLE_SCO_CVSD;
-		break;
-
-	case BT_CODEC_TRANSPARENT:
-		notify_air_mode = HCI_NOTIFY_ENABLE_SCO_TRANSP;
-		break;
-
-	default:
-		return;
-	}
-
-	bt_dev_info(hdev, "enabling SCO with air mode %u", ev->air_mode);
-	data->sco_num = 1;
-	data->air_mode = notify_air_mode;
-	schedule_work(&data->work);
-}
-
 static int btusb_recv_event(struct btusb_data *data, struct sk_buff *skb)
 {
 	if (data->intr_interval) {
@@ -1161,10 +1132,6 @@ static int btusb_recv_event(struct btusb_data *data, struct sk_buff *skb)
 		schedule_delayed_work(&data->rx_work, 0);
 	}
 
-	/* Configure altsetting for HCI_USER_CHANNEL on SCO connected */
-	if (auto_isoc_alt && hci_dev_test_flag(data->hdev, HCI_USER_CHANNEL))
-		btusb_sco_connected(data, skb);
-
 	return data->recv_event(data->hdev, skb);
 }
 
@@ -3010,55 +2977,27 @@ static void btusb_coredump_qca(struct hci_dev *hdev)
 		bt_dev_err(hdev, "%s: triggle crash failed (%d)", __func__, err);
 }
 
-/*
- * ==0: not a dump pkt.
- * < 0: fails to handle a dump pkt
- * > 0: otherwise.
- */
+/* Return: 0 on success, negative errno on failure. */
 static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	int ret = 1;
+	int ret = 0;
+	unsigned int skip = 0;
 	u8 pkt_type;
-	u8 *sk_ptr;
-	unsigned int sk_len;
 	u16 seqno;
 	u32 dump_size;
 
-	struct hci_event_hdr *event_hdr;
-	struct hci_acl_hdr *acl_hdr;
 	struct qca_dump_hdr *dump_hdr;
 	struct btusb_data *btdata = hci_get_drvdata(hdev);
 	struct usb_device *udev = btdata->udev;
 
 	pkt_type = hci_skb_pkt_type(skb);
-	sk_ptr = skb->data;
-	sk_len = skb->len;
+	skip = sizeof(struct hci_event_hdr);
+	if (pkt_type == HCI_ACLDATA_PKT)
+		skip += sizeof(struct hci_acl_hdr);
 
-	if (pkt_type == HCI_ACLDATA_PKT) {
-		acl_hdr = hci_acl_hdr(skb);
-		if (le16_to_cpu(acl_hdr->handle) != QCA_MEMDUMP_ACL_HANDLE)
-			return 0;
-		sk_ptr += HCI_ACL_HDR_SIZE;
-		sk_len -= HCI_ACL_HDR_SIZE;
-		event_hdr = (struct hci_event_hdr *)sk_ptr;
-	} else {
-		event_hdr = hci_event_hdr(skb);
-	}
-
-	if ((event_hdr->evt != HCI_VENDOR_PKT)
-		|| (event_hdr->plen != (sk_len - HCI_EVENT_HDR_SIZE)))
-		return 0;
-
-	sk_ptr += HCI_EVENT_HDR_SIZE;
-	sk_len -= HCI_EVENT_HDR_SIZE;
-
-	dump_hdr = (struct qca_dump_hdr *)sk_ptr;
-	if ((sk_len < offsetof(struct qca_dump_hdr, data))
-		|| (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS)
-	    || (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
-		return 0;
+	skb_pull(skb, skip);
+	dump_hdr = (struct qca_dump_hdr *)skb->data;
 
-	/*it is dump pkt now*/
 	seqno = le16_to_cpu(dump_hdr->seqno);
 	if (seqno == 0) {
 		set_bit(BTUSB_HW_SSR_ACTIVE, &btdata->flags);
@@ -3078,16 +3017,15 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
 
 		btdata->qca_dump.ram_dump_size = dump_size;
 		btdata->qca_dump.ram_dump_seqno = 0;
-		sk_ptr += offsetof(struct qca_dump_hdr, data0);
-		sk_len -= offsetof(struct qca_dump_hdr, data0);
+
+		skb_pull(skb, offsetof(struct qca_dump_hdr, data0));
 
 		usb_disable_autosuspend(udev);
 		bt_dev_info(hdev, "%s memdump size(%u)\n",
 			    (pkt_type == HCI_ACLDATA_PKT) ? "ACL" : "event",
 			    dump_size);
 	} else {
-		sk_ptr += offsetof(struct qca_dump_hdr, data);
-		sk_len -= offsetof(struct qca_dump_hdr, data);
+		skb_pull(skb, offsetof(struct qca_dump_hdr, data));
 	}
 
 	if (!btdata->qca_dump.ram_dump_size) {
@@ -3107,7 +3045,6 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
 		return ret;
 	}
 
-	skb_pull(skb, skb->len - sk_len);
 	hci_devcd_append(hdev, skb);
 	btdata->qca_dump.ram_dump_seqno++;
 	if (seqno == QCA_LAST_SEQUENCE_NUM) {
@@ -3132,17 +3069,74 @@ out:
 	return ret;
 }
 
+/* Return: true if the ACL packet is a dump packet, false otherwise. */
+static bool acl_pkt_is_dump_qca(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_event_hdr *event_hdr;
+	struct hci_acl_hdr *acl_hdr;
+	struct qca_dump_hdr *dump_hdr;
+	struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
+	bool is_dump = false;
+
+	if (!clone)
+		return false;
+
+	acl_hdr = skb_pull_data(clone, sizeof(*acl_hdr));
+	if (!acl_hdr || (le16_to_cpu(acl_hdr->handle) != QCA_MEMDUMP_ACL_HANDLE))
+		goto out;
+
+	event_hdr = skb_pull_data(clone, sizeof(*event_hdr));
+	if (!event_hdr || (event_hdr->evt != HCI_VENDOR_PKT))
+		goto out;
+
+	dump_hdr = skb_pull_data(clone, sizeof(*dump_hdr));
+	if (!dump_hdr || (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) ||
+	   (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
+		goto out;
+
+	is_dump = true;
+out:
+	consume_skb(clone);
+	return is_dump;
+}
+
+/* Return: true if the event packet is a dump packet, false otherwise. */
+static bool evt_pkt_is_dump_qca(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_event_hdr *event_hdr;
+	struct qca_dump_hdr *dump_hdr;
+	struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
+	bool is_dump = false;
+
+	if (!clone)
+		return false;
+
+	event_hdr = skb_pull_data(clone, sizeof(*event_hdr));
+	if (!event_hdr || (event_hdr->evt != HCI_VENDOR_PKT))
+		goto out;
+
+	dump_hdr = skb_pull_data(clone, sizeof(*dump_hdr));
+	if (!dump_hdr || (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) ||
+	   (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
+		goto out;
+
+	is_dump = true;
+out:
+	consume_skb(clone);
+	return is_dump;
+}
+
 static int btusb_recv_acl_qca(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	if (handle_dump_pkt_qca(hdev, skb))
-		return 0;
+	if (acl_pkt_is_dump_qca(hdev, skb))
+		return handle_dump_pkt_qca(hdev, skb);
 	return hci_recv_frame(hdev, skb);
 }
 
 static int btusb_recv_evt_qca(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	if (handle_dump_pkt_qca(hdev, skb))
-		return 0;
+	if (evt_pkt_is_dump_qca(hdev, skb))
+		return handle_dump_pkt_qca(hdev, skb);
 	return hci_recv_frame(hdev, skb);
 }
 
@@ -3726,31 +3720,133 @@ static const struct file_operations force_poll_sync_fops = {
 	.llseek		= default_llseek,
 };
 
-static ssize_t isoc_alt_show(struct device *dev,
-			     struct device_attribute *attr,
-			     char *buf)
+#define BTUSB_HCI_DRV_OP_SUPPORTED_ALTSETTINGS \
+		hci_opcode_pack(HCI_DRV_OGF_DRIVER_SPECIFIC, 0x0000)
+#define BTUSB_HCI_DRV_SUPPORTED_ALTSETTINGS_SIZE	0
+struct btusb_hci_drv_rp_supported_altsettings {
+	__u8	num;
+	__u8	altsettings[];
+} __packed;
+
+#define BTUSB_HCI_DRV_OP_SWITCH_ALTSETTING \
+		hci_opcode_pack(HCI_DRV_OGF_DRIVER_SPECIFIC, 0x0001)
+#define BTUSB_HCI_DRV_SWITCH_ALTSETTING_SIZE		1
+struct btusb_hci_drv_cmd_switch_altsetting {
+	__u8	altsetting;
+} __packed;
+
+static const struct {
+	u16 opcode;
+	const char *desc;
+} btusb_hci_drv_supported_commands[] = {
+	/* Common commands */
+	{ HCI_DRV_OP_READ_INFO, "Read Info" },
+
+	/* Driver specific commands */
+	{ BTUSB_HCI_DRV_OP_SUPPORTED_ALTSETTINGS, "Supported Altsettings" },
+	{ BTUSB_HCI_DRV_OP_SWITCH_ALTSETTING,     "Switch Altsetting" },
+};
+static int btusb_hci_drv_read_info(struct hci_dev *hdev, void *data,
+				   u16 data_len)
 {
-	struct btusb_data *data = dev_get_drvdata(dev);
+	struct hci_drv_rp_read_info *rp;
+	size_t rp_size;
+	int err, i;
+	u16 opcode, num_supported_commands =
+		ARRAY_SIZE(btusb_hci_drv_supported_commands);
+
+	rp_size = sizeof(*rp) + num_supported_commands * 2;
+
+	rp = kmalloc(rp_size, GFP_KERNEL);
+	if (!rp)
+		return -ENOMEM;
 
-	return sysfs_emit(buf, "%d\n", data->isoc_altsetting);
+	strscpy_pad(rp->driver_name, btusb_driver.name);
+
+	rp->num_supported_commands = cpu_to_le16(num_supported_commands);
+	for (i = 0; i < num_supported_commands; i++) {
+		opcode = btusb_hci_drv_supported_commands[i].opcode;
+		bt_dev_info(hdev,
+			    "Supported HCI Drv command (0x%02x|0x%04x): %s",
+			    hci_opcode_ogf(opcode),
+			    hci_opcode_ocf(opcode),
+			    btusb_hci_drv_supported_commands[i].desc);
+		rp->supported_commands[i] = cpu_to_le16(opcode);
+	}
+
+	err = hci_drv_cmd_complete(hdev, HCI_DRV_OP_READ_INFO,
+				   HCI_DRV_STATUS_SUCCESS, rp, rp_size);
+
+	kfree(rp);
+	return err;
 }
 
-static ssize_t isoc_alt_store(struct device *dev,
-			      struct device_attribute *attr,
-			      const char *buf, size_t count)
+static int btusb_hci_drv_supported_altsettings(struct hci_dev *hdev, void *data,
+					       u16 data_len)
 {
-	struct btusb_data *data = dev_get_drvdata(dev);
-	int alt;
-	int ret;
+	struct btusb_data *drvdata = hci_get_drvdata(hdev);
+	struct btusb_hci_drv_rp_supported_altsettings *rp;
+	size_t rp_size;
+	int err;
+	u8 i;
+
+	/* There are at most 7 alt (0 - 6) */
+	rp = kmalloc(sizeof(*rp) + 7, GFP_KERNEL);
+
+	rp->num = 0;
+	if (!drvdata->isoc)
+		goto done;
+
+	for (i = 0; i <= 6; i++) {
+		if (btusb_find_altsetting(drvdata, i))
+			rp->altsettings[rp->num++] = i;
+	}
+
+done:
+	rp_size = sizeof(*rp) + rp->num;
+
+	err = hci_drv_cmd_complete(hdev, BTUSB_HCI_DRV_OP_SUPPORTED_ALTSETTINGS,
+				   HCI_DRV_STATUS_SUCCESS, rp, rp_size);
+	kfree(rp);
+	return err;
+}
+
+static int btusb_hci_drv_switch_altsetting(struct hci_dev *hdev, void *data,
+					   u16 data_len)
+{
+	struct btusb_hci_drv_cmd_switch_altsetting *cmd = data;
+	u8 status;
 
-	if (kstrtoint(buf, 10, &alt))
-		return -EINVAL;
+	if (cmd->altsetting > 6) {
+		status = HCI_DRV_STATUS_INVALID_PARAMETERS;
+	} else {
+		if (btusb_switch_alt_setting(hdev, cmd->altsetting))
+			status = HCI_DRV_STATUS_UNSPECIFIED_ERROR;
+		else
+			status = HCI_DRV_STATUS_SUCCESS;
+	}
 
-	ret = btusb_switch_alt_setting(data->hdev, alt);
-	return ret < 0 ? ret : count;
+	return hci_drv_cmd_status(hdev, BTUSB_HCI_DRV_OP_SWITCH_ALTSETTING,
+				  status);
 }
 
-static DEVICE_ATTR_RW(isoc_alt);
+static const struct hci_drv_handler btusb_hci_drv_common_handlers[] = {
+	{ btusb_hci_drv_read_info,	HCI_DRV_READ_INFO_SIZE },
+};
+
+static const struct hci_drv_handler btusb_hci_drv_specific_handlers[] = {
+	{ btusb_hci_drv_supported_altsettings,
+				BTUSB_HCI_DRV_SUPPORTED_ALTSETTINGS_SIZE },
+	{ btusb_hci_drv_switch_altsetting,
+				BTUSB_HCI_DRV_SWITCH_ALTSETTING_SIZE },
+};
+
+static struct hci_drv btusb_hci_drv = {
+	.common_handler_count	= ARRAY_SIZE(btusb_hci_drv_common_handlers),
+	.common_handlers	= btusb_hci_drv_common_handlers,
+	.specific_handler_count	= ARRAY_SIZE(btusb_hci_drv_specific_handlers),
+	.specific_handlers	= btusb_hci_drv_specific_handlers,
+};
 
 static int btusb_probe(struct usb_interface *intf,
 		       const struct usb_device_id *id)
@@ -3891,12 +3987,13 @@ static int btusb_probe(struct usb_interface *intf,
 		data->reset_gpio = reset_gpio;
 	}
 
-	hdev->open   = btusb_open;
-	hdev->close  = btusb_close;
-	hdev->flush  = btusb_flush;
-	hdev->send   = btusb_send_frame;
-	hdev->notify = btusb_notify;
-	hdev->wakeup = btusb_wakeup;
+	hdev->open    = btusb_open;
+	hdev->close   = btusb_close;
+	hdev->flush   = btusb_flush;
+	hdev->send    = btusb_send_frame;
+	hdev->notify  = btusb_notify;
+	hdev->wakeup  = btusb_wakeup;
+	hdev->hci_drv = &btusb_hci_drv;
 
 #ifdef CONFIG_PM
 	err = btusb_config_oob_wake(hdev);
@@ -4115,10 +4212,6 @@ static int btusb_probe(struct usb_interface *intf,
 						 data->isoc, data);
 		if (err < 0)
 			goto out_free_dev;
-
-		err = device_create_file(&intf->dev, &dev_attr_isoc_alt);
-		if (err)
-			goto out_free_dev;
 	}
 
 	if (IS_ENABLED(CONFIG_BT_HCIBTUSB_BCM) && data->diag) {
@@ -4165,10 +4258,8 @@ static void btusb_disconnect(struct usb_interface *intf)
 	hdev = data->hdev;
 	usb_set_intfdata(data->intf, NULL);
 
-	if (data->isoc) {
-		device_remove_file(&intf->dev, &dev_attr_isoc_alt);
+	if (data->isoc)
 		usb_set_intfdata(data->isoc, NULL);
-	}
 
 	if (data->diag)
 		usb_set_intfdata(data->diag, NULL);
diff --git a/drivers/bluetooth/hci_aml.c b/drivers/bluetooth/hci_aml.c
index dc9541e76d81..1394c575aa6d 100644
--- a/drivers/bluetooth/hci_aml.c
+++ b/drivers/bluetooth/hci_aml.c
@@ -313,8 +313,7 @@ static int aml_download_firmware(struct hci_dev *hdev, const char *fw_name)
 		goto exit;
 
 exit:
-	if (firmware)
-		release_firmware(firmware);
+	release_firmware(firmware);
 	return ret;
 }
 
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index a51935d37e5d..59f4d7bdffdc 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -289,18 +289,18 @@ static void vhci_coredump(struct hci_dev *hdev)
 
 static void vhci_coredump_hdr(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	char buf[80];
+	const char *buf;
 
-	snprintf(buf, sizeof(buf), "Controller Name: vhci_ctrl\n");
+	buf = "Controller Name: vhci_ctrl\n";
 	skb_put_data(skb, buf, strlen(buf));
 
-	snprintf(buf, sizeof(buf), "Firmware Version: vhci_fw\n");
+	buf = "Firmware Version: vhci_fw\n";
 	skb_put_data(skb, buf, strlen(buf));
 
-	snprintf(buf, sizeof(buf), "Driver: vhci_drv\n");
+	buf = "Driver: vhci_drv\n";
 	skb_put_data(skb, buf, strlen(buf));
 
-	snprintf(buf, sizeof(buf), "Vendor: vhci\n");
+	buf = "Vendor: vhci\n";
 	skb_put_data(skb, buf, strlen(buf));
 }
 
diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index f7dd455dd0dd..dda466f9181a 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -315,7 +315,7 @@ static int __init misc_init(void)
 		goto fail_remove;
 
 	err = -EIO;
-	if (register_chrdev(MISC_MAJOR, "misc", &misc_fops))
+	if (__register_chrdev(MISC_MAJOR, 0, MINORMASK + 1, "misc", &misc_fops))
 		goto fail_printk;
 	return 0;
 
diff --git a/drivers/char/tpm/tpm-buf.c b/drivers/char/tpm/tpm-buf.c
index e49a19fea3bd..dc882fc9fa9e 100644
--- a/drivers/char/tpm/tpm-buf.c
+++ b/drivers/char/tpm/tpm-buf.c
@@ -201,7 +201,7 @@ static void tpm_buf_read(struct tpm_buf *buf, off_t *offset, size_t count, void
  */
 u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset)
 {
-	u8 value;
+	u8 value = 0;
 
 	tpm_buf_read(buf, offset, sizeof(value), &value);
 
@@ -218,7 +218,7 @@ EXPORT_SYMBOL_GPL(tpm_buf_read_u8);
  */
 u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset)
 {
-	u16 value;
+	u16 value = 0;
 
 	tpm_buf_read(buf, offset, sizeof(value), &value);
 
@@ -235,7 +235,7 @@ EXPORT_SYMBOL_GPL(tpm_buf_read_u16);
  */
 u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset)
 {
-	u32 value;
+	u32 value = 0;
 
 	tpm_buf_read(buf, offset, sizeof(value), &value);
 
diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c
index 3f89635ba5e8..7b5049b3d476 100644
--- a/drivers/char/tpm/tpm2-sessions.c
+++ b/drivers/char/tpm/tpm2-sessions.c
@@ -40,11 +40,6 @@
  *
  * These are the usage functions:
  *
- * tpm2_start_auth_session() which allocates the opaque auth structure
- *	and gets a session from the TPM.  This must be called before
- *	any of the following functions.  The session is protected by a
- *	session_key which is derived from a random salt value
- *	encrypted to the NULL seed.
  * tpm2_end_auth_session() kills the session and frees the resources.
  *	Under normal operation this function is done by
  *	tpm_buf_check_hmac_response(), so this is only to be used on
@@ -963,16 +958,13 @@ err:
 }
 
 /**
- * tpm2_start_auth_session() - create a HMAC authentication session with the TPM
- * @chip: the TPM chip structure to create the session with
+ * tpm2_start_auth_session() - Create an a HMAC authentication session
+ * @chip:	A TPM chip
  *
- * This function loads the NULL seed from its saved context and starts
- * an authentication session on the null seed, fills in the
- * @chip->auth structure to contain all the session details necessary
- * for performing the HMAC, encrypt and decrypt operations and
- * returns.  The NULL seed is flushed before this function returns.
+ * Loads the ephemeral key (null seed), and starts an HMAC authenticated
+ * session. The null seed is flushed before the return.
  *
- * Return: zero on success or actual error encountered.
+ * Returns zero on success, or a POSIX error code.
  */
 int tpm2_start_auth_session(struct tpm_chip *chip)
 {
@@ -1024,7 +1016,7 @@ int tpm2_start_auth_session(struct tpm_chip *chip)
 	/* hash algorithm for session */
 	tpm_buf_append_u16(&buf, TPM_ALG_SHA256);
 
-	rc = tpm_transmit_cmd(chip, &buf, 0, "start auth session");
+	rc = tpm_ret_to_err(tpm_transmit_cmd(chip, &buf, 0, "StartAuthSession"));
 	tpm2_flush_context(chip, null_key);
 
 	if (rc == TPM2_RC_SUCCESS)
diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h
index 970d02c337c7..6c3aa480396b 100644
--- a/drivers/char/tpm/tpm_tis_core.h
+++ b/drivers/char/tpm/tpm_tis_core.h
@@ -54,7 +54,7 @@ enum tis_int_flags {
 enum tis_defaults {
 	TIS_MEM_LEN = 0x5000,
 	TIS_SHORT_TIMEOUT = 750,	/* ms */
-	TIS_LONG_TIMEOUT = 2000,	/* 2 sec */
+	TIS_LONG_TIMEOUT = 4000,	/* 4 secs */
 	TIS_TIMEOUT_MIN_ATML = 14700,	/* usecs */
 	TIS_TIMEOUT_MAX_ATML = 15000,	/* usecs */
 };
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 5f04951d0dd4..088182e54deb 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1576,8 +1576,8 @@ static void handle_control_message(struct virtio_device *vdev,
 		break;
 	case VIRTIO_CONSOLE_RESIZE: {
 		struct {
-			__u16 rows;
-			__u16 cols;
+			__virtio16 cols;
+			__virtio16 rows;
 		} size;
 
 		if (!is_console_port(port))
@@ -1585,7 +1585,8 @@ static void handle_control_message(struct virtio_device *vdev,
 
 		memcpy(&size, buf->buf + buf->offset + sizeof(*cpkt),
 		       sizeof(size));
-		set_console_size(port, size.rows, size.cols);
+		set_console_size(port, virtio16_to_cpu(vdev, size.rows),
+				 virtio16_to_cpu(vdev, size.cols));
 
 		port->cons.hvc->irq_requested = 1;
 		resize_console(port);
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
index 014db6386624..8ddf3a9a53df 100644
--- a/drivers/clk/clk-s2mps11.c
+++ b/drivers/clk/clk-s2mps11.c
@@ -137,6 +137,8 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 	if (!clk_data)
 		return -ENOMEM;
 
+	clk_data->num = S2MPS11_CLKS_NUM;
+
 	switch (hwid) {
 	case S2MPS11X:
 		s2mps11_reg = S2MPS11_REG_RTC_CTRL;
@@ -186,7 +188,6 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 		clk_data->hws[i] = &s2mps11_clks[i].hw;
 	}
 
-	clk_data->num = S2MPS11_CLKS_NUM;
 	of_clk_add_hw_provider(s2mps11_clks->clk_np, of_clk_hw_onecell_get,
 			       clk_data);
 
diff --git a/drivers/clk/rockchip/clk-rk3576.c b/drivers/clk/rockchip/clk-rk3576.c
index 595e010341f7..be703f250197 100644
--- a/drivers/clk/rockchip/clk-rk3576.c
+++ b/drivers/clk/rockchip/clk-rk3576.c
@@ -541,6 +541,8 @@ static struct rockchip_clk_branch rk3576_clk_branches[] __initdata = {
 			RK3576_CLKGATE_CON(5), 14, GFLAGS),
 	GATE(CLK_OTPC_AUTO_RD_G, "clk_otpc_auto_rd_g", "xin24m", 0,
 			RK3576_CLKGATE_CON(5), 15, GFLAGS),
+	GATE(CLK_OTP_PHY_G, "clk_otp_phy_g", "xin24m", 0,
+			RK3576_CLKGATE_CON(6), 0, GFLAGS),
 	COMPOSITE(CLK_MIPI_CAMERAOUT_M0, "clk_mipi_cameraout_m0", mux_24m_spll_gpll_cpll_p, 0,
 			RK3576_CLKSEL_CON(38), 8, 2, MFLAGS, 0, 8, DFLAGS,
 			RK3576_CLKGATE_CON(6), 3, GFLAGS),
diff --git a/drivers/clk/sunxi-ng/ccu-sun20i-d1.c b/drivers/clk/sunxi-ng/ccu-sun20i-d1.c
index bb66c906ebbb..e83d4fd40240 100644
--- a/drivers/clk/sunxi-ng/ccu-sun20i-d1.c
+++ b/drivers/clk/sunxi-ng/ccu-sun20i-d1.c
@@ -412,19 +412,23 @@ static const struct clk_parent_data mmc0_mmc1_parents[] = {
 	{ .hw = &pll_periph0_2x_clk.common.hw },
 	{ .hw = &pll_audio1_div2_clk.common.hw },
 };
-static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc0_clk, "mmc0", mmc0_mmc1_parents, 0x830,
-				       0, 4,	/* M */
-				       8, 2,	/* P */
-				       24, 3,	/* mux */
-				       BIT(31),	/* gate */
-				       0);
-
-static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc1_clk, "mmc1", mmc0_mmc1_parents, 0x834,
-				       0, 4,	/* M */
-				       8, 2,	/* P */
-				       24, 3,	/* mux */
-				       BIT(31),	/* gate */
-				       0);
+static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc0_clk, "mmc0",
+					       mmc0_mmc1_parents, 0x830,
+					       0, 4,		/* M */
+					       8, 2,		/* P */
+					       24, 3,		/* mux */
+					       BIT(31),		/* gate */
+					       2,		/* post-div */
+					       0);
+
+static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1",
+					       mmc0_mmc1_parents, 0x834,
+					       0, 4,		/* M */
+					       8, 2,		/* P */
+					       24, 3,		/* mux */
+					       BIT(31),		/* gate */
+					       2,		/* post-div */
+					       0);
 
 static const struct clk_parent_data mmc2_parents[] = {
 	{ .fw_name = "hosc" },
@@ -433,12 +437,14 @@ static const struct clk_parent_data mmc2_parents[] = {
 	{ .hw = &pll_periph0_800M_clk.common.hw },
 	{ .hw = &pll_audio1_div2_clk.common.hw },
 };
-static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc2_clk, "mmc2", mmc2_parents, 0x838,
-				       0, 4,	/* M */
-				       8, 2,	/* P */
-				       24, 3,	/* mux */
-				       BIT(31),	/* gate */
-				       0);
+static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2", mmc2_parents,
+					       0x838,
+					       0, 4,		/* M */
+					       8, 2,		/* P */
+					       24, 3,		/* mux */
+					       BIT(31),		/* gate */
+					       2,		/* post-div */
+					       0);
 
 static SUNXI_CCU_GATE_HWS(bus_mmc0_clk, "bus-mmc0", psi_ahb_hws,
 			  0x84c, BIT(0), 0);
diff --git a/drivers/clk/sunxi-ng/ccu_mp.h b/drivers/clk/sunxi-ng/ccu_mp.h
index b35aeec70484..bb09c649bfa3 100644
--- a/drivers/clk/sunxi-ng/ccu_mp.h
+++ b/drivers/clk/sunxi-ng/ccu_mp.h
@@ -52,6 +52,28 @@ struct ccu_mp {
 		}							\
 	}
 
+#define SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(_struct, _name, _parents, \
+						_reg,			\
+						_mshift, _mwidth,	\
+						_pshift, _pwidth,	\
+						_muxshift, _muxwidth,	\
+						_gate, _postdiv, _flags)\
+	struct ccu_mp _struct = {					\
+		.enable	= _gate,					\
+		.m	= _SUNXI_CCU_DIV(_mshift, _mwidth),		\
+		.p	= _SUNXI_CCU_DIV(_pshift, _pwidth),		\
+		.mux	= _SUNXI_CCU_MUX(_muxshift, _muxwidth),		\
+		.fixed_post_div	= _postdiv,				\
+		.common	= {						\
+			.reg		= _reg,				\
+			.features	= CCU_FEATURE_FIXED_POSTDIV,	\
+			.hw.init	= CLK_HW_INIT_PARENTS_DATA(_name, \
+							_parents,	\
+							&ccu_mp_ops,	\
+							_flags),	\
+		}							\
+	}
+
 #define SUNXI_CCU_MP_WITH_MUX_GATE(_struct, _name, _parents, _reg,	\
 				   _mshift, _mwidth,			\
 				   _pshift, _pwidth,			\
@@ -109,8 +131,7 @@ struct ccu_mp {
 					     _mshift, _mwidth,		\
 					     _pshift, _pwidth,		\
 					     _muxshift, _muxwidth,	\
-					     _gate, _features,		\
-					     _flags)			\
+					     _gate, _flags, _features)	\
 	struct ccu_mp _struct = {					\
 		.enable	= _gate,					\
 		.m	= _SUNXI_CCU_DIV(_mshift, _mwidth),		\
diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
index 39f7c2d736d1..b603c25f3dfa 100644
--- a/drivers/clocksource/i8253.c
+++ b/drivers/clocksource/i8253.c
@@ -103,7 +103,7 @@ int __init clocksource_i8253_init(void)
 #ifdef CONFIG_CLKEVT_I8253
 void clockevent_i8253_disable(void)
 {
-	raw_spin_lock(&i8253_lock);
+	guard(raw_spinlock_irqsave)(&i8253_lock);
 
 	/*
 	 * Writing the MODE register should stop the counter, according to
@@ -132,8 +132,6 @@ void clockevent_i8253_disable(void)
 	outb_p(0, PIT_CH0);
 
 	outb_p(0x30, PIT_MODE);
-
-	raw_spin_unlock(&i8253_lock);
 }
 
 static int pit_shutdown(struct clock_event_device *evt)
diff --git a/drivers/comedi/drivers/jr3_pci.c b/drivers/comedi/drivers/jr3_pci.c
index cdc842b32bab..75dce1ff2419 100644
--- a/drivers/comedi/drivers/jr3_pci.c
+++ b/drivers/comedi/drivers/jr3_pci.c
@@ -758,7 +758,7 @@ static void jr3_pci_detach(struct comedi_device *dev)
 	struct jr3_pci_dev_private *devpriv = dev->private;
 
 	if (devpriv)
-		timer_delete_sync(&devpriv->timer);
+		timer_shutdown_sync(&devpriv->timer);
 
 	comedi_pci_detach(dev);
 }
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 4f9cb943d945..0d46402e3094 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -76,7 +76,7 @@ config ARM_VEXPRESS_SPC_CPUFREQ
 config ARM_BRCMSTB_AVS_CPUFREQ
 	tristate "Broadcom STB AVS CPUfreq driver"
 	depends on (ARCH_BRCMSTB && !ARM_SCMI_CPUFREQ) || COMPILE_TEST
-	default y
+	default y if ARCH_BRCMSTB && !ARM_SCMI_CPUFREQ
 	help
 	  Some Broadcom STB SoCs use a co-processor running proprietary firmware
 	  ("AVS") to handle voltage and frequency scaling. This driver provides
@@ -88,7 +88,7 @@ config ARM_HIGHBANK_CPUFREQ
 	tristate "Calxeda Highbank-based"
 	depends on ARCH_HIGHBANK || COMPILE_TEST
 	depends on CPUFREQ_DT && REGULATOR && PL320_MBOX
-	default m
+	default m if ARCH_HIGHBANK
 	help
 	  This adds the CPUFreq driver for Calxeda Highbank SoC
 	  based boards.
@@ -133,7 +133,7 @@ config ARM_MEDIATEK_CPUFREQ
 config ARM_MEDIATEK_CPUFREQ_HW
 	tristate "MediaTek CPUFreq HW driver"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
-	default m
+	default m if ARCH_MEDIATEK
 	help
 	  Support for the CPUFreq HW driver.
 	  Some MediaTek chipsets have a HW engine to offload the steps
@@ -181,7 +181,7 @@ config ARM_RASPBERRYPI_CPUFREQ
 config ARM_S3C64XX_CPUFREQ
 	bool "Samsung S3C64XX"
 	depends on CPU_S3C6410 || COMPILE_TEST
-	default y
+	default CPU_S3C6410
 	help
 	  This adds the CPUFreq driver for Samsung S3C6410 SoC.
 
@@ -190,7 +190,7 @@ config ARM_S3C64XX_CPUFREQ
 config ARM_S5PV210_CPUFREQ
 	bool "Samsung S5PV210 and S5PC110"
 	depends on CPU_S5PV210 || COMPILE_TEST
-	default y
+	default CPU_S5PV210
 	help
 	  This adds the CPUFreq driver for Samsung S5PV210 and
 	  S5PC110 SoCs.
@@ -214,7 +214,7 @@ config ARM_SCMI_CPUFREQ
 config ARM_SPEAR_CPUFREQ
 	bool "SPEAr CPUFreq support"
 	depends on PLAT_SPEAR || COMPILE_TEST
-	default y
+	default PLAT_SPEAR
 	help
 	  This adds the CPUFreq driver support for SPEAr SOCs.
 
@@ -233,7 +233,7 @@ config ARM_TEGRA20_CPUFREQ
 	tristate "Tegra20/30 CPUFreq support"
 	depends on ARCH_TEGRA || COMPILE_TEST
 	depends on CPUFREQ_DT
-	default y
+	default ARCH_TEGRA
 	help
 	  This adds the CPUFreq driver support for Tegra20/30 SOCs.
 
@@ -241,7 +241,7 @@ config ARM_TEGRA124_CPUFREQ
 	bool "Tegra124 CPUFreq support"
 	depends on ARCH_TEGRA || COMPILE_TEST
 	depends on CPUFREQ_DT
-	default y
+	default ARCH_TEGRA
 	help
 	  This adds the CPUFreq driver support for Tegra124 SOCs.
 
@@ -256,14 +256,14 @@ config ARM_TEGRA194_CPUFREQ
 	tristate "Tegra194 CPUFreq support"
 	depends on ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC || (64BIT && COMPILE_TEST)
 	depends on TEGRA_BPMP
-	default y
+	default ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC
 	help
 	  This adds CPU frequency driver support for Tegra194 SOCs.
 
 config ARM_TI_CPUFREQ
 	bool "Texas Instruments CPUFreq support"
 	depends on ARCH_OMAP2PLUS || ARCH_K3 || COMPILE_TEST
-	default y
+	default ARCH_OMAP2PLUS || ARCH_K3
 	help
 	  This driver enables valid OPPs on the running platform based on
 	  values contained within the SoC in use. Enable this in order to
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 924314cdeebc..d26b610e4f24 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -909,8 +909,19 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	if (perf->states[0].core_frequency * 1000 != freq_table[0].frequency)
 		pr_warn(FW_WARN "P-state 0 is not max freq\n");
 
-	if (acpi_cpufreq_driver.set_boost)
-		policy->boost_supported = true;
+	if (acpi_cpufreq_driver.set_boost) {
+		if (policy->boost_supported) {
+			/*
+			 * The firmware may have altered boost state while the
+			 * CPU was offline (for example during a suspend-resume
+			 * cycle).
+			 */
+			if (policy->boost_enabled != boost_state(cpu))
+				set_boost(policy, policy->boost_enabled);
+		} else {
+			policy->boost_supported = true;
+		}
+	}
 
 	return result;
 
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 6789eed1bb5b..b961f3a3b580 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -607,13 +607,16 @@ static void amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
 	union perf_cached perf = READ_ONCE(cpudata->perf);
 
 	perf.max_limit_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->max);
-	perf.min_limit_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->min);
+	WRITE_ONCE(cpudata->max_limit_freq, policy->max);
 
-	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
+	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		perf.min_limit_perf = min(perf.nominal_perf, perf.max_limit_perf);
+		WRITE_ONCE(cpudata->min_limit_freq, min(cpudata->nominal_freq, cpudata->max_limit_freq));
+	} else {
+		perf.min_limit_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->min);
+		WRITE_ONCE(cpudata->min_limit_freq, policy->min);
+	}
 
-	WRITE_ONCE(cpudata->max_limit_freq, policy->max);
-	WRITE_ONCE(cpudata->min_limit_freq, policy->min);
 	WRITE_ONCE(cpudata->perf, perf);
 }
 
@@ -791,16 +794,6 @@ static void amd_perf_ctl_reset(unsigned int cpu)
 	wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0);
 }
 
-/*
- * Set amd-pstate preferred core enable can't be done directly from cpufreq callbacks
- * due to locking, so queue the work for later.
- */
-static void amd_pstste_sched_prefcore_workfn(struct work_struct *work)
-{
-	sched_set_itmt_support();
-}
-static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn);
-
 #define CPPC_MAX_PERF	U8_MAX
 
 static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
@@ -811,14 +804,8 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
 
 	cpudata->hw_prefcore = true;
 
-	/*
-	 * The priorities can be set regardless of whether or not
-	 * sched_set_itmt_support(true) has been called and it is valid to
-	 * update them at any time after it has been called.
-	 */
+	/* Priorities must be initialized before ITMT support can be toggled on. */
 	sched_set_itmt_core_prio((int)READ_ONCE(cpudata->prefcore_ranking), cpudata->cpu);
-
-	schedule_work(&sched_prefcore_work);
 }
 
 static void amd_pstate_update_limits(unsigned int cpu)
@@ -1193,6 +1180,9 @@ static ssize_t show_energy_performance_preference(
 
 static void amd_pstate_driver_cleanup(void)
 {
+	if (amd_pstate_prefcore)
+		sched_clear_itmt_support();
+
 	cppc_state = AMD_PSTATE_DISABLE;
 	current_pstate_driver = NULL;
 }
@@ -1235,6 +1225,10 @@ static int amd_pstate_register_driver(int mode)
 		return ret;
 	}
 
+	/* Enable ITMT support once all CPUs have initialized their asym priorities. */
+	if (amd_pstate_prefcore)
+		sched_set_itmt_support();
+
 	return 0;
 }
 
diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c
index 4994c86feb57..b1d29b7af232 100644
--- a/drivers/cpufreq/apple-soc-cpufreq.c
+++ b/drivers/cpufreq/apple-soc-cpufreq.c
@@ -134,11 +134,17 @@ static const struct of_device_id apple_soc_cpufreq_of_match[] __maybe_unused = {
 
 static unsigned int apple_soc_cpufreq_get_rate(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	struct apple_cpu_priv *priv = policy->driver_data;
+	struct cpufreq_policy *policy;
+	struct apple_cpu_priv *priv;
 	struct cpufreq_frequency_table *p;
 	unsigned int pstate;
 
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (unlikely(!policy))
+		return 0;
+
+	priv = policy->driver_data;
+
 	if (priv->info->cur_pstate_mask) {
 		u32 reg = readl_relaxed(priv->reg_base + APPLE_DVFS_STATUS);
 
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index b3d74f9adcf0..cb93f00bafdb 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -747,7 +747,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 	int ret;
 
 	if (!policy)
-		return -ENODEV;
+		return 0;
 
 	cpu_data = policy->driver_data;
 
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 2aa00769cf09..a010da0f6337 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -175,6 +175,7 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "qcom,sm8350", },
 	{ .compatible = "qcom,sm8450", },
 	{ .compatible = "qcom,sm8550", },
+	{ .compatible = "qcom,sm8650", },
 
 	{ .compatible = "st,stih407", },
 	{ .compatible = "st,stih410", },
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 3841c9da6cac..f45ded62b0e0 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -536,16 +536,18 @@ void cpufreq_disable_fast_switch(struct cpufreq_policy *policy)
 EXPORT_SYMBOL_GPL(cpufreq_disable_fast_switch);
 
 static unsigned int __resolve_freq(struct cpufreq_policy *policy,
-		unsigned int target_freq, unsigned int relation)
+				   unsigned int target_freq,
+				   unsigned int min, unsigned int max,
+				   unsigned int relation)
 {
 	unsigned int idx;
 
-	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	target_freq = clamp_val(target_freq, min, max);
 
 	if (!policy->freq_table)
 		return target_freq;
 
-	idx = cpufreq_frequency_table_target(policy, target_freq, relation);
+	idx = cpufreq_frequency_table_target(policy, target_freq, min, max, relation);
 	policy->cached_resolved_idx = idx;
 	policy->cached_target_freq = target_freq;
 	return policy->freq_table[idx].frequency;
@@ -565,7 +567,21 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy,
 unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy,
 					 unsigned int target_freq)
 {
-	return __resolve_freq(policy, target_freq, CPUFREQ_RELATION_LE);
+	unsigned int min = READ_ONCE(policy->min);
+	unsigned int max = READ_ONCE(policy->max);
+
+	/*
+	 * If this function runs in parallel with cpufreq_set_policy(), it may
+	 * read policy->min before the update and policy->max after the update
+	 * or the other way around, so there is no ordering guarantee.
+	 *
+	 * Resolve this by always honoring the max (in case it comes from
+	 * thermal throttling or similar).
+	 */
+	if (unlikely(min > max))
+		min = max;
+
+	return __resolve_freq(policy, target_freq, min, max, CPUFREQ_RELATION_LE);
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq);
 
@@ -2384,7 +2400,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	if (cpufreq_disabled())
 		return -ENODEV;
 
-	target_freq = __resolve_freq(policy, target_freq, relation);
+	target_freq = __resolve_freq(policy, target_freq, policy->min,
+				     policy->max, relation);
 
 	pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n",
 		 policy->cpu, target_freq, relation, old_target_freq);
@@ -2708,11 +2725,18 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	 * Resolve policy min/max to available frequencies. It ensures
 	 * no frequency resolution will neither overshoot the requested maximum
 	 * nor undershoot the requested minimum.
+	 *
+	 * Avoid storing intermediate values in policy->max or policy->min and
+	 * compiler optimizations around them because they may be accessed
+	 * concurrently by cpufreq_driver_resolve_freq() during the update.
 	 */
-	policy->min = new_data.min;
-	policy->max = new_data.max;
-	policy->min = __resolve_freq(policy, policy->min, CPUFREQ_RELATION_L);
-	policy->max = __resolve_freq(policy, policy->max, CPUFREQ_RELATION_H);
+	WRITE_ONCE(policy->max, __resolve_freq(policy, new_data.max,
+					       new_data.min, new_data.max,
+					       CPUFREQ_RELATION_H));
+	new_data.min = __resolve_freq(policy, new_data.min, new_data.min,
+				      new_data.max, CPUFREQ_RELATION_L);
+	WRITE_ONCE(policy->min, new_data.min > policy->max ? policy->max : new_data.min);
+
 	trace_cpu_frequency_limits(policy);
 
 	cpufreq_update_pressure(policy);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index a7c38b8b3e78..0e65d37c9231 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -76,7 +76,8 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy,
 		return freq_next;
 	}
 
-	index = cpufreq_frequency_table_target(policy, freq_next, relation);
+	index = cpufreq_frequency_table_target(policy, freq_next, policy->min,
+					       policy->max, relation);
 	freq_req = freq_table[index].frequency;
 	freq_reduc = freq_req * od_tuners->powersave_bias / 1000;
 	freq_avg = freq_req - freq_reduc;
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index c03a91502f84..35de513af6c9 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -115,8 +115,8 @@ int cpufreq_generic_frequency_table_verify(struct cpufreq_policy_data *policy)
 EXPORT_SYMBOL_GPL(cpufreq_generic_frequency_table_verify);
 
 int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
-				 unsigned int target_freq,
-				 unsigned int relation)
+				 unsigned int target_freq, unsigned int min,
+				 unsigned int max, unsigned int relation)
 {
 	struct cpufreq_frequency_table optimal = {
 		.driver_data = ~0,
@@ -147,7 +147,7 @@ int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
 	cpufreq_for_each_valid_entry_idx(pos, table, i) {
 		freq = pos->frequency;
 
-		if ((freq < policy->min) || (freq > policy->max))
+		if (freq < min || freq > max)
 			continue;
 		if (freq == target_freq) {
 			optimal.driver_data = i;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 4aad79d26c64..ba9bf06f1c77 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -598,6 +598,9 @@ static bool turbo_is_disabled(void)
 {
 	u64 misc_en;
 
+	if (!cpu_feature_enabled(X86_FEATURE_IDA))
+		return true;
+
 	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
 
 	return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
@@ -2209,7 +2212,7 @@ static int knl_get_turbo_pstate(int cpu)
 static int hwp_get_cpu_scaling(int cpu)
 {
 	if (hybrid_scaling_factor) {
-		struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+		struct cpuinfo_x86 *c = &cpu_data(cpu);
 		u8 cpu_type = c->topo.intel_type;
 
 		/*
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index c310aeebc8f3..944e899eb1be 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -37,11 +37,17 @@ static struct cpufreq_driver scmi_cpufreq_driver;
 
 static unsigned int scmi_cpufreq_get_rate(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	struct scmi_data *priv = policy->driver_data;
+	struct cpufreq_policy *policy;
+	struct scmi_data *priv;
 	unsigned long rate;
 	int ret;
 
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (unlikely(!policy))
+		return 0;
+
+	priv = policy->driver_data;
+
 	ret = perf_ops->freq_get(ph, priv->domain_id, &rate, false);
 	if (ret)
 		return 0;
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index 17cda84f00df..dcbb0ae7dd47 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -29,9 +29,16 @@ static struct scpi_ops *scpi_ops;
 
 static unsigned int scpi_cpufreq_get_rate(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	struct scpi_data *priv = policy->driver_data;
-	unsigned long rate = clk_get_rate(priv->clk);
+	struct cpufreq_policy *policy;
+	struct scpi_data *priv;
+	unsigned long rate;
+
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (unlikely(!policy))
+		return 0;
+
+	priv = policy->driver_data;
+	rate = clk_get_rate(priv->clk);
 
 	return rate / 1000;
 }
diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
index 47d6840b3489..744312a44279 100644
--- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c
+++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
@@ -194,7 +194,9 @@ static int sun50i_cpufreq_get_efuse(void)
 	struct nvmem_cell *speedbin_nvmem;
 	const struct of_device_id *match;
 	struct device *cpu_dev;
-	u32 *speedbin;
+	void *speedbin_ptr;
+	u32 speedbin = 0;
+	size_t len;
 	int ret;
 
 	cpu_dev = get_cpu_device(0);
@@ -217,14 +219,18 @@ static int sun50i_cpufreq_get_efuse(void)
 		return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem),
 				     "Could not get nvmem cell\n");
 
-	speedbin = nvmem_cell_read(speedbin_nvmem, NULL);
+	speedbin_ptr = nvmem_cell_read(speedbin_nvmem, &len);
 	nvmem_cell_put(speedbin_nvmem);
-	if (IS_ERR(speedbin))
-		return PTR_ERR(speedbin);
+	if (IS_ERR(speedbin_ptr))
+		return PTR_ERR(speedbin_ptr);
 
-	ret = opp_data->efuse_xlate(*speedbin);
+	if (len <= 4)
+		memcpy(&speedbin, speedbin_ptr, len);
+	speedbin = le32_to_cpu(speedbin);
 
-	kfree(speedbin);
+	ret = opp_data->efuse_xlate(speedbin);
+
+	kfree(speedbin_ptr);
 
 	return ret;
 };
diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
index 75bebec2c757..0fcf4a39de27 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -163,6 +163,12 @@ static int atmel_sha204a_probe(struct i2c_client *client)
 	i2c_priv->hwrng.name = dev_name(&client->dev);
 	i2c_priv->hwrng.read = atmel_sha204a_rng_read;
 
+	/*
+	 * According to review by Bill Cox [1], this HWRNG has very low entropy.
+	 * [1] https://www.metzdowd.com/pipermail/cryptography/2014-December/023858.html
+	 */
+	i2c_priv->hwrng.quality = 1;
+
 	ret = devm_hwrng_register(&client->dev, &i2c_priv->hwrng);
 	if (ret)
 		dev_warn(&client->dev, "failed to register RNG (%d)\n", ret);
diff --git a/drivers/crypto/caam/qi.c b/drivers/crypto/caam/qi.c
index 7701d00bcb3a..b6e7c0b29d4e 100644
--- a/drivers/crypto/caam/qi.c
+++ b/drivers/crypto/caam/qi.c
@@ -122,12 +122,12 @@ int caam_qi_enqueue(struct device *qidev, struct caam_drv_req *req)
 	qm_fd_addr_set64(&fd, addr);
 
 	do {
+		refcount_inc(&req->drv_ctx->refcnt);
 		ret = qman_enqueue(req->drv_ctx->req_fq, &fd);
-		if (likely(!ret)) {
-			refcount_inc(&req->drv_ctx->refcnt);
+		if (likely(!ret))
 			return 0;
-		}
 
+		refcount_dec(&req->drv_ctx->refcnt);
 		if (ret != -EBUSY)
 			break;
 		num_retries++;
diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c
index ca9d0cca1f74..0e07d0523291 100644
--- a/drivers/crypto/tegra/tegra-se-aes.c
+++ b/drivers/crypto/tegra/tegra-se-aes.c
@@ -269,7 +269,7 @@ static int tegra_aes_do_one_req(struct crypto_engine *engine, void *areq)
 	unsigned int cmdlen, key1_id, key2_id;
 	int ret;
 
-	rctx->iv = (u32 *)req->iv;
+	rctx->iv = (ctx->alg == SE_ALG_ECB) ? NULL : (u32 *)req->iv;
 	rctx->len = req->cryptlen;
 	key1_id = ctx->key1_id;
 	key2_id = ctx->key2_id;
@@ -498,9 +498,6 @@ static int tegra_aes_crypt(struct skcipher_request *req, bool encrypt)
 	if (!req->cryptlen)
 		return 0;
 
-	if (ctx->alg == SE_ALG_ECB)
-		req->iv = NULL;
-
 	rctx->encrypt = encrypt;
 
 	return crypto_transfer_skcipher_request_to_engine(ctx->se->engine, req);
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 15699299dc11..17b692eb3257 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -119,7 +119,7 @@ int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
 
 int cxl_ras_init(void);
 void cxl_ras_exit(void);
-int cxl_gpf_port_setup(struct device *dport_dev, struct cxl_port *port);
+int cxl_gpf_port_setup(struct cxl_dport *dport);
 int cxl_acpi_get_extended_linear_cache_size(struct resource *backing_res,
 					    int nid, resource_size_t *size);
 
diff --git a/drivers/cxl/core/features.c b/drivers/cxl/core/features.c
index f4daefe3180e..1498e2369c37 100644
--- a/drivers/cxl/core/features.c
+++ b/drivers/cxl/core/features.c
@@ -528,13 +528,13 @@ static void *cxlctl_set_feature(struct cxl_features_state *cxlfs,
 	rc = cxl_set_feature(cxl_mbox, &feat_in->uuid,
 			     feat_in->version, feat_in->feat_data,
 			     data_size, flags, offset, &return_code);
+	*out_len = sizeof(*rpc_out);
 	if (rc) {
 		rpc_out->retval = return_code;
 		return no_free_ptr(rpc_out);
 	}
 
 	rpc_out->retval = CXL_MBOX_CMD_RC_SUCCESS;
-	*out_len = sizeof(*rpc_out);
 
 	return no_free_ptr(rpc_out);
 }
@@ -677,7 +677,7 @@ static void free_memdev_fwctl(void *_fwctl_dev)
 	fwctl_put(fwctl_dev);
 }
 
-int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd)
+int devm_cxl_setup_fwctl(struct device *host, struct cxl_memdev *cxlmd)
 {
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct cxl_features_state *cxlfs;
@@ -700,7 +700,7 @@ int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd)
 	if (rc)
 		return rc;
 
-	return devm_add_action_or_reset(&cxlmd->dev, free_memdev_fwctl,
+	return devm_add_action_or_reset(host, free_memdev_fwctl,
 					no_free_ptr(fwctl_dev));
 }
 EXPORT_SYMBOL_NS_GPL(devm_cxl_setup_fwctl, "CXL");
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 96fecb799cbc..3b80e9a76ba8 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -1072,14 +1072,20 @@ int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c)
 #define GPF_TIMEOUT_BASE_MAX 2
 #define GPF_TIMEOUT_SCALE_MAX 7 /* 10 seconds */
 
-u16 cxl_gpf_get_dvsec(struct device *dev, bool is_port)
+u16 cxl_gpf_get_dvsec(struct device *dev)
 {
+	struct pci_dev *pdev;
+	bool is_port = true;
 	u16 dvsec;
 
 	if (!dev_is_pci(dev))
 		return 0;
 
-	dvsec = pci_find_dvsec_capability(to_pci_dev(dev), PCI_VENDOR_ID_CXL,
+	pdev = to_pci_dev(dev);
+	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ENDPOINT)
+		is_port = false;
+
+	dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_CXL,
 			is_port ? CXL_DVSEC_PORT_GPF : CXL_DVSEC_DEVICE_GPF);
 	if (!dvsec)
 		dev_warn(dev, "%s GPF DVSEC not present\n",
@@ -1128,26 +1134,24 @@ static int update_gpf_port_dvsec(struct pci_dev *pdev, int dvsec, int phase)
 	return rc;
 }
 
-int cxl_gpf_port_setup(struct device *dport_dev, struct cxl_port *port)
+int cxl_gpf_port_setup(struct cxl_dport *dport)
 {
-	struct pci_dev *pdev;
-
-	if (!port)
+	if (!dport)
 		return -EINVAL;
 
-	if (!port->gpf_dvsec) {
+	if (!dport->gpf_dvsec) {
+		struct pci_dev *pdev;
 		int dvsec;
 
-		dvsec = cxl_gpf_get_dvsec(dport_dev, true);
+		dvsec = cxl_gpf_get_dvsec(dport->dport_dev);
 		if (!dvsec)
 			return -EINVAL;
 
-		port->gpf_dvsec = dvsec;
+		dport->gpf_dvsec = dvsec;
+		pdev = to_pci_dev(dport->dport_dev);
+		update_gpf_port_dvsec(pdev, dport->gpf_dvsec, 1);
+		update_gpf_port_dvsec(pdev, dport->gpf_dvsec, 2);
 	}
 
-	pdev = to_pci_dev(dport_dev);
-	update_gpf_port_dvsec(pdev, port->gpf_dvsec, 1);
-	update_gpf_port_dvsec(pdev, port->gpf_dvsec, 2);
-
 	return 0;
 }
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 0fd6646c1a2e..726bd4a7de27 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1678,7 +1678,7 @@ retry:
 			if (rc && rc != -EBUSY)
 				return rc;
 
-			cxl_gpf_port_setup(dport_dev, port);
+			cxl_gpf_port_setup(dport);
 
 			/* Any more ports to add between this one and the root? */
 			if (!dev_is_cxl_root_child(&port->dev))
diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c
index 117c2e94c761..5ca7b0eed568 100644
--- a/drivers/cxl/core/regs.c
+++ b/drivers/cxl/core/regs.c
@@ -581,7 +581,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
 	resource_size_t rcrb = ri->base;
 	void __iomem *addr;
 	u32 bar0, bar1;
-	u16 cmd;
 	u32 id;
 
 	if (which == CXL_RCRB_UPSTREAM)
@@ -603,7 +602,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
 	}
 
 	id = readl(addr + PCI_VENDOR_ID);
-	cmd = readw(addr + PCI_COMMAND);
 	bar0 = readl(addr + PCI_BASE_ADDRESS_0);
 	bar1 = readl(addr + PCI_BASE_ADDRESS_1);
 	iounmap(addr);
@@ -618,8 +616,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
 			dev_err(dev, "Failed to access Downstream Port RCRB\n");
 		return CXL_RESOURCE_NONE;
 	}
-	if (!(cmd & PCI_COMMAND_MEMORY))
-		return CXL_RESOURCE_NONE;
 	/* The RCRB is a Memory Window, and the MEM_TYPE_1M bit is obsolete */
 	if (bar0 & (PCI_BASE_ADDRESS_MEM_TYPE_1M | PCI_BASE_ADDRESS_SPACE_IO))
 		return CXL_RESOURCE_NONE;
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index be8a7dc77719..a9ab46eb0610 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -592,7 +592,6 @@ struct cxl_dax_region {
  * @cdat: Cached CDAT data
  * @cdat_available: Should a CDAT attribute be available in sysfs
  * @pci_latency: Upstream latency in picoseconds
- * @gpf_dvsec: Cached GPF port DVSEC
  */
 struct cxl_port {
 	struct device dev;
@@ -616,7 +615,6 @@ struct cxl_port {
 	} cdat;
 	bool cdat_available;
 	long pci_latency;
-	int gpf_dvsec;
 };
 
 /**
@@ -664,6 +662,7 @@ struct cxl_rcrb_info {
  * @regs: Dport parsed register blocks
  * @coord: access coordinates (bandwidth and latency performance attributes)
  * @link_latency: calculated PCIe downstream latency
+ * @gpf_dvsec: Cached GPF port DVSEC
  */
 struct cxl_dport {
 	struct device *dport_dev;
@@ -675,6 +674,7 @@ struct cxl_dport {
 	struct cxl_regs regs;
 	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
 	long link_latency;
+	int gpf_dvsec;
 };
 
 /**
@@ -910,6 +910,6 @@ bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port);
 #define __mock static
 #endif
 
-u16 cxl_gpf_get_dvsec(struct device *dev, bool is_port);
+u16 cxl_gpf_get_dvsec(struct device *dev);
 
 #endif /* __CXL_H__ */
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 7b14a154463c..785aa2af5eaa 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -1018,7 +1018,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (rc)
 		return rc;
 
-	rc = devm_cxl_setup_fwctl(cxlmd);
+	rc = devm_cxl_setup_fwctl(&pdev->dev, cxlmd);
 	if (rc)
 		dev_dbg(&pdev->dev, "No CXL FWCTL setup\n");
 
diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c
index d061fe3d2b86..e197883690ef 100644
--- a/drivers/cxl/pmem.c
+++ b/drivers/cxl/pmem.c
@@ -108,7 +108,7 @@ static void cxl_nvdimm_arm_dirty_shutdown_tracking(struct cxl_nvdimm *cxl_nvd)
 		return;
 	}
 
-	if (!cxl_gpf_get_dvsec(cxlds->dev, false))
+	if (!cxl_gpf_get_dvsec(cxlds->dev))
 		return;
 
 	if (cxl_get_dirty_count(mds, &count)) {
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 5f8d010516f0..b1ef4546346d 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -320,8 +320,9 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
 	count++;
 
 	dma_resv_list_set(fobj, i, fence, usage);
-	/* pointer update must be visible before we extend the num_fences */
-	smp_store_mb(fobj->num_fences, count);
+	/* fence update must be visible before we extend the num_fences */
+	smp_wmb();
+	fobj->num_fences = count;
 }
 EXPORT_SYMBOL(dma_resv_add_fence);
 
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index f5905d67dedb..22a808995f10 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -438,15 +438,17 @@ static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long a
 		return -EINVAL;
 
 	pt = dma_fence_to_sync_pt(fence);
-	if (!pt)
-		return -EINVAL;
+	if (!pt) {
+		ret = -EINVAL;
+		goto put_fence;
+	}
 
 	spin_lock_irqsave(fence->lock, flags);
-	if (test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) {
-		data.deadline_ns = ktime_to_ns(pt->deadline);
-	} else {
+	if (!test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) {
 		ret = -ENOENT;
+		goto unlock;
 	}
+	data.deadline_ns = ktime_to_ns(pt->deadline);
 	spin_unlock_irqrestore(fence->lock, flags);
 
 	dma_fence_put(fence);
@@ -458,6 +460,13 @@ static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long a
 		return -EFAULT;
 
 	return 0;
+
+unlock:
+	spin_unlock_irqrestore(fence->lock, flags);
+put_fence:
+	dma_fence_put(fence);
+
+	return ret;
 }
 
 static long sw_sync_ioctl(struct file *file, unsigned int cmd,
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index cc7398cc17d6..e74e36a8ecda 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -393,7 +393,7 @@ static long udmabuf_create(struct miscdevice *device,
 	if (!ubuf)
 		return -ENOMEM;
 
-	pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT;
+	pglimit = ((u64)size_limit_mb * 1024 * 1024) >> PAGE_SHIFT;
 	for (i = 0; i < head->count; i++) {
 		pgoff_t subpgcnt;
 
diff --git a/drivers/dma/amd/ptdma/ptdma-dmaengine.c b/drivers/dma/amd/ptdma/ptdma-dmaengine.c
index 715ac3ae067b..81339664036f 100644
--- a/drivers/dma/amd/ptdma/ptdma-dmaengine.c
+++ b/drivers/dma/amd/ptdma/ptdma-dmaengine.c
@@ -342,6 +342,9 @@ static void pt_cmd_callback_work(void *data, int err)
 	struct pt_dma_chan *chan;
 	unsigned long flags;
 
+	if (!desc)
+		return;
+
 	dma_chan = desc->vd.tx.chan;
 	chan = to_pt_chan(dma_chan);
 
@@ -355,16 +358,14 @@ static void pt_cmd_callback_work(void *data, int err)
 		desc->status = DMA_ERROR;
 
 	spin_lock_irqsave(&chan->vc.lock, flags);
-	if (desc) {
-		if (desc->status != DMA_COMPLETE) {
-			if (desc->status != DMA_ERROR)
-				desc->status = DMA_COMPLETE;
+	if (desc->status != DMA_COMPLETE) {
+		if (desc->status != DMA_ERROR)
+			desc->status = DMA_COMPLETE;
 
-			dma_cookie_complete(tx_desc);
-			dma_descriptor_unmap(tx_desc);
-		} else {
-			tx_desc = NULL;
-		}
+		dma_cookie_complete(tx_desc);
+		dma_descriptor_unmap(tx_desc);
+	} else {
+		tx_desc = NULL;
 	}
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index d891dfca358e..91b2fbc0b864 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -841,9 +841,9 @@ static int dmatest_func(void *data)
 		} else {
 			dma_async_issue_pending(chan);
 
-			wait_event_timeout(thread->done_wait,
-					   done->done,
-					   msecs_to_jiffies(params->timeout));
+			wait_event_freezable_timeout(thread->done_wait,
+					done->done,
+					msecs_to_jiffies(params->timeout));
 
 			status = dma_async_is_tx_complete(chan, cookie, NULL,
 							  NULL);
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 756d67325db5..66bfa28d984e 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -57,7 +57,7 @@ static irqreturn_t fsl_edma3_tx_handler(int irq, void *dev_id)
 
 	intr = edma_readl_chreg(fsl_chan, ch_int);
 	if (!intr)
-		return IRQ_HANDLED;
+		return IRQ_NONE;
 
 	edma_writel_chreg(fsl_chan, 1, ch_int);
 
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index ff94ee892339..6d12033649f8 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -222,7 +222,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
 	struct idxd_wq *wq;
 	struct device *dev, *fdev;
 	int rc = 0;
-	struct iommu_sva *sva;
+	struct iommu_sva *sva = NULL;
 	unsigned int pasid;
 	struct idxd_cdev *idxd_cdev;
 
@@ -317,7 +317,7 @@ failed_set_pasid:
 	if (device_user_pasid_enabled(idxd))
 		idxd_xa_pasid_remove(ctx);
 failed_get_pasid:
-	if (device_user_pasid_enabled(idxd))
+	if (device_user_pasid_enabled(idxd) && !IS_ERR_OR_NULL(sva))
 		iommu_sva_unbind_device(sva);
 failed:
 	mutex_unlock(&wq->wq_lock);
@@ -407,6 +407,9 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (!idxd->user_submission_safe && !capable(CAP_SYS_RAWIO))
 		return -EPERM;
 
+	if (current->mm != ctx->mm)
+		return -EPERM;
+
 	rc = check_vma(wq, vma, __func__);
 	if (rc < 0)
 		return rc;
@@ -473,6 +476,9 @@ static ssize_t idxd_cdev_write(struct file *filp, const char __user *buf, size_t
 	ssize_t written = 0;
 	int i;
 
+	if (current->mm != ctx->mm)
+		return -EPERM;
+
 	for (i = 0; i < len/sizeof(struct dsa_hw_desc); i++) {
 		int rc = idxd_submit_user_descriptor(ctx, udesc + i);
 
@@ -493,6 +499,9 @@ static __poll_t idxd_cdev_poll(struct file *filp,
 	struct idxd_device *idxd = wq->idxd;
 	__poll_t out = 0;
 
+	if (current->mm != ctx->mm)
+		return POLLNVAL;
+
 	poll_wait(filp, &wq->err_queue, wait);
 	spin_lock(&idxd->dev_lock);
 	if (idxd->sw_err.valid)
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index fca1d2924999..760b7d81fcd8 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -155,6 +155,25 @@ static void idxd_cleanup_interrupts(struct idxd_device *idxd)
 	pci_free_irq_vectors(pdev);
 }
 
+static void idxd_clean_wqs(struct idxd_device *idxd)
+{
+	struct idxd_wq *wq;
+	struct device *conf_dev;
+	int i;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		wq = idxd->wqs[i];
+		if (idxd->hw.wq_cap.op_config)
+			bitmap_free(wq->opcap_bmap);
+		kfree(wq->wqcfg);
+		conf_dev = wq_confdev(wq);
+		put_device(conf_dev);
+		kfree(wq);
+	}
+	bitmap_free(idxd->wq_enable_map);
+	kfree(idxd->wqs);
+}
+
 static int idxd_setup_wqs(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
@@ -169,8 +188,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 
 	idxd->wq_enable_map = bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, dev_to_node(dev));
 	if (!idxd->wq_enable_map) {
-		kfree(idxd->wqs);
-		return -ENOMEM;
+		rc = -ENOMEM;
+		goto err_bitmap;
 	}
 
 	for (i = 0; i < idxd->max_wqs; i++) {
@@ -189,10 +208,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 		conf_dev->bus = &dsa_bus_type;
 		conf_dev->type = &idxd_wq_device_type;
 		rc = dev_set_name(conf_dev, "wq%d.%d", idxd->id, wq->id);
-		if (rc < 0) {
-			put_device(conf_dev);
+		if (rc < 0)
 			goto err;
-		}
 
 		mutex_init(&wq->wq_lock);
 		init_waitqueue_head(&wq->err_queue);
@@ -203,7 +220,6 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 		wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
 		wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev));
 		if (!wq->wqcfg) {
-			put_device(conf_dev);
 			rc = -ENOMEM;
 			goto err;
 		}
@@ -211,9 +227,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 		if (idxd->hw.wq_cap.op_config) {
 			wq->opcap_bmap = bitmap_zalloc(IDXD_MAX_OPCAP_BITS, GFP_KERNEL);
 			if (!wq->opcap_bmap) {
-				put_device(conf_dev);
 				rc = -ENOMEM;
-				goto err;
+				goto err_opcap_bmap;
 			}
 			bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS);
 		}
@@ -224,15 +239,46 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 
 	return 0;
 
- err:
+err_opcap_bmap:
+	kfree(wq->wqcfg);
+
+err:
+	put_device(conf_dev);
+	kfree(wq);
+
 	while (--i >= 0) {
 		wq = idxd->wqs[i];
+		if (idxd->hw.wq_cap.op_config)
+			bitmap_free(wq->opcap_bmap);
+		kfree(wq->wqcfg);
 		conf_dev = wq_confdev(wq);
 		put_device(conf_dev);
+		kfree(wq);
+
 	}
+	bitmap_free(idxd->wq_enable_map);
+
+err_bitmap:
+	kfree(idxd->wqs);
+
 	return rc;
 }
 
+static void idxd_clean_engines(struct idxd_device *idxd)
+{
+	struct idxd_engine *engine;
+	struct device *conf_dev;
+	int i;
+
+	for (i = 0; i < idxd->max_engines; i++) {
+		engine = idxd->engines[i];
+		conf_dev = engine_confdev(engine);
+		put_device(conf_dev);
+		kfree(engine);
+	}
+	kfree(idxd->engines);
+}
+
 static int idxd_setup_engines(struct idxd_device *idxd)
 {
 	struct idxd_engine *engine;
@@ -263,6 +309,7 @@ static int idxd_setup_engines(struct idxd_device *idxd)
 		rc = dev_set_name(conf_dev, "engine%d.%d", idxd->id, engine->id);
 		if (rc < 0) {
 			put_device(conf_dev);
+			kfree(engine);
 			goto err;
 		}
 
@@ -276,10 +323,26 @@ static int idxd_setup_engines(struct idxd_device *idxd)
 		engine = idxd->engines[i];
 		conf_dev = engine_confdev(engine);
 		put_device(conf_dev);
+		kfree(engine);
 	}
+	kfree(idxd->engines);
+
 	return rc;
 }
 
+static void idxd_clean_groups(struct idxd_device *idxd)
+{
+	struct idxd_group *group;
+	int i;
+
+	for (i = 0; i < idxd->max_groups; i++) {
+		group = idxd->groups[i];
+		put_device(group_confdev(group));
+		kfree(group);
+	}
+	kfree(idxd->groups);
+}
+
 static int idxd_setup_groups(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
@@ -310,6 +373,7 @@ static int idxd_setup_groups(struct idxd_device *idxd)
 		rc = dev_set_name(conf_dev, "group%d.%d", idxd->id, group->id);
 		if (rc < 0) {
 			put_device(conf_dev);
+			kfree(group);
 			goto err;
 		}
 
@@ -334,20 +398,18 @@ static int idxd_setup_groups(struct idxd_device *idxd)
 	while (--i >= 0) {
 		group = idxd->groups[i];
 		put_device(group_confdev(group));
+		kfree(group);
 	}
+	kfree(idxd->groups);
+
 	return rc;
 }
 
 static void idxd_cleanup_internals(struct idxd_device *idxd)
 {
-	int i;
-
-	for (i = 0; i < idxd->max_groups; i++)
-		put_device(group_confdev(idxd->groups[i]));
-	for (i = 0; i < idxd->max_engines; i++)
-		put_device(engine_confdev(idxd->engines[i]));
-	for (i = 0; i < idxd->max_wqs; i++)
-		put_device(wq_confdev(idxd->wqs[i]));
+	idxd_clean_groups(idxd);
+	idxd_clean_engines(idxd);
+	idxd_clean_wqs(idxd);
 	destroy_workqueue(idxd->wq);
 }
 
@@ -390,7 +452,7 @@ static int idxd_init_evl(struct idxd_device *idxd)
 static int idxd_setup_internals(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
-	int rc, i;
+	int rc;
 
 	init_waitqueue_head(&idxd->cmd_waitq);
 
@@ -421,14 +483,11 @@ static int idxd_setup_internals(struct idxd_device *idxd)
  err_evl:
 	destroy_workqueue(idxd->wq);
  err_wkq_create:
-	for (i = 0; i < idxd->max_groups; i++)
-		put_device(group_confdev(idxd->groups[i]));
+	idxd_clean_groups(idxd);
  err_group:
-	for (i = 0; i < idxd->max_engines; i++)
-		put_device(engine_confdev(idxd->engines[i]));
+	idxd_clean_engines(idxd);
  err_engine:
-	for (i = 0; i < idxd->max_wqs; i++)
-		put_device(wq_confdev(idxd->wqs[i]));
+	idxd_clean_wqs(idxd);
  err_wqs:
 	return rc;
 }
@@ -528,6 +587,17 @@ static void idxd_read_caps(struct idxd_device *idxd)
 		idxd->hw.iaa_cap.bits = ioread64(idxd->reg_base + IDXD_IAACAP_OFFSET);
 }
 
+static void idxd_free(struct idxd_device *idxd)
+{
+	if (!idxd)
+		return;
+
+	put_device(idxd_confdev(idxd));
+	bitmap_free(idxd->opcap_bmap);
+	ida_free(&idxd_ida, idxd->id);
+	kfree(idxd);
+}
+
 static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_data *data)
 {
 	struct device *dev = &pdev->dev;
@@ -545,28 +615,34 @@ static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_d
 	idxd_dev_set_type(&idxd->idxd_dev, idxd->data->type);
 	idxd->id = ida_alloc(&idxd_ida, GFP_KERNEL);
 	if (idxd->id < 0)
-		return NULL;
+		goto err_ida;
 
 	idxd->opcap_bmap = bitmap_zalloc_node(IDXD_MAX_OPCAP_BITS, GFP_KERNEL, dev_to_node(dev));
-	if (!idxd->opcap_bmap) {
-		ida_free(&idxd_ida, idxd->id);
-		return NULL;
-	}
+	if (!idxd->opcap_bmap)
+		goto err_opcap;
 
 	device_initialize(conf_dev);
 	conf_dev->parent = dev;
 	conf_dev->bus = &dsa_bus_type;
 	conf_dev->type = idxd->data->dev_type;
 	rc = dev_set_name(conf_dev, "%s%d", idxd->data->name_prefix, idxd->id);
-	if (rc < 0) {
-		put_device(conf_dev);
-		return NULL;
-	}
+	if (rc < 0)
+		goto err_name;
 
 	spin_lock_init(&idxd->dev_lock);
 	spin_lock_init(&idxd->cmd_lock);
 
 	return idxd;
+
+err_name:
+	put_device(conf_dev);
+	bitmap_free(idxd->opcap_bmap);
+err_opcap:
+	ida_free(&idxd_ida, idxd->id);
+err_ida:
+	kfree(idxd);
+
+	return NULL;
 }
 
 static int idxd_enable_system_pasid(struct idxd_device *idxd)
@@ -1190,7 +1266,7 @@ int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev,
  err:
 	pci_iounmap(pdev, idxd->reg_base);
  err_iomap:
-	put_device(idxd_confdev(idxd));
+	idxd_free(idxd);
  err_idxd_alloc:
 	pci_disable_device(pdev);
 	return rc;
@@ -1232,7 +1308,6 @@ static void idxd_shutdown(struct pci_dev *pdev)
 static void idxd_remove(struct pci_dev *pdev)
 {
 	struct idxd_device *idxd = pci_get_drvdata(pdev);
-	struct idxd_irq_entry *irq_entry;
 
 	idxd_unregister_devices(idxd);
 	/*
@@ -1245,20 +1320,12 @@ static void idxd_remove(struct pci_dev *pdev)
 	get_device(idxd_confdev(idxd));
 	device_unregister(idxd_confdev(idxd));
 	idxd_shutdown(pdev);
-	if (device_pasid_enabled(idxd))
-		idxd_disable_system_pasid(idxd);
 	idxd_device_remove_debugfs(idxd);
-
-	irq_entry = idxd_get_ie(idxd, 0);
-	free_irq(irq_entry->vector, irq_entry);
-	pci_free_irq_vectors(pdev);
+	idxd_cleanup(idxd);
 	pci_iounmap(pdev, idxd->reg_base);
-	if (device_user_pasid_enabled(idxd))
-		idxd_disable_sva(pdev);
-	pci_disable_device(pdev);
-	destroy_workqueue(idxd->wq);
-	perfmon_pmu_remove(idxd);
 	put_device(idxd_confdev(idxd));
+	idxd_free(idxd);
+	pci_disable_device(pdev);
 }
 
 static struct pci_driver idxd_pci_driver = {
diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c
index d5ddb4e30e71..47c8adfdc155 100644
--- a/drivers/dma/mediatek/mtk-cqdma.c
+++ b/drivers/dma/mediatek/mtk-cqdma.c
@@ -420,15 +420,11 @@ static struct virt_dma_desc *mtk_cqdma_find_active_desc(struct dma_chan *c,
 {
 	struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
 	struct virt_dma_desc *vd;
-	unsigned long flags;
 
-	spin_lock_irqsave(&cvc->pc->lock, flags);
 	list_for_each_entry(vd, &cvc->pc->queue, node)
 		if (vd->tx.cookie == cookie) {
-			spin_unlock_irqrestore(&cvc->pc->lock, flags);
 			return vd;
 		}
-	spin_unlock_irqrestore(&cvc->pc->lock, flags);
 
 	list_for_each_entry(vd, &cvc->vc.desc_issued, node)
 		if (vd->tx.cookie == cookie)
@@ -452,9 +448,11 @@ static enum dma_status mtk_cqdma_tx_status(struct dma_chan *c,
 	if (ret == DMA_COMPLETE || !txstate)
 		return ret;
 
+	spin_lock_irqsave(&cvc->pc->lock, flags);
 	spin_lock_irqsave(&cvc->vc.lock, flags);
 	vd = mtk_cqdma_find_active_desc(c, cookie);
 	spin_unlock_irqrestore(&cvc->vc.lock, flags);
+	spin_unlock_irqrestore(&cvc->pc->lock, flags);
 
 	if (vd) {
 		cvd = to_cqdma_vdesc(vd);
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index b223a7aacb0c..b6255c0601bb 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -1091,8 +1091,11 @@ static void udma_check_tx_completion(struct work_struct *work)
 	u32 residue_diff;
 	ktime_t time_diff;
 	unsigned long delay;
+	unsigned long flags;
 
 	while (1) {
+		spin_lock_irqsave(&uc->vc.lock, flags);
+
 		if (uc->desc) {
 			/* Get previous residue and time stamp */
 			residue_diff = uc->tx_drain.residue;
@@ -1127,6 +1130,8 @@ static void udma_check_tx_completion(struct work_struct *work)
 				break;
 			}
 
+			spin_unlock_irqrestore(&uc->vc.lock, flags);
+
 			usleep_range(ktime_to_us(delay),
 				     ktime_to_us(delay) + 10);
 			continue;
@@ -1143,6 +1148,8 @@ static void udma_check_tx_completion(struct work_struct *work)
 
 		break;
 	}
+
+	spin_unlock_irqrestore(&uc->vc.lock, flags);
 }
 
 static irqreturn_t udma_ring_irq_handler(int irq, void *data)
@@ -4246,7 +4253,6 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
 				      struct of_dma *ofdma)
 {
 	struct udma_dev *ud = ofdma->of_dma_data;
-	dma_cap_mask_t mask = ud->ddev.cap_mask;
 	struct udma_filter_param filter_param;
 	struct dma_chan *chan;
 
@@ -4278,7 +4284,7 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
 		}
 	}
 
-	chan = __dma_request_channel(&mask, udma_dma_filter_fn, &filter_param,
+	chan = __dma_request_channel(&ud->ddev.cap_mask, udma_dma_filter_fn, &filter_param,
 				     ofdma->of_node);
 	if (!chan) {
 		dev_err(ud->dev, "get channel fail in %s.\n", __func__);
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index 3e971f902363..dcd7008fe06b 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -99,7 +99,7 @@ static irqreturn_t altr_sdram_mc_err_handler(int irq, void *dev_id)
 	if (status & priv->ecc_stat_ce_mask) {
 		regmap_read(drvdata->mc_vbase, priv->ecc_saddr_offset,
 			    &err_addr);
-		if (priv->ecc_uecnt_offset)
+		if (priv->ecc_cecnt_offset)
 			regmap_read(drvdata->mc_vbase,  priv->ecc_cecnt_offset,
 				    &err_count);
 		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, err_count,
@@ -1005,9 +1005,6 @@ altr_init_a10_ecc_block(struct device_node *np, u32 irq_mask,
 		}
 	}
 
-	/* Interrupt mode set to every SBERR */
-	regmap_write(ecc_mgr_map, ALTR_A10_ECC_INTMODE_OFST,
-		     ALTR_A10_ECC_INTMODE);
 	/* Enable ECC */
 	ecc_set_bits(ecc_ctrl_en_mask, (ecc_block_base +
 					ALTR_A10_ECC_CTRL_OFST));
@@ -2127,6 +2124,10 @@ static int altr_edac_a10_probe(struct platform_device *pdev)
 		return PTR_ERR(edac->ecc_mgr_map);
 	}
 
+	/* Set irq mask for DDR SBE to avoid any pending irq before registration */
+	regmap_write(edac->ecc_mgr_map, A10_SYSMGR_ECC_INTMASK_SET_OFST,
+		     (A10_SYSMGR_ECC_INTMASK_SDMMCB | A10_SYSMGR_ECC_INTMASK_DDR0));
+
 	edac->irq_chip.name = pdev->dev.of_node->name;
 	edac->irq_chip.irq_mask = a10_eccmgr_irq_mask;
 	edac->irq_chip.irq_unmask = a10_eccmgr_irq_unmask;
diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h
index 3727e72c8c2e..7248d24c4908 100644
--- a/drivers/edac/altera_edac.h
+++ b/drivers/edac/altera_edac.h
@@ -249,6 +249,8 @@ struct altr_sdram_mc_data {
 #define A10_SYSMGR_ECC_INTMASK_SET_OFST   0x94
 #define A10_SYSMGR_ECC_INTMASK_CLR_OFST   0x98
 #define A10_SYSMGR_ECC_INTMASK_OCRAM      BIT(1)
+#define A10_SYSMGR_ECC_INTMASK_SDMMCB     BIT(16)
+#define A10_SYSMGR_ECC_INTMASK_DDR0       BIT(17)
 
 #define A10_SYSMGR_ECC_INTSTAT_SERR_OFST  0x9C
 #define A10_SYSMGR_ECC_INTSTAT_DERR_OFST  0xA0
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 19295282de24..fe55613a8ea9 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -299,7 +299,8 @@ __ffa_partition_info_get(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3,
 				import_uuid(&buf->uuid, (u8 *)&rx_buf->uuid);
 		}
 
-	ffa_rx_release();
+	if (!(flags & PARTITION_INFO_GET_RETURN_COUNT_ONLY))
+		ffa_rx_release();
 
 	mutex_unlock(&drv_info->rx_lock);
 
diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c
index 7af01664ce7e..3a5474015f7d 100644
--- a/drivers/firmware/arm_scmi/bus.c
+++ b/drivers/firmware/arm_scmi/bus.c
@@ -255,6 +255,9 @@ static struct scmi_device *scmi_child_dev_find(struct device *parent,
 	if (!dev)
 		return NULL;
 
+	/* Drop the refcnt bumped implicitly by device_find_child */
+	put_device(dev);
+
 	return to_scmi_dev(dev);
 }
 
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index 1c75a4c9c371..0390d5ff195e 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -1248,7 +1248,8 @@ static void xfer_put(const struct scmi_protocol_handle *ph,
 }
 
 static bool scmi_xfer_done_no_timeout(struct scmi_chan_info *cinfo,
-				      struct scmi_xfer *xfer, ktime_t stop)
+				      struct scmi_xfer *xfer, ktime_t stop,
+				      bool *ooo)
 {
 	struct scmi_info *info = handle_to_scmi_info(cinfo->handle);
 
@@ -1257,7 +1258,7 @@ static bool scmi_xfer_done_no_timeout(struct scmi_chan_info *cinfo,
 	 * in case of out-of-order receptions of delayed responses
 	 */
 	return info->desc->ops->poll_done(cinfo, xfer) ||
-	       try_wait_for_completion(&xfer->done) ||
+	       (*ooo = try_wait_for_completion(&xfer->done)) ||
 	       ktime_after(ktime_get(), stop);
 }
 
@@ -1274,15 +1275,17 @@ static int scmi_wait_for_reply(struct device *dev, const struct scmi_desc *desc,
 		 * itself to support synchronous commands replies.
 		 */
 		if (!desc->sync_cmds_completed_on_ret) {
+			bool ooo = false;
+
 			/*
 			 * Poll on xfer using transport provided .poll_done();
 			 * assumes no completion interrupt was available.
 			 */
 			ktime_t stop = ktime_add_ms(ktime_get(), timeout_ms);
 
-			spin_until_cond(scmi_xfer_done_no_timeout(cinfo,
-								  xfer, stop));
-			if (ktime_after(ktime_get(), stop)) {
+			spin_until_cond(scmi_xfer_done_no_timeout(cinfo, xfer,
+								  stop, &ooo));
+			if (!ooo && !info->desc->ops->poll_done(cinfo, xfer)) {
 				dev_err(dev,
 					"timed out in resp(caller: %pS) - polling\n",
 					(void *)_RET_IP_);
diff --git a/drivers/firmware/cirrus/Kconfig b/drivers/firmware/cirrus/Kconfig
index 0a883091259a..e3c2e38b746d 100644
--- a/drivers/firmware/cirrus/Kconfig
+++ b/drivers/firmware/cirrus/Kconfig
@@ -6,14 +6,11 @@ config FW_CS_DSP
 
 config FW_CS_DSP_KUNIT_TEST_UTILS
 	tristate
-	depends on KUNIT && REGMAP
-	select FW_CS_DSP
 
 config FW_CS_DSP_KUNIT_TEST
 	tristate "KUnit tests for Cirrus Logic cs_dsp" if !KUNIT_ALL_TESTS
-	depends on KUNIT && REGMAP
+	depends on KUNIT && REGMAP && FW_CS_DSP
 	default KUNIT_ALL_TESTS
-	select FW_CS_DSP
 	select FW_CS_DSP_KUNIT_TEST_UTILS
 	help
 	  This builds KUnit tests for cs_dsp.
diff --git a/drivers/firmware/cirrus/test/cs_dsp_mock_mem_maps.c b/drivers/firmware/cirrus/test/cs_dsp_mock_mem_maps.c
index 161272e47bda..73412bcef50c 100644
--- a/drivers/firmware/cirrus/test/cs_dsp_mock_mem_maps.c
+++ b/drivers/firmware/cirrus/test/cs_dsp_mock_mem_maps.c
@@ -462,36 +462,6 @@ unsigned int cs_dsp_mock_xm_header_get_alg_base_in_words(struct cs_dsp_test *pri
 EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_xm_header_get_alg_base_in_words, "FW_CS_DSP_KUNIT_TEST_UTILS");
 
 /**
- * cs_dsp_mock_xm_header_get_fw_version_from_regmap() - Firmware version.
- *
- * @priv:	Pointer to struct cs_dsp_test.
- *
- * Return: Firmware version word value.
- */
-unsigned int cs_dsp_mock_xm_header_get_fw_version_from_regmap(struct cs_dsp_test *priv)
-{
-	unsigned int xm = cs_dsp_mock_base_addr_for_mem(priv, WMFW_ADSP2_XM);
-	union {
-		struct wmfw_id_hdr adsp2;
-		struct wmfw_v3_id_hdr halo;
-	} hdr;
-
-	switch (priv->dsp->type) {
-	case WMFW_ADSP2:
-		regmap_raw_read(priv->dsp->regmap, xm, &hdr.adsp2, sizeof(hdr.adsp2));
-		return be32_to_cpu(hdr.adsp2.ver);
-	case WMFW_HALO:
-		regmap_raw_read(priv->dsp->regmap, xm, &hdr.halo, sizeof(hdr.halo));
-		return be32_to_cpu(hdr.halo.ver);
-	default:
-		KUNIT_FAIL(priv->test, NULL);
-		return 0;
-	}
-}
-EXPORT_SYMBOL_NS_GPL(cs_dsp_mock_xm_header_get_fw_version_from_regmap,
-		     "FW_CS_DSP_KUNIT_TEST_UTILS");
-
-/**
  * cs_dsp_mock_xm_header_get_fw_version() - Firmware version.
  *
  * @header:	Pointer to struct cs_dsp_mock_xm_header.
diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_bin.c b/drivers/firmware/cirrus/test/cs_dsp_test_bin.c
index 1e161bbc5b4a..163b7faecff4 100644
--- a/drivers/firmware/cirrus/test/cs_dsp_test_bin.c
+++ b/drivers/firmware/cirrus/test/cs_dsp_test_bin.c
@@ -2198,7 +2198,7 @@ static int cs_dsp_bin_test_common_init(struct kunit *test, struct cs_dsp *dsp)
 
 	priv->local->bin_builder =
 		cs_dsp_mock_bin_init(priv, 1,
-				     cs_dsp_mock_xm_header_get_fw_version_from_regmap(priv));
+				     cs_dsp_mock_xm_header_get_fw_version(xm_hdr));
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, priv->local->bin_builder);
 
 	/* We must provide a dummy wmfw to load */
diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c b/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c
index 8748874f0552..a7ec956d2724 100644
--- a/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c
+++ b/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c
@@ -451,7 +451,7 @@ static int cs_dsp_bin_err_test_common_init(struct kunit *test, struct cs_dsp *ds
 
 	local->bin_builder =
 		cs_dsp_mock_bin_init(priv, 1,
-				     cs_dsp_mock_xm_header_get_fw_version_from_regmap(priv));
+				     cs_dsp_mock_xm_header_get_fw_version(local->xm_header));
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, local->bin_builder);
 
 	/* Init cs_dsp */
diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index 3c52cb73237a..e3f990d888d7 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -1224,22 +1224,28 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	if (!svc->intel_svc_fcs) {
 		dev_err(dev, "failed to allocate %s device\n", INTEL_FCS);
 		ret = -ENOMEM;
-		goto err_unregister_dev;
+		goto err_unregister_rsu_dev;
 	}
 
 	ret = platform_device_add(svc->intel_svc_fcs);
 	if (ret) {
 		platform_device_put(svc->intel_svc_fcs);
-		goto err_unregister_dev;
+		goto err_unregister_rsu_dev;
 	}
 
+	ret = of_platform_default_populate(dev_of_node(dev), NULL, dev);
+	if (ret)
+		goto err_unregister_fcs_dev;
+
 	dev_set_drvdata(dev, svc);
 
 	pr_info("Intel Service Layer Driver Initialized\n");
 
 	return 0;
 
-err_unregister_dev:
+err_unregister_fcs_dev:
+	platform_device_unregister(svc->intel_svc_fcs);
+err_unregister_rsu_dev:
 	platform_device_unregister(svc->stratix10_svc_rsu);
 err_free_kfifo:
 	kfifo_free(&controller->svc_fifo);
@@ -1253,6 +1259,8 @@ static void stratix10_svc_drv_remove(struct platform_device *pdev)
 	struct stratix10_svc *svc = dev_get_drvdata(&pdev->dev);
 	struct stratix10_svc_controller *ctrl = platform_get_drvdata(pdev);
 
+	of_platform_depopulate(ctrl->dev);
+
 	platform_device_unregister(svc->intel_svc_fcs);
 	platform_device_unregister(svc->stratix10_svc_rsu);
 
diff --git a/drivers/fpga/tests/fpga-bridge-test.c b/drivers/fpga/tests/fpga-bridge-test.c
index b9ab29809e96..124ba40e32b1 100644
--- a/drivers/fpga/tests/fpga-bridge-test.c
+++ b/drivers/fpga/tests/fpga-bridge-test.c
@@ -170,4 +170,5 @@ static struct kunit_suite fpga_bridge_suite = {
 
 kunit_test_suite(fpga_bridge_suite);
 
+MODULE_DESCRIPTION("KUnit test for the FPGA Bridge");
 MODULE_LICENSE("GPL");
diff --git a/drivers/fpga/tests/fpga-mgr-test.c b/drivers/fpga/tests/fpga-mgr-test.c
index 9cb37aefbac4..8748babb0504 100644
--- a/drivers/fpga/tests/fpga-mgr-test.c
+++ b/drivers/fpga/tests/fpga-mgr-test.c
@@ -330,4 +330,5 @@ static struct kunit_suite fpga_mgr_suite = {
 
 kunit_test_suite(fpga_mgr_suite);
 
+MODULE_DESCRIPTION("KUnit test for the FPGA Manager");
 MODULE_LICENSE("GPL");
diff --git a/drivers/fpga/tests/fpga-region-test.c b/drivers/fpga/tests/fpga-region-test.c
index 6a108cafded8..020ceac48509 100644
--- a/drivers/fpga/tests/fpga-region-test.c
+++ b/drivers/fpga/tests/fpga-region-test.c
@@ -214,4 +214,5 @@ static struct kunit_suite fpga_region_suite = {
 
 kunit_test_suite(fpga_region_suite);
 
+MODULE_DESCRIPTION("KUnit test for the FPGA Region");
 MODULE_LICENSE("GPL");
diff --git a/drivers/fwctl/main.c b/drivers/fwctl/main.c
index cb1ac9c40239..bc6378506296 100644
--- a/drivers/fwctl/main.c
+++ b/drivers/fwctl/main.c
@@ -105,7 +105,7 @@ static int fwctl_cmd_rpc(struct fwctl_ucmd *ucmd)
 		if (!test_and_set_bit(0, &fwctl_tainted)) {
 			dev_warn(
 				&fwctl->dev,
-				"%s(%d): has requested full access to the physical device device",
+				"%s(%d): has requested full access to the physical device",
 				current->comm, task_pid_nr(current));
 			add_taint(TAINT_FWCTL, LOCKDEP_STILL_OK);
 		}
diff --git a/drivers/fwctl/pds/main.c b/drivers/fwctl/pds/main.c
index 284c4165fdd4..9b9d1f6b5556 100644
--- a/drivers/fwctl/pds/main.c
+++ b/drivers/fwctl/pds/main.c
@@ -105,12 +105,14 @@ static int pdsfc_identify(struct pdsfc_dev *pdsfc)
 static void pdsfc_free_endpoints(struct pdsfc_dev *pdsfc)
 {
 	struct device *dev = &pdsfc->fwctl.dev;
+	u32 num_endpoints;
 	int i;
 
 	if (!pdsfc->endpoints)
 		return;
 
-	for (i = 0; pdsfc->endpoint_info && i < pdsfc->endpoints->num_entries; i++)
+	num_endpoints = le32_to_cpu(pdsfc->endpoints->num_entries);
+	for (i = 0; pdsfc->endpoint_info && i < num_endpoints; i++)
 		mutex_destroy(&pdsfc->endpoint_info[i].lock);
 	vfree(pdsfc->endpoint_info);
 	pdsfc->endpoint_info = NULL;
@@ -199,7 +201,7 @@ static int pdsfc_init_endpoints(struct pdsfc_dev *pdsfc)
 	ep_entry = (struct pds_fwctl_query_data_endpoint *)pdsfc->endpoints->entries;
 	for (i = 0; i < num_endpoints; i++) {
 		mutex_init(&pdsfc->endpoint_info[i].lock);
-		pdsfc->endpoint_info[i].endpoint = ep_entry[i].id;
+		pdsfc->endpoint_info[i].endpoint = le32_to_cpu(ep_entry[i].id);
 	}
 
 	return 0;
@@ -214,6 +216,7 @@ static struct pds_fwctl_query_data *pdsfc_get_operations(struct pdsfc_dev *pdsfc
 	struct pds_fwctl_query_data *data;
 	union pds_core_adminq_cmd cmd;
 	dma_addr_t data_pa;
+	u32 num_entries;
 	int err;
 	int i;
 
@@ -246,8 +249,9 @@ static struct pds_fwctl_query_data *pdsfc_get_operations(struct pdsfc_dev *pdsfc
 	*pa = data_pa;
 
 	entries = (struct pds_fwctl_query_data_operation *)data->entries;
-	dev_dbg(dev, "num_entries %d\n", data->num_entries);
-	for (i = 0; i < data->num_entries; i++) {
+	num_entries = le32_to_cpu(data->num_entries);
+	dev_dbg(dev, "num_entries %d\n", num_entries);
+	for (i = 0; i < num_entries; i++) {
 
 		/* Translate FW command attribute to fwctl scope */
 		switch (entries[i].scope) {
@@ -267,7 +271,7 @@ static struct pds_fwctl_query_data *pdsfc_get_operations(struct pdsfc_dev *pdsfc
 			break;
 		}
 		dev_dbg(dev, "endpoint %d operation: id %x scope %d\n",
-			ep, entries[i].id, entries[i].scope);
+			ep, le32_to_cpu(entries[i].id), entries[i].scope);
 	}
 
 	return data;
@@ -280,24 +284,26 @@ static int pdsfc_validate_rpc(struct pdsfc_dev *pdsfc,
 	struct pds_fwctl_query_data_operation *op_entry;
 	struct pdsfc_rpc_endpoint_info *ep_info = NULL;
 	struct device *dev = &pdsfc->fwctl.dev;
+	u32 num_entries;
 	int i;
 
 	/* validate rpc in_len & out_len based
 	 * on ident.max_req_sz & max_resp_sz
 	 */
-	if (rpc->in.len > pdsfc->ident.max_req_sz) {
+	if (rpc->in.len > le32_to_cpu(pdsfc->ident.max_req_sz)) {
 		dev_dbg(dev, "Invalid request size %u, max %u\n",
-			rpc->in.len, pdsfc->ident.max_req_sz);
+			rpc->in.len, le32_to_cpu(pdsfc->ident.max_req_sz));
 		return -EINVAL;
 	}
 
-	if (rpc->out.len > pdsfc->ident.max_resp_sz) {
+	if (rpc->out.len > le32_to_cpu(pdsfc->ident.max_resp_sz)) {
 		dev_dbg(dev, "Invalid response size %u, max %u\n",
-			rpc->out.len, pdsfc->ident.max_resp_sz);
+			rpc->out.len, le32_to_cpu(pdsfc->ident.max_resp_sz));
 		return -EINVAL;
 	}
 
-	for (i = 0; i < pdsfc->endpoints->num_entries; i++) {
+	num_entries = le32_to_cpu(pdsfc->endpoints->num_entries);
+	for (i = 0; i < num_entries; i++) {
 		if (pdsfc->endpoint_info[i].endpoint == rpc->in.ep) {
 			ep_info = &pdsfc->endpoint_info[i];
 			break;
@@ -326,8 +332,9 @@ static int pdsfc_validate_rpc(struct pdsfc_dev *pdsfc,
 
 	/* reject unsupported and/or out of scope commands */
 	op_entry = (struct pds_fwctl_query_data_operation *)ep_info->operations->entries;
-	for (i = 0; i < ep_info->operations->num_entries; i++) {
-		if (PDS_FWCTL_RPC_OPCODE_CMP(rpc->in.op, op_entry[i].id)) {
+	num_entries = le32_to_cpu(ep_info->operations->num_entries);
+	for (i = 0; i < num_entries; i++) {
+		if (PDS_FWCTL_RPC_OPCODE_CMP(rpc->in.op, le32_to_cpu(op_entry[i].id))) {
 			if (scope < op_entry[i].scope)
 				return -EPERM;
 			return 0;
@@ -402,7 +409,7 @@ static void *pdsfc_fw_rpc(struct fwctl_uctx *uctx, enum fwctl_rpc_scope scope,
 	cmd = (union pds_core_adminq_cmd) {
 		.fwctl_rpc = {
 			.opcode = PDS_FWCTL_CMD_RPC,
-			.flags = PDS_FWCTL_RPC_IND_REQ | PDS_FWCTL_RPC_IND_RESP,
+			.flags = cpu_to_le16(PDS_FWCTL_RPC_IND_REQ | PDS_FWCTL_RPC_IND_RESP),
 			.ep = cpu_to_le32(rpc->in.ep),
 			.op = cpu_to_le32(rpc->in.op),
 			.req_pa = cpu_to_le64(in_payload_dma_addr),
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 442435ded020..13cc120cf11f 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -1204,6 +1204,8 @@ static int pca953x_restore_context(struct pca953x_chip *chip)
 
 	guard(mutex)(&chip->i2c_lock);
 
+	if (chip->client->irq > 0)
+		enable_irq(chip->client->irq);
 	regcache_cache_only(chip->regmap, false);
 	regcache_mark_dirty(chip->regmap);
 	ret = pca953x_regcache_sync(chip);
@@ -1216,6 +1218,10 @@ static int pca953x_restore_context(struct pca953x_chip *chip)
 static void pca953x_save_context(struct pca953x_chip *chip)
 {
 	guard(mutex)(&chip->i2c_lock);
+
+	/* Disable IRQ to prevent early triggering while regmap "cache only" is on */
+	if (chip->client->irq > 0)
+		disable_irq(chip->client->irq);
 	regcache_cache_only(chip->regmap, true);
 }
 
diff --git a/drivers/gpio/gpio-virtuser.c b/drivers/gpio/gpio-virtuser.c
index 13407fd4f0eb..eab6726953b4 100644
--- a/drivers/gpio/gpio-virtuser.c
+++ b/drivers/gpio/gpio-virtuser.c
@@ -401,10 +401,15 @@ static ssize_t gpio_virtuser_direction_do_write(struct file *file,
 	char buf[32], *trimmed;
 	int ret, dir, val = 0;
 
-	ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count);
+	if (count >= sizeof(buf))
+		return -EINVAL;
+
+	ret = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, user_buf, count);
 	if (ret < 0)
 		return ret;
 
+	buf[ret] = '\0';
+
 	trimmed = strim(buf);
 
 	if (strcmp(trimmed, "input") == 0) {
@@ -623,12 +628,15 @@ static ssize_t gpio_virtuser_consumer_write(struct file *file,
 	char buf[GPIO_VIRTUSER_NAME_BUF_LEN + 2];
 	int ret;
 
+	if (count >= sizeof(buf))
+		return -EINVAL;
+
 	ret = simple_write_to_buffer(buf, GPIO_VIRTUSER_NAME_BUF_LEN, ppos,
 				     user_buf, count);
 	if (ret < 0)
 		return ret;
 
-	buf[strlen(buf) - 1] = '\0';
+	buf[ret] = '\0';
 
 	ret = gpiod_set_consumer_name(data->ad.desc, buf);
 	if (ret)
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index b8197502a5ac..113c5d90f2df 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -742,6 +742,12 @@ EXPORT_SYMBOL_GPL(gpiochip_query_valid_mask);
 bool gpiochip_line_is_valid(const struct gpio_chip *gc,
 				unsigned int offset)
 {
+	/*
+	 * hog pins are requested before registering GPIO chip
+	 */
+	if (!gc->gpiodev)
+		return true;
+
 	/* No mask means all valid */
 	if (likely(!gc->gpiodev->valid_mask))
 		return true;
@@ -2879,7 +2885,7 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value)
 	 * output-only, but if there is then not even a .set() operation it
 	 * is pretty tricky to drive the output line.
 	 */
-	if (!guard.gc->set && !guard.gc->direction_output) {
+	if (!guard.gc->set && !guard.gc->set_rv && !guard.gc->direction_output) {
 		gpiod_warn(desc,
 			   "%s: missing set() and direction_output() operations\n",
 			   __func__);
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 2cba2b6ebe1c..f01925ed8176 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -188,7 +188,7 @@ config DRM_DEBUG_DP_MST_TOPOLOGY_REFS
         bool "Enable refcount backtrace history in the DP MST helpers"
 	depends on STACKTRACE_SUPPORT
         select STACKDEPOT
-        depends on DRM_KMS_HELPER
+        select DRM_KMS_HELPER
         depends on DEBUG_KERNEL
         depends on EXPERT
         help
diff --git a/drivers/gpu/drm/adp/adp_drv.c b/drivers/gpu/drm/adp/adp_drv.c
index c98c647f981d..54cde090c3f4 100644
--- a/drivers/gpu/drm/adp/adp_drv.c
+++ b/drivers/gpu/drm/adp/adp_drv.c
@@ -121,7 +121,6 @@ struct adp_drv_private {
 	dma_addr_t mask_iova;
 	int be_irq;
 	int fe_irq;
-	spinlock_t irq_lock;
 	struct drm_pending_vblank_event *event;
 };
 
@@ -288,6 +287,7 @@ static void adp_crtc_atomic_enable(struct drm_crtc *crtc,
 	writel(BIT(0), adp->be + ADBE_BLEND_EN3);
 	writel(BIT(0), adp->be + ADBE_BLEND_BYPASS);
 	writel(BIT(0), adp->be + ADBE_BLEND_EN4);
+	drm_crtc_vblank_on(crtc);
 }
 
 static void adp_crtc_atomic_disable(struct drm_crtc *crtc,
@@ -310,6 +310,7 @@ static void adp_crtc_atomic_flush(struct drm_crtc *crtc,
 				  struct drm_atomic_state *state)
 {
 	u32 frame_num = 1;
+	unsigned long flags;
 	struct adp_drv_private *adp = crtc_to_adp(crtc);
 	struct drm_crtc_state *new_state = drm_atomic_get_new_crtc_state(state, crtc);
 	u64 new_size = ALIGN(new_state->mode.hdisplay *
@@ -330,13 +331,19 @@ static void adp_crtc_atomic_flush(struct drm_crtc *crtc,
 	}
 	writel(ADBE_FIFO_SYNC | frame_num, adp->be + ADBE_FIFO);
 	//FIXME: use adbe flush interrupt
-	spin_lock_irq(&crtc->dev->event_lock);
 	if (crtc->state->event) {
-		drm_crtc_vblank_get(crtc);
-		adp->event = crtc->state->event;
+		struct drm_pending_vblank_event *event = crtc->state->event;
+
+		crtc->state->event = NULL;
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+
+		if (drm_crtc_vblank_get(crtc) != 0)
+			drm_crtc_send_vblank_event(crtc, event);
+		else
+			adp->event = event;
+
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 	}
-	crtc->state->event = NULL;
-	spin_unlock_irq(&crtc->dev->event_lock);
 }
 
 static const struct drm_crtc_funcs adp_crtc_funcs = {
@@ -482,8 +489,6 @@ static irqreturn_t adp_fe_irq(int irq, void *arg)
 	u32 int_status;
 	u32 int_ctl;
 
-	spin_lock(&adp->irq_lock);
-
 	int_status = readl(adp->fe + ADP_INT_STATUS);
 	if (int_status & ADP_INT_STATUS_VBLANK) {
 		drm_crtc_handle_vblank(&adp->crtc);
@@ -501,7 +506,6 @@ static irqreturn_t adp_fe_irq(int irq, void *arg)
 
 	writel(int_status, adp->fe + ADP_INT_STATUS);
 
-	spin_unlock(&adp->irq_lock);
 
 	return IRQ_HANDLED;
 }
@@ -512,8 +516,7 @@ static int adp_drm_bind(struct device *dev)
 	struct adp_drv_private *adp = to_adp(drm);
 	int err;
 
-	adp_disable_vblank(adp);
-	writel(ADP_CTRL_FIFO_ON | ADP_CTRL_VBLANK_ON, adp->fe + ADP_CTRL);
+	writel(ADP_CTRL_FIFO_ON, adp->fe + ADP_CTRL);
 
 	adp->next_bridge = drmm_of_get_bridge(&adp->drm, dev->of_node, 0, 0);
 	if (IS_ERR(adp->next_bridge)) {
@@ -567,8 +570,6 @@ static int adp_probe(struct platform_device *pdev)
 	if (IS_ERR(adp))
 		return PTR_ERR(adp);
 
-	spin_lock_init(&adp->irq_lock);
-
 	dev_set_drvdata(&pdev->dev, &adp->drm);
 
 	err = adp_parse_of(pdev, adp);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 6d83ccfa42ee..c3641331d4de 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -353,7 +353,6 @@ enum amdgpu_kiq_irq {
 	AMDGPU_CP_KIQ_IRQ_DRIVER0 = 0,
 	AMDGPU_CP_KIQ_IRQ_LAST
 };
-#define SRIOV_USEC_TIMEOUT  1200000 /* wait 12 * 100ms for SRIOV */
 #define MAX_KIQ_REG_WAIT       5000 /* in usecs, 5ms */
 #define MAX_KIQ_REG_BAILOUT_INTERVAL   5 /* in msecs, 5ms */
 #define MAX_KIQ_REG_TRY 1000
@@ -1124,6 +1123,7 @@ struct amdgpu_device {
 	bool				in_s3;
 	bool				in_s4;
 	bool				in_s0ix;
+	suspend_state_t			last_suspend_state;
 
 	enum pp_mp1_state               mp1_state;
 	struct amdgpu_doorbell_index doorbell_index;
@@ -1614,11 +1614,9 @@ static inline void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_cap
 #if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
 bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev);
 bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
-void amdgpu_choose_low_power_state(struct amdgpu_device *adev);
 #else
 static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
 static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; }
-static inline void amdgpu_choose_low_power_state(struct amdgpu_device *adev) { }
 #endif
 
 void amdgpu_register_gpu_instance(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index b7f8f2ff143d..707e131f89d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1533,22 +1533,4 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
 #endif /* CONFIG_AMD_PMC */
 }
 
-/**
- * amdgpu_choose_low_power_state
- *
- * @adev: amdgpu_device_pointer
- *
- * Choose the target low power state for the GPU
- */
-void amdgpu_choose_low_power_state(struct amdgpu_device *adev)
-{
-	if (adev->in_runpm)
-		return;
-
-	if (amdgpu_acpi_is_s0ix_active(adev))
-		adev->in_s0ix = true;
-	else if (amdgpu_acpi_is_s3_active(adev))
-		adev->in_s3 = true;
-}
-
 #endif /* CONFIG_SUSPEND */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
index cfdf558b48b6..02138aa55793 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
@@ -109,7 +109,7 @@ int amdgpu_unmap_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	struct drm_exec exec;
 	int r;
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
+	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = amdgpu_vm_lock_pd(vm, &exec, 0);
 		if (likely(!r))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a30111d2c3ea..f8b3e04d71ed 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3510,6 +3510,7 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 			amdgpu_device_mem_scratch_fini(adev);
 			amdgpu_ib_pool_fini(adev);
 			amdgpu_seq64_fini(adev);
+			amdgpu_doorbell_fini(adev);
 		}
 		if (adev->ip_blocks[i].version->funcs->sw_fini) {
 			r = adev->ip_blocks[i].version->funcs->sw_fini(&adev->ip_blocks[i]);
@@ -3643,6 +3644,13 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 			    adev, adev->ip_blocks[i].version->type))
 			continue;
 
+		/* Since we skip suspend for S0i3, we need to cancel the delayed
+		 * idle work here as the suspend callback never gets called.
+		 */
+		if (adev->in_s0ix &&
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX &&
+		    amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(10, 0, 0))
+			cancel_delayed_work_sync(&adev->gfx.idle_work);
 		/* skip suspend of gfx/mes and psp for S0ix
 		 * gfx is in gfxoff state, so on resume it will exit gfxoff just
 		 * like at runtime. PSP is also part of the always on hardware
@@ -4851,7 +4859,6 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 
 		iounmap(adev->rmmio);
 		adev->rmmio = NULL;
-		amdgpu_doorbell_fini(adev);
 		drm_dev_exit(idx);
 	}
 
@@ -4900,28 +4907,20 @@ static int amdgpu_device_evict_resources(struct amdgpu_device *adev)
  * @data: data
  *
  * This function is called when the system is about to suspend or hibernate.
- * It is used to evict resources from the device before the system goes to
- * sleep while there is still access to swap.
+ * It is used to set the appropriate flags so that eviction can be optimized
+ * in the pm prepare callback.
  */
 static int amdgpu_device_pm_notifier(struct notifier_block *nb, unsigned long mode,
 				     void *data)
 {
 	struct amdgpu_device *adev = container_of(nb, struct amdgpu_device, pm_nb);
-	int r;
 
 	switch (mode) {
 	case PM_HIBERNATION_PREPARE:
 		adev->in_s4 = true;
-		fallthrough;
-	case PM_SUSPEND_PREPARE:
-		r = amdgpu_device_evict_resources(adev);
-		/*
-		 * This is considered non-fatal at this time because
-		 * amdgpu_device_prepare() will also fatally evict resources.
-		 * See https://gitlab.freedesktop.org/drm/amd/-/issues/3781
-		 */
-		if (r)
-			drm_warn(adev_to_drm(adev), "Failed to evict resources, freeze active processes if problems occur: %d\n", r);
+		break;
+	case PM_POST_HIBERNATION:
+		adev->in_s4 = false;
 		break;
 	}
 
@@ -4942,15 +4941,13 @@ int amdgpu_device_prepare(struct drm_device *dev)
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	int i, r;
 
-	amdgpu_choose_low_power_state(adev);
-
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
 	/* Evict the majority of BOs before starting suspend sequence */
 	r = amdgpu_device_evict_resources(adev);
 	if (r)
-		goto unprepare;
+		return r;
 
 	flush_delayed_work(&adev->gfx.gfx_off_delay_work);
 
@@ -4961,15 +4958,10 @@ int amdgpu_device_prepare(struct drm_device *dev)
 			continue;
 		r = adev->ip_blocks[i].version->funcs->prepare_suspend(&adev->ip_blocks[i]);
 		if (r)
-			goto unprepare;
+			return r;
 	}
 
 	return 0;
-
-unprepare:
-	adev->in_s0ix = adev->in_s3 = adev->in_s4 = false;
-
-	return r;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index dc2713ec95a5..9e738fae2b74 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -120,6 +120,8 @@ MODULE_FIRMWARE("amdgpu/vega20_ip_discovery.bin");
 MODULE_FIRMWARE("amdgpu/raven_ip_discovery.bin");
 MODULE_FIRMWARE("amdgpu/raven2_ip_discovery.bin");
 MODULE_FIRMWARE("amdgpu/picasso_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/arcturus_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/aldebaran_ip_discovery.bin");
 
 #define mmIP_DISCOVERY_VERSION  0x16A00
 #define mmRCC_CONFIG_MEMSIZE	0xde3
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 9f627caedc3f..44e120f9f764 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -43,6 +43,29 @@
 #include <linux/dma-fence-array.h>
 #include <linux/pci-p2pdma.h>
 
+static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops;
+
+/**
+ * dma_buf_attach_adev - Helper to get adev of an attachment
+ *
+ * @attach: attachment
+ *
+ * Returns:
+ * A struct amdgpu_device * if the attaching device is an amdgpu device or
+ * partition, NULL otherwise.
+ */
+static struct amdgpu_device *dma_buf_attach_adev(struct dma_buf_attachment *attach)
+{
+	if (attach->importer_ops == &amdgpu_dma_buf_attach_ops) {
+		struct drm_gem_object *obj = attach->importer_priv;
+		struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+		return amdgpu_ttm_adev(bo->tbo.bdev);
+	}
+
+	return NULL;
+}
+
 /**
  * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
  *
@@ -54,11 +77,13 @@
 static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
 				 struct dma_buf_attachment *attach)
 {
+	struct amdgpu_device *attach_adev = dma_buf_attach_adev(attach);
 	struct drm_gem_object *obj = dmabuf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 
-	if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
+	if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) &&
+	    pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
 		attach->peer2peer = false;
 
 	amdgpu_vm_bo_update_shared(bo);
@@ -75,11 +100,35 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
  */
 static int amdgpu_dma_buf_pin(struct dma_buf_attachment *attach)
 {
-	struct drm_gem_object *obj = attach->dmabuf->priv;
-	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	struct dma_buf *dmabuf = attach->dmabuf;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(dmabuf->priv);
+	u32 domains = bo->allowed_domains;
+
+	dma_resv_assert_held(dmabuf->resv);
+
+	/* Try pinning into VRAM to allow P2P with RDMA NICs without ODP
+	 * support if all attachments can do P2P. If any attachment can't do
+	 * P2P just pin into GTT instead.
+	 *
+	 * To avoid with conflicting pinnings between GPUs and RDMA when move
+	 * notifiers are disabled, only allow pinning in VRAM when move
+	 * notiers are enabled.
+	 */
+	if (!IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)) {
+		domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+	} else {
+		list_for_each_entry(attach, &dmabuf->attachments, node)
+			if (!attach->peer2peer)
+				domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+	}
 
-	/* pin buffer into GTT */
-	return amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
+	if (domains & AMDGPU_GEM_DOMAIN_VRAM)
+		bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+
+	if (WARN_ON(!domains))
+		return -EINVAL;
+
+	return amdgpu_bo_pin(bo, domains);
 }
 
 /**
@@ -134,9 +183,6 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		if (r)
 			return ERR_PTR(r);
-
-	} else if (bo->tbo.resource->mem_type != TTM_PL_TT) {
-		return ERR_PTR(-EBUSY);
 	}
 
 	switch (bo->tbo.resource->mem_type) {
@@ -153,6 +199,11 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
 		break;
 
 	case TTM_PL_VRAM:
+		/* XGMI-accessible memory should never be DMA-mapped */
+		if (WARN_ON(amdgpu_dmabuf_is_xgmi_accessible(
+				dma_buf_attach_adev(attach), bo)))
+			return ERR_PTR(-EINVAL);
+
 		r = amdgpu_vram_mgr_alloc_sgt(adev, bo->tbo.resource, 0,
 					      bo->tbo.base.size, attach->dev,
 					      dir, &sgt);
@@ -184,7 +235,7 @@ static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach,
 				 struct sg_table *sgt,
 				 enum dma_data_direction dir)
 {
-	if (sgt->sgl->page_link) {
+	if (sg_page(sgt->sgl)) {
 		dma_unmap_sgtable(attach->dev, sgt, dir, 0);
 		sg_free_table(sgt);
 		kfree(sgt);
@@ -459,6 +510,9 @@ bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev,
 	struct drm_gem_object *obj = &bo->tbo.base;
 	struct drm_gem_object *gobj;
 
+	if (!adev)
+		return false;
+
 	if (obj->import_attach) {
 		struct dma_buf *dma_buf = obj->import_attach->dmabuf;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 26bf896f1444..72c807f5822e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2548,8 +2548,20 @@ static int amdgpu_pmops_suspend(struct device *dev)
 		adev->in_s0ix = true;
 	else if (amdgpu_acpi_is_s3_active(adev))
 		adev->in_s3 = true;
-	if (!adev->in_s0ix && !adev->in_s3)
+	if (!adev->in_s0ix && !adev->in_s3) {
+		/* don't allow going deep first time followed by s2idle the next time */
+		if (adev->last_suspend_state != PM_SUSPEND_ON &&
+		    adev->last_suspend_state != pm_suspend_target_state) {
+			drm_err_once(drm_dev, "Unsupported suspend state %d\n",
+				     pm_suspend_target_state);
+			return -EINVAL;
+		}
 		return 0;
+	}
+
+	/* cache the state last used for suspend */
+	adev->last_suspend_state = pm_suspend_target_state;
+
 	return amdgpu_device_suspend(drm_dev, true);
 }
 
@@ -2603,13 +2615,8 @@ static int amdgpu_pmops_freeze(struct device *dev)
 static int amdgpu_pmops_thaw(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = drm_to_adev(drm_dev);
-	int r;
-
-	r = amdgpu_device_resume(drm_dev, true);
-	adev->in_s4 = false;
 
-	return r;
+	return amdgpu_device_resume(drm_dev, true);
 }
 
 static int amdgpu_pmops_poweroff(struct device *dev)
@@ -2622,9 +2629,6 @@ static int amdgpu_pmops_poweroff(struct device *dev)
 static int amdgpu_pmops_restore(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = drm_to_adev(drm_dev);
-
-	adev->in_s4 = false;
 
 	return amdgpu_device_resume(drm_dev, true);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 72af5e5a894a..cf2df7790077 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1438,9 +1438,11 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 	struct drm_gpu_scheduler *sched = &ring->sched;
 	struct drm_sched_entity entity;
+	static atomic_t counter;
 	struct dma_fence *f;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
+	void *owner;
 	int i, r;
 
 	/* Initialize the scheduler entity */
@@ -1451,9 +1453,15 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring)
 		goto err;
 	}
 
-	r = amdgpu_job_alloc_with_ib(ring->adev, &entity, NULL,
-				     64, 0,
-				     &job);
+	/*
+	 * Use some unique dummy value as the owner to make sure we execute
+	 * the cleaner shader on each submission. The value just need to change
+	 * for each submission and is otherwise meaningless.
+	 */
+	owner = (void *)(unsigned long)atomic_inc_return(&counter);
+
+	r = amdgpu_job_alloc_with_ib(ring->adev, &entity, owner,
+				     64, 0, &job);
 	if (r)
 		goto err;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 464625282872..ecb74ccf1d90 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -699,12 +699,10 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 				   uint32_t flush_type, bool all_hub,
 				   uint32_t inst)
 {
-	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT :
-		adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq[inst].ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq[inst];
 	unsigned int ndw;
-	int r;
+	int r, cnt = 0;
 	uint32_t seq;
 
 	/*
@@ -761,10 +759,21 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq[inst].ring_lock);
-		if (amdgpu_fence_wait_polling(ring, seq, usec_timeout) < 1) {
+
+		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+
+		might_sleep();
+		while (r < 1 && cnt++ < MAX_KIQ_REG_TRY &&
+		       !amdgpu_reset_pending(adev->reset_domain)) {
+			msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
+			r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+		}
+
+		if (cnt > MAX_KIQ_REG_TRY) {
 			dev_err(adev->dev, "timeout waiting for kiq fence\n");
 			r = -ETIME;
-		}
+		} else
+			r = 0;
 	}
 
 error_unlock_reset:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 80cd6f5273db..0b9987781f76 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -163,8 +163,8 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		 * When GTT is just an alternative to VRAM make sure that we
 		 * only use it as fallback and still try to fill up VRAM first.
 		 */
-		if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM &&
-		    !(adev->flags & AMD_IS_APU))
+		if (abo->tbo.resource && !(adev->flags & AMD_IS_APU) &&
+		    domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM)
 			places[c].flags |= TTM_PL_FLAG_FALLBACK;
 		c++;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index cdcdae7f71ce..83adf81defc7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -66,7 +66,6 @@
 #define VCN_ENC_CMD_REG_WAIT		0x0000000c
 
 #define VCN_AON_SOC_ADDRESS_2_0 	0x1f800
-#define VCN1_AON_SOC_ADDRESS_3_0 	0x48000
 #define VCN_VID_IP_ADDRESS_2_0		0x0
 #define VCN_AON_IP_ADDRESS_2_0		0x30000
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 6da8994e0469..2d7f82e98df9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -24,6 +24,7 @@
 
 #include <linux/dma-mapping.h>
 #include <drm/ttm/ttm_range_manager.h>
+#include <drm/drm_drv.h>
 
 #include "amdgpu.h"
 #include "amdgpu_vm.h"
@@ -907,6 +908,9 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 	struct ttm_resource_manager *man = &mgr->manager;
 	int err;
 
+	man->cg = drmm_cgroup_register_region(adev_to_drm(adev), "vram", adev->gmc.real_vram_size);
+	if (IS_ERR(man->cg))
+		return PTR_ERR(man->cg);
 	ttm_resource_manager_init(man, &adev->mman.bdev,
 				  adev->gmc.real_vram_size);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index a63ce747863f..23e6a05359c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -6114,7 +6114,7 @@ static int gfx_v10_0_cp_gfx_load_pfp_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_PFP_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_PFP_IC_BASE_CNTL, VMID, 0);
@@ -6192,7 +6192,7 @@ static int gfx_v10_0_cp_gfx_load_ce_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_CE_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_CE_IC_BASE_CNTL, VMID, 0);
@@ -6269,7 +6269,7 @@ static int gfx_v10_0_cp_gfx_load_me_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_ME_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_ME_IC_BASE_CNTL, VMID, 0);
@@ -6644,7 +6644,7 @@ static int gfx_v10_0_cp_compute_load_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_CPC_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_CPC_IC_BASE_CNTL, CACHE_POLICY, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index d57db42f9536..2a5c2a1ae3c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -2428,7 +2428,7 @@ static int gfx_v11_0_config_me_cache(struct amdgpu_device *adev, uint64_t addr)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, regCP_ME_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_ME_IC_BASE_CNTL, VMID, 0);
@@ -2472,7 +2472,7 @@ static int gfx_v11_0_config_pfp_cache(struct amdgpu_device *adev, uint64_t addr)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_PFP_IC_BASE_CNTL, VMID, 0);
@@ -2517,7 +2517,7 @@ static int gfx_v11_0_config_mec_cache(struct amdgpu_device *adev, uint64_t addr)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, regCP_CPC_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_CPC_IC_BASE_CNTL, CACHE_POLICY, 0);
@@ -3153,7 +3153,7 @@ static int gfx_v11_0_cp_gfx_load_pfp_microcode_rs64(struct amdgpu_device *adev)
 	amdgpu_bo_unreserve(adev->gfx.pfp.pfp_fw_data_obj);
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	WREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_LO,
 		lower_32_bits(adev->gfx.pfp.pfp_fw_gpu_addr));
@@ -3371,7 +3371,7 @@ static int gfx_v11_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev)
 	amdgpu_bo_unreserve(adev->gfx.me.me_fw_data_obj);
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	WREG32_SOC15(GC, 0, regCP_ME_IC_BASE_LO,
 		lower_32_bits(adev->gfx.me.me_fw_gpu_addr));
@@ -4541,7 +4541,7 @@ static int gfx_v11_0_gfxhub_enable(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index e7b58e470292..62a257a4a3e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -2324,7 +2324,7 @@ static int gfx_v12_0_cp_gfx_load_pfp_microcode_rs64(struct amdgpu_device *adev)
 	amdgpu_bo_unreserve(adev->gfx.pfp.pfp_fw_data_obj);
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	WREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_LO,
 		lower_32_bits(adev->gfx.pfp.pfp_fw_gpu_addr));
@@ -2468,7 +2468,7 @@ static int gfx_v12_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev)
 	amdgpu_bo_unreserve(adev->gfx.me.me_fw_data_obj);
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	WREG32_SOC15(GC, 0, regCP_ME_IC_BASE_LO,
 		lower_32_bits(adev->gfx.me.me_fw_gpu_addr));
@@ -3426,7 +3426,7 @@ static int gfx_v12_0_gfxhub_enable(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 95d894a231fc..809b3a882d0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -268,7 +268,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
 
 	/* flush hdp cache */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	/* This is necessary for SRIOV as well as for GFXOFF to function
 	 * properly under bare metal
@@ -969,7 +969,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev)
 	adev->hdp.funcs->init_registers(adev);
 
 	/* Flush HDP after it is initialized */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index ad099f136f84..fec9a007533a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -229,7 +229,7 @@ static void gmc_v11_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
 
 	/* flush hdp cache */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	/* This is necessary for SRIOV as well as for GFXOFF to function
 	 * properly under bare metal
@@ -752,6 +752,18 @@ static int gmc_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 	adev->gmc.vram_type = vram_type;
 	adev->gmc.vram_vendor = vram_vendor;
 
+	/* The mall_size is already calculated as mall_size_per_umc * num_umc.
+	 * However, for gfx1151, which features a 2-to-1 UMC mapping,
+	 * the result must be multiplied by 2 to determine the actual mall size.
+	 */
+	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(11, 5, 1):
+		adev->gmc.mall_size *= 2;
+		break;
+	default:
+		break;
+	}
+
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(11, 0, 0):
 	case IP_VERSION(11, 0, 1):
@@ -899,7 +911,7 @@ static int gmc_v11_0_gart_enable(struct amdgpu_device *adev)
 		return r;
 
 	/* Flush HDP after it is initialized */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index 05c026d0b0d9..c6f290704d47 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -297,7 +297,7 @@ static void gmc_v12_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 		return;
 
 	/* flush hdp cache */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	/* This is necessary for SRIOV as well as for GFXOFF to function
 	 * properly under bare metal
@@ -881,7 +881,7 @@ static int gmc_v12_0_gart_enable(struct amdgpu_device *adev)
 		return r;
 
 	/* Flush HDP after it is initialized */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 783e0c3b86b4..5effe8327d29 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -2435,7 +2435,7 @@ static int gmc_v9_0_hw_init(struct amdgpu_ip_block *ip_block)
 	adev->hdp.funcs->init_registers(adev);
 
 	/* After HDP is initialized, flush HDP.*/
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS)
 		value = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
index f1dc13b3ab38..cbbeadeb53f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
@@ -41,7 +41,12 @@ static void hdp_v4_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
index 43195c079748..086a647308df 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
@@ -32,7 +32,12 @@ static void hdp_v5_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
index fcb8dd2876bc..40940b4ab400 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
@@ -33,7 +33,17 @@ static void hdp_v5_2_flush_hdp(struct amdgpu_device *adev,
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2,
 			0);
-		RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		if (amdgpu_sriov_vf(adev)) {
+			/* this is fine because SR_IOV doesn't remap the register */
+			RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		} else {
+			/* We just need to read back a register to post the write.
+			 * Reading back the remapped register causes problems on
+			 * some platforms so just read back the memory size register.
+			 */
+			if (adev->nbio.funcs->get_memsize)
+				adev->nbio.funcs->get_memsize(adev);
+		}
 	} else {
 		amdgpu_ring_emit_wreg(ring,
 			(adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2,
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
index a88d25a06c29..6ccd31c8bc69 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
@@ -35,7 +35,12 @@ static void hdp_v6_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
index 49f7eb4fbd11..2c9239a22f39 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
@@ -32,7 +32,12 @@ static void hdp_v7_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index e65916ada23b..ef9538fbbf53 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -894,6 +894,10 @@ static void mes_v11_0_get_fw_version(struct amdgpu_device *adev)
 {
 	int pipe;
 
+	/* return early if we have already fetched these */
+	if (adev->mes.sched_version && adev->mes.kiq_version)
+		return;
+
 	/* get MES scheduler/KIQ versions */
 	mutex_lock(&adev->srbm_mutex);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 183dd3346da5..e6ab617b9a40 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -1392,17 +1392,20 @@ static int mes_v12_0_queue_init(struct amdgpu_device *adev,
 		mes_v12_0_queue_init_register(ring);
 	}
 
-	/* get MES scheduler/KIQ versions */
-	mutex_lock(&adev->srbm_mutex);
-	soc21_grbm_select(adev, 3, pipe, 0, 0);
+	if (((pipe == AMDGPU_MES_SCHED_PIPE) && !adev->mes.sched_version) ||
+	    ((pipe == AMDGPU_MES_KIQ_PIPE) && !adev->mes.kiq_version)) {
+		/* get MES scheduler/KIQ versions */
+		mutex_lock(&adev->srbm_mutex);
+		soc21_grbm_select(adev, 3, pipe, 0, 0);
 
-	if (pipe == AMDGPU_MES_SCHED_PIPE)
-		adev->mes.sched_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
-	else if (pipe == AMDGPU_MES_KIQ_PIPE && adev->enable_mes_kiq)
-		adev->mes.kiq_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
+		if (pipe == AMDGPU_MES_SCHED_PIPE)
+			adev->mes.sched_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
+		else if (pipe == AMDGPU_MES_KIQ_PIPE && adev->enable_mes_kiq)
+			adev->mes.kiq_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
 
-	soc21_grbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+		soc21_grbm_select(adev, 0, 0, 0, 0);
+		mutex_unlock(&adev->srbm_mutex);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
index 2ece3ae75ec1..bed5ef4d8788 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
@@ -360,7 +360,7 @@ static void nbio_v7_11_get_clockgating_state(struct amdgpu_device *adev,
 		*flags |= AMD_CG_SUPPORT_BIF_LS;
 }
 
-#define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE)
+#define MMIO_REG_HOLE_OFFSET 0x44000
 
 static void nbio_v7_11_set_reg_remap(struct amdgpu_device *adev)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index bb5dfc410a66..215543575f47 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -533,7 +533,7 @@ static int psp_v11_0_memory_training(struct psp_context *psp, uint32_t ops)
 			}
 
 			memcpy_toio(adev->mman.aper_base_kaddr, buf, sz);
-			adev->hdp.funcs->flush_hdp(adev, NULL);
+			amdgpu_device_flush_hdp(adev, NULL);
 			vfree(buf);
 			drm_dev_exit(idx);
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index cc621064610f..afdf8ce3b4c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -610,7 +610,7 @@ static int psp_v13_0_memory_training(struct psp_context *psp, uint32_t ops)
 			}
 
 			memcpy_toio(adev->mman.aper_base_kaddr, buf, sz);
-			adev->hdp.funcs->flush_hdp(adev, NULL);
+			amdgpu_device_flush_hdp(adev, NULL);
 			vfree(buf);
 			drm_dev_exit(idx);
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
index 7c49c3f3c388..256288c6cd78 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
@@ -498,7 +498,7 @@ static int psp_v14_0_memory_training(struct psp_context *psp, uint32_t ops)
 			}
 
 			memcpy_toio(adev->mman.aper_base_kaddr, buf, sz);
-			adev->hdp.funcs->flush_hdp(adev, NULL);
+			amdgpu_device_flush_hdp(adev, NULL);
 			vfree(buf);
 			drm_dev_exit(idx);
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 8e7a36f26e9c..b8d835c9e17e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -39,6 +39,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0					0x1fa00
 #define VCN1_VID_SOC_ADDRESS_3_0				0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0				0x48000
 
 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET			0x1fd
 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET			0x503
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index d716510b8dd6..3eec1b8feaee 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -39,6 +39,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0					0x1fa00
 #define VCN1_VID_SOC_ADDRESS_3_0				0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0				0x48000
 
 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET			0x27
 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET			0x0f
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 22ae1939476f..0b19f0ab4480 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -40,6 +40,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0					0x1fa00
 #define VCN1_VID_SOC_ADDRESS_3_0				0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0				0x48000
 
 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET			0x27
 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET			0x0f
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index c6f6392c1c20..1f777c125b00 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -46,6 +46,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0							0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0						0x48300
+#define VCN1_AON_SOC_ADDRESS_3_0						0x48000
 
 #define VCN_HARVEST_MMSCH								0
 
@@ -614,7 +615,8 @@ static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
 
 	/* VCN global tiling registers */
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
-		VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+			VCN, inst_idx, regUVD_GFX10_ADDR_CONFIG),
+			adev->gfx.config.gb_addr_config, 0, indirect);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 3e176b4b7c69..012f6ea928ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -45,6 +45,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0		0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0	0x48300
+#define VCN1_AON_SOC_ADDRESS_3_0	0x48000
 
 static const struct amdgpu_hwip_reg_entry vcn_reg_list_4_0_3[] = {
 	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_POWER_STATUS),
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index ba603b2246e2..f11df9c2ec13 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -46,6 +46,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0						0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0					(0x48300 + 0x38000)
+#define VCN1_AON_SOC_ADDRESS_3_0					(0x48000 + 0x38000)
 
 #define VCN_HARVEST_MMSCH							0
 
@@ -1022,6 +1023,10 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 			ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
 			VCN_RB1_DB_CTRL__EN_MASK);
 
+	/* Keeping one read-back to ensure all register writes are done, otherwise
+	 * it may introduce race conditions */
+	RREG32_SOC15(VCN, inst_idx, regVCN_RB1_DB_CTRL);
+
 	return 0;
 }
 
@@ -1204,6 +1209,10 @@ static int vcn_v4_0_5_start(struct amdgpu_vcn_inst *vinst)
 	WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
 	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
 
+	/* Keeping one read-back to ensure all register writes are done, otherwise
+	 * it may introduce race conditions */
+	RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index d99d05f42f1d..b90da3d3e140 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -533,7 +533,8 @@ static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
 
 	/* VCN global tiling registers */
 	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
-		VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+		VCN, inst_idx, regUVD_GFX10_ADDR_CONFIG),
+		adev->gfx.config.gb_addr_config, 0, indirect);
 
 	return;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index 581d8629b9d9..e0e84ef7f568 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -503,6 +503,52 @@ static void vcn_v5_0_1_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
 }
 
 /**
+ * vcn_v5_0_1_pause_dpg_mode - VCN pause with dpg mode
+ *
+ * @vinst: VCN instance
+ * @new_state: pause state
+ *
+ * Pause dpg mode for VCN block
+ */
+static int vcn_v5_0_1_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     struct dpg_pause_state *new_state)
+{
+	struct amdgpu_device *adev = vinst->adev;
+	uint32_t reg_data = 0;
+	int vcn_inst;
+
+	vcn_inst = GET_INST(VCN, vinst->inst);
+
+	/* pause/unpause if state is changed */
+	if (vinst->pause_state.fw_based != new_state->fw_based) {
+		DRM_DEV_DEBUG(adev->dev, "dpg pause state changed %d -> %d %s\n",
+			vinst->pause_state.fw_based, new_state->fw_based,
+			new_state->fw_based ? "VCN_DPG_STATE__PAUSE" : "VCN_DPG_STATE__UNPAUSE");
+		reg_data = RREG32_SOC15(VCN, vcn_inst, regUVD_DPG_PAUSE) &
+			(~UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
+
+		if (new_state->fw_based == VCN_DPG_STATE__PAUSE) {
+			/* pause DPG */
+			reg_data |= UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
+			WREG32_SOC15(VCN, vcn_inst, regUVD_DPG_PAUSE, reg_data);
+
+			/* wait for ACK */
+			SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_DPG_PAUSE,
+					UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK,
+					UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
+		} else {
+			/* unpause DPG, no need to wait */
+			reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
+			WREG32_SOC15(VCN, vcn_inst, regUVD_DPG_PAUSE, reg_data);
+		}
+		vinst->pause_state.fw_based = new_state->fw_based;
+	}
+
+	return 0;
+}
+
+
+/**
  * vcn_v5_0_1_start_dpg_mode - VCN start with dpg mode
  *
  * @vinst: VCN instance
@@ -518,6 +564,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 	volatile struct amdgpu_vcn5_fw_shared *fw_shared =
 		adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
+	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__PAUSE};
 	int vcn_inst;
 	uint32_t tmp;
 
@@ -582,6 +629,9 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 	if (indirect)
 		amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
 
+	/* Pause dpg */
+	vcn_v5_0_1_pause_dpg_mode(vinst, &state);
+
 	ring = &adev->vcn.inst[inst_idx].ring_enc[0];
 
 	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, lower_32_bits(ring->gpu_addr));
@@ -775,9 +825,13 @@ static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
 	int inst_idx = vinst->inst;
 	uint32_t tmp;
 	int vcn_inst;
+	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE};
 
 	vcn_inst = GET_INST(VCN, inst_idx);
 
+	/* Unpause dpg */
+	vcn_v5_0_1_pause_dpg_mode(vinst, &state);
+
 	/* Wait for power status to be 1 */
 	SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_POWER_STATUS, 1,
 		UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 86d8bc10d90a..9b3510e53112 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -239,6 +239,13 @@ static const struct amdgpu_video_codec_info cz_video_codecs_decode_array[] =
 		.max_pixels_per_frame = 4096 * 4096,
 		.max_level = 186,
 	},
+	{
+		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
+		.max_width = 4096,
+		.max_height = 4096,
+		.max_pixels_per_frame = 4096 * 4096,
+		.max_level = 0,
+	},
 };
 
 static const struct amdgpu_video_codecs cz_video_codecs_decode =
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index e477d7509646..9bbee484d57c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1983,9 +1983,6 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev)
 	if (kfd_dbg_has_ttmps_always_setup(dev->gpu))
 		dev->node_props.debug_prop |= HSA_DBG_DISPATCH_INFO_ALWAYS_VALID;
 
-	if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)
-		dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED;
-
 	if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0)) {
 		if (KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 3) ||
 		    KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 4))
@@ -2001,7 +1998,11 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev)
 			dev->node_props.capability |=
 				HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED;
 
-		dev->node_props.capability |= HSA_CAP_PER_QUEUE_RESET_SUPPORTED;
+		if (!amdgpu_sriov_vf(dev->gpu->adev))
+			dev->node_props.capability |= HSA_CAP_PER_QUEUE_RESET_SUPPORTED;
+
+		if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)
+			dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED;
 	} else {
 		dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 |
 					HSA_DBG_WATCH_ADDR_MASK_HI_BIT;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d0d8ad5368c3..cc01b9c68b47 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -372,6 +372,8 @@ get_crtc_by_otg_inst(struct amdgpu_device *adev,
 static inline bool is_dc_timing_adjust_needed(struct dm_crtc_state *old_state,
 					      struct dm_crtc_state *new_state)
 {
+	if (new_state->stream->adjust.timing_adjust_pending)
+		return true;
 	if (new_state->freesync_config.state ==  VRR_STATE_ACTIVE_FIXED)
 		return true;
 	else if (amdgpu_dm_crtc_vrr_active(old_state) != amdgpu_dm_crtc_vrr_active(new_state))
@@ -673,15 +675,21 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 
 	if (acrtc->dm_irq_params.stream &&
-	    acrtc->dm_irq_params.vrr_params.supported &&
-	    acrtc->dm_irq_params.freesync_config.state ==
-		    VRR_STATE_ACTIVE_VARIABLE) {
+		acrtc->dm_irq_params.vrr_params.supported) {
+		bool replay_en = acrtc->dm_irq_params.stream->link->replay_settings.replay_feature_enabled;
+		bool psr_en = acrtc->dm_irq_params.stream->link->psr_settings.psr_feature_enabled;
+		bool fs_active_var_en = acrtc->dm_irq_params.freesync_config.state == VRR_STATE_ACTIVE_VARIABLE;
+
 		mod_freesync_handle_v_update(adev->dm.freesync_module,
 					     acrtc->dm_irq_params.stream,
 					     &acrtc->dm_irq_params.vrr_params);
 
-		dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc->dm_irq_params.stream,
-					   &acrtc->dm_irq_params.vrr_params.adjust);
+		/* update vmin_vmax only if freesync is enabled, or only if PSR and REPLAY are disabled */
+		if (fs_active_var_en || (!fs_active_var_en && !replay_en && !psr_en)) {
+			dc_stream_adjust_vmin_vmax(adev->dm.dc,
+					acrtc->dm_irq_params.stream,
+					&acrtc->dm_irq_params.vrr_params.adjust);
+		}
 	}
 
 	/*
@@ -1726,9 +1734,30 @@ static const struct dmi_system_id dmi_quirk_table[] = {
 		.callback = edp0_on_dp1_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 645 14 inch G11 Notebook PC"),
+		},
+	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 665 16 inch G11 Notebook PC"),
 		},
 	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook 445 14 inch G11 Notebook PC"),
+		},
+	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook 465 16 inch G11 Notebook PC"),
+		},
+	},
 	{}
 	/* TODO: refactor this from a fixed table to a dynamic option */
 };
@@ -1899,26 +1928,6 @@ static enum dmub_ips_disable_type dm_get_default_ips_mode(
 	switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) {
 	case IP_VERSION(3, 5, 0):
 	case IP_VERSION(3, 6, 0):
-		/*
-		 * On DCN35 systems with Z8 enabled, it's possible for IPS2 + Z8 to
-		 * cause a hard hang. A fix exists for newer PMFW.
-		 *
-		 * As a workaround, for non-fixed PMFW, force IPS1+RCG as the deepest
-		 * IPS state in all cases, except for s0ix and all displays off (DPMS),
-		 * where IPS2 is allowed.
-		 *
-		 * When checking pmfw version, use the major and minor only.
-		 */
-		if ((adev->pm.fw_version & 0x00FFFF00) < 0x005D6300)
-			ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
-		else if (amdgpu_ip_version(adev, GC_HWIP, 0) > IP_VERSION(11, 5, 0))
-			/*
-			 * Other ASICs with DCN35 that have residency issues with
-			 * IPS2 in idle.
-			 * We want them to use IPS2 only in display off cases.
-			 */
-			ret =  DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
-		break;
 	case IP_VERSION(3, 5, 1):
 		ret =  DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
 		break;
@@ -3334,16 +3343,16 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state,
 	for (k = 0; k < dc_state->stream_count; k++) {
 		bundle->stream_update.stream = dc_state->streams[k];
 
-		for (m = 0; m < dc_state->stream_status->plane_count; m++) {
+		for (m = 0; m < dc_state->stream_status[k].plane_count; m++) {
 			bundle->surface_updates[m].surface =
-				dc_state->stream_status->plane_states[m];
+				dc_state->stream_status[k].plane_states[m];
 			bundle->surface_updates[m].surface->force_full_update =
 				true;
 		}
 
 		update_planes_and_stream_adapter(dm->dc,
 					 UPDATE_TYPE_FULL,
-					 dc_state->stream_status->plane_count,
+					 dc_state->stream_status[k].plane_count,
 					 dc_state->streams[k],
 					 &bundle->stream_update,
 					 bundle->surface_updates);
@@ -6500,12 +6509,12 @@ decide_crtc_timing_for_drm_display_mode(struct drm_display_mode *drm_mode,
 					const struct drm_display_mode *native_mode,
 					bool scale_enabled)
 {
-	if (scale_enabled) {
-		copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
-	} else if (native_mode->clock == drm_mode->clock &&
-			native_mode->htotal == drm_mode->htotal &&
-			native_mode->vtotal == drm_mode->vtotal) {
-		copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
+	if (scale_enabled || (
+	    native_mode->clock == drm_mode->clock &&
+	    native_mode->htotal == drm_mode->htotal &&
+	    native_mode->vtotal == drm_mode->vtotal)) {
+		if (native_mode->crtc_clock)
+			copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
 	} else {
 		/* no scaling nor amdgpu inserted, no need to patch */
 	}
@@ -11022,6 +11031,9 @@ static bool should_reset_plane(struct drm_atomic_state *state,
 	    state->allow_modeset)
 		return true;
 
+	if (amdgpu_in_reset(adev) && state->allow_modeset)
+		return true;
+
 	/* Exit early if we know that we're adding or removing the plane. */
 	if (old_plane_state->crtc != new_plane_state->crtc)
 		return true;
@@ -12739,7 +12751,7 @@ int amdgpu_dm_process_dmub_aux_transfer_sync(
 		 * Transient states before tunneling is enabled could
 		 * lead to this error. We can ignore this for now.
 		 */
-		if (p_notify->result != AUX_RET_ERROR_PROTOCOL_ERROR) {
+		if (p_notify->result == AUX_RET_ERROR_PROTOCOL_ERROR) {
 			DRM_WARN("DPIA AUX failed on 0x%x(%d), error %d\n",
 					payload->address, payload->length,
 					p_notify->result);
@@ -12748,22 +12760,15 @@ int amdgpu_dm_process_dmub_aux_transfer_sync(
 		goto out;
 	}
 
+	payload->reply[0] = adev->dm.dmub_notify->aux_reply.command & 0xF;
+	if (adev->dm.dmub_notify->aux_reply.command & 0xF0)
+		/* The reply is stored in the top nibble of the command. */
+		payload->reply[0] = (adev->dm.dmub_notify->aux_reply.command >> 4) & 0xF;
 
-	payload->reply[0] = adev->dm.dmub_notify->aux_reply.command;
-	if (!payload->write && p_notify->aux_reply.length &&
-			(payload->reply[0] == AUX_TRANSACTION_REPLY_AUX_ACK)) {
-
-		if (payload->length != p_notify->aux_reply.length) {
-			DRM_WARN("invalid read length %d from DPIA AUX 0x%x(%d)!\n",
-				p_notify->aux_reply.length,
-					payload->address, payload->length);
-			*operation_result = AUX_RET_ERROR_INVALID_REPLY;
-			goto out;
-		}
-
+	/*write req may receive a byte indicating partially written number as well*/
+	if (p_notify->aux_reply.length)
 		memcpy(payload->data, p_notify->aux_reply.data,
 				p_notify->aux_reply.length);
-	}
 
 	/* success */
 	ret = p_notify->aux_reply.length;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 36a830a7440f..e8bdd7f0c460 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -113,6 +113,7 @@ bool amdgpu_dm_crtc_vrr_active(const struct dm_crtc_state *dm_state)
  *
  * Panel Replay and PSR SU
  * - Enable when:
+ *      - VRR is disabled
  *      - vblank counter is disabled
  *      - entry is allowed: usermode demonstrates an adequate number of fast
  *        commits)
@@ -131,19 +132,20 @@ static void amdgpu_dm_crtc_set_panel_sr_feature(
 	bool is_sr_active = (link->replay_settings.replay_allow_active ||
 				 link->psr_settings.psr_allow_active);
 	bool is_crc_window_active = false;
+	bool vrr_active = amdgpu_dm_crtc_vrr_active_irq(vblank_work->acrtc);
 
 #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
 	is_crc_window_active =
 		amdgpu_dm_crc_window_is_activated(&vblank_work->acrtc->base);
 #endif
 
-	if (link->replay_settings.replay_feature_enabled &&
+	if (link->replay_settings.replay_feature_enabled && !vrr_active &&
 		allow_sr_entry && !is_sr_active && !is_crc_window_active) {
 		amdgpu_dm_replay_enable(vblank_work->stream, true);
 	} else if (vblank_enabled) {
 		if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1 && is_sr_active)
 			amdgpu_dm_psr_disable(vblank_work->stream, false);
-	} else if (link->psr_settings.psr_feature_enabled &&
+	} else if (link->psr_settings.psr_feature_enabled && !vrr_active &&
 		allow_sr_entry && !is_sr_active && !is_crc_window_active) {
 
 		struct amdgpu_dm_connector *aconn =
@@ -244,6 +246,8 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 	struct vblank_control_work *vblank_work =
 		container_of(work, struct vblank_control_work, work);
 	struct amdgpu_display_manager *dm = vblank_work->dm;
+	struct amdgpu_device *adev = drm_to_adev(dm->ddev);
+	int r;
 
 	mutex_lock(&dm->dc_lock);
 
@@ -271,8 +275,15 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 			vblank_work->acrtc->dm_irq_params.allow_sr_entry);
 	}
 
-	if (dm->active_vblank_irq_count == 0)
+	if (dm->active_vblank_irq_count == 0) {
+		r = amdgpu_dpm_pause_power_profile(adev, true);
+		if (r)
+			dev_warn(adev->dev, "failed to set default power profile mode\n");
 		dc_allow_idle_optimizations(dm->dc, true);
+		r = amdgpu_dpm_pause_power_profile(adev, false);
+		if (r)
+			dev_warn(adev->dev, "failed to restore the power profile mode\n");
+	}
 
 	mutex_unlock(&dm->dc_lock);
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index 5198a079b463..8f22ad966543 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -173,6 +173,9 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work,
 	unsigned int conn_index = aconnector->base.index;
 
 	guard(mutex)(&hdcp_w->mutex);
+	drm_connector_get(&aconnector->base);
+	if (hdcp_w->aconnector[conn_index])
+		drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
 	hdcp_w->aconnector[conn_index] = aconnector;
 
 	memset(&link_adjust, 0, sizeof(link_adjust));
@@ -220,7 +223,6 @@ static void hdcp_remove_display(struct hdcp_workqueue *hdcp_work,
 	unsigned int conn_index = aconnector->base.index;
 
 	guard(mutex)(&hdcp_w->mutex);
-	hdcp_w->aconnector[conn_index] = aconnector;
 
 	/* the removal of display will invoke auth reset -> hdcp destroy and
 	 * we'd expect the Content Protection (CP) property changed back to
@@ -236,7 +238,10 @@ static void hdcp_remove_display(struct hdcp_workqueue *hdcp_work,
 	}
 
 	mod_hdcp_remove_display(&hdcp_w->hdcp, aconnector->base.index, &hdcp_w->output);
-
+	if (hdcp_w->aconnector[conn_index]) {
+		drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
+		hdcp_w->aconnector[conn_index] = NULL;
+	}
 	process_output(hdcp_w);
 }
 
@@ -254,6 +259,10 @@ void hdcp_reset_display(struct hdcp_workqueue *hdcp_work, unsigned int link_inde
 	for (conn_index = 0; conn_index < AMDGPU_DM_MAX_DISPLAY_INDEX; conn_index++) {
 		hdcp_w->encryption_status[conn_index] =
 			MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+		if (hdcp_w->aconnector[conn_index]) {
+			drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
+			hdcp_w->aconnector[conn_index] = NULL;
+		}
 	}
 
 	process_output(hdcp_w);
@@ -488,6 +497,7 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
 	struct hdcp_workqueue *hdcp_work = handle;
 	struct amdgpu_dm_connector *aconnector = config->dm_stream_ctx;
 	int link_index = aconnector->dc_link->link_index;
+	unsigned int conn_index = aconnector->base.index;
 	struct mod_hdcp_display *display = &hdcp_work[link_index].display;
 	struct mod_hdcp_link *link = &hdcp_work[link_index].link;
 	struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
@@ -544,7 +554,10 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
 	guard(mutex)(&hdcp_w->mutex);
 
 	mod_hdcp_add_display(&hdcp_w->hdcp, link, display, &hdcp_w->output);
-
+	drm_connector_get(&aconnector->base);
+	if (hdcp_w->aconnector[conn_index])
+		drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
+	hdcp_w->aconnector[conn_index] = aconnector;
 	process_output(hdcp_w);
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 2cd35392e2da..1395a748d726 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -918,7 +918,7 @@ dm_helpers_probe_acpi_edid(void *data, u8 *buf, unsigned int block, size_t len)
 {
 	struct drm_connector *connector = data;
 	struct acpi_device *acpidev = ACPI_COMPANION(connector->dev->dev);
-	unsigned char start = block * EDID_LENGTH;
+	unsigned short start = block * EDID_LENGTH;
 	struct edid *edid;
 	int r;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 7ceedf626d23..5cdbc86ef8f5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -51,6 +51,9 @@
 
 #define PEAK_FACTOR_X1000 1006
 
+/*
+ * This function handles both native AUX and I2C-Over-AUX transactions.
+ */
 static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 				  struct drm_dp_aux_msg *msg)
 {
@@ -59,6 +62,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	enum aux_return_code_type operation_result;
 	struct amdgpu_device *adev;
 	struct ddc_service *ddc;
+	uint8_t copy[16];
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
@@ -74,6 +78,11 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 			(msg->request & DP_AUX_I2C_WRITE_STATUS_UPDATE) != 0;
 	payload.defer_delay = 0;
 
+	if (payload.write) {
+		memcpy(copy, msg->buffer, msg->size);
+		payload.data = copy;
+	}
+
 	result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload,
 				      &operation_result);
 
@@ -87,15 +96,25 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	if (adev->dm.aux_hpd_discon_quirk) {
 		if (msg->address == DP_SIDEBAND_MSG_DOWN_REQ_BASE &&
 			operation_result == AUX_RET_ERROR_HPD_DISCON) {
-			result = 0;
+			result = msg->size;
 			operation_result = AUX_RET_SUCCESS;
 		}
 	}
 
-	if (payload.write && result >= 0)
-		result = msg->size;
+	/*
+	 * result equals to 0 includes the cases of AUX_DEFER/I2C_DEFER
+	 */
+	if (payload.write && result >= 0) {
+		if (result) {
+			/*one byte indicating partially written bytes*/
+			drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX partially written\n");
+			result = payload.data[0];
+		} else if (!payload.reply[0])
+			/*I2C_ACK|AUX_ACK*/
+			result = msg->size;
+	}
 
-	if (result < 0)
+	if (result < 0) {
 		switch (operation_result) {
 		case AUX_RET_SUCCESS:
 			break;
@@ -114,6 +133,13 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 			break;
 		}
 
+		drm_dbg_dp(adev_to_drm(adev), "amdgpu: DP AUX transfer fail:%d\n", operation_result);
+	}
+
+	if (payload.reply[0])
+		drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX reply command not ACK: 0x%02x.",
+			payload.reply[0]);
+
 	return result;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 28d1353f403d..ba4ce8a63158 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -439,9 +439,12 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 	 * Don't adjust DRR while there's bandwidth optimizations pending to
 	 * avoid conflicting with firmware updates.
 	 */
-	if (dc->ctx->dce_version > DCE_VERSION_MAX)
-		if (dc->optimized_required || dc->wm_optimized_required)
+	if (dc->ctx->dce_version > DCE_VERSION_MAX) {
+		if (dc->optimized_required || dc->wm_optimized_required) {
+			stream->adjust.timing_adjust_pending = true;
 			return false;
+		}
+	}
 
 	dc_exit_ips_for_hw_access(dc);
 
@@ -3168,7 +3171,8 @@ static void copy_stream_update_to_stream(struct dc *dc,
 
 	if (update->crtc_timing_adjust) {
 		if (stream->adjust.v_total_min != update->crtc_timing_adjust->v_total_min ||
-			stream->adjust.v_total_max != update->crtc_timing_adjust->v_total_max)
+			stream->adjust.v_total_max != update->crtc_timing_adjust->v_total_max ||
+			stream->adjust.timing_adjust_pending)
 			update->crtc_timing_adjust->timing_adjust_pending = true;
 		stream->adjust = *update->crtc_timing_adjust;
 		update->crtc_timing_adjust->timing_adjust_pending = false;
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
index 0c8ec30ea672..731fbd4bc600 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
@@ -910,7 +910,7 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm
 }
 
 //TODO : Could be possibly moved to a common helper layer.
-static bool dml21_wrapper_get_plane_id(const struct dc_state *context, const struct dc_plane_state *plane, unsigned int *plane_id)
+static bool dml21_wrapper_get_plane_id(const struct dc_state *context, unsigned int stream_id, const struct dc_plane_state *plane, unsigned int *plane_id)
 {
 	int i, j;
 
@@ -918,10 +918,12 @@ static bool dml21_wrapper_get_plane_id(const struct dc_state *context, const str
 		return false;
 
 	for (i = 0; i < context->stream_count; i++) {
-		for (j = 0; j < context->stream_status[i].plane_count; j++) {
-			if (context->stream_status[i].plane_states[j] == plane) {
-				*plane_id = (i << 16) | j;
-				return true;
+		if (context->streams[i]->stream_id == stream_id) {
+			for (j = 0; j < context->stream_status[i].plane_count; j++) {
+				if (context->stream_status[i].plane_states[j] == plane) {
+					*plane_id = (i << 16) | j;
+					return true;
+				}
 			}
 		}
 	}
@@ -944,14 +946,14 @@ static unsigned int map_stream_to_dml21_display_cfg(const struct dml2_context *d
 	return location;
 }
 
-static unsigned int map_plane_to_dml21_display_cfg(const struct dml2_context *dml_ctx,
+static unsigned int map_plane_to_dml21_display_cfg(const struct dml2_context *dml_ctx, unsigned int stream_id,
 		const struct dc_plane_state *plane, const struct dc_state *context)
 {
 	unsigned int plane_id;
 	int i = 0;
 	int location = -1;
 
-	if (!dml21_wrapper_get_plane_id(context, plane, &plane_id)) {
+	if (!dml21_wrapper_get_plane_id(context, stream_id, plane, &plane_id)) {
 		ASSERT(false);
 		return -1;
 	}
@@ -1037,7 +1039,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s
 			dml_dispcfg->plane_descriptors[disp_cfg_plane_location].stream_index = disp_cfg_stream_location;
 		} else {
 			for (plane_index = 0; plane_index < context->stream_status[stream_index].plane_count; plane_index++) {
-				disp_cfg_plane_location = map_plane_to_dml21_display_cfg(dml_ctx, context->stream_status[stream_index].plane_states[plane_index], context);
+				disp_cfg_plane_location = map_plane_to_dml21_display_cfg(dml_ctx, context->streams[stream_index]->stream_id, context->stream_status[stream_index].plane_states[plane_index], context);
 
 				if (disp_cfg_plane_location < 0)
 					disp_cfg_plane_location = dml_dispcfg->num_planes++;
@@ -1048,7 +1050,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s
 				populate_dml21_plane_config_from_plane_state(dml_ctx, &dml_dispcfg->plane_descriptors[disp_cfg_plane_location], context->stream_status[stream_index].plane_states[plane_index], context, stream_index);
 				dml_dispcfg->plane_descriptors[disp_cfg_plane_location].stream_index = disp_cfg_stream_location;
 
-				if (dml21_wrapper_get_plane_id(context, context->stream_status[stream_index].plane_states[plane_index], &dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[disp_cfg_plane_location]))
+				if (dml21_wrapper_get_plane_id(context, context->streams[stream_index]->stream_id, context->stream_status[stream_index].plane_states[plane_index], &dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[disp_cfg_plane_location]))
 					dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id_valid[disp_cfg_plane_location] = true;
 
 				/* apply forced pstate policy */
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
index be54f0e696ce..ed6584535e89 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
@@ -2,6 +2,7 @@
 //
 // Copyright 2024 Advanced Micro Devices, Inc.
 
+#include <linux/vmalloc.h>
 
 #include "dml2_internal_types.h"
 #include "dml_top.h"
@@ -13,11 +14,11 @@
 
 static bool dml21_allocate_memory(struct dml2_context **dml_ctx)
 {
-	*dml_ctx = kzalloc(sizeof(struct dml2_context), GFP_KERNEL);
+	*dml_ctx = vzalloc(sizeof(struct dml2_context));
 	if (!(*dml_ctx))
 		return false;
 
-	(*dml_ctx)->v21.dml_init.dml2_instance = kzalloc(sizeof(struct dml2_instance), GFP_KERNEL);
+	(*dml_ctx)->v21.dml_init.dml2_instance = vzalloc(sizeof(struct dml2_instance));
 	if (!((*dml_ctx)->v21.dml_init.dml2_instance))
 		return false;
 
@@ -27,7 +28,7 @@ static bool dml21_allocate_memory(struct dml2_context **dml_ctx)
 	(*dml_ctx)->v21.mode_support.display_config = &(*dml_ctx)->v21.display_config;
 	(*dml_ctx)->v21.mode_programming.display_config = (*dml_ctx)->v21.mode_support.display_config;
 
-	(*dml_ctx)->v21.mode_programming.programming = kzalloc(sizeof(struct dml2_display_cfg_programming), GFP_KERNEL);
+	(*dml_ctx)->v21.mode_programming.programming = vzalloc(sizeof(struct dml2_display_cfg_programming));
 	if (!((*dml_ctx)->v21.mode_programming.programming))
 		return false;
 
@@ -86,6 +87,8 @@ static void dml21_init(const struct dc *in_dc, struct dml2_context **dml_ctx, co
 	/* Store configuration options */
 	(*dml_ctx)->config = *config;
 
+	DC_FP_START();
+
 	/*Initialize SOCBB and DCNIP params */
 	dml21_initialize_soc_bb_params(&(*dml_ctx)->v21.dml_init, config, in_dc);
 	dml21_initialize_ip_params(&(*dml_ctx)->v21.dml_init, config, in_dc);
@@ -96,6 +99,8 @@ static void dml21_init(const struct dc *in_dc, struct dml2_context **dml_ctx, co
 
 	/*Initialize DML21 instance */
 	dml2_initialize_instance(&(*dml_ctx)->v21.dml_init);
+
+	DC_FP_END();
 }
 
 bool dml21_create(const struct dc *in_dc, struct dml2_context **dml_ctx, const struct dml2_configuration_options *config)
@@ -111,8 +116,8 @@ bool dml21_create(const struct dc *in_dc, struct dml2_context **dml_ctx, const s
 
 void dml21_destroy(struct dml2_context *dml2)
 {
-	kfree(dml2->v21.dml_init.dml2_instance);
-	kfree(dml2->v21.mode_programming.programming);
+	vfree(dml2->v21.dml_init.dml2_instance);
+	vfree(dml2->v21.mode_programming.programming);
 }
 
 static void dml21_calculate_rq_and_dlg_params(const struct dc *dc, struct dc_state *context, struct resource_context *out_new_hw_state,
@@ -229,7 +234,9 @@ static bool dml21_mode_check_and_programming(const struct dc *in_dc, struct dc_s
 	if (!result)
 		return false;
 
+	DC_FP_START();
 	result = dml2_build_mode_programming(mode_programming);
+	DC_FP_END();
 	if (!result)
 		return false;
 
@@ -272,7 +279,9 @@ static bool dml21_check_mode_support(const struct dc *in_dc, struct dc_state *co
 	mode_support->dml2_instance = dml_init->dml2_instance;
 	dml21_map_dc_state_into_dml_display_cfg(in_dc, context, dml_ctx);
 	dml_ctx->v21.mode_programming.dml2_instance->scratch.build_mode_programming_locals.mode_programming_params.programming = dml_ctx->v21.mode_programming.programming;
+	DC_FP_START();
 	is_supported = dml2_check_mode_supported(mode_support);
+	DC_FP_END();
 	if (!is_supported)
 		return false;
 
@@ -284,10 +293,11 @@ bool dml21_validate(const struct dc *in_dc, struct dc_state *context, struct dml
 	bool out = false;
 
 	/* Use dml_validate_only for fast_validate path */
-	if (fast_validate) {
+	if (fast_validate)
 		out = dml21_check_mode_support(in_dc, context, dml_ctx);
-	} else
+	else
 		out = dml21_mode_check_and_programming(in_dc, context, dml_ctx);
+
 	return out;
 }
 
@@ -426,8 +436,12 @@ void dml21_copy(struct dml2_context *dst_dml_ctx,
 
 	dst_dml_ctx->v21.mode_programming.programming = dst_dml2_programming;
 
+	DC_FP_START();
+
 	/* need to initialize copied instance for internal references to be correct */
 	dml2_initialize_instance(&dst_dml_ctx->v21.dml_init);
+
+	DC_FP_END();
 }
 
 bool dml21_create_copy(struct dml2_context **dst_dml_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 2061d43b92e1..ab6baf269801 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -973,7 +973,9 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
 	}
 }
 
-static void get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc_state *context, struct scaler_data *out)
+static struct scaler_data *get_scaler_data_for_plane(
+		const struct dc_plane_state *in,
+		struct dc_state *context)
 {
 	int i;
 	struct pipe_ctx *temp_pipe = &context->res_ctx.temp_pipe;
@@ -994,7 +996,7 @@ static void get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc
 	}
 
 	ASSERT(i < MAX_PIPES);
-	memcpy(out, &temp_pipe->plane_res.scl_data, sizeof(*out));
+	return &temp_pipe->plane_res.scl_data;
 }
 
 static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location,
@@ -1057,11 +1059,7 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out
 						    const struct dc_plane_state *in, struct dc_state *context,
 						    const struct soc_bounding_box_st *soc)
 {
-	struct scaler_data *scaler_data = kzalloc(sizeof(*scaler_data), GFP_KERNEL);
-	if (!scaler_data)
-		return;
-
-	get_scaler_data_for_plane(in, context, scaler_data);
+	struct scaler_data *scaler_data = get_scaler_data_for_plane(in, context);
 
 	out->CursorBPP[location] = dml_cur_32bit;
 	out->CursorWidth[location] = 256;
@@ -1126,8 +1124,6 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out
 	out->DynamicMetadataTransmittedBytes[location] = 0;
 
 	out->NumberOfCursors[location] = 1;
-
-	kfree(scaler_data);
 }
 
 static unsigned int map_stream_to_dml_display_cfg(const struct dml2_context *dml2,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
index 939ee0708bd2..e89571874185 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
@@ -24,6 +24,8 @@
  *
  */
 
+#include <linux/vmalloc.h>
+
 #include "display_mode_core.h"
 #include "dml2_internal_types.h"
 #include "dml2_utils.h"
@@ -732,17 +734,22 @@ bool dml2_validate(const struct dc *in_dc, struct dc_state *context, struct dml2
 		return out;
 	}
 
+	DC_FP_START();
+
 	/* Use dml_validate_only for fast_validate path */
 	if (fast_validate)
 		out = dml2_validate_only(context);
 	else
 		out = dml2_validate_and_build_resource(in_dc, context);
+
+	DC_FP_END();
+
 	return out;
 }
 
 static inline struct dml2_context *dml2_allocate_memory(void)
 {
-	return (struct dml2_context *) kzalloc(sizeof(struct dml2_context), GFP_KERNEL);
+	return (struct dml2_context *) vzalloc(sizeof(struct dml2_context));
 }
 
 static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2)
@@ -779,11 +786,15 @@ static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_op
 		break;
 	}
 
+	DC_FP_START();
+
 	initialize_dml2_ip_params(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.ip);
 
 	initialize_dml2_soc_bbox(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc);
 
 	initialize_dml2_soc_states(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc, &(*dml2)->v20.dml_core_ctx.states);
+
+	DC_FP_END();
 }
 
 bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2)
@@ -812,7 +823,7 @@ void dml2_destroy(struct dml2_context *dml2)
 
 	if (dml2->architecture == dml2_architecture_21)
 		dml21_destroy(dml2);
-	kfree(dml2);
+	vfree(dml2);
 }
 
 void dml2_extract_dram_and_fclk_change_support(struct dml2_context *dml2,
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
index 1236e0f9a256..712aff7e17f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
@@ -120,10 +120,11 @@ void dpp401_set_cursor_attributes(
 	enum dc_cursor_color_format color_format = cursor_attributes->color_format;
 	int cur_rom_en = 0;
 
-	// DCN4 should always do Cursor degamma for Cursor Color modes
 	if (color_format == CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA ||
 		color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) {
-		cur_rom_en = 1;
+		if (cursor_attributes->attribute_flags.bits.ENABLE_CURSOR_DEGAMMA) {
+			cur_rom_en = 1;
+		}
 	}
 
 	REG_UPDATE_3(CURSOR0_CONTROL,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
index 5489f3d431f6..3af6a3402b89 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -1980,9 +1980,9 @@ void dcn401_program_pipe(
 				dc->res_pool->hubbub, pipe_ctx->plane_res.hubp->inst, pipe_ctx->hubp_regs.det_size);
 	}
 
-	if (pipe_ctx->update_flags.raw ||
-		(pipe_ctx->plane_state && pipe_ctx->plane_state->update_flags.raw) ||
-		pipe_ctx->stream->update_flags.raw)
+	if (pipe_ctx->plane_state && (pipe_ctx->update_flags.raw ||
+	    pipe_ctx->plane_state->update_flags.raw ||
+	    pipe_ctx->stream->update_flags.raw))
 		dc->hwss.update_dchubp_dpp(dc, pipe_ctx, context);
 
 	if (pipe_ctx->plane_state && (pipe_ctx->update_flags.bits.enable ||
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 268626e73c54..53c961f86d43 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -148,6 +148,7 @@ void link_blank_dp_stream(struct dc_link *link, bool hw_init)
 void link_set_all_streams_dpms_off_for_link(struct dc_link *link)
 {
 	struct pipe_ctx *pipes[MAX_PIPES];
+	struct dc_stream_state *streams[MAX_PIPES];
 	struct dc_state *state = link->dc->current_state;
 	uint8_t count;
 	int i;
@@ -160,10 +161,18 @@ void link_set_all_streams_dpms_off_for_link(struct dc_link *link)
 
 	link_get_master_pipes_with_dpms_on(link, state, &count, pipes);
 
+	/* The subsequent call to dc_commit_updates_for_stream for a full update
+	 * will release the current state and swap to a new state. Releasing the
+	 * current state results in the stream pointers in the pipe_ctx structs
+	 * to be zero'd. Hence, cache all streams prior to dc_commit_updates_for_stream.
+	 */
+	for (i = 0; i < count; i++)
+		streams[i] = pipes[i]->stream;
+
 	for (i = 0; i < count; i++) {
-		stream_update.stream = pipes[i]->stream;
+		stream_update.stream = streams[i];
 		dc_commit_updates_for_stream(link->ctx->dc, NULL, 0,
-				pipes[i]->stream, &stream_update,
+				streams[i], &stream_update,
 				state);
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
index 34d2e097ca2e..5a5d48fadbf2 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
@@ -35,6 +35,17 @@
 #define DC_LOGGER \
 	link->ctx->logger
 
+static void get_default_8b_10b_lttpr_aux_rd_interval(
+		union training_aux_rd_interval *training_rd_interval)
+{
+	/* LTTPR are required to program DPCD 0000Eh to 0x4 (16ms) upon AUX
+	 * read reply to this register. Since old sinks with DPCD rev 1.1
+	 * and earlier may not support this register, assume the mandatory
+	 * value is programmed by the LTTPR to avoid AUX timeout issues.
+	 */
+	training_rd_interval->raw = 0x4;
+}
+
 static int32_t get_cr_training_aux_rd_interval(struct dc_link *link,
 		const struct dc_link_settings *link_settings,
 		enum lttpr_mode lttpr_mode)
@@ -43,17 +54,22 @@ static int32_t get_cr_training_aux_rd_interval(struct dc_link *link,
 	uint32_t wait_in_micro_secs = 100;
 
 	memset(&training_rd_interval, 0, sizeof(training_rd_interval));
-	if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING &&
-			link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) {
-		core_link_read_dpcd(
-				link,
-				DP_TRAINING_AUX_RD_INTERVAL,
-				(uint8_t *)&training_rd_interval,
-				sizeof(training_rd_interval));
-		if (lttpr_mode != LTTPR_MODE_NON_TRANSPARENT)
-			wait_in_micro_secs = 400;
-		if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL)
-			wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
+	if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) {
+		if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12)
+			core_link_read_dpcd(
+					link,
+					DP_TRAINING_AUX_RD_INTERVAL,
+					(uint8_t *)&training_rd_interval,
+					sizeof(training_rd_interval));
+		else if (dp_is_lttpr_present(link))
+			get_default_8b_10b_lttpr_aux_rd_interval(&training_rd_interval);
+
+		if (training_rd_interval.raw != 0) {
+			if (lttpr_mode != LTTPR_MODE_NON_TRANSPARENT)
+				wait_in_micro_secs = 400;
+			if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL)
+				wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
+		}
 	}
 	return wait_in_micro_secs;
 }
@@ -71,13 +87,15 @@ static uint32_t get_eq_training_aux_rd_interval(
 				DP_128B132B_TRAINING_AUX_RD_INTERVAL,
 				(uint8_t *)&training_rd_interval,
 				sizeof(training_rd_interval));
-	} else if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING &&
-			link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) {
-		core_link_read_dpcd(
-				link,
-				DP_TRAINING_AUX_RD_INTERVAL,
-				(uint8_t *)&training_rd_interval,
-				sizeof(training_rd_interval));
+	} else if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) {
+		if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12)
+			core_link_read_dpcd(
+					link,
+					DP_TRAINING_AUX_RD_INTERVAL,
+					(uint8_t *)&training_rd_interval,
+					sizeof(training_rd_interval));
+		else if (dp_is_lttpr_present(link))
+			get_default_8b_10b_lttpr_aux_rd_interval(&training_rd_interval);
 	}
 
 	switch (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL) {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index 2a59cc61ed8c..944650cb13de 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -2114,8 +2114,6 @@ static bool dcn32_resource_construct(
 #define REG_STRUCT dccg_regs
 	dccg_regs_init();
 
-	DC_FP_START();
-
 	ctx->dc_bios->regs = &bios_regs;
 
 	pool->base.res_cap = &res_cap_dcn32;
@@ -2501,14 +2499,10 @@ static bool dcn32_resource_construct(
 	if (ASICREV_IS_GC_11_0_3(dc->ctx->asic_id.hw_internal_rev) && (dc->config.sdpif_request_limit_words_per_umc == 0))
 		dc->config.sdpif_request_limit_words_per_umc = 16;
 
-	DC_FP_END();
-
 	return true;
 
 create_fail:
 
-	DC_FP_END();
-
 	dcn32_resource_destruct(pool);
 
 	return false;
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 2a9606118d89..21dc956b5f35 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -429,6 +429,7 @@ struct amd_pm_funcs {
 	int (*set_pp_table)(void *handle, const char *buf, size_t size);
 	void (*debugfs_print_current_performance_level)(void *handle, struct seq_file *m);
 	int (*switch_power_profile)(void *handle, enum PP_SMC_POWER_PROFILE type, bool en);
+	int (*pause_power_profile)(void *handle, bool pause);
 /* export to amdgpu */
 	struct amd_vce_state *(*get_vce_clock_state)(void *handle, u32 idx);
 	int (*dispatch_tasks)(void *handle, enum amd_pp_task task_id,
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 81e9b443ca0a..3533d43ed1e7 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -349,6 +349,25 @@ int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev,
 	return ret;
 }
 
+int amdgpu_dpm_pause_power_profile(struct amdgpu_device *adev,
+				   bool pause)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	int ret = 0;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	if (pp_funcs && pp_funcs->pause_power_profile) {
+		mutex_lock(&adev->pm.mutex);
+		ret = pp_funcs->pause_power_profile(
+			adev->powerplay.pp_handle, pause);
+		mutex_unlock(&adev->pm.mutex);
+	}
+
+	return ret;
+}
+
 int amdgpu_dpm_set_xgmi_pstate(struct amdgpu_device *adev,
 			       uint32_t pstate)
 {
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index f93d287dbf13..4c0f7ad14816 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -410,6 +410,8 @@ int amdgpu_dpm_set_xgmi_pstate(struct amdgpu_device *adev,
 int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev,
 				    enum PP_SMC_POWER_PROFILE type,
 				    bool en);
+int amdgpu_dpm_pause_power_profile(struct amdgpu_device *adev,
+				   bool pause);
 
 int amdgpu_dpm_baco_reset(struct amdgpu_device *adev);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 033c3229b555..46cce1d2aaf3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -2398,7 +2398,11 @@ static int smu_switch_power_profile(void *handle,
 			smu_power_profile_mode_get(smu, type);
 		else
 			smu_power_profile_mode_put(smu, type);
-		ret = smu_bump_power_profile_mode(smu, NULL, 0);
+		/* don't switch the active workload when paused */
+		if (smu->pause_workload)
+			ret = 0;
+		else
+			ret = smu_bump_power_profile_mode(smu, NULL, 0);
 		if (ret) {
 			if (enable)
 				smu_power_profile_mode_put(smu, type);
@@ -2411,6 +2415,35 @@ static int smu_switch_power_profile(void *handle,
 	return 0;
 }
 
+static int smu_pause_power_profile(void *handle,
+				   bool pause)
+{
+	struct smu_context *smu = handle;
+	struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
+	u32 workload_mask = 1 << PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
+	int ret;
+
+	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
+		return -EOPNOTSUPP;
+
+	if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
+	    smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) {
+		smu->pause_workload = pause;
+
+		/* force to bootup default profile */
+		if (smu->pause_workload && smu->ppt_funcs->set_power_profile_mode)
+			ret = smu->ppt_funcs->set_power_profile_mode(smu,
+								     workload_mask,
+								     NULL,
+								     0);
+		else
+			ret = smu_bump_power_profile_mode(smu, NULL, 0);
+		return ret;
+	}
+
+	return 0;
+}
+
 static enum amd_dpm_forced_level smu_get_performance_level(void *handle)
 {
 	struct smu_context *smu = handle;
@@ -3733,6 +3766,7 @@ static const struct amd_pm_funcs swsmu_pm_funcs = {
 	.get_pp_table            = smu_sys_get_pp_table,
 	.set_pp_table            = smu_sys_set_pp_table,
 	.switch_power_profile    = smu_switch_power_profile,
+	.pause_power_profile     = smu_pause_power_profile,
 	/* export to amdgpu */
 	.dispatch_tasks          = smu_handle_dpm_task,
 	.load_firmware           = smu_load_microcode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 3ba169639f54..dd6d0e7aa242 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -558,6 +558,7 @@ struct smu_context {
 
 	/* asic agnostic workload mask */
 	uint32_t workload_mask;
+	bool pause_workload;
 	/* default/user workload preference */
 	uint32_t power_profile_mode;
 	uint32_t workload_refcount[PP_SMC_POWER_PROFILE_COUNT];
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 78391d8f35a9..25fabf336a64 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1204,7 +1204,7 @@ int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 	uint32_t crystal_clock_freq = 2500;
 	uint32_t tach_period;
 
-	if (speed == 0)
+	if (!speed || speed > UINT_MAX/8)
 		return -EINVAL;
 	/*
 	 * To prevent from possible overheat, some ASICs may have requirement
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 17fc5dc708f4..60e5ac179c15 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -549,7 +549,7 @@ int drm_dev_wedged_event(struct drm_device *dev, unsigned long method)
 		if (drm_WARN_ONCE(dev, !recovery, "invalid recovery method %u\n", opt))
 			break;
 
-		len += scnprintf(event_string + len, sizeof(event_string), "%s,", recovery);
+		len += scnprintf(event_string + len, sizeof(event_string) - len, "%s,", recovery);
 	}
 
 	if (recovery)
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index c299cd94d3f7..cf2463090d3a 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -964,6 +964,10 @@ void drm_show_fdinfo(struct seq_file *m, struct file *f)
 	struct drm_file *file = f->private_data;
 	struct drm_device *dev = file->minor->dev;
 	struct drm_printer p = drm_seq_file_printer(m);
+	int idx;
+
+	if (!drm_dev_enter(dev, &idx))
+		return;
 
 	drm_printf(&p, "drm-driver:\t%s\n", dev->driver->name);
 	drm_printf(&p, "drm-client-id:\t%llu\n", file->client_id);
@@ -983,6 +987,8 @@ void drm_show_fdinfo(struct seq_file *m, struct file *f)
 
 	if (dev->driver->show_fdinfo)
 		dev->driver->show_fdinfo(&p, file);
+
+	drm_dev_exit(idx);
 }
 EXPORT_SYMBOL(drm_show_fdinfo);
 
diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c
index 38431e8360e7..4b2f32889f00 100644
--- a/drivers/gpu/drm/drm_gpusvm.c
+++ b/drivers/gpu/drm/drm_gpusvm.c
@@ -1118,6 +1118,10 @@ static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm,
 	lockdep_assert_held(&gpusvm->notifier_lock);
 
 	if (range->flags.has_dma_mapping) {
+		struct drm_gpusvm_range_flags flags = {
+			.__flags = range->flags.__flags,
+		};
+
 		for (i = 0, j = 0; i < npages; j++) {
 			struct drm_pagemap_device_addr *addr = &range->dma_addr[j];
 
@@ -1131,8 +1135,12 @@ static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm,
 							    dev, *addr);
 			i += 1 << addr->order;
 		}
-		range->flags.has_devmem_pages = false;
-		range->flags.has_dma_mapping = false;
+
+		/* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */
+		flags.has_devmem_pages = false;
+		flags.has_dma_mapping = false;
+		WRITE_ONCE(range->flags.__flags, flags.__flags);
+
 		range->dpagemap = NULL;
 	}
 }
@@ -1334,6 +1342,7 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
 	int err = 0;
 	struct dev_pagemap *pagemap;
 	struct drm_pagemap *dpagemap;
+	struct drm_gpusvm_range_flags flags;
 
 retry:
 	hmm_range.notifier_seq = mmu_interval_read_begin(notifier);
@@ -1378,7 +1387,8 @@ map_pages:
 	 */
 	drm_gpusvm_notifier_lock(gpusvm);
 
-	if (range->flags.unmapped) {
+	flags.__flags = range->flags.__flags;
+	if (flags.unmapped) {
 		drm_gpusvm_notifier_unlock(gpusvm);
 		err = -EFAULT;
 		goto err_free;
@@ -1454,6 +1464,11 @@ map_pages:
 				goto err_unmap;
 			}
 
+			if (ctx->devmem_only) {
+				err = -EFAULT;
+				goto err_unmap;
+			}
+
 			addr = dma_map_page(gpusvm->drm->dev,
 					    page, 0,
 					    PAGE_SIZE << order,
@@ -1469,14 +1484,17 @@ map_pages:
 		}
 		i += 1 << order;
 		num_dma_mapped = i;
+		flags.has_dma_mapping = true;
 	}
 
-	range->flags.has_dma_mapping = true;
 	if (zdd) {
-		range->flags.has_devmem_pages = true;
+		flags.has_devmem_pages = true;
 		range->dpagemap = dpagemap;
 	}
 
+	/* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */
+	WRITE_ONCE(range->flags.__flags, flags.__flags);
+
 	drm_gpusvm_notifier_unlock(gpusvm);
 	kvfree(pfns);
 set_seqno:
@@ -1765,6 +1783,8 @@ int drm_gpusvm_migrate_to_devmem(struct drm_gpusvm *gpusvm,
 		goto err_finalize;
 
 	/* Upon success bind devmem allocation to range and zdd */
+	devmem_allocation->timeslice_expiration = get_jiffies_64() +
+		msecs_to_jiffies(ctx->timeslice_ms);
 	zdd->devmem_allocation = devmem_allocation;	/* Owns ref */
 
 err_finalize:
@@ -1985,6 +2005,13 @@ static int __drm_gpusvm_migrate_to_ram(struct vm_area_struct *vas,
 	void *buf;
 	int i, err = 0;
 
+	if (page) {
+		zdd = page->zone_device_data;
+		if (time_before64(get_jiffies_64(),
+				  zdd->devmem_allocation->timeslice_expiration))
+			return 0;
+	}
+
 	start = ALIGN_DOWN(fault_addr, size);
 	end = ALIGN(fault_addr + 1, size);
 
diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c
index 89e05a5bed1d..a4cd476f9b30 100644
--- a/drivers/gpu/drm/drm_mipi_dbi.c
+++ b/drivers/gpu/drm/drm_mipi_dbi.c
@@ -404,12 +404,16 @@ static void mipi_dbi_blank(struct mipi_dbi_dev *dbidev)
 	u16 height = drm->mode_config.min_height;
 	u16 width = drm->mode_config.min_width;
 	struct mipi_dbi *dbi = &dbidev->dbi;
-	size_t len = width * height * 2;
+	const struct drm_format_info *dst_format;
+	size_t len;
 	int idx;
 
 	if (!drm_dev_enter(drm, &idx))
 		return;
 
+	dst_format = drm_format_info(dbidev->pixel_format);
+	len = drm_format_info_min_pitch(dst_format, 0, width) * height;
+
 	memset(dbidev->tx_buf, 0, len);
 
 	mipi_dbi_set_window_address(dbidev, 0, width - 1, 0, height - 1);
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 5170f72b0830..f91daefa9d2b 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -43,13 +43,13 @@ struct decon_data {
 	unsigned int wincon_burstlen_shift;
 };
 
-static struct decon_data exynos7_decon_data = {
+static const struct decon_data exynos7_decon_data = {
 	.vidw_buf_start_base = 0x80,
 	.shadowcon_win_protect_shift = 10,
 	.wincon_burstlen_shift = 11,
 };
 
-static struct decon_data exynos7870_decon_data = {
+static const struct decon_data exynos7870_decon_data = {
 	.vidw_buf_start_base = 0x880,
 	.shadowcon_win_protect_shift = 8,
 	.wincon_burstlen_shift = 10,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index f313ae7bc3a3..6cc7bf77bcac 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -355,8 +355,7 @@ static void exynos_drm_platform_shutdown(struct platform_device *pdev)
 {
 	struct drm_device *drm = platform_get_drvdata(pdev);
 
-	if (drm)
-		drm_atomic_helper_shutdown(drm);
+	drm_atomic_helper_shutdown(drm);
 }
 
 static struct platform_driver exynos_drm_platform_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index b150cfd92f6e..09e33a26caaf 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -908,7 +908,7 @@ static void fimc_dst_set_buf_seq(struct fimc_context *ctx, u32 buf_id,
 	u32 buf_num;
 	u32 cfg;
 
-	DRM_DEV_DEBUG_KMS(ctx->dev, "buf_id[%d]enqueu[%d]\n", buf_id, enqueue);
+	DRM_DEV_DEBUG_KMS(ctx->dev, "buf_id[%d]enqueue[%d]\n", buf_id, enqueue);
 
 	spin_lock_irqsave(&ctx->lock, flags);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 1ad87584b1c2..c394cc702d7d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -731,7 +731,7 @@ static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win,
 	/*
 	 * Setting dma-burst to 16Word causes permanent tearing for very small
 	 * buffers, e.g. cursor buffer. Burst Mode switching which based on
-	 * plane size is not recommended as plane size varies alot towards the
+	 * plane size is not recommended as plane size varies a lot towards the
 	 * end of the screen and rapid movement causes unstable DMA, but it is
 	 * still better to change dma-burst than displaying garbage.
 	 */
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 08cf79a62025..e644e2382d77 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -312,9 +312,6 @@ static int vidi_get_modes(struct drm_connector *connector)
 	else
 		drm_edid = drm_edid_alloc(fake_edid_info, sizeof(fake_edid_info));
 
-	if (!drm_edid)
-		return 0;
-
 	drm_edid_connector_update(connector, drm_edid);
 
 	count = drm_edid_connector_add_modes(connector);
diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index 048be2872247..98b898a1de8f 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -244,6 +244,7 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv,
 			qi->deinterleave = 4;
 			break;
 		case INTEL_DRAM_GDDR:
+		case INTEL_DRAM_GDDR_ECC:
 			qi->channel_width = 32;
 			break;
 		default:
@@ -398,6 +399,12 @@ static const struct intel_sa_info xe2_hpd_sa_info = {
 	/* Other values not used by simplified algorithm */
 };
 
+static const struct intel_sa_info xe2_hpd_ecc_sa_info = {
+	.derating = 45,
+	.deprogbwlimit = 53,
+	/* Other values not used by simplified algorithm */
+};
+
 static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel_sa_info *sa)
 {
 	struct intel_qgv_info qi = {};
@@ -740,10 +747,15 @@ static unsigned int icl_qgv_bw(struct drm_i915_private *i915,
 
 void intel_bw_init_hw(struct drm_i915_private *dev_priv)
 {
+	const struct dram_info *dram_info = &dev_priv->dram_info;
+
 	if (!HAS_DISPLAY(dev_priv))
 		return;
 
-	if (DISPLAY_VERx100(dev_priv) >= 1401 && IS_DGFX(dev_priv))
+	if (DISPLAY_VERx100(dev_priv) >= 1401 && IS_DGFX(dev_priv) &&
+		 dram_info->type == INTEL_DRAM_GDDR_ECC)
+		xe2_hpd_get_bw_info(dev_priv, &xe2_hpd_ecc_sa_info);
+	else if (DISPLAY_VERx100(dev_priv) >= 1401 && IS_DGFX(dev_priv))
 		xe2_hpd_get_bw_info(dev_priv, &xe2_hpd_sa_info);
 	else if (DISPLAY_VER(dev_priv) >= 14)
 		tgl_get_bw_info(dev_priv, &mtl_sa_info);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 3afb85fe8536..3b509c70fb58 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -968,7 +968,9 @@ static bool vrr_params_changed(const struct intel_crtc_state *old_crtc_state,
 		old_crtc_state->vrr.vmin != new_crtc_state->vrr.vmin ||
 		old_crtc_state->vrr.vmax != new_crtc_state->vrr.vmax ||
 		old_crtc_state->vrr.guardband != new_crtc_state->vrr.guardband ||
-		old_crtc_state->vrr.pipeline_full != new_crtc_state->vrr.pipeline_full;
+		old_crtc_state->vrr.pipeline_full != new_crtc_state->vrr.pipeline_full ||
+		old_crtc_state->vrr.vsync_start != new_crtc_state->vrr.vsync_start ||
+		old_crtc_state->vrr.vsync_end != new_crtc_state->vrr.vsync_end;
 }
 
 static bool cmrr_params_changed(const struct intel_crtc_state *old_crtc_state,
diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h
index 717286981687..7a3bb77c7af7 100644
--- a/drivers/gpu/drm/i915/display/intel_display_device.h
+++ b/drivers/gpu/drm/i915/display/intel_display_device.h
@@ -161,6 +161,7 @@ struct intel_display_platforms {
 #define HAS_DPT(__display)		(DISPLAY_VER(__display) >= 13)
 #define HAS_DSB(__display)		(DISPLAY_INFO(__display)->has_dsb)
 #define HAS_DSC(__display)		(DISPLAY_RUNTIME_INFO(__display)->has_dsc)
+#define HAS_DSC_3ENGINES(__display)	(DISPLAY_VERx100(__display) == 1401 && HAS_DSC(__display))
 #define HAS_DSC_MST(__display)		(DISPLAY_VER(__display) >= 12 && HAS_DSC(__display))
 #define HAS_FBC(__display)		(DISPLAY_RUNTIME_INFO(__display)->fbc_mask != 0)
 #define HAS_FBC_DIRTY_RECT(__display)	(DISPLAY_VER(__display) >= 30)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index a236b5fc7a3d..392c3653d0d7 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -172,10 +172,28 @@ int intel_dp_link_symbol_clock(int rate)
 
 static int max_dprx_rate(struct intel_dp *intel_dp)
 {
+	struct intel_display *display = to_intel_display(intel_dp);
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	int max_rate;
+
 	if (intel_dp_tunnel_bw_alloc_is_enabled(intel_dp))
-		return drm_dp_tunnel_max_dprx_rate(intel_dp->tunnel);
+		max_rate = drm_dp_tunnel_max_dprx_rate(intel_dp->tunnel);
+	else
+		max_rate = drm_dp_bw_code_to_link_rate(intel_dp->dpcd[DP_MAX_LINK_RATE]);
 
-	return drm_dp_bw_code_to_link_rate(intel_dp->dpcd[DP_MAX_LINK_RATE]);
+	/*
+	 * Some broken eDP sinks illegally declare support for
+	 * HBR3 without TPS4, and are unable to produce a stable
+	 * output. Reject HBR3 when TPS4 is not available.
+	 */
+	if (max_rate >= 810000 && !drm_dp_tps4_supported(intel_dp->dpcd)) {
+		drm_dbg_kms(display->drm,
+			    "[ENCODER:%d:%s] Rejecting HBR3 due to missing TPS4 support\n",
+			    encoder->base.base.id, encoder->base.name);
+		max_rate = 540000;
+	}
+
+	return max_rate;
 }
 
 static int max_dprx_lane_count(struct intel_dp *intel_dp)
@@ -1032,10 +1050,11 @@ u8 intel_dp_dsc_get_slice_count(const struct intel_connector *connector,
 		u8 test_slice_count = valid_dsc_slicecount[i] * num_joined_pipes;
 
 		/*
-		 * 3 DSC Slices per pipe need 3 DSC engines,
-		 * which is supported only with Ultrajoiner.
+		 * 3 DSC Slices per pipe need 3 DSC engines, which is supported only
+		 * with Ultrajoiner only for some platforms.
 		 */
-		if (valid_dsc_slicecount[i] == 3 && num_joined_pipes != 4)
+		if (valid_dsc_slicecount[i] == 3 &&
+		    (!HAS_DSC_3ENGINES(display) || num_joined_pipes != 4))
 			continue;
 
 		if (test_slice_count >
@@ -4170,6 +4189,9 @@ static void intel_edp_mso_init(struct intel_dp *intel_dp)
 static void
 intel_edp_set_sink_rates(struct intel_dp *intel_dp)
 {
+	struct intel_display *display = to_intel_display(intel_dp);
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+
 	intel_dp->num_sink_rates = 0;
 
 	if (intel_dp->edp_dpcd[0] >= DP_EDP_14) {
@@ -4180,10 +4202,7 @@ intel_edp_set_sink_rates(struct intel_dp *intel_dp)
 				 sink_rates, sizeof(sink_rates));
 
 		for (i = 0; i < ARRAY_SIZE(sink_rates); i++) {
-			int val = le16_to_cpu(sink_rates[i]);
-
-			if (val == 0)
-				break;
+			int rate;
 
 			/* Value read multiplied by 200kHz gives the per-lane
 			 * link rate in kHz. The source rates are, however,
@@ -4191,7 +4210,24 @@ intel_edp_set_sink_rates(struct intel_dp *intel_dp)
 			 * back to symbols is
 			 * (val * 200kHz)*(8/10 ch. encoding)*(1/8 bit to Byte)
 			 */
-			intel_dp->sink_rates[i] = (val * 200) / 10;
+			rate = le16_to_cpu(sink_rates[i]) * 200 / 10;
+
+			if (rate == 0)
+				break;
+
+			/*
+			 * Some broken eDP sinks illegally declare support for
+			 * HBR3 without TPS4, and are unable to produce a stable
+			 * output. Reject HBR3 when TPS4 is not available.
+			 */
+			if (rate >= 810000 && !drm_dp_tps4_supported(intel_dp->dpcd)) {
+				drm_dbg_kms(display->drm,
+					    "[ENCODER:%d:%s] Rejecting HBR3 due to missing TPS4 support\n",
+					    encoder->base.base.id, encoder->base.name);
+				break;
+			}
+
+			intel_dp->sink_rates[i] = rate;
 		}
 		intel_dp->num_sink_rates = i;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 02f95108c637..6dc2d31ccb5a 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -242,7 +242,7 @@ int intel_dp_mtp_tu_compute_config(struct intel_dp *intel_dp,
 		to_intel_connector(conn_state->connector);
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->hw.adjusted_mode;
-	bool is_mst = intel_dp->is_mst;
+	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
 	int bpp_x16, slots = -EINVAL;
 	int dsc_slice_count = 0;
 	int max_dpt_bpp_x16;
diff --git a/drivers/gpu/drm/i915/display/intel_vblank.c b/drivers/gpu/drm/i915/display/intel_vblank.c
index 4efd4f7d497a..7b240ce681a0 100644
--- a/drivers/gpu/drm/i915/display/intel_vblank.c
+++ b/drivers/gpu/drm/i915/display/intel_vblank.c
@@ -222,7 +222,9 @@ int intel_crtc_scanline_offset(const struct intel_crtc_state *crtc_state)
 	 * However if queried just before the start of vblank we'll get an
 	 * answer that's slightly in the future.
 	 */
-	if (DISPLAY_VER(display) == 2)
+	if (DISPLAY_VER(display) >= 20 || display->platform.battlemage)
+		return 1;
+	else if (DISPLAY_VER(display) == 2)
 		return -1;
 	else if (HAS_DDI(display) && intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
 		return 2;
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index 9378d5901c49..9ca42589da4d 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -117,21 +117,10 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 			GEN6_RC_CTL_RC6_ENABLE |
 			GEN6_RC_CTL_EI_MODE(1);
 
-	/*
-	 * BSpec 52698 - Render powergating must be off.
-	 * FIXME BSpec is outdated, disabling powergating for MTL is just
-	 * temporary wa and should be removed after fixing real cause
-	 * of forcewake timeouts.
-	 */
-	if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)))
-		pg_enable =
-			GEN9_MEDIA_PG_ENABLE |
-			GEN11_MEDIA_SAMPLER_PG_ENABLE;
-	else
-		pg_enable =
-			GEN9_RENDER_PG_ENABLE |
-			GEN9_MEDIA_PG_ENABLE |
-			GEN11_MEDIA_SAMPLER_PG_ENABLE;
+	pg_enable =
+		GEN9_RENDER_PG_ENABLE |
+		GEN9_MEDIA_PG_ENABLE |
+		GEN11_MEDIA_SAMPLER_PG_ENABLE;
 
 	if (GRAPHICS_VER(gt->i915) >= 12 && !IS_DG1(gt->i915)) {
 		for (i = 0; i < I915_MAX_VCS; i++)
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 64e9317f58fb..71ee01d9ef64 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -1001,6 +1001,10 @@ void intel_rps_dec_waiters(struct intel_rps *rps)
 	if (rps_uses_slpc(rps)) {
 		slpc = rps_to_slpc(rps);
 
+		/* Don't decrement num_waiters for req where increment was skipped */
+		if (slpc->power_profile == SLPC_POWER_PROFILES_POWER_SAVING)
+			return;
+
 		intel_guc_slpc_dec_waiters(slpc);
 	} else {
 		atomic_dec(&rps->num_waiters);
@@ -1029,11 +1033,15 @@ void intel_rps_boost(struct i915_request *rq)
 			if (slpc->power_profile == SLPC_POWER_PROFILES_POWER_SAVING)
 				return;
 
-			if (slpc->min_freq_softlimit >= slpc->boost_freq)
-				return;
-
 			/* Return if old value is non zero */
 			if (!atomic_fetch_inc(&slpc->num_waiters)) {
+				/*
+				 * Skip queuing boost work if frequency is already boosted,
+				 * but still increment num_waiters.
+				 */
+				if (slpc->min_freq_softlimit >= slpc->boost_freq)
+					return;
+
 				GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n",
 					 rq->fence.context, rq->fence.seqno);
 				queue_work(rps_to_gt(rps)->i915->unordered_wq,
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index d791f9baa11d..456d3372eef8 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -317,6 +317,11 @@ void intel_huc_init_early(struct intel_huc *huc)
 	}
 }
 
+void intel_huc_fini_late(struct intel_huc *huc)
+{
+	delayed_huc_load_fini(huc);
+}
+
 #define HUC_LOAD_MODE_STRING(x) (x ? "GSC" : "legacy")
 static int check_huc_loading_mode(struct intel_huc *huc)
 {
@@ -414,12 +419,6 @@ out:
 
 void intel_huc_fini(struct intel_huc *huc)
 {
-	/*
-	 * the fence is initialized in init_early, so we need to clean it up
-	 * even if HuC loading is off.
-	 */
-	delayed_huc_load_fini(huc);
-
 	if (huc->heci_pkt)
 		i915_vma_unpin_and_release(&huc->heci_pkt, 0);
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
index d5e441b9e08d..921ad4b1687f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
@@ -55,6 +55,7 @@ struct intel_huc {
 
 int intel_huc_sanitize(struct intel_huc *huc);
 void intel_huc_init_early(struct intel_huc *huc);
+void intel_huc_fini_late(struct intel_huc *huc);
 int intel_huc_init(struct intel_huc *huc);
 void intel_huc_fini(struct intel_huc *huc);
 int intel_huc_auth(struct intel_huc *huc, enum intel_huc_authentication_type type);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 90ba1b0b4c9d..4a3493e8d433 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -136,6 +136,7 @@ void intel_uc_init_late(struct intel_uc *uc)
 
 void intel_uc_driver_late_release(struct intel_uc *uc)
 {
+	intel_huc_fini_late(&uc->huc);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index 509f9ccae3a9..dbad4d853d3a 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -222,7 +222,6 @@ int intel_vgpu_init_opregion(struct intel_vgpu *vgpu)
 	u8 *buf;
 	struct opregion_header *header;
 	struct vbt v;
-	const char opregion_signature[16] = OPREGION_SIGNATURE;
 
 	gvt_dbg_core("init vgpu%d opregion\n", vgpu->id);
 	vgpu_opregion(vgpu)->va = (void *)__get_free_pages(GFP_KERNEL |
@@ -236,8 +235,10 @@ int intel_vgpu_init_opregion(struct intel_vgpu *vgpu)
 	/* emulated opregion with VBT mailbox only */
 	buf = (u8 *)vgpu_opregion(vgpu)->va;
 	header = (struct opregion_header *)buf;
-	memcpy(header->signature, opregion_signature,
-	       sizeof(opregion_signature));
+
+	static_assert(sizeof(header->signature) == sizeof(OPREGION_SIGNATURE) - 1);
+	memcpy(header->signature, OPREGION_SIGNATURE, sizeof(header->signature));
+
 	header->size = 0x8;
 	header->opregion_ver = 0x02000000;
 	header->mboxes = MBOX_VBT;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ffc346379cc2..54538b6f85df 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -305,6 +305,7 @@ struct drm_i915_private {
 			INTEL_DRAM_DDR5,
 			INTEL_DRAM_LPDDR5,
 			INTEL_DRAM_GDDR,
+			INTEL_DRAM_GDDR_ECC,
 		} type;
 		u8 num_qgv_points;
 		u8 num_psf_gv_points;
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
index 9aae779c4da3..4969d3de2bac 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
@@ -23,6 +23,7 @@ int intel_pxp_gsccs_init(struct intel_pxp *pxp);
 
 int intel_pxp_gsccs_create_session(struct intel_pxp *pxp, int arb_session_id);
 void intel_pxp_gsccs_end_arb_fw_session(struct intel_pxp *pxp, u32 arb_session_id);
+bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp);
 
 #else
 static inline void intel_pxp_gsccs_fini(struct intel_pxp *pxp)
@@ -34,8 +35,11 @@ static inline int intel_pxp_gsccs_init(struct intel_pxp *pxp)
 	return 0;
 }
 
-#endif
+static inline bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp)
+{
+	return false;
+}
 
-bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp);
+#endif
 
 #endif /*__INTEL_PXP_GSCCS_H__ */
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index fee76c1d2f45..889281819c5b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -23,7 +23,9 @@
 
 #include <linux/random.h>
 
+#include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
+#include "gt/intel_gt_regs.h"
 #include "gt/uc/intel_gsc_fw.h"
 
 #include "i915_driver.h"
@@ -253,11 +255,27 @@ int i915_mock_selftests(void)
 int i915_live_selftests(struct pci_dev *pdev)
 {
 	struct drm_i915_private *i915 = pdev_to_i915(pdev);
+	struct intel_uncore *uncore = &i915->uncore;
 	int err;
+	u32 pg_enable;
+	intel_wakeref_t wakeref;
 
 	if (!i915_selftest.live)
 		return 0;
 
+	/*
+	 * FIXME Disable render powergating, this is temporary wa and should be removed
+	 * after fixing real cause of forcewake timeouts.
+	 */
+	with_intel_runtime_pm(uncore->rpm, wakeref) {
+		if (IS_GFX_GT_IP_RANGE(to_gt(i915), IP_VER(12, 00), IP_VER(12, 74))) {
+			pg_enable = intel_uncore_read(uncore, GEN9_PG_ENABLE);
+			if (pg_enable & GEN9_RENDER_PG_ENABLE)
+				intel_uncore_write_fw(uncore, GEN9_PG_ENABLE,
+						      pg_enable & ~GEN9_RENDER_PG_ENABLE);
+		}
+	}
+
 	__wait_gsc_proxy_completed(i915);
 	__wait_gsc_huc_load_completed(i915);
 
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index 9e310f4099f4..f60eedb0e92c 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -687,6 +687,10 @@ static int xelpdp_get_dram_info(struct drm_i915_private *i915)
 		drm_WARN_ON(&i915->drm, !IS_DGFX(i915));
 		dram_info->type = INTEL_DRAM_GDDR;
 		break;
+	case 9:
+		drm_WARN_ON(&i915->drm, !IS_DGFX(i915));
+		dram_info->type = INTEL_DRAM_GDDR_ECC;
+		break;
 	default:
 		MISSING_CASE(val);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/imagination/pvr_fw.c b/drivers/gpu/drm/imagination/pvr_fw.c
index 3debc9870a82..d09c4c684116 100644
--- a/drivers/gpu/drm/imagination/pvr_fw.c
+++ b/drivers/gpu/drm/imagination/pvr_fw.c
@@ -732,7 +732,7 @@ pvr_fw_process(struct pvr_device *pvr_dev)
 					       fw_mem->core_data, fw_mem->core_code_alloc_size);
 
 	if (err)
-		goto err_free_fw_core_data_obj;
+		goto err_free_kdata;
 
 	memcpy(fw_code_ptr, fw_mem->code, fw_mem->code_alloc_size);
 	memcpy(fw_data_ptr, fw_mem->data, fw_mem->data_alloc_size);
@@ -742,10 +742,14 @@ pvr_fw_process(struct pvr_device *pvr_dev)
 		memcpy(fw_core_data_ptr, fw_mem->core_data, fw_mem->core_data_alloc_size);
 
 	/* We're finished with the firmware section memory on the CPU, unmap. */
-	if (fw_core_data_ptr)
+	if (fw_core_data_ptr) {
 		pvr_fw_object_vunmap(fw_mem->core_data_obj);
-	if (fw_core_code_ptr)
+		fw_core_data_ptr = NULL;
+	}
+	if (fw_core_code_ptr) {
 		pvr_fw_object_vunmap(fw_mem->core_code_obj);
+		fw_core_code_ptr = NULL;
+	}
 	pvr_fw_object_vunmap(fw_mem->data_obj);
 	fw_data_ptr = NULL;
 	pvr_fw_object_vunmap(fw_mem->code_obj);
@@ -753,7 +757,7 @@ pvr_fw_process(struct pvr_device *pvr_dev)
 
 	err = pvr_fw_create_fwif_connection_ctl(pvr_dev);
 	if (err)
-		goto err_free_fw_core_data_obj;
+		goto err_free_kdata;
 
 	return 0;
 
@@ -763,13 +767,16 @@ err_free_kdata:
 	kfree(fw_mem->data);
 	kfree(fw_mem->code);
 
-err_free_fw_core_data_obj:
 	if (fw_core_data_ptr)
-		pvr_fw_object_unmap_and_destroy(fw_mem->core_data_obj);
+		pvr_fw_object_vunmap(fw_mem->core_data_obj);
+	if (fw_mem->core_data_obj)
+		pvr_fw_object_destroy(fw_mem->core_data_obj);
 
 err_free_fw_core_code_obj:
 	if (fw_core_code_ptr)
-		pvr_fw_object_unmap_and_destroy(fw_mem->core_code_obj);
+		pvr_fw_object_vunmap(fw_mem->core_code_obj);
+	if (fw_mem->core_code_obj)
+		pvr_fw_object_destroy(fw_mem->core_code_obj);
 
 err_free_fw_data_obj:
 	if (fw_data_ptr)
@@ -836,6 +843,12 @@ pvr_fw_cleanup(struct pvr_device *pvr_dev)
 	struct pvr_fw_mem *fw_mem = &pvr_dev->fw_dev.mem;
 
 	pvr_fw_fini_fwif_connection_ctl(pvr_dev);
+
+	kfree(fw_mem->core_data);
+	kfree(fw_mem->core_code);
+	kfree(fw_mem->data);
+	kfree(fw_mem->code);
+
 	if (fw_mem->core_code_obj)
 		pvr_fw_object_destroy(fw_mem->core_code_obj);
 	if (fw_mem->core_data_obj)
diff --git a/drivers/gpu/drm/imagination/pvr_job.c b/drivers/gpu/drm/imagination/pvr_job.c
index 1cdb3cfd058d..59b334d094fa 100644
--- a/drivers/gpu/drm/imagination/pvr_job.c
+++ b/drivers/gpu/drm/imagination/pvr_job.c
@@ -671,6 +671,13 @@ pvr_jobs_link_geom_frag(struct pvr_job_data *job_data, u32 *job_count)
 		geom_job->paired_job = frag_job;
 		frag_job->paired_job = geom_job;
 
+		/* The geometry job pvr_job structure is used when the fragment
+		 * job is being prepared by the GPU scheduler. Have the fragment
+		 * job hold a reference on the geometry job to prevent it being
+		 * freed until the fragment job has finished with it.
+		 */
+		pvr_job_get(geom_job);
+
 		/* Skip the fragment job we just paired to the geometry job. */
 		i++;
 	}
diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c
index eba69309bb6c..5e9bc0992824 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.c
+++ b/drivers/gpu/drm/imagination/pvr_queue.c
@@ -866,6 +866,10 @@ static void pvr_queue_free_job(struct drm_sched_job *sched_job)
 	struct pvr_job *job = container_of(sched_job, struct pvr_job, base);
 
 	drm_sched_job_cleanup(sched_job);
+
+	if (job->type == DRM_PVR_JOB_TYPE_FRAGMENT && job->paired_job)
+		pvr_job_put(job->paired_job);
+
 	job->paired_job = NULL;
 	pvr_job_put(job);
 }
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 81d2ee37e773..49ff9f1f16d3 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -169,7 +169,7 @@ static const struct meson_drm_soc_attr meson_drm_soc_attrs[] = {
 	/* S805X/S805Y HDMI PLL won't lock for HDMI PHY freq > 1,65GHz */
 	{
 		.limits = {
-			.max_hdmi_phy_freq = 1650000,
+			.max_hdmi_phy_freq = 1650000000,
 		},
 		.attrs = (const struct soc_device_attribute []) {
 			{ .soc_id = "GXL (S805*)", },
diff --git a/drivers/gpu/drm/meson/meson_drv.h b/drivers/gpu/drm/meson/meson_drv.h
index 3f9345c14f31..be4b0e4df6e1 100644
--- a/drivers/gpu/drm/meson/meson_drv.h
+++ b/drivers/gpu/drm/meson/meson_drv.h
@@ -37,7 +37,7 @@ struct meson_drm_match_data {
 };
 
 struct meson_drm_soc_limits {
-	unsigned int max_hdmi_phy_freq;
+	unsigned long long max_hdmi_phy_freq;
 };
 
 struct meson_drm {
diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
index 6d1c9262a2cf..c08fa93e50a3 100644
--- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
@@ -70,12 +70,12 @@ static void meson_encoder_hdmi_set_vclk(struct meson_encoder_hdmi *encoder_hdmi,
 {
 	struct meson_drm *priv = encoder_hdmi->priv;
 	int vic = drm_match_cea_mode(mode);
-	unsigned int phy_freq;
-	unsigned int vclk_freq;
-	unsigned int venc_freq;
-	unsigned int hdmi_freq;
+	unsigned long long phy_freq;
+	unsigned long long vclk_freq;
+	unsigned long long venc_freq;
+	unsigned long long hdmi_freq;
 
-	vclk_freq = mode->clock;
+	vclk_freq = mode->clock * 1000ULL;
 
 	/* For 420, pixel clock is half unlike venc clock */
 	if (encoder_hdmi->output_bus_fmt == MEDIA_BUS_FMT_UYYVYY8_0_5X24)
@@ -107,7 +107,8 @@ static void meson_encoder_hdmi_set_vclk(struct meson_encoder_hdmi *encoder_hdmi,
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		venc_freq /= 2;
 
-	dev_dbg(priv->dev, "vclk:%d phy=%d venc=%d hdmi=%d enci=%d\n",
+	dev_dbg(priv->dev,
+		"vclk:%lluHz phy=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n",
 		phy_freq, vclk_freq, venc_freq, hdmi_freq,
 		priv->venc.hdmi_use_enci);
 
@@ -122,10 +123,11 @@ static enum drm_mode_status meson_encoder_hdmi_mode_valid(struct drm_bridge *bri
 	struct meson_encoder_hdmi *encoder_hdmi = bridge_to_meson_encoder_hdmi(bridge);
 	struct meson_drm *priv = encoder_hdmi->priv;
 	bool is_hdmi2_sink = display_info->hdmi.scdc.supported;
-	unsigned int phy_freq;
-	unsigned int vclk_freq;
-	unsigned int venc_freq;
-	unsigned int hdmi_freq;
+	unsigned long long clock = mode->clock * 1000ULL;
+	unsigned long long phy_freq;
+	unsigned long long vclk_freq;
+	unsigned long long venc_freq;
+	unsigned long long hdmi_freq;
 	int vic = drm_match_cea_mode(mode);
 	enum drm_mode_status status;
 
@@ -144,12 +146,12 @@ static enum drm_mode_status meson_encoder_hdmi_mode_valid(struct drm_bridge *bri
 		if (status != MODE_OK)
 			return status;
 
-		return meson_vclk_dmt_supported_freq(priv, mode->clock);
+		return meson_vclk_dmt_supported_freq(priv, clock);
 	/* Check against supported VIC modes */
 	} else if (!meson_venc_hdmi_supported_vic(vic))
 		return MODE_BAD;
 
-	vclk_freq = mode->clock;
+	vclk_freq = clock;
 
 	/* For 420, pixel clock is half unlike venc clock */
 	if (drm_mode_is_420_only(display_info, mode) ||
@@ -179,7 +181,8 @@ static enum drm_mode_status meson_encoder_hdmi_mode_valid(struct drm_bridge *bri
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		venc_freq /= 2;
 
-	dev_dbg(priv->dev, "%s: vclk:%d phy=%d venc=%d hdmi=%d\n",
+	dev_dbg(priv->dev,
+		"%s: vclk:%lluHz phy=%lluHz venc=%lluHz hdmi=%lluHz\n",
 		__func__, phy_freq, vclk_freq, venc_freq, hdmi_freq);
 
 	return meson_vclk_vic_supported_freq(priv, phy_freq, vclk_freq);
diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c
index 2a942dc6a6dc..3325580d885d 100644
--- a/drivers/gpu/drm/meson/meson_vclk.c
+++ b/drivers/gpu/drm/meson/meson_vclk.c
@@ -110,7 +110,10 @@
 #define HDMI_PLL_LOCK		BIT(31)
 #define HDMI_PLL_LOCK_G12A	(3 << 30)
 
-#define FREQ_1000_1001(_freq)	DIV_ROUND_CLOSEST(_freq * 1000, 1001)
+#define PIXEL_FREQ_1000_1001(_freq)	\
+	DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL)
+#define PHY_FREQ_1000_1001(_freq)	\
+	(PIXEL_FREQ_1000_1001(DIV_ROUND_DOWN_ULL(_freq, 10ULL)) * 10)
 
 /* VID PLL Dividers */
 enum {
@@ -360,11 +363,11 @@ enum {
 };
 
 struct meson_vclk_params {
-	unsigned int pll_freq;
-	unsigned int phy_freq;
-	unsigned int vclk_freq;
-	unsigned int venc_freq;
-	unsigned int pixel_freq;
+	unsigned long long pll_freq;
+	unsigned long long phy_freq;
+	unsigned long long vclk_freq;
+	unsigned long long venc_freq;
+	unsigned long long pixel_freq;
 	unsigned int pll_od1;
 	unsigned int pll_od2;
 	unsigned int pll_od3;
@@ -372,11 +375,11 @@ struct meson_vclk_params {
 	unsigned int vclk_div;
 } params[] = {
 	[MESON_VCLK_HDMI_ENCI_54000] = {
-		.pll_freq = 4320000,
-		.phy_freq = 270000,
-		.vclk_freq = 54000,
-		.venc_freq = 54000,
-		.pixel_freq = 54000,
+		.pll_freq = 4320000000,
+		.phy_freq = 270000000,
+		.vclk_freq = 54000000,
+		.venc_freq = 54000000,
+		.pixel_freq = 54000000,
 		.pll_od1 = 4,
 		.pll_od2 = 4,
 		.pll_od3 = 1,
@@ -384,11 +387,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_DDR_54000] = {
-		.pll_freq = 4320000,
-		.phy_freq = 270000,
-		.vclk_freq = 54000,
-		.venc_freq = 54000,
-		.pixel_freq = 27000,
+		.pll_freq = 4320000000,
+		.phy_freq = 270000000,
+		.vclk_freq = 54000000,
+		.venc_freq = 54000000,
+		.pixel_freq = 27000000,
 		.pll_od1 = 4,
 		.pll_od2 = 4,
 		.pll_od3 = 1,
@@ -396,11 +399,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_DDR_148500] = {
-		.pll_freq = 2970000,
-		.phy_freq = 742500,
-		.vclk_freq = 148500,
-		.venc_freq = 148500,
-		.pixel_freq = 74250,
+		.pll_freq = 2970000000,
+		.phy_freq = 742500000,
+		.vclk_freq = 148500000,
+		.venc_freq = 148500000,
+		.pixel_freq = 74250000,
 		.pll_od1 = 4,
 		.pll_od2 = 1,
 		.pll_od3 = 1,
@@ -408,11 +411,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_74250] = {
-		.pll_freq = 2970000,
-		.phy_freq = 742500,
-		.vclk_freq = 74250,
-		.venc_freq = 74250,
-		.pixel_freq = 74250,
+		.pll_freq = 2970000000,
+		.phy_freq = 742500000,
+		.vclk_freq = 74250000,
+		.venc_freq = 74250000,
+		.pixel_freq = 74250000,
 		.pll_od1 = 2,
 		.pll_od2 = 2,
 		.pll_od3 = 2,
@@ -420,11 +423,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_148500] = {
-		.pll_freq = 2970000,
-		.phy_freq = 1485000,
-		.vclk_freq = 148500,
-		.venc_freq = 148500,
-		.pixel_freq = 148500,
+		.pll_freq = 2970000000,
+		.phy_freq = 1485000000,
+		.vclk_freq = 148500000,
+		.venc_freq = 148500000,
+		.pixel_freq = 148500000,
 		.pll_od1 = 1,
 		.pll_od2 = 2,
 		.pll_od3 = 2,
@@ -432,11 +435,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_297000] = {
-		.pll_freq = 5940000,
-		.phy_freq = 2970000,
-		.venc_freq = 297000,
-		.vclk_freq = 297000,
-		.pixel_freq = 297000,
+		.pll_freq = 5940000000,
+		.phy_freq = 2970000000,
+		.venc_freq = 297000000,
+		.vclk_freq = 297000000,
+		.pixel_freq = 297000000,
 		.pll_od1 = 2,
 		.pll_od2 = 1,
 		.pll_od3 = 1,
@@ -444,11 +447,11 @@ struct meson_vclk_params {
 		.vclk_div = 2,
 	},
 	[MESON_VCLK_HDMI_594000] = {
-		.pll_freq = 5940000,
-		.phy_freq = 5940000,
-		.venc_freq = 594000,
-		.vclk_freq = 594000,
-		.pixel_freq = 594000,
+		.pll_freq = 5940000000,
+		.phy_freq = 5940000000,
+		.venc_freq = 594000000,
+		.vclk_freq = 594000000,
+		.pixel_freq = 594000000,
 		.pll_od1 = 1,
 		.pll_od2 = 1,
 		.pll_od3 = 2,
@@ -456,11 +459,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_594000_YUV420] = {
-		.pll_freq = 5940000,
-		.phy_freq = 2970000,
-		.venc_freq = 594000,
-		.vclk_freq = 594000,
-		.pixel_freq = 297000,
+		.pll_freq = 5940000000,
+		.phy_freq = 2970000000,
+		.venc_freq = 594000000,
+		.vclk_freq = 594000000,
+		.pixel_freq = 297000000,
 		.pll_od1 = 2,
 		.pll_od2 = 1,
 		.pll_od3 = 1,
@@ -617,16 +620,16 @@ static void meson_hdmi_pll_set_params(struct meson_drm *priv, unsigned int m,
 				3 << 20, pll_od_to_reg(od3) << 20);
 }
 
-#define XTAL_FREQ 24000
+#define XTAL_FREQ (24 * 1000 * 1000)
 
 static unsigned int meson_hdmi_pll_get_m(struct meson_drm *priv,
-					 unsigned int pll_freq)
+					 unsigned long long pll_freq)
 {
 	/* The GXBB PLL has a /2 pre-multiplier */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB))
-		pll_freq /= 2;
+		pll_freq = DIV_ROUND_DOWN_ULL(pll_freq, 2);
 
-	return pll_freq / XTAL_FREQ;
+	return DIV_ROUND_DOWN_ULL(pll_freq, XTAL_FREQ);
 }
 
 #define HDMI_FRAC_MAX_GXBB	4096
@@ -635,12 +638,13 @@ static unsigned int meson_hdmi_pll_get_m(struct meson_drm *priv,
 
 static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
 					    unsigned int m,
-					    unsigned int pll_freq)
+					    unsigned long long pll_freq)
 {
-	unsigned int parent_freq = XTAL_FREQ;
+	unsigned long long parent_freq = XTAL_FREQ;
 	unsigned int frac_max = HDMI_FRAC_MAX_GXL;
 	unsigned int frac_m;
 	unsigned int frac;
+	u32 remainder;
 
 	/* The GXBB PLL has a /2 pre-multiplier and a larger FRAC width */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
@@ -652,11 +656,11 @@ static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
 		frac_max = HDMI_FRAC_MAX_G12A;
 
 	/* We can have a perfect match !*/
-	if (pll_freq / m == parent_freq &&
-	    pll_freq % m == 0)
+	if (div_u64_rem(pll_freq, m, &remainder) == parent_freq &&
+	    remainder == 0)
 		return 0;
 
-	frac = div_u64((u64)pll_freq * (u64)frac_max, parent_freq);
+	frac = mul_u64_u64_div_u64(pll_freq, frac_max, parent_freq);
 	frac_m = m * frac_max;
 	if (frac_m > frac)
 		return frac_max;
@@ -666,7 +670,7 @@ static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
 }
 
 static bool meson_hdmi_pll_validate_params(struct meson_drm *priv,
-					   unsigned int m,
+					   unsigned long long m,
 					   unsigned int frac)
 {
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
@@ -694,7 +698,7 @@ static bool meson_hdmi_pll_validate_params(struct meson_drm *priv,
 }
 
 static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
-				       unsigned int freq,
+				       unsigned long long freq,
 				       unsigned int *m,
 				       unsigned int *frac,
 				       unsigned int *od)
@@ -706,7 +710,7 @@ static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
 			continue;
 		*frac = meson_hdmi_pll_get_frac(priv, *m, freq * *od);
 
-		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d\n",
+		DRM_DEBUG_DRIVER("PLL params for %lluHz: m=%x frac=%x od=%d\n",
 				 freq, *m, *frac, *od);
 
 		if (meson_hdmi_pll_validate_params(priv, *m, *frac))
@@ -718,7 +722,7 @@ static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
 
 /* pll_freq is the frequency after the OD dividers */
 enum drm_mode_status
-meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq)
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned long long freq)
 {
 	unsigned int od, m, frac;
 
@@ -741,7 +745,7 @@ EXPORT_SYMBOL_GPL(meson_vclk_dmt_supported_freq);
 
 /* pll_freq is the frequency after the OD dividers */
 static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
-				       unsigned int pll_freq)
+				       unsigned long long pll_freq)
 {
 	unsigned int od, m, frac, od1, od2, od3;
 
@@ -756,7 +760,7 @@ static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
 			od1 = od / od2;
 		}
 
-		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d/%d/%d\n",
+		DRM_DEBUG_DRIVER("PLL params for %lluHz: m=%x frac=%x od=%d/%d/%d\n",
 				 pll_freq, m, frac, od1, od2, od3);
 
 		meson_hdmi_pll_set_params(priv, m, frac, od1, od2, od3);
@@ -764,17 +768,18 @@ static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
 		return;
 	}
 
-	DRM_ERROR("Fatal, unable to find parameters for PLL freq %d\n",
+	DRM_ERROR("Fatal, unable to find parameters for PLL freq %lluHz\n",
 		  pll_freq);
 }
 
 enum drm_mode_status
-meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
-			      unsigned int vclk_freq)
+meson_vclk_vic_supported_freq(struct meson_drm *priv,
+			      unsigned long long phy_freq,
+			      unsigned long long vclk_freq)
 {
 	int i;
 
-	DRM_DEBUG_DRIVER("phy_freq = %d vclk_freq = %d\n",
+	DRM_DEBUG_DRIVER("phy_freq = %lluHz vclk_freq = %lluHz\n",
 			 phy_freq, vclk_freq);
 
 	/* Check against soc revision/package limits */
@@ -785,19 +790,19 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
 	}
 
 	for (i = 0 ; params[i].pixel_freq ; ++i) {
-		DRM_DEBUG_DRIVER("i = %d pixel_freq = %d alt = %d\n",
+		DRM_DEBUG_DRIVER("i = %d pixel_freq = %lluHz alt = %lluHz\n",
 				 i, params[i].pixel_freq,
-				 FREQ_1000_1001(params[i].pixel_freq));
-		DRM_DEBUG_DRIVER("i = %d phy_freq = %d alt = %d\n",
+				 PIXEL_FREQ_1000_1001(params[i].pixel_freq));
+		DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n",
 				 i, params[i].phy_freq,
-				 FREQ_1000_1001(params[i].phy_freq/1000)*1000);
+				 PHY_FREQ_1000_1001(params[i].phy_freq));
 		/* Match strict frequency */
 		if (phy_freq == params[i].phy_freq &&
 		    vclk_freq == params[i].vclk_freq)
 			return MODE_OK;
 		/* Match 1000/1001 variant */
-		if (phy_freq == (FREQ_1000_1001(params[i].phy_freq/1000)*1000) &&
-		    vclk_freq == FREQ_1000_1001(params[i].vclk_freq))
+		if (phy_freq == PHY_FREQ_1000_1001(params[i].phy_freq) &&
+		    vclk_freq == PIXEL_FREQ_1000_1001(params[i].vclk_freq))
 			return MODE_OK;
 	}
 
@@ -805,8 +810,9 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
 }
 EXPORT_SYMBOL_GPL(meson_vclk_vic_supported_freq);
 
-static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
-			   unsigned int od1, unsigned int od2, unsigned int od3,
+static void meson_vclk_set(struct meson_drm *priv,
+			   unsigned long long pll_base_freq, unsigned int od1,
+			   unsigned int od2, unsigned int od3,
 			   unsigned int vid_pll_div, unsigned int vclk_div,
 			   unsigned int hdmi_tx_div, unsigned int venc_div,
 			   bool hdmi_use_enci, bool vic_alternate_clock)
@@ -826,15 +832,15 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
 		meson_hdmi_pll_generic_set(priv, pll_base_freq);
 	} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
 		switch (pll_base_freq) {
-		case 2970000:
+		case 2970000000:
 			m = 0x3d;
 			frac = vic_alternate_clock ? 0xd02 : 0xe00;
 			break;
-		case 4320000:
+		case 4320000000:
 			m = vic_alternate_clock ? 0x59 : 0x5a;
 			frac = vic_alternate_clock ? 0xe8f : 0;
 			break;
-		case 5940000:
+		case 5940000000:
 			m = 0x7b;
 			frac = vic_alternate_clock ? 0xa05 : 0xc00;
 			break;
@@ -844,15 +850,15 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
 	} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) ||
 		   meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL)) {
 		switch (pll_base_freq) {
-		case 2970000:
+		case 2970000000:
 			m = 0x7b;
 			frac = vic_alternate_clock ? 0x281 : 0x300;
 			break;
-		case 4320000:
+		case 4320000000:
 			m = vic_alternate_clock ? 0xb3 : 0xb4;
 			frac = vic_alternate_clock ? 0x347 : 0;
 			break;
-		case 5940000:
+		case 5940000000:
 			m = 0xf7;
 			frac = vic_alternate_clock ? 0x102 : 0x200;
 			break;
@@ -861,15 +867,15 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
 		meson_hdmi_pll_set_params(priv, m, frac, od1, od2, od3);
 	} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
 		switch (pll_base_freq) {
-		case 2970000:
+		case 2970000000:
 			m = 0x7b;
 			frac = vic_alternate_clock ? 0x140b4 : 0x18000;
 			break;
-		case 4320000:
+		case 4320000000:
 			m = vic_alternate_clock ? 0xb3 : 0xb4;
 			frac = vic_alternate_clock ? 0x1a3ee : 0;
 			break;
-		case 5940000:
+		case 5940000000:
 			m = 0xf7;
 			frac = vic_alternate_clock ? 0x8148 : 0x10000;
 			break;
@@ -1025,14 +1031,14 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
 }
 
 void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
-		      unsigned int phy_freq, unsigned int vclk_freq,
-		      unsigned int venc_freq, unsigned int dac_freq,
+		      unsigned long long phy_freq, unsigned long long vclk_freq,
+		      unsigned long long venc_freq, unsigned long long dac_freq,
 		      bool hdmi_use_enci)
 {
 	bool vic_alternate_clock = false;
-	unsigned int freq;
-	unsigned int hdmi_tx_div;
-	unsigned int venc_div;
+	unsigned long long freq;
+	unsigned long long hdmi_tx_div;
+	unsigned long long venc_div;
 
 	if (target == MESON_VCLK_TARGET_CVBS) {
 		meson_venci_cvbs_clock_config(priv);
@@ -1052,27 +1058,27 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 		return;
 	}
 
-	hdmi_tx_div = vclk_freq / dac_freq;
+	hdmi_tx_div = DIV_ROUND_DOWN_ULL(vclk_freq, dac_freq);
 
 	if (hdmi_tx_div == 0) {
-		pr_err("Fatal Error, invalid HDMI-TX freq %d\n",
+		pr_err("Fatal Error, invalid HDMI-TX freq %lluHz\n",
 		       dac_freq);
 		return;
 	}
 
-	venc_div = vclk_freq / venc_freq;
+	venc_div = DIV_ROUND_DOWN_ULL(vclk_freq, venc_freq);
 
 	if (venc_div == 0) {
-		pr_err("Fatal Error, invalid HDMI venc freq %d\n",
+		pr_err("Fatal Error, invalid HDMI venc freq %lluHz\n",
 		       venc_freq);
 		return;
 	}
 
 	for (freq = 0 ; params[freq].pixel_freq ; ++freq) {
 		if ((phy_freq == params[freq].phy_freq ||
-		     phy_freq == FREQ_1000_1001(params[freq].phy_freq/1000)*1000) &&
+		     phy_freq == PHY_FREQ_1000_1001(params[freq].phy_freq)) &&
 		    (vclk_freq == params[freq].vclk_freq ||
-		     vclk_freq == FREQ_1000_1001(params[freq].vclk_freq))) {
+		     vclk_freq == PIXEL_FREQ_1000_1001(params[freq].vclk_freq))) {
 			if (vclk_freq != params[freq].vclk_freq)
 				vic_alternate_clock = true;
 			else
@@ -1098,7 +1104,8 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 	}
 
 	if (!params[freq].pixel_freq) {
-		pr_err("Fatal Error, invalid HDMI vclk freq %d\n", vclk_freq);
+		pr_err("Fatal Error, invalid HDMI vclk freq %lluHz\n",
+		       vclk_freq);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/meson/meson_vclk.h b/drivers/gpu/drm/meson/meson_vclk.h
index 60617aaf18dd..7ac55744e574 100644
--- a/drivers/gpu/drm/meson/meson_vclk.h
+++ b/drivers/gpu/drm/meson/meson_vclk.h
@@ -20,17 +20,18 @@ enum {
 };
 
 /* 27MHz is the CVBS Pixel Clock */
-#define MESON_VCLK_CVBS			27000
+#define MESON_VCLK_CVBS			(27 * 1000 * 1000)
 
 enum drm_mode_status
-meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq);
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned long long freq);
 enum drm_mode_status
-meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
-			      unsigned int vclk_freq);
+meson_vclk_vic_supported_freq(struct meson_drm *priv,
+			      unsigned long long phy_freq,
+			      unsigned long long vclk_freq);
 
 void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
-		      unsigned int phy_freq, unsigned int vclk_freq,
-		      unsigned int venc_freq, unsigned int dac_freq,
+		      unsigned long long phy_freq, unsigned long long vclk_freq,
+		      unsigned long long venc_freq, unsigned long long dac_freq,
 		      bool hdmi_use_enci);
 
 #endif /* __MESON_VCLK_H */
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index fb71658c3117..6067d08aeee3 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -223,7 +223,7 @@ void mgag200_set_mode_regs(struct mga_device *mdev, const struct drm_display_mod
 	vsyncstr = mode->crtc_vsync_start - 1;
 	vsyncend = mode->crtc_vsync_end - 1;
 	vtotal = mode->crtc_vtotal - 2;
-	vblkstr = mode->crtc_vblank_start;
+	vblkstr = mode->crtc_vblank_start - 1;
 	vblkend = vtotal + 1;
 
 	linecomp = vdispend;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 06465bc2d0b4..242d02d48c0c 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -242,10 +242,10 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 				break;
 			fallthrough;
 		case MSM_SUBMIT_CMD_BUF:
-			OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
+			OUT_PKT7(ring, CP_INDIRECT_BUFFER, 3);
 			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
 			OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
-			OUT_RING(ring, submit->cmd[i].size);
+			OUT_RING(ring, A5XX_CP_INDIRECT_BUFFER_2_IB_SIZE(submit->cmd[i].size));
 			ibs++;
 			break;
 		}
@@ -377,10 +377,10 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 				break;
 			fallthrough;
 		case MSM_SUBMIT_CMD_BUF:
-			OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
+			OUT_PKT7(ring, CP_INDIRECT_BUFFER, 3);
 			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
 			OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
-			OUT_RING(ring, submit->cmd[i].size);
+			OUT_RING(ring, A5XX_CP_INDIRECT_BUFFER_2_IB_SIZE(submit->cmd[i].size));
 			ibs++;
 			break;
 		}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h
index 1f32807bb5e5..ad60089f18ea 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h
@@ -132,7 +132,6 @@ static const struct dpu_intf_cfg msm8937_intf[] = {
 		.prog_fetch_lines_worst_case = 14,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_2", .id = INTF_2,
 		.base = 0x6b000, .len = 0x268,
@@ -141,7 +140,6 @@ static const struct dpu_intf_cfg msm8937_intf[] = {
 		.prog_fetch_lines_worst_case = 14,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h
index 42131959ff22..a1cf89a0a42d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h
@@ -118,7 +118,6 @@ static const struct dpu_intf_cfg msm8917_intf[] = {
 		.prog_fetch_lines_worst_case = 14,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h
index 2b4723a5c676..eea9b80e2287 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h
@@ -131,7 +131,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = {
 		.prog_fetch_lines_worst_case = 14,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x268,
@@ -140,7 +139,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = {
 		.prog_fetch_lines_worst_case = 14,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_2", .id = INTF_2,
 		.base = 0x6b000, .len = 0x268,
@@ -149,7 +147,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = {
 		.prog_fetch_lines_worst_case = 14,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h
index 5cf19de71f06..ae18a354e5d2 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h
@@ -241,7 +241,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = {
 		.prog_fetch_lines_worst_case = 25,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x268,
@@ -250,7 +249,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = {
 		.prog_fetch_lines_worst_case = 25,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_2", .id = INTF_2,
 		.base = 0x6b000, .len = 0x268,
@@ -259,7 +257,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = {
 		.prog_fetch_lines_worst_case = 25,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_3", .id = INTF_3,
 		.base = 0x6b800, .len = 0x268,
@@ -267,7 +264,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = {
 		.prog_fetch_lines_worst_case = 25,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h
index 4f2f68b07f20..bb89da0a481d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h
@@ -202,7 +202,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = {
 		.prog_fetch_lines_worst_case = 21,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x280,
@@ -211,7 +210,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = {
 		.prog_fetch_lines_worst_case = 21,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_2", .id = INTF_2,
 		.base = 0x6b000, .len = 0x280,
@@ -220,7 +218,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = {
 		.prog_fetch_lines_worst_case = 21,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h
index c70bef025ac4..7caf876ca3e3 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h
@@ -147,7 +147,6 @@ static const struct dpu_intf_cfg sdm630_intf[] = {
 		.prog_fetch_lines_worst_case = 21,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25),
-		.intr_tear_rd_ptr = -1,
 	}, {
 		.name = "intf_1", .id = INTF_1,
 		.base = 0x6a800, .len = 0x280,
@@ -156,7 +155,6 @@ static const struct dpu_intf_cfg sdm630_intf[] = {
 		.prog_fetch_lines_worst_case = 21,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27),
-		.intr_tear_rd_ptr = -1,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 8610bbf2b87c..862e9e6bf0a5 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -1666,7 +1666,7 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
  */
 static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
 {
-	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(phys->parent);
+	struct dpu_encoder_virt *dpu_enc;
 
 	if (!phys) {
 		DPU_ERROR("invalid argument(s)\n");
@@ -1678,6 +1678,8 @@ static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
 		return;
 	}
 
+	dpu_enc = to_dpu_encoder_virt(phys->parent);
+
 	if (phys->parent->encoder_type == DRM_MODE_ENCODER_VIRTUAL &&
 	    dpu_enc->cwb_mask) {
 		DPU_DEBUG("encoder %d CWB enabled, skipping\n", DRMID(phys->parent));
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index af3e541f60c3..e03d6091f736 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -729,12 +729,40 @@ static int dpu_plane_check_inline_rotation(struct dpu_plane *pdpu,
 static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu,
 		struct dpu_sw_pipe *pipe,
 		struct dpu_sw_pipe_cfg *pipe_cfg,
-		const struct msm_format *fmt,
-		const struct drm_display_mode *mode)
+		const struct drm_display_mode *mode,
+		struct drm_plane_state *new_plane_state)
 {
 	uint32_t min_src_size;
 	struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base);
 	int ret;
+	const struct msm_format *fmt;
+	uint32_t supported_rotations;
+	const struct dpu_sspp_cfg *pipe_hw_caps;
+	const struct dpu_sspp_sub_blks *sblk;
+
+	pipe_hw_caps = pipe->sspp->cap;
+	sblk = pipe->sspp->cap->sblk;
+
+	/*
+	 * We already have verified scaling against platform limitations.
+	 * Now check if the SSPP supports scaling at all.
+	 */
+	if (!sblk->scaler_blk.len &&
+	    ((drm_rect_width(&new_plane_state->src) >> 16 !=
+	      drm_rect_width(&new_plane_state->dst)) ||
+	     (drm_rect_height(&new_plane_state->src) >> 16 !=
+	      drm_rect_height(&new_plane_state->dst))))
+		return -ERANGE;
+
+	fmt = msm_framebuffer_format(new_plane_state->fb);
+
+	supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0;
+
+	if (pipe_hw_caps->features & BIT(DPU_SSPP_INLINE_ROTATION))
+		supported_rotations |= DRM_MODE_ROTATE_90;
+
+	pipe_cfg->rotation = drm_rotation_simplify(new_plane_state->rotation,
+						   supported_rotations);
 
 	min_src_size = MSM_FORMAT_IS_YUV(fmt) ? 2 : 1;
 
@@ -923,47 +951,20 @@ static int dpu_plane_atomic_check_sspp(struct drm_plane *plane,
 	struct dpu_plane_state *pstate = to_dpu_plane_state(new_plane_state);
 	struct dpu_sw_pipe *pipe = &pstate->pipe;
 	struct dpu_sw_pipe *r_pipe = &pstate->r_pipe;
-	const struct msm_format *fmt;
 	struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg;
 	struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg;
-	uint32_t supported_rotations;
-	const struct dpu_sspp_cfg *pipe_hw_caps;
-	const struct dpu_sspp_sub_blks *sblk;
 	int ret = 0;
 
-	pipe_hw_caps = pipe->sspp->cap;
-	sblk = pipe->sspp->cap->sblk;
-
-	/*
-	 * We already have verified scaling against platform limitations.
-	 * Now check if the SSPP supports scaling at all.
-	 */
-	if (!sblk->scaler_blk.len &&
-	    ((drm_rect_width(&new_plane_state->src) >> 16 !=
-	      drm_rect_width(&new_plane_state->dst)) ||
-	     (drm_rect_height(&new_plane_state->src) >> 16 !=
-	      drm_rect_height(&new_plane_state->dst))))
-		return -ERANGE;
-
-	fmt = msm_framebuffer_format(new_plane_state->fb);
-
-	supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0;
-
-	if (pipe_hw_caps->features & BIT(DPU_SSPP_INLINE_ROTATION))
-		supported_rotations |= DRM_MODE_ROTATE_90;
-
-	pipe_cfg->rotation = drm_rotation_simplify(new_plane_state->rotation,
-						   supported_rotations);
-	r_pipe_cfg->rotation = pipe_cfg->rotation;
-
-	ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt,
-					  &crtc_state->adjusted_mode);
+	ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg,
+					  &crtc_state->adjusted_mode,
+					  new_plane_state);
 	if (ret)
 		return ret;
 
 	if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) {
-		ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg, fmt,
-						  &crtc_state->adjusted_mode);
+		ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg,
+						  &crtc_state->adjusted_mode,
+						  new_plane_state);
 		if (ret)
 			return ret;
 	}
@@ -1059,6 +1060,9 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane,
 	struct drm_crtc_state *crtc_state;
 	int ret;
 
+	if (IS_ERR(plane_state))
+		return PTR_ERR(plane_state);
+
 	if (plane_state->crtc)
 		crtc_state = drm_atomic_get_new_crtc_state(state,
 							   plane_state->crtc);
diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
index 55a35182858c..5a6ae9fc3194 100644
--- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
+++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
@@ -2259,5 +2259,12 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords)
 	</reg32>
 </domain>
 
+<domain name="CP_INDIRECT_BUFFER" width="32" varset="chip" prefix="chip" variants="A5XX-">
+	<reg64 offset="0" name="IB_BASE" type="address"/>
+	<reg32 offset="2" name="2">
+		<bitfield name="IB_SIZE" low="0" high="19"/>
+	</reg32>
+</domain>
+
 </database>
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index db961eade225..2016c1e7242f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -144,6 +144,9 @@ nouveau_bo_del_ttm(struct ttm_buffer_object *bo)
 	nouveau_bo_del_io_reserve_lru(bo);
 	nv10_bo_put_tile_region(dev, nvbo->tile, NULL);
 
+	if (bo->base.import_attach)
+		drm_prime_gem_destroy(&bo->base, bo->sg);
+
 	/*
 	 * If nouveau_bo_new() allocated this buffer, the GEM object was never
 	 * initialized, so don't attempt to release it.
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 7cc84472cece..edddfc036c6d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -90,7 +90,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
 	while (!list_empty(&fctx->pending)) {
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 
-		if (error)
+		if (error && !dma_fence_is_signaled_locked(&fence->base))
 			dma_fence_set_error(&fence->base, error);
 
 		if (nouveau_fence_signal(fence))
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 9ae2cee1c7c5..67e3c99de73a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -87,9 +87,6 @@ nouveau_gem_object_del(struct drm_gem_object *gem)
 		return;
 	}
 
-	if (gem->import_attach)
-		drm_prime_gem_destroy(gem, nvbo->bo.sg);
-
 	ttm_bo_put(&nvbo->bo);
 
 	pm_runtime_mark_last_busy(dev);
diff --git a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
index 7d68a8acfe2e..eb0f8373258c 100644
--- a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
+++ b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
@@ -129,11 +129,11 @@ static int jadard_unprepare(struct drm_panel *panel)
 {
 	struct jadard *jadard = panel_to_jadard(panel);
 
-	gpiod_set_value(jadard->reset, 1);
+	gpiod_set_value(jadard->reset, 0);
 	msleep(120);
 
 	if (jadard->desc->reset_before_power_off_vcioo) {
-		gpiod_set_value(jadard->reset, 0);
+		gpiod_set_value(jadard->reset, 1);
 
 		usleep_range(1000, 2000);
 	}
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 232b03c1a259..33a37539de57 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1027,27 +1027,28 @@ static const struct panel_desc auo_g070vvn01 = {
 	},
 };
 
-static const struct drm_display_mode auo_g101evn010_mode = {
-	.clock = 68930,
-	.hdisplay = 1280,
-	.hsync_start = 1280 + 82,
-	.hsync_end = 1280 + 82 + 2,
-	.htotal = 1280 + 82 + 2 + 84,
-	.vdisplay = 800,
-	.vsync_start = 800 + 8,
-	.vsync_end = 800 + 8 + 2,
-	.vtotal = 800 + 8 + 2 + 6,
+static const struct display_timing auo_g101evn010_timing = {
+	.pixelclock = { 64000000, 68930000, 85000000 },
+	.hactive = { 1280, 1280, 1280 },
+	.hfront_porch = { 8, 64, 256 },
+	.hback_porch = { 8, 64, 256 },
+	.hsync_len = { 40, 168, 767 },
+	.vactive = { 800, 800, 800 },
+	.vfront_porch = { 4, 8, 100 },
+	.vback_porch = { 4, 8, 100 },
+	.vsync_len = { 8, 16, 223 },
 };
 
 static const struct panel_desc auo_g101evn010 = {
-	.modes = &auo_g101evn010_mode,
-	.num_modes = 1,
+	.timings = &auo_g101evn010_timing,
+	.num_timings = 1,
 	.bpc = 6,
 	.size = {
 		.width = 216,
 		.height = 135,
 	},
 	.bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
 };
 
diff --git a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
index 3d1dddb34603..7d531b6f4c09 100644
--- a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
@@ -94,6 +94,7 @@ struct rockchip_hdmi_qp {
 	struct gpio_desc *enable_gpio;
 	struct delayed_work hpd_work;
 	int port_id;
+	const struct rockchip_hdmi_qp_ctrl_ops *ctrl_ops;
 };
 
 struct rockchip_hdmi_qp_ctrl_ops {
@@ -461,6 +462,7 @@ static int dw_hdmi_qp_rockchip_bind(struct device *dev, struct device *master,
 		return -ENODEV;
 	}
 
+	hdmi->ctrl_ops = cfg->ctrl_ops;
 	hdmi->dev = &pdev->dev;
 	hdmi->port_id = -ENODEV;
 
@@ -600,27 +602,8 @@ static void dw_hdmi_qp_rockchip_remove(struct platform_device *pdev)
 static int __maybe_unused dw_hdmi_qp_rockchip_resume(struct device *dev)
 {
 	struct rockchip_hdmi_qp *hdmi = dev_get_drvdata(dev);
-	u32 val;
 
-	val = HIWORD_UPDATE(RK3588_SCLIN_MASK, RK3588_SCLIN_MASK) |
-	      HIWORD_UPDATE(RK3588_SDAIN_MASK, RK3588_SDAIN_MASK) |
-	      HIWORD_UPDATE(RK3588_MODE_MASK, RK3588_MODE_MASK) |
-	      HIWORD_UPDATE(RK3588_I2S_SEL_MASK, RK3588_I2S_SEL_MASK);
-	regmap_write(hdmi->vo_regmap,
-		     hdmi->port_id ? RK3588_GRF_VO1_CON6 : RK3588_GRF_VO1_CON3,
-		     val);
-
-	val = HIWORD_UPDATE(RK3588_SET_HPD_PATH_MASK,
-			    RK3588_SET_HPD_PATH_MASK);
-	regmap_write(hdmi->regmap, RK3588_GRF_SOC_CON7, val);
-
-	if (hdmi->port_id)
-		val = HIWORD_UPDATE(RK3588_HDMI1_GRANT_SEL,
-				    RK3588_HDMI1_GRANT_SEL);
-	else
-		val = HIWORD_UPDATE(RK3588_HDMI0_GRANT_SEL,
-				    RK3588_HDMI0_GRANT_SEL);
-	regmap_write(hdmi->vo_regmap, RK3588_GRF_VO1_CON9, val);
+	hdmi->ctrl_ops->io_init(hdmi);
 
 	dw_hdmi_qp_resume(dev, hdmi->hdmi);
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
index 14958d6b3d2e..0a2840cbe8e2 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
@@ -1754,9 +1754,9 @@ static unsigned long rk3588_set_intf_mux(struct vop2_video_port *vp, int id, u32
 		dip |= FIELD_PREP(RK3588_DSP_IF_POL__DP0_PIN_POL, polflags);
 		break;
 	case ROCKCHIP_VOP2_EP_DP1:
-		die &= ~RK3588_SYS_DSP_INFACE_EN_MIPI1_MUX;
-		die |= RK3588_SYS_DSP_INFACE_EN_MIPI1 |
-			   FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_MIPI1_MUX, vp->id);
+		die &= ~RK3588_SYS_DSP_INFACE_EN_DP1_MUX;
+		die |= RK3588_SYS_DSP_INFACE_EN_DP1 |
+			   FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_DP1_MUX, vp->id);
 		dip &= ~RK3588_DSP_IF_POL__DP1_PIN_POL;
 		dip |= FIELD_PREP(RK3588_DSP_IF_POL__DP1_PIN_POL, polflags);
 		break;
diff --git a/drivers/gpu/drm/sti/Makefile b/drivers/gpu/drm/sti/Makefile
index f203ac5514ae..f778a4eee7c9 100644
--- a/drivers/gpu/drm/sti/Makefile
+++ b/drivers/gpu/drm/sti/Makefile
@@ -7,8 +7,6 @@ sti-drm-y := \
 	sti_compositor.o \
 	sti_crtc.o \
 	sti_plane.o \
-	sti_crtc.o \
-	sti_plane.o \
 	sti_hdmi.o \
 	sti_hdmi_tx3g4c28phy.o \
 	sti_dvo.o \
diff --git a/drivers/gpu/drm/tests/drm_client_modeset_test.c b/drivers/gpu/drm/tests/drm_client_modeset_test.c
index 7516f6cb36e4..b2fdb1a774fe 100644
--- a/drivers/gpu/drm/tests/drm_client_modeset_test.c
+++ b/drivers/gpu/drm/tests/drm_client_modeset_test.c
@@ -95,6 +95,9 @@ static void drm_test_pick_cmdline_res_1920_1080_60(struct kunit *test)
 	expected_mode = drm_mode_find_dmt(priv->drm, 1920, 1080, 60, false);
 	KUNIT_ASSERT_NOT_NULL(test, expected_mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, expected_mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_ASSERT_TRUE(test,
 			  drm_mode_parse_command_line_for_connector(cmdline,
 								    connector,
@@ -129,7 +132,8 @@ static void drm_test_pick_cmdline_named(struct kunit *test)
 	struct drm_device *drm = priv->drm;
 	struct drm_connector *connector = &priv->connector;
 	struct drm_cmdline_mode *cmdline_mode = &connector->cmdline_mode;
-	const struct drm_display_mode *expected_mode, *mode;
+	const struct drm_display_mode *mode;
+	struct drm_display_mode *expected_mode;
 	const char *cmdline = params->cmdline;
 	int ret;
 
@@ -149,6 +153,9 @@ static void drm_test_pick_cmdline_named(struct kunit *test)
 	expected_mode = params->func(drm);
 	KUNIT_ASSERT_NOT_NULL(test, expected_mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, expected_mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_EXPECT_TRUE(test, drm_mode_equal(expected_mode, mode));
 }
 
diff --git a/drivers/gpu/drm/tests/drm_cmdline_parser_test.c b/drivers/gpu/drm/tests/drm_cmdline_parser_test.c
index 59c8408c453c..1cfcb597b088 100644
--- a/drivers/gpu/drm/tests/drm_cmdline_parser_test.c
+++ b/drivers/gpu/drm/tests/drm_cmdline_parser_test.c
@@ -7,6 +7,7 @@
 #include <kunit/test.h>
 
 #include <drm/drm_connector.h>
+#include <drm/drm_kunit_helpers.h>
 #include <drm/drm_modes.h>
 
 static const struct drm_connector no_connector = {};
@@ -955,8 +956,15 @@ struct drm_cmdline_tv_option_test {
 static void drm_test_cmdline_tv_options(struct kunit *test)
 {
 	const struct drm_cmdline_tv_option_test *params = test->param_value;
-	const struct drm_display_mode *expected_mode = params->mode_fn(NULL);
+	struct drm_display_mode *expected_mode;
 	struct drm_cmdline_mode mode = { };
+	int ret;
+
+	expected_mode = params->mode_fn(NULL);
+	KUNIT_ASSERT_NOT_NULL(test, expected_mode);
+
+	ret = drm_kunit_add_mode_destroy_action(test, expected_mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	KUNIT_EXPECT_TRUE(test, drm_mode_parse_command_line_for_connector(params->cmdline,
 									  &no_connector, &mode));
diff --git a/drivers/gpu/drm/tests/drm_gem_shmem_test.c b/drivers/gpu/drm/tests/drm_gem_shmem_test.c
index fd4215e2f982..925fbc2cda70 100644
--- a/drivers/gpu/drm/tests/drm_gem_shmem_test.c
+++ b/drivers/gpu/drm/tests/drm_gem_shmem_test.c
@@ -216,6 +216,9 @@ static void drm_gem_shmem_test_get_pages_sgt(struct kunit *test)
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sgt);
 	KUNIT_EXPECT_NULL(test, shmem->sgt);
 
+	ret = kunit_add_action_or_reset(test, kfree_wrapper, sgt);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	ret = kunit_add_action_or_reset(test, sg_free_table_wrapper, sgt);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
diff --git a/drivers/gpu/drm/tests/drm_kunit_helpers.c b/drivers/gpu/drm/tests/drm_kunit_helpers.c
index a4eb68f0decc..6f6616cf4966 100644
--- a/drivers/gpu/drm/tests/drm_kunit_helpers.c
+++ b/drivers/gpu/drm/tests/drm_kunit_helpers.c
@@ -279,6 +279,28 @@ static void kunit_action_drm_mode_destroy(void *ptr)
 }
 
 /**
+ * drm_kunit_add_mode_destroy_action() - Add a drm_destroy_mode kunit action
+ * @test: The test context object
+ * @mode: The drm_display_mode to destroy eventually
+ *
+ * Registers a kunit action that will destroy the drm_display_mode at
+ * the end of the test.
+ *
+ * If an error occurs, the drm_display_mode will be destroyed.
+ *
+ * Returns:
+ * 0 on success, an error code otherwise.
+ */
+int drm_kunit_add_mode_destroy_action(struct kunit *test,
+				      struct drm_display_mode *mode)
+{
+	return kunit_add_action_or_reset(test,
+					 kunit_action_drm_mode_destroy,
+					 mode);
+}
+EXPORT_SYMBOL_GPL(drm_kunit_add_mode_destroy_action);
+
+/**
  * drm_kunit_display_mode_from_cea_vic() - return a mode for CEA VIC for a KUnit test
  * @test: The test context object
  * @dev: DRM device
diff --git a/drivers/gpu/drm/tests/drm_modes_test.c b/drivers/gpu/drm/tests/drm_modes_test.c
index 6ed51f99e133..f5b20f92df8b 100644
--- a/drivers/gpu/drm/tests/drm_modes_test.c
+++ b/drivers/gpu/drm/tests/drm_modes_test.c
@@ -40,6 +40,7 @@ static void drm_test_modes_analog_tv_ntsc_480i(struct kunit *test)
 {
 	struct drm_test_modes_priv *priv = test->priv;
 	struct drm_display_mode *mode;
+	int ret;
 
 	mode = drm_analog_tv_mode(priv->drm,
 				  DRM_MODE_TV_MODE_NTSC,
@@ -47,6 +48,9 @@ static void drm_test_modes_analog_tv_ntsc_480i(struct kunit *test)
 				  true);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_EXPECT_EQ(test, drm_mode_vrefresh(mode), 60);
 	KUNIT_EXPECT_EQ(test, mode->hdisplay, 720);
 
@@ -70,6 +74,7 @@ static void drm_test_modes_analog_tv_ntsc_480i_inlined(struct kunit *test)
 {
 	struct drm_test_modes_priv *priv = test->priv;
 	struct drm_display_mode *expected, *mode;
+	int ret;
 
 	expected = drm_analog_tv_mode(priv->drm,
 				      DRM_MODE_TV_MODE_NTSC,
@@ -77,9 +82,15 @@ static void drm_test_modes_analog_tv_ntsc_480i_inlined(struct kunit *test)
 				      true);
 	KUNIT_ASSERT_NOT_NULL(test, expected);
 
+	ret = drm_kunit_add_mode_destroy_action(test, expected);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	mode = drm_mode_analog_ntsc_480i(priv->drm);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_EXPECT_TRUE(test, drm_mode_equal(expected, mode));
 }
 
@@ -87,6 +98,7 @@ static void drm_test_modes_analog_tv_pal_576i(struct kunit *test)
 {
 	struct drm_test_modes_priv *priv = test->priv;
 	struct drm_display_mode *mode;
+	int ret;
 
 	mode = drm_analog_tv_mode(priv->drm,
 				  DRM_MODE_TV_MODE_PAL,
@@ -94,6 +106,9 @@ static void drm_test_modes_analog_tv_pal_576i(struct kunit *test)
 				  true);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_EXPECT_EQ(test, drm_mode_vrefresh(mode), 50);
 	KUNIT_EXPECT_EQ(test, mode->hdisplay, 720);
 
@@ -117,6 +132,7 @@ static void drm_test_modes_analog_tv_pal_576i_inlined(struct kunit *test)
 {
 	struct drm_test_modes_priv *priv = test->priv;
 	struct drm_display_mode *expected, *mode;
+	int ret;
 
 	expected = drm_analog_tv_mode(priv->drm,
 				      DRM_MODE_TV_MODE_PAL,
@@ -124,9 +140,15 @@ static void drm_test_modes_analog_tv_pal_576i_inlined(struct kunit *test)
 				      true);
 	KUNIT_ASSERT_NOT_NULL(test, expected);
 
+	ret = drm_kunit_add_mode_destroy_action(test, expected);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	mode = drm_mode_analog_pal_576i(priv->drm);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_EXPECT_TRUE(test, drm_mode_equal(expected, mode));
 }
 
@@ -134,6 +156,7 @@ static void drm_test_modes_analog_tv_mono_576i(struct kunit *test)
 {
 	struct drm_test_modes_priv *priv = test->priv;
 	struct drm_display_mode *mode;
+	int ret;
 
 	mode = drm_analog_tv_mode(priv->drm,
 				  DRM_MODE_TV_MODE_MONOCHROME,
@@ -141,6 +164,9 @@ static void drm_test_modes_analog_tv_mono_576i(struct kunit *test)
 				  true);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_EXPECT_EQ(test, drm_mode_vrefresh(mode), 50);
 	KUNIT_EXPECT_EQ(test, mode->hdisplay, 720);
 
diff --git a/drivers/gpu/drm/tests/drm_probe_helper_test.c b/drivers/gpu/drm/tests/drm_probe_helper_test.c
index bc09ff38aca1..db0e4f5df275 100644
--- a/drivers/gpu/drm/tests/drm_probe_helper_test.c
+++ b/drivers/gpu/drm/tests/drm_probe_helper_test.c
@@ -98,7 +98,7 @@ drm_test_connector_helper_tv_get_modes_check(struct kunit *test)
 	struct drm_connector *connector = &priv->connector;
 	struct drm_cmdline_mode *cmdline = &connector->cmdline_mode;
 	struct drm_display_mode *mode;
-	const struct drm_display_mode *expected;
+	struct drm_display_mode *expected;
 	size_t len;
 	int ret;
 
@@ -134,6 +134,9 @@ drm_test_connector_helper_tv_get_modes_check(struct kunit *test)
 
 		KUNIT_EXPECT_TRUE(test, drm_mode_equal(mode, expected));
 		KUNIT_EXPECT_TRUE(test, mode->type & DRM_MODE_TYPE_PREFERRED);
+
+		ret = drm_kunit_add_mode_destroy_action(test, expected);
+		KUNIT_ASSERT_EQ(test, ret, 0);
 	}
 
 	if (params->num_expected_modes >= 2) {
@@ -145,6 +148,9 @@ drm_test_connector_helper_tv_get_modes_check(struct kunit *test)
 
 		KUNIT_EXPECT_TRUE(test, drm_mode_equal(mode, expected));
 		KUNIT_EXPECT_FALSE(test, mode->type & DRM_MODE_TYPE_PREFERRED);
+
+		ret = drm_kunit_add_mode_destroy_action(test, expected);
+		KUNIT_ASSERT_EQ(test, ret, 0);
 	}
 
 	mutex_unlock(&priv->drm->mode_config.mutex);
diff --git a/drivers/gpu/drm/tiny/panel-mipi-dbi.c b/drivers/gpu/drm/tiny/panel-mipi-dbi.c
index 0460ecaef4bd..23914a9f7fd3 100644
--- a/drivers/gpu/drm/tiny/panel-mipi-dbi.c
+++ b/drivers/gpu/drm/tiny/panel-mipi-dbi.c
@@ -390,7 +390,10 @@ static int panel_mipi_dbi_spi_probe(struct spi_device *spi)
 
 	spi_set_drvdata(spi, drm);
 
-	drm_client_setup(drm, NULL);
+	if (bpp == 16)
+		drm_client_setup_with_fourcc(drm, DRM_FORMAT_RGB565);
+	else
+		drm_client_setup_with_fourcc(drm, DRM_FORMAT_RGB888);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_backup.c b/drivers/gpu/drm/ttm/ttm_backup.c
index 93c007f18855..9e2d72c447ee 100644
--- a/drivers/gpu/drm/ttm/ttm_backup.c
+++ b/drivers/gpu/drm/ttm/ttm_backup.c
@@ -8,20 +8,6 @@
 #include <linux/swap.h>
 
 /*
- * Casting from randomized struct file * to struct ttm_backup * is fine since
- * struct ttm_backup is never defined nor dereferenced.
- */
-static struct file *ttm_backup_to_file(struct ttm_backup *backup)
-{
-	return (void *)backup;
-}
-
-static struct ttm_backup *ttm_file_to_backup(struct file *file)
-{
-	return (void *)file;
-}
-
-/*
  * Need to map shmem indices to handle since a handle value
  * of 0 means error, following the swp_entry_t convention.
  */
@@ -40,12 +26,12 @@ static pgoff_t ttm_backup_handle_to_shmem_idx(pgoff_t handle)
  * @backup: The struct backup pointer used to obtain the handle
  * @handle: The handle obtained from the @backup_page function.
  */
-void ttm_backup_drop(struct ttm_backup *backup, pgoff_t handle)
+void ttm_backup_drop(struct file *backup, pgoff_t handle)
 {
 	loff_t start = ttm_backup_handle_to_shmem_idx(handle);
 
 	start <<= PAGE_SHIFT;
-	shmem_truncate_range(file_inode(ttm_backup_to_file(backup)), start,
+	shmem_truncate_range(file_inode(backup), start,
 			     start + PAGE_SIZE - 1);
 }
 
@@ -55,16 +41,15 @@ void ttm_backup_drop(struct ttm_backup *backup, pgoff_t handle)
  * @backup: The struct backup pointer used to back up the page.
  * @dst: The struct page to copy into.
  * @handle: The handle returned when the page was backed up.
- * @intr: Try to perform waits interruptable or at least killable.
+ * @intr: Try to perform waits interruptible or at least killable.
  *
  * Return: 0 on success, Negative error code on failure, notably
  * -EINTR if @intr was set to true and a signal is pending.
  */
-int ttm_backup_copy_page(struct ttm_backup *backup, struct page *dst,
+int ttm_backup_copy_page(struct file *backup, struct page *dst,
 			 pgoff_t handle, bool intr)
 {
-	struct file *filp = ttm_backup_to_file(backup);
-	struct address_space *mapping = filp->f_mapping;
+	struct address_space *mapping = backup->f_mapping;
 	struct folio *from_folio;
 	pgoff_t idx = ttm_backup_handle_to_shmem_idx(handle);
 
@@ -106,12 +91,11 @@ int ttm_backup_copy_page(struct ttm_backup *backup, struct page *dst,
  * the folio size- and usage.
  */
 s64
-ttm_backup_backup_page(struct ttm_backup *backup, struct page *page,
+ttm_backup_backup_page(struct file *backup, struct page *page,
 		       bool writeback, pgoff_t idx, gfp_t page_gfp,
 		       gfp_t alloc_gfp)
 {
-	struct file *filp = ttm_backup_to_file(backup);
-	struct address_space *mapping = filp->f_mapping;
+	struct address_space *mapping = backup->f_mapping;
 	unsigned long handle = 0;
 	struct folio *to_folio;
 	int ret;
@@ -161,9 +145,9 @@ ttm_backup_backup_page(struct ttm_backup *backup, struct page *page,
  *
  * After a call to this function, it's illegal to use the @backup pointer.
  */
-void ttm_backup_fini(struct ttm_backup *backup)
+void ttm_backup_fini(struct file *backup)
 {
-	fput(ttm_backup_to_file(backup));
+	fput(backup);
 }
 
 /**
@@ -194,14 +178,10 @@ EXPORT_SYMBOL_GPL(ttm_backup_bytes_avail);
  *
  * Create a backup utilizing shmem objects.
  *
- * Return: A pointer to a struct ttm_backup on success,
+ * Return: A pointer to a struct file on success,
  * an error pointer on error.
  */
-struct ttm_backup *ttm_backup_shmem_create(loff_t size)
+struct file *ttm_backup_shmem_create(loff_t size)
 {
-	struct file *filp;
-
-	filp = shmem_file_setup("ttm shmem backup", size, 0);
-
-	return ttm_file_to_backup(filp);
+	return shmem_file_setup("ttm shmem backup", size, 0);
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 95b86003c50d..5bf3c969907c 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1093,7 +1093,8 @@ struct ttm_bo_swapout_walk {
 	struct ttm_lru_walk walk;
 	/** @gfp_flags: The gfp flags to use for ttm_tt_swapout() */
 	gfp_t gfp_flags;
-
+	/** @hit_low: Whether we should attempt to swap BO's with low watermark threshold */
+	/** @evict_low: If we cannot swap a bo when @try_low is false (first pass) */
 	bool hit_low, evict_low;
 };
 
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 83b10706ba89..c2ea865be657 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -506,7 +506,7 @@ static void ttm_pool_allocated_page_commit(struct page *allocated,
  * if successful, populate the page-table and dma-address arrays.
  */
 static int ttm_pool_restore_commit(struct ttm_pool_tt_restore *restore,
-				   struct ttm_backup *backup,
+				   struct file *backup,
 				   const struct ttm_operation_ctx *ctx,
 				   struct ttm_pool_alloc_state *alloc)
 
@@ -655,7 +655,7 @@ static void ttm_pool_free_range(struct ttm_pool *pool, struct ttm_tt *tt,
 				pgoff_t start_page, pgoff_t end_page)
 {
 	struct page **pages = &tt->pages[start_page];
-	struct ttm_backup *backup = tt->backup;
+	struct file *backup = tt->backup;
 	pgoff_t i, nr;
 
 	for (i = start_page; i < end_page; i += nr, pages += nr) {
@@ -963,7 +963,7 @@ void ttm_pool_drop_backed_up(struct ttm_tt *tt)
 long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt,
 		     const struct ttm_backup_flags *flags)
 {
-	struct ttm_backup *backup = tt->backup;
+	struct file *backup = tt->backup;
 	struct page *page;
 	unsigned long handle;
 	gfp_t alloc_gfp;
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index df0aa6c4b8b8..698cd4bf5e46 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -544,7 +544,7 @@ EXPORT_SYMBOL(ttm_tt_pages_limit);
  */
 int ttm_tt_setup_backup(struct ttm_tt *tt)
 {
-	struct ttm_backup *backup =
+	struct file *backup =
 		ttm_backup_shmem_create(((loff_t)tt->num_pages) << PAGE_SHIFT);
 
 	if (WARN_ON_ONCE(!(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE)))
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 34c42d6e12cd..eb35482f6fb5 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -428,7 +428,8 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
 	struct v3d_bo *bo = to_v3d_bo(job->base.bo[0]);
 	struct v3d_bo *indirect = to_v3d_bo(indirect_csd->indirect);
 	struct drm_v3d_submit_csd *args = &indirect_csd->job->args;
-	u32 *wg_counts;
+	struct v3d_dev *v3d = job->base.v3d;
+	u32 num_batches, *wg_counts;
 
 	v3d_get_bo_vaddr(bo);
 	v3d_get_bo_vaddr(indirect);
@@ -441,8 +442,17 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
 	args->cfg[0] = wg_counts[0] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
 	args->cfg[1] = wg_counts[1] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
 	args->cfg[2] = wg_counts[2] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
-	args->cfg[4] = DIV_ROUND_UP(indirect_csd->wg_size, 16) *
-		       (wg_counts[0] * wg_counts[1] * wg_counts[2]) - 1;
+
+	num_batches = DIV_ROUND_UP(indirect_csd->wg_size, 16) *
+		      (wg_counts[0] * wg_counts[1] * wg_counts[2]);
+
+	/* V3D 7.1.6 and later don't subtract 1 from the number of batches */
+	if (v3d->ver < 71 || (v3d->ver == 71 && v3d->rev < 6))
+		args->cfg[4] = num_batches - 1;
+	else
+		args->cfg[4] = num_batches;
+
+	WARN_ON(args->cfg[4] == ~0);
 
 	for (int i = 0; i < 3; i++) {
 		/* 0xffffffff indicates that the uniform rewrite is not needed */
@@ -734,11 +744,16 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job)
 	return DRM_GPU_SCHED_STAT_NOMINAL;
 }
 
-/* If the current address or return address have changed, then the GPU
- * has probably made progress and we should delay the reset.  This
- * could fail if the GPU got in an infinite loop in the CL, but that
- * is pretty unlikely outside of an i-g-t testcase.
- */
+static void
+v3d_sched_skip_reset(struct drm_sched_job *sched_job)
+{
+	struct drm_gpu_scheduler *sched = sched_job->sched;
+
+	spin_lock(&sched->job_list_lock);
+	list_add(&sched_job->list, &sched->pending_list);
+	spin_unlock(&sched->job_list_lock);
+}
+
 static enum drm_gpu_sched_stat
 v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
 		    u32 *timedout_ctca, u32 *timedout_ctra)
@@ -748,9 +763,16 @@ v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
 	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(q));
 	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(q));
 
+	/* If the current address or return address have changed, then the GPU
+	 * has probably made progress and we should delay the reset. This
+	 * could fail if the GPU got in an infinite loop in the CL, but that
+	 * is pretty unlikely outside of an i-g-t testcase.
+	 */
 	if (*timedout_ctca != ctca || *timedout_ctra != ctra) {
 		*timedout_ctca = ctca;
 		*timedout_ctra = ctra;
+
+		v3d_sched_skip_reset(sched_job);
 		return DRM_GPU_SCHED_STAT_NOMINAL;
 	}
 
@@ -790,11 +812,13 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job)
 	struct v3d_dev *v3d = job->base.v3d;
 	u32 batches = V3D_CORE_READ(0, V3D_CSD_CURRENT_CFG4(v3d->ver));
 
-	/* If we've made progress, skip reset and let the timer get
-	 * rearmed.
+	/* If we've made progress, skip reset, add the job to the pending
+	 * list, and let the timer get rearmed.
 	 */
 	if (job->timedout_batches != batches) {
 		job->timedout_batches = batches;
+
+		v3d_sched_skip_reset(sched_job);
 		return DRM_GPU_SCHED_STAT_NOMINAL;
 	}
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index 2d88e390feb4..e32e680c7197 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -128,6 +128,14 @@ static void virtio_gpu_remove(struct virtio_device *vdev)
 	drm_dev_put(dev);
 }
 
+static void virtio_gpu_shutdown(struct virtio_device *vdev)
+{
+	/*
+	 * drm does its own synchronization on shutdown.
+	 * Do nothing here, opt out of device reset.
+	 */
+}
+
 static void virtio_gpu_config_changed(struct virtio_device *vdev)
 {
 	struct drm_device *dev = vdev->priv;
@@ -162,6 +170,7 @@ static struct virtio_driver virtio_gpu_driver = {
 	.id_table = id_table,
 	.probe = virtio_gpu_probe,
 	.remove = virtio_gpu_remove,
+	.shutdown = virtio_gpu_shutdown,
 	.config_changed = virtio_gpu_config_changed
 };
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c
index dde8fc1a3689..90c99d83c4cf 100644
--- a/drivers/gpu/drm/virtio/virtgpu_gem.c
+++ b/drivers/gpu/drm/virtio/virtgpu_gem.c
@@ -115,13 +115,14 @@ int virtio_gpu_gem_object_open(struct drm_gem_object *obj,
 	if (!vgdev->has_context_init)
 		virtio_gpu_create_context(obj->dev, file);
 
-	objs = virtio_gpu_array_alloc(1);
-	if (!objs)
-		return -ENOMEM;
-	virtio_gpu_array_add_obj(objs, obj);
+	if (vfpriv->context_created) {
+		objs = virtio_gpu_array_alloc(1);
+		if (!objs)
+			return -ENOMEM;
+		virtio_gpu_array_add_obj(objs, obj);
 
-	if (vfpriv->ctx_id)
 		virtio_gpu_cmd_context_attach_resource(vgdev, vfpriv->ctx_id, objs);
+	}
 
 out_notify:
 	virtio_gpu_notify(vgdev);
diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
index a6f5a78f436a..87e584add042 100644
--- a/drivers/gpu/drm/virtio/virtgpu_plane.c
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -366,12 +366,6 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane,
 		return 0;
 
 	obj = new_state->fb->obj[0];
-	if (obj->import_attach) {
-		ret = virtio_gpu_prepare_imported_obj(plane, new_state, obj);
-		if (ret)
-			return ret;
-	}
-
 	if (bo->dumb || obj->import_attach) {
 		vgplane_st->fence = virtio_gpu_fence_alloc(vgdev,
 						     vgdev->fence_drv.context,
@@ -380,7 +374,21 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane,
 			return -ENOMEM;
 	}
 
+	if (obj->import_attach) {
+		ret = virtio_gpu_prepare_imported_obj(plane, new_state, obj);
+		if (ret)
+			goto err_fence;
+	}
+
 	return 0;
+
+err_fence:
+	if (vgplane_st->fence) {
+		dma_fence_put(&vgplane_st->fence->f);
+		vgplane_st->fence = NULL;
+	}
+
+	return ret;
 }
 
 static void virtio_gpu_cleanup_imported_obj(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c
index fe6a0b018571..4de2a63ccd18 100644
--- a/drivers/gpu/drm/virtio/virtgpu_prime.c
+++ b/drivers/gpu/drm/virtio/virtgpu_prime.c
@@ -321,6 +321,7 @@ struct drm_gem_object *virtgpu_gem_prime_import(struct drm_device *dev,
 		return ERR_PTR(-ENOMEM);
 
 	obj = &bo->base.base;
+	obj->resv = buf->resv;
 	obj->funcs = &virtgpu_gem_dma_buf_funcs;
 	drm_gem_private_object_init(dev, obj, buf->size);
 
diff --git a/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h b/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h
index a255946b6f77..8cfcd3360896 100644
--- a/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h
+++ b/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h
@@ -41,6 +41,7 @@
 
 #define GFX_OP_PIPE_CONTROL(len)	((0x3<<29)|(0x3<<27)|(0x2<<24)|((len)-2))
 
+#define	  PIPE_CONTROL0_L3_READ_ONLY_CACHE_INVALIDATE	BIT(10)	/* gen12 */
 #define	  PIPE_CONTROL0_HDC_PIPELINE_FLUSH		BIT(9)	/* gen12 */
 
 #define   PIPE_CONTROL_COMMAND_CACHE_INVALIDATE		(1<<29)
diff --git a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
index 167fb0f742de..5a47991b4b81 100644
--- a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
+++ b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
@@ -47,6 +47,10 @@
 #define   MI_LRI_FORCE_POSTED		REG_BIT(12)
 #define   MI_LRI_LEN(x)			(((x) & 0xff) + 1)
 
+#define MI_STORE_REGISTER_MEM		(__MI_INSTR(0x24) | XE_INSTR_NUM_DW(4))
+#define   MI_SRM_USE_GGTT		REG_BIT(22)
+#define   MI_SRM_ADD_CS_OFFSET		REG_BIT(19)
+
 #define MI_FLUSH_DW			__MI_INSTR(0x26)
 #define   MI_FLUSH_DW_PROTECTED_MEM_EN	REG_BIT(22)
 #define   MI_FLUSH_DW_STORE_INDEX	REG_BIT(21)
diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index fb8ec317b6ee..891f928d80ce 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -43,6 +43,10 @@
 #define XEHPC_BCS8_RING_BASE			0x3ee000
 #define GSCCS_RING_BASE				0x11a000
 
+#define ENGINE_ID(base)				XE_REG((base) + 0x8c)
+#define   ENGINE_INSTANCE_ID			REG_GENMASK(9, 4)
+#define   ENGINE_CLASS_ID			REG_GENMASK(2, 0)
+
 #define RING_TAIL(base)				XE_REG((base) + 0x30)
 #define   TAIL_ADDR				REG_GENMASK(20, 3)
 
@@ -154,6 +158,7 @@
 #define   STOP_RING				REG_BIT(8)
 
 #define RING_CTX_TIMESTAMP(base)		XE_REG((base) + 0x3a8)
+#define RING_CTX_TIMESTAMP_UDW(base)		XE_REG((base) + 0x3ac)
 #define CSBE_DEBUG_STATUS(base)			XE_REG((base) + 0x3fc)
 
 #define RING_FORCE_TO_NONPRIV(base, i)		XE_REG(((base) + 0x4d0) + (i) * 4)
diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index da1f198ac107..181913967ac9 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -157,6 +157,7 @@
 #define XEHPG_SC_INSTDONE_EXTRA2		XE_REG_MCR(0x7108)
 
 #define COMMON_SLICE_CHICKEN4			XE_REG(0x7300, XE_REG_OPTION_MASKED)
+#define   SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE	REG_BIT(12)
 #define   DISABLE_TDC_LOAD_BALANCING_CALC	REG_BIT(6)
 
 #define COMMON_SLICE_CHICKEN3				XE_REG(0x7304, XE_REG_OPTION_MASKED)
diff --git a/drivers/gpu/drm/xe/regs/xe_lrc_layout.h b/drivers/gpu/drm/xe/regs/xe_lrc_layout.h
index 57944f90bbf6..994af591a2e8 100644
--- a/drivers/gpu/drm/xe/regs/xe_lrc_layout.h
+++ b/drivers/gpu/drm/xe/regs/xe_lrc_layout.h
@@ -11,7 +11,9 @@
 #define CTX_RING_TAIL			(0x06 + 1)
 #define CTX_RING_START			(0x08 + 1)
 #define CTX_RING_CTL			(0x0a + 1)
+#define CTX_BB_PER_CTX_PTR		(0x12 + 1)
 #define CTX_TIMESTAMP			(0x22 + 1)
+#define CTX_TIMESTAMP_UDW		(0x24 + 1)
 #define CTX_INDIRECT_RING_STATE		(0x26 + 1)
 #define CTX_PDP0_UDW			(0x30 + 1)
 #define CTX_PDP0_LDW			(0x32 + 1)
diff --git a/drivers/gpu/drm/xe/tests/xe_mocs.c b/drivers/gpu/drm/xe/tests/xe_mocs.c
index ef1e5256c56a..0e502feaca81 100644
--- a/drivers/gpu/drm/xe/tests/xe_mocs.c
+++ b/drivers/gpu/drm/xe/tests/xe_mocs.c
@@ -46,8 +46,11 @@ static void read_l3cc_table(struct xe_gt *gt,
 	unsigned int fw_ref, i;
 	u32 reg_val;
 
-	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
-	KUNIT_ASSERT_NE_MSG(test, fw_ref, 0, "Forcewake Failed.\n");
+	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
+	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) {
+		xe_force_wake_put(gt_to_fw(gt), fw_ref);
+		KUNIT_ASSERT_TRUE_MSG(test, true, "Forcewake Failed.\n");
+	}
 
 	for (i = 0; i < info->num_mocs_regs; i++) {
 		if (!(i & 1)) {
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 72ef0b6fc425..0482f26aa480 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -330,6 +330,8 @@ struct xe_device {
 		u8 has_sriov:1;
 		/** @info.has_usm: Device has unified shared memory support */
 		u8 has_usm:1;
+		/** @info.has_64bit_timestamp: Device supports 64-bit timestamps */
+		u8 has_64bit_timestamp:1;
 		/** @info.is_dgfx: is discrete device */
 		u8 is_dgfx:1;
 		/**
@@ -585,6 +587,7 @@ struct xe_device {
 			INTEL_DRAM_DDR5,
 			INTEL_DRAM_LPDDR5,
 			INTEL_DRAM_GDDR,
+			INTEL_DRAM_GDDR_ECC,
 		} type;
 		u8 num_qgv_points;
 		u8 num_psf_gv_points;
diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c
index f67803e15a0e..f7a20264ea33 100644
--- a/drivers/gpu/drm/xe/xe_dma_buf.c
+++ b/drivers/gpu/drm/xe/xe_dma_buf.c
@@ -145,10 +145,7 @@ static void xe_dma_buf_unmap(struct dma_buf_attachment *attach,
 			     struct sg_table *sgt,
 			     enum dma_data_direction dir)
 {
-	struct dma_buf *dma_buf = attach->dmabuf;
-	struct xe_bo *bo = gem_to_xe_bo(dma_buf->priv);
-
-	if (!xe_bo_is_vram(bo)) {
+	if (sg_page(sgt->sgl)) {
 		dma_unmap_sgtable(attach->dev, sgt, dir, 0);
 		sg_free_table(sgt);
 		kfree(sgt);
diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c
index f2bb9168967c..e2bb156c71fb 100644
--- a/drivers/gpu/drm/xe/xe_eu_stall.c
+++ b/drivers/gpu/drm/xe/xe_eu_stall.c
@@ -52,6 +52,8 @@ struct xe_eu_stall_data_stream {
 
 	struct xe_gt *gt;
 	struct xe_bo *bo;
+	/* Lock to protect data buffer pointers */
+	struct mutex xecore_buf_lock;
 	struct per_xecore_buf *xecore_buf;
 	struct {
 		bool reported_to_user;
@@ -208,6 +210,9 @@ int xe_eu_stall_init(struct xe_gt *gt)
 	struct xe_device *xe = gt_to_xe(gt);
 	int ret;
 
+	if (!xe_eu_stall_supported_on_platform(xe))
+		return 0;
+
 	gt->eu_stall = kzalloc(sizeof(*gt->eu_stall), GFP_KERNEL);
 	if (!gt->eu_stall) {
 		ret = -ENOMEM;
@@ -378,7 +383,7 @@ static bool eu_stall_data_buf_poll(struct xe_eu_stall_data_stream *stream)
 	u16 group, instance;
 	unsigned int xecore;
 
-	mutex_lock(&gt->eu_stall->stream_lock);
+	mutex_lock(&stream->xecore_buf_lock);
 	for_each_dss_steering(xecore, gt, group, instance) {
 		xecore_buf = &stream->xecore_buf[xecore];
 		read_ptr = xecore_buf->read;
@@ -396,7 +401,7 @@ static bool eu_stall_data_buf_poll(struct xe_eu_stall_data_stream *stream)
 			set_bit(xecore, stream->data_drop.mask);
 		xecore_buf->write = write_ptr;
 	}
-	mutex_unlock(&gt->eu_stall->stream_lock);
+	mutex_unlock(&stream->xecore_buf_lock);
 
 	return min_data_present;
 }
@@ -511,11 +516,13 @@ static ssize_t xe_eu_stall_stream_read_locked(struct xe_eu_stall_data_stream *st
 	unsigned int xecore;
 	int ret = 0;
 
+	mutex_lock(&stream->xecore_buf_lock);
 	if (bitmap_weight(stream->data_drop.mask, XE_MAX_DSS_FUSE_BITS)) {
 		if (!stream->data_drop.reported_to_user) {
 			stream->data_drop.reported_to_user = true;
 			xe_gt_dbg(gt, "EU stall data dropped in XeCores: %*pb\n",
 				  XE_MAX_DSS_FUSE_BITS, stream->data_drop.mask);
+			mutex_unlock(&stream->xecore_buf_lock);
 			return -EIO;
 		}
 		stream->data_drop.reported_to_user = false;
@@ -527,6 +534,7 @@ static ssize_t xe_eu_stall_stream_read_locked(struct xe_eu_stall_data_stream *st
 		if (ret || count == total_size)
 			break;
 	}
+	mutex_unlock(&stream->xecore_buf_lock);
 	return total_size ?: (ret ?: -EAGAIN);
 }
 
@@ -583,6 +591,7 @@ static void xe_eu_stall_stream_free(struct xe_eu_stall_data_stream *stream)
 {
 	struct xe_gt *gt = stream->gt;
 
+	mutex_destroy(&stream->xecore_buf_lock);
 	gt->eu_stall->stream = NULL;
 	kfree(stream);
 }
@@ -718,6 +727,7 @@ static int xe_eu_stall_stream_init(struct xe_eu_stall_data_stream *stream,
 	}
 
 	init_waitqueue_head(&stream->poll_wq);
+	mutex_init(&stream->xecore_buf_lock);
 	INIT_DELAYED_WORK(&stream->buf_poll_work, eu_stall_data_buf_poll_work_fn);
 	stream->per_xecore_buf_size = per_xecore_buf_size;
 	stream->sampling_rate_mult = props->sampling_rate_mult;
diff --git a/drivers/gpu/drm/xe/xe_eu_stall.h b/drivers/gpu/drm/xe/xe_eu_stall.h
index ed9d0f233566..d1c76e503799 100644
--- a/drivers/gpu/drm/xe/xe_eu_stall.h
+++ b/drivers/gpu/drm/xe/xe_eu_stall.h
@@ -7,6 +7,7 @@
 #define __XE_EU_STALL_H__
 
 #include "xe_gt_types.h"
+#include "xe_sriov.h"
 
 size_t xe_eu_stall_get_per_xecore_buf_size(void);
 size_t xe_eu_stall_data_record_size(struct xe_device *xe);
@@ -19,6 +20,6 @@ int xe_eu_stall_stream_open(struct drm_device *dev,
 
 static inline bool xe_eu_stall_supported_on_platform(struct xe_device *xe)
 {
-	return xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20;
+	return !IS_SRIOV_VF(xe) && (xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20);
 }
 #endif
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 606922d9dd73..cd9b1c32f30f 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -830,7 +830,7 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 {
 	struct xe_device *xe = gt_to_xe(q->gt);
 	struct xe_lrc *lrc;
-	u32 old_ts, new_ts;
+	u64 old_ts, new_ts;
 	int idx;
 
 	/*
diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c
index fd41113f8572..0bcf97063ff6 100644
--- a/drivers/gpu/drm/xe/xe_gsc.c
+++ b/drivers/gpu/drm/xe/xe_gsc.c
@@ -555,6 +555,28 @@ void xe_gsc_wait_for_worker_completion(struct xe_gsc *gsc)
 		flush_work(&gsc->work);
 }
 
+void xe_gsc_stop_prepare(struct xe_gsc *gsc)
+{
+	struct xe_gt *gt = gsc_to_gt(gsc);
+	int ret;
+
+	if (!xe_uc_fw_is_loadable(&gsc->fw) || xe_uc_fw_is_in_error_state(&gsc->fw))
+		return;
+
+	xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GSC);
+
+	/*
+	 * If the GSC FW load or the proxy init are interrupted, the only way
+	 * to recover it is to do an FLR and reload the GSC from scratch.
+	 * Therefore, let's wait for the init to complete before stopping
+	 * operations. The proxy init is the last step, so we can just wait on
+	 * that
+	 */
+	ret = xe_gsc_wait_for_proxy_init_done(gsc);
+	if (ret)
+		xe_gt_err(gt, "failed to wait for GSC init completion before uc stop\n");
+}
+
 /*
  * wa_14015076503: if the GSC FW is loaded, we need to alert it before doing a
  * GSC engine reset by writing a notification bit in the GS1 register and then
diff --git a/drivers/gpu/drm/xe/xe_gsc.h b/drivers/gpu/drm/xe/xe_gsc.h
index d99f66c38075..b8b8e0810ad9 100644
--- a/drivers/gpu/drm/xe/xe_gsc.h
+++ b/drivers/gpu/drm/xe/xe_gsc.h
@@ -16,6 +16,7 @@ struct xe_hw_engine;
 int xe_gsc_init(struct xe_gsc *gsc);
 int xe_gsc_init_post_hwconfig(struct xe_gsc *gsc);
 void xe_gsc_wait_for_worker_completion(struct xe_gsc *gsc);
+void xe_gsc_stop_prepare(struct xe_gsc *gsc);
 void xe_gsc_load_start(struct xe_gsc *gsc);
 void xe_gsc_hwe_irq_handler(struct xe_hw_engine *hwe, u16 intr_vec);
 
diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.c b/drivers/gpu/drm/xe/xe_gsc_proxy.c
index 8cf70b228ff3..d0519cd6704a 100644
--- a/drivers/gpu/drm/xe/xe_gsc_proxy.c
+++ b/drivers/gpu/drm/xe/xe_gsc_proxy.c
@@ -71,6 +71,17 @@ bool xe_gsc_proxy_init_done(struct xe_gsc *gsc)
 	       HECI1_FWSTS1_PROXY_STATE_NORMAL;
 }
 
+int xe_gsc_wait_for_proxy_init_done(struct xe_gsc *gsc)
+{
+	struct xe_gt *gt = gsc_to_gt(gsc);
+
+	/* Proxy init can take up to 500ms, so wait double that for safety */
+	return xe_mmio_wait32(&gt->mmio, HECI_FWSTS1(MTL_GSC_HECI1_BASE),
+			      HECI1_FWSTS1_CURRENT_STATE,
+			      HECI1_FWSTS1_PROXY_STATE_NORMAL,
+			      USEC_PER_SEC, NULL, false);
+}
+
 static void __gsc_proxy_irq_rmw(struct xe_gsc *gsc, u32 clr, u32 set)
 {
 	struct xe_gt *gt = gsc_to_gt(gsc);
diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.h b/drivers/gpu/drm/xe/xe_gsc_proxy.h
index fdef56995cd4..765602221dbc 100644
--- a/drivers/gpu/drm/xe/xe_gsc_proxy.h
+++ b/drivers/gpu/drm/xe/xe_gsc_proxy.h
@@ -12,6 +12,7 @@ struct xe_gsc;
 
 int xe_gsc_proxy_init(struct xe_gsc *gsc);
 bool xe_gsc_proxy_init_done(struct xe_gsc *gsc);
+int xe_gsc_wait_for_proxy_init_done(struct xe_gsc *gsc);
 int xe_gsc_proxy_start(struct xe_gsc *gsc);
 
 int xe_gsc_proxy_request_handler(struct xe_gsc *gsc);
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 10a9e3c72b36..66198cf2662c 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -857,7 +857,7 @@ void xe_gt_suspend_prepare(struct xe_gt *gt)
 
 	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
 
-	xe_uc_stop_prepare(&gt->uc);
+	xe_uc_suspend_prepare(&gt->uc);
 
 	xe_force_wake_put(gt_to_fw(gt), fw_ref);
 }
diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c
index 2d63a69cbfa3..f7005a3643e6 100644
--- a/drivers/gpu/drm/xe/xe_gt_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c
@@ -92,22 +92,23 @@ static int hw_engines(struct xe_gt *gt, struct drm_printer *p)
 	struct xe_hw_engine *hwe;
 	enum xe_hw_engine_id id;
 	unsigned int fw_ref;
+	int ret = 0;
 
 	xe_pm_runtime_get(xe);
 	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
 	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) {
-		xe_pm_runtime_put(xe);
-		xe_force_wake_put(gt_to_fw(gt), fw_ref);
-		return -ETIMEDOUT;
+		ret = -ETIMEDOUT;
+		goto fw_put;
 	}
 
 	for_each_hw_engine(hwe, gt, id)
 		xe_hw_engine_print(hwe, p);
 
+fw_put:
 	xe_force_wake_put(gt_to_fw(gt), fw_ref);
 	xe_pm_runtime_put(xe);
 
-	return 0;
+	return ret;
 }
 
 static int powergate_info(struct xe_gt *gt, struct drm_printer *p)
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index c5ad9a0a89c2..0c22b3a36655 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -435,9 +435,16 @@ static int xe_alloc_pf_queue(struct xe_gt *gt, struct pf_queue *pf_queue)
 	num_eus = bitmap_weight(gt->fuse_topo.eu_mask_per_dss,
 				XE_MAX_EU_FUSE_BITS) * num_dss;
 
-	/* user can issue separate page faults per EU and per CS */
+	/*
+	 * user can issue separate page faults per EU and per CS
+	 *
+	 * XXX: Multiplier required as compute UMD are getting PF queue errors
+	 * without it. Follow on why this multiplier is required.
+	 */
+#define PF_MULTIPLIER	8
 	pf_queue->num_dw =
-		(num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW;
+		(num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW * PF_MULTIPLIER;
+#undef PF_MULTIPLIER
 
 	pf_queue->gt = gt;
 	pf_queue->data = devm_kcalloc(xe->drm.dev, pf_queue->num_dw,
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 03072e094991..084cbdeba8ea 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -322,6 +322,13 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
 	return 0;
 }
 
+/*
+ * Ensure that roundup_pow_of_two(length) doesn't overflow.
+ * Note that roundup_pow_of_two() operates on unsigned long,
+ * not on u64.
+ */
+#define MAX_RANGE_TLB_INVALIDATION_LENGTH (rounddown_pow_of_two(ULONG_MAX))
+
 /**
  * xe_gt_tlb_invalidation_range - Issue a TLB invalidation on this GT for an
  * address range
@@ -346,6 +353,7 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
 	struct xe_device *xe = gt_to_xe(gt);
 #define MAX_TLB_INVALIDATION_LEN	7
 	u32 action[MAX_TLB_INVALIDATION_LEN];
+	u64 length = end - start;
 	int len = 0;
 
 	xe_gt_assert(gt, fence);
@@ -358,11 +366,11 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
 
 	action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
 	action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */
-	if (!xe->info.has_range_tlb_invalidation) {
+	if (!xe->info.has_range_tlb_invalidation ||
+	    length > MAX_RANGE_TLB_INVALIDATION_LENGTH) {
 		action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL);
 	} else {
 		u64 orig_start = start;
-		u64 length = end - start;
 		u64 align;
 
 		if (length < SZ_4K)
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index e7c9e095a19f..7031542a70ce 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -490,24 +490,52 @@ static void fill_engine_enable_masks(struct xe_gt *gt,
 		       engine_enable_mask(gt, XE_ENGINE_CLASS_OTHER));
 }
 
-static void guc_prep_golden_lrc_null(struct xe_guc_ads *ads)
+/*
+ * Write the offsets corresponding to the golden LRCs. The actual data is
+ * populated later by guc_golden_lrc_populate()
+ */
+static void guc_golden_lrc_init(struct xe_guc_ads *ads)
 {
 	struct xe_device *xe = ads_to_xe(ads);
+	struct xe_gt *gt = ads_to_gt(ads);
 	struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
 			offsetof(struct __guc_ads_blob, system_info));
-	u8 guc_class;
+	size_t alloc_size, real_size;
+	u32 addr_ggtt, offset;
+	int class;
+
+	offset = guc_ads_golden_lrc_offset(ads);
+	addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset;
+
+	for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) {
+		u8 guc_class;
+
+		guc_class = xe_engine_class_to_guc_class(class);
 
-	for (guc_class = 0; guc_class <= GUC_MAX_ENGINE_CLASSES; ++guc_class) {
 		if (!info_map_read(xe, &info_map,
 				   engine_enabled_masks[guc_class]))
 			continue;
 
+		real_size = xe_gt_lrc_size(gt, class);
+		alloc_size = PAGE_ALIGN(real_size);
+
+		/*
+		 * This interface is slightly confusing. We need to pass the
+		 * base address of the full golden context and the size of just
+		 * the engine state, which is the section of the context image
+		 * that starts after the execlists LRC registers. This is
+		 * required to allow the GuC to restore just the engine state
+		 * when a watchdog reset occurs.
+		 * We calculate the engine state size by removing the size of
+		 * what comes before it in the context image (which is identical
+		 * on all engines).
+		 */
 		ads_blob_write(ads, ads.eng_state_size[guc_class],
-			       guc_ads_golden_lrc_size(ads) -
-			       xe_lrc_skip_size(xe));
+			       real_size - xe_lrc_skip_size(xe));
 		ads_blob_write(ads, ads.golden_context_lrca[guc_class],
-			       xe_bo_ggtt_addr(ads->bo) +
-			       guc_ads_golden_lrc_offset(ads));
+			       addr_ggtt);
+
+		addr_ggtt += alloc_size;
 	}
 }
 
@@ -857,7 +885,7 @@ void xe_guc_ads_populate_minimal(struct xe_guc_ads *ads)
 
 	xe_map_memset(ads_to_xe(ads), ads_to_map(ads), 0, 0, ads->bo->size);
 	guc_policies_init(ads);
-	guc_prep_golden_lrc_null(ads);
+	guc_golden_lrc_init(ads);
 	guc_mapping_table_init_invalid(gt, &info_map);
 	guc_doorbell_init(ads);
 
@@ -883,7 +911,7 @@ void xe_guc_ads_populate(struct xe_guc_ads *ads)
 	guc_policies_init(ads);
 	fill_engine_enable_masks(gt, &info_map);
 	guc_mmio_reg_state_init(ads);
-	guc_prep_golden_lrc_null(ads);
+	guc_golden_lrc_init(ads);
 	guc_mapping_table_init(gt, &info_map);
 	guc_capture_prep_lists(ads);
 	guc_doorbell_init(ads);
@@ -903,18 +931,22 @@ void xe_guc_ads_populate(struct xe_guc_ads *ads)
 		       guc_ads_private_data_offset(ads));
 }
 
-static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
+/*
+ * After the golden LRC's are recorded for each engine class by the first
+ * submission, copy them to the ADS, as initialized earlier by
+ * guc_golden_lrc_init().
+ */
+static void guc_golden_lrc_populate(struct xe_guc_ads *ads)
 {
 	struct xe_device *xe = ads_to_xe(ads);
 	struct xe_gt *gt = ads_to_gt(ads);
 	struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
 			offsetof(struct __guc_ads_blob, system_info));
 	size_t total_size = 0, alloc_size, real_size;
-	u32 addr_ggtt, offset;
+	u32 offset;
 	int class;
 
 	offset = guc_ads_golden_lrc_offset(ads);
-	addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset;
 
 	for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) {
 		u8 guc_class;
@@ -931,26 +963,9 @@ static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
 		alloc_size = PAGE_ALIGN(real_size);
 		total_size += alloc_size;
 
-		/*
-		 * This interface is slightly confusing. We need to pass the
-		 * base address of the full golden context and the size of just
-		 * the engine state, which is the section of the context image
-		 * that starts after the execlists LRC registers. This is
-		 * required to allow the GuC to restore just the engine state
-		 * when a watchdog reset occurs.
-		 * We calculate the engine state size by removing the size of
-		 * what comes before it in the context image (which is identical
-		 * on all engines).
-		 */
-		ads_blob_write(ads, ads.eng_state_size[guc_class],
-			       real_size - xe_lrc_skip_size(xe));
-		ads_blob_write(ads, ads.golden_context_lrca[guc_class],
-			       addr_ggtt);
-
 		xe_map_memcpy_to(xe, ads_to_map(ads), offset,
 				 gt->default_lrc[class], real_size);
 
-		addr_ggtt += alloc_size;
 		offset += alloc_size;
 	}
 
@@ -959,7 +974,7 @@ static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
 
 void xe_guc_ads_populate_post_load(struct xe_guc_ads *ads)
 {
-	guc_populate_golden_lrc(ads);
+	guc_golden_lrc_populate(ads);
 }
 
 static int guc_ads_action_update_policies(struct xe_guc_ads *ads, u32 policy_offset)
diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c
index f6d523e4c5fe..9095618648bc 100644
--- a/drivers/gpu/drm/xe/xe_guc_capture.c
+++ b/drivers/gpu/drm/xe/xe_guc_capture.c
@@ -359,7 +359,7 @@ static void __fill_ext_reg(struct __guc_mmio_reg_descr *ext,
 
 	ext->reg = XE_REG(extlist->reg.__reg.addr);
 	ext->flags = FIELD_PREP(GUC_REGSET_STEERING_NEEDED, 1);
-	ext->flags = FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id);
+	ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id);
 	ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, subslice_id);
 	ext->regname = extlist->name;
 }
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 85215313976c..43b1192ba61c 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -1070,6 +1070,7 @@ int xe_guc_pc_start(struct xe_guc_pc *pc)
 		if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING,
 				      SLPC_RESET_EXTENDED_TIMEOUT_MS)) {
 			xe_gt_err(gt, "GuC PC Start failed: Dynamic GT frequency control and GT sleep states are now disabled.\n");
+			ret = -EIO;
 			goto out;
 		}
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 31bc2022bfc2..769781d577df 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -941,7 +941,7 @@ static bool check_timeout(struct xe_exec_queue *q, struct xe_sched_job *job)
 		return xe_sched_invalidate_job(job, 2);
 	}
 
-	ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]);
+	ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(q->lrc[0]));
 	ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]);
 
 	/*
diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index c3cc0fa105e8..57b71956ddf4 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -19,29 +19,6 @@ static u64 xe_npages_in_range(unsigned long start, unsigned long end)
 	return (end - start) >> PAGE_SHIFT;
 }
 
-/**
- * xe_mark_range_accessed() - mark a range is accessed, so core mm
- * have such information for memory eviction or write back to
- * hard disk
- * @range: the range to mark
- * @write: if write to this range, we mark pages in this range
- * as dirty
- */
-static void xe_mark_range_accessed(struct hmm_range *range, bool write)
-{
-	struct page *page;
-	u64 i, npages;
-
-	npages = xe_npages_in_range(range->start, range->end);
-	for (i = 0; i < npages; i++) {
-		page = hmm_pfn_to_page(range->hmm_pfns[i]);
-		if (write)
-			set_page_dirty_lock(page);
-
-		mark_page_accessed(page);
-	}
-}
-
 static int xe_alloc_sg(struct xe_device *xe, struct sg_table *st,
 		       struct hmm_range *range, struct rw_semaphore *notifier_sem)
 {
@@ -331,7 +308,6 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 	if (ret)
 		goto out_unlock;
 
-	xe_mark_range_accessed(&hmm_range, write);
 	userptr->sg = &userptr->sgt;
 	xe_hmm_userptr_set_mapped(uvma);
 	userptr->notifier_seq = hmm_range.notifier_seq;
diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
index 8c05fd30b7df..93241fd0a4ba 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine.c
@@ -389,12 +389,6 @@ xe_hw_engine_setup_default_lrc_state(struct xe_hw_engine *hwe)
 				 blit_cctl_val,
 				 XE_RTP_ACTION_FLAG(ENGINE_BASE)))
 		},
-		/* Use Fixed slice CCS mode */
-		{ XE_RTP_NAME("RCU_MODE_FIXED_SLICE_CCS_MODE"),
-		  XE_RTP_RULES(FUNC(xe_hw_engine_match_fixed_cslice_mode)),
-		  XE_RTP_ACTIONS(FIELD_SET(RCU_MODE, RCU_MODE_FIXED_SLICE_CCS_MODE,
-					   RCU_MODE_FIXED_SLICE_CCS_MODE))
-		},
 		/* Disable WMTP if HW doesn't support it */
 		{ XE_RTP_NAME("DISABLE_WMTP_ON_UNSUPPORTED_HW"),
 		  XE_RTP_RULES(FUNC(xe_rtp_cfeg_wmtp_disabled)),
@@ -461,6 +455,12 @@ hw_engine_setup_default_state(struct xe_hw_engine *hwe)
 		  XE_RTP_ACTIONS(SET(CSFE_CHICKEN1(0), CS_PRIORITY_MEM_READ,
 				     XE_RTP_ACTION_FLAG(ENGINE_BASE)))
 		},
+		/* Use Fixed slice CCS mode */
+		{ XE_RTP_NAME("RCU_MODE_FIXED_SLICE_CCS_MODE"),
+		  XE_RTP_RULES(FUNC(xe_hw_engine_match_fixed_cslice_mode)),
+		  XE_RTP_ACTIONS(FIELD_SET(RCU_MODE, RCU_MODE_FIXED_SLICE_CCS_MODE,
+					   RCU_MODE_FIXED_SLICE_CCS_MODE))
+		},
 	};
 
 	xe_rtp_process_to_sr(&ctx, engine_entries, ARRAY_SIZE(engine_entries), &hwe->reg_sr);
diff --git a/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c b/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c
index b53e8d2accdb..a440442b4d72 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c
@@ -32,14 +32,61 @@ bool xe_hw_engine_timeout_in_range(u64 timeout, u64 min, u64 max)
 	return timeout >= min && timeout <= max;
 }
 
-static void kobj_xe_hw_engine_release(struct kobject *kobj)
+static void xe_hw_engine_sysfs_kobj_release(struct kobject *kobj)
 {
 	kfree(kobj);
 }
 
+static ssize_t xe_hw_engine_class_sysfs_attr_show(struct kobject *kobj,
+						  struct attribute *attr,
+						  char *buf)
+{
+	struct xe_device *xe = kobj_to_xe(kobj);
+	struct kobj_attribute *kattr;
+	ssize_t ret = -EIO;
+
+	kattr = container_of(attr, struct kobj_attribute, attr);
+	if (kattr->show) {
+		xe_pm_runtime_get(xe);
+		ret = kattr->show(kobj, kattr, buf);
+		xe_pm_runtime_put(xe);
+	}
+
+	return ret;
+}
+
+static ssize_t xe_hw_engine_class_sysfs_attr_store(struct kobject *kobj,
+						   struct attribute *attr,
+						   const char *buf,
+						   size_t count)
+{
+	struct xe_device *xe = kobj_to_xe(kobj);
+	struct kobj_attribute *kattr;
+	ssize_t ret = -EIO;
+
+	kattr = container_of(attr, struct kobj_attribute, attr);
+	if (kattr->store) {
+		xe_pm_runtime_get(xe);
+		ret = kattr->store(kobj, kattr, buf, count);
+		xe_pm_runtime_put(xe);
+	}
+
+	return ret;
+}
+
+static const struct sysfs_ops xe_hw_engine_class_sysfs_ops = {
+	.show = xe_hw_engine_class_sysfs_attr_show,
+	.store = xe_hw_engine_class_sysfs_attr_store,
+};
+
 static const struct kobj_type kobj_xe_hw_engine_type = {
-	.release = kobj_xe_hw_engine_release,
-	.sysfs_ops = &kobj_sysfs_ops
+	.release = xe_hw_engine_sysfs_kobj_release,
+	.sysfs_ops = &xe_hw_engine_class_sysfs_ops,
+};
+
+static const struct kobj_type kobj_xe_hw_engine_type_def = {
+	.release = xe_hw_engine_sysfs_kobj_release,
+	.sysfs_ops = &kobj_sysfs_ops,
 };
 
 static ssize_t job_timeout_max_store(struct kobject *kobj,
@@ -543,7 +590,7 @@ static int xe_add_hw_engine_class_defaults(struct xe_device *xe,
 	if (!kobj)
 		return -ENOMEM;
 
-	kobject_init(kobj, &kobj_xe_hw_engine_type);
+	kobject_init(kobj, &kobj_xe_hw_engine_type_def);
 	err = kobject_add(kobj, parent, "%s", ".defaults");
 	if (err)
 		goto err_object;
@@ -559,57 +606,6 @@ err_object:
 	return err;
 }
 
-static void xe_hw_engine_sysfs_kobj_release(struct kobject *kobj)
-{
-	kfree(kobj);
-}
-
-static ssize_t xe_hw_engine_class_sysfs_attr_show(struct kobject *kobj,
-						  struct attribute *attr,
-						  char *buf)
-{
-	struct xe_device *xe = kobj_to_xe(kobj);
-	struct kobj_attribute *kattr;
-	ssize_t ret = -EIO;
-
-	kattr = container_of(attr, struct kobj_attribute, attr);
-	if (kattr->show) {
-		xe_pm_runtime_get(xe);
-		ret = kattr->show(kobj, kattr, buf);
-		xe_pm_runtime_put(xe);
-	}
-
-	return ret;
-}
-
-static ssize_t xe_hw_engine_class_sysfs_attr_store(struct kobject *kobj,
-						   struct attribute *attr,
-						   const char *buf,
-						   size_t count)
-{
-	struct xe_device *xe = kobj_to_xe(kobj);
-	struct kobj_attribute *kattr;
-	ssize_t ret = -EIO;
-
-	kattr = container_of(attr, struct kobj_attribute, attr);
-	if (kattr->store) {
-		xe_pm_runtime_get(xe);
-		ret = kattr->store(kobj, kattr, buf, count);
-		xe_pm_runtime_put(xe);
-	}
-
-	return ret;
-}
-
-static const struct sysfs_ops xe_hw_engine_class_sysfs_ops = {
-	.show = xe_hw_engine_class_sysfs_attr_show,
-	.store = xe_hw_engine_class_sysfs_attr_store,
-};
-
-static const struct kobj_type xe_hw_engine_sysfs_kobj_type = {
-	.release = xe_hw_engine_sysfs_kobj_release,
-	.sysfs_ops = &xe_hw_engine_class_sysfs_ops,
-};
 
 static void hw_engine_class_sysfs_fini(void *arg)
 {
@@ -640,7 +636,7 @@ int xe_hw_engine_class_sysfs_init(struct xe_gt *gt)
 	if (!kobj)
 		return -ENOMEM;
 
-	kobject_init(kobj, &xe_hw_engine_sysfs_kobj_type);
+	kobject_init(kobj, &kobj_xe_hw_engine_type);
 
 	err = kobject_add(kobj, gt->sysfs, "engines");
 	if (err)
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index df3ceddede07..03bfba696b37 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -24,6 +24,7 @@
 #include "xe_hw_fence.h"
 #include "xe_map.h"
 #include "xe_memirq.h"
+#include "xe_mmio.h"
 #include "xe_sriov.h"
 #include "xe_trace_lrc.h"
 #include "xe_vm.h"
@@ -650,6 +651,7 @@ u32 xe_lrc_pphwsp_offset(struct xe_lrc *lrc)
 #define LRC_START_SEQNO_PPHWSP_OFFSET (LRC_SEQNO_PPHWSP_OFFSET + 8)
 #define LRC_CTX_JOB_TIMESTAMP_OFFSET (LRC_START_SEQNO_PPHWSP_OFFSET + 8)
 #define LRC_PARALLEL_PPHWSP_OFFSET 2048
+#define LRC_ENGINE_ID_PPHWSP_OFFSET 2096
 #define LRC_PPHWSP_SIZE SZ_4K
 
 u32 xe_lrc_regs_offset(struct xe_lrc *lrc)
@@ -684,7 +686,7 @@ static inline u32 __xe_lrc_start_seqno_offset(struct xe_lrc *lrc)
 
 static u32 __xe_lrc_ctx_job_timestamp_offset(struct xe_lrc *lrc)
 {
-	/* The start seqno is stored in the driver-defined portion of PPHWSP */
+	/* This is stored in the driver-defined portion of PPHWSP */
 	return xe_lrc_pphwsp_offset(lrc) + LRC_CTX_JOB_TIMESTAMP_OFFSET;
 }
 
@@ -694,11 +696,21 @@ static inline u32 __xe_lrc_parallel_offset(struct xe_lrc *lrc)
 	return xe_lrc_pphwsp_offset(lrc) + LRC_PARALLEL_PPHWSP_OFFSET;
 }
 
+static inline u32 __xe_lrc_engine_id_offset(struct xe_lrc *lrc)
+{
+	return xe_lrc_pphwsp_offset(lrc) + LRC_ENGINE_ID_PPHWSP_OFFSET;
+}
+
 static u32 __xe_lrc_ctx_timestamp_offset(struct xe_lrc *lrc)
 {
 	return __xe_lrc_regs_offset(lrc) + CTX_TIMESTAMP * sizeof(u32);
 }
 
+static u32 __xe_lrc_ctx_timestamp_udw_offset(struct xe_lrc *lrc)
+{
+	return __xe_lrc_regs_offset(lrc) + CTX_TIMESTAMP_UDW * sizeof(u32);
+}
+
 static inline u32 __xe_lrc_indirect_ring_offset(struct xe_lrc *lrc)
 {
 	/* Indirect ring state page is at the very end of LRC */
@@ -726,8 +738,10 @@ DECL_MAP_ADDR_HELPERS(regs)
 DECL_MAP_ADDR_HELPERS(start_seqno)
 DECL_MAP_ADDR_HELPERS(ctx_job_timestamp)
 DECL_MAP_ADDR_HELPERS(ctx_timestamp)
+DECL_MAP_ADDR_HELPERS(ctx_timestamp_udw)
 DECL_MAP_ADDR_HELPERS(parallel)
 DECL_MAP_ADDR_HELPERS(indirect_ring)
+DECL_MAP_ADDR_HELPERS(engine_id)
 
 #undef DECL_MAP_ADDR_HELPERS
 
@@ -743,18 +757,37 @@ u32 xe_lrc_ctx_timestamp_ggtt_addr(struct xe_lrc *lrc)
 }
 
 /**
+ * xe_lrc_ctx_timestamp_udw_ggtt_addr() - Get ctx timestamp udw GGTT address
+ * @lrc: Pointer to the lrc.
+ *
+ * Returns: ctx timestamp udw GGTT address
+ */
+u32 xe_lrc_ctx_timestamp_udw_ggtt_addr(struct xe_lrc *lrc)
+{
+	return __xe_lrc_ctx_timestamp_udw_ggtt_addr(lrc);
+}
+
+/**
  * xe_lrc_ctx_timestamp() - Read ctx timestamp value
  * @lrc: Pointer to the lrc.
  *
  * Returns: ctx timestamp value
  */
-u32 xe_lrc_ctx_timestamp(struct xe_lrc *lrc)
+u64 xe_lrc_ctx_timestamp(struct xe_lrc *lrc)
 {
 	struct xe_device *xe = lrc_to_xe(lrc);
 	struct iosys_map map;
+	u32 ldw, udw = 0;
 
 	map = __xe_lrc_ctx_timestamp_map(lrc);
-	return xe_map_read32(xe, &map);
+	ldw = xe_map_read32(xe, &map);
+
+	if (xe->info.has_64bit_timestamp) {
+		map = __xe_lrc_ctx_timestamp_udw_map(lrc);
+		udw = xe_map_read32(xe, &map);
+	}
+
+	return (u64)udw << 32 | ldw;
 }
 
 /**
@@ -864,7 +897,7 @@ static void *empty_lrc_data(struct xe_hw_engine *hwe)
 
 static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm)
 {
-	u64 desc = xe_vm_pdp4_descriptor(vm, lrc->tile);
+	u64 desc = xe_vm_pdp4_descriptor(vm, gt_to_tile(lrc->gt));
 
 	xe_lrc_write_ctx_reg(lrc, CTX_PDP0_UDW, upper_32_bits(desc));
 	xe_lrc_write_ctx_reg(lrc, CTX_PDP0_LDW, lower_32_bits(desc));
@@ -877,6 +910,65 @@ static void xe_lrc_finish(struct xe_lrc *lrc)
 	xe_bo_unpin(lrc->bo);
 	xe_bo_unlock(lrc->bo);
 	xe_bo_put(lrc->bo);
+	xe_bo_unpin_map_no_vm(lrc->bb_per_ctx_bo);
+}
+
+/*
+ * xe_lrc_setup_utilization() - Setup wa bb to assist in calculating active
+ * context run ticks.
+ * @lrc: Pointer to the lrc.
+ *
+ * Context Timestamp (CTX_TIMESTAMP) in the LRC accumulates the run ticks of the
+ * context, but only gets updated when the context switches out. In order to
+ * check how long a context has been active before it switches out, two things
+ * are required:
+ *
+ * (1) Determine if the context is running:
+ * To do so, we program the WA BB to set an initial value for CTX_TIMESTAMP in
+ * the LRC. The value chosen is 1 since 0 is the initial value when the LRC is
+ * initialized. During a query, we just check for this value to determine if the
+ * context is active. If the context switched out, it would overwrite this
+ * location with the actual CTX_TIMESTAMP MMIO value. Note that WA BB runs as
+ * the last part of context restore, so reusing this LRC location will not
+ * clobber anything.
+ *
+ * (2) Calculate the time that the context has been active for:
+ * The CTX_TIMESTAMP ticks only when the context is active. If a context is
+ * active, we just use the CTX_TIMESTAMP MMIO as the new value of utilization.
+ * While doing so, we need to read the CTX_TIMESTAMP MMIO for the specific
+ * engine instance. Since we do not know which instance the context is running
+ * on until it is scheduled, we also read the ENGINE_ID MMIO in the WA BB and
+ * store it in the PPHSWP.
+ */
+#define CONTEXT_ACTIVE 1ULL
+static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
+{
+	u32 *cmd;
+
+	cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+
+	*cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
+	*cmd++ = ENGINE_ID(0).addr;
+	*cmd++ = __xe_lrc_engine_id_ggtt_addr(lrc);
+	*cmd++ = 0;
+
+	*cmd++ = MI_STORE_DATA_IMM | MI_SDI_GGTT | MI_SDI_NUM_DW(1);
+	*cmd++ = __xe_lrc_ctx_timestamp_ggtt_addr(lrc);
+	*cmd++ = 0;
+	*cmd++ = lower_32_bits(CONTEXT_ACTIVE);
+
+	if (lrc_to_xe(lrc)->info.has_64bit_timestamp) {
+		*cmd++ = MI_STORE_DATA_IMM | MI_SDI_GGTT | MI_SDI_NUM_DW(1);
+		*cmd++ = __xe_lrc_ctx_timestamp_udw_ggtt_addr(lrc);
+		*cmd++ = 0;
+		*cmd++ = upper_32_bits(CONTEXT_ACTIVE);
+	}
+
+	*cmd++ = MI_BATCH_BUFFER_END;
+
+	xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR,
+			     xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1);
+
 }
 
 #define PVC_CTX_ASID		(0x2e + 1)
@@ -893,31 +985,40 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	void *init_data = NULL;
 	u32 arb_enable;
 	u32 lrc_size;
+	u32 bo_flags;
 	int err;
 
 	kref_init(&lrc->refcount);
+	lrc->gt = gt;
 	lrc->flags = 0;
 	lrc_size = ring_size + xe_gt_lrc_size(gt, hwe->class);
 	if (xe_gt_has_indirect_ring_state(gt))
 		lrc->flags |= XE_LRC_FLAG_INDIRECT_RING_STATE;
 
+	bo_flags = XE_BO_FLAG_VRAM_IF_DGFX(tile) | XE_BO_FLAG_GGTT |
+		   XE_BO_FLAG_GGTT_INVALIDATE;
+
 	/*
 	 * FIXME: Perma-pinning LRC as we don't yet support moving GGTT address
 	 * via VM bind calls.
 	 */
 	lrc->bo = xe_bo_create_pin_map(xe, tile, vm, lrc_size,
 				       ttm_bo_type_kernel,
-				       XE_BO_FLAG_VRAM_IF_DGFX(tile) |
-				       XE_BO_FLAG_GGTT |
-				       XE_BO_FLAG_GGTT_INVALIDATE);
+				       bo_flags);
 	if (IS_ERR(lrc->bo))
 		return PTR_ERR(lrc->bo);
 
+	lrc->bb_per_ctx_bo = xe_bo_create_pin_map(xe, tile, NULL, SZ_4K,
+						  ttm_bo_type_kernel,
+						  bo_flags);
+	if (IS_ERR(lrc->bb_per_ctx_bo)) {
+		err = PTR_ERR(lrc->bb_per_ctx_bo);
+		goto err_lrc_finish;
+	}
+
 	lrc->size = lrc_size;
-	lrc->tile = gt_to_tile(hwe->gt);
 	lrc->ring.size = ring_size;
 	lrc->ring.tail = 0;
-	lrc->ctx_timestamp = 0;
 
 	xe_hw_fence_ctx_init(&lrc->fence_ctx, hwe->gt,
 			     hwe->fence_irq, hwe->name);
@@ -990,7 +1091,10 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 				     xe_lrc_read_ctx_reg(lrc, CTX_CONTEXT_CONTROL) |
 				     _MASKED_BIT_ENABLE(CTX_CTRL_PXP_ENABLE));
 
+	lrc->ctx_timestamp = 0;
 	xe_lrc_write_ctx_reg(lrc, CTX_TIMESTAMP, 0);
+	if (lrc_to_xe(lrc)->info.has_64bit_timestamp)
+		xe_lrc_write_ctx_reg(lrc, CTX_TIMESTAMP_UDW, 0);
 
 	if (xe->info.has_asid && vm)
 		xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, vm->usm.asid);
@@ -1019,6 +1123,8 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	map = __xe_lrc_start_seqno_map(lrc);
 	xe_map_write32(lrc_to_xe(lrc), &map, lrc->fence_ctx.next_seqno - 1);
 
+	xe_lrc_setup_utilization(lrc);
+
 	return 0;
 
 err_lrc_finish:
@@ -1238,6 +1344,21 @@ struct iosys_map xe_lrc_parallel_map(struct xe_lrc *lrc)
 	return __xe_lrc_parallel_map(lrc);
 }
 
+/**
+ * xe_lrc_engine_id() - Read engine id value
+ * @lrc: Pointer to the lrc.
+ *
+ * Returns: context id value
+ */
+static u32 xe_lrc_engine_id(struct xe_lrc *lrc)
+{
+	struct xe_device *xe = lrc_to_xe(lrc);
+	struct iosys_map map;
+
+	map = __xe_lrc_engine_id_map(lrc);
+	return xe_map_read32(xe, &map);
+}
+
 static int instr_dw(u32 cmd_header)
 {
 	/* GFXPIPE "SINGLE_DW" opcodes are a single dword */
@@ -1684,7 +1805,7 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc)
 	snapshot->lrc_offset = xe_lrc_pphwsp_offset(lrc);
 	snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset;
 	snapshot->lrc_snapshot = NULL;
-	snapshot->ctx_timestamp = xe_lrc_ctx_timestamp(lrc);
+	snapshot->ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(lrc));
 	snapshot->ctx_job_timestamp = xe_lrc_ctx_job_timestamp(lrc);
 	return snapshot;
 }
@@ -1784,22 +1905,74 @@ void xe_lrc_snapshot_free(struct xe_lrc_snapshot *snapshot)
 	kfree(snapshot);
 }
 
+static int get_ctx_timestamp(struct xe_lrc *lrc, u32 engine_id, u64 *reg_ctx_ts)
+{
+	u16 class = REG_FIELD_GET(ENGINE_CLASS_ID, engine_id);
+	u16 instance = REG_FIELD_GET(ENGINE_INSTANCE_ID, engine_id);
+	struct xe_hw_engine *hwe;
+	u64 val;
+
+	hwe = xe_gt_hw_engine(lrc->gt, class, instance, false);
+	if (xe_gt_WARN_ONCE(lrc->gt, !hwe || xe_hw_engine_is_reserved(hwe),
+			    "Unexpected engine class:instance %d:%d for context utilization\n",
+			    class, instance))
+		return -1;
+
+	if (lrc_to_xe(lrc)->info.has_64bit_timestamp)
+		val = xe_mmio_read64_2x32(&hwe->gt->mmio,
+					  RING_CTX_TIMESTAMP(hwe->mmio_base));
+	else
+		val = xe_mmio_read32(&hwe->gt->mmio,
+				     RING_CTX_TIMESTAMP(hwe->mmio_base));
+
+	*reg_ctx_ts = val;
+
+	return 0;
+}
+
 /**
  * xe_lrc_update_timestamp() - Update ctx timestamp
  * @lrc: Pointer to the lrc.
  * @old_ts: Old timestamp value
  *
  * Populate @old_ts current saved ctx timestamp, read new ctx timestamp and
- * update saved value.
+ * update saved value. With support for active contexts, the calculation may be
+ * slightly racy, so follow a read-again logic to ensure that the context is
+ * still active before returning the right timestamp.
  *
  * Returns: New ctx timestamp value
  */
-u32 xe_lrc_update_timestamp(struct xe_lrc *lrc, u32 *old_ts)
+u64 xe_lrc_update_timestamp(struct xe_lrc *lrc, u64 *old_ts)
 {
+	u64 lrc_ts, reg_ts;
+	u32 engine_id;
+
 	*old_ts = lrc->ctx_timestamp;
 
-	lrc->ctx_timestamp = xe_lrc_ctx_timestamp(lrc);
+	lrc_ts = xe_lrc_ctx_timestamp(lrc);
+	/* CTX_TIMESTAMP mmio read is invalid on VF, so return the LRC value */
+	if (IS_SRIOV_VF(lrc_to_xe(lrc))) {
+		lrc->ctx_timestamp = lrc_ts;
+		goto done;
+	}
+
+	if (lrc_ts == CONTEXT_ACTIVE) {
+		engine_id = xe_lrc_engine_id(lrc);
+		if (!get_ctx_timestamp(lrc, engine_id, &reg_ts))
+			lrc->ctx_timestamp = reg_ts;
+
+		/* read lrc again to ensure context is still active */
+		lrc_ts = xe_lrc_ctx_timestamp(lrc);
+	}
+
+	/*
+	 * If context switched out, just use the lrc_ts. Note that this needs to
+	 * be a separate if condition.
+	 */
+	if (lrc_ts != CONTEXT_ACTIVE)
+		lrc->ctx_timestamp = lrc_ts;
 
+done:
 	trace_xe_lrc_update_timestamp(lrc, *old_ts);
 
 	return lrc->ctx_timestamp;
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index 0b40f349ab95..eb6e8de8c939 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -120,7 +120,8 @@ void xe_lrc_snapshot_print(struct xe_lrc_snapshot *snapshot, struct drm_printer
 void xe_lrc_snapshot_free(struct xe_lrc_snapshot *snapshot);
 
 u32 xe_lrc_ctx_timestamp_ggtt_addr(struct xe_lrc *lrc);
-u32 xe_lrc_ctx_timestamp(struct xe_lrc *lrc);
+u32 xe_lrc_ctx_timestamp_udw_ggtt_addr(struct xe_lrc *lrc);
+u64 xe_lrc_ctx_timestamp(struct xe_lrc *lrc);
 u32 xe_lrc_ctx_job_timestamp_ggtt_addr(struct xe_lrc *lrc);
 u32 xe_lrc_ctx_job_timestamp(struct xe_lrc *lrc);
 
@@ -136,6 +137,6 @@ u32 xe_lrc_ctx_job_timestamp(struct xe_lrc *lrc);
  *
  * Returns the current LRC timestamp
  */
-u32 xe_lrc_update_timestamp(struct xe_lrc *lrc, u32 *old_ts);
+u64 xe_lrc_update_timestamp(struct xe_lrc *lrc, u64 *old_ts);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_lrc_types.h b/drivers/gpu/drm/xe/xe_lrc_types.h
index 71ecb453f811..ae24cf6f8dd9 100644
--- a/drivers/gpu/drm/xe/xe_lrc_types.h
+++ b/drivers/gpu/drm/xe/xe_lrc_types.h
@@ -25,8 +25,8 @@ struct xe_lrc {
 	/** @size: size of lrc including any indirect ring state page */
 	u32 size;
 
-	/** @tile: tile which this LRC belongs to */
-	struct xe_tile *tile;
+	/** @gt: gt which this LRC belongs to */
+	struct xe_gt *gt;
 
 	/** @flags: LRC flags */
 #define XE_LRC_FLAG_INDIRECT_RING_STATE		0x1
@@ -52,7 +52,10 @@ struct xe_lrc {
 	struct xe_hw_fence_ctx fence_ctx;
 
 	/** @ctx_timestamp: readout value of CTX_TIMESTAMP on last update */
-	u32 ctx_timestamp;
+	u64 ctx_timestamp;
+
+	/** @bb_per_ctx_bo: buffer object for per context batch wa buffer */
+	struct xe_bo *bb_per_ctx_bo;
 };
 
 struct xe_lrc_snapshot;
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index df4282c71bf0..5a3e89022c38 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -1177,7 +1177,7 @@ err:
 err_sync:
 		/* Sync partial copies if any. FIXME: job_mutex? */
 		if (fence) {
-			dma_fence_wait(m->fence, false);
+			dma_fence_wait(fence, false);
 			dma_fence_put(fence);
 		}
 
@@ -1547,7 +1547,7 @@ void xe_migrate_wait(struct xe_migrate *m)
 static u32 pte_update_cmd_size(u64 size)
 {
 	u32 num_dword;
-	u64 entries = DIV_ROUND_UP(size, XE_PAGE_SIZE);
+	u64 entries = DIV_U64_ROUND_UP(size, XE_PAGE_SIZE);
 
 	XE_WARN_ON(size > MAX_PREEMPTDISABLE_TRANSFER);
 	/*
@@ -1558,7 +1558,7 @@ static u32 pte_update_cmd_size(u64 size)
 	 * 2 dword for the page table's physical location
 	 * 2*n dword for value of pte to fill (each pte entry is 2 dwords)
 	 */
-	num_dword = (1 + 2) * DIV_ROUND_UP(entries, 0x1ff);
+	num_dword = (1 + 2) * DIV_U64_ROUND_UP(entries, 0x1ff);
 	num_dword += entries * 2;
 
 	return num_dword;
diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
index 9f4632e39a1a..e861c694f336 100644
--- a/drivers/gpu/drm/xe/xe_module.c
+++ b/drivers/gpu/drm/xe/xe_module.c
@@ -29,9 +29,6 @@ struct xe_modparam xe_modparam = {
 module_param_named(svm_notifier_size, xe_modparam.svm_notifier_size, uint, 0600);
 MODULE_PARM_DESC(svm_notifier_size, "Set the svm notifier size(in MiB), must be power of 2");
 
-module_param_named(always_migrate_to_vram, xe_modparam.always_migrate_to_vram, bool, 0444);
-MODULE_PARM_DESC(always_migrate_to_vram, "Always migrate to VRAM on GPU fault");
-
 module_param_named_unsafe(force_execlist, xe_modparam.force_execlist, bool, 0444);
 MODULE_PARM_DESC(force_execlist, "Force Execlist submission");
 
diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h
index 84339e509c80..5a3bfea8b7b4 100644
--- a/drivers/gpu/drm/xe/xe_module.h
+++ b/drivers/gpu/drm/xe/xe_module.h
@@ -12,7 +12,6 @@
 struct xe_modparam {
 	bool force_execlist;
 	bool probe_display;
-	bool always_migrate_to_vram;
 	u32 force_vram_bar_size;
 	int guc_log_level;
 	char *guc_firmware_path;
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 818f023166d5..f4d108dc49b1 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -140,6 +140,7 @@ static const struct xe_graphics_desc graphics_xelpg = {
 	.has_indirect_ring_state = 1, \
 	.has_range_tlb_invalidation = 1, \
 	.has_usm = 1, \
+	.has_64bit_timestamp = 1, \
 	.va_bits = 48, \
 	.vm_max_level = 4, \
 	.hw_engine_mask = \
@@ -668,6 +669,7 @@ static int xe_info_init(struct xe_device *xe,
 
 	xe->info.has_range_tlb_invalidation = graphics_desc->has_range_tlb_invalidation;
 	xe->info.has_usm = graphics_desc->has_usm;
+	xe->info.has_64bit_timestamp = graphics_desc->has_64bit_timestamp;
 
 	for_each_remote_tile(tile, xe, id) {
 		int err;
diff --git a/drivers/gpu/drm/xe/xe_pci_types.h b/drivers/gpu/drm/xe/xe_pci_types.h
index e9b9bbc138d3..ca6b10d35573 100644
--- a/drivers/gpu/drm/xe/xe_pci_types.h
+++ b/drivers/gpu/drm/xe/xe_pci_types.h
@@ -21,6 +21,7 @@ struct xe_graphics_desc {
 	u8 has_indirect_ring_state:1;
 	u8 has_range_tlb_invalidation:1;
 	u8 has_usm:1;
+	u8 has_64bit_timestamp:1;
 };
 
 struct xe_media_desc {
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index ffaf0d02dc7d..856038553b81 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -2232,11 +2232,19 @@ static void op_commit(struct xe_vm *vm,
 	}
 	case DRM_GPUVA_OP_DRIVER:
 	{
+		/* WRITE_ONCE pairs with READ_ONCE in xe_svm.c */
+
 		if (op->subop == XE_VMA_SUBOP_MAP_RANGE) {
-			op->map_range.range->tile_present |= BIT(tile->id);
-			op->map_range.range->tile_invalidated &= ~BIT(tile->id);
+			WRITE_ONCE(op->map_range.range->tile_present,
+				   op->map_range.range->tile_present |
+				   BIT(tile->id));
+			WRITE_ONCE(op->map_range.range->tile_invalidated,
+				   op->map_range.range->tile_invalidated &
+				   ~BIT(tile->id));
 		} else if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE) {
-			op->unmap_range.range->tile_present &= ~BIT(tile->id);
+			WRITE_ONCE(op->unmap_range.range->tile_present,
+				   op->unmap_range.range->tile_present &
+				   ~BIT(tile->id));
 		}
 		break;
 	}
diff --git a/drivers/gpu/drm/xe/xe_pxp_debugfs.c b/drivers/gpu/drm/xe/xe_pxp_debugfs.c
index ccfbacf08efc..525a2f6bb076 100644
--- a/drivers/gpu/drm/xe/xe_pxp_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_pxp_debugfs.c
@@ -66,9 +66,18 @@ static int pxp_terminate(struct seq_file *m, void *data)
 {
 	struct xe_pxp *pxp = node_to_pxp(m->private);
 	struct drm_printer p = drm_seq_file_printer(m);
+	int ready = xe_pxp_get_readiness_status(pxp);
 
-	if (!xe_pxp_is_enabled(pxp))
-		return -ENODEV;
+	if (ready < 0)
+		return ready; /* disabled or error occurred */
+	else if (!ready)
+		return -EBUSY; /* init still in progress */
+
+	/* no need for a termination if PXP is not active */
+	if (pxp->status != XE_PXP_ACTIVE) {
+		drm_printf(&p, "PXP not active\n");
+		return 0;
+	}
 
 	/* simulate a termination interrupt */
 	spin_lock_irq(&pxp->xe->irq.lock);
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 917fc16de866..bc1689db4cd7 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -137,7 +137,8 @@ emit_pipe_control(u32 *dw, int i, u32 bit_group_0, u32 bit_group_1, u32 offset,
 static int emit_pipe_invalidate(u32 mask_flags, bool invalidate_tlb, u32 *dw,
 				int i)
 {
-	u32 flags = PIPE_CONTROL_CS_STALL |
+	u32 flags0 = 0;
+	u32 flags1 = PIPE_CONTROL_CS_STALL |
 		PIPE_CONTROL_COMMAND_CACHE_INVALIDATE |
 		PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE |
 		PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
@@ -148,11 +149,15 @@ static int emit_pipe_invalidate(u32 mask_flags, bool invalidate_tlb, u32 *dw,
 		PIPE_CONTROL_STORE_DATA_INDEX;
 
 	if (invalidate_tlb)
-		flags |= PIPE_CONTROL_TLB_INVALIDATE;
+		flags1 |= PIPE_CONTROL_TLB_INVALIDATE;
 
-	flags &= ~mask_flags;
+	flags1 &= ~mask_flags;
 
-	return emit_pipe_control(dw, i, 0, flags, LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR, 0);
+	if (flags1 & PIPE_CONTROL_VF_CACHE_INVALIDATE)
+		flags0 |= PIPE_CONTROL0_L3_READ_ONLY_CACHE_INVALIDATE;
+
+	return emit_pipe_control(dw, i, flags0, flags1,
+				 LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR, 0);
 }
 
 static int emit_store_imm_ppgtt_posted(u64 addr, u64 value,
@@ -229,13 +234,10 @@ static u32 get_ppgtt_flag(struct xe_sched_job *job)
 
 static int emit_copy_timestamp(struct xe_lrc *lrc, u32 *dw, int i)
 {
-	dw[i++] = MI_COPY_MEM_MEM | MI_COPY_MEM_MEM_SRC_GGTT |
-		MI_COPY_MEM_MEM_DST_GGTT;
+	dw[i++] = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
+	dw[i++] = RING_CTX_TIMESTAMP(0).addr;
 	dw[i++] = xe_lrc_ctx_job_timestamp_ggtt_addr(lrc);
 	dw[i++] = 0;
-	dw[i++] = xe_lrc_ctx_timestamp_ggtt_addr(lrc);
-	dw[i++] = 0;
-	dw[i++] = MI_NOOP;
 
 	return i;
 }
diff --git a/drivers/gpu/drm/xe/xe_shrinker.c b/drivers/gpu/drm/xe/xe_shrinker.c
index 8184390f9c7b..86d47aaf0358 100644
--- a/drivers/gpu/drm/xe/xe_shrinker.c
+++ b/drivers/gpu/drm/xe/xe_shrinker.c
@@ -227,7 +227,7 @@ struct xe_shrinker *xe_shrinker_create(struct xe_device *xe)
 	if (!shrinker)
 		return ERR_PTR(-ENOMEM);
 
-	shrinker->shrink = shrinker_alloc(0, "xe system shrinker");
+	shrinker->shrink = shrinker_alloc(0, "drm-xe_gem:%s", xe->drm.unique);
 	if (!shrinker->shrink) {
 		kfree(shrinker);
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 3e829c87d7b4..975094c1a582 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -15,8 +15,17 @@
 
 static bool xe_svm_range_in_vram(struct xe_svm_range *range)
 {
-	/* Not reliable without notifier lock */
-	return range->base.flags.has_devmem_pages;
+	/*
+	 * Advisory only check whether the range is currently backed by VRAM
+	 * memory.
+	 */
+
+	struct drm_gpusvm_range_flags flags = {
+		/* Pairs with WRITE_ONCE in drm_gpusvm.c */
+		.__flags = READ_ONCE(range->base.flags.__flags),
+	};
+
+	return flags.has_devmem_pages;
 }
 
 static bool xe_svm_range_has_vram_binding(struct xe_svm_range *range)
@@ -79,7 +88,7 @@ xe_svm_range_alloc(struct drm_gpusvm *gpusvm)
 
 	range = kzalloc(sizeof(*range), GFP_KERNEL);
 	if (!range)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	INIT_LIST_HEAD(&range->garbage_collector_link);
 	xe_vm_get(gpusvm_to_vm(gpusvm));
@@ -645,9 +654,16 @@ void xe_svm_fini(struct xe_vm *vm)
 }
 
 static bool xe_svm_range_is_valid(struct xe_svm_range *range,
-				  struct xe_tile *tile)
+				  struct xe_tile *tile,
+				  bool devmem_only)
 {
-	return (range->tile_present & ~range->tile_invalidated) & BIT(tile->id);
+	/*
+	 * Advisory only check whether the range currently has a valid mapping,
+	 * READ_ONCE pairs with WRITE_ONCE in xe_pt.c
+	 */
+	return ((READ_ONCE(range->tile_present) &
+		 ~READ_ONCE(range->tile_invalidated)) & BIT(tile->id)) &&
+		(!devmem_only || xe_svm_range_in_vram(range));
 }
 
 static struct xe_vram_region *tile_to_vr(struct xe_tile *tile)
@@ -696,11 +712,14 @@ retry:
 	list_for_each_entry(block, blocks, link)
 		block->private = vr;
 
+	xe_bo_get(bo);
 	err = drm_gpusvm_migrate_to_devmem(&vm->svm.gpusvm, &range->base,
 					   &bo->devmem_allocation, ctx);
-	xe_bo_unlock(bo);
 	if (err)
-		xe_bo_put(bo);	/* Creation ref */
+		xe_svm_devmem_release(&bo->devmem_allocation);
+
+	xe_bo_unlock(bo);
+	xe_bo_put(bo);
 
 unlock:
 	mmap_read_unlock(mm);
@@ -709,6 +728,36 @@ unlock:
 	return err;
 }
 
+static bool supports_4K_migration(struct xe_device *xe)
+{
+	if (xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K)
+		return false;
+
+	return true;
+}
+
+static bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range,
+					       struct xe_vma *vma)
+{
+	struct xe_vm *vm = range_to_vm(&range->base);
+	u64 range_size = xe_svm_range_size(range);
+
+	if (!range->base.flags.migrate_devmem)
+		return false;
+
+	if (xe_svm_range_in_vram(range)) {
+		drm_dbg(&vm->xe->drm, "Range is already in VRAM\n");
+		return false;
+	}
+
+	if (range_size <= SZ_64K && !supports_4K_migration(vm->xe)) {
+		drm_dbg(&vm->xe->drm, "Platform doesn't support SZ_4K range migration\n");
+		return false;
+	}
+
+	return true;
+}
+
 /**
  * xe_svm_handle_pagefault() - SVM handle page fault
  * @vm: The VM.
@@ -732,11 +781,16 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
 			IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR),
 		.check_pages_threshold = IS_DGFX(vm->xe) &&
 			IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? SZ_64K : 0,
+		.devmem_only = atomic && IS_DGFX(vm->xe) &&
+			IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR),
+		.timeslice_ms = atomic && IS_DGFX(vm->xe) &&
+			IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? 5 : 0,
 	};
 	struct xe_svm_range *range;
 	struct drm_gpusvm_range *r;
 	struct drm_exec exec;
 	struct dma_fence *fence;
+	int migrate_try_count = ctx.devmem_only ? 3 : 1;
 	ktime_t end = 0;
 	int err;
 
@@ -755,24 +809,31 @@ retry:
 	if (IS_ERR(r))
 		return PTR_ERR(r);
 
+	if (ctx.devmem_only && !r->flags.migrate_devmem)
+		return -EACCES;
+
 	range = to_xe_range(r);
-	if (xe_svm_range_is_valid(range, tile))
+	if (xe_svm_range_is_valid(range, tile, ctx.devmem_only))
 		return 0;
 
 	range_debug(range, "PAGE FAULT");
 
-	/* XXX: Add migration policy, for now migrate range once */
-	if (!range->skip_migrate && range->base.flags.migrate_devmem &&
-	    xe_svm_range_size(range) >= SZ_64K) {
-		range->skip_migrate = true;
-
+	if (--migrate_try_count >= 0 &&
+	    xe_svm_range_needs_migrate_to_vram(range, vma)) {
 		err = xe_svm_alloc_vram(vm, tile, range, &ctx);
+		ctx.timeslice_ms <<= 1;	/* Double timeslice if we have to retry */
 		if (err) {
-			drm_dbg(&vm->xe->drm,
-				"VRAM allocation failed, falling back to "
-				"retrying fault, asid=%u, errno=%pe\n",
-				vm->usm.asid, ERR_PTR(err));
-			goto retry;
+			if (migrate_try_count || !ctx.devmem_only) {
+				drm_dbg(&vm->xe->drm,
+					"VRAM allocation failed, falling back to retrying fault, asid=%u, errno=%pe\n",
+					vm->usm.asid, ERR_PTR(err));
+				goto retry;
+			} else {
+				drm_err(&vm->xe->drm,
+					"VRAM allocation failed, retry count exceeded, asid=%u, errno=%pe\n",
+					vm->usm.asid, ERR_PTR(err));
+				return err;
+			}
 		}
 	}
 
@@ -780,15 +841,23 @@ retry:
 	err = drm_gpusvm_range_get_pages(&vm->svm.gpusvm, r, &ctx);
 	/* Corner where CPU mappings have changed */
 	if (err == -EOPNOTSUPP || err == -EFAULT || err == -EPERM) {
-		if (err == -EOPNOTSUPP) {
-			range_debug(range, "PAGE FAULT - EVICT PAGES");
-			drm_gpusvm_range_evict(&vm->svm.gpusvm, &range->base);
+		ctx.timeslice_ms <<= 1;	/* Double timeslice if we have to retry */
+		if (migrate_try_count > 0 || !ctx.devmem_only) {
+			if (err == -EOPNOTSUPP) {
+				range_debug(range, "PAGE FAULT - EVICT PAGES");
+				drm_gpusvm_range_evict(&vm->svm.gpusvm,
+						       &range->base);
+			}
+			drm_dbg(&vm->xe->drm,
+				"Get pages failed, falling back to retrying, asid=%u, gpusvm=%p, errno=%pe\n",
+				vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
+			range_debug(range, "PAGE FAULT - RETRY PAGES");
+			goto retry;
+		} else {
+			drm_err(&vm->xe->drm,
+				"Get pages failed, retry count exceeded, asid=%u, gpusvm=%p, errno=%pe\n",
+				vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
 		}
-		drm_dbg(&vm->xe->drm,
-			"Get pages failed, falling back to retrying, asid=%u, gpusvm=%p, errno=%pe\n",
-			vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
-		range_debug(range, "PAGE FAULT - RETRY PAGES");
-		goto retry;
 	}
 	if (err) {
 		range_debug(range, "PAGE FAULT - FAIL PAGE COLLECT");
@@ -812,6 +881,7 @@ retry_bind:
 			drm_exec_fini(&exec);
 			err = PTR_ERR(fence);
 			if (err == -EAGAIN) {
+				ctx.timeslice_ms <<= 1;	/* Double timeslice if we have to retry */
 				range_debug(range, "PAGE FAULT - RETRY BIND");
 				goto retry;
 			}
@@ -822,9 +892,6 @@ retry_bind:
 	}
 	drm_exec_fini(&exec);
 
-	if (xe_modparam.always_migrate_to_vram)
-		range->skip_migrate = false;
-
 	dma_fence_wait(fence, false);
 	dma_fence_put(fence);
 
@@ -944,3 +1011,15 @@ int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr)
 	return 0;
 }
 #endif
+
+/**
+ * xe_svm_flush() - SVM flush
+ * @vm: The VM.
+ *
+ * Flush all SVM actions.
+ */
+void xe_svm_flush(struct xe_vm *vm)
+{
+	if (xe_vm_in_fault_mode(vm))
+		flush_work(&vm->svm.garbage_collector.work);
+}
diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
index e059590e5076..fe58ac2f4baa 100644
--- a/drivers/gpu/drm/xe/xe_svm.h
+++ b/drivers/gpu/drm/xe/xe_svm.h
@@ -36,11 +36,6 @@ struct xe_svm_range {
 	 * range. Protected by GPU SVM notifier lock.
 	 */
 	u8 tile_invalidated;
-	/**
-	 * @skip_migrate: Skip migration to VRAM, protected by GPU fault handler
-	 * locking.
-	 */
-	u8 skip_migrate	:1;
 };
 
 #if IS_ENABLED(CONFIG_DRM_GPUSVM)
@@ -72,6 +67,9 @@ bool xe_svm_has_mapping(struct xe_vm *vm, u64 start, u64 end);
 int xe_svm_bo_evict(struct xe_bo *bo);
 
 void xe_svm_range_debug(struct xe_svm_range *range, const char *operation);
+
+void xe_svm_flush(struct xe_vm *vm);
+
 #else
 static inline bool xe_svm_range_pages_valid(struct xe_svm_range *range)
 {
@@ -124,6 +122,11 @@ static inline
 void xe_svm_range_debug(struct xe_svm_range *range, const char *operation)
 {
 }
+
+static inline void xe_svm_flush(struct xe_vm *vm)
+{
+}
+
 #endif
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_trace_lrc.h b/drivers/gpu/drm/xe/xe_trace_lrc.h
index 5c669a0b2180..d525cbee1e34 100644
--- a/drivers/gpu/drm/xe/xe_trace_lrc.h
+++ b/drivers/gpu/drm/xe/xe_trace_lrc.h
@@ -19,12 +19,12 @@
 #define __dev_name_lrc(lrc)	dev_name(gt_to_xe((lrc)->fence_ctx.gt)->drm.dev)
 
 TRACE_EVENT(xe_lrc_update_timestamp,
-	    TP_PROTO(struct xe_lrc *lrc, uint32_t old),
+	    TP_PROTO(struct xe_lrc *lrc, uint64_t old),
 	    TP_ARGS(lrc, old),
 	    TP_STRUCT__entry(
 		     __field(struct xe_lrc *, lrc)
-		     __field(u32, old)
-		     __field(u32, new)
+		     __field(u64, old)
+		     __field(u64, new)
 		     __string(name, lrc->fence_ctx.name)
 		     __string(device_id, __dev_name_lrc(lrc))
 	    ),
@@ -36,7 +36,7 @@ TRACE_EVENT(xe_lrc_update_timestamp,
 		   __assign_str(name);
 		   __assign_str(device_id);
 		   ),
-	    TP_printk("lrc=:%p lrc->name=%s old=%u new=%u device_id:%s",
+	    TP_printk("lrc=:%p lrc->name=%s old=%llu new=%llu device_id:%s",
 		      __entry->lrc, __get_str(name),
 		      __entry->old, __entry->new,
 		      __get_str(device_id))
diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c
index c14bd2282044..3a8751a8b92d 100644
--- a/drivers/gpu/drm/xe/xe_uc.c
+++ b/drivers/gpu/drm/xe/xe_uc.c
@@ -244,7 +244,7 @@ void xe_uc_gucrc_disable(struct xe_uc *uc)
 
 void xe_uc_stop_prepare(struct xe_uc *uc)
 {
-	xe_gsc_wait_for_worker_completion(&uc->gsc);
+	xe_gsc_stop_prepare(&uc->gsc);
 	xe_guc_stop_prepare(&uc->guc);
 }
 
@@ -278,6 +278,12 @@ again:
 		goto again;
 }
 
+void xe_uc_suspend_prepare(struct xe_uc *uc)
+{
+	xe_gsc_wait_for_worker_completion(&uc->gsc);
+	xe_guc_stop_prepare(&uc->guc);
+}
+
 int xe_uc_suspend(struct xe_uc *uc)
 {
 	/* GuC submission not enabled, nothing to do */
diff --git a/drivers/gpu/drm/xe/xe_uc.h b/drivers/gpu/drm/xe/xe_uc.h
index 3813c1ede450..c23e6f5e2514 100644
--- a/drivers/gpu/drm/xe/xe_uc.h
+++ b/drivers/gpu/drm/xe/xe_uc.h
@@ -18,6 +18,7 @@ int xe_uc_reset_prepare(struct xe_uc *uc);
 void xe_uc_stop_prepare(struct xe_uc *uc);
 void xe_uc_stop(struct xe_uc *uc);
 int xe_uc_start(struct xe_uc *uc);
+void xe_uc_suspend_prepare(struct xe_uc *uc);
 int xe_uc_suspend(struct xe_uc *uc);
 int xe_uc_sanitize_reset(struct xe_uc *uc);
 void xe_uc_declare_wedged(struct xe_uc *uc);
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 60303998bd61..367c84b90e9e 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3312,8 +3312,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	}
 
 	/* Ensure all UNMAPs visible */
-	if (xe_vm_in_fault_mode(vm))
-		flush_work(&vm->svm.garbage_collector.work);
+	xe_svm_flush(vm);
 
 	err = down_write_killable(&vm->lock);
 	if (err)
diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index 24f644c0a673..2f833f0d575f 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -815,6 +815,10 @@ static const struct xe_rtp_entry_sr lrc_was[] = {
 	  XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)),
 	  XE_RTP_ACTIONS(SET(CHICKEN_RASTER_1, DIS_CLIP_NEGATIVE_BOUNDING_BOX))
 	},
+	{ XE_RTP_NAME("22021007897"),
+	  XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)),
+	  XE_RTP_ACTIONS(SET(COMMON_SLICE_CHICKEN4, SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE))
+	},
 
 	/* Xe3_LPG */
 	{ XE_RTP_NAME("14021490052"),
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 0c738af24f7c..9b9e176992a8 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -32,8 +32,10 @@
 		GRAPHICS_VERSION(3001)
 14022293748	GRAPHICS_VERSION(2001)
 		GRAPHICS_VERSION(2004)
+		GRAPHICS_VERSION_RANGE(3000, 3001)
 22019794406	GRAPHICS_VERSION(2001)
 		GRAPHICS_VERSION(2004)
+		GRAPHICS_VERSION_RANGE(3000, 3001)
 22019338487	MEDIA_VERSION(2000)
 		GRAPHICS_VERSION(2001)
 		MEDIA_VERSION(3000), MEDIA_STEP(A0, B0), FUNC(xe_rtp_match_not_sriov_vf)
diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index 17c9660da450..ab0e5a72a059 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -93,7 +93,7 @@ impl Chipset {
 // For now, redirect to fmt::Debug for convenience.
 impl fmt::Display for Chipset {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(f, "{:?}", self)
+        write!(f, "{self:?}")
     }
 }
 
diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
index 25f0ebfcbd5f..0a9b44ce4904 100644
--- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
+++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
@@ -83,6 +83,9 @@ static int amd_sfh_hid_client_deinit(struct amd_mp2_dev *privdata)
 		case ALS_IDX:
 			privdata->dev_en.is_als_present = false;
 			break;
+		case SRA_IDX:
+			privdata->dev_en.is_sra_present = false;
+			break;
 		}
 
 		if (cl_data->sensor_sts[i] == SENSOR_ENABLED) {
@@ -134,9 +137,6 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata)
 	for (i = 0; i < cl_data->num_hid_devices; i++) {
 		cl_data->sensor_sts[i] = SENSOR_DISABLED;
 
-		if (cl_data->num_hid_devices == 1 && cl_data->sensor_idx[0] == SRA_IDX)
-			break;
-
 		if (cl_data->sensor_idx[i] == SRA_IDX) {
 			info.sensor_idx = cl_data->sensor_idx[i];
 			writel(0, privdata->mmio + amd_get_p2c_val(privdata, 0));
@@ -145,8 +145,10 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata)
 				(privdata, cl_data->sensor_idx[i], ENABLE_SENSOR);
 
 			cl_data->sensor_sts[i] = (status == 0) ? SENSOR_ENABLED : SENSOR_DISABLED;
-			if (cl_data->sensor_sts[i] == SENSOR_ENABLED)
+			if (cl_data->sensor_sts[i] == SENSOR_ENABLED) {
+				cl_data->is_any_sensor_enabled = true;
 				privdata->dev_en.is_sra_present = true;
+			}
 			continue;
 		}
 
@@ -238,6 +240,8 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata)
 cleanup:
 	amd_sfh_hid_client_deinit(privdata);
 	for (i = 0; i < cl_data->num_hid_devices; i++) {
+		if (cl_data->sensor_idx[i] == SRA_IDX)
+			continue;
 		devm_kfree(dev, cl_data->feature_report[i]);
 		devm_kfree(dev, in_data->input_report[i]);
 		devm_kfree(dev, cl_data->report_descr[i]);
diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c
index 2e96ec6a3073..9a06f9b0e4ef 100644
--- a/drivers/hid/bpf/hid_bpf_dispatch.c
+++ b/drivers/hid/bpf/hid_bpf_dispatch.c
@@ -38,6 +38,9 @@ dispatch_hid_bpf_device_event(struct hid_device *hdev, enum hid_report_type type
 	struct hid_bpf_ops *e;
 	int ret;
 
+	if (unlikely(hdev->bpf.destroyed))
+		return ERR_PTR(-ENODEV);
+
 	if (type >= HID_REPORT_TYPES)
 		return ERR_PTR(-EINVAL);
 
@@ -93,6 +96,9 @@ int dispatch_hid_bpf_raw_requests(struct hid_device *hdev,
 	struct hid_bpf_ops *e;
 	int ret, idx;
 
+	if (unlikely(hdev->bpf.destroyed))
+		return -ENODEV;
+
 	if (rtype >= HID_REPORT_TYPES)
 		return -EINVAL;
 
@@ -130,6 +136,9 @@ int dispatch_hid_bpf_output_report(struct hid_device *hdev,
 	struct hid_bpf_ops *e;
 	int ret, idx;
 
+	if (unlikely(hdev->bpf.destroyed))
+		return -ENODEV;
+
 	idx = srcu_read_lock(&hdev->bpf.srcu);
 	list_for_each_entry_srcu(e, &hdev->bpf.prog_list, list,
 				 srcu_read_lock_held(&hdev->bpf.srcu)) {
diff --git a/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c b/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c
index 1a0aeea6a081..a754710fc90b 100644
--- a/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c
+++ b/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c
@@ -157,6 +157,7 @@ static const __u8 fixed_rdesc_vendor[] = {
 			ReportCount(5) // padding
 			Input(Const)
 			// Byte 4 in report - just exists so we get to be a tablet pad
+			UsagePage_Digitizers
 			Usage_Dig_BarrelSwitch // BTN_STYLUS
 			ReportCount(1)
 			ReportSize(1)
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 288a2b864cc4..1062731315a2 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -41,6 +41,10 @@
 #define USB_VENDOR_ID_ACTIONSTAR	0x2101
 #define USB_DEVICE_ID_ACTIONSTAR_1011	0x1011
 
+#define USB_VENDOR_ID_ADATA_XPG 0x125f
+#define USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE 0x7505
+#define USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE_DONGLE 0x7506
+
 #define USB_VENDOR_ID_ADS_TECH		0x06e1
 #define USB_DEVICE_ID_ADS_TECH_RADIO_SI470X	0xa155
 
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 646171598e41..0731473cc9b1 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -27,6 +27,8 @@
 static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_GAMEPAD), HID_QUIRK_BADPAD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_PREDATOR), HID_QUIRK_BADPAD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ADATA_XPG, USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE), HID_QUIRK_ALWAYS_POLL },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ADATA_XPG, USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE_DONGLE), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AFATECH, USB_DEVICE_ID_AFATECH_AF9016), HID_QUIRK_FULLSPEED_INTERVAL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AIREN, USB_DEVICE_ID_AIREN_SLIMPLUS), HID_QUIRK_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AKAI_09E8, USB_DEVICE_ID_AKAI_09E8_MIDIMIX), HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index dfd9d22ed559..949d307c66a8 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -1150,11 +1150,9 @@ static void steam_client_ll_close(struct hid_device *hdev)
 	struct steam_device *steam = hdev->driver_data;
 
 	unsigned long flags;
-	bool connected;
 
 	spin_lock_irqsave(&steam->lock, flags);
 	steam->client_opened--;
-	connected = steam->connected && !steam->client_opened;
 	spin_unlock_irqrestore(&steam->lock, flags);
 
 	schedule_work(&steam->unregister_work);
diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c
index 3b81468a1df2..0bf70664c35e 100644
--- a/drivers/hid/hid-thrustmaster.c
+++ b/drivers/hid/hid-thrustmaster.c
@@ -174,6 +174,7 @@ static void thrustmaster_interrupts(struct hid_device *hdev)
 	u8 ep_addr[2] = {b_ep, 0};
 
 	if (!usb_check_int_endpoints(usbif, ep_addr)) {
+		kfree(send_buf);
 		hid_err(hdev, "Unexpected non-int endpoint\n");
 		return;
 	}
diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c
index a367df6ea01f..61a4019ddc74 100644
--- a/drivers/hid/hid-uclogic-core.c
+++ b/drivers/hid/hid-uclogic-core.c
@@ -142,11 +142,12 @@ static int uclogic_input_configured(struct hid_device *hdev,
 			suffix = "System Control";
 			break;
 		}
-	}
-
-	if (suffix)
+	} else {
 		hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL,
 						 "%s %s", hdev->name, suffix);
+		if (!hi->input->name)
+			return -ENOMEM;
+	}
 
 	return 0;
 }
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 1556d4287fa5..eaf099b2efdb 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -70,10 +70,16 @@ static void wacom_wac_queue_flush(struct hid_device *hdev,
 {
 	while (!kfifo_is_empty(fifo)) {
 		int size = kfifo_peek_len(fifo);
-		u8 *buf = kzalloc(size, GFP_KERNEL);
+		u8 *buf;
 		unsigned int count;
 		int err;
 
+		buf = kzalloc(size, GFP_KERNEL);
+		if (!buf) {
+			kfifo_skip(fifo);
+			continue;
+		}
+
 		count = kfifo_out(fifo, buf, size);
 		if (count != size) {
 			// Hard to say what is the "right" action in this
@@ -81,6 +87,7 @@ static void wacom_wac_queue_flush(struct hid_device *hdev,
 			// to flush seems reasonable enough, however.
 			hid_warn(hdev, "%s: removed fifo entry with unexpected size\n",
 				 __func__);
+			kfree(buf);
 			continue;
 		}
 		err = hid_report_raw_event(hdev, HID_INPUT_REPORT, buf, size, false);
@@ -2361,6 +2368,8 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
 	unsigned int connect_mask = HID_CONNECT_HIDRAW;
 
 	features->pktlen = wacom_compute_pktlen(hdev);
+	if (!features->pktlen)
+		return -ENODEV;
 
 	if (!devres_open_group(&hdev->dev, wacom, GFP_KERNEL))
 		return -ENOMEM;
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index fb8cd8469328..35f26fa1ffe7 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -1077,68 +1077,10 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
 EXPORT_SYMBOL(vmbus_sendpacket);
 
 /*
- * vmbus_sendpacket_pagebuffer - Send a range of single-page buffer
- * packets using a GPADL Direct packet type. This interface allows you
- * to control notifying the host. This will be useful for sending
- * batched data. Also the sender can control the send flags
- * explicitly.
- */
-int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
-				struct hv_page_buffer pagebuffers[],
-				u32 pagecount, void *buffer, u32 bufferlen,
-				u64 requestid)
-{
-	int i;
-	struct vmbus_channel_packet_page_buffer desc;
-	u32 descsize;
-	u32 packetlen;
-	u32 packetlen_aligned;
-	struct kvec bufferlist[3];
-	u64 aligned_data = 0;
-
-	if (pagecount > MAX_PAGE_BUFFER_COUNT)
-		return -EINVAL;
-
-	/*
-	 * Adjust the size down since vmbus_channel_packet_page_buffer is the
-	 * largest size we support
-	 */
-	descsize = sizeof(struct vmbus_channel_packet_page_buffer) -
-			  ((MAX_PAGE_BUFFER_COUNT - pagecount) *
-			  sizeof(struct hv_page_buffer));
-	packetlen = descsize + bufferlen;
-	packetlen_aligned = ALIGN(packetlen, sizeof(u64));
-
-	/* Setup the descriptor */
-	desc.type = VM_PKT_DATA_USING_GPA_DIRECT;
-	desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
-	desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */
-	desc.length8 = (u16)(packetlen_aligned >> 3);
-	desc.transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */
-	desc.reserved = 0;
-	desc.rangecount = pagecount;
-
-	for (i = 0; i < pagecount; i++) {
-		desc.range[i].len = pagebuffers[i].len;
-		desc.range[i].offset = pagebuffers[i].offset;
-		desc.range[i].pfn	 = pagebuffers[i].pfn;
-	}
-
-	bufferlist[0].iov_base = &desc;
-	bufferlist[0].iov_len = descsize;
-	bufferlist[1].iov_base = buffer;
-	bufferlist[1].iov_len = bufferlen;
-	bufferlist[2].iov_base = &aligned_data;
-	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
-
-	return hv_ringbuffer_write(channel, bufferlist, 3, requestid, NULL);
-}
-EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer);
-
-/*
- * vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet
+ * vmbus_sendpacket_mpb_desc - Send one or more multi-page buffer packets
  * using a GPADL Direct packet type.
- * The buffer includes the vmbus descriptor.
+ * The desc argument must include space for the VMBus descriptor. The
+ * rangecount field must already be set.
  */
 int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 			      struct vmbus_packet_mpb_array *desc,
@@ -1160,7 +1102,6 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 	desc->length8 = (u16)(packetlen_aligned >> 3);
 	desc->transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */
 	desc->reserved = 0;
-	desc->rangecount = 1;
 
 	bufferlist[0].iov_base = desc;
 	bufferlist[0].iov_len = desc_size;
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index b3b11be11650..59792e00cecf 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -307,7 +307,7 @@ void __init hv_get_partition_id(void)
 
 	local_irq_save(flags);
 	output = *this_cpu_ptr(hyperv_pcpu_input_arg);
-	status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, &output);
+	status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output);
 	pt_id = output->partition_id;
 	local_irq_restore(flags);
 
@@ -566,9 +566,11 @@ int hv_common_cpu_die(unsigned int cpu)
 	 * originally allocated memory is reused in hv_common_cpu_init().
 	 */
 
-	synic_eventring_tail = this_cpu_ptr(hv_synic_eventring_tail);
-	kfree(*synic_eventring_tail);
-	*synic_eventring_tail = NULL;
+	if (hv_root_partition()) {
+		synic_eventring_tail = this_cpu_ptr(hv_synic_eventring_tail);
+		kfree(*synic_eventring_tail);
+		*synic_eventring_tail = NULL;
+	}
 
 	return 0;
 }
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 29780f3a7478..0b450e53161e 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -477,4 +477,10 @@ static inline int hv_debug_add_dev_dir(struct hv_device *dev)
 
 #endif /* CONFIG_HYPERV_TESTING */
 
+/* Create and remove sysfs entry for memory mapped ring buffers for a channel */
+int hv_create_ring_sysfs(struct vmbus_channel *channel,
+			 int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
+						    struct vm_area_struct *vma));
+int hv_remove_ring_sysfs(struct vmbus_channel *channel);
+
 #endif /* _HYPERV_VMBUS_H */
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 8d3cff42bdbb..e3d51a316316 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1802,6 +1802,26 @@ static ssize_t subchannel_id_show(struct vmbus_channel *channel,
 }
 static VMBUS_CHAN_ATTR_RO(subchannel_id);
 
+static int hv_mmap_ring_buffer_wrapper(struct file *filp, struct kobject *kobj,
+				       const struct bin_attribute *attr,
+				       struct vm_area_struct *vma)
+{
+	struct vmbus_channel *channel = container_of(kobj, struct vmbus_channel, kobj);
+
+	/*
+	 * hv_(create|remove)_ring_sysfs implementation ensures that mmap_ring_buffer
+	 * is not NULL.
+	 */
+	return channel->mmap_ring_buffer(channel, vma);
+}
+
+static struct bin_attribute chan_attr_ring_buffer = {
+	.attr = {
+		.name = "ring",
+		.mode = 0600,
+	},
+	.mmap = hv_mmap_ring_buffer_wrapper,
+};
 static struct attribute *vmbus_chan_attrs[] = {
 	&chan_attr_out_mask.attr,
 	&chan_attr_in_mask.attr,
@@ -1821,6 +1841,11 @@ static struct attribute *vmbus_chan_attrs[] = {
 	NULL
 };
 
+static struct bin_attribute *vmbus_chan_bin_attrs[] = {
+	&chan_attr_ring_buffer,
+	NULL
+};
+
 /*
  * Channel-level attribute_group callback function. Returns the permission for
  * each attribute, and returns 0 if an attribute is not visible.
@@ -1841,9 +1866,34 @@ static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj,
 	return attr->mode;
 }
 
+static umode_t vmbus_chan_bin_attr_is_visible(struct kobject *kobj,
+					      const struct bin_attribute *attr, int idx)
+{
+	const struct vmbus_channel *channel =
+		container_of(kobj, struct vmbus_channel, kobj);
+
+	/* Hide ring attribute if channel's ring_sysfs_visible is set to false */
+	if (attr ==  &chan_attr_ring_buffer && !channel->ring_sysfs_visible)
+		return 0;
+
+	return attr->attr.mode;
+}
+
+static size_t vmbus_chan_bin_size(struct kobject *kobj,
+				  const struct bin_attribute *bin_attr, int a)
+{
+	const struct vmbus_channel *channel =
+		container_of(kobj, struct vmbus_channel, kobj);
+
+	return channel->ringbuffer_pagecount << PAGE_SHIFT;
+}
+
 static const struct attribute_group vmbus_chan_group = {
 	.attrs = vmbus_chan_attrs,
-	.is_visible = vmbus_chan_attr_is_visible
+	.bin_attrs = vmbus_chan_bin_attrs,
+	.is_visible = vmbus_chan_attr_is_visible,
+	.is_bin_visible = vmbus_chan_bin_attr_is_visible,
+	.bin_size = vmbus_chan_bin_size,
 };
 
 static const struct kobj_type vmbus_chan_ktype = {
@@ -1851,6 +1901,63 @@ static const struct kobj_type vmbus_chan_ktype = {
 	.release = vmbus_chan_release,
 };
 
+/**
+ * hv_create_ring_sysfs() - create "ring" sysfs entry corresponding to ring buffers for a channel.
+ * @channel: Pointer to vmbus_channel structure
+ * @hv_mmap_ring_buffer: function pointer for initializing the function to be called on mmap of
+ *                       channel's "ring" sysfs node, which is for the ring buffer of that channel.
+ *                       Function pointer is of below type:
+ *                       int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
+ *                                                  struct vm_area_struct *vma))
+ *                       This has a pointer to the channel and a pointer to vm_area_struct,
+ *                       used for mmap, as arguments.
+ *
+ * Sysfs node for ring buffer of a channel is created along with other fields, however its
+ * visibility is disabled by default. Sysfs creation needs to be controlled when the use-case
+ * is running.
+ * For example, HV_NIC device is used either by uio_hv_generic or hv_netvsc at any given point of
+ * time, and "ring" sysfs is needed only when uio_hv_generic is bound to that device. To avoid
+ * exposing the ring buffer by default, this function is reponsible to enable visibility of
+ * ring for userspace to use.
+ * Note: Race conditions can happen with userspace and it is not encouraged to create new
+ * use-cases for this. This was added to maintain backward compatibility, while solving
+ * one of the race conditions in uio_hv_generic while creating sysfs.
+ *
+ * Returns 0 on success or error code on failure.
+ */
+int hv_create_ring_sysfs(struct vmbus_channel *channel,
+			 int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
+						    struct vm_area_struct *vma))
+{
+	struct kobject *kobj = &channel->kobj;
+
+	channel->mmap_ring_buffer = hv_mmap_ring_buffer;
+	channel->ring_sysfs_visible = true;
+
+	return sysfs_update_group(kobj, &vmbus_chan_group);
+}
+EXPORT_SYMBOL_GPL(hv_create_ring_sysfs);
+
+/**
+ * hv_remove_ring_sysfs() - remove ring sysfs entry corresponding to ring buffers for a channel.
+ * @channel: Pointer to vmbus_channel structure
+ *
+ * Hide "ring" sysfs for a channel by changing its is_visible attribute and updating sysfs group.
+ *
+ * Returns 0 on success or error code on failure.
+ */
+int hv_remove_ring_sysfs(struct vmbus_channel *channel)
+{
+	struct kobject *kobj = &channel->kobj;
+	int ret;
+
+	channel->ring_sysfs_visible = false;
+	ret = sysfs_update_group(kobj, &vmbus_chan_group);
+	channel->mmap_ring_buffer = NULL;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hv_remove_ring_sysfs);
+
 /*
  * vmbus_add_channel_kobj - setup a sub-directory under device/channels
  */
diff --git a/drivers/hwtracing/intel_th/Kconfig b/drivers/hwtracing/intel_th/Kconfig
index 4b6359326ede..4f7d2b6d79e2 100644
--- a/drivers/hwtracing/intel_th/Kconfig
+++ b/drivers/hwtracing/intel_th/Kconfig
@@ -60,6 +60,7 @@ config INTEL_TH_STH
 
 config INTEL_TH_MSU
 	tristate "Intel(R) Trace Hub Memory Storage Unit"
+	depends on MMU
 	help
 	  Memory Storage Unit (MSU) trace output device enables
 	  storing STP traces to system memory. It supports single
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index bf99d79a4192..7163950eb371 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -19,6 +19,7 @@
 #include <linux/io.h>
 #include <linux/workqueue.h>
 #include <linux/dma-mapping.h>
+#include <linux/pfn_t.h>
 
 #ifdef CONFIG_X86
 #include <asm/set_memory.h>
@@ -976,7 +977,6 @@ static void msc_buffer_contig_free(struct msc *msc)
 	for (off = 0; off < msc->nr_pages << PAGE_SHIFT; off += PAGE_SIZE) {
 		struct page *page = virt_to_page(msc->base + off);
 
-		page->mapping = NULL;
 		__free_page(page);
 	}
 
@@ -1158,9 +1158,6 @@ static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win)
 	int i;
 
 	for_each_sg(win->sgt->sgl, sg, win->nr_segs, i) {
-		struct page *page = msc_sg_page(sg);
-
-		page->mapping = NULL;
 		dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
 				  sg_virt(sg), sg_dma_address(sg));
 	}
@@ -1601,22 +1598,10 @@ static void msc_mmap_close(struct vm_area_struct *vma)
 {
 	struct msc_iter *iter = vma->vm_file->private_data;
 	struct msc *msc = iter->msc;
-	unsigned long pg;
 
 	if (!atomic_dec_and_mutex_lock(&msc->mmap_count, &msc->buf_mutex))
 		return;
 
-	/* drop page _refcounts */
-	for (pg = 0; pg < msc->nr_pages; pg++) {
-		struct page *page = msc_buffer_get_page(msc, pg);
-
-		if (WARN_ON_ONCE(!page))
-			continue;
-
-		if (page->mapping)
-			page->mapping = NULL;
-	}
-
 	/* last mapping -- drop user_count */
 	atomic_dec(&msc->user_count);
 	mutex_unlock(&msc->buf_mutex);
@@ -1626,16 +1611,14 @@ static vm_fault_t msc_mmap_fault(struct vm_fault *vmf)
 {
 	struct msc_iter *iter = vmf->vma->vm_file->private_data;
 	struct msc *msc = iter->msc;
+	struct page *page;
 
-	vmf->page = msc_buffer_get_page(msc, vmf->pgoff);
-	if (!vmf->page)
+	page = msc_buffer_get_page(msc, vmf->pgoff);
+	if (!page)
 		return VM_FAULT_SIGBUS;
 
-	get_page(vmf->page);
-	vmf->page->mapping = vmf->vma->vm_file->f_mapping;
-	vmf->page->index = vmf->pgoff;
-
-	return 0;
+	get_page(page);
+	return vmf_insert_mixed(vmf->vma, vmf->address, page_to_pfn_t(page));
 }
 
 static const struct vm_operations_struct msc_mmap_ops = {
@@ -1676,7 +1659,7 @@ out:
 		atomic_dec(&msc->user_count);
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY);
+	vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY | VM_MIXEDMAP);
 	vma->vm_ops = &msc_mmap_ops;
 	return ret;
 }
diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
index 43bf90d90eeb..208ce4f9e782 100644
--- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c
+++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
@@ -247,6 +247,9 @@ static int ec_i2c_probe(struct platform_device *pdev)
 	u32 remote_bus;
 	int err;
 
+	if (!ec)
+		return dev_err_probe(dev, -EPROBE_DEFER, "couldn't find parent EC device\n");
+
 	if (!ec->cmd_xfer) {
 		dev_err(dev, "Missing sendrecv\n");
 		return -EINVAL;
diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c
index 8e0267c7cc29..f21f9877c040 100644
--- a/drivers/i2c/busses/i2c-designware-pcidrv.c
+++ b/drivers/i2c/busses/i2c-designware-pcidrv.c
@@ -278,9 +278,11 @@ static int i2c_dw_pci_probe(struct pci_dev *pdev,
 
 	if ((dev->flags & MODEL_MASK) == MODEL_AMD_NAVI_GPU) {
 		dev->slave = i2c_new_ccgx_ucsi(&dev->adapter, dev->irq, &dgpu_node);
-		if (IS_ERR(dev->slave))
+		if (IS_ERR(dev->slave)) {
+			i2c_del_adapter(&dev->adapter);
 			return dev_err_probe(device, PTR_ERR(dev->slave),
 					     "register UCSI failed\n");
+		}
 	}
 
 	pm_runtime_set_autosuspend_delay(device, 1000);
diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c
index 0d4b3935e687..342d47e67586 100644
--- a/drivers/i2c/busses/i2c-imx-lpi2c.c
+++ b/drivers/i2c/busses/i2c-imx-lpi2c.c
@@ -1380,9 +1380,9 @@ static int lpi2c_imx_probe(struct platform_device *pdev)
 	return 0;
 
 rpm_disable:
-	pm_runtime_put(&pdev->dev);
-	pm_runtime_disable(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 
 	return ret;
 }
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 16afb9ca19bb..876791d20ed5 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1454,7 +1454,7 @@ omap_i2c_probe(struct platform_device *pdev)
 				       (1000 * omap->speed / 8);
 	}
 
-	if (of_property_read_bool(node, "mux-states")) {
+	if (of_property_present(node, "mux-states")) {
 		struct mux_state *mux_state;
 
 		mux_state = devm_mux_state_get(&pdev->dev, NULL);
diff --git a/drivers/i2c/i2c-atr.c b/drivers/i2c/i2c-atr.c
index 8fe9ddff8e96..783fb8df2ebe 100644
--- a/drivers/i2c/i2c-atr.c
+++ b/drivers/i2c/i2c-atr.c
@@ -8,12 +8,12 @@
  * Originally based on i2c-mux.c
  */
 
-#include <linux/fwnode.h>
 #include <linux/i2c-atr.h>
 #include <linux/i2c.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/property.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
diff --git a/drivers/iio/accel/adis16201.c b/drivers/iio/accel/adis16201.c
index 8601b9a8b8e7..5127e58eebc7 100644
--- a/drivers/iio/accel/adis16201.c
+++ b/drivers/iio/accel/adis16201.c
@@ -211,9 +211,9 @@ static const struct iio_chan_spec adis16201_channels[] = {
 			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
 	ADIS_AUX_ADC_CHAN(ADIS16201_AUX_ADC_REG, ADIS16201_SCAN_AUX_ADC, 0, 12),
 	ADIS_INCLI_CHAN(X, ADIS16201_XINCL_OUT_REG, ADIS16201_SCAN_INCLI_X,
-			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
+			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12),
 	ADIS_INCLI_CHAN(Y, ADIS16201_YINCL_OUT_REG, ADIS16201_SCAN_INCLI_Y,
-			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
+			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12),
 	IIO_CHAN_SOFT_TIMESTAMP(7)
 };
 
diff --git a/drivers/iio/accel/adxl355_core.c b/drivers/iio/accel/adxl355_core.c
index e8cd21fa77a6..cbac622ef821 100644
--- a/drivers/iio/accel/adxl355_core.c
+++ b/drivers/iio/accel/adxl355_core.c
@@ -231,7 +231,7 @@ struct adxl355_data {
 		u8 transf_buf[3];
 		struct {
 			u8 buf[14];
-			s64 ts;
+			aligned_s64 ts;
 		} buffer;
 	} __aligned(IIO_DMA_MINALIGN);
 };
diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c
index add4053e7a02..0c04b2bb7efb 100644
--- a/drivers/iio/accel/adxl367.c
+++ b/drivers/iio/accel/adxl367.c
@@ -601,18 +601,14 @@ static int _adxl367_set_odr(struct adxl367_state *st, enum adxl367_odr odr)
 	if (ret)
 		return ret;
 
+	st->odr = odr;
+
 	/* Activity timers depend on ODR */
 	ret = _adxl367_set_act_time_ms(st, st->act_time_ms);
 	if (ret)
 		return ret;
 
-	ret = _adxl367_set_inact_time_ms(st, st->inact_time_ms);
-	if (ret)
-		return ret;
-
-	st->odr = odr;
-
-	return 0;
+	return _adxl367_set_inact_time_ms(st, st->inact_time_ms);
 }
 
 static int adxl367_set_odr(struct iio_dev *indio_dev, enum adxl367_odr odr)
diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c
index 48e4282964a0..bf1d3923a181 100644
--- a/drivers/iio/accel/fxls8962af-core.c
+++ b/drivers/iio/accel/fxls8962af-core.c
@@ -1226,8 +1226,11 @@ int fxls8962af_core_probe(struct device *dev, struct regmap *regmap, int irq)
 	if (ret)
 		return ret;
 
-	if (device_property_read_bool(dev, "wakeup-source"))
-		device_init_wakeup(dev, true);
+	if (device_property_read_bool(dev, "wakeup-source")) {
+		ret = devm_device_init_wakeup(dev);
+		if (ret)
+			return dev_err_probe(dev, ret, "Failed to init wakeup\n");
+	}
 
 	return devm_iio_device_register(dev, indio_dev);
 }
diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index 18559757f908..7fef2727f89e 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -45,7 +45,7 @@ struct ad7266_state {
 	 */
 	struct {
 		__be16 sample[2];
-		s64 timestamp;
+		aligned_s64 timestamp;
 	} data __aligned(IIO_DMA_MINALIGN);
 };
 
diff --git a/drivers/iio/adc/ad7380.c b/drivers/iio/adc/ad7380.c
index 4fcb49fdf566..aef85093eb16 100644
--- a/drivers/iio/adc/ad7380.c
+++ b/drivers/iio/adc/ad7380.c
@@ -1211,6 +1211,9 @@ static int ad7380_offload_buffer_predisable(struct iio_dev *indio_dev)
 	struct ad7380_state *st = iio_priv(indio_dev);
 	int ret;
 
+	spi_offload_trigger_disable(st->offload, st->offload_trigger);
+	spi_unoptimize_message(&st->offload_msg);
+
 	if (st->seq) {
 		ret = regmap_update_bits(st->regmap,
 					 AD7380_REG_ADDR_CONFIG1,
@@ -1222,10 +1225,6 @@ static int ad7380_offload_buffer_predisable(struct iio_dev *indio_dev)
 		st->seq = false;
 	}
 
-	spi_offload_trigger_disable(st->offload, st->offload_trigger);
-
-	spi_unoptimize_message(&st->offload_msg);
-
 	return 0;
 }
 
@@ -1611,11 +1610,25 @@ static int ad7380_write_event_config(struct iio_dev *indio_dev,
 	return ret;
 }
 
-static int ad7380_get_alert_th(struct ad7380_state *st,
+static int ad7380_get_alert_th(struct iio_dev *indio_dev,
+			       const struct iio_chan_spec *chan,
 			       enum iio_event_direction dir,
 			       int *val)
 {
-	int ret, tmp;
+	struct ad7380_state *st = iio_priv(indio_dev);
+	const struct iio_scan_type *scan_type;
+	int ret, tmp, shift;
+
+	scan_type = iio_get_current_scan_type(indio_dev, chan);
+	if (IS_ERR(scan_type))
+		return PTR_ERR(scan_type);
+
+	/*
+	 * The register value is 12-bits and is compared to the most significant
+	 * bits of raw value, therefore a shift is required to convert this to
+	 * the same scale as the raw value.
+	 */
+	shift = scan_type->realbits - 12;
 
 	switch (dir) {
 	case IIO_EV_DIR_RISING:
@@ -1625,7 +1638,7 @@ static int ad7380_get_alert_th(struct ad7380_state *st,
 		if (ret)
 			return ret;
 
-		*val = FIELD_GET(AD7380_ALERT_HIGH_TH, tmp);
+		*val = FIELD_GET(AD7380_ALERT_HIGH_TH, tmp) << shift;
 		return IIO_VAL_INT;
 	case IIO_EV_DIR_FALLING:
 		ret = regmap_read(st->regmap,
@@ -1634,7 +1647,7 @@ static int ad7380_get_alert_th(struct ad7380_state *st,
 		if (ret)
 			return ret;
 
-		*val = FIELD_GET(AD7380_ALERT_LOW_TH, tmp);
+		*val = FIELD_GET(AD7380_ALERT_LOW_TH, tmp) << shift;
 		return IIO_VAL_INT;
 	default:
 		return -EINVAL;
@@ -1648,7 +1661,6 @@ static int ad7380_read_event_value(struct iio_dev *indio_dev,
 				   enum iio_event_info info,
 				   int *val, int *val2)
 {
-	struct ad7380_state *st = iio_priv(indio_dev);
 	int ret;
 
 	switch (info) {
@@ -1656,7 +1668,7 @@ static int ad7380_read_event_value(struct iio_dev *indio_dev,
 		if (!iio_device_claim_direct(indio_dev))
 			return -EBUSY;
 
-		ret = ad7380_get_alert_th(st, dir, val);
+		ret = ad7380_get_alert_th(indio_dev, chan, dir, val);
 
 		iio_device_release_direct(indio_dev);
 		return ret;
diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c
index 1a314fddd7eb..703556eb7257 100644
--- a/drivers/iio/adc/ad7606.c
+++ b/drivers/iio/adc/ad7606.c
@@ -1236,9 +1236,11 @@ static int ad7616_sw_mode_setup(struct iio_dev *indio_dev)
 	st->write_scale = ad7616_write_scale_sw;
 	st->write_os = &ad7616_write_os_sw;
 
-	ret = st->bops->sw_mode_config(indio_dev);
-	if (ret)
-		return ret;
+	if (st->bops->sw_mode_config) {
+		ret = st->bops->sw_mode_config(indio_dev);
+		if (ret)
+			return ret;
+	}
 
 	/* Activate Burst mode and SEQEN MODE */
 	return ad7606_write_mask(st, AD7616_CONFIGURATION_REGISTER,
@@ -1268,6 +1270,9 @@ static int ad7606b_sw_mode_setup(struct iio_dev *indio_dev)
 	st->write_scale = ad7606_write_scale_sw;
 	st->write_os = &ad7606_write_os_sw;
 
+	if (!st->bops->sw_mode_config)
+		return 0;
+
 	return st->bops->sw_mode_config(indio_dev);
 }
 
diff --git a/drivers/iio/adc/ad7606_spi.c b/drivers/iio/adc/ad7606_spi.c
index 885bf0b68e77..179115e90988 100644
--- a/drivers/iio/adc/ad7606_spi.c
+++ b/drivers/iio/adc/ad7606_spi.c
@@ -131,7 +131,7 @@ static int ad7606_spi_reg_read(struct ad7606_state *st, unsigned int addr)
 		{
 			.tx_buf = &st->d16[0],
 			.len = 2,
-			.cs_change = 0,
+			.cs_change = 1,
 		}, {
 			.rx_buf = &st->d16[1],
 			.len = 2,
diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c
index 5a863005aca6..5e0be36af0c5 100644
--- a/drivers/iio/adc/ad7768-1.c
+++ b/drivers/iio/adc/ad7768-1.c
@@ -168,7 +168,7 @@ struct ad7768_state {
 	union {
 		struct {
 			__be32 chan;
-			s64 timestamp;
+			aligned_s64 timestamp;
 		} scan;
 		__be32 d32;
 		u8 d8[2];
diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c
index a1e48a756a7b..359e26e3f5bc 100644
--- a/drivers/iio/adc/dln2-adc.c
+++ b/drivers/iio/adc/dln2-adc.c
@@ -466,7 +466,7 @@ static irqreturn_t dln2_adc_trigger_h(int irq, void *p)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct {
 		__le16 values[DLN2_ADC_MAX_CHANNELS];
-		int64_t timestamp_space;
+		aligned_s64 timestamp_space;
 	} data;
 	struct dln2_adc_get_all_vals dev_data;
 	struct dln2_adc *dln2 = iio_priv(indio_dev);
diff --git a/drivers/iio/adc/qcom-spmi-iadc.c b/drivers/iio/adc/qcom-spmi-iadc.c
index 7fb8b2499a1d..b64a8a407168 100644
--- a/drivers/iio/adc/qcom-spmi-iadc.c
+++ b/drivers/iio/adc/qcom-spmi-iadc.c
@@ -543,7 +543,9 @@ static int iadc_probe(struct platform_device *pdev)
 		else
 			return ret;
 	} else {
-		device_init_wakeup(iadc->dev, 1);
+		ret = devm_device_init_wakeup(iadc->dev);
+		if (ret)
+			return dev_err_probe(iadc->dev, ret, "Failed to init wakeup\n");
 	}
 
 	ret = iadc_update_offset(iadc);
diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c
index 9a099df79518..5e28bd28b81a 100644
--- a/drivers/iio/adc/rockchip_saradc.c
+++ b/drivers/iio/adc/rockchip_saradc.c
@@ -520,15 +520,6 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
 	if (info->reset)
 		rockchip_saradc_reset_controller(info->reset);
 
-	/*
-	 * Use a default value for the converter clock.
-	 * This may become user-configurable in the future.
-	 */
-	ret = clk_set_rate(info->clk, info->data->clk_rate);
-	if (ret < 0)
-		return dev_err_probe(&pdev->dev, ret,
-				     "failed to set adc clk rate\n");
-
 	ret = regulator_enable(info->vref);
 	if (ret < 0)
 		return dev_err_probe(&pdev->dev, ret,
@@ -555,6 +546,14 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
 	if (IS_ERR(info->clk))
 		return dev_err_probe(&pdev->dev, PTR_ERR(info->clk),
 				     "failed to get adc clock\n");
+	/*
+	 * Use a default value for the converter clock.
+	 * This may become user-configurable in the future.
+	 */
+	ret = clk_set_rate(info->clk, info->data->clk_rate);
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "failed to set adc clk rate\n");
 
 	platform_set_drvdata(pdev, indio_dev);
 
diff --git a/drivers/iio/chemical/pms7003.c b/drivers/iio/chemical/pms7003.c
index d0bd94912e0a..e05ce1f12065 100644
--- a/drivers/iio/chemical/pms7003.c
+++ b/drivers/iio/chemical/pms7003.c
@@ -5,7 +5,6 @@
  * Copyright (c) Tomasz Duszynski <tduszyns@gmail.com>
  */
 
-#include <linux/unaligned.h>
 #include <linux/completion.h>
 #include <linux/device.h>
 #include <linux/errno.h>
@@ -19,6 +18,8 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/serdev.h>
+#include <linux/types.h>
+#include <linux/unaligned.h>
 
 #define PMS7003_DRIVER_NAME "pms7003"
 
@@ -76,7 +77,7 @@ struct pms7003_state {
 	/* Used to construct scan to push to the IIO buffer */
 	struct {
 		u16 data[3]; /* PM1, PM2P5, PM10 */
-		s64 ts;
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/chemical/sps30.c b/drivers/iio/chemical/sps30.c
index 6f4f2ba2c09d..a7888146188d 100644
--- a/drivers/iio/chemical/sps30.c
+++ b/drivers/iio/chemical/sps30.c
@@ -108,7 +108,7 @@ static irqreturn_t sps30_trigger_handler(int irq, void *p)
 	int ret;
 	struct {
 		s32 data[4]; /* PM1, PM2P5, PM4, PM10 */
-		s64 ts;
+		aligned_s64 ts;
 	} scan;
 
 	mutex_lock(&state->lock);
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
index ad1882f608c0..2055a03cbeb1 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
@@ -66,6 +66,10 @@ static struct {
 	{HID_USAGE_SENSOR_HUMIDITY, 0, 1000, 0},
 	{HID_USAGE_SENSOR_HINGE, 0, 0, 17453293},
 	{HID_USAGE_SENSOR_HINGE, HID_USAGE_SENSOR_UNITS_DEGREES, 0, 17453293},
+
+	{HID_USAGE_SENSOR_HUMAN_PRESENCE, 0, 1, 0},
+	{HID_USAGE_SENSOR_HUMAN_PROXIMITY, 0, 1, 0},
+	{HID_USAGE_SENSOR_HUMAN_ATTENTION, 0, 1, 0},
 };
 
 static void simple_div(int dividend, int divisor, int *whole,
diff --git a/drivers/iio/imu/adis16550.c b/drivers/iio/imu/adis16550.c
index b14ea8937c7f..28f0dbd0226c 100644
--- a/drivers/iio/imu/adis16550.c
+++ b/drivers/iio/imu/adis16550.c
@@ -836,7 +836,7 @@ static irqreturn_t adis16550_trigger_handler(int irq, void *p)
 	u16 dummy;
 	bool valid;
 	struct iio_poll_func *pf = p;
-	__be32 data[ADIS16550_MAX_SCAN_DATA];
+	__be32 data[ADIS16550_MAX_SCAN_DATA] __aligned(8);
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct adis16550 *st = iio_priv(indio_dev);
 	struct adis *adis = iio_device_get_drvdata(indio_dev);
diff --git a/drivers/iio/imu/bmi270/bmi270_core.c b/drivers/iio/imu/bmi270/bmi270_core.c
index a86be5af5ccb..2e4469f30d53 100644
--- a/drivers/iio/imu/bmi270/bmi270_core.c
+++ b/drivers/iio/imu/bmi270/bmi270_core.c
@@ -918,8 +918,7 @@ static int bmi270_configure_imu(struct bmi270_data *data)
 			      FIELD_PREP(BMI270_ACC_CONF_ODR_MSK,
 					 BMI270_ACC_CONF_ODR_100HZ) |
 			      FIELD_PREP(BMI270_ACC_CONF_BWP_MSK,
-					 BMI270_ACC_CONF_BWP_NORMAL_MODE) |
-			      BMI270_PWR_CONF_ADV_PWR_SAVE_MSK);
+					 BMI270_ACC_CONF_BWP_NORMAL_MODE));
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to configure accelerometer");
 
@@ -927,8 +926,7 @@ static int bmi270_configure_imu(struct bmi270_data *data)
 			      FIELD_PREP(BMI270_GYR_CONF_ODR_MSK,
 					 BMI270_GYR_CONF_ODR_200HZ) |
 			      FIELD_PREP(BMI270_GYR_CONF_BWP_MSK,
-					 BMI270_GYR_CONF_BWP_NORMAL_MODE) |
-			      BMI270_PWR_CONF_ADV_PWR_SAVE_MSK);
+					 BMI270_GYR_CONF_BWP_NORMAL_MODE));
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to configure gyroscope");
 
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
index 3d3b27f28c9d..273196e647a2 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
@@ -50,7 +50,7 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
 	u16 fifo_count;
 	u32 fifo_period;
 	s64 timestamp;
-	u8 data[INV_MPU6050_OUTPUT_DATA_SIZE];
+	u8 data[INV_MPU6050_OUTPUT_DATA_SIZE] __aligned(8);
 	size_t i, nb;
 
 	mutex_lock(&st->lock);
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index 0a7cd8c1aa33..8a9d2593576a 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -392,6 +392,9 @@ int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw)
 	if (fifo_status & cpu_to_le16(ST_LSM6DSX_FIFO_EMPTY_MASK))
 		return 0;
 
+	if (!pattern_len)
+		pattern_len = ST_LSM6DSX_SAMPLE_SIZE;
+
 	fifo_len = (le16_to_cpu(fifo_status) & fifo_diff_mask) *
 		   ST_LSM6DSX_CHAN_SIZE;
 	fifo_len = (fifo_len / pattern_len) * pattern_len;
@@ -623,6 +626,9 @@ int st_lsm6dsx_read_tagged_fifo(struct st_lsm6dsx_hw *hw)
 	if (!fifo_len)
 		return 0;
 
+	if (!pattern_len)
+		pattern_len = ST_LSM6DSX_TAGGED_SAMPLE_SIZE;
+
 	for (read_len = 0; read_len < fifo_len; read_len += pattern_len) {
 		err = st_lsm6dsx_read_block(hw,
 					    ST_LSM6DSX_REG_FIFO_OUT_TAG_ADDR,
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
index 4fdcc2acc94e..96c6106b95ee 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
@@ -2719,8 +2719,11 @@ int st_lsm6dsx_probe(struct device *dev, int irq, int hw_id,
 	}
 
 	if (device_property_read_bool(dev, "wakeup-source") ||
-	    (pdata && pdata->wakeup_source))
-		device_init_wakeup(dev, true);
+	    (pdata && pdata->wakeup_source)) {
+		err = devm_device_init_wakeup(dev);
+		if (err)
+			return dev_err_probe(dev, err, "Failed to init wakeup\n");
+	}
 
 	return 0;
 }
diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index 76b76d12b388..4c65b32d34ce 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -34,9 +34,9 @@ struct prox_state {
 	struct iio_chan_spec channels[MAX_CHANNELS];
 	u32 channel2usage[MAX_CHANNELS];
 	u32 human_presence[MAX_CHANNELS];
-	int scale_pre_decml;
-	int scale_post_decml;
-	int scale_precision;
+	int scale_pre_decml[MAX_CHANNELS];
+	int scale_post_decml[MAX_CHANNELS];
+	int scale_precision[MAX_CHANNELS];
 	unsigned long scan_mask[2]; /* One entry plus one terminator. */
 	int num_channels;
 };
@@ -116,13 +116,15 @@ static int prox_read_raw(struct iio_dev *indio_dev,
 		ret_type = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SCALE:
-		*val = prox_state->scale_pre_decml;
-		*val2 = prox_state->scale_post_decml;
-		ret_type = prox_state->scale_precision;
+		if (chan->scan_index >= prox_state->num_channels)
+			return -EINVAL;
+
+		*val = prox_state->scale_pre_decml[chan->scan_index];
+		*val2 = prox_state->scale_post_decml[chan->scan_index];
+		ret_type = prox_state->scale_precision[chan->scan_index];
 		break;
 	case IIO_CHAN_INFO_OFFSET:
-		*val = hid_sensor_convert_exponent(
-			prox_state->prox_attr[chan->scan_index].unit_expo);
+		*val = 0;
 		ret_type = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SAMP_FREQ:
@@ -249,6 +251,10 @@ static int prox_parse_report(struct platform_device *pdev,
 					     st->prox_attr[index].size);
 		dev_dbg(&pdev->dev, "prox %x:%x\n", st->prox_attr[index].index,
 			st->prox_attr[index].report_id);
+		st->scale_precision[index] =
+			hid_sensor_format_scale(usage_id, &st->prox_attr[index],
+						&st->scale_pre_decml[index],
+						&st->scale_post_decml[index]);
 		index++;
 	}
 
diff --git a/drivers/iio/light/opt3001.c b/drivers/iio/light/opt3001.c
index 65b295877b41..393a3d2fbe1d 100644
--- a/drivers/iio/light/opt3001.c
+++ b/drivers/iio/light/opt3001.c
@@ -788,8 +788,9 @@ static irqreturn_t opt3001_irq(int irq, void *_iio)
 	int ret;
 	bool wake_result_ready_queue = false;
 	enum iio_chan_type chan_type = opt->chip_info->chan_type;
+	bool ok_to_ignore_lock = opt->ok_to_ignore_lock;
 
-	if (!opt->ok_to_ignore_lock)
+	if (!ok_to_ignore_lock)
 		mutex_lock(&opt->lock);
 
 	ret = i2c_smbus_read_word_swapped(opt->client, OPT3001_CONFIGURATION);
@@ -826,7 +827,7 @@ static irqreturn_t opt3001_irq(int irq, void *_iio)
 	}
 
 out:
-	if (!opt->ok_to_ignore_lock)
+	if (!ok_to_ignore_lock)
 		mutex_unlock(&opt->lock);
 
 	if (wake_result_ready_queue)
diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c
index 08975c60e325..7bc341c69697 100644
--- a/drivers/iio/magnetometer/ak8974.c
+++ b/drivers/iio/magnetometer/ak8974.c
@@ -535,8 +535,8 @@ static int ak8974_detect(struct ak8974 *ak8974)
 				       fab_data2, sizeof(fab_data2));
 
 		for (i = 0; i < 3; ++i) {
-			static const char axis[3] = "XYZ";
-			static const char pgaxis[6] = "ZYZXYX";
+			static const char axis[] = "XYZ";
+			static const char pgaxis[] = "ZYZXYX";
 			unsigned offz = le16_to_cpu(fab_data2[i]) & 0x7F;
 			unsigned fine = le16_to_cpu(fab_data1[i]);
 			unsigned sens = le16_to_cpu(fab_data1[i + 3]);
diff --git a/drivers/iio/pressure/mprls0025pa.h b/drivers/iio/pressure/mprls0025pa.h
index 9d5c30afa9d6..d62a018eaff3 100644
--- a/drivers/iio/pressure/mprls0025pa.h
+++ b/drivers/iio/pressure/mprls0025pa.h
@@ -34,16 +34,6 @@ struct iio_dev;
 struct mpr_data;
 struct mpr_ops;
 
-/**
- * struct mpr_chan
- * @pres: pressure value
- * @ts: timestamp
- */
-struct mpr_chan {
-	s32 pres;
-	s64 ts;
-};
-
 enum mpr_func_id {
 	MPR_FUNCTION_A,
 	MPR_FUNCTION_B,
@@ -69,6 +59,8 @@ enum mpr_func_id {
  *       reading in a loop until data is ready
  * @completion: handshake from irq to read
  * @chan: channel values for buffered mode
+ * @chan.pres: pressure value
+ * @chan.ts: timestamp
  * @buffer: raw conversion data
  */
 struct mpr_data {
@@ -87,7 +79,10 @@ struct mpr_data {
 	struct gpio_desc	*gpiod_reset;
 	int			irq;
 	struct completion	completion;
-	struct mpr_chan		chan;
+	struct {
+		s32 pres;
+		aligned_s64 ts;
+	} chan;
 	u8	    buffer[MPR_MEASUREMENT_RD_SIZE] __aligned(IIO_DMA_MINALIGN);
 };
 
diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c
index c28a7a6dea5f..555a61e2f3fd 100644
--- a/drivers/iio/temperature/maxim_thermocouple.c
+++ b/drivers/iio/temperature/maxim_thermocouple.c
@@ -121,9 +121,9 @@ static const struct maxim_thermocouple_chip maxim_thermocouple_chips[] = {
 struct maxim_thermocouple_data {
 	struct spi_device *spi;
 	const struct maxim_thermocouple_chip *chip;
+	char tc_type;
 
 	u8 buffer[16] __aligned(IIO_DMA_MINALIGN);
-	char tc_type;
 };
 
 static int maxim_thermocouple_read(struct maxim_thermocouple_data *data,
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index fedcdb56fb6b..ab31eefa916b 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -72,6 +72,8 @@ static const char * const cma_events[] = {
 static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid,
 			      enum ib_gid_type gid_type);
 
+static void cma_netevent_work_handler(struct work_struct *_work);
+
 const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event)
 {
 	size_t index = event;
@@ -1047,6 +1049,7 @@ __rdma_create_id(struct net *net, rdma_cm_event_handler event_handler,
 	get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num);
 	id_priv->id.route.addr.dev_addr.net = get_net(net);
 	id_priv->seq_num &= 0x00ffffff;
+	INIT_WORK(&id_priv->id.net_work, cma_netevent_work_handler);
 
 	rdma_restrack_new(&id_priv->res, RDMA_RESTRACK_CM_ID);
 	if (parent)
@@ -5241,7 +5244,6 @@ static int cma_netevent_callback(struct notifier_block *self,
 		if (!memcmp(current_id->id.route.addr.dev_addr.dst_dev_addr,
 			   neigh->ha, ETH_ALEN))
 			continue;
-		INIT_WORK(&current_id->id.net_work, cma_netevent_work_handler);
 		cma_id_get(current_id);
 		queue_work(cma_wq, &current_id->id.net_work);
 	}
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index b4e3e4beb7f4..d4263385850a 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1352,6 +1352,9 @@ static void ib_device_notify_register(struct ib_device *device)
 
 	down_read(&devices_rwsem);
 
+	/* Mark for userspace that device is ready */
+	kobject_uevent(&device->dev.kobj, KOBJ_ADD);
+
 	ret = rdma_nl_notify_event(device, 0, RDMA_REGISTER_EVENT);
 	if (ret)
 		goto out;
@@ -1468,10 +1471,9 @@ int ib_register_device(struct ib_device *device, const char *name,
 		return ret;
 	}
 	dev_set_uevent_suppress(&device->dev, false);
-	/* Mark for userspace that device is ready */
-	kobject_uevent(&device->dev.kobj, KOBJ_ADD);
 
 	ib_device_notify_register(device);
+
 	ib_device_put(device);
 
 	return 0;
diff --git a/drivers/infiniband/core/ucaps.c b/drivers/infiniband/core/ucaps.c
index 6853c6d078f9..de5cb8bf0a61 100644
--- a/drivers/infiniband/core/ucaps.c
+++ b/drivers/infiniband/core/ucaps.c
@@ -170,7 +170,7 @@ int ib_create_ucap(enum rdma_user_cap type)
 	ucap->dev.class = &ucaps_class;
 	ucap->dev.devt = MKDEV(MAJOR(ucaps_base_dev), type);
 	ucap->dev.release = ucap_dev_release;
-	ret = dev_set_name(&ucap->dev, ucap_names[type]);
+	ret = dev_set_name(&ucap->dev, "%s", ucap_names[type]);
 	if (ret)
 		goto err_device;
 
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index e9fa22d31c23..c48ef6083020 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -76,12 +76,14 @@ static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
 
 		npfns = (end - start) >> PAGE_SHIFT;
 		umem_odp->pfn_list = kvcalloc(
-			npfns, sizeof(*umem_odp->pfn_list), GFP_KERNEL);
+			npfns, sizeof(*umem_odp->pfn_list),
+			GFP_KERNEL | __GFP_NOWARN);
 		if (!umem_odp->pfn_list)
 			return -ENOMEM;
 
 		umem_odp->dma_list = kvcalloc(
-			ndmas, sizeof(*umem_odp->dma_list), GFP_KERNEL);
+			ndmas, sizeof(*umem_odp->dma_list),
+			GFP_KERNEL | __GFP_NOWARN);
 		if (!umem_odp->dma_list) {
 			ret = -ENOMEM;
 			goto out_pfn_list;
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 9082b3fd2b47..063801384b2b 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -1774,10 +1774,7 @@ int bnxt_re_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata)
 					       ib_srq);
 	struct bnxt_re_dev *rdev = srq->rdev;
 	struct bnxt_qplib_srq *qplib_srq = &srq->qplib_srq;
-	struct bnxt_qplib_nq *nq = NULL;
 
-	if (qplib_srq->cq)
-		nq = qplib_srq->cq->nq;
 	if (rdev->chip_ctx->modes.toggle_bits & BNXT_QPLIB_SRQ_TOGGLE_BIT) {
 		free_page((unsigned long)srq->uctx_srq_page);
 		hash_del(&srq->hash_entry);
@@ -1785,8 +1782,6 @@ int bnxt_re_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata)
 	bnxt_qplib_destroy_srq(&rdev->qplib_res, qplib_srq);
 	ib_umem_release(srq->umem);
 	atomic_dec(&rdev->stats.res.srq_count);
-	if (nq)
-		nq->budget--;
 	return 0;
 }
 
@@ -1827,7 +1822,6 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 		       struct ib_udata *udata)
 {
 	struct bnxt_qplib_dev_attr *dev_attr;
-	struct bnxt_qplib_nq *nq = NULL;
 	struct bnxt_re_ucontext *uctx;
 	struct bnxt_re_dev *rdev;
 	struct bnxt_re_srq *srq;
@@ -1873,7 +1867,6 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 	srq->qplib_srq.eventq_hw_ring_id = rdev->nqr->nq[0].ring_id;
 	srq->qplib_srq.sg_info.pgsize = PAGE_SIZE;
 	srq->qplib_srq.sg_info.pgshft = PAGE_SHIFT;
-	nq = &rdev->nqr->nq[0];
 
 	if (udata) {
 		rc = bnxt_re_init_user_srq(rdev, pd, srq, udata);
@@ -1908,8 +1901,6 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 			goto fail;
 		}
 	}
-	if (nq)
-		nq->budget++;
 	active_srqs = atomic_inc_return(&rdev->stats.res.srq_count);
 	if (active_srqs > rdev->stats.res.srq_watermark)
 		rdev->stats.res.srq_watermark = active_srqs;
@@ -3079,7 +3070,6 @@ int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 	ib_umem_release(cq->umem);
 
 	atomic_dec(&rdev->stats.res.cq_count);
-	nq->budget--;
 	kfree(cq->cql);
 	return 0;
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index cf89a8db4f64..8d0b63d4b50a 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -763,7 +763,7 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 		if (ret)
 			return ret;
 	}
-	dma_set_max_seg_size(dev, UINT_MAX);
+	dma_set_max_seg_size(dev, SZ_2G);
 	ret = ib_register_device(ib_dev, "hns_%d", dev);
 	if (ret) {
 		dev_err(dev, "ib_register_device failed!\n");
diff --git a/drivers/infiniband/hw/irdma/main.c b/drivers/infiniband/hw/irdma/main.c
index 1ee8969595d3..1e840bbd619d 100644
--- a/drivers/infiniband/hw/irdma/main.c
+++ b/drivers/infiniband/hw/irdma/main.c
@@ -1,10 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2015 - 2021 Intel Corporation */
 #include "main.h"
-#include "../../../net/ethernet/intel/ice/ice.h"
 
 MODULE_ALIAS("i40iw");
-MODULE_AUTHOR("Intel Corporation, <e1000-rdma@lists.sourceforge.net>");
 MODULE_DESCRIPTION("Intel(R) Ethernet Protocol Driver for RDMA");
 MODULE_LICENSE("Dual BSD/GPL");
 
@@ -61,7 +59,7 @@ static void irdma_log_invalid_mtu(u16 mtu, struct irdma_sc_dev *dev)
 }
 
 static void irdma_fill_qos_info(struct irdma_l2params *l2params,
-				struct iidc_qos_params *qos_info)
+				struct iidc_rdma_qos_params *qos_info)
 {
 	int i;
 
@@ -85,12 +83,13 @@ static void irdma_fill_qos_info(struct irdma_l2params *l2params,
 	}
 }
 
-static void irdma_iidc_event_handler(struct ice_pf *pf, struct iidc_event *event)
+static void irdma_iidc_event_handler(struct iidc_rdma_core_dev_info *cdev_info,
+				     struct iidc_rdma_event *event)
 {
-	struct irdma_device *iwdev = dev_get_drvdata(&pf->adev->dev);
+	struct irdma_device *iwdev = dev_get_drvdata(&cdev_info->adev->dev);
 	struct irdma_l2params l2params = {};
 
-	if (*event->type & BIT(IIDC_EVENT_AFTER_MTU_CHANGE)) {
+	if (*event->type & BIT(IIDC_RDMA_EVENT_AFTER_MTU_CHANGE)) {
 		ibdev_dbg(&iwdev->ibdev, "CLNT: new MTU = %d\n", iwdev->netdev->mtu);
 		if (iwdev->vsi.mtu != iwdev->netdev->mtu) {
 			l2params.mtu = iwdev->netdev->mtu;
@@ -98,25 +97,26 @@ static void irdma_iidc_event_handler(struct ice_pf *pf, struct iidc_event *event
 			irdma_log_invalid_mtu(l2params.mtu, &iwdev->rf->sc_dev);
 			irdma_change_l2params(&iwdev->vsi, &l2params);
 		}
-	} else if (*event->type & BIT(IIDC_EVENT_BEFORE_TC_CHANGE)) {
+	} else if (*event->type & BIT(IIDC_RDMA_EVENT_BEFORE_TC_CHANGE)) {
 		if (iwdev->vsi.tc_change_pending)
 			return;
 
 		irdma_prep_tc_change(iwdev);
-	} else if (*event->type & BIT(IIDC_EVENT_AFTER_TC_CHANGE)) {
-		struct iidc_qos_params qos_info = {};
+	} else if (*event->type & BIT(IIDC_RDMA_EVENT_AFTER_TC_CHANGE)) {
+		struct iidc_rdma_priv_dev_info *iidc_priv = cdev_info->iidc_priv;
 
 		if (!iwdev->vsi.tc_change_pending)
 			return;
 
 		l2params.tc_changed = true;
 		ibdev_dbg(&iwdev->ibdev, "CLNT: TC Change\n");
-		ice_get_qos_params(pf, &qos_info);
-		irdma_fill_qos_info(&l2params, &qos_info);
+
+		irdma_fill_qos_info(&l2params, &iidc_priv->qos_info);
 		if (iwdev->rf->protocol_used != IRDMA_IWARP_PROTOCOL_ONLY)
-			iwdev->dcb_vlan_mode = qos_info.num_tc > 1 && !l2params.dscp_mode;
+			iwdev->dcb_vlan_mode =
+				l2params.num_tc > 1 && !l2params.dscp_mode;
 		irdma_change_l2params(&iwdev->vsi, &l2params);
-	} else if (*event->type & BIT(IIDC_EVENT_CRIT_ERR)) {
+	} else if (*event->type & BIT(IIDC_RDMA_EVENT_CRIT_ERR)) {
 		ibdev_warn(&iwdev->ibdev, "ICE OICR event notification: oicr = 0x%08x\n",
 			   event->reg);
 		if (event->reg & IRDMAPFINT_OICR_PE_CRITERR_M) {
@@ -151,10 +151,8 @@ static void irdma_iidc_event_handler(struct ice_pf *pf, struct iidc_event *event
  */
 static void irdma_request_reset(struct irdma_pci_f *rf)
 {
-	struct ice_pf *pf = rf->cdev;
-
 	ibdev_warn(&rf->iwdev->ibdev, "Requesting a reset\n");
-	ice_rdma_request_reset(pf, IIDC_PFR);
+	ice_rdma_request_reset(rf->cdev, IIDC_FUNC_RESET);
 }
 
 /**
@@ -166,14 +164,15 @@ static int irdma_lan_register_qset(struct irdma_sc_vsi *vsi,
 				   struct irdma_ws_node *tc_node)
 {
 	struct irdma_device *iwdev = vsi->back_vsi;
-	struct ice_pf *pf = iwdev->rf->cdev;
+	struct iidc_rdma_core_dev_info *cdev_info;
 	struct iidc_rdma_qset_params qset = {};
 	int ret;
 
+	cdev_info = iwdev->rf->cdev;
 	qset.qs_handle = tc_node->qs_handle;
 	qset.tc = tc_node->traffic_class;
 	qset.vport_id = vsi->vsi_idx;
-	ret = ice_add_rdma_qset(pf, &qset);
+	ret = ice_add_rdma_qset(cdev_info, &qset);
 	if (ret) {
 		ibdev_dbg(&iwdev->ibdev, "WS: LAN alloc_res for rdma qset failed.\n");
 		return ret;
@@ -194,19 +193,20 @@ static void irdma_lan_unregister_qset(struct irdma_sc_vsi *vsi,
 				      struct irdma_ws_node *tc_node)
 {
 	struct irdma_device *iwdev = vsi->back_vsi;
-	struct ice_pf *pf = iwdev->rf->cdev;
+	struct iidc_rdma_core_dev_info *cdev_info;
 	struct iidc_rdma_qset_params qset = {};
 
+	cdev_info = iwdev->rf->cdev;
 	qset.qs_handle = tc_node->qs_handle;
 	qset.tc = tc_node->traffic_class;
 	qset.vport_id = vsi->vsi_idx;
 	qset.teid = tc_node->l2_sched_node_id;
 
-	if (ice_del_rdma_qset(pf, &qset))
+	if (ice_del_rdma_qset(cdev_info, &qset))
 		ibdev_dbg(&iwdev->ibdev, "WS: LAN free_res for rdma qset failed.\n");
 }
 
-static int irdma_init_interrupts(struct irdma_pci_f *rf, struct ice_pf *pf)
+static int irdma_init_interrupts(struct irdma_pci_f *rf, struct iidc_rdma_core_dev_info *cdev)
 {
 	int i;
 
@@ -217,12 +217,12 @@ static int irdma_init_interrupts(struct irdma_pci_f *rf, struct ice_pf *pf)
 		return -ENOMEM;
 
 	for (i = 0; i < rf->msix_count; i++)
-		if (ice_alloc_rdma_qvector(pf, &rf->msix_entries[i]))
+		if (ice_alloc_rdma_qvector(cdev, &rf->msix_entries[i]))
 			break;
 
 	if (i < IRDMA_MIN_MSIX) {
-		for (; i > 0; i--)
-			ice_free_rdma_qvector(pf, &rf->msix_entries[i]);
+		while (--i >= 0)
+			ice_free_rdma_qvector(cdev, &rf->msix_entries[i]);
 
 		kfree(rf->msix_entries);
 		return -ENOMEM;
@@ -233,54 +233,65 @@ static int irdma_init_interrupts(struct irdma_pci_f *rf, struct ice_pf *pf)
 	return 0;
 }
 
-static void irdma_deinit_interrupts(struct irdma_pci_f *rf, struct ice_pf *pf)
+static void irdma_deinit_interrupts(struct irdma_pci_f *rf, struct iidc_rdma_core_dev_info *cdev)
 {
 	int i;
 
 	for (i = 0; i < rf->msix_count; i++)
-		ice_free_rdma_qvector(pf, &rf->msix_entries[i]);
+		ice_free_rdma_qvector(cdev, &rf->msix_entries[i]);
 
 	kfree(rf->msix_entries);
 }
 
 static void irdma_remove(struct auxiliary_device *aux_dev)
 {
-	struct iidc_auxiliary_dev *iidc_adev = container_of(aux_dev,
-							    struct iidc_auxiliary_dev,
-							    adev);
-	struct ice_pf *pf = iidc_adev->pf;
 	struct irdma_device *iwdev = auxiliary_get_drvdata(aux_dev);
+	struct iidc_rdma_core_auxiliary_dev *iidc_adev;
+	struct iidc_rdma_core_dev_info *cdev_info;
+
+	iidc_adev = container_of(aux_dev, struct iidc_rdma_core_auxiliary_dev, adev);
+	cdev_info = iidc_adev->cdev_info;
 
+	ice_rdma_update_vsi_filter(cdev_info, iwdev->vsi_num, false);
 	irdma_ib_unregister_device(iwdev);
-	ice_rdma_update_vsi_filter(pf, iwdev->vsi_num, false);
-	irdma_deinit_interrupts(iwdev->rf, pf);
+	irdma_deinit_interrupts(iwdev->rf, cdev_info);
 
-	pr_debug("INIT: Gen2 PF[%d] device remove success\n", PCI_FUNC(pf->pdev->devfn));
+	kfree(iwdev->rf);
+
+	pr_debug("INIT: Gen2 PF[%d] device remove success\n", PCI_FUNC(cdev_info->pdev->devfn));
 }
 
-static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf,
-				   struct ice_vsi *vsi)
+static void irdma_fill_device_info(struct irdma_device *iwdev,
+				   struct iidc_rdma_core_dev_info *cdev_info)
 {
+	struct iidc_rdma_priv_dev_info *iidc_priv = cdev_info->iidc_priv;
 	struct irdma_pci_f *rf = iwdev->rf;
 
-	rf->cdev = pf;
+	rf->sc_dev.hw = &rf->hw;
+	rf->iwdev = iwdev;
+	rf->cdev = cdev_info;
+	rf->hw.hw_addr = iidc_priv->hw_addr;
+	rf->pcidev = cdev_info->pdev;
+	rf->hw.device = &rf->pcidev->dev;
+	rf->pf_id = iidc_priv->pf_id;
 	rf->gen_ops.register_qset = irdma_lan_register_qset;
 	rf->gen_ops.unregister_qset = irdma_lan_unregister_qset;
-	rf->hw.hw_addr = pf->hw.hw_addr;
-	rf->pcidev = pf->pdev;
-	rf->pf_id = pf->hw.pf_id;
-	rf->default_vsi.vsi_idx = vsi->vsi_num;
-	rf->protocol_used = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ?
-			    IRDMA_ROCE_PROTOCOL_ONLY : IRDMA_IWARP_PROTOCOL_ONLY;
+
+	rf->default_vsi.vsi_idx = iidc_priv->vport_id;
+	rf->protocol_used =
+		cdev_info->rdma_protocol == IIDC_RDMA_PROTOCOL_ROCEV2 ?
+		IRDMA_ROCE_PROTOCOL_ONLY : IRDMA_IWARP_PROTOCOL_ONLY;
 	rf->rdma_ver = IRDMA_GEN_2;
 	rf->rsrc_profile = IRDMA_HMC_PROFILE_DEFAULT;
 	rf->rst_to = IRDMA_RST_TIMEOUT_HZ;
 	rf->gen_ops.request_reset = irdma_request_reset;
 	rf->limits_sel = 7;
 	rf->iwdev = iwdev;
+
 	mutex_init(&iwdev->ah_tbl_lock);
-	iwdev->netdev = vsi->netdev;
-	iwdev->vsi_num = vsi->vsi_num;
+
+	iwdev->netdev = iidc_priv->netdev;
+	iwdev->vsi_num = iidc_priv->vport_id;
 	iwdev->init_state = INITIAL_STATE;
 	iwdev->roce_cwnd = IRDMA_ROCE_CWND_DEFAULT;
 	iwdev->roce_ackcreds = IRDMA_ROCE_ACKCREDS_DEFAULT;
@@ -292,19 +303,18 @@ static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf
 
 static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_device_id *id)
 {
-	struct iidc_auxiliary_dev *iidc_adev = container_of(aux_dev,
-							    struct iidc_auxiliary_dev,
-							    adev);
-	struct ice_pf *pf = iidc_adev->pf;
-	struct ice_vsi *vsi = ice_get_main_vsi(pf);
-	struct iidc_qos_params qos_info = {};
+	struct iidc_rdma_core_auxiliary_dev *iidc_adev;
+	struct iidc_rdma_core_dev_info *cdev_info;
+	struct iidc_rdma_priv_dev_info *iidc_priv;
+	struct irdma_l2params l2params = {};
 	struct irdma_device *iwdev;
 	struct irdma_pci_f *rf;
-	struct irdma_l2params l2params = {};
 	int err;
 
-	if (!vsi)
-		return -EIO;
+	iidc_adev = container_of(aux_dev, struct iidc_rdma_core_auxiliary_dev, adev);
+	cdev_info = iidc_adev->cdev_info;
+	iidc_priv = cdev_info->iidc_priv;
+
 	iwdev = ib_alloc_device(irdma_device, ibdev);
 	if (!iwdev)
 		return -ENOMEM;
@@ -314,10 +324,10 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_
 		return -ENOMEM;
 	}
 
-	irdma_fill_device_info(iwdev, pf, vsi);
+	irdma_fill_device_info(iwdev, cdev_info);
 	rf = iwdev->rf;
 
-	err = irdma_init_interrupts(rf, pf);
+	err = irdma_init_interrupts(rf, cdev_info);
 	if (err)
 		goto err_init_interrupts;
 
@@ -326,8 +336,7 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_
 		goto err_ctrl_init;
 
 	l2params.mtu = iwdev->netdev->mtu;
-	ice_get_qos_params(pf, &qos_info);
-	irdma_fill_qos_info(&l2params, &qos_info);
+	irdma_fill_qos_info(&l2params, &iidc_priv->qos_info);
 	if (iwdev->rf->protocol_used != IRDMA_IWARP_PROTOCOL_ONLY)
 		iwdev->dcb_vlan_mode = l2params.num_tc > 1 && !l2params.dscp_mode;
 
@@ -339,7 +348,7 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_
 	if (err)
 		goto err_ibreg;
 
-	ice_rdma_update_vsi_filter(pf, iwdev->vsi_num, true);
+	ice_rdma_update_vsi_filter(cdev_info, iwdev->vsi_num, true);
 
 	ibdev_dbg(&iwdev->ibdev, "INIT: Gen2 PF[%d] device probe success\n", PCI_FUNC(rf->pcidev->devfn));
 	auxiliary_set_drvdata(aux_dev, iwdev);
@@ -351,7 +360,7 @@ err_ibreg:
 err_rt_init:
 	irdma_ctrl_deinit_hw(rf);
 err_ctrl_init:
-	irdma_deinit_interrupts(rf, pf);
+	irdma_deinit_interrupts(rf, cdev_info);
 err_init_interrupts:
 	kfree(iwdev->rf);
 	ib_dealloc_device(&iwdev->ibdev);
@@ -367,7 +376,7 @@ static const struct auxiliary_device_id irdma_auxiliary_id_table[] = {
 
 MODULE_DEVICE_TABLE(auxiliary, irdma_auxiliary_id_table);
 
-static struct iidc_auxiliary_drv irdma_auxiliary_drv = {
+static struct iidc_rdma_core_auxiliary_drv irdma_auxiliary_drv = {
 	.adrv = {
 	    .id_table = irdma_auxiliary_id_table,
 	    .probe = irdma_probe,
diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h
index bb0b6494ccb2..674acc952168 100644
--- a/drivers/infiniband/hw/irdma/main.h
+++ b/drivers/infiniband/hw/irdma/main.h
@@ -29,7 +29,8 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 #endif
 #include <linux/auxiliary_bus.h>
-#include <linux/net/intel/iidc.h>
+#include <linux/net/intel/iidc_rdma.h>
+#include <linux/net/intel/iidc_rdma_ice.h>
 #include <rdma/ib_smi.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_pack.h>
diff --git a/drivers/infiniband/hw/irdma/osdep.h b/drivers/infiniband/hw/irdma/osdep.h
index 4b4f78288d12..3f73ceacccb6 100644
--- a/drivers/infiniband/hw/irdma/osdep.h
+++ b/drivers/infiniband/hw/irdma/osdep.h
@@ -5,8 +5,8 @@
 
 #include <linux/pci.h>
 #include <linux/bitfield.h>
-#include <linux/net/intel/iidc.h>
 #include <rdma/ib_verbs.h>
+#include <net/dscp.h>
 
 #define STATS_TIMER_DELAY	60000
 
diff --git a/drivers/infiniband/hw/irdma/type.h b/drivers/infiniband/hw/irdma/type.h
index 59b34afa867b..527c6da2c1ac 100644
--- a/drivers/infiniband/hw/irdma/type.h
+++ b/drivers/infiniband/hw/irdma/type.h
@@ -567,7 +567,7 @@ struct irdma_sc_vsi {
 	u8 qos_rel_bw;
 	u8 qos_prio_type;
 	u8 stats_idx;
-	u8 dscp_map[IIDC_MAX_DSCP_MAPPING];
+	u8 dscp_map[DSCP_MAX];
 	struct irdma_qos qos[IRDMA_MAX_USER_PRIORITY];
 	u64 hw_stats_regs[IRDMA_HW_STAT_INDEX_MAX_GEN_1];
 	bool dscp_mode:1;
@@ -695,7 +695,7 @@ struct irdma_l2params {
 	u16 qs_handle_list[IRDMA_MAX_USER_PRIORITY];
 	u16 mtu;
 	u8 up2tc[IRDMA_MAX_USER_PRIORITY];
-	u8 dscp_map[IIDC_MAX_DSCP_MAPPING];
+	u8 dscp_map[DSCP_MAX];
 	u8 num_tc;
 	u8 vsi_rel_bw;
 	u8 vsi_prio_type;
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index eeb932e58730..1e8c92826de2 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -4871,5 +4871,4 @@ void irdma_ib_dealloc_device(struct ib_device *ibdev)
 
 	irdma_rt_deinit_hw(iwdev);
 	irdma_ctrl_deinit_hw(iwdev->rf);
-	kfree(iwdev->rf);
 }
diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c
index 251246c73b33..0ff9f18a71e8 100644
--- a/drivers/infiniband/hw/mlx5/fs.c
+++ b/drivers/infiniband/hw/mlx5/fs.c
@@ -3461,7 +3461,6 @@ DECLARE_UVERBS_NAMED_OBJECT(
 	&UVERBS_METHOD(MLX5_IB_METHOD_STEERING_ANCHOR_DESTROY));
 
 const struct uapi_definition mlx5_ib_flow_defs[] = {
-#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(
 		MLX5_IB_OBJECT_FLOW_MATCHER),
 	UAPI_DEF_CHAIN_OBJ_TREE(
@@ -3472,7 +3471,6 @@ const struct uapi_definition mlx5_ib_flow_defs[] = {
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(
 		MLX5_IB_OBJECT_STEERING_ANCHOR,
 		UAPI_DEF_IS_OBJ_SUPPORTED(mlx5_ib_shared_ft_allowed)),
-#endif
 	{},
 };
 
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c
index 4ddcd5860e0f..11eca39b73a9 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_main.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c
@@ -397,7 +397,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev)
 	if (!us_ibdev) {
 		usnic_err("Device %s context alloc failed\n",
 				netdev_name(pci_get_drvdata(dev)));
-		return ERR_PTR(-EFAULT);
+		return NULL;
 	}
 
 	us_ibdev->ufdev = usnic_fwd_dev_alloc(dev);
@@ -517,8 +517,8 @@ static struct usnic_ib_dev *usnic_ib_discover_pf(struct usnic_vnic *vnic)
 	}
 
 	us_ibdev = usnic_ib_device_add(parent_pci);
-	if (IS_ERR_OR_NULL(us_ibdev)) {
-		us_ibdev = us_ibdev ? us_ibdev : ERR_PTR(-EFAULT);
+	if (!us_ibdev) {
+		us_ibdev = ERR_PTR(-EFAULT);
 		goto out;
 	}
 
@@ -586,10 +586,10 @@ static int usnic_ib_pci_probe(struct pci_dev *pdev,
 	}
 
 	pf = usnic_ib_discover_pf(vf->vnic);
-	if (IS_ERR_OR_NULL(pf)) {
-		usnic_err("Failed to discover pf of vnic %s with err%ld\n",
-				pci_name(pdev), PTR_ERR(pf));
-		err = pf ? PTR_ERR(pf) : -EFAULT;
+	if (IS_ERR(pf)) {
+		err = PTR_ERR(pf);
+		usnic_err("Failed to discover pf of vnic %s with err%d\n",
+				pci_name(pdev), err);
 		goto out_clean_vnic;
 	}
 
diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c
index fec87c9030ab..fffd144d509e 100644
--- a/drivers/infiniband/sw/rxe/rxe_cq.c
+++ b/drivers/infiniband/sw/rxe/rxe_cq.c
@@ -56,11 +56,8 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe,
 
 	err = do_mmap_info(rxe, uresp ? &uresp->mi : NULL, udata,
 			   cq->queue->buf, cq->queue->buf_size, &cq->queue->ip);
-	if (err) {
-		vfree(cq->queue->buf);
-		kfree(cq->queue);
+	if (err)
 		return err;
-	}
 
 	cq->is_user = uresp;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index feb386d98d1d..0bc3fbb6554f 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -140,6 +140,12 @@ static inline int qp_mtu(struct rxe_qp *qp)
 		return IB_MTU_4096;
 }
 
+static inline bool is_odp_mr(struct rxe_mr *mr)
+{
+	return IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) && mr->umem &&
+	       mr->umem->is_odp;
+}
+
 void free_rd_atomic_resource(struct resp_res *res);
 
 static inline void rxe_advance_resp_resource(struct rxe_qp *qp)
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 868d2f0b74e9..432d864c3ce9 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -323,7 +323,7 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr,
 		return err;
 	}
 
-	if (mr->umem->is_odp)
+	if (is_odp_mr(mr))
 		return rxe_odp_mr_copy(mr, iova, addr, length, dir);
 	else
 		return rxe_mr_copy_xarray(mr, iova, addr, length, dir);
@@ -536,7 +536,7 @@ int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
 	u64 *va;
 
 	/* ODP is not supported right now. WIP. */
-	if (mr->umem->is_odp)
+	if (is_odp_mr(mr))
 		return RESPST_ERR_UNSUPPORTED_OPCODE;
 
 	/* See IBA oA19-28 */
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 54ba9ee1acc5..5d9174e408db 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -650,7 +650,7 @@ static enum resp_states process_flush(struct rxe_qp *qp,
 	struct resp_res *res = qp->resp.res;
 
 	/* ODP is not supported right now. WIP. */
-	if (mr->umem->is_odp)
+	if (is_odp_mr(mr))
 		return RESPST_ERR_UNSUPPORTED_OPCODE;
 
 	/* oA19-14, oA19-15 */
@@ -706,7 +706,7 @@ static enum resp_states atomic_reply(struct rxe_qp *qp,
 	if (!res->replay) {
 		u64 iova = qp->resp.va + qp->resp.offset;
 
-		if (mr->umem->is_odp)
+		if (is_odp_mr(mr))
 			err = rxe_odp_atomic_op(mr, iova, pkt->opcode,
 						atmeth_comp(pkt),
 						atmeth_swap_add(pkt),
diff --git a/drivers/infiniband/sw/siw/Kconfig b/drivers/infiniband/sw/siw/Kconfig
index ae4a953e2a03..186f182b80e7 100644
--- a/drivers/infiniband/sw/siw/Kconfig
+++ b/drivers/infiniband/sw/siw/Kconfig
@@ -3,6 +3,7 @@ config RDMA_SIW
 	depends on INET && INFINIBAND
 	depends on INFINIBAND_VIRT_DMA
 	select CRC32
+	select NET_CRC32C
 	help
 	This driver implements the iWARP RDMA transport over
 	the Linux TCP/IP network stack. It enables a system with a
diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h
index 385067e07faf..d9e5a2e4c471 100644
--- a/drivers/infiniband/sw/siw/siw.h
+++ b/drivers/infiniband/sw/siw/siw.h
@@ -693,29 +693,9 @@ static inline void siw_crc_oneshot(const void *data, size_t len, u8 out[4])
 	return siw_crc_final(&crc, out);
 }
 
-static inline __wsum siw_csum_update(const void *buff, int len, __wsum sum)
-{
-	return (__force __wsum)crc32c((__force __u32)sum, buff, len);
-}
-
-static inline __wsum siw_csum_combine(__wsum csum, __wsum csum2, int offset,
-				      int len)
-{
-	return (__force __wsum)crc32c_combine((__force __u32)csum,
-					      (__force __u32)csum2, len);
-}
-
 static inline void siw_crc_skb(struct siw_rx_stream *srx, unsigned int len)
 {
-	const struct skb_checksum_ops siw_cs_ops = {
-		.update = siw_csum_update,
-		.combine = siw_csum_combine,
-	};
-	__wsum crc = (__force __wsum)srx->mpa_crc;
-
-	crc = __skb_checksum(srx->skb, srx->skb_offset, len, crc,
-			     &siw_cs_ops);
-	srx->mpa_crc = (__force u32)crc;
+	srx->mpa_crc = skb_crc32c(srx->skb, srx->skb_offset, len, srx->mpa_crc);
 }
 
 #define siw_dbg(ibdev, fmt, ...)                                               \
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index abe0522b7df4..91f866e3fb8b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -329,14 +329,6 @@ struct ipoib_dev_priv {
 
 	unsigned long flags;
 
-	/*
-	 * This protects access to the child_intfs list.
-	 * To READ from child_intfs the RTNL or vlan_rwsem read side must be
-	 * held.  To WRITE RTNL and the vlan_rwsem write side must be held (in
-	 * that order) This lock exists because we have a few contexts where
-	 * we need the child_intfs, but do not want to grab the RTNL.
-	 */
-	struct rw_semaphore vlan_rwsem;
 	struct mutex mcast_mutex;
 
 	struct rb_root  path_tree;
@@ -399,6 +391,9 @@ struct ipoib_dev_priv {
 	struct ib_event_handler event_handler;
 
 	struct net_device *parent;
+	/* 'child_intfs' and 'list' membership of all child devices are
+	 * protected by the netdev instance lock of 'dev'.
+	 */
 	struct list_head child_intfs;
 	struct list_head list;
 	int    child_type;
@@ -512,6 +507,8 @@ int ipoib_intf_init(struct ib_device *hca, u32 port, const char *format,
 void ipoib_ib_dev_flush_light(struct work_struct *work);
 void ipoib_ib_dev_flush_normal(struct work_struct *work);
 void ipoib_ib_dev_flush_heavy(struct work_struct *work);
+void ipoib_queue_work(struct ipoib_dev_priv *priv,
+		      enum ipoib_flush_level level);
 void ipoib_ib_tx_timeout_work(struct work_struct *work);
 void ipoib_ib_dev_cleanup(struct net_device *dev);
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 5cde275daa94..10b0dbda6cd5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -40,6 +40,7 @@
 
 #include <linux/ip.h>
 #include <linux/tcp.h>
+#include <net/netdev_lock.h>
 #include <rdma/ib_cache.h>
 
 #include "ipoib.h"
@@ -781,16 +782,20 @@ static void ipoib_napi_enable(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 
-	napi_enable(&priv->recv_napi);
-	napi_enable(&priv->send_napi);
+	netdev_lock_ops_to_full(dev);
+	napi_enable_locked(&priv->recv_napi);
+	napi_enable_locked(&priv->send_napi);
+	netdev_unlock_full_to_ops(dev);
 }
 
 static void ipoib_napi_disable(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 
-	napi_disable(&priv->recv_napi);
-	napi_disable(&priv->send_napi);
+	netdev_lock_ops_to_full(dev);
+	napi_disable_locked(&priv->recv_napi);
+	napi_disable_locked(&priv->send_napi);
+	netdev_unlock_full_to_ops(dev);
 }
 
 int ipoib_ib_dev_stop_default(struct net_device *dev)
@@ -1172,24 +1177,11 @@ out:
 }
 
 static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
-				enum ipoib_flush_level level,
-				int nesting)
+				enum ipoib_flush_level level)
 {
-	struct ipoib_dev_priv *cpriv;
 	struct net_device *dev = priv->dev;
 	int result;
 
-	down_read_nested(&priv->vlan_rwsem, nesting);
-
-	/*
-	 * Flush any child interfaces too -- they might be up even if
-	 * the parent is down.
-	 */
-	list_for_each_entry(cpriv, &priv->child_intfs, list)
-		__ipoib_ib_dev_flush(cpriv, level, nesting + 1);
-
-	up_read(&priv->vlan_rwsem);
-
 	if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags) &&
 	    level != IPOIB_FLUSH_HEAVY) {
 		/* Make sure the dev_addr is set even if not flushing */
@@ -1253,10 +1245,14 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 		ipoib_ib_dev_down(dev);
 
 	if (level == IPOIB_FLUSH_HEAVY) {
+		netdev_lock_ops(dev);
 		if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
 			ipoib_ib_dev_stop(dev);
 
-		if (ipoib_ib_dev_open(dev))
+		result = ipoib_ib_dev_open(dev);
+		netdev_unlock_ops(dev);
+
+		if (result)
 			return;
 
 		if (netif_queue_stopped(dev))
@@ -1280,7 +1276,7 @@ void ipoib_ib_dev_flush_light(struct work_struct *work)
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_light);
 
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT, 0);
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT);
 }
 
 void ipoib_ib_dev_flush_normal(struct work_struct *work)
@@ -1288,7 +1284,7 @@ void ipoib_ib_dev_flush_normal(struct work_struct *work)
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_normal);
 
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL, 0);
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL);
 }
 
 void ipoib_ib_dev_flush_heavy(struct work_struct *work)
@@ -1297,10 +1293,35 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work)
 		container_of(work, struct ipoib_dev_priv, flush_heavy);
 
 	rtnl_lock();
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY, 0);
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY);
 	rtnl_unlock();
 }
 
+void ipoib_queue_work(struct ipoib_dev_priv *priv,
+		      enum ipoib_flush_level level)
+{
+	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
+		struct ipoib_dev_priv *cpriv;
+
+		netdev_lock(priv->dev);
+		list_for_each_entry(cpriv, &priv->child_intfs, list)
+			ipoib_queue_work(cpriv, level);
+		netdev_unlock(priv->dev);
+	}
+
+	switch (level) {
+	case IPOIB_FLUSH_LIGHT:
+		queue_work(ipoib_workqueue, &priv->flush_light);
+		break;
+	case IPOIB_FLUSH_NORMAL:
+		queue_work(ipoib_workqueue, &priv->flush_normal);
+		break;
+	case IPOIB_FLUSH_HEAVY:
+		queue_work(ipoib_workqueue, &priv->flush_heavy);
+		break;
+	}
+}
+
 void ipoib_ib_dev_cleanup(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 3b463db8ce39..f2f5465f2a90 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -49,6 +49,7 @@
 #include <linux/jhash.h>
 #include <net/arp.h>
 #include <net/addrconf.h>
+#include <net/netdev_lock.h>
 #include <net/pkt_sched.h>
 #include <linux/inetdevice.h>
 #include <rdma/ib_cache.h>
@@ -132,6 +133,52 @@ static int ipoib_netdev_event(struct notifier_block *this,
 }
 #endif
 
+struct ipoib_ifupdown_work {
+	struct work_struct work;
+	struct net_device *dev;
+	netdevice_tracker dev_tracker;
+	bool up;
+};
+
+static void ipoib_ifupdown_task(struct work_struct *work)
+{
+	struct ipoib_ifupdown_work *pwork =
+		container_of(work, struct ipoib_ifupdown_work, work);
+	struct net_device *dev = pwork->dev;
+	unsigned int flags;
+
+	rtnl_lock();
+	flags = dev->flags;
+	if (pwork->up)
+		flags |= IFF_UP;
+	else
+		flags &= ~IFF_UP;
+
+	if (dev->flags != flags)
+		dev_change_flags(dev, flags, NULL);
+	rtnl_unlock();
+	netdev_put(dev, &pwork->dev_tracker);
+	kfree(pwork);
+}
+
+static void ipoib_schedule_ifupdown_task(struct net_device *dev, bool up)
+{
+	struct ipoib_ifupdown_work *work;
+
+	if ((up && (dev->flags & IFF_UP)) ||
+	    (!up && !(dev->flags & IFF_UP)))
+		return;
+
+	work = kmalloc(sizeof(*work), GFP_KERNEL);
+	if (!work)
+		return;
+	work->dev = dev;
+	netdev_hold(dev, &work->dev_tracker, GFP_KERNEL);
+	work->up = up;
+	INIT_WORK(&work->work, ipoib_ifupdown_task);
+	queue_work(ipoib_workqueue, &work->work);
+}
+
 int ipoib_open(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
@@ -154,17 +201,10 @@ int ipoib_open(struct net_device *dev)
 		struct ipoib_dev_priv *cpriv;
 
 		/* Bring up any child interfaces too */
-		down_read(&priv->vlan_rwsem);
-		list_for_each_entry(cpriv, &priv->child_intfs, list) {
-			int flags;
-
-			flags = cpriv->dev->flags;
-			if (flags & IFF_UP)
-				continue;
-
-			dev_change_flags(cpriv->dev, flags | IFF_UP, NULL);
-		}
-		up_read(&priv->vlan_rwsem);
+		netdev_lock_ops_to_full(dev);
+		list_for_each_entry(cpriv, &priv->child_intfs, list)
+			ipoib_schedule_ifupdown_task(cpriv->dev, true);
+		netdev_unlock_full_to_ops(dev);
 	} else if (priv->parent) {
 		struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent);
 
@@ -199,17 +239,10 @@ static int ipoib_stop(struct net_device *dev)
 		struct ipoib_dev_priv *cpriv;
 
 		/* Bring down any child interfaces too */
-		down_read(&priv->vlan_rwsem);
-		list_for_each_entry(cpriv, &priv->child_intfs, list) {
-			int flags;
-
-			flags = cpriv->dev->flags;
-			if (!(flags & IFF_UP))
-				continue;
-
-			dev_change_flags(cpriv->dev, flags & ~IFF_UP, NULL);
-		}
-		up_read(&priv->vlan_rwsem);
+		netdev_lock_ops_to_full(dev);
+		list_for_each_entry(cpriv, &priv->child_intfs, list)
+			ipoib_schedule_ifupdown_task(cpriv->dev, false);
+		netdev_unlock_full_to_ops(dev);
 	}
 
 	return 0;
@@ -426,17 +459,20 @@ static int ipoib_match_gid_pkey_addr(struct ipoib_dev_priv *priv,
 		}
 	}
 
+	if (test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags))
+		return matches;
+
 	/* Check child interfaces */
-	down_read_nested(&priv->vlan_rwsem, nesting);
+	netdev_lock(priv->dev);
 	list_for_each_entry(child_priv, &priv->child_intfs, list) {
 		matches += ipoib_match_gid_pkey_addr(child_priv, gid,
-						    pkey_index, addr,
-						    nesting + 1,
-						    found_net_dev);
+						     pkey_index, addr,
+						     nesting + 1,
+						     found_net_dev);
 		if (matches > 1)
 			break;
 	}
-	up_read(&priv->vlan_rwsem);
+	netdev_unlock(priv->dev);
 
 	return matches;
 }
@@ -531,9 +567,11 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 		set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
 		ipoib_warn(priv, "enabling connected mode "
 			   "will cause multicast packet drops\n");
+		netdev_lock_ops(dev);
 		netdev_update_features(dev);
-		dev_set_mtu(dev, ipoib_cm_max_mtu(dev));
+		netif_set_mtu(dev, ipoib_cm_max_mtu(dev));
 		netif_set_real_num_tx_queues(dev, 1);
+		netdev_unlock_ops(dev);
 		rtnl_unlock();
 		priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM;
 
@@ -543,9 +581,11 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 
 	if (!strcmp(buf, "datagram\n")) {
 		clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
+		netdev_lock_ops(dev);
 		netdev_update_features(dev);
-		dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu));
+		netif_set_mtu(dev, min(priv->mcast_mtu, dev->mtu));
 		netif_set_real_num_tx_queues(dev, dev->num_tx_queues);
+		netdev_unlock_ops(dev);
 		rtnl_unlock();
 		ipoib_flush_paths(dev);
 		return (!rtnl_trylock()) ? -EBUSY : 0;
@@ -1212,6 +1252,7 @@ void ipoib_ib_tx_timeout_work(struct work_struct *work)
 	int err;
 
 	rtnl_lock();
+	netdev_lock_ops(priv->dev);
 
 	if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
 		goto unlock;
@@ -1226,6 +1267,7 @@ void ipoib_ib_tx_timeout_work(struct work_struct *work)
 
 	netif_tx_wake_all_queues(priv->dev);
 unlock:
+	netdev_unlock_ops(priv->dev);
 	rtnl_unlock();
 
 }
@@ -1992,9 +2034,9 @@ static int ipoib_ndo_init(struct net_device *ndev)
 
 		dev_hold(priv->parent);
 
-		down_write(&ppriv->vlan_rwsem);
+		netdev_lock(priv->parent);
 		list_add_tail(&priv->list, &ppriv->child_intfs);
-		up_write(&ppriv->vlan_rwsem);
+		netdev_unlock(priv->parent);
 	}
 
 	return 0;
@@ -2004,8 +2046,6 @@ static void ipoib_ndo_uninit(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 
-	ASSERT_RTNL();
-
 	/*
 	 * ipoib_remove_one guarantees the children are removed before the
 	 * parent, and that is the only place where a parent can be removed.
@@ -2015,9 +2055,9 @@ static void ipoib_ndo_uninit(struct net_device *dev)
 	if (priv->parent) {
 		struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent);
 
-		down_write(&ppriv->vlan_rwsem);
+		netdev_lock(ppriv->dev);
 		list_del(&priv->list);
-		up_write(&ppriv->vlan_rwsem);
+		netdev_unlock(ppriv->dev);
 	}
 
 	ipoib_neigh_hash_uninit(dev);
@@ -2167,7 +2207,6 @@ static void ipoib_build_priv(struct net_device *dev)
 
 	priv->dev = dev;
 	spin_lock_init(&priv->lock);
-	init_rwsem(&priv->vlan_rwsem);
 	mutex_init(&priv->mcast_mutex);
 
 	INIT_LIST_HEAD(&priv->path_list);
@@ -2372,10 +2411,10 @@ static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid)
 	netif_addr_unlock_bh(netdev);
 
 	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
-		down_read(&priv->vlan_rwsem);
+		netdev_lock_ops_to_full(priv->dev);
 		list_for_each_entry(child_priv, &priv->child_intfs, list)
 			set_base_guid(child_priv, gid);
-		up_read(&priv->vlan_rwsem);
+		netdev_unlock_full_to_ops(priv->dev);
 	}
 }
 
@@ -2415,6 +2454,14 @@ static int ipoib_set_mac(struct net_device *dev, void *addr)
 
 	set_base_guid(priv, (union ib_gid *)(ss->__data + 4));
 
+	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
+		struct ipoib_dev_priv *cpriv;
+
+		netdev_lock_ops_to_full(dev);
+		list_for_each_entry(cpriv, &priv->child_intfs, list)
+			queue_work(ipoib_workqueue, &cpriv->flush_light);
+		netdev_unlock_full_to_ops(dev);
+	}
 	queue_work(ipoib_workqueue, &priv->flush_light);
 
 	return 0;
@@ -2526,7 +2573,7 @@ static struct net_device *ipoib_add_port(const char *format,
 	ib_register_event_handler(&priv->event_handler);
 
 	/* call event handler to ensure pkey in sync */
-	queue_work(ipoib_workqueue, &priv->flush_heavy);
+	ipoib_queue_work(priv, IPOIB_FLUSH_HEAVY);
 
 	ndev->rtnl_link_ops = ipoib_get_link_ops();
 
@@ -2624,9 +2671,11 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data)
 
 		rtnl_lock();
 
+		netdev_lock(priv->dev);
 		list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs,
 					 list)
 			unregister_netdevice_queue(cpriv->dev, &head);
+		netdev_unlock(priv->dev);
 		unregister_netdevice_queue(priv->dev, &head);
 		unregister_netdevice_many(&head);
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 368e5d77416d..86983080d28b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -280,15 +280,15 @@ void ipoib_event(struct ib_event_handler *handler,
 		  dev_name(&record->device->dev), record->element.port_num);
 
 	if (record->event == IB_EVENT_CLIENT_REREGISTER) {
-		queue_work(ipoib_workqueue, &priv->flush_light);
+		ipoib_queue_work(priv, IPOIB_FLUSH_LIGHT);
 	} else if (record->event == IB_EVENT_PORT_ERR ||
 		   record->event == IB_EVENT_PORT_ACTIVE ||
 		   record->event == IB_EVENT_LID_CHANGE) {
-		queue_work(ipoib_workqueue, &priv->flush_normal);
+		ipoib_queue_work(priv, IPOIB_FLUSH_NORMAL);
 	} else if (record->event == IB_EVENT_PKEY_CHANGE) {
-		queue_work(ipoib_workqueue, &priv->flush_heavy);
+		ipoib_queue_work(priv, IPOIB_FLUSH_HEAVY);
 	} else if (record->event == IB_EVENT_GID_CHANGE &&
 		   !test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) {
-		queue_work(ipoib_workqueue, &priv->flush_light);
+		ipoib_queue_work(priv, IPOIB_FLUSH_LIGHT);
 	}
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index 562df2b3ef18..243e8f555eca 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -53,8 +53,7 @@ static bool is_child_unique(struct ipoib_dev_priv *ppriv,
 			    struct ipoib_dev_priv *priv)
 {
 	struct ipoib_dev_priv *tpriv;
-
-	ASSERT_RTNL();
+	bool result = true;
 
 	/*
 	 * Since the legacy sysfs interface uses pkey for deletion it cannot
@@ -73,13 +72,17 @@ static bool is_child_unique(struct ipoib_dev_priv *ppriv,
 	if (ppriv->pkey == priv->pkey)
 		return false;
 
+	netdev_lock(ppriv->dev);
 	list_for_each_entry(tpriv, &ppriv->child_intfs, list) {
 		if (tpriv->pkey == priv->pkey &&
-		    tpriv->child_type == IPOIB_LEGACY_CHILD)
-			return false;
+		    tpriv->child_type == IPOIB_LEGACY_CHILD) {
+			result = false;
+			break;
+		}
 	}
+	netdev_unlock(ppriv->dev);
 
-	return true;
+	return result;
 }
 
 /*
@@ -98,8 +101,6 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 	int result;
 	struct rdma_netdev *rn = netdev_priv(ndev);
 
-	ASSERT_RTNL();
-
 	/*
 	 * We do not need to touch priv if register_netdevice fails, so just
 	 * always use this flow.
@@ -267,6 +268,7 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 	ppriv = ipoib_priv(pdev);
 
 	rc = -ENODEV;
+	netdev_lock(ppriv->dev);
 	list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
 		if (priv->pkey == pkey &&
 		    priv->child_type == IPOIB_LEGACY_CHILD) {
@@ -278,9 +280,7 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 				goto out;
 			}
 
-			down_write(&ppriv->vlan_rwsem);
 			list_del_init(&priv->list);
-			up_write(&ppriv->vlan_rwsem);
 			work->dev = priv->dev;
 			INIT_WORK(&work->work, ipoib_vlan_delete_task);
 			queue_work(ipoib_workqueue, &work->work);
@@ -291,6 +291,7 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
 	}
 
 out:
+	netdev_unlock(ppriv->dev);
 	rtnl_unlock();
 
 	return rc;
diff --git a/drivers/input/joystick/magellan.c b/drivers/input/joystick/magellan.c
index 2eaa25c9c68c..7622638e5bb8 100644
--- a/drivers/input/joystick/magellan.c
+++ b/drivers/input/joystick/magellan.c
@@ -48,7 +48,7 @@ struct magellan {
 
 static int magellan_crunch_nibbles(unsigned char *data, int count)
 {
-	static unsigned char nibbles[16] = "0AB3D56GH9:K<MN?";
+	static const unsigned char nibbles[16] __nonstring = "0AB3D56GH9:K<MN?";
 
 	do {
 		if (data[count] == nibbles[data[count] & 0xf])
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index c33e6f33265b..57a5ff3d1992 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -77,12 +77,13 @@
  * xbox d-pads should map to buttons, as is required for DDR pads
  * but we map them to axes when possible to simplify things
  */
-#define MAP_DPAD_TO_BUTTONS		(1 << 0)
-#define MAP_TRIGGERS_TO_BUTTONS		(1 << 1)
-#define MAP_STICKS_TO_NULL		(1 << 2)
-#define MAP_SELECT_BUTTON		(1 << 3)
-#define MAP_PADDLES			(1 << 4)
-#define MAP_PROFILE_BUTTON		(1 << 5)
+#define MAP_DPAD_TO_BUTTONS		BIT(0)
+#define MAP_TRIGGERS_TO_BUTTONS		BIT(1)
+#define MAP_STICKS_TO_NULL		BIT(2)
+#define MAP_SHARE_BUTTON		BIT(3)
+#define MAP_PADDLES			BIT(4)
+#define MAP_PROFILE_BUTTON		BIT(5)
+#define MAP_SHARE_OFFSET		BIT(6)
 
 #define DANCEPAD_MAP_CONFIG	(MAP_DPAD_TO_BUTTONS |			\
 				MAP_TRIGGERS_TO_BUTTONS | MAP_STICKS_TO_NULL)
@@ -135,14 +136,14 @@ static const struct xpad_device {
 	{ 0x03f0, 0x048D, "HyperX Clutch", 0, XTYPE_XBOX360 },			/* wireless */
 	{ 0x03f0, 0x0495, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE },
 	{ 0x03f0, 0x07A0, "HyperX Clutch Gladiate RGB", 0, XTYPE_XBOXONE },
-	{ 0x03f0, 0x08B6, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE },		/* v2 */
+	{ 0x03f0, 0x08B6, "HyperX Clutch Gladiate", MAP_SHARE_BUTTON, XTYPE_XBOXONE },		/* v2 */
 	{ 0x03f0, 0x09B4, "HyperX Clutch Tanto", 0, XTYPE_XBOXONE },
 	{ 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
-	{ 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE },
 	{ 0x044f, 0x0f10, "Thrustmaster Modena GT Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0xb326, "Thrustmaster Gamepad GP XID", 0, XTYPE_XBOX360 },
+	{ 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE },
 	{ 0x045e, 0x0202, "Microsoft X-Box pad v1 (US)", 0, XTYPE_XBOX },
 	{ 0x045e, 0x0285, "Microsoft X-Box pad (Japan)", 0, XTYPE_XBOX },
 	{ 0x045e, 0x0287, "Microsoft Xbox Controller S", 0, XTYPE_XBOX },
@@ -159,7 +160,7 @@ static const struct xpad_device {
 	{ 0x045e, 0x0719, "Xbox 360 Wireless Receiver", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W },
 	{ 0x045e, 0x0b00, "Microsoft X-Box One Elite 2 pad", MAP_PADDLES, XTYPE_XBOXONE },
 	{ 0x045e, 0x0b0a, "Microsoft X-Box Adaptive Controller", MAP_PROFILE_BUTTON, XTYPE_XBOXONE },
-	{ 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE },
+	{ 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SHARE_BUTTON | MAP_SHARE_OFFSET, XTYPE_XBOXONE },
 	{ 0x046d, 0xc21d, "Logitech Gamepad F310", 0, XTYPE_XBOX360 },
 	{ 0x046d, 0xc21e, "Logitech Gamepad F510", 0, XTYPE_XBOX360 },
 	{ 0x046d, 0xc21f, "Logitech Gamepad F710", 0, XTYPE_XBOX360 },
@@ -205,13 +206,13 @@ static const struct xpad_device {
 	{ 0x0738, 0x9871, "Mad Catz Portable Drum", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xb726, "Mad Catz Xbox controller - MW2", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xb738, "Mad Catz MVC2TE Stick 2", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
-	{ 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", XTYPE_XBOX360 },
+	{ 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xcb02, "Saitek Cyborg Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xcb03, "Saitek P3200 Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xcb29, "Saitek Aviator Stick AV8R02", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xf738, "Super SFIV FightStick TE S", 0, XTYPE_XBOX360 },
 	{ 0x07ff, 0xffff, "Mad Catz GamePad", 0, XTYPE_XBOX360 },
-	{ 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", 0, XTYPE_XBOXONE },
+	{ 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
 	{ 0x0b05, 0x1abb, "ASUS ROG RAIKIRI PRO", 0, XTYPE_XBOXONE },
 	{ 0x0c12, 0x0005, "Intec wireless", 0, XTYPE_XBOX },
 	{ 0x0c12, 0x8801, "Nyko Xbox Controller", 0, XTYPE_XBOX },
@@ -240,7 +241,7 @@ static const struct xpad_device {
 	{ 0x0e6f, 0x0146, "Rock Candy Wired Controller for Xbox One", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0147, "PDP Marvel Xbox One Controller", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x015c, "PDP Xbox One Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
-	{ 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", XTYPE_XBOXONE },
+	{ 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0161, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0162, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0163, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
@@ -281,6 +282,7 @@ static const struct xpad_device {
 	{ 0x0f0d, 0x00dc, "HORIPAD FPS for Nintendo Switch", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x0f0d, 0x0151, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE },
 	{ 0x0f0d, 0x0152, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE },
+	{ 0x0f0d, 0x01b2, "HORI Taiko No Tatsujin Drum Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
 	{ 0x0f30, 0x010b, "Philips Recoil", 0, XTYPE_XBOX },
 	{ 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX },
 	{ 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX },
@@ -353,6 +355,8 @@ static const struct xpad_device {
 	{ 0x20d6, 0x2001, "BDA Xbox Series X Wired Controller", 0, XTYPE_XBOXONE },
 	{ 0x20d6, 0x2009, "PowerA Enhanced Wired Controller for Xbox Series X|S", 0, XTYPE_XBOXONE },
 	{ 0x20d6, 0x281f, "PowerA Wired Controller For Xbox 360", 0, XTYPE_XBOX360 },
+	{ 0x20d6, 0x400b, "PowerA FUSION Pro 4 Wired Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
+	{ 0x20d6, 0x890b, "PowerA MOGA XP-Ultra Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
 	{ 0x2345, 0xe00b, "Machenike G5 Pro Controller", 0, XTYPE_XBOX360 },
 	{ 0x24c6, 0x5000, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x24c6, 0x5300, "PowerA MINI PROEX Controller", 0, XTYPE_XBOX360 },
@@ -384,13 +388,16 @@ static const struct xpad_device {
 	{ 0x294b, 0x3404, "Snakebyte GAMEPAD RGB X", 0, XTYPE_XBOXONE },
 	{ 0x2993, 0x2001, "TECNO Pocket Go", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE },
+	{ 0x2dc8, 0x200f, "8BitDo Ultimate 3-mode Controller for Xbox", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
 	{ 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x3109, "8BitDo Ultimate Wireless Bluetooth", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x310a, "8BitDo Ultimate 2C Wireless Controller", 0, XTYPE_XBOX360 },
+	{ 0x2dc8, 0x310b, "8BitDo Ultimate 2 Wireless Controller", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x6001, "8BitDo SN30 Pro", 0, XTYPE_XBOX360 },
+	{ 0x2e24, 0x0423, "Hyperkin DuchesS Xbox One pad", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
 	{ 0x2e24, 0x0652, "Hyperkin Duke X-Box One pad", 0, XTYPE_XBOXONE },
 	{ 0x2e24, 0x1688, "Hyperkin X91 X-Box One pad", 0, XTYPE_XBOXONE },
-	{ 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE },
+	{ 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
 	{ 0x31e3, 0x1100, "Wooting One", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1200, "Wooting Two", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1210, "Wooting Lekker", 0, XTYPE_XBOX360 },
@@ -714,8 +721,10 @@ static const struct xboxone_init_packet xboxone_init_packets[] = {
 	XBOXONE_INIT_PKT(0x045e, 0x0b00, xboxone_s_init),
 	XBOXONE_INIT_PKT(0x045e, 0x0b00, extra_input_packet_init),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_led_on),
+	XBOXONE_INIT_PKT(0x0f0d, 0x01b2, xboxone_pdp_led_on),
 	XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_led_on),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_auth),
+	XBOXONE_INIT_PKT(0x0f0d, 0x01b2, xboxone_pdp_auth),
 	XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_auth),
 	XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init),
 	XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_rumblebegin_init),
@@ -1027,7 +1036,7 @@ static void xpad360w_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned cha
  *	The report format was gleaned from
  *	https://github.com/kylelemons/xbox/blob/master/xbox.go
  */
-static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data)
+static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data, u32 len)
 {
 	struct input_dev *dev = xpad->dev;
 	bool do_sync = false;
@@ -1068,8 +1077,12 @@ static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char
 		/* menu/view buttons */
 		input_report_key(dev, BTN_START,  data[4] & BIT(2));
 		input_report_key(dev, BTN_SELECT, data[4] & BIT(3));
-		if (xpad->mapping & MAP_SELECT_BUTTON)
-			input_report_key(dev, KEY_RECORD, data[22] & BIT(0));
+		if (xpad->mapping & MAP_SHARE_BUTTON) {
+			if (xpad->mapping & MAP_SHARE_OFFSET)
+				input_report_key(dev, KEY_RECORD, data[len - 26] & BIT(0));
+			else
+				input_report_key(dev, KEY_RECORD, data[len - 18] & BIT(0));
+		}
 
 		/* buttons A,B,X,Y */
 		input_report_key(dev, BTN_A,	data[4] & BIT(4));
@@ -1217,7 +1230,7 @@ static void xpad_irq_in(struct urb *urb)
 		xpad360w_process_packet(xpad, 0, xpad->idata);
 		break;
 	case XTYPE_XBOXONE:
-		xpadone_process_packet(xpad, 0, xpad->idata);
+		xpadone_process_packet(xpad, 0, xpad->idata, urb->actual_length);
 		break;
 	default:
 		xpad_process_packet(xpad, 0, xpad->idata);
@@ -1944,7 +1957,7 @@ static int xpad_init_input(struct usb_xpad *xpad)
 	    xpad->xtype == XTYPE_XBOXONE) {
 		for (i = 0; xpad360_btn[i] >= 0; i++)
 			input_set_capability(input_dev, EV_KEY, xpad360_btn[i]);
-		if (xpad->mapping & MAP_SELECT_BUTTON)
+		if (xpad->mapping & MAP_SHARE_BUTTON)
 			input_set_capability(input_dev, EV_KEY, KEY_RECORD);
 	} else {
 		for (i = 0; xpad_btn[i] >= 0; i++)
diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c
index 5ad6be914160..061d48350df6 100644
--- a/drivers/input/keyboard/mtk-pmic-keys.c
+++ b/drivers/input/keyboard/mtk-pmic-keys.c
@@ -147,8 +147,8 @@ static void mtk_pmic_keys_lp_reset_setup(struct mtk_pmic_keys *keys,
 	u32 value, mask;
 	int error;
 
-	kregs_home = keys->keys[MTK_PMIC_HOMEKEY_INDEX].regs;
-	kregs_pwr = keys->keys[MTK_PMIC_PWRKEY_INDEX].regs;
+	kregs_home = &regs->keys_regs[MTK_PMIC_HOMEKEY_INDEX];
+	kregs_pwr = &regs->keys_regs[MTK_PMIC_PWRKEY_INDEX];
 
 	error = of_property_read_u32(keys->dev->of_node, "power-off-time-sec",
 				     &long_press_debounce);
diff --git a/drivers/input/misc/hisi_powerkey.c b/drivers/input/misc/hisi_powerkey.c
index d3c293a95d32..d315017324d9 100644
--- a/drivers/input/misc/hisi_powerkey.c
+++ b/drivers/input/misc/hisi_powerkey.c
@@ -30,7 +30,7 @@ static irqreturn_t hi65xx_power_press_isr(int irq, void *q)
 {
 	struct input_dev *input = q;
 
-	pm_wakeup_event(input->dev.parent, MAX_HELD_TIME);
+	pm_wakeup_dev_event(input->dev.parent, MAX_HELD_TIME, true);
 	input_report_key(input, KEY_POWER, 1);
 	input_sync(input);
 
diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c
index 8d7303fc13bc..1cfadd73829f 100644
--- a/drivers/input/misc/sparcspkr.c
+++ b/drivers/input/misc/sparcspkr.c
@@ -74,9 +74,14 @@ static int bbc_spkr_event(struct input_dev *dev, unsigned int type, unsigned int
 		return -1;
 
 	switch (code) {
-		case SND_BELL: if (value) value = 1000;
-		case SND_TONE: break;
-		default: return -1;
+	case SND_BELL:
+		if (value)
+			value = 1000;
+		break;
+	case SND_TONE:
+		break;
+	default:
+		return -1;
 	}
 
 	if (value > 20 && value < 32767)
@@ -109,9 +114,14 @@ static int grover_spkr_event(struct input_dev *dev, unsigned int type, unsigned
 		return -1;
 
 	switch (code) {
-		case SND_BELL: if (value) value = 1000;
-		case SND_TONE: break;
-		default: return -1;
+	case SND_BELL:
+		if (value)
+			value = 1000;
+		break;
+	case SND_TONE:
+		break;
+	default:
+		return -1;
 	}
 
 	if (value > 20 && value < 32767)
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 309c360aab55..c5c88a75a019 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -164,6 +164,7 @@ static const char * const topbuttonpad_pnp_ids[] = {
 #ifdef CONFIG_MOUSE_PS2_SYNAPTICS_SMBUS
 static const char * const smbus_pnp_ids[] = {
 	/* all of the topbuttonpad_pnp_ids are valid, we just add some extras */
+	"DLL060d", /* Dell Precision M3800 */
 	"LEN0048", /* X1 Carbon 3 */
 	"LEN0046", /* X250 */
 	"LEN0049", /* Yoga 11e */
@@ -190,11 +191,15 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN2054", /* E480 */
 	"LEN2055", /* E580 */
 	"LEN2068", /* T14 Gen 1 */
+	"SYN1221", /* TUXEDO InfinityBook Pro 14 v5 */
+	"SYN3003", /* HP EliteBook 850 G1 */
 	"SYN3015", /* HP EliteBook 840 G2 */
 	"SYN3052", /* HP EliteBook 840 G4 */
 	"SYN3221", /* HP 15-ay000 */
 	"SYN323d", /* HP Spectre X360 13-w013dx */
 	"SYN3257", /* HP Envy 13-ad105ng */
+	"TOS01f6", /* Dynabook Portege X30L-G */
+	"TOS0213", /* Dynabook Portege X30-D */
 	NULL
 };
 #endif
diff --git a/drivers/input/touchscreen/cyttsp5.c b/drivers/input/touchscreen/cyttsp5.c
index eafe5a9b8964..071b7c9bf566 100644
--- a/drivers/input/touchscreen/cyttsp5.c
+++ b/drivers/input/touchscreen/cyttsp5.c
@@ -580,7 +580,7 @@ static int cyttsp5_power_control(struct cyttsp5 *ts, bool on)
 	int rc;
 
 	SET_CMD_REPORT_TYPE(cmd[0], 0);
-	SET_CMD_REPORT_ID(cmd[0], HID_POWER_SLEEP);
+	SET_CMD_REPORT_ID(cmd[0], state);
 	SET_CMD_OPCODE(cmd[1], HID_CMD_SET_POWER);
 
 	rc = cyttsp5_write(ts, HID_COMMAND_REG, cmd, sizeof(cmd));
@@ -870,13 +870,16 @@ static int cyttsp5_probe(struct device *dev, struct regmap *regmap, int irq,
 	ts->input->phys = ts->phys;
 	input_set_drvdata(ts->input, ts);
 
-	/* Reset the gpio to be in a reset state */
+	/* Assert gpio to be in a reset state */
 	ts->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(ts->reset_gpio)) {
 		error = PTR_ERR(ts->reset_gpio);
 		dev_err(dev, "Failed to request reset gpio, error %d\n", error);
 		return error;
 	}
+
+	fsleep(10); /* Ensure long-enough reset pulse (minimum 10us). */
+
 	gpiod_set_value_cansleep(ts->reset_gpio, 0);
 
 	/* Need a delay to have device up */
diff --git a/drivers/input/touchscreen/stmpe-ts.c b/drivers/input/touchscreen/stmpe-ts.c
index a94a1997f96b..af0fb38bcfdc 100644
--- a/drivers/input/touchscreen/stmpe-ts.c
+++ b/drivers/input/touchscreen/stmpe-ts.c
@@ -366,12 +366,7 @@ static struct platform_driver stmpe_ts_driver = {
 };
 module_platform_driver(stmpe_ts_driver);
 
-static const struct of_device_id stmpe_ts_ids[] = {
-	{ .compatible = "st,stmpe-ts", },
-	{ },
-};
-MODULE_DEVICE_TABLE(of, stmpe_ts_ids);
-
+MODULE_ALIAS("platform:stmpe-ts");
 MODULE_AUTHOR("Luotao Fu <l.fu@pengutronix.de>");
 MODULE_DESCRIPTION("STMPEXXX touchscreen driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index dd9e26b7b718..14aa0d77df26 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -3664,6 +3664,14 @@ found:
 	while (*uid == '0' && *(uid + 1))
 		uid++;
 
+	if (strlen(hid) >= ACPIHID_HID_LEN) {
+		pr_err("Invalid command line: hid is too long\n");
+		return 1;
+	} else if (strlen(uid) >= ACPIHID_UID_LEN) {
+		pr_err("Invalid command line: uid is too long\n");
+		return 1;
+	}
+
 	i = early_acpihid_map_size++;
 	memcpy(early_acpihid_map[i].hid, hid, strlen(hid));
 	memcpy(early_acpihid_map[i].uid, uid, strlen(uid));
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index be8761bbef0f..f34209b08b4c 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3869,6 +3869,9 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
 	struct iommu_dev_data *dev_data;
 
+	if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)))
+		return -EINVAL;
+
 	if (ir_data->iommu == NULL)
 		return -EINVAL;
 
@@ -3879,21 +3882,11 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 	 * we should not modify the IRTE
 	 */
 	if (!dev_data || !dev_data->use_vapic)
-		return 0;
+		return -EINVAL;
 
 	ir_data->cfg = irqd_cfg(data);
 	pi_data->ir_data = ir_data;
 
-	/* Note:
-	 * SVM tries to set up for VAPIC mode, but we are in
-	 * legacy mode. So, we force legacy mode instead.
-	 */
-	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) {
-		pr_debug("%s: Fall back to using intr legacy remap\n",
-			 __func__);
-		pi_data->is_guest_mode = false;
-	}
-
 	pi_data->prev_ga_tag = ir_data->cached_ga_tag;
 	if (pi_data->is_guest_mode) {
 		ir_data->ga_root_ptr = (pi_data->base >> 12);
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index 9ba596430e7c..980cc6b33c43 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -411,6 +411,12 @@ struct iommu_domain *arm_smmu_sva_domain_alloc(struct device *dev,
 		return ERR_CAST(smmu_domain);
 	smmu_domain->domain.type = IOMMU_DOMAIN_SVA;
 	smmu_domain->domain.ops = &arm_smmu_sva_domain_ops;
+
+	/*
+	 * Choose page_size as the leaf page size for invalidation when
+	 * ARM_SMMU_FEAT_RANGE_INV is present
+	 */
+	smmu_domain->domain.pgsize_bitmap = PAGE_SIZE;
 	smmu_domain->smmu = smmu;
 
 	ret = xa_alloc(&arm_smmu_asid_xa, &asid, smmu_domain,
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index b4c21aaed126..48d910399a1b 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3388,6 +3388,7 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 	mutex_lock(&smmu->streams_mutex);
 	for (i = 0; i < fwspec->num_ids; i++) {
 		struct arm_smmu_stream *new_stream = &master->streams[i];
+		struct rb_node *existing;
 		u32 sid = fwspec->ids[i];
 
 		new_stream->id = sid;
@@ -3398,11 +3399,21 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 			break;
 
 		/* Insert into SID tree */
-		if (rb_find_add(&new_stream->node, &smmu->streams,
-				arm_smmu_streams_cmp_node)) {
-			dev_warn(master->dev, "stream %u already in tree\n",
-				 sid);
-			ret = -EINVAL;
+		existing = rb_find_add(&new_stream->node, &smmu->streams,
+				       arm_smmu_streams_cmp_node);
+		if (existing) {
+			struct arm_smmu_master *existing_master =
+				rb_entry(existing, struct arm_smmu_stream, node)
+					->master;
+
+			/* Bridged PCI devices may end up with duplicated IDs */
+			if (existing_master == master)
+				continue;
+
+			dev_warn(master->dev,
+				 "Aliasing StreamID 0x%x (from %s) unsupported, expect DMA to be broken\n",
+				 sid, dev_name(existing_master->dev));
+			ret = -ENODEV;
 			break;
 		}
 	}
@@ -4429,6 +4440,8 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3);
 	if (FIELD_GET(IDR3_RIL, reg))
 		smmu->features |= ARM_SMMU_FEAT_RANGE_INV;
+	if (FIELD_GET(IDR3_FWB, reg))
+		smmu->features |= ARM_SMMU_FEAT_S2FWB;
 
 	/* IDR5 */
 	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
index d525ab43a4ae..dd7d030d2e89 100644
--- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
+++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
@@ -487,17 +487,6 @@ static int tegra241_cmdqv_hw_reset(struct arm_smmu_device *smmu)
 
 /* VCMDQ Resource Helpers */
 
-static void tegra241_vcmdq_free_smmu_cmdq(struct tegra241_vcmdq *vcmdq)
-{
-	struct arm_smmu_queue *q = &vcmdq->cmdq.q;
-	size_t nents = 1 << q->llq.max_n_shift;
-	size_t qsz = nents << CMDQ_ENT_SZ_SHIFT;
-
-	if (!q->base)
-		return;
-	dmam_free_coherent(vcmdq->cmdqv->smmu.dev, qsz, q->base, q->base_dma);
-}
-
 static int tegra241_vcmdq_alloc_smmu_cmdq(struct tegra241_vcmdq *vcmdq)
 {
 	struct arm_smmu_device *smmu = &vcmdq->cmdqv->smmu;
@@ -560,7 +549,8 @@ static void tegra241_vintf_free_lvcmdq(struct tegra241_vintf *vintf, u16 lidx)
 	struct tegra241_vcmdq *vcmdq = vintf->lvcmdqs[lidx];
 	char header[64];
 
-	tegra241_vcmdq_free_smmu_cmdq(vcmdq);
+	/* Note that the lvcmdq queue memory space is managed by devres */
+
 	tegra241_vintf_deinit_lvcmdq(vintf, lidx);
 
 	dev_dbg(vintf->cmdqv->dev,
@@ -768,13 +758,13 @@ static int tegra241_cmdqv_init_structures(struct arm_smmu_device *smmu)
 
 	vintf = kzalloc(sizeof(*vintf), GFP_KERNEL);
 	if (!vintf)
-		goto out_fallback;
+		return -ENOMEM;
 
 	/* Init VINTF0 for in-kernel use */
 	ret = tegra241_cmdqv_init_vintf(cmdqv, 0, vintf);
 	if (ret) {
 		dev_err(cmdqv->dev, "failed to init vintf0: %d\n", ret);
-		goto free_vintf;
+		return ret;
 	}
 
 	/* Preallocate logical VCMDQs to VINTF0 */
@@ -783,24 +773,12 @@ static int tegra241_cmdqv_init_structures(struct arm_smmu_device *smmu)
 
 		vcmdq = tegra241_vintf_alloc_lvcmdq(vintf, lidx);
 		if (IS_ERR(vcmdq))
-			goto free_lvcmdq;
+			return PTR_ERR(vcmdq);
 	}
 
 	/* Now, we are ready to run all the impl ops */
 	smmu->impl_ops = &tegra241_cmdqv_impl_ops;
 	return 0;
-
-free_lvcmdq:
-	for (lidx--; lidx >= 0; lidx--)
-		tegra241_vintf_free_lvcmdq(vintf, lidx);
-	tegra241_cmdqv_deinit_vintf(cmdqv, vintf->idx);
-free_vintf:
-	kfree(vintf);
-out_fallback:
-	dev_info(smmu->impl_dev, "Falling back to standard SMMU CMDQ\n");
-	smmu->options &= ~ARM_SMMU_OPT_TEGRA241_CMDQV;
-	tegra241_cmdqv_remove(smmu);
-	return 0;
 }
 
 #ifdef CONFIG_IOMMU_DEBUGFS
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index cb7e29dcac15..a775e4dbe06f 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1754,7 +1754,7 @@ static size_t cookie_msi_granule(const struct iommu_domain *domain)
 		return PAGE_SIZE;
 	default:
 		BUG();
-	};
+	}
 }
 
 static struct list_head *cookie_msi_pages(const struct iommu_domain *domain)
@@ -1766,7 +1766,7 @@ static struct list_head *cookie_msi_pages(const struct iommu_domain *domain)
 		return &domain->msi_cookie->msi_page_list;
 	default:
 		BUG();
-	};
+	}
 }
 
 static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 69e23e017d9e..317266aca6e2 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -832,7 +832,7 @@ static int __maybe_unused exynos_sysmmu_suspend(struct device *dev)
 		struct exynos_iommu_owner *owner = dev_iommu_priv_get(master);
 
 		mutex_lock(&owner->rpm_lock);
-		if (&data->domain->domain != &exynos_identity_domain) {
+		if (data->domain) {
 			dev_dbg(data->sysmmu, "saving state\n");
 			__sysmmu_disable(data);
 		}
@@ -850,7 +850,7 @@ static int __maybe_unused exynos_sysmmu_resume(struct device *dev)
 		struct exynos_iommu_owner *owner = dev_iommu_priv_get(master);
 
 		mutex_lock(&owner->rpm_lock);
-		if (&data->domain->domain != &exynos_identity_domain) {
+		if (data->domain) {
 			dev_dbg(data->sysmmu, "restoring state\n");
 			__sysmmu_enable(data);
 		}
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 6e67cc66a204..cb0b993bebb4 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3785,6 +3785,22 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 
 	intel_iommu_debugfs_create_dev(info);
 
+	return &iommu->iommu;
+free_table:
+	intel_pasid_free_table(dev);
+clear_rbtree:
+	device_rbtree_remove(info);
+free:
+	kfree(info);
+
+	return ERR_PTR(ret);
+}
+
+static void intel_iommu_probe_finalize(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+
 	/*
 	 * The PCIe spec, in its wisdom, declares that the behaviour of the
 	 * device is undefined if you enable PASID support after ATS support.
@@ -3792,22 +3808,12 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 	 * we can't yet know if we're ever going to use it.
 	 */
 	if (info->pasid_supported &&
-	    !pci_enable_pasid(pdev, info->pasid_supported & ~1))
+	    !pci_enable_pasid(to_pci_dev(dev), info->pasid_supported & ~1))
 		info->pasid_enabled = 1;
 
-	if (sm_supported(iommu))
+	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev))
 		iommu_enable_pci_ats(info);
 	iommu_enable_pci_pri(info);
-
-	return &iommu->iommu;
-free_table:
-	intel_pasid_free_table(dev);
-clear_rbtree:
-	device_rbtree_remove(info);
-free:
-	kfree(info);
-
-	return ERR_PTR(ret);
 }
 
 static void intel_iommu_release_device(struct device *dev)
@@ -3835,7 +3841,6 @@ static void intel_iommu_release_device(struct device *dev)
 	intel_pasid_free_table(dev);
 	intel_iommu_debugfs_remove_dev(info);
 	kfree(info);
-	set_dma_ops(dev, NULL);
 }
 
 static void intel_iommu_get_resv_regions(struct device *device,
@@ -4392,6 +4397,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.domain_alloc_sva	= intel_svm_domain_alloc,
 	.domain_alloc_nested	= intel_iommu_domain_alloc_nested,
 	.probe_device		= intel_iommu_probe_device,
+	.probe_finalize		= intel_iommu_probe_finalize,
 	.release_device		= intel_iommu_release_device,
 	.get_resv_regions	= intel_iommu_get_resv_regions,
 	.device_group		= intel_iommu_device_group,
@@ -4433,6 +4439,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_igfx);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_igfx);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_igfx);
 
+/* QM57/QS57 integrated gfx malfunctions with dmar */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_iommu_igfx);
+
 /* Broadwell igfx malfunctions with dmar */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1606, quirk_iommu_igfx);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160B, quirk_iommu_igfx);
@@ -4510,7 +4519,6 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
 	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);
 
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index ea3ca5203919..3bc2a03cceca 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -1287,43 +1287,44 @@ static struct irq_chip intel_ir_chip = {
 };
 
 /*
- * With posted MSIs, all vectors are multiplexed into a single notification
- * vector. Devices MSIs are then dispatched in a demux loop where
- * EOIs can be coalesced as well.
+ * With posted MSIs, the MSI vectors are multiplexed into a single notification
+ * vector, and only the notification vector is sent to the APIC IRR.  Device
+ * MSIs are then dispatched in a demux loop that harvests the MSIs from the
+ * CPU's Posted Interrupt Request bitmap.  I.e. Posted MSIs never get sent to
+ * the APIC IRR, and thus do not need an EOI.  The notification handler instead
+ * performs a single EOI after processing the PIR.
  *
- * "INTEL-IR-POST" IRQ chip does not do EOI on ACK, thus the dummy irq_ack()
- * function. Instead EOI is performed by the posted interrupt notification
- * handler.
+ * Note!  Pending SMP/CPU affinity changes, which are per MSI, must still be
+ * honored, only the APIC EOI is omitted.
  *
  * For the example below, 3 MSIs are coalesced into one CPU notification. Only
- * one apic_eoi() is needed.
+ * one apic_eoi() is needed, but each MSI needs to process pending changes to
+ * its CPU affinity.
  *
  * __sysvec_posted_msi_notification()
  *	irq_enter();
  *		handle_edge_irq()
  *			irq_chip_ack_parent()
- *				dummy(); // No EOI
+ *				irq_move_irq(); // No EOI
  *			handle_irq_event()
  *				driver_handler()
  *		handle_edge_irq()
  *			irq_chip_ack_parent()
- *				dummy(); // No EOI
+ *				irq_move_irq(); // No EOI
  *			handle_irq_event()
  *				driver_handler()
  *		handle_edge_irq()
  *			irq_chip_ack_parent()
- *				dummy(); // No EOI
+ *				irq_move_irq(); // No EOI
  *			handle_irq_event()
  *				driver_handler()
  *	apic_eoi()
  *	irq_exit()
+ *
  */
-
-static void dummy_ack(struct irq_data *d) { }
-
 static struct irq_chip intel_ir_chip_post_msi = {
 	.name			= "INTEL-IR-POST",
-	.irq_ack		= dummy_ack,
+	.irq_ack		= irq_move_irq,
 	.irq_set_affinity	= intel_ir_set_affinity,
 	.irq_compose_msi_msg	= intel_ir_compose_msi_msg,
 	.irq_set_vcpu_affinity	= intel_ir_set_vcpu_affinity,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index c8033ca66377..4f91a740c15f 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -538,6 +538,9 @@ static void iommu_deinit_device(struct device *dev)
 	dev->iommu_group = NULL;
 	module_put(ops->owner);
 	dev_iommu_free(dev);
+#ifdef CONFIG_IOMMU_DMA
+	dev->dma_iommu = false;
+#endif
 }
 
 static struct iommu_domain *pasid_array_entry_to_domain(void *entry)
@@ -2717,7 +2720,8 @@ int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
 	 * if upper layers showed interest and installed a fault handler,
 	 * invoke it.
 	 */
-	if (domain->handler)
+	if (domain->cookie_type == IOMMU_COOKIE_FAULT_HANDLER &&
+	    domain->handler)
 		ret = domain->handler(domain, dev, iova, flags,
 						domain->handler_token);
 
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 074daf1aac4e..e424b279a8cd 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -1081,31 +1081,24 @@ static int ipmmu_probe(struct platform_device *pdev)
 		}
 	}
 
+	platform_set_drvdata(pdev, mmu);
 	/*
 	 * Register the IPMMU to the IOMMU subsystem in the following cases:
 	 * - R-Car Gen2 IPMMU (all devices registered)
 	 * - R-Car Gen3 IPMMU (leaf devices only - skip root IPMMU-MM device)
 	 */
-	if (!mmu->features->has_cache_leaf_nodes || !ipmmu_is_root(mmu)) {
-		ret = iommu_device_sysfs_add(&mmu->iommu, &pdev->dev, NULL,
-					     dev_name(&pdev->dev));
-		if (ret)
-			return ret;
-
-		ret = iommu_device_register(&mmu->iommu, &ipmmu_ops, &pdev->dev);
-		if (ret)
-			return ret;
-	}
+	if (mmu->features->has_cache_leaf_nodes && ipmmu_is_root(mmu))
+		return 0;
 
-	/*
-	 * We can't create the ARM mapping here as it requires the bus to have
-	 * an IOMMU, which only happens when bus_set_iommu() is called in
-	 * ipmmu_init() after the probe function returns.
-	 */
+	ret = iommu_device_sysfs_add(&mmu->iommu, &pdev->dev, NULL, dev_name(&pdev->dev));
+	if (ret)
+		return ret;
 
-	platform_set_drvdata(pdev, mmu);
+	ret = iommu_device_register(&mmu->iommu, &ipmmu_ops, &pdev->dev);
+	if (ret)
+		iommu_device_sysfs_remove(&mmu->iommu);
 
-	return 0;
+	return ret;
 }
 
 static void ipmmu_remove(struct platform_device *pdev)
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 034b0e670384..df98d0c65f54 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -1372,15 +1372,6 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, data);
 	mutex_init(&data->mutex);
 
-	ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
-				     "mtk-iommu.%pa", &ioaddr);
-	if (ret)
-		goto out_link_remove;
-
-	ret = iommu_device_register(&data->iommu, &mtk_iommu_ops, dev);
-	if (ret)
-		goto out_sysfs_remove;
-
 	if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE)) {
 		list_add_tail(&data->list, data->plat_data->hw_list);
 		data->hw_list = data->plat_data->hw_list;
@@ -1390,19 +1381,28 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 		data->hw_list = &data->hw_list_head;
 	}
 
+	ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
+				     "mtk-iommu.%pa", &ioaddr);
+	if (ret)
+		goto out_list_del;
+
+	ret = iommu_device_register(&data->iommu, &mtk_iommu_ops, dev);
+	if (ret)
+		goto out_sysfs_remove;
+
 	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
 		ret = component_master_add_with_match(dev, &mtk_iommu_com_ops, match);
 		if (ret)
-			goto out_list_del;
+			goto out_device_unregister;
 	}
 	return ret;
 
-out_list_del:
-	list_del(&data->list);
+out_device_unregister:
 	iommu_device_unregister(&data->iommu);
 out_sysfs_remove:
 	iommu_device_sysfs_remove(&data->iommu);
-out_link_remove:
+out_list_del:
+	list_del(&data->list);
 	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
 		device_link_remove(data->smicomm_dev, dev);
 out_runtime_disable:
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index cec05e443083..08bb3b031f23 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -114,8 +114,8 @@ config I8259
 
 config BCM2712_MIP
 	tristate "Broadcom BCM2712 MSI-X Interrupt Peripheral support"
-	depends on ARCH_BRCMSTB || COMPILE_TEST
-	default m if ARCH_BRCMSTB
+	depends on ARCH_BRCMSTB || ARCH_BCM2835 || COMPILE_TEST
+	default m if ARCH_BRCMSTB || ARCH_BCM2835
 	depends on ARM_GIC
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN_HIERARCHY
diff --git a/drivers/irqchip/irq-bcm2712-mip.c b/drivers/irqchip/irq-bcm2712-mip.c
index 49a19db2d1e1..4cce24233f0f 100644
--- a/drivers/irqchip/irq-bcm2712-mip.c
+++ b/drivers/irqchip/irq-bcm2712-mip.c
@@ -163,6 +163,7 @@ static const struct irq_domain_ops mip_middle_domain_ops = {
 static const struct msi_parent_ops mip_msi_parent_ops = {
 	.supported_flags	= MIP_MSI_FLAGS_SUPPORTED,
 	.required_flags		= MIP_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_token       = DOMAIN_BUS_GENERIC_MSI,
 	.bus_select_mask	= MATCH_PCI_MSI,
 	.prefix			= "MIP-MSI-",
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index c69894861866..cc6a6c1585d2 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -252,7 +252,7 @@ static void __init gicv2m_teardown(void)
 static struct msi_parent_ops gicv2m_msi_parent_ops = {
 	.supported_flags	= GICV2M_MSI_FLAGS_SUPPORTED,
 	.required_flags		= GICV2M_MSI_FLAGS_REQUIRED,
-	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
 	.prefix			= "GICv2m-",
@@ -421,7 +421,7 @@ static int __init gicv2m_of_init(struct fwnode_handle *parent_handle,
 #ifdef CONFIG_ACPI
 static int acpi_num_msi;
 
-static __init struct fwnode_handle *gicv2m_get_fwnode(struct device *dev)
+static struct fwnode_handle *gicv2m_get_fwnode(struct device *dev)
 {
 	struct v2m_data *data;
 
diff --git a/drivers/irqchip/irq-gic-v3-its-msi-parent.c b/drivers/irqchip/irq-gic-v3-its-msi-parent.c
index bdb04c808148..c5a7eb1c0419 100644
--- a/drivers/irqchip/irq-gic-v3-its-msi-parent.c
+++ b/drivers/irqchip/irq-gic-v3-its-msi-parent.c
@@ -203,7 +203,7 @@ static bool its_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 const struct msi_parent_ops gic_v3_its_msi_parent_ops = {
 	.supported_flags	= ITS_MSI_FLAGS_SUPPORTED,
 	.required_flags		= ITS_MSI_FLAGS_REQUIRED,
-	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
 	.prefix			= "ITS-",
diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c
index 34e9ca77a8c3..647b18e24e0c 100644
--- a/drivers/irqchip/irq-gic-v3-mbi.c
+++ b/drivers/irqchip/irq-gic-v3-mbi.c
@@ -197,7 +197,7 @@ static bool mbi_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 static const struct msi_parent_ops gic_v3_mbi_msi_parent_ops = {
 	.supported_flags	= MBI_MSI_FLAGS_SUPPORTED,
 	.required_flags		= MBI_MSI_FLAGS_REQUIRED,
-	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.bus_select_mask	= MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
 	.prefix			= "MBI-",
diff --git a/drivers/irqchip/irq-mvebu-gicp.c b/drivers/irqchip/irq-mvebu-gicp.c
index d67f93f6d750..60b976286636 100644
--- a/drivers/irqchip/irq-mvebu-gicp.c
+++ b/drivers/irqchip/irq-mvebu-gicp.c
@@ -161,7 +161,7 @@ static const struct irq_domain_ops gicp_domain_ops = {
 static const struct msi_parent_ops gicp_msi_parent_ops = {
 	.supported_flags	= GICP_MSI_FLAGS_SUPPORTED,
 	.required_flags		= GICP_MSI_FLAGS_REQUIRED,
-	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI,
 	.bus_select_token       = DOMAIN_BUS_GENERIC_MSI,
 	.bus_select_mask	= MATCH_PLATFORM_MSI,
 	.prefix			= "GICP-",
diff --git a/drivers/irqchip/irq-mvebu-odmi.c b/drivers/irqchip/irq-mvebu-odmi.c
index 28f7e81df94f..54f6f0811573 100644
--- a/drivers/irqchip/irq-mvebu-odmi.c
+++ b/drivers/irqchip/irq-mvebu-odmi.c
@@ -157,7 +157,7 @@ static const struct irq_domain_ops odmi_domain_ops = {
 static const struct msi_parent_ops odmi_msi_parent_ops = {
 	.supported_flags	= ODMI_MSI_FLAGS_SUPPORTED,
 	.required_flags		= ODMI_MSI_FLAGS_REQUIRED,
-	.chip_flags		= MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI,
 	.bus_select_token	= DOMAIN_BUS_GENERIC_MSI,
 	.bus_select_mask	= MATCH_PLATFORM_MSI,
 	.prefix			= "ODMI-",
diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c
index 7942d8eb3d00..f772deb9cba5 100644
--- a/drivers/irqchip/irq-qcom-mpm.c
+++ b/drivers/irqchip/irq-qcom-mpm.c
@@ -227,6 +227,9 @@ static int qcom_mpm_alloc(struct irq_domain *domain, unsigned int virq,
 	if (ret)
 		return ret;
 
+	if (pin == GPIO_NO_WAKE_IRQ)
+		return irq_domain_disconnect_hierarchy(domain, virq);
+
 	ret = irq_domain_set_hwirq_and_chip(domain, virq, pin,
 					    &qcom_mpm_chip, priv);
 	if (ret)
diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index 3d5b5fdf9bde..0f0fd7d4dfdf 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -170,6 +170,14 @@ static void rzv2h_tint_irq_endisable(struct irq_data *d, bool enable)
 	else
 		tssr &= ~ICU_TSSR_TIEN(tssel_n, priv->info->field_width);
 	writel_relaxed(tssr, priv->base + priv->info->t_offs + ICU_TSSR(k));
+
+	/*
+	 * A glitch in the edge detection circuit can cause a spurious
+	 * interrupt. Clear the status flag after setting the ICU_TSSRk
+	 * registers, which is recommended by the hardware manual as a
+	 * countermeasure.
+	 */
+	writel_relaxed(BIT(tint_nr), priv->base + priv->info->t_offs + ICU_TSCLR);
 }
 
 static void rzv2h_icu_irq_disable(struct irq_data *d)
diff --git a/drivers/irqchip/irq-riscv-imsic-state.c b/drivers/irqchip/irq-riscv-imsic-state.c
index bdf5cd2037f2..62f76950a113 100644
--- a/drivers/irqchip/irq-riscv-imsic-state.c
+++ b/drivers/irqchip/irq-riscv-imsic-state.c
@@ -208,17 +208,17 @@ skip:
 }
 
 #ifdef CONFIG_SMP
-static void __imsic_local_timer_start(struct imsic_local_priv *lpriv)
+static void __imsic_local_timer_start(struct imsic_local_priv *lpriv, unsigned int cpu)
 {
 	lockdep_assert_held(&lpriv->lock);
 
 	if (!timer_pending(&lpriv->timer)) {
 		lpriv->timer.expires = jiffies + 1;
-		add_timer_on(&lpriv->timer, smp_processor_id());
+		add_timer_on(&lpriv->timer, cpu);
 	}
 }
 #else
-static inline void __imsic_local_timer_start(struct imsic_local_priv *lpriv)
+static inline void __imsic_local_timer_start(struct imsic_local_priv *lpriv, unsigned int cpu)
 {
 }
 #endif
@@ -233,7 +233,7 @@ void imsic_local_sync_all(bool force_all)
 	if (force_all)
 		bitmap_fill(lpriv->dirty_bitmap, imsic->global.nr_ids + 1);
 	if (!__imsic_local_sync(lpriv))
-		__imsic_local_timer_start(lpriv);
+		__imsic_local_timer_start(lpriv, smp_processor_id());
 
 	raw_spin_unlock_irqrestore(&lpriv->lock, flags);
 }
@@ -278,7 +278,7 @@ static void __imsic_remote_sync(struct imsic_local_priv *lpriv, unsigned int cpu
 				return;
 		}
 
-		__imsic_local_timer_start(lpriv);
+		__imsic_local_timer_start(lpriv, cpu);
 	}
 }
 #else
diff --git a/drivers/irqchip/irq-sg2042-msi.c b/drivers/irqchip/irq-sg2042-msi.c
index ee682e87eb8b..375b55aa0acd 100644
--- a/drivers/irqchip/irq-sg2042-msi.c
+++ b/drivers/irqchip/irq-sg2042-msi.c
@@ -151,6 +151,7 @@ static const struct irq_domain_ops sg2042_msi_middle_domain_ops = {
 static const struct msi_parent_ops sg2042_msi_parent_ops = {
 	.required_flags		= SG2042_MSI_FLAGS_REQUIRED,
 	.supported_flags	= SG2042_MSI_FLAGS_SUPPORTED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_ACK,
 	.bus_select_mask	= MATCH_PCI_MSI,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
 	.prefix			= "SG2042-",
diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c
index 02a680c73979..bf0d7d58c8b0 100644
--- a/drivers/mcb/mcb-parse.c
+++ b/drivers/mcb/mcb-parse.c
@@ -96,7 +96,7 @@ static int chameleon_parse_gdd(struct mcb_bus *bus,
 
 	ret = mcb_device_register(bus, mdev);
 	if (ret < 0)
-		goto err;
+		return ret;
 
 	return 0;
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index e42f1400cea9..813b38aec3e4 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -546,7 +546,7 @@ static struct uuid_entry *uuid_find(struct cache_set *c, const char *uuid)
 
 static struct uuid_entry *uuid_find_empty(struct cache_set *c)
 {
-	static const char zero_uuid[16] = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0";
+	static const char zero_uuid[16] = { 0 };
 
 	return uuid_find(c, zero_uuid);
 }
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 9c8ed65cd87e..f0b5a6931161 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -68,6 +68,8 @@
 #define LIST_DIRTY	1
 #define LIST_SIZE	2
 
+#define SCAN_RESCHED_CYCLE	16
+
 /*--------------------------------------------------------------*/
 
 /*
@@ -2424,7 +2426,12 @@ static void __scan(struct dm_bufio_client *c)
 
 			atomic_long_dec(&c->need_shrink);
 			freed++;
-			cond_resched();
+
+			if (unlikely(freed % SCAN_RESCHED_CYCLE == 0)) {
+				dm_bufio_unlock(c);
+				cond_resched();
+				dm_bufio_lock(c);
+			}
 		}
 	}
 }
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 2a283feb3319..cc3d3897ef42 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -5164,7 +5164,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 	BUG_ON(!RB_EMPTY_ROOT(&ic->in_progress));
 	BUG_ON(!list_empty(&ic->wait_list));
 
-	if (ic->mode == 'B')
+	if (ic->mode == 'B' && ic->bitmap_flush_work.work.func)
 		cancel_delayed_work_sync(&ic->bitmap_flush_work);
 	if (ic->metadata_wq)
 		destroy_workqueue(ic->metadata_wq);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 35100a435c88..6b23e777e10e 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -523,8 +523,9 @@ static char **realloc_argv(unsigned int *size, char **old_argv)
 		gfp = GFP_NOIO;
 	}
 	argv = kmalloc_array(new_size, sizeof(*argv), gfp);
-	if (argv && old_argv) {
-		memcpy(argv, old_argv, *size * sizeof(*argv));
+	if (argv) {
+		if (old_argv)
+			memcpy(argv, old_argv, *size * sizeof(*argv));
 		*size = new_size;
 	}
 
@@ -1049,7 +1050,6 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
 	unsigned int min_pool_size = 0, pool_size;
 	struct dm_md_mempools *pools;
 	unsigned int bioset_flags = 0;
-	bool mempool_needs_integrity = t->integrity_supported;
 
 	if (unlikely(type == DM_TYPE_NONE)) {
 		DMERR("no table type is set, can't allocate mempools");
@@ -1074,8 +1074,6 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
 
 		per_io_data_size = max(per_io_data_size, ti->per_io_data_size);
 		min_pool_size = max(min_pool_size, ti->num_flush_bios);
-
-		mempool_needs_integrity |= ti->mempool_needs_integrity;
 	}
 	pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size);
 	front_pad = roundup(per_io_data_size,
@@ -1175,7 +1173,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile,
 
 	t = dm_get_live_table(md, &srcu_idx);
 	if (!t)
-		return 0;
+		goto put_live_table;
 
 	for (unsigned int i = 0; i < t->num_targets; i++) {
 		struct dm_target *ti = dm_table_get_target(t, i);
@@ -1186,6 +1184,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile,
 					  (void *)key);
 	}
 
+put_live_table:
 	dm_put_live_table(md, srcu_idx);
 	return 0;
 }
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 44ec9b17cfd3..37b08f26c62f 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -2357,9 +2357,8 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats)
 
 	if (!bitmap)
 		return -ENOENT;
-	if (bitmap->mddev->bitmap_info.external)
-		return -ENOENT;
-	if (!bitmap->storage.sb_page) /* no superblock */
+	if (!bitmap->mddev->bitmap_info.external &&
+	    !bitmap->storage.sb_page)
 		return -EINVAL;
 	sb = kmap_local_page(bitmap->storage.sb_page);
 	stats->sync_size = le64_to_cpu(sb->sync_size);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 0efc03cea24e..de9bccbe7337 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -2200,14 +2200,9 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 				if (!rdev_set_badblocks(rdev, sect, s, 0))
 					abort = 1;
 			}
-			if (abort) {
-				conf->recovery_disabled =
-					mddev->recovery_disabled;
-				set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-				md_done_sync(mddev, r1_bio->sectors, 0);
-				put_buf(r1_bio);
+			if (abort)
 				return 0;
-			}
+
 			/* Try next page */
 			sectors -= s;
 			sect += s;
@@ -2346,10 +2341,21 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 	int disks = conf->raid_disks * 2;
 	struct bio *wbio;
 
-	if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
-		/* ouch - failed to read all of that. */
-		if (!fix_sync_read_error(r1_bio))
+	if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) {
+		/*
+		 * ouch - failed to read all of that.
+		 * No need to fix read error for check/repair
+		 * because all member disks are read.
+		 */
+		if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) ||
+		    !fix_sync_read_error(r1_bio)) {
+			conf->recovery_disabled = mddev->recovery_disabled;
+			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+			md_done_sync(mddev, r1_bio->sectors, 0);
+			put_buf(r1_bio);
 			return;
+		}
+	}
 
 	if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 		process_checks(r1_bio);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 846c5f29486e..ba32bac975b8 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1735,6 +1735,7 @@ retry_discard:
 	 * The discard bio returns only first r10bio finishes
 	 */
 	if (first_copy) {
+		md_account_bio(mddev, &bio);
 		r10_bio->master_bio = bio;
 		set_bit(R10BIO_Discard, &r10_bio->state);
 		first_copy = false;
diff --git a/drivers/media/cec/i2c/Kconfig b/drivers/media/cec/i2c/Kconfig
index b9d21643eef1..c31abc26f602 100644
--- a/drivers/media/cec/i2c/Kconfig
+++ b/drivers/media/cec/i2c/Kconfig
@@ -16,6 +16,7 @@ config CEC_CH7322
 
 config CEC_NXP_TDA9950
 	tristate "NXP Semiconductors TDA9950/TDA998X HDMI CEC"
+	depends on I2C
 	select CEC_NOTIFIER
 	select CEC_CORE
 	default DRM_I2C_NXP_TDA998X
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index e576b213084d..e45ba127069f 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -1149,8 +1149,11 @@ config VIDEO_ISL7998X
 
 config VIDEO_LT6911UXE
 	tristate "Lontium LT6911UXE decoder"
-	depends on ACPI && VIDEO_DEV
+	depends on ACPI && VIDEO_DEV && I2C
 	select V4L2_FWNODE
+	select V4L2_CCI_I2C
+	select MEDIA_CONTROLLER
+	select VIDEO_V4L2_SUBDEV_API
 	help
 	  This is a Video4Linux2 sensor-level driver for the Lontium
 	  LT6911UXE HDMI to MIPI CSI-2 bridge.
diff --git a/drivers/media/platform/synopsys/hdmirx/Kconfig b/drivers/media/platform/synopsys/hdmirx/Kconfig
index 27e6706f84a3..4321f985f632 100644
--- a/drivers/media/platform/synopsys/hdmirx/Kconfig
+++ b/drivers/media/platform/synopsys/hdmirx/Kconfig
@@ -2,6 +2,7 @@
 
 config VIDEO_SYNOPSYS_HDMIRX
 	tristate "Synopsys DesignWare HDMI Receiver driver"
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
 	depends on VIDEO_DEV
 	select MEDIA_CONTROLLER
 	select VIDEO_V4L2_SUBDEV_API
diff --git a/drivers/media/test-drivers/vivid/Kconfig b/drivers/media/test-drivers/vivid/Kconfig
index e95edc0f22bf..cc470070a7a5 100644
--- a/drivers/media/test-drivers/vivid/Kconfig
+++ b/drivers/media/test-drivers/vivid/Kconfig
@@ -32,7 +32,8 @@ config VIDEO_VIVID_CEC
 
 config VIDEO_VIVID_OSD
 	bool "Enable Framebuffer for testing Output Overlay"
-	depends on VIDEO_VIVID && FB
+	depends on VIDEO_VIVID && FB_CORE
+	depends on VIDEO_VIVID=m || FB_CORE=y
 	default y
 	select FB_IOMEM_HELPERS
 	help
diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
index 04756302b878..98d3d123004c 100644
--- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
+++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
@@ -37,6 +37,7 @@
 struct pci1xxxx_gpio {
 	struct auxiliary_device *aux_dev;
 	void __iomem *reg_base;
+	raw_spinlock_t wa_lock;
 	struct gpio_chip gpio;
 	spinlock_t lock;
 	int irq_base;
@@ -167,7 +168,7 @@ static void pci1xxxx_gpio_irq_ack(struct irq_data *data)
 	unsigned long flags;
 
 	spin_lock_irqsave(&priv->lock, flags);
-	pci1xxx_assign_bit(priv->reg_base, INTR_STAT_OFFSET(gpio), (gpio % 32), true);
+	writel(BIT(gpio % 32), priv->reg_base + INTR_STAT_OFFSET(gpio));
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
@@ -257,6 +258,7 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id)
 	struct pci1xxxx_gpio *priv = dev_id;
 	struct gpio_chip *gc =  &priv->gpio;
 	unsigned long int_status = 0;
+	unsigned long wa_flags;
 	unsigned long flags;
 	u8 pincount;
 	int bit;
@@ -280,7 +282,9 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id)
 			writel(BIT(bit), priv->reg_base + INTR_STATUS_OFFSET(gpiobank));
 			spin_unlock_irqrestore(&priv->lock, flags);
 			irq = irq_find_mapping(gc->irq.domain, (bit + (gpiobank * 32)));
-			handle_nested_irq(irq);
+			raw_spin_lock_irqsave(&priv->wa_lock, wa_flags);
+			generic_handle_irq(irq);
+			raw_spin_unlock_irqrestore(&priv->wa_lock, wa_flags);
 		}
 	}
 	spin_lock_irqsave(&priv->lock, flags);
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index a5f88ec97df7..bc40b940ae21 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -117,6 +117,7 @@
 
 #define MEI_DEV_ID_LNL_M      0xA870  /* Lunar Lake Point M */
 
+#define MEI_DEV_ID_PTL_H      0xE370  /* Panther Lake H */
 #define MEI_DEV_ID_PTL_P      0xE470  /* Panther Lake P */
 
 /*
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index d6ff9d82ae94..3f9c60b579ae 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -124,6 +124,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_LNL_M, MEI_ME_PCH15_CFG)},
 
+	{MEI_PCI_DEVICE(MEI_DEV_ID_PTL_H, MEI_ME_PCH15_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_PTL_P, MEI_ME_PCH15_CFG)},
 
 	/* required last entry */
diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c
index 7be1649b1972..da26a080916c 100644
--- a/drivers/misc/mei/vsc-tp.c
+++ b/drivers/misc/mei/vsc-tp.c
@@ -36,20 +36,24 @@
 #define VSC_TP_XFER_TIMEOUT_BYTES		700
 #define VSC_TP_PACKET_PADDING_SIZE		1
 #define VSC_TP_PACKET_SIZE(pkt) \
-	(sizeof(struct vsc_tp_packet) + le16_to_cpu((pkt)->len) + VSC_TP_CRC_SIZE)
+	(sizeof(struct vsc_tp_packet_hdr) + le16_to_cpu((pkt)->hdr.len) + VSC_TP_CRC_SIZE)
 #define VSC_TP_MAX_PACKET_SIZE \
-	(sizeof(struct vsc_tp_packet) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
+	(sizeof(struct vsc_tp_packet_hdr) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
 #define VSC_TP_MAX_XFER_SIZE \
 	(VSC_TP_MAX_PACKET_SIZE + VSC_TP_XFER_TIMEOUT_BYTES)
 #define VSC_TP_NEXT_XFER_LEN(len, offset) \
-	(len + sizeof(struct vsc_tp_packet) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
+	(len + sizeof(struct vsc_tp_packet_hdr) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
 
-struct vsc_tp_packet {
+struct vsc_tp_packet_hdr {
 	__u8 sync;
 	__u8 cmd;
 	__le16 len;
 	__le32 seq;
-	__u8 buf[] __counted_by(len);
+};
+
+struct vsc_tp_packet {
+	struct vsc_tp_packet_hdr hdr;
+	__u8 buf[VSC_TP_MAX_XFER_SIZE - sizeof(struct vsc_tp_packet_hdr)];
 };
 
 struct vsc_tp {
@@ -67,8 +71,8 @@ struct vsc_tp {
 	u32 seq;
 
 	/* command buffer */
-	void *tx_buf;
-	void *rx_buf;
+	struct vsc_tp_packet *tx_buf;
+	struct vsc_tp_packet *rx_buf;
 
 	atomic_t assert_cnt;
 	wait_queue_head_t xfer_wait;
@@ -158,12 +162,12 @@ static int vsc_tp_dev_xfer(struct vsc_tp *tp, void *obuf, void *ibuf, size_t len
 static int vsc_tp_xfer_helper(struct vsc_tp *tp, struct vsc_tp_packet *pkt,
 			      void *ibuf, u16 ilen)
 {
-	int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet);
+	int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet_hdr);
 	int next_xfer_len = VSC_TP_PACKET_SIZE(pkt) + VSC_TP_XFER_TIMEOUT_BYTES;
-	u8 *src, *crc_src, *rx_buf = tp->rx_buf;
+	u8 *src, *crc_src, *rx_buf = (u8 *)tp->rx_buf;
 	int count_down = VSC_TP_MAX_XFER_COUNT;
 	u32 recv_crc = 0, crc = ~0;
-	struct vsc_tp_packet ack;
+	struct vsc_tp_packet_hdr ack;
 	u8 *dst = (u8 *)&ack;
 	bool synced = false;
 
@@ -280,10 +284,10 @@ int vsc_tp_xfer(struct vsc_tp *tp, u8 cmd, const void *obuf, size_t olen,
 
 	guard(mutex)(&tp->mutex);
 
-	pkt->sync = VSC_TP_PACKET_SYNC;
-	pkt->cmd = cmd;
-	pkt->len = cpu_to_le16(olen);
-	pkt->seq = cpu_to_le32(++tp->seq);
+	pkt->hdr.sync = VSC_TP_PACKET_SYNC;
+	pkt->hdr.cmd = cmd;
+	pkt->hdr.len = cpu_to_le16(olen);
+	pkt->hdr.seq = cpu_to_le32(++tp->seq);
 	memcpy(pkt->buf, obuf, olen);
 
 	crc = ~crc32(~0, (u8 *)pkt, sizeof(pkt) + olen);
@@ -320,7 +324,7 @@ int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len)
 	guard(mutex)(&tp->mutex);
 
 	/* rom xfer is big endian */
-	cpu_to_be32_array(tp->tx_buf, obuf, words);
+	cpu_to_be32_array((u32 *)tp->tx_buf, obuf, words);
 
 	ret = read_poll_timeout(gpiod_get_value_cansleep, ret,
 				!ret, VSC_TP_ROM_XFER_POLL_DELAY_US,
@@ -336,7 +340,7 @@ int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len)
 		return ret;
 
 	if (ibuf)
-		be32_to_cpu_array(ibuf, tp->rx_buf, words);
+		be32_to_cpu_array(ibuf, (u32 *)tp->rx_buf, words);
 
 	return ret;
 }
@@ -490,11 +494,11 @@ static int vsc_tp_probe(struct spi_device *spi)
 	if (!tp)
 		return -ENOMEM;
 
-	tp->tx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+	tp->tx_buf = devm_kzalloc(dev, sizeof(*tp->tx_buf), GFP_KERNEL);
 	if (!tp->tx_buf)
 		return -ENOMEM;
 
-	tp->rx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+	tp->rx_buf = devm_kzalloc(dev, sizeof(*tp->rx_buf), GFP_KERNEL);
 	if (!tp->rx_buf)
 		return -ENOMEM;
 
diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index d294850a35a1..c4e5e2c977be 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -122,7 +122,6 @@ struct pci_endpoint_test {
 struct pci_endpoint_test_data {
 	enum pci_barno test_reg_bar;
 	size_t alignment;
-	int irq_type;
 };
 
 static inline u32 pci_endpoint_test_readl(struct pci_endpoint_test *test,
@@ -948,7 +947,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 		test_reg_bar = data->test_reg_bar;
 		test->test_reg_bar = test_reg_bar;
 		test->alignment = data->alignment;
-		test->irq_type = data->irq_type;
 	}
 
 	init_completion(&test->irq_raised);
@@ -970,10 +968,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
-	ret = pci_endpoint_test_alloc_irq_vectors(test, test->irq_type);
-	if (ret)
-		goto err_disable_irq;
-
 	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
 		if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) {
 			base = pci_ioremap_bar(pdev, bar);
@@ -1009,10 +1003,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 		goto err_ida_remove;
 	}
 
-	ret = pci_endpoint_test_request_irq(test);
-	if (ret)
-		goto err_kfree_test_name;
-
 	pci_endpoint_test_get_capabilities(test);
 
 	misc_device = &test->miscdev;
@@ -1020,7 +1010,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 	misc_device->name = kstrdup(name, GFP_KERNEL);
 	if (!misc_device->name) {
 		ret = -ENOMEM;
-		goto err_release_irq;
+		goto err_kfree_test_name;
 	}
 	misc_device->parent = &pdev->dev;
 	misc_device->fops = &pci_endpoint_test_fops;
@@ -1036,9 +1026,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 err_kfree_name:
 	kfree(misc_device->name);
 
-err_release_irq:
-	pci_endpoint_test_release_irq(test);
-
 err_kfree_test_name:
 	kfree(test->name);
 
@@ -1051,8 +1038,6 @@ err_iounmap:
 			pci_iounmap(pdev, test->bar[bar]);
 	}
 
-err_disable_irq:
-	pci_endpoint_test_free_irq_vectors(test);
 	pci_release_regions(pdev);
 
 err_disable_pdev:
@@ -1092,23 +1077,19 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev)
 static const struct pci_endpoint_test_data default_data = {
 	.test_reg_bar = BAR_0,
 	.alignment = SZ_4K,
-	.irq_type = PCITEST_IRQ_TYPE_MSI,
 };
 
 static const struct pci_endpoint_test_data am654_data = {
 	.test_reg_bar = BAR_2,
 	.alignment = SZ_64K,
-	.irq_type = PCITEST_IRQ_TYPE_MSI,
 };
 
 static const struct pci_endpoint_test_data j721e_data = {
 	.alignment = 256,
-	.irq_type = PCITEST_IRQ_TYPE_MSI,
 };
 
 static const struct pci_endpoint_test_data rk3588_data = {
 	.alignment = SZ_64K,
-	.irq_type = PCITEST_IRQ_TYPE_MSI,
 };
 
 /*
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 6824131b69b1..264e11fa58ea 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -691,8 +691,8 @@ config MMC_TMIO_CORE
 config MMC_SDHI
 	tristate "Renesas SDHI SD/SDIO controller support"
 	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
+	depends on (RESET_CONTROLLER && REGULATOR) || !OF
 	select MMC_TMIO_CORE
-	select RESET_CONTROLLER if ARCH_RENESAS
 	help
 	  This provides support for the SDHI SD/SDIO controller found in
 	  Renesas SuperH, ARM and ARM64 based SoCs
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index fa6526be3638..8c83e203c516 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -1179,7 +1179,7 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 		if (IS_ERR(rdev)) {
 			dev_err(dev, "regulator register failed err=%ld", PTR_ERR(rdev));
 			ret = PTR_ERR(rdev);
-			goto efree;
+			goto edisclk;
 		}
 		priv->rdev = rdev;
 	}
@@ -1243,26 +1243,26 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	num_irqs = platform_irq_count(pdev);
 	if (num_irqs < 0) {
 		ret = num_irqs;
-		goto eirq;
+		goto edisclk;
 	}
 
 	/* There must be at least one IRQ source */
 	if (!num_irqs) {
 		ret = -ENXIO;
-		goto eirq;
+		goto edisclk;
 	}
 
 	for (i = 0; i < num_irqs; i++) {
 		irq = platform_get_irq(pdev, i);
 		if (irq < 0) {
 			ret = irq;
-			goto eirq;
+			goto edisclk;
 		}
 
 		ret = devm_request_irq(&pdev->dev, irq, tmio_mmc_irq, 0,
 				       dev_name(&pdev->dev), host);
 		if (ret)
-			goto eirq;
+			goto edisclk;
 	}
 
 	ret = tmio_mmc_host_probe(host);
@@ -1274,8 +1274,6 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 
 	return ret;
 
-eirq:
-	tmio_mmc_host_remove(host);
 edisclk:
 	renesas_sdhi_clk_disable(host);
 efree:
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 271520510b5f..b29628d46be9 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -115,6 +115,21 @@ config WIREGUARD_DEBUG
 
 	  Say N here unless you know what you're doing.
 
+config OVPN
+	tristate "OpenVPN data channel offload"
+	depends on NET && INET
+	depends on IPV6 || !IPV6
+	select DST_CACHE
+	select NET_UDP_TUNNEL
+	select CRYPTO
+	select CRYPTO_AES
+	select CRYPTO_GCM
+	select CRYPTO_CHACHA20POLY1305
+	select STREAM_PARSER
+	help
+	  This module enhances the performance of the OpenVPN userspace software
+	  by offloading the data channel processing to kernelspace.
+
 config EQUALIZER
 	tristate "EQL (serial line load balancing) support"
 	help
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 75333251a01a..73bc63ecd65f 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_IPVLAN) += ipvlan/
 obj-$(CONFIG_IPVTAP) += ipvlan/
 obj-$(CONFIG_DUMMY) += dummy.o
 obj-$(CONFIG_WIREGUARD) += wireguard/
+obj-$(CONFIG_OVPN) += ovpn/
 obj-$(CONFIG_EQUALIZER) += eql.o
 obj-$(CONFIG_IFB) += ifb.o
 obj-$(CONFIG_MACSEC) += macsec.o
diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index d1473c5f8eef..a9dffdcac805 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -777,27 +777,19 @@ static __net_init int bareudp_init_net(struct net *net)
 	return 0;
 }
 
-static void bareudp_destroy_tunnels(struct net *net, struct list_head *head)
+static void __net_exit bareudp_exit_rtnl_net(struct net *net,
+					     struct list_head *dev_kill_list)
 {
 	struct bareudp_net *bn = net_generic(net, bareudp_net_id);
 	struct bareudp_dev *bareudp, *next;
 
 	list_for_each_entry_safe(bareudp, next, &bn->bareudp_list, next)
-		unregister_netdevice_queue(bareudp->dev, head);
-}
-
-static void __net_exit bareudp_exit_batch_rtnl(struct list_head *net_list,
-					       struct list_head *dev_kill_list)
-{
-	struct net *net;
-
-	list_for_each_entry(net, net_list, exit_list)
-		bareudp_destroy_tunnels(net, dev_kill_list);
+		bareudp_dellink(bareudp->dev, dev_kill_list);
 }
 
 static struct pernet_operations bareudp_net_ops = {
 	.init = bareudp_init_net,
-	.exit_batch_rtnl = bareudp_exit_batch_rtnl,
+	.exit_rtnl = bareudp_exit_rtnl_net,
 	.id   = &bareudp_net_id,
 	.size = sizeof(struct bareudp_net),
 };
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8ed8c29659a0..98cf4486fcee 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -847,8 +847,9 @@ static int bond_check_dev_link(struct bonding *bond,
 			       struct net_device *slave_dev, int reporting)
 {
 	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
-	struct ifreq ifr;
 	struct mii_ioctl_data *mii;
+	struct ifreq ifr;
+	int ret;
 
 	if (!reporting && !netif_running(slave_dev))
 		return 0;
@@ -857,9 +858,13 @@ static int bond_check_dev_link(struct bonding *bond,
 		return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;
 
 	/* Try to get link status using Ethtool first. */
-	if (slave_dev->ethtool_ops->get_link)
-		return slave_dev->ethtool_ops->get_link(slave_dev) ?
-			BMSR_LSTATUS : 0;
+	if (slave_dev->ethtool_ops->get_link) {
+		netdev_lock_ops(slave_dev);
+		ret = slave_dev->ethtool_ops->get_link(slave_dev);
+		netdev_unlock_ops(slave_dev);
+
+		return ret ? BMSR_LSTATUS : 0;
+	}
 
 	/* Ethtool can't be used, fallback to MII ioctls. */
 	if (slave_ops->ndo_eth_ioctl) {
@@ -2110,15 +2115,26 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		 * set the master's mac address to that of the first slave
 		 */
 		memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
-		ss.ss_family = slave_dev->type;
-		res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss,
-					  extack);
-		if (res) {
-			slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res);
-			goto err_restore_mtu;
-		}
+	} else if (bond->params.fail_over_mac == BOND_FOM_FOLLOW &&
+		   BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP &&
+		   memcmp(slave_dev->dev_addr, bond_dev->dev_addr, bond_dev->addr_len) == 0) {
+		/* Set slave to random address to avoid duplicate mac
+		 * address in later fail over.
+		 */
+		eth_random_addr(ss.__data);
+	} else {
+		goto skip_mac_set;
 	}
 
+	ss.ss_family = slave_dev->type;
+	res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, extack);
+	if (res) {
+		slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res);
+		goto err_restore_mtu;
+	}
+
+skip_mac_set:
+
 	/* set no_addrconf flag before open to prevent IPv6 addrconf */
 	slave_dev->priv_flags |= IFF_NO_ADDRCONF;
 
@@ -6555,7 +6571,7 @@ static int __net_init bond_net_init(struct net *net)
 
 /* According to commit 69b0216ac255 ("bonding: fix bonding_masters
  * race condition in bond unloading") we need to remove sysfs files
- * before we remove our devices (done later in bond_net_exit_batch_rtnl())
+ * before we remove our devices (done later in bond_net_exit_rtnl())
  */
 static void __net_exit bond_net_pre_exit(struct net *net)
 {
@@ -6564,25 +6580,20 @@ static void __net_exit bond_net_pre_exit(struct net *net)
 	bond_destroy_sysfs(bn);
 }
 
-static void __net_exit bond_net_exit_batch_rtnl(struct list_head *net_list,
-						struct list_head *dev_kill_list)
+static void __net_exit bond_net_exit_rtnl(struct net *net,
+					  struct list_head *dev_kill_list)
 {
-	struct bond_net *bn;
-	struct net *net;
+	struct bond_net *bn = net_generic(net, bond_net_id);
+	struct bonding *bond, *tmp_bond;
 
 	/* Kill off any bonds created after unregistering bond rtnl ops */
-	list_for_each_entry(net, net_list, exit_list) {
-		struct bonding *bond, *tmp_bond;
-
-		bn = net_generic(net, bond_net_id);
-		list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list)
-			unregister_netdevice_queue(bond->dev, dev_kill_list);
-	}
+	list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list)
+		unregister_netdevice_queue(bond->dev, dev_kill_list);
 }
 
 /* According to commit 23fa5c2caae0 ("bonding: destroy proc directory
  * only after all bonds are gone") bond_destroy_proc_dir() is called
- * after bond_net_exit_batch_rtnl() has completed.
+ * after bond_net_exit_rtnl() has completed.
  */
 static void __net_exit bond_net_exit_batch(struct list_head *net_list)
 {
@@ -6598,7 +6609,7 @@ static void __net_exit bond_net_exit_batch(struct list_head *net_list)
 static struct pernet_operations bond_net_ops = {
 	.init = bond_net_init,
 	.pre_exit = bond_net_pre_exit,
-	.exit_batch_rtnl = bond_net_exit_batch_rtnl,
+	.exit_rtnl = bond_net_exit_rtnl,
 	.exit_batch = bond_net_exit_batch,
 	.id   = &bond_net_id,
 	.size = sizeof(struct bond_net),
diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c
index f65c1a1e05cc..bf6398772960 100644
--- a/drivers/net/can/ctucanfd/ctucanfd_base.c
+++ b/drivers/net/can/ctucanfd/ctucanfd_base.c
@@ -275,7 +275,7 @@ static int ctucan_set_bittiming(struct net_device *ndev)
 static int ctucan_set_data_bittiming(struct net_device *ndev)
 {
 	struct ctucan_priv *priv = netdev_priv(ndev);
-	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 
 	/* Note that dbt may be modified here */
 	return ctucan_set_btr(ndev, dbt, false);
@@ -290,7 +290,7 @@ static int ctucan_set_data_bittiming(struct net_device *ndev)
 static int ctucan_set_secondary_sample_point(struct net_device *ndev)
 {
 	struct ctucan_priv *priv = netdev_priv(ndev);
-	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	int ssp_offset = 0;
 	u32 ssp_cfg = 0; /* No SSP by default */
 
@@ -1358,12 +1358,12 @@ int ctucan_probe_common(struct device *dev, void __iomem *addr, int irq, unsigne
 	priv->ntxbufs = ntxbufs;
 	priv->dev = dev;
 	priv->can.bittiming_const = &ctu_can_fd_bit_timing_max;
-	priv->can.data_bittiming_const = &ctu_can_fd_bit_timing_data_max;
+	priv->can.fd.data_bittiming_const = &ctu_can_fd_bit_timing_data_max;
 	priv->can.do_set_mode = ctucan_do_set_mode;
 
 	/* Needed for timing adjustment to be performed as soon as possible */
 	priv->can.do_set_bittiming = ctucan_set_bittiming;
-	priv->can.do_set_data_bittiming = ctucan_set_data_bittiming;
+	priv->can.fd.do_set_data_bittiming = ctucan_set_data_bittiming;
 
 	priv->can.do_get_berr_counter = ctucan_get_berr_counter;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK
diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c
index 5ec3170b896a..ea8c807af4d8 100644
--- a/drivers/net/can/dev/dev.c
+++ b/drivers/net/can/dev/dev.c
@@ -404,8 +404,8 @@ int open_candev(struct net_device *dev)
 
 	/* For CAN FD the data bitrate has to be >= the arbitration bitrate */
 	if ((priv->ctrlmode & CAN_CTRLMODE_FD) &&
-	    (!priv->data_bittiming.bitrate ||
-	     priv->data_bittiming.bitrate < priv->bittiming.bitrate)) {
+	    (!priv->fd.data_bittiming.bitrate ||
+	     priv->fd.data_bittiming.bitrate < priv->bittiming.bitrate)) {
 		netdev_err(dev, "incorrect/missing data bit-timing\n");
 		return -EINVAL;
 	}
@@ -543,16 +543,16 @@ int register_candev(struct net_device *dev)
 	if (!priv->bitrate_const != !priv->bitrate_const_cnt)
 		return -EINVAL;
 
-	if (!priv->data_bitrate_const != !priv->data_bitrate_const_cnt)
+	if (!priv->fd.data_bitrate_const != !priv->fd.data_bitrate_const_cnt)
 		return -EINVAL;
 
 	/* We only support either fixed bit rates or bit timing const. */
-	if ((priv->bitrate_const || priv->data_bitrate_const) &&
-	    (priv->bittiming_const || priv->data_bittiming_const))
+	if ((priv->bitrate_const || priv->fd.data_bitrate_const) &&
+	    (priv->bittiming_const || priv->fd.data_bittiming_const))
 		return -EINVAL;
 
 	if (!can_bittiming_const_valid(priv->bittiming_const) ||
-	    !can_bittiming_const_valid(priv->data_bittiming_const))
+	    !can_bittiming_const_valid(priv->fd.data_bittiming_const))
 		return -EINVAL;
 
 	if (!priv->termination_const) {
diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index f1db9b7ffd4d..a36842ace084 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -141,7 +141,7 @@ static int can_tdc_changelink(struct can_priv *priv, const struct nlattr *nla,
 {
 	struct nlattr *tb_tdc[IFLA_CAN_TDC_MAX + 1];
 	struct can_tdc tdc = { 0 };
-	const struct can_tdc_const *tdc_const = priv->tdc_const;
+	const struct can_tdc_const *tdc_const = priv->fd.tdc_const;
 	int err;
 
 	if (!tdc_const || !can_tdc_is_enabled(priv))
@@ -179,7 +179,7 @@ static int can_tdc_changelink(struct can_priv *priv, const struct nlattr *nla,
 		tdc.tdcf = tdcf;
 	}
 
-	priv->tdc = tdc;
+	priv->fd.tdc = tdc;
 
 	return 0;
 }
@@ -228,10 +228,10 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 			dev->mtu = CANFD_MTU;
 		} else {
 			dev->mtu = CAN_MTU;
-			memset(&priv->data_bittiming, 0,
-			       sizeof(priv->data_bittiming));
+			memset(&priv->fd.data_bittiming, 0,
+			       sizeof(priv->fd.data_bittiming));
 			priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK;
-			memset(&priv->tdc, 0, sizeof(priv->tdc));
+			memset(&priv->fd.tdc, 0, sizeof(priv->fd.tdc));
 		}
 
 		tdc_mask = cm->mask & CAN_CTRLMODE_TDC_MASK;
@@ -312,16 +312,16 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 		 * directly via do_set_bitrate(). Bail out if neither
 		 * is given.
 		 */
-		if (!priv->data_bittiming_const && !priv->do_set_data_bittiming &&
-		    !priv->data_bitrate_const)
+		if (!priv->fd.data_bittiming_const && !priv->fd.do_set_data_bittiming &&
+		    !priv->fd.data_bitrate_const)
 			return -EOPNOTSUPP;
 
 		memcpy(&dbt, nla_data(data[IFLA_CAN_DATA_BITTIMING]),
 		       sizeof(dbt));
 		err = can_get_bittiming(dev, &dbt,
-					priv->data_bittiming_const,
-					priv->data_bitrate_const,
-					priv->data_bitrate_const_cnt,
+					priv->fd.data_bittiming_const,
+					priv->fd.data_bitrate_const,
+					priv->fd.data_bitrate_const_cnt,
 					extack);
 		if (err)
 			return err;
@@ -333,7 +333,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 			return -EINVAL;
 		}
 
-		memset(&priv->tdc, 0, sizeof(priv->tdc));
+		memset(&priv->fd.tdc, 0, sizeof(priv->fd.tdc));
 		if (data[IFLA_CAN_TDC]) {
 			/* TDC parameters are provided: use them */
 			err = can_tdc_changelink(priv, data[IFLA_CAN_TDC],
@@ -346,17 +346,17 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 			/* Neither of TDC parameters nor TDC flags are
 			 * provided: do calculation
 			 */
-			can_calc_tdco(&priv->tdc, priv->tdc_const, &dbt,
+			can_calc_tdco(&priv->fd.tdc, priv->fd.tdc_const, &dbt,
 				      &priv->ctrlmode, priv->ctrlmode_supported);
 		} /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly
 		   * turned off. TDC is disabled: do nothing
 		   */
 
-		memcpy(&priv->data_bittiming, &dbt, sizeof(dbt));
+		memcpy(&priv->fd.data_bittiming, &dbt, sizeof(dbt));
 
-		if (priv->do_set_data_bittiming) {
+		if (priv->fd.do_set_data_bittiming) {
 			/* Finally, set the bit-timing registers */
-			err = priv->do_set_data_bittiming(dev);
+			err = priv->fd.do_set_data_bittiming(dev);
 			if (err)
 				return err;
 		}
@@ -394,7 +394,7 @@ static size_t can_tdc_get_size(const struct net_device *dev)
 	struct can_priv *priv = netdev_priv(dev);
 	size_t size;
 
-	if (!priv->tdc_const)
+	if (!priv->fd.tdc_const)
 		return 0;
 
 	size = nla_total_size(0);			/* nest IFLA_CAN_TDC */
@@ -404,17 +404,17 @@ static size_t can_tdc_get_size(const struct net_device *dev)
 	}
 	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_TDCO_MIN */
 	size += nla_total_size(sizeof(u32));		/* IFLA_CAN_TDCO_MAX */
-	if (priv->tdc_const->tdcf_max) {
+	if (priv->fd.tdc_const->tdcf_max) {
 		size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCF_MIN */
 		size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCF_MAX */
 	}
 
 	if (can_tdc_is_enabled(priv)) {
 		if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL ||
-		    priv->do_get_auto_tdcv)
+		    priv->fd.do_get_auto_tdcv)
 			size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCV */
 		size += nla_total_size(sizeof(u32));		/* IFLA_CAN_TDCO */
-		if (priv->tdc_const->tdcf_max)
+		if (priv->fd.tdc_const->tdcf_max)
 			size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCF */
 	}
 
@@ -442,9 +442,9 @@ static size_t can_get_size(const struct net_device *dev)
 	size += nla_total_size(sizeof(u32));			/* IFLA_CAN_RESTART_MS */
 	if (priv->do_get_berr_counter)				/* IFLA_CAN_BERR_COUNTER */
 		size += nla_total_size(sizeof(struct can_berr_counter));
-	if (priv->data_bittiming.bitrate)			/* IFLA_CAN_DATA_BITTIMING */
+	if (priv->fd.data_bittiming.bitrate)			/* IFLA_CAN_DATA_BITTIMING */
 		size += nla_total_size(sizeof(struct can_bittiming));
-	if (priv->data_bittiming_const)				/* IFLA_CAN_DATA_BITTIMING_CONST */
+	if (priv->fd.data_bittiming_const)			/* IFLA_CAN_DATA_BITTIMING_CONST */
 		size += nla_total_size(sizeof(struct can_bittiming_const));
 	if (priv->termination_const) {
 		size += nla_total_size(sizeof(priv->termination));		/* IFLA_CAN_TERMINATION */
@@ -454,9 +454,9 @@ static size_t can_get_size(const struct net_device *dev)
 	if (priv->bitrate_const)				/* IFLA_CAN_BITRATE_CONST */
 		size += nla_total_size(sizeof(*priv->bitrate_const) *
 				       priv->bitrate_const_cnt);
-	if (priv->data_bitrate_const)				/* IFLA_CAN_DATA_BITRATE_CONST */
-		size += nla_total_size(sizeof(*priv->data_bitrate_const) *
-				       priv->data_bitrate_const_cnt);
+	if (priv->fd.data_bitrate_const)			/* IFLA_CAN_DATA_BITRATE_CONST */
+		size += nla_total_size(sizeof(*priv->fd.data_bitrate_const) *
+				       priv->fd.data_bitrate_const_cnt);
 	size += sizeof(priv->bitrate_max);			/* IFLA_CAN_BITRATE_MAX */
 	size += can_tdc_get_size(dev);				/* IFLA_CAN_TDC */
 	size += can_ctrlmode_ext_get_size();			/* IFLA_CAN_CTRLMODE_EXT */
@@ -468,8 +468,8 @@ static int can_tdc_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
 	struct nlattr *nest;
 	struct can_priv *priv = netdev_priv(dev);
-	struct can_tdc *tdc = &priv->tdc;
-	const struct can_tdc_const *tdc_const = priv->tdc_const;
+	struct can_tdc *tdc = &priv->fd.tdc;
+	const struct can_tdc_const *tdc_const = priv->fd.tdc_const;
 
 	if (!tdc_const)
 		return 0;
@@ -497,8 +497,8 @@ static int can_tdc_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL) {
 			tdcv = tdc->tdcv;
 			err = 0;
-		} else if (priv->do_get_auto_tdcv) {
-			err = priv->do_get_auto_tdcv(dev, &tdcv);
+		} else if (priv->fd.do_get_auto_tdcv) {
+			err = priv->fd.do_get_auto_tdcv(dev, &tdcv);
 		}
 		if (!err && nla_put_u32(skb, IFLA_CAN_TDC_TDCV, tdcv))
 			goto err_cancel;
@@ -564,14 +564,14 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	     !priv->do_get_berr_counter(dev, &bec) &&
 	     nla_put(skb, IFLA_CAN_BERR_COUNTER, sizeof(bec), &bec)) ||
 
-	    (priv->data_bittiming.bitrate &&
+	    (priv->fd.data_bittiming.bitrate &&
 	     nla_put(skb, IFLA_CAN_DATA_BITTIMING,
-		     sizeof(priv->data_bittiming), &priv->data_bittiming)) ||
+		     sizeof(priv->fd.data_bittiming), &priv->fd.data_bittiming)) ||
 
-	    (priv->data_bittiming_const &&
+	    (priv->fd.data_bittiming_const &&
 	     nla_put(skb, IFLA_CAN_DATA_BITTIMING_CONST,
-		     sizeof(*priv->data_bittiming_const),
-		     priv->data_bittiming_const)) ||
+		     sizeof(*priv->fd.data_bittiming_const),
+		     priv->fd.data_bittiming_const)) ||
 
 	    (priv->termination_const &&
 	     (nla_put_u16(skb, IFLA_CAN_TERMINATION, priv->termination) ||
@@ -586,11 +586,11 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		     priv->bitrate_const_cnt,
 		     priv->bitrate_const)) ||
 
-	    (priv->data_bitrate_const &&
+	    (priv->fd.data_bitrate_const &&
 	     nla_put(skb, IFLA_CAN_DATA_BITRATE_CONST,
-		     sizeof(*priv->data_bitrate_const) *
-		     priv->data_bitrate_const_cnt,
-		     priv->data_bitrate_const)) ||
+		     sizeof(*priv->fd.data_bitrate_const) *
+		     priv->fd.data_bitrate_const_cnt,
+		     priv->fd.data_bitrate_const)) ||
 
 	    (nla_put(skb, IFLA_CAN_BITRATE_MAX,
 		     sizeof(priv->bitrate_max),
diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index 6d80c341b26f..06d5d35fc1b5 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -1226,7 +1226,7 @@ static void flexcan_set_bittiming_cbt(const struct net_device *dev)
 {
 	struct flexcan_priv *priv = netdev_priv(dev);
 	struct can_bittiming *bt = &priv->can.bittiming;
-	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	struct flexcan_regs __iomem *regs = priv->regs;
 	u32 reg_cbt, reg_fdctrl;
 
@@ -2239,7 +2239,7 @@ static int flexcan_probe(struct platform_device *pdev)
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD |
 			CAN_CTRLMODE_FD_NON_ISO;
 		priv->can.bittiming_const = &flexcan_fd_bittiming_const;
-		priv->can.data_bittiming_const =
+		priv->can.fd.data_bittiming_const =
 			&flexcan_fd_data_bittiming_const;
 	} else {
 		priv->can.bittiming_const = &flexcan_bittiming_const;
diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c
index c86b57d47085..2eeee65f606f 100644
--- a/drivers/net/can/ifi_canfd/ifi_canfd.c
+++ b/drivers/net/can/ifi_canfd/ifi_canfd.c
@@ -669,7 +669,7 @@ static void ifi_canfd_set_bittiming(struct net_device *ndev)
 {
 	struct ifi_canfd_priv *priv = netdev_priv(ndev);
 	const struct can_bittiming *bt = &priv->can.bittiming;
-	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	const struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	u16 brp, sjw, tseg1, tseg2, tdc;
 
 	/* Configure bit timing */
@@ -1000,10 +1000,10 @@ static int ifi_canfd_plat_probe(struct platform_device *pdev)
 
 	priv->can.clock.freq = readl(addr + IFI_CANFD_CANCLOCK);
 
-	priv->can.bittiming_const	= &ifi_canfd_bittiming_const;
-	priv->can.data_bittiming_const	= &ifi_canfd_bittiming_const;
-	priv->can.do_set_mode		= ifi_canfd_set_mode;
-	priv->can.do_get_berr_counter	= ifi_canfd_get_berr_counter;
+	priv->can.bittiming_const = &ifi_canfd_bittiming_const;
+	priv->can.fd.data_bittiming_const = &ifi_canfd_bittiming_const;
+	priv->can.do_set_mode = ifi_canfd_set_mode;
+	priv->can.do_get_berr_counter = ifi_canfd_get_berr_counter;
 
 	/* IFI CANFD can do both Bosch FD and ISO FD */
 	priv->can.ctrlmode = CAN_CTRLMODE_FD;
diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index cf0d51805272..7d3066691d5d 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -16,6 +16,7 @@
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/timer.h>
+#include <net/netdev_queues.h>
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Kvaser AB <support@kvaser.com>");
@@ -410,10 +411,13 @@ struct kvaser_pciefd_can {
 	void __iomem *reg_base;
 	struct can_berr_counter bec;
 	u8 cmd_seq;
+	u8 tx_max_count;
+	u8 tx_idx;
+	u8 ack_idx;
 	int err_rep_cnt;
-	int echo_idx;
+	unsigned int completed_tx_pkts;
+	unsigned int completed_tx_bytes;
 	spinlock_t lock; /* Locks sensitive registers (e.g. MODE) */
-	spinlock_t echo_lock; /* Locks the message echo buffer */
 	struct timer_list bec_poll_timer;
 	struct completion start_comp, flush_comp;
 };
@@ -714,6 +718,9 @@ static int kvaser_pciefd_open(struct net_device *netdev)
 	int ret;
 	struct kvaser_pciefd_can *can = netdev_priv(netdev);
 
+	can->tx_idx = 0;
+	can->ack_idx = 0;
+
 	ret = open_candev(netdev);
 	if (ret)
 		return ret;
@@ -745,21 +752,26 @@ static int kvaser_pciefd_stop(struct net_device *netdev)
 		timer_delete(&can->bec_poll_timer);
 	}
 	can->can.state = CAN_STATE_STOPPED;
+	netdev_reset_queue(netdev);
 	close_candev(netdev);
 
 	return ret;
 }
 
+static unsigned int kvaser_pciefd_tx_avail(const struct kvaser_pciefd_can *can)
+{
+	return can->tx_max_count - (READ_ONCE(can->tx_idx) - READ_ONCE(can->ack_idx));
+}
+
 static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p,
-					   struct kvaser_pciefd_can *can,
+					   struct can_priv *can, u8 seq,
 					   struct sk_buff *skb)
 {
 	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
 	int packet_size;
-	int seq = can->echo_idx;
 
 	memset(p, 0, sizeof(*p));
-	if (can->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT)
+	if (can->ctrlmode & CAN_CTRLMODE_ONE_SHOT)
 		p->header[1] |= KVASER_PCIEFD_TPACKET_SMS;
 
 	if (cf->can_id & CAN_RTR_FLAG)
@@ -782,7 +794,7 @@ static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p,
 	} else {
 		p->header[1] |=
 			FIELD_PREP(KVASER_PCIEFD_RPACKET_DLC_MASK,
-				   can_get_cc_dlc((struct can_frame *)cf, can->can.ctrlmode));
+				   can_get_cc_dlc((struct can_frame *)cf, can->ctrlmode));
 	}
 
 	p->header[1] |= FIELD_PREP(KVASER_PCIEFD_PACKET_SEQ_MASK, seq);
@@ -797,22 +809,24 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb,
 					    struct net_device *netdev)
 {
 	struct kvaser_pciefd_can *can = netdev_priv(netdev);
-	unsigned long irq_flags;
 	struct kvaser_pciefd_tx_packet packet;
+	unsigned int seq = can->tx_idx & (can->can.echo_skb_max - 1);
+	unsigned int frame_len;
 	int nr_words;
-	u8 count;
 
 	if (can_dev_dropped_skb(netdev, skb))
 		return NETDEV_TX_OK;
+	if (!netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1))
+		return NETDEV_TX_BUSY;
 
-	nr_words = kvaser_pciefd_prepare_tx_packet(&packet, can, skb);
+	nr_words = kvaser_pciefd_prepare_tx_packet(&packet, &can->can, seq, skb);
 
-	spin_lock_irqsave(&can->echo_lock, irq_flags);
 	/* Prepare and save echo skb in internal slot */
-	can_put_echo_skb(skb, netdev, can->echo_idx, 0);
-
-	/* Move echo index to the next slot */
-	can->echo_idx = (can->echo_idx + 1) % can->can.echo_skb_max;
+	WRITE_ONCE(can->can.echo_skb[seq], NULL);
+	frame_len = can_skb_get_frame_len(skb);
+	can_put_echo_skb(skb, netdev, seq, frame_len);
+	netdev_sent_queue(netdev, frame_len);
+	WRITE_ONCE(can->tx_idx, can->tx_idx + 1);
 
 	/* Write header to fifo */
 	iowrite32(packet.header[0],
@@ -836,14 +850,7 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb,
 			     KVASER_PCIEFD_KCAN_FIFO_LAST_REG);
 	}
 
-	count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK,
-			  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
-	/* No room for a new message, stop the queue until at least one
-	 * successful transmit
-	 */
-	if (count >= can->can.echo_skb_max || can->can.echo_skb[can->echo_idx])
-		netif_stop_queue(netdev);
-	spin_unlock_irqrestore(&can->echo_lock, irq_flags);
+	netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1);
 
 	return NETDEV_TX_OK;
 }
@@ -856,7 +863,7 @@ static int kvaser_pciefd_set_bittiming(struct kvaser_pciefd_can *can, bool data)
 	struct can_bittiming *bt;
 
 	if (data)
-		bt = &can->can.data_bittiming;
+		bt = &can->can.fd.data_bittiming;
 	else
 		bt = &can->can.bittiming;
 
@@ -970,6 +977,8 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		can->kv_pcie = pcie;
 		can->cmd_seq = 0;
 		can->err_rep_cnt = 0;
+		can->completed_tx_pkts = 0;
+		can->completed_tx_bytes = 0;
 		can->bec.txerr = 0;
 		can->bec.rxerr = 0;
 
@@ -983,17 +992,16 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		tx_nr_packets_max =
 			FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_MAX_MASK,
 				  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
+		can->tx_max_count = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1);
 
 		can->can.clock.freq = pcie->freq;
-		can->can.echo_skb_max = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1);
-		can->echo_idx = 0;
-		spin_lock_init(&can->echo_lock);
+		can->can.echo_skb_max = roundup_pow_of_two(can->tx_max_count);
 		spin_lock_init(&can->lock);
 
 		can->can.bittiming_const = &kvaser_pciefd_bittiming_const;
-		can->can.data_bittiming_const = &kvaser_pciefd_bittiming_const;
+		can->can.fd.data_bittiming_const = &kvaser_pciefd_bittiming_const;
 		can->can.do_set_bittiming = kvaser_pciefd_set_nominal_bittiming;
-		can->can.do_set_data_bittiming = kvaser_pciefd_set_data_bittiming;
+		can->can.fd.do_set_data_bittiming = kvaser_pciefd_set_data_bittiming;
 		can->can.do_set_mode = kvaser_pciefd_set_mode;
 		can->can.do_get_berr_counter = kvaser_pciefd_get_berr_counter;
 		can->can.ctrlmode_supported = CAN_CTRLMODE_LISTENONLY |
@@ -1201,7 +1209,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 		skb = alloc_canfd_skb(priv->dev, &cf);
 		if (!skb) {
 			priv->dev->stats.rx_dropped++;
-			return -ENOMEM;
+			return 0;
 		}
 
 		cf->len = can_fd_dlc2len(dlc);
@@ -1213,7 +1221,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 		skb = alloc_can_skb(priv->dev, (struct can_frame **)&cf);
 		if (!skb) {
 			priv->dev->stats.rx_dropped++;
-			return -ENOMEM;
+			return 0;
 		}
 		can_frame_set_cc_len((struct can_frame *)cf, dlc, priv->ctrlmode);
 	}
@@ -1231,7 +1239,9 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 	priv->dev->stats.rx_packets++;
 	kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
 
-	return netif_rx(skb);
+	netif_rx(skb);
+
+	return 0;
 }
 
 static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can,
@@ -1510,19 +1520,21 @@ static int kvaser_pciefd_handle_ack_packet(struct kvaser_pciefd *pcie,
 		netdev_dbg(can->can.dev, "Packet was flushed\n");
 	} else {
 		int echo_idx = FIELD_GET(KVASER_PCIEFD_PACKET_SEQ_MASK, p->header[0]);
-		int len;
-		u8 count;
+		unsigned int len, frame_len = 0;
 		struct sk_buff *skb;
 
+		if (echo_idx != (can->ack_idx & (can->can.echo_skb_max - 1)))
+			return 0;
 		skb = can->can.echo_skb[echo_idx];
-		if (skb)
-			kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
-		len = can_get_echo_skb(can->can.dev, echo_idx, NULL);
-		count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK,
-				  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
+		if (!skb)
+			return 0;
+		kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
+		len = can_get_echo_skb(can->can.dev, echo_idx, &frame_len);
 
-		if (count < can->can.echo_skb_max && netif_queue_stopped(can->can.dev))
-			netif_wake_queue(can->can.dev);
+		/* Pairs with barrier in kvaser_pciefd_start_xmit() */
+		smp_store_release(&can->ack_idx, can->ack_idx + 1);
+		can->completed_tx_pkts++;
+		can->completed_tx_bytes += frame_len;
 
 		if (!one_shot_fail) {
 			can->can.dev->stats.tx_bytes += len;
@@ -1638,32 +1650,51 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf)
 {
 	int pos = 0;
 	int res = 0;
+	unsigned int i;
 
 	do {
 		res = kvaser_pciefd_read_packet(pcie, &pos, dma_buf);
 	} while (!res && pos > 0 && pos < KVASER_PCIEFD_DMA_SIZE);
 
+	/* Report ACKs in this buffer to BQL en masse for correct periods */
+	for (i = 0; i < pcie->nr_channels; ++i) {
+		struct kvaser_pciefd_can *can = pcie->can[i];
+
+		if (!can->completed_tx_pkts)
+			continue;
+		netif_subqueue_completed_wake(can->can.dev, 0,
+					      can->completed_tx_pkts,
+					      can->completed_tx_bytes,
+					      kvaser_pciefd_tx_avail(can), 1);
+		can->completed_tx_pkts = 0;
+		can->completed_tx_bytes = 0;
+	}
+
 	return res;
 }
 
-static u32 kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
+static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
 {
+	void __iomem *srb_cmd_reg = KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG;
 	u32 irq = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
 
-	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
+	iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
+
+	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) {
 		kvaser_pciefd_read_buffer(pcie, 0);
+		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, srb_cmd_reg); /* Rearm buffer */
+	}
 
-	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
+	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) {
 		kvaser_pciefd_read_buffer(pcie, 1);
+		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, srb_cmd_reg); /* Rearm buffer */
+	}
 
 	if (unlikely(irq & KVASER_PCIEFD_SRB_IRQ_DOF0 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DOF1 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DUF0 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DUF1))
 		dev_err(&pcie->pci->dev, "DMA IRQ error 0x%08X\n", irq);
-
-	iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
-	return irq;
 }
 
 static void kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can)
@@ -1691,29 +1722,22 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev)
 	struct kvaser_pciefd *pcie = (struct kvaser_pciefd *)dev;
 	const struct kvaser_pciefd_irq_mask *irq_mask = pcie->driver_data->irq_mask;
 	u32 pci_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie));
-	u32 srb_irq = 0;
-	u32 srb_release = 0;
 	int i;
 
 	if (!(pci_irq & irq_mask->all))
 		return IRQ_NONE;
 
+	iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
+
 	if (pci_irq & irq_mask->kcan_rx0)
-		srb_irq = kvaser_pciefd_receive_irq(pcie);
+		kvaser_pciefd_receive_irq(pcie);
 
 	for (i = 0; i < pcie->nr_channels; i++) {
 		if (pci_irq & irq_mask->kcan_tx[i])
 			kvaser_pciefd_transmit_irq(pcie->can[i]);
 	}
 
-	if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
-		srb_release |= KVASER_PCIEFD_SRB_CMD_RDB0;
-
-	if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
-		srb_release |= KVASER_PCIEFD_SRB_CMD_RDB1;
-
-	if (srb_release)
-		iowrite32(srb_release, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
+	iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
 
 	return IRQ_HANDLED;
 }
@@ -1733,13 +1757,22 @@ static void kvaser_pciefd_teardown_can_ctrls(struct kvaser_pciefd *pcie)
 	}
 }
 
+static void kvaser_pciefd_disable_irq_srcs(struct kvaser_pciefd *pcie)
+{
+	unsigned int i;
+
+	/* Masking PCI_IRQ is insufficient as running ISR will unmask it */
+	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG);
+	for (i = 0; i < pcie->nr_channels; ++i)
+		iowrite32(0, pcie->can[i]->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
+}
+
 static int kvaser_pciefd_probe(struct pci_dev *pdev,
 			       const struct pci_device_id *id)
 {
 	int ret;
 	struct kvaser_pciefd *pcie;
 	const struct kvaser_pciefd_irq_mask *irq_mask;
-	void __iomem *irq_en_base;
 
 	pcie = devm_kzalloc(&pdev->dev, sizeof(*pcie), GFP_KERNEL);
 	if (!pcie)
@@ -1805,8 +1838,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG);
 
 	/* Enable PCI interrupts */
-	irq_en_base = KVASER_PCIEFD_PCI_IEN_ADDR(pcie);
-	iowrite32(irq_mask->all, irq_en_base);
+	iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
 	/* Ready the DMA buffers */
 	iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0,
 		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
@@ -1820,8 +1852,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 	return 0;
 
 err_free_irq:
-	/* Disable PCI interrupts */
-	iowrite32(0, irq_en_base);
+	kvaser_pciefd_disable_irq_srcs(pcie);
 	free_irq(pcie->pci->irq, pcie);
 
 err_pci_free_irq_vectors:
@@ -1844,35 +1875,26 @@ err_disable_pci:
 	return ret;
 }
 
-static void kvaser_pciefd_remove_all_ctrls(struct kvaser_pciefd *pcie)
-{
-	int i;
-
-	for (i = 0; i < pcie->nr_channels; i++) {
-		struct kvaser_pciefd_can *can = pcie->can[i];
-
-		if (can) {
-			iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
-			unregister_candev(can->can.dev);
-			timer_delete(&can->bec_poll_timer);
-			kvaser_pciefd_pwm_stop(can);
-			free_candev(can->can.dev);
-		}
-	}
-}
-
 static void kvaser_pciefd_remove(struct pci_dev *pdev)
 {
 	struct kvaser_pciefd *pcie = pci_get_drvdata(pdev);
+	unsigned int i;
 
-	kvaser_pciefd_remove_all_ctrls(pcie);
+	for (i = 0; i < pcie->nr_channels; ++i) {
+		struct kvaser_pciefd_can *can = pcie->can[i];
 
-	/* Disable interrupts */
-	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG);
-	iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
+		unregister_candev(can->can.dev);
+		timer_delete(&can->bec_poll_timer);
+		kvaser_pciefd_pwm_stop(can);
+	}
 
+	kvaser_pciefd_disable_irq_srcs(pcie);
 	free_irq(pcie->pci->irq, pcie);
 	pci_free_irq_vectors(pcie->pci);
+
+	for (i = 0; i < pcie->nr_channels; ++i)
+		free_candev(pcie->can[i]->can.dev);
+
 	pci_iounmap(pdev, pcie->reg_base);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 884a6352c42b..6c656bfdb323 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1372,7 +1372,7 @@ static int m_can_set_bittiming(struct net_device *dev)
 {
 	struct m_can_classdev *cdev = netdev_priv(dev);
 	const struct can_bittiming *bt = &cdev->can.bittiming;
-	const struct can_bittiming *dbt = &cdev->can.data_bittiming;
+	const struct can_bittiming *dbt = &cdev->can.fd.data_bittiming;
 	u16 brp, sjw, tseg1, tseg2;
 	u32 reg_btp;
 
@@ -1738,7 +1738,7 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
 		if (err)
 			return err;
 		cdev->can.bittiming_const = &m_can_bittiming_const_30X;
-		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_30X;
+		cdev->can.fd.data_bittiming_const = &m_can_data_bittiming_const_30X;
 		break;
 	case 31:
 		/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */
@@ -1746,13 +1746,13 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
 		if (err)
 			return err;
 		cdev->can.bittiming_const = &m_can_bittiming_const_31X;
-		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X;
+		cdev->can.fd.data_bittiming_const = &m_can_data_bittiming_const_31X;
 		break;
 	case 32:
 	case 33:
 		/* Support both MCAN version v3.2.x and v3.3.0 */
 		cdev->can.bittiming_const = &m_can_bittiming_const_31X;
-		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X;
+		cdev->can.fd.data_bittiming_const = &m_can_data_bittiming_const_31X;
 
 		niso = m_can_niso_supported(cdev);
 		if (niso < 0)
@@ -2379,6 +2379,7 @@ struct m_can_classdev *m_can_class_allocate_dev(struct device *dev,
 	SET_NETDEV_DEV(net_dev, dev);
 
 	m_can_of_parse_mram(class_dev, mram_config_vals);
+	spin_lock_init(&class_dev->tx_handling_spinlock);
 out:
 	return class_dev;
 }
@@ -2462,9 +2463,9 @@ EXPORT_SYMBOL_GPL(m_can_class_register);
 
 void m_can_class_unregister(struct m_can_classdev *cdev)
 {
+	unregister_candev(cdev->net);
 	if (cdev->is_peripheral)
 		can_rx_offload_del(&cdev->offload);
-	unregister_candev(cdev->net);
 }
 EXPORT_SYMBOL_GPL(m_can_class_unregister);
 
diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index 28f3fd805273..77292afaed22 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -624,7 +624,7 @@ static int peak_canfd_set_data_bittiming(struct net_device *ndev)
 {
 	struct peak_canfd_priv *priv = netdev_priv(ndev);
 
-	return pucan_set_timing_fast(priv, &priv->can.data_bittiming);
+	return pucan_set_timing_fast(priv, &priv->can.fd.data_bittiming);
 }
 
 static int peak_canfd_close(struct net_device *ndev)
@@ -813,12 +813,12 @@ struct net_device *alloc_peak_canfd_dev(int sizeof_priv, int index,
 	/* complete now socket-can initialization side */
 	priv->can.state = CAN_STATE_STOPPED;
 	priv->can.bittiming_const = &peak_canfd_nominal_const;
-	priv->can.data_bittiming_const = &peak_canfd_data_const;
+	priv->can.fd.data_bittiming_const = &peak_canfd_data_const;
 
 	priv->can.do_set_mode = peak_canfd_set_mode;
 	priv->can.do_get_berr_counter = peak_canfd_get_berr_counter;
 	priv->can.do_set_bittiming = peak_canfd_set_bittiming;
-	priv->can.do_set_data_bittiming = peak_canfd_set_data_bittiming;
+	priv->can.fd.do_set_data_bittiming = peak_canfd_set_data_bittiming;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 				       CAN_CTRLMODE_LISTENONLY |
 				       CAN_CTRLMODE_3_SAMPLES |
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index aa3df0d05b85..7f10213738e5 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -21,6 +21,7 @@
  * wherever it is modified to a readable name.
  */
 
+#include <linux/bitfield.h>
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <linux/can/dev.h>
@@ -74,33 +75,24 @@
 #define RCANFD_GSTS_GNOPM		(BIT(0) | BIT(1) | BIT(2) | BIT(3))
 
 /* RSCFDnCFDGERFL / RSCFDnGERFL */
-#define RCANFD_GERFL_EEF0_7		GENMASK(23, 16)
-#define RCANFD_GERFL_EEF(ch)		BIT(16 + (ch))
+#define RCANFD_GERFL_EEF		GENMASK(23, 16)
 #define RCANFD_GERFL_CMPOF		BIT(3)	/* CAN FD only */
 #define RCANFD_GERFL_THLES		BIT(2)
 #define RCANFD_GERFL_MES		BIT(1)
 #define RCANFD_GERFL_DEF		BIT(0)
 
 #define RCANFD_GERFL_ERR(gpriv, x) \
-	((x) & (reg_gen4(gpriv, RCANFD_GERFL_EEF0_7, \
-			 RCANFD_GERFL_EEF(0) | RCANFD_GERFL_EEF(1)) | \
-		RCANFD_GERFL_MES | \
-		((gpriv)->fdmode ? RCANFD_GERFL_CMPOF : 0)))
+({\
+	typeof(gpriv) (_gpriv) = (gpriv); \
+	((x) & ((FIELD_PREP(RCANFD_GERFL_EEF, (_gpriv)->channels_mask)) | \
+		RCANFD_GERFL_MES | ((_gpriv)->fdmode ? RCANFD_GERFL_CMPOF : 0))); \
+})
 
 /* AFL Rx rules registers */
 
-/* RSCFDnCFDGAFLCFG0 / RSCFDnGAFLCFG0 */
-#define RCANFD_GAFLCFG_SETRNC(gpriv, n, x) \
-	(((x) & reg_gen4(gpriv, 0x1ff, 0xff)) << \
-	 (reg_gen4(gpriv, 16, 24) - ((n) & 1) * reg_gen4(gpriv, 16, 8)))
-
-#define RCANFD_GAFLCFG_GETRNC(gpriv, n, x) \
-	(((x) >> (reg_gen4(gpriv, 16, 24) - ((n) & 1) * reg_gen4(gpriv, 16, 8))) & \
-	 reg_gen4(gpriv, 0x1ff, 0xff))
-
 /* RSCFDnCFDGAFLECTR / RSCFDnGAFLECTR */
 #define RCANFD_GAFLECTR_AFLDAE		BIT(8)
-#define RCANFD_GAFLECTR_AFLPN(gpriv, x)	((x) & reg_gen4(gpriv, 0x7f, 0x1f))
+#define RCANFD_GAFLECTR_AFLPN(gpriv, page_num)	((page_num) & (gpriv)->info->max_aflpn)
 
 /* RSCFDnCFDGAFLIDj / RSCFDnGAFLIDj */
 #define RCANFD_GAFLID_GAFLLB		BIT(29)
@@ -118,13 +110,13 @@
 
 /* RSCFDnCFDCmNCFG - CAN FD only */
 #define RCANFD_NCFG_NTSEG2(gpriv, x) \
-	(((x) & reg_gen4(gpriv, 0x7f, 0x1f)) << reg_gen4(gpriv, 25, 24))
+	(((x) & ((gpriv)->info->nom_bittiming->tseg2_max - 1)) << (gpriv)->info->sh->ntseg2)
 
 #define RCANFD_NCFG_NTSEG1(gpriv, x) \
-	(((x) & reg_gen4(gpriv, 0xff, 0x7f)) << reg_gen4(gpriv, 17, 16))
+	(((x) & ((gpriv)->info->nom_bittiming->tseg1_max - 1)) << (gpriv)->info->sh->ntseg1)
 
 #define RCANFD_NCFG_NSJW(gpriv, x) \
-	(((x) & reg_gen4(gpriv, 0x7f, 0x1f)) << reg_gen4(gpriv, 10, 11))
+	(((x) & ((gpriv)->info->nom_bittiming->sjw_max - 1)) << (gpriv)->info->sh->nsjw)
 
 #define RCANFD_NCFG_NBRP(x)		(((x) & 0x3ff) << 0)
 
@@ -186,13 +178,13 @@
 #define RCANFD_CERFL_ERR(x)		((x) & (0x7fff)) /* above bits 14:0 */
 
 /* RSCFDnCFDCmDCFG */
-#define RCANFD_DCFG_DSJW(gpriv, x)	(((x) & reg_gen4(gpriv, 0xf, 0x7)) << 24)
+#define RCANFD_DCFG_DSJW(gpriv, x)	(((x) & ((gpriv)->info->data_bittiming->sjw_max - 1)) << 24)
 
 #define RCANFD_DCFG_DTSEG2(gpriv, x) \
-	(((x) & reg_gen4(gpriv, 0x0f, 0x7)) << reg_gen4(gpriv, 16, 20))
+	(((x) & ((gpriv)->info->data_bittiming->tseg2_max - 1)) << (gpriv)->info->sh->dtseg2)
 
 #define RCANFD_DCFG_DTSEG1(gpriv, x) \
-	(((x) & reg_gen4(gpriv, 0x1f, 0xf)) << reg_gen4(gpriv, 8, 16))
+	(((x) & ((gpriv)->info->data_bittiming->tseg1_max - 1)) << (gpriv)->info->sh->dtseg1)
 
 #define RCANFD_DCFG_DBRP(x)		(((x) & 0xff) << 0)
 
@@ -233,11 +225,14 @@
 /* Common FIFO bits */
 
 /* RSCFDnCFDCFCCk */
-#define RCANFD_CFCC_CFTML(gpriv, x)	\
-	(((x) & reg_gen4(gpriv, 0x1f, 0xf)) << reg_gen4(gpriv, 16, 20))
-#define RCANFD_CFCC_CFM(gpriv, x)	(((x) & 0x3) << reg_gen4(gpriv,  8, 16))
+#define RCANFD_CFCC_CFTML(gpriv, cftml) \
+({\
+	typeof(gpriv) (_gpriv) = (gpriv); \
+	(((cftml) & (_gpriv)->info->max_cftml) << (_gpriv)->info->sh->cftml); \
+})
+#define RCANFD_CFCC_CFM(gpriv, x)	(((x) & 0x3) << (gpriv)->info->sh->cfm)
 #define RCANFD_CFCC_CFIM		BIT(12)
-#define RCANFD_CFCC_CFDC(gpriv, x)	(((x) & 0x7) << reg_gen4(gpriv, 21,  8))
+#define RCANFD_CFCC_CFDC(gpriv, x)	(((x) & 0x7) << (gpriv)->info->sh->cfdc)
 #define RCANFD_CFCC_CFPLS(x)		(((x) & 0x7) << 4)
 #define RCANFD_CFCC_CFTXIE		BIT(2)
 #define RCANFD_CFCC_CFE			BIT(0)
@@ -298,14 +293,14 @@
 /* RSCFDnCFDGAFLECTR / RSCFDnGAFLECTR */
 #define RCANFD_GAFLECTR			(0x0098)
 /* RSCFDnCFDGAFLCFG / RSCFDnGAFLCFG */
-#define RCANFD_GAFLCFG(ch)		(0x009c + (0x04 * ((ch) / 2)))
+#define RCANFD_GAFLCFG(w)		(0x009c + (0x04 * (w)))
 /* RSCFDnCFDRMNB / RSCFDnRMNB */
 #define RCANFD_RMNB			(0x00a4)
 /* RSCFDnCFDRMND / RSCFDnRMND */
 #define RCANFD_RMND(y)			(0x00a8 + (0x04 * (y)))
 
 /* RSCFDnCFDRFCCx / RSCFDnRFCCx */
-#define RCANFD_RFCC(gpriv, x)		(reg_gen4(gpriv, 0x00c0, 0x00b8) + (0x04 * (x)))
+#define RCANFD_RFCC(gpriv, x)		((gpriv)->info->regs->rfcc + (0x04 * (x)))
 /* RSCFDnCFDRFSTSx / RSCFDnRFSTSx */
 #define RCANFD_RFSTS(gpriv, x)		(RCANFD_RFCC(gpriv, x) + 0x20)
 /* RSCFDnCFDRFPCTRx / RSCFDnRFPCTRx */
@@ -315,13 +310,13 @@
 
 /* RSCFDnCFDCFCCx / RSCFDnCFCCx */
 #define RCANFD_CFCC(gpriv, ch, idx) \
-	(reg_gen4(gpriv, 0x0120, 0x0118) + (0x0c * (ch)) + (0x04 * (idx)))
+	((gpriv)->info->regs->cfcc + (0x0c * (ch)) + (0x04 * (idx)))
 /* RSCFDnCFDCFSTSx / RSCFDnCFSTSx */
 #define RCANFD_CFSTS(gpriv, ch, idx) \
-	(reg_gen4(gpriv, 0x01e0, 0x0178) + (0x0c * (ch)) + (0x04 * (idx)))
+	((gpriv)->info->regs->cfsts + (0x0c * (ch)) + (0x04 * (idx)))
 /* RSCFDnCFDCFPCTRx / RSCFDnCFPCTRx */
 #define RCANFD_CFPCTR(gpriv, ch, idx) \
-	(reg_gen4(gpriv, 0x0240, 0x01d8) + (0x0c * (ch)) + (0x04 * (idx)))
+	((gpriv)->info->regs->cfpctr + (0x0c * (ch)) + (0x04 * (idx)))
 
 /* RSCFDnCFDFESTS / RSCFDnFESTS */
 #define RCANFD_FESTS			(0x0238)
@@ -437,7 +432,7 @@
 /* CAN FD mode specific register map */
 
 /* RSCFDnCFDCmXXX -> RCANFD_F_XXX(m) */
-#define RCANFD_F_DCFG(gpriv, m)		(reg_gen4(gpriv, 0x1400, 0x0500) + (0x20 * (m)))
+#define RCANFD_F_DCFG(gpriv, m)		((gpriv)->info->regs->f_dcfg + (0x20 * (m)))
 #define RCANFD_F_CFDCFG(m)		(0x0504 + (0x20 * (m)))
 #define RCANFD_F_CFDCTR(m)		(0x0508 + (0x20 * (m)))
 #define RCANFD_F_CFDSTS(m)		(0x050c + (0x20 * (m)))
@@ -453,7 +448,7 @@
 #define RCANFD_F_RMDF(q, b)		(0x200c + (0x04 * (b)) + (0x20 * (q)))
 
 /* RSCFDnCFDRFXXx -> RCANFD_F_RFXX(x) */
-#define RCANFD_F_RFOFFSET(gpriv)	reg_gen4(gpriv, 0x6000, 0x3000)
+#define RCANFD_F_RFOFFSET(gpriv)	((gpriv)->info->regs->rfoffset)
 #define RCANFD_F_RFID(gpriv, x)		(RCANFD_F_RFOFFSET(gpriv) + (0x80 * (x)))
 #define RCANFD_F_RFPTR(gpriv, x)	(RCANFD_F_RFOFFSET(gpriv) + 0x04 + (0x80 * (x)))
 #define RCANFD_F_RFFDSTS(gpriv, x)	(RCANFD_F_RFOFFSET(gpriv) + 0x08 + (0x80 * (x)))
@@ -461,7 +456,7 @@
 	(RCANFD_F_RFOFFSET(gpriv) + 0x0c + (0x80 * (x)) + (0x04 * (df)))
 
 /* RSCFDnCFDCFXXk -> RCANFD_F_CFXX(ch, k) */
-#define RCANFD_F_CFOFFSET(gpriv)	reg_gen4(gpriv, 0x6400, 0x3400)
+#define RCANFD_F_CFOFFSET(gpriv)	((gpriv)->info->regs->cfoffset)
 
 #define RCANFD_F_CFID(gpriv, ch, idx) \
 	(RCANFD_F_CFOFFSET(gpriv) + (0x180 * (ch)) + (0x80 * (idx)))
@@ -510,12 +505,43 @@
 
 struct rcar_canfd_global;
 
+struct rcar_canfd_regs {
+	u16 rfcc;	/* RX FIFO Configuration/Control Register */
+	u16 cfcc;	/* Common FIFO Configuration/Control Register */
+	u16 cfsts;	/* Common FIFO Status Register */
+	u16 cfpctr;	/* Common FIFO Pointer Control Register */
+	u16 f_dcfg;	/* Global FD Configuration Register */
+	u16 rfoffset;	/* Receive FIFO buffer access ID register */
+	u16 cfoffset;	/* Transmit/receive FIFO buffer access ID register */
+};
+
+struct rcar_canfd_shift_data {
+	u8 ntseg2;	/* Nominal Bit Rate Time Segment 2 Control */
+	u8 ntseg1;	/* Nominal Bit Rate Time Segment 1 Control */
+	u8 nsjw;	/* Nominal Bit Rate Resynchronization Jump Width Control */
+	u8 dtseg2;	/* Data Bit Rate Time Segment 2 Control */
+	u8 dtseg1;	/* Data Bit Rate Time Segment 1 Control */
+	u8 cftml;	/* Common FIFO TX Message Buffer Link */
+	u8 cfm;		/* Common FIFO Mode */
+	u8 cfdc;	/* Common FIFO Depth Configuration */
+};
+
 struct rcar_canfd_hw_info {
+	const struct can_bittiming_const *nom_bittiming;
+	const struct can_bittiming_const *data_bittiming;
+	const struct rcar_canfd_regs *regs;
+	const struct rcar_canfd_shift_data *sh;
+	u8 rnc_field_width;
+	u8 max_aflpn;
+	u8 max_cftml;
 	u8 max_channels;
 	u8 postdiv;
 	/* hardware features */
 	unsigned shared_global_irqs:1;	/* Has shared global irqs */
 	unsigned multi_channel_irqs:1;	/* Has multiple channel irqs */
+	unsigned ch_interface_mode:1;	/* Has channel interface mode */
+	unsigned shared_can_regs:1;	/* Has shared classical can registers */
+	unsigned external_clk:1;	/* Has external clock */
 };
 
 /* Channel priv data */
@@ -548,7 +574,7 @@ struct rcar_canfd_global {
 };
 
 /* CAN FD mode nominal rate constants */
-static const struct can_bittiming_const rcar_canfd_nom_bittiming_const = {
+static const struct can_bittiming_const rcar_canfd_gen3_nom_bittiming_const = {
 	.name = RCANFD_DRV_NAME,
 	.tseg1_min = 2,
 	.tseg1_max = 128,
@@ -560,8 +586,20 @@ static const struct can_bittiming_const rcar_canfd_nom_bittiming_const = {
 	.brp_inc = 1,
 };
 
+static const struct can_bittiming_const rcar_canfd_gen4_nom_bittiming_const = {
+	.name = RCANFD_DRV_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 256,
+	.tseg2_min = 2,
+	.tseg2_max = 128,
+	.sjw_max = 128,
+	.brp_min = 1,
+	.brp_max = 1024,
+	.brp_inc = 1,
+};
+
 /* CAN FD mode data rate constants */
-static const struct can_bittiming_const rcar_canfd_data_bittiming_const = {
+static const struct can_bittiming_const rcar_canfd_gen3_data_bittiming_const = {
 	.name = RCANFD_DRV_NAME,
 	.tseg1_min = 2,
 	.tseg1_max = 16,
@@ -573,6 +611,18 @@ static const struct can_bittiming_const rcar_canfd_data_bittiming_const = {
 	.brp_inc = 1,
 };
 
+static const struct can_bittiming_const rcar_canfd_gen4_data_bittiming_const = {
+	.name = RCANFD_DRV_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 32,
+	.tseg2_min = 2,
+	.tseg2_max = 16,
+	.sjw_max = 16,
+	.brp_min = 1,
+	.brp_max = 256,
+	.brp_inc = 1,
+};
+
 /* Classical CAN mode bitrate constants */
 static const struct can_bittiming_const rcar_canfd_bittiming_const = {
 	.name = RCANFD_DRV_NAME,
@@ -586,36 +636,113 @@ static const struct can_bittiming_const rcar_canfd_bittiming_const = {
 	.brp_inc = 1,
 };
 
+static const struct rcar_canfd_regs rcar_gen3_regs = {
+	.rfcc = 0x00b8,
+	.cfcc = 0x0118,
+	.cfsts = 0x0178,
+	.cfpctr = 0x01d8,
+	.f_dcfg = 0x0500,
+	.rfoffset = 0x3000,
+	.cfoffset = 0x3400,
+};
+
+static const struct rcar_canfd_regs rcar_gen4_regs = {
+	.rfcc = 0x00c0,
+	.cfcc = 0x0120,
+	.cfsts = 0x01e0,
+	.cfpctr = 0x0240,
+	.f_dcfg = 0x1400,
+	.rfoffset = 0x6000,
+	.cfoffset = 0x6400,
+};
+
+static const struct rcar_canfd_shift_data rcar_gen3_shift_data = {
+	.ntseg2 = 24,
+	.ntseg1 = 16,
+	.nsjw = 11,
+	.dtseg2 = 20,
+	.dtseg1 = 16,
+	.cftml = 20,
+	.cfm = 16,
+	.cfdc = 8,
+};
+
+static const struct rcar_canfd_shift_data rcar_gen4_shift_data = {
+	.ntseg2 = 25,
+	.ntseg1 = 17,
+	.nsjw = 10,
+	.dtseg2 = 16,
+	.dtseg1 = 8,
+	.cftml = 16,
+	.cfm = 8,
+	.cfdc = 21,
+};
+
 static const struct rcar_canfd_hw_info rcar_gen3_hw_info = {
+	.nom_bittiming = &rcar_canfd_gen3_nom_bittiming_const,
+	.data_bittiming = &rcar_canfd_gen3_data_bittiming_const,
+	.regs = &rcar_gen3_regs,
+	.sh = &rcar_gen3_shift_data,
+	.rnc_field_width = 8,
+	.max_aflpn = 31,
+	.max_cftml = 15,
 	.max_channels = 2,
 	.postdiv = 2,
 	.shared_global_irqs = 1,
+	.ch_interface_mode = 0,
+	.shared_can_regs = 0,
+	.external_clk = 1,
 };
 
 static const struct rcar_canfd_hw_info rcar_gen4_hw_info = {
+	.nom_bittiming = &rcar_canfd_gen4_nom_bittiming_const,
+	.data_bittiming = &rcar_canfd_gen4_data_bittiming_const,
+	.regs = &rcar_gen4_regs,
+	.sh = &rcar_gen4_shift_data,
+	.rnc_field_width = 16,
+	.max_aflpn = 127,
+	.max_cftml = 31,
 	.max_channels = 8,
 	.postdiv = 2,
 	.shared_global_irqs = 1,
+	.ch_interface_mode = 1,
+	.shared_can_regs = 1,
+	.external_clk = 1,
 };
 
 static const struct rcar_canfd_hw_info rzg2l_hw_info = {
+	.nom_bittiming = &rcar_canfd_gen3_nom_bittiming_const,
+	.data_bittiming = &rcar_canfd_gen3_data_bittiming_const,
+	.regs = &rcar_gen3_regs,
+	.sh = &rcar_gen3_shift_data,
+	.rnc_field_width = 8,
+	.max_aflpn = 31,
+	.max_cftml = 15,
 	.max_channels = 2,
 	.postdiv = 1,
 	.multi_channel_irqs = 1,
+	.ch_interface_mode = 0,
+	.shared_can_regs = 0,
+	.external_clk = 1,
 };
 
-/* Helper functions */
-static inline bool is_gen4(struct rcar_canfd_global *gpriv)
-{
-	return gpriv->info == &rcar_gen4_hw_info;
-}
-
-static inline u32 reg_gen4(struct rcar_canfd_global *gpriv,
-			   u32 gen4, u32 not_gen4)
-{
-	return is_gen4(gpriv) ? gen4 : not_gen4;
-}
+static const struct rcar_canfd_hw_info r9a09g047_hw_info = {
+	.nom_bittiming = &rcar_canfd_gen4_nom_bittiming_const,
+	.data_bittiming = &rcar_canfd_gen4_data_bittiming_const,
+	.regs = &rcar_gen4_regs,
+	.sh = &rcar_gen4_shift_data,
+	.rnc_field_width = 16,
+	.max_aflpn = 63,
+	.max_cftml = 31,
+	.max_channels = 6,
+	.postdiv = 1,
+	.multi_channel_irqs = 1,
+	.ch_interface_mode = 1,
+	.shared_can_regs = 1,
+	.external_clk = 0,
+};
 
+/* Helper functions */
 static inline void rcar_canfd_update(u32 mask, u32 val, u32 __iomem *reg)
 {
 	u32 data = readl(reg);
@@ -681,9 +808,20 @@ static void rcar_canfd_tx_failure_cleanup(struct net_device *ndev)
 		can_free_echo_skb(ndev, i, NULL);
 }
 
+static void rcar_canfd_setrnc(struct rcar_canfd_global *gpriv, unsigned int ch,
+			      unsigned int num_rules)
+{
+	unsigned int rnc_stride = 32 / gpriv->info->rnc_field_width;
+	unsigned int shift = 32 - (ch % rnc_stride + 1) * gpriv->info->rnc_field_width;
+	unsigned int w = ch / rnc_stride;
+	u32 rnc = num_rules << shift;
+
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLCFG(w), rnc);
+}
+
 static void rcar_canfd_set_mode(struct rcar_canfd_global *gpriv)
 {
-	if (is_gen4(gpriv)) {
+	if (gpriv->info->ch_interface_mode) {
 		u32 ch, val = gpriv->fdmode ? RCANFD_GEN4_FDCFG_FDOE
 					    : RCANFD_GEN4_FDCFG_CLOE;
 
@@ -789,7 +927,7 @@ static void rcar_canfd_configure_controller(struct rcar_canfd_global *gpriv)
 static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv,
 					   u32 ch, u32 rule_entry)
 {
-	int offset, page, num_rules = RCANFD_CHANNEL_NUMRULES;
+	unsigned int offset, page, num_rules = RCANFD_CHANNEL_NUMRULES;
 	u32 rule_entry_index = rule_entry % 16;
 	u32 ridx = ch + RCANFD_RFFIFO_IDX;
 
@@ -800,9 +938,8 @@ static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv,
 			    RCANFD_GAFLECTR_AFLDAE));
 
 	/* Write number of rules for channel */
-	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLCFG(ch),
-			   RCANFD_GAFLCFG_SETRNC(gpriv, ch, num_rules));
-	if (is_gen4(gpriv))
+	rcar_canfd_setrnc(gpriv, ch, num_rules);
+	if (gpriv->info->shared_can_regs)
 		offset = RCANFD_GEN4_GAFL_OFFSET;
 	else if (gpriv->fdmode)
 		offset = RCANFD_F_GAFL_OFFSET;
@@ -942,7 +1079,7 @@ static void rcar_canfd_global_error(struct net_device *ndev)
 	u32 ridx = ch + RCANFD_RFFIFO_IDX;
 
 	gerfl = rcar_canfd_read(priv->base, RCANFD_GERFL);
-	if (gerfl & RCANFD_GERFL_EEF(ch)) {
+	if (gerfl & FIELD_PREP(RCANFD_GERFL_EEF, BIT(ch))) {
 		netdev_dbg(ndev, "Ch%u: ECC Error flag\n", ch);
 		stats->tx_dropped++;
 	}
@@ -1304,7 +1441,7 @@ static void rcar_canfd_set_bittiming(struct net_device *dev)
 	struct rcar_canfd_channel *priv = netdev_priv(dev);
 	struct rcar_canfd_global *gpriv = priv->gpriv;
 	const struct can_bittiming *bt = &priv->can.bittiming;
-	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	const struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	u16 brp, sjw, tseg1, tseg2;
 	u32 cfg;
 	u32 ch = priv->channel;
@@ -1338,7 +1475,7 @@ static void rcar_canfd_set_bittiming(struct net_device *dev)
 			   brp, sjw, tseg1, tseg2);
 	} else {
 		/* Classical CAN only mode */
-		if (is_gen4(gpriv)) {
+		if (gpriv->info->shared_can_regs) {
 			cfg = (RCANFD_NCFG_NTSEG1(gpriv, tseg1) |
 			       RCANFD_NCFG_NBRP(brp) |
 			       RCANFD_NCFG_NSJW(gpriv, sjw) |
@@ -1503,7 +1640,7 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb,
 
 	dlc = RCANFD_CFPTR_CFDLC(can_fd_len2dlc(cf->len));
 
-	if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_gen4(gpriv)) {
+	if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || gpriv->info->shared_can_regs) {
 		rcar_canfd_write(priv->base,
 				 RCANFD_F_CFID(gpriv, ch, RCANFD_CFFIFO_IDX), id);
 		rcar_canfd_write(priv->base,
@@ -1562,7 +1699,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
 	u32 ch = priv->channel;
 	u32 ridx = ch + RCANFD_RFFIFO_IDX;
 
-	if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_gen4(gpriv)) {
+	if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || gpriv->info->shared_can_regs) {
 		id = rcar_canfd_read(priv->base, RCANFD_F_RFID(gpriv, ridx));
 		dlc = rcar_canfd_read(priv->base, RCANFD_F_RFPTR(gpriv, ridx));
 
@@ -1613,7 +1750,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
 		cf->len = can_cc_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
 		if (id & RCANFD_RFID_RFRTR)
 			cf->can_id |= CAN_RTR_FLAG;
-		else if (is_gen4(gpriv))
+		else if (gpriv->info->shared_can_regs)
 			rcar_canfd_get_data(priv, cf, RCANFD_F_RFDF(gpriv, ridx, 0));
 		else
 			rcar_canfd_get_data(priv, cf, RCANFD_C_RFDF(ridx, 0));
@@ -1736,16 +1873,19 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
 
 	if (info->multi_channel_irqs) {
 		char *irq_name;
+		char name[10];
 		int err_irq;
 		int tx_irq;
 
-		err_irq = platform_get_irq_byname(pdev, ch == 0 ? "ch0_err" : "ch1_err");
+		scnprintf(name, sizeof(name), "ch%u_err", ch);
+		err_irq = platform_get_irq_byname(pdev, name);
 		if (err_irq < 0) {
 			err = err_irq;
 			goto fail;
 		}
 
-		tx_irq = platform_get_irq_byname(pdev, ch == 0 ? "ch0_trx" : "ch1_trx");
+		scnprintf(name, sizeof(name), "ch%u_trx", ch);
+		tx_irq = platform_get_irq_byname(pdev, name);
 		if (tx_irq < 0) {
 			err = tx_irq;
 			goto fail;
@@ -1782,9 +1922,8 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
 	}
 
 	if (gpriv->fdmode) {
-		priv->can.bittiming_const = &rcar_canfd_nom_bittiming_const;
-		priv->can.data_bittiming_const =
-			&rcar_canfd_data_bittiming_const;
+		priv->can.bittiming_const = gpriv->info->nom_bittiming;
+		priv->can.fd.data_bittiming_const = gpriv->info->data_bittiming;
 
 		/* Controller starts in CAN FD only mode */
 		err = can_set_static_ctrlmode(ndev, CAN_CTRLMODE_FD);
@@ -1846,6 +1985,7 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 	u32 rule_entry = 0;
 	bool fdmode = true;			/* CAN FD only mode - default */
 	char name[9] = "channelX";
+	struct clk *clk_ram;
 	int i;
 
 	info = of_device_get_match_data(dev);
@@ -1855,13 +1995,13 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 
 	for (i = 0; i < info->max_channels; ++i) {
 		name[7] = '0' + i;
-		of_child = of_get_child_by_name(dev->of_node, name);
-		if (of_child && of_device_is_available(of_child)) {
+		of_child = of_get_available_child_by_name(dev->of_node, name);
+		if (of_child) {
 			channels_mask |= BIT(i);
 			transceivers[i] = devm_of_phy_optional_get(dev,
 							of_child, NULL);
+			of_node_put(of_child);
 		}
-		of_node_put(of_child);
 		if (IS_ERR(transceivers[i]))
 			return PTR_ERR(transceivers[i]);
 	}
@@ -1932,9 +2072,14 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 		fcan_freq = clk_get_rate(gpriv->can_clk) / info->postdiv;
 	} else {
 		fcan_freq = clk_get_rate(gpriv->can_clk);
-		gpriv->extclk = true;
+		gpriv->extclk = gpriv->info->external_clk;
 	}
 
+	clk_ram = devm_clk_get_optional_enabled(dev, "ram_clk");
+	if (IS_ERR(clk_ram))
+		return dev_err_probe(dev, PTR_ERR(clk_ram),
+				     "cannot get enabled ram clock\n");
+
 	addr = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(addr)) {
 		err = PTR_ERR(addr);
@@ -2097,6 +2242,7 @@ static SIMPLE_DEV_PM_OPS(rcar_canfd_pm_ops, rcar_canfd_suspend,
 
 static const __maybe_unused struct of_device_id rcar_canfd_of_table[] = {
 	{ .compatible = "renesas,r8a779a0-canfd", .data = &rcar_gen4_hw_info },
+	{ .compatible = "renesas,r9a09g047-canfd", .data = &r9a09g047_hw_info },
 	{ .compatible = "renesas,rcar-gen3-canfd", .data = &rcar_gen3_hw_info },
 	{ .compatible = "renesas,rcar-gen4-canfd", .data = &rcar_gen4_hw_info },
 	{ .compatible = "renesas,rzg2l-canfd", .data = &rzg2l_hw_info },
diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 46201c126703..046f0a0ae4d4 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -118,7 +118,7 @@ static void rkcanfd_chip_set_work_mode(const struct rkcanfd_priv *priv)
 
 static int rkcanfd_set_bittiming(struct rkcanfd_priv *priv)
 {
-	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	const struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	const struct can_bittiming *bt = &priv->can.bittiming;
 	u32 reg_nbt, reg_dbt, reg_tdc;
 	u32 tdco;
@@ -899,18 +899,19 @@ static int rkcanfd_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, priv);
 	priv->can.clock.freq = clk_get_rate(priv->clks[0].clk);
 	priv->can.bittiming_const = &rkcanfd_bittiming_const;
-	priv->can.data_bittiming_const = &rkcanfd_data_bittiming_const;
+	priv->can.fd.data_bittiming_const = &rkcanfd_data_bittiming_const;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 		CAN_CTRLMODE_BERR_REPORTING;
-	if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_CANFD_BROKEN))
-		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
 	priv->can.do_set_mode = rkcanfd_set_mode;
 	priv->can.do_get_berr_counter = rkcanfd_get_berr_counter;
 	priv->ndev = ndev;
 
 	match = device_get_match_data(&pdev->dev);
-	if (match)
+	if (match) {
 		priv->devtype_data = *(struct rkcanfd_devtype_data *)match;
+		if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_CANFD_BROKEN))
+			priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
+	}
 
 	err = can_rx_offload_add_manual(ndev, &priv->offload,
 					RKCANFD_NAPI_WEIGHT);
@@ -936,8 +937,8 @@ static void rkcanfd_remove(struct platform_device *pdev)
 	struct rkcanfd_priv *priv = platform_get_drvdata(pdev);
 	struct net_device *ndev = priv->ndev;
 
-	can_rx_offload_del(&priv->offload);
 	rkcanfd_unregister(priv);
+	can_rx_offload_del(&priv->offload);
 	free_candev(ndev);
 }
 
diff --git a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
index 43d4b5721812..fa85a75be65a 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
@@ -39,7 +39,7 @@ static void rkcanfd_timestamp_work(struct work_struct *work)
 
 void rkcanfd_timestamp_init(struct rkcanfd_priv *priv)
 {
-	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	const struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	const struct can_bittiming *bt = &priv->can.bittiming;
 	struct cyclecounter *cc = &priv->cc;
 	u32 bitrate, div, reg, rate;
diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c
index 24c6622d36bd..58ff2ec1d975 100644
--- a/drivers/net/can/slcan/slcan-core.c
+++ b/drivers/net/can/slcan/slcan-core.c
@@ -71,12 +71,21 @@ MODULE_AUTHOR("Dario Binacchi <dario.binacchi@amarulasolutions.com>");
 #define SLCAN_CMD_LEN 1
 #define SLCAN_SFF_ID_LEN 3
 #define SLCAN_EFF_ID_LEN 8
+#define SLCAN_DATA_LENGTH_LEN 1
+#define SLCAN_ERROR_LEN 1
 #define SLCAN_STATE_LEN 1
 #define SLCAN_STATE_BE_RXCNT_LEN 3
 #define SLCAN_STATE_BE_TXCNT_LEN 3
-#define SLCAN_STATE_FRAME_LEN       (1 + SLCAN_CMD_LEN + \
-				     SLCAN_STATE_BE_RXCNT_LEN + \
-				     SLCAN_STATE_BE_TXCNT_LEN)
+#define SLCAN_STATE_MSG_LEN     (SLCAN_CMD_LEN +		\
+                                 SLCAN_STATE_LEN +		\
+                                 SLCAN_STATE_BE_RXCNT_LEN +	\
+                                 SLCAN_STATE_BE_TXCNT_LEN)
+#define SLCAN_ERROR_MSG_LEN_MIN (SLCAN_CMD_LEN +	\
+                                 SLCAN_ERROR_LEN +	\
+                                 SLCAN_DATA_LENGTH_LEN)
+#define SLCAN_FRAME_MSG_LEN_MIN (SLCAN_CMD_LEN +	\
+                                 SLCAN_SFF_ID_LEN +	\
+                                 SLCAN_DATA_LENGTH_LEN)
 struct slcan {
 	struct can_priv         can;
 
@@ -176,6 +185,9 @@ static void slcan_bump_frame(struct slcan *sl)
 	u32 tmpid;
 	char *cmd = sl->rbuff;
 
+	if (sl->rcount < SLCAN_FRAME_MSG_LEN_MIN)
+		return;
+
 	skb = alloc_can_skb(sl->dev, &cf);
 	if (unlikely(!skb)) {
 		sl->dev->stats.rx_dropped++;
@@ -281,7 +293,7 @@ static void slcan_bump_state(struct slcan *sl)
 		return;
 	}
 
-	if (state == sl->can.state || sl->rcount < SLCAN_STATE_FRAME_LEN)
+	if (state == sl->can.state || sl->rcount != SLCAN_STATE_MSG_LEN)
 		return;
 
 	cmd += SLCAN_STATE_BE_RXCNT_LEN + SLCAN_CMD_LEN + 1;
@@ -328,6 +340,9 @@ static void slcan_bump_err(struct slcan *sl)
 	bool rx_errors = false, tx_errors = false, rx_over_errors = false;
 	int i, len;
 
+	if (sl->rcount < SLCAN_ERROR_MSG_LEN_MIN)
+		return;
+
 	/* get len from sanitized ASCII value */
 	len = cmd[1];
 	if (len >= '0' && len < '9')
@@ -456,8 +471,7 @@ static void slcan_bump(struct slcan *sl)
 static void slcan_unesc(struct slcan *sl, unsigned char s)
 {
 	if ((s == '\r') || (s == '\a')) { /* CR or BEL ends the pdu */
-		if (!test_and_clear_bit(SLF_ERROR, &sl->flags) &&
-		    sl->rcount > 4)
+		if (!test_and_clear_bit(SLF_ERROR, &sl->flags))
 			slcan_bump(sl);
 
 		sl->rcount = 0;
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 3bc56517fe7a..7450ea42c1ea 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -75,6 +75,24 @@ static const struct can_bittiming_const mcp251xfd_data_bittiming_const = {
 	.brp_inc = 1,
 };
 
+/* The datasheet of the mcp2518fd (DS20006027B) specifies a range of
+ * [-64,63] for TDCO, indicating a relative TDCO.
+ *
+ * Manual tests have shown, that using a relative TDCO configuration
+ * results in bus off, while an absolute configuration works.
+ *
+ * For TDCO use the max value (63) from the data sheet, but 0 as the
+ * minimum.
+ */
+static const struct can_tdc_const mcp251xfd_tdc_const = {
+	.tdcv_min = 0,
+	.tdcv_max = 63,
+	.tdco_min = 0,
+	.tdco_max = 63,
+	.tdcf_min = 0,
+	.tdcf_max = 0,
+};
+
 static const char *__mcp251xfd_get_model_str(enum mcp251xfd_model model)
 {
 	switch (model) {
@@ -509,9 +527,8 @@ static int mcp251xfd_chip_timestamp_init(const struct mcp251xfd_priv *priv)
 static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv)
 {
 	const struct can_bittiming *bt = &priv->can.bittiming;
-	const struct can_bittiming *dbt = &priv->can.data_bittiming;
-	u32 val = 0;
-	s8 tdco;
+	const struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
+	u32 tdcmod, val = 0;
 	int err;
 
 	/* CAN Control Register
@@ -575,11 +592,16 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv)
 		return err;
 
 	/* Transmitter Delay Compensation */
-	tdco = clamp_t(int, dbt->brp * (dbt->prop_seg + dbt->phase_seg1),
-		       -64, 63);
-	val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK,
-			 MCP251XFD_REG_TDC_TDCMOD_AUTO) |
-		FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, tdco);
+	if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_AUTO)
+		tdcmod = MCP251XFD_REG_TDC_TDCMOD_AUTO;
+	else if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_MANUAL)
+		tdcmod = MCP251XFD_REG_TDC_TDCMOD_MANUAL;
+	else
+		tdcmod = MCP251XFD_REG_TDC_TDCMOD_DISABLED;
+
+	val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK, tdcmod) |
+	      FIELD_PREP(MCP251XFD_REG_TDC_TDCV_MASK, priv->can.fd.tdc.tdcv) |
+	      FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, priv->can.fd.tdc.tdco);
 
 	return regmap_write(priv->map_reg, MCP251XFD_REG_TDC, val);
 }
@@ -2082,11 +2104,13 @@ static int mcp251xfd_probe(struct spi_device *spi)
 	priv->can.do_set_mode = mcp251xfd_set_mode;
 	priv->can.do_get_berr_counter = mcp251xfd_get_berr_counter;
 	priv->can.bittiming_const = &mcp251xfd_bittiming_const;
-	priv->can.data_bittiming_const = &mcp251xfd_data_bittiming_const;
+	priv->can.fd.data_bittiming_const = &mcp251xfd_data_bittiming_const;
+	priv->can.fd.tdc_const = &mcp251xfd_tdc_const;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 		CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING |
 		CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO |
-		CAN_CTRLMODE_CC_LEN8_DLC;
+		CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO |
+		CAN_CTRLMODE_TDC_MANUAL;
 	set_bit(MCP251XFD_FLAGS_DOWN, priv->flags);
 	priv->ndev = ndev;
 	priv->spi = spi;
@@ -2174,8 +2198,8 @@ static void mcp251xfd_remove(struct spi_device *spi)
 	struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
 	struct net_device *ndev = priv->ndev;
 
-	can_rx_offload_del(&priv->offload);
 	mcp251xfd_unregister(priv);
+	can_rx_offload_del(&priv->offload);
 	spi->max_speed_hz = priv->spi_max_speed_hz_orig;
 	free_candev(ndev);
 }
diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c
index 03ad10b01867..27a3818885c2 100644
--- a/drivers/net/can/usb/esd_usb.c
+++ b/drivers/net/can/usb/esd_usb.c
@@ -1098,7 +1098,7 @@ static int esd_usb_3_set_bittiming(struct net_device *netdev)
 	const struct can_bittiming_const *data_btc = &esd_usb_3_data_bittiming_const;
 	struct esd_usb_net_priv *priv = netdev_priv(netdev);
 	struct can_bittiming *nom_bt = &priv->can.bittiming;
-	struct can_bittiming *data_bt = &priv->can.data_bittiming;
+	struct can_bittiming *data_bt = &priv->can.fd.data_bittiming;
 	struct esd_usb_3_set_baudrate_msg_x *baud_x;
 	union esd_usb_msg *msg;
 	u16 flags = 0;
@@ -1218,9 +1218,9 @@ static int esd_usb_probe_one_net(struct usb_interface *intf, int index)
 		priv->can.clock.freq = ESD_USB_3_CAN_CLOCK;
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
 		priv->can.bittiming_const = &esd_usb_3_nom_bittiming_const;
-		priv->can.data_bittiming_const = &esd_usb_3_data_bittiming_const;
+		priv->can.fd.data_bittiming_const = &esd_usb_3_data_bittiming_const;
 		priv->can.do_set_bittiming = esd_usb_3_set_bittiming;
-		priv->can.do_set_data_bittiming = esd_usb_3_set_bittiming;
+		priv->can.fd.do_set_data_bittiming = esd_usb_3_set_bittiming;
 		break;
 
 	case ESD_USB_CANUSBM_PRODUCT_ID:
diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c
index 71f24dc0a927..db1acf6d504c 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_core.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_core.c
@@ -2059,8 +2059,8 @@ static int es58x_init_priv(struct es58x_device *es58x_dev,
 
 	can->bittiming_const = param->bittiming_const;
 	if (param->ctrlmode_supported & CAN_CTRLMODE_FD) {
-		can->data_bittiming_const = param->data_bittiming_const;
-		can->tdc_const = param->tdc_const;
+		can->fd.data_bittiming_const = param->data_bittiming_const;
+		can->fd.tdc_const = param->tdc_const;
 	}
 	can->bitrate_max = param->bitrate_max;
 	can->clock = param->clock;
diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c
index 84ffa1839bac..d924b053677b 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_fd.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c
@@ -427,12 +427,12 @@ static int es58x_fd_enable_channel(struct es58x_priv *priv)
 
 	if (tx_conf_msg.canfd_enabled) {
 		es58x_fd_convert_bittiming(&tx_conf_msg.data_bittiming,
-					   &priv->can.data_bittiming);
+					   &priv->can.fd.data_bittiming);
 
 		if (can_tdc_is_enabled(&priv->can)) {
 			tx_conf_msg.tdc_enabled = 1;
-			tx_conf_msg.tdco = cpu_to_le16(priv->can.tdc.tdco);
-			tx_conf_msg.tdcf = cpu_to_le16(priv->can.tdc.tdcf);
+			tx_conf_msg.tdco = cpu_to_le16(priv->can.fd.tdc.tdco);
+			tx_conf_msg.tdcf = cpu_to_le16(priv->can.fd.tdc.tdcf);
 		}
 
 		conf_len = ES58X_FD_CANFD_CONF_LEN;
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 3ccac6781b98..bb6335278e46 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -728,7 +728,7 @@ static int gs_usb_set_bittiming(struct net_device *netdev)
 static int gs_usb_set_data_bittiming(struct net_device *netdev)
 {
 	struct gs_can *dev = netdev_priv(netdev);
-	struct can_bittiming *bt = &dev->can.data_bittiming;
+	struct can_bittiming *bt = &dev->can.fd.data_bittiming;
 	struct gs_device_bittiming dbt = {
 		.prop_seg = cpu_to_le32(bt->prop_seg),
 		.phase_seg1 = cpu_to_le32(bt->phase_seg1),
@@ -1300,8 +1300,8 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 		/* The data bit timing will be overwritten, if
 		 * GS_CAN_FEATURE_BT_CONST_EXT is set.
 		 */
-		dev->can.data_bittiming_const = &dev->bt_const;
-		dev->can.do_set_data_bittiming = gs_usb_set_data_bittiming;
+		dev->can.fd.data_bittiming_const = &dev->bt_const;
+		dev->can.fd.do_set_data_bittiming = gs_usb_set_data_bittiming;
 	}
 
 	if (feature & GS_CAN_FEATURE_TERMINATION) {
@@ -1381,7 +1381,7 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 		dev->data_bt_const.brp_max = le32_to_cpu(bt_const_extended.dbrp_max);
 		dev->data_bt_const.brp_inc = le32_to_cpu(bt_const_extended.dbrp_inc);
 
-		dev->can.data_bittiming_const = &dev->data_bt_const;
+		dev->can.fd.data_bittiming_const = &dev->data_bt_const;
 	}
 
 	can_rx_offload_add_manual(netdev, &dev->offload, GS_NAPI_WEIGHT);
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
index 078496d9b7ba..f6c77eca9f43 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
@@ -137,7 +137,7 @@ struct kvaser_usb_net_priv {
  * @dev_set_mode:		used for can.do_set_mode
  * @dev_set_bittiming:		used for can.do_set_bittiming
  * @dev_get_busparams:		readback arbitration busparams
- * @dev_set_data_bittiming:	used for can.do_set_data_bittiming
+ * @dev_set_data_bittiming:	used for can.fd.do_set_data_bittiming
  * @dev_get_data_busparams:	readback data busparams
  * @dev_get_berr_counter:	used for can.do_get_berr_counter
  *
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index dcb0bcbe0565..daf42080f942 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -592,7 +592,7 @@ static int kvaser_usb_set_data_bittiming(struct net_device *netdev)
 	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
 	struct kvaser_usb *dev = priv->dev;
 	const struct kvaser_usb_dev_ops *ops = dev->driver_info->ops;
-	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	struct kvaser_usb_busparams busparams;
 	int tseg1 = dbt->prop_seg + dbt->phase_seg1;
 	int tseg2 = dbt->phase_seg2;
@@ -842,8 +842,8 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel)
 	priv->can.ctrlmode_supported |= dev->card_data.ctrlmode_supported;
 
 	if (priv->can.ctrlmode_supported & CAN_CTRLMODE_FD) {
-		priv->can.data_bittiming_const = dev->cfg->data_bittiming_const;
-		priv->can.do_set_data_bittiming = kvaser_usb_set_data_bittiming;
+		priv->can.fd.data_bittiming_const = dev->cfg->data_bittiming_const;
+		priv->can.fd.do_set_data_bittiming = kvaser_usb_set_data_bittiming;
 	}
 
 	netdev->flags |= IFF_ECHO;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 59f7cd8ceb39..117637b9b995 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -770,7 +770,7 @@ static int peak_usb_set_data_bittiming(struct net_device *netdev)
 	const struct peak_usb_adapter *pa = dev->adapter;
 
 	if (pa->dev_set_data_bittiming) {
-		struct can_bittiming *bt = &dev->can.data_bittiming;
+		struct can_bittiming *bt = &dev->can.fd.data_bittiming;
 		int err = pa->dev_set_data_bittiming(dev, bt);
 
 		if (err)
@@ -954,8 +954,8 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter,
 	dev->can.clock = peak_usb_adapter->clock;
 	dev->can.bittiming_const = peak_usb_adapter->bittiming_const;
 	dev->can.do_set_bittiming = peak_usb_set_bittiming;
-	dev->can.data_bittiming_const = peak_usb_adapter->data_bittiming_const;
-	dev->can.do_set_data_bittiming = peak_usb_set_data_bittiming;
+	dev->can.fd.data_bittiming_const = peak_usb_adapter->data_bittiming_const;
+	dev->can.fd.do_set_data_bittiming = peak_usb_set_data_bittiming;
 	dev->can.do_set_mode = peak_usb_set_mode;
 	dev->can.do_get_berr_counter = peak_usb_adapter->do_get_berr_counter;
 	dev->can.ctrlmode_supported = peak_usb_adapter->ctrlmode_supported;
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 436c0e4b0344..3f2e378199ab 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -481,7 +481,7 @@ static int xcan_set_bittiming(struct net_device *ndev)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
 	struct can_bittiming *bt = &priv->can.bittiming;
-	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct can_bittiming *dbt = &priv->can.fd.data_bittiming;
 	u32 btr0, btr1;
 	u32 is_config_mode;
 
@@ -517,10 +517,10 @@ static int xcan_set_bittiming(struct net_device *ndev)
 		btr0 = dbt->brp - 1;
 		if (can_tdc_is_enabled(&priv->can)) {
 			if (priv->devtype.cantype == XAXI_CANFD)
-				btr0 |= FIELD_PREP(XCAN_BRPR_TDCO_MASK, priv->can.tdc.tdco) |
+				btr0 |= FIELD_PREP(XCAN_BRPR_TDCO_MASK, priv->can.fd.tdc.tdco) |
 					XCAN_BRPR_TDC_ENABLE;
 			else
-				btr0 |= FIELD_PREP(XCAN_2_BRPR_TDCO_MASK, priv->can.tdc.tdco) |
+				btr0 |= FIELD_PREP(XCAN_2_BRPR_TDCO_MASK, priv->can.fd.tdc.tdco) |
 					XCAN_BRPR_TDC_ENABLE;
 		}
 
@@ -1967,22 +1967,22 @@ static int xcan_probe(struct platform_device *pdev)
 		goto err_free;
 
 	if (devtype->cantype == XAXI_CANFD) {
-		priv->can.data_bittiming_const =
+		priv->can.fd.data_bittiming_const =
 			&xcan_data_bittiming_const_canfd;
-		priv->can.tdc_const = &xcan_tdc_const_canfd;
+		priv->can.fd.tdc_const = &xcan_tdc_const_canfd;
 	}
 
 	if (devtype->cantype == XAXI_CANFD_2_0) {
-		priv->can.data_bittiming_const =
+		priv->can.fd.data_bittiming_const =
 			&xcan_data_bittiming_const_canfd2;
-		priv->can.tdc_const = &xcan_tdc_const_canfd2;
+		priv->can.fd.tdc_const = &xcan_tdc_const_canfd2;
 	}
 
 	if (devtype->cantype == XAXI_CANFD ||
 	    devtype->cantype == XAXI_CANFD_2_0) {
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD |
 						CAN_CTRLMODE_TDC_AUTO;
-		priv->can.do_get_auto_tdcv = xcan_get_auto_tdcv;
+		priv->can.fd.do_get_auto_tdcv = xcan_get_auto_tdcv;
 	}
 
 	priv->reg_base = addr;
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 61d164ffb3ae..132683ed3abe 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -21,6 +21,7 @@
 #include <linux/export.h>
 #include <linux/gpio.h>
 #include <linux/kernel.h>
+#include <linux/math.h>
 #include <linux/module.h>
 #include <linux/platform_data/b53.h>
 #include <linux/phy.h>
@@ -326,6 +327,26 @@ static void b53_get_vlan_entry(struct b53_device *dev, u16 vid,
 	}
 }
 
+static void b53_set_eap_mode(struct b53_device *dev, int port, int mode)
+{
+	u64 eap_conf;
+
+	if (is5325(dev) || is5365(dev) || dev->chip_id == BCM5389_DEVICE_ID)
+		return;
+
+	b53_read64(dev, B53_EAP_PAGE, B53_PORT_EAP_CONF(port), &eap_conf);
+
+	if (is63xx(dev)) {
+		eap_conf &= ~EAP_MODE_MASK_63XX;
+		eap_conf |= (u64)mode << EAP_MODE_SHIFT_63XX;
+	} else {
+		eap_conf &= ~EAP_MODE_MASK;
+		eap_conf |= (u64)mode << EAP_MODE_SHIFT;
+	}
+
+	b53_write64(dev, B53_EAP_PAGE, B53_PORT_EAP_CONF(port), eap_conf);
+}
+
 static void b53_set_forwarding(struct b53_device *dev, int enable)
 {
 	u8 mgmt;
@@ -373,15 +394,17 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
 		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, &vc5);
 	}
 
+	vc1 &= ~VC1_RX_MCST_FWD_EN;
+
 	if (enable) {
 		vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID;
-		vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN;
+		vc1 |= VC1_RX_MCST_UNTAG_EN;
 		vc4 &= ~VC4_ING_VID_CHECK_MASK;
 		if (enable_filtering) {
 			vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S;
 			vc5 |= VC5_DROP_VTABLE_MISS;
 		} else {
-			vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S;
+			vc4 |= VC4_NO_ING_VID_CHK << VC4_ING_VID_CHECK_S;
 			vc5 &= ~VC5_DROP_VTABLE_MISS;
 		}
 
@@ -393,7 +416,7 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
 
 	} else {
 		vc0 &= ~(VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID);
-		vc1 &= ~(VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN);
+		vc1 &= ~VC1_RX_MCST_UNTAG_EN;
 		vc4 &= ~VC4_ING_VID_CHECK_MASK;
 		vc5 &= ~VC5_DROP_VTABLE_MISS;
 
@@ -576,6 +599,25 @@ static void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable)
 	b53_write16(dev, B53_EEE_PAGE, B53_EEE_EN_CTRL, reg);
 }
 
+int b53_setup_port(struct dsa_switch *ds, int port)
+{
+	struct b53_device *dev = ds->priv;
+
+	b53_port_set_ucast_flood(dev, port, true);
+	b53_port_set_mcast_flood(dev, port, true);
+	b53_port_set_learning(dev, port, false);
+
+	/* Force all traffic to go to the CPU port to prevent the ASIC from
+	 * trying to forward to bridged ports on matching FDB entries, then
+	 * dropping frames because it isn't allowed to forward there.
+	 */
+	if (dsa_is_user_port(ds, port))
+		b53_set_eap_mode(dev, port, EAP_MODE_SIMPLIFIED);
+
+	return 0;
+}
+EXPORT_SYMBOL(b53_setup_port);
+
 int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 {
 	struct b53_device *dev = ds->priv;
@@ -588,10 +630,6 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 
 	cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
 
-	b53_port_set_ucast_flood(dev, port, true);
-	b53_port_set_mcast_flood(dev, port, true);
-	b53_port_set_learning(dev, port, false);
-
 	if (dev->ops->irq_enable)
 		ret = dev->ops->irq_enable(dev, port);
 	if (ret)
@@ -722,10 +760,6 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port)
 	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl);
 
 	b53_brcm_hdr_setup(dev->ds, port);
-
-	b53_port_set_ucast_flood(dev, port, true);
-	b53_port_set_mcast_flood(dev, port, true);
-	b53_port_set_learning(dev, port, false);
 }
 
 static void b53_enable_mib(struct b53_device *dev)
@@ -737,6 +771,15 @@ static void b53_enable_mib(struct b53_device *dev)
 	b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc);
 }
 
+static void b53_enable_stp(struct b53_device *dev)
+{
+	u8 gc;
+
+	b53_read8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, &gc);
+	gc |= GC_RX_BPDU_EN;
+	b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc);
+}
+
 static u16 b53_default_pvid(struct b53_device *dev)
 {
 	if (is5325(dev) || is5365(dev))
@@ -752,6 +795,22 @@ static bool b53_vlan_port_needs_forced_tagged(struct dsa_switch *ds, int port)
 	return dev->tag_protocol == DSA_TAG_PROTO_NONE && dsa_is_cpu_port(ds, port);
 }
 
+static bool b53_vlan_port_may_join_untagged(struct dsa_switch *ds, int port)
+{
+	struct b53_device *dev = ds->priv;
+	struct dsa_port *dp;
+
+	if (!dev->vlan_filtering)
+		return true;
+
+	dp = dsa_to_port(ds, port);
+
+	if (dsa_port_is_cpu(dp))
+		return true;
+
+	return dp->bridge == NULL;
+}
+
 int b53_configure_vlan(struct dsa_switch *ds)
 {
 	struct b53_device *dev = ds->priv;
@@ -770,7 +829,7 @@ int b53_configure_vlan(struct dsa_switch *ds)
 		b53_do_vlan_op(dev, VTA_CMD_CLEAR);
 	}
 
-	b53_enable_vlan(dev, -1, dev->vlan_enabled, ds->vlan_filtering);
+	b53_enable_vlan(dev, -1, dev->vlan_enabled, dev->vlan_filtering);
 
 	/* Create an untagged VLAN entry for the default PVID in case
 	 * CONFIG_VLAN_8021Q is disabled and there are no calls to
@@ -778,26 +837,39 @@ int b53_configure_vlan(struct dsa_switch *ds)
 	 * entry. Do this only when the tagging protocol is not
 	 * DSA_TAG_PROTO_NONE
 	 */
+	v = &dev->vlans[def_vid];
 	b53_for_each_port(dev, i) {
-		v = &dev->vlans[def_vid];
-		v->members |= BIT(i);
+		if (!b53_vlan_port_may_join_untagged(ds, i))
+			continue;
+
+		vl.members |= BIT(i);
 		if (!b53_vlan_port_needs_forced_tagged(ds, i))
-			v->untag = v->members;
-		b53_write16(dev, B53_VLAN_PAGE,
-			    B53_VLAN_PORT_DEF_TAG(i), def_vid);
+			vl.untag = vl.members;
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(i),
+			    def_vid);
 	}
+	b53_set_vlan_entry(dev, def_vid, &vl);
 
-	/* Upon initial call we have not set-up any VLANs, but upon
-	 * system resume, we need to restore all VLAN entries.
-	 */
-	for (vid = def_vid; vid < dev->num_vlans; vid++) {
-		v = &dev->vlans[vid];
+	if (dev->vlan_filtering) {
+		/* Upon initial call we have not set-up any VLANs, but upon
+		 * system resume, we need to restore all VLAN entries.
+		 */
+		for (vid = def_vid + 1; vid < dev->num_vlans; vid++) {
+			v = &dev->vlans[vid];
 
-		if (!v->members)
-			continue;
+			if (!v->members)
+				continue;
 
-		b53_set_vlan_entry(dev, vid, v);
-		b53_fast_age_vlan(dev, vid);
+			b53_set_vlan_entry(dev, vid, v);
+			b53_fast_age_vlan(dev, vid);
+		}
+
+		b53_for_each_port(dev, i) {
+			if (!dsa_is_cpu_port(ds, i))
+				b53_write16(dev, B53_VLAN_PAGE,
+					    B53_VLAN_PORT_DEF_TAG(i),
+					    dev->ports[i].pvid);
+		}
 	}
 
 	return 0;
@@ -876,6 +948,7 @@ static int b53_switch_reset(struct b53_device *dev)
 	}
 
 	b53_enable_mib(dev);
+	b53_enable_stp(dev);
 
 	return b53_flush_arl(dev, FAST_AGE_STATIC);
 }
@@ -1115,7 +1188,9 @@ EXPORT_SYMBOL(b53_setup_devlink_resources);
 static int b53_setup(struct dsa_switch *ds)
 {
 	struct b53_device *dev = ds->priv;
+	struct b53_vlan *vl;
 	unsigned int port;
+	u16 pvid;
 	int ret;
 
 	/* Request bridge PVID untagged when DSA_TAG_PROTO_NONE is set
@@ -1123,12 +1198,30 @@ static int b53_setup(struct dsa_switch *ds)
 	 */
 	ds->untag_bridge_pvid = dev->tag_protocol == DSA_TAG_PROTO_NONE;
 
+	/* The switch does not tell us the original VLAN for untagged
+	 * packets, so keep the CPU port always tagged.
+	 */
+	ds->untag_vlan_aware_bridge_pvid = true;
+
+	/* Ageing time is set in seconds */
+	ds->ageing_time_min = 1 * 1000;
+	ds->ageing_time_max = AGE_TIME_MAX * 1000;
+
 	ret = b53_reset_switch(dev);
 	if (ret) {
 		dev_err(ds->dev, "failed to reset switch\n");
 		return ret;
 	}
 
+	/* setup default vlan for filtering mode */
+	pvid = b53_default_pvid(dev);
+	vl = &dev->vlans[pvid];
+	b53_for_each_port(dev, port) {
+		vl->members |= BIT(port);
+		if (!b53_vlan_port_needs_forced_tagged(ds, port))
+			vl->untag |= BIT(port);
+	}
+
 	b53_reset_mib(dev);
 
 	ret = b53_apply_config(dev);
@@ -1482,7 +1575,10 @@ int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering,
 {
 	struct b53_device *dev = ds->priv;
 
-	b53_enable_vlan(dev, port, dev->vlan_enabled, vlan_filtering);
+	if (dev->vlan_filtering != vlan_filtering) {
+		dev->vlan_filtering = vlan_filtering;
+		b53_apply_config(dev);
+	}
 
 	return 0;
 }
@@ -1507,7 +1603,7 @@ static int b53_vlan_prepare(struct dsa_switch *ds, int port,
 	if (vlan->vid >= dev->num_vlans)
 		return -ERANGE;
 
-	b53_enable_vlan(dev, port, true, ds->vlan_filtering);
+	b53_enable_vlan(dev, port, true, dev->vlan_filtering);
 
 	return 0;
 }
@@ -1520,18 +1616,29 @@ int b53_vlan_add(struct dsa_switch *ds, int port,
 	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
 	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
 	struct b53_vlan *vl;
+	u16 old_pvid, new_pvid;
 	int err;
 
 	err = b53_vlan_prepare(ds, port, vlan);
 	if (err)
 		return err;
 
-	vl = &dev->vlans[vlan->vid];
+	if (vlan->vid == 0)
+		return 0;
 
-	b53_get_vlan_entry(dev, vlan->vid, vl);
+	old_pvid = dev->ports[port].pvid;
+	if (pvid)
+		new_pvid = vlan->vid;
+	else if (!pvid && vlan->vid == old_pvid)
+		new_pvid = b53_default_pvid(dev);
+	else
+		new_pvid = old_pvid;
+	dev->ports[port].pvid = new_pvid;
+
+	vl = &dev->vlans[vlan->vid];
 
-	if (vlan->vid == 0 && vlan->vid == b53_default_pvid(dev))
-		untagged = true;
+	if (dsa_is_cpu_port(ds, port))
+		untagged = false;
 
 	vl->members |= BIT(port);
 	if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
@@ -1539,13 +1646,16 @@ int b53_vlan_add(struct dsa_switch *ds, int port,
 	else
 		vl->untag &= ~BIT(port);
 
+	if (!dev->vlan_filtering)
+		return 0;
+
 	b53_set_vlan_entry(dev, vlan->vid, vl);
 	b53_fast_age_vlan(dev, vlan->vid);
 
-	if (pvid && !dsa_is_cpu_port(ds, port)) {
+	if (!dsa_is_cpu_port(ds, port) && new_pvid != old_pvid) {
 		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port),
-			    vlan->vid);
-		b53_fast_age_vlan(dev, vlan->vid);
+			    new_pvid);
+		b53_fast_age_vlan(dev, old_pvid);
 	}
 
 	return 0;
@@ -1560,20 +1670,25 @@ int b53_vlan_del(struct dsa_switch *ds, int port,
 	struct b53_vlan *vl;
 	u16 pvid;
 
-	b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid);
+	if (vlan->vid == 0)
+		return 0;
 
-	vl = &dev->vlans[vlan->vid];
+	pvid = dev->ports[port].pvid;
 
-	b53_get_vlan_entry(dev, vlan->vid, vl);
+	vl = &dev->vlans[vlan->vid];
 
 	vl->members &= ~BIT(port);
 
 	if (pvid == vlan->vid)
 		pvid = b53_default_pvid(dev);
+	dev->ports[port].pvid = pvid;
 
 	if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
 		vl->untag &= ~(BIT(port));
 
+	if (!dev->vlan_filtering)
+		return 0;
+
 	b53_set_vlan_entry(dev, vlan->vid, vl);
 	b53_fast_age_vlan(dev, vlan->vid);
 
@@ -1906,8 +2021,9 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 		bool *tx_fwd_offload, struct netlink_ext_ack *extack)
 {
 	struct b53_device *dev = ds->priv;
+	struct b53_vlan *vl;
 	s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
-	u16 pvlan, reg;
+	u16 pvlan, reg, pvid;
 	unsigned int i;
 
 	/* On 7278, port 7 which connects to the ASP should only receive
@@ -1916,15 +2032,29 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 	if (dev->chip_id == BCM7278_DEVICE_ID && port == 7)
 		return -EINVAL;
 
-	/* Make this port leave the all VLANs join since we will have proper
-	 * VLAN entries from now on
-	 */
-	if (is58xx(dev)) {
-		b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, &reg);
-		reg &= ~BIT(port);
-		if ((reg & BIT(cpu_port)) == BIT(cpu_port))
-			reg &= ~BIT(cpu_port);
-		b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
+	pvid = b53_default_pvid(dev);
+	vl = &dev->vlans[pvid];
+
+	if (dev->vlan_filtering) {
+		/* Make this port leave the all VLANs join since we will have
+		 * proper VLAN entries from now on
+		 */
+		if (is58xx(dev)) {
+			b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN,
+				   &reg);
+			reg &= ~BIT(port);
+			if ((reg & BIT(cpu_port)) == BIT(cpu_port))
+				reg &= ~BIT(cpu_port);
+			b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN,
+				    reg);
+		}
+
+		b53_get_vlan_entry(dev, pvid, vl);
+		vl->members &= ~BIT(port);
+		if (vl->members == BIT(cpu_port))
+			vl->members &= ~BIT(cpu_port);
+		vl->untag = vl->members;
+		b53_set_vlan_entry(dev, pvid, vl);
 	}
 
 	b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
@@ -1944,6 +2074,9 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 		pvlan |= BIT(i);
 	}
 
+	/* Disable redirection of unknown SA to the CPU port */
+	b53_set_eap_mode(dev, port, EAP_MODE_BASIC);
+
 	/* Configure the local port VLAN control membership to include
 	 * remote ports and update the local port bitmask
 	 */
@@ -1957,7 +2090,7 @@ EXPORT_SYMBOL(b53_br_join);
 void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
 {
 	struct b53_device *dev = ds->priv;
-	struct b53_vlan *vl = &dev->vlans[0];
+	struct b53_vlan *vl;
 	s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
 	unsigned int i;
 	u16 pvlan, reg, pvid;
@@ -1979,19 +2112,25 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
 			pvlan &= ~BIT(i);
 	}
 
+	/* Enable redirection of unknown SA to the CPU port */
+	b53_set_eap_mode(dev, port, EAP_MODE_SIMPLIFIED);
+
 	b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan);
 	dev->ports[port].vlan_ctl_mask = pvlan;
 
 	pvid = b53_default_pvid(dev);
+	vl = &dev->vlans[pvid];
+
+	if (dev->vlan_filtering) {
+		/* Make this port join all VLANs without VLAN entries */
+		if (is58xx(dev)) {
+			b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, &reg);
+			reg |= BIT(port);
+			if (!(reg & BIT(cpu_port)))
+				reg |= BIT(cpu_port);
+			b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
+		}
 
-	/* Make this port join all VLANs without VLAN entries */
-	if (is58xx(dev)) {
-		b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, &reg);
-		reg |= BIT(port);
-		if (!(reg & BIT(cpu_port)))
-			reg |= BIT(cpu_port);
-		b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
-	} else {
 		b53_get_vlan_entry(dev, pvid, vl);
 		vl->members |= BIT(port) | BIT(cpu_port);
 		vl->untag |= BIT(port) | BIT(cpu_port);
@@ -2272,6 +2411,28 @@ static int b53_get_max_mtu(struct dsa_switch *ds, int port)
 	return B53_MAX_MTU;
 }
 
+int b53_set_ageing_time(struct dsa_switch *ds, unsigned int msecs)
+{
+	struct b53_device *dev = ds->priv;
+	u32 atc;
+	int reg;
+
+	if (is63xx(dev))
+		reg = B53_AGING_TIME_CONTROL_63XX;
+	else
+		reg = B53_AGING_TIME_CONTROL;
+
+	atc = DIV_ROUND_CLOSEST(msecs, 1000);
+
+	if (!is5325(dev) && !is5365(dev))
+		atc |= AGE_CHANGE;
+
+	b53_write32(dev, B53_MGMT_PAGE, reg, atc);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(b53_set_ageing_time);
+
 static const struct phylink_mac_ops b53_phylink_mac_ops = {
 	.mac_select_pcs	= b53_phylink_mac_select_pcs,
 	.mac_config	= b53_phylink_mac_config,
@@ -2290,10 +2451,12 @@ static const struct dsa_switch_ops b53_switch_ops = {
 	.phy_read		= b53_phy_read16,
 	.phy_write		= b53_phy_write16,
 	.phylink_get_caps	= b53_phylink_get_caps,
+	.port_setup		= b53_setup_port,
 	.port_enable		= b53_enable_port,
 	.port_disable		= b53_disable_port,
 	.support_eee		= b53_support_eee,
 	.set_mac_eee		= b53_set_mac_eee,
+	.set_ageing_time	= b53_set_ageing_time,
 	.port_bridge_join	= b53_br_join,
 	.port_bridge_leave	= b53_br_leave,
 	.port_pre_bridge_flags	= b53_br_flags_pre,
@@ -2747,6 +2910,7 @@ struct b53_device *b53_switch_alloc(struct device *base,
 	ds->ops = &b53_switch_ops;
 	ds->phylink_mac_ops = &b53_phylink_mac_ops;
 	dev->vlan_enabled = true;
+	dev->vlan_filtering = false;
 	/* Let DSA handle the case were multiple bridges span the same switch
 	 * device and different VLAN awareness settings are requested, which
 	 * would be breaking filtering semantics for any of the other bridge
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 0166c37a13a7..a5ef7071ba07 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -96,6 +96,7 @@ struct b53_pcs {
 
 struct b53_port {
 	u16		vlan_ctl_mask;
+	u16		pvid;
 	struct ethtool_keee eee;
 };
 
@@ -147,6 +148,7 @@ struct b53_device {
 	unsigned int num_vlans;
 	struct b53_vlan *vlans;
 	bool vlan_enabled;
+	bool vlan_filtering;
 	unsigned int num_ports;
 	struct b53_port *ports;
 
@@ -341,6 +343,7 @@ void b53_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data);
 int b53_get_sset_count(struct dsa_switch *ds, int port, int sset);
 void b53_get_ethtool_phy_stats(struct dsa_switch *ds, int port, uint64_t *data);
+int b53_set_ageing_time(struct dsa_switch *ds, unsigned int msecs);
 int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 		bool *tx_fwd_offload, struct netlink_ext_ack *extack);
 void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge);
@@ -382,6 +385,7 @@ enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port,
 					   enum dsa_tag_protocol mprot);
 void b53_mirror_del(struct dsa_switch *ds, int port,
 		    struct dsa_mall_mirror_tc_entry *mirror);
+int b53_setup_port(struct dsa_switch *ds, int port);
 int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
 void b53_disable_port(struct dsa_switch *ds, int port);
 void b53_brcm_hdr_setup(struct dsa_switch *ds, int port);
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index bfbcb66bef66..1fbc5a204bc7 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -50,6 +50,9 @@
 /* Jumbo Frame Registers */
 #define B53_JUMBO_PAGE			0x40
 
+/* EAP Registers */
+#define B53_EAP_PAGE			0x42
+
 /* EEE Control Registers Page */
 #define B53_EEE_PAGE			0x92
 
@@ -217,6 +220,13 @@
 #define   BRCM_HDR_P5_EN		BIT(1) /* Enable tagging on port 5 */
 #define   BRCM_HDR_P7_EN		BIT(2) /* Enable tagging on port 7 */
 
+/* Aging Time control register (32 bit) */
+#define B53_AGING_TIME_CONTROL		0x06
+#define B53_AGING_TIME_CONTROL_63XX	0x08
+#define  AGE_CHANGE			BIT(20)
+#define  AGE_TIME_MASK			0x7ffff
+#define  AGE_TIME_MAX			1048575
+
 /* Mirror capture control register (16 bit) */
 #define B53_MIR_CAP_CTL			0x10
 #define  CAP_PORT_MASK			0xf
@@ -481,6 +491,17 @@
 #define   JMS_MAX_SIZE			9724
 
 /*************************************************************************
+ * EAP Page Registers
+ *************************************************************************/
+#define B53_PORT_EAP_CONF(i)		(0x20 + 8 * (i))
+#define  EAP_MODE_SHIFT			51
+#define  EAP_MODE_SHIFT_63XX		50
+#define  EAP_MODE_MASK			(0x3ull << EAP_MODE_SHIFT)
+#define  EAP_MODE_MASK_63XX		(0x3ull << EAP_MODE_SHIFT_63XX)
+#define  EAP_MODE_BASIC			0
+#define  EAP_MODE_SIMPLIFIED		3
+
+/*************************************************************************
  * EEE Configuration Page Registers
  *************************************************************************/
 
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index fa2bf3fa9019..960685596093 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1230,10 +1230,12 @@ static const struct dsa_switch_ops bcm_sf2_ops = {
 	.resume			= bcm_sf2_sw_resume,
 	.get_wol		= bcm_sf2_sw_get_wol,
 	.set_wol		= bcm_sf2_sw_set_wol,
+	.port_setup		= b53_setup_port,
 	.port_enable		= bcm_sf2_port_setup,
 	.port_disable		= bcm_sf2_port_disable,
 	.support_eee		= b53_support_eee,
 	.set_mac_eee		= b53_set_mac_eee,
+	.set_ageing_time	= b53_set_ageing_time,
 	.port_bridge_join	= b53_br_join,
 	.port_bridge_leave	= b53_br_leave,
 	.port_pre_bridge_flags	= b53_br_flags_pre,
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index adbab544c60f..d8a35f25a4c8 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -405,7 +405,7 @@ static int __init dsa_loop_init(void)
 	unsigned int i, ret;
 
 	for (i = 0; i < NUM_FIXED_PHYS; i++)
-		phydevs[i] = fixed_phy_register(PHY_POLL, &status, NULL);
+		phydevs[i] = fixed_phy_register(&status, NULL);
 
 	ret = mdio_driver_register(&dsa_loop_drv);
 	if (ret)
diff --git a/drivers/net/dsa/hirschmann/hellcreek.h b/drivers/net/dsa/hirschmann/hellcreek.h
index 9c2ed2ba79da..bebf0d3ff330 100644
--- a/drivers/net/dsa/hirschmann/hellcreek.h
+++ b/drivers/net/dsa/hirschmann/hellcreek.h
@@ -244,7 +244,7 @@ struct hellcreek_port_hwtstamp {
 	struct sk_buff *tx_skb;
 
 	/* Current timestamp configuration */
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 };
 
 struct hellcreek_port {
diff --git a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c
index ca2500aba96f..99941ff1ebf9 100644
--- a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c
+++ b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c
@@ -40,7 +40,7 @@ int hellcreek_get_ts_info(struct dsa_switch *ds, int port,
  * the user requested what is actually available or not
  */
 static int hellcreek_set_hwtstamp_config(struct hellcreek *hellcreek, int port,
-					 struct hwtstamp_config *config)
+					 struct kernel_hwtstamp_config *config)
 {
 	struct hellcreek_port_hwtstamp *ps =
 		&hellcreek->ports[port].port_hwtstamp;
@@ -110,41 +110,35 @@ static int hellcreek_set_hwtstamp_config(struct hellcreek *hellcreek, int port,
 }
 
 int hellcreek_port_hwtstamp_set(struct dsa_switch *ds, int port,
-				struct ifreq *ifr)
+				struct kernel_hwtstamp_config *config,
+				struct netlink_ext_ack *extack)
 {
 	struct hellcreek *hellcreek = ds->priv;
 	struct hellcreek_port_hwtstamp *ps;
-	struct hwtstamp_config config;
 	int err;
 
 	ps = &hellcreek->ports[port].port_hwtstamp;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = hellcreek_set_hwtstamp_config(hellcreek, port, &config);
+	err = hellcreek_set_hwtstamp_config(hellcreek, port, config);
 	if (err)
 		return err;
 
 	/* Save the chosen configuration to be returned later */
-	memcpy(&ps->tstamp_config, &config, sizeof(config));
+	ps->tstamp_config = *config;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 int hellcreek_port_hwtstamp_get(struct dsa_switch *ds, int port,
-				struct ifreq *ifr)
+				struct kernel_hwtstamp_config *config)
 {
 	struct hellcreek *hellcreek = ds->priv;
 	struct hellcreek_port_hwtstamp *ps;
-	struct hwtstamp_config *config;
 
 	ps = &hellcreek->ports[port].port_hwtstamp;
-	config = &ps->tstamp_config;
+	*config = ps->tstamp_config;
 
-	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 /* Returns a pointer to the PTP header if the caller should time stamp, or NULL
diff --git a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.h b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.h
index 7d88da2134f2..388821c4aa10 100644
--- a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.h
+++ b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.h
@@ -38,9 +38,10 @@
 #define TX_TSTAMP_TIMEOUT	msecs_to_jiffies(40)
 
 int hellcreek_port_hwtstamp_set(struct dsa_switch *ds, int port,
-				struct ifreq *ifr);
+				struct kernel_hwtstamp_config *config,
+				struct netlink_ext_ack *extack);
 int hellcreek_port_hwtstamp_get(struct dsa_switch *ds, int port,
-				struct ifreq *ifr);
+				struct kernel_hwtstamp_config *config);
 
 bool hellcreek_port_rxtstamp(struct dsa_switch *ds, int port,
 			     struct sk_buff *clone, unsigned int type);
diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig
index 12a86585a77f..c71d3fd5dfeb 100644
--- a/drivers/net/dsa/microchip/Kconfig
+++ b/drivers/net/dsa/microchip/Kconfig
@@ -6,6 +6,7 @@ menuconfig NET_DSA_MICROCHIP_KSZ_COMMON
 	select NET_DSA_TAG_NONE
 	select NET_IEEE8021Q_HELPERS
 	select DCB
+	select PCS_XPCS
 	help
 	  This driver adds support for Microchip KSZ8, KSZ9 and
 	  LAN937X series switch chips, being KSZ8863/8873,
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 29fe79ea74cd..d747ea1c41a7 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -2,7 +2,7 @@
 /*
  * Microchip KSZ9477 switch driver main logic
  *
- * Copyright (C) 2017-2024 Microchip Technology Inc.
+ * Copyright (C) 2017-2025 Microchip Technology Inc.
  */
 
 #include <linux/kernel.h>
@@ -161,6 +161,190 @@ static int ksz9477_wait_alu_sta_ready(struct ksz_device *dev)
 					10, 1000);
 }
 
+static void port_sgmii_s(struct ksz_device *dev, uint port, u16 devid, u16 reg)
+{
+	u32 data;
+
+	data = (devid & MII_MMD_CTRL_DEVAD_MASK) << 16;
+	data |= reg;
+	ksz_pwrite32(dev, port, REG_PORT_SGMII_ADDR__4, data);
+}
+
+static void port_sgmii_r(struct ksz_device *dev, uint port, u16 devid, u16 reg,
+			 u16 *buf)
+{
+	port_sgmii_s(dev, port, devid, reg);
+	ksz_pread16(dev, port, REG_PORT_SGMII_DATA__4 + 2, buf);
+}
+
+static void port_sgmii_w(struct ksz_device *dev, uint port, u16 devid, u16 reg,
+			 u16 buf)
+{
+	port_sgmii_s(dev, port, devid, reg);
+	ksz_pwrite32(dev, port, REG_PORT_SGMII_DATA__4, buf);
+}
+
+static int ksz9477_pcs_read(struct mii_bus *bus, int phy, int mmd, int reg)
+{
+	struct ksz_device *dev = bus->priv;
+	int port = ksz_get_sgmii_port(dev);
+	u16 val;
+
+	port_sgmii_r(dev, port, mmd, reg, &val);
+
+	/* Simulate a value to activate special code in the XPCS driver if
+	 * supported.
+	 */
+	if (mmd == MDIO_MMD_PMAPMD) {
+		if (reg == MDIO_DEVID1)
+			val = 0x9477;
+		else if (reg == MDIO_DEVID2)
+			val = 0x22 << 10;
+	} else if (mmd == MDIO_MMD_VEND2) {
+		struct ksz_port *p = &dev->ports[port];
+
+		/* Need to update MII_BMCR register with the exact speed and
+		 * duplex mode when running in SGMII mode and this register is
+		 * used to detect connected speed in that mode.
+		 */
+		if (reg == MMD_SR_MII_AUTO_NEG_STATUS) {
+			int duplex, speed;
+
+			if (val & SR_MII_STAT_LINK_UP) {
+				speed = (val >> SR_MII_STAT_S) & SR_MII_STAT_M;
+				if (speed == SR_MII_STAT_1000_MBPS)
+					speed = SPEED_1000;
+				else if (speed == SR_MII_STAT_100_MBPS)
+					speed = SPEED_100;
+				else
+					speed = SPEED_10;
+
+				if (val & SR_MII_STAT_FULL_DUPLEX)
+					duplex = DUPLEX_FULL;
+				else
+					duplex = DUPLEX_HALF;
+
+				if (!p->phydev.link ||
+				    p->phydev.speed != speed ||
+				    p->phydev.duplex != duplex) {
+					u16 ctrl;
+
+					p->phydev.link = 1;
+					p->phydev.speed = speed;
+					p->phydev.duplex = duplex;
+					port_sgmii_r(dev, port, mmd, MII_BMCR,
+						     &ctrl);
+					ctrl &= BMCR_ANENABLE;
+					ctrl |= mii_bmcr_encode_fixed(speed,
+								      duplex);
+					port_sgmii_w(dev, port, mmd, MII_BMCR,
+						     ctrl);
+				}
+			} else {
+				p->phydev.link = 0;
+			}
+		} else if (reg == MII_BMSR) {
+			p->phydev.link = (val & BMSR_LSTATUS);
+		}
+	}
+
+	return val;
+}
+
+static int ksz9477_pcs_write(struct mii_bus *bus, int phy, int mmd, int reg,
+			     u16 val)
+{
+	struct ksz_device *dev = bus->priv;
+	int port = ksz_get_sgmii_port(dev);
+
+	if (mmd == MDIO_MMD_VEND2) {
+		struct ksz_port *p = &dev->ports[port];
+
+		if (reg == MMD_SR_MII_AUTO_NEG_CTRL) {
+			u16 sgmii_mode = SR_MII_PCS_SGMII << SR_MII_PCS_MODE_S;
+
+			/* Need these bits for 1000BASE-X mode to work with
+			 * AN on.
+			 */
+			if (!(val & sgmii_mode))
+				val |= SR_MII_SGMII_LINK_UP |
+				       SR_MII_TX_CFG_PHY_MASTER;
+
+			/* SGMII interrupt in the port cannot be masked, so
+			 * make sure interrupt is not enabled as it is not
+			 * handled.
+			 */
+			val &= ~SR_MII_AUTO_NEG_COMPLETE_INTR;
+		} else if (reg == MII_BMCR) {
+			/* The MII_ADVERTISE register needs to write once
+			 * before doing auto-negotiation for the correct
+			 * config_word to be sent out after reset.
+			 */
+			if ((val & BMCR_ANENABLE) && !p->sgmii_adv_write) {
+				u16 adv;
+
+				/* The SGMII port cannot disable flow control
+				 * so it is better to just advertise symmetric
+				 * pause.
+				 */
+				port_sgmii_r(dev, port, mmd, MII_ADVERTISE,
+					     &adv);
+				adv |= ADVERTISE_1000XPAUSE;
+				adv &= ~ADVERTISE_1000XPSE_ASYM;
+				port_sgmii_w(dev, port, mmd, MII_ADVERTISE,
+					     adv);
+				p->sgmii_adv_write = 1;
+			} else if (val & BMCR_RESET) {
+				p->sgmii_adv_write = 0;
+			}
+		} else if (reg == MII_ADVERTISE) {
+			/* XPCS driver writes to this register so there is no
+			 * need to update it for the errata.
+			 */
+			p->sgmii_adv_write = 1;
+		}
+	}
+	port_sgmii_w(dev, port, mmd, reg, val);
+
+	return 0;
+}
+
+int ksz9477_pcs_create(struct ksz_device *dev)
+{
+	/* This chip has a SGMII port. */
+	if (ksz_has_sgmii_port(dev)) {
+		int port = ksz_get_sgmii_port(dev);
+		struct ksz_port *p = &dev->ports[port];
+		struct phylink_pcs *pcs;
+		struct mii_bus *bus;
+		int ret;
+
+		bus = devm_mdiobus_alloc(dev->dev);
+		if (!bus)
+			return -ENOMEM;
+
+		bus->name = "ksz_pcs_mdio_bus";
+		snprintf(bus->id, MII_BUS_ID_SIZE, "%s-pcs",
+			 dev_name(dev->dev));
+		bus->read_c45 = &ksz9477_pcs_read;
+		bus->write_c45 = &ksz9477_pcs_write;
+		bus->parent = dev->dev;
+		bus->phy_mask = ~0;
+		bus->priv = dev;
+
+		ret = devm_mdiobus_register(dev->dev, bus);
+		if (ret)
+			return ret;
+
+		pcs = xpcs_create_pcs_mdiodev(bus, 0);
+		if (IS_ERR(pcs))
+			return PTR_ERR(pcs);
+		p->pcs = pcs;
+	}
+
+	return 0;
+}
+
 int ksz9477_reset_switch(struct ksz_device *dev)
 {
 	u8 data8;
@@ -978,6 +1162,14 @@ void ksz9477_get_caps(struct ksz_device *dev, int port,
 
 	if (dev->info->gbit_capable[port])
 		config->mac_capabilities |= MAC_1000FD;
+
+	if (ksz_is_sgmii_port(dev, port)) {
+		struct ksz_port *p = &dev->ports[port];
+
+		phy_interface_or(config->supported_interfaces,
+				 config->supported_interfaces,
+				 p->pcs->supported_interfaces);
+	}
 }
 
 int ksz9477_set_ageing_time(struct ksz_device *dev, unsigned int msecs)
diff --git a/drivers/net/dsa/microchip/ksz9477.h b/drivers/net/dsa/microchip/ksz9477.h
index d2166b0d881e..0d1a6dfda23e 100644
--- a/drivers/net/dsa/microchip/ksz9477.h
+++ b/drivers/net/dsa/microchip/ksz9477.h
@@ -2,7 +2,7 @@
 /*
  * Microchip KSZ9477 series Header file
  *
- * Copyright (C) 2017-2022 Microchip Technology Inc.
+ * Copyright (C) 2017-2025 Microchip Technology Inc.
  */
 
 #ifndef __KSZ9477_H
@@ -97,4 +97,6 @@ void ksz9477_acl_match_process_l2(struct ksz_device *dev, int port,
 				  u16 ethtype, u8 *src_mac, u8 *dst_mac,
 				  unsigned long cookie, u32 prio);
 
+int ksz9477_pcs_create(struct ksz_device *dev);
+
 #endif
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 89f0796894af..f424b3d10781 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -2,7 +2,7 @@
 /*
  * Microchip switch driver main logic
  *
- * Copyright (C) 2017-2024 Microchip Technology Inc.
+ * Copyright (C) 2017-2025 Microchip Technology Inc.
  */
 
 #include <linux/delay.h>
@@ -265,16 +265,70 @@ static void ksz_phylink_mac_link_down(struct phylink_config *config,
 				      unsigned int mode,
 				      phy_interface_t interface);
 
+/**
+ * ksz_phylink_mac_disable_tx_lpi() - Callback to signal LPI support (Dummy)
+ * @config: phylink config structure
+ *
+ * This function is a dummy handler. See ksz_phylink_mac_enable_tx_lpi() for
+ * a detailed explanation of EEE/LPI handling in KSZ switches.
+ */
+static void ksz_phylink_mac_disable_tx_lpi(struct phylink_config *config)
+{
+}
+
+/**
+ * ksz_phylink_mac_enable_tx_lpi() - Callback to signal LPI support (Dummy)
+ * @config: phylink config structure
+ * @timer: timer value before entering LPI (unused)
+ * @tx_clock_stop: whether to stop the TX clock in LPI mode (unused)
+ *
+ * This function signals to phylink that the driver architecture supports
+ * LPI management, enabling phylink to control EEE advertisement during
+ * negotiation according to IEEE Std 802.3 (Clause 78).
+ *
+ * Hardware Management of EEE/LPI State:
+ * For KSZ switch ports with integrated PHYs (e.g., KSZ9893R ports 1-2),
+ * observation and testing suggest that the actual EEE / Low Power Idle (LPI)
+ * state transitions are managed autonomously by the hardware based on
+ * the auto-negotiation results. (Note: While the datasheet describes EEE
+ * operation based on negotiation, it doesn't explicitly detail the internal
+ * MAC/PHY interaction, so autonomous hardware management of the MAC state
+ * for LPI is inferred from observed behavior).
+ * This hardware control, consistent with the switch's ability to operate
+ * autonomously via strapping, means MAC-level software intervention is not
+ * required or exposed for managing the LPI state once EEE is negotiated.
+ * (Ref: KSZ9893R Data Sheet DS00002420D, primarily Section 4.7.5 explaining
+ * EEE, also Sections 4.1.7 on Auto-Negotiation and 3.2.1 on Configuration
+ * Straps).
+ *
+ * Additionally, ports configured as MAC interfaces (e.g., KSZ9893R port 3)
+ * lack documented MAC-level LPI control.
+ *
+ * Therefore, this callback performs no action and serves primarily to inform
+ * phylink of LPI awareness and to document the inferred hardware behavior.
+ *
+ * Returns: 0 (Always success)
+ */
+static int ksz_phylink_mac_enable_tx_lpi(struct phylink_config *config,
+					 u32 timer, bool tx_clock_stop)
+{
+	return 0;
+}
+
 static const struct phylink_mac_ops ksz88x3_phylink_mac_ops = {
 	.mac_config	= ksz88x3_phylink_mac_config,
 	.mac_link_down	= ksz_phylink_mac_link_down,
 	.mac_link_up	= ksz8_phylink_mac_link_up,
+	.mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
 };
 
 static const struct phylink_mac_ops ksz8_phylink_mac_ops = {
 	.mac_config	= ksz_phylink_mac_config,
 	.mac_link_down	= ksz_phylink_mac_link_down,
 	.mac_link_up	= ksz8_phylink_mac_link_up,
+	.mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
 };
 
 static const struct ksz_dev_ops ksz88xx_dev_ops = {
@@ -354,10 +408,29 @@ static void ksz9477_phylink_mac_link_up(struct phylink_config *config,
 					int speed, int duplex, bool tx_pause,
 					bool rx_pause);
 
+static struct phylink_pcs *
+ksz_phylink_mac_select_pcs(struct phylink_config *config,
+			   phy_interface_t interface)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct ksz_device *dev = dp->ds->priv;
+	struct ksz_port *p = &dev->ports[dp->index];
+
+	if (ksz_is_sgmii_port(dev, dp->index) &&
+	    (interface == PHY_INTERFACE_MODE_SGMII ||
+	    interface == PHY_INTERFACE_MODE_1000BASEX))
+		return p->pcs;
+
+	return NULL;
+}
+
 static const struct phylink_mac_ops ksz9477_phylink_mac_ops = {
 	.mac_config	= ksz_phylink_mac_config,
 	.mac_link_down	= ksz_phylink_mac_link_down,
 	.mac_link_up	= ksz9477_phylink_mac_link_up,
+	.mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
+	.mac_select_pcs	= ksz_phylink_mac_select_pcs,
 };
 
 static const struct ksz_dev_ops ksz9477_dev_ops = {
@@ -395,12 +468,15 @@ static const struct ksz_dev_ops ksz9477_dev_ops = {
 	.reset = ksz9477_reset_switch,
 	.init = ksz9477_switch_init,
 	.exit = ksz9477_switch_exit,
+	.pcs_create = ksz9477_pcs_create,
 };
 
 static const struct phylink_mac_ops lan937x_phylink_mac_ops = {
 	.mac_config	= ksz_phylink_mac_config,
 	.mac_link_down	= ksz_phylink_mac_link_down,
 	.mac_link_up	= ksz9477_phylink_mac_link_up,
+	.mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
 };
 
 static const struct ksz_dev_ops lan937x_dev_ops = {
@@ -1035,8 +1111,7 @@ static const struct regmap_range ksz9477_valid_regs[] = {
 	regmap_reg_range(0x701b, 0x701b),
 	regmap_reg_range(0x701f, 0x7020),
 	regmap_reg_range(0x7030, 0x7030),
-	regmap_reg_range(0x7200, 0x7203),
-	regmap_reg_range(0x7206, 0x7207),
+	regmap_reg_range(0x7200, 0x7207),
 	regmap_reg_range(0x7300, 0x7301),
 	regmap_reg_range(0x7400, 0x7401),
 	regmap_reg_range(0x7403, 0x7403),
@@ -1552,6 +1627,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 				   true, false, false},
 		.gbit_capable	= {true, true, true, true, true, true, true},
 		.ptp_capable = true,
+		.sgmii_port = 7,
 		.wr_table = &ksz9477_register_set,
 		.rd_table = &ksz9477_register_set,
 	},
@@ -1944,6 +2020,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.internal_phy	= {true, true, true, true,
 				   true, false, false},
 		.gbit_capable	= {true, true, true, true, true, true, true},
+		.sgmii_port = 7,
 		.wr_table = &ksz9477_register_set,
 		.rd_table = &ksz9477_register_set,
 	},
@@ -2016,6 +2093,18 @@ static void ksz_phylink_get_caps(struct dsa_switch *ds, int port,
 
 	if (dev->dev_ops->get_caps)
 		dev->dev_ops->get_caps(dev, port, config);
+
+	if (ds->ops->support_eee && ds->ops->support_eee(ds, port)) {
+		memcpy(config->lpi_interfaces, config->supported_interfaces,
+		       sizeof(config->lpi_interfaces));
+
+		config->lpi_capabilities = MAC_100FD;
+		if (dev->info->gbit_capable[port])
+			config->lpi_capabilities |= MAC_1000FD;
+
+		/* EEE is fully operational */
+		config->eee_enabled_default = true;
+	}
 }
 
 void ksz_r_mib_stats64(struct ksz_device *dev, int port)
@@ -2067,7 +2156,7 @@ void ksz_r_mib_stats64(struct ksz_device *dev, int port)
 
 	spin_unlock(&mib->stats64_lock);
 
-	if (dev->info->phy_errata_9477) {
+	if (dev->info->phy_errata_9477 && !ksz_is_sgmii_port(dev, port)) {
 		ret = ksz9477_errata_monitor(dev, port, raw->tx_late_col);
 		if (ret)
 			dev_err(dev->dev, "Failed to monitor transmission halt\n");
@@ -2775,6 +2864,12 @@ static int ksz_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;
 
+	if (ksz_has_sgmii_port(dev) && dev->dev_ops->pcs_create) {
+		ret = dev->dev_ops->pcs_create(dev);
+		if (ret)
+			return ret;
+	}
+
 	/* set broadcast storm protection 10% rate */
 	regmap_update_bits(ksz_regmap_16(dev), regs[S_BROADCAST_CTRL],
 			   BROADCAST_STORM_RATE,
@@ -3008,31 +3103,6 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port)
 		if (!port)
 			return MICREL_KSZ8_P1_ERRATA;
 		break;
-	case KSZ8567_CHIP_ID:
-		/* KSZ8567R Errata DS80000752C Module 4 */
-	case KSZ8765_CHIP_ID:
-	case KSZ8794_CHIP_ID:
-	case KSZ8795_CHIP_ID:
-		/* KSZ879x/KSZ877x/KSZ876x Errata DS80000687C Module 2 */
-	case KSZ9477_CHIP_ID:
-		/* KSZ9477S Errata DS80000754A Module 4 */
-	case KSZ9567_CHIP_ID:
-		/* KSZ9567S Errata DS80000756A Module 4 */
-	case KSZ9896_CHIP_ID:
-		/* KSZ9896C Errata DS80000757A Module 3 */
-	case KSZ9897_CHIP_ID:
-	case LAN9646_CHIP_ID:
-		/* KSZ9897R Errata DS80000758C Module 4 */
-		/* Energy Efficient Ethernet (EEE) feature select must be manually disabled
-		 *   The EEE feature is enabled by default, but it is not fully
-		 *   operational. It must be manually disabled through register
-		 *   controls. If not disabled, the PHY ports can auto-negotiate
-		 *   to enable EEE, and this feature can cause link drops when
-		 *   linked to another device supporting EEE.
-		 *
-		 * The same item appears in the errata for all switches above.
-		 */
-		return MICREL_NO_EEE;
 	}
 
 	return 0;
@@ -3466,6 +3536,20 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port)
 	return -EOPNOTSUPP;
 }
 
+/**
+ * ksz_support_eee - Determine Energy Efficient Ethernet (EEE) support for a
+ *                   port
+ * @ds: Pointer to the DSA switch structure
+ * @port: Port number to check
+ *
+ * This function also documents devices where EEE was initially advertised but
+ * later withdrawn due to reliability issues, as described in official errata
+ * documents. These devices are explicitly listed to record known limitations,
+ * even if there is no technical necessity for runtime checks.
+ *
+ * Returns: true if the internal PHY on the given port supports fully
+ * operational EEE, false otherwise.
+ */
 static bool ksz_support_eee(struct dsa_switch *ds, int port)
 {
 	struct ksz_device *dev = ds->priv;
@@ -3475,15 +3559,35 @@ static bool ksz_support_eee(struct dsa_switch *ds, int port)
 
 	switch (dev->chip_id) {
 	case KSZ8563_CHIP_ID:
+	case KSZ9563_CHIP_ID:
+	case KSZ9893_CHIP_ID:
+		return true;
 	case KSZ8567_CHIP_ID:
+		/* KSZ8567R Errata DS80000752C Module 4 */
+	case KSZ8765_CHIP_ID:
+	case KSZ8794_CHIP_ID:
+	case KSZ8795_CHIP_ID:
+		/* KSZ879x/KSZ877x/KSZ876x Errata DS80000687C Module 2 */
 	case KSZ9477_CHIP_ID:
-	case KSZ9563_CHIP_ID:
+		/* KSZ9477S Errata DS80000754A Module 4 */
 	case KSZ9567_CHIP_ID:
-	case KSZ9893_CHIP_ID:
+		/* KSZ9567S Errata DS80000756A Module 4 */
 	case KSZ9896_CHIP_ID:
+		/* KSZ9896C Errata DS80000757A Module 3 */
 	case KSZ9897_CHIP_ID:
 	case LAN9646_CHIP_ID:
-		return true;
+		/* KSZ9897R Errata DS80000758C Module 4 */
+		/* Energy Efficient Ethernet (EEE) feature select must be
+		 * manually disabled
+		 *   The EEE feature is enabled by default, but it is not fully
+		 *   operational. It must be manually disabled through register
+		 *   controls. If not disabled, the PHY ports can auto-negotiate
+		 *   to enable EEE, and this feature can cause link drops when
+		 *   linked to another device supporting EEE.
+		 *
+		 * The same item appears in the errata for all switches above.
+		 */
+		break;
 	}
 
 	return false;
@@ -3613,6 +3717,10 @@ static void ksz_phylink_mac_config(struct phylink_config *config,
 	if (dev->info->internal_phy[port])
 		return;
 
+	/* No need to configure XMII control register when using SGMII. */
+	if (ksz_is_sgmii_port(dev, port))
+		return;
+
 	if (phylink_autoneg_inband(mode)) {
 		dev_err(dev->dev, "In-band AN not supported!\n");
 		return;
@@ -3999,6 +4107,89 @@ static int ksz_ets_band_to_queue(struct tc_ets_qopt_offload_replace_params *p,
 	return p->bands - 1 - band;
 }
 
+/**
+ * ksz88x3_tc_ets_add - Configure ETS (Enhanced Transmission Selection)
+ *                      for a port on KSZ88x3 switch
+ * @dev: Pointer to the KSZ switch device structure
+ * @port: Port number to configure
+ * @p: Pointer to offload replace parameters describing ETS bands and mapping
+ *
+ * The KSZ88x3 supports two scheduling modes: Strict Priority and
+ * Weighted Fair Queuing (WFQ). Both modes have fixed behavior:
+ *   - No configurable queue-to-priority mapping
+ *   - No weight adjustment in WFQ mode
+ *
+ * This function configures the switch to use strict priority mode by
+ * clearing the WFQ enable bit for all queues associated with ETS bands.
+ * If strict priority is not explicitly requested, the switch will default
+ * to WFQ mode.
+ *
+ * Return: 0 on success, or a negative error code on failure
+ */
+static int ksz88x3_tc_ets_add(struct ksz_device *dev, int port,
+			      struct tc_ets_qopt_offload_replace_params *p)
+{
+	int ret, band;
+
+	/* Only strict priority mode is supported for now.
+	 * WFQ is implicitly enabled when strict mode is disabled.
+	 */
+	for (band = 0; band < p->bands; band++) {
+		int queue = ksz_ets_band_to_queue(p, band);
+		u8 reg;
+
+		/* Calculate TXQ Split Control register address for this
+		 * port/queue
+		 */
+		reg = KSZ8873_TXQ_SPLIT_CTRL_REG(port, queue);
+
+		/* Clear WFQ enable bit to select strict priority scheduling */
+		ret = ksz_rmw8(dev, reg, KSZ8873_TXQ_WFQ_ENABLE, 0);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * ksz88x3_tc_ets_del - Reset ETS (Enhanced Transmission Selection) config
+ *                      for a port on KSZ88x3 switch
+ * @dev: Pointer to the KSZ switch device structure
+ * @port: Port number to reset
+ *
+ * The KSZ88x3 supports only fixed scheduling modes: Strict Priority or
+ * Weighted Fair Queuing (WFQ), with no reconfiguration of weights or
+ * queue mapping. This function resets the port’s scheduling mode to
+ * the default, which is WFQ, by enabling the WFQ bit for all queues.
+ *
+ * Return: 0 on success, or a negative error code on failure
+ */
+static int ksz88x3_tc_ets_del(struct ksz_device *dev, int port)
+{
+	int ret, queue;
+
+	/* Iterate over all transmit queues for this port */
+	for (queue = 0; queue < dev->info->num_tx_queues; queue++) {
+		u8 reg;
+
+		/* Calculate TXQ Split Control register address for this
+		 * port/queue
+		 */
+		reg = KSZ8873_TXQ_SPLIT_CTRL_REG(port, queue);
+
+		/* Set WFQ enable bit to revert back to default scheduling
+		 * mode
+		 */
+		ret = ksz_rmw8(dev, reg, KSZ8873_TXQ_WFQ_ENABLE,
+			       KSZ8873_TXQ_WFQ_ENABLE);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int ksz_queue_set_strict(struct ksz_device *dev, int port, int queue)
 {
 	int ret;
@@ -4080,6 +4271,7 @@ static int ksz_tc_ets_del(struct ksz_device *dev, int port)
 	for (queue = 0; queue < dev->info->num_tx_queues; queue++) {
 		ret = ksz_queue_set_wrr(dev, port, queue,
 					KSZ9477_DEFAULT_WRR_WEIGHT);
+
 		if (ret)
 			return ret;
 	}
@@ -4132,7 +4324,7 @@ static int ksz_tc_setup_qdisc_ets(struct dsa_switch *ds, int port,
 	struct ksz_device *dev = ds->priv;
 	int ret;
 
-	if (is_ksz8(dev))
+	if (is_ksz8(dev) && !ksz_is_ksz88x3(dev))
 		return -EOPNOTSUPP;
 
 	if (qopt->parent != TC_H_ROOT) {
@@ -4146,9 +4338,16 @@ static int ksz_tc_setup_qdisc_ets(struct dsa_switch *ds, int port,
 		if (ret)
 			return ret;
 
-		return ksz_tc_ets_add(dev, port, &qopt->replace_params);
+		if (ksz_is_ksz88x3(dev))
+			return ksz88x3_tc_ets_add(dev, port,
+						  &qopt->replace_params);
+		else
+			return ksz_tc_ets_add(dev, port, &qopt->replace_params);
 	case TC_ETS_DESTROY:
-		return ksz_tc_ets_del(dev, port);
+		if (ksz_is_ksz88x3(dev))
+			return ksz88x3_tc_ets_del(dev, port);
+		else
+			return ksz_tc_ets_del(dev, port);
 	case TC_ETS_STATS:
 	case TC_ETS_GRAFT:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index af17a9c030d4..a08417df2ca4 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Microchip switch driver common header
  *
- * Copyright (C) 2017-2024 Microchip Technology Inc.
+ * Copyright (C) 2017-2025 Microchip Technology Inc.
  */
 
 #ifndef __KSZ_COMMON_H
@@ -10,6 +10,7 @@
 #include <linux/etherdevice.h>
 #include <linux/kernel.h>
 #include <linux/mutex.h>
+#include <linux/pcs/pcs-xpcs.h>
 #include <linux/phy.h>
 #include <linux/regmap.h>
 #include <net/dsa.h>
@@ -93,6 +94,7 @@ struct ksz_chip_data {
 	bool internal_phy[KSZ_MAX_NUM_PORTS];
 	bool gbit_capable[KSZ_MAX_NUM_PORTS];
 	bool ptp_capable;
+	u8 sgmii_port;
 	const struct regmap_access_table *wr_table;
 	const struct regmap_access_table *rd_table;
 };
@@ -132,6 +134,7 @@ struct ksz_port {
 	u32 force:1;
 	u32 read:1;			/* read MIB counters in background */
 	u32 freeze:1;			/* MIB counter freeze is enabled */
+	u32 sgmii_adv_write:1;
 
 	struct ksz_port_mib mib;
 	phy_interface_t interface;
@@ -141,8 +144,9 @@ struct ksz_port {
 	void *acl_priv;
 	struct ksz_irq pirq;
 	u8 num;
+	struct phylink_pcs *pcs;
 #if IS_ENABLED(CONFIG_NET_DSA_MICROCHIP_KSZ_PTP)
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 	bool hwts_tx_en;
 	bool hwts_rx_en;
 	struct ksz_irq ptpirq;
@@ -440,6 +444,8 @@ struct ksz_dev_ops {
 	int (*reset)(struct ksz_device *dev);
 	int (*init)(struct ksz_device *dev);
 	void (*exit)(struct ksz_device *dev);
+
+	int (*pcs_create)(struct ksz_device *dev);
 };
 
 struct ksz_device *ksz_switch_alloc(struct device *base, void *priv);
@@ -731,6 +737,21 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 		dev->chip_id == LAN9372_CHIP_ID) && port == KSZ_PORT_4;
 }
 
+static inline int ksz_get_sgmii_port(struct ksz_device *dev)
+{
+	return dev->info->sgmii_port - 1;
+}
+
+static inline bool ksz_has_sgmii_port(struct ksz_device *dev)
+{
+	return dev->info->sgmii_port > 0;
+}
+
+static inline bool ksz_is_sgmii_port(struct ksz_device *dev, int port)
+{
+	return dev->info->sgmii_port == port + 1;
+}
+
 /* STP State Defines */
 #define PORT_TX_ENABLE			BIT(2)
 #define PORT_RX_ENABLE			BIT(1)
@@ -836,6 +857,25 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 #define SW_HI_SPEED_DRIVE_STRENGTH_S	4
 #define SW_LO_SPEED_DRIVE_STRENGTH_S	0
 
+/* TXQ Split Control Register for per-port, per-queue configuration.
+ * Register 0xAF is TXQ Split for Q3 on Port 1.
+ * Register offset formula: 0xAF + (port * 4) + (3 - queue)
+ *   where: port = 0..2, queue = 0..3
+ */
+#define KSZ8873_TXQ_SPLIT_CTRL_REG(port, queue) \
+	(0xAF + ((port) * 4) + (3 - (queue)))
+
+/* Bit 7 selects between:
+ *   0 = Strict priority mode (highest-priority queue first)
+ *   1 = Weighted Fair Queuing (WFQ) mode:
+ *       Queue weights: Q3:Q2:Q1:Q0 = 8:4:2:1
+ *       If any queues are empty, weight is redistributed.
+ *
+ * Note: This is referred to as "Weighted Fair Queuing" (WFQ) in KSZ8863/8873
+ * documentation, and as "Weighted Round Robin" (WRR) in KSZ9477 family docs.
+ */
+#define KSZ8873_TXQ_WFQ_ENABLE		BIT(7)
+
 #define KSZ9477_REG_PORT_OUT_RATE_0	0x0420
 #define KSZ9477_OUT_RATE_NO_LIMIT	0
 
diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c
index 22fb9ef4645c..bc54a96ba646 100644
--- a/drivers/net/dsa/microchip/ksz_ptp.c
+++ b/drivers/net/dsa/microchip/ksz_ptp.c
@@ -319,22 +319,21 @@ int ksz_get_ts_info(struct dsa_switch *ds, int port, struct kernel_ethtool_ts_in
 	return 0;
 }
 
-int ksz_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr)
+int ksz_hwtstamp_get(struct dsa_switch *ds, int port,
+		     struct kernel_hwtstamp_config *config)
 {
 	struct ksz_device *dev = ds->priv;
-	struct hwtstamp_config *config;
 	struct ksz_port *prt;
 
 	prt = &dev->ports[port];
-	config = &prt->tstamp_config;
+	*config = prt->tstamp_config;
 
-	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 static int ksz_set_hwtstamp_config(struct ksz_device *dev,
 				   struct ksz_port *prt,
-				   struct hwtstamp_config *config)
+				   struct kernel_hwtstamp_config *config)
 {
 	int ret;
 
@@ -404,26 +403,21 @@ static int ksz_set_hwtstamp_config(struct ksz_device *dev,
 	return ksz_ptp_enable_mode(dev);
 }
 
-int ksz_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr)
+int ksz_hwtstamp_set(struct dsa_switch *ds, int port,
+		     struct kernel_hwtstamp_config *config,
+		     struct netlink_ext_ack *extack)
 {
 	struct ksz_device *dev = ds->priv;
-	struct hwtstamp_config config;
 	struct ksz_port *prt;
 	int ret;
 
 	prt = &dev->ports[port];
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	ret = ksz_set_hwtstamp_config(dev, prt, &config);
+	ret = ksz_set_hwtstamp_config(dev, prt, config);
 	if (ret)
 		return ret;
 
-	memcpy(&prt->tstamp_config, &config, sizeof(config));
-
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	prt->tstamp_config = *config;
 
 	return 0;
 }
diff --git a/drivers/net/dsa/microchip/ksz_ptp.h b/drivers/net/dsa/microchip/ksz_ptp.h
index 2f1783c0d723..3086e519b1b6 100644
--- a/drivers/net/dsa/microchip/ksz_ptp.h
+++ b/drivers/net/dsa/microchip/ksz_ptp.h
@@ -39,8 +39,11 @@ void ksz_ptp_clock_unregister(struct dsa_switch *ds);
 
 int ksz_get_ts_info(struct dsa_switch *ds, int port,
 		    struct kernel_ethtool_ts_info *ts);
-int ksz_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr);
-int ksz_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr);
+int ksz_hwtstamp_get(struct dsa_switch *ds, int port,
+		     struct kernel_hwtstamp_config *config);
+int ksz_hwtstamp_set(struct dsa_switch *ds, int port,
+		     struct kernel_hwtstamp_config *config,
+		     struct netlink_ext_ack *extack);
 void ksz_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb);
 void ksz_port_deferred_xmit(struct kthread_work *work);
 bool ksz_port_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb,
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index d70399bce5b9..7361380ffb5f 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -32,47 +32,15 @@ static struct mt753x_pcs *pcs_to_mt753x_pcs(struct phylink_pcs *pcs)
 
 /* String, offset, and register size in bytes if different from 4 bytes */
 static const struct mt7530_mib_desc mt7530_mib[] = {
-	MIB_DESC(1, 0x00, "TxDrop"),
-	MIB_DESC(1, 0x04, "TxCrcErr"),
-	MIB_DESC(1, 0x08, "TxUnicast"),
-	MIB_DESC(1, 0x0c, "TxMulticast"),
-	MIB_DESC(1, 0x10, "TxBroadcast"),
-	MIB_DESC(1, 0x14, "TxCollision"),
-	MIB_DESC(1, 0x18, "TxSingleCollision"),
-	MIB_DESC(1, 0x1c, "TxMultipleCollision"),
-	MIB_DESC(1, 0x20, "TxDeferred"),
-	MIB_DESC(1, 0x24, "TxLateCollision"),
-	MIB_DESC(1, 0x28, "TxExcessiveCollistion"),
-	MIB_DESC(1, 0x2c, "TxPause"),
-	MIB_DESC(1, 0x30, "TxPktSz64"),
-	MIB_DESC(1, 0x34, "TxPktSz65To127"),
-	MIB_DESC(1, 0x38, "TxPktSz128To255"),
-	MIB_DESC(1, 0x3c, "TxPktSz256To511"),
-	MIB_DESC(1, 0x40, "TxPktSz512To1023"),
-	MIB_DESC(1, 0x44, "Tx1024ToMax"),
-	MIB_DESC(2, 0x48, "TxBytes"),
-	MIB_DESC(1, 0x60, "RxDrop"),
-	MIB_DESC(1, 0x64, "RxFiltering"),
-	MIB_DESC(1, 0x68, "RxUnicast"),
-	MIB_DESC(1, 0x6c, "RxMulticast"),
-	MIB_DESC(1, 0x70, "RxBroadcast"),
-	MIB_DESC(1, 0x74, "RxAlignErr"),
-	MIB_DESC(1, 0x78, "RxCrcErr"),
-	MIB_DESC(1, 0x7c, "RxUnderSizeErr"),
-	MIB_DESC(1, 0x80, "RxFragErr"),
-	MIB_DESC(1, 0x84, "RxOverSzErr"),
-	MIB_DESC(1, 0x88, "RxJabberErr"),
-	MIB_DESC(1, 0x8c, "RxPause"),
-	MIB_DESC(1, 0x90, "RxPktSz64"),
-	MIB_DESC(1, 0x94, "RxPktSz65To127"),
-	MIB_DESC(1, 0x98, "RxPktSz128To255"),
-	MIB_DESC(1, 0x9c, "RxPktSz256To511"),
-	MIB_DESC(1, 0xa0, "RxPktSz512To1023"),
-	MIB_DESC(1, 0xa4, "RxPktSz1024ToMax"),
-	MIB_DESC(2, 0xa8, "RxBytes"),
-	MIB_DESC(1, 0xb0, "RxCtrlDrop"),
-	MIB_DESC(1, 0xb4, "RxIngressDrop"),
-	MIB_DESC(1, 0xb8, "RxArlDrop"),
+	MIB_DESC(1, MT7530_PORT_MIB_TX_DROP, "TxDrop"),
+	MIB_DESC(1, MT7530_PORT_MIB_TX_CRC_ERR, "TxCrcErr"),
+	MIB_DESC(1, MT7530_PORT_MIB_TX_COLLISION, "TxCollision"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_DROP, "RxDrop"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_FILTERING, "RxFiltering"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_CRC_ERR, "RxCrcErr"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_CTRL_DROP, "RxCtrlDrop"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_INGRESS_DROP, "RxIngressDrop"),
+	MIB_DESC(1, MT7530_PORT_MIB_RX_ARL_DROP, "RxArlDrop"),
 };
 
 static void
@@ -790,23 +758,33 @@ mt7530_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 }
 
 static void
+mt7530_read_port_stats(struct mt7530_priv *priv, int port,
+		       u32 offset, u8 size, uint64_t *data)
+{
+	u32 val, reg = MT7530_PORT_MIB_COUNTER(port) + offset;
+
+	val = mt7530_read(priv, reg);
+	*data = val;
+
+	if (size == 2) {
+		val = mt7530_read(priv, reg + 4);
+		*data |= (u64)val << 32;
+	}
+}
+
+static void
 mt7530_get_ethtool_stats(struct dsa_switch *ds, int port,
 			 uint64_t *data)
 {
 	struct mt7530_priv *priv = ds->priv;
 	const struct mt7530_mib_desc *mib;
-	u32 reg, i;
-	u64 hi;
+	int i;
 
 	for (i = 0; i < ARRAY_SIZE(mt7530_mib); i++) {
 		mib = &mt7530_mib[i];
-		reg = MT7530_PORT_MIB_COUNTER(port) + mib->offset;
 
-		data[i] = mt7530_read(priv, reg);
-		if (mib->size == 2) {
-			hi = mt7530_read(priv, reg + 4);
-			data[i] |= hi << 32;
-		}
+		mt7530_read_port_stats(priv, port, mib->offset, mib->size,
+				       data + i);
 	}
 }
 
@@ -819,6 +797,172 @@ mt7530_get_sset_count(struct dsa_switch *ds, int port, int sset)
 	return ARRAY_SIZE(mt7530_mib);
 }
 
+static void mt7530_get_eth_mac_stats(struct dsa_switch *ds, int port,
+				     struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	/* MIB counter doesn't provide a FramesTransmittedOK but instead
+	 * provide stats for Unicast, Broadcast and Multicast frames separately.
+	 * To simulate a global frame counter, read Unicast and addition Multicast
+	 * and Broadcast later
+	 */
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_UNICAST, 1,
+			       &mac_stats->FramesTransmittedOK);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_SINGLE_COLLISION, 1,
+			       &mac_stats->SingleCollisionFrames);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_MULTIPLE_COLLISION, 1,
+			       &mac_stats->MultipleCollisionFrames);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_UNICAST, 1,
+			       &mac_stats->FramesReceivedOK);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_BYTES, 2,
+			       &mac_stats->OctetsTransmittedOK);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_ALIGN_ERR, 1,
+			       &mac_stats->AlignmentErrors);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_DEFERRED, 1,
+			       &mac_stats->FramesWithDeferredXmissions);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_LATE_COLLISION, 1,
+			       &mac_stats->LateCollisions);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_EXCESSIVE_COLLISION, 1,
+			       &mac_stats->FramesAbortedDueToXSColls);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_BYTES, 2,
+			       &mac_stats->OctetsReceivedOK);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_MULTICAST, 1,
+			       &mac_stats->MulticastFramesXmittedOK);
+	mac_stats->FramesTransmittedOK += mac_stats->MulticastFramesXmittedOK;
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_BROADCAST, 1,
+			       &mac_stats->BroadcastFramesXmittedOK);
+	mac_stats->FramesTransmittedOK += mac_stats->BroadcastFramesXmittedOK;
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_MULTICAST, 1,
+			       &mac_stats->MulticastFramesReceivedOK);
+	mac_stats->FramesReceivedOK += mac_stats->MulticastFramesReceivedOK;
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_BROADCAST, 1,
+			       &mac_stats->BroadcastFramesReceivedOK);
+	mac_stats->FramesReceivedOK += mac_stats->BroadcastFramesReceivedOK;
+}
+
+static const struct ethtool_rmon_hist_range mt7530_rmon_ranges[] = {
+	{ 0, 64 },
+	{ 65, 127 },
+	{ 128, 255 },
+	{ 256, 511 },
+	{ 512, 1023 },
+	{ 1024, MT7530_MAX_MTU },
+	{}
+};
+
+static void mt7530_get_rmon_stats(struct dsa_switch *ds, int port,
+				  struct ethtool_rmon_stats *rmon_stats,
+				  const struct ethtool_rmon_hist_range **ranges)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_UNDER_SIZE_ERR, 1,
+			       &rmon_stats->undersize_pkts);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_OVER_SZ_ERR, 1,
+			       &rmon_stats->oversize_pkts);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_FRAG_ERR, 1,
+			       &rmon_stats->fragments);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_JABBER_ERR, 1,
+			       &rmon_stats->jabbers);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_64, 1,
+			       &rmon_stats->hist[0]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_65_TO_127, 1,
+			       &rmon_stats->hist[1]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_128_TO_255, 1,
+			       &rmon_stats->hist[2]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_256_TO_511, 1,
+			       &rmon_stats->hist[3]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_512_TO_1023, 1,
+			       &rmon_stats->hist[4]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PKT_SZ_1024_TO_MAX, 1,
+			       &rmon_stats->hist[5]);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_64, 1,
+			       &rmon_stats->hist_tx[0]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_65_TO_127, 1,
+			       &rmon_stats->hist_tx[1]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_128_TO_255, 1,
+			       &rmon_stats->hist_tx[2]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_256_TO_511, 1,
+			       &rmon_stats->hist_tx[3]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_512_TO_1023, 1,
+			       &rmon_stats->hist_tx[4]);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PKT_SZ_1024_TO_MAX, 1,
+			       &rmon_stats->hist_tx[5]);
+
+	*ranges = mt7530_rmon_ranges;
+}
+
+static void mt7530_get_stats64(struct dsa_switch *ds, int port,
+			       struct rtnl_link_stats64 *storage)
+{
+	struct mt7530_priv *priv = ds->priv;
+	uint64_t data;
+
+	/* MIB counter doesn't provide a FramesTransmittedOK but instead
+	 * provide stats for Unicast, Broadcast and Multicast frames separately.
+	 * To simulate a global frame counter, read Unicast and addition Multicast
+	 * and Broadcast later
+	 */
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_UNICAST, 1,
+			       &storage->rx_packets);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_MULTICAST, 1,
+			       &storage->multicast);
+	storage->rx_packets += storage->multicast;
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_BROADCAST, 1,
+			       &data);
+	storage->rx_packets += data;
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_UNICAST, 1,
+			       &storage->tx_packets);
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_MULTICAST, 1,
+			       &data);
+	storage->tx_packets += data;
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_BROADCAST, 1,
+			       &data);
+	storage->tx_packets += data;
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_BYTES, 2,
+			       &storage->rx_bytes);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_BYTES, 2,
+			       &storage->tx_bytes);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_DROP, 1,
+			       &storage->rx_dropped);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_DROP, 1,
+			       &storage->tx_dropped);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_CRC_ERR, 1,
+			       &storage->rx_crc_errors);
+}
+
+static void mt7530_get_eth_ctrl_stats(struct dsa_switch *ds, int port,
+				      struct ethtool_eth_ctrl_stats *ctrl_stats)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_TX_PAUSE, 1,
+			       &ctrl_stats->MACControlFramesTransmitted);
+
+	mt7530_read_port_stats(priv, port, MT7530_PORT_MIB_RX_PAUSE, 1,
+			       &ctrl_stats->MACControlFramesReceived);
+}
+
 static int
 mt7530_set_ageing_time(struct dsa_switch *ds, unsigned int msecs)
 {
@@ -2419,6 +2563,9 @@ mt7531_setup_common(struct dsa_switch *ds)
 	struct mt7530_priv *priv = ds->priv;
 	int ret, i;
 
+	ds->assisted_learning_on_cpu_port = true;
+	ds->mtu_enforcement_ingress = true;
+
 	mt753x_trap_frames(priv);
 
 	/* Enable and reset MIB counters */
@@ -2571,9 +2718,6 @@ mt7531_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;
 
-	ds->assisted_learning_on_cpu_port = true;
-	ds->mtu_enforcement_ingress = true;
-
 	return 0;
 }
 
@@ -3105,6 +3249,10 @@ const struct dsa_switch_ops mt7530_switch_ops = {
 	.get_strings		= mt7530_get_strings,
 	.get_ethtool_stats	= mt7530_get_ethtool_stats,
 	.get_sset_count		= mt7530_get_sset_count,
+	.get_eth_mac_stats	= mt7530_get_eth_mac_stats,
+	.get_rmon_stats		= mt7530_get_rmon_stats,
+	.get_eth_ctrl_stats	= mt7530_get_eth_ctrl_stats,
+	.get_stats64		= mt7530_get_stats64,
 	.set_ageing_time	= mt7530_set_ageing_time,
 	.port_enable		= mt7530_port_enable,
 	.port_disable		= mt7530_port_disable,
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index c3ea403d7acf..d4b838a055ad 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -423,6 +423,48 @@ enum mt7530_vlan_port_acc_frm {
 
 /* Register for MIB */
 #define MT7530_PORT_MIB_COUNTER(x)	(0x4000 + (x) * 0x100)
+/* Each define is an offset of MT7530_PORT_MIB_COUNTER */
+#define   MT7530_PORT_MIB_TX_DROP	0x00
+#define   MT7530_PORT_MIB_TX_CRC_ERR	0x04
+#define   MT7530_PORT_MIB_TX_UNICAST	0x08
+#define   MT7530_PORT_MIB_TX_MULTICAST	0x0c
+#define   MT7530_PORT_MIB_TX_BROADCAST	0x10
+#define   MT7530_PORT_MIB_TX_COLLISION	0x14
+#define   MT7530_PORT_MIB_TX_SINGLE_COLLISION 0x18
+#define   MT7530_PORT_MIB_TX_MULTIPLE_COLLISION 0x1c
+#define   MT7530_PORT_MIB_TX_DEFERRED	0x20
+#define   MT7530_PORT_MIB_TX_LATE_COLLISION 0x24
+#define   MT7530_PORT_MIB_TX_EXCESSIVE_COLLISION 0x28
+#define   MT7530_PORT_MIB_TX_PAUSE	0x2c
+#define   MT7530_PORT_MIB_TX_PKT_SZ_64	0x30
+#define   MT7530_PORT_MIB_TX_PKT_SZ_65_TO_127 0x34
+#define   MT7530_PORT_MIB_TX_PKT_SZ_128_TO_255 0x38
+#define   MT7530_PORT_MIB_TX_PKT_SZ_256_TO_511 0x3c
+#define   MT7530_PORT_MIB_TX_PKT_SZ_512_TO_1023 0x40
+#define   MT7530_PORT_MIB_TX_PKT_SZ_1024_TO_MAX 0x44
+#define   MT7530_PORT_MIB_TX_BYTES	0x48 /* 64 bytes */
+#define   MT7530_PORT_MIB_RX_DROP	0x60
+#define   MT7530_PORT_MIB_RX_FILTERING	0x64
+#define   MT7530_PORT_MIB_RX_UNICAST	0x68
+#define   MT7530_PORT_MIB_RX_MULTICAST	0x6c
+#define   MT7530_PORT_MIB_RX_BROADCAST	0x70
+#define   MT7530_PORT_MIB_RX_ALIGN_ERR	0x74
+#define   MT7530_PORT_MIB_RX_CRC_ERR	0x78
+#define   MT7530_PORT_MIB_RX_UNDER_SIZE_ERR 0x7c
+#define   MT7530_PORT_MIB_RX_FRAG_ERR	0x80
+#define   MT7530_PORT_MIB_RX_OVER_SZ_ERR 0x84
+#define   MT7530_PORT_MIB_RX_JABBER_ERR	0x88
+#define   MT7530_PORT_MIB_RX_PAUSE	0x8c
+#define   MT7530_PORT_MIB_RX_PKT_SZ_64	0x90
+#define   MT7530_PORT_MIB_RX_PKT_SZ_65_TO_127 0x94
+#define   MT7530_PORT_MIB_RX_PKT_SZ_128_TO_255 0x98
+#define   MT7530_PORT_MIB_RX_PKT_SZ_256_TO_511 0x9c
+#define   MT7530_PORT_MIB_RX_PKT_SZ_512_TO_1023 0xa0
+#define   MT7530_PORT_MIB_RX_PKT_SZ_1024_TO_MAX 0xa4
+#define   MT7530_PORT_MIB_RX_BYTES	0xa8 /* 64 bytes */
+#define   MT7530_PORT_MIB_RX_CTRL_DROP	0xb0
+#define   MT7530_PORT_MIB_RX_INGRESS_DROP 0xb4
+#define   MT7530_PORT_MIB_RX_ARL_DROP	0xb8
 #define MT7530_MIB_CCR			0x4fe0
 #define  CCR_MIB_ENABLE			BIT(31)
 #define  CCR_RX_OCT_CNT_GOOD		BIT(7)
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 29a89ab4b789..08db846cda8d 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -1852,6 +1852,8 @@ static int mv88e6xxx_vtu_get(struct mv88e6xxx_chip *chip, u16 vid,
 	if (!chip->info->ops->vtu_getnext)
 		return -EOPNOTSUPP;
 
+	memset(entry, 0, sizeof(*entry));
+
 	entry->vid = vid ? vid - 1 : mv88e6xxx_max_vid(chip);
 	entry->valid = false;
 
@@ -1960,7 +1962,16 @@ static int mv88e6xxx_mst_put(struct mv88e6xxx_chip *chip, u8 sid)
 	struct mv88e6xxx_mst *mst, *tmp;
 	int err;
 
-	if (!sid)
+	/* If the SID is zero, it is for a VLAN mapped to the default MSTI,
+	 * and mv88e6xxx_stu_setup() made sure it is always present, and thus,
+	 * should not be removed here.
+	 *
+	 * If the chip lacks STU support, numerically the "sid" variable will
+	 * happen to also be zero, but we don't want to rely on that fact, so
+	 * we explicitly test that first. In that case, there is also nothing
+	 * to do here.
+	 */
+	if (!mv88e6xxx_has_stu(chip) || !sid)
 		return 0;
 
 	list_for_each_entry_safe(mst, tmp, &chip->msts, node) {
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 86bf113c9bfa..7d00482f53a3 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -241,7 +241,7 @@ struct mv88e6xxx_port_hwtstamp {
 	u16 tx_seq_id;
 
 	/* Current timestamp configuration */
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 };
 
 enum mv88e6xxx_policy_mapping {
diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c
index 795c8df7b6a7..195460a0a0d4 100644
--- a/drivers/net/dsa/mv88e6xxx/devlink.c
+++ b/drivers/net/dsa/mv88e6xxx/devlink.c
@@ -736,7 +736,8 @@ void mv88e6xxx_teardown_devlink_regions_global(struct dsa_switch *ds)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(mv88e6xxx_regions); i++)
-		dsa_devlink_region_destroy(chip->regions[i]);
+		if (chip->regions[i])
+			dsa_devlink_region_destroy(chip->regions[i]);
 }
 
 void mv88e6xxx_teardown_devlink_regions_port(struct dsa_switch *ds, int port)
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
index 49e6e1355142..f663799b0b3b 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
@@ -89,7 +89,7 @@ int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 }
 
 static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port,
-					 struct hwtstamp_config *config)
+					 struct kernel_hwtstamp_config *config)
 {
 	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port];
@@ -169,42 +169,38 @@ static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port,
 }
 
 int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, int port,
-				struct ifreq *ifr)
+				struct kernel_hwtstamp_config *config,
+				struct netlink_ext_ack *extack)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
 	struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port];
-	struct hwtstamp_config config;
 	int err;
 
 	if (!chip->info->ptp_support)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = mv88e6xxx_set_hwtstamp_config(chip, port, &config);
+	err = mv88e6xxx_set_hwtstamp_config(chip, port, config);
 	if (err)
 		return err;
 
 	/* Save the chosen configuration to be returned later. */
-	memcpy(&ps->tstamp_config, &config, sizeof(config));
+	ps->tstamp_config = *config;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port,
-				struct ifreq *ifr)
+				struct kernel_hwtstamp_config *config)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
 	struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port];
-	struct hwtstamp_config *config = &ps->tstamp_config;
 
 	if (!chip->info->ptp_support)
 		return -EOPNOTSUPP;
 
-	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
-		-EFAULT : 0;
+	*config = ps->tstamp_config;
+
+	return 0;
 }
 
 /* Returns a pointer to the PTP header if the caller should time stamp,
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.h b/drivers/net/dsa/mv88e6xxx/hwtstamp.h
index 85acc758e3eb..22e4acc957f0 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.h
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.h
@@ -111,9 +111,10 @@
 #ifdef CONFIG_NET_DSA_MV88E6XXX_PTP
 
 int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, int port,
-				struct ifreq *ifr);
+				struct kernel_hwtstamp_config *cfg,
+				struct netlink_ext_ack *extack);
 int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port,
-				struct ifreq *ifr);
+				struct kernel_hwtstamp_config *cfg);
 
 bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port,
 			     struct sk_buff *clone, unsigned int type);
@@ -132,14 +133,17 @@ int mv88e6165_global_disable(struct mv88e6xxx_chip *chip);
 
 #else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */
 
-static inline int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds,
-					      int port, struct ifreq *ifr)
+static inline int
+mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, int port,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds,
-					      int port, struct ifreq *ifr)
+static inline int
+mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port,
+			    struct kernel_hwtstamp_config *config)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c
index aed4a4b07f34..1d3b2c94c53e 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.c
+++ b/drivers/net/dsa/mv88e6xxx/ptp.c
@@ -332,13 +332,6 @@ static int mv88e6352_ptp_enable_extts(struct mv88e6xxx_chip *chip,
 	int pin;
 	int err;
 
-	/* Reject requests with unsupported flags */
-	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-				PTP_RISING_EDGE |
-				PTP_FALLING_EDGE |
-				PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	/* Reject requests to enable time stamping on both edges. */
 	if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 	    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -566,6 +559,10 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
 	chip->ptp_clock_info.verify	= ptp_ops->ptp_verify;
 	chip->ptp_clock_info.do_aux_work = mv88e6xxx_hwtstamp_work;
 
+	chip->ptp_clock_info.supported_extts_flags = PTP_RISING_EDGE |
+						     PTP_FALLING_EDGE |
+						     PTP_STRICT_FLAGS;
+
 	if (ptp_ops->set_ptp_cpu_port) {
 		struct dsa_port *dp;
 		int upstream = 0;
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 0a4e682a55ef..2dd4e56e1cf1 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -1774,22 +1774,25 @@ static void felix_teardown(struct dsa_switch *ds)
 }
 
 static int felix_hwtstamp_get(struct dsa_switch *ds, int port,
-			      struct ifreq *ifr)
+			      struct kernel_hwtstamp_config *config)
 {
 	struct ocelot *ocelot = ds->priv;
 
-	return ocelot_hwstamp_get(ocelot, port, ifr);
+	ocelot_hwstamp_get(ocelot, port, config);
+
+	return 0;
 }
 
 static int felix_hwtstamp_set(struct dsa_switch *ds, int port,
-			      struct ifreq *ifr)
+			      struct kernel_hwtstamp_config *config,
+			      struct netlink_ext_ack *extack)
 {
 	struct ocelot *ocelot = ds->priv;
 	struct felix *felix = ocelot_to_felix(ocelot);
 	bool using_tag_8021q;
 	int err;
 
-	err = ocelot_hwstamp_set(ocelot, port, ifr);
+	err = ocelot_hwstamp_set(ocelot, port, config, extack);
 	if (err)
 		return err;
 
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 940f1b71226d..7b35d24c38d7 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1543,7 +1543,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 	struct tc_taprio_qopt_offload *taprio;
 	struct ocelot_port *ocelot_port;
 	struct timespec64 base_ts;
-	int port;
+	int i, port;
 	u32 val;
 
 	mutex_lock(&ocelot->fwd_domain_lock);
@@ -1575,6 +1575,9 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 			   QSYS_PARAM_CFG_REG_3_BASE_TIME_SEC_MSB_M,
 			   QSYS_PARAM_CFG_REG_3);
 
+		for (i = 0; i < taprio->num_entries; i++)
+			vsc9959_tas_gcl_set(ocelot, i, &taprio->entries[i]);
+
 		ocelot_rmw(ocelot, QSYS_TAS_PARAM_CFG_CTRL_CONFIG_CHANGE,
 			   QSYS_TAS_PARAM_CFG_CTRL_CONFIG_CHANGE,
 			   QSYS_TAS_PARAM_CFG_CTRL);
diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c
index 31ea8130a495..df7466d4fe8f 100644
--- a/drivers/net/dsa/rzn1_a5psw.c
+++ b/drivers/net/dsa/rzn1_a5psw.c
@@ -337,8 +337,9 @@ static void a5psw_port_rx_block_set(struct a5psw *a5psw, int port, bool block)
 static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port,
 					  bool set)
 {
-	u8 offsets[] = {A5PSW_UCAST_DEF_MASK, A5PSW_BCAST_DEF_MASK,
-			A5PSW_MCAST_DEF_MASK};
+	static const u8 offsets[] = {
+		A5PSW_UCAST_DEF_MASK, A5PSW_BCAST_DEF_MASK, A5PSW_MCAST_DEF_MASK
+	};
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(offsets); i++)
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index f8454f3b6f9c..f674c400f05b 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2081,6 +2081,7 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port,
 	switch (state) {
 	case BR_STATE_DISABLED:
 	case BR_STATE_BLOCKING:
+	case BR_STATE_LISTENING:
 		/* From UM10944 description of DRPDTAG (why put this there?):
 		 * "Management traffic flows to the port regardless of the state
 		 * of the INGRESS flag". So BPDUs are still be allowed to pass.
@@ -2090,11 +2091,6 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port,
 		mac[port].egress    = false;
 		mac[port].dyn_learn = false;
 		break;
-	case BR_STATE_LISTENING:
-		mac[port].ingress   = true;
-		mac[port].egress    = false;
-		mac[port].dyn_learn = false;
-		break;
 	case BR_STATE_LEARNING:
 		mac[port].ingress   = true;
 		mac[port].egress    = false;
diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c
index 198e787e8560..fefe46e2a5e6 100644
--- a/drivers/net/dsa/sja1105/sja1105_ptp.c
+++ b/drivers/net/dsa/sja1105/sja1105_ptp.c
@@ -58,19 +58,17 @@ enum sja1105_ptp_clk_mode {
 #define ptp_data_to_sja1105(d) \
 		container_of((d), struct sja1105_private, ptp_data)
 
-int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr)
+int sja1105_hwtstamp_set(struct dsa_switch *ds, int port,
+			 struct kernel_hwtstamp_config *config,
+			 struct netlink_ext_ack *extack)
 {
 	struct sja1105_private *priv = ds->priv;
 	unsigned long hwts_tx_en, hwts_rx_en;
-	struct hwtstamp_config config;
-
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
 
 	hwts_tx_en = priv->hwts_tx_en;
 	hwts_rx_en = priv->hwts_rx_en;
 
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		hwts_tx_en &= ~BIT(port);
 		break;
@@ -81,7 +79,7 @@ int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		hwts_rx_en &= ~BIT(port);
 		break;
@@ -92,32 +90,28 @@ int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
-
 	priv->hwts_tx_en = hwts_tx_en;
 	priv->hwts_rx_en = hwts_rx_en;
 
 	return 0;
 }
 
-int sja1105_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr)
+int sja1105_hwtstamp_get(struct dsa_switch *ds, int port,
+			 struct kernel_hwtstamp_config *config)
 {
 	struct sja1105_private *priv = ds->priv;
-	struct hwtstamp_config config;
 
-	config.flags = 0;
+	config->flags = 0;
 	if (priv->hwts_tx_en & BIT(port))
-		config.tx_type = HWTSTAMP_TX_ON;
+		config->tx_type = HWTSTAMP_TX_ON;
 	else
-		config.tx_type = HWTSTAMP_TX_OFF;
+		config->tx_type = HWTSTAMP_TX_OFF;
 	if (priv->hwts_rx_en & BIT(port))
-		config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 	else
-		config.rx_filter = HWTSTAMP_FILTER_NONE;
+		config->rx_filter = HWTSTAMP_FILTER_NONE;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
 int sja1105_get_ts_info(struct dsa_switch *ds, int port,
@@ -737,10 +731,6 @@ static int sja1105_per_out_enable(struct sja1105_private *priv,
 	if (perout->index != 0)
 		return -EOPNOTSUPP;
 
-	/* Reject requests with unsupported flags */
-	if (perout->flags)
-		return -EOPNOTSUPP;
-
 	mutex_lock(&ptp_data->lock);
 
 	rc = sja1105_change_ptp_clk_pin_func(priv, PTP_PF_PEROUT);
@@ -820,13 +810,6 @@ static int sja1105_extts_enable(struct sja1105_private *priv,
 	if (extts->index != 0)
 		return -EOPNOTSUPP;
 
-	/* Reject requests with unsupported flags */
-	if (extts->flags & ~(PTP_ENABLE_FEATURE |
-			     PTP_RISING_EDGE |
-			     PTP_FALLING_EDGE |
-			     PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	/* We can only enable time stamping on both edges, sadly. */
 	if ((extts->flags & PTP_STRICT_FLAGS) &&
 	    (extts->flags & PTP_ENABLE_FEATURE) &&
@@ -912,6 +895,9 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds)
 		.n_pins		= 1,
 		.n_ext_ts	= 1,
 		.n_per_out	= 1,
+		.supported_extts_flags = PTP_RISING_EDGE |
+					 PTP_FALLING_EDGE |
+					 PTP_STRICT_FLAGS,
 	};
 
 	/* Only used on SJA1105 */
diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h
index 8add2bd5f728..325e3777ea07 100644
--- a/drivers/net/dsa/sja1105/sja1105_ptp.h
+++ b/drivers/net/dsa/sja1105/sja1105_ptp.h
@@ -112,9 +112,12 @@ bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port,
 void sja1105_port_txtstamp(struct dsa_switch *ds, int port,
 			   struct sk_buff *skb);
 
-int sja1105_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr);
+int sja1105_hwtstamp_get(struct dsa_switch *ds, int port,
+			 struct kernel_hwtstamp_config *config);
 
-int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr);
+int sja1105_hwtstamp_set(struct dsa_switch *ds, int port,
+			 struct kernel_hwtstamp_config *config,
+			 struct netlink_ext_ack *extack);
 
 int __sja1105_ptp_gettimex(struct dsa_switch *ds, u64 *ns,
 			   struct ptp_system_timestamp *sts);
diff --git a/drivers/net/ethernet/airoha/Kconfig b/drivers/net/ethernet/airoha/Kconfig
index 1a4cf6a259f6..ad3ce501e7a5 100644
--- a/drivers/net/ethernet/airoha/Kconfig
+++ b/drivers/net/ethernet/airoha/Kconfig
@@ -24,4 +24,11 @@ config NET_AIROHA
 	  This driver supports the gigabit ethernet MACs in the
 	  Airoha SoC family.
 
+config NET_AIROHA_FLOW_STATS
+	default y
+	bool "Airoha flow stats"
+	depends on NET_AIROHA && NET_AIROHA_NPU
+	help
+	  Enable Aiorha flowtable statistic counters.
+
 endif #NET_VENDOR_AIROHA
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index d748dc6de923..507ba046c719 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -5,6 +5,7 @@
  */
 #include <linux/of.h>
 #include <linux/of_net.h>
+#include <linux/of_reserved_mem.h>
 #include <linux/platform_device.h>
 #include <linux/tcp.h>
 #include <linux/u64_stats_sync.h>
@@ -34,46 +35,40 @@ u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
 	return val;
 }
 
-static void airoha_qdma_set_irqmask(struct airoha_qdma *qdma, int index,
-				    u32 clear, u32 set)
+static void airoha_qdma_set_irqmask(struct airoha_irq_bank *irq_bank,
+				    int index, u32 clear, u32 set)
 {
+	struct airoha_qdma *qdma = irq_bank->qdma;
+	int bank = irq_bank - &qdma->irq_banks[0];
 	unsigned long flags;
 
-	if (WARN_ON_ONCE(index >= ARRAY_SIZE(qdma->irqmask)))
+	if (WARN_ON_ONCE(index >= ARRAY_SIZE(irq_bank->irqmask)))
 		return;
 
-	spin_lock_irqsave(&qdma->irq_lock, flags);
+	spin_lock_irqsave(&irq_bank->irq_lock, flags);
 
-	qdma->irqmask[index] &= ~clear;
-	qdma->irqmask[index] |= set;
-	airoha_qdma_wr(qdma, REG_INT_ENABLE(index), qdma->irqmask[index]);
+	irq_bank->irqmask[index] &= ~clear;
+	irq_bank->irqmask[index] |= set;
+	airoha_qdma_wr(qdma, REG_INT_ENABLE(bank, index),
+		       irq_bank->irqmask[index]);
 	/* Read irq_enable register in order to guarantee the update above
 	 * completes in the spinlock critical section.
 	 */
-	airoha_qdma_rr(qdma, REG_INT_ENABLE(index));
+	airoha_qdma_rr(qdma, REG_INT_ENABLE(bank, index));
 
-	spin_unlock_irqrestore(&qdma->irq_lock, flags);
+	spin_unlock_irqrestore(&irq_bank->irq_lock, flags);
 }
 
-static void airoha_qdma_irq_enable(struct airoha_qdma *qdma, int index,
-				   u32 mask)
+static void airoha_qdma_irq_enable(struct airoha_irq_bank *irq_bank,
+				   int index, u32 mask)
 {
-	airoha_qdma_set_irqmask(qdma, index, 0, mask);
+	airoha_qdma_set_irqmask(irq_bank, index, 0, mask);
 }
 
-static void airoha_qdma_irq_disable(struct airoha_qdma *qdma, int index,
-				    u32 mask)
+static void airoha_qdma_irq_disable(struct airoha_irq_bank *irq_bank,
+				    int index, u32 mask)
 {
-	airoha_qdma_set_irqmask(qdma, index, mask, 0);
-}
-
-static bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port)
-{
-	/* GDM1 port on EN7581 SoC is connected to the lan dsa switch.
-	 * GDM{2,3,4} can be used as wan port connected to an external
-	 * phy module.
-	 */
-	return port->id == 1;
+	airoha_qdma_set_irqmask(irq_bank, index, mask, 0);
 }
 
 static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr)
@@ -527,6 +522,25 @@ static int airoha_fe_init(struct airoha_eth *eth)
 	/* disable IFC by default */
 	airoha_fe_clear(eth, REG_FE_CSR_IFC_CFG, FE_IFC_EN_MASK);
 
+	airoha_fe_wr(eth, REG_PPE_DFT_CPORT0(0),
+		     FIELD_PREP(DFT_CPORT_MASK(7), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(6), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(5), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(4), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(3), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(2), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(1), FE_PSE_PORT_CDM1) |
+		     FIELD_PREP(DFT_CPORT_MASK(0), FE_PSE_PORT_CDM1));
+	airoha_fe_wr(eth, REG_PPE_DFT_CPORT0(1),
+		     FIELD_PREP(DFT_CPORT_MASK(7), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(6), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(5), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(4), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(3), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(2), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(1), FE_PSE_PORT_CDM2) |
+		     FIELD_PREP(DFT_CPORT_MASK(0), FE_PSE_PORT_CDM2));
+
 	/* enable 1:N vlan action, init vlan table */
 	airoha_fe_set(eth, REG_MC_VLAN_EN, MC_VLAN_EN_MASK);
 
@@ -614,7 +628,6 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 		struct airoha_queue_entry *e = &q->entry[q->tail];
 		struct airoha_qdma_desc *desc = &q->desc[q->tail];
 		u32 hash, reason, msg1 = le32_to_cpu(desc->msg1);
-		dma_addr_t dma_addr = le32_to_cpu(desc->addr);
 		struct page *page = virt_to_head_page(e->buf);
 		u32 desc_ctrl = le32_to_cpu(desc->ctrl);
 		struct airoha_gdm_port *port;
@@ -623,22 +636,16 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 		if (!(desc_ctrl & QDMA_DESC_DONE_MASK))
 			break;
 
-		if (!dma_addr)
-			break;
-
-		len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl);
-		if (!len)
-			break;
-
 		q->tail = (q->tail + 1) % q->ndesc;
 		q->queued--;
 
-		dma_sync_single_for_cpu(eth->dev, dma_addr,
+		dma_sync_single_for_cpu(eth->dev, e->dma_addr,
 					SKB_WITH_OVERHEAD(q->buf_size), dir);
 
+		len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl);
 		data_len = q->skb ? q->buf_size
 				  : SKB_WITH_OVERHEAD(q->buf_size);
-		if (data_len < len)
+		if (!len || data_len < len)
 			goto free_frag;
 
 		p = airoha_qdma_get_gdm_port(eth, desc);
@@ -694,16 +701,19 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 
 		reason = FIELD_GET(AIROHA_RXD4_PPE_CPU_REASON, msg1);
 		if (reason == PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED)
-			airoha_ppe_check_skb(eth->ppe, hash);
+			airoha_ppe_check_skb(eth->ppe, q->skb, hash);
 
 		done++;
 		napi_gro_receive(&q->napi, q->skb);
 		q->skb = NULL;
 		continue;
 free_frag:
-		page_pool_put_full_page(q->page_pool, page, true);
-		dev_kfree_skb(q->skb);
-		q->skb = NULL;
+		if (q->skb) {
+			dev_kfree_skb(q->skb);
+			q->skb = NULL;
+		} else {
+			page_pool_put_full_page(q->page_pool, page, true);
+		}
 	}
 	airoha_qdma_fill_rx_queue(q);
 
@@ -720,9 +730,20 @@ static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget)
 		done += cur;
 	} while (cur && done < budget);
 
-	if (done < budget && napi_complete(napi))
-		airoha_qdma_irq_enable(q->qdma, QDMA_INT_REG_IDX1,
-				       RX_DONE_INT_MASK);
+	if (done < budget && napi_complete(napi)) {
+		struct airoha_qdma *qdma = q->qdma;
+		int i, qid = q - &qdma->q_rx[0];
+		int intr_reg = qid < RX_DONE_HIGH_OFFSET ? QDMA_INT_REG_IDX1
+							 : QDMA_INT_REG_IDX2;
+
+		for (i = 0; i < ARRAY_SIZE(qdma->irq_banks); i++) {
+			if (!(BIT(qid) & RX_IRQ_BANK_PIN_MASK(i)))
+				continue;
+
+			airoha_qdma_irq_enable(&qdma->irq_banks[i], intr_reg,
+					       BIT(qid % RX_DONE_HIGH_OFFSET));
+		}
+	}
 
 	return done;
 }
@@ -925,7 +946,7 @@ unlock:
 	}
 
 	if (done < budget && napi_complete(napi))
-		airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0,
+		airoha_qdma_irq_enable(&qdma->irq_banks[0], QDMA_INT_REG_IDX0,
 				       TX_DONE_INT_MASK(id));
 
 	return done;
@@ -1043,24 +1064,46 @@ static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q)
 static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 {
 	struct airoha_eth *eth = qdma->eth;
+	int id = qdma - &eth->qdma[0];
 	dma_addr_t dma_addr;
+	const char *name;
+	int size, index;
 	u32 status;
-	int size;
 
 	size = HW_DSCP_NUM * sizeof(struct airoha_qdma_fwd_desc);
-	qdma->hfwd.desc = dmam_alloc_coherent(eth->dev, size, &dma_addr,
-					      GFP_KERNEL);
-	if (!qdma->hfwd.desc)
+	if (!dmam_alloc_coherent(eth->dev, size, &dma_addr, GFP_KERNEL))
 		return -ENOMEM;
 
 	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
 
-	size = AIROHA_MAX_PACKET_SIZE * HW_DSCP_NUM;
-	qdma->hfwd.q = dmam_alloc_coherent(eth->dev, size, &dma_addr,
-					   GFP_KERNEL);
-	if (!qdma->hfwd.q)
+	name = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d-buf", id);
+	if (!name)
 		return -ENOMEM;
 
+	index = of_property_match_string(eth->dev->of_node,
+					 "memory-region-names", name);
+	if (index >= 0) {
+		struct reserved_mem *rmem;
+		struct device_node *np;
+
+		/* Consume reserved memory for hw forwarding buffers queue if
+		 * available in the DTS
+		 */
+		np = of_parse_phandle(eth->dev->of_node, "memory-region",
+				      index);
+		if (!np)
+			return -ENODEV;
+
+		rmem = of_reserved_mem_lookup(np);
+		of_node_put(np);
+		dma_addr = rmem->base;
+	} else {
+		size = AIROHA_MAX_PACKET_SIZE * HW_DSCP_NUM;
+		if (!dmam_alloc_coherent(eth->dev, size, &dma_addr,
+					 GFP_KERNEL))
+			return -ENOMEM;
+	}
+
 	airoha_qdma_wr(qdma, REG_FWD_BUF_BASE, dma_addr);
 
 	airoha_qdma_rmw(qdma, REG_HW_FWD_DSCP_CFG,
@@ -1072,7 +1115,7 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 			LMGR_INIT_START | LMGR_SRAM_MODE_MASK |
 			HW_FWD_DESC_NUM_MASK,
 			FIELD_PREP(HW_FWD_DESC_NUM_MASK, HW_DSCP_NUM) |
-			LMGR_INIT_START);
+			LMGR_INIT_START | LMGR_SRAM_MODE_MASK);
 
 	return read_poll_timeout(airoha_qdma_rr, status,
 				 !(status & LMGR_INIT_START), USEC_PER_MSEC,
@@ -1155,14 +1198,24 @@ static int airoha_qdma_hw_init(struct airoha_qdma *qdma)
 {
 	int i;
 
-	/* clear pending irqs */
-	for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++)
+	for (i = 0; i < ARRAY_SIZE(qdma->irq_banks); i++) {
+		/* clear pending irqs */
 		airoha_qdma_wr(qdma, REG_INT_STATUS(i), 0xffffffff);
-
-	/* setup irqs */
-	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0, INT_IDX0_MASK);
-	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX1, INT_IDX1_MASK);
-	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX4, INT_IDX4_MASK);
+		/* setup rx irqs */
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX0,
+				       INT_RX0_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX1,
+				       INT_RX1_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX2,
+				       INT_RX2_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+		airoha_qdma_irq_enable(&qdma->irq_banks[i], QDMA_INT_REG_IDX3,
+				       INT_RX3_MASK(RX_IRQ_BANK_PIN_MASK(i)));
+	}
+	/* setup tx irqs */
+	airoha_qdma_irq_enable(&qdma->irq_banks[0], QDMA_INT_REG_IDX0,
+			       TX_COHERENT_LOW_INT_MASK | INT_TX_MASK);
+	airoha_qdma_irq_enable(&qdma->irq_banks[0], QDMA_INT_REG_IDX4,
+			       TX_COHERENT_HIGH_INT_MASK);
 
 	/* setup irq binding */
 	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
@@ -1207,30 +1260,39 @@ static int airoha_qdma_hw_init(struct airoha_qdma *qdma)
 
 static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 {
-	struct airoha_qdma *qdma = dev_instance;
-	u32 intr[ARRAY_SIZE(qdma->irqmask)];
+	struct airoha_irq_bank *irq_bank = dev_instance;
+	struct airoha_qdma *qdma = irq_bank->qdma;
+	u32 rx_intr_mask = 0, rx_intr1, rx_intr2;
+	u32 intr[ARRAY_SIZE(irq_bank->irqmask)];
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++) {
+	for (i = 0; i < ARRAY_SIZE(intr); i++) {
 		intr[i] = airoha_qdma_rr(qdma, REG_INT_STATUS(i));
-		intr[i] &= qdma->irqmask[i];
+		intr[i] &= irq_bank->irqmask[i];
 		airoha_qdma_wr(qdma, REG_INT_STATUS(i), intr[i]);
 	}
 
 	if (!test_bit(DEV_STATE_INITIALIZED, &qdma->eth->state))
 		return IRQ_NONE;
 
-	if (intr[1] & RX_DONE_INT_MASK) {
-		airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX1,
-					RX_DONE_INT_MASK);
+	rx_intr1 = intr[1] & RX_DONE_LOW_INT_MASK;
+	if (rx_intr1) {
+		airoha_qdma_irq_disable(irq_bank, QDMA_INT_REG_IDX1, rx_intr1);
+		rx_intr_mask |= rx_intr1;
+	}
 
-		for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
-			if (!qdma->q_rx[i].ndesc)
-				continue;
+	rx_intr2 = intr[2] & RX_DONE_HIGH_INT_MASK;
+	if (rx_intr2) {
+		airoha_qdma_irq_disable(irq_bank, QDMA_INT_REG_IDX2, rx_intr2);
+		rx_intr_mask |= (rx_intr2 << 16);
+	}
 
-			if (intr[1] & BIT(i))
-				napi_schedule(&qdma->q_rx[i].napi);
-		}
+	for (i = 0; rx_intr_mask && i < ARRAY_SIZE(qdma->q_rx); i++) {
+		if (!qdma->q_rx[i].ndesc)
+			continue;
+
+		if (rx_intr_mask & BIT(i))
+			napi_schedule(&qdma->q_rx[i].napi);
 	}
 
 	if (intr[0] & INT_TX_MASK) {
@@ -1238,7 +1300,7 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 			if (!(intr[0] & TX_DONE_INT_MASK(i)))
 				continue;
 
-			airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX0,
+			airoha_qdma_irq_disable(irq_bank, QDMA_INT_REG_IDX0,
 						TX_DONE_INT_MASK(i));
 			napi_schedule(&qdma->q_tx_irq[i].napi);
 		}
@@ -1247,6 +1309,39 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 	return IRQ_HANDLED;
 }
 
+static int airoha_qdma_init_irq_banks(struct platform_device *pdev,
+				      struct airoha_qdma *qdma)
+{
+	struct airoha_eth *eth = qdma->eth;
+	int i, id = qdma - &eth->qdma[0];
+
+	for (i = 0; i < ARRAY_SIZE(qdma->irq_banks); i++) {
+		struct airoha_irq_bank *irq_bank = &qdma->irq_banks[i];
+		int err, irq_index = 4 * id + i;
+		const char *name;
+
+		spin_lock_init(&irq_bank->irq_lock);
+		irq_bank->qdma = qdma;
+
+		irq_bank->irq = platform_get_irq(pdev, irq_index);
+		if (irq_bank->irq < 0)
+			return irq_bank->irq;
+
+		name = devm_kasprintf(eth->dev, GFP_KERNEL,
+				      KBUILD_MODNAME ".%d", irq_index);
+		if (!name)
+			return -ENOMEM;
+
+		err = devm_request_irq(eth->dev, irq_bank->irq,
+				       airoha_irq_handler, IRQF_SHARED, name,
+				       irq_bank);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int airoha_qdma_init(struct platform_device *pdev,
 			    struct airoha_eth *eth,
 			    struct airoha_qdma *qdma)
@@ -1254,9 +1349,7 @@ static int airoha_qdma_init(struct platform_device *pdev,
 	int err, id = qdma - &eth->qdma[0];
 	const char *res;
 
-	spin_lock_init(&qdma->irq_lock);
 	qdma->eth = eth;
-
 	res = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d", id);
 	if (!res)
 		return -ENOMEM;
@@ -1266,12 +1359,7 @@ static int airoha_qdma_init(struct platform_device *pdev,
 		return dev_err_probe(eth->dev, PTR_ERR(qdma->regs),
 				     "failed to iomap qdma%d regs\n", id);
 
-	qdma->irq = platform_get_irq(pdev, 4 * id);
-	if (qdma->irq < 0)
-		return qdma->irq;
-
-	err = devm_request_irq(eth->dev, qdma->irq, airoha_irq_handler,
-			       IRQF_SHARED, KBUILD_MODNAME, qdma);
+	err = airoha_qdma_init_irq_banks(pdev, qdma);
 	if (err)
 		return err;
 
@@ -1631,7 +1719,6 @@ static void airhoha_set_gdm2_loopback(struct airoha_gdm_port *port)
 
 	if (port->id == 3) {
 		/* FIXME: handle XSI_PCE1_PORT */
-		airoha_fe_wr(eth, REG_PPE_DFT_CPORT0(0),  0x5500);
 		airoha_fe_rmw(eth, REG_FE_WAN_PORT,
 			      WAN1_EN_MASK | WAN1_MASK | WAN0_MASK,
 			      FIELD_PREP(WAN0_MASK, HSGMII_LAN_PCIE0_SRCPORT));
@@ -2109,6 +2196,125 @@ static int airoha_tc_setup_qdisc_ets(struct airoha_gdm_port *port,
 	}
 }
 
+static int airoha_qdma_get_rl_param(struct airoha_qdma *qdma, int queue_id,
+				    u32 addr, enum trtcm_param_type param,
+				    u32 *val_low, u32 *val_high)
+{
+	u32 idx = QDMA_METER_IDX(queue_id), group = QDMA_METER_GROUP(queue_id);
+	u32 val, config = FIELD_PREP(RATE_LIMIT_PARAM_TYPE_MASK, param) |
+			  FIELD_PREP(RATE_LIMIT_METER_GROUP_MASK, group) |
+			  FIELD_PREP(RATE_LIMIT_PARAM_INDEX_MASK, idx);
+
+	airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config);
+	if (read_poll_timeout(airoha_qdma_rr, val,
+			      val & RATE_LIMIT_PARAM_RW_DONE_MASK,
+			      USEC_PER_MSEC, 10 * USEC_PER_MSEC, true, qdma,
+			      REG_TRTCM_CFG_PARAM(addr)))
+		return -ETIMEDOUT;
+
+	*val_low = airoha_qdma_rr(qdma, REG_TRTCM_DATA_LOW(addr));
+	if (val_high)
+		*val_high = airoha_qdma_rr(qdma, REG_TRTCM_DATA_HIGH(addr));
+
+	return 0;
+}
+
+static int airoha_qdma_set_rl_param(struct airoha_qdma *qdma, int queue_id,
+				    u32 addr, enum trtcm_param_type param,
+				    u32 val)
+{
+	u32 idx = QDMA_METER_IDX(queue_id), group = QDMA_METER_GROUP(queue_id);
+	u32 config = RATE_LIMIT_PARAM_RW_MASK |
+		     FIELD_PREP(RATE_LIMIT_PARAM_TYPE_MASK, param) |
+		     FIELD_PREP(RATE_LIMIT_METER_GROUP_MASK, group) |
+		     FIELD_PREP(RATE_LIMIT_PARAM_INDEX_MASK, idx);
+
+	airoha_qdma_wr(qdma, REG_TRTCM_DATA_LOW(addr), val);
+	airoha_qdma_wr(qdma, REG_TRTCM_CFG_PARAM(addr), config);
+
+	return read_poll_timeout(airoha_qdma_rr, val,
+				 val & RATE_LIMIT_PARAM_RW_DONE_MASK,
+				 USEC_PER_MSEC, 10 * USEC_PER_MSEC, true,
+				 qdma, REG_TRTCM_CFG_PARAM(addr));
+}
+
+static int airoha_qdma_set_rl_config(struct airoha_qdma *qdma, int queue_id,
+				     u32 addr, bool enable, u32 enable_mask)
+{
+	u32 val;
+	int err;
+
+	err = airoha_qdma_get_rl_param(qdma, queue_id, addr, TRTCM_MISC_MODE,
+				       &val, NULL);
+	if (err)
+		return err;
+
+	val = enable ? val | enable_mask : val & ~enable_mask;
+
+	return airoha_qdma_set_rl_param(qdma, queue_id, addr, TRTCM_MISC_MODE,
+					val);
+}
+
+static int airoha_qdma_set_rl_token_bucket(struct airoha_qdma *qdma,
+					   int queue_id, u32 rate_val,
+					   u32 bucket_size)
+{
+	u32 val, config, tick, unit, rate, rate_frac;
+	int err;
+
+	err = airoha_qdma_get_rl_param(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+				       TRTCM_MISC_MODE, &config, NULL);
+	if (err)
+		return err;
+
+	val = airoha_qdma_rr(qdma, REG_INGRESS_TRTCM_CFG);
+	tick = FIELD_GET(INGRESS_FAST_TICK_MASK, val);
+	if (config & TRTCM_TICK_SEL)
+		tick *= FIELD_GET(INGRESS_SLOW_TICK_RATIO_MASK, val);
+	if (!tick)
+		return -EINVAL;
+
+	unit = (config & TRTCM_PKT_MODE) ? 1000000 / tick : 8000 / tick;
+	if (!unit)
+		return -EINVAL;
+
+	rate = rate_val / unit;
+	rate_frac = rate_val % unit;
+	rate_frac = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate_frac) / unit;
+	rate = FIELD_PREP(TRTCM_TOKEN_RATE_MASK, rate) |
+	       FIELD_PREP(TRTCM_TOKEN_RATE_FRACTION_MASK, rate_frac);
+
+	err = airoha_qdma_set_rl_param(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+				       TRTCM_TOKEN_RATE_MODE, rate);
+	if (err)
+		return err;
+
+	val = bucket_size;
+	if (!(config & TRTCM_PKT_MODE))
+		val = max_t(u32, val, MIN_TOKEN_SIZE);
+	val = min_t(u32, __fls(val), MAX_TOKEN_SIZE_OFFSET);
+
+	return airoha_qdma_set_rl_param(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+					TRTCM_BUCKETSIZE_SHIFT_MODE, val);
+}
+
+static int airoha_qdma_init_rl_config(struct airoha_qdma *qdma, int queue_id,
+				      bool enable, enum trtcm_unit_type unit)
+{
+	bool tick_sel = queue_id == 0 || queue_id == 2 || queue_id == 8;
+	enum trtcm_param mode = TRTCM_METER_MODE;
+	int err;
+
+	mode |= unit == TRTCM_PACKET_UNIT ? TRTCM_PKT_MODE : 0;
+	err = airoha_qdma_set_rl_config(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+					enable, mode);
+	if (err)
+		return err;
+
+	return airoha_qdma_set_rl_config(qdma, queue_id, REG_INGRESS_TRTCM_CFG,
+					 tick_sel, TRTCM_TICK_SEL);
+}
+
 static int airoha_qdma_get_trtcm_param(struct airoha_qdma *qdma, int channel,
 				       u32 addr, enum trtcm_param_type param,
 				       enum trtcm_mode_type mode,
@@ -2273,10 +2479,142 @@ static int airoha_tc_htb_alloc_leaf_queue(struct airoha_gdm_port *port,
 	return 0;
 }
 
+static int airoha_qdma_set_rx_meter(struct airoha_gdm_port *port,
+				    u32 rate, u32 bucket_size,
+				    enum trtcm_unit_type unit_type)
+{
+	struct airoha_qdma *qdma = port->qdma;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
+		int err;
+
+		if (!qdma->q_rx[i].ndesc)
+			continue;
+
+		err = airoha_qdma_init_rl_config(qdma, i, !!rate, unit_type);
+		if (err)
+			return err;
+
+		err = airoha_qdma_set_rl_token_bucket(qdma, i, rate,
+						      bucket_size);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int airoha_tc_matchall_act_validate(struct tc_cls_matchall_offload *f)
+{
+	const struct flow_action *actions = &f->rule->action;
+	const struct flow_action_entry *act;
+
+	if (!flow_action_has_entries(actions)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "filter run with no actions");
+		return -EINVAL;
+	}
+
+	if (!flow_offload_has_one_action(actions)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "only once action per filter is supported");
+		return -EOPNOTSUPP;
+	}
+
+	act = &actions->entries[0];
+	if (act->id != FLOW_ACTION_POLICE) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "unsupported action");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.exceed.act_id != FLOW_ACTION_DROP) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "invalid exceed action id");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.notexceed.act_id != FLOW_ACTION_ACCEPT) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "invalid notexceed action id");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.notexceed.act_id == FLOW_ACTION_ACCEPT &&
+	    !flow_action_is_last_entry(actions, act)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "action accept must be last");
+		return -EOPNOTSUPP;
+	}
+
+	if (act->police.peakrate_bytes_ps || act->police.avrate ||
+	    act->police.overhead || act->police.mtu) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "peakrate/avrate/overhead/mtu unsupported");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int airoha_dev_tc_matchall(struct net_device *dev,
+				  struct tc_cls_matchall_offload *f)
+{
+	enum trtcm_unit_type unit_type = TRTCM_BYTE_UNIT;
+	struct airoha_gdm_port *port = netdev_priv(dev);
+	u32 rate = 0, bucket_size = 0;
+
+	switch (f->command) {
+	case TC_CLSMATCHALL_REPLACE: {
+		const struct flow_action_entry *act;
+		int err;
+
+		err = airoha_tc_matchall_act_validate(f);
+		if (err)
+			return err;
+
+		act = &f->rule->action.entries[0];
+		if (act->police.rate_pkt_ps) {
+			rate = act->police.rate_pkt_ps;
+			bucket_size = act->police.burst_pkt;
+			unit_type = TRTCM_PACKET_UNIT;
+		} else {
+			rate = div_u64(act->police.rate_bytes_ps, 1000);
+			rate = rate << 3; /* Kbps */
+			bucket_size = act->police.burst;
+		}
+		fallthrough;
+	}
+	case TC_CLSMATCHALL_DESTROY:
+		return airoha_qdma_set_rx_meter(port, rate, bucket_size,
+						unit_type);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int airoha_dev_setup_tc_block_cb(enum tc_setup_type type,
+					void *type_data, void *cb_priv)
+{
+	struct net_device *dev = cb_priv;
+
+	if (!tc_can_offload(dev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return airoha_ppe_setup_tc_block_cb(dev, type_data);
+	case TC_SETUP_CLSMATCHALL:
+		return airoha_dev_tc_matchall(dev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int airoha_dev_setup_tc_block(struct airoha_gdm_port *port,
 				     struct flow_block_offload *f)
 {
-	flow_setup_cb_t *cb = airoha_ppe_setup_tc_block_cb;
+	flow_setup_cb_t *cb = airoha_dev_setup_tc_block_cb;
 	static LIST_HEAD(block_cb_list);
 	struct flow_block_cb *block_cb;
 
@@ -2515,7 +2853,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth,
 	dev->features |= dev->hw_features;
 	dev->vlan_features = dev->hw_features;
 	dev->dev.of_node = np;
-	dev->irq = qdma->irq;
+	dev->irq = qdma->irq_banks[0].irq;
 	SET_NETDEV_DEV(dev, eth->dev);
 
 	/* reserve hw queues for HTB offloading */
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index ec8908f904c6..b815697302bf 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -17,6 +17,7 @@
 
 #define AIROHA_MAX_NUM_GDM_PORTS	4
 #define AIROHA_MAX_NUM_QDMA		2
+#define AIROHA_MAX_NUM_IRQ_BANKS	4
 #define AIROHA_MAX_DSA_PORTS		7
 #define AIROHA_MAX_NUM_RSTS		3
 #define AIROHA_MAX_NUM_XSI_RSTS		5
@@ -49,6 +50,14 @@
 #define PPE_NUM				2
 #define PPE1_SRAM_NUM_ENTRIES		(8 * 1024)
 #define PPE_SRAM_NUM_ENTRIES		(2 * PPE1_SRAM_NUM_ENTRIES)
+#ifdef CONFIG_NET_AIROHA_FLOW_STATS
+#define PPE1_STATS_NUM_ENTRIES		(4 * 1024)
+#else
+#define PPE1_STATS_NUM_ENTRIES		0
+#endif /* CONFIG_NET_AIROHA_FLOW_STATS */
+#define PPE_STATS_NUM_ENTRIES		(2 * PPE1_STATS_NUM_ENTRIES)
+#define PPE1_SRAM_NUM_DATA_ENTRIES	(PPE1_SRAM_NUM_ENTRIES - PPE1_STATS_NUM_ENTRIES)
+#define PPE_SRAM_NUM_DATA_ENTRIES	(2 * PPE1_SRAM_NUM_DATA_ENTRIES)
 #define PPE_DRAM_NUM_ENTRIES		(16 * 1024)
 #define PPE_NUM_ENTRIES			(PPE_SRAM_NUM_ENTRIES + PPE_DRAM_NUM_ENTRIES)
 #define PPE_HASH_MASK			(PPE_NUM_ENTRIES - 1)
@@ -127,6 +136,11 @@ enum tx_sched_mode {
 	TC_SCH_WRR2,
 };
 
+enum trtcm_unit_type {
+	TRTCM_BYTE_UNIT,
+	TRTCM_PACKET_UNIT,
+};
+
 enum trtcm_param_type {
 	TRTCM_MISC_MODE, /* meter_en, pps_mode, tick_sel */
 	TRTCM_TOKEN_RATE_MODE,
@@ -255,6 +269,8 @@ struct airoha_foe_mac_info {
 
 	u16 pppoe_id;
 	u16 src_mac_lo;
+
+	u32 meter;
 };
 
 #define AIROHA_FOE_IB1_UNBIND_PREBIND		BIT(24)
@@ -290,6 +306,11 @@ struct airoha_foe_mac_info {
 #define AIROHA_FOE_TUNNEL			BIT(6)
 #define AIROHA_FOE_TUNNEL_ID			GENMASK(5, 0)
 
+#define AIROHA_FOE_TUNNEL_MTU			GENMASK(31, 16)
+#define AIROHA_FOE_ACNT_GRP3			GENMASK(15, 9)
+#define AIROHA_FOE_METER_GRP3			GENMASK(8, 5)
+#define AIROHA_FOE_METER_GRP2			GENMASK(4, 0)
+
 struct airoha_foe_bridge {
 	u32 dest_mac_hi;
 
@@ -373,6 +394,8 @@ struct airoha_foe_ipv6 {
 	u32 ib2;
 
 	struct airoha_foe_mac_info_common l2;
+
+	u32 meter;
 };
 
 struct airoha_foe_entry {
@@ -391,6 +414,16 @@ struct airoha_foe_entry {
 	};
 };
 
+struct airoha_foe_stats {
+	u32 bytes;
+	u32 packets;
+};
+
+struct airoha_foe_stats64 {
+	u64 bytes;
+	u64 packets;
+};
+
 struct airoha_flow_data {
 	struct ethhdr eth;
 
@@ -422,37 +455,64 @@ struct airoha_flow_data {
 	} pppoe;
 };
 
+enum airoha_flow_entry_type {
+	FLOW_TYPE_L4,
+	FLOW_TYPE_L2,
+	FLOW_TYPE_L2_SUBFLOW,
+};
+
 struct airoha_flow_table_entry {
-	struct hlist_node list;
+	union {
+		struct hlist_node list; /* PPE L3 flow entry */
+		struct {
+			struct rhash_head l2_node;  /* L2 flow entry */
+			struct hlist_head l2_flows; /* PPE L2 subflows list */
+		};
+	};
 
 	struct airoha_foe_entry data;
+	struct hlist_node l2_subflow_node; /* PPE L2 subflow entry */
 	u32 hash;
 
+	struct airoha_foe_stats64 stats;
+	enum airoha_flow_entry_type type;
+
 	struct rhash_head node;
 	unsigned long cookie;
 };
 
-struct airoha_qdma {
-	struct airoha_eth *eth;
-	void __iomem *regs;
+/* RX queue to IRQ mapping: BIT(q) in IRQ(n) */
+#define RX_IRQ0_BANK_PIN_MASK			0x839f
+#define RX_IRQ1_BANK_PIN_MASK			0x7fe00000
+#define RX_IRQ2_BANK_PIN_MASK			0x20
+#define RX_IRQ3_BANK_PIN_MASK			0x40
+#define RX_IRQ_BANK_PIN_MASK(_n)		\
+	(((_n) == 3) ? RX_IRQ3_BANK_PIN_MASK :	\
+	 ((_n) == 2) ? RX_IRQ2_BANK_PIN_MASK :	\
+	 ((_n) == 1) ? RX_IRQ1_BANK_PIN_MASK :	\
+	 RX_IRQ0_BANK_PIN_MASK)
+
+struct airoha_irq_bank {
+	struct airoha_qdma *qdma;
 
 	/* protect concurrent irqmask accesses */
 	spinlock_t irq_lock;
 	u32 irqmask[QDMA_INT_REG_MAX];
 	int irq;
+};
+
+struct airoha_qdma {
+	struct airoha_eth *eth;
+	void __iomem *regs;
 
 	atomic_t users;
 
+	struct airoha_irq_bank irq_banks[AIROHA_MAX_NUM_IRQ_BANKS];
+
 	struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ];
 
 	struct airoha_queue q_tx[AIROHA_NUM_TX_RING];
 	struct airoha_queue q_rx[AIROHA_NUM_RX_RING];
-
-	/* descriptor and packet buffers for qdma hw forward */
-	struct {
-		void *desc;
-		void *q;
-	} hfwd;
 };
 
 struct airoha_gdm_port {
@@ -480,9 +540,14 @@ struct airoha_ppe {
 	void *foe;
 	dma_addr_t foe_dma;
 
+	struct rhashtable l2_flows;
+
 	struct hlist_head *foe_flow;
 	u16 foe_check_time[PPE_NUM_ENTRIES];
 
+	struct airoha_foe_stats *foe_stats;
+	dma_addr_t foe_stats_dma;
+
 	struct dentry *debugfs_dir;
 };
 
@@ -532,16 +597,27 @@ u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val);
 #define airoha_qdma_clear(qdma, offset, val)			\
 	airoha_rmw((qdma)->regs, (offset), (val), 0)
 
+static inline bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port)
+{
+	/* GDM1 port on EN7581 SoC is connected to the lan dsa switch.
+	 * GDM{2,3,4} can be used as wan port connected to an external
+	 * phy module.
+	 */
+	return port->id == 1;
+}
+
 bool airoha_is_valid_gdm_port(struct airoha_eth *eth,
 			      struct airoha_gdm_port *port);
 
-void airoha_ppe_check_skb(struct airoha_ppe *ppe, u16 hash);
-int airoha_ppe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
-				 void *cb_priv);
+void airoha_ppe_check_skb(struct airoha_ppe *ppe, struct sk_buff *skb,
+			  u16 hash);
+int airoha_ppe_setup_tc_block_cb(struct net_device *dev, void *type_data);
 int airoha_ppe_init(struct airoha_eth *eth);
 void airoha_ppe_deinit(struct airoha_eth *eth);
 struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
 						  u32 hash);
+void airoha_ppe_foe_entry_get_stats(struct airoha_ppe *ppe, u32 hash,
+				    struct airoha_foe_stats64 *stats);
 
 #ifdef CONFIG_DEBUG_FS
 int airoha_ppe_debugfs_init(struct airoha_ppe *ppe);
diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c
index 7a5710f9ccf6..0e5b8c21b9aa 100644
--- a/drivers/net/ethernet/airoha/airoha_npu.c
+++ b/drivers/net/ethernet/airoha/airoha_npu.c
@@ -12,6 +12,7 @@
 #include <linux/of_reserved_mem.h>
 #include <linux/regmap.h>
 
+#include "airoha_eth.h"
 #include "airoha_npu.h"
 
 #define NPU_EN7581_FIRMWARE_DATA		"airoha/en7581_npu_data.bin"
@@ -72,6 +73,7 @@ enum {
 	PPE_FUNC_SET_WAIT_HWNAT_INIT,
 	PPE_FUNC_SET_WAIT_HWNAT_DEINIT,
 	PPE_FUNC_SET_WAIT_API,
+	PPE_FUNC_SET_WAIT_FLOW_STATS_SETUP,
 };
 
 enum {
@@ -104,15 +106,21 @@ struct ppe_mbox_data {
 			u8 xpon_hal_api;
 			u8 wan_xsi;
 			u8 ct_joyme4;
-			int ppe_type;
-			int wan_mode;
-			int wan_sel;
+			u8 max_packet;
+			u8 rsv[3];
+			u32 ppe_type;
+			u32 wan_mode;
+			u32 wan_sel;
 		} init_info;
 		struct {
-			int func_id;
+			u32 func_id;
 			u32 size;
 			u32 data;
 		} set_info;
+		struct {
+			u32 npu_stats_addr;
+			u32 foe_stats_addr;
+		} stats_info;
 	};
 };
 
@@ -122,17 +130,12 @@ static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id,
 	u16 core = 0; /* FIXME */
 	u32 val, offset = core << 4;
 	dma_addr_t dma_addr;
-	void *addr;
 	int ret;
 
-	addr = kmemdup(p, size, GFP_ATOMIC);
-	if (!addr)
-		return -ENOMEM;
-
-	dma_addr = dma_map_single(npu->dev, addr, size, DMA_TO_DEVICE);
+	dma_addr = dma_map_single(npu->dev, p, size, DMA_TO_DEVICE);
 	ret = dma_mapping_error(npu->dev, dma_addr);
 	if (ret)
-		goto out;
+		return ret;
 
 	spin_lock_bh(&npu->cores[core].lock);
 
@@ -153,8 +156,6 @@ static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id,
 	spin_unlock_bh(&npu->cores[core].lock);
 
 	dma_unmap_single(npu->dev, dma_addr, size, DMA_TO_DEVICE);
-out:
-	kfree(addr);
 
 	return ret;
 }
@@ -259,79 +260,137 @@ static irqreturn_t airoha_npu_wdt_handler(int irq, void *core_instance)
 
 static int airoha_npu_ppe_init(struct airoha_npu *npu)
 {
-	struct ppe_mbox_data ppe_data = {
-		.func_type = NPU_OP_SET,
-		.func_id = PPE_FUNC_SET_WAIT_HWNAT_INIT,
-		.init_info = {
-			.ppe_type = PPE_TYPE_L2B_IPV4_IPV6,
-			.wan_mode = QDMA_WAN_ETHER,
-		},
-	};
+	struct ppe_mbox_data *ppe_data;
+	int err;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_KERNEL);
+	if (!ppe_data)
+		return -ENOMEM;
 
-	return airoha_npu_send_msg(npu, NPU_FUNC_PPE, &ppe_data,
-				   sizeof(struct ppe_mbox_data));
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_HWNAT_INIT;
+	ppe_data->init_info.ppe_type = PPE_TYPE_L2B_IPV4_IPV6;
+	ppe_data->init_info.wan_mode = QDMA_WAN_ETHER;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	kfree(ppe_data);
+
+	return err;
 }
 
 static int airoha_npu_ppe_deinit(struct airoha_npu *npu)
 {
-	struct ppe_mbox_data ppe_data = {
-		.func_type = NPU_OP_SET,
-		.func_id = PPE_FUNC_SET_WAIT_HWNAT_DEINIT,
-	};
+	struct ppe_mbox_data *ppe_data;
+	int err;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_KERNEL);
+	if (!ppe_data)
+		return -ENOMEM;
 
-	return airoha_npu_send_msg(npu, NPU_FUNC_PPE, &ppe_data,
-				   sizeof(struct ppe_mbox_data));
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_HWNAT_DEINIT;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	kfree(ppe_data);
+
+	return err;
 }
 
 static int airoha_npu_ppe_flush_sram_entries(struct airoha_npu *npu,
 					     dma_addr_t foe_addr,
 					     int sram_num_entries)
 {
-	struct ppe_mbox_data ppe_data = {
-		.func_type = NPU_OP_SET,
-		.func_id = PPE_FUNC_SET_WAIT_API,
-		.set_info = {
-			.func_id = PPE_SRAM_RESET_VAL,
-			.data = foe_addr,
-			.size = sram_num_entries,
-		},
-	};
+	struct ppe_mbox_data *ppe_data;
+	int err;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_KERNEL);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_API;
+	ppe_data->set_info.func_id = PPE_SRAM_RESET_VAL;
+	ppe_data->set_info.data = foe_addr;
+	ppe_data->set_info.size = sram_num_entries;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	kfree(ppe_data);
 
-	return airoha_npu_send_msg(npu, NPU_FUNC_PPE, &ppe_data,
-				   sizeof(struct ppe_mbox_data));
+	return err;
 }
 
 static int airoha_npu_foe_commit_entry(struct airoha_npu *npu,
 				       dma_addr_t foe_addr,
 				       u32 entry_size, u32 hash, bool ppe2)
 {
-	struct ppe_mbox_data ppe_data = {
-		.func_type = NPU_OP_SET,
-		.func_id = PPE_FUNC_SET_WAIT_API,
-		.set_info = {
-			.data = foe_addr,
-			.size = entry_size,
-		},
-	};
+	struct ppe_mbox_data *ppe_data;
 	int err;
 
-	ppe_data.set_info.func_id = ppe2 ? PPE2_SRAM_SET_ENTRY
-					 : PPE_SRAM_SET_ENTRY;
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_ATOMIC);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_API;
+	ppe_data->set_info.data = foe_addr;
+	ppe_data->set_info.size = entry_size;
+	ppe_data->set_info.func_id = ppe2 ? PPE2_SRAM_SET_ENTRY
+					  : PPE_SRAM_SET_ENTRY;
 
-	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, &ppe_data,
-				  sizeof(struct ppe_mbox_data));
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
 	if (err)
-		return err;
+		goto out;
+
+	ppe_data->set_info.func_id = PPE_SRAM_SET_VAL;
+	ppe_data->set_info.data = hash;
+	ppe_data->set_info.size = sizeof(u32);
 
-	ppe_data.set_info.func_id = PPE_SRAM_SET_VAL;
-	ppe_data.set_info.data = hash;
-	ppe_data.set_info.size = sizeof(u32);
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+out:
+	kfree(ppe_data);
 
-	return airoha_npu_send_msg(npu, NPU_FUNC_PPE, &ppe_data,
-				   sizeof(struct ppe_mbox_data));
+	return err;
 }
 
-struct airoha_npu *airoha_npu_get(struct device *dev)
+static int airoha_npu_stats_setup(struct airoha_npu *npu,
+				  dma_addr_t foe_stats_addr)
+{
+	int err, size = PPE_STATS_NUM_ENTRIES * sizeof(*npu->stats);
+	struct ppe_mbox_data *ppe_data;
+
+	if (!size) /* flow stats are disabled */
+		return 0;
+
+	ppe_data = kzalloc(sizeof(*ppe_data), GFP_ATOMIC);
+	if (!ppe_data)
+		return -ENOMEM;
+
+	ppe_data->func_type = NPU_OP_SET;
+	ppe_data->func_id = PPE_FUNC_SET_WAIT_FLOW_STATS_SETUP;
+	ppe_data->stats_info.foe_stats_addr = foe_stats_addr;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, ppe_data,
+				  sizeof(*ppe_data));
+	if (err)
+		goto out;
+
+	npu->stats = devm_ioremap(npu->dev,
+				  ppe_data->stats_info.npu_stats_addr,
+				  size);
+	if (!npu->stats)
+		err = -ENOMEM;
+out:
+	kfree(ppe_data);
+
+	return err;
+}
+
+struct airoha_npu *airoha_npu_get(struct device *dev, dma_addr_t *stats_addr)
 {
 	struct platform_device *pdev;
 	struct device_node *np;
@@ -369,6 +428,17 @@ struct airoha_npu *airoha_npu_get(struct device *dev)
 		goto error_module_put;
 	}
 
+	if (stats_addr) {
+		int err;
+
+		err = airoha_npu_stats_setup(npu, *stats_addr);
+		if (err) {
+			dev_err(dev, "failed to allocate npu stats buffer\n");
+			npu = ERR_PTR(err);
+			goto error_module_put;
+		}
+	}
+
 	return npu;
 
 error_module_put:
diff --git a/drivers/net/ethernet/airoha/airoha_npu.h b/drivers/net/ethernet/airoha/airoha_npu.h
index a2b8ae4d9473..98ec3be74ce4 100644
--- a/drivers/net/ethernet/airoha/airoha_npu.h
+++ b/drivers/net/ethernet/airoha/airoha_npu.h
@@ -17,6 +17,8 @@ struct airoha_npu {
 		struct work_struct wdt_work;
 	} cores[NPU_NUM_CORES];
 
+	struct airoha_foe_stats __iomem *stats;
+
 	struct {
 		int (*ppe_init)(struct airoha_npu *npu);
 		int (*ppe_deinit)(struct airoha_npu *npu);
@@ -30,5 +32,5 @@ struct airoha_npu {
 	} ops;
 };
 
-struct airoha_npu *airoha_npu_get(struct device *dev);
+struct airoha_npu *airoha_npu_get(struct device *dev, dma_addr_t *stats_addr);
 void airoha_npu_put(struct airoha_npu *npu);
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index f10dab935cab..12d32c92717a 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -24,6 +24,13 @@ static const struct rhashtable_params airoha_flow_table_params = {
 	.automatic_shrinking = true,
 };
 
+static const struct rhashtable_params airoha_l2_flow_table_params = {
+	.head_offset = offsetof(struct airoha_flow_table_entry, l2_node),
+	.key_offset = offsetof(struct airoha_flow_table_entry, data.bridge),
+	.key_len = 2 * ETH_ALEN,
+	.automatic_shrinking = true,
+};
+
 static bool airoha_ppe2_is_enabled(struct airoha_eth *eth)
 {
 	return airoha_fe_rr(eth, REG_PPE_GLO_CFG(1)) & PPE_GLO_CFG_EN_MASK;
@@ -77,6 +84,7 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe)
 
 		airoha_fe_rmw(eth, REG_PPE_TB_CFG(i),
 			      PPE_TB_CFG_SEARCH_MISS_MASK |
+			      PPE_TB_CFG_KEEPALIVE_MASK |
 			      PPE_TB_ENTRY_SIZE_MASK,
 			      FIELD_PREP(PPE_TB_CFG_SEARCH_MISS_MASK, 3) |
 			      FIELD_PREP(PPE_TB_ENTRY_SIZE_MASK, 0));
@@ -95,7 +103,7 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe)
 
 	if (airoha_ppe2_is_enabled(eth)) {
 		sram_num_entries =
-			PPE_RAM_NUM_ENTRIES_SHIFT(PPE1_SRAM_NUM_ENTRIES);
+			PPE_RAM_NUM_ENTRIES_SHIFT(PPE1_SRAM_NUM_DATA_ENTRIES);
 		airoha_fe_rmw(eth, REG_PPE_TB_CFG(0),
 			      PPE_SRAM_TB_NUM_ENTRY_MASK |
 			      PPE_DRAM_TB_NUM_ENTRY_MASK,
@@ -112,7 +120,7 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe)
 					 dram_num_entries));
 	} else {
 		sram_num_entries =
-			PPE_RAM_NUM_ENTRIES_SHIFT(PPE_SRAM_NUM_ENTRIES);
+			PPE_RAM_NUM_ENTRIES_SHIFT(PPE_SRAM_NUM_DATA_ENTRIES);
 		airoha_fe_rmw(eth, REG_PPE_TB_CFG(0),
 			      PPE_SRAM_TB_NUM_ENTRY_MASK |
 			      PPE_DRAM_TB_NUM_ENTRY_MASK,
@@ -197,6 +205,15 @@ static int airoha_get_dsa_port(struct net_device **dev)
 #endif
 }
 
+static void airoha_ppe_foe_set_bridge_addrs(struct airoha_foe_bridge *br,
+					    struct ethhdr *eh)
+{
+	br->dest_mac_hi = get_unaligned_be32(eh->h_dest);
+	br->dest_mac_lo = get_unaligned_be16(eh->h_dest + 4);
+	br->src_mac_hi = get_unaligned_be16(eh->h_source);
+	br->src_mac_lo = get_unaligned_be32(eh->h_source + 2);
+}
+
 static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
 					struct airoha_foe_entry *hwe,
 					struct net_device *dev, int type,
@@ -234,6 +251,12 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
 		else
 			pse_port = 2; /* uplink relies on GDM2 loopback */
 		val |= FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT, pse_port);
+
+		/* For downlink traffic consume SRAM memory for hw forwarding
+		 * descriptors queue.
+		 */
+		if (airhoa_is_lan_gdm_port(port))
+			val |= AIROHA_FOE_IB2_FAST_PATH;
 	}
 
 	if (is_multicast_ether_addr(data->eth.h_dest))
@@ -247,13 +270,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
 
 	qdata = FIELD_PREP(AIROHA_FOE_SHAPER_ID, 0x7f);
 	if (type == PPE_PKT_TYPE_BRIDGE) {
-		hwe->bridge.dest_mac_hi = get_unaligned_be32(data->eth.h_dest);
-		hwe->bridge.dest_mac_lo =
-			get_unaligned_be16(data->eth.h_dest + 4);
-		hwe->bridge.src_mac_hi =
-			get_unaligned_be16(data->eth.h_source);
-		hwe->bridge.src_mac_lo =
-			get_unaligned_be32(data->eth.h_source + 2);
+		airoha_ppe_foe_set_bridge_addrs(&hwe->bridge, &data->eth);
 		hwe->bridge.data = qdata;
 		hwe->bridge.ib2 = val;
 		l2 = &hwe->bridge.l2.common;
@@ -378,6 +395,19 @@ static u32 airoha_ppe_foe_get_entry_hash(struct airoha_foe_entry *hwe)
 		hv3 = hwe->ipv6.src_ip[1] ^ hwe->ipv6.dest_ip[1];
 		hv3 ^= hwe->ipv6.src_ip[0];
 		break;
+	case PPE_PKT_TYPE_BRIDGE: {
+		struct airoha_foe_mac_info *l2 = &hwe->bridge.l2;
+
+		hv1 = l2->common.src_mac_hi & 0xffff;
+		hv1 = hv1 << 16 | l2->src_mac_lo;
+
+		hv2 = l2->common.dest_mac_lo;
+		hv2 = hv2 << 16;
+		hv2 = hv2 | ((l2->common.src_mac_hi & 0xffff0000) >> 16);
+
+		hv3 = l2->common.dest_mac_hi;
+		break;
+	}
 	case PPE_PKT_TYPE_IPV4_DSLITE:
 	case PPE_PKT_TYPE_IPV6_6RD:
 	default:
@@ -394,6 +424,77 @@ static u32 airoha_ppe_foe_get_entry_hash(struct airoha_foe_entry *hwe)
 	return hash;
 }
 
+static u32 airoha_ppe_foe_get_flow_stats_index(struct airoha_ppe *ppe, u32 hash)
+{
+	if (!airoha_ppe2_is_enabled(ppe->eth))
+		return hash;
+
+	return hash >= PPE_STATS_NUM_ENTRIES ? hash - PPE1_STATS_NUM_ENTRIES
+					     : hash;
+}
+
+static void airoha_ppe_foe_flow_stat_entry_reset(struct airoha_ppe *ppe,
+						 struct airoha_npu *npu,
+						 int index)
+{
+	memset_io(&npu->stats[index], 0, sizeof(*npu->stats));
+	memset(&ppe->foe_stats[index], 0, sizeof(*ppe->foe_stats));
+}
+
+static void airoha_ppe_foe_flow_stats_reset(struct airoha_ppe *ppe,
+					    struct airoha_npu *npu)
+{
+	int i;
+
+	for (i = 0; i < PPE_STATS_NUM_ENTRIES; i++)
+		airoha_ppe_foe_flow_stat_entry_reset(ppe, npu, i);
+}
+
+static void airoha_ppe_foe_flow_stats_update(struct airoha_ppe *ppe,
+					     struct airoha_npu *npu,
+					     struct airoha_foe_entry *hwe,
+					     u32 hash)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	u32 index, pse_port, val, *data, *ib2, *meter;
+	u8 nbq;
+
+	index = airoha_ppe_foe_get_flow_stats_index(ppe, hash);
+	if (index >= PPE_STATS_NUM_ENTRIES)
+		return;
+
+	if (type == PPE_PKT_TYPE_BRIDGE) {
+		data = &hwe->bridge.data;
+		ib2 = &hwe->bridge.ib2;
+		meter = &hwe->bridge.l2.meter;
+	} else if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+		data = &hwe->ipv6.data;
+		ib2 = &hwe->ipv6.ib2;
+		meter = &hwe->ipv6.meter;
+	} else {
+		data = &hwe->ipv4.data;
+		ib2 = &hwe->ipv4.ib2;
+		meter = &hwe->ipv4.l2.meter;
+	}
+
+	airoha_ppe_foe_flow_stat_entry_reset(ppe, npu, index);
+
+	val = FIELD_GET(AIROHA_FOE_CHANNEL | AIROHA_FOE_QID, *data);
+	*data = (*data & ~AIROHA_FOE_ACTDP) |
+		FIELD_PREP(AIROHA_FOE_ACTDP, val);
+
+	val = *ib2 & (AIROHA_FOE_IB2_NBQ | AIROHA_FOE_IB2_PSE_PORT |
+		      AIROHA_FOE_IB2_PSE_QOS | AIROHA_FOE_IB2_FAST_PATH);
+	*meter |= FIELD_PREP(AIROHA_FOE_TUNNEL_MTU, val);
+
+	pse_port = FIELD_GET(AIROHA_FOE_IB2_PSE_PORT, *ib2);
+	nbq = pse_port == 1 ? 6 : 5;
+	*ib2 &= ~(AIROHA_FOE_IB2_NBQ | AIROHA_FOE_IB2_PSE_PORT |
+		  AIROHA_FOE_IB2_PSE_QOS);
+	*ib2 |= FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT, 6) |
+		FIELD_PREP(AIROHA_FOE_IB2_NBQ, nbq);
+}
+
 struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
 						  u32 hash)
 {
@@ -447,6 +548,8 @@ static int airoha_ppe_foe_commit_entry(struct airoha_ppe *ppe,
 	struct airoha_foe_entry *hwe = ppe->foe + hash * sizeof(*hwe);
 	u32 ts = airoha_ppe_get_timestamp(ppe);
 	struct airoha_eth *eth = ppe->eth;
+	struct airoha_npu *npu;
+	int err = 0;
 
 	memcpy(&hwe->d, &e->d, sizeof(*hwe) - sizeof(hwe->ib1));
 	wmb();
@@ -455,31 +558,127 @@ static int airoha_ppe_foe_commit_entry(struct airoha_ppe *ppe,
 	e->ib1 |= FIELD_PREP(AIROHA_FOE_IB1_BIND_TIMESTAMP, ts);
 	hwe->ib1 = e->ib1;
 
+	rcu_read_lock();
+
+	npu = rcu_dereference(eth->npu);
+	if (!npu) {
+		err = -ENODEV;
+		goto unlock;
+	}
+
+	airoha_ppe_foe_flow_stats_update(ppe, npu, hwe, hash);
+
 	if (hash < PPE_SRAM_NUM_ENTRIES) {
 		dma_addr_t addr = ppe->foe_dma + hash * sizeof(*hwe);
 		bool ppe2 = airoha_ppe2_is_enabled(eth) &&
 			    hash >= PPE1_SRAM_NUM_ENTRIES;
-		struct airoha_npu *npu;
-		int err = -ENODEV;
 
-		rcu_read_lock();
-		npu = rcu_dereference(eth->npu);
-		if (npu)
-			err = npu->ops.ppe_foe_commit_entry(npu, addr,
-							    sizeof(*hwe), hash,
-							    ppe2);
-		rcu_read_unlock();
+		err = npu->ops.ppe_foe_commit_entry(npu, addr, sizeof(*hwe),
+						    hash, ppe2);
+	}
+unlock:
+	rcu_read_unlock();
+
+	return err;
+}
 
-		return err;
+static void airoha_ppe_foe_remove_flow(struct airoha_ppe *ppe,
+				       struct airoha_flow_table_entry *e)
+{
+	lockdep_assert_held(&ppe_lock);
+
+	hlist_del_init(&e->list);
+	if (e->hash != 0xffff) {
+		e->data.ib1 &= ~AIROHA_FOE_IB1_BIND_STATE;
+		e->data.ib1 |= FIELD_PREP(AIROHA_FOE_IB1_BIND_STATE,
+					  AIROHA_FOE_STATE_INVALID);
+		airoha_ppe_foe_commit_entry(ppe, &e->data, e->hash);
+		e->hash = 0xffff;
+	}
+	if (e->type == FLOW_TYPE_L2_SUBFLOW) {
+		hlist_del_init(&e->l2_subflow_node);
+		kfree(e);
 	}
+}
+
+static void airoha_ppe_foe_remove_l2_flow(struct airoha_ppe *ppe,
+					  struct airoha_flow_table_entry *e)
+{
+	struct hlist_head *head = &e->l2_flows;
+	struct hlist_node *n;
+
+	lockdep_assert_held(&ppe_lock);
+
+	rhashtable_remove_fast(&ppe->l2_flows, &e->l2_node,
+			       airoha_l2_flow_table_params);
+	hlist_for_each_entry_safe(e, n, head, l2_subflow_node)
+		airoha_ppe_foe_remove_flow(ppe, e);
+}
+
+static void airoha_ppe_foe_flow_remove_entry(struct airoha_ppe *ppe,
+					     struct airoha_flow_table_entry *e)
+{
+	spin_lock_bh(&ppe_lock);
+
+	if (e->type == FLOW_TYPE_L2)
+		airoha_ppe_foe_remove_l2_flow(ppe, e);
+	else
+		airoha_ppe_foe_remove_flow(ppe, e);
+
+	spin_unlock_bh(&ppe_lock);
+}
+
+static int
+airoha_ppe_foe_commit_subflow_entry(struct airoha_ppe *ppe,
+				    struct airoha_flow_table_entry *e,
+				    u32 hash)
+{
+	u32 mask = AIROHA_FOE_IB1_BIND_PACKET_TYPE | AIROHA_FOE_IB1_BIND_UDP;
+	struct airoha_foe_entry *hwe_p, hwe;
+	struct airoha_flow_table_entry *f;
+	struct airoha_foe_mac_info *l2;
+	int type;
+
+	hwe_p = airoha_ppe_foe_get_entry(ppe, hash);
+	if (!hwe_p)
+		return -EINVAL;
+
+	f = kzalloc(sizeof(*f), GFP_ATOMIC);
+	if (!f)
+		return -ENOMEM;
+
+	hlist_add_head(&f->l2_subflow_node, &e->l2_flows);
+	f->type = FLOW_TYPE_L2_SUBFLOW;
+	f->hash = hash;
+
+	memcpy(&hwe, hwe_p, sizeof(*hwe_p));
+	hwe.ib1 = (hwe.ib1 & mask) | (e->data.ib1 & ~mask);
+	l2 = &hwe.bridge.l2;
+	memcpy(l2, &e->data.bridge.l2, sizeof(*l2));
+
+	type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe.ib1);
+	if (type == PPE_PKT_TYPE_IPV4_HNAPT)
+		memcpy(&hwe.ipv4.new_tuple, &hwe.ipv4.orig_tuple,
+		       sizeof(hwe.ipv4.new_tuple));
+	else if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T &&
+		 l2->common.etype == ETH_P_IP)
+		l2->common.etype = ETH_P_IPV6;
+
+	hwe.bridge.ib2 = e->data.bridge.ib2;
+	hwe.bridge.data = e->data.bridge.data;
+	airoha_ppe_foe_commit_entry(ppe, &hwe, hash);
 
 	return 0;
 }
 
-static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe, u32 hash)
+static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe,
+					struct sk_buff *skb,
+					u32 hash)
 {
 	struct airoha_flow_table_entry *e;
+	struct airoha_foe_bridge br = {};
 	struct airoha_foe_entry *hwe;
+	bool commit_done = false;
 	struct hlist_node *n;
 	u32 index, state;
 
@@ -495,21 +694,68 @@ static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe, u32 hash)
 
 	index = airoha_ppe_foe_get_entry_hash(hwe);
 	hlist_for_each_entry_safe(e, n, &ppe->foe_flow[index], list) {
-		if (airoha_ppe_foe_compare_entry(e, hwe)) {
-			airoha_ppe_foe_commit_entry(ppe, &e->data, hash);
-			e->hash = hash;
-			break;
+		if (e->type == FLOW_TYPE_L2_SUBFLOW) {
+			state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, hwe->ib1);
+			if (state != AIROHA_FOE_STATE_BIND) {
+				e->hash = 0xffff;
+				airoha_ppe_foe_remove_flow(ppe, e);
+			}
+			continue;
+		}
+
+		if (commit_done || !airoha_ppe_foe_compare_entry(e, hwe)) {
+			e->hash = 0xffff;
+			continue;
 		}
+
+		airoha_ppe_foe_commit_entry(ppe, &e->data, hash);
+		commit_done = true;
+		e->hash = hash;
 	}
+
+	if (commit_done)
+		goto unlock;
+
+	airoha_ppe_foe_set_bridge_addrs(&br, eth_hdr(skb));
+	e = rhashtable_lookup_fast(&ppe->l2_flows, &br,
+				   airoha_l2_flow_table_params);
+	if (e)
+		airoha_ppe_foe_commit_subflow_entry(ppe, e, hash);
 unlock:
 	spin_unlock_bh(&ppe_lock);
 }
 
+static int
+airoha_ppe_foe_l2_flow_commit_entry(struct airoha_ppe *ppe,
+				    struct airoha_flow_table_entry *e)
+{
+	struct airoha_flow_table_entry *prev;
+
+	e->type = FLOW_TYPE_L2;
+	prev = rhashtable_lookup_get_insert_fast(&ppe->l2_flows, &e->l2_node,
+						 airoha_l2_flow_table_params);
+	if (!prev)
+		return 0;
+
+	if (IS_ERR(prev))
+		return PTR_ERR(prev);
+
+	return rhashtable_replace_fast(&ppe->l2_flows, &prev->l2_node,
+				       &e->l2_node,
+				       airoha_l2_flow_table_params);
+}
+
 static int airoha_ppe_foe_flow_commit_entry(struct airoha_ppe *ppe,
 					    struct airoha_flow_table_entry *e)
 {
-	u32 hash = airoha_ppe_foe_get_entry_hash(&e->data);
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, e->data.ib1);
+	u32 hash;
+
+	if (type == PPE_PKT_TYPE_BRIDGE)
+		return airoha_ppe_foe_l2_flow_commit_entry(ppe, e);
 
+	hash = airoha_ppe_foe_get_entry_hash(&e->data);
+	e->type = FLOW_TYPE_L4;
 	e->hash = 0xffff;
 
 	spin_lock_bh(&ppe_lock);
@@ -519,23 +765,98 @@ static int airoha_ppe_foe_flow_commit_entry(struct airoha_ppe *ppe,
 	return 0;
 }
 
-static void airoha_ppe_foe_flow_remove_entry(struct airoha_ppe *ppe,
+static int airoha_ppe_get_entry_idle_time(struct airoha_ppe *ppe, u32 ib1)
+{
+	u32 state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, ib1);
+	u32 ts, ts_mask, now = airoha_ppe_get_timestamp(ppe);
+	int idle;
+
+	if (state == AIROHA_FOE_STATE_BIND) {
+		ts = FIELD_GET(AIROHA_FOE_IB1_BIND_TIMESTAMP, ib1);
+		ts_mask = AIROHA_FOE_IB1_BIND_TIMESTAMP;
+	} else {
+		ts = FIELD_GET(AIROHA_FOE_IB1_UNBIND_TIMESTAMP, ib1);
+		now = FIELD_GET(AIROHA_FOE_IB1_UNBIND_TIMESTAMP, now);
+		ts_mask = AIROHA_FOE_IB1_UNBIND_TIMESTAMP;
+	}
+	idle = now - ts;
+
+	return idle < 0 ? idle + ts_mask + 1 : idle;
+}
+
+static void
+airoha_ppe_foe_flow_l2_entry_update(struct airoha_ppe *ppe,
+				    struct airoha_flow_table_entry *e)
+{
+	int min_idle = airoha_ppe_get_entry_idle_time(ppe, e->data.ib1);
+	struct airoha_flow_table_entry *iter;
+	struct hlist_node *n;
+
+	lockdep_assert_held(&ppe_lock);
+
+	hlist_for_each_entry_safe(iter, n, &e->l2_flows, l2_subflow_node) {
+		struct airoha_foe_entry *hwe;
+		u32 ib1, state;
+		int idle;
+
+		hwe = airoha_ppe_foe_get_entry(ppe, iter->hash);
+		ib1 = READ_ONCE(hwe->ib1);
+
+		state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, ib1);
+		if (state != AIROHA_FOE_STATE_BIND) {
+			iter->hash = 0xffff;
+			airoha_ppe_foe_remove_flow(ppe, iter);
+			continue;
+		}
+
+		idle = airoha_ppe_get_entry_idle_time(ppe, ib1);
+		if (idle >= min_idle)
+			continue;
+
+		min_idle = idle;
+		e->data.ib1 &= ~AIROHA_FOE_IB1_BIND_TIMESTAMP;
+		e->data.ib1 |= ib1 & AIROHA_FOE_IB1_BIND_TIMESTAMP;
+	}
+}
+
+static void airoha_ppe_foe_flow_entry_update(struct airoha_ppe *ppe,
 					     struct airoha_flow_table_entry *e)
 {
+	struct airoha_foe_entry *hwe_p, hwe = {};
+
 	spin_lock_bh(&ppe_lock);
 
-	hlist_del_init(&e->list);
-	if (e->hash != 0xffff) {
-		e->data.ib1 &= ~AIROHA_FOE_IB1_BIND_STATE;
-		e->data.ib1 |= FIELD_PREP(AIROHA_FOE_IB1_BIND_STATE,
-					  AIROHA_FOE_STATE_INVALID);
-		airoha_ppe_foe_commit_entry(ppe, &e->data, e->hash);
+	if (e->type == FLOW_TYPE_L2) {
+		airoha_ppe_foe_flow_l2_entry_update(ppe, e);
+		goto unlock;
+	}
+
+	if (e->hash == 0xffff)
+		goto unlock;
+
+	hwe_p = airoha_ppe_foe_get_entry(ppe, e->hash);
+	if (!hwe_p)
+		goto unlock;
+
+	memcpy(&hwe, hwe_p, sizeof(*hwe_p));
+	if (!airoha_ppe_foe_compare_entry(e, &hwe)) {
 		e->hash = 0xffff;
+		goto unlock;
 	}
 
+	e->data.ib1 = hwe.ib1;
+unlock:
 	spin_unlock_bh(&ppe_lock);
 }
 
+static int airoha_ppe_entry_idle_time(struct airoha_ppe *ppe,
+				      struct airoha_flow_table_entry *e)
+{
+	airoha_ppe_foe_flow_entry_update(ppe, e);
+
+	return airoha_ppe_get_entry_idle_time(ppe, e->data.ib1);
+}
+
 static int airoha_ppe_flow_offload_replace(struct airoha_gdm_port *port,
 					   struct flow_cls_offload *f)
 {
@@ -751,6 +1072,60 @@ static int airoha_ppe_flow_offload_destroy(struct airoha_gdm_port *port,
 	return 0;
 }
 
+void airoha_ppe_foe_entry_get_stats(struct airoha_ppe *ppe, u32 hash,
+				    struct airoha_foe_stats64 *stats)
+{
+	u32 index = airoha_ppe_foe_get_flow_stats_index(ppe, hash);
+	struct airoha_eth *eth = ppe->eth;
+	struct airoha_npu *npu;
+
+	if (index >= PPE_STATS_NUM_ENTRIES)
+		return;
+
+	rcu_read_lock();
+
+	npu = rcu_dereference(eth->npu);
+	if (npu) {
+		u64 packets = ppe->foe_stats[index].packets;
+		u64 bytes = ppe->foe_stats[index].bytes;
+		struct airoha_foe_stats npu_stats;
+
+		memcpy_fromio(&npu_stats, &npu->stats[index],
+			      sizeof(*npu->stats));
+		stats->packets = packets << 32 | npu_stats.packets;
+		stats->bytes = bytes << 32 | npu_stats.bytes;
+	}
+
+	rcu_read_unlock();
+}
+
+static int airoha_ppe_flow_offload_stats(struct airoha_gdm_port *port,
+					 struct flow_cls_offload *f)
+{
+	struct airoha_eth *eth = port->qdma->eth;
+	struct airoha_flow_table_entry *e;
+	u32 idle;
+
+	e = rhashtable_lookup(&eth->flow_table, &f->cookie,
+			      airoha_flow_table_params);
+	if (!e)
+		return -ENOENT;
+
+	idle = airoha_ppe_entry_idle_time(eth->ppe, e);
+	f->stats.lastused = jiffies - idle * HZ;
+
+	if (e->hash != 0xffff) {
+		struct airoha_foe_stats64 stats = {};
+
+		airoha_ppe_foe_entry_get_stats(eth->ppe, e->hash, &stats);
+		f->stats.pkts += (stats.packets - e->stats.packets);
+		f->stats.bytes += (stats.bytes - e->stats.bytes);
+		e->stats = stats;
+	}
+
+	return 0;
+}
+
 static int airoha_ppe_flow_offload_cmd(struct airoha_gdm_port *port,
 				       struct flow_cls_offload *f)
 {
@@ -759,6 +1134,8 @@ static int airoha_ppe_flow_offload_cmd(struct airoha_gdm_port *port,
 		return airoha_ppe_flow_offload_replace(port, f);
 	case FLOW_CLS_DESTROY:
 		return airoha_ppe_flow_offload_destroy(port, f);
+	case FLOW_CLS_STATS:
+		return airoha_ppe_flow_offload_stats(port, f);
 	default:
 		break;
 	}
@@ -784,11 +1161,12 @@ static int airoha_ppe_flush_sram_entries(struct airoha_ppe *ppe,
 
 static struct airoha_npu *airoha_ppe_npu_get(struct airoha_eth *eth)
 {
-	struct airoha_npu *npu = airoha_npu_get(eth->dev);
+	struct airoha_npu *npu = airoha_npu_get(eth->dev,
+						&eth->ppe->foe_stats_dma);
 
 	if (IS_ERR(npu)) {
 		request_module("airoha-npu");
-		npu = airoha_npu_get(eth->dev);
+		npu = airoha_npu_get(eth->dev, &eth->ppe->foe_stats_dma);
 	}
 
 	return npu;
@@ -811,6 +1189,8 @@ static int airoha_ppe_offload_setup(struct airoha_eth *eth)
 	if (err)
 		goto error_npu_put;
 
+	airoha_ppe_foe_flow_stats_reset(eth->ppe, npu);
+
 	rcu_assign_pointer(eth->npu, npu);
 	synchronize_rcu();
 
@@ -822,18 +1202,13 @@ error_npu_put:
 	return err;
 }
 
-int airoha_ppe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
-				 void *cb_priv)
+int airoha_ppe_setup_tc_block_cb(struct net_device *dev, void *type_data)
 {
-	struct flow_cls_offload *cls = type_data;
-	struct net_device *dev = cb_priv;
 	struct airoha_gdm_port *port = netdev_priv(dev);
+	struct flow_cls_offload *cls = type_data;
 	struct airoha_eth *eth = port->qdma->eth;
 	int err = 0;
 
-	if (!tc_can_offload(dev) || type != TC_SETUP_CLSFLOWER)
-		return -EOPNOTSUPP;
-
 	mutex_lock(&flow_offload_mutex);
 
 	if (!eth->npu)
@@ -846,7 +1221,8 @@ int airoha_ppe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	return err;
 }
 
-void airoha_ppe_check_skb(struct airoha_ppe *ppe, u16 hash)
+void airoha_ppe_check_skb(struct airoha_ppe *ppe, struct sk_buff *skb,
+			  u16 hash)
 {
 	u16 now, diff;
 
@@ -859,7 +1235,7 @@ void airoha_ppe_check_skb(struct airoha_ppe *ppe, u16 hash)
 		return;
 
 	ppe->foe_check_time[hash] = now;
-	airoha_ppe_foe_insert_entry(ppe, hash);
+	airoha_ppe_foe_insert_entry(ppe, skb, hash);
 }
 
 int airoha_ppe_init(struct airoha_eth *eth)
@@ -886,13 +1262,33 @@ int airoha_ppe_init(struct airoha_eth *eth)
 	if (!ppe->foe_flow)
 		return -ENOMEM;
 
+	foe_size = PPE_STATS_NUM_ENTRIES * sizeof(*ppe->foe_stats);
+	if (foe_size) {
+		ppe->foe_stats = dmam_alloc_coherent(eth->dev, foe_size,
+						     &ppe->foe_stats_dma,
+						     GFP_KERNEL);
+		if (!ppe->foe_stats)
+			return -ENOMEM;
+	}
+
 	err = rhashtable_init(&eth->flow_table, &airoha_flow_table_params);
 	if (err)
 		return err;
 
+	err = rhashtable_init(&ppe->l2_flows, &airoha_l2_flow_table_params);
+	if (err)
+		goto error_flow_table_destroy;
+
 	err = airoha_ppe_debugfs_init(ppe);
 	if (err)
-		rhashtable_destroy(&eth->flow_table);
+		goto error_l2_flow_table_destroy;
+
+	return 0;
+
+error_l2_flow_table_destroy:
+	rhashtable_destroy(&ppe->l2_flows);
+error_flow_table_destroy:
+	rhashtable_destroy(&eth->flow_table);
 
 	return err;
 }
@@ -909,6 +1305,7 @@ void airoha_ppe_deinit(struct airoha_eth *eth)
 	}
 	rcu_read_unlock();
 
+	rhashtable_destroy(&eth->ppe->l2_flows);
 	rhashtable_destroy(&eth->flow_table);
 	debugfs_remove(eth->ppe->debugfs_dir);
 }
diff --git a/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c
index 3cdc6fd53fc7..05a756233f6a 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c
@@ -61,6 +61,7 @@ static int airoha_ppe_debugfs_foe_show(struct seq_file *m, void *private,
 		u16 *src_port = NULL, *dest_port = NULL;
 		struct airoha_foe_mac_info_common *l2;
 		unsigned char h_source[ETH_ALEN] = {};
+		struct airoha_foe_stats64 stats = {};
 		unsigned char h_dest[ETH_ALEN];
 		struct airoha_foe_entry *hwe;
 		u32 type, state, ib2, data;
@@ -144,14 +145,18 @@ static int airoha_ppe_debugfs_foe_show(struct seq_file *m, void *private,
 				cpu_to_be16(hwe->ipv4.l2.src_mac_lo);
 		}
 
+		airoha_ppe_foe_entry_get_stats(ppe, i, &stats);
+
 		*((__be32 *)h_dest) = cpu_to_be32(l2->dest_mac_hi);
 		*((__be16 *)&h_dest[4]) = cpu_to_be16(l2->dest_mac_lo);
 		*((__be32 *)h_source) = cpu_to_be32(l2->src_mac_hi);
 
 		seq_printf(m, " eth=%pM->%pM etype=%04x data=%08x"
-			      " vlan=%d,%d ib1=%08x ib2=%08x\n",
+			      " vlan=%d,%d ib1=%08x ib2=%08x"
+			      " packets=%llu bytes=%llu\n",
 			   h_source, h_dest, l2->etype, data,
-			   l2->vlan1, l2->vlan2, hwe->ib1, ib2);
+			   l2->vlan1, l2->vlan2, hwe->ib1, ib2,
+			   stats.packets, stats.bytes);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
index 8146cde4e8ba..d931530fc96f 100644
--- a/drivers/net/ethernet/airoha/airoha_regs.h
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -283,6 +283,7 @@
 #define PPE_HASH_SEED				0x12345678
 
 #define REG_PPE_DFT_CPORT0(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x248)
+#define DFT_CPORT_MASK(_n)			GENMASK(3 + ((_n) << 2), ((_n) << 2))
 
 #define REG_PPE_DFT_CPORT1(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x24c)
 
@@ -422,11 +423,12 @@
 	 ((_n) == 2) ? 0x0720 :		\
 	 ((_n) == 1) ? 0x0024 : 0x0020)
 
-#define REG_INT_ENABLE(_n)		\
-	(((_n) == 4) ? 0x0750 :		\
-	 ((_n) == 3) ? 0x0744 :		\
-	 ((_n) == 2) ? 0x0740 :		\
-	 ((_n) == 1) ? 0x002c : 0x0028)
+#define REG_INT_ENABLE(_b, _n)		\
+	(((_n) == 4) ? 0x0750 + ((_b) << 5) :	\
+	 ((_n) == 3) ? 0x0744 + ((_b) << 5) :	\
+	 ((_n) == 2) ? 0x0740 + ((_b) << 5) :	\
+	 ((_n) == 1) ? 0x002c + ((_b) << 3) :	\
+		       0x0028 + ((_b) << 3))
 
 /* QDMA_CSR_INT_ENABLE1 */
 #define RX15_COHERENT_INT_MASK		BIT(31)
@@ -461,6 +463,26 @@
 #define IRQ0_FULL_INT_MASK		BIT(1)
 #define IRQ0_INT_MASK			BIT(0)
 
+#define RX_COHERENT_LOW_INT_MASK				\
+	(RX15_COHERENT_INT_MASK | RX14_COHERENT_INT_MASK |	\
+	 RX13_COHERENT_INT_MASK | RX12_COHERENT_INT_MASK |	\
+	 RX11_COHERENT_INT_MASK | RX10_COHERENT_INT_MASK |	\
+	 RX9_COHERENT_INT_MASK | RX8_COHERENT_INT_MASK |	\
+	 RX7_COHERENT_INT_MASK | RX6_COHERENT_INT_MASK |	\
+	 RX5_COHERENT_INT_MASK | RX4_COHERENT_INT_MASK |	\
+	 RX3_COHERENT_INT_MASK | RX2_COHERENT_INT_MASK |	\
+	 RX1_COHERENT_INT_MASK | RX0_COHERENT_INT_MASK)
+
+#define RX_COHERENT_LOW_OFFSET	__ffs(RX_COHERENT_LOW_INT_MASK)
+#define INT_RX0_MASK(_n)					\
+	(((_n) << RX_COHERENT_LOW_OFFSET) & RX_COHERENT_LOW_INT_MASK)
+
+#define TX_COHERENT_LOW_INT_MASK				\
+	(TX7_COHERENT_INT_MASK | TX6_COHERENT_INT_MASK |	\
+	 TX5_COHERENT_INT_MASK | TX4_COHERENT_INT_MASK |	\
+	 TX3_COHERENT_INT_MASK | TX2_COHERENT_INT_MASK |	\
+	 TX1_COHERENT_INT_MASK | TX0_COHERENT_INT_MASK)
+
 #define TX_DONE_INT_MASK(_n)					\
 	((_n) ? IRQ1_INT_MASK | IRQ1_FULL_INT_MASK		\
 	      : IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
@@ -469,17 +491,6 @@
 	(IRQ1_INT_MASK | IRQ1_FULL_INT_MASK |			\
 	 IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
 
-#define INT_IDX0_MASK						\
-	(TX0_COHERENT_INT_MASK | TX1_COHERENT_INT_MASK |	\
-	 TX2_COHERENT_INT_MASK | TX3_COHERENT_INT_MASK |	\
-	 TX4_COHERENT_INT_MASK | TX5_COHERENT_INT_MASK |	\
-	 TX6_COHERENT_INT_MASK | TX7_COHERENT_INT_MASK |	\
-	 RX0_COHERENT_INT_MASK | RX1_COHERENT_INT_MASK |	\
-	 RX2_COHERENT_INT_MASK | RX3_COHERENT_INT_MASK |	\
-	 RX4_COHERENT_INT_MASK | RX7_COHERENT_INT_MASK |	\
-	 RX8_COHERENT_INT_MASK | RX9_COHERENT_INT_MASK |	\
-	 RX15_COHERENT_INT_MASK | INT_TX_MASK)
-
 /* QDMA_CSR_INT_ENABLE2 */
 #define RX15_NO_CPU_DSCP_INT_MASK	BIT(31)
 #define RX14_NO_CPU_DSCP_INT_MASK	BIT(30)
@@ -514,19 +525,121 @@
 #define RX1_DONE_INT_MASK		BIT(1)
 #define RX0_DONE_INT_MASK		BIT(0)
 
-#define RX_DONE_INT_MASK					\
-	(RX0_DONE_INT_MASK | RX1_DONE_INT_MASK |		\
-	 RX2_DONE_INT_MASK | RX3_DONE_INT_MASK |		\
-	 RX4_DONE_INT_MASK | RX7_DONE_INT_MASK |		\
-	 RX8_DONE_INT_MASK | RX9_DONE_INT_MASK |		\
-	 RX15_DONE_INT_MASK)
-#define INT_IDX1_MASK						\
-	(RX_DONE_INT_MASK |					\
-	 RX0_NO_CPU_DSCP_INT_MASK | RX1_NO_CPU_DSCP_INT_MASK |	\
-	 RX2_NO_CPU_DSCP_INT_MASK | RX3_NO_CPU_DSCP_INT_MASK |	\
-	 RX4_NO_CPU_DSCP_INT_MASK | RX7_NO_CPU_DSCP_INT_MASK |	\
-	 RX8_NO_CPU_DSCP_INT_MASK | RX9_NO_CPU_DSCP_INT_MASK |	\
-	 RX15_NO_CPU_DSCP_INT_MASK)
+#define RX_NO_CPU_DSCP_LOW_INT_MASK					\
+	(RX15_NO_CPU_DSCP_INT_MASK | RX14_NO_CPU_DSCP_INT_MASK |	\
+	 RX13_NO_CPU_DSCP_INT_MASK | RX12_NO_CPU_DSCP_INT_MASK |	\
+	 RX11_NO_CPU_DSCP_INT_MASK | RX10_NO_CPU_DSCP_INT_MASK |	\
+	 RX9_NO_CPU_DSCP_INT_MASK | RX8_NO_CPU_DSCP_INT_MASK |		\
+	 RX7_NO_CPU_DSCP_INT_MASK | RX6_NO_CPU_DSCP_INT_MASK |		\
+	 RX5_NO_CPU_DSCP_INT_MASK | RX4_NO_CPU_DSCP_INT_MASK |		\
+	 RX3_NO_CPU_DSCP_INT_MASK | RX2_NO_CPU_DSCP_INT_MASK |		\
+	 RX1_NO_CPU_DSCP_INT_MASK | RX0_NO_CPU_DSCP_INT_MASK)
+
+#define RX_DONE_LOW_INT_MASK				\
+	(RX15_DONE_INT_MASK | RX14_DONE_INT_MASK |	\
+	 RX13_DONE_INT_MASK | RX12_DONE_INT_MASK |	\
+	 RX11_DONE_INT_MASK | RX10_DONE_INT_MASK |	\
+	 RX9_DONE_INT_MASK | RX8_DONE_INT_MASK |	\
+	 RX7_DONE_INT_MASK | RX6_DONE_INT_MASK |	\
+	 RX5_DONE_INT_MASK | RX4_DONE_INT_MASK |	\
+	 RX3_DONE_INT_MASK | RX2_DONE_INT_MASK |	\
+	 RX1_DONE_INT_MASK | RX0_DONE_INT_MASK)
+
+#define RX_NO_CPU_DSCP_LOW_OFFSET	__ffs(RX_NO_CPU_DSCP_LOW_INT_MASK)
+#define INT_RX1_MASK(_n)							\
+	((((_n) << RX_NO_CPU_DSCP_LOW_OFFSET) & RX_NO_CPU_DSCP_LOW_INT_MASK) |	\
+	 (RX_DONE_LOW_INT_MASK & (_n)))
+
+/* QDMA_CSR_INT_ENABLE3 */
+#define RX31_NO_CPU_DSCP_INT_MASK	BIT(31)
+#define RX30_NO_CPU_DSCP_INT_MASK	BIT(30)
+#define RX29_NO_CPU_DSCP_INT_MASK	BIT(29)
+#define RX28_NO_CPU_DSCP_INT_MASK	BIT(28)
+#define RX27_NO_CPU_DSCP_INT_MASK	BIT(27)
+#define RX26_NO_CPU_DSCP_INT_MASK	BIT(26)
+#define RX25_NO_CPU_DSCP_INT_MASK	BIT(25)
+#define RX24_NO_CPU_DSCP_INT_MASK	BIT(24)
+#define RX23_NO_CPU_DSCP_INT_MASK	BIT(23)
+#define RX22_NO_CPU_DSCP_INT_MASK	BIT(22)
+#define RX21_NO_CPU_DSCP_INT_MASK	BIT(21)
+#define RX20_NO_CPU_DSCP_INT_MASK	BIT(20)
+#define RX19_NO_CPU_DSCP_INT_MASK	BIT(19)
+#define RX18_NO_CPU_DSCP_INT_MASK	BIT(18)
+#define RX17_NO_CPU_DSCP_INT_MASK	BIT(17)
+#define RX16_NO_CPU_DSCP_INT_MASK	BIT(16)
+#define RX31_DONE_INT_MASK		BIT(15)
+#define RX30_DONE_INT_MASK		BIT(14)
+#define RX29_DONE_INT_MASK		BIT(13)
+#define RX28_DONE_INT_MASK		BIT(12)
+#define RX27_DONE_INT_MASK		BIT(11)
+#define RX26_DONE_INT_MASK		BIT(10)
+#define RX25_DONE_INT_MASK		BIT(9)
+#define RX24_DONE_INT_MASK		BIT(8)
+#define RX23_DONE_INT_MASK		BIT(7)
+#define RX22_DONE_INT_MASK		BIT(6)
+#define RX21_DONE_INT_MASK		BIT(5)
+#define RX20_DONE_INT_MASK		BIT(4)
+#define RX19_DONE_INT_MASK		BIT(3)
+#define RX18_DONE_INT_MASK		BIT(2)
+#define RX17_DONE_INT_MASK		BIT(1)
+#define RX16_DONE_INT_MASK		BIT(0)
+
+#define RX_NO_CPU_DSCP_HIGH_INT_MASK					\
+	(RX31_NO_CPU_DSCP_INT_MASK | RX30_NO_CPU_DSCP_INT_MASK |	\
+	 RX29_NO_CPU_DSCP_INT_MASK | RX28_NO_CPU_DSCP_INT_MASK |	\
+	 RX27_NO_CPU_DSCP_INT_MASK | RX26_NO_CPU_DSCP_INT_MASK |	\
+	 RX25_NO_CPU_DSCP_INT_MASK | RX24_NO_CPU_DSCP_INT_MASK |	\
+	 RX23_NO_CPU_DSCP_INT_MASK | RX22_NO_CPU_DSCP_INT_MASK |	\
+	 RX21_NO_CPU_DSCP_INT_MASK | RX20_NO_CPU_DSCP_INT_MASK |	\
+	 RX19_NO_CPU_DSCP_INT_MASK | RX18_NO_CPU_DSCP_INT_MASK |	\
+	 RX17_NO_CPU_DSCP_INT_MASK | RX16_NO_CPU_DSCP_INT_MASK)
+
+#define RX_DONE_HIGH_INT_MASK				\
+	(RX31_DONE_INT_MASK | RX30_DONE_INT_MASK |	\
+	 RX29_DONE_INT_MASK | RX28_DONE_INT_MASK |	\
+	 RX27_DONE_INT_MASK | RX26_DONE_INT_MASK |	\
+	 RX25_DONE_INT_MASK | RX24_DONE_INT_MASK |	\
+	 RX23_DONE_INT_MASK | RX22_DONE_INT_MASK |	\
+	 RX21_DONE_INT_MASK | RX20_DONE_INT_MASK |	\
+	 RX19_DONE_INT_MASK | RX18_DONE_INT_MASK |	\
+	 RX17_DONE_INT_MASK | RX16_DONE_INT_MASK)
+
+#define RX_DONE_INT_MASK	(RX_DONE_HIGH_INT_MASK | RX_DONE_LOW_INT_MASK)
+#define RX_DONE_HIGH_OFFSET	fls(RX_DONE_HIGH_INT_MASK)
+
+#define INT_RX2_MASK(_n)				\
+	((RX_NO_CPU_DSCP_HIGH_INT_MASK & (_n)) |	\
+	 (((_n) >> RX_DONE_HIGH_OFFSET) & RX_DONE_HIGH_INT_MASK))
+
+/* QDMA_CSR_INT_ENABLE4 */
+#define RX31_COHERENT_INT_MASK		BIT(31)
+#define RX30_COHERENT_INT_MASK		BIT(30)
+#define RX29_COHERENT_INT_MASK		BIT(29)
+#define RX28_COHERENT_INT_MASK		BIT(28)
+#define RX27_COHERENT_INT_MASK		BIT(27)
+#define RX26_COHERENT_INT_MASK		BIT(26)
+#define RX25_COHERENT_INT_MASK		BIT(25)
+#define RX24_COHERENT_INT_MASK		BIT(24)
+#define RX23_COHERENT_INT_MASK		BIT(23)
+#define RX22_COHERENT_INT_MASK		BIT(22)
+#define RX21_COHERENT_INT_MASK		BIT(21)
+#define RX20_COHERENT_INT_MASK		BIT(20)
+#define RX19_COHERENT_INT_MASK		BIT(19)
+#define RX18_COHERENT_INT_MASK		BIT(18)
+#define RX17_COHERENT_INT_MASK		BIT(17)
+#define RX16_COHERENT_INT_MASK		BIT(16)
+
+#define RX_COHERENT_HIGH_INT_MASK				\
+	(RX31_COHERENT_INT_MASK | RX30_COHERENT_INT_MASK |	\
+	 RX29_COHERENT_INT_MASK | RX28_COHERENT_INT_MASK |	\
+	 RX27_COHERENT_INT_MASK | RX26_COHERENT_INT_MASK |	\
+	 RX25_COHERENT_INT_MASK | RX24_COHERENT_INT_MASK |	\
+	 RX23_COHERENT_INT_MASK | RX22_COHERENT_INT_MASK |	\
+	 RX21_COHERENT_INT_MASK | RX20_COHERENT_INT_MASK |	\
+	 RX19_COHERENT_INT_MASK | RX18_COHERENT_INT_MASK |	\
+	 RX17_COHERENT_INT_MASK | RX16_COHERENT_INT_MASK)
+
+#define INT_RX3_MASK(_n)	(RX_COHERENT_HIGH_INT_MASK & (_n))
 
 /* QDMA_CSR_INT_ENABLE5 */
 #define TX31_COHERENT_INT_MASK		BIT(31)
@@ -554,19 +667,19 @@
 #define TX9_COHERENT_INT_MASK		BIT(9)
 #define TX8_COHERENT_INT_MASK		BIT(8)
 
-#define INT_IDX4_MASK						\
-	(TX8_COHERENT_INT_MASK | TX9_COHERENT_INT_MASK |	\
-	 TX10_COHERENT_INT_MASK | TX11_COHERENT_INT_MASK |	\
-	 TX12_COHERENT_INT_MASK | TX13_COHERENT_INT_MASK |	\
-	 TX14_COHERENT_INT_MASK | TX15_COHERENT_INT_MASK |	\
-	 TX16_COHERENT_INT_MASK | TX17_COHERENT_INT_MASK |	\
-	 TX18_COHERENT_INT_MASK | TX19_COHERENT_INT_MASK |	\
-	 TX20_COHERENT_INT_MASK | TX21_COHERENT_INT_MASK |	\
-	 TX22_COHERENT_INT_MASK | TX23_COHERENT_INT_MASK |	\
-	 TX24_COHERENT_INT_MASK | TX25_COHERENT_INT_MASK |	\
-	 TX26_COHERENT_INT_MASK | TX27_COHERENT_INT_MASK |	\
-	 TX28_COHERENT_INT_MASK | TX29_COHERENT_INT_MASK |	\
-	 TX30_COHERENT_INT_MASK | TX31_COHERENT_INT_MASK)
+#define TX_COHERENT_HIGH_INT_MASK				\
+	(TX31_COHERENT_INT_MASK | TX30_COHERENT_INT_MASK |	\
+	 TX29_COHERENT_INT_MASK | TX28_COHERENT_INT_MASK |	\
+	 TX27_COHERENT_INT_MASK | TX26_COHERENT_INT_MASK |	\
+	 TX25_COHERENT_INT_MASK | TX24_COHERENT_INT_MASK |	\
+	 TX23_COHERENT_INT_MASK | TX22_COHERENT_INT_MASK |	\
+	 TX21_COHERENT_INT_MASK | TX20_COHERENT_INT_MASK |	\
+	 TX19_COHERENT_INT_MASK | TX18_COHERENT_INT_MASK |	\
+	 TX17_COHERENT_INT_MASK | TX16_COHERENT_INT_MASK |	\
+	 TX15_COHERENT_INT_MASK | TX14_COHERENT_INT_MASK |	\
+	 TX13_COHERENT_INT_MASK | TX12_COHERENT_INT_MASK |	\
+	 TX11_COHERENT_INT_MASK | TX10_COHERENT_INT_MASK |	\
+	 TX9_COHERENT_INT_MASK | TX8_COHERENT_INT_MASK)
 
 #define REG_TX_IRQ_BASE(_n)		((_n) ? 0x0048 : 0x0050)
 
@@ -691,6 +804,12 @@
 #define REG_TRTCM_DATA_LOW(_n)		((_n) + 0x8)
 #define REG_TRTCM_DATA_HIGH(_n)		((_n) + 0xc)
 
+#define RATE_LIMIT_PARAM_RW_MASK	BIT(31)
+#define RATE_LIMIT_PARAM_RW_DONE_MASK	BIT(30)
+#define RATE_LIMIT_PARAM_TYPE_MASK	GENMASK(29, 28)
+#define RATE_LIMIT_METER_GROUP_MASK	GENMASK(27, 26)
+#define RATE_LIMIT_PARAM_INDEX_MASK	GENMASK(23, 16)
+
 #define REG_TXWRR_MODE_CFG		0x1020
 #define TWRR_WEIGHT_SCALE_MASK		BIT(31)
 #define TWRR_WEIGHT_BASE_MASK		BIT(3)
diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index c83a0a80d533..097bb092bdb8 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -5,11 +5,6 @@
 
 #include "core.h"
 
-struct pdsc_wait_context {
-	struct pdsc_qcq *qcq;
-	struct completion wait_completion;
-};
-
 static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
 {
 	union pds_core_notifyq_comp *comp;
@@ -109,10 +104,10 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
 		q_info = &q->info[q->tail_idx];
 		q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1);
 
-		/* Copy out the completion data */
-		memcpy(q_info->dest, comp, sizeof(*comp));
-
-		complete_all(&q_info->wc->wait_completion);
+		if (!completion_done(&q_info->completion)) {
+			memcpy(q_info->dest, comp, sizeof(*comp));
+			complete(&q_info->completion);
+		}
 
 		if (cq->tail_idx == cq->num_descs - 1)
 			cq->done_color = !cq->done_color;
@@ -162,8 +157,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
 static int __pdsc_adminq_post(struct pdsc *pdsc,
 			      struct pdsc_qcq *qcq,
 			      union pds_core_adminq_cmd *cmd,
-			      union pds_core_adminq_comp *comp,
-			      struct pdsc_wait_context *wc)
+			      union pds_core_adminq_comp *comp)
 {
 	struct pdsc_queue *q = &qcq->q;
 	struct pdsc_q_info *q_info;
@@ -205,9 +199,9 @@ static int __pdsc_adminq_post(struct pdsc *pdsc,
 	/* Post the request */
 	index = q->head_idx;
 	q_info = &q->info[index];
-	q_info->wc = wc;
 	q_info->dest = comp;
 	memcpy(q_info->desc, cmd, sizeof(*cmd));
+	reinit_completion(&q_info->completion);
 
 	dev_dbg(pdsc->dev, "head_idx %d tail_idx %d\n",
 		q->head_idx, q->tail_idx);
@@ -231,16 +225,13 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 		     union pds_core_adminq_comp *comp,
 		     bool fast_poll)
 {
-	struct pdsc_wait_context wc = {
-		.wait_completion =
-			COMPLETION_INITIALIZER_ONSTACK(wc.wait_completion),
-	};
-	unsigned long poll_interval = 1;
+	unsigned long poll_interval = 200;
 	unsigned long poll_jiffies;
 	unsigned long time_limit;
 	unsigned long time_start;
 	unsigned long time_done;
 	unsigned long remaining;
+	struct completion *wc;
 	int err = 0;
 	int index;
 
@@ -250,20 +241,19 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 		return -ENXIO;
 	}
 
-	wc.qcq = &pdsc->adminqcq;
-	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
+	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp);
 	if (index < 0) {
 		err = index;
 		goto err_out;
 	}
 
+	wc = &pdsc->adminqcq.q.info[index].completion;
 	time_start = jiffies;
 	time_limit = time_start + HZ * pdsc->devcmd_timeout;
 	do {
 		/* Timeslice the actual wait to catch IO errors etc early */
-		poll_jiffies = msecs_to_jiffies(poll_interval);
-		remaining = wait_for_completion_timeout(&wc.wait_completion,
-							poll_jiffies);
+		poll_jiffies = usecs_to_jiffies(poll_interval);
+		remaining = wait_for_completion_timeout(wc, poll_jiffies);
 		if (remaining)
 			break;
 
@@ -292,9 +282,11 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 	dev_dbg(pdsc->dev, "%s: elapsed %d msecs\n",
 		__func__, jiffies_to_msecs(time_done - time_start));
 
-	/* Check the results */
-	if (time_after_eq(time_done, time_limit))
+	/* Check the results and clear an un-completed timeout */
+	if (time_after_eq(time_done, time_limit) && !completion_done(wc)) {
 		err = -ETIMEDOUT;
+		complete(wc);
+	}
 
 	dev_dbg(pdsc->dev, "read admin queue completion idx %d:\n", index);
 	dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1,
diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c
index eeb72b1809ea..92f359f2b449 100644
--- a/drivers/net/ethernet/amd/pds_core/auxbus.c
+++ b/drivers/net/ethernet/amd/pds_core/auxbus.c
@@ -107,9 +107,6 @@ int pds_client_adminq_cmd(struct pds_auxiliary_dev *padev,
 	dev_dbg(pf->dev, "%s: %s opcode %d\n",
 		__func__, dev_name(&padev->aux_dev.dev), req->opcode);
 
-	if (pf->state)
-		return -ENXIO;
-
 	/* Wrap the client's request */
 	cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD;
 	cmd.client_request.client_id = cpu_to_le16(padev->client_id);
@@ -189,7 +186,6 @@ void pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf,
 	pds_client_unregister(pf, padev->client_id);
 	auxiliary_device_delete(&padev->aux_dev);
 	auxiliary_device_uninit(&padev->aux_dev);
-	padev->client_id = 0;
 	*pd_ptr = NULL;
 
 	mutex_unlock(&pf->config_lock);
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 1eb0d92786f7..076dfe2910c7 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -167,8 +167,10 @@ static void pdsc_q_map(struct pdsc_queue *q, void *base, dma_addr_t base_pa)
 	q->base = base;
 	q->base_pa = base_pa;
 
-	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++)
+	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) {
 		cur->desc = base + (i * q->desc_size);
+		init_completion(&cur->completion);
+	}
 }
 
 static void pdsc_cq_map(struct pdsc_cq *cq, void *base, dma_addr_t base_pa)
@@ -325,10 +327,7 @@ static int pdsc_core_init(struct pdsc *pdsc)
 	size_t sz;
 	int err;
 
-	/* Scale the descriptor ring length based on number of CPUs and VFs */
-	numdescs = max_t(int, PDSC_ADMINQ_MIN_LENGTH, num_online_cpus());
-	numdescs += 2 * pci_sriov_get_totalvfs(pdsc->pdev);
-	numdescs = roundup_pow_of_two(numdescs);
+	numdescs = PDSC_ADMINQ_MAX_LENGTH;
 	err = pdsc_qcq_alloc(pdsc, PDS_CORE_QTYPE_ADMINQ, 0, "adminq",
 			     PDS_CORE_QCQ_F_CORE | PDS_CORE_QCQ_F_INTR,
 			     numdescs,
@@ -403,6 +402,7 @@ err_out_uninit:
 
 static struct pdsc_viftype pdsc_viftype_defaults[] = {
 	[PDS_DEV_TYPE_FWCTL] = { .name = PDS_DEV_TYPE_FWCTL_STR,
+				 .enabled = true,
 				 .vif_id = PDS_DEV_TYPE_FWCTL,
 				 .dl_id = -1 },
 	[PDS_DEV_TYPE_VDPA] = { .name = PDS_DEV_TYPE_VDPA_STR,
@@ -415,7 +415,8 @@ static int pdsc_viftypes_init(struct pdsc *pdsc)
 {
 	enum pds_core_vif_types vt;
 
-	pdsc->viftype_status = kzalloc(sizeof(pdsc_viftype_defaults),
+	pdsc->viftype_status = kcalloc(ARRAY_SIZE(pdsc_viftype_defaults),
+				       sizeof(*pdsc->viftype_status),
 				       GFP_KERNEL);
 	if (!pdsc->viftype_status)
 		return -ENOMEM;
@@ -432,9 +433,6 @@ static int pdsc_viftypes_init(struct pdsc *pdsc)
 		/* See what the Core device has for support */
 		vt_support = !!le16_to_cpu(pdsc->dev_ident.vif_types[vt]);
 
-		if (vt == PDS_DEV_TYPE_FWCTL)
-			pdsc->viftype_status[vt].enabled = true;
-
 		dev_dbg(pdsc->dev, "VIF %s is %ssupported\n",
 			pdsc->viftype_status[vt].name,
 			vt_support ? "" : "not ");
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index 0bf320c43083..0b53a1fab46d 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -16,7 +16,7 @@
 
 #define PDSC_WATCHDOG_SECS	5
 #define PDSC_QUEUE_NAME_MAX_SZ  16
-#define PDSC_ADMINQ_MIN_LENGTH	16	/* must be a power of two */
+#define PDSC_ADMINQ_MAX_LENGTH	16	/* must be a power of two */
 #define PDSC_NOTIFYQ_LENGTH	64	/* must be a power of two */
 #define PDSC_TEARDOWN_RECOVERY	false
 #define PDSC_TEARDOWN_REMOVING	true
@@ -96,7 +96,7 @@ struct pdsc_q_info {
 	unsigned int bytes;
 	unsigned int nbufs;
 	struct pdsc_buf_info bufs[PDS_CORE_MAX_FRAGS];
-	struct pdsc_wait_context *wc;
+	struct completion completion;
 	void *dest;
 };
 
diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c
index ac37a4e738ae..04c5e3abd8d7 100644
--- a/drivers/net/ethernet/amd/pds_core/debugfs.c
+++ b/drivers/net/ethernet/amd/pds_core/debugfs.c
@@ -154,8 +154,9 @@ void pdsc_debugfs_add_qcq(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 		debugfs_create_u32("index", 0400, intr_dentry, &intr->index);
 		debugfs_create_u32("vector", 0400, intr_dentry, &intr->vector);
 
-		intr_ctrl_regset = kzalloc(sizeof(*intr_ctrl_regset),
-					   GFP_KERNEL);
+		intr_ctrl_regset = devm_kzalloc(pdsc->dev,
+						sizeof(*intr_ctrl_regset),
+						GFP_KERNEL);
 		if (!intr_ctrl_regset)
 			return;
 		intr_ctrl_regset->regs = intr_ctrl_regs;
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index c5c787df61a4..d8dc39da4161 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -105,7 +105,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 		.fw_control.opcode = PDS_CORE_CMD_FW_CONTROL,
 		.fw_control.oper = PDS_CORE_FW_GET_LIST,
 	};
-	struct pds_core_fw_list_info fw_list;
+	struct pds_core_fw_list_info fw_list = {};
 	struct pdsc *pdsc = devlink_priv(dl);
 	union pds_core_dev_comp comp;
 	char buf[32];
@@ -118,8 +118,6 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 	if (!err)
 		memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
 	mutex_unlock(&pdsc->devcmd_lock);
-	if (err && err != -EIO)
-		return err;
 
 	listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names));
 	for (i = 0; i < listlen; i++) {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index e3d33f5b9642..e1296cbf4ff3 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -791,6 +791,11 @@
 #define PCS_V2_RV_WINDOW_SELECT		0x1064
 #define PCS_V2_YC_WINDOW_DEF		0x18060
 #define PCS_V2_YC_WINDOW_SELECT		0x18064
+#define PCS_V3_RN_WINDOW_DEF		0xf8078
+#define PCS_V3_RN_WINDOW_SELECT		0xf807c
+
+#define PCS_RN_SMN_BASE_ADDR		0x11e00000
+#define PCS_RN_PORT_ADDR_SIZE		0x100000
 
 /* PCS register entry bit positions and sizes */
 #define PCS_V2_WINDOW_DEF_OFFSET_INDEX	6
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index 7dba849bcd6b..7c8a19988a52 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -264,8 +264,13 @@ static int xgbe_map_rx_buffer(struct xgbe_prv_data *pdata,
 	}
 
 	/* Set up the header page info */
-	xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
-			     XGBE_SKB_ALLOC_SIZE);
+	if (pdata->netdev->features & NETIF_F_RXCSUM) {
+		xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+				     XGBE_SKB_ALLOC_SIZE);
+	} else {
+		xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+				     pdata->rx_buf_size);
+	}
 
 	/* Set up the buffer page info */
 	xgbe_set_buffer_data(&rdata->rx.buf, &ring->rx_buf_pa,
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index b51a3666dddb..466b5f6e5578 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -11,9 +11,11 @@
 #include <linux/bitrev.h>
 #include <linux/crc32.h>
 #include <linux/crc32poly.h>
+#include <linux/pci.h>
 
 #include "xgbe.h"
 #include "xgbe-common.h"
+#include "xgbe-smn.h"
 
 static inline unsigned int xgbe_get_max_frame(struct xgbe_prv_data *pdata)
 {
@@ -211,6 +213,18 @@ static void xgbe_config_sph_mode(struct xgbe_prv_data *pdata)
 	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, HDSMS, XGBE_SPH_HDSMS_SIZE);
 }
 
+static void xgbe_disable_sph_mode(struct xgbe_prv_data *pdata)
+{
+	unsigned int i;
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		if (!pdata->channel[i]->rx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(pdata->channel[i], DMA_CH_CR, SPH, 0);
+	}
+}
+
 static int xgbe_write_rss_reg(struct xgbe_prv_data *pdata, unsigned int type,
 			      unsigned int index, unsigned int val)
 {
@@ -1041,18 +1055,19 @@ static int xgbe_set_gpio(struct xgbe_prv_data *pdata, unsigned int gpio)
 	return 0;
 }
 
-static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
-				 int mmd_reg)
+static unsigned int xgbe_get_mmd_address(struct xgbe_prv_data *pdata,
+					 int mmd_reg)
 {
-	unsigned long flags;
-	unsigned int mmd_address, index, offset;
-	int mmd_data;
-
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	return (mmd_reg & XGBE_ADDR_C45) ?
+		mmd_reg & ~XGBE_ADDR_C45 :
+		(pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+}
 
+static void xgbe_get_pcs_index_and_offset(struct xgbe_prv_data *pdata,
+					  unsigned int mmd_address,
+					  unsigned int *index,
+					  unsigned int *offset)
+{
 	/* The PCS registers are accessed using mmio. The underlying
 	 * management interface uses indirect addressing to access the MMD
 	 * register sets. This requires accessing of the PCS register in two
@@ -1063,8 +1078,98 @@ static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
 	 * offset 1 bit and reading 16 bits of data.
 	 */
 	mmd_address <<= 1;
-	index = mmd_address & ~pdata->xpcs_window_mask;
-	offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
+	*index = mmd_address & ~pdata->xpcs_window_mask;
+	*offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
+}
+
+static int xgbe_read_mmd_regs_v3(struct xgbe_prv_data *pdata, int prtad,
+				 int mmd_reg)
+{
+	unsigned int mmd_address, index, offset;
+	u32 smn_address;
+	int mmd_data;
+	int ret;
+
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
+
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
+
+	smn_address = pdata->smn_base + pdata->xpcs_window_sel_reg;
+	ret = amd_smn_write(0, smn_address, index);
+	if (ret)
+		return ret;
+
+	ret = amd_smn_read(0, pdata->smn_base + offset, &mmd_data);
+	if (ret)
+		return ret;
+
+	mmd_data = (offset % 4) ? FIELD_GET(XGBE_GEN_HI_MASK, mmd_data) :
+				  FIELD_GET(XGBE_GEN_LO_MASK, mmd_data);
+
+	return mmd_data;
+}
+
+static void xgbe_write_mmd_regs_v3(struct xgbe_prv_data *pdata, int prtad,
+				   int mmd_reg, int mmd_data)
+{
+	unsigned int pci_mmd_data, hi_mask, lo_mask;
+	unsigned int mmd_address, index, offset;
+	struct pci_dev *dev;
+	u32 smn_address;
+	int ret;
+
+	dev = pdata->pcidev;
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
+
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
+
+	smn_address = pdata->smn_base + pdata->xpcs_window_sel_reg;
+	ret = amd_smn_write(0, smn_address, index);
+	if (ret) {
+		pci_err(dev, "Failed to write data 0x%x\n", index);
+		return;
+	}
+
+	ret = amd_smn_read(0, pdata->smn_base + offset, &pci_mmd_data);
+	if (ret) {
+		pci_err(dev, "Failed to read data\n");
+		return;
+	}
+
+	if (offset % 4) {
+		hi_mask = FIELD_PREP(XGBE_GEN_HI_MASK, mmd_data);
+		lo_mask = FIELD_GET(XGBE_GEN_LO_MASK, pci_mmd_data);
+	} else {
+		hi_mask = FIELD_PREP(XGBE_GEN_HI_MASK,
+				     FIELD_GET(XGBE_GEN_HI_MASK, pci_mmd_data));
+		lo_mask = FIELD_GET(XGBE_GEN_LO_MASK, mmd_data);
+	}
+
+	pci_mmd_data = hi_mask | lo_mask;
+
+	ret = amd_smn_write(0, smn_address, index);
+	if (ret) {
+		pci_err(dev, "Failed to write data 0x%x\n", index);
+		return;
+	}
+
+	ret = amd_smn_write(0, (pdata->smn_base + offset), pci_mmd_data);
+	if (ret) {
+		pci_err(dev, "Failed to write data 0x%x\n", pci_mmd_data);
+		return;
+	}
+}
+
+static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
+				 int mmd_reg)
+{
+	unsigned int mmd_address, index, offset;
+	unsigned long flags;
+	int mmd_data;
+
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
+
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
 
 	spin_lock_irqsave(&pdata->xpcs_lock, flags);
 	XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index);
@@ -1080,23 +1185,9 @@ static void xgbe_write_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
 	unsigned long flags;
 	unsigned int mmd_address, index, offset;
 
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
 
-	/* The PCS registers are accessed using mmio. The underlying
-	 * management interface uses indirect addressing to access the MMD
-	 * register sets. This requires accessing of the PCS register in two
-	 * phases, an address phase and a data phase.
-	 *
-	 * The mmio interface is based on 16-bit offsets and values. All
-	 * register offsets must therefore be adjusted by left shifting the
-	 * offset 1 bit and writing 16 bits of data.
-	 */
-	mmd_address <<= 1;
-	index = mmd_address & ~pdata->xpcs_window_mask;
-	offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
+	xgbe_get_pcs_index_and_offset(pdata, mmd_address, &index, &offset);
 
 	spin_lock_irqsave(&pdata->xpcs_lock, flags);
 	XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index);
@@ -1111,10 +1202,7 @@ static int xgbe_read_mmd_regs_v1(struct xgbe_prv_data *pdata, int prtad,
 	unsigned int mmd_address;
 	int mmd_data;
 
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
 
 	/* The PCS registers are accessed using mmio. The underlying APB3
 	 * management interface uses indirect addressing to access the MMD
@@ -1139,10 +1227,7 @@ static void xgbe_write_mmd_regs_v1(struct xgbe_prv_data *pdata, int prtad,
 	unsigned int mmd_address;
 	unsigned long flags;
 
-	if (mmd_reg & XGBE_ADDR_C45)
-		mmd_address = mmd_reg & ~XGBE_ADDR_C45;
-	else
-		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+	mmd_address = xgbe_get_mmd_address(pdata, mmd_reg);
 
 	/* The PCS registers are accessed using mmio. The underlying APB3
 	 * management interface uses indirect addressing to access the MMD
@@ -1169,6 +1254,9 @@ static int xgbe_read_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
 	case XGBE_XPCS_ACCESS_V2:
 	default:
 		return xgbe_read_mmd_regs_v2(pdata, prtad, mmd_reg);
+
+	case XGBE_XPCS_ACCESS_V3:
+		return xgbe_read_mmd_regs_v3(pdata, prtad, mmd_reg);
 	}
 }
 
@@ -1179,6 +1267,9 @@ static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
 	case XGBE_XPCS_ACCESS_V1:
 		return xgbe_write_mmd_regs_v1(pdata, prtad, mmd_reg, mmd_data);
 
+	case XGBE_XPCS_ACCESS_V3:
+		return xgbe_write_mmd_regs_v3(pdata, prtad, mmd_reg, mmd_data);
+
 	case XGBE_XPCS_ACCESS_V2:
 	default:
 		return xgbe_write_mmd_regs_v2(pdata, prtad, mmd_reg, mmd_data);
@@ -3436,8 +3527,12 @@ static int xgbe_init(struct xgbe_prv_data *pdata)
 	xgbe_config_tx_coalesce(pdata);
 	xgbe_config_rx_buffer_size(pdata);
 	xgbe_config_tso_mode(pdata);
-	xgbe_config_sph_mode(pdata);
-	xgbe_config_rss(pdata);
+
+	if (pdata->netdev->features & NETIF_F_RXCSUM) {
+		xgbe_config_sph_mode(pdata);
+		xgbe_config_rss(pdata);
+	}
+
 	desc_if->wrapper_tx_desc_init(pdata);
 	desc_if->wrapper_rx_desc_init(pdata);
 	xgbe_enable_dma_interrupts(pdata);
@@ -3593,5 +3688,9 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if)
 	hw_if->disable_vxlan = xgbe_disable_vxlan;
 	hw_if->set_vxlan_id = xgbe_set_vxlan_id;
 
+	/* For Split Header*/
+	hw_if->enable_sph = xgbe_config_sph_mode;
+	hw_if->disable_sph = xgbe_disable_sph_mode;
+
 	DBGPR("<--xgbe_init_function_ptrs\n");
 }
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 0697eed1cb72..76c328721fcd 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -2148,10 +2148,17 @@ static int xgbe_set_features(struct net_device *netdev,
 	if (ret)
 		return ret;
 
-	if ((features & NETIF_F_RXCSUM) && !rxcsum)
+	if ((features & NETIF_F_RXCSUM) && !rxcsum) {
+		hw_if->enable_sph(pdata);
+		hw_if->enable_vxlan(pdata);
 		hw_if->enable_rx_csum(pdata);
-	else if (!(features & NETIF_F_RXCSUM) && rxcsum)
+		schedule_work(&pdata->restart_work);
+	} else if (!(features & NETIF_F_RXCSUM) && rxcsum) {
+		hw_if->disable_sph(pdata);
+		hw_if->disable_vxlan(pdata);
 		hw_if->disable_rx_csum(pdata);
+		schedule_work(&pdata->restart_work);
+	}
 
 	if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan)
 		hw_if->enable_rx_vlan_stripping(pdata);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index 3e9f31256dce..097ec5e4f261 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -9,6 +9,7 @@
 #include <linux/device.h>
 #include <linux/pci.h>
 #include <linux/log2.h>
+#include "xgbe-smn.h"
 
 #include "xgbe.h"
 #include "xgbe-common.h"
@@ -98,14 +99,14 @@ out:
 
 static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	struct xgbe_prv_data *pdata;
-	struct device *dev = &pdev->dev;
 	void __iomem * const *iomap_table;
-	struct pci_dev *rdev;
+	unsigned int port_addr_size, reg;
+	struct device *dev = &pdev->dev;
+	struct xgbe_prv_data *pdata;
 	unsigned int ma_lo, ma_hi;
-	unsigned int reg;
-	int bar_mask;
-	int ret;
+	struct pci_dev *rdev;
+	int bar_mask, ret;
+	u32 address;
 
 	pdata = xgbe_alloc_pdata(dev);
 	if (IS_ERR(pdata)) {
@@ -165,20 +166,31 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	/* Set the PCS indirect addressing definition registers */
 	rdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0));
-	if (rdev &&
-	    (rdev->vendor == PCI_VENDOR_ID_AMD) && (rdev->device == 0x15d0)) {
-		pdata->xpcs_window_def_reg = PCS_V2_RV_WINDOW_DEF;
-		pdata->xpcs_window_sel_reg = PCS_V2_RV_WINDOW_SELECT;
-	} else if (rdev && (rdev->vendor == PCI_VENDOR_ID_AMD) &&
-		   (rdev->device == 0x14b5)) {
-		pdata->xpcs_window_def_reg = PCS_V2_YC_WINDOW_DEF;
-		pdata->xpcs_window_sel_reg = PCS_V2_YC_WINDOW_SELECT;
-
-		/* Yellow Carp devices do not need cdr workaround */
-		pdata->vdata->an_cdr_workaround = 0;
-
-		/* Yellow Carp devices do not need rrc */
-		pdata->vdata->enable_rrc = 0;
+	if (rdev && rdev->vendor == PCI_VENDOR_ID_AMD) {
+		switch (rdev->device) {
+		case XGBE_RV_PCI_DEVICE_ID:
+			pdata->xpcs_window_def_reg = PCS_V2_RV_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V2_RV_WINDOW_SELECT;
+			break;
+		case XGBE_YC_PCI_DEVICE_ID:
+			pdata->xpcs_window_def_reg = PCS_V2_YC_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V2_YC_WINDOW_SELECT;
+
+			/* Yellow Carp devices do not need cdr workaround */
+			pdata->vdata->an_cdr_workaround = 0;
+
+			/* Yellow Carp devices do not need rrc */
+			pdata->vdata->enable_rrc = 0;
+			break;
+		case XGBE_RN_PCI_DEVICE_ID:
+			pdata->xpcs_window_def_reg = PCS_V3_RN_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V3_RN_WINDOW_SELECT;
+			break;
+		default:
+			pdata->xpcs_window_def_reg = PCS_V2_WINDOW_DEF;
+			pdata->xpcs_window_sel_reg = PCS_V2_WINDOW_SELECT;
+			break;
+		}
 	} else {
 		pdata->xpcs_window_def_reg = PCS_V2_WINDOW_DEF;
 		pdata->xpcs_window_sel_reg = PCS_V2_WINDOW_SELECT;
@@ -186,7 +198,22 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	pci_dev_put(rdev);
 
 	/* Configure the PCS indirect addressing support */
-	reg = XPCS32_IOREAD(pdata, pdata->xpcs_window_def_reg);
+	if (pdata->vdata->xpcs_access == XGBE_XPCS_ACCESS_V3) {
+		reg = XP_IOREAD(pdata, XP_PROP_0);
+		port_addr_size = PCS_RN_PORT_ADDR_SIZE *
+				 XP_GET_BITS(reg, XP_PROP_0, PORT_ID);
+		pdata->smn_base = PCS_RN_SMN_BASE_ADDR + port_addr_size;
+
+		address = pdata->smn_base + (pdata->xpcs_window_def_reg);
+		ret = amd_smn_read(0, address, &reg);
+		if (ret) {
+			pci_err(pdata->pcidev, "Failed to read data\n");
+			goto err_pci_enable;
+		}
+	} else {
+		reg = XPCS32_IOREAD(pdata, pdata->xpcs_window_def_reg);
+	}
+
 	pdata->xpcs_window = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, OFFSET);
 	pdata->xpcs_window <<= 6;
 	pdata->xpcs_window_size = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, SIZE);
@@ -364,6 +391,22 @@ static int __maybe_unused xgbe_pci_resume(struct device *dev)
 	return ret;
 }
 
+static struct xgbe_version_data xgbe_v3 = {
+	.init_function_ptrs_phy_impl	= xgbe_init_function_ptrs_phy_v2,
+	.xpcs_access			= XGBE_XPCS_ACCESS_V3,
+	.mmc_64bit			= 1,
+	.tx_max_fifo_size		= 65536,
+	.rx_max_fifo_size		= 65536,
+	.tx_tstamp_workaround		= 1,
+	.ecc_support			= 1,
+	.i2c_support			= 1,
+	.irq_reissue_support		= 1,
+	.tx_desc_prefetch		= 5,
+	.rx_desc_prefetch		= 5,
+	.an_cdr_workaround		= 0,
+	.enable_rrc			= 0,
+};
+
 static struct xgbe_version_data xgbe_v2a = {
 	.init_function_ptrs_phy_impl	= xgbe_init_function_ptrs_phy_v2,
 	.xpcs_access			= XGBE_XPCS_ACCESS_V2,
@@ -401,6 +444,8 @@ static const struct pci_device_id xgbe_pci_table[] = {
 	  .driver_data = (kernel_ulong_t)&xgbe_v2a },
 	{ PCI_VDEVICE(AMD, 0x1459),
 	  .driver_data = (kernel_ulong_t)&xgbe_v2b },
+	{ PCI_VDEVICE(AMD, 0x1641),
+	  .driver_data = (kernel_ulong_t)&xgbe_v3 },
 	/* Last entry must be zero */
 	{ 0, }
 };
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-smn.h b/drivers/net/ethernet/amd/xgbe/xgbe-smn.h
new file mode 100644
index 000000000000..3fd03d39c18a
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-smn.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause) */
+/*
+ * Copyright (c) 2014-2025, Advanced Micro Devices, Inc.
+ * Copyright (c) 2014, Synopsys, Inc.
+ * All rights reserved
+ *
+ * Author: Raju Rangoju <Raju.Rangoju@amd.com>
+ */
+
+#ifndef __SMN_H__
+#define __SMN_H__
+
+#ifdef CONFIG_AMD_NB
+
+#include <asm/amd_nb.h>
+
+#else
+
+static inline int amd_smn_write(u16 node, u32 address, u32 value)
+{
+	return -ENODEV;
+}
+
+static inline int amd_smn_read(u16 node, u32 address, u32 *value)
+{
+	return -ENODEV;
+}
+
+#endif
+#endif
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index e5f5104342aa..6359bb87dc13 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -238,6 +238,15 @@
 		    (_src)->link_modes._sname,		\
 		    __ETHTOOL_LINK_MODE_MASK_NBITS)
 
+/* XGBE PCI device id */
+#define XGBE_RV_PCI_DEVICE_ID	0x15d0
+#define XGBE_YC_PCI_DEVICE_ID	0x14b5
+#define XGBE_RN_PCI_DEVICE_ID	0x1630
+
+ /* Generic low and high masks */
+#define XGBE_GEN_HI_MASK	GENMASK(31, 16)
+#define XGBE_GEN_LO_MASK	GENMASK(15, 0)
+
 struct xgbe_prv_data;
 
 struct xgbe_packet_data {
@@ -456,6 +465,7 @@ enum xgbe_speed {
 enum xgbe_xpcs_access {
 	XGBE_XPCS_ACCESS_V1 = 0,
 	XGBE_XPCS_ACCESS_V2,
+	XGBE_XPCS_ACCESS_V3,
 };
 
 enum xgbe_an_mode {
@@ -756,6 +766,10 @@ struct xgbe_hw_if {
 	void (*enable_vxlan)(struct xgbe_prv_data *);
 	void (*disable_vxlan)(struct xgbe_prv_data *);
 	void (*set_vxlan_id)(struct xgbe_prv_data *);
+
+	/* For Split Header */
+	void (*enable_sph)(struct xgbe_prv_data *pdata);
+	void (*disable_sph)(struct xgbe_prv_data *pdata);
 };
 
 /* This structure represents implementation specific routines for an
@@ -947,6 +961,7 @@ struct xgbe_prv_data {
 	struct device *dev;
 	struct platform_device *phy_platdev;
 	struct device *phy_dev;
+	unsigned int smn_base;
 
 	/* Version related data */
 	struct xgbe_version_data *vdata;
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index b9fdd61f1fdb..b50052c25a91 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -20,7 +20,6 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/crc32.h>
-#include <linux/crc32poly.h>
 #include <linux/bitrev.h>
 #include <linux/ethtool.h>
 #include <linux/slab.h>
@@ -796,59 +795,6 @@ static irqreturn_t bmac_txdma_intr(int irq, void *dev_id)
 }
 
 #ifndef SUNHME_MULTICAST
-/* Real fast bit-reversal algorithm, 6-bit values */
-static int reverse6[64] = {
-	0x0,0x20,0x10,0x30,0x8,0x28,0x18,0x38,
-	0x4,0x24,0x14,0x34,0xc,0x2c,0x1c,0x3c,
-	0x2,0x22,0x12,0x32,0xa,0x2a,0x1a,0x3a,
-	0x6,0x26,0x16,0x36,0xe,0x2e,0x1e,0x3e,
-	0x1,0x21,0x11,0x31,0x9,0x29,0x19,0x39,
-	0x5,0x25,0x15,0x35,0xd,0x2d,0x1d,0x3d,
-	0x3,0x23,0x13,0x33,0xb,0x2b,0x1b,0x3b,
-	0x7,0x27,0x17,0x37,0xf,0x2f,0x1f,0x3f
-};
-
-static unsigned int
-crc416(unsigned int curval, unsigned short nxtval)
-{
-	unsigned int counter, cur = curval, next = nxtval;
-	int high_crc_set, low_data_set;
-
-	/* Swap bytes */
-	next = ((next & 0x00FF) << 8) | (next >> 8);
-
-	/* Compute bit-by-bit */
-	for (counter = 0; counter < 16; ++counter) {
-		/* is high CRC bit set? */
-		if ((cur & 0x80000000) == 0) high_crc_set = 0;
-		else high_crc_set = 1;
-
-		cur = cur << 1;
-
-		if ((next & 0x0001) == 0) low_data_set = 0;
-		else low_data_set = 1;
-
-		next = next >> 1;
-
-		/* do the XOR */
-		if (high_crc_set ^ low_data_set) cur = cur ^ CRC32_POLY_BE;
-	}
-	return cur;
-}
-
-static unsigned int
-bmac_crc(unsigned short *address)
-{
-	unsigned int newcrc;
-
-	XXDEBUG(("bmac_crc: addr=%#04x, %#04x, %#04x\n", *address, address[1], address[2]));
-	newcrc = crc416(0xffffffff, *address);	/* address bits 47 - 32 */
-	newcrc = crc416(newcrc, address[1]);	/* address bits 31 - 16 */
-	newcrc = crc416(newcrc, address[2]);	/* address bits 15 - 0  */
-
-	return(newcrc);
-}
-
 /*
  * Add requested mcast addr to BMac's hash table filter.
  *
@@ -861,8 +807,7 @@ bmac_addhash(struct bmac_data *bp, unsigned char *addr)
 	unsigned short	 mask;
 
 	if (!(*addr)) return;
-	crc = bmac_crc((unsigned short *)addr) & 0x3f; /* Big-endian alert! */
-	crc = reverse6[crc];	/* Hyperfast bit-reversing algorithm */
+	crc = crc32(~0, addr, ETH_ALEN) >> 26;
 	if (bp->hash_use_count[crc]++) return; /* This bit is already set */
 	mask = crc % 16;
 	mask = (unsigned char)1 << mask;
@@ -876,8 +821,7 @@ bmac_removehash(struct bmac_data *bp, unsigned char *addr)
 	unsigned char mask;
 
 	/* Now, delete the address from the filter copy, as indicated */
-	crc = bmac_crc((unsigned short *)addr) & 0x3f; /* Big-endian alert! */
-	crc = reverse6[crc];	/* Hyperfast bit-reversing algorithm */
+	crc = crc32(~0, addr, ETH_ALEN) >> 26;
 	if (bp->hash_use_count[crc] == 0) return; /* That bit wasn't in use! */
 	if (--bp->hash_use_count[crc]) return; /* That bit is still in use */
 	mask = crc % 16;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index c1d1673c5749..b565189e5913 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -123,7 +123,6 @@ static netdev_tx_t aq_ndev_start_xmit(struct sk_buff *skb, struct net_device *nd
 	}
 #endif
 
-	skb_tx_timestamp(skb);
 	return aq_nic_xmit(aq_nic, skb);
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index bf3aa46887a1..e71cd10e4e1f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -898,6 +898,8 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 
 	frags = aq_nic_map_skb(self, skb, ring);
 
+	skb_tx_timestamp(skb);
+
 	if (likely(frags)) {
 		err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw,
 						       ring, frags);
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 1bd4313215d7..636520bb4b8c 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -123,6 +123,7 @@ config TIGON3
 	tristate "Broadcom Tigon3 support"
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
+	select CRC32
 	select PHYLIB
 	help
 	  This driver supports Broadcom Tigon3 based gigabit Ethernet cards.
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index a68fab1b05f0..fd35f4b4dc50 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -141,7 +141,7 @@ void bcmasp_flush_rx_port(struct bcmasp_intf *intf)
 		return;
 	}
 
-	rx_ctrl_core_wl(priv, mask, priv->hw_info->rx_ctrl_flush);
+	rx_ctrl_core_wl(priv, mask, ASP_RX_CTRL_FLUSH);
 }
 
 static void bcmasp_netfilt_hw_en_wake(struct bcmasp_priv *priv,
@@ -518,7 +518,7 @@ void bcmasp_netfilt_suspend(struct bcmasp_intf *intf)
 	int ret, i;
 
 	/* Write all filters to HW */
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		/* If the filter does not match the port, skip programming. */
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
@@ -551,7 +551,7 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 	struct bcmasp_priv *priv = intf->parent;
 	int j = 0, i;
 
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -577,7 +577,7 @@ int bcmasp_netfilt_get_active(struct bcmasp_intf *intf)
 	struct bcmasp_priv *priv = intf->parent;
 	int cnt = 0, i;
 
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -602,7 +602,7 @@ bool bcmasp_netfilt_check_dup(struct bcmasp_intf *intf,
 	size_t fs_size = 0;
 	int i;
 
-	for (i = 0; i < NUM_NET_FILTERS; i++) {
+	for (i = 0; i < priv->num_net_filters; i++) {
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -670,7 +670,7 @@ struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf,
 	int i, open_index = -1;
 
 	/* Check whether we exceed the filter table capacity */
-	if (loc != RX_CLS_LOC_ANY && loc >= NUM_NET_FILTERS)
+	if (loc != RX_CLS_LOC_ANY && loc >= priv->num_net_filters)
 		return ERR_PTR(-EINVAL);
 
 	/* If the filter location is busy (already claimed) and we are initializing
@@ -686,7 +686,7 @@ struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf,
 	/* Initialize the loop index based on the desired location or from 0 */
 	i = loc == RX_CLS_LOC_ANY ? 0 : loc;
 
-	for ( ; i < NUM_NET_FILTERS; i++) {
+	for ( ; i < priv->num_net_filters; i++) {
 		/* Found matching network filter */
 		if (!init &&
 		    priv->net_filters[i].claimed &&
@@ -779,7 +779,7 @@ static void bcmasp_en_mda_filter(struct bcmasp_intf *intf, bool en,
 	priv->mda_filters[i].en = en;
 	priv->mda_filters[i].port = intf->port;
 
-	rx_filter_core_wl(priv, ((intf->channel + 8) |
+	rx_filter_core_wl(priv, ((intf->channel + priv->tx_chan_offset) |
 			  (en << ASP_RX_FILTER_MDA_CFG_EN_SHIFT) |
 			  ASP_RX_FILTER_MDA_CFG_UMC_SEL(intf->port)),
 			  ASP_RX_FILTER_MDA_CFG(i));
@@ -865,7 +865,7 @@ void bcmasp_disable_all_filters(struct bcmasp_intf *intf)
 	res_count = bcmasp_total_res_mda_cnt(intf->parent);
 
 	/* Disable all filters held by this port */
-	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+	for (i = res_count; i < priv->num_mda_filters; i++) {
 		if (priv->mda_filters[i].en &&
 		    priv->mda_filters[i].port == intf->port)
 			bcmasp_en_mda_filter(intf, 0, i);
@@ -909,7 +909,7 @@ int bcmasp_set_en_mda_filter(struct bcmasp_intf *intf, unsigned char *addr,
 
 	res_count = bcmasp_total_res_mda_cnt(intf->parent);
 
-	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+	for (i = res_count; i < priv->num_mda_filters; i++) {
 		/* If filter not enabled or belongs to another port skip */
 		if (!priv->mda_filters[i].en ||
 		    priv->mda_filters[i].port != intf->port)
@@ -924,7 +924,7 @@ int bcmasp_set_en_mda_filter(struct bcmasp_intf *intf, unsigned char *addr,
 	}
 
 	/* Create new filter if possible */
-	for (i = res_count; i < NUM_MDA_FILTERS; i++) {
+	for (i = res_count; i < priv->num_mda_filters; i++) {
 		if (priv->mda_filters[i].en)
 			continue;
 
@@ -944,12 +944,12 @@ static void bcmasp_core_init_filters(struct bcmasp_priv *priv)
 	/* Disable all filters and reset software view since the HW
 	 * can lose context while in deep sleep suspend states
 	 */
-	for (i = 0; i < NUM_MDA_FILTERS; i++) {
+	for (i = 0; i < priv->num_mda_filters; i++) {
 		rx_filter_core_wl(priv, 0x0, ASP_RX_FILTER_MDA_CFG(i));
 		priv->mda_filters[i].en = 0;
 	}
 
-	for (i = 0; i < NUM_NET_FILTERS; i++)
+	for (i = 0; i < priv->num_net_filters; i++)
 		rx_filter_core_wl(priv, 0x0, ASP_RX_FILTER_NET_CFG(i));
 
 	/* Top level filter enable bit should be enabled at all times, set
@@ -966,18 +966,8 @@ static void bcmasp_core_init_filters(struct bcmasp_priv *priv)
 /* ASP core initialization */
 static void bcmasp_core_init(struct bcmasp_priv *priv)
 {
-	tx_analytics_core_wl(priv, 0x0, ASP_TX_ANALYTICS_CTRL);
-	rx_analytics_core_wl(priv, 0x4, ASP_RX_ANALYTICS_CTRL);
-
-	rx_edpkt_core_wl(priv, (ASP_EDPKT_HDR_SZ_128 << ASP_EDPKT_HDR_SZ_SHIFT),
-			 ASP_EDPKT_HDR_CFG);
-	rx_edpkt_core_wl(priv,
-			 (ASP_EDPKT_ENDI_BT_SWP_WD << ASP_EDPKT_ENDI_DESC_SHIFT),
-			 ASP_EDPKT_ENDI);
-
 	rx_edpkt_core_wl(priv, 0x1b, ASP_EDPKT_BURST_BUF_PSCAL_TOUT);
 	rx_edpkt_core_wl(priv, 0x3e8, ASP_EDPKT_BURST_BUF_WRITE_TOUT);
-	rx_edpkt_core_wl(priv, 0x3e8, ASP_EDPKT_BURST_BUF_READ_TOUT);
 
 	rx_edpkt_core_wl(priv, ASP_EDPKT_ENABLE_EN, ASP_EDPKT_ENABLE);
 
@@ -1020,6 +1010,18 @@ static void bcmasp_core_clock_select_one(struct bcmasp_priv *priv, bool slow)
 	ctrl_core_wl(priv, reg, ASP_CTRL_CORE_CLOCK_SELECT);
 }
 
+static void bcmasp_core_clock_select_one_ctrl2(struct bcmasp_priv *priv, bool slow)
+{
+	u32 reg;
+
+	reg = ctrl2_core_rl(priv, ASP_CTRL2_CORE_CLOCK_SELECT);
+	if (slow)
+		reg &= ~ASP_CTRL2_CORE_CLOCK_SELECT_MAIN;
+	else
+		reg |= ASP_CTRL2_CORE_CLOCK_SELECT_MAIN;
+	ctrl2_core_wl(priv, reg, ASP_CTRL2_CORE_CLOCK_SELECT);
+}
+
 static void bcmasp_core_clock_set_ll(struct bcmasp_priv *priv, u32 clr, u32 set)
 {
 	u32 reg;
@@ -1108,7 +1110,7 @@ static int bcmasp_get_and_request_irq(struct bcmasp_priv *priv, int i)
 	return irq;
 }
 
-static void bcmasp_init_wol_shared(struct bcmasp_priv *priv)
+static void bcmasp_init_wol(struct bcmasp_priv *priv)
 {
 	struct platform_device *pdev = priv->pdev;
 	struct device *dev = &pdev->dev;
@@ -1125,7 +1127,7 @@ static void bcmasp_init_wol_shared(struct bcmasp_priv *priv)
 	device_set_wakeup_capable(&pdev->dev, 1);
 }
 
-static void bcmasp_enable_wol_shared(struct bcmasp_intf *intf, bool en)
+void bcmasp_enable_wol(struct bcmasp_intf *intf, bool en)
 {
 	struct bcmasp_priv *priv = intf->parent;
 	struct device *dev = &priv->pdev->dev;
@@ -1154,54 +1156,12 @@ static void bcmasp_enable_wol_shared(struct bcmasp_intf *intf, bool en)
 	}
 }
 
-static void bcmasp_wol_irq_destroy_shared(struct bcmasp_priv *priv)
+static void bcmasp_wol_irq_destroy(struct bcmasp_priv *priv)
 {
 	if (priv->wol_irq > 0)
 		free_irq(priv->wol_irq, priv);
 }
 
-static void bcmasp_init_wol_per_intf(struct bcmasp_priv *priv)
-{
-	struct platform_device *pdev = priv->pdev;
-	struct device *dev = &pdev->dev;
-	struct bcmasp_intf *intf;
-	int irq;
-
-	list_for_each_entry(intf, &priv->intfs, list) {
-		irq = bcmasp_get_and_request_irq(priv, intf->port + 1);
-		if (irq < 0) {
-			dev_warn(dev, "Failed to init WoL irq(port %d): %d\n",
-				 intf->port, irq);
-			continue;
-		}
-
-		intf->wol_irq = irq;
-		intf->wol_irq_enabled = false;
-		device_set_wakeup_capable(&pdev->dev, 1);
-	}
-}
-
-static void bcmasp_enable_wol_per_intf(struct bcmasp_intf *intf, bool en)
-{
-	struct device *dev = &intf->parent->pdev->dev;
-
-	if (en ^ intf->wol_irq_enabled)
-		irq_set_irq_wake(intf->wol_irq, en);
-
-	intf->wol_irq_enabled = en;
-	device_set_wakeup_enable(dev, en);
-}
-
-static void bcmasp_wol_irq_destroy_per_intf(struct bcmasp_priv *priv)
-{
-	struct bcmasp_intf *intf;
-
-	list_for_each_entry(intf, &priv->intfs, list) {
-		if (intf->wol_irq > 0)
-			free_irq(intf->wol_irq, priv);
-	}
-}
-
 static void bcmasp_eee_fixup(struct bcmasp_intf *intf, bool en)
 {
 	u32 reg, phy_lpi_overwrite;
@@ -1220,70 +1180,53 @@ static void bcmasp_eee_fixup(struct bcmasp_intf *intf, bool en)
 	usleep_range(50, 100);
 }
 
-static struct bcmasp_hw_info v20_hw_info = {
-	.rx_ctrl_flush = ASP_RX_CTRL_FLUSH,
-	.umac2fb = UMAC2FB_OFFSET,
-	.rx_ctrl_fb_out_frame_count = ASP_RX_CTRL_FB_OUT_FRAME_COUNT,
-	.rx_ctrl_fb_filt_out_frame_count = ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT,
-	.rx_ctrl_fb_rx_fifo_depth = ASP_RX_CTRL_FB_RX_FIFO_DEPTH,
-};
-
-static const struct bcmasp_plat_data v20_plat_data = {
-	.init_wol = bcmasp_init_wol_per_intf,
-	.enable_wol = bcmasp_enable_wol_per_intf,
-	.destroy_wol = bcmasp_wol_irq_destroy_per_intf,
-	.core_clock_select = bcmasp_core_clock_select_one,
-	.hw_info = &v20_hw_info,
-};
-
-static struct bcmasp_hw_info v21_hw_info = {
-	.rx_ctrl_flush = ASP_RX_CTRL_FLUSH_2_1,
-	.umac2fb = UMAC2FB_OFFSET_2_1,
-	.rx_ctrl_fb_out_frame_count = ASP_RX_CTRL_FB_OUT_FRAME_COUNT_2_1,
-	.rx_ctrl_fb_filt_out_frame_count =
-		ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT_2_1,
-	.rx_ctrl_fb_rx_fifo_depth = ASP_RX_CTRL_FB_RX_FIFO_DEPTH_2_1,
-};
-
 static const struct bcmasp_plat_data v21_plat_data = {
-	.init_wol = bcmasp_init_wol_shared,
-	.enable_wol = bcmasp_enable_wol_shared,
-	.destroy_wol = bcmasp_wol_irq_destroy_shared,
 	.core_clock_select = bcmasp_core_clock_select_one,
-	.hw_info = &v21_hw_info,
+	.num_mda_filters = 32,
+	.num_net_filters = 32,
+	.tx_chan_offset = 8,
+	.rx_ctrl_offset = 0x0,
 };
 
 static const struct bcmasp_plat_data v22_plat_data = {
-	.init_wol = bcmasp_init_wol_shared,
-	.enable_wol = bcmasp_enable_wol_shared,
-	.destroy_wol = bcmasp_wol_irq_destroy_shared,
 	.core_clock_select = bcmasp_core_clock_select_many,
-	.hw_info = &v21_hw_info,
 	.eee_fixup = bcmasp_eee_fixup,
+	.num_mda_filters = 32,
+	.num_net_filters = 32,
+	.tx_chan_offset = 8,
+	.rx_ctrl_offset = 0x0,
+};
+
+static const struct bcmasp_plat_data v30_plat_data = {
+	.core_clock_select = bcmasp_core_clock_select_one_ctrl2,
+	.num_mda_filters = 20,
+	.num_net_filters = 16,
+	.tx_chan_offset = 0,
+	.rx_ctrl_offset = 0x10000,
 };
 
 static void bcmasp_set_pdata(struct bcmasp_priv *priv, const struct bcmasp_plat_data *pdata)
 {
-	priv->init_wol = pdata->init_wol;
-	priv->enable_wol = pdata->enable_wol;
-	priv->destroy_wol = pdata->destroy_wol;
 	priv->core_clock_select = pdata->core_clock_select;
 	priv->eee_fixup = pdata->eee_fixup;
-	priv->hw_info = pdata->hw_info;
+	priv->num_mda_filters = pdata->num_mda_filters;
+	priv->num_net_filters = pdata->num_net_filters;
+	priv->tx_chan_offset = pdata->tx_chan_offset;
+	priv->rx_ctrl_offset = pdata->rx_ctrl_offset;
 }
 
 static const struct of_device_id bcmasp_of_match[] = {
-	{ .compatible = "brcm,asp-v2.0", .data = &v20_plat_data },
 	{ .compatible = "brcm,asp-v2.1", .data = &v21_plat_data },
 	{ .compatible = "brcm,asp-v2.2", .data = &v22_plat_data },
+	{ .compatible = "brcm,asp-v3.0", .data = &v30_plat_data },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, bcmasp_of_match);
 
 static const struct of_device_id bcmasp_mdio_of_match[] = {
-	{ .compatible = "brcm,asp-v2.2-mdio", },
 	{ .compatible = "brcm,asp-v2.1-mdio", },
-	{ .compatible = "brcm,asp-v2.0-mdio", },
+	{ .compatible = "brcm,asp-v2.2-mdio", },
+	{ .compatible = "brcm,asp-v3.0-mdio", },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, bcmasp_mdio_of_match);
@@ -1365,6 +1308,17 @@ static int bcmasp_probe(struct platform_device *pdev)
 	 * how many interfaces come up.
 	 */
 	bcmasp_core_init(priv);
+
+	priv->mda_filters = devm_kcalloc(dev, priv->num_mda_filters,
+					 sizeof(*priv->mda_filters), GFP_KERNEL);
+	if (!priv->mda_filters)
+		return -ENOMEM;
+
+	priv->net_filters = devm_kcalloc(dev, priv->num_net_filters,
+					 sizeof(*priv->net_filters), GFP_KERNEL);
+	if (!priv->net_filters)
+		return -ENOMEM;
+
 	bcmasp_core_init_filters(priv);
 
 	ports_node = of_find_node_by_name(dev->of_node, "ethernet-ports");
@@ -1387,7 +1341,7 @@ static int bcmasp_probe(struct platform_device *pdev)
 	}
 
 	/* Check and enable WoL */
-	priv->init_wol(priv);
+	bcmasp_init_wol(priv);
 
 	/* Drop the clock reference count now and let ndo_open()/ndo_close()
 	 * manage it for us from now on.
@@ -1404,7 +1358,7 @@ static int bcmasp_probe(struct platform_device *pdev)
 		if (ret) {
 			netdev_err(intf->ndev,
 				   "failed to register net_device: %d\n", ret);
-			priv->destroy_wol(priv);
+			bcmasp_wol_irq_destroy(priv);
 			bcmasp_remove_intfs(priv);
 			goto of_put_exit;
 		}
@@ -1425,7 +1379,7 @@ static void bcmasp_remove(struct platform_device *pdev)
 	if (!priv)
 		return;
 
-	priv->destroy_wol(priv);
+	bcmasp_wol_irq_destroy(priv);
 	bcmasp_remove_intfs(priv);
 }
 
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
index 8fc75bcedb70..74adfdb50e11 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h
@@ -53,22 +53,15 @@
 #define ASP_RX_CTRL_FB_0_FRAME_COUNT		0x14
 #define ASP_RX_CTRL_FB_1_FRAME_COUNT		0x18
 #define ASP_RX_CTRL_FB_8_FRAME_COUNT		0x1c
-/* asp2.1 diverges offsets here */
-/* ASP2.0 */
-#define ASP_RX_CTRL_FB_OUT_FRAME_COUNT		0x20
-#define ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT	0x24
-#define ASP_RX_CTRL_FLUSH			0x28
-#define  ASP_CTRL_UMAC0_FLUSH_MASK		(BIT(0) | BIT(12))
-#define  ASP_CTRL_UMAC1_FLUSH_MASK		(BIT(1) | BIT(13))
-#define  ASP_CTRL_SPB_FLUSH_MASK		(BIT(8) | BIT(20))
-#define ASP_RX_CTRL_FB_RX_FIFO_DEPTH		0x30
-/* ASP2.1 */
-#define ASP_RX_CTRL_FB_9_FRAME_COUNT_2_1	0x20
-#define ASP_RX_CTRL_FB_10_FRAME_COUNT_2_1	0x24
-#define ASP_RX_CTRL_FB_OUT_FRAME_COUNT_2_1	0x28
-#define ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT_2_1	0x2c
-#define ASP_RX_CTRL_FLUSH_2_1			0x30
-#define ASP_RX_CTRL_FB_RX_FIFO_DEPTH_2_1	0x38
+#define ASP_RX_CTRL_FB_9_FRAME_COUNT		0x20
+#define ASP_RX_CTRL_FB_10_FRAME_COUNT		0x24
+#define ASP_RX_CTRL_FB_OUT_FRAME_COUNT		0x28
+#define ASP_RX_CTRL_FB_FILT_OUT_FRAME_COUNT	0x2c
+#define ASP_RX_CTRL_FLUSH			0x30
+#define  ASP_CTRL_UMAC0_FLUSH_MASK             (BIT(0) | BIT(12))
+#define  ASP_CTRL_UMAC1_FLUSH_MASK             (BIT(1) | BIT(13))
+#define  ASP_CTRL_SPB_FLUSH_MASK               (BIT(8) | BIT(20))
+#define ASP_RX_CTRL_FB_RX_FIFO_DEPTH		0x38
 
 #define ASP_RX_FILTER_OFFSET			0x80000
 #define  ASP_RX_FILTER_BLK_CTRL			0x0
@@ -345,9 +338,6 @@ struct bcmasp_intf {
 
 	u32				wolopts;
 	u8				sopass[SOPASS_MAX];
-	/* Used if per intf wol irq */
-	int				wol_irq;
-	unsigned int			wol_irq_enabled:1;
 };
 
 #define NUM_NET_FILTERS				32
@@ -370,21 +360,13 @@ struct bcmasp_mda_filter {
 	u8		mask[ETH_ALEN];
 };
 
-struct bcmasp_hw_info {
-	u32		rx_ctrl_flush;
-	u32		umac2fb;
-	u32		rx_ctrl_fb_out_frame_count;
-	u32		rx_ctrl_fb_filt_out_frame_count;
-	u32		rx_ctrl_fb_rx_fifo_depth;
-};
-
 struct bcmasp_plat_data {
-	void (*init_wol)(struct bcmasp_priv *priv);
-	void (*enable_wol)(struct bcmasp_intf *intf, bool en);
-	void (*destroy_wol)(struct bcmasp_priv *priv);
 	void (*core_clock_select)(struct bcmasp_priv *priv, bool slow);
 	void (*eee_fixup)(struct bcmasp_intf *priv, bool en);
-	struct bcmasp_hw_info		*hw_info;
+	unsigned int num_mda_filters;
+	unsigned int num_net_filters;
+	unsigned int tx_chan_offset;
+	unsigned int rx_ctrl_offset;
 };
 
 struct bcmasp_priv {
@@ -399,18 +381,18 @@ struct bcmasp_priv {
 	int				wol_irq;
 	unsigned long			wol_irq_enabled_mask;
 
-	void (*init_wol)(struct bcmasp_priv *priv);
-	void (*enable_wol)(struct bcmasp_intf *intf, bool en);
-	void (*destroy_wol)(struct bcmasp_priv *priv);
 	void (*core_clock_select)(struct bcmasp_priv *priv, bool slow);
 	void (*eee_fixup)(struct bcmasp_intf *intf, bool en);
+	unsigned int			num_mda_filters;
+	unsigned int			num_net_filters;
+	unsigned int			tx_chan_offset;
+	unsigned int			rx_ctrl_offset;
 
 	void __iomem			*base;
-	struct	bcmasp_hw_info		*hw_info;
 
 	struct list_head		intfs;
 
-	struct bcmasp_mda_filter	mda_filters[NUM_MDA_FILTERS];
+	struct bcmasp_mda_filter	*mda_filters;
 
 	/* MAC destination address filters lock */
 	spinlock_t			mda_lock;
@@ -418,7 +400,7 @@ struct bcmasp_priv {
 	/* Protects accesses to ASP_CTRL_CLOCK_CTRL */
 	spinlock_t			clk_lock;
 
-	struct bcmasp_net_filter	net_filters[NUM_NET_FILTERS];
+	struct bcmasp_net_filter	*net_filters;
 
 	/* Network filter lock */
 	struct mutex			net_lock;
@@ -508,8 +490,8 @@ BCMASP_FP_IO_MACRO_Q(rx_edpkt_cfg);
 #define  PKT_OFFLOAD_EPKT_IP(x)		((x) << 21)
 #define  PKT_OFFLOAD_EPKT_TP(x)		((x) << 19)
 #define  PKT_OFFLOAD_EPKT_LEN(x)	((x) << 16)
-#define  PKT_OFFLOAD_EPKT_CSUM_L3	BIT(15)
-#define  PKT_OFFLOAD_EPKT_CSUM_L2	BIT(14)
+#define  PKT_OFFLOAD_EPKT_CSUM_L4	BIT(15)
+#define  PKT_OFFLOAD_EPKT_CSUM_L3	BIT(14)
 #define  PKT_OFFLOAD_EPKT_ID(x)		((x) << 12)
 #define  PKT_OFFLOAD_EPKT_SEQ(x)	((x) << 10)
 #define  PKT_OFFLOAD_EPKT_TS(x)		((x) << 8)
@@ -541,12 +523,27 @@ BCMASP_CORE_IO_MACRO(intr2, ASP_INTR2_OFFSET);
 BCMASP_CORE_IO_MACRO(wakeup_intr2, ASP_WAKEUP_INTR2_OFFSET);
 BCMASP_CORE_IO_MACRO(tx_analytics, ASP_TX_ANALYTICS_OFFSET);
 BCMASP_CORE_IO_MACRO(rx_analytics, ASP_RX_ANALYTICS_OFFSET);
-BCMASP_CORE_IO_MACRO(rx_ctrl, ASP_RX_CTRL_OFFSET);
 BCMASP_CORE_IO_MACRO(rx_filter, ASP_RX_FILTER_OFFSET);
 BCMASP_CORE_IO_MACRO(rx_edpkt, ASP_EDPKT_OFFSET);
 BCMASP_CORE_IO_MACRO(ctrl, ASP_CTRL_OFFSET);
 BCMASP_CORE_IO_MACRO(ctrl2, ASP_CTRL2_OFFSET);
 
+#define BCMASP_CORE_IO_MACRO_OFFSET(name, offset)			\
+static inline u32 name##_core_rl(struct bcmasp_priv *priv,		\
+				 u32 off)				\
+{									\
+	u32 reg = readl_relaxed(priv->base + priv->name##_offset +	\
+				(offset) + off);			\
+	return reg;							\
+}									\
+static inline void name##_core_wl(struct bcmasp_priv *priv,		\
+				  u32 val, u32 off)			\
+{									\
+	writel_relaxed(val, priv->base + priv->name##_offset +		\
+		       (offset) + off);					\
+}
+BCMASP_CORE_IO_MACRO_OFFSET(rx_ctrl, ASP_RX_CTRL_OFFSET);
+
 struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv,
 					    struct device_node *ndev_dn, int i);
 
@@ -599,4 +596,5 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 
 void bcmasp_netfilt_suspend(struct bcmasp_intf *intf);
 
+void bcmasp_enable_wol(struct bcmasp_intf *intf, bool en);
 #endif
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
index a537c121d3e2..4381a4cfd8c6 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c
@@ -10,7 +10,6 @@
 #include "bcmasp_intf_defs.h"
 
 enum bcmasp_stat_type {
-	BCMASP_STAT_RX_EDPKT,
 	BCMASP_STAT_RX_CTRL,
 	BCMASP_STAT_RX_CTRL_PER_INTF,
 	BCMASP_STAT_SOFT,
@@ -33,8 +32,6 @@ struct bcmasp_stats {
 	.reg_offset = offset, \
 }
 
-#define STAT_BCMASP_RX_EDPKT(str, offset) \
-	STAT_BCMASP_OFFSET(str, BCMASP_STAT_RX_EDPKT, offset)
 #define STAT_BCMASP_RX_CTRL(str, offset) \
 	STAT_BCMASP_OFFSET(str, BCMASP_STAT_RX_CTRL, offset)
 #define STAT_BCMASP_RX_CTRL_PER_INTF(str, offset) \
@@ -42,11 +39,6 @@ struct bcmasp_stats {
 
 /* Must match the order of struct bcmasp_mib_counters */
 static const struct bcmasp_stats bcmasp_gstrings_stats[] = {
-	/* EDPKT counters */
-	STAT_BCMASP_RX_EDPKT("RX Time Stamp", ASP_EDPKT_RX_TS_COUNTER),
-	STAT_BCMASP_RX_EDPKT("RX PKT Count", ASP_EDPKT_RX_PKT_CNT),
-	STAT_BCMASP_RX_EDPKT("RX PKT Buffered", ASP_EDPKT_HDR_EXTR_CNT),
-	STAT_BCMASP_RX_EDPKT("RX PKT Pushed to DRAM", ASP_EDPKT_HDR_OUT_CNT),
 	/* ASP RX control */
 	STAT_BCMASP_RX_CTRL_PER_INTF("Frames From Unimac",
 				     ASP_RX_CTRL_UMAC_0_FRAME_COUNT),
@@ -71,23 +63,6 @@ static const struct bcmasp_stats bcmasp_gstrings_stats[] = {
 
 #define BCMASP_STATS_LEN	ARRAY_SIZE(bcmasp_gstrings_stats)
 
-static u16 bcmasp_stat_fixup_offset(struct bcmasp_intf *intf,
-				    const struct bcmasp_stats *s)
-{
-	struct bcmasp_priv *priv = intf->parent;
-
-	if (!strcmp("Frames Out(Buffer)", s->stat_string))
-		return priv->hw_info->rx_ctrl_fb_out_frame_count;
-
-	if (!strcmp("Frames Out(Filters)", s->stat_string))
-		return priv->hw_info->rx_ctrl_fb_filt_out_frame_count;
-
-	if (!strcmp("RX Buffer FIFO Depth", s->stat_string))
-		return priv->hw_info->rx_ctrl_fb_rx_fifo_depth;
-
-	return s->reg_offset;
-}
-
 static int bcmasp_get_sset_count(struct net_device *dev, int string_set)
 {
 	switch (string_set) {
@@ -126,13 +101,10 @@ static void bcmasp_update_mib_counters(struct bcmasp_intf *intf)
 		char *p;
 
 		s = &bcmasp_gstrings_stats[i];
-		offset = bcmasp_stat_fixup_offset(intf, s);
+		offset = s->reg_offset;
 		switch (s->type) {
 		case BCMASP_STAT_SOFT:
 			continue;
-		case BCMASP_STAT_RX_EDPKT:
-			val = rx_edpkt_core_rl(intf->parent, offset);
-			break;
 		case BCMASP_STAT_RX_CTRL:
 			val = rx_ctrl_core_rl(intf->parent, offset);
 			break;
@@ -215,7 +187,7 @@ static int bcmasp_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 		memcpy(intf->sopass, wol->sopass, sizeof(wol->sopass));
 
 	mutex_lock(&priv->wol_lock);
-	priv->enable_wol(intf, !!intf->wolopts);
+	bcmasp_enable_wol(intf, !!intf->wolopts);
 	mutex_unlock(&priv->wol_lock);
 
 	return 0;
@@ -289,7 +261,7 @@ static int bcmasp_flow_get(struct bcmasp_intf *intf, struct ethtool_rxnfc *cmd)
 
 	memcpy(&cmd->fs, &nfilter->fs, sizeof(nfilter->fs));
 
-	cmd->data = NUM_NET_FILTERS;
+	cmd->data = intf->parent->num_net_filters;
 
 	return 0;
 }
@@ -336,7 +308,7 @@ static int bcmasp_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		break;
 	case ETHTOOL_GRXCLSRLALL:
 		err = bcmasp_netfilt_get_all_active(intf, rule_locs, &cmd->rule_cnt);
-		cmd->data = NUM_NET_FILTERS;
+		cmd->data = intf->parent->num_net_filters;
 		break;
 	default:
 		err = -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index 45ec1a9214a2..0d61b8580d72 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -180,14 +180,14 @@ static struct sk_buff *bcmasp_csum_offload(struct net_device *dev,
 	case htons(ETH_P_IP):
 		header |= PKT_OFFLOAD_HDR_SIZE_2((ip_hdrlen(skb) >> 8) & 0xf);
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_2(ip_hdrlen(skb) & 0xff);
-		epkt |= PKT_OFFLOAD_EPKT_IP(0) | PKT_OFFLOAD_EPKT_CSUM_L2;
+		epkt |= PKT_OFFLOAD_EPKT_IP(0);
 		ip_proto = ip_hdr(skb)->protocol;
 		header_cnt += 2;
 		break;
 	case htons(ETH_P_IPV6):
 		header |= PKT_OFFLOAD_HDR_SIZE_2((IP6_HLEN >> 8) & 0xf);
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_2(IP6_HLEN & 0xff);
-		epkt |= PKT_OFFLOAD_EPKT_IP(1) | PKT_OFFLOAD_EPKT_CSUM_L2;
+		epkt |= PKT_OFFLOAD_EPKT_IP(1);
 		ip_proto = ipv6_hdr(skb)->nexthdr;
 		header_cnt += 2;
 		break;
@@ -198,12 +198,12 @@ static struct sk_buff *bcmasp_csum_offload(struct net_device *dev,
 	switch (ip_proto) {
 	case IPPROTO_TCP:
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_3(tcp_hdrlen(skb));
-		epkt |= PKT_OFFLOAD_EPKT_TP(0) | PKT_OFFLOAD_EPKT_CSUM_L3;
+		epkt |= PKT_OFFLOAD_EPKT_TP(0) | PKT_OFFLOAD_EPKT_CSUM_L4;
 		header_cnt++;
 		break;
 	case IPPROTO_UDP:
 		header2 |= PKT_OFFLOAD_HDR2_SIZE_3(UDP_HLEN);
-		epkt |= PKT_OFFLOAD_EPKT_TP(1) | PKT_OFFLOAD_EPKT_CSUM_L3;
+		epkt |= PKT_OFFLOAD_EPKT_TP(1) | PKT_OFFLOAD_EPKT_CSUM_L4;
 		header_cnt++;
 		break;
 	default:
@@ -818,9 +818,7 @@ static void bcmasp_init_tx(struct bcmasp_intf *intf)
 	/* Tx SPB */
 	tx_spb_ctrl_wl(intf, ((intf->channel + 8) << TX_SPB_CTRL_XF_BID_SHIFT),
 		       TX_SPB_CTRL_XF_CTRL2);
-	tx_pause_ctrl_wl(intf, (1 << (intf->channel + 8)), TX_PAUSE_MAP_VECTOR);
 	tx_spb_top_wl(intf, 0x1e, TX_SPB_TOP_BLKOUT);
-	tx_spb_top_wl(intf, 0x0, TX_SPB_TOP_SPRE_BW_CTRL);
 
 	tx_spb_dma_wq(intf, intf->tx_spb_dma_addr, TX_SPB_DMA_READ);
 	tx_spb_dma_wq(intf, intf->tx_spb_dma_addr, TX_SPB_DMA_BASE);
@@ -1185,7 +1183,7 @@ static void bcmasp_map_res(struct bcmasp_priv *priv, struct bcmasp_intf *intf)
 {
 	/* Per port */
 	intf->res.umac = priv->base + UMC_OFFSET(intf);
-	intf->res.umac2fb = priv->base + (priv->hw_info->umac2fb +
+	intf->res.umac2fb = priv->base + (UMAC2FB_OFFSET + priv->rx_ctrl_offset +
 					  (intf->port * 0x4));
 	intf->res.rgmii = priv->base + RGMII_OFFSET(intf);
 
@@ -1200,7 +1198,6 @@ static void bcmasp_map_res(struct bcmasp_priv *priv, struct bcmasp_intf *intf)
 	intf->rx_edpkt_cfg = priv->base + RX_EDPKT_CFG_OFFSET(intf);
 }
 
-#define MAX_IRQ_STR_LEN		64
 struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv,
 					    struct device_node *ndev_dn, int i)
 {
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
index ad742612895f..af7418348e81 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf_defs.h
@@ -118,8 +118,7 @@
 #define  UMC_PSW_MS			0x624
 #define  UMC_PSW_LS			0x628
 
-#define UMAC2FB_OFFSET_2_1		0x9f044
-#define UMAC2FB_OFFSET			0x9f03c
+#define UMAC2FB_OFFSET			0x9f044
 #define  UMAC2FB_CFG			0x0
 #define   UMAC2FB_CFG_OPUT_EN		BIT(0)
 #define   UMAC2FB_CFG_VLAN_EN		BIT(1)
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index a461ec612e95..3e9c57196a39 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1446,7 +1446,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac)
 	struct phy_device *phy_dev;
 	int err;
 
-	phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
+	phy_dev = fixed_phy_register(&fphy_status, NULL);
 	if (IS_ERR(phy_dev)) {
 		dev_err(bgmac->dev, "Failed to register fixed PHY device\n");
 		return PTR_ERR(phy_dev);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8725e1e13908..d5495762c945 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -787,7 +787,7 @@ tx_free:
 	dev_kfree_skb_any(skb);
 tx_kick_pending:
 	if (BNXT_TX_PTP_IS_SET(lflags)) {
-		txr->tx_buf_ring[txr->tx_prod].is_ts_pkt = 0;
+		txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].is_ts_pkt = 0;
 		atomic64_inc(&bp->ptp_cfg->stats.ts_err);
 		if (!(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
 			/* set SKB to err so PTP worker will clean up */
@@ -795,7 +795,7 @@ tx_kick_pending:
 	}
 	if (txr->kick_pending)
 		bnxt_txr_db_kick(bp, txr, txr->tx_prod);
-	txr->tx_buf_ring[txr->tx_prod].skb = NULL;
+	txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].skb = NULL;
 	dev_core_stats_tx_dropped_inc(dev);
 	return NETDEV_TX_OK;
 }
@@ -893,9 +893,9 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 		bnapi->events &= ~BNXT_TX_CMP_EVENT;
 }
 
-static bool bnxt_separate_head_pool(void)
+static bool bnxt_separate_head_pool(struct bnxt_rx_ring_info *rxr)
 {
-	return PAGE_SIZE > BNXT_RX_PAGE_SIZE;
+	return rxr->need_head_pool || PAGE_SIZE > BNXT_RX_PAGE_SIZE;
 }
 
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
@@ -919,6 +919,20 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 	return page;
 }
 
+static netmem_ref __bnxt_alloc_rx_netmem(struct bnxt *bp, dma_addr_t *mapping,
+					 struct bnxt_rx_ring_info *rxr,
+					 gfp_t gfp)
+{
+	netmem_ref netmem;
+
+	netmem = page_pool_alloc_netmems(rxr->page_pool, gfp);
+	if (!netmem)
+		return 0;
+
+	*mapping = page_pool_get_dma_addr_netmem(netmem);
+	return netmem;
+}
+
 static inline u8 *__bnxt_alloc_rx_frag(struct bnxt *bp, dma_addr_t *mapping,
 				       struct bnxt_rx_ring_info *rxr,
 				       gfp_t gfp)
@@ -999,21 +1013,19 @@ static inline u16 bnxt_find_next_agg_idx(struct bnxt_rx_ring_info *rxr, u16 idx)
 	return next;
 }
 
-static inline int bnxt_alloc_rx_page(struct bnxt *bp,
-				     struct bnxt_rx_ring_info *rxr,
-				     u16 prod, gfp_t gfp)
+static int bnxt_alloc_rx_netmem(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
+				u16 prod, gfp_t gfp)
 {
 	struct rx_bd *rxbd =
 		&rxr->rx_agg_desc_ring[RX_AGG_RING(bp, prod)][RX_IDX(prod)];
 	struct bnxt_sw_rx_agg_bd *rx_agg_buf;
-	struct page *page;
-	dma_addr_t mapping;
 	u16 sw_prod = rxr->rx_sw_agg_prod;
 	unsigned int offset = 0;
+	dma_addr_t mapping;
+	netmem_ref netmem;
 
-	page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp);
-
-	if (!page)
+	netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, gfp);
+	if (!netmem)
 		return -ENOMEM;
 
 	if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap)))
@@ -1023,7 +1035,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 	rx_agg_buf = &rxr->rx_agg_ring[sw_prod];
 	rxr->rx_sw_agg_prod = RING_RX_AGG(bp, NEXT_RX_AGG(sw_prod));
 
-	rx_agg_buf->page = page;
+	rx_agg_buf->netmem = netmem;
 	rx_agg_buf->offset = offset;
 	rx_agg_buf->mapping = mapping;
 	rxbd->rx_bd_haddr = cpu_to_le64(mapping);
@@ -1067,11 +1079,11 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
 		p5_tpa = true;
 
 	for (i = 0; i < agg_bufs; i++) {
-		u16 cons;
-		struct rx_agg_cmp *agg;
 		struct bnxt_sw_rx_agg_bd *cons_rx_buf, *prod_rx_buf;
+		struct rx_agg_cmp *agg;
 		struct rx_bd *prod_bd;
-		struct page *page;
+		netmem_ref netmem;
+		u16 cons;
 
 		if (p5_tpa)
 			agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, start + i);
@@ -1088,11 +1100,11 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
 		cons_rx_buf = &rxr->rx_agg_ring[cons];
 
 		/* It is possible for sw_prod to be equal to cons, so
-		 * set cons_rx_buf->page to NULL first.
+		 * set cons_rx_buf->netmem to 0 first.
 		 */
-		page = cons_rx_buf->page;
-		cons_rx_buf->page = NULL;
-		prod_rx_buf->page = page;
+		netmem = cons_rx_buf->netmem;
+		cons_rx_buf->netmem = 0;
+		prod_rx_buf->netmem = netmem;
 		prod_rx_buf->offset = cons_rx_buf->offset;
 
 		prod_rx_buf->mapping = cons_rx_buf->mapping;
@@ -1218,29 +1230,35 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp,
 	return skb;
 }
 
-static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
-			       struct bnxt_cp_ring_info *cpr,
-			       struct skb_shared_info *shinfo,
-			       u16 idx, u32 agg_bufs, bool tpa,
-			       struct xdp_buff *xdp)
+static u32 __bnxt_rx_agg_netmems(struct bnxt *bp,
+				 struct bnxt_cp_ring_info *cpr,
+				 u16 idx, u32 agg_bufs, bool tpa,
+				 struct sk_buff *skb,
+				 struct xdp_buff *xdp)
 {
 	struct bnxt_napi *bnapi = cpr->bnapi;
-	struct pci_dev *pdev = bp->pdev;
-	struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
-	u16 prod = rxr->rx_agg_prod;
+	struct skb_shared_info *shinfo;
+	struct bnxt_rx_ring_info *rxr;
 	u32 i, total_frag_len = 0;
 	bool p5_tpa = false;
+	u16 prod;
+
+	rxr = bnapi->rx_ring;
+	prod = rxr->rx_agg_prod;
 
 	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && tpa)
 		p5_tpa = true;
 
+	if (skb)
+		shinfo = skb_shinfo(skb);
+	else
+		shinfo = xdp_get_shared_info_from_buff(xdp);
+
 	for (i = 0; i < agg_bufs; i++) {
-		skb_frag_t *frag = &shinfo->frags[i];
-		u16 cons, frag_len;
-		struct rx_agg_cmp *agg;
 		struct bnxt_sw_rx_agg_bd *cons_rx_buf;
-		struct page *page;
-		dma_addr_t mapping;
+		struct rx_agg_cmp *agg;
+		u16 cons, frag_len;
+		netmem_ref netmem;
 
 		if (p5_tpa)
 			agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, i);
@@ -1251,27 +1269,41 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 			    RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT;
 
 		cons_rx_buf = &rxr->rx_agg_ring[cons];
-		skb_frag_fill_page_desc(frag, cons_rx_buf->page,
-					cons_rx_buf->offset, frag_len);
-		shinfo->nr_frags = i + 1;
+		if (skb) {
+			skb_add_rx_frag_netmem(skb, i, cons_rx_buf->netmem,
+					       cons_rx_buf->offset,
+					       frag_len, BNXT_RX_PAGE_SIZE);
+		} else {
+			skb_frag_t *frag = &shinfo->frags[i];
+
+			skb_frag_fill_netmem_desc(frag, cons_rx_buf->netmem,
+						  cons_rx_buf->offset,
+						  frag_len);
+			shinfo->nr_frags = i + 1;
+		}
 		__clear_bit(cons, rxr->rx_agg_bmap);
 
-		/* It is possible for bnxt_alloc_rx_page() to allocate
+		/* It is possible for bnxt_alloc_rx_netmem() to allocate
 		 * a sw_prod index that equals the cons index, so we
 		 * need to clear the cons entry now.
 		 */
-		mapping = cons_rx_buf->mapping;
-		page = cons_rx_buf->page;
-		cons_rx_buf->page = NULL;
+		netmem = cons_rx_buf->netmem;
+		cons_rx_buf->netmem = 0;
 
-		if (xdp && page_is_pfmemalloc(page))
+		if (xdp && netmem_is_pfmemalloc(netmem))
 			xdp_buff_set_frag_pfmemalloc(xdp);
 
-		if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_ATOMIC) != 0) {
+		if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_ATOMIC) != 0) {
+			if (skb) {
+				skb->len -= frag_len;
+				skb->data_len -= frag_len;
+				skb->truesize -= BNXT_RX_PAGE_SIZE;
+			}
+
 			--shinfo->nr_frags;
-			cons_rx_buf->page = page;
+			cons_rx_buf->netmem = netmem;
 
-			/* Update prod since possibly some pages have been
+			/* Update prod since possibly some netmems have been
 			 * allocated already.
 			 */
 			rxr->rx_agg_prod = prod;
@@ -1279,8 +1311,8 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 			return 0;
 		}
 
-		dma_sync_single_for_cpu(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
-					bp->rx_dir);
+		page_pool_dma_sync_netmem_for_cpu(rxr->page_pool, netmem, 0,
+						  BNXT_RX_PAGE_SIZE);
 
 		total_frag_len += frag_len;
 		prod = NEXT_RX_AGG(prod);
@@ -1289,32 +1321,28 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 	return total_frag_len;
 }
 
-static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp,
-					     struct bnxt_cp_ring_info *cpr,
-					     struct sk_buff *skb, u16 idx,
-					     u32 agg_bufs, bool tpa)
+static struct sk_buff *bnxt_rx_agg_netmems_skb(struct bnxt *bp,
+					       struct bnxt_cp_ring_info *cpr,
+					       struct sk_buff *skb, u16 idx,
+					       u32 agg_bufs, bool tpa)
 {
-	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	u32 total_frag_len = 0;
 
-	total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo, idx,
-					     agg_bufs, tpa, NULL);
+	total_frag_len = __bnxt_rx_agg_netmems(bp, cpr, idx, agg_bufs, tpa,
+					       skb, NULL);
 	if (!total_frag_len) {
 		skb_mark_for_recycle(skb);
 		dev_kfree_skb(skb);
 		return NULL;
 	}
 
-	skb->data_len += total_frag_len;
-	skb->len += total_frag_len;
-	skb->truesize += BNXT_RX_PAGE_SIZE * agg_bufs;
 	return skb;
 }
 
-static u32 bnxt_rx_agg_pages_xdp(struct bnxt *bp,
-				 struct bnxt_cp_ring_info *cpr,
-				 struct xdp_buff *xdp, u16 idx,
-				 u32 agg_bufs, bool tpa)
+static u32 bnxt_rx_agg_netmems_xdp(struct bnxt *bp,
+				   struct bnxt_cp_ring_info *cpr,
+				   struct xdp_buff *xdp, u16 idx,
+				   u32 agg_bufs, bool tpa)
 {
 	struct skb_shared_info *shinfo = xdp_get_shared_info_from_buff(xdp);
 	u32 total_frag_len = 0;
@@ -1322,8 +1350,8 @@ static u32 bnxt_rx_agg_pages_xdp(struct bnxt *bp,
 	if (!xdp_buff_has_frags(xdp))
 		shinfo->nr_frags = 0;
 
-	total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo,
-					     idx, agg_bufs, tpa, xdp);
+	total_frag_len = __bnxt_rx_agg_netmems(bp, cpr, idx, agg_bufs, tpa,
+					       NULL, xdp);
 	if (total_frag_len) {
 		xdp_buff_set_frags_flag(xdp);
 		shinfo->nr_frags = agg_bufs;
@@ -1895,7 +1923,8 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 	}
 
 	if (agg_bufs) {
-		skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, idx, agg_bufs, true);
+		skb = bnxt_rx_agg_netmems_skb(bp, cpr, skb, idx, agg_bufs,
+					      true);
 		if (!skb) {
 			/* Page reuse already handled by bnxt_rx_pages(). */
 			cpr->sw_stats->rx.rx_oom_discards += 1;
@@ -2015,6 +2044,7 @@ static struct sk_buff *bnxt_rx_vlan(struct sk_buff *skb, u8 cmp_type,
 	}
 	return skb;
 vlan_err:
+	skb_mark_for_recycle(skb);
 	dev_kfree_skb(skb);
 	return NULL;
 }
@@ -2175,9 +2205,10 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	if (bnxt_xdp_attached(bp, rxr)) {
 		bnxt_xdp_buff_init(bp, rxr, cons, data_ptr, len, &xdp);
 		if (agg_bufs) {
-			u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
-							     cp_cons, agg_bufs,
-							     false);
+			u32 frag_len = bnxt_rx_agg_netmems_xdp(bp, cpr, &xdp,
+							       cp_cons,
+							       agg_bufs,
+							       false);
 			if (!frag_len)
 				goto oom_next_rx;
 
@@ -2229,7 +2260,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 	if (agg_bufs) {
 		if (!xdp_active) {
-			skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, cp_cons, agg_bufs, false);
+			skb = bnxt_rx_agg_netmems_skb(bp, cpr, skb, cp_cons,
+						      agg_bufs, false);
 			if (!skb)
 				goto oom_next_rx;
 		} else {
@@ -3414,6 +3446,9 @@ static void bnxt_free_tx_skbs(struct bnxt *bp)
 
 		bnxt_free_one_tx_ring_skbs(bp, txr, i);
 	}
+
+	if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
+		bnxt_ptp_free_txts_skbs(bp->ptp_cfg);
 }
 
 static void bnxt_free_one_rx_ring(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
@@ -3445,15 +3480,15 @@ static void bnxt_free_one_rx_agg_ring(struct bnxt *bp, struct bnxt_rx_ring_info
 
 	for (i = 0; i < max_idx; i++) {
 		struct bnxt_sw_rx_agg_bd *rx_agg_buf = &rxr->rx_agg_ring[i];
-		struct page *page = rx_agg_buf->page;
+		netmem_ref netmem = rx_agg_buf->netmem;
 
-		if (!page)
+		if (!netmem)
 			continue;
 
-		rx_agg_buf->page = NULL;
+		rx_agg_buf->netmem = 0;
 		__clear_bit(i, rxr->rx_agg_bmap);
 
-		page_pool_recycle_direct(rxr->page_pool, page);
+		page_pool_recycle_direct_netmem(rxr->page_pool, netmem);
 	}
 }
 
@@ -3746,7 +3781,7 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
 			xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
 		page_pool_destroy(rxr->page_pool);
-		if (bnxt_separate_head_pool())
+		if (bnxt_separate_head_pool(rxr))
 			page_pool_destroy(rxr->head_pool);
 		rxr->page_pool = rxr->head_pool = NULL;
 
@@ -3777,15 +3812,19 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 	pp.dev = &bp->pdev->dev;
 	pp.dma_dir = bp->rx_dir;
 	pp.max_len = PAGE_SIZE;
-	pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+	pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV |
+		   PP_FLAG_ALLOW_UNREADABLE_NETMEM;
+	pp.queue_idx = rxr->bnapi->index;
 
 	pool = page_pool_create(&pp);
 	if (IS_ERR(pool))
 		return PTR_ERR(pool);
 	rxr->page_pool = pool;
 
-	if (bnxt_separate_head_pool()) {
+	rxr->need_head_pool = page_pool_is_unreadable(pool);
+	if (bnxt_separate_head_pool(rxr)) {
 		pp.pool_size = max(bp->rx_ring_size, 1024);
+		pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
 		pool = page_pool_create(&pp);
 		if (IS_ERR(pool))
 			goto err_destroy_pp;
@@ -4197,6 +4236,8 @@ static void bnxt_reset_rx_ring_struct(struct bnxt *bp,
 
 	rxr->page_pool->p.napi = NULL;
 	rxr->page_pool = NULL;
+	rxr->head_pool->p.napi = NULL;
+	rxr->head_pool = NULL;
 	memset(&rxr->xdp_rxq, 0, sizeof(struct xdp_rxq_info));
 
 	ring = &rxr->rx_ring_struct;
@@ -4321,16 +4362,16 @@ static void bnxt_alloc_one_rx_ring_skb(struct bnxt *bp,
 	rxr->rx_prod = prod;
 }
 
-static void bnxt_alloc_one_rx_ring_page(struct bnxt *bp,
-					struct bnxt_rx_ring_info *rxr,
-					int ring_nr)
+static void bnxt_alloc_one_rx_ring_netmem(struct bnxt *bp,
+					  struct bnxt_rx_ring_info *rxr,
+					  int ring_nr)
 {
 	u32 prod;
 	int i;
 
 	prod = rxr->rx_agg_prod;
 	for (i = 0; i < bp->rx_agg_ring_size; i++) {
-		if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_KERNEL)) {
+		if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_KERNEL)) {
 			netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d pages only\n",
 				    ring_nr, i, bp->rx_ring_size);
 			break;
@@ -4371,7 +4412,7 @@ static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr)
 	if (!(bp->flags & BNXT_FLAG_AGG_RINGS))
 		return 0;
 
-	bnxt_alloc_one_rx_ring_page(bp, rxr, ring_nr);
+	bnxt_alloc_one_rx_ring_netmem(bp, rxr, ring_nr);
 
 	if (rxr->rx_tpa) {
 		rc = bnxt_alloc_one_tpa_info_data(bp, rxr);
@@ -10073,7 +10114,7 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	struct hwrm_ver_get_input *req;
 	u16 fw_maj, fw_min, fw_bld, fw_rsv;
 	u32 dev_caps_cfg, hwrm_ver;
-	int rc, len;
+	int rc, len, max_tmo_secs;
 
 	rc = hwrm_req_init(bp, req, HWRM_VER_GET);
 	if (rc)
@@ -10146,9 +10187,14 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	bp->hwrm_cmd_max_timeout = le16_to_cpu(resp->max_req_timeout) * 1000;
 	if (!bp->hwrm_cmd_max_timeout)
 		bp->hwrm_cmd_max_timeout = HWRM_CMD_MAX_TIMEOUT;
-	else if (bp->hwrm_cmd_max_timeout > HWRM_CMD_MAX_TIMEOUT)
-		netdev_warn(bp->dev, "Device requests max timeout of %d seconds, may trigger hung task watchdog\n",
-			    bp->hwrm_cmd_max_timeout / 1000);
+	max_tmo_secs = bp->hwrm_cmd_max_timeout / 1000;
+#ifdef CONFIG_DETECT_HUNG_TASK
+	if (bp->hwrm_cmd_max_timeout > HWRM_CMD_MAX_TIMEOUT ||
+	    max_tmo_secs > CONFIG_DEFAULT_HUNG_TASK_TIMEOUT) {
+		netdev_warn(bp->dev, "Device requests max timeout of %d seconds, may trigger hung task watchdog (kernel default %ds)\n",
+			    max_tmo_secs, CONFIG_DEFAULT_HUNG_TASK_TIMEOUT);
+	}
+#endif
 
 	if (resp->hwrm_intf_maj_8b >= 1) {
 		bp->hwrm_max_req_len = le16_to_cpu(resp->max_req_win_len);
@@ -11599,6 +11645,9 @@ static void bnxt_init_napi(struct bnxt *bp)
 		poll_fn = bnxt_poll_p5;
 	else if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		cp_nr_rings--;
+
+	set_bit(BNXT_STATE_NAPI_DISABLED, &bp->state);
+
 	for (i = 0; i < cp_nr_rings; i++) {
 		bnapi = bp->bnapi[i];
 		netif_napi_add_config_locked(bp->dev, &bnapi->napi, poll_fn,
@@ -12318,12 +12367,15 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 {
 	struct hwrm_func_drv_if_change_output *resp;
 	struct hwrm_func_drv_if_change_input *req;
-	bool fw_reset = !bp->irq_tbl;
 	bool resc_reinit = false;
 	bool caps_change = false;
 	int rc, retry = 0;
+	bool fw_reset;
 	u32 flags = 0;
 
+	fw_reset = (bp->fw_reset_state == BNXT_FW_RESET_STATE_ABORT);
+	bp->fw_reset_state = 0;
+
 	if (!(bp->fw_cap & BNXT_FW_CAP_IF_CHANGE))
 		return 0;
 
@@ -12392,13 +12444,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 				set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
 				return rc;
 			}
+			/* IRQ will be initialized later in bnxt_request_irq()*/
 			bnxt_clear_int_mode(bp);
-			rc = bnxt_init_int_mode(bp);
-			if (rc) {
-				clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
-				netdev_err(bp->dev, "init int mode failed\n");
-				return rc;
-			}
 		}
 		rc = bnxt_cancel_reservations(bp, fw_reset);
 	}
@@ -12797,8 +12844,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	/* VF-reps may need to be re-opened after the PF is re-opened */
 	if (BNXT_PF(bp))
 		bnxt_vf_reps_open(bp);
-	if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
-		WRITE_ONCE(bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS);
 	bnxt_ptp_init_rtc(bp, true);
 	bnxt_ptp_cfg_tstamp_filters(bp);
 	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
@@ -14010,13 +14055,28 @@ static void bnxt_unlock_sp(struct bnxt *bp)
 	netdev_unlock(bp->dev);
 }
 
+/* Same as bnxt_lock_sp() with additional rtnl_lock */
+static void bnxt_rtnl_lock_sp(struct bnxt *bp)
+{
+	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+	rtnl_lock();
+	netdev_lock(bp->dev);
+}
+
+static void bnxt_rtnl_unlock_sp(struct bnxt *bp)
+{
+	set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+	netdev_unlock(bp->dev);
+	rtnl_unlock();
+}
+
 /* Only called from bnxt_sp_task() */
 static void bnxt_reset(struct bnxt *bp, bool silent)
 {
-	bnxt_lock_sp(bp);
+	bnxt_rtnl_lock_sp(bp);
 	if (test_bit(BNXT_STATE_OPEN, &bp->state))
 		bnxt_reset_task(bp, silent);
-	bnxt_unlock_sp(bp);
+	bnxt_rtnl_unlock_sp(bp);
 }
 
 /* Only called from bnxt_sp_task() */
@@ -14024,9 +14084,9 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 {
 	int i;
 
-	bnxt_lock_sp(bp);
+	bnxt_rtnl_lock_sp(bp);
 	if (!test_bit(BNXT_STATE_OPEN, &bp->state)) {
-		bnxt_unlock_sp(bp);
+		bnxt_rtnl_unlock_sp(bp);
 		return;
 	}
 	/* Disable and flush TPA before resetting the RX ring */
@@ -14065,7 +14125,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 	}
 	if (bp->flags & BNXT_FLAG_TPA)
 		bnxt_set_tpa(bp, true);
-	bnxt_unlock_sp(bp);
+	bnxt_rtnl_unlock_sp(bp);
 }
 
 static void bnxt_fw_fatal_close(struct bnxt *bp)
@@ -14833,7 +14893,7 @@ static void bnxt_fw_reset_abort(struct bnxt *bp, int rc)
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF)
 		bnxt_dl_health_fw_status_update(bp, false);
-	bp->fw_reset_state = 0;
+	bp->fw_reset_state = BNXT_FW_RESET_STATE_ABORT;
 	netif_close(bp->dev);
 }
 
@@ -14957,15 +15017,17 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING;
 		fallthrough;
 	case BNXT_FW_RESET_STATE_OPENING:
-		while (!netdev_trylock(bp->dev)) {
+		while (!rtnl_trylock()) {
 			bnxt_queue_fw_reset_work(bp, HZ / 10);
 			return;
 		}
+		netdev_lock(bp->dev);
 		rc = bnxt_open(bp->dev);
 		if (rc) {
 			netdev_err(bp->dev, "bnxt_open() failed during FW reset\n");
 			bnxt_fw_reset_abort(bp, rc);
 			netdev_unlock(bp->dev);
+			rtnl_unlock();
 			goto ulp_start;
 		}
 
@@ -14985,6 +15047,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			bnxt_dl_health_fw_status_update(bp, true);
 		}
 		netdev_unlock(bp->dev);
+		rtnl_unlock();
 		bnxt_ulp_start(bp, 0);
 		bnxt_reenable_sriov(bp);
 		netdev_lock(bp->dev);
@@ -15708,6 +15771,7 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 	clone->rx_agg_prod = 0;
 	clone->rx_sw_agg_prod = 0;
 	clone->rx_next_cons = 0;
+	clone->need_head_pool = false;
 
 	rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid);
 	if (rc)
@@ -15750,7 +15814,7 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 
 	bnxt_alloc_one_rx_ring_skb(bp, clone, idx);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
-		bnxt_alloc_one_rx_ring_page(bp, clone, idx);
+		bnxt_alloc_one_rx_ring_netmem(bp, clone, idx);
 	if (bp->flags & BNXT_FLAG_TPA)
 		bnxt_alloc_one_tpa_info_data(bp, clone);
 
@@ -15766,7 +15830,7 @@ err_rxq_info_unreg:
 	xdp_rxq_info_unreg(&clone->xdp_rxq);
 err_page_pool_destroy:
 	page_pool_destroy(clone->page_pool);
-	if (bnxt_separate_head_pool())
+	if (bnxt_separate_head_pool(clone))
 		page_pool_destroy(clone->head_pool);
 	clone->page_pool = NULL;
 	clone->head_pool = NULL;
@@ -15785,7 +15849,7 @@ static void bnxt_queue_mem_free(struct net_device *dev, void *qmem)
 	xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
 	page_pool_destroy(rxr->page_pool);
-	if (bnxt_separate_head_pool())
+	if (bnxt_separate_head_pool(rxr))
 		page_pool_destroy(rxr->head_pool);
 	rxr->page_pool = NULL;
 	rxr->head_pool = NULL;
@@ -15876,6 +15940,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	rxr->page_pool = clone->page_pool;
 	rxr->head_pool = clone->head_pool;
 	rxr->xdp_rxq = clone->xdp_rxq;
+	rxr->need_head_pool = clone->need_head_pool;
 
 	bnxt_copy_rx_ring(bp, rxr, clone);
 
@@ -15933,7 +15998,7 @@ err_reset:
 		   rc);
 	napi_enable_locked(&bnapi->napi);
 	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
-	bnxt_reset_task(bp, true);
+	netif_close(dev);
 	return rc;
 }
 
@@ -15961,7 +16026,7 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 	bnxt_hwrm_rx_ring_free(bp, rxr, false);
 	bnxt_hwrm_rx_agg_ring_free(bp, rxr, false);
 	page_pool_disable_direct_recycling(rxr->page_pool);
-	if (bnxt_separate_head_pool())
+	if (bnxt_separate_head_pool(rxr))
 		page_pool_disable_direct_recycling(rxr->head_pool);
 
 	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
@@ -16003,8 +16068,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 
 	bnxt_rdma_aux_device_del(bp);
 
-	bnxt_ptp_clear(bp);
 	unregister_netdev(dev);
+	bnxt_ptp_clear(bp);
 
 	bnxt_rdma_aux_device_uninit(bp);
 
@@ -16749,6 +16814,7 @@ static int bnxt_resume(struct device *device)
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
+	rtnl_lock();
 	netdev_lock(dev);
 	rc = pci_enable_device(bp->pdev);
 	if (rc) {
@@ -16793,6 +16859,7 @@ static int bnxt_resume(struct device *device)
 
 resume_exit:
 	netdev_unlock(bp->dev);
+	rtnl_unlock();
 	bnxt_ulp_start(bp, rc);
 	if (!rc)
 		bnxt_reenable_sriov(bp);
@@ -16931,10 +16998,9 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 		if (!err)
 			result = PCI_ERS_RESULT_RECOVERED;
 
+		/* IRQ will be initialized later in bnxt_io_resume */
 		bnxt_ulp_irq_stop(bp);
 		bnxt_clear_int_mode(bp);
-		err = bnxt_init_int_mode(bp);
-		bnxt_ulp_irq_restart(bp, err);
 	}
 
 reset_exit:
@@ -16959,20 +17025,25 @@ static void bnxt_io_resume(struct pci_dev *pdev)
 	int err;
 
 	netdev_info(bp->dev, "PCI Slot Resume\n");
+	rtnl_lock();
 	netdev_lock(netdev);
 
 	err = bnxt_hwrm_func_qcaps(bp);
 	if (!err) {
-		if (netif_running(netdev))
+		if (netif_running(netdev)) {
 			err = bnxt_open(netdev);
-		else
+		} else {
 			err = bnxt_reserve_rings(bp, true);
+			if (!err)
+				err = bnxt_init_int_mode(bp);
+		}
 	}
 
 	if (!err)
 		netif_device_attach(netdev);
 
 	netdev_unlock(netdev);
+	rtnl_unlock();
 	bnxt_ulp_start(bp, err);
 	if (!err)
 		bnxt_reenable_sriov(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 21726cf56586..fda0d3cc6227 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -903,7 +903,7 @@ struct bnxt_sw_rx_bd {
 };
 
 struct bnxt_sw_rx_agg_bd {
-	struct page		*page;
+	netmem_ref		netmem;
 	unsigned int		offset;
 	dma_addr_t		mapping;
 };
@@ -1106,6 +1106,7 @@ struct bnxt_rx_ring_info {
 
 	unsigned long		*rx_agg_bmap;
 	u16			rx_agg_bmap_size;
+	bool                    need_head_pool;
 
 	dma_addr_t		rx_desc_mapping[MAX_RX_PAGES];
 	dma_addr_t		rx_agg_desc_mapping[MAX_RX_AGG_PAGES];
@@ -2614,6 +2615,7 @@ struct bnxt {
 #define BNXT_FW_RESET_STATE_POLL_FW	4
 #define BNXT_FW_RESET_STATE_OPENING	5
 #define BNXT_FW_RESET_STATE_POLL_FW_DOWN	6
+#define BNXT_FW_RESET_STATE_ABORT	7
 
 	u16			fw_reset_min_dsecs;
 #define BNXT_DFLT_FW_RST_MIN_DSECS	20
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
index 5576e7cf8463..ce97befd3cb3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
@@ -110,20 +110,30 @@ static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg,
 			}
 		}
 
+		if (cmn_req->req_type ==
+				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
+			info->dest_buf_size += len;
+
 		if (info->dest_buf) {
 			if ((info->seg_start + off + len) <=
 			    BNXT_COREDUMP_BUF_LEN(info->buf_len)) {
-				memcpy(info->dest_buf + off, dma_buf, len);
+				u16 copylen = min_t(u16, len,
+						    info->dest_buf_size - off);
+
+				memcpy(info->dest_buf + off, dma_buf, copylen);
+				if (copylen < len)
+					break;
 			} else {
 				rc = -ENOBUFS;
+				if (cmn_req->req_type ==
+				    cpu_to_le16(HWRM_DBG_COREDUMP_LIST)) {
+					kfree(info->dest_buf);
+					info->dest_buf = NULL;
+				}
 				break;
 			}
 		}
 
-		if (cmn_req->req_type ==
-				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
-			info->dest_buf_size += len;
-
 		if (!(cmn_resp->flags & HWRM_DBG_CMN_FLAGS_MORE))
 			break;
 
@@ -496,9 +506,16 @@ err:
 					  start_utc, coredump.total_segs + 1,
 					  rc);
 	kfree(coredump.data);
-	*dump_len += sizeof(struct bnxt_coredump_record);
-	if (rc == -ENOBUFS)
+	if (!rc) {
+		*dump_len += sizeof(struct bnxt_coredump_record);
+		/* The actual coredump length can be smaller than the FW
+		 * reported length earlier.  Use the ethtool provided length.
+		 */
+		if (buf_len)
+			*dump_len = buf_len;
+	} else if (rc == -ENOBUFS) {
 		netdev_err(bp->dev, "Firmware returned large coredump buffer\n");
+	}
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 48dd5922e4dd..f5d490bf997e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2062,6 +2062,17 @@ static int bnxt_get_regs_len(struct net_device *dev)
 	return reg_len;
 }
 
+#define BNXT_PCIE_32B_ENTRY(start, end)			\
+	 { offsetof(struct pcie_ctx_hw_stats, start),	\
+	   offsetof(struct pcie_ctx_hw_stats, end) }
+
+static const struct {
+	u16 start;
+	u16 end;
+} bnxt_pcie_32b_entries[] = {
+	BNXT_PCIE_32B_ENTRY(pcie_ltssm_histogram[0], pcie_ltssm_histogram[3]),
+};
+
 static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 			  void *_p)
 {
@@ -2094,12 +2105,27 @@ static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	req->pcie_stat_host_addr = cpu_to_le64(hw_pcie_stats_addr);
 	rc = hwrm_req_send(bp, req);
 	if (!rc) {
-		__le64 *src = (__le64 *)hw_pcie_stats;
-		u64 *dst = (u64 *)(_p + BNXT_PXP_REG_LEN);
-		int i;
-
-		for (i = 0; i < sizeof(*hw_pcie_stats) / sizeof(__le64); i++)
-			dst[i] = le64_to_cpu(src[i]);
+		u8 *dst = (u8 *)(_p + BNXT_PXP_REG_LEN);
+		u8 *src = (u8 *)hw_pcie_stats;
+		int i, j;
+
+		for (i = 0, j = 0; i < sizeof(*hw_pcie_stats); ) {
+			if (i >= bnxt_pcie_32b_entries[j].start &&
+			    i <= bnxt_pcie_32b_entries[j].end) {
+				u32 *dst32 = (u32 *)(dst + i);
+
+				*dst32 = le32_to_cpu(*(__le32 *)(src + i));
+				i += 4;
+				if (i > bnxt_pcie_32b_entries[j].end &&
+				    j < ARRAY_SIZE(bnxt_pcie_32b_entries) - 1)
+					j++;
+			} else {
+				u64 *dst64 = (u64 *)(dst + i);
+
+				*dst64 = le64_to_cpu(*(__le64 *)(src + i));
+				i += 8;
+			}
+		}
 	}
 	hwrm_req_drop(bp, req);
 }
@@ -4991,6 +5017,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 	if (!bp->num_tests || !BNXT_PF(bp))
 		return;
 
+	memset(buf, 0, sizeof(u64) * bp->num_tests);
 	if (etest->flags & ETH_TEST_FL_OFFLINE &&
 	    bnxt_ulp_registered(bp->edev)) {
 		etest->flags |= ETH_TEST_FL_FAILED;
@@ -4998,7 +5025,6 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		return;
 	}
 
-	memset(buf, 0, sizeof(u64) * bp->num_tests);
 	if (!netif_running(dev)) {
 		etest->flags |= ETH_TEST_FL_FAILED;
 		return;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
index 15ca51b5d204..fb5f5b063c3d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
@@ -58,7 +58,7 @@ void hwrm_update_token(struct bnxt *bp, u16 seq, enum bnxt_hwrm_wait_state s);
 
 #define BNXT_HWRM_MAX_REQ_LEN		(bp->hwrm_max_req_len)
 #define BNXT_HWRM_SHORT_REQ_LEN		sizeof(struct hwrm_short_input)
-#define HWRM_CMD_MAX_TIMEOUT		40000U
+#define HWRM_CMD_MAX_TIMEOUT		60000U
 #define SHORT_HWRM_CMD_TIMEOUT		20
 #define HWRM_CMD_TIMEOUT		(bp->hwrm_cmd_timeout)
 #define HWRM_RESET_TIMEOUT		((HWRM_CMD_TIMEOUT) * 4)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 2d4e19b96ee7..0669d43472f5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -794,6 +794,27 @@ next_slot:
 	return HZ;
 }
 
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp)
+{
+	struct bnxt_ptp_tx_req *txts_req;
+	u16 cons = ptp->txts_cons;
+
+	/* make sure ptp aux worker finished with
+	 * possible BNXT_STATE_OPEN set
+	 */
+	ptp_cancel_worker_sync(ptp->ptp_clock);
+
+	ptp->tx_avail = BNXT_MAX_TX_TS;
+	while (cons != ptp->txts_prod) {
+		txts_req = &ptp->txts_req[cons];
+		if (!IS_ERR_OR_NULL(txts_req->tx_skb))
+			dev_kfree_skb_any(txts_req->tx_skb);
+		cons = NEXT_TXTS(cons);
+	}
+	ptp->txts_cons = cons;
+	ptp_schedule_worker(ptp->ptp_clock, 0);
+}
+
 int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod)
 {
 	spin_lock_bh(&ptp->ptp_tx_lock);
@@ -1105,7 +1126,6 @@ out:
 void bnxt_ptp_clear(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
-	int i;
 
 	if (!ptp)
 		return;
@@ -1117,12 +1137,5 @@ void bnxt_ptp_clear(struct bnxt *bp)
 	kfree(ptp->ptp_info.pin_config);
 	ptp->ptp_info.pin_config = NULL;
 
-	for (i = 0; i < BNXT_MAX_TX_TS; i++) {
-		if (ptp->txts_req[i].tx_skb) {
-			dev_kfree_skb_any(ptp->txts_req[i].tx_skb);
-			ptp->txts_req[i].tx_skb = NULL;
-		}
-	}
-
 	bnxt_unmap_ptp_regs(bp);
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index a95f05e9c579..0481161d26ef 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -162,6 +162,7 @@ int bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp);
 void bnxt_ptp_reapply_pps(struct bnxt *bp);
 int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr);
 int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp);
 int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod);
 void bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb, u16 prod);
 int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index a8e930d5dbb0..84c4812414fd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -20,6 +20,7 @@
 #include <asm/byteorder.h>
 #include <linux/bitmap.h>
 #include <linux/auxiliary_bus.h>
+#include <net/netdev_lock.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -148,7 +149,6 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_ulp *ulp;
-	int i = 0;
 
 	ulp = edev->ulp_tbl;
 	netdev_lock(dev);
@@ -164,10 +164,6 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 	synchronize_rcu();
 	ulp->max_async_event_id = 0;
 	ulp->async_events_bmap = NULL;
-	while (atomic_read(&ulp->ref_count) != 0 && i < 10) {
-		msleep(100);
-		i++;
-	}
 	mutex_unlock(&edev->en_dev_lock);
 	netdev_unlock(dev);
 	return;
@@ -309,14 +305,12 @@ void bnxt_ulp_irq_stop(struct bnxt *bp)
 		if (!ulp->msix_requested)
 			return;
 
-		netdev_lock(bp->dev);
-		ops = rcu_dereference(ulp->ulp_ops);
+		ops = netdev_lock_dereference(ulp->ulp_ops, bp->dev);
 		if (!ops || !ops->ulp_irq_stop)
 			return;
 		if (test_bit(BNXT_STATE_FW_RESET_DET, &bp->state))
 			reset = true;
 		ops->ulp_irq_stop(ulp->handle, reset);
-		netdev_unlock(bp->dev);
 	}
 }
 
@@ -335,8 +329,7 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err)
 		if (!ulp->msix_requested)
 			return;
 
-		netdev_lock(bp->dev);
-		ops = rcu_dereference(ulp->ulp_ops);
+		ops = netdev_lock_dereference(ulp->ulp_ops, bp->dev);
 		if (!ops || !ops->ulp_irq_restart)
 			return;
 
@@ -348,7 +341,6 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err)
 			bnxt_fill_msix_vecs(bp, ent);
 		}
 		ops->ulp_irq_restart(ulp->handle, ent);
-		netdev_unlock(bp->dev);
 		kfree(ent);
 	}
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index 7fa3b8d1ebd2..7b9dd8ebe4bc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -10,9 +10,6 @@
 #ifndef BNXT_ULP_H
 #define BNXT_ULP_H
 
-#define BNXT_ROCE_ULP	0
-#define BNXT_MAX_ULP	1
-
 #define BNXT_MIN_ROCE_CP_RINGS	2
 #define BNXT_MIN_ROCE_STAT_CTXS	1
 
@@ -50,7 +47,6 @@ struct bnxt_ulp {
 	unsigned long	*async_events_bmap;
 	u16		max_async_event_id;
 	u16		msix_requested;
-	atomic_t	ref_count;
 };
 
 struct bnxt_en_dev {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index e675611777b5..4a6d8cb9f970 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -425,9 +425,9 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 
 	if (prog) {
 		bnxt_set_rx_skb_mode(bp, true);
-		xdp_features_set_redirect_target(dev, true);
+		xdp_features_set_redirect_target_locked(dev, true);
 	} else {
-		xdp_features_clear_redirect_target(dev);
+		xdp_features_clear_redirect_target_locked(dev);
 		bnxt_set_rx_skb_mode(bp, false);
 	}
 	bp->tx_nr_rings_xdp = tx_xdp;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 73d78dcb774d..fa0077bc67b7 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -969,12 +969,13 @@ static int bcmgenet_set_pauseparam(struct net_device *dev,
 
 /* standard ethtool support functions. */
 enum bcmgenet_stat_type {
-	BCMGENET_STAT_NETDEV = -1,
+	BCMGENET_STAT_RTNL = -1,
 	BCMGENET_STAT_MIB_RX,
 	BCMGENET_STAT_MIB_TX,
 	BCMGENET_STAT_RUNT,
 	BCMGENET_STAT_MISC,
 	BCMGENET_STAT_SOFT,
+	BCMGENET_STAT_SOFT64,
 };
 
 struct bcmgenet_stats {
@@ -984,13 +985,15 @@ struct bcmgenet_stats {
 	enum bcmgenet_stat_type type;
 	/* reg offset from UMAC base for misc counters */
 	u16 reg_offset;
+	/* sync for u64 stats counters */
+	int syncp_offset;
 };
 
-#define STAT_NETDEV(m) { \
+#define STAT_RTNL(m) { \
 	.stat_string = __stringify(m), \
-	.stat_sizeof = sizeof(((struct net_device_stats *)0)->m), \
-	.stat_offset = offsetof(struct net_device_stats, m), \
-	.type = BCMGENET_STAT_NETDEV, \
+	.stat_sizeof = sizeof(((struct rtnl_link_stats64 *)0)->m), \
+	.stat_offset = offsetof(struct rtnl_link_stats64, m), \
+	.type = BCMGENET_STAT_RTNL, \
 }
 
 #define STAT_GENET_MIB(str, m, _type) { \
@@ -1000,6 +1003,14 @@ struct bcmgenet_stats {
 	.type = _type, \
 }
 
+#define STAT_GENET_SOFT_MIB64(str, s, m) { \
+	.stat_string = str, \
+	.stat_sizeof = sizeof(((struct bcmgenet_priv *)0)->s.m), \
+	.stat_offset = offsetof(struct bcmgenet_priv, s.m), \
+	.type = BCMGENET_STAT_SOFT64, \
+	.syncp_offset = offsetof(struct bcmgenet_priv, s.syncp), \
+}
+
 #define STAT_GENET_MIB_RX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_RX)
 #define STAT_GENET_MIB_TX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_TX)
 #define STAT_GENET_RUNT(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_RUNT)
@@ -1014,18 +1025,38 @@ struct bcmgenet_stats {
 }
 
 #define STAT_GENET_Q(num) \
-	STAT_GENET_SOFT_MIB("txq" __stringify(num) "_packets", \
-			tx_rings[num].packets), \
-	STAT_GENET_SOFT_MIB("txq" __stringify(num) "_bytes", \
-			tx_rings[num].bytes), \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_bytes", \
-			rx_rings[num].bytes),	 \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_packets", \
-			rx_rings[num].packets), \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_errors", \
-			rx_rings[num].errors), \
-	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_dropped", \
-			rx_rings[num].dropped)
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_packets", \
+			tx_rings[num].stats64, packets), \
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_bytes", \
+			tx_rings[num].stats64, bytes), \
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_errors", \
+			tx_rings[num].stats64, errors), \
+	STAT_GENET_SOFT_MIB64("txq" __stringify(num) "_dropped", \
+			tx_rings[num].stats64, dropped), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_bytes", \
+			rx_rings[num].stats64, bytes),	 \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_packets", \
+			rx_rings[num].stats64, packets), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_errors", \
+			rx_rings[num].stats64, errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_dropped", \
+			rx_rings[num].stats64, dropped), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_multicast", \
+			rx_rings[num].stats64, multicast), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_missed", \
+			rx_rings[num].stats64, missed), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_length_errors", \
+			rx_rings[num].stats64, length_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_over_errors", \
+			rx_rings[num].stats64, over_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_crc_errors", \
+			rx_rings[num].stats64, crc_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_frame_errors", \
+			rx_rings[num].stats64, frame_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_fragmented_errors", \
+			rx_rings[num].stats64, fragmented_errors), \
+	STAT_GENET_SOFT_MIB64("rxq" __stringify(num) "_broadcast", \
+			rx_rings[num].stats64, broadcast)
 
 /* There is a 0xC gap between the end of RX and beginning of TX stats and then
  * between the end of TX stats and the beginning of the RX RUNT
@@ -1037,15 +1068,20 @@ struct bcmgenet_stats {
  */
 static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
 	/* general stats */
-	STAT_NETDEV(rx_packets),
-	STAT_NETDEV(tx_packets),
-	STAT_NETDEV(rx_bytes),
-	STAT_NETDEV(tx_bytes),
-	STAT_NETDEV(rx_errors),
-	STAT_NETDEV(tx_errors),
-	STAT_NETDEV(rx_dropped),
-	STAT_NETDEV(tx_dropped),
-	STAT_NETDEV(multicast),
+	STAT_RTNL(rx_packets),
+	STAT_RTNL(tx_packets),
+	STAT_RTNL(rx_bytes),
+	STAT_RTNL(tx_bytes),
+	STAT_RTNL(rx_errors),
+	STAT_RTNL(tx_errors),
+	STAT_RTNL(rx_dropped),
+	STAT_RTNL(tx_dropped),
+	STAT_RTNL(multicast),
+	STAT_RTNL(rx_missed_errors),
+	STAT_RTNL(rx_length_errors),
+	STAT_RTNL(rx_over_errors),
+	STAT_RTNL(rx_crc_errors),
+	STAT_RTNL(rx_frame_errors),
 	/* UniMAC RSV counters */
 	STAT_GENET_MIB_RX("rx_64_octets", mib.rx.pkt_cnt.cnt_64),
 	STAT_GENET_MIB_RX("rx_65_127_oct", mib.rx.pkt_cnt.cnt_127),
@@ -1133,6 +1169,20 @@ static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
 
 #define BCMGENET_STATS_LEN	ARRAY_SIZE(bcmgenet_gstrings_stats)
 
+#define BCMGENET_STATS64_ADD(stats, m, v) \
+	do { \
+		u64_stats_update_begin(&stats->syncp); \
+		u64_stats_add(&stats->m, v); \
+		u64_stats_update_end(&stats->syncp); \
+	} while (0)
+
+#define BCMGENET_STATS64_INC(stats, m) \
+	do { \
+		u64_stats_update_begin(&stats->syncp); \
+		u64_stats_inc(&stats->m); \
+		u64_stats_update_end(&stats->syncp); \
+	} while (0)
+
 static void bcmgenet_get_drvinfo(struct net_device *dev,
 				 struct ethtool_drvinfo *info)
 {
@@ -1216,8 +1266,9 @@ static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv)
 
 		s = &bcmgenet_gstrings_stats[i];
 		switch (s->type) {
-		case BCMGENET_STAT_NETDEV:
+		case BCMGENET_STAT_RTNL:
 		case BCMGENET_STAT_SOFT:
+		case BCMGENET_STAT_SOFT64:
 			continue;
 		case BCMGENET_STAT_RUNT:
 			offset += BCMGENET_STAT_OFFSET;
@@ -1255,28 +1306,40 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev,
 				       u64 *data)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct rtnl_link_stats64 stats64;
+	struct u64_stats_sync *syncp;
+	unsigned int start;
 	int i;
 
 	if (netif_running(dev))
 		bcmgenet_update_mib_counters(priv);
 
-	dev->netdev_ops->ndo_get_stats(dev);
+	dev_get_stats(dev, &stats64);
 
 	for (i = 0; i < BCMGENET_STATS_LEN; i++) {
 		const struct bcmgenet_stats *s;
 		char *p;
 
 		s = &bcmgenet_gstrings_stats[i];
-		if (s->type == BCMGENET_STAT_NETDEV)
-			p = (char *)&dev->stats;
-		else
-			p = (char *)priv;
-		p += s->stat_offset;
-		if (sizeof(unsigned long) != sizeof(u32) &&
-		    s->stat_sizeof == sizeof(unsigned long))
-			data[i] = *(unsigned long *)p;
-		else
-			data[i] = *(u32 *)p;
+		p = (char *)priv;
+
+		if (s->type == BCMGENET_STAT_SOFT64) {
+			syncp = (struct u64_stats_sync *)(p + s->syncp_offset);
+			do {
+				start = u64_stats_fetch_begin(syncp);
+				data[i] = u64_stats_read((u64_stats_t *)(p + s->stat_offset));
+			} while (u64_stats_fetch_retry(syncp, start));
+		} else {
+			if (s->type == BCMGENET_STAT_RTNL)
+				p = (char *)&stats64;
+
+			p += s->stat_offset;
+			if (sizeof(unsigned long) != sizeof(u32) &&
+				s->stat_sizeof == sizeof(unsigned long))
+				data[i] = *(unsigned long *)p;
+			else
+				data[i] = *(u32 *)p;
+		}
 	}
 }
 
@@ -1856,6 +1919,7 @@ static struct sk_buff *bcmgenet_free_rx_cb(struct device *dev,
 static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 					  struct bcmgenet_tx_ring *ring)
 {
+	struct bcmgenet_tx_stats64 *stats = &ring->stats64;
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	unsigned int txbds_processed = 0;
 	unsigned int bytes_compl = 0;
@@ -1896,8 +1960,10 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	ring->free_bds += txbds_processed;
 	ring->c_index = c_index;
 
-	ring->packets += pkts_compl;
-	ring->bytes += bytes_compl;
+	u64_stats_update_begin(&stats->syncp);
+	u64_stats_add(&stats->packets, pkts_compl);
+	u64_stats_add(&stats->bytes, bytes_compl);
+	u64_stats_update_end(&stats->syncp);
 
 	netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->index),
 				  pkts_compl, bytes_compl);
@@ -1983,8 +2049,10 @@ static void bcmgenet_tx_reclaim_all(struct net_device *dev)
  * the transmit checksum offsets in the descriptors
  */
 static struct sk_buff *bcmgenet_add_tsb(struct net_device *dev,
-					struct sk_buff *skb)
+					struct sk_buff *skb,
+					struct bcmgenet_tx_ring *ring)
 {
+	struct bcmgenet_tx_stats64 *stats = &ring->stats64;
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct status_64 *status = NULL;
 	struct sk_buff *new_skb;
@@ -2001,7 +2069,7 @@ static struct sk_buff *bcmgenet_add_tsb(struct net_device *dev,
 		if (!new_skb) {
 			dev_kfree_skb_any(skb);
 			priv->mib.tx_realloc_tsb_failed++;
-			dev->stats.tx_dropped++;
+			BCMGENET_STATS64_INC(stats, dropped);
 			return NULL;
 		}
 		dev_consume_skb_any(skb);
@@ -2089,7 +2157,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 	GENET_CB(skb)->bytes_sent = skb->len;
 
 	/* add the Transmit Status Block */
-	skb = bcmgenet_add_tsb(dev, skb);
+	skb = bcmgenet_add_tsb(dev, skb, ring);
 	if (!skb) {
 		ret = NETDEV_TX_OK;
 		goto out;
@@ -2231,6 +2299,7 @@ static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv,
 static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 				     unsigned int budget)
 {
+	struct bcmgenet_rx_stats64 *stats = &ring->stats64;
 	struct bcmgenet_priv *priv = ring->priv;
 	struct net_device *dev = priv->dev;
 	struct enet_cb *cb;
@@ -2253,7 +2322,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		   DMA_P_INDEX_DISCARD_CNT_MASK;
 	if (discards > ring->old_discards) {
 		discards = discards - ring->old_discards;
-		ring->errors += discards;
+		BCMGENET_STATS64_ADD(stats, missed, discards);
 		ring->old_discards += discards;
 
 		/* Clear HW register when we reach 75% of maximum 0xFFFF */
@@ -2279,7 +2348,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		skb = bcmgenet_rx_refill(priv, cb);
 
 		if (unlikely(!skb)) {
-			ring->dropped++;
+			BCMGENET_STATS64_INC(stats, dropped);
 			goto next;
 		}
 
@@ -2306,8 +2375,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 
 		if (unlikely(len > RX_BUF_LENGTH)) {
 			netif_err(priv, rx_status, dev, "oversized packet\n");
-			dev->stats.rx_length_errors++;
-			dev->stats.rx_errors++;
+			BCMGENET_STATS64_INC(stats, length_errors);
 			dev_kfree_skb_any(skb);
 			goto next;
 		}
@@ -2315,7 +2383,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) {
 			netif_err(priv, rx_status, dev,
 				  "dropping fragmented packet!\n");
-			ring->errors++;
+			BCMGENET_STATS64_INC(stats, fragmented_errors);
 			dev_kfree_skb_any(skb);
 			goto next;
 		}
@@ -2328,15 +2396,22 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 						DMA_RX_RXER))) {
 			netif_err(priv, rx_status, dev, "dma_flag=0x%x\n",
 				  (unsigned int)dma_flag);
+			u64_stats_update_begin(&stats->syncp);
 			if (dma_flag & DMA_RX_CRC_ERROR)
-				dev->stats.rx_crc_errors++;
+				u64_stats_inc(&stats->crc_errors);
 			if (dma_flag & DMA_RX_OV)
-				dev->stats.rx_over_errors++;
+				u64_stats_inc(&stats->over_errors);
 			if (dma_flag & DMA_RX_NO)
-				dev->stats.rx_frame_errors++;
+				u64_stats_inc(&stats->frame_errors);
 			if (dma_flag & DMA_RX_LG)
-				dev->stats.rx_length_errors++;
-			dev->stats.rx_errors++;
+				u64_stats_inc(&stats->length_errors);
+			if ((dma_flag & (DMA_RX_CRC_ERROR |
+						DMA_RX_OV |
+						DMA_RX_NO |
+						DMA_RX_LG |
+						DMA_RX_RXER)) == DMA_RX_RXER)
+				u64_stats_inc(&stats->errors);
+			u64_stats_update_end(&stats->syncp);
 			dev_kfree_skb_any(skb);
 			goto next;
 		} /* error packet */
@@ -2356,10 +2431,15 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 
 		/*Finish setting up the received SKB and send it to the kernel*/
 		skb->protocol = eth_type_trans(skb, priv->dev);
-		ring->packets++;
-		ring->bytes += len;
+
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->packets);
+		u64_stats_add(&stats->bytes, len);
 		if (dma_flag & DMA_RX_MULT)
-			dev->stats.multicast++;
+			u64_stats_inc(&stats->multicast);
+		else if (dma_flag & DMA_RX_BRDCAST)
+			u64_stats_inc(&stats->broadcast);
+		u64_stats_update_end(&stats->syncp);
 
 		/* Notify kernel */
 		napi_gro_receive(&ring->napi, skb);
@@ -3420,7 +3500,7 @@ static void bcmgenet_timeout(struct net_device *dev, unsigned int txqueue)
 
 	netif_trans_update(dev);
 
-	dev->stats.tx_errors++;
+	BCMGENET_STATS64_INC((&priv->tx_rings[txqueue].stats64), errors);
 
 	netif_tx_wake_all_queues(dev);
 }
@@ -3509,39 +3589,72 @@ static int bcmgenet_set_mac_addr(struct net_device *dev, void *p)
 	return 0;
 }
 
-static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
+static void bcmgenet_get_stats64(struct net_device *dev,
+				 struct rtnl_link_stats64 *stats)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	unsigned long tx_bytes = 0, tx_packets = 0;
-	unsigned long rx_bytes = 0, rx_packets = 0;
-	unsigned long rx_errors = 0, rx_dropped = 0;
-	struct bcmgenet_tx_ring *tx_ring;
-	struct bcmgenet_rx_ring *rx_ring;
+	struct bcmgenet_tx_stats64 *tx_stats;
+	struct bcmgenet_rx_stats64 *rx_stats;
+	u64 rx_length_errors, rx_over_errors;
+	u64 rx_missed, rx_fragmented_errors;
+	u64 rx_crc_errors, rx_frame_errors;
+	u64 tx_errors, tx_dropped;
+	u64 rx_errors, rx_dropped;
+	u64 tx_bytes, tx_packets;
+	u64 rx_bytes, rx_packets;
+	unsigned int start;
 	unsigned int q;
+	u64 multicast;
 
 	for (q = 0; q <= priv->hw_params->tx_queues; q++) {
-		tx_ring = &priv->tx_rings[q];
-		tx_bytes += tx_ring->bytes;
-		tx_packets += tx_ring->packets;
+		tx_stats = &priv->tx_rings[q].stats64;
+		do {
+			start = u64_stats_fetch_begin(&tx_stats->syncp);
+			tx_bytes = u64_stats_read(&tx_stats->bytes);
+			tx_packets = u64_stats_read(&tx_stats->packets);
+			tx_errors = u64_stats_read(&tx_stats->errors);
+			tx_dropped = u64_stats_read(&tx_stats->dropped);
+		} while (u64_stats_fetch_retry(&tx_stats->syncp, start));
+
+		stats->tx_bytes += tx_bytes;
+		stats->tx_packets += tx_packets;
+		stats->tx_errors += tx_errors;
+		stats->tx_dropped += tx_dropped;
 	}
 
 	for (q = 0; q <= priv->hw_params->rx_queues; q++) {
-		rx_ring = &priv->rx_rings[q];
-
-		rx_bytes += rx_ring->bytes;
-		rx_packets += rx_ring->packets;
-		rx_errors += rx_ring->errors;
-		rx_dropped += rx_ring->dropped;
+		rx_stats = &priv->rx_rings[q].stats64;
+		do {
+			start = u64_stats_fetch_begin(&rx_stats->syncp);
+			rx_bytes = u64_stats_read(&rx_stats->bytes);
+			rx_packets = u64_stats_read(&rx_stats->packets);
+			rx_errors = u64_stats_read(&rx_stats->errors);
+			rx_dropped = u64_stats_read(&rx_stats->dropped);
+			rx_missed = u64_stats_read(&rx_stats->missed);
+			rx_length_errors = u64_stats_read(&rx_stats->length_errors);
+			rx_over_errors = u64_stats_read(&rx_stats->over_errors);
+			rx_crc_errors = u64_stats_read(&rx_stats->crc_errors);
+			rx_frame_errors = u64_stats_read(&rx_stats->frame_errors);
+			rx_fragmented_errors = u64_stats_read(&rx_stats->fragmented_errors);
+			multicast = u64_stats_read(&rx_stats->multicast);
+		} while (u64_stats_fetch_retry(&rx_stats->syncp, start));
+
+		rx_errors += rx_length_errors;
+		rx_errors += rx_crc_errors;
+		rx_errors += rx_frame_errors;
+		rx_errors += rx_fragmented_errors;
+
+		stats->rx_bytes += rx_bytes;
+		stats->rx_packets += rx_packets;
+		stats->rx_errors += rx_errors;
+		stats->rx_dropped += rx_dropped;
+		stats->rx_missed_errors += rx_missed;
+		stats->rx_length_errors += rx_length_errors;
+		stats->rx_over_errors += rx_over_errors;
+		stats->rx_crc_errors += rx_crc_errors;
+		stats->rx_frame_errors += rx_frame_errors;
+		stats->multicast += multicast;
 	}
-
-	dev->stats.tx_bytes = tx_bytes;
-	dev->stats.tx_packets = tx_packets;
-	dev->stats.rx_bytes = rx_bytes;
-	dev->stats.rx_packets = rx_packets;
-	dev->stats.rx_errors = rx_errors;
-	dev->stats.rx_missed_errors = rx_errors;
-	dev->stats.rx_dropped = rx_dropped;
-	return &dev->stats;
 }
 
 static int bcmgenet_change_carrier(struct net_device *dev, bool new_carrier)
@@ -3569,7 +3682,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_set_mac_address	= bcmgenet_set_mac_addr,
 	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_set_features	= bcmgenet_set_features,
-	.ndo_get_stats		= bcmgenet_get_stats,
+	.ndo_get_stats64	= bcmgenet_get_stats64,
 	.ndo_change_carrier	= bcmgenet_change_carrier,
 };
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 10c631bbe964..5ec3979779ec 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -155,6 +155,30 @@ struct bcmgenet_mib_counters {
 	u32	tx_realloc_tsb_failed;
 };
 
+struct bcmgenet_tx_stats64 {
+	struct u64_stats_sync syncp;
+	u64_stats_t	packets;
+	u64_stats_t	bytes;
+	u64_stats_t	errors;
+	u64_stats_t	dropped;
+};
+
+struct bcmgenet_rx_stats64 {
+	struct u64_stats_sync syncp;
+	u64_stats_t	bytes;
+	u64_stats_t	packets;
+	u64_stats_t	errors;
+	u64_stats_t	dropped;
+	u64_stats_t	multicast;
+	u64_stats_t	broadcast;
+	u64_stats_t	missed;
+	u64_stats_t	length_errors;
+	u64_stats_t	over_errors;
+	u64_stats_t	crc_errors;
+	u64_stats_t	frame_errors;
+	u64_stats_t	fragmented_errors;
+};
+
 #define UMAC_MIB_START			0x400
 
 #define UMAC_MDIO_CMD			0x614
@@ -515,8 +539,7 @@ struct bcmgenet_skb_cb {
 struct bcmgenet_tx_ring {
 	spinlock_t	lock;		/* ring lock */
 	struct napi_struct napi;	/* NAPI per tx queue */
-	unsigned long	packets;
-	unsigned long	bytes;
+	struct bcmgenet_tx_stats64 stats64;
 	unsigned int	index;		/* ring index */
 	struct enet_cb	*cbs;		/* tx ring buffer control block*/
 	unsigned int	size;		/* size of each tx ring */
@@ -540,10 +563,7 @@ struct bcmgenet_net_dim {
 
 struct bcmgenet_rx_ring {
 	struct napi_struct napi;	/* Rx NAPI struct */
-	unsigned long	bytes;
-	unsigned long	packets;
-	unsigned long	errors;
-	unsigned long	dropped;
+	struct bcmgenet_rx_stats64 stats64;
 	unsigned int	index;		/* Rx ring index */
 	struct enet_cb	*cbs;		/* Rx ring buffer control block */
 	unsigned int	size;		/* Rx ring size */
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 71c619d2bea5..b6437ba7a2eb 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -625,7 +625,7 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 			.asym_pause = 0,
 		};
 
-		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
+		phydev = fixed_phy_register(&fphy_status, NULL);
 		if (IS_ERR(phydev)) {
 			dev_err(kdev, "failed to register fixed PHY device\n");
 			return PTR_ERR(phydev);
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index d1f541af4e3b..ff47e96b9124 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -54,7 +54,7 @@
 #include <linux/ssb/ssb_driver_gige.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
-#include <linux/crc32poly.h>
+#include <linux/crc32.h>
 #include <linux/dmi.h>
 
 #include <net/checksum.h>
@@ -9809,26 +9809,7 @@ static void tg3_setup_rxbd_thresholds(struct tg3 *tp)
 
 static inline u32 calc_crc(unsigned char *buf, int len)
 {
-	u32 reg;
-	u32 tmp;
-	int j, k;
-
-	reg = 0xffffffff;
-
-	for (j = 0; j < len; j++) {
-		reg ^= buf[j];
-
-		for (k = 0; k < 8; k++) {
-			tmp = reg & 0x01;
-
-			reg >>= 1;
-
-			if (tmp)
-				reg ^= CRC32_POLY_LE;
-		}
-	}
-
-	return ~reg;
+	return ~crc32(~0, buf, len);
 }
 
 static void tg3_set_multi(struct tg3 *tp, unsigned int accept_all)
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index a03eff3d4425..50eb54ecf1ba 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -1735,7 +1735,7 @@ bnad_iocpf_sem_timeout(struct timer_list *t)
  *	Time	CPU m	CPU n
  *	0       1 = test_bit
  *	1			clear_bit
- *	2			del_timer_sync
+ *	2			timer_delete_sync
  *	3	mod_timer
  */
 
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 1fe8ec37491b..e1e8bd2ec155 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -997,22 +997,15 @@ static void macb_update_stats(struct macb *bp)
 
 static int macb_halt_tx(struct macb *bp)
 {
-	unsigned long	halt_time, timeout;
-	u32		status;
+	u32 status;
 
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(THALT));
 
-	timeout = jiffies + usecs_to_jiffies(MACB_HALT_TIMEOUT);
-	do {
-		halt_time = jiffies;
-		status = macb_readl(bp, TSR);
-		if (!(status & MACB_BIT(TGO)))
-			return 0;
-
-		udelay(250);
-	} while (time_before(halt_time, timeout));
-
-	return -ETIMEDOUT;
+	/* Poll TSR until TGO is cleared or timeout. */
+	return read_poll_timeout_atomic(macb_readl, status,
+					!(status & MACB_BIT(TGO)),
+					250, MACB_HALT_TIMEOUT, false,
+					bp, TSR);
 }
 
 static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budget)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 06397cc8bb36..5211759bfe47 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -1389,11 +1389,9 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
 		this_cpu_inc(nic->pnicvf->drv_stats->tx_tso);
 	}
 
-	/* Check if timestamp is requested */
-	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
-		skb_tx_timestamp(skb);
+	/* Check if hw timestamp is requested */
+	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		return;
-	}
 
 	/* Tx timestamping not supported along with TSO, so ignore request */
 	if (skb_shinfo(skb)->gso_size)
@@ -1472,6 +1470,8 @@ static inline void nicvf_sq_doorbell(struct nicvf *nic, struct sk_buff *skb,
 
 	netdev_tx_sent_queue(txq, skb->len);
 
+	skb_tx_timestamp(skb);
+
 	/* make sure all memory stores are done before ringing doorbell */
 	smp_wmb();
 
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 608cc6af5af1..3b7ad744b2dd 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1605,10 +1605,10 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return dev_err_probe(dev, err, "Failed to enable PCI device\n");
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
-		goto err_disable_device;
+		goto err_zero_drv_data;
 	}
 
 	/* MAP configuration registers */
@@ -1616,7 +1616,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!bgx->reg_base) {
 		dev_err(dev, "BGX: Cannot map CSR memory space, aborting\n");
 		err = -ENOMEM;
-		goto err_release_regions;
+		goto err_zero_drv_data;
 	}
 
 	set_max_bgx_per_node(pdev);
@@ -1688,10 +1688,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 err_enable:
 	bgx_vnic[bgx->bgx_id] = NULL;
 	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
-err_release_regions:
-	pci_release_regions(pdev);
-err_disable_device:
-	pci_disable_device(pdev);
+err_zero_drv_data:
 	pci_set_drvdata(pdev, NULL);
 	return err;
 }
@@ -1710,8 +1707,6 @@ static void bgx_remove(struct pci_dev *pdev)
 	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
 
 	bgx_vnic[bgx->bgx_id] = NULL;
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
 	pci_set_drvdata(pdev, NULL);
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index 3b7068832f95..4a0e2d2eb60a 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -351,7 +351,7 @@ static void set_msglevel(struct net_device *dev, u32 val)
 	adapter->msg_enable = val;
 }
 
-static const char stats_strings[][ETH_GSTRING_LEN] = {
+static const char stats_strings[][ETH_GSTRING_LEN] __nonstring_array = {
 	"TxOctetsOK",
 	"TxOctetsBad",
 	"TxUnicastFramesOK",
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 7f3f5afa864f..1546c3db08f0 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -2270,6 +2270,7 @@ int cxgb4_init_ethtool_filters(struct adapter *adap)
 		eth_filter->port[i].bmap = bitmap_zalloc(nentries, GFP_KERNEL);
 		if (!eth_filter->port[i].bmap) {
 			ret = -ENOMEM;
+			kvfree(eth_filter->port[i].loc_array);
 			goto free_eth_finfo;
 		}
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index f991a28a71c3..f2d533acb056 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1533,7 +1533,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else {
 		q = &adap->sge.ethtxq[qidx + pi->first_qset];
 	}
-	skb_tx_timestamp(skb);
 
 	reclaim_completed_tx(adap, &q->q, -1, true);
 	cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
@@ -1706,6 +1705,8 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	cpl->len = htons(skb->len);
 	cpl->ctrl1 = cpu_to_be64(cntrl);
 
+	skb_tx_timestamp(skb);
+
 	if (immediate) {
 		cxgb4_inline_tx_skb(skb, &q->q, sgl);
 		dev_consume_skb_any(skb);
@@ -2268,7 +2269,6 @@ static int ethofld_hard_xmit(struct net_device *dev,
 
 	d = &eosw_txq->desc[eosw_txq->last_pidx];
 	skb = d->skb;
-	skb_tx_timestamp(skb);
 
 	wr = (struct fw_eth_tx_eo_wr *)&eohw_txq->q.desc[eohw_txq->q.pidx];
 	if (unlikely(eosw_txq->state != CXGB4_EO_STATE_ACTIVE &&
@@ -2373,6 +2373,7 @@ write_wr_headers:
 		eohw_txq->vlan_ins++;
 
 	txq_advance(&eohw_txq->q, ndesc);
+	skb_tx_timestamp(skb);
 	cxgb4_ring_tx_db(adap, &eohw_txq->q, ndesc);
 	eosw_txq_advance_index(&eosw_txq->last_pidx, 1, eosw_txq->ndesc);
 
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index e8e460a92e0e..4e2096e49684 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -1640,6 +1640,7 @@ static int chcr_ktls_tunnel_pkt(struct chcr_ktls_info *tx_info,
 	cxgb4_write_sgl(skb, &q->q, pos, end, 0, sgl_sdesc->addr);
 	sgl_sdesc->skb = skb;
 	chcr_txq_advance(&q->q, ndesc);
+	skb_tx_timestamp(skb);
 	cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc);
 	return 0;
 }
@@ -1903,7 +1904,6 @@ static int chcr_ktls_sw_fallback(struct sk_buff *skb,
 	th = tcp_hdr(nskb);
 	skb_offset = skb_tcp_all_headers(nskb);
 	data_len = nskb->len - skb_offset;
-	skb_tx_timestamp(nskb);
 
 	if (chcr_ktls_tunnel_pkt(tx_info, nskb, q))
 		goto out;
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 9c12e967e9f1..301b3f3114af 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -26,6 +26,7 @@
 
 #define ENIC_WQ_MAX		256
 #define ENIC_RQ_MAX		256
+#define ENIC_RQ_MIN_DEFAULT	8
 
 #define ENIC_WQ_NAPI_BUDGET	256
 
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index c753c35b26eb..6ef8a0d90bce 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2296,7 +2296,8 @@ static int enic_adjust_resources(struct enic *enic)
 		 * used based on which resource is the most constrained
 		 */
 		wq_avail = min(enic->wq_avail, ENIC_WQ_MAX);
-		rq_default = netif_get_num_default_rss_queues();
+		rq_default = max(netif_get_num_default_rss_queues(),
+				 ENIC_RQ_MIN_DEFAULT);
 		rq_avail = min3(enic->rq_avail, ENIC_RQ_MAX, rq_default);
 		max_queues = min(enic->cq_avail,
 				 enic->intr_avail - ENIC_MSIX_RESERVED_INTR);
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index c8c53121557f..bec76e7bf5dd 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -1411,7 +1411,7 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* grab all resources from both PIO and MMIO regions, as we
 	 * don't want anyone else messing around with our hardware */
-	if (pci_request_regions(pdev, DRV_NAME))
+	if (pcim_request_all_regions(pdev, DRV_NAME))
 		return -ENODEV;
 
 	ioaddr = pcim_iomap(pdev, TULIP_BAR, tulip_tbl[chip_idx].io_size);
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index 5930cdec6f2f..e593273b2867 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -375,7 +375,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENOMEM;
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
-	if (pci_request_regions(pdev, DRV_NAME))
+	if (pcim_request_all_regions(pdev, DRV_NAME))
 		goto err_out_netdev;
 
 	ioaddr = pci_iomap(pdev, TULIP_BAR, netdev_res_size);
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index d88fbecdab4b..038a0400c1f9 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -146,6 +146,8 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent)
 	np->ioaddr = ioaddr;
 	np->chip_id = chip_idx;
 	np->pdev = pdev;
+
+	spin_lock_init(&np->stats_lock);
 	spin_lock_init (&np->tx_lock);
 	spin_lock_init (&np->rx_lock);
 
@@ -352,7 +354,7 @@ parse_eeprom (struct net_device *dev)
 	eth_hw_addr_set(dev, psrom->mac_addr);
 
 	if (np->chip_id == CHIP_IP1000A) {
-		np->led_mode = psrom->led_mode;
+		np->led_mode = le16_to_cpu(psrom->led_mode);
 		return 0;
 	}
 
@@ -865,7 +867,6 @@ tx_error (struct net_device *dev, int tx_status)
 	frame_id = (tx_status & 0xffff0000);
 	printk (KERN_ERR "%s: Transmit error, TxStatus %4.4x, FrameId %d.\n",
 		dev->name, tx_status, frame_id);
-	dev->stats.tx_errors++;
 	/* Ttransmit Underrun */
 	if (tx_status & 0x10) {
 		dev->stats.tx_fifo_errors++;
@@ -902,9 +903,15 @@ tx_error (struct net_device *dev, int tx_status)
 		rio_set_led_mode(dev);
 		/* Let TxStartThresh stay default value */
 	}
+
+	spin_lock(&np->stats_lock);
 	/* Maximum Collisions */
 	if (tx_status & 0x08)
 		dev->stats.collisions++;
+
+	dev->stats.tx_errors++;
+	spin_unlock(&np->stats_lock);
+
 	/* Restart the Tx */
 	dw32(MACCtrl, dr16(MACCtrl) | TxEnable);
 }
@@ -1073,7 +1080,9 @@ get_stats (struct net_device *dev)
 	int i;
 #endif
 	unsigned int stat_reg;
+	unsigned long flags;
 
+	spin_lock_irqsave(&np->stats_lock, flags);
 	/* All statistics registers need to be acknowledged,
 	   else statistic overflow could cause problems */
 
@@ -1123,6 +1132,9 @@ get_stats (struct net_device *dev)
 	dr16(TCPCheckSumErrors);
 	dr16(UDPCheckSumErrors);
 	dr16(IPCheckSumErrors);
+
+	spin_unlock_irqrestore(&np->stats_lock, flags);
+
 	return &dev->stats;
 }
 
diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h
index 195dc6cfd895..ba679025e866 100644
--- a/drivers/net/ethernet/dlink/dl2k.h
+++ b/drivers/net/ethernet/dlink/dl2k.h
@@ -329,18 +329,18 @@ enum _pcs_anlpar {
 };
 
 typedef struct t_SROM {
-	u16 config_param;	/* 0x00 */
-	u16 asic_ctrl;		/* 0x02 */
-	u16 sub_vendor_id;	/* 0x04 */
-	u16 sub_system_id;	/* 0x06 */
-	u16 pci_base_1;		/* 0x08 (IP1000A only) */
-	u16 pci_base_2;		/* 0x0a (IP1000A only) */
-	u16 led_mode;		/* 0x0c (IP1000A only) */
-	u16 reserved1[9];	/* 0x0e-0x1f */
+	__le16 config_param;	/* 0x00 */
+	__le16 asic_ctrl;	/* 0x02 */
+	__le16 sub_vendor_id;	/* 0x04 */
+	__le16 sub_system_id;	/* 0x06 */
+	__le16 pci_base_1;	/* 0x08 (IP1000A only) */
+	__le16 pci_base_2;	/* 0x0a (IP1000A only) */
+	__le16 led_mode;	/* 0x0c (IP1000A only) */
+	__le16 reserved1[9];	/* 0x0e-0x1f */
 	u8 mac_addr[6];		/* 0x20-0x25 */
 	u8 reserved2[10];	/* 0x26-0x2f */
 	u8 sib[204];		/* 0x30-0xfb */
-	u32 crc;		/* 0xfc-0xff */
+	__le32 crc;		/* 0xfc-0xff */
 } SROM_t, *PSROM_t;
 
 /* Ioctl custom data */
@@ -372,6 +372,8 @@ struct netdev_private {
 	struct pci_dev *pdev;
 	void __iomem *ioaddr;
 	void __iomem *eeprom_addr;
+	// To ensure synchronization when stats are updated.
+	spinlock_t stats_lock;
 	spinlock_t tx_lock;
 	spinlock_t rx_lock;
 	unsigned int rx_buf_sz;		/* Based on MTU+slack. */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 51b8377edd1d..d730af4a50c7 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1609,7 +1609,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	/* version 1 of the cmd is not supported only by BE2 */
 	if (BE2_chip(adapter))
 		hdr->version = 0;
-	if (BE3_chip(adapter) || lancer_chip(adapter))
+	else if (BE3_chip(adapter) || lancer_chip(adapter))
 		hdr->version = 1;
 	else
 		hdr->version = 2;
@@ -2615,7 +2615,11 @@ err:
 	return status;
 }
 
-static char flash_cookie[2][16] = {"*** SE FLAS", "H DIRECTORY *** "};
+/*
+ * Since the cookie is text, add a parsing-skipped space to keep it from
+ * ever being matched on storage holding this source file.
+ */
+static const char flash_cookie[32] __nonstring = "*** SE FLAS" "H DIRECTORY *** ";
 
 static bool phy_flashing_required(struct be_adapter *adapter)
 {
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index d70818f06be7..5e2d3ddb5d43 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1415,7 +1415,7 @@ struct flash_section_entry {
 } __packed;
 
 struct flash_section_info {
-	u8 cookie[32];
+	u8 cookie[32] __nonstring;
 	struct flash_section_hdr fsec_hdr;
 	struct flash_section_entry fsec_entry[32];
 } __packed;
diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 625245b0845c..eba73246f986 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -67,6 +67,8 @@
 #define TSNEP_TX_TYPE_XDP_NDO_MAP_PAGE	(TSNEP_TX_TYPE_XDP_NDO | TSNEP_TX_TYPE_MAP_PAGE)
 #define TSNEP_TX_TYPE_XDP		(TSNEP_TX_TYPE_XDP_TX | TSNEP_TX_TYPE_XDP_NDO)
 #define TSNEP_TX_TYPE_XSK		BIT(12)
+#define TSNEP_TX_TYPE_TSTAMP		BIT(13)
+#define TSNEP_TX_TYPE_SKB_TSTAMP	(TSNEP_TX_TYPE_SKB | TSNEP_TX_TYPE_TSTAMP)
 
 #define TSNEP_XDP_TX		BIT(0)
 #define TSNEP_XDP_REDIRECT	BIT(1)
@@ -386,8 +388,7 @@ static void tsnep_tx_activate(struct tsnep_tx *tx, int index, int length,
 	if (entry->skb) {
 		entry->properties = length & TSNEP_DESC_LENGTH_MASK;
 		entry->properties |= TSNEP_DESC_INTERRUPT_FLAG;
-		if ((entry->type & TSNEP_TX_TYPE_SKB) &&
-		    (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS))
+		if ((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP)
 			entry->properties |= TSNEP_DESC_EXTENDED_WRITEBACK_FLAG;
 
 		/* toggle user flag to prevent false acknowledge
@@ -479,7 +480,8 @@ static int tsnep_tx_map_frag(skb_frag_t *frag, struct tsnep_tx_entry *entry,
 	return mapped;
 }
 
-static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count)
+static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count,
+			bool do_tstamp)
 {
 	struct device *dmadev = tx->adapter->dmadev;
 	struct tsnep_tx_entry *entry;
@@ -505,6 +507,9 @@ static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count)
 				entry->type = TSNEP_TX_TYPE_SKB_INLINE;
 				mapped = 0;
 			}
+
+			if (do_tstamp)
+				entry->type |= TSNEP_TX_TYPE_TSTAMP;
 		} else {
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
 
@@ -558,11 +563,12 @@ static int tsnep_tx_unmap(struct tsnep_tx *tx, int index, int count)
 static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 					 struct tsnep_tx *tx)
 {
-	int count = 1;
 	struct tsnep_tx_entry *entry;
+	bool do_tstamp = false;
+	int count = 1;
 	int length;
-	int i;
 	int retval;
+	int i;
 
 	if (skb_shinfo(skb)->nr_frags > 0)
 		count += skb_shinfo(skb)->nr_frags;
@@ -579,7 +585,13 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 	entry = &tx->entry[tx->write];
 	entry->skb = skb;
 
-	retval = tsnep_tx_map(skb, tx, count);
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    tx->adapter->hwtstamp_config.tx_type == HWTSTAMP_TX_ON) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		do_tstamp = true;
+	}
+
+	retval = tsnep_tx_map(skb, tx, count, do_tstamp);
 	if (retval < 0) {
 		tsnep_tx_unmap(tx, tx->write, count);
 		dev_kfree_skb_any(entry->skb);
@@ -591,9 +603,6 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 	}
 	length = retval;
 
-	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)
-		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-
 	for (i = 0; i < count; i++)
 		tsnep_tx_activate(tx, (tx->write + i) & TSNEP_RING_MASK, length,
 				  i == count - 1);
@@ -844,8 +853,7 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget)
 
 		length = tsnep_tx_unmap(tx, tx->read, count);
 
-		if ((entry->type & TSNEP_TX_TYPE_SKB) &&
-		    (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS) &&
+		if (((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP) &&
 		    (__le32_to_cpu(entry->desc_wb->properties) &
 		     TSNEP_DESC_EXTENDED_WRITEBACK_FLAG)) {
 			struct skb_shared_hwtstamps hwtstamps;
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 17ec35e75a65..a98d5af3f9e3 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1906,7 +1906,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
 			goto err_phy_connect;
 		}
 
-		phydev = fixed_phy_register(PHY_POLL, &ncsi_phy_status, np);
+		phydev = fixed_phy_register(&ncsi_phy_status, np);
 		if (IS_ERR(phydev)) {
 			dev_err(&pdev->dev, "failed to register fixed PHY device\n");
 			err = PTR_ERR(phydev);
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index a2d7300925a8..bbef47c3480c 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -71,7 +71,6 @@ config FSL_XGMAC_MDIO
 	tristate "Freescale XGMAC MDIO"
 	select PHYLIB
 	depends on OF
-	select MDIO_DEVRES
 	select OF_MDIO
 	help
 	  This driver supports the MDIO bus on the Fman 10G Ethernet MACs, and
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 4948b4906584..23c23cca2620 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -3089,15 +3089,25 @@ static int dpaa_xdp_xmit(struct net_device *net_dev, int n,
 	return nxmit;
 }
 
-static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+static int dpaa_hwtstamp_get(struct net_device *dev,
+			     struct kernel_hwtstamp_config *config)
 {
 	struct dpaa_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config config;
 
-	if (copy_from_user(&config, rq->ifr_data, sizeof(config)))
-		return -EFAULT;
+	config->tx_type = priv->tx_tstamp ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	config->rx_filter = priv->rx_tstamp ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
 
-	switch (config.tx_type) {
+	return 0;
+}
+
+static int dpaa_hwtstamp_set(struct net_device *dev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
+{
+	struct dpaa_priv *priv = netdev_priv(dev);
+
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		/* Couldn't disable rx/tx timestamping separately.
 		 * Do nothing here.
@@ -3112,7 +3122,7 @@ static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		return -ERANGE;
 	}
 
-	if (config.rx_filter == HWTSTAMP_FILTER_NONE) {
+	if (config->rx_filter == HWTSTAMP_FILTER_NONE) {
 		/* Couldn't disable rx/tx timestamping separately.
 		 * Do nothing here.
 		 */
@@ -3121,28 +3131,17 @@ static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		priv->mac_dev->set_tstamp(priv->mac_dev->fman_mac, true);
 		priv->rx_tstamp = true;
 		/* TS is set for all frame types, not only those requested */
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 	}
 
-	return copy_to_user(rq->ifr_data, &config, sizeof(config)) ?
-			-EFAULT : 0;
+	return 0;
 }
 
 static int dpaa_ioctl(struct net_device *net_dev, struct ifreq *rq, int cmd)
 {
-	int ret = -EINVAL;
 	struct dpaa_priv *priv = netdev_priv(net_dev);
 
-	if (cmd == SIOCGMIIREG) {
-		if (net_dev->phydev)
-			return phylink_mii_ioctl(priv->mac_dev->phylink, rq,
-						 cmd);
-	}
-
-	if (cmd == SIOCSHWTSTAMP)
-		return dpaa_ts_ioctl(net_dev, rq, cmd);
-
-	return ret;
+	return phylink_mii_ioctl(priv->mac_dev->phylink, rq, cmd);
 }
 
 static const struct net_device_ops dpaa_ops = {
@@ -3160,6 +3159,8 @@ static const struct net_device_ops dpaa_ops = {
 	.ndo_change_mtu = dpaa_change_mtu,
 	.ndo_bpf = dpaa_xdp,
 	.ndo_xdp_xmit = dpaa_xdp_xmit,
+	.ndo_hwtstamp_get = dpaa_hwtstamp_get,
+	.ndo_hwtstamp_set = dpaa_hwtstamp_set,
 };
 
 static int dpaa_napi_add(struct net_device *net_dev)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 29886a8ba73f..2ec2c3dab250 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2585,40 +2585,52 @@ static int dpaa2_eth_set_features(struct net_device *net_dev,
 	return 0;
 }
 
-static int dpaa2_eth_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+static int dpaa2_eth_hwtstamp_set(struct net_device *dev,
+				  struct kernel_hwtstamp_config *config,
+				  struct netlink_ext_ack *extack)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config config;
 
 	if (!dpaa2_ptp)
 		return -EINVAL;
 
-	if (copy_from_user(&config, rq->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 	case HWTSTAMP_TX_ON:
 	case HWTSTAMP_TX_ONESTEP_SYNC:
-		priv->tx_tstamp_type = config.tx_type;
+		priv->tx_tstamp_type = config->tx_type;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	if (config.rx_filter == HWTSTAMP_FILTER_NONE) {
+	if (config->rx_filter == HWTSTAMP_FILTER_NONE) {
 		priv->rx_tstamp = false;
 	} else {
 		priv->rx_tstamp = true;
 		/* TS is set for all frame types, not only those requested */
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 	}
 
 	if (priv->tx_tstamp_type == HWTSTAMP_TX_ONESTEP_SYNC)
 		dpaa2_ptp_onestep_reg_update_method(priv);
 
-	return copy_to_user(rq->ifr_data, &config, sizeof(config)) ?
-			-EFAULT : 0;
+	return 0;
+}
+
+static int dpaa2_eth_hwtstamp_get(struct net_device *dev,
+				  struct kernel_hwtstamp_config *config)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+
+	if (!dpaa2_ptp)
+		return -EINVAL;
+
+	config->tx_type = priv->tx_tstamp_type;
+	config->rx_filter = priv->rx_tstamp ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
+
+	return 0;
 }
 
 static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
@@ -2626,9 +2638,6 @@ static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	struct dpaa2_eth_priv *priv = netdev_priv(dev);
 	int err;
 
-	if (cmd == SIOCSHWTSTAMP)
-		return dpaa2_eth_ts_ioctl(dev, rq, cmd);
-
 	mutex_lock(&priv->mac_lock);
 
 	if (dpaa2_eth_is_type_phy(priv)) {
@@ -3034,7 +3043,9 @@ static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_xsk_wakeup = dpaa2_xsk_wakeup,
 	.ndo_setup_tc = dpaa2_eth_setup_tc,
 	.ndo_vlan_rx_add_vid = dpaa2_eth_rx_add_vid,
-	.ndo_vlan_rx_kill_vid = dpaa2_eth_rx_kill_vid
+	.ndo_vlan_rx_kill_vid = dpaa2_eth_rx_kill_vid,
+	.ndo_hwtstamp_get = dpaa2_eth_hwtstamp_get,
+	.ndo_hwtstamp_set = dpaa2_eth_hwtstamp_set,
 };
 
 static void dpaa2_eth_cdan_cb(struct dpaa2_io_notification_ctx *ctx)
diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig
index 6c2779047dcd..e917132d3714 100644
--- a/drivers/net/ethernet/freescale/enetc/Kconfig
+++ b/drivers/net/ethernet/freescale/enetc/Kconfig
@@ -15,10 +15,16 @@ config NXP_ENETC_PF_COMMON
 
 	  If compiled as module (M), the module name is nxp-enetc-pf-common.
 
+config NXP_NETC_LIB
+	tristate
+	help
+	  This module provides common functionalities for both ENETC and NETC
+	  Switch, such as NETC Table Management Protocol (NTMP) 2.0, common tc
+	  flower and debugfs interfaces and so on.
+
 config FSL_ENETC
 	tristate "ENETC PF driver"
 	depends on PCI_MSI
-	select MDIO_DEVRES
 	select FSL_ENETC_CORE
 	select FSL_ENETC_IERB
 	select FSL_ENETC_MDIO
@@ -36,10 +42,10 @@ config FSL_ENETC
 config NXP_ENETC4
 	tristate "ENETC4 PF driver"
 	depends on PCI_MSI
-	select MDIO_DEVRES
 	select FSL_ENETC_CORE
 	select FSL_ENETC_MDIO
 	select NXP_ENETC_PF_COMMON
+	select NXP_NETC_LIB
 	select PHYLINK
 	select DIMLIB
 	help
@@ -73,7 +79,7 @@ config FSL_ENETC_IERB
 
 config FSL_ENETC_MDIO
 	tristate "ENETC MDIO driver"
-	depends on PCI && MDIO_DEVRES && MDIO_BUS
+	depends on PCI && PHYLIB
 	help
 	  This driver supports NXP ENETC Central MDIO controller as a PCIe
 	  physical function (PF) device.
diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile
index 6fd27ee4fcd1..f1c5ad45fd76 100644
--- a/drivers/net/ethernet/freescale/enetc/Makefile
+++ b/drivers/net/ethernet/freescale/enetc/Makefile
@@ -6,6 +6,9 @@ fsl-enetc-core-y := enetc.o enetc_cbdr.o enetc_ethtool.o
 obj-$(CONFIG_NXP_ENETC_PF_COMMON) += nxp-enetc-pf-common.o
 nxp-enetc-pf-common-y := enetc_pf_common.o
 
+obj-$(CONFIG_NXP_NETC_LIB) += nxp-netc-lib.o
+nxp-netc-lib-y := ntmp.o
+
 obj-$(CONFIG_FSL_ENETC) += fsl-enetc.o
 fsl-enetc-y := enetc_pf.o
 fsl-enetc-$(CONFIG_PCI_IOV) += enetc_msg.o
@@ -13,6 +16,7 @@ fsl-enetc-$(CONFIG_FSL_ENETC_QOS) += enetc_qos.o
 
 obj-$(CONFIG_NXP_ENETC4) += nxp-enetc4.o
 nxp-enetc4-y := enetc4_pf.o
+nxp-enetc4-$(CONFIG_DEBUG_FS) += enetc4_debugfs.o
 
 obj-$(CONFIG_FSL_ENETC_VF) += fsl-enetc-vf.o
 fsl-enetc-vf-y := enetc_vf.o
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 2106861463e4..dcc3fbac3481 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -36,6 +36,42 @@ static void enetc_change_preemptible_tcs(struct enetc_ndev_priv *priv,
 	enetc_mm_commit_preemptible_tcs(priv);
 }
 
+static int enetc_mac_addr_hash_idx(const u8 *addr)
+{
+	u64 fold = __swab64(ether_addr_to_u64(addr)) >> 16;
+	u64 mask = 0;
+	int res = 0;
+	int i;
+
+	for (i = 0; i < 8; i++)
+		mask |= BIT_ULL(i * 6);
+
+	for (i = 0; i < 6; i++)
+		res |= (hweight64(fold & (mask << i)) & 0x1) << i;
+
+	return res;
+}
+
+void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
+				  const unsigned char *addr)
+{
+	int idx = enetc_mac_addr_hash_idx(addr);
+
+	/* add hash table entry */
+	__set_bit(idx, filter->mac_hash_table);
+	filter->mac_addr_cnt++;
+}
+EXPORT_SYMBOL_GPL(enetc_add_mac_addr_ht_filter);
+
+void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter)
+{
+	filter->mac_addr_cnt = 0;
+
+	bitmap_zero(filter->mac_hash_table,
+		    ENETC_MADDR_HASH_TBL_SZ);
+}
+EXPORT_SYMBOL_GPL(enetc_reset_mac_addr_filter);
+
 static int enetc_num_stack_tx_queues(struct enetc_ndev_priv *priv)
 {
 	int num_tx_rings = priv->num_tx_rings;
@@ -1850,6 +1886,16 @@ static void enetc_xdp_drop(struct enetc_bdr *rx_ring, int rx_ring_first,
 	}
 }
 
+static void enetc_bulk_flip_buff(struct enetc_bdr *rx_ring, int rx_ring_first,
+				 int rx_ring_last)
+{
+	while (rx_ring_first != rx_ring_last) {
+		enetc_flip_rx_buff(rx_ring,
+				   &rx_ring->rx_swbd[rx_ring_first]);
+		enetc_bdr_idx_inc(rx_ring, &rx_ring_first);
+	}
+}
+
 static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				   struct napi_struct *napi, int work_limit,
 				   struct bpf_prog *prog)
@@ -1868,11 +1914,10 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 
 	while (likely(rx_frm_cnt < work_limit)) {
 		union enetc_rx_bd *rxbd, *orig_rxbd;
-		int orig_i, orig_cleaned_cnt;
 		struct xdp_buff xdp_buff;
 		struct sk_buff *skb;
+		int orig_i, err;
 		u32 bd_status;
-		int err;
 
 		rxbd = enetc_rxbd(rx_ring, i);
 		bd_status = le32_to_cpu(rxbd->r.lstatus);
@@ -1887,7 +1932,6 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			break;
 
 		orig_rxbd = rxbd;
-		orig_cleaned_cnt = cleaned_cnt;
 		orig_i = i;
 
 		enetc_build_xdp_buff(rx_ring, bd_status, &rxbd, &i,
@@ -1915,15 +1959,21 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			rx_ring->stats.xdp_drops++;
 			break;
 		case XDP_PASS:
-			rxbd = orig_rxbd;
-			cleaned_cnt = orig_cleaned_cnt;
-			i = orig_i;
-
-			skb = enetc_build_skb(rx_ring, bd_status, &rxbd,
-					      &i, &cleaned_cnt,
-					      ENETC_RXB_DMA_SIZE_XDP);
-			if (unlikely(!skb))
+			skb = xdp_build_skb_from_buff(&xdp_buff);
+			/* Probably under memory pressure, stop NAPI */
+			if (unlikely(!skb)) {
+				enetc_xdp_drop(rx_ring, orig_i, i);
+				rx_ring->stats.xdp_drops++;
 				goto out;
+			}
+
+			enetc_get_offloads(rx_ring, orig_rxbd, skb);
+
+			/* These buffers are about to be owned by the stack.
+			 * Update our buffer cache (the rx_swbd array elements)
+			 * with their other page halves.
+			 */
+			enetc_bulk_flip_buff(rx_ring, orig_i, i);
 
 			napi_gro_receive(napi, skb);
 			break;
@@ -1965,11 +2015,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				rx_ring->stats.xdp_redirect_failures++;
 			} else {
-				while (orig_i != i) {
-					enetc_flip_rx_buff(rx_ring,
-							   &rx_ring->rx_swbd[orig_i]);
-					enetc_bdr_idx_inc(rx_ring, &orig_i);
-				}
+				enetc_bulk_flip_buff(rx_ring, orig_i, i);
 				xdp_redirect_frm_cnt++;
 				rx_ring->stats.xdp_redirect++;
 			}
@@ -2369,7 +2415,7 @@ static int enetc_setup_default_rss_table(struct enetc_si *si, int num_groups)
 	for (i = 0; i < si->num_rss; i++)
 		rss_table[i] = i % num_groups;
 
-	enetc_set_rss_table(si, rss_table, si->num_rss);
+	si->ops->set_rss_table(si, rss_table, si->num_rss);
 
 	kfree(rss_table);
 
@@ -2384,6 +2430,20 @@ static void enetc_set_lso_flags_mask(struct enetc_hw *hw)
 	enetc_wr(hw, ENETC4_SILSOSFMR1, 0);
 }
 
+static void enetc_set_rss(struct net_device *ndev, int en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	u32 reg;
+
+	enetc_wr(hw, ENETC_SIRBGCR, priv->num_rx_rings);
+
+	reg = enetc_rd(hw, ENETC_SIMR);
+	reg &= ~ENETC_SIMR_RSSE;
+	reg |= (en) ? ENETC_SIMR_RSSE : 0;
+	enetc_wr(hw, ENETC_SIMR, reg);
+}
+
 int enetc_configure_si(struct enetc_ndev_priv *priv)
 {
 	struct enetc_si *si = priv->si;
@@ -2400,13 +2460,13 @@ int enetc_configure_si(struct enetc_ndev_priv *priv)
 	if (si->hw_features & ENETC_SI_F_LSO)
 		enetc_set_lso_flags_mask(hw);
 
-	/* TODO: RSS support for i.MX95 will be supported later, and the
-	 * is_enetc_rev1() condition will be removed
-	 */
-	if (si->num_rss && is_enetc_rev1(si)) {
+	if (si->num_rss) {
 		err = enetc_setup_default_rss_table(si, priv->num_rx_rings);
 		if (err)
 			return err;
+
+		if (priv->ndev->features & NETIF_F_RXHASH)
+			enetc_set_rss(priv->ndev, true);
 	}
 
 	return 0;
@@ -3199,22 +3259,6 @@ struct net_device_stats *enetc_get_stats(struct net_device *ndev)
 }
 EXPORT_SYMBOL_GPL(enetc_get_stats);
 
-static int enetc_set_rss(struct net_device *ndev, int en)
-{
-	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_hw *hw = &priv->si->hw;
-	u32 reg;
-
-	enetc_wr(hw, ENETC_SIRBGCR, priv->num_rx_rings);
-
-	reg = enetc_rd(hw, ENETC_SIMR);
-	reg &= ~ENETC_SIMR_RSSE;
-	reg |= (en) ? ENETC_SIMR_RSSE : 0;
-	enetc_wr(hw, ENETC_SIMR, reg);
-
-	return 0;
-}
-
 static void enetc_enable_rxvlan(struct net_device *ndev, bool en)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
@@ -3252,16 +3296,17 @@ void enetc_set_features(struct net_device *ndev, netdev_features_t features)
 }
 EXPORT_SYMBOL_GPL(enetc_set_features);
 
-static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
+int enetc_hwtstamp_set(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	int err, new_offloads = priv->active_offloads;
-	struct hwtstamp_config config;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	if (!IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK))
+		return -EOPNOTSUPP;
 
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		new_offloads &= ~ENETC_F_TX_TSTAMP_MASK;
 		break;
@@ -3280,13 +3325,13 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		new_offloads &= ~ENETC_F_RX_TSTAMP;
 		break;
 	default:
 		new_offloads |= ENETC_F_RX_TSTAMP;
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 	}
 
 	if ((new_offloads ^ priv->active_offloads) & ENETC_F_RX_TSTAMP) {
@@ -3299,42 +3344,36 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 
 	priv->active_offloads = new_offloads;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-	       -EFAULT : 0;
+	return 0;
 }
+EXPORT_SYMBOL_GPL(enetc_hwtstamp_set);
 
-static int enetc_hwtstamp_get(struct net_device *ndev, struct ifreq *ifr)
+int enetc_hwtstamp_get(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct hwtstamp_config config;
 
-	config.flags = 0;
+	if (!IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK))
+		return -EOPNOTSUPP;
 
 	if (priv->active_offloads & ENETC_F_TX_ONESTEP_SYNC_TSTAMP)
-		config.tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
+		config->tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
 	else if (priv->active_offloads & ENETC_F_TX_TSTAMP)
-		config.tx_type = HWTSTAMP_TX_ON;
+		config->tx_type = HWTSTAMP_TX_ON;
 	else
-		config.tx_type = HWTSTAMP_TX_OFF;
+		config->tx_type = HWTSTAMP_TX_OFF;
 
-	config.rx_filter = (priv->active_offloads & ENETC_F_RX_TSTAMP) ?
-			    HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+	config->rx_filter = (priv->active_offloads & ENETC_F_RX_TSTAMP) ?
+			     HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-	       -EFAULT : 0;
+	return 0;
 }
+EXPORT_SYMBOL_GPL(enetc_hwtstamp_get);
 
 int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 
-	if (IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK)) {
-		if (cmd == SIOCSHWTSTAMP)
-			return enetc_hwtstamp_set(ndev, rq);
-		if (cmd == SIOCGHWTSTAMP)
-			return enetc_hwtstamp_get(ndev, rq);
-	}
-
 	if (!priv->phylink)
 		return -EOPNOTSUPP;
 
@@ -3362,7 +3401,8 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i,
 	bdr->buffer_offset = ENETC_RXB_PAD;
 	priv->rx_ring[i] = bdr;
 
-	err = xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0);
+	err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0,
+				 ENETC_RXB_DMA_SIZE_XDP);
 	if (err)
 		goto free_vector;
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 4ad4eb5c5a74..872d2cbd088b 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -8,6 +8,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/skbuff.h>
 #include <linux/ethtool.h>
+#include <linux/fsl/ntmp.h>
 #include <linux/if_vlan.h>
 #include <linux/phylink.h>
 #include <linux/dim.h>
@@ -22,6 +23,18 @@
 
 #define ENETC_CBD_DATA_MEM_ALIGN 64
 
+#define ENETC_MADDR_HASH_TBL_SZ	64
+
+enum enetc_mac_addr_type {UC, MC, MADDR_TYPE};
+
+struct enetc_mac_filter {
+	union {
+		char mac_addr[ETH_ALEN];
+		DECLARE_BITMAP(mac_hash_table, ENETC_MADDR_HASH_TBL_SZ);
+	};
+	int mac_addr_cnt;
+};
+
 struct enetc_tx_swbd {
 	union {
 		struct sk_buff *skb;
@@ -266,6 +279,19 @@ struct enetc_platform_info {
 	const struct enetc_drvdata *data;
 };
 
+struct enetc_si;
+
+/*
+ * This structure defines the some common hooks for ENETC PSI and VSI.
+ * In addition, since VSI only uses the struct enetc_si as its private
+ * driver data, so this structure also define some hooks specifically
+ * for VSI. For VSI-specific hooks, the format is ‘vf_*()’.
+ */
+struct enetc_si_ops {
+	int (*get_rss_table)(struct enetc_si *si, u32 *table, int count);
+	int (*set_rss_table)(struct enetc_si *si, const u32 *table, int count);
+};
+
 /* PCI IEP device data */
 struct enetc_si {
 	struct pci_dev *pdev;
@@ -274,7 +300,10 @@ struct enetc_si {
 
 	struct net_device *ndev; /* back ref. */
 
-	struct enetc_cbdr cbd_ring;
+	union {
+		struct enetc_cbdr cbd_ring; /* Only ENETC 1.0 */
+		struct ntmp_user ntmp_user; /* ENETC 4.1 and later */
+	};
 
 	int num_rx_rings; /* how many rings are available in the SI */
 	int num_tx_rings;
@@ -284,6 +313,11 @@ struct enetc_si {
 	u16 revision;
 	int hw_features;
 	const struct enetc_drvdata *drvdata;
+	const struct enetc_si_ops *ops;
+
+	struct workqueue_struct *workqueue;
+	struct work_struct rx_mode_task;
+	struct dentry *debugfs_root;
 };
 
 #define ENETC_SI_ALIGN	32
@@ -466,6 +500,9 @@ int enetc_alloc_si_resources(struct enetc_ndev_priv *priv);
 void enetc_free_si_resources(struct enetc_ndev_priv *priv);
 int enetc_configure_si(struct enetc_ndev_priv *priv);
 int enetc_get_driver_data(struct enetc_si *si);
+void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
+				  const unsigned char *addr);
+void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter);
 
 int enetc_open(struct net_device *ndev);
 int enetc_close(struct net_device *ndev);
@@ -481,6 +518,12 @@ int enetc_setup_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
 int enetc_xdp_xmit(struct net_device *ndev, int num_frames,
 		   struct xdp_frame **frames, u32 flags);
 
+int enetc_hwtstamp_get(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config);
+int enetc_hwtstamp_set(struct net_device *ndev,
+		       struct kernel_hwtstamp_config *config,
+		       struct netlink_ext_ack *extack);
+
 /* ethtool */
 extern const struct ethtool_ops enetc_pf_ethtool_ops;
 extern const struct ethtool_ops enetc4_pf_ethtool_ops;
@@ -493,15 +536,19 @@ void enetc_mm_commit_preemptible_tcs(struct enetc_ndev_priv *priv);
 int enetc_setup_cbdr(struct device *dev, struct enetc_hw *hw, int bd_count,
 		     struct enetc_cbdr *cbdr);
 void enetc_teardown_cbdr(struct enetc_cbdr *cbdr);
+int enetc4_setup_cbdr(struct enetc_si *si);
+void enetc4_teardown_cbdr(struct enetc_si *si);
 int enetc_set_mac_flt_entry(struct enetc_si *si, int index,
 			    char *mac_addr, int si_map);
 int enetc_clear_mac_flt_entry(struct enetc_si *si, int index);
 int enetc_set_fs_entry(struct enetc_si *si, struct enetc_cmd_rfse *rfse,
 		       int index);
-void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes);
+void enetc_set_rss_key(struct enetc_si *si, const u8 *bytes);
 int enetc_get_rss_table(struct enetc_si *si, u32 *table, int count);
 int enetc_set_rss_table(struct enetc_si *si, const u32 *table, int count);
 int enetc_send_cmd(struct enetc_si *si, struct enetc_cbd *cbd);
+int enetc4_get_rss_table(struct enetc_si *si, u32 *table, int count);
+int enetc4_set_rss_table(struct enetc_si *si, const u32 *table, int count);
 
 static inline void *enetc_cbd_alloc_data_mem(struct enetc_si *si,
 					     struct enetc_cbd *cbd,
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
new file mode 100644
index 000000000000..1b1591dce73d
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright 2025 NXP */
+
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/string_choices.h>
+
+#include "enetc_pf.h"
+#include "enetc4_debugfs.h"
+
+static void enetc_show_si_mac_hash_filter(struct seq_file *s, int i)
+{
+	struct enetc_si *si = s->private;
+	struct enetc_hw *hw = &si->hw;
+	u32 hash_h, hash_l;
+
+	hash_l = enetc_port_rd(hw, ENETC4_PSIUMHFR0(i));
+	hash_h = enetc_port_rd(hw, ENETC4_PSIUMHFR1(i));
+	seq_printf(s, "SI %d unicast MAC hash filter: 0x%08x%08x\n",
+		   i, hash_h, hash_l);
+
+	hash_l = enetc_port_rd(hw, ENETC4_PSIMMHFR0(i));
+	hash_h = enetc_port_rd(hw, ENETC4_PSIMMHFR1(i));
+	seq_printf(s, "SI %d multicast MAC hash filter: 0x%08x%08x\n",
+		   i, hash_h, hash_l);
+}
+
+static int enetc_mac_filter_show(struct seq_file *s, void *data)
+{
+	struct enetc_si *si = s->private;
+	struct enetc_hw *hw = &si->hw;
+	struct maft_entry_data maft;
+	struct enetc_pf *pf;
+	int i, err, num_si;
+	u32 val;
+
+	pf = enetc_si_priv(si);
+	num_si = pf->caps.num_vsi + 1;
+
+	val = enetc_port_rd(hw, ENETC4_PSIPMMR);
+	for (i = 0; i < num_si; i++) {
+		seq_printf(s, "SI %d Unicast Promiscuous mode: %s\n", i,
+			   str_enabled_disabled(PSIPMMR_SI_MAC_UP(i) & val));
+		seq_printf(s, "SI %d Multicast Promiscuous mode: %s\n", i,
+			   str_enabled_disabled(PSIPMMR_SI_MAC_MP(i) & val));
+	}
+
+	/* MAC hash filter table */
+	for (i = 0; i < num_si; i++)
+		enetc_show_si_mac_hash_filter(s, i);
+
+	if (!pf->num_mfe)
+		return 0;
+
+	/* MAC address filter table */
+	seq_puts(s, "MAC address filter table\n");
+	for (i = 0; i < pf->num_mfe; i++) {
+		memset(&maft, 0, sizeof(maft));
+		err = ntmp_maft_query_entry(&si->ntmp_user, i, &maft);
+		if (err)
+			return err;
+
+		seq_printf(s, "Entry %d, MAC: %pM, SI bitmap: 0x%04x\n", i,
+			   maft.keye.mac_addr, le16_to_cpu(maft.cfge.si_bitmap));
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(enetc_mac_filter);
+
+void enetc_create_debugfs(struct enetc_si *si)
+{
+	struct net_device *ndev = si->ndev;
+	struct dentry *root;
+
+	root = debugfs_create_dir(netdev_name(ndev), NULL);
+	if (IS_ERR(root))
+		return;
+
+	si->debugfs_root = root;
+
+	debugfs_create_file("mac_filter", 0444, root, si, &enetc_mac_filter_fops);
+}
+
+void enetc_remove_debugfs(struct enetc_si *si)
+{
+	debugfs_remove(si->debugfs_root);
+	si->debugfs_root = NULL;
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.h b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.h
new file mode 100644
index 000000000000..96caca35f79d
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_debugfs.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2025 NXP */
+
+#ifndef __ENETC4_DEBUGFS_H
+#define __ENETC4_DEBUGFS_H
+
+#if IS_ENABLED(CONFIG_DEBUG_FS)
+void enetc_create_debugfs(struct enetc_si *si);
+void enetc_remove_debugfs(struct enetc_si *si);
+#else
+static inline void enetc_create_debugfs(struct enetc_si *si)
+{
+}
+
+static inline void enetc_remove_debugfs(struct enetc_si *si)
+{
+}
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
index 695cb07c74bc..aa25b445d301 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
@@ -99,6 +99,18 @@
 #define ENETC4_PSICFGR2(a)		((a) * 0x80 + 0x2018)
 #define  PSICFGR2_NUM_MSIX		GENMASK(5, 0)
 
+/* Port station interface a unicast MAC hash filter register 0/1 */
+#define ENETC4_PSIUMHFR0(a)		((a) * 0x80 + 0x2050)
+#define ENETC4_PSIUMHFR1(a)		((a) * 0x80 + 0x2054)
+
+/* Port station interface a multicast MAC hash filter register 0/1 */
+#define ENETC4_PSIMMHFR0(a)		((a) * 0x80 + 0x2058)
+#define ENETC4_PSIMMHFR1(a)		((a) * 0x80 + 0x205c)
+
+/* Port station interface a VLAN hash filter register 0/1 */
+#define ENETC4_PSIVHFR0(a)		((a) * 0x80 + 0x2060)
+#define ENETC4_PSIVHFR1(a)		((a) * 0x80 + 0x2064)
+
 #define ENETC4_PMCAPR			0x4004
 #define  PMCAPR_HD			BIT(8)
 #define  PMCAPR_FP			GENMASK(10, 9)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 73ac8c6afb3a..b3dc1afeefd1 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -8,9 +8,19 @@
 #include <linux/unaligned.h>
 
 #include "enetc_pf_common.h"
+#include "enetc4_debugfs.h"
 
 #define ENETC_SI_MAX_RING_NUM	8
 
+#define ENETC_MAC_FILTER_TYPE_UC	BIT(0)
+#define ENETC_MAC_FILTER_TYPE_MC	BIT(1)
+#define ENETC_MAC_FILTER_TYPE_ALL	(ENETC_MAC_FILTER_TYPE_UC | \
+					 ENETC_MAC_FILTER_TYPE_MC)
+
+struct enetc_mac_addr {
+	u8 addr[ETH_ALEN];
+};
+
 static void enetc4_get_port_caps(struct enetc_pf *pf)
 {
 	struct enetc_hw *hw = &pf->si->hw;
@@ -26,6 +36,9 @@ static void enetc4_get_port_caps(struct enetc_pf *pf)
 
 	val = enetc_port_rd(hw, ENETC4_PMCAPR);
 	pf->caps.half_duplex = (val & PMCAPR_HD) ? 1 : 0;
+
+	val = enetc_port_rd(hw, ENETC4_PSIMAFCAPR);
+	pf->caps.mac_filter_num = val & PSIMAFCAPR_NUM_MAC_AFTE;
 }
 
 static void enetc4_pf_set_si_primary_mac(struct enetc_hw *hw, int si,
@@ -56,6 +69,200 @@ static void enetc4_pf_get_si_primary_mac(struct enetc_hw *hw, int si,
 	put_unaligned_le16(lower, addr + 4);
 }
 
+static void enetc4_pf_set_si_mac_promisc(struct enetc_hw *hw, int si,
+					 bool uc_promisc, bool mc_promisc)
+{
+	u32 val = enetc_port_rd(hw, ENETC4_PSIPMMR);
+
+	if (uc_promisc)
+		val |= PSIPMMR_SI_MAC_UP(si);
+	else
+		val &= ~PSIPMMR_SI_MAC_UP(si);
+
+	if (mc_promisc)
+		val |= PSIPMMR_SI_MAC_MP(si);
+	else
+		val &= ~PSIPMMR_SI_MAC_MP(si);
+
+	enetc_port_wr(hw, ENETC4_PSIPMMR, val);
+}
+
+static void enetc4_pf_set_si_uc_hash_filter(struct enetc_hw *hw, int si,
+					    u64 hash)
+{
+	enetc_port_wr(hw, ENETC4_PSIUMHFR0(si), lower_32_bits(hash));
+	enetc_port_wr(hw, ENETC4_PSIUMHFR1(si), upper_32_bits(hash));
+}
+
+static void enetc4_pf_set_si_mc_hash_filter(struct enetc_hw *hw, int si,
+					    u64 hash)
+{
+	enetc_port_wr(hw, ENETC4_PSIMMHFR0(si), lower_32_bits(hash));
+	enetc_port_wr(hw, ENETC4_PSIMMHFR1(si), upper_32_bits(hash));
+}
+
+static void enetc4_pf_set_loopback(struct net_device *ndev, bool en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_si *si = priv->si;
+	u32 val;
+
+	val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0));
+	val = u32_replace_bits(val, en ? 1 : 0, PM_CMD_CFG_LOOP_EN);
+	/* Default to select MAC level loopback mode if loopback is enabled. */
+	val = u32_replace_bits(val, en ? LPBCK_MODE_MAC_LEVEL : 0,
+			       PM_CMD_CFG_LPBK_MODE);
+
+	enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val);
+}
+
+static void enetc4_pf_clear_maft_entries(struct enetc_pf *pf)
+{
+	int i;
+
+	for (i = 0; i < pf->num_mfe; i++)
+		ntmp_maft_delete_entry(&pf->si->ntmp_user, i);
+
+	pf->num_mfe = 0;
+}
+
+static int enetc4_pf_add_maft_entries(struct enetc_pf *pf,
+				      struct enetc_mac_addr *mac,
+				      int mac_cnt)
+{
+	struct maft_entry_data maft = {};
+	u16 si_bit = BIT(0);
+	int i, err;
+
+	maft.cfge.si_bitmap = cpu_to_le16(si_bit);
+	for (i = 0; i < mac_cnt; i++) {
+		ether_addr_copy(maft.keye.mac_addr, mac[i].addr);
+		err = ntmp_maft_add_entry(&pf->si->ntmp_user, i, &maft);
+		if (unlikely(err)) {
+			pf->num_mfe = i;
+			goto clear_maft_entries;
+		}
+	}
+
+	pf->num_mfe = mac_cnt;
+
+	return 0;
+
+clear_maft_entries:
+	enetc4_pf_clear_maft_entries(pf);
+
+	return  err;
+}
+
+static int enetc4_pf_set_uc_exact_filter(struct enetc_pf *pf)
+{
+	int max_num_mfe = pf->caps.mac_filter_num;
+	struct enetc_mac_filter mac_filter = {};
+	struct net_device *ndev = pf->si->ndev;
+	struct enetc_hw *hw = &pf->si->hw;
+	struct enetc_mac_addr *mac_tbl;
+	struct netdev_hw_addr *ha;
+	int i = 0, err;
+	int mac_cnt;
+
+	netif_addr_lock_bh(ndev);
+
+	mac_cnt = netdev_uc_count(ndev);
+	if (!mac_cnt) {
+		netif_addr_unlock_bh(ndev);
+		/* clear both MAC hash and exact filters */
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+		enetc4_pf_clear_maft_entries(pf);
+
+		return 0;
+	}
+
+	if (mac_cnt > max_num_mfe) {
+		err = -ENOSPC;
+		goto unlock_netif_addr;
+	}
+
+	mac_tbl = kcalloc(mac_cnt, sizeof(*mac_tbl), GFP_ATOMIC);
+	if (!mac_tbl) {
+		err = -ENOMEM;
+		goto unlock_netif_addr;
+	}
+
+	netdev_for_each_uc_addr(ha, ndev) {
+		enetc_add_mac_addr_ht_filter(&mac_filter, ha->addr);
+		ether_addr_copy(mac_tbl[i++].addr, ha->addr);
+	}
+
+	netif_addr_unlock_bh(ndev);
+
+	/* Set temporary unicast hash filters in case of Rx loss when
+	 * updating MAC address filter table
+	 */
+	enetc4_pf_set_si_uc_hash_filter(hw, 0, *mac_filter.mac_hash_table);
+	enetc4_pf_clear_maft_entries(pf);
+
+	if (!enetc4_pf_add_maft_entries(pf, mac_tbl, i))
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+
+	kfree(mac_tbl);
+
+	return 0;
+
+unlock_netif_addr:
+	netif_addr_unlock_bh(ndev);
+
+	return err;
+}
+
+static void enetc4_pf_set_mac_hash_filter(struct enetc_pf *pf, int type)
+{
+	struct net_device *ndev = pf->si->ndev;
+	struct enetc_mac_filter *mac_filter;
+	struct enetc_hw *hw = &pf->si->hw;
+	struct netdev_hw_addr *ha;
+
+	netif_addr_lock_bh(ndev);
+	if (type & ENETC_MAC_FILTER_TYPE_UC) {
+		mac_filter = &pf->mac_filter[UC];
+		enetc_reset_mac_addr_filter(mac_filter);
+		netdev_for_each_uc_addr(ha, ndev)
+			enetc_add_mac_addr_ht_filter(mac_filter, ha->addr);
+
+		enetc4_pf_set_si_uc_hash_filter(hw, 0,
+						*mac_filter->mac_hash_table);
+	}
+
+	if (type & ENETC_MAC_FILTER_TYPE_MC) {
+		mac_filter = &pf->mac_filter[MC];
+		enetc_reset_mac_addr_filter(mac_filter);
+		netdev_for_each_mc_addr(ha, ndev)
+			enetc_add_mac_addr_ht_filter(mac_filter, ha->addr);
+
+		enetc4_pf_set_si_mc_hash_filter(hw, 0,
+						*mac_filter->mac_hash_table);
+	}
+	netif_addr_unlock_bh(ndev);
+}
+
+static void enetc4_pf_set_mac_filter(struct enetc_pf *pf, int type)
+{
+	/* Currently, the MAC address filter table (MAFT) only has 4 entries,
+	 * and multiple multicast addresses for filtering will be configured
+	 * in the default network configuration, so MAFT is only suitable for
+	 * unicast filtering. If the number of unicast addresses exceeds the
+	 * table capacity, the MAC hash filter will be used.
+	 */
+	if (type & ENETC_MAC_FILTER_TYPE_UC && enetc4_pf_set_uc_exact_filter(pf)) {
+		/* Fall back to the MAC hash filter */
+		enetc4_pf_set_mac_hash_filter(pf, ENETC_MAC_FILTER_TYPE_UC);
+		/* Clear the old MAC exact filter */
+		enetc4_pf_clear_maft_entries(pf);
+	}
+
+	if (type & ENETC_MAC_FILTER_TYPE_MC)
+		enetc4_pf_set_mac_hash_filter(pf, ENETC_MAC_FILTER_TYPE_MC);
+}
+
 static const struct enetc_pf_ops enetc4_pf_ops = {
 	.set_si_primary_mac = enetc4_pf_set_si_primary_mac,
 	.get_si_primary_mac = enetc4_pf_get_si_primary_mac,
@@ -226,24 +433,6 @@ static void enetc4_set_trx_frame_size(struct enetc_pf *pf)
 	enetc4_pf_reset_tc_msdu(&si->hw);
 }
 
-static void enetc4_set_rss_key(struct enetc_hw *hw, const u8 *bytes)
-{
-	int i;
-
-	for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
-		enetc_port_wr(hw, ENETC4_PRSSKR(i), ((u32 *)bytes)[i]);
-}
-
-static void enetc4_set_default_rss_key(struct enetc_pf *pf)
-{
-	u8 hash_key[ENETC_RSSHASH_KEY_SIZE] = {0};
-	struct enetc_hw *hw = &pf->si->hw;
-
-	/* set up hash key */
-	get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE);
-	enetc4_set_rss_key(hw, hash_key);
-}
-
 static void enetc4_enable_trx(struct enetc_pf *pf)
 {
 	struct enetc_hw *hw = &pf->si->hw;
@@ -256,10 +445,25 @@ static void enetc4_configure_port(struct enetc_pf *pf)
 {
 	enetc4_configure_port_si(pf);
 	enetc4_set_trx_frame_size(pf);
-	enetc4_set_default_rss_key(pf);
+	enetc_set_default_rss_key(pf);
 	enetc4_enable_trx(pf);
 }
 
+static int enetc4_init_ntmp_user(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+
+	/* For ENETC 4.1, all table versions are 0 */
+	memset(&user->tbl, 0, sizeof(user->tbl));
+
+	return enetc4_setup_cbdr(si);
+}
+
+static void enetc4_free_ntmp_user(struct enetc_si *si)
+{
+	enetc4_teardown_cbdr(si);
+}
+
 static int enetc4_pf_init(struct enetc_pf *pf)
 {
 	struct device *dev = &pf->si->pdev->dev;
@@ -272,17 +476,99 @@ static int enetc4_pf_init(struct enetc_pf *pf)
 		return err;
 	}
 
+	err = enetc4_init_ntmp_user(pf->si);
+	if (err) {
+		dev_err(dev, "Failed to init CBDR\n");
+		return err;
+	}
+
 	enetc4_configure_port(pf);
 
 	return 0;
 }
 
+static void enetc4_pf_free(struct enetc_pf *pf)
+{
+	enetc4_free_ntmp_user(pf->si);
+}
+
+static void enetc4_psi_do_set_rx_mode(struct work_struct *work)
+{
+	struct enetc_si *si = container_of(work, struct enetc_si, rx_mode_task);
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct net_device *ndev = si->ndev;
+	struct enetc_hw *hw = &si->hw;
+	bool uc_promisc = false;
+	bool mc_promisc = false;
+	int type = 0;
+
+	rtnl_lock();
+
+	if (ndev->flags & IFF_PROMISC) {
+		uc_promisc = true;
+		mc_promisc = true;
+	} else if (ndev->flags & IFF_ALLMULTI) {
+		mc_promisc = true;
+		type = ENETC_MAC_FILTER_TYPE_UC;
+	} else {
+		type = ENETC_MAC_FILTER_TYPE_ALL;
+	}
+
+	enetc4_pf_set_si_mac_promisc(hw, 0, uc_promisc, mc_promisc);
+
+	if (uc_promisc) {
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+		enetc4_pf_clear_maft_entries(pf);
+	}
+
+	if (mc_promisc)
+		enetc4_pf_set_si_mc_hash_filter(hw, 0, 0);
+
+	/* Set new MAC filter */
+	enetc4_pf_set_mac_filter(pf, type);
+
+	rtnl_unlock();
+}
+
+static void enetc4_pf_set_rx_mode(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_si *si = priv->si;
+
+	queue_work(si->workqueue, &si->rx_mode_task);
+}
+
+static int enetc4_pf_set_features(struct net_device *ndev,
+				  netdev_features_t features)
+{
+	netdev_features_t changed = ndev->features ^ features;
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		bool promisc_en = !(features & NETIF_F_HW_VLAN_CTAG_FILTER);
+
+		enetc4_pf_set_si_vlan_promisc(hw, 0, promisc_en);
+	}
+
+	if (changed & NETIF_F_LOOPBACK)
+		enetc4_pf_set_loopback(ndev, !!(features & NETIF_F_LOOPBACK));
+
+	enetc_set_features(ndev, features);
+
+	return 0;
+}
+
 static const struct net_device_ops enetc4_ndev_ops = {
 	.ndo_open		= enetc_open,
 	.ndo_stop		= enetc_close,
 	.ndo_start_xmit		= enetc_xmit,
 	.ndo_get_stats		= enetc_get_stats,
 	.ndo_set_mac_address	= enetc_pf_set_mac_addr,
+	.ndo_set_rx_mode	= enetc4_pf_set_rx_mode,
+	.ndo_set_features	= enetc4_pf_set_features,
+	.ndo_vlan_rx_add_vid	= enetc_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= enetc_vlan_rx_del_vid,
 };
 
 static struct phylink_pcs *
@@ -617,6 +903,19 @@ static void enetc4_link_deinit(struct enetc_ndev_priv *priv)
 	enetc_mdiobus_destroy(pf);
 }
 
+static int enetc4_psi_wq_task_init(struct enetc_si *si)
+{
+	char wq_name[24];
+
+	INIT_WORK(&si->rx_mode_task, enetc4_psi_do_set_rx_mode);
+	snprintf(wq_name, sizeof(wq_name), "enetc-%s", pci_name(si->pdev));
+	si->workqueue = create_singlethread_workqueue(wq_name);
+	if (!si->workqueue)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int enetc4_pf_netdev_create(struct enetc_si *si)
 {
 	struct device *dev = &si->pdev->dev;
@@ -657,6 +956,12 @@ static int enetc4_pf_netdev_create(struct enetc_si *si)
 	if (err)
 		goto err_link_init;
 
+	err = enetc4_psi_wq_task_init(si);
+	if (err) {
+		dev_err(dev, "Failed to init workqueue\n");
+		goto err_wq_init;
+	}
+
 	err = register_netdev(ndev);
 	if (err) {
 		dev_err(dev, "Failed to register netdev\n");
@@ -666,6 +971,8 @@ static int enetc4_pf_netdev_create(struct enetc_si *si)
 	return 0;
 
 err_reg_netdev:
+	destroy_workqueue(si->workqueue);
+err_wq_init:
 	enetc4_link_deinit(priv);
 err_link_init:
 	enetc_free_msix(priv);
@@ -683,11 +990,18 @@ static void enetc4_pf_netdev_destroy(struct enetc_si *si)
 	struct net_device *ndev = si->ndev;
 
 	unregister_netdev(ndev);
+	cancel_work(&si->rx_mode_task);
+	destroy_workqueue(si->workqueue);
 	enetc4_link_deinit(priv);
 	enetc_free_msix(priv);
 	free_netdev(ndev);
 }
 
+static const struct enetc_si_ops enetc4_psi_ops = {
+	.get_rss_table = enetc4_get_rss_table,
+	.set_rss_table = enetc4_set_rss_table,
+};
+
 static int enetc4_pf_probe(struct pci_dev *pdev,
 			   const struct pci_device_id *ent)
 {
@@ -712,6 +1026,7 @@ static int enetc4_pf_probe(struct pci_dev *pdev,
 				     "Couldn't map PF only space\n");
 
 	si->revision = enetc_get_ip_revision(&si->hw);
+	si->ops = &enetc4_psi_ops;
 	err = enetc_get_driver_data(si);
 	if (err)
 		return dev_err_probe(dev, err,
@@ -728,14 +1043,28 @@ static int enetc4_pf_probe(struct pci_dev *pdev,
 
 	enetc_get_si_caps(si);
 
-	return enetc4_pf_netdev_create(si);
+	err = enetc4_pf_netdev_create(si);
+	if (err)
+		goto err_netdev_create;
+
+	enetc_create_debugfs(si);
+
+	return 0;
+
+err_netdev_create:
+	enetc4_pf_free(pf);
+
+	return err;
 }
 
 static void enetc4_pf_remove(struct pci_dev *pdev)
 {
 	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_pf *pf = enetc_si_priv(si);
 
+	enetc_remove_debugfs(si);
 	enetc4_pf_netdev_destroy(si);
+	enetc4_pf_free(pf);
 }
 
 static const struct pci_device_id enetc4_pf_id_table[] = {
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
index 20bfdf7fb4b4..3d5f31879d5c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
@@ -60,6 +60,44 @@ void enetc_teardown_cbdr(struct enetc_cbdr *cbdr)
 }
 EXPORT_SYMBOL_GPL(enetc_teardown_cbdr);
 
+int enetc4_setup_cbdr(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+	struct device *dev = &si->pdev->dev;
+	struct enetc_hw *hw = &si->hw;
+	struct netc_cbdr_regs regs;
+
+	user->cbdr_num = 1;
+	user->dev = dev;
+	user->ring = devm_kcalloc(dev, user->cbdr_num,
+				  sizeof(struct netc_cbdr), GFP_KERNEL);
+	if (!user->ring)
+		return -ENOMEM;
+
+	/* set CBDR cache attributes */
+	enetc_wr(hw, ENETC_SICAR2,
+		 ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT);
+
+	regs.pir = hw->reg + ENETC_SICBDRPIR;
+	regs.cir = hw->reg + ENETC_SICBDRCIR;
+	regs.mr = hw->reg + ENETC_SICBDRMR;
+	regs.bar0 = hw->reg + ENETC_SICBDRBAR0;
+	regs.bar1 = hw->reg + ENETC_SICBDRBAR1;
+	regs.lenr = hw->reg + ENETC_SICBDRLENR;
+
+	return ntmp_init_cbdr(user->ring, dev, &regs);
+}
+EXPORT_SYMBOL_GPL(enetc4_setup_cbdr);
+
+void enetc4_teardown_cbdr(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+
+	ntmp_free_cbdr(user->ring);
+	user->dev = NULL;
+}
+EXPORT_SYMBOL_GPL(enetc4_teardown_cbdr);
+
 static void enetc_clean_cbdr(struct enetc_cbdr *ring)
 {
 	struct enetc_cbd *dest_cbd;
@@ -256,3 +294,15 @@ int enetc_set_rss_table(struct enetc_si *si, const u32 *table, int count)
 	return enetc_cmd_rss_table(si, (u32 *)table, count, false);
 }
 EXPORT_SYMBOL_GPL(enetc_set_rss_table);
+
+int enetc4_get_rss_table(struct enetc_si *si, u32 *table, int count)
+{
+	return ntmp_rsst_query_entry(&si->ntmp_user, table, count);
+}
+EXPORT_SYMBOL_GPL(enetc4_get_rss_table);
+
+int enetc4_set_rss_table(struct enetc_si *si, const u32 *table, int count)
+{
+	return ntmp_rsst_update_entry(&si->ntmp_user, table, count);
+}
+EXPORT_SYMBOL_GPL(enetc4_set_rss_table);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index ece3ae28ba82..d38cd36be4a6 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -141,7 +141,7 @@ static const struct {
 
 static const struct {
 	int reg;
-	char name[ETH_GSTRING_LEN];
+	char name[ETH_GSTRING_LEN] __nonstring;
 } enetc_port_counters[] = {
 	{ ENETC_PM_REOCT(0),	"MAC rx ethernet octets" },
 	{ ENETC_PM_RALN(0),	"MAC rx alignment errors" },
@@ -264,7 +264,7 @@ static void enetc_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 			break;
 
 		for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++)
-			ethtool_puts(&data, enetc_port_counters[i].name);
+			ethtool_cpy(&data, enetc_port_counters[i].name);
 
 		break;
 	}
@@ -625,6 +625,29 @@ static int enetc_get_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc,
 	return 0;
 }
 
+/* i.MX95 ENETC does not support RFS table, but we can use ingress port
+ * filter table to implement Wake-on-LAN filter or drop the matched flow,
+ * so the implementation will be different from enetc_get_rxnfc() and
+ * enetc_set_rxnfc(). Therefore, add enetc4_get_rxnfc() for ENETC v4 PF.
+ */
+static int enetc4_get_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc,
+			    u32 *rule_locs)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	switch (rxnfc->cmd) {
+	case ETHTOOL_GRXRINGS:
+		rxnfc->data = priv->num_rx_rings;
+		break;
+	case ETHTOOL_GRXFH:
+		return enetc_get_rsshash(rxnfc);
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static int enetc_set_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
@@ -677,36 +700,53 @@ static u32 enetc_get_rxfh_indir_size(struct net_device *ndev)
 	return priv->si->num_rss;
 }
 
+static int enetc_get_rss_key_base(struct enetc_si *si)
+{
+	if (is_enetc_rev1(si))
+		return ENETC_PRSSK(0);
+
+	return ENETC4_PRSSKR(0);
+}
+
+static void enetc_get_rss_key(struct enetc_si *si, const u8 *key)
+{
+	int base = enetc_get_rss_key_base(si);
+	struct enetc_hw *hw = &si->hw;
+	int i;
+
+	for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
+		((u32 *)key)[i] = enetc_port_rd(hw, base + i * 4);
+}
+
 static int enetc_get_rxfh(struct net_device *ndev,
 			  struct ethtool_rxfh_param *rxfh)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_hw *hw = &priv->si->hw;
-	int err = 0, i;
+	struct enetc_si *si = priv->si;
+	int err = 0;
 
 	/* return hash function */
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	/* return hash key */
-	if (rxfh->key && hw->port)
-		for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
-			((u32 *)rxfh->key)[i] = enetc_port_rd(hw,
-							      ENETC_PRSSK(i));
+	if (rxfh->key && enetc_si_is_pf(si))
+		enetc_get_rss_key(si, rxfh->key);
 
 	/* return RSS table */
 	if (rxfh->indir)
-		err = enetc_get_rss_table(priv->si, rxfh->indir,
-					  priv->si->num_rss);
+		err = si->ops->get_rss_table(si, rxfh->indir, si->num_rss);
 
 	return err;
 }
 
-void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes)
+void enetc_set_rss_key(struct enetc_si *si, const u8 *bytes)
 {
+	int base = enetc_get_rss_key_base(si);
+	struct enetc_hw *hw = &si->hw;
 	int i;
 
 	for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
-		enetc_port_wr(hw, ENETC_PRSSK(i), ((u32 *)bytes)[i]);
+		enetc_port_wr(hw, base + i * 4, ((u32 *)bytes)[i]);
 }
 EXPORT_SYMBOL_GPL(enetc_set_rss_key);
 
@@ -715,17 +755,16 @@ static int enetc_set_rxfh(struct net_device *ndev,
 			  struct netlink_ext_ack *extack)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_hw *hw = &priv->si->hw;
+	struct enetc_si *si = priv->si;
 	int err = 0;
 
 	/* set hash key, if PF */
-	if (rxfh->key && hw->port)
-		enetc_set_rss_key(hw, rxfh->key);
+	if (rxfh->key && enetc_si_is_pf(si))
+		enetc_set_rss_key(si, rxfh->key);
 
 	/* set RSS table */
 	if (rxfh->indir)
-		err = enetc_set_rss_table(priv->si, rxfh->indir,
-					  priv->si->num_rss);
+		err = si->ops->set_rss_table(si, rxfh->indir, si->num_rss);
 
 	return err;
 }
@@ -1240,6 +1279,11 @@ const struct ethtool_ops enetc4_pf_ethtool_ops = {
 	.set_wol = enetc_set_wol,
 	.get_pauseparam = enetc_get_pauseparam,
 	.set_pauseparam = enetc_set_pauseparam,
+	.get_rxnfc = enetc4_get_rxnfc,
+	.get_rxfh_key_size = enetc_get_rxfh_key_size,
+	.get_rxfh_indir_size = enetc_get_rxfh_indir_size,
+	.get_rxfh = enetc_get_rxfh,
+	.set_rxfh = enetc_set_rxfh,
 };
 
 void enetc_set_ethtool_ops(struct net_device *ndev)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 203862ec1114..f63a29e2e031 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -72,30 +72,6 @@ static void enetc_set_isol_vlan(struct enetc_hw *hw, int si, u16 vlan, u8 qos)
 	enetc_port_wr(hw, ENETC_PSIVLANR(si), val);
 }
 
-static int enetc_mac_addr_hash_idx(const u8 *addr)
-{
-	u64 fold = __swab64(ether_addr_to_u64(addr)) >> 16;
-	u64 mask = 0;
-	int res = 0;
-	int i;
-
-	for (i = 0; i < 8; i++)
-		mask |= BIT_ULL(i * 6);
-
-	for (i = 0; i < 6; i++)
-		res |= (hweight64(fold & (mask << i)) & 0x1) << i;
-
-	return res;
-}
-
-static void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter)
-{
-	filter->mac_addr_cnt = 0;
-
-	bitmap_zero(filter->mac_hash_table,
-		    ENETC_MADDR_HASH_TBL_SZ);
-}
-
 static void enetc_add_mac_addr_em_filter(struct enetc_mac_filter *filter,
 					 const unsigned char *addr)
 {
@@ -104,16 +80,6 @@ static void enetc_add_mac_addr_em_filter(struct enetc_mac_filter *filter,
 	filter->mac_addr_cnt++;
 }
 
-static void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
-					 const unsigned char *addr)
-{
-	int idx = enetc_mac_addr_hash_idx(addr);
-
-	/* add hash table entry */
-	__set_bit(idx, filter->mac_hash_table);
-	filter->mac_addr_cnt++;
-}
-
 static void enetc_clear_mac_ht_flt(struct enetc_si *si, int si_idx, int type)
 {
 	bool err = si->errata & ENETC_ERR_UCMCSWP;
@@ -250,67 +216,6 @@ static void enetc_pf_set_rx_mode(struct net_device *ndev)
 	enetc_port_wr(hw, ENETC_PSIPMR, psipmr);
 }
 
-static void enetc_set_vlan_ht_filter(struct enetc_hw *hw, int si_idx,
-				     unsigned long hash)
-{
-	enetc_port_wr(hw, ENETC_PSIVHFR0(si_idx), lower_32_bits(hash));
-	enetc_port_wr(hw, ENETC_PSIVHFR1(si_idx), upper_32_bits(hash));
-}
-
-static int enetc_vid_hash_idx(unsigned int vid)
-{
-	int res = 0;
-	int i;
-
-	for (i = 0; i < 6; i++)
-		res |= (hweight8(vid & (BIT(i) | BIT(i + 6))) & 0x1) << i;
-
-	return res;
-}
-
-static void enetc_sync_vlan_ht_filter(struct enetc_pf *pf, bool rehash)
-{
-	int i;
-
-	if (rehash) {
-		bitmap_zero(pf->vlan_ht_filter, ENETC_VLAN_HT_SIZE);
-
-		for_each_set_bit(i, pf->active_vlans, VLAN_N_VID) {
-			int hidx = enetc_vid_hash_idx(i);
-
-			__set_bit(hidx, pf->vlan_ht_filter);
-		}
-	}
-
-	enetc_set_vlan_ht_filter(&pf->si->hw, 0, *pf->vlan_ht_filter);
-}
-
-static int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid)
-{
-	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_pf *pf = enetc_si_priv(priv->si);
-	int idx;
-
-	__set_bit(vid, pf->active_vlans);
-
-	idx = enetc_vid_hash_idx(vid);
-	if (!__test_and_set_bit(idx, pf->vlan_ht_filter))
-		enetc_sync_vlan_ht_filter(pf, false);
-
-	return 0;
-}
-
-static int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid)
-{
-	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	struct enetc_pf *pf = enetc_si_priv(priv->si);
-
-	__clear_bit(vid, pf->active_vlans);
-	enetc_sync_vlan_ht_filter(pf, true);
-
-	return 0;
-}
-
 static void enetc_set_loopback(struct net_device *ndev, bool en)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
@@ -549,7 +454,6 @@ static void enetc_mac_enable(struct enetc_si *si, bool en)
 
 static void enetc_configure_port(struct enetc_pf *pf)
 {
-	u8 hash_key[ENETC_RSSHASH_KEY_SIZE];
 	struct enetc_hw *hw = &pf->si->hw;
 
 	enetc_configure_port_mac(pf->si);
@@ -557,8 +461,7 @@ static void enetc_configure_port(struct enetc_pf *pf)
 	enetc_port_si_configure(pf->si);
 
 	/* set up hash key */
-	get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE);
-	enetc_set_rss_key(hw, hash_key);
+	enetc_set_default_rss_key(pf);
 
 	/* split up RFS entries */
 	enetc_port_assign_rfs_entries(pf->si);
@@ -728,6 +631,8 @@ static const struct net_device_ops enetc_ndev_ops = {
 	.ndo_setup_tc		= enetc_pf_setup_tc,
 	.ndo_bpf		= enetc_setup_bpf,
 	.ndo_xdp_xmit		= enetc_xdp_xmit,
+	.ndo_hwtstamp_get	= enetc_hwtstamp_get,
+	.ndo_hwtstamp_set	= enetc_hwtstamp_set,
 };
 
 static struct phylink_pcs *
@@ -939,6 +844,11 @@ static int enetc_pf_register_with_ierb(struct pci_dev *pdev)
 	return enetc_ierb_register_pf(ierb_pdev, pdev);
 }
 
+static const struct enetc_si_ops enetc_psi_ops = {
+	.get_rss_table = enetc_get_rss_table,
+	.set_rss_table = enetc_set_rss_table,
+};
+
 static struct enetc_si *enetc_psi_create(struct pci_dev *pdev)
 {
 	struct enetc_si *si;
@@ -958,6 +868,7 @@ static struct enetc_si *enetc_psi_create(struct pci_dev *pdev)
 	}
 
 	si->revision = enetc_get_ip_revision(&si->hw);
+	si->ops = &enetc_psi_ops;
 	err = enetc_get_driver_data(si);
 	if (err) {
 		dev_err(&pdev->dev, "Could not get PF driver data\n");
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
index a26a12863855..ae407e9e9ee7 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -5,19 +5,8 @@
 #include <linux/phylink.h>
 
 #define ENETC_PF_NUM_RINGS	8
-
-enum enetc_mac_addr_type {UC, MC, MADDR_TYPE};
 #define ENETC_MAX_NUM_MAC_FLT	((ENETC_MAX_NUM_VFS + 1) * MADDR_TYPE)
 
-#define ENETC_MADDR_HASH_TBL_SZ	64
-struct enetc_mac_filter {
-	union {
-		char mac_addr[ETH_ALEN];
-		DECLARE_BITMAP(mac_hash_table, ENETC_MADDR_HASH_TBL_SZ);
-	};
-	int mac_addr_cnt;
-};
-
 #define ENETC_VLAN_HT_SIZE	64
 
 enum enetc_vf_flags {
@@ -34,6 +23,7 @@ struct enetc_port_caps {
 	int num_msix;
 	int num_rx_bdr;
 	int num_tx_bdr;
+	int mac_filter_num;
 };
 
 struct enetc_pf;
@@ -71,6 +61,8 @@ struct enetc_pf {
 
 	struct enetc_port_caps caps;
 	const struct enetc_pf_ops *ops;
+
+	int num_mfe;	/* number of mac address filter table entries */
 };
 
 #define phylink_to_enetc_pf(config) \
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 3fd9b0727875..edf14a95cab7 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -128,14 +128,14 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	if (si->hw_features & ENETC_SI_F_LSO)
 		priv->active_offloads |= ENETC_F_LSO;
 
-	/* TODO: currently, i.MX95 ENETC driver does not support advanced features */
-	if (!is_enetc_rev1(si)) {
-		ndev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK);
-		goto end;
+	if (si->num_rss) {
+		ndev->hw_features |= NETIF_F_RXHASH;
+		ndev->features |= NETIF_F_RXHASH;
 	}
 
-	if (si->num_rss)
-		ndev->hw_features |= NETIF_F_RXHASH;
+	/* TODO: currently, i.MX95 ENETC driver does not support advanced features */
+	if (!is_enetc_rev1(si))
+		goto end;
 
 	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
 			     NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
@@ -341,5 +341,86 @@ void enetc_phylink_destroy(struct enetc_ndev_priv *priv)
 }
 EXPORT_SYMBOL_GPL(enetc_phylink_destroy);
 
+void enetc_set_default_rss_key(struct enetc_pf *pf)
+{
+	u8 hash_key[ENETC_RSSHASH_KEY_SIZE] = {0};
+
+	/* set up hash key */
+	get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE);
+	enetc_set_rss_key(pf->si, hash_key);
+}
+EXPORT_SYMBOL_GPL(enetc_set_default_rss_key);
+
+static int enetc_vid_hash_idx(unsigned int vid)
+{
+	int res = 0;
+	int i;
+
+	for (i = 0; i < 6; i++)
+		res |= (hweight8(vid & (BIT(i) | BIT(i + 6))) & 0x1) << i;
+
+	return res;
+}
+
+static void enetc_refresh_vlan_ht_filter(struct enetc_pf *pf)
+{
+	int i;
+
+	bitmap_zero(pf->vlan_ht_filter, ENETC_VLAN_HT_SIZE);
+	for_each_set_bit(i, pf->active_vlans, VLAN_N_VID) {
+		int hidx = enetc_vid_hash_idx(i);
+
+		__set_bit(hidx, pf->vlan_ht_filter);
+	}
+}
+
+static void enetc_set_si_vlan_ht_filter(struct enetc_si *si,
+					int si_id, u64 hash)
+{
+	struct enetc_hw *hw = &si->hw;
+	int high_reg_off, low_reg_off;
+
+	if (is_enetc_rev1(si)) {
+		low_reg_off = ENETC_PSIVHFR0(si_id);
+		high_reg_off = ENETC_PSIVHFR1(si_id);
+	} else {
+		low_reg_off = ENETC4_PSIVHFR0(si_id);
+		high_reg_off = ENETC4_PSIVHFR1(si_id);
+	}
+
+	enetc_port_wr(hw, low_reg_off, lower_32_bits(hash));
+	enetc_port_wr(hw, high_reg_off, upper_32_bits(hash));
+}
+
+int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	int idx;
+
+	__set_bit(vid, pf->active_vlans);
+
+	idx = enetc_vid_hash_idx(vid);
+	if (!__test_and_set_bit(idx, pf->vlan_ht_filter))
+		enetc_set_si_vlan_ht_filter(pf->si, 0, *pf->vlan_ht_filter);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(enetc_vlan_rx_add_vid);
+
+int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+
+	if (__test_and_clear_bit(vid, pf->active_vlans)) {
+		enetc_refresh_vlan_ht_filter(pf);
+		enetc_set_si_vlan_ht_filter(pf->si, 0, *pf->vlan_ht_filter);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(enetc_vlan_rx_del_vid);
+
 MODULE_DESCRIPTION("NXP ENETC PF common functionality driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
index 48f55ee743ad..96d4840a3107 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
@@ -12,6 +12,9 @@ void enetc_mdiobus_destroy(struct enetc_pf *pf);
 int enetc_phylink_create(struct enetc_ndev_priv *priv, struct device_node *node,
 			 const struct phylink_mac_ops *ops);
 void enetc_phylink_destroy(struct enetc_ndev_priv *priv);
+void enetc_set_default_rss_key(struct enetc_pf *pf);
+int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid);
+int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid);
 
 static inline u16 enetc_get_ip_revision(struct enetc_hw *hw)
 {
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
index 3768752b6008..6c4b374bcb0e 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -121,6 +121,8 @@ static const struct net_device_ops enetc_ndev_ops = {
 	.ndo_set_features	= enetc_vf_set_features,
 	.ndo_eth_ioctl		= enetc_ioctl,
 	.ndo_setup_tc		= enetc_vf_setup_tc,
+	.ndo_hwtstamp_get	= enetc_hwtstamp_get,
+	.ndo_hwtstamp_set	= enetc_hwtstamp_set,
 };
 
 static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
@@ -155,13 +157,20 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM |
 			      NETIF_F_TSO | NETIF_F_TSO6;
 
-	if (si->num_rss)
+	if (si->num_rss) {
 		ndev->hw_features |= NETIF_F_RXHASH;
+		ndev->features |= NETIF_F_RXHASH;
+	}
 
 	/* pick up primary MAC address from SI */
 	enetc_load_primary_mac_addr(&si->hw, ndev);
 }
 
+static const struct enetc_si_ops enetc_vsi_ops = {
+	.get_rss_table = enetc_get_rss_table,
+	.set_rss_table = enetc_set_rss_table,
+};
+
 static int enetc_vf_probe(struct pci_dev *pdev,
 			  const struct pci_device_id *ent)
 {
@@ -176,6 +185,7 @@ static int enetc_vf_probe(struct pci_dev *pdev,
 
 	si = pci_get_drvdata(pdev);
 	si->revision = ENETC_REV_1_0;
+	si->ops = &enetc_vsi_ops;
 	err = enetc_get_driver_data(si);
 	if (err) {
 		dev_err_probe(&pdev->dev, err,
diff --git a/drivers/net/ethernet/freescale/enetc/ntmp.c b/drivers/net/ethernet/freescale/enetc/ntmp.c
new file mode 100644
index 000000000000..ba32c1bbd9e1
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/ntmp.c
@@ -0,0 +1,462 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/*
+ * NETC NTMP (NETC Table Management Protocol) 2.0 Library
+ * Copyright 2025 NXP
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/fsl/netc_global.h>
+#include <linux/iopoll.h>
+
+#include "ntmp_private.h"
+
+#define NETC_CBDR_TIMEOUT		1000 /* us */
+#define NETC_CBDR_DELAY_US		10
+#define NETC_CBDR_MR_EN			BIT(31)
+
+#define NTMP_BASE_ADDR_ALIGN		128
+#define NTMP_DATA_ADDR_ALIGN		32
+
+/* Define NTMP Table ID */
+#define NTMP_MAFT_ID			1
+#define NTMP_RSST_ID			3
+
+/* Generic Update Actions for most tables */
+#define NTMP_GEN_UA_CFGEU		BIT(0)
+#define NTMP_GEN_UA_STSEU		BIT(1)
+
+#define NTMP_ENTRY_ID_SIZE		4
+#define RSST_ENTRY_NUM			64
+#define RSST_STSE_DATA_SIZE(n)		((n) * 8)
+#define RSST_CFGE_DATA_SIZE(n)		(n)
+
+int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev,
+		   const struct netc_cbdr_regs *regs)
+{
+	int cbd_num = NETC_CBDR_BD_NUM;
+	size_t size;
+
+	size = cbd_num * sizeof(union netc_cbd) + NTMP_BASE_ADDR_ALIGN;
+	cbdr->addr_base = dma_alloc_coherent(dev, size, &cbdr->dma_base,
+					     GFP_KERNEL);
+	if (!cbdr->addr_base)
+		return -ENOMEM;
+
+	cbdr->dma_size = size;
+	cbdr->bd_num = cbd_num;
+	cbdr->regs = *regs;
+	cbdr->dev = dev;
+
+	/* The base address of the Control BD Ring must be 128 bytes aligned */
+	cbdr->dma_base_align =  ALIGN(cbdr->dma_base,  NTMP_BASE_ADDR_ALIGN);
+	cbdr->addr_base_align = PTR_ALIGN(cbdr->addr_base,
+					  NTMP_BASE_ADDR_ALIGN);
+
+	cbdr->next_to_clean = 0;
+	cbdr->next_to_use = 0;
+	spin_lock_init(&cbdr->ring_lock);
+
+	/* Step 1: Configure the base address of the Control BD Ring */
+	netc_write(cbdr->regs.bar0, lower_32_bits(cbdr->dma_base_align));
+	netc_write(cbdr->regs.bar1, upper_32_bits(cbdr->dma_base_align));
+
+	/* Step 2: Configure the producer index register */
+	netc_write(cbdr->regs.pir, cbdr->next_to_clean);
+
+	/* Step 3: Configure the consumer index register */
+	netc_write(cbdr->regs.cir, cbdr->next_to_use);
+
+	/* Step4: Configure the number of BDs of the Control BD Ring */
+	netc_write(cbdr->regs.lenr, cbdr->bd_num);
+
+	/* Step 5: Enable the Control BD Ring */
+	netc_write(cbdr->regs.mr, NETC_CBDR_MR_EN);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ntmp_init_cbdr);
+
+void ntmp_free_cbdr(struct netc_cbdr *cbdr)
+{
+	/* Disable the Control BD Ring */
+	netc_write(cbdr->regs.mr, 0);
+	dma_free_coherent(cbdr->dev, cbdr->dma_size, cbdr->addr_base,
+			  cbdr->dma_base);
+	memset(cbdr, 0, sizeof(*cbdr));
+}
+EXPORT_SYMBOL_GPL(ntmp_free_cbdr);
+
+static int ntmp_get_free_cbd_num(struct netc_cbdr *cbdr)
+{
+	return (cbdr->next_to_clean - cbdr->next_to_use - 1 +
+		cbdr->bd_num) % cbdr->bd_num;
+}
+
+static union netc_cbd *ntmp_get_cbd(struct netc_cbdr *cbdr, int index)
+{
+	return &((union netc_cbd *)(cbdr->addr_base_align))[index];
+}
+
+static void ntmp_clean_cbdr(struct netc_cbdr *cbdr)
+{
+	union netc_cbd *cbd;
+	int i;
+
+	i = cbdr->next_to_clean;
+	while (netc_read(cbdr->regs.cir) != i) {
+		cbd = ntmp_get_cbd(cbdr, i);
+		memset(cbd, 0, sizeof(*cbd));
+		i = (i + 1) % cbdr->bd_num;
+	}
+
+	cbdr->next_to_clean = i;
+}
+
+static int netc_xmit_ntmp_cmd(struct ntmp_user *user, union netc_cbd *cbd)
+{
+	union netc_cbd *cur_cbd;
+	struct netc_cbdr *cbdr;
+	int i, err;
+	u16 status;
+	u32 val;
+
+	/* Currently only i.MX95 ENETC is supported, and it only has one
+	 * command BD ring
+	 */
+	cbdr = &user->ring[0];
+
+	spin_lock_bh(&cbdr->ring_lock);
+
+	if (unlikely(!ntmp_get_free_cbd_num(cbdr)))
+		ntmp_clean_cbdr(cbdr);
+
+	i = cbdr->next_to_use;
+	cur_cbd = ntmp_get_cbd(cbdr, i);
+	*cur_cbd = *cbd;
+	dma_wmb();
+
+	/* Update producer index of both software and hardware */
+	i = (i + 1) % cbdr->bd_num;
+	cbdr->next_to_use = i;
+	netc_write(cbdr->regs.pir, i);
+
+	err = read_poll_timeout_atomic(netc_read, val, val == i,
+				       NETC_CBDR_DELAY_US, NETC_CBDR_TIMEOUT,
+				       true, cbdr->regs.cir);
+	if (unlikely(err))
+		goto cbdr_unlock;
+
+	dma_rmb();
+	/* Get the writeback command BD, because the caller may need
+	 * to check some other fields of the response header.
+	 */
+	*cbd = *cur_cbd;
+
+	/* Check the writeback error status */
+	status = le16_to_cpu(cbd->resp_hdr.error_rr) & NTMP_RESP_ERROR;
+	if (unlikely(status)) {
+		err = -EIO;
+		dev_err(user->dev, "Command BD error: 0x%04x\n", status);
+	}
+
+	ntmp_clean_cbdr(cbdr);
+	dma_wmb();
+
+cbdr_unlock:
+	spin_unlock_bh(&cbdr->ring_lock);
+
+	return err;
+}
+
+static int ntmp_alloc_data_mem(struct ntmp_dma_buf *data, void **buf_align)
+{
+	void *buf;
+
+	buf = dma_alloc_coherent(data->dev, data->size + NTMP_DATA_ADDR_ALIGN,
+				 &data->dma, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	data->buf = buf;
+	*buf_align = PTR_ALIGN(buf, NTMP_DATA_ADDR_ALIGN);
+
+	return 0;
+}
+
+static void ntmp_free_data_mem(struct ntmp_dma_buf *data)
+{
+	dma_free_coherent(data->dev, data->size + NTMP_DATA_ADDR_ALIGN,
+			  data->buf, data->dma);
+}
+
+static void ntmp_fill_request_hdr(union netc_cbd *cbd, dma_addr_t dma,
+				  int len, int table_id, int cmd,
+				  int access_method)
+{
+	dma_addr_t dma_align;
+
+	memset(cbd, 0, sizeof(*cbd));
+	dma_align = ALIGN(dma, NTMP_DATA_ADDR_ALIGN);
+	cbd->req_hdr.addr = cpu_to_le64(dma_align);
+	cbd->req_hdr.len = cpu_to_le32(len);
+	cbd->req_hdr.cmd = cmd;
+	cbd->req_hdr.access_method = FIELD_PREP(NTMP_ACCESS_METHOD,
+						access_method);
+	cbd->req_hdr.table_id = table_id;
+	cbd->req_hdr.ver_cci_rr = FIELD_PREP(NTMP_HDR_VERSION,
+					     NTMP_HDR_VER2);
+	/* For NTMP version 2.0 or later version */
+	cbd->req_hdr.npf = cpu_to_le32(NTMP_NPF);
+}
+
+static void ntmp_fill_crd(struct ntmp_cmn_req_data *crd, u8 tblv,
+			  u8 qa, u16 ua)
+{
+	crd->update_act = cpu_to_le16(ua);
+	crd->tblv_qact = NTMP_TBLV_QACT(tblv, qa);
+}
+
+static void ntmp_fill_crd_eid(struct ntmp_req_by_eid *rbe, u8 tblv,
+			      u8 qa, u16 ua, u32 entry_id)
+{
+	ntmp_fill_crd(&rbe->crd, tblv, qa, ua);
+	rbe->entry_id = cpu_to_le32(entry_id);
+}
+
+static const char *ntmp_table_name(int tbl_id)
+{
+	switch (tbl_id) {
+	case NTMP_MAFT_ID:
+		return "MAC Address Filter Table";
+	case NTMP_RSST_ID:
+		return "RSS Table";
+	default:
+		return "Unknown Table";
+	};
+}
+
+static int ntmp_delete_entry_by_id(struct ntmp_user *user, int tbl_id,
+				   u8 tbl_ver, u32 entry_id, u32 req_len,
+				   u32 resp_len)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = max(req_len, resp_len),
+	};
+	struct ntmp_req_by_eid *req;
+	union netc_cbd cbd;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	ntmp_fill_crd_eid(req, tbl_ver, 0, 0, entry_id);
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(req_len, resp_len),
+			      tbl_id, NTMP_CMD_DELETE, NTMP_AM_ENTRY_ID);
+
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev,
+			"Failed to delete entry 0x%x of %s, err: %pe",
+			entry_id, ntmp_table_name(tbl_id), ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+
+static int ntmp_query_entry_by_id(struct ntmp_user *user, int tbl_id,
+				  u32 len, struct ntmp_req_by_eid *req,
+				  dma_addr_t dma, bool compare_eid)
+{
+	struct ntmp_cmn_resp_query *resp;
+	int cmd = NTMP_CMD_QUERY;
+	union netc_cbd cbd;
+	u32 entry_id;
+	int err;
+
+	entry_id = le32_to_cpu(req->entry_id);
+	if (le16_to_cpu(req->crd.update_act))
+		cmd = NTMP_CMD_QU;
+
+	/* Request header */
+	ntmp_fill_request_hdr(&cbd, dma, len, tbl_id, cmd, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err) {
+		dev_err(user->dev,
+			"Failed to query entry 0x%x of %s, err: %pe\n",
+			entry_id, ntmp_table_name(tbl_id), ERR_PTR(err));
+		return err;
+	}
+
+	/* For a few tables, the first field of their response data is not
+	 * entry_id, so directly return success.
+	 */
+	if (!compare_eid)
+		return 0;
+
+	resp = (struct ntmp_cmn_resp_query *)req;
+	if (unlikely(le32_to_cpu(resp->entry_id) != entry_id)) {
+		dev_err(user->dev,
+			"%s: query EID 0x%x doesn't match response EID 0x%x\n",
+			ntmp_table_name(tbl_id), entry_id, le32_to_cpu(resp->entry_id));
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id,
+			struct maft_entry_data *maft)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = sizeof(struct maft_req_add),
+	};
+	struct maft_req_add *req;
+	union netc_cbd cbd;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set mac address filter table request data buffer */
+	ntmp_fill_crd_eid(&req->rbe, user->tbl.maft_ver, 0, 0, entry_id);
+	req->keye = maft->keye;
+	req->cfge = maft->cfge;
+
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(data.size, 0),
+			      NTMP_MAFT_ID, NTMP_CMD_ADD, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev, "Failed to add MAFT entry 0x%x, err: %pe\n",
+			entry_id, ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_add_entry);
+
+int ntmp_maft_query_entry(struct ntmp_user *user, u32 entry_id,
+			  struct maft_entry_data *maft)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = sizeof(struct maft_resp_query),
+	};
+	struct maft_resp_query *resp;
+	struct ntmp_req_by_eid *req;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	ntmp_fill_crd_eid(req, user->tbl.maft_ver, 0, 0, entry_id);
+	err = ntmp_query_entry_by_id(user, NTMP_MAFT_ID,
+				     NTMP_LEN(sizeof(*req), data.size),
+				     req, data.dma, true);
+	if (err)
+		goto end;
+
+	resp = (struct maft_resp_query *)req;
+	maft->keye = resp->keye;
+	maft->cfge = resp->cfge;
+
+end:
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_query_entry);
+
+int ntmp_maft_delete_entry(struct ntmp_user *user, u32 entry_id)
+{
+	return ntmp_delete_entry_by_id(user, NTMP_MAFT_ID, user->tbl.maft_ver,
+				       entry_id, NTMP_EID_REQ_LEN, 0);
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_delete_entry);
+
+int ntmp_rsst_update_entry(struct ntmp_user *user, const u32 *table,
+			   int count)
+{
+	struct ntmp_dma_buf data = {.dev = user->dev};
+	struct rsst_req_update *req;
+	union netc_cbd cbd;
+	int err, i;
+
+	if (count != RSST_ENTRY_NUM)
+		/* HW only takes in a full 64 entry table */
+		return -EINVAL;
+
+	data.size = struct_size(req, groups, count);
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set the request data buffer */
+	ntmp_fill_crd_eid(&req->rbe, user->tbl.rsst_ver, 0,
+			  NTMP_GEN_UA_CFGEU | NTMP_GEN_UA_STSEU, 0);
+	for (i = 0; i < count; i++)
+		req->groups[i] = (u8)(table[i]);
+
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(data.size, 0),
+			      NTMP_RSST_ID, NTMP_CMD_UPDATE, NTMP_AM_ENTRY_ID);
+
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev, "Failed to update RSST entry, err: %pe\n",
+			ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_rsst_update_entry);
+
+int ntmp_rsst_query_entry(struct ntmp_user *user, u32 *table, int count)
+{
+	struct ntmp_dma_buf data = {.dev = user->dev};
+	struct ntmp_req_by_eid *req;
+	union netc_cbd cbd;
+	int err, i;
+	u8 *group;
+
+	if (count != RSST_ENTRY_NUM)
+		/* HW only takes in a full 64 entry table */
+		return -EINVAL;
+
+	data.size = NTMP_ENTRY_ID_SIZE + RSST_STSE_DATA_SIZE(count) +
+		    RSST_CFGE_DATA_SIZE(count);
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set the request data buffer */
+	ntmp_fill_crd_eid(req, user->tbl.rsst_ver, 0, 0, 0);
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(sizeof(*req), data.size),
+			      NTMP_RSST_ID, NTMP_CMD_QUERY, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err) {
+		dev_err(user->dev, "Failed to query RSST entry, err: %pe\n",
+			ERR_PTR(err));
+		goto end;
+	}
+
+	group = (u8 *)req;
+	group += NTMP_ENTRY_ID_SIZE + RSST_STSE_DATA_SIZE(count);
+	for (i = 0; i < count; i++)
+		table[i] = group[i];
+
+end:
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_rsst_query_entry);
+
+MODULE_DESCRIPTION("NXP NETC Library");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/freescale/enetc/ntmp_private.h b/drivers/net/ethernet/freescale/enetc/ntmp_private.h
new file mode 100644
index 000000000000..34394e40fddd
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/ntmp_private.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/*
+ * NTMP table request and response data buffer formats
+ * Copyright 2025 NXP
+ */
+
+#ifndef __NTMP_PRIVATE_H
+#define __NTMP_PRIVATE_H
+
+#include <linux/bitfield.h>
+#include <linux/fsl/ntmp.h>
+
+#define NTMP_EID_REQ_LEN	8
+#define NETC_CBDR_BD_NUM	256
+
+union netc_cbd {
+	struct {
+		__le64 addr;
+		__le32 len;
+#define NTMP_RESP_LEN		GENMASK(19, 0)
+#define NTMP_REQ_LEN		GENMASK(31, 20)
+#define NTMP_LEN(req, resp)	(FIELD_PREP(NTMP_REQ_LEN, (req)) | \
+				((resp) & NTMP_RESP_LEN))
+		u8 cmd;
+#define NTMP_CMD_DELETE		BIT(0)
+#define NTMP_CMD_UPDATE		BIT(1)
+#define NTMP_CMD_QUERY		BIT(2)
+#define NTMP_CMD_ADD		BIT(3)
+#define NTMP_CMD_QU		(NTMP_CMD_QUERY | NTMP_CMD_UPDATE)
+		u8 access_method;
+#define NTMP_ACCESS_METHOD	GENMASK(7, 4)
+#define NTMP_AM_ENTRY_ID	0
+#define NTMP_AM_EXACT_KEY	1
+#define NTMP_AM_SEARCH		2
+#define NTMP_AM_TERNARY_KEY	3
+		u8 table_id;
+		u8 ver_cci_rr;
+#define NTMP_HDR_VERSION	GENMASK(5, 0)
+#define NTMP_HDR_VER2		2
+#define NTMP_CCI		BIT(6)
+#define NTMP_RR			BIT(7)
+		__le32 resv[3];
+		__le32 npf;
+#define NTMP_NPF		BIT(15)
+	} req_hdr;	/* NTMP Request Message Header Format */
+
+	struct {
+		__le32 resv0[3];
+		__le16 num_matched;
+		__le16 error_rr;
+#define NTMP_RESP_ERROR		GENMASK(11, 0)
+#define NTMP_RESP_RR		BIT(15)
+		__le32 resv1[4];
+	} resp_hdr; /* NTMP Response Message Header Format */
+};
+
+struct ntmp_dma_buf {
+	struct device *dev;
+	size_t size;
+	void *buf;
+	dma_addr_t dma;
+};
+
+struct ntmp_cmn_req_data {
+	__le16 update_act;
+	u8 dbg_opt;
+	u8 tblv_qact;
+#define NTMP_QUERY_ACT		GENMASK(3, 0)
+#define NTMP_TBL_VER		GENMASK(7, 4)
+#define NTMP_TBLV_QACT(v, a)	(FIELD_PREP(NTMP_TBL_VER, (v)) | \
+				 ((a) & NTMP_QUERY_ACT))
+};
+
+struct ntmp_cmn_resp_query {
+	__le32 entry_id;
+};
+
+/* Generic structure for request data by entry ID  */
+struct ntmp_req_by_eid {
+	struct ntmp_cmn_req_data crd;
+	__le32 entry_id;
+};
+
+/* MAC Address Filter Table Request Data Buffer Format of Add action */
+struct maft_req_add {
+	struct ntmp_req_by_eid rbe;
+	struct maft_keye_data keye;
+	struct maft_cfge_data cfge;
+};
+
+/* MAC Address Filter Table Response Data Buffer Format of Query action */
+struct maft_resp_query {
+	__le32 entry_id;
+	struct maft_keye_data keye;
+	struct maft_cfge_data cfge;
+};
+
+/* RSS Table Request Data Buffer Format of Update action */
+struct rsst_req_update {
+	struct ntmp_req_by_eid rbe;
+	u8 groups[];
+};
+
+#endif
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index a86cfebedaa8..17e9bddb9ddd 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -714,7 +714,12 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 	txq->bd.cur = bdp;
 
 	/* Trigger transmission start */
-	writel(0, txq->bd.reg_desc_active);
+	if (!(fep->quirks & FEC_QUIRK_ERR007885) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active))
+		writel(0, txq->bd.reg_desc_active);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index deb35b38c976..bcbcad613512 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2061,15 +2061,13 @@ static void gfar_timeout(struct net_device *dev, unsigned int txqueue)
 	schedule_work(&priv->reset_task);
 }
 
-static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
+static int gfar_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
 	struct gfar_private *priv = netdev_priv(netdev);
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		priv->hwts_tx_en = 0;
 		break;
@@ -2082,7 +2080,7 @@ static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		if (priv->hwts_rx_en) {
 			priv->hwts_rx_en = 0;
@@ -2096,44 +2094,23 @@ static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 			priv->hwts_rx_en = 1;
 			reset_gfar(netdev);
 		}
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	}
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
+	return 0;
 }
 
-static int gfar_hwtstamp_get(struct net_device *netdev, struct ifreq *ifr)
+static int gfar_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config config;
 	struct gfar_private *priv = netdev_priv(netdev);
 
-	config.flags = 0;
-	config.tx_type = priv->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	config.rx_filter = (priv->hwts_rx_en ?
-			    HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE);
-
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
-}
-
-static int gfar_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
-	struct phy_device *phydev = dev->phydev;
+	config->tx_type = priv->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	config->rx_filter = priv->hwts_rx_en ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
 
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	if (cmd == SIOCSHWTSTAMP)
-		return gfar_hwtstamp_set(dev, rq);
-	if (cmd == SIOCGHWTSTAMP)
-		return gfar_hwtstamp_get(dev, rq);
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_mii_ioctl(phydev, rq, cmd);
+	return 0;
 }
 
 /* Interrupt Handler for Transmit complete */
@@ -3174,7 +3151,7 @@ static const struct net_device_ops gfar_netdev_ops = {
 	.ndo_set_features = gfar_set_features,
 	.ndo_set_rx_mode = gfar_set_multi,
 	.ndo_tx_timeout = gfar_timeout,
-	.ndo_eth_ioctl = gfar_ioctl,
+	.ndo_eth_ioctl = phy_do_ioctl_running,
 	.ndo_get_stats64 = gfar_get_stats64,
 	.ndo_change_carrier = fixed_phy_change_carrier,
 	.ndo_set_mac_address = gfar_set_mac_addr,
@@ -3182,6 +3159,8 @@ static const struct net_device_ops gfar_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = gfar_netpoll,
 #endif
+	.ndo_hwtstamp_get = gfar_hwtstamp_get,
+	.ndo_hwtstamp_set = gfar_hwtstamp_set,
 };
 
 /* Set up the ethernet device structure, private data,
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index eae1a7595a69..3c1da0cf3f61 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -67,7 +67,7 @@ static const char gve_gstrings_tx_stats[][ETH_GSTRING_LEN] = {
 	"tx_xsk_sent[%u]", "tx_xdp_xmit[%u]", "tx_xdp_xmit_errors[%u]"
 };
 
-static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = {
+static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] __nonstring_array = {
 	"adminq_prod_cnt", "adminq_cmd_fail", "adminq_timeouts",
 	"adminq_describe_device_cnt", "adminq_cfg_device_resources_cnt",
 	"adminq_register_page_list_cnt", "adminq_unregister_page_list_cnt",
@@ -113,7 +113,7 @@ static void gve_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 						i);
 
 		for (i = 0; i < ARRAY_SIZE(gve_gstrings_adminq_stats); i++)
-			ethtool_puts(&s, gve_gstrings_adminq_stats[i]);
+			ethtool_cpy(&s, gve_gstrings_adminq_stats[i]);
 
 		break;
 
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 8aaac9101377..e1ffbd561fac 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -1830,7 +1830,7 @@ static void gve_turndown(struct gve_priv *priv)
 	/* Stop tx queues */
 	netif_tx_disable(priv->dev);
 
-	xdp_features_clear_redirect_target(priv->dev);
+	xdp_features_clear_redirect_target_locked(priv->dev);
 
 	gve_clear_napi_enabled(priv);
 	gve_clear_report_stats(priv);
@@ -1902,7 +1902,7 @@ static void gve_turnup(struct gve_priv *priv)
 	}
 
 	if (priv->tx_cfg.num_xdp_queues && gve_supports_xdp_xmit(priv))
-		xdp_features_set_redirect_target(priv->dev, false);
+		xdp_features_set_redirect_target_locked(priv->dev, false);
 
 	gve_set_napi_enabled(priv);
 }
@@ -2659,6 +2659,9 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto abort_with_wq;
 
+	if (!gve_is_gqi(priv) && !gve_is_qpl(priv))
+		dev->netmem_tx = true;
+
 	err = register_netdev(dev);
 	if (err)
 		goto abort_with_gve_init;
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index 2eba868d8037..a27f1574a733 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -660,7 +660,8 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx,
 			goto err;
 
 		dma_unmap_len_set(pkt, len[pkt->num_bufs], len);
-		dma_unmap_addr_set(pkt, dma[pkt->num_bufs], addr);
+		netmem_dma_unmap_addr_set(skb_frag_netmem(frag), pkt,
+					  dma[pkt->num_bufs], addr);
 		++pkt->num_bufs;
 
 		gve_tx_fill_pkt_desc_dqo(tx, desc_idx, skb, len, addr,
@@ -1038,8 +1039,9 @@ static void gve_unmap_packet(struct device *dev,
 	dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]),
 			 dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE);
 	for (i = 1; i < pkt->num_bufs; i++) {
-		dma_unmap_page(dev, dma_unmap_addr(pkt, dma[i]),
-			       dma_unmap_len(pkt, len[i]), DMA_TO_DEVICE);
+		netmem_dma_unmap_page_attrs(dev, dma_unmap_addr(pkt, dma[i]),
+					    dma_unmap_len(pkt, len[i]),
+					    DMA_TO_DEVICE, 0);
 	}
 	pkt->num_bufs = 0;
 }
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
index f8cdab62bf85..7725cb0c5c8a 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
@@ -108,14 +108,16 @@ struct hbg_irq_info {
 	bool re_enable;
 	bool need_print;
 	bool need_reset;
-	u64 count;
 
-	void (*irq_handle)(struct hbg_priv *priv, struct hbg_irq_info *info);
+	void (*irq_handle)(struct hbg_priv *priv,
+			   const struct hbg_irq_info *info);
 };
 
 struct hbg_vector {
 	char name[HBG_VECTOR_NUM][32];
-	struct hbg_irq_info *info_array;
+
+	u64 *stats_array;
+	const struct hbg_irq_info *info_array;
 	u32 info_array_len;
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
index 5e0ba4d5b08d..01ad82d2f5cc 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
@@ -61,7 +61,7 @@ static int hbg_dbg_irq_info(struct seq_file *s, void *unused)
 {
 	struct net_device *netdev = dev_get_drvdata(s->private);
 	struct hbg_priv *priv = netdev_priv(netdev);
-	struct hbg_irq_info *info;
+	const struct hbg_irq_info *info;
 	u32 i;
 
 	for (i = 0; i < priv->vectors.info_array_len; i++) {
@@ -73,7 +73,7 @@ static int hbg_dbg_irq_info(struct seq_file *s, void *unused)
 								info->mask)),
 			   str_true_false(info->need_reset),
 			   str_true_false(info->need_print),
-			   info->count);
+			   priv->vectors.stats_array[i]);
 	}
 
 	return 0;
@@ -106,6 +106,7 @@ static int hbg_dbg_nic_state(struct seq_file *s, void *unused)
 {
 	struct net_device *netdev = dev_get_drvdata(s->private);
 	struct hbg_priv *priv = netdev_priv(netdev);
+	bool np_link_fail;
 
 	seq_printf(s, "event handling state: %s\n",
 		   state_str_true_false(priv, HBG_NIC_STATE_EVENT_HANDLING));
@@ -117,8 +118,10 @@ static int hbg_dbg_nic_state(struct seq_file *s, void *unused)
 		   reset_type_str[priv->reset_type]);
 	seq_printf(s, "need reset state: %s\n",
 		   state_str_true_false(priv, HBG_NIC_STATE_NEED_RESET));
-	seq_printf(s, "np_link fail state: %s\n",
-		   state_str_true_false(priv, HBG_NIC_STATE_NP_LINK_FAIL));
+
+	np_link_fail = !hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR,
+					   HBG_REG_AN_NEG_STATE_NP_LINK_OK_B);
+	seq_printf(s, "np_link fail state: %s\n", str_true_false(np_link_fail));
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
index d61c03f34ff0..f23fb5920c3c 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
@@ -234,7 +234,7 @@ static u64 hbg_get_irq_stats(struct hbg_vector *vectors, u32 mask)
 
 	for (i = 0; i < vectors->info_array_len; i++)
 		if (vectors->info_array[i].mask == mask)
-			return vectors->info_array[i].count;
+			return vectors->stats_array[i];
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
index 4e8cb66f601c..ff3295b60a69 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
@@ -26,12 +26,15 @@ static void hbg_restore_mac_table(struct hbg_priv *priv)
 
 static void hbg_restore_user_def_settings(struct hbg_priv *priv)
 {
+	/* The index of host mac is always 0. */
+	u64 rx_pause_addr = ether_addr_to_u64(priv->filter.mac_table[0].addr);
 	struct ethtool_pauseparam *pause_param = &priv->user_def.pause_param;
 
 	hbg_restore_mac_table(priv);
 	hbg_hw_set_mtu(priv, priv->netdev->mtu);
 	hbg_hw_set_pause_enable(priv, pause_param->tx_pause,
 				pause_param->rx_pause);
+	hbg_hw_set_rx_pause_mac_addr(priv, rx_pause_addr);
 }
 
 int hbg_rebuild(struct hbg_priv *priv)
@@ -58,6 +61,8 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
 		return -EBUSY;
 	}
 
+	netif_device_detach(priv->netdev);
+
 	priv->reset_type = type;
 	set_bit(HBG_NIC_STATE_RESETTING, &priv->state);
 	clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
@@ -88,6 +93,8 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
 		return ret;
 	}
 
+	netif_device_attach(priv->netdev);
+
 	dev_info(&priv->pdev->dev, "reset done\n");
 	return ret;
 }
@@ -114,16 +121,13 @@ void hbg_err_reset(struct hbg_priv *priv)
 	if (running)
 		dev_close(priv->netdev);
 
-	hbg_reset(priv);
-
-	/* in hbg_pci_err_detected(), we will detach first,
-	 * so we need to attach before open
-	 */
-	if (!netif_device_present(priv->netdev))
-		netif_device_attach(priv->netdev);
+	if (hbg_reset(priv))
+		goto err_unlock;
 
 	if (running)
 		dev_open(priv->netdev, NULL);
+
+err_unlock:
 	rtnl_unlock();
 }
 
@@ -157,7 +161,6 @@ static pci_ers_result_t hbg_pci_err_slot_reset(struct pci_dev *pdev)
 	pci_save_state(pdev);
 
 	hbg_err_reset(priv);
-	netif_device_attach(netdev);
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
index 8f1107b85fbb..55520053270a 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
@@ -317,6 +317,9 @@ static void hbg_update_stats_by_info(struct hbg_priv *priv,
 	const struct hbg_ethtool_stats *stats;
 	u32 i;
 
+	if (test_bit(HBG_NIC_STATE_RESETTING, &priv->state))
+		return;
+
 	for (i = 0; i < info_len; i++) {
 		stats = &info[i];
 		if (!stats->reg)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
index 74a18033b444..9b65eef62b3f 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
@@ -234,6 +234,10 @@ void hbg_hw_set_mac_filter_enable(struct hbg_priv *priv, u32 enable)
 {
 	hbg_reg_write_field(priv, HBG_REG_REC_FILT_CTRL_ADDR,
 			    HBG_REG_REC_FILT_CTRL_UC_MATCH_EN_B, enable);
+
+	/* only uc filter is supported, so set all bits of mc mask reg to 1 */
+	hbg_reg_write64(priv, HBG_REG_STATION_ADDR_LOW_MSK_0, U64_MAX);
+	hbg_reg_write64(priv, HBG_REG_STATION_ADDR_LOW_MSK_1, U64_MAX);
 }
 
 void hbg_hw_set_pause_enable(struct hbg_priv *priv, u32 tx_en, u32 rx_en)
@@ -242,6 +246,9 @@ void hbg_hw_set_pause_enable(struct hbg_priv *priv, u32 tx_en, u32 rx_en)
 			    HBG_REG_PAUSE_ENABLE_TX_B, tx_en);
 	hbg_reg_write_field(priv, HBG_REG_PAUSE_ENABLE_ADDR,
 			    HBG_REG_PAUSE_ENABLE_RX_B, rx_en);
+
+	hbg_reg_write_field(priv, HBG_REG_REC_FILT_CTRL_ADDR,
+			    HBG_REG_REC_FILT_CTRL_PAUSE_FRM_PASS_B, rx_en);
 }
 
 void hbg_hw_get_pause_enable(struct hbg_priv *priv, u32 *tx_en, u32 *rx_en)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
index e79e9ab3e530..8af0bc4cca21 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
@@ -6,7 +6,7 @@
 #include "hbg_hw.h"
 
 static void hbg_irq_handle_err(struct hbg_priv *priv,
-			       struct hbg_irq_info *irq_info)
+			       const struct hbg_irq_info *irq_info)
 {
 	if (irq_info->need_print)
 		dev_err(&priv->pdev->dev,
@@ -17,30 +17,30 @@ static void hbg_irq_handle_err(struct hbg_priv *priv,
 }
 
 static void hbg_irq_handle_tx(struct hbg_priv *priv,
-			      struct hbg_irq_info *irq_info)
+			      const struct hbg_irq_info *irq_info)
 {
 	napi_schedule(&priv->tx_ring.napi);
 }
 
 static void hbg_irq_handle_rx(struct hbg_priv *priv,
-			      struct hbg_irq_info *irq_info)
+			      const struct hbg_irq_info *irq_info)
 {
 	napi_schedule(&priv->rx_ring.napi);
 }
 
 static void hbg_irq_handle_rx_buf_val(struct hbg_priv *priv,
-				      struct hbg_irq_info *irq_info)
+				      const struct hbg_irq_info *irq_info)
 {
 	priv->stats.rx_fifo_less_empty_thrsld_cnt++;
 }
 
 #define HBG_IRQ_I(name, handle) \
-	{#name, HBG_INT_MSK_##name##_B, false, false, false, 0, handle}
+	{#name, HBG_INT_MSK_##name##_B, false, false, false, handle}
 #define HBG_ERR_IRQ_I(name, need_print, ndde_reset) \
 	{#name, HBG_INT_MSK_##name##_B, true, need_print, \
-	ndde_reset, 0, hbg_irq_handle_err}
+	ndde_reset, hbg_irq_handle_err}
 
-static struct hbg_irq_info hbg_irqs[] = {
+static const struct hbg_irq_info hbg_irqs[] = {
 	HBG_IRQ_I(RX, hbg_irq_handle_rx),
 	HBG_IRQ_I(TX, hbg_irq_handle_tx),
 	HBG_ERR_IRQ_I(TX_PKT_CPL, true, true),
@@ -64,7 +64,7 @@ static struct hbg_irq_info hbg_irqs[] = {
 
 static irqreturn_t hbg_irq_handle(int irq_num, void *p)
 {
-	struct hbg_irq_info *info;
+	const struct hbg_irq_info *info;
 	struct hbg_priv *priv = p;
 	u32 status;
 	u32 i;
@@ -79,7 +79,7 @@ static irqreturn_t hbg_irq_handle(int irq_num, void *p)
 			hbg_hw_irq_enable(priv, info->mask, false);
 			hbg_hw_irq_clear(priv, info->mask);
 
-			info->count++;
+			priv->vectors.stats_array[i]++;
 			if (info->irq_handle)
 				info->irq_handle(priv, info);
 
@@ -132,6 +132,12 @@ int hbg_irq_init(struct hbg_priv *priv)
 					     irq_names_map[i]);
 	}
 
+	vectors->stats_array = devm_kcalloc(&priv->pdev->dev,
+					    ARRAY_SIZE(hbg_irqs),
+					    sizeof(u64), GFP_KERNEL);
+	if (!vectors->stats_array)
+		return -ENOMEM;
+
 	vectors->info_array = hbg_irqs;
 	vectors->info_array_len = ARRAY_SIZE(hbg_irqs);
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
index 2ac5454338e4..2e64dc1ab355 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
@@ -21,7 +21,7 @@
 
 static void hbg_all_irq_enable(struct hbg_priv *priv, bool enabled)
 {
-	struct hbg_irq_info *info;
+	const struct hbg_irq_info *info;
 	u32 i;
 
 	for (i = 0; i < priv->vectors.info_array_len; i++) {
@@ -203,12 +203,12 @@ static int hbg_net_change_mtu(struct net_device *netdev, int new_mtu)
 	if (netif_running(netdev))
 		return -EBUSY;
 
-	hbg_hw_set_mtu(priv, new_mtu);
-	WRITE_ONCE(netdev->mtu, new_mtu);
-
 	dev_dbg(&priv->pdev->dev,
 		"change mtu from %u to %u\n", netdev->mtu, new_mtu);
 
+	hbg_hw_set_mtu(priv, new_mtu);
+	WRITE_ONCE(netdev->mtu, new_mtu);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
index f29a937ad087..42b0083c9193 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
@@ -2,6 +2,7 @@
 // Copyright (c) 2024 Hisilicon Limited.
 
 #include <linux/phy.h>
+#include <linux/rtnetlink.h>
 #include "hbg_common.h"
 #include "hbg_hw.h"
 #include "hbg_mdio.h"
@@ -133,12 +134,17 @@ void hbg_fix_np_link_fail(struct hbg_priv *priv)
 {
 	struct device *dev = &priv->pdev->dev;
 
+	rtnl_lock();
+
 	if (priv->stats.np_link_fail_cnt >= HBG_NP_LINK_FAIL_RETRY_TIMES) {
 		dev_err(dev, "failed to fix the MAC link status\n");
 		priv->stats.np_link_fail_cnt = 0;
-		return;
+		goto unlock;
 	}
 
+	if (!priv->mac.phydev->link)
+		goto unlock;
+
 	priv->stats.np_link_fail_cnt++;
 	dev_err(dev, "failed to link between MAC and PHY, try to fix...\n");
 
@@ -147,6 +153,9 @@ void hbg_fix_np_link_fail(struct hbg_priv *priv)
 	 */
 	hbg_phy_stop(priv);
 	hbg_phy_start(priv);
+
+unlock:
+	rtnl_unlock();
 }
 
 static void hbg_phy_adjust_link(struct net_device *netdev)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
index cc2cc612770d..a6e7f5e62b48 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
@@ -68,6 +68,7 @@
 #define HBG_REG_TRANSMIT_CTRL_AN_EN_B		BIT(5)
 #define HBG_REG_REC_FILT_CTRL_ADDR		(HBG_REG_SGMII_BASE + 0x0064)
 #define HBG_REG_REC_FILT_CTRL_UC_MATCH_EN_B	BIT(0)
+#define HBG_REG_REC_FILT_CTRL_PAUSE_FRM_PASS_B	BIT(4)
 #define HBG_REG_RX_OCTETS_TOTAL_OK_ADDR		(HBG_REG_SGMII_BASE + 0x0080)
 #define HBG_REG_RX_OCTETS_BAD_ADDR		(HBG_REG_SGMII_BASE + 0x0084)
 #define HBG_REG_RX_UC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0088)
@@ -134,6 +135,8 @@
 #define HBG_REG_STATION_ADDR_HIGH_4_ADDR	(HBG_REG_SGMII_BASE + 0x0224)
 #define HBG_REG_STATION_ADDR_LOW_5_ADDR		(HBG_REG_SGMII_BASE + 0x0228)
 #define HBG_REG_STATION_ADDR_HIGH_5_ADDR	(HBG_REG_SGMII_BASE + 0x022C)
+#define HBG_REG_STATION_ADDR_LOW_MSK_0		(HBG_REG_SGMII_BASE + 0x0230)
+#define HBG_REG_STATION_ADDR_LOW_MSK_1		(HBG_REG_SGMII_BASE + 0x0238)
 
 /* PCU */
 #define HBG_REG_TX_FIFO_THRSLD_ADDR		(HBG_REG_SGMII_BASE + 0x0420)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 09749e9f7398..4e5d8bc39a1b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -61,7 +61,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
 		.name = "tm_qset",
 		.cmd = HNAE3_DBG_CMD_TM_QSET,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
+		.buf_len = HNS3_DBG_READ_LEN_1MB,
 		.init = hns3_dbg_common_file_init,
 	},
 	{
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 9ff797fb36c4..b03b8758c777 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -473,20 +473,14 @@ static void hns3_mask_vector_irq(struct hns3_enet_tqp_vector *tqp_vector,
 	writel(mask_en, tqp_vector->mask_addr);
 }
 
-static void hns3_vector_enable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_enable(struct hns3_enet_tqp_vector *tqp_vector)
 {
 	napi_enable(&tqp_vector->napi);
 	enable_irq(tqp_vector->vector_irq);
-
-	/* enable vector */
-	hns3_mask_vector_irq(tqp_vector, 1);
 }
 
-static void hns3_vector_disable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_disable(struct hns3_enet_tqp_vector *tqp_vector)
 {
-	/* disable vector */
-	hns3_mask_vector_irq(tqp_vector, 0);
-
 	disable_irq(tqp_vector->vector_irq);
 	napi_disable(&tqp_vector->napi);
 	cancel_work_sync(&tqp_vector->rx_group.dim.work);
@@ -707,11 +701,42 @@ static int hns3_set_rx_cpu_rmap(struct net_device *netdev)
 	return 0;
 }
 
+static void hns3_enable_irqs_and_tqps(struct net_device *netdev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = priv->ae_handle;
+	u16 i;
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_irq_enable(&priv->tqp_vector[i]);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_mask_vector_irq(&priv->tqp_vector[i], 1);
+
+	for (i = 0; i < h->kinfo.num_tqps; i++)
+		hns3_tqp_enable(h->kinfo.tqp[i]);
+}
+
+static void hns3_disable_irqs_and_tqps(struct net_device *netdev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = priv->ae_handle;
+	u16 i;
+
+	for (i = 0; i < h->kinfo.num_tqps; i++)
+		hns3_tqp_disable(h->kinfo.tqp[i]);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_mask_vector_irq(&priv->tqp_vector[i], 0);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_irq_disable(&priv->tqp_vector[i]);
+}
+
 static int hns3_nic_net_up(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = priv->ae_handle;
-	int i, j;
 	int ret;
 
 	ret = hns3_nic_reset_all_ring(h);
@@ -720,23 +745,13 @@ static int hns3_nic_net_up(struct net_device *netdev)
 
 	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
-	/* enable the vectors */
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_enable(&priv->tqp_vector[i]);
-
-	/* enable rcb */
-	for (j = 0; j < h->kinfo.num_tqps; j++)
-		hns3_tqp_enable(h->kinfo.tqp[j]);
+	hns3_enable_irqs_and_tqps(netdev);
 
 	/* start the ae_dev */
 	ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0;
 	if (ret) {
 		set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
-		while (j--)
-			hns3_tqp_disable(h->kinfo.tqp[j]);
-
-		for (j = i - 1; j >= 0; j--)
-			hns3_vector_disable(&priv->tqp_vector[j]);
+		hns3_disable_irqs_and_tqps(netdev);
 	}
 
 	return ret;
@@ -823,17 +838,9 @@ static void hns3_reset_tx_queue(struct hnae3_handle *h)
 static void hns3_nic_net_down(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = hns3_get_handle(netdev);
 	const struct hnae3_ae_ops *ops;
-	int i;
 
-	/* disable vectors */
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_disable(&priv->tqp_vector[i]);
-
-	/* disable rcb */
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_disable(h->kinfo.tqp[i]);
+	hns3_disable_irqs_and_tqps(netdev);
 
 	/* stop ae_dev */
 	ops = priv->ae_handle->ae_algo->ops;
@@ -5864,8 +5871,6 @@ int hns3_set_channels(struct net_device *netdev,
 void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
 {
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
-	struct hnae3_handle *h = priv->ae_handle;
-	int i;
 
 	if (!if_running)
 		return;
@@ -5876,11 +5881,7 @@ void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
 	netif_carrier_off(ndev);
 	netif_tx_disable(ndev);
 
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_disable(&priv->tqp_vector[i]);
-
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_disable(h->kinfo.tqp[i]);
+	hns3_disable_irqs_and_tqps(ndev);
 
 	/* delay ring buffer clearing to hns3_reset_notify_uninit_enet
 	 * during reset process, because driver may not be able
@@ -5896,7 +5897,6 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
 {
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
 	struct hnae3_handle *h = priv->ae_handle;
-	int i;
 
 	if (!if_running)
 		return;
@@ -5912,11 +5912,7 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
 
 	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_enable(&priv->tqp_vector[i]);
-
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_enable(h->kinfo.tqp[i]);
+	hns3_enable_irqs_and_tqps(ndev);
 
 	netif_tx_wake_all_queues(ndev);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index 59cc9221185f..ec581d4b696f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -440,6 +440,13 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
 	ptp->info.settime64 = hclge_ptp_settime;
 
 	ptp->info.n_alarm = 0;
+
+	spin_lock_init(&ptp->lock);
+	ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
+	ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+	ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
+	hdev->ptp = ptp;
+
 	ptp->clock = ptp_clock_register(&ptp->info, &hdev->pdev->dev);
 	if (IS_ERR(ptp->clock)) {
 		dev_err(&hdev->pdev->dev,
@@ -451,12 +458,6 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
 		return -ENODEV;
 	}
 
-	spin_lock_init(&ptp->lock);
-	ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
-	ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
-	ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
-	hdev->ptp = ptp;
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 9ba767740a04..dada42e7e0ec 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1292,9 +1292,8 @@ static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev)
 	rtnl_unlock();
 }
 
-static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+static int hclgevf_en_hw_strip_rxvtag_cmd(struct hclgevf_dev *hdev, bool enable)
 {
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	struct hclge_vf_to_pf_msg send_msg;
 
 	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN,
@@ -1303,6 +1302,19 @@ static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 	return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
 }
 
+static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int ret;
+
+	ret = hclgevf_en_hw_strip_rxvtag_cmd(hdev, enable);
+	if (ret)
+		return ret;
+
+	hdev->rxvtag_strip_en = enable;
+	return 0;
+}
+
 static int hclgevf_reset_tqp(struct hnae3_handle *handle)
 {
 #define HCLGEVF_RESET_ALL_QUEUE_DONE	1U
@@ -2204,12 +2216,13 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
 					  tc_valid, tc_size);
 }
 
-static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
+static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev,
+				    bool rxvtag_strip_en)
 {
 	struct hnae3_handle *nic = &hdev->nic;
 	int ret;
 
-	ret = hclgevf_en_hw_strip_rxvtag(nic, true);
+	ret = hclgevf_en_hw_strip_rxvtag(nic, rxvtag_strip_en);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to enable rx vlan offload, ret = %d\n", ret);
@@ -2879,7 +2892,7 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 	if (ret)
 		return ret;
 
-	ret = hclgevf_init_vlan_config(hdev);
+	ret = hclgevf_init_vlan_config(hdev, hdev->rxvtag_strip_en);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed(%d) to initialize VLAN config\n", ret);
@@ -2994,7 +3007,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_config;
 	}
 
-	ret = hclgevf_init_vlan_config(hdev);
+	ret = hclgevf_init_vlan_config(hdev, true);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed(%d) to initialize VLAN config\n", ret);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index cccef3228461..0208425ab594 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -253,6 +253,7 @@ struct hclgevf_dev {
 	int *vector_irq;
 
 	bool gro_en;
+	bool rxvtag_strip_en;
 
 	unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
 
diff --git a/drivers/net/ethernet/huawei/Kconfig b/drivers/net/ethernet/huawei/Kconfig
index c05fce15eb51..7d0feb1da158 100644
--- a/drivers/net/ethernet/huawei/Kconfig
+++ b/drivers/net/ethernet/huawei/Kconfig
@@ -16,5 +16,6 @@ config NET_VENDOR_HUAWEI
 if NET_VENDOR_HUAWEI
 
 source "drivers/net/ethernet/huawei/hinic/Kconfig"
+source "drivers/net/ethernet/huawei/hinic3/Kconfig"
 
 endif # NET_VENDOR_HUAWEI
diff --git a/drivers/net/ethernet/huawei/Makefile b/drivers/net/ethernet/huawei/Makefile
index 2549ad5afe6d..59865b882879 100644
--- a/drivers/net/ethernet/huawei/Makefile
+++ b/drivers/net/ethernet/huawei/Makefile
@@ -4,3 +4,4 @@
 #
 
 obj-$(CONFIG_HINIC) += hinic/
+obj-$(CONFIG_HINIC3) += hinic3/
diff --git a/drivers/net/ethernet/huawei/hinic3/Kconfig b/drivers/net/ethernet/huawei/hinic3/Kconfig
new file mode 100644
index 000000000000..ce4331d1387b
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/Kconfig
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Huawei driver configuration
+#
+
+config HINIC3
+	tristate "Huawei 3rd generation network adapters (HINIC3) support"
+	# Fields of HW and management structures are little endian and are
+	# currently not converted
+	depends on !CPU_BIG_ENDIAN
+	depends on X86 || ARM64 || COMPILE_TEST
+	depends on PCI_MSI && 64BIT
+	select AUXILIARY_BUS
+	select PAGE_POOL
+	help
+	  This driver supports HiNIC 3rd gen Network Adapter (HINIC3).
+	  The driver is supported on X86_64 and ARM64 little endian.
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called hinic3.
diff --git a/drivers/net/ethernet/huawei/hinic3/Makefile b/drivers/net/ethernet/huawei/hinic3/Makefile
new file mode 100644
index 000000000000..509dfbfb0e96
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/Makefile
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+obj-$(CONFIG_HINIC3) += hinic3.o
+
+hinic3-objs := hinic3_common.o \
+	       hinic3_hw_cfg.o \
+	       hinic3_hw_comm.o \
+	       hinic3_hwdev.o \
+	       hinic3_hwif.o \
+	       hinic3_irq.o \
+	       hinic3_lld.o \
+	       hinic3_main.o \
+	       hinic3_mbox.o \
+	       hinic3_netdev_ops.o \
+	       hinic3_nic_cfg.o \
+	       hinic3_nic_io.o \
+	       hinic3_queue_common.o \
+	       hinic3_rx.o \
+	       hinic3_tx.o \
+	       hinic3_wq.o
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_common.c b/drivers/net/ethernet/huawei/hinic3/hinic3_common.c
new file mode 100644
index 000000000000..0aa42068728c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_common.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+
+#include "hinic3_common.h"
+
+int hinic3_dma_zalloc_coherent_align(struct device *dev, u32 size, u32 align,
+				     gfp_t flag,
+				     struct hinic3_dma_addr_align *mem_align)
+{
+	dma_addr_t paddr, align_paddr;
+	void *vaddr, *align_vaddr;
+	u32 real_size = size;
+
+	vaddr = dma_alloc_coherent(dev, real_size, &paddr, flag);
+	if (!vaddr)
+		return -ENOMEM;
+
+	align_paddr = ALIGN(paddr, align);
+	if (align_paddr == paddr) {
+		align_vaddr = vaddr;
+		goto out;
+	}
+
+	dma_free_coherent(dev, real_size, vaddr, paddr);
+
+	/* realloc memory for align */
+	real_size = size + align;
+	vaddr = dma_alloc_coherent(dev, real_size, &paddr, flag);
+	if (!vaddr)
+		return -ENOMEM;
+
+	align_paddr = ALIGN(paddr, align);
+	align_vaddr = vaddr + (align_paddr - paddr);
+
+out:
+	mem_align->real_size = real_size;
+	mem_align->ori_vaddr = vaddr;
+	mem_align->ori_paddr = paddr;
+	mem_align->align_vaddr = align_vaddr;
+	mem_align->align_paddr = align_paddr;
+
+	return 0;
+}
+
+void hinic3_dma_free_coherent_align(struct device *dev,
+				    struct hinic3_dma_addr_align *mem_align)
+{
+	dma_free_coherent(dev, mem_align->real_size,
+			  mem_align->ori_vaddr, mem_align->ori_paddr);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_common.h b/drivers/net/ethernet/huawei/hinic3/hinic3_common.h
new file mode 100644
index 000000000000..bb795dace04c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_common.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_COMMON_H_
+#define _HINIC3_COMMON_H_
+
+#include <linux/device.h>
+
+#define HINIC3_MIN_PAGE_SIZE  0x1000
+
+struct hinic3_dma_addr_align {
+	u32        real_size;
+
+	void       *ori_vaddr;
+	dma_addr_t ori_paddr;
+
+	void       *align_vaddr;
+	dma_addr_t align_paddr;
+};
+
+int hinic3_dma_zalloc_coherent_align(struct device *dev, u32 size, u32 align,
+				     gfp_t flag,
+				     struct hinic3_dma_addr_align *mem_align);
+void hinic3_dma_free_coherent_align(struct device *dev,
+				    struct hinic3_dma_addr_align *mem_align);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c
new file mode 100644
index 000000000000..87d9450c30ca
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/device.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+bool hinic3_support_nic(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.supp_svcs_bitmap &
+	       BIT(HINIC3_SERVICE_T_NIC);
+}
+
+u16 hinic3_func_max_qnum(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.nic_svc_cap.max_sqs;
+}
+
+u8 hinic3_physical_port_id(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.port_id;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h
new file mode 100644
index 000000000000..e017b1ae9f05
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_CFG_H_
+#define _HINIC3_HW_CFG_H_
+
+#include <linux/mutex.h>
+#include <linux/pci.h>
+
+struct hinic3_hwdev;
+
+struct hinic3_irq {
+	u32  irq_id;
+	u16  msix_entry_idx;
+	bool allocated;
+};
+
+struct hinic3_irq_info {
+	struct hinic3_irq *irq;
+	u16               num_irq;
+	/* device max irq number */
+	u16               num_irq_hw;
+	/* protect irq alloc and free */
+	struct mutex      irq_mutex;
+};
+
+struct hinic3_nic_service_cap {
+	u16 max_sqs;
+};
+
+/* Device capabilities */
+struct hinic3_dev_cap {
+	/* Bitmasks of services supported by device */
+	u16                           supp_svcs_bitmap;
+	/* Physical port */
+	u8                            port_id;
+	struct hinic3_nic_service_cap nic_svc_cap;
+};
+
+struct hinic3_cfg_mgmt_info {
+	struct hinic3_irq_info irq_info;
+	struct hinic3_dev_cap  cap;
+};
+
+int hinic3_alloc_irqs(struct hinic3_hwdev *hwdev, u16 num,
+		      struct msix_entry *alloc_arr, u16 *act_num);
+void hinic3_free_irq(struct hinic3_hwdev *hwdev, u32 irq_id);
+
+bool hinic3_support_nic(struct hinic3_hwdev *hwdev);
+u16 hinic3_func_max_qnum(struct hinic3_hwdev *hwdev);
+u8 hinic3_physical_port_id(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c
new file mode 100644
index 000000000000..434696ce7dc2
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+int hinic3_func_reset(struct hinic3_hwdev *hwdev, u16 func_id, u64 reset_flag)
+{
+	struct comm_cmd_func_reset func_reset = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	func_reset.func_id = func_id;
+	func_reset.reset_flag = reset_flag;
+
+	mgmt_msg_params_init_default(&msg_params, &func_reset,
+				     sizeof(func_reset));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_FUNC_RESET, &msg_params);
+	if (err || func_reset.head.status) {
+		dev_err(hwdev->dev, "Failed to reset func resources, reset_flag 0x%llx, err: %d, status: 0x%x\n",
+			reset_flag, err, func_reset.head.status);
+		return -EIO;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h
new file mode 100644
index 000000000000..c33a1c77da9c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_COMM_H_
+#define _HINIC3_HW_COMM_H_
+
+#include "hinic3_hw_intf.h"
+
+struct hinic3_hwdev;
+
+int hinic3_func_reset(struct hinic3_hwdev *hwdev, u16 func_id, u64 reset_flag);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h
new file mode 100644
index 000000000000..22c84093efa2
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_INTF_H_
+#define _HINIC3_HW_INTF_H_
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+#define MGMT_MSG_CMD_OP_SET   1
+#define MGMT_MSG_CMD_OP_GET   0
+
+#define MGMT_STATUS_PF_SET_VF_ALREADY  0x4
+#define MGMT_STATUS_EXIST              0x6
+#define MGMT_STATUS_CMD_UNSUPPORTED    0xFF
+
+#define MGMT_MSG_POLLING_TIMEOUT 0
+
+struct mgmt_msg_head {
+	u8 status;
+	u8 version;
+	u8 rsvd0[6];
+};
+
+struct mgmt_msg_params {
+	const void  *buf_in;
+	u32         in_size;
+	void        *buf_out;
+	u32         expected_out_size;
+	u32         timeout_ms;
+};
+
+/* CMDQ MODULE_TYPE */
+enum mgmt_mod_type {
+	/* HW communication module */
+	MGMT_MOD_COMM   = 0,
+	/* L2NIC module */
+	MGMT_MOD_L2NIC  = 1,
+	/* Configuration module */
+	MGMT_MOD_CFGM   = 7,
+	MGMT_MOD_HILINK = 14,
+};
+
+static inline void mgmt_msg_params_init_default(struct mgmt_msg_params *msg_params,
+						void *inout_buf, u32 buf_size)
+{
+	msg_params->buf_in = inout_buf;
+	msg_params->buf_out = inout_buf;
+	msg_params->in_size = buf_size;
+	msg_params->expected_out_size = buf_size;
+	msg_params->timeout_ms = 0;
+}
+
+/* COMM Commands between Driver to fw */
+enum comm_cmd {
+	/* Commands for clearing FLR and resources */
+	COMM_CMD_FUNC_RESET              = 0,
+	COMM_CMD_FEATURE_NEGO            = 1,
+	COMM_CMD_FLUSH_DOORBELL          = 2,
+	COMM_CMD_START_FLUSH             = 3,
+	COMM_CMD_GET_GLOBAL_ATTR         = 5,
+	COMM_CMD_SET_FUNC_SVC_USED_STATE = 7,
+
+	/* Driver Configuration Commands */
+	COMM_CMD_SET_CMDQ_CTXT           = 20,
+	COMM_CMD_SET_VAT                 = 21,
+	COMM_CMD_CFG_PAGESIZE            = 22,
+	COMM_CMD_CFG_MSIX_CTRL_REG       = 23,
+	COMM_CMD_SET_CEQ_CTRL_REG        = 24,
+	COMM_CMD_SET_DMA_ATTR            = 25,
+};
+
+enum comm_func_reset_bits {
+	COMM_FUNC_RESET_BIT_FLUSH        = BIT(0),
+	COMM_FUNC_RESET_BIT_MQM          = BIT(1),
+	COMM_FUNC_RESET_BIT_SMF          = BIT(2),
+	COMM_FUNC_RESET_BIT_PF_BW_CFG    = BIT(3),
+
+	COMM_FUNC_RESET_BIT_COMM         = BIT(10),
+	/* clear mbox and aeq, The COMM_FUNC_RESET_BIT_COMM bit must be set */
+	COMM_FUNC_RESET_BIT_COMM_MGMT_CH = BIT(11),
+	/* clear cmdq and ceq, The COMM_FUNC_RESET_BIT_COMM bit must be set */
+	COMM_FUNC_RESET_BIT_COMM_CMD_CH  = BIT(12),
+	COMM_FUNC_RESET_BIT_NIC          = BIT(13),
+};
+
+struct comm_cmd_func_reset {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u16                  rsvd1[3];
+	u64                  reset_flag;
+};
+
+#define COMM_MAX_FEATURE_QWORD  4
+struct comm_cmd_feature_nego {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u8                   opcode;
+	u8                   rsvd;
+	u64                  s_feature[COMM_MAX_FEATURE_QWORD];
+};
+
+/* Services supported by HW. HW uses these values when delivering events.
+ * HW supports multiple services that are not yet supported by driver
+ * (e.g. RoCE).
+ */
+enum hinic3_service_type {
+	HINIC3_SERVICE_T_NIC = 0,
+	/* MAX is only used by SW for array sizes. */
+	HINIC3_SERVICE_T_MAX = 1,
+};
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c
new file mode 100644
index 000000000000..6e8788a64925
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+#include "hinic3_mgmt.h"
+
+int hinic3_init_hwdev(struct pci_dev *pdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+void hinic3_free_hwdev(struct hinic3_hwdev *hwdev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
+
+void hinic3_set_api_stop(struct hinic3_hwdev *hwdev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h
new file mode 100644
index 000000000000..62e2745e9316
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HWDEV_H_
+#define _HINIC3_HWDEV_H_
+
+#include <linux/auxiliary_bus.h>
+#include <linux/pci.h>
+
+#include "hinic3_hw_intf.h"
+
+struct hinic3_cmdqs;
+struct hinic3_hwif;
+
+enum hinic3_event_service_type {
+	HINIC3_EVENT_SRV_COMM = 0,
+	HINIC3_EVENT_SRV_NIC  = 1
+};
+
+#define HINIC3_SRV_EVENT_TYPE(svc, type)    (((svc) << 16) | (type))
+
+/* driver-specific data of pci_dev */
+struct hinic3_pcidev {
+	struct pci_dev       *pdev;
+	struct hinic3_hwdev  *hwdev;
+	/* Auxiliary devices */
+	struct hinic3_adev   *hadev[HINIC3_SERVICE_T_MAX];
+
+	void __iomem         *cfg_reg_base;
+	void __iomem         *intr_reg_base;
+	void __iomem         *db_base;
+	u64                  db_dwqe_len;
+	u64                  db_base_phy;
+
+	/* lock for attach/detach uld */
+	struct mutex         pdev_mutex;
+	unsigned long        state;
+};
+
+struct hinic3_hwdev {
+	struct hinic3_pcidev        *adapter;
+	struct pci_dev              *pdev;
+	struct device               *dev;
+	int                         dev_id;
+	struct hinic3_hwif          *hwif;
+	struct hinic3_cfg_mgmt_info *cfg_mgmt;
+	struct hinic3_aeqs          *aeqs;
+	struct hinic3_ceqs          *ceqs;
+	struct hinic3_mbox          *mbox;
+	struct hinic3_cmdqs         *cmdqs;
+	struct workqueue_struct     *workq;
+	/* protect channel init and uninit */
+	spinlock_t                  channel_lock;
+	u64                         features[COMM_MAX_FEATURE_QWORD];
+	u32                         wq_page_size;
+	u8                          max_cmdq;
+	ulong                       func_state;
+};
+
+struct hinic3_event_info {
+	/* enum hinic3_event_service_type */
+	u16 service;
+	u16 type;
+	u8  event_data[104];
+};
+
+struct hinic3_adev {
+	struct auxiliary_device  adev;
+	struct hinic3_hwdev      *hwdev;
+	enum hinic3_service_type svc_type;
+
+	void (*event)(struct auxiliary_device *adev,
+		      struct hinic3_event_info *event);
+};
+
+int hinic3_init_hwdev(struct pci_dev *pdev);
+void hinic3_free_hwdev(struct hinic3_hwdev *hwdev);
+
+void hinic3_set_api_stop(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c
new file mode 100644
index 000000000000..0865453bf0e7
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/bitfield.h>
+#include <linux/device.h>
+#include <linux/io.h>
+
+#include "hinic3_common.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+
+void hinic3_set_msix_state(struct hinic3_hwdev *hwdev, u16 msix_idx,
+			   enum hinic3_msix_state flag)
+{
+	/* Completed by later submission due to LoC limit. */
+}
+
+u16 hinic3_global_func_id(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->hwif->attr.func_global_idx;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h
new file mode 100644
index 000000000000..513c9680e6b6
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HWIF_H_
+#define _HINIC3_HWIF_H_
+
+#include <linux/build_bug.h>
+#include <linux/spinlock_types.h>
+
+struct hinic3_hwdev;
+
+enum hinic3_func_type {
+	HINIC3_FUNC_TYPE_VF = 1,
+};
+
+struct hinic3_db_area {
+	unsigned long *db_bitmap_array;
+	u32           db_max_areas;
+	/* protect doorbell area alloc and free */
+	spinlock_t    idx_lock;
+};
+
+struct hinic3_func_attr {
+	enum hinic3_func_type func_type;
+	u16                   func_global_idx;
+	u16                   global_vf_id_of_pf;
+	u16                   num_irqs;
+	u16                   num_sq;
+	u8                    port_to_port_idx;
+	u8                    pci_intf_idx;
+	u8                    ppf_idx;
+	u8                    num_aeqs;
+	u8                    num_ceqs;
+	u8                    msix_flex_en;
+};
+
+static_assert(sizeof(struct hinic3_func_attr) == 20);
+
+struct hinic3_hwif {
+	u8 __iomem              *cfg_regs_base;
+	u64                     db_base_phy;
+	u64                     db_dwqe_len;
+	u8 __iomem              *db_base;
+	struct hinic3_db_area   db_area;
+	struct hinic3_func_attr attr;
+};
+
+enum hinic3_msix_state {
+	HINIC3_MSIX_ENABLE,
+	HINIC3_MSIX_DISABLE,
+};
+
+void hinic3_set_msix_state(struct hinic3_hwdev *hwdev, u16 msix_idx,
+			   enum hinic3_msix_state flag);
+
+u16 hinic3_global_func_id(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c
new file mode 100644
index 000000000000..8b92eed25edf
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/netdevice.h>
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+static int hinic3_poll(struct napi_struct *napi, int budget)
+{
+	struct hinic3_irq_cfg *irq_cfg =
+		container_of(napi, struct hinic3_irq_cfg, napi);
+	struct hinic3_nic_dev *nic_dev;
+	bool busy = false;
+	int work_done;
+
+	nic_dev = netdev_priv(irq_cfg->netdev);
+
+	busy |= hinic3_tx_poll(irq_cfg->txq, budget);
+
+	if (unlikely(!budget))
+		return 0;
+
+	work_done = hinic3_rx_poll(irq_cfg->rxq, budget);
+	busy |= work_done >= budget;
+
+	if (busy)
+		return budget;
+
+	if (likely(napi_complete_done(napi, work_done)))
+		hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx,
+				      HINIC3_MSIX_ENABLE);
+
+	return work_done;
+}
+
+void qp_add_napi(struct hinic3_irq_cfg *irq_cfg)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(irq_cfg->netdev);
+
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_RX, &irq_cfg->napi);
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_TX, &irq_cfg->napi);
+	netif_napi_add(nic_dev->netdev, &irq_cfg->napi, hinic3_poll);
+	napi_enable(&irq_cfg->napi);
+}
+
+void qp_del_napi(struct hinic3_irq_cfg *irq_cfg)
+{
+	napi_disable(&irq_cfg->napi);
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_RX, NULL);
+	netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id,
+			     NETDEV_QUEUE_TYPE_TX, NULL);
+	netif_stop_subqueue(irq_cfg->netdev, irq_cfg->irq_id);
+	netif_napi_del(&irq_cfg->napi);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c
new file mode 100644
index 000000000000..4827326e6a59
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c
@@ -0,0 +1,414 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+#include <linux/iopoll.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_lld.h"
+#include "hinic3_mgmt.h"
+
+#define HINIC3_VF_PCI_CFG_REG_BAR  0
+#define HINIC3_PCI_INTR_REG_BAR    2
+#define HINIC3_PCI_DB_BAR          4
+
+#define HINIC3_EVENT_POLL_SLEEP_US   1000
+#define HINIC3_EVENT_POLL_TIMEOUT_US 10000000
+
+static struct hinic3_adev_device {
+	const char *name;
+} hinic3_adev_devices[HINIC3_SERVICE_T_MAX] = {
+	[HINIC3_SERVICE_T_NIC] = {
+		.name = "nic",
+	},
+};
+
+static bool hinic3_adev_svc_supported(struct hinic3_hwdev *hwdev,
+				      enum hinic3_service_type svc_type)
+{
+	switch (svc_type) {
+	case HINIC3_SERVICE_T_NIC:
+		return hinic3_support_nic(hwdev);
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static void hinic3_comm_adev_release(struct device *dev)
+{
+	struct hinic3_adev *hadev = container_of(dev, struct hinic3_adev,
+						 adev.dev);
+
+	kfree(hadev);
+}
+
+static struct hinic3_adev *hinic3_add_one_adev(struct hinic3_hwdev *hwdev,
+					       enum hinic3_service_type svc_type)
+{
+	struct hinic3_adev *hadev;
+	const char *svc_name;
+	int ret;
+
+	hadev = kzalloc(sizeof(*hadev), GFP_KERNEL);
+	if (!hadev)
+		return NULL;
+
+	svc_name = hinic3_adev_devices[svc_type].name;
+	hadev->adev.name = svc_name;
+	hadev->adev.id = hwdev->dev_id;
+	hadev->adev.dev.parent = hwdev->dev;
+	hadev->adev.dev.release = hinic3_comm_adev_release;
+	hadev->svc_type = svc_type;
+	hadev->hwdev = hwdev;
+
+	ret = auxiliary_device_init(&hadev->adev);
+	if (ret) {
+		dev_err(hwdev->dev, "failed init adev %s %u\n",
+			svc_name, hwdev->dev_id);
+		kfree(hadev);
+		return NULL;
+	}
+
+	ret = auxiliary_device_add(&hadev->adev);
+	if (ret) {
+		dev_err(hwdev->dev, "failed to add adev %s %u\n",
+			svc_name, hwdev->dev_id);
+		auxiliary_device_uninit(&hadev->adev);
+		return NULL;
+	}
+
+	return hadev;
+}
+
+static void hinic3_del_one_adev(struct hinic3_hwdev *hwdev,
+				enum hinic3_service_type svc_type)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	struct hinic3_adev *hadev;
+	int timeout;
+	bool state;
+
+	timeout = read_poll_timeout(test_and_set_bit, state, !state,
+				    HINIC3_EVENT_POLL_SLEEP_US,
+				    HINIC3_EVENT_POLL_TIMEOUT_US,
+				    false, svc_type, &pci_adapter->state);
+
+	hadev = pci_adapter->hadev[svc_type];
+	auxiliary_device_delete(&hadev->adev);
+	auxiliary_device_uninit(&hadev->adev);
+	pci_adapter->hadev[svc_type] = NULL;
+	if (!timeout)
+		clear_bit(svc_type, &pci_adapter->state);
+}
+
+static int hinic3_attach_aux_devices(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	enum hinic3_service_type svc_type;
+
+	mutex_lock(&pci_adapter->pdev_mutex);
+
+	for (svc_type = 0; svc_type < HINIC3_SERVICE_T_MAX; svc_type++) {
+		if (!hinic3_adev_svc_supported(hwdev, svc_type))
+			continue;
+
+		pci_adapter->hadev[svc_type] = hinic3_add_one_adev(hwdev,
+								   svc_type);
+		if (!pci_adapter->hadev[svc_type])
+			goto err_del_adevs;
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+	return 0;
+
+err_del_adevs:
+	while (svc_type > 0) {
+		svc_type--;
+		if (pci_adapter->hadev[svc_type]) {
+			hinic3_del_one_adev(hwdev, svc_type);
+			pci_adapter->hadev[svc_type] = NULL;
+		}
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+	return -ENOMEM;
+}
+
+static void hinic3_detach_aux_devices(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	int i;
+
+	mutex_lock(&pci_adapter->pdev_mutex);
+	for (i = 0; i < ARRAY_SIZE(hinic3_adev_devices); i++) {
+		if (pci_adapter->hadev[i])
+			hinic3_del_one_adev(hwdev, i);
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+}
+
+struct hinic3_hwdev *hinic3_adev_get_hwdev(struct auxiliary_device *adev)
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+	return hadev->hwdev;
+}
+
+void hinic3_adev_event_register(struct auxiliary_device *adev,
+				void (*event_handler)(struct auxiliary_device *adev,
+						      struct hinic3_event_info *event))
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+	hadev->event = event_handler;
+}
+
+void hinic3_adev_event_unregister(struct auxiliary_device *adev)
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+	hadev->event = NULL;
+}
+
+static int hinic3_mapping_bar(struct pci_dev *pdev,
+			      struct hinic3_pcidev *pci_adapter)
+{
+	pci_adapter->cfg_reg_base = pci_ioremap_bar(pdev,
+						    HINIC3_VF_PCI_CFG_REG_BAR);
+	if (!pci_adapter->cfg_reg_base) {
+		dev_err(&pdev->dev, "Failed to map configuration regs\n");
+		return -ENOMEM;
+	}
+
+	pci_adapter->intr_reg_base = pci_ioremap_bar(pdev,
+						     HINIC3_PCI_INTR_REG_BAR);
+	if (!pci_adapter->intr_reg_base) {
+		dev_err(&pdev->dev, "Failed to map interrupt regs\n");
+		goto err_unmap_cfg_reg_base;
+	}
+
+	pci_adapter->db_base_phy = pci_resource_start(pdev, HINIC3_PCI_DB_BAR);
+	pci_adapter->db_dwqe_len = pci_resource_len(pdev, HINIC3_PCI_DB_BAR);
+	pci_adapter->db_base = pci_ioremap_bar(pdev, HINIC3_PCI_DB_BAR);
+	if (!pci_adapter->db_base) {
+		dev_err(&pdev->dev, "Failed to map doorbell regs\n");
+		goto err_unmap_intr_reg_base;
+	}
+
+	return 0;
+
+err_unmap_intr_reg_base:
+	iounmap(pci_adapter->intr_reg_base);
+
+err_unmap_cfg_reg_base:
+	iounmap(pci_adapter->cfg_reg_base);
+
+	return -ENOMEM;
+}
+
+static void hinic3_unmapping_bar(struct hinic3_pcidev *pci_adapter)
+{
+	iounmap(pci_adapter->db_base);
+	iounmap(pci_adapter->intr_reg_base);
+	iounmap(pci_adapter->cfg_reg_base);
+}
+
+static int hinic3_pci_init(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter;
+	int err;
+
+	pci_adapter = kzalloc(sizeof(*pci_adapter), GFP_KERNEL);
+	if (!pci_adapter)
+		return -ENOMEM;
+
+	pci_adapter->pdev = pdev;
+	mutex_init(&pci_adapter->pdev_mutex);
+
+	pci_set_drvdata(pdev, pci_adapter);
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to enable PCI device\n");
+		goto err_free_pci_adapter;
+	}
+
+	err = pci_request_regions(pdev, HINIC3_NIC_DRV_NAME);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to request regions\n");
+		goto err_disable_device;
+	}
+
+	pci_set_master(pdev);
+
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (err) {
+		dev_err(&pdev->dev, "Failed to set DMA mask\n");
+		goto err_release_regions;
+	}
+
+	return 0;
+
+err_release_regions:
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+
+err_disable_device:
+	pci_disable_device(pdev);
+
+err_free_pci_adapter:
+	pci_set_drvdata(pdev, NULL);
+	mutex_destroy(&pci_adapter->pdev_mutex);
+	kfree(pci_adapter);
+
+	return err;
+}
+
+static void hinic3_pci_uninit(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+	mutex_destroy(&pci_adapter->pdev_mutex);
+	kfree(pci_adapter);
+}
+
+static int hinic3_func_init(struct pci_dev *pdev,
+			    struct hinic3_pcidev *pci_adapter)
+{
+	int err;
+
+	err = hinic3_init_hwdev(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to initialize hardware device\n");
+		return err;
+	}
+
+	err = hinic3_attach_aux_devices(pci_adapter->hwdev);
+	if (err)
+		goto err_free_hwdev;
+
+	return 0;
+
+err_free_hwdev:
+	hinic3_free_hwdev(pci_adapter->hwdev);
+
+	return err;
+}
+
+static void hinic3_func_uninit(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	hinic3_detach_aux_devices(pci_adapter->hwdev);
+	hinic3_free_hwdev(pci_adapter->hwdev);
+}
+
+static int hinic3_probe_func(struct hinic3_pcidev *pci_adapter)
+{
+	struct pci_dev *pdev = pci_adapter->pdev;
+	int err;
+
+	err = hinic3_mapping_bar(pdev, pci_adapter);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to map bar\n");
+		goto err_out;
+	}
+
+	err = hinic3_func_init(pdev, pci_adapter);
+	if (err)
+		goto err_unmap_bar;
+
+	return 0;
+
+err_unmap_bar:
+	hinic3_unmapping_bar(pci_adapter);
+
+err_out:
+	dev_err(&pdev->dev, "PCIe device probe function failed\n");
+	return err;
+}
+
+static void hinic3_remove_func(struct hinic3_pcidev *pci_adapter)
+{
+	struct pci_dev *pdev = pci_adapter->pdev;
+
+	hinic3_func_uninit(pdev);
+	hinic3_unmapping_bar(pci_adapter);
+}
+
+static int hinic3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct hinic3_pcidev *pci_adapter;
+	int err;
+
+	err = hinic3_pci_init(pdev);
+	if (err)
+		goto err_out;
+
+	pci_adapter = pci_get_drvdata(pdev);
+	err = hinic3_probe_func(pci_adapter);
+	if (err)
+		goto err_uninit_pci;
+
+	return 0;
+
+err_uninit_pci:
+	hinic3_pci_uninit(pdev);
+
+err_out:
+	dev_err(&pdev->dev, "PCIe device probe failed\n");
+	return err;
+}
+
+static void hinic3_remove(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	hinic3_remove_func(pci_adapter);
+	hinic3_pci_uninit(pdev);
+}
+
+static const struct pci_device_id hinic3_pci_table[] = {
+	/* Completed by later submission due to LoC limit. */
+	{0, 0}
+
+};
+
+MODULE_DEVICE_TABLE(pci, hinic3_pci_table);
+
+static void hinic3_shutdown(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	pci_disable_device(pdev);
+
+	if (pci_adapter)
+		hinic3_set_api_stop(pci_adapter->hwdev);
+}
+
+static struct pci_driver hinic3_driver = {
+	.name            = HINIC3_NIC_DRV_NAME,
+	.id_table        = hinic3_pci_table,
+	.probe           = hinic3_probe,
+	.remove          = hinic3_remove,
+	.shutdown        = hinic3_shutdown,
+	.sriov_configure = pci_sriov_configure_simple
+};
+
+int hinic3_lld_init(void)
+{
+	return pci_register_driver(&hinic3_driver);
+}
+
+void hinic3_lld_exit(void)
+{
+	pci_unregister_driver(&hinic3_driver);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h
new file mode 100644
index 000000000000..322b44803476
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_LLD_H_
+#define _HINIC3_LLD_H_
+
+#include <linux/auxiliary_bus.h>
+
+struct hinic3_event_info;
+
+#define HINIC3_NIC_DRV_NAME "hinic3"
+
+int hinic3_lld_init(void);
+void hinic3_lld_exit(void);
+void hinic3_adev_event_register(struct auxiliary_device *adev,
+				void (*event_handler)(struct auxiliary_device *adev,
+						      struct hinic3_event_info *event));
+void hinic3_adev_event_unregister(struct auxiliary_device *adev);
+struct hinic3_hwdev *hinic3_adev_get_hwdev(struct auxiliary_device *adev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_main.c b/drivers/net/ethernet/huawei/hinic3/hinic3_main.c
new file mode 100644
index 000000000000..093aa6d775ff
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_main.c
@@ -0,0 +1,354 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+
+#include "hinic3_common.h"
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_lld.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+#define HINIC3_NIC_DRV_DESC  "Intelligent Network Interface Card Driver"
+
+#define HINIC3_RX_BUF_LEN            2048
+#define HINIC3_LRO_REPLENISH_THLD    256
+#define HINIC3_NIC_DEV_WQ_NAME       "hinic3_nic_dev_wq"
+
+#define HINIC3_SQ_DEPTH              1024
+#define HINIC3_RQ_DEPTH              1024
+
+static int hinic3_alloc_txrxqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	err = hinic3_alloc_txqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc txqs\n");
+		return err;
+	}
+
+	err = hinic3_alloc_rxqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc rxqs\n");
+		goto err_free_txqs;
+	}
+
+	return 0;
+
+err_free_txqs:
+	hinic3_free_txqs(netdev);
+
+	return err;
+}
+
+static void hinic3_free_txrxqs(struct net_device *netdev)
+{
+	hinic3_free_rxqs(netdev);
+	hinic3_free_txqs(netdev);
+}
+
+static int hinic3_init_nic_dev(struct net_device *netdev,
+			       struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct pci_dev *pdev = hwdev->pdev;
+
+	nic_dev->netdev = netdev;
+	SET_NETDEV_DEV(netdev, &pdev->dev);
+	nic_dev->hwdev = hwdev;
+	nic_dev->pdev = pdev;
+
+	nic_dev->rx_buf_len = HINIC3_RX_BUF_LEN;
+	nic_dev->lro_replenish_thld = HINIC3_LRO_REPLENISH_THLD;
+	nic_dev->nic_svc_cap = hwdev->cfg_mgmt->cap.nic_svc_cap;
+
+	return 0;
+}
+
+static int hinic3_sw_init(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	nic_dev->q_params.sq_depth = HINIC3_SQ_DEPTH;
+	nic_dev->q_params.rq_depth = HINIC3_RQ_DEPTH;
+
+	/* VF driver always uses random MAC address. During VM migration to a
+	 * new device, the new device should learn the VMs old MAC rather than
+	 * provide its own MAC. The product design assumes that every VF is
+	 * suspectable to migration so the device avoids offering MAC address
+	 * to VFs.
+	 */
+	eth_hw_addr_random(netdev);
+	err = hinic3_set_mac(hwdev, netdev->dev_addr, 0,
+			     hinic3_global_func_id(hwdev));
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set default MAC\n");
+		return err;
+	}
+
+	err = hinic3_alloc_txrxqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc qps\n");
+		goto err_del_mac;
+	}
+
+	return 0;
+
+err_del_mac:
+	hinic3_del_mac(hwdev, netdev->dev_addr, 0,
+		       hinic3_global_func_id(hwdev));
+
+	return err;
+}
+
+static void hinic3_sw_uninit(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	hinic3_free_txrxqs(netdev);
+	hinic3_del_mac(nic_dev->hwdev, netdev->dev_addr, 0,
+		       hinic3_global_func_id(nic_dev->hwdev));
+}
+
+static void hinic3_assign_netdev_ops(struct net_device *netdev)
+{
+	hinic3_set_netdev_ops(netdev);
+}
+
+static void netdev_feature_init(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	netdev_features_t cso_fts = 0;
+	netdev_features_t tso_fts = 0;
+	netdev_features_t dft_fts;
+
+	dft_fts = NETIF_F_SG | NETIF_F_HIGHDMA;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_CSUM))
+		cso_fts |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_SCTP_CRC))
+		cso_fts |= NETIF_F_SCTP_CRC;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_TSO))
+		tso_fts |= NETIF_F_TSO | NETIF_F_TSO6;
+
+	netdev->features |= dft_fts | cso_fts | tso_fts;
+}
+
+static int hinic3_set_default_hw_feature(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	err = hinic3_set_nic_feature_to_hw(nic_dev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set nic features\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static void hinic3_link_status_change(struct net_device *netdev,
+				      bool link_status_up)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	if (link_status_up) {
+		if (netif_carrier_ok(netdev))
+			return;
+
+		nic_dev->link_status_up = true;
+		netif_carrier_on(netdev);
+		netdev_dbg(netdev, "Link is up\n");
+	} else {
+		if (!netif_carrier_ok(netdev))
+			return;
+
+		nic_dev->link_status_up = false;
+		netif_carrier_off(netdev);
+		netdev_dbg(netdev, "Link is down\n");
+	}
+}
+
+static void hinic3_nic_event(struct auxiliary_device *adev,
+			     struct hinic3_event_info *event)
+{
+	struct hinic3_nic_dev *nic_dev = dev_get_drvdata(&adev->dev);
+	struct net_device *netdev;
+
+	netdev = nic_dev->netdev;
+
+	switch (HINIC3_SRV_EVENT_TYPE(event->service, event->type)) {
+	case HINIC3_SRV_EVENT_TYPE(HINIC3_EVENT_SRV_NIC,
+				   HINIC3_NIC_EVENT_LINK_UP):
+		hinic3_link_status_change(netdev, true);
+		break;
+	case HINIC3_SRV_EVENT_TYPE(HINIC3_EVENT_SRV_NIC,
+				   HINIC3_NIC_EVENT_LINK_DOWN):
+		hinic3_link_status_change(netdev, false);
+		break;
+	default:
+		break;
+	}
+}
+
+static int hinic3_nic_probe(struct auxiliary_device *adev,
+			    const struct auxiliary_device_id *id)
+{
+	struct hinic3_hwdev *hwdev = hinic3_adev_get_hwdev(adev);
+	struct pci_dev *pdev = hwdev->pdev;
+	struct hinic3_nic_dev *nic_dev;
+	struct net_device *netdev;
+	u16 max_qps, glb_func_id;
+	int err;
+
+	if (!hinic3_support_nic(hwdev)) {
+		dev_dbg(&adev->dev, "HW doesn't support nic\n");
+		return 0;
+	}
+
+	hinic3_adev_event_register(adev, hinic3_nic_event);
+
+	glb_func_id = hinic3_global_func_id(hwdev);
+	err = hinic3_func_reset(hwdev, glb_func_id, COMM_FUNC_RESET_BIT_NIC);
+	if (err) {
+		dev_err(&adev->dev, "Failed to reset function\n");
+		goto err_unregister_adev_event;
+	}
+
+	max_qps = hinic3_func_max_qnum(hwdev);
+	netdev = alloc_etherdev_mq(sizeof(*nic_dev), max_qps);
+	if (!netdev) {
+		dev_err(&adev->dev, "Failed to allocate netdev\n");
+		err = -ENOMEM;
+		goto err_unregister_adev_event;
+	}
+
+	nic_dev = netdev_priv(netdev);
+	dev_set_drvdata(&adev->dev, nic_dev);
+	err = hinic3_init_nic_dev(netdev, hwdev);
+	if (err)
+		goto err_free_netdev;
+
+	err = hinic3_init_nic_io(nic_dev);
+	if (err)
+		goto err_free_netdev;
+
+	err = hinic3_sw_init(netdev);
+	if (err)
+		goto err_free_nic_io;
+
+	hinic3_assign_netdev_ops(netdev);
+
+	netdev_feature_init(netdev);
+	err = hinic3_set_default_hw_feature(netdev);
+	if (err)
+		goto err_uninit_sw;
+
+	netif_carrier_off(netdev);
+
+	err = register_netdev(netdev);
+	if (err)
+		goto err_uninit_nic_feature;
+
+	return 0;
+
+err_uninit_nic_feature:
+	hinic3_update_nic_feature(nic_dev, 0);
+	hinic3_set_nic_feature_to_hw(nic_dev);
+
+err_uninit_sw:
+	hinic3_sw_uninit(netdev);
+
+err_free_nic_io:
+	hinic3_free_nic_io(nic_dev);
+
+err_free_netdev:
+	free_netdev(netdev);
+
+err_unregister_adev_event:
+	hinic3_adev_event_unregister(adev);
+	dev_err(&pdev->dev, "NIC service probe failed\n");
+
+	return err;
+}
+
+static void hinic3_nic_remove(struct auxiliary_device *adev)
+{
+	struct hinic3_nic_dev *nic_dev = dev_get_drvdata(&adev->dev);
+	struct net_device *netdev;
+
+	if (!hinic3_support_nic(nic_dev->hwdev))
+		return;
+
+	netdev = nic_dev->netdev;
+	unregister_netdev(netdev);
+
+	hinic3_update_nic_feature(nic_dev, 0);
+	hinic3_set_nic_feature_to_hw(nic_dev);
+	hinic3_sw_uninit(netdev);
+
+	hinic3_free_nic_io(nic_dev);
+
+	free_netdev(netdev);
+}
+
+static const struct auxiliary_device_id hinic3_nic_id_table[] = {
+	{
+		.name = HINIC3_NIC_DRV_NAME ".nic",
+	},
+	{}
+};
+
+static struct auxiliary_driver hinic3_nic_driver = {
+	.probe    = hinic3_nic_probe,
+	.remove   = hinic3_nic_remove,
+	.suspend  = NULL,
+	.resume   = NULL,
+	.name     = "nic",
+	.id_table = hinic3_nic_id_table,
+};
+
+static __init int hinic3_nic_lld_init(void)
+{
+	int err;
+
+	pr_info("%s: %s\n", HINIC3_NIC_DRV_NAME, HINIC3_NIC_DRV_DESC);
+
+	err = hinic3_lld_init();
+	if (err)
+		return err;
+
+	err = auxiliary_driver_register(&hinic3_nic_driver);
+	if (err) {
+		hinic3_lld_exit();
+		return err;
+	}
+
+	return 0;
+}
+
+static __exit void hinic3_nic_lld_exit(void)
+{
+	auxiliary_driver_unregister(&hinic3_nic_driver);
+
+	hinic3_lld_exit();
+}
+
+module_init(hinic3_nic_lld_init);
+module_exit(hinic3_nic_lld_exit);
+
+MODULE_AUTHOR("Huawei Technologies CO., Ltd");
+MODULE_DESCRIPTION(HINIC3_NIC_DRV_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c
new file mode 100644
index 000000000000..e74d1eb09730
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/dma-mapping.h>
+
+#include "hinic3_common.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+int hinic3_send_mbox_to_mgmt(struct hinic3_hwdev *hwdev, u8 mod, u16 cmd,
+			     const struct mgmt_msg_params *msg_params)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h
new file mode 100644
index 000000000000..d7a6c37b7eff
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MBOX_H_
+#define _HINIC3_MBOX_H_
+
+#include <linux/bitfield.h>
+#include <linux/mutex.h>
+
+struct hinic3_hwdev;
+
+int hinic3_send_mbox_to_mgmt(struct hinic3_hwdev *hwdev, u8 mod, u16 cmd,
+			     const struct mgmt_msg_params *msg_params);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h
new file mode 100644
index 000000000000..4edabeb32112
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MGMT_H_
+#define _HINIC3_MGMT_H_
+
+#include <linux/types.h>
+
+struct hinic3_hwdev;
+
+void hinic3_flush_mgmt_workq(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h
new file mode 100644
index 000000000000..c4434efdc7f7
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MGMT_INTERFACE_H_
+#define _HINIC3_MGMT_INTERFACE_H_
+
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/if_ether.h>
+
+#include "hinic3_hw_intf.h"
+
+struct l2nic_cmd_feature_nego {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u8                   opcode;
+	u8                   rsvd;
+	u64                  s_feature[4];
+};
+
+enum l2nic_func_tbl_cfg_bitmap {
+	L2NIC_FUNC_TBL_CFG_INIT        = 0,
+	L2NIC_FUNC_TBL_CFG_RX_BUF_SIZE = 1,
+	L2NIC_FUNC_TBL_CFG_MTU         = 2,
+};
+
+struct l2nic_func_tbl_cfg {
+	u16 rx_wqe_buf_size;
+	u16 mtu;
+	u32 rsvd[9];
+};
+
+struct l2nic_cmd_set_func_tbl {
+	struct mgmt_msg_head      msg_head;
+	u16                       func_id;
+	u16                       rsvd;
+	u32                       cfg_bitmap;
+	struct l2nic_func_tbl_cfg tbl_cfg;
+};
+
+struct l2nic_cmd_set_mac {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u16                  vlan_id;
+	u16                  rsvd1;
+	u8                   mac[ETH_ALEN];
+};
+
+struct l2nic_cmd_update_mac {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u16                  vlan_id;
+	u16                  rsvd1;
+	u8                   old_mac[ETH_ALEN];
+	u16                  rsvd2;
+	u8                   new_mac[ETH_ALEN];
+};
+
+struct l2nic_cmd_force_pkt_drop {
+	struct mgmt_msg_head msg_head;
+	u8                   port;
+	u8                   rsvd1[3];
+};
+
+/* Commands between NIC to fw */
+enum l2nic_cmd {
+	/* FUNC CFG */
+	L2NIC_CMD_SET_FUNC_TBL        = 5,
+	L2NIC_CMD_SET_VPORT_ENABLE    = 6,
+	L2NIC_CMD_SET_SQ_CI_ATTR      = 8,
+	L2NIC_CMD_CLEAR_QP_RESOURCE   = 11,
+	L2NIC_CMD_FEATURE_NEGO        = 15,
+	L2NIC_CMD_SET_MAC             = 21,
+	L2NIC_CMD_DEL_MAC             = 22,
+	L2NIC_CMD_UPDATE_MAC          = 23,
+	L2NIC_CMD_CFG_RSS             = 60,
+	L2NIC_CMD_CFG_RSS_HASH_KEY    = 63,
+	L2NIC_CMD_CFG_RSS_HASH_ENGINE = 64,
+	L2NIC_CMD_SET_RSS_CTX_TBL     = 65,
+	L2NIC_CMD_QOS_DCB_STATE       = 110,
+	L2NIC_CMD_FORCE_PKT_DROP      = 113,
+	L2NIC_CMD_MAX                 = 256,
+};
+
+enum hinic3_nic_feature_cap {
+	HINIC3_NIC_F_CSUM           = BIT(0),
+	HINIC3_NIC_F_SCTP_CRC       = BIT(1),
+	HINIC3_NIC_F_TSO            = BIT(2),
+	HINIC3_NIC_F_LRO            = BIT(3),
+	HINIC3_NIC_F_UFO            = BIT(4),
+	HINIC3_NIC_F_RSS            = BIT(5),
+	HINIC3_NIC_F_RX_VLAN_FILTER = BIT(6),
+	HINIC3_NIC_F_RX_VLAN_STRIP  = BIT(7),
+	HINIC3_NIC_F_TX_VLAN_INSERT = BIT(8),
+	HINIC3_NIC_F_VXLAN_OFFLOAD  = BIT(9),
+	HINIC3_NIC_F_FDIR           = BIT(11),
+	HINIC3_NIC_F_PROMISC        = BIT(12),
+	HINIC3_NIC_F_ALLMULTI       = BIT(13),
+	HINIC3_NIC_F_RATE_LIMIT     = BIT(16),
+};
+
+#define HINIC3_NIC_F_ALL_MASK           0x33bff
+#define HINIC3_NIC_DRV_DEFAULT_FEATURE  0x3f03f
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c b/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c
new file mode 100644
index 000000000000..71104a6b8bef
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+
+#include "hinic3_hwif.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+static int hinic3_open(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+static int hinic3_close(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+static int hinic3_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	int err;
+
+	err = hinic3_set_port_mtu(netdev, new_mtu);
+	if (err) {
+		netdev_err(netdev, "Failed to change port mtu to %d\n",
+			   new_mtu);
+		return err;
+	}
+
+	netdev_dbg(netdev, "Change mtu from %u to %d\n", netdev->mtu, new_mtu);
+	WRITE_ONCE(netdev->mtu, new_mtu);
+
+	return 0;
+}
+
+static int hinic3_set_mac_addr(struct net_device *netdev, void *addr)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct sockaddr *saddr = addr;
+	int err;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	if (ether_addr_equal(netdev->dev_addr, saddr->sa_data))
+		return 0;
+
+	err = hinic3_update_mac(nic_dev->hwdev, netdev->dev_addr,
+				saddr->sa_data, 0,
+				hinic3_global_func_id(nic_dev->hwdev));
+
+	if (err)
+		return err;
+
+	eth_hw_addr_set(netdev, saddr->sa_data);
+
+	return 0;
+}
+
+static const struct net_device_ops hinic3_netdev_ops = {
+	.ndo_open             = hinic3_open,
+	.ndo_stop             = hinic3_close,
+	.ndo_change_mtu       = hinic3_change_mtu,
+	.ndo_set_mac_address  = hinic3_set_mac_addr,
+	.ndo_start_xmit       = hinic3_xmit_frame,
+};
+
+void hinic3_set_netdev_ops(struct net_device *netdev)
+{
+	netdev->netdev_ops = &hinic3_netdev_ops;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c
new file mode 100644
index 000000000000..5b1a91a18c67
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/if_vlan.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+
+static int hinic3_feature_nego(struct hinic3_hwdev *hwdev, u8 opcode,
+			       u64 *s_feature, u16 size)
+{
+	struct l2nic_cmd_feature_nego feature_nego = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	feature_nego.func_id = hinic3_global_func_id(hwdev);
+	feature_nego.opcode = opcode;
+	if (opcode == MGMT_MSG_CMD_OP_SET)
+		memcpy(feature_nego.s_feature, s_feature, size * sizeof(u64));
+
+	mgmt_msg_params_init_default(&msg_params, &feature_nego,
+				     sizeof(feature_nego));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_FEATURE_NEGO, &msg_params);
+	if (err || feature_nego.msg_head.status) {
+		dev_err(hwdev->dev, "Failed to negotiate nic feature, err:%d, status: 0x%x\n",
+			err, feature_nego.msg_head.status);
+		return -EIO;
+	}
+
+	if (opcode == MGMT_MSG_CMD_OP_GET)
+		memcpy(s_feature, feature_nego.s_feature, size * sizeof(u64));
+
+	return 0;
+}
+
+int hinic3_set_nic_feature_to_hw(struct hinic3_nic_dev *nic_dev)
+{
+	return hinic3_feature_nego(nic_dev->hwdev, MGMT_MSG_CMD_OP_SET,
+				   &nic_dev->nic_io->feature_cap, 1);
+}
+
+bool hinic3_test_support(struct hinic3_nic_dev *nic_dev,
+			 enum hinic3_nic_feature_cap feature_bits)
+{
+	return (nic_dev->nic_io->feature_cap & feature_bits) == feature_bits;
+}
+
+void hinic3_update_nic_feature(struct hinic3_nic_dev *nic_dev, u64 feature_cap)
+{
+	nic_dev->nic_io->feature_cap = feature_cap;
+}
+
+static int hinic3_set_function_table(struct hinic3_hwdev *hwdev, u32 cfg_bitmap,
+				     const struct l2nic_func_tbl_cfg *cfg)
+{
+	struct l2nic_cmd_set_func_tbl cmd_func_tbl = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	cmd_func_tbl.func_id = hinic3_global_func_id(hwdev);
+	cmd_func_tbl.cfg_bitmap = cfg_bitmap;
+	cmd_func_tbl.tbl_cfg = *cfg;
+
+	mgmt_msg_params_init_default(&msg_params, &cmd_func_tbl,
+				     sizeof(cmd_func_tbl));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_SET_FUNC_TBL, &msg_params);
+	if (err || cmd_func_tbl.msg_head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set func table, bitmap: 0x%x, err: %d, status: 0x%x\n",
+			cfg_bitmap, err, cmd_func_tbl.msg_head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+int hinic3_set_port_mtu(struct net_device *netdev, u16 new_mtu)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct l2nic_func_tbl_cfg func_tbl_cfg = {};
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+
+	func_tbl_cfg.mtu = new_mtu;
+	return hinic3_set_function_table(hwdev, BIT(L2NIC_FUNC_TBL_CFG_MTU),
+					 &func_tbl_cfg);
+}
+
+static int hinic3_check_mac_info(struct hinic3_hwdev *hwdev, u8 status,
+				 u16 vlan_id)
+{
+	if ((status && status != MGMT_STATUS_EXIST) ||
+	    ((vlan_id & BIT(15)) && status == MGMT_STATUS_EXIST)) {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic3_set_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id)
+{
+	struct l2nic_cmd_set_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.mac, mac_addr);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_SET_MAC, &msg_params);
+	if (err || hinic3_check_mac_info(hwdev, mac_info.msg_head.status,
+					 mac_info.vlan_id)) {
+		dev_err(hwdev->dev,
+			"Failed to update MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return -EIO;
+	}
+
+	if (mac_info.msg_head.status == MGMT_STATUS_PF_SET_VF_ALREADY) {
+		dev_warn(hwdev->dev, "PF has already set VF mac, Ignore set operation\n");
+		return 0;
+	}
+
+	if (mac_info.msg_head.status == MGMT_STATUS_EXIST) {
+		dev_warn(hwdev->dev, "MAC is repeated. Ignore update operation\n");
+		return 0;
+	}
+
+	return 0;
+}
+
+int hinic3_del_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id)
+{
+	struct l2nic_cmd_set_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.mac, mac_addr);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_DEL_MAC, &msg_params);
+	if (err) {
+		dev_err(hwdev->dev,
+			"Failed to delete MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return err;
+	}
+
+	return 0;
+}
+
+int hinic3_update_mac(struct hinic3_hwdev *hwdev, const u8 *old_mac,
+		      u8 *new_mac, u16 vlan_id, u16 func_id)
+{
+	struct l2nic_cmd_update_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.old_mac, old_mac);
+	ether_addr_copy(mac_info.new_mac, new_mac);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_UPDATE_MAC, &msg_params);
+	if (err || hinic3_check_mac_info(hwdev, mac_info.msg_head.status,
+					 mac_info.vlan_id)) {
+		dev_err(hwdev->dev,
+			"Failed to update MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return -EIO;
+	}
+	return 0;
+}
+
+int hinic3_force_drop_tx_pkt(struct hinic3_hwdev *hwdev)
+{
+	struct l2nic_cmd_force_pkt_drop pkt_drop = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	pkt_drop.port = hinic3_physical_port_id(hwdev);
+
+	mgmt_msg_params_init_default(&msg_params, &pkt_drop, sizeof(pkt_drop));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_FORCE_PKT_DROP, &msg_params);
+	if ((pkt_drop.msg_head.status != MGMT_STATUS_CMD_UNSUPPORTED &&
+	     pkt_drop.msg_head.status) || err) {
+		dev_err(hwdev->dev,
+			"Failed to set force tx packets drop, err: %d, status: 0x%x\n",
+			err, pkt_drop.msg_head.status);
+		return -EFAULT;
+	}
+
+	return pkt_drop.msg_head.status;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h
new file mode 100644
index 000000000000..bf9ce51dc401
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_CFG_H_
+#define _HINIC3_NIC_CFG_H_
+
+#include <linux/types.h>
+
+#include "hinic3_hw_intf.h"
+#include "hinic3_mgmt_interface.h"
+
+struct hinic3_hwdev;
+struct hinic3_nic_dev;
+
+#define HINIC3_MIN_MTU_SIZE          256
+#define HINIC3_MAX_JUMBO_FRAME_SIZE  9600
+
+#define HINIC3_VLAN_ID_MASK          0x7FFF
+
+enum hinic3_nic_event_type {
+	HINIC3_NIC_EVENT_LINK_DOWN = 0,
+	HINIC3_NIC_EVENT_LINK_UP   = 1,
+};
+
+int hinic3_set_nic_feature_to_hw(struct hinic3_nic_dev *nic_dev);
+bool hinic3_test_support(struct hinic3_nic_dev *nic_dev,
+			 enum hinic3_nic_feature_cap feature_bits);
+void hinic3_update_nic_feature(struct hinic3_nic_dev *nic_dev, u64 feature_cap);
+
+int hinic3_set_port_mtu(struct net_device *netdev, u16 new_mtu);
+
+int hinic3_set_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id);
+int hinic3_del_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		   u16 func_id);
+int hinic3_update_mac(struct hinic3_hwdev *hwdev, const u8 *old_mac,
+		      u8 *new_mac, u16 vlan_id, u16 func_id);
+
+int hinic3_force_drop_tx_pkt(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h
new file mode 100644
index 000000000000..c994fc9b6ee0
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_DEV_H_
+#define _HINIC3_NIC_DEV_H_
+
+#include <linux/netdevice.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_mgmt_interface.h"
+
+enum hinic3_flags {
+	HINIC3_RSS_ENABLE,
+};
+
+enum hinic3_rss_hash_type {
+	HINIC3_RSS_HASH_ENGINE_TYPE_XOR  = 0,
+	HINIC3_RSS_HASH_ENGINE_TYPE_TOEP = 1,
+};
+
+struct hinic3_rss_type {
+	u8 tcp_ipv6_ext;
+	u8 ipv6_ext;
+	u8 tcp_ipv6;
+	u8 ipv6;
+	u8 tcp_ipv4;
+	u8 ipv4;
+	u8 udp_ipv6;
+	u8 udp_ipv4;
+};
+
+struct hinic3_irq_cfg {
+	struct net_device  *netdev;
+	u16                msix_entry_idx;
+	/* provided by OS */
+	u32                irq_id;
+	char               irq_name[IFNAMSIZ + 16];
+	struct napi_struct napi;
+	cpumask_t          affinity_mask;
+	struct hinic3_txq  *txq;
+	struct hinic3_rxq  *rxq;
+};
+
+struct hinic3_dyna_txrxq_params {
+	u16                        num_qps;
+	u32                        sq_depth;
+	u32                        rq_depth;
+
+	struct hinic3_dyna_txq_res *txqs_res;
+	struct hinic3_dyna_rxq_res *rxqs_res;
+	struct hinic3_irq_cfg      *irq_cfg;
+};
+
+struct hinic3_nic_dev {
+	struct pci_dev                  *pdev;
+	struct net_device               *netdev;
+	struct hinic3_hwdev             *hwdev;
+	struct hinic3_nic_io            *nic_io;
+
+	u16                             max_qps;
+	u16                             rx_buf_len;
+	u32                             lro_replenish_thld;
+	unsigned long                   flags;
+	struct hinic3_nic_service_cap   nic_svc_cap;
+
+	struct hinic3_dyna_txrxq_params q_params;
+	struct hinic3_txq               *txqs;
+	struct hinic3_rxq               *rxqs;
+
+	u16                             num_qp_irq;
+	struct msix_entry               *qps_msix_entries;
+
+	bool                            link_status_up;
+};
+
+void hinic3_set_netdev_ops(struct net_device *netdev);
+
+/* Temporary prototypes. Functions become static in later submission. */
+void qp_add_napi(struct hinic3_irq_cfg *irq_cfg);
+void qp_del_napi(struct hinic3_irq_cfg *irq_cfg);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c
new file mode 100644
index 000000000000..34a1f5bd5ac1
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hw_intf.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+
+int hinic3_init_nic_io(struct hinic3_nic_dev *nic_dev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+void hinic3_free_nic_io(struct hinic3_nic_dev *nic_dev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h
new file mode 100644
index 000000000000..865ba6878c48
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_IO_H_
+#define _HINIC3_NIC_IO_H_
+
+#include <linux/bitfield.h>
+
+#include "hinic3_wq.h"
+
+struct hinic3_nic_dev;
+
+#define HINIC3_SQ_WQEBB_SHIFT      4
+#define HINIC3_RQ_WQEBB_SHIFT      3
+#define HINIC3_SQ_WQEBB_SIZE       BIT(HINIC3_SQ_WQEBB_SHIFT)
+
+/* ******************** RQ_CTRL ******************** */
+enum hinic3_rq_wqe_type {
+	HINIC3_NORMAL_RQ_WQE = 1,
+};
+
+/* ******************** SQ_CTRL ******************** */
+#define HINIC3_TX_MSS_DEFAULT  0x3E00
+#define HINIC3_TX_MSS_MIN      0x50
+#define HINIC3_MAX_SQ_SGE      18
+
+struct hinic3_io_queue {
+	struct hinic3_wq  wq;
+	u8                owner;
+	u16               q_id;
+	u16               msix_entry_idx;
+	u8 __iomem        *db_addr;
+	u16               *cons_idx_addr;
+} ____cacheline_aligned;
+
+static inline u16 hinic3_get_sq_local_ci(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return wq->cons_idx & wq->idx_mask;
+}
+
+static inline u16 hinic3_get_sq_local_pi(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return wq->prod_idx & wq->idx_mask;
+}
+
+static inline u16 hinic3_get_sq_hw_ci(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return READ_ONCE(*sq->cons_idx_addr) & wq->idx_mask;
+}
+
+/* ******************** DB INFO ******************** */
+#define DB_INFO_QID_MASK    GENMASK(12, 0)
+#define DB_INFO_CFLAG_MASK  BIT(23)
+#define DB_INFO_COS_MASK    GENMASK(26, 24)
+#define DB_INFO_TYPE_MASK   GENMASK(31, 27)
+#define DB_INFO_SET(val, member)  \
+	FIELD_PREP(DB_INFO_##member##_MASK, val)
+
+#define DB_PI_LOW_MASK   0xFFU
+#define DB_PI_HIGH_MASK  0xFFU
+#define DB_PI_HI_SHIFT   8
+#define DB_PI_LOW(pi)    ((pi) & DB_PI_LOW_MASK)
+#define DB_PI_HIGH(pi)   (((pi) >> DB_PI_HI_SHIFT) & DB_PI_HIGH_MASK)
+#define DB_ADDR(q, pi)   ((u64 __iomem *)((q)->db_addr) + DB_PI_LOW(pi))
+#define DB_SRC_TYPE      1
+
+/* CFLAG_DATA_PATH */
+#define DB_CFLAG_DP_SQ   0
+#define DB_CFLAG_DP_RQ   1
+
+struct hinic3_nic_db {
+	u32 db_info;
+	u32 pi_hi;
+};
+
+static inline void hinic3_write_db(struct hinic3_io_queue *queue, int cos,
+				   u8 cflag, u16 pi)
+{
+	struct hinic3_nic_db db;
+
+	db.db_info = DB_INFO_SET(DB_SRC_TYPE, TYPE) |
+		     DB_INFO_SET(cflag, CFLAG) |
+		     DB_INFO_SET(cos, COS) |
+		     DB_INFO_SET(queue->q_id, QID);
+	db.pi_hi = DB_PI_HIGH(pi);
+
+	writeq(*((u64 *)&db), DB_ADDR(queue, pi));
+}
+
+struct hinic3_nic_io {
+	struct hinic3_io_queue *sq;
+	struct hinic3_io_queue *rq;
+
+	u16                    num_qps;
+	u16                    max_qps;
+
+	/* Base address for consumer index of all tx queues. Each queue is
+	 * given a full cache line to hold its consumer index. HW updates
+	 * current consumer index as it consumes tx WQEs.
+	 */
+	void                   *ci_vaddr_base;
+	dma_addr_t             ci_dma_base;
+
+	u8 __iomem             *sqs_db_addr;
+	u8 __iomem             *rqs_db_addr;
+
+	u16                    rx_buf_len;
+	u64                    feature_cap;
+};
+
+int hinic3_init_nic_io(struct hinic3_nic_dev *nic_dev);
+void hinic3_free_nic_io(struct hinic3_nic_dev *nic_dev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c
new file mode 100644
index 000000000000..fab9011de9ad
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/device.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_queue_common.h"
+
+void hinic3_queue_pages_init(struct hinic3_queue_pages *qpages, u32 q_depth,
+			     u32 page_size, u32 elem_size)
+{
+	u32 elem_per_page;
+
+	elem_per_page = min(page_size / elem_size, q_depth);
+
+	qpages->pages = NULL;
+	qpages->page_size = page_size;
+	qpages->num_pages = max(q_depth / elem_per_page, 1);
+	qpages->elem_size_shift = ilog2(elem_size);
+	qpages->elem_per_pg_shift = ilog2(elem_per_page);
+}
+
+static void __queue_pages_free(struct hinic3_hwdev *hwdev,
+			       struct hinic3_queue_pages *qpages, u32 pg_cnt)
+{
+	while (pg_cnt > 0) {
+		pg_cnt--;
+		hinic3_dma_free_coherent_align(hwdev->dev,
+					       qpages->pages + pg_cnt);
+	}
+	kfree(qpages->pages);
+	qpages->pages = NULL;
+}
+
+void hinic3_queue_pages_free(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages)
+{
+	__queue_pages_free(hwdev, qpages, qpages->num_pages);
+}
+
+int hinic3_queue_pages_alloc(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages, u32 align)
+{
+	u32 pg_idx;
+	int err;
+
+	qpages->pages = kcalloc(qpages->num_pages, sizeof(qpages->pages[0]),
+				GFP_KERNEL);
+	if (!qpages->pages)
+		return -ENOMEM;
+
+	if (align == 0)
+		align = qpages->page_size;
+
+	for (pg_idx = 0; pg_idx < qpages->num_pages; pg_idx++) {
+		err = hinic3_dma_zalloc_coherent_align(hwdev->dev,
+						       qpages->page_size,
+						       align,
+						       GFP_KERNEL,
+						       qpages->pages + pg_idx);
+		if (err) {
+			__queue_pages_free(hwdev, qpages, pg_idx);
+			return err;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h
new file mode 100644
index 000000000000..ec4cae0a0929
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_QUEUE_COMMON_H_
+#define _HINIC3_QUEUE_COMMON_H_
+
+#include <linux/types.h>
+
+#include "hinic3_common.h"
+
+struct hinic3_hwdev;
+
+struct hinic3_queue_pages {
+	/* Array of DMA-able pages that actually holds the queue entries. */
+	struct hinic3_dma_addr_align  *pages;
+	/* Page size in bytes. */
+	u32                           page_size;
+	/* Number of pages, must be power of 2. */
+	u16                           num_pages;
+	u8                            elem_size_shift;
+	u8                            elem_per_pg_shift;
+};
+
+void hinic3_queue_pages_init(struct hinic3_queue_pages *qpages, u32 q_depth,
+			     u32 page_size, u32 elem_size);
+int hinic3_queue_pages_alloc(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages, u32 align);
+void hinic3_queue_pages_free(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages);
+
+/* Get pointer to queue entry at the specified index. Index does not have to be
+ * masked to queue depth, only least significant bits will be used. Also
+ * provides remaining elements in same page (including the first one) in case
+ * caller needs multiple entries.
+ */
+static inline void *get_q_element(const struct hinic3_queue_pages *qpages,
+				  u32 idx, u32 *remaining_in_page)
+{
+	const struct hinic3_dma_addr_align *page;
+	u32 page_idx, elem_idx, elem_per_pg, ofs;
+	u8 shift;
+
+	shift = qpages->elem_per_pg_shift;
+	page_idx = (idx >> shift) & (qpages->num_pages - 1);
+	elem_per_pg = 1 << shift;
+	elem_idx = idx & (elem_per_pg - 1);
+	if (remaining_in_page)
+		*remaining_in_page = elem_per_pg - elem_idx;
+	ofs = elem_idx << qpages->elem_size_shift;
+	page = qpages->pages + page_idx;
+	return (char *)page->align_vaddr + ofs;
+}
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c
new file mode 100644
index 000000000000..860163e9d66c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c
@@ -0,0 +1,341 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/netdevice.h>
+#include <net/gro.h>
+#include <net/page_pool/helpers.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rx.h"
+
+#define HINIC3_RX_HDR_SIZE              256
+#define HINIC3_RX_BUFFER_WRITE          16
+
+#define HINIC3_RX_TCP_PKT               0x3
+#define HINIC3_RX_UDP_PKT               0x4
+#define HINIC3_RX_SCTP_PKT              0x7
+
+#define HINIC3_RX_IPV4_PKT              0
+#define HINIC3_RX_IPV6_PKT              1
+#define HINIC3_RX_INVALID_IP_TYPE       2
+
+#define HINIC3_RX_PKT_FORMAT_NON_TUNNEL 0
+#define HINIC3_RX_PKT_FORMAT_VXLAN      1
+
+#define HINIC3_LRO_PKT_HDR_LEN_IPV4     66
+#define HINIC3_LRO_PKT_HDR_LEN_IPV6     86
+#define HINIC3_LRO_PKT_HDR_LEN(cqe) \
+	(RQ_CQE_OFFOLAD_TYPE_GET((cqe)->offload_type, IP_TYPE) == \
+	 HINIC3_RX_IPV6_PKT ? HINIC3_LRO_PKT_HDR_LEN_IPV6 : \
+	 HINIC3_LRO_PKT_HDR_LEN_IPV4)
+
+int hinic3_alloc_rxqs(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+void hinic3_free_rxqs(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
+
+static int rx_alloc_mapped_page(struct page_pool *page_pool,
+				struct hinic3_rx_info *rx_info, u16 buf_len)
+{
+	struct page *page;
+	u32 page_offset;
+
+	page = page_pool_dev_alloc_frag(page_pool, &page_offset, buf_len);
+	if (unlikely(!page))
+		return -ENOMEM;
+
+	rx_info->page = page;
+	rx_info->page_offset = page_offset;
+
+	return 0;
+}
+
+static void rq_wqe_buf_set(struct hinic3_io_queue *rq, uint32_t wqe_idx,
+			   dma_addr_t dma_addr, u16 len)
+{
+	struct hinic3_rq_wqe *rq_wqe;
+
+	rq_wqe = get_q_element(&rq->wq.qpages, wqe_idx, NULL);
+	rq_wqe->buf_hi_addr = upper_32_bits(dma_addr);
+	rq_wqe->buf_lo_addr = lower_32_bits(dma_addr);
+}
+
+static u32 hinic3_rx_fill_buffers(struct hinic3_rxq *rxq)
+{
+	u32 i, free_wqebbs = rxq->delta - 1;
+	struct hinic3_rx_info *rx_info;
+	dma_addr_t dma_addr;
+	int err;
+
+	for (i = 0; i < free_wqebbs; i++) {
+		rx_info = &rxq->rx_info[rxq->next_to_update];
+
+		err = rx_alloc_mapped_page(rxq->page_pool, rx_info,
+					   rxq->buf_len);
+		if (unlikely(err))
+			break;
+
+		dma_addr = page_pool_get_dma_addr(rx_info->page) +
+			rx_info->page_offset;
+		rq_wqe_buf_set(rxq->rq, rxq->next_to_update, dma_addr,
+			       rxq->buf_len);
+		rxq->next_to_update = (rxq->next_to_update + 1) & rxq->q_mask;
+	}
+
+	if (likely(i)) {
+		hinic3_write_db(rxq->rq, rxq->q_id & 3, DB_CFLAG_DP_RQ,
+				rxq->next_to_update << HINIC3_NORMAL_RQ_WQE);
+		rxq->delta -= i;
+		rxq->next_to_alloc = rxq->next_to_update;
+	}
+
+	return i;
+}
+
+static void hinic3_add_rx_frag(struct hinic3_rxq *rxq,
+			       struct hinic3_rx_info *rx_info,
+			       struct sk_buff *skb, u32 size)
+{
+	struct page *page;
+	u8 *va;
+
+	page = rx_info->page;
+	va = (u8 *)page_address(page) + rx_info->page_offset;
+	net_prefetch(va);
+
+	page_pool_dma_sync_for_cpu(rxq->page_pool, page, rx_info->page_offset,
+				   rxq->buf_len);
+
+	if (size <= HINIC3_RX_HDR_SIZE && !skb_is_nonlinear(skb)) {
+		memcpy(__skb_put(skb, size), va,
+		       ALIGN(size, sizeof(long)));
+		page_pool_put_full_page(rxq->page_pool, page, false);
+
+		return;
+	}
+
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+			rx_info->page_offset, size, rxq->buf_len);
+	skb_mark_for_recycle(skb);
+}
+
+static void packaging_skb(struct hinic3_rxq *rxq, struct sk_buff *skb,
+			  u32 sge_num, u32 pkt_len)
+{
+	struct hinic3_rx_info *rx_info;
+	u32 temp_pkt_len = pkt_len;
+	u32 temp_sge_num = sge_num;
+	u32 sw_ci;
+	u32 size;
+
+	sw_ci = rxq->cons_idx & rxq->q_mask;
+	while (temp_sge_num) {
+		rx_info = &rxq->rx_info[sw_ci];
+		sw_ci = (sw_ci + 1) & rxq->q_mask;
+		if (unlikely(temp_pkt_len > rxq->buf_len)) {
+			size = rxq->buf_len;
+			temp_pkt_len -= rxq->buf_len;
+		} else {
+			size = temp_pkt_len;
+		}
+
+		hinic3_add_rx_frag(rxq, rx_info, skb, size);
+
+		/* clear contents of buffer_info */
+		rx_info->page = NULL;
+		temp_sge_num--;
+	}
+}
+
+static u32 hinic3_get_sge_num(struct hinic3_rxq *rxq, u32 pkt_len)
+{
+	u32 sge_num;
+
+	sge_num = pkt_len >> rxq->buf_len_shift;
+	sge_num += (pkt_len & (rxq->buf_len - 1)) ? 1 : 0;
+
+	return sge_num;
+}
+
+static struct sk_buff *hinic3_fetch_rx_buffer(struct hinic3_rxq *rxq,
+					      u32 pkt_len)
+{
+	struct sk_buff *skb;
+	u32 sge_num;
+
+	skb = napi_alloc_skb(&rxq->irq_cfg->napi, HINIC3_RX_HDR_SIZE);
+	if (unlikely(!skb))
+		return NULL;
+
+	sge_num = hinic3_get_sge_num(rxq, pkt_len);
+
+	net_prefetchw(skb->data);
+	packaging_skb(rxq, skb, sge_num, pkt_len);
+
+	rxq->cons_idx += sge_num;
+	rxq->delta += sge_num;
+
+	return skb;
+}
+
+static void hinic3_pull_tail(struct sk_buff *skb)
+{
+	skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
+	unsigned int pull_len;
+	unsigned char *va;
+
+	va = skb_frag_address(frag);
+
+	/* we need the header to contain the greater of either ETH_HLEN or
+	 * 60 bytes if the skb->len is less than 60 for skb_pad.
+	 */
+	pull_len = eth_get_headlen(skb->dev, va, HINIC3_RX_HDR_SIZE);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
+
+	/* update all of the pointers */
+	skb_frag_size_sub(frag, pull_len);
+	skb_frag_off_add(frag, pull_len);
+
+	skb->data_len -= pull_len;
+	skb->tail += pull_len;
+}
+
+static void hinic3_rx_csum(struct hinic3_rxq *rxq, u32 offload_type,
+			   u32 status, struct sk_buff *skb)
+{
+	u32 pkt_fmt = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, TUNNEL_PKT_FORMAT);
+	u32 pkt_type = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, PKT_TYPE);
+	u32 ip_type = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, IP_TYPE);
+	u32 csum_err = RQ_CQE_STATUS_GET(status, CSUM_ERR);
+	struct net_device *netdev = rxq->netdev;
+
+	if (!(netdev->features & NETIF_F_RXCSUM))
+		return;
+
+	if (unlikely(csum_err)) {
+		/* pkt type is recognized by HW, and csum is wrong */
+		skb->ip_summed = CHECKSUM_NONE;
+		return;
+	}
+
+	if (ip_type == HINIC3_RX_INVALID_IP_TYPE ||
+	    !(pkt_fmt == HINIC3_RX_PKT_FORMAT_NON_TUNNEL ||
+	      pkt_fmt == HINIC3_RX_PKT_FORMAT_VXLAN)) {
+		skb->ip_summed = CHECKSUM_NONE;
+		return;
+	}
+
+	switch (pkt_type) {
+	case HINIC3_RX_TCP_PKT:
+	case HINIC3_RX_UDP_PKT:
+	case HINIC3_RX_SCTP_PKT:
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		break;
+	default:
+		skb->ip_summed = CHECKSUM_NONE;
+		break;
+	}
+}
+
+static void hinic3_lro_set_gso_params(struct sk_buff *skb, u16 num_lro)
+{
+	struct ethhdr *eth = (struct ethhdr *)(skb->data);
+	__be16 proto;
+
+	proto = __vlan_get_protocol(skb, eth->h_proto, NULL);
+
+	skb_shinfo(skb)->gso_size = DIV_ROUND_UP(skb->len - skb_headlen(skb),
+						 num_lro);
+	skb_shinfo(skb)->gso_type = proto == htons(ETH_P_IP) ?
+				    SKB_GSO_TCPV4 : SKB_GSO_TCPV6;
+	skb_shinfo(skb)->gso_segs = num_lro;
+}
+
+static int recv_one_pkt(struct hinic3_rxq *rxq, struct hinic3_rq_cqe *rx_cqe,
+			u32 pkt_len, u32 vlan_len, u32 status)
+{
+	struct net_device *netdev = rxq->netdev;
+	struct sk_buff *skb;
+	u32 offload_type;
+	u16 num_lro;
+
+	skb = hinic3_fetch_rx_buffer(rxq, pkt_len);
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	/* place header in linear portion of buffer */
+	if (skb_is_nonlinear(skb))
+		hinic3_pull_tail(skb);
+
+	offload_type = rx_cqe->offload_type;
+	hinic3_rx_csum(rxq, offload_type, status, skb);
+
+	num_lro = RQ_CQE_STATUS_GET(status, NUM_LRO);
+	if (num_lro)
+		hinic3_lro_set_gso_params(skb, num_lro);
+
+	skb_record_rx_queue(skb, rxq->q_id);
+	skb->protocol = eth_type_trans(skb, netdev);
+
+	if (skb_has_frag_list(skb)) {
+		napi_gro_flush(&rxq->irq_cfg->napi, false);
+		netif_receive_skb(skb);
+	} else {
+		napi_gro_receive(&rxq->irq_cfg->napi, skb);
+	}
+
+	return 0;
+}
+
+int hinic3_rx_poll(struct hinic3_rxq *rxq, int budget)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(rxq->netdev);
+	u32 sw_ci, status, pkt_len, vlan_len;
+	struct hinic3_rq_cqe *rx_cqe;
+	u32 num_wqe = 0;
+	int nr_pkts = 0;
+	u16 num_lro;
+
+	while (likely(nr_pkts < budget)) {
+		sw_ci = rxq->cons_idx & rxq->q_mask;
+		rx_cqe = rxq->cqe_arr + sw_ci;
+		status = rx_cqe->status;
+		if (!RQ_CQE_STATUS_GET(status, RXDONE))
+			break;
+
+		/* make sure we read rx_done before packet length */
+		rmb();
+
+		vlan_len = rx_cqe->vlan_len;
+		pkt_len = RQ_CQE_SGE_GET(vlan_len, LEN);
+		if (recv_one_pkt(rxq, rx_cqe, pkt_len, vlan_len, status))
+			break;
+
+		nr_pkts++;
+		num_lro = RQ_CQE_STATUS_GET(status, NUM_LRO);
+		if (num_lro)
+			num_wqe += hinic3_get_sge_num(rxq, pkt_len);
+
+		rx_cqe->status = 0;
+
+		if (num_wqe >= nic_dev->lro_replenish_thld)
+			break;
+	}
+
+	if (rxq->delta >= HINIC3_RX_BUFFER_WRITE)
+		hinic3_rx_fill_buffers(rxq);
+
+	return nr_pkts;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h
new file mode 100644
index 000000000000..1cca21858d40
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_RX_H_
+#define _HINIC3_RX_H_
+
+#include <linux/bitfield.h>
+#include <linux/netdevice.h>
+
+#define RQ_CQE_OFFOLAD_TYPE_PKT_TYPE_MASK           GENMASK(4, 0)
+#define RQ_CQE_OFFOLAD_TYPE_IP_TYPE_MASK            GENMASK(6, 5)
+#define RQ_CQE_OFFOLAD_TYPE_TUNNEL_PKT_FORMAT_MASK  GENMASK(11, 8)
+#define RQ_CQE_OFFOLAD_TYPE_VLAN_EN_MASK            BIT(21)
+#define RQ_CQE_OFFOLAD_TYPE_GET(val, member) \
+	FIELD_GET(RQ_CQE_OFFOLAD_TYPE_##member##_MASK, val)
+
+#define RQ_CQE_SGE_VLAN_MASK  GENMASK(15, 0)
+#define RQ_CQE_SGE_LEN_MASK   GENMASK(31, 16)
+#define RQ_CQE_SGE_GET(val, member) \
+	FIELD_GET(RQ_CQE_SGE_##member##_MASK, val)
+
+#define RQ_CQE_STATUS_CSUM_ERR_MASK  GENMASK(15, 0)
+#define RQ_CQE_STATUS_NUM_LRO_MASK   GENMASK(23, 16)
+#define RQ_CQE_STATUS_RXDONE_MASK    BIT(31)
+#define RQ_CQE_STATUS_GET(val, member) \
+	FIELD_GET(RQ_CQE_STATUS_##member##_MASK, val)
+
+/* RX Completion information that is provided by HW for a specific RX WQE */
+struct hinic3_rq_cqe {
+	u32 status;
+	u32 vlan_len;
+	u32 offload_type;
+	u32 rsvd3;
+	u32 rsvd4;
+	u32 rsvd5;
+	u32 rsvd6;
+	u32 pkt_info;
+};
+
+struct hinic3_rq_wqe {
+	u32 buf_hi_addr;
+	u32 buf_lo_addr;
+	u32 cqe_hi_addr;
+	u32 cqe_lo_addr;
+};
+
+struct hinic3_rx_info {
+	struct page      *page;
+	u32              page_offset;
+};
+
+struct hinic3_rxq {
+	struct net_device       *netdev;
+
+	u16                     q_id;
+	u32                     q_depth;
+	u32                     q_mask;
+
+	u16                     buf_len;
+	u32                     buf_len_shift;
+
+	u32                     cons_idx;
+	u32                     delta;
+
+	u32                     irq_id;
+	u16                     msix_entry_idx;
+
+	/* cqe_arr and rx_info are arrays of rq_depth elements. Each element is
+	 * statically associated (by index) to a specific rq_wqe.
+	 */
+	struct hinic3_rq_cqe   *cqe_arr;
+	struct hinic3_rx_info  *rx_info;
+	struct page_pool       *page_pool;
+
+	struct hinic3_io_queue *rq;
+
+	struct hinic3_irq_cfg  *irq_cfg;
+	u16                    next_to_alloc;
+	u16                    next_to_update;
+	struct device          *dev; /* device for DMA mapping */
+
+	dma_addr_t             cqe_start_paddr;
+} ____cacheline_aligned;
+
+int hinic3_alloc_rxqs(struct net_device *netdev);
+void hinic3_free_rxqs(struct net_device *netdev);
+
+int hinic3_rx_poll(struct hinic3_rxq *rxq, int budget);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
new file mode 100644
index 000000000000..ae08257dd1d2
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
@@ -0,0 +1,670 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/if_vlan.h>
+#include <linux/iopoll.h>
+#include <net/ip6_checksum.h>
+#include <net/ipv6.h>
+#include <net/netdev_queues.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_tx.h"
+#include "hinic3_wq.h"
+
+#define MIN_SKB_LEN                32
+
+int hinic3_alloc_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	u16 q_id, num_txqs = nic_dev->max_qps;
+	struct pci_dev *pdev = nic_dev->pdev;
+	struct hinic3_txq *txq;
+
+	if (!num_txqs) {
+		dev_err(hwdev->dev, "Cannot allocate zero size txqs\n");
+		return -EINVAL;
+	}
+
+	nic_dev->txqs = kcalloc(num_txqs, sizeof(*nic_dev->txqs),  GFP_KERNEL);
+	if (!nic_dev->txqs)
+		return -ENOMEM;
+
+	for (q_id = 0; q_id < num_txqs; q_id++) {
+		txq = &nic_dev->txqs[q_id];
+		txq->netdev = netdev;
+		txq->q_id = q_id;
+		txq->q_depth = nic_dev->q_params.sq_depth;
+		txq->q_mask = nic_dev->q_params.sq_depth - 1;
+		txq->dev = &pdev->dev;
+	}
+
+	return 0;
+}
+
+void hinic3_free_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	kfree(nic_dev->txqs);
+}
+
+static void hinic3_set_buf_desc(struct hinic3_sq_bufdesc *buf_descs,
+				dma_addr_t addr, u32 len)
+{
+	buf_descs->hi_addr = upper_32_bits(addr);
+	buf_descs->lo_addr = lower_32_bits(addr);
+	buf_descs->len  = len;
+}
+
+static int hinic3_tx_map_skb(struct net_device *netdev, struct sk_buff *skb,
+			     struct hinic3_txq *txq,
+			     struct hinic3_tx_info *tx_info,
+			     struct hinic3_sq_wqe_combo *wqe_combo)
+{
+	struct hinic3_sq_wqe_desc *wqe_desc = wqe_combo->ctrl_bd0;
+	struct hinic3_sq_bufdesc *buf_desc = wqe_combo->bds_head;
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_dma_info *dma_info = tx_info->dma_info;
+	struct pci_dev *pdev = nic_dev->pdev;
+	skb_frag_t *frag;
+	u32 i, idx;
+	int err;
+
+	dma_info[0].dma = dma_map_single(&pdev->dev, skb->data,
+					 skb_headlen(skb), DMA_TO_DEVICE);
+	if (dma_mapping_error(&pdev->dev, dma_info[0].dma))
+		return -EFAULT;
+
+	dma_info[0].len = skb_headlen(skb);
+
+	wqe_desc->hi_addr = upper_32_bits(dma_info[0].dma);
+	wqe_desc->lo_addr = lower_32_bits(dma_info[0].dma);
+
+	wqe_desc->ctrl_len = dma_info[0].len;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		frag = &(skb_shinfo(skb)->frags[i]);
+		if (unlikely(i == wqe_combo->first_bds_num))
+			buf_desc = wqe_combo->bds_sec2;
+
+		idx = i + 1;
+		dma_info[idx].dma = skb_frag_dma_map(&pdev->dev, frag, 0,
+						     skb_frag_size(frag),
+						     DMA_TO_DEVICE);
+		if (dma_mapping_error(&pdev->dev, dma_info[idx].dma)) {
+			err = -EFAULT;
+			goto err_unmap_page;
+		}
+		dma_info[idx].len = skb_frag_size(frag);
+
+		hinic3_set_buf_desc(buf_desc, dma_info[idx].dma,
+				    dma_info[idx].len);
+		buf_desc++;
+	}
+
+	return 0;
+
+err_unmap_page:
+	while (idx > 1) {
+		idx--;
+		dma_unmap_page(&pdev->dev, dma_info[idx].dma,
+			       dma_info[idx].len, DMA_TO_DEVICE);
+	}
+	dma_unmap_single(&pdev->dev, dma_info[0].dma, dma_info[0].len,
+			 DMA_TO_DEVICE);
+	return err;
+}
+
+static void hinic3_tx_unmap_skb(struct net_device *netdev,
+				struct sk_buff *skb,
+				struct hinic3_dma_info *dma_info)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct pci_dev *pdev = nic_dev->pdev;
+	int i;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags;) {
+		i++;
+		dma_unmap_page(&pdev->dev,
+			       dma_info[i].dma,
+			       dma_info[i].len, DMA_TO_DEVICE);
+	}
+
+	dma_unmap_single(&pdev->dev, dma_info[0].dma,
+			 dma_info[0].len, DMA_TO_DEVICE);
+}
+
+union hinic3_ip {
+	struct iphdr   *v4;
+	struct ipv6hdr *v6;
+	unsigned char  *hdr;
+};
+
+union hinic3_l4 {
+	struct tcphdr *tcp;
+	struct udphdr *udp;
+	unsigned char *hdr;
+};
+
+enum hinic3_l3_type {
+	HINIC3_L3_UNKNOWN         = 0,
+	HINIC3_L3_IP6_PKT         = 1,
+	HINIC3_L3_IP4_PKT_NO_CSUM = 2,
+	HINIC3_L3_IP4_PKT_CSUM    = 3,
+};
+
+enum hinic3_l4_offload_type {
+	HINIC3_L4_OFFLOAD_DISABLE = 0,
+	HINIC3_L4_OFFLOAD_TCP     = 1,
+	HINIC3_L4_OFFLOAD_STCP    = 2,
+	HINIC3_L4_OFFLOAD_UDP     = 3,
+};
+
+/* initialize l4 offset and offload */
+static void get_inner_l4_info(struct sk_buff *skb, union hinic3_l4 *l4,
+			      u8 l4_proto, u32 *offset,
+			      enum hinic3_l4_offload_type *l4_offload)
+{
+	switch (l4_proto) {
+	case IPPROTO_TCP:
+		*l4_offload = HINIC3_L4_OFFLOAD_TCP;
+		/* To be same with TSO, payload offset begins from payload */
+		*offset = (l4->tcp->doff << TCP_HDR_DATA_OFF_UNIT_SHIFT) +
+			   TRANSPORT_OFFSET(l4->hdr, skb);
+		break;
+
+	case IPPROTO_UDP:
+		*l4_offload = HINIC3_L4_OFFLOAD_UDP;
+		*offset = TRANSPORT_OFFSET(l4->hdr, skb);
+		break;
+	default:
+		*l4_offload = HINIC3_L4_OFFLOAD_DISABLE;
+		*offset = 0;
+	}
+}
+
+static int hinic3_tx_csum(struct hinic3_txq *txq, struct hinic3_sq_task *task,
+			  struct sk_buff *skb)
+{
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	if (skb->encapsulation) {
+		union hinic3_ip ip;
+		u8 l4_proto;
+
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1, TUNNEL_FLAG);
+
+		ip.hdr = skb_network_header(skb);
+		if (ip.v4->version == 4) {
+			l4_proto = ip.v4->protocol;
+		} else if (ip.v4->version == 6) {
+			union hinic3_l4 l4;
+			unsigned char *exthdr;
+			__be16 frag_off;
+
+			exthdr = ip.hdr + sizeof(*ip.v6);
+			l4_proto = ip.v6->nexthdr;
+			l4.hdr = skb_transport_header(skb);
+			if (l4.hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data,
+						 &l4_proto, &frag_off);
+		} else {
+			l4_proto = IPPROTO_RAW;
+		}
+
+		if (l4_proto != IPPROTO_UDP ||
+		    ((struct udphdr *)skb_transport_header(skb))->dest !=
+		    VXLAN_OFFLOAD_PORT_LE) {
+			/* Unsupported tunnel packet, disable csum offload */
+			skb_checksum_help(skb);
+			return 0;
+		}
+	}
+
+	task->pkt_info0 |= SQ_TASK_INFO0_SET(1, INNER_L4_EN);
+
+	return 1;
+}
+
+static void get_inner_l3_l4_type(struct sk_buff *skb, union hinic3_ip *ip,
+				 union hinic3_l4 *l4,
+				 enum hinic3_l3_type *l3_type, u8 *l4_proto)
+{
+	unsigned char *exthdr;
+	__be16 frag_off;
+
+	if (ip->v4->version == 4) {
+		*l3_type = HINIC3_L3_IP4_PKT_CSUM;
+		*l4_proto = ip->v4->protocol;
+	} else if (ip->v4->version == 6) {
+		*l3_type = HINIC3_L3_IP6_PKT;
+		exthdr = ip->hdr + sizeof(*ip->v6);
+		*l4_proto = ip->v6->nexthdr;
+		if (exthdr != l4->hdr) {
+			ipv6_skip_exthdr(skb, exthdr - skb->data,
+					 l4_proto, &frag_off);
+		}
+	} else {
+		*l3_type = HINIC3_L3_UNKNOWN;
+		*l4_proto = 0;
+	}
+}
+
+static void hinic3_set_tso_info(struct hinic3_sq_task *task, u32 *queue_info,
+				enum hinic3_l4_offload_type l4_offload,
+				u32 offset, u32 mss)
+{
+	if (l4_offload == HINIC3_L4_OFFLOAD_TCP) {
+		*queue_info |= SQ_CTRL_QUEUE_INFO_SET(1, TSO);
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1, INNER_L4_EN);
+	} else if (l4_offload == HINIC3_L4_OFFLOAD_UDP) {
+		*queue_info |= SQ_CTRL_QUEUE_INFO_SET(1, UFO);
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1, INNER_L4_EN);
+	}
+
+	/* enable L3 calculation */
+	task->pkt_info0 |= SQ_TASK_INFO0_SET(1, INNER_L3_EN);
+
+	*queue_info |= SQ_CTRL_QUEUE_INFO_SET(offset >> 1, PLDOFF);
+
+	/* set MSS value */
+	*queue_info &= ~SQ_CTRL_QUEUE_INFO_MSS_MASK;
+	*queue_info |= SQ_CTRL_QUEUE_INFO_SET(mss, MSS);
+}
+
+static __sum16 csum_magic(union hinic3_ip *ip, unsigned short proto)
+{
+	return (ip->v4->version == 4) ?
+		csum_tcpudp_magic(ip->v4->saddr, ip->v4->daddr, 0, proto, 0) :
+		csum_ipv6_magic(&ip->v6->saddr, &ip->v6->daddr, 0, proto, 0);
+}
+
+static int hinic3_tso(struct hinic3_sq_task *task, u32 *queue_info,
+		      struct sk_buff *skb)
+{
+	enum hinic3_l4_offload_type l4_offload;
+	enum hinic3_l3_type l3_type;
+	union hinic3_ip ip;
+	union hinic3_l4 l4;
+	u8 l4_proto;
+	u32 offset;
+	int err;
+
+	if (!skb_is_gso(skb))
+		return 0;
+
+	err = skb_cow_head(skb, 0);
+	if (err < 0)
+		return err;
+
+	if (skb->encapsulation) {
+		u32 gso_type = skb_shinfo(skb)->gso_type;
+		/* L3 checksum is always enabled */
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1, OUT_L3_EN);
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1, TUNNEL_FLAG);
+
+		l4.hdr = skb_transport_header(skb);
+		ip.hdr = skb_network_header(skb);
+
+		if (gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+			l4.udp->check = ~csum_magic(&ip, IPPROTO_UDP);
+			task->pkt_info0 |= SQ_TASK_INFO0_SET(1, OUT_L4_EN);
+		}
+
+		ip.hdr = skb_inner_network_header(skb);
+		l4.hdr = skb_inner_transport_header(skb);
+	} else {
+		ip.hdr = skb_network_header(skb);
+		l4.hdr = skb_transport_header(skb);
+	}
+
+	get_inner_l3_l4_type(skb, &ip, &l4, &l3_type, &l4_proto);
+
+	if (l4_proto == IPPROTO_TCP)
+		l4.tcp->check = ~csum_magic(&ip, IPPROTO_TCP);
+
+	get_inner_l4_info(skb, &l4, l4_proto, &offset, &l4_offload);
+
+	hinic3_set_tso_info(task, queue_info, l4_offload, offset,
+			    skb_shinfo(skb)->gso_size);
+
+	return 1;
+}
+
+static void hinic3_set_vlan_tx_offload(struct hinic3_sq_task *task,
+				       u16 vlan_tag, u8 vlan_tpid)
+{
+	/* vlan_tpid: 0=select TPID0 in IPSU, 1=select TPID1 in IPSU
+	 * 2=select TPID2 in IPSU, 3=select TPID3 in IPSU,
+	 * 4=select TPID4 in IPSU
+	 */
+	task->vlan_offload = SQ_TASK_INFO3_SET(vlan_tag, VLAN_TAG) |
+			     SQ_TASK_INFO3_SET(vlan_tpid, VLAN_TPID) |
+			     SQ_TASK_INFO3_SET(1, VLAN_TAG_VALID);
+}
+
+static u32 hinic3_tx_offload(struct sk_buff *skb, struct hinic3_sq_task *task,
+			     u32 *queue_info, struct hinic3_txq *txq)
+{
+	u32 offload = 0;
+	int tso_cs_en;
+
+	task->pkt_info0 = 0;
+	task->ip_identify = 0;
+	task->rsvd = 0;
+	task->vlan_offload = 0;
+
+	tso_cs_en = hinic3_tso(task, queue_info, skb);
+	if (tso_cs_en < 0) {
+		offload = HINIC3_TX_OFFLOAD_INVALID;
+		return offload;
+	} else if (tso_cs_en) {
+		offload |= HINIC3_TX_OFFLOAD_TSO;
+	} else {
+		tso_cs_en = hinic3_tx_csum(txq, task, skb);
+		if (tso_cs_en)
+			offload |= HINIC3_TX_OFFLOAD_CSUM;
+	}
+
+#define VLAN_INSERT_MODE_MAX 5
+	if (unlikely(skb_vlan_tag_present(skb))) {
+		/* select vlan insert mode by qid, default 802.1Q Tag type */
+		hinic3_set_vlan_tx_offload(task, skb_vlan_tag_get(skb),
+					   txq->q_id % VLAN_INSERT_MODE_MAX);
+		offload |= HINIC3_TX_OFFLOAD_VLAN;
+	}
+
+	if (unlikely(SQ_CTRL_QUEUE_INFO_GET(*queue_info, PLDOFF) >
+		     SQ_CTRL_MAX_PLDOFF)) {
+		offload = HINIC3_TX_OFFLOAD_INVALID;
+		return offload;
+	}
+
+	return offload;
+}
+
+static u16 hinic3_get_and_update_sq_owner(struct hinic3_io_queue *sq,
+					  u16 curr_pi, u16 wqebb_cnt)
+{
+	u16 owner = sq->owner;
+
+	if (unlikely(curr_pi + wqebb_cnt >= sq->wq.q_depth))
+		sq->owner = !sq->owner;
+
+	return owner;
+}
+
+static u16 hinic3_set_wqe_combo(struct hinic3_txq *txq,
+				struct hinic3_sq_wqe_combo *wqe_combo,
+				u32 offload, u16 num_sge, u16 *curr_pi)
+{
+	struct hinic3_sq_bufdesc *first_part_wqebbs, *second_part_wqebbs;
+	u16 first_part_wqebbs_num, tmp_pi;
+
+	wqe_combo->ctrl_bd0 = hinic3_wq_get_one_wqebb(&txq->sq->wq, curr_pi);
+	if (!offload && num_sge == 1) {
+		wqe_combo->wqe_type = SQ_WQE_COMPACT_TYPE;
+		return hinic3_get_and_update_sq_owner(txq->sq, *curr_pi, 1);
+	}
+
+	wqe_combo->wqe_type = SQ_WQE_EXTENDED_TYPE;
+
+	if (offload) {
+		wqe_combo->task = hinic3_wq_get_one_wqebb(&txq->sq->wq,
+							  &tmp_pi);
+		wqe_combo->task_type = SQ_WQE_TASKSECT_16BYTES;
+	} else {
+		wqe_combo->task_type = SQ_WQE_TASKSECT_46BITS;
+	}
+
+	if (num_sge > 1) {
+		/* first wqebb contain bd0, and bd size is equal to sq wqebb
+		 * size, so we use (num_sge - 1) as wanted weqbb_cnt
+		 */
+		hinic3_wq_get_multi_wqebbs(&txq->sq->wq, num_sge - 1, &tmp_pi,
+					   &first_part_wqebbs,
+					   &second_part_wqebbs,
+					   &first_part_wqebbs_num);
+		wqe_combo->bds_head = first_part_wqebbs;
+		wqe_combo->bds_sec2 = second_part_wqebbs;
+		wqe_combo->first_bds_num = first_part_wqebbs_num;
+	}
+
+	return hinic3_get_and_update_sq_owner(txq->sq, *curr_pi,
+					      num_sge + !!offload);
+}
+
+static void hinic3_prepare_sq_ctrl(struct hinic3_sq_wqe_combo *wqe_combo,
+				   u32 queue_info, int nr_descs, u16 owner)
+{
+	struct hinic3_sq_wqe_desc *wqe_desc = wqe_combo->ctrl_bd0;
+
+	if (wqe_combo->wqe_type == SQ_WQE_COMPACT_TYPE) {
+		wqe_desc->ctrl_len |=
+		    SQ_CTRL_SET(SQ_NORMAL_WQE, DATA_FORMAT) |
+		    SQ_CTRL_SET(wqe_combo->wqe_type, EXTENDED) |
+		    SQ_CTRL_SET(owner, OWNER);
+
+		/* compact wqe queue_info will transfer to chip */
+		wqe_desc->queue_info = 0;
+		return;
+	}
+
+	wqe_desc->ctrl_len |= SQ_CTRL_SET(nr_descs, BUFDESC_NUM) |
+			      SQ_CTRL_SET(wqe_combo->task_type, TASKSECT_LEN) |
+			      SQ_CTRL_SET(SQ_NORMAL_WQE, DATA_FORMAT) |
+			      SQ_CTRL_SET(wqe_combo->wqe_type, EXTENDED) |
+			      SQ_CTRL_SET(owner, OWNER);
+
+	wqe_desc->queue_info = queue_info;
+	wqe_desc->queue_info |= SQ_CTRL_QUEUE_INFO_SET(1, UC);
+
+	if (!SQ_CTRL_QUEUE_INFO_GET(wqe_desc->queue_info, MSS)) {
+		wqe_desc->queue_info |=
+		    SQ_CTRL_QUEUE_INFO_SET(HINIC3_TX_MSS_DEFAULT, MSS);
+	} else if (SQ_CTRL_QUEUE_INFO_GET(wqe_desc->queue_info, MSS) <
+		   HINIC3_TX_MSS_MIN) {
+		/* mss should not be less than 80 */
+		wqe_desc->queue_info &= ~SQ_CTRL_QUEUE_INFO_MSS_MASK;
+		wqe_desc->queue_info |=
+		    SQ_CTRL_QUEUE_INFO_SET(HINIC3_TX_MSS_MIN, MSS);
+	}
+}
+
+static netdev_tx_t hinic3_send_one_skb(struct sk_buff *skb,
+				       struct net_device *netdev,
+				       struct hinic3_txq *txq)
+{
+	struct hinic3_sq_wqe_combo wqe_combo = {};
+	struct hinic3_tx_info *tx_info;
+	struct hinic3_txq *tx_q = txq;
+	u32 offload, queue_info = 0;
+	struct hinic3_sq_task task;
+	u16 wqebb_cnt, num_sge;
+	u16 saved_wq_prod_idx;
+	u16 owner, pi = 0;
+	u8 saved_sq_owner;
+	int err;
+
+	if (unlikely(skb->len < MIN_SKB_LEN)) {
+		if (skb_pad(skb, MIN_SKB_LEN - skb->len))
+			goto err_out;
+
+		skb->len = MIN_SKB_LEN;
+	}
+
+	num_sge = skb_shinfo(skb)->nr_frags + 1;
+	/* assume normal wqe format + 1 wqebb for task info */
+	wqebb_cnt = num_sge + 1;
+
+	if (unlikely(hinic3_wq_free_wqebbs(&txq->sq->wq) < wqebb_cnt)) {
+		if (likely(wqebb_cnt > txq->tx_stop_thrs))
+			txq->tx_stop_thrs = min(wqebb_cnt, txq->tx_start_thrs);
+
+		netif_subqueue_try_stop(netdev, tx_q->sq->q_id,
+					hinic3_wq_free_wqebbs(&tx_q->sq->wq),
+					tx_q->tx_start_thrs);
+
+		return NETDEV_TX_BUSY;
+	}
+
+	offload = hinic3_tx_offload(skb, &task, &queue_info, txq);
+	if (unlikely(offload == HINIC3_TX_OFFLOAD_INVALID)) {
+		goto err_drop_pkt;
+	} else if (!offload) {
+		wqebb_cnt -= 1;
+		if (unlikely(num_sge == 1 &&
+			     skb->len > HINIC3_COMPACT_WQEE_SKB_MAX_LEN))
+			goto err_drop_pkt;
+	}
+
+	saved_wq_prod_idx = txq->sq->wq.prod_idx;
+	saved_sq_owner = txq->sq->owner;
+
+	owner = hinic3_set_wqe_combo(txq, &wqe_combo, offload, num_sge, &pi);
+	if (offload)
+		*wqe_combo.task = task;
+
+	tx_info = &txq->tx_info[pi];
+	tx_info->skb = skb;
+	tx_info->wqebb_cnt = wqebb_cnt;
+
+	err = hinic3_tx_map_skb(netdev, skb, txq, tx_info, &wqe_combo);
+	if (err) {
+		/* Rollback work queue to reclaim the wqebb we did not use */
+		txq->sq->wq.prod_idx = saved_wq_prod_idx;
+		txq->sq->owner = saved_sq_owner;
+		goto err_drop_pkt;
+	}
+
+	netdev_tx_sent_queue(netdev_get_tx_queue(netdev, txq->sq->q_id),
+			     skb->len);
+	netif_subqueue_maybe_stop(netdev, tx_q->sq->q_id,
+				  hinic3_wq_free_wqebbs(&tx_q->sq->wq),
+				  tx_q->tx_stop_thrs,
+				  tx_q->tx_start_thrs);
+
+	hinic3_prepare_sq_ctrl(&wqe_combo, queue_info, num_sge, owner);
+	hinic3_write_db(txq->sq, 0, DB_CFLAG_DP_SQ,
+			hinic3_get_sq_local_pi(txq->sq));
+
+	return NETDEV_TX_OK;
+
+err_drop_pkt:
+	dev_kfree_skb_any(skb);
+
+err_out:
+	return NETDEV_TX_OK;
+}
+
+netdev_tx_t hinic3_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 q_id = skb_get_queue_mapping(skb);
+
+	if (unlikely(!netif_carrier_ok(netdev)))
+		goto err_drop_pkt;
+
+	if (unlikely(q_id >= nic_dev->q_params.num_qps))
+		goto err_drop_pkt;
+
+	return hinic3_send_one_skb(skb, netdev, &nic_dev->txqs[q_id]);
+
+err_drop_pkt:
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
+}
+
+static bool is_hw_complete_sq_process(struct hinic3_io_queue *sq)
+{
+	u16 sw_pi, hw_ci;
+
+	sw_pi = hinic3_get_sq_local_pi(sq);
+	hw_ci = hinic3_get_sq_hw_ci(sq);
+
+	return sw_pi == hw_ci;
+}
+
+#define HINIC3_FLUSH_QUEUE_POLL_SLEEP_US   10000
+#define HINIC3_FLUSH_QUEUE_POLL_TIMEOUT_US 10000000
+static int hinic3_stop_sq(struct hinic3_txq *txq)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(txq->netdev);
+	int err, rc;
+
+	err = read_poll_timeout(hinic3_force_drop_tx_pkt, rc,
+				is_hw_complete_sq_process(txq->sq) || rc,
+				HINIC3_FLUSH_QUEUE_POLL_SLEEP_US,
+				HINIC3_FLUSH_QUEUE_POLL_TIMEOUT_US,
+				true, nic_dev->hwdev);
+	if (rc)
+		return rc;
+	else
+		return err;
+}
+
+/* packet transmission should be stopped before calling this function */
+void hinic3_flush_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 qid;
+	int err;
+
+	for (qid = 0; qid < nic_dev->q_params.num_qps; qid++) {
+		err = hinic3_stop_sq(&nic_dev->txqs[qid]);
+		netdev_tx_reset_subqueue(netdev, qid);
+		if (err)
+			netdev_err(netdev, "Failed to stop sq%u\n", qid);
+	}
+}
+
+#define HINIC3_BDS_PER_SQ_WQEBB \
+	(HINIC3_SQ_WQEBB_SIZE / sizeof(struct hinic3_sq_bufdesc))
+
+bool hinic3_tx_poll(struct hinic3_txq *txq, int budget)
+{
+	struct net_device *netdev = txq->netdev;
+	u16 hw_ci, sw_ci, q_id = txq->sq->q_id;
+	struct hinic3_tx_info *tx_info;
+	struct hinic3_txq *tx_q = txq;
+	unsigned int bytes_compl = 0;
+	unsigned int pkts = 0;
+	u16 wqebb_cnt = 0;
+
+	hw_ci = hinic3_get_sq_hw_ci(txq->sq);
+	dma_rmb();
+	sw_ci = hinic3_get_sq_local_ci(txq->sq);
+
+	do {
+		tx_info = &txq->tx_info[sw_ci];
+
+		/* Did all wqebb of this wqe complete? */
+		if (hw_ci == sw_ci ||
+		    ((hw_ci - sw_ci) & txq->q_mask) < tx_info->wqebb_cnt)
+			break;
+
+		sw_ci = (sw_ci + tx_info->wqebb_cnt) & txq->q_mask;
+		net_prefetch(&txq->tx_info[sw_ci]);
+
+		wqebb_cnt += tx_info->wqebb_cnt;
+		bytes_compl += tx_info->skb->len;
+		pkts++;
+
+		hinic3_tx_unmap_skb(netdev, tx_info->skb, tx_info->dma_info);
+		napi_consume_skb(tx_info->skb, budget);
+		tx_info->skb = NULL;
+	} while (likely(pkts < HINIC3_TX_POLL_WEIGHT));
+
+	hinic3_wq_put_wqebbs(&txq->sq->wq, wqebb_cnt);
+
+	netif_subqueue_completed_wake(netdev, q_id, pkts, bytes_compl,
+				      hinic3_wq_free_wqebbs(&tx_q->sq->wq),
+				      tx_q->tx_start_thrs);
+
+	return pkts == HINIC3_TX_POLL_WEIGHT;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h
new file mode 100644
index 000000000000..9e505cc19dd5
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_TX_H_
+#define _HINIC3_TX_H_
+
+#include <linux/bitops.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/netdevice.h>
+#include <net/checksum.h>
+
+#define VXLAN_OFFLOAD_PORT_LE            cpu_to_be16(4789)
+#define TCP_HDR_DATA_OFF_UNIT_SHIFT      2
+#define TRANSPORT_OFFSET(l4_hdr, skb)    ((l4_hdr) - (skb)->data)
+
+#define HINIC3_COMPACT_WQEE_SKB_MAX_LEN  16383
+#define HINIC3_TX_POLL_WEIGHT		 64
+#define HINIC3_DEFAULT_STOP_THRS	 6
+#define HINIC3_DEFAULT_START_THRS	 24
+
+enum sq_wqe_data_format {
+	SQ_NORMAL_WQE = 0,
+};
+
+enum sq_wqe_ec_type {
+	SQ_WQE_COMPACT_TYPE  = 0,
+	SQ_WQE_EXTENDED_TYPE = 1,
+};
+
+enum sq_wqe_tasksect_len_type {
+	SQ_WQE_TASKSECT_46BITS  = 0,
+	SQ_WQE_TASKSECT_16BYTES = 1,
+};
+
+enum hinic3_tx_offload_type {
+	HINIC3_TX_OFFLOAD_TSO     = BIT(0),
+	HINIC3_TX_OFFLOAD_CSUM    = BIT(1),
+	HINIC3_TX_OFFLOAD_VLAN    = BIT(2),
+	HINIC3_TX_OFFLOAD_INVALID = BIT(3),
+	HINIC3_TX_OFFLOAD_ESP     = BIT(4),
+};
+
+#define SQ_CTRL_BUFDESC_NUM_MASK   GENMASK(26, 19)
+#define SQ_CTRL_TASKSECT_LEN_MASK  BIT(27)
+#define SQ_CTRL_DATA_FORMAT_MASK   BIT(28)
+#define SQ_CTRL_EXTENDED_MASK      BIT(30)
+#define SQ_CTRL_OWNER_MASK         BIT(31)
+#define SQ_CTRL_SET(val, member) \
+	FIELD_PREP(SQ_CTRL_##member##_MASK, val)
+
+#define SQ_CTRL_QUEUE_INFO_PLDOFF_MASK  GENMASK(9, 2)
+#define SQ_CTRL_QUEUE_INFO_UFO_MASK     BIT(10)
+#define SQ_CTRL_QUEUE_INFO_TSO_MASK     BIT(11)
+#define SQ_CTRL_QUEUE_INFO_MSS_MASK     GENMASK(26, 13)
+#define SQ_CTRL_QUEUE_INFO_UC_MASK      BIT(28)
+
+#define SQ_CTRL_QUEUE_INFO_SET(val, member) \
+	FIELD_PREP(SQ_CTRL_QUEUE_INFO_##member##_MASK, val)
+#define SQ_CTRL_QUEUE_INFO_GET(val, member) \
+	FIELD_GET(SQ_CTRL_QUEUE_INFO_##member##_MASK, val)
+
+#define SQ_CTRL_MAX_PLDOFF  221
+
+#define SQ_TASK_INFO0_TUNNEL_FLAG_MASK  BIT(19)
+#define SQ_TASK_INFO0_INNER_L4_EN_MASK  BIT(24)
+#define SQ_TASK_INFO0_INNER_L3_EN_MASK  BIT(25)
+#define SQ_TASK_INFO0_OUT_L4_EN_MASK    BIT(27)
+#define SQ_TASK_INFO0_OUT_L3_EN_MASK    BIT(28)
+#define SQ_TASK_INFO0_SET(val, member) \
+	FIELD_PREP(SQ_TASK_INFO0_##member##_MASK, val)
+
+#define SQ_TASK_INFO3_VLAN_TAG_MASK        GENMASK(15, 0)
+#define SQ_TASK_INFO3_VLAN_TPID_MASK       GENMASK(18, 16)
+#define SQ_TASK_INFO3_VLAN_TAG_VALID_MASK  BIT(19)
+#define SQ_TASK_INFO3_SET(val, member) \
+	FIELD_PREP(SQ_TASK_INFO3_##member##_MASK, val)
+
+struct hinic3_sq_wqe_desc {
+	u32 ctrl_len;
+	u32 queue_info;
+	u32 hi_addr;
+	u32 lo_addr;
+};
+
+struct hinic3_sq_task {
+	u32 pkt_info0;
+	u32 ip_identify;
+	u32 rsvd;
+	u32 vlan_offload;
+};
+
+struct hinic3_sq_wqe_combo {
+	struct hinic3_sq_wqe_desc *ctrl_bd0;
+	struct hinic3_sq_task     *task;
+	struct hinic3_sq_bufdesc  *bds_head;
+	struct hinic3_sq_bufdesc  *bds_sec2;
+	u16                       first_bds_num;
+	u32                       wqe_type;
+	u32                       task_type;
+};
+
+struct hinic3_dma_info {
+	dma_addr_t dma;
+	u32        len;
+};
+
+struct hinic3_tx_info {
+	struct sk_buff         *skb;
+	u16                    wqebb_cnt;
+	struct hinic3_dma_info *dma_info;
+};
+
+struct hinic3_txq {
+	struct net_device       *netdev;
+	struct device           *dev;
+
+	u16                     q_id;
+	u16                     tx_stop_thrs;
+	u16                     tx_start_thrs;
+	u32                     q_mask;
+	u32                     q_depth;
+
+	struct hinic3_tx_info   *tx_info;
+	struct hinic3_io_queue  *sq;
+} ____cacheline_aligned;
+
+int hinic3_alloc_txqs(struct net_device *netdev);
+void hinic3_free_txqs(struct net_device *netdev);
+
+netdev_tx_t hinic3_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
+bool hinic3_tx_poll(struct hinic3_txq *txq, int budget);
+void hinic3_flush_txqs(struct net_device *netdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c
new file mode 100644
index 000000000000..2ac7efcd1365
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/dma-mapping.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_wq.h"
+
+void hinic3_wq_get_multi_wqebbs(struct hinic3_wq *wq,
+				u16 num_wqebbs, u16 *prod_idx,
+				struct hinic3_sq_bufdesc **first_part_wqebbs,
+				struct hinic3_sq_bufdesc **second_part_wqebbs,
+				u16 *first_part_wqebbs_num)
+{
+	u32 idx, remaining;
+
+	idx = wq->prod_idx & wq->idx_mask;
+	wq->prod_idx += num_wqebbs;
+	*prod_idx = idx;
+	*first_part_wqebbs = get_q_element(&wq->qpages, idx, &remaining);
+	if (likely(remaining >= num_wqebbs)) {
+		*first_part_wqebbs_num = num_wqebbs;
+		*second_part_wqebbs = NULL;
+	} else {
+		*first_part_wqebbs_num = remaining;
+		idx += remaining;
+		*second_part_wqebbs = get_q_element(&wq->qpages, idx, NULL);
+	}
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h
new file mode 100644
index 000000000000..ab37893efd7e
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_WQ_H_
+#define _HINIC3_WQ_H_
+
+#include <linux/io.h>
+
+#include "hinic3_queue_common.h"
+
+struct hinic3_sq_bufdesc {
+	/* 31-bits Length, L2NIC only uses length[17:0] */
+	u32 len;
+	u32 rsvd;
+	u32 hi_addr;
+	u32 lo_addr;
+};
+
+/* Work queue is used to submit elements (tx, rx, cmd) to hw.
+ * Driver is the producer that advances prod_idx. cons_idx is advanced when
+ * HW reports completions of previously submitted elements.
+ */
+struct hinic3_wq {
+	struct hinic3_queue_pages qpages;
+	/* Unmasked producer/consumer indices that are advanced to natural
+	 * integer overflow regardless of queue depth.
+	 */
+	u16                       cons_idx;
+	u16                       prod_idx;
+
+	u32                       q_depth;
+	u16                       idx_mask;
+
+	/* Work Queue (logical WQEBB array) is mapped to hw via Chip Logical
+	 * Address (CLA) using 1 of 2 levels:
+	 *     level 0 - direct mapping of single wq page
+	 *     level 1 - indirect mapping of multiple pages via additional page
+	 *               table.
+	 * When wq uses level 1, wq_block will hold the allocated indirection
+	 * table.
+	 */
+	dma_addr_t                wq_block_paddr;
+	__be64                    *wq_block_vaddr;
+} ____cacheline_aligned;
+
+/* Get number of elements in work queue that are in-use. */
+static inline u16 hinic3_wq_get_used(const struct hinic3_wq *wq)
+{
+	return READ_ONCE(wq->prod_idx) - READ_ONCE(wq->cons_idx);
+}
+
+static inline u16 hinic3_wq_free_wqebbs(struct hinic3_wq *wq)
+{
+	/* Don't allow queue to become completely full, report (free - 1). */
+	return wq->q_depth - hinic3_wq_get_used(wq) - 1;
+}
+
+static inline void *hinic3_wq_get_one_wqebb(struct hinic3_wq *wq, u16 *pi)
+{
+	*pi = wq->prod_idx & wq->idx_mask;
+	wq->prod_idx++;
+	return get_q_element(&wq->qpages, *pi, NULL);
+}
+
+static inline void hinic3_wq_put_wqebbs(struct hinic3_wq *wq, u16 num_wqebbs)
+{
+	wq->cons_idx += num_wqebbs;
+}
+
+void hinic3_wq_get_multi_wqebbs(struct hinic3_wq *wq,
+				u16 num_wqebbs, u16 *prod_idx,
+				struct hinic3_sq_bufdesc **first_part_wqebbs,
+				struct hinic3_sq_bufdesc **second_part_wqebbs,
+				u16 *first_part_wqebbs_num);
+
+#endif
diff --git a/drivers/net/ethernet/ibm/Kconfig b/drivers/net/ethernet/ibm/Kconfig
index c0c112d95b89..4f4b23465c47 100644
--- a/drivers/net/ethernet/ibm/Kconfig
+++ b/drivers/net/ethernet/ibm/Kconfig
@@ -27,6 +27,19 @@ config IBMVETH
 	  To compile this driver as a module, choose M here. The module will
 	  be called ibmveth.
 
+config IBMVETH_KUNIT_TEST
+	bool "KUnit test for IBM LAN Virtual Ethernet support" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	depends on KUNIT=y && IBMVETH=y
+	default KUNIT_ALL_TESTS
+	help
+	  This builds unit tests for the IBM LAN Virtual Ethernet driver.
+
+	  For more information on KUnit and unit tests in general, please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
 source "drivers/net/ethernet/ibm/emac/Kconfig"
 
 config EHEA
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 04192190beba..24046fe16634 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -39,8 +39,6 @@
 #include "ibmveth.h"
 
 static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance);
-static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
-				       bool reuse);
 static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev);
 
 static struct kobj_type ktype_veth_pool;
@@ -231,7 +229,10 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter,
 		index = pool->free_map[free_index];
 		skb = NULL;
 
-		BUG_ON(index == IBM_VETH_INVALID_MAP);
+		if (WARN_ON(index == IBM_VETH_INVALID_MAP)) {
+			schedule_work(&adapter->work);
+			goto bad_index_failure;
+		}
 
 		/* are we allocating a new buffer or recycling an old one */
 		if (pool->skbuff[index])
@@ -300,6 +301,7 @@ failure:
 		                 DMA_FROM_DEVICE);
 	dev_kfree_skb_any(pool->skbuff[index]);
 	pool->skbuff[index] = NULL;
+bad_index_failure:
 	adapter->replenish_add_buff_failure++;
 
 	mb();
@@ -370,20 +372,36 @@ static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter,
 	}
 }
 
-/* remove a buffer from a pool */
-static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
-					    u64 correlator, bool reuse)
+/**
+ * ibmveth_remove_buffer_from_pool - remove a buffer from a pool
+ * @adapter: adapter instance
+ * @correlator: identifies pool and index
+ * @reuse: whether to reuse buffer
+ *
+ * Return:
+ * * %0       - success
+ * * %-EINVAL - correlator maps to pool or index out of range
+ * * %-EFAULT - pool and index map to null skb
+ */
+static int ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
+					   u64 correlator, bool reuse)
 {
 	unsigned int pool  = correlator >> 32;
 	unsigned int index = correlator & 0xffffffffUL;
 	unsigned int free_index;
 	struct sk_buff *skb;
 
-	BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS);
-	BUG_ON(index >= adapter->rx_buff_pool[pool].size);
+	if (WARN_ON(pool >= IBMVETH_NUM_BUFF_POOLS) ||
+	    WARN_ON(index >= adapter->rx_buff_pool[pool].size)) {
+		schedule_work(&adapter->work);
+		return -EINVAL;
+	}
 
 	skb = adapter->rx_buff_pool[pool].skbuff[index];
-	BUG_ON(skb == NULL);
+	if (WARN_ON(!skb)) {
+		schedule_work(&adapter->work);
+		return -EFAULT;
+	}
 
 	/* if we are going to reuse the buffer then keep the pointers around
 	 * but mark index as available. replenish will see the skb pointer and
@@ -411,6 +429,8 @@ static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
 	mb();
 
 	atomic_dec(&(adapter->rx_buff_pool[pool].available));
+
+	return 0;
 }
 
 /* get the current buffer on the rx queue */
@@ -420,24 +440,44 @@ static inline struct sk_buff *ibmveth_rxq_get_buffer(struct ibmveth_adapter *ada
 	unsigned int pool = correlator >> 32;
 	unsigned int index = correlator & 0xffffffffUL;
 
-	BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS);
-	BUG_ON(index >= adapter->rx_buff_pool[pool].size);
+	if (WARN_ON(pool >= IBMVETH_NUM_BUFF_POOLS) ||
+	    WARN_ON(index >= adapter->rx_buff_pool[pool].size)) {
+		schedule_work(&adapter->work);
+		return NULL;
+	}
 
 	return adapter->rx_buff_pool[pool].skbuff[index];
 }
 
-static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
-				       bool reuse)
+/**
+ * ibmveth_rxq_harvest_buffer - Harvest buffer from pool
+ *
+ * @adapter: pointer to adapter
+ * @reuse:   whether to reuse buffer
+ *
+ * Context: called from ibmveth_poll
+ *
+ * Return:
+ * * %0    - success
+ * * other - non-zero return from ibmveth_remove_buffer_from_pool
+ */
+static int ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
+				      bool reuse)
 {
 	u64 cor;
+	int rc;
 
 	cor = adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator;
-	ibmveth_remove_buffer_from_pool(adapter, cor, reuse);
+	rc = ibmveth_remove_buffer_from_pool(adapter, cor, reuse);
+	if (unlikely(rc))
+		return rc;
 
 	if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
 		adapter->rx_queue.index = 0;
 		adapter->rx_queue.toggle = !adapter->rx_queue.toggle;
 	}
+
+	return 0;
 }
 
 static void ibmveth_free_tx_ltb(struct ibmveth_adapter *adapter, int idx)
@@ -709,6 +749,35 @@ static int ibmveth_close(struct net_device *netdev)
 	return 0;
 }
 
+/**
+ * ibmveth_reset - Handle scheduled reset work
+ *
+ * @w: pointer to work_struct embedded in adapter structure
+ *
+ * Context: This routine acquires rtnl_mutex and disables its NAPI through
+ *          ibmveth_close. It can't be called directly in a context that has
+ *          already acquired rtnl_mutex or disabled its NAPI, or directly from
+ *          a poll routine.
+ *
+ * Return: void
+ */
+static void ibmveth_reset(struct work_struct *w)
+{
+	struct ibmveth_adapter *adapter = container_of(w, struct ibmveth_adapter, work);
+	struct net_device *netdev = adapter->netdev;
+
+	netdev_dbg(netdev, "reset starting\n");
+
+	rtnl_lock();
+
+	dev_close(adapter->netdev);
+	dev_open(adapter->netdev, NULL);
+
+	rtnl_unlock();
+
+	netdev_dbg(netdev, "reset complete\n");
+}
+
 static int ibmveth_set_link_ksettings(struct net_device *dev,
 				      const struct ethtool_link_ksettings *cmd)
 {
@@ -1324,7 +1393,8 @@ restart_poll:
 			wmb(); /* suggested by larson1 */
 			adapter->rx_invalid_buffer++;
 			netdev_dbg(netdev, "recycling invalid buffer\n");
-			ibmveth_rxq_harvest_buffer(adapter, true);
+			if (unlikely(ibmveth_rxq_harvest_buffer(adapter, true)))
+				break;
 		} else {
 			struct sk_buff *skb, *new_skb;
 			int length = ibmveth_rxq_frame_length(adapter);
@@ -1334,6 +1404,8 @@ restart_poll:
 			__sum16 iph_check = 0;
 
 			skb = ibmveth_rxq_get_buffer(adapter);
+			if (unlikely(!skb))
+				break;
 
 			/* if the large packet bit is set in the rx queue
 			 * descriptor, the mss will be written by PHYP eight
@@ -1357,10 +1429,12 @@ restart_poll:
 				if (rx_flush)
 					ibmveth_flush_buffer(skb->data,
 						length + offset);
-				ibmveth_rxq_harvest_buffer(adapter, true);
+				if (unlikely(ibmveth_rxq_harvest_buffer(adapter, true)))
+					break;
 				skb = new_skb;
 			} else {
-				ibmveth_rxq_harvest_buffer(adapter, false);
+				if (unlikely(ibmveth_rxq_harvest_buffer(adapter, false)))
+					break;
 				skb_reserve(skb, offset);
 			}
 
@@ -1407,7 +1481,10 @@ restart_poll:
 	 * then check once more to make sure we are done.
 	 */
 	lpar_rc = h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_ENABLE);
-	BUG_ON(lpar_rc != H_SUCCESS);
+	if (WARN_ON(lpar_rc != H_SUCCESS)) {
+		schedule_work(&adapter->work);
+		goto out;
+	}
 
 	if (ibmveth_rxq_pending_buffer(adapter) && napi_schedule(napi)) {
 		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
@@ -1428,7 +1505,7 @@ static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance)
 	if (napi_schedule_prep(&adapter->napi)) {
 		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
 				       VIO_IRQ_DISABLE);
-		BUG_ON(lpar_rc != H_SUCCESS);
+		WARN_ON(lpar_rc != H_SUCCESS);
 		__napi_schedule(&adapter->napi);
 	}
 	return IRQ_HANDLED;
@@ -1670,6 +1747,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 
 	adapter->vdev = dev;
 	adapter->netdev = netdev;
+	INIT_WORK(&adapter->work, ibmveth_reset);
 	adapter->mcastFilterSize = be32_to_cpu(*mcastFilterSize_p);
 	ibmveth_init_link_settings(netdev);
 
@@ -1762,6 +1840,8 @@ static void ibmveth_remove(struct vio_dev *dev)
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
 	int i;
 
+	cancel_work_sync(&adapter->work);
+
 	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
 		kobject_put(&adapter->rx_buff_pool[i].kobj);
 
@@ -1791,6 +1871,26 @@ static ssize_t veth_pool_show(struct kobject *kobj,
 	return 0;
 }
 
+/**
+ * veth_pool_store - sysfs store handler for pool attributes
+ * @kobj: kobject embedded in pool
+ * @attr: attribute being changed
+ * @buf: value being stored
+ * @count: length of @buf in bytes
+ *
+ * Stores new value in pool attribute. Verifies the range of the new value for
+ * size and buff_size. Verifies that at least one pool remains available to
+ * receive MTU-sized packets.
+ *
+ * Context: Process context.
+ *          Takes and releases rtnl_mutex to ensure correct ordering of close
+ *	    and open calls.
+ * Return:
+ * * %-EPERM  - Not allowed to disabled all MTU-sized buffer pools
+ * * %-EINVAL - New pool size or buffer size is out of range
+ * * count    - Return count for success
+ * * other    - Return value from a failed ibmveth_open call
+ */
 static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 			       const char *buf, size_t count)
 {
@@ -1800,28 +1900,30 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 	struct net_device *netdev = dev_get_drvdata(kobj_to_dev(kobj->parent));
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
 	long value = simple_strtol(buf, NULL, 10);
+	bool change = false;
+	u32 newbuff_size;
+	u32 oldbuff_size;
+	int newactive;
+	int oldactive;
+	u32 newsize;
+	u32 oldsize;
 	long rc;
 
 	rtnl_lock();
 
+	oldbuff_size = pool->buff_size;
+	oldactive = pool->active;
+	oldsize = pool->size;
+
+	newbuff_size = oldbuff_size;
+	newactive = oldactive;
+	newsize = oldsize;
+
 	if (attr == &veth_active_attr) {
-		if (value && !pool->active) {
-			if (netif_running(netdev)) {
-				if (ibmveth_alloc_buffer_pool(pool)) {
-					netdev_err(netdev,
-						   "unable to alloc pool\n");
-					rc = -ENOMEM;
-					goto unlock_err;
-				}
-				pool->active = 1;
-				ibmveth_close(netdev);
-				rc = ibmveth_open(netdev);
-				if (rc)
-					goto unlock_err;
-			} else {
-				pool->active = 1;
-			}
-		} else if (!value && pool->active) {
+		if (value && !oldactive) {
+			newactive = 1;
+			change = true;
+		} else if (!value && oldactive) {
 			int mtu = netdev->mtu + IBMVETH_BUFF_OH;
 			int i;
 			/* Make sure there is a buffer pool with buffers that
@@ -1841,43 +1943,44 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 				goto unlock_err;
 			}
 
-			if (netif_running(netdev)) {
-				ibmveth_close(netdev);
-				pool->active = 0;
-				rc = ibmveth_open(netdev);
-				if (rc)
-					goto unlock_err;
-			}
-			pool->active = 0;
+			newactive = 0;
+			change = true;
 		}
 	} else if (attr == &veth_num_attr) {
 		if (value <= 0 || value > IBMVETH_MAX_POOL_COUNT) {
 			rc = -EINVAL;
 			goto unlock_err;
-		} else {
-			if (netif_running(netdev)) {
-				ibmveth_close(netdev);
-				pool->size = value;
-				rc = ibmveth_open(netdev);
-				if (rc)
-					goto unlock_err;
-			} else {
-				pool->size = value;
-			}
+		}
+		if (value != oldsize) {
+			newsize = value;
+			change = true;
 		}
 	} else if (attr == &veth_size_attr) {
 		if (value <= IBMVETH_BUFF_OH || value > IBMVETH_MAX_BUF_SIZE) {
 			rc = -EINVAL;
 			goto unlock_err;
-		} else {
-			if (netif_running(netdev)) {
-				ibmveth_close(netdev);
-				pool->buff_size = value;
-				rc = ibmveth_open(netdev);
-				if (rc)
-					goto unlock_err;
-			} else {
-				pool->buff_size = value;
+		}
+		if (value != oldbuff_size) {
+			newbuff_size = value;
+			change = true;
+		}
+	}
+
+	if (change) {
+		if (netif_running(netdev))
+			ibmveth_close(netdev);
+
+		pool->active = newactive;
+		pool->buff_size = newbuff_size;
+		pool->size = newsize;
+
+		if (netif_running(netdev)) {
+			rc = ibmveth_open(netdev);
+			if (rc) {
+				pool->active = oldactive;
+				pool->buff_size = oldbuff_size;
+				pool->size = oldsize;
+				goto unlock_err;
 			}
 		}
 	}
@@ -1962,3 +2065,132 @@ static void __exit ibmveth_module_exit(void)
 
 module_init(ibmveth_module_init);
 module_exit(ibmveth_module_exit);
+
+#ifdef CONFIG_IBMVETH_KUNIT_TEST
+#include <kunit/test.h>
+
+/**
+ * ibmveth_reset_kunit - reset routine for running in KUnit environment
+ *
+ * @w: pointer to work_struct embedded in adapter structure
+ *
+ * Context: Called in the KUnit environment. Does nothing.
+ *
+ * Return: void
+ */
+static void ibmveth_reset_kunit(struct work_struct *w)
+{
+	netdev_dbg(NULL, "reset_kunit starting\n");
+	netdev_dbg(NULL, "reset_kunit complete\n");
+}
+
+/**
+ * ibmveth_remove_buffer_from_pool_test - unit test for some of
+ *                                        ibmveth_remove_buffer_from_pool
+ * @test: pointer to kunit structure
+ *
+ * Tests the error returns from ibmveth_remove_buffer_from_pool.
+ * ibmveth_remove_buffer_from_pool also calls WARN_ON, so dmesg should be
+ * checked to see that these warnings happened.
+ *
+ * Return: void
+ */
+static void ibmveth_remove_buffer_from_pool_test(struct kunit *test)
+{
+	struct ibmveth_adapter *adapter = kunit_kzalloc(test, sizeof(*adapter), GFP_KERNEL);
+	struct ibmveth_buff_pool *pool;
+	u64 correlator;
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adapter);
+
+	INIT_WORK(&adapter->work, ibmveth_reset_kunit);
+
+	/* Set sane values for buffer pools */
+	for (int i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
+		ibmveth_init_buffer_pool(&adapter->rx_buff_pool[i], i,
+					 pool_count[i], pool_size[i],
+					 pool_active[i]);
+
+	pool = &adapter->rx_buff_pool[0];
+	pool->skbuff = kunit_kcalloc(test, pool->size, sizeof(void *), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pool->skbuff);
+
+	correlator = ((u64)IBMVETH_NUM_BUFF_POOLS << 32) | 0;
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, false));
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, true));
+
+	correlator = ((u64)0 << 32) | adapter->rx_buff_pool[0].size;
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, false));
+	KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, true));
+
+	correlator = (u64)0 | 0;
+	pool->skbuff[0] = NULL;
+	KUNIT_EXPECT_EQ(test, -EFAULT, ibmveth_remove_buffer_from_pool(adapter, correlator, false));
+	KUNIT_EXPECT_EQ(test, -EFAULT, ibmveth_remove_buffer_from_pool(adapter, correlator, true));
+
+	flush_work(&adapter->work);
+}
+
+/**
+ * ibmveth_rxq_get_buffer_test - unit test for ibmveth_rxq_get_buffer
+ * @test: pointer to kunit structure
+ *
+ * Tests ibmveth_rxq_get_buffer. ibmveth_rxq_get_buffer also calls WARN_ON for
+ * the NULL returns, so dmesg should be checked to see that these warnings
+ * happened.
+ *
+ * Return: void
+ */
+static void ibmveth_rxq_get_buffer_test(struct kunit *test)
+{
+	struct ibmveth_adapter *adapter = kunit_kzalloc(test, sizeof(*adapter), GFP_KERNEL);
+	struct sk_buff *skb = kunit_kzalloc(test, sizeof(*skb), GFP_KERNEL);
+	struct ibmveth_buff_pool *pool;
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adapter);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	INIT_WORK(&adapter->work, ibmveth_reset_kunit);
+
+	adapter->rx_queue.queue_len = 1;
+	adapter->rx_queue.index = 0;
+	adapter->rx_queue.queue_addr = kunit_kzalloc(test, sizeof(struct ibmveth_rx_q_entry),
+						     GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adapter->rx_queue.queue_addr);
+
+	/* Set sane values for buffer pools */
+	for (int i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
+		ibmveth_init_buffer_pool(&adapter->rx_buff_pool[i], i,
+					 pool_count[i], pool_size[i],
+					 pool_active[i]);
+
+	pool = &adapter->rx_buff_pool[0];
+	pool->skbuff = kunit_kcalloc(test, pool->size, sizeof(void *), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pool->skbuff);
+
+	adapter->rx_queue.queue_addr[0].correlator = (u64)IBMVETH_NUM_BUFF_POOLS << 32 | 0;
+	KUNIT_EXPECT_PTR_EQ(test, NULL, ibmveth_rxq_get_buffer(adapter));
+
+	adapter->rx_queue.queue_addr[0].correlator = (u64)0 << 32 | adapter->rx_buff_pool[0].size;
+	KUNIT_EXPECT_PTR_EQ(test, NULL, ibmveth_rxq_get_buffer(adapter));
+
+	pool->skbuff[0] = skb;
+	adapter->rx_queue.queue_addr[0].correlator = (u64)0 << 32 | 0;
+	KUNIT_EXPECT_PTR_EQ(test, skb, ibmveth_rxq_get_buffer(adapter));
+
+	flush_work(&adapter->work);
+}
+
+static struct kunit_case ibmveth_test_cases[] = {
+	KUNIT_CASE(ibmveth_remove_buffer_from_pool_test),
+	KUNIT_CASE(ibmveth_rxq_get_buffer_test),
+	{}
+};
+
+static struct kunit_suite ibmveth_test_suite = {
+	.name = "ibmveth-kunit-test",
+	.test_cases = ibmveth_test_cases,
+};
+
+kunit_test_suite(ibmveth_test_suite);
+#endif
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 8468e2c59d7a..b0a2460ec9f9 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -134,38 +134,39 @@ struct ibmveth_rx_q {
 };
 
 struct ibmveth_adapter {
-    struct vio_dev *vdev;
-    struct net_device *netdev;
-    struct napi_struct napi;
-    unsigned int mcastFilterSize;
-    void * buffer_list_addr;
-    void * filter_list_addr;
-    void *tx_ltb_ptr[IBMVETH_MAX_QUEUES];
-    unsigned int tx_ltb_size;
-    dma_addr_t tx_ltb_dma[IBMVETH_MAX_QUEUES];
-    dma_addr_t buffer_list_dma;
-    dma_addr_t filter_list_dma;
-    struct ibmveth_buff_pool rx_buff_pool[IBMVETH_NUM_BUFF_POOLS];
-    struct ibmveth_rx_q rx_queue;
-    int rx_csum;
-    int large_send;
-    bool is_active_trunk;
-
-    u64 fw_ipv6_csum_support;
-    u64 fw_ipv4_csum_support;
-    u64 fw_large_send_support;
-    /* adapter specific stats */
-    u64 replenish_task_cycles;
-    u64 replenish_no_mem;
-    u64 replenish_add_buff_failure;
-    u64 replenish_add_buff_success;
-    u64 rx_invalid_buffer;
-    u64 rx_no_buffer;
-    u64 tx_map_failed;
-    u64 tx_send_failed;
-    u64 tx_large_packets;
-    u64 rx_large_packets;
-    /* Ethtool settings */
+	struct vio_dev *vdev;
+	struct net_device *netdev;
+	struct napi_struct napi;
+	struct work_struct work;
+	unsigned int mcastFilterSize;
+	void *buffer_list_addr;
+	void *filter_list_addr;
+	void *tx_ltb_ptr[IBMVETH_MAX_QUEUES];
+	unsigned int tx_ltb_size;
+	dma_addr_t tx_ltb_dma[IBMVETH_MAX_QUEUES];
+	dma_addr_t buffer_list_dma;
+	dma_addr_t filter_list_dma;
+	struct ibmveth_buff_pool rx_buff_pool[IBMVETH_NUM_BUFF_POOLS];
+	struct ibmveth_rx_q rx_queue;
+	int rx_csum;
+	int large_send;
+	bool is_active_trunk;
+
+	u64 fw_ipv6_csum_support;
+	u64 fw_ipv4_csum_support;
+	u64 fw_large_send_support;
+	/* adapter specific stats */
+	u64 replenish_task_cycles;
+	u64 replenish_no_mem;
+	u64 replenish_add_buff_failure;
+	u64 replenish_add_buff_success;
+	u64 rx_invalid_buffer;
+	u64 rx_no_buffer;
+	u64 tx_map_failed;
+	u64 tx_send_failed;
+	u64 tx_large_packets;
+	u64 rx_large_packets;
+	/* Ethtool settings */
 	u8 duplex;
 	u32 speed;
 };
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 1640d2f27833..5a331c1c76cb 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -147,6 +147,8 @@ config IXGBE
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
 	select MDIO
+	select NET_DEVLINK
+	select PLDMFW
 	select PHYLIB
 	help
 	  This driver supports Intel(R) 10GbE PCI Express family of
@@ -367,6 +369,7 @@ config IGC
 	default n
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
+	depends on ETHTOOL_NETLINK
 	help
 	  This driver supports Intel(R) Ethernet Controller I225-LM/I225-V
 	  family of adapters.
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index ba9c19e6994c..952898151565 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -319,7 +319,7 @@ struct e1000_adapter {
 	u16 tx_ring_count;
 	u16 rx_ring_count;
 
-	struct hwtstamp_config hwtstamp_config;
+	struct kernel_hwtstamp_config hwtstamp_config;
 	struct delayed_work systim_overflow_work;
 	struct sk_buff *tx_hwtstamp_skb;
 	unsigned long tx_hwtstamp_start;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 8ebcb6a7d608..e0f492a6723f 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3574,6 +3574,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
  * e1000e_config_hwtstamp - configure the hwtstamp registers and enable/disable
  * @adapter: board private structure
  * @config: timestamp configuration
+ * @extack: netlink extended ACK for error report
  *
  * Outgoing time stamping can be enabled and disabled. Play nice and
  * disable it when requested, although it shouldn't cause any overhead
@@ -3587,7 +3588,8 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
  * exception of "all V2 events regardless of level 2 or 4".
  **/
 static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
-				  struct hwtstamp_config *config)
+				  struct kernel_hwtstamp_config *config,
+				  struct netlink_ext_ack *extack)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED;
@@ -3598,8 +3600,10 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 	bool is_l2 = false;
 	u32 regval;
 
-	if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP))
+	if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP)) {
+		NL_SET_ERR_MSG(extack, "No HW timestamp support");
 		return -EINVAL;
+	}
 
 	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
@@ -3608,6 +3612,7 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 	case HWTSTAMP_TX_ON:
 		break;
 	default:
+		NL_SET_ERR_MSG(extack, "Unsupported TX HW timestamp type");
 		return -ERANGE;
 	}
 
@@ -3681,6 +3686,7 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
+		NL_SET_ERR_MSG(extack, "Unsupported RX HW timestamp filter");
 		return -ERANGE;
 	}
 
@@ -3693,7 +3699,8 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 	ew32(TSYNCTXCTL, regval);
 	if ((er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_ENABLED) !=
 	    (regval & E1000_TSYNCTXCTL_ENABLED)) {
-		e_err("Timesync Tx Control register not set as expected\n");
+		NL_SET_ERR_MSG(extack,
+			       "Timesync Tx Control register not set as expected");
 		return -EAGAIN;
 	}
 
@@ -3706,7 +3713,8 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 				 E1000_TSYNCRXCTL_TYPE_MASK)) !=
 	    (regval & (E1000_TSYNCRXCTL_ENABLED |
 		       E1000_TSYNCRXCTL_TYPE_MASK))) {
-		e_err("Timesync Rx Control register not set as expected\n");
+		NL_SET_ERR_MSG(extack,
+			       "Timesync Rx Control register not set as expected");
 		return -EAGAIN;
 	}
 
@@ -3901,6 +3909,7 @@ static void e1000e_systim_reset(struct e1000_adapter *adapter)
 {
 	struct ptp_clock_info *info = &adapter->ptp_clock_info;
 	struct e1000_hw *hw = &adapter->hw;
+	struct netlink_ext_ack extack = {};
 	unsigned long flags;
 	u32 timinca;
 	s32 ret_val;
@@ -3932,7 +3941,12 @@ static void e1000e_systim_reset(struct e1000_adapter *adapter)
 	spin_unlock_irqrestore(&adapter->systim_lock, flags);
 
 	/* restore the previous hwtstamp configuration settings */
-	e1000e_config_hwtstamp(adapter, &adapter->hwtstamp_config);
+	ret_val = e1000e_config_hwtstamp(adapter, &adapter->hwtstamp_config,
+					 &extack);
+	if (ret_val) {
+		if (extack._msg)
+			e_err("%s\n", extack._msg);
+	}
 }
 
 /**
@@ -6079,8 +6093,7 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 	return 0;
 }
 
-static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
-			   int cmd)
+static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct mii_ioctl_data *data = if_mii(ifr);
@@ -6140,7 +6153,8 @@ static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
 /**
  * e1000e_hwtstamp_set - control hardware time stamping
  * @netdev: network interface device structure
- * @ifr: interface request
+ * @config: timestamp configuration
+ * @extack: netlink extended ACK report
  *
  * Outgoing time stamping can be enabled and disabled. Play nice and
  * disable it when requested, although it shouldn't cause any overhead
@@ -6153,20 +6167,18 @@ static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
  * specified. Matching the kind of event packet is not supported, with the
  * exception of "all V2 events regardless of level 2 or 4".
  **/
-static int e1000e_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
+static int e1000e_hwtstamp_set(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
-	struct hwtstamp_config config;
 	int ret_val;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	ret_val = e1000e_config_hwtstamp(adapter, &config);
+	ret_val = e1000e_config_hwtstamp(adapter, config, extack);
 	if (ret_val)
 		return ret_val;
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
@@ -6178,38 +6190,23 @@ static int e1000e_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 		 * by hardware so notify the caller the requested packets plus
 		 * some others are time stamped.
 		 */
-		config.rx_filter = HWTSTAMP_FILTER_SOME;
+		config->rx_filter = HWTSTAMP_FILTER_SOME;
 		break;
 	default:
 		break;
 	}
 
-	return copy_to_user(ifr->ifr_data, &config,
-			    sizeof(config)) ? -EFAULT : 0;
+	return 0;
 }
 
-static int e1000e_hwtstamp_get(struct net_device *netdev, struct ifreq *ifr)
+static int e1000e_hwtstamp_get(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *kernel_config)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 
-	return copy_to_user(ifr->ifr_data, &adapter->hwtstamp_config,
-			    sizeof(adapter->hwtstamp_config)) ? -EFAULT : 0;
-}
+	*kernel_config = adapter->hwtstamp_config;
 
-static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
-	switch (cmd) {
-	case SIOCGMIIPHY:
-	case SIOCGMIIREG:
-	case SIOCSMIIREG:
-		return e1000_mii_ioctl(netdev, ifr, cmd);
-	case SIOCSHWTSTAMP:
-		return e1000e_hwtstamp_set(netdev, ifr);
-	case SIOCGHWTSTAMP:
-		return e1000e_hwtstamp_get(netdev, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
+	return 0;
 }
 
 static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc)
@@ -7346,9 +7343,11 @@ static const struct net_device_ops e1000e_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= e1000_netpoll,
 #endif
-	.ndo_set_features = e1000_set_features,
-	.ndo_fix_features = e1000_fix_features,
+	.ndo_set_features	= e1000_set_features,
+	.ndo_fix_features	= e1000_fix_features,
 	.ndo_features_check	= passthru_features_check,
+	.ndo_hwtstamp_get	= e1000e_hwtstamp_get,
+	.ndo_hwtstamp_set	= e1000e_hwtstamp_set,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 370b4bddee44..b11c35e307ca 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -817,10 +817,11 @@ int i40e_pf_reset(struct i40e_hw *hw)
 void i40e_clear_hw(struct i40e_hw *hw)
 {
 	u32 num_queues, base_queue;
-	u32 num_pf_int;
-	u32 num_vf_int;
+	s32 num_pf_int;
+	s32 num_vf_int;
 	u32 num_vfs;
-	u32 i, j;
+	s32 i;
+	u32 j;
 	u32 val;
 	u32 eol = 0x7ff;
 
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index fcb199efbea5..4af60e2f37df 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -1339,8 +1339,13 @@ ice_devlink_enable_roce_get(struct devlink *devlink, u32 id,
 			    struct devlink_param_gset_ctx *ctx)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
 
-	ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? true : false;
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
+	ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2);
 
 	return 0;
 }
@@ -1350,19 +1355,24 @@ static int ice_devlink_enable_roce_set(struct devlink *devlink, u32 id,
 				       struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
 	bool roce_ena = ctx->val.vbool;
 	int ret;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
 	if (!roce_ena) {
 		ice_unplug_aux_dev(pf);
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
 		return 0;
 	}
 
-	pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2;
+	cdev->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2;
 	ret = ice_plug_aux_dev(pf);
 	if (ret)
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_ROCEV2;
 
 	return ret;
 }
@@ -1373,11 +1383,16 @@ ice_devlink_enable_roce_validate(struct devlink *devlink, u32 id,
 				 struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
+
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
 
 	if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
-	if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP) {
+	if (cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP) {
 		NL_SET_ERR_MSG_MOD(extack, "iWARP is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously");
 		return -EOPNOTSUPP;
 	}
@@ -1390,8 +1405,13 @@ ice_devlink_enable_iw_get(struct devlink *devlink, u32 id,
 			  struct devlink_param_gset_ctx *ctx)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
 
-	ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP;
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
+	ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP);
 
 	return 0;
 }
@@ -1401,19 +1421,24 @@ static int ice_devlink_enable_iw_set(struct devlink *devlink, u32 id,
 				     struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
+	struct iidc_rdma_core_dev_info *cdev;
 	bool iw_ena = ctx->val.vbool;
 	int ret;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
 	if (!iw_ena) {
 		ice_unplug_aux_dev(pf);
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_IWARP;
 		return 0;
 	}
 
-	pf->rdma_mode |= IIDC_RDMA_PROTOCOL_IWARP;
+	cdev->rdma_protocol |= IIDC_RDMA_PROTOCOL_IWARP;
 	ret = ice_plug_aux_dev(pf);
 	if (ret)
-		pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP;
+		cdev->rdma_protocol &= ~IIDC_RDMA_PROTOCOL_IWARP;
 
 	return ret;
 }
@@ -1428,7 +1453,7 @@ ice_devlink_enable_iw_validate(struct devlink *devlink, u32 id,
 	if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
 		return -EOPNOTSUPP;
 
-	if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2) {
+	if (pf->cdev_info->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2) {
 		NL_SET_ERR_MSG_MOD(extack, "RoCEv2 is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously");
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index fd083647c14a..ddd0ad68185b 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -193,8 +193,6 @@
 
 #define ice_pf_to_dev(pf) (&((pf)->pdev->dev))
 
-#define ice_pf_src_tmr_owned(pf) ((pf)->hw.func_caps.ts_func_info.src_tmr_owned)
-
 enum ice_feature {
 	ICE_F_DSCP,
 	ICE_F_PHY_RCLK,
@@ -401,7 +399,6 @@ struct ice_vsi {
 	u16 req_rxq;			 /* User requested Rx queues */
 	u16 num_rx_desc;
 	u16 num_tx_desc;
-	u16 qset_handle[ICE_MAX_TRAFFIC_CLASS];
 	struct ice_tc_cfg tc_cfg;
 	struct bpf_prog *xdp_prog;
 	struct ice_tx_ring **xdp_rings;	 /* XDP ring array */
@@ -515,6 +512,7 @@ enum ice_pf_flags {
 	ICE_FLAG_MTU_CHANGED,
 	ICE_FLAG_GNSS,			/* GNSS successfully initialized */
 	ICE_FLAG_DPLL,			/* SyncE/PTP dplls initialized */
+	ICE_FLAG_LLDP_AQ_FLTR,
 	ICE_PF_FLAGS_NBITS		/* must be last */
 };
 
@@ -557,7 +555,6 @@ struct ice_pf {
 	struct devlink_port devlink_port;
 
 	/* OS reserved IRQ details */
-	struct msix_entry *msix_entries;
 	struct ice_irq_tracker irq_tracker;
 	struct ice_virt_irq_tracker virt_irq_tracker;
 
@@ -592,7 +589,6 @@ struct ice_pf {
 	struct gnss_serial *gnss_serial;
 	struct gnss_device *gnss_dev;
 	u16 num_rdma_msix;		/* Total MSIX vectors for RDMA driver */
-	u16 rdma_base_vector;
 
 	/* spinlock to protect the AdminQ wait list */
 	spinlock_t aq_wait_lock;
@@ -625,14 +621,12 @@ struct ice_pf {
 	struct ice_hw_port_stats stats_prev;
 	struct ice_hw hw;
 	u8 stat_prev_loaded:1; /* has previous stats been loaded */
-	u8 rdma_mode;
 	u16 dcbx_cap;
 	u32 tx_timeout_count;
 	unsigned long tx_timeout_last_recovery;
 	u32 tx_timeout_recovery_level;
 	char int_name[ICE_INT_NAME_STR_LEN];
 	char int_name_ll_ts[ICE_INT_NAME_STR_LEN];
-	struct auxiliary_device *adev;
 	int aux_idx;
 	u32 sw_int_count;
 	/* count of tc_flower filters specific to channel (aka where filter
@@ -664,6 +658,7 @@ struct ice_pf {
 	struct ice_dplls dplls;
 	struct device *hwmon_dev;
 	struct ice_health health_reporters;
+	struct iidc_rdma_core_dev_info *cdev_info;
 
 	u8 num_quanta_prof_used;
 };
@@ -1045,4 +1040,62 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf)
 }
 
 extern const struct xdp_metadata_ops ice_xdp_md_ops;
+
+/**
+ * ice_is_dual - Check if given config is multi-NAC
+ * @hw: pointer to HW structure
+ *
+ * Return: true if the device is running in mutli-NAC (Network
+ * Acceleration Complex) configuration variant, false otherwise
+ * (always false for non-E825 devices).
+ */
+static inline bool ice_is_dual(struct ice_hw *hw)
+{
+	return hw->mac_type == ICE_MAC_GENERIC_3K_E825 &&
+	       (hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_DUAL_M);
+}
+
+/**
+ * ice_is_primary - Check if given device belongs to the primary complex
+ * @hw: pointer to HW structure
+ *
+ * Check if given PF/HW is running on primary complex in multi-NAC
+ * configuration.
+ *
+ * Return: true if the device is dual, false otherwise (always true
+ * for non-E825 devices).
+ */
+static inline bool ice_is_primary(struct ice_hw *hw)
+{
+	return hw->mac_type != ICE_MAC_GENERIC_3K_E825 ||
+	       !ice_is_dual(hw) ||
+	       (hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M);
+}
+
+/**
+ * ice_pf_src_tmr_owned - Check if a primary timer is owned by PF
+ * @pf: pointer to PF structure
+ *
+ * Return: true if PF owns primary timer, false otherwise.
+ */
+static inline bool ice_pf_src_tmr_owned(struct ice_pf *pf)
+{
+	return pf->hw.func_caps.ts_func_info.src_tmr_owned &&
+	       ice_is_primary(&pf->hw);
+}
+
+/**
+ * ice_get_primary_hw - Get pointer to primary ice_hw structure
+ * @pf: pointer to PF structure
+ *
+ * Return: A pointer to ice_hw structure with access to timesync
+ * register space.
+ */
+static inline struct ice_hw *ice_get_primary_hw(struct ice_pf *pf)
+{
+	if (!pf->adapter->ctrl_pf)
+		return &pf->hw;
+	else
+		return &pf->adapter->ctrl_pf->hw;
+}
 #endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c
index 01a08cfd0090..66e070095d1b 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.c
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 // SPDX-FileCopyrightText: Copyright Red Hat
 
-#include <linux/bitfield.h>
 #include <linux/cleanup.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
@@ -14,32 +13,16 @@
 static DEFINE_XARRAY(ice_adapters);
 static DEFINE_MUTEX(ice_adapters_mutex);
 
-/* PCI bus number is 8 bits. Slot is 5 bits. Domain can have the rest. */
-#define INDEX_FIELD_DOMAIN GENMASK(BITS_PER_LONG - 1, 13)
-#define INDEX_FIELD_DEV    GENMASK(31, 16)
-#define INDEX_FIELD_BUS    GENMASK(12, 5)
-#define INDEX_FIELD_SLOT   GENMASK(4, 0)
-
-static unsigned long ice_adapter_index(const struct pci_dev *pdev)
+static unsigned long ice_adapter_index(u64 dsn)
 {
-	unsigned int domain = pci_domain_nr(pdev->bus);
-
-	WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN));
-
-	switch (pdev->device) {
-	case ICE_DEV_ID_E825C_BACKPLANE:
-	case ICE_DEV_ID_E825C_QSFP:
-	case ICE_DEV_ID_E825C_SFP:
-	case ICE_DEV_ID_E825C_SGMII:
-		return FIELD_PREP(INDEX_FIELD_DEV, pdev->device);
-	default:
-		return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) |
-		       FIELD_PREP(INDEX_FIELD_BUS,    pdev->bus->number) |
-		       FIELD_PREP(INDEX_FIELD_SLOT,   PCI_SLOT(pdev->devfn));
-	}
+#if BITS_PER_LONG == 64
+	return dsn;
+#else
+	return (u32)dsn ^ (u32)(dsn >> 32);
+#endif
 }
 
-static struct ice_adapter *ice_adapter_new(void)
+static struct ice_adapter *ice_adapter_new(u64 dsn)
 {
 	struct ice_adapter *adapter;
 
@@ -47,6 +30,7 @@ static struct ice_adapter *ice_adapter_new(void)
 	if (!adapter)
 		return NULL;
 
+	adapter->device_serial_number = dsn;
 	spin_lock_init(&adapter->ptp_gltsyn_time_lock);
 	refcount_set(&adapter->refcount, 1);
 
@@ -77,23 +61,26 @@ static void ice_adapter_free(struct ice_adapter *adapter)
  * Return:  Pointer to ice_adapter on success.
  *          ERR_PTR() on error. -ENOMEM is the only possible error.
  */
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev)
 {
-	unsigned long index = ice_adapter_index(pdev);
+	u64 dsn = pci_get_dsn(pdev);
 	struct ice_adapter *adapter;
+	unsigned long index;
 	int err;
 
+	index = ice_adapter_index(dsn);
 	scoped_guard(mutex, &ice_adapters_mutex) {
 		err = xa_insert(&ice_adapters, index, NULL, GFP_KERNEL);
 		if (err == -EBUSY) {
 			adapter = xa_load(&ice_adapters, index);
 			refcount_inc(&adapter->refcount);
+			WARN_ON_ONCE(adapter->device_serial_number != dsn);
 			return adapter;
 		}
 		if (err)
 			return ERR_PTR(err);
 
-		adapter = ice_adapter_new();
+		adapter = ice_adapter_new(dsn);
 		if (!adapter)
 			return ERR_PTR(-ENOMEM);
 		xa_store(&ice_adapters, index, adapter, GFP_KERNEL);
@@ -110,11 +97,13 @@ struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
  *
  * Context: Process, may sleep.
  */
-void ice_adapter_put(const struct pci_dev *pdev)
+void ice_adapter_put(struct pci_dev *pdev)
 {
-	unsigned long index = ice_adapter_index(pdev);
+	u64 dsn = pci_get_dsn(pdev);
 	struct ice_adapter *adapter;
+	unsigned long index;
 
+	index = ice_adapter_index(dsn);
 	scoped_guard(mutex, &ice_adapters_mutex) {
 		adapter = xa_load(&ice_adapters, index);
 		if (WARN_ON(!adapter))
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h
index e233225848b3..ac15c0d2bc1a 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.h
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.h
@@ -32,6 +32,7 @@ struct ice_port_list {
  * @refcount: Reference count. struct ice_pf objects hold the references.
  * @ctrl_pf: Control PF of the adapter
  * @ports: Ports list
+ * @device_serial_number: DSN cached for collision detection on 32bit systems
  */
 struct ice_adapter {
 	refcount_t refcount;
@@ -40,9 +41,10 @@ struct ice_adapter {
 
 	struct ice_pf *ctrl_pf;
 	struct ice_port_list ports;
+	u64 device_serial_number;
 };
 
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev);
-void ice_adapter_put(const struct pci_dev *pdev);
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev);
+void ice_adapter_put(struct pci_dev *pdev);
 
 #endif /* _ICE_ADAPTER_H */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 59df31c2c83f..4fedf0181c4e 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1135,6 +1135,8 @@ int ice_init_hw(struct ice_hw *hw)
 		}
 	}
 
+	hw->lane_num = ice_get_phy_lane_number(hw);
+
 	return 0;
 err_unroll_fltr_mgmt_struct:
 	ice_cleanup_fltr_mgmt_struct(hw);
@@ -3434,7 +3436,7 @@ int ice_aq_get_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port,
 	msg.msg_addr_low = lower_16_bits(reg_offset);
 	msg.msg_addr_high = receiver_id;
 	msg.opcode = ice_sbq_msg_rd;
-	msg.dest_dev = rmn_0;
+	msg.dest_dev = ice_sbq_dev_phy_0;
 
 	err = ice_sbq_rw_reg(hw, &msg, flag);
 	if (err)
@@ -4082,10 +4084,12 @@ int ice_get_phy_lane_number(struct ice_hw *hw)
 			continue;
 
 		if (hw->pf_id == lport) {
+			if (hw->mac_type == ICE_MAC_GENERIC_3K_E825 &&
+			    ice_is_dual(hw) && !ice_is_primary(hw))
+				lane += ICE_PORTS_PER_QUAD;
 			kfree(options);
 			return lane;
 		}
-
 		lport++;
 	}
 
@@ -6011,15 +6015,21 @@ bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw)
 /**
  * ice_lldp_fltr_add_remove - add or remove a LLDP Rx switch filter
  * @hw: pointer to HW struct
- * @vsi_num: absolute HW index for VSI
+ * @vsi: VSI to add the filter to
  * @add: boolean for if adding or removing a filter
+ *
+ * Return: 0 on success, -EOPNOTSUPP if the operation cannot be performed
+ *	   with this HW or VSI, otherwise an error corresponding to
+ *	   the AQ transaction result.
  */
-int
-ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add)
+int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add)
 {
 	struct ice_aqc_lldp_filter_ctrl *cmd;
 	struct ice_aq_desc desc;
 
+	if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw))
+		return -EOPNOTSUPP;
+
 	cmd = &desc.params.lldp_filter_ctrl;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_filter_ctrl);
@@ -6029,7 +6039,7 @@ ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add)
 	else
 		cmd->cmd_flags = ICE_AQC_LLDP_FILTER_ACTION_DELETE;
 
-	cmd->vsi_num = cpu_to_le16(vsi_num);
+	cmd->vsi_num = cpu_to_le16(vsi->vsi_num);
 
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 9b00aa0ddf10..64c530b39191 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -290,8 +290,7 @@ int
 ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size,
 		    struct ice_sq_cd *cd);
 bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw);
-int
-ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add);
+int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add);
 int ice_lldp_execute_pending_mib(struct ice_hw *hw);
 int
 ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c
index 74418c445cc4..64737fc62306 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.c
@@ -1288,7 +1288,7 @@ ice_add_dscp_up_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
 	tlv->ouisubtype = htonl(ouisubtype);
 
 	/* bytes 0 - 63 - IPv4 DSCP2UP LUT */
-	for (i = 0; i < ICE_DSCP_NUM_VAL; i++) {
+	for (i = 0; i < DSCP_MAX; i++) {
 		/* IPv4 mapping */
 		buf[i] = dcbcfg->dscp_map[i];
 		/* IPv6 mapping */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index a7c510832824..533eb8930aa8 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -352,8 +352,8 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
 	struct ice_aqc_port_ets_elem buf = { 0 };
 	struct ice_dcbx_cfg *old_cfg, *curr_cfg;
 	struct device *dev = ice_pf_to_dev(pf);
+	struct iidc_rdma_event *event;
 	int ret = ICE_DCB_NO_HW_CHG;
-	struct iidc_event *event;
 	struct ice_vsi *pf_vsi;
 
 	curr_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
@@ -405,7 +405,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
 		goto free_cfg;
 	}
 
-	set_bit(IIDC_EVENT_BEFORE_TC_CHANGE, event->type);
+	set_bit(IIDC_RDMA_EVENT_BEFORE_TC_CHANGE, event->type);
 	ice_send_event_to_aux(pf, event);
 	kfree(event);
 
@@ -740,7 +740,9 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf)
 void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked)
 {
 	struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
-	struct iidc_event *event;
+	struct iidc_rdma_priv_dev_info *privd;
+	struct iidc_rdma_core_dev_info *cdev;
+	struct iidc_rdma_event *event;
 	u8 tc_map = 0;
 	int v, ret;
 
@@ -783,13 +785,17 @@ void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked)
 		if (vsi->type == ICE_VSI_PF)
 			ice_dcbnl_set_all(vsi);
 	}
-	if (!locked) {
+
+	cdev = pf->cdev_info;
+	if (cdev && !locked) {
+		privd = cdev->iidc_priv;
+		ice_setup_dcb_qos_info(pf, &privd->qos_info);
 		/* Notify the AUX drivers that TC change is finished */
 		event = kzalloc(sizeof(*event), GFP_KERNEL);
 		if (!event)
 			return;
 
-		set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type);
+		set_bit(IIDC_RDMA_EVENT_AFTER_TC_CHANGE, event->type);
 		ice_send_event_to_aux(pf, event);
 		kfree(event);
 	}
@@ -846,7 +852,7 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
 			goto dcb_init_err;
 		}
 
-		ice_cfg_sw_lldp(pf_vsi, false, true);
+		ice_cfg_sw_rx_lldp(pf, true);
 
 		pf->dcbx_cap = ice_dcb_get_mode(port_info, true);
 		return 0;
@@ -945,6 +951,37 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring,
 }
 
 /**
+ * ice_setup_dcb_qos_info - Setup DCB QoS information
+ * @pf: ptr to ice_pf
+ * @qos_info: QoS param instance
+ */
+void ice_setup_dcb_qos_info(struct ice_pf *pf, struct iidc_rdma_qos_params *qos_info)
+{
+	struct ice_dcbx_cfg *dcbx_cfg;
+	unsigned int i;
+	u32 up2tc;
+
+	if (!pf || !qos_info)
+		return;
+
+	dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
+	up2tc = rd32(&pf->hw, PRTDCB_TUP2TC);
+
+	qos_info->num_tc = ice_dcb_get_num_tc(dcbx_cfg);
+
+	for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++)
+		qos_info->up2tc[i] = (up2tc >> (i * 3)) & 0x7;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		qos_info->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i];
+
+	qos_info->pfc_mode = dcbx_cfg->pfc_mode;
+	if (qos_info->pfc_mode == IIDC_DSCP_PFC_MODE)
+		for (i = 0; i < DSCP_MAX; i++)
+			qos_info->dscp_map[i] = dcbx_cfg->dscp_map[i];
+}
+
+/**
  * ice_dcb_is_mib_change_pending - Check if MIB change is pending
  * @state: MIB change state
  */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
index 800879a88c5e..da9ba814b4e8 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
@@ -31,6 +31,9 @@ void
 ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring,
 			      struct ice_tx_buf *first);
 void
+ice_setup_dcb_qos_info(struct ice_pf *pf,
+		       struct iidc_rdma_qos_params *qos_info);
+void
 ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
 				    struct ice_rq_event_info *event);
 /**
@@ -134,5 +137,11 @@ static inline void ice_update_dcb_stats(struct ice_pf *pf) { }
 static inline void
 ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event) { }
 static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, u8 dcb_tc) { }
+static inline void
+ice_setup_dcb_qos_info(struct ice_pf *pf, struct iidc_rdma_qos_params *qos_info)
+{
+	qos_info->num_tc = 1;
+	qos_info->tc_info[0].rel_bw = 100;
+}
 #endif /* CONFIG_DCB */
 #endif /* _ICE_DCB_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
index 6d50b90a7359..a10c1c8d8697 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
@@ -754,7 +754,7 @@ static int ice_dcbnl_setapp(struct net_device *netdev, struct dcb_app *app)
 	if (!ice_is_feature_supported(pf, ICE_F_DSCP))
 		return -EOPNOTSUPP;
 
-	if (app->protocol >= ICE_DSCP_NUM_VAL) {
+	if (app->protocol >= DSCP_MAX) {
 		netdev_err(netdev, "DSCP value 0x%04X out of range\n",
 			   app->protocol);
 		return -EINVAL;
@@ -931,7 +931,7 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app)
 	/* if the last DSCP mapping just got deleted, need to switch
 	 * to L2 VLAN QoS mode
 	 */
-	if (bitmap_empty(new_cfg->dscp_mapped, ICE_DSCP_NUM_VAL) &&
+	if (bitmap_empty(new_cfg->dscp_mapped, DSCP_MAX) &&
 	    new_cfg->pfc_mode == ICE_QOS_MODE_DSCP) {
 		ret = ice_aq_set_pfc_mode(&pf->hw,
 					  ICE_AQC_PFC_VLAN_BASED_PFC,
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index 69d5b1a28491..59323c019544 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -2345,15 +2345,15 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
 			cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM |
 					  ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW;
 
-		if (hw->mac_type == ICE_MAC_GENERIC_3K_E825)
-			desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
 	} else {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo);
 		cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM;
-	}
 
-	if (hw->mac_type != ICE_MAC_GENERIC_3K_E825)
-		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		if (hw->mac_type == ICE_MAC_E810 ||
+		    hw->mac_type == ICE_MAC_GENERIC)
+			desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	}
 
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
 	if (status)
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index ed21d7f55ac1..6aae03771746 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -29,6 +29,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 			return -ENODEV;
 
 	ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx);
+	ice_vsi_cfg_sw_lldp(uplink_vsi, true, false);
 
 	netif_addr_lock_bh(netdev);
 	__dev_uc_unsync(netdev, NULL);
@@ -245,6 +246,10 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb,
 	u64 cd_cmd, dst_vsi;
 
 	if (!dst) {
+		struct ethhdr *eth = (struct ethhdr *)skb_mac_header(skb);
+
+		if (unlikely(eth->h_proto == htons(ETH_P_LLDP)))
+			return;
 		cd_cmd = ICE_TX_CTX_DESC_SWTCH_UPLINK << ICE_TXD_CTX_QW1_CMD_S;
 		off->cd_qw1 |= (cd_cmd | ICE_TX_DESC_DTYPE_CTX);
 	} else {
@@ -278,6 +283,7 @@ static void ice_eswitch_release_env(struct ice_pf *pf)
 	ice_fltr_add_mac_and_broadcast(uplink_vsi,
 				       uplink_vsi->port_info->mac.perm_addr,
 				       ICE_FWD_TO_VSI);
+	ice_vsi_cfg_sw_lldp(uplink_vsi, true, true);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 7c2dc347e4e5..bbf9e6fd315b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -1818,7 +1818,7 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags)
 			/* Remove rule to direct LLDP packets to default VSI.
 			 * The FW LLDP engine will now be consuming them.
 			 */
-			ice_cfg_sw_lldp(vsi, false, false);
+			ice_cfg_sw_rx_lldp(vsi->back, false);
 
 			/* AQ command to start FW LLDP agent will return an
 			 * error if the agent is already started
@@ -3964,11 +3964,11 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 		return -EINVAL;
 	}
 
-	if (pf->adev) {
+	if (pf->cdev_info && pf->cdev_info->adev) {
 		mutex_lock(&pf->adev_mutex);
-		device_lock(&pf->adev->dev);
+		device_lock(&pf->cdev_info->adev->dev);
 		locked = true;
-		if (pf->adev->dev.driver) {
+		if (pf->cdev_info->adev->dev.driver) {
 			netdev_err(dev, "Cannot change channels when RDMA is active\n");
 			ret = -EBUSY;
 			goto adev_unlock;
@@ -3987,7 +3987,7 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 
 adev_unlock:
 	if (locked) {
-		device_unlock(&pf->adev->dev);
+		device_unlock(&pf->cdev_info->adev->dev);
 		mutex_unlock(&pf->adev_mutex);
 	}
 	return ret;
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index 1d118171de37..aceec184e89b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -1605,7 +1605,7 @@ void ice_fdir_replay_fltrs(struct ice_pf *pf)
  */
 int ice_fdir_create_dflt_rules(struct ice_pf *pf)
 {
-	const enum ice_fltr_ptype dflt_rules[] = {
+	static const enum ice_fltr_ptype dflt_rules[] = {
 		ICE_FLTR_PTYPE_NONF_IPV4_TCP, ICE_FLTR_PTYPE_NONF_IPV4_UDP,
 		ICE_FLTR_PTYPE_NONF_IPV6_TCP, ICE_FLTR_PTYPE_NONF_IPV6_UDP,
 	};
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
index bab3e81cad5d..6ab53e430f91 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc.c
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -9,22 +9,25 @@
 static DEFINE_XARRAY_ALLOC1(ice_aux_id);
 
 /**
- * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct
- * @pf: pointer to PF struct
+ * ice_get_auxiliary_drv - retrieve iidc_rdma_core_auxiliary_drv struct
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  *
  * This function has to be called with a device_lock on the
- * pf->adev.dev to avoid race conditions.
+ * cdev->adev.dev to avoid race conditions.
+ *
+ * Return: pointer to the matched auxiliary driver struct
  */
-static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf)
+static struct iidc_rdma_core_auxiliary_drv *
+ice_get_auxiliary_drv(struct iidc_rdma_core_dev_info *cdev)
 {
 	struct auxiliary_device *adev;
 
-	adev = pf->adev;
+	adev = cdev->adev;
 	if (!adev || !adev->dev.driver)
 		return NULL;
 
-	return container_of(adev->dev.driver, struct iidc_auxiliary_drv,
-			    adrv.driver);
+	return container_of(adev->dev.driver,
+			    struct iidc_rdma_core_auxiliary_drv, adrv.driver);
 }
 
 /**
@@ -32,44 +35,54 @@ static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf)
  * @pf: pointer to PF struct
  * @event: event struct
  */
-void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event)
+void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_rdma_event *event)
 {
-	struct iidc_auxiliary_drv *iadrv;
+	struct iidc_rdma_core_auxiliary_drv *iadrv;
+	struct iidc_rdma_core_dev_info *cdev;
 
 	if (WARN_ON_ONCE(!in_task()))
 		return;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return;
+
 	mutex_lock(&pf->adev_mutex);
-	if (!pf->adev)
+	if (!cdev->adev)
 		goto finish;
 
-	device_lock(&pf->adev->dev);
-	iadrv = ice_get_auxiliary_drv(pf);
+	device_lock(&cdev->adev->dev);
+	iadrv = ice_get_auxiliary_drv(cdev);
 	if (iadrv && iadrv->event_handler)
-		iadrv->event_handler(pf, event);
-	device_unlock(&pf->adev->dev);
+		iadrv->event_handler(cdev, event);
+	device_unlock(&cdev->adev->dev);
 finish:
 	mutex_unlock(&pf->adev_mutex);
 }
 
 /**
  * ice_add_rdma_qset - Add Leaf Node for RDMA Qset
- * @pf: PF struct
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @qset: Resource to be allocated
+ *
+ * Return: Zero on success or error code encountered
  */
-int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
+int ice_add_rdma_qset(struct iidc_rdma_core_dev_info *cdev,
+		      struct iidc_rdma_qset_params *qset)
 {
 	u16 max_rdmaqs[ICE_MAX_TRAFFIC_CLASS];
 	struct ice_vsi *vsi;
 	struct device *dev;
+	struct ice_pf *pf;
 	u32 qset_teid;
 	u16 qs_handle;
 	int status;
 	int i;
 
-	if (WARN_ON(!pf || !qset))
+	if (WARN_ON(!cdev || !qset))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
 	dev = ice_pf_to_dev(pf);
 
 	if (!ice_is_rdma_ena(pf))
@@ -100,7 +113,6 @@ int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
 		dev_err(dev, "Failed VSI RDMA Qset enable\n");
 		return status;
 	}
-	vsi->qset_handle[qset->tc] = qset->qs_handle;
 	qset->teid = qset_teid;
 
 	return 0;
@@ -109,18 +121,23 @@ EXPORT_SYMBOL_GPL(ice_add_rdma_qset);
 
 /**
  * ice_del_rdma_qset - Delete leaf node for RDMA Qset
- * @pf: PF struct
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @qset: Resource to be freed
+ *
+ * Return: Zero on success, error code on failure
  */
-int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
+int ice_del_rdma_qset(struct iidc_rdma_core_dev_info *cdev,
+		      struct iidc_rdma_qset_params *qset)
 {
 	struct ice_vsi *vsi;
+	struct ice_pf *pf;
 	u32 teid;
 	u16 q_id;
 
-	if (WARN_ON(!pf || !qset))
+	if (WARN_ON(!cdev || !qset))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
 	vsi = ice_find_vsi(pf, qset->vport_id);
 	if (!vsi) {
 		dev_err(ice_pf_to_dev(pf), "RDMA Invalid VSI\n");
@@ -130,36 +147,36 @@ int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
 	q_id = qset->qs_handle;
 	teid = qset->teid;
 
-	vsi->qset_handle[qset->tc] = 0;
-
 	return ice_dis_vsi_rdma_qset(vsi->port_info, 1, &teid, &q_id);
 }
 EXPORT_SYMBOL_GPL(ice_del_rdma_qset);
 
 /**
  * ice_rdma_request_reset - accept request from RDMA to perform a reset
- * @pf: struct for PF
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @reset_type: type of reset
+ *
+ * Return: Zero on success, error code on failure
  */
-int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type)
+int ice_rdma_request_reset(struct iidc_rdma_core_dev_info *cdev,
+			   enum iidc_rdma_reset_type reset_type)
 {
 	enum ice_reset_req reset;
+	struct ice_pf *pf;
 
-	if (WARN_ON(!pf))
+	if (WARN_ON(!cdev))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
+
 	switch (reset_type) {
-	case IIDC_PFR:
+	case IIDC_FUNC_RESET:
 		reset = ICE_RESET_PFR;
 		break;
-	case IIDC_CORER:
+	case IIDC_DEV_RESET:
 		reset = ICE_RESET_CORER;
 		break;
-	case IIDC_GLOBR:
-		reset = ICE_RESET_GLOBR;
-		break;
 	default:
-		dev_err(ice_pf_to_dev(pf), "incorrect reset request\n");
 		return -EINVAL;
 	}
 
@@ -169,18 +186,23 @@ EXPORT_SYMBOL_GPL(ice_rdma_request_reset);
 
 /**
  * ice_rdma_update_vsi_filter - update main VSI filters for RDMA
- * @pf: pointer to struct for PF
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @vsi_id: VSI HW idx to update filter on
  * @enable: bool whether to enable or disable filters
+ *
+ * Return: Zero on success, error code on failure
  */
-int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable)
+int ice_rdma_update_vsi_filter(struct iidc_rdma_core_dev_info *cdev,
+			       u16 vsi_id, bool enable)
 {
 	struct ice_vsi *vsi;
+	struct ice_pf *pf;
 	int status;
 
-	if (WARN_ON(!pf))
+	if (WARN_ON(!cdev))
 		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
 	vsi = ice_find_vsi(pf, vsi_id);
 	if (!vsi)
 		return -EINVAL;
@@ -201,37 +223,23 @@ int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable)
 EXPORT_SYMBOL_GPL(ice_rdma_update_vsi_filter);
 
 /**
- * ice_get_qos_params - parse QoS params for RDMA consumption
- * @pf: pointer to PF struct
- * @qos: set of QoS values
+ * ice_alloc_rdma_qvector - alloc vector resources reserved for RDMA driver
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
+ * @entry: MSI-X entry to be removed
+ *
+ * Return: Zero on success, error code on failure
  */
-void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos)
+int ice_alloc_rdma_qvector(struct iidc_rdma_core_dev_info *cdev,
+			   struct msix_entry *entry)
 {
-	struct ice_dcbx_cfg *dcbx_cfg;
-	unsigned int i;
-	u32 up2tc;
-
-	dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
-	up2tc = rd32(&pf->hw, PRTDCB_TUP2TC);
-
-	qos->num_tc = ice_dcb_get_num_tc(dcbx_cfg);
-	for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++)
-		qos->up2tc[i] = (up2tc >> (i * 3)) & 0x7;
-
-	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
-		qos->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i];
-
-	qos->pfc_mode = dcbx_cfg->pfc_mode;
-	if (qos->pfc_mode == IIDC_DSCP_PFC_MODE)
-		for (i = 0; i < IIDC_MAX_DSCP_MAPPING; i++)
-			qos->dscp_map[i] = dcbx_cfg->dscp_map[i];
-}
-EXPORT_SYMBOL_GPL(ice_get_qos_params);
+	struct msi_map map;
+	struct ice_pf *pf;
 
-int ice_alloc_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry)
-{
-	struct msi_map map = ice_alloc_irq(pf, true);
+	if (WARN_ON(!cdev))
+		return -EINVAL;
 
+	pf = pci_get_drvdata(cdev->pdev);
+	map = ice_alloc_irq(pf, true);
 	if (map.index < 0)
 		return -ENOMEM;
 
@@ -244,12 +252,19 @@ EXPORT_SYMBOL_GPL(ice_alloc_rdma_qvector);
 
 /**
  * ice_free_rdma_qvector - free vector resources reserved for RDMA driver
- * @pf: board private structure to initialize
+ * @cdev: pointer to iidc_rdma_core_dev_info struct
  * @entry: MSI-X entry to be removed
  */
-void ice_free_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry)
+void ice_free_rdma_qvector(struct iidc_rdma_core_dev_info *cdev,
+			   struct msix_entry *entry)
 {
 	struct msi_map map;
+	struct ice_pf *pf;
+
+	if (WARN_ON(!cdev || !entry))
+		return;
+
+	pf = pci_get_drvdata(cdev->pdev);
 
 	map.index = entry->entry;
 	map.virq = entry->vector;
@@ -263,19 +278,23 @@ EXPORT_SYMBOL_GPL(ice_free_rdma_qvector);
  */
 static void ice_adev_release(struct device *dev)
 {
-	struct iidc_auxiliary_dev *iadev;
+	struct iidc_rdma_core_auxiliary_dev *iadev;
 
-	iadev = container_of(dev, struct iidc_auxiliary_dev, adev.dev);
+	iadev = container_of(dev, struct iidc_rdma_core_auxiliary_dev,
+			     adev.dev);
 	kfree(iadev);
 }
 
 /**
  * ice_plug_aux_dev - allocate and register AUX device
  * @pf: pointer to pf struct
+ *
+ * Return: Zero on success, error code on failure
  */
 int ice_plug_aux_dev(struct ice_pf *pf)
 {
-	struct iidc_auxiliary_dev *iadev;
+	struct iidc_rdma_core_auxiliary_dev *iadev;
+	struct iidc_rdma_core_dev_info *cdev;
 	struct auxiliary_device *adev;
 	int ret;
 
@@ -285,17 +304,22 @@ int ice_plug_aux_dev(struct ice_pf *pf)
 	if (!ice_is_rdma_ena(pf))
 		return 0;
 
+	cdev = pf->cdev_info;
+	if (!cdev)
+		return -ENODEV;
+
 	iadev = kzalloc(sizeof(*iadev), GFP_KERNEL);
 	if (!iadev)
 		return -ENOMEM;
 
 	adev = &iadev->adev;
-	iadev->pf = pf;
+	iadev->cdev_info = cdev;
 
 	adev->id = pf->aux_idx;
 	adev->dev.release = ice_adev_release;
 	adev->dev.parent = &pf->pdev->dev;
-	adev->name = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? "roce" : "iwarp";
+	adev->name = cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2 ?
+		"roce" : "iwarp";
 
 	ret = auxiliary_device_init(adev);
 	if (ret) {
@@ -310,7 +334,7 @@ int ice_plug_aux_dev(struct ice_pf *pf)
 	}
 
 	mutex_lock(&pf->adev_mutex);
-	pf->adev = adev;
+	cdev->adev = adev;
 	mutex_unlock(&pf->adev_mutex);
 
 	return 0;
@@ -324,8 +348,8 @@ void ice_unplug_aux_dev(struct ice_pf *pf)
 	struct auxiliary_device *adev;
 
 	mutex_lock(&pf->adev_mutex);
-	adev = pf->adev;
-	pf->adev = NULL;
+	adev = pf->cdev_info->adev;
+	pf->cdev_info->adev = NULL;
 	mutex_unlock(&pf->adev_mutex);
 
 	if (adev) {
@@ -340,7 +364,9 @@ void ice_unplug_aux_dev(struct ice_pf *pf)
  */
 int ice_init_rdma(struct ice_pf *pf)
 {
+	struct iidc_rdma_priv_dev_info *privd;
 	struct device *dev = &pf->pdev->dev;
+	struct iidc_rdma_core_dev_info *cdev;
 	int ret;
 
 	if (!ice_is_rdma_ena(pf)) {
@@ -348,22 +374,50 @@ int ice_init_rdma(struct ice_pf *pf)
 		return 0;
 	}
 
+	cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
+	if (!cdev)
+		return -ENOMEM;
+
+	pf->cdev_info = cdev;
+
+	privd = kzalloc(sizeof(*privd), GFP_KERNEL);
+	if (!privd) {
+		ret = -ENOMEM;
+		goto err_privd_alloc;
+	}
+
+	privd->pf_id = pf->hw.pf_id;
 	ret = xa_alloc(&ice_aux_id, &pf->aux_idx, NULL, XA_LIMIT(1, INT_MAX),
 		       GFP_KERNEL);
 	if (ret) {
 		dev_err(dev, "Failed to allocate device ID for AUX driver\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_alloc_xa;
 	}
 
-	pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2;
+	cdev->iidc_priv = privd;
+	privd->netdev = pf->vsi[0]->netdev;
+
+	privd->hw_addr = (u8 __iomem *)pf->hw.hw_addr;
+	cdev->pdev = pf->pdev;
+	privd->vport_id = pf->vsi[0]->vsi_num;
+
+	pf->cdev_info->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2;
+	ice_setup_dcb_qos_info(pf, &privd->qos_info);
 	ret = ice_plug_aux_dev(pf);
 	if (ret)
 		goto err_plug_aux_dev;
 	return 0;
 
 err_plug_aux_dev:
-	pf->adev = NULL;
+	pf->cdev_info->adev = NULL;
 	xa_erase(&ice_aux_id, pf->aux_idx);
+err_alloc_xa:
+	kfree(privd);
+err_privd_alloc:
+	kfree(cdev);
+	pf->cdev_info = NULL;
+
 	return ret;
 }
 
@@ -378,4 +432,7 @@ void ice_deinit_rdma(struct ice_pf *pf)
 
 	ice_unplug_aux_dev(pf);
 	xa_erase(&ice_aux_id, pf->aux_idx);
+	kfree(pf->cdev_info->iidc_priv);
+	kfree(pf->cdev_info);
+	pf->cdev_info = NULL;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_idc_int.h b/drivers/net/ethernet/intel/ice/ice_idc_int.h
index 4b0c86757df9..17dbfcfb6a2a 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc_int.h
+++ b/drivers/net/ethernet/intel/ice/ice_idc_int.h
@@ -4,10 +4,11 @@
 #ifndef _ICE_IDC_INT_H_
 #define _ICE_IDC_INT_H_
 
-#include <linux/net/intel/iidc.h>
+#include <linux/net/intel/iidc_rdma.h>
+#include <linux/net/intel/iidc_rdma_ice.h>
 
 struct ice_pf;
 
-void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event);
+void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_rdma_event *event);
 
 #endif /* !_ICE_IDC_INT_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 22371011c249..2410aee59fb2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -1321,12 +1321,18 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 		 */
 		if (!primary_lag) {
 			lag->primary = true;
+			if (!ice_is_switchdev_running(lag->pf))
+				return;
+
 			/* Configure primary's SWID to be shared */
 			ice_lag_primary_swid(lag, true);
 			primary_lag = lag;
 		} else {
 			u16 swid;
 
+			if (!ice_is_switchdev_running(primary_lag->pf))
+				return;
+
 			swid = primary_lag->pf->hw.port_info->sw_id;
 			ice_lag_set_swid(swid, lag, true);
 			ice_lag_add_prune_list(primary_lag, lag->pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 0bcf9d127ac9..03bb16191237 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2065,12 +2065,15 @@ static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi)
 }
 
 /**
- * ice_cfg_sw_lldp - Config switch rules for LLDP packet handling
+ * ice_vsi_cfg_sw_lldp - Config switch rules for LLDP packet handling
  * @vsi: the VSI being configured
  * @tx: bool to determine Tx or Rx rule
  * @create: bool to determine create or remove Rule
+ *
+ * Adding an ethtype Tx rule to the uplink VSI results in it being applied
+ * to the whole port, so LLDP transmission for VFs will be blocked too.
  */
-void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
+void ice_vsi_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
 {
 	int (*eth_fltr)(struct ice_vsi *v, u16 type, u16 flag,
 			enum ice_sw_fwd_act_type act);
@@ -2085,19 +2088,59 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
 		status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_TX,
 				  ICE_DROP_PACKET);
 	} else {
-		if (ice_fw_supports_lldp_fltr_ctrl(&pf->hw)) {
-			status = ice_lldp_fltr_add_remove(&pf->hw, vsi->vsi_num,
-							  create);
-		} else {
+		if (!test_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags)) {
 			status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_RX,
 					  ICE_FWD_TO_VSI);
+			if (!status || !create)
+				goto report;
+
+			dev_info(dev,
+				 "Failed to add generic LLDP Rx filter on VSI %i error: %d, falling back to specialized AQ control\n",
+				 vsi->vsi_num, status);
 		}
+
+		status = ice_lldp_fltr_add_remove(&pf->hw, vsi, create);
+		if (!status)
+			set_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags);
+
 	}
 
+report:
 	if (status)
-		dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %d\n",
-			create ? "adding" : "removing", tx ? "TX" : "RX",
-			vsi->vsi_num, status);
+		dev_warn(dev, "Failed to %s %s LLDP rule on VSI %i error: %d\n",
+			 create ? "add" : "remove", tx ? "Tx" : "Rx",
+			 vsi->vsi_num, status);
+}
+
+/**
+ * ice_cfg_sw_rx_lldp - Enable/disable software handling of LLDP
+ * @pf: the PF being configured
+ * @enable: enable or disable
+ *
+ * Configure switch rules to enable/disable LLDP handling by software
+ * across PF.
+ */
+void ice_cfg_sw_rx_lldp(struct ice_pf *pf, bool enable)
+{
+	struct ice_vsi *vsi;
+	struct ice_vf *vf;
+	unsigned int bkt;
+
+	vsi = ice_get_main_vsi(pf);
+	ice_vsi_cfg_sw_lldp(vsi, false, enable);
+
+	if (!test_bit(ICE_FLAG_SRIOV_ENA, pf->flags))
+		return;
+
+	ice_for_each_vf(pf, bkt, vf) {
+		vsi = ice_get_vf_vsi(vf);
+
+		if (WARN_ON(!vsi))
+			continue;
+
+		if (ice_vf_is_lldp_ena(vf))
+			ice_vsi_cfg_sw_lldp(vsi, false, enable);
+	}
 }
 
 /**
@@ -2528,7 +2571,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params)
 	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF) {
 		ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX,
 				 ICE_DROP_PACKET);
-		ice_cfg_sw_lldp(vsi, true, true);
+		ice_vsi_cfg_sw_lldp(vsi, true, true);
 	}
 
 	if (!vsi->agg_node)
@@ -2825,9 +2868,11 @@ int ice_vsi_release(struct ice_vsi *vsi)
 	/* The Rx rule will only exist to remove if the LLDP FW
 	 * engine is currently stopped
 	 */
-	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF &&
-	    !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
-		ice_cfg_sw_lldp(vsi, false, false);
+	if (!ice_is_safe_mode(pf) &&
+	    !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags) &&
+	    (vsi->type == ICE_VSI_PF || (vsi->type == ICE_VSI_VF &&
+	     ice_vf_is_lldp_ena(vsi->vf))))
+		ice_vsi_cfg_sw_lldp(vsi, false, false);
 
 	ice_vsi_decfg(vsi);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index b4c9cb28a016..654516c5fc3e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -29,7 +29,8 @@ ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 
 int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi);
 
-void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);
+void ice_vsi_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);
+void ice_cfg_sw_rx_lldp(struct ice_pf *pf, bool enable);
 
 int ice_set_link(struct ice_vsi *vsi, bool ena);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index d390157b59fe..20d3baf955e3 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2401,11 +2401,11 @@ static void ice_service_task(struct work_struct *work)
 	}
 
 	if (test_and_clear_bit(ICE_AUX_ERR_PENDING, pf->state)) {
-		struct iidc_event *event;
+		struct iidc_rdma_event *event;
 
 		event = kzalloc(sizeof(*event), GFP_KERNEL);
 		if (event) {
-			set_bit(IIDC_EVENT_CRIT_ERR, event->type);
+			set_bit(IIDC_RDMA_EVENT_CRIT_ERR, event->type);
 			/* report the entire OICR value to AUX driver */
 			swap(event->reg, pf->oicr_err_reg);
 			ice_send_event_to_aux(pf, event);
@@ -2424,11 +2424,11 @@ static void ice_service_task(struct work_struct *work)
 		ice_plug_aux_dev(pf);
 
 	if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) {
-		struct iidc_event *event;
+		struct iidc_rdma_event *event;
 
 		event = kzalloc(sizeof(*event), GFP_KERNEL);
 		if (event) {
-			set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type);
+			set_bit(IIDC_RDMA_EVENT_AFTER_MTU_CHANGE, event->type);
 			ice_send_event_to_aux(pf, event);
 			kfree(event);
 		}
@@ -8330,11 +8330,16 @@ void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
  * @np: net device to configure
  * @filter_dev: device on which filter is added
  * @cls_flower: offload data
+ * @ingress: if the rule is added to an ingress block
+ *
+ * Return: 0 if the flower was successfully added or deleted,
+ *	   negative error code otherwise.
  */
 static int
 ice_setup_tc_cls_flower(struct ice_netdev_priv *np,
 			struct net_device *filter_dev,
-			struct flow_cls_offload *cls_flower)
+			struct flow_cls_offload *cls_flower,
+			bool ingress)
 {
 	struct ice_vsi *vsi = np->vsi;
 
@@ -8343,7 +8348,7 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np,
 
 	switch (cls_flower->command) {
 	case FLOW_CLS_REPLACE:
-		return ice_add_cls_flower(filter_dev, vsi, cls_flower);
+		return ice_add_cls_flower(filter_dev, vsi, cls_flower, ingress);
 	case FLOW_CLS_DESTROY:
 		return ice_del_cls_flower(vsi, cls_flower);
 	default:
@@ -8352,20 +8357,46 @@ ice_setup_tc_cls_flower(struct ice_netdev_priv *np,
 }
 
 /**
- * ice_setup_tc_block_cb - callback handler registered for TC block
+ * ice_setup_tc_block_cb_ingress - callback handler for ingress TC block
  * @type: TC SETUP type
  * @type_data: TC flower offload data that contains user input
  * @cb_priv: netdev private data
+ *
+ * Return: 0 if the setup was successful, negative error code otherwise.
  */
 static int
-ice_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
+ice_setup_tc_block_cb_ingress(enum tc_setup_type type, void *type_data,
+			      void *cb_priv)
 {
 	struct ice_netdev_priv *np = cb_priv;
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return ice_setup_tc_cls_flower(np, np->vsi->netdev,
-					       type_data);
+					       type_data, true);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/**
+ * ice_setup_tc_block_cb_egress - callback handler for egress TC block
+ * @type: TC SETUP type
+ * @type_data: TC flower offload data that contains user input
+ * @cb_priv: netdev private data
+ *
+ * Return: 0 if the setup was successful, negative error code otherwise.
+ */
+static int
+ice_setup_tc_block_cb_egress(enum tc_setup_type type, void *type_data,
+			     void *cb_priv)
+{
+	struct ice_netdev_priv *np = cb_priv;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return ice_setup_tc_cls_flower(np, np->vsi->netdev,
+					       type_data, false);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -9310,27 +9341,45 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 	     void *type_data)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
+	enum flow_block_binder_type binder_type;
+	struct iidc_rdma_core_dev_info *cdev;
 	struct ice_pf *pf = np->vsi->back;
+	flow_setup_cb_t *flower_handler;
 	bool locked = false;
 	int err;
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
+		binder_type =
+			((struct flow_block_offload *)type_data)->binder_type;
+
+		switch (binder_type) {
+		case FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS:
+			flower_handler = ice_setup_tc_block_cb_ingress;
+			break;
+		case FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS:
+			flower_handler = ice_setup_tc_block_cb_egress;
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+
 		return flow_block_cb_setup_simple(type_data,
 						  &ice_block_cb_list,
-						  ice_setup_tc_block_cb,
-						  np, np, true);
+						  flower_handler,
+						  np, np, false);
 	case TC_SETUP_QDISC_MQPRIO:
 		if (ice_is_eswitch_mode_switchdev(pf)) {
 			netdev_err(netdev, "TC MQPRIO offload not supported, switchdev is enabled\n");
 			return -EOPNOTSUPP;
 		}
 
-		if (pf->adev) {
+		cdev = pf->cdev_info;
+		if (cdev && cdev->adev) {
 			mutex_lock(&pf->adev_mutex);
-			device_lock(&pf->adev->dev);
+			device_lock(&cdev->adev->dev);
 			locked = true;
-			if (pf->adev->dev.driver) {
+			if (cdev->adev->dev.driver) {
 				netdev_err(netdev, "Cannot change qdisc when RDMA is active\n");
 				err = -EBUSY;
 				goto adev_unlock;
@@ -9344,7 +9393,7 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 
 adev_unlock:
 		if (locked) {
-			device_unlock(&pf->adev->dev);
+			device_unlock(&cdev->adev->dev);
 			mutex_unlock(&pf->adev_mutex);
 		}
 		return err;
@@ -9380,7 +9429,7 @@ ice_indr_setup_block_cb(enum tc_setup_type type, void *type_data,
 	case TC_SETUP_CLSFLOWER:
 		return ice_setup_tc_cls_flower(np, priv->netdev,
 					       (struct flow_cls_offload *)
-					       type_data);
+					       type_data, false);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 1fd1ae03eb90..b79a148ed0f2 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -305,6 +305,9 @@ u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf,
 	u32 hi, lo, lo2;
 	u8 tmr_idx;
 
+	if (!ice_is_primary(hw))
+		hw = ice_get_primary_hw(pf);
+
 	tmr_idx = ice_get_ptp_src_clock_index(hw);
 	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
 	/* Read the system timestamp pre PHC read */
@@ -1624,14 +1627,6 @@ static int ice_ptp_cfg_extts(struct ice_pf *pf, struct ptp_extts_request *rq,
 	int pin_desc_idx;
 	u8 tmr_idx;
 
-	/* Reject requests with unsupported flags */
-
-	if (rq->flags & ~(PTP_ENABLE_FEATURE |
-			  PTP_RISING_EDGE |
-			  PTP_FALLING_EDGE |
-			  PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 	chan = rq->index;
 
@@ -1802,9 +1797,6 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq,
 	struct ice_hw *hw = &pf->hw;
 	int pin_desc_idx;
 
-	if (rq->flags & ~PTP_PEROUT_PHASE)
-		return -EOPNOTSUPP;
-
 	pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_PEROUT, rq->index);
 	if (pin_desc_idx < 0)
 		return -EIO;
@@ -2737,6 +2729,11 @@ static void ice_ptp_set_caps(struct ice_pf *pf)
 	info->enable = ice_ptp_gpio_enable;
 	info->verify = ice_verify_pin;
 
+	info->supported_extts_flags = PTP_RISING_EDGE |
+				      PTP_FALLING_EDGE |
+				      PTP_STRICT_FLAGS;
+	info->supported_perout_flags = PTP_PEROUT_PHASE;
+
 	switch (pf->hw.mac_type) {
 	case ICE_MAC_E810:
 		ice_ptp_set_funcs_e810(pf);
@@ -2986,6 +2983,32 @@ static void ice_ptp_periodic_work(struct kthread_work *work)
 }
 
 /**
+ * ice_ptp_prepare_rebuild_sec - Prepare second NAC for PTP reset or rebuild
+ * @pf: Board private structure
+ * @rebuild: rebuild if true, prepare if false
+ * @reset_type: the reset type being performed
+ */
+static void ice_ptp_prepare_rebuild_sec(struct ice_pf *pf, bool rebuild,
+					enum ice_reset_req reset_type)
+{
+	struct list_head *entry;
+
+	list_for_each(entry, &pf->adapter->ports.ports) {
+		struct ice_ptp_port *port = list_entry(entry,
+						       struct ice_ptp_port,
+						       list_node);
+		struct ice_pf *peer_pf = ptp_port_to_pf(port);
+
+		if (!ice_is_primary(&peer_pf->hw)) {
+			if (rebuild)
+				ice_ptp_rebuild(peer_pf, reset_type);
+			else
+				ice_ptp_prepare_for_reset(peer_pf, reset_type);
+		}
+	}
+}
+
+/**
  * ice_ptp_prepare_for_reset - Prepare PTP for reset
  * @pf: Board private structure
  * @reset_type: the reset type being performed
@@ -2993,6 +3016,7 @@ static void ice_ptp_periodic_work(struct kthread_work *work)
 void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 {
 	struct ice_ptp *ptp = &pf->ptp;
+	struct ice_hw *hw = &pf->hw;
 	u8 src_tmr;
 
 	if (ptp->state != ICE_PTP_READY)
@@ -3008,6 +3032,9 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 	if (reset_type == ICE_RESET_PFR)
 		return;
 
+	if (ice_pf_src_tmr_owned(pf) && hw->mac_type == ICE_MAC_GENERIC_3K_E825)
+		ice_ptp_prepare_rebuild_sec(pf, false, reset_type);
+
 	ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx);
 
 	/* Disable periodic outputs */
@@ -3129,13 +3156,6 @@ err:
 	dev_err(ice_pf_to_dev(pf), "PTP reset failed %d\n", err);
 }
 
-static bool ice_is_primary(struct ice_hw *hw)
-{
-	return hw->mac_type == ICE_MAC_GENERIC_3K_E825 && ice_is_dual(hw) ?
-		       !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) :
-		       true;
-}
-
 static int ice_ptp_setup_adapter(struct ice_pf *pf)
 {
 	if (!ice_pf_src_tmr_owned(pf) || !ice_is_primary(&pf->hw))
@@ -3355,17 +3375,16 @@ void ice_ptp_init(struct ice_pf *pf)
 {
 	struct ice_ptp *ptp = &pf->ptp;
 	struct ice_hw *hw = &pf->hw;
-	int lane_num, err;
+	int err;
 
 	ptp->state = ICE_PTP_INITIALIZING;
 
-	lane_num = ice_get_phy_lane_number(hw);
-	if (lane_num < 0) {
-		err = lane_num;
+	if (hw->lane_num < 0) {
+		err = hw->lane_num;
 		goto err_exit;
 	}
+	ptp->port.port_num = hw->lane_num;
 
-	ptp->port.port_num = (u8)lane_num;
 	ice_ptp_init_hw(hw);
 
 	ice_ptp_init_tx_interrupt_mode(pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 89bb8461284a..ccac84eb34c9 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -240,7 +240,7 @@ static int ice_read_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 *val)
 {
 	struct ice_sbq_msg_input cgu_msg = {
 		.opcode = ice_sbq_msg_rd,
-		.dest_dev = cgu,
+		.dest_dev = ice_sbq_dev_cgu,
 		.msg_addr_low = addr
 	};
 	int err;
@@ -272,7 +272,7 @@ static int ice_write_cgu_reg_e82x(struct ice_hw *hw, u32 addr, u32 val)
 {
 	struct ice_sbq_msg_input cgu_msg = {
 		.opcode = ice_sbq_msg_wr,
-		.dest_dev = cgu,
+		.dest_dev = ice_sbq_dev_cgu,
 		.msg_addr_low = addr,
 		.data = val
 	};
@@ -874,8 +874,12 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw,
  */
 void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 {
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 	u32 cmd_val = ice_ptp_tmr_cmd_to_src_reg(hw, cmd);
 
+	if (!ice_is_primary(hw))
+		hw = ice_get_primary_hw(pf);
+
 	wr32(hw, GLTSYN_CMD, cmd_val);
 }
 
@@ -891,6 +895,9 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
 {
 	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 
+	if (!ice_is_primary(hw))
+		hw = ice_get_primary_hw(pf);
+
 	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
 	wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD);
 	ice_flush(hw);
@@ -919,16 +926,24 @@ static void ice_ptp_cfg_sync_delay(const struct ice_hw *hw, u32 delay)
  *
  * Return: destination sideband queue PHY device.
  */
-static enum ice_sbq_msg_dev ice_ptp_get_dest_dev_e825(struct ice_hw *hw,
-						      u8 port)
+static enum ice_sbq_dev_id ice_ptp_get_dest_dev_e825(struct ice_hw *hw,
+						     u8 port)
 {
-	/* On a single complex E825, PHY 0 is always destination device phy_0
+	u8 curr_phy, tgt_phy;
+
+	tgt_phy = port >= hw->ptp.ports_per_phy;
+	curr_phy = hw->lane_num >= hw->ptp.ports_per_phy;
+	/* In the driver, lanes 4..7 are in fact 0..3 on a second PHY.
+	 * On a single complex E825C, PHY 0 is always destination device phy_0
 	 * and PHY 1 is phy_0_peer.
+	 * On dual complex E825C, device phy_0 points to PHY on a current
+	 * complex and phy_0_peer to PHY on a different complex.
 	 */
-	if (port >= hw->ptp.ports_per_phy)
-		return eth56g_phy_1;
+	if ((!ice_is_dual(hw) && tgt_phy == 1) ||
+	    (ice_is_dual(hw) && tgt_phy != curr_phy))
+		return ice_sbq_dev_phy_0_peer;
 	else
-		return eth56g_phy_0;
+		return ice_sbq_dev_phy_0;
 }
 
 /**
@@ -2417,6 +2432,7 @@ int ice_phy_cfg_intr_eth56g(struct ice_hw *hw, u8 port, bool ena, u8 threshold)
 static int ice_read_phy_and_phc_time_eth56g(struct ice_hw *hw, u8 port,
 					    u64 *phy_time, u64 *phc_time)
 {
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 	u64 tx_time, rx_time;
 	u32 zo, lo;
 	u8 tmr_idx;
@@ -2436,8 +2452,13 @@ static int ice_read_phy_and_phc_time_eth56g(struct ice_hw *hw, u8 port,
 	ice_ptp_exec_tmr_cmd(hw);
 
 	/* Read the captured PHC time from the shadow time registers */
-	zo = rd32(hw, GLTSYN_SHTIME_0(tmr_idx));
-	lo = rd32(hw, GLTSYN_SHTIME_L(tmr_idx));
+	if (ice_is_primary(hw)) {
+		zo = rd32(hw, GLTSYN_SHTIME_0(tmr_idx));
+		lo = rd32(hw, GLTSYN_SHTIME_L(tmr_idx));
+	} else {
+		zo = rd32(ice_get_primary_hw(pf), GLTSYN_SHTIME_0(tmr_idx));
+		lo = rd32(ice_get_primary_hw(pf), GLTSYN_SHTIME_L(tmr_idx));
+	}
 	*phc_time = (u64)lo << 32 | zo;
 
 	/* Read the captured PHY time from the PHY shadow registers */
@@ -2574,6 +2595,7 @@ int ice_stop_phy_timer_eth56g(struct ice_hw *hw, u8 port, bool soft_reset)
  */
 int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port)
 {
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
 	u32 lo, hi;
 	u64 incval;
 	u8 tmr_idx;
@@ -2599,8 +2621,13 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port)
 	if (err)
 		return err;
 
-	lo = rd32(hw, GLTSYN_INCVAL_L(tmr_idx));
-	hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx));
+	if (ice_is_primary(hw)) {
+		lo = rd32(hw, GLTSYN_INCVAL_L(tmr_idx));
+		hi = rd32(hw, GLTSYN_INCVAL_H(tmr_idx));
+	} else {
+		lo = rd32(ice_get_primary_hw(pf), GLTSYN_INCVAL_L(tmr_idx));
+		hi = rd32(ice_get_primary_hw(pf), GLTSYN_INCVAL_H(tmr_idx));
+	}
 	incval = (u64)hi << 32 | lo;
 
 	err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_REG_TIMETUS_L, incval);
@@ -2631,25 +2658,6 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port)
 }
 
 /**
- * ice_sb_access_ena_eth56g - Enable SB devices (PHY and others) access
- * @hw: pointer to HW struct
- * @enable: Enable or disable access
- *
- * Enable sideband devices (PHY and others) access.
- */
-static void ice_sb_access_ena_eth56g(struct ice_hw *hw, bool enable)
-{
-	u32 val = rd32(hw, PF_SB_REM_DEV_CTL);
-
-	if (enable)
-		val |= BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1);
-	else
-		val &= ~(BIT(eth56g_phy_0) | BIT(cgu) | BIT(eth56g_phy_1));
-
-	wr32(hw, PF_SB_REM_DEV_CTL, val);
-}
-
-/**
  * ice_ptp_init_phc_e825 - Perform E825 specific PHC initialization
  * @hw: pointer to HW struct
  *
@@ -2659,8 +2667,6 @@ static void ice_sb_access_ena_eth56g(struct ice_hw *hw, bool enable)
  */
 static int ice_ptp_init_phc_e825(struct ice_hw *hw)
 {
-	ice_sb_access_ena_eth56g(hw, true);
-
 	/* Initialize the Clock Generation Unit */
 	return ice_init_cgu_e82x(hw);
 }
@@ -2747,8 +2753,6 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw)
 	params->num_phys = 2;
 	ptp->ports_per_phy = 4;
 	ptp->num_lports = params->num_phys * ptp->ports_per_phy;
-
-	ice_sb_access_ena_eth56g(hw, true);
 }
 
 /* E822 family functions
@@ -2781,7 +2785,7 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw,
 		msg->msg_addr_high = P_Q1_H(P_4_BASE + offset, phy_port);
 	}
 
-	msg->dest_dev = rmn_0;
+	msg->dest_dev = ice_sbq_dev_phy_0;
 }
 
 /**
@@ -3104,7 +3108,7 @@ static int ice_fill_quad_msg_e82x(struct ice_hw *hw,
 	if (quad >= ICE_GET_QUAD_NUM(hw->ptp.num_lports))
 		return -EINVAL;
 
-	msg->dest_dev = rmn_0;
+	msg->dest_dev = ice_sbq_dev_phy_0;
 
 	if (!(quad % ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy)))
 		addr = Q_0_BASE + offset;
@@ -4823,7 +4827,7 @@ static int ice_read_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 *val)
 	msg.msg_addr_low = lower_16_bits(addr);
 	msg.msg_addr_high = upper_16_bits(addr);
 	msg.opcode = ice_sbq_msg_rd;
-	msg.dest_dev = rmn_0;
+	msg.dest_dev = ice_sbq_dev_phy_0;
 
 	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
 	if (err) {
@@ -4853,7 +4857,7 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val)
 	msg.msg_addr_low = lower_16_bits(addr);
 	msg.msg_addr_high = upper_16_bits(addr);
 	msg.opcode = ice_sbq_msg_wr;
-	msg.dest_dev = rmn_0;
+	msg.dest_dev = ice_sbq_dev_phy_0;
 	msg.data = val;
 
 	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index e5925ccc2613..83f20fa7ace7 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -444,11 +444,6 @@ static inline u64 ice_get_base_incval(struct ice_hw *hw)
 	}
 }
 
-static inline bool ice_is_dual(struct ice_hw *hw)
-{
-	return !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_DUAL_M);
-}
-
 #define PFTSYN_SEM_BYTES	4
 
 #define ICE_PTP_CLOCK_INDEX_0	0x00
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index fb7a1b9a4313..cb08746556a6 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -219,7 +219,8 @@ ice_repr_setup_tc_cls_flower(struct ice_repr *repr,
 {
 	switch (flower->command) {
 	case FLOW_CLS_REPLACE:
-		return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower);
+		return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower,
+					  true);
 	case FLOW_CLS_DESTROY:
 		return ice_del_cls_flower(repr->src_vsi, flower);
 	default:
@@ -336,6 +337,7 @@ void ice_repr_destroy(struct ice_repr *repr)
 static void ice_repr_rem_vf(struct ice_repr *repr)
 {
 	ice_eswitch_decfg_vsi(repr->src_vsi, repr->parent_mac);
+	ice_pass_vf_tx_lldp(repr->src_vsi, true);
 	unregister_netdev(repr->netdev);
 	ice_devlink_destroy_vf_port(repr->vf);
 	ice_virtchnl_set_dflt_ops(repr->vf);
@@ -417,6 +419,10 @@ static int ice_repr_add_vf(struct ice_repr *repr)
 	if (err)
 		goto err_netdev;
 
+	err = ice_drop_vf_tx_lldp(repr->src_vsi, true);
+	if (err)
+		goto err_drop_lldp;
+
 	err = ice_eswitch_cfg_vsi(repr->src_vsi, repr->parent_mac);
 	if (err)
 		goto err_cfg_vsi;
@@ -429,6 +435,8 @@ static int ice_repr_add_vf(struct ice_repr *repr)
 	return 0;
 
 err_cfg_vsi:
+	ice_pass_vf_tx_lldp(repr->src_vsi, true);
+err_drop_lldp:
 	unregister_netdev(repr->netdev);
 err_netdev:
 	ice_devlink_destroy_vf_port(vf);
diff --git a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
index 3b0054faf70c..183dd5457d6a 100644
--- a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
@@ -46,13 +46,10 @@ struct ice_sbq_evt_desc {
 	u8 data[24];
 };
 
-enum ice_sbq_msg_dev {
-	eth56g_phy_0	= 0x02,
-	rmn_0		= 0x02,
-	rmn_1		= 0x03,
-	rmn_2		= 0x04,
-	cgu		= 0x06,
-	eth56g_phy_1	= 0x0D,
+enum ice_sbq_dev_id {
+	ice_sbq_dev_phy_0	= 0x02,
+	ice_sbq_dev_cgu		= 0x06,
+	ice_sbq_dev_phy_0_peer	= 0x0D,
 };
 
 enum ice_sbq_msg_opcode {
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index f1648cf103b7..0e4dc1a5cff0 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -63,6 +63,7 @@ static void ice_free_vf_res(struct ice_vf *vf)
 	if (vf->lan_vsi_idx != ICE_NO_VSI) {
 		ice_vf_vsi_release(vf);
 		vf->num_mac = 0;
+		vf->num_mac_lldp = 0;
 	}
 
 	last_vector_idx = vf->first_vector_idx + vf->num_msix - 1;
@@ -1402,6 +1403,9 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted)
 
 	mutex_lock(&vf->cfg_lock);
 
+	while (!trusted && vf->num_mac_lldp)
+		ice_vf_update_mac_lldp_num(vf, ice_get_vf_vsi(vf), false);
+
 	vf->trusted = trusted;
 	ice_reset_vf(vf, ICE_VF_RESET_NOTIFY);
 	dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n",
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 4a91e0aaf0a5..9d9a7edd3618 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -3146,7 +3146,7 @@ ice_add_update_vsi_list(struct ice_hw *hw,
 		u16 vsi_handle_arr[2];
 
 		/* A rule already exists with the new VSI being added */
-		if (cur_fltr->fwd_id.hw_vsi_id == new_fltr->fwd_id.hw_vsi_id)
+		if (cur_fltr->vsi_handle == new_fltr->vsi_handle)
 			return -EEXIST;
 
 		vsi_handle_arr[0] = cur_fltr->vsi_handle;
@@ -5978,7 +5978,7 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw,
 
 		/* A rule already exists with the new VSI being added */
 		if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map))
-			return 0;
+			return -EEXIST;
 
 		/* Update the previously created VSI list set with
 		 * the new VSI ID passed in
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index ea39b999a0d0..fb9ea7f8ef44 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -12,14 +12,11 @@
 /**
  * ice_tc_count_lkups - determine lookup count for switch filter
  * @flags: TC-flower flags
- * @headers: Pointer to TC flower filter header structure
  * @fltr: Pointer to outer TC filter structure
  *
- * Determine lookup count based on TC flower input for switch filter.
+ * Return: lookup count based on TC flower input for a switch filter.
  */
-static int
-ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers,
-		   struct ice_tc_flower_fltr *fltr)
+static int ice_tc_count_lkups(u32 flags, struct ice_tc_flower_fltr *fltr)
 {
 	int lkups_cnt = 1; /* 0th lookup is metadata */
 
@@ -684,26 +681,26 @@ static int ice_tc_setup_action(struct net_device *filter_dev,
 	fltr->action.fltr_act = action;
 
 	if (ice_is_port_repr_netdev(filter_dev) &&
-	    ice_is_port_repr_netdev(target_dev)) {
+	    ice_is_port_repr_netdev(target_dev) &&
+	    fltr->direction == ICE_ESWITCH_FLTR_EGRESS) {
 		repr = ice_netdev_to_repr(target_dev);
 
 		fltr->dest_vsi = repr->src_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
 	} else if (ice_is_port_repr_netdev(filter_dev) &&
-		   ice_tc_is_dev_uplink(target_dev)) {
+		   ice_tc_is_dev_uplink(target_dev) &&
+		   fltr->direction == ICE_ESWITCH_FLTR_EGRESS) {
 		repr = ice_netdev_to_repr(filter_dev);
 
 		fltr->dest_vsi = repr->src_vsi->back->eswitch.uplink_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
 	} else if (ice_tc_is_dev_uplink(filter_dev) &&
-		   ice_is_port_repr_netdev(target_dev)) {
+		   ice_is_port_repr_netdev(target_dev) &&
+		   fltr->direction == ICE_ESWITCH_FLTR_INGRESS) {
 		repr = ice_netdev_to_repr(target_dev);
 
 		fltr->dest_vsi = repr->src_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
 	} else {
 		NL_SET_ERR_MSG_MOD(fltr->extack,
-				   "Unsupported netdevice in switchdev mode");
+				   "The action is not supported for this netdevice");
 		return -EINVAL;
 	}
 
@@ -716,13 +713,11 @@ ice_tc_setup_drop_action(struct net_device *filter_dev,
 {
 	fltr->action.fltr_act = ICE_DROP_PACKET;
 
-	if (ice_is_port_repr_netdev(filter_dev)) {
-		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
-	} else if (ice_tc_is_dev_uplink(filter_dev)) {
-		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
-	} else {
+	if (!ice_tc_is_dev_uplink(filter_dev) &&
+	    !(ice_is_port_repr_netdev(filter_dev) &&
+	      fltr->direction == ICE_ESWITCH_FLTR_INGRESS)) {
 		NL_SET_ERR_MSG_MOD(fltr->extack,
-				   "Unsupported netdevice in switchdev mode");
+				   "The action is not supported for this netdevice");
 		return -EINVAL;
 	}
 
@@ -767,10 +762,157 @@ static int ice_eswitch_tc_parse_action(struct net_device *filter_dev,
 	return 0;
 }
 
+static bool ice_is_fltr_lldp(struct ice_tc_flower_fltr *fltr)
+{
+	return fltr->outer_headers.l2_key.n_proto == htons(ETH_P_LLDP);
+}
+
+static bool ice_is_fltr_pf_tx_lldp(struct ice_tc_flower_fltr *fltr)
+{
+	struct ice_vsi *vsi = fltr->src_vsi, *uplink;
+
+	if (!ice_is_switchdev_running(vsi->back))
+		return false;
+
+	uplink = vsi->back->eswitch.uplink_vsi;
+	return vsi == uplink && fltr->action.fltr_act == ICE_DROP_PACKET &&
+	       ice_is_fltr_lldp(fltr) &&
+	       fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+	       fltr->flags == ICE_TC_FLWR_FIELD_ETH_TYPE_ID;
+}
+
+static bool ice_is_fltr_vf_tx_lldp(struct ice_tc_flower_fltr *fltr)
+{
+	struct ice_vsi *vsi = fltr->src_vsi, *uplink;
+
+	uplink = vsi->back->eswitch.uplink_vsi;
+	return fltr->src_vsi->type == ICE_VSI_VF && ice_is_fltr_lldp(fltr) &&
+	       fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+	       fltr->dest_vsi == uplink;
+}
+
+static struct ice_tc_flower_fltr *
+ice_find_pf_tx_lldp_fltr(struct ice_pf *pf)
+{
+	struct ice_tc_flower_fltr *fltr;
+
+	hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node)
+		if (ice_is_fltr_pf_tx_lldp(fltr))
+			return fltr;
+
+	return NULL;
+}
+
+static bool ice_any_vf_lldp_tx_ena(struct ice_pf *pf)
+{
+	struct ice_vf *vf;
+	unsigned int bkt;
+
+	ice_for_each_vf(pf, bkt, vf)
+		if (vf->lldp_tx_ena)
+			return true;
+
+	return false;
+}
+
+int ice_pass_vf_tx_lldp(struct ice_vsi *vsi, bool deinit)
+{
+	struct ice_rule_query_data remove_entry = {
+		.rid = vsi->vf->lldp_recipe_id,
+		.rule_id = vsi->vf->lldp_rule_id,
+		.vsi_handle = vsi->idx,
+	};
+	struct ice_pf *pf = vsi->back;
+	int err;
+
+	if (vsi->vf->lldp_tx_ena)
+		return 0;
+
+	if (!deinit && !ice_find_pf_tx_lldp_fltr(vsi->back))
+		return -EINVAL;
+
+	if (!deinit && ice_any_vf_lldp_tx_ena(pf))
+		return -EINVAL;
+
+	err = ice_rem_adv_rule_by_id(&pf->hw, &remove_entry);
+	if (!err)
+		vsi->vf->lldp_tx_ena = true;
+
+	return err;
+}
+
+int ice_drop_vf_tx_lldp(struct ice_vsi *vsi, bool init)
+{
+	struct ice_rule_query_data rule_added;
+	struct ice_adv_rule_info rinfo = {
+		.priority = 7,
+		.src_vsi = vsi->idx,
+		.sw_act = {
+			.src = vsi->idx,
+			.flag = ICE_FLTR_TX,
+			.fltr_act = ICE_DROP_PACKET,
+			.vsi_handle = vsi->idx,
+		},
+		.flags_info.act_valid = true,
+	};
+	struct ice_adv_lkup_elem list[3];
+	struct ice_pf *pf = vsi->back;
+	int err;
+
+	if (!init && !vsi->vf->lldp_tx_ena)
+		return 0;
+
+	memset(list, 0, sizeof(list));
+	ice_rule_add_direction_metadata(&list[0]);
+	ice_rule_add_src_vsi_metadata(&list[1]);
+	list[2].type = ICE_ETYPE_OL;
+	list[2].h_u.ethertype.ethtype_id = htons(ETH_P_LLDP);
+	list[2].m_u.ethertype.ethtype_id = htons(0xFFFF);
+
+	err = ice_add_adv_rule(&pf->hw, list, ARRAY_SIZE(list), &rinfo,
+			       &rule_added);
+	if (err) {
+		dev_err(&pf->pdev->dev,
+			"Failed to add an LLDP rule to VSI 0x%X: %d\n",
+			vsi->idx, err);
+	} else {
+		vsi->vf->lldp_recipe_id = rule_added.rid;
+		vsi->vf->lldp_rule_id = rule_added.rule_id;
+		vsi->vf->lldp_tx_ena = false;
+	}
+
+	return err;
+}
+
+static void ice_handle_add_pf_lldp_drop_rule(struct ice_vsi *vsi)
+{
+	struct ice_tc_flower_fltr *fltr;
+	struct ice_pf *pf = vsi->back;
+
+	hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node) {
+		if (!ice_is_fltr_vf_tx_lldp(fltr))
+			continue;
+		ice_pass_vf_tx_lldp(fltr->src_vsi, true);
+		break;
+	}
+}
+
+static void ice_handle_del_pf_lldp_drop_rule(struct ice_pf *pf)
+{
+	int i;
+
+	/* Make the VF LLDP fwd to uplink rule dormant */
+	ice_for_each_vsi(pf, i) {
+		struct ice_vsi *vf_vsi = pf->vsi[i];
+
+		if (vf_vsi && vf_vsi->type == ICE_VSI_VF)
+			ice_drop_vf_tx_lldp(vf_vsi, false);
+	}
+}
+
 static int
 ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 {
-	struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers;
 	struct ice_adv_rule_info rule_info = { 0 };
 	struct ice_rule_query_data rule_added;
 	struct ice_hw *hw = &vsi->back->hw;
@@ -785,7 +927,10 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		return -EOPNOTSUPP;
 	}
 
-	lkups_cnt = ice_tc_count_lkups(flags, headers, fltr);
+	if (ice_is_fltr_vf_tx_lldp(fltr))
+		return ice_pass_vf_tx_lldp(vsi, false);
+
+	lkups_cnt = ice_tc_count_lkups(flags, fltr);
 	list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC);
 	if (!list)
 		return -ENOMEM;
@@ -814,6 +959,11 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		rule_info.sw_act.src = hw->pf_id;
 		rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE;
 	} else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+		   !fltr->dest_vsi && vsi == vsi->back->eswitch.uplink_vsi) {
+		/* PF to Uplink */
+		rule_info.sw_act.flag |= ICE_FLTR_TX;
+		rule_info.sw_act.src = vsi->idx;
+	} else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
 		   fltr->dest_vsi == vsi->back->eswitch.uplink_vsi) {
 		/* VF to Uplink */
 		rule_info.sw_act.flag |= ICE_FLTR_TX;
@@ -846,11 +996,17 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because it already exist");
 		ret = -EINVAL;
 		goto exit;
+	} else if (ret == -ENOSPC) {
+		NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter: insufficient space available.");
+		goto exit;
 	} else if (ret) {
 		NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter due to error");
 		goto exit;
 	}
 
+	if (ice_is_fltr_pf_tx_lldp(fltr))
+		ice_handle_add_pf_lldp_drop_rule(vsi);
+
 	/* store the output params, which are needed later for removing
 	 * advanced switch filter
 	 */
@@ -985,7 +1141,6 @@ static int
 ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 			   struct ice_tc_flower_fltr *tc_fltr)
 {
-	struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers;
 	struct ice_adv_rule_info rule_info = {0};
 	struct ice_rule_query_data rule_added;
 	struct ice_adv_lkup_elem *list;
@@ -1021,7 +1176,7 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 			return PTR_ERR(dest_vsi);
 	}
 
-	lkups_cnt = ice_tc_count_lkups(flags, headers, tc_fltr);
+	lkups_cnt = ice_tc_count_lkups(flags, tc_fltr);
 	list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC);
 	if (!list)
 		return -ENOMEM;
@@ -1056,8 +1211,13 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 			tc_fltr->action.fwd.q.hw_queue, lkups_cnt);
 		break;
 	case ICE_DROP_PACKET:
-		rule_info.sw_act.flag |= ICE_FLTR_RX;
-		rule_info.sw_act.src = hw->pf_id;
+		if (tc_fltr->direction == ICE_ESWITCH_FLTR_EGRESS) {
+			rule_info.sw_act.flag |= ICE_FLTR_TX;
+			rule_info.sw_act.src = vsi->idx;
+		} else {
+			rule_info.sw_act.flag |= ICE_FLTR_RX;
+			rule_info.sw_act.src = hw->pf_id;
+		}
 		rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI;
 		break;
 	default:
@@ -1071,6 +1231,10 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 				   "Unable to add filter because it already exist");
 		ret = -EINVAL;
 		goto exit;
+	} else if (ret == -ENOSPC) {
+		NL_SET_ERR_MSG_MOD(tc_fltr->extack,
+				   "Unable to add filter: insufficient space available.");
+		goto exit;
 	} else if (ret) {
 		NL_SET_ERR_MSG_MOD(tc_fltr->extack,
 				   "Unable to add filter due to error");
@@ -1463,11 +1627,16 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule,
  * @filter_dev: Pointer to device on which filter is being added
  * @f: Pointer to struct flow_cls_offload
  * @fltr: Pointer to filter structure
+ * @ingress: if the rule is added to an ingress block
+ *
+ * Return: 0 if the flower was parsed successfully, -EINVAL if the flower
+ *	   cannot be parsed, -EOPNOTSUPP if such filter cannot be configured
+ *	   for the given VSI.
  */
 static int
 ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 		     struct flow_cls_offload *f,
-		     struct ice_tc_flower_fltr *fltr)
+		     struct ice_tc_flower_fltr *fltr, bool ingress)
 {
 	struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers;
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
@@ -1551,6 +1720,20 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 			fltr->flags |= ICE_TC_FLWR_FIELD_ETH_TYPE_ID;
 		}
 
+		if (!ingress) {
+			bool switchdev =
+				ice_is_eswitch_mode_switchdev(vsi->back);
+
+			if (switchdev != (n_proto_key == ETH_P_LLDP)) {
+				NL_SET_ERR_MSG_FMT_MOD(fltr->extack,
+						       "%sLLDP filtering is not supported on egress in %s mode",
+						       switchdev ? "Non-" : "",
+						       switchdev ? "switchdev" :
+								   "legacy");
+				return -EOPNOTSUPP;
+			}
+		}
+
 		headers->l2_key.n_proto = cpu_to_be16(n_proto_key);
 		headers->l2_mask.n_proto = cpu_to_be16(n_proto_mask);
 		headers->l3_key.ip_proto = match.key->ip_proto;
@@ -1726,6 +1909,14 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 			return -EINVAL;
 		}
 	}
+
+	/* Ingress filter on representor results in an egress filter in HW
+	 * and vice versa
+	 */
+	ingress = ice_is_port_repr_netdev(filter_dev) ? !ingress : ingress;
+	fltr->direction = ingress ? ICE_ESWITCH_FLTR_INGRESS :
+				    ICE_ESWITCH_FLTR_EGRESS;
+
 	return 0;
 }
 
@@ -1939,6 +2130,12 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 	struct ice_pf *pf = vsi->back;
 	int err;
 
+	if (ice_is_fltr_pf_tx_lldp(fltr))
+		ice_handle_del_pf_lldp_drop_rule(pf);
+
+	if (ice_is_fltr_vf_tx_lldp(fltr))
+		return ice_drop_vf_tx_lldp(vsi, false);
+
 	rule_rem.rid = fltr->rid;
 	rule_rem.rule_id = fltr->rule_id;
 	rule_rem.vsi_handle = fltr->dest_vsi_handle;
@@ -1975,14 +2172,18 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
  * @vsi: Pointer to VSI
  * @f: Pointer to flower offload structure
  * @__fltr: Pointer to struct ice_tc_flower_fltr
+ * @ingress: if the rule is added to an ingress block
  *
  * This function parses TC-flower input fields, parses action,
  * and adds a filter.
+ *
+ * Return: 0 if the filter was successfully added,
+ *	   negative error code otherwise.
  */
 static int
 ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi,
 		struct flow_cls_offload *f,
-		struct ice_tc_flower_fltr **__fltr)
+		struct ice_tc_flower_fltr **__fltr, bool ingress)
 {
 	struct ice_tc_flower_fltr *fltr;
 	int err;
@@ -1999,7 +2200,7 @@ ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi,
 	fltr->src_vsi = vsi;
 	INIT_HLIST_NODE(&fltr->tc_flower_node);
 
-	err = ice_parse_cls_flower(netdev, vsi, f, fltr);
+	err = ice_parse_cls_flower(netdev, vsi, f, fltr, ingress);
 	if (err < 0)
 		goto err;
 
@@ -2042,10 +2243,13 @@ ice_find_tc_flower_fltr(struct ice_pf *pf, unsigned long cookie)
  * @netdev: Pointer to filter device
  * @vsi: Pointer to VSI
  * @cls_flower: Pointer to flower offload structure
+ * @ingress: if the rule is added to an ingress block
+ *
+ * Return: 0 if the flower was successfully added,
+ *	   negative error code otherwise.
  */
-int
-ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
-		   struct flow_cls_offload *cls_flower)
+int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
+		       struct flow_cls_offload *cls_flower, bool ingress)
 {
 	struct netlink_ext_ack *extack = cls_flower->common.extack;
 	struct net_device *vsi_netdev = vsi->netdev;
@@ -2080,7 +2284,7 @@ ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
 	}
 
 	/* prep and add TC-flower filter in HW */
-	err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr);
+	err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr, ingress);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
index d84f153517ec..8a3ab2f22af9 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
@@ -211,13 +211,14 @@ static inline int ice_chnl_dmac_fltr_cnt(struct ice_pf *pf)
 }
 
 struct ice_vsi *ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue);
-int
-ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
-		   struct flow_cls_offload *cls_flower);
-int
-ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower);
+int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
+		       struct flow_cls_offload *cls_flower, bool ingress);
+int ice_del_cls_flower(struct ice_vsi *vsi,
+		       struct flow_cls_offload *cls_flower);
 void ice_replay_tc_fltrs(struct ice_pf *pf);
 bool ice_is_tunnel_supported(struct net_device *dev);
+int ice_drop_vf_tx_lldp(struct ice_vsi *vsi, bool init);
+int ice_pass_vf_tx_lldp(struct ice_vsi *vsi, bool deinit);
 
 static inline bool ice_is_forward_action(enum ice_sw_fwd_act_type fltr_act)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 1e4f6f6ee449..0e5107fe62ad 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -2440,19 +2440,20 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 
 	/* allow CONTROL frames egress from main VSI if FW LLDP disabled */
 	eth = (struct ethhdr *)skb_mac_header(skb);
-	if (unlikely((skb->priority == TC_PRIO_CONTROL ||
-		      eth->h_proto == htons(ETH_P_LLDP)) &&
-		     vsi->type == ICE_VSI_PF &&
-		     vsi->port_info->qos_cfg.is_sw_lldp))
-		offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
-					ICE_TX_CTX_DESC_SWTCH_UPLINK <<
-					ICE_TXD_CTX_QW1_CMD_S);
 
-	ice_tstamp(tx_ring, skb, first, &offload);
 	if ((ice_is_switchdev_running(vsi->back) ||
 	     ice_lag_is_switchdev_running(vsi->back)) &&
 	    vsi->type != ICE_VSI_SF)
 		ice_eswitch_set_target_vsi(skb, &offload);
+	else if (unlikely((skb->priority == TC_PRIO_CONTROL ||
+			   eth->h_proto == htons(ETH_P_LLDP)) &&
+			   vsi->type == ICE_VSI_PF &&
+			   vsi->port_info->qos_cfg.is_sw_lldp))
+		offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
+					ICE_TX_CTX_DESC_SWTCH_UPLINK <<
+					ICE_TXD_CTX_QW1_CMD_S);
+
+	ice_tstamp(tx_ring, skb, first, &offload);
 
 	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
 		struct ice_tx_ctx_desc *cdesc;
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 0aab21113cc4..3d68f465952d 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -19,6 +19,7 @@
 #include "ice_vlan_mode.h"
 #include "ice_fwlog.h"
 #include <linux/wait.h>
+#include <net/dscp.h>
 
 static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc)
 {
@@ -695,7 +696,6 @@ struct ice_dcb_app_priority_table {
 
 #define ICE_MAX_USER_PRIORITY	8
 #define ICE_DCBX_MAX_APPS	64
-#define ICE_DSCP_NUM_VAL	64
 #define ICE_LLDPDU_SIZE		1500
 #define ICE_TLV_STATUS_OPER	0x1
 #define ICE_TLV_STATUS_SYNC	0x2
@@ -718,9 +718,9 @@ struct ice_dcbx_cfg {
 	u8 pfc_mode;
 	struct ice_dcb_app_priority_table app[ICE_DCBX_MAX_APPS];
 	/* when DSCP mapping defined by user set its bit to 1 */
-	DECLARE_BITMAP(dscp_mapped, ICE_DSCP_NUM_VAL);
+	DECLARE_BITMAP(dscp_mapped, DSCP_MAX);
 	/* array holding DSCP -> UP/TC values for DSCP L3 QoS mode */
-	u8 dscp_map[ICE_DSCP_NUM_VAL];
+	u8 dscp_map[DSCP_MAX];
 	u8 dcbx_mode;
 #define ICE_DCBX_MODE_CEE	0x1
 #define ICE_DCBX_MODE_IEEE	0x2
@@ -970,6 +970,7 @@ struct ice_hw {
 	u8 intrl_gran;
 
 	struct ice_ptp_hw ptp;
+	s8 lane_num;
 
 	/* Active package version (currently active) */
 	struct ice_pkg_ver active_pkg_ver;
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index 815ad0bfe832..48cd533e93b7 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -226,6 +226,7 @@ static void ice_vf_clear_counters(struct ice_vf *vf)
 		vsi->num_vlan = 0;
 
 	vf->num_mac = 0;
+	vf->num_mac_lldp = 0;
 	memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events));
 	memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events));
 }
@@ -1401,3 +1402,28 @@ struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi)
 	rcu_read_unlock();
 	return ctrl_vsi;
 }
+
+/**
+ * ice_vf_update_mac_lldp_num - update the VF's number of LLDP addresses
+ * @vf: a VF to add the address to
+ * @vsi: the corresponding VSI
+ * @incr: is the rule added or removed
+ */
+void ice_vf_update_mac_lldp_num(struct ice_vf *vf, struct ice_vsi *vsi,
+				bool incr)
+{
+	bool lldp_by_fw = test_bit(ICE_FLAG_FW_LLDP_AGENT, vsi->back->flags);
+	bool was_ena = ice_vf_is_lldp_ena(vf) && !lldp_by_fw;
+	bool is_ena;
+
+	if (WARN_ON(!vsi)) {
+		vf->num_mac_lldp = 0;
+		return;
+	}
+
+	vf->num_mac_lldp += incr ? 1 : -1;
+	is_ena = ice_vf_is_lldp_ena(vf) && !lldp_by_fw;
+
+	if (was_ena != is_ena)
+		ice_vsi_cfg_sw_lldp(vsi, false, is_ena);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
index 799b2c1f1184..482f4285fd35 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
@@ -124,6 +124,7 @@ struct ice_vf {
 	u8 spoofchk:1;
 	u8 link_forced:1;
 	u8 link_up:1;			/* only valid if VF link is forced */
+	u8 lldp_tx_ena:1;
 
 	u32 ptp_caps;
 
@@ -134,6 +135,7 @@ struct ice_vf {
 	unsigned long vf_caps;		/* VF's adv. capabilities */
 	u8 num_req_qs;			/* num of queue pairs requested by VF */
 	u16 num_mac;
+	u16 num_mac_lldp;
 	u16 num_vf_qs;			/* num of queue configured per VF */
 	u8 vlan_strip_ena;		/* Outer and Inner VLAN strip enable */
 #define ICE_INNER_VLAN_STRIP_ENA	BIT(0)
@@ -149,6 +151,9 @@ struct ice_vf {
 	/* devlink port data */
 	struct devlink_port devlink_port;
 
+	u16 lldp_recipe_id;
+	u16 lldp_rule_id;
+
 	u16 num_msix;			/* num of MSI-X configured on this VF */
 	struct ice_vf_qs_bw qs_bw[ICE_MAX_RSS_QS_PER_VF];
 };
@@ -180,6 +185,11 @@ static inline u16 ice_vf_get_port_vlan_tpid(struct ice_vf *vf)
 	return vf->port_vlan_info.tpid;
 }
 
+static inline bool ice_vf_is_lldp_ena(struct ice_vf *vf)
+{
+	return vf->num_mac_lldp && vf->trusted;
+}
+
 /* VF Hash Table access functions
  *
  * These functions provide abstraction for interacting with the VF hash table.
@@ -245,6 +255,8 @@ ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m);
 int ice_reset_vf(struct ice_vf *vf, u32 flags);
 void ice_reset_all_vfs(struct ice_pf *pf);
 struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi);
+void ice_vf_update_mac_lldp_num(struct ice_vf *vf, struct ice_vsi *vsi,
+				bool incr);
 #else /* CONFIG_PCI_IOV */
 static inline struct ice_vf *ice_get_vf_by_id(struct ice_pf *pf, u16 vf_id)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 7c3006eb68dd..eeeb9968e477 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -2266,6 +2266,51 @@ ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr)
 }
 
 /**
+ * ice_is_mc_lldp_eth_addr - check if the given MAC is a multicast LLDP address
+ * @mac: address to check
+ *
+ * Return: true if the address is one of the three possible LLDP multicast
+ *	   addresses, false otherwise.
+ */
+static bool ice_is_mc_lldp_eth_addr(const u8 *mac)
+{
+	const u8 lldp_mac_base[] = {0x01, 0x80, 0xc2, 0x00, 0x00};
+
+	if (memcmp(mac, lldp_mac_base, sizeof(lldp_mac_base)))
+		return false;
+
+	return (mac[5] == 0x0e || mac[5] == 0x03 || mac[5] == 0x00);
+}
+
+/**
+ * ice_vc_can_add_mac - check if the VF is allowed to add a given MAC
+ * @vf: a VF to add the address to
+ * @mac: address to check
+ *
+ * Return: true if the VF is allowed to add such MAC address, false otherwise.
+ */
+static bool ice_vc_can_add_mac(const struct ice_vf *vf, const u8 *mac)
+{
+	struct device *dev = ice_pf_to_dev(vf->pf);
+
+	if (is_unicast_ether_addr(mac) &&
+	    !ice_can_vf_change_mac((struct ice_vf *)vf)) {
+		dev_err(dev,
+			"VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
+		return false;
+	}
+
+	if (!vf->trusted && ice_is_mc_lldp_eth_addr(mac)) {
+		dev_warn(dev,
+			 "An untrusted VF %u is attempting to configure an LLDP multicast address\n",
+			 vf->vf_id);
+		return false;
+	}
+
+	return true;
+}
+
+/**
  * ice_vc_add_mac_addr - attempt to add the MAC address passed in
  * @vf: pointer to the VF info
  * @vsi: pointer to the VF's VSI
@@ -2283,10 +2328,8 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
 	if (ether_addr_equal(mac_addr, vf->dev_lan_addr))
 		return 0;
 
-	if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) {
-		dev_err(dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
+	if (!ice_vc_can_add_mac(vf, mac_addr))
 		return -EPERM;
-	}
 
 	ret = ice_fltr_add_mac(vsi, mac_addr, ICE_FWD_TO_VSI);
 	if (ret == -EEXIST) {
@@ -2301,6 +2344,8 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
 		return ret;
 	} else {
 		vf->num_mac++;
+		if (ice_is_mc_lldp_eth_addr(mac_addr))
+			ice_vf_update_mac_lldp_num(vf, vsi, true);
 	}
 
 	ice_vfhw_mac_add(vf, vc_ether_addr);
@@ -2395,6 +2440,8 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
 	ice_vfhw_mac_del(vf, vc_ether_addr);
 
 	vf->num_mac--;
+	if (ice_is_mc_lldp_eth_addr(mac_addr))
+		ice_vf_update_mac_lldp_num(vf, vsi, false);
 
 	return 0;
 }
@@ -4275,7 +4322,6 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg)
 		}
 
 		ice_vfhw_mac_add(vf, &al->list[i]);
-		vf->num_mac++;
 		break;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index 7752920d7a8e..1cca9b2262e8 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -2097,6 +2097,11 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
 	pf = vf->pf;
 	dev = ice_pf_to_dev(pf);
 	vf_vsi = ice_get_vf_vsi(vf);
+	if (!vf_vsi) {
+		dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id);
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err_exit;
+	}
 
 #define ICE_VF_MAX_FDIR_FILTERS	128
 	if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) ||
diff --git a/drivers/net/ethernet/intel/idpf/Kconfig b/drivers/net/ethernet/intel/idpf/Kconfig
index 1addd663acad..2c359a8551c7 100644
--- a/drivers/net/ethernet/intel/idpf/Kconfig
+++ b/drivers/net/ethernet/intel/idpf/Kconfig
@@ -4,6 +4,7 @@
 config IDPF
 	tristate "Intel(R) Infrastructure Data Path Function Support"
 	depends on PCI_MSI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select DIMLIB
 	select LIBETH
 	help
diff --git a/drivers/net/ethernet/intel/idpf/Makefile b/drivers/net/ethernet/intel/idpf/Makefile
index 2ce01a0b5898..83ac5e296382 100644
--- a/drivers/net/ethernet/intel/idpf/Makefile
+++ b/drivers/net/ethernet/intel/idpf/Makefile
@@ -17,3 +17,6 @@ idpf-y := \
 	idpf_vf_dev.o
 
 idpf-$(CONFIG_IDPF_SINGLEQ)	+= idpf_singleq_txrx.o
+
+idpf-$(CONFIG_PTP_1588_CLOCK)	+= idpf_ptp.o
+idpf-$(CONFIG_PTP_1588_CLOCK)	+= idpf_virtchnl_ptp.o
diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index 66544faab710..1e812c3f62f9 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -143,6 +143,7 @@ enum idpf_vport_state {
  * @vport_id: Vport identifier
  * @link_speed_mbps: Link speed in mbps
  * @vport_idx: Relative vport index
+ * @max_tx_hdr_size: Max header length hardware can support
  * @state: See enum idpf_vport_state
  * @netstats: Packet and byte stats
  * @stats_lock: Lock to protect stats update
@@ -153,6 +154,7 @@ struct idpf_netdev_priv {
 	u32 vport_id;
 	u32 link_speed_mbps;
 	u16 vport_idx;
+	u16 max_tx_hdr_size;
 	enum idpf_vport_state state;
 	struct rtnl_link_stats64 netstats;
 	spinlock_t stats_lock;
@@ -189,6 +191,7 @@ struct idpf_vport_max_q {
  * @mb_intr_reg_init: Mailbox interrupt register initialization
  * @reset_reg_init: Reset register initialization
  * @trigger_reset: Trigger a reset to occur
+ * @ptp_reg_init: PTP register initialization
  */
 struct idpf_reg_ops {
 	void (*ctlq_reg_init)(struct idpf_ctlq_create_info *cq);
@@ -197,6 +200,7 @@ struct idpf_reg_ops {
 	void (*reset_reg_init)(struct idpf_adapter *adapter);
 	void (*trigger_reset)(struct idpf_adapter *adapter,
 			      enum idpf_flags trig_cause);
+	void (*ptp_reg_init)(const struct idpf_adapter *adapter);
 };
 
 /**
@@ -290,6 +294,9 @@ struct idpf_port_stats {
  * @port_stats: per port csum, header split, and other offload stats
  * @link_up: True if link is up
  * @sw_marker_wq: workqueue for marker packets
+ * @tx_tstamp_caps: Capabilities negotiated for Tx timestamping
+ * @tstamp_config: The Tx tstamp config
+ * @tstamp_task: Tx timestamping task
  */
 struct idpf_vport {
 	u16 num_txq;
@@ -334,6 +341,10 @@ struct idpf_vport {
 	bool link_up;
 
 	wait_queue_head_t sw_marker_wq;
+
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct kernel_hwtstamp_config tstamp_config;
+	struct work_struct tstamp_task;
 };
 
 /**
@@ -478,6 +489,13 @@ struct idpf_vport_config {
 
 struct idpf_vc_xn_manager;
 
+#define idpf_for_each_vport(adapter, iter) \
+	for (struct idpf_vport **__##iter = &(adapter)->vports[0], \
+	     *iter = (adapter)->max_vports ? *__##iter : NULL; \
+	     iter; \
+	     iter = (++__##iter) < &(adapter)->vports[(adapter)->max_vports] ? \
+	     *__##iter : NULL)
+
 /**
  * struct idpf_adapter - Device data struct generated on probe
  * @pdev: PCI device struct given on probe
@@ -530,6 +548,7 @@ struct idpf_vc_xn_manager;
  * @vector_lock: Lock to protect vector distribution
  * @queue_lock: Lock to protect queue distribution
  * @vc_buf_lock: Lock to protect virtchnl buffer
+ * @ptp: Storage for PTP-related data
  */
 struct idpf_adapter {
 	struct pci_dev *pdev;
@@ -587,6 +606,8 @@ struct idpf_adapter {
 	struct mutex vector_lock;
 	struct mutex queue_lock;
 	struct mutex vc_buf_lock;
+
+	struct idpf_ptp *ptp;
 };
 
 /**
@@ -629,13 +650,13 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
 	VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V4	|\
 	VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V6)
 
-#define IDPF_CAP_RX_CSUM_L4V4 (\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_TCP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_UDP)
+#define IDPF_CAP_TX_CSUM_L4V4 (\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_TCP	|\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_UDP)
 
-#define IDPF_CAP_RX_CSUM_L4V6 (\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
+#define IDPF_CAP_TX_CSUM_L4V6 (\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_TCP	|\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_UDP)
 
 #define IDPF_CAP_RX_CSUM (\
 	VIRTCHNL2_CAP_RX_CSUM_L3_IPV4		|\
@@ -644,11 +665,9 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
 	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP	|\
 	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
 
-#define IDPF_CAP_SCTP_CSUM (\
+#define IDPF_CAP_TX_SCTP_CSUM (\
 	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_SCTP	|\
-	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_SCTP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_SCTP)
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP)
 
 #define IDPF_CAP_TUNNEL_TX_CSUM (\
 	VIRTCHNL2_CAP_TX_CSUM_L3_SINGLE_TUNNEL	|\
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
index e8e046ef2f0d..9642494a67d8 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
@@ -123,9 +123,12 @@ struct idpf_ctlq_info {
 /**
  * enum idpf_mbx_opc - PF/VF mailbox commands
  * @idpf_mbq_opc_send_msg_to_cp: used by PF or VF to send a message to its CP
+ * @idpf_mbq_opc_send_msg_to_peer_drv: used by PF or VF to send a message to
+ *				       any peer driver
  */
 enum idpf_mbx_opc {
 	idpf_mbq_opc_send_msg_to_cp		= 0x0801,
+	idpf_mbq_opc_send_msg_to_peer_drv	= 0x0804,
 };
 
 /* API supported for control queue management */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c
index 41e4bd49402a..3fae81f1f988 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c
@@ -4,6 +4,7 @@
 #include "idpf.h"
 #include "idpf_lan_pf_regs.h"
 #include "idpf_virtchnl.h"
+#include "idpf_ptp.h"
 
 #define IDPF_PF_ITR_IDX_SPACING		0x4
 
@@ -149,6 +150,18 @@ static void idpf_trigger_reset(struct idpf_adapter *adapter,
 }
 
 /**
+ * idpf_ptp_reg_init - Initialize required registers
+ * @adapter: Driver specific private structure
+ *
+ * Set the bits required for enabling shtime and cmd execution
+ */
+static void idpf_ptp_reg_init(const struct idpf_adapter *adapter)
+{
+	adapter->ptp->cmd.shtime_enable_mask = PF_GLTSYN_CMD_SYNC_SHTIME_EN_M;
+	adapter->ptp->cmd.exec_cmd_mask = PF_GLTSYN_CMD_SYNC_EXEC_CMD_M;
+}
+
+/**
  * idpf_reg_ops_init - Initialize register API function pointers
  * @adapter: Driver specific private structure
  */
@@ -159,6 +172,7 @@ static void idpf_reg_ops_init(struct idpf_adapter *adapter)
 	adapter->dev_ops.reg_ops.mb_intr_reg_init = idpf_mb_intr_reg_init;
 	adapter->dev_ops.reg_ops.reset_reg_init = idpf_reset_reg_init;
 	adapter->dev_ops.reg_ops.trigger_reset = idpf_trigger_reset;
+	adapter->dev_ops.reg_ops.ptp_reg_init = idpf_ptp_reg_init;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
index 59b1a1a09996..9bdb309b668e 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2023 Intel Corporation */
 
 #include "idpf.h"
+#include "idpf_ptp.h"
 
 /**
  * idpf_get_rxnfc - command to get RX flow classification rules
@@ -1312,6 +1313,71 @@ static int idpf_get_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
+/**
+ * idpf_get_timestamp_filters - Get the supported timestamping mode
+ * @vport: Virtual port structure
+ * @info: ethtool timestamping info structure
+ *
+ * Get the Tx/Rx timestamp filters.
+ */
+static void idpf_get_timestamp_filters(const struct idpf_vport *vport,
+				       struct kernel_ethtool_ts_info *info)
+{
+	info->so_timestamping = SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	info->tx_types = BIT(HWTSTAMP_TX_OFF);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL);
+
+	if (!vport->tx_tstamp_caps ||
+	    vport->adapter->ptp->tx_tstamp_access == IDPF_PTP_NONE)
+		return;
+
+	info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
+				 SOF_TIMESTAMPING_TX_HARDWARE;
+
+	info->tx_types |= BIT(HWTSTAMP_TX_ON);
+}
+
+/**
+ * idpf_get_ts_info - Get device PHC association
+ * @netdev: network interface device structure
+ * @info: ethtool timestamping info structure
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_get_ts_info(struct net_device *netdev,
+			    struct kernel_ethtool_ts_info *info)
+{
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport *vport;
+	int err = 0;
+
+	if (!mutex_trylock(&np->adapter->vport_ctrl_lock))
+		return -EBUSY;
+
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->adapter->ptp) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	if (idpf_is_cap_ena(vport->adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PTP) &&
+	    vport->adapter->ptp->clock) {
+		info->phc_index = ptp_clock_index(vport->adapter->ptp->clock);
+		idpf_get_timestamp_filters(vport, info);
+	} else {
+		pci_dbg(vport->adapter->pdev, "PTP clock not detected\n");
+		err = ethtool_op_get_ts_info(netdev, info);
+	}
+
+unlock:
+	mutex_unlock(&np->adapter->vport_ctrl_lock);
+
+	return err;
+}
+
 static const struct ethtool_ops idpf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
@@ -1336,6 +1402,7 @@ static const struct ethtool_ops idpf_ethtool_ops = {
 	.get_ringparam		= idpf_get_ringparam,
 	.set_ringparam		= idpf_set_ringparam,
 	.get_link_ksettings	= idpf_get_link_ksettings,
+	.get_ts_info		= idpf_get_ts_info,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
index 24edb8a6ec2e..cc9aa2b6a14a 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
@@ -53,6 +53,10 @@
 #define PF_FW_ATQH_ATQH_M		GENMASK(9, 0)
 #define PF_FW_ATQT			(PF_FW_BASE + 0x24)
 
+/* Timesync registers */
+#define PF_GLTSYN_CMD_SYNC_EXEC_CMD_M	GENMASK(1, 0)
+#define PF_GLTSYN_CMD_SYNC_SHTIME_EN_M	BIT(2)
+
 /* Interrupts */
 #define PF_GLINT_BASE			0x08900000
 #define PF_GLINT_DYN_CTL(_INT)		(PF_GLINT_BASE + ((_INT) * 0x1000))
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
index 8c7f8ef8f1a1..7492d1713243 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
@@ -282,7 +282,18 @@ struct idpf_flex_tx_tso_ctx_qw {
 	u8 flex;
 };
 
-struct idpf_flex_tx_ctx_desc {
+union idpf_flex_tx_ctx_desc {
+	/* DTYPE = IDPF_TX_DESC_DTYPE_CTX (0x01) */
+	struct {
+		__le64 qw0;
+#define IDPF_TX_CTX_L2TAG2_M	GENMASK_ULL(47, 32)
+		__le64 qw1;
+#define IDPF_TX_CTX_DTYPE_M	GENMASK_ULL(3, 0)
+#define IDPF_TX_CTX_CMD_M	GENMASK_ULL(15, 4)
+#define IDPF_TX_CTX_TSYN_REG_M	GENMASK_ULL(47, 30)
+#define IDPF_TX_CTX_MSS_M	GENMASK_ULL(50, 63)
+	} tsyn;
+
 	/* DTYPE = IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX (0x05) */
 	struct {
 		struct idpf_flex_tx_tso_ctx_qw qw0;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index aa755dedb41d..bab12ecb2df5 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -3,6 +3,7 @@
 
 #include "idpf.h"
 #include "idpf_virtchnl.h"
+#include "idpf_ptp.h"
 
 static const struct net_device_ops idpf_netdev_ops;
 
@@ -144,22 +145,6 @@ static int idpf_mb_intr_req_irq(struct idpf_adapter *adapter)
 }
 
 /**
- * idpf_set_mb_vec_id - Set vector index for mailbox
- * @adapter: adapter structure to access the vector chunks
- *
- * The first vector id in the requested vector chunks from the CP is for
- * the mailbox
- */
-static void idpf_set_mb_vec_id(struct idpf_adapter *adapter)
-{
-	if (adapter->req_vec_chunks)
-		adapter->mb_vector.v_idx =
-			le16_to_cpu(adapter->caps.mailbox_vector_id);
-	else
-		adapter->mb_vector.v_idx = 0;
-}
-
-/**
  * idpf_mb_intr_init - Initialize the mailbox interrupt
  * @adapter: adapter structure to store the mailbox vector
  */
@@ -349,7 +334,7 @@ int idpf_intr_req(struct idpf_adapter *adapter)
 		goto free_irq;
 	}
 
-	idpf_set_mb_vec_id(adapter);
+	adapter->mb_vector.v_idx = le16_to_cpu(adapter->caps.mailbox_vector_id);
 
 	vecids = kcalloc(total_vecs, sizeof(u16), GFP_KERNEL);
 	if (!vecids) {
@@ -703,8 +688,10 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 {
 	struct idpf_adapter *adapter = vport->adapter;
 	struct idpf_vport_config *vport_config;
+	netdev_features_t other_offloads = 0;
+	netdev_features_t csum_offloads = 0;
+	netdev_features_t tso_offloads = 0;
 	netdev_features_t dflt_features;
-	netdev_features_t offloads = 0;
 	struct idpf_netdev_priv *np;
 	struct net_device *netdev;
 	u16 idx = vport->idx;
@@ -721,6 +708,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 		np->vport = vport;
 		np->vport_idx = vport->idx;
 		np->vport_id = vport->vport_id;
+		np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter);
 		vport->netdev = netdev;
 
 		return idpf_init_mac_addr(vport, netdev);
@@ -738,6 +726,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 	np->adapter = adapter;
 	np->vport_idx = vport->idx;
 	np->vport_id = vport->vport_id;
+	np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter);
 
 	spin_lock_init(&np->stats_lock);
 
@@ -766,53 +755,32 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 
 	if (idpf_is_cap_ena_all(adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
 		dflt_features |= NETIF_F_RXHASH;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V4))
-		dflt_features |= NETIF_F_IP_CSUM;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V6))
-		dflt_features |= NETIF_F_IPV6_CSUM;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V4))
+		csum_offloads |= NETIF_F_IP_CSUM;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V6))
+		csum_offloads |= NETIF_F_IPV6_CSUM;
 	if (idpf_is_cap_ena(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM))
-		dflt_features |= NETIF_F_RXCSUM;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_SCTP_CSUM))
-		dflt_features |= NETIF_F_SCTP_CRC;
+		csum_offloads |= NETIF_F_RXCSUM;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_SCTP_CSUM))
+		csum_offloads |= NETIF_F_SCTP_CRC;
 
 	if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV4_TCP))
-		dflt_features |= NETIF_F_TSO;
+		tso_offloads |= NETIF_F_TSO;
 	if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV6_TCP))
-		dflt_features |= NETIF_F_TSO6;
+		tso_offloads |= NETIF_F_TSO6;
 	if (idpf_is_cap_ena_all(adapter, IDPF_SEG_CAPS,
 				VIRTCHNL2_CAP_SEG_IPV4_UDP |
 				VIRTCHNL2_CAP_SEG_IPV6_UDP))
-		dflt_features |= NETIF_F_GSO_UDP_L4;
+		tso_offloads |= NETIF_F_GSO_UDP_L4;
 	if (idpf_is_cap_ena_all(adapter, IDPF_RSC_CAPS, IDPF_CAP_RSC))
-		offloads |= NETIF_F_GRO_HW;
-	/* advertise to stack only if offloads for encapsulated packets is
-	 * supported
-	 */
-	if (idpf_is_cap_ena(vport->adapter, IDPF_SEG_CAPS,
-			    VIRTCHNL2_CAP_SEG_TX_SINGLE_TUNNEL)) {
-		offloads |= NETIF_F_GSO_UDP_TUNNEL	|
-			    NETIF_F_GSO_GRE		|
-			    NETIF_F_GSO_GRE_CSUM	|
-			    NETIF_F_GSO_PARTIAL		|
-			    NETIF_F_GSO_UDP_TUNNEL_CSUM	|
-			    NETIF_F_GSO_IPXIP4		|
-			    NETIF_F_GSO_IPXIP6		|
-			    0;
-
-		if (!idpf_is_cap_ena_all(vport->adapter, IDPF_CSUM_CAPS,
-					 IDPF_CAP_TUNNEL_TX_CSUM))
-			netdev->gso_partial_features |=
-				NETIF_F_GSO_UDP_TUNNEL_CSUM;
-
-		netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
-		offloads |= NETIF_F_TSO_MANGLEID;
-	}
+		other_offloads |= NETIF_F_GRO_HW;
 	if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_LOOPBACK))
-		offloads |= NETIF_F_LOOPBACK;
+		other_offloads |= NETIF_F_LOOPBACK;
 
-	netdev->features |= dflt_features;
-	netdev->hw_features |= dflt_features | offloads;
-	netdev->hw_enc_features |= dflt_features | offloads;
+	netdev->features |= dflt_features | csum_offloads | tso_offloads;
+	netdev->hw_features |=  netdev->features | other_offloads;
+	netdev->vlan_features |= netdev->features | other_offloads;
+	netdev->hw_enc_features |= dflt_features | other_offloads;
 	idpf_set_ethtool_ops(netdev);
 	netif_set_affinity_auto(netdev);
 	SET_NETDEV_DEV(netdev, &adapter->pdev->dev);
@@ -1132,11 +1100,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 
 	num_max_q = max(max_q->max_txq, max_q->max_rxq);
 	vport->q_vector_idxs = kcalloc(num_max_q, sizeof(u16), GFP_KERNEL);
-	if (!vport->q_vector_idxs) {
-		kfree(vport);
+	if (!vport->q_vector_idxs)
+		goto free_vport;
 
-		return NULL;
-	}
 	idpf_vport_init(vport, max_q);
 
 	/* This alloc is done separate from the LUT because it's not strictly
@@ -1146,11 +1112,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	 */
 	rss_data = &adapter->vport_config[idx]->user_config.rss_data;
 	rss_data->rss_key = kzalloc(rss_data->rss_key_size, GFP_KERNEL);
-	if (!rss_data->rss_key) {
-		kfree(vport);
+	if (!rss_data->rss_key)
+		goto free_vector_idxs;
 
-		return NULL;
-	}
 	/* Initialize default rss key */
 	netdev_rss_key_fill((void *)rss_data->rss_key, rss_data->rss_key_size);
 
@@ -1163,6 +1127,13 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	adapter->next_vport = idpf_get_free_slot(adapter);
 
 	return vport;
+
+free_vector_idxs:
+	kfree(vport->q_vector_idxs);
+free_vport:
+	kfree(vport);
+
+	return NULL;
 }
 
 /**
@@ -2219,8 +2190,8 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 					     struct net_device *netdev,
 					     netdev_features_t features)
 {
-	struct idpf_vport *vport = idpf_netdev_to_vport(netdev);
-	struct idpf_adapter *adapter = vport->adapter;
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	u16 max_tx_hdr_size = np->max_tx_hdr_size;
 	size_t len;
 
 	/* No point in doing any of this if neither checksum nor GSO are
@@ -2243,7 +2214,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 		goto unsupported;
 
 	len = skb_network_header_len(skb);
-	if (unlikely(len > idpf_get_max_tx_hdr_size(adapter)))
+	if (unlikely(len > max_tx_hdr_size))
 		goto unsupported;
 
 	if (!skb->encapsulation)
@@ -2256,7 +2227,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 
 	/* IPLEN can support at most 127 dwords */
 	len = skb_inner_network_header_len(skb);
-	if (unlikely(len > idpf_get_max_tx_hdr_size(adapter)))
+	if (unlikely(len > max_tx_hdr_size))
 		goto unsupported;
 
 	/* No need to validate L4LEN as TCP is the only protocol with a
@@ -2358,6 +2329,60 @@ void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem)
 	mem->pa = 0;
 }
 
+static int idpf_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
+{
+	struct idpf_vport *vport;
+	int err;
+
+	idpf_vport_ctrl_lock(netdev);
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->link_up) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EPERM;
+	}
+
+	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport) &&
+	    !idpf_ptp_is_vport_rx_tstamp_ena(vport)) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EOPNOTSUPP;
+	}
+
+	err = idpf_ptp_set_timestamp_mode(vport, config);
+
+	idpf_vport_ctrl_unlock(netdev);
+
+	return err;
+}
+
+static int idpf_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config)
+{
+	struct idpf_vport *vport;
+
+	idpf_vport_ctrl_lock(netdev);
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->link_up) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EPERM;
+	}
+
+	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport) &&
+	    !idpf_ptp_is_vport_rx_tstamp_ena(vport)) {
+		idpf_vport_ctrl_unlock(netdev);
+		return 0;
+	}
+
+	*config = vport->tstamp_config;
+
+	idpf_vport_ctrl_unlock(netdev);
+
+	return 0;
+}
+
 static const struct net_device_ops idpf_netdev_ops = {
 	.ndo_open = idpf_open,
 	.ndo_stop = idpf_stop,
@@ -2370,4 +2395,6 @@ static const struct net_device_ops idpf_netdev_ops = {
 	.ndo_get_stats64 = idpf_get_stats64,
 	.ndo_set_features = idpf_set_features,
 	.ndo_tx_timeout = idpf_tx_timeout,
+	.ndo_hwtstamp_get = idpf_hwtstamp_get,
+	.ndo_hwtstamp_set = idpf_hwtstamp_set,
 };
diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c
index bec4a02c5373..0efd9c0c7a90 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_main.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_main.c
@@ -89,6 +89,7 @@ static void idpf_shutdown(struct pci_dev *pdev)
 {
 	struct idpf_adapter *adapter = pci_get_drvdata(pdev);
 
+	cancel_delayed_work_sync(&adapter->serv_task);
 	cancel_delayed_work_sync(&adapter->vc_event_task);
 	idpf_vc_core_deinit(adapter);
 	idpf_deinit_dflt_mbx(adapter);
@@ -167,6 +168,10 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_free;
 	}
 
+	err = pci_enable_ptm(pdev, NULL);
+	if (err)
+		pci_dbg(pdev, "PCIe PTM is not supported by PCIe bus/controller\n");
+
 	/* set up for high or low dma */
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (err) {
@@ -198,9 +203,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_serv_wq_alloc;
 	}
 
-	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx",
-					  WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
-					  dev_driver_string(dev),
+	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", WQ_UNBOUND | WQ_HIGHPRI,
+					  0, dev_driver_string(dev),
 					  dev_name(dev));
 	if (!adapter->mbx_wq) {
 		dev_err(dev, "Failed to allocate mailbox workqueue\n");
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
new file mode 100644
index 000000000000..4f8725c85332
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
@@ -0,0 +1,873 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation */
+
+#include "idpf.h"
+#include "idpf_ptp.h"
+
+/**
+ * idpf_ptp_get_access - Determine the access type of the PTP features
+ * @adapter: Driver specific private structure
+ * @direct: Capability that indicates the direct access
+ * @mailbox: Capability that indicates the mailbox access
+ *
+ * Return: the type of supported access for the PTP feature.
+ */
+static enum idpf_ptp_access
+idpf_ptp_get_access(const struct idpf_adapter *adapter, u32 direct, u32 mailbox)
+{
+	if (adapter->ptp->caps & direct)
+		return IDPF_PTP_DIRECT;
+	else if (adapter->ptp->caps & mailbox)
+		return IDPF_PTP_MAILBOX;
+	else
+		return IDPF_PTP_NONE;
+}
+
+/**
+ * idpf_ptp_get_features_access - Determine the access type of PTP features
+ * @adapter: Driver specific private structure
+ *
+ * Fulfill the adapter structure with type of the supported PTP features
+ * access.
+ */
+void idpf_ptp_get_features_access(const struct idpf_adapter *adapter)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+	u32 direct, mailbox;
+
+	/* Get the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME;
+	mailbox = VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB;
+	ptp->get_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Set the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME;
+	mailbox = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME;
+	ptp->set_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Adjust the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK;
+	mailbox = VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB;
+	ptp->adj_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Tx timestamping */
+	direct = VIRTCHNL2_CAP_PTP_TX_TSTAMPS;
+	mailbox = VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB;
+	ptp->tx_tstamp_access = idpf_ptp_get_access(adapter,
+						    direct,
+						    mailbox);
+}
+
+/**
+ * idpf_ptp_enable_shtime - Enable shadow time and execute a command
+ * @adapter: Driver specific private structure
+ */
+static void idpf_ptp_enable_shtime(struct idpf_adapter *adapter)
+{
+	u32 shtime_enable, exec_cmd;
+
+	/* Get offsets */
+	shtime_enable = adapter->ptp->cmd.shtime_enable_mask;
+	exec_cmd = adapter->ptp->cmd.exec_cmd_mask;
+
+	/* Set the shtime en and the sync field */
+	writel(shtime_enable, adapter->ptp->dev_clk_regs.cmd_sync);
+	writel(exec_cmd | shtime_enable, adapter->ptp->dev_clk_regs.cmd_sync);
+}
+
+/**
+ * idpf_ptp_read_src_clk_reg_direct - Read directly the main timer value
+ * @adapter: Driver specific private structure
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored when NULL is given.
+ *
+ * Return: the device clock time.
+ */
+static u64 idpf_ptp_read_src_clk_reg_direct(struct idpf_adapter *adapter,
+					    struct ptp_system_timestamp *sts)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+	u32 hi, lo;
+
+	spin_lock(&ptp->read_dev_clk_lock);
+
+	/* Read the system timestamp pre PHC read */
+	ptp_read_system_prets(sts);
+
+	idpf_ptp_enable_shtime(adapter);
+
+	/* Read the system timestamp post PHC read */
+	ptp_read_system_postts(sts);
+
+	lo = readl(ptp->dev_clk_regs.dev_clk_ns_l);
+	hi = readl(ptp->dev_clk_regs.dev_clk_ns_h);
+
+	spin_unlock(&ptp->read_dev_clk_lock);
+
+	return ((u64)hi << 32) | lo;
+}
+
+/**
+ * idpf_ptp_read_src_clk_reg_mailbox - Read the main timer value through mailbox
+ * @adapter: Driver specific private structure
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored when NULL is given.
+ * @src_clk: Returned main timer value in nanoseconds unit
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_read_src_clk_reg_mailbox(struct idpf_adapter *adapter,
+					     struct ptp_system_timestamp *sts,
+					     u64 *src_clk)
+{
+	struct idpf_ptp_dev_timers clk_time;
+	int err;
+
+	/* Read the system timestamp pre PHC read */
+	ptp_read_system_prets(sts);
+
+	err = idpf_ptp_get_dev_clk_time(adapter, &clk_time);
+	if (err)
+		return err;
+
+	/* Read the system timestamp post PHC read */
+	ptp_read_system_postts(sts);
+
+	*src_clk = clk_time.dev_clk_time_ns;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_read_src_clk_reg - Read the main timer value
+ * @adapter: Driver specific private structure
+ * @src_clk: Returned main timer value in nanoseconds unit
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored if NULL is given.
+ *
+ * Return: the device clock time on success, -errno otherwise.
+ */
+static int idpf_ptp_read_src_clk_reg(struct idpf_adapter *adapter, u64 *src_clk,
+				     struct ptp_system_timestamp *sts)
+{
+	switch (adapter->ptp->get_dev_clk_time_access) {
+	case IDPF_PTP_NONE:
+		return -EOPNOTSUPP;
+	case IDPF_PTP_MAILBOX:
+		return idpf_ptp_read_src_clk_reg_mailbox(adapter, sts, src_clk);
+	case IDPF_PTP_DIRECT:
+		*src_clk = idpf_ptp_read_src_clk_reg_direct(adapter, sts);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_gettimex64 - Get the time of the clock
+ * @info: the driver's PTP info structure
+ * @ts: timespec64 structure to hold the current time value
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored if NULL is given.
+ *
+ * Return: the device clock value in ns, after converting it into a timespec
+ * struct on success, -errno otherwise.
+ */
+static int idpf_ptp_gettimex64(struct ptp_clock_info *info,
+			       struct timespec64 *ts,
+			       struct ptp_system_timestamp *sts)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	u64 time_ns;
+	int err;
+
+	err = idpf_ptp_read_src_clk_reg(adapter, &time_ns, sts);
+	if (err)
+		return -EACCES;
+
+	*ts = ns_to_timespec64(time_ns);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_update_phctime_rxq_grp - Update the cached PHC time for a given Rx
+ *				     queue group.
+ * @grp: receive queue group in which Rx timestamp is enabled
+ * @split: Indicates whether the queue model is split or single queue
+ * @systime: Cached system time
+ */
+static void
+idpf_ptp_update_phctime_rxq_grp(const struct idpf_rxq_group *grp, bool split,
+				u64 systime)
+{
+	struct idpf_rx_queue *rxq;
+	u16 i;
+
+	if (!split) {
+		for (i = 0; i < grp->singleq.num_rxq; i++) {
+			rxq = grp->singleq.rxqs[i];
+			if (rxq)
+				WRITE_ONCE(rxq->cached_phc_time, systime);
+		}
+	} else {
+		for (i = 0; i < grp->splitq.num_rxq_sets; i++) {
+			rxq = &grp->splitq.rxq_sets[i]->rxq;
+			if (rxq)
+				WRITE_ONCE(rxq->cached_phc_time, systime);
+		}
+	}
+}
+
+/**
+ * idpf_ptp_update_cached_phctime - Update the cached PHC time values
+ * @adapter: Driver specific private structure
+ *
+ * This function updates the system time values which are cached in the adapter
+ * structure and the Rx queues.
+ *
+ * This function must be called periodically to ensure that the cached value
+ * is never more than 2 seconds old.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_update_cached_phctime(struct idpf_adapter *adapter)
+{
+	u64 systime;
+	int err;
+
+	err = idpf_ptp_read_src_clk_reg(adapter, &systime, NULL);
+	if (err)
+		return -EACCES;
+
+	/* Update the cached PHC time stored in the adapter structure.
+	 * These values are used to extend Tx timestamp values to 64 bit
+	 * expected by the stack.
+	 */
+	WRITE_ONCE(adapter->ptp->cached_phc_time, systime);
+	WRITE_ONCE(adapter->ptp->cached_phc_jiffies, jiffies);
+
+	idpf_for_each_vport(adapter, vport) {
+		bool split;
+
+		if (!vport || !vport->rxq_grps)
+			continue;
+
+		split = idpf_is_queue_model_split(vport->rxq_model);
+
+		for (u16 i = 0; i < vport->num_rxq_grp; i++) {
+			struct idpf_rxq_group *grp = &vport->rxq_grps[i];
+
+			idpf_ptp_update_phctime_rxq_grp(grp, split, systime);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_settime64 - Set the time of the clock
+ * @info: the driver's PTP info structure
+ * @ts: timespec64 structure that holds the new time value
+ *
+ * Set the device clock to the user input value. The conversion from timespec
+ * to ns happens in the write function.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_settime64(struct ptp_clock_info *info,
+			      const struct timespec64 *ts)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	int err;
+	u64 ns;
+
+	access = adapter->ptp->set_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	ns = timespec64_to_ns(ts);
+
+	err = idpf_ptp_set_dev_clk_time(adapter, ns);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to set the time, err: %pe\n",
+			ERR_PTR(err));
+		return err;
+	}
+
+	err = idpf_ptp_update_cached_phctime(adapter);
+	if (err)
+		pci_warn(adapter->pdev,
+			 "Unable to immediately update cached PHC time\n");
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adjtime_nonatomic - Do a non-atomic clock adjustment
+ * @info: the driver's PTP info structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta)
+{
+	struct timespec64 now, then;
+	int err;
+
+	err = idpf_ptp_gettimex64(info, &now, NULL);
+	if (err)
+		return err;
+
+	then = ns_to_timespec64(delta);
+	now = timespec64_add(now, then);
+
+	return idpf_ptp_settime64(info, &now);
+}
+
+/**
+ * idpf_ptp_adjtime - Adjust the time of the clock by the indicated delta
+ * @info: the driver's PTP info structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjtime(struct ptp_clock_info *info, s64 delta)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	int err;
+
+	access = adapter->ptp->adj_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	/* Hardware only supports atomic adjustments using signed 32-bit
+	 * integers. For any adjustment outside this range, perform
+	 * a non-atomic get->adjust->set flow.
+	 */
+	if (delta > S32_MAX || delta < S32_MIN)
+		return idpf_ptp_adjtime_nonatomic(info, delta);
+
+	err = idpf_ptp_adj_dev_clk_time(adapter, delta);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to adjust the clock with delta %lld err: %pe\n",
+			delta, ERR_PTR(err));
+		return err;
+	}
+
+	err = idpf_ptp_update_cached_phctime(adapter);
+	if (err)
+		pci_warn(adapter->pdev,
+			 "Unable to immediately update cached PHC time\n");
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adjfine - Adjust clock increment rate
+ * @info: the driver's PTP info structure
+ * @scaled_ppm: Parts per million with 16-bit fractional field
+ *
+ * Adjust the frequency of the clock by the indicated scaled ppm from the
+ * base frequency.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	u64 incval, diff;
+	int err;
+
+	access = adapter->ptp->adj_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	incval = adapter->ptp->base_incval;
+
+	diff = adjust_by_scaled_ppm(incval, scaled_ppm);
+	err = idpf_ptp_adj_dev_clk_fine(adapter, diff);
+	if (err)
+		pci_err(adapter->pdev, "Failed to adjust clock increment rate for scaled ppm %ld %pe\n",
+			scaled_ppm, ERR_PTR(err));
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_verify_pin - Verify if pin supports requested pin function
+ * @info: the driver's PTP info structure
+ * @pin: Pin index
+ * @func: Assigned function
+ * @chan: Assigned channel
+ *
+ * Return: EOPNOTSUPP as not supported yet.
+ */
+static int idpf_ptp_verify_pin(struct ptp_clock_info *info, unsigned int pin,
+			       enum ptp_pin_function func, unsigned int chan)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * idpf_ptp_gpio_enable - Enable/disable ancillary features of PHC
+ * @info: the driver's PTP info structure
+ * @rq: The requested feature to change
+ * @on: Enable/disable flag
+ *
+ * Return: EOPNOTSUPP as not supported yet.
+ */
+static int idpf_ptp_gpio_enable(struct ptp_clock_info *info,
+				struct ptp_clock_request *rq, int on)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * idpf_ptp_tstamp_extend_32b_to_64b - Convert a 32b nanoseconds Tx or Rx
+ *				       timestamp value to 64b.
+ * @cached_phc_time: recently cached copy of PHC time
+ * @in_timestamp: Ingress/egress 32b nanoseconds timestamp value
+ *
+ * Hardware captures timestamps which contain only 32 bits of nominal
+ * nanoseconds, as opposed to the 64bit timestamps that the stack expects.
+ *
+ * Return: Tx timestamp value extended to 64 bits based on cached PHC time.
+ */
+u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time, u32 in_timestamp)
+{
+	u32 delta, phc_time_lo;
+	u64 ns;
+
+	/* Extract the lower 32 bits of the PHC time */
+	phc_time_lo = (u32)cached_phc_time;
+
+	/* Calculate the delta between the lower 32bits of the cached PHC
+	 * time and the in_timestamp value.
+	 */
+	delta = in_timestamp - phc_time_lo;
+
+	if (delta > U32_MAX / 2) {
+		/* Reverse the delta calculation here */
+		delta = phc_time_lo - in_timestamp;
+		ns = cached_phc_time - delta;
+	} else {
+		ns = cached_phc_time + delta;
+	}
+
+	return ns;
+}
+
+/**
+ * idpf_ptp_extend_ts - Convert a 40b timestamp to 64b nanoseconds
+ * @vport: Virtual port structure
+ * @in_tstamp: Ingress/egress timestamp value
+ *
+ * It is assumed that the caller verifies the timestamp is valid prior to
+ * calling this function.
+ *
+ * Extract the 32bit nominal nanoseconds and extend them. Use the cached PHC
+ * time stored in the device private PTP structure as the basis for timestamp
+ * extension.
+ *
+ * Return: Tx timestamp value extended to 64 bits.
+ */
+u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u64 in_tstamp)
+{
+	struct idpf_ptp *ptp = vport->adapter->ptp;
+	unsigned long discard_time;
+
+	discard_time = ptp->cached_phc_jiffies + 2 * HZ;
+
+	if (time_is_before_jiffies(discard_time))
+		return 0;
+
+	return idpf_ptp_tstamp_extend_32b_to_64b(ptp->cached_phc_time,
+						 lower_32_bits(in_tstamp));
+}
+
+/**
+ * idpf_ptp_request_ts - Request an available Tx timestamp index
+ * @tx_q: Transmit queue on which the Tx timestamp is requested
+ * @skb: The SKB to associate with this timestamp request
+ * @idx: Index of the Tx timestamp latch
+ *
+ * Request tx timestamp index negotiated during PTP init that will be set into
+ * Tx descriptor.
+ *
+ * Return: 0 and the index that can be provided to Tx descriptor on success,
+ * -errno otherwise.
+ */
+int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			u32 *idx)
+{
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp;
+	struct list_head *head;
+
+	/* Get the index from the free latches list */
+	spin_lock(&tx_q->cached_tstamp_caps->latches_lock);
+
+	head = &tx_q->cached_tstamp_caps->latches_free;
+	if (list_empty(head)) {
+		spin_unlock(&tx_q->cached_tstamp_caps->latches_lock);
+		return -ENOBUFS;
+	}
+
+	ptp_tx_tstamp = list_first_entry(head, struct idpf_ptp_tx_tstamp,
+					 list_member);
+	list_del(&ptp_tx_tstamp->list_member);
+
+	ptp_tx_tstamp->skb = skb_get(skb);
+	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+	/* Move the element to the used latches list */
+	list_add(&ptp_tx_tstamp->list_member,
+		 &tx_q->cached_tstamp_caps->latches_in_use);
+	spin_unlock(&tx_q->cached_tstamp_caps->latches_lock);
+
+	*idx = ptp_tx_tstamp->idx;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_set_rx_tstamp - Enable or disable Rx timestamping
+ * @vport: Virtual port structure
+ * @rx_filter: Receive timestamp filter
+ */
+static void idpf_ptp_set_rx_tstamp(struct idpf_vport *vport, int rx_filter)
+{
+	bool enable = true, splitq;
+
+	splitq = idpf_is_queue_model_split(vport->rxq_model);
+
+	if (rx_filter == HWTSTAMP_FILTER_NONE) {
+		enable = false;
+		vport->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+	} else {
+		vport->tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL;
+	}
+
+	for (u16 i = 0; i < vport->num_rxq_grp; i++) {
+		struct idpf_rxq_group *grp = &vport->rxq_grps[i];
+		struct idpf_rx_queue *rx_queue;
+		u16 j, num_rxq;
+
+		if (splitq)
+			num_rxq = grp->splitq.num_rxq_sets;
+		else
+			num_rxq = grp->singleq.num_rxq;
+
+		for (j = 0; j < num_rxq; j++) {
+			if (splitq)
+				rx_queue = &grp->splitq.rxq_sets[j]->rxq;
+			else
+				rx_queue = grp->singleq.rxqs[j];
+
+			if (enable)
+				idpf_queue_set(PTP, rx_queue);
+			else
+				idpf_queue_clear(PTP, rx_queue);
+		}
+	}
+}
+
+/**
+ * idpf_ptp_set_timestamp_mode - Setup driver for requested timestamp mode
+ * @vport: Virtual port structure
+ * @config: Hwtstamp settings requested or saved
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+				struct kernel_hwtstamp_config *config)
+{
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		break;
+	case HWTSTAMP_TX_ON:
+		if (!idpf_ptp_is_vport_tx_tstamp_ena(vport))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	vport->tstamp_config.tx_type = config->tx_type;
+	idpf_ptp_set_rx_tstamp(vport, config->rx_filter);
+	*config = vport->tstamp_config;
+
+	return 0;
+}
+
+/**
+ * idpf_tstamp_task - Delayed task to handle Tx tstamps
+ * @work: work_struct handle
+ */
+void idpf_tstamp_task(struct work_struct *work)
+{
+	struct idpf_vport *vport;
+
+	vport = container_of(work, struct idpf_vport, tstamp_task);
+
+	idpf_ptp_get_tx_tstamp(vport);
+}
+
+/**
+ * idpf_ptp_do_aux_work - Do PTP periodic work
+ * @info: Driver's PTP info structure
+ *
+ * Return: Number of jiffies to periodic work.
+ */
+static long idpf_ptp_do_aux_work(struct ptp_clock_info *info)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+
+	idpf_ptp_update_cached_phctime(adapter);
+
+	return msecs_to_jiffies(500);
+}
+
+/**
+ * idpf_ptp_set_caps - Set PTP capabilities
+ * @adapter: Driver specific private structure
+ *
+ * This function sets the PTP functions.
+ */
+static void idpf_ptp_set_caps(const struct idpf_adapter *adapter)
+{
+	struct ptp_clock_info *info = &adapter->ptp->info;
+
+	snprintf(info->name, sizeof(info->name), "%s-%s-clk",
+		 KBUILD_MODNAME, pci_name(adapter->pdev));
+
+	info->owner = THIS_MODULE;
+	info->max_adj = adapter->ptp->max_adj;
+	info->gettimex64 = idpf_ptp_gettimex64;
+	info->settime64 = idpf_ptp_settime64;
+	info->adjfine = idpf_ptp_adjfine;
+	info->adjtime = idpf_ptp_adjtime;
+	info->verify = idpf_ptp_verify_pin;
+	info->enable = idpf_ptp_gpio_enable;
+	info->do_aux_work = idpf_ptp_do_aux_work;
+}
+
+/**
+ * idpf_ptp_create_clock - Create PTP clock device for userspace
+ * @adapter: Driver specific private structure
+ *
+ * This function creates a new PTP clock device.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_create_clock(const struct idpf_adapter *adapter)
+{
+	struct ptp_clock *clock;
+
+	idpf_ptp_set_caps(adapter);
+
+	/* Attempt to register the clock before enabling the hardware. */
+	clock = ptp_clock_register(&adapter->ptp->info,
+				   &adapter->pdev->dev);
+	if (IS_ERR(clock)) {
+		pci_err(adapter->pdev, "PTP clock creation failed: %pe\n",
+			clock);
+		return PTR_ERR(clock);
+	}
+
+	adapter->ptp->clock = clock;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_release_vport_tstamp - Release the Tx timestamps trakcers for a
+ *				   given vport.
+ * @vport: Virtual port structure
+ *
+ * Remove the queues and delete lists that tracks Tx timestamp entries for a
+ * given vport.
+ */
+static void idpf_ptp_release_vport_tstamp(struct idpf_vport *vport)
+{
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp, *tmp;
+	struct list_head *head;
+
+	cancel_work_sync(&vport->tstamp_task);
+
+	/* Remove list with free latches */
+	spin_lock_bh(&vport->tx_tstamp_caps->latches_lock);
+
+	head = &vport->tx_tstamp_caps->latches_free;
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		list_del(&ptp_tx_tstamp->list_member);
+		kfree(ptp_tx_tstamp);
+	}
+
+	/* Remove list with latches in use */
+	head = &vport->tx_tstamp_caps->latches_in_use;
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		list_del(&ptp_tx_tstamp->list_member);
+		kfree(ptp_tx_tstamp);
+	}
+
+	spin_unlock_bh(&vport->tx_tstamp_caps->latches_lock);
+
+	kfree(vport->tx_tstamp_caps);
+	vport->tx_tstamp_caps = NULL;
+}
+
+/**
+ * idpf_ptp_release_tstamp - Release the Tx timestamps trackers
+ * @adapter: Driver specific private structure
+ *
+ * Remove the queues and delete lists that tracks Tx timestamp entries.
+ */
+static void idpf_ptp_release_tstamp(struct idpf_adapter *adapter)
+{
+	idpf_for_each_vport(adapter, vport) {
+		if (!idpf_ptp_is_vport_tx_tstamp_ena(vport))
+			continue;
+
+		idpf_ptp_release_vport_tstamp(vport);
+	}
+}
+
+/**
+ * idpf_ptp_get_txq_tstamp_capability - Verify the timestamping capability
+ *					for a given tx queue.
+ * @txq: Transmit queue
+ *
+ * Since performing timestamp flows requires reading the device clock value and
+ * the support in the Control Plane, the function checks both factors and
+ * summarizes the support for the timestamping.
+ *
+ * Return: true if the timestamping is supported, false otherwise.
+ */
+bool idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq)
+{
+	if (!txq || !txq->cached_tstamp_caps)
+		return false;
+	else if (txq->cached_tstamp_caps->access)
+		return true;
+	else
+		return false;
+}
+
+/**
+ * idpf_ptp_init - Initialize PTP hardware clock support
+ * @adapter: Driver specific private structure
+ *
+ * Set up the device for interacting with the PTP hardware clock for all
+ * functions. Function will allocate and register a ptp_clock with the
+ * PTP_1588_CLOCK infrastructure.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_init(struct idpf_adapter *adapter)
+{
+	struct timespec64 ts;
+	int err;
+
+	if (!idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PTP)) {
+		pci_dbg(adapter->pdev, "PTP capability is not detected\n");
+		return -EOPNOTSUPP;
+	}
+
+	adapter->ptp = kzalloc(sizeof(*adapter->ptp), GFP_KERNEL);
+	if (!adapter->ptp)
+		return -ENOMEM;
+
+	/* add a back pointer to adapter */
+	adapter->ptp->adapter = adapter;
+
+	if (adapter->dev_ops.reg_ops.ptp_reg_init)
+		adapter->dev_ops.reg_ops.ptp_reg_init(adapter);
+
+	err = idpf_ptp_get_caps(adapter);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to get PTP caps err %d\n", err);
+		goto free_ptp;
+	}
+
+	err = idpf_ptp_create_clock(adapter);
+	if (err)
+		goto free_ptp;
+
+	if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+		ptp_schedule_worker(adapter->ptp->clock, 0);
+
+	/* Write the default increment time value if the clock adjustments
+	 * are enabled.
+	 */
+	if (adapter->ptp->adj_dev_clk_time_access != IDPF_PTP_NONE) {
+		err = idpf_ptp_adj_dev_clk_fine(adapter,
+						adapter->ptp->base_incval);
+		if (err)
+			goto remove_clock;
+	}
+
+	/* Write the initial time value if the set time operation is enabled */
+	if (adapter->ptp->set_dev_clk_time_access != IDPF_PTP_NONE) {
+		ts = ktime_to_timespec64(ktime_get_real());
+		err = idpf_ptp_settime64(&adapter->ptp->info, &ts);
+		if (err)
+			goto remove_clock;
+	}
+
+	spin_lock_init(&adapter->ptp->read_dev_clk_lock);
+
+	pci_dbg(adapter->pdev, "PTP init successful\n");
+
+	return 0;
+
+remove_clock:
+	if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+		ptp_cancel_worker_sync(adapter->ptp->clock);
+
+	ptp_clock_unregister(adapter->ptp->clock);
+	adapter->ptp->clock = NULL;
+
+free_ptp:
+	kfree(adapter->ptp);
+	adapter->ptp = NULL;
+
+	return err;
+}
+
+/**
+ * idpf_ptp_release - Clear PTP hardware clock support
+ * @adapter: Driver specific private structure
+ */
+void idpf_ptp_release(struct idpf_adapter *adapter)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+
+	if (!ptp)
+		return;
+
+	if (ptp->tx_tstamp_access != IDPF_PTP_NONE &&
+	    ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+		idpf_ptp_release_tstamp(adapter);
+
+	if (ptp->clock) {
+		if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+			ptp_cancel_worker_sync(adapter->ptp->clock);
+
+		ptp_clock_unregister(ptp->clock);
+	}
+
+	kfree(ptp);
+	adapter->ptp = NULL;
+}
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
new file mode 100644
index 000000000000..a876749d6116
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
@@ -0,0 +1,362 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef _IDPF_PTP_H
+#define _IDPF_PTP_H
+
+#include <linux/ptp_clock_kernel.h>
+
+/**
+ * struct idpf_ptp_cmd - PTP command masks
+ * @exec_cmd_mask: mask to trigger command execution
+ * @shtime_enable_mask: mask to enable shadow time
+ */
+struct idpf_ptp_cmd {
+	u32 exec_cmd_mask;
+	u32 shtime_enable_mask;
+};
+
+/* struct idpf_ptp_dev_clk_regs - PTP device registers
+ * @dev_clk_ns_l: low part of the device clock register
+ * @dev_clk_ns_h: high part of the device clock register
+ * @phy_clk_ns_l: low part of the PHY clock register
+ * @phy_clk_ns_h: high part of the PHY clock register
+ * @incval_l: low part of the increment value register
+ * @incval_h: high part of the increment value register
+ * @shadj_l: low part of the shadow adjust register
+ * @shadj_h: high part of the shadow adjust register
+ * @phy_incval_l: low part of the PHY increment value register
+ * @phy_incval_h: high part of the PHY increment value register
+ * @phy_shadj_l: low part of the PHY shadow adjust register
+ * @phy_shadj_h: high part of the PHY shadow adjust register
+ * @cmd: PTP command register
+ * @phy_cmd: PHY command register
+ * @cmd_sync: PTP command synchronization register
+ */
+struct idpf_ptp_dev_clk_regs {
+	/* Main clock */
+	void __iomem *dev_clk_ns_l;
+	void __iomem *dev_clk_ns_h;
+
+	/* PHY timer */
+	void __iomem *phy_clk_ns_l;
+	void __iomem *phy_clk_ns_h;
+
+	/* Main timer adjustments */
+	void __iomem *incval_l;
+	void __iomem *incval_h;
+	void __iomem *shadj_l;
+	void __iomem *shadj_h;
+
+	/* PHY timer adjustments */
+	void __iomem *phy_incval_l;
+	void __iomem *phy_incval_h;
+	void __iomem *phy_shadj_l;
+	void __iomem *phy_shadj_h;
+
+	/* Command */
+	void __iomem *cmd;
+	void __iomem *phy_cmd;
+	void __iomem *cmd_sync;
+};
+
+/**
+ * enum idpf_ptp_access - the type of access to PTP operations
+ * @IDPF_PTP_NONE: no access
+ * @IDPF_PTP_DIRECT: direct access through BAR registers
+ * @IDPF_PTP_MAILBOX: access through mailbox messages
+ */
+enum idpf_ptp_access {
+	IDPF_PTP_NONE = 0,
+	IDPF_PTP_DIRECT,
+	IDPF_PTP_MAILBOX,
+};
+
+/**
+ * struct idpf_ptp_secondary_mbx - PTP secondary mailbox
+ * @peer_mbx_q_id: PTP mailbox queue ID
+ * @peer_id: Peer ID for PTP Device Control daemon
+ * @valid: indicates whether secondary mailblox is supported by the Control
+ *	   Plane
+ */
+struct idpf_ptp_secondary_mbx {
+	u16 peer_mbx_q_id;
+	u16 peer_id;
+	bool valid:1;
+};
+
+/**
+ * enum idpf_ptp_tx_tstamp_state - Tx timestamp states
+ * @IDPF_PTP_FREE: Tx timestamp index free to use
+ * @IDPF_PTP_REQUEST: Tx timestamp index set to the Tx descriptor
+ * @IDPF_PTP_READ_VALUE: Tx timestamp value ready to be read
+ */
+enum idpf_ptp_tx_tstamp_state {
+	IDPF_PTP_FREE,
+	IDPF_PTP_REQUEST,
+	IDPF_PTP_READ_VALUE,
+};
+
+/**
+ * struct idpf_ptp_tx_tstamp_status - Parameters to track Tx timestamp
+ * @skb: the pointer to the SKB that received the completion tag
+ * @state: the state of the Tx timestamp
+ */
+struct idpf_ptp_tx_tstamp_status {
+	struct sk_buff *skb;
+	enum idpf_ptp_tx_tstamp_state state;
+};
+
+/**
+ * struct idpf_ptp_tx_tstamp - Parameters for Tx timestamping
+ * @list_member: the list member structure
+ * @tx_latch_reg_offset_l: Tx tstamp latch low register offset
+ * @tx_latch_reg_offset_h: Tx tstamp latch high register offset
+ * @skb: the pointer to the SKB for this timestamp request
+ * @tstamp: the Tx tstamp value
+ * @idx: the index of the Tx tstamp
+ */
+struct idpf_ptp_tx_tstamp {
+	struct list_head list_member;
+	u32 tx_latch_reg_offset_l;
+	u32 tx_latch_reg_offset_h;
+	struct sk_buff *skb;
+	u64 tstamp;
+	u32 idx;
+};
+
+/**
+ * struct idpf_ptp_vport_tx_tstamp_caps - Tx timestamp capabilities
+ * @vport_id: the vport id
+ * @num_entries: the number of negotiated Tx timestamp entries
+ * @tstamp_ns_lo_bit: first bit for nanosecond part of the timestamp
+ * @latches_lock: the lock to the lists of free/used timestamp indexes
+ * @status_lock: the lock to the status tracker
+ * @access: indicates an access to Tx timestamp
+ * @latches_free: the list of the free Tx timestamps latches
+ * @latches_in_use: the list of the used Tx timestamps latches
+ * @tx_tstamp_status: Tx tstamp status tracker
+ */
+struct idpf_ptp_vport_tx_tstamp_caps {
+	u32 vport_id;
+	u16 num_entries;
+	u16 tstamp_ns_lo_bit;
+	spinlock_t latches_lock;
+	spinlock_t status_lock;
+	bool access:1;
+	struct list_head latches_free;
+	struct list_head latches_in_use;
+	struct idpf_ptp_tx_tstamp_status tx_tstamp_status[];
+};
+
+/**
+ * struct idpf_ptp - PTP parameters
+ * @info: structure defining PTP hardware capabilities
+ * @clock: pointer to registered PTP clock device
+ * @adapter: back pointer to the adapter
+ * @base_incval: base increment value of the PTP clock
+ * @max_adj: maximum adjustment of the PTP clock
+ * @cmd: HW specific command masks
+ * @cached_phc_time: a cached copy of the PHC time for timestamp extension
+ * @cached_phc_jiffies: jiffies when cached_phc_time was last updated
+ * @dev_clk_regs: the set of registers to access the device clock
+ * @caps: PTP capabilities negotiated with the Control Plane
+ * @get_dev_clk_time_access: access type for getting the device clock time
+ * @set_dev_clk_time_access: access type for setting the device clock time
+ * @adj_dev_clk_time_access: access type for the adjusting the device clock
+ * @tx_tstamp_access: access type for the Tx timestamp value read
+ * @rsv: reserved bits
+ * @secondary_mbx: parameters for using dedicated PTP mailbox
+ * @read_dev_clk_lock: spinlock protecting access to the device clock read
+ *		       operation executed by the HW latch
+ */
+struct idpf_ptp {
+	struct ptp_clock_info info;
+	struct ptp_clock *clock;
+	struct idpf_adapter *adapter;
+	u64 base_incval;
+	u64 max_adj;
+	struct idpf_ptp_cmd cmd;
+	u64 cached_phc_time;
+	unsigned long cached_phc_jiffies;
+	struct idpf_ptp_dev_clk_regs dev_clk_regs;
+	u32 caps;
+	enum idpf_ptp_access get_dev_clk_time_access:2;
+	enum idpf_ptp_access set_dev_clk_time_access:2;
+	enum idpf_ptp_access adj_dev_clk_time_access:2;
+	enum idpf_ptp_access tx_tstamp_access:2;
+	u8 rsv;
+	struct idpf_ptp_secondary_mbx secondary_mbx;
+	spinlock_t read_dev_clk_lock;
+};
+
+/**
+ * idpf_ptp_info_to_adapter - get driver adapter struct from ptp_clock_info
+ * @info: pointer to ptp_clock_info struct
+ *
+ * Return: pointer to the corresponding adapter struct
+ */
+static inline struct idpf_adapter *
+idpf_ptp_info_to_adapter(const struct ptp_clock_info *info)
+{
+	const struct idpf_ptp *ptp = container_of_const(info, struct idpf_ptp,
+							info);
+	return ptp->adapter;
+}
+
+/**
+ * struct idpf_ptp_dev_timers - System time and device time values
+ * @sys_time_ns: system time value expressed in nanoseconds
+ * @dev_clk_time_ns: device clock time value expressed in nanoseconds
+ */
+struct idpf_ptp_dev_timers {
+	u64 sys_time_ns;
+	u64 dev_clk_time_ns;
+};
+
+/**
+ * idpf_ptp_is_vport_tx_tstamp_ena - Verify the Tx timestamping enablement for
+ *				     a given vport.
+ * @vport: Virtual port structure
+ *
+ * Tx timestamp capabilities are negotiated with the Control Plane only if the
+ * device clock value can be read, Tx timestamp access type is different than
+ * NONE, and the PTP clock for the adapter is created. When all those conditions
+ * are satisfied, Tx timestamp feature is enabled and tx_tstamp_caps is
+ * allocated and fulfilled.
+ *
+ * Return: true if the Tx timestamping is enabled, false otherwise.
+ */
+static inline bool idpf_ptp_is_vport_tx_tstamp_ena(struct idpf_vport *vport)
+{
+	if (!vport->tx_tstamp_caps)
+		return false;
+	else
+		return true;
+}
+
+/**
+ * idpf_ptp_is_vport_rx_tstamp_ena - Verify the Rx timestamping enablement for
+ *				     a given vport.
+ * @vport: Virtual port structure
+ *
+ * Rx timestamp feature is enabled if the PTP clock for the adapter is created
+ * and it is possible to read the value of the device clock. The second
+ * assumption comes from the need to extend the Rx timestamp value to 64 bit
+ * based on the current device clock time.
+ *
+ * Return: true if the Rx timestamping is enabled, false otherwise.
+ */
+static inline bool idpf_ptp_is_vport_rx_tstamp_ena(struct idpf_vport *vport)
+{
+	if (!vport->adapter->ptp ||
+	    vport->adapter->ptp->get_dev_clk_time_access == IDPF_PTP_NONE)
+		return false;
+	else
+		return true;
+}
+
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+int idpf_ptp_init(struct idpf_adapter *adapter);
+void idpf_ptp_release(struct idpf_adapter *adapter);
+int idpf_ptp_get_caps(struct idpf_adapter *adapter);
+void idpf_ptp_get_features_access(const struct idpf_adapter *adapter);
+bool idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq);
+int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			      struct idpf_ptp_dev_timers *dev_clk_time);
+int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time);
+int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval);
+int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta);
+int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport);
+int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport);
+int idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+				struct kernel_hwtstamp_config *config);
+u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u64 in_tstamp);
+u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time, u32 in_timestamp);
+int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			u32 *idx);
+void idpf_tstamp_task(struct work_struct *work);
+#else /* CONFIG_PTP_1588_CLOCK */
+static inline int idpf_ptp_init(struct idpf_adapter *adapter)
+{
+	return 0;
+}
+
+static inline void idpf_ptp_release(struct idpf_adapter *adapter) { }
+
+static inline int idpf_ptp_get_caps(struct idpf_adapter *adapter)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void
+idpf_ptp_get_features_access(const struct idpf_adapter *adapter) { }
+
+static inline bool
+idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq)
+{
+	return false;
+}
+
+static inline int
+idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			  struct idpf_ptp_dev_timers *dev_clk_time)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter,
+					    u64 time)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter,
+					    u64 incval)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter,
+					    s64 delta)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+			    struct kernel_hwtstamp_config *config)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u32 in_tstamp)
+{
+	return 0;
+}
+
+static inline u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time,
+						    u32 in_timestamp)
+{
+	return 0;
+}
+
+static inline int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q,
+				      struct sk_buff *skb, u32 *idx)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void idpf_tstamp_task(struct work_struct *work) { }
+#endif /* CONFIG_PTP_1588_CLOCK */
+#endif /* _IDPF_PTP_H */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index eae1b6f474e6..2e356dd10812 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -891,7 +891,6 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q,
  * idpf_rx_singleq_extract_base_fields - Extract fields from the Rx descriptor
  * @rx_desc: the descriptor to process
  * @fields: storage for extracted values
- * @ptype: pointer that will store packet type
  *
  * Decode the Rx descriptor and extract relevant information including the
  * size and Rx packet type.
@@ -901,21 +900,20 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q,
  */
 static void
 idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc,
-				    struct libeth_rqe_info *fields, u32 *ptype)
+				    struct libeth_rqe_info *fields)
 {
 	u64 qword;
 
 	qword = le64_to_cpu(rx_desc->base_wb.qword1.status_error_ptype_len);
 
 	fields->len = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword);
-	*ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword);
+	fields->ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword);
 }
 
 /**
  * idpf_rx_singleq_extract_flex_fields - Extract fields from the Rx descriptor
  * @rx_desc: the descriptor to process
  * @fields: storage for extracted values
- * @ptype: pointer that will store packet type
  *
  * Decode the Rx descriptor and extract relevant information including the
  * size and Rx packet type.
@@ -925,12 +923,12 @@ idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc,
  */
 static void
 idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc,
-				    struct libeth_rqe_info *fields, u32 *ptype)
+				    struct libeth_rqe_info *fields)
 {
 	fields->len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M,
 				le16_to_cpu(rx_desc->flex_nic_wb.pkt_len));
-	*ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M,
-			   le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0));
+	fields->ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M,
+				  le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0));
 }
 
 /**
@@ -938,18 +936,17 @@ idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc,
  * @rx_q: Rx descriptor queue
  * @rx_desc: the descriptor to process
  * @fields: storage for extracted values
- * @ptype: pointer that will store packet type
  *
  */
 static void
 idpf_rx_singleq_extract_fields(const struct idpf_rx_queue *rx_q,
 			       const union virtchnl2_rx_desc *rx_desc,
-			       struct libeth_rqe_info *fields, u32 *ptype)
+			       struct libeth_rqe_info *fields)
 {
 	if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M)
-		idpf_rx_singleq_extract_base_fields(rx_desc, fields, ptype);
+		idpf_rx_singleq_extract_base_fields(rx_desc, fields);
 	else
-		idpf_rx_singleq_extract_flex_fields(rx_desc, fields, ptype);
+		idpf_rx_singleq_extract_flex_fields(rx_desc, fields);
 }
 
 /**
@@ -972,7 +969,6 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget)
 		struct libeth_rqe_info fields = { };
 		union virtchnl2_rx_desc *rx_desc;
 		struct idpf_rx_buf *rx_buf;
-		u32 ptype;
 
 		/* get the Rx desc from Rx queue based on 'next_to_clean' */
 		rx_desc = &rx_q->rx[ntc];
@@ -993,7 +989,7 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget)
 		 */
 		dma_rmb();
 
-		idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields, &ptype);
+		idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields);
 
 		rx_buf = &rx_q->rx_buf[ntc];
 		if (!libeth_rx_sync_for_cpu(rx_buf, fields.len))
@@ -1037,7 +1033,8 @@ skip_data:
 		total_rx_bytes += skb->len;
 
 		/* protocol */
-		idpf_rx_singleq_process_skb_fields(rx_q, skb, rx_desc, ptype);
+		idpf_rx_singleq_process_skb_fields(rx_q, skb, rx_desc,
+						   fields.ptype);
 
 		/* send completed skb up the stack */
 		napi_gro_receive(rx_q->pp->p.napi, skb);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index bdf52cef3891..631679cdaa6f 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -5,6 +5,7 @@
 #include <net/libeth/tx.h>
 
 #include "idpf.h"
+#include "idpf_ptp.h"
 #include "idpf_virtchnl.h"
 
 struct idpf_tx_stash {
@@ -1107,6 +1108,8 @@ void idpf_vport_queues_rel(struct idpf_vport *vport)
  */
 static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport)
 {
+	struct idpf_ptp_vport_tx_tstamp_caps *caps = vport->tx_tstamp_caps;
+	struct work_struct *tstamp_task = &vport->tstamp_task;
 	int i, j, k = 0;
 
 	vport->txqs = kcalloc(vport->num_txq, sizeof(*vport->txqs),
@@ -1121,6 +1124,12 @@ static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport)
 		for (j = 0; j < tx_grp->num_txq; j++, k++) {
 			vport->txqs[k] = tx_grp->txqs[j];
 			vport->txqs[k]->idx = k;
+
+			if (!caps)
+				continue;
+
+			vport->txqs[k]->cached_tstamp_caps = caps;
+			vport->txqs[k]->tstamp_task = tstamp_task;
 		}
 	}
 
@@ -1655,6 +1664,40 @@ static void idpf_tx_handle_sw_marker(struct idpf_tx_queue *tx_q)
 }
 
 /**
+ * idpf_tx_read_tstamp - schedule a work to read Tx timestamp value
+ * @txq: queue to read the timestamp from
+ * @skb: socket buffer to provide Tx timestamp value
+ *
+ * Schedule a work to read Tx timestamp value generated once the packet is
+ * transmitted.
+ */
+static void idpf_tx_read_tstamp(struct idpf_tx_queue *txq, struct sk_buff *skb)
+{
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct idpf_ptp_tx_tstamp_status *tx_tstamp_status;
+
+	tx_tstamp_caps = txq->cached_tstamp_caps;
+	spin_lock_bh(&tx_tstamp_caps->status_lock);
+
+	for (u32 i = 0; i < tx_tstamp_caps->num_entries; i++) {
+		tx_tstamp_status = &tx_tstamp_caps->tx_tstamp_status[i];
+		if (tx_tstamp_status->state != IDPF_PTP_FREE)
+			continue;
+
+		tx_tstamp_status->skb = skb;
+		tx_tstamp_status->state = IDPF_PTP_REQUEST;
+
+		/* Fetch timestamp from completion descriptor through
+		 * virtchnl msg to report to stack.
+		 */
+		queue_work(system_unbound_wq, txq->tstamp_task);
+		break;
+	}
+
+	spin_unlock_bh(&tx_tstamp_caps->status_lock);
+}
+
+/**
  * idpf_tx_clean_stashed_bufs - clean bufs that were stored for
  * out of order completions
  * @txq: queue to clean
@@ -1682,6 +1725,11 @@ static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq,
 			continue;
 
 		hash_del(&stash->hlist);
+
+		if (stash->buf.type == LIBETH_SQE_SKB &&
+		    (skb_shinfo(stash->buf.skb)->tx_flags & SKBTX_IN_PROGRESS))
+			idpf_tx_read_tstamp(txq, stash->buf.skb);
+
 		libeth_tx_complete(&stash->buf, &cp);
 
 		/* Push shadow buf back onto stack */
@@ -1876,8 +1924,12 @@ static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
 		     idpf_tx_buf_compl_tag(tx_buf) != compl_tag))
 		return false;
 
-	if (tx_buf->type == LIBETH_SQE_SKB)
+	if (tx_buf->type == LIBETH_SQE_SKB) {
+		if (skb_shinfo(tx_buf->skb)->tx_flags & SKBTX_IN_PROGRESS)
+			idpf_tx_read_tstamp(txq, tx_buf->skb);
+
 		libeth_tx_complete(tx_buf, &cp);
+	}
 
 	idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
 
@@ -2127,7 +2179,7 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 				    struct idpf_tx_splitq_params *params,
 				    u16 td_cmd, u16 size)
 {
-	desc->flow.qw1.cmd_dtype = (u16)params->dtype | td_cmd;
+	*(u32 *)&desc->flow.qw1.cmd_dtype = (u8)(params->dtype | td_cmd);
 	desc->flow.qw1.rxr_bufsize = cpu_to_le16((u16)size);
 	desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag);
 }
@@ -2296,7 +2348,7 @@ void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
 		 * descriptor. Reset that here.
 		 */
 		tx_desc = &txq->flex_tx[idx];
-		memset(tx_desc, 0, sizeof(struct idpf_flex_tx_ctx_desc));
+		memset(tx_desc, 0, sizeof(*tx_desc));
 		if (idx == 0)
 			idx = txq->desc_count;
 		idx--;
@@ -2699,10 +2751,10 @@ static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
  * Since the TX buffer rings mimics the descriptor ring, update the tx buffer
  * ring entry to reflect that this index is a context descriptor
  */
-static struct idpf_flex_tx_ctx_desc *
+static union idpf_flex_tx_ctx_desc *
 idpf_tx_splitq_get_ctx_desc(struct idpf_tx_queue *txq)
 {
-	struct idpf_flex_tx_ctx_desc *desc;
+	union idpf_flex_tx_ctx_desc *desc;
 	int i = txq->next_to_use;
 
 	txq->tx_buf[i].type = LIBETH_SQE_CTX;
@@ -2732,6 +2784,73 @@ netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb)
 	return NETDEV_TX_OK;
 }
 
+#if (IS_ENABLED(CONFIG_PTP_1588_CLOCK))
+/**
+ * idpf_tx_tstamp - set up context descriptor for hardware timestamp
+ * @tx_q: queue to send buffer on
+ * @skb: pointer to the SKB we're sending
+ * @off: pointer to the offload struct
+ *
+ * Return: Positive index number on success, negative otherwise.
+ */
+static int idpf_tx_tstamp(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			  struct idpf_tx_offload_params *off)
+{
+	int err, idx;
+
+	/* only timestamp the outbound packet if the user has requested it */
+	if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
+		return -1;
+
+	if (!idpf_ptp_get_txq_tstamp_capability(tx_q))
+		return -1;
+
+	/* Tx timestamps cannot be sampled when doing TSO */
+	if (off->tx_flags & IDPF_TX_FLAGS_TSO)
+		return -1;
+
+	/* Grab an open timestamp slot */
+	err = idpf_ptp_request_ts(tx_q, skb, &idx);
+	if (err) {
+		u64_stats_update_begin(&tx_q->stats_sync);
+		u64_stats_inc(&tx_q->q_stats.tstamp_skipped);
+		u64_stats_update_end(&tx_q->stats_sync);
+
+		return -1;
+	}
+
+	off->tx_flags |= IDPF_TX_FLAGS_TSYN;
+
+	return idx;
+}
+
+/**
+ * idpf_tx_set_tstamp_desc - Set the Tx descriptor fields needed to generate
+ *			     PHY Tx timestamp
+ * @ctx_desc: Context descriptor
+ * @idx: Index of the Tx timestamp latch
+ */
+static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc,
+				    u32 idx)
+{
+	ctx_desc->tsyn.qw1 = le64_encode_bits(IDPF_TX_DESC_DTYPE_CTX,
+					      IDPF_TX_CTX_DTYPE_M) |
+			     le64_encode_bits(IDPF_TX_CTX_DESC_TSYN,
+					      IDPF_TX_CTX_CMD_M) |
+			     le64_encode_bits(idx, IDPF_TX_CTX_TSYN_REG_M);
+}
+#else /* CONFIG_PTP_1588_CLOCK */
+static int idpf_tx_tstamp(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			  struct idpf_tx_offload_params *off)
+{
+	return -1;
+}
+
+static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc,
+				    u32 idx)
+{ }
+#endif /* CONFIG_PTP_1588_CLOCK */
+
 /**
  * idpf_tx_splitq_frame - Sends buffer on Tx ring using flex descriptors
  * @skb: send buffer
@@ -2743,9 +2862,10 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 					struct idpf_tx_queue *tx_q)
 {
 	struct idpf_tx_splitq_params tx_params = { };
+	union idpf_flex_tx_ctx_desc *ctx_desc;
 	struct idpf_tx_buf *first;
 	unsigned int count;
-	int tso;
+	int tso, idx;
 
 	count = idpf_tx_desc_count_required(tx_q, skb);
 	if (unlikely(!count))
@@ -2765,8 +2885,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 
 	if (tso) {
 		/* If tso is needed, set up context desc */
-		struct idpf_flex_tx_ctx_desc *ctx_desc =
-			idpf_tx_splitq_get_ctx_desc(tx_q);
+		ctx_desc = idpf_tx_splitq_get_ctx_desc(tx_q);
 
 		ctx_desc->tso.qw1.cmd_dtype =
 				cpu_to_le16(IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX |
@@ -2784,6 +2903,12 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 		u64_stats_update_end(&tx_q->stats_sync);
 	}
 
+	idx = idpf_tx_tstamp(tx_q, skb, &tx_params.offload);
+	if (idx != -1) {
+		ctx_desc = idpf_tx_splitq_get_ctx_desc(tx_q);
+		idpf_tx_set_tstamp_desc(ctx_desc, idx);
+	}
+
 	/* record the location of the first descriptor for this packet */
 	first = &tx_q->tx_buf[tx_q->next_to_use];
 	first->skb = skb;
@@ -3046,6 +3171,33 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 }
 
 /**
+ * idpf_rx_hwtstamp - check for an RX timestamp and pass up the stack
+ * @rxq: pointer to the rx queue that receives the timestamp
+ * @rx_desc: pointer to rx descriptor containing timestamp
+ * @skb: skb to put timestamp in
+ */
+static void
+idpf_rx_hwtstamp(const struct idpf_rx_queue *rxq,
+		 const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc,
+		 struct sk_buff *skb)
+{
+	u64 cached_time, ts_ns;
+	u32 ts_high;
+
+	if (!(rx_desc->ts_low & VIRTCHNL2_RX_FLEX_TSTAMP_VALID))
+		return;
+
+	cached_time = READ_ONCE(rxq->cached_phc_time);
+
+	ts_high = le32_to_cpu(rx_desc->ts_high);
+	ts_ns = idpf_ptp_tstamp_extend_32b_to_64b(cached_time, ts_high);
+
+	*skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) {
+		.hwtstamp = ns_to_ktime(ts_ns),
+	};
+}
+
+/**
  * idpf_rx_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rxq: Rx descriptor ring packet is being transacted on
  * @skb: pointer to current skb being populated
@@ -3070,6 +3222,9 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	/* process RSS/hash */
 	idpf_rx_hash(rxq, skb, rx_desc, decoded);
 
+	if (idpf_queue_has(PTP, rxq))
+		idpf_rx_hwtstamp(rxq, rx_desc, skb);
+
 	skb->protocol = eth_type_trans(skb, rxq->netdev);
 	skb_record_rx_queue(skb, rxq->idx);
 
@@ -4025,6 +4180,14 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
 		return budget;
 	}
 
+	/* Switch to poll mode in the tear-down path after sending disable
+	 * queues virtchnl message, as the interrupts will be disabled after
+	 * that.
+	 */
+	if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE,
+							 q_vector->tx[0])))
+		return budget;
+
 	work_done = min_t(int, work_done, budget - 1);
 
 	/* Exit the polling mode, but don't re-enable interrupts if stack might
@@ -4035,15 +4198,7 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
 	else
 		idpf_vport_intr_set_wb_on_itr(q_vector);
 
-	/* Switch to poll mode in the tear-down path after sending disable
-	 * queues virtchnl message, as the interrupts will be disabled after
-	 * that
-	 */
-	if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE,
-							 q_vector->tx[0])))
-		return budget;
-	else
-		return work_done;
+	return work_done;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index b029f566e57c..c779fe71df99 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -142,6 +142,7 @@ do {								\
 #define IDPF_TX_FLAGS_IPV4		BIT(1)
 #define IDPF_TX_FLAGS_IPV6		BIT(2)
 #define IDPF_TX_FLAGS_TUNNEL		BIT(3)
+#define IDPF_TX_FLAGS_TSYN		BIT(4)
 
 union idpf_tx_flex_desc {
 	struct idpf_flex_tx_desc q; /* queue based scheduling */
@@ -289,6 +290,8 @@ struct idpf_ptype_state {
  * @__IDPF_Q_POLL_MODE: Enable poll mode
  * @__IDPF_Q_CRC_EN: enable CRC offload in singleq mode
  * @__IDPF_Q_HSPLIT_EN: enable header split on Rx (splitq)
+ * @__IDPF_Q_PTP: indicates whether the Rx timestamping is enabled for the
+ *		  queue
  * @__IDPF_Q_FLAGS_NBITS: Must be last
  */
 enum idpf_queue_flags_t {
@@ -299,6 +302,7 @@ enum idpf_queue_flags_t {
 	__IDPF_Q_POLL_MODE,
 	__IDPF_Q_CRC_EN,
 	__IDPF_Q_HSPLIT_EN,
+	__IDPF_Q_PTP,
 
 	__IDPF_Q_FLAGS_NBITS,
 };
@@ -443,6 +447,7 @@ struct idpf_tx_queue_stats {
 	u64_stats_t q_busy;
 	u64_stats_t skb_drops;
 	u64_stats_t dma_map_errs;
+	u64_stats_t tstamp_skipped;
 };
 
 #define IDPF_ITR_DYNAMIC	1
@@ -494,6 +499,7 @@ struct idpf_txq_stash {
  * @next_to_alloc: RX buffer to allocate at
  * @skb: Pointer to the skb
  * @truesize: data buffer truesize in singleq
+ * @cached_phc_time: Cached PHC time for the Rx queue
  * @stats_sync: See struct u64_stats_sync
  * @q_stats: See union idpf_rx_queue_stats
  * @q_id: Queue id
@@ -541,6 +547,7 @@ struct idpf_rx_queue {
 
 	struct sk_buff *skb;
 	u32 truesize;
+	u64 cached_phc_time;
 
 	struct u64_stats_sync stats_sync;
 	struct idpf_rx_queue_stats q_stats;
@@ -560,7 +567,7 @@ struct idpf_rx_queue {
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
-			    80 + sizeof(struct u64_stats_sync),
+			    88 + sizeof(struct u64_stats_sync),
 			    32);
 
 /**
@@ -617,6 +624,8 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  * @compl_tag_bufid_m: Completion tag buffer id mask
  * @compl_tag_cur_gen: Used to keep track of current completion tag generation
  * @compl_tag_gen_max: To determine when compl_tag_cur_gen should be reset
+ * @cached_tstamp_caps: Tx timestamp capabilities negotiated with the CP
+ * @tstamp_task: Work that handles Tx timestamp read
  * @stats_sync: See struct u64_stats_sync
  * @q_stats: See union idpf_tx_queue_stats
  * @q_id: Queue id
@@ -630,7 +639,7 @@ struct idpf_tx_queue {
 		struct idpf_base_tx_desc *base_tx;
 		struct idpf_base_tx_ctx_desc *base_ctx;
 		union idpf_tx_flex_desc *flex_tx;
-		struct idpf_flex_tx_ctx_desc *flex_ctx;
+		union idpf_flex_tx_ctx_desc *flex_ctx;
 
 		void *desc_ring;
 	};
@@ -666,6 +675,9 @@ struct idpf_tx_queue {
 	u16 compl_tag_cur_gen;
 	u16 compl_tag_gen_max;
 
+	struct idpf_ptp_vport_tx_tstamp_caps *cached_tstamp_caps;
+	struct work_struct *tstamp_task;
+
 	struct u64_stats_sync stats_sync;
 	struct idpf_tx_queue_stats q_stats;
 	__cacheline_group_end_aligned(read_write);
@@ -679,7 +691,7 @@ struct idpf_tx_queue {
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_tx_queue, 64,
-			    88 + sizeof(struct u64_stats_sync),
+			    112 + sizeof(struct u64_stats_sync),
 			    24);
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 3d2413b8684f..07a9f5ae34fd 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -5,88 +5,7 @@
 
 #include "idpf.h"
 #include "idpf_virtchnl.h"
-
-#define IDPF_VC_XN_MIN_TIMEOUT_MSEC	2000
-#define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC	(60 * 1000)
-#define IDPF_VC_XN_IDX_M		GENMASK(7, 0)
-#define IDPF_VC_XN_SALT_M		GENMASK(15, 8)
-#define IDPF_VC_XN_RING_LEN		U8_MAX
-
-/**
- * enum idpf_vc_xn_state - Virtchnl transaction status
- * @IDPF_VC_XN_IDLE: not expecting a reply, ready to be used
- * @IDPF_VC_XN_WAITING: expecting a reply, not yet received
- * @IDPF_VC_XN_COMPLETED_SUCCESS: a reply was expected and received,
- *				  buffer updated
- * @IDPF_VC_XN_COMPLETED_FAILED: a reply was expected and received, but there
- *				 was an error, buffer not updated
- * @IDPF_VC_XN_SHUTDOWN: transaction object cannot be used, VC torn down
- * @IDPF_VC_XN_ASYNC: transaction sent asynchronously and doesn't have the
- *		      return context; a callback may be provided to handle
- *		      return
- */
-enum idpf_vc_xn_state {
-	IDPF_VC_XN_IDLE = 1,
-	IDPF_VC_XN_WAITING,
-	IDPF_VC_XN_COMPLETED_SUCCESS,
-	IDPF_VC_XN_COMPLETED_FAILED,
-	IDPF_VC_XN_SHUTDOWN,
-	IDPF_VC_XN_ASYNC,
-};
-
-struct idpf_vc_xn;
-/* Callback for asynchronous messages */
-typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *,
-			    const struct idpf_ctlq_msg *);
-
-/**
- * struct idpf_vc_xn - Data structure representing virtchnl transactions
- * @completed: virtchnl event loop uses that to signal when a reply is
- *	       available, uses kernel completion API
- * @state: virtchnl event loop stores the data below, protected by the
- *	   completion's lock.
- * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be
- *	      truncated on its way to the receiver thread according to
- *	      reply_buf.iov_len.
- * @reply: Reference to the buffer(s) where the reply data should be written
- *	   to. May be 0-length (then NULL address permitted) if the reply data
- *	   should be ignored.
- * @async_handler: if sent asynchronously, a callback can be provided to handle
- *		   the reply when it's received
- * @vc_op: corresponding opcode sent with this transaction
- * @idx: index used as retrieval on reply receive, used for cookie
- * @salt: changed every message to make unique, used for cookie
- */
-struct idpf_vc_xn {
-	struct completion completed;
-	enum idpf_vc_xn_state state;
-	size_t reply_sz;
-	struct kvec reply;
-	async_vc_cb async_handler;
-	u32 vc_op;
-	u8 idx;
-	u8 salt;
-};
-
-/**
- * struct idpf_vc_xn_params - Parameters for executing transaction
- * @send_buf: kvec for send buffer
- * @recv_buf: kvec for recv buffer, may be NULL, must then have zero length
- * @timeout_ms: timeout to wait for reply
- * @async: send message asynchronously, will not wait on completion
- * @async_handler: If sent asynchronously, optional callback handler. The user
- *		   must be careful when using async handlers as the memory for
- *		   the recv_buf _cannot_ be on stack if this is async.
- * @vc_op: virtchnl op to send
- */
-struct idpf_vc_xn_params {
-	struct kvec send_buf;
-	struct kvec recv_buf;
-	int timeout_ms;
-	bool async;
-	async_vc_cb async_handler;
-	u32 vc_op;
-};
+#include "idpf_ptp.h"
 
 /**
  * struct idpf_vc_xn_manager - Manager for tracking transactions
@@ -235,6 +154,55 @@ err_kfree:
 	return err;
 }
 
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+/**
+ * idpf_ptp_is_mb_msg - Check if the message is PTP-related
+ * @op: virtchnl opcode
+ *
+ * Return: true if msg is PTP-related, false otherwise.
+ */
+static bool idpf_ptp_is_mb_msg(u32 op)
+{
+	switch (op) {
+	case VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_GET_CROSS_TIME:
+	case VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE:
+	case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS:
+	case VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * idpf_prepare_ptp_mb_msg - Prepare PTP related message
+ *
+ * @adapter: Driver specific private structure
+ * @op: virtchnl opcode
+ * @ctlq_msg: Corresponding control queue message
+ */
+static void idpf_prepare_ptp_mb_msg(struct idpf_adapter *adapter, u32 op,
+				    struct idpf_ctlq_msg *ctlq_msg)
+{
+	/* If the message is PTP-related and the secondary mailbox is available,
+	 * send the message through the secondary mailbox.
+	 */
+	if (!idpf_ptp_is_mb_msg(op) || !adapter->ptp->secondary_mbx.valid)
+		return;
+
+	ctlq_msg->opcode = idpf_mbq_opc_send_msg_to_peer_drv;
+	ctlq_msg->func_id = adapter->ptp->secondary_mbx.peer_mbx_q_id;
+	ctlq_msg->host_id = adapter->ptp->secondary_mbx.peer_id;
+}
+#else /* !CONFIG_PTP_1588_CLOCK */
+static void idpf_prepare_ptp_mb_msg(struct idpf_adapter *adapter, u32 op,
+				    struct idpf_ctlq_msg *ctlq_msg)
+{ }
+#endif /* CONFIG_PTP_1588_CLOCK */
+
 /**
  * idpf_send_mb_msg - Send message over mailbox
  * @adapter: Driver specific private structure
@@ -278,6 +246,9 @@ int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op,
 
 	ctlq_msg->opcode = idpf_mbq_opc_send_msg_to_cp;
 	ctlq_msg->func_id = 0;
+
+	idpf_prepare_ptp_mb_msg(adapter, op, ctlq_msg);
+
 	ctlq_msg->data_len = msg_size;
 	ctlq_msg->cookie.mbx.chnl_opcode = op;
 	ctlq_msg->cookie.mbx.chnl_retval = 0;
@@ -449,8 +420,8 @@ static void idpf_vc_xn_push_free(struct idpf_vc_xn_manager *vcxn_mngr,
  * >= @recv_buf.iov_len, but we never overflow @@recv_buf_iov_base). < 0 for
  * error.
  */
-static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
-			       const struct idpf_vc_xn_params *params)
+ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
+			const struct idpf_vc_xn_params *params)
 {
 	const struct kvec *send_buf = &params->send_buf;
 	struct idpf_vc_xn *xn;
@@ -900,7 +871,8 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter)
 			    VIRTCHNL2_CAP_MACFILTER		|
 			    VIRTCHNL2_CAP_SPLITQ_QSCHED		|
 			    VIRTCHNL2_CAP_PROMISC		|
-			    VIRTCHNL2_CAP_LOOPBACK);
+			    VIRTCHNL2_CAP_LOOPBACK		|
+			    VIRTCHNL2_CAP_PTP);
 
 	xn_params.vc_op = VIRTCHNL2_OP_GET_CAPS;
 	xn_params.send_buf.iov_base = &caps;
@@ -3029,6 +3001,11 @@ restart:
 		goto err_intr_req;
 	}
 
+	err = idpf_ptp_init(adapter);
+	if (err)
+		pci_err(adapter->pdev, "PTP init failed, err=%pe\n",
+			ERR_PTR(err));
+
 	idpf_init_avail_queues(adapter);
 
 	/* Skew the delay for init tasks for each function based on fn number
@@ -3091,6 +3068,7 @@ void idpf_vc_core_deinit(struct idpf_adapter *adapter)
 	if (!remove_in_prog)
 		idpf_vc_xn_shutdown(adapter->vcxn_mngr);
 
+	idpf_ptp_release(adapter);
 	idpf_deinit_task(adapter);
 	idpf_intr_rel(adapter);
 
@@ -3158,6 +3136,7 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q)
 	u16 rx_itr[] = {2, 8, 32, 96, 128};
 	struct idpf_rss_data *rss_data;
 	u16 idx = vport->idx;
+	int err;
 
 	vport_config = adapter->vport_config[idx];
 	rss_data = &vport_config->user_config.rss_data;
@@ -3192,6 +3171,18 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q)
 	idpf_vport_alloc_vec_indexes(vport);
 
 	vport->crc_enable = adapter->crc_enable;
+
+	if (!(vport_msg->vport_flags &
+	      cpu_to_le16(VIRTCHNL2_VPORT_UPLINK_PORT)))
+		return;
+
+	err = idpf_ptp_get_vport_tstamps_caps(vport);
+	if (err) {
+		pci_dbg(vport->adapter->pdev, "Tx timestamping not supported\n");
+		return;
+	}
+
+	INIT_WORK(&vport->tstamp_task, idpf_tstamp_task);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
index 83da5d8da56b..3522c1238ea2 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
@@ -4,6 +4,88 @@
 #ifndef _IDPF_VIRTCHNL_H_
 #define _IDPF_VIRTCHNL_H_
 
+#define IDPF_VC_XN_MIN_TIMEOUT_MSEC	2000
+#define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC	(60 * 1000)
+#define IDPF_VC_XN_IDX_M		GENMASK(7, 0)
+#define IDPF_VC_XN_SALT_M		GENMASK(15, 8)
+#define IDPF_VC_XN_RING_LEN		U8_MAX
+
+/**
+ * enum idpf_vc_xn_state - Virtchnl transaction status
+ * @IDPF_VC_XN_IDLE: not expecting a reply, ready to be used
+ * @IDPF_VC_XN_WAITING: expecting a reply, not yet received
+ * @IDPF_VC_XN_COMPLETED_SUCCESS: a reply was expected and received, buffer
+ *				  updated
+ * @IDPF_VC_XN_COMPLETED_FAILED: a reply was expected and received, but there
+ *				 was an error, buffer not updated
+ * @IDPF_VC_XN_SHUTDOWN: transaction object cannot be used, VC torn down
+ * @IDPF_VC_XN_ASYNC: transaction sent asynchronously and doesn't have the
+ *		      return context; a callback may be provided to handle
+ *		      return
+ */
+enum idpf_vc_xn_state {
+	IDPF_VC_XN_IDLE = 1,
+	IDPF_VC_XN_WAITING,
+	IDPF_VC_XN_COMPLETED_SUCCESS,
+	IDPF_VC_XN_COMPLETED_FAILED,
+	IDPF_VC_XN_SHUTDOWN,
+	IDPF_VC_XN_ASYNC,
+};
+
+struct idpf_vc_xn;
+/* Callback for asynchronous messages */
+typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *,
+			    const struct idpf_ctlq_msg *);
+
+/**
+ * struct idpf_vc_xn - Data structure representing virtchnl transactions
+ * @completed: virtchnl event loop uses that to signal when a reply is
+ *	       available, uses kernel completion API
+ * @state: virtchnl event loop stores the data below, protected by the
+ *	   completion's lock.
+ * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be
+ *	      truncated on its way to the receiver thread according to
+ *	      reply_buf.iov_len.
+ * @reply: Reference to the buffer(s) where the reply data should be written
+ *	   to. May be 0-length (then NULL address permitted) if the reply data
+ *	   should be ignored.
+ * @async_handler: if sent asynchronously, a callback can be provided to handle
+ *		   the reply when it's received
+ * @vc_op: corresponding opcode sent with this transaction
+ * @idx: index used as retrieval on reply receive, used for cookie
+ * @salt: changed every message to make unique, used for cookie
+ */
+struct idpf_vc_xn {
+	struct completion completed;
+	enum idpf_vc_xn_state state;
+	size_t reply_sz;
+	struct kvec reply;
+	async_vc_cb async_handler;
+	u32 vc_op;
+	u8 idx;
+	u8 salt;
+};
+
+/**
+ * struct idpf_vc_xn_params - Parameters for executing transaction
+ * @send_buf: kvec for send buffer
+ * @recv_buf: kvec for recv buffer, may be NULL, must then have zero length
+ * @timeout_ms: timeout to wait for reply
+ * @async: send message asynchronously, will not wait on completion
+ * @async_handler: If sent asynchronously, optional callback handler. The user
+ *		   must be careful when using async handlers as the memory for
+ *		   the recv_buf _cannot_ be on stack if this is async.
+ * @vc_op: virtchnl op to send
+ */
+struct idpf_vc_xn_params {
+	struct kvec send_buf;
+	struct kvec recv_buf;
+	int timeout_ms;
+	bool async;
+	async_vc_cb async_handler;
+	u32 vc_op;
+};
+
 struct idpf_adapter;
 struct idpf_netdev_priv;
 struct idpf_vec_regs;
@@ -11,6 +93,8 @@ struct idpf_vport;
 struct idpf_vport_max_q;
 struct idpf_vport_user_config_data;
 
+ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
+			const struct idpf_vc_xn_params *params);
 int idpf_init_dflt_mbx(struct idpf_adapter *adapter);
 void idpf_deinit_dflt_mbx(struct idpf_adapter *adapter);
 int idpf_vc_core_init(struct idpf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
new file mode 100644
index 000000000000..bdcc54a5fb56
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
@@ -0,0 +1,615 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation */
+
+#include "idpf.h"
+#include "idpf_ptp.h"
+#include "idpf_virtchnl.h"
+
+/**
+ * idpf_ptp_get_caps - Send virtchnl get ptp capabilities message
+ * @adapter: Driver specific private structure
+ *
+ * Send virtchnl get PTP capabilities message.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int idpf_ptp_get_caps(struct idpf_adapter *adapter)
+{
+	struct virtchnl2_ptp_get_caps *recv_ptp_caps_msg __free(kfree) = NULL;
+	struct virtchnl2_ptp_get_caps send_ptp_caps_msg = {
+		.caps = cpu_to_le32(VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME |
+				    VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB |
+				    VIRTCHNL2_CAP_PTP_GET_CROSS_TIME |
+				    VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB |
+				    VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB |
+				    VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB)
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_CAPS,
+		.send_buf.iov_base = &send_ptp_caps_msg,
+		.send_buf.iov_len = sizeof(send_ptp_caps_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	struct virtchnl2_ptp_clk_adj_reg_offsets clk_adj_offsets;
+	struct virtchnl2_ptp_clk_reg_offsets clock_offsets;
+	struct idpf_ptp_secondary_mbx *scnd_mbx;
+	struct idpf_ptp *ptp = adapter->ptp;
+	enum idpf_ptp_access access_type;
+	u32 temp_offset;
+	int reply_sz;
+
+	recv_ptp_caps_msg = kzalloc(sizeof(struct virtchnl2_ptp_get_caps),
+				    GFP_KERNEL);
+	if (!recv_ptp_caps_msg)
+		return -ENOMEM;
+
+	xn_params.recv_buf.iov_base = recv_ptp_caps_msg;
+	xn_params.recv_buf.iov_len = sizeof(*recv_ptp_caps_msg);
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	else if (reply_sz != sizeof(*recv_ptp_caps_msg))
+		return -EIO;
+
+	ptp->caps = le32_to_cpu(recv_ptp_caps_msg->caps);
+	ptp->base_incval = le64_to_cpu(recv_ptp_caps_msg->base_incval);
+	ptp->max_adj = le32_to_cpu(recv_ptp_caps_msg->max_adj);
+
+	scnd_mbx = &ptp->secondary_mbx;
+	scnd_mbx->peer_mbx_q_id = le16_to_cpu(recv_ptp_caps_msg->peer_mbx_q_id);
+
+	/* if the ptp_mb_q_id holds invalid value (0xffff), the secondary
+	 * mailbox is not supported.
+	 */
+	scnd_mbx->valid = scnd_mbx->peer_mbx_q_id != 0xffff;
+	if (scnd_mbx->valid)
+		scnd_mbx->peer_id = recv_ptp_caps_msg->peer_id;
+
+	/* Determine the access type for the PTP features */
+	idpf_ptp_get_features_access(adapter);
+
+	access_type = ptp->get_dev_clk_time_access;
+	if (access_type != IDPF_PTP_DIRECT)
+		goto discipline_clock;
+
+	clock_offsets = recv_ptp_caps_msg->clk_offsets;
+
+	temp_offset = le32_to_cpu(clock_offsets.dev_clk_ns_l);
+	ptp->dev_clk_regs.dev_clk_ns_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.dev_clk_ns_h);
+	ptp->dev_clk_regs.dev_clk_ns_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.phy_clk_ns_l);
+	ptp->dev_clk_regs.phy_clk_ns_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.phy_clk_ns_h);
+	ptp->dev_clk_regs.phy_clk_ns_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.cmd_sync_trigger);
+	ptp->dev_clk_regs.cmd_sync = idpf_get_reg_addr(adapter, temp_offset);
+
+discipline_clock:
+	access_type = ptp->adj_dev_clk_time_access;
+	if (access_type != IDPF_PTP_DIRECT)
+		return 0;
+
+	clk_adj_offsets = recv_ptp_caps_msg->clk_adj_offsets;
+
+	/* Device clock offsets */
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_cmd_type);
+	ptp->dev_clk_regs.cmd = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_incval_l);
+	ptp->dev_clk_regs.incval_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_incval_h);
+	ptp->dev_clk_regs.incval_h = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_shadj_l);
+	ptp->dev_clk_regs.shadj_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_shadj_h);
+	ptp->dev_clk_regs.shadj_h = idpf_get_reg_addr(adapter, temp_offset);
+
+	/* PHY clock offsets */
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_cmd_type);
+	ptp->dev_clk_regs.phy_cmd = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_incval_l);
+	ptp->dev_clk_regs.phy_incval_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_incval_h);
+	ptp->dev_clk_regs.phy_incval_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_shadj_l);
+	ptp->dev_clk_regs.phy_shadj_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_shadj_h);
+	ptp->dev_clk_regs.phy_shadj_h = idpf_get_reg_addr(adapter, temp_offset);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_dev_clk_time - Send virtchnl get device clk time message
+ * @adapter: Driver specific private structure
+ * @dev_clk_time: Pointer to the device clock structure where the value is set
+ *
+ * Send virtchnl get time message to get the time of the clock.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			      struct idpf_ptp_dev_timers *dev_clk_time)
+{
+	struct virtchnl2_ptp_get_dev_clk_time get_dev_clk_time_msg;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME,
+		.send_buf.iov_base = &get_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(get_dev_clk_time_msg),
+		.recv_buf.iov_base = &get_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(get_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+	u64 dev_time;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(get_dev_clk_time_msg))
+		return -EIO;
+
+	dev_time = le64_to_cpu(get_dev_clk_time_msg.dev_time_ns);
+	dev_clk_time->dev_clk_time_ns = dev_time;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_set_dev_clk_time - Send virtchnl set device time message
+ * @adapter: Driver specific private structure
+ * @time: New time value
+ *
+ * Send virtchnl set time message to set the time of the clock.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time)
+{
+	struct virtchnl2_ptp_set_dev_clk_time set_dev_clk_time_msg = {
+		.dev_time_ns = cpu_to_le64(time),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME,
+		.send_buf.iov_base = &set_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(set_dev_clk_time_msg),
+		.recv_buf.iov_base = &set_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(set_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(set_dev_clk_time_msg))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adj_dev_clk_time - Send virtchnl adj device clock time message
+ * @adapter: Driver specific private structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Send virtchnl adj time message to adjust the clock by the indicated delta.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta)
+{
+	struct virtchnl2_ptp_adj_dev_clk_time adj_dev_clk_time_msg = {
+		.delta = cpu_to_le64(delta),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME,
+		.send_buf.iov_base = &adj_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(adj_dev_clk_time_msg),
+		.recv_buf.iov_base = &adj_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(adj_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(adj_dev_clk_time_msg))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adj_dev_clk_fine - Send virtchnl adj time message
+ * @adapter: Driver specific private structure
+ * @incval: Source timer increment value per clock cycle
+ *
+ * Send virtchnl adj fine message to adjust the frequency of the clock by
+ * incval.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval)
+{
+	struct virtchnl2_ptp_adj_dev_clk_fine adj_dev_clk_fine_msg = {
+		.incval = cpu_to_le64(incval),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE,
+		.send_buf.iov_base = &adj_dev_clk_fine_msg,
+		.send_buf.iov_len = sizeof(adj_dev_clk_fine_msg),
+		.recv_buf.iov_base = &adj_dev_clk_fine_msg,
+		.recv_buf.iov_len = sizeof(adj_dev_clk_fine_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(adj_dev_clk_fine_msg))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_vport_tstamps_caps - Send virtchnl to get tstamps caps for vport
+ * @vport: Virtual port structure
+ *
+ * Send virtchnl get vport tstamps caps message to receive the set of tstamp
+ * capabilities per vport.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_caps send_tx_tstamp_caps;
+	struct virtchnl2_ptp_get_vport_tx_tstamp_caps *rcv_tx_tstamp_caps;
+	struct virtchnl2_ptp_tx_tstamp_latch_caps tx_tstamp_latch_caps;
+	struct idpf_ptp_vport_tx_tstamp_caps *tstamp_caps;
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp, *tmp;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS,
+		.send_buf.iov_base = &send_tx_tstamp_caps,
+		.send_buf.iov_len = sizeof(send_tx_tstamp_caps),
+		.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN,
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	enum idpf_ptp_access tstamp_access, get_dev_clk_access;
+	struct idpf_ptp *ptp = vport->adapter->ptp;
+	struct list_head *head;
+	int err = 0, reply_sz;
+	u16 num_latches;
+	u32 size;
+
+	if (!ptp)
+		return -EOPNOTSUPP;
+
+	tstamp_access = ptp->tx_tstamp_access;
+	get_dev_clk_access = ptp->get_dev_clk_time_access;
+	if (tstamp_access == IDPF_PTP_NONE ||
+	    get_dev_clk_access == IDPF_PTP_NONE)
+		return -EOPNOTSUPP;
+
+	rcv_tx_tstamp_caps = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL);
+	if (!rcv_tx_tstamp_caps)
+		return -ENOMEM;
+
+	send_tx_tstamp_caps.vport_id = cpu_to_le32(vport->vport_id);
+	xn_params.recv_buf.iov_base = rcv_tx_tstamp_caps;
+
+	reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
+	if (reply_sz < 0) {
+		err = reply_sz;
+		goto get_tstamp_caps_out;
+	}
+
+	num_latches = le16_to_cpu(rcv_tx_tstamp_caps->num_latches);
+	size = struct_size(rcv_tx_tstamp_caps, tstamp_latches, num_latches);
+	if (reply_sz != size) {
+		err = -EIO;
+		goto get_tstamp_caps_out;
+	}
+
+	size = struct_size(tstamp_caps, tx_tstamp_status, num_latches);
+	tstamp_caps = kzalloc(size, GFP_KERNEL);
+	if (!tstamp_caps) {
+		err = -ENOMEM;
+		goto get_tstamp_caps_out;
+	}
+
+	tstamp_caps->access = true;
+	tstamp_caps->num_entries = num_latches;
+
+	INIT_LIST_HEAD(&tstamp_caps->latches_in_use);
+	INIT_LIST_HEAD(&tstamp_caps->latches_free);
+
+	spin_lock_init(&tstamp_caps->latches_lock);
+	spin_lock_init(&tstamp_caps->status_lock);
+
+	tstamp_caps->tstamp_ns_lo_bit = rcv_tx_tstamp_caps->tstamp_ns_lo_bit;
+
+	for (u16 i = 0; i < tstamp_caps->num_entries; i++) {
+		__le32 offset_l, offset_h;
+
+		ptp_tx_tstamp = kzalloc(sizeof(*ptp_tx_tstamp), GFP_KERNEL);
+		if (!ptp_tx_tstamp) {
+			err = -ENOMEM;
+			goto err_free_ptp_tx_stamp_list;
+		}
+
+		tx_tstamp_latch_caps = rcv_tx_tstamp_caps->tstamp_latches[i];
+
+		if (tstamp_access != IDPF_PTP_DIRECT)
+			goto skip_offsets;
+
+		offset_l = tx_tstamp_latch_caps.tx_latch_reg_offset_l;
+		offset_h = tx_tstamp_latch_caps.tx_latch_reg_offset_h;
+		ptp_tx_tstamp->tx_latch_reg_offset_l = le32_to_cpu(offset_l);
+		ptp_tx_tstamp->tx_latch_reg_offset_h = le32_to_cpu(offset_h);
+
+skip_offsets:
+		ptp_tx_tstamp->idx = tx_tstamp_latch_caps.index;
+
+		list_add(&ptp_tx_tstamp->list_member,
+			 &tstamp_caps->latches_free);
+
+		tstamp_caps->tx_tstamp_status[i].state = IDPF_PTP_FREE;
+	}
+
+	vport->tx_tstamp_caps = tstamp_caps;
+	kfree(rcv_tx_tstamp_caps);
+
+	return 0;
+
+err_free_ptp_tx_stamp_list:
+	head = &tstamp_caps->latches_free;
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		list_del(&ptp_tx_tstamp->list_member);
+		kfree(ptp_tx_tstamp);
+	}
+
+	kfree(tstamp_caps);
+get_tstamp_caps_out:
+	kfree(rcv_tx_tstamp_caps);
+
+	return err;
+}
+
+/**
+ * idpf_ptp_update_tstamp_tracker - Update the Tx timestamp tracker based on
+ *				    the skb compatibility.
+ * @caps: Tx timestamp capabilities that monitor the latch status
+ * @skb: skb for which the tstamp value is returned through virtchnl message
+ * @current_state: Current state of the Tx timestamp latch
+ * @expected_state: Expected state of the Tx timestamp latch
+ *
+ * Find a proper skb tracker for which the Tx timestamp is received and change
+ * the state to expected value.
+ *
+ * Return: true if the tracker has been found and updated, false otherwise.
+ */
+static bool
+idpf_ptp_update_tstamp_tracker(struct idpf_ptp_vport_tx_tstamp_caps *caps,
+			       struct sk_buff *skb,
+			       enum idpf_ptp_tx_tstamp_state current_state,
+			       enum idpf_ptp_tx_tstamp_state expected_state)
+{
+	bool updated = false;
+
+	spin_lock(&caps->status_lock);
+	for (u16 i = 0; i < caps->num_entries; i++) {
+		struct idpf_ptp_tx_tstamp_status *status;
+
+		status = &caps->tx_tstamp_status[i];
+
+		if (skb == status->skb && status->state == current_state) {
+			status->state = expected_state;
+			updated = true;
+			break;
+		}
+	}
+	spin_unlock(&caps->status_lock);
+
+	return updated;
+}
+
+/**
+ * idpf_ptp_get_tstamp_value - Get the Tx timestamp value and provide it
+ *			       back to the skb.
+ * @vport: Virtual port structure
+ * @tstamp_latch: Tx timestamp latch structure fulfilled by the Control Plane
+ * @ptp_tx_tstamp: Tx timestamp latch to add to the free list
+ *
+ * Read the value of the Tx timestamp for a given latch received from the
+ * Control Plane, extend it to 64 bit and provide back to the skb.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int
+idpf_ptp_get_tstamp_value(struct idpf_vport *vport,
+			  struct virtchnl2_ptp_tx_tstamp_latch *tstamp_latch,
+			  struct idpf_ptp_tx_tstamp *ptp_tx_tstamp)
+{
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct skb_shared_hwtstamps shhwtstamps;
+	bool state_upd = false;
+	u8 tstamp_ns_lo_bit;
+	u64 tstamp;
+
+	tx_tstamp_caps = vport->tx_tstamp_caps;
+	tstamp_ns_lo_bit = tx_tstamp_caps->tstamp_ns_lo_bit;
+
+	ptp_tx_tstamp->tstamp = le64_to_cpu(tstamp_latch->tstamp);
+	ptp_tx_tstamp->tstamp >>= tstamp_ns_lo_bit;
+
+	state_upd = idpf_ptp_update_tstamp_tracker(tx_tstamp_caps,
+						   ptp_tx_tstamp->skb,
+						   IDPF_PTP_READ_VALUE,
+						   IDPF_PTP_FREE);
+	if (!state_upd)
+		return -EINVAL;
+
+	tstamp = idpf_ptp_extend_ts(vport, ptp_tx_tstamp->tstamp);
+	shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
+	skb_tstamp_tx(ptp_tx_tstamp->skb, &shhwtstamps);
+	consume_skb(ptp_tx_tstamp->skb);
+
+	list_add(&ptp_tx_tstamp->list_member,
+		 &tx_tstamp_caps->latches_free);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_tx_tstamp_async_handler - Async callback for getting Tx tstamps
+ * @adapter: Driver specific private structure
+ * @xn: transaction for message
+ * @ctlq_msg: received message
+ *
+ * Read the tstamps Tx tstamp values from a received message and put them
+ * directly to the skb. The number of timestamps to read is specified by
+ * the virtchnl message.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int
+idpf_ptp_get_tx_tstamp_async_handler(struct idpf_adapter *adapter,
+				     struct idpf_vc_xn *xn,
+				     const struct idpf_ctlq_msg *ctlq_msg)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_latches *recv_tx_tstamp_msg;
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct virtchnl2_ptp_tx_tstamp_latch tstamp_latch;
+	struct idpf_ptp_tx_tstamp *tx_tstamp, *tmp;
+	struct idpf_vport *tstamp_vport = NULL;
+	struct list_head *head;
+	u16 num_latches;
+	u32 vport_id;
+	int err = 0;
+
+	recv_tx_tstamp_msg = ctlq_msg->ctx.indirect.payload->va;
+	vport_id = le32_to_cpu(recv_tx_tstamp_msg->vport_id);
+
+	idpf_for_each_vport(adapter, vport) {
+		if (!vport)
+			continue;
+
+		if (vport->vport_id == vport_id) {
+			tstamp_vport = vport;
+			break;
+		}
+	}
+
+	if (!tstamp_vport || !tstamp_vport->tx_tstamp_caps)
+		return -EINVAL;
+
+	tx_tstamp_caps = tstamp_vport->tx_tstamp_caps;
+	num_latches = le16_to_cpu(recv_tx_tstamp_msg->num_latches);
+
+	spin_lock_bh(&tx_tstamp_caps->latches_lock);
+	head = &tx_tstamp_caps->latches_in_use;
+
+	for (u16 i = 0; i < num_latches; i++) {
+		tstamp_latch = recv_tx_tstamp_msg->tstamp_latches[i];
+
+		if (!tstamp_latch.valid)
+			continue;
+
+		if (list_empty(head)) {
+			err = -ENOBUFS;
+			goto unlock;
+		}
+
+		list_for_each_entry_safe(tx_tstamp, tmp, head, list_member) {
+			if (tstamp_latch.index == tx_tstamp->idx) {
+				list_del(&tx_tstamp->list_member);
+				err = idpf_ptp_get_tstamp_value(tstamp_vport,
+								&tstamp_latch,
+								tx_tstamp);
+				if (err)
+					goto unlock;
+
+				break;
+			}
+		}
+	}
+
+unlock:
+	spin_unlock_bh(&tx_tstamp_caps->latches_lock);
+
+	return err;
+}
+
+/**
+ * idpf_ptp_get_tx_tstamp - Send virtchnl get Tx timestamp latches message
+ * @vport: Virtual port structure
+ *
+ * Send virtchnl get Tx tstamp message to read the value of the HW timestamp.
+ * The message contains a list of indexes set in the Tx descriptors.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_latches *send_tx_tstamp_msg;
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP,
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+		.async = true,
+		.async_handler = idpf_ptp_get_tx_tstamp_async_handler,
+	};
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp;
+	int reply_sz, size, msg_size;
+	struct list_head *head;
+	bool state_upd;
+	u16 id = 0;
+
+	tx_tstamp_caps = vport->tx_tstamp_caps;
+	head = &tx_tstamp_caps->latches_in_use;
+
+	size = struct_size(send_tx_tstamp_msg, tstamp_latches,
+			   tx_tstamp_caps->num_entries);
+	send_tx_tstamp_msg = kzalloc(size, GFP_KERNEL);
+	if (!send_tx_tstamp_msg)
+		return -ENOMEM;
+
+	spin_lock_bh(&tx_tstamp_caps->latches_lock);
+	list_for_each_entry(ptp_tx_tstamp, head, list_member) {
+		u8 idx;
+
+		state_upd = idpf_ptp_update_tstamp_tracker(tx_tstamp_caps,
+							   ptp_tx_tstamp->skb,
+							   IDPF_PTP_REQUEST,
+							   IDPF_PTP_READ_VALUE);
+		if (!state_upd)
+			continue;
+
+		idx = ptp_tx_tstamp->idx;
+		send_tx_tstamp_msg->tstamp_latches[id].index = idx;
+		id++;
+	}
+	spin_unlock_bh(&tx_tstamp_caps->latches_lock);
+
+	msg_size = struct_size(send_tx_tstamp_msg, tstamp_latches, id);
+	send_tx_tstamp_msg->vport_id = cpu_to_le32(vport->vport_id);
+	send_tx_tstamp_msg->num_latches = cpu_to_le16(id);
+	xn_params.send_buf.iov_base = send_tx_tstamp_msg;
+	xn_params.send_buf.iov_len = msg_size;
+
+	reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
+	kfree(send_tx_tstamp_msg);
+
+	return min(reply_sz, 0);
+}
diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index 63deb120359c..11b8f6f05799 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -68,6 +68,16 @@ enum virtchnl2_op {
 	VIRTCHNL2_OP_ADD_MAC_ADDR		= 535,
 	VIRTCHNL2_OP_DEL_MAC_ADDR		= 536,
 	VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE	= 537,
+
+	/* TimeSync opcodes */
+	VIRTCHNL2_OP_PTP_GET_CAPS			= 541,
+	VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP		= 542,
+	VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME		= 543,
+	VIRTCHNL2_OP_PTP_GET_CROSS_TIME			= 544,
+	VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME		= 545,
+	VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE		= 546,
+	VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME		= 547,
+	VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS	= 548,
 };
 
 /**
@@ -560,6 +570,14 @@ struct virtchnl2_queue_reg_chunks {
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks);
 
 /**
+ * enum virtchnl2_vport_flags - Vport flags that indicate vport capabilities.
+ * @VIRTCHNL2_VPORT_UPLINK_PORT: Representatives of underlying physical ports
+ */
+enum virtchnl2_vport_flags {
+	VIRTCHNL2_VPORT_UPLINK_PORT	= BIT(0),
+};
+
+/**
  * struct virtchnl2_create_vport - Create vport config info.
  * @vport_type: See enum virtchnl2_vport_type.
  * @txq_model: See virtchnl2_queue_model.
@@ -577,7 +595,7 @@ VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks);
  * @max_mtu: Max MTU. CP populates this field on response.
  * @vport_id: Vport id. CP populates this field on response.
  * @default_mac_addr: Default MAC address.
- * @pad: Padding.
+ * @vport_flags: See enum virtchnl2_vport_flags.
  * @rx_desc_ids: See VIRTCHNL2_RX_DESC_IDS definitions.
  * @tx_desc_ids: See VIRTCHNL2_TX_DESC_IDS definitions.
  * @pad1: Padding.
@@ -610,7 +628,7 @@ struct virtchnl2_create_vport {
 	__le16 max_mtu;
 	__le32 vport_id;
 	u8 default_mac_addr[ETH_ALEN];
-	__le16 pad;
+	__le16 vport_flags;
 	__le64 rx_desc_ids;
 	__le64 tx_desc_ids;
 	u8 pad1[72];
@@ -1270,4 +1288,296 @@ struct virtchnl2_promisc_info {
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_promisc_info);
 
+/**
+ * enum virtchnl2_ptp_caps - PTP capabilities
+ * @VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME: direct access to get the time of
+ *					   device clock
+ * @VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB: mailbox access to get the time of
+ *					      device clock
+ * @VIRTCHNL2_CAP_PTP_GET_CROSS_TIME: direct access to cross timestamp
+ * @VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB: mailbox access to cross timestamp
+ * @VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME: direct access to set the time of
+ *					   device clock
+ * @VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB: mailbox access to set the time of
+ *					      device clock
+ * @VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK: direct access to adjust the time of device
+ *				      clock
+ * @VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB: mailbox access to adjust the time of
+ *					 device clock
+ * @VIRTCHNL2_CAP_PTP_TX_TSTAMPS: direct access to the Tx timestamping
+ * @VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB: mailbox access to the Tx timestamping
+ *
+ * PF/VF negotiates a set of supported PTP capabilities with the Control Plane.
+ * There are two access methods - mailbox (_MB) and direct.
+ * PTP capabilities enables Main Timer operations: get/set/adjust Main Timer,
+ * cross timestamping and the Tx timestamping.
+ */
+enum virtchnl2_ptp_caps {
+	VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME		= BIT(0),
+	VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB	= BIT(1),
+	VIRTCHNL2_CAP_PTP_GET_CROSS_TIME		= BIT(2),
+	VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB		= BIT(3),
+	VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME		= BIT(4),
+	VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB	= BIT(5),
+	VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK		= BIT(6),
+	VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB		= BIT(7),
+	VIRTCHNL2_CAP_PTP_TX_TSTAMPS			= BIT(8),
+	VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB			= BIT(9),
+};
+
+/**
+ * struct virtchnl2_ptp_clk_reg_offsets - Offsets of device and PHY clocks
+ *					  registers.
+ * @dev_clk_ns_l: Device clock low register offset
+ * @dev_clk_ns_h: Device clock high register offset
+ * @phy_clk_ns_l: PHY clock low register offset
+ * @phy_clk_ns_h: PHY clock high register offset
+ * @cmd_sync_trigger: The command sync trigger register offset
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_clk_reg_offsets {
+	__le32 dev_clk_ns_l;
+	__le32 dev_clk_ns_h;
+	__le32 phy_clk_ns_l;
+	__le32 phy_clk_ns_h;
+	__le32 cmd_sync_trigger;
+	u8 pad[4];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(24, virtchnl2_ptp_clk_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_cross_time_reg_offsets - Offsets of the device cross
+ *						 time registers.
+ * @sys_time_ns_l: System time low register offset
+ * @sys_time_ns_h: System time high register offset
+ * @cmd_sync_trigger: The command sync trigger register offset
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_cross_time_reg_offsets {
+	__le32 sys_time_ns_l;
+	__le32 sys_time_ns_h;
+	__le32 cmd_sync_trigger;
+	u8 pad[4];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_cross_time_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_clk_adj_reg_offsets - Offsets of device and PHY clocks
+ *					      adjustments registers.
+ * @dev_clk_cmd_type: Device clock command type register offset
+ * @dev_clk_incval_l: Device clock increment value low register offset
+ * @dev_clk_incval_h: Device clock increment value high registers offset
+ * @dev_clk_shadj_l: Device clock shadow adjust low register offset
+ * @dev_clk_shadj_h: Device clock shadow adjust high register offset
+ * @phy_clk_cmd_type: PHY timer command type register offset
+ * @phy_clk_incval_l: PHY timer increment value low register offset
+ * @phy_clk_incval_h: PHY timer increment value high register offset
+ * @phy_clk_shadj_l: PHY timer shadow adjust low register offset
+ * @phy_clk_shadj_h: PHY timer shadow adjust high register offset
+ */
+struct virtchnl2_ptp_clk_adj_reg_offsets {
+	__le32 dev_clk_cmd_type;
+	__le32 dev_clk_incval_l;
+	__le32 dev_clk_incval_h;
+	__le32 dev_clk_shadj_l;
+	__le32 dev_clk_shadj_h;
+	__le32 phy_clk_cmd_type;
+	__le32 phy_clk_incval_l;
+	__le32 phy_clk_incval_h;
+	__le32 phy_clk_shadj_l;
+	__le32 phy_clk_shadj_h;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(40, virtchnl2_ptp_clk_adj_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_tx_tstamp_latch_caps - PTP Tx timestamp latch
+ *					       capabilities.
+ * @tx_latch_reg_offset_l: Tx timestamp latch low register offset
+ * @tx_latch_reg_offset_h: Tx timestamp latch high register offset
+ * @index: Latch index provided to the Tx descriptor
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_tx_tstamp_latch_caps {
+	__le32 tx_latch_reg_offset_l;
+	__le32 tx_latch_reg_offset_h;
+	u8 index;
+	u8 pad[7];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_tx_tstamp_latch_caps);
+
+/**
+ * struct virtchnl2_ptp_get_vport_tx_tstamp_caps - Structure that defines Tx
+ *						   tstamp entries.
+ * @vport_id: Vport number
+ * @num_latches: Total number of latches
+ * @tstamp_ns_lo_bit: First bit for nanosecond part of the timestamp
+ * @tstamp_ns_hi_bit: Last bit for nanosecond part of the timestamp
+ * @pad: Padding for future tstamp granularity extensions
+ * @tstamp_latches: Capabilities of Tx timestamp entries
+ *
+ * PF/VF sends this message to negotiate the Tx timestamp latches for each
+ * Vport.
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS.
+ */
+struct virtchnl2_ptp_get_vport_tx_tstamp_caps {
+	__le32 vport_id;
+	__le16 num_latches;
+	u8 tstamp_ns_lo_bit;
+	u8 tstamp_ns_hi_bit;
+	u8 pad[8];
+
+	struct virtchnl2_ptp_tx_tstamp_latch_caps tstamp_latches[]
+						  __counted_by_le(num_latches);
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_vport_tx_tstamp_caps);
+
+/**
+ * struct virtchnl2_ptp_get_caps - Get PTP capabilities
+ * @caps: PTP capability bitmap. See enum virtchnl2_ptp_caps
+ * @max_adj: The maximum possible frequency adjustment
+ * @base_incval: The default timer increment value
+ * @peer_mbx_q_id: ID of the PTP Device Control daemon queue
+ * @peer_id: Peer ID for PTP Device Control daemon
+ * @secondary_mbx: Indicates to the driver that it should create a secondary
+ *		   mailbox to inetract with control plane for PTP
+ * @pad: Padding for future extensions
+ * @clk_offsets: Main timer and PHY registers offsets
+ * @cross_time_offsets: Cross time registers offsets
+ * @clk_adj_offsets: Offsets needed to adjust the PHY and the main timer
+ *
+ * PF/VF sends this message to negotiate PTP capabilities. CP updates bitmap
+ * with supported features and fulfills appropriate structures.
+ * If HW uses primary MBX for PTP: secondary_mbx is set to false.
+ * If HW uses secondary MBX for PTP: secondary_mbx is set to true.
+ *	Control plane has 2 MBX and the driver has 1 MBX, send to peer
+ *	driver may be used to send a message using valid ptp_peer_mb_q_id and
+ *	ptp_peer_id.
+ * If HW does not use send to peer driver: secondary_mbx is no care field and
+ * peer_mbx_q_id holds invalid value (0xFFFF).
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_CAPS.
+ */
+struct virtchnl2_ptp_get_caps {
+	__le32 caps;
+	__le32 max_adj;
+	__le64 base_incval;
+	__le16 peer_mbx_q_id;
+	u8 peer_id;
+	u8 secondary_mbx;
+	u8 pad[4];
+
+	struct virtchnl2_ptp_clk_reg_offsets clk_offsets;
+	struct virtchnl2_ptp_cross_time_reg_offsets cross_time_offsets;
+	struct virtchnl2_ptp_clk_adj_reg_offsets clk_adj_offsets;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(104, virtchnl2_ptp_get_caps);
+
+/**
+ * struct virtchnl2_ptp_tx_tstamp_latch - Structure that describes tx tstamp
+ *					  values, index and validity.
+ * @tstamp: Timestamp value
+ * @index: Timestamp index from which the value is read
+ * @valid: Timestamp validity
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_tx_tstamp_latch {
+	__le64 tstamp;
+	u8 index;
+	u8 valid;
+	u8 pad[6];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_tx_tstamp_latch);
+
+/**
+ * struct virtchnl2_ptp_get_vport_tx_tstamp_latches - Tx timestamp latches
+ *						      associated with the vport.
+ * @vport_id: Number of vport that requests the timestamp
+ * @num_latches: Number of latches
+ * @get_devtime_with_txtstmp: Flag to request device time along with Tx timestamp
+ * @pad: Padding for future extensions
+ * @device_time: device time if get_devtime_with_txtstmp was set in request
+ * @tstamp_latches: PTP TX timestamp latch
+ *
+ * PF/VF sends this message to receive a specified number of timestamps
+ * entries.
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP.
+ */
+struct virtchnl2_ptp_get_vport_tx_tstamp_latches {
+	__le32 vport_id;
+	__le16 num_latches;
+	u8 get_devtime_with_txtstmp;
+	u8 pad[1];
+	__le64 device_time;
+
+	struct virtchnl2_ptp_tx_tstamp_latch tstamp_latches[]
+					     __counted_by_le(num_latches);
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_vport_tx_tstamp_latches);
+
+/**
+ * struct virtchnl2_ptp_get_dev_clk_time - Associated with message
+ *					   VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME.
+ * @dev_time_ns: Device clock time value in nanoseconds
+ *
+ * PF/VF sends this message to receive the time from the main timer.
+ */
+struct virtchnl2_ptp_get_dev_clk_time {
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_get_dev_clk_time);
+
+/**
+ * struct virtchnl2_ptp_get_cross_time: Associated with message
+ *					VIRTCHNL2_OP_PTP_GET_CROSS_TIME.
+ * @sys_time_ns: System counter value expressed in nanoseconds, read
+ *		 synchronously with device time
+ * @dev_time_ns: Device clock time value expressed in nanoseconds
+ *
+ * PF/VF sends this message to receive the cross time.
+ */
+struct virtchnl2_ptp_get_cross_time {
+	__le64 sys_time_ns;
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_cross_time);
+
+/**
+ * struct virtchnl2_ptp_set_dev_clk_time: Associated with message
+ *					  VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME.
+ * @dev_time_ns: Device time value expressed in nanoseconds to set
+ *
+ * PF/VF sends this message to set the time of the main timer.
+ */
+struct virtchnl2_ptp_set_dev_clk_time {
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_set_dev_clk_time);
+
+/**
+ * struct virtchnl2_ptp_adj_dev_clk_fine: Associated with message
+ *					  VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE.
+ * @incval: Source timer increment value per clock cycle
+ *
+ * PF/VF sends this message to adjust the frequency of the main timer by the
+ * indicated increment value.
+ */
+struct virtchnl2_ptp_adj_dev_clk_fine {
+	__le64 incval;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_adj_dev_clk_fine);
+
+/**
+ * struct virtchnl2_ptp_adj_dev_clk_time: Associated with message
+ *					  VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME.
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * PF/VF sends this message to adjust the time of the main timer by the delta.
+ */
+struct virtchnl2_ptp_adj_dev_clk_time {
+	__le64 delta;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_adj_dev_clk_time);
+
 #endif /* _VIRTCHNL_2_H_ */
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 02f340280d20..f34ead8243e9 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -391,7 +391,8 @@ enum e1000_ring_flags_t {
 	IGB_RING_FLAG_RX_LB_VLAN_BSWAP,
 	IGB_RING_FLAG_TX_CTX_IDX,
 	IGB_RING_FLAG_TX_DETECT_HANG,
-	IGB_RING_FLAG_TX_DISABLED
+	IGB_RING_FLAG_TX_DISABLED,
+	IGB_RING_FLAG_RX_ALLOC_FAILED,
 };
 
 #define ring_uses_large_buffer(ring) \
@@ -722,6 +723,8 @@ enum igb_boards {
 
 extern char igb_driver_name[];
 
+void igb_set_queue_napi(struct igb_adapter *adapter, int q_idx,
+			struct napi_struct *napi);
 int igb_xmit_xdp_ring(struct igb_adapter *adapter,
 		      struct igb_ring *ring,
 		      struct xdp_frame *xdpf);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index c646c71915f0..9e9a5900e6e5 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -947,6 +947,9 @@ static int igb_request_msix(struct igb_adapter *adapter)
 				  q_vector);
 		if (err)
 			goto err_free;
+
+		netif_napi_set_irq(&q_vector->napi,
+				   adapter->msix_entries[vector].vector);
 	}
 
 	igb_configure_msix(adapter);
@@ -1194,7 +1197,8 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 		return -ENOMEM;
 
 	/* initialize NAPI */
-	netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll);
+	netif_napi_add_config(adapter->netdev, &q_vector->napi, igb_poll,
+			      v_idx);
 
 	/* tie q_vector and adapter together */
 	adapter->q_vector[v_idx] = q_vector;
@@ -2096,6 +2100,22 @@ static void igb_check_swap_media(struct igb_adapter *adapter)
 	wr32(E1000_CTRL_EXT, ctrl_ext);
 }
 
+void igb_set_queue_napi(struct igb_adapter *adapter, int vector,
+			struct napi_struct *napi)
+{
+	struct igb_q_vector *q_vector = adapter->q_vector[vector];
+
+	if (q_vector->rx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->rx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_RX, napi);
+
+	if (q_vector->tx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->tx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_TX, napi);
+}
+
 /**
  *  igb_up - Open the interface and prepare it to handle traffic
  *  @adapter: board private structure
@@ -2103,6 +2123,7 @@ static void igb_check_swap_media(struct igb_adapter *adapter)
 int igb_up(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int i;
 
 	/* hardware has been reset, we need to reload some things */
@@ -2110,8 +2131,11 @@ int igb_up(struct igb_adapter *adapter)
 
 	clear_bit(__IGB_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&(adapter->q_vector[i]->napi));
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igb_set_queue_napi(adapter, i, napi);
+	}
 
 	if (adapter->flags & IGB_FLAG_HAS_MSIX)
 		igb_configure_msix(adapter);
@@ -2181,6 +2205,7 @@ void igb_down(struct igb_adapter *adapter)
 	for (i = 0; i < adapter->num_q_vectors; i++) {
 		if (adapter->q_vector[i]) {
 			napi_synchronize(&adapter->q_vector[i]->napi);
+			igb_set_queue_napi(adapter, i, NULL);
 			napi_disable(&adapter->q_vector[i]->napi);
 		}
 	}
@@ -4113,8 +4138,9 @@ static int igb_sw_init(struct igb_adapter *adapter)
 static int __igb_open(struct net_device *netdev, bool resuming)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
-	struct e1000_hw *hw = &adapter->hw;
 	struct pci_dev *pdev = adapter->pdev;
+	struct e1000_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int err;
 	int i;
 
@@ -4166,8 +4192,11 @@ static int __igb_open(struct net_device *netdev, bool resuming)
 	/* From here on the code is the same as igb_up() */
 	clear_bit(__IGB_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&(adapter->q_vector[i]->napi));
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igb_set_queue_napi(adapter, i, napi);
+	}
 
 	/* Clear any pending interrupts. */
 	rd32(E1000_TSICR);
@@ -5726,11 +5755,29 @@ no_wait:
 	if (adapter->flags & IGB_FLAG_HAS_MSIX) {
 		u32 eics = 0;
 
-		for (i = 0; i < adapter->num_q_vectors; i++)
-			eics |= adapter->q_vector[i]->eims_value;
-		wr32(E1000_EICS, eics);
+		for (i = 0; i < adapter->num_q_vectors; i++) {
+			struct igb_q_vector *q_vector = adapter->q_vector[i];
+			struct igb_ring *rx_ring;
+
+			if (!q_vector->rx.ring)
+				continue;
+
+			rx_ring = adapter->rx_ring[q_vector->rx.ring->queue_index];
+
+			if (test_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) {
+				eics |= q_vector->eims_value;
+				clear_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
+			}
+		}
+		if (eics)
+			wr32(E1000_EICS, eics);
 	} else {
-		wr32(E1000_ICS, E1000_ICS_RXDMT0);
+		struct igb_ring *rx_ring = adapter->rx_ring[0];
+
+		if (test_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) {
+			clear_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
+			wr32(E1000_ICS, E1000_ICS_RXDMT0);
+		}
 	}
 
 	igb_spoof_check(adapter);
@@ -9061,6 +9108,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		if (!xdp_res && !skb) {
 			rx_ring->rx_stats.alloc_failed++;
 			rx_buffer->pagecnt_bias++;
+			set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 			break;
 		}
 
@@ -9120,6 +9168,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 	page = dev_alloc_pages(igb_rx_pg_order(rx_ring));
 	if (unlikely(!page)) {
 		rx_ring->rx_stats.alloc_failed++;
+		set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 		return false;
 	}
 
@@ -9136,6 +9185,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 		__free_pages(page, igb_rx_pg_order(rx_ring));
 
 		rx_ring->rx_stats.alloc_failed++;
+		set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 		return false;
 	}
 
@@ -9674,8 +9724,11 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev,
 	if (state == pci_channel_io_perm_failure)
 		return PCI_ERS_RESULT_DISCONNECT;
 
+	rtnl_lock();
 	if (netif_running(netdev))
 		igb_down(adapter);
+	rtnl_unlock();
+
 	pci_disable_device(pdev);
 
 	/* Request a slot reset. */
@@ -9734,16 +9787,21 @@ static void igb_io_resume(struct pci_dev *pdev)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
 
+	rtnl_lock();
 	if (netif_running(netdev)) {
 		if (!test_bit(__IGB_DOWN, &adapter->state)) {
 			dev_dbg(&pdev->dev, "Resuming from non-fatal error, do nothing.\n");
+			rtnl_unlock();
 			return;
 		}
+
 		if (igb_up(adapter)) {
 			dev_err(&pdev->dev, "igb_up failed after reset\n");
+			rtnl_unlock();
 			return;
 		}
 	}
+	rtnl_unlock();
 
 	netif_device_attach(netdev);
 
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index f323e1c1989f..793c96016288 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -502,13 +502,6 @@ static int igb_ptp_feature_enable_82580(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		/* Reject requests with unsupported flags */
-		if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-					PTP_RISING_EDGE |
-					PTP_FALLING_EDGE |
-					PTP_STRICT_FLAGS))
-			return -EOPNOTSUPP;
-
 		/* Both the rising and falling edge are timestamped */
 		if (rq->extts.flags & PTP_STRICT_FLAGS &&
 		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -658,13 +651,6 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		/* Reject requests with unsupported flags */
-		if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-					PTP_RISING_EDGE |
-					PTP_FALLING_EDGE |
-					PTP_STRICT_FLAGS))
-			return -EOPNOTSUPP;
-
 		/* Reject requests failing to enable both edges. */
 		if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -1356,6 +1342,9 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.n_per_out = IGB_N_PEROUT;
 		adapter->ptp_caps.n_pins = IGB_N_SDP;
 		adapter->ptp_caps.pps = 0;
+		adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE |
+							  PTP_FALLING_EDGE |
+							  PTP_STRICT_FLAGS;
 		adapter->ptp_caps.pin_config = adapter->sdp_config;
 		adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
@@ -1378,6 +1367,9 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.n_ext_ts = IGB_N_EXTTS;
 		adapter->ptp_caps.n_per_out = IGB_N_PEROUT;
 		adapter->ptp_caps.n_pins = IGB_N_SDP;
+		adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE |
+							  PTP_FALLING_EDGE |
+							  PTP_STRICT_FLAGS;
 		adapter->ptp_caps.pps = 1;
 		adapter->ptp_caps.pin_config = adapter->sdp_config;
 		adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c
index 157d43787fa0..5cf67ba29269 100644
--- a/drivers/net/ethernet/intel/igb/igb_xsk.c
+++ b/drivers/net/ethernet/intel/igb/igb_xsk.c
@@ -415,6 +415,7 @@ int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector,
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->rx_stats.alloc_failed++;
+			set_bit(IGB_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 			break;
 		}
 
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index c35cc5cb1185..859a15e4ccba 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -40,6 +40,11 @@ void igc_ethtool_set_ops(struct net_device *);
 
 #define IGC_MAX_TX_TSTAMP_REGS		4
 
+struct igc_fpe_t {
+	struct ethtool_mmsv mmsv;
+	u32 tx_min_frag_size;
+};
+
 enum igc_mac_filter_type {
 	IGC_MAC_FILTER_TYPE_DST = 0,
 	IGC_MAC_FILTER_TYPE_SRC
@@ -319,6 +324,7 @@ struct igc_adapter {
 	struct timespec64 prev_ptp_time; /* Pre-reset PTP clock */
 	ktime_t ptp_reset_start; /* Reset time in clock mono */
 	struct system_time_snapshot snapshot;
+	struct mutex ptm_lock; /* Only allow one PTM transaction at a time */
 
 	char fw_version[32];
 
@@ -332,6 +338,8 @@ struct igc_adapter {
 		struct timespec64 period;
 	} perout[IGC_N_PEROUT];
 
+	struct igc_fpe_t fpe;
+
 	/* LEDs */
 	struct mutex led_mutex;
 	struct igc_led_classdev *leds;
@@ -386,11 +394,11 @@ extern char igc_driver_name[];
 #define IGC_FLAG_RX_LEGACY		BIT(16)
 #define IGC_FLAG_TSN_QBV_ENABLED	BIT(17)
 #define IGC_FLAG_TSN_QAV_ENABLED	BIT(18)
-#define IGC_FLAG_TSN_LEGACY_ENABLED	BIT(19)
+#define IGC_FLAG_TSN_PREEMPT_ENABLED	BIT(19)
 
 #define IGC_FLAG_TSN_ANY_ENABLED				\
 	(IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED |	\
-	 IGC_FLAG_TSN_LEGACY_ENABLED)
+	 IGC_FLAG_TSN_PREEMPT_ENABLED)
 
 #define IGC_FLAG_RSS_FIELD_IPV4_UDP	BIT(6)
 #define IGC_FLAG_RSS_FIELD_IPV6_UDP	BIT(7)
@@ -735,7 +743,10 @@ struct igc_nfc_rule *igc_get_nfc_rule(struct igc_adapter *adapter,
 				      u32 location);
 int igc_add_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule);
 void igc_del_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule);
-
+void igc_disable_empty_addr_recv(struct igc_adapter *adapter);
+int igc_enable_empty_addr_recv(struct igc_adapter *adapter);
+struct igc_ring *igc_get_tx_ring(struct igc_adapter *adapter, int cpu);
+void igc_flush_tx_descriptors(struct igc_ring *ring);
 void igc_ptp_init(struct igc_adapter *adapter);
 void igc_ptp_reset(struct igc_adapter *adapter);
 void igc_ptp_suspend(struct igc_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h
index bf8cdfbba9ff..6320eabb72fe 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.h
+++ b/drivers/net/ethernet/intel/igc/igc_base.h
@@ -49,6 +49,7 @@ struct igc_adv_tx_context_desc {
 #define IGC_ADVTXD_DCMD_DEXT	0x20000000 /* Descriptor extension (1=Adv) */
 #define IGC_ADVTXD_DCMD_VLE	0x40000000 /* VLAN pkt enable */
 #define IGC_ADVTXD_DCMD_TSE	0x80000000 /* TCP Seg enable */
+#define IGC_ADVTXD_PAYLEN_MASK	0XFFFFC000 /* Adv desc PAYLEN mask */
 #define IGC_ADVTXD_PAYLEN_SHIFT	14 /* Adv desc PAYLEN shift */
 
 #define IGC_RAR_ENTRIES		16
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 8e449904aa7d..7189dfc389ad 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -308,6 +308,8 @@
 #define IGC_TXD_DTYP_C		0x00000000 /* Context Descriptor */
 #define IGC_TXD_POPTS_IXSM	0x01       /* Insert IP checksum */
 #define IGC_TXD_POPTS_TXSM	0x02       /* Insert TCP/UDP checksum */
+#define IGC_TXD_POPTS_SMD_MASK	0x3000     /* Indicates whether it's SMD-V or SMD-R */
+
 #define IGC_TXD_CMD_EOP		0x01000000 /* End of Packet */
 #define IGC_TXD_CMD_IC		0x04000000 /* Insert Checksum */
 #define IGC_TXD_CMD_DEXT	0x20000000 /* Desc extension (0 = legacy) */
@@ -363,6 +365,8 @@
 #define IGC_SRRCTL_TIMER0SEL(timer)	(((timer) & 0x3) << 17)
 
 /* Receive Descriptor bit definitions */
+#define IGC_RXD_STAT_SMD_TYPE_V	0x01	/* SMD-V Packet */
+#define IGC_RXD_STAT_SMD_TYPE_R	0x02	/* SMD-R Packet */
 #define IGC_RXD_STAT_EOP	0x02	/* End of Packet */
 #define IGC_RXD_STAT_IXSM	0x04	/* Ignore checksum */
 #define IGC_RXD_STAT_UDPCS	0x10	/* UDP xsum calculated */
@@ -372,7 +376,8 @@
 #define IGC_RXDEXT_STATERR_LB	0x00040000
 
 /* Advanced Receive Descriptor bit definitions */
-#define IGC_RXDADV_STAT_TSIP	0x08000 /* timestamp in packet */
+#define IGC_RXDADV_STAT_SMD_TYPE_MASK	0x06000
+#define IGC_RXDADV_STAT_TSIP		0x08000 /* timestamp in packet */
 
 #define IGC_RXDEXT_STATERR_L4E		0x20000000
 #define IGC_RXDEXT_STATERR_IPE		0x40000000
@@ -396,11 +401,47 @@
 #define IGC_RCTL_PMCF		0x00800000 /* pass MAC control frames */
 #define IGC_RCTL_SECRC		0x04000000 /* Strip Ethernet CRC */
 
-#define I225_RXPBSIZE_DEFAULT	0x000000A2 /* RXPBSIZE default */
-#define I225_TXPBSIZE_DEFAULT	0x04000014 /* TXPBSIZE default */
-#define IGC_RXPBS_CFG_TS_EN	0x80000000 /* Timestamp in Rx buffer */
-
-#define IGC_TXPBSIZE_TSN	0x04145145 /* 5k bytes buffer for each queue */
+/* Mask for RX packet buffer size */
+#define IGC_RXPBSIZE_EXP_MASK		GENMASK(5, 0)
+#define IGC_BMC2OSPBSIZE_MASK		GENMASK(11, 6)
+#define IGC_RXPBSIZE_BE_MASK		GENMASK(17, 12)
+/* Mask for timestamp in RX buffer */
+#define IGC_RXPBS_CFG_TS_EN_MASK	GENMASK(31, 31)
+/* High-priority RX packet buffer size (KB). Used for Express traffic when preemption is enabled */
+#define IGC_RXPBSIZE_EXP(x)		FIELD_PREP(IGC_RXPBSIZE_EXP_MASK, (x))
+/* BMC to OS packet buffer size in KB */
+#define IGC_BMC2OSPBSIZE(x)		FIELD_PREP(IGC_BMC2OSPBSIZE_MASK, (x))
+/* Low-priority RX packet buffer size (KB). Used for BE traffic when preemption is enabled */
+#define IGC_RXPBSIZE_BE(x)		FIELD_PREP(IGC_RXPBSIZE_BE_MASK, (x))
+/* Enable RX packet buffer for timestamp descriptor, saving 16 bytes per packet if set */
+#define IGC_RXPBS_CFG_TS_EN		FIELD_PREP(IGC_RXPBS_CFG_TS_EN_MASK, 1)
+/* Default value following I225/I226 SW User Manual Section 8.3.1 */
+#define IGC_RXPBSIZE_EXP_BMC_DEFAULT ( \
+	IGC_RXPBSIZE_EXP(34) | IGC_BMC2OSPBSIZE(2))
+#define IGC_RXPBSIZE_EXP_BMC_BE_TSN ( \
+	IGC_RXPBSIZE_EXP(15) | IGC_BMC2OSPBSIZE(2) | IGC_RXPBSIZE_BE(15))
+
+/* Mask for TX packet buffer size */
+#define IGC_TXPB0SIZE_MASK		GENMASK(5, 0)
+#define IGC_TXPB1SIZE_MASK		GENMASK(11, 6)
+#define IGC_TXPB2SIZE_MASK		GENMASK(17, 12)
+#define IGC_TXPB3SIZE_MASK		GENMASK(23, 18)
+/* Mask for OS to BMC packet buffer size */
+#define IGC_OS2BMCPBSIZE_MASK		GENMASK(29, 24)
+/* TX Packet buffer size in KB */
+#define IGC_TXPB0SIZE(x)		FIELD_PREP(IGC_TXPB0SIZE_MASK, (x))
+#define IGC_TXPB1SIZE(x)		FIELD_PREP(IGC_TXPB1SIZE_MASK, (x))
+#define IGC_TXPB2SIZE(x)		FIELD_PREP(IGC_TXPB2SIZE_MASK, (x))
+#define IGC_TXPB3SIZE(x)		FIELD_PREP(IGC_TXPB3SIZE_MASK, (x))
+/* OS to BMC packet buffer size in KB */
+#define IGC_OS2BMCPBSIZE(x)		FIELD_PREP(IGC_OS2BMCPBSIZE_MASK, (x))
+/* Default value following I225/I226 SW User Manual Section 8.3.2 */
+#define IGC_TXPBSIZE_DEFAULT ( \
+	IGC_TXPB0SIZE(20) | IGC_TXPB1SIZE(0) | IGC_TXPB2SIZE(0) | \
+	IGC_TXPB3SIZE(0) | IGC_OS2BMCPBSIZE(4))
+#define IGC_TXPBSIZE_TSN ( \
+	IGC_TXPB0SIZE(7) | IGC_TXPB1SIZE(7) | IGC_TXPB2SIZE(7) | \
+	IGC_TXPB3SIZE(7) | IGC_OS2BMCPBSIZE(4))
 
 #define IGC_DTXMXPKTSZ_TSN	0x19 /* 1600 bytes of max TX DMA packet size */
 #define IGC_DTXMXPKTSZ_DEFAULT	0x98 /* 9728-byte Jumbo frames */
@@ -539,8 +580,10 @@
 
 /* Transmit Scheduling */
 #define IGC_TQAVCTRL_TRANSMIT_MODE_TSN	0x00000001
+#define IGC_TQAVCTRL_PREEMPT_ENA	0x00000002
 #define IGC_TQAVCTRL_ENHANCED_QAV	0x00000008
 #define IGC_TQAVCTRL_FUTSCDDIS		0x00000080
+#define IGC_TQAVCTRL_MIN_FRAG_MASK	0x0000C000
 
 #define IGC_TXQCTL_QUEUE_MODE_LAUNCHT	0x00000001
 #define IGC_TXQCTL_STRICT_CYCLE		0x00000002
@@ -574,7 +617,10 @@
 #define IGC_PTM_CTRL_SHRT_CYC(usec)	(((usec) & 0x3f) << 2)
 #define IGC_PTM_CTRL_PTM_TO(usec)	(((usec) & 0xff) << 8)
 
-#define IGC_PTM_SHORT_CYC_DEFAULT	1   /* Default short cycle interval */
+/* A short cycle time of 1us theoretically should work, but appears to be too
+ * short in practice.
+ */
+#define IGC_PTM_SHORT_CYC_DEFAULT	4   /* Default short cycle interval */
 #define IGC_PTM_CYC_TIME_DEFAULT	5   /* Default PTM cycle time */
 #define IGC_PTM_TIMEOUT_DEFAULT		255 /* Default timeout for PTM errors */
 
@@ -593,6 +639,7 @@
 #define IGC_PTM_STAT_T4M1_OVFL		BIT(3) /* T4 minus T1 overflow */
 #define IGC_PTM_STAT_ADJUST_1ST		BIT(4) /* 1588 timer adjusted during 1st PTM cycle */
 #define IGC_PTM_STAT_ADJUST_CYC		BIT(5) /* 1588 timer adjusted during non-1st PTM cycle */
+#define IGC_PTM_STAT_ALL		GENMASK(5, 0) /* Used to clear all status */
 
 /* PCIe PTM Cycle Control */
 #define IGC_PTM_CYCLE_CTRL_CYC_TIME(msec)	((msec) & 0x3ff) /* PTM Cycle Time (msec) */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 817838677817..3fc1eded9605 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -8,6 +8,7 @@
 
 #include "igc.h"
 #include "igc_diag.h"
+#include "igc_tsn.h"
 
 /* forward declaration */
 struct igc_stats {
@@ -1781,6 +1782,83 @@ static int igc_ethtool_set_eee(struct net_device *netdev,
 	return 0;
 }
 
+static int igc_ethtool_get_mm(struct net_device *netdev,
+			      struct ethtool_mm_state *cmd)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_fpe_t *fpe = &adapter->fpe;
+
+	ethtool_mmsv_get_mm(&fpe->mmsv, cmd);
+	cmd->tx_min_frag_size = fpe->tx_min_frag_size;
+	cmd->rx_min_frag_size = IGC_RX_MIN_FRAG_SIZE;
+
+	return 0;
+}
+
+static int igc_ethtool_set_mm(struct net_device *netdev,
+			      struct ethtool_mm_cfg *cmd,
+			      struct netlink_ext_ack *extack)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_fpe_t *fpe = &adapter->fpe;
+
+	fpe->tx_min_frag_size = igc_fpe_get_supported_frag_size(cmd->tx_min_frag_size);
+	if (fpe->tx_min_frag_size != cmd->tx_min_frag_size)
+		NL_SET_ERR_MSG_MOD(extack,
+				   "tx-min-frag-size value set is unsupported. Rounded up to supported value (64, 128, 192, 256)");
+
+	if (fpe->mmsv.pmac_enabled != cmd->pmac_enabled) {
+		if (cmd->pmac_enabled)
+			static_branch_inc(&igc_fpe_enabled);
+		else
+			static_branch_dec(&igc_fpe_enabled);
+	}
+
+	ethtool_mmsv_set_mm(&fpe->mmsv, cmd);
+
+	return igc_tsn_offload_apply(adapter);
+}
+
+/**
+ * igc_ethtool_get_frame_ass_error - Get the frame assembly error count.
+ * @reg_value: Register value for IGC_PRMEXCPRCNT
+ * Return: The count of frame assembly errors.
+ */
+static u64 igc_ethtool_get_frame_ass_error(u32 reg_value)
+{
+	/* Out of order statistics */
+	u32 ooo_frame_cnt, ooo_frag_cnt;
+	u32 miss_frame_frag_cnt;
+
+	ooo_frame_cnt = FIELD_GET(IGC_PRMEXCPRCNT_OOO_FRAME_CNT, reg_value);
+	ooo_frag_cnt = FIELD_GET(IGC_PRMEXCPRCNT_OOO_FRAG_CNT, reg_value);
+	miss_frame_frag_cnt = FIELD_GET(IGC_PRMEXCPRCNT_MISS_FRAME_FRAG_CNT,
+					reg_value);
+
+	return ooo_frame_cnt + ooo_frag_cnt + miss_frame_frag_cnt;
+}
+
+static u64 igc_ethtool_get_frame_smd_error(u32 reg_value)
+{
+	return FIELD_GET(IGC_PRMEXCPRCNT_OOO_SMDC, reg_value);
+}
+
+static void igc_ethtool_get_mm_stats(struct net_device *dev,
+				     struct ethtool_mm_stats *stats)
+{
+	struct igc_adapter *adapter = netdev_priv(dev);
+	struct igc_hw *hw = &adapter->hw;
+	u32 reg_value;
+
+	reg_value = rd32(IGC_PRMEXCPRCNT);
+
+	stats->MACMergeFrameAssErrorCount = igc_ethtool_get_frame_ass_error(reg_value);
+	stats->MACMergeFrameSmdErrorCount = igc_ethtool_get_frame_smd_error(reg_value);
+	stats->MACMergeFrameAssOkCount = rd32(IGC_PRMPTDRCNT);
+	stats->MACMergeFragCountRx = rd32(IGC_PRMEVNTRCNT);
+	stats->MACMergeFragCountTx = rd32(IGC_PRMEVNTTCNT);
+}
+
 static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 					  struct ethtool_link_ksettings *cmd)
 {
@@ -2076,6 +2154,9 @@ static const struct ethtool_ops igc_ethtool_ops = {
 	.get_link_ksettings	= igc_ethtool_get_link_ksettings,
 	.set_link_ksettings	= igc_ethtool_set_link_ksettings,
 	.self_test		= igc_ethtool_diag_test,
+	.get_mm			= igc_ethtool_get_mm,
+	.get_mm_stats		= igc_ethtool_get_mm_stats,
+	.set_mm			= igc_ethtool_set_mm,
 };
 
 void igc_ethtool_set_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index f1330379e6bb..27575a1e1777 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2464,8 +2464,7 @@ unmap:
 	return -ENOMEM;
 }
 
-static struct igc_ring *igc_xdp_get_tx_ring(struct igc_adapter *adapter,
-					    int cpu)
+struct igc_ring *igc_get_tx_ring(struct igc_adapter *adapter, int cpu)
 {
 	int index = cpu;
 
@@ -2489,7 +2488,7 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp)
 	if (unlikely(!xdpf))
 		return -EFAULT;
 
-	ring = igc_xdp_get_tx_ring(adapter, cpu);
+	ring = igc_get_tx_ring(adapter, cpu);
 	nq = txring_txq(ring);
 
 	__netif_tx_lock(nq, cpu);
@@ -2549,7 +2548,7 @@ out:
 }
 
 /* This function assumes __netif_tx_lock is held by the caller. */
-static void igc_flush_tx_descriptors(struct igc_ring *ring)
+void igc_flush_tx_descriptors(struct igc_ring *ring)
 {
 	/* Once tail pointer is updated, hardware can fetch the descriptors
 	 * any time so we issue a write membar here to ensure all memory
@@ -2566,7 +2565,7 @@ static void igc_finalize_xdp(struct igc_adapter *adapter, int status)
 	struct igc_ring *ring;
 
 	if (status & IGC_XDP_TX) {
-		ring = igc_xdp_get_tx_ring(adapter, cpu);
+		ring = igc_get_tx_ring(adapter, cpu);
 		nq = txring_txq(ring);
 
 		__netif_tx_lock(nq, cpu);
@@ -2638,6 +2637,14 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			size -= IGC_TS_HDR_LEN;
 		}
 
+		if (igc_fpe_is_pmac_enabled(adapter) &&
+		    igc_fpe_handle_mpacket(adapter, rx_desc, size, pktbuf)) {
+			/* Advance the ring next-to-clean */
+			igc_is_non_eop(rx_ring, rx_desc);
+			cleaned_count++;
+			continue;
+		}
+
 		if (!skb) {
 			xdp_init_buff(&ctx.xdp, truesize, &rx_ring->xdp_rxq);
 			xdp_prepare_buff(&ctx.xdp, pktbuf - igc_rx_offset(rx_ring),
@@ -3145,6 +3152,11 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 		if (!(eop_desc->wb.status & cpu_to_le32(IGC_TXD_STAT_DD)))
 			break;
 
+		if (igc_fpe_is_pmac_enabled(adapter) &&
+		    igc_fpe_transmitted_smd_v(tx_desc))
+			ethtool_mmsv_event_handle(&adapter->fpe.mmsv,
+						  ETHTOOL_MMSV_LD_SENT_VERIFY_MPACKET);
+
 		/* Hold the completions while there's a pending tx hardware
 		 * timestamp request from XDP Tx metadata.
 		 */
@@ -4037,6 +4049,30 @@ static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 }
 
 /**
+ * igc_enable_empty_addr_recv - Enable Rx of packets with all-zeroes MAC address
+ * @adapter: Pointer to the igc_adapter structure.
+ *
+ * Frame preemption verification requires that packets with the all-zeroes
+ * MAC address are allowed to be received by the driver. This function adds the
+ * all-zeroes destination address to the list of acceptable addresses.
+ *
+ * Return: 0 on success, negative value otherwise.
+ */
+int igc_enable_empty_addr_recv(struct igc_adapter *adapter)
+{
+	u8 empty[ETH_ALEN] = {};
+
+	return igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty, -1);
+}
+
+void igc_disable_empty_addr_recv(struct igc_adapter *adapter)
+{
+	u8 empty[ETH_ALEN] = {};
+
+	igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty);
+}
+
+/**
  * igc_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set
  * @netdev: network interface device structure
  *
@@ -5311,6 +5347,9 @@ void igc_down(struct igc_adapter *adapter)
 	igc_disable_all_tx_rings_hw(adapter);
 	igc_clean_all_tx_rings(adapter);
 	igc_clean_all_rx_rings(adapter);
+
+	if (adapter->fpe.mmsv.pmac_enabled)
+		ethtool_mmsv_stop(&adapter->fpe.mmsv);
 }
 
 void igc_reinit_locked(struct igc_adapter *adapter)
@@ -5835,6 +5874,10 @@ static void igc_watchdog_task(struct work_struct *work)
 			 */
 			igc_tsn_adjust_txtime_offset(adapter);
 
+			if (adapter->fpe.mmsv.pmac_enabled)
+				ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv,
+							       true);
+
 			if (adapter->link_speed != SPEED_1000)
 				goto no_wait;
 
@@ -5870,6 +5913,10 @@ no_wait:
 			netdev_info(netdev, "NIC Link is Down\n");
 			netif_carrier_off(netdev);
 
+			if (adapter->fpe.mmsv.pmac_enabled)
+				ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv,
+							       false);
+
 			/* link state has changed, schedule phy info update */
 			if (!test_bit(__IGC_DOWN, &adapter->state))
 				mod_timer(&adapter->phy_info_timer,
@@ -6439,6 +6486,10 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	if (!validate_schedule(adapter, qopt))
 		return -EINVAL;
 
+	/* preemptible isn't supported yet */
+	if (qopt->mqprio.preemptible_tcs)
+		return -EOPNOTSUPP;
+
 	igc_ptp_read(adapter, &now);
 
 	if (igc_tsn_is_taprio_activated_by_user(adapter) &&
@@ -6679,13 +6730,14 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter,
 				 struct tc_mqprio_qopt_offload *mqprio)
 {
 	struct igc_hw *hw = &adapter->hw;
-	int i;
+	int err, i;
 
 	if (hw->mac.type != igc_i225)
 		return -EOPNOTSUPP;
 
 	if (!mqprio->qopt.num_tc) {
 		adapter->strict_priority_enable = false;
+		netdev_reset_tc(adapter->netdev);
 		goto apply;
 	}
 
@@ -6716,6 +6768,21 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter,
 	igc_save_mqprio_params(adapter, mqprio->qopt.num_tc,
 			       mqprio->qopt.offset);
 
+	err = netdev_set_num_tc(adapter->netdev, adapter->num_tc);
+	if (err)
+		return err;
+
+	for (i = 0; i < adapter->num_tc; i++) {
+		err = netdev_set_tc_queue(adapter->netdev, i, 1,
+					  adapter->queue_per_tc[i]);
+		if (err)
+			return err;
+	}
+
+	/* In case the card is configured with less than four queues. */
+	for (; i < IGC_MAX_TX_QUEUES; i++)
+		adapter->queue_per_tc[i] = i;
+
 	mqprio->qopt.hw = TC_MQPRIO_HW_OFFLOAD_TCS;
 
 apply:
@@ -6779,7 +6846,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
-	ring = igc_xdp_get_tx_ring(adapter, cpu);
+	ring = igc_get_tx_ring(adapter, cpu);
 	nq = txring_txq(ring);
 
 	__netif_tx_lock(nq, cpu);
@@ -7125,6 +7192,9 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
 			       NETDEV_XDP_ACT_XSK_ZEROCOPY;
 
+	/* enable HW vlan tag insertion/stripping by default */
+	netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
+
 	/* MTU range: 68 - 9216 */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;
@@ -7157,8 +7227,8 @@ static int igc_probe(struct pci_dev *pdev,
 	}
 
 	/* configure RXPBSIZE and TXPBSIZE */
-	wr32(IGC_RXPBS, I225_RXPBSIZE_DEFAULT);
-	wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
+	wr32(IGC_RXPBS, IGC_RXPBSIZE_EXP_BMC_DEFAULT);
+	wr32(IGC_TXPBS, IGC_TXPBSIZE_DEFAULT);
 
 	timer_setup(&adapter->watchdog_timer, igc_watchdog, 0);
 	timer_setup(&adapter->phy_info_timer, igc_update_phy_info, 0);
@@ -7190,6 +7260,8 @@ static int igc_probe(struct pci_dev *pdev,
 
 	igc_tsn_clear_schedule(adapter);
 
+	igc_fpe_init(adapter);
+
 	/* reset the hardware with the new settings */
 	igc_reset(adapter);
 
@@ -7231,6 +7303,7 @@ static int igc_probe(struct pci_dev *pdev,
 
 err_register:
 	igc_release_hw_control(adapter);
+	igc_ptp_stop(adapter);
 err_eeprom:
 	if (!igc_check_reset_block(hw))
 		igc_reset_phy(hw);
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 946edbad4302..f4f5c28615d3 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -257,13 +257,6 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		/* Reject requests with unsupported flags */
-		if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-					PTP_RISING_EDGE |
-					PTP_FALLING_EDGE |
-					PTP_STRICT_FLAGS))
-			return -EOPNOTSUPP;
-
 		/* Reject requests failing to enable both edges. */
 		if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -300,10 +293,6 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
 		return 0;
 
 	case PTP_CLK_REQ_PEROUT:
-		/* Reject requests with unsupported flags */
-		if (rq->perout.flags)
-			return -EOPNOTSUPP;
-
 		if (on) {
 			pin = ptp_find_pin(igc->ptp_clock, PTP_PF_PEROUT,
 					   rq->perout.index);
@@ -974,45 +963,62 @@ static void igc_ptm_log_error(struct igc_adapter *adapter, u32 ptm_stat)
 	}
 }
 
+/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_trigger() */
+static void igc_ptm_trigger(struct igc_hw *hw)
+{
+	u32 ctrl;
+
+	/* To "manually" start the PTM cycle we need to set the
+	 * trigger (TRIG) bit
+	 */
+	ctrl = rd32(IGC_PTM_CTRL);
+	ctrl |= IGC_PTM_CTRL_TRIG;
+	wr32(IGC_PTM_CTRL, ctrl);
+	/* Perform flush after write to CTRL register otherwise
+	 * transaction may not start
+	 */
+	wrfl();
+}
+
+/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_reset() */
+static void igc_ptm_reset(struct igc_hw *hw)
+{
+	u32 ctrl;
+
+	ctrl = rd32(IGC_PTM_CTRL);
+	ctrl &= ~IGC_PTM_CTRL_TRIG;
+	wr32(IGC_PTM_CTRL, ctrl);
+	/* Write to clear all status */
+	wr32(IGC_PTM_STAT, IGC_PTM_STAT_ALL);
+}
+
 static int igc_phc_get_syncdevicetime(ktime_t *device,
 				      struct system_counterval_t *system,
 				      void *ctx)
 {
-	u32 stat, t2_curr_h, t2_curr_l, ctrl;
 	struct igc_adapter *adapter = ctx;
 	struct igc_hw *hw = &adapter->hw;
+	u32 stat, t2_curr_h, t2_curr_l;
 	int err, count = 100;
 	ktime_t t1, t2_curr;
 
-	/* Get a snapshot of system clocks to use as historic value. */
-	ktime_get_snapshot(&adapter->snapshot);
-
+	/* Doing this in a loop because in the event of a
+	 * badly timed (ha!) system clock adjustment, we may
+	 * get PTM errors from the PCI root, but these errors
+	 * are transitory. Repeating the process returns valid
+	 * data eventually.
+	 */
 	do {
-		/* Doing this in a loop because in the event of a
-		 * badly timed (ha!) system clock adjustment, we may
-		 * get PTM errors from the PCI root, but these errors
-		 * are transitory. Repeating the process returns valid
-		 * data eventually.
-		 */
-
-		/* To "manually" start the PTM cycle we need to clear and
-		 * then set again the TRIG bit.
-		 */
-		ctrl = rd32(IGC_PTM_CTRL);
-		ctrl &= ~IGC_PTM_CTRL_TRIG;
-		wr32(IGC_PTM_CTRL, ctrl);
-		ctrl |= IGC_PTM_CTRL_TRIG;
-		wr32(IGC_PTM_CTRL, ctrl);
+		/* Get a snapshot of system clocks to use as historic value. */
+		ktime_get_snapshot(&adapter->snapshot);
 
-		/* The cycle only starts "for real" when software notifies
-		 * that it has read the registers, this is done by setting
-		 * VALID bit.
-		 */
-		wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID);
+		igc_ptm_trigger(hw);
 
 		err = readx_poll_timeout(rd32, IGC_PTM_STAT, stat,
 					 stat, IGC_PTM_STAT_SLEEP,
 					 IGC_PTM_STAT_TIMEOUT);
+		igc_ptm_reset(hw);
+
 		if (err < 0) {
 			netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
 			return err;
@@ -1021,15 +1027,7 @@ static int igc_phc_get_syncdevicetime(ktime_t *device,
 		if ((stat & IGC_PTM_STAT_VALID) == IGC_PTM_STAT_VALID)
 			break;
 
-		if (stat & ~IGC_PTM_STAT_VALID) {
-			/* An error occurred, log it. */
-			igc_ptm_log_error(adapter, stat);
-			/* The STAT register is write-1-to-clear (W1C),
-			 * so write the previous error status to clear it.
-			 */
-			wr32(IGC_PTM_STAT, stat);
-			continue;
-		}
+		igc_ptm_log_error(adapter, stat);
 	} while (--count);
 
 	if (!count) {
@@ -1061,9 +1059,16 @@ static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 {
 	struct igc_adapter *adapter = container_of(ptp, struct igc_adapter,
 						   ptp_caps);
+	int ret;
+
+	/* This blocks until any in progress PTM transactions complete */
+	mutex_lock(&adapter->ptm_lock);
 
-	return get_device_system_crosststamp(igc_phc_get_syncdevicetime,
-					     adapter, &adapter->snapshot, cts);
+	ret = get_device_system_crosststamp(igc_phc_get_syncdevicetime,
+					    adapter, &adapter->snapshot, cts);
+	mutex_unlock(&adapter->ptm_lock);
+
+	return ret;
 }
 
 static int igc_ptp_getcyclesx64(struct ptp_clock_info *ptp,
@@ -1146,6 +1151,9 @@ void igc_ptp_init(struct igc_adapter *adapter)
 		adapter->ptp_caps.pin_config = adapter->sdp_config;
 		adapter->ptp_caps.n_ext_ts = IGC_N_EXTTS;
 		adapter->ptp_caps.n_per_out = IGC_N_PEROUT;
+		adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE |
+							  PTP_FALLING_EDGE |
+							  PTP_STRICT_FLAGS;
 		adapter->ptp_caps.n_pins = IGC_N_SDP;
 		adapter->ptp_caps.verify = igc_ptp_verify_pin;
 
@@ -1162,6 +1170,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	spin_lock_init(&adapter->ptp_tx_lock);
 	spin_lock_init(&adapter->free_timer_lock);
 	spin_lock_init(&adapter->tmreg_lock);
+	mutex_init(&adapter->ptm_lock);
 
 	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
@@ -1174,6 +1183,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	if (IS_ERR(adapter->ptp_clock)) {
 		adapter->ptp_clock = NULL;
 		netdev_err(netdev, "ptp_clock_register failed\n");
+		mutex_destroy(&adapter->ptm_lock);
 	} else if (adapter->ptp_clock) {
 		netdev_info(netdev, "PHC added\n");
 		adapter->ptp_flags |= IGC_PTP_ENABLED;
@@ -1203,10 +1213,12 @@ static void igc_ptm_stop(struct igc_adapter *adapter)
 	struct igc_hw *hw = &adapter->hw;
 	u32 ctrl;
 
+	mutex_lock(&adapter->ptm_lock);
 	ctrl = rd32(IGC_PTM_CTRL);
 	ctrl &= ~IGC_PTM_CTRL_EN;
 
 	wr32(IGC_PTM_CTRL, ctrl);
+	mutex_unlock(&adapter->ptm_lock);
 }
 
 /**
@@ -1237,13 +1249,18 @@ void igc_ptp_suspend(struct igc_adapter *adapter)
  **/
 void igc_ptp_stop(struct igc_adapter *adapter)
 {
+	if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
+		return;
+
 	igc_ptp_suspend(adapter);
 
+	adapter->ptp_flags &= ~IGC_PTP_ENABLED;
 	if (adapter->ptp_clock) {
 		ptp_clock_unregister(adapter->ptp_clock);
 		netdev_info(adapter->netdev, "PHC removed\n");
 		adapter->ptp_flags &= ~IGC_PTP_ENABLED;
 	}
+	mutex_destroy(&adapter->ptm_lock);
 }
 
 /**
@@ -1255,13 +1272,18 @@ void igc_ptp_stop(struct igc_adapter *adapter)
 void igc_ptp_reset(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
-	u32 cycle_ctrl, ctrl;
+	u32 cycle_ctrl, ctrl, stat;
 	unsigned long flags;
 	u32 timadj;
 
+	if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
+		return;
+
 	/* reset the tstamp_config */
 	igc_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config);
 
+	mutex_lock(&adapter->ptm_lock);
+
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
 
 	switch (adapter->hw.mac.type) {
@@ -1290,14 +1312,19 @@ void igc_ptp_reset(struct igc_adapter *adapter)
 		ctrl = IGC_PTM_CTRL_EN |
 			IGC_PTM_CTRL_START_NOW |
 			IGC_PTM_CTRL_SHRT_CYC(IGC_PTM_SHORT_CYC_DEFAULT) |
-			IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT) |
-			IGC_PTM_CTRL_TRIG;
+			IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT);
 
 		wr32(IGC_PTM_CTRL, ctrl);
 
 		/* Force the first cycle to run. */
-		wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID);
+		igc_ptm_trigger(hw);
 
+		if (readx_poll_timeout_atomic(rd32, IGC_PTM_STAT, stat,
+					      stat, IGC_PTM_STAT_SLEEP,
+					      IGC_PTM_STAT_TIMEOUT))
+			netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
+
+		igc_ptm_reset(hw);
 		break;
 	default:
 		/* No work to do. */
@@ -1314,5 +1341,7 @@ void igc_ptp_reset(struct igc_adapter *adapter)
 out:
 	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
 
+	mutex_unlock(&adapter->ptm_lock);
+
 	wrfl();
 }
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 12ddc5793651..f343c6bfc6be 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -222,6 +222,22 @@
 
 #define IGC_FTQF(_n)	(0x059E0 + (4 * (_n)))  /* 5-tuple Queue Fltr */
 
+/* Time sync registers - preemption statistics */
+#define IGC_PRMPTDRCNT		0x04284	/* Good RX Preempted Packets */
+#define IGC_PRMEVNTTCNT		0x04298	/* TX Preemption event counter */
+#define IGC_PRMEVNTRCNT		0x0429C	/* RX Preemption event counter */
+
+ /* Preemption Exception Counter */
+ #define IGC_PRMEXCPRCNT				0x42A0
+/* Received out of order packets with SMD-C */
+#define IGC_PRMEXCPRCNT_OOO_SMDC			0x000000FF
+/* Received out of order packets with SMD-C and wrong Frame CNT */
+#define IGC_PRMEXCPRCNT_OOO_FRAME_CNT			0x0000FF00
+/* Received out of order packets with SMD-C and wrong Frag CNT */
+#define IGC_PRMEXCPRCNT_OOO_FRAG_CNT			0x00FF0000
+/* Received packets with SMD-S and wrong Frag CNT and Frame CNT */
+#define IGC_PRMEXCPRCNT_MISS_FRAME_FRAG_CNT		0xFF000000
+
 /* Transmit Scheduling Registers */
 #define IGC_TQAVCTRL		0x3570
 #define IGC_TXQCTL(_n)		(0x3344 + 0x4 * (_n))
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
index 1e44374ca1ff..f22cc4d4f459 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.c
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
@@ -2,9 +2,143 @@
 /* Copyright (c)  2019 Intel Corporation */
 
 #include "igc.h"
+#include "igc_base.h"
 #include "igc_hw.h"
 #include "igc_tsn.h"
 
+#define MIN_MULTPLIER_TX_MIN_FRAG	0
+#define MAX_MULTPLIER_TX_MIN_FRAG	3
+/* Frag size is based on the Section 8.12.2 of the SW User Manual */
+#define TX_MIN_FRAG_SIZE		64
+#define TX_MAX_FRAG_SIZE	(TX_MIN_FRAG_SIZE * \
+				 (MAX_MULTPLIER_TX_MIN_FRAG + 1))
+
+DEFINE_STATIC_KEY_FALSE(igc_fpe_enabled);
+
+static int igc_fpe_init_smd_frame(struct igc_ring *ring,
+				  struct igc_tx_buffer *buffer,
+				  struct sk_buff *skb)
+{
+	dma_addr_t dma = dma_map_single(ring->dev, skb->data, skb->len,
+					DMA_TO_DEVICE);
+
+	if (dma_mapping_error(ring->dev, dma)) {
+		netdev_err_once(ring->netdev, "Failed to map DMA for TX\n");
+		return -ENOMEM;
+	}
+
+	buffer->skb = skb;
+	buffer->protocol = 0;
+	buffer->bytecount = skb->len;
+	buffer->gso_segs = 1;
+	buffer->time_stamp = jiffies;
+	dma_unmap_len_set(buffer, len, skb->len);
+	dma_unmap_addr_set(buffer, dma, dma);
+
+	return 0;
+}
+
+static int igc_fpe_init_tx_descriptor(struct igc_ring *ring,
+				      struct sk_buff *skb,
+				      enum igc_txd_popts_type type)
+{
+	u32 cmd_type, olinfo_status = 0;
+	struct igc_tx_buffer *buffer;
+	union igc_adv_tx_desc *desc;
+	int err;
+
+	if (!igc_desc_unused(ring))
+		return -EBUSY;
+
+	buffer = &ring->tx_buffer_info[ring->next_to_use];
+	err = igc_fpe_init_smd_frame(ring, buffer, skb);
+	if (err)
+		return err;
+
+	cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT |
+		   IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD |
+		   buffer->bytecount;
+
+	olinfo_status |= FIELD_PREP(IGC_ADVTXD_PAYLEN_MASK, buffer->bytecount);
+
+	switch (type) {
+	case SMD_V:
+	case SMD_R:
+		olinfo_status |= FIELD_PREP(IGC_TXD_POPTS_SMD_MASK, type);
+		break;
+	}
+
+	desc = IGC_TX_DESC(ring, ring->next_to_use);
+	desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+	desc->read.olinfo_status = cpu_to_le32(olinfo_status);
+	desc->read.buffer_addr = cpu_to_le64(dma_unmap_addr(buffer, dma));
+
+	netdev_tx_sent_queue(txring_txq(ring), skb->len);
+
+	buffer->next_to_watch = desc;
+	ring->next_to_use = (ring->next_to_use + 1) % ring->count;
+
+	return 0;
+}
+
+static int igc_fpe_xmit_smd_frame(struct igc_adapter *adapter,
+				  enum igc_txd_popts_type type)
+{
+	int cpu = smp_processor_id();
+	struct netdev_queue *nq;
+	struct igc_ring *ring;
+	struct sk_buff *skb;
+	int err;
+
+	ring = igc_get_tx_ring(adapter, cpu);
+	nq = txring_txq(ring);
+
+	skb = alloc_skb(SMD_FRAME_SIZE, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_put_zero(skb, SMD_FRAME_SIZE);
+
+	__netif_tx_lock(nq, cpu);
+
+	err = igc_fpe_init_tx_descriptor(ring, skb, type);
+	igc_flush_tx_descriptors(ring);
+
+	__netif_tx_unlock(nq);
+
+	return err;
+}
+
+static void igc_fpe_send_mpacket(struct ethtool_mmsv *mmsv,
+				 enum ethtool_mpacket type)
+{
+	struct igc_fpe_t *fpe = container_of(mmsv, struct igc_fpe_t, mmsv);
+	struct igc_adapter *adapter;
+	int err;
+
+	adapter = container_of(fpe, struct igc_adapter, fpe);
+
+	if (type == ETHTOOL_MPACKET_VERIFY) {
+		err = igc_fpe_xmit_smd_frame(adapter, SMD_V);
+		if (err && net_ratelimit())
+			netdev_err(adapter->netdev, "Error sending SMD-V\n");
+	} else if (type == ETHTOOL_MPACKET_RESPONSE) {
+		err = igc_fpe_xmit_smd_frame(adapter, SMD_R);
+		if (err && net_ratelimit())
+			netdev_err(adapter->netdev, "Error sending SMD-R frame\n");
+	}
+}
+
+static const struct ethtool_mmsv_ops igc_mmsv_ops = {
+	.send_mpacket = igc_fpe_send_mpacket,
+};
+
+void igc_fpe_init(struct igc_adapter *adapter)
+{
+	adapter->fpe.tx_min_frag_size = TX_MIN_FRAG_SIZE;
+	ethtool_mmsv_init(&adapter->fpe.mmsv, adapter->netdev, &igc_mmsv_ops);
+}
+
 static bool is_any_launchtime(struct igc_adapter *adapter)
 {
 	int i;
@@ -37,17 +171,16 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter)
 {
 	unsigned int new_flags = adapter->flags & ~IGC_FLAG_TSN_ANY_ENABLED;
 
-	if (adapter->taprio_offload_enable)
-		new_flags |= IGC_FLAG_TSN_QBV_ENABLED;
 
-	if (is_any_launchtime(adapter))
+	if (adapter->taprio_offload_enable || is_any_launchtime(adapter) ||
+	    adapter->strict_priority_enable)
 		new_flags |= IGC_FLAG_TSN_QBV_ENABLED;
 
 	if (is_cbs_enabled(adapter))
 		new_flags |= IGC_FLAG_TSN_QAV_ENABLED;
 
-	if (adapter->strict_priority_enable)
-		new_flags |= IGC_FLAG_TSN_LEGACY_ENABLED;
+	if (adapter->fpe.mmsv.pmac_enabled)
+		new_flags |= IGC_FLAG_TSN_PREEMPT_ENABLED;
 
 	return new_flags;
 }
@@ -125,6 +258,29 @@ static void igc_tsn_tx_arb(struct igc_adapter *adapter, u16 *queue_per_tc)
 	wr32(IGC_TXARB, txarb);
 }
 
+/**
+ * igc_tsn_set_rxpbsize - Set the receive packet buffer size
+ * @adapter: Pointer to the igc_adapter structure
+ * @rxpbs_exp_bmc_be: Value to set the receive packet buffer size, including
+ *                    express buffer, BMC buffer, and Best Effort buffer
+ *
+ * The IGC_RXPBS register value may include allocations for the Express buffer,
+ * BMC buffer, Best Effort buffer, and the timestamp descriptor buffer
+ * (IGC_RXPBS_CFG_TS_EN).
+ */
+static void igc_tsn_set_rxpbsize(struct igc_adapter *adapter,
+				 u32 rxpbs_exp_bmc_be)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 rxpbs = rd32(IGC_RXPBS);
+
+	rxpbs &= ~(IGC_RXPBSIZE_EXP_MASK | IGC_BMC2OSPBSIZE_MASK |
+		   IGC_RXPBSIZE_BE_MASK);
+	rxpbs |= rxpbs_exp_bmc_be;
+
+	wr32(IGC_RXPBS, rxpbs);
+}
+
 /* Returns the TSN specific registers to their default values after
  * the adapter is reset.
  */
@@ -136,15 +292,18 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 	int i;
 
 	wr32(IGC_GTXOFFSET, 0);
-	wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
+	wr32(IGC_TXPBS, IGC_TXPBSIZE_DEFAULT);
 	wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT);
 
+	igc_tsn_set_rxpbsize(adapter, IGC_RXPBSIZE_EXP_BMC_DEFAULT);
+
 	if (igc_is_device_id_i226(hw))
 		igc_tsn_restore_retx_default(adapter);
 
 	tqavctrl = rd32(IGC_TQAVCTRL);
 	tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN |
-		      IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS);
+		      IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS |
+		      IGC_TQAVCTRL_PREEMPT_ENA | IGC_TQAVCTRL_MIN_FRAG_MASK);
 
 	wr32(IGC_TQAVCTRL, tqavctrl);
 
@@ -157,16 +316,12 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 	wr32(IGC_QBVCYCLET_S, 0);
 	wr32(IGC_QBVCYCLET, NSEC_PER_SEC);
 
-	/* Reset mqprio TC configuration. */
-	netdev_reset_tc(adapter->netdev);
-
 	/* Restore the default Tx arbitration: Priority 0 has the highest
 	 * priority and is assigned to queue 0 and so on and so forth.
 	 */
 	igc_tsn_tx_arb(adapter, queue_per_tc);
 
 	adapter->flags &= ~IGC_FLAG_TSN_QBV_ENABLED;
-	adapter->flags &= ~IGC_FLAG_TSN_LEGACY_ENABLED;
 
 	return 0;
 }
@@ -190,53 +345,51 @@ static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter)
 	wr32(IGC_RETX_CTL, retxctl);
 }
 
+static u8 igc_fpe_get_frag_size_mult(const struct igc_fpe_t *fpe)
+{
+	u8 mult = (fpe->tx_min_frag_size / TX_MIN_FRAG_SIZE) - 1;
+
+	return clamp_t(u8, mult, MIN_MULTPLIER_TX_MIN_FRAG,
+		       MAX_MULTPLIER_TX_MIN_FRAG);
+}
+
+u32 igc_fpe_get_supported_frag_size(u32 frag_size)
+{
+	const u32 supported_sizes[] = {64, 128, 192, 256};
+
+	/* Find the smallest supported size that is >= frag_size */
+	for (int i = 0; i < ARRAY_SIZE(supported_sizes); i++) {
+		if (frag_size <= supported_sizes[i])
+			return supported_sizes[i];
+	}
+
+	/* Should not happen */
+	return TX_MAX_FRAG_SIZE;
+}
+
 static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
 	u32 tqavctrl, baset_l, baset_h;
 	u32 sec, nsec, cycle;
 	ktime_t base_time, systim;
+	u32 frag_size_mult;
 	int i;
 
 	wr32(IGC_TSAUXC, 0);
 	wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN);
 	wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN);
 
+	igc_tsn_set_rxpbsize(adapter, IGC_RXPBSIZE_EXP_BMC_BE_TSN);
+
 	if (igc_is_device_id_i226(hw))
 		igc_tsn_set_retx_qbvfullthreshold(adapter);
 
 	if (adapter->strict_priority_enable) {
-		int err;
-
-		err = netdev_set_num_tc(adapter->netdev, adapter->num_tc);
-		if (err)
-			return err;
-
-		for (i = 0; i < adapter->num_tc; i++) {
-			err = netdev_set_tc_queue(adapter->netdev, i, 1,
-						  adapter->queue_per_tc[i]);
-			if (err)
-				return err;
-		}
-
-		/* In case the card is configured with less than four queues. */
-		for (; i < IGC_MAX_TX_QUEUES; i++)
-			adapter->queue_per_tc[i] = i;
-
 		/* Configure queue priorities according to the user provided
 		 * mapping.
 		 */
 		igc_tsn_tx_arb(adapter, adapter->queue_per_tc);
-
-		/* Enable legacy TSN mode which will do strict priority without
-		 * any other TSN features.
-		 */
-		tqavctrl = rd32(IGC_TQAVCTRL);
-		tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN;
-		tqavctrl &= ~IGC_TQAVCTRL_ENHANCED_QAV;
-		wr32(IGC_TQAVCTRL, tqavctrl);
-
-		return 0;
 	}
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
@@ -361,10 +514,16 @@ skip_cbs:
 		wr32(IGC_TXQCTL(i), txqctl);
 	}
 
-	tqavctrl = rd32(IGC_TQAVCTRL) & ~IGC_TQAVCTRL_FUTSCDDIS;
-
+	tqavctrl = rd32(IGC_TQAVCTRL) & ~(IGC_TQAVCTRL_FUTSCDDIS |
+		   IGC_TQAVCTRL_PREEMPT_ENA | IGC_TQAVCTRL_MIN_FRAG_MASK);
 	tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV;
 
+	if (adapter->fpe.mmsv.pmac_enabled)
+		tqavctrl |= IGC_TQAVCTRL_PREEMPT_ENA;
+
+	frag_size_mult = igc_fpe_get_frag_size_mult(&adapter->fpe);
+	tqavctrl |= FIELD_PREP(IGC_TQAVCTRL_MIN_FRAG_MASK, frag_size_mult);
+
 	adapter->qbv_count++;
 
 	cycle = adapter->cycle_time;
@@ -425,6 +584,14 @@ int igc_tsn_reset(struct igc_adapter *adapter)
 	unsigned int new_flags;
 	int err = 0;
 
+	if (adapter->fpe.mmsv.pmac_enabled) {
+		err = igc_enable_empty_addr_recv(adapter);
+		if (err && net_ratelimit())
+			netdev_err(adapter->netdev, "Error adding empty address to MAC filter\n");
+	} else {
+		igc_disable_empty_addr_recv(adapter);
+	}
+
 	new_flags = igc_tsn_new_flags(adapter);
 
 	if (!(new_flags & IGC_FLAG_TSN_ANY_ENABLED))
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h
index 98ec845a86bf..c2a77229207b 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.h
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.h
@@ -4,9 +4,61 @@
 #ifndef _IGC_TSN_H_
 #define _IGC_TSN_H_
 
+#define IGC_RX_MIN_FRAG_SIZE		60
+#define SMD_FRAME_SIZE			60
+
+enum igc_txd_popts_type {
+	SMD_V = 0x01,
+	SMD_R = 0x02,
+};
+
+DECLARE_STATIC_KEY_FALSE(igc_fpe_enabled);
+
+void igc_fpe_init(struct igc_adapter *adapter);
+u32 igc_fpe_get_supported_frag_size(u32 frag_size);
 int igc_tsn_offload_apply(struct igc_adapter *adapter);
 int igc_tsn_reset(struct igc_adapter *adapter);
 void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter);
 bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter);
 
+static inline bool igc_fpe_is_pmac_enabled(struct igc_adapter *adapter)
+{
+	return static_branch_unlikely(&igc_fpe_enabled) &&
+	       adapter->fpe.mmsv.pmac_enabled;
+}
+
+static inline bool igc_fpe_handle_mpacket(struct igc_adapter *adapter,
+					  union igc_adv_rx_desc *rx_desc,
+					  unsigned int size, void *pktbuf)
+{
+	u32 status_error = le32_to_cpu(rx_desc->wb.upper.status_error);
+	int smd;
+
+	smd = FIELD_GET(IGC_RXDADV_STAT_SMD_TYPE_MASK, status_error);
+	if (smd != IGC_RXD_STAT_SMD_TYPE_V && smd != IGC_RXD_STAT_SMD_TYPE_R)
+		return false;
+
+	if (size == SMD_FRAME_SIZE && mem_is_zero(pktbuf, SMD_FRAME_SIZE)) {
+		struct ethtool_mmsv *mmsv = &adapter->fpe.mmsv;
+		enum ethtool_mmsv_event event;
+
+		if (smd == IGC_RXD_STAT_SMD_TYPE_V)
+			event = ETHTOOL_MMSV_LP_SENT_VERIFY_MPACKET;
+		else
+			event = ETHTOOL_MMSV_LP_SENT_RESPONSE_MPACKET;
+
+		ethtool_mmsv_event_handle(mmsv, event);
+	}
+
+	return true;
+}
+
+static inline bool igc_fpe_transmitted_smd_v(union igc_adv_tx_desc *tx_desc)
+{
+	u32 olinfo_status = le32_to_cpu(tx_desc->read.olinfo_status);
+	u8 smd = FIELD_GET(IGC_TXD_POPTS_SMD_MASK, olinfo_status);
+
+	return smd == SMD_V;
+}
+
 #endif /* _IGC_BASE_H */
diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile
index b456d102655a..2e7738f41c58 100644
--- a/drivers/net/ethernet/intel/ixgbe/Makefile
+++ b/drivers/net/ethernet/intel/ixgbe/Makefile
@@ -4,12 +4,14 @@
 # Makefile for the Intel(R) 10GbE PCI Express ethernet driver
 #
 
+subdir-ccflags-y += -I$(src)
 obj-$(CONFIG_IXGBE) += ixgbe.o
 
 ixgbe-y := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
            ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
            ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \
-           ixgbe_xsk.o ixgbe_e610.o
+           ixgbe_xsk.o ixgbe_e610.o devlink/devlink.o ixgbe_fw_update.o \
+	   devlink/region.o
 
 ixgbe-$(CONFIG_IXGBE_DCB) +=  ixgbe_dcb.o ixgbe_dcb_82598.o \
                               ixgbe_dcb_82599.o ixgbe_dcb_nl.o
diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c
new file mode 100644
index 000000000000..54f1b83dfe42
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c
@@ -0,0 +1,557 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025, Intel Corporation. */
+
+#include "ixgbe.h"
+#include "devlink.h"
+#include "ixgbe_fw_update.h"
+
+struct ixgbe_info_ctx {
+	char buf[128];
+	struct ixgbe_orom_info pending_orom;
+	struct ixgbe_nvm_info pending_nvm;
+	struct ixgbe_netlist_info pending_netlist;
+	struct ixgbe_hw_dev_caps dev_caps;
+};
+
+enum ixgbe_devlink_version_type {
+	IXGBE_DL_VERSION_RUNNING,
+	IXGBE_DL_VERSION_STORED
+};
+
+static void ixgbe_info_get_dsn(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx)
+{
+	u8 dsn[8];
+
+	/* Copy the DSN into an array in Big Endian format */
+	put_unaligned_be64(pci_get_dsn(adapter->pdev), dsn);
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%8phD", dsn);
+}
+
+static void ixgbe_info_orom_ver(struct ixgbe_adapter *adapter,
+				struct ixgbe_info_ctx *ctx,
+				enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_nvm_version nvm_ver;
+
+	ctx->buf[0] = '\0';
+
+	if (hw->mac.type == ixgbe_mac_e610) {
+		struct ixgbe_orom_info *orom = &adapter->hw.flash.orom;
+
+		if (type == IXGBE_DL_VERSION_STORED &&
+		    ctx->dev_caps.common_cap.nvm_update_pending_orom)
+			orom = &ctx->pending_orom;
+
+		snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u",
+			 orom->major, orom->build, orom->patch);
+		return;
+	}
+
+	ixgbe_get_oem_prod_version(hw, &nvm_ver);
+	if (nvm_ver.oem_valid) {
+		snprintf(ctx->buf, sizeof(ctx->buf), "%x.%x.%x",
+			 nvm_ver.oem_major, nvm_ver.oem_minor,
+			 nvm_ver.oem_release);
+
+		return;
+	}
+
+	ixgbe_get_orom_version(hw, &nvm_ver);
+	if (nvm_ver.or_valid)
+		snprintf(ctx->buf, sizeof(ctx->buf), "%d.%d.%d",
+			 nvm_ver.or_major, nvm_ver.or_build, nvm_ver.or_patch);
+}
+
+static void ixgbe_info_eetrack(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx,
+			       enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_nvm_version nvm_ver;
+
+	if (hw->mac.type == ixgbe_mac_e610) {
+		u32 eetrack = hw->flash.nvm.eetrack;
+
+		if (type == IXGBE_DL_VERSION_STORED &&
+		    ctx->dev_caps.common_cap.nvm_update_pending_nvm)
+			eetrack = ctx->pending_nvm.eetrack;
+
+		snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", eetrack);
+		return;
+	}
+
+	ixgbe_get_oem_prod_version(hw, &nvm_ver);
+
+	/* No ETRACK version for OEM */
+	if (nvm_ver.oem_valid) {
+		ctx->buf[0] = '\0';
+		return;
+	}
+
+	ixgbe_get_etk_id(hw, &nvm_ver);
+	snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", nvm_ver.etk_id);
+}
+
+static void ixgbe_info_fw_api(struct ixgbe_adapter *adapter,
+			      struct ixgbe_info_ctx *ctx)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u",
+		 hw->api_maj_ver, hw->api_min_ver, hw->api_patch);
+}
+
+static void ixgbe_info_fw_build(struct ixgbe_adapter *adapter,
+				struct ixgbe_info_ctx *ctx)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", hw->fw_build);
+}
+
+static void ixgbe_info_fw_srev(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx,
+			       enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_nvm)
+		nvm = &ctx->pending_nvm;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%u", nvm->srev);
+}
+
+static void ixgbe_info_orom_srev(struct ixgbe_adapter *adapter,
+				 struct ixgbe_info_ctx *ctx,
+				 enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_orom_info *orom = &adapter->hw.flash.orom;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_orom)
+		orom = &ctx->pending_orom;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%u", orom->srev);
+}
+
+static void ixgbe_info_nvm_ver(struct ixgbe_adapter *adapter,
+			       struct ixgbe_info_ctx *ctx,
+			       enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_nvm)
+		nvm = &ctx->pending_nvm;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "%x.%02x", nvm->major, nvm->minor);
+}
+
+static void ixgbe_info_netlist_ver(struct ixgbe_adapter *adapter,
+				   struct ixgbe_info_ctx *ctx,
+				   enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_netlist_info *netlist = &adapter->hw.flash.netlist;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_netlist)
+		netlist = &ctx->pending_netlist;
+
+	/* The netlist version fields are BCD formatted */
+	snprintf(ctx->buf, sizeof(ctx->buf), "%x.%x.%x-%x.%x.%x",
+		 netlist->major, netlist->minor,
+		 netlist->type >> 16, netlist->type & 0xFFFF,
+		 netlist->rev, netlist->cust_ver);
+}
+
+static void ixgbe_info_netlist_build(struct ixgbe_adapter *adapter,
+				     struct ixgbe_info_ctx *ctx,
+				     enum ixgbe_devlink_version_type type)
+{
+	struct ixgbe_netlist_info *netlist = &adapter->hw.flash.netlist;
+
+	if (type == IXGBE_DL_VERSION_STORED &&
+	    ctx->dev_caps.common_cap.nvm_update_pending_netlist)
+		netlist = &ctx->pending_netlist;
+
+	snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", netlist->hash);
+}
+
+static int ixgbe_set_ctx_dev_caps(struct ixgbe_hw *hw,
+				  struct ixgbe_info_ctx *ctx,
+				  struct netlink_ext_ack *extack)
+{
+	bool *pending_orom, *pending_nvm, *pending_netlist;
+	int err;
+
+	err = ixgbe_discover_dev_caps(hw, &ctx->dev_caps);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to discover device capabilities");
+		return err;
+	}
+
+	pending_orom = &ctx->dev_caps.common_cap.nvm_update_pending_orom;
+	pending_nvm = &ctx->dev_caps.common_cap.nvm_update_pending_nvm;
+	pending_netlist = &ctx->dev_caps.common_cap.nvm_update_pending_netlist;
+
+	if (*pending_orom) {
+		err = ixgbe_get_inactive_orom_ver(hw, &ctx->pending_orom);
+		if (err)
+			*pending_orom = false;
+	}
+
+	if (*pending_nvm) {
+		err = ixgbe_get_inactive_nvm_ver(hw, &ctx->pending_nvm);
+		if (err)
+			*pending_nvm = false;
+	}
+
+	if (*pending_netlist) {
+		err = ixgbe_get_inactive_netlist_ver(hw, &ctx->pending_netlist);
+		if (err)
+			*pending_netlist = false;
+	}
+
+	return 0;
+}
+
+static int ixgbe_devlink_info_get_e610(struct ixgbe_adapter *adapter,
+				       struct devlink_info_req *req,
+				       struct ixgbe_info_ctx *ctx)
+{
+	int err;
+
+	ixgbe_info_fw_api(adapter, ctx);
+	err = devlink_info_version_running_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW_MGMT_API,
+					       ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_fw_build(adapter, ctx);
+	err = devlink_info_version_running_put(req, "fw.mgmt.build", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_fw_srev(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.mgmt.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_orom_srev(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.undi.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_nvm_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.psid.api", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req, "fw.netlist", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_build(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	return devlink_info_version_running_put(req, "fw.netlist.build",
+						ctx->buf);
+}
+
+static int
+ixgbe_devlink_pending_info_get_e610(struct ixgbe_adapter *adapter,
+				    struct devlink_info_req *req,
+				    struct ixgbe_info_ctx *ctx)
+{
+	int err;
+
+	ixgbe_info_orom_ver(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req,
+					      DEVLINK_INFO_VERSION_GENERIC_FW_UNDI,
+					      ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_eetrack(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req,
+					      DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID,
+					      ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_fw_srev(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.mgmt.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_orom_srev(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.undi.srev", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_nvm_ver(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.psid.api", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_ver(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	err = devlink_info_version_stored_put(req, "fw.netlist", ctx->buf);
+	if (err)
+		return err;
+
+	ixgbe_info_netlist_build(adapter, ctx, IXGBE_DL_VERSION_STORED);
+	return devlink_info_version_stored_put(req, "fw.netlist.build",
+					       ctx->buf);
+}
+
+static int ixgbe_devlink_info_get(struct devlink *devlink,
+				  struct devlink_info_req *req,
+				  struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_info_ctx *ctx;
+	int err;
+
+	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	if (hw->mac.type == ixgbe_mac_e610)
+		ixgbe_refresh_fw_version(adapter);
+
+	ixgbe_info_get_dsn(adapter, ctx);
+	err = devlink_info_serial_number_put(req, ctx->buf);
+	if (err)
+		goto free_ctx;
+
+	err = hw->eeprom.ops.read_pba_string(hw, ctx->buf, sizeof(ctx->buf));
+	if (err)
+		goto free_ctx;
+
+	err = devlink_info_version_fixed_put(req,
+					     DEVLINK_INFO_VERSION_GENERIC_BOARD_ID,
+					     ctx->buf);
+	if (err)
+		goto free_ctx;
+
+	ixgbe_info_orom_ver(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW_UNDI,
+					       ctx->buf);
+	if (err)
+		goto free_ctx;
+
+	ixgbe_info_eetrack(adapter, ctx, IXGBE_DL_VERSION_RUNNING);
+	err = devlink_info_version_running_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID,
+					       ctx->buf);
+	if (err || hw->mac.type != ixgbe_mac_e610)
+		goto free_ctx;
+
+	err = ixgbe_set_ctx_dev_caps(hw, ctx, extack);
+	if (err)
+		goto free_ctx;
+
+	err = ixgbe_devlink_info_get_e610(adapter, req, ctx);
+	if (err)
+		goto free_ctx;
+
+	err = ixgbe_devlink_pending_info_get_e610(adapter, req, ctx);
+free_ctx:
+	kfree(ctx);
+	return err;
+}
+
+/**
+ * ixgbe_devlink_reload_empr_start - Start EMP reset to activate new firmware
+ * @devlink: pointer to the devlink instance to reload
+ * @netns_change: if true, the network namespace is changing
+ * @action: the action to perform. Must be DEVLINK_RELOAD_ACTION_FW_ACTIVATE
+ * @limit: limits on what reload should do, such as not resetting
+ * @extack: netlink extended ACK structure
+ *
+ * Allow user to activate new Embedded Management Processor firmware by
+ * issuing device specific EMP reset. Called in response to
+ * a DEVLINK_CMD_RELOAD with the DEVLINK_RELOAD_ACTION_FW_ACTIVATE.
+ *
+ * Note that teardown and rebuild of the driver state happens automatically as
+ * part of an interrupt and watchdog task. This is because all physical
+ * functions on the device must be able to reset when an EMP reset occurs from
+ * any source.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_devlink_reload_empr_start(struct devlink *devlink,
+					   bool netns_change,
+					   enum devlink_reload_action action,
+					   enum devlink_reload_limit limit,
+					   struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 pending;
+	int err;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		return -EOPNOTSUPP;
+
+	err = ixgbe_get_pending_updates(adapter, &pending, extack);
+	if (err)
+		return err;
+
+	/* Pending is a bitmask of which flash banks have a pending update,
+	 * including the main NVM bank, the Option ROM bank, and the netlist
+	 * bank. If any of these bits are set, then there is a pending update
+	 * waiting to be activated.
+	 */
+	if (!pending) {
+		NL_SET_ERR_MSG_MOD(extack, "No pending firmware update");
+		return -ECANCELED;
+	}
+
+	if (adapter->fw_emp_reset_disabled) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "EMP reset is not available. To activate firmware, a reboot or power cycle is needed");
+		return -ECANCELED;
+	}
+
+	err = ixgbe_aci_nvm_update_empr(hw);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to trigger EMP device reset to reload firmware");
+
+	return err;
+}
+
+/*Wait for 10 sec with 0.5 sec tic. EMPR takes no less than half of a sec */
+#define IXGBE_DEVLINK_RELOAD_TIMEOUT_SEC	20
+
+/**
+ * ixgbe_devlink_reload_empr_finish - finishes EMP reset
+ * @devlink: pointer to the devlink instance
+ * @action: the action to perform.
+ * @limit: limits on what reload should do
+ * @actions_performed: actions performed
+ * @extack: netlink extended ACK structure
+ *
+ * Wait for new NVM to be loaded during EMP reset.
+ *
+ * Return: -ETIME when timer is exceeded, 0 on success.
+ */
+static int ixgbe_devlink_reload_empr_finish(struct devlink *devlink,
+					    enum devlink_reload_action action,
+					    enum devlink_reload_limit limit,
+					    u32 *actions_performed,
+					    struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i = 0;
+	u32 fwsm;
+
+	do {
+		/* Just right away after triggering EMP reset the FWSM register
+		 * may be not cleared yet, so begin the loop with the delay
+		 * in order to not check the not updated register.
+		 */
+		mdelay(500);
+
+		fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
+
+		if (i++ >= IXGBE_DEVLINK_RELOAD_TIMEOUT_SEC)
+			return -ETIME;
+
+	} while (!(fwsm & IXGBE_FWSM_FW_VAL_BIT));
+
+	*actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE);
+
+	adapter->flags2 &= ~(IXGBE_FLAG2_API_MISMATCH |
+			     IXGBE_FLAG2_FW_ROLLBACK);
+
+	return 0;
+}
+
+static const struct devlink_ops ixgbe_devlink_ops = {
+	.info_get = ixgbe_devlink_info_get,
+	.supported_flash_update_params =
+		DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK,
+	.flash_update = ixgbe_flash_pldm_image,
+	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE),
+	.reload_down = ixgbe_devlink_reload_empr_start,
+	.reload_up = ixgbe_devlink_reload_empr_finish,
+};
+
+/**
+ * ixgbe_allocate_devlink - Allocate devlink instance
+ * @dev: device to allocate devlink for
+ *
+ * Allocate a devlink instance for this physical function.
+ *
+ * Return: pointer to the device adapter structure on success,
+ * ERR_PTR(-ENOMEM) when allocation failed.
+ */
+struct ixgbe_adapter *ixgbe_allocate_devlink(struct device *dev)
+{
+	struct ixgbe_adapter *adapter;
+	struct devlink *devlink;
+
+	devlink = devlink_alloc(&ixgbe_devlink_ops, sizeof(*adapter), dev);
+	if (!devlink)
+		return ERR_PTR(-ENOMEM);
+
+	adapter = devlink_priv(devlink);
+	adapter->devlink = devlink;
+
+	return adapter;
+}
+
+/**
+ * ixgbe_devlink_set_switch_id - Set unique switch ID based on PCI DSN
+ * @adapter: pointer to the device adapter structure
+ * @ppid: struct with switch id information
+ */
+static void ixgbe_devlink_set_switch_id(struct ixgbe_adapter *adapter,
+					struct netdev_phys_item_id *ppid)
+{
+	u64 id = pci_get_dsn(adapter->pdev);
+
+	ppid->id_len = sizeof(id);
+	put_unaligned_be64(id, &ppid->id);
+}
+
+/**
+ * ixgbe_devlink_register_port - Register devlink port
+ * @adapter: pointer to the device adapter structure
+ *
+ * Create and register a devlink_port for this physical function.
+ *
+ * Return: 0 on success, error code on failure.
+ */
+int ixgbe_devlink_register_port(struct ixgbe_adapter *adapter)
+{
+	struct devlink_port *devlink_port = &adapter->devlink_port;
+	struct devlink *devlink = adapter->devlink;
+	struct device *dev = &adapter->pdev->dev;
+	struct devlink_port_attrs attrs = {};
+	int err;
+
+	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+	attrs.phys.port_number = adapter->hw.bus.func;
+	ixgbe_devlink_set_switch_id(adapter, &attrs.switch_id);
+
+	devlink_port_attrs_set(devlink_port, &attrs);
+
+	err = devl_port_register(devlink, devlink_port, 0);
+	if (err) {
+		dev_err(dev,
+			"devlink port registration failed, err %d\n", err);
+	}
+
+	return err;
+}
diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h
new file mode 100644
index 000000000000..381558058048
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025, Intel Corporation. */
+
+#ifndef _IXGBE_DEVLINK_H_
+#define _IXGBE_DEVLINK_H_
+
+struct ixgbe_adapter *ixgbe_allocate_devlink(struct device *dev);
+int ixgbe_devlink_register_port(struct ixgbe_adapter *adapter);
+void ixgbe_devlink_init_regions(struct ixgbe_adapter *adapter);
+void ixgbe_devlink_destroy_regions(struct ixgbe_adapter *adapter);
+
+#endif /* _IXGBE_DEVLINK_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/region.c b/drivers/net/ethernet/intel/ixgbe/devlink/region.c
new file mode 100644
index 000000000000..76f6571c3c34
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/devlink/region.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025, Intel Corporation. */
+
+#include "ixgbe.h"
+#include "devlink.h"
+
+#define IXGBE_DEVLINK_READ_BLK_SIZE (1024 * 1024)
+
+static const struct devlink_region_ops ixgbe_nvm_region_ops;
+static const struct devlink_region_ops ixgbe_sram_region_ops;
+
+static int ixgbe_devlink_parse_region(struct ixgbe_hw *hw,
+				      const struct devlink_region_ops *ops,
+				      bool *read_shadow_ram, u32 *nvm_size)
+{
+	if (ops == &ixgbe_nvm_region_ops) {
+		*read_shadow_ram = false;
+		*nvm_size = hw->flash.flash_size;
+	} else if (ops == &ixgbe_sram_region_ops) {
+		*read_shadow_ram = true;
+		*nvm_size = hw->flash.sr_words * 2u;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_devlink_nvm_snapshot - Capture a snapshot of the NVM content
+ * @devlink: the devlink instance
+ * @ops: the devlink region being snapshotted
+ * @extack: extended ACK response structure
+ * @data: on exit points to snapshot data buffer
+ *
+ * This function is called in response to the DEVLINK_CMD_REGION_NEW cmd.
+ *
+ * Capture a snapshot of the whole requested NVM region.
+ *
+ * No need to worry with freeing @data, devlink core takes care if it.
+ *
+ * Return: 0 on success, -EOPNOTSUPP for unsupported regions, -EBUSY when
+ * cannot lock NVM, -ENOMEM when cannot alloc mem and -EIO when error
+ * occurs during reading.
+ */
+static int ixgbe_devlink_nvm_snapshot(struct devlink *devlink,
+				      const struct devlink_region_ops *ops,
+				      struct netlink_ext_ack *extack, u8 **data)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool read_shadow_ram;
+	u8 *nvm_data, *buf;
+	u32 nvm_size, left;
+	u8 num_blks;
+	int err;
+
+	err = ixgbe_devlink_parse_region(hw, ops, &read_shadow_ram, &nvm_size);
+	if (err)
+		return err;
+
+	nvm_data = kvzalloc(nvm_size, GFP_KERNEL);
+	if (!nvm_data)
+		return -ENOMEM;
+
+	num_blks = DIV_ROUND_UP(nvm_size, IXGBE_DEVLINK_READ_BLK_SIZE);
+	buf = nvm_data;
+	left = nvm_size;
+
+	for (int i = 0; i < num_blks; i++) {
+		u32 read_sz = min_t(u32, IXGBE_DEVLINK_READ_BLK_SIZE, left);
+
+		/* Need to acquire NVM lock during each loop run because the
+		 * total period of reading whole NVM is longer than the maximum
+		 * period the lock can be taken defined by the IXGBE_NVM_TIMEOUT.
+		 */
+		err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to acquire NVM semaphore");
+			kvfree(nvm_data);
+			return -EBUSY;
+		}
+
+		err = ixgbe_read_flat_nvm(hw, i * IXGBE_DEVLINK_READ_BLK_SIZE,
+					  &read_sz, buf, read_shadow_ram);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to read RAM content");
+			ixgbe_release_nvm(hw);
+			kvfree(nvm_data);
+			return -EIO;
+		}
+
+		ixgbe_release_nvm(hw);
+
+		buf += read_sz;
+		left -= read_sz;
+	}
+
+	*data = nvm_data;
+	return 0;
+}
+
+/**
+ * ixgbe_devlink_devcaps_snapshot - Capture a snapshot of device capabilities
+ * @devlink: the devlink instance
+ * @ops: the devlink region being snapshotted
+ * @extack: extended ACK response structure
+ * @data: on exit points to snapshot data buffer
+ *
+ * This function is called in response to the DEVLINK_CMD_REGION_NEW for
+ * the device-caps devlink region.
+ *
+ * Capture a snapshot of the device capabilities reported by firmware.
+ *
+ * No need to worry with freeing @data, devlink core takes care if it.
+ *
+ * Return: 0 on success, -ENOMEM when cannot alloc mem, or return code of
+ * the reading operation.
+ */
+static int ixgbe_devlink_devcaps_snapshot(struct devlink *devlink,
+					  const struct devlink_region_ops *ops,
+					  struct netlink_ext_ack *extack,
+					  u8 **data)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_aci_cmd_list_caps_elem *caps;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	caps = kvzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL);
+	if (!caps)
+		return -ENOMEM;
+
+	err = ixgbe_aci_list_caps(hw, caps, IXGBE_ACI_MAX_BUFFER_SIZE, NULL,
+				  ixgbe_aci_opc_list_dev_caps);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to read device capabilities");
+		kvfree(caps);
+		return err;
+	}
+
+	*data = (u8 *)caps;
+	return 0;
+}
+
+/**
+ * ixgbe_devlink_nvm_read - Read a portion of NVM flash content
+ * @devlink: the devlink instance
+ * @ops: the devlink region to snapshot
+ * @extack: extended ACK response structure
+ * @offset: the offset to start at
+ * @size: the amount to read
+ * @data: the data buffer to read into
+ *
+ * This function is called in response to DEVLINK_CMD_REGION_READ to directly
+ * read a section of the NVM contents.
+ *
+ * Read from either the nvm-flash region either shadow-ram region.
+ *
+ * Return: 0 on success, -EOPNOTSUPP for unsupported regions, -EBUSY when
+ * cannot lock NVM, -ERANGE when buffer limit exceeded and -EIO when error
+ * occurs during reading.
+ */
+static int ixgbe_devlink_nvm_read(struct devlink *devlink,
+				  const struct devlink_region_ops *ops,
+				  struct netlink_ext_ack *extack,
+				  u64 offset, u32 size, u8 *data)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool read_shadow_ram;
+	u32 nvm_size;
+	int err;
+
+	err = ixgbe_devlink_parse_region(hw, ops, &read_shadow_ram, &nvm_size);
+	if (err)
+		return err;
+
+	if (offset + size > nvm_size) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot read beyond the region size");
+		return -ERANGE;
+	}
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore");
+		return -EBUSY;
+	}
+
+	err = ixgbe_read_flat_nvm(hw, (u32)offset, &size, data, read_shadow_ram);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents");
+		ixgbe_release_nvm(hw);
+		return -EIO;
+	}
+
+	ixgbe_release_nvm(hw);
+	return 0;
+}
+
+static const struct devlink_region_ops ixgbe_nvm_region_ops = {
+	.name = "nvm-flash",
+	.destructor = kvfree,
+	.snapshot = ixgbe_devlink_nvm_snapshot,
+	.read = ixgbe_devlink_nvm_read,
+};
+
+static const struct devlink_region_ops ixgbe_sram_region_ops = {
+	.name = "shadow-ram",
+	.destructor = kvfree,
+	.snapshot = ixgbe_devlink_nvm_snapshot,
+	.read = ixgbe_devlink_nvm_read,
+};
+
+static const struct devlink_region_ops ixgbe_devcaps_region_ops = {
+	.name = "device-caps",
+	.destructor = kvfree,
+	.snapshot = ixgbe_devlink_devcaps_snapshot,
+};
+
+/**
+ * ixgbe_devlink_init_regions - Initialize devlink regions
+ * @adapter: adapter instance
+ *
+ * Create devlink regions used to enable access to dump the contents of the
+ * flash memory of the device.
+ */
+void ixgbe_devlink_init_regions(struct ixgbe_adapter *adapter)
+{
+	struct devlink *devlink = adapter->devlink;
+	struct device *dev = &adapter->pdev->dev;
+	u64 nvm_size, sram_size;
+
+	if (adapter->hw.mac.type != ixgbe_mac_e610)
+		return;
+
+	nvm_size = adapter->hw.flash.flash_size;
+	adapter->nvm_region = devl_region_create(devlink, &ixgbe_nvm_region_ops,
+						 1, nvm_size);
+	if (IS_ERR(adapter->nvm_region)) {
+		dev_err(dev,
+			"Failed to create NVM devlink region, err %ld\n",
+			PTR_ERR(adapter->nvm_region));
+		adapter->nvm_region = NULL;
+	}
+
+	sram_size = adapter->hw.flash.sr_words * 2u;
+	adapter->sram_region = devl_region_create(devlink, &ixgbe_sram_region_ops,
+						  1, sram_size);
+	if (IS_ERR(adapter->sram_region)) {
+		dev_err(dev,
+			"Failed to create shadow-ram devlink region, err %ld\n",
+			PTR_ERR(adapter->sram_region));
+		adapter->sram_region = NULL;
+	}
+
+	adapter->devcaps_region = devl_region_create(devlink,
+						     &ixgbe_devcaps_region_ops,
+						     10, IXGBE_ACI_MAX_BUFFER_SIZE);
+	if (IS_ERR(adapter->devcaps_region)) {
+		dev_err(dev,
+			"Failed to create device-caps devlink region, err %ld\n",
+			PTR_ERR(adapter->devcaps_region));
+		adapter->devcaps_region = NULL;
+	}
+}
+
+/**
+ * ixgbe_devlink_destroy_regions - Destroy devlink regions
+ * @adapter: adapter instance
+ *
+ * Remove previously created regions for this adapter instance.
+ */
+void ixgbe_devlink_destroy_regions(struct ixgbe_adapter *adapter)
+{
+	if (adapter->hw.mac.type != ixgbe_mac_e610)
+		return;
+
+	if (adapter->nvm_region)
+		devl_region_destroy(adapter->nvm_region);
+
+	if (adapter->sram_region)
+		devl_region_destroy(adapter->sram_region);
+
+	if (adapter->devcaps_region)
+		devl_region_destroy(adapter->devcaps_region);
+}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index e6a380d4929b..47311b134a7a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -17,6 +17,8 @@
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 
+#include <net/devlink.h>
+
 #include "ixgbe_type.h"
 #include "ixgbe_common.h"
 #include "ixgbe_dcb.h"
@@ -612,6 +614,11 @@ struct ixgbe_adapter {
 	struct bpf_prog *xdp_prog;
 	struct pci_dev *pdev;
 	struct mii_bus *mii_bus;
+	struct devlink *devlink;
+	struct devlink_port devlink_port;
+	struct devlink_region *nvm_region;
+	struct devlink_region *sram_region;
+	struct devlink_region *devcaps_region;
 
 	unsigned long state;
 
@@ -667,6 +674,8 @@ struct ixgbe_adapter {
 #define IXGBE_FLAG2_PHY_FW_LOAD_FAILED		BIT(20)
 #define IXGBE_FLAG2_NO_MEDIA			BIT(21)
 #define IXGBE_FLAG2_MOD_POWER_UNSUPPORTED	BIT(22)
+#define IXGBE_FLAG2_API_MISMATCH		BIT(23)
+#define IXGBE_FLAG2_FW_ROLLBACK			BIT(24)
 
 	/* Tx fast path data */
 	int num_tx_queues;
@@ -755,6 +764,8 @@ struct ixgbe_adapter {
 	u32 atr_sample_rate;
 	spinlock_t fdir_perfect_lock;
 
+	bool fw_emp_reset_disabled;
+
 #ifdef IXGBE_FCOE
 	struct ixgbe_fcoe fcoe;
 #endif /* IXGBE_FCOE */
@@ -830,6 +841,17 @@ struct ixgbe_adapter {
 	spinlock_t vfs_lock;
 };
 
+struct ixgbe_netdevice_priv {
+	struct ixgbe_adapter *adapter;
+};
+
+static inline struct ixgbe_adapter *ixgbe_from_netdev(struct net_device *netdev)
+{
+	struct ixgbe_netdevice_priv *priv = netdev_priv(netdev);
+
+	return priv->adapter;
+}
+
 static inline int ixgbe_determine_xdp_q_idx(int cpu)
 {
 	if (static_key_enabled(&ixgbe_xdp_locking_key))
@@ -945,6 +967,8 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter);
 int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter);
 bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
 			 u16 subdevice_id);
+void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter);
+void ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter);
 #ifdef CONFIG_PCI_IOV
 void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter);
 #endif
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
index 4aaaea3b5f8f..444da982593f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
@@ -1169,6 +1169,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_82598 = {
 	.calc_checksum          = &ixgbe_calc_eeprom_checksum_generic,
 	.validate_checksum	= &ixgbe_validate_eeprom_checksum_generic,
 	.update_checksum	= &ixgbe_update_eeprom_checksum_generic,
+	.read_pba_string        = &ixgbe_read_pba_string_generic,
 };
 
 static const struct ixgbe_phy_operations phy_ops_82598 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index 964988b4d58b..d5b1b974b4a3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -2230,6 +2230,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_82599 = {
 	.calc_checksum		= &ixgbe_calc_eeprom_checksum_generic,
 	.validate_checksum	= &ixgbe_validate_eeprom_checksum_generic,
 	.update_checksum	= &ixgbe_update_eeprom_checksum_generic,
+	.read_pba_string        = &ixgbe_read_pba_string_generic,
 };
 
 static const struct ixgbe_phy_operations phy_ops_82599 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 7beaf6ea57f9..5784d5d1896e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -332,6 +332,7 @@ int ixgbe_start_hw_generic(struct ixgbe_hw *hw)
  * Devices in the second generation:
  *     82599
  *     X540
+ *     E610
  **/
 int ixgbe_start_hw_gen2(struct ixgbe_hw *hw)
 {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
index 19d6b6fa8fb3..3dd5a16a14df 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
@@ -118,14 +118,14 @@ static int ixgbe_copy_dcb_cfg(struct ixgbe_adapter *adapter, int tc_max)
 
 static u8 ixgbe_dcbnl_get_state(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	return !!(adapter->flags & IXGBE_FLAG_DCB_ENABLED);
 }
 
 static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* Fail command if not in CEE mode */
 	if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
@@ -142,7 +142,7 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
 static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev,
 					 u8 *perm_addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int i, j;
 
 	memset(perm_addr, 0xff, MAX_ADDR_LEN);
@@ -167,7 +167,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 					 u8 prio, u8 bwg_id, u8 bw_pct,
 					 u8 up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (prio != DCB_ATTR_VALUE_UNDEFINED)
 		adapter->temp_dcb_cfg.tc_config[tc].path[0].prio_type = prio;
@@ -184,7 +184,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
 					  u8 bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] = bw_pct;
 }
@@ -193,7 +193,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 					 u8 prio, u8 bwg_id, u8 bw_pct,
 					 u8 up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (prio != DCB_ATTR_VALUE_UNDEFINED)
 		adapter->temp_dcb_cfg.tc_config[tc].path[1].prio_type = prio;
@@ -210,7 +210,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 					  u8 bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] = bw_pct;
 }
@@ -219,7 +219,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 					 u8 *prio, u8 *bwg_id, u8 *bw_pct,
 					 u8 *up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*prio = adapter->dcb_cfg.tc_config[tc].path[0].prio_type;
 	*bwg_id = adapter->dcb_cfg.tc_config[tc].path[0].bwg_id;
@@ -230,7 +230,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_get_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
 					  u8 *bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*bw_pct = adapter->dcb_cfg.bw_percentage[0][bwg_id];
 }
@@ -239,7 +239,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 					 u8 *prio, u8 *bwg_id, u8 *bw_pct,
 					 u8 *up_map)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*prio = adapter->dcb_cfg.tc_config[tc].path[1].prio_type;
 	*bwg_id = adapter->dcb_cfg.tc_config[tc].path[1].bwg_id;
@@ -250,7 +250,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 					  u8 *bw_pct)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*bw_pct = adapter->dcb_cfg.bw_percentage[1][bwg_id];
 }
@@ -258,7 +258,7 @@ static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
 				    u8 setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc = setting;
 	if (adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc !=
@@ -269,14 +269,14 @@ static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
 static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
 				    u8 *setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	*setting = adapter->dcb_cfg.tc_config[priority].dcb_pfc;
 }
 
 static void ixgbe_dcbnl_devreset(struct net_device *dev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
 		usleep_range(1000, 2000);
@@ -295,7 +295,7 @@ static void ixgbe_dcbnl_devreset(struct net_device *dev)
 
 static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_dcb_config *dcb_cfg = &adapter->dcb_cfg;
 	struct ixgbe_hw *hw = &adapter->hw;
 	int ret = DCB_NO_HW_CHG;
@@ -383,7 +383,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 
 static u8 ixgbe_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	switch (capid) {
 	case DCB_CAP_ATTR_PG:
@@ -420,7 +420,7 @@ static u8 ixgbe_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap)
 
 static int ixgbe_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
 		switch (tcid) {
@@ -447,14 +447,14 @@ static int ixgbe_dcbnl_setnumtcs(struct net_device *netdev, int tcid, u8 num)
 
 static u8 ixgbe_dcbnl_getpfcstate(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	return adapter->dcb_cfg.pfc_mode_enable;
 }
 
 static void ixgbe_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->temp_dcb_cfg.pfc_mode_enable = state;
 }
@@ -471,7 +471,7 @@ static void ixgbe_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
  */
 static int ixgbe_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct dcb_app app = {
 				.selector = idtype,
 				.protocol = id,
@@ -486,7 +486,7 @@ static int ixgbe_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
 static int ixgbe_dcbnl_ieee_getets(struct net_device *dev,
 				   struct ieee_ets *ets)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ieee_ets *my_ets = adapter->ixgbe_ieee_ets;
 
 	ets->ets_cap = adapter->dcb_cfg.num_tcs.pg_tcs;
@@ -506,7 +506,7 @@ static int ixgbe_dcbnl_ieee_getets(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_setets(struct net_device *dev,
 				   struct ieee_ets *ets)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN;
 	int i, err;
 	__u8 max_tc = 0;
@@ -559,7 +559,7 @@ static int ixgbe_dcbnl_ieee_setets(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev,
 				   struct ieee_pfc *pfc)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ieee_pfc *my_pfc = adapter->ixgbe_ieee_pfc;
 	int i;
 
@@ -584,7 +584,7 @@ static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev,
 				   struct ieee_pfc *pfc)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u8 *prio_tc;
 	int err;
@@ -616,7 +616,7 @@ static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev,
 				   struct dcb_app *app)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int err;
 
 	if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
@@ -661,7 +661,7 @@ static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev,
 static int ixgbe_dcbnl_ieee_delapp(struct net_device *dev,
 				   struct dcb_app *app)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int err;
 
 	if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
@@ -705,13 +705,13 @@ static int ixgbe_dcbnl_ieee_delapp(struct net_device *dev,
 
 static u8 ixgbe_dcbnl_getdcbx(struct net_device *dev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	return adapter->dcbx_cap;
 }
 
 static u8 ixgbe_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ieee_ets ets = {0};
 	struct ieee_pfc pfc = {0};
 	int err = 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
index 00935747c8c5..71ea25de1bac 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
@@ -344,6 +344,40 @@ void ixgbe_fill_dflt_direct_cmd_desc(struct ixgbe_aci_desc *desc, u16 opcode)
 }
 
 /**
+ * ixgbe_aci_get_fw_ver - Get the firmware version
+ * @hw: pointer to the HW struct
+ *
+ * Get the firmware version using ACI command (0x0001).
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_aci_get_fw_ver(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_cmd_get_ver *resp;
+	struct ixgbe_aci_desc desc;
+	int err;
+
+	resp = &desc.params.get_ver;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_ver);
+
+	err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+	if (!err) {
+		hw->fw_branch = resp->fw_branch;
+		hw->fw_maj_ver = resp->fw_major;
+		hw->fw_min_ver = resp->fw_minor;
+		hw->fw_patch = resp->fw_patch;
+		hw->fw_build = le32_to_cpu(resp->fw_build);
+		hw->api_branch = resp->api_branch;
+		hw->api_maj_ver = resp->api_major;
+		hw->api_min_ver = resp->api_minor;
+		hw->api_patch = resp->api_patch;
+	}
+
+	return err;
+}
+
+/**
  * ixgbe_aci_req_res - request a common resource
  * @hw: pointer to the HW struct
  * @res: resource ID
@@ -554,6 +588,20 @@ static bool ixgbe_parse_e610_caps(struct ixgbe_hw *hw,
 		break;
 	case IXGBE_ACI_CAPS_NVM_VER:
 		break;
+	case IXGBE_ACI_CAPS_PENDING_NVM_VER:
+		caps->nvm_update_pending_nvm = true;
+		break;
+	case IXGBE_ACI_CAPS_PENDING_OROM_VER:
+		caps->nvm_update_pending_orom = true;
+		break;
+	case IXGBE_ACI_CAPS_PENDING_NET_VER:
+		caps->nvm_update_pending_netlist = true;
+		break;
+	case IXGBE_ACI_CAPS_NVM_MGMT:
+		caps->nvm_unified_update =
+			(number & IXGBE_NVM_MGMT_UNIFIED_UPD_SUPPORT) ?
+			true : false;
+		break;
 	case IXGBE_ACI_CAPS_MAX_MTU:
 		caps->max_mtu = number;
 		break;
@@ -1411,6 +1459,61 @@ int ixgbe_configure_lse(struct ixgbe_hw *hw, bool activate, u16 mask)
 }
 
 /**
+ * ixgbe_start_hw_e610 - Prepare hardware for Tx/Rx
+ * @hw: pointer to hardware structure
+ *
+ * Get firmware version and start the hardware using the generic
+ * start_hw() and ixgbe_start_hw_gen2() functions.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_start_hw_e610(struct ixgbe_hw *hw)
+{
+	int err;
+
+	err = ixgbe_aci_get_fw_ver(hw);
+	if (err)
+		return err;
+
+	err = ixgbe_start_hw_generic(hw);
+	if (err)
+		return err;
+
+	ixgbe_start_hw_gen2(hw);
+
+	return 0;
+}
+
+/**
+ * ixgbe_aci_set_port_id_led - set LED value for the given port
+ * @hw: pointer to the HW struct
+ * @orig_mode: set LED original mode
+ *
+ * Set LED value for the given port (0x06E9)
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_set_port_id_led(struct ixgbe_hw *hw, bool orig_mode)
+{
+	struct ixgbe_aci_cmd_set_port_id_led *cmd;
+	struct ixgbe_aci_desc desc;
+
+	cmd = &desc.params.set_port_id_led;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_port_id_led);
+
+	cmd->lport_num = (u8)hw->bus.func;
+	cmd->lport_num_valid = IXGBE_ACI_PORT_ID_PORT_NUM_VALID;
+
+	if (orig_mode)
+		cmd->ident_mode = IXGBE_ACI_PORT_IDENT_LED_ORIG;
+	else
+		cmd->ident_mode = IXGBE_ACI_PORT_IDENT_LED_BLINK;
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
  * ixgbe_get_media_type_e610 - Gets media type
  * @hw: pointer to the HW struct
  *
@@ -1743,6 +1846,38 @@ void ixgbe_disable_rx_e610(struct ixgbe_hw *hw)
 }
 
 /**
+ * ixgbe_fw_recovery_mode_e610 - Check FW NVM recovery mode
+ * @hw: pointer to hardware structure
+ *
+ * Check FW NVM recovery mode by reading the value of
+ * the dedicated register.
+ *
+ * Return: true if FW is in recovery mode, otherwise false.
+ */
+static bool ixgbe_fw_recovery_mode_e610(struct ixgbe_hw *hw)
+{
+	u32 fwsm = IXGBE_READ_REG(hw, IXGBE_GL_MNG_FWSM);
+
+	return !!(fwsm & IXGBE_GL_MNG_FWSM_RECOVERY_M);
+}
+
+/**
+ * ixgbe_fw_rollback_mode_e610 - Check FW NVM rollback mode
+ * @hw: pointer to hardware structure
+ *
+ * Check FW NVM rollback mode by reading the value of
+ * the dedicated register.
+ *
+ * Return: true if FW is in rollback mode, otherwise false.
+ */
+static bool ixgbe_fw_rollback_mode_e610(struct ixgbe_hw *hw)
+{
+	u32 fwsm = IXGBE_READ_REG(hw, IXGBE_GL_MNG_FWSM);
+
+	return !!(fwsm & IXGBE_GL_MNG_FWSM_ROLLBACK_M);
+}
+
+/**
  * ixgbe_init_phy_ops_e610 - PHY specific init
  * @hw: pointer to hardware structure
  *
@@ -2226,6 +2361,131 @@ int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset,
 }
 
 /**
+ * ixgbe_aci_erase_nvm - erase NVM sector
+ * @hw: pointer to the HW struct
+ * @module_typeid: module pointer location in words from the NVM beginning
+ *
+ * Erase the NVM sector using the ACI command (0x0702).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_erase_nvm(struct ixgbe_hw *hw, u16 module_typeid)
+{
+	struct ixgbe_aci_cmd_nvm *cmd;
+	struct ixgbe_aci_desc desc;
+	__le16 len;
+	int err;
+
+	/* Read a length value from SR, so module_typeid is equal to 0,
+	 * calculate offset where module size is placed from bytes to words
+	 * set last command and read from SR values to true.
+	 */
+	err = ixgbe_aci_read_nvm(hw, 0, 2 * module_typeid + 2, 2, &len, true,
+				 true);
+	if (err)
+		return err;
+
+	cmd = &desc.params.nvm;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_erase);
+
+	cmd->module_typeid = cpu_to_le16(module_typeid);
+	cmd->length = len;
+	cmd->offset_low = 0;
+	cmd->offset_high = 0;
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/**
+ * ixgbe_aci_update_nvm - update NVM
+ * @hw: pointer to the HW struct
+ * @module_typeid: module pointer location in words from the NVM beginning
+ * @offset: byte offset from the module beginning
+ * @length: length of the section to be written (in bytes from the offset)
+ * @data: command buffer (size [bytes] = length)
+ * @last_command: tells if this is the last command in a series
+ * @command_flags: command parameters
+ *
+ * Update the NVM using the ACI command (0x0703).
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_update_nvm(struct ixgbe_hw *hw, u16 module_typeid,
+			 u32 offset, u16 length, void *data,
+			 bool last_command, u8 command_flags)
+{
+	struct ixgbe_aci_cmd_nvm *cmd;
+	struct ixgbe_aci_desc desc;
+
+	cmd = &desc.params.nvm;
+
+	/* In offset the highest byte must be zeroed. */
+	if (offset & 0xFF000000)
+		return -EINVAL;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_write);
+
+	cmd->cmd_flags |= command_flags;
+
+	/* If this is the last command in a series, set the proper flag. */
+	if (last_command)
+		cmd->cmd_flags |= IXGBE_ACI_NVM_LAST_CMD;
+	cmd->module_typeid = cpu_to_le16(module_typeid);
+	cmd->offset_low = cpu_to_le16(offset & 0xFFFF);
+	cmd->offset_high = FIELD_GET(IXGBE_ACI_NVM_OFFSET_HI_U_MASK, offset);
+	cmd->length = cpu_to_le16(length);
+
+	desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD);
+
+	return ixgbe_aci_send_cmd(hw, &desc, data, length);
+}
+
+/**
+ * ixgbe_nvm_write_activate - NVM activate write
+ * @hw: pointer to the HW struct
+ * @cmd_flags: flags for write activate command
+ * @response_flags: response indicators from firmware
+ *
+ * Update the control word with the required banks' validity bits
+ * and dumps the Shadow RAM to flash using ACI command (0x0707).
+ *
+ * cmd_flags controls which banks to activate, the preservation level to use
+ * when activating the NVM bank, and whether an EMP reset is required for
+ * activation.
+ *
+ * Note that the 16bit cmd_flags value is split between two separate 1 byte
+ * flag values in the descriptor.
+ *
+ * On successful return of the firmware command, the response_flags variable
+ * is updated with the flags reported by firmware indicating certain status,
+ * such as whether EMP reset is enabled.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_nvm_write_activate(struct ixgbe_hw *hw, u16 cmd_flags,
+			     u8 *response_flags)
+{
+	struct ixgbe_aci_cmd_nvm *cmd;
+	struct ixgbe_aci_desc desc;
+	s32 err;
+
+	cmd = &desc.params.nvm;
+	ixgbe_fill_dflt_direct_cmd_desc(&desc,
+					ixgbe_aci_opc_nvm_write_activate);
+
+	cmd->cmd_flags = (u8)(cmd_flags & 0xFF);
+	cmd->offset_high = (u8)FIELD_GET(IXGBE_ACI_NVM_OFFSET_HI_A_MASK,
+					 cmd_flags);
+
+	err = ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+	if (!err && response_flags)
+		*response_flags = cmd->cmd_flags;
+
+	return err;
+}
+
+/**
  * ixgbe_nvm_validate_checksum - validate checksum
  * @hw: pointer to the HW struct
  *
@@ -2267,6 +2527,955 @@ int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw)
 }
 
 /**
+ * ixgbe_discover_flash_size - Discover the available flash size
+ * @hw: pointer to the HW struct
+ *
+ * The device flash could be up to 16MB in size. However, it is possible that
+ * the actual size is smaller. Use bisection to determine the accessible size
+ * of flash memory.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_discover_flash_size(struct ixgbe_hw *hw)
+{
+	u32 min_size = 0, max_size = IXGBE_ACI_NVM_MAX_OFFSET + 1;
+	int err;
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	if (err)
+		return err;
+
+	while ((max_size - min_size) > 1) {
+		u32 offset = (max_size + min_size) / 2;
+		u32 len = 1;
+		u8 data;
+
+		err = ixgbe_read_flat_nvm(hw, offset, &len, &data, false);
+		if (err == -EIO &&
+		    hw->aci.last_status == IXGBE_ACI_RC_EINVAL) {
+			err = 0;
+			max_size = offset;
+		} else if (!err) {
+			min_size = offset;
+		} else {
+			/* an unexpected error occurred */
+			goto err_read_flat_nvm;
+		}
+	}
+
+	hw->flash.flash_size = max_size;
+
+err_read_flat_nvm:
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_sr_base_address - Read the value of a Shadow RAM pointer word
+ * @hw: pointer to the HW structure
+ * @offset: the word offset of the Shadow RAM word to read
+ * @pointer: pointer value read from Shadow RAM
+ *
+ * Read the given Shadow RAM word, and convert it to a pointer value specified
+ * in bytes. This function assumes the specified offset is a valid pointer
+ * word.
+ *
+ * Each pointer word specifies whether it is stored in word size or 4KB
+ * sector size by using the highest bit. The reported pointer value will be in
+ * bytes, intended for flat NVM reads.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_sr_base_address(struct ixgbe_hw *hw, u16 offset,
+				      u32 *pointer)
+{
+	u16 value;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, offset, &value);
+	if (err)
+		return err;
+
+	/* Determine if the pointer is in 4KB or word units */
+	if (value & IXGBE_SR_NVM_PTR_4KB_UNITS)
+		*pointer = (value & ~IXGBE_SR_NVM_PTR_4KB_UNITS) * SZ_4K;
+	else
+		*pointer = value * sizeof(u16);
+
+	return 0;
+}
+
+/**
+ * ixgbe_read_sr_area_size - Read an area size from a Shadow RAM word
+ * @hw: pointer to the HW structure
+ * @offset: the word offset of the Shadow RAM to read
+ * @size: size value read from the Shadow RAM
+ *
+ * Read the given Shadow RAM word, and convert it to an area size value
+ * specified in bytes. This function assumes the specified offset is a valid
+ * area size word.
+ *
+ * Each area size word is specified in 4KB sector units. This function reports
+ * the size in bytes, intended for flat NVM reads.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_sr_area_size(struct ixgbe_hw *hw, u16 offset, u32 *size)
+{
+	u16 value;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, offset, &value);
+	if (err)
+		return err;
+
+	/* Area sizes are always specified in 4KB units */
+	*size = value * SZ_4K;
+
+	return 0;
+}
+
+/**
+ * ixgbe_determine_active_flash_banks - Discover active bank for each module
+ * @hw: pointer to the HW struct
+ *
+ * Read the Shadow RAM control word and determine which banks are active for
+ * the NVM, OROM, and Netlist modules. Also read and calculate the associated
+ * pointer and size. These values are then cached into the ixgbe_flash_info
+ * structure for later use in order to calculate the correct offset to read
+ * from the active module.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_determine_active_flash_banks(struct ixgbe_hw *hw)
+{
+	struct ixgbe_bank_info *banks = &hw->flash.banks;
+	u16 ctrl_word;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, IXGBE_E610_SR_NVM_CTRL_WORD,
+				     &ctrl_word);
+	if (err)
+		return err;
+
+	if (FIELD_GET(IXGBE_SR_CTRL_WORD_1_M, ctrl_word) !=
+	    IXGBE_SR_CTRL_WORD_VALID)
+		return -ENODATA;
+
+	if (!(ctrl_word & IXGBE_SR_CTRL_WORD_NVM_BANK))
+		banks->nvm_bank = IXGBE_1ST_FLASH_BANK;
+	else
+		banks->nvm_bank = IXGBE_2ND_FLASH_BANK;
+
+	if (!(ctrl_word & IXGBE_SR_CTRL_WORD_OROM_BANK))
+		banks->orom_bank = IXGBE_1ST_FLASH_BANK;
+	else
+		banks->orom_bank = IXGBE_2ND_FLASH_BANK;
+
+	if (!(ctrl_word & IXGBE_SR_CTRL_WORD_NETLIST_BANK))
+		banks->netlist_bank = IXGBE_1ST_FLASH_BANK;
+	else
+		banks->netlist_bank = IXGBE_2ND_FLASH_BANK;
+
+	err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_1ST_NVM_BANK_PTR,
+					 &banks->nvm_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_NVM_BANK_SIZE,
+				      &banks->nvm_size);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_1ST_OROM_BANK_PTR,
+					 &banks->orom_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_OROM_BANK_SIZE,
+				      &banks->orom_size);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_base_address(hw, IXGBE_E610_SR_NETLIST_BANK_PTR,
+					 &banks->netlist_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_sr_area_size(hw, IXGBE_E610_SR_NETLIST_BANK_SIZE,
+				      &banks->netlist_size);
+
+	return err;
+}
+
+/**
+ * ixgbe_get_flash_bank_offset - Get offset into requested flash bank
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from the active or inactive flash bank
+ * @module: the module to read from
+ *
+ * Based on the module, lookup the module offset from the beginning of the
+ * flash.
+ *
+ * Return: the flash offset. Note that a value of zero is invalid and must be
+ * treated as an error.
+ */
+static int ixgbe_get_flash_bank_offset(struct ixgbe_hw *hw,
+				       enum ixgbe_bank_select bank,
+				       u16 module)
+{
+	struct ixgbe_bank_info *banks = &hw->flash.banks;
+	enum ixgbe_flash_bank active_bank;
+	bool second_bank_active;
+	u32 offset, size;
+
+	switch (module) {
+	case IXGBE_E610_SR_1ST_NVM_BANK_PTR:
+		offset = banks->nvm_ptr;
+		size = banks->nvm_size;
+		active_bank = banks->nvm_bank;
+		break;
+	case IXGBE_E610_SR_1ST_OROM_BANK_PTR:
+		offset = banks->orom_ptr;
+		size = banks->orom_size;
+		active_bank = banks->orom_bank;
+		break;
+	case IXGBE_E610_SR_NETLIST_BANK_PTR:
+		offset = banks->netlist_ptr;
+		size = banks->netlist_size;
+		active_bank = banks->netlist_bank;
+		break;
+	default:
+		return 0;
+	}
+
+	switch (active_bank) {
+	case IXGBE_1ST_FLASH_BANK:
+		second_bank_active = false;
+		break;
+	case IXGBE_2ND_FLASH_BANK:
+		second_bank_active = true;
+		break;
+	default:
+		return 0;
+	}
+
+	/* The second flash bank is stored immediately following the first
+	 * bank. Based on whether the 1st or 2nd bank is active, and whether
+	 * we want the active or inactive bank, calculate the desired offset.
+	 */
+	switch (bank) {
+	case IXGBE_ACTIVE_FLASH_BANK:
+		return offset + (second_bank_active ? size : 0);
+	case IXGBE_INACTIVE_FLASH_BANK:
+		return offset + (second_bank_active ? 0 : size);
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_read_flash_module - Read a word from one of the main NVM modules
+ * @hw: pointer to the HW structure
+ * @bank: which bank of the module to read
+ * @module: the module to read
+ * @offset: the offset into the module in bytes
+ * @data: storage for the word read from the flash
+ * @length: bytes of data to read
+ *
+ * Read data from the specified flash module. The bank parameter indicates
+ * whether or not to read from the active bank or the inactive bank of that
+ * module.
+ *
+ * The word will be read using flat NVM access, and relies on the
+ * hw->flash.banks data being setup by ixgbe_determine_active_flash_banks()
+ * during initialization.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_flash_module(struct ixgbe_hw *hw,
+				   enum ixgbe_bank_select bank,
+				   u16 module, u32 offset, u8 *data, u32 length)
+{
+	u32 start;
+	int err;
+
+	start = ixgbe_get_flash_bank_offset(hw, bank, module);
+	if (!start)
+		return -EINVAL;
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	if (err)
+		return err;
+
+	err = ixgbe_read_flat_nvm(hw, start + offset, &length, data, false);
+
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_nvm_module - Read from the active main NVM module
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from active or inactive NVM module
+ * @offset: offset into the NVM module to read, in words
+ * @data: storage for returned word value
+ *
+ * Read the specified word from the active NVM module. This includes the CSS
+ * header at the start of the NVM module.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_nvm_module(struct ixgbe_hw *hw,
+				 enum ixgbe_bank_select bank,
+				 u32 offset, u16 *data)
+{
+	__le16 data_local;
+	int err;
+
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_1ST_NVM_BANK_PTR,
+				      offset * sizeof(data_local),
+				      (u8 *)&data_local,
+				      sizeof(data_local));
+	if (!err)
+		*data = le16_to_cpu(data_local);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_netlist_module - Read data from the netlist module area
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from the active or inactive module
+ * @offset: offset into the netlist to read from
+ * @data: storage for returned word value
+ *
+ * Read a word from the specified netlist bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_netlist_module(struct ixgbe_hw *hw,
+				     enum ixgbe_bank_select bank,
+				     u32 offset, u16 *data)
+{
+	__le16 data_local;
+	int err;
+
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_NETLIST_BANK_PTR,
+				      offset * sizeof(data_local),
+				      (u8 *)&data_local, sizeof(data_local));
+	if (!err)
+		*data = le16_to_cpu(data_local);
+
+	return err;
+}
+
+/**
+ * ixgbe_read_orom_module - Read from the active Option ROM module
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from active or inactive OROM module
+ * @offset: offset into the OROM module to read, in words
+ * @data: storage for returned word value
+ *
+ * Read the specified word from the active Option ROM module of the flash.
+ * Note that unlike the NVM module, the CSS data is stored at the end of the
+ * module instead of at the beginning.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_orom_module(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  u32 offset, u16 *data)
+{
+	__le16 data_local;
+	int err;
+
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_1ST_OROM_BANK_PTR,
+				      offset * sizeof(data_local),
+				      (u8 *)&data_local, sizeof(data_local));
+	if (!err)
+		*data = le16_to_cpu(data_local);
+
+	return err;
+}
+
+/**
+ * ixgbe_get_nvm_css_hdr_len - Read the CSS header length
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @hdr_len: storage for header length in words
+ *
+ * Read the CSS header length from the NVM CSS header and add the
+ * Authentication header size, and then convert to words.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_nvm_css_hdr_len(struct ixgbe_hw *hw,
+				     enum ixgbe_bank_select bank,
+				     u32 *hdr_len)
+{
+	u16 hdr_len_l, hdr_len_h;
+	u32 hdr_len_dword;
+	int err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_HDR_LEN_L,
+				    &hdr_len_l);
+	if (err)
+		return err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_HDR_LEN_H,
+				    &hdr_len_h);
+	if (err)
+		return err;
+
+	/* CSS header length is in DWORD, so convert to words and add
+	 * authentication header size.
+	 */
+	hdr_len_dword = (hdr_len_h << 16) | hdr_len_l;
+	*hdr_len = hdr_len_dword * 2 + IXGBE_NVM_AUTH_HEADER_LEN;
+
+	return 0;
+}
+
+/**
+ * ixgbe_read_nvm_sr_copy - Read a word from the Shadow RAM copy
+ * @hw: pointer to the HW structure
+ * @bank: whether to read from the active or inactive NVM module
+ * @offset: offset into the Shadow RAM copy to read, in words
+ * @data: storage for returned word value
+ *
+ * Read the specified word from the copy of the Shadow RAM found in the
+ * specified NVM module.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_nvm_sr_copy(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  u32 offset, u16 *data)
+{
+	u32 hdr_len;
+	int err;
+
+	err = ixgbe_get_nvm_css_hdr_len(hw, bank, &hdr_len);
+	if (err)
+		return err;
+
+	hdr_len = round_up(hdr_len, IXGBE_HDR_LEN_ROUNDUP);
+
+	return ixgbe_read_nvm_module(hw, bank, hdr_len + offset, data);
+}
+
+/**
+ * ixgbe_get_nvm_srev - Read the security revision from the NVM CSS header
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @srev: storage for security revision
+ *
+ * Read the security revision out of the CSS header of the active NVM module
+ * bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_nvm_srev(struct ixgbe_hw *hw,
+			      enum ixgbe_bank_select bank, u32 *srev)
+{
+	u16 srev_l, srev_h;
+	int err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_SREV_L, &srev_l);
+	if (err)
+		return err;
+
+	err = ixgbe_read_nvm_module(hw, bank, IXGBE_NVM_CSS_SREV_H, &srev_h);
+	if (err)
+		return err;
+
+	*srev = (srev_h << 16) | srev_l;
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_orom_civd_data - Get the combo version information from Option ROM
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash module
+ * @civd: storage for the Option ROM CIVD data.
+ *
+ * Searches through the Option ROM flash contents to locate the CIVD data for
+ * the image.
+ *
+ * Return: the exit code of the operation.
+ */
+static int
+ixgbe_get_orom_civd_data(struct ixgbe_hw *hw, enum ixgbe_bank_select bank,
+			 struct ixgbe_orom_civd_info *civd)
+{
+	struct ixgbe_orom_civd_info tmp;
+	u32 offset;
+	int err;
+
+	/* The CIVD section is located in the Option ROM aligned to 512 bytes.
+	 * The first 4 bytes must contain the ASCII characters "$CIV".
+	 * A simple modulo 256 sum of all of the bytes of the structure must
+	 * equal 0.
+	 */
+	for (offset = 0; (offset + SZ_512) <= hw->flash.banks.orom_size;
+	     offset += SZ_512) {
+		u8 sum = 0;
+		u32 i;
+
+		err = ixgbe_read_flash_module(hw, bank,
+					      IXGBE_E610_SR_1ST_OROM_BANK_PTR,
+					      offset,
+					      (u8 *)&tmp, sizeof(tmp));
+		if (err)
+			return err;
+
+		/* Skip forward until we find a matching signature */
+		if (memcmp(IXGBE_OROM_CIV_SIGNATURE, tmp.signature,
+			   sizeof(tmp.signature)))
+			continue;
+
+		/* Verify that the simple checksum is zero */
+		for (i = 0; i < sizeof(tmp); i++)
+			sum += ((u8 *)&tmp)[i];
+
+		if (sum)
+			return -EDOM;
+
+		*civd = tmp;
+		return 0;
+	}
+
+	return -ENODATA;
+}
+
+/**
+ * ixgbe_get_orom_srev - Read the security revision from the OROM CSS header
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from active or inactive flash module
+ * @srev: storage for security revision
+ *
+ * Read the security revision out of the CSS header of the active OROM module
+ * bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_orom_srev(struct ixgbe_hw *hw,
+			       enum ixgbe_bank_select bank,
+			       u32 *srev)
+{
+	u32 orom_size_word = hw->flash.banks.orom_size / 2;
+	u32 css_start, hdr_len;
+	u16 srev_l, srev_h;
+	int err;
+
+	err = ixgbe_get_nvm_css_hdr_len(hw, bank, &hdr_len);
+	if (err)
+		return err;
+
+	if (orom_size_word < hdr_len)
+		return -EINVAL;
+
+	/* Calculate how far into the Option ROM the CSS header starts. Note
+	 * that ixgbe_read_orom_module takes a word offset.
+	 */
+	css_start = orom_size_word - hdr_len;
+	err = ixgbe_read_orom_module(hw, bank,
+				     css_start + IXGBE_NVM_CSS_SREV_L,
+				     &srev_l);
+	if (err)
+		return err;
+
+	err = ixgbe_read_orom_module(hw, bank,
+				     css_start + IXGBE_NVM_CSS_SREV_H,
+				     &srev_h);
+	if (err)
+		return err;
+
+	*srev = srev_h << 16 | srev_l;
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_orom_ver_info - Read Option ROM version information
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash module
+ * @orom: pointer to Option ROM info structure
+ *
+ * Read Option ROM version and security revision from the Option ROM flash
+ * section.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_orom_ver_info(struct ixgbe_hw *hw,
+				   enum ixgbe_bank_select bank,
+				   struct ixgbe_orom_info *orom)
+{
+	struct ixgbe_orom_civd_info civd;
+	u32 combo_ver;
+	int err;
+
+	err = ixgbe_get_orom_civd_data(hw, bank, &civd);
+	if (err)
+		return err;
+
+	combo_ver = le32_to_cpu(civd.combo_ver);
+
+	orom->major = (u8)FIELD_GET(IXGBE_OROM_VER_MASK, combo_ver);
+	orom->patch = (u8)FIELD_GET(IXGBE_OROM_VER_PATCH_MASK, combo_ver);
+	orom->build = (u16)FIELD_GET(IXGBE_OROM_VER_BUILD_MASK, combo_ver);
+
+	return ixgbe_get_orom_srev(hw, bank, &orom->srev);
+}
+
+/**
+ * ixgbe_get_inactive_orom_ver - Read Option ROM version from the inactive bank
+ * @hw: pointer to the HW structure
+ * @orom: storage for Option ROM version information
+ *
+ * Read the Option ROM version and security revision data for the inactive
+ * section of flash. Used to access version data for a pending update that has
+ * not yet been activated.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_inactive_orom_ver(struct ixgbe_hw *hw,
+				struct ixgbe_orom_info *orom)
+{
+	return ixgbe_get_orom_ver_info(hw, IXGBE_INACTIVE_FLASH_BANK, orom);
+}
+
+/**
+ * ixgbe_get_nvm_ver_info - Read NVM version information
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @nvm: pointer to NVM info structure
+ *
+ * Read the NVM EETRACK ID and map version of the main NVM image bank, filling
+ * in the nvm info structure.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_nvm_ver_info(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  struct ixgbe_nvm_info *nvm)
+{
+	u16 eetrack_lo, eetrack_hi, ver;
+	int err;
+
+	err = ixgbe_read_nvm_sr_copy(hw, bank,
+				     IXGBE_E610_SR_NVM_DEV_STARTER_VER, &ver);
+	if (err)
+		return err;
+
+	nvm->major = FIELD_GET(IXGBE_E610_NVM_VER_HI_MASK, ver);
+	nvm->minor = FIELD_GET(IXGBE_E610_NVM_VER_LO_MASK, ver);
+
+	err = ixgbe_read_nvm_sr_copy(hw, bank, IXGBE_E610_SR_NVM_EETRACK_LO,
+				     &eetrack_lo);
+	if (err)
+		return err;
+
+	err = ixgbe_read_nvm_sr_copy(hw, bank, IXGBE_E610_SR_NVM_EETRACK_HI,
+				     &eetrack_hi);
+	if (err)
+		return err;
+
+	nvm->eetrack = (eetrack_hi << 16) | eetrack_lo;
+
+	ixgbe_get_nvm_srev(hw, bank, &nvm->srev);
+
+	return 0;
+}
+
+/**
+ * ixgbe_get_inactive_nvm_ver - Read Option ROM version from the inactive bank
+ * @hw: pointer to the HW structure
+ * @nvm: storage for Option ROM version information
+ *
+ * Read the NVM EETRACK ID, Map version, and security revision of the
+ * inactive NVM bank. Used to access version data for a pending update that
+ * has not yet been activated.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_inactive_nvm_ver(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm)
+{
+	return ixgbe_get_nvm_ver_info(hw, IXGBE_INACTIVE_FLASH_BANK, nvm);
+}
+
+/**
+ * ixgbe_get_active_nvm_ver - Read Option ROM version from the active bank
+ * @hw: pointer to the HW structure
+ * @nvm: storage for Option ROM version information
+ *
+ * Reads the NVM EETRACK ID, Map version, and security revision of the
+ * active NVM bank.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_active_nvm_ver(struct ixgbe_hw *hw,
+				    struct ixgbe_nvm_info *nvm)
+{
+	return ixgbe_get_nvm_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK, nvm);
+}
+
+/**
+ * ixgbe_get_netlist_info - Read the netlist version information
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @netlist: pointer to netlist version info structure
+ *
+ * Get the netlist version information from the requested bank. Reads the Link
+ * Topology section to find the Netlist ID block and extract the relevant
+ * information into the netlist version structure.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_netlist_info(struct ixgbe_hw *hw,
+				  enum ixgbe_bank_select bank,
+				  struct ixgbe_netlist_info *netlist)
+{
+	u16 module_id, length, node_count, i;
+	u16 *id_blk;
+	int err;
+
+	err = ixgbe_read_netlist_module(hw, bank, IXGBE_NETLIST_TYPE_OFFSET,
+					&module_id);
+	if (err)
+		return err;
+
+	if (module_id != IXGBE_NETLIST_LINK_TOPO_MOD_ID)
+		return -EIO;
+
+	err = ixgbe_read_netlist_module(hw, bank, IXGBE_LINK_TOPO_MODULE_LEN,
+					&length);
+	if (err)
+		return err;
+
+	/* Sanity check that we have at least enough words to store the
+	 * netlist ID block.
+	 */
+	if (length < IXGBE_NETLIST_ID_BLK_SIZE)
+		return -EIO;
+
+	err = ixgbe_read_netlist_module(hw, bank, IXGBE_LINK_TOPO_NODE_COUNT,
+					&node_count);
+	if (err)
+		return err;
+
+	node_count &= IXGBE_LINK_TOPO_NODE_COUNT_M;
+
+	id_blk = kcalloc(IXGBE_NETLIST_ID_BLK_SIZE, sizeof(*id_blk), GFP_KERNEL);
+	if (!id_blk)
+		return -ENOMEM;
+
+	/* Read out the entire Netlist ID Block at once. */
+	err = ixgbe_read_flash_module(hw, bank, IXGBE_E610_SR_NETLIST_BANK_PTR,
+				      IXGBE_NETLIST_ID_BLK_OFFSET(node_count) *
+				      sizeof(*id_blk), (u8 *)id_blk,
+				      IXGBE_NETLIST_ID_BLK_SIZE *
+				      sizeof(*id_blk));
+	if (err)
+		goto free_id_blk;
+
+	for (i = 0; i < IXGBE_NETLIST_ID_BLK_SIZE; i++)
+		id_blk[i] = le16_to_cpu(((__le16 *)id_blk)[i]);
+
+	netlist->major = id_blk[IXGBE_NETLIST_ID_BLK_MAJOR_VER_HIGH] << 16 |
+			 id_blk[IXGBE_NETLIST_ID_BLK_MAJOR_VER_LOW];
+	netlist->minor = id_blk[IXGBE_NETLIST_ID_BLK_MINOR_VER_HIGH] << 16 |
+			 id_blk[IXGBE_NETLIST_ID_BLK_MINOR_VER_LOW];
+	netlist->type = id_blk[IXGBE_NETLIST_ID_BLK_TYPE_HIGH] << 16 |
+			id_blk[IXGBE_NETLIST_ID_BLK_TYPE_LOW];
+	netlist->rev = id_blk[IXGBE_NETLIST_ID_BLK_REV_HIGH] << 16 |
+		       id_blk[IXGBE_NETLIST_ID_BLK_REV_LOW];
+	netlist->cust_ver = id_blk[IXGBE_NETLIST_ID_BLK_CUST_VER];
+	/* Read the left most 4 bytes of SHA */
+	netlist->hash = id_blk[IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(15)] << 16 |
+			id_blk[IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(14)];
+
+free_id_blk:
+	kfree(id_blk);
+	return err;
+}
+
+/**
+ * ixgbe_get_inactive_netlist_ver - Read netlist version from the inactive bank
+ * @hw: pointer to the HW struct
+ * @netlist: pointer to netlist version info structure
+ *
+ * Read the netlist version data from the inactive netlist bank. Used to
+ * extract version data of a pending flash update in order to display the
+ * version data.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_inactive_netlist_ver(struct ixgbe_hw *hw,
+				   struct ixgbe_netlist_info *netlist)
+{
+	return ixgbe_get_netlist_info(hw, IXGBE_INACTIVE_FLASH_BANK, netlist);
+}
+
+/**
+ * ixgbe_get_flash_data - get flash data
+ * @hw: pointer to the HW struct
+ *
+ * Read and populate flash data such as Shadow RAM size,
+ * max_timeout and blank_nvm_mode
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_get_flash_data(struct ixgbe_hw *hw)
+{
+	struct ixgbe_flash_info *flash = &hw->flash;
+	u32 fla, gens_stat;
+	u8 sr_size;
+	int err;
+
+	/* The SR size is stored regardless of the NVM programming mode
+	 * as the blank mode may be used in the factory line.
+	 */
+	gens_stat = IXGBE_READ_REG(hw, GLNVM_GENS);
+	sr_size = FIELD_GET(GLNVM_GENS_SR_SIZE_M, gens_stat);
+
+	/* Switching to words (sr_size contains power of 2) */
+	flash->sr_words = BIT(sr_size) * (SZ_1K / sizeof(u16));
+
+	/* Check if we are in the normal or blank NVM programming mode */
+	fla = IXGBE_READ_REG(hw, IXGBE_GLNVM_FLA);
+	if (fla & IXGBE_GLNVM_FLA_LOCKED_M) {
+		flash->blank_nvm_mode = false;
+	} else {
+		flash->blank_nvm_mode = true;
+		return -EIO;
+	}
+
+	err = ixgbe_discover_flash_size(hw);
+	if (err)
+		return err;
+
+	err = ixgbe_determine_active_flash_banks(hw);
+	if (err)
+		return err;
+
+	err = ixgbe_get_nvm_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK,
+				     &flash->nvm);
+	if (err)
+		return err;
+
+	err = ixgbe_get_orom_ver_info(hw, IXGBE_ACTIVE_FLASH_BANK,
+				      &flash->orom);
+	if (err)
+		return err;
+
+	err = ixgbe_get_netlist_info(hw, IXGBE_ACTIVE_FLASH_BANK,
+				     &flash->netlist);
+	return err;
+}
+
+/**
+ * ixgbe_aci_nvm_update_empr - update NVM using EMPR
+ * @hw: pointer to the HW struct
+ *
+ * Force EMP reset using ACI command (0x0709). This command allows SW to
+ * request an EMPR to activate new FW.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_aci_nvm_update_empr(struct ixgbe_hw *hw)
+{
+	struct ixgbe_aci_desc desc;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_update_empr);
+
+	return ixgbe_aci_send_cmd(hw, &desc, NULL, 0);
+}
+
+/* ixgbe_nvm_set_pkg_data - NVM set package data
+ * @hw: pointer to the HW struct
+ * @del_pkg_data_flag: If is set then the current pkg_data store by FW
+ *		       is deleted.
+ *		       If bit is set to 1, then buffer should be size 0.
+ * @data: pointer to buffer
+ * @length: length of the buffer
+ *
+ * Set package data using ACI command (0x070A).
+ * This command is equivalent to the reception of
+ * a PLDM FW Update GetPackageData cmd. This command should be sent
+ * as part of the NVM update as the first cmd in the flow.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_nvm_set_pkg_data(struct ixgbe_hw *hw, bool del_pkg_data_flag,
+			   u8 *data, u16 length)
+{
+	struct ixgbe_aci_cmd_nvm_pkg_data *cmd;
+	struct ixgbe_aci_desc desc;
+
+	if (length != 0 && !data)
+		return -EINVAL;
+
+	cmd = &desc.params.pkg_data;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_pkg_data);
+	desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD);
+
+	if (del_pkg_data_flag)
+		cmd->cmd_flags |= IXGBE_ACI_NVM_PKG_DELETE;
+
+	return ixgbe_aci_send_cmd(hw, &desc, data, length);
+}
+
+/* ixgbe_nvm_pass_component_tbl - NVM pass component table
+ * @hw: pointer to the HW struct
+ * @data: pointer to buffer
+ * @length: length of the buffer
+ * @transfer_flag: parameter for determining stage of the update
+ * @comp_response: a pointer to the response from the 0x070B ACI.
+ * @comp_response_code: a pointer to the response code from the 0x070B ACI.
+ *
+ * Pass component table using ACI command (0x070B). This command is equivalent
+ * to the reception of a PLDM FW Update PassComponentTable cmd.
+ * This command should be sent once per component. It can be only sent after
+ * Set Package Data cmd and before actual update. FW will assume these
+ * commands are going to be sent until the TransferFlag is set to End or
+ * StartAndEnd.
+ *
+ * Return: the exit code of the operation.
+ */
+int ixgbe_nvm_pass_component_tbl(struct ixgbe_hw *hw, u8 *data, u16 length,
+				 u8 transfer_flag, u8 *comp_response,
+				 u8 *comp_response_code)
+{
+	struct ixgbe_aci_cmd_nvm_pass_comp_tbl *cmd;
+	struct ixgbe_aci_desc desc;
+	int err;
+
+	if (!data || !comp_response || !comp_response_code)
+		return -EINVAL;
+
+	cmd = &desc.params.pass_comp_tbl;
+
+	ixgbe_fill_dflt_direct_cmd_desc(&desc,
+					ixgbe_aci_opc_nvm_pass_component_tbl);
+	desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD);
+
+	cmd->transfer_flag = transfer_flag;
+	err = ixgbe_aci_send_cmd(hw, &desc, data, length);
+	if (!err) {
+		*comp_response = cmd->component_response;
+		*comp_response_code = cmd->component_response_code;
+	}
+
+	return err;
+}
+
+/**
  * ixgbe_read_sr_word_aci - Reads Shadow RAM via ACI
  * @hw: pointer to the HW structure
  * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
@@ -2485,7 +3694,7 @@ int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val)
 		if (err)
 			return err;
 
-		err = ixgbe_read_sr_word_aci(hw, E610_SR_SW_CHECKSUM_WORD,
+		err = ixgbe_read_sr_word_aci(hw, IXGBE_E610_SR_SW_CHECKSUM_WORD,
 					     &tmp_checksum);
 		ixgbe_release_nvm(hw);
 
@@ -2580,9 +3789,129 @@ reset_hw_out:
 	return err;
 }
 
+/**
+ * ixgbe_get_pfa_module_tlv - Read sub module TLV from NVM PFA
+ * @hw: pointer to hardware structure
+ * @module_tlv: pointer to module TLV to return
+ * @module_tlv_len: pointer to module TLV length to return
+ * @module_type: module type requested
+ *
+ * Find the requested sub module TLV type from the Preserved Field
+ * Area (PFA) and returns the TLV pointer and length. The caller can
+ * use these to read the variable length TLV value.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_get_pfa_module_tlv(struct ixgbe_hw *hw, u16 *module_tlv,
+				    u16 *module_tlv_len, u16 module_type)
+{
+	u16 pfa_len, pfa_ptr, pfa_end_ptr;
+	u16 next_tlv;
+	int err;
+
+	err = ixgbe_read_ee_aci_e610(hw, IXGBE_E610_SR_PFA_PTR, &pfa_ptr);
+	if (err)
+		return err;
+
+	err = ixgbe_read_ee_aci_e610(hw, pfa_ptr, &pfa_len);
+	if (err)
+		return err;
+
+	/* Starting with first TLV after PFA length, iterate through the list
+	 * of TLVs to find the requested one.
+	 */
+	next_tlv = pfa_ptr + 1;
+	pfa_end_ptr = pfa_ptr + pfa_len;
+	while (next_tlv < pfa_end_ptr) {
+		u16 tlv_sub_module_type, tlv_len;
+
+		/* Read TLV type */
+		err = ixgbe_read_ee_aci_e610(hw, next_tlv,
+					     &tlv_sub_module_type);
+		if (err)
+			break;
+
+		/* Read TLV length */
+		err = ixgbe_read_ee_aci_e610(hw, next_tlv + 1, &tlv_len);
+		if (err)
+			break;
+
+		if (tlv_sub_module_type == module_type) {
+			if (tlv_len) {
+				*module_tlv = next_tlv;
+				*module_tlv_len = tlv_len;
+				return 0;
+			}
+			return -EIO;
+		}
+		/* Check next TLV, i.e. current TLV pointer + length + 2 words
+		 * (for current TLV's type and length).
+		 */
+		next_tlv = next_tlv + tlv_len + 2;
+	}
+	/* Module does not exist */
+	return -ENODATA;
+}
+
+/**
+ * ixgbe_read_pba_string_e610 - Read PBA string from NVM
+ * @hw: pointer to hardware structure
+ * @pba_num: stores the part number string from the NVM
+ * @pba_num_size: part number string buffer length
+ *
+ * Read the part number string from the NVM.
+ *
+ * Return: the exit code of the operation.
+ */
+static int ixgbe_read_pba_string_e610(struct ixgbe_hw *hw, u8 *pba_num,
+				      u32 pba_num_size)
+{
+	u16 pba_tlv, pba_tlv_len;
+	u16 pba_word, pba_size;
+	int err;
+
+	*pba_num = '\0';
+
+	err = ixgbe_get_pfa_module_tlv(hw, &pba_tlv, &pba_tlv_len,
+				       IXGBE_E610_SR_PBA_BLOCK_PTR);
+	if (err)
+		return err;
+
+	/* pba_size is the next word */
+	err = ixgbe_read_ee_aci_e610(hw, (pba_tlv + 2), &pba_size);
+	if (err)
+		return err;
+
+	if (pba_tlv_len < pba_size)
+		return -EINVAL;
+
+	/* Subtract one to get PBA word count (PBA Size word is included in
+	 * total size).
+	 */
+	pba_size--;
+
+	if (pba_num_size < (((u32)pba_size * 2) + 1))
+		return -EINVAL;
+
+	for (u16 i = 0; i < pba_size; i++) {
+		err = ixgbe_read_ee_aci_e610(hw, (pba_tlv + 2 + 1) + i,
+					     &pba_word);
+		if (err)
+			return err;
+
+		pba_num[(i * 2)] = FIELD_GET(IXGBE_E610_SR_PBA_BLOCK_MASK,
+					     pba_word);
+		pba_num[(i * 2) + 1] = pba_word & 0xFF;
+	}
+
+	pba_num[(pba_size * 2)] = '\0';
+
+	return err;
+}
+
 static const struct ixgbe_mac_operations mac_ops_e610 = {
 	.init_hw			= ixgbe_init_hw_generic,
-	.start_hw			= ixgbe_start_hw_X540,
+	.start_hw			= ixgbe_start_hw_e610,
 	.clear_hw_cntrs			= ixgbe_clear_hw_cntrs_generic,
 	.enable_rx_dma			= ixgbe_enable_rx_dma_generic,
 	.get_mac_addr			= ixgbe_get_mac_addr_generic,
@@ -2621,8 +3950,12 @@ static const struct ixgbe_mac_operations mac_ops_e610 = {
 	.led_off			= ixgbe_led_off_generic,
 	.init_led_link_act		= ixgbe_init_led_link_act_generic,
 	.reset_hw			= ixgbe_reset_hw_e610,
+	.get_fw_ver                     = ixgbe_aci_get_fw_ver,
 	.get_media_type			= ixgbe_get_media_type_e610,
 	.setup_link			= ixgbe_setup_link_e610,
+	.fw_recovery_mode		= ixgbe_fw_recovery_mode_e610,
+	.fw_rollback_mode		= ixgbe_fw_rollback_mode_e610,
+	.get_nvm_ver			= ixgbe_get_active_nvm_ver,
 	.get_link_capabilities		= ixgbe_get_link_capabilities_e610,
 	.get_bus_info			= ixgbe_get_bus_info_generic,
 	.acquire_swfw_sync		= ixgbe_acquire_swfw_sync_X540,
@@ -2647,6 +3980,8 @@ static const struct ixgbe_eeprom_operations eeprom_ops_e610 = {
 	.read				= ixgbe_read_ee_aci_e610,
 	.read_buffer			= ixgbe_read_ee_aci_buffer_e610,
 	.validate_checksum		= ixgbe_validate_eeprom_checksum_e610,
+	.read_pba_string		= ixgbe_read_pba_string_e610,
+	.init_params			= ixgbe_init_eeprom_params_e610,
 };
 
 const struct ixgbe_info ixgbe_e610_info = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h
index ba8c06b73810..bb31d65bd1c8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h
@@ -36,6 +36,7 @@ int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse,
 			    struct ixgbe_link_status *link);
 int ixgbe_aci_set_event_mask(struct ixgbe_hw *hw, u8 port_num, u16 mask);
 int ixgbe_configure_lse(struct ixgbe_hw *hw, bool activate, u16 mask);
+int ixgbe_aci_set_port_id_led(struct ixgbe_hw *hw, bool orig_mode);
 enum ixgbe_media_type ixgbe_get_media_type_e610(struct ixgbe_hw *hw);
 int ixgbe_setup_link_e610(struct ixgbe_hw *hw, ixgbe_link_speed speed,
 			  bool autoneg_wait);
@@ -67,6 +68,11 @@ int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset,
 		       u16 length, void *data, bool last_command,
 		       bool read_shadow_ram);
 int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw);
+int ixgbe_get_inactive_orom_ver(struct ixgbe_hw *hw,
+				struct ixgbe_orom_info *orom);
+int ixgbe_get_inactive_nvm_ver(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm);
+int ixgbe_get_inactive_netlist_ver(struct ixgbe_hw *hw,
+				   struct ixgbe_netlist_info *netlist);
 int ixgbe_read_sr_word_aci(struct ixgbe_hw  *hw, u16 offset, u16 *data);
 int ixgbe_read_flat_nvm(struct ixgbe_hw  *hw, u32 offset, u32 *length,
 			u8 *data, bool read_shadow_ram);
@@ -77,5 +83,18 @@ int ixgbe_read_ee_aci_buffer_e610(struct ixgbe_hw *hw, u16 offset,
 				  u16 words, u16 *data);
 int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val);
 int ixgbe_reset_hw_e610(struct ixgbe_hw *hw);
+int ixgbe_get_flash_data(struct ixgbe_hw *hw);
+int ixgbe_aci_nvm_update_empr(struct ixgbe_hw *hw);
+int ixgbe_nvm_set_pkg_data(struct ixgbe_hw *hw, bool del_pkg_data_flag,
+			   u8 *data, u16 length);
+int ixgbe_nvm_pass_component_tbl(struct ixgbe_hw *hw, u8 *data, u16 length,
+				 u8 transfer_flag, u8 *comp_response,
+				 u8 *comp_response_code);
+int ixgbe_aci_erase_nvm(struct ixgbe_hw *hw, u16 module_typeid);
+int ixgbe_aci_update_nvm(struct ixgbe_hw *hw, u16 module_typeid,
+			 u32 offset, u16 length, void *data,
+			 bool last_command, u8 command_flags);
+int ixgbe_nvm_write_activate(struct ixgbe_hw *hw, u16 cmd_flags,
+			     u8 *response_flags);
 
 #endif /* _IXGBE_E610_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index f03925c1f521..d8a919ab7027 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -213,7 +213,7 @@ static void ixgbe_set_advertising_10gtypes(struct ixgbe_hw *hw,
 static int ixgbe_get_link_ksettings(struct net_device *netdev,
 				    struct ethtool_link_ksettings *cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	ixgbe_link_speed supported_link;
 	bool autoneg = false;
@@ -458,7 +458,7 @@ static int ixgbe_get_link_ksettings(struct net_device *netdev,
 static int ixgbe_set_link_ksettings(struct net_device *netdev,
 				    const struct ethtool_link_ksettings *cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 advertised, old;
 	int err = 0;
@@ -535,7 +535,7 @@ static int ixgbe_set_link_ksettings(struct net_device *netdev,
 static void ixgbe_get_pause_stats(struct net_device *netdev,
 				  struct ethtool_pause_stats *stats)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw_stats *hwstats = &adapter->stats;
 
 	stats->tx_pause_frames = hwstats->lxontxc + hwstats->lxofftxc;
@@ -545,7 +545,7 @@ static void ixgbe_get_pause_stats(struct net_device *netdev,
 static void ixgbe_get_pauseparam(struct net_device *netdev,
 				 struct ethtool_pauseparam *pause)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (ixgbe_device_supports_autoneg_fc(hw) &&
@@ -564,10 +564,26 @@ static void ixgbe_get_pauseparam(struct net_device *netdev,
 	}
 }
 
+static void ixgbe_set_pauseparam_finalize(struct net_device *netdev,
+					  struct ixgbe_fc_info *fc)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	/* If the thing changed then we'll update and use new autoneg. */
+	if (memcmp(fc, &hw->fc, sizeof(*fc))) {
+		hw->fc = *fc;
+		if (netif_running(netdev))
+			ixgbe_reinit_locked(adapter);
+		else
+			ixgbe_reset(adapter);
+	}
+}
+
 static int ixgbe_set_pauseparam(struct net_device *netdev,
 				struct ethtool_pauseparam *pause)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ixgbe_fc_info fc = hw->fc;
 
@@ -592,27 +608,52 @@ static int ixgbe_set_pauseparam(struct net_device *netdev,
 	else
 		fc.requested_mode = ixgbe_fc_none;
 
-	/* if the thing changed then we'll update and use new autoneg */
-	if (memcmp(&fc, &hw->fc, sizeof(struct ixgbe_fc_info))) {
-		hw->fc = fc;
-		if (netif_running(netdev))
-			ixgbe_reinit_locked(adapter);
-		else
-			ixgbe_reset(adapter);
+	ixgbe_set_pauseparam_finalize(netdev, &fc);
+
+	return 0;
+}
+
+static int ixgbe_set_pauseparam_e610(struct net_device *netdev,
+				     struct ethtool_pauseparam *pause)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_fc_info fc = hw->fc;
+
+	if (!ixgbe_device_supports_autoneg_fc(hw))
+		return -EOPNOTSUPP;
+
+	if (pause->autoneg == AUTONEG_DISABLE) {
+		netdev_info(netdev,
+			    "Cannot disable autonegotiation on this device.\n");
+		return -EOPNOTSUPP;
 	}
 
+	fc.disable_fc_autoneg = false;
+
+	if (pause->rx_pause && pause->tx_pause)
+		fc.requested_mode = ixgbe_fc_full;
+	else if (pause->rx_pause)
+		fc.requested_mode = ixgbe_fc_rx_pause;
+	else if (pause->tx_pause)
+		fc.requested_mode = ixgbe_fc_tx_pause;
+	else
+		fc.requested_mode = ixgbe_fc_none;
+
+	ixgbe_set_pauseparam_finalize(netdev, &fc);
+
 	return 0;
 }
 
 static u32 ixgbe_get_msglevel(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	return adapter->msg_enable;
 }
 
 static void ixgbe_set_msglevel(struct net_device *netdev, u32 data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	adapter->msg_enable = data;
 }
 
@@ -627,7 +668,7 @@ static int ixgbe_get_regs_len(struct net_device *netdev)
 static void ixgbe_get_regs(struct net_device *netdev,
 			   struct ethtool_regs *regs, void *p)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 *regs_buff = p;
 	u8 i;
@@ -994,14 +1035,14 @@ static void ixgbe_get_regs(struct net_device *netdev,
 
 static int ixgbe_get_eeprom_len(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	return adapter->hw.eeprom.word_size * 2;
 }
 
 static int ixgbe_get_eeprom(struct net_device *netdev,
 			    struct ethtool_eeprom *eeprom, u8 *bytes)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u16 *eeprom_buff;
 	int first_word, last_word, eeprom_len;
@@ -1037,7 +1078,7 @@ static int ixgbe_get_eeprom(struct net_device *netdev,
 static int ixgbe_set_eeprom(struct net_device *netdev,
 			    struct ethtool_eeprom *eeprom, u8 *bytes)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u16 *eeprom_buff;
 	void *ptr;
@@ -1104,10 +1145,22 @@ err:
 	return ret_val;
 }
 
+void ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	ixgbe_get_flash_data(hw);
+	ixgbe_set_fw_version_e610(adapter);
+}
+
 static void ixgbe_get_drvinfo(struct net_device *netdev,
 			      struct ethtool_drvinfo *drvinfo)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+
+	/* need to refresh info for e610 in case fw reloads in runtime */
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		ixgbe_refresh_fw_version(adapter);
 
 	strscpy(drvinfo->driver, ixgbe_driver_name, sizeof(drvinfo->driver));
 
@@ -1161,7 +1214,7 @@ static void ixgbe_get_ringparam(struct net_device *netdev,
 				struct kernel_ethtool_ringparam *kernel_ring,
 				struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_ring *tx_ring = adapter->tx_ring[0];
 	struct ixgbe_ring *rx_ring = adapter->rx_ring[0];
 
@@ -1176,7 +1229,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
 			       struct kernel_ethtool_ringparam *kernel_ring,
 			       struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_ring *temp_ring;
 	int i, j, err = 0;
 	u32 new_rx_count, new_tx_count;
@@ -1336,7 +1389,7 @@ static int ixgbe_get_sset_count(struct net_device *netdev, int sset)
 static void ixgbe_get_ethtool_stats(struct net_device *netdev,
 				    struct ethtool_stats *stats, u64 *data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct rtnl_link_stats64 temp;
 	const struct rtnl_link_stats64 *net_stats;
 	unsigned int start;
@@ -1710,7 +1763,7 @@ static int ixgbe_eeprom_test(struct ixgbe_adapter *adapter, u64 *data)
 static irqreturn_t ixgbe_test_intr(int irq, void *data)
 {
 	struct net_device *netdev = (struct net_device *) data;
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	adapter->test_icr |= IXGBE_READ_REG(&adapter->hw, IXGBE_EICR);
 
@@ -2183,7 +2236,7 @@ out:
 static void ixgbe_diag_test(struct net_device *netdev,
 			    struct ethtool_test *eth_test, u64 *data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	bool if_running = netif_running(netdev);
 
 	if (ixgbe_removed(adapter->hw.hw_addr)) {
@@ -2306,7 +2359,7 @@ static int ixgbe_wol_exclusion(struct ixgbe_adapter *adapter,
 static void ixgbe_get_wol(struct net_device *netdev,
 			  struct ethtool_wolinfo *wol)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	wol->supported = WAKE_UCAST | WAKE_MCAST |
 			 WAKE_BCAST | WAKE_MAGIC;
@@ -2328,7 +2381,7 @@ static void ixgbe_get_wol(struct net_device *netdev,
 
 static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE |
 			    WAKE_FILTER))
@@ -2353,9 +2406,53 @@ static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	return 0;
 }
 
+static int ixgbe_set_wol_acpi(struct net_device *netdev,
+			      struct ethtool_wolinfo *wol)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 grc;
+
+	if (ixgbe_wol_exclusion(adapter, wol))
+		return wol->wolopts ? -EOPNOTSUPP : 0;
+
+	/* disable APM wakeup */
+	grc = IXGBE_READ_REG(hw, IXGBE_GRC_X550EM_a);
+	grc &= ~IXGBE_GRC_APME;
+	IXGBE_WRITE_REG(hw, IXGBE_GRC_X550EM_a, grc);
+
+	/* erase existing filters */
+	IXGBE_WRITE_REG(hw, IXGBE_WUFC, 0);
+	adapter->wol = 0;
+
+	if (wol->wolopts & WAKE_UCAST)
+		adapter->wol |= IXGBE_WUFC_EX;
+	if (wol->wolopts & WAKE_MCAST)
+		adapter->wol |= IXGBE_WUFC_MC;
+	if (wol->wolopts & WAKE_BCAST)
+		adapter->wol |= IXGBE_WUFC_BC;
+
+	IXGBE_WRITE_REG(hw, IXGBE_WUC, IXGBE_WUC_PME_EN);
+	IXGBE_WRITE_REG(hw, IXGBE_WUFC, adapter->wol);
+
+	hw->wol_enabled = adapter->wol;
+	device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol);
+
+	return 0;
+}
+
+static int ixgbe_set_wol_e610(struct net_device *netdev,
+			      struct ethtool_wolinfo *wol)
+{
+	if (wol->wolopts & (WAKE_UCAST | WAKE_MCAST | WAKE_BCAST))
+		return ixgbe_set_wol_acpi(netdev, wol);
+	else
+		return ixgbe_set_wol(netdev, wol);
+}
+
 static int ixgbe_nway_reset(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (netif_running(netdev))
 		ixgbe_reinit_locked(adapter);
@@ -2366,7 +2463,7 @@ static int ixgbe_nway_reset(struct net_device *netdev)
 static int ixgbe_set_phys_id(struct net_device *netdev,
 			     enum ethtool_phys_id_state state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (!hw->mac.ops.led_on || !hw->mac.ops.led_off)
@@ -2394,12 +2491,32 @@ static int ixgbe_set_phys_id(struct net_device *netdev,
 	return 0;
 }
 
+static int ixgbe_set_phys_id_e610(struct net_device *netdev,
+				  enum ethtool_phys_id_state state)
+{
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+	bool led_active;
+
+	switch (state) {
+	case ETHTOOL_ID_ACTIVE:
+		led_active = true;
+		break;
+	case ETHTOOL_ID_INACTIVE:
+		led_active = false;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return ixgbe_aci_set_port_id_led(&adapter->hw, !led_active);
+}
+
 static int ixgbe_get_coalesce(struct net_device *netdev,
 			      struct ethtool_coalesce *ec,
 			      struct kernel_ethtool_coalesce *kernel_coal,
 			      struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* only valid if in constant ITR mode */
 	if (adapter->rx_itr_setting <= 1)
@@ -2455,7 +2572,7 @@ static int ixgbe_set_coalesce(struct net_device *netdev,
 			      struct kernel_ethtool_coalesce *kernel_coal,
 			      struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_q_vector *q_vector;
 	int i;
 	u16 tx_itr_param, rx_itr_param, tx_itr_prev;
@@ -2681,7 +2798,7 @@ static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter)
 static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 			   u32 *rule_locs)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
@@ -3069,7 +3186,7 @@ static int ixgbe_set_rss_hash_opt(struct ixgbe_adapter *adapter,
 
 static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
@@ -3096,7 +3213,7 @@ static u32 ixgbe_get_rxfh_key_size(struct net_device *netdev)
 
 static u32 ixgbe_rss_indir_size(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	return ixgbe_rss_indir_tbl_entries(adapter);
 }
@@ -3116,7 +3233,7 @@ static void ixgbe_get_reta(struct ixgbe_adapter *adapter, u32 *indir)
 static int ixgbe_get_rxfh(struct net_device *netdev,
 			  struct ethtool_rxfh_param *rxfh)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
@@ -3134,7 +3251,7 @@ static int ixgbe_set_rxfh(struct net_device *netdev,
 			  struct ethtool_rxfh_param *rxfh,
 			  struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int i;
 	u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter);
 
@@ -3176,7 +3293,7 @@ static int ixgbe_set_rxfh(struct net_device *netdev,
 static int ixgbe_get_ts_info(struct net_device *dev,
 			     struct kernel_ethtool_ts_info *info)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	/* we always support timestamping disabled */
 	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE);
@@ -3252,7 +3369,7 @@ static unsigned int ixgbe_max_channels(struct ixgbe_adapter *adapter)
 static void ixgbe_get_channels(struct net_device *dev,
 			       struct ethtool_channels *ch)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	/* report maximum channels */
 	ch->max_combined = ixgbe_max_channels(adapter);
@@ -3289,7 +3406,7 @@ static void ixgbe_get_channels(struct net_device *dev,
 static int ixgbe_set_channels(struct net_device *dev,
 			      struct ethtool_channels *ch)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	unsigned int count = ch->combined_count;
 	u8 max_rss_indices = ixgbe_max_rss_indices(adapter);
 
@@ -3327,7 +3444,7 @@ static int ixgbe_set_channels(struct net_device *dev,
 static int ixgbe_get_module_info(struct net_device *dev,
 				       struct ethtool_modinfo *modinfo)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u8 sff8472_rev, addr_mode;
 	bool page_swap = false;
@@ -3373,7 +3490,7 @@ static int ixgbe_get_module_eeprom(struct net_device *dev,
 					 struct ethtool_eeprom *ee,
 					 u8 *data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	int status = -EFAULT;
 	u8 databyte = 0xFF;
@@ -3469,7 +3586,7 @@ ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_keee *edata)
 
 static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (!(adapter->flags2 & IXGBE_FLAG2_EEE_CAPABLE))
@@ -3483,7 +3600,7 @@ static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
 
 static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_keee *edata)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ethtool_keee eee_data;
 	int ret_val;
@@ -3538,7 +3655,7 @@ static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_keee *edata)
 
 static u32 ixgbe_get_priv_flags(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	u32 priv_flags = 0;
 
 	if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
@@ -3555,7 +3672,7 @@ static u32 ixgbe_get_priv_flags(struct net_device *netdev)
 
 static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	unsigned int flags2 = adapter->flags2;
 	unsigned int i;
 
@@ -3638,7 +3755,57 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
 	.set_link_ksettings     = ixgbe_set_link_ksettings,
 };
 
+static const struct ethtool_ops ixgbe_ethtool_ops_e610 = {
+	.supported_coalesce_params = ETHTOOL_COALESCE_USECS,
+	.get_drvinfo            = ixgbe_get_drvinfo,
+	.get_regs_len           = ixgbe_get_regs_len,
+	.get_regs               = ixgbe_get_regs,
+	.get_wol                = ixgbe_get_wol,
+	.set_wol                = ixgbe_set_wol_e610,
+	.nway_reset             = ixgbe_nway_reset,
+	.get_link               = ethtool_op_get_link,
+	.get_eeprom_len         = ixgbe_get_eeprom_len,
+	.get_eeprom             = ixgbe_get_eeprom,
+	.set_eeprom             = ixgbe_set_eeprom,
+	.get_ringparam          = ixgbe_get_ringparam,
+	.set_ringparam          = ixgbe_set_ringparam,
+	.get_pause_stats	= ixgbe_get_pause_stats,
+	.get_pauseparam         = ixgbe_get_pauseparam,
+	.set_pauseparam         = ixgbe_set_pauseparam_e610,
+	.get_msglevel           = ixgbe_get_msglevel,
+	.set_msglevel           = ixgbe_set_msglevel,
+	.self_test              = ixgbe_diag_test,
+	.get_strings            = ixgbe_get_strings,
+	.set_phys_id            = ixgbe_set_phys_id_e610,
+	.get_sset_count         = ixgbe_get_sset_count,
+	.get_ethtool_stats      = ixgbe_get_ethtool_stats,
+	.get_coalesce           = ixgbe_get_coalesce,
+	.set_coalesce           = ixgbe_set_coalesce,
+	.get_rxnfc		= ixgbe_get_rxnfc,
+	.set_rxnfc		= ixgbe_set_rxnfc,
+	.get_rxfh_indir_size	= ixgbe_rss_indir_size,
+	.get_rxfh_key_size	= ixgbe_get_rxfh_key_size,
+	.get_rxfh		= ixgbe_get_rxfh,
+	.set_rxfh		= ixgbe_set_rxfh,
+	.get_eee		= ixgbe_get_eee,
+	.set_eee		= ixgbe_set_eee,
+	.get_channels		= ixgbe_get_channels,
+	.set_channels		= ixgbe_set_channels,
+	.get_priv_flags		= ixgbe_get_priv_flags,
+	.set_priv_flags		= ixgbe_set_priv_flags,
+	.get_ts_info		= ixgbe_get_ts_info,
+	.get_module_info	= ixgbe_get_module_info,
+	.get_module_eeprom	= ixgbe_get_module_eeprom,
+	.get_link_ksettings     = ixgbe_get_link_ksettings,
+	.set_link_ksettings     = ixgbe_set_link_ksettings,
+};
+
 void ixgbe_set_ethtool_ops(struct net_device *netdev)
 {
-	netdev->ethtool_ops = &ixgbe_ethtool_ops;
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
+
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		netdev->ethtool_ops = &ixgbe_ethtool_ops_e610;
+	else
+		netdev->ethtool_ops = &ixgbe_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
index 955dced844a9..7dcf6ecd157b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
@@ -56,7 +56,7 @@ int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid)
 	if (xid >= netdev->fcoe_ddp_xid)
 		return 0;
 
-	adapter = netdev_priv(netdev);
+	adapter = ixgbe_from_netdev(netdev);
 	fcoe = &adapter->fcoe;
 	ddp = &fcoe->ddp[xid];
 	if (!ddp->udl)
@@ -153,7 +153,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid,
 	if (!netdev || !sgl)
 		return 0;
 
-	adapter = netdev_priv(netdev);
+	adapter = ixgbe_from_netdev(netdev);
 	if (xid >= netdev->fcoe_ddp_xid) {
 		e_warn(drv, "xid=0x%x out-of-range\n", xid);
 		return 0;
@@ -834,7 +834,7 @@ static void ixgbe_fcoe_ddp_disable(struct ixgbe_adapter *adapter)
  */
 int ixgbe_fcoe_enable(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_fcoe *fcoe = &adapter->fcoe;
 
 	atomic_inc(&fcoe->refcnt);
@@ -881,7 +881,7 @@ int ixgbe_fcoe_enable(struct net_device *netdev)
  */
 int ixgbe_fcoe_disable(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (!atomic_dec_and_test(&adapter->fcoe.refcnt))
 		return -EINVAL;
@@ -927,7 +927,7 @@ int ixgbe_fcoe_disable(struct net_device *netdev)
 int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type)
 {
 	u16 prefix = 0xffff;
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_mac_info *mac = &adapter->hw.mac;
 
 	switch (type) {
@@ -967,7 +967,7 @@ int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type)
 int ixgbe_fcoe_get_hbainfo(struct net_device *netdev,
 			   struct netdev_fcoe_hbainfo *info)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u64 dsn;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c
new file mode 100644
index 000000000000..49d3b66add7e
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c
@@ -0,0 +1,707 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2025 Intel Corporation. */
+
+#include <linux/crc32.h>
+#include <linux/pldmfw.h>
+#include <linux/uuid.h>
+
+#include "ixgbe.h"
+#include "ixgbe_fw_update.h"
+
+struct ixgbe_fwu_priv {
+	struct pldmfw context;
+
+	struct ixgbe_adapter *adapter;
+	struct netlink_ext_ack *extack;
+
+	/* Track which NVM banks to activate at the end of the update */
+	u8 activate_flags;
+	bool emp_reset_available;
+};
+
+/**
+ * ixgbe_send_package_data - Send record package data to firmware
+ * @context: PLDM fw update structure
+ * @data: pointer to the package data
+ * @length: length of the package data
+ *
+ * Send a copy of the package data associated with the PLDM record matching
+ * this device to the firmware.
+ *
+ * Note that this function sends an AdminQ command that will fail unless the
+ * NVM resource has been acquired.
+ *
+ * Return: zero on success, or a negative error code on failure.
+ */
+static int ixgbe_send_package_data(struct pldmfw *context,
+				   const u8 *data, u16 length)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct ixgbe_adapter *adapter = priv->adapter;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 *package_data;
+	int err;
+
+	package_data = kmemdup(data, length, GFP_KERNEL);
+	if (!package_data)
+		return -ENOMEM;
+
+	err = ixgbe_nvm_set_pkg_data(hw, false, package_data, length);
+
+	kfree(package_data);
+
+	return err;
+}
+
+/**
+ * ixgbe_check_component_response - Report firmware response to a component
+ * @adapter: device private data structure
+ * @response: indicates whether this component can be updated
+ * @code: code indicating reason for response
+ * @extack: netlink extended ACK structure
+ *
+ * Check whether firmware indicates if this component can be updated. Report
+ * a suitable error message over the netlink extended ACK if the component
+ * cannot be updated.
+ *
+ * Return: 0 if the component can be updated, or -ECANCELED if the
+ * firmware indicates the component cannot be updated.
+ */
+static int ixgbe_check_component_response(struct ixgbe_adapter *adapter,
+					  u8 response, u8 code,
+					  struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	switch (response) {
+	case IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED:
+		/* Firmware indicated this update is good to proceed. */
+		return 0;
+	case IXGBE_ACI_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Firmware recommends not updating, as it may result in a downgrade. Continuing anyways");
+		return 0;
+	case IXGBE_ACI_NVM_PASS_COMP_CAN_NOT_BE_UPDATED:
+		NL_SET_ERR_MSG_MOD(extack, "Firmware has rejected updating.");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_PARTIAL_CHECK:
+		if (hw->mac.ops.fw_recovery_mode &&
+		    hw->mac.ops.fw_recovery_mode(hw))
+			return 0;
+		break;
+	}
+
+	switch (code) {
+	case IXGBE_ACI_NVM_PASS_COMP_STAMP_IDENTICAL_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component comparison stamp is identical to running image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_STAMP_LOWER:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component comparison stamp is lower than running image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_INVALID_STAMP_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component comparison stamp is invalid");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_CONFLICT_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component table conflict occurred");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_PRE_REQ_NOT_MET_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Component pre-requisites not met");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_NOT_SUPPORTED_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Component not supported");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_CANNOT_DOWNGRADE_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Component cannot be downgraded");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_INCOMPLETE_IMAGE_CODE:
+		NL_SET_ERR_MSG_MOD(extack, "Incomplete component image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_VER_STR_IDENTICAL_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component version is identical to running image");
+		break;
+	case IXGBE_ACI_NVM_PASS_COMP_VER_STR_LOWER_CODE:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Component version is lower than the running image");
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Received unexpected response code from firmware");
+		break;
+	}
+
+	return -ECANCELED;
+}
+
+/**
+ * ixgbe_send_component_table - Send PLDM component table to firmware
+ * @context: PLDM fw update structure
+ * @component: the component to process
+ * @transfer_flag: relative transfer order of this component
+ *
+ * Read relevant data from the component and forward it to the device
+ * firmware. Check the response to determine if the firmware indicates that
+ * the update can proceed.
+ *
+ * This function sends ACI commands related to the NVM, and assumes that
+ * the NVM resource has been acquired.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_send_component_table(struct pldmfw *context,
+				      struct pldmfw_component *component,
+				      u8 transfer_flag)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct ixgbe_adapter *adapter = priv->adapter;
+	struct netlink_ext_ack *extack = priv->extack;
+	struct ixgbe_aci_cmd_nvm_comp_tbl *comp_tbl;
+	u8 comp_response, comp_response_code;
+	struct ixgbe_hw *hw = &adapter->hw;
+	size_t length;
+	int err;
+
+	switch (component->identifier) {
+	case NVM_COMP_ID_OROM:
+	case NVM_COMP_ID_NVM:
+	case NVM_COMP_ID_NETLIST:
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to update due to unknown firmware component");
+		return -EOPNOTSUPP;
+	}
+
+	length = struct_size(comp_tbl, cvs, component->version_len);
+	comp_tbl = kzalloc(length, GFP_KERNEL);
+	if (!comp_tbl)
+		return -ENOMEM;
+
+	comp_tbl->comp_class = cpu_to_le16(component->classification);
+	comp_tbl->comp_id = cpu_to_le16(component->identifier);
+	comp_tbl->comp_class_idx = FWU_COMP_CLASS_IDX_NOT_USE;
+	comp_tbl->comp_cmp_stamp = cpu_to_le32(component->comparison_stamp);
+	comp_tbl->cvs_type = component->version_type;
+	comp_tbl->cvs_len = component->version_len;
+
+	memcpy(comp_tbl->cvs, component->version_string,
+	       component->version_len);
+
+	err = ixgbe_nvm_pass_component_tbl(hw, (u8 *)comp_tbl, length,
+					   transfer_flag, &comp_response,
+					   &comp_response_code);
+
+	kfree(comp_tbl);
+
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to transfer component table to firmware");
+		return -EIO;
+	}
+
+	return ixgbe_check_component_response(adapter,
+					      comp_response,
+					      comp_response_code, extack);
+}
+
+/**
+ * ixgbe_write_one_nvm_block - Write an NVM block and await completion response
+ * @adapter: the PF data structure
+ * @module: the module to write to
+ * @offset: offset in bytes
+ * @block_size: size of the block to write, up to 4k
+ * @block: pointer to block of data to write
+ * @last_cmd: whether this is the last command
+ * @extack: netlink extended ACK structure
+ *
+ * Write a block of data to a flash module, and await for the completion
+ * response message from firmware.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * On successful return, reset level indicates the device reset required to
+ * complete the update.
+ *
+ *   0 - IXGBE_ACI_NVM_POR_FLAG - A full power on is required
+ *   1 - IXGBE_ACI_NVM_PERST_FLAG - A cold PCIe reset is required
+ *   2 - IXGBE_ACI_NVM_EMPR_FLAG - An EMP reset is required
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_write_one_nvm_block(struct ixgbe_adapter *adapter,
+				     u16 module, u32 offset,
+				     u16 block_size, u8 *block, bool last_cmd,
+				     struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	return ixgbe_aci_update_nvm(hw, module, offset, block_size, block,
+				    last_cmd, 0);
+}
+
+/**
+ * ixgbe_write_nvm_module - Write data to an NVM module
+ * @adapter: the PF driver structure
+ * @module: the module id to program
+ * @component: the name of the component being updated
+ * @image: buffer of image data to write to the NVM
+ * @length: length of the buffer
+ * @extack: netlink extended ACK structure
+ *
+ * Loop over the data for a given NVM module and program it in 4 Kb
+ * blocks. Notify devlink core of progress after each block is programmed.
+ * Loops over a block of data and programs the NVM in 4k block chunks.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_write_nvm_module(struct ixgbe_adapter *adapter, u16 module,
+				  const char *component, const u8 *image,
+				  u32 length,
+				  struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = adapter->devlink;
+	u32 offset = 0;
+	bool last_cmd;
+	u8 *block;
+	int err;
+
+	devlink_flash_update_status_notify(devlink, "Flashing",
+					   component, 0, length);
+
+	block = kzalloc(IXGBE_ACI_MAX_BUFFER_SIZE, GFP_KERNEL);
+	if (!block)
+		return -ENOMEM;
+
+	do {
+		u32 block_size;
+
+		block_size = min_t(u32, IXGBE_ACI_MAX_BUFFER_SIZE,
+				   length - offset);
+		last_cmd = !(offset + block_size < length);
+
+		memcpy(block, image + offset, block_size);
+
+		err = ixgbe_write_one_nvm_block(adapter, module, offset,
+						block_size, block, last_cmd,
+						extack);
+		if (err)
+			break;
+
+		offset += block_size;
+
+		devlink_flash_update_status_notify(devlink, "Flashing",
+						   component, offset, length);
+	} while (!last_cmd);
+
+	if (err)
+		devlink_flash_update_status_notify(devlink, "Flashing failed",
+						   component, length, length);
+	else
+		devlink_flash_update_status_notify(devlink, "Flashing done",
+						   component, length, length);
+
+	kfree(block);
+
+	return err;
+}
+
+/* Length in seconds to wait before timing out when erasing a flash module.
+ * Yes, erasing really can take minutes to complete.
+ */
+#define IXGBE_FW_ERASE_TIMEOUT 300
+
+/**
+ * ixgbe_erase_nvm_module - Erase an NVM module and await firmware completion
+ * @adapter: the PF data structure
+ * @module: the module to erase
+ * @component: name of the component being updated
+ * @extack: netlink extended ACK structure
+ *
+ * Erase the inactive NVM bank associated with this module, and await for
+ * a completion response message from firmware.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_erase_nvm_module(struct ixgbe_adapter *adapter, u16 module,
+				  const char *component,
+				  struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = adapter->devlink;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	devlink_flash_update_timeout_notify(devlink, "Erasing", component,
+					    IXGBE_FW_ERASE_TIMEOUT);
+
+	err = ixgbe_aci_erase_nvm(hw, module);
+	if (err)
+		devlink_flash_update_status_notify(devlink, "Erasing failed",
+						   component, 0, 0);
+	else
+		devlink_flash_update_status_notify(devlink, "Erasing done",
+						   component, 0, 0);
+
+	return err;
+}
+
+/**
+ * ixgbe_switch_flash_banks - Tell firmware to switch NVM banks
+ * @adapter: Pointer to the PF data structure
+ * @activate_flags: flags used for the activation command
+ * @emp_reset_available: on return, indicates if EMP reset is available
+ * @extack: netlink extended ACK structure
+ *
+ * Notify firmware to activate the newly written flash banks, and wait for the
+ * firmware response.
+ *
+ * Return: 0 on success or an error code on failure.
+ */
+static int ixgbe_switch_flash_banks(struct ixgbe_adapter *adapter,
+				    u8 activate_flags,
+				    bool *emp_reset_available,
+				    struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 response_flags;
+	int err;
+
+	err = ixgbe_nvm_write_activate(hw, activate_flags, &response_flags);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to switch active flash banks");
+		return err;
+	}
+
+	if (emp_reset_available) {
+		if (hw->dev_caps.common_cap.reset_restrict_support)
+			*emp_reset_available =
+				response_flags & IXGBE_ACI_NVM_EMPR_ENA;
+		else
+			*emp_reset_available = true;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_flash_component - Flash a component of the NVM
+ * @context: PLDM fw update structure
+ * @component: the component table to program
+ *
+ * Program the flash contents for a given component. First, determine the
+ * module id. Then, erase the secondary bank for this module. Finally, write
+ * the contents of the component to the NVM.
+ *
+ * Note this function assumes the caller has acquired the NVM resource.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_flash_component(struct pldmfw *context,
+				 struct pldmfw_component *component)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct netlink_ext_ack *extack = priv->extack;
+	struct ixgbe_adapter *adapter = priv->adapter;
+	const char *name;
+	u16 module;
+	int err;
+	u8 flag;
+
+	switch (component->identifier) {
+	case NVM_COMP_ID_OROM:
+		module = IXGBE_E610_SR_1ST_OROM_BANK_PTR;
+		flag = IXGBE_ACI_NVM_ACTIV_SEL_OROM;
+		name = "fw.undi";
+		break;
+	case NVM_COMP_ID_NVM:
+		module = IXGBE_E610_SR_1ST_NVM_BANK_PTR;
+		flag = IXGBE_ACI_NVM_ACTIV_SEL_NVM;
+		name = "fw.mgmt";
+		break;
+	case NVM_COMP_ID_NETLIST:
+		module = IXGBE_E610_SR_NETLIST_BANK_PTR;
+		flag = IXGBE_ACI_NVM_ACTIV_SEL_NETLIST;
+		name = "fw.netlist";
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* Mark this component for activating at the end. */
+	priv->activate_flags |= flag;
+
+	err = ixgbe_erase_nvm_module(adapter, module, name, extack);
+	if (err)
+		return err;
+
+	return ixgbe_write_nvm_module(adapter, module, name,
+				      component->component_data,
+				      component->component_size, extack);
+}
+
+/**
+ * ixgbe_finalize_update - Perform last steps to complete device update
+ * @context: PLDM fw update structure
+ *
+ * Called as the last step of the update process. Complete the update by
+ * telling the firmware to switch active banks, and perform a reset of
+ * configured.
+ *
+ * Return: 0 on success, or an error code on failure.
+ */
+static int ixgbe_finalize_update(struct pldmfw *context)
+{
+	struct ixgbe_fwu_priv *priv = container_of(context,
+						   struct ixgbe_fwu_priv,
+						   context);
+	struct ixgbe_adapter *adapter = priv->adapter;
+	struct netlink_ext_ack *extack = priv->extack;
+	struct devlink *devlink = adapter->devlink;
+	int err;
+
+	/* Finally, notify firmware to activate the written NVM banks */
+	err = ixgbe_switch_flash_banks(adapter, priv->activate_flags,
+				       &priv->emp_reset_available, extack);
+	if (err)
+		return err;
+
+	adapter->fw_emp_reset_disabled = !priv->emp_reset_available;
+
+	if (!adapter->fw_emp_reset_disabled)
+		devlink_flash_update_status_notify(devlink,
+						   "Suggested is to activate new firmware by devlink reload, if it doesn't work then a power cycle is required",
+						   NULL, 0, 0);
+
+	return 0;
+}
+
+static const struct pldmfw_ops ixgbe_fwu_ops_e610 = {
+	.match_record = &pldmfw_op_pci_match_record,
+	.send_package_data = &ixgbe_send_package_data,
+	.send_component_table = &ixgbe_send_component_table,
+	.flash_component = &ixgbe_flash_component,
+	.finalize_update = &ixgbe_finalize_update,
+};
+
+/**
+ * ixgbe_get_pending_updates - Check if the component has a pending update
+ * @adapter: the PF driver structure
+ * @pending: on return, bitmap of updates pending
+ * @extack: Netlink extended ACK
+ *
+ * Check if the device has any pending updates on any flash components.
+ *
+ * Return: 0 on success, or a negative error code on failure. Update
+ * pending with the bitmap of pending updates.
+ */
+int ixgbe_get_pending_updates(struct ixgbe_adapter *adapter, u8 *pending,
+			      struct netlink_ext_ack *extack)
+{
+	struct ixgbe_hw_dev_caps *dev_caps;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	dev_caps = kzalloc(sizeof(*dev_caps), GFP_KERNEL);
+	if (!dev_caps)
+		return -ENOMEM;
+
+	err = ixgbe_discover_dev_caps(hw, dev_caps);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to read device capabilities");
+		kfree(dev_caps);
+		return -EIO;
+	}
+
+	*pending = 0;
+
+	if (dev_caps->common_cap.nvm_update_pending_nvm)
+		*pending |= IXGBE_ACI_NVM_ACTIV_SEL_NVM;
+
+	if (dev_caps->common_cap.nvm_update_pending_orom)
+		*pending |= IXGBE_ACI_NVM_ACTIV_SEL_OROM;
+
+	if (dev_caps->common_cap.nvm_update_pending_netlist)
+		*pending |= IXGBE_ACI_NVM_ACTIV_SEL_NETLIST;
+
+	kfree(dev_caps);
+
+	return 0;
+}
+
+/**
+ * ixgbe_cancel_pending_update - Cancel any pending update for a component
+ * @adapter: the PF driver structure
+ * @component: if not NULL, the name of the component being updated
+ * @extack: Netlink extended ACK structure
+ *
+ * Cancel any pending update for the specified component. If component is
+ * NULL, all device updates will be canceled.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int ixgbe_cancel_pending_update(struct ixgbe_adapter *adapter,
+				       const char *component,
+				       struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = adapter->devlink;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 pending;
+	int err;
+
+	err = ixgbe_get_pending_updates(adapter, &pending, extack);
+	if (err)
+		return err;
+
+	/* If the flash_update request is for a specific component, ignore all
+	 * of the other components.
+	 */
+	if (component) {
+		if (strcmp(component, "fw.mgmt") == 0)
+			pending &= IXGBE_ACI_NVM_ACTIV_SEL_NVM;
+		else if (strcmp(component, "fw.undi") == 0)
+			pending &= IXGBE_ACI_NVM_ACTIV_SEL_OROM;
+		else if (strcmp(component, "fw.netlist") == 0)
+			pending &= IXGBE_ACI_NVM_ACTIV_SEL_NETLIST;
+		else
+			return -EINVAL;
+	}
+
+	/* There is no previous pending update, so this request may continue */
+	if (!pending)
+		return 0;
+
+	/* In order to allow overwriting a previous pending update, notify
+	 * firmware to cancel that update by issuing the appropriate command.
+	 */
+	devlink_flash_update_status_notify(devlink,
+					   "Canceling previous pending update",
+					   component, 0, 0);
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_WRITE);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to acquire device flash lock");
+		return -EIO;
+	}
+
+	pending |= IXGBE_ACI_NVM_REVERT_LAST_ACTIV;
+	err = ixgbe_switch_flash_banks(adapter, pending, NULL, extack);
+
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ixgbe_flash_pldm_image - Write a PLDM-formatted firmware image to the device
+ * @devlink: pointer to devlink associated with the device to update
+ * @params: devlink flash update parameters
+ * @extack: netlink extended ACK structure
+ *
+ * Parse the data for a given firmware file, verifying that it is a valid PLDM
+ * formatted image that matches this device.
+ *
+ * Extract the device record Package Data and Component Tables and send them
+ * to the firmware. Extract and write the flash data for each of the three
+ * main flash components, "fw.mgmt", "fw.undi", and "fw.netlist". Notify
+ * firmware once the data is written to the inactive banks.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int ixgbe_flash_pldm_image(struct devlink *devlink,
+			   struct devlink_flash_update_params *params,
+			   struct netlink_ext_ack *extack)
+{
+	struct ixgbe_adapter *adapter = devlink_priv(devlink);
+	struct device *dev = &adapter->pdev->dev;
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_fwu_priv priv;
+	u8 preservation;
+	int err;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		return -EOPNOTSUPP;
+
+	switch (params->overwrite_mask) {
+	case 0:
+		/* preserve all settings and identifiers */
+		preservation = IXGBE_ACI_NVM_PRESERVE_ALL;
+		break;
+	case DEVLINK_FLASH_OVERWRITE_SETTINGS:
+		/* Overwrite settings, but preserve vital information such as
+		 * device identifiers.
+		 */
+		preservation = IXGBE_ACI_NVM_PRESERVE_SELECTED;
+		break;
+	case (DEVLINK_FLASH_OVERWRITE_SETTINGS |
+	      DEVLINK_FLASH_OVERWRITE_IDENTIFIERS):
+		/* overwrite both settings and identifiers, preserve nothing */
+		preservation = IXGBE_ACI_NVM_NO_PRESERVATION;
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Requested overwrite mask is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	/* Cannot get caps in recovery mode, so lack of nvm_unified_update bit
+	 * cannot lead to error
+	 */
+	if (!hw->dev_caps.common_cap.nvm_unified_update &&
+	    (hw->mac.ops.fw_recovery_mode &&
+	     !hw->mac.ops.fw_recovery_mode(hw))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Current firmware does not support unified update");
+		return -EOPNOTSUPP;
+	}
+
+	memset(&priv, 0, sizeof(priv));
+
+	priv.context.ops = &ixgbe_fwu_ops_e610;
+	priv.context.dev = dev;
+	priv.extack = extack;
+	priv.adapter = adapter;
+	priv.activate_flags = preservation;
+
+	devlink_flash_update_status_notify(devlink,
+					   "Preparing to flash", NULL, 0, 0);
+
+	err = ixgbe_cancel_pending_update(adapter, NULL, extack);
+	if (err)
+		return err;
+
+	err = ixgbe_acquire_nvm(hw, IXGBE_RES_WRITE);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to acquire device flash lock");
+		return -EIO;
+	}
+
+	err = pldmfw_flash_image(&priv.context, params->fw);
+	if (err == -ENOENT) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Firmware image has no record matching this device");
+	} else if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to flash PLDM image");
+	}
+
+	ixgbe_release_nvm(hw);
+
+	return err;
+}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h
new file mode 100644
index 000000000000..abdd708c93df
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2025 Intel Corporation. */
+
+#ifndef _IXGBE_FW_UPDATE_H_
+#define _IXGBE_FW_UPDATE_H_
+
+int ixgbe_flash_pldm_image(struct devlink *devlink,
+			   struct devlink_flash_update_params *params,
+			   struct netlink_ext_ack *extack);
+int ixgbe_get_pending_updates(struct ixgbe_adapter *adapter, u8 *pending,
+			      struct netlink_ext_ack *extack);
+#endif
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 796e90d741f0..d1f4073b36f9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -480,7 +480,7 @@ static int ixgbe_ipsec_parse_proto_keys(struct net_device *dev,
 static int ixgbe_ipsec_check_mgmt_ip(struct net_device *dev,
 				     struct xfrm_state *xs)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 mfval, manc, reg;
 	int num_filters = 4;
@@ -566,7 +566,7 @@ static int ixgbe_ipsec_add_sa(struct net_device *dev,
 			      struct xfrm_state *xs,
 			      struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct ixgbe_hw *hw = &adapter->hw;
 	int checked, match, first;
@@ -760,7 +760,7 @@ static int ixgbe_ipsec_add_sa(struct net_device *dev,
  **/
 static void ixgbe_ipsec_del_sa(struct net_device *dev, struct xfrm_state *xs)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 zerobuf[4] = {0, 0, 0, 0};
@@ -1057,7 +1057,7 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring,
 		   struct ixgbe_tx_buffer *first,
 		   struct ixgbe_ipsec_tx_data *itd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(tx_ring->netdev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct xfrm_state *xs;
 	struct sec_path *sp;
@@ -1147,7 +1147,7 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
 		    union ixgbe_adv_rx_desc *rx_desc,
 		    struct sk_buff *skb)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(rx_ring->netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(rx_ring->netdev);
 	__le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
 	__le16 ipsec_pkt_types = cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH |
 					     IXGBE_RXDADV_PKTTYPE_IPSEC_ESP);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a2718218963e..03d31e5b131d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -49,6 +49,7 @@
 #include "ixgbe_sriov.h"
 #include "ixgbe_model.h"
 #include "ixgbe_txrx_common.h"
+#include "devlink/devlink.h"
 
 char ixgbe_driver_name[] = "ixgbe";
 static const char ixgbe_driver_string[] =
@@ -1095,7 +1096,7 @@ static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
 static int ixgbe_tx_maxrate(struct net_device *netdev,
 			    int queue_index, u32 maxrate)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 bcnrc_val = ixgbe_link_mbps(adapter);
 
@@ -4678,7 +4679,7 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
 static int ixgbe_vlan_rx_add_vid(struct net_device *netdev,
 				 __be16 proto, u16 vid)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	/* add VID to filter table */
@@ -4737,7 +4738,7 @@ void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid)
 static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev,
 				  __be16 proto, u16 vid)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	/* remove VID from filter table */
@@ -4962,7 +4963,7 @@ static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter)
  **/
 static int ixgbe_write_mc_addr_list(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (!netif_running(netdev))
@@ -5138,7 +5139,7 @@ int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter,
 
 static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int ret;
 
 	ret = ixgbe_add_mac_filter(adapter, addr, VMDQ_P(0));
@@ -5148,7 +5149,7 @@ static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr)
 
 static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	ixgbe_del_mac_filter(adapter, addr, VMDQ_P(0));
 
@@ -5166,7 +5167,7 @@ static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr)
  **/
 void ixgbe_set_rx_mode(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE;
 	netdev_features_t features = netdev->features;
@@ -5268,7 +5269,7 @@ static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter)
 
 static int ixgbe_udp_tunnel_sync(struct net_device *dev, unsigned int table)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct udp_tunnel_info ti;
 
@@ -6600,7 +6601,7 @@ static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter)
  **/
 static void ixgbe_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* Do the reset outside of interrupt context */
 	ixgbe_tx_timeout_reset(adapter);
@@ -6849,7 +6850,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
 	adapter->tx_work_limit = IXGBE_DEFAULT_TX_WORK;
 
 	/* initialize eeprom parameters */
-	if (ixgbe_init_eeprom_params_generic(hw)) {
+	if (hw->eeprom.ops.init_params(hw)) {
 		e_dev_err("EEPROM initialization failed\n");
 		return -EIO;
 	}
@@ -7165,7 +7166,7 @@ static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter)
  **/
 static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (ixgbe_enabled_xdp_adapter(adapter)) {
 		int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD;
@@ -7212,7 +7213,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
  **/
 int ixgbe_open(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	int err, queues;
 
@@ -7316,7 +7317,7 @@ static void ixgbe_close_suspend(struct ixgbe_adapter *adapter)
  **/
 int ixgbe_close(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	ixgbe_ptp_stop(adapter);
 
@@ -8364,6 +8365,34 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter)
 	rtnl_unlock();
 }
 
+static int ixgbe_check_fw_api_mismatch(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		return 0;
+
+	if (hw->mac.ops.get_fw_ver && hw->mac.ops.get_fw_ver(hw))
+		return 0;
+
+	if (hw->api_maj_ver > IXGBE_FW_API_VER_MAJOR) {
+		e_dev_err("The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n");
+
+		adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH;
+		return -EOPNOTSUPP;
+	} else if (hw->api_maj_ver == IXGBE_FW_API_VER_MAJOR &&
+		   hw->api_min_ver > IXGBE_FW_API_VER_MINOR + IXGBE_FW_API_VER_DIFF_ALLOWED) {
+		e_dev_info("The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n");
+		adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH;
+	} else if (hw->api_maj_ver < IXGBE_FW_API_VER_MAJOR ||
+		   hw->api_min_ver < IXGBE_FW_API_VER_MINOR - IXGBE_FW_API_VER_DIFF_ALLOWED) {
+		e_dev_info("The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
+		adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH;
+	}
+
+	return 0;
+}
+
 /**
  * ixgbe_check_fw_error - Check firmware for errors
  * @adapter: the adapter private structure
@@ -8374,12 +8403,14 @@ static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 fwsm;
+	int err;
 
 	/* read fwsm.ext_err_ind register and log errors */
 	fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
 
+	/* skip if E610's FW is reloading, warning in that case may be misleading */
 	if (fwsm & IXGBE_FWSM_EXT_ERR_IND_MASK ||
-	    !(fwsm & IXGBE_FWSM_FW_VAL_BIT))
+	    (!(fwsm & IXGBE_FWSM_FW_VAL_BIT) && !(hw->mac.type == ixgbe_mac_e610)))
 		e_dev_warn("Warning firmware error detected FWSM: 0x%08X\n",
 			   fwsm);
 
@@ -8387,10 +8418,53 @@ static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter)
 		e_dev_err("Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n");
 		return true;
 	}
+	if (!(adapter->flags2 & IXGBE_FLAG2_API_MISMATCH)) {
+		err = ixgbe_check_fw_api_mismatch(adapter);
+		if (err)
+			return true;
+	}
+
+	/* return here if FW rollback mode has been already detected */
+	if (adapter->flags2 & IXGBE_FLAG2_FW_ROLLBACK)
+		return false;
+
+	if (hw->mac.ops.fw_rollback_mode && hw->mac.ops.fw_rollback_mode(hw)) {
+		struct ixgbe_nvm_info *nvm_info = &adapter->hw.flash.nvm;
+		char ver_buff[64] = "";
+
+		if (hw->mac.ops.get_fw_ver && hw->mac.ops.get_fw_ver(hw))
+			goto no_version;
+
+		if (hw->mac.ops.get_nvm_ver &&
+		    hw->mac.ops.get_nvm_ver(hw, nvm_info))
+			goto no_version;
+
+		snprintf(ver_buff, sizeof(ver_buff),
+			 "Current version is NVM:%x.%x.%x, FW:%d.%d. ",
+			 nvm_info->major, nvm_info->minor, nvm_info->eetrack,
+			 hw->fw_maj_ver, hw->fw_maj_ver);
+no_version:
+		e_dev_warn("Firmware rollback mode detected. %sDevice may exhibit limited functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware rollback mode.",
+			   ver_buff);
+
+		adapter->flags2 |= IXGBE_FLAG2_FW_ROLLBACK;
+	}
 
 	return false;
 }
 
+static void ixgbe_recovery_service_task(struct work_struct *work)
+{
+	struct ixgbe_adapter *adapter = container_of(work,
+						     struct ixgbe_adapter,
+						     service_task);
+
+	ixgbe_handle_fw_event(adapter);
+	ixgbe_service_event_complete(adapter);
+
+	mod_timer(&adapter->service_timer, jiffies + msecs_to_jiffies(100));
+}
+
 /**
  * ixgbe_service_task - manages and runs subtasks
  * @work: pointer to work_struct containing our data
@@ -8410,8 +8484,13 @@ static void ixgbe_service_task(struct work_struct *work)
 		return;
 	}
 	if (ixgbe_check_fw_error(adapter)) {
-		if (!test_bit(__IXGBE_DOWN, &adapter->state))
+		if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
+			if (adapter->mii_bus) {
+				mdiobus_unregister(adapter->mii_bus);
+				adapter->mii_bus = NULL;
+			}
 			unregister_netdev(adapter->netdev);
+		}
 		ixgbe_service_event_complete(adapter);
 		return;
 	}
@@ -9001,7 +9080,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 	switch (vlan_get_protocol(skb)) {
 	case htons(ETH_P_FCOE):
 	case htons(ETH_P_FIP):
-		adapter = netdev_priv(dev);
+		adapter = ixgbe_from_netdev(dev);
 
 		if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
 			break;
@@ -9260,7 +9339,7 @@ static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb,
 				      struct net_device *netdev,
 				      struct ixgbe_ring *ring)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_ring *tx_ring;
 
 	/*
@@ -9292,7 +9371,7 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb,
  **/
 static int ixgbe_set_mac(struct net_device *netdev, void *p)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct sockaddr *addr = p;
 
@@ -9310,7 +9389,7 @@ static int ixgbe_set_mac(struct net_device *netdev, void *p)
 static int
 ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u16 value;
 	int rc;
@@ -9336,7 +9415,7 @@ ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr)
 static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad,
 			    u16 addr, u16 value)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (adapter->mii_bus) {
@@ -9356,7 +9435,7 @@ static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad,
 
 static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	switch (cmd) {
 	case SIOCSHWTSTAMP:
@@ -9382,7 +9461,7 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
 static int ixgbe_add_sanmac_netdev(struct net_device *dev)
 {
 	int err = 0;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (is_valid_ether_addr(hw->mac.san_addr)) {
@@ -9406,7 +9485,7 @@ static int ixgbe_add_sanmac_netdev(struct net_device *dev)
 static int ixgbe_del_sanmac_netdev(struct net_device *dev)
 {
 	int err = 0;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_mac_info *mac = &adapter->hw.mac;
 
 	if (is_valid_ether_addr(mac->san_addr)) {
@@ -9437,7 +9516,7 @@ static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats,
 static void ixgbe_get_stats64(struct net_device *netdev,
 			      struct rtnl_link_stats64 *stats)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int i;
 
 	rcu_read_lock();
@@ -9480,7 +9559,7 @@ static void ixgbe_get_stats64(struct net_device *netdev,
 static int ixgbe_ndo_get_vf_stats(struct net_device *netdev, int vf,
 				  struct ifla_vf_stats *vf_stats)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (vf < 0 || vf >= adapter->num_vfs)
 		return -EINVAL;
@@ -9597,7 +9676,7 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev,
 
 static void ixgbe_defrag_macvlan_pools(struct net_device *dev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct netdev_nested_priv priv = {
 		.data = (void *)adapter,
 	};
@@ -9618,7 +9697,7 @@ static void ixgbe_defrag_macvlan_pools(struct net_device *dev)
  */
 int ixgbe_setup_tc(struct net_device *dev, u8 tc)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	/* Hardware supports up to 8 traffic classes */
@@ -10176,7 +10255,7 @@ static LIST_HEAD(ixgbe_block_cb_list);
 static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			    void *type_data)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
@@ -10204,7 +10283,7 @@ void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter)
 #endif
 void ixgbe_do_reset(struct net_device *netdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (netif_running(netdev))
 		ixgbe_reinit_locked(adapter);
@@ -10215,7 +10294,7 @@ void ixgbe_do_reset(struct net_device *netdev)
 static netdev_features_t ixgbe_fix_features(struct net_device *netdev,
 					    netdev_features_t features)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* If Rx checksum is disabled, then RSC/LRO should also be disabled */
 	if (!(features & NETIF_F_RXCSUM))
@@ -10252,7 +10331,7 @@ static void ixgbe_reset_l2fw_offload(struct ixgbe_adapter *adapter)
 static int ixgbe_set_features(struct net_device *netdev,
 			      netdev_features_t features)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	netdev_features_t changed = netdev->features ^ features;
 	bool need_reset = false;
 
@@ -10328,7 +10407,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 {
 	/* guarantee we can provide a unique filter for the unicast address */
 	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
-		struct ixgbe_adapter *adapter = netdev_priv(dev);
+		struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 		u16 pool = VMDQ_P(0);
 
 		if (netdev_uc_count(dev) >= ixgbe_available_rars(adapter, pool))
@@ -10416,7 +10495,7 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
 				    struct nlmsghdr *nlh, u16 flags,
 				    struct netlink_ext_ack *extack)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct nlattr *attr, *br_spec;
 	int rem;
 
@@ -10444,7 +10523,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 				    struct net_device *dev,
 				    u32 filter_mask, int nlflags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
 		return 0;
@@ -10456,7 +10535,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 
 static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(pdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(pdev);
 	struct ixgbe_fwd_adapter *accel;
 	int tcs = adapter->hw_tcs ? : 1;
 	int pool, err;
@@ -10553,7 +10632,7 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 {
 	struct ixgbe_fwd_adapter *accel = priv;
-	struct ixgbe_adapter *adapter = netdev_priv(pdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(pdev);
 	unsigned int rxbase = accel->rx_base_queue;
 	unsigned int i;
 
@@ -10631,7 +10710,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev,
 static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 {
 	int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct bpf_prog *old_prog;
 	bool need_reset;
 	int num_queues;
@@ -10703,7 +10782,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 
 static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
@@ -10738,7 +10817,7 @@ void ixgbe_xdp_ring_update_tail_locked(struct ixgbe_ring *ring)
 static int ixgbe_xdp_xmit(struct net_device *dev, int n,
 			  struct xdp_frame **frames, u32 flags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ring *ring;
 	int nxmit = 0;
 	int i;
@@ -11146,7 +11225,7 @@ bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
  * format to display. The FW version is taken from the EEPROM/NVM.
  *
  */
-static void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter)
+void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_orom_info *orom = &adapter->hw.flash.orom;
 	struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm;
@@ -11197,6 +11276,66 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_recovery_probe - Handle FW recovery mode during probe
+ * @adapter: the adapter private structure
+ *
+ * Perform limited driver initialization when FW error is detected.
+ *
+ * Return: 0 on successful probe for E610, -EIO if recovery mode is detected
+ * for non-E610 adapter, error status code on any other case.
+ */
+static int ixgbe_recovery_probe(struct ixgbe_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct pci_dev *pdev = adapter->pdev;
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool disable_dev;
+	int err = -EIO;
+
+	if (hw->mac.type != ixgbe_mac_e610)
+		goto clean_up_probe;
+
+	ixgbe_get_hw_control(adapter);
+	mutex_init(&hw->aci.lock);
+	err = ixgbe_get_flash_data(&adapter->hw);
+	if (err)
+		goto shutdown_aci;
+
+	timer_setup(&adapter->service_timer, ixgbe_service_timer, 0);
+	INIT_WORK(&adapter->service_task, ixgbe_recovery_service_task);
+	set_bit(__IXGBE_SERVICE_INITED, &adapter->state);
+	clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
+
+	if (hw->mac.ops.get_bus_info)
+		hw->mac.ops.get_bus_info(hw);
+
+	pci_set_drvdata(pdev, adapter);
+	/* We are creating devlink interface so NIC can be managed,
+	 * e.g. new NVM image loaded
+	 */
+	devl_lock(adapter->devlink);
+	ixgbe_devlink_register_port(adapter);
+	SET_NETDEV_DEVLINK_PORT(adapter->netdev,
+				&adapter->devlink_port);
+	ixgbe_devlink_init_regions(adapter);
+	devl_register(adapter->devlink);
+	devl_unlock(adapter->devlink);
+
+	return 0;
+shutdown_aci:
+	mutex_destroy(&adapter->hw.aci.lock);
+	ixgbe_release_hw_control(adapter);
+	devlink_free(adapter->devlink);
+clean_up_probe:
+	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
+	free_netdev(netdev);
+	pci_release_mem_regions(pdev);
+	if (disable_dev)
+		pci_disable_device(pdev);
+	return err;
+}
+
+/**
  * ixgbe_probe - Device Initialization Routine
  * @pdev: PCI device information struct
  * @ent: entry in ixgbe_pci_tbl
@@ -11210,6 +11349,7 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter)
 static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *netdev;
+	struct ixgbe_netdevice_priv *netdev_priv_wrapper;
 	struct ixgbe_adapter *adapter = NULL;
 	struct ixgbe_hw *hw;
 	const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data];
@@ -11263,7 +11403,13 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		indices = IXGBE_MAX_RSS_INDICES_X550;
 	}
 
-	netdev = alloc_etherdev_mq(sizeof(struct ixgbe_adapter), indices);
+	adapter = ixgbe_allocate_devlink(&pdev->dev);
+	if (IS_ERR(adapter)) {
+		err = PTR_ERR(adapter);
+		goto err_devlink;
+	}
+
+	netdev = alloc_etherdev_mq(sizeof(*netdev_priv_wrapper), indices);
 	if (!netdev) {
 		err = -ENOMEM;
 		goto err_alloc_etherdev;
@@ -11271,7 +11417,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 
-	adapter = netdev_priv(netdev);
+	netdev_priv_wrapper = netdev_priv(netdev);
+	netdev_priv_wrapper->adapter = adapter;
 
 	adapter->netdev = netdev;
 	adapter->pdev = pdev;
@@ -11287,11 +11434,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_ioremap;
 	}
 
-	netdev->netdev_ops = &ixgbe_netdev_ops;
-	ixgbe_set_ethtool_ops(netdev);
-	netdev->watchdog_timeo = 5 * HZ;
-	strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name));
-
 	/* Setup hw api */
 	hw->mac.ops   = *ii->mac_ops;
 	hw->mac.type  = ii->mac;
@@ -11321,15 +11463,31 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw->phy.mdio.mdio_read = ixgbe_mdio_read;
 	hw->phy.mdio.mdio_write = ixgbe_mdio_write;
 
+	netdev->netdev_ops = &ixgbe_netdev_ops;
+	ixgbe_set_ethtool_ops(netdev);
+	netdev->watchdog_timeo = 5 * HZ;
+	strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name));
+
 	/* setup the private structure */
 	err = ixgbe_sw_init(adapter, ii);
 	if (err)
 		goto err_sw_init;
 
+	/* Make sure the SWFW semaphore is in a valid state */
+	if (hw->mac.ops.init_swfw_sync)
+		hw->mac.ops.init_swfw_sync(hw);
+
+	if (ixgbe_check_fw_error(adapter))
+		return ixgbe_recovery_probe(adapter);
+
 	if (adapter->hw.mac.type == ixgbe_mac_e610) {
 		err = ixgbe_get_caps(&adapter->hw);
 		if (err)
 			dev_err(&pdev->dev, "ixgbe_get_caps failed %d\n", err);
+
+		err = ixgbe_get_flash_data(&adapter->hw);
+		if (err)
+			goto err_sw_init;
 	}
 
 	if (adapter->hw.mac.type == ixgbe_mac_82599EB)
@@ -11348,10 +11506,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		break;
 	}
 
-	/* Make sure the SWFW semaphore is in a valid state */
-	if (hw->mac.ops.init_swfw_sync)
-		hw->mac.ops.init_swfw_sync(hw);
-
 	/* Make it possible the adapter to be woken up via WOL */
 	switch (adapter->hw.mac.type) {
 	case ixgbe_mac_82599EB:
@@ -11504,11 +11658,6 @@ skip_sriov:
 	if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
 		netdev->features |= NETIF_F_LRO;
 
-	if (ixgbe_check_fw_error(adapter)) {
-		err = -EIO;
-		goto err_sw_init;
-	}
-
 	/* make sure the EEPROM is good */
 	if (hw->eeprom.ops.validate_checksum(hw, NULL) < 0) {
 		e_dev_err("The EEPROM Checksum Is Not Valid\n");
@@ -11591,7 +11740,7 @@ skip_sriov:
 	if (expected_gts > 0)
 		ixgbe_check_minimum_link(adapter, expected_gts);
 
-	err = ixgbe_read_pba_string_generic(hw, part_str, sizeof(part_str));
+	err = hw->eeprom.ops.read_pba_string(hw, part_str, sizeof(part_str));
 	if (err)
 		strscpy(part_str, "Unknown", sizeof(part_str));
 	if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present)
@@ -11617,6 +11766,11 @@ skip_sriov:
 	}
 	strcpy(netdev->name, "eth%d");
 	pci_set_drvdata(pdev, adapter);
+
+	devl_lock(adapter->devlink);
+	ixgbe_devlink_register_port(adapter);
+	SET_NETDEV_DEVLINK_PORT(adapter->netdev, &adapter->devlink_port);
+
 	err = register_netdev(netdev);
 	if (err)
 		goto err_register;
@@ -11671,11 +11825,16 @@ skip_sriov:
 	if (err)
 		goto err_netdev;
 
+	ixgbe_devlink_init_regions(adapter);
+	devl_register(adapter->devlink);
+	devl_unlock(adapter->devlink);
 	return 0;
 
 err_netdev:
 	unregister_netdev(netdev);
 err_register:
+	devl_port_unregister(&adapter->devlink_port);
+	devl_unlock(adapter->devlink);
 	ixgbe_release_hw_control(adapter);
 	ixgbe_clear_interrupt_scheme(adapter);
 	if (hw->mac.type == ixgbe_mac_e610)
@@ -11692,7 +11851,9 @@ err_ioremap:
 	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
 	free_netdev(netdev);
 err_alloc_etherdev:
+	devlink_free(adapter->devlink);
 	pci_release_mem_regions(pdev);
+err_devlink:
 err_pci_reg:
 err_dma:
 	if (!adapter || disable_dev)
@@ -11721,6 +11882,9 @@ static void ixgbe_remove(struct pci_dev *pdev)
 		return;
 
 	netdev  = adapter->netdev;
+	devl_lock(adapter->devlink);
+	devl_unregister(adapter->devlink);
+	ixgbe_devlink_destroy_regions(adapter);
 	ixgbe_dbg_adapter_exit(adapter);
 
 	set_bit(__IXGBE_REMOVING, &adapter->state);
@@ -11756,6 +11920,10 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	if (netdev->reg_state == NETREG_REGISTERED)
 		unregister_netdev(netdev);
 
+	devl_port_unregister(&adapter->devlink_port);
+	devl_unlock(adapter->devlink);
+	devlink_free(adapter->devlink);
+
 	ixgbe_stop_ipsec_offload(adapter);
 	ixgbe_clear_interrupt_scheme(adapter);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 0a03a8bb5f88..2d54828bdfbb 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -167,7 +167,7 @@ int ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
 					 u16 reg, u16 val, bool lock)
 {
 	u32 swfw_mask = hw->phy.phy_semaphore_mask;
-	int max_retry = 1;
+	int max_retry = 3;
 	int retry = 0;
 	u8 reg_high;
 	u8 csum;
@@ -2285,7 +2285,7 @@ static int ixgbe_write_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset,
 					    u8 dev_addr, u8 data, bool lock)
 {
 	u32 swfw_mask = hw->phy.phy_semaphore_mask;
-	u32 max_retry = 1;
+	u32 max_retry = 3;
 	u32 retry = 0;
 	int status;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index ccdce80edd14..0dbbd2befd4d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -1418,7 +1418,7 @@ void ixgbe_set_all_vfs(struct ixgbe_adapter *adapter)
 
 int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int retval;
 
 	if (vf >= adapter->num_vfs)
@@ -1526,7 +1526,7 @@ int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
 			  u8 qos, __be16 vlan_proto)
 {
 	int err = 0;
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7))
 		return -EINVAL;
@@ -1644,7 +1644,7 @@ void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter)
 int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate,
 			int max_tx_rate)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int link_speed;
 
 	/* verify VF is active */
@@ -1679,7 +1679,7 @@ int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate,
 
 int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if (vf >= adapter->num_vfs)
@@ -1757,7 +1757,7 @@ void ixgbe_set_vf_link_state(struct ixgbe_adapter *adapter, int vf, int state)
  **/
 int ixgbe_ndo_set_vf_link_state(struct net_device *netdev, int vf, int state)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	int ret = 0;
 
 	if (vf < 0 || vf >= adapter->num_vfs) {
@@ -1794,7 +1794,7 @@ int ixgbe_ndo_set_vf_link_state(struct net_device *netdev, int vf, int state)
 int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf,
 				  bool setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	/* This operation is currently supported only for 82599 and x540
 	 * devices.
@@ -1813,7 +1813,7 @@ int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf,
 
 int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
 	if (vf >= adapter->num_vfs)
 		return -EINVAL;
@@ -1836,7 +1836,7 @@ int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting)
 int ixgbe_ndo_get_vf_config(struct net_device *netdev,
 			    int vf, struct ifla_vf_info *ivi)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 	if (vf >= adapter->num_vfs)
 		return -EINVAL;
 	ivi->vf = vf;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 5fdf32d79d82..892fa6c1f879 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -3446,6 +3446,8 @@ struct ixgbe_eeprom_operations {
 	int (*validate_checksum)(struct ixgbe_hw *, u16 *);
 	int (*update_checksum)(struct ixgbe_hw *);
 	int (*calc_checksum)(struct ixgbe_hw *);
+	int (*read_pba_string)(struct ixgbe_hw *hw, u8 *pba_num,
+			       u32 pba_num_size);
 };
 
 struct ixgbe_mac_operations {
@@ -3454,6 +3456,7 @@ struct ixgbe_mac_operations {
 	int (*start_hw)(struct ixgbe_hw *);
 	int (*clear_hw_cntrs)(struct ixgbe_hw *);
 	enum ixgbe_media_type (*get_media_type)(struct ixgbe_hw *);
+	int (*get_fw_ver)(struct ixgbe_hw *hw);
 	int (*get_mac_addr)(struct ixgbe_hw *, u8 *);
 	int (*get_san_mac_addr)(struct ixgbe_hw *, u8 *);
 	int (*get_device_caps)(struct ixgbe_hw *, u16 *);
@@ -3522,6 +3525,8 @@ struct ixgbe_mac_operations {
 	int (*get_thermal_sensor_data)(struct ixgbe_hw *);
 	int (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw);
 	bool (*fw_recovery_mode)(struct ixgbe_hw *hw);
+	bool (*fw_rollback_mode)(struct ixgbe_hw *hw);
+	int (*get_nvm_ver)(struct ixgbe_hw *hw, struct ixgbe_nvm_info *nvm);
 	void (*disable_rx)(struct ixgbe_hw *hw);
 	void (*enable_rx)(struct ixgbe_hw *hw);
 	void (*set_source_address_pruning)(struct ixgbe_hw *, bool,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
index 617e07878e4f..09df67f03cf4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
@@ -10,11 +10,75 @@
 #define IXGBE_MAX_VSI			768
 
 /* Checksum and Shadow RAM pointers */
-#define E610_SR_SW_CHECKSUM_WORD		0x3F
+#define IXGBE_E610_SR_NVM_CTRL_WORD		0x00
+#define IXGBE_E610_SR_PBA_BLOCK_PTR		0x16
+#define IXGBE_E610_SR_PBA_BLOCK_MASK		GENMASK(15, 8)
+#define IXGBE_E610_SR_NVM_DEV_STARTER_VER	0x18
+#define IXGBE_E610_SR_NVM_EETRACK_LO		0x2D
+#define IXGBE_E610_SR_NVM_EETRACK_HI		0x2E
+#define IXGBE_E610_NVM_VER_LO_MASK		GENMASK(7, 0)
+#define IXGBE_E610_NVM_VER_HI_MASK		GENMASK(15, 12)
+#define IXGBE_E610_SR_SW_CHECKSUM_WORD		0x3F
+#define IXGBE_E610_SR_PFA_PTR			0x40
+#define IXGBE_E610_SR_1ST_NVM_BANK_PTR		0x42
+#define IXGBE_E610_SR_NVM_BANK_SIZE		0x43
+#define IXGBE_E610_SR_1ST_OROM_BANK_PTR		0x44
+#define IXGBE_E610_SR_OROM_BANK_SIZE		0x45
+#define IXGBE_E610_SR_NETLIST_BANK_PTR		0x46
+#define IXGBE_E610_SR_NETLIST_BANK_SIZE		0x47
+
+/* The OROM version topology */
+#define IXGBE_OROM_VER_PATCH_MASK		GENMASK_ULL(7, 0)
+#define IXGBE_OROM_VER_BUILD_MASK		GENMASK_ULL(23, 8)
+#define IXGBE_OROM_VER_MASK			GENMASK_ULL(31, 24)
+
+/* CSS Header words */
+#define IXGBE_NVM_CSS_HDR_LEN_L			0x02
+#define IXGBE_NVM_CSS_HDR_LEN_H			0x03
+#define IXGBE_NVM_CSS_SREV_L			0x14
+#define IXGBE_NVM_CSS_SREV_H			0x15
+
+#define IXGBE_HDR_LEN_ROUNDUP			32
+
+/* Length of Authentication header section in words */
+#define IXGBE_NVM_AUTH_HEADER_LEN		0x08
 
 /* Shadow RAM related */
 #define IXGBE_SR_WORDS_IN_1KB	512
 
+/* The Netlist ID Block is located after all of the Link Topology nodes. */
+#define IXGBE_NETLIST_ID_BLK_SIZE		0x30
+#define IXGBE_NETLIST_ID_BLK_OFFSET(n)		IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0004 + 2 * (n))
+
+/* netlist ID block field offsets (word offsets) */
+#define IXGBE_NETLIST_ID_BLK_MAJOR_VER_LOW	0x02
+#define IXGBE_NETLIST_ID_BLK_MAJOR_VER_HIGH	0x03
+#define IXGBE_NETLIST_ID_BLK_MINOR_VER_LOW	0x04
+#define IXGBE_NETLIST_ID_BLK_MINOR_VER_HIGH	0x05
+#define IXGBE_NETLIST_ID_BLK_TYPE_LOW		0x06
+#define IXGBE_NETLIST_ID_BLK_TYPE_HIGH		0x07
+#define IXGBE_NETLIST_ID_BLK_REV_LOW		0x08
+#define IXGBE_NETLIST_ID_BLK_REV_HIGH		0x09
+#define IXGBE_NETLIST_ID_BLK_SHA_HASH_WORD(n)	(0x0A + (n))
+#define IXGBE_NETLIST_ID_BLK_CUST_VER		0x2F
+
+/* The Link Topology Netlist section is stored as a series of words. It is
+ * stored in the NVM as a TLV, with the first two words containing the type
+ * and length.
+ */
+#define IXGBE_NETLIST_LINK_TOPO_MOD_ID		0x011B
+#define IXGBE_NETLIST_TYPE_OFFSET		0x0000
+#define IXGBE_NETLIST_LEN_OFFSET		0x0001
+
+/* The Link Topology section follows the TLV header. When reading the netlist
+ * using ixgbe_read_netlist_module, we need to account for the 2-word TLV
+ * header.
+ */
+#define IXGBE_NETLIST_LINK_TOPO_OFFSET(n)	((n) + 2)
+#define IXGBE_LINK_TOPO_MODULE_LEN	IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0000)
+#define IXGBE_LINK_TOPO_NODE_COUNT	IXGBE_NETLIST_LINK_TOPO_OFFSET(0x0001)
+#define IXGBE_LINK_TOPO_NODE_COUNT_M		GENMASK_ULL(9, 0)
+
 /* Firmware Status Register (GL_FWSTS) */
 #define GL_FWSTS		0x00083048 /* Reset Source: POR */
 #define GL_FWSTS_EP_PF0		BIT(24)
@@ -24,11 +88,23 @@
 #define GLNVM_GENS		0x000B6100 /* Reset Source: POR */
 #define GLNVM_GENS_SR_SIZE_M	GENMASK(7, 5)
 
+#define IXGBE_GL_MNG_FWSM		0x000B6134 /* Reset Source: POR */
+#define IXGBE_GL_MNG_FWSM_RECOVERY_M	BIT(1)
+#define IXGBE_GL_MNG_FWSM_ROLLBACK_M    BIT(2)
+
 /* Flash Access Register */
 #define IXGBE_GLNVM_FLA			0x000B6108 /* Reset Source: POR */
 #define IXGBE_GLNVM_FLA_LOCKED_S	6
 #define IXGBE_GLNVM_FLA_LOCKED_M	BIT(6)
 
+/* Auxiliary field, mask and shift definition for Shadow RAM and NVM Flash */
+#define IXGBE_SR_CTRL_WORD_1_M		GENMASK(7, 6)
+#define IXGBE_SR_CTRL_WORD_VALID	BIT(0)
+#define IXGBE_SR_CTRL_WORD_OROM_BANK	BIT(3)
+#define IXGBE_SR_CTRL_WORD_NETLIST_BANK	BIT(4)
+#define IXGBE_SR_CTRL_WORD_NVM_BANK	BIT(5)
+#define IXGBE_SR_NVM_PTR_4KB_UNITS	BIT(15)
+
 /* Admin Command Interface (ACI) registers */
 #define IXGBE_PF_HIDA(_i)			(0x00085000 + ((_i) * 4))
 #define IXGBE_PF_HIDA_2(_i)			(0x00085020 + ((_i) * 4))
@@ -40,6 +116,10 @@
 #define IXGBE_PF_HICR_SV			BIT(2)
 #define IXGBE_PF_HICR_EV			BIT(3)
 
+#define IXGBE_FW_API_VER_MAJOR		0x01
+#define IXGBE_FW_API_VER_MINOR		0x07
+#define IXGBE_FW_API_VER_DIFF_ALLOWED	0x02
+
 #define IXGBE_ACI_DESC_SIZE		32
 #define IXGBE_ACI_DESC_SIZE_IN_DWORDS	(IXGBE_ACI_DESC_SIZE / BYTES_PER_DWORD)
 
@@ -143,6 +223,7 @@ enum ixgbe_aci_opc {
 	ixgbe_aci_opc_write_mdio			= 0x06E5,
 	ixgbe_aci_opc_set_gpio_by_func			= 0x06E6,
 	ixgbe_aci_opc_get_gpio_by_func			= 0x06E7,
+	ixgbe_aci_opc_set_port_id_led			= 0x06E9,
 	ixgbe_aci_opc_set_gpio				= 0x06EC,
 	ixgbe_aci_opc_get_gpio				= 0x06ED,
 	ixgbe_aci_opc_sff_eeprom			= 0x06EE,
@@ -728,6 +809,18 @@ struct ixgbe_aci_cmd_get_link_topo_pin {
 	u8 rsvd[7];
 };
 
+/* Set Port Identification LED (direct, 0x06E9) */
+struct ixgbe_aci_cmd_set_port_id_led {
+	u8 lport_num;
+	u8 lport_num_valid;
+	u8 ident_mode;
+	u8 rsvd[13];
+};
+
+#define IXGBE_ACI_PORT_ID_PORT_NUM_VALID	BIT(0)
+#define IXGBE_ACI_PORT_IDENT_LED_ORIG		0
+#define IXGBE_ACI_PORT_IDENT_LED_BLINK		BIT(0)
+
 /* Read/Write SFF EEPROM command (indirect 0x06EE) */
 struct ixgbe_aci_cmd_sff_eeprom {
 	u8 lport_num;
@@ -761,6 +854,8 @@ struct ixgbe_aci_cmd_nvm {
 #define IXGBE_ACI_NVM_MAX_OFFSET	0xFFFFFF
 	__le16 offset_low;
 	u8 offset_high; /* For Write Activate offset_high is used as flags2 */
+#define IXGBE_ACI_NVM_OFFSET_HI_A_MASK  GENMASK(15, 8)
+#define IXGBE_ACI_NVM_OFFSET_HI_U_MASK	GENMASK(23, 16)
 	u8 cmd_flags;
 #define IXGBE_ACI_NVM_LAST_CMD		BIT(0)
 #define IXGBE_ACI_NVM_PCIR_REQ		BIT(0) /* Used by NVM Write reply */
@@ -776,6 +871,9 @@ struct ixgbe_aci_cmd_nvm {
 #define IXGBE_ACI_NVM_PERST_FLAG	1
 #define IXGBE_ACI_NVM_EMPR_FLAG		2
 #define IXGBE_ACI_NVM_EMPR_ENA		BIT(0) /* Write Activate reply only */
+#define IXGBE_ACI_NVM_NO_PRESERVATION	0x0
+#define IXGBE_ACI_NVM_PRESERVE_SELECTED	0x6
+
 	/* For Write Activate, several flags are sent as part of a separate
 	 * flags2 field using a separate byte. For simplicity of the software
 	 * interface, we pass the flags as a 16 bit value so these flags are
@@ -805,6 +903,63 @@ struct ixgbe_aci_cmd_nvm_checksum {
 	u8 rsvd2[12];
 };
 
+/* Used for NVM Set Package Data command - 0x070A */
+struct ixgbe_aci_cmd_nvm_pkg_data {
+	u8 reserved[3];
+	u8 cmd_flags;
+#define IXGBE_ACI_NVM_PKG_DELETE	BIT(0) /* used for command call */
+
+	u32 reserved1;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Used for Pass Component Table command - 0x070B */
+struct ixgbe_aci_cmd_nvm_pass_comp_tbl {
+	u8 component_response; /* Response only */
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED		0x0
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE	0x1
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_NOT_BE_UPDATED	0x2
+#define IXGBE_ACI_NVM_PASS_COMP_PARTIAL_CHECK		0x3
+	u8 component_response_code; /* Response only */
+#define IXGBE_ACI_NVM_PASS_COMP_CAN_BE_UPDATED_CODE	0x0
+#define IXGBE_ACI_NVM_PASS_COMP_STAMP_IDENTICAL_CODE	0x1
+#define IXGBE_ACI_NVM_PASS_COMP_STAMP_LOWER		0x2
+#define IXGBE_ACI_NVM_PASS_COMP_INVALID_STAMP_CODE	0x3
+#define IXGBE_ACI_NVM_PASS_COMP_CONFLICT_CODE		0x4
+#define IXGBE_ACI_NVM_PASS_COMP_PRE_REQ_NOT_MET_CODE	0x5
+#define IXGBE_ACI_NVM_PASS_COMP_NOT_SUPPORTED_CODE	0x6
+#define IXGBE_ACI_NVM_PASS_COMP_CANNOT_DOWNGRADE_CODE	0x7
+#define IXGBE_ACI_NVM_PASS_COMP_INCOMPLETE_IMAGE_CODE	0x8
+#define IXGBE_ACI_NVM_PASS_COMP_VER_STR_IDENTICAL_CODE	0xA
+#define IXGBE_ACI_NVM_PASS_COMP_VER_STR_LOWER_CODE	0xB
+	u8 reserved;
+	u8 transfer_flag;
+	__le32 reserved1;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+struct ixgbe_aci_cmd_nvm_comp_tbl {
+	__le16 comp_class;
+#define NVM_COMP_CLASS_ALL_FW		0x000A
+
+	__le16 comp_id;
+#define NVM_COMP_ID_OROM		0x5
+#define NVM_COMP_ID_NVM			0x6
+#define NVM_COMP_ID_NETLIST		0x8
+
+	u8 comp_class_idx;
+#define FWU_COMP_CLASS_IDX_NOT_USE	0x0
+
+	__le32 comp_cmp_stamp;
+	u8 cvs_type;
+#define NVM_CVS_TYPE_ASCII		0x1
+
+	u8 cvs_len;
+	u8 cvs[]; /* Component Version String */
+} __packed;
+
 /**
  * struct ixgbe_aci_desc - Admin Command (AC) descriptor
  * @flags: IXGBE_ACI_FLAG_* flags
@@ -843,11 +998,14 @@ struct ixgbe_aci_desc {
 		struct ixgbe_aci_cmd_restart_an restart_an;
 		struct ixgbe_aci_cmd_get_link_status get_link_status;
 		struct ixgbe_aci_cmd_set_event_mask set_event_mask;
+		struct ixgbe_aci_cmd_set_port_id_led set_port_id_led;
 		struct ixgbe_aci_cmd_get_link_topo get_link_topo;
 		struct ixgbe_aci_cmd_get_link_topo_pin get_link_topo_pin;
 		struct ixgbe_aci_cmd_sff_eeprom read_write_sff_param;
 		struct ixgbe_aci_cmd_nvm nvm;
 		struct ixgbe_aci_cmd_nvm_checksum nvm_checksum;
+		struct ixgbe_aci_cmd_nvm_pkg_data pkg_data;
+		struct ixgbe_aci_cmd_nvm_pass_comp_tbl pass_comp_tbl;
 	} params;
 };
 
@@ -984,6 +1142,16 @@ struct ixgbe_hw_caps {
 #define IXGBE_EXT_TOPO_DEV_IMG_PROG_EN	BIT(1)
 } __packed;
 
+#define IXGBE_OROM_CIV_SIGNATURE	"$CIV"
+
+struct ixgbe_orom_civd_info {
+	u8 signature[4];	/* Must match ASCII '$CIV' characters */
+	u8 checksum;		/* Simple modulo 256 sum of all structure bytes must equal 0 */
+	__le32 combo_ver;	/* Combo Image Version number */
+	u8 combo_name_len;	/* Length of the unicode combo image version string, max of 32 */
+	__le16 combo_name[32];	/* Unicode string representing the Combo Image version */
+};
+
 /* Function specific capabilities */
 struct ixgbe_hw_func_caps {
 	u32 num_allocd_vfs;		/* Number of allocated VFs */
@@ -1015,6 +1183,11 @@ struct ixgbe_aci_info {
 	enum ixgbe_aci_err last_status;	/* last status of sent admin command */
 };
 
+enum ixgbe_bank_select {
+	IXGBE_ACTIVE_FLASH_BANK,
+	IXGBE_INACTIVE_FLASH_BANK,
+};
+
 /* Option ROM version information */
 struct ixgbe_orom_info {
 	u8 major;			/* Major version of OROM */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
index 1fc821fb351a..f1ab95aa8c83 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
@@ -894,6 +894,7 @@ static const struct ixgbe_eeprom_operations eeprom_ops_X540 = {
 	.calc_checksum		= &ixgbe_calc_eeprom_checksum_X540,
 	.validate_checksum      = &ixgbe_validate_eeprom_checksum_X540,
 	.update_checksum        = &ixgbe_update_eeprom_checksum_X540,
+	.read_pba_string        = &ixgbe_read_pba_string_generic,
 };
 
 static const struct ixgbe_phy_operations phy_ops_X540 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 277ceaf8a793..1d2acdb64f45 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -3959,6 +3959,7 @@ static const struct ixgbe_mac_operations mac_ops_x550em_a_fw = {
 	.validate_checksum	= &ixgbe_validate_eeprom_checksum_X550, \
 	.update_checksum	= &ixgbe_update_eeprom_checksum_X550, \
 	.calc_checksum		= &ixgbe_calc_eeprom_checksum_X550, \
+	.read_pba_string        = &ixgbe_read_pba_string_generic, \
 
 static const struct ixgbe_eeprom_operations eeprom_ops_X550 = {
 	X550_COMMON_EEP
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 3e3b471e53f0..ac58964b2f08 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -508,7 +508,7 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
 
 int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev);
 	struct ixgbe_ring *ring;
 
 	if (test_bit(__IXGBE_DOWN, &adapter->state))
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index 837295fecd17..50f7c59e8a04 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -34,7 +34,6 @@ config MV643XX_ETH
 config MVMDIO
 	tristate "Marvell MDIO interface support"
 	depends on HAS_IOMEM
-	select MDIO_DEVRES
 	select PHYLIB
 	help
 	  This driver supports the MDIO interface found in the network
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 416a926a8281..a7872d14a49d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5173,38 +5173,40 @@ mvpp2_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	stats->tx_dropped	= dev->stats.tx_dropped;
 }
 
-static int mvpp2_set_ts_config(struct mvpp2_port *port, struct ifreq *ifr)
+static int mvpp2_hwtstamp_set(struct net_device *dev,
+			      struct kernel_hwtstamp_config *config,
+			      struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
+	struct mvpp2_port *port = netdev_priv(dev);
 	void __iomem *ptp;
 	u32 gcr, int_mask;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	if (!port->hwtstamp)
+		return -EOPNOTSUPP;
 
-	if (config.tx_type != HWTSTAMP_TX_OFF &&
-	    config.tx_type != HWTSTAMP_TX_ON)
+	if (config->tx_type != HWTSTAMP_TX_OFF &&
+	    config->tx_type != HWTSTAMP_TX_ON)
 		return -ERANGE;
 
 	ptp = port->priv->iface_base + MVPP22_PTP_BASE(port->gop_id);
 
 	int_mask = gcr = 0;
-	if (config.tx_type != HWTSTAMP_TX_OFF) {
+	if (config->tx_type != HWTSTAMP_TX_OFF) {
 		gcr |= MVPP22_PTP_GCR_TSU_ENABLE | MVPP22_PTP_GCR_TX_RESET;
 		int_mask |= MVPP22_PTP_INT_MASK_QUEUE1 |
 			    MVPP22_PTP_INT_MASK_QUEUE0;
 	}
 
 	/* It seems we must also release the TX reset when enabling the TSU */
-	if (config.rx_filter != HWTSTAMP_FILTER_NONE)
+	if (config->rx_filter != HWTSTAMP_FILTER_NONE)
 		gcr |= MVPP22_PTP_GCR_TSU_ENABLE | MVPP22_PTP_GCR_RX_RESET |
 		       MVPP22_PTP_GCR_TX_RESET;
 
 	if (gcr & MVPP22_PTP_GCR_TSU_ENABLE)
 		mvpp22_tai_start(port->priv->tai);
 
-	if (config.rx_filter != HWTSTAMP_FILTER_NONE) {
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
+	if (config->rx_filter != HWTSTAMP_FILTER_NONE) {
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
 		mvpp2_modify(ptp + MVPP22_PTP_GCR,
 			     MVPP22_PTP_GCR_RX_RESET |
 			     MVPP22_PTP_GCR_TX_RESET |
@@ -5225,26 +5227,22 @@ static int mvpp2_set_ts_config(struct mvpp2_port *port, struct ifreq *ifr)
 	if (!(gcr & MVPP22_PTP_GCR_TSU_ENABLE))
 		mvpp22_tai_stop(port->priv->tai);
 
-	port->tx_hwtstamp_type = config.tx_type;
-
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	port->tx_hwtstamp_type = config->tx_type;
 
 	return 0;
 }
 
-static int mvpp2_get_ts_config(struct mvpp2_port *port, struct ifreq *ifr)
+static int mvpp2_hwtstamp_get(struct net_device *dev,
+			      struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config config;
-
-	memset(&config, 0, sizeof(config));
+	struct mvpp2_port *port = netdev_priv(dev);
 
-	config.tx_type = port->tx_hwtstamp_type;
-	config.rx_filter = port->rx_hwtstamp ?
-		HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+	if (!port->hwtstamp)
+		return -EOPNOTSUPP;
 
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	config->tx_type = port->tx_hwtstamp_type;
+	config->rx_filter = port->rx_hwtstamp ? HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
 
 	return 0;
 }
@@ -5274,18 +5272,6 @@ static int mvpp2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
 
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		if (port->hwtstamp)
-			return mvpp2_set_ts_config(port, ifr);
-		break;
-
-	case SIOCGHWTSTAMP:
-		if (port->hwtstamp)
-			return mvpp2_get_ts_config(port, ifr);
-		break;
-	}
-
 	if (!port->phylink)
 		return -ENOTSUPP;
 
@@ -5799,6 +5785,8 @@ static const struct net_device_ops mvpp2_netdev_ops = {
 	.ndo_set_features	= mvpp2_set_features,
 	.ndo_bpf		= mvpp2_xdp,
 	.ndo_xdp_xmit		= mvpp2_xdp_xmit,
+	.ndo_hwtstamp_get	= mvpp2_hwtstamp_get,
+	.ndo_hwtstamp_set	= mvpp2_hwtstamp_set,
 };
 
 static const struct ethtool_ops mvpp2_eth_tool_ops = {
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index 0a679e95196f..24499bb36c00 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -1223,7 +1223,7 @@ static void octep_hb_timeout_task(struct work_struct *work)
 		miss_cnt);
 	rtnl_lock();
 	if (netif_running(oct->netdev))
-		octep_stop(oct->netdev);
+		dev_close(oct->netdev);
 	rtnl_unlock();
 }
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
index 18c922dd5fc6..420c3f4cf741 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
@@ -18,8 +18,6 @@
 #include "octep_vf_config.h"
 #include "octep_vf_main.h"
 
-struct workqueue_struct *octep_vf_wq;
-
 /* Supported Devices */
 static const struct pci_device_id octep_vf_pci_id_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CN93_VF)},
@@ -835,7 +833,9 @@ static void octep_vf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	struct octep_vf_device *oct = netdev_priv(netdev);
 
 	netdev_hold(netdev, NULL, GFP_ATOMIC);
-	schedule_work(&oct->tx_timeout_task);
+	if (!schedule_work(&oct->tx_timeout_task))
+		netdev_put(netdev, NULL);
+
 }
 
 static int octep_vf_set_mac(struct net_device *netdev, void *p)
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
index 1a352f41f823..b9f13506f462 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
@@ -320,8 +320,6 @@ static inline u16 OCTEP_VF_MINOR_REV(struct octep_vf_device *oct)
 #define octep_vf_read_csr64(octep_vf_dev, reg_off)         \
 	readq((octep_vf_dev)->mmio.hw_addr + (reg_off))
 
-extern struct workqueue_struct *octep_vf_wq;
-
 int octep_vf_device_setup(struct octep_vf_device *oct);
 int octep_vf_setup_iqs(struct octep_vf_device *oct);
 void octep_vf_free_iqs(struct octep_vf_device *oct);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 0b27a695008b..971993586fb4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -717,6 +717,11 @@ int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat)
 
 	if (!is_lmac_valid(cgx, lmac_id))
 		return -ENODEV;
+
+	/* pass lmac as 0 for CGX_CMR_RX_STAT9-12 */
+	if (idx >= CGX_RX_STAT_GLOBAL_INDEX)
+		lmac_id = 0;
+
 	*rx_stat =  cgx_read(cgx, lmac_id, CGXX_CMRX_RX_STAT0 + (idx * 8));
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
index 1e5aa5397504..7d21905deed8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -188,14 +188,13 @@ int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid)
 {
 	unsigned long timeout = jiffies + msecs_to_jiffies(MBOX_RSP_TIMEOUT);
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
-	struct device *sender = &mbox->pdev->dev;
 
 	while (!time_after(jiffies, timeout)) {
 		if (mdev->num_msgs == mdev->msgs_acked)
 			return 0;
 		usleep_range(800, 1000);
 	}
-	dev_dbg(sender, "timed out while waiting for rsp\n");
+	trace_otx2_msg_wait_rsp(mbox->pdev);
 	return -EIO;
 }
 EXPORT_SYMBOL(otx2_mbox_wait_for_rsp);
@@ -219,6 +218,7 @@ static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data)
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
 	struct mbox_hdr *tx_hdr, *rx_hdr;
 	void *hw_mbase = mdev->hwbase;
+	struct mbox_msghdr *msg;
 	u64 intr_val;
 
 	tx_hdr = hw_mbase + mbox->tx_start;
@@ -251,7 +251,10 @@ static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data)
 	tx_hdr->num_msgs = mdev->num_msgs;
 	rx_hdr->num_msgs = 0;
 
-	trace_otx2_msg_send(mbox->pdev, tx_hdr->num_msgs, tx_hdr->msg_size);
+	msg = (struct mbox_msghdr *)(hw_mbase + mbox->tx_start + msgs_offset);
+
+	trace_otx2_msg_send(mbox->pdev, tx_hdr->num_msgs, tx_hdr->msg_size,
+			    msg->id, msg->pcifunc);
 
 	spin_unlock(&mdev->mbox_lock);
 
@@ -445,6 +448,14 @@ const char *otx2_mbox_id2name(u16 id)
 #define M(_name, _id, _1, _2, _3) case _id: return # _name;
 	MBOX_MESSAGES
 #undef M
+
+#define M(_name, _id, _1, _2, _3) case _id: return # _name;
+	MBOX_UP_CGX_MESSAGES
+#undef M
+
+#define M(_name, _id, _1, _2, _3) case _id: return # _name;
+	MBOX_UP_CPT_MESSAGES
+#undef M
 	default:
 		return "INVALID ID";
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 6575c422635b..19a5f0da4c7f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -1393,8 +1393,6 @@ static void rvu_detach_block(struct rvu *rvu, int pcifunc, int blktype)
 	if (blkaddr < 0)
 		return;
 
-	if (blktype == BLKTYPE_NIX)
-		rvu_nix_reset_mac(pfvf, pcifunc);
 
 	block = &hw->block[blkaddr];
 
@@ -1407,6 +1405,10 @@ static void rvu_detach_block(struct rvu *rvu, int pcifunc, int blktype)
 		if (lf < 0) /* This should never happen */
 			continue;
 
+		if (blktype == BLKTYPE_NIX) {
+			rvu_nix_reset_mac(pfvf, pcifunc);
+			rvu_npc_clear_ucast_entry(rvu, pcifunc, lf);
+		}
 		/* Disable the LF */
 		rvu_write64(rvu, blkaddr, block->lfcfg_reg |
 			    (lf << block->lfshift), 0x00ULL);
@@ -2173,7 +2175,7 @@ static int rvu_process_mbox_msg(struct otx2_mbox *mbox, int devid,
 		if (rsp && err)						\
 			rsp->hdr.rc = err;				\
 									\
-		trace_otx2_msg_process(mbox->pdev, _id, err);		\
+		trace_otx2_msg_process(mbox->pdev, _id, err, req->pcifunc); \
 		return rsp ? err : -ENOMEM;				\
 	}
 MBOX_MESSAGES
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 60f085b00a8c..48f66292ad5c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -969,8 +969,6 @@ void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 				  bool enable);
 void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, u64 chan);
-void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
-				bool enable);
 void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    u64 chan);
 void rvu_npc_enable_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
@@ -996,6 +994,8 @@ void rvu_npc_get_mcam_entry_alloc_info(struct rvu *rvu, u16 pcifunc,
 void rvu_npc_get_mcam_counter_alloc_info(struct rvu *rvu, u16 pcifunc,
 					 int blkaddr, int *alloc_cnt,
 					 int *enable_cnt);
+void rvu_npc_clear_ucast_entry(struct rvu *rvu, int pcifunc, int nixlf);
+
 bool is_npc_intf_tx(u8 intf);
 bool is_npc_intf_rx(u8 intf);
 bool is_npc_interface_valid(struct rvu *rvu, u8 intf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 992fa0b82e8d..38db06b1784c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -34,7 +34,7 @@ static struct _req_type __maybe_unused					\
 		return NULL;						\
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;				\
 	req->hdr.id = _id;						\
-	trace_otx2_msg_alloc(rvu->pdev, _id, sizeof(*req));		\
+	trace_otx2_msg_alloc(rvu->pdev, _id, sizeof(*req), 0);		\
 	return req;							\
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
index 7fa98aeb3663..4a3370a40dd8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
@@ -13,19 +13,26 @@
 /* RVU LMTST */
 #define LMT_TBL_OP_READ		0
 #define LMT_TBL_OP_WRITE	1
-#define LMT_MAP_TABLE_SIZE	(128 * 1024)
 #define LMT_MAPTBL_ENTRY_SIZE	16
+#define LMT_MAX_VFS		256
+
+#define LMT_MAP_ENTRY_ENA      BIT_ULL(20)
+#define LMT_MAP_ENTRY_LINES    GENMASK_ULL(18, 16)
 
 /* Function to perform operations (read/write) on lmtst map table */
 static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 			       int lmt_tbl_op)
 {
 	void __iomem *lmt_map_base;
-	u64 tbl_base;
+	u64 tbl_base, cfg;
+	int pfs, vfs;
 
 	tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+	cfg  = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG);
+	vfs = 1 << (cfg & 0xF);
+	pfs = 1 << ((cfg >> 4) & 0x7);
 
-	lmt_map_base = ioremap_wc(tbl_base, LMT_MAP_TABLE_SIZE);
+	lmt_map_base = ioremap_wc(tbl_base, pfs * vfs * LMT_MAPTBL_ENTRY_SIZE);
 	if (!lmt_map_base) {
 		dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
 		return -ENOMEM;
@@ -35,6 +42,13 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 		*val = readq(lmt_map_base + index);
 	} else {
 		writeq((*val), (lmt_map_base + index));
+
+		cfg = FIELD_PREP(LMT_MAP_ENTRY_ENA, 0x1);
+		/* 2048 LMTLINES */
+		cfg |= FIELD_PREP(LMT_MAP_ENTRY_LINES, 0x6);
+
+		writeq(cfg, (lmt_map_base + (index + 8)));
+
 		/* Flushing the AP interceptor cache to make APR_LMT_MAP_ENTRY_S
 		 * changes effective. Write 1 for flush and read is being used as a
 		 * barrier and sets up a data dependency. Write to 0 after a write
@@ -52,7 +66,7 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 #define LMT_MAP_TBL_W1_OFF  8
 static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc)
 {
-	return ((rvu_get_pf(pcifunc) * rvu->hw->total_vfs) +
+	return ((rvu_get_pf(pcifunc) * LMT_MAX_VFS) +
 		(pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE;
 }
 
@@ -69,7 +83,7 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc,
 
 	mutex_lock(&rvu->rsrc_lock);
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova);
-	pf = rvu_get_pf(pcifunc) & 0x1F;
+	pf = rvu_get_pf(pcifunc) & RVU_PFVF_PF_MASK;
 	val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 |
 	      ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF);
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index a1f9ec03c2ce..c827da626471 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -553,6 +553,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 	u64 lmt_addr, val, tbl_base;
 	int pf, vf, num_vfs, hw_vfs;
 	void __iomem *lmt_map_base;
+	int apr_pfs, apr_vfs;
 	int buf_size = 10240;
 	size_t off = 0;
 	int index = 0;
@@ -568,8 +569,12 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		return -ENOMEM;
 
 	tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+	val  = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG);
+	apr_vfs = 1 << (val & 0xF);
+	apr_pfs = 1 << ((val >> 4) & 0x7);
 
-	lmt_map_base = ioremap_wc(tbl_base, 128 * 1024);
+	lmt_map_base = ioremap_wc(tbl_base, apr_pfs * apr_vfs *
+				  LMT_MAPTBL_ENTRY_SIZE);
 	if (!lmt_map_base) {
 		dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
 		kfree(buf);
@@ -591,7 +596,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		off += scnprintf(&buf[off], buf_size - 1 - off, "PF%d  \t\t\t",
 				    pf);
 
-		index = pf * rvu->hw->total_vfs * LMT_MAPTBL_ENTRY_SIZE;
+		index = pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE;
 		off += scnprintf(&buf[off], buf_size - 1 - off, " 0x%llx\t\t",
 				 (tbl_base + index));
 		lmt_addr = readq(lmt_map_base + index);
@@ -604,7 +609,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		/* Reading num of VFs per PF */
 		rvu_get_pf_numvfs(rvu, pf, &num_vfs, &hw_vfs);
 		for (vf = 0; vf < num_vfs; vf++) {
-			index = (pf * rvu->hw->total_vfs * 16) +
+			index = (pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE) +
 				((vf + 1)  * LMT_MAPTBL_ENTRY_SIZE);
 			off += scnprintf(&buf[off], buf_size - 1 - off,
 					    "PF%d:VF%d  \t\t", pf, vf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 821fe242f821..da15bb451178 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -820,24 +820,6 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
 }
 
-void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
-				bool enable)
-{
-	struct npc_mcam *mcam = &rvu->hw->mcam;
-	int blkaddr, index;
-
-	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
-	if (blkaddr < 0)
-		return;
-
-	/* Get 'pcifunc' of PF device */
-	pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;
-
-	index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf,
-					 NIXLF_BCAST_ENTRY);
-	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
-}
-
 void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    u64 chan)
 {
@@ -1125,6 +1107,7 @@ void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc,
 static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, bool enable)
 {
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	int index, blkaddr;
 
@@ -1133,9 +1116,12 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
 		return;
 
 	/* Ucast MCAM match entry of this PF/VF */
-	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
-					 nixlf, NIXLF_UCAST_ENTRY);
-	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+	if (npc_is_feature_supported(rvu, BIT_ULL(NPC_DMAC),
+				     pfvf->nix_rx_intf)) {
+		index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+						 nixlf, NIXLF_UCAST_ENTRY);
+		npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+	}
 
 	/* Nothing to do for VFs, on platforms where pkt replication
 	 * is not supported
@@ -3588,3 +3574,33 @@ int rvu_mbox_handler_npc_mcam_entry_stats(struct rvu *rvu,
 
 	return 0;
 }
+
+void rvu_npc_clear_ucast_entry(struct rvu *rvu, int pcifunc, int nixlf)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct rvu_npc_mcam_rule *rule;
+	int ucast_idx, blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return;
+
+	ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					     nixlf, NIXLF_UCAST_ENTRY);
+
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, ucast_idx, false);
+
+	npc_set_mcam_action(rvu, mcam, blkaddr, ucast_idx, 0);
+
+	npc_clear_mcam_entry(rvu, mcam, blkaddr, ucast_idx);
+
+	mutex_lock(&mcam->lock);
+	list_for_each_entry(rule, &mcam->mcam_rules, list) {
+		if (rule->entry == ucast_idx) {
+			list_del(&rule->list);
+			kfree(rule);
+			break;
+		}
+	}
+	mutex_unlock(&mcam->lock);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
index 775fd4c35794..19e0d16b12f6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
@@ -11,3 +11,5 @@
 EXPORT_TRACEPOINT_SYMBOL(otx2_msg_alloc);
 EXPORT_TRACEPOINT_SYMBOL(otx2_msg_interrupt);
 EXPORT_TRACEPOINT_SYMBOL(otx2_msg_process);
+EXPORT_TRACEPOINT_SYMBOL(otx2_msg_status);
+EXPORT_TRACEPOINT_SYMBOL(otx2_parse_dump);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
index 5704520f9b02..4cd0fc4b0d20 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
@@ -18,33 +18,42 @@
 #include "mbox.h"
 
 TRACE_EVENT(otx2_msg_alloc,
-	    TP_PROTO(const struct pci_dev *pdev, u16 id, u64 size),
-	    TP_ARGS(pdev, id, size),
+	    TP_PROTO(const struct pci_dev *pdev, u16 id, u64 size, u16 pcifunc),
+	    TP_ARGS(pdev, id, size, pcifunc),
 	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
 			     __field(u16, id)
 			     __field(u64, size)
+			     __field(u16, pcifunc)
 	    ),
 	    TP_fast_assign(__assign_str(dev);
 			   __entry->id = id;
 			   __entry->size = size;
+			   __entry->pcifunc = pcifunc;
 	    ),
-	    TP_printk("[%s] msg:(%s) size:%lld\n", __get_str(dev),
-		      otx2_mbox_id2name(__entry->id), __entry->size)
+	    TP_printk("[%s] msg:(%s) size:%lld pcifunc:0x%x\n", __get_str(dev),
+		      otx2_mbox_id2name(__entry->id), __entry->size,
+		      __entry->pcifunc)
 );
 
 TRACE_EVENT(otx2_msg_send,
-	    TP_PROTO(const struct pci_dev *pdev, u16 num_msgs, u64 msg_size),
-	    TP_ARGS(pdev, num_msgs, msg_size),
+	    TP_PROTO(const struct pci_dev *pdev, u16 num_msgs, u64 msg_size,
+		     u16 id, u16 pcifunc),
+	    TP_ARGS(pdev, num_msgs, msg_size, id, pcifunc),
 	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
 			     __field(u16, num_msgs)
 			     __field(u64, msg_size)
+			     __field(u16, id)
+			     __field(u16, pcifunc)
 	    ),
 	    TP_fast_assign(__assign_str(dev);
 			   __entry->num_msgs = num_msgs;
 			   __entry->msg_size = msg_size;
+			   __entry->id = id;
+			   __entry->pcifunc = pcifunc;
 	    ),
-	    TP_printk("[%s] sent %d msg(s) of size:%lld\n", __get_str(dev),
-		      __entry->num_msgs, __entry->msg_size)
+	    TP_printk("[%s] sent %d msg(s) of size:%lld msg:(%s) pcifunc:0x%x\n",
+		      __get_str(dev), __entry->num_msgs, __entry->msg_size,
+		      otx2_mbox_id2name(__entry->id), __entry->pcifunc)
 );
 
 TRACE_EVENT(otx2_msg_check,
@@ -81,18 +90,73 @@ TRACE_EVENT(otx2_msg_interrupt,
 );
 
 TRACE_EVENT(otx2_msg_process,
-	    TP_PROTO(const struct pci_dev *pdev, u16 id, int err),
-	    TP_ARGS(pdev, id, err),
+	    TP_PROTO(const struct pci_dev *pdev, u16 id, int err, u16 pcifunc),
+	    TP_ARGS(pdev, id, err, pcifunc),
 	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
 			     __field(u16, id)
 			     __field(int, err)
+			     __field(u16, pcifunc)
 	    ),
 	    TP_fast_assign(__assign_str(dev);
 			   __entry->id = id;
 			   __entry->err = err;
+			   __entry->pcifunc = pcifunc;
+	    ),
+	    TP_printk("[%s] msg:(%s) error:%d pcifunc:0x%x\n", __get_str(dev),
+		      otx2_mbox_id2name(__entry->id),
+		      __entry->err, __entry->pcifunc)
+);
+
+TRACE_EVENT(otx2_msg_wait_rsp,
+	    TP_PROTO(const struct pci_dev *pdev),
+	    TP_ARGS(pdev),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+	    ),
+	    TP_fast_assign(__assign_str(dev)
+	    ),
+	    TP_printk("[%s] timed out while waiting for response\n",
+		      __get_str(dev))
+);
+
+TRACE_EVENT(otx2_msg_status,
+	    TP_PROTO(const struct pci_dev *pdev, const char *msg, u16 num_msgs),
+	    TP_ARGS(pdev, msg, num_msgs),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+			     __string(str, msg)
+			     __field(u16, num_msgs)
+	    ),
+	    TP_fast_assign(__assign_str(dev);
+			   __assign_str(str);
+			   __entry->num_msgs = num_msgs;
+	    ),
+	    TP_printk("[%s] %s num_msgs:%d\n", __get_str(dev),
+		      __get_str(str), __entry->num_msgs)
+);
+
+TRACE_EVENT(otx2_parse_dump,
+	    TP_PROTO(const struct pci_dev *pdev, char *msg, u64 *word),
+	    TP_ARGS(pdev, msg, word),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+			     __string(str, msg)
+			     __field(u64, w0)
+			     __field(u64, w1)
+			     __field(u64, w2)
+			     __field(u64, w3)
+			     __field(u64, w4)
+			     __field(u64, w5)
+	    ),
+	    TP_fast_assign(__assign_str(dev);
+			   __assign_str(str);
+			   __entry->w0 = *(word + 0);
+			   __entry->w1 = *(word + 1);
+			   __entry->w2 = *(word + 2);
+			   __entry->w3 = *(word + 3);
+			   __entry->w4 = *(word + 4);
+			   __entry->w5 = *(word + 5);
 	    ),
-	    TP_printk("[%s] msg:(%s) error:%d\n", __get_str(dev),
-		      otx2_mbox_id2name(__entry->id), __entry->err)
+	    TP_printk("[%s] nix parse %s W0:%#llx W1:%#llx W2:%#llx W3:%#llx W4:%#llx W5:%#llx\n",
+		      __get_str(dev), __get_str(str), __entry->w0, __entry->w1, __entry->w2,
+		      __entry->w3, __entry->w4, __entry->w5)
 );
 
 #endif /* __RVU_TRACE_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
index f3b9daffaec3..4c7e0f345cb5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
@@ -531,7 +531,8 @@ static int cn10k_mcs_write_tx_secy(struct otx2_nic *pfvf,
 	if (sw_tx_sc->encrypt)
 		sectag_tci |= (MCS_TCI_E | MCS_TCI_C);
 
-	policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU, secy->netdev->mtu);
+	policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU,
+			    pfvf->netdev->mtu + OTX2_ETH_HLEN);
 	/* Write SecTag excluding AN bits(1..0) */
 	policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_TCI, sectag_tci >> 2);
 	policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_OFFSET, tag_offset);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 1e88422825be..6a38f91bbf5e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -356,6 +356,7 @@ struct otx2_flow_config {
 	struct list_head	flow_list_tc;
 	u8			ucast_flt_cnt;
 	bool			ntuple;
+	u16			ntuple_cnt;
 };
 
 struct dev_hw_ops {
@@ -871,6 +872,7 @@ static struct _req_type __maybe_unused					\
 *otx2_mbox_alloc_msg_ ## _fn_name(struct mbox *mbox)                    \
 {									\
 	struct _req_type *req;						\
+	u16 pcifunc = mbox->pfvf->pcifunc;				\
 									\
 	req = (struct _req_type *)otx2_mbox_alloc_msg_rsp(		\
 		&mbox->mbox, 0, sizeof(struct _req_type),		\
@@ -879,7 +881,8 @@ static struct _req_type __maybe_unused					\
 		return NULL;						\
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;				\
 	req->hdr.id = _id;						\
-	trace_otx2_msg_alloc(mbox->mbox.pdev, _id, sizeof(*req));	\
+	req->hdr.pcifunc = pcifunc;					\
+	trace_otx2_msg_alloc(mbox->mbox.pdev, _id, sizeof(*req), pcifunc); \
 	return req;							\
 }
 
@@ -1107,6 +1110,8 @@ int otx2_enable_rxvlan(struct otx2_nic *pf, bool enable);
 int otx2_install_rxvlan_offload_flow(struct otx2_nic *pfvf);
 bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, struct xdp_frame *xdpf,
 			    u64 iova, int len, u16 qidx, u16 flags);
+void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, struct xdp_frame *xdpf,
+			 u64 dma_addr, int len, int *offset, u16 flags);
 u16 otx2_get_max_mtu(struct otx2_nic *pfvf);
 int otx2_handle_ntuple_tc_features(struct net_device *netdev,
 				   netdev_features_t features);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
index 33ec9a7f7c03..e13ae5484c19 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
@@ -41,6 +41,7 @@ static int otx2_dl_mcam_count_set(struct devlink *devlink, u32 id,
 	if (!pfvf->flow_cfg)
 		return 0;
 
+	pfvf->flow_cfg->ntuple_cnt = ctx->val.vu16;
 	otx2_alloc_mcam_entries(pfvf, ctx->val.vu16);
 
 	return 0;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 010385b29988..45b8c9230184 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -315,7 +315,7 @@ static void otx2_get_pauseparam(struct net_device *netdev,
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 	struct cgx_pause_frm_cfg *req, *rsp;
 
-	if (is_otx2_lbkvf(pfvf->pdev))
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
 		return;
 
 	mutex_lock(&pfvf->mbox.lock);
@@ -347,7 +347,7 @@ static int otx2_set_pauseparam(struct net_device *netdev,
 	if (pause->autoneg)
 		return -EOPNOTSUPP;
 
-	if (is_otx2_lbkvf(pfvf->pdev))
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
 		return -EOPNOTSUPP;
 
 	if (pause->rx_pause)
@@ -941,8 +941,8 @@ static u32 otx2_get_link(struct net_device *netdev)
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 
-	/* LBK link is internal and always UP */
-	if (is_otx2_lbkvf(pfvf->pdev))
+	/* LBK and SDP links are internal and always UP */
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
 		return 1;
 	return pfvf->linfo.link_up;
 }
@@ -1413,7 +1413,7 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev,
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
 
-	if (is_otx2_lbkvf(pfvf->pdev)) {
+	if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev)) {
 		cmd->base.duplex = DUPLEX_FULL;
 		cmd->base.speed = SPEED_100000;
 	} else {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 47bfd1fb37d4..64c6d9162ef6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -247,7 +247,7 @@ int otx2_mcam_entry_init(struct otx2_nic *pfvf)
 	mutex_unlock(&pfvf->mbox.lock);
 
 	/* Allocate entries for Ntuple filters */
-	count = otx2_alloc_mcam_entries(pfvf, OTX2_DEFAULT_FLOWCOUNT);
+	count = otx2_alloc_mcam_entries(pfvf, flow_cfg->ntuple_cnt);
 	if (count <= 0) {
 		otx2_clear_ntuple_flow_info(pfvf, flow_cfg);
 		return 0;
@@ -307,6 +307,7 @@ int otx2_mcam_flow_init(struct otx2_nic *pf)
 	INIT_LIST_HEAD(&pf->flow_cfg->flow_list_tc);
 
 	pf->flow_cfg->ucast_flt_cnt = OTX2_DEFAULT_UNICAST_FLOWS;
+	pf->flow_cfg->ntuple_cnt = OTX2_DEFAULT_FLOWCOUNT;
 
 	/* Allocate bare minimum number of MCAM entries needed for
 	 * unicast and ntuple filters.
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index cfed9ec5b157..d79b4b30176d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -465,6 +465,9 @@ static void otx2_pfvf_mbox_handler(struct work_struct *work)
 
 	offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
 
+	trace_otx2_msg_status(pf->pdev, "PF-VF down queue handler(forwarding)",
+			      vf_mbox->num_msgs);
+
 	for (id = 0; id < vf_mbox->num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + mbox->rx_start +
 					     offset);
@@ -473,7 +476,7 @@ static void otx2_pfvf_mbox_handler(struct work_struct *work)
 			goto inval_msg;
 
 		/* Set VF's number in each of the msg */
-		msg->pcifunc &= RVU_PFVF_FUNC_MASK;
+		msg->pcifunc &= ~RVU_PFVF_FUNC_MASK;
 		msg->pcifunc |= (vf_idx + 1) & RVU_PFVF_FUNC_MASK;
 		offset = msg->next_msgoff;
 	}
@@ -503,6 +506,9 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work)
 
 	offset = mbox->rx_start + ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
 
+	trace_otx2_msg_status(pf->pdev, "PF-VF up queue handler(response)",
+			      vf_mbox->up_num_msgs);
+
 	for (id = 0; id < vf_mbox->up_num_msgs; id++) {
 		msg = mdev->mbase + offset;
 
@@ -819,6 +825,9 @@ static void otx2_pfaf_mbox_handler(struct work_struct *work)
 	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
 	pf = af_mbox->pfvf;
 
+	trace_otx2_msg_status(pf->pdev, "PF-AF down queue handler(response)",
+			      num_msgs);
+
 	for (id = 0; id < num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
 		otx2_process_pfaf_mbox_msg(pf, msg);
@@ -974,6 +983,9 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work)
 
 	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
 
+	trace_otx2_msg_status(pf->pdev, "PF-AF up queue handler(notification)",
+			      num_msgs);
+
 	for (id = 0; id < num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
 
@@ -1023,6 +1035,9 @@ static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
 
 		trace_otx2_msg_interrupt(pf->pdev, "UP message from AF to PF",
 					 BIT_ULL(0));
+
+		trace_otx2_msg_status(pf->pdev, "PF-AF up work queued(interrupt)",
+				      hdr->num_msgs);
 	}
 
 	if (mbox_data & MBOX_DOWN_MSG) {
@@ -1039,6 +1054,9 @@ static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
 
 		trace_otx2_msg_interrupt(pf->pdev, "DOWN reply from AF to PF",
 					 BIT_ULL(0));
+
+		trace_otx2_msg_status(pf->pdev, "PF-AF down work queued(interrupt)",
+				      hdr->num_msgs);
 	}
 
 	return IRQ_HANDLED;
@@ -3048,7 +3066,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return err;
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
 		return err;
@@ -3057,7 +3075,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "DMA mask config failed, abort\n");
-		goto err_release_regions;
+		return err;
 	}
 
 	pci_set_master(pdev);
@@ -3067,10 +3085,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	qos_txqs = min_t(int, qcount, OTX2_QOS_MAX_LEAF_NODES);
 
 	netdev = alloc_etherdev_mqs(sizeof(*pf), qcount + qos_txqs, qcount);
-	if (!netdev) {
-		err = -ENOMEM;
-		goto err_release_regions;
-	}
+	if (!netdev)
+		return -ENOMEM;
 
 	pci_set_drvdata(pdev, netdev);
 	SET_NETDEV_DEV(netdev, &pdev->dev);
@@ -3246,8 +3262,6 @@ err_detach_rsrc:
 err_free_netdev:
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-err_release_regions:
-	pci_release_regions(pdev);
 	return err;
 }
 
@@ -3289,6 +3303,7 @@ static void otx2_vf_link_event_task(struct work_struct *work)
 	req = (struct cgx_link_info_msg *)msghdr;
 	req->hdr.id = MBOX_MSG_CGX_LINK_EVENT;
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = pf->pcifunc;
 	memcpy(&req->link_info, &pf->linfo, sizeof(req->link_info));
 
 	otx2_mbox_wait_for_zero(&pf->mbox_pfvf[0].mbox_up, vf_idx);
@@ -3447,8 +3462,6 @@ static void otx2_remove(struct pci_dev *pdev)
 	pci_free_irq_vectors(pf->pdev);
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-
-	pci_release_regions(pdev);
 }
 
 static struct pci_driver otx2_pf_driver = {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 0a6bb346ba45..99ace381cc78 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -335,6 +335,7 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 	struct nix_rx_parse_s *parse = &cqe->parse;
 	struct nix_rx_sg_s *sg = &cqe->sg;
 	struct sk_buff *skb = NULL;
+	u64 *word = (u64 *)parse;
 	void *end, *start;
 	u32 metasize = 0;
 	u64 *seg_addr;
@@ -342,9 +343,12 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 	int seg;
 
 	if (unlikely(parse->errlev || parse->errcode)) {
-		if (otx2_check_rcv_errors(pfvf, cqe, cq->cq_idx))
+		if (otx2_check_rcv_errors(pfvf, cqe, cq->cq_idx)) {
+			trace_otx2_parse_dump(pfvf->pdev, "Err:", word);
 			return;
+		}
 	}
+	trace_otx2_parse_dump(pfvf->pdev, "", word);
 
 	if (pfvf->xdp_prog)
 		if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq,
@@ -1410,9 +1414,8 @@ void otx2_free_pending_sqe(struct otx2_nic *pfvf)
 	}
 }
 
-static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq,
-				struct xdp_frame *xdpf,
-				u64 dma_addr, int len, int *offset, u16 flags)
+void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, struct xdp_frame *xdpf,
+			 u64 dma_addr, int len, int *offset, u16 flags)
 {
 	struct nix_sqe_sg_s *sg = NULL;
 	u64 *iova = NULL;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index 7ef3ba477d49..8a8b598bd389 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -136,7 +136,7 @@ static int otx2vf_process_mbox_msg_up(struct otx2_nic *vf,
 
 		rsp->hdr.id = MBOX_MSG_CGX_LINK_EVENT;
 		rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
-		rsp->hdr.pcifunc = 0;
+		rsp->hdr.pcifunc = req->pcifunc;
 		rsp->hdr.rc = 0;
 		err = otx2_mbox_up_handler_cgx_link_event(
 				vf, (struct cgx_link_info_msg *)req, rsp);
@@ -548,7 +548,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return err;
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
 		return err;
@@ -557,7 +557,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "DMA mask config failed, abort\n");
-		goto err_release_regions;
+		return err;
 	}
 
 	pci_set_master(pdev);
@@ -565,10 +565,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	qcount = num_online_cpus();
 	qos_txqs = min_t(int, qcount, OTX2_QOS_MAX_LEAF_NODES);
 	netdev = alloc_etherdev_mqs(sizeof(*vf), qcount + qos_txqs, qcount);
-	if (!netdev) {
-		err = -ENOMEM;
-		goto err_release_regions;
-	}
+	if (!netdev)
+		return -ENOMEM;
 
 	pci_set_drvdata(pdev, netdev);
 	SET_NETDEV_DEV(netdev, &pdev->dev);
@@ -729,9 +727,12 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 #ifdef CONFIG_DCB
-	err = otx2_dcbnl_set_ops(netdev);
-	if (err)
-		goto err_free_zc_bmap;
+	/* Priority flow control is not supported for LBK and SDP vf(s) */
+	if (!(is_otx2_lbkvf(vf->pdev) || is_otx2_sdp_rep(vf->pdev))) {
+		err = otx2_dcbnl_set_ops(netdev);
+		if (err)
+			goto err_free_zc_bmap;
+	}
 #endif
 	otx2_qos_init(vf, qos_txqs);
 
@@ -765,8 +766,6 @@ err_free_irq_vectors:
 err_free_netdev:
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-err_release_regions:
-	pci_release_regions(pdev);
 	return err;
 }
 
@@ -815,8 +814,6 @@ static void otx2vf_remove(struct pci_dev *pdev)
 	pci_free_irq_vectors(vf->pdev);
 	pci_set_drvdata(pdev, NULL);
 	free_netdev(netdev);
-
-	pci_release_regions(pdev);
 }
 
 static struct pci_driver otx2vf_driver = {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
index ce10caea8511..b328aae23d73 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
@@ -11,6 +11,7 @@
 #include <net/xdp.h>
 
 #include "otx2_common.h"
+#include "otx2_struct.h"
 #include "otx2_xsk.h"
 
 int otx2_xsk_pool_alloc_buf(struct otx2_nic *pfvf, struct otx2_pool *pool,
@@ -196,11 +197,39 @@ void otx2_attach_xsk_buff(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, int
 		sq->xsk_pool = xsk_get_pool_from_qid(pfvf->netdev, qidx);
 }
 
+static void otx2_xsk_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len,
+				   u16 qidx)
+{
+	struct nix_sqe_hdr_s *sqe_hdr;
+	struct otx2_snd_queue *sq;
+	int offset;
+
+	sq = &pfvf->qset.sq[qidx];
+	memset(sq->sqe_base + 8, 0, sq->sqe_size - 8);
+
+	sqe_hdr = (struct nix_sqe_hdr_s *)(sq->sqe_base);
+
+	if (!sqe_hdr->total) {
+		sqe_hdr->aura = sq->aura_id;
+		sqe_hdr->df = 1;
+		sqe_hdr->sq = qidx;
+		sqe_hdr->pnc = 1;
+	}
+	sqe_hdr->total = len;
+	sqe_hdr->sqe_id = sq->head;
+
+	offset = sizeof(*sqe_hdr);
+
+	otx2_xdp_sqe_add_sg(sq, NULL, iova, len, &offset, OTX2_AF_XDP_FRAME);
+	sqe_hdr->sizem1 = (offset / 16) - 1;
+	pfvf->hw_ops->sqe_flush(pfvf, sq, offset, qidx);
+}
+
 void otx2_zc_napi_handler(struct otx2_nic *pfvf, struct xsk_buff_pool *pool,
 			  int queue, int budget)
 {
 	struct xdp_desc *xdp_desc = pool->tx_descs;
-	int err, i, work_done = 0, batch;
+	int  i, batch;
 
 	budget = min(budget, otx2_read_free_sqe(pfvf, queue));
 	batch = xsk_tx_peek_release_desc_batch(pool, budget);
@@ -211,15 +240,6 @@ void otx2_zc_napi_handler(struct otx2_nic *pfvf, struct xsk_buff_pool *pool,
 		dma_addr_t dma_addr;
 
 		dma_addr = xsk_buff_raw_get_dma(pool, xdp_desc[i].addr);
-		err = otx2_xdp_sq_append_pkt(pfvf, NULL, dma_addr, xdp_desc[i].len,
-					     queue, OTX2_AF_XDP_FRAME);
-		if (!err) {
-			netdev_err(pfvf->netdev, "AF_XDP: Unable to transfer packet err%d\n", err);
-			break;
-		}
-		work_done++;
+		otx2_xsk_sq_append_pkt(pfvf, dma_addr, xdp_desc[i].len, queue);
 	}
-
-	if (work_done)
-		xsk_tx_release(pool);
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
index 04e08e06f30f..2cd3da3b6843 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
@@ -67,6 +67,8 @@ static int rvu_rep_mcam_flow_init(struct rep_dev *rep)
 
 		rsp = (struct npc_mcam_alloc_entry_rsp *)otx2_mbox_get_rsp
 			(&priv->mbox.mbox, 0, &req->hdr);
+		if (IS_ERR(rsp))
+			goto exit;
 
 		for (ent = 0; ent < rsp->count; ent++)
 			rep->flow_cfg->flow_ent[ent + allocated] = rsp->entry_list[ent];
@@ -763,7 +765,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return err;
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	err = pcim_request_all_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
 		return err;
@@ -772,7 +774,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "DMA mask config failed, abort\n");
-		goto err_release_regions;
+		goto err_set_drv_data;
 	}
 
 	pci_set_master(pdev);
@@ -780,7 +782,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
 		err = -ENOMEM;
-		goto err_release_regions;
+		goto err_set_drv_data;
 	}
 
 	pci_set_drvdata(pdev, priv);
@@ -797,7 +799,7 @@ static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	err = otx2_init_rsrc(pdev, priv);
 	if (err)
-		goto err_release_regions;
+		goto err_set_drv_data;
 
 	priv->iommu_domain = iommu_get_domain_for_dev(dev);
 
@@ -820,9 +822,8 @@ err_detach_rsrc:
 	otx2_disable_mbox_intr(priv);
 	otx2_pfaf_mbox_destroy(priv);
 	pci_free_irq_vectors(pdev);
-err_release_regions:
+err_set_drv_data:
 	pci_set_drvdata(pdev, NULL);
-	pci_release_regions(pdev);
 	return err;
 }
 
@@ -842,7 +843,6 @@ static void rvu_rep_remove(struct pci_dev *pdev)
 	otx2_pfaf_mbox_destroy(priv);
 	pci_free_irq_vectors(priv->pdev);
 	pci_set_drvdata(pdev, NULL);
-	pci_release_regions(pdev);
 }
 
 static struct pci_driver rvu_rep_driver = {
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_counter.c b/drivers/net/ethernet/marvell/prestera/prestera_counter.c
index 4cd53a2dae46..634f4543c1d7 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_counter.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_counter.c
@@ -336,8 +336,7 @@ prestera_counter_block_get_by_idx(struct prestera_counter *counter, u32 idx)
 
 static void prestera_counter_stats_work(struct work_struct *work)
 {
-	struct delayed_work *dl_work =
-		container_of(work, struct delayed_work, work);
+	struct delayed_work *dl_work = to_delayed_work(work);
 	struct prestera_counter *counter =
 		container_of(dl_work, struct prestera_counter, stats_dw);
 	struct prestera_counter_block *block;
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
index 35857dc19542..c45d108b2f6d 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
@@ -845,9 +845,9 @@ static int prestera_pci_probe(struct pci_dev *pdev,
 		goto err_pci_enable_device;
 	}
 
-	err = pci_request_regions(pdev, driver_name);
+	err = pcim_request_all_regions(pdev, driver_name);
 	if (err) {
-		dev_err(&pdev->dev, "pci_request_regions failed\n");
+		dev_err(&pdev->dev, "pcim_request_all_regions failed\n");
 		goto err_pci_request_regions;
 	}
 
@@ -938,7 +938,6 @@ err_pci_dev_alloc:
 err_pp_ioremap:
 err_mem_ioremap:
 err_dma_mask:
-	pci_release_regions(pdev);
 err_pci_request_regions:
 err_pci_enable_device:
 	return err;
@@ -953,7 +952,6 @@ static void prestera_pci_remove(struct pci_dev *pdev)
 	pci_free_irq_vectors(pdev);
 	destroy_workqueue(fw->wq);
 	prestera_fw_uninit(fw);
-	pci_release_regions(pdev);
 }
 
 static const struct pci_device_id prestera_pci_devices[] = {
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_path.c b/drivers/net/ethernet/mediatek/mtk_eth_path.c
index 7c27a19c4d8f..b4c01e2878f6 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_path.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_path.c
@@ -14,7 +14,7 @@
 
 struct mtk_eth_muxc {
 	const char	*name;
-	int		cap_bit;
+	u64		cap_bit;
 	int		(*set_path)(struct mtk_eth *eth, u64 path);
 };
 
@@ -31,6 +31,8 @@ static const char *mtk_eth_path_name(u64 path)
 		return "gmac2_rgmii";
 	case MTK_ETH_PATH_GMAC2_SGMII:
 		return "gmac2_sgmii";
+	case MTK_ETH_PATH_GMAC2_2P5GPHY:
+		return "gmac2_2p5gphy";
 	case MTK_ETH_PATH_GMAC2_GEPHY:
 		return "gmac2_gephy";
 	case MTK_ETH_PATH_GDM1_ESW:
@@ -127,6 +129,29 @@ static int set_mux_u3_gmac2_to_qphy(struct mtk_eth *eth, u64 path)
 	return 0;
 }
 
+static int set_mux_gmac2_to_2p5gphy(struct mtk_eth *eth, u64 path)
+{
+	int ret;
+
+	if (path == MTK_ETH_PATH_GMAC2_2P5GPHY) {
+		ret = regmap_clear_bits(eth->ethsys, ETHSYS_SYSCFG0,
+					SYSCFG0_SGMII_GMAC2_V2);
+		if (ret)
+			return ret;
+
+		/* Setup mux to 2p5g PHY */
+		ret = regmap_clear_bits(eth->infra, TOP_MISC_NETSYS_PCS_MUX,
+					MUX_G2_USXGMII_SEL);
+		if (ret)
+			return ret;
+
+		dev_dbg(eth->dev, "path %s in %s updated\n",
+			mtk_eth_path_name(path), __func__);
+	}
+
+	return 0;
+}
+
 static int set_mux_gmac1_gmac2_to_sgmii_rgmii(struct mtk_eth *eth, u64 path)
 {
 	unsigned int val = 0;
@@ -210,6 +235,10 @@ static const struct mtk_eth_muxc mtk_eth_muxc[] = {
 		.cap_bit = MTK_ETH_MUX_U3_GMAC2_TO_QPHY,
 		.set_path = set_mux_u3_gmac2_to_qphy,
 	}, {
+		.name = "mux_gmac2_to_2p5gphy",
+		.cap_bit = MTK_ETH_MUX_GMAC2_TO_2P5GPHY,
+		.set_path = set_mux_gmac2_to_2p5gphy,
+	}, {
 		.name = "mux_gmac1_gmac2_to_sgmii_rgmii",
 		.cap_bit = MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII,
 		.set_path = set_mux_gmac1_gmac2_to_sgmii_rgmii,
@@ -260,6 +289,20 @@ int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id)
 	return mtk_eth_mux_setup(eth, path);
 }
 
+int mtk_gmac_2p5gphy_path_setup(struct mtk_eth *eth, int mac_id)
+{
+	u64 path = 0;
+
+	if (mac_id == MTK_GMAC2_ID)
+		path = MTK_ETH_PATH_GMAC2_2P5GPHY;
+
+	if (!path)
+		return -EINVAL;
+
+	/* Setup proper MUXes along the path */
+	return mtk_eth_mux_setup(eth, path);
+}
+
 int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id)
 {
 	u64 path = 0;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 43197b28b3e7..b38e4f2de674 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -269,12 +269,8 @@ static const char * const mtk_clks_source_name[] = {
 	"ethwarp_wocpu2",
 	"ethwarp_wocpu1",
 	"ethwarp_wocpu0",
-	"top_usxgmii0_sel",
-	"top_usxgmii1_sel",
 	"top_sgm0_sel",
 	"top_sgm1_sel",
-	"top_xfi_phy0_xtal_sel",
-	"top_xfi_phy1_xtal_sel",
 	"top_eth_gmii_sel",
 	"top_eth_refck_50m_sel",
 	"top_eth_sys_200m_sel",
@@ -507,7 +503,7 @@ static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth,
 static void mtk_setup_bridge_switch(struct mtk_eth *eth)
 {
 	/* Force Port1 XGMAC Link Up */
-	mtk_m32(eth, 0, MTK_XGMAC_FORCE_LINK(MTK_GMAC1_ID),
+	mtk_m32(eth, 0, MTK_XGMAC_FORCE_MODE(MTK_GMAC1_ID),
 		MTK_XGMAC_STS(MTK_GMAC1_ID));
 
 	/* Adjust GSW bridge IPG to 11 */
@@ -536,6 +532,26 @@ static struct phylink_pcs *mtk_mac_select_pcs(struct phylink_config *config,
 	return NULL;
 }
 
+static int mtk_mac_prepare(struct phylink_config *config, unsigned int mode,
+			   phy_interface_t iface)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+	struct mtk_eth *eth = mac->hw;
+
+	if (mtk_interface_mode_is_xgmii(eth, iface) &&
+	    mac->id != MTK_GMAC1_ID) {
+		mtk_m32(mac->hw, XMAC_MCR_TRX_DISABLE,
+			XMAC_MCR_TRX_DISABLE, MTK_XMAC_MCR(mac->id));
+
+		mtk_m32(mac->hw, MTK_XGMAC_FORCE_MODE(mac->id) |
+				 MTK_XGMAC_FORCE_LINK(mac->id),
+			MTK_XGMAC_FORCE_MODE(mac->id), MTK_XGMAC_STS(mac->id));
+	}
+
+	return 0;
+}
+
 static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 			   const struct phylink_link_state *state)
 {
@@ -577,6 +593,12 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 			}
 			break;
 		case PHY_INTERFACE_MODE_INTERNAL:
+			if (mac->id == MTK_GMAC2_ID &&
+			    MTK_HAS_CAPS(eth->soc->caps, MTK_2P5GPHY)) {
+				err = mtk_gmac_2p5gphy_path_setup(eth, mac->id);
+				if (err)
+					goto init_err;
+			}
 			break;
 		default:
 			goto err_phy;
@@ -648,12 +670,12 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 	}
 
 	/* Setup gmac */
-	if (mtk_is_netsys_v3_or_greater(eth) &&
-	    mac->interface == PHY_INTERFACE_MODE_INTERNAL) {
+	if (mtk_interface_mode_is_xgmii(eth, state->interface)) {
 		mtk_w32(mac->hw, MTK_GDMA_XGDM_SEL, MTK_GDMA_EG_CTRL(mac->id));
 		mtk_w32(mac->hw, MAC_MCR_FORCE_LINK_DOWN, MTK_MAC_MCR(mac->id));
 
-		mtk_setup_bridge_switch(eth);
+		if (mac->id == MTK_GMAC1_ID)
+			mtk_setup_bridge_switch(eth);
 	}
 
 	return;
@@ -700,10 +722,19 @@ static void mtk_mac_link_down(struct phylink_config *config, unsigned int mode,
 {
 	struct mtk_mac *mac = container_of(config, struct mtk_mac,
 					   phylink_config);
-	u32 mcr = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id));
 
-	mcr &= ~(MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK);
-	mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id));
+	if (!mtk_interface_mode_is_xgmii(mac->hw, interface)) {
+		/* GMAC modes */
+		mtk_m32(mac->hw,
+			MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK, 0,
+			MTK_MAC_MCR(mac->id));
+	} else if (mac->id != MTK_GMAC1_ID) {
+		/* XGMAC except for built-in switch */
+		mtk_m32(mac->hw, XMAC_MCR_TRX_DISABLE, XMAC_MCR_TRX_DISABLE,
+			MTK_XMAC_MCR(mac->id));
+		mtk_m32(mac->hw, MTK_XGMAC_FORCE_LINK(mac->id), 0,
+			MTK_XGMAC_STS(mac->id));
+	}
 }
 
 static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
@@ -734,7 +765,7 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 		case SPEED_100:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 103) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 3);
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 3) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1);
 			break;
 		case SPEED_1000:
@@ -757,13 +788,13 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 		case SPEED_100:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5);
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1);
 			break;
 		case SPEED_1000:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 10) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5) |
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) |
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 6) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 10);
 			break;
 		default:
@@ -775,13 +806,12 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 	mtk_w32(eth, val, soc->reg_map->qdma.qtx_sch + ofs);
 }
 
-static void mtk_mac_link_up(struct phylink_config *config,
-			    struct phy_device *phy,
-			    unsigned int mode, phy_interface_t interface,
-			    int speed, int duplex, bool tx_pause, bool rx_pause)
+static void mtk_gdm_mac_link_up(struct mtk_mac *mac,
+				struct phy_device *phy,
+				unsigned int mode, phy_interface_t interface,
+				int speed, int duplex, bool tx_pause,
+				bool rx_pause)
 {
-	struct mtk_mac *mac = container_of(config, struct mtk_mac,
-					   phylink_config);
 	u32 mcr;
 
 	mcr = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id));
@@ -815,6 +845,56 @@ static void mtk_mac_link_up(struct phylink_config *config,
 	mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id));
 }
 
+static void mtk_xgdm_mac_link_up(struct mtk_mac *mac,
+				 struct phy_device *phy,
+				 unsigned int mode, phy_interface_t interface,
+				 int speed, int duplex, bool tx_pause,
+				 bool rx_pause)
+{
+	u32 mcr;
+
+	if (mac->id == MTK_GMAC1_ID)
+		return;
+
+	/* Eliminate the interference(before link-up) caused by PHY noise */
+	mtk_m32(mac->hw, XMAC_LOGIC_RST, 0, MTK_XMAC_LOGIC_RST(mac->id));
+	mdelay(20);
+	mtk_m32(mac->hw, XMAC_GLB_CNTCLR, XMAC_GLB_CNTCLR,
+		MTK_XMAC_CNT_CTRL(mac->id));
+
+	mtk_m32(mac->hw, MTK_XGMAC_FORCE_LINK(mac->id),
+		MTK_XGMAC_FORCE_LINK(mac->id), MTK_XGMAC_STS(mac->id));
+
+	mcr = mtk_r32(mac->hw, MTK_XMAC_MCR(mac->id));
+	mcr &= ~(XMAC_MCR_FORCE_TX_FC | XMAC_MCR_FORCE_RX_FC |
+		 XMAC_MCR_TRX_DISABLE);
+	/* Configure pause modes -
+	 * phylink will avoid these for half duplex
+	 */
+	if (tx_pause)
+		mcr |= XMAC_MCR_FORCE_TX_FC;
+	if (rx_pause)
+		mcr |= XMAC_MCR_FORCE_RX_FC;
+
+	mtk_w32(mac->hw, mcr, MTK_XMAC_MCR(mac->id));
+}
+
+static void mtk_mac_link_up(struct phylink_config *config,
+			    struct phy_device *phy,
+			    unsigned int mode, phy_interface_t interface,
+			    int speed, int duplex, bool tx_pause, bool rx_pause)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+
+	if (mtk_interface_mode_is_xgmii(mac->hw, interface))
+		mtk_xgdm_mac_link_up(mac, phy, mode, interface, speed, duplex,
+				     tx_pause, rx_pause);
+	else
+		mtk_gdm_mac_link_up(mac, phy, mode, interface, speed, duplex,
+				    tx_pause, rx_pause);
+}
+
 static void mtk_mac_disable_tx_lpi(struct phylink_config *config)
 {
 	struct mtk_mac *mac = container_of(config, struct mtk_mac,
@@ -832,6 +912,9 @@ static int mtk_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 	struct mtk_eth *eth = mac->hw;
 	u32 val;
 
+	if (mtk_interface_mode_is_xgmii(eth, mac->interface))
+		return -EOPNOTSUPP;
+
 	/* Tx idle timer in ms */
 	timer = DIV_ROUND_UP(timer, 1000);
 
@@ -862,6 +945,7 @@ static int mtk_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 }
 
 static const struct phylink_mac_ops mtk_phylink_ops = {
+	.mac_prepare = mtk_mac_prepare,
 	.mac_select_pcs = mtk_mac_select_pcs,
 	.mac_config = mtk_mac_config,
 	.mac_finish = mtk_mac_finish,
@@ -871,9 +955,25 @@ static const struct phylink_mac_ops mtk_phylink_ops = {
 	.mac_enable_tx_lpi = mtk_mac_enable_tx_lpi,
 };
 
+static void mtk_mdio_config(struct mtk_eth *eth)
+{
+	u32 val;
+
+	/* Configure MDC Divider */
+	val = FIELD_PREP(PPSC_MDC_CFG, eth->mdc_divider);
+
+	/* Configure MDC Turbo Mode */
+	if (mtk_is_netsys_v3_or_greater(eth))
+		mtk_m32(eth, 0, MISC_MDC_TURBO, MTK_MAC_MISC_V3);
+	else
+		val |= PPSC_MDC_TURBO;
+
+	mtk_m32(eth, PPSC_MDC_CFG, val, MTK_PPSC);
+}
+
 static int mtk_mdio_init(struct mtk_eth *eth)
 {
-	unsigned int max_clk = 2500000, divider;
+	unsigned int max_clk = 2500000;
 	struct device_node *mii_np;
 	int ret;
 	u32 val;
@@ -908,20 +1008,9 @@ static int mtk_mdio_init(struct mtk_eth *eth)
 		}
 		max_clk = val;
 	}
-	divider = min_t(unsigned int, DIV_ROUND_UP(MDC_MAX_FREQ, max_clk), 63);
-
-	/* Configure MDC Turbo Mode */
-	if (mtk_is_netsys_v3_or_greater(eth))
-		mtk_m32(eth, 0, MISC_MDC_TURBO, MTK_MAC_MISC_V3);
-
-	/* Configure MDC Divider */
-	val = FIELD_PREP(PPSC_MDC_CFG, divider);
-	if (!mtk_is_netsys_v3_or_greater(eth))
-		val |= PPSC_MDC_TURBO;
-	mtk_m32(eth, PPSC_MDC_CFG, val, MTK_PPSC);
-
-	dev_dbg(eth->dev, "MDC is running on %d Hz\n", MDC_MAX_FREQ / divider);
-
+	eth->mdc_divider = min_t(unsigned int, DIV_ROUND_UP(MDC_MAX_FREQ, max_clk), 63);
+	mtk_mdio_config(eth);
+	dev_dbg(eth->dev, "MDC is running on %d Hz\n", MDC_MAX_FREQ / eth->mdc_divider);
 	ret = of_mdiobus_register(eth->mii_bus, mii_np);
 
 err_put_node:
@@ -2247,14 +2336,18 @@ skip_rx:
 		ring->data[idx] = new_data;
 		rxd->rxd1 = (unsigned int)dma_addr;
 release_desc:
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
+			if (unlikely(dma_addr == DMA_MAPPING_ERROR))
+				addr64 = FIELD_GET(RX_DMA_ADDR64_MASK,
+						   rxd->rxd2);
+			else
+				addr64 = RX_DMA_PREP_ADDR64(dma_addr);
+		}
+
 		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
 			rxd->rxd2 = RX_DMA_LSO;
 		else
-			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size);
-
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA) &&
-		    likely(dma_addr != DMA_MAPPING_ERROR))
-			rxd->rxd2 |= RX_DMA_PREP_ADDR64(dma_addr);
+			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size) | addr64;
 
 		ring->calc_idx = idx;
 		done++;
@@ -3181,11 +3274,19 @@ static int mtk_dma_init(struct mtk_eth *eth)
 static void mtk_dma_free(struct mtk_eth *eth)
 {
 	const struct mtk_soc_data *soc = eth->soc;
-	int i;
+	int i, j, txqs = 1;
+
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA))
+		txqs = MTK_QDMA_NUM_QUEUES;
+
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
+		if (!eth->netdev[i])
+			continue;
+
+		for (j = 0; j < txqs; j++)
+			netdev_tx_reset_subqueue(eth->netdev[i], j);
+	}
 
-	for (i = 0; i < MTK_MAX_DEVS; i++)
-		if (eth->netdev[i])
-			netdev_reset_queue(eth->netdev[i]);
 	if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && eth->scratch_ring) {
 		dma_free_coherent(eth->dma_dev,
 				  MTK_QDMA_RING_SIZE * soc->tx.desc_size,
@@ -3315,7 +3416,7 @@ static int mtk_start_dma(struct mtk_eth *eth)
 		if (mtk_is_netsys_v2_or_greater(eth))
 			val |= MTK_MUTLI_CNT | MTK_RESV_BUF |
 			       MTK_WCOMP_EN | MTK_DMAD_WR_WDONE |
-			       MTK_CHK_DDONE_EN | MTK_LEAKY_BUCKET_EN;
+			       MTK_CHK_DDONE_EN;
 		else
 			val |= MTK_RX_BT_32DWORDS;
 		mtk_w32(eth, val, reg_map->qdma.glo_cfg);
@@ -3460,9 +3561,6 @@ static int mtk_open(struct net_device *dev)
 			}
 			mtk_gdm_config(eth, target_mac->id, gdm_config);
 		}
-		/* Reset and enable PSE */
-		mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
-		mtk_w32(eth, 0, MTK_RST_GL);
 
 		napi_enable(&eth->tx_napi);
 		napi_enable(&eth->rx_napi);
@@ -3974,6 +4072,10 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	else
 		mtk_hw_reset(eth);
 
+	/* No MT7628/88 support yet */
+	if (reset && !MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
+		mtk_mdio_config(eth);
+
 	if (mtk_is_netsys_v3_or_greater(eth)) {
 		/* Set FE to PDMAv2 if necessary */
 		val = mtk_r32(eth, MTK_FE_GLO_MISC);
@@ -4034,11 +4136,27 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);
 
 	if (mtk_is_netsys_v3_or_greater(eth)) {
-		/* PSE should not drop port1, port8 and port9 packets */
-		mtk_w32(eth, 0x00000302, PSE_DROP_CFG);
+		/* PSE dummy page mechanism */
+		mtk_w32(eth, PSE_DUMMY_WORK_GDM(1) | PSE_DUMMY_WORK_GDM(2) |
+			PSE_DUMMY_WORK_GDM(3) | DUMMY_PAGE_THR, PSE_DUMY_REQ);
+
+		/* PSE free buffer drop threshold */
+		mtk_w32(eth, 0x00600009, PSE_IQ_REV(8));
+
+		/* PSE should not drop port8, port9 and port13 packets from
+		 * WDMA Tx
+		 */
+		mtk_w32(eth, 0x00002300, PSE_DROP_CFG);
+
+		/* PSE should drop packets to port8, port9 and port13 on WDMA Rx
+		 * ring full
+		 */
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(0));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(1));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(2));
 
 		/* GDM and CDM Threshold */
-		mtk_w32(eth, 0x00000707, MTK_CDMW0_THRES);
+		mtk_w32(eth, 0x08000707, MTK_CDMW0_THRES);
 		mtk_w32(eth, 0x00000077, MTK_CDMW1_THRES);
 
 		/* Disable GDM1 RX CRC stripping */
@@ -4055,7 +4173,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 		mtk_w32(eth, 0x00000300, PSE_DROP_CFG);
 
 		/* PSE should drop packets to port 8/9 on WDMA Rx ring full */
-		mtk_w32(eth, 0x00000300, PSE_PPE0_DROP);
+		mtk_w32(eth, 0x00000300, PSE_PPE_DROP(0));
 
 		/* PSE Free Queue Flow Control  */
 		mtk_w32(eth, 0x01fa01f4, PSE_FQFC_CFG2);
@@ -4718,7 +4836,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	}
 
 	if (mtk_is_netsys_v3_or_greater(mac->hw) &&
-	    MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW_BIT) &&
+	    MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW) &&
 	    id == MTK_GMAC1_ID) {
 		mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE |
 						       MAC_SYM_PAUSE |
@@ -4738,6 +4856,11 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 
 	mac->phylink = phylink;
 
+	if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_2P5GPHY) &&
+	    id == MTK_GMAC2_ID)
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  mac->phylink_config.supported_interfaces);
+
 	SET_NETDEV_DEV(eth->netdev[id], eth->dev);
 	eth->netdev[id]->watchdog_timeo = 5 * HZ;
 	eth->netdev[id]->netdev_ops = &mtk_netdev_ops;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 90a377ab4359..6f72a8c8ae1e 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -151,7 +151,15 @@
 #define PSE_FQFC_CFG1		0x100
 #define PSE_FQFC_CFG2		0x104
 #define PSE_DROP_CFG		0x108
-#define PSE_PPE0_DROP		0x110
+#define PSE_PPE_DROP(x)		(0x110 + ((x) * 0x4))
+
+/* PSE Last FreeQ Page Request Control */
+#define PSE_DUMY_REQ		0x10C
+/* PSE_DUMY_REQ is not a typo but actually called like that also in
+ * MediaTek's datasheet
+ */
+#define PSE_DUMMY_WORK_GDM(x)	BIT(16 + (x))
+#define DUMMY_PAGE_THR		0x1
 
 /* PSE Input Queue Reservation Register*/
 #define PSE_IQ_REV(x)		(0x140 + (((x) - 1) << 2))
@@ -423,7 +431,8 @@
 
 /* XMAC status registers */
 #define MTK_XGMAC_STS(x)	(((x) == MTK_GMAC3_ID) ? 0x1001C : 0x1000C)
-#define MTK_XGMAC_FORCE_LINK(x)	(((x) == MTK_GMAC2_ID) ? BIT(31) : BIT(15))
+#define MTK_XGMAC_FORCE_MODE(x)	(((x) == MTK_GMAC2_ID) ? BIT(31) : BIT(15))
+#define MTK_XGMAC_FORCE_LINK(x)	(((x) == MTK_GMAC2_ID) ? BIT(27) : BIT(11))
 #define MTK_USXGMII_PCS_LINK	BIT(8)
 #define MTK_XGMAC_RX_FC		BIT(5)
 #define MTK_XGMAC_TX_FC		BIT(4)
@@ -516,6 +525,21 @@
 #define INTF_MODE_RGMII_1000    (TRGMII_MODE | TRGMII_CENTRAL_ALIGNED)
 #define INTF_MODE_RGMII_10_100  0
 
+/* XFI Mac control registers */
+#define MTK_XMAC_BASE(x)	(0x12000 + (((x) - 1) * 0x1000))
+#define MTK_XMAC_MCR(x)		(MTK_XMAC_BASE(x))
+#define XMAC_MCR_TRX_DISABLE	0xf
+#define XMAC_MCR_FORCE_TX_FC	BIT(5)
+#define XMAC_MCR_FORCE_RX_FC	BIT(4)
+
+/* XFI Mac logic reset registers */
+#define MTK_XMAC_LOGIC_RST(x)	(MTK_XMAC_BASE(x) + 0x10)
+#define XMAC_LOGIC_RST		BIT(0)
+
+/* XFI Mac count global control */
+#define MTK_XMAC_CNT_CTRL(x)	(MTK_XMAC_BASE(x) + 0x100)
+#define XMAC_GLB_CNTCLR		BIT(0)
+
 /* GPIO port control registers for GMAC 2*/
 #define GPIO_OD33_CTRL8		0x4c0
 #define GPIO_BIAS_CTRL		0xed0
@@ -579,6 +603,10 @@
 #define GEPHY_MAC_SEL          BIT(1)
 
 /* Top misc registers */
+#define TOP_MISC_NETSYS_PCS_MUX	0x0
+#define NETSYS_PCS_MUX_MASK	GENMASK(1, 0)
+#define MUX_G2_USXGMII_SEL	BIT(1)
+
 #define USB_PHY_SWITCH_REG	0x218
 #define QPHY_SEL_MASK		GENMASK(1, 0)
 #define SGMII_QPHY_SEL		0x2
@@ -943,6 +971,7 @@ enum mkt_eth_capabilities {
 	MTK_RGMII_BIT = 0,
 	MTK_TRGMII_BIT,
 	MTK_SGMII_BIT,
+	MTK_2P5GPHY_BIT,
 	MTK_ESW_BIT,
 	MTK_GEPHY_BIT,
 	MTK_MUX_BIT,
@@ -963,6 +992,7 @@ enum mkt_eth_capabilities {
 	MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT,
 	MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY_BIT,
 	MTK_ETH_MUX_U3_GMAC2_TO_QPHY_BIT,
+	MTK_ETH_MUX_GMAC2_TO_2P5GPHY_BIT,
 	MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII_BIT,
 	MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII_BIT,
 
@@ -972,6 +1002,7 @@ enum mkt_eth_capabilities {
 	MTK_ETH_PATH_GMAC1_SGMII_BIT,
 	MTK_ETH_PATH_GMAC2_RGMII_BIT,
 	MTK_ETH_PATH_GMAC2_SGMII_BIT,
+	MTK_ETH_PATH_GMAC2_2P5GPHY_BIT,
 	MTK_ETH_PATH_GMAC2_GEPHY_BIT,
 	MTK_ETH_PATH_GDM1_ESW_BIT,
 };
@@ -980,6 +1011,7 @@ enum mkt_eth_capabilities {
 #define MTK_RGMII		BIT_ULL(MTK_RGMII_BIT)
 #define MTK_TRGMII		BIT_ULL(MTK_TRGMII_BIT)
 #define MTK_SGMII		BIT_ULL(MTK_SGMII_BIT)
+#define MTK_2P5GPHY		BIT_ULL(MTK_2P5GPHY_BIT)
 #define MTK_ESW			BIT_ULL(MTK_ESW_BIT)
 #define MTK_GEPHY		BIT_ULL(MTK_GEPHY_BIT)
 #define MTK_MUX			BIT_ULL(MTK_MUX_BIT)
@@ -1002,6 +1034,8 @@ enum mkt_eth_capabilities {
 	BIT_ULL(MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY_BIT)
 #define MTK_ETH_MUX_U3_GMAC2_TO_QPHY		\
 	BIT_ULL(MTK_ETH_MUX_U3_GMAC2_TO_QPHY_BIT)
+#define MTK_ETH_MUX_GMAC2_TO_2P5GPHY		\
+	BIT_ULL(MTK_ETH_MUX_GMAC2_TO_2P5GPHY_BIT)
 #define MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII	\
 	BIT_ULL(MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII_BIT)
 #define MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII	\
@@ -1013,6 +1047,7 @@ enum mkt_eth_capabilities {
 #define MTK_ETH_PATH_GMAC1_SGMII	BIT_ULL(MTK_ETH_PATH_GMAC1_SGMII_BIT)
 #define MTK_ETH_PATH_GMAC2_RGMII	BIT_ULL(MTK_ETH_PATH_GMAC2_RGMII_BIT)
 #define MTK_ETH_PATH_GMAC2_SGMII	BIT_ULL(MTK_ETH_PATH_GMAC2_SGMII_BIT)
+#define MTK_ETH_PATH_GMAC2_2P5GPHY	BIT_ULL(MTK_ETH_PATH_GMAC2_2P5GPHY_BIT)
 #define MTK_ETH_PATH_GMAC2_GEPHY	BIT_ULL(MTK_ETH_PATH_GMAC2_GEPHY_BIT)
 #define MTK_ETH_PATH_GDM1_ESW		BIT_ULL(MTK_ETH_PATH_GDM1_ESW_BIT)
 
@@ -1022,6 +1057,7 @@ enum mkt_eth_capabilities {
 #define MTK_GMAC2_RGMII		(MTK_ETH_PATH_GMAC2_RGMII | MTK_RGMII)
 #define MTK_GMAC2_SGMII		(MTK_ETH_PATH_GMAC2_SGMII | MTK_SGMII)
 #define MTK_GMAC2_GEPHY		(MTK_ETH_PATH_GMAC2_GEPHY | MTK_GEPHY)
+#define MTK_GMAC2_2P5GPHY	(MTK_ETH_PATH_GMAC2_2P5GPHY | MTK_2P5GPHY)
 #define MTK_GDM1_ESW		(MTK_ETH_PATH_GDM1_ESW | MTK_ESW)
 
 /* MUXes present on SoCs */
@@ -1041,6 +1077,10 @@ enum mkt_eth_capabilities {
 	(MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII | MTK_MUX | \
 	MTK_SHARED_SGMII)
 
+/* 2: GMAC2 -> 2P5GPHY */
+#define MTK_MUX_GMAC2_TO_2P5GPHY      \
+	(MTK_ETH_MUX_GMAC2_TO_2P5GPHY | MTK_MUX | MTK_INFRA)
+
 /* 0: GMACx -> GEPHY, 1: GMACx -> SGMII where x is 1 or 2 */
 #define MTK_MUX_GMAC12_TO_GEPHY_SGMII   \
 	(MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII | MTK_MUX)
@@ -1076,8 +1116,9 @@ enum mkt_eth_capabilities {
 		      MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \
 		      MTK_RSTCTRL_PPE1 | MTK_SRAM)
 
-#define MT7988_CAPS  (MTK_36BIT_DMA | MTK_GDM1_ESW | MTK_QDMA | \
-		      MTK_RSTCTRL_PPE1 | MTK_RSTCTRL_PPE2 | MTK_SRAM)
+#define MT7988_CAPS  (MTK_36BIT_DMA | MTK_GDM1_ESW | MTK_GMAC2_2P5GPHY | \
+		      MTK_MUX_GMAC2_TO_2P5GPHY | MTK_QDMA | MTK_RSTCTRL_PPE1 | \
+		      MTK_RSTCTRL_PPE2 | MTK_SRAM)
 
 struct mtk_tx_dma_desc_info {
 	dma_addr_t	addr;
@@ -1137,7 +1178,7 @@ struct mtk_reg_map {
 };
 
 /* struct mtk_eth_data -	This is the structure holding all differences
- *				among various plaforms
+ *				among various platforms
  * @reg_map			Soc register map.
  * @ana_rgc3:                   The offset for register ANA_RGC3 related to
  *				sgmiisys syscon
@@ -1237,7 +1278,7 @@ struct mtk_soc_data {
  * @mii_bus:		If there is a bus we need to create an instance for it
  * @pending_work:	The workqueue used to reset the dma ring
  * @state:		Initialization and runtime state of the device
- * @soc:		Holding specific data among vaious SoCs
+ * @soc:		Holding specific data among various SoCs
  */
 
 struct mtk_eth {
@@ -1271,6 +1312,7 @@ struct mtk_eth {
 	struct clk			*clks[MTK_CLK_MAX];
 
 	struct mii_bus			*mii_bus;
+	unsigned int			mdc_divider;
 	struct work_struct		pending_work;
 	unsigned long			state;
 
@@ -1428,6 +1470,23 @@ static inline u32 mtk_get_ib2_multicast_mask(struct mtk_eth *eth)
 	return MTK_FOE_IB2_MULTICAST;
 }
 
+static inline bool mtk_interface_mode_is_xgmii(struct mtk_eth *eth,
+					       phy_interface_t interface)
+{
+	if (!mtk_is_netsys_v3_or_greater(eth))
+		return false;
+
+	switch (interface) {
+	case PHY_INTERFACE_MODE_INTERNAL:
+	case PHY_INTERFACE_MODE_USXGMII:
+	case PHY_INTERFACE_MODE_10GBASER:
+	case PHY_INTERFACE_MODE_5GBASER:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /* read the hardware status register */
 void mtk_stats_update_mac(struct mtk_mac *mac);
 
@@ -1436,6 +1495,7 @@ u32 mtk_r32(struct mtk_eth *eth, unsigned reg);
 u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned int reg);
 
 int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id);
+int mtk_gmac_2p5gphy_path_setup(struct mtk_eth *eth, int mac_id);
 int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id);
 int mtk_gmac_rgmii_path_setup(struct mtk_eth *eth, int mac_id);
 
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 76f202d7f055..b175119a6a7d 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1163,6 +1163,7 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
 	struct net_device *ndev = priv->ndev;
 	unsigned int head = ring->head;
 	unsigned int entry = ring->tail;
+	unsigned long flags;
 
 	while (entry != head && count < (MTK_STAR_RING_NUM_DESCS - 1)) {
 		ret = mtk_star_tx_complete_one(priv);
@@ -1182,9 +1183,9 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
 		netif_wake_queue(ndev);
 
 	if (napi_complete(napi)) {
-		spin_lock(&priv->lock);
+		spin_lock_irqsave(&priv->lock, flags);
 		mtk_star_enable_dma_irq(priv, false, true);
-		spin_unlock(&priv->lock);
+		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 
 	return 0;
@@ -1341,16 +1342,16 @@ push_new_skb:
 static int mtk_star_rx_poll(struct napi_struct *napi, int budget)
 {
 	struct mtk_star_priv *priv;
+	unsigned long flags;
 	int work_done = 0;
 
 	priv = container_of(napi, struct mtk_star_priv, rx_napi);
 
 	work_done = mtk_star_rx(priv, budget);
-	if (work_done < budget) {
-		napi_complete_done(napi, work_done);
-		spin_lock(&priv->lock);
+	if (work_done < budget && napi_complete_done(napi, work_done)) {
+		spin_lock_irqsave(&priv->lock, flags);
 		mtk_star_enable_dma_irq(priv, true, false);
-		spin_unlock(&priv->lock);
+		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 
 	return work_done;
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index e212a4ba9275..351dd152f4f3 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -2000,7 +2000,7 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask)
 		if (mtk_wed_is_v3_or_greater(dev->hw))
 			wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_TX_TKID_ALI_EN);
 
-		/* initail tx interrupt trigger */
+		/* initial tx interrupt trigger */
 		wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_TX,
 			MTK_WED_WPDMA_INT_CTRL_TX0_DONE_EN |
 			MTK_WED_WPDMA_INT_CTRL_TX0_DONE_CLR |
@@ -2011,7 +2011,7 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask)
 			FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_TX1_DONE_TRIG,
 				   dev->wlan.tx_tbit[1]));
 
-		/* initail txfree interrupt trigger */
+		/* initial txfree interrupt trigger */
 		wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_TX_FREE,
 			MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_EN |
 			MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_CLR |
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index cd17a3f4faf8..a68cd3f0304c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1897,6 +1897,7 @@ static int mlx4_en_get_ts_info(struct net_device *dev,
 	if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) {
 		info->so_timestamping |=
 			SOF_TIMESTAMPING_TX_HARDWARE |
+			SOF_TIMESTAMPING_TX_SOFTWARE |
 			SOF_TIMESTAMPING_RX_HARDWARE |
 			SOF_TIMESTAMPING_RAW_HARDWARE;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index d7444782bfdd..698a5d1f0d7e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -106,7 +106,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 	buddy->max_order = max_order;
 	spin_lock_init(&buddy->lock);
 
-	buddy->bits = kcalloc(buddy->max_order + 1, sizeof(long *),
+	buddy->bits = kcalloc(buddy->max_order + 1, sizeof(*buddy->bits),
 			      GFP_KERNEL);
 	buddy->num_free = kcalloc(buddy->max_order + 1, sizeof(*buddy->num_free),
 				  GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 568bbe5f83f5..d292e6a9e22c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -154,7 +154,8 @@ mlx5_core-$(CONFIG_MLX5_HW_STEERING) += steering/hws/cmd.o \
 					steering/hws/vport.o \
 					steering/hws/bwc_complex.o \
 					steering/hws/fs_hws_pools.o \
-					steering/hws/fs_hws.o
+					steering/hws/fs_hws.o \
+					steering/hws/action_ste_pool.o
 
 #
 # SF device
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index e53dbdc0a7a1..b1aeea7c4a91 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -927,8 +927,7 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
 
 static void cb_timeout_handler(struct work_struct *work)
 {
-	struct delayed_work *dwork = container_of(work, struct delayed_work,
-						  work);
+	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5_cmd_work_ent *ent = container_of(dwork,
 						     struct mlx5_cmd_work_ent,
 						     cb_timeout_work);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 32ed4963b8ad..5b0d03b3efe8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -520,6 +520,12 @@ struct mlx5e_xdpsq {
 	struct mlx5e_channel      *channel;
 } ____cacheline_aligned_in_smp;
 
+struct mlx5e_xdp_buff {
+	struct xdp_buff xdp;
+	struct mlx5_cqe64 *cqe;
+	struct mlx5e_rq *rq;
+};
+
 struct mlx5e_ktls_resync_resp;
 
 struct mlx5e_icosq {
@@ -716,6 +722,7 @@ struct mlx5e_rq {
 	struct mlx5e_xdpsq    *xdpsq;
 	DECLARE_BITMAP(flags, 8);
 	struct page_pool      *page_pool;
+	struct mlx5e_xdp_buff mxbuf;
 
 	/* AF_XDP zero-copy */
 	struct xsk_buff_pool  *xsk_pool;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
index 81523825faa2..cb972b2d46e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -114,6 +114,7 @@ int mlx5e_health_recover_channels(struct mlx5e_priv *priv)
 	int err = 0;
 
 	rtnl_lock();
+	netdev_lock(priv->netdev);
 	mutex_lock(&priv->state_lock);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
@@ -123,6 +124,7 @@ int mlx5e_health_recover_channels(struct mlx5e_priv *priv)
 
 out:
 	mutex_unlock(&priv->state_lock);
+	netdev_unlock(priv->netdev);
 	rtnl_unlock();
 
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index 131ed97ca997..5d0014129a7e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -8,6 +8,7 @@
 #include "en/fs_tt_redirect.h"
 #include <linux/list.h>
 #include <linux/spinlock.h>
+#include <net/netdev_lock.h>
 
 struct mlx5e_ptp_fs {
 	struct mlx5_flow_handle *l2_rule;
@@ -449,8 +450,22 @@ static void mlx5e_ptpsq_unhealthy_work(struct work_struct *work)
 {
 	struct mlx5e_ptpsq *ptpsq =
 		container_of(work, struct mlx5e_ptpsq, report_unhealthy_work);
+	struct mlx5e_txqsq *sq = &ptpsq->txqsq;
+
+	/* Recovering the PTP SQ means re-enabling NAPI, which requires the
+	 * netdev instance lock. However, SQ closing has to wait for this work
+	 * task to finish while also holding the same lock. So either get the
+	 * lock or find that the SQ is no longer enabled and thus this work is
+	 * not relevant anymore.
+	 */
+	while (!netdev_trylock(sq->netdev)) {
+		if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))
+			return;
+		msleep(20);
+	}
 
 	mlx5e_reporter_tx_ptpsq_unhealthy(ptpsq);
+	netdev_unlock(sq->netdev);
 }
 
 static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn,
@@ -892,7 +907,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	if (err)
 		goto err_free;
 
-	netif_napi_add(netdev, &c->napi, mlx5e_ptp_napi_poll);
+	netif_napi_add_locked(netdev, &c->napi, mlx5e_ptp_napi_poll);
 
 	mlx5e_ptp_build_params(c, cparams, params);
 
@@ -910,7 +925,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	return 0;
 
 err_napi_del:
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 err_free:
 	kvfree(cparams);
 	kvfree(c);
@@ -920,7 +935,7 @@ err_free:
 void mlx5e_ptp_close(struct mlx5e_ptp *c)
 {
 	mlx5e_ptp_close_queues(c);
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 
 	kvfree(c);
 }
@@ -929,7 +944,7 @@ void mlx5e_ptp_activate_channel(struct mlx5e_ptp *c)
 {
 	int tc;
 
-	napi_enable(&c->napi);
+	napi_enable_locked(&c->napi);
 
 	if (test_bit(MLX5E_PTP_STATE_TX, c->state)) {
 		for (tc = 0; tc < c->num_tc; tc++)
@@ -957,7 +972,7 @@ void mlx5e_ptp_deactivate_channel(struct mlx5e_ptp *c)
 			mlx5e_deactivate_txqsq(&c->ptpsq[tc].txqsq);
 	}
 
-	napi_disable(&c->napi);
+	napi_disable_locked(&c->napi);
 }
 
 int mlx5e_ptp_get_rqn(struct mlx5e_ptp *c, u32 *rqn)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 532c7fa94d17..c3bda4612fa9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -107,9 +107,7 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx)
 	mlx5e_reset_txqsq_cc_pc(sq);
 	sq->stats->recover++;
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
-	rtnl_lock();
 	mlx5e_activate_txqsq(sq);
-	rtnl_unlock();
 
 	if (sq->channel)
 		mlx5e_trigger_napi_icosq(sq->channel);
@@ -183,16 +181,12 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
 	carrier_ok = netif_carrier_ok(netdev);
 	netif_carrier_off(netdev);
 
-	rtnl_lock();
 	mlx5e_deactivate_priv_channels(priv);
-	rtnl_unlock();
 
 	mlx5e_ptp_close(chs->ptp);
 	err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp);
 
-	rtnl_lock();
 	mlx5e_activate_priv_channels(priv);
-	rtnl_unlock();
 
 	/* return carrier back if needed */
 	if (carrier_ok)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index 5c762a71818d..7a18a469961d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -165,9 +165,6 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 	struct flow_match_enc_keyid enc_keyid;
 	void *misc_c, *misc_v;
 
-	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
-	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-
 	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID))
 		return 0;
 
@@ -182,6 +179,30 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 		err = mlx5e_tc_tun_parse_vxlan_gbp_option(priv, spec, f);
 		if (err)
 			return err;
+
+		/* We can't mix custom tunnel headers with symbolic ones and we
+		 * don't have a symbolic field name for GBP, so we use custom
+		 * tunnel headers in this case. We need hardware support to
+		 * match on custom tunnel headers, but we already know it's
+		 * supported because the previous call successfully checked for
+		 * that.
+		 */
+		misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				      misc_parameters_5);
+		misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				      misc_parameters_5);
+
+		/* Shift by 8 to account for the reserved bits in the vxlan
+		 * header after the VNI.
+		 */
+		MLX5_SET(fte_match_set_misc5, misc_c, tunnel_header_1,
+			 be32_to_cpu(enc_keyid.mask->keyid) << 8);
+		MLX5_SET(fte_match_set_misc5, misc_v, tunnel_header_1,
+			 be32_to_cpu(enc_keyid.key->keyid) << 8);
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_5;
+
+		return 0;
 	}
 
 	/* match on VNI is required */
@@ -195,6 +216,11 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
+	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			      misc_parameters);
+	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			      misc_parameters);
+
 	MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
 		 be32_to_cpu(enc_keyid.mask->keyid));
 	MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index 140606fcd23b..b5c19396e096 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -149,7 +149,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
 	t->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey);
 	t->stats    = &priv->trap_stats.ch;
 
-	netif_napi_add(netdev, &t->napi, mlx5e_trap_napi_poll);
+	netif_napi_add_locked(netdev, &t->napi, mlx5e_trap_napi_poll);
 
 	err = mlx5e_open_trap_rq(priv, t);
 	if (unlikely(err))
@@ -164,7 +164,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
 err_close_trap_rq:
 	mlx5e_close_trap_rq(&t->rq);
 err_napi_del:
-	netif_napi_del(&t->napi);
+	netif_napi_del_locked(&t->napi);
 	kvfree(t);
 	return ERR_PTR(err);
 }
@@ -173,13 +173,13 @@ void mlx5e_close_trap(struct mlx5e_trap *trap)
 {
 	mlx5e_tir_destroy(&trap->tir);
 	mlx5e_close_trap_rq(&trap->rq);
-	netif_napi_del(&trap->napi);
+	netif_napi_del_locked(&trap->napi);
 	kvfree(trap);
 }
 
 static void mlx5e_activate_trap(struct mlx5e_trap *trap)
 {
-	napi_enable(&trap->napi);
+	napi_enable_locked(&trap->napi);
 	mlx5e_activate_rq(&trap->rq);
 	mlx5e_trigger_napi_sched(&trap->napi);
 }
@@ -189,7 +189,7 @@ void mlx5e_deactivate_trap(struct mlx5e_priv *priv)
 	struct mlx5e_trap *trap = priv->en_trap;
 
 	mlx5e_deactivate_rq(&trap->rq);
-	napi_disable(&trap->napi);
+	napi_disable_locked(&trap->napi);
 }
 
 static struct mlx5e_trap *mlx5e_add_trap_queue(struct mlx5e_priv *priv)
@@ -285,6 +285,7 @@ int mlx5e_handle_trap_event(struct mlx5e_priv *priv, struct mlx5_trap_ctx *trap_
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		return 0;
 
+	netdev_lock(priv->netdev);
 	switch (trap_ctx->action) {
 	case DEVLINK_TRAP_ACTION_TRAP:
 		err = mlx5e_handle_action_trap(priv, trap_ctx->id);
@@ -297,6 +298,7 @@ int mlx5e_handle_trap_event(struct mlx5e_priv *priv, struct mlx5_trap_ctx *trap_
 			    trap_ctx->action);
 		err = -EINVAL;
 	}
+	netdev_unlock(priv->netdev);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index f803e1c93590..5ce1b463b7a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -707,8 +707,8 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
 				page = xdpi.page.page;
 
-				/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
-				 * as we know this is a page_pool page.
+				/* No need to check page_pool_page_is_pp() as we
+				 * know this is a page_pool page.
 				 */
 				page_pool_recycle_direct(page->pp, page);
 			} while (++n < num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 446e492c6bb8..46ab0a9e8cdd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -45,12 +45,6 @@
 	(MLX5E_XDP_INLINE_WQE_MAX_DS_CNT * MLX5_SEND_WQE_DS - \
 	 sizeof(struct mlx5_wqe_inline_seg))
 
-struct mlx5e_xdp_buff {
-	struct xdp_buff xdp;
-	struct mlx5_cqe64 *cqe;
-	struct mlx5e_rq *rq;
-};
-
 /* XDP packets can be transmitted in different ways. On completion, we need to
  * distinguish between them to clean up things in a proper way.
  */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 8705cffc747f..5fe016e477b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -1147,6 +1147,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state)
 	bool reset = true;
 	int err;
 
+	netdev_lock(priv->netdev);
 	mutex_lock(&priv->state_lock);
 
 	new_params = priv->channels.params;
@@ -1162,6 +1163,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state)
 				       &trust_state, reset);
 
 	mutex_unlock(&priv->state_lock);
+	netdev_unlock(priv->netdev);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index fdf9e9bb99ac..ea078c9f5d15 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1689,6 +1689,7 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 		return 0;
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_TX_SOFTWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
 
@@ -2059,14 +2060,9 @@ int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 	if (err)
 		return err;
 
-	dev_hold(dev);
-	rtnl_unlock();
-
 	err = mlx5_firmware_flash(mdev, fw, NULL);
 	release_firmware(fw);
 
-	rtnl_lock();
-	dev_put(dev);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 05058710d2c7..04a969128161 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -484,7 +484,9 @@ static int mlx5e_vlan_rx_add_svid(struct mlx5e_flow_steering *fs,
 	}
 
 	/* Need to fix some features.. */
+	netdev_lock(netdev);
 	netdev_update_features(netdev);
+	netdev_unlock(netdev);
 	return err;
 }
 
@@ -521,7 +523,9 @@ int mlx5e_fs_vlan_rx_kill_vid(struct mlx5e_flow_steering *fs,
 	} else if (be16_to_cpu(proto) == ETH_P_8021AD) {
 		clear_bit(vid, fs->vlan->active_svlans);
 		mlx5e_fs_del_vlan_rule(fs, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, vid);
+		netdev_lock(netdev);
 		netdev_update_features(netdev);
+		netdev_unlock(netdev);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3506024c2453..ea822c69d137 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -39,6 +39,7 @@
 #include <linux/debugfs.h>
 #include <linux/if_bridge.h>
 #include <linux/filter.h>
+#include <net/netdev_lock.h>
 #include <net/netdev_queues.h>
 #include <net/page_pool/types.h>
 #include <net/pkt_sched.h>
@@ -1903,7 +1904,20 @@ void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 	struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq,
 					      recover_work);
 
+	/* Recovering queues means re-enabling NAPI, which requires the netdev
+	 * instance lock. However, SQ closing flows have to wait for work tasks
+	 * to finish while also holding the netdev instance lock. So either get
+	 * the lock or find that the SQ is no longer enabled and thus this work
+	 * is not relevant anymore.
+	 */
+	while (!netdev_trylock(sq->netdev)) {
+		if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))
+			return;
+		msleep(20);
+	}
+
 	mlx5e_reporter_tx_err_cqe(sq);
+	netdev_unlock(sq->netdev);
 }
 
 static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
@@ -2705,8 +2719,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->aff_mask = irq_get_effective_affinity_mask(irq);
 	c->lag_port = mlx5e_enumerate_lag_port(mdev, ix);
 
-	netif_napi_add_config(netdev, &c->napi, mlx5e_napi_poll, ix);
-	netif_napi_set_irq(&c->napi, irq);
+	netif_napi_add_config_locked(netdev, &c->napi, mlx5e_napi_poll, ix);
+	netif_napi_set_irq_locked(&c->napi, irq);
 
 	err = mlx5e_open_queues(c, params, cparam);
 	if (unlikely(err))
@@ -2728,7 +2742,7 @@ err_close_queues:
 	mlx5e_close_queues(c);
 
 err_napi_del:
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 
 err_free:
 	kvfree(cparam);
@@ -2741,7 +2755,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 {
 	int tc;
 
-	napi_enable(&c->napi);
+	napi_enable_locked(&c->napi);
 
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_activate_txqsq(&c->sq[tc]);
@@ -2773,7 +2787,7 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 		mlx5e_deactivate_txqsq(&c->sq[tc]);
 	mlx5e_qos_deactivate_queues(c);
 
-	napi_disable(&c->napi);
+	napi_disable_locked(&c->napi);
 }
 
 static void mlx5e_close_channel(struct mlx5e_channel *c)
@@ -2782,7 +2796,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 		mlx5e_close_xsk(c);
 	mlx5e_close_queues(c);
 	mlx5e_qos_close_queues(c);
-	netif_napi_del(&c->napi);
+	netif_napi_del_locked(&c->napi);
 
 	kvfree(c);
 }
@@ -4276,7 +4290,7 @@ void mlx5e_set_xdp_feature(struct net_device *netdev)
 
 	if (!netdev->netdev_ops->ndo_bpf ||
 	    params->packet_merge.type != MLX5E_PACKET_MERGE_NONE) {
-		xdp_clear_features_flag(netdev);
+		xdp_set_features_flag_locked(netdev, 0);
 		return;
 	}
 
@@ -4285,7 +4299,7 @@ void mlx5e_set_xdp_feature(struct net_device *netdev)
 	      NETDEV_XDP_ACT_RX_SG |
 	      NETDEV_XDP_ACT_NDO_XMIT |
 	      NETDEV_XDP_ACT_NDO_XMIT_SG;
-	xdp_set_features_flag(netdev, val);
+	xdp_set_features_flag_locked(netdev, val);
 }
 
 int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
@@ -4349,6 +4363,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev
 	if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
 		netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n");
 
+	features &= ~NETIF_F_HW_MACSEC;
+	if (netdev->features & NETIF_F_HW_MACSEC)
+		netdev_warn(netdev, "Disabling HW MACsec offload, not supported in switchdev mode\n");
+
 	return features;
 }
 
@@ -4964,21 +4982,19 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	struct net_device *netdev = priv->netdev;
 	int i;
 
-	/* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues
-	 * through this flow. However, channel closing flows have to wait for
-	 * this work to finish while holding rtnl lock too. So either get the
-	 * lock or find that channels are being closed for other reason and
-	 * this work is not relevant anymore.
+	/* Recovering the TX queues implies re-enabling NAPI, which requires
+	 * the netdev instance lock.
+	 * However, channel closing flows have to wait for this work to finish
+	 * while holding the same lock. So either get the lock or find that
+	 * channels are being closed for other reason and this work is not
+	 * relevant anymore.
 	 */
-	while (!rtnl_trylock()) {
+	while (!netdev_trylock(netdev)) {
 		if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state))
 			return;
 		msleep(20);
 	}
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto unlock;
-
 	for (i = 0; i < netdev->real_num_tx_queues; i++) {
 		struct netdev_queue *dev_queue =
 			netdev_get_tx_queue(netdev, i);
@@ -4992,8 +5008,7 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 			break;
 	}
 
-unlock:
-	rtnl_unlock();
+	netdev_unlock(netdev);
 }
 
 static void mlx5e_tx_timeout(struct net_device *dev, unsigned int txqueue)
@@ -5317,7 +5332,6 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i,
 	struct mlx5e_rq_stats *xskrq_stats;
 	struct mlx5e_rq_stats *rq_stats;
 
-	ASSERT_RTNL();
 	if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch)
 		return;
 
@@ -5337,7 +5351,6 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_sq_stats *sq_stats;
 
-	ASSERT_RTNL();
 	if (!priv->stats_nch)
 		return;
 
@@ -5358,7 +5371,6 @@ static void mlx5e_get_base_stats(struct net_device *dev,
 	struct mlx5e_ptp *ptp_channel;
 	int i, tc;
 
-	ASSERT_RTNL();
 	if (!mlx5e_is_uplink_rep(priv)) {
 		rx->packets = 0;
 		rx->bytes = 0;
@@ -5454,6 +5466,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->netdev_ops = &mlx5e_netdev_ops;
 	netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops;
 	netdev->xsk_tx_metadata_ops = &mlx5e_xsk_tx_metadata_ops;
+	netdev->request_ops_lock = true;
+	netdev_lockdep_set_classes(netdev);
 
 	mlx5e_dcbnl_build_netdev(netdev);
 
@@ -5835,9 +5849,11 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	mlx5e_nic_set_rx_mode(priv);
 
 	rtnl_lock();
+	netdev_lock(netdev);
 	if (netif_running(netdev))
 		mlx5e_open(netdev);
 	udp_tunnel_nic_reset_ntf(priv->netdev);
+	netdev_unlock(netdev);
 	netif_device_attach(netdev);
 	rtnl_unlock();
 }
@@ -5850,9 +5866,16 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 		mlx5e_dcbnl_delete_app(priv);
 
 	rtnl_lock();
+	netdev_lock(priv->netdev);
 	if (netif_running(priv->netdev))
 		mlx5e_close(priv->netdev);
 	netif_device_detach(priv->netdev);
+	if (priv->en_trap) {
+		mlx5e_deactivate_trap(priv);
+		mlx5e_close_trap(priv->en_trap);
+		priv->en_trap = NULL;
+	}
+	netdev_unlock(priv->netdev);
 	rtnl_unlock();
 
 	mlx5e_nic_set_rx_mode(priv);
@@ -5862,11 +5885,6 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 		mlx5e_monitor_counter_cleanup(priv);
 
 	mlx5e_disable_blocking_events(priv);
-	if (priv->en_trap) {
-		mlx5e_deactivate_trap(priv);
-		mlx5e_close_trap(priv->en_trap);
-		priv->en_trap = NULL;
-	}
 	mlx5e_disable_async_events(priv);
 	mlx5_lag_remove_netdev(mdev, priv->netdev);
 	mlx5_vxlan_reset_to_default(mdev->vxlan);
@@ -6121,7 +6139,9 @@ static void mlx5e_update_features(struct net_device *netdev)
 		return; /* features will be updated on netdev registration */
 
 	rtnl_lock();
+	netdev_lock(netdev);
 	netdev_update_features(netdev);
+	netdev_unlock(netdev);
 	rtnl_unlock();
 }
 
@@ -6132,7 +6152,7 @@ static void mlx5e_reset_channels(struct net_device *netdev)
 
 int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 {
-	const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED;
+	const bool need_lock = priv->netdev->reg_state == NETREG_REGISTERED;
 	const struct mlx5e_profile *profile = priv->profile;
 	int max_nch;
 	int err;
@@ -6174,15 +6194,19 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 	 * 2. Set our default XPS cpumask.
 	 * 3. Build the RQT.
 	 *
-	 * rtnl_lock is required by netif_set_real_num_*_queues in case the
+	 * Locking is required by netif_set_real_num_*_queues in case the
 	 * netdev has been registered by this point (if this function was called
 	 * in the reload or resume flow).
 	 */
-	if (take_rtnl)
+	if (need_lock) {
 		rtnl_lock();
+		netdev_lock(priv->netdev);
+	}
 	err = mlx5e_num_channels_changed(priv);
-	if (take_rtnl)
+	if (need_lock) {
+		netdev_unlock(priv->netdev);
 		rtnl_unlock();
+	}
 	if (err)
 		goto out;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 2abab241f03b..719aa16bd404 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -33,6 +33,7 @@
 #include <linux/dim.h>
 #include <linux/debugfs.h>
 #include <linux/mlx5/fs.h>
+#include <net/netdev_lock.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
 #include <net/act_api.h>
@@ -885,6 +886,8 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev,
 {
 	SET_NETDEV_DEV(netdev, mdev->device);
 	netdev->netdev_ops = &mlx5e_netdev_ops_rep;
+	netdev->request_ops_lock = true;
+	netdev_lockdep_set_classes(netdev);
 	eth_hw_addr_random(netdev);
 	netdev->ethtool_ops = &mlx5e_rep_ethtool_ops;
 
@@ -1344,9 +1347,11 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 	netdev->wanted_features |= NETIF_F_HW_TC;
 
 	rtnl_lock();
+	netdev_lock(netdev);
 	if (netif_running(netdev))
 		mlx5e_open(netdev);
 	udp_tunnel_nic_reset_ntf(priv->netdev);
+	netdev_unlock(netdev);
 	netif_device_attach(netdev);
 	rtnl_unlock();
 }
@@ -1356,9 +1361,11 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 
 	rtnl_lock();
+	netdev_lock(priv->netdev);
 	if (netif_running(priv->netdev))
 		mlx5e_close(priv->netdev);
 	netif_device_detach(priv->netdev);
+	netdev_unlock(priv->netdev);
 	rtnl_unlock();
 
 	mlx5e_rep_bridge_cleanup(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 5fd70b4d55be..84b1ab8233b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1684,17 +1684,17 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi,
 
 	prog = rcu_dereference(rq->xdp_prog);
 	if (prog) {
-		struct mlx5e_xdp_buff mxbuf;
+		struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 
 		net_prefetchw(va); /* xdp_frame data area */
 		mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, rq->buff.frame0_sz,
-				 cqe_bcnt, &mxbuf);
-		if (mlx5e_xdp_handle(rq, prog, &mxbuf))
+				 cqe_bcnt, mxbuf);
+		if (mlx5e_xdp_handle(rq, prog, mxbuf))
 			return NULL; /* page/packet was consumed by XDP */
 
-		rx_headroom = mxbuf.xdp.data - mxbuf.xdp.data_hard_start;
-		metasize = mxbuf.xdp.data - mxbuf.xdp.data_meta;
-		cqe_bcnt = mxbuf.xdp.data_end - mxbuf.xdp.data;
+		rx_headroom = mxbuf->xdp.data - mxbuf->xdp.data_hard_start;
+		metasize = mxbuf->xdp.data - mxbuf->xdp.data_meta;
+		cqe_bcnt = mxbuf->xdp.data_end - mxbuf->xdp.data;
 	}
 	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt, metasize);
@@ -1713,11 +1713,11 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 			     struct mlx5_cqe64 *cqe, u32 cqe_bcnt)
 {
 	struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
+	struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 	struct mlx5e_wqe_frag_info *head_wi = wi;
 	u16 rx_headroom = rq->buff.headroom;
 	struct mlx5e_frag_page *frag_page;
 	struct skb_shared_info *sinfo;
-	struct mlx5e_xdp_buff mxbuf;
 	u32 frag_consumed_bytes;
 	struct bpf_prog *prog;
 	struct sk_buff *skb;
@@ -1737,8 +1737,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 	net_prefetch(va + rx_headroom);
 
 	mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, rq->buff.frame0_sz,
-			 frag_consumed_bytes, &mxbuf);
-	sinfo = xdp_get_shared_info_from_buff(&mxbuf.xdp);
+			 frag_consumed_bytes, mxbuf);
+	sinfo = xdp_get_shared_info_from_buff(&mxbuf->xdp);
 	truesize = 0;
 
 	cqe_bcnt -= frag_consumed_bytes;
@@ -1750,8 +1750,9 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 		frag_consumed_bytes = min_t(u32, frag_info->frag_size, cqe_bcnt);
 
-		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf.xdp, frag_page,
-					       wi->offset, frag_consumed_bytes);
+		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf->xdp,
+					       frag_page, wi->offset,
+					       frag_consumed_bytes);
 		truesize += frag_info->frag_stride;
 
 		cqe_bcnt -= frag_consumed_bytes;
@@ -1760,7 +1761,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 	}
 
 	prog = rcu_dereference(rq->xdp_prog);
-	if (prog && mlx5e_xdp_handle(rq, prog, &mxbuf)) {
+	if (prog && mlx5e_xdp_handle(rq, prog, mxbuf)) {
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 			struct mlx5e_wqe_frag_info *pwi;
 
@@ -1770,21 +1771,23 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 		return NULL; /* page/packet was consumed by XDP */
 	}
 
-	skb = mlx5e_build_linear_skb(rq, mxbuf.xdp.data_hard_start, rq->buff.frame0_sz,
-				     mxbuf.xdp.data - mxbuf.xdp.data_hard_start,
-				     mxbuf.xdp.data_end - mxbuf.xdp.data,
-				     mxbuf.xdp.data - mxbuf.xdp.data_meta);
+	skb = mlx5e_build_linear_skb(
+		rq, mxbuf->xdp.data_hard_start, rq->buff.frame0_sz,
+		mxbuf->xdp.data - mxbuf->xdp.data_hard_start,
+		mxbuf->xdp.data_end - mxbuf->xdp.data,
+		mxbuf->xdp.data - mxbuf->xdp.data_meta);
 	if (unlikely(!skb))
 		return NULL;
 
 	skb_mark_for_recycle(skb);
 	head_wi->frag_page->frags++;
 
-	if (xdp_buff_has_frags(&mxbuf.xdp)) {
+	if (xdp_buff_has_frags(&mxbuf->xdp)) {
 		/* sinfo->nr_frags is reset by build_skb, calculate again. */
 		xdp_update_skb_shared_info(skb, wi - head_wi - 1,
 					   sinfo->xdp_frags_size, truesize,
-					   xdp_buff_is_frag_pfmemalloc(&mxbuf.xdp));
+					   xdp_buff_is_frag_pfmemalloc(
+						&mxbuf->xdp));
 
 		for (struct mlx5e_wqe_frag_info *pwi = head_wi + 1; pwi < wi; pwi++)
 			pwi->frag_page->frags++;
@@ -1984,10 +1987,10 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	struct mlx5e_frag_page *frag_page = &wi->alloc_units.frag_pages[page_idx];
 	u16 headlen = min_t(u16, MLX5E_RX_MAX_HEAD, cqe_bcnt);
 	struct mlx5e_frag_page *head_page = frag_page;
+	struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 	u32 frag_offset    = head_offset;
 	u32 byte_cnt       = cqe_bcnt;
 	struct skb_shared_info *sinfo;
-	struct mlx5e_xdp_buff mxbuf;
 	unsigned int truesize = 0;
 	struct bpf_prog *prog;
 	struct sk_buff *skb;
@@ -2033,9 +2036,10 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		}
 	}
 
-	mlx5e_fill_mxbuf(rq, cqe, va, linear_hr, linear_frame_sz, linear_data_len, &mxbuf);
+	mlx5e_fill_mxbuf(rq, cqe, va, linear_hr, linear_frame_sz,
+			 linear_data_len, mxbuf);
 
-	sinfo = xdp_get_shared_info_from_buff(&mxbuf.xdp);
+	sinfo = xdp_get_shared_info_from_buff(&mxbuf->xdp);
 
 	while (byte_cnt) {
 		/* Non-linear mode, hence non-XSK, which always uses PAGE_SIZE. */
@@ -2046,7 +2050,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		else
 			truesize += ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz));
 
-		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf.xdp, frag_page, frag_offset,
+		mlx5e_add_skb_shared_info_frag(rq, sinfo, &mxbuf->xdp,
+					       frag_page, frag_offset,
 					       pg_consumed_bytes);
 		byte_cnt -= pg_consumed_bytes;
 		frag_offset = 0;
@@ -2054,7 +2059,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	}
 
 	if (prog) {
-		if (mlx5e_xdp_handle(rq, prog, &mxbuf)) {
+		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 				struct mlx5e_frag_page *pfp;
 
@@ -2067,10 +2072,10 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			return NULL; /* page/packet was consumed by XDP */
 		}
 
-		skb = mlx5e_build_linear_skb(rq, mxbuf.xdp.data_hard_start,
-					     linear_frame_sz,
-					     mxbuf.xdp.data - mxbuf.xdp.data_hard_start, 0,
-					     mxbuf.xdp.data - mxbuf.xdp.data_meta);
+		skb = mlx5e_build_linear_skb(
+			rq, mxbuf->xdp.data_hard_start, linear_frame_sz,
+			mxbuf->xdp.data - mxbuf->xdp.data_hard_start, 0,
+			mxbuf->xdp.data - mxbuf->xdp.data_meta);
 		if (unlikely(!skb)) {
 			mlx5e_page_release_fragmented(rq, &wi->linear_page);
 			return NULL;
@@ -2080,13 +2085,14 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		wi->linear_page.frags++;
 		mlx5e_page_release_fragmented(rq, &wi->linear_page);
 
-		if (xdp_buff_has_frags(&mxbuf.xdp)) {
+		if (xdp_buff_has_frags(&mxbuf->xdp)) {
 			struct mlx5e_frag_page *pagep;
 
 			/* sinfo->nr_frags is reset by build_skb, calculate again. */
 			xdp_update_skb_shared_info(skb, frag_page - head_page,
 						   sinfo->xdp_frags_size, truesize,
-						   xdp_buff_is_frag_pfmemalloc(&mxbuf.xdp));
+						   xdp_buff_is_frag_pfmemalloc(
+							&mxbuf->xdp));
 
 			pagep = head_page;
 			do
@@ -2097,12 +2103,13 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	} else {
 		dma_addr_t addr;
 
-		if (xdp_buff_has_frags(&mxbuf.xdp)) {
+		if (xdp_buff_has_frags(&mxbuf->xdp)) {
 			struct mlx5e_frag_page *pagep;
 
 			xdp_update_skb_shared_info(skb, sinfo->nr_frags,
 						   sinfo->xdp_frags_size, truesize,
-						   xdp_buff_is_frag_pfmemalloc(&mxbuf.xdp));
+						   xdp_buff_is_frag_pfmemalloc(
+							&mxbuf->xdp));
 
 			pagep = frag_page - sinfo->nr_frags;
 			do
@@ -2152,20 +2159,20 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 
 	prog = rcu_dereference(rq->xdp_prog);
 	if (prog) {
-		struct mlx5e_xdp_buff mxbuf;
+		struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
 
 		net_prefetchw(va); /* xdp_frame data area */
 		mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, rq->buff.frame0_sz,
-				 cqe_bcnt, &mxbuf);
-		if (mlx5e_xdp_handle(rq, prog, &mxbuf)) {
+				 cqe_bcnt, mxbuf);
+		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
 				frag_page->frags++;
 			return NULL; /* page/packet was consumed by XDP */
 		}
 
-		rx_headroom = mxbuf.xdp.data - mxbuf.xdp.data_hard_start;
-		metasize = mxbuf.xdp.data - mxbuf.xdp.data_meta;
-		cqe_bcnt = mxbuf.xdp.data_end - mxbuf.xdp.data;
+		rx_headroom = mxbuf->xdp.data - mxbuf->xdp.data_hard_start;
+		metasize =  mxbuf->xdp.data -  mxbuf->xdp.data_meta;
+		cqe_bcnt =  mxbuf->xdp.data_end -  mxbuf->xdp.data;
 	}
 	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt, metasize);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 1c121b435016..19664fa7f217 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -2424,8 +2424,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ptp)
 	}
 	if (priv->rx_ptp_opened) {
 		for (i = 0; i < NUM_PTP_RQ_STATS; i++)
-			ethtool_sprintf(data, ptp_rq_stats_desc[i].format,
-					MLX5E_PTP_CHANNEL_IX);
+			ethtool_puts(data, ptp_rq_stats_desc[i].format);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 8de6fcbd3a03..def5dea1463d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -54,7 +54,7 @@
 #define MLX5E_DECLARE_PTP_TX_STAT(type, fld) "ptp_tx%d_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_PTP_CH_STAT(type, fld) "ptp_ch_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_PTP_CQ_STAT(type, fld) "ptp_cq%d_"#fld, offsetof(type, fld)
-#define MLX5E_DECLARE_PTP_RQ_STAT(type, fld) "ptp_rq%d_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_PTP_RQ_STAT(type, fld) "ptp_rq0_"#fld, offsetof(type, fld)
 
 #define MLX5E_DECLARE_QOS_TX_STAT(type, fld) "qos_tx%d_"#fld, offsetof(type, fld)
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9ba99609999f..f1d908f61134 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1750,9 +1750,6 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
 	    !list_is_first(&attr->list, &flow->attrs))
 		return 0;
 
-	if (flow_flag_test(flow, SLOW))
-		return 0;
-
 	esw_attr = attr->esw_attr;
 	if (!esw_attr->split_count ||
 	    esw_attr->split_count == esw_attr->out_count - 1)
@@ -1766,7 +1763,7 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
 	for (i = esw_attr->split_count; i < esw_attr->out_count; i++) {
 		/* external dest with encap is considered as internal by firmware */
 		if (esw_attr->dests[i].vport == MLX5_VPORT_UPLINK &&
-		    !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID))
+		    !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP))
 			ext_dest = true;
 		else
 			int_dest = true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 4fd853d19e31..55a8629f0792 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -337,10 +337,11 @@ static void mlx5e_sq_calc_wqe_attr(struct sk_buff *skb, const struct mlx5e_tx_at
 	};
 }
 
-static void mlx5e_tx_skb_update_hwts_flags(struct sk_buff *skb)
+static void mlx5e_tx_skb_update_ts_flags(struct sk_buff *skb)
 {
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+	skb_tx_timestamp(skb);
 }
 
 static void mlx5e_tx_check_stop(struct mlx5e_txqsq *sq)
@@ -392,7 +393,7 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | attr->opcode);
 	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | wqe_attr->ds_cnt);
 
-	mlx5e_tx_skb_update_hwts_flags(skb);
+	mlx5e_tx_skb_update_ts_flags(skb);
 
 	sq->pc += wi->num_wqebbs;
 
@@ -625,7 +626,7 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	mlx5e_dma_push(sq, txd.dma_addr, txd.len, MLX5E_DMA_MAP_SINGLE);
 	mlx5e_skb_fifo_push(&sq->db.skb_fifo, skb);
 	mlx5e_tx_mpwqe_add_dseg(sq, &txd);
-	mlx5e_tx_skb_update_hwts_flags(skb);
+	mlx5e_tx_skb_update_ts_flags(skb);
 
 	if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe))) {
 		/* Might stop the queue and affect the retval of __netdev_tx_sent_queue. */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index a6a8eea5980c..0e3a977d5332 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3533,7 +3533,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	int err;
 
 	mutex_init(&esw->offloads.termtbl_mutex);
-	mlx5_rdma_enable_roce(esw->dev);
+	err = mlx5_rdma_enable_roce(esw->dev);
+	if (err)
+		goto err_roce;
 
 	err = mlx5_esw_host_number_init(esw);
 	if (err)
@@ -3594,6 +3596,7 @@ err_vport_metadata:
 	esw_offloads_metadata_uninit(esw);
 err_metadata:
 	mlx5_rdma_disable_roce(esw->dev);
+err_roce:
 	mutex_destroy(&esw->offloads.termtbl_mutex);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index a47c29571f64..1af76da8b132 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -527,7 +527,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	struct mlx5_flow_rule *dst;
 	void *in_flow_context, *vlan;
 	void *in_match_value;
-	int reformat_id = 0;
+	u32 reformat_id = 0;
 	unsigned int inlen;
 	int dst_cnt_size;
 	u32 *in, action;
@@ -580,23 +580,21 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(flow_context, in_flow_context, action, action);
 
 	if (!extended_dest && fte->act_dests.action.pkt_reformat) {
-		struct mlx5_pkt_reformat *pkt_reformat = fte->act_dests.action.pkt_reformat;
-
-		if (pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_SW) {
-			reformat_id = mlx5_fs_dr_action_get_pkt_reformat_id(pkt_reformat);
-			if (reformat_id < 0) {
-				mlx5_core_err(dev,
-					      "Unsupported SW-owned pkt_reformat type (%d) in FW-owned table\n",
-					      pkt_reformat->reformat_type);
-				err = reformat_id;
-				goto err_out;
-			}
-		} else {
-			reformat_id = fte->act_dests.action.pkt_reformat->id;
+		struct mlx5_pkt_reformat *pkt_reformat =
+			fte->act_dests.action.pkt_reformat;
+
+		err = mlx5_fs_get_packet_reformat_id(pkt_reformat,
+						     &reformat_id);
+		if (err) {
+			mlx5_core_err(dev,
+				      "Unsupported pkt_reformat type (%d)\n",
+				      pkt_reformat->reformat_type);
+			goto err_out;
 		}
 	}
 
-	MLX5_SET(flow_context, in_flow_context, packet_reformat_id, (u32)reformat_id);
+	MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
+		 reformat_id);
 
 	if (fte->act_dests.action.modify_hdr) {
 		if (fte->act_dests.action.modify_hdr->owner == MLX5_FLOW_RESOURCE_OWNER_SW) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 6163bc98d94a..23a7e8e7adfa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1830,14 +1830,35 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft,
 	return err;
 }
 
+int mlx5_fs_get_packet_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				   u32 *id)
+{
+	switch (pkt_reformat->owner) {
+	case MLX5_FLOW_RESOURCE_OWNER_FW:
+		*id = pkt_reformat->id;
+		return 0;
+	case MLX5_FLOW_RESOURCE_OWNER_SW:
+		return mlx5_fs_dr_action_get_pkt_reformat_id(pkt_reformat, id);
+	case MLX5_FLOW_RESOURCE_OWNER_HWS:
+		return mlx5_fs_hws_action_get_pkt_reformat_id(pkt_reformat, id);
+	default:
+		return -EINVAL;
+	}
+}
+
 static bool mlx5_pkt_reformat_cmp(struct mlx5_pkt_reformat *p1,
 				  struct mlx5_pkt_reformat *p2)
 {
-	return p1->owner == p2->owner &&
-		(p1->owner == MLX5_FLOW_RESOURCE_OWNER_FW ?
-		 p1->id == p2->id :
-		 mlx5_fs_dr_action_get_pkt_reformat_id(p1) ==
-		 mlx5_fs_dr_action_get_pkt_reformat_id(p2));
+	int err1, err2;
+	u32 id1, id2;
+
+	if (p1->owner != p2->owner)
+		return false;
+
+	err1 = mlx5_fs_get_packet_reformat_id(p1, &id1);
+	err2 = mlx5_fs_get_packet_reformat_id(p2, &id2);
+
+	return !err1 && !err2 && id1 == id2;
 }
 
 static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 0767239f651c..500826229b0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -58,6 +58,7 @@ struct mlx5_flow_definer {
 enum mlx5_flow_resource_owner {
 	MLX5_FLOW_RESOURCE_OWNER_FW,
 	MLX5_FLOW_RESOURCE_OWNER_SW,
+	MLX5_FLOW_RESOURCE_OWNER_HWS,
 };
 
 struct mlx5_modify_hdr {
@@ -386,6 +387,9 @@ u32 mlx5_fs_get_capabilities(struct mlx5_core_dev *dev, enum mlx5_flow_namespace
 
 struct mlx5_flow_root_namespace *find_root(struct fs_node *node);
 
+int mlx5_fs_get_packet_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				   u32 *id);
+
 #define fs_get_obj(v, _node)  {v = container_of((_node), typeof(*v), node); }
 
 #define fs_list_for_each_entry(pos, root)		\
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 0979d672d47f..79ae3a51a4b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -32,6 +32,7 @@
 
 #include <rdma/ib_verbs.h>
 #include <linux/mlx5/fs.h>
+#include <net/netdev_lock.h>
 #include "en.h"
 #include "en/params.h"
 #include "ipoib.h"
@@ -102,6 +103,8 @@ int mlx5i_init(struct mlx5_core_dev *mdev, struct net_device *netdev)
 
 	netdev->netdev_ops = &mlx5i_netdev_ops;
 	netdev->ethtool_ops = &mlx5i_ethtool_ops;
+	netdev->request_ops_lock = true;
+	netdev_lockdep_set_classes(netdev);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 65a94e46edcf..cec18efadc73 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -643,13 +643,6 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 	int pin = -1;
 	int err = 0;
 
-	/* Reject requests with unsupported flags */
-	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-				PTP_RISING_EDGE |
-				PTP_FALLING_EDGE |
-				PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	/* Reject requests to enable time stamping on both edges. */
 	if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 	    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -820,12 +813,6 @@ static int perout_conf_npps_real_time(struct mlx5_core_dev *mdev, struct ptp_clo
 	return 0;
 }
 
-static bool mlx5_perout_verify_flags(struct mlx5_core_dev *mdev, unsigned int flags)
-{
-	return ((!mlx5_npps_real_time_supported(mdev) && flags) ||
-		(mlx5_npps_real_time_supported(mdev) && flags & ~PTP_PEROUT_DUTY_CYCLE));
-}
-
 static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 				 struct ptp_clock_request *rq,
 				 int on)
@@ -861,12 +848,6 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 		goto unlock;
 	}
 
-	/* Reject requests with unsupported flags */
-	if (mlx5_perout_verify_flags(mdev, rq->perout.flags)) {
-		err = -EOPNOTSUPP;
-		goto unlock;
-	}
-
 	if (on) {
 		pin_mode = MLX5_PIN_MODE_OUT;
 		pattern = MLX5_OUT_PATTERN_PERIODIC;
@@ -1034,6 +1015,13 @@ static void mlx5_init_pin_config(struct mlx5_core_dev *mdev)
 	clock->ptp_info.verify = mlx5_ptp_verify;
 	clock->ptp_info.pps = 1;
 
+	clock->ptp_info.supported_extts_flags = PTP_RISING_EDGE |
+						PTP_FALLING_EDGE |
+						PTP_STRICT_FLAGS;
+
+	if (mlx5_npps_real_time_supported(mdev))
+		clock->ptp_info.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE;
+
 	for (i = 0; i < clock->ptp_info.n_pins; i++) {
 		snprintf(clock->ptp_info.pin_config[i].name,
 			 sizeof(clock->ptp_info.pin_config[i].name),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
index eb3bd9c7f66e..ca9ecec358b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
@@ -637,10 +637,6 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
 	bool use_l4_type;
 	int err;
 
-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -654,7 +650,16 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	groups = use_l4_type ? &inner_ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
 			       &inner_ttc_groups[TTC_GROUPS_DEFAULT];
 
@@ -710,10 +715,6 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 	bool use_l4_type;
 	int err;
 
-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -727,7 +728,16 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	groups = use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
 			       &ttc_groups[TTC_GROUPS_DEFAULT];
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 2c5f850c31f6..40024cfa3099 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -148,7 +148,7 @@ out:
  * Free the IRQ and other resources such as rmap from the system.
  * BUT doesn't free or remove reference from mlx5.
  * This function is very important for the shutdown flow, where we need to
- * cleanup system resoruces but keep mlx5 objects alive,
+ * cleanup system resources but keep mlx5 objects alive,
  * see mlx5_irq_table_free_irqs().
  */
 static void mlx5_system_free_irq(struct mlx5_irq *irq)
@@ -588,7 +588,7 @@ static void irq_pool_free(struct mlx5_irq_pool *pool)
 	struct mlx5_irq *irq;
 	unsigned long index;
 
-	/* There are cases in which we are destrying the irq_table before
+	/* There are cases in which we are destroying the irq_table before
 	 * freeing all the IRQs, fast teardown for example. Hence, free the irqs
 	 * which might not have been freed.
 	 */
@@ -617,7 +617,7 @@ static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pcif_vec,
 	if (!mlx5_sf_max_functions(dev))
 		return 0;
 	if (sf_vec < MLX5_IRQ_VEC_COMP_BASE_SF) {
-		mlx5_core_dbg(dev, "Not enught IRQs for SFs. SF may run at lower performance\n");
+		mlx5_core_dbg(dev, "Not enough IRQs for SFs. SF may run at lower performance\n");
 		return 0;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index a42f6cd99b74..5c552b71e371 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -118,8 +118,8 @@ static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *
 
 static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
 {
+	u8 mac[ETH_ALEN] = {};
 	union ib_gid gid;
-	u8 mac[ETH_ALEN];
 
 	mlx5_rdma_make_default_gid(dev, &gid);
 	return mlx5_core_roce_gid_set(dev, 0,
@@ -140,17 +140,17 @@ void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
 	mlx5_nic_vport_disable_roce(dev);
 }
 
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
 {
 	int err;
 
 	if (!MLX5_CAP_GEN(dev, roce))
-		return;
+		return 0;
 
 	err = mlx5_nic_vport_enable_roce(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
-		return;
+		return err;
 	}
 
 	err = mlx5_rdma_add_roce_addr(dev);
@@ -165,10 +165,11 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
 		goto del_roce_addr;
 	}
 
-	return;
+	return err;
 
 del_roce_addr:
 	mlx5_rdma_del_roce_addr(dev);
 disable_roce:
 	mlx5_nic_vport_disable_roce(dev);
+	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
index 750cff2a71a4..3d9e76c3d42f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
@@ -8,12 +8,12 @@
 
 #ifdef CONFIG_MLX5_ESWITCH
 
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
 void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev);
 
 #else /* CONFIG_MLX5_ESWITCH */
 
-static inline void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) {}
+static inline int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) {}
 
 #endif /* CONFIG_MLX5_ESWITCH */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
index b5332c54d4fb..fb62f3bc4bd4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
@@ -72,6 +72,11 @@ enum mlx5hws_action_type mlx5hws_action_get_type(struct mlx5hws_action *action)
 	return action->type;
 }
 
+struct mlx5_core_dev *mlx5hws_action_get_dev(struct mlx5hws_action *action)
+{
+	return action->ctx->mdev;
+}
+
 static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 					 enum mlx5hws_context_shared_stc_type stc_type,
 					 u8 tbl_type)
@@ -238,6 +243,7 @@ hws_action_fixup_stc_attr(struct mlx5hws_context *ctx,
 			  enum mlx5hws_table_type table_type,
 			  bool is_mirror)
 {
+	struct mlx5hws_pool *pool;
 	bool use_fixup = false;
 	u32 fw_tbl_type;
 	u32 base_id;
@@ -253,13 +259,11 @@ hws_action_fixup_stc_attr(struct mlx5hws_context *ctx,
 			use_fixup = true;
 			break;
 		}
+		pool = stc_attr->ste_table.ste_pool;
 		if (!is_mirror)
-			base_id = mlx5hws_pool_chunk_get_base_id(stc_attr->ste_table.ste_pool,
-								 &stc_attr->ste_table.ste);
+			base_id = mlx5hws_pool_get_base_id(pool);
 		else
-			base_id =
-				mlx5hws_pool_chunk_get_base_mirror_id(stc_attr->ste_table.ste_pool,
-								      &stc_attr->ste_table.ste);
+			base_id = mlx5hws_pool_get_base_mirror_id(pool);
 
 		*fixup_stc_attr = *stc_attr;
 		fixup_stc_attr->ste_table.ste_obj_id = base_id;
@@ -337,7 +341,7 @@ __must_hold(&ctx->ctrl_lock)
 	if (!mlx5hws_context_cap_dynamic_reparse(ctx))
 		stc_attr->reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
 
-	obj_0_id = mlx5hws_pool_chunk_get_base_id(stc_pool, stc);
+	obj_0_id = mlx5hws_pool_get_base_id(stc_pool);
 
 	/* According to table/action limitation change the stc_attr */
 	use_fixup = hws_action_fixup_stc_attr(ctx, stc_attr, &fixup_stc_attr, table_type, false);
@@ -353,7 +357,7 @@ __must_hold(&ctx->ctrl_lock)
 	if (table_type == MLX5HWS_TABLE_TYPE_FDB) {
 		u32 obj_1_id;
 
-		obj_1_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, stc);
+		obj_1_id = mlx5hws_pool_get_base_mirror_id(stc_pool);
 
 		use_fixup = hws_action_fixup_stc_attr(ctx, stc_attr,
 						      &fixup_stc_attr,
@@ -393,11 +397,11 @@ __must_hold(&ctx->ctrl_lock)
 	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_DROP;
 	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
 	stc_attr.stc_offset = stc->offset;
-	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, stc);
+	obj_id = mlx5hws_pool_get_base_id(stc_pool);
 	mlx5hws_cmd_stc_modify(ctx->mdev, obj_id, &stc_attr);
 
 	if (table_type == MLX5HWS_TABLE_TYPE_FDB) {
-		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, stc);
+		obj_id = mlx5hws_pool_get_base_mirror_id(stc_pool);
 		mlx5hws_cmd_stc_modify(ctx->mdev, obj_id, &stc_attr);
 	}
 
@@ -1186,14 +1190,15 @@ hws_action_create_modify_header_hws(struct mlx5hws_action *action,
 				    struct mlx5hws_action_mh_pattern *pattern,
 				    u32 log_bulk_size)
 {
+	u16 num_actions, max_mh_actions = 0, hw_max_actions;
 	struct mlx5hws_context *ctx = action->ctx;
-	u16 num_actions, max_mh_actions = 0;
 	int i, ret, size_in_bytes;
 	u32 pat_id, arg_id = 0;
 	__be64 *new_pattern;
 	size_t pat_max_sz;
 
 	pat_max_sz = MLX5HWS_ARG_CHUNK_SIZE_MAX * MLX5HWS_ARG_DATA_SIZE;
+	hw_max_actions = pat_max_sz / MLX5HWS_MODIFY_ACTION_SIZE;
 	size_in_bytes = pat_max_sz * sizeof(__be64);
 	new_pattern = kcalloc(num_of_patterns, size_in_bytes, GFP_KERNEL);
 	if (!new_pattern)
@@ -1203,16 +1208,20 @@ hws_action_create_modify_header_hws(struct mlx5hws_action *action,
 	for (i = 0; i < num_of_patterns; i++) {
 		size_t new_num_actions;
 		size_t cur_num_actions;
-		u32 nope_location;
+		u32 nop_locations;
 
 		cur_num_actions = pattern[i].sz / MLX5HWS_MODIFY_ACTION_SIZE;
 
-		mlx5hws_pat_calc_nope(pattern[i].data, cur_num_actions,
-				      pat_max_sz / MLX5HWS_MODIFY_ACTION_SIZE,
-				      &new_num_actions, &nope_location,
-				      &new_pattern[i * pat_max_sz]);
+		ret = mlx5hws_pat_calc_nop(pattern[i].data, cur_num_actions,
+					   hw_max_actions, &new_num_actions,
+					   &nop_locations,
+					   &new_pattern[i * pat_max_sz]);
+		if (ret) {
+			mlx5hws_err(ctx, "Too many actions after nop insertion\n");
+			goto free_new_pat;
+		}
 
-		action[i].modify_header.nope_locations = nope_location;
+		action[i].modify_header.nop_locations = nop_locations;
 		action[i].modify_header.num_of_actions = new_num_actions;
 
 		max_mh_actions = max(max_mh_actions, new_num_actions);
@@ -1259,7 +1268,7 @@ hws_action_create_modify_header_hws(struct mlx5hws_action *action,
 				MLX5_GET(set_action_in, pattern[i].data, action_type);
 		} else {
 			/* Multiple modify actions require a pattern */
-			if (unlikely(action[i].modify_header.nope_locations)) {
+			if (unlikely(action[i].modify_header.nop_locations)) {
 				size_t pattern_sz;
 
 				pattern_sz = action[i].modify_header.num_of_actions *
@@ -1575,17 +1584,15 @@ hws_action_create_dest_match_range_definer(struct mlx5hws_context *ctx)
 	return definer;
 }
 
-static struct mlx5hws_matcher_action_ste *
+static struct mlx5hws_range_action_table *
 hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 					 struct mlx5hws_definer *definer,
 					 u32 miss_ft_id)
 {
 	struct mlx5hws_cmd_rtc_create_attr rtc_attr = {0};
-	struct mlx5hws_action_default_stc *default_stc;
-	struct mlx5hws_matcher_action_ste *table_ste;
+	struct mlx5hws_range_action_table *table_ste;
 	struct mlx5hws_pool_attr pool_attr = {0};
 	struct mlx5hws_pool *ste_pool, *stc_pool;
-	struct mlx5hws_pool_chunk *ste;
 	u32 *rtc_0_id, *rtc_1_id;
 	u32 obj_id;
 	int ret;
@@ -1604,7 +1611,6 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 
 	pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB;
 	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL;
 	pool_attr.alloc_log_sz = 1;
 	table_ste->pool = mlx5hws_pool_create(ctx, &pool_attr);
 	if (!table_ste->pool) {
@@ -1616,8 +1622,6 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 	rtc_0_id = &table_ste->rtc_0_id;
 	rtc_1_id = &table_ste->rtc_1_id;
 	ste_pool = table_ste->pool;
-	ste = &table_ste->ste;
-	ste->order = 1;
 
 	rtc_attr.log_size = 0;
 	rtc_attr.log_depth = 0;
@@ -1629,18 +1633,16 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 	rtc_attr.fw_gen_wqe = true;
 	rtc_attr.is_scnd_range = true;
 
-	obj_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
+	obj_id = mlx5hws_pool_get_base_id(ste_pool);
 
 	rtc_attr.pd = ctx->pd_num;
 	rtc_attr.ste_base = obj_id;
-	rtc_attr.ste_offset = ste->offset;
 	rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
 	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(MLX5HWS_TABLE_TYPE_FDB, false);
 
 	/* STC is a single resource (obj_id), use any STC for the ID */
 	stc_pool = ctx->stc_pool;
-	default_stc = ctx->common_res.default_stc;
-	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit);
+	obj_id = mlx5hws_pool_get_base_id(stc_pool);
 	rtc_attr.stc_base = obj_id;
 
 	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_0_id);
@@ -1650,11 +1652,11 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 	}
 
 	/* Create mirror RTC */
-	obj_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
+	obj_id = mlx5hws_pool_get_base_mirror_id(ste_pool);
 	rtc_attr.ste_base = obj_id;
 	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(MLX5HWS_TABLE_TYPE_FDB, true);
 
-	obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, &default_stc->default_hit);
+	obj_id = mlx5hws_pool_get_base_mirror_id(stc_pool);
 	rtc_attr.stc_base = obj_id;
 
 	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_1_id);
@@ -1677,9 +1679,9 @@ free_ste:
 	return NULL;
 }
 
-static void
-hws_action_destroy_dest_match_range_table(struct mlx5hws_context *ctx,
-					  struct mlx5hws_matcher_action_ste *table_ste)
+static void hws_action_destroy_dest_match_range_table(
+	struct mlx5hws_context *ctx,
+	struct mlx5hws_range_action_table *table_ste)
 {
 	mutex_lock(&ctx->ctrl_lock);
 
@@ -1691,12 +1693,11 @@ hws_action_destroy_dest_match_range_table(struct mlx5hws_context *ctx,
 	mutex_unlock(&ctx->ctrl_lock);
 }
 
-static int
-hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx,
-					      struct mlx5hws_matcher_action_ste *table_ste,
-					      struct mlx5hws_action *hit_ft_action,
-					      struct mlx5hws_definer *range_definer,
-					      u32 min, u32 max)
+static int hws_action_create_dest_match_range_fill_table(
+	struct mlx5hws_context *ctx,
+	struct mlx5hws_range_action_table *table_ste,
+	struct mlx5hws_action *hit_ft_action,
+	struct mlx5hws_definer *range_definer, u32 min, u32 max)
 {
 	struct mlx5hws_wqe_gta_data_seg_ste match_wqe_data = {0};
 	struct mlx5hws_wqe_gta_data_seg_ste range_wqe_data = {0};
@@ -1792,7 +1793,7 @@ mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx,
 				       u32 min, u32 max, u32 flags)
 {
 	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
-	struct mlx5hws_matcher_action_ste *table_ste;
+	struct mlx5hws_range_action_table *table_ste;
 	struct mlx5hws_action *hit_ft_action;
 	struct mlx5hws_definer *definer;
 	struct mlx5hws_action *action;
@@ -1837,7 +1838,6 @@ mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx,
 	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
 	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
 	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
-	stc_attr.ste_table.ste = table_ste->ste;
 	stc_attr.ste_table.ste_pool = table_ste->pool;
 	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
 
@@ -2110,21 +2110,23 @@ static void hws_action_modify_write(struct mlx5hws_send_engine *queue,
 				    u32 arg_idx,
 				    u8 *arg_data,
 				    u16 num_of_actions,
-				    u32 nope_locations)
+				    u32 nop_locations)
 {
 	u8 *new_arg_data = NULL;
 	int i, j;
 
-	if (unlikely(nope_locations)) {
+	if (unlikely(nop_locations)) {
 		new_arg_data = kcalloc(num_of_actions,
 				       MLX5HWS_MODIFY_ACTION_SIZE, GFP_KERNEL);
 		if (unlikely(!new_arg_data))
 			return;
 
-		for (i = 0, j = 0; i < num_of_actions; i++, j++) {
-			memcpy(&new_arg_data[j], arg_data, MLX5HWS_MODIFY_ACTION_SIZE);
-			if (BIT(i) & nope_locations)
+		for (i = 0, j = 0; j < num_of_actions; i++, j++) {
+			if (BIT(i) & nop_locations)
 				j++;
+			memcpy(&new_arg_data[j * MLX5HWS_MODIFY_ACTION_SIZE],
+			       &arg_data[i * MLX5HWS_MODIFY_ACTION_SIZE],
+			       MLX5HWS_MODIFY_ACTION_SIZE);
 		}
 	}
 
@@ -2220,6 +2222,7 @@ hws_action_setter_modify_header(struct mlx5hws_actions_apply_data *apply,
 	struct mlx5hws_action *action;
 	u32 arg_sz, arg_idx;
 	u8 *single_action;
+	u8 max_actions;
 	__be32 stc_idx;
 
 	rule_action = &apply->rule_action[setter->idx_double];
@@ -2247,21 +2250,23 @@ hws_action_setter_modify_header(struct mlx5hws_actions_apply_data *apply,
 
 		apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] =
 			*(__be32 *)MLX5_ADDR_OF(set_action_in, single_action, data);
-	} else {
-		/* Argument offset multiple with number of args per these actions */
-		arg_sz = mlx5hws_arg_get_arg_size(action->modify_header.max_num_of_actions);
-		arg_idx = rule_action->modify_header.offset * arg_sz;
-
-		apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
-
-		if (!(action->flags & MLX5HWS_ACTION_FLAG_SHARED)) {
-			apply->require_dep = 1;
-			hws_action_modify_write(apply->queue,
-						action->modify_header.arg_id + arg_idx,
-						rule_action->modify_header.data,
-						action->modify_header.num_of_actions,
-						action->modify_header.nope_locations);
-		}
+		return;
+	}
+
+	/* Argument offset multiple with number of args per these actions */
+	max_actions = action->modify_header.max_num_of_actions;
+	arg_sz = mlx5hws_arg_get_arg_size(max_actions);
+	arg_idx = rule_action->modify_header.offset * arg_sz;
+
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
+
+	if (!(action->flags & MLX5HWS_ACTION_FLAG_SHARED)) {
+		apply->require_dep = 1;
+		hws_action_modify_write(apply->queue,
+					action->modify_header.arg_id + arg_idx,
+					rule_action->modify_header.data,
+					action->modify_header.num_of_actions,
+					action->modify_header.nop_locations);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
index 64b76075f7f8..55a079fdd08f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
@@ -118,6 +118,12 @@ struct mlx5hws_action_template {
 	u8 only_term;
 };
 
+struct mlx5hws_range_action_table {
+	struct mlx5hws_pool *pool;
+	u32 rtc_0_id;
+	u32 rtc_1_id;
+};
+
 struct mlx5hws_action {
 	u8 type;
 	u8 flags;
@@ -130,7 +136,7 @@ struct mlx5hws_action {
 					u32 pat_id;
 					u32 arg_id;
 					__be64 single_action;
-					u32 nope_locations;
+					u32 nop_locations;
 					u8 num_of_patterns;
 					u8 single_action_type;
 					u8 num_of_actions;
@@ -186,7 +192,7 @@ struct mlx5hws_action {
 					size_t size;
 				} remove_header;
 				struct {
-					struct mlx5hws_matcher_action_ste *table_ste;
+					struct mlx5hws_range_action_table *table_ste;
 					struct mlx5hws_action *hit_ft_action;
 					struct mlx5hws_definer *definer;
 				} range;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.c
new file mode 100644
index 000000000000..5766a9c82f96
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.c
@@ -0,0 +1,467 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#include "internal.h"
+
+static const char *
+hws_pool_opt_to_str(enum mlx5hws_pool_optimize opt)
+{
+	switch (opt) {
+	case MLX5HWS_POOL_OPTIMIZE_NONE:
+		return "rx-and-tx";
+	case MLX5HWS_POOL_OPTIMIZE_ORIG:
+		return "rx-only";
+	case MLX5HWS_POOL_OPTIMIZE_MIRROR:
+		return "tx-only";
+	default:
+		return "unknown";
+	}
+}
+
+static int
+hws_action_ste_table_create_pool(struct mlx5hws_context *ctx,
+				 struct mlx5hws_action_ste_table *action_tbl,
+				 enum mlx5hws_pool_optimize opt, size_t log_sz)
+{
+	struct mlx5hws_pool_attr pool_attr = { 0 };
+
+	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
+	pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB;
+	pool_attr.flags = MLX5HWS_POOL_FLAG_BUDDY;
+	pool_attr.opt_type = opt;
+	pool_attr.alloc_log_sz = log_sz;
+
+	action_tbl->pool = mlx5hws_pool_create(ctx, &pool_attr);
+	if (!action_tbl->pool) {
+		mlx5hws_err(ctx, "Failed to allocate STE pool\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hws_action_ste_table_create_single_rtc(
+	struct mlx5hws_context *ctx,
+	struct mlx5hws_action_ste_table *action_tbl,
+	enum mlx5hws_pool_optimize opt, size_t log_sz, bool tx)
+{
+	struct mlx5hws_cmd_rtc_create_attr rtc_attr = { 0 };
+	u32 *rtc_id;
+
+	rtc_attr.log_depth = 0;
+	rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
+	/* Action STEs use the default always hit definer. */
+	rtc_attr.match_definer_0 = ctx->caps->trivial_match_definer;
+	rtc_attr.is_frst_jumbo = false;
+	rtc_attr.miss_ft_id = 0;
+	rtc_attr.pd = ctx->pd_num;
+	rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
+
+	if (tx) {
+		rtc_attr.table_type = FS_FT_FDB_TX;
+		rtc_attr.ste_base =
+			mlx5hws_pool_get_base_mirror_id(action_tbl->pool);
+		rtc_attr.stc_base =
+			mlx5hws_pool_get_base_mirror_id(ctx->stc_pool);
+		rtc_attr.log_size =
+			opt == MLX5HWS_POOL_OPTIMIZE_ORIG ? 0 : log_sz;
+		rtc_id = &action_tbl->rtc_1_id;
+	} else {
+		rtc_attr.table_type = FS_FT_FDB_RX;
+		rtc_attr.ste_base = mlx5hws_pool_get_base_id(action_tbl->pool);
+		rtc_attr.stc_base = mlx5hws_pool_get_base_id(ctx->stc_pool);
+		rtc_attr.log_size =
+			opt == MLX5HWS_POOL_OPTIMIZE_MIRROR ? 0 : log_sz;
+		rtc_id = &action_tbl->rtc_0_id;
+	}
+
+	return mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_id);
+}
+
+static int
+hws_action_ste_table_create_rtcs(struct mlx5hws_context *ctx,
+				 struct mlx5hws_action_ste_table *action_tbl,
+				 enum mlx5hws_pool_optimize opt, size_t log_sz)
+{
+	int err;
+
+	err = hws_action_ste_table_create_single_rtc(ctx, action_tbl, opt,
+						     log_sz, false);
+	if (err)
+		return err;
+
+	err = hws_action_ste_table_create_single_rtc(ctx, action_tbl, opt,
+						     log_sz, true);
+	if (err) {
+		mlx5hws_cmd_rtc_destroy(ctx->mdev, action_tbl->rtc_0_id);
+		return err;
+	}
+
+	return 0;
+}
+
+static void
+hws_action_ste_table_destroy_rtcs(struct mlx5hws_action_ste_table *action_tbl)
+{
+	mlx5hws_cmd_rtc_destroy(action_tbl->pool->ctx->mdev,
+				action_tbl->rtc_1_id);
+	mlx5hws_cmd_rtc_destroy(action_tbl->pool->ctx->mdev,
+				action_tbl->rtc_0_id);
+}
+
+static int
+hws_action_ste_table_create_stc(struct mlx5hws_context *ctx,
+				struct mlx5hws_action_ste_table *action_tbl)
+{
+	struct mlx5hws_cmd_stc_modify_attr stc_attr = { 0 };
+
+	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
+	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+	stc_attr.ste_table.ste_pool = action_tbl->pool;
+	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
+
+	return mlx5hws_action_alloc_single_stc(ctx, &stc_attr,
+					       MLX5HWS_TABLE_TYPE_FDB,
+					       &action_tbl->stc);
+}
+
+static struct mlx5hws_action_ste_table *
+hws_action_ste_table_alloc(struct mlx5hws_action_ste_pool_element *parent_elem)
+{
+	enum mlx5hws_pool_optimize opt = parent_elem->opt;
+	struct mlx5hws_context *ctx = parent_elem->ctx;
+	struct mlx5hws_action_ste_table *action_tbl;
+	size_t log_sz;
+	int err;
+
+	log_sz = min(parent_elem->log_sz ?
+			     parent_elem->log_sz +
+				     MLX5HWS_ACTION_STE_TABLE_STEP_LOG_SZ :
+				   MLX5HWS_ACTION_STE_TABLE_INIT_LOG_SZ,
+		     MLX5HWS_ACTION_STE_TABLE_MAX_LOG_SZ);
+
+	action_tbl = kzalloc(sizeof(*action_tbl), GFP_KERNEL);
+	if (!action_tbl)
+		return ERR_PTR(-ENOMEM);
+
+	err = hws_action_ste_table_create_pool(ctx, action_tbl, opt, log_sz);
+	if (err)
+		goto free_tbl;
+
+	err = hws_action_ste_table_create_rtcs(ctx, action_tbl, opt, log_sz);
+	if (err)
+		goto destroy_pool;
+
+	err = hws_action_ste_table_create_stc(ctx, action_tbl);
+	if (err)
+		goto destroy_rtcs;
+
+	action_tbl->parent_elem = parent_elem;
+	INIT_LIST_HEAD(&action_tbl->list_node);
+	action_tbl->last_used = jiffies;
+	list_add(&action_tbl->list_node, &parent_elem->available);
+	parent_elem->log_sz = log_sz;
+
+	mlx5hws_dbg(ctx,
+		    "Allocated %s action STE table log_sz %zu; STEs (%d, %d); RTCs (%d, %d); STC %d\n",
+		    hws_pool_opt_to_str(opt), log_sz,
+		    mlx5hws_pool_get_base_id(action_tbl->pool),
+		    mlx5hws_pool_get_base_mirror_id(action_tbl->pool),
+		    action_tbl->rtc_0_id, action_tbl->rtc_1_id,
+		    action_tbl->stc.offset);
+
+	return action_tbl;
+
+destroy_rtcs:
+	hws_action_ste_table_destroy_rtcs(action_tbl);
+destroy_pool:
+	mlx5hws_pool_destroy(action_tbl->pool);
+free_tbl:
+	kfree(action_tbl);
+
+	return ERR_PTR(err);
+}
+
+static void
+hws_action_ste_table_destroy(struct mlx5hws_action_ste_table *action_tbl)
+{
+	struct mlx5hws_context *ctx = action_tbl->parent_elem->ctx;
+
+	mlx5hws_dbg(ctx,
+		    "Destroying %s action STE table: STEs (%d, %d); RTCs (%d, %d); STC %d\n",
+		    hws_pool_opt_to_str(action_tbl->parent_elem->opt),
+		    mlx5hws_pool_get_base_id(action_tbl->pool),
+		    mlx5hws_pool_get_base_mirror_id(action_tbl->pool),
+		    action_tbl->rtc_0_id, action_tbl->rtc_1_id,
+		    action_tbl->stc.offset);
+
+	mlx5hws_action_free_single_stc(ctx, MLX5HWS_TABLE_TYPE_FDB,
+				       &action_tbl->stc);
+	hws_action_ste_table_destroy_rtcs(action_tbl);
+	mlx5hws_pool_destroy(action_tbl->pool);
+
+	list_del(&action_tbl->list_node);
+	kfree(action_tbl);
+}
+
+static int
+hws_action_ste_pool_element_init(struct mlx5hws_context *ctx,
+				 struct mlx5hws_action_ste_pool_element *elem,
+				 enum mlx5hws_pool_optimize opt)
+{
+	elem->ctx = ctx;
+	elem->opt = opt;
+	INIT_LIST_HEAD(&elem->available);
+	INIT_LIST_HEAD(&elem->full);
+
+	return 0;
+}
+
+static void hws_action_ste_pool_element_destroy(
+	struct mlx5hws_action_ste_pool_element *elem)
+{
+	struct mlx5hws_action_ste_table *action_tbl, *p;
+
+	/* This should be empty, but attempt to free its elements anyway. */
+	list_for_each_entry_safe(action_tbl, p, &elem->full, list_node)
+		hws_action_ste_table_destroy(action_tbl);
+
+	list_for_each_entry_safe(action_tbl, p, &elem->available, list_node)
+		hws_action_ste_table_destroy(action_tbl);
+}
+
+static int hws_action_ste_pool_init(struct mlx5hws_context *ctx,
+				    struct mlx5hws_action_ste_pool *pool)
+{
+	enum mlx5hws_pool_optimize opt;
+	int err;
+
+	mutex_init(&pool->lock);
+
+	/* Rules which are added for both RX and TX must use the same action STE
+	 * indices for both. If we were to use a single table, then RX-only and
+	 * TX-only rules would waste the unused entries. Thus, we use separate
+	 * table sets for the three cases.
+	 */
+	for (opt = MLX5HWS_POOL_OPTIMIZE_NONE; opt < MLX5HWS_POOL_OPTIMIZE_MAX;
+	     opt++) {
+		err = hws_action_ste_pool_element_init(ctx, &pool->elems[opt],
+						       opt);
+		if (err)
+			goto destroy_elems;
+		pool->elems[opt].parent_pool = pool;
+	}
+
+	return 0;
+
+destroy_elems:
+	while (opt-- > MLX5HWS_POOL_OPTIMIZE_NONE)
+		hws_action_ste_pool_element_destroy(&pool->elems[opt]);
+
+	return err;
+}
+
+static void hws_action_ste_pool_destroy(struct mlx5hws_action_ste_pool *pool)
+{
+	int opt;
+
+	for (opt = MLX5HWS_POOL_OPTIMIZE_MAX - 1;
+	     opt >= MLX5HWS_POOL_OPTIMIZE_NONE; opt--)
+		hws_action_ste_pool_element_destroy(&pool->elems[opt]);
+}
+
+static void hws_action_ste_pool_element_collect_stale(
+	struct mlx5hws_action_ste_pool_element *elem, struct list_head *cleanup)
+{
+	struct mlx5hws_action_ste_table *action_tbl, *p;
+	unsigned long expire_time, now;
+
+	expire_time = secs_to_jiffies(MLX5HWS_ACTION_STE_POOL_EXPIRE_SECONDS);
+	now = jiffies;
+
+	list_for_each_entry_safe(action_tbl, p, &elem->available, list_node) {
+		if (mlx5hws_pool_full(action_tbl->pool) &&
+		    time_before(action_tbl->last_used + expire_time, now))
+			list_move(&action_tbl->list_node, cleanup);
+	}
+}
+
+static void hws_action_ste_table_cleanup_list(struct list_head *cleanup)
+{
+	struct mlx5hws_action_ste_table *action_tbl, *p;
+
+	list_for_each_entry_safe(action_tbl, p, cleanup, list_node)
+		hws_action_ste_table_destroy(action_tbl);
+}
+
+static void hws_action_ste_pool_cleanup(struct work_struct *work)
+{
+	enum mlx5hws_pool_optimize opt;
+	struct mlx5hws_context *ctx;
+	LIST_HEAD(cleanup);
+	int i;
+
+	ctx = container_of(work, struct mlx5hws_context,
+			   action_ste_cleanup.work);
+
+	for (i = 0; i < ctx->queues; i++) {
+		struct mlx5hws_action_ste_pool *p = &ctx->action_ste_pool[i];
+
+		mutex_lock(&p->lock);
+		for (opt = MLX5HWS_POOL_OPTIMIZE_NONE;
+		     opt < MLX5HWS_POOL_OPTIMIZE_MAX; opt++)
+			hws_action_ste_pool_element_collect_stale(
+				&p->elems[opt], &cleanup);
+		mutex_unlock(&p->lock);
+	}
+
+	hws_action_ste_table_cleanup_list(&cleanup);
+
+	schedule_delayed_work(&ctx->action_ste_cleanup,
+			      secs_to_jiffies(
+				  MLX5HWS_ACTION_STE_POOL_CLEANUP_SECONDS));
+}
+
+int mlx5hws_action_ste_pool_init(struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_action_ste_pool *pool;
+	size_t queues = ctx->queues;
+	int i, err;
+
+	pool = kcalloc(queues, sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return -ENOMEM;
+
+	for (i = 0; i < queues; i++) {
+		err = hws_action_ste_pool_init(ctx, &pool[i]);
+		if (err)
+			goto free_pool;
+	}
+
+	ctx->action_ste_pool = pool;
+
+	INIT_DELAYED_WORK(&ctx->action_ste_cleanup,
+			  hws_action_ste_pool_cleanup);
+	schedule_delayed_work(
+		&ctx->action_ste_cleanup,
+		secs_to_jiffies(MLX5HWS_ACTION_STE_POOL_CLEANUP_SECONDS));
+
+	return 0;
+
+free_pool:
+	while (i--)
+		hws_action_ste_pool_destroy(&pool[i]);
+	kfree(pool);
+
+	return err;
+}
+
+void mlx5hws_action_ste_pool_uninit(struct mlx5hws_context *ctx)
+{
+	size_t queues = ctx->queues;
+	int i;
+
+	cancel_delayed_work_sync(&ctx->action_ste_cleanup);
+
+	for (i = 0; i < queues; i++)
+		hws_action_ste_pool_destroy(&ctx->action_ste_pool[i]);
+
+	kfree(ctx->action_ste_pool);
+}
+
+static struct mlx5hws_action_ste_pool_element *
+hws_action_ste_choose_elem(struct mlx5hws_action_ste_pool *pool,
+			   bool skip_rx, bool skip_tx)
+{
+	if (skip_rx)
+		return &pool->elems[MLX5HWS_POOL_OPTIMIZE_MIRROR];
+
+	if (skip_tx)
+		return &pool->elems[MLX5HWS_POOL_OPTIMIZE_ORIG];
+
+	return &pool->elems[MLX5HWS_POOL_OPTIMIZE_NONE];
+}
+
+static int
+hws_action_ste_table_chunk_alloc(struct mlx5hws_action_ste_table *action_tbl,
+				 struct mlx5hws_action_ste_chunk *chunk)
+{
+	int err;
+
+	err = mlx5hws_pool_chunk_alloc(action_tbl->pool, &chunk->ste);
+	if (err)
+		return err;
+
+	chunk->action_tbl = action_tbl;
+	action_tbl->last_used = jiffies;
+
+	return 0;
+}
+
+int mlx5hws_action_ste_chunk_alloc(struct mlx5hws_action_ste_pool *pool,
+				   bool skip_rx, bool skip_tx,
+				   struct mlx5hws_action_ste_chunk *chunk)
+{
+	struct mlx5hws_action_ste_pool_element *elem;
+	struct mlx5hws_action_ste_table *action_tbl;
+	bool found;
+	int err;
+
+	if (skip_rx && skip_tx)
+		return -EINVAL;
+
+	mutex_lock(&pool->lock);
+
+	elem = hws_action_ste_choose_elem(pool, skip_rx, skip_tx);
+
+	mlx5hws_dbg(elem->ctx,
+		    "Allocating action STEs skip_rx %d skip_tx %d order %d\n",
+		    skip_rx, skip_tx, chunk->ste.order);
+
+	found = false;
+	list_for_each_entry(action_tbl, &elem->available, list_node) {
+		if (!hws_action_ste_table_chunk_alloc(action_tbl, chunk)) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		action_tbl = hws_action_ste_table_alloc(elem);
+		if (IS_ERR(action_tbl)) {
+			err = PTR_ERR(action_tbl);
+			goto out;
+		}
+
+		err = hws_action_ste_table_chunk_alloc(action_tbl, chunk);
+		if (err)
+			goto out;
+	}
+
+	if (mlx5hws_pool_empty(action_tbl->pool))
+		list_move(&action_tbl->list_node, &elem->full);
+
+	err = 0;
+
+out:
+	mutex_unlock(&pool->lock);
+
+	return err;
+}
+
+void mlx5hws_action_ste_chunk_free(struct mlx5hws_action_ste_chunk *chunk)
+{
+	struct mutex *lock = &chunk->action_tbl->parent_elem->parent_pool->lock;
+
+	mlx5hws_dbg(chunk->action_tbl->pool->ctx,
+		    "Freeing action STEs offset %d order %d\n",
+		    chunk->ste.offset, chunk->ste.order);
+
+	mutex_lock(lock);
+	mlx5hws_pool_chunk_free(chunk->action_tbl->pool, &chunk->ste);
+	chunk->action_tbl->last_used = jiffies;
+	list_move(&chunk->action_tbl->list_node,
+		  &chunk->action_tbl->parent_elem->available);
+	mutex_unlock(lock);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.h
new file mode 100644
index 000000000000..a8ba97359e31
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action_ste_pool.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#ifndef ACTION_STE_POOL_H_
+#define ACTION_STE_POOL_H_
+
+#define MLX5HWS_ACTION_STE_TABLE_INIT_LOG_SZ 10
+#define MLX5HWS_ACTION_STE_TABLE_STEP_LOG_SZ 1
+#define MLX5HWS_ACTION_STE_TABLE_MAX_LOG_SZ 20
+
+#define MLX5HWS_ACTION_STE_POOL_CLEANUP_SECONDS 300
+#define MLX5HWS_ACTION_STE_POOL_EXPIRE_SECONDS 300
+
+struct mlx5hws_action_ste_pool_element;
+
+struct mlx5hws_action_ste_table {
+	struct mlx5hws_action_ste_pool_element *parent_elem;
+	/* Wraps the RTC and STE range for this given action. */
+	struct mlx5hws_pool *pool;
+	/* Match STEs use this STC to jump to this pool's RTC. */
+	struct mlx5hws_pool_chunk stc;
+	u32 rtc_0_id;
+	u32 rtc_1_id;
+	struct list_head list_node;
+	unsigned long last_used;
+};
+
+struct mlx5hws_action_ste_pool_element {
+	struct mlx5hws_context *ctx;
+	struct mlx5hws_action_ste_pool *parent_pool;
+	size_t log_sz;  /* Size of the largest table so far. */
+	enum mlx5hws_pool_optimize opt;
+	struct list_head available;
+	struct list_head full;
+};
+
+/* Central repository of action STEs. The context contains one of these pools
+ * per queue.
+ */
+struct mlx5hws_action_ste_pool {
+	/* Protects the entire pool. We have one pool per queue and only one
+	 * operation can be active per rule at a given time. Thus this lock
+	 * protects solely against concurrent garbage collection and we expect
+	 * very little contention.
+	 */
+	struct mutex lock;
+	struct mlx5hws_action_ste_pool_element elems[MLX5HWS_POOL_OPTIMIZE_MAX];
+};
+
+/* A chunk of STEs and the table it was allocated from. Used by rules. */
+struct mlx5hws_action_ste_chunk {
+	struct mlx5hws_action_ste_table *action_tbl;
+	struct mlx5hws_pool_chunk ste;
+};
+
+int mlx5hws_action_ste_pool_init(struct mlx5hws_context *ctx);
+
+void mlx5hws_action_ste_pool_uninit(struct mlx5hws_context *ctx);
+
+/* Callers are expected to fill chunk->ste.order. On success, this function
+ * populates chunk->tbl and chunk->ste.offset.
+ */
+int mlx5hws_action_ste_chunk_alloc(struct mlx5hws_action_ste_pool *pool,
+				   bool skip_rx, bool skip_tx,
+				   struct mlx5hws_action_ste_chunk *chunk);
+
+void mlx5hws_action_ste_chunk_free(struct mlx5hws_action_ste_chunk *chunk);
+
+#endif /* ACTION_STE_POOL_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
index 19dce1ba512d..9e057f808ea5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
@@ -46,10 +46,14 @@ static void hws_bwc_unlock_all_queues(struct mlx5hws_context *ctx)
 	}
 }
 
-static void hws_bwc_matcher_init_attr(struct mlx5hws_matcher_attr *attr,
+static void hws_bwc_matcher_init_attr(struct mlx5hws_bwc_matcher *bwc_matcher,
 				      u32 priority,
-				      u8 size_log)
+				      u8 size_log,
+				      struct mlx5hws_matcher_attr *attr)
 {
+	struct mlx5hws_bwc_matcher *first_matcher =
+		bwc_matcher->complex_first_bwc_matcher;
+
 	memset(attr, 0, sizeof(*attr));
 
 	attr->priority = priority;
@@ -61,6 +65,9 @@ static void hws_bwc_matcher_init_attr(struct mlx5hws_matcher_attr *attr,
 	attr->rule.num_log = size_log;
 	attr->resizable = true;
 	attr->max_num_of_at_attach = MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM;
+
+	attr->isolated_matcher_end_ft_id =
+		first_matcher ? first_matcher->matcher->end_ft_id : 0;
 }
 
 int mlx5hws_bwc_matcher_create_simple(struct mlx5hws_bwc_matcher *bwc_matcher,
@@ -83,20 +90,27 @@ int mlx5hws_bwc_matcher_create_simple(struct mlx5hws_bwc_matcher *bwc_matcher,
 	for (i = 0; i < bwc_queues; i++)
 		INIT_LIST_HEAD(&bwc_matcher->rules[i]);
 
-	hws_bwc_matcher_init_attr(&attr,
+	hws_bwc_matcher_init_attr(bwc_matcher,
 				  priority,
-				  MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG);
+				  MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG,
+				  &attr);
 
 	bwc_matcher->priority = priority;
 	bwc_matcher->size_log = MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG;
 
+	bwc_matcher->size_of_at_array = MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM;
+	bwc_matcher->at = kcalloc(bwc_matcher->size_of_at_array,
+				  sizeof(*bwc_matcher->at), GFP_KERNEL);
+	if (!bwc_matcher->at)
+		goto free_bwc_matcher_rules;
+
 	/* create dummy action template */
 	bwc_matcher->at[0] =
 		mlx5hws_action_template_create(action_types ?
 					       action_types : init_action_types);
 	if (!bwc_matcher->at[0]) {
 		mlx5hws_err(table->ctx, "BWC matcher: failed creating action template\n");
-		goto free_bwc_matcher_rules;
+		goto free_bwc_matcher_at_array;
 	}
 
 	bwc_matcher->num_of_at = 1;
@@ -126,6 +140,8 @@ free_mt:
 	mlx5hws_match_template_destroy(bwc_matcher->mt);
 free_at:
 	mlx5hws_action_template_destroy(bwc_matcher->at[0]);
+free_bwc_matcher_at_array:
+	kfree(bwc_matcher->at);
 free_bwc_matcher_rules:
 	kfree(bwc_matcher->rules);
 err:
@@ -153,6 +169,7 @@ mlx5hws_bwc_matcher_create(struct mlx5hws_table *table,
 		return NULL;
 
 	atomic_set(&bwc_matcher->num_of_rules, 0);
+	atomic_set(&bwc_matcher->rehash_required, false);
 
 	/* Check if the required match params can be all matched
 	 * in single STE, otherwise complex matcher is needed.
@@ -192,6 +209,7 @@ int mlx5hws_bwc_matcher_destroy_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 
 	for (i = 0; i < bwc_matcher->num_of_at; i++)
 		mlx5hws_action_template_destroy(bwc_matcher->at[i]);
+	kfree(bwc_matcher->at);
 
 	mlx5hws_match_template_destroy(bwc_matcher->mt);
 	kfree(bwc_matcher->rules);
@@ -208,16 +226,19 @@ int mlx5hws_bwc_matcher_destroy(struct mlx5hws_bwc_matcher *bwc_matcher)
 			    "BWC matcher destroy: matcher still has %d rules\n",
 			    num_of_rules);
 
-	mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
+	if (bwc_matcher->complex)
+		mlx5hws_bwc_matcher_destroy_complex(bwc_matcher);
+	else
+		mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
 
 	kfree(bwc_matcher);
 	return 0;
 }
 
-static int hws_bwc_queue_poll(struct mlx5hws_context *ctx,
-			      u16 queue_id,
-			      u32 *pending_rules,
-			      bool drain)
+int mlx5hws_bwc_queue_poll(struct mlx5hws_context *ctx,
+			   u16 queue_id,
+			   u32 *pending_rules,
+			   bool drain)
 {
 	unsigned long timeout = jiffies +
 				secs_to_jiffies(MLX5HWS_BWC_POLLING_TIMEOUT);
@@ -320,16 +341,12 @@ static void hws_bwc_rule_list_add(struct mlx5hws_bwc_rule *bwc_rule, u16 idx)
 {
 	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
 
-	atomic_inc(&bwc_matcher->num_of_rules);
 	bwc_rule->bwc_queue_idx = idx;
 	list_add(&bwc_rule->list_node, &bwc_matcher->rules[idx]);
 }
 
 static void hws_bwc_rule_list_remove(struct mlx5hws_bwc_rule *bwc_rule)
 {
-	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
-
-	atomic_dec(&bwc_matcher->num_of_rules);
 	list_del_init(&bwc_rule->list_node);
 }
 
@@ -352,7 +369,8 @@ hws_bwc_rule_destroy_hws_sync(struct mlx5hws_bwc_rule *bwc_rule,
 	if (unlikely(ret))
 		return ret;
 
-	ret = hws_bwc_queue_poll(ctx, rule_attr->queue_id, &expected_completions, true);
+	ret = mlx5hws_bwc_queue_poll(ctx, rule_attr->queue_id,
+				     &expected_completions, true);
 	if (unlikely(ret))
 		return ret;
 
@@ -382,6 +400,7 @@ int mlx5hws_bwc_rule_destroy_simple(struct mlx5hws_bwc_rule *bwc_rule)
 	mutex_lock(queue_lock);
 
 	ret = hws_bwc_rule_destroy_hws_sync(bwc_rule, &attr);
+	atomic_dec(&bwc_matcher->num_of_rules);
 	hws_bwc_rule_list_remove(bwc_rule);
 
 	mutex_unlock(queue_lock);
@@ -391,9 +410,13 @@ int mlx5hws_bwc_rule_destroy_simple(struct mlx5hws_bwc_rule *bwc_rule)
 
 int mlx5hws_bwc_rule_destroy(struct mlx5hws_bwc_rule *bwc_rule)
 {
-	int ret;
+	bool is_complex = !!bwc_rule->bwc_matcher->complex;
+	int ret = 0;
 
-	ret = mlx5hws_bwc_rule_destroy_simple(bwc_rule);
+	if (is_complex)
+		ret = mlx5hws_bwc_rule_destroy_complex(bwc_rule);
+	else
+		ret = mlx5hws_bwc_rule_destroy_simple(bwc_rule);
 
 	mlx5hws_bwc_rule_free(bwc_rule);
 	return ret;
@@ -433,9 +456,8 @@ hws_bwc_rule_create_sync(struct mlx5hws_bwc_rule *bwc_rule,
 	if (unlikely(ret))
 		return ret;
 
-	ret = hws_bwc_queue_poll(ctx, rule_attr->queue_id, &expected_completions, true);
-
-	return ret;
+	return mlx5hws_bwc_queue_poll(ctx, rule_attr->queue_id,
+				      &expected_completions, true);
 }
 
 static int
@@ -456,7 +478,8 @@ hws_bwc_rule_update_sync(struct mlx5hws_bwc_rule *bwc_rule,
 	if (unlikely(ret))
 		return ret;
 
-	ret = hws_bwc_queue_poll(ctx, rule_attr->queue_id, &expected_completions, true);
+	ret = mlx5hws_bwc_queue_poll(ctx, rule_attr->queue_id,
+				     &expected_completions, true);
 	if (unlikely(ret))
 		mlx5hws_err(ctx, "Failed updating BWC rule (%d)\n", ret);
 
@@ -469,21 +492,9 @@ hws_bwc_matcher_size_maxed_out(struct mlx5hws_bwc_matcher *bwc_matcher)
 	struct mlx5hws_cmd_query_caps *caps = bwc_matcher->matcher->tbl->ctx->caps;
 
 	/* check the match RTC size */
-	if ((bwc_matcher->size_log +
-	     MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH +
-	     MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP) >
-	    (caps->ste_alloc_log_max - 1))
-		return true;
-
-	/* check the action RTC size */
-	if ((bwc_matcher->size_log +
-	     MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP +
-	     ilog2(roundup_pow_of_two(bwc_matcher->matcher->action_ste.max_stes)) +
-	     MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT) >
-	    (caps->ste_alloc_log_max - 1))
-		return true;
-
-	return false;
+	return (bwc_matcher->size_log + MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH +
+		MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP) >
+	       (caps->ste_alloc_log_max - 1);
 }
 
 static bool
@@ -520,6 +531,23 @@ hws_bwc_matcher_extend_at(struct mlx5hws_bwc_matcher *bwc_matcher,
 			  struct mlx5hws_rule_action rule_actions[])
 {
 	enum mlx5hws_action_type action_types[MLX5HWS_BWC_MAX_ACTS];
+	void *p;
+
+	if (unlikely(bwc_matcher->num_of_at >= bwc_matcher->size_of_at_array)) {
+		if (bwc_matcher->size_of_at_array >= MLX5HWS_MATCHER_MAX_AT)
+			return -ENOMEM;
+		bwc_matcher->size_of_at_array *= 2;
+		p = krealloc(bwc_matcher->at,
+			     bwc_matcher->size_of_at_array *
+				     sizeof(*bwc_matcher->at),
+			     __GFP_ZERO | GFP_KERNEL);
+		if (!p) {
+			bwc_matcher->size_of_at_array /= 2;
+			return -ENOMEM;
+		}
+
+		bwc_matcher->at = p;
+	}
 
 	hws_bwc_rule_actions_to_action_types(rule_actions, action_types);
 
@@ -582,100 +610,79 @@ hws_bwc_matcher_find_at(struct mlx5hws_bwc_matcher *bwc_matcher,
 
 static int hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
+	bool move_error = false, poll_error = false, drain_error = false;
 	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_matcher *matcher = bwc_matcher->matcher;
 	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
-	struct mlx5hws_bwc_rule **bwc_rules;
 	struct mlx5hws_rule_attr rule_attr;
-	u32 *pending_rules;
-	int i, j, ret = 0;
-	bool all_done;
-	u16 burst_th;
+	struct mlx5hws_bwc_rule *bwc_rule;
+	struct mlx5hws_send_engine *queue;
+	struct list_head *rules_list;
+	u32 pending_rules;
+	int i, ret = 0;
 
 	mlx5hws_bwc_rule_fill_attr(bwc_matcher, 0, 0, &rule_attr);
 
-	pending_rules = kcalloc(bwc_queues, sizeof(*pending_rules), GFP_KERNEL);
-	if (!pending_rules)
-		return -ENOMEM;
-
-	bwc_rules = kcalloc(bwc_queues, sizeof(*bwc_rules), GFP_KERNEL);
-	if (!bwc_rules) {
-		ret = -ENOMEM;
-		goto free_pending_rules;
-	}
-
 	for (i = 0; i < bwc_queues; i++) {
 		if (list_empty(&bwc_matcher->rules[i]))
-			bwc_rules[i] = NULL;
-		else
-			bwc_rules[i] = list_first_entry(&bwc_matcher->rules[i],
-							struct mlx5hws_bwc_rule,
-							list_node);
-	}
-
-	do {
-		all_done = true;
+			continue;
 
-		for (i = 0; i < bwc_queues; i++) {
-			rule_attr.queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
-			burst_th = hws_bwc_get_burst_th(ctx, rule_attr.queue_id);
+		pending_rules = 0;
+		rule_attr.queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
+		rules_list = &bwc_matcher->rules[i];
 
-			for (j = 0; j < burst_th && bwc_rules[i]; j++) {
-				rule_attr.burst = !!((j + 1) % burst_th);
-				ret = mlx5hws_matcher_resize_rule_move(bwc_matcher->matcher,
-								       bwc_rules[i]->rule,
-								       &rule_attr);
-				if (unlikely(ret)) {
-					mlx5hws_err(ctx,
-						    "Moving BWC rule failed during rehash (%d)\n",
-						    ret);
-					goto free_bwc_rules;
-				}
-
-				all_done = false;
-				pending_rules[i]++;
-				bwc_rules[i] = list_is_last(&bwc_rules[i]->list_node,
-							    &bwc_matcher->rules[i]) ?
-					       NULL : list_next_entry(bwc_rules[i], list_node);
+		list_for_each_entry(bwc_rule, rules_list, list_node) {
+			ret = mlx5hws_matcher_resize_rule_move(matcher,
+							       bwc_rule->rule,
+							       &rule_attr);
+			if (unlikely(ret && !move_error)) {
+				mlx5hws_err(ctx,
+					    "Moving BWC rule: move failed (%d), attempting to move rest of the rules\n",
+					    ret);
+				move_error = true;
+			}
 
-				ret = hws_bwc_queue_poll(ctx, rule_attr.queue_id,
-							 &pending_rules[i], false);
-				if (unlikely(ret)) {
-					mlx5hws_err(ctx,
-						    "Moving BWC rule failed during rehash (%d)\n",
-						    ret);
-					goto free_bwc_rules;
-				}
+			pending_rules++;
+			ret = mlx5hws_bwc_queue_poll(ctx,
+						     rule_attr.queue_id,
+						     &pending_rules,
+						     false);
+			if (unlikely(ret && !poll_error)) {
+				mlx5hws_err(ctx,
+					    "Moving BWC rule: poll failed (%d), attempting to move rest of the rules\n",
+					    ret);
+				poll_error = true;
 			}
 		}
-	} while (!all_done);
 
-	/* drain all the bwc queues */
-	for (i = 0; i < bwc_queues; i++) {
-		if (pending_rules[i]) {
-			u16 queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
-
-			mlx5hws_send_engine_flush_queue(&ctx->send_queue[queue_id]);
-			ret = hws_bwc_queue_poll(ctx, queue_id,
-						 &pending_rules[i], true);
-			if (unlikely(ret)) {
+		if (pending_rules) {
+			queue = &ctx->send_queue[rule_attr.queue_id];
+			mlx5hws_send_engine_flush_queue(queue);
+			ret = mlx5hws_bwc_queue_poll(ctx,
+						     rule_attr.queue_id,
+						     &pending_rules,
+						     true);
+			if (unlikely(ret && !drain_error)) {
 				mlx5hws_err(ctx,
-					    "Moving BWC rule failed during rehash (%d)\n", ret);
-				goto free_bwc_rules;
+					    "Moving BWC rule: drain failed (%d), attempting to move rest of the rules\n",
+					    ret);
+				drain_error = true;
 			}
 		}
 	}
 
-free_bwc_rules:
-	kfree(bwc_rules);
-free_pending_rules:
-	kfree(pending_rules);
+	if (move_error || poll_error || drain_error)
+		ret = -EINVAL;
 
 	return ret;
 }
 
 static int hws_bwc_matcher_move_all(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	return hws_bwc_matcher_move_all_simple(bwc_matcher);
+	if (!bwc_matcher->complex)
+		return hws_bwc_matcher_move_all_simple(bwc_matcher);
+
+	return mlx5hws_bwc_matcher_move_all_complex(bwc_matcher);
 }
 
 static int hws_bwc_matcher_move(struct mlx5hws_bwc_matcher *bwc_matcher)
@@ -686,9 +693,10 @@ static int hws_bwc_matcher_move(struct mlx5hws_bwc_matcher *bwc_matcher)
 	struct mlx5hws_matcher *new_matcher;
 	int ret;
 
-	hws_bwc_matcher_init_attr(&matcher_attr,
+	hws_bwc_matcher_init_attr(bwc_matcher,
 				  bwc_matcher->priority,
-				  bwc_matcher->size_log);
+				  bwc_matcher->size_log,
+				  &matcher_attr);
 
 	old_matcher = bwc_matcher->matcher;
 	new_matcher = mlx5hws_matcher_create(old_matcher->tbl,
@@ -708,15 +716,18 @@ static int hws_bwc_matcher_move(struct mlx5hws_bwc_matcher *bwc_matcher)
 	}
 
 	ret = hws_bwc_matcher_move_all(bwc_matcher);
-	if (ret) {
-		mlx5hws_err(ctx, "Rehash error: moving rules failed\n");
-		return -ENOMEM;
-	}
+	if (ret)
+		mlx5hws_err(ctx, "Rehash error: moving rules failed, attempting to remove the old matcher\n");
+
+	/* Error during rehash can't be rolled back.
+	 * The best option here is to allow the rehash to complete and remove
+	 * the old matcher - can't leave the matcher in the 'in_resize' state.
+	 */
 
 	bwc_matcher->matcher = new_matcher;
 	mlx5hws_matcher_destroy(old_matcher);
 
-	return 0;
+	return ret;
 }
 
 static int
@@ -733,9 +744,9 @@ hws_bwc_matcher_rehash_size(struct mlx5hws_bwc_matcher *bwc_matcher)
 
 	/* It is possible that other rule has already performed rehash.
 	 * Need to check again if we really need rehash.
-	 * If the reason for rehash was size, but not any more - skip rehash.
 	 */
-	if (!hws_bwc_matcher_rehash_size_needed(bwc_matcher,
+	if (!atomic_read(&bwc_matcher->rehash_required) &&
+	    !hws_bwc_matcher_rehash_size_needed(bwc_matcher,
 						atomic_read(&bwc_matcher->num_of_rules)))
 		return 0;
 
@@ -746,6 +757,8 @@ hws_bwc_matcher_rehash_size(struct mlx5hws_bwc_matcher *bwc_matcher)
 	 *  - destroy the old matcher
 	 */
 
+	atomic_set(&bwc_matcher->rehash_required, false);
+
 	ret = hws_bwc_matcher_extend_size(bwc_matcher);
 	if (ret)
 		return ret;
@@ -753,17 +766,51 @@ hws_bwc_matcher_rehash_size(struct mlx5hws_bwc_matcher *bwc_matcher)
 	return hws_bwc_matcher_move(bwc_matcher);
 }
 
-static int
-hws_bwc_matcher_rehash_at(struct mlx5hws_bwc_matcher *bwc_matcher)
+static int hws_bwc_rule_get_at_idx(struct mlx5hws_bwc_rule *bwc_rule,
+				   struct mlx5hws_rule_action rule_actions[],
+				   u16 bwc_queue_idx)
 {
-	/* Rehash by action template doesn't require any additional checking.
-	 * The bwc_matcher already contains the new action template.
-	 * Just do the usual rehash:
-	 *  - create new matcher
-	 *  - move all the rules to the new matcher
-	 *  - destroy the old matcher
-	 */
-	return hws_bwc_matcher_move(bwc_matcher);
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mutex *queue_lock; /* Protect the queue */
+	int at_idx, ret;
+
+	/* check if rehash needed due to missing action template */
+	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	if (likely(at_idx >= 0))
+		return at_idx;
+
+	/* we need to extend BWC matcher action templates array */
+	queue_lock = hws_bwc_get_queue_lock(ctx, bwc_queue_idx);
+	mutex_unlock(queue_lock);
+	hws_bwc_lock_all_queues(ctx);
+
+	/* check again - perhaps other thread already did extend_at */
+	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	if (at_idx >= 0)
+		goto out;
+
+	ret = hws_bwc_matcher_extend_at(bwc_matcher, rule_actions);
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx, "BWC rule: failed extending AT (%d)", ret);
+		at_idx = -EINVAL;
+		goto out;
+	}
+
+	/* action templates array was extended, we need the last idx */
+	at_idx = bwc_matcher->num_of_at - 1;
+	ret = mlx5hws_matcher_attach_at(bwc_matcher->matcher,
+					bwc_matcher->at[at_idx]);
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx, "BWC rule: failed attaching new AT (%d)", ret);
+		at_idx = -EINVAL;
+		goto out;
+	}
+
+out:
+	hws_bwc_unlock_all_queues(ctx);
+	mutex_lock(queue_lock);
+	return at_idx;
 }
 
 int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
@@ -786,50 +833,16 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 
 	mutex_lock(queue_lock);
 
-	/* check if rehash needed due to missing action template */
-	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	at_idx = hws_bwc_rule_get_at_idx(bwc_rule, rule_actions, bwc_queue_idx);
 	if (unlikely(at_idx < 0)) {
-		/* we need to extend BWC matcher action templates array */
 		mutex_unlock(queue_lock);
-		hws_bwc_lock_all_queues(ctx);
-
-		ret = hws_bwc_matcher_extend_at(bwc_matcher, rule_actions);
-		if (unlikely(ret)) {
-			hws_bwc_unlock_all_queues(ctx);
-			return ret;
-		}
-
-		/* action templates array was extended, we need the last idx */
-		at_idx = bwc_matcher->num_of_at - 1;
-
-		ret = mlx5hws_matcher_attach_at(bwc_matcher->matcher,
-						bwc_matcher->at[at_idx]);
-		if (unlikely(ret)) {
-			/* Action template attach failed, possibly due to
-			 * requiring more action STEs.
-			 * Need to attempt creating new matcher with all
-			 * the action templates, including the new one.
-			 */
-			ret = hws_bwc_matcher_rehash_at(bwc_matcher);
-			if (unlikely(ret)) {
-				mlx5hws_action_template_destroy(bwc_matcher->at[at_idx]);
-				bwc_matcher->at[at_idx] = NULL;
-				bwc_matcher->num_of_at--;
-
-				hws_bwc_unlock_all_queues(ctx);
-
-				mlx5hws_err(ctx,
-					    "BWC rule insertion: rehash AT failed (%d)\n", ret);
-				return ret;
-			}
-		}
-
-		hws_bwc_unlock_all_queues(ctx);
-		mutex_lock(queue_lock);
+		mlx5hws_err(ctx, "BWC rule create: failed getting AT (%d)",
+			    ret);
+		return -EINVAL;
 	}
 
 	/* check if number of rules require rehash */
-	num_of_rules = atomic_read(&bwc_matcher->num_of_rules);
+	num_of_rules = atomic_inc_return(&bwc_matcher->num_of_rules);
 
 	if (unlikely(hws_bwc_matcher_rehash_size_needed(bwc_matcher, num_of_rules))) {
 		mutex_unlock(queue_lock);
@@ -843,6 +856,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 				    bwc_matcher->size_log - MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP,
 				    bwc_matcher->size_log,
 				    ret);
+			atomic_dec(&bwc_matcher->num_of_rules);
 			return ret;
 		}
 
@@ -867,6 +881,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 	 * Try rehash by size and insert rule again - last chance.
 	 */
 
+	atomic_set(&bwc_matcher->rehash_required, true);
 	mutex_unlock(queue_lock);
 
 	hws_bwc_lock_all_queues(ctx);
@@ -875,6 +890,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 
 	if (ret) {
 		mlx5hws_err(ctx, "BWC rule insertion: rehash failed (%d)\n", ret);
+		atomic_dec(&bwc_matcher->num_of_rules);
 		return ret;
 	}
 
@@ -890,6 +906,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 	if (unlikely(ret)) {
 		mutex_unlock(queue_lock);
 		mlx5hws_err(ctx, "BWC rule insertion failed (%d)\n", ret);
+		atomic_dec(&bwc_matcher->num_of_rules);
 		return ret;
 	}
 
@@ -921,11 +938,18 @@ mlx5hws_bwc_rule_create(struct mlx5hws_bwc_matcher *bwc_matcher,
 
 	bwc_queue_idx = hws_bwc_gen_queue_idx(ctx);
 
-	ret = mlx5hws_bwc_rule_create_simple(bwc_rule,
-					     params->match_buf,
-					     rule_actions,
-					     flow_source,
-					     bwc_queue_idx);
+	if (bwc_matcher->complex)
+		ret = mlx5hws_bwc_rule_create_complex(bwc_rule,
+						      params,
+						      flow_source,
+						      rule_actions,
+						      bwc_queue_idx);
+	else
+		ret = mlx5hws_bwc_rule_create_simple(bwc_rule,
+						     params->match_buf,
+						     rule_actions,
+						     flow_source,
+						     bwc_queue_idx);
 	if (unlikely(ret)) {
 		mlx5hws_bwc_rule_free(bwc_rule);
 		return NULL;
@@ -952,52 +976,11 @@ hws_bwc_rule_action_update(struct mlx5hws_bwc_rule *bwc_rule,
 
 	mutex_lock(queue_lock);
 
-	/* check if rehash needed due to missing action template */
-	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	at_idx = hws_bwc_rule_get_at_idx(bwc_rule, rule_actions, idx);
 	if (unlikely(at_idx < 0)) {
-		/* we need to extend BWC matcher action templates array */
 		mutex_unlock(queue_lock);
-		hws_bwc_lock_all_queues(ctx);
-
-		/* check again - perhaps other thread already did extend_at */
-		at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
-		if (likely(at_idx < 0)) {
-			ret = hws_bwc_matcher_extend_at(bwc_matcher, rule_actions);
-			if (unlikely(ret)) {
-				hws_bwc_unlock_all_queues(ctx);
-				mlx5hws_err(ctx, "BWC rule update: failed extending AT (%d)", ret);
-				return -EINVAL;
-			}
-
-			/* action templates array was extended, we need the last idx */
-			at_idx = bwc_matcher->num_of_at - 1;
-
-			ret = mlx5hws_matcher_attach_at(bwc_matcher->matcher,
-							bwc_matcher->at[at_idx]);
-			if (unlikely(ret)) {
-				/* Action template attach failed, possibly due to
-				 * requiring more action STEs.
-				 * Need to attempt creating new matcher with all
-				 * the action templates, including the new one.
-				 */
-				ret = hws_bwc_matcher_rehash_at(bwc_matcher);
-				if (unlikely(ret)) {
-					mlx5hws_action_template_destroy(bwc_matcher->at[at_idx]);
-					bwc_matcher->at[at_idx] = NULL;
-					bwc_matcher->num_of_at--;
-
-					hws_bwc_unlock_all_queues(ctx);
-
-					mlx5hws_err(ctx,
-						    "BWC rule update: rehash AT failed (%d)\n",
-						    ret);
-					return ret;
-				}
-			}
-		}
-
-		hws_bwc_unlock_all_queues(ctx);
-		mutex_lock(queue_lock);
+		mlx5hws_err(ctx, "BWC rule update: failed getting AT\n");
+		return -EINVAL;
 	}
 
 	ret = hws_bwc_rule_update_sync(bwc_rule,
@@ -1023,5 +1006,10 @@ int mlx5hws_bwc_rule_action_update(struct mlx5hws_bwc_rule *bwc_rule,
 		return -EINVAL;
 	}
 
-	return hws_bwc_rule_action_update(bwc_rule, rule_actions);
+	/* For complex rule, the update should happen on the second matcher */
+	if (bwc_rule->isolated_bwc_rule)
+		return hws_bwc_rule_action_update(bwc_rule->isolated_bwc_rule,
+						  rule_actions);
+	else
+		return hws_bwc_rule_action_update(bwc_rule, rule_actions);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
index 47f7ed141553..d21fc247a510 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
@@ -10,9 +10,7 @@
 #define MLX5HWS_BWC_MATCHER_REHASH_BURST_TH 32
 
 /* Max number of AT attach operations for the same matcher.
- * When the limit is reached, next attempt to attach new AT
- * will result in creation of a new matcher and moving all
- * the rules to this matcher.
+ * When the limit is reached, a larger buffer is allocated for the ATs.
  */
 #define MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM 8
 
@@ -20,20 +18,27 @@
 
 #define MLX5HWS_BWC_POLLING_TIMEOUT 60
 
+struct mlx5hws_bwc_matcher_complex_data;
 struct mlx5hws_bwc_matcher {
 	struct mlx5hws_matcher *matcher;
 	struct mlx5hws_match_template *mt;
-	struct mlx5hws_action_template *at[MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM];
-	u32 priority;
+	struct mlx5hws_action_template **at;
+	struct mlx5hws_bwc_matcher_complex_data *complex;
+	struct mlx5hws_bwc_matcher *complex_first_bwc_matcher;
 	u8 num_of_at;
+	u8 size_of_at_array;
 	u8 size_log;
+	u32 priority;
 	atomic_t num_of_rules;
+	atomic_t rehash_required;
 	struct list_head *rules;
 };
 
 struct mlx5hws_bwc_rule {
 	struct mlx5hws_bwc_matcher *bwc_matcher;
 	struct mlx5hws_rule *rule;
+	struct mlx5hws_bwc_rule *isolated_bwc_rule;
+	struct mlx5hws_bwc_complex_rule_hash_node *complex_hash_node;
 	u16 bwc_queue_idx;
 	struct list_head list_node;
 };
@@ -65,6 +70,11 @@ void mlx5hws_bwc_rule_fill_attr(struct mlx5hws_bwc_matcher *bwc_matcher,
 				u32 flow_source,
 				struct mlx5hws_rule_attr *rule_attr);
 
+int mlx5hws_bwc_queue_poll(struct mlx5hws_context *ctx,
+			   u16 queue_id,
+			   u32 *pending_rules,
+			   bool drain);
+
 static inline u16 mlx5hws_bwc_queues(struct mlx5hws_context *ctx)
 {
 	/* Besides the control queue, half of the queues are
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
index 9fb059a6511f..5d30c5b094fc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
@@ -3,6 +3,22 @@
 
 #include "internal.h"
 
+#define HWS_CLEAR_MATCH_PARAM(mask, field) \
+	MLX5_SET(fte_match_param, (mask)->match_buf, field, 0)
+
+#define HWS_SZ_MATCH_PARAM (MLX5_ST_SZ_DW_MATCH_PARAM * 4)
+
+static const struct rhashtable_params hws_refcount_hash = {
+	.key_len = sizeof_field(struct mlx5hws_bwc_complex_rule_hash_node,
+				match_buf),
+	.key_offset = offsetof(struct mlx5hws_bwc_complex_rule_hash_node,
+			       match_buf),
+	.head_offset = offsetof(struct mlx5hws_bwc_complex_rule_hash_node,
+				hash_node),
+	.automatic_shrinking = true,
+	.min_size = 1,
+};
+
 bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
 					 u8 match_criteria_enable,
 					 struct mlx5hws_match_parameters *mask)
@@ -48,20 +64,1078 @@ bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
 	return is_complex;
 }
 
+static void
+hws_bwc_matcher_complex_params_clear_fld(struct mlx5hws_context *ctx,
+					 enum mlx5hws_definer_fname fname,
+					 struct mlx5hws_match_parameters *mask)
+{
+	struct mlx5hws_cmd_query_caps *caps = ctx->caps;
+
+	switch (fname) {
+	case MLX5HWS_DEFINER_FNAME_ETH_TYPE_O:
+	case MLX5HWS_DEFINER_FNAME_ETH_TYPE_I:
+	case MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_O:
+	case MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_I:
+	case MLX5HWS_DEFINER_FNAME_IP_VERSION_O:
+	case MLX5HWS_DEFINER_FNAME_IP_VERSION_I:
+		/* Because of the strict requirements for IP address matching
+		 * that require ethtype/ip_version matching as well, don't clear
+		 * these fields - have them in both parts of the complex matcher
+		 */
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.smac_47_16);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.smac_47_16);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.smac_15_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.smac_15_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.dmac_47_16);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.dmac_47_16);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.dmac_15_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.dmac_15_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_TYPE_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.cvlan_tag);
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.svlan_tag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_TYPE_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.cvlan_tag);
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.svlan_tag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_FIRST_PRIO_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.first_prio);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_FIRST_PRIO_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.first_prio);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_CFI_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.first_cfi);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_CFI_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.first_cfi);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_ID_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.first_vid);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_ID_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.first_vid);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_TYPE_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.outer_second_cvlan_tag);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.outer_second_svlan_tag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_TYPE_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.inner_second_cvlan_tag);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.inner_second_svlan_tag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_PRIO_O:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.outer_second_prio);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_PRIO_I:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.inner_second_prio);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_CFI_O:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.outer_second_cfi);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_CFI_I:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.inner_second_cfi);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_ID_O:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.outer_second_vid);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VLAN_SECOND_ID_I:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.inner_second_vid);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_IHL_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.ipv4_ihl);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_IHL_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.ipv4_ihl);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_DSCP_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.ip_dscp);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_DSCP_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.ip_dscp);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_ECN_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.ip_ecn);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_ECN_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.ip_ecn);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_TTL_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.ttl_hoplimit);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_TTL_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.ttl_hoplimit);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_DST_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_SRC_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_DST_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV4_SRC_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_FRAG_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.frag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_FRAG_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.frag);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_FLOW_LABEL_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.outer_ipv6_flow_label);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_FLOW_LABEL_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.inner_ipv6_flow_label);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_95_64);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_63_32);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_O:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_O:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_95_64);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_63_32);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_95_64);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_63_32);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_I:
+	case MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_I:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_95_64);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_63_32);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_PROTOCOL_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.ip_protocol);
+		break;
+	case MLX5HWS_DEFINER_FNAME_IP_PROTOCOL_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.ip_protocol);
+		break;
+	case MLX5HWS_DEFINER_FNAME_L4_SPORT_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.tcp_sport);
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.udp_sport);
+		break;
+	case MLX5HWS_DEFINER_FNAME_L4_SPORT_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.tcp_dport);
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.udp_dport);
+		break;
+	case MLX5HWS_DEFINER_FNAME_L4_DPORT_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.tcp_dport);
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.udp_dport);
+		break;
+	case MLX5HWS_DEFINER_FNAME_L4_DPORT_I:
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.tcp_dport);
+		HWS_CLEAR_MATCH_PARAM(mask, inner_headers.udp_dport);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TCP_FLAGS_O:
+		HWS_CLEAR_MATCH_PARAM(mask, outer_headers.tcp_flags);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TCP_ACK_NUM:
+	case MLX5HWS_DEFINER_FNAME_TCP_SEQ_NUM:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.outer_tcp_seq_num);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.outer_tcp_ack_num);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.inner_tcp_seq_num);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.inner_tcp_ack_num);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GTP_TEID:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.gtpu_teid);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GTP_MSG_TYPE:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.gtpu_msg_type);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.gtpu_msg_flags);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GTPU_FIRST_EXT_DW0:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.gtpu_first_ext_dw_0);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.gtpu_dw_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GTPU_DW2:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.gtpu_dw_2);
+		break;
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_0:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_1:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_2:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_3:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_4:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_5:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_6:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER_7:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_2.outer_first_mpls_over_gre);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_2.outer_first_mpls_over_udp);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.geneve_tlv_option_0_data);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_id_0);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_value_0);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_value_1);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_id_2);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_value_2);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_id_3);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_4.prog_sample_field_value_3);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VXLAN_VNI:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.vxlan_vni);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VXLAN_GPE_FLAGS:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.outer_vxlan_gpe_flags);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VXLAN_GPE_RSVD0:
+		break;
+	case MLX5HWS_DEFINER_FNAME_VXLAN_GPE_PROTO:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.outer_vxlan_gpe_next_protocol);
+		break;
+	case MLX5HWS_DEFINER_FNAME_VXLAN_GPE_VNI:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.outer_vxlan_gpe_vni);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GENEVE_OPT_LEN:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.geneve_opt_len);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GENEVE_OAM:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.geneve_oam);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GENEVE_PROTO:
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.geneve_protocol_type);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GENEVE_VNI:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.geneve_vni);
+		break;
+	case MLX5HWS_DEFINER_FNAME_SOURCE_QP:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.source_sqn);
+		break;
+	case MLX5HWS_DEFINER_FNAME_SOURCE_GVMI:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.source_port);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.source_eswitch_owner_vhca_id);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_0:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_1:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_1);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_2:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_2);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_3:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_3);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_4:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_4);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_5:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_5);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_7:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_c_7);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_A:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.metadata_reg_a);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GRE_C:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.gre_c_present);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GRE_K:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.gre_k_present);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GRE_S:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.gre_s_present);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GRE_PROTOCOL:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.gre_protocol);
+		break;
+	case MLX5HWS_DEFINER_FNAME_GRE_OPT_KEY:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters.gre_key.key);
+		break;
+	case MLX5HWS_DEFINER_FNAME_ICMP_DW1:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.icmp_header_data);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.icmp_type);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.icmp_code);
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters_3.icmpv6_header_data);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.icmpv6_type);
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_3.icmpv6_code);
+		break;
+	case MLX5HWS_DEFINER_FNAME_MPLS0_O:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.outer_first_mpls);
+		break;
+	case MLX5HWS_DEFINER_FNAME_MPLS0_I:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_2.inner_first_mpls);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TNL_HDR_0:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_5.tunnel_header_0);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TNL_HDR_1:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_5.tunnel_header_1);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TNL_HDR_2:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_5.tunnel_header_2);
+		break;
+	case MLX5HWS_DEFINER_FNAME_TNL_HDR_3:
+		HWS_CLEAR_MATCH_PARAM(mask, misc_parameters_5.tunnel_header_3);
+		break;
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER0_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER1_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER2_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER3_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER4_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER5_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER6_OK:
+	case MLX5HWS_DEFINER_FNAME_FLEX_PARSER7_OK:
+		/* assuming this is flex parser for geneve option */
+		if ((fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER0_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 0) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER1_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 1) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER2_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 2) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER3_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 3) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER4_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 4) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER5_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 5) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER6_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 6) ||
+		    (fname == MLX5HWS_DEFINER_FNAME_FLEX_PARSER7_OK &&
+		     ctx->caps->flex_parser_id_geneve_tlv_option_0 != 7)) {
+			mlx5hws_err(ctx,
+				    "Complex params: unsupported field %s (%d), flex parser ID for geneve is %d\n",
+				    mlx5hws_definer_fname_to_str(fname), fname,
+				    caps->flex_parser_id_geneve_tlv_option_0);
+			break;
+		}
+		HWS_CLEAR_MATCH_PARAM(mask,
+				      misc_parameters.geneve_tlv_option_0_exist);
+		break;
+	case MLX5HWS_DEFINER_FNAME_REG_6:
+	default:
+		mlx5hws_err(ctx, "Complex params: unsupported field %s (%d)\n",
+			    mlx5hws_definer_fname_to_str(fname), fname);
+		break;
+	}
+}
+
+static bool
+hws_bwc_matcher_complex_params_comb_is_valid(struct mlx5hws_definer_fc *fc,
+					     int fc_sz,
+					     u32 combination_num)
+{
+	bool m1[MLX5HWS_DEFINER_FNAME_MAX] = {0};
+	bool m2[MLX5HWS_DEFINER_FNAME_MAX] = {0};
+	bool is_first_matcher;
+	int i;
+
+	for (i = 0; i < fc_sz; i++) {
+		is_first_matcher = !(combination_num & BIT(i));
+		if (is_first_matcher)
+			m1[fc[i].fname] = true;
+		else
+			m2[fc[i].fname] = true;
+	}
+
+	/* Not all the fields can be split into separate matchers.
+	 * Some should be together on the same matcher.
+	 * For example, IPv6 parts - the whole IPv6 address should be on the
+	 * same matcher in order for us to deduce if it's IPv6 or IPv4 address.
+	 */
+	if (m1[MLX5HWS_DEFINER_FNAME_IP_FRAG_O] &&
+	    (m2[MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_O]))
+		return false;
+
+	if (m2[MLX5HWS_DEFINER_FNAME_IP_FRAG_O] &&
+	    (m1[MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_O]))
+		return false;
+
+	if (m1[MLX5HWS_DEFINER_FNAME_IP_FRAG_I] &&
+	    (m2[MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_I]))
+		return false;
+
+	if (m2[MLX5HWS_DEFINER_FNAME_IP_FRAG_I] &&
+	    (m1[MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_I]))
+		return false;
+
+	/* Don't split outer IPv6 dest address. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_O]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_O]))
+		return false;
+
+	/* Don't split outer IPv6 source address. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_O] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_O]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_O] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_O]))
+		return false;
+
+	/* Don't split inner IPv6 dest address. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_I]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_I]))
+		return false;
+
+	/* Don't split inner IPv6 source address. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_I] ||
+	     m1[MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_I]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_I] ||
+	     m2[MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_I]))
+		return false;
+
+	/* Don't split GRE parameters. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_GRE_C] ||
+	     m1[MLX5HWS_DEFINER_FNAME_GRE_K] ||
+	     m1[MLX5HWS_DEFINER_FNAME_GRE_S] ||
+	     m1[MLX5HWS_DEFINER_FNAME_GRE_PROTOCOL]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_GRE_C] ||
+	     m2[MLX5HWS_DEFINER_FNAME_GRE_K] ||
+	     m2[MLX5HWS_DEFINER_FNAME_GRE_S] ||
+	     m2[MLX5HWS_DEFINER_FNAME_GRE_PROTOCOL]))
+		return false;
+
+	/* Don't split TCP ack/seq numbers. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_TCP_ACK_NUM] ||
+	     m1[MLX5HWS_DEFINER_FNAME_TCP_SEQ_NUM]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_TCP_ACK_NUM] ||
+	     m2[MLX5HWS_DEFINER_FNAME_TCP_SEQ_NUM]))
+		return false;
+
+	/* Don't split flex parser. */
+	if ((m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_0] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_1] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_2] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_3] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_4] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_5] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_6] ||
+	     m1[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_7]) &&
+	    (m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_0] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_1] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_2] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_3] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_4] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_5] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_6] ||
+	     m2[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_7]))
+		return false;
+
+	return true;
+}
+
+static void
+hws_bwc_matcher_complex_params_comb_create(struct mlx5hws_context *ctx,
+					   struct mlx5hws_match_parameters *m,
+					   struct mlx5hws_match_parameters *m1,
+					   struct mlx5hws_match_parameters *m2,
+					   struct mlx5hws_definer_fc *fc,
+					   int fc_sz,
+					   u32 combination_num)
+{
+	bool is_first_matcher;
+	int i;
+
+	memcpy(m1->match_buf, m->match_buf, m->match_sz);
+	memcpy(m2->match_buf, m->match_buf, m->match_sz);
+
+	for (i = 0; i < fc_sz; i++) {
+		is_first_matcher = !(combination_num & BIT(i));
+		hws_bwc_matcher_complex_params_clear_fld(ctx,
+							 fc[i].fname,
+							 is_first_matcher ?
+							 m2 : m1);
+	}
+
+	MLX5_SET(fte_match_param, m2->match_buf,
+		 misc_parameters_2.metadata_reg_c_6, -1);
+}
+
+static void
+hws_bwc_matcher_complex_params_destroy(struct mlx5hws_match_parameters *mask_1,
+				       struct mlx5hws_match_parameters *mask_2)
+{
+	kfree(mask_1->match_buf);
+	kfree(mask_2->match_buf);
+}
+
+static int
+hws_bwc_matcher_complex_params_create(struct mlx5hws_context *ctx,
+				      u8 match_criteria,
+				      struct mlx5hws_match_parameters *mask,
+				      struct mlx5hws_match_parameters *mask_1,
+				      struct mlx5hws_match_parameters *mask_2)
+{
+	struct mlx5hws_definer_fc *fc;
+	u32 num_of_combinations;
+	int fc_sz = 0;
+	int res = 0;
+	u32 i;
+
+	if (MLX5_GET(fte_match_param, mask->match_buf,
+		     misc_parameters_2.metadata_reg_c_6)) {
+		mlx5hws_err(ctx, "Complex matcher: REG_C_6 matching is reserved\n");
+		res = -EINVAL;
+		goto out;
+	}
+
+	mask_1->match_buf = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param),
+				    GFP_KERNEL);
+	mask_2->match_buf = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param),
+				    GFP_KERNEL);
+	if (!mask_1->match_buf || !mask_2->match_buf) {
+		mlx5hws_err(ctx, "Complex matcher: failed to allocate match_param\n");
+		res = -ENOMEM;
+		goto free_params;
+	}
+
+	mask_1->match_sz = mask->match_sz;
+	mask_2->match_sz = mask->match_sz;
+
+	fc = mlx5hws_definer_conv_match_params_to_compressed_fc(ctx,
+								match_criteria,
+								mask->match_buf,
+								&fc_sz);
+	if (!fc) {
+		res = -ENOMEM;
+		goto free_params;
+	}
+
+	if (fc_sz >= sizeof(num_of_combinations) * BITS_PER_BYTE) {
+		mlx5hws_err(ctx,
+			    "Complex matcher: too many match parameters (%d)\n",
+			    fc_sz);
+		res = -EINVAL;
+		goto free_fc;
+	}
+
+	/* We have list of all the match fields from the match parameter.
+	 * Now try all the possibilities of splitting them into two match
+	 * buffers and look for the supported combination.
+	 */
+	num_of_combinations = 1 << fc_sz;
+
+	/* Start from combination at index 1 - we know that 0 is unsupported */
+	for (i = 1; i < num_of_combinations; i++) {
+		if (!hws_bwc_matcher_complex_params_comb_is_valid(fc, fc_sz, i))
+			continue;
+
+		hws_bwc_matcher_complex_params_comb_create(ctx,
+							   mask, mask_1, mask_2,
+							   fc, fc_sz, i);
+		/* We now have two separate sets of match params.
+		 * Check if each of them can be used in its own matcher.
+		 */
+		if (!mlx5hws_bwc_match_params_is_complex(ctx,
+							 match_criteria,
+							 mask_1) &&
+		    !mlx5hws_bwc_match_params_is_complex(ctx,
+							 match_criteria,
+							 mask_2))
+			break;
+	}
+
+	if (i == num_of_combinations) {
+		/* We've scanned all the combinations, but to no avail */
+		mlx5hws_err(ctx, "Complex matcher: couldn't find match params combination\n");
+		res = -EINVAL;
+		goto free_fc;
+	}
+
+	kfree(fc);
+	return 0;
+
+free_fc:
+	kfree(fc);
+free_params:
+	hws_bwc_matcher_complex_params_destroy(mask_1, mask_2);
+out:
+	return res;
+}
+
+static int
+hws_bwc_isolated_table_create(struct mlx5hws_bwc_matcher *bwc_matcher,
+			      struct mlx5hws_table *table)
+{
+	struct mlx5hws_cmd_ft_modify_attr ft_attr = {0};
+	struct mlx5hws_context *ctx = table->ctx;
+	struct mlx5hws_table_attr tbl_attr = {0};
+	struct mlx5hws_table *isolated_tbl;
+	int ret = 0;
+
+	tbl_attr.type = table->type;
+	tbl_attr.level = table->level;
+
+	bwc_matcher->complex->isolated_tbl =
+		mlx5hws_table_create(ctx, &tbl_attr);
+	isolated_tbl = bwc_matcher->complex->isolated_tbl;
+	if (!isolated_tbl)
+		return -EINVAL;
+
+	/* Set the default miss of the isolated table to
+	 * point to the end anchor of the original matcher.
+	 */
+	mlx5hws_cmd_set_attr_connect_miss_tbl(ctx,
+					      isolated_tbl->fw_ft_type,
+					      isolated_tbl->type,
+					      &ft_attr);
+	ft_attr.table_miss_id = bwc_matcher->matcher->end_ft_id;
+
+	ret = mlx5hws_cmd_flow_table_modify(ctx->mdev,
+					    &ft_attr,
+					    isolated_tbl->ft_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed setting isolated tbl default miss\n");
+		goto destroy_tbl;
+	}
+
+	return 0;
+
+destroy_tbl:
+	mlx5hws_table_destroy(isolated_tbl);
+	return ret;
+}
+
+static void hws_bwc_isolated_table_destroy(struct mlx5hws_table *isolated_tbl)
+{
+	/* This table is isolated - no table is pointing to it, no need to
+	 * disconnect it from anywhere, it won't affect any other table's miss.
+	 */
+	mlx5hws_table_destroy(isolated_tbl);
+}
+
+static int
+hws_bwc_isolated_matcher_create(struct mlx5hws_bwc_matcher *bwc_matcher,
+				struct mlx5hws_table *table,
+				u8 match_criteria_enable,
+				struct mlx5hws_match_parameters *mask)
+{
+	struct mlx5hws_table *isolated_tbl = bwc_matcher->complex->isolated_tbl;
+	struct mlx5hws_bwc_matcher *isolated_bwc_matcher;
+	struct mlx5hws_context *ctx = table->ctx;
+	int ret;
+
+	isolated_bwc_matcher = kzalloc(sizeof(*bwc_matcher), GFP_KERNEL);
+	if (!isolated_bwc_matcher)
+		return -ENOMEM;
+
+	bwc_matcher->complex->isolated_bwc_matcher = isolated_bwc_matcher;
+
+	/* Isolated BWC matcher needs access to the first BWC matcher */
+	isolated_bwc_matcher->complex_first_bwc_matcher = bwc_matcher;
+
+	/* Isolated matcher needs to match on REG_C_6,
+	 * so make sure its criteria bit is on.
+	 */
+	match_criteria_enable |= MLX5HWS_DEFINER_MATCH_CRITERIA_MISC2;
+
+	ret = mlx5hws_bwc_matcher_create_simple(isolated_bwc_matcher,
+						isolated_tbl,
+						0,
+						match_criteria_enable,
+						mask,
+						NULL);
+	if (ret) {
+		mlx5hws_err(ctx, "Complex matcher: failed creating isolated BWC matcher\n");
+		goto free_matcher;
+	}
+
+	return 0;
+
+free_matcher:
+	kfree(bwc_matcher->complex->isolated_bwc_matcher);
+	return ret;
+}
+
+static void
+hws_bwc_isolated_matcher_destroy(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
+	kfree(bwc_matcher);
+}
+
+static int
+hws_bwc_isolated_actions_create(struct mlx5hws_bwc_matcher *bwc_matcher,
+				struct mlx5hws_table *table)
+{
+	struct mlx5hws_table *isolated_tbl = bwc_matcher->complex->isolated_tbl;
+	u8 modify_hdr_action[MLX5_ST_SZ_BYTES(set_action_in)] = {0};
+	struct mlx5hws_context *ctx = table->ctx;
+	struct mlx5hws_action_mh_pattern ptrn;
+	int ret = 0;
+
+	/* Create action to jump to isolated table */
+
+	bwc_matcher->complex->action_go_to_tbl =
+		mlx5hws_action_create_dest_table(ctx,
+						 isolated_tbl,
+						 MLX5HWS_ACTION_FLAG_HWS_FDB);
+	if (!bwc_matcher->complex->action_go_to_tbl) {
+		mlx5hws_err(ctx, "Complex matcher: failed to create go-to-tbl action\n");
+		return -EINVAL;
+	}
+
+	/* Create modify header action to set REG_C_6 */
+
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 action_type, MLX5_MODIFICATION_TYPE_SET);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 field, MLX5_MODI_META_REG_C_6);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 length, 0); /* zero means length of 32 */
+	MLX5_SET(set_action_in, modify_hdr_action, offset, 0);
+	MLX5_SET(set_action_in, modify_hdr_action, data, 0);
+
+	ptrn.data = (void *)modify_hdr_action;
+	ptrn.sz = MLX5HWS_ACTION_DOUBLE_SIZE;
+
+	bwc_matcher->complex->action_metadata =
+		mlx5hws_action_create_modify_header(ctx, 1, &ptrn, 0,
+						    MLX5HWS_ACTION_FLAG_HWS_FDB);
+	if (!bwc_matcher->complex->action_metadata) {
+		ret = -EINVAL;
+		goto destroy_action_go_to_tbl;
+	}
+
+	/* Create last action */
+
+	bwc_matcher->complex->action_last =
+		mlx5hws_action_create_last(ctx, MLX5HWS_ACTION_FLAG_HWS_FDB);
+	if (!bwc_matcher->complex->action_last) {
+		mlx5hws_err(ctx, "Complex matcher: failed to create last action\n");
+		ret = -EINVAL;
+		goto destroy_action_metadata;
+	}
+
+	return 0;
+
+destroy_action_metadata:
+	mlx5hws_action_destroy(bwc_matcher->complex->action_metadata);
+destroy_action_go_to_tbl:
+	mlx5hws_action_destroy(bwc_matcher->complex->action_go_to_tbl);
+	return ret;
+}
+
+static void
+hws_bwc_isolated_actions_destroy(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	mlx5hws_action_destroy(bwc_matcher->complex->action_last);
+	mlx5hws_action_destroy(bwc_matcher->complex->action_metadata);
+	mlx5hws_action_destroy(bwc_matcher->complex->action_go_to_tbl);
+}
+
 int mlx5hws_bwc_matcher_create_complex(struct mlx5hws_bwc_matcher *bwc_matcher,
 				       struct mlx5hws_table *table,
 				       u32 priority,
 				       u8 match_criteria_enable,
 				       struct mlx5hws_match_parameters *mask)
 {
-	mlx5hws_err(table->ctx, "Complex matcher is not supported yet\n");
-	return -EOPNOTSUPP;
+	enum mlx5hws_action_type complex_init_action_types[3];
+	struct mlx5hws_bwc_matcher *isolated_bwc_matcher;
+	struct mlx5hws_match_parameters mask_1 = {0};
+	struct mlx5hws_match_parameters mask_2 = {0};
+	struct mlx5hws_context *ctx = table->ctx;
+	int ret;
+
+	ret = hws_bwc_matcher_complex_params_create(table->ctx,
+						    match_criteria_enable,
+						    mask, &mask_1, &mask_2);
+	if (ret)
+		goto err;
+
+	bwc_matcher->complex =
+		kzalloc(sizeof(*bwc_matcher->complex), GFP_KERNEL);
+	if (!bwc_matcher->complex) {
+		ret = -ENOMEM;
+		goto free_masks;
+	}
+
+	ret = rhashtable_init(&bwc_matcher->complex->refcount_hash,
+			      &hws_refcount_hash);
+	if (ret) {
+		mlx5hws_err(ctx, "Complex matcher: failed to initialize rhashtable\n");
+		goto free_complex;
+	}
+
+	mutex_init(&bwc_matcher->complex->hash_lock);
+	ida_init(&bwc_matcher->complex->metadata_ida);
+
+	/* Create initial action template for the first matcher.
+	 * Usually the initial AT is just dummy, but in case of complex
+	 * matcher we know exactly which actions should it have.
+	 */
+
+	complex_init_action_types[0] = MLX5HWS_ACTION_TYP_MODIFY_HDR;
+	complex_init_action_types[1] = MLX5HWS_ACTION_TYP_TBL;
+	complex_init_action_types[2] = MLX5HWS_ACTION_TYP_LAST;
+
+	/* Create the first matcher */
+
+	ret = mlx5hws_bwc_matcher_create_simple(bwc_matcher,
+						table,
+						priority,
+						match_criteria_enable,
+						&mask_1,
+						complex_init_action_types);
+	if (ret)
+		goto destroy_ida;
+
+	/* Create isolated table to hold the second isolated matcher */
+
+	ret = hws_bwc_isolated_table_create(bwc_matcher, table);
+	if (ret) {
+		mlx5hws_err(ctx, "Complex matcher: failed creating isolated table\n");
+		goto destroy_first_matcher;
+	}
+
+	/* Now create the second BWC matcher - the isolated one */
+
+	ret = hws_bwc_isolated_matcher_create(bwc_matcher, table,
+					      match_criteria_enable, &mask_2);
+	if (ret) {
+		mlx5hws_err(ctx, "Complex matcher: failed creating isolated matcher\n");
+		goto destroy_isolated_tbl;
+	}
+
+	/* Create action for isolated matcher's rules */
+
+	ret = hws_bwc_isolated_actions_create(bwc_matcher, table);
+	if (ret) {
+		mlx5hws_err(ctx, "Complex matcher: failed creating isolated actions\n");
+		goto destroy_isolated_matcher;
+	}
+
+	hws_bwc_matcher_complex_params_destroy(&mask_1, &mask_2);
+	return 0;
+
+destroy_isolated_matcher:
+	isolated_bwc_matcher = bwc_matcher->complex->isolated_bwc_matcher;
+	hws_bwc_isolated_matcher_destroy(isolated_bwc_matcher);
+destroy_isolated_tbl:
+	hws_bwc_isolated_table_destroy(bwc_matcher->complex->isolated_tbl);
+destroy_first_matcher:
+	mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
+destroy_ida:
+	ida_destroy(&bwc_matcher->complex->metadata_ida);
+	mutex_destroy(&bwc_matcher->complex->hash_lock);
+	rhashtable_destroy(&bwc_matcher->complex->refcount_hash);
+free_complex:
+	kfree(bwc_matcher->complex);
+	bwc_matcher->complex = NULL;
+free_masks:
+	hws_bwc_matcher_complex_params_destroy(&mask_1, &mask_2);
+err:
+	return ret;
 }
 
 void
 mlx5hws_bwc_matcher_destroy_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	/* nothing to do here */
+	struct mlx5hws_bwc_matcher *isolated_bwc_matcher =
+		bwc_matcher->complex->isolated_bwc_matcher;
+
+	hws_bwc_isolated_actions_destroy(bwc_matcher);
+	hws_bwc_isolated_matcher_destroy(isolated_bwc_matcher);
+	hws_bwc_isolated_table_destroy(bwc_matcher->complex->isolated_tbl);
+	mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
+	ida_destroy(&bwc_matcher->complex->metadata_ida);
+	mutex_destroy(&bwc_matcher->complex->hash_lock);
+	rhashtable_destroy(&bwc_matcher->complex->refcount_hash);
+	kfree(bwc_matcher->complex);
+	bwc_matcher->complex = NULL;
+}
+
+static void
+hws_bwc_matcher_complex_hash_lock(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	mutex_lock(&bwc_matcher->complex->hash_lock);
+}
+
+static void
+hws_bwc_matcher_complex_hash_unlock(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	mutex_unlock(&bwc_matcher->complex->hash_lock);
+}
+
+static int
+hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule,
+				   struct mlx5hws_match_parameters *params)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_bwc_complex_rule_hash_node *node, *old_node;
+	struct rhashtable *refcount_hash;
+	int i;
+
+	bwc_rule->complex_hash_node = NULL;
+
+	node = kzalloc(sizeof(*node), GFP_KERNEL);
+	if (unlikely(!node))
+		return -ENOMEM;
+
+	node->tag = ida_alloc(&bwc_matcher->complex->metadata_ida, GFP_KERNEL);
+	refcount_set(&node->refcount, 1);
+
+	/* Clear match buffer - turn off all the unrelated fields
+	 * in accordance with the match params mask for the first
+	 * matcher out of the two parts of the complex matcher.
+	 * The resulting mask is the key for the hash.
+	 */
+	for (i = 0; i < MLX5_ST_SZ_DW_MATCH_PARAM; i++)
+		node->match_buf[i] = params->match_buf[i] &
+				     bwc_matcher->mt->match_param[i];
+
+	refcount_hash = &bwc_matcher->complex->refcount_hash;
+	old_node = rhashtable_lookup_get_insert_fast(refcount_hash,
+						     &node->hash_node,
+						     hws_refcount_hash);
+	if (old_node) {
+		/* Rule with the same tag already exists - update refcount */
+		refcount_inc(&old_node->refcount);
+		/* Let the new rule use the same tag as the existing rule.
+		 * Note that we don't have any indication for the rule creation
+		 * process that a rule with similar matching params already
+		 * exists - no harm done when this rule is be overwritten by
+		 * the same STE.
+		 * There's some performance advantage in skipping such cases,
+		 * so this is left for future optimizations.
+		 */
+		ida_free(&bwc_matcher->complex->metadata_ida, node->tag);
+		kfree(node);
+		node = old_node;
+	}
+
+	bwc_rule->complex_hash_node = node;
+	return 0;
+}
+
+static void
+hws_bwc_rule_complex_hash_node_put(struct mlx5hws_bwc_rule *bwc_rule,
+				   bool *is_last_rule)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_bwc_complex_rule_hash_node *node;
+
+	if (is_last_rule)
+		*is_last_rule = false;
+
+	node = bwc_rule->complex_hash_node;
+	if (refcount_dec_and_test(&node->refcount)) {
+		rhashtable_remove_fast(&bwc_matcher->complex->refcount_hash,
+				       &node->hash_node,
+				       hws_refcount_hash);
+		ida_free(&bwc_matcher->complex->metadata_ida, node->tag);
+		kfree(node);
+		if (is_last_rule)
+			*is_last_rule = true;
+	}
+
+	bwc_rule->complex_hash_node = NULL;
 }
 
 int mlx5hws_bwc_rule_create_complex(struct mlx5hws_bwc_rule *bwc_rule,
@@ -70,19 +1144,271 @@ int mlx5hws_bwc_rule_create_complex(struct mlx5hws_bwc_rule *bwc_rule,
 				    struct mlx5hws_rule_action rule_actions[],
 				    u16 bwc_queue_idx)
 {
-	mlx5hws_err(bwc_rule->bwc_matcher->matcher->tbl->ctx,
-		    "Complex rule is not supported yet\n");
-	return -EOPNOTSUPP;
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	u8 modify_hdr_action[MLX5_ST_SZ_BYTES(set_action_in)] = {0};
+	struct mlx5hws_rule_action rule_actions_1[3] = {0};
+	struct mlx5hws_bwc_matcher *isolated_bwc_matcher;
+	u32 *match_buf_2;
+	u32 metadata_val;
+	int ret = 0;
+
+	isolated_bwc_matcher = bwc_matcher->complex->isolated_bwc_matcher;
+	bwc_rule->isolated_bwc_rule =
+		mlx5hws_bwc_rule_alloc(isolated_bwc_matcher);
+	if (unlikely(!bwc_rule->isolated_bwc_rule))
+		return -ENOMEM;
+
+	hws_bwc_matcher_complex_hash_lock(bwc_matcher);
+
+	/* Get a new hash node for this complex rule.
+	 * If this is a unique set of match params for the first matcher,
+	 * we will get a new hash node with newly allocated IDA.
+	 * Otherwise we will get an existing node with IDA and updated refcount.
+	 */
+	ret = hws_bwc_rule_complex_hash_node_get(bwc_rule, params);
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx, "Complex rule: failed getting RHT node for this rule\n");
+		goto free_isolated_rule;
+	}
+
+	/* No need to clear match buffer's fields in accordance to what
+	 * will actually be matched on first and second matchers.
+	 * Both matchers were created with the appropriate masks
+	 * and each of them holds the appropriate field copy array,
+	 * so rule creation will use only the fields that will be copied
+	 * in accordance with setters in field copy array.
+	 * We do, however, need to temporary allocate match buffer
+	 * for the second (isolated) rule in order to not modify
+	 * user's match params buffer.
+	 */
+
+	match_buf_2 = kmemdup(params->match_buf,
+			      MLX5_ST_SZ_BYTES(fte_match_param),
+			      GFP_KERNEL);
+	if (unlikely(!match_buf_2)) {
+		mlx5hws_err(ctx, "Complex rule: failed allocating match_buf\n");
+		ret = ENOMEM;
+		goto hash_node_put;
+	}
+
+	/* On 2nd matcher, use unique 32-bit ID as a matching tag */
+	metadata_val = bwc_rule->complex_hash_node->tag;
+	MLX5_SET(fte_match_param, match_buf_2,
+		 misc_parameters_2.metadata_reg_c_6, metadata_val);
+
+	/* Isolated rule's rule_actions contain all the original actions */
+	ret = mlx5hws_bwc_rule_create_simple(bwc_rule->isolated_bwc_rule,
+					     match_buf_2,
+					     rule_actions,
+					     flow_source,
+					     bwc_queue_idx);
+	kfree(match_buf_2);
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx,
+			    "Complex rule: failed creating isolated BWC rule (%d)\n",
+			    ret);
+		goto hash_node_put;
+	}
+
+	/* First rule's rule_actions contain setting metadata and
+	 * jump to isolated table that contains the second matcher.
+	 * Set metadata value to a unique value for this rule.
+	 */
+
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 action_type, MLX5_MODIFICATION_TYPE_SET);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 field, MLX5_MODI_META_REG_C_6);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 length, 0); /* zero means length of 32 */
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 offset, 0);
+	MLX5_SET(set_action_in, modify_hdr_action,
+		 data, metadata_val);
+
+	rule_actions_1[0].action = bwc_matcher->complex->action_metadata;
+	rule_actions_1[0].modify_header.offset = 0;
+	rule_actions_1[0].modify_header.data = modify_hdr_action;
+
+	rule_actions_1[1].action = bwc_matcher->complex->action_go_to_tbl;
+	rule_actions_1[2].action = bwc_matcher->complex->action_last;
+
+	ret = mlx5hws_bwc_rule_create_simple(bwc_rule,
+					     params->match_buf,
+					     rule_actions_1,
+					     flow_source,
+					     bwc_queue_idx);
+
+	if (unlikely(ret)) {
+		mlx5hws_err(ctx,
+			    "Complex rule: failed creating first BWC rule (%d)\n",
+			    ret);
+		goto destroy_isolated_rule;
+	}
+
+	hws_bwc_matcher_complex_hash_unlock(bwc_matcher);
+
+	return 0;
+
+destroy_isolated_rule:
+	mlx5hws_bwc_rule_destroy_simple(bwc_rule->isolated_bwc_rule);
+hash_node_put:
+	hws_bwc_rule_complex_hash_node_put(bwc_rule, NULL);
+free_isolated_rule:
+	hws_bwc_matcher_complex_hash_unlock(bwc_matcher);
+	mlx5hws_bwc_rule_free(bwc_rule->isolated_bwc_rule);
+	return ret;
 }
 
 int mlx5hws_bwc_rule_destroy_complex(struct mlx5hws_bwc_rule *bwc_rule)
 {
-	return 0;
+	struct mlx5hws_context *ctx = bwc_rule->bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_bwc_rule *isolated_bwc_rule;
+	int ret_isolated, ret;
+	bool is_last_rule;
+
+	hws_bwc_matcher_complex_hash_lock(bwc_rule->bwc_matcher);
+
+	hws_bwc_rule_complex_hash_node_put(bwc_rule, &is_last_rule);
+	bwc_rule->rule->skip_delete = !is_last_rule;
+
+	ret = mlx5hws_bwc_rule_destroy_simple(bwc_rule);
+	if (unlikely(ret))
+		mlx5hws_err(ctx, "BWC complex rule: failed destroying first rule\n");
+
+	isolated_bwc_rule = bwc_rule->isolated_bwc_rule;
+	ret_isolated = mlx5hws_bwc_rule_destroy_simple(isolated_bwc_rule);
+	if (unlikely(ret_isolated))
+		mlx5hws_err(ctx, "BWC complex rule: failed destroying second (isolated) rule\n");
+
+	hws_bwc_matcher_complex_hash_unlock(bwc_rule->bwc_matcher);
+
+	mlx5hws_bwc_rule_free(isolated_bwc_rule);
+
+	return ret || ret_isolated;
+}
+
+static void
+hws_bwc_matcher_clear_hash_rtcs(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_bwc_complex_rule_hash_node *node;
+	struct rhashtable_iter iter;
+
+	rhashtable_walk_enter(&bwc_matcher->complex->refcount_hash, &iter);
+	rhashtable_walk_start(&iter);
+
+	while ((node = rhashtable_walk_next(&iter)) != NULL) {
+		if (IS_ERR(node))
+			continue;
+		node->rtc_valid = false;
+	}
+
+	rhashtable_walk_stop(&iter);
+	rhashtable_walk_exit(&iter);
 }
 
-int mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
+int
+mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	mlx5hws_err(bwc_matcher->matcher->tbl->ctx,
-		    "Moving complex rule is not supported yet\n");
-	return -EOPNOTSUPP;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_matcher *matcher = bwc_matcher->matcher;
+	bool move_error = false, poll_error = false;
+	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
+	struct mlx5hws_bwc_rule *tmp_bwc_rule;
+	struct mlx5hws_rule_attr rule_attr;
+	struct mlx5hws_table *isolated_tbl;
+	struct mlx5hws_rule *tmp_rule;
+	struct list_head *rules_list;
+	u32 expected_completions = 1;
+	u32 end_ft_id;
+	int i, ret;
+
+	/* We are rehashing the matcher that is the first part of the complex
+	 * matcher. Need to update the isolated matcher to point to the end_ft
+	 * of this new matcher. This needs to be done before moving any rules
+	 * to prevent possible steering loops.
+	 */
+	isolated_tbl = bwc_matcher->complex->isolated_tbl;
+	end_ft_id = bwc_matcher->matcher->resize_dst->end_ft_id;
+	ret = mlx5hws_matcher_update_end_ft_isolated(isolated_tbl, end_ft_id);
+	if (ret) {
+		mlx5hws_err(ctx,
+			    "Failed updating end_ft of isolated matcher (%d)\n",
+			    ret);
+		return ret;
+	}
+
+	hws_bwc_matcher_clear_hash_rtcs(bwc_matcher);
+
+	mlx5hws_bwc_rule_fill_attr(bwc_matcher, 0, 0, &rule_attr);
+
+	for (i = 0; i < bwc_queues; i++) {
+		rules_list = &bwc_matcher->rules[i];
+		if (list_empty(rules_list))
+			continue;
+
+		rule_attr.queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
+
+		list_for_each_entry(tmp_bwc_rule, rules_list, list_node) {
+			/* Check if a rule with similar tag has already
+			 * been moved.
+			 */
+			if (tmp_bwc_rule->complex_hash_node->rtc_valid) {
+				/* This rule is a duplicate of rule with similar
+				 * tag that has already been moved earlier.
+				 * Just update this rule's RTCs.
+				 */
+				tmp_bwc_rule->rule->rtc_0 =
+					tmp_bwc_rule->complex_hash_node->rtc_0;
+				tmp_bwc_rule->rule->rtc_1 =
+					tmp_bwc_rule->complex_hash_node->rtc_1;
+				tmp_bwc_rule->rule->matcher =
+					tmp_bwc_rule->rule->matcher->resize_dst;
+				continue;
+			}
+
+			/* First time we're moving rule with this tag.
+			 * Move it for real.
+			 */
+			tmp_rule = tmp_bwc_rule->rule;
+			tmp_rule->skip_delete = false;
+			ret = mlx5hws_matcher_resize_rule_move(matcher,
+							       tmp_rule,
+							       &rule_attr);
+			if (unlikely(ret && !move_error)) {
+				mlx5hws_err(ctx,
+					    "Moving complex BWC rule failed (%d), attempting to move rest of the rules\n",
+					    ret);
+				move_error = true;
+			}
+
+			expected_completions = 1;
+			ret = mlx5hws_bwc_queue_poll(ctx,
+						     rule_attr.queue_id,
+						     &expected_completions,
+						     true);
+			if (unlikely(ret && !poll_error)) {
+				mlx5hws_err(ctx,
+					    "Moving complex BWC rule: poll failed (%d), attempting to move rest of the rules\n",
+					    ret);
+				poll_error = true;
+			}
+
+			/* Done moving the rule to the new matcher,
+			 * now update RTCs for all the duplicated rules.
+			 */
+			tmp_bwc_rule->complex_hash_node->rtc_0 =
+				tmp_bwc_rule->rule->rtc_0;
+			tmp_bwc_rule->complex_hash_node->rtc_1 =
+				tmp_bwc_rule->rule->rtc_1;
+
+			tmp_bwc_rule->complex_hash_node->rtc_valid = true;
+		}
+	}
+
+	if (move_error || poll_error)
+		ret = -EINVAL;
+
+	return ret;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h
index 340f0688e394..a6887c7e39d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h
@@ -4,6 +4,27 @@
 #ifndef HWS_BWC_COMPLEX_H_
 #define HWS_BWC_COMPLEX_H_
 
+struct mlx5hws_bwc_complex_rule_hash_node {
+	u32 match_buf[MLX5_ST_SZ_DW_MATCH_PARAM];
+	u32 tag;
+	refcount_t refcount;
+	bool rtc_valid;
+	u32 rtc_0;
+	u32 rtc_1;
+	struct rhash_head hash_node;
+};
+
+struct mlx5hws_bwc_matcher_complex_data {
+	struct mlx5hws_table *isolated_tbl;
+	struct mlx5hws_bwc_matcher *isolated_bwc_matcher;
+	struct mlx5hws_action *action_metadata;
+	struct mlx5hws_action *action_go_to_tbl;
+	struct mlx5hws_action *action_last;
+	struct rhashtable refcount_hash;
+	struct mutex hash_lock; /* Protect the refcount rhashtable */
+	struct ida metadata_ida;
+};
+
 bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
 					 u8 match_criteria_enable,
 					 struct mlx5hws_match_parameters *mask);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
index e8f98c109b99..9c83753e4592 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
@@ -406,7 +406,6 @@ int mlx5hws_cmd_rtc_create(struct mlx5_core_dev *mdev,
 	MLX5_SET(rtc, attr, match_definer_1, rtc_attr->match_definer_1);
 	MLX5_SET(rtc, attr, stc_id, rtc_attr->stc_base);
 	MLX5_SET(rtc, attr, ste_table_base_id, rtc_attr->ste_base);
-	MLX5_SET(rtc, attr, ste_table_offset, rtc_attr->ste_offset);
 	MLX5_SET(rtc, attr, miss_flow_table_id, rtc_attr->miss_ft_id);
 	MLX5_SET(rtc, attr, reparse_mode, rtc_attr->reparse_mode);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
index 51d9e0291ac1..fa6bff210266 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
@@ -70,7 +70,6 @@ struct mlx5hws_cmd_rtc_create_attr {
 	u32 pd;
 	u32 stc_base;
 	u32 ste_base;
-	u32 ste_offset;
 	u32 miss_ft_id;
 	bool fw_gen_wqe;
 	u8 update_index_mode;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
index 9cda2774fd64..428dae869706 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
@@ -34,7 +34,6 @@ static int hws_context_pools_init(struct mlx5hws_context *ctx)
 
 	/* Create an STC pool per FT type */
 	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STC;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STC_POOL;
 	max_log_sz = min(MLX5HWS_POOL_STC_LOG_SZ, ctx->caps->stc_alloc_log_max);
 	pool_attr.alloc_log_sz = max(max_log_sz, ctx->caps->stc_alloc_log_gran);
 
@@ -159,10 +158,16 @@ static int hws_context_init_hws(struct mlx5hws_context *ctx,
 	if (ret)
 		goto pools_uninit;
 
+	ret = mlx5hws_action_ste_pool_init(ctx);
+	if (ret)
+		goto close_queues;
+
 	INIT_LIST_HEAD(&ctx->tbl_list);
 
 	return 0;
 
+close_queues:
+	mlx5hws_send_queues_close(ctx);
 pools_uninit:
 	hws_context_pools_uninit(ctx);
 uninit_pd:
@@ -175,6 +180,7 @@ static void hws_context_uninit_hws(struct mlx5hws_context *ctx)
 	if (!(ctx->flags & MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT))
 		return;
 
+	mlx5hws_action_ste_pool_uninit(ctx);
 	mlx5hws_send_queues_close(ctx);
 	hws_context_pools_uninit(ctx);
 	hws_context_uninit_pd(ctx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
index 38c3647444ad..3f8938c73dc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
@@ -39,6 +39,8 @@ struct mlx5hws_context {
 	struct mlx5hws_cmd_query_caps *caps;
 	u32 pd_num;
 	struct mlx5hws_pool *stc_pool;
+	struct mlx5hws_action_ste_pool *action_ste_pool; /* One per queue */
+	struct delayed_work action_ste_cleanup;
 	struct mlx5hws_context_common_res common_res;
 	struct mlx5hws_pattern_cache *pattern_cache;
 	struct mlx5hws_definer_cache *definer_cache;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
index 696275fd0ce2..91568d6c1dac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
@@ -118,7 +118,6 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 {
 	enum mlx5hws_table_type tbl_type = matcher->tbl->type;
 	struct mlx5hws_cmd_ft_query_attr ft_attr = {0};
-	struct mlx5hws_pool_chunk *ste;
 	struct mlx5hws_pool *ste_pool;
 	u64 icm_addr_0 = 0;
 	u64 icm_addr_1 = 0;
@@ -134,12 +133,11 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 		   matcher->end_ft_id,
 		   matcher->col_matcher ? HWS_PTR_TO_ID(matcher->col_matcher) : 0);
 
-	ste = &matcher->match_ste.ste;
 	ste_pool = matcher->match_ste.pool;
 	if (ste_pool) {
-		ste_0_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
+		ste_0_id = mlx5hws_pool_get_base_id(ste_pool);
 		if (tbl_type == MLX5HWS_TABLE_TYPE_FDB)
-			ste_1_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
+			ste_1_id = mlx5hws_pool_get_base_mirror_id(ste_pool);
 	}
 
 	seq_printf(f, ",%d,%d,%d,%d",
@@ -148,19 +146,6 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 		   matcher->match_ste.rtc_1_id,
 		   (int)ste_1_id);
 
-	ste = &matcher->action_ste.ste;
-	ste_pool = matcher->action_ste.pool;
-	if (ste_pool) {
-		ste_0_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
-		if (tbl_type == MLX5HWS_TABLE_TYPE_FDB)
-			ste_1_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
-		else
-			ste_1_id = -1;
-	} else {
-		ste_0_id = -1;
-		ste_1_id = -1;
-	}
-
 	ft_attr.type = matcher->tbl->fw_ft_type;
 	ret = mlx5hws_cmd_flow_table_query(matcher->tbl->ctx->mdev,
 					   matcher->end_ft_id,
@@ -170,10 +155,7 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma
 	if (ret)
 		return ret;
 
-	seq_printf(f, ",%d,%d,%d,%d,%d,0x%llx,0x%llx\n",
-		   matcher->action_ste.rtc_0_id, (int)ste_0_id,
-		   matcher->action_ste.rtc_1_id, (int)ste_1_id,
-		   0,
+	seq_printf(f, ",-1,-1,-1,-1,0,0x%llx,0x%llx\n",
 		   mlx5hws_debug_icm_to_idx(icm_addr_0),
 		   mlx5hws_debug_icm_to_idx(icm_addr_1));
 
@@ -387,14 +369,17 @@ static int hws_debug_dump_context_stc(struct seq_file *f, struct mlx5hws_context
 	if (!stc_pool)
 		return 0;
 
-	if (stc_pool->resource[0]) {
-		ret = hws_debug_dump_context_stc_resource(f, ctx, stc_pool->resource[0]);
+	if (stc_pool->resource) {
+		ret = hws_debug_dump_context_stc_resource(f, ctx,
+							  stc_pool->resource);
 		if (ret)
 			return ret;
 	}
 
-	if (stc_pool->mirror_resource[0]) {
-		ret = hws_debug_dump_context_stc_resource(f, ctx, stc_pool->mirror_resource[0]);
+	if (stc_pool->mirror_resource) {
+		struct mlx5hws_pool_resource *res = stc_pool->mirror_resource;
+
+		ret = hws_debug_dump_context_stc_resource(f, ctx, res);
 		if (ret)
 			return ret;
 	}
@@ -402,10 +387,41 @@ static int hws_debug_dump_context_stc(struct seq_file *f, struct mlx5hws_context
 	return 0;
 }
 
+static void
+hws_debug_dump_action_ste_table(struct seq_file *f,
+				struct mlx5hws_action_ste_table *action_tbl)
+{
+	int ste_0_id = mlx5hws_pool_get_base_id(action_tbl->pool);
+	int ste_1_id = mlx5hws_pool_get_base_mirror_id(action_tbl->pool);
+
+	seq_printf(f, "%d,0x%llx,%d,%d,%d,%d\n",
+		   MLX5HWS_DEBUG_RES_TYPE_ACTION_STE_TABLE,
+		   HWS_PTR_TO_ID(action_tbl),
+		   action_tbl->rtc_0_id, ste_0_id,
+		   action_tbl->rtc_1_id, ste_1_id);
+}
+
+static void hws_debug_dump_action_ste_pool(struct seq_file *f,
+					   struct mlx5hws_action_ste_pool *pool)
+{
+	struct mlx5hws_action_ste_table *action_tbl;
+	enum mlx5hws_pool_optimize opt;
+
+	mutex_lock(&pool->lock);
+	for (opt = MLX5HWS_POOL_OPTIMIZE_NONE; opt < MLX5HWS_POOL_OPTIMIZE_MAX;
+	     opt++) {
+		list_for_each_entry(action_tbl, &pool->elems[opt].available,
+				    list_node) {
+			hws_debug_dump_action_ste_table(f, action_tbl);
+		}
+	}
+	mutex_unlock(&pool->lock);
+}
+
 static int hws_debug_dump_context(struct seq_file *f, struct mlx5hws_context *ctx)
 {
 	struct mlx5hws_table *tbl;
-	int ret;
+	int ret, i;
 
 	ret = hws_debug_dump_context_info(f, ctx);
 	if (ret)
@@ -425,6 +441,9 @@ static int hws_debug_dump_context(struct seq_file *f, struct mlx5hws_context *ct
 			return ret;
 	}
 
+	for (i = 0; i < ctx->queues; i++)
+		hws_debug_dump_action_ste_pool(f, &ctx->action_ste_pool[i]);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h
index e44e7ae28f93..89c396f9f266 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h
@@ -26,6 +26,8 @@ enum mlx5hws_debug_res_type {
 	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_HASH_DEFINER = 4205,
 	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_RANGE_DEFINER = 4206,
 	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_COMPARE_MATCH_DEFINER = 4207,
+
+	MLX5HWS_DEBUG_RES_TYPE_ACTION_STE_TABLE = 4300,
 };
 
 static inline u64
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
index c8cc0c8115f5..5cc0dc002ac1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
@@ -158,6 +158,218 @@ struct mlx5hws_definer_conv_data {
 	u32 match_flags;
 };
 
+#define HWS_DEFINER_ENTRY(name)[MLX5HWS_DEFINER_FNAME_##name] = #name
+
+static const char * const hws_definer_fname_to_str[] = {
+	HWS_DEFINER_ENTRY(ETH_SMAC_47_16_O),
+	HWS_DEFINER_ENTRY(ETH_SMAC_47_16_I),
+	HWS_DEFINER_ENTRY(ETH_SMAC_15_0_O),
+	HWS_DEFINER_ENTRY(ETH_SMAC_15_0_I),
+	HWS_DEFINER_ENTRY(ETH_DMAC_47_16_O),
+	HWS_DEFINER_ENTRY(ETH_DMAC_47_16_I),
+	HWS_DEFINER_ENTRY(ETH_DMAC_15_0_O),
+	HWS_DEFINER_ENTRY(ETH_DMAC_15_0_I),
+	HWS_DEFINER_ENTRY(ETH_TYPE_O),
+	HWS_DEFINER_ENTRY(ETH_TYPE_I),
+	HWS_DEFINER_ENTRY(ETH_L3_TYPE_O),
+	HWS_DEFINER_ENTRY(ETH_L3_TYPE_I),
+	HWS_DEFINER_ENTRY(VLAN_TYPE_O),
+	HWS_DEFINER_ENTRY(VLAN_TYPE_I),
+	HWS_DEFINER_ENTRY(VLAN_FIRST_PRIO_O),
+	HWS_DEFINER_ENTRY(VLAN_FIRST_PRIO_I),
+	HWS_DEFINER_ENTRY(VLAN_CFI_O),
+	HWS_DEFINER_ENTRY(VLAN_CFI_I),
+	HWS_DEFINER_ENTRY(VLAN_ID_O),
+	HWS_DEFINER_ENTRY(VLAN_ID_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_TYPE_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_TYPE_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_PRIO_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_PRIO_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_CFI_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_CFI_I),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_ID_O),
+	HWS_DEFINER_ENTRY(VLAN_SECOND_ID_I),
+	HWS_DEFINER_ENTRY(IPV4_IHL_O),
+	HWS_DEFINER_ENTRY(IPV4_IHL_I),
+	HWS_DEFINER_ENTRY(IP_DSCP_O),
+	HWS_DEFINER_ENTRY(IP_DSCP_I),
+	HWS_DEFINER_ENTRY(IP_ECN_O),
+	HWS_DEFINER_ENTRY(IP_ECN_I),
+	HWS_DEFINER_ENTRY(IP_TTL_O),
+	HWS_DEFINER_ENTRY(IP_TTL_I),
+	HWS_DEFINER_ENTRY(IPV4_DST_O),
+	HWS_DEFINER_ENTRY(IPV4_DST_I),
+	HWS_DEFINER_ENTRY(IPV4_SRC_O),
+	HWS_DEFINER_ENTRY(IPV4_SRC_I),
+	HWS_DEFINER_ENTRY(IP_VERSION_O),
+	HWS_DEFINER_ENTRY(IP_VERSION_I),
+	HWS_DEFINER_ENTRY(IP_FRAG_O),
+	HWS_DEFINER_ENTRY(IP_FRAG_I),
+	HWS_DEFINER_ENTRY(IP_LEN_O),
+	HWS_DEFINER_ENTRY(IP_LEN_I),
+	HWS_DEFINER_ENTRY(IP_TOS_O),
+	HWS_DEFINER_ENTRY(IP_TOS_I),
+	HWS_DEFINER_ENTRY(IPV6_FLOW_LABEL_O),
+	HWS_DEFINER_ENTRY(IPV6_FLOW_LABEL_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_127_96_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_95_64_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_63_32_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_31_0_O),
+	HWS_DEFINER_ENTRY(IPV6_DST_127_96_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_95_64_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_63_32_I),
+	HWS_DEFINER_ENTRY(IPV6_DST_31_0_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_127_96_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_95_64_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_63_32_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_31_0_O),
+	HWS_DEFINER_ENTRY(IPV6_SRC_127_96_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_95_64_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_63_32_I),
+	HWS_DEFINER_ENTRY(IPV6_SRC_31_0_I),
+	HWS_DEFINER_ENTRY(IP_PROTOCOL_O),
+	HWS_DEFINER_ENTRY(IP_PROTOCOL_I),
+	HWS_DEFINER_ENTRY(L4_SPORT_O),
+	HWS_DEFINER_ENTRY(L4_SPORT_I),
+	HWS_DEFINER_ENTRY(L4_DPORT_O),
+	HWS_DEFINER_ENTRY(L4_DPORT_I),
+	HWS_DEFINER_ENTRY(TCP_FLAGS_I),
+	HWS_DEFINER_ENTRY(TCP_FLAGS_O),
+	HWS_DEFINER_ENTRY(TCP_SEQ_NUM),
+	HWS_DEFINER_ENTRY(TCP_ACK_NUM),
+	HWS_DEFINER_ENTRY(GTP_TEID),
+	HWS_DEFINER_ENTRY(GTP_MSG_TYPE),
+	HWS_DEFINER_ENTRY(GTP_EXT_FLAG),
+	HWS_DEFINER_ENTRY(GTP_NEXT_EXT_HDR),
+	HWS_DEFINER_ENTRY(GTP_EXT_HDR_PDU),
+	HWS_DEFINER_ENTRY(GTP_EXT_HDR_QFI),
+	HWS_DEFINER_ENTRY(GTPU_DW0),
+	HWS_DEFINER_ENTRY(GTPU_FIRST_EXT_DW0),
+	HWS_DEFINER_ENTRY(GTPU_DW2),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_0),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_1),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_2),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_3),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_4),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_5),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_6),
+	HWS_DEFINER_ENTRY(FLEX_PARSER_7),
+	HWS_DEFINER_ENTRY(VPORT_REG_C_0),
+	HWS_DEFINER_ENTRY(VXLAN_FLAGS),
+	HWS_DEFINER_ENTRY(VXLAN_VNI),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_FLAGS),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_RSVD0),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_PROTO),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_VNI),
+	HWS_DEFINER_ENTRY(VXLAN_GPE_RSVD1),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_LEN),
+	HWS_DEFINER_ENTRY(GENEVE_OAM),
+	HWS_DEFINER_ENTRY(GENEVE_PROTO),
+	HWS_DEFINER_ENTRY(GENEVE_VNI),
+	HWS_DEFINER_ENTRY(SOURCE_QP),
+	HWS_DEFINER_ENTRY(SOURCE_GVMI),
+	HWS_DEFINER_ENTRY(REG_0),
+	HWS_DEFINER_ENTRY(REG_1),
+	HWS_DEFINER_ENTRY(REG_2),
+	HWS_DEFINER_ENTRY(REG_3),
+	HWS_DEFINER_ENTRY(REG_4),
+	HWS_DEFINER_ENTRY(REG_5),
+	HWS_DEFINER_ENTRY(REG_6),
+	HWS_DEFINER_ENTRY(REG_7),
+	HWS_DEFINER_ENTRY(REG_8),
+	HWS_DEFINER_ENTRY(REG_9),
+	HWS_DEFINER_ENTRY(REG_10),
+	HWS_DEFINER_ENTRY(REG_11),
+	HWS_DEFINER_ENTRY(REG_A),
+	HWS_DEFINER_ENTRY(REG_B),
+	HWS_DEFINER_ENTRY(GRE_KEY_PRESENT),
+	HWS_DEFINER_ENTRY(GRE_C),
+	HWS_DEFINER_ENTRY(GRE_K),
+	HWS_DEFINER_ENTRY(GRE_S),
+	HWS_DEFINER_ENTRY(GRE_PROTOCOL),
+	HWS_DEFINER_ENTRY(GRE_OPT_KEY),
+	HWS_DEFINER_ENTRY(GRE_OPT_SEQ),
+	HWS_DEFINER_ENTRY(GRE_OPT_CHECKSUM),
+	HWS_DEFINER_ENTRY(INTEGRITY_O),
+	HWS_DEFINER_ENTRY(INTEGRITY_I),
+	HWS_DEFINER_ENTRY(ICMP_DW1),
+	HWS_DEFINER_ENTRY(ICMP_DW2),
+	HWS_DEFINER_ENTRY(ICMP_DW3),
+	HWS_DEFINER_ENTRY(IPSEC_SPI),
+	HWS_DEFINER_ENTRY(IPSEC_SEQUENCE_NUMBER),
+	HWS_DEFINER_ENTRY(IPSEC_SYNDROME),
+	HWS_DEFINER_ENTRY(MPLS0_O),
+	HWS_DEFINER_ENTRY(MPLS1_O),
+	HWS_DEFINER_ENTRY(MPLS2_O),
+	HWS_DEFINER_ENTRY(MPLS3_O),
+	HWS_DEFINER_ENTRY(MPLS4_O),
+	HWS_DEFINER_ENTRY(MPLS0_I),
+	HWS_DEFINER_ENTRY(MPLS1_I),
+	HWS_DEFINER_ENTRY(MPLS2_I),
+	HWS_DEFINER_ENTRY(MPLS3_I),
+	HWS_DEFINER_ENTRY(MPLS4_I),
+	HWS_DEFINER_ENTRY(FLEX_PARSER0_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER1_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER2_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER3_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER4_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER5_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER6_OK),
+	HWS_DEFINER_ENTRY(FLEX_PARSER7_OK),
+	HWS_DEFINER_ENTRY(OKS2_MPLS0_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS1_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS2_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS3_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS4_O),
+	HWS_DEFINER_ENTRY(OKS2_MPLS0_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS1_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS2_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS3_I),
+	HWS_DEFINER_ENTRY(OKS2_MPLS4_I),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_0),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_1),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_2),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_3),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_4),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_5),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_6),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_OK_7),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_0),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_1),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_2),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_3),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_4),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_5),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_6),
+	HWS_DEFINER_ENTRY(GENEVE_OPT_DW_7),
+	HWS_DEFINER_ENTRY(IB_L4_OPCODE),
+	HWS_DEFINER_ENTRY(IB_L4_QPN),
+	HWS_DEFINER_ENTRY(IB_L4_A),
+	HWS_DEFINER_ENTRY(RANDOM_NUM),
+	HWS_DEFINER_ENTRY(PTYPE_L2_O),
+	HWS_DEFINER_ENTRY(PTYPE_L2_I),
+	HWS_DEFINER_ENTRY(PTYPE_L3_O),
+	HWS_DEFINER_ENTRY(PTYPE_L3_I),
+	HWS_DEFINER_ENTRY(PTYPE_L4_O),
+	HWS_DEFINER_ENTRY(PTYPE_L4_I),
+	HWS_DEFINER_ENTRY(PTYPE_L4_EXT_O),
+	HWS_DEFINER_ENTRY(PTYPE_L4_EXT_I),
+	HWS_DEFINER_ENTRY(PTYPE_FRAG_O),
+	HWS_DEFINER_ENTRY(PTYPE_FRAG_I),
+	HWS_DEFINER_ENTRY(TNL_HDR_0),
+	HWS_DEFINER_ENTRY(TNL_HDR_1),
+	HWS_DEFINER_ENTRY(TNL_HDR_2),
+	HWS_DEFINER_ENTRY(TNL_HDR_3),
+	[MLX5HWS_DEFINER_FNAME_MAX] = "DEFINER_FNAME_UNKNOWN",
+};
+
+const char *mlx5hws_definer_fname_to_str(enum mlx5hws_definer_fname fname)
+{
+	if (fname > MLX5HWS_DEFINER_FNAME_MAX)
+		fname = MLX5HWS_DEFINER_FNAME_MAX;
+	return hws_definer_fname_to_str[fname];
+}
+
 static void
 hws_definer_ones_set(struct mlx5hws_definer_fc *fc,
 		     void *match_param,
@@ -509,7 +721,7 @@ static int
 hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 		       u32 *match_param)
 {
-	bool is_s_ipv6, is_d_ipv6, smac_set, dmac_set;
+	bool is_ipv6, smac_set, dmac_set, ip_addr_set, ip_ver_set;
 	struct mlx5hws_definer_fc *fc = cd->fc;
 	struct mlx5hws_definer_fc *curr_fc;
 	u32 *s_ipv6, *d_ipv6;
@@ -521,6 +733,20 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 		return -EINVAL;
 	}
 
+	ip_addr_set = HWS_IS_FLD_SET_SZ(match_param,
+					outer_headers.src_ipv4_src_ipv6,
+					0x80) ||
+		      HWS_IS_FLD_SET_SZ(match_param,
+					outer_headers.dst_ipv4_dst_ipv6, 0x80);
+	ip_ver_set = HWS_IS_FLD_SET(match_param, outer_headers.ip_version) ||
+		     HWS_IS_FLD_SET(match_param, outer_headers.ethertype);
+
+	if (ip_addr_set && !ip_ver_set) {
+		mlx5hws_err(cd->ctx,
+			    "Unsupported match on IP address without version or ethertype\n");
+		return -EINVAL;
+	}
+
 	/* L2 Check ethertype */
 	HWS_SET_HDR(fc, match_param, ETH_TYPE_O,
 		    outer_headers.ethertype,
@@ -570,10 +796,16 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 			      outer_headers.dst_ipv4_dst_ipv6.ipv6_layout);
 
 	/* Assume IPv6 is used if ipv6 bits are set */
-	is_s_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2];
-	is_d_ipv6 = d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+	is_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2] ||
+		  d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+
+	/* IHL is an IPv4-specific field. */
+	if (is_ipv6 && HWS_IS_FLD_SET(match_param, outer_headers.ipv4_ihl)) {
+		mlx5hws_err(cd->ctx, "Unsupported match on IPv6 address and IPv4 IHL\n");
+		return -EINVAL;
+	}
 
-	if (is_s_ipv6) {
+	if (is_ipv6) {
 		/* Handle IPv6 source address */
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_127_96_O,
 			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -587,13 +819,6 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_31_0_O,
 			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_src_outer.ipv6_address_31_0);
-	} else {
-		/* Handle IPv4 source address */
-		HWS_SET_HDR(fc, match_param, IPV4_SRC_O,
-			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
-			    ipv4_src_dest_outer.source_address);
-	}
-	if (is_d_ipv6) {
 		/* Handle IPv6 destination address */
 		HWS_SET_HDR(fc, match_param, IPV6_DST_127_96_O,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -608,6 +833,10 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_dst_outer.ipv6_address_31_0);
 	} else {
+		/* Handle IPv4 source address */
+		HWS_SET_HDR(fc, match_param, IPV4_SRC_O,
+			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_outer.source_address);
 		/* Handle IPv4 destination address */
 		HWS_SET_HDR(fc, match_param, IPV4_DST_O,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
@@ -665,7 +894,7 @@ static int
 hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 		       u32 *match_param)
 {
-	bool is_s_ipv6, is_d_ipv6, smac_set, dmac_set;
+	bool is_ipv6, smac_set, dmac_set, ip_addr_set, ip_ver_set;
 	struct mlx5hws_definer_fc *fc = cd->fc;
 	struct mlx5hws_definer_fc *curr_fc;
 	u32 *s_ipv6, *d_ipv6;
@@ -677,6 +906,20 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 		return -EINVAL;
 	}
 
+	ip_addr_set = HWS_IS_FLD_SET_SZ(match_param,
+					inner_headers.src_ipv4_src_ipv6,
+					0x80) ||
+		      HWS_IS_FLD_SET_SZ(match_param,
+					inner_headers.dst_ipv4_dst_ipv6, 0x80);
+	ip_ver_set = HWS_IS_FLD_SET(match_param, inner_headers.ip_version) ||
+		     HWS_IS_FLD_SET(match_param, inner_headers.ethertype);
+
+	if (ip_addr_set && !ip_ver_set) {
+		mlx5hws_err(cd->ctx,
+			    "Unsupported match on IP address without version or ethertype\n");
+		return -EINVAL;
+	}
+
 	/* L2 Check ethertype */
 	HWS_SET_HDR(fc, match_param, ETH_TYPE_I,
 		    inner_headers.ethertype,
@@ -728,10 +971,16 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 			      inner_headers.dst_ipv4_dst_ipv6.ipv6_layout);
 
 	/* Assume IPv6 is used if ipv6 bits are set */
-	is_s_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2];
-	is_d_ipv6 = d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+	is_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2] ||
+		  d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
 
-	if (is_s_ipv6) {
+	/* IHL is an IPv4-specific field. */
+	if (is_ipv6 && HWS_IS_FLD_SET(match_param, inner_headers.ipv4_ihl)) {
+		mlx5hws_err(cd->ctx, "Unsupported match on IPv6 address and IPv4 IHL\n");
+		return -EINVAL;
+	}
+
+	if (is_ipv6) {
 		/* Handle IPv6 source address */
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_127_96_I,
 			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -745,13 +994,6 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_31_0_I,
 			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_src_inner.ipv6_address_31_0);
-	} else {
-		/* Handle IPv4 source address */
-		HWS_SET_HDR(fc, match_param, IPV4_SRC_I,
-			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
-			    ipv4_src_dest_inner.source_address);
-	}
-	if (is_d_ipv6) {
 		/* Handle IPv6 destination address */
 		HWS_SET_HDR(fc, match_param, IPV6_DST_127_96_I,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -766,6 +1008,10 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_dst_inner.ipv6_address_31_0);
 	} else {
+		/* Handle IPv4 source address */
+		HWS_SET_HDR(fc, match_param, IPV4_SRC_I,
+			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_inner.source_address);
 		/* Handle IPv4 destination address */
 		HWS_SET_HDR(fc, match_param, IPV4_DST_I,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
index 5c1a2086efba..62da55389331 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
@@ -831,4 +831,6 @@ mlx5hws_definer_conv_match_params_to_compressed_fc(struct mlx5hws_context *ctx,
 						   u32 *match_param,
 						   int *fc_sz);
 
+const char *mlx5hws_definer_fname_to_str(enum mlx5hws_definer_fname fname);
+
 #endif /* HWS_DEFINER_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
index 1b787cd66e6f..9d1c0e4b224a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
@@ -1081,13 +1081,8 @@ static int mlx5_cmd_hws_create_fte(struct mlx5_flow_root_namespace *ns,
 	struct mlx5hws_bwc_rule *rule;
 	int err = 0;
 
-	if (mlx5_fs_cmd_is_fw_term_table(ft)) {
-		/* Packet reformat on terminamtion table not supported yet */
-		if (fte->act_dests.action.action &
-		    MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT)
-			return -EOPNOTSUPP;
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
 		return mlx5_fs_cmd_get_fw_cmds()->create_fte(ns, ft, group, fte);
-	}
 
 	err = mlx5_fs_fte_get_hws_actions(ns, ft, group, fte, &ractions);
 	if (err)
@@ -1362,7 +1357,7 @@ mlx5_cmd_hws_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
 		pkt_reformat->fs_hws_action.pr_data = pr_data;
 	}
 
-	pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_SW;
+	pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_HWS;
 	pkt_reformat->fs_hws_action.hws_action = hws_action;
 	return 0;
 
@@ -1380,6 +1375,15 @@ static void mlx5_cmd_hws_packet_reformat_dealloc(struct mlx5_flow_root_namespace
 	struct mlx5_fs_hws_pr *pr_data;
 	struct mlx5_fs_pool *pr_pool;
 
+	if (pkt_reformat->fs_hws_action.fw_reformat_id != 0) {
+		struct mlx5_pkt_reformat fw_pkt_reformat = { 0 };
+
+		fw_pkt_reformat.id = pkt_reformat->fs_hws_action.fw_reformat_id;
+		mlx5_fs_cmd_get_fw_cmds()->
+			packet_reformat_dealloc(ns, &fw_pkt_reformat);
+		pkt_reformat->fs_hws_action.fw_reformat_id = 0;
+	}
+
 	if (pkt_reformat->reformat_type == MLX5_REFORMAT_TYPE_REMOVE_HDR)
 		return;
 
@@ -1499,6 +1503,7 @@ static int mlx5_cmd_hws_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 		err = -ENOMEM;
 		goto release_mh;
 	}
+	mutex_init(&modify_hdr->fs_hws_action.lock);
 	modify_hdr->fs_hws_action.mh_data = mh_data;
 	modify_hdr->fs_hws_action.fs_pool = pool;
 	modify_hdr->owner = MLX5_FLOW_RESOURCE_OWNER_SW;
@@ -1532,6 +1537,58 @@ static void mlx5_cmd_hws_modify_header_dealloc(struct mlx5_flow_root_namespace *
 	modify_hdr->fs_hws_action.mh_data = NULL;
 }
 
+int
+mlx5_fs_hws_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				       u32 *reformat_id)
+{
+	enum mlx5_flow_namespace_type ns_type = pkt_reformat->ns_type;
+	struct mutex *lock = &pkt_reformat->fs_hws_action.lock;
+	u32 *id = &pkt_reformat->fs_hws_action.fw_reformat_id;
+	struct mlx5_pkt_reformat fw_pkt_reformat = { 0 };
+	struct mlx5_pkt_reformat_params params = { 0 };
+	struct mlx5_flow_root_namespace *ns;
+	struct mlx5_core_dev *dev;
+	int ret;
+
+	mutex_lock(lock);
+
+	if (*id != 0) {
+		*reformat_id = *id;
+		ret = 0;
+		goto unlock;
+	}
+
+	dev = mlx5hws_action_get_dev(pkt_reformat->fs_hws_action.hws_action);
+	if (!dev) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	ns = mlx5_get_root_namespace(dev, ns_type);
+	if (!ns) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	params.type = pkt_reformat->reformat_type;
+	params.size = pkt_reformat->fs_hws_action.pr_data->data_size;
+	params.data = pkt_reformat->fs_hws_action.pr_data->data;
+
+	ret = mlx5_fs_cmd_get_fw_cmds()->
+		packet_reformat_alloc(ns, &params, ns_type, &fw_pkt_reformat);
+	if (ret)
+		goto unlock;
+
+	*id = fw_pkt_reformat.id;
+	*reformat_id = *id;
+	ret = 0;
+
+unlock:
+	mutex_unlock(lock);
+
+	return ret;
+}
+
 static int mlx5_cmd_hws_create_match_definer(struct mlx5_flow_root_namespace *ns,
 					     u16 format_id, u32 *match_mask)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
index 8b56298288da..b92d55b2d147 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
@@ -41,6 +41,11 @@ struct mlx5_fs_hws_action {
 	struct mlx5_fs_pool *fs_pool;
 	struct mlx5_fs_hws_pr *pr_data;
 	struct mlx5_fs_hws_mh *mh_data;
+	u32 fw_reformat_id;
+	/* Protect `fw_reformat_id` against being initialized from multiple
+	 * threads.
+	 */
+	struct mutex lock;
 };
 
 struct mlx5_fs_hws_matcher {
@@ -84,12 +89,23 @@ void mlx5_fs_put_hws_action(struct mlx5_fs_hws_data *fs_hws_data);
 
 #ifdef CONFIG_MLX5_HW_STEERING
 
+int
+mlx5_fs_hws_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				       u32 *reformat_id);
+
 bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev);
 
 const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void);
 
 #else
 
+static inline int
+mlx5_fs_hws_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				       u32 *reformat_id)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev)
 {
 	return false;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h
index 30ccd635b505..21279d503117 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h
@@ -17,6 +17,7 @@
 #include "context.h"
 #include "table.h"
 #include "send.h"
+#include "action_ste_pool.h"
 #include "rule.h"
 #include "cmd.h"
 #include "action.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
index b61864b32053..ce28ee1c0e41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
@@ -3,25 +3,6 @@
 
 #include "internal.h"
 
-enum mlx5hws_matcher_rtc_type {
-	HWS_MATCHER_RTC_TYPE_MATCH,
-	HWS_MATCHER_RTC_TYPE_STE_ARRAY,
-	HWS_MATCHER_RTC_TYPE_MAX,
-};
-
-static const char * const mlx5hws_matcher_rtc_type_str[] = {
-	[HWS_MATCHER_RTC_TYPE_MATCH] = "MATCH",
-	[HWS_MATCHER_RTC_TYPE_STE_ARRAY] = "STE_ARRAY",
-	[HWS_MATCHER_RTC_TYPE_MAX] = "UNKNOWN",
-};
-
-static const char *hws_matcher_rtc_type_to_str(enum mlx5hws_matcher_rtc_type rtc_type)
-{
-	if (rtc_type > HWS_MATCHER_RTC_TYPE_MAX)
-		rtc_type = HWS_MATCHER_RTC_TYPE_MAX;
-	return mlx5hws_matcher_rtc_type_str[rtc_type];
-}
-
 static bool hws_matcher_requires_col_tbl(u8 log_num_of_rules)
 {
 	/* Collision table concatenation is done only for large rule tables */
@@ -42,19 +23,199 @@ static void hws_matcher_destroy_end_ft(struct mlx5hws_matcher *matcher)
 	mlx5hws_table_destroy_default_ft(matcher->tbl, matcher->end_ft_id);
 }
 
+int mlx5hws_matcher_update_end_ft_isolated(struct mlx5hws_table *tbl,
+					   u32 miss_ft_id)
+{
+	struct mlx5hws_matcher *tmp_matcher;
+
+	if (list_empty(&tbl->matchers_list))
+		return -EINVAL;
+
+	/* Update isolated_matcher_end_ft_id attribute for all
+	 * the matchers in isolated table.
+	 */
+	list_for_each_entry(tmp_matcher, &tbl->matchers_list, list_node)
+		tmp_matcher->attr.isolated_matcher_end_ft_id = miss_ft_id;
+
+	tmp_matcher = list_last_entry(&tbl->matchers_list,
+				      struct mlx5hws_matcher,
+				      list_node);
+
+	return mlx5hws_table_ft_set_next_ft(tbl->ctx,
+					    tmp_matcher->end_ft_id,
+					    tbl->fw_ft_type,
+					    miss_ft_id);
+}
+
+static int hws_matcher_connect_end_ft_isolated(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	u32 end_ft_id;
+	int ret;
+
+	/* Reset end_ft next RTCs */
+	ret = mlx5hws_table_ft_set_next_rtc(tbl->ctx,
+					    matcher->end_ft_id,
+					    matcher->tbl->fw_ft_type,
+					    0, 0);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to reset FT's next RTCs\n");
+		return ret;
+	}
+
+	/* Connect isolated matcher's end_ft to the complex matcher's end FT */
+	end_ft_id = matcher->attr.isolated_matcher_end_ft_id;
+	ret = mlx5hws_table_ft_set_next_ft(tbl->ctx,
+					   matcher->end_ft_id,
+					   matcher->tbl->fw_ft_type,
+					   end_ft_id);
+
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to set FT's miss_ft_id\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int hws_matcher_create_end_ft_isolated(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	int ret;
+
+	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev,
+					      tbl,
+					      &matcher->end_ft_id);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to create end flow table\n");
+		return ret;
+	}
+
+	ret = hws_matcher_connect_end_ft_isolated(matcher);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to connect end FT\n");
+		goto destroy_default_ft;
+	}
+
+	return 0;
+
+destroy_default_ft:
+	mlx5hws_table_destroy_default_ft(tbl, matcher->end_ft_id);
+	return ret;
+}
+
 static int hws_matcher_create_end_ft(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_table *tbl = matcher->tbl;
 	int ret;
 
-	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, &matcher->end_ft_id);
+	if (mlx5hws_matcher_is_isolated(matcher))
+		ret = hws_matcher_create_end_ft_isolated(matcher);
+	else
+		ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl,
+						      &matcher->end_ft_id);
+
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Failed to create matcher end flow table\n");
 		return ret;
 	}
+
 	return 0;
 }
 
+static int hws_matcher_connect_isolated_first(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	int ret;
+
+	/* Isolated matcher's end_ft is already pointing to the end_ft
+	 * of the complex matcher - it was set at creation of end_ft,
+	 * so no need to connect it.
+	 * We still need to connect the isolated table's start FT to
+	 * this matcher's RTC.
+	 */
+	ret = mlx5hws_table_ft_set_next_rtc(ctx,
+					    tbl->ft_id,
+					    tbl->fw_ft_type,
+					    matcher->match_ste.rtc_0_id,
+					    matcher->match_ste.rtc_1_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Isolated matcher: failed to connect start FT to match RTC\n");
+		return ret;
+	}
+
+	/* Reset table's FT default miss (drop refcount) */
+	ret = mlx5hws_table_ft_set_default_next_ft(tbl, tbl->ft_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Isolated matcher: failed to reset table ft default miss\n");
+		return ret;
+	}
+
+	list_add(&matcher->list_node, &tbl->matchers_list);
+
+	return ret;
+}
+
+static int hws_matcher_connect_isolated_last(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	struct mlx5hws_matcher *last;
+	int ret;
+
+	last = list_last_entry(&tbl->matchers_list,
+			       struct mlx5hws_matcher,
+			       list_node);
+
+	/* New matcher's end_ft is already pointing to the end_ft of
+	 * the complex matcher.
+	 * Connect previous matcher's end_ft to this new matcher RTC.
+	 */
+	ret = mlx5hws_table_ft_set_next_rtc(ctx,
+					    last->end_ft_id,
+					    tbl->fw_ft_type,
+					    matcher->match_ste.rtc_0_id,
+					    matcher->match_ste.rtc_1_id);
+	if (ret) {
+		mlx5hws_err(ctx,
+			    "Isolated matcher: failed to connect matcher end_ft to new match RTC\n");
+		return ret;
+	}
+
+	/* Reset prev matcher FT default miss (drop refcount) */
+	ret = mlx5hws_table_ft_set_default_next_ft(tbl, last->end_ft_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Isolated matcher: failed to reset matcher ft default miss\n");
+		return ret;
+	}
+
+	/* Insert after the last matcher */
+	list_add(&matcher->list_node, &last->list_node);
+
+	return 0;
+}
+
+static int hws_matcher_connect_isolated(struct mlx5hws_matcher *matcher)
+{
+	/* Isolated matcher is expected to be the only one in its table.
+	 * However, it can have a collision matcher, and it can go through
+	 * rehash process, in which case we will temporary have both old and
+	 * new matchers in the isolated table.
+	 * Check if this is the first matcher in the isolated table.
+	 */
+	if (list_empty(&matcher->tbl->matchers_list))
+		return hws_matcher_connect_isolated_first(matcher);
+
+	/* If this wasn't the first matcher, then we have 3 possible cases:
+	 *  - this is a collision matcher for the first matcher
+	 *  - this is a new rehash dest matcher
+	 *  - this is a collision matcher for the new rehash dest matcher
+	 * The logic to add new matcher is the same for all these cases.
+	 */
+	return hws_matcher_connect_isolated_last(matcher);
+}
+
 static int hws_matcher_connect(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_table *tbl = matcher->tbl;
@@ -64,6 +225,9 @@ static int hws_matcher_connect(struct mlx5hws_matcher *matcher)
 	struct mlx5hws_matcher *tmp_matcher;
 	int ret;
 
+	if (mlx5hws_matcher_is_isolated(matcher))
+		return hws_matcher_connect_isolated(matcher);
+
 	/* Find location in matcher list */
 	if (list_empty(&tbl->matchers_list)) {
 		list_add(&matcher->list_node, &tbl->matchers_list);
@@ -140,6 +304,92 @@ remove_from_list:
 	return ret;
 }
 
+static int hws_matcher_disconnect_isolated(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_matcher *first, *last, *prev, *next;
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	u32 end_ft_id;
+	int ret;
+
+	first = list_first_entry(&tbl->matchers_list,
+				 struct mlx5hws_matcher,
+				 list_node);
+	last = list_last_entry(&tbl->matchers_list,
+			       struct mlx5hws_matcher,
+			       list_node);
+	prev = list_prev_entry(matcher, list_node);
+	next = list_next_entry(matcher, list_node);
+
+	list_del_init(&matcher->list_node);
+
+	if (first == last) {
+		/* This was the only matcher in the list.
+		 * Reset isolated table FT next RTCs and connect it
+		 * to the whole complex matcher end FT instead.
+		 */
+		ret = mlx5hws_table_ft_set_next_rtc(ctx,
+						    tbl->ft_id,
+						    tbl->fw_ft_type,
+						    0, 0);
+		if (ret) {
+			mlx5hws_err(tbl->ctx, "Isolated matcher: failed to reset FT's next RTCs\n");
+			return ret;
+		}
+
+		end_ft_id = matcher->attr.isolated_matcher_end_ft_id;
+		ret = mlx5hws_table_ft_set_next_ft(tbl->ctx,
+						   tbl->ft_id,
+						   tbl->fw_ft_type,
+						   end_ft_id);
+		if (ret) {
+			mlx5hws_err(tbl->ctx, "Isolated matcher: failed to set FT's miss_ft_id\n");
+			return ret;
+		}
+
+		return 0;
+	}
+
+	/* At this point we know that there are more matchers in the list */
+
+	if (matcher == first) {
+		/* We've disconnected the first matcher.
+		 * Now update isolated table default FT.
+		 */
+		if (!next)
+			return -EINVAL;
+		return mlx5hws_table_ft_set_next_rtc(ctx,
+						     tbl->ft_id,
+						     tbl->fw_ft_type,
+						     next->match_ste.rtc_0_id,
+						     next->match_ste.rtc_1_id);
+	}
+
+	if (matcher == last) {
+		/* If we've disconnected the last matcher - update prev
+		 * matcher's end_ft to point to the complex matcher end_ft.
+		 */
+		if (!prev)
+			return -EINVAL;
+		return hws_matcher_connect_end_ft_isolated(prev);
+	}
+
+	/* This wasn't the first or the last matcher, which means that it has
+	 * both prev and next matchers. Note that this only happens if we're
+	 * disconnecting collision matcher of the old matcher during rehash.
+	 */
+	if (!prev || !next ||
+	    !(matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION))
+		return -EINVAL;
+
+	/* Update prev end FT to point to next match RTC */
+	return mlx5hws_table_ft_set_next_rtc(ctx,
+					     prev->end_ft_id,
+					     tbl->fw_ft_type,
+					     next->match_ste.rtc_0_id,
+					     next->match_ste.rtc_1_id);
+}
+
 static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_matcher *next = NULL, *prev = NULL;
@@ -147,6 +397,9 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 	u32 prev_ft_id = tbl->ft_id;
 	int ret;
 
+	if (mlx5hws_matcher_is_isolated(matcher))
+		return hws_matcher_disconnect_isolated(matcher);
+
 	if (!list_is_first(&matcher->list_node, &tbl->matchers_list)) {
 		prev = list_prev_entry(matcher, list_node);
 		prev_ft_id = prev->end_ft_id;
@@ -197,149 +450,96 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 
 static void hws_matcher_set_rtc_attr_sz(struct mlx5hws_matcher *matcher,
 					struct mlx5hws_cmd_rtc_create_attr *rtc_attr,
-					enum mlx5hws_matcher_rtc_type rtc_type,
 					bool is_mirror)
 {
-	struct mlx5hws_pool_chunk *ste = &matcher->action_ste.ste;
 	enum mlx5hws_matcher_flow_src flow_src = matcher->attr.optimize_flow_src;
-	bool is_match_rtc = rtc_type == HWS_MATCHER_RTC_TYPE_MATCH;
 
 	if ((flow_src == MLX5HWS_MATCHER_FLOW_SRC_VPORT && !is_mirror) ||
 	    (flow_src == MLX5HWS_MATCHER_FLOW_SRC_WIRE && is_mirror)) {
 		/* Optimize FDB RTC */
 		rtc_attr->log_size = 0;
 		rtc_attr->log_depth = 0;
-	} else {
-		/* Keep original values */
-		rtc_attr->log_size = is_match_rtc ? matcher->attr.table.sz_row_log : ste->order;
-		rtc_attr->log_depth = is_match_rtc ? matcher->attr.table.sz_col_log : 0;
 	}
 }
 
-static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher,
-				  enum mlx5hws_matcher_rtc_type rtc_type)
+static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher)
 {
 	struct mlx5hws_matcher_attr *attr = &matcher->attr;
 	struct mlx5hws_cmd_rtc_create_attr rtc_attr = {0};
 	struct mlx5hws_match_template *mt = matcher->mt;
 	struct mlx5hws_context *ctx = matcher->tbl->ctx;
-	struct mlx5hws_action_default_stc *default_stc;
-	struct mlx5hws_matcher_action_ste *action_ste;
 	struct mlx5hws_table *tbl = matcher->tbl;
-	struct mlx5hws_pool *ste_pool, *stc_pool;
-	struct mlx5hws_pool_chunk *ste;
-	u32 *rtc_0_id, *rtc_1_id;
 	u32 obj_id;
 	int ret;
 
-	switch (rtc_type) {
-	case HWS_MATCHER_RTC_TYPE_MATCH:
-		rtc_0_id = &matcher->match_ste.rtc_0_id;
-		rtc_1_id = &matcher->match_ste.rtc_1_id;
-		ste_pool = matcher->match_ste.pool;
-		ste = &matcher->match_ste.ste;
-		ste->order = attr->table.sz_col_log + attr->table.sz_row_log;
-
-		rtc_attr.log_size = attr->table.sz_row_log;
-		rtc_attr.log_depth = attr->table.sz_col_log;
-		rtc_attr.is_frst_jumbo = mlx5hws_matcher_mt_is_jumbo(mt);
-		rtc_attr.is_scnd_range = 0;
-		rtc_attr.miss_ft_id = matcher->end_ft_id;
-
-		if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_HASH) {
-			/* The usual Hash Table */
-			rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_HASH;
-
-			/* The first mt is used since all share the same definer */
-			rtc_attr.match_definer_0 = mlx5hws_definer_get_id(mt->definer);
-		} else if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX) {
-			rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
-			rtc_attr.num_hash_definer = 1;
-
-			if (attr->distribute_mode == MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH) {
-				/* Hash Split Table */
-				rtc_attr.access_index_mode = MLX5_IFC_RTC_STE_ACCESS_MODE_BY_HASH;
-				rtc_attr.match_definer_0 = mlx5hws_definer_get_id(mt->definer);
-			} else if (attr->distribute_mode == MLX5HWS_MATCHER_DISTRIBUTE_BY_LINEAR) {
-				/* Linear Lookup Table */
-				rtc_attr.access_index_mode = MLX5_IFC_RTC_STE_ACCESS_MODE_LINEAR;
-				rtc_attr.match_definer_0 = ctx->caps->linear_match_definer;
-			}
-		}
-
-		/* Match pool requires implicit allocation */
-		ret = mlx5hws_pool_chunk_alloc(ste_pool, ste);
-		if (ret) {
-			mlx5hws_err(ctx, "Failed to allocate STE for %s RTC",
-				    hws_matcher_rtc_type_to_str(rtc_type));
-			return ret;
+	rtc_attr.log_size = attr->table.sz_row_log;
+	rtc_attr.log_depth = attr->table.sz_col_log;
+	rtc_attr.is_frst_jumbo = mlx5hws_matcher_mt_is_jumbo(mt);
+	rtc_attr.is_scnd_range = 0;
+	rtc_attr.miss_ft_id = matcher->end_ft_id;
+
+	if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_HASH) {
+		/* The usual Hash Table */
+		rtc_attr.update_index_mode =
+			MLX5_IFC_RTC_STE_UPDATE_MODE_BY_HASH;
+
+		/* The first mt is used since all share the same definer */
+		rtc_attr.match_definer_0 = mlx5hws_definer_get_id(mt->definer);
+	} else if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX) {
+		rtc_attr.update_index_mode =
+			MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
+		rtc_attr.num_hash_definer = 1;
+
+		if (attr->distribute_mode ==
+		    MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH) {
+			/* Hash Split Table */
+			rtc_attr.access_index_mode =
+				MLX5_IFC_RTC_STE_ACCESS_MODE_BY_HASH;
+			rtc_attr.match_definer_0 =
+				mlx5hws_definer_get_id(mt->definer);
+		} else if (attr->distribute_mode ==
+			   MLX5HWS_MATCHER_DISTRIBUTE_BY_LINEAR) {
+			/* Linear Lookup Table */
+			rtc_attr.access_index_mode =
+				MLX5_IFC_RTC_STE_ACCESS_MODE_LINEAR;
+			rtc_attr.match_definer_0 =
+				ctx->caps->linear_match_definer;
 		}
-		break;
-
-	case HWS_MATCHER_RTC_TYPE_STE_ARRAY:
-		action_ste = &matcher->action_ste;
-
-		rtc_0_id = &action_ste->rtc_0_id;
-		rtc_1_id = &action_ste->rtc_1_id;
-		ste_pool = action_ste->pool;
-		ste = &action_ste->ste;
-		/* Action RTC size calculation:
-		 * log((max number of rules in matcher) *
-		 *     (max number of action STEs per rule) *
-		 *     (2 to support writing new STEs for update rule))
-		 */
-		ste->order = ilog2(roundup_pow_of_two(action_ste->max_stes)) +
-			     attr->table.sz_row_log +
-			     MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT;
-		rtc_attr.log_size = ste->order;
-		rtc_attr.log_depth = 0;
-		rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
-		/* The action STEs use the default always hit definer */
-		rtc_attr.match_definer_0 = ctx->caps->trivial_match_definer;
-		rtc_attr.is_frst_jumbo = false;
-		rtc_attr.miss_ft_id = 0;
-		break;
-
-	default:
-		mlx5hws_err(ctx, "HWS Invalid RTC type\n");
-		return -EINVAL;
 	}
 
-	obj_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
+	obj_id = mlx5hws_pool_get_base_id(matcher->match_ste.pool);
 
 	rtc_attr.pd = ctx->pd_num;
 	rtc_attr.ste_base = obj_id;
-	rtc_attr.ste_offset = ste->offset;
 	rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
 	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(tbl->type, false);
-	hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, rtc_type, false);
+	hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, false);
 
 	/* STC is a single resource (obj_id), use any STC for the ID */
-	stc_pool = ctx->stc_pool;
-	default_stc = ctx->common_res.default_stc;
-	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit);
+	obj_id = mlx5hws_pool_get_base_id(ctx->stc_pool);
 	rtc_attr.stc_base = obj_id;
 
-	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_0_id);
+	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr,
+				     &matcher->match_ste.rtc_0_id);
 	if (ret) {
-		mlx5hws_err(ctx, "Failed to create matcher RTC of type %s",
-			    hws_matcher_rtc_type_to_str(rtc_type));
-		goto free_ste;
+		mlx5hws_err(ctx, "Failed to create matcher RTC\n");
+		return ret;
 	}
 
 	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB) {
-		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
+		obj_id = mlx5hws_pool_get_base_mirror_id(
+			matcher->match_ste.pool);
 		rtc_attr.ste_base = obj_id;
 		rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(tbl->type, true);
 
-		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, &default_stc->default_hit);
+		obj_id = mlx5hws_pool_get_base_mirror_id(ctx->stc_pool);
 		rtc_attr.stc_base = obj_id;
-		hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, rtc_type, true);
+		hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, true);
 
-		ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_1_id);
+		ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr,
+					     &matcher->match_ste.rtc_1_id);
 		if (ret) {
-			mlx5hws_err(ctx, "Failed to create peer matcher RTC of type %s",
-				    hws_matcher_rtc_type_to_str(rtc_type));
+			mlx5hws_err(ctx, "Failed to create mirror matcher RTC\n");
 			goto destroy_rtc_0;
 		}
 	}
@@ -347,46 +547,18 @@ static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher,
 	return 0;
 
 destroy_rtc_0:
-	mlx5hws_cmd_rtc_destroy(ctx->mdev, *rtc_0_id);
-free_ste:
-	if (rtc_type == HWS_MATCHER_RTC_TYPE_MATCH)
-		mlx5hws_pool_chunk_free(ste_pool, ste);
+	mlx5hws_cmd_rtc_destroy(ctx->mdev, matcher->match_ste.rtc_0_id);
 	return ret;
 }
 
-static void hws_matcher_destroy_rtc(struct mlx5hws_matcher *matcher,
-				    enum mlx5hws_matcher_rtc_type rtc_type)
+static void hws_matcher_destroy_rtc(struct mlx5hws_matcher *matcher)
 {
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_table *tbl = matcher->tbl;
-	struct mlx5hws_pool_chunk *ste;
-	struct mlx5hws_pool *ste_pool;
-	u32 rtc_0_id, rtc_1_id;
-
-	switch (rtc_type) {
-	case HWS_MATCHER_RTC_TYPE_MATCH:
-		rtc_0_id = matcher->match_ste.rtc_0_id;
-		rtc_1_id = matcher->match_ste.rtc_1_id;
-		ste_pool = matcher->match_ste.pool;
-		ste = &matcher->match_ste.ste;
-		break;
-	case HWS_MATCHER_RTC_TYPE_STE_ARRAY:
-		action_ste = &matcher->action_ste;
-		rtc_0_id = action_ste->rtc_0_id;
-		rtc_1_id = action_ste->rtc_1_id;
-		ste_pool = action_ste->pool;
-		ste = &action_ste->ste;
-		break;
-	default:
-		return;
-	}
+	struct mlx5_core_dev *mdev = matcher->tbl->ctx->mdev;
 
-	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB)
-		mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, rtc_1_id);
+	if (matcher->tbl->type == MLX5HWS_TABLE_TYPE_FDB)
+		mlx5hws_cmd_rtc_destroy(mdev, matcher->match_ste.rtc_1_id);
 
-	mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, rtc_0_id);
-	if (rtc_type == HWS_MATCHER_RTC_TYPE_MATCH)
-		mlx5hws_pool_chunk_free(ste_pool, ste);
+	mlx5hws_cmd_rtc_destroy(mdev, matcher->match_ste.rtc_0_id);
 }
 
 static int
@@ -454,85 +626,17 @@ static int hws_matcher_check_and_process_at(struct mlx5hws_matcher *matcher,
 	return 0;
 }
 
-static int hws_matcher_resize_init(struct mlx5hws_matcher *src_matcher)
-{
-	struct mlx5hws_matcher_resize_data *resize_data;
-
-	resize_data = kzalloc(sizeof(*resize_data), GFP_KERNEL);
-	if (!resize_data)
-		return -ENOMEM;
-
-	resize_data->max_stes = src_matcher->action_ste.max_stes;
-
-	resize_data->stc = src_matcher->action_ste.stc;
-	resize_data->rtc_0_id = src_matcher->action_ste.rtc_0_id;
-	resize_data->rtc_1_id = src_matcher->action_ste.rtc_1_id;
-	resize_data->pool = src_matcher->action_ste.max_stes ?
-			    src_matcher->action_ste.pool : NULL;
-
-	/* Place the new resized matcher on the dst matcher's list */
-	list_add(&resize_data->list_node, &src_matcher->resize_dst->resize_data);
-
-	/* Move all the previous resized matchers to the dst matcher's list */
-	while (!list_empty(&src_matcher->resize_data)) {
-		resize_data = list_first_entry(&src_matcher->resize_data,
-					       struct mlx5hws_matcher_resize_data,
-					       list_node);
-		list_del_init(&resize_data->list_node);
-		list_add(&resize_data->list_node, &src_matcher->resize_dst->resize_data);
-	}
-
-	return 0;
-}
-
-static void hws_matcher_resize_uninit(struct mlx5hws_matcher *matcher)
-{
-	struct mlx5hws_matcher_resize_data *resize_data;
-
-	if (!mlx5hws_matcher_is_resizable(matcher))
-		return;
-
-	while (!list_empty(&matcher->resize_data)) {
-		resize_data = list_first_entry(&matcher->resize_data,
-					       struct mlx5hws_matcher_resize_data,
-					       list_node);
-		list_del_init(&resize_data->list_node);
-
-		if (resize_data->max_stes) {
-			mlx5hws_action_free_single_stc(matcher->tbl->ctx,
-						       matcher->tbl->type,
-						       &resize_data->stc);
-
-			if (matcher->tbl->type == MLX5HWS_TABLE_TYPE_FDB)
-				mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
-							resize_data->rtc_1_id);
-
-			mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
-						resize_data->rtc_0_id);
-
-			if (resize_data->pool)
-				mlx5hws_pool_destroy(resize_data->pool);
-		}
-
-		kfree(resize_data);
-	}
-}
-
 static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher)
 {
 	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt);
-	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_table *tbl = matcher->tbl;
-	struct mlx5hws_pool_attr pool_attr = {0};
-	struct mlx5hws_context *ctx = tbl->ctx;
-	u32 required_stes;
-	u8 max_stes = 0;
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	u8 required_stes, max_stes;
 	int i, ret;
 
 	if (matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION)
 		return 0;
 
+	max_stes = 0;
 	for (i = 0; i < matcher->num_of_at; i++) {
 		struct mlx5hws_action_template *at = &matcher->at[i];
 
@@ -548,75 +652,33 @@ static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher)
 		/* Future: Optimize reparse */
 	}
 
-	/* There are no additional STEs required for matcher */
-	if (!max_stes)
-		return 0;
-
-	matcher->action_ste.max_stes = max_stes;
-
-	action_ste = &matcher->action_ste;
-
-	/* Allocate action STE mempool */
-	pool_attr.table_type = tbl->type;
-	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL;
-	/* Pool size is similar to action RTC size */
-	pool_attr.alloc_log_sz = ilog2(roundup_pow_of_two(action_ste->max_stes)) +
-				 matcher->attr.table.sz_row_log +
-				 MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT;
-	hws_matcher_set_pool_attr(&pool_attr, matcher);
-	action_ste->pool = mlx5hws_pool_create(ctx, &pool_attr);
-	if (!action_ste->pool) {
-		mlx5hws_err(ctx, "Failed to create action ste pool\n");
-		return -EINVAL;
-	}
-
-	/* Allocate action RTC */
-	ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY);
-	if (ret) {
-		mlx5hws_err(ctx, "Failed to create action RTC\n");
-		goto free_ste_pool;
-	}
-
-	/* Allocate STC for jumps to STE */
-	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
-	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
-	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
-	stc_attr.ste_table.ste = action_ste->ste;
-	stc_attr.ste_table.ste_pool = action_ste->pool;
-	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
-
-	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl->type,
-					      &action_ste->stc);
-	if (ret) {
-		mlx5hws_err(ctx, "Failed to create action jump to table STC\n");
-		goto free_rtc;
-	}
+	matcher->num_of_action_stes = max_stes;
 
 	return 0;
-
-free_rtc:
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY);
-free_ste_pool:
-	mlx5hws_pool_destroy(action_ste->pool);
-	return ret;
 }
 
-static void hws_matcher_unbind_at(struct mlx5hws_matcher *matcher)
+static void hws_matcher_set_ip_version_match(struct mlx5hws_matcher *matcher)
 {
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_table *tbl = matcher->tbl;
-
-	action_ste = &matcher->action_ste;
-
-	if (!action_ste->max_stes ||
-	    matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION ||
-	    mlx5hws_matcher_is_in_resize(matcher))
-		return;
+	int i;
 
-	mlx5hws_action_free_single_stc(tbl->ctx, tbl->type, &action_ste->stc);
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY);
-	mlx5hws_pool_destroy(action_ste->pool);
+	for (i = 0; i < matcher->mt->fc_sz; i++) {
+		switch (matcher->mt->fc[i].fname) {
+		case MLX5HWS_DEFINER_FNAME_ETH_TYPE_O:
+			matcher->matches_outer_ethertype = 1;
+			break;
+		case MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_O:
+			matcher->matches_outer_ip_version = 1;
+			break;
+		case MLX5HWS_DEFINER_FNAME_ETH_TYPE_I:
+			matcher->matches_inner_ethertype = 1;
+			break;
+		case MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_I:
+			matcher->matches_inner_ip_version = 1;
+			break;
+		default:
+			break;
+		}
+	}
 }
 
 static int hws_matcher_bind_mt(struct mlx5hws_matcher *matcher)
@@ -635,10 +697,11 @@ static int hws_matcher_bind_mt(struct mlx5hws_matcher *matcher)
 		}
 	}
 
+	hws_matcher_set_ip_version_match(matcher);
+
 	/* Create an STE pool per matcher*/
 	pool_attr.table_type = matcher->tbl->type;
 	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
-	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_MATCHER_STE_POOL;
 	pool_attr.alloc_log_sz = matcher->attr.table.sz_col_log +
 				 matcher->attr.table.sz_row_log;
 	hws_matcher_set_pool_attr(&pool_attr, matcher);
@@ -740,6 +803,8 @@ hws_matcher_process_attr(struct mlx5hws_cmd_query_caps *caps,
 		attr->table.sz_col_log = hws_matcher_rules_to_tbl_depth(attr->rule.num_log);
 
 	matcher->flags |= attr->resizable ? MLX5HWS_MATCHER_FLAGS_RESIZABLE : 0;
+	matcher->flags |= attr->isolated_matcher_end_ft_id ?
+			  MLX5HWS_MATCHER_FLAGS_ISOLATED : 0;
 
 	return hws_matcher_check_attr_sz(caps, matcher);
 }
@@ -761,10 +826,10 @@ static int hws_matcher_create_and_connect(struct mlx5hws_matcher *matcher)
 	/* Create matcher end flow table anchor */
 	ret = hws_matcher_create_end_ft(matcher);
 	if (ret)
-		goto unbind_at;
+		goto unbind_mt;
 
 	/* Allocate the RTC for the new matcher */
-	ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH);
+	ret = hws_matcher_create_rtc(matcher);
 	if (ret)
 		goto destroy_end_ft;
 
@@ -776,11 +841,9 @@ static int hws_matcher_create_and_connect(struct mlx5hws_matcher *matcher)
 	return 0;
 
 destroy_rtc:
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH);
+	hws_matcher_destroy_rtc(matcher);
 destroy_end_ft:
 	hws_matcher_destroy_end_ft(matcher);
-unbind_at:
-	hws_matcher_unbind_at(matcher);
 unbind_mt:
 	hws_matcher_unbind_mt(matcher);
 	return ret;
@@ -788,11 +851,9 @@ unbind_mt:
 
 static void hws_matcher_destroy_and_disconnect(struct mlx5hws_matcher *matcher)
 {
-	hws_matcher_resize_uninit(matcher);
 	hws_matcher_disconnect(matcher);
-	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH);
+	hws_matcher_destroy_rtc(matcher);
 	hws_matcher_destroy_end_ft(matcher);
-	hws_matcher_unbind_at(matcher);
 	hws_matcher_unbind_mt(matcher);
 }
 
@@ -814,8 +875,6 @@ hws_matcher_create_col_matcher(struct mlx5hws_matcher *matcher)
 	if (!col_matcher)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&col_matcher->resize_data);
-
 	col_matcher->tbl = matcher->tbl;
 	col_matcher->mt = matcher->mt;
 	col_matcher->at = matcher->at;
@@ -832,6 +891,8 @@ hws_matcher_create_col_matcher(struct mlx5hws_matcher *matcher)
 		col_matcher->attr.table.sz_row_log -= MLX5HWS_MATCHER_ASSURED_ROW_RATIO;
 
 	col_matcher->attr.max_num_of_at_attach = matcher->attr.max_num_of_at_attach;
+	col_matcher->attr.isolated_matcher_end_ft_id =
+		matcher->attr.isolated_matcher_end_ft_id;
 
 	ret = hws_matcher_process_attr(ctx->caps, col_matcher);
 	if (ret)
@@ -869,8 +930,6 @@ static int hws_matcher_init(struct mlx5hws_matcher *matcher)
 	struct mlx5hws_context *ctx = matcher->tbl->ctx;
 	int ret;
 
-	INIT_LIST_HEAD(&matcher->resize_data);
-
 	mutex_lock(&ctx->ctrl_lock);
 
 	/* Allocate matcher resource and connect to the packet pipe */
@@ -905,18 +964,44 @@ static int hws_matcher_uninit(struct mlx5hws_matcher *matcher)
 	return 0;
 }
 
+static int hws_matcher_grow_at_array(struct mlx5hws_matcher *matcher)
+{
+	void *p;
+
+	if (matcher->size_of_at_array >= MLX5HWS_MATCHER_MAX_AT)
+		return -ENOMEM;
+
+	matcher->size_of_at_array *= 2;
+	p = krealloc(matcher->at,
+		     matcher->size_of_at_array * sizeof(*matcher->at),
+		     __GFP_ZERO | GFP_KERNEL);
+	if (!p) {
+		matcher->size_of_at_array /= 2;
+		return -ENOMEM;
+	}
+
+	matcher->at = p;
+
+	return 0;
+}
+
 int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher,
 			      struct mlx5hws_action_template *at)
 {
 	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt);
-	struct mlx5hws_context *ctx = matcher->tbl->ctx;
 	u32 required_stes;
 	int ret;
 
-	if (!matcher->attr.max_num_of_at_attach) {
-		mlx5hws_dbg(ctx, "Num of current at (%d) exceed allowed value\n",
-			    matcher->num_of_at);
-		return -EOPNOTSUPP;
+	if (unlikely(matcher->num_of_at >= matcher->size_of_at_array)) {
+		ret = hws_matcher_grow_at_array(matcher);
+		if (ret)
+			return ret;
+
+		if (matcher->col_matcher) {
+			ret = hws_matcher_grow_at_array(matcher->col_matcher);
+			if (ret)
+				return ret;
+		}
 	}
 
 	ret = hws_matcher_check_and_process_at(matcher, at);
@@ -924,15 +1009,11 @@ int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher,
 		return ret;
 
 	required_stes = at->num_of_action_stes - (!is_jumbo || at->only_term);
-	if (matcher->action_ste.max_stes < required_stes) {
-		mlx5hws_dbg(ctx, "Required STEs [%d] exceeds initial action template STE [%d]\n",
-			    required_stes, matcher->action_ste.max_stes);
-		return -ENOMEM;
-	}
+	if (matcher->num_of_action_stes < required_stes)
+		matcher->num_of_action_stes = required_stes;
 
 	matcher->at[matcher->num_of_at] = *at;
 	matcher->num_of_at += 1;
-	matcher->attr.max_num_of_at_attach -= 1;
 
 	if (matcher->col_matcher)
 		matcher->col_matcher->num_of_at = matcher->num_of_at;
@@ -960,8 +1041,9 @@ hws_matcher_set_templates(struct mlx5hws_matcher *matcher,
 	if (!matcher->mt)
 		return -ENOMEM;
 
-	matcher->at = kvcalloc(num_of_at + matcher->attr.max_num_of_at_attach,
-			       sizeof(*matcher->at),
+	matcher->size_of_at_array =
+		num_of_at + matcher->attr.max_num_of_at_attach;
+	matcher->at = kvcalloc(matcher->size_of_at_array, sizeof(*matcher->at),
 			       GFP_KERNEL);
 	if (!matcher->at) {
 		mlx5hws_err(ctx, "Failed to allocate action template array\n");
@@ -1110,7 +1192,7 @@ static int hws_matcher_resize_precheck(struct mlx5hws_matcher *src_matcher,
 		return -EINVAL;
 	}
 
-	if (src_matcher->action_ste.max_stes > dst_matcher->action_ste.max_stes) {
+	if (src_matcher->num_of_action_stes > dst_matcher->num_of_action_stes) {
 		mlx5hws_err(ctx, "Src/dst matcher max STEs mismatch\n");
 		return -EINVAL;
 	}
@@ -1139,10 +1221,6 @@ int mlx5hws_matcher_resize_set_target(struct mlx5hws_matcher *src_matcher,
 
 	src_matcher->resize_dst = dst_matcher;
 
-	ret = hws_matcher_resize_init(src_matcher);
-	if (ret)
-		src_matcher->resize_dst = NULL;
-
 out:
 	mutex_unlock(&src_matcher->tbl->ctx->ctrl_lock);
 	return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h
index 020de70270c5..32e83cddcd60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h
@@ -23,6 +23,9 @@
  */
 #define MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT 1
 
+/* Maximum number of action templates that can be attached to a matcher. */
+#define MLX5HWS_MATCHER_MAX_AT 128
+
 enum mlx5hws_matcher_offset {
 	MLX5HWS_MATCHER_OFFSET_TAG_DW1 = 12,
 	MLX5HWS_MATCHER_OFFSET_TAG_DW0 = 13,
@@ -31,6 +34,7 @@ enum mlx5hws_matcher_offset {
 enum mlx5hws_matcher_flags {
 	MLX5HWS_MATCHER_FLAGS_COLLISION = 1 << 2,
 	MLX5HWS_MATCHER_FLAGS_RESIZABLE	= 1 << 3,
+	MLX5HWS_MATCHER_FLAGS_ISOLATED	= 1 << 4,
 };
 
 struct mlx5hws_match_template {
@@ -42,28 +46,15 @@ struct mlx5hws_match_template {
 };
 
 struct mlx5hws_matcher_match_ste {
-	struct mlx5hws_pool_chunk ste;
 	u32 rtc_0_id;
 	u32 rtc_1_id;
 	struct mlx5hws_pool *pool;
 };
 
-struct mlx5hws_matcher_action_ste {
-	struct mlx5hws_pool_chunk ste;
-	struct mlx5hws_pool_chunk stc;
-	u32 rtc_0_id;
-	u32 rtc_1_id;
-	struct mlx5hws_pool *pool;
-	u8 max_stes;
-};
-
-struct mlx5hws_matcher_resize_data {
-	struct mlx5hws_pool_chunk stc;
-	u32 rtc_0_id;
-	u32 rtc_1_id;
-	struct mlx5hws_pool *pool;
-	u8 max_stes;
-	struct list_head list_node;
+enum {
+	MLX5HWS_MATCHER_IPV_UNSET = 0,
+	MLX5HWS_MATCHER_IPV_4 = 1,
+	MLX5HWS_MATCHER_IPV_6 = 2,
 };
 
 struct mlx5hws_matcher {
@@ -72,16 +63,22 @@ struct mlx5hws_matcher {
 	struct mlx5hws_match_template *mt;
 	struct mlx5hws_action_template *at;
 	u8 num_of_at;
+	u8 size_of_at_array;
 	u8 num_of_mt;
+	u8 num_of_action_stes;
 	/* enum mlx5hws_matcher_flags */
 	u8 flags;
+	u8 matches_outer_ethertype:1;
+	u8 matches_outer_ip_version:1;
+	u8 matches_inner_ethertype:1;
+	u8 matches_inner_ip_version:1;
+	u8 outer_ip_version:2;
+	u8 inner_ip_version:2;
 	u32 end_ft_id;
 	struct mlx5hws_matcher *col_matcher;
 	struct mlx5hws_matcher *resize_dst;
 	struct mlx5hws_matcher_match_ste match_ste;
-	struct mlx5hws_matcher_action_ste action_ste;
 	struct list_head list_node;
-	struct list_head resize_data;
 };
 
 static inline bool
@@ -100,9 +97,17 @@ static inline bool mlx5hws_matcher_is_in_resize(struct mlx5hws_matcher *matcher)
 	return !!matcher->resize_dst;
 }
 
+static inline bool mlx5hws_matcher_is_isolated(struct mlx5hws_matcher *matcher)
+{
+	return !!(matcher->flags & MLX5HWS_MATCHER_FLAGS_ISOLATED);
+}
+
 static inline bool mlx5hws_matcher_is_insert_by_idx(struct mlx5hws_matcher *matcher)
 {
 	return matcher->attr.insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX;
 }
 
+int mlx5hws_matcher_update_end_ft_isolated(struct mlx5hws_table *tbl,
+					   u32 miss_ft_id);
+
 #endif /* HWS_MATCHER_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
index 5121951f2778..9bbadc4d8a0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
@@ -119,6 +119,8 @@ struct mlx5hws_matcher_attr {
 	};
 	/* Optional AT attach configuration - Max number of additional AT */
 	u8 max_num_of_at_attach;
+	/* Optional end FT (miss FT ID) for match RTC (for isolated matcher) */
+	u32 isolated_matcher_end_ft_id;
 };
 
 struct mlx5hws_rule_attr {
@@ -502,6 +504,15 @@ enum mlx5hws_action_type
 mlx5hws_action_get_type(struct mlx5hws_action *action);
 
 /**
+ * mlx5hws_action_get_dev - Get mlx5 core device.
+ *
+ * @action: The action to get the device from.
+ *
+ * Return: mlx5 core device.
+ */
+struct mlx5_core_dev *mlx5hws_action_get_dev(struct mlx5hws_action *action);
+
+/**
  * mlx5hws_action_create_dest_drop - Create a direct rule drop action.
  *
  * @ctx: The context in which the new action will be created.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
index f51ed24526b9..51e4c551e0ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
@@ -490,8 +490,8 @@ hws_action_modify_get_target_fields(u8 action_type, __be64 *pattern,
 	switch (action_type) {
 	case MLX5_ACTION_TYPE_SET:
 	case MLX5_ACTION_TYPE_ADD:
-		*src_field = MLX5_GET(set_action_in, pattern, field);
-		*dst_field = INVALID_FIELD;
+		*src_field = INVALID_FIELD;
+		*dst_field = MLX5_GET(set_action_in, pattern, field);
 		break;
 	case MLX5_ACTION_TYPE_COPY:
 		*src_field = MLX5_GET(copy_action_in, pattern, src_field);
@@ -522,57 +522,59 @@ bool mlx5hws_pat_verify_actions(struct mlx5hws_context *ctx, __be64 pattern[], s
 	return true;
 }
 
-void mlx5hws_pat_calc_nope(__be64 *pattern, size_t num_actions,
-			   size_t max_actions, size_t *new_size,
-			   u32 *nope_location, __be64 *new_pat)
+int mlx5hws_pat_calc_nop(__be64 *pattern, size_t num_actions,
+			 size_t max_actions, size_t *new_size,
+			 u32 *nop_locations, __be64 *new_pat)
 {
-	u16 prev_src_field = 0, prev_dst_field = 0;
+	u16 prev_src_field = INVALID_FIELD, prev_dst_field = INVALID_FIELD;
 	u16 src_field, dst_field;
 	u8 action_type;
+	bool dependent;
 	size_t i, j;
 
 	*new_size = num_actions;
-	*nope_location = 0;
+	*nop_locations = 0;
 
 	if (num_actions == 1)
-		return;
+		return 0;
 
 	for (i = 0, j = 0; i < num_actions; i++, j++) {
-		action_type = MLX5_GET(set_action_in, &pattern[i], action_type);
+		if (j >= max_actions)
+			return -EINVAL;
 
+		action_type = MLX5_GET(set_action_in, &pattern[i], action_type);
 		hws_action_modify_get_target_fields(action_type, &pattern[i],
 						    &src_field, &dst_field);
-		if (i % 2) {
-			if (action_type == MLX5_ACTION_TYPE_COPY &&
-			    (prev_src_field == src_field ||
-			     prev_dst_field == dst_field)) {
-				/* need Nope */
-				*new_size += 1;
-				*nope_location |= BIT(i);
-				memset(&new_pat[j], 0, MLX5HWS_MODIFY_ACTION_SIZE);
-				MLX5_SET(set_action_in, &new_pat[j],
-					 action_type,
-					 MLX5_MODIFICATION_TYPE_NOP);
-				j++;
-			} else if (prev_src_field == src_field) {
-				/* need Nope*/
-				*new_size += 1;
-				*nope_location |= BIT(i);
-				MLX5_SET(set_action_in, &new_pat[j],
-					 action_type,
-					 MLX5_MODIFICATION_TYPE_NOP);
-				j++;
-			}
-		}
-		memcpy(&new_pat[j], &pattern[i], MLX5HWS_MODIFY_ACTION_SIZE);
-		/* check if no more space */
-		if (j > max_actions) {
-			*new_size = num_actions;
-			*nope_location = 0;
-			return;
+
+		/* For every action, look at it and the previous one. The two
+		 * actions are dependent if:
+		 */
+		dependent =
+			(i > 0) &&
+			/* At least one of the actions is a write and */
+			(dst_field != INVALID_FIELD ||
+			 prev_dst_field != INVALID_FIELD) &&
+			/* One reads from the other's source */
+			(dst_field == prev_src_field ||
+			 src_field == prev_dst_field ||
+			 /* Or both write to the same destination */
+			 dst_field == prev_dst_field);
+
+		if (dependent) {
+			*new_size += 1;
+			*nop_locations |= BIT(i);
+			memset(&new_pat[j], 0, MLX5HWS_MODIFY_ACTION_SIZE);
+			MLX5_SET(set_action_in, &new_pat[j], action_type,
+				 MLX5_MODIFICATION_TYPE_NOP);
+			j++;
+			if (j >= max_actions)
+				return -EINVAL;
 		}
 
+		memcpy(&new_pat[j], &pattern[i], MLX5HWS_MODIFY_ACTION_SIZE);
 		prev_src_field = src_field;
 		prev_dst_field = dst_field;
 	}
+
+	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
index 8ddb51980044..7fbd8dc7aa18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
@@ -96,6 +96,7 @@ int mlx5hws_arg_write_inline_arg_data(struct mlx5hws_context *ctx,
 				      u8 *arg_data,
 				      size_t data_size);
 
-void mlx5hws_pat_calc_nope(__be64 *pattern, size_t num_actions, size_t max_actions,
-			   size_t *new_size, u32 *nope_location, __be64 *new_pat);
+int mlx5hws_pat_calc_nop(__be64 *pattern, size_t num_actions,
+			 size_t max_actions, size_t *new_size,
+			 u32 *nop_locations, __be64 *new_pat);
 #endif /* MLX5HWS_PAT_ARG_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
index 50a81d360bb2..7e37d6e9eb83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
@@ -20,15 +20,14 @@ static void hws_pool_free_one_resource(struct mlx5hws_pool_resource *resource)
 	kfree(resource);
 }
 
-static void hws_pool_resource_free(struct mlx5hws_pool *pool,
-				   int resource_idx)
+static void hws_pool_resource_free(struct mlx5hws_pool *pool)
 {
-	hws_pool_free_one_resource(pool->resource[resource_idx]);
-	pool->resource[resource_idx] = NULL;
+	hws_pool_free_one_resource(pool->resource);
+	pool->resource = NULL;
 
 	if (pool->tbl_type == MLX5HWS_TABLE_TYPE_FDB) {
-		hws_pool_free_one_resource(pool->mirror_resource[resource_idx]);
-		pool->mirror_resource[resource_idx] = NULL;
+		hws_pool_free_one_resource(pool->mirror_resource);
+		pool->mirror_resource = NULL;
 	}
 }
 
@@ -61,10 +60,8 @@ hws_pool_create_one_resource(struct mlx5hws_pool *pool, u32 log_range,
 		ret = -EINVAL;
 	}
 
-	if (ret) {
-		mlx5hws_err(pool->ctx, "Failed to allocate resource objects\n");
+	if (ret)
 		goto free_resource;
-	}
 
 	resource->pool = pool;
 	resource->range = 1 << log_range;
@@ -77,199 +74,114 @@ free_resource:
 	return NULL;
 }
 
-static int
-hws_pool_resource_alloc(struct mlx5hws_pool *pool, u32 log_range, int idx)
+static int hws_pool_resource_alloc(struct mlx5hws_pool *pool)
 {
 	struct mlx5hws_pool_resource *resource;
 	u32 fw_ft_type, opt_log_range;
 
 	fw_ft_type = mlx5hws_table_get_res_fw_ft_type(pool->tbl_type, false);
-	opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_ORIG ? 0 : log_range;
+	opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_MIRROR ?
+				0 : pool->alloc_log_sz;
 	resource = hws_pool_create_one_resource(pool, opt_log_range, fw_ft_type);
 	if (!resource) {
-		mlx5hws_err(pool->ctx, "Failed allocating resource\n");
+		mlx5hws_err(pool->ctx, "Failed to allocate resource\n");
 		return -EINVAL;
 	}
 
-	pool->resource[idx] = resource;
+	pool->resource = resource;
 
 	if (pool->tbl_type == MLX5HWS_TABLE_TYPE_FDB) {
 		struct mlx5hws_pool_resource *mirror_resource;
 
 		fw_ft_type = mlx5hws_table_get_res_fw_ft_type(pool->tbl_type, true);
-		opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_MIRROR ? 0 : log_range;
+		opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_ORIG ?
+					0 : pool->alloc_log_sz;
 		mirror_resource = hws_pool_create_one_resource(pool, opt_log_range, fw_ft_type);
 		if (!mirror_resource) {
-			mlx5hws_err(pool->ctx, "Failed allocating mirrored resource\n");
+			mlx5hws_err(pool->ctx, "Failed to allocate mirrored resource\n");
 			hws_pool_free_one_resource(resource);
-			pool->resource[idx] = NULL;
+			pool->resource = NULL;
 			return -EINVAL;
 		}
-		pool->mirror_resource[idx] = mirror_resource;
+		pool->mirror_resource = mirror_resource;
 	}
 
 	return 0;
 }
 
-static unsigned long *hws_pool_create_and_init_bitmap(u32 log_range)
-{
-	unsigned long *cur_bmp;
-
-	cur_bmp = bitmap_zalloc(1 << log_range, GFP_KERNEL);
-	if (!cur_bmp)
-		return NULL;
-
-	bitmap_fill(cur_bmp, 1 << log_range);
-
-	return cur_bmp;
-}
-
-static void hws_pool_buddy_db_put_chunk(struct mlx5hws_pool *pool,
-					struct mlx5hws_pool_chunk *chunk)
+static int hws_pool_buddy_init(struct mlx5hws_pool *pool)
 {
 	struct mlx5hws_buddy_mem *buddy;
 
-	buddy = pool->db.buddy_manager->buddies[chunk->resource_idx];
+	buddy = mlx5hws_buddy_create(pool->alloc_log_sz);
 	if (!buddy) {
-		mlx5hws_err(pool->ctx, "No such buddy (%d)\n", chunk->resource_idx);
-		return;
-	}
-
-	mlx5hws_buddy_free_mem(buddy, chunk->offset, chunk->order);
-}
-
-static struct mlx5hws_buddy_mem *
-hws_pool_buddy_get_next_buddy(struct mlx5hws_pool *pool, int idx,
-			      u32 order, bool *is_new_buddy)
-{
-	static struct mlx5hws_buddy_mem *buddy;
-	u32 new_buddy_size;
-
-	buddy = pool->db.buddy_manager->buddies[idx];
-	if (buddy)
-		return buddy;
-
-	new_buddy_size = max(pool->alloc_log_sz, order);
-	*is_new_buddy = true;
-	buddy = mlx5hws_buddy_create(new_buddy_size);
-	if (!buddy) {
-		mlx5hws_err(pool->ctx, "Failed to create buddy order: %d index: %d\n",
-			    new_buddy_size, idx);
-		return NULL;
+		mlx5hws_err(pool->ctx, "Failed to create buddy order: %zu\n",
+			    pool->alloc_log_sz);
+		return -ENOMEM;
 	}
 
-	if (hws_pool_resource_alloc(pool, new_buddy_size, idx) != 0) {
-		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
-			    pool->type, new_buddy_size, idx);
+	if (hws_pool_resource_alloc(pool) != 0) {
+		mlx5hws_err(pool->ctx, "Failed to create resource type: %d size %zu\n",
+			    pool->type, pool->alloc_log_sz);
 		mlx5hws_buddy_cleanup(buddy);
-		return NULL;
+		return -ENOMEM;
 	}
 
-	pool->db.buddy_manager->buddies[idx] = buddy;
+	pool->db.buddy = buddy;
 
-	return buddy;
+	return 0;
 }
 
-static int hws_pool_buddy_get_mem_chunk(struct mlx5hws_pool *pool,
-					int order,
-					u32 *buddy_idx,
-					int *seg)
+static int hws_pool_buddy_db_get_chunk(struct mlx5hws_pool *pool,
+				       struct mlx5hws_pool_chunk *chunk)
 {
-	struct mlx5hws_buddy_mem *buddy;
-	bool new_mem = false;
-	int ret = 0;
-	int i;
-
-	*seg = -1;
-
-	/* Find the next free place from the buddy array */
-	while (*seg < 0) {
-		for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-			buddy = hws_pool_buddy_get_next_buddy(pool, i,
-							      order,
-							      &new_mem);
-			if (!buddy) {
-				ret = -ENOMEM;
-				goto out;
-			}
-
-			*seg = mlx5hws_buddy_alloc_mem(buddy, order);
-			if (*seg >= 0)
-				goto found;
-
-			if (pool->flags & MLX5HWS_POOL_FLAGS_ONE_RESOURCE) {
-				mlx5hws_err(pool->ctx,
-					    "Fail to allocate seg for one resource pool\n");
-				ret = -ENOMEM;
-				goto out;
-			}
-
-			if (new_mem) {
-				/* We have new memory pool, should be place for us */
-				mlx5hws_err(pool->ctx,
-					    "No memory for order: %d with buddy no: %d\n",
-					    order, i);
-				ret = -ENOMEM;
-				goto out;
-			}
-		}
+	struct mlx5hws_buddy_mem *buddy = pool->db.buddy;
+
+	if (!buddy) {
+		mlx5hws_err(pool->ctx, "Bad buddy state\n");
+		return -EINVAL;
 	}
 
-found:
-	*buddy_idx = i;
-out:
-	return ret;
+	chunk->offset = mlx5hws_buddy_alloc_mem(buddy, chunk->order);
+	if (chunk->offset >= 0)
+		return 0;
+
+	return -ENOMEM;
 }
 
-static int hws_pool_buddy_db_get_chunk(struct mlx5hws_pool *pool,
-				       struct mlx5hws_pool_chunk *chunk)
+static void hws_pool_buddy_db_put_chunk(struct mlx5hws_pool *pool,
+					struct mlx5hws_pool_chunk *chunk)
 {
-	int ret = 0;
+	struct mlx5hws_buddy_mem *buddy;
 
-	/* Go over the buddies and find next free slot */
-	ret = hws_pool_buddy_get_mem_chunk(pool, chunk->order,
-					   &chunk->resource_idx,
-					   &chunk->offset);
-	if (ret)
-		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
-			    chunk->order);
+	buddy = pool->db.buddy;
+	if (!buddy) {
+		mlx5hws_err(pool->ctx, "Bad buddy state\n");
+		return;
+	}
 
-	return ret;
+	mlx5hws_buddy_free_mem(buddy, chunk->offset, chunk->order);
 }
 
 static void hws_pool_buddy_db_uninit(struct mlx5hws_pool *pool)
 {
 	struct mlx5hws_buddy_mem *buddy;
-	int i;
-
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-		buddy = pool->db.buddy_manager->buddies[i];
-		if (buddy) {
-			mlx5hws_buddy_cleanup(buddy);
-			kfree(buddy);
-			pool->db.buddy_manager->buddies[i] = NULL;
-		}
-	}
 
-	kfree(pool->db.buddy_manager);
+	buddy = pool->db.buddy;
+	if (buddy) {
+		mlx5hws_buddy_cleanup(buddy);
+		kfree(buddy);
+		pool->db.buddy = NULL;
+	}
 }
 
-static int hws_pool_buddy_db_init(struct mlx5hws_pool *pool, u32 log_range)
+static int hws_pool_buddy_db_init(struct mlx5hws_pool *pool)
 {
-	pool->db.buddy_manager = kzalloc(sizeof(*pool->db.buddy_manager), GFP_KERNEL);
-	if (!pool->db.buddy_manager)
-		return -ENOMEM;
-
-	if (pool->flags & MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE) {
-		bool new_buddy;
+	int ret;
 
-		if (!hws_pool_buddy_get_next_buddy(pool, 0, log_range, &new_buddy)) {
-			mlx5hws_err(pool->ctx,
-				    "Failed allocating memory on create log_sz: %d\n", log_range);
-			kfree(pool->db.buddy_manager);
-			return -ENOMEM;
-		}
-	}
+	ret = hws_pool_buddy_init(pool);
+	if (ret)
+		return ret;
 
 	pool->p_db_uninit = &hws_pool_buddy_db_uninit;
 	pool->p_get_chunk = &hws_pool_buddy_db_get_chunk;
@@ -278,261 +190,105 @@ static int hws_pool_buddy_db_init(struct mlx5hws_pool *pool, u32 log_range)
 	return 0;
 }
 
-static int hws_pool_create_resource_on_index(struct mlx5hws_pool *pool,
-					     u32 alloc_size, int idx)
-{
-	int ret = hws_pool_resource_alloc(pool, alloc_size, idx);
-
-	if (ret) {
-		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
-			    pool->type, alloc_size, idx);
-		return ret;
-	}
-
-	return 0;
-}
-
-static struct mlx5hws_pool_elements *
-hws_pool_element_create_new_elem(struct mlx5hws_pool *pool, u32 order, int idx)
+static unsigned long *hws_pool_create_and_init_bitmap(u32 log_range)
 {
-	struct mlx5hws_pool_elements *elem;
-	u32 alloc_size;
-
-	alloc_size = pool->alloc_log_sz;
+	unsigned long *bitmap;
 
-	elem = kzalloc(sizeof(*elem), GFP_KERNEL);
-	if (!elem)
+	bitmap = bitmap_zalloc(1 << log_range, GFP_KERNEL);
+	if (!bitmap)
 		return NULL;
 
-	/* Sharing the same resource, also means that all the elements are with size 1 */
-	if ((pool->flags & MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS) &&
-	    !(pool->flags & MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK)) {
-		 /* Currently all chunks in size 1 */
-		elem->bitmap = hws_pool_create_and_init_bitmap(alloc_size - order);
-		if (!elem->bitmap) {
-			mlx5hws_err(pool->ctx,
-				    "Failed to create bitmap type: %d: size %d index: %d\n",
-				    pool->type, alloc_size, idx);
-			goto free_elem;
-		}
-
-		elem->log_size = alloc_size - order;
-	}
-
-	if (hws_pool_create_resource_on_index(pool, alloc_size, idx)) {
-		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
-			    pool->type, alloc_size, idx);
-		goto free_db;
-	}
-
-	pool->db.element_manager->elements[idx] = elem;
-
-	return elem;
+	bitmap_fill(bitmap, 1 << log_range);
 
-free_db:
-	bitmap_free(elem->bitmap);
-free_elem:
-	kfree(elem);
-	return NULL;
+	return bitmap;
 }
 
-static int hws_pool_element_find_seg(struct mlx5hws_pool_elements *elem, int *seg)
+static int hws_pool_bitmap_init(struct mlx5hws_pool *pool)
 {
-	unsigned int segment, size;
-
-	size = 1 << elem->log_size;
+	unsigned long *bitmap;
 
-	segment = find_first_bit(elem->bitmap, size);
-	if (segment >= size) {
-		elem->is_full = true;
+	bitmap = hws_pool_create_and_init_bitmap(pool->alloc_log_sz);
+	if (!bitmap) {
+		mlx5hws_err(pool->ctx, "Failed to create bitmap order: %zu\n",
+			    pool->alloc_log_sz);
 		return -ENOMEM;
 	}
 
-	bitmap_clear(elem->bitmap, segment, 1);
-	*seg = segment;
-	return 0;
-}
-
-static int
-hws_pool_onesize_element_get_mem_chunk(struct mlx5hws_pool *pool, u32 order,
-				       u32 *idx, int *seg)
-{
-	struct mlx5hws_pool_elements *elem;
-
-	elem = pool->db.element_manager->elements[0];
-	if (!elem)
-		elem = hws_pool_element_create_new_elem(pool, order, 0);
-	if (!elem)
-		goto err_no_elem;
-
-	if (hws_pool_element_find_seg(elem, seg) != 0) {
-		mlx5hws_err(pool->ctx, "No more resources (last request order: %d)\n", order);
+	if (hws_pool_resource_alloc(pool) != 0) {
+		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %zu\n",
+			    pool->type, pool->alloc_log_sz);
+		bitmap_free(bitmap);
 		return -ENOMEM;
 	}
 
-	*idx = 0;
-	elem->num_of_elements++;
-	return 0;
+	pool->db.bitmap = bitmap;
 
-err_no_elem:
-	mlx5hws_err(pool->ctx, "Failed to allocate element for order: %d\n", order);
-	return -ENOMEM;
-}
-
-static int
-hws_pool_general_element_get_mem_chunk(struct mlx5hws_pool *pool, u32 order,
-				       u32 *idx, int *seg)
-{
-	int ret, i;
-
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-		if (!pool->resource[i]) {
-			ret = hws_pool_create_resource_on_index(pool, order, i);
-			if (ret)
-				goto err_no_res;
-			*idx = i;
-			*seg = 0; /* One memory slot in that element */
-			return 0;
-		}
-	}
-
-	mlx5hws_err(pool->ctx, "No more resources (last request order: %d)\n", order);
-	return -ENOMEM;
-
-err_no_res:
-	mlx5hws_err(pool->ctx, "Failed to allocate element for order: %d\n", order);
-	return -ENOMEM;
+	return 0;
 }
 
-static int hws_pool_general_element_db_get_chunk(struct mlx5hws_pool *pool,
-						 struct mlx5hws_pool_chunk *chunk)
+static int hws_pool_bitmap_db_get_chunk(struct mlx5hws_pool *pool,
+					struct mlx5hws_pool_chunk *chunk)
 {
-	int ret;
-
-	/* Go over all memory elements and find/allocate free slot */
-	ret = hws_pool_general_element_get_mem_chunk(pool, chunk->order,
-						     &chunk->resource_idx,
-						     &chunk->offset);
-	if (ret)
-		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
-			    chunk->order);
+	unsigned long *bitmap, size;
 
-	return ret;
-}
+	if (chunk->order != 0) {
+		mlx5hws_err(pool->ctx, "Pool only supports order 0 allocs\n");
+		return -EINVAL;
+	}
 
-static void hws_pool_general_element_db_put_chunk(struct mlx5hws_pool *pool,
-						  struct mlx5hws_pool_chunk *chunk)
-{
-	if (unlikely(!pool->resource[chunk->resource_idx]))
-		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
+	bitmap = pool->db.bitmap;
+	if (!bitmap) {
+		mlx5hws_err(pool->ctx, "Bad bitmap state\n");
+		return -EINVAL;
+	}
 
-	if (pool->flags & MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE)
-		hws_pool_resource_free(pool, chunk->resource_idx);
-}
+	size = 1 << pool->alloc_log_sz;
 
-static void hws_pool_general_element_db_uninit(struct mlx5hws_pool *pool)
-{
-	(void)pool;
-}
+	chunk->offset = find_first_bit(bitmap, size);
+	if (chunk->offset >= size)
+		return -ENOMEM;
 
-/* This memory management works as the following:
- * - At start doesn't allocate no mem at all.
- * - When new request for chunk arrived:
- *	allocate resource and give it.
- * - When free that chunk:
- *	the resource is freed.
- */
-static int hws_pool_general_element_db_init(struct mlx5hws_pool *pool)
-{
-	pool->p_db_uninit = &hws_pool_general_element_db_uninit;
-	pool->p_get_chunk = &hws_pool_general_element_db_get_chunk;
-	pool->p_put_chunk = &hws_pool_general_element_db_put_chunk;
+	bitmap_clear(bitmap, chunk->offset, 1);
 
 	return 0;
 }
 
-static void hws_onesize_element_db_destroy_element(struct mlx5hws_pool *pool,
-						   struct mlx5hws_pool_elements *elem,
-						   struct mlx5hws_pool_chunk *chunk)
-{
-	if (unlikely(!pool->resource[chunk->resource_idx]))
-		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
-
-	hws_pool_resource_free(pool, chunk->resource_idx);
-	kfree(elem);
-	pool->db.element_manager->elements[chunk->resource_idx] = NULL;
-}
-
-static void hws_onesize_element_db_put_chunk(struct mlx5hws_pool *pool,
-					     struct mlx5hws_pool_chunk *chunk)
+static void hws_pool_bitmap_db_put_chunk(struct mlx5hws_pool *pool,
+					 struct mlx5hws_pool_chunk *chunk)
 {
-	struct mlx5hws_pool_elements *elem;
+	unsigned long *bitmap;
 
-	if (unlikely(chunk->resource_idx))
-		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
-
-	elem = pool->db.element_manager->elements[chunk->resource_idx];
-	if (!elem) {
-		mlx5hws_err(pool->ctx, "No such element (%d)\n", chunk->resource_idx);
+	bitmap = pool->db.bitmap;
+	if (!bitmap) {
+		mlx5hws_err(pool->ctx, "Bad bitmap state\n");
 		return;
 	}
 
-	bitmap_set(elem->bitmap, chunk->offset, 1);
-	elem->is_full = false;
-	elem->num_of_elements--;
-
-	if (pool->flags & MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE &&
-	    !elem->num_of_elements)
-		hws_onesize_element_db_destroy_element(pool, elem, chunk);
+	bitmap_set(bitmap, chunk->offset, 1);
 }
 
-static int hws_onesize_element_db_get_chunk(struct mlx5hws_pool *pool,
-					    struct mlx5hws_pool_chunk *chunk)
+static void hws_pool_bitmap_db_uninit(struct mlx5hws_pool *pool)
 {
-	int ret = 0;
+	unsigned long *bitmap;
 
-	/* Go over all memory elements and find/allocate free slot */
-	ret = hws_pool_onesize_element_get_mem_chunk(pool, chunk->order,
-						     &chunk->resource_idx,
-						     &chunk->offset);
-	if (ret)
-		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
-			    chunk->order);
-
-	return ret;
-}
-
-static void hws_onesize_element_db_uninit(struct mlx5hws_pool *pool)
-{
-	struct mlx5hws_pool_elements *elem;
-	int i;
-
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
-		elem = pool->db.element_manager->elements[i];
-		if (elem) {
-			bitmap_free(elem->bitmap);
-			kfree(elem);
-			pool->db.element_manager->elements[i] = NULL;
-		}
+	bitmap = pool->db.bitmap;
+	if (bitmap) {
+		bitmap_free(bitmap);
+		pool->db.bitmap = NULL;
 	}
-	kfree(pool->db.element_manager);
 }
 
-/* This memory management works as the following:
- * - At start doesn't allocate no mem at all.
- * - When new request for chunk arrived:
- *  aloocate the first and only slot of memory/resource
- *  when it ended return error.
- */
-static int hws_pool_onesize_element_db_init(struct mlx5hws_pool *pool)
+static int hws_pool_bitmap_db_init(struct mlx5hws_pool *pool)
 {
-	pool->db.element_manager = kzalloc(sizeof(*pool->db.element_manager), GFP_KERNEL);
-	if (!pool->db.element_manager)
-		return -ENOMEM;
+	int ret;
 
-	pool->p_db_uninit = &hws_onesize_element_db_uninit;
-	pool->p_get_chunk = &hws_onesize_element_db_get_chunk;
-	pool->p_put_chunk = &hws_onesize_element_db_put_chunk;
+	ret = hws_pool_bitmap_init(pool);
+	if (ret)
+		return ret;
+
+	pool->p_db_uninit = &hws_pool_bitmap_db_uninit;
+	pool->p_get_chunk = &hws_pool_bitmap_db_get_chunk;
+	pool->p_put_chunk = &hws_pool_bitmap_db_put_chunk;
 
 	return 0;
 }
@@ -542,15 +298,14 @@ static int hws_pool_db_init(struct mlx5hws_pool *pool,
 {
 	int ret;
 
-	if (db_type == MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE)
-		ret = hws_pool_general_element_db_init(pool);
-	else if (db_type == MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE)
-		ret = hws_pool_onesize_element_db_init(pool);
+	if (db_type == MLX5HWS_POOL_DB_TYPE_BITMAP)
+		ret = hws_pool_bitmap_db_init(pool);
 	else
-		ret = hws_pool_buddy_db_init(pool, pool->alloc_log_sz);
+		ret = hws_pool_buddy_db_init(pool);
 
 	if (ret) {
-		mlx5hws_err(pool->ctx, "Failed to init general db : %d (ret: %d)\n", db_type, ret);
+		mlx5hws_err(pool->ctx, "Failed to init pool type: %d (ret: %d)\n",
+			    db_type, ret);
 		return ret;
 	}
 
@@ -569,6 +324,8 @@ int mlx5hws_pool_chunk_alloc(struct mlx5hws_pool *pool,
 
 	mutex_lock(&pool->lock);
 	ret = pool->p_get_chunk(pool, chunk);
+	if (ret == 0)
+		pool->available_elems -= 1 << chunk->order;
 	mutex_unlock(&pool->lock);
 
 	return ret;
@@ -579,6 +336,7 @@ void mlx5hws_pool_chunk_free(struct mlx5hws_pool *pool,
 {
 	mutex_lock(&pool->lock);
 	pool->p_put_chunk(pool, chunk);
+	pool->available_elems += 1 << chunk->order;
 	mutex_unlock(&pool->lock);
 }
 
@@ -599,17 +357,13 @@ mlx5hws_pool_create(struct mlx5hws_context *ctx, struct mlx5hws_pool_attr *pool_
 	pool->tbl_type = pool_attr->table_type;
 	pool->opt_type = pool_attr->opt_type;
 
-	/* Support general db */
-	if (pool->flags == (MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE |
-			    MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK))
-		res_db_type = MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE;
-	else if (pool->flags == (MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
-				 MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS))
-		res_db_type = MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE;
-	else
+	if (pool->flags & MLX5HWS_POOL_FLAG_BUDDY)
 		res_db_type = MLX5HWS_POOL_DB_TYPE_BUDDY;
+	else
+		res_db_type = MLX5HWS_POOL_DB_TYPE_BITMAP;
 
 	pool->alloc_log_sz = pool_attr->alloc_log_sz;
+	pool->available_elems = 1 << pool_attr->alloc_log_sz;
 
 	if (hws_pool_db_init(pool, res_db_type))
 		goto free_pool;
@@ -623,18 +377,17 @@ free_pool:
 	return NULL;
 }
 
-int mlx5hws_pool_destroy(struct mlx5hws_pool *pool)
+void mlx5hws_pool_destroy(struct mlx5hws_pool *pool)
 {
-	int i;
-
 	mutex_destroy(&pool->lock);
 
-	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++)
-		if (pool->resource[i])
-			hws_pool_resource_free(pool, i);
+	if (pool->available_elems != 1 << pool->alloc_log_sz)
+		mlx5hws_err(pool->ctx, "Attempting to destroy non-empty pool\n");
+
+	if (pool->resource)
+		hws_pool_resource_free(pool);
 
 	hws_pool_db_unint(pool);
 
 	kfree(pool);
-	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h
index 621298b352b2..33e33d5f1fb3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h
@@ -6,16 +6,12 @@
 
 #define MLX5HWS_POOL_STC_LOG_SZ 15
 
-#define MLX5HWS_POOL_RESOURCE_ARR_SZ 100
-
 enum mlx5hws_pool_type {
 	MLX5HWS_POOL_TYPE_STE,
 	MLX5HWS_POOL_TYPE_STC,
 };
 
 struct mlx5hws_pool_chunk {
-	u32 resource_idx;
-	/* Internal offset, relative to base index */
 	int offset;
 	int order;
 };
@@ -27,35 +23,17 @@ struct mlx5hws_pool_resource {
 };
 
 enum mlx5hws_pool_flags {
-	/* Only a one resource in that pool */
-	MLX5HWS_POOL_FLAGS_ONE_RESOURCE = 1 << 0,
-	MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE = 1 << 1,
-	/* No sharing resources between chunks */
-	MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK = 1 << 2,
-	/* All objects are in the same size */
-	MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS = 1 << 3,
-	/* Managed by buddy allocator */
-	MLX5HWS_POOL_FLAGS_BUDDY_MANAGED = 1 << 4,
-	/* Allocate pool_type memory on pool creation */
-	MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE = 1 << 5,
-
-	/* These values should be used by the caller */
-	MLX5HWS_POOL_FLAGS_FOR_STC_POOL =
-		MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
-		MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS,
-	MLX5HWS_POOL_FLAGS_FOR_MATCHER_STE_POOL =
-		MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE |
-		MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK,
-	MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL =
-		MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
-		MLX5HWS_POOL_FLAGS_BUDDY_MANAGED |
-		MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE,
+	/* Managed by a buddy allocator. If this is not set only allocations of
+	 * order 0 are supported.
+	 */
+	MLX5HWS_POOL_FLAG_BUDDY = BIT(0),
 };
 
 enum mlx5hws_pool_optimize {
 	MLX5HWS_POOL_OPTIMIZE_NONE = 0x0,
 	MLX5HWS_POOL_OPTIMIZE_ORIG = 0x1,
 	MLX5HWS_POOL_OPTIMIZE_MIRROR = 0x2,
+	MLX5HWS_POOL_OPTIMIZE_MAX = 0x3,
 };
 
 struct mlx5hws_pool_attr {
@@ -68,34 +46,17 @@ struct mlx5hws_pool_attr {
 };
 
 enum mlx5hws_db_type {
-	/* Uses for allocating chunk of big memory, each element has its own resource in the FW*/
-	MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE,
-	/* One resource only, all the elements are with same one size */
-	MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE,
-	/* Many resources, the memory allocated with buddy mechanism */
+	/* Uses a bitmap, supports only allocations of order 0. */
+	MLX5HWS_POOL_DB_TYPE_BITMAP,
+	/* Entries are managed using a buddy mechanism. */
 	MLX5HWS_POOL_DB_TYPE_BUDDY,
 };
 
-struct mlx5hws_buddy_manager {
-	struct mlx5hws_buddy_mem *buddies[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-};
-
-struct mlx5hws_pool_elements {
-	u32 num_of_elements;
-	unsigned long *bitmap;
-	u32 log_size;
-	bool is_full;
-};
-
-struct mlx5hws_element_manager {
-	struct mlx5hws_pool_elements *elements[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-};
-
 struct mlx5hws_pool_db {
 	enum mlx5hws_db_type type;
 	union {
-		struct mlx5hws_element_manager *element_manager;
-		struct mlx5hws_buddy_manager *buddy_manager;
+		unsigned long *bitmap;
+		struct mlx5hws_buddy_mem *buddy;
 	};
 };
 
@@ -111,11 +72,11 @@ struct mlx5hws_pool {
 	enum mlx5hws_pool_flags flags;
 	struct mutex lock; /* protect the pool */
 	size_t alloc_log_sz;
+	size_t available_elems;
 	enum mlx5hws_table_type tbl_type;
 	enum mlx5hws_pool_optimize opt_type;
-	struct mlx5hws_pool_resource *resource[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-	struct mlx5hws_pool_resource *mirror_resource[MLX5HWS_POOL_RESOURCE_ARR_SZ];
-	/* DB */
+	struct mlx5hws_pool_resource *resource;
+	struct mlx5hws_pool_resource *mirror_resource;
 	struct mlx5hws_pool_db db;
 	/* Functions */
 	mlx5hws_pool_unint_db p_db_uninit;
@@ -127,7 +88,7 @@ struct mlx5hws_pool *
 mlx5hws_pool_create(struct mlx5hws_context *ctx,
 		    struct mlx5hws_pool_attr *pool_attr);
 
-int mlx5hws_pool_destroy(struct mlx5hws_pool *pool);
+void mlx5hws_pool_destroy(struct mlx5hws_pool *pool);
 
 int mlx5hws_pool_chunk_alloc(struct mlx5hws_pool *pool,
 			     struct mlx5hws_pool_chunk *chunk);
@@ -135,17 +96,37 @@ int mlx5hws_pool_chunk_alloc(struct mlx5hws_pool *pool,
 void mlx5hws_pool_chunk_free(struct mlx5hws_pool *pool,
 			     struct mlx5hws_pool_chunk *chunk);
 
-static inline u32
-mlx5hws_pool_chunk_get_base_id(struct mlx5hws_pool *pool,
-			       struct mlx5hws_pool_chunk *chunk)
+static inline u32 mlx5hws_pool_get_base_id(struct mlx5hws_pool *pool)
 {
-	return pool->resource[chunk->resource_idx]->base_id;
+	return pool->resource->base_id;
 }
 
-static inline u32
-mlx5hws_pool_chunk_get_base_mirror_id(struct mlx5hws_pool *pool,
-				      struct mlx5hws_pool_chunk *chunk)
+static inline u32 mlx5hws_pool_get_base_mirror_id(struct mlx5hws_pool *pool)
 {
-	return pool->mirror_resource[chunk->resource_idx]->base_id;
+	return pool->mirror_resource->base_id;
+}
+
+static inline bool
+mlx5hws_pool_empty(struct mlx5hws_pool *pool)
+{
+	bool ret;
+
+	mutex_lock(&pool->lock);
+	ret = pool->available_elems == 0;
+	mutex_unlock(&pool->lock);
+
+	return ret;
+}
+
+static inline bool
+mlx5hws_pool_full(struct mlx5hws_pool *pool)
+{
+	bool ret;
+
+	mutex_lock(&pool->lock);
+	ret = pool->available_elems == (1 << pool->alloc_log_sz);
+	mutex_unlock(&pool->lock);
+
+	return ret;
 }
 #endif /* MLX5HWS_POOL_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
index a27a2d5ffc7b..5342a4cc7194 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
@@ -195,44 +195,30 @@ hws_rule_load_delete_info(struct mlx5hws_rule *rule,
 	}
 }
 
-static int hws_rule_alloc_action_ste(struct mlx5hws_rule *rule)
+static int mlx5hws_rule_alloc_action_ste(struct mlx5hws_rule *rule,
+					 u16 queue_id, bool skip_rx,
+					 bool skip_tx)
 {
 	struct mlx5hws_matcher *matcher = rule->matcher;
-	struct mlx5hws_matcher_action_ste *action_ste;
-	struct mlx5hws_pool_chunk ste = {0};
-	int ret;
-
-	action_ste = &matcher->action_ste;
-	ste.order = ilog2(roundup_pow_of_two(action_ste->max_stes));
-	ret = mlx5hws_pool_chunk_alloc(action_ste->pool, &ste);
-	if (unlikely(ret)) {
-		mlx5hws_err(matcher->tbl->ctx,
-			    "Failed to allocate STE for rule actions");
-		return ret;
-	}
-
-	rule->action_ste.pool = matcher->action_ste.pool;
-	rule->action_ste.num_stes = matcher->action_ste.max_stes;
-	rule->action_ste.index = ste.offset;
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
 
-	return 0;
+	rule->action_ste.ste.order =
+		ilog2(roundup_pow_of_two(matcher->num_of_action_stes));
+	return mlx5hws_action_ste_chunk_alloc(&ctx->action_ste_pool[queue_id],
+					      skip_rx, skip_tx,
+					      &rule->action_ste);
 }
 
-void mlx5hws_rule_free_action_ste(struct mlx5hws_rule_action_ste_info *action_ste)
+void mlx5hws_rule_free_action_ste(struct mlx5hws_action_ste_chunk *action_ste)
 {
-	struct mlx5hws_pool_chunk ste = {0};
-
-	if (!action_ste->num_stes)
+	if (!action_ste->action_tbl)
 		return;
 
-	ste.order = ilog2(roundup_pow_of_two(action_ste->num_stes));
-	ste.offset = action_ste->index;
-
 	/* This release is safe only when the rule match STE was deleted
 	 * (when the rule is being deleted) or replaced with the new STE that
 	 * isn't pointing to old action STEs (when the rule is being updated).
 	 */
-	mlx5hws_pool_chunk_free(action_ste->pool, &ste);
+	mlx5hws_action_ste_chunk_free(action_ste);
 }
 
 static void hws_rule_create_init(struct mlx5hws_rule *rule,
@@ -250,22 +236,15 @@ static void hws_rule_create_init(struct mlx5hws_rule *rule,
 		rule->rtc_0 = 0;
 		rule->rtc_1 = 0;
 
-		rule->action_ste.pool = NULL;
-		rule->action_ste.num_stes = 0;
-		rule->action_ste.index = -1;
-
 		rule->status = MLX5HWS_RULE_STATUS_CREATING;
 	} else {
 		rule->status = MLX5HWS_RULE_STATUS_UPDATING;
+		/* Save the old action STE info so we can free it after writing
+		 * new action STEs and a corresponding match STE.
+		 */
+		rule->old_action_ste = rule->action_ste;
 	}
 
-	/* Initialize the old action STE info - shallow-copy action_ste.
-	 * In create flow this will set old_action_ste fields to initial values.
-	 * In update flow this will save the existing action STE info,
-	 * so that we will later use it to free old STEs.
-	 */
-	rule->old_action_ste = rule->action_ste;
-
 	rule->pending_wqes = 0;
 
 	/* Init default send STE attributes */
@@ -277,7 +256,6 @@ static void hws_rule_create_init(struct mlx5hws_rule *rule,
 	/* Init default action apply */
 	apply->tbl_type = tbl->type;
 	apply->common_res = &ctx->common_res;
-	apply->jump_to_action_stc = matcher->action_ste.stc.offset;
 	apply->require_dep = 0;
 }
 
@@ -353,17 +331,24 @@ static int hws_rule_create_hws(struct mlx5hws_rule *rule,
 
 	if (action_stes) {
 		/* Allocate action STEs for rules that need more than match STE */
-		ret = hws_rule_alloc_action_ste(rule);
+		ret = mlx5hws_rule_alloc_action_ste(rule, attr->queue_id,
+						    !!ste_attr.rtc_0,
+						    !!ste_attr.rtc_1);
 		if (ret) {
 			mlx5hws_err(ctx, "Failed to allocate action memory %d", ret);
 			mlx5hws_send_abort_new_dep_wqe(queue);
 			return ret;
 		}
+		apply.jump_to_action_stc =
+			rule->action_ste.action_tbl->stc.offset;
 		/* Skip RX/TX based on the dep_wqe init */
-		ste_attr.rtc_0 = dep_wqe->rtc_0 ? matcher->action_ste.rtc_0_id : 0;
-		ste_attr.rtc_1 = dep_wqe->rtc_1 ? matcher->action_ste.rtc_1_id : 0;
+		ste_attr.rtc_0 = dep_wqe->rtc_0 ?
+				 rule->action_ste.action_tbl->rtc_0_id : 0;
+		ste_attr.rtc_1 = dep_wqe->rtc_1 ?
+				 rule->action_ste.action_tbl->rtc_1_id : 0;
 		/* Action STEs are written to a specific index last to first */
-		ste_attr.direct_index = rule->action_ste.index + action_stes;
+		ste_attr.direct_index =
+			rule->action_ste.ste.offset + action_stes;
 		apply.next_direct_idx = ste_attr.direct_index;
 	} else {
 		apply.next_direct_idx = 0;
@@ -670,6 +655,124 @@ int mlx5hws_rule_move_hws_add(struct mlx5hws_rule *rule,
 	return 0;
 }
 
+static u8 hws_rule_ethertype_to_matcher_ipv(u32 ethertype)
+{
+	switch (ethertype) {
+	case ETH_P_IP:
+		return MLX5HWS_MATCHER_IPV_4;
+	case ETH_P_IPV6:
+		return MLX5HWS_MATCHER_IPV_6;
+	default:
+		return MLX5HWS_MATCHER_IPV_UNSET;
+	}
+}
+
+static u8 hws_rule_ip_version_to_matcher_ipv(u32 ip_version)
+{
+	switch (ip_version) {
+	case 4:
+		return MLX5HWS_MATCHER_IPV_4;
+	case 6:
+		return MLX5HWS_MATCHER_IPV_6;
+	default:
+		return MLX5HWS_MATCHER_IPV_UNSET;
+	}
+}
+
+static int hws_rule_check_outer_ip_version(struct mlx5hws_matcher *matcher,
+					   u32 *match_param)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	u8 outer_ipv_ether = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 outer_ipv_ip = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 outer_ipv, ver;
+
+	if (matcher->matches_outer_ethertype) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       outer_headers.ethertype);
+		outer_ipv_ether = hws_rule_ethertype_to_matcher_ipv(ver);
+	}
+	if (matcher->matches_outer_ip_version) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       outer_headers.ip_version);
+		outer_ipv_ip = hws_rule_ip_version_to_matcher_ipv(ver);
+	}
+
+	if (outer_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET &&
+	    outer_ipv_ip != MLX5HWS_MATCHER_IPV_UNSET &&
+	    outer_ipv_ether != outer_ipv_ip) {
+		mlx5hws_err(ctx, "Rule matches on inconsistent outer ethertype and ip version\n");
+		return -EINVAL;
+	}
+
+	outer_ipv = outer_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET ?
+		    outer_ipv_ether : outer_ipv_ip;
+	if (outer_ipv != MLX5HWS_MATCHER_IPV_UNSET &&
+	    matcher->outer_ip_version != MLX5HWS_MATCHER_IPV_UNSET &&
+	    outer_ipv != matcher->outer_ip_version) {
+		mlx5hws_err(ctx, "Matcher and rule disagree on outer IP version\n");
+		return -EINVAL;
+	}
+	matcher->outer_ip_version = outer_ipv;
+
+	return 0;
+}
+
+static int hws_rule_check_inner_ip_version(struct mlx5hws_matcher *matcher,
+					   u32 *match_param)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	u8 inner_ipv_ether = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 inner_ipv_ip = MLX5HWS_MATCHER_IPV_UNSET;
+	u8 inner_ipv, ver;
+
+	if (matcher->matches_inner_ethertype) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       inner_headers.ethertype);
+		inner_ipv_ether = hws_rule_ethertype_to_matcher_ipv(ver);
+	}
+	if (matcher->matches_inner_ip_version) {
+		ver = MLX5_GET(fte_match_param, match_param,
+			       inner_headers.ip_version);
+		inner_ipv_ip = hws_rule_ip_version_to_matcher_ipv(ver);
+	}
+
+	if (inner_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET &&
+	    inner_ipv_ip != MLX5HWS_MATCHER_IPV_UNSET &&
+	    inner_ipv_ether != inner_ipv_ip) {
+		mlx5hws_err(ctx, "Rule matches on inconsistent inner ethertype and ip version\n");
+		return -EINVAL;
+	}
+
+	inner_ipv = inner_ipv_ether != MLX5HWS_MATCHER_IPV_UNSET ?
+		    inner_ipv_ether : inner_ipv_ip;
+	if (inner_ipv != MLX5HWS_MATCHER_IPV_UNSET &&
+	    matcher->inner_ip_version != MLX5HWS_MATCHER_IPV_UNSET &&
+	    inner_ipv != matcher->inner_ip_version) {
+		mlx5hws_err(ctx, "Matcher and rule disagree on inner IP version\n");
+		return -EINVAL;
+	}
+	matcher->inner_ip_version = inner_ipv;
+
+	return 0;
+}
+
+static int hws_rule_check_ip_version(struct mlx5hws_matcher *matcher,
+				     u32 *match_param)
+{
+	int ret;
+
+	ret = hws_rule_check_outer_ip_version(matcher, match_param);
+	if (unlikely(ret))
+		return ret;
+
+	ret = hws_rule_check_inner_ip_version(matcher, match_param);
+	if (unlikely(ret))
+		return ret;
+
+	return 0;
+}
+
 int mlx5hws_rule_create(struct mlx5hws_matcher *matcher,
 			u8 mt_idx,
 			u32 *match_param,
@@ -680,6 +783,10 @@ int mlx5hws_rule_create(struct mlx5hws_matcher *matcher,
 {
 	int ret;
 
+	ret = hws_rule_check_ip_version(matcher, match_param);
+	if (unlikely(ret))
+		return ret;
+
 	rule_handle->matcher = matcher;
 
 	ret = hws_rule_enqueue_precheck_create(rule_handle, attr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h
index b5ee94ac449b..1c47a9c11572 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h
@@ -43,12 +43,6 @@ struct mlx5hws_rule_match_tag {
 	};
 };
 
-struct mlx5hws_rule_action_ste_info {
-	struct mlx5hws_pool *pool;
-	int index; /* STE array index */
-	u8 num_stes;
-};
-
 struct mlx5hws_rule_resize_info {
 	u32 rtc_0;
 	u32 rtc_1;
@@ -64,8 +58,8 @@ struct mlx5hws_rule {
 		struct mlx5hws_rule_match_tag tag;
 		struct mlx5hws_rule_resize_info *resize_info;
 	};
-	struct mlx5hws_rule_action_ste_info action_ste;
-	struct mlx5hws_rule_action_ste_info old_action_ste;
+	struct mlx5hws_action_ste_chunk action_ste;
+	struct mlx5hws_action_ste_chunk old_action_ste;
 	u32 rtc_0; /* The RTC into which the STE was inserted */
 	u32 rtc_1; /* The RTC into which the STE was inserted */
 	u8 status; /* enum mlx5hws_rule_status */
@@ -75,7 +69,7 @@ struct mlx5hws_rule {
 			   */
 };
 
-void mlx5hws_rule_free_action_ste(struct mlx5hws_rule_action_ste_info *action_ste);
+void mlx5hws_rule_free_action_ste(struct mlx5hws_action_ste_chunk *action_ste);
 
 int mlx5hws_rule_move_hws_remove(struct mlx5hws_rule *rule,
 				 void *queue, void *user_data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
index cb6abc4ab7df..c4b22be19a9b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
@@ -344,18 +344,133 @@ hws_send_engine_update_rule_resize(struct mlx5hws_send_engine *queue,
 	}
 }
 
+static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
+					   struct mlx5hws_send_ring_priv *priv,
+					   struct mlx5_cqe64 *cqe)
+{
+	u8 wqe_opcode = cqe ? be32_to_cpu(cqe->sop_drop_qpn) >> 24 : 0;
+	struct mlx5hws_context *ctx = priv->rule->matcher->tbl->ctx;
+	u32 opcode = cqe ? get_cqe_opcode(cqe) : 0;
+	struct mlx5hws_rule *rule = priv->rule;
+
+	/* If something bad happens and lots of rules are failing, we don't
+	 * want to pollute dmesg. Print only the first bad cqe per engine,
+	 * the one that started the avalanche.
+	 */
+	if (queue->error_cqe_printed)
+		return;
+
+	queue->error_cqe_printed = true;
+
+	if (mlx5hws_rule_move_in_progress(rule))
+		mlx5hws_err(ctx,
+			    "--- rule 0x%08llx: error completion moving rule: phase %s, wqes left %d\n",
+			    HWS_PTR_TO_ID(rule),
+			    rule->resize_info->state ==
+			    MLX5HWS_RULE_RESIZE_STATE_WRITING ? "WRITING" :
+			    rule->resize_info->state ==
+			    MLX5HWS_RULE_RESIZE_STATE_DELETING ? "DELETING" :
+			    "UNKNOWN",
+			    rule->pending_wqes);
+	else
+		mlx5hws_err(ctx,
+			    "--- rule 0x%08llx: error completion %s (%d), wqes left %d\n",
+			    HWS_PTR_TO_ID(rule),
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_CREATING ? "CREATING" :
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_DELETING ? "DELETING" :
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_FAILING ? "FAILING" :
+			    rule->status ==
+			    MLX5HWS_RULE_STATUS_UPDATING ? "UPDATING" : "NA",
+			    rule->status,
+			    rule->pending_wqes);
+
+	mlx5hws_err(ctx, "    rule 0x%08llx: matcher 0x%llx %s\n",
+		    HWS_PTR_TO_ID(rule),
+		    HWS_PTR_TO_ID(rule->matcher),
+		    (rule->matcher->flags & MLX5HWS_MATCHER_FLAGS_ISOLATED) ?
+		    "(isolated)" : "");
+
+	if (!cqe) {
+		mlx5hws_err(ctx, "    rule 0x%08llx: no CQE\n",
+			    HWS_PTR_TO_ID(rule));
+		return;
+	}
+
+	mlx5hws_err(ctx, "    rule 0x%08llx: cqe->opcode      = %d %s\n",
+		    HWS_PTR_TO_ID(rule), opcode,
+		    opcode == MLX5_CQE_REQ ? "(MLX5_CQE_REQ)" :
+		    opcode == MLX5_CQE_REQ_ERR ? "(MLX5_CQE_REQ_ERR)" : " ");
+
+	if (opcode == MLX5_CQE_REQ_ERR) {
+		struct mlx5_err_cqe *err_cqe = (struct mlx5_err_cqe *)cqe;
+
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- hw_error_syndrome = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->rsvd1[16]);
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- hw_syndrome_type = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->rsvd1[17] >> 4);
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- vendor_err_synd = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->vendor_err_synd);
+		mlx5hws_err(ctx,
+			    "    rule 0x%08llx:  |--- syndrome = 0x%x\n",
+			    HWS_PTR_TO_ID(rule),
+			    err_cqe->syndrome);
+	}
+
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx: cqe->byte_cnt      = 0x%08x\n",
+		    HWS_PTR_TO_ID(rule), be32_to_cpu(cqe->byte_cnt));
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |-- UPDATE STATUS = %s\n",
+		    HWS_PTR_TO_ID(rule),
+		    (be32_to_cpu(cqe->byte_cnt) & 0x80000000) ?
+		    "FAILURE" : "SUCCESS");
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |------- SYNDROME = %s\n",
+		    HWS_PTR_TO_ID(rule),
+		    ((be32_to_cpu(cqe->byte_cnt) & 0x00000003) == 1) ?
+		    "SET_FLOW_FAIL" :
+		    ((be32_to_cpu(cqe->byte_cnt) & 0x00000003) == 2) ?
+		    "DISABLE_FLOW_FAIL" : "UNKNOWN");
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx: cqe->sop_drop_qpn  = 0x%08x\n",
+		    HWS_PTR_TO_ID(rule), be32_to_cpu(cqe->sop_drop_qpn));
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |-send wqe opcode = 0x%02x %s\n",
+		    HWS_PTR_TO_ID(rule), wqe_opcode,
+		    wqe_opcode == MLX5HWS_WQE_OPCODE_TBL_ACCESS ?
+		    "(MLX5HWS_WQE_OPCODE_TBL_ACCESS)" : "(UNKNOWN)");
+	mlx5hws_err(ctx,
+		    "    rule 0x%08llx:  |------------ qpn = 0x%06x\n",
+		    HWS_PTR_TO_ID(rule),
+		    be32_to_cpu(cqe->sop_drop_qpn) & 0xffffff);
+}
+
 static void hws_send_engine_update_rule(struct mlx5hws_send_engine *queue,
 					struct mlx5hws_send_ring_priv *priv,
 					u16 wqe_cnt,
-					enum mlx5hws_flow_op_status *status)
+					enum mlx5hws_flow_op_status *status,
+					struct mlx5_cqe64 *cqe)
 {
 	priv->rule->pending_wqes--;
 
-	if (*status == MLX5HWS_FLOW_OP_ERROR) {
+	if (unlikely(*status == MLX5HWS_FLOW_OP_ERROR)) {
 		if (priv->retry_id) {
+			/* If there is a retry_id, then it's not an error yet,
+			 * retry to insert this rule in the collision RTC.
+			 */
 			hws_send_engine_retry_post_send(queue, priv, wqe_cnt);
 			return;
 		}
+		hws_send_engine_dump_error_cqe(queue, priv, cqe);
 		/* Some part of the rule failed */
 		priv->rule->status = MLX5HWS_RULE_STATUS_FAILING;
 		*priv->used_id = 0;
@@ -420,7 +535,8 @@ static void hws_send_engine_update(struct mlx5hws_send_engine *queue,
 
 	if (priv->user_data) {
 		if (priv->rule) {
-			hws_send_engine_update_rule(queue, priv, wqe_cnt, &status);
+			hws_send_engine_update_rule(queue, priv, wqe_cnt,
+						    &status, cqe);
 			/* Completion is provided on the last rule WQE */
 			if (priv->rule->pending_wqes)
 				return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h
index f833092235c1..3fb8e99309b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h
@@ -140,6 +140,7 @@ struct mlx5hws_send_engine {
 	u16 used_entries;
 	u16 num_entries;
 	bool err;
+	bool error_cqe_printed;
 	struct mutex lock; /* Protects the send engine */
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
index ab1297531232..568f691733f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
@@ -342,10 +342,10 @@ int mlx5hws_table_ft_set_next_rtc(struct mlx5hws_context *ctx,
 	return mlx5hws_cmd_flow_table_modify(ctx->mdev, &ft_attr, ft_id);
 }
 
-static int hws_table_ft_set_next_ft(struct mlx5hws_context *ctx,
-				    u32 ft_id,
-				    u32 fw_ft_type,
-				    u32 next_ft_id)
+int mlx5hws_table_ft_set_next_ft(struct mlx5hws_context *ctx,
+				 u32 ft_id,
+				 u32 fw_ft_type,
+				 u32 next_ft_id)
 {
 	struct mlx5hws_cmd_ft_modify_attr ft_attr = {0};
 
@@ -389,10 +389,10 @@ int mlx5hws_table_connect_to_miss_table(struct mlx5hws_table *src_tbl,
 	if (dst_tbl) {
 		if (list_empty(&dst_tbl->matchers_list)) {
 			/* Connect src_tbl last_ft to dst_tbl start anchor */
-			ret = hws_table_ft_set_next_ft(src_tbl->ctx,
-						       last_ft_id,
-						       src_tbl->fw_ft_type,
-						       dst_tbl->ft_id);
+			ret = mlx5hws_table_ft_set_next_ft(src_tbl->ctx,
+							   last_ft_id,
+							   src_tbl->fw_ft_type,
+							   dst_tbl->ft_id);
 			if (ret)
 				return ret;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
index dd50420eec9e..0400cce0c317 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
@@ -65,4 +65,9 @@ int mlx5hws_table_ft_set_next_rtc(struct mlx5hws_context *ctx,
 				  u32 rtc_0_id,
 				  u32 rtc_1_id);
 
+int mlx5hws_table_ft_set_next_ft(struct mlx5hws_context *ctx,
+				 u32 ft_id,
+				 u32 fw_ft_type,
+				 u32 next_ft_id);
+
 #endif /* MLX5HWS_TABLE_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c
index 8007d3f523c9..f367997ab61e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c
@@ -833,15 +833,21 @@ static u32 mlx5_cmd_dr_get_capabilities(struct mlx5_flow_root_namespace *ns,
 	return steering_caps;
 }
 
-int mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat)
+int
+mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				      u32 *reformat_id)
 {
+	struct mlx5dr_action *dr_action;
+
 	switch (pkt_reformat->reformat_type) {
 	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
 	case MLX5_REFORMAT_TYPE_L2_TO_NVGRE:
 	case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
 	case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
 	case MLX5_REFORMAT_TYPE_INSERT_HDR:
-		return mlx5dr_action_get_pkt_reformat_id(pkt_reformat->fs_dr_action.dr_action);
+		dr_action = pkt_reformat->fs_dr_action.dr_action;
+		*reformat_id = mlx5dr_action_get_pkt_reformat_id(dr_action);
+		return 0;
 	}
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h
index 99a3b2eff6b8..f869f2daefbf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h
@@ -38,7 +38,9 @@ struct mlx5_fs_dr_table {
 
 bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev);
 
-int mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat);
+int
+mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				      u32 *reformat_id);
 
 const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void);
 
@@ -49,9 +51,11 @@ static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void)
 	return NULL;
 }
 
-static inline u32 mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat)
+static inline int
+mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat,
+				      u32 *reformat_id)
 {
-	return 0;
+	return -EOPNOTSUPP;
 }
 
 static inline bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3080ea032e7f..618957d65663 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1159,63 +1159,31 @@ static int mlxsw_sp_set_features(struct net_device *dev,
 	return 0;
 }
 
-static int mlxsw_sp_port_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct ifreq *ifr)
+static int mlxsw_sp_port_hwtstamp_set(struct net_device *dev,
+				      struct kernel_hwtstamp_config *config,
+				      struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config config;
-	int err;
-
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	err = mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port,
-							     &config);
-	if (err)
-		return err;
-
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 
-	return 0;
+	return mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port,
+							      config, extack);
 }
 
-static int mlxsw_sp_port_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct ifreq *ifr)
+static int mlxsw_sp_port_hwtstamp_get(struct net_device *dev,
+				      struct kernel_hwtstamp_config *config)
 {
-	struct hwtstamp_config config;
-	int err;
-
-	err = mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_get(mlxsw_sp_port,
-							     &config);
-	if (err)
-		return err;
-
-	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
-		return -EFAULT;
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 
-	return 0;
+	return mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_get(mlxsw_sp_port,
+							      config);
 }
 
 static inline void mlxsw_sp_port_ptp_clear(struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	struct hwtstamp_config config = {0};
-
-	mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port, &config);
-}
-
-static int
-mlxsw_sp_port_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct kernel_hwtstamp_config config = {};
 
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return mlxsw_sp_port_hwtstamp_set(mlxsw_sp_port, ifr);
-	case SIOCGHWTSTAMP:
-		return mlxsw_sp_port_hwtstamp_get(mlxsw_sp_port, ifr);
-	default:
-		return -EOPNOTSUPP;
-	}
+	mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port, &config,
+						       NULL);
 }
 
 static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
@@ -1232,7 +1200,8 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= mlxsw_sp_port_add_vid,
 	.ndo_vlan_rx_kill_vid	= mlxsw_sp_port_kill_vid,
 	.ndo_set_features	= mlxsw_sp_set_features,
-	.ndo_eth_ioctl		= mlxsw_sp_port_ioctl,
+	.ndo_hwtstamp_get	= mlxsw_sp_port_hwtstamp_get,
+	.ndo_hwtstamp_set	= mlxsw_sp_port_hwtstamp_set,
 };
 
 static int
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 37cd1d002b3b..b03ff9e044f9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -233,9 +233,10 @@ struct mlxsw_sp_ptp_ops {
 			    u16 local_port);
 
 	int (*hwtstamp_get)(struct mlxsw_sp_port *mlxsw_sp_port,
-			    struct hwtstamp_config *config);
+			    struct kernel_hwtstamp_config *config);
 	int (*hwtstamp_set)(struct mlxsw_sp_port *mlxsw_sp_port,
-			    struct hwtstamp_config *config);
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack);
 	void (*shaper_work)(struct work_struct *work);
 	int (*get_ts_info)(struct mlxsw_sp *mlxsw_sp,
 			   struct kernel_ethtool_ts_info *info);
@@ -351,7 +352,7 @@ struct mlxsw_sp_port {
 	struct mlxsw_sp_flow_block *eg_flow_block;
 	struct {
 		struct delayed_work shaper_dw;
-		struct hwtstamp_config hwtstamp_config;
+		struct kernel_hwtstamp_config hwtstamp_config;
 		u16 ing_types;
 		u16 egr_types;
 		struct mlxsw_sp_ptp_port_stats stats;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
index 3f64cdbabfa3..0a8fb9c842d3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
@@ -262,7 +262,7 @@ err_port_pause_configure:
 }
 
 struct mlxsw_sp_port_hw_stats {
-	char str[ETH_GSTRING_LEN];
+	char str[ETH_GSTRING_LEN] __nonstring;
 	u64 (*getter)(const char *payload);
 	bool cells_bytes;
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index ca8b9d18fbb9..e8182dd76c7d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -46,7 +46,7 @@ struct mlxsw_sp2_ptp_state {
 	refcount_t ptp_port_enabled_ref; /* Number of ports with time stamping
 					  * enabled.
 					  */
-	struct hwtstamp_config config;
+	struct kernel_hwtstamp_config config;
 	struct mutex lock; /* Protects 'config' and HW configuration. */
 };
 
@@ -1083,14 +1083,14 @@ void mlxsw_sp1_ptp_fini(struct mlxsw_sp_ptp_state *ptp_state_common)
 }
 
 int mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config)
 {
 	*config = mlxsw_sp_port->ptp.hwtstamp_config;
 	return 0;
 }
 
 static int
-mlxsw_sp1_ptp_get_message_types(const struct hwtstamp_config *config,
+mlxsw_sp1_ptp_get_message_types(const struct kernel_hwtstamp_config *config,
 				u16 *p_ing_types, u16 *p_egr_types,
 				enum hwtstamp_rx_filters *p_rx_filter)
 {
@@ -1246,7 +1246,8 @@ void mlxsw_sp1_ptp_shaper_work(struct work_struct *work)
 }
 
 int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
 {
 	enum hwtstamp_rx_filters rx_filter;
 	u16 ing_types;
@@ -1270,7 +1271,7 @@ int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (err)
 		return err;
 
-	/* Notify the ioctl caller what we are actually timestamping. */
+	/* Notify the caller what we are actually timestamping. */
 	config->rx_filter = rx_filter;
 
 	return 0;
@@ -1451,7 +1452,7 @@ void mlxsw_sp2_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
 }
 
 int mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state;
 
@@ -1465,7 +1466,7 @@ int mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
 }
 
 static int
-mlxsw_sp2_ptp_get_message_types(const struct hwtstamp_config *config,
+mlxsw_sp2_ptp_get_message_types(const struct kernel_hwtstamp_config *config,
 				u16 *p_ing_types, u16 *p_egr_types,
 				enum hwtstamp_rx_filters *p_rx_filter)
 {
@@ -1542,7 +1543,7 @@ static int mlxsw_sp2_ptp_mtpcpc_set(struct mlxsw_sp *mlxsw_sp, bool ptp_trap_en,
 
 static int mlxsw_sp2_ptp_enable(struct mlxsw_sp *mlxsw_sp, u16 ing_types,
 				u16 egr_types,
-				struct hwtstamp_config new_config)
+				struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp);
 	int err;
@@ -1556,7 +1557,7 @@ static int mlxsw_sp2_ptp_enable(struct mlxsw_sp *mlxsw_sp, u16 ing_types,
 }
 
 static int mlxsw_sp2_ptp_disable(struct mlxsw_sp *mlxsw_sp,
-				 struct hwtstamp_config new_config)
+				 struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp);
 	int err;
@@ -1571,7 +1572,7 @@ static int mlxsw_sp2_ptp_disable(struct mlxsw_sp *mlxsw_sp,
 
 static int mlxsw_sp2_ptp_configure_port(struct mlxsw_sp_port *mlxsw_sp_port,
 					u16 ing_types, u16 egr_types,
-					struct hwtstamp_config new_config)
+					struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
@@ -1592,7 +1593,7 @@ static int mlxsw_sp2_ptp_configure_port(struct mlxsw_sp_port *mlxsw_sp_port,
 }
 
 static int mlxsw_sp2_ptp_deconfigure_port(struct mlxsw_sp_port *mlxsw_sp_port,
-					  struct hwtstamp_config new_config)
+					  struct kernel_hwtstamp_config new_config)
 {
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
@@ -1614,11 +1615,12 @@ err_ptp_disable:
 }
 
 int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config)
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
 {
+	struct kernel_hwtstamp_config new_config;
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	enum hwtstamp_rx_filters rx_filter;
-	struct hwtstamp_config new_config;
 	u16 new_ing_types, new_egr_types;
 	bool ptp_enabled;
 	int err;
@@ -1652,7 +1654,7 @@ int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->ptp.ing_types = new_ing_types;
 	mlxsw_sp_port->ptp.egr_types = new_egr_types;
 
-	/* Notify the ioctl caller what we are actually timestamping. */
+	/* Notify the caller what we are actually timestamping. */
 	config->rx_filter = rx_filter;
 	mutex_unlock(&ptp_state->lock);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
index 102db9060135..df37f1470830 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
@@ -34,10 +34,11 @@ void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
 				 u64 timestamp);
 
 int mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config);
 
 int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack);
 
 void mlxsw_sp1_ptp_shaper_work(struct work_struct *work);
 
@@ -65,10 +66,11 @@ void mlxsw_sp2_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
 			       struct sk_buff *skb, u16 local_port);
 
 int mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config);
 
 int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			       struct hwtstamp_config *config);
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack);
 
 int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
 			      struct kernel_ethtool_ts_info *info);
@@ -117,14 +119,15 @@ mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
 
 static inline int
 mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
+			   struct kernel_hwtstamp_config *config)
 {
 	return -EOPNOTSUPP;
 }
 
 static inline int
 mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
@@ -181,14 +184,15 @@ static inline void mlxsw_sp2_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
 
 static inline int
 mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
+			   struct kernel_hwtstamp_config *config)
 {
 	return -EOPNOTSUPP;
 }
 
 static inline int
 mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct hwtstamp_config *config)
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 464821dd492d..a2033837182e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3014,6 +3014,9 @@ static int mlxsw_sp_neigh_rif_made_sync(struct mlxsw_sp *mlxsw_sp,
 		.rif = rif,
 	};
 
+	if (!mlxsw_sp_dev_lower_is_port(mlxsw_sp_rif_dev(rif)))
+		return 0;
+
 	neigh_for_each(&arp_tbl, mlxsw_sp_neigh_rif_made_sync_each, &rms);
 	if (rms.err)
 		goto err_arp;
diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig
index 831921b9d4d5..3ba527514f1e 100644
--- a/drivers/net/ethernet/meta/Kconfig
+++ b/drivers/net/ethernet/meta/Kconfig
@@ -27,6 +27,7 @@ config FBNIC
 	select NET_DEVLINK
 	select PAGE_POOL
 	select PHYLINK
+	select PLDMFW
 	help
 	  This driver supports Meta Platforms Host Network Interface.
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index 4ca7b99ef131..65815d4f379e 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -19,6 +19,7 @@
 struct fbnic_napi_vector;
 
 #define FBNIC_MAX_NAPI_VECTORS		128u
+#define FBNIC_MBX_CMPL_SLOTS		4
 
 struct fbnic_dev {
 	struct device *dev;
@@ -42,7 +43,7 @@ struct fbnic_dev {
 
 	struct fbnic_fw_mbx mbx[FBNIC_IPC_MBX_INDICES];
 	struct fbnic_fw_cap fw_cap;
-	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_fw_completion *cmpl_data[FBNIC_MBX_CMPL_SLOTS];
 	/* Lock protecting Tx Mailbox queue to prevent possible races */
 	spinlock_t fw_tx_lock;
 
@@ -81,6 +82,9 @@ struct fbnic_dev {
 
 	/* Local copy of hardware statistics */
 	struct fbnic_hw_stats hw_stats;
+
+	/* Lock protecting access to hw_stats */
+	spinlock_t hw_stats_lock;
 };
 
 /* Reserve entry 0 in the MSI-X "others" array until we have filled all
@@ -154,14 +158,14 @@ struct fbnic_dev *fbnic_devlink_alloc(struct pci_dev *pdev);
 void fbnic_devlink_register(struct fbnic_dev *fbd);
 void fbnic_devlink_unregister(struct fbnic_dev *fbd);
 
-int fbnic_fw_enable_mbx(struct fbnic_dev *fbd);
-void fbnic_fw_disable_mbx(struct fbnic_dev *fbd);
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd);
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd);
 
 void fbnic_hwmon_register(struct fbnic_dev *fbd);
 void fbnic_hwmon_unregister(struct fbnic_dev *fbd);
 
-int fbnic_pcs_irq_enable(struct fbnic_dev *fbd);
-void fbnic_pcs_irq_disable(struct fbnic_dev *fbd);
+int fbnic_pcs_request_irq(struct fbnic_dev *fbd);
+void fbnic_pcs_free_irq(struct fbnic_dev *fbd);
 
 void fbnic_napi_name_irqs(struct fbnic_dev *fbd);
 int fbnic_napi_request_irq(struct fbnic_dev *fbd,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index 3b12a0ab5906..36393a17d92d 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -397,6 +397,15 @@ enum {
 #define FBNIC_TCE_DROP_CTRL_TTI_FRM_DROP_EN	CSR_BIT(1)
 #define FBNIC_TCE_DROP_CTRL_TTI_TBI_DROP_EN	CSR_BIT(2)
 
+#define FBNIC_TCE_TTI_CM_DROP_PKTS	0x0403e		/* 0x100f8 */
+#define FBNIC_TCE_TTI_CM_DROP_BYTE_L	0x0403f		/* 0x100fc */
+#define FBNIC_TCE_TTI_CM_DROP_BYTE_H	0x04040		/* 0x10100 */
+#define FBNIC_TCE_TTI_FRAME_DROP_PKTS	0x04041		/* 0x10104 */
+#define FBNIC_TCE_TTI_FRAME_DROP_BYTE_L	0x04042		/* 0x10108 */
+#define FBNIC_TCE_TTI_FRAME_DROP_BYTE_H	0x04043		/* 0x1010c */
+#define FBNIC_TCE_TBI_DROP_PKTS		0x04044		/* 0x10110 */
+#define FBNIC_TCE_TBI_DROP_BYTE_L	0x04045		/* 0x10114 */
+
 #define FBNIC_TCE_TCAM_IDX2DEST_MAP	0x0404A		/* 0x10128 */
 #define FBNIC_TCE_TCAM_IDX2DEST_MAP_DEST_ID_0	CSR_GENMASK(3, 0)
 enum {
@@ -432,6 +441,11 @@ enum {
 #define FBNIC_TMI_SOP_PROT_CTRL		0x04400		/* 0x11000 */
 #define FBNIC_TMI_DROP_CTRL		0x04401		/* 0x11004 */
 #define FBNIC_TMI_DROP_CTRL_EN			CSR_BIT(0)
+#define FBNIC_TMI_DROP_PKTS		0x04402		/* 0x11008 */
+#define FBNIC_TMI_DROP_BYTE_L		0x04403		/* 0x1100c */
+#define FBNIC_TMI_ILLEGAL_PTP_REQS	0x04409		/* 0x11024 */
+#define FBNIC_TMI_GOOD_PTP_TS		0x0440a		/* 0x11028 */
+#define FBNIC_TMI_BAD_PTP_TS		0x0440b		/* 0x1102c */
 #define FBNIC_CSR_END_TMI		0x0443f	/* CSR section delimiter */
 
 /* Precision Time Protocol Registers */
@@ -485,6 +499,14 @@ enum {
 	FBNIC_RXB_FIFO_INDICES		= 8
 };
 
+enum {
+	FBNIC_RXB_INTF_NET = 0,
+	FBNIC_RXB_INTF_RBT = 1,
+	/* Unused */
+	/* Unused */
+	FBNIC_RXB_INTF_INDICES	= 4
+};
+
 #define FBNIC_RXB_CT_SIZE(n)		(0x08000 + (n))	/* 0x20000 + 4*n */
 #define FBNIC_RXB_CT_SIZE_CNT			8
 #define FBNIC_RXB_CT_SIZE_HEADER		CSR_GENMASK(5, 0)
@@ -796,8 +818,10 @@ enum {
 /* PUL User Registers */
 #define FBNIC_CSR_START_PUL_USER	0x31000	/* CSR section delimiter */
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG	0x3103d		/* 0xc40f4 */
+#define FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH	CSR_BIT(19)
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME		CSR_BIT(18)
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG	0x3103e		/* 0xc40f8 */
+#define FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH	CSR_BIT(19)
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME		CSR_BIT(18)
 #define FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0 \
 					0x3106e		/* 0xc41b8 */
@@ -864,6 +888,12 @@ enum {
 #define FBNIC_QUEUE_TWQ1_BAL		0x022		/* 0x088 */
 #define FBNIC_QUEUE_TWQ1_BAH		0x023		/* 0x08c */
 
+/* Tx Work Queue Statistics Registers */
+#define FBNIC_QUEUE_TWQ0_PKT_CNT	0x062		/* 0x188 */
+#define FBNIC_QUEUE_TWQ0_ERR_CNT	0x063		/* 0x18c */
+#define FBNIC_QUEUE_TWQ1_PKT_CNT	0x072		/* 0x1c8 */
+#define FBNIC_QUEUE_TWQ1_ERR_CNT	0x073		/* 0x1cc */
+
 /* Tx Completion Queue Registers */
 #define FBNIC_QUEUE_TCQ_CTL		0x080		/* 0x200 */
 #define FBNIC_QUEUE_TCQ_CTL_RESET		CSR_BIT(0)
@@ -953,6 +983,12 @@ enum {
 	FBNIC_QUEUE_RDE_CTL1_PAYLD_PACK_RSS	= 2,
 };
 
+/* Rx Per CQ Statistics Counters */
+#define FBNIC_QUEUE_RDE_PKT_CNT		0x2a2		/* 0xa88 */
+#define FBNIC_QUEUE_RDE_PKT_ERR_CNT	0x2a3		/* 0xa8c */
+#define FBNIC_QUEUE_RDE_CQ_DROP_CNT	0x2a4		/* 0xa90 */
+#define FBNIC_QUEUE_RDE_BDQ_DROP_CNT	0x2a5		/* 0xa94 */
+
 /* Rx Interrupt Manager Registers */
 #define FBNIC_QUEUE_RIM_CTL		0x2c0		/* 0xb00 */
 #define FBNIC_QUEUE_RIM_CTL_MSIX_MASK		CSR_GENMASK(7, 0)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c b/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
index 0072d612215e..4c4938eedd7b 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
@@ -3,10 +3,12 @@
 
 #include <linux/unaligned.h>
 #include <linux/pci.h>
+#include <linux/pldmfw.h>
 #include <linux/types.h>
 #include <net/devlink.h>
 
 #include "fbnic.h"
+#include "fbnic_tlv.h"
 
 #define FBNIC_SN_STR_LEN	24
 
@@ -109,8 +111,262 @@ static int fbnic_devlink_info_get(struct devlink *devlink,
 	return 0;
 }
 
+static bool
+fbnic_pldm_match_record(struct pldmfw *context, struct pldmfw_record *record)
+{
+	struct pldmfw_desc_tlv *desc;
+	u32 anti_rollback_ver = 0;
+	struct devlink *devlink;
+	struct fbnic_dev *fbd;
+	struct pci_dev *pdev;
+
+	/* First, use the standard PCI matching function */
+	if (!pldmfw_op_pci_match_record(context, record))
+		return false;
+
+	pdev = to_pci_dev(context->dev);
+	fbd = pci_get_drvdata(pdev);
+	devlink = priv_to_devlink(fbd);
+
+	/* If PCI match is successful, check for vendor-specific descriptors */
+	list_for_each_entry(desc, &record->descs, entry) {
+		if (desc->type != PLDM_DESC_ID_VENDOR_DEFINED)
+			continue;
+
+		if (desc->size < 21 || desc->data[0] != 1 ||
+		    desc->data[1] != 15)
+			continue;
+
+		if (memcmp(desc->data + 2, "AntiRollbackVer", 15) != 0)
+			continue;
+
+		anti_rollback_ver = get_unaligned_le32(desc->data + 17);
+		break;
+	}
+
+	/* Compare versions and return error if they do not match */
+	if (anti_rollback_ver < fbd->fw_cap.anti_rollback_version) {
+		char buf[128];
+
+		snprintf(buf, sizeof(buf),
+			 "New firmware anti-rollback version (0x%x) is older than device version (0x%x)!",
+			 anti_rollback_ver, fbd->fw_cap.anti_rollback_version);
+		devlink_flash_update_status_notify(devlink, buf,
+						   "Anti-Rollback", 0, 0);
+
+		return false;
+	}
+
+	return true;
+}
+
+static int
+fbnic_flash_start(struct fbnic_dev *fbd, struct pldmfw_component *component)
+{
+	struct fbnic_fw_completion *cmpl;
+	int err;
+
+	cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ);
+	if (!cmpl)
+		return -ENOMEM;
+
+	err = fbnic_fw_xmit_fw_start_upgrade(fbd, cmpl,
+					     component->identifier,
+					     component->component_size);
+	if (err)
+		goto cmpl_free;
+
+	/* Wait for firmware to ack firmware upgrade start */
+	if (wait_for_completion_timeout(&cmpl->done, 10 * HZ))
+		err = cmpl->result;
+	else
+		err = -ETIMEDOUT;
+
+	fbnic_fw_clear_cmpl(fbd, cmpl);
+cmpl_free:
+	fbnic_fw_put_cmpl(cmpl);
+
+	return err;
+}
+
+static int
+fbnic_flash_component(struct pldmfw *context,
+		      struct pldmfw_component *component)
+{
+	const u8 *data = component->component_data;
+	const u32 size = component->component_size;
+	struct fbnic_fw_completion *cmpl;
+	const char *component_name;
+	struct devlink *devlink;
+	struct fbnic_dev *fbd;
+	struct pci_dev *pdev;
+	u32 offset = 0;
+	u32 length = 0;
+	char buf[32];
+	int err;
+
+	pdev = to_pci_dev(context->dev);
+	fbd = pci_get_drvdata(pdev);
+	devlink = priv_to_devlink(fbd);
+
+	switch (component->identifier) {
+	case QSPI_SECTION_CMRT:
+		component_name = "boot1";
+		break;
+	case QSPI_SECTION_CONTROL_FW:
+		component_name = "boot2";
+		break;
+	case QSPI_SECTION_OPTION_ROM:
+		component_name = "option-rom";
+		break;
+	default:
+		snprintf(buf, sizeof(buf), "Unknown component ID %u!",
+			 component->identifier);
+		devlink_flash_update_status_notify(devlink, buf, NULL, 0,
+						   size);
+		return -EINVAL;
+	}
+
+	/* Once firmware receives the request to start upgrading it responds
+	 * with two messages:
+	 * 1. An ACK that it received the message and possible error code
+	 *    indicating that an upgrade is not currently possible.
+	 * 2. A request for the first chunk of data
+	 *
+	 * Setup completions for write before issuing the start message so
+	 * the driver can catch both messages.
+	 */
+	cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ);
+	if (!cmpl)
+		return -ENOMEM;
+
+	err = fbnic_mbx_set_cmpl(fbd, cmpl);
+	if (err)
+		goto cmpl_free;
+
+	devlink_flash_update_timeout_notify(devlink, "Initializing",
+					    component_name, 15);
+	err = fbnic_flash_start(fbd, component);
+	if (err)
+		goto err_no_msg;
+
+	while (offset < size) {
+		if (!wait_for_completion_timeout(&cmpl->done, 15 * HZ)) {
+			err = -ETIMEDOUT;
+			break;
+		}
+
+		err = cmpl->result;
+		if (err)
+			break;
+
+		/* Verify firmware is requesting the next chunk in the seq. */
+		if (cmpl->u.fw_update.offset != offset + length) {
+			err = -EFAULT;
+			break;
+		}
+
+		offset = cmpl->u.fw_update.offset;
+		length = cmpl->u.fw_update.length;
+
+		if (length > TLV_MAX_DATA || offset + length > size) {
+			err = -EFAULT;
+			break;
+		}
+
+		devlink_flash_update_status_notify(devlink, "Flashing",
+						   component_name,
+						   offset, size);
+
+		/* Mailbox will set length to 0 once it receives the finish
+		 * message.
+		 */
+		if (!length)
+			continue;
+
+		reinit_completion(&cmpl->done);
+		err = fbnic_fw_xmit_fw_write_chunk(fbd, data, offset, length,
+						   0);
+		if (err)
+			break;
+	}
+
+	if (err) {
+		fbnic_fw_xmit_fw_write_chunk(fbd, NULL, 0, 0, err);
+err_no_msg:
+		snprintf(buf, sizeof(buf), "Mailbox encountered error %d!",
+			 err);
+		devlink_flash_update_status_notify(devlink, buf,
+						   component_name, 0, 0);
+	}
+
+	fbnic_fw_clear_cmpl(fbd, cmpl);
+cmpl_free:
+	fbnic_fw_put_cmpl(cmpl);
+
+	return err;
+}
+
+static const struct pldmfw_ops fbnic_pldmfw_ops = {
+	.match_record = fbnic_pldm_match_record,
+	.flash_component = fbnic_flash_component,
+};
+
+static int
+fbnic_devlink_flash_update(struct devlink *devlink,
+			   struct devlink_flash_update_params *params,
+			   struct netlink_ext_ack *extack)
+{
+	struct fbnic_dev *fbd = devlink_priv(devlink);
+	const struct firmware *fw = params->fw;
+	struct device *dev = fbd->dev;
+	struct pldmfw context;
+	char *err_msg;
+	int err;
+
+	context.ops = &fbnic_pldmfw_ops;
+	context.dev = dev;
+
+	err = pldmfw_flash_image(&context, fw);
+	if (err) {
+		switch (err) {
+		case -EINVAL:
+			err_msg = "Invalid image";
+			break;
+		case -EOPNOTSUPP:
+			err_msg = "Unsupported image";
+			break;
+		case -ENOMEM:
+			err_msg = "Out of memory";
+			break;
+		case -EFAULT:
+			err_msg = "Invalid header";
+			break;
+		case -ENOENT:
+			err_msg = "No matching record";
+			break;
+		case -ENODEV:
+			err_msg = "No matching device";
+			break;
+		case -ETIMEDOUT:
+			err_msg = "Timed out waiting for reply";
+			break;
+		default:
+			err_msg = "Unknown error";
+			break;
+		}
+
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Failed to flash PLDM Image: %s (error: %d)",
+				       err_msg, err);
+	}
+
+	return err;
+}
+
 static const struct devlink_ops fbnic_devlink_ops = {
-	.info_get = fbnic_devlink_info_get,
+	.info_get	= fbnic_devlink_info_get,
+	.flash_update	= fbnic_devlink_flash_update,
 };
 
 void fbnic_devlink_free(struct fbnic_dev *fbd)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
index 0a751a2aaf73..5c7556c8c4c5 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
@@ -27,6 +27,19 @@ struct fbnic_stat {
 	FBNIC_STAT_FIELDS(fbnic_hw_stats, name, stat)
 
 static const struct fbnic_stat fbnic_gstrings_hw_stats[] = {
+	/* TTI */
+	FBNIC_HW_STAT("tti_cm_drop_frames", tti.cm_drop.frames),
+	FBNIC_HW_STAT("tti_cm_drop_bytes", tti.cm_drop.bytes),
+	FBNIC_HW_STAT("tti_frame_drop_frames", tti.frame_drop.frames),
+	FBNIC_HW_STAT("tti_frame_drop_bytes", tti.frame_drop.bytes),
+	FBNIC_HW_STAT("tti_tbi_drop_frames", tti.tbi_drop.frames),
+	FBNIC_HW_STAT("tti_tbi_drop_bytes", tti.tbi_drop.bytes),
+
+	/* TMI */
+	FBNIC_HW_STAT("ptp_illegal_req", tmi.ptp_illegal_req),
+	FBNIC_HW_STAT("ptp_good_ts", tmi.ptp_good_ts),
+	FBNIC_HW_STAT("ptp_bad_ts", tmi.ptp_bad_ts),
+
 	/* RPC */
 	FBNIC_HW_STAT("rpc_unkn_etype", rpc.unkn_etype),
 	FBNIC_HW_STAT("rpc_unkn_ext_hdr", rpc.unkn_ext_hdr),
@@ -39,7 +52,64 @@ static const struct fbnic_stat fbnic_gstrings_hw_stats[] = {
 };
 
 #define FBNIC_HW_FIXED_STATS_LEN ARRAY_SIZE(fbnic_gstrings_hw_stats)
-#define FBNIC_HW_STATS_LEN	FBNIC_HW_FIXED_STATS_LEN
+
+#define FBNIC_RXB_ENQUEUE_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_rxb_enqueue_stats, name, stat)
+
+static const struct fbnic_stat fbnic_gstrings_rxb_enqueue_stats[] = {
+	FBNIC_RXB_ENQUEUE_STAT("rxb_integrity_err%u", integrity_err),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_mac_err%u", mac_err),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_parser_err%u", parser_err),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_frm_err%u", frm_err),
+
+	FBNIC_RXB_ENQUEUE_STAT("rxb_drbo%u_frames", drbo.frames),
+	FBNIC_RXB_ENQUEUE_STAT("rxb_drbo%u_bytes", drbo.bytes),
+};
+
+#define FBNIC_HW_RXB_ENQUEUE_STATS_LEN \
+	ARRAY_SIZE(fbnic_gstrings_rxb_enqueue_stats)
+
+#define FBNIC_RXB_FIFO_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_rxb_fifo_stats, name, stat)
+
+static const struct fbnic_stat fbnic_gstrings_rxb_fifo_stats[] = {
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_drop", trans_drop),
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_dropped_frames", drop.frames),
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_ecn", trans_ecn),
+	FBNIC_RXB_FIFO_STAT("rxb_fifo%u_level", level),
+};
+
+#define FBNIC_HW_RXB_FIFO_STATS_LEN ARRAY_SIZE(fbnic_gstrings_rxb_fifo_stats)
+
+#define FBNIC_RXB_DEQUEUE_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_rxb_dequeue_stats, name, stat)
+
+static const struct fbnic_stat fbnic_gstrings_rxb_dequeue_stats[] = {
+	FBNIC_RXB_DEQUEUE_STAT("rxb_intf%u_frames", intf.frames),
+	FBNIC_RXB_DEQUEUE_STAT("rxb_intf%u_bytes", intf.bytes),
+	FBNIC_RXB_DEQUEUE_STAT("rxb_pbuf%u_frames", pbuf.frames),
+	FBNIC_RXB_DEQUEUE_STAT("rxb_pbuf%u_bytes", pbuf.bytes),
+};
+
+#define FBNIC_HW_RXB_DEQUEUE_STATS_LEN \
+	ARRAY_SIZE(fbnic_gstrings_rxb_dequeue_stats)
+
+#define FBNIC_HW_Q_STAT(name, stat) \
+	FBNIC_STAT_FIELDS(fbnic_hw_q_stats, name, stat.value)
+
+static const struct fbnic_stat fbnic_gstrings_hw_q_stats[] = {
+	FBNIC_HW_Q_STAT("rde_%u_pkt_err", rde_pkt_err),
+	FBNIC_HW_Q_STAT("rde_%u_pkt_cq_drop", rde_pkt_cq_drop),
+	FBNIC_HW_Q_STAT("rde_%u_pkt_bdq_drop", rde_pkt_bdq_drop),
+};
+
+#define FBNIC_HW_Q_STATS_LEN ARRAY_SIZE(fbnic_gstrings_hw_q_stats)
+#define FBNIC_HW_STATS_LEN \
+	(FBNIC_HW_FIXED_STATS_LEN + \
+	 FBNIC_HW_RXB_ENQUEUE_STATS_LEN * FBNIC_RXB_ENQUEUE_INDICES + \
+	 FBNIC_HW_RXB_FIFO_STATS_LEN * FBNIC_RXB_FIFO_INDICES + \
+	 FBNIC_HW_RXB_DEQUEUE_STATS_LEN * FBNIC_RXB_DEQUEUE_INDICES + \
+	 FBNIC_HW_Q_STATS_LEN * FBNIC_MAX_QUEUES)
 
 static void
 fbnic_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
@@ -298,31 +368,125 @@ err_free_clone:
 	return err;
 }
 
-static void fbnic_get_strings(struct net_device *dev, u32 sset, u8 *data)
+static void fbnic_get_rxb_enqueue_strings(u8 **data, unsigned int idx)
+{
+	const struct fbnic_stat *stat;
+	int i;
+
+	stat = fbnic_gstrings_rxb_enqueue_stats;
+	for (i = 0; i < FBNIC_HW_RXB_ENQUEUE_STATS_LEN; i++, stat++)
+		ethtool_sprintf(data, stat->string, idx);
+}
+
+static void fbnic_get_rxb_fifo_strings(u8 **data, unsigned int idx)
+{
+	const struct fbnic_stat *stat;
+	int i;
+
+	stat = fbnic_gstrings_rxb_fifo_stats;
+	for (i = 0; i < FBNIC_HW_RXB_FIFO_STATS_LEN; i++, stat++)
+		ethtool_sprintf(data, stat->string, idx);
+}
+
+static void fbnic_get_rxb_dequeue_strings(u8 **data, unsigned int idx)
 {
+	const struct fbnic_stat *stat;
 	int i;
 
+	stat = fbnic_gstrings_rxb_dequeue_stats;
+	for (i = 0; i < FBNIC_HW_RXB_DEQUEUE_STATS_LEN; i++, stat++)
+		ethtool_sprintf(data, stat->string, idx);
+}
+
+static void fbnic_get_strings(struct net_device *dev, u32 sset, u8 *data)
+{
+	const struct fbnic_stat *stat;
+	int i, idx;
+
 	switch (sset) {
 	case ETH_SS_STATS:
-		for (i = 0; i < FBNIC_HW_STATS_LEN; i++)
+		for (i = 0; i < FBNIC_HW_FIXED_STATS_LEN; i++)
 			ethtool_puts(&data, fbnic_gstrings_hw_stats[i].string);
+
+		for (i = 0; i < FBNIC_RXB_ENQUEUE_INDICES; i++)
+			fbnic_get_rxb_enqueue_strings(&data, i);
+
+		for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+			fbnic_get_rxb_fifo_strings(&data, i);
+
+		for (i = 0; i < FBNIC_RXB_DEQUEUE_INDICES; i++)
+			fbnic_get_rxb_dequeue_strings(&data, i);
+
+		for (idx = 0; idx < FBNIC_MAX_QUEUES; idx++) {
+			stat = fbnic_gstrings_hw_q_stats;
+
+			for (i = 0; i < FBNIC_HW_Q_STATS_LEN; i++, stat++)
+				ethtool_sprintf(&data, stat->string, idx);
+		}
 		break;
 	}
 }
 
+static void fbnic_report_hw_stats(const struct fbnic_stat *stat,
+				  const void *base, int len, u64 **data)
+{
+	while (len--) {
+		u8 *curr = (u8 *)base + stat->offset;
+
+		**data = *(u64 *)curr;
+
+		stat++;
+		(*data)++;
+	}
+}
+
 static void fbnic_get_ethtool_stats(struct net_device *dev,
 				    struct ethtool_stats *stats, u64 *data)
 {
 	struct fbnic_net *fbn = netdev_priv(dev);
-	const struct fbnic_stat *stat;
+	struct fbnic_dev *fbd = fbn->fbd;
 	int i;
 
 	fbnic_get_hw_stats(fbn->fbd);
 
-	for (i = 0; i < FBNIC_HW_STATS_LEN; i++) {
-		stat = &fbnic_gstrings_hw_stats[i];
-		data[i] = *(u64 *)((u8 *)&fbn->fbd->hw_stats + stat->offset);
+	spin_lock(&fbd->hw_stats_lock);
+	fbnic_report_hw_stats(fbnic_gstrings_hw_stats, &fbd->hw_stats,
+			      FBNIC_HW_FIXED_STATS_LEN, &data);
+
+	for (i = 0; i < FBNIC_RXB_ENQUEUE_INDICES; i++) {
+		const struct fbnic_rxb_enqueue_stats *enq;
+
+		enq = &fbd->hw_stats.rxb.enq[i];
+		fbnic_report_hw_stats(fbnic_gstrings_rxb_enqueue_stats,
+				      enq, FBNIC_HW_RXB_ENQUEUE_STATS_LEN,
+				      &data);
+	}
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++) {
+		const struct fbnic_rxb_fifo_stats *fifo;
+
+		fifo = &fbd->hw_stats.rxb.fifo[i];
+		fbnic_report_hw_stats(fbnic_gstrings_rxb_fifo_stats,
+				      fifo, FBNIC_HW_RXB_FIFO_STATS_LEN,
+				      &data);
+	}
+
+	for (i = 0; i < FBNIC_RXB_DEQUEUE_INDICES; i++) {
+		const struct fbnic_rxb_dequeue_stats *deq;
+
+		deq = &fbd->hw_stats.rxb.deq[i];
+		fbnic_report_hw_stats(fbnic_gstrings_rxb_dequeue_stats,
+				      deq, FBNIC_HW_RXB_DEQUEUE_STATS_LEN,
+				      &data);
+	}
+
+	for (i  = 0; i < FBNIC_MAX_QUEUES; i++) {
+		const struct fbnic_hw_q_stats *hw_q = &fbd->hw_stats.hw_q[i];
+
+		fbnic_report_hw_stats(fbnic_gstrings_hw_q_stats, hw_q,
+				      FBNIC_HW_Q_STATS_LEN, &data);
 	}
+	spin_unlock(&fbd->hw_stats_lock);
 }
 
 static int fbnic_get_sset_count(struct net_device *dev, int sset)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 88db3dacb940..e2368075ab8c 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -17,11 +17,29 @@ static void __fbnic_mbx_wr_desc(struct fbnic_dev *fbd, int mbx_idx,
 {
 	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
 
+	/* Write the upper 32b and then the lower 32b. Doing this the
+	 * FW can then read lower, upper, lower to verify that the state
+	 * of the descriptor wasn't changed mid-transaction.
+	 */
 	fw_wr32(fbd, desc_offset + 1, upper_32_bits(desc));
 	fw_wrfl(fbd);
 	fw_wr32(fbd, desc_offset, lower_32_bits(desc));
 }
 
+static void __fbnic_mbx_invalidate_desc(struct fbnic_dev *fbd, int mbx_idx,
+					int desc_idx, u32 desc)
+{
+	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
+
+	/* For initialization we write the lower 32b of the descriptor first.
+	 * This way we can set the state to mark it invalid before we clear the
+	 * upper 32b.
+	 */
+	fw_wr32(fbd, desc_offset, desc);
+	fw_wrfl(fbd);
+	fw_wr32(fbd, desc_offset + 1, 0);
+}
+
 static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
 {
 	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
@@ -33,29 +51,41 @@ static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
 	return desc;
 }
 
-static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_reset_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	int desc_idx;
 
+	/* Disable DMA transactions from the device,
+	 * and flush any transactions triggered during cleaning
+	 */
+	switch (mbx_idx) {
+	case FBNIC_IPC_MBX_RX_IDX:
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH);
+		break;
+	case FBNIC_IPC_MBX_TX_IDX:
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH);
+		break;
+	}
+
+	wrfl(fbd);
+
 	/* Initialize first descriptor to all 0s. Doing this gives us a
 	 * solid stop for the firmware to hit when it is done looping
 	 * through the ring.
 	 */
-	__fbnic_mbx_wr_desc(fbd, mbx_idx, 0, 0);
-
-	fw_wrfl(fbd);
+	__fbnic_mbx_invalidate_desc(fbd, mbx_idx, 0, 0);
 
 	/* We then fill the rest of the ring starting at the end and moving
 	 * back toward descriptor 0 with skip descriptors that have no
 	 * length nor address, and tell the firmware that they can skip
 	 * them and just move past them to the one we initialized to 0.
 	 */
-	for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;) {
-		__fbnic_mbx_wr_desc(fbd, mbx_idx, desc_idx,
-				    FBNIC_IPC_MBX_DESC_FW_CMPL |
-				    FBNIC_IPC_MBX_DESC_HOST_CMPL);
-		fw_wrfl(fbd);
-	}
+	for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;)
+		__fbnic_mbx_invalidate_desc(fbd, mbx_idx, desc_idx,
+					    FBNIC_IPC_MBX_DESC_FW_CMPL |
+					    FBNIC_IPC_MBX_DESC_HOST_CMPL);
 }
 
 void fbnic_mbx_init(struct fbnic_dev *fbd)
@@ -76,7 +106,7 @@ void fbnic_mbx_init(struct fbnic_dev *fbd)
 	wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
 	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
-		fbnic_mbx_init_desc_ring(fbd, i);
+		fbnic_mbx_reset_desc_ring(fbd, i);
 }
 
 static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
@@ -141,7 +171,7 @@ static void fbnic_mbx_clean_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	int i;
 
-	fbnic_mbx_init_desc_ring(fbd, mbx_idx);
+	fbnic_mbx_reset_desc_ring(fbd, mbx_idx);
 
 	for (i = FBNIC_IPC_MBX_DESC_LEN; i--;)
 		fbnic_mbx_unmap_and_free_msg(fbd, mbx_idx, i);
@@ -207,6 +237,44 @@ static int fbnic_mbx_map_tlv_msg(struct fbnic_dev *fbd,
 	return err;
 }
 
+static int fbnic_mbx_set_cmpl_slot(struct fbnic_dev *fbd,
+				   struct fbnic_fw_completion *cmpl_data)
+{
+	struct fbnic_fw_mbx *tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
+	int free = -EXFULL;
+	int i;
+
+	if (!tx_mbx->ready)
+		return -ENODEV;
+
+	for (i = 0; i < FBNIC_MBX_CMPL_SLOTS; i++) {
+		if (!fbd->cmpl_data[i])
+			free = i;
+		else if (fbd->cmpl_data[i]->msg_type == cmpl_data->msg_type)
+			return -EEXIST;
+	}
+
+	if (free == -EXFULL)
+		return -EXFULL;
+
+	fbd->cmpl_data[free] = cmpl_data;
+
+	return 0;
+}
+
+static void fbnic_mbx_clear_cmpl_slot(struct fbnic_dev *fbd,
+				      struct fbnic_fw_completion *cmpl_data)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_MBX_CMPL_SLOTS; i++) {
+		if (fbd->cmpl_data[i] == cmpl_data) {
+			fbd->cmpl_data[i] = NULL;
+			break;
+		}
+	}
+}
+
 static void fbnic_mbx_process_tx_msgs(struct fbnic_dev *fbd)
 {
 	struct fbnic_fw_mbx *tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
@@ -228,6 +296,19 @@ static void fbnic_mbx_process_tx_msgs(struct fbnic_dev *fbd)
 	tx_mbx->head = head;
 }
 
+int fbnic_mbx_set_cmpl(struct fbnic_dev *fbd,
+		       struct fbnic_fw_completion *cmpl_data)
+{
+	unsigned long flags;
+	int err;
+
+	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
+	err = fbnic_mbx_set_cmpl_slot(fbd, cmpl_data);
+	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
+
+	return err;
+}
+
 static int fbnic_mbx_map_req_w_cmpl(struct fbnic_dev *fbd,
 				    struct fbnic_tlv_msg *msg,
 				    struct fbnic_fw_completion *cmpl_data)
@@ -236,23 +317,20 @@ static int fbnic_mbx_map_req_w_cmpl(struct fbnic_dev *fbd,
 	int err;
 
 	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
-
-	/* If we are already waiting on a completion then abort */
-	if (cmpl_data && fbd->cmpl_data) {
-		err = -EBUSY;
-		goto unlock_mbx;
+	if (cmpl_data) {
+		err = fbnic_mbx_set_cmpl_slot(fbd, cmpl_data);
+		if (err)
+			goto unlock_mbx;
 	}
 
-	/* Record completion location and submit request */
-	if (cmpl_data)
-		fbd->cmpl_data = cmpl_data;
-
 	err = fbnic_mbx_map_msg(fbd, FBNIC_IPC_MBX_TX_IDX, msg,
 				le16_to_cpu(msg->hdr.len) * sizeof(u32), 1);
 
-	/* If msg failed then clear completion data for next caller */
+	/* If we successfully reserved a completion and msg failed
+	 * then clear completion data for next caller
+	 */
 	if (err && cmpl_data)
-		fbd->cmpl_data = NULL;
+		fbnic_mbx_clear_cmpl_slot(fbd, cmpl_data);
 
 unlock_mbx:
 	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
@@ -274,12 +352,18 @@ fbnic_fw_get_cmpl_by_type(struct fbnic_dev *fbd, u32 msg_type)
 {
 	struct fbnic_fw_completion *cmpl_data = NULL;
 	unsigned long flags;
+	int i;
 
 	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
-	if (fbd->cmpl_data && fbd->cmpl_data->msg_type == msg_type) {
-		cmpl_data = fbd->cmpl_data;
-		kref_get(&fbd->cmpl_data->ref_count);
+	for (i = 0; i < FBNIC_MBX_CMPL_SLOTS; i++) {
+		if (fbd->cmpl_data[i] &&
+		    fbd->cmpl_data[i]->msg_type == msg_type) {
+			cmpl_data = fbd->cmpl_data[i];
+			kref_get(&cmpl_data->ref_count);
+			break;
+		}
 	}
+
 	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
 
 	return cmpl_data;
@@ -322,67 +406,41 @@ static int fbnic_fw_xmit_simple_msg(struct fbnic_dev *fbd, u32 msg_type)
 	return err;
 }
 
-/**
- * fbnic_fw_xmit_cap_msg - Allocate and populate a FW capabilities message
- * @fbd: FBNIC device structure
- *
- * Return: NULL on failure to allocate, error pointer on error, or pointer
- * to new TLV test message.
- *
- * Sends a single TLV header indicating the host wants the firmware to
- * confirm the capabilities and version.
- **/
-static int fbnic_fw_xmit_cap_msg(struct fbnic_dev *fbd)
-{
-	int err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
-
-	/* Return 0 if we are not calling this on ASIC */
-	return (err == -EOPNOTSUPP) ? 0 : err;
-}
-
-static void fbnic_mbx_postinit_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	struct fbnic_fw_mbx *mbx = &fbd->mbx[mbx_idx];
 
-	/* This is a one time init, so just exit if it is completed */
-	if (mbx->ready)
-		return;
-
 	mbx->ready = true;
 
 	switch (mbx_idx) {
 	case FBNIC_IPC_MBX_RX_IDX:
+		/* Enable DMA writes from the device */
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
+
 		/* Make sure we have a page for the FW to write to */
 		fbnic_mbx_alloc_rx_msgs(fbd);
 		break;
 	case FBNIC_IPC_MBX_TX_IDX:
-		/* Force version to 1 if we successfully requested an update
-		 * from the firmware. This should be overwritten once we get
-		 * the actual version from the firmware in the capabilities
-		 * request message.
-		 */
-		if (!fbnic_fw_xmit_cap_msg(fbd) &&
-		    !fbd->fw_cap.running.mgmt.version)
-			fbd->fw_cap.running.mgmt.version = 1;
+		/* Enable DMA reads from the device */
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
 		break;
 	}
 }
 
-static void fbnic_mbx_postinit(struct fbnic_dev *fbd)
+static bool fbnic_mbx_event(struct fbnic_dev *fbd)
 {
-	int i;
-
-	/* We only need to do this on the first interrupt following init.
+	/* We only need to do this on the first interrupt following reset.
 	 * this primes the mailbox so that we will have cleared all the
 	 * skip descriptors.
 	 */
 	if (!(rd32(fbd, FBNIC_INTR_STATUS(0)) & (1u << FBNIC_FW_MSIX_ENTRY)))
-		return;
+		return false;
 
 	wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
-	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
-		fbnic_mbx_postinit_desc_ring(fbd, i);
+	return true;
 }
 
 /**
@@ -460,6 +518,7 @@ static const struct fbnic_tlv_index fbnic_fw_cap_resp_index[] = {
 	FBNIC_TLV_ATTR_U32(FBNIC_FW_CAP_RESP_UEFI_VERSION),
 	FBNIC_TLV_ATTR_STRING(FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR,
 			      FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_CAP_RESP_ANTI_ROLLBACK_VERSION),
 	FBNIC_TLV_ATTR_LAST
 };
 
@@ -582,6 +641,9 @@ static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 	if (results[FBNIC_FW_CAP_RESP_BMC_ALL_MULTI] || !bmc_present)
 		fbd->fw_cap.all_multi = all_multi;
 
+	fbd->fw_cap.anti_rollback_version =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_ANTI_ROLLBACK_VERSION);
+
 	return 0;
 }
 
@@ -704,6 +766,188 @@ void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd)
 		dev_warn(fbd->dev, "Failed to send heartbeat message\n");
 }
 
+int fbnic_fw_xmit_fw_start_upgrade(struct fbnic_dev *fbd,
+				   struct fbnic_fw_completion *cmpl_data,
+				   unsigned int id, unsigned int len)
+{
+	struct fbnic_tlv_msg *msg;
+	int err;
+
+	if (!fbnic_fw_present(fbd))
+		return -ENODEV;
+
+	if (!len)
+		return -EINVAL;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ);
+	if (!msg)
+		return -ENOMEM;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_START_UPGRADE_SECTION, id);
+	if (err)
+		goto free_message;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_START_UPGRADE_IMAGE_LENGTH,
+				     len);
+	if (err)
+		goto free_message;
+
+	err = fbnic_mbx_map_req_w_cmpl(fbd, msg, cmpl_data);
+	if (err)
+		goto free_message;
+
+	return 0;
+
+free_message:
+	free_page((unsigned long)msg);
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_fw_start_upgrade_resp_index[] = {
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_START_UPGRADE_ERROR),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_fw_start_upgrade_resp(void *opaque,
+						struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	u32 msg_type;
+	s32 err;
+
+	/* Verify we have a completion pointer */
+	msg_type = FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ;
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, msg_type);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	/* Check for errors */
+	err = fta_get_sint(results, FBNIC_FW_START_UPGRADE_ERROR);
+
+	cmpl_data->result = err;
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return 0;
+}
+
+int fbnic_fw_xmit_fw_write_chunk(struct fbnic_dev *fbd,
+				 const u8 *data, u32 offset, u16 length,
+				 int cancel_error)
+{
+	struct fbnic_tlv_msg *msg;
+	int err;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_RESP);
+	if (!msg)
+		return -ENOMEM;
+
+	/* Report error to FW to cancel upgrade */
+	if (cancel_error) {
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_WRITE_CHUNK_ERROR,
+					     cancel_error);
+		if (err)
+			goto free_message;
+	}
+
+	if (data) {
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_WRITE_CHUNK_OFFSET,
+					     offset);
+		if (err)
+			goto free_message;
+
+		err = fbnic_tlv_attr_put_int(msg, FBNIC_FW_WRITE_CHUNK_LENGTH,
+					     length);
+		if (err)
+			goto free_message;
+
+		err = fbnic_tlv_attr_put_value(msg, FBNIC_FW_WRITE_CHUNK_DATA,
+					       data + offset, length);
+		if (err)
+			goto free_message;
+	}
+
+	err = fbnic_mbx_map_tlv_msg(fbd, msg);
+	if (err)
+		goto free_message;
+
+	return 0;
+
+free_message:
+	free_page((unsigned long)msg);
+	return err;
+}
+
+static const struct fbnic_tlv_index fbnic_fw_write_chunk_req_index[] = {
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_WRITE_CHUNK_OFFSET),
+	FBNIC_TLV_ATTR_U32(FBNIC_FW_WRITE_CHUNK_LENGTH),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_fw_write_chunk_req(void *opaque,
+					     struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	u32 msg_type;
+	u32 offset;
+	u32 length;
+
+	/* Verify we have a completion pointer */
+	msg_type = FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ;
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, msg_type);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	/* Pull length/offset pair and mark it as complete */
+	offset = fta_get_uint(results, FBNIC_FW_WRITE_CHUNK_OFFSET);
+	length = fta_get_uint(results, FBNIC_FW_WRITE_CHUNK_LENGTH);
+	cmpl_data->u.fw_update.offset = offset;
+	cmpl_data->u.fw_update.length = length;
+
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return 0;
+}
+
+static const struct fbnic_tlv_index fbnic_fw_finish_upgrade_req_index[] = {
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_FINISH_UPGRADE_ERROR),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_fw_finish_upgrade_req(void *opaque,
+						struct fbnic_tlv_msg **results)
+{
+	struct fbnic_fw_completion *cmpl_data;
+	struct fbnic_dev *fbd = opaque;
+	u32 msg_type;
+	s32 err;
+
+	/* Verify we have a completion pointer */
+	msg_type = FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ;
+	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, msg_type);
+	if (!cmpl_data)
+		return -ENOSPC;
+
+	/* Check for errors */
+	err = fta_get_sint(results, FBNIC_FW_FINISH_UPGRADE_ERROR);
+
+	/* Close out update by incrementing offset by length which should
+	 * match the total size of the component. Set length to 0 since no
+	 * new chunks will be requested.
+	 */
+	cmpl_data->u.fw_update.offset += cmpl_data->u.fw_update.length;
+	cmpl_data->u.fw_update.length = 0;
+
+	cmpl_data->result = err;
+	complete(&cmpl_data->done);
+	fbnic_fw_put_cmpl(cmpl_data);
+
+	return 0;
+}
+
 /**
  * fbnic_fw_xmit_tsene_read_msg - Create and transmit a sensor read request
  * @fbd: FBNIC device structure
@@ -788,6 +1032,15 @@ static const struct fbnic_tlv_parser fbnic_fw_tlv_parser[] = {
 			 fbnic_fw_parse_ownership_resp),
 	FBNIC_TLV_PARSER(HEARTBEAT_RESP, fbnic_heartbeat_resp_index,
 			 fbnic_fw_parse_heartbeat_resp),
+	FBNIC_TLV_PARSER(FW_START_UPGRADE_RESP,
+			 fbnic_fw_start_upgrade_resp_index,
+			 fbnic_fw_parse_fw_start_upgrade_resp),
+	FBNIC_TLV_PARSER(FW_WRITE_CHUNK_REQ,
+			 fbnic_fw_write_chunk_req_index,
+			 fbnic_fw_parse_fw_write_chunk_req),
+	FBNIC_TLV_PARSER(FW_FINISH_UPGRADE_REQ,
+			 fbnic_fw_finish_upgrade_req_index,
+			 fbnic_fw_parse_fw_finish_upgrade_req),
 	FBNIC_TLV_PARSER(TSENE_READ_RESP,
 			 fbnic_tsene_read_resp_index,
 			 fbnic_fw_parse_tsene_read_resp),
@@ -859,7 +1112,7 @@ next_page:
 
 void fbnic_mbx_poll(struct fbnic_dev *fbd)
 {
-	fbnic_mbx_postinit(fbd);
+	fbnic_mbx_event(fbd);
 
 	fbnic_mbx_process_tx_msgs(fbd);
 	fbnic_mbx_process_rx_msgs(fbd);
@@ -867,60 +1120,103 @@ void fbnic_mbx_poll(struct fbnic_dev *fbd)
 
 int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 {
-	struct fbnic_fw_mbx *tx_mbx;
-	int attempts = 50;
+	unsigned long timeout = jiffies + 10 * HZ + 1;
+	int err, i;
 
-	/* Immediate fail if BAR4 isn't there */
-	if (!fbnic_fw_present(fbd))
-		return -ENODEV;
+	do {
+		if (!time_is_after_jiffies(timeout))
+			return -ETIMEDOUT;
 
-	tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
-	while (!tx_mbx->ready && --attempts) {
 		/* Force the firmware to trigger an interrupt response to
 		 * avoid the mailbox getting stuck closed if the interrupt
 		 * is reset.
 		 */
-		fbnic_mbx_init_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
+		fbnic_mbx_reset_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
 
-		msleep(200);
+		/* Immediate fail if BAR4 went away */
+		if (!fbnic_fw_present(fbd))
+			return -ENODEV;
+
+		msleep(20);
+	} while (!fbnic_mbx_event(fbd));
 
-		fbnic_mbx_poll(fbd);
+	/* FW has shown signs of life. Enable DMA and start Tx/Rx */
+	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
+		fbnic_mbx_init_desc_ring(fbd, i);
+
+	/* Request an update from the firmware. This should overwrite
+	 * mgmt.version once we get the actual version from the firmware
+	 * in the capabilities request message.
+	 */
+	err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
+	if (err)
+		goto clean_mbx;
+
+	/* Use "1" to indicate we entered the state waiting for a response */
+	fbd->fw_cap.running.mgmt.version = 1;
+
+	return 0;
+clean_mbx:
+	/* Cleanup Rx buffers and disable mailbox */
+	fbnic_mbx_clean(fbd);
+	return err;
+}
+
+static void __fbnic_fw_evict_cmpl(struct fbnic_fw_completion *cmpl_data)
+{
+	cmpl_data->result = -EPIPE;
+	complete(&cmpl_data->done);
+}
+
+static void fbnic_mbx_evict_all_cmpl(struct fbnic_dev *fbd)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_MBX_CMPL_SLOTS; i++) {
+		struct fbnic_fw_completion *cmpl_data = fbd->cmpl_data[i];
+
+		if (cmpl_data)
+			__fbnic_fw_evict_cmpl(cmpl_data);
 	}
 
-	return attempts ? 0 : -ETIMEDOUT;
+	memset(fbd->cmpl_data, 0, sizeof(fbd->cmpl_data));
 }
 
 void fbnic_mbx_flush_tx(struct fbnic_dev *fbd)
 {
+	unsigned long timeout = jiffies + 10 * HZ + 1;
 	struct fbnic_fw_mbx *tx_mbx;
-	int attempts = 50;
-	u8 count = 0;
-
-	/* Nothing to do if there is no mailbox */
-	if (!fbnic_fw_present(fbd))
-		return;
+	u8 tail;
 
 	/* Record current Rx stats */
 	tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
 
-	/* Nothing to do if mailbox never got to ready */
-	if (!tx_mbx->ready)
-		return;
+	spin_lock_irq(&fbd->fw_tx_lock);
+
+	/* Clear ready to prevent any further attempts to transmit */
+	tx_mbx->ready = false;
+
+	/* Read tail to determine the last tail state for the ring */
+	tail = tx_mbx->tail;
+
+	/* Flush any completions as we are no longer processing Rx */
+	fbnic_mbx_evict_all_cmpl(fbd);
+
+	spin_unlock_irq(&fbd->fw_tx_lock);
 
 	/* Give firmware time to process packet,
-	 * we will wait up to 10 seconds which is 50 waits of 200ms.
+	 * we will wait up to 10 seconds which is 500 waits of 20ms.
 	 */
 	do {
 		u8 head = tx_mbx->head;
 
-		if (head == tx_mbx->tail)
+		/* Tx ring is empty once head == tail */
+		if (head == tail)
 			break;
 
-		msleep(200);
+		msleep(20);
 		fbnic_mbx_process_tx_msgs(fbd);
-
-		count += (tx_mbx->head - head) % FBNIC_IPC_MBX_DESC_LEN;
-	} while (count < FBNIC_IPC_MBX_DESC_LEN && --attempts);
+	} while (time_is_after_jiffies(timeout));
 }
 
 void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version,
@@ -936,20 +1232,28 @@ void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version,
 				 fw_version, str_sz);
 }
 
-void fbnic_fw_init_cmpl(struct fbnic_fw_completion *fw_cmpl,
-			u32 msg_type)
+struct fbnic_fw_completion *fbnic_fw_alloc_cmpl(u32 msg_type)
 {
-	fw_cmpl->msg_type = msg_type;
-	init_completion(&fw_cmpl->done);
-	kref_init(&fw_cmpl->ref_count);
+	struct fbnic_fw_completion *cmpl;
+
+	cmpl = kzalloc(sizeof(*cmpl), GFP_KERNEL);
+	if (!cmpl)
+		return NULL;
+
+	cmpl->msg_type = msg_type;
+	init_completion(&cmpl->done);
+	kref_init(&cmpl->ref_count);
+
+	return cmpl;
 }
 
-void fbnic_fw_clear_compl(struct fbnic_dev *fbd)
+void fbnic_fw_clear_cmpl(struct fbnic_dev *fbd,
+			 struct fbnic_fw_completion *fw_cmpl)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&fbd->fw_tx_lock, flags);
-	fbd->cmpl_data = NULL;
+	fbnic_mbx_clear_cmpl_slot(fbd, fw_cmpl);
 	spin_unlock_irqrestore(&fbd->fw_tx_lock, flags);
 }
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
index a3618e7826c2..08bc4b918de7 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
@@ -42,6 +42,7 @@ struct fbnic_fw_cap {
 	u8	all_multi	: 1;
 	u8	link_speed;
 	u8	link_fec;
+	u32	anti_rollback_version;
 };
 
 struct fbnic_fw_completion {
@@ -51,6 +52,10 @@ struct fbnic_fw_completion {
 	int result;
 	union {
 		struct {
+			u32 offset;
+			u32 length;
+		} fw_update;
+		struct {
 			s32 millivolts;
 			s32 millidegrees;
 		} tsene;
@@ -59,17 +64,25 @@ struct fbnic_fw_completion {
 
 void fbnic_mbx_init(struct fbnic_dev *fbd);
 void fbnic_mbx_clean(struct fbnic_dev *fbd);
+int fbnic_mbx_set_cmpl(struct fbnic_dev *fbd,
+		       struct fbnic_fw_completion *cmpl_data);
 void fbnic_mbx_poll(struct fbnic_dev *fbd);
 int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd);
 void fbnic_mbx_flush_tx(struct fbnic_dev *fbd);
 int fbnic_fw_xmit_ownership_msg(struct fbnic_dev *fbd, bool take_ownership);
 int fbnic_fw_init_heartbeat(struct fbnic_dev *fbd, bool poll);
 void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd);
+int fbnic_fw_xmit_fw_start_upgrade(struct fbnic_dev *fbd,
+				   struct fbnic_fw_completion *cmpl_data,
+				   unsigned int id, unsigned int len);
+int fbnic_fw_xmit_fw_write_chunk(struct fbnic_dev *fbd,
+				 const u8 *data, u32 offset, u16 length,
+				 int cancel_error);
 int fbnic_fw_xmit_tsene_read_msg(struct fbnic_dev *fbd,
 				 struct fbnic_fw_completion *cmpl_data);
-void fbnic_fw_init_cmpl(struct fbnic_fw_completion *cmpl_data,
-			u32 msg_type);
-void fbnic_fw_clear_compl(struct fbnic_dev *fbd);
+struct fbnic_fw_completion *fbnic_fw_alloc_cmpl(u32 msg_type);
+void fbnic_fw_clear_cmpl(struct fbnic_dev *fbd,
+			 struct fbnic_fw_completion *cmpl_data);
 void fbnic_fw_put_cmpl(struct fbnic_fw_completion *cmpl_data);
 
 #define fbnic_mk_full_fw_ver_str(_rev_id, _delim, _commit, _str, _str_sz) \
@@ -86,6 +99,15 @@ do {									\
 #define fbnic_mk_fw_ver_str(_rev_id, _str) \
 	fbnic_mk_full_fw_ver_str(_rev_id, "", "", _str, sizeof(_str))
 
+enum {
+	QSPI_SECTION_CMRT			= 0,
+	QSPI_SECTION_CONTROL_FW			= 1,
+	QSPI_SECTION_UCODE			= 2,
+	QSPI_SECTION_OPTION_ROM			= 3,
+	QSPI_SECTION_USER			= 4,
+	QSPI_SECTION_INVALID,
+};
+
 #define FW_HEARTBEAT_PERIOD		(10 * HZ)
 
 enum {
@@ -95,6 +117,12 @@ enum {
 	FBNIC_TLV_MSG_ID_OWNERSHIP_RESP			= 0x13,
 	FBNIC_TLV_MSG_ID_HEARTBEAT_REQ			= 0x14,
 	FBNIC_TLV_MSG_ID_HEARTBEAT_RESP			= 0x15,
+	FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ		= 0x22,
+	FBNIC_TLV_MSG_ID_FW_START_UPGRADE_RESP		= 0x23,
+	FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ		= 0x24,
+	FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_RESP		= 0x25,
+	FBNIC_TLV_MSG_ID_FW_FINISH_UPGRADE_REQ		= 0x28,
+	FBNIC_TLV_MSG_ID_FW_FINISH_UPGRADE_RESP		= 0x29,
 	FBNIC_TLV_MSG_ID_TSENE_READ_REQ			= 0x3C,
 	FBNIC_TLV_MSG_ID_TSENE_READ_RESP		= 0x3D,
 };
@@ -122,6 +150,7 @@ enum {
 	FBNIC_FW_CAP_RESP_STORED_CMRT_COMMIT_STR	= 0x10,
 	FBNIC_FW_CAP_RESP_UEFI_VERSION			= 0x11,
 	FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR		= 0x12,
+	FBNIC_FW_CAP_RESP_ANTI_ROLLBACK_VERSION		= 0x15,
 	FBNIC_FW_CAP_RESP_MSG_MAX
 };
 
@@ -149,4 +178,25 @@ enum {
 	FBNIC_FW_OWNERSHIP_FLAG			= 0x0,
 	FBNIC_FW_OWNERSHIP_MSG_MAX
 };
+
+enum {
+	FBNIC_FW_START_UPGRADE_ERROR		= 0x0,
+	FBNIC_FW_START_UPGRADE_SECTION		= 0x1,
+	FBNIC_FW_START_UPGRADE_IMAGE_LENGTH	= 0x2,
+	FBNIC_FW_START_UPGRADE_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_WRITE_CHUNK_OFFSET		= 0x0,
+	FBNIC_FW_WRITE_CHUNK_LENGTH		= 0x1,
+	FBNIC_FW_WRITE_CHUNK_DATA		= 0x2,
+	FBNIC_FW_WRITE_CHUNK_ERROR		= 0x3,
+	FBNIC_FW_WRITE_CHUNK_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_FINISH_UPGRADE_ERROR		= 0x0,
+	FBNIC_FW_FINISH_UPGRADE_MSG_MAX
+};
+
 #endif /* _FBNIC_FW_H_ */
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c
index 89ac6bc8c7fc..4223d8100e64 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c
@@ -70,6 +70,100 @@ static void fbnic_hw_stat_rd64(struct fbnic_dev *fbd, u32 reg, s32 offset,
 	stat->u.old_reg_value_64 = new_reg_value;
 }
 
+static void fbnic_reset_tmi_stats(struct fbnic_dev *fbd,
+				  struct fbnic_tmi_stats *tmi)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_TMI_DROP_PKTS, &tmi->drop.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_TMI_DROP_BYTE_L, 1, &tmi->drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TMI_ILLEGAL_PTP_REQS,
+			    &tmi->ptp_illegal_req);
+	fbnic_hw_stat_rst32(fbd, FBNIC_TMI_GOOD_PTP_TS, &tmi->ptp_good_ts);
+	fbnic_hw_stat_rst32(fbd, FBNIC_TMI_BAD_PTP_TS, &tmi->ptp_bad_ts);
+}
+
+static void fbnic_get_tmi_stats32(struct fbnic_dev *fbd,
+				  struct fbnic_tmi_stats *tmi)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_TMI_DROP_PKTS, &tmi->drop.frames);
+
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TMI_ILLEGAL_PTP_REQS,
+			   &tmi->ptp_illegal_req);
+	fbnic_hw_stat_rd32(fbd, FBNIC_TMI_GOOD_PTP_TS, &tmi->ptp_good_ts);
+	fbnic_hw_stat_rd32(fbd, FBNIC_TMI_BAD_PTP_TS, &tmi->ptp_bad_ts);
+}
+
+static void fbnic_get_tmi_stats(struct fbnic_dev *fbd,
+				struct fbnic_tmi_stats *tmi)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_TMI_DROP_BYTE_L, 1, &tmi->drop.bytes);
+}
+
+static void fbnic_reset_tti_stats(struct fbnic_dev *fbd,
+				  struct fbnic_tti_stats *tti)
+{
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TCE_TTI_CM_DROP_PKTS,
+			    &tti->cm_drop.frames);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_TCE_TTI_CM_DROP_BYTE_L,
+			    1,
+			    &tti->cm_drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TCE_TTI_FRAME_DROP_PKTS,
+			    &tti->frame_drop.frames);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_TCE_TTI_FRAME_DROP_BYTE_L,
+			    1,
+			    &tti->frame_drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TCE_TBI_DROP_PKTS,
+			    &tti->tbi_drop.frames);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_TCE_TBI_DROP_BYTE_L,
+			    1,
+			    &tti->tbi_drop.bytes);
+}
+
+static void fbnic_get_tti_stats32(struct fbnic_dev *fbd,
+				  struct fbnic_tti_stats *tti)
+{
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TCE_TTI_CM_DROP_PKTS,
+			   &tti->cm_drop.frames);
+
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TCE_TTI_FRAME_DROP_PKTS,
+			   &tti->frame_drop.frames);
+
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TCE_TBI_DROP_PKTS,
+			   &tti->tbi_drop.frames);
+}
+
+static void fbnic_get_tti_stats(struct fbnic_dev *fbd,
+				struct fbnic_tti_stats *tti)
+{
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_TCE_TTI_CM_DROP_BYTE_L,
+			   1,
+			   &tti->cm_drop.bytes);
+
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_TCE_TTI_FRAME_DROP_BYTE_L,
+			   1,
+			   &tti->frame_drop.bytes);
+
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_TCE_TBI_DROP_BYTE_L,
+			   1,
+			   &tti->tbi_drop.bytes);
+}
+
 static void fbnic_reset_rpc_stats(struct fbnic_dev *fbd,
 				  struct fbnic_rpc_stats *rpc)
 {
@@ -117,6 +211,221 @@ static void fbnic_get_rpc_stats32(struct fbnic_dev *fbd,
 			   &rpc->ovr_size_err);
 }
 
+static void fbnic_reset_rxb_fifo_stats(struct fbnic_dev *fbd, int i,
+				       struct fbnic_rxb_fifo_stats *fifo)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_DROP_FRMS_STS(i),
+			    &fifo->drop.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_DROP_BYTES_STS_L(i), 1,
+			    &fifo->drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_TRUN_FRMS_STS(i),
+			    &fifo->trunc.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_TRUN_BYTES_STS_L(i), 1,
+			    &fifo->trunc.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_TRANS_DROP_STS(i),
+			    &fifo->trans_drop);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_TRANS_ECN_STS(i),
+			    &fifo->trans_ecn);
+
+	fifo->level.u.old_reg_value_32 = 0;
+}
+
+static void fbnic_reset_rxb_enq_stats(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_enqueue_stats *enq)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_DRBO_FRM_CNT_SRC(i),
+			    &enq->drbo.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_DRBO_BYTE_CNT_SRC_L(i), 4,
+			    &enq->drbo.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_INTEGRITY_ERR(i),
+			    &enq->integrity_err);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_MAC_ERR(i),
+			    &enq->mac_err);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_PARSER_ERR(i),
+			    &enq->parser_err);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_FRM_ERR(i),
+			    &enq->frm_err);
+}
+
+static void fbnic_reset_rxb_deq_stats(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_dequeue_stats *deq)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_INTF_FRM_CNT_DST(i),
+			    &deq->intf.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_INTF_BYTE_CNT_DST_L(i), 4,
+			    &deq->intf.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_PBUF_FRM_CNT_DST(i),
+			    &deq->pbuf.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_PBUF_BYTE_CNT_DST_L(i), 4,
+			    &deq->pbuf.bytes);
+}
+
+static void fbnic_reset_rxb_stats(struct fbnic_dev *fbd,
+				  struct fbnic_rxb_stats *rxb)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+		fbnic_reset_rxb_fifo_stats(fbd, i, &rxb->fifo[i]);
+
+	for (i = 0; i < FBNIC_RXB_INTF_INDICES; i++) {
+		fbnic_reset_rxb_enq_stats(fbd, i, &rxb->enq[i]);
+		fbnic_reset_rxb_deq_stats(fbd, i, &rxb->deq[i]);
+	}
+}
+
+static void fbnic_get_rxb_fifo_stats32(struct fbnic_dev *fbd, int i,
+				       struct fbnic_rxb_fifo_stats *fifo)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_DROP_FRMS_STS(i),
+			   &fifo->drop.frames);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_TRUN_FRMS_STS(i),
+			   &fifo->trunc.frames);
+
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_TRANS_DROP_STS(i),
+			   &fifo->trans_drop);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_TRANS_ECN_STS(i),
+			   &fifo->trans_ecn);
+
+	fifo->level.value = rd32(fbd, FBNIC_RXB_PBUF_FIFO_LEVEL(i));
+}
+
+static void fbnic_get_rxb_fifo_stats(struct fbnic_dev *fbd, int i,
+				     struct fbnic_rxb_fifo_stats *fifo)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_DROP_BYTES_STS_L(i), 1,
+			   &fifo->drop.bytes);
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_TRUN_BYTES_STS_L(i), 1,
+			   &fifo->trunc.bytes);
+
+	fbnic_get_rxb_fifo_stats32(fbd, i, fifo);
+}
+
+static void fbnic_get_rxb_enq_stats32(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_enqueue_stats *enq)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_DRBO_FRM_CNT_SRC(i),
+			   &enq->drbo.frames);
+
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_INTEGRITY_ERR(i),
+			   &enq->integrity_err);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_MAC_ERR(i),
+			   &enq->mac_err);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_PARSER_ERR(i),
+			   &enq->parser_err);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_FRM_ERR(i),
+			   &enq->frm_err);
+}
+
+static void fbnic_get_rxb_enq_stats(struct fbnic_dev *fbd, int i,
+				    struct fbnic_rxb_enqueue_stats *enq)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_DRBO_BYTE_CNT_SRC_L(i), 4,
+			   &enq->drbo.bytes);
+
+	fbnic_get_rxb_enq_stats32(fbd, i, enq);
+}
+
+static void fbnic_get_rxb_deq_stats32(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_dequeue_stats *deq)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_INTF_FRM_CNT_DST(i),
+			   &deq->intf.frames);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_PBUF_FRM_CNT_DST(i),
+			   &deq->pbuf.frames);
+}
+
+static void fbnic_get_rxb_deq_stats(struct fbnic_dev *fbd, int i,
+				    struct fbnic_rxb_dequeue_stats *deq)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_INTF_BYTE_CNT_DST_L(i), 4,
+			   &deq->intf.bytes);
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_PBUF_BYTE_CNT_DST_L(i), 4,
+			   &deq->pbuf.bytes);
+
+	fbnic_get_rxb_deq_stats32(fbd, i, deq);
+}
+
+static void fbnic_get_rxb_stats32(struct fbnic_dev *fbd,
+				  struct fbnic_rxb_stats *rxb)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+		fbnic_get_rxb_fifo_stats32(fbd, i, &rxb->fifo[i]);
+
+	for (i = 0; i < FBNIC_RXB_INTF_INDICES; i++) {
+		fbnic_get_rxb_enq_stats32(fbd, i, &rxb->enq[i]);
+		fbnic_get_rxb_deq_stats32(fbd, i, &rxb->deq[i]);
+	}
+}
+
+static void fbnic_get_rxb_stats(struct fbnic_dev *fbd,
+				struct fbnic_rxb_stats *rxb)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+		fbnic_get_rxb_fifo_stats(fbd, i, &rxb->fifo[i]);
+
+	for (i = 0; i < FBNIC_RXB_INTF_INDICES; i++) {
+		fbnic_get_rxb_enq_stats(fbd, i, &rxb->enq[i]);
+		fbnic_get_rxb_deq_stats(fbd, i, &rxb->deq[i]);
+	}
+}
+
+static void fbnic_reset_hw_rxq_stats(struct fbnic_dev *fbd,
+				     struct fbnic_hw_q_stats *hw_q)
+{
+	int i;
+
+	for (i = 0; i < fbd->max_num_queues; i++, hw_q++) {
+		u32 base = FBNIC_QUEUE(i);
+
+		fbnic_hw_stat_rst32(fbd,
+				    base + FBNIC_QUEUE_RDE_PKT_ERR_CNT,
+				    &hw_q->rde_pkt_err);
+		fbnic_hw_stat_rst32(fbd,
+				    base + FBNIC_QUEUE_RDE_CQ_DROP_CNT,
+				    &hw_q->rde_pkt_cq_drop);
+		fbnic_hw_stat_rst32(fbd,
+				    base + FBNIC_QUEUE_RDE_BDQ_DROP_CNT,
+				    &hw_q->rde_pkt_bdq_drop);
+	}
+}
+
+static void fbnic_get_hw_rxq_stats32(struct fbnic_dev *fbd,
+				     struct fbnic_hw_q_stats *hw_q)
+{
+	int i;
+
+	for (i = 0; i < fbd->max_num_queues; i++, hw_q++) {
+		u32 base = FBNIC_QUEUE(i);
+
+		fbnic_hw_stat_rd32(fbd,
+				   base + FBNIC_QUEUE_RDE_PKT_ERR_CNT,
+				   &hw_q->rde_pkt_err);
+		fbnic_hw_stat_rd32(fbd,
+				   base + FBNIC_QUEUE_RDE_CQ_DROP_CNT,
+				   &hw_q->rde_pkt_cq_drop);
+		fbnic_hw_stat_rd32(fbd,
+				   base + FBNIC_QUEUE_RDE_BDQ_DROP_CNT,
+				   &hw_q->rde_pkt_bdq_drop);
+	}
+}
+
+void fbnic_get_hw_q_stats(struct fbnic_dev *fbd,
+			  struct fbnic_hw_q_stats *hw_q)
+{
+	spin_lock(&fbd->hw_stats_lock);
+	fbnic_get_hw_rxq_stats32(fbd, hw_q);
+	spin_unlock(&fbd->hw_stats_lock);
+}
+
 static void fbnic_reset_pcie_stats_asic(struct fbnic_dev *fbd,
 					struct fbnic_pcie_stats *pcie)
 {
@@ -203,18 +512,40 @@ static void fbnic_get_pcie_stats_asic64(struct fbnic_dev *fbd,
 
 void fbnic_reset_hw_stats(struct fbnic_dev *fbd)
 {
+	spin_lock(&fbd->hw_stats_lock);
+	fbnic_reset_tmi_stats(fbd, &fbd->hw_stats.tmi);
+	fbnic_reset_tti_stats(fbd, &fbd->hw_stats.tti);
 	fbnic_reset_rpc_stats(fbd, &fbd->hw_stats.rpc);
+	fbnic_reset_rxb_stats(fbd, &fbd->hw_stats.rxb);
+	fbnic_reset_hw_rxq_stats(fbd, fbd->hw_stats.hw_q);
 	fbnic_reset_pcie_stats_asic(fbd, &fbd->hw_stats.pcie);
+	spin_unlock(&fbd->hw_stats_lock);
 }
 
-void fbnic_get_hw_stats32(struct fbnic_dev *fbd)
+static void __fbnic_get_hw_stats32(struct fbnic_dev *fbd)
 {
+	fbnic_get_tmi_stats32(fbd, &fbd->hw_stats.tmi);
+	fbnic_get_tti_stats32(fbd, &fbd->hw_stats.tti);
 	fbnic_get_rpc_stats32(fbd, &fbd->hw_stats.rpc);
+	fbnic_get_rxb_stats32(fbd, &fbd->hw_stats.rxb);
+	fbnic_get_hw_rxq_stats32(fbd, fbd->hw_stats.hw_q);
+}
+
+void fbnic_get_hw_stats32(struct fbnic_dev *fbd)
+{
+	spin_lock(&fbd->hw_stats_lock);
+	__fbnic_get_hw_stats32(fbd);
+	spin_unlock(&fbd->hw_stats_lock);
 }
 
 void fbnic_get_hw_stats(struct fbnic_dev *fbd)
 {
-	fbnic_get_hw_stats32(fbd);
+	spin_lock(&fbd->hw_stats_lock);
+	__fbnic_get_hw_stats32(fbd);
 
+	fbnic_get_tmi_stats(fbd, &fbd->hw_stats.tmi);
+	fbnic_get_tti_stats(fbd, &fbd->hw_stats.tti);
+	fbnic_get_rxb_stats(fbd, &fbd->hw_stats.rxb);
 	fbnic_get_pcie_stats_asic64(fbd, &fbd->hw_stats.pcie);
+	spin_unlock(&fbd->hw_stats_lock);
 }
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h
index 78df56b87745..07e54bb75bf3 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h
@@ -17,6 +17,11 @@ struct fbnic_stat_counter {
 	bool reported;
 };
 
+struct fbnic_hw_stat {
+	struct fbnic_stat_counter frames;
+	struct fbnic_stat_counter bytes;
+};
+
 struct fbnic_eth_mac_stats {
 	struct fbnic_stat_counter FramesTransmittedOK;
 	struct fbnic_stat_counter FramesReceivedOK;
@@ -37,12 +42,49 @@ struct fbnic_mac_stats {
 	struct fbnic_eth_mac_stats eth_mac;
 };
 
+struct fbnic_tmi_stats {
+	struct fbnic_hw_stat drop;
+	struct fbnic_stat_counter ptp_illegal_req, ptp_good_ts, ptp_bad_ts;
+};
+
+struct fbnic_tti_stats {
+	struct fbnic_hw_stat cm_drop, frame_drop, tbi_drop;
+};
+
 struct fbnic_rpc_stats {
 	struct fbnic_stat_counter unkn_etype, unkn_ext_hdr;
 	struct fbnic_stat_counter ipv4_frag, ipv6_frag, ipv4_esp, ipv6_esp;
 	struct fbnic_stat_counter tcp_opt_err, out_of_hdr_err, ovr_size_err;
 };
 
+struct fbnic_rxb_enqueue_stats {
+	struct fbnic_hw_stat drbo;
+	struct fbnic_stat_counter integrity_err, mac_err;
+	struct fbnic_stat_counter parser_err, frm_err;
+};
+
+struct fbnic_rxb_fifo_stats {
+	struct fbnic_hw_stat drop, trunc;
+	struct fbnic_stat_counter trans_drop, trans_ecn;
+	struct fbnic_stat_counter level;
+};
+
+struct fbnic_rxb_dequeue_stats {
+	struct fbnic_hw_stat intf, pbuf;
+};
+
+struct fbnic_rxb_stats {
+	struct fbnic_rxb_enqueue_stats enq[FBNIC_RXB_ENQUEUE_INDICES];
+	struct fbnic_rxb_fifo_stats fifo[FBNIC_RXB_FIFO_INDICES];
+	struct fbnic_rxb_dequeue_stats deq[FBNIC_RXB_DEQUEUE_INDICES];
+};
+
+struct fbnic_hw_q_stats {
+	struct fbnic_stat_counter rde_pkt_err;
+	struct fbnic_stat_counter rde_pkt_cq_drop;
+	struct fbnic_stat_counter rde_pkt_bdq_drop;
+};
+
 struct fbnic_pcie_stats {
 	struct fbnic_stat_counter ob_rd_tlp, ob_rd_dword;
 	struct fbnic_stat_counter ob_wr_tlp, ob_wr_dword;
@@ -55,13 +97,19 @@ struct fbnic_pcie_stats {
 
 struct fbnic_hw_stats {
 	struct fbnic_mac_stats mac;
+	struct fbnic_tmi_stats tmi;
+	struct fbnic_tti_stats tti;
 	struct fbnic_rpc_stats rpc;
+	struct fbnic_rxb_stats rxb;
+	struct fbnic_hw_q_stats hw_q[FBNIC_MAX_QUEUES];
 	struct fbnic_pcie_stats pcie;
 };
 
 u64 fbnic_stat_rd64(struct fbnic_dev *fbd, u32 reg, u32 offset);
 
 void fbnic_reset_hw_stats(struct fbnic_dev *fbd);
+void fbnic_get_hw_q_stats(struct fbnic_dev *fbd,
+			  struct fbnic_hw_q_stats *hw_q);
 void fbnic_get_hw_stats32(struct fbnic_dev *fbd);
 void fbnic_get_hw_stats(struct fbnic_dev *fbd);
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
index 1bbc0e56f3a0..1c88a2bf3a7a 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
@@ -19,69 +19,105 @@ static irqreturn_t fbnic_fw_msix_intr(int __always_unused irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static int __fbnic_fw_enable_mbx(struct fbnic_dev *fbd, int vector)
+{
+	int err;
+
+	/* Initialize mailbox and attempt to poll it into ready state */
+	fbnic_mbx_init(fbd);
+	err = fbnic_mbx_poll_tx_ready(fbd);
+	if (err) {
+		dev_warn(fbd->dev, "FW mailbox did not enter ready state\n");
+		return err;
+	}
+
+	/* Enable interrupt and unmask the vector */
+	enable_irq(vector);
+	fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
+
+	return 0;
+}
+
 /**
- * fbnic_fw_enable_mbx - Configure and initialize Firmware Mailbox
+ * fbnic_fw_request_mbx - Configure and initialize Firmware Mailbox
  * @fbd: Pointer to device to initialize
  *
- * This function will initialize the firmware mailbox rings, enable the IRQ
- * and initialize the communication between the Firmware and the host. The
- * firmware is expected to respond to the initialization by sending an
- * interrupt essentially notifying the host that it has seen the
- * initialization and is now synced up.
+ * This function will allocate the IRQ and then reinitialize the mailbox
+ * starting communication between the host and firmware.
  *
  * Return: non-zero on failure.
  **/
-int fbnic_fw_enable_mbx(struct fbnic_dev *fbd)
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd)
 {
-	u32 vector = fbd->fw_msix_vector;
-	int err;
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int vector, err;
+
+	WARN_ON(fbd->fw_msix_vector);
+
+	vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY);
+	if (vector < 0)
+		return vector;
 
 	/* Request the IRQ for FW Mailbox vector. */
 	err = request_threaded_irq(vector, NULL, &fbnic_fw_msix_intr,
-				   IRQF_ONESHOT, dev_name(fbd->dev), fbd);
+				   IRQF_ONESHOT | IRQF_NO_AUTOEN,
+				   dev_name(fbd->dev), fbd);
 	if (err)
 		return err;
 
 	/* Initialize mailbox and attempt to poll it into ready state */
-	fbnic_mbx_init(fbd);
-	err = fbnic_mbx_poll_tx_ready(fbd);
-	if (err) {
-		dev_warn(fbd->dev, "FW mailbox did not enter ready state\n");
+	err = __fbnic_fw_enable_mbx(fbd, vector);
+	if (err)
 		free_irq(vector, fbd);
-		return err;
-	}
 
-	/* Enable interrupts */
-	fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
+	fbd->fw_msix_vector = vector;
 
-	return 0;
+	return err;
 }
 
 /**
- * fbnic_fw_disable_mbx - Disable mailbox and place it in standby state
- * @fbd: Pointer to device to disable
+ * fbnic_fw_disable_mbx - Temporarily place mailbox in standby state
+ * @fbd: Pointer to device
  *
- * This function will disable the mailbox interrupt, free any messages still
- * in the mailbox and place it into a standby state. The firmware is
- * expected to see the update and assume that the host is in the reset state.
+ * Shutdown the mailbox by notifying the firmware to stop sending us logs, mask
+ * and synchronize the IRQ, and then clean up the rings.
  **/
-void fbnic_fw_disable_mbx(struct fbnic_dev *fbd)
+static void fbnic_fw_disable_mbx(struct fbnic_dev *fbd)
 {
-	/* Disable interrupt and free vector */
-	fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY);
+	/* Disable interrupt and synchronize the IRQ */
+	disable_irq(fbd->fw_msix_vector);
 
-	/* Free the vector */
-	free_irq(fbd->fw_msix_vector, fbd);
+	/* Mask the vector */
+	fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
 	/* Make sure disabling logs message is sent, must be done here to
 	 * avoid risk of completing without a running interrupt.
 	 */
 	fbnic_mbx_flush_tx(fbd);
-
-	/* Reset the mailboxes to the initialized state */
 	fbnic_mbx_clean(fbd);
 }
 
+/**
+ * fbnic_fw_free_mbx - Disable mailbox and place it in standby state
+ * @fbd: Pointer to device to disable
+ *
+ * This function will disable the mailbox interrupt, free any messages still
+ * in the mailbox and place it into a disabled state. The firmware is
+ * expected to see the update and assume that the host is in the reset state.
+ **/
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd)
+{
+	/* Vector has already been freed */
+	if (!fbd->fw_msix_vector)
+		return;
+
+	fbnic_fw_disable_mbx(fbd);
+
+	/* Free the vector */
+	free_irq(fbd->fw_msix_vector, fbd);
+	fbd->fw_msix_vector = 0;
+}
+
 static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
 {
 	struct fbnic_dev *fbd = data;
@@ -101,7 +137,7 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
 }
 
 /**
- * fbnic_pcs_irq_enable - Configure the MAC to enable it to advertise link
+ * fbnic_pcs_request_irq - Configure the PCS to enable it to advertise link
  * @fbd: Pointer to device to initialize
  *
  * This function provides basic bringup for the MAC/PCS IRQ. For now the IRQ
@@ -109,41 +145,61 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
  *
  * Return: non-zero on failure.
  **/
-int fbnic_pcs_irq_enable(struct fbnic_dev *fbd)
+int fbnic_pcs_request_irq(struct fbnic_dev *fbd)
 {
-	u32 vector = fbd->pcs_msix_vector;
-	int err;
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int vector, err;
 
-	/* Request the IRQ for MAC link vector.
-	 * Map MAC cause to it, and unmask it
+	WARN_ON(fbd->pcs_msix_vector);
+
+	vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY);
+	if (vector < 0)
+		return vector;
+
+	/* Request the IRQ for PCS link vector.
+	 * Map PCS cause to it, and unmask it
 	 */
 	err = request_irq(vector, &fbnic_pcs_msix_intr, 0,
 			  fbd->netdev->name, fbd);
 	if (err)
 		return err;
 
+	/* Map and enable interrupt, unmask vector after link is configured */
 	fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
 		   FBNIC_PCS_MSIX_ENTRY | FBNIC_INTR_MSIX_CTRL_ENABLE);
 
+	fbd->pcs_msix_vector = vector;
+
 	return 0;
 }
 
 /**
- * fbnic_pcs_irq_disable - Teardown the MAC IRQ to prepare for stopping
+ * fbnic_pcs_free_irq - Teardown the PCS IRQ to prepare for stopping
  * @fbd: Pointer to device that is stopping
  *
- * This function undoes the work done in fbnic_pcs_irq_enable and prepares
+ * This function undoes the work done in fbnic_pcs_request_irq and prepares
  * the device to no longer receive traffic on the host interface.
  **/
-void fbnic_pcs_irq_disable(struct fbnic_dev *fbd)
+void fbnic_pcs_free_irq(struct fbnic_dev *fbd)
 {
+	/* Vector has already been freed */
+	if (!fbd->pcs_msix_vector)
+		return;
+
 	/* Disable interrupt */
 	fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
 		   FBNIC_PCS_MSIX_ENTRY);
+	fbnic_wrfl(fbd);
+
+	/* Synchronize IRQ to prevent race that would unmask vector */
+	synchronize_irq(fbd->pcs_msix_vector);
+
+	/* Mask the vector */
 	fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_PCS_MSIX_ENTRY);
 
 	/* Free the vector */
 	free_irq(fbd->pcs_msix_vector, fbd);
+	fbd->pcs_msix_vector = 0;
 }
 
 void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr)
@@ -226,9 +282,6 @@ void fbnic_free_irqs(struct fbnic_dev *fbd)
 {
 	struct pci_dev *pdev = to_pci_dev(fbd->dev);
 
-	fbd->pcs_msix_vector = 0;
-	fbd->fw_msix_vector = 0;
-
 	fbd->num_irqs = 0;
 
 	pci_free_irq_vectors(pdev);
@@ -254,8 +307,5 @@ int fbnic_alloc_irqs(struct fbnic_dev *fbd)
 
 	fbd->num_irqs = num_irqs;
 
-	fbd->pcs_msix_vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY);
-	fbd->fw_msix_vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY);
-
 	return 0;
 }
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
index 14291401f463..10e108c1fcd0 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
@@ -79,12 +79,6 @@ static void fbnic_mac_init_axi(struct fbnic_dev *fbd)
 	fbnic_init_readrq(fbd, FBNIC_QM_RNI_RBP_CTL, cls, readrq);
 	fbnic_init_mps(fbd, FBNIC_QM_RNI_RDE_CTL, cls, mps);
 	fbnic_init_mps(fbd, FBNIC_QM_RNI_RCM_CTL, cls, mps);
-
-	/* Enable XALI AR/AW outbound */
-	wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
-	     FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
-	wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
-	     FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
 }
 
 static void fbnic_mac_init_qm(struct fbnic_dev *fbd)
@@ -693,13 +687,10 @@ static int fbnic_mac_get_sensor_asic(struct fbnic_dev *fbd, int id,
 	int err = 0, retries = 5;
 	s32 *sensor;
 
-	fw_cmpl = kzalloc(sizeof(*fw_cmpl), GFP_KERNEL);
+	fw_cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_TSENE_READ_RESP);
 	if (!fw_cmpl)
 		return -ENOMEM;
 
-	/* Initialize completion and queue it for FW to process */
-	fbnic_fw_init_cmpl(fw_cmpl, FBNIC_TLV_MSG_ID_TSENE_READ_RESP);
-
 	switch (id) {
 	case FBNIC_SENSOR_TEMP:
 		sensor = &fw_cmpl->u.tsene.millidegrees;
@@ -750,7 +741,7 @@ static int fbnic_mac_get_sensor_asic(struct fbnic_dev *fbd, int id,
 
 	*val = *sensor;
 exit_cleanup:
-	fbnic_fw_clear_compl(fbd);
+	fbnic_fw_clear_cmpl(fbd, fw_cmpl);
 exit_free:
 	fbnic_fw_put_cmpl(fw_cmpl);
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index 79a01fdd1dd1..aa812c63d5af 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -44,9 +44,10 @@ int __fbnic_open(struct fbnic_net *fbn)
 	if (err)
 		goto time_stop;
 
-	err = fbnic_pcs_irq_enable(fbd);
+	err = fbnic_pcs_request_irq(fbd);
 	if (err)
 		goto time_stop;
+
 	/* Pull the BMC config and initialize the RPC */
 	fbnic_bmc_rpc_init(fbd);
 	fbnic_rss_reinit(fbd, fbn);
@@ -82,7 +83,7 @@ static int fbnic_stop(struct net_device *netdev)
 	struct fbnic_net *fbn = netdev_priv(netdev);
 
 	fbnic_down(fbn);
-	fbnic_pcs_irq_disable(fbn->fbd);
+	fbnic_pcs_free_irq(fbn->fbd);
 
 	fbnic_time_stop(fbn);
 	fbnic_fw_xmit_ownership_msg(fbn->fbd, false);
@@ -403,12 +404,16 @@ static int fbnic_hwtstamp_set(struct net_device *netdev,
 static void fbnic_get_stats64(struct net_device *dev,
 			      struct rtnl_link_stats64 *stats64)
 {
+	u64 rx_bytes, rx_packets, rx_dropped = 0, rx_errors = 0;
 	u64 tx_bytes, tx_packets, tx_dropped = 0;
-	u64 rx_bytes, rx_packets, rx_dropped = 0;
 	struct fbnic_net *fbn = netdev_priv(dev);
+	struct fbnic_dev *fbd = fbn->fbd;
 	struct fbnic_queue_stats *stats;
+	u64 rx_over = 0, rx_missed = 0;
 	unsigned int start, i;
 
+	fbnic_get_hw_stats(fbd);
+
 	stats = &fbn->tx_stats;
 
 	tx_bytes = stats->bytes;
@@ -419,6 +424,12 @@ static void fbnic_get_stats64(struct net_device *dev,
 	stats64->tx_packets = tx_packets;
 	stats64->tx_dropped = tx_dropped;
 
+	/* Record drops from Tx HW Datapath */
+	tx_dropped += fbd->hw_stats.tmi.drop.frames.value +
+		      fbd->hw_stats.tti.cm_drop.frames.value +
+		      fbd->hw_stats.tti.frame_drop.frames.value +
+		      fbd->hw_stats.tti.tbi_drop.frames.value;
+
 	for (i = 0; i < fbn->num_tx_queues; i++) {
 		struct fbnic_ring *txr = fbn->tx[i];
 
@@ -444,9 +455,34 @@ static void fbnic_get_stats64(struct net_device *dev,
 	rx_packets = stats->packets;
 	rx_dropped = stats->dropped;
 
+	spin_lock(&fbd->hw_stats_lock);
+	/* Record drops for the host FIFOs.
+	 * 4: network to Host,	6: BMC to Host
+	 * Exclude the BMC and MC FIFOs as those stats may contain drops
+	 * due to unrelated items such as TCAM misses. They are still
+	 * accessible through the ethtool stats.
+	 */
+	i = FBNIC_RXB_FIFO_HOST;
+	rx_missed += fbd->hw_stats.rxb.fifo[i].drop.frames.value;
+	i = FBNIC_RXB_FIFO_BMC_TO_HOST;
+	rx_missed += fbd->hw_stats.rxb.fifo[i].drop.frames.value;
+
+	for (i = 0; i < fbd->max_num_queues; i++) {
+		/* Report packets dropped due to CQ/BDQ being full/empty */
+		rx_over += fbd->hw_stats.hw_q[i].rde_pkt_cq_drop.value;
+		rx_over += fbd->hw_stats.hw_q[i].rde_pkt_bdq_drop.value;
+
+		/* Report packets with errors */
+		rx_errors += fbd->hw_stats.hw_q[i].rde_pkt_err.value;
+	}
+	spin_unlock(&fbd->hw_stats_lock);
+
 	stats64->rx_bytes = rx_bytes;
 	stats64->rx_packets = rx_packets;
 	stats64->rx_dropped = rx_dropped;
+	stats64->rx_over_errors = rx_over;
+	stats64->rx_errors = rx_errors;
+	stats64->rx_missed_errors = rx_missed;
 
 	for (i = 0; i < fbn->num_rx_queues; i++) {
 		struct fbnic_ring *rxr = fbn->rx[i];
@@ -486,6 +522,7 @@ static void fbnic_get_queue_stats_rx(struct net_device *dev, int idx,
 {
 	struct fbnic_net *fbn = netdev_priv(dev);
 	struct fbnic_ring *rxr = fbn->rx[idx];
+	struct fbnic_dev *fbd = fbn->fbd;
 	struct fbnic_queue_stats *stats;
 	u64 bytes, packets, alloc_fail;
 	u64 csum_complete, csum_none;
@@ -509,6 +546,15 @@ static void fbnic_get_queue_stats_rx(struct net_device *dev, int idx,
 	rx->alloc_fail = alloc_fail;
 	rx->csum_complete = csum_complete;
 	rx->csum_none = csum_none;
+
+	fbnic_get_hw_q_stats(fbd, fbd->hw_stats.hw_q);
+
+	spin_lock(&fbd->hw_stats_lock);
+	rx->hw_drop_overruns = fbd->hw_stats.hw_q[idx].rde_pkt_cq_drop.value +
+			       fbd->hw_stats.hw_q[idx].rde_pkt_bdq_drop.value;
+	rx->hw_drops = fbd->hw_stats.hw_q[idx].rde_pkt_err.value +
+		       rx->hw_drop_overruns;
+	spin_unlock(&fbd->hw_stats_lock);
 }
 
 static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
index 6cbbc2ee3e1f..249d3ef862d5 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <linux/rtnetlink.h>
 #include <linux/types.h>
+#include <net/devlink.h>
 
 #include "fbnic.h"
 #include "fbnic_drvinfo.h"
@@ -283,7 +284,7 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto free_irqs;
 	}
 
-	err = fbnic_fw_enable_mbx(fbd);
+	err = fbnic_fw_request_mbx(fbd);
 	if (err) {
 		dev_err(&pdev->dev,
 			"Firmware mailbox initialization failure\n");
@@ -292,6 +293,7 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	fbnic_devlink_register(fbd);
 	fbnic_dbg_fbd_init(fbd);
+	spin_lock_init(&fbd->hw_stats_lock);
 
 	/* Capture snapshot of hardware stats so netdev can calculate delta */
 	fbnic_reset_hw_stats(fbd);
@@ -363,7 +365,7 @@ static void fbnic_remove(struct pci_dev *pdev)
 	fbnic_hwmon_unregister(fbd);
 	fbnic_dbg_fbd_exit(fbd);
 	fbnic_devlink_unregister(fbd);
-	fbnic_fw_disable_mbx(fbd);
+	fbnic_fw_free_mbx(fbd);
 	fbnic_free_irqs(fbd);
 
 	fbnic_devlink_free(fbd);
@@ -387,7 +389,11 @@ static int fbnic_pm_suspend(struct device *dev)
 	rtnl_unlock();
 
 null_uc_addr:
-	fbnic_fw_disable_mbx(fbd);
+	devl_lock(priv_to_devlink(fbd));
+
+	fbnic_fw_free_mbx(fbd);
+
+	devl_unlock(priv_to_devlink(fbd));
 
 	/* Free the IRQs so they aren't trying to occupy sleeping CPUs */
 	fbnic_free_irqs(fbd);
@@ -419,11 +425,15 @@ static int __fbnic_pm_resume(struct device *dev)
 
 	fbd->mac->init_regs(fbd);
 
+	devl_lock(priv_to_devlink(fbd));
+
 	/* Re-enable mailbox */
-	err = fbnic_fw_enable_mbx(fbd);
+	err = fbnic_fw_request_mbx(fbd);
 	if (err)
 		goto err_free_irqs;
 
+	devl_unlock(priv_to_devlink(fbd));
+
 	/* No netdev means there isn't a network interface to bring up */
 	if (fbnic_init_failure(fbd))
 		return 0;
@@ -438,15 +448,15 @@ static int __fbnic_pm_resume(struct device *dev)
 	if (netif_running(netdev)) {
 		err = __fbnic_open(fbn);
 		if (err)
-			goto err_disable_mbx;
+			goto err_free_mbx;
 	}
 
 	rtnl_unlock();
 
 	return 0;
-err_disable_mbx:
+err_free_mbx:
 	rtnl_unlock();
-	fbnic_fw_disable_mbx(fbd);
+	fbnic_fw_free_mbx(fbd);
 err_free_irqs:
 	fbnic_free_irqs(fbd);
 err_invalidate_uc_addr:
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 23760b613d3e..7e71579632f3 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1729,6 +1729,7 @@ int lan743x_rx_set_tstamp_mode(struct lan743x_adapter *adapter,
 	default:
 			return -ERANGE;
 	}
+	adapter->rx_tstamp_filter = rx_filter;
 	return 0;
 }
 
@@ -1815,6 +1816,7 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
 	if (nr_frags <= 0) {
 		tx->frame_data0 |= TX_DESC_DATA0_LS_;
 		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+		tx->frame_last = tx->frame_first;
 	}
 	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	tx_descriptor->data0 = cpu_to_le32(tx->frame_data0);
@@ -1884,6 +1886,7 @@ static int lan743x_tx_frame_add_fragment(struct lan743x_tx *tx,
 		tx->frame_first = 0;
 		tx->frame_data0 = 0;
 		tx->frame_tail = 0;
+		tx->frame_last = 0;
 		return -ENOMEM;
 	}
 
@@ -1924,16 +1927,18 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx,
 	    TX_DESC_DATA0_DTYPE_DATA_) {
 		tx->frame_data0 |= TX_DESC_DATA0_LS_;
 		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+		tx->frame_last = tx->frame_tail;
 	}
 
-	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
-	buffer_info = &tx->buffer_info[tx->frame_tail];
+	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_last];
+	buffer_info = &tx->buffer_info[tx->frame_last];
 	buffer_info->skb = skb;
 	if (time_stamp)
 		buffer_info->flags |= TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED;
 	if (ignore_sync)
 		buffer_info->flags |= TX_BUFFER_INFO_FLAG_IGNORE_SYNC;
 
+	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	tx_descriptor->data0 = cpu_to_le32(tx->frame_data0);
 	tx->frame_tail = lan743x_tx_next_index(tx, tx->frame_tail);
 	tx->last_tail = tx->frame_tail;
@@ -2495,8 +2500,7 @@ static int lan743x_rx_process_buffer(struct lan743x_rx *rx)
 
 	/* save existing skb, allocate new skb and map to dma */
 	skb = buffer_info->skb;
-	if (lan743x_rx_init_ring_element(rx, rx->last_head,
-					 GFP_ATOMIC | GFP_DMA)) {
+	if (lan743x_rx_init_ring_element(rx, rx->last_head, GFP_ATOMIC)) {
 		/* failed to allocate next skb.
 		 * Memory is very low.
 		 * Drop this packet and reuse buffer.
@@ -3348,8 +3352,6 @@ static int lan743x_netdev_ioctl(struct net_device *netdev,
 
 	if (!netif_running(netdev))
 		return -EINVAL;
-	if (cmd == SIOCSHWTSTAMP)
-		return lan743x_ptp_ioctl(netdev, ifr, cmd);
 
 	return phylink_mii_ioctl(adapter->phylink, ifr, cmd);
 }
@@ -3444,6 +3446,8 @@ static const struct net_device_ops lan743x_netdev_ops = {
 	.ndo_change_mtu		= lan743x_netdev_change_mtu,
 	.ndo_get_stats64	= lan743x_netdev_get_stats64,
 	.ndo_set_mac_address	= lan743x_netdev_set_mac_address,
+	.ndo_hwtstamp_get	= lan743x_ptp_hwtstamp_get,
+	.ndo_hwtstamp_set	= lan743x_ptp_hwtstamp_set,
 };
 
 static void lan743x_hardware_cleanup(struct lan743x_adapter *adapter)
@@ -3491,6 +3495,7 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 				 struct pci_dev *pdev)
 {
 	struct lan743x_tx *tx;
+	u32 sgmii_ctl;
 	int index;
 	int ret;
 
@@ -3503,6 +3508,15 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 		spin_lock_init(&adapter->eth_syslock_spinlock);
 		mutex_init(&adapter->sgmii_rw_lock);
 		pci11x1x_set_rfe_rd_fifo_threshold(adapter);
+		sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
+		if (adapter->is_sgmii_en) {
+			sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_;
+			sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_;
+		} else {
+			sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_;
+			sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_;
+		}
+		lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
 	} else {
 		adapter->max_tx_channels = LAN743X_MAX_TX_CHANNELS;
 		adapter->used_tx_channels = LAN743X_USED_TX_CHANNELS;
@@ -3554,7 +3568,6 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 
 static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
 {
-	u32 sgmii_ctl;
 	int ret;
 
 	adapter->mdiobus = devm_mdiobus_alloc(&adapter->pdev->dev);
@@ -3566,10 +3579,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
 	adapter->mdiobus->priv = (void *)adapter;
 	if (adapter->is_pci11x1x) {
 		if (adapter->is_sgmii_en) {
-			sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
-			sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_;
-			sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_;
-			lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
 			netif_dbg(adapter, drv, adapter->netdev,
 				  "SGMII operation\n");
 			adapter->mdiobus->read = lan743x_mdiobus_read_c22;
@@ -3580,10 +3589,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
 			netif_dbg(adapter, drv, adapter->netdev,
 				  "lan743x-mdiobus-c45\n");
 		} else {
-			sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
-			sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_;
-			sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_;
-			lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
 			netif_dbg(adapter, drv, adapter->netdev,
 				  "RGMII operation\n");
 			// Only C22 support when RGMII I/F
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 7f73d66854be..02a28b709163 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -980,6 +980,7 @@ struct lan743x_tx {
 	u32		frame_first;
 	u32		frame_data0;
 	u32		frame_tail;
+	u32		frame_last;
 
 	struct lan743x_tx_buffer_info *buffer_info;
 
@@ -1086,6 +1087,7 @@ struct lan743x_adapter {
 	phy_interface_t		phy_interface;
 	struct phylink		*phylink;
 	struct phylink_config	phylink_config;
+	int			rx_tstamp_filter;
 };
 
 #define LAN743X_COMPONENT_FLAG_RX(channel)  BIT(20 + (channel))
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c
index 0be44dcb3393..a3b48388b3fd 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.c
@@ -463,10 +463,6 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on,
 	struct lan743x_ptp_perout *perout = &ptp->perout[index];
 	int ret = 0;
 
-	/* Reject requests with unsupported flags */
-	if (perout_request->flags & ~PTP_PEROUT_DUTY_CYCLE)
-		return -EOPNOTSUPP;
-
 	if (on) {
 		perout_pin = ptp_find_pin(ptp->ptp_clock, PTP_PF_PEROUT,
 					  perout_request->index);
@@ -942,12 +938,6 @@ static int lan743x_ptp_io_extts(struct lan743x_adapter *adapter, int on,
 
 	extts = &ptp->extts[index];
 
-	if (extts_request->flags & ~(PTP_ENABLE_FEATURE |
-				     PTP_RISING_EDGE |
-				     PTP_FALLING_EDGE |
-				     PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	if (on) {
 		extts_pin = ptp_find_pin(ptp->ptp_clock, PTP_PF_EXTTS, index);
 		if (extts_pin < 0)
@@ -1543,6 +1533,10 @@ int lan743x_ptp_open(struct lan743x_adapter *adapter)
 	ptp->ptp_clock_info.n_per_out = LAN743X_PTP_N_EVENT_CHAN;
 	ptp->ptp_clock_info.n_pins = n_pins;
 	ptp->ptp_clock_info.pps = LAN743X_PTP_N_PPS;
+	ptp->ptp_clock_info.supported_extts_flags = PTP_RISING_EDGE |
+						    PTP_FALLING_EDGE |
+						    PTP_STRICT_FLAGS;
+	ptp->ptp_clock_info.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE;
 	ptp->ptp_clock_info.pin_config = ptp->pin_config;
 	ptp->ptp_clock_info.adjfine = lan743x_ptpci_adjfine;
 	ptp->ptp_clock_info.adjtime = lan743x_ptpci_adjtime;
@@ -1742,23 +1736,32 @@ void lan743x_ptp_tx_timestamp_skb(struct lan743x_adapter *adapter,
 	lan743x_ptp_tx_ts_complete(adapter);
 }
 
-int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+int lan743x_ptp_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
-	struct hwtstamp_config config;
-	int ret = 0;
-	int index;
+	struct lan743x_tx *tx = &adapter->tx[0];
 
-	if (!ifr) {
-		netif_err(adapter, drv, adapter->netdev,
-			  "SIOCSHWTSTAMP, ifr == NULL\n");
-		return -EINVAL;
-	}
+	if (tx->ts_flags & TX_TS_FLAG_ONE_STEP_SYNC)
+		config->tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
+	else if (tx->ts_flags & TX_TS_FLAG_TIMESTAMPING_ENABLED)
+		config->tx_type = HWTSTAMP_TX_ON;
+	else
+		config->tx_type = HWTSTAMP_TX_OFF;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	config->rx_filter = adapter->rx_tstamp_filter;
 
-	switch (config.tx_type) {
+	return 0;
+}
+
+int lan743x_ptp_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int index;
+
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		for (index = 0; index < adapter->used_tx_channels;
 		     index++)
@@ -1782,19 +1785,12 @@ int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 		lan743x_ptp_set_sync_ts_insert(adapter, true);
 		break;
 	case HWTSTAMP_TX_ONESTEP_P2P:
-		ret = -ERANGE;
-		break;
+		return -ERANGE;
 	default:
 		netif_warn(adapter, drv, adapter->netdev,
-			   "  tx_type = %d, UNKNOWN\n", config.tx_type);
-		ret = -EINVAL;
-		break;
+			   "  tx_type = %d, UNKNOWN\n", config->tx_type);
+		return -EINVAL;
 	}
 
-	ret = lan743x_rx_set_tstamp_mode(adapter, config.rx_filter);
-
-	if (!ret)
-		return copy_to_user(ifr->ifr_data, &config,
-			sizeof(config)) ? -EFAULT : 0;
-	return ret;
+	return lan743x_rx_set_tstamp_mode(adapter, config->rx_filter);
 }
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.h b/drivers/net/ethernet/microchip/lan743x_ptp.h
index 0d29914cd460..e8d073bfa2ca 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.h
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.h
@@ -51,8 +51,11 @@ int lan743x_ptp_open(struct lan743x_adapter *adapter);
 void lan743x_ptp_close(struct lan743x_adapter *adapter);
 void lan743x_ptp_update_latency(struct lan743x_adapter *adapter,
 				u32 link_speed);
-
-int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
+int lan743x_ptp_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config);
+int lan743x_ptp_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack);
 
 #define LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS (4)
 
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
index 63905bb5a63a..098406e2e5bb 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
@@ -815,10 +815,6 @@ static int lan966x_ptp_perout(struct ptp_clock_info *ptp,
 	bool pps = false;
 	int pin;
 
-	if (rq->perout.flags & ~(PTP_PEROUT_DUTY_CYCLE |
-				 PTP_PEROUT_PHASE))
-		return -EOPNOTSUPP;
-
 	pin = ptp_find_pin(phc->clock, PTP_PF_PEROUT, rq->perout.index);
 	if (pin == -1 || pin >= LAN966X_PHC_PINS_NUM)
 		return -EINVAL;
@@ -917,12 +913,6 @@ static int lan966x_ptp_extts(struct ptp_clock_info *ptp,
 	if (lan966x->ptp_ext_irq <= 0)
 		return -EOPNOTSUPP;
 
-	/* Reject requests with unsupported flags */
-	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-				PTP_RISING_EDGE |
-				PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	pin = ptp_find_pin(phc->clock, PTP_PF_EXTTS, rq->extts.index);
 	if (pin == -1 || pin >= LAN966X_PHC_PINS_NUM)
 		return -EINVAL;
@@ -978,6 +968,10 @@ static struct ptp_clock_info lan966x_ptp_clock_info = {
 	.n_per_out	= LAN966X_PHC_PINS_NUM,
 	.n_ext_ts	= LAN966X_PHC_PINS_NUM,
 	.n_pins		= LAN966X_PHC_PINS_NUM,
+	.supported_extts_flags = PTP_RISING_EDGE |
+				 PTP_STRICT_FLAGS,
+	.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE |
+				  PTP_PEROUT_PHASE,
 };
 
 static int lan966x_ptp_phc_init(struct lan966x *lan966x,
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index ef93df520887..08bee56aea35 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -830,6 +830,7 @@ EXPORT_SYMBOL(ocelot_vlan_prepare);
 int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 		    bool untagged)
 {
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	int err;
 
 	/* Ignore VID 0 added to our RX filter by the 8021q module, since
@@ -849,6 +850,11 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 					   ocelot_bridge_vlan_find(ocelot, vid));
 		if (err)
 			return err;
+	} else if (ocelot_port->pvid_vlan &&
+		   ocelot_bridge_vlan_find(ocelot, vid) == ocelot_port->pvid_vlan) {
+		err = ocelot_port_set_pvid(ocelot, port, NULL);
+		if (err)
+			return err;
 	}
 
 	/* Untagged egress vlan clasification */
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 7663d196eaf8..469784d3a1a6 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -870,23 +870,30 @@ static int ocelot_set_features(struct net_device *dev,
 
 static int ocelot_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
+	return phy_mii_ioctl(dev->phydev, ifr, cmd);
+}
+
+static int ocelot_port_hwtstamp_get(struct net_device *dev,
+				    struct kernel_hwtstamp_config *cfg)
+{
 	struct ocelot_port_private *priv = netdev_priv(dev);
 	struct ocelot *ocelot = priv->port.ocelot;
 	int port = priv->port.index;
 
-	/* If the attached PHY device isn't capable of timestamping operations,
-	 * use our own (when possible).
-	 */
-	if (!phy_has_hwtstamp(dev->phydev) && ocelot->ptp) {
-		switch (cmd) {
-		case SIOCSHWTSTAMP:
-			return ocelot_hwstamp_set(ocelot, port, ifr);
-		case SIOCGHWTSTAMP:
-			return ocelot_hwstamp_get(ocelot, port, ifr);
-		}
-	}
+	ocelot_hwstamp_get(ocelot, port, cfg);
 
-	return phy_mii_ioctl(dev->phydev, ifr, cmd);
+	return 0;
+}
+
+static int ocelot_port_hwtstamp_set(struct net_device *dev,
+				    struct kernel_hwtstamp_config *cfg,
+				    struct netlink_ext_ack *extack)
+{
+	struct ocelot_port_private *priv = netdev_priv(dev);
+	struct ocelot *ocelot = priv->port.ocelot;
+	int port = priv->port.index;
+
+	return ocelot_hwstamp_set(ocelot, port, cfg, extack);
 }
 
 static int ocelot_change_mtu(struct net_device *dev, int new_mtu)
@@ -917,6 +924,8 @@ static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_set_features		= ocelot_set_features,
 	.ndo_setup_tc			= ocelot_setup_tc,
 	.ndo_eth_ioctl			= ocelot_ioctl,
+	.ndo_hwtstamp_get		= ocelot_port_hwtstamp_get,
+	.ndo_hwtstamp_set		= ocelot_port_hwtstamp_set,
 };
 
 struct net_device *ocelot_port_to_netdev(struct ocelot *ocelot, int port)
diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c
index cc1088988da0..88b5422cc2a0 100644
--- a/drivers/net/ethernet/mscc/ocelot_ptp.c
+++ b/drivers/net/ethernet/mscc/ocelot_ptp.c
@@ -211,11 +211,6 @@ int ocelot_ptp_enable(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_PEROUT:
-		/* Reject requests with unsupported flags */
-		if (rq->perout.flags & ~(PTP_PEROUT_DUTY_CYCLE |
-					 PTP_PEROUT_PHASE))
-			return -EOPNOTSUPP;
-
 		pin = ptp_find_pin(ocelot->ptp_clock, PTP_PF_PEROUT,
 				   rq->perout.index);
 		if (pin == 0)
@@ -519,47 +514,42 @@ static int ocelot_ptp_tx_type_to_cmd(int tx_type, int *ptp_cmd)
 	return 0;
 }
 
-int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr)
+void ocelot_hwstamp_get(struct ocelot *ocelot, int port,
+			struct kernel_hwtstamp_config *cfg)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	struct hwtstamp_config cfg = {};
 
 	switch (ocelot_port->ptp_cmd) {
 	case IFH_REW_OP_TWO_STEP_PTP:
-		cfg.tx_type = HWTSTAMP_TX_ON;
+		cfg->tx_type = HWTSTAMP_TX_ON;
 		break;
 	case IFH_REW_OP_ORIGIN_PTP:
-		cfg.tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
+		cfg->tx_type = HWTSTAMP_TX_ONESTEP_SYNC;
 		break;
 	default:
-		cfg.tx_type = HWTSTAMP_TX_OFF;
+		cfg->tx_type = HWTSTAMP_TX_OFF;
 		break;
 	}
 
-	cfg.rx_filter = ocelot_traps_to_ptp_rx_filter(ocelot_port->trap_proto);
-
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	cfg->rx_filter = ocelot_traps_to_ptp_rx_filter(ocelot_port->trap_proto);
 }
 EXPORT_SYMBOL(ocelot_hwstamp_get);
 
-int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr)
+int ocelot_hwstamp_set(struct ocelot *ocelot, int port,
+		       struct kernel_hwtstamp_config *cfg,
+		       struct netlink_ext_ack *extack)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	int ptp_cmd, old_ptp_cmd = ocelot_port->ptp_cmd;
 	bool l2 = false, l4 = false;
-	struct hwtstamp_config cfg;
-	bool old_l2, old_l4;
+	int ptp_cmd;
 	int err;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
 	/* Tx type sanity check */
-	err = ocelot_ptp_tx_type_to_cmd(cfg.tx_type, &ptp_cmd);
+	err = ocelot_ptp_tx_type_to_cmd(cfg->tx_type, &ptp_cmd);
 	if (err)
 		return err;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
@@ -582,27 +572,15 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	old_l2 = ocelot_port->trap_proto & OCELOT_PROTO_PTP_L2;
-	old_l4 = ocelot_port->trap_proto & OCELOT_PROTO_PTP_L4;
-
 	err = ocelot_setup_ptp_traps(ocelot, port, l2, l4);
 	if (err)
 		return err;
 
 	ocelot_port->ptp_cmd = ptp_cmd;
 
-	cfg.rx_filter = ocelot_traps_to_ptp_rx_filter(ocelot_port->trap_proto);
-
-	if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) {
-		err = -EFAULT;
-		goto out_restore_ptp_traps;
-	}
+	cfg->rx_filter = ocelot_traps_to_ptp_rx_filter(ocelot_port->trap_proto);
 
 	return 0;
-out_restore_ptp_traps:
-	ocelot_setup_ptp_traps(ocelot, port, old_l2, old_l4);
-	ocelot_port->ptp_cmd = old_ptp_cmd;
-	return err;
 }
 EXPORT_SYMBOL(ocelot_hwstamp_set);
 
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 055b55651a49..498eec8ae61d 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -108,6 +108,8 @@ static struct ptp_clock_info ocelot_ptp_clock_info = {
 	.n_ext_ts	= 0,
 	.n_per_out	= OCELOT_PTP_PINS_NUM,
 	.n_pins		= OCELOT_PTP_PINS_NUM,
+	.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE |
+				  PTP_PEROUT_PHASE,
 	.pps		= 0,
 	.gettime64	= ocelot_ptp_gettime64,
 	.settime64	= ocelot_ptp_settime64,
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index 05606692e631..dd279788cf9e 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -846,7 +846,7 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENOMEM;
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
-	i = pci_request_regions(pdev, DRV_NAME);
+	i = pcim_request_all_regions(pdev, DRV_NAME);
 	if (i)
 		goto err_pci_request_regions;
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 95514fabadf2..28997ddab966 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2538,7 +2538,7 @@ nfp_net_alloc(struct pci_dev *pdev, const struct nfp_dev_info *dev_info,
 				  nn->dp.num_r_vecs, num_online_cpus());
 	nn->max_r_vecs = nn->dp.num_r_vecs;
 
-	nn->dp.xsk_pools = kcalloc(nn->max_r_vecs, sizeof(nn->dp.xsk_pools),
+	nn->dp.xsk_pools = kcalloc(nn->max_r_vecs, sizeof(*nn->dp.xsk_pools),
 				   GFP_KERNEL);
 	if (!nn->dp.xsk_pools) {
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index a2d4336d2766..92f30ff2d631 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -948,64 +948,20 @@ static int ionic_get_tunable(struct net_device *netdev,
 	return 0;
 }
 
-static int ionic_get_module_info(struct net_device *netdev,
-				 struct ethtool_modinfo *modinfo)
-
-{
-	struct ionic_lif *lif = netdev_priv(netdev);
-	struct ionic_dev *idev = &lif->ionic->idev;
-	struct ionic_xcvr_status *xcvr;
-	struct sfp_eeprom_base *sfp;
-
-	xcvr = &idev->port_info->status.xcvr;
-	sfp = (struct sfp_eeprom_base *) xcvr->sprom;
-
-	/* report the module data type and length */
-	switch (sfp->phys_id) {
-	case SFF8024_ID_SFP:
-		modinfo->type = ETH_MODULE_SFF_8079;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
-		break;
-	case SFF8024_ID_QSFP_8436_8636:
-	case SFF8024_ID_QSFP28_8636:
-	case SFF8024_ID_QSFP_PLUS_CMIS:
-		modinfo->type = ETH_MODULE_SFF_8436;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
-		break;
-	default:
-		netdev_info(netdev, "unknown xcvr type 0x%02x\n",
-			    xcvr->sprom[0]);
-		modinfo->type = 0;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
-		break;
-	}
-
-	return 0;
-}
-
-static int ionic_get_module_eeprom(struct net_device *netdev,
-				   struct ethtool_eeprom *ee,
-				   u8 *data)
+static int ionic_do_module_copy(u8 *dst, u8 *src, u32 len)
 {
-	struct ionic_lif *lif = netdev_priv(netdev);
-	struct ionic_dev *idev = &lif->ionic->idev;
-	struct ionic_xcvr_status *xcvr;
-	char tbuf[sizeof(xcvr->sprom)];
+	char tbuf[sizeof_field(struct ionic_xcvr_status, sprom)];
 	int count = 10;
-	u32 len;
 
 	/* The NIC keeps the module prom up-to-date in the DMA space
 	 * so we can simply copy the module bytes into the data buffer.
 	 */
-	xcvr = &idev->port_info->status.xcvr;
-	len = min_t(u32, sizeof(xcvr->sprom), ee->len);
-
 	do {
-		memcpy(data, &xcvr->sprom[ee->offset], len);
-		memcpy(tbuf, &xcvr->sprom[ee->offset], len);
+		memcpy(dst, src, len);
+		memcpy(tbuf, src, len);
 
 		/* Let's make sure we got a consistent copy */
-		if (!memcmp(data, tbuf, len))
+		if (!memcmp(dst, tbuf, len))
 			break;
 
 	} while (--count);
@@ -1016,6 +972,48 @@ static int ionic_get_module_eeprom(struct net_device *netdev,
 	return 0;
 }
 
+static int ionic_get_module_eeprom_by_page(struct net_device *netdev,
+					   const struct ethtool_module_eeprom *page_data,
+					   struct netlink_ext_ack *extack)
+{
+	struct ionic_lif *lif = netdev_priv(netdev);
+	struct ionic_dev *idev = &lif->ionic->idev;
+	u32 err = -EINVAL;
+	u8 *src;
+
+	if (!page_data->length)
+		return -EINVAL;
+
+	if (page_data->bank != 0) {
+		NL_SET_ERR_MSG_MOD(extack, "Only bank 0 is supported");
+		return -EINVAL;
+	}
+
+	switch (page_data->page) {
+	case 0:
+		src = &idev->port_info->status.xcvr.sprom[page_data->offset];
+		break;
+	case 1:
+		src = &idev->port_info->sprom_page1[page_data->offset - 128];
+		break;
+	case 2:
+		src = &idev->port_info->sprom_page2[page_data->offset - 128];
+		break;
+	case 17:
+		src = &idev->port_info->sprom_page17[page_data->offset - 128];
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	memset(page_data->data, 0, page_data->length);
+	err = ionic_do_module_copy(page_data->data, src, page_data->length);
+	if (err)
+		return err;
+
+	return page_data->length;
+}
+
 static int ionic_get_ts_info(struct net_device *netdev,
 			     struct kernel_ethtool_ts_info *info)
 {
@@ -1161,8 +1159,7 @@ static const struct ethtool_ops ionic_ethtool_ops = {
 	.set_rxfh		= ionic_set_rxfh,
 	.get_tunable		= ionic_get_tunable,
 	.set_tunable		= ionic_set_tunable,
-	.get_module_info	= ionic_get_module_info,
-	.get_module_eeprom	= ionic_get_module_eeprom,
+	.get_module_eeprom_by_page	= ionic_get_module_eeprom_by_page,
 	.get_pauseparam		= ionic_get_pauseparam,
 	.set_pauseparam		= ionic_set_pauseparam,
 	.get_fecparam		= ionic_get_fecparam,
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index 830c8adbfbee..f1ddbe9994a3 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -2839,6 +2839,10 @@ union ionic_port_identity {
  * @status:          Port status data
  * @stats:           Port statistics data
  * @mgmt_stats:      Port management statistics data
+ * @sprom_epage:     Extended Transceiver sprom
+ * @sprom_page1:     Extended Transceiver sprom, page 1
+ * @sprom_page2:     Extended Transceiver sprom, page 2
+ * @sprom_page17:    Extended Transceiver sprom, page 17
  * @rsvd:            reserved byte(s)
  * @pb_stats:        uplink pb drop stats
  */
@@ -2849,8 +2853,17 @@ struct ionic_port_info {
 		struct ionic_port_stats      stats;
 		struct ionic_mgmt_port_stats mgmt_stats;
 	};
-	/* room for pb_stats to start at 2k offset */
-	u8                          rsvd[760];
+	union {
+		u8     sprom_epage[384];
+		struct {
+			u8 sprom_page1[128];
+			u8 sprom_page2[128];
+			u8 sprom_page17[128];
+		};
+	};
+	u8     rsvd[376];
+
+	/* pb_stats must start at 2k offset */
 	struct ionic_port_pb_stats  pb_stats;
 };
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index b7def3b54937..016b575861b9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -939,7 +939,6 @@ u16 qed_get_cm_pq_idx_ofld_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 
 /* doorbell recovery mechanism */
-void qed_db_recovery_dp(struct qed_hwfn *p_hwfn);
 void qed_db_recovery_execute(struct qed_hwfn *p_hwfn);
 bool qed_edpm_enabled(struct qed_hwfn *p_hwfn);
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dbg_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_dbg_hsi.h
index f6cd1b3efdfd..27e91d0d39f8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dbg_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dbg_hsi.h
@@ -1305,37 +1305,6 @@ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn,
 					    char *results_buf);
 
 /**
- * qed_print_mcp_trace_results_cont(): Prints MCP Trace results, and
- * keeps the MCP trace meta data allocated, to support continuous MCP Trace
- * parsing. After the continuous parsing ends, mcp_trace_free_meta_data should
- * be called to free the meta data.
- *
- * @p_hwfn: HW device data.
- * @dump_buf: MVP trace dump buffer, starting from the header.
- * @results_buf: Buffer for printing the mcp trace results.
- *
- * Return: Error if the parsing fails, ok otherwise.
- */
-enum dbg_status qed_print_mcp_trace_results_cont(struct qed_hwfn *p_hwfn,
-						 u32 *dump_buf,
-						 char *results_buf);
-
-/**
- * qed_print_mcp_trace_line(): Prints MCP Trace results for a single line
- *
- * @p_hwfn: HW device data.
- * @dump_buf: MCP trace dump buffer, starting from the header.
- * @num_dumped_bytes: Number of bytes that were dumped.
- * @results_buf: Buffer for printing the mcp trace results.
- *
- * Return: Error if the parsing fails, ok otherwise.
- */
-enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn,
-					 u8 *dump_buf,
-					 u32 num_dumped_bytes,
-					 char *results_buf);
-
-/**
  * qed_mcp_trace_free_meta_data(): Frees the MCP Trace meta data.
  * Should be called after continuous MCP Trace parsing.
  *
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 464a72afb758..9c3d3dd2f847 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -7614,31 +7614,6 @@ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn,
 					results_buf, &parsed_buf_size, true);
 }
 
-enum dbg_status qed_print_mcp_trace_results_cont(struct qed_hwfn *p_hwfn,
-						 u32 *dump_buf,
-						 char *results_buf)
-{
-	u32 parsed_buf_size;
-
-	return qed_parse_mcp_trace_dump(p_hwfn, dump_buf, results_buf,
-					&parsed_buf_size, false);
-}
-
-enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn,
-					 u8 *dump_buf,
-					 u32 num_dumped_bytes,
-					 char *results_buf)
-{
-	u32 parsed_results_bytes;
-
-	return qed_parse_mcp_trace_buf(p_hwfn,
-				       dump_buf,
-				       num_dumped_bytes,
-				       0,
-				       num_dumped_bytes,
-				       results_buf, &parsed_results_bytes);
-}
-
 /* Frees the specified MCP Trace meta data */
 void qed_mcp_trace_free_meta_data(struct qed_hwfn *p_hwfn)
 {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 86a93cac2647..9659ce5b0712 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -255,25 +255,6 @@ static void qed_db_recovery_teardown(struct qed_hwfn *p_hwfn)
 	p_hwfn->db_recovery_info.db_recovery_counter = 0;
 }
 
-/* Print the content of the doorbell recovery mechanism */
-void qed_db_recovery_dp(struct qed_hwfn *p_hwfn)
-{
-	struct qed_db_recovery_entry *db_entry = NULL;
-
-	DP_NOTICE(p_hwfn,
-		  "Displaying doorbell recovery database. Counter was %d\n",
-		  p_hwfn->db_recovery_info.db_recovery_counter);
-
-	/* Protect the list */
-	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
-	list_for_each_entry(db_entry,
-			    &p_hwfn->db_recovery_info.list, list_entry) {
-		qed_db_recovery_dp_entry(p_hwfn, db_entry, "Printing");
-	}
-
-	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
-}
-
 /* Ring the doorbell of a single doorbell recovery entry */
 static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
 				 struct qed_db_recovery_entry *db_entry)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index ed1a84542ad2..10e355397cee 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -2666,58 +2666,6 @@ void qed_gft_config(struct qed_hwfn *p_hwfn,
 void qed_enable_context_validation(struct qed_hwfn *p_hwfn,
 				   struct qed_ptt *p_ptt);
 
-/**
- * qed_calc_session_ctx_validation(): Calcualte validation byte for
- *                                    session context.
- *
- * @p_ctx_mem: Pointer to context memory.
- * @ctx_size: Context size.
- * @ctx_type: Context type.
- * @cid: Context cid.
- *
- * Return: Void.
- */
-void qed_calc_session_ctx_validation(void *p_ctx_mem,
-				     u16 ctx_size, u8 ctx_type, u32 cid);
-
-/**
- * qed_calc_task_ctx_validation(): Calcualte validation byte for task
- *                                 context.
- *
- * @p_ctx_mem: Pointer to context memory.
- * @ctx_size: Context size.
- * @ctx_type: Context type.
- * @tid: Context tid.
- *
- * Return: Void.
- */
-void qed_calc_task_ctx_validation(void *p_ctx_mem,
-				  u16 ctx_size, u8 ctx_type, u32 tid);
-
-/**
- * qed_memset_session_ctx(): Memset session context to 0 while
- *                            preserving validation bytes.
- *
- * @p_ctx_mem: Pointer to context memory.
- * @ctx_size: Size to initialzie.
- * @ctx_type: Context type.
- *
- * Return: Void.
- */
-void qed_memset_session_ctx(void *p_ctx_mem, u32 ctx_size, u8 ctx_type);
-
-/**
- * qed_memset_task_ctx(): Memset task context to 0 while preserving
- *                        validation bytes.
- *
- * @p_ctx_mem: Pointer to context memory.
- * @ctx_size: size to initialzie.
- * @ctx_type: context type.
- *
- * Return: Void.
- */
-void qed_memset_task_ctx(void *p_ctx_mem, u32 ctx_size, u8 ctx_type);
-
 #define NUM_STORMS 6
 
 /**
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 9e5f0dbc8a07..9907973399dc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -69,17 +69,6 @@ int qed_ptt_pool_alloc(struct qed_hwfn *p_hwfn)
 	return 0;
 }
 
-void qed_ptt_invalidate(struct qed_hwfn *p_hwfn)
-{
-	struct qed_ptt *p_ptt;
-	int i;
-
-	for (i = 0; i < PXP_EXTERNAL_BAR_PF_WINDOW_NUM; i++) {
-		p_ptt = &p_hwfn->p_ptt_pool->ptts[i];
-		p_ptt->pxp.offset = QED_BAR_INVALID_OFFSET;
-	}
-}
-
 void qed_ptt_pool_free(struct qed_hwfn *p_hwfn)
 {
 	kfree(p_hwfn->p_ptt_pool);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.h b/drivers/net/ethernet/qlogic/qed/qed_hw.h
index e535983ce21b..3c98f58a184f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.h
@@ -62,15 +62,6 @@ enum _dmae_cmd_crc_mask {
 void qed_gtt_init(struct qed_hwfn *p_hwfn);
 
 /**
- * qed_ptt_invalidate(): Forces all ptt entries to be re-configured
- *
- * @p_hwfn: HW device data.
- *
- * Return: Void.
- */
-void qed_ptt_invalidate(struct qed_hwfn *p_hwfn);
-
-/**
  * qed_ptt_pool_alloc(): Allocate and initialize PTT pool.
  *
  * @p_hwfn: HW device data.
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index 407029a36fa1..aa20bb8caa9a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -18,16 +18,6 @@
 
 #define CDU_VALIDATION_DEFAULT_CFG CDU_CONTEXT_VALIDATION_DEFAULT_CFG
 
-static u16 con_region_offsets[3][NUM_OF_CONNECTION_TYPES] = {
-	{400, 336, 352, 368, 304, 384, 416, 352},	/* region 3 offsets */
-	{528, 496, 416, 512, 448, 512, 544, 480},	/* region 4 offsets */
-	{608, 544, 496, 576, 576, 592, 624, 560}	/* region 5 offsets */
-};
-
-static u16 task_region_offsets[1][NUM_OF_CONNECTION_TYPES] = {
-	{240, 240, 112, 0, 0, 0, 0, 96}	/* region 1 offsets */
-};
-
 /* General constants */
 #define QM_PQ_MEM_4KB(pq_size)	(pq_size ? DIV_ROUND_UP((pq_size + 1) *	\
 							QM_PQ_ELEMENT_SIZE, \
@@ -1576,134 +1566,6 @@ void qed_gft_config(struct qed_hwfn *p_hwfn,
 	qed_wr(p_hwfn, p_ptt, PRS_REG_SEARCH_GFT, 1);
 }
 
-DECLARE_CRC8_TABLE(cdu_crc8_table);
-
-/* Calculate and return CDU validation byte per connection type/region/cid */
-static u8 qed_calc_cdu_validation_byte(u8 conn_type, u8 region, u32 cid)
-{
-	const u8 validation_cfg = CDU_VALIDATION_DEFAULT_CFG;
-	u8 crc, validation_byte = 0;
-	static u8 crc8_table_valid; /* automatically initialized to 0 */
-	u32 validation_string = 0;
-	__be32 data_to_crc;
-
-	if (!crc8_table_valid) {
-		crc8_populate_msb(cdu_crc8_table, 0x07);
-		crc8_table_valid = 1;
-	}
-
-	/* The CRC is calculated on the String-to-compress:
-	 * [31:8]  = {CID[31:20],CID[11:0]}
-	 * [7:4]   = Region
-	 * [3:0]   = Type
-	 */
-	if ((validation_cfg >> CDU_CONTEXT_VALIDATION_CFG_USE_CID) & 1)
-		validation_string |= (cid & 0xFFF00000) | ((cid & 0xFFF) << 8);
-
-	if ((validation_cfg >> CDU_CONTEXT_VALIDATION_CFG_USE_REGION) & 1)
-		validation_string |= ((region & 0xF) << 4);
-
-	if ((validation_cfg >> CDU_CONTEXT_VALIDATION_CFG_USE_TYPE) & 1)
-		validation_string |= (conn_type & 0xF);
-
-	/* Convert to big-endian and calculate CRC8 */
-	data_to_crc = cpu_to_be32(validation_string);
-	crc = crc8(cdu_crc8_table, (u8 *)&data_to_crc, sizeof(data_to_crc),
-		   CRC8_INIT_VALUE);
-
-	/* The validation byte [7:0] is composed:
-	 * for type A validation
-	 * [7]          = active configuration bit
-	 * [6:0]        = crc[6:0]
-	 *
-	 * for type B validation
-	 * [7]          = active configuration bit
-	 * [6:3]        = connection_type[3:0]
-	 * [2:0]        = crc[2:0]
-	 */
-	validation_byte |=
-	    ((validation_cfg >>
-	      CDU_CONTEXT_VALIDATION_CFG_USE_ACTIVE) & 1) << 7;
-
-	if ((validation_cfg >>
-	     CDU_CONTEXT_VALIDATION_CFG_VALIDATION_TYPE_SHIFT) & 1)
-		validation_byte |= ((conn_type & 0xF) << 3) | (crc & 0x7);
-	else
-		validation_byte |= crc & 0x7F;
-
-	return validation_byte;
-}
-
-/* Calcualte and set validation bytes for session context */
-void qed_calc_session_ctx_validation(void *p_ctx_mem,
-				     u16 ctx_size, u8 ctx_type, u32 cid)
-{
-	u8 *x_val_ptr, *t_val_ptr, *u_val_ptr, *p_ctx;
-
-	p_ctx = (u8 * const)p_ctx_mem;
-	x_val_ptr = &p_ctx[con_region_offsets[0][ctx_type]];
-	t_val_ptr = &p_ctx[con_region_offsets[1][ctx_type]];
-	u_val_ptr = &p_ctx[con_region_offsets[2][ctx_type]];
-
-	memset(p_ctx, 0, ctx_size);
-
-	*x_val_ptr = qed_calc_cdu_validation_byte(ctx_type, 3, cid);
-	*t_val_ptr = qed_calc_cdu_validation_byte(ctx_type, 4, cid);
-	*u_val_ptr = qed_calc_cdu_validation_byte(ctx_type, 5, cid);
-}
-
-/* Calcualte and set validation bytes for task context */
-void qed_calc_task_ctx_validation(void *p_ctx_mem,
-				  u16 ctx_size, u8 ctx_type, u32 tid)
-{
-	u8 *p_ctx, *region1_val_ptr;
-
-	p_ctx = (u8 * const)p_ctx_mem;
-	region1_val_ptr = &p_ctx[task_region_offsets[0][ctx_type]];
-
-	memset(p_ctx, 0, ctx_size);
-
-	*region1_val_ptr = qed_calc_cdu_validation_byte(ctx_type, 1, tid);
-}
-
-/* Memset session context to 0 while preserving validation bytes */
-void qed_memset_session_ctx(void *p_ctx_mem, u32 ctx_size, u8 ctx_type)
-{
-	u8 *x_val_ptr, *t_val_ptr, *u_val_ptr, *p_ctx;
-	u8 x_val, t_val, u_val;
-
-	p_ctx = (u8 * const)p_ctx_mem;
-	x_val_ptr = &p_ctx[con_region_offsets[0][ctx_type]];
-	t_val_ptr = &p_ctx[con_region_offsets[1][ctx_type]];
-	u_val_ptr = &p_ctx[con_region_offsets[2][ctx_type]];
-
-	x_val = *x_val_ptr;
-	t_val = *t_val_ptr;
-	u_val = *u_val_ptr;
-
-	memset(p_ctx, 0, ctx_size);
-
-	*x_val_ptr = x_val;
-	*t_val_ptr = t_val;
-	*u_val_ptr = u_val;
-}
-
-/* Memset task context to 0 while preserving validation bytes */
-void qed_memset_task_ctx(void *p_ctx_mem, u32 ctx_size, u8 ctx_type)
-{
-	u8 *p_ctx, *region1_val_ptr;
-	u8 region1_val;
-
-	p_ctx = (u8 * const)p_ctx_mem;
-	region1_val_ptr = &p_ctx[task_region_offsets[0][ctx_type]];
-
-	region1_val = *region1_val_ptr;
-
-	memset(p_ctx, 0, ctx_size);
-
-	*region1_val_ptr = region1_val;
-}
-
 /* Enable and configure context validation */
 void qed_enable_context_validation(struct qed_hwfn *p_hwfn,
 				   struct qed_ptt *p_ptt)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 99df00c30b8c..b5d744d2586f 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -203,7 +203,7 @@ static struct pci_driver qede_pci_driver = {
 };
 
 static struct qed_eth_cb_ops qede_ll_ops = {
-	{
+	.common = {
 #ifdef CONFIG_RFS_ACCEL
 		.arfs_filter_op = qede_arfs_filter_op,
 #endif
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index 28d24d59efb8..d57b976b9040 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -1484,8 +1484,11 @@ static int qlcnic_sriov_channel_cfg_cmd(struct qlcnic_adapter *adapter, u8 cmd_o
 	}
 
 	cmd_op = (cmd.rsp.arg[0] & 0xff);
-	if (cmd.rsp.arg[0] >> 25 == 2)
-		return 2;
+	if (cmd.rsp.arg[0] >> 25 == 2) {
+		ret = 2;
+		goto out;
+	}
+
 	if (cmd_op == QLCNIC_BC_CMD_CHANNEL_INIT)
 		set_bit(QLC_BC_VF_STATE, &vf->state);
 	else
diff --git a/drivers/net/ethernet/qualcomm/Kconfig b/drivers/net/ethernet/qualcomm/Kconfig
index 9210ff360fdc..a4434eb38950 100644
--- a/drivers/net/ethernet/qualcomm/Kconfig
+++ b/drivers/net/ethernet/qualcomm/Kconfig
@@ -52,7 +52,6 @@ config QCOM_EMAC
 	depends on HAS_DMA && HAS_IOMEM
 	select CRC32
 	select PHYLIB
-	select MDIO_DEVRES
 	help
 	  This driver supports the Qualcomm Technologies, Inc. Gigabit
 	  Ethernet Media Access Controller (EMAC). The controller
diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h
index 7a194a8ab989..2c1a0c21af8d 100644
--- a/drivers/net/ethernet/realtek/r8169.h
+++ b/drivers/net/ethernet/realtek/r8169.h
@@ -64,16 +64,15 @@ enum mac_version {
 	/* support for RTL_GIGA_MAC_VER_50 has been removed */
 	RTL_GIGA_MAC_VER_51,
 	RTL_GIGA_MAC_VER_52,
-	RTL_GIGA_MAC_VER_53,
 	/* support for RTL_GIGA_MAC_VER_60 has been removed */
 	RTL_GIGA_MAC_VER_61,
 	RTL_GIGA_MAC_VER_63,
 	RTL_GIGA_MAC_VER_64,
-	RTL_GIGA_MAC_VER_65,
 	RTL_GIGA_MAC_VER_66,
 	RTL_GIGA_MAC_VER_70,
-	RTL_GIGA_MAC_VER_71,
-	RTL_GIGA_MAC_NONE
+	RTL_GIGA_MAC_VER_80,
+	RTL_GIGA_MAC_NONE,
+	RTL_GIGA_MAC_VER_LAST = RTL_GIGA_MAC_NONE - 1
 };
 
 struct rtl8169_private;
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 8e62b109518b..43170500d566 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -60,6 +60,7 @@
 #define FIRMWARE_8125BP_2	"rtl_nic/rtl8125bp-2.fw"
 #define FIRMWARE_8126A_2	"rtl_nic/rtl8126a-2.fw"
 #define FIRMWARE_8126A_3	"rtl_nic/rtl8126a-3.fw"
+#define FIRMWARE_8127A_1	"rtl_nic/rtl8127a-1.fw"
 
 #define TX_DMA_BURST	7	/* Maximum PCI burst, '7' is unlimited */
 #define InterFrameGap	0x03	/* 3 means InterFrameGap = the shortest one */
@@ -91,61 +92,117 @@
 #define JUMBO_9K	(9 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
 #define JUMBO_16K	(SZ_16K - VLAN_ETH_HLEN - ETH_FCS_LEN)
 
-static const struct {
+static const struct rtl_chip_info {
+	u16 mask;
+	u16 val;
+	enum mac_version mac_version;
 	const char *name;
 	const char *fw_name;
 } rtl_chip_infos[] = {
-	/* PCI devices. */
-	[RTL_GIGA_MAC_VER_02] = {"RTL8169s"				},
-	[RTL_GIGA_MAC_VER_03] = {"RTL8110s"				},
-	[RTL_GIGA_MAC_VER_04] = {"RTL8169sb/8110sb"			},
-	[RTL_GIGA_MAC_VER_05] = {"RTL8169sc/8110sc"			},
-	[RTL_GIGA_MAC_VER_06] = {"RTL8169sc/8110sc"			},
-	/* PCI-E devices. */
-	[RTL_GIGA_MAC_VER_07] = {"RTL8102e"				},
-	[RTL_GIGA_MAC_VER_08] = {"RTL8102e"				},
-	[RTL_GIGA_MAC_VER_09] = {"RTL8102e/RTL8103e"			},
-	[RTL_GIGA_MAC_VER_10] = {"RTL8101e/RTL8100e"			},
-	[RTL_GIGA_MAC_VER_14] = {"RTL8401"				},
-	[RTL_GIGA_MAC_VER_17] = {"RTL8168b/8111b"			},
-	[RTL_GIGA_MAC_VER_18] = {"RTL8168cp/8111cp"			},
-	[RTL_GIGA_MAC_VER_19] = {"RTL8168c/8111c"			},
-	[RTL_GIGA_MAC_VER_20] = {"RTL8168c/8111c"			},
-	[RTL_GIGA_MAC_VER_21] = {"RTL8168c/8111c"			},
-	[RTL_GIGA_MAC_VER_22] = {"RTL8168c/8111c"			},
-	[RTL_GIGA_MAC_VER_23] = {"RTL8168cp/8111cp"			},
-	[RTL_GIGA_MAC_VER_24] = {"RTL8168cp/8111cp"			},
-	[RTL_GIGA_MAC_VER_25] = {"RTL8168d/8111d",	FIRMWARE_8168D_1},
-	[RTL_GIGA_MAC_VER_26] = {"RTL8168d/8111d",	FIRMWARE_8168D_2},
-	[RTL_GIGA_MAC_VER_28] = {"RTL8168dp/8111dp"			},
-	[RTL_GIGA_MAC_VER_29] = {"RTL8105e",		FIRMWARE_8105E_1},
-	[RTL_GIGA_MAC_VER_30] = {"RTL8105e",		FIRMWARE_8105E_1},
-	[RTL_GIGA_MAC_VER_31] = {"RTL8168dp/8111dp"			},
-	[RTL_GIGA_MAC_VER_32] = {"RTL8168e/8111e",	FIRMWARE_8168E_1},
-	[RTL_GIGA_MAC_VER_33] = {"RTL8168e/8111e",	FIRMWARE_8168E_2},
-	[RTL_GIGA_MAC_VER_34] = {"RTL8168evl/8111evl",	FIRMWARE_8168E_3},
-	[RTL_GIGA_MAC_VER_35] = {"RTL8168f/8111f",	FIRMWARE_8168F_1},
-	[RTL_GIGA_MAC_VER_36] = {"RTL8168f/8111f",	FIRMWARE_8168F_2},
-	[RTL_GIGA_MAC_VER_37] = {"RTL8402",		FIRMWARE_8402_1 },
-	[RTL_GIGA_MAC_VER_38] = {"RTL8411",		FIRMWARE_8411_1 },
-	[RTL_GIGA_MAC_VER_39] = {"RTL8106e",		FIRMWARE_8106E_1},
-	[RTL_GIGA_MAC_VER_40] = {"RTL8168g/8111g",	FIRMWARE_8168G_2},
-	[RTL_GIGA_MAC_VER_42] = {"RTL8168gu/8111gu",	FIRMWARE_8168G_3},
-	[RTL_GIGA_MAC_VER_43] = {"RTL8106eus",		FIRMWARE_8106E_2},
-	[RTL_GIGA_MAC_VER_44] = {"RTL8411b",		FIRMWARE_8411_2 },
-	[RTL_GIGA_MAC_VER_46] = {"RTL8168h/8111h",	FIRMWARE_8168H_2},
-	[RTL_GIGA_MAC_VER_48] = {"RTL8107e",		FIRMWARE_8107E_2},
-	[RTL_GIGA_MAC_VER_51] = {"RTL8168ep/8111ep"			},
-	[RTL_GIGA_MAC_VER_52] = {"RTL8168fp/RTL8117",  FIRMWARE_8168FP_3},
-	[RTL_GIGA_MAC_VER_53] = {"RTL8168fp/RTL8117",			},
-	[RTL_GIGA_MAC_VER_61] = {"RTL8125A",		FIRMWARE_8125A_3},
-	/* reserve 62 for CFG_METHOD_4 in the vendor driver */
-	[RTL_GIGA_MAC_VER_63] = {"RTL8125B",		FIRMWARE_8125B_2},
-	[RTL_GIGA_MAC_VER_64] = {"RTL8125D",		FIRMWARE_8125D_1},
-	[RTL_GIGA_MAC_VER_65] = {"RTL8125D",		FIRMWARE_8125D_2},
-	[RTL_GIGA_MAC_VER_66] = {"RTL8125BP",		FIRMWARE_8125BP_2},
-	[RTL_GIGA_MAC_VER_70] = {"RTL8126A",		FIRMWARE_8126A_2},
-	[RTL_GIGA_MAC_VER_71] = {"RTL8126A",		FIRMWARE_8126A_3},
+	/* 8127A family. */
+	{ 0x7cf, 0x6c9,	RTL_GIGA_MAC_VER_80, "RTL8127A", FIRMWARE_8127A_1 },
+
+	/* 8126A family. */
+	{ 0x7cf, 0x64a,	RTL_GIGA_MAC_VER_70, "RTL8126A", FIRMWARE_8126A_3 },
+	{ 0x7cf, 0x649,	RTL_GIGA_MAC_VER_70, "RTL8126A", FIRMWARE_8126A_2 },
+
+	/* 8125BP family. */
+	{ 0x7cf, 0x681,	RTL_GIGA_MAC_VER_66, "RTL8125BP", FIRMWARE_8125BP_2 },
+
+	/* 8125D family. */
+	{ 0x7cf, 0x689,	RTL_GIGA_MAC_VER_64, "RTL8125D", FIRMWARE_8125D_2 },
+	{ 0x7cf, 0x688,	RTL_GIGA_MAC_VER_64, "RTL8125D", FIRMWARE_8125D_1 },
+
+	/* 8125B family. */
+	{ 0x7cf, 0x641,	RTL_GIGA_MAC_VER_63, "RTL8125B", FIRMWARE_8125B_2 },
+
+	/* 8125A family. */
+	{ 0x7cf, 0x609,	RTL_GIGA_MAC_VER_61, "RTL8125A", FIRMWARE_8125A_3 },
+
+	/* RTL8117 */
+	{ 0x7cf, 0x54b,	RTL_GIGA_MAC_VER_52, "RTL8168fp/RTL8117" },
+	{ 0x7cf, 0x54a,	RTL_GIGA_MAC_VER_52, "RTL8168fp/RTL8117",
+	  FIRMWARE_8168FP_3 },
+
+	/* 8168EP family. */
+	{ 0x7cf, 0x502,	RTL_GIGA_MAC_VER_51, "RTL8168ep/8111ep" },
+
+	/* 8168H family. */
+	{ 0x7cf, 0x541,	RTL_GIGA_MAC_VER_46, "RTL8168h/8111h",
+	  FIRMWARE_8168H_2 },
+	/* Realtek calls it RTL8168M, but it's handled like RTL8168H */
+	{ 0x7cf, 0x6c0,	RTL_GIGA_MAC_VER_46, "RTL8168M", FIRMWARE_8168H_2 },
+
+	/* 8168G family. */
+	{ 0x7cf, 0x5c8,	RTL_GIGA_MAC_VER_44, "RTL8411b", FIRMWARE_8411_2 },
+	{ 0x7cf, 0x509,	RTL_GIGA_MAC_VER_42, "RTL8168gu/8111gu",
+	  FIRMWARE_8168G_3 },
+	{ 0x7cf, 0x4c0,	RTL_GIGA_MAC_VER_40, "RTL8168g/8111g",
+	  FIRMWARE_8168G_2 },
+
+	/* 8168F family. */
+	{ 0x7c8, 0x488,	RTL_GIGA_MAC_VER_38, "RTL8411", FIRMWARE_8411_1 },
+	{ 0x7cf, 0x481,	RTL_GIGA_MAC_VER_36, "RTL8168f/8111f",
+	  FIRMWARE_8168F_2 },
+	{ 0x7cf, 0x480,	RTL_GIGA_MAC_VER_35, "RTL8168f/8111f",
+	  FIRMWARE_8168F_1 },
+
+	/* 8168E family. */
+	{ 0x7c8, 0x2c8,	RTL_GIGA_MAC_VER_34, "RTL8168evl/8111evl",
+	  FIRMWARE_8168E_3 },
+	{ 0x7cf, 0x2c1,	RTL_GIGA_MAC_VER_32, "RTL8168e/8111e",
+	  FIRMWARE_8168E_1 },
+	{ 0x7c8, 0x2c0,	RTL_GIGA_MAC_VER_33, "RTL8168e/8111e",
+	  FIRMWARE_8168E_2 },
+
+	/* 8168D family. */
+	{ 0x7cf, 0x281,	RTL_GIGA_MAC_VER_25, "RTL8168d/8111d",
+	  FIRMWARE_8168D_1 },
+	{ 0x7c8, 0x280,	RTL_GIGA_MAC_VER_26, "RTL8168d/8111d",
+	  FIRMWARE_8168D_2 },
+
+	/* 8168DP family. */
+	{ 0x7cf, 0x28a,	RTL_GIGA_MAC_VER_28, "RTL8168dp/8111dp" },
+	{ 0x7cf, 0x28b,	RTL_GIGA_MAC_VER_31, "RTL8168dp/8111dp" },
+
+	/* 8168C family. */
+	{ 0x7cf, 0x3c9,	RTL_GIGA_MAC_VER_23, "RTL8168cp/8111cp" },
+	{ 0x7cf, 0x3c8,	RTL_GIGA_MAC_VER_18, "RTL8168cp/8111cp" },
+	{ 0x7c8, 0x3c8,	RTL_GIGA_MAC_VER_24, "RTL8168cp/8111cp" },
+	{ 0x7cf, 0x3c0,	RTL_GIGA_MAC_VER_19, "RTL8168c/8111c" },
+	{ 0x7cf, 0x3c2,	RTL_GIGA_MAC_VER_20, "RTL8168c/8111c" },
+	{ 0x7cf, 0x3c3,	RTL_GIGA_MAC_VER_21, "RTL8168c/8111c" },
+	{ 0x7c8, 0x3c0,	RTL_GIGA_MAC_VER_22, "RTL8168c/8111c" },
+
+	/* 8168B family. */
+	{ 0x7c8, 0x380,	RTL_GIGA_MAC_VER_17, "RTL8168b/8111b" },
+	/* This one is very old and rare, support has been removed.
+	 * { 0x7c8, 0x300, RTL_GIGA_MAC_VER_11, "RTL8168b/8111b" },
+	 */
+
+	/* 8101 family. */
+	{ 0x7c8, 0x448,	RTL_GIGA_MAC_VER_39, "RTL8106e", FIRMWARE_8106E_1 },
+	{ 0x7c8, 0x440,	RTL_GIGA_MAC_VER_37, "RTL8402", FIRMWARE_8402_1 },
+	{ 0x7cf, 0x409,	RTL_GIGA_MAC_VER_29, "RTL8105e", FIRMWARE_8105E_1 },
+	{ 0x7c8, 0x408,	RTL_GIGA_MAC_VER_30, "RTL8105e", FIRMWARE_8105E_1 },
+	{ 0x7cf, 0x349,	RTL_GIGA_MAC_VER_08, "RTL8102e" },
+	{ 0x7cf, 0x249,	RTL_GIGA_MAC_VER_08, "RTL8102e" },
+	{ 0x7cf, 0x348,	RTL_GIGA_MAC_VER_07, "RTL8102e" },
+	{ 0x7cf, 0x248,	RTL_GIGA_MAC_VER_07, "RTL8102e" },
+	{ 0x7cf, 0x240,	RTL_GIGA_MAC_VER_14, "RTL8401" },
+	{ 0x7c8, 0x348,	RTL_GIGA_MAC_VER_09, "RTL8102e/RTL8103e" },
+	{ 0x7c8, 0x248,	RTL_GIGA_MAC_VER_09, "RTL8102e/RTL8103e" },
+	{ 0x7c8, 0x340,	RTL_GIGA_MAC_VER_10, "RTL8101e/RTL8100e" },
+
+	/* 8110 family. */
+	{ 0xfc8, 0x980,	RTL_GIGA_MAC_VER_06, "RTL8169sc/8110sc" },
+	{ 0xfc8, 0x180,	RTL_GIGA_MAC_VER_05, "RTL8169sc/8110sc" },
+	{ 0xfc8, 0x100,	RTL_GIGA_MAC_VER_04, "RTL8169sb/8110sb" },
+	{ 0xfc8, 0x040,	RTL_GIGA_MAC_VER_03, "RTL8110s" },
+	{ 0xfc8, 0x008,	RTL_GIGA_MAC_VER_02, "RTL8169s" },
+
+	/* Catch-all */
+	{ 0x000, 0x000,	RTL_GIGA_MAC_NONE }
 };
 
 static const struct pci_device_id rtl8169_pci_tbl[] = {
@@ -169,8 +226,10 @@ static const struct pci_device_id rtl8169_pci_tbl[] = {
 	{ 0x0001, 0x8168, PCI_ANY_ID, 0x2410 },
 	{ PCI_VDEVICE(REALTEK,	0x8125) },
 	{ PCI_VDEVICE(REALTEK,	0x8126) },
+	{ PCI_VDEVICE(REALTEK,	0x8127) },
 	{ PCI_VDEVICE(REALTEK,	0x3000) },
 	{ PCI_VDEVICE(REALTEK,	0x5000) },
+	{ PCI_VDEVICE(REALTEK,	0x0e10) },
 	{}
 };
 
@@ -716,6 +775,7 @@ MODULE_FIRMWARE(FIRMWARE_8125D_2);
 MODULE_FIRMWARE(FIRMWARE_8125BP_2);
 MODULE_FIRMWARE(FIRMWARE_8126A_2);
 MODULE_FIRMWARE(FIRMWARE_8126A_3);
+MODULE_FIRMWARE(FIRMWARE_8127A_1);
 
 static inline struct device *tp_to_dev(struct rtl8169_private *tp)
 {
@@ -777,7 +837,7 @@ static bool rtl_is_8168evl_up(struct rtl8169_private *tp)
 {
 	return tp->mac_version >= RTL_GIGA_MAC_VER_34 &&
 	       tp->mac_version != RTL_GIGA_MAC_VER_39 &&
-	       tp->mac_version <= RTL_GIGA_MAC_VER_53;
+	       tp->mac_version <= RTL_GIGA_MAC_VER_52;
 }
 
 static bool rtl_supports_eee(struct rtl8169_private *tp)
@@ -945,9 +1005,7 @@ void r8169_get_led_name(struct rtl8169_private *tp, int idx,
 static void r8168fp_adjust_ocp_cmd(struct rtl8169_private *tp, u32 *cmd, int type)
 {
 	/* based on RTL8168FP_OOBMAC_BASE in vendor driver */
-	if (type == ERIAR_OOB &&
-	    (tp->mac_version == RTL_GIGA_MAC_VER_52 ||
-	     tp->mac_version == RTL_GIGA_MAC_VER_53))
+	if (type == ERIAR_OOB && tp->mac_version == RTL_GIGA_MAC_VER_52)
 		*cmd |= 0xf70 << 18;
 }
 
@@ -1236,7 +1294,7 @@ static void rtl_writephy(struct rtl8169_private *tp, int location, int val)
 	case RTL_GIGA_MAC_VER_31:
 		r8168dp_2_mdio_write(tp, location, val);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_LAST:
 		r8168g_mdio_write(tp, location, val);
 		break;
 	default:
@@ -1251,7 +1309,7 @@ static int rtl_readphy(struct rtl8169_private *tp, int location)
 	case RTL_GIGA_MAC_VER_28:
 	case RTL_GIGA_MAC_VER_31:
 		return r8168dp_2_mdio_read(tp, location);
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_LAST:
 		return r8168g_mdio_read(tp, location);
 	default:
 		return r8169_mdio_read(tp, location);
@@ -1447,7 +1505,7 @@ static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_28:
 	case RTL_GIGA_MAC_VER_31:
 		return RTL_DASH_DP;
-	case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_53:
+	case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_52:
 		return RTL_DASH_EP;
 	case RTL_GIGA_MAC_VER_66:
 		return RTL_DASH_25_BP;
@@ -1603,7 +1661,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 		break;
 	case RTL_GIGA_MAC_VER_34:
 	case RTL_GIGA_MAC_VER_37:
-	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_LAST:
 		r8169_mod_reg8_cond(tp, Config2, PME_SIGNAL, wolopts);
 		break;
 	default:
@@ -2076,7 +2134,7 @@ static void rtl_set_eee_txidle_timer(struct rtl8169_private *tp)
 		tp->tx_lpi_timer = timer_val;
 		r8168_mac_ocp_write(tp, 0xe048, timer_val);
 		break;
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
 		tp->tx_lpi_timer = timer_val;
 		RTL_W16(tp, EEE_TXIDLE_TIMER_8125, timer_val);
 		break;
@@ -2265,151 +2323,30 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_eth_ctrl_stats	= rtl8169_get_eth_ctrl_stats,
 };
 
-static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii)
+static const struct rtl_chip_info *rtl8169_get_chip_version(u16 xid, bool gmii)
 {
-	/*
-	 * The driver currently handles the 8168Bf and the 8168Be identically
-	 * but they can be identified more specifically through the test below
-	 * if needed:
-	 *
-	 * (RTL_R32(tp, TxConfig) & 0x700000) == 0x500000 ? 8168Bf : 8168Be
-	 *
-	 * Same thing for the 8101Eb and the 8101Ec:
-	 *
-	 * (RTL_R32(tp, TxConfig) & 0x700000) == 0x200000 ? 8101Eb : 8101Ec
-	 */
-	static const struct rtl_mac_info {
-		u16 mask;
-		u16 val;
-		enum mac_version ver;
-	} mac_info[] = {
-		/* 8126A family. */
-		{ 0x7cf, 0x64a,	RTL_GIGA_MAC_VER_71 },
-		{ 0x7cf, 0x649,	RTL_GIGA_MAC_VER_70 },
-
-		/* 8125BP family. */
-		{ 0x7cf, 0x681,	RTL_GIGA_MAC_VER_66 },
-
-		/* 8125D family. */
-		{ 0x7cf, 0x689,	RTL_GIGA_MAC_VER_65 },
-		{ 0x7cf, 0x688,	RTL_GIGA_MAC_VER_64 },
-
-		/* 8125B family. */
-		{ 0x7cf, 0x641,	RTL_GIGA_MAC_VER_63 },
-
-		/* 8125A family. */
-		{ 0x7cf, 0x609,	RTL_GIGA_MAC_VER_61 },
-		/* It seems only XID 609 made it to the mass market.
-		 * { 0x7cf, 0x608,	RTL_GIGA_MAC_VER_60 },
-		 * { 0x7c8, 0x608,	RTL_GIGA_MAC_VER_61 },
-		 */
-
-		/* RTL8117 */
-		{ 0x7cf, 0x54b,	RTL_GIGA_MAC_VER_53 },
-		{ 0x7cf, 0x54a,	RTL_GIGA_MAC_VER_52 },
-
-		/* 8168EP family. */
-		{ 0x7cf, 0x502,	RTL_GIGA_MAC_VER_51 },
-		/* It seems this chip version never made it to
-		 * the wild. Let's disable detection.
-		 * { 0x7cf, 0x501,      RTL_GIGA_MAC_VER_50 },
-		 * { 0x7cf, 0x500,      RTL_GIGA_MAC_VER_49 },
-		 */
-
-		/* 8168H family. */
-		{ 0x7cf, 0x541,	RTL_GIGA_MAC_VER_46 },
-		/* It seems this chip version never made it to
-		 * the wild. Let's disable detection.
-		 * { 0x7cf, 0x540,	RTL_GIGA_MAC_VER_45 },
-		 */
-		/* Realtek calls it RTL8168M, but it's handled like RTL8168H */
-		{ 0x7cf, 0x6c0,	RTL_GIGA_MAC_VER_46 },
-
-		/* 8168G family. */
-		{ 0x7cf, 0x5c8,	RTL_GIGA_MAC_VER_44 },
-		{ 0x7cf, 0x509,	RTL_GIGA_MAC_VER_42 },
-		/* It seems this chip version never made it to
-		 * the wild. Let's disable detection.
-		 * { 0x7cf, 0x4c1,	RTL_GIGA_MAC_VER_41 },
-		 */
-		{ 0x7cf, 0x4c0,	RTL_GIGA_MAC_VER_40 },
-
-		/* 8168F family. */
-		{ 0x7c8, 0x488,	RTL_GIGA_MAC_VER_38 },
-		{ 0x7cf, 0x481,	RTL_GIGA_MAC_VER_36 },
-		{ 0x7cf, 0x480,	RTL_GIGA_MAC_VER_35 },
-
-		/* 8168E family. */
-		{ 0x7c8, 0x2c8,	RTL_GIGA_MAC_VER_34 },
-		{ 0x7cf, 0x2c1,	RTL_GIGA_MAC_VER_32 },
-		{ 0x7c8, 0x2c0,	RTL_GIGA_MAC_VER_33 },
-
-		/* 8168D family. */
-		{ 0x7cf, 0x281,	RTL_GIGA_MAC_VER_25 },
-		{ 0x7c8, 0x280,	RTL_GIGA_MAC_VER_26 },
-
-		/* 8168DP family. */
-		/* It seems this early RTL8168dp version never made it to
-		 * the wild. Support has been removed.
-		 * { 0x7cf, 0x288,      RTL_GIGA_MAC_VER_27 },
-		 */
-		{ 0x7cf, 0x28a,	RTL_GIGA_MAC_VER_28 },
-		{ 0x7cf, 0x28b,	RTL_GIGA_MAC_VER_31 },
-
-		/* 8168C family. */
-		{ 0x7cf, 0x3c9,	RTL_GIGA_MAC_VER_23 },
-		{ 0x7cf, 0x3c8,	RTL_GIGA_MAC_VER_18 },
-		{ 0x7c8, 0x3c8,	RTL_GIGA_MAC_VER_24 },
-		{ 0x7cf, 0x3c0,	RTL_GIGA_MAC_VER_19 },
-		{ 0x7cf, 0x3c2,	RTL_GIGA_MAC_VER_20 },
-		{ 0x7cf, 0x3c3,	RTL_GIGA_MAC_VER_21 },
-		{ 0x7c8, 0x3c0,	RTL_GIGA_MAC_VER_22 },
-
-		/* 8168B family. */
-		{ 0x7c8, 0x380,	RTL_GIGA_MAC_VER_17 },
-		/* This one is very old and rare, support has been removed.
-		 * { 0x7c8, 0x300,	RTL_GIGA_MAC_VER_11 },
-		 */
-
-		/* 8101 family. */
-		{ 0x7c8, 0x448,	RTL_GIGA_MAC_VER_39 },
-		{ 0x7c8, 0x440,	RTL_GIGA_MAC_VER_37 },
-		{ 0x7cf, 0x409,	RTL_GIGA_MAC_VER_29 },
-		{ 0x7c8, 0x408,	RTL_GIGA_MAC_VER_30 },
-		{ 0x7cf, 0x349,	RTL_GIGA_MAC_VER_08 },
-		{ 0x7cf, 0x249,	RTL_GIGA_MAC_VER_08 },
-		{ 0x7cf, 0x348,	RTL_GIGA_MAC_VER_07 },
-		{ 0x7cf, 0x248,	RTL_GIGA_MAC_VER_07 },
-		{ 0x7cf, 0x240,	RTL_GIGA_MAC_VER_14 },
-		{ 0x7c8, 0x348,	RTL_GIGA_MAC_VER_09 },
-		{ 0x7c8, 0x248,	RTL_GIGA_MAC_VER_09 },
-		{ 0x7c8, 0x340,	RTL_GIGA_MAC_VER_10 },
-
-		/* 8110 family. */
-		{ 0xfc8, 0x980,	RTL_GIGA_MAC_VER_06 },
-		{ 0xfc8, 0x180,	RTL_GIGA_MAC_VER_05 },
-		{ 0xfc8, 0x100,	RTL_GIGA_MAC_VER_04 },
-		{ 0xfc8, 0x040,	RTL_GIGA_MAC_VER_03 },
-		{ 0xfc8, 0x008,	RTL_GIGA_MAC_VER_02 },
-
-		/* Catch-all */
-		{ 0x000, 0x000,	RTL_GIGA_MAC_NONE   }
+	/* Chips combining a 1Gbps MAC with a 100Mbps PHY */
+	static const struct rtl_chip_info rtl8106eus_info = {
+		.mac_version = RTL_GIGA_MAC_VER_43,
+		.name = "RTL8106eus",
+		.fw_name = FIRMWARE_8106E_2,
+	};
+	static const struct rtl_chip_info rtl8107e_info = {
+		.mac_version = RTL_GIGA_MAC_VER_48,
+		.name = "RTL8107e",
+		.fw_name = FIRMWARE_8107E_2,
 	};
-	const struct rtl_mac_info *p = mac_info;
-	enum mac_version ver;
+	const struct rtl_chip_info *p = rtl_chip_infos;
 
 	while ((xid & p->mask) != p->val)
 		p++;
-	ver = p->ver;
 
-	if (ver != RTL_GIGA_MAC_NONE && !gmii) {
-		if (ver == RTL_GIGA_MAC_VER_42)
-			ver = RTL_GIGA_MAC_VER_43;
-		else if (ver == RTL_GIGA_MAC_VER_46)
-			ver = RTL_GIGA_MAC_VER_48;
-	}
+	if (p->mac_version == RTL_GIGA_MAC_VER_42 && !gmii)
+		return &rtl8106eus_info;
+	if (p->mac_version == RTL_GIGA_MAC_VER_46 && !gmii)
+		return &rtl8107e_info;
 
-	return ver;
+	return p;
 }
 
 static void rtl_release_firmware(struct rtl8169_private *tp)
@@ -2553,13 +2490,13 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_38:
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_52:
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
 		break;
 	case RTL_GIGA_MAC_VER_61:
 		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST);
 		break;
-	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_LAST:
 		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST |
 			RX_PAUSE_SLOT_ON);
 		break;
@@ -2684,14 +2621,14 @@ DECLARE_RTL_COND(rtl_rxtx_empty_cond_2)
 static void rtl_wait_txrx_fifo_empty(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_52:
 		rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 42);
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
 		break;
 	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_61:
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
 		break;
-	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_LAST:
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond_2, 100, 42);
@@ -2966,7 +2903,7 @@ static void rtl_enable_exit_l1(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_38:
 		rtl_eri_set_bits(tp, 0xd4, 0x0c00);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_LAST:
 		r8168_mac_ocp_modify(tp, 0xc0ac, 0, 0x1f80);
 		break;
 	default:
@@ -2980,7 +2917,7 @@ static void rtl_disable_exit_l1(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
 		rtl_eri_clear_bits(tp, 0xd4, 0x1f00);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_LAST:
 		r8168_mac_ocp_modify(tp, 0xc0ac, 0x1f80, 0);
 		break;
 	default:
@@ -3007,7 +2944,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 		rtl_mod_config5(tp, 0, ASPM_en);
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_70:
-		case RTL_GIGA_MAC_VER_71:
+		case RTL_GIGA_MAC_VER_80:
 			val8 = RTL_R8(tp, INT_CFG0_8125) | INT_CFG0_CLKREQEN;
 			RTL_W8(tp, INT_CFG0_8125, val8);
 			break;
@@ -3018,7 +2955,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
-		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
+		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
 			/* reset ephy tx/rx disable timer */
 			r8168_mac_ocp_modify(tp, 0xe094, 0xff00, 0);
 			/* chip can trigger L1.2 */
@@ -3030,7 +2967,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 	} else {
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
-		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
+		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
 			r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, 0);
 			break;
 		default:
@@ -3039,7 +2976,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_70:
-		case RTL_GIGA_MAC_VER_71:
+		case RTL_GIGA_MAC_VER_80:
 			val8 = RTL_R8(tp, INT_CFG0_8125) & ~INT_CFG0_CLKREQEN;
 			RTL_W8(tp, INT_CFG0_8125, val8);
 			break;
@@ -3760,11 +3697,12 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
 	r8168_mac_ocp_modify(tp, 0xeb58, 0x0001, 0x0000);
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_70 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_71)
+	    tp->mac_version == RTL_GIGA_MAC_VER_80)
 		RTL_W8(tp, 0xD8, RTL_R8(tp, 0xD8) & ~0x02);
 
-	if (tp->mac_version == RTL_GIGA_MAC_VER_70 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_71)
+	if (tp->mac_version == RTL_GIGA_MAC_VER_80)
+		r8168_mac_ocp_modify(tp, 0xe614, 0x0f00, 0x0f00);
+	else if (tp->mac_version == RTL_GIGA_MAC_VER_70)
 		r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0400);
 	else if (tp->mac_version == RTL_GIGA_MAC_VER_63)
 		r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0200);
@@ -3783,7 +3721,7 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
 	r8168_mac_ocp_modify(tp, 0xe040, 0x1000, 0x0000);
 	r8168_mac_ocp_modify(tp, 0xea1c, 0x0003, 0x0001);
 	if (tp->mac_version == RTL_GIGA_MAC_VER_70 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_71)
+	    tp->mac_version == RTL_GIGA_MAC_VER_80)
 		r8168_mac_ocp_modify(tp, 0xea1c, 0x0300, 0x0000);
 	else
 		r8168_mac_ocp_modify(tp, 0xea1c, 0x0004, 0x0000);
@@ -3861,6 +3799,12 @@ static void rtl_hw_start_8126a(struct rtl8169_private *tp)
 	rtl_hw_start_8125_common(tp);
 }
 
+static void rtl_hw_start_8127a(struct rtl8169_private *tp)
+{
+	rtl_set_def_aspm_entry_latency(tp);
+	rtl_hw_start_8125_common(tp);
+}
+
 static void rtl_hw_config(struct rtl8169_private *tp)
 {
 	static const rtl_generic_fct hw_configs[] = {
@@ -3899,14 +3843,12 @@ static void rtl_hw_config(struct rtl8169_private *tp)
 		[RTL_GIGA_MAC_VER_48] = rtl_hw_start_8168h_1,
 		[RTL_GIGA_MAC_VER_51] = rtl_hw_start_8168ep_3,
 		[RTL_GIGA_MAC_VER_52] = rtl_hw_start_8117,
-		[RTL_GIGA_MAC_VER_53] = rtl_hw_start_8117,
 		[RTL_GIGA_MAC_VER_61] = rtl_hw_start_8125a_2,
 		[RTL_GIGA_MAC_VER_63] = rtl_hw_start_8125b,
 		[RTL_GIGA_MAC_VER_64] = rtl_hw_start_8125d,
-		[RTL_GIGA_MAC_VER_65] = rtl_hw_start_8125d,
 		[RTL_GIGA_MAC_VER_66] = rtl_hw_start_8125d,
 		[RTL_GIGA_MAC_VER_70] = rtl_hw_start_8126a,
-		[RTL_GIGA_MAC_VER_71] = rtl_hw_start_8126a,
+		[RTL_GIGA_MAC_VER_80] = rtl_hw_start_8127a,
 	};
 
 	if (hw_configs[tp->mac_version])
@@ -3923,14 +3865,15 @@ static void rtl_hw_start_8125(struct rtl8169_private *tp)
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_61:
 	case RTL_GIGA_MAC_VER_64:
-	case RTL_GIGA_MAC_VER_65:
 	case RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_80:
 		for (i = 0xa00; i < 0xb00; i += 4)
 			RTL_W32(tp, i, 0);
+		if (tp->mac_version == RTL_GIGA_MAC_VER_80)
+			RTL_W16(tp, INT_CFG1_8125, 0x0000);
 		break;
 	case RTL_GIGA_MAC_VER_63:
 	case RTL_GIGA_MAC_VER_70:
-	case RTL_GIGA_MAC_VER_71:
 		for (i = 0xa00; i < 0xa80; i += 4)
 			RTL_W32(tp, i, 0);
 		RTL_W16(tp, INT_CFG1_8125, 0x0000);
@@ -4162,7 +4105,7 @@ static void rtl8169_cleanup(struct rtl8169_private *tp)
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
 		rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_LAST:
 		rtl_enable_rxdvgate(tp);
 		fsleep(2000);
 		break;
@@ -4319,7 +4262,7 @@ static unsigned int rtl_quirk_packet_padto(struct rtl8169_private *tp,
 
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_34:
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
 		padto = max_t(unsigned int, padto, ETH_ZLEN);
 		break;
 	default:
@@ -5107,10 +5050,8 @@ static void rtl_shutdown(struct pci_dev *pdev)
 	/* Restore original MAC address */
 	rtl_rar_set(tp, tp->dev->perm_addr);
 
-	if (system_state == SYSTEM_POWER_OFF && !tp->dash_enabled) {
-		pci_wake_from_d3(pdev, tp->saved_wolopts);
-		pci_set_power_state(pdev, PCI_D3hot);
-	}
+	if (system_state == SYSTEM_POWER_OFF && !tp->dash_enabled)
+		pci_prepare_to_sleep(pdev);
 }
 
 static void rtl_remove_one(struct pci_dev *pdev)
@@ -5364,13 +5305,13 @@ static void rtl_hw_init_8125(struct rtl8169_private *tp)
 static void rtl_hw_initialize(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_53:
+	case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_52:
 		rtl8168ep_stop_cmac(tp);
 		fallthrough;
 	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48:
 		rtl_hw_init_8168g(tp);
 		break;
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
 		rtl_hw_init_8125(tp);
 		break;
 	default:
@@ -5395,7 +5336,7 @@ static int rtl_jumbo_max(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_24:
 		return JUMBO_6K;
 	/* RTL8125/8126 */
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
 		return JUMBO_16K;
 	default:
 		return JUMBO_9K;
@@ -5440,9 +5381,9 @@ static bool rtl_aspm_is_safe(struct rtl8169_private *tp)
 
 static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
+	const struct rtl_chip_info *chip;
 	struct rtl8169_private *tp;
 	int jumbo_max, region, rc;
-	enum mac_version chipset;
 	struct net_device *dev;
 	u32 txconfig;
 	u16 xid;
@@ -5492,12 +5433,13 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	xid = (txconfig >> 20) & 0xfcf;
 
 	/* Identify chip attached to board */
-	chipset = rtl8169_get_mac_version(xid, tp->supports_gmii);
-	if (chipset == RTL_GIGA_MAC_NONE)
+	chip = rtl8169_get_chip_version(xid, tp->supports_gmii);
+	if (chip->mac_version == RTL_GIGA_MAC_NONE)
 		return dev_err_probe(&pdev->dev, -ENODEV,
 				     "unknown chip XID %03x, contact r8169 maintainers (see MAINTAINERS file)\n",
 				     xid);
-	tp->mac_version = chipset;
+	tp->mac_version = chip->mac_version;
+	tp->fw_name = chip->fw_name;
 
 	/* Disable ASPM L1 as that cause random device stop working
 	 * problems as well as full system hangs for some PCIe devices users.
@@ -5602,8 +5544,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	rtl_set_irq_mask(tp);
 
-	tp->fw_name = rtl_chip_infos[chipset].fw_name;
-
 	tp->counters = dmam_alloc_coherent (&pdev->dev, sizeof(*tp->counters),
 					    &tp->counters_phys_addr,
 					    GFP_KERNEL);
@@ -5628,7 +5568,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	netdev_info(dev, "%s, %pM, XID %03x, IRQ %d\n",
-		    rtl_chip_infos[chipset].name, dev->dev_addr, xid, tp->irq);
+		    chip->name, dev->dev_addr, xid, tp->irq);
 
 	if (jumbo_max)
 		netdev_info(dev, "jumbo features [frames: %d bytes, tx checksumming: %s]\n",
diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c
index 748ca8b212ba..032d9d2cfa2a 100644
--- a/drivers/net/ethernet/realtek/r8169_phy_config.c
+++ b/drivers/net/ethernet/realtek/r8169_phy_config.c
@@ -1130,6 +1130,171 @@ static void rtl8126a_hw_phy_config(struct rtl8169_private *tp,
 	rtl8125_common_config_eee_phy(phydev);
 }
 
+static void rtl8127a_1_hw_phy_config(struct rtl8169_private *tp,
+				     struct phy_device *phydev)
+{
+	r8169_apply_firmware(tp);
+	rtl8168g_enable_gphy_10m(phydev);
+
+	r8168g_phy_param(phydev, 0x8415, 0xff00, 0x9300);
+	r8168g_phy_param(phydev, 0x81a3, 0xff00, 0x0f00);
+	r8168g_phy_param(phydev, 0x81ae, 0xff00, 0x0f00);
+	r8168g_phy_param(phydev, 0x81b9, 0xff00, 0xb900);
+	rtl8125_phy_param(phydev, 0x83b0, 0x0e00, 0x0000);
+	rtl8125_phy_param(phydev, 0x83C5, 0x0e00, 0x0000);
+	rtl8125_phy_param(phydev, 0x83da, 0x0e00, 0x0000);
+	rtl8125_phy_param(phydev, 0x83ef, 0x0e00, 0x0000);
+	phy_modify_paged(phydev, 0x0bf3, 0x14, 0x01f0, 0x0160);
+	phy_modify_paged(phydev, 0x0bf3, 0x15, 0x001f, 0x0014);
+	phy_modify_paged(phydev, 0x0bf2, 0x14, 0x6000, 0x0000);
+	phy_modify_paged(phydev, 0x0bf2, 0x16, 0xc000, 0x0000);
+	phy_modify_paged(phydev, 0x0bf2, 0x14, 0x1fff, 0x0187);
+	phy_modify_paged(phydev, 0x0bf2, 0x15, 0x003f, 0x0003);
+
+	r8168g_phy_param(phydev, 0x8173, 0xffff, 0x8620);
+	r8168g_phy_param(phydev, 0x8175, 0xffff, 0x8671);
+	r8168g_phy_param(phydev, 0x817c, 0x0000, 0x2000);
+	r8168g_phy_param(phydev, 0x8187, 0x0000, 0x2000);
+	r8168g_phy_param(phydev, 0x8192, 0x0000, 0x2000);
+	r8168g_phy_param(phydev, 0x819d, 0x0000, 0x2000);
+	r8168g_phy_param(phydev, 0x81a8, 0x2000, 0x0000);
+	r8168g_phy_param(phydev, 0x81b3, 0x2000, 0x0000);
+	r8168g_phy_param(phydev, 0x81be, 0x0000, 0x2000);
+	r8168g_phy_param(phydev, 0x817d, 0xff00, 0xa600);
+	r8168g_phy_param(phydev, 0x8188, 0xff00, 0xa600);
+	r8168g_phy_param(phydev, 0x8193, 0xff00, 0xa600);
+	r8168g_phy_param(phydev, 0x819e, 0xff00, 0xa600);
+	r8168g_phy_param(phydev, 0x81a9, 0xff00, 0x1400);
+	r8168g_phy_param(phydev, 0x81b4, 0xff00, 0x1400);
+	r8168g_phy_param(phydev, 0x81bf, 0xff00, 0xa600);
+
+	phy_modify_paged(phydev, 0x0aea, 0x15, 0x0028, 0x0000);
+
+	rtl8125_phy_param(phydev, 0x84f0, 0xffff, 0x201c);
+	rtl8125_phy_param(phydev, 0x84f2, 0xffff, 0x3117);
+
+	phy_write_paged(phydev, 0x0aec, 0x13, 0x0000);
+	phy_write_paged(phydev, 0x0ae2, 0x10, 0xffff);
+	phy_write_paged(phydev, 0x0aec, 0x17, 0xffff);
+	phy_write_paged(phydev, 0x0aed, 0x11, 0xffff);
+	phy_write_paged(phydev, 0x0aec, 0x14, 0x0000);
+	phy_modify_paged(phydev, 0x0aed, 0x10, 0x0001, 0x0000);
+	phy_write_paged(phydev, 0x0adb, 0x14, 0x0150);
+	rtl8125_phy_param(phydev, 0x8197, 0xff00, 0x5000);
+	rtl8125_phy_param(phydev, 0x8231, 0xff00, 0x5000);
+	rtl8125_phy_param(phydev, 0x82cb, 0xff00, 0x5000);
+	rtl8125_phy_param(phydev, 0x82cd, 0xff00, 0x5700);
+	rtl8125_phy_param(phydev, 0x8233, 0xff00, 0x5700);
+	rtl8125_phy_param(phydev, 0x8199, 0xff00, 0x5700);
+
+	rtl8125_phy_param(phydev, 0x815a, 0xffff, 0x0150);
+	rtl8125_phy_param(phydev, 0x81f4, 0xffff, 0x0150);
+	rtl8125_phy_param(phydev, 0x828e, 0xffff, 0x0150);
+	rtl8125_phy_param(phydev, 0x81b1, 0xffff, 0x0000);
+	rtl8125_phy_param(phydev, 0x824b, 0xffff, 0x0000);
+	rtl8125_phy_param(phydev, 0x82e5, 0xffff, 0x0000);
+
+	rtl8125_phy_param(phydev, 0x84f7, 0xff00, 0x2800);
+	phy_modify_paged(phydev, 0x0aec, 0x11, 0x0000, 0x1000);
+	rtl8125_phy_param(phydev, 0x81b3, 0xff00, 0xad00);
+	rtl8125_phy_param(phydev, 0x824d, 0xff00, 0xad00);
+	rtl8125_phy_param(phydev, 0x82e7, 0xff00, 0xad00);
+	phy_modify_paged(phydev, 0x0ae4, 0x17, 0x000f, 0x0001);
+	rtl8125_phy_param(phydev, 0x82ce, 0xf000, 0x4000);
+
+	rtl8125_phy_param(phydev, 0x84ac, 0xffff, 0x0000);
+	rtl8125_phy_param(phydev, 0x84ae, 0xffff, 0x0000);
+	rtl8125_phy_param(phydev, 0x84b0, 0xffff, 0xf818);
+	rtl8125_phy_param(phydev, 0x84b2, 0xff00, 0x6000);
+
+	rtl8125_phy_param(phydev, 0x8ffc, 0xffff, 0x6008);
+	rtl8125_phy_param(phydev, 0x8ffe, 0xffff, 0xf450);
+
+	rtl8125_phy_param(phydev, 0x8015, 0x0000, 0x0200);
+	rtl8125_phy_param(phydev, 0x8016, 0x0800, 0x0000);
+	rtl8125_phy_param(phydev, 0x8fe6, 0xff00, 0x0800);
+	rtl8125_phy_param(phydev, 0x8fe4, 0xffff, 0x2114);
+
+	rtl8125_phy_param(phydev, 0x8647, 0xffff, 0xa7b1);
+	rtl8125_phy_param(phydev, 0x8649, 0xffff, 0xbbca);
+	rtl8125_phy_param(phydev, 0x864b, 0xff00, 0xdc00);
+
+	rtl8125_phy_param(phydev, 0x8154, 0xc000, 0x4000);
+	rtl8125_phy_param(phydev, 0x8158, 0xc000, 0x0000);
+
+	rtl8125_phy_param(phydev, 0x826c, 0xffff, 0xffff);
+	rtl8125_phy_param(phydev, 0x826e, 0xffff, 0xffff);
+
+	rtl8125_phy_param(phydev, 0x8872, 0xff00, 0x0e00);
+	r8168g_phy_param(phydev, 0x8012, 0x0000, 0x0800);
+	r8168g_phy_param(phydev, 0x8012, 0x0000, 0x4000);
+	phy_modify_paged(phydev, 0x0b57, 0x13, 0x0000, 0x0001);
+	r8168g_phy_param(phydev, 0x834a, 0xff00, 0x0700);
+	rtl8125_phy_param(phydev, 0x8217, 0x3f00, 0x2a00);
+	r8168g_phy_param(phydev, 0x81b1, 0xff00, 0x0b00);
+	rtl8125_phy_param(phydev, 0x8fed, 0xff00, 0x4e00);
+
+	rtl8125_phy_param(phydev, 0x88ac, 0xff00, 0x2300);
+	phy_modify_paged(phydev, 0x0bf0, 0x16, 0x0000, 0x3800);
+	rtl8125_phy_param(phydev, 0x88de, 0xff00, 0x0000);
+	rtl8125_phy_param(phydev, 0x80b4, 0xffff, 0x5195);
+
+	r8168g_phy_param(phydev, 0x8370, 0xffff, 0x8671);
+	r8168g_phy_param(phydev, 0x8372, 0xffff, 0x86c8);
+
+	r8168g_phy_param(phydev, 0x8401, 0xffff, 0x86c8);
+	r8168g_phy_param(phydev, 0x8403, 0xffff, 0x86da);
+	r8168g_phy_param(phydev, 0x8406, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x8408, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x840a, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x840c, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x840e, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x8410, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x8412, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x8414, 0x1800, 0x1000);
+	r8168g_phy_param(phydev, 0x8416, 0x1800, 0x1000);
+
+	r8168g_phy_param(phydev, 0x82bd, 0xffff, 0x1f40);
+
+	phy_modify_paged(phydev, 0x0bfb, 0x12, 0x07ff, 0x0328);
+	phy_write_paged(phydev, 0x0bfb, 0x13, 0x3e14);
+
+	r8168g_phy_param(phydev, 0x81c4, 0xffff, 0x003b);
+	r8168g_phy_param(phydev, 0x81c6, 0xffff, 0x0086);
+	r8168g_phy_param(phydev, 0x81c8, 0xffff, 0x00b7);
+	r8168g_phy_param(phydev, 0x81ca, 0xffff, 0x00db);
+	r8168g_phy_param(phydev, 0x81cc, 0xffff, 0x00fe);
+	r8168g_phy_param(phydev, 0x81ce, 0xffff, 0x00fe);
+	r8168g_phy_param(phydev, 0x81d0, 0xffff, 0x00fe);
+	r8168g_phy_param(phydev, 0x81d2, 0xffff, 0x00fe);
+	r8168g_phy_param(phydev, 0x81d4, 0xffff, 0x00c3);
+	r8168g_phy_param(phydev, 0x81d6, 0xffff, 0x0078);
+	r8168g_phy_param(phydev, 0x81d8, 0xffff, 0x0047);
+	r8168g_phy_param(phydev, 0x81da, 0xffff, 0x0023);
+
+	rtl8125_phy_param(phydev, 0x88d7, 0xffff, 0x01a0);
+	rtl8125_phy_param(phydev, 0x88d9, 0xffff, 0x01a0);
+	rtl8125_phy_param(phydev, 0x8ffa, 0xffff, 0x002a);
+
+	rtl8125_phy_param(phydev, 0x8fee, 0xffff, 0xffdf);
+	rtl8125_phy_param(phydev, 0x8ff0, 0xffff, 0xffff);
+	rtl8125_phy_param(phydev, 0x8ff2, 0xffff, 0x0a4a);
+	rtl8125_phy_param(phydev, 0x8ff4, 0xffff, 0xaa5a);
+	rtl8125_phy_param(phydev, 0x8ff6, 0xffff, 0x0a4a);
+
+	rtl8125_phy_param(phydev, 0x8ff8, 0xffff, 0xaa5a);
+	rtl8125_phy_param(phydev, 0x88d5, 0xff00, 0x0200);
+
+	r8168g_phy_param(phydev, 0x84bb, 0xff00, 0x0a00);
+	r8168g_phy_param(phydev, 0x84c0, 0xff00, 0x1600);
+
+	phy_modify_paged(phydev, 0x0a43, 0x10, 0x0000, 0x0003);
+
+	rtl8125_legacy_force_mode(phydev);
+	rtl8168g_disable_aldps(phydev);
+	rtl8125_common_config_eee_phy(phydev);
+}
+
 void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
 			 enum mac_version ver)
 {
@@ -1176,14 +1341,12 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
 		[RTL_GIGA_MAC_VER_48] = rtl8168h_2_hw_phy_config,
 		[RTL_GIGA_MAC_VER_51] = rtl8168ep_2_hw_phy_config,
 		[RTL_GIGA_MAC_VER_52] = rtl8117_hw_phy_config,
-		[RTL_GIGA_MAC_VER_53] = rtl8117_hw_phy_config,
 		[RTL_GIGA_MAC_VER_61] = rtl8125a_2_hw_phy_config,
 		[RTL_GIGA_MAC_VER_63] = rtl8125b_hw_phy_config,
 		[RTL_GIGA_MAC_VER_64] = rtl8125d_hw_phy_config,
-		[RTL_GIGA_MAC_VER_65] = rtl8125d_hw_phy_config,
 		[RTL_GIGA_MAC_VER_66] = rtl8125bp_hw_phy_config,
 		[RTL_GIGA_MAC_VER_70] = rtl8126a_hw_phy_config,
-		[RTL_GIGA_MAC_VER_71] = rtl8126a_hw_phy_config,
+		[RTL_GIGA_MAC_VER_80] = rtl8127a_1_hw_phy_config,
 	};
 
 	if (phy_configs[ver])
diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h
index 2bbfcad613ab..498cfe4d0cac 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase.h
+++ b/drivers/net/ethernet/realtek/rtase/rtase.h
@@ -170,6 +170,7 @@ enum rtase_registers {
 #define RTASE_TC_MODE_MASK GENMASK(11, 10)
 
 	RTASE_TOKSEL      = 0x2046,
+	RTASE_TXQCRDT_0   = 0x2500,
 	RTASE_RFIFONFULL  = 0x4406,
 	RTASE_INT_MITI_TX = 0x0A00,
 	RTASE_INT_MITI_RX = 0x0A80,
@@ -259,6 +260,12 @@ union rtase_rx_desc {
 #define RTASE_VLAN_TAG_MASK     GENMASK(15, 0)
 #define RTASE_RX_PKT_SIZE_MASK  GENMASK(13, 0)
 
+/* txqos hardware definitions */
+#define RTASE_1T_CLOCK            64
+#define RTASE_1T_POWER            10000000
+#define RTASE_IDLESLOPE_INT_SHIFT 25
+#define RTASE_IDLESLOPE_INT_MASK  GENMASK(31, 25)
+
 #define RTASE_IVEC_NAME_SIZE (IFNAMSIZ + 10)
 
 struct rtase_int_vector {
@@ -294,6 +301,13 @@ struct rtase_ring {
 	u64 alloc_fail;
 };
 
+struct rtase_txqos {
+	int hicredit;
+	int locredit;
+	int idleslope;
+	int sendslope;
+};
+
 struct rtase_stats {
 	u64 tx_dropped;
 	u64 rx_dropped;
@@ -313,6 +327,7 @@ struct rtase_private {
 
 	struct page_pool *page_pool;
 	struct rtase_ring tx_ring[RTASE_NUM_TX_QUEUE];
+	struct rtase_txqos tx_qos[RTASE_NUM_TX_QUEUE];
 	struct rtase_ring rx_ring[RTASE_NUM_RX_QUEUE];
 	struct rtase_counters *tally_vaddr;
 	dma_addr_t tally_paddr;
diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 2aacc1996796..4d37217e9a14 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1114,7 +1114,7 @@ static int rtase_open(struct net_device *dev)
 		/* request other interrupts to handle multiqueue */
 		for (i = 1; i < tp->int_nums; i++) {
 			ivec = &tp->int_vector[i];
-			snprintf(ivec->name, sizeof(ivec->name), "%s_int%i",
+			snprintf(ivec->name, sizeof(ivec->name), "%s_int%u",
 				 tp->dev->name, i);
 			ret = request_irq(ivec->irq, rtase_q_interrupt, 0,
 					  ivec->name, ivec);
@@ -1661,6 +1661,65 @@ static void rtase_get_stats64(struct net_device *dev,
 	stats->rx_length_errors = tp->stats.rx_length_errors;
 }
 
+static void rtase_set_hw_cbs(const struct rtase_private *tp, u32 queue)
+{
+	u32 idle = tp->tx_qos[queue].idleslope * RTASE_1T_CLOCK;
+	u32 val, i;
+
+	val = u32_encode_bits(idle / RTASE_1T_POWER, RTASE_IDLESLOPE_INT_MASK);
+	idle %= RTASE_1T_POWER;
+
+	for (i = 1; i <= RTASE_IDLESLOPE_INT_SHIFT; i++) {
+		idle *= 2;
+		if ((idle / RTASE_1T_POWER) == 1)
+			val |= BIT(RTASE_IDLESLOPE_INT_SHIFT - i);
+
+		idle %= RTASE_1T_POWER;
+	}
+
+	rtase_w32(tp, RTASE_TXQCRDT_0 + queue * 4, val);
+}
+
+static int rtase_setup_tc_cbs(struct rtase_private *tp,
+			      const struct tc_cbs_qopt_offload *qopt)
+{
+	int queue = qopt->queue;
+
+	if (queue < 0 || queue >= tp->func_tx_queue_num)
+		return -EINVAL;
+
+	if (!qopt->enable) {
+		tp->tx_qos[queue].hicredit = 0;
+		tp->tx_qos[queue].locredit = 0;
+		tp->tx_qos[queue].idleslope = 0;
+		tp->tx_qos[queue].sendslope = 0;
+
+		rtase_w32(tp, RTASE_TXQCRDT_0 + queue * 4, 0);
+	} else {
+		tp->tx_qos[queue].hicredit = qopt->hicredit;
+		tp->tx_qos[queue].locredit = qopt->locredit;
+		tp->tx_qos[queue].idleslope = qopt->idleslope;
+		tp->tx_qos[queue].sendslope = qopt->sendslope;
+
+		rtase_set_hw_cbs(tp, queue);
+	}
+
+	return 0;
+}
+
+static int rtase_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			  void *type_data)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_QDISC_CBS:
+		return rtase_setup_tc_cbs(tp, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static netdev_features_t rtase_fix_features(struct net_device *dev,
 					    netdev_features_t features)
 {
@@ -1696,6 +1755,7 @@ static const struct net_device_ops rtase_netdev_ops = {
 	.ndo_change_mtu = rtase_change_mtu,
 	.ndo_tx_timeout = rtase_tx_timeout,
 	.ndo_get_stats64 = rtase_get_stats64,
+	.ndo_setup_tc = rtase_setup_tc,
 	.ndo_fix_features = rtase_fix_features,
 	.ndo_set_features = rtase_set_features,
 };
@@ -1923,10 +1983,10 @@ static u16 rtase_calc_time_mitigation(u32 time_us)
 	u8 msb, time_count, time_unit;
 	u16 int_miti;
 
-	time_us = min_t(int, time_us, RTASE_MITI_MAX_TIME);
+	time_us = min(time_us, RTASE_MITI_MAX_TIME);
 
-	msb = fls(time_us);
-	if (msb >= RTASE_MITI_COUNT_BIT_NUM) {
+	if (time_us > RTASE_MITI_TIME_COUNT_MASK) {
+		msb = fls(time_us);
 		time_unit = msb - RTASE_MITI_COUNT_BIT_NUM;
 		time_count = time_us >> (msb - RTASE_MITI_COUNT_BIT_NUM);
 	} else {
@@ -1945,7 +2005,7 @@ static u16 rtase_calc_packet_num_mitigation(u16 pkt_num)
 	u8 msb, pkt_num_count, pkt_num_unit;
 	u16 int_miti;
 
-	pkt_num = min_t(int, pkt_num, RTASE_MITI_MAX_PKT_NUM);
+	pkt_num = min(pkt_num, RTASE_MITI_MAX_PKT_NUM);
 
 	if (pkt_num > 60) {
 		pkt_num_unit = RTASE_MITI_MAX_PKT_NUM_IDX;
diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c
index b4365906669f..226c6c0ab945 100644
--- a/drivers/net/ethernet/renesas/ravb_ptp.c
+++ b/drivers/net/ethernet/renesas/ravb_ptp.c
@@ -176,12 +176,6 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp,
 	struct net_device *ndev = priv->ndev;
 	unsigned long flags;
 
-	/* Reject requests with unsupported flags */
-	if (req->flags & ~(PTP_ENABLE_FEATURE |
-			   PTP_RISING_EDGE |
-			   PTP_FALLING_EDGE))
-		return -EOPNOTSUPP;
-
 	if (req->index)
 		return -EINVAL;
 
@@ -212,10 +206,6 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp,
 	unsigned long flags;
 	int error = 0;
 
-	/* Reject requests with unsupported flags */
-	if (req->flags)
-		return -EOPNOTSUPP;
-
 	if (req->index)
 		return -EINVAL;
 
@@ -287,6 +277,7 @@ static const struct ptp_clock_info ravb_ptp_info = {
 	.max_adj	= 50000000,
 	.n_ext_ts	= N_EXT_TS,
 	.n_per_out	= N_PER_OUT,
+	.supported_extts_flags = PTP_RISING_EDGE | PTP_FALLING_EDGE,
 	.adjfine	= ravb_ptp_adjfine,
 	.adjtime	= ravb_ptp_adjtime,
 	.gettime64	= ravb_ptp_gettime64,
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 332cbd725900..df869f82cae8 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -468,7 +468,7 @@ static int sis900_probe(struct pci_dev *pci_dev,
 	SET_NETDEV_DEV(net_dev, &pci_dev->dev);
 
 	/* We do a request_region() to register /proc/ioports info. */
-	ret = pci_request_regions(pci_dev, "sis900");
+	ret = pcim_request_all_regions(pci_dev, "sis900");
 	if (ret)
 		goto err_out;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 3c820ef56775..67fa879b1e52 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -3,6 +3,7 @@ config STMMAC_ETH
 	tristate "STMicroelectronics Multi-Gigabit Ethernet driver"
 	depends on HAS_IOMEM && HAS_DMA
 	depends on PTP_1588_CLOCK_OPTIONAL
+	depends on ETHTOOL_NETLINK
 	select MII
 	select PCS_XPCS
 	select PAGE_POOL
@@ -131,6 +132,17 @@ config DWMAC_QCOM_ETHQOS
 	  This selects the Qualcomm ETHQOS glue layer support for the
 	  stmmac device driver.
 
+config DWMAC_RENESAS_GBETH
+	tristate "Renesas RZ/V2H(P) GBETH support"
+	default ARCH_RENESAS
+	depends on OF && (ARCH_RENESAS || COMPILE_TEST)
+	help
+	  Support for Gigabit Ethernet Interface (GBETH) on Renesas
+	  RZ/V2H(P) SoCs.
+
+	  This selects the Renesas RZ/V2H(P) Soc specific glue layer support
+	  for the stmmac device driver.
+
 config DWMAC_ROCKCHIP
 	tristate "Rockchip dwmac support"
 	default ARCH_ROCKCHIP
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 594883fb4164..b591d93f8503 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -6,7 +6,7 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o	\
 	      mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o	\
 	      dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o hwif.o \
 	      stmmac_tc.o dwxgmac2_core.o dwxgmac2_dma.o dwxgmac2_descs.o \
-	      stmmac_xdp.o stmmac_est.o stmmac_fpe.o \
+	      stmmac_xdp.o stmmac_est.o stmmac_fpe.o stmmac_vlan.o \
 	      $(stmmac-y)
 
 stmmac-$(CONFIG_STMMAC_SELFTESTS) += stmmac_selftests.o
@@ -20,6 +20,7 @@ obj-$(CONFIG_DWMAC_LPC18XX)	+= dwmac-lpc18xx.o
 obj-$(CONFIG_DWMAC_MEDIATEK)	+= dwmac-mediatek.o
 obj-$(CONFIG_DWMAC_MESON)	+= dwmac-meson.o dwmac-meson8b.o
 obj-$(CONFIG_DWMAC_QCOM_ETHQOS)	+= dwmac-qcom-ethqos.o
+obj-$(CONFIG_DWMAC_RENESAS_GBETH) += dwmac-renesas-gbeth.o
 obj-$(CONFIG_DWMAC_ROCKCHIP)	+= dwmac-rk.o
 obj-$(CONFIG_DWMAC_RZN1)	+= dwmac-rzn1.o
 obj-$(CONFIG_DWMAC_S32)		+= dwmac-s32.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 412b07e77945..ea5da5793362 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -602,6 +602,7 @@ struct mac_device_info {
 	const struct stmmac_tc_ops *tc;
 	const struct stmmac_mmc_ops *mmc;
 	const struct stmmac_est_ops *est;
+	const struct stmmac_vlan_ops *vlan;
 	struct dw_xpcs *xpcs;
 	struct phylink_pcs *phylink_pcs;
 	struct mii_regs mii;	/* MII register Addresses */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
index 37fe7c288878..84072c8ed741 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
@@ -65,13 +65,12 @@ anarion_config_dt(struct platform_device *pdev,
 {
 	struct anarion_gmac *gmac;
 	void __iomem *ctl_block;
-	int err;
 
 	ctl_block = devm_platform_ioremap_resource(pdev, 1);
 	if (IS_ERR(ctl_block)) {
-		err = PTR_ERR(ctl_block);
-		dev_err(&pdev->dev, "Cannot get reset region (%d)!\n", err);
-		return ERR_PTR(err);
+		dev_err(&pdev->dev, "Cannot get reset region (%pe)!\n",
+			ctl_block);
+		return ERR_CAST(ctl_block);
 	}
 
 	gmac = devm_kzalloc(&pdev->dev, sizeof(*gmac), GFP_KERNEL);
@@ -80,17 +79,11 @@ anarion_config_dt(struct platform_device *pdev,
 
 	gmac->ctl_block = ctl_block;
 
-	switch (plat_dat->phy_interface) {
-	case PHY_INTERFACE_MODE_RGMII:
-		fallthrough;
-	case PHY_INTERFACE_MODE_RGMII_ID:
-	case PHY_INTERFACE_MODE_RGMII_RXID:
-	case PHY_INTERFACE_MODE_RGMII_TXID:
+	if (phy_interface_mode_is_rgmii(plat_dat->phy_interface)) {
 		gmac->phy_intf_sel = GMAC_CONFIG_INTF_RGMII;
-		break;
-	default:
-		dev_err(&pdev->dev, "Unsupported phy-mode (%d)\n",
-			plat_dat->phy_interface);
+	} else {
+		dev_err(&pdev->dev, "Unsupported phy-mode (%s)\n",
+			phy_modes(plat_dat->phy_interface));
 		return ERR_PTR(-ENOTSUPP);
 	}
 
@@ -118,10 +111,9 @@ static int anarion_dwmac_probe(struct platform_device *pdev)
 
 	plat_dat->init = anarion_gmac_init;
 	plat_dat->exit = anarion_gmac_exit;
-	anarion_gmac_init(pdev, gmac);
 	plat_dat->bsp_priv = gmac;
 
-	return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 }
 
 static const struct of_device_id anarion_dwmac_match[] = {
@@ -132,7 +124,6 @@ MODULE_DEVICE_TABLE(of, anarion_dwmac_match);
 
 static struct platform_driver anarion_dwmac_driver = {
 	.probe  = anarion_dwmac_probe,
-	.remove = stmmac_pltfr_remove,
 	.driver = {
 		.name           = "anarion-dwmac",
 		.pm		= &stmmac_pltfr_pm_ops,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 5db318327d33..09ae16e026eb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -29,7 +29,6 @@ struct tegra_eqos {
 	void __iomem *regs;
 
 	struct reset_control *rst;
-	struct clk *clk_slave;
 
 	struct gpio_desc *reset;
 };
@@ -137,10 +136,11 @@ static int dwc_qos_probe(struct platform_device *pdev,
 #define AUTO_CAL_STATUS 0x880c
 #define  AUTO_CAL_STATUS_ACTIVE BIT(31)
 
-static void tegra_eqos_fix_speed(void *priv, int speed, unsigned int mode)
+static void tegra_eqos_fix_speed(void *bsp_priv, int speed, unsigned int mode)
 {
-	struct tegra_eqos *eqos = priv;
+	struct tegra_eqos *eqos = bsp_priv;
 	bool needs_calibration = false;
+	struct stmmac_priv *priv;
 	u32 value;
 	int err;
 
@@ -159,6 +159,11 @@ static void tegra_eqos_fix_speed(void *priv, int speed, unsigned int mode)
 	}
 
 	if (needs_calibration) {
+		priv = netdev_priv(dev_get_drvdata(eqos->dev));
+
+		/* Calibration should be done with the MDIO bus idle */
+		mutex_lock(&priv->mii->mdio_lock);
+
 		/* calibrate */
 		value = readl(eqos->regs + SDMEMCOMPPADCTRL);
 		value |= SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
@@ -192,6 +197,8 @@ static void tegra_eqos_fix_speed(void *priv, int speed, unsigned int mode)
 		value = readl(eqos->regs + SDMEMCOMPPADCTRL);
 		value &= ~SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
 		writel(value, eqos->regs + SDMEMCOMPPADCTRL);
+
+		mutex_unlock(&priv->mii->mdio_lock);
 	} else {
 		value = readl(eqos->regs + AUTO_CAL_CONFIG);
 		value &= ~AUTO_CAL_CONFIG_ENABLE;
@@ -199,20 +206,6 @@ static void tegra_eqos_fix_speed(void *priv, int speed, unsigned int mode)
 	}
 }
 
-static int tegra_eqos_init(struct platform_device *pdev, void *priv)
-{
-	struct tegra_eqos *eqos = priv;
-	unsigned long rate;
-	u32 value;
-
-	rate = clk_get_rate(eqos->clk_slave);
-
-	value = (rate / 1000000) - 1;
-	writel(value, eqos->regs + GMAC_1US_TIC_COUNTER);
-
-	return 0;
-}
-
 static int tegra_eqos_probe(struct platform_device *pdev,
 			    struct plat_stmmacenet_data *plat_dat,
 			    struct stmmac_resources *res)
@@ -227,7 +220,6 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 
 	eqos->dev = &pdev->dev;
 	eqos->regs = res->addr;
-	eqos->clk_slave = plat_dat->stmmac_clk;
 
 	if (!is_of_node(dev->fwnode))
 		goto bypass_clk_reset_gpio;
@@ -267,17 +259,12 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 bypass_clk_reset_gpio:
 	plat_dat->fix_mac_speed = tegra_eqos_fix_speed;
 	plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
-	plat_dat->init = tegra_eqos_init;
 	plat_dat->bsp_priv = eqos;
-	plat_dat->flags |= STMMAC_FLAG_SPH_DISABLE;
-
-	err = tegra_eqos_init(pdev, eqos);
-	if (err < 0)
-		goto reset;
+	plat_dat->flags |= STMMAC_FLAG_SPH_DISABLE |
+			   STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP;
 
 	return 0;
-reset:
-	reset_control_assert(eqos->rst);
+
 reset_phy:
 	gpiod_set_value(eqos->reset, 1);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index 5d279fa54b3e..889e2bb6f7f5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -379,10 +379,6 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = imx_dwmac_init(pdev, dwmac);
-	if (ret)
-		goto err_dwmac_init;
-
 	if (dwmac->ops->fix_mac_speed) {
 		plat_dat->fix_mac_speed = dwmac->ops->fix_mac_speed;
 	} else if (!dwmac->ops->mac_rgmii_txclk_auto_adj) {
@@ -392,16 +388,10 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 
 	dwmac->plat_dat->fix_soc_reset = dwmac->ops->fix_soc_reset;
 
-	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+	ret = stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 	if (ret)
-		goto err_drv_probe;
-
-	return 0;
+		imx_dwmac_clks_config(dwmac, false);
 
-err_drv_probe:
-	imx_dwmac_exit(pdev, plat_dat->bsp_priv);
-err_dwmac_init:
-	imx_dwmac_clks_config(dwmac, false);
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
index 066783d66422..15abe214131f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
@@ -56,6 +56,7 @@ enum ingenic_mac_version {
 
 struct ingenic_mac {
 	const struct ingenic_soc_info *soc_info;
+	struct plat_stmmacenet_data *plat_dat;
 	struct device *dev;
 	struct regmap *regmap;
 
@@ -70,13 +71,13 @@ struct ingenic_soc_info {
 	int (*set_mode)(struct plat_stmmacenet_data *plat_dat);
 };
 
-static int ingenic_mac_init(struct plat_stmmacenet_data *plat_dat)
+static int ingenic_mac_init(struct platform_device *pdev, void *bsp_priv)
 {
-	struct ingenic_mac *mac = plat_dat->bsp_priv;
+	struct ingenic_mac *mac = bsp_priv;
 	int ret;
 
 	if (mac->soc_info->set_mode) {
-		ret = mac->soc_info->set_mode(plat_dat);
+		ret = mac->soc_info->set_mode(mac->plat_dat);
 		if (ret)
 			return ret;
 	}
@@ -284,44 +285,14 @@ static int ingenic_mac_probe(struct platform_device *pdev)
 
 	mac->soc_info = data;
 	mac->dev = &pdev->dev;
+	mac->plat_dat = plat_dat;
 
 	plat_dat->bsp_priv = mac;
+	plat_dat->init = ingenic_mac_init;
 
-	ret = ingenic_mac_init(plat_dat);
-	if (ret)
-		return ret;
-
-	return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int ingenic_mac_suspend(struct device *dev)
-{
-	int ret;
-
-	ret = stmmac_suspend(dev);
-
-	return ret;
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 }
 
-static int ingenic_mac_resume(struct device *dev)
-{
-	struct net_device *ndev = dev_get_drvdata(dev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-	int ret;
-
-	ret = ingenic_mac_init(priv->plat);
-	if (ret)
-		return ret;
-
-	ret = stmmac_resume(dev);
-
-	return ret;
-}
-#endif /* CONFIG_PM_SLEEP */
-
-static SIMPLE_DEV_PM_OPS(ingenic_mac_pm_ops, ingenic_mac_suspend, ingenic_mac_resume);
-
 static struct ingenic_soc_info jz4775_soc_info = {
 	.version = ID_JZ4775,
 	.mask = MACPHYC_TXCLK_SEL_MASK | MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK,
@@ -370,10 +341,9 @@ MODULE_DEVICE_TABLE(of, ingenic_mac_of_matches);
 
 static struct platform_driver ingenic_mac_driver = {
 	.probe		= ingenic_mac_probe,
-	.remove		= stmmac_pltfr_remove,
 	.driver		= {
 		.name	= "ingenic-mac",
-		.pm		= pm_ptr(&ingenic_mac_pm_ops),
+		.pm		= &stmmac_pltfr_pm_ops,
 		.of_match_table = ingenic_mac_of_matches,
 	},
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
index 599def7b3a64..4ea7b0a803d7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
@@ -113,16 +113,7 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 
 	plat_dat->clk_tx_i = dwmac->tx_clk;
 	plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
-
 	plat_dat->bsp_priv = dwmac;
-	plat_dat->eee_usecs_rate = plat_dat->clk_ptp_rate;
-
-	if (plat_dat->eee_usecs_rate > 0) {
-		u32 tx_lpi_usec;
-
-		tx_lpi_usec = (plat_dat->eee_usecs_rate / 1000000) - 1;
-		writel(tx_lpi_usec, stmmac_res.addr + GMAC_1US_TIC_COUNTER);
-	}
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index c8bb9265bbb4..9a47015254bb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -284,28 +284,28 @@ static void intel_serdes_powerdown(struct net_device *ndev, void *intel_data)
 	}
 }
 
-static void intel_speed_mode_2500(struct net_device *ndev, void *intel_data)
+static void tgl_get_interfaces(struct stmmac_priv *priv, void *bsp_priv,
+			       unsigned long *interfaces)
 {
-	struct intel_priv_data *intel_priv = intel_data;
-	struct stmmac_priv *priv = netdev_priv(ndev);
-	int serdes_phy_addr = 0;
-	u32 data = 0;
-
-	serdes_phy_addr = intel_priv->mdio_adhoc_addr;
+	struct intel_priv_data *intel_priv = bsp_priv;
+	phy_interface_t interface;
+	int data;
 
 	/* Determine the link speed mode: 2.5Gbps/1Gbps */
-	data = mdiobus_read(priv->mii, serdes_phy_addr,
-			    SERDES_GCR);
+	data = mdiobus_read(priv->mii, intel_priv->mdio_adhoc_addr, SERDES_GCR);
+	if (data < 0)
+		return;
 
-	if (((data & SERDES_LINK_MODE_MASK) >> SERDES_LINK_MODE_SHIFT) ==
-	    SERDES_LINK_MODE_2G5) {
+	if (FIELD_GET(SERDES_LINK_MODE_MASK, data) == SERDES_LINK_MODE_2G5) {
 		dev_info(priv->device, "Link Speed Mode: 2.5Gbps\n");
-		priv->plat->max_speed = 2500;
-		priv->plat->phy_interface = PHY_INTERFACE_MODE_2500BASEX;
 		priv->plat->mdio_bus_data->default_an_inband = false;
+		interface = PHY_INTERFACE_MODE_2500BASEX;
 	} else {
-		priv->plat->max_speed = 1000;
+		interface = PHY_INTERFACE_MODE_SGMII;
 	}
+
+	__set_bit(interface, interfaces);
+	priv->plat->phy_interface = interface;
 }
 
 /* Program PTP Clock Frequency for different variant of
@@ -682,7 +682,6 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	plat->axi->axi_blen[2] = 16;
 
 	plat->ptp_max_adj = plat->clk_ptp_rate;
-	plat->eee_usecs_rate = plat->clk_ptp_rate;
 
 	/* Set system clock */
 	sprintf(clk_name, "%s-%s", "stmmac", pci_name(pdev));
@@ -933,7 +932,7 @@ static int tgl_common_data(struct pci_dev *pdev,
 	plat->rx_queues_to_use = 6;
 	plat->tx_queues_to_use = 4;
 	plat->clk_ptp_rate = 204800000;
-	plat->speed_mode_2500 = intel_speed_mode_2500;
+	plat->get_interfaces = tgl_get_interfaces;
 
 	plat->safety_feat_cfg->tsoee = 1;
 	plat->safety_feat_cfg->mrxpee = 0;
@@ -952,7 +951,6 @@ static int tgl_sgmii_phy0_data(struct pci_dev *pdev,
 			       struct plat_stmmacenet_data *plat)
 {
 	plat->bus_id = 1;
-	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
 	return tgl_common_data(pdev, plat);
@@ -966,7 +964,6 @@ static int tgl_sgmii_phy1_data(struct pci_dev *pdev,
 			       struct plat_stmmacenet_data *plat)
 {
 	plat->bus_id = 2;
-	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
 	return tgl_common_data(pdev, plat);
@@ -980,7 +977,6 @@ static int adls_sgmii_phy0_data(struct pci_dev *pdev,
 				struct plat_stmmacenet_data *plat)
 {
 	plat->bus_id = 1;
-	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
 
 	/* SerDes power up and power down are done in BIOS for ADL */
 
@@ -995,7 +991,6 @@ static int adls_sgmii_phy1_data(struct pci_dev *pdev,
 				struct plat_stmmacenet_data *plat)
 {
 	plat->bus_id = 2;
-	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
 
 	/* SerDes power up and power down are done in BIOS for ADL */
 
@@ -1313,13 +1308,6 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	memset(&res, 0, sizeof(res));
 	res.addr = pcim_iomap_table(pdev)[0];
 
-	if (plat->eee_usecs_rate > 0) {
-		u32 tx_lpi_usec;
-
-		tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1;
-		writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER);
-	}
-
 	ret = stmmac_config_multi_msi(pdev, plat, &res);
 	if (ret) {
 		ret = stmmac_config_single_msi(pdev, plat, &res);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
index a12f8e65f89f..7511c224b312 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
@@ -21,7 +21,6 @@
 #define SERDES_RATE_MASK	GENMASK(9, 8)
 #define SERDES_PCLK_MASK	GENMASK(14, 12)	/* PCLK rate to PHY */
 #define SERDES_LINK_MODE_MASK	GENMASK(2, 1)
-#define SERDES_LINK_MODE_SHIFT	1
 #define SERDES_PWR_ST_SHIFT	4
 #define SERDES_PWR_ST_P0	0x0
 #define SERDES_PWR_ST_P3	0x3
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 1a93787056a7..e1591e6217d4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -66,12 +66,14 @@
 					 DMA_STATUS_TPS | DMA_STATUS_TI  | \
 					 DMA_STATUS_MSK_COMMON_LOONGSON)
 
-#define PCI_DEVICE_ID_LOONGSON_GMAC	0x7a03
+#define PCI_DEVICE_ID_LOONGSON_GMAC1	0x7a03
+#define PCI_DEVICE_ID_LOONGSON_GMAC2	0x7a23
 #define PCI_DEVICE_ID_LOONGSON_GNET	0x7a13
-#define DWMAC_CORE_LS_MULTICHAN	0x10	/* Loongson custom ID */
-#define CHANNEL_NUM			8
+#define DWMAC_CORE_MULTICHAN_V1	0x10	/* Loongson custom ID 0x10 */
+#define DWMAC_CORE_MULTICHAN_V2	0x12	/* Loongson custom ID 0x12 */
 
 struct loongson_data {
+	u32 multichan;
 	u32 loongson_id;
 	struct device *dev;
 };
@@ -83,6 +85,8 @@ struct stmmac_pci_info {
 static void loongson_default_data(struct pci_dev *pdev,
 				  struct plat_stmmacenet_data *plat)
 {
+	struct loongson_data *ld = plat->bsp_priv;
+
 	/* Get bus_id, this can be overwritten later */
 	plat->bus_id = pci_dev_id(pdev);
 
@@ -116,31 +120,37 @@ static void loongson_default_data(struct pci_dev *pdev,
 
 	plat->dma_cfg->pbl = 32;
 	plat->dma_cfg->pblx8 = true;
-}
-
-static int loongson_gmac_data(struct pci_dev *pdev,
-			      struct plat_stmmacenet_data *plat)
-{
-	struct loongson_data *ld;
-	int i;
-
-	ld = plat->bsp_priv;
 
-	loongson_default_data(pdev, plat);
-
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) {
-		plat->rx_queues_to_use = CHANNEL_NUM;
-		plat->tx_queues_to_use = CHANNEL_NUM;
+	switch (ld->loongson_id) {
+	case DWMAC_CORE_MULTICHAN_V1:
+		ld->multichan = 1;
+		plat->rx_queues_to_use = 8;
+		plat->tx_queues_to_use = 8;
 
 		/* Only channel 0 supports checksum,
 		 * so turn off checksum to enable multiple channels.
 		 */
-		for (i = 1; i < CHANNEL_NUM; i++)
+		for (int i = 1; i < 8; i++)
 			plat->tx_queues_cfg[i].coe_unsupported = 1;
-	} else {
+
+		break;
+	case DWMAC_CORE_MULTICHAN_V2:
+		ld->multichan = 1;
+		plat->rx_queues_to_use = 4;
+		plat->tx_queues_to_use = 4;
+		break;
+	default:
+		ld->multichan = 0;
 		plat->tx_queues_to_use = 1;
 		plat->rx_queues_to_use = 1;
+		break;
 	}
+}
+
+static int loongson_gmac_data(struct pci_dev *pdev,
+			      struct plat_stmmacenet_data *plat)
+{
+	loongson_default_data(pdev, plat);
 
 	plat->phy_interface = PHY_INTERFACE_MODE_RGMII_ID;
 
@@ -172,27 +182,8 @@ static void loongson_gnet_fix_speed(void *priv, int speed, unsigned int mode)
 static int loongson_gnet_data(struct pci_dev *pdev,
 			      struct plat_stmmacenet_data *plat)
 {
-	struct loongson_data *ld;
-	int i;
-
-	ld = plat->bsp_priv;
-
 	loongson_default_data(pdev, plat);
 
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) {
-		plat->rx_queues_to_use = CHANNEL_NUM;
-		plat->tx_queues_to_use = CHANNEL_NUM;
-
-		/* Only channel 0 supports checksum,
-		 * so turn off checksum to enable multiple channels.
-		 */
-		for (i = 1; i < CHANNEL_NUM; i++)
-			plat->tx_queues_cfg[i].coe_unsupported = 1;
-	} else {
-		plat->tx_queues_to_use = 1;
-		plat->rx_queues_to_use = 1;
-	}
-
 	plat->phy_interface = PHY_INTERFACE_MODE_GMII;
 	plat->mdio_bus_data->phy_mask = ~(u32)BIT(2);
 	plat->fix_mac_speed = loongson_gnet_fix_speed;
@@ -350,14 +341,14 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv)
 		return NULL;
 
 	/* The Loongson GMAC and GNET devices are based on the DW GMAC
-	 * v3.50a and v3.73a IP-cores. But the HW designers have changed the
-	 * GMAC_VERSION.SNPSVER field to the custom 0x10 value on the
-	 * network controllers with the multi-channels feature
+	 * v3.50a and v3.73a IP-cores. But the HW designers have changed
+	 * the GMAC_VERSION.SNPSVER field to the custom 0x10/0x12 value
+	 * on the network controllers with the multi-channels feature
 	 * available to emphasize the differences: multiple DMA-channels,
 	 * AV feature and GMAC_INT_STATUS CSR flags layout. Get back the
 	 * original value so the correct HW-interface would be selected.
 	 */
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) {
+	if (ld->multichan) {
 		priv->synopsys_id = DWMAC_CORE_3_70;
 		*dma = dwmac1000_dma_ops;
 		dma->init_chan = loongson_dwmac_dma_init_channel;
@@ -378,13 +369,13 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv)
 	if (mac->multicast_filter_bins)
 		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
 
-	/* Loongson GMAC doesn't support the flow control. LS2K2000
-	 * GNET doesn't support the half-duplex link mode.
+	/* Loongson GMAC doesn't support the flow control. Loongson GNET
+	 * without multi-channel doesn't support the half-duplex link mode.
 	 */
-	if (pdev->device == PCI_DEVICE_ID_LOONGSON_GMAC) {
+	if (pdev->device != PCI_DEVICE_ID_LOONGSON_GNET) {
 		mac->link.caps = MAC_10 | MAC_100 | MAC_1000;
 	} else {
-		if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+		if (ld->multichan)
 			mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 					 MAC_10 | MAC_100 | MAC_1000;
 		else
@@ -413,9 +404,11 @@ static int loongson_dwmac_msi_config(struct pci_dev *pdev,
 				     struct plat_stmmacenet_data *plat,
 				     struct stmmac_resources *res)
 {
-	int i, ret, vecs;
+	int i, ch_num, ret, vecs;
+
+	ch_num = min(plat->tx_queues_to_use, plat->rx_queues_to_use);
 
-	vecs = roundup_pow_of_two(CHANNEL_NUM * 2 + 1);
+	vecs = roundup_pow_of_two(ch_num * 2 + 1);
 	ret = pci_alloc_irq_vectors(pdev, vecs, vecs, PCI_IRQ_MSI);
 	if (ret < 0) {
 		dev_warn(&pdev->dev, "Failed to allocate MSI IRQs\n");
@@ -424,14 +417,12 @@ static int loongson_dwmac_msi_config(struct pci_dev *pdev,
 
 	res->irq = pci_irq_vector(pdev, 0);
 
-	for (i = 0; i < plat->rx_queues_to_use; i++) {
-		res->rx_irq[CHANNEL_NUM - 1 - i] =
-			pci_irq_vector(pdev, 1 + i * 2);
+	for (i = 0; i < ch_num; i++) {
+		res->rx_irq[ch_num - 1 - i] = pci_irq_vector(pdev, 1 + i * 2);
 	}
 
-	for (i = 0; i < plat->tx_queues_to_use; i++) {
-		res->tx_irq[CHANNEL_NUM - 1 - i] =
-			pci_irq_vector(pdev, 2 + i * 2);
+	for (i = 0; i < ch_num; i++) {
+		res->tx_irq[ch_num - 1 - i] = pci_irq_vector(pdev, 2 + i * 2);
 	}
 
 	plat->flags |= STMMAC_FLAG_MULTI_MSI_EN;
@@ -593,7 +584,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 		goto err_disable_device;
 
 	/* Use the common MAC IRQ if per-channel MSIs allocation failed */
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+	if (ld->multichan)
 		loongson_dwmac_msi_config(pdev, plat, &res);
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat, &res);
@@ -605,7 +596,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 err_plat_clear:
 	if (dev_of_node(&pdev->dev))
 		loongson_dwmac_dt_clear(pdev, plat);
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+	if (ld->multichan)
 		loongson_dwmac_msi_clear(pdev);
 err_disable_device:
 	pci_disable_device(pdev);
@@ -624,7 +615,7 @@ static void loongson_dwmac_remove(struct pci_dev *pdev)
 	if (dev_of_node(&pdev->dev))
 		loongson_dwmac_dt_clear(pdev, priv->plat);
 
-	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+	if (ld->multichan)
 		loongson_dwmac_msi_clear(pdev);
 
 	pci_disable_device(pdev);
@@ -669,7 +660,8 @@ static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend,
 			 loongson_dwmac_resume);
 
 static const struct pci_device_id loongson_dwmac_id_table[] = {
-	{ PCI_DEVICE_DATA(LOONGSON, GMAC, &loongson_gmac_pci_info) },
+	{ PCI_DEVICE_DATA(LOONGSON, GMAC1, &loongson_gmac_pci_info) },
+	{ PCI_DEVICE_DATA(LOONGSON, GMAC2, &loongson_gmac_pci_info) },
 	{ PCI_DEVICE_DATA(LOONGSON, GNET, &loongson_gnet_pci_info) },
 	{}
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index d178d5ddc7c7..39421d6a34e4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -581,7 +581,6 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev,
 	int i;
 
 	priv_plat->phy_mode = plat->phy_interface;
-	plat->mac_interface = priv_plat->phy_mode;
 	if (priv_plat->mac_wol)
 		plat->flags &= ~STMMAC_FLAG_USE_PHY_WOL;
 	else
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 0e4da216f942..e30bdf72331a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -106,12 +106,11 @@ struct qcom_ethqos {
 	struct platform_device *pdev;
 	void __iomem *rgmii_base;
 	void __iomem *mac_base;
-	int (*configure_func)(struct qcom_ethqos *ethqos);
+	int (*configure_func)(struct qcom_ethqos *ethqos, int speed);
 
 	unsigned int link_clk_rate;
 	struct clk *link_clk;
 	struct phy *serdes_phy;
-	int speed;
 	int serdes_speed;
 	phy_interface_t phy_mode;
 
@@ -385,7 +384,7 @@ static int ethqos_dll_configure(struct qcom_ethqos *ethqos)
 	return 0;
 }
 
-static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos)
+static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos, int speed)
 {
 	struct device *dev = &ethqos->pdev->dev;
 	int phase_shift;
@@ -412,7 +411,7 @@ static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos)
 	rgmii_updatel(ethqos, RGMII_CONFIG_INTF_SEL,
 		      0, RGMII_IO_MACRO_CONFIG);
 
-	switch (ethqos->speed) {
+	switch (speed) {
 	case SPEED_1000:
 		rgmii_updatel(ethqos, RGMII_CONFIG_DDR_MODE,
 			      RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG);
@@ -532,14 +531,14 @@ static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos)
 			      loopback, RGMII_IO_MACRO_CONFIG);
 		break;
 	default:
-		dev_err(dev, "Invalid speed %d\n", ethqos->speed);
+		dev_err(dev, "Invalid speed %d\n", speed);
 		return -EINVAL;
 	}
 
 	return 0;
 }
 
-static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
+static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos, int speed)
 {
 	struct device *dev = &ethqos->pdev->dev;
 	volatile unsigned int dll_lock;
@@ -562,7 +561,7 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
 		      SDCC_DLL_CONFIG_PDN, SDCC_HC_REG_DLL_CONFIG);
 
 	if (ethqos->has_emac_ge_3) {
-		if (ethqos->speed == SPEED_1000) {
+		if (speed == SPEED_1000) {
 			rgmii_writel(ethqos, 0x1800000, SDCC_TEST_CTL);
 			rgmii_writel(ethqos, 0x2C010800, SDCC_USR_CTL);
 			rgmii_writel(ethqos, 0xA001, SDCC_HC_REG_DLL_CONFIG2);
@@ -580,7 +579,7 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
 	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_PDN, 0,
 		      SDCC_HC_REG_DLL_CONFIG);
 
-	if (ethqos->speed != SPEED_100 && ethqos->speed != SPEED_10) {
+	if (speed != SPEED_100 && speed != SPEED_10) {
 		/* Set DLL_EN */
 		rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_EN,
 			      SDCC_DLL_CONFIG_DLL_EN, SDCC_HC_REG_DLL_CONFIG);
@@ -607,10 +606,10 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
 			dev_err(dev, "Timeout while waiting for DLL lock\n");
 	}
 
-	if (ethqos->speed == SPEED_1000)
+	if (speed == SPEED_1000)
 		ethqos_dll_configure(ethqos);
 
-	ethqos_rgmii_macro_init(ethqos);
+	ethqos_rgmii_macro_init(ethqos, speed);
 
 	return 0;
 }
@@ -626,7 +625,7 @@ static void ethqos_set_serdes_speed(struct qcom_ethqos *ethqos, int speed)
 /* On interface toggle MAC registers gets reset.
  * Configure MAC block for SGMII on ethernet phy link up
  */
-static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
+static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos, int speed)
 {
 	struct net_device *dev = platform_get_drvdata(ethqos->pdev);
 	struct stmmac_priv *priv = netdev_priv(dev);
@@ -634,7 +633,7 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 
 	val = readl(ethqos->mac_base + MAC_CTRL_REG);
 
-	switch (ethqos->speed) {
+	switch (speed) {
 	case SPEED_2500:
 		val &= ~ETHQOS_MAC_CTRL_PORT_SEL;
 		rgmii_updatel(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG,
@@ -673,17 +672,9 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 	return val;
 }
 
-static void qcom_ethqos_speed_mode_2500(struct net_device *ndev, void *data)
+static int ethqos_configure(struct qcom_ethqos *ethqos, int speed)
 {
-	struct stmmac_priv *priv = netdev_priv(ndev);
-
-	priv->plat->max_speed = 2500;
-	priv->plat->phy_interface = PHY_INTERFACE_MODE_2500BASEX;
-}
-
-static int ethqos_configure(struct qcom_ethqos *ethqos)
-{
-	return ethqos->configure_func(ethqos);
+	return ethqos->configure_func(ethqos, speed);
 }
 
 static void ethqos_fix_mac_speed(void *priv, int speed, unsigned int mode)
@@ -691,9 +682,8 @@ static void ethqos_fix_mac_speed(void *priv, int speed, unsigned int mode)
 	struct qcom_ethqos *ethqos = priv;
 
 	qcom_ethqos_set_sgmii_loopback(ethqos, false);
-	ethqos->speed = speed;
 	ethqos_update_link_clk(ethqos, speed);
-	ethqos_configure(ethqos);
+	ethqos_configure(ethqos, speed);
 }
 
 static int qcom_ethqos_serdes_powerup(struct net_device *ndev, void *priv)
@@ -709,7 +699,7 @@ static int qcom_ethqos_serdes_powerup(struct net_device *ndev, void *priv)
 	if (ret)
 		return ret;
 
-	return phy_set_speed(ethqos->serdes_phy, ethqos->speed);
+	return phy_set_speed(ethqos->serdes_phy, ethqos->serdes_speed);
 }
 
 static void qcom_ethqos_serdes_powerdown(struct net_device *ndev, void *priv)
@@ -803,8 +793,6 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 		ethqos->configure_func = ethqos_configure_rgmii;
 		break;
 	case PHY_INTERFACE_MODE_2500BASEX:
-		plat_dat->speed_mode_2500 = qcom_ethqos_speed_mode_2500;
-		fallthrough;
 	case PHY_INTERFACE_MODE_SGMII:
 		ethqos->configure_func = ethqos_configure_sgmii;
 		break;
@@ -847,7 +835,6 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, PTR_ERR(ethqos->serdes_phy),
 				     "Failed to get serdes phy\n");
 
-	ethqos->speed = SPEED_1000;
 	ethqos->serdes_speed = SPEED_1000;
 	ethqos_update_link_clk(ethqos, SPEED_1000);
 	ethqos_set_func_clk_en(ethqos);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c
new file mode 100644
index 000000000000..9a774046455b
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * dwmac-renesas-gbeth.c - DWMAC Specific Glue layer for Renesas GBETH
+ *
+ * The Rx and Tx clocks are supplied as follows for the GBETH IP.
+ *
+ *                         Rx / Tx
+ *   -------+------------- on / off -------
+ *          |
+ *          |            Rx-180 / Tx-180
+ *          +---- not ---- on / off -------
+ *
+ * Copyright (C) 2025 Renesas Electronics Corporation
+ */
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#include "stmmac_platform.h"
+
+struct renesas_gbeth {
+	struct plat_stmmacenet_data *plat_dat;
+	struct reset_control *rstc;
+	struct device *dev;
+};
+
+static const char *const renesas_gbeth_clks[] = {
+	"tx", "tx-180", "rx", "rx-180",
+};
+
+static int renesas_gbeth_init(struct platform_device *pdev, void *priv)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct renesas_gbeth *gbeth = priv;
+	int ret;
+
+	plat_dat = gbeth->plat_dat;
+
+	ret = reset_control_deassert(gbeth->rstc);
+	if (ret) {
+		dev_err(gbeth->dev, "Reset deassert failed\n");
+		return ret;
+	}
+
+	ret = clk_bulk_prepare_enable(plat_dat->num_clks,
+				      plat_dat->clks);
+	if (ret)
+		reset_control_assert(gbeth->rstc);
+
+	return ret;
+}
+
+static void renesas_gbeth_exit(struct platform_device *pdev, void *priv)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct renesas_gbeth *gbeth = priv;
+	int ret;
+
+	plat_dat = gbeth->plat_dat;
+
+	clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks);
+
+	ret = reset_control_assert(gbeth->rstc);
+	if (ret)
+		dev_err(gbeth->dev, "Reset assert failed\n");
+}
+
+static int renesas_gbeth_probe(struct platform_device *pdev)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct stmmac_resources stmmac_res;
+	struct device *dev = &pdev->dev;
+	struct renesas_gbeth *gbeth;
+	unsigned int i;
+	int err;
+
+	err = stmmac_get_platform_resources(pdev, &stmmac_res);
+	if (err)
+		return dev_err_probe(dev, err,
+				     "failed to get resources\n");
+
+	plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac);
+	if (IS_ERR(plat_dat))
+		return dev_err_probe(dev, PTR_ERR(plat_dat),
+				     "dt configuration failed\n");
+
+	gbeth = devm_kzalloc(dev, sizeof(*gbeth), GFP_KERNEL);
+	if (!gbeth)
+		return -ENOMEM;
+
+	plat_dat->num_clks = ARRAY_SIZE(renesas_gbeth_clks);
+	plat_dat->clks = devm_kcalloc(dev, plat_dat->num_clks,
+				      sizeof(*plat_dat->clks), GFP_KERNEL);
+	if (!plat_dat->clks)
+		return -ENOMEM;
+
+	for (i = 0; i < plat_dat->num_clks; i++)
+		plat_dat->clks[i].id = renesas_gbeth_clks[i];
+
+	err = devm_clk_bulk_get(dev, plat_dat->num_clks, plat_dat->clks);
+	if (err < 0)
+		return err;
+
+	plat_dat->clk_tx_i = stmmac_pltfr_find_clk(plat_dat, "tx");
+	if (!plat_dat->clk_tx_i)
+		return dev_err_probe(dev, -EINVAL,
+				     "error finding tx clock\n");
+
+	gbeth->rstc = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR(gbeth->rstc))
+		return PTR_ERR(gbeth->rstc);
+
+	gbeth->dev = dev;
+	gbeth->plat_dat = plat_dat;
+	plat_dat->bsp_priv = gbeth;
+	plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
+	plat_dat->init = renesas_gbeth_init;
+	plat_dat->exit = renesas_gbeth_exit;
+	plat_dat->flags |= STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY |
+			   STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP |
+			   STMMAC_FLAG_SPH_DISABLE;
+
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
+}
+
+static const struct of_device_id renesas_gbeth_match[] = {
+	{ .compatible = "renesas,rzv2h-gbeth", },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, renesas_gbeth_match);
+
+static struct platform_driver renesas_gbeth_driver = {
+	.probe  = renesas_gbeth_probe,
+	.driver = {
+		.name		= "renesas-gbeth",
+		.of_match_table	= renesas_gbeth_match,
+	},
+};
+module_platform_driver(renesas_gbeth_driver);
+
+MODULE_AUTHOR("Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>");
+MODULE_DESCRIPTION("Renesas GBETH DWMAC Specific Glue layer");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 116855658559..72b50f6d72f4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -50,6 +50,7 @@ struct socfpga_dwmac {
 	u32	reg_offset;
 	u32	reg_shift;
 	struct	device *dev;
+	struct plat_stmmacenet_data *plat_dat;
 	struct regmap *sys_mgr_base_addr;
 	struct reset_control *stmmac_rst;
 	struct reset_control *stmmac_ocp_rst;
@@ -58,17 +59,15 @@ struct socfpga_dwmac {
 	void __iomem *sgmii_adapter_base;
 	bool f2h_ptp_ref_clk;
 	const struct socfpga_dwmac_ops *ops;
-	struct mdio_device *pcs_mdiodev;
 };
 
-static void socfpga_dwmac_fix_mac_speed(void *priv, int speed, unsigned int mode)
+static void socfpga_dwmac_fix_mac_speed(void *bsp_priv, int speed,
+					unsigned int mode)
 {
-	struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)priv;
+	struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)bsp_priv;
+	struct stmmac_priv *priv = netdev_priv(dev_get_drvdata(dwmac->dev));
 	void __iomem *splitter_base = dwmac->splitter_base;
 	void __iomem *sgmii_adapter_base = dwmac->sgmii_adapter_base;
-	struct device *dev = dwmac->dev;
-	struct net_device *ndev = dev_get_drvdata(dev);
-	struct phy_device *phy_dev = ndev->phydev;
 	u32 val;
 
 	if (sgmii_adapter_base)
@@ -95,7 +94,9 @@ static void socfpga_dwmac_fix_mac_speed(void *priv, int speed, unsigned int mode
 		writel(val, splitter_base + EMAC_SPLITTER_CTRL_REG);
 	}
 
-	if (phy_dev && sgmii_adapter_base)
+	if ((priv->plat->phy_interface == PHY_INTERFACE_MODE_SGMII ||
+	     priv->plat->phy_interface == PHY_INTERFACE_MODE_1000BASEX) &&
+	     sgmii_adapter_base)
 		writew(SGMII_ADAPTER_ENABLE,
 		       sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG);
 }
@@ -233,10 +234,7 @@ err_node_put:
 
 static int socfpga_get_plat_phymode(struct socfpga_dwmac *dwmac)
 {
-	struct net_device *ndev = dev_get_drvdata(dwmac->dev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-
-	return priv->plat->mac_interface;
+	return dwmac->plat_dat->mac_interface;
 }
 
 static void socfpga_sgmii_config(struct socfpga_dwmac *dwmac, bool enable)
@@ -258,6 +256,7 @@ static int socfpga_set_phy_mode_common(int phymode, u32 *val)
 	case PHY_INTERFACE_MODE_MII:
 	case PHY_INTERFACE_MODE_GMII:
 	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_1000BASEX:
 		*val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII;
 		break;
 	case PHY_INTERFACE_MODE_RMII:
@@ -435,6 +434,13 @@ static struct phylink_pcs *socfpga_dwmac_select_pcs(struct stmmac_priv *priv,
 	return priv->hw->phylink_pcs;
 }
 
+static int socfpga_dwmac_init(struct platform_device *pdev, void *bsp_priv)
+{
+	struct socfpga_dwmac *dwmac = bsp_priv;
+
+	return dwmac->ops->set_phy_mode(dwmac);
+}
+
 static int socfpga_dwmac_probe(struct platform_device *pdev)
 {
 	struct plat_stmmacenet_data *plat_dat;
@@ -442,8 +448,6 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 	struct device		*dev = &pdev->dev;
 	int			ret;
 	struct socfpga_dwmac	*dwmac;
-	struct net_device	*ndev;
-	struct stmmac_priv	*stpriv;
 	const struct socfpga_dwmac_ops *ops;
 
 	ops = device_get_match_data(&pdev->dev);
@@ -479,9 +483,17 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/* The socfpga driver needs to control the stmmac reset to set the phy
+	 * mode. Create a copy of the core reset handle so it can be used by
+	 * the driver later.
+	 */
+	dwmac->stmmac_rst = plat_dat->stmmac_rst;
 	dwmac->ops = ops;
+	dwmac->plat_dat = plat_dat;
+
 	plat_dat->bsp_priv = dwmac;
 	plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed;
+	plat_dat->init = socfpga_dwmac_init;
 	plat_dat->pcs_init = socfpga_dwmac_pcs_init;
 	plat_dat->pcs_exit = socfpga_dwmac_pcs_exit;
 	plat_dat->select_pcs = socfpga_dwmac_select_pcs;
@@ -489,67 +501,9 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 
 	plat_dat->riwt_off = 1;
 
-	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-	if (ret)
-		return ret;
-
-	ndev = platform_get_drvdata(pdev);
-	stpriv = netdev_priv(ndev);
-
-	/* The socfpga driver needs to control the stmmac reset to set the phy
-	 * mode. Create a copy of the core reset handle so it can be used by
-	 * the driver later.
-	 */
-	dwmac->stmmac_rst = stpriv->plat->stmmac_rst;
-
-	ret = ops->set_phy_mode(dwmac);
-	if (ret)
-		goto err_dvr_remove;
-
-	return 0;
-
-err_dvr_remove:
-	stmmac_dvr_remove(&pdev->dev);
-
-	return ret;
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int socfpga_dwmac_resume(struct device *dev)
-{
-	struct net_device *ndev = dev_get_drvdata(dev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-	struct socfpga_dwmac *dwmac_priv = get_stmmac_bsp_priv(dev);
-
-	dwmac_priv->ops->set_phy_mode(priv->plat->bsp_priv);
-
-	return stmmac_resume(dev);
-}
-#endif /* CONFIG_PM_SLEEP */
-
-static int __maybe_unused socfpga_dwmac_runtime_suspend(struct device *dev)
-{
-	struct net_device *ndev = dev_get_drvdata(dev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-
-	stmmac_bus_clks_config(priv, false);
-
-	return 0;
-}
-
-static int __maybe_unused socfpga_dwmac_runtime_resume(struct device *dev)
-{
-	struct net_device *ndev = dev_get_drvdata(dev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-
-	return stmmac_bus_clks_config(priv, true);
-}
-
-static const struct dev_pm_ops socfpga_dwmac_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(stmmac_suspend, socfpga_dwmac_resume)
-	SET_RUNTIME_PM_OPS(socfpga_dwmac_runtime_suspend, socfpga_dwmac_runtime_resume, NULL)
-};
-
 static const struct socfpga_dwmac_ops socfpga_gen5_ops = {
 	.set_phy_mode = socfpga_gen5_set_phy_mode,
 };
@@ -567,10 +521,9 @@ MODULE_DEVICE_TABLE(of, socfpga_dwmac_match);
 
 static struct platform_driver socfpga_dwmac_driver = {
 	.probe  = socfpga_dwmac_probe,
-	.remove = stmmac_pltfr_remove,
 	.driver = {
 		.name           = "socfpga-dwmac",
-		.pm		= &socfpga_dwmac_pm_ops,
+		.pm		= &stmmac_pltfr_pm_ops,
 		.of_match_table = socfpga_dwmac_match,
 	},
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
index be57c6c12c1c..53d5ce1f6dc6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -23,12 +23,7 @@
 
 #define DWMAC_50MHZ	50000000
 
-#define IS_PHY_IF_MODE_RGMII(iface)	(iface == PHY_INTERFACE_MODE_RGMII || \
-			iface == PHY_INTERFACE_MODE_RGMII_ID || \
-			iface == PHY_INTERFACE_MODE_RGMII_RXID || \
-			iface == PHY_INTERFACE_MODE_RGMII_TXID)
-
-#define IS_PHY_IF_MODE_GBIT(iface)	(IS_PHY_IF_MODE_RGMII(iface) || \
+#define IS_PHY_IF_MODE_GBIT(iface)	(phy_interface_mode_is_rgmii(iface) || \
 					 iface == PHY_INTERFACE_MODE_GMII)
 
 /* STiH4xx register definitions (STiH407/STiH410 families)
@@ -148,7 +143,7 @@ static void stih4xx_fix_retime_src(void *priv, int spd, unsigned int mode)
 			src = TX_RETIME_SRC_CLKGEN;
 			freq = DWMAC_50MHZ;
 		}
-	} else if (IS_PHY_IF_MODE_RGMII(dwmac->interface)) {
+	} else if (phy_interface_mode_is_rgmii(dwmac->interface)) {
 		/* On GiGa clk source can be either ext or from clkgen */
 		freq = rgmii_clock(spd);
 
@@ -238,6 +233,29 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
 	return 0;
 }
 
+static int sti_dwmac_init(struct platform_device *pdev, void *bsp_priv)
+{
+	struct sti_dwmac *dwmac = bsp_priv;
+	int ret;
+
+	ret = clk_prepare_enable(dwmac->clk);
+	if (ret)
+		return ret;
+
+	ret = sti_dwmac_set_mode(dwmac);
+	if (ret)
+		clk_disable_unprepare(dwmac->clk);
+
+	return ret;
+}
+
+static void sti_dwmac_exit(struct platform_device *pdev, void *bsp_priv)
+{
+	struct sti_dwmac *dwmac = bsp_priv;
+
+	clk_disable_unprepare(dwmac->clk);
+}
+
 static int sti_dwmac_probe(struct platform_device *pdev)
 {
 	struct plat_stmmacenet_data *plat_dat;
@@ -274,59 +292,12 @@ static int sti_dwmac_probe(struct platform_device *pdev)
 
 	plat_dat->bsp_priv = dwmac;
 	plat_dat->fix_mac_speed = data->fix_retime_src;
+	plat_dat->init = sti_dwmac_init;
+	plat_dat->exit = sti_dwmac_exit;
 
-	ret = clk_prepare_enable(dwmac->clk);
-	if (ret)
-		return ret;
-
-	ret = sti_dwmac_set_mode(dwmac);
-	if (ret)
-		goto disable_clk;
-
-	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-	if (ret)
-		goto disable_clk;
-
-	return 0;
-
-disable_clk:
-	clk_disable_unprepare(dwmac->clk);
-
-	return ret;
-}
-
-static void sti_dwmac_remove(struct platform_device *pdev)
-{
-	struct sti_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev);
-
-	stmmac_dvr_remove(&pdev->dev);
-
-	clk_disable_unprepare(dwmac->clk);
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 }
 
-static int sti_dwmac_suspend(struct device *dev)
-{
-	struct sti_dwmac *dwmac = get_stmmac_bsp_priv(dev);
-	int ret = stmmac_suspend(dev);
-
-	clk_disable_unprepare(dwmac->clk);
-
-	return ret;
-}
-
-static int sti_dwmac_resume(struct device *dev)
-{
-	struct sti_dwmac *dwmac = get_stmmac_bsp_priv(dev);
-
-	clk_prepare_enable(dwmac->clk);
-	sti_dwmac_set_mode(dwmac);
-
-	return stmmac_resume(dev);
-}
-
-static DEFINE_SIMPLE_DEV_PM_OPS(sti_dwmac_pm_ops, sti_dwmac_suspend,
-						  sti_dwmac_resume);
-
 static const struct sti_dwmac_of_data stih4xx_dwmac_data = {
 	.fix_retime_src = stih4xx_fix_retime_src,
 };
@@ -339,10 +310,9 @@ MODULE_DEVICE_TABLE(of, sti_dwmac_match);
 
 static struct platform_driver sti_dwmac_driver = {
 	.probe  = sti_dwmac_probe,
-	.remove = sti_dwmac_remove,
 	.driver = {
 		.name           = "sti-dwmac",
-		.pm		= pm_sleep_ptr(&sti_dwmac_pm_ops),
+		.pm		= &stmmac_pltfr_pm_ops,
 		.of_match_table = sti_dwmac_match,
 	},
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
index c3d321192581..1eb16eec9c0d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
@@ -119,7 +119,7 @@ struct stm32_ops {
 	u32 syscfg_clr_off;
 };
 
-static int stm32_dwmac_clk_enable(struct stm32_dwmac *dwmac, bool resume)
+static int stm32_dwmac_clk_enable(struct stm32_dwmac *dwmac)
 {
 	int ret;
 
@@ -127,11 +127,9 @@ static int stm32_dwmac_clk_enable(struct stm32_dwmac *dwmac, bool resume)
 	if (ret)
 		goto err_clk_tx;
 
-	if (!dwmac->ops->clk_rx_enable_in_suspend || !resume) {
-		ret = clk_prepare_enable(dwmac->clk_rx);
-		if (ret)
-			goto err_clk_rx;
-	}
+	ret = clk_prepare_enable(dwmac->clk_rx);
+	if (ret)
+		goto err_clk_rx;
 
 	ret = clk_prepare_enable(dwmac->syscfg_clk);
 	if (ret)
@@ -148,15 +146,14 @@ static int stm32_dwmac_clk_enable(struct stm32_dwmac *dwmac, bool resume)
 err_clk_eth_ck:
 	clk_disable_unprepare(dwmac->syscfg_clk);
 err_syscfg_clk:
-	if (!dwmac->ops->clk_rx_enable_in_suspend || !resume)
-		clk_disable_unprepare(dwmac->clk_rx);
+	clk_disable_unprepare(dwmac->clk_rx);
 err_clk_rx:
 	clk_disable_unprepare(dwmac->clk_tx);
 err_clk_tx:
 	return ret;
 }
 
-static int stm32_dwmac_init(struct plat_stmmacenet_data *plat_dat, bool resume)
+static int stm32_dwmac_init(struct plat_stmmacenet_data *plat_dat)
 {
 	struct stm32_dwmac *dwmac = plat_dat->bsp_priv;
 	int ret;
@@ -167,7 +164,7 @@ static int stm32_dwmac_init(struct plat_stmmacenet_data *plat_dat, bool resume)
 			return ret;
 	}
 
-	return stm32_dwmac_clk_enable(dwmac, resume);
+	return stm32_dwmac_clk_enable(dwmac);
 }
 
 static int stm32mp1_select_ethck_external(struct plat_stmmacenet_data *plat_dat)
@@ -382,12 +379,10 @@ static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat)
 				 SYSCFG_MCU_ETH_MASK, val << 23);
 }
 
-static void stm32_dwmac_clk_disable(struct stm32_dwmac *dwmac, bool suspend)
+static void stm32_dwmac_clk_disable(struct stm32_dwmac *dwmac)
 {
 	clk_disable_unprepare(dwmac->clk_tx);
-	if (!dwmac->ops->clk_rx_enable_in_suspend || !suspend)
-		clk_disable_unprepare(dwmac->clk_rx);
-
+	clk_disable_unprepare(dwmac->clk_rx);
 	clk_disable_unprepare(dwmac->syscfg_clk);
 	if (dwmac->enable_eth_ck)
 		clk_disable_unprepare(dwmac->clk_eth_ck);
@@ -541,18 +536,32 @@ static int stm32_dwmac_probe(struct platform_device *pdev)
 	plat_dat->flags |= STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP;
 	plat_dat->bsp_priv = dwmac;
 
-	ret = stm32_dwmac_init(plat_dat, false);
+	ret = stm32_dwmac_init(plat_dat);
 	if (ret)
 		return ret;
 
+	/* If this platform requires the clock to be running in suspend,
+	 * prepare and enable the receive clock an additional time to keep
+	 * it running.
+	 */
+	if (dwmac->ops->clk_rx_enable_in_suspend) {
+		ret = clk_prepare_enable(dwmac->clk_rx);
+		if (ret)
+			goto err_clk_disable;
+	}
+
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
-		goto err_clk_disable;
+		goto err_clk_disable_suspend;
 
 	return 0;
 
+err_clk_disable_suspend:
+	if (dwmac->ops->clk_rx_enable_in_suspend)
+		clk_disable_unprepare(dwmac->clk_rx);
+
 err_clk_disable:
-	stm32_dwmac_clk_disable(dwmac, false);
+	stm32_dwmac_clk_disable(dwmac);
 
 	return ret;
 }
@@ -565,7 +574,15 @@ static void stm32_dwmac_remove(struct platform_device *pdev)
 
 	stmmac_dvr_remove(&pdev->dev);
 
-	stm32_dwmac_clk_disable(dwmac, false);
+	/* If this platform requires the clock to be running in suspend,
+	 * we need to disable and unprepare the receive clock an additional
+	 * time to balance the extra clk_prepare_enable() in the probe
+	 * function.
+	 */
+	if (dwmac->ops->clk_rx_enable_in_suspend)
+		clk_disable_unprepare(dwmac->clk_rx);
+
+	stm32_dwmac_clk_disable(dwmac);
 
 	if (dwmac->irq_pwr_wakeup >= 0) {
 		dev_pm_clear_wake_irq(&pdev->dev);
@@ -596,7 +613,7 @@ static int stm32_dwmac_suspend(struct device *dev)
 	if (ret)
 		return ret;
 
-	stm32_dwmac_clk_disable(dwmac, true);
+	stm32_dwmac_clk_disable(dwmac);
 
 	if (dwmac->ops->suspend)
 		ret = dwmac->ops->suspend(dwmac);
@@ -614,7 +631,7 @@ static int stm32_dwmac_resume(struct device *dev)
 	if (dwmac->ops->resume)
 		dwmac->ops->resume(dwmac);
 
-	ret = stm32_dwmac_init(priv->plat, true);
+	ret = stm32_dwmac_init(priv->plat);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 85723a78793a..2796dc426943 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -964,7 +964,7 @@ static int sun8i_dwmac_set_syscon(struct device *dev,
 		/* of_mdio_parse_addr returns a valid (0 ~ 31) PHY
 		 * address. No need to mask it again.
 		 */
-		reg |= 1 << H3_EPHY_ADDR_SHIFT;
+		reg |= ret << H3_EPHY_ADDR_SHIFT;
 	} else {
 		/* For SoCs without internal PHY the PHY selection bit should be
 		 * set to 0 (external PHY).
@@ -1239,14 +1239,10 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = sun8i_dwmac_init(pdev, plat_dat->bsp_priv);
+	ret = stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 	if (ret)
 		goto dwmac_syscon;
 
-	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-	if (ret)
-		goto dwmac_exit;
-
 	ndev = dev_get_drvdata(&pdev->dev);
 	priv = netdev_priv(ndev);
 
@@ -1283,9 +1279,7 @@ dwmac_mux:
 	clk_put(gmac->ephy_clk);
 dwmac_remove:
 	pm_runtime_put_noidle(&pdev->dev);
-	stmmac_dvr_remove(&pdev->dev);
-dwmac_exit:
-	sun8i_dwmac_exit(pdev, gmac);
+	stmmac_pltfr_remove(pdev);
 dwmac_syscon:
 	sun8i_dwmac_unset_syscon(gmac);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index 9f098ff0ff05..1eadcf5d1ad6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -72,28 +72,28 @@ static void sun7i_gmac_exit(struct platform_device *pdev, void *priv)
 		regulator_disable(gmac->regulator);
 }
 
-static void sun7i_fix_speed(void *priv, int speed, unsigned int mode)
+static int sun7i_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+				 phy_interface_t interface, int speed)
 {
-	struct sunxi_priv_data *gmac = priv;
-
-	/* only GMII mode requires us to reconfigure the clock lines */
-	if (gmac->interface != PHY_INTERFACE_MODE_GMII)
-		return;
-
-	if (gmac->clk_enabled) {
-		clk_disable(gmac->tx_clk);
-		gmac->clk_enabled = 0;
-	}
-	clk_unprepare(gmac->tx_clk);
-
-	if (speed == 1000) {
-		clk_set_rate(gmac->tx_clk, SUN7I_GMAC_GMII_RGMII_RATE);
-		clk_prepare_enable(gmac->tx_clk);
-		gmac->clk_enabled = 1;
-	} else {
-		clk_set_rate(gmac->tx_clk, SUN7I_GMAC_MII_RATE);
-		clk_prepare(gmac->tx_clk);
+	struct sunxi_priv_data *gmac = bsp_priv;
+
+	if (interface == PHY_INTERFACE_MODE_GMII) {
+		if (gmac->clk_enabled) {
+			clk_disable(gmac->tx_clk);
+			gmac->clk_enabled = 0;
+		}
+		clk_unprepare(gmac->tx_clk);
+
+		if (speed == 1000) {
+			clk_set_rate(gmac->tx_clk, SUN7I_GMAC_GMII_RGMII_RATE);
+			clk_prepare_enable(gmac->tx_clk);
+			gmac->clk_enabled = 1;
+		} else {
+			clk_set_rate(gmac->tx_clk, SUN7I_GMAC_MII_RATE);
+			clk_prepare(gmac->tx_clk);
+		}
 	}
+	return 0;
 }
 
 static int sun7i_gmac_probe(struct platform_device *pdev)
@@ -140,24 +140,11 @@ static int sun7i_gmac_probe(struct platform_device *pdev)
 	plat_dat->bsp_priv = gmac;
 	plat_dat->init = sun7i_gmac_init;
 	plat_dat->exit = sun7i_gmac_exit;
-	plat_dat->fix_mac_speed = sun7i_fix_speed;
+	plat_dat->set_clk_tx_rate = sun7i_set_clk_tx_rate;
 	plat_dat->tx_fifo_size = 4096;
 	plat_dat->rx_fifo_size = 16384;
 
-	ret = sun7i_gmac_init(pdev, plat_dat->bsp_priv);
-	if (ret)
-		return ret;
-
-	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-	if (ret)
-		goto err_gmac_exit;
-
-	return 0;
-
-err_gmac_exit:
-	sun7i_gmac_exit(pdev, plat_dat->bsp_priv);
-
-	return ret;
+	return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res);
 }
 
 static const struct of_device_id sun7i_dwmac_match[] = {
@@ -168,7 +155,6 @@ MODULE_DEVICE_TABLE(of, sun7i_dwmac_match);
 
 static struct platform_driver sun7i_dwmac_driver = {
 	.probe  = sun7i_gmac_probe,
-	.remove = stmmac_pltfr_remove,
 	.driver = {
 		.name           = "sun7i-dwmac",
 		.pm		= &stmmac_pltfr_pm_ops,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
index 33cf99797df5..5e6ac82a89b9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
@@ -51,21 +51,14 @@ struct visconti_eth {
 	u32 phy_intf_sel;
 	struct clk *phy_ref_clk;
 	struct device *dev;
-	spinlock_t lock; /* lock to protect register update */
 };
 
-static void visconti_eth_fix_mac_speed(void *priv, int speed, unsigned int mode)
+static int visconti_eth_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+					phy_interface_t interface, int speed)
 {
-	struct visconti_eth *dwmac = priv;
+	struct visconti_eth *dwmac = bsp_priv;
 	struct net_device *netdev = dev_get_drvdata(dwmac->dev);
 	unsigned int val, clk_sel_val = 0;
-	unsigned long flags;
-
-	spin_lock_irqsave(&dwmac->lock, flags);
-
-	/* adjust link */
-	val = readl(dwmac->reg + MAC_CTRL_REG);
-	val &= ~(GMAC_CONFIG_PS | GMAC_CONFIG_FES);
 
 	switch (speed) {
 	case SPEED_1000:
@@ -77,24 +70,19 @@ static void visconti_eth_fix_mac_speed(void *priv, int speed, unsigned int mode)
 			clk_sel_val = ETHER_CLK_SEL_FREQ_SEL_25M;
 		if (dwmac->phy_intf_sel == ETHER_CONFIG_INTF_RMII)
 			clk_sel_val = ETHER_CLK_SEL_DIV_SEL_2;
-		val |= GMAC_CONFIG_PS | GMAC_CONFIG_FES;
 		break;
 	case SPEED_10:
 		if (dwmac->phy_intf_sel == ETHER_CONFIG_INTF_RGMII)
 			clk_sel_val = ETHER_CLK_SEL_FREQ_SEL_2P5M;
 		if (dwmac->phy_intf_sel == ETHER_CONFIG_INTF_RMII)
 			clk_sel_val = ETHER_CLK_SEL_DIV_SEL_20;
-		val |= GMAC_CONFIG_PS;
 		break;
 	default:
 		/* No bit control */
 		netdev_err(netdev, "Unsupported speed request (%d)", speed);
-		spin_unlock_irqrestore(&dwmac->lock, flags);
-		return;
+		return -EINVAL;
 	}
 
-	writel(val, dwmac->reg + MAC_CTRL_REG);
-
 	/* Stop internal clock */
 	val = readl(dwmac->reg + REG_ETHER_CLOCK_SEL);
 	val &= ~(ETHER_CLK_SEL_RMII_CLK_EN | ETHER_CLK_SEL_RX_TX_CLK_EN);
@@ -136,7 +124,7 @@ static void visconti_eth_fix_mac_speed(void *priv, int speed, unsigned int mode)
 		break;
 	}
 
-	spin_unlock_irqrestore(&dwmac->lock, flags);
+	return 0;
 }
 
 static int visconti_eth_init_hw(struct platform_device *pdev, struct plat_stmmacenet_data *plat_dat)
@@ -228,11 +216,10 @@ static int visconti_eth_dwmac_probe(struct platform_device *pdev)
 	if (!dwmac)
 		return -ENOMEM;
 
-	spin_lock_init(&dwmac->lock);
 	dwmac->reg = stmmac_res.addr;
 	dwmac->dev = &pdev->dev;
 	plat_dat->bsp_priv = dwmac;
-	plat_dat->fix_mac_speed = visconti_eth_fix_mac_speed;
+	plat_dat->set_clk_tx_rate = visconti_eth_set_clk_tx_rate;
 
 	ret = visconti_eth_clock_probe(pdev, plat_dat);
 	if (ret)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index 967a16212faf..0c011a47d5a3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -320,8 +320,8 @@ enum rtc_control {
 
 /* PTP and timestamping registers */
 
-#define GMAC3_X_ATSNS       GENMASK(19, 16)
-#define GMAC3_X_ATSNS_SHIFT 16
+#define GMAC3_X_ATSNS       GENMASK(29, 25)
+#define GMAC3_X_ATSNS_SHIFT 25
 
 #define GMAC_PTP_TCR_ATSFC	BIT(24)
 #define GMAC_PTP_TCR_ATSEN0	BIT(25)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index a8b901cdf5cb..56b76aaa58f0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -553,7 +553,7 @@ void dwmac1000_get_ptptime(void __iomem *ptpaddr, u64 *ptp_time)
 	u64 ns;
 
 	ns = readl(ptpaddr + GMAC_PTP_ATNR);
-	ns += readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;
+	ns += (u64)readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;
 
 	*ptp_time = ns;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 42fe29a4e300..f4694fd576f5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -17,11 +17,7 @@
 #define GMAC_EXT_CONFIG			0x00000004
 #define GMAC_PACKET_FILTER		0x00000008
 #define GMAC_HASH_TAB(x)		(0x10 + (x) * 4)
-#define GMAC_VLAN_TAG			0x00000050
-#define GMAC_VLAN_TAG_DATA		0x00000054
-#define GMAC_VLAN_HASH_TABLE		0x00000058
 #define GMAC_RX_FLOW_CTRL		0x00000090
-#define GMAC_VLAN_INCL			0x00000060
 #define GMAC_QX_TX_FLOW_CTRL(x)		(0x70 + x * 4)
 #define GMAC_TXQ_PRTY_MAP0		0x98
 #define GMAC_TXQ_PRTY_MAP1		0x9C
@@ -31,7 +27,6 @@
 #define GMAC_RXQ_CTRL3			0x000000ac
 #define GMAC_INT_STATUS			0x000000b0
 #define GMAC_INT_EN			0x000000b4
-#define GMAC_1US_TIC_COUNTER		0x000000dc
 #define GMAC_PCS_BASE			0x000000e0
 #define GMAC_PHYIF_CONTROL_STATUS	0x000000f8
 #define GMAC_PMT			0x000000c0
@@ -82,42 +77,6 @@
 
 #define GMAC_MAX_PERFECT_ADDRESSES	128
 
-/* MAC VLAN */
-#define GMAC_VLAN_EDVLP			BIT(26)
-#define GMAC_VLAN_VTHM			BIT(25)
-#define GMAC_VLAN_DOVLTC		BIT(20)
-#define GMAC_VLAN_ESVL			BIT(18)
-#define GMAC_VLAN_ETV			BIT(16)
-#define GMAC_VLAN_VID			GENMASK(15, 0)
-#define GMAC_VLAN_VLTI			BIT(20)
-#define GMAC_VLAN_CSVL			BIT(19)
-#define GMAC_VLAN_VLC			GENMASK(17, 16)
-#define GMAC_VLAN_VLC_SHIFT		16
-#define GMAC_VLAN_VLHT			GENMASK(15, 0)
-
-/* MAC VLAN Tag */
-#define GMAC_VLAN_TAG_VID		GENMASK(15, 0)
-#define GMAC_VLAN_TAG_ETV		BIT(16)
-
-/* MAC VLAN Tag Control */
-#define GMAC_VLAN_TAG_CTRL_OB		BIT(0)
-#define GMAC_VLAN_TAG_CTRL_CT		BIT(1)
-#define GMAC_VLAN_TAG_CTRL_OFS_MASK	GENMASK(6, 2)
-#define GMAC_VLAN_TAG_CTRL_OFS_SHIFT	2
-#define GMAC_VLAN_TAG_CTRL_EVLS_MASK	GENMASK(22, 21)
-#define GMAC_VLAN_TAG_CTRL_EVLS_SHIFT	21
-#define GMAC_VLAN_TAG_CTRL_EVLRXS	BIT(24)
-
-#define GMAC_VLAN_TAG_STRIP_NONE	(0x0 << GMAC_VLAN_TAG_CTRL_EVLS_SHIFT)
-#define GMAC_VLAN_TAG_STRIP_PASS	(0x1 << GMAC_VLAN_TAG_CTRL_EVLS_SHIFT)
-#define GMAC_VLAN_TAG_STRIP_FAIL	(0x2 << GMAC_VLAN_TAG_CTRL_EVLS_SHIFT)
-#define GMAC_VLAN_TAG_STRIP_ALL		(0x3 << GMAC_VLAN_TAG_CTRL_EVLS_SHIFT)
-
-/* MAC VLAN Tag Data/Filter */
-#define GMAC_VLAN_TAG_DATA_VID		GENMASK(15, 0)
-#define GMAC_VLAN_TAG_DATA_VEN		BIT(16)
-#define GMAC_VLAN_TAG_DATA_ETV		BIT(17)
-
 /* MAC RX Queue Enable */
 #define GMAC_RX_QUEUE_CLEAR(queue)	~(GENMASK(1, 0) << ((queue) * 2))
 #define GMAC_RX_AV_QUEUE_ENABLE(queue)	BIT((queue) * 2)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index cc4ddf608652..9c2549d4100f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -18,6 +18,7 @@
 #include "stmmac.h"
 #include "stmmac_fpe.h"
 #include "stmmac_pcs.h"
+#include "stmmac_vlan.h"
 #include "dwmac4.h"
 #include "dwmac5.h"
 
@@ -448,165 +449,6 @@ static void dwmac4_set_eee_timer(struct mac_device_info *hw, int ls, int tw)
 	writel(value, ioaddr + GMAC4_LPI_TIMER_CTRL);
 }
 
-static void dwmac4_write_single_vlan(struct net_device *dev, u16 vid)
-{
-	void __iomem *ioaddr = (void __iomem *)dev->base_addr;
-	u32 val;
-
-	val = readl(ioaddr + GMAC_VLAN_TAG);
-	val &= ~GMAC_VLAN_TAG_VID;
-	val |= GMAC_VLAN_TAG_ETV | vid;
-
-	writel(val, ioaddr + GMAC_VLAN_TAG);
-}
-
-static int dwmac4_write_vlan_filter(struct net_device *dev,
-				    struct mac_device_info *hw,
-				    u8 index, u32 data)
-{
-	void __iomem *ioaddr = (void __iomem *)dev->base_addr;
-	int ret;
-	u32 val;
-
-	if (index >= hw->num_vlan)
-		return -EINVAL;
-
-	writel(data, ioaddr + GMAC_VLAN_TAG_DATA);
-
-	val = readl(ioaddr + GMAC_VLAN_TAG);
-	val &= ~(GMAC_VLAN_TAG_CTRL_OFS_MASK |
-		GMAC_VLAN_TAG_CTRL_CT |
-		GMAC_VLAN_TAG_CTRL_OB);
-	val |= (index << GMAC_VLAN_TAG_CTRL_OFS_SHIFT) | GMAC_VLAN_TAG_CTRL_OB;
-
-	writel(val, ioaddr + GMAC_VLAN_TAG);
-
-	ret = readl_poll_timeout(ioaddr + GMAC_VLAN_TAG, val,
-				 !(val & GMAC_VLAN_TAG_CTRL_OB),
-				 1000, 500000);
-	if (ret) {
-		netdev_err(dev, "Timeout accessing MAC_VLAN_Tag_Filter\n");
-		return -EBUSY;
-	}
-
-	return 0;
-}
-
-static int dwmac4_add_hw_vlan_rx_fltr(struct net_device *dev,
-				      struct mac_device_info *hw,
-				      __be16 proto, u16 vid)
-{
-	int index = -1;
-	u32 val = 0;
-	int i, ret;
-
-	if (vid > 4095)
-		return -EINVAL;
-
-	/* Single Rx VLAN Filter */
-	if (hw->num_vlan == 1) {
-		/* For single VLAN filter, VID 0 means VLAN promiscuous */
-		if (vid == 0) {
-			netdev_warn(dev, "Adding VLAN ID 0 is not supported\n");
-			return -EPERM;
-		}
-
-		if (hw->vlan_filter[0] & GMAC_VLAN_TAG_VID) {
-			netdev_err(dev, "Only single VLAN ID supported\n");
-			return -EPERM;
-		}
-
-		hw->vlan_filter[0] = vid;
-		dwmac4_write_single_vlan(dev, vid);
-
-		return 0;
-	}
-
-	/* Extended Rx VLAN Filter Enable */
-	val |= GMAC_VLAN_TAG_DATA_ETV | GMAC_VLAN_TAG_DATA_VEN | vid;
-
-	for (i = 0; i < hw->num_vlan; i++) {
-		if (hw->vlan_filter[i] == val)
-			return 0;
-		else if (!(hw->vlan_filter[i] & GMAC_VLAN_TAG_DATA_VEN))
-			index = i;
-	}
-
-	if (index == -1) {
-		netdev_err(dev, "MAC_VLAN_Tag_Filter full (size: %0u)\n",
-			   hw->num_vlan);
-		return -EPERM;
-	}
-
-	ret = dwmac4_write_vlan_filter(dev, hw, index, val);
-
-	if (!ret)
-		hw->vlan_filter[index] = val;
-
-	return ret;
-}
-
-static int dwmac4_del_hw_vlan_rx_fltr(struct net_device *dev,
-				      struct mac_device_info *hw,
-				      __be16 proto, u16 vid)
-{
-	int i, ret = 0;
-
-	/* Single Rx VLAN Filter */
-	if (hw->num_vlan == 1) {
-		if ((hw->vlan_filter[0] & GMAC_VLAN_TAG_VID) == vid) {
-			hw->vlan_filter[0] = 0;
-			dwmac4_write_single_vlan(dev, 0);
-		}
-		return 0;
-	}
-
-	/* Extended Rx VLAN Filter Enable */
-	for (i = 0; i < hw->num_vlan; i++) {
-		if ((hw->vlan_filter[i] & GMAC_VLAN_TAG_DATA_VID) == vid) {
-			ret = dwmac4_write_vlan_filter(dev, hw, i, 0);
-
-			if (!ret)
-				hw->vlan_filter[i] = 0;
-			else
-				return ret;
-		}
-	}
-
-	return ret;
-}
-
-static void dwmac4_restore_hw_vlan_rx_fltr(struct net_device *dev,
-					   struct mac_device_info *hw)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-	u32 hash;
-	u32 val;
-	int i;
-
-	/* Single Rx VLAN Filter */
-	if (hw->num_vlan == 1) {
-		dwmac4_write_single_vlan(dev, hw->vlan_filter[0]);
-		return;
-	}
-
-	/* Extended Rx VLAN Filter Enable */
-	for (i = 0; i < hw->num_vlan; i++) {
-		if (hw->vlan_filter[i] & GMAC_VLAN_TAG_DATA_VEN) {
-			val = hw->vlan_filter[i];
-			dwmac4_write_vlan_filter(dev, hw, i, val);
-		}
-	}
-
-	hash = readl(ioaddr + GMAC_VLAN_HASH_TABLE);
-	if (hash & GMAC_VLAN_VLHT) {
-		value = readl(ioaddr + GMAC_VLAN_TAG);
-		value |= GMAC_VLAN_VTHM;
-		writel(value, ioaddr + GMAC_VLAN_TAG);
-	}
-}
-
 static void dwmac4_set_filter(struct mac_device_info *hw,
 			      struct net_device *dev)
 {
@@ -965,45 +807,6 @@ static void dwmac4_set_mac_loopback(void __iomem *ioaddr, bool enable)
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash,
-				    u16 perfect_match, bool is_double)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-
-	writel(hash, ioaddr + GMAC_VLAN_HASH_TABLE);
-
-	value = readl(ioaddr + GMAC_VLAN_TAG);
-
-	if (hash) {
-		value |= GMAC_VLAN_VTHM | GMAC_VLAN_ETV;
-		if (is_double) {
-			value |= GMAC_VLAN_EDVLP;
-			value |= GMAC_VLAN_ESVL;
-			value |= GMAC_VLAN_DOVLTC;
-		}
-
-		writel(value, ioaddr + GMAC_VLAN_TAG);
-	} else if (perfect_match) {
-		u32 value = GMAC_VLAN_ETV;
-
-		if (is_double) {
-			value |= GMAC_VLAN_EDVLP;
-			value |= GMAC_VLAN_ESVL;
-			value |= GMAC_VLAN_DOVLTC;
-		}
-
-		writel(value | perfect_match, ioaddr + GMAC_VLAN_TAG);
-	} else {
-		value &= ~(GMAC_VLAN_VTHM | GMAC_VLAN_ETV);
-		value &= ~(GMAC_VLAN_EDVLP | GMAC_VLAN_ESVL);
-		value &= ~GMAC_VLAN_DOVLTC;
-		value &= ~GMAC_VLAN_VID;
-
-		writel(value, ioaddr + GMAC_VLAN_TAG);
-	}
-}
-
 static void dwmac4_sarc_configure(void __iomem *ioaddr, int val)
 {
 	u32 value = readl(ioaddr + GMAC_CONFIG);
@@ -1014,19 +817,6 @@ static void dwmac4_sarc_configure(void __iomem *ioaddr, int val)
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-static void dwmac4_enable_vlan(struct mac_device_info *hw, u32 type)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-
-	value = readl(ioaddr + GMAC_VLAN_INCL);
-	value |= GMAC_VLAN_VLTI;
-	value |= GMAC_VLAN_CSVL; /* Only use SVLAN */
-	value &= ~GMAC_VLAN_VLC;
-	value |= (type << GMAC_VLAN_VLC_SHIFT) & GMAC_VLAN_VLC;
-	writel(value, ioaddr + GMAC_VLAN_INCL);
-}
-
 static void dwmac4_set_arp_offload(struct mac_device_info *hw, bool en,
 				   u32 addr)
 {
@@ -1143,35 +933,6 @@ static int dwmac4_config_l4_filter(struct mac_device_info *hw, u32 filter_no,
 	return 0;
 }
 
-static void dwmac4_rx_hw_vlan(struct mac_device_info *hw,
-			      struct dma_desc *rx_desc, struct sk_buff *skb)
-{
-	if (hw->desc->get_rx_vlan_valid(rx_desc)) {
-		u16 vid = hw->desc->get_rx_vlan_tci(rx_desc);
-
-		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
-	}
-}
-
-static void dwmac4_set_hw_vlan_mode(struct mac_device_info *hw)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value = readl(ioaddr + GMAC_VLAN_TAG);
-
-	value &= ~GMAC_VLAN_TAG_CTRL_EVLS_MASK;
-
-	if (hw->hw_vlan_en)
-		/* Always strip VLAN on Receive */
-		value |= GMAC_VLAN_TAG_STRIP_ALL;
-	else
-		/* Do not strip VLAN on Receive */
-		value |= GMAC_VLAN_TAG_STRIP_NONE;
-
-	/* Enable outer VLAN Tag in Rx DMA descriptor */
-	value |= GMAC_VLAN_TAG_CTRL_EVLRXS;
-	writel(value, ioaddr + GMAC_VLAN_TAG);
-}
-
 const struct stmmac_ops dwmac4_ops = {
 	.core_init = dwmac4_core_init,
 	.update_caps = dwmac4_update_caps,
@@ -1201,17 +962,10 @@ const struct stmmac_ops dwmac4_ops = {
 	.debug = dwmac4_debug,
 	.set_filter = dwmac4_set_filter,
 	.set_mac_loopback = dwmac4_set_mac_loopback,
-	.update_vlan_hash = dwmac4_update_vlan_hash,
 	.sarc_configure = dwmac4_sarc_configure,
-	.enable_vlan = dwmac4_enable_vlan,
 	.set_arp_offload = dwmac4_set_arp_offload,
 	.config_l3_filter = dwmac4_config_l3_filter,
 	.config_l4_filter = dwmac4_config_l4_filter,
-	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
-	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
-	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
-	.rx_hw_vlan = dwmac4_rx_hw_vlan,
-	.set_hw_vlan_mode = dwmac4_set_hw_vlan_mode,
 };
 
 const struct stmmac_ops dwmac410_ops = {
@@ -1244,18 +998,11 @@ const struct stmmac_ops dwmac410_ops = {
 	.set_filter = dwmac4_set_filter,
 	.flex_pps_config = dwmac5_flex_pps_config,
 	.set_mac_loopback = dwmac4_set_mac_loopback,
-	.update_vlan_hash = dwmac4_update_vlan_hash,
 	.sarc_configure = dwmac4_sarc_configure,
-	.enable_vlan = dwmac4_enable_vlan,
 	.set_arp_offload = dwmac4_set_arp_offload,
 	.config_l3_filter = dwmac4_config_l3_filter,
 	.config_l4_filter = dwmac4_config_l4_filter,
 	.fpe_map_preemption_class = dwmac5_fpe_map_preemption_class,
-	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
-	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
-	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
-	.rx_hw_vlan = dwmac4_rx_hw_vlan,
-	.set_hw_vlan_mode = dwmac4_set_hw_vlan_mode,
 };
 
 const struct stmmac_ops dwmac510_ops = {
@@ -1292,51 +1039,13 @@ const struct stmmac_ops dwmac510_ops = {
 	.rxp_config = dwmac5_rxp_config,
 	.flex_pps_config = dwmac5_flex_pps_config,
 	.set_mac_loopback = dwmac4_set_mac_loopback,
-	.update_vlan_hash = dwmac4_update_vlan_hash,
 	.sarc_configure = dwmac4_sarc_configure,
-	.enable_vlan = dwmac4_enable_vlan,
 	.set_arp_offload = dwmac4_set_arp_offload,
 	.config_l3_filter = dwmac4_config_l3_filter,
 	.config_l4_filter = dwmac4_config_l4_filter,
 	.fpe_map_preemption_class = dwmac5_fpe_map_preemption_class,
-	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
-	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
-	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
-	.rx_hw_vlan = dwmac4_rx_hw_vlan,
-	.set_hw_vlan_mode = dwmac4_set_hw_vlan_mode,
 };
 
-static u32 dwmac4_get_num_vlan(void __iomem *ioaddr)
-{
-	u32 val, num_vlan;
-
-	val = readl(ioaddr + GMAC_HW_FEATURE3);
-	switch (val & GMAC_HW_FEAT_NRVF) {
-	case 0:
-		num_vlan = 1;
-		break;
-	case 1:
-		num_vlan = 4;
-		break;
-	case 2:
-		num_vlan = 8;
-		break;
-	case 3:
-		num_vlan = 16;
-		break;
-	case 4:
-		num_vlan = 24;
-		break;
-	case 5:
-		num_vlan = 32;
-		break;
-	default:
-		num_vlan = 1;
-	}
-
-	return num_vlan;
-}
-
 int dwmac4_setup(struct stmmac_priv *priv)
 {
 	struct mac_device_info *mac = priv->hw;
@@ -1368,7 +1077,7 @@ int dwmac4_setup(struct stmmac_priv *priv)
 	mac->mii.reg_mask = GENMASK(20, 16);
 	mac->mii.clk_csr_shift = 8;
 	mac->mii.clk_csr_mask = GENMASK(11, 8);
-	mac->num_vlan = dwmac4_get_num_vlan(priv->ioaddr);
+	mac->num_vlan = stmmac_get_num_vlan(priv->ioaddr);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index a03f5d771566..0d408ee17f33 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -57,19 +57,6 @@
 #define XGMAC_FILTER_PR			BIT(0)
 #define XGMAC_HASH_TABLE(x)		(0x00000010 + (x) * 4)
 #define XGMAC_MAX_HASH_TABLE		8
-#define XGMAC_VLAN_TAG			0x00000050
-#define XGMAC_VLAN_EDVLP		BIT(26)
-#define XGMAC_VLAN_VTHM			BIT(25)
-#define XGMAC_VLAN_DOVLTC		BIT(20)
-#define XGMAC_VLAN_ESVL			BIT(18)
-#define XGMAC_VLAN_ETV			BIT(16)
-#define XGMAC_VLAN_VID			GENMASK(15, 0)
-#define XGMAC_VLAN_HASH_TABLE		0x00000058
-#define XGMAC_VLAN_INCL			0x00000060
-#define XGMAC_VLAN_VLTI			BIT(20)
-#define XGMAC_VLAN_CSVL			BIT(19)
-#define XGMAC_VLAN_VLC			GENMASK(17, 16)
-#define XGMAC_VLAN_VLC_SHIFT		16
 #define XGMAC_RXQ_CTRL0			0x000000a0
 #define XGMAC_RXQEN(x)			GENMASK((x) * 2 + 1, (x) * 2)
 #define XGMAC_RXQEN_SHIFT(x)		((x) * 2)
@@ -477,6 +464,7 @@
 #define XGMAC_RDES3_RSV			BIT(26)
 #define XGMAC_RDES3_L34T		GENMASK(23, 20)
 #define XGMAC_RDES3_L34T_SHIFT		20
+#define XGMAC_RDES3_ET_LT		GENMASK(19, 16)
 #define XGMAC_L34T_IP4TCP		0x1
 #define XGMAC_L34T_IP4UDP		0x2
 #define XGMAC_L34T_IP6TCP		0x9
@@ -486,6 +474,17 @@
 #define XGMAC_RDES3_TSD			BIT(6)
 #define XGMAC_RDES3_TSA			BIT(4)
 
+/* RDES0 (write back format) */
+#define XGMAC_RDES0_VLAN_TAG_MASK	GENMASK(15, 0)
+
+/* Error Type or L2 Type(ET/LT) Field Number */
+#define XGMAC_ET_LT_VLAN_STAG		8
+#define XGMAC_ET_LT_VLAN_CTAG		9
+#define XGMAC_ET_LT_DVLAN_CTAG_CTAG	10
+#define XGMAC_ET_LT_DVLAN_STAG_STAG	11
+#define XGMAC_ET_LT_DVLAN_CTAG_STAG	12
+#define XGMAC_ET_LT_DVLAN_STAG_CTAG	13
+
 extern const struct stmmac_ops dwxgmac210_ops;
 extern const struct stmmac_ops dwxlgmac2_ops;
 extern const struct stmmac_dma_ops dwxgmac210_dma_ops;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index a6d395c6bacd..6cadf8de4fdf 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -10,6 +10,7 @@
 #include "stmmac.h"
 #include "stmmac_fpe.h"
 #include "stmmac_ptp.h"
+#include "stmmac_vlan.h"
 #include "dwxlgmac2.h"
 #include "dwxgmac2.h"
 
@@ -614,76 +615,6 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw,
 	return 0;
 }
 
-static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash,
-				      u16 perfect_match, bool is_double)
-{
-	void __iomem *ioaddr = hw->pcsr;
-
-	writel(hash, ioaddr + XGMAC_VLAN_HASH_TABLE);
-
-	if (hash) {
-		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
-
-		value |= XGMAC_FILTER_VTFE;
-
-		writel(value, ioaddr + XGMAC_PACKET_FILTER);
-
-		value = readl(ioaddr + XGMAC_VLAN_TAG);
-
-		value |= XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV;
-		if (is_double) {
-			value |= XGMAC_VLAN_EDVLP;
-			value |= XGMAC_VLAN_ESVL;
-			value |= XGMAC_VLAN_DOVLTC;
-		} else {
-			value &= ~XGMAC_VLAN_EDVLP;
-			value &= ~XGMAC_VLAN_ESVL;
-			value &= ~XGMAC_VLAN_DOVLTC;
-		}
-
-		value &= ~XGMAC_VLAN_VID;
-		writel(value, ioaddr + XGMAC_VLAN_TAG);
-	} else if (perfect_match) {
-		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
-
-		value |= XGMAC_FILTER_VTFE;
-
-		writel(value, ioaddr + XGMAC_PACKET_FILTER);
-
-		value = readl(ioaddr + XGMAC_VLAN_TAG);
-
-		value &= ~XGMAC_VLAN_VTHM;
-		value |= XGMAC_VLAN_ETV;
-		if (is_double) {
-			value |= XGMAC_VLAN_EDVLP;
-			value |= XGMAC_VLAN_ESVL;
-			value |= XGMAC_VLAN_DOVLTC;
-		} else {
-			value &= ~XGMAC_VLAN_EDVLP;
-			value &= ~XGMAC_VLAN_ESVL;
-			value &= ~XGMAC_VLAN_DOVLTC;
-		}
-
-		value &= ~XGMAC_VLAN_VID;
-		writel(value | perfect_match, ioaddr + XGMAC_VLAN_TAG);
-	} else {
-		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
-
-		value &= ~XGMAC_FILTER_VTFE;
-
-		writel(value, ioaddr + XGMAC_PACKET_FILTER);
-
-		value = readl(ioaddr + XGMAC_VLAN_TAG);
-
-		value &= ~(XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV);
-		value &= ~(XGMAC_VLAN_EDVLP | XGMAC_VLAN_ESVL);
-		value &= ~XGMAC_VLAN_DOVLTC;
-		value &= ~XGMAC_VLAN_VID;
-
-		writel(value, ioaddr + XGMAC_VLAN_TAG);
-	}
-}
-
 struct dwxgmac3_error_desc {
 	bool valid;
 	const char *desc;
@@ -1300,19 +1231,6 @@ static void dwxgmac2_sarc_configure(void __iomem *ioaddr, int val)
 	writel(value, ioaddr + XGMAC_TX_CONFIG);
 }
 
-static void dwxgmac2_enable_vlan(struct mac_device_info *hw, u32 type)
-{
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-
-	value = readl(ioaddr + XGMAC_VLAN_INCL);
-	value |= XGMAC_VLAN_VLTI;
-	value |= XGMAC_VLAN_CSVL; /* Only use SVLAN */
-	value &= ~XGMAC_VLAN_VLC;
-	value |= (type << XGMAC_VLAN_VLC_SHIFT) & XGMAC_VLAN_VLC;
-	writel(value, ioaddr + XGMAC_VLAN_INCL);
-}
-
 static int dwxgmac2_filter_wait(struct mac_device_info *hw)
 {
 	void __iomem *ioaddr = hw->pcsr;
@@ -1534,12 +1452,10 @@ const struct stmmac_ops dwxgmac210_ops = {
 	.safety_feat_dump = dwxgmac3_safety_feat_dump,
 	.set_mac_loopback = dwxgmac2_set_mac_loopback,
 	.rss_configure = dwxgmac2_rss_configure,
-	.update_vlan_hash = dwxgmac2_update_vlan_hash,
 	.rxp_config = dwxgmac3_rxp_config,
 	.get_mac_tx_timestamp = dwxgmac2_get_mac_tx_timestamp,
 	.flex_pps_config = dwxgmac2_flex_pps_config,
 	.sarc_configure = dwxgmac2_sarc_configure,
-	.enable_vlan = dwxgmac2_enable_vlan,
 	.config_l3_filter = dwxgmac2_config_l3_filter,
 	.config_l4_filter = dwxgmac2_config_l4_filter,
 	.set_arp_offload = dwxgmac2_set_arp_offload,
@@ -1590,12 +1506,10 @@ const struct stmmac_ops dwxlgmac2_ops = {
 	.safety_feat_dump = dwxgmac3_safety_feat_dump,
 	.set_mac_loopback = dwxgmac2_set_mac_loopback,
 	.rss_configure = dwxgmac2_rss_configure,
-	.update_vlan_hash = dwxgmac2_update_vlan_hash,
 	.rxp_config = dwxgmac3_rxp_config,
 	.get_mac_tx_timestamp = dwxgmac2_get_mac_tx_timestamp,
 	.flex_pps_config = dwxgmac2_flex_pps_config,
 	.sarc_configure = dwxgmac2_sarc_configure,
-	.enable_vlan = dwxgmac2_enable_vlan,
 	.config_l3_filter = dwxgmac2_config_l3_filter,
 	.config_l4_filter = dwxgmac2_config_l4_filter,
 	.set_arp_offload = dwxgmac2_set_arp_offload,
@@ -1638,6 +1552,7 @@ int dwxgmac2_setup(struct stmmac_priv *priv)
 	mac->mii.reg_mask = GENMASK(15, 0);
 	mac->mii.clk_csr_shift = 19;
 	mac->mii.clk_csr_mask = GENMASK(21, 19);
+	mac->num_vlan = stmmac_get_num_vlan(priv->ioaddr);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
index 389aad7b5c1e..a2980482fcce 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -4,6 +4,7 @@
  * stmmac XGMAC support.
  */
 
+#include <linux/bitfield.h>
 #include <linux/stmmac.h>
 #include "common.h"
 #include "dwxgmac2.h"
@@ -69,6 +70,21 @@ static int dwxgmac2_get_tx_ls(struct dma_desc *p)
 	return (le32_to_cpu(p->des3) & XGMAC_RDES3_LD) > 0;
 }
 
+static u16 dwxgmac2_wrback_get_rx_vlan_tci(struct dma_desc *p)
+{
+	return le32_to_cpu(p->des0) & XGMAC_RDES0_VLAN_TAG_MASK;
+}
+
+static bool dwxgmac2_wrback_get_rx_vlan_valid(struct dma_desc *p)
+{
+	u32 et_lt;
+
+	et_lt = FIELD_GET(XGMAC_RDES3_ET_LT, le32_to_cpu(p->des3));
+
+	return et_lt >= XGMAC_ET_LT_VLAN_STAG &&
+	       et_lt <= XGMAC_ET_LT_DVLAN_STAG_CTAG;
+}
+
 static int dwxgmac2_get_rx_frame_len(struct dma_desc *p, int rx_coe)
 {
 	return (le32_to_cpu(p->des3) & XGMAC_RDES3_PL);
@@ -351,6 +367,8 @@ const struct stmmac_desc_ops dwxgmac210_desc_ops = {
 	.set_tx_owner = dwxgmac2_set_tx_owner,
 	.set_rx_owner = dwxgmac2_set_rx_owner,
 	.get_tx_ls = dwxgmac2_get_tx_ls,
+	.get_rx_vlan_tci = dwxgmac2_wrback_get_rx_vlan_tci,
+	.get_rx_vlan_valid = dwxgmac2_wrback_get_rx_vlan_valid,
 	.get_rx_frame_len = dwxgmac2_get_rx_frame_len,
 	.enable_tx_timestamp = dwxgmac2_enable_tx_timestamp,
 	.get_tx_timestamp_status = dwxgmac2_get_tx_timestamp_status,
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 31bdbab9a46c..99635b37044a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -9,6 +9,7 @@
 #include "stmmac_fpe.h"
 #include "stmmac_ptp.h"
 #include "stmmac_est.h"
+#include "stmmac_vlan.h"
 #include "dwmac4_descs.h"
 #include "dwxgmac2.h"
 
@@ -120,6 +121,7 @@ static const struct stmmac_hwif_entry {
 	const void *tc;
 	const void *mmc;
 	const void *est;
+	const void *vlan;
 	int (*setup)(struct stmmac_priv *priv);
 	int (*quirks)(struct stmmac_priv *priv);
 } stmmac_hw[] = {
@@ -175,6 +177,7 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac4_dma_ops,
 		.mac = &dwmac4_ops,
+		.vlan = &dwmac_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = NULL,
@@ -197,6 +200,7 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac4_dma_ops,
 		.mac = &dwmac410_ops,
+		.vlan = &dwmac_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = &dwmac4_ring_mode_ops,
@@ -219,6 +223,7 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac410_dma_ops,
 		.mac = &dwmac410_ops,
+		.vlan = &dwmac_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = &dwmac4_ring_mode_ops,
@@ -241,6 +246,7 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac410_dma_ops,
 		.mac = &dwmac510_ops,
+		.vlan = &dwmac_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = &dwmac4_ring_mode_ops,
@@ -264,6 +270,7 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwxgmac210_desc_ops,
 		.dma = &dwxgmac210_dma_ops,
 		.mac = &dwxgmac210_ops,
+		.vlan = &dwxgmac210_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = NULL,
@@ -287,6 +294,7 @@ static const struct stmmac_hwif_entry {
 		.desc = &dwxgmac210_desc_ops,
 		.dma = &dwxgmac210_dma_ops,
 		.mac = &dwxlgmac2_ops,
+		.vlan = &dwxlgmac2_vlan_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.ptp = &stmmac_ptp_clock_ops,
 		.mode = NULL,
@@ -368,6 +376,7 @@ int stmmac_hwif_init(struct stmmac_priv *priv)
 		mac->tc = mac->tc ? : entry->tc;
 		mac->mmc = mac->mmc ? : entry->mmc;
 		mac->est = mac->est ? : entry->est;
+		mac->vlan = mac->vlan ? : entry->vlan;
 
 		priv->hw = mac;
 		priv->fpe_cfg.reg = entry->regs.fpe_reg;
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 27c63a9fc163..ae4efffb785f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -398,21 +398,6 @@ struct stmmac_ops {
 	/* RSS */
 	int (*rss_configure)(struct mac_device_info *hw,
 			     struct stmmac_rss *cfg, u32 num_rxq);
-	/* VLAN */
-	void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash,
-				 u16 perfect_match, bool is_double);
-	void (*enable_vlan)(struct mac_device_info *hw, u32 type);
-	void (*rx_hw_vlan)(struct mac_device_info *hw, struct dma_desc *rx_desc,
-			   struct sk_buff *skb);
-	void (*set_hw_vlan_mode)(struct mac_device_info *hw);
-	int (*add_hw_vlan_rx_fltr)(struct net_device *dev,
-				   struct mac_device_info *hw,
-				   __be16 proto, u16 vid);
-	int (*del_hw_vlan_rx_fltr)(struct net_device *dev,
-				   struct mac_device_info *hw,
-				   __be16 proto, u16 vid);
-	void (*restore_hw_vlan_rx_fltr)(struct net_device *dev,
-					struct mac_device_info *hw);
 	/* TX Timestamp */
 	int (*get_mac_tx_timestamp)(struct mac_device_info *hw, u64 *ts);
 	/* Source Address Insertion / Replacement */
@@ -498,20 +483,6 @@ struct stmmac_ops {
 	stmmac_do_void_callback(__priv, mac, set_mac_loopback, __args)
 #define stmmac_rss_configure(__priv, __args...) \
 	stmmac_do_callback(__priv, mac, rss_configure, __args)
-#define stmmac_update_vlan_hash(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, update_vlan_hash, __args)
-#define stmmac_enable_vlan(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, enable_vlan, __args)
-#define stmmac_rx_hw_vlan(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, rx_hw_vlan, __args)
-#define stmmac_set_hw_vlan_mode(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, set_hw_vlan_mode, __args)
-#define stmmac_add_hw_vlan_rx_fltr(__priv, __args...) \
-	stmmac_do_callback(__priv, mac, add_hw_vlan_rx_fltr, __args)
-#define stmmac_del_hw_vlan_rx_fltr(__priv, __args...) \
-	stmmac_do_callback(__priv, mac, del_hw_vlan_rx_fltr, __args)
-#define stmmac_restore_hw_vlan_rx_fltr(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, restore_hw_vlan_rx_fltr, __args)
 #define stmmac_get_mac_tx_timestamp(__priv, __args...) \
 	stmmac_do_callback(__priv, mac, get_mac_tx_timestamp, __args)
 #define stmmac_sarc_configure(__priv, __args...) \
@@ -659,6 +630,39 @@ struct stmmac_est_ops {
 #define stmmac_est_irq_status(__priv, __args...) \
 	stmmac_do_void_callback(__priv, est, irq_status, __args)
 
+struct stmmac_vlan_ops {
+	/* VLAN */
+	void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash,
+				 u16 perfect_match, bool is_double);
+	void (*enable_vlan)(struct mac_device_info *hw, u32 type);
+	void (*rx_hw_vlan)(struct mac_device_info *hw, struct dma_desc *rx_desc,
+			   struct sk_buff *skb);
+	void (*set_hw_vlan_mode)(struct mac_device_info *hw);
+	int (*add_hw_vlan_rx_fltr)(struct net_device *dev,
+				   struct mac_device_info *hw,
+				   __be16 proto, u16 vid);
+	int (*del_hw_vlan_rx_fltr)(struct net_device *dev,
+				   struct mac_device_info *hw,
+				   __be16 proto, u16 vid);
+	void (*restore_hw_vlan_rx_fltr)(struct net_device *dev,
+					struct mac_device_info *hw);
+};
+
+#define stmmac_update_vlan_hash(__priv, __args...) \
+	stmmac_do_void_callback(__priv, vlan, update_vlan_hash, __args)
+#define stmmac_enable_vlan(__priv, __args...) \
+	stmmac_do_void_callback(__priv, vlan, enable_vlan, __args)
+#define stmmac_rx_hw_vlan(__priv, __args...) \
+	stmmac_do_void_callback(__priv, vlan, rx_hw_vlan, __args)
+#define stmmac_set_hw_vlan_mode(__priv, __args...) \
+	stmmac_do_void_callback(__priv, vlan, set_hw_vlan_mode, __args)
+#define stmmac_add_hw_vlan_rx_fltr(__priv, __args...) \
+	stmmac_do_callback(__priv, vlan, add_hw_vlan_rx_fltr, __args)
+#define stmmac_del_hw_vlan_rx_fltr(__priv, __args...) \
+	stmmac_do_callback(__priv, vlan, del_hw_vlan_rx_fltr, __args)
+#define stmmac_restore_hw_vlan_rx_fltr(__priv, __args...) \
+	stmmac_do_void_callback(__priv, vlan, restore_hw_vlan_rx_fltr, __args)
+
 struct stmmac_regs_off {
 	const struct stmmac_fpe_reg *fpe_reg;
 	u32 ptp_off;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index bddfa0f4aa21..cda09cf5dcca 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -149,21 +149,9 @@ struct stmmac_channel {
 };
 
 struct stmmac_fpe_cfg {
-	/* Serialize access to MAC Merge state between ethtool requests
-	 * and link state updates.
-	 */
-	spinlock_t lock;
-
+	struct ethtool_mmsv mmsv;
 	const struct stmmac_fpe_reg *reg;
-	u32 fpe_csr;				/* MAC_FPE_CTRL_STS reg cache */
-
-	enum ethtool_mm_verify_status status;
-	struct timer_list verify_timer;
-	bool verify_enabled;
-	int verify_retries;
-	bool pmac_enabled;
-	u32 verify_time;
-	bool tx_enabled;
+	u32 fpe_csr;	/* MAC_FPE_CTRL_STS reg cache */
 };
 
 struct stmmac_tc_entry {
@@ -313,7 +301,7 @@ struct stmmac_priv {
 	unsigned int mode;
 	unsigned int chain_mode;
 	int extend_desc;
-	struct hwtstamp_config tstamp_config;
+	struct kernel_hwtstamp_config tstamp_config;
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_clock_ops;
 	unsigned int default_addend;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 918a32f8fda8..f702f7b7bf9f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -37,7 +37,7 @@
 #define ETHTOOL_DMA_OFFSET	55
 
 struct stmmac_stats {
-	char stat_string[ETH_GSTRING_LEN];
+	char stat_string[ETH_GSTRING_LEN] __nonstring;
 	int sizeof_stat;
 	int stat_offset;
 };
@@ -1210,36 +1210,16 @@ static int stmmac_get_mm(struct net_device *ndev,
 			 struct ethtool_mm_state *state)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
-	unsigned long flags;
 	u32 frag_size;
 
 	if (!stmmac_fpe_supported(priv))
 		return -EOPNOTSUPP;
 
-	spin_lock_irqsave(&priv->fpe_cfg.lock, flags);
-
-	state->max_verify_time = STMMAC_FPE_MM_MAX_VERIFY_TIME_MS;
-	state->verify_enabled = priv->fpe_cfg.verify_enabled;
-	state->pmac_enabled = priv->fpe_cfg.pmac_enabled;
-	state->verify_time = priv->fpe_cfg.verify_time;
-	state->tx_enabled = priv->fpe_cfg.tx_enabled;
-	state->verify_status = priv->fpe_cfg.status;
 	state->rx_min_frag_size = ETH_ZLEN;
-
-	/* FPE active if common tx_enabled and
-	 * (verification success or disabled(forced))
-	 */
-	if (state->tx_enabled &&
-	    (state->verify_status == ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED ||
-	     state->verify_status == ETHTOOL_MM_VERIFY_STATUS_DISABLED))
-		state->tx_active = true;
-	else
-		state->tx_active = false;
-
 	frag_size = stmmac_fpe_get_add_frag_size(priv);
 	state->tx_min_frag_size = ethtool_mm_frag_size_add_to_min(frag_size);
 
-	spin_unlock_irqrestore(&priv->fpe_cfg.lock, flags);
+	ethtool_mmsv_get_mm(&priv->fpe_cfg.mmsv, state);
 
 	return 0;
 }
@@ -1248,8 +1228,6 @@ static int stmmac_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg,
 			 struct netlink_ext_ack *extack)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
-	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
-	unsigned long flags;
 	u32 frag_size;
 	int err;
 
@@ -1258,23 +1236,8 @@ static int stmmac_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg,
 	if (err)
 		return err;
 
-	/* Wait for the verification that's currently in progress to finish */
-	timer_shutdown_sync(&fpe_cfg->verify_timer);
-
-	spin_lock_irqsave(&fpe_cfg->lock, flags);
-
-	fpe_cfg->verify_enabled = cfg->verify_enabled;
-	fpe_cfg->pmac_enabled = cfg->pmac_enabled;
-	fpe_cfg->verify_time = cfg->verify_time;
-	fpe_cfg->tx_enabled = cfg->tx_enabled;
-
-	if (!cfg->verify_enabled)
-		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_DISABLED;
-
 	stmmac_fpe_set_add_frag_size(priv, frag_size);
-	stmmac_fpe_apply(priv);
-
-	spin_unlock_irqrestore(&fpe_cfg->lock, flags);
+	ethtool_mmsv_set_mm(&priv->fpe_cfg.mmsv, cfg);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c
index 3a4bee029c7f..75b470ee621a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c
@@ -27,12 +27,6 @@
 #define STMMAC_MAC_FPE_CTRL_STS_SVER	BIT(1)
 #define STMMAC_MAC_FPE_CTRL_STS_EFPE	BIT(0)
 
-/* FPE link-partner hand-shaking mPacket type */
-enum stmmac_mpacket_type {
-	MPACKET_VERIFY = 0,
-	MPACKET_RESPONSE = 1,
-};
-
 struct stmmac_fpe_reg {
 	const u32 mac_fpe_reg;		/* offset of MAC_FPE_CTRL_STS */
 	const u32 mtl_fpe_reg;		/* offset of MTL_FPE_CTRL_STS */
@@ -48,10 +42,10 @@ bool stmmac_fpe_supported(struct stmmac_priv *priv)
 		priv->hw->mac->fpe_map_preemption_class;
 }
 
-static void stmmac_fpe_configure(struct stmmac_priv *priv, bool tx_enable,
-				 bool pmac_enable)
+static void stmmac_fpe_configure_tx(struct ethtool_mmsv *mmsv, bool tx_enable)
 {
-	struct stmmac_fpe_cfg *cfg = &priv->fpe_cfg;
+	struct stmmac_fpe_cfg *cfg = container_of(mmsv, struct stmmac_fpe_cfg, mmsv);
+	struct stmmac_priv *priv = container_of(cfg, struct stmmac_priv, fpe_cfg);
 	const struct stmmac_fpe_reg *reg = cfg->reg;
 	u32 num_rxq = priv->plat->rx_queues_to_use;
 	void __iomem *ioaddr = priv->ioaddr;
@@ -68,6 +62,15 @@ static void stmmac_fpe_configure(struct stmmac_priv *priv, bool tx_enable,
 		cfg->fpe_csr = 0;
 	}
 	writel(cfg->fpe_csr, ioaddr + reg->mac_fpe_reg);
+}
+
+static void stmmac_fpe_configure_pmac(struct ethtool_mmsv *mmsv, bool pmac_enable)
+{
+	struct stmmac_fpe_cfg *cfg = container_of(mmsv, struct stmmac_fpe_cfg, mmsv);
+	struct stmmac_priv *priv = container_of(cfg, struct stmmac_priv, fpe_cfg);
+	const struct stmmac_fpe_reg *reg = cfg->reg;
+	void __iomem *ioaddr = priv->ioaddr;
+	u32 value;
 
 	value = readl(ioaddr + reg->int_en_reg);
 
@@ -85,47 +88,45 @@ static void stmmac_fpe_configure(struct stmmac_priv *priv, bool tx_enable,
 	writel(value, ioaddr + reg->int_en_reg);
 }
 
-static void stmmac_fpe_send_mpacket(struct stmmac_priv *priv,
-				    enum stmmac_mpacket_type type)
+static void stmmac_fpe_send_mpacket(struct ethtool_mmsv *mmsv,
+				    enum ethtool_mpacket type)
 {
-	const struct stmmac_fpe_reg *reg = priv->fpe_cfg.reg;
+	struct stmmac_fpe_cfg *cfg = container_of(mmsv, struct stmmac_fpe_cfg, mmsv);
+	struct stmmac_priv *priv = container_of(cfg, struct stmmac_priv, fpe_cfg);
+	const struct stmmac_fpe_reg *reg = cfg->reg;
 	void __iomem *ioaddr = priv->ioaddr;
-	u32 value = priv->fpe_cfg.fpe_csr;
+	u32 value = cfg->fpe_csr;
 
-	if (type == MPACKET_VERIFY)
+	if (type == ETHTOOL_MPACKET_VERIFY)
 		value |= STMMAC_MAC_FPE_CTRL_STS_SVER;
-	else if (type == MPACKET_RESPONSE)
+	else if (type == ETHTOOL_MPACKET_RESPONSE)
 		value |= STMMAC_MAC_FPE_CTRL_STS_SRSP;
 
 	writel(value, ioaddr + reg->mac_fpe_reg);
 }
 
+static const struct ethtool_mmsv_ops stmmac_mmsv_ops = {
+	.configure_tx = stmmac_fpe_configure_tx,
+	.configure_pmac = stmmac_fpe_configure_pmac,
+	.send_mpacket = stmmac_fpe_send_mpacket,
+};
+
 static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status)
 {
 	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
+	struct ethtool_mmsv *mmsv = &fpe_cfg->mmsv;
 
-	/* This is interrupt context, just spin_lock() */
-	spin_lock(&fpe_cfg->lock);
-
-	if (!fpe_cfg->pmac_enabled || status == FPE_EVENT_UNKNOWN)
-		goto unlock_out;
+	if (status == FPE_EVENT_UNKNOWN)
+		return;
 
-	/* LP has sent verify mPacket */
 	if ((status & FPE_EVENT_RVER) == FPE_EVENT_RVER)
-		stmmac_fpe_send_mpacket(priv, MPACKET_RESPONSE);
+		ethtool_mmsv_event_handle(mmsv, ETHTOOL_MMSV_LP_SENT_VERIFY_MPACKET);
 
-	/* Local has sent verify mPacket */
-	if ((status & FPE_EVENT_TVER) == FPE_EVENT_TVER &&
-	    fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED)
-		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_VERIFYING;
+	if ((status & FPE_EVENT_TVER) == FPE_EVENT_TVER)
+		ethtool_mmsv_event_handle(mmsv, ETHTOOL_MMSV_LD_SENT_VERIFY_MPACKET);
 
-	/* LP has sent response mPacket */
-	if ((status & FPE_EVENT_RRSP) == FPE_EVENT_RRSP &&
-	    fpe_cfg->status == ETHTOOL_MM_VERIFY_STATUS_VERIFYING)
-		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED;
-
-unlock_out:
-	spin_unlock(&fpe_cfg->lock);
+	if ((status & FPE_EVENT_RRSP) == FPE_EVENT_RRSP)
+		ethtool_mmsv_event_handle(mmsv, ETHTOOL_MMSV_LP_SENT_RESPONSE_MPACKET);
 }
 
 void stmmac_fpe_irq_status(struct stmmac_priv *priv)
@@ -164,119 +165,16 @@ void stmmac_fpe_irq_status(struct stmmac_priv *priv)
 	stmmac_fpe_event_status(priv, status);
 }
 
-/**
- * stmmac_fpe_verify_timer - Timer for MAC Merge verification
- * @t:  timer_list struct containing private info
- *
- * Verify the MAC Merge capability in the local TX direction, by
- * transmitting Verify mPackets up to 3 times. Wait until link
- * partner responds with a Response mPacket, otherwise fail.
- */
-static void stmmac_fpe_verify_timer(struct timer_list *t)
-{
-	struct stmmac_fpe_cfg *fpe_cfg = from_timer(fpe_cfg, t, verify_timer);
-	struct stmmac_priv *priv = container_of(fpe_cfg, struct stmmac_priv,
-						fpe_cfg);
-	unsigned long flags;
-	bool rearm = false;
-
-	spin_lock_irqsave(&fpe_cfg->lock, flags);
-
-	switch (fpe_cfg->status) {
-	case ETHTOOL_MM_VERIFY_STATUS_INITIAL:
-	case ETHTOOL_MM_VERIFY_STATUS_VERIFYING:
-		if (fpe_cfg->verify_retries != 0) {
-			stmmac_fpe_send_mpacket(priv, MPACKET_VERIFY);
-			rearm = true;
-		} else {
-			fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_FAILED;
-		}
-
-		fpe_cfg->verify_retries--;
-		break;
-
-	case ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED:
-		stmmac_fpe_configure(priv, true, true);
-		break;
-
-	default:
-		break;
-	}
-
-	if (rearm) {
-		mod_timer(&fpe_cfg->verify_timer,
-			  jiffies + msecs_to_jiffies(fpe_cfg->verify_time));
-	}
-
-	spin_unlock_irqrestore(&fpe_cfg->lock, flags);
-}
-
-static void stmmac_fpe_verify_timer_arm(struct stmmac_fpe_cfg *fpe_cfg)
-{
-	if (fpe_cfg->pmac_enabled && fpe_cfg->tx_enabled &&
-	    fpe_cfg->verify_enabled &&
-	    fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_FAILED &&
-	    fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED) {
-		timer_setup(&fpe_cfg->verify_timer, stmmac_fpe_verify_timer, 0);
-		mod_timer(&fpe_cfg->verify_timer, jiffies);
-	}
-}
-
 void stmmac_fpe_init(struct stmmac_priv *priv)
 {
-	priv->fpe_cfg.verify_retries = STMMAC_FPE_MM_MAX_VERIFY_RETRIES;
-	priv->fpe_cfg.verify_time = STMMAC_FPE_MM_MAX_VERIFY_TIME_MS;
-	priv->fpe_cfg.status = ETHTOOL_MM_VERIFY_STATUS_DISABLED;
-	timer_setup(&priv->fpe_cfg.verify_timer, stmmac_fpe_verify_timer, 0);
-	spin_lock_init(&priv->fpe_cfg.lock);
+	ethtool_mmsv_init(&priv->fpe_cfg.mmsv, priv->dev,
+			  &stmmac_mmsv_ops);
 
 	if ((!priv->fpe_cfg.reg || !priv->hw->mac->fpe_map_preemption_class) &&
 	    priv->dma_cap.fpesel)
 		dev_info(priv->device, "FPE is not supported by driver.\n");
 }
 
-void stmmac_fpe_apply(struct stmmac_priv *priv)
-{
-	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
-
-	/* If verification is disabled, configure FPE right away.
-	 * Otherwise let the timer code do it.
-	 */
-	if (!fpe_cfg->verify_enabled) {
-		stmmac_fpe_configure(priv, fpe_cfg->tx_enabled,
-				     fpe_cfg->pmac_enabled);
-	} else {
-		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_INITIAL;
-		fpe_cfg->verify_retries = STMMAC_FPE_MM_MAX_VERIFY_RETRIES;
-
-		if (netif_running(priv->dev))
-			stmmac_fpe_verify_timer_arm(fpe_cfg);
-	}
-}
-
-void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up)
-{
-	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
-	unsigned long flags;
-
-	timer_shutdown_sync(&fpe_cfg->verify_timer);
-
-	spin_lock_irqsave(&fpe_cfg->lock, flags);
-
-	if (is_up && fpe_cfg->pmac_enabled) {
-		/* VERIFY process requires pmac enabled when NIC comes up */
-		stmmac_fpe_configure(priv, false, true);
-
-		/* New link => maybe new partner => new verification process */
-		stmmac_fpe_apply(priv);
-	} else {
-		/* No link => turn off EFPE */
-		stmmac_fpe_configure(priv, false, false);
-	}
-
-	spin_unlock_irqrestore(&fpe_cfg->lock, flags);
-}
-
 int stmmac_fpe_get_add_frag_size(struct stmmac_priv *priv)
 {
 	const struct stmmac_fpe_reg *reg = priv->fpe_cfg.reg;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.h
index b884eac7142d..3fc46acf7001 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.h
@@ -9,15 +9,10 @@
 #include <linux/types.h>
 #include <linux/netdevice.h>
 
-#define STMMAC_FPE_MM_MAX_VERIFY_RETRIES	3
-#define STMMAC_FPE_MM_MAX_VERIFY_TIME_MS	128
-
 struct stmmac_priv;
 
-void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up);
 bool stmmac_fpe_supported(struct stmmac_priv *priv);
 void stmmac_fpe_init(struct stmmac_priv *priv);
-void stmmac_fpe_apply(struct stmmac_priv *priv);
 void stmmac_fpe_irq_status(struct stmmac_priv *priv);
 int stmmac_fpe_get_add_frag_size(struct stmmac_priv *priv);
 void stmmac_fpe_set_add_frag_size(struct stmmac_priv *priv, u32 add_frag_size);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 0f59aa982604..e2840fa241f2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -222,7 +222,7 @@ static void get_ptptime(void __iomem *ptpaddr, u64 *ptp_time)
 	u64 ns;
 
 	ns = readl(ptpaddr + PTP_ATNR);
-	ns += readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;
+	ns += (u64)readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;
 
 	*ptp_time = ns;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 59d07d0d3369..085c09039af4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -568,18 +568,19 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
 /**
  *  stmmac_hwtstamp_set - control hardware timestamping.
  *  @dev: device pointer.
- *  @ifr: An IOCTL specific structure, that can contain a pointer to
- *  a proprietary structure used to pass information to the driver.
+ *  @config: the timestamping configuration.
+ *  @extack: netlink extended ack structure for error reporting.
  *  Description:
  *  This function configures the MAC to enable/disable both outgoing(TX)
  *  and incoming(RX) packets time stamping based on user input.
  *  Return Value:
  *  0 on success and an appropriate -ve integer on failure.
  */
-static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
+static int stmmac_hwtstamp_set(struct net_device *dev,
+			       struct kernel_hwtstamp_config *config,
+			       struct netlink_ext_ack *extack)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config config;
 	u32 ptp_v2 = 0;
 	u32 tstamp_all = 0;
 	u32 ptp_over_ipv4_udp = 0;
@@ -590,34 +591,36 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	u32 ts_event_en = 0;
 
 	if (!(priv->dma_cap.time_stamp || priv->adv_ts)) {
-		netdev_alert(priv->dev, "No support for HW time stamping\n");
+		NL_SET_ERR_MSG_MOD(extack, "No support for HW time stamping");
 		priv->hwts_tx_en = 0;
 		priv->hwts_rx_en = 0;
 
 		return -EOPNOTSUPP;
 	}
 
-	if (copy_from_user(&config, ifr->ifr_data,
-			   sizeof(config)))
-		return -EFAULT;
+	if (!netif_running(dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot change timestamping configuration while down");
+		return -ENODEV;
+	}
 
 	netdev_dbg(priv->dev, "%s config flags:0x%x, tx_type:0x%x, rx_filter:0x%x\n",
-		   __func__, config.flags, config.tx_type, config.rx_filter);
+		   __func__, config->flags, config->tx_type, config->rx_filter);
 
-	if (config.tx_type != HWTSTAMP_TX_OFF &&
-	    config.tx_type != HWTSTAMP_TX_ON)
+	if (config->tx_type != HWTSTAMP_TX_OFF &&
+	    config->tx_type != HWTSTAMP_TX_ON)
 		return -ERANGE;
 
 	if (priv->adv_ts) {
-		switch (config.rx_filter) {
+		switch (config->rx_filter) {
 		case HWTSTAMP_FILTER_NONE:
 			/* time stamp no incoming packet at all */
-			config.rx_filter = HWTSTAMP_FILTER_NONE;
+			config->rx_filter = HWTSTAMP_FILTER_NONE;
 			break;
 
 		case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 			/* PTP v1, UDP, any kind of event packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 			/* 'xmac' hardware can support Sync, Pdelay_Req and
 			 * Pdelay_resp by setting bit14 and bits17/16 to 01
 			 * This leaves Delay_Req timestamps out.
@@ -631,7 +634,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 			/* PTP v1, UDP, Sync packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_SYNC;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_SYNC;
 			/* take time stamp for SYNC messages only */
 			ts_event_en = PTP_TCR_TSEVNTENA;
 
@@ -641,7 +644,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
 			/* PTP v1, UDP, Delay_req packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ;
 			/* take time stamp for Delay_Req messages only */
 			ts_master_en = PTP_TCR_TSMSTRENA;
 			ts_event_en = PTP_TCR_TSEVNTENA;
@@ -652,7 +655,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 			/* PTP v2, UDP, any kind of event packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for all event messages */
 			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
@@ -663,7 +666,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 			/* PTP v2, UDP, Sync packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_SYNC;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_SYNC;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for SYNC messages only */
 			ts_event_en = PTP_TCR_TSEVNTENA;
@@ -674,7 +677,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
 			/* PTP v2, UDP, Delay_req packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for Delay_Req messages only */
 			ts_master_en = PTP_TCR_TSMSTRENA;
@@ -686,7 +689,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_EVENT:
 			/* PTP v2/802.AS1 any layer, any kind of event packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
 			if (priv->synopsys_id < DWMAC_CORE_4_10)
@@ -698,7 +701,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_SYNC:
 			/* PTP v2/802.AS1, any layer, Sync packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_SYNC;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_SYNC;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for SYNC messages only */
 			ts_event_en = PTP_TCR_TSEVNTENA;
@@ -710,7 +713,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 		case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 			/* PTP v2/802.AS1, any layer, Delay_req packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_DELAY_REQ;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_DELAY_REQ;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for Delay_Req messages only */
 			ts_master_en = PTP_TCR_TSMSTRENA;
@@ -724,7 +727,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 		case HWTSTAMP_FILTER_NTP_ALL:
 		case HWTSTAMP_FILTER_ALL:
 			/* time stamp any incoming packet */
-			config.rx_filter = HWTSTAMP_FILTER_ALL;
+			config->rx_filter = HWTSTAMP_FILTER_ALL;
 			tstamp_all = PTP_TCR_TSENALL;
 			break;
 
@@ -732,18 +735,18 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 			return -ERANGE;
 		}
 	} else {
-		switch (config.rx_filter) {
+		switch (config->rx_filter) {
 		case HWTSTAMP_FILTER_NONE:
-			config.rx_filter = HWTSTAMP_FILTER_NONE;
+			config->rx_filter = HWTSTAMP_FILTER_NONE;
 			break;
 		default:
 			/* PTP v1, UDP, any kind of event packet */
-			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+			config->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 			break;
 		}
 	}
-	priv->hwts_rx_en = ((config.rx_filter == HWTSTAMP_FILTER_NONE) ? 0 : 1);
-	priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON;
+	priv->hwts_rx_en = config->rx_filter != HWTSTAMP_FILTER_NONE;
+	priv->hwts_tx_en = config->tx_type == HWTSTAMP_TX_ON;
 
 	priv->systime_flags = STMMAC_HWTS_ACTIVE;
 
@@ -756,31 +759,30 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 	stmmac_config_hw_tstamping(priv, priv->ptpaddr, priv->systime_flags);
 
-	memcpy(&priv->tstamp_config, &config, sizeof(config));
+	priv->tstamp_config = *config;
 
-	return copy_to_user(ifr->ifr_data, &config,
-			    sizeof(config)) ? -EFAULT : 0;
+	return 0;
 }
 
 /**
  *  stmmac_hwtstamp_get - read hardware timestamping.
  *  @dev: device pointer.
- *  @ifr: An IOCTL specific structure, that can contain a pointer to
- *  a proprietary structure used to pass information to the driver.
+ *  @config: the timestamping configuration.
  *  Description:
  *  This function obtain the current hardware timestamping settings
  *  as requested.
  */
-static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+static int stmmac_hwtstamp_get(struct net_device *dev,
+			       struct kernel_hwtstamp_config *config)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config *config = &priv->tstamp_config;
 
 	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
 		return -EOPNOTSUPP;
 
-	return copy_to_user(ifr->ifr_data, config,
-			    sizeof(*config)) ? -EFAULT : 0;
+	*config = priv->tstamp_config;
+
+	return 0;
 }
 
 /**
@@ -946,7 +948,7 @@ static void stmmac_mac_link_down(struct phylink_config *config,
 		stmmac_set_eee_pls(priv, priv->hw, false);
 
 	if (stmmac_fpe_supported(priv))
-		stmmac_fpe_link_state_handle(priv, false);
+		ethtool_mmsv_link_state_handle(&priv->fpe_cfg.mmsv, false);
 }
 
 static void stmmac_mac_link_up(struct phylink_config *config,
@@ -1064,7 +1066,7 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 		stmmac_set_eee_pls(priv, priv->hw, true);
 
 	if (stmmac_fpe_supported(priv))
-		stmmac_fpe_link_state_handle(priv, true);
+		ethtool_mmsv_link_state_handle(&priv->fpe_cfg.mmsv, true);
 
 	if (priv->plat->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY)
 		stmmac_hwtstamp_correct_latency(priv, priv);
@@ -1258,20 +1260,22 @@ static int stmmac_init_phy(struct net_device *dev)
 static int stmmac_phy_setup(struct stmmac_priv *priv)
 {
 	struct stmmac_mdio_bus_data *mdio_bus_data;
-	int mode = priv->plat->phy_interface;
+	struct phylink_config *config;
 	struct fwnode_handle *fwnode;
 	struct phylink_pcs *pcs;
 	struct phylink *phylink;
 
-	priv->phylink_config.dev = &priv->dev->dev;
-	priv->phylink_config.type = PHYLINK_NETDEV;
-	priv->phylink_config.mac_managed_pm = true;
+	config = &priv->phylink_config;
+
+	config->dev = &priv->dev->dev;
+	config->type = PHYLINK_NETDEV;
+	config->mac_managed_pm = true;
 
 	/* Stmmac always requires an RX clock for hardware initialization */
-	priv->phylink_config.mac_requires_rxc = true;
+	config->mac_requires_rxc = true;
 
 	if (!(priv->plat->flags & STMMAC_FLAG_RX_CLK_RUNS_IN_LPI))
-		priv->phylink_config.eee_rx_clk_stop_enable = true;
+		config->eee_rx_clk_stop_enable = true;
 
 	/* Set the default transmit clock stop bit based on the platform glue */
 	priv->tx_lpi_clk_stop = priv->plat->flags &
@@ -1279,13 +1283,22 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 
 	mdio_bus_data = priv->plat->mdio_bus_data;
 	if (mdio_bus_data)
-		priv->phylink_config.default_an_inband =
-			mdio_bus_data->default_an_inband;
+		config->default_an_inband = mdio_bus_data->default_an_inband;
 
-	/* Set the platform/firmware specified interface mode. Note, phylink
-	 * deals with the PHY interface mode, not the MAC interface mode.
+	/* Get the PHY interface modes (at the PHY end of the link) that
+	 * are supported by the platform.
 	 */
-	__set_bit(mode, priv->phylink_config.supported_interfaces);
+	if (priv->plat->get_interfaces)
+		priv->plat->get_interfaces(priv, priv->plat->bsp_priv,
+					   config->supported_interfaces);
+
+	/* Set the platform/firmware specified interface mode if the
+	 * supported interfaces have not already been provided using
+	 * phy_interface as a last resort.
+	 */
+	if (phy_interface_empty(config->supported_interfaces))
+		__set_bit(priv->plat->phy_interface,
+			  config->supported_interfaces);
 
 	/* If we have an xpcs, it defines which PHY interfaces are supported. */
 	if (priv->hw->xpcs)
@@ -1294,29 +1307,27 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 		pcs = priv->hw->phylink_pcs;
 
 	if (pcs)
-		phy_interface_or(priv->phylink_config.supported_interfaces,
-				 priv->phylink_config.supported_interfaces,
+		phy_interface_or(config->supported_interfaces,
+				 config->supported_interfaces,
 				 pcs->supported_interfaces);
 
 	if (priv->dma_cap.eee) {
 		/* Assume all supported interfaces also support LPI */
-		memcpy(priv->phylink_config.lpi_interfaces,
-		       priv->phylink_config.supported_interfaces,
-		       sizeof(priv->phylink_config.lpi_interfaces));
+		memcpy(config->lpi_interfaces, config->supported_interfaces,
+		       sizeof(config->lpi_interfaces));
 
 		/* All full duplex speeds above 100Mbps are supported */
-		priv->phylink_config.lpi_capabilities = ~(MAC_1000FD - 1) |
-							MAC_100FD;
-		priv->phylink_config.lpi_timer_default = eee_timer * 1000;
-		priv->phylink_config.eee_enabled_default = true;
+		config->lpi_capabilities = ~(MAC_1000FD - 1) | MAC_100FD;
+		config->lpi_timer_default = eee_timer * 1000;
+		config->eee_enabled_default = true;
 	}
 
 	fwnode = priv->plat->port_node;
 	if (!fwnode)
 		fwnode = dev_fwnode(priv->device);
 
-	phylink = phylink_create(&priv->phylink_config, fwnode,
-				 mode, &stmmac_phylink_mac_ops);
+	phylink = phylink_create(config, fwnode, priv->plat->phy_interface,
+				 &stmmac_phylink_mac_ops);
 	if (IS_ERR(phylink))
 		return PTR_ERR(phylink);
 
@@ -4152,7 +4163,7 @@ static int stmmac_release(struct net_device *dev)
 	stmmac_release_ptp(priv);
 
 	if (stmmac_fpe_supported(priv))
-		timer_shutdown_sync(&priv->fpe_cfg.verify_timer);
+		ethtool_mmsv_stop(&priv->fpe_cfg.mmsv);
 
 	pm_runtime_put(priv->device);
 
@@ -4488,8 +4499,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
 
-	skb_tx_timestamp(skb);
-
 	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
 		     priv->hwts_tx_en)) {
 		/* declare that device is doing timestamping */
@@ -4522,6 +4531,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
+	skb_tx_timestamp(skb);
 
 	stmmac_flush_tx_descriptors(priv, queue);
 	stmmac_tx_timer_arm(priv, queue);
@@ -4765,8 +4775,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
 
-	skb_tx_timestamp(skb);
-
 	/* Ready to fill the first descriptor and set the OWN bit w/o any
 	 * problems because all the descriptors are actually ready to be
 	 * passed to the DMA engine.
@@ -4813,7 +4821,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr, queue);
-
+	skb_tx_timestamp(skb);
 	stmmac_flush_tx_descriptors(priv, queue);
 	stmmac_tx_timer_arm(priv, queue);
 
@@ -6219,12 +6227,6 @@ static int stmmac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	case SIOCSMIIREG:
 		ret = phylink_mii_ioctl(priv->phylink, rq, cmd);
 		break;
-	case SIOCSHWTSTAMP:
-		ret = stmmac_hwtstamp_set(dev, rq);
-		break;
-	case SIOCGHWTSTAMP:
-		ret = stmmac_hwtstamp_get(dev, rq);
-		break;
 	default:
 		break;
 	}
@@ -7163,6 +7165,8 @@ static const struct net_device_ops stmmac_netdev_ops = {
 	.ndo_bpf = stmmac_bpf,
 	.ndo_xdp_xmit = stmmac_xdp_xmit,
 	.ndo_xsk_wakeup = stmmac_xsk_wakeup,
+	.ndo_hwtstamp_get = stmmac_hwtstamp_get,
+	.ndo_hwtstamp_set = stmmac_hwtstamp_set,
 };
 
 static void stmmac_reset_subtask(struct stmmac_priv *priv)
@@ -7644,7 +7648,7 @@ int stmmac_dvr_probe(struct device *device,
 #ifdef STMMAC_VLAN_TAG_USED
 	/* Both mac100 and gmac support receive VLAN tag detection */
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX;
-	if (priv->plat->has_gmac4) {
+	if (priv->plat->has_gmac4 || priv->plat->has_xgmac) {
 		ndev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
 		priv->hw->hw_vlan_en = true;
 	}
@@ -7727,9 +7731,6 @@ int stmmac_dvr_probe(struct device *device,
 		goto error_mdio_register;
 	}
 
-	if (priv->plat->speed_mode_2500)
-		priv->plat->speed_mode_2500(ndev, priv->plat->bsp_priv);
-
 	ret = stmmac_pcs_setup(ndev);
 	if (ret)
 		goto error_pcs_setup;
@@ -7871,7 +7872,7 @@ int stmmac_suspend(struct device *dev)
 	rtnl_unlock();
 
 	if (stmmac_fpe_supported(priv))
-		timer_shutdown_sync(&priv->fpe_cfg.verify_timer);
+		ethtool_mmsv_stop(&priv->fpe_cfg.mmsv);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
new file mode 100644
index 000000000000..0b6f6228ae35
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
@@ -0,0 +1,374 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025, Altera Corporation
+ * stmmac VLAN (802.1Q) handling
+ */
+
+#include "stmmac.h"
+#include "stmmac_vlan.h"
+
+static void vlan_write_single(struct net_device *dev, u16 vid)
+{
+	void __iomem *ioaddr = (void __iomem *)dev->base_addr;
+	u32 val;
+
+	val = readl(ioaddr + VLAN_TAG);
+	val &= ~VLAN_TAG_VID;
+	val |= VLAN_TAG_ETV | vid;
+
+	writel(val, ioaddr + VLAN_TAG);
+}
+
+static int vlan_write_filter(struct net_device *dev,
+			     struct mac_device_info *hw,
+			     u8 index, u32 data)
+{
+	void __iomem *ioaddr = (void __iomem *)dev->base_addr;
+	int ret;
+	u32 val;
+
+	if (index >= hw->num_vlan)
+		return -EINVAL;
+
+	writel(data, ioaddr + VLAN_TAG_DATA);
+
+	val = readl(ioaddr + VLAN_TAG);
+	val &= ~(VLAN_TAG_CTRL_OFS_MASK |
+		VLAN_TAG_CTRL_CT |
+		VLAN_TAG_CTRL_OB);
+	val |= (index << VLAN_TAG_CTRL_OFS_SHIFT) | VLAN_TAG_CTRL_OB;
+
+	writel(val, ioaddr + VLAN_TAG);
+
+	ret = readl_poll_timeout(ioaddr + VLAN_TAG, val,
+				 !(val & VLAN_TAG_CTRL_OB),
+				 1000, 500000);
+	if (ret) {
+		netdev_err(dev, "Timeout accessing MAC_VLAN_Tag_Filter\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int vlan_add_hw_rx_fltr(struct net_device *dev,
+			       struct mac_device_info *hw,
+			       __be16 proto, u16 vid)
+{
+	int index = -1;
+	u32 val = 0;
+	int i, ret;
+
+	if (vid > 4095)
+		return -EINVAL;
+
+	/* Single Rx VLAN Filter */
+	if (hw->num_vlan == 1) {
+		/* For single VLAN filter, VID 0 means VLAN promiscuous */
+		if (vid == 0) {
+			netdev_warn(dev, "Adding VLAN ID 0 is not supported\n");
+			return -EPERM;
+		}
+
+		if (hw->vlan_filter[0] & VLAN_TAG_VID) {
+			netdev_err(dev, "Only single VLAN ID supported\n");
+			return -EPERM;
+		}
+
+		hw->vlan_filter[0] = vid;
+		vlan_write_single(dev, vid);
+
+		return 0;
+	}
+
+	/* Extended Rx VLAN Filter Enable */
+	val |= VLAN_TAG_DATA_ETV | VLAN_TAG_DATA_VEN | vid;
+
+	for (i = 0; i < hw->num_vlan; i++) {
+		if (hw->vlan_filter[i] == val)
+			return 0;
+		else if (!(hw->vlan_filter[i] & VLAN_TAG_DATA_VEN))
+			index = i;
+	}
+
+	if (index == -1) {
+		netdev_err(dev, "MAC_VLAN_Tag_Filter full (size: %0u)\n",
+			   hw->num_vlan);
+		return -EPERM;
+	}
+
+	ret = vlan_write_filter(dev, hw, index, val);
+
+	if (!ret)
+		hw->vlan_filter[index] = val;
+
+	return ret;
+}
+
+static int vlan_del_hw_rx_fltr(struct net_device *dev,
+			       struct mac_device_info *hw,
+			       __be16 proto, u16 vid)
+{
+	int i, ret = 0;
+
+	/* Single Rx VLAN Filter */
+	if (hw->num_vlan == 1) {
+		if ((hw->vlan_filter[0] & VLAN_TAG_VID) == vid) {
+			hw->vlan_filter[0] = 0;
+			vlan_write_single(dev, 0);
+		}
+		return 0;
+	}
+
+	/* Extended Rx VLAN Filter Enable */
+	for (i = 0; i < hw->num_vlan; i++) {
+		if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid) {
+			ret = vlan_write_filter(dev, hw, i, 0);
+
+			if (!ret)
+				hw->vlan_filter[i] = 0;
+			else
+				return ret;
+		}
+	}
+
+	return ret;
+}
+
+static void vlan_restore_hw_rx_fltr(struct net_device *dev,
+				    struct mac_device_info *hw)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+	u32 hash;
+	u32 val;
+	int i;
+
+	/* Single Rx VLAN Filter */
+	if (hw->num_vlan == 1) {
+		vlan_write_single(dev, hw->vlan_filter[0]);
+		return;
+	}
+
+	/* Extended Rx VLAN Filter Enable */
+	for (i = 0; i < hw->num_vlan; i++) {
+		if (hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) {
+			val = hw->vlan_filter[i];
+			vlan_write_filter(dev, hw, i, val);
+		}
+	}
+
+	hash = readl(ioaddr + VLAN_HASH_TABLE);
+	if (hash & VLAN_VLHT) {
+		value = readl(ioaddr + VLAN_TAG);
+		value |= VLAN_VTHM;
+		writel(value, ioaddr + VLAN_TAG);
+	}
+}
+
+static void vlan_update_hash(struct mac_device_info *hw, u32 hash,
+			     u16 perfect_match, bool is_double)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	writel(hash, ioaddr + VLAN_HASH_TABLE);
+
+	value = readl(ioaddr + VLAN_TAG);
+
+	if (hash) {
+		value |= VLAN_VTHM | VLAN_ETV;
+		if (is_double) {
+			value |= VLAN_EDVLP;
+			value |= VLAN_ESVL;
+			value |= VLAN_DOVLTC;
+		}
+
+		writel(value, ioaddr + VLAN_TAG);
+	} else if (perfect_match) {
+		u32 value = VLAN_ETV;
+
+		if (is_double) {
+			value |= VLAN_EDVLP;
+			value |= VLAN_ESVL;
+			value |= VLAN_DOVLTC;
+		}
+
+		writel(value | perfect_match, ioaddr + VLAN_TAG);
+	} else {
+		value &= ~(VLAN_VTHM | VLAN_ETV);
+		value &= ~(VLAN_EDVLP | VLAN_ESVL);
+		value &= ~VLAN_DOVLTC;
+		value &= ~VLAN_VID;
+
+		writel(value, ioaddr + VLAN_TAG);
+	}
+}
+
+static void vlan_enable(struct mac_device_info *hw, u32 type)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = readl(ioaddr + VLAN_INCL);
+	value |= VLAN_VLTI;
+	value |= VLAN_CSVL; /* Only use SVLAN */
+	value &= ~VLAN_VLC;
+	value |= (type << VLAN_VLC_SHIFT) & VLAN_VLC;
+	writel(value, ioaddr + VLAN_INCL);
+}
+
+static void vlan_rx_hw(struct mac_device_info *hw,
+		       struct dma_desc *rx_desc, struct sk_buff *skb)
+{
+	if (hw->desc->get_rx_vlan_valid(rx_desc)) {
+		u16 vid = hw->desc->get_rx_vlan_tci(rx_desc);
+
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
+	}
+}
+
+static void vlan_set_hw_mode(struct mac_device_info *hw)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + VLAN_TAG);
+
+	value &= ~VLAN_TAG_CTRL_EVLS_MASK;
+
+	if (hw->hw_vlan_en)
+		/* Always strip VLAN on Receive */
+		value |= VLAN_TAG_STRIP_ALL;
+	else
+		/* Do not strip VLAN on Receive */
+		value |= VLAN_TAG_STRIP_NONE;
+
+	/* Enable outer VLAN Tag in Rx DMA descriptor */
+	value |= VLAN_TAG_CTRL_EVLRXS;
+	writel(value, ioaddr + VLAN_TAG);
+}
+
+static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash,
+				      u16 perfect_match, bool is_double)
+{
+	void __iomem *ioaddr = hw->pcsr;
+
+	writel(hash, ioaddr + VLAN_HASH_TABLE);
+
+	if (hash) {
+		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
+
+		value |= XGMAC_FILTER_VTFE;
+
+		writel(value, ioaddr + XGMAC_PACKET_FILTER);
+
+		value = readl(ioaddr + VLAN_TAG);
+
+		value |= VLAN_VTHM | VLAN_ETV;
+		if (is_double) {
+			value |= VLAN_EDVLP;
+			value |= VLAN_ESVL;
+			value |= VLAN_DOVLTC;
+		} else {
+			value &= ~VLAN_EDVLP;
+			value &= ~VLAN_ESVL;
+			value &= ~VLAN_DOVLTC;
+		}
+
+		value &= ~VLAN_VID;
+		writel(value, ioaddr + VLAN_TAG);
+	} else if (perfect_match) {
+		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
+
+		value |= XGMAC_FILTER_VTFE;
+
+		writel(value, ioaddr + XGMAC_PACKET_FILTER);
+
+		value = readl(ioaddr + VLAN_TAG);
+
+		value &= ~VLAN_VTHM;
+		value |= VLAN_ETV;
+		if (is_double) {
+			value |= VLAN_EDVLP;
+			value |= VLAN_ESVL;
+			value |= VLAN_DOVLTC;
+		} else {
+			value &= ~VLAN_EDVLP;
+			value &= ~VLAN_ESVL;
+			value &= ~VLAN_DOVLTC;
+		}
+
+		value &= ~VLAN_VID;
+		writel(value | perfect_match, ioaddr + VLAN_TAG);
+	} else {
+		u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
+
+		value &= ~XGMAC_FILTER_VTFE;
+
+		writel(value, ioaddr + XGMAC_PACKET_FILTER);
+
+		value = readl(ioaddr + VLAN_TAG);
+
+		value &= ~(VLAN_VTHM | VLAN_ETV);
+		value &= ~(VLAN_EDVLP | VLAN_ESVL);
+		value &= ~VLAN_DOVLTC;
+		value &= ~VLAN_VID;
+
+		writel(value, ioaddr + VLAN_TAG);
+	}
+}
+
+const struct stmmac_vlan_ops dwmac_vlan_ops = {
+	.update_vlan_hash = vlan_update_hash,
+	.enable_vlan = vlan_enable,
+	.add_hw_vlan_rx_fltr = vlan_add_hw_rx_fltr,
+	.del_hw_vlan_rx_fltr = vlan_del_hw_rx_fltr,
+	.restore_hw_vlan_rx_fltr = vlan_restore_hw_rx_fltr,
+	.rx_hw_vlan = vlan_rx_hw,
+	.set_hw_vlan_mode = vlan_set_hw_mode,
+};
+
+const struct stmmac_vlan_ops dwxlgmac2_vlan_ops = {
+	.update_vlan_hash = dwxgmac2_update_vlan_hash,
+	.enable_vlan = vlan_enable,
+};
+
+const struct stmmac_vlan_ops dwxgmac210_vlan_ops = {
+	.update_vlan_hash = dwxgmac2_update_vlan_hash,
+	.enable_vlan = vlan_enable,
+	.add_hw_vlan_rx_fltr = vlan_add_hw_rx_fltr,
+	.del_hw_vlan_rx_fltr = vlan_del_hw_rx_fltr,
+	.restore_hw_vlan_rx_fltr = vlan_restore_hw_rx_fltr,
+	.rx_hw_vlan = vlan_rx_hw,
+	.set_hw_vlan_mode = vlan_set_hw_mode,
+};
+
+u32 stmmac_get_num_vlan(void __iomem *ioaddr)
+{
+	u32 val, num_vlan;
+
+	val = readl(ioaddr + HW_FEATURE3);
+	switch (val & VLAN_HW_FEAT_NRVF) {
+	case 0:
+		num_vlan = 1;
+		break;
+	case 1:
+		num_vlan = 4;
+		break;
+	case 2:
+		num_vlan = 8;
+		break;
+	case 3:
+		num_vlan = 16;
+		break;
+	case 4:
+		num_vlan = 24;
+		break;
+	case 5:
+		num_vlan = 32;
+		break;
+	default:
+		num_vlan = 1;
+	}
+
+	return num_vlan;
+}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.h
new file mode 100644
index 000000000000..c24f89a9049b
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2025, Altera Corporation
+ * stmmac VLAN(802.1Q) handling
+ */
+
+#ifndef __STMMAC_VLAN_H__
+#define __STMMAC_VLAN_H__
+
+#include <linux/bitfield.h>
+#include "dwxgmac2.h"
+
+#define VLAN_TAG			0x00000050
+#define VLAN_TAG_DATA			0x00000054
+#define VLAN_HASH_TABLE			0x00000058
+#define VLAN_INCL			0x00000060
+
+/* MAC VLAN */
+#define VLAN_EDVLP			BIT(26)
+#define VLAN_VTHM			BIT(25)
+#define VLAN_DOVLTC			BIT(20)
+#define VLAN_ESVL			BIT(18)
+#define VLAN_ETV			BIT(16)
+#define VLAN_VID			GENMASK(15, 0)
+#define VLAN_VLTI			BIT(20)
+#define VLAN_CSVL			BIT(19)
+#define VLAN_VLC			GENMASK(17, 16)
+#define VLAN_VLC_SHIFT			16
+#define VLAN_VLHT			GENMASK(15, 0)
+
+/* MAC VLAN Tag */
+#define VLAN_TAG_VID			GENMASK(15, 0)
+#define VLAN_TAG_ETV			BIT(16)
+
+/* MAC VLAN Tag Control */
+#define VLAN_TAG_CTRL_OB		BIT(0)
+#define VLAN_TAG_CTRL_CT		BIT(1)
+#define VLAN_TAG_CTRL_OFS_MASK		GENMASK(6, 2)
+#define VLAN_TAG_CTRL_OFS_SHIFT		2
+#define VLAN_TAG_CTRL_EVLS_MASK		GENMASK(22, 21)
+#define VLAN_TAG_CTRL_EVLS_SHIFT	21
+#define VLAN_TAG_CTRL_EVLRXS		BIT(24)
+
+#define VLAN_TAG_STRIP_NONE		FIELD_PREP(VLAN_TAG_CTRL_EVLS_MASK, 0x0)
+#define VLAN_TAG_STRIP_PASS		FIELD_PREP(VLAN_TAG_CTRL_EVLS_MASK, 0x1)
+#define VLAN_TAG_STRIP_FAIL		FIELD_PREP(VLAN_TAG_CTRL_EVLS_MASK, 0x2)
+#define VLAN_TAG_STRIP_ALL		FIELD_PREP(VLAN_TAG_CTRL_EVLS_MASK, 0x3)
+
+/* MAC VLAN Tag Data/Filter */
+#define VLAN_TAG_DATA_VID		GENMASK(15, 0)
+#define VLAN_TAG_DATA_VEN		BIT(16)
+#define VLAN_TAG_DATA_ETV		BIT(17)
+
+/* MAC VLAN HW FEAT */
+#define HW_FEATURE3			0x00000128
+#define VLAN_HW_FEAT_NRVF		GENMASK(2, 0)
+
+extern const struct stmmac_vlan_ops dwmac_vlan_ops;
+extern const struct stmmac_vlan_ops dwxgmac210_vlan_ops;
+extern const struct stmmac_vlan_ops dwxlgmac2_vlan_ops;
+
+u32 stmmac_get_num_vlan(void __iomem *ioaddr);
+
+#endif /* __STMMAC_VLAN_H__ */
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 73c07f10f053..379b6e90121d 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -9064,6 +9064,8 @@ static void niu_try_msix(struct niu *np, u8 *ldg_num_map)
 		msi_vec[i].entry = i;
 	}
 
+	pdev->dev_flags |= PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST;
+
 	num_irqs = pci_enable_msix_range(pdev, msi_vec, 1, num_irqs);
 	if (num_irqs < 0) {
 		np->flags &= ~NIU_FLAGS_MSIX;
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index e78de79a5d78..f20d1ff192ef 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2666,7 +2666,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 				of_property_read_bool(port_np, "ti,mac-only");
 
 		/* get phy/link info */
-		port->slave.port_np = port_np;
+		port->slave.port_np = of_node_get(port_np);
 		ret = of_get_phy_mode(port_np, &port->slave.phy_if);
 		if (ret) {
 			dev_err(dev, "%pOF read phy-mode err %d\n",
@@ -2679,13 +2679,15 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 			goto of_node_put;
 
 		ret = of_get_mac_address(port_np, port->slave.mac_addr);
-		if (ret) {
+		if (ret == -EPROBE_DEFER) {
+			goto of_node_put;
+		} else if (ret) {
 			am65_cpsw_am654_get_efuse_macid(port_np,
 							port->port_id,
 							port->slave.mac_addr);
 			if (!is_valid_ether_addr(port->slave.mac_addr)) {
 				eth_random_addr(port->slave.mac_addr);
-				dev_err(dev, "Use random MAC address\n");
+				dev_info(dev, "Use random MAC address\n");
 			}
 		}
 
@@ -2720,6 +2722,17 @@ static void am65_cpsw_nuss_phylink_cleanup(struct am65_cpsw_common *common)
 	}
 }
 
+static void am65_cpsw_remove_dt(struct am65_cpsw_common *common)
+{
+	struct am65_cpsw_port *port;
+	int i;
+
+	for (i = 0; i < common->port_num; i++) {
+		port = &common->ports[i];
+		of_node_put(port->slave.port_np);
+	}
+}
+
 static int
 am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 {
@@ -2749,7 +2762,7 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 	mutex_init(&ndev_priv->mm_lock);
 	port->qos.link_speed = SPEED_UNKNOWN;
 	SET_NETDEV_DEV(port->ndev, dev);
-	port->ndev->dev.of_node = port->slave.port_np;
+	device_set_node(&port->ndev->dev, of_fwnode_handle(port->slave.port_np));
 
 	eth_hw_addr_set(port->ndev, port->slave.mac_addr);
 
@@ -3550,6 +3563,16 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	am65_cpsw_nuss_get_ver(common);
+
+	ret = am65_cpsw_nuss_init_host_p(common);
+	if (ret)
+		goto err_pm_clear;
+
+	ret = am65_cpsw_nuss_init_slave_ports(common);
+	if (ret)
+		goto err_pm_clear;
+
 	node = of_get_child_by_name(dev->of_node, "mdio");
 	if (!node) {
 		dev_warn(dev, "MDIO node not found\n");
@@ -3566,16 +3589,6 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 	}
 	of_node_put(node);
 
-	am65_cpsw_nuss_get_ver(common);
-
-	ret = am65_cpsw_nuss_init_host_p(common);
-	if (ret)
-		goto err_of_clear;
-
-	ret = am65_cpsw_nuss_init_slave_ports(common);
-	if (ret)
-		goto err_of_clear;
-
 	/* init common data */
 	ale_params.dev = dev;
 	ale_params.ale_ageout = AM65_CPSW_ALE_AGEOUT_DEFAULT;
@@ -3622,6 +3635,7 @@ err_ndevs_clear:
 	am65_cpsw_nuss_cleanup_ndev(common);
 	am65_cpsw_nuss_phylink_cleanup(common);
 	am65_cpts_release(common->cpts);
+	am65_cpsw_remove_dt(common);
 err_of_clear:
 	if (common->mdio_dev)
 		of_platform_device_destroy(common->mdio_dev, NULL);
@@ -3661,6 +3675,7 @@ static void am65_cpsw_nuss_remove(struct platform_device *pdev)
 	am65_cpsw_nuss_phylink_cleanup(common);
 	am65_cpts_release(common->cpts);
 	am65_cpsw_disable_serdes_phy(common);
+	am65_cpsw_remove_dt(common);
 
 	if (common->mdio_dev)
 		of_platform_device_destroy(common->mdio_dev, NULL);
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index a984b7d84e5e..54c24cd3d3be 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1156,6 +1156,27 @@ static void cpsw_ndo_poll_controller(struct net_device *ndev)
 }
 #endif
 
+/* We need a custom implementation of phy_do_ioctl_running() because in switch
+ * mode, dev->phydev may be different than the phy of the active_slave. We need
+ * to operate on the locally saved phy instead.
+ */
+static int cpsw_ndo_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
+{
+	struct cpsw_priv *priv = netdev_priv(dev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+	struct phy_device *phy;
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	phy = cpsw->slaves[slave_no].phy;
+	if (phy)
+		return phy_mii_ioctl(phy, req, cmd);
+
+	return -EOPNOTSUPP;
+}
+
 static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_open		= cpsw_ndo_open,
 	.ndo_stop		= cpsw_ndo_stop,
@@ -1174,6 +1195,8 @@ static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_setup_tc           = cpsw_ndo_setup_tc,
 	.ndo_bpf		= cpsw_ndo_bpf,
 	.ndo_xdp_xmit		= cpsw_ndo_xdp_xmit,
+	.ndo_hwtstamp_get	= cpsw_hwtstamp_get,
+	.ndo_hwtstamp_set	= cpsw_hwtstamp_set,
 };
 
 static void cpsw_get_drvinfo(struct net_device *ndev,
@@ -1646,6 +1669,9 @@ static int cpsw_probe(struct platform_device *pdev)
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
 	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
 			     NETDEV_XDP_ACT_NDO_XMIT;
+	/* Hijack PHY timestamping requests in order to block them */
+	if (!cpsw->data.dual_emac)
+		ndev->see_all_hwtstamp_requests = true;
 
 	ndev->netdev_ops = &cpsw_netdev_ops;
 	ndev->ethtool_ops = &cpsw_ethtool_ops;
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 5b5b52e4e7a7..8b9e2078c602 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1132,7 +1132,7 @@ static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_stop		= cpsw_ndo_stop,
 	.ndo_start_xmit		= cpsw_ndo_start_xmit,
 	.ndo_set_mac_address	= cpsw_ndo_set_mac_address,
-	.ndo_eth_ioctl		= cpsw_ndo_ioctl,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= cpsw_ndo_tx_timeout,
 	.ndo_set_rx_mode	= cpsw_ndo_set_rx_mode,
@@ -1147,6 +1147,8 @@ static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_bpf		= cpsw_ndo_bpf,
 	.ndo_xdp_xmit		= cpsw_ndo_xdp_xmit,
 	.ndo_get_port_parent_id	= cpsw_get_port_parent_id,
+	.ndo_hwtstamp_get	= cpsw_hwtstamp_get,
+	.ndo_hwtstamp_set	= cpsw_hwtstamp_set,
 };
 
 static void cpsw_get_drvinfo(struct net_device *ndev,
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index 6fe4edabba44..bc4fdf17a99e 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -614,24 +614,29 @@ static void cpsw_hwtstamp_v2(struct cpsw_priv *priv)
 	writel_relaxed(ETH_P_8021Q, &cpsw->regs->vlan_ltype);
 }
 
-static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
+int cpsw_hwtstamp_set(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg,
+		      struct netlink_ext_ack *extack)
 {
 	struct cpsw_priv *priv = netdev_priv(dev);
 	struct cpsw_common *cpsw = priv->cpsw;
-	struct hwtstamp_config cfg;
+
+	/* This will only execute if dev->see_all_hwtstamp_requests is set */
+	if (cfg->source != HWTSTAMP_SOURCE_NETDEV) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Switch mode only supports MAC timestamping");
+		return -EOPNOTSUPP;
+	}
 
 	if (cpsw->version != CPSW_VERSION_1 &&
 	    cpsw->version != CPSW_VERSION_2 &&
 	    cpsw->version != CPSW_VERSION_3)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	if (cfg.tx_type != HWTSTAMP_TX_OFF && cfg.tx_type != HWTSTAMP_TX_ON)
+	if (cfg->tx_type != HWTSTAMP_TX_OFF && cfg->tx_type != HWTSTAMP_TX_ON)
 		return -ERANGE;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		priv->rx_ts_enabled = 0;
 		break;
@@ -651,13 +656,13 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 		priv->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V2_EVENT;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	priv->tx_ts_enabled = cfg.tx_type == HWTSTAMP_TX_ON;
+	priv->tx_ts_enabled = cfg->tx_type == HWTSTAMP_TX_ON;
 
 	switch (cpsw->version) {
 	case CPSW_VERSION_1:
@@ -671,65 +676,40 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 		WARN_ON(1);
 	}
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
-static int cpsw_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+int cpsw_hwtstamp_get(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg)
 {
 	struct cpsw_common *cpsw = ndev_to_cpsw(dev);
 	struct cpsw_priv *priv = netdev_priv(dev);
-	struct hwtstamp_config cfg;
 
 	if (cpsw->version != CPSW_VERSION_1 &&
 	    cpsw->version != CPSW_VERSION_2 &&
 	    cpsw->version != CPSW_VERSION_3)
 		return -EOPNOTSUPP;
 
-	cfg.flags = 0;
-	cfg.tx_type = priv->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	cfg.rx_filter = priv->rx_ts_enabled;
+	cfg->tx_type = priv->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	cfg->rx_filter = priv->rx_ts_enabled;
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 #else
-static int cpsw_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+int cpsw_hwtstamp_get(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg)
 {
 	return -EOPNOTSUPP;
 }
 
-static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
+int cpsw_hwtstamp_set(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg,
+		      struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
 #endif /*CONFIG_TI_CPTS*/
 
-int cpsw_ndo_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
-{
-	struct cpsw_priv *priv = netdev_priv(dev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int slave_no = cpsw_slave_index(cpsw, priv);
-	struct phy_device *phy;
-
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	phy = cpsw->slaves[slave_no].phy;
-
-	if (!phy_has_hwtstamp(phy)) {
-		switch (cmd) {
-		case SIOCSHWTSTAMP:
-			return cpsw_hwtstamp_set(dev, req);
-		case SIOCGHWTSTAMP:
-			return cpsw_hwtstamp_get(dev, req);
-		}
-	}
-
-	if (phy)
-		return phy_mii_ioctl(phy, req, cmd);
-
-	return -EOPNOTSUPP;
-}
-
 int cpsw_ndo_set_tx_maxrate(struct net_device *ndev, int queue, u32 rate)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index f2fc55d9295d..91add8925e23 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -461,7 +461,6 @@ void soft_reset(const char *module, void __iomem *reg);
 void cpsw_set_slave_mac(struct cpsw_slave *slave, struct cpsw_priv *priv);
 void cpsw_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue);
 int cpsw_need_resplit(struct cpsw_common *cpsw);
-int cpsw_ndo_ioctl(struct net_device *dev, struct ifreq *req, int cmd);
 int cpsw_ndo_set_tx_maxrate(struct net_device *ndev, int queue, u32 rate);
 int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 		      void *type_data);
@@ -469,6 +468,11 @@ bool cpsw_shp_is_off(struct cpsw_priv *priv);
 void cpsw_cbs_resume(struct cpsw_slave *slave, struct cpsw_priv *priv);
 void cpsw_mqprio_resume(struct cpsw_slave *slave, struct cpsw_priv *priv);
 void cpsw_qos_clsflower_resume(struct cpsw_priv *priv);
+int cpsw_hwtstamp_get(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg);
+int cpsw_hwtstamp_set(struct net_device *dev,
+		      struct kernel_hwtstamp_config *cfg,
+		      struct netlink_ext_ack *extack);
 
 /* ethtool */
 u32 cpsw_get_msglevel(struct net_device *ndev);
diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index b4a34c57b7b4..2a1c43316f46 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -412,6 +412,22 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 	int ret;
 	u64 cmp;
 
+	if (!on) {
+		/* Disable CMP 1 */
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+				   IEP_CMP_CFG_CMP_EN(1), 0);
+
+		/* clear CMP regs */
+		regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
+		if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+			regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
+
+		/* Disable sync */
+		regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0);
+
+		return 0;
+	}
+
 	/* Calculate width of the signal for PPS/PEROUT handling */
 	ts.tv_sec = req->on.sec;
 	ts.tv_nsec = req->on.nsec;
@@ -430,64 +446,39 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 		if (ret)
 			return ret;
 
-		if (on) {
-			/* Configure CMP */
-			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, lower_32_bits(cmp));
-			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
-				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, upper_32_bits(cmp));
-			/* Configure SYNC, based on req on width */
-			regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
-				     div_u64(ns_width, iep->def_inc));
-			regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
-			regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
-				     div_u64(ns_start, iep->def_inc));
-			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0); /* one-shot mode */
-			/* Enable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
-		} else {
-			/* Disable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), 0);
-
-			/* clear regs */
-			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
-			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
-				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
-		}
+		/* Configure CMP */
+		regmap_write(iep->map, ICSS_IEP_CMP1_REG0, lower_32_bits(cmp));
+		if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+			regmap_write(iep->map, ICSS_IEP_CMP1_REG1, upper_32_bits(cmp));
+		/* Configure SYNC, based on req on width */
+		regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
+			     div_u64(ns_width, iep->def_inc));
+		regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
+		regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
+			     div_u64(ns_start, iep->def_inc));
+		regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0); /* one-shot mode */
+		/* Enable CMP 1 */
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+				   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
 	} else {
-		if (on) {
-			u64 start_ns;
-
-			iep->period = ((u64)req->period.sec * NSEC_PER_SEC) +
-				      req->period.nsec;
-			start_ns = ((u64)req->period.sec * NSEC_PER_SEC)
-				   + req->period.nsec;
-			icss_iep_update_to_next_boundary(iep, start_ns);
-
-			regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
-				     div_u64(ns_width, iep->def_inc));
-			regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
-				     div_u64(ns_start, iep->def_inc));
-			/* Enable Sync in single shot mode  */
-			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG,
-				     IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN);
-			/* Enable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
-		} else {
-			/* Disable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), 0);
-
-			/* clear CMP regs */
-			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
-			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
-				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
-
-			/* Disable sync */
-			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0);
-		}
+		u64 start_ns;
+
+		iep->period = ((u64)req->period.sec * NSEC_PER_SEC) +
+				req->period.nsec;
+		start_ns = ((u64)req->period.sec * NSEC_PER_SEC)
+				+ req->period.nsec;
+		icss_iep_update_to_next_boundary(iep, start_ns);
+
+		regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
+			     div_u64(ns_width, iep->def_inc));
+		regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
+			     div_u64(ns_start, iep->def_inc));
+		/* Enable Sync in single shot mode  */
+		regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG,
+			     IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN);
+		/* Enable CMP 1 */
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+				   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
 	}
 
 	return 0;
@@ -498,11 +489,21 @@ static int icss_iep_perout_enable(struct icss_iep *iep,
 {
 	int ret = 0;
 
+	if (!on)
+		goto disable;
+
 	/* Reject requests with unsupported flags */
 	if (req->flags & ~(PTP_PEROUT_DUTY_CYCLE |
 			  PTP_PEROUT_PHASE))
 		return -EOPNOTSUPP;
 
+	/* Set default "on" time (1ms) for the signal if not passed by the app */
+	if (!(req->flags & PTP_PEROUT_DUTY_CYCLE)) {
+		req->on.sec = 0;
+		req->on.nsec = NSEC_PER_MSEC;
+	}
+
+disable:
 	mutex_lock(&iep->ptp_clk_mutex);
 
 	if (iep->pps_enabled) {
@@ -513,12 +514,6 @@ static int icss_iep_perout_enable(struct icss_iep *iep,
 	if (iep->perout_enabled == !!on)
 		goto exit;
 
-	/* Set default "on" time (1ms) for the signal if not passed by the app */
-	if (!(req->flags & PTP_PEROUT_DUTY_CYCLE)) {
-		req->on.sec = 0;
-		req->on.nsec = NSEC_PER_MSEC;
-	}
-
 	ret = icss_iep_perout_enable_hw(iep, req, on);
 	if (!ret)
 		iep->perout_enabled = !!on;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index 14002b026452..5b8fdb882172 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -187,7 +187,6 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
 			xdp_return_frame(xdpf);
 			break;
 		default:
-			netdev_err(ndev, "tx_complete: invalid swdata type %d\n", swdata->type);
 			prueth_xmit_free(tx_chn, desc_tx);
 			ndev->stats.tx_dropped++;
 			continue;
@@ -567,6 +566,7 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
 {
 	struct cppi5_host_desc_t *first_desc;
 	struct net_device *ndev = emac->ndev;
+	struct netdev_queue *netif_txq;
 	struct prueth_tx_chn *tx_chn;
 	dma_addr_t desc_dma, buf_dma;
 	struct prueth_swdata *swdata;
@@ -583,7 +583,7 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
 	first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
 	if (!first_desc) {
 		netdev_dbg(ndev, "xdp tx: failed to allocate descriptor\n");
-		goto drop_free_descs;	/* drop */
+		return ICSSG_XDP_CONSUMED;	/* drop */
 	}
 
 	if (page) { /* already DMA mapped by page_pool */
@@ -620,12 +620,17 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
 		swdata->data.xdpf = xdpf;
 	}
 
+	/* Report BQL before sending the packet */
+	netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
+	netdev_tx_sent_queue(netif_txq, xdpf->len);
+
 	cppi5_hdesc_set_pktlen(first_desc, xdpf->len);
 	desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
 
 	ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
 	if (ret) {
 		netdev_err(ndev, "xdp tx: push failed: %d\n", ret);
+		netdev_tx_completed_queue(netif_txq, 1, xdpf->len);
 		goto drop_free_descs;
 	}
 
@@ -650,6 +655,8 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
 			struct page *page, u32 *len)
 {
 	struct net_device *ndev = emac->ndev;
+	struct netdev_queue *netif_txq;
+	int cpu = smp_processor_id();
 	struct bpf_prog *xdp_prog;
 	struct xdp_frame *xdpf;
 	u32 pkt_len = *len;
@@ -669,10 +676,15 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
 			goto drop;
 		}
 
-		q_idx = smp_processor_id() % emac->tx_ch_num;
+		q_idx = cpu % emac->tx_ch_num;
+		netif_txq = netdev_get_tx_queue(ndev, q_idx);
+		__netif_tx_lock(netif_txq, cpu);
 		result = emac_xmit_xdp_frame(emac, xdpf, page, q_idx);
-		if (result == ICSSG_XDP_CONSUMED)
+		__netif_tx_unlock(netif_txq);
+		if (result == ICSSG_XDP_CONSUMED) {
+			ndev->stats.tx_dropped++;
 			goto drop;
+		}
 
 		dev_sw_netstats_rx_add(ndev, xdpf->len);
 		return result;
@@ -977,6 +989,7 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev
 	ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
 	if (ret) {
 		netdev_err(ndev, "tx: push failed: %d\n", ret);
+		netdev_tx_completed_queue(netif_txq, 1, pkt_len);
 		goto drop_free_descs;
 	}
 
@@ -1215,9 +1228,6 @@ void prueth_reset_rx_chan(struct prueth_rx_chn *chn,
 					  prueth_rx_cleanup);
 	if (disable)
 		k3_udma_glue_disable_rx_chn(chn->rx_chn);
-
-	page_pool_destroy(chn->pg_pool);
-	chn->pg_pool = NULL;
 }
 EXPORT_SYMBOL_GPL(prueth_reset_rx_chan);
 
@@ -1319,10 +1329,28 @@ void icssg_ndo_get_stats64(struct net_device *ndev,
 	stats->rx_over_errors = emac_get_stat_by_name(emac, "rx_over_errors");
 	stats->multicast      = emac_get_stat_by_name(emac, "rx_multicast_frames");
 
-	stats->rx_errors  = ndev->stats.rx_errors;
-	stats->rx_dropped = ndev->stats.rx_dropped;
+	stats->rx_errors  = ndev->stats.rx_errors +
+			    emac_get_stat_by_name(emac, "FW_RX_ERROR") +
+			    emac_get_stat_by_name(emac, "FW_RX_EOF_SHORT_FRMERR") +
+			    emac_get_stat_by_name(emac, "FW_RX_B0_DROP_EARLY_EOF") +
+			    emac_get_stat_by_name(emac, "FW_RX_EXP_FRAG_Q_DROP") +
+			    emac_get_stat_by_name(emac, "FW_RX_FIFO_OVERRUN");
+	stats->rx_dropped = ndev->stats.rx_dropped +
+			    emac_get_stat_by_name(emac, "FW_DROPPED_PKT") +
+			    emac_get_stat_by_name(emac, "FW_INF_PORT_DISABLED") +
+			    emac_get_stat_by_name(emac, "FW_INF_SAV") +
+			    emac_get_stat_by_name(emac, "FW_INF_SA_DL") +
+			    emac_get_stat_by_name(emac, "FW_INF_PORT_BLOCKED") +
+			    emac_get_stat_by_name(emac, "FW_INF_DROP_TAGGED") +
+			    emac_get_stat_by_name(emac, "FW_INF_DROP_PRIOTAGGED") +
+			    emac_get_stat_by_name(emac, "FW_INF_DROP_NOTAG") +
+			    emac_get_stat_by_name(emac, "FW_INF_DROP_NOTMEMBER");
 	stats->tx_errors  = ndev->stats.tx_errors;
-	stats->tx_dropped = ndev->stats.tx_dropped;
+	stats->tx_dropped = ndev->stats.tx_dropped +
+			    emac_get_stat_by_name(emac, "FW_RTU_PKT_DROP") +
+			    emac_get_stat_by_name(emac, "FW_TX_DROPPED_PACKET") +
+			    emac_get_stat_by_name(emac, "FW_TX_TS_DROPPED_PACKET") +
+			    emac_get_stat_by_name(emac, "FW_TX_JUMBO_FRM_CUTOFF");
 }
 EXPORT_SYMBOL_GPL(icssg_ndo_get_stats64);
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 443f90fa6557..86fc1278127c 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1075,17 +1075,21 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame
 {
 	struct prueth_emac *emac = netdev_priv(dev);
 	struct net_device *ndev = emac->ndev;
+	struct netdev_queue *netif_txq;
+	int cpu = smp_processor_id();
 	struct xdp_frame *xdpf;
 	unsigned int q_idx;
 	int nxmit = 0;
 	u32 err;
 	int i;
 
-	q_idx = smp_processor_id() % emac->tx_ch_num;
+	q_idx = cpu % emac->tx_ch_num;
+	netif_txq = netdev_get_tx_queue(ndev, q_idx);
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
+	__netif_tx_lock(netif_txq, cpu);
 	for (i = 0; i < n; i++) {
 		xdpf = frames[i];
 		err = emac_xmit_xdp_frame(emac, xdpf, NULL, q_idx);
@@ -1095,6 +1099,7 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame
 		}
 		nxmit++;
 	}
+	__netif_tx_unlock(netif_txq);
 
 	return nxmit;
 }
@@ -1109,11 +1114,6 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame
 static int emac_xdp_setup(struct prueth_emac *emac, struct netdev_bpf *bpf)
 {
 	struct bpf_prog *prog = bpf->prog;
-	xdp_features_t val;
-
-	val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
-	      NETDEV_XDP_ACT_NDO_XMIT;
-	xdp_set_features_flag(emac->ndev, val);
 
 	if (!emac->xdpi.prog && !prog)
 		return 0;
@@ -1291,6 +1291,10 @@ static int prueth_netdev_init(struct prueth *prueth,
 	ndev->hw_features = NETIF_F_SG;
 	ndev->features = ndev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
 	ndev->hw_features |= NETIF_PRUETH_HSR_OFFLOAD_FEATURES;
+	xdp_set_features_flag(ndev,
+			      NETDEV_XDP_ACT_BASIC |
+			      NETDEV_XDP_ACT_REDIRECT |
+			      NETDEV_XDP_ACT_NDO_XMIT);
 
 	netif_napi_add(ndev, &emac->napi_rx, icssg_napi_rx_poll);
 	hrtimer_setup(&emac->rx_hrtimer, &emac_rx_timer_callback, CLOCK_MONOTONIC,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index b6be4aa57a61..23c465f1ce7f 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -54,7 +54,7 @@
 
 #define ICSSG_MAX_RFLOWS	8	/* per slice */
 
-#define ICSSG_NUM_PA_STATS	4
+#define ICSSG_NUM_PA_STATS	32
 #define ICSSG_NUM_MIIG_STATS	60
 /* Number of ICSSG related stats */
 #define ICSSG_NUM_STATS (ICSSG_NUM_MIIG_STATS + ICSSG_NUM_PA_STATS)
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c
index 6f0edae38ea2..e8241e998aa9 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c
@@ -11,7 +11,6 @@
 
 #define ICSSG_TX_PACKET_OFFSET	0xA0
 #define ICSSG_TX_BYTE_OFFSET	0xEC
-#define ICSSG_FW_STATS_BASE	0x0248
 
 static u32 stats_base[] = {	0x54c,	/* Slice 0 stats start */
 				0xb18,	/* Slice 1 stats start */
@@ -46,9 +45,8 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 
 	if (prueth->pa_stats) {
 		for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) {
-			reg = ICSSG_FW_STATS_BASE +
-			      icssg_all_pa_stats[i].offset *
-			      PRUETH_NUM_MACS + slice * sizeof(u32);
+			reg = icssg_all_pa_stats[i].offset +
+			      slice * sizeof(u32);
 			regmap_read(prueth->pa_stats, reg, &val);
 			emac->pa_stats[i] += val;
 		}
@@ -80,7 +78,7 @@ int emac_get_stat_by_name(struct prueth_emac *emac, char *stat_name)
 	if (emac->prueth->pa_stats) {
 		for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) {
 			if (!strcmp(icssg_all_pa_stats[i].name, stat_name))
-				return emac->pa_stats[icssg_all_pa_stats[i].offset / sizeof(u32)];
+				return emac->pa_stats[i];
 		}
 	}
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.h b/drivers/net/ethernet/ti/icssg/icssg_stats.h
index e88b919f532c..5ec0b38e0c67 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.h
@@ -155,24 +155,10 @@ static const struct icssg_miig_stats icssg_all_miig_stats[] = {
 	ICSSG_MIIG_STATS(tx_bytes, true),
 };
 
-/**
- * struct pa_stats_regs - ICSSG Firmware maintained PA Stats register
- * @fw_rx_cnt: Number of valid packets sent by Rx PRU to Host on PSI
- * @fw_tx_cnt: Number of valid packets copied by RTU0 to Tx queues
- * @fw_tx_pre_overflow: Host Egress Q (Pre-emptible) Overflow Counter
- * @fw_tx_exp_overflow: Host Egress Q (Express) Overflow Counter
- */
-struct pa_stats_regs {
-	u32 fw_rx_cnt;
-	u32 fw_tx_cnt;
-	u32 fw_tx_pre_overflow;
-	u32 fw_tx_exp_overflow;
-};
-
-#define ICSSG_PA_STATS(field)			\
-{						\
-	#field,					\
-	offsetof(struct pa_stats_regs, field),	\
+#define ICSSG_PA_STATS(field)	\
+{				\
+	#field,			\
+	field,			\
 }
 
 struct icssg_pa_stats {
@@ -181,10 +167,38 @@ struct icssg_pa_stats {
 };
 
 static const struct icssg_pa_stats icssg_all_pa_stats[] = {
-	ICSSG_PA_STATS(fw_rx_cnt),
-	ICSSG_PA_STATS(fw_tx_cnt),
-	ICSSG_PA_STATS(fw_tx_pre_overflow),
-	ICSSG_PA_STATS(fw_tx_exp_overflow),
+	ICSSG_PA_STATS(FW_RTU_PKT_DROP),
+	ICSSG_PA_STATS(FW_Q0_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q1_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q2_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q3_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q4_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q5_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q6_OVERFLOW),
+	ICSSG_PA_STATS(FW_Q7_OVERFLOW),
+	ICSSG_PA_STATS(FW_DROPPED_PKT),
+	ICSSG_PA_STATS(FW_RX_ERROR),
+	ICSSG_PA_STATS(FW_RX_DS_INVALID),
+	ICSSG_PA_STATS(FW_TX_DROPPED_PACKET),
+	ICSSG_PA_STATS(FW_TX_TS_DROPPED_PACKET),
+	ICSSG_PA_STATS(FW_INF_PORT_DISABLED),
+	ICSSG_PA_STATS(FW_INF_SAV),
+	ICSSG_PA_STATS(FW_INF_SA_DL),
+	ICSSG_PA_STATS(FW_INF_PORT_BLOCKED),
+	ICSSG_PA_STATS(FW_INF_DROP_TAGGED),
+	ICSSG_PA_STATS(FW_INF_DROP_PRIOTAGGED),
+	ICSSG_PA_STATS(FW_INF_DROP_NOTAG),
+	ICSSG_PA_STATS(FW_INF_DROP_NOTMEMBER),
+	ICSSG_PA_STATS(FW_RX_EOF_SHORT_FRMERR),
+	ICSSG_PA_STATS(FW_RX_B0_DROP_EARLY_EOF),
+	ICSSG_PA_STATS(FW_TX_JUMBO_FRM_CUTOFF),
+	ICSSG_PA_STATS(FW_RX_EXP_FRAG_Q_DROP),
+	ICSSG_PA_STATS(FW_RX_FIFO_OVERRUN),
+	ICSSG_PA_STATS(FW_CUT_THR_PKT),
+	ICSSG_PA_STATS(FW_HOST_RX_PKT_CNT),
+	ICSSG_PA_STATS(FW_HOST_TX_PKT_CNT),
+	ICSSG_PA_STATS(FW_HOST_EGRESS_Q_PRE_OVERFLOW),
+	ICSSG_PA_STATS(FW_HOST_EGRESS_Q_EXP_OVERFLOW),
 };
 
 #endif /* __NET_TI_ICSSG_STATS_H */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h
index 424a7e945ea8..490a9cc06fb0 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h
@@ -231,4 +231,37 @@
 /* Start of 32 bits PA_STAT counters */
 #define PA_STAT_32b_START_OFFSET                           0x0080
 
+#define FW_RTU_PKT_DROP			0x0088
+#define FW_Q0_OVERFLOW			0x0090
+#define FW_Q1_OVERFLOW			0x0098
+#define FW_Q2_OVERFLOW			0x00A0
+#define FW_Q3_OVERFLOW			0x00A8
+#define FW_Q4_OVERFLOW			0x00B0
+#define FW_Q5_OVERFLOW			0x00B8
+#define FW_Q6_OVERFLOW			0x00C0
+#define FW_Q7_OVERFLOW			0x00C8
+#define FW_DROPPED_PKT			0x00F8
+#define FW_RX_ERROR			0x0100
+#define FW_RX_DS_INVALID		0x0108
+#define FW_TX_DROPPED_PACKET		0x0110
+#define FW_TX_TS_DROPPED_PACKET		0x0118
+#define FW_INF_PORT_DISABLED		0x0120
+#define FW_INF_SAV			0x0128
+#define FW_INF_SA_DL			0x0130
+#define FW_INF_PORT_BLOCKED		0x0138
+#define FW_INF_DROP_TAGGED		0x0140
+#define FW_INF_DROP_PRIOTAGGED		0x0148
+#define FW_INF_DROP_NOTAG		0x0150
+#define FW_INF_DROP_NOTMEMBER		0x0158
+#define FW_RX_EOF_SHORT_FRMERR		0x0188
+#define FW_RX_B0_DROP_EARLY_EOF		0x0190
+#define FW_TX_JUMBO_FRM_CUTOFF		0x0198
+#define FW_RX_EXP_FRAG_Q_DROP		0x01A0
+#define FW_RX_FIFO_OVERRUN		0x01A8
+#define FW_CUT_THR_PKT			0x01B0
+#define FW_HOST_RX_PKT_CNT		0x0248
+#define FW_HOST_TX_PKT_CNT		0x0250
+#define FW_HOST_EGRESS_Q_PRE_OVERFLOW	0x0258
+#define FW_HOST_EGRESS_Q_EXP_OVERFLOW	0x0260
+
 #endif /* __NET_TI_ICSSG_SWITCH_MAP_H  */
diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c
index 89dc4c401a8d..a75bca1243e3 100644
--- a/drivers/net/ethernet/vertexcom/mse102x.c
+++ b/drivers/net/ethernet/vertexcom/mse102x.c
@@ -6,7 +6,9 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/if_vlan.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
@@ -15,6 +17,7 @@
 #include <linux/cache.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/string_choices.h>
 
 #include <linux/spi/spi.h>
 #include <linux/of_net.h>
@@ -33,7 +36,7 @@
 #define CMD_CTR		(0x2 << CMD_SHIFT)
 
 #define CMD_MASK	GENMASK(15, CMD_SHIFT)
-#define LEN_MASK	GENMASK(CMD_SHIFT - 1, 0)
+#define LEN_MASK	GENMASK(CMD_SHIFT - 2, 0)
 
 #define DET_CMD_LEN	4
 #define DET_SOF_LEN	2
@@ -44,7 +47,6 @@
 
 struct mse102x_stats {
 	u64 xfer_err;
-	u64 invalid_cmd;
 	u64 invalid_ctr;
 	u64 invalid_dft;
 	u64 invalid_len;
@@ -55,7 +57,6 @@ struct mse102x_stats {
 
 static const char mse102x_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"SPI transfer errors",
-	"Invalid command",
 	"Invalid CTR",
 	"Invalid DFT",
 	"Invalid frame length",
@@ -84,6 +85,8 @@ struct mse102x_net_spi {
 	struct spi_message	spi_msg;
 	struct spi_transfer	spi_xfer;
 
+	bool			valid_cmd_received;
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry		*device_root;
 #endif
@@ -97,16 +100,18 @@ static int mse102x_info_show(struct seq_file *s, void *what)
 {
 	struct mse102x_net_spi *mses = s->private;
 
-	seq_printf(s, "TX ring size        : %u\n",
+	seq_printf(s, "TX ring size            : %u\n",
 		   skb_queue_len(&mses->mse102x.txq));
 
-	seq_printf(s, "IRQ                 : %d\n",
+	seq_printf(s, "IRQ                     : %d\n",
 		   mses->spidev->irq);
 
-	seq_printf(s, "SPI effective speed : %lu\n",
+	seq_printf(s, "SPI effective speed     : %lu\n",
 		   (unsigned long)mses->spi_xfer.effective_speed_hz);
-	seq_printf(s, "SPI mode            : %x\n",
+	seq_printf(s, "SPI mode                : %x\n",
 		   mses->spidev->mode);
+	seq_printf(s, "Received valid CMD once : %s\n",
+		   str_yes_no(mses->valid_cmd_received));
 
 	return 0;
 }
@@ -193,10 +198,10 @@ static int mse102x_rx_cmd_spi(struct mse102x_net *mse, u8 *rxb)
 	} else if (*cmd != cpu_to_be16(DET_CMD)) {
 		net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n",
 				    __func__, *cmd);
-		mse->stats.invalid_cmd++;
 		ret = -EIO;
 	} else {
 		memcpy(rxb, trx + 2, 2);
+		mses->valid_cmd_received = true;
 	}
 
 	return ret;
@@ -262,7 +267,7 @@ static int mse102x_tx_frame_spi(struct mse102x_net *mse, struct sk_buff *txp,
 }
 
 static int mse102x_rx_frame_spi(struct mse102x_net *mse, u8 *buff,
-				unsigned int frame_len)
+				unsigned int frame_len, bool drop)
 {
 	struct mse102x_net_spi *mses = to_mse102x_spi(mse);
 	struct spi_transfer *xfer = &mses->spi_xfer;
@@ -280,6 +285,9 @@ static int mse102x_rx_frame_spi(struct mse102x_net *mse, u8 *buff,
 		netdev_err(mse->ndev, "%s: spi_sync() failed: %d\n",
 			   __func__, ret);
 		mse->stats.xfer_err++;
+	} else if (drop) {
+		netdev_dbg(mse->ndev, "%s: Drop frame\n", __func__);
+		ret = -EINVAL;
 	} else if (*sof != cpu_to_be16(DET_SOF)) {
 		netdev_dbg(mse->ndev, "%s: SPI start of frame is invalid (0x%04x)\n",
 			   __func__, *sof);
@@ -302,61 +310,60 @@ static void mse102x_dump_packet(const char *msg, int len, const char *data)
 		       data, len, true);
 }
 
-static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
+static irqreturn_t mse102x_rx_pkt_spi(struct mse102x_net *mse)
 {
 	struct sk_buff *skb;
 	unsigned int rxalign;
 	unsigned int rxlen;
+	bool drop = false;
 	__be16 rx = 0;
 	u16 cmd_resp;
 	u8 *rxpkt;
-	int ret;
 
 	mse102x_tx_cmd_spi(mse, CMD_CTR);
-	ret = mse102x_rx_cmd_spi(mse, (u8 *)&rx);
-	cmd_resp = be16_to_cpu(rx);
-
-	if (ret || ((cmd_resp & CMD_MASK) != CMD_RTS)) {
+	if (mse102x_rx_cmd_spi(mse, (u8 *)&rx)) {
 		usleep_range(50, 100);
+		return IRQ_NONE;
+	}
 
-		mse102x_tx_cmd_spi(mse, CMD_CTR);
-		ret = mse102x_rx_cmd_spi(mse, (u8 *)&rx);
-		if (ret)
-			return;
-
-		cmd_resp = be16_to_cpu(rx);
-		if ((cmd_resp & CMD_MASK) != CMD_RTS) {
-			net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n",
-					    __func__, cmd_resp);
-			mse->stats.invalid_rts++;
-			return;
-		}
-
-		net_dbg_ratelimited("%s: Unexpected response to first CMD\n",
-				    __func__);
+	cmd_resp = be16_to_cpu(rx);
+	if ((cmd_resp & CMD_MASK) != CMD_RTS) {
+		net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n",
+				    __func__, cmd_resp);
+		mse->stats.invalid_rts++;
+		drop = true;
+		goto drop;
 	}
 
 	rxlen = cmd_resp & LEN_MASK;
-	if (!rxlen) {
-		net_dbg_ratelimited("%s: No frame length defined\n", __func__);
+	if (rxlen < ETH_ZLEN || rxlen > VLAN_ETH_FRAME_LEN) {
+		net_dbg_ratelimited("%s: Invalid frame length: %d\n", __func__,
+				    rxlen);
 		mse->stats.invalid_len++;
-		return;
+		drop = true;
 	}
 
+	/* In case of a invalid CMD_RTS, the frame must be consumed anyway.
+	 * So assume the maximum possible frame length.
+	 */
+drop:
+	if (drop)
+		rxlen = VLAN_ETH_FRAME_LEN;
+
 	rxalign = ALIGN(rxlen + DET_SOF_LEN + DET_DFT_LEN, 4);
 	skb = netdev_alloc_skb_ip_align(mse->ndev, rxalign);
 	if (!skb)
-		return;
+		return IRQ_NONE;
 
 	/* 2 bytes Start of frame (before ethernet header)
 	 * 2 bytes Data frame tail (after ethernet frame)
 	 * They are copied, but ignored.
 	 */
 	rxpkt = skb_put(skb, rxlen) - DET_SOF_LEN;
-	if (mse102x_rx_frame_spi(mse, rxpkt, rxlen)) {
+	if (mse102x_rx_frame_spi(mse, rxpkt, rxlen, drop)) {
 		mse->ndev->stats.rx_errors++;
 		dev_kfree_skb(skb);
-		return;
+		return IRQ_HANDLED;
 	}
 
 	if (netif_msg_pktdata(mse))
@@ -367,6 +374,8 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
 
 	mse->ndev->stats.rx_packets++;
 	mse->ndev->stats.rx_bytes += rxlen;
+
+	return IRQ_HANDLED;
 }
 
 static int mse102x_tx_pkt_spi(struct mse102x_net *mse, struct sk_buff *txb,
@@ -498,19 +507,36 @@ static irqreturn_t mse102x_irq(int irq, void *_mse)
 {
 	struct mse102x_net *mse = _mse;
 	struct mse102x_net_spi *mses = to_mse102x_spi(mse);
+	irqreturn_t ret;
 
 	mutex_lock(&mses->lock);
-	mse102x_rx_pkt_spi(mse);
+	ret = mse102x_rx_pkt_spi(mse);
 	mutex_unlock(&mses->lock);
 
-	return IRQ_HANDLED;
+	return ret;
 }
 
 static int mse102x_net_open(struct net_device *ndev)
 {
+	struct irq_data *irq_data = irq_get_irq_data(ndev->irq);
 	struct mse102x_net *mse = netdev_priv(ndev);
+	struct mse102x_net_spi *mses = to_mse102x_spi(mse);
 	int ret;
 
+	if (!irq_data) {
+		netdev_err(ndev, "Invalid IRQ: %d\n", ndev->irq);
+		return -EINVAL;
+	}
+
+	switch (irqd_get_trigger_type(irq_data)) {
+	case IRQ_TYPE_LEVEL_HIGH:
+	case IRQ_TYPE_LEVEL_LOW:
+		break;
+	default:
+		netdev_warn_once(ndev, "Only IRQ type level recommended, please update your device tree firmware.\n");
+		break;
+	}
+
 	ret = request_threaded_irq(ndev->irq, NULL, mse102x_irq, IRQF_ONESHOT,
 				   ndev->name, mse);
 	if (ret < 0) {
@@ -524,6 +550,14 @@ static int mse102x_net_open(struct net_device *ndev)
 
 	netif_carrier_on(ndev);
 
+	/* The SPI interrupt can stuck in case of pending packet(s).
+	 * So poll for possible packet(s) to re-arm the interrupt.
+	 */
+	mutex_lock(&mses->lock);
+	if (mse102x_rx_pkt_spi(mse) == IRQ_NONE)
+		mse102x_rx_pkt_spi(mse);
+	mutex_unlock(&mses->lock);
+
 	netif_dbg(mse, ifup, ndev, "network device up\n");
 
 	return 0;
diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig
index 47e3e8434b9e..e5fc942c28cc 100644
--- a/drivers/net/ethernet/wangxun/Kconfig
+++ b/drivers/net/ethernet/wangxun/Kconfig
@@ -40,7 +40,7 @@ config NGBE
 	  will be called ngbe.
 
 config TXGBE
-	tristate "Wangxun(R) 10GbE PCI Express adapters support"
+	tristate "Wangxun(R) 10/25/40GbE PCI Express adapters support"
 	depends on PCI
 	depends on COMMON_CLK
 	depends on I2C_DESIGNWARE_PLATFORM
@@ -55,7 +55,7 @@ config TXGBE
 	select PCS_XPCS
 	select LIBWX
 	help
-	  This driver supports Wangxun(R) 10GbE PCI Express family of
+	  This driver supports Wangxun(R) 10/25/40GbE PCI Express family of
 	  adapters.
 
 	  More specific information on configuring the driver is in
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
index 43019ec9329c..c12a4cb951f6 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
@@ -219,7 +219,7 @@ int wx_nway_reset(struct net_device *netdev)
 {
 	struct wx *wx = netdev_priv(netdev);
 
-	if (wx->mac.type == wx_mac_aml)
+	if (wx->mac.type == wx_mac_aml40)
 		return -EOPNOTSUPP;
 
 	return phylink_ethtool_nway_reset(wx->phylink);
@@ -231,9 +231,6 @@ int wx_get_link_ksettings(struct net_device *netdev,
 {
 	struct wx *wx = netdev_priv(netdev);
 
-	if (wx->mac.type == wx_mac_aml)
-		return -EOPNOTSUPP;
-
 	return phylink_ethtool_ksettings_get(wx->phylink, cmd);
 }
 EXPORT_SYMBOL(wx_get_link_ksettings);
@@ -243,7 +240,7 @@ int wx_set_link_ksettings(struct net_device *netdev,
 {
 	struct wx *wx = netdev_priv(netdev);
 
-	if (wx->mac.type == wx_mac_aml)
+	if (wx->mac.type == wx_mac_aml40)
 		return -EOPNOTSUPP;
 
 	return phylink_ethtool_ksettings_set(wx->phylink, cmd);
@@ -255,7 +252,7 @@ void wx_get_pauseparam(struct net_device *netdev,
 {
 	struct wx *wx = netdev_priv(netdev);
 
-	if (wx->mac.type == wx_mac_aml)
+	if (wx->mac.type == wx_mac_aml40)
 		return;
 
 	phylink_ethtool_get_pauseparam(wx->phylink, pause);
@@ -267,7 +264,7 @@ int wx_set_pauseparam(struct net_device *netdev,
 {
 	struct wx *wx = netdev_priv(netdev);
 
-	if (wx->mac.type == wx_mac_aml)
+	if (wx->mac.type == wx_mac_aml40)
 		return -EOPNOTSUPP;
 
 	return phylink_ethtool_set_pauseparam(wx->phylink, pause);
@@ -345,6 +342,7 @@ int wx_set_coalesce(struct net_device *netdev,
 		max_eitr = WX_SP_MAX_EITR;
 		break;
 	case wx_mac_aml:
+	case wx_mac_aml40:
 		max_eitr = WX_AML_MAX_EITR;
 		break;
 	default:
@@ -375,6 +373,7 @@ int wx_set_coalesce(struct net_device *netdev,
 		switch (wx->mac.type) {
 		case wx_mac_sp:
 		case wx_mac_aml:
+		case wx_mac_aml40:
 			tx_itr_param = WX_12K_ITR;
 			break;
 		default:
@@ -413,15 +412,10 @@ static unsigned int wx_max_channels(struct wx *wx)
 		max_combined = 1;
 	} else {
 		/* support up to max allowed queues with RSS */
-		switch (wx->mac.type) {
-		case wx_mac_sp:
-		case wx_mac_aml:
+		if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags))
 			max_combined = 63;
-			break;
-		default:
+		else
 			max_combined = 8;
-			break;
-		}
 	}
 
 	return max_combined;
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index 3c3aa5f4ebbf..c6744a363e97 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -113,15 +113,10 @@ static void wx_intr_disable(struct wx *wx, u64 qmask)
 	if (mask)
 		wr32(wx, WX_PX_IMS(0), mask);
 
-	switch (wx->mac.type) {
-	case wx_mac_sp:
-	case wx_mac_aml:
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		mask = (qmask >> 32);
 		if (mask)
 			wr32(wx, WX_PX_IMS(1), mask);
-		break;
-	default:
-		break;
 	}
 }
 
@@ -133,15 +128,10 @@ void wx_intr_enable(struct wx *wx, u64 qmask)
 	if (mask)
 		wr32(wx, WX_PX_IMC(0), mask);
 
-	switch (wx->mac.type) {
-	case wx_mac_sp:
-	case wx_mac_aml:
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		mask = (qmask >> 32);
 		if (mask)
 			wr32(wx, WX_PX_IMC(1), mask);
-		break;
-	default:
-		break;
 	}
 }
 EXPORT_SYMBOL(wx_intr_enable);
@@ -435,14 +425,20 @@ static int wx_host_interface_command_r(struct wx *wx, u32 *buffer,
 	wr32m(wx, WX_SW2FW_MBOX_CMD, WX_SW2FW_MBOX_CMD_VLD, WX_SW2FW_MBOX_CMD_VLD);
 
 	/* polling reply from FW */
-	err = read_poll_timeout(wx_poll_fw_reply, reply, reply, 1000, 50000,
-				true, wx, buffer, send_cmd);
+	err = read_poll_timeout(wx_poll_fw_reply, reply, reply, 2000,
+				timeout * 1000, true, wx, buffer, send_cmd);
 	if (err) {
 		wx_err(wx, "Polling from FW messages timeout, cmd: 0x%x, index: %d\n",
 		       send_cmd, wx->swfw_index);
 		goto rel_out;
 	}
 
+	if (hdr->cmd_or_resp.ret_status == 0x80) {
+		wx_err(wx, "Unknown FW command: 0x%x\n", send_cmd);
+		err = -EINVAL;
+		goto rel_out;
+	}
+
 	/* expect no reply from FW then return */
 	if (!return_data)
 		goto rel_out;
@@ -699,6 +695,7 @@ void wx_init_eeprom_params(struct wx *wx)
 	switch (wx->mac.type) {
 	case wx_mac_sp:
 	case wx_mac_aml:
+	case wx_mac_aml40:
 		if (wx_read_ee_hostif(wx, WX_SW_REGION_PTR, &data)) {
 			wx_err(wx, "NVM Read Error\n");
 			return;
@@ -768,14 +765,8 @@ static int wx_set_rar(struct wx *wx, u32 index, u8 *addr, u64 pools,
 	/* setup VMDq pool mapping */
 	wr32(wx, WX_PSR_MAC_SWC_VM_L, pools & 0xFFFFFFFF);
 
-	switch (wx->mac.type) {
-	case wx_mac_sp:
-	case wx_mac_aml:
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags))
 		wr32(wx, WX_PSR_MAC_SWC_VM_H, pools >> 32);
-		break;
-	default:
-		break;
-	}
 
 	/* HW expects these in little endian so we reverse the byte
 	 * order from network order (big endian) to little endian
@@ -913,14 +904,9 @@ void wx_init_rx_addrs(struct wx *wx)
 
 		wx_set_rar(wx, 0, wx->mac.addr, 0, WX_PSR_MAC_SWC_AD_H_AV);
 
-		switch (wx->mac.type) {
-		case wx_mac_sp:
-		case wx_mac_aml:
+		if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 			/* clear VMDq pool/queue selection for RAR 0 */
 			wx_clear_vmdq(wx, 0, WX_CLEAR_VMDQ_ALL);
-			break;
-		default:
-			break;
 		}
 	}
 
@@ -1506,7 +1492,7 @@ static void wx_configure_virtualization(struct wx *wx)
 		wr32m(wx, WX_PSR_VM_L2CTL(pool),
 		      WX_PSR_VM_L2CTL_AUPE, WX_PSR_VM_L2CTL_AUPE);
 
-	if (wx->mac.type == wx_mac_em) {
+	if (!test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		vf_shift = BIT(VMDQ_P(0));
 		/* Enable only the PF pools for Tx/Rx */
 		wr32(wx, WX_RDM_VF_RE(0), vf_shift);
@@ -1537,7 +1523,7 @@ static void wx_configure_port(struct wx *wx)
 {
 	u32 value, i;
 
-	if (wx->mac.type == wx_mac_em) {
+	if (!test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		value = (wx->num_vfs == 0) ?
 			WX_CFG_PORT_CTL_NUM_VT_NONE :
 			WX_CFG_PORT_CTL_NUM_VT_8;
@@ -2068,7 +2054,7 @@ static void wx_setup_psrtype(struct wx *wx)
 		  WX_RDB_PL_CFG_TUN_OUTL2HDR |
 		  WX_RDB_PL_CFG_TUN_TUNHDR;
 
-	if (wx->mac.type == wx_mac_em) {
+	if (!test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		for_each_set_bit(pool, &wx->fwd_bitmask, 8)
 			wr32(wx, WX_RDB_PL_CFG(VMDQ_P(pool)), psrtype);
 	} else {
@@ -2266,10 +2252,8 @@ int wx_stop_adapter(struct wx *wx)
 }
 EXPORT_SYMBOL(wx_stop_adapter);
 
-void wx_reset_misc(struct wx *wx)
+void wx_reset_mac(struct wx *wx)
 {
-	int i;
-
 	/* receive packets that size > 2048 */
 	wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_JE, WX_MAC_RX_CFG_JE);
 
@@ -2281,6 +2265,14 @@ void wx_reset_misc(struct wx *wx)
 	      WX_MAC_RX_FLOW_CTRL_RFE, WX_MAC_RX_FLOW_CTRL_RFE);
 
 	wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR);
+}
+EXPORT_SYMBOL(wx_reset_mac);
+
+void wx_reset_misc(struct wx *wx)
+{
+	int i;
+
+	wx_reset_mac(wx);
 
 	wr32m(wx, WX_MIS_RST_ST,
 	      WX_MIS_RST_ST_RST_INIT, 0x1E00);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
index 91c1d6135045..26a56cba60b9 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
@@ -42,6 +42,7 @@ void wx_configure(struct wx *wx);
 void wx_start_hw(struct wx *wx);
 int wx_disable_pcie_master(struct wx *wx);
 int wx_stop_adapter(struct wx *wx);
+void wx_reset_mac(struct wx *wx);
 void wx_reset_misc(struct wx *wx);
 int wx_get_pcie_msix_counts(struct wx *wx, u16 *msix_count, u16 max_msix_count);
 int wx_sw_init(struct wx *wx);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 18422b940dbe..5c747509d56b 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -5,6 +5,7 @@
 #include <net/ip6_checksum.h>
 #include <net/page_pool/helpers.h>
 #include <net/inet_ecn.h>
+#include <linux/workqueue.h>
 #include <linux/iopoll.h>
 #include <linux/sctp.h>
 #include <linux/pci.h>
@@ -1633,7 +1634,7 @@ static bool wx_set_vmdq_queues(struct wx *wx)
 	/* Add starting offset to total pool count */
 	vmdq_i += wx->ring_feature[RING_F_VMDQ].offset;
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		/* double check we are limited to maximum pools */
 		vmdq_i = min_t(u16, 64, vmdq_i);
 
@@ -1693,7 +1694,7 @@ static void wx_set_rss_queues(struct wx *wx)
 
 	/* set mask for 16 queue limit of RSS */
 	f = &wx->ring_feature[RING_F_RSS];
-	if (wx->mac.type == wx_mac_sp)
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags))
 		f->mask = WX_RSS_64Q_MASK;
 	else
 		f->mask = WX_RSS_8Q_MASK;
@@ -1853,7 +1854,7 @@ static bool wx_cache_ring_vmdq(struct wx *wx)
 	if (!test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags))
 		return false;
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		/* start at VMDq register offset for SR-IOV enabled setups */
 		reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask);
 		for (i = 0; i < wx->num_rx_queues; i++, reg_idx++) {
@@ -1959,6 +1960,7 @@ static int wx_alloc_q_vector(struct wx *wx,
 	switch (wx->mac.type) {
 	case wx_mac_sp:
 	case wx_mac_aml:
+	case wx_mac_aml40:
 		default_itr = WX_12K_ITR;
 		break;
 	default:
@@ -2327,6 +2329,7 @@ void wx_write_eitr(struct wx_q_vector *q_vector)
 		itr_reg = q_vector->itr & WX_SP_MAX_EITR;
 		break;
 	case wx_mac_aml:
+	case wx_mac_aml40:
 		itr_reg = (q_vector->itr >> 3) & WX_AML_MAX_EITR;
 		break;
 	default:
@@ -2354,10 +2357,10 @@ void wx_configure_vectors(struct wx *wx)
 
 	if (pdev->msix_enabled) {
 		/* Populate MSIX to EITR Select */
-		if (wx->mac.type == wx_mac_sp) {
+		if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 			if (wx->num_vfs >= 32)
 				eitrsel = BIT(wx->num_vfs % 32) - 1;
-		} else if (wx->mac.type == wx_mac_em) {
+		} else {
 			for (i = 0; i < wx->num_vfs; i++)
 				eitrsel |= BIT(i);
 		}
@@ -3000,6 +3003,33 @@ netdev_features_t wx_fix_features(struct net_device *netdev,
 }
 EXPORT_SYMBOL(wx_fix_features);
 
+#define WX_MAX_TUNNEL_HDR_LEN	80
+netdev_features_t wx_features_check(struct sk_buff *skb,
+				    struct net_device *netdev,
+				    netdev_features_t features)
+{
+	struct wx *wx = netdev_priv(netdev);
+
+	if (!skb->encapsulation)
+		return features;
+
+	if (wx->mac.type == wx_mac_em)
+		return features & ~NETIF_F_CSUM_MASK;
+
+	if (unlikely(skb_inner_mac_header(skb) - skb_transport_header(skb) >
+		     WX_MAX_TUNNEL_HDR_LEN))
+		return features & ~NETIF_F_CSUM_MASK;
+
+	if (skb->inner_protocol_type == ENCAP_TYPE_ETHER &&
+	    skb->inner_protocol != htons(ETH_P_IP) &&
+	    skb->inner_protocol != htons(ETH_P_IPV6) &&
+	    skb->inner_protocol != htons(ETH_P_TEB))
+		return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+
+	return features;
+}
+EXPORT_SYMBOL(wx_features_check);
+
 void wx_set_ring(struct wx *wx, u32 new_tx_count,
 		 u32 new_rx_count, struct wx_ring *temp_ring)
 {
@@ -3066,5 +3096,35 @@ void wx_set_ring(struct wx *wx, u32 new_tx_count,
 }
 EXPORT_SYMBOL(wx_set_ring);
 
+void wx_service_event_schedule(struct wx *wx)
+{
+	if (!test_and_set_bit(WX_STATE_SERVICE_SCHED, wx->state))
+		queue_work(system_power_efficient_wq, &wx->service_task);
+}
+EXPORT_SYMBOL(wx_service_event_schedule);
+
+void wx_service_event_complete(struct wx *wx)
+{
+	if (WARN_ON(!test_bit(WX_STATE_SERVICE_SCHED, wx->state)))
+		return;
+
+	/* flush memory to make sure state is correct before next watchdog */
+	smp_mb__before_atomic();
+	clear_bit(WX_STATE_SERVICE_SCHED, wx->state);
+}
+EXPORT_SYMBOL(wx_service_event_complete);
+
+void wx_service_timer(struct timer_list *t)
+{
+	struct wx *wx = from_timer(wx, t, service_timer);
+	unsigned long next_event_offset = HZ * 2;
+
+	/* Reset the timer */
+	mod_timer(&wx->service_timer, next_event_offset + jiffies);
+
+	wx_service_event_schedule(wx);
+}
+EXPORT_SYMBOL(wx_service_timer);
+
 MODULE_DESCRIPTION("Common library for Wangxun(R) Ethernet drivers.");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
index fdeb0c315b75..aed6ea8cf0d6 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h
@@ -33,7 +33,13 @@ void wx_get_stats64(struct net_device *netdev,
 int wx_set_features(struct net_device *netdev, netdev_features_t features);
 netdev_features_t wx_fix_features(struct net_device *netdev,
 				  netdev_features_t features);
+netdev_features_t wx_features_check(struct sk_buff *skb,
+				    struct net_device *netdev,
+				    netdev_features_t features);
 void wx_set_ring(struct wx *wx, u32 new_tx_count,
 		 u32 new_rx_count, struct wx_ring *temp_ring);
+void wx_service_event_schedule(struct wx *wx);
+void wx_service_event_complete(struct wx *wx);
+void wx_service_timer(struct timer_list *t);
 
-#endif /* _NGBE_LIB_H_ */
+#endif /* _WX_LIB_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ptp.c b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
index 07c015ba338f..2c39b879f977 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
@@ -15,12 +15,14 @@
 #define WX_INCVAL_100         0xA00000
 #define WX_INCVAL_10          0xC7F380
 #define WX_INCVAL_EM          0x2000000
+#define WX_INCVAL_AML         0xA00000
 
 #define WX_INCVAL_SHIFT_10GB  20
 #define WX_INCVAL_SHIFT_1GB   18
 #define WX_INCVAL_SHIFT_100   15
 #define WX_INCVAL_SHIFT_10    12
 #define WX_INCVAL_SHIFT_EM    22
+#define WX_INCVAL_SHIFT_AML   21
 
 #define WX_OVERFLOW_PERIOD    (HZ * 30)
 #define WX_PTP_TX_TIMEOUT     (HZ)
@@ -504,15 +506,27 @@ static long wx_ptp_create_clock(struct wx *wx)
 	wx->ptp_caps.gettimex64 = wx_ptp_gettimex64;
 	wx->ptp_caps.settime64 = wx_ptp_settime64;
 	wx->ptp_caps.do_aux_work = wx_ptp_do_aux_work;
-	if (wx->mac.type == wx_mac_em) {
-		wx->ptp_caps.max_adj = 500000000;
+	switch (wx->mac.type) {
+	case wx_mac_aml:
+	case wx_mac_aml40:
+		wx->ptp_caps.max_adj = 250000000;
 		wx->ptp_caps.n_per_out = 1;
 		wx->ptp_setup_sdp = wx_ptp_setup_sdp;
 		wx->ptp_caps.enable = wx_ptp_feature_enable;
-	} else {
+		break;
+	case wx_mac_sp:
 		wx->ptp_caps.max_adj = 250000000;
 		wx->ptp_caps.n_per_out = 0;
 		wx->ptp_setup_sdp = NULL;
+		break;
+	case wx_mac_em:
+		wx->ptp_caps.max_adj = 500000000;
+		wx->ptp_caps.n_per_out = 1;
+		wx->ptp_setup_sdp = wx_ptp_setup_sdp;
+		wx->ptp_caps.enable = wx_ptp_feature_enable;
+		break;
+	default:
+		return -EOPNOTSUPP;
 	}
 
 	wx->ptp_clock = ptp_clock_register(&wx->ptp_caps, &wx->pdev->dev);
@@ -647,10 +661,18 @@ static u64 wx_ptp_read(const struct cyclecounter *hw_cc)
 
 static void wx_ptp_link_speed_adjust(struct wx *wx, u32 *shift, u32 *incval)
 {
-	if (wx->mac.type == wx_mac_em) {
+	switch (wx->mac.type) {
+	case wx_mac_aml:
+	case wx_mac_aml40:
+		*shift = WX_INCVAL_SHIFT_AML;
+		*incval = WX_INCVAL_AML;
+		return;
+	case wx_mac_em:
 		*shift = WX_INCVAL_SHIFT_EM;
 		*incval = WX_INCVAL_EM;
 		return;
+	default:
+		break;
 	}
 
 	switch (wx->speed) {
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
index 52e6a6faf715..e8656d9d733b 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
@@ -76,7 +76,7 @@ static int __wx_enable_sriov(struct wx *wx, u8 num_vfs)
 	u32 value = 0;
 
 	set_bit(WX_FLAG_SRIOV_ENABLED, wx->flags);
-	wx_err(wx, "SR-IOV enabled with %d VFs\n", num_vfs);
+	dev_info(&wx->pdev->dev, "SR-IOV enabled with %d VFs\n", num_vfs);
 
 	/* Enable VMDq flag so device will be set in VM mode */
 	set_bit(WX_FLAG_VMDQ_ENABLED, wx->flags);
@@ -106,7 +106,7 @@ static int __wx_enable_sriov(struct wx *wx, u8 num_vfs)
 		wx->vfinfo[i].xcast_mode = WXVF_XCAST_MODE_NONE;
 	}
 
-	if (wx->mac.type == wx_mac_em) {
+	if (!test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		value = WX_CFG_PORT_CTL_NUM_VT_8;
 	} else {
 		if (num_vfs < 32)
@@ -599,10 +599,10 @@ static int wx_set_vf_vlan_msg(struct wx *wx, u32 *msgbuf, u16 vf)
 		if (VMDQ_P(0) < 32) {
 			bits = rd32(wx, WX_PSR_VLAN_SWC_VM_L);
 			bits &= ~BIT(VMDQ_P(0));
-			if (wx->mac.type != wx_mac_em)
+			if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags))
 				bits |= rd32(wx, WX_PSR_VLAN_SWC_VM_H);
 		} else {
-			if (wx->mac.type != wx_mac_em)
+			if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags))
 				bits = rd32(wx, WX_PSR_VLAN_SWC_VM_H);
 			bits &= ~BIT(VMDQ_P(0) % 32);
 			bits |= rd32(wx, WX_PSR_VLAN_SWC_VM_L);
@@ -848,7 +848,7 @@ void wx_disable_vf_rx_tx(struct wx *wx)
 {
 	wr32(wx, WX_TDM_VFTE_CLR(0), U32_MAX);
 	wr32(wx, WX_RDM_VFRE_CLR(0), U32_MAX);
-	if (wx->mac.type != wx_mac_em) {
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		wr32(wx, WX_TDM_VFTE_CLR(1), U32_MAX);
 		wr32(wx, WX_RDM_VFRE_CLR(1), U32_MAX);
 	}
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 8cfed5d4ebf7..7730c9fc3e02 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -838,13 +838,14 @@ enum wx_mac_type {
 	wx_mac_sp,
 	wx_mac_em,
 	wx_mac_aml,
+	wx_mac_aml40,
 };
 
-enum sp_media_type {
-	sp_media_unknown = 0,
-	sp_media_fiber,
-	sp_media_copper,
-	sp_media_backplane
+enum wx_media_type {
+	wx_media_unknown = 0,
+	wx_media_fiber,
+	wx_media_copper,
+	wx_media_backplane
 };
 
 enum em_mac_type {
@@ -1153,6 +1154,7 @@ enum wx_state {
 	WX_STATE_SWFW_BUSY,
 	WX_STATE_PTP_RUNNING,
 	WX_STATE_PTP_TX_IN_PROGRESS,
+	WX_STATE_SERVICE_SCHED,
 	WX_STATE_NBITS		/* must be last */
 };
 
@@ -1184,6 +1186,7 @@ struct vf_macvlans {
 };
 
 enum wx_pf_flags {
+	WX_FLAG_MULTI_64_FUNC,
 	WX_FLAG_SWFW_RING,
 	WX_FLAG_VMDQ_ENABLED,
 	WX_FLAG_VLAN_PROMISC,
@@ -1195,6 +1198,8 @@ enum wx_pf_flags {
 	WX_FLAG_RX_HWTSTAMP_ENABLED,
 	WX_FLAG_RX_HWTSTAMP_IN_REGISTER,
 	WX_FLAG_PTP_PPS_ENABLED,
+	WX_FLAG_NEED_LINK_CONFIG,
+	WX_FLAG_NEED_SFP_RESET,
 	WX_PF_FLAGS_NBITS               /* must be last */
 };
 
@@ -1211,7 +1216,7 @@ struct wx {
 	struct wx_mbx_info mbx;
 	struct wx_mac_info mac;
 	enum em_mac_type mac_type;
-	enum sp_media_type media_type;
+	enum wx_media_type media_type;
 	struct wx_eeprom_info eeprom;
 	struct wx_addr_filter_info addr_ctrl;
 	struct wx_fc_info fc;
@@ -1233,6 +1238,8 @@ struct wx {
 
 	/* PHY stuff */
 	bool notify_down;
+	int adv_speed;
+	int adv_duplex;
 	unsigned int link;
 	int speed;
 	int duplex;
@@ -1330,6 +1337,9 @@ struct wx {
 	struct ptp_clock_info ptp_caps;
 	struct kernel_hwtstamp_config tstamp_config;
 	struct sk_buff *ptp_tx_skb;
+
+	struct timer_list service_timer;
+	struct work_struct service_task;
 };
 
 #define WX_INTR_ALL (~0ULL)
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index fd102078f5c9..b5022c49dc5e 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -587,6 +587,7 @@ static const struct net_device_ops ngbe_netdev_ops = {
 	.ndo_set_rx_mode        = wx_set_rx_mode,
 	.ndo_set_features       = wx_set_features,
 	.ndo_fix_features       = wx_fix_features,
+	.ndo_features_check     = wx_features_check,
 	.ndo_validate_addr      = eth_validate_addr,
 	.ndo_set_mac_address    = wx_set_mac,
 	.ndo_get_stats64        = wx_get_stats64,
@@ -698,7 +699,7 @@ static int ngbe_probe(struct pci_dev *pdev,
 	/* setup the private structure */
 	err = ngbe_sw_init(wx);
 	if (err)
-		goto err_free_mac_table;
+		goto err_pci_release_regions;
 
 	/* check if flash load is done after hw power up */
 	err = wx_check_flash_load(wx, NGBE_SPI_ILDR_STATUS_PERST);
@@ -792,6 +793,7 @@ err_register:
 err_clear_interrupt_scheme:
 	wx_clear_interrupt_scheme(wx);
 err_free_mac_table:
+	kfree(wx->rss_key);
 	kfree(wx->mac_table);
 err_pci_release_regions:
 	pci_release_selected_regions(pdev,
diff --git a/drivers/net/ethernet/wangxun/txgbe/Makefile b/drivers/net/ethernet/wangxun/txgbe/Makefile
index f74576fe7062..c757fa95e58e 100644
--- a/drivers/net/ethernet/wangxun/txgbe/Makefile
+++ b/drivers/net/ethernet/wangxun/txgbe/Makefile
@@ -11,4 +11,5 @@ txgbe-objs := txgbe_main.o \
               txgbe_phy.o \
               txgbe_irq.o \
               txgbe_fdir.o \
-              txgbe_ethtool.o
+              txgbe_ethtool.o \
+              txgbe_aml.o
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c
new file mode 100644
index 000000000000..7dbcf41750c1
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c
@@ -0,0 +1,385 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#include <linux/phylink.h>
+#include <linux/iopoll.h>
+#include <linux/pci.h>
+#include <linux/phy.h>
+
+#include "../libwx/wx_type.h"
+#include "../libwx/wx_lib.h"
+#include "../libwx/wx_ptp.h"
+#include "../libwx/wx_hw.h"
+#include "../libwx/wx_sriov.h"
+#include "txgbe_type.h"
+#include "txgbe_aml.h"
+#include "txgbe_hw.h"
+
+void txgbe_gpio_init_aml(struct wx *wx)
+{
+	u32 status;
+
+	wr32(wx, WX_GPIO_INTTYPE_LEVEL, TXGBE_GPIOBIT_2 | TXGBE_GPIOBIT_3);
+	wr32(wx, WX_GPIO_INTEN, TXGBE_GPIOBIT_2 | TXGBE_GPIOBIT_3);
+
+	status = rd32(wx, WX_GPIO_INTSTATUS);
+	for (int i = 0; i < 6; i++) {
+		if (status & BIT(i))
+			wr32(wx, WX_GPIO_EOI, BIT(i));
+	}
+}
+
+irqreturn_t txgbe_gpio_irq_handler_aml(int irq, void *data)
+{
+	struct txgbe *txgbe = data;
+	struct wx *wx = txgbe->wx;
+	u32 status;
+
+	wr32(wx, WX_GPIO_INTMASK, 0xFF);
+	status = rd32(wx, WX_GPIO_INTSTATUS);
+	if (status & TXGBE_GPIOBIT_2) {
+		set_bit(WX_FLAG_NEED_SFP_RESET, wx->flags);
+		wr32(wx, WX_GPIO_EOI, TXGBE_GPIOBIT_2);
+		wx_service_event_schedule(wx);
+	}
+	if (status & TXGBE_GPIOBIT_3) {
+		set_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags);
+		wx_service_event_schedule(wx);
+		wr32(wx, WX_GPIO_EOI, TXGBE_GPIOBIT_3);
+	}
+
+	wr32(wx, WX_GPIO_INTMASK, 0);
+	return IRQ_HANDLED;
+}
+
+int txgbe_test_hostif(struct wx *wx)
+{
+	struct txgbe_hic_ephy_getlink buffer;
+
+	if (wx->mac.type != wx_mac_aml)
+		return 0;
+
+	buffer.hdr.cmd = FW_PHY_GET_LINK_CMD;
+	buffer.hdr.buf_len = sizeof(struct txgbe_hic_ephy_getlink) -
+			     sizeof(struct wx_hic_hdr);
+	buffer.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED;
+
+	return wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer),
+					WX_HI_COMMAND_TIMEOUT, true);
+}
+
+static int txgbe_identify_sfp_hostif(struct wx *wx, struct txgbe_hic_i2c_read *buffer)
+{
+	buffer->hdr.cmd = FW_READ_SFP_INFO_CMD;
+	buffer->hdr.buf_len = sizeof(struct txgbe_hic_i2c_read) -
+			      sizeof(struct wx_hic_hdr);
+	buffer->hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED;
+
+	return wx_host_interface_command(wx, (u32 *)buffer,
+					 sizeof(struct txgbe_hic_i2c_read),
+					 WX_HI_COMMAND_TIMEOUT, true);
+}
+
+static int txgbe_set_phy_link_hostif(struct wx *wx, int speed, int autoneg, int duplex)
+{
+	struct txgbe_hic_ephy_setlink buffer;
+
+	buffer.hdr.cmd = FW_PHY_SET_LINK_CMD;
+	buffer.hdr.buf_len = sizeof(struct txgbe_hic_ephy_setlink) -
+			     sizeof(struct wx_hic_hdr);
+	buffer.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED;
+
+	switch (speed) {
+	case SPEED_25000:
+		buffer.speed = TXGBE_LINK_SPEED_25GB_FULL;
+		break;
+	case SPEED_10000:
+		buffer.speed = TXGBE_LINK_SPEED_10GB_FULL;
+		break;
+	}
+
+	buffer.fec_mode = TXGBE_PHY_FEC_AUTO;
+	buffer.autoneg = autoneg;
+	buffer.duplex = duplex;
+
+	return wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer),
+					 WX_HI_COMMAND_TIMEOUT, true);
+}
+
+static void txgbe_get_link_capabilities(struct wx *wx)
+{
+	struct txgbe *txgbe = wx->priv;
+
+	if (test_bit(PHY_INTERFACE_MODE_25GBASER, txgbe->sfp_interfaces))
+		wx->adv_speed = SPEED_25000;
+	else if (test_bit(PHY_INTERFACE_MODE_10GBASER, txgbe->sfp_interfaces))
+		wx->adv_speed = SPEED_10000;
+	else
+		wx->adv_speed = SPEED_UNKNOWN;
+
+	wx->adv_duplex = wx->adv_speed == SPEED_UNKNOWN ?
+			 DUPLEX_HALF : DUPLEX_FULL;
+}
+
+static void txgbe_get_phy_link(struct wx *wx, int *speed)
+{
+	u32 status;
+
+	status = rd32(wx, TXGBE_CFG_PORT_ST);
+	if (!(status & TXGBE_CFG_PORT_ST_LINK_UP))
+		*speed = SPEED_UNKNOWN;
+	else if (status & TXGBE_CFG_PORT_ST_LINK_AML_25G)
+		*speed = SPEED_25000;
+	else if (status & TXGBE_CFG_PORT_ST_LINK_AML_10G)
+		*speed = SPEED_10000;
+	else
+		*speed = SPEED_UNKNOWN;
+}
+
+int txgbe_set_phy_link(struct wx *wx)
+{
+	int speed, err;
+	u32 gpio;
+
+	/* Check RX signal */
+	gpio = rd32(wx, WX_GPIO_EXT);
+	if (gpio & TXGBE_GPIOBIT_3)
+		return -ENODEV;
+
+	txgbe_get_link_capabilities(wx);
+	if (wx->adv_speed == SPEED_UNKNOWN)
+		return -ENODEV;
+
+	txgbe_get_phy_link(wx, &speed);
+	if (speed == wx->adv_speed)
+		return 0;
+
+	err = txgbe_set_phy_link_hostif(wx, wx->adv_speed, 0, wx->adv_duplex);
+	if (err) {
+		wx_err(wx, "Failed to setup link\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int txgbe_sfp_to_linkmodes(struct wx *wx, struct txgbe_sfp_id *id)
+{
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = { 0, };
+	DECLARE_PHY_INTERFACE_MASK(interfaces);
+	struct txgbe *txgbe = wx->priv;
+
+	if (id->com_25g_code & (TXGBE_SFF_25GBASESR_CAPABLE |
+				TXGBE_SFF_25GBASEER_CAPABLE |
+				TXGBE_SFF_25GBASELR_CAPABLE)) {
+		phylink_set(modes, 25000baseSR_Full);
+		__set_bit(PHY_INTERFACE_MODE_25GBASER, interfaces);
+	}
+	if (id->com_10g_code & TXGBE_SFF_10GBASESR_CAPABLE) {
+		phylink_set(modes, 10000baseSR_Full);
+		__set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces);
+	}
+	if (id->com_10g_code & TXGBE_SFF_10GBASELR_CAPABLE) {
+		phylink_set(modes, 10000baseLR_Full);
+		__set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces);
+	}
+
+	if (phy_interface_empty(interfaces)) {
+		wx_err(wx, "unsupported SFP module\n");
+		return -EINVAL;
+	}
+
+	phylink_set(modes, Pause);
+	phylink_set(modes, Asym_Pause);
+	phylink_set(modes, FIBRE);
+	txgbe->link_port = PORT_FIBRE;
+
+	if (!linkmode_equal(txgbe->sfp_support, modes)) {
+		linkmode_copy(txgbe->sfp_support, modes);
+		phy_interface_and(txgbe->sfp_interfaces,
+				  wx->phylink_config.supported_interfaces,
+				  interfaces);
+		linkmode_copy(txgbe->advertising, modes);
+
+		set_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags);
+	}
+
+	return 0;
+}
+
+int txgbe_identify_sfp(struct wx *wx)
+{
+	struct txgbe_hic_i2c_read buffer;
+	struct txgbe_sfp_id *id;
+	int err = 0;
+	u32 gpio;
+
+	gpio = rd32(wx, WX_GPIO_EXT);
+	if (gpio & TXGBE_GPIOBIT_2)
+		return -ENODEV;
+
+	err = txgbe_identify_sfp_hostif(wx, &buffer);
+	if (err) {
+		wx_err(wx, "Failed to identify SFP module\n");
+		return err;
+	}
+
+	id = &buffer.id;
+	if (id->identifier != TXGBE_SFF_IDENTIFIER_SFP) {
+		wx_err(wx, "Invalid SFP module\n");
+		return -ENODEV;
+	}
+
+	err = txgbe_sfp_to_linkmodes(wx, id);
+	if (err)
+		return err;
+
+	if (gpio & TXGBE_GPIOBIT_3)
+		set_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags);
+
+	return 0;
+}
+
+void txgbe_setup_link(struct wx *wx)
+{
+	struct txgbe *txgbe = wx->priv;
+
+	phy_interface_zero(txgbe->sfp_interfaces);
+	linkmode_zero(txgbe->sfp_support);
+
+	txgbe_identify_sfp(wx);
+}
+
+static void txgbe_get_link_state(struct phylink_config *config,
+				 struct phylink_link_state *state)
+{
+	struct wx *wx = phylink_to_wx(config);
+	int speed;
+
+	txgbe_get_phy_link(wx, &speed);
+	state->link = speed != SPEED_UNKNOWN;
+	state->speed = speed;
+	state->duplex = state->link ? DUPLEX_FULL : DUPLEX_UNKNOWN;
+}
+
+static void txgbe_reconfig_mac(struct wx *wx)
+{
+	u32 wdg, fc;
+
+	wdg = rd32(wx, WX_MAC_WDG_TIMEOUT);
+	fc = rd32(wx, WX_MAC_RX_FLOW_CTRL);
+
+	wr32(wx, WX_MIS_RST, TXGBE_MIS_RST_MAC_RST(wx->bus.func));
+	/* wait for MAC reset complete */
+	usleep_range(1000, 1500);
+
+	wr32m(wx, TXGBE_MAC_MISC_CTL, TXGBE_MAC_MISC_CTL_LINK_STS_MOD,
+	      TXGBE_MAC_MISC_CTL_LINK_BOTH);
+	wx_reset_mac(wx);
+
+	wr32(wx, WX_MAC_WDG_TIMEOUT, wdg);
+	wr32(wx, WX_MAC_RX_FLOW_CTRL, fc);
+}
+
+static void txgbe_mac_link_up_aml(struct phylink_config *config,
+				  struct phy_device *phy,
+				  unsigned int mode,
+				  phy_interface_t interface,
+				  int speed, int duplex,
+				  bool tx_pause, bool rx_pause)
+{
+	struct wx *wx = phylink_to_wx(config);
+	u32 txcfg;
+
+	wx_fc_enable(wx, tx_pause, rx_pause);
+
+	txgbe_reconfig_mac(wx);
+
+	txcfg = rd32(wx, TXGBE_AML_MAC_TX_CFG);
+	txcfg &= ~TXGBE_AML_MAC_TX_CFG_SPEED_MASK;
+
+	switch (speed) {
+	case SPEED_25000:
+		txcfg |= TXGBE_AML_MAC_TX_CFG_SPEED_25G;
+		break;
+	case SPEED_10000:
+		txcfg |= TXGBE_AML_MAC_TX_CFG_SPEED_10G;
+		break;
+	default:
+		break;
+	}
+
+	wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_RE, WX_MAC_RX_CFG_RE);
+	wr32(wx, TXGBE_AML_MAC_TX_CFG, txcfg | TXGBE_AML_MAC_TX_CFG_TE);
+
+	wx->speed = speed;
+	wx->last_rx_ptp_check = jiffies;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going up */
+	wx_ping_all_vfs_with_link_status(wx, true);
+}
+
+static void txgbe_mac_link_down_aml(struct phylink_config *config,
+				    unsigned int mode,
+				    phy_interface_t interface)
+{
+	struct wx *wx = phylink_to_wx(config);
+
+	wr32m(wx, TXGBE_AML_MAC_TX_CFG, TXGBE_AML_MAC_TX_CFG_TE, 0);
+	wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_RE, 0);
+
+	wx->speed = SPEED_UNKNOWN;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going down */
+	wx_ping_all_vfs_with_link_status(wx, false);
+}
+
+static void txgbe_mac_config_aml(struct phylink_config *config, unsigned int mode,
+				 const struct phylink_link_state *state)
+{
+}
+
+static const struct phylink_mac_ops txgbe_mac_ops_aml = {
+	.mac_config = txgbe_mac_config_aml,
+	.mac_link_down = txgbe_mac_link_down_aml,
+	.mac_link_up = txgbe_mac_link_up_aml,
+};
+
+int txgbe_phylink_init_aml(struct txgbe *txgbe)
+{
+	struct phylink_link_state state;
+	struct phylink_config *config;
+	struct wx *wx = txgbe->wx;
+	phy_interface_t phy_mode;
+	struct phylink *phylink;
+	int err;
+
+	config = &wx->phylink_config;
+	config->dev = &wx->netdev->dev;
+	config->type = PHYLINK_NETDEV;
+	config->mac_capabilities = MAC_25000FD | MAC_10000FD |
+				   MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
+	config->get_fixed_state = txgbe_get_link_state;
+
+	phy_mode = PHY_INTERFACE_MODE_25GBASER;
+	__set_bit(PHY_INTERFACE_MODE_25GBASER, config->supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_10GBASER, config->supported_interfaces);
+
+	phylink = phylink_create(config, NULL, phy_mode, &txgbe_mac_ops_aml);
+	if (IS_ERR(phylink))
+		return PTR_ERR(phylink);
+
+	state.speed = SPEED_25000;
+	state.duplex = DUPLEX_FULL;
+	err = phylink_set_fixed_link(phylink, &state);
+	if (err) {
+		wx_err(wx, "Failed to set fixed link\n");
+		return err;
+	}
+
+	wx->phylink = phylink;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.h
new file mode 100644
index 000000000000..25d4971ca0d9
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#ifndef _TXGBE_AML_H_
+#define _TXGBE_AML_H_
+
+void txgbe_gpio_init_aml(struct wx *wx);
+irqreturn_t txgbe_gpio_irq_handler_aml(int irq, void *data);
+int txgbe_test_hostif(struct wx *wx);
+int txgbe_set_phy_link(struct wx *wx);
+int txgbe_identify_sfp(struct wx *wx);
+void txgbe_setup_link(struct wx *wx);
+int txgbe_phylink_init_aml(struct txgbe *txgbe);
+
+#endif /* _TXGBE_AML_H_ */
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
index 78999d484f18..fa770961df5f 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
@@ -12,6 +12,31 @@
 #include "txgbe_fdir.h"
 #include "txgbe_ethtool.h"
 
+int txgbe_get_link_ksettings(struct net_device *netdev,
+			     struct ethtool_link_ksettings *cmd)
+{
+	struct wx *wx = netdev_priv(netdev);
+	struct txgbe *txgbe = wx->priv;
+	int err;
+
+	if (wx->mac.type == wx_mac_aml40)
+		return -EOPNOTSUPP;
+
+	err = wx_get_link_ksettings(netdev, cmd);
+	if (err)
+		return err;
+
+	if (wx->mac.type == wx_mac_sp)
+		return 0;
+
+	cmd->base.port = txgbe->link_port;
+	cmd->base.autoneg = AUTONEG_DISABLE;
+	linkmode_copy(cmd->link_modes.supported, txgbe->sfp_support);
+	linkmode_copy(cmd->link_modes.advertising, txgbe->advertising);
+
+	return 0;
+}
+
 static int txgbe_set_ringparam(struct net_device *netdev,
 			       struct ethtool_ringparam *ring,
 			       struct kernel_ethtool_ringparam *kernel_ring,
@@ -510,7 +535,7 @@ static const struct ethtool_ops txgbe_ethtool_ops = {
 	.get_drvinfo		= wx_get_drvinfo,
 	.nway_reset		= wx_nway_reset,
 	.get_link		= ethtool_op_get_link,
-	.get_link_ksettings	= wx_get_link_ksettings,
+	.get_link_ksettings	= txgbe_get_link_ksettings,
 	.set_link_ksettings	= wx_set_link_ksettings,
 	.get_sset_count		= wx_get_sset_count,
 	.get_strings		= wx_get_strings,
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.h
index ace1b3571012..66dbc8ec1bb6 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.h
@@ -4,6 +4,8 @@
 #ifndef _TXGBE_ETHTOOL_H_
 #define _TXGBE_ETHTOOL_H_
 
+int txgbe_get_link_ksettings(struct net_device *netdev,
+			     struct ethtool_link_ksettings *cmd);
 void txgbe_set_ethtool_ops(struct net_device *netdev);
 
 #endif /* _TXGBE_ETHTOOL_H_ */
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
index 4b9921b7bb11..e551ae0e2069 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
@@ -99,9 +99,15 @@ static int txgbe_calc_eeprom_checksum(struct wx *wx, u16 *checksum)
 	}
 	local_buffer = eeprom_ptrs;
 
-	for (i = 0; i < TXGBE_EEPROM_LAST_WORD; i++)
+	for (i = 0; i < TXGBE_EEPROM_LAST_WORD; i++) {
+		if (wx->mac.type == wx_mac_aml) {
+			if (i >= TXGBE_EEPROM_I2C_SRART_PTR &&
+			    i < TXGBE_EEPROM_I2C_END_PTR)
+				local_buffer[i] = 0xffff;
+		}
 		if (i != wx->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM)
 			*checksum += local_buffer[i];
+	}
 
 	kvfree(eeprom_ptrs);
 
@@ -182,7 +188,7 @@ int txgbe_reset_hw(struct wx *wx)
 	if (status != 0)
 		return status;
 
-	if (wx->media_type != sp_media_copper) {
+	if (wx->media_type != wx_media_copper) {
 		u32 val;
 
 		val = WX_MIS_RST_LAN_RST(wx->bus.func);
@@ -212,7 +218,7 @@ int txgbe_reset_hw(struct wx *wx)
 	 * clear the multicast table.  Also reset num_rar_entries to 128,
 	 * since we modify this value when programming the SAN MAC address.
 	 */
-	wx->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES;
+	wx->mac.num_rar_entries = TXGBE_RAR_ENTRIES;
 	wx_init_rx_addrs(wx);
 
 	pci_set_master(wx->pdev);
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
index 3b9e831cf0ef..dfc3a2cc27f6 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
@@ -6,11 +6,13 @@
 
 #include "../libwx/wx_type.h"
 #include "../libwx/wx_lib.h"
+#include "../libwx/wx_ptp.h"
 #include "../libwx/wx_hw.h"
 #include "../libwx/wx_sriov.h"
 #include "txgbe_type.h"
 #include "txgbe_phy.h"
 #include "txgbe_irq.h"
+#include "txgbe_aml.h"
 
 /**
  * txgbe_irq_enable - Enable default interrupt generation settings
@@ -19,7 +21,14 @@
  **/
 void txgbe_irq_enable(struct wx *wx, bool queues)
 {
-	wr32(wx, WX_PX_MISC_IEN, TXGBE_PX_MISC_IEN_MASK);
+	u32 misc_ien = TXGBE_PX_MISC_IEN_MASK;
+
+	if (wx->mac.type == wx_mac_aml) {
+		misc_ien |= TXGBE_PX_MISC_GPIO;
+		txgbe_gpio_init_aml(wx);
+	}
+
+	wr32(wx, WX_PX_MISC_IEN, misc_ien);
 
 	/* unmask interrupt */
 	wx_intr_enable(wx, TXGBE_INTR_MISC);
@@ -81,6 +90,14 @@ static int txgbe_request_link_irq(struct txgbe *txgbe)
 				    IRQF_ONESHOT, "txgbe-link-irq", txgbe);
 }
 
+static int txgbe_request_gpio_irq(struct txgbe *txgbe)
+{
+	txgbe->gpio_irq = irq_find_mapping(txgbe->misc.domain, TXGBE_IRQ_GPIO);
+	return request_threaded_irq(txgbe->gpio_irq, NULL,
+				    txgbe_gpio_irq_handler_aml,
+				    IRQF_ONESHOT, "txgbe-gpio-irq", txgbe);
+}
+
 static const struct irq_chip txgbe_irq_chip = {
 	.name = "txgbe-misc-irq",
 };
@@ -112,8 +129,6 @@ static irqreturn_t txgbe_misc_irq_handle(int irq, void *data)
 
 	if (wx->pdev->msix_enabled) {
 		eicr = wx_misc_isb(wx, WX_ISB_MISC);
-		if (!eicr)
-			return IRQ_NONE;
 		txgbe->eicr = eicr;
 		if (eicr & TXGBE_PX_MISC_IC_VF_MBOX) {
 			wx_msg_task(txgbe->wx);
@@ -139,10 +154,7 @@ static irqreturn_t txgbe_misc_irq_handle(int irq, void *data)
 	q_vector = wx->q_vector[0];
 	napi_schedule_irqoff(&q_vector->napi);
 
-	eicr = wx_misc_isb(wx, WX_ISB_MISC);
-	if (!eicr)
-		return IRQ_NONE;
-	txgbe->eicr = eicr;
+	txgbe->eicr = wx_misc_isb(wx, WX_ISB_MISC);
 
 	return IRQ_WAKE_THREAD;
 }
@@ -162,6 +174,15 @@ static irqreturn_t txgbe_misc_irq_thread_fn(int irq, void *data)
 		handle_nested_irq(sub_irq);
 		nhandled++;
 	}
+	if (eicr & TXGBE_PX_MISC_GPIO) {
+		sub_irq = irq_find_mapping(txgbe->misc.domain, TXGBE_IRQ_GPIO);
+		handle_nested_irq(sub_irq);
+		nhandled++;
+	}
+	if (unlikely(eicr & TXGBE_PX_MISC_IC_TIMESYNC)) {
+		wx_ptp_check_pps_event(wx);
+		nhandled++;
+	}
 
 	wx_intr_enable(wx, TXGBE_INTR_MISC);
 	return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE);
@@ -181,9 +202,12 @@ static void txgbe_del_irq_domain(struct txgbe *txgbe)
 
 void txgbe_free_misc_irq(struct txgbe *txgbe)
 {
-	if (txgbe->wx->mac.type == wx_mac_aml)
+	if (txgbe->wx->mac.type == wx_mac_aml40)
 		return;
 
+	if (txgbe->wx->mac.type == wx_mac_aml)
+		free_irq(txgbe->gpio_irq, txgbe);
+
 	free_irq(txgbe->link_irq, txgbe);
 	free_irq(txgbe->misc.irq, txgbe);
 	txgbe_del_irq_domain(txgbe);
@@ -195,7 +219,7 @@ int txgbe_setup_misc_irq(struct txgbe *txgbe)
 	struct wx *wx = txgbe->wx;
 	int hwirq, err;
 
-	if (wx->mac.type == wx_mac_aml)
+	if (wx->mac.type == wx_mac_aml40)
 		goto skip_sp_irq;
 
 	txgbe->misc.nirqs = TXGBE_IRQ_MAX;
@@ -227,11 +251,20 @@ int txgbe_setup_misc_irq(struct txgbe *txgbe)
 	if (err)
 		goto free_msic_irq;
 
+	if (wx->mac.type == wx_mac_sp)
+		goto skip_sp_irq;
+
+	err = txgbe_request_gpio_irq(txgbe);
+	if (err)
+		goto free_link_irq;
+
 skip_sp_irq:
 	wx->misc_irq_domain = true;
 
 	return 0;
 
+free_link_irq:
+	free_irq(txgbe->link_irq, txgbe);
 free_msic_irq:
 	free_irq(txgbe->misc.irq, txgbe);
 del_misc_irq:
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index 6d9134a3ce4d..f3d2778b8e35 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -8,6 +8,7 @@
 #include <linux/string.h>
 #include <linux/etherdevice.h>
 #include <linux/phylink.h>
+#include <net/udp_tunnel.h>
 #include <net/ip.h>
 #include <linux/if_vlan.h>
 
@@ -20,6 +21,7 @@
 #include "txgbe_type.h"
 #include "txgbe_hw.h"
 #include "txgbe_phy.h"
+#include "txgbe_aml.h"
 #include "txgbe_irq.h"
 #include "txgbe_fdir.h"
 #include "txgbe_ethtool.h"
@@ -87,9 +89,62 @@ static int txgbe_enumerate_functions(struct wx *wx)
 	return physfns;
 }
 
+static void txgbe_sfp_detection_subtask(struct wx *wx)
+{
+	int err;
+
+	if (!test_bit(WX_FLAG_NEED_SFP_RESET, wx->flags))
+		return;
+
+	/* wait for SFP module ready */
+	msleep(200);
+
+	err = txgbe_identify_sfp(wx);
+	if (err)
+		return;
+
+	clear_bit(WX_FLAG_NEED_SFP_RESET, wx->flags);
+}
+
+static void txgbe_link_config_subtask(struct wx *wx)
+{
+	int err;
+
+	if (!test_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags))
+		return;
+
+	err = txgbe_set_phy_link(wx);
+	if (err)
+		return;
+
+	clear_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags);
+}
+
+/**
+ * txgbe_service_task - manages and runs subtasks
+ * @work: pointer to work_struct containing our data
+ **/
+static void txgbe_service_task(struct work_struct *work)
+{
+	struct wx *wx = container_of(work, struct wx, service_task);
+
+	txgbe_sfp_detection_subtask(wx);
+	txgbe_link_config_subtask(wx);
+
+	wx_service_event_complete(wx);
+}
+
+static void txgbe_init_service(struct wx *wx)
+{
+	timer_setup(&wx->service_timer, wx_service_timer, 0);
+	INIT_WORK(&wx->service_task, txgbe_service_task);
+	clear_bit(WX_STATE_SERVICE_SCHED, wx->state);
+}
+
 static void txgbe_up_complete(struct wx *wx)
 {
 	struct net_device *netdev = wx->netdev;
+	u32 reg;
 
 	wx_control_hw(wx, true);
 	wx_configure_vectors(wx);
@@ -98,17 +153,26 @@ static void txgbe_up_complete(struct wx *wx)
 	smp_mb__before_atomic();
 	wx_napi_enable_all(wx);
 
-	if (wx->mac.type == wx_mac_aml) {
-		u32 reg;
-
+	switch (wx->mac.type) {
+	case wx_mac_aml40:
 		reg = rd32(wx, TXGBE_AML_MAC_TX_CFG);
 		reg &= ~TXGBE_AML_MAC_TX_CFG_SPEED_MASK;
-		reg |= TXGBE_AML_MAC_TX_CFG_SPEED_25G;
+		reg |= TXGBE_AML_MAC_TX_CFG_SPEED_40G;
 		wr32(wx, WX_MAC_TX_CFG, reg);
 		txgbe_enable_sec_tx_path(wx);
 		netif_carrier_on(wx->netdev);
-	} else {
+		break;
+	case wx_mac_aml:
+		/* Enable TX laser */
+		wr32m(wx, WX_GPIO_DR, TXGBE_GPIOBIT_1, 0);
+		txgbe_setup_link(wx);
+		phylink_start(wx->phylink);
+		break;
+	case wx_mac_sp:
 		phylink_start(wx->phylink);
+		break;
+	default:
+		break;
 	}
 
 	/* clear any pending interrupts, may auto mask */
@@ -119,6 +183,7 @@ static void txgbe_up_complete(struct wx *wx)
 
 	/* enable transmits */
 	netif_tx_start_all_queues(netdev);
+	mod_timer(&wx->service_timer, jiffies);
 
 	/* Set PF Reset Done bit so PF/VF Mail Ops can work */
 	wr32m(wx, WX_CFG_PORT_CTL, WX_CFG_PORT_CTL_PFRSTD,
@@ -167,6 +232,8 @@ static void txgbe_disable_device(struct wx *wx)
 	wx_irq_disable(wx);
 	wx_napi_disable_all(wx);
 
+	timer_delete_sync(&wx->service_timer);
+
 	if (wx->bus.func < 2)
 		wr32m(wx, TXGBE_MIS_PRB_CTL, TXGBE_MIS_PRB_CTL_LAN_UP(wx->bus.func), 0);
 	else
@@ -206,10 +273,22 @@ void txgbe_down(struct wx *wx)
 {
 	txgbe_disable_device(wx);
 	txgbe_reset(wx);
-	if (wx->mac.type == wx_mac_aml)
+
+	switch (wx->mac.type) {
+	case wx_mac_aml40:
 		netif_carrier_off(wx->netdev);
-	else
+		break;
+	case wx_mac_aml:
 		phylink_stop(wx->phylink);
+		/* Disable TX laser */
+		wr32m(wx, WX_GPIO_DR, TXGBE_GPIOBIT_1, TXGBE_GPIOBIT_1);
+		break;
+	case wx_mac_sp:
+		phylink_stop(wx->phylink);
+		break;
+	default:
+		break;
+	}
 
 	wx_clean_all_tx_rings(wx);
 	wx_clean_all_rx_rings(wx);
@@ -239,9 +318,11 @@ static void txgbe_init_type_code(struct wx *wx)
 	case TXGBE_DEV_ID_AML5110:
 	case TXGBE_DEV_ID_AML5025:
 	case TXGBE_DEV_ID_AML5125:
+		wx->mac.type = wx_mac_aml;
+		break;
 	case TXGBE_DEV_ID_AML5040:
 	case TXGBE_DEV_ID_AML5140:
-		wx->mac.type = wx_mac_aml;
+		wx->mac.type = wx_mac_aml40;
 		break;
 	default:
 		wx->mac.type = wx_mac_unknown;
@@ -250,25 +331,25 @@ static void txgbe_init_type_code(struct wx *wx)
 
 	switch (device_type) {
 	case TXGBE_ID_SFP:
-		wx->media_type = sp_media_fiber;
+		wx->media_type = wx_media_fiber;
 		break;
 	case TXGBE_ID_XAUI:
 	case TXGBE_ID_SGMII:
-		wx->media_type = sp_media_copper;
+		wx->media_type = wx_media_copper;
 		break;
 	case TXGBE_ID_KR_KX_KX4:
 	case TXGBE_ID_MAC_XAUI:
 	case TXGBE_ID_MAC_SGMII:
-		wx->media_type = sp_media_backplane;
+		wx->media_type = wx_media_backplane;
 		break;
 	case TXGBE_ID_SFI_XAUI:
 		if (wx->bus.func == 0)
-			wx->media_type = sp_media_fiber;
+			wx->media_type = wx_media_fiber;
 		else
-			wx->media_type = sp_media_copper;
+			wx->media_type = wx_media_copper;
 		break;
 	default:
-		wx->media_type = sp_media_unknown;
+		wx->media_type = wx_media_unknown;
 		break;
 	}
 }
@@ -282,13 +363,13 @@ static int txgbe_sw_init(struct wx *wx)
 	u16 msix_count = 0;
 	int err;
 
-	wx->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES;
-	wx->mac.max_tx_queues = TXGBE_SP_MAX_TX_QUEUES;
-	wx->mac.max_rx_queues = TXGBE_SP_MAX_RX_QUEUES;
-	wx->mac.mcft_size = TXGBE_SP_MC_TBL_SIZE;
-	wx->mac.vft_size = TXGBE_SP_VFT_TBL_SIZE;
-	wx->mac.rx_pb_size = TXGBE_SP_RX_PB_SIZE;
-	wx->mac.tx_pb_size = TXGBE_SP_TDB_PB_SZ;
+	wx->mac.num_rar_entries = TXGBE_RAR_ENTRIES;
+	wx->mac.max_tx_queues = TXGBE_MAX_TXQ;
+	wx->mac.max_rx_queues = TXGBE_MAX_RXQ;
+	wx->mac.mcft_size = TXGBE_MC_TBL_SIZE;
+	wx->mac.vft_size = TXGBE_VFT_TBL_SIZE;
+	wx->mac.rx_pb_size = TXGBE_RX_PB_SIZE;
+	wx->mac.tx_pb_size = TXGBE_TDB_PB_SZ;
 
 	/* PCI config space info */
 	err = wx_sw_init(wx);
@@ -317,6 +398,7 @@ static int txgbe_sw_init(struct wx *wx)
 	wx->configure_fdir = txgbe_configure_fdir;
 
 	set_bit(WX_FLAG_RSC_CAPABLE, wx->flags);
+	set_bit(WX_FLAG_MULTI_64_FUNC, wx->flags);
 
 	/* enable itr by default in dynamic mode */
 	wx->rx_itr_setting = 1;
@@ -339,6 +421,7 @@ static int txgbe_sw_init(struct wx *wx)
 	case wx_mac_sp:
 		break;
 	case wx_mac_aml:
+	case wx_mac_aml40:
 		set_bit(WX_FLAG_SWFW_RING, wx->flags);
 		wx->swfw_index = 0;
 		break;
@@ -537,6 +620,39 @@ void txgbe_do_reset(struct net_device *netdev)
 		txgbe_reset(wx);
 }
 
+static int txgbe_udp_tunnel_sync(struct net_device *dev, unsigned int table)
+{
+	struct wx *wx = netdev_priv(dev);
+	struct udp_tunnel_info ti;
+
+	udp_tunnel_nic_get_port(dev, table, 0, &ti);
+	switch (ti.type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		wr32(wx, TXGBE_CFG_VXLAN, ntohs(ti.port));
+		break;
+	case UDP_TUNNEL_TYPE_VXLAN_GPE:
+		wr32(wx, TXGBE_CFG_VXLAN_GPE, ntohs(ti.port));
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		wr32(wx, TXGBE_CFG_GENEVE, ntohs(ti.port));
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const struct udp_tunnel_nic_info txgbe_udp_tunnels = {
+	.sync_table	= txgbe_udp_tunnel_sync,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.tables		= {
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, },
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN_GPE, },
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
+	},
+};
+
 static const struct net_device_ops txgbe_netdev_ops = {
 	.ndo_open               = txgbe_open,
 	.ndo_stop               = txgbe_close,
@@ -545,6 +661,7 @@ static const struct net_device_ops txgbe_netdev_ops = {
 	.ndo_set_rx_mode        = wx_set_rx_mode,
 	.ndo_set_features       = wx_set_features,
 	.ndo_fix_features       = wx_fix_features,
+	.ndo_features_check     = wx_features_check,
 	.ndo_validate_addr      = eth_validate_addr,
 	.ndo_set_mac_address    = wx_set_mac,
 	.ndo_get_stats64        = wx_get_stats64,
@@ -632,11 +749,12 @@ static int txgbe_probe(struct pci_dev *pdev,
 	wx->driver_name = txgbe_driver_name;
 	txgbe_set_ethtool_ops(netdev);
 	netdev->netdev_ops = &txgbe_netdev_ops;
+	netdev->udp_tunnel_nic_info = &txgbe_udp_tunnels;
 
 	/* setup the private structure */
 	err = txgbe_sw_init(wx);
 	if (err)
-		goto err_free_mac_table;
+		goto err_pci_release_regions;
 
 	/* check if flash load is done after hw power up */
 	err = wx_check_flash_load(wx, TXGBE_SPI_ILDR_STATUS_PERST);
@@ -677,6 +795,7 @@ static int txgbe_probe(struct pci_dev *pdev,
 	netdev->features |= NETIF_F_HIGHDMA;
 	netdev->hw_features |= NETIF_F_GRO;
 	netdev->features |= NETIF_F_GRO;
+	netdev->features |= NETIF_F_RX_UDP_TUNNEL_PORT;
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
@@ -698,9 +817,11 @@ static int txgbe_probe(struct pci_dev *pdev,
 	eth_hw_addr_set(netdev, wx->mac.perm_addr);
 	wx_mac_set_default_filter(wx, wx->mac.perm_addr);
 
+	txgbe_init_service(wx);
+
 	err = wx_init_interrupt_scheme(wx);
 	if (err)
-		goto err_free_mac_table;
+		goto err_cancel_service;
 
 	/* Save off EEPROM version number and Option Rom version which
 	 * together make a unique identify for the eeprom
@@ -743,6 +864,13 @@ static int txgbe_probe(struct pci_dev *pdev,
 	if (etrack_id < 0x20010)
 		dev_warn(&pdev->dev, "Please upgrade the firmware to 0x20010 or above.\n");
 
+	err = txgbe_test_hostif(wx);
+	if (err != 0) {
+		dev_err(&pdev->dev, "Mismatched Firmware version\n");
+		err = -EIO;
+		goto err_release_hw;
+	}
+
 	txgbe = devm_kzalloc(&pdev->dev, sizeof(*txgbe), GFP_KERNEL);
 	if (!txgbe) {
 		err = -ENOMEM;
@@ -793,7 +921,11 @@ err_free_misc_irq:
 err_release_hw:
 	wx_clear_interrupt_scheme(wx);
 	wx_control_hw(wx, false);
+err_cancel_service:
+	timer_delete_sync(&wx->service_timer);
+	cancel_work_sync(&wx->service_task);
 err_free_mac_table:
+	kfree(wx->rss_key);
 	kfree(wx->mac_table);
 err_pci_release_regions:
 	pci_release_selected_regions(pdev,
@@ -818,6 +950,8 @@ static void txgbe_remove(struct pci_dev *pdev)
 	struct txgbe *txgbe = wx->priv;
 	struct net_device *netdev;
 
+	cancel_work_sync(&wx->service_task);
+
 	netdev = wx->netdev;
 	wx_disable_sriov(wx);
 	unregister_netdev(netdev);
@@ -849,5 +983,5 @@ module_pci_driver(txgbe_driver);
 
 MODULE_DEVICE_TABLE(pci, txgbe_pci_tbl);
 MODULE_AUTHOR("Beijing WangXun Technology Co., Ltd, <software@trustnetic.com>");
-MODULE_DESCRIPTION("WangXun(R) 10 Gigabit PCI Express Network Driver");
+MODULE_DESCRIPTION("WangXun(R) 10/25/40 Gigabit PCI Express Network Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 1863cfd27ee7..03f1b9bc604d 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -20,6 +20,7 @@
 #include "../libwx/wx_mbx.h"
 #include "../libwx/wx_hw.h"
 #include "txgbe_type.h"
+#include "txgbe_aml.h"
 #include "txgbe_phy.h"
 #include "txgbe_hw.h"
 
@@ -165,7 +166,7 @@ static struct phylink_pcs *txgbe_phylink_mac_select(struct phylink_config *confi
 	struct wx *wx = phylink_to_wx(config);
 	struct txgbe *txgbe = wx->priv;
 
-	if (wx->media_type != sp_media_copper)
+	if (wx->media_type != wx_media_copper)
 		return txgbe->pcs;
 
 	return NULL;
@@ -278,7 +279,7 @@ static int txgbe_phylink_init(struct txgbe *txgbe)
 	config->mac_capabilities = MAC_10000FD | MAC_1000FD | MAC_100FD |
 				   MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
 
-	if (wx->media_type == sp_media_copper) {
+	if (wx->media_type == wx_media_copper) {
 		phy_mode = PHY_INTERFACE_MODE_XAUI;
 		__set_bit(PHY_INTERFACE_MODE_XAUI, config->supported_interfaces);
 	} else {
@@ -318,7 +319,10 @@ irqreturn_t txgbe_link_irq_handler(int irq, void *data)
 	status = rd32(wx, TXGBE_CFG_PORT_ST);
 	up = !!(status & TXGBE_CFG_PORT_ST_LINK_UP);
 
-	phylink_pcs_change(txgbe->pcs, up);
+	if (txgbe->pcs)
+		phylink_pcs_change(txgbe->pcs, up);
+	else
+		phylink_mac_change(wx->phylink, up);
 
 	return IRQ_HANDLED;
 }
@@ -573,11 +577,18 @@ int txgbe_init_phy(struct txgbe *txgbe)
 	struct wx *wx = txgbe->wx;
 	int ret;
 
-	if (wx->mac.type == wx_mac_aml)
+	switch (wx->mac.type) {
+	case wx_mac_aml40:
 		return 0;
-
-	if (txgbe->wx->media_type == sp_media_copper)
-		return txgbe_ext_phy_init(txgbe);
+	case wx_mac_aml:
+		return txgbe_phylink_init_aml(txgbe);
+	case wx_mac_sp:
+		if (wx->media_type == wx_media_copper)
+			return txgbe_ext_phy_init(txgbe);
+		break;
+	default:
+		break;
+	}
 
 	ret = txgbe_swnodes_register(txgbe);
 	if (ret) {
@@ -640,13 +651,21 @@ err_unregister_swnode:
 
 void txgbe_remove_phy(struct txgbe *txgbe)
 {
-	if (txgbe->wx->mac.type == wx_mac_aml)
+	switch (txgbe->wx->mac.type) {
+	case wx_mac_aml40:
 		return;
-
-	if (txgbe->wx->media_type == sp_media_copper) {
-		phylink_disconnect_phy(txgbe->wx->phylink);
+	case wx_mac_aml:
 		phylink_destroy(txgbe->wx->phylink);
 		return;
+	case wx_mac_sp:
+		if (txgbe->wx->media_type == wx_media_copper) {
+			phylink_disconnect_phy(txgbe->wx->phylink);
+			phylink_destroy(txgbe->wx->phylink);
+			return;
+		}
+		break;
+	default:
+		break;
 	}
 
 	platform_device_unregister(txgbe->sfp_dev);
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h
index 3938985355ed..a32b19d71ea2 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h
@@ -8,4 +8,4 @@ irqreturn_t txgbe_link_irq_handler(int irq, void *data);
 int txgbe_init_phy(struct txgbe *txgbe);
 void txgbe_remove_phy(struct txgbe *txgbe);
 
-#endif /* _TXGBE_NODE_H_ */
+#endif /* _TXGBE_PHY_H_ */
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
index 5937cbc6bd05..7a00e3343be6 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
@@ -6,6 +6,8 @@
 
 #include <linux/property.h>
 #include <linux/irq.h>
+#include <linux/phy.h>
+#include "../libwx/wx_type.h"
 
 /* Device IDs */
 #define TXGBE_DEV_ID_SP1000                     0x1001
@@ -50,6 +52,8 @@
 
 /**************** SP Registers ****************************/
 /* chip control Registers */
+#define TXGBE_MIS_RST                           0x1000C
+#define TXGBE_MIS_RST_MAC_RST(_i)               BIT(20 - (_i) * 3)
 #define TXGBE_MIS_PRB_CTL                       0x10010
 #define TXGBE_MIS_PRB_CTL_LAN_UP(_i)            BIT(1 - (_i))
 /* FMGR Registers */
@@ -62,6 +66,11 @@
 #define TXGBE_TS_CTL                            0x10300
 #define TXGBE_TS_CTL_EVAL_MD                    BIT(31)
 
+/* MAC Misc Registers */
+#define TXGBE_MAC_MISC_CTL                      0x11F00
+#define TXGBE_MAC_MISC_CTL_LINK_STS_MOD         BIT(0)
+#define TXGBE_MAC_MISC_CTL_LINK_PCS             FIELD_PREP(BIT(0), 0)
+#define TXGBE_MAC_MISC_CTL_LINK_BOTH            FIELD_PREP(BIT(0), 1)
 /* GPIO register bit */
 #define TXGBE_GPIOBIT_0                         BIT(0) /* I:tx fault */
 #define TXGBE_GPIOBIT_1                         BIT(1) /* O:tx disabled */
@@ -73,6 +82,7 @@
 /* Extended Interrupt Enable Set */
 #define TXGBE_PX_MISC_ETH_LKDN                  BIT(8)
 #define TXGBE_PX_MISC_DEV_RST                   BIT(10)
+#define TXGBE_PX_MISC_IC_TIMESYNC               BIT(11)
 #define TXGBE_PX_MISC_ETH_EVENT                 BIT(17)
 #define TXGBE_PX_MISC_ETH_LK                    BIT(18)
 #define TXGBE_PX_MISC_ETH_AN                    BIT(19)
@@ -83,11 +93,16 @@
 	(TXGBE_PX_MISC_ETH_LKDN | TXGBE_PX_MISC_DEV_RST | \
 	 TXGBE_PX_MISC_ETH_EVENT | TXGBE_PX_MISC_ETH_LK | \
 	 TXGBE_PX_MISC_ETH_AN | TXGBE_PX_MISC_INT_ERR | \
-	 TXGBE_PX_MISC_IC_VF_MBOX)
+	 TXGBE_PX_MISC_IC_VF_MBOX | TXGBE_PX_MISC_IC_TIMESYNC)
 
 /* Port cfg registers */
 #define TXGBE_CFG_PORT_ST                       0x14404
 #define TXGBE_CFG_PORT_ST_LINK_UP               BIT(0)
+#define TXGBE_CFG_PORT_ST_LINK_AML_25G          BIT(3)
+#define TXGBE_CFG_PORT_ST_LINK_AML_10G          BIT(4)
+#define TXGBE_CFG_VXLAN                         0x14410
+#define TXGBE_CFG_VXLAN_GPE                     0x14414
+#define TXGBE_CFG_GENEVE                        0x14418
 
 /* I2C registers */
 #define TXGBE_I2C_BASE                          0x14900
@@ -148,8 +163,11 @@
 /*************************** Amber Lite Registers ****************************/
 #define TXGBE_PX_PF_BME                         0x4B8
 #define TXGBE_AML_MAC_TX_CFG                    0x11000
+#define TXGBE_AML_MAC_TX_CFG_TE                 BIT(0)
 #define TXGBE_AML_MAC_TX_CFG_SPEED_MASK         GENMASK(30, 27)
-#define TXGBE_AML_MAC_TX_CFG_SPEED_25G          BIT(28)
+#define TXGBE_AML_MAC_TX_CFG_SPEED_40G          FIELD_PREP(GENMASK(30, 27), 0)
+#define TXGBE_AML_MAC_TX_CFG_SPEED_25G          FIELD_PREP(GENMASK(30, 27), 2)
+#define TXGBE_AML_MAC_TX_CFG_SPEED_10G          FIELD_PREP(GENMASK(30, 27), 8)
 #define TXGBE_RDM_RSC_CTL                       0x1200C
 #define TXGBE_RDM_RSC_CTL_FREE_CTL              BIT(7)
 
@@ -160,6 +178,8 @@
 #define TXGBE_EEPROM_VERSION_L                  0x1D
 #define TXGBE_EEPROM_VERSION_H                  0x1E
 #define TXGBE_ISCSI_BOOT_CONFIG                 0x07
+#define TXGBE_EEPROM_I2C_SRART_PTR              0x580
+#define TXGBE_EEPROM_I2C_END_PTR                0x800
 
 #define TXGBE_MAX_MSIX_VECTORS          64
 #define TXGBE_MAX_FDIR_INDICES          63
@@ -168,13 +188,13 @@
 #define TXGBE_MAX_RX_QUEUES   (TXGBE_MAX_FDIR_INDICES + 1)
 #define TXGBE_MAX_TX_QUEUES   (TXGBE_MAX_FDIR_INDICES + 1)
 
-#define TXGBE_SP_MAX_TX_QUEUES  128
-#define TXGBE_SP_MAX_RX_QUEUES  128
-#define TXGBE_SP_RAR_ENTRIES    128
-#define TXGBE_SP_MC_TBL_SIZE    128
-#define TXGBE_SP_VFT_TBL_SIZE   128
-#define TXGBE_SP_RX_PB_SIZE     512
-#define TXGBE_SP_TDB_PB_SZ      (160 * 1024) /* 160KB Packet Buffer */
+#define TXGBE_MAX_TXQ        128
+#define TXGBE_MAX_RXQ        128
+#define TXGBE_RAR_ENTRIES    128
+#define TXGBE_MC_TBL_SIZE    128
+#define TXGBE_VFT_TBL_SIZE   128
+#define TXGBE_RX_PB_SIZE     512
+#define TXGBE_TDB_PB_SZ      (160 * 1024) /* 160KB Packet Buffer */
 
 #define TXGBE_MAX_VFS_DRV_LIMIT                 63
 
@@ -294,6 +314,72 @@ void txgbe_up(struct wx *wx);
 int txgbe_setup_tc(struct net_device *dev, u8 tc);
 void txgbe_do_reset(struct net_device *netdev);
 
+#define TXGBE_LINK_SPEED_10GB_FULL      4
+#define TXGBE_LINK_SPEED_25GB_FULL      0x10
+
+#define TXGBE_SFF_IDENTIFIER_SFP        0x3
+#define TXGBE_SFF_DA_PASSIVE_CABLE      0x4
+#define TXGBE_SFF_DA_ACTIVE_CABLE       0x8
+#define TXGBE_SFF_DA_SPEC_ACTIVE_LIMIT  0x4
+#define TXGBE_SFF_FCPI4_LIMITING        0x3
+#define TXGBE_SFF_10GBASESR_CAPABLE     0x10
+#define TXGBE_SFF_10GBASELR_CAPABLE     0x20
+#define TXGBE_SFF_25GBASESR_CAPABLE     0x2
+#define TXGBE_SFF_25GBASELR_CAPABLE     0x3
+#define TXGBE_SFF_25GBASEER_CAPABLE     0x4
+#define TXGBE_SFF_25GBASECR_91FEC       0xB
+#define TXGBE_SFF_25GBASECR_74FEC       0xC
+#define TXGBE_SFF_25GBASECR_NOFEC       0xD
+
+#define TXGBE_PHY_FEC_RS                BIT(0)
+#define TXGBE_PHY_FEC_BASER             BIT(1)
+#define TXGBE_PHY_FEC_OFF               BIT(2)
+#define TXGBE_PHY_FEC_AUTO              (TXGBE_PHY_FEC_OFF | \
+					 TXGBE_PHY_FEC_BASER |\
+					 TXGBE_PHY_FEC_RS)
+
+#define FW_PHY_GET_LINK_CMD             0xC0
+#define FW_PHY_SET_LINK_CMD             0xC1
+#define FW_READ_SFP_INFO_CMD            0xC5
+
+struct txgbe_sfp_id {
+	u8 identifier;		/* A0H 0x00 */
+	u8 com_1g_code;		/* A0H 0x06 */
+	u8 com_10g_code;	/* A0H 0x03 */
+	u8 com_25g_code;	/* A0H 0x24 */
+	u8 cable_spec;		/* A0H 0x3C */
+	u8 cable_tech;		/* A0H 0x08 */
+	u8 vendor_oui0;		/* A0H 0x25 */
+	u8 vendor_oui1;		/* A0H 0x26 */
+	u8 vendor_oui2;		/* A0H 0x27 */
+	u8 reserved[3];
+};
+
+struct txgbe_hic_i2c_read {
+	struct wx_hic_hdr hdr;
+	struct txgbe_sfp_id id;
+};
+
+struct txgbe_hic_ephy_setlink {
+	struct wx_hic_hdr hdr;
+	u8 speed;
+	u8 duplex;
+	u8 autoneg;
+	u8 fec_mode;
+	u8 resv[4];
+};
+
+struct txgbe_hic_ephy_getlink {
+	struct wx_hic_hdr hdr;
+	u8 speed;
+	u8 duplex;
+	u8 autoneg;
+	u8 flow_ctl;
+	u8 power;
+	u8 fec_mode;
+	u8 resv[6];
+};
+
 #define NODE_PROP(_NAME, _PROP)			\
 	(const struct software_node) {		\
 		.name = _NAME,			\
@@ -331,6 +417,7 @@ struct txgbe_nodes {
 
 enum txgbe_misc_irqs {
 	TXGBE_IRQ_LINK = 0,
+	TXGBE_IRQ_GPIO,
 	TXGBE_IRQ_MAX
 };
 
@@ -352,6 +439,7 @@ struct txgbe {
 	struct clk *clk;
 	struct gpio_chip *gpio;
 	unsigned int link_irq;
+	unsigned int gpio_irq;
 	u32 eicr;
 
 	/* flow director */
@@ -359,6 +447,11 @@ struct txgbe {
 	union txgbe_atr_input fdir_mask;
 	int fdir_filter_count;
 	spinlock_t fdir_perfect_lock; /* spinlock for FDIR */
+
+	DECLARE_PHY_INTERFACE_MASK(sfp_interfaces);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
+	u8 link_port;
 };
 
 #endif /* _TXGBE_TYPE_H_ */
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 054abf283ab3..1b7a653c1f4e 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -2980,7 +2980,7 @@ static int axienet_probe(struct platform_device *pdev)
 			}
 		}
 		if (!IS_ENABLED(CONFIG_64BIT) && lp->features & XAE_FEATURE_DMA_64BIT) {
-			dev_err(&pdev->dev, "64-bit addressable DMA is not compatible with 32-bit archecture\n");
+			dev_err(&pdev->dev, "64-bit addressable DMA is not compatible with 32-bit architecture\n");
 			ret = -EINVAL;
 			goto cleanup_clk;
 		}
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index a2ab1c150822..e1e7f65553e7 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -394,16 +394,20 @@ static void ixp_tx_timestamp(struct port *port, struct sk_buff *skb)
 	__raw_writel(TX_SNAPSHOT_LOCKED, &regs->channel[ch].ch_event);
 }
 
-static int hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
+static int ixp4xx_hwtstamp_set(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *cfg,
+			       struct netlink_ext_ack *extack)
 {
-	struct hwtstamp_config cfg;
 	struct ixp46x_ts_regs *regs;
 	struct port *port = netdev_priv(netdev);
 	int ret;
 	int ch;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
+	if (!cpu_is_ixp46x())
+		return -EOPNOTSUPP;
+
+	if (!netif_running(netdev))
+		return -EINVAL;
 
 	ret = ixp46x_ptp_find(&port->timesync_regs, &port->phc_index);
 	if (ret)
@@ -412,10 +416,10 @@ static int hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 	ch = PORT2CHANNEL(port);
 	regs = port->timesync_regs;
 
-	if (cfg.tx_type != HWTSTAMP_TX_OFF && cfg.tx_type != HWTSTAMP_TX_ON)
+	if (cfg->tx_type != HWTSTAMP_TX_OFF && cfg->tx_type != HWTSTAMP_TX_ON)
 		return -ERANGE;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		port->hwts_rx_en = 0;
 		break;
@@ -431,39 +435,45 @@ static int hwtstamp_set(struct net_device *netdev, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	port->hwts_tx_en = cfg.tx_type == HWTSTAMP_TX_ON;
+	port->hwts_tx_en = cfg->tx_type == HWTSTAMP_TX_ON;
 
 	/* Clear out any old time stamps. */
 	__raw_writel(TX_SNAPSHOT_LOCKED | RX_SNAPSHOT_LOCKED,
 		     &regs->channel[ch].ch_event);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
-static int hwtstamp_get(struct net_device *netdev, struct ifreq *ifr)
+static int ixp4xx_hwtstamp_get(struct net_device *netdev,
+			       struct kernel_hwtstamp_config *cfg)
 {
-	struct hwtstamp_config cfg;
 	struct port *port = netdev_priv(netdev);
 
-	cfg.flags = 0;
-	cfg.tx_type = port->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	if (!cpu_is_ixp46x())
+		return -EOPNOTSUPP;
+
+	if (!netif_running(netdev))
+		return -EINVAL;
+
+	cfg->flags = 0;
+	cfg->tx_type = port->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
 
 	switch (port->hwts_rx_en) {
 	case 0:
-		cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+		cfg->rx_filter = HWTSTAMP_FILTER_NONE;
 		break;
 	case PTP_SLAVE_MODE:
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_SYNC;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_SYNC;
 		break;
 	case PTP_MASTER_MODE:
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ;
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		return -ERANGE;
 	}
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static int ixp4xx_mdio_cmd(struct mii_bus *bus, int phy_id, int location,
@@ -985,21 +995,6 @@ static void eth_set_mcast_list(struct net_device *dev)
 }
 
 
-static int eth_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
-{
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	if (cpu_is_ixp46x()) {
-		if (cmd == SIOCSHWTSTAMP)
-			return hwtstamp_set(dev, req);
-		if (cmd == SIOCGHWTSTAMP)
-			return hwtstamp_get(dev, req);
-	}
-
-	return phy_mii_ioctl(dev->phydev, req, cmd);
-}
-
 /* ethtool support */
 
 static void ixp4xx_get_drvinfo(struct net_device *dev,
@@ -1433,9 +1428,11 @@ static const struct net_device_ops ixp4xx_netdev_ops = {
 	.ndo_change_mtu = ixp4xx_eth_change_mtu,
 	.ndo_start_xmit = eth_xmit,
 	.ndo_set_rx_mode = eth_set_mcast_list,
-	.ndo_eth_ioctl = eth_ioctl,
+	.ndo_eth_ioctl = phy_do_ioctl_running,
 	.ndo_set_mac_address = eth_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
+	.ndo_hwtstamp_get = ixp4xx_hwtstamp_get,
+	.ndo_hwtstamp_set = ixp4xx_hwtstamp_set,
 };
 
 static struct eth_plat_info *ixp4xx_of_get_platdata(struct device *dev)
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 66e38ce9cd1d..ffc15a432689 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1946,22 +1946,14 @@ static __net_init int geneve_init_net(struct net *net)
 	return 0;
 }
 
-static void geneve_destroy_tunnels(struct net *net, struct list_head *head)
+static void __net_exit geneve_exit_rtnl_net(struct net *net,
+					    struct list_head *dev_to_kill)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_dev *geneve, *next;
 
 	list_for_each_entry_safe(geneve, next, &gn->geneve_list, next)
-		geneve_dellink(geneve->dev, head);
-}
-
-static void __net_exit geneve_exit_batch_rtnl(struct list_head *net_list,
-					      struct list_head *dev_to_kill)
-{
-	struct net *net;
-
-	list_for_each_entry(net, net_list, exit_list)
-		geneve_destroy_tunnels(net, dev_to_kill);
+		geneve_dellink(geneve->dev, dev_to_kill);
 }
 
 static void __net_exit geneve_exit_net(struct net *net)
@@ -1973,7 +1965,7 @@ static void __net_exit geneve_exit_net(struct net *net)
 
 static struct pernet_operations geneve_net_ops = {
 	.init = geneve_init_net,
-	.exit_batch_rtnl = geneve_exit_batch_rtnl,
+	.exit_rtnl = geneve_exit_rtnl_net,
 	.exit = geneve_exit_net,
 	.id   = &geneve_net_id,
 	.size = sizeof(struct geneve_net),
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index ef793607890d..d4dec741c7f4 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -2475,23 +2475,19 @@ static int __net_init gtp_net_init(struct net *net)
 	return 0;
 }
 
-static void __net_exit gtp_net_exit_batch_rtnl(struct list_head *net_list,
-					       struct list_head *dev_to_kill)
+static void __net_exit gtp_net_exit_rtnl(struct net *net,
+					 struct list_head *dev_to_kill)
 {
-	struct net *net;
-
-	list_for_each_entry(net, net_list, exit_list) {
-		struct gtp_net *gn = net_generic(net, gtp_net_id);
-		struct gtp_dev *gtp, *gtp_next;
+	struct gtp_net *gn = net_generic(net, gtp_net_id);
+	struct gtp_dev *gtp, *gtp_next;
 
-		list_for_each_entry_safe(gtp, gtp_next, &gn->gtp_dev_list, list)
-			gtp_dellink(gtp->dev, dev_to_kill);
-	}
+	list_for_each_entry_safe(gtp, gtp_next, &gn->gtp_dev_list, list)
+		gtp_dellink(gtp->dev, dev_to_kill);
 }
 
 static struct pernet_operations gtp_net_ops = {
 	.init	= gtp_net_init,
-	.exit_batch_rtnl = gtp_net_exit_batch_rtnl,
+	.exit_rtnl = gtp_net_exit_rtnl,
 	.id	= &gtp_net_id,
 	.size	= sizeof(struct gtp_net),
 };
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 70f7cb383228..cb6f5482d203 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -158,7 +158,6 @@ struct hv_netvsc_packet {
 	u8 cp_partial; /* partial copy into send buffer */
 
 	u8 rmsg_size; /* RNDIS header and PPI size */
-	u8 rmsg_pgcnt; /* page count of RNDIS header and PPI */
 	u8 page_buf_cnt;
 
 	u16 q_idx;
@@ -893,6 +892,18 @@ struct nvsp_message {
 				 sizeof(struct nvsp_message))
 #define NETVSC_MIN_IN_MSG_SIZE sizeof(struct vmpacket_descriptor)
 
+/* Maximum # of contiguous data ranges that can make up a trasmitted packet.
+ * Typically it's the max SKB fragments plus 2 for the rndis packet and the
+ * linear portion of the SKB. But if MAX_SKB_FRAGS is large, the value may
+ * need to be limited to MAX_PAGE_BUFFER_COUNT, which is the max # of entries
+ * in a GPA direct packet sent to netvsp over VMBus.
+ */
+#if MAX_SKB_FRAGS + 2 < MAX_PAGE_BUFFER_COUNT
+#define MAX_DATA_RANGES (MAX_SKB_FRAGS + 2)
+#else
+#define MAX_DATA_RANGES MAX_PAGE_BUFFER_COUNT
+#endif
+
 /* Estimated requestor size:
  * out_ring_size/min_out_msg_size + in_ring_size/min_in_msg_size
  */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index d6f5b9ea3109..720104661d7f 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -953,8 +953,7 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		     + pend_size;
 	int i;
 	u32 padding = 0;
-	u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt :
-		packet->page_buf_cnt;
+	u32 page_count = packet->cp_partial ? 1 : packet->page_buf_cnt;
 	u32 remain;
 
 	/* Add padding */
@@ -1055,6 +1054,42 @@ static int netvsc_dma_map(struct hv_device *hv_dev,
 	return 0;
 }
 
+/* Build an "array" of mpb entries describing the data to be transferred
+ * over VMBus. After the desc header fields, each "array" entry is variable
+ * size, and each entry starts after the end of the previous entry. The
+ * "offset" and "len" fields for each entry imply the size of the entry.
+ *
+ * The pfns are in HV_HYP_PAGE_SIZE, because all communication with Hyper-V
+ * uses that granularity, even if the system page size of the guest is larger.
+ * Each entry in the input "pb" array must describe a contiguous range of
+ * guest physical memory so that the pfns are sequential if the range crosses
+ * a page boundary. The offset field must be < HV_HYP_PAGE_SIZE.
+ */
+static inline void netvsc_build_mpb_array(struct hv_page_buffer *pb,
+				u32 page_buffer_count,
+				struct vmbus_packet_mpb_array *desc,
+				u32 *desc_size)
+{
+	struct hv_mpb_array *mpb_entry = &desc->range;
+	int i, j;
+
+	for (i = 0; i < page_buffer_count; i++) {
+		u32 offset = pb[i].offset;
+		u32 len = pb[i].len;
+
+		mpb_entry->offset = offset;
+		mpb_entry->len = len;
+
+		for (j = 0; j < HVPFN_UP(offset + len); j++)
+			mpb_entry->pfn_array[j] = pb[i].pfn + j;
+
+		mpb_entry = (struct hv_mpb_array *)&mpb_entry->pfn_array[j];
+	}
+
+	desc->rangecount = page_buffer_count;
+	*desc_size = (char *)mpb_entry - (char *)desc;
+}
+
 static inline int netvsc_send_pkt(
 	struct hv_device *device,
 	struct hv_netvsc_packet *packet,
@@ -1097,8 +1132,11 @@ static inline int netvsc_send_pkt(
 
 	packet->dma_range = NULL;
 	if (packet->page_buf_cnt) {
+		struct vmbus_channel_packet_page_buffer desc;
+		u32 desc_size;
+
 		if (packet->cp_partial)
-			pb += packet->rmsg_pgcnt;
+			pb++;
 
 		ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb);
 		if (ret) {
@@ -1106,11 +1144,12 @@ static inline int netvsc_send_pkt(
 			goto exit;
 		}
 
-		ret = vmbus_sendpacket_pagebuffer(out_channel,
-						  pb, packet->page_buf_cnt,
-						  &nvmsg, sizeof(nvmsg),
-						  req_id);
-
+		netvsc_build_mpb_array(pb, packet->page_buf_cnt,
+				(struct vmbus_packet_mpb_array *)&desc,
+				 &desc_size);
+		ret = vmbus_sendpacket_mpb_desc(out_channel,
+				(struct vmbus_packet_mpb_array *)&desc,
+				desc_size, &nvmsg, sizeof(nvmsg), req_id);
 		if (ret)
 			netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
 	} else {
@@ -1259,7 +1298,7 @@ int netvsc_send(struct net_device *ndev,
 		packet->send_buf_index = section_index;
 
 		if (packet->cp_partial) {
-			packet->page_buf_cnt -= packet->rmsg_pgcnt;
+			packet->page_buf_cnt--;
 			packet->total_data_buflen = msd_len + packet->rmsg_size;
 		} else {
 			packet->page_buf_cnt = 0;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index c51b318b8a72..d8b169ac0343 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -326,43 +326,10 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	return txq;
 }
 
-static u32 fill_pg_buf(unsigned long hvpfn, u32 offset, u32 len,
-		       struct hv_page_buffer *pb)
-{
-	int j = 0;
-
-	hvpfn += offset >> HV_HYP_PAGE_SHIFT;
-	offset = offset & ~HV_HYP_PAGE_MASK;
-
-	while (len > 0) {
-		unsigned long bytes;
-
-		bytes = HV_HYP_PAGE_SIZE - offset;
-		if (bytes > len)
-			bytes = len;
-		pb[j].pfn = hvpfn;
-		pb[j].offset = offset;
-		pb[j].len = bytes;
-
-		offset += bytes;
-		len -= bytes;
-
-		if (offset == HV_HYP_PAGE_SIZE && len) {
-			hvpfn++;
-			offset = 0;
-			j++;
-		}
-	}
-
-	return j + 1;
-}
-
 static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
 			   struct hv_netvsc_packet *packet,
 			   struct hv_page_buffer *pb)
 {
-	u32 slots_used = 0;
-	char *data = skb->data;
 	int frags = skb_shinfo(skb)->nr_frags;
 	int i;
 
@@ -371,28 +338,27 @@ static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
 	 * 2. skb linear data
 	 * 3. skb fragment data
 	 */
-	slots_used += fill_pg_buf(virt_to_hvpfn(hdr),
-				  offset_in_hvpage(hdr),
-				  len,
-				  &pb[slots_used]);
 
+	pb[0].offset = offset_in_hvpage(hdr);
+	pb[0].len = len;
+	pb[0].pfn = virt_to_hvpfn(hdr);
 	packet->rmsg_size = len;
-	packet->rmsg_pgcnt = slots_used;
 
-	slots_used += fill_pg_buf(virt_to_hvpfn(data),
-				  offset_in_hvpage(data),
-				  skb_headlen(skb),
-				  &pb[slots_used]);
+	pb[1].offset = offset_in_hvpage(skb->data);
+	pb[1].len = skb_headlen(skb);
+	pb[1].pfn = virt_to_hvpfn(skb->data);
 
 	for (i = 0; i < frags; i++) {
 		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+		struct hv_page_buffer *cur_pb = &pb[i + 2];
+		u64 pfn = page_to_hvpfn(skb_frag_page(frag));
+		u32 offset = skb_frag_off(frag);
 
-		slots_used += fill_pg_buf(page_to_hvpfn(skb_frag_page(frag)),
-					  skb_frag_off(frag),
-					  skb_frag_size(frag),
-					  &pb[slots_used]);
+		cur_pb->offset = offset_in_hvpage(offset);
+		cur_pb->len = skb_frag_size(frag);
+		cur_pb->pfn = pfn + (offset >> HV_HYP_PAGE_SHIFT);
 	}
-	return slots_used;
+	return frags + 2;
 }
 
 static int count_skb_frag_slots(struct sk_buff *skb)
@@ -483,7 +449,7 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx)
 	struct net_device *vf_netdev;
 	u32 rndis_msg_size;
 	u32 hash;
-	struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
+	struct hv_page_buffer pb[MAX_DATA_RANGES];
 
 	/* If VF is present and up then redirect packets to it.
 	 * Skip the VF if it is marked down or has no carrier.
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 82747dfacd70..9e73959e61ee 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -225,8 +225,7 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 				  struct rndis_request *req)
 {
 	struct hv_netvsc_packet *packet;
-	struct hv_page_buffer page_buf[2];
-	struct hv_page_buffer *pb = page_buf;
+	struct hv_page_buffer pb;
 	int ret;
 
 	/* Setup the packet to send it */
@@ -235,27 +234,14 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 	packet->total_data_buflen = req->request_msg.msg_len;
 	packet->page_buf_cnt = 1;
 
-	pb[0].pfn = virt_to_phys(&req->request_msg) >>
-					HV_HYP_PAGE_SHIFT;
-	pb[0].len = req->request_msg.msg_len;
-	pb[0].offset = offset_in_hvpage(&req->request_msg);
-
-	/* Add one page_buf when request_msg crossing page boundary */
-	if (pb[0].offset + pb[0].len > HV_HYP_PAGE_SIZE) {
-		packet->page_buf_cnt++;
-		pb[0].len = HV_HYP_PAGE_SIZE -
-			pb[0].offset;
-		pb[1].pfn = virt_to_phys((void *)&req->request_msg
-			+ pb[0].len) >> HV_HYP_PAGE_SHIFT;
-		pb[1].offset = 0;
-		pb[1].len = req->request_msg.msg_len -
-			pb[0].len;
-	}
+	pb.pfn = virt_to_phys(&req->request_msg) >> HV_HYP_PAGE_SHIFT;
+	pb.len = req->request_msg.msg_len;
+	pb.offset = offset_in_hvpage(&req->request_msg);
 
 	trace_rndis_send(dev->ndev, 0, &req->request_msg);
 
 	rcu_read_lock_bh();
-	ret = netvsc_send(dev->ndev, packet, NULL, pb, NULL, false);
+	ret = netvsc_send(dev->ndev, packet, NULL, &pb, NULL, false);
 	rcu_read_unlock_bh();
 
 	return ret;
diff --git a/drivers/net/ipa/data/ipa_data-v3.1.c b/drivers/net/ipa/data/ipa_data-v3.1.c
index e902d731776d..65dba4729155 100644
--- a/drivers/net/ipa/data/ipa_data-v3.1.c
+++ b/drivers/net/ipa/data/ipa_data-v3.1.c
@@ -493,7 +493,6 @@ static const struct ipa_mem_data ipa_mem_data = {
 	.local		= ipa_mem_local_data,
 	.imem_addr	= 0x146bd000,
 	.imem_size	= 0x00002000,
-	.smem_id	= 497,
 	.smem_size	= 0x00002000,
 };
 
diff --git a/drivers/net/ipa/data/ipa_data-v3.5.1.c b/drivers/net/ipa/data/ipa_data-v3.5.1.c
index f632aab56f4c..315e617a8eeb 100644
--- a/drivers/net/ipa/data/ipa_data-v3.5.1.c
+++ b/drivers/net/ipa/data/ipa_data-v3.5.1.c
@@ -374,7 +374,6 @@ static const struct ipa_mem_data ipa_mem_data = {
 	.local		= ipa_mem_local_data,
 	.imem_addr	= 0x146bd000,
 	.imem_size	= 0x00002000,
-	.smem_id	= 497,
 	.smem_size	= 0x00002000,
 };
 
diff --git a/drivers/net/ipa/data/ipa_data-v4.11.c b/drivers/net/ipa/data/ipa_data-v4.11.c
index c1428483ca34..f5d66779c2fb 100644
--- a/drivers/net/ipa/data/ipa_data-v4.11.c
+++ b/drivers/net/ipa/data/ipa_data-v4.11.c
@@ -367,7 +367,6 @@ static const struct ipa_mem_data ipa_mem_data = {
 	.local		= ipa_mem_local_data,
 	.imem_addr	= 0x146a8000,
 	.imem_size	= 0x00002000,
-	.smem_id	= 497,
 	.smem_size	= 0x00009000,
 };
 
diff --git a/drivers/net/ipa/data/ipa_data-v4.2.c b/drivers/net/ipa/data/ipa_data-v4.2.c
index 2c7e8cb429b9..f5ed5d745aeb 100644
--- a/drivers/net/ipa/data/ipa_data-v4.2.c
+++ b/drivers/net/ipa/data/ipa_data-v4.2.c
@@ -340,7 +340,6 @@ static const struct ipa_mem_data ipa_mem_data = {
 	.local		= ipa_mem_local_data,
 	.imem_addr	= 0x146a8000,
 	.imem_size	= 0x00002000,
-	.smem_id	= 497,
 	.smem_size	= 0x00002000,
 };
 
diff --git a/drivers/net/ipa/data/ipa_data-v4.5.c b/drivers/net/ipa/data/ipa_data-v4.5.c
index 57dc78c526b0..730d8c43a45c 100644
--- a/drivers/net/ipa/data/ipa_data-v4.5.c
+++ b/drivers/net/ipa/data/ipa_data-v4.5.c
@@ -418,7 +418,6 @@ static const struct ipa_mem_data ipa_mem_data = {
 	.local		= ipa_mem_local_data,
 	.imem_addr	= 0x14688000,
 	.imem_size	= 0x00003000,
-	.smem_id	= 497,
 	.smem_size	= 0x00009000,
 };
 
diff --git a/drivers/net/ipa/data/ipa_data-v4.7.c b/drivers/net/ipa/data/ipa_data-v4.7.c
index 41f212209993..5e1d9049c62b 100644
--- a/drivers/net/ipa/data/ipa_data-v4.7.c
+++ b/drivers/net/ipa/data/ipa_data-v4.7.c
@@ -360,7 +360,6 @@ static const struct ipa_mem_data ipa_mem_data = {
 	.local		= ipa_mem_local_data,
 	.imem_addr	= 0x146a8000,
 	.imem_size	= 0x00002000,
-	.smem_id	= 497,
 	.smem_size	= 0x00009000,
 };
 
diff --git a/drivers/net/ipa/data/ipa_data-v4.9.c b/drivers/net/ipa/data/ipa_data-v4.9.c
index 4eb9c909d5b3..da472a2a2e29 100644
--- a/drivers/net/ipa/data/ipa_data-v4.9.c
+++ b/drivers/net/ipa/data/ipa_data-v4.9.c
@@ -416,7 +416,6 @@ static const struct ipa_mem_data ipa_mem_data = {
 	.local		= ipa_mem_local_data,
 	.imem_addr	= 0x146bd000,
 	.imem_size	= 0x00002000,
-	.smem_id	= 497,
 	.smem_size	= 0x00009000,
 };
 
diff --git a/drivers/net/ipa/data/ipa_data-v5.0.c b/drivers/net/ipa/data/ipa_data-v5.0.c
index 050580c99b65..bc5722e4b053 100644
--- a/drivers/net/ipa/data/ipa_data-v5.0.c
+++ b/drivers/net/ipa/data/ipa_data-v5.0.c
@@ -442,7 +442,6 @@ static const struct ipa_mem_data ipa_mem_data = {
 	.local		= ipa_mem_local_data,
 	.imem_addr	= 0x14688000,
 	.imem_size	= 0x00003000,
-	.smem_id	= 497,
 	.smem_size	= 0x00009000,
 };
 
diff --git a/drivers/net/ipa/data/ipa_data-v5.5.c b/drivers/net/ipa/data/ipa_data-v5.5.c
index 0e6663e22533..741ae21d9d78 100644
--- a/drivers/net/ipa/data/ipa_data-v5.5.c
+++ b/drivers/net/ipa/data/ipa_data-v5.5.c
@@ -448,7 +448,6 @@ static const struct ipa_mem_data ipa_mem_data = {
 	.local		= ipa_mem_local_data,
 	.imem_addr	= 0x14688000,
 	.imem_size	= 0x00002000,
-	.smem_id	= 497,
 	.smem_size	= 0x0000b000,
 };
 
diff --git a/drivers/net/ipa/ipa_data.h b/drivers/net/ipa/ipa_data.h
index d88cbbbf18b7..2fd03f0799b2 100644
--- a/drivers/net/ipa/ipa_data.h
+++ b/drivers/net/ipa/ipa_data.h
@@ -180,7 +180,6 @@ struct ipa_resource_data {
  * @local:		array of IPA-local memory region descriptors
  * @imem_addr:		physical address of IPA region within IMEM
  * @imem_size:		size in bytes of IPA IMEM region
- * @smem_id:		item identifier for IPA region within SMEM memory
  * @smem_size:		size in bytes of the IPA SMEM region
  */
 struct ipa_mem_data {
@@ -188,7 +187,6 @@ struct ipa_mem_data {
 	const struct ipa_mem *local;
 	u32 imem_addr;
 	u32 imem_size;
-	u32 smem_id;
 	u32 smem_size;
 };
 
diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c
index dee985eb08cb..835a3c9c1fd4 100644
--- a/drivers/net/ipa/ipa_mem.c
+++ b/drivers/net/ipa/ipa_mem.c
@@ -26,6 +26,8 @@
 /* SMEM host id representing the modem. */
 #define QCOM_SMEM_HOST_MODEM	1
 
+#define SMEM_IPA_FILTER_TABLE	497
+
 const struct ipa_mem *ipa_mem_find(struct ipa *ipa, enum ipa_mem_id mem_id)
 {
 	u32 i;
@@ -509,7 +511,6 @@ static void ipa_imem_exit(struct ipa *ipa)
 /**
  * ipa_smem_init() - Initialize SMEM memory used by the IPA
  * @ipa:	IPA pointer
- * @item:	Item ID of SMEM memory
  * @size:	Size (bytes) of SMEM memory region
  *
  * SMEM is a managed block of shared DRAM, from which numbered "items"
@@ -523,7 +524,7 @@ static void ipa_imem_exit(struct ipa *ipa)
  *
  * Note: @size and the item address are is not guaranteed to be page-aligned.
  */
-static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size)
+static int ipa_smem_init(struct ipa *ipa, size_t size)
 {
 	struct device *dev = ipa->dev;
 	struct iommu_domain *domain;
@@ -545,25 +546,25 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size)
 	 * The item might have already been allocated, in which case we
 	 * use it unless the size isn't what we expect.
 	 */
-	ret = qcom_smem_alloc(QCOM_SMEM_HOST_MODEM, item, size);
+	ret = qcom_smem_alloc(QCOM_SMEM_HOST_MODEM, SMEM_IPA_FILTER_TABLE, size);
 	if (ret && ret != -EEXIST) {
-		dev_err(dev, "error %d allocating size %zu SMEM item %u\n",
-			ret, size, item);
+		dev_err(dev, "error %d allocating size %zu SMEM item\n",
+			ret, size);
 		return ret;
 	}
 
 	/* Now get the address of the SMEM memory region */
-	virt = qcom_smem_get(QCOM_SMEM_HOST_MODEM, item, &actual);
+	virt = qcom_smem_get(QCOM_SMEM_HOST_MODEM, SMEM_IPA_FILTER_TABLE, &actual);
 	if (IS_ERR(virt)) {
 		ret = PTR_ERR(virt);
-		dev_err(dev, "error %d getting SMEM item %u\n", ret, item);
+		dev_err(dev, "error %d getting SMEM item\n", ret);
 		return ret;
 	}
 
 	/* In case the region was already allocated, verify the size */
 	if (ret && actual != size) {
-		dev_err(dev, "SMEM item %u has size %zu, expected %zu\n",
-			item, actual, size);
+		dev_err(dev, "SMEM item has size %zu, expected %zu\n",
+			actual, size);
 		return -EINVAL;
 	}
 
@@ -659,7 +660,7 @@ int ipa_mem_init(struct ipa *ipa, struct platform_device *pdev,
 	if (ret)
 		goto err_unmap;
 
-	ret = ipa_smem_init(ipa, mem_data->smem_id, mem_data->smem_size);
+	ret = ipa_smem_init(ipa, mem_data->smem_size);
 	if (ret)
 		goto err_imem_exit;
 
diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig
index 4a7a303be2f7..7db40aaa079d 100644
--- a/drivers/net/mdio/Kconfig
+++ b/drivers/net/mdio/Kconfig
@@ -3,49 +3,30 @@
 # MDIO Layer Configuration
 #
 
-menuconfig MDIO_DEVICE
-	tristate "MDIO bus device drivers"
-	help
-	  MDIO devices and driver infrastructure code.
-
-if MDIO_DEVICE
-
 config MDIO_BUS
-	tristate
-	default m if PHYLIB=m
-	default MDIO_DEVICE
+	tristate "MDIO bus consumer layer"
 	help
-	  This internal symbol is used for link time dependencies and it
-	  reflects whether the mdio_bus/mdio_device code is built as a
-	  loadable module or built-in.
+	  MDIO bus consumer layer
+
+if PHYLIB
 
 config FWNODE_MDIO
-	def_tristate PHYLIB
-	depends on (ACPI || OF) || COMPILE_TEST
+	def_tristate (ACPI || OF) || COMPILE_TEST
 	select FIXED_PHY
 	help
 	  FWNODE MDIO bus (Ethernet PHY) accessors
 
 config OF_MDIO
-	def_tristate PHYLIB
-	depends on OF
-	depends on PHYLIB
+	def_tristate OF
 	select FIXED_PHY
 	help
 	  OpenFirmware MDIO bus (Ethernet PHY) accessors
 
 config ACPI_MDIO
-	def_tristate PHYLIB
-	depends on ACPI
-	depends on PHYLIB
+	def_tristate ACPI
 	help
 	  ACPI MDIO bus (Ethernet PHY) accessors
 
-if MDIO_BUS
-
-config MDIO_DEVRES
-	tristate
-
 config MDIO_SUN4I
 	tristate "Allwinner sun4i MDIO interface support"
 	depends on ARCH_SUNXI || COMPILE_TEST
@@ -65,7 +46,6 @@ config MDIO_ASPEED
 	tristate "ASPEED MDIO bus controller"
 	depends on ARCH_ASPEED || COMPILE_TEST
 	depends on OF_MDIO && HAS_IOMEM
-	depends on MDIO_DEVRES
 	help
 	  This module provides a driver for the independent MDIO bus
 	  controllers found in the ASPEED AST2600 SoC. This is a driver for the
@@ -135,7 +115,6 @@ config MDIO_I2C
 config MDIO_MVUSB
 	tristate "Marvell USB to MDIO Adapter"
 	depends on USB
-	select MDIO_DEVRES
 	help
 	  A USB to MDIO converter present on development boards for
 	  Marvell's Link Street family of Ethernet switches.
@@ -143,7 +122,6 @@ config MDIO_MVUSB
 config MDIO_MSCC_MIIM
 	tristate "Microsemi MIIM interface support"
 	depends on HAS_IOMEM && REGMAP_MMIO
-	select MDIO_DEVRES
 	help
 	  This driver supports the MIIM (MDIO) interface found in the network
 	  switches of the Microsemi SoCs; it is recommended to switch on
@@ -161,7 +139,6 @@ config MDIO_OCTEON
 	depends on (64BIT && OF_MDIO) || COMPILE_TEST
 	depends on HAS_IOMEM
 	select MDIO_CAVIUM
-	select MDIO_DEVRES
 	help
 	  This module provides a driver for the Octeon and ThunderX MDIO
 	  buses. It is required by the Octeon and ThunderX ethernet device
@@ -171,7 +148,6 @@ config MDIO_IPQ4019
 	tristate "Qualcomm IPQ4019 MDIO interface support"
 	depends on HAS_IOMEM && OF_MDIO
 	depends on COMMON_CLK
-	depends on MDIO_DEVRES
 	help
 	  This driver supports the MDIO interface found in Qualcomm
 	  IPQ40xx, IPQ60xx, IPQ807x and IPQ50xx series Soc-s.
@@ -180,11 +156,17 @@ config MDIO_IPQ8064
 	tristate "Qualcomm IPQ8064 MDIO interface support"
 	depends on HAS_IOMEM && OF_MDIO
 	depends on MFD_SYSCON
-	depends on MDIO_DEVRES
 	help
 	  This driver supports the MDIO interface found in the network
 	  interface units of the IPQ8064 SoC
 
+config MDIO_REALTEK_RTL9300
+	tristate "Realtek RTL9300 MDIO interface support"
+	depends on MACH_REALTEK_RTL || COMPILE_TEST
+	help
+	  This driver supports the MDIO interface found in the Realtek
+	  RTL9300 family of Ethernet switches with integrated SoC.
+
 config MDIO_REGMAP
 	tristate
 	help
@@ -201,7 +183,6 @@ config MDIO_THUNDER
 	depends on 64BIT
 	depends on PCI
 	select MDIO_CAVIUM
-	select MDIO_DEVRES
 	help
 	  This driver supports the MDIO interfaces found on Cavium
 	  ThunderX SoCs when the MDIO bus device appears as a PCI
@@ -299,4 +280,3 @@ config MDIO_BUS_MUX_MMIOREG
 
 
 endif
-endif
diff --git a/drivers/net/mdio/Makefile b/drivers/net/mdio/Makefile
index 1015f0db4531..c23778e73890 100644
--- a/drivers/net/mdio/Makefile
+++ b/drivers/net/mdio/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_MDIO_MOXART)		+= mdio-moxart.o
 obj-$(CONFIG_MDIO_MSCC_MIIM)		+= mdio-mscc-miim.o
 obj-$(CONFIG_MDIO_MVUSB)		+= mdio-mvusb.o
 obj-$(CONFIG_MDIO_OCTEON)		+= mdio-octeon.o
+obj-$(CONFIG_MDIO_REALTEK_RTL9300)	+= mdio-realtek-rtl9300.o
 obj-$(CONFIG_MDIO_REGMAP)		+= mdio-regmap.o
 obj-$(CONFIG_MDIO_SUN4I)		+= mdio-sun4i.o
 obj-$(CONFIG_MDIO_THUNDER)		+= mdio-thunder.o
diff --git a/drivers/net/mdio/mdio-bcm-unimac.c b/drivers/net/mdio/mdio-bcm-unimac.c
index 074d96328f41..b6e30bdf5325 100644
--- a/drivers/net/mdio/mdio-bcm-unimac.c
+++ b/drivers/net/mdio/mdio-bcm-unimac.c
@@ -334,9 +334,9 @@ static SIMPLE_DEV_PM_OPS(unimac_mdio_pm_ops,
 			 NULL, unimac_mdio_resume);
 
 static const struct of_device_id unimac_mdio_ids[] = {
+	{ .compatible = "brcm,asp-v3.0-mdio", },
 	{ .compatible = "brcm,asp-v2.2-mdio", },
 	{ .compatible = "brcm,asp-v2.1-mdio", },
-	{ .compatible = "brcm,asp-v2.0-mdio", },
 	{ .compatible = "brcm,bcm6846-mdio", },
 	{ .compatible = "brcm,genet-mdio-v5", },
 	{ .compatible = "brcm,genet-mdio-v4", },
diff --git a/drivers/net/mdio/mdio-mux-meson-gxl.c b/drivers/net/mdio/mdio-mux-meson-gxl.c
index 00c66240136b..3dd12a8c8b03 100644
--- a/drivers/net/mdio/mdio-mux-meson-gxl.c
+++ b/drivers/net/mdio/mdio-mux-meson-gxl.c
@@ -17,6 +17,7 @@
 #define  REG2_LEDACT		GENMASK(23, 22)
 #define  REG2_LEDLINK		GENMASK(25, 24)
 #define  REG2_DIV4SEL		BIT(27)
+#define  REG2_REVERSED		BIT(28)
 #define  REG2_ADCBYPASS		BIT(30)
 #define  REG2_CLKINSEL		BIT(31)
 #define ETH_REG3		0x4
@@ -65,7 +66,7 @@ static void gxl_enable_internal_mdio(struct gxl_mdio_mux *priv)
 	 * The only constraint is that it must match the one in
 	 * drivers/net/phy/meson-gxl.c to properly match the PHY.
 	 */
-	writel(FIELD_PREP(REG2_PHYID, EPHY_GXL_ID),
+	writel(REG2_REVERSED | FIELD_PREP(REG2_PHYID, EPHY_GXL_ID),
 	       priv->regs + ETH_REG2);
 
 	/* Enable the internal phy */
diff --git a/drivers/net/mdio/mdio-realtek-rtl9300.c b/drivers/net/mdio/mdio-realtek-rtl9300.c
new file mode 100644
index 000000000000..33694c3ff9a7
--- /dev/null
+++ b/drivers/net/mdio/mdio-realtek-rtl9300.c
@@ -0,0 +1,522 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * MDIO controller for RTL9300 switches with integrated SoC.
+ *
+ * The MDIO communication is abstracted by the switch. At the software level
+ * communication uses the switch port to address the PHY. We work out the
+ * mapping based on the MDIO bus described in device tree and phandles on the
+ * ethernet-ports property.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bitmap.h>
+#include <linux/bits.h>
+#include <linux/find.h>
+#include <linux/mdio.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mod_devicetable.h>
+#include <linux/mutex.h>
+#include <linux/of_mdio.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+
+#define SMI_GLB_CTRL			0xca00
+#define   GLB_CTRL_INTF_SEL(intf)	BIT(16 + (intf))
+#define SMI_PORT0_15_POLLING_SEL	0xca08
+#define SMI_ACCESS_PHY_CTRL_0		0xcb70
+#define SMI_ACCESS_PHY_CTRL_1		0xcb74
+#define   PHY_CTRL_REG_ADDR		GENMASK(24, 20)
+#define   PHY_CTRL_PARK_PAGE		GENMASK(19, 15)
+#define   PHY_CTRL_MAIN_PAGE		GENMASK(14, 3)
+#define   PHY_CTRL_WRITE		BIT(2)
+#define   PHY_CTRL_READ			0
+#define   PHY_CTRL_TYPE_C45		BIT(1)
+#define   PHY_CTRL_TYPE_C22		0
+#define   PHY_CTRL_CMD			BIT(0)
+#define   PHY_CTRL_FAIL			BIT(25)
+#define SMI_ACCESS_PHY_CTRL_2		0xcb78
+#define   PHY_CTRL_INDATA		GENMASK(31, 16)
+#define   PHY_CTRL_DATA			GENMASK(15, 0)
+#define SMI_ACCESS_PHY_CTRL_3		0xcb7c
+#define   PHY_CTRL_MMD_DEVAD		GENMASK(20, 16)
+#define   PHY_CTRL_MMD_REG		GENMASK(15, 0)
+#define SMI_PORT0_5_ADDR_CTRL		0xcb80
+
+#define MAX_PORTS       28
+#define MAX_SMI_BUSSES  4
+#define MAX_SMI_ADDR	0x1f
+
+struct rtl9300_mdio_priv {
+	struct regmap *regmap;
+	struct mutex lock; /* protect HW access */
+	DECLARE_BITMAP(valid_ports, MAX_PORTS);
+	u8 smi_bus[MAX_PORTS];
+	u8 smi_addr[MAX_PORTS];
+	bool smi_bus_is_c45[MAX_SMI_BUSSES];
+	struct mii_bus *bus[MAX_SMI_BUSSES];
+};
+
+struct rtl9300_mdio_chan {
+	struct rtl9300_mdio_priv *priv;
+	u8 mdio_bus;
+};
+
+static int rtl9300_mdio_phy_to_port(struct mii_bus *bus, int phy_id)
+{
+	struct rtl9300_mdio_chan *chan = bus->priv;
+	struct rtl9300_mdio_priv *priv;
+	int i;
+
+	priv = chan->priv;
+
+	for_each_set_bit(i, priv->valid_ports, MAX_PORTS)
+		if (priv->smi_bus[i] == chan->mdio_bus &&
+		    priv->smi_addr[i] == phy_id)
+			return i;
+
+	return -ENOENT;
+}
+
+static int rtl9300_mdio_wait_ready(struct rtl9300_mdio_priv *priv)
+{
+	struct regmap *regmap = priv->regmap;
+	u32 val;
+
+	lockdep_assert_held(&priv->lock);
+
+	return regmap_read_poll_timeout(regmap, SMI_ACCESS_PHY_CTRL_1,
+					val, !(val & PHY_CTRL_CMD), 10, 1000);
+}
+
+static int rtl9300_mdio_read_c22(struct mii_bus *bus, int phy_id, int regnum)
+{
+	struct rtl9300_mdio_chan *chan = bus->priv;
+	struct rtl9300_mdio_priv *priv;
+	struct regmap *regmap;
+	int port;
+	u32 val;
+	int err;
+
+	priv = chan->priv;
+	regmap = priv->regmap;
+
+	port = rtl9300_mdio_phy_to_port(bus, phy_id);
+	if (port < 0)
+		return port;
+
+	mutex_lock(&priv->lock);
+	err = rtl9300_mdio_wait_ready(priv);
+	if (err)
+		goto out_err;
+
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_2, FIELD_PREP(PHY_CTRL_INDATA, port));
+	if (err)
+		goto out_err;
+
+	val = FIELD_PREP(PHY_CTRL_REG_ADDR, regnum) |
+	      FIELD_PREP(PHY_CTRL_PARK_PAGE, 0x1f) |
+	      FIELD_PREP(PHY_CTRL_MAIN_PAGE, 0xfff) |
+	      PHY_CTRL_READ | PHY_CTRL_TYPE_C22 | PHY_CTRL_CMD;
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_1, val);
+	if (err)
+		goto out_err;
+
+	err = rtl9300_mdio_wait_ready(priv);
+	if (err)
+		goto out_err;
+
+	err = regmap_read(regmap, SMI_ACCESS_PHY_CTRL_2, &val);
+	if (err)
+		goto out_err;
+
+	mutex_unlock(&priv->lock);
+	return FIELD_GET(PHY_CTRL_DATA, val);
+
+out_err:
+	mutex_unlock(&priv->lock);
+	return err;
+}
+
+static int rtl9300_mdio_write_c22(struct mii_bus *bus, int phy_id, int regnum, u16 value)
+{
+	struct rtl9300_mdio_chan *chan = bus->priv;
+	struct rtl9300_mdio_priv *priv;
+	struct regmap *regmap;
+	int port;
+	u32 val;
+	int err;
+
+	priv = chan->priv;
+	regmap = priv->regmap;
+
+	port = rtl9300_mdio_phy_to_port(bus, phy_id);
+	if (port < 0)
+		return port;
+
+	mutex_lock(&priv->lock);
+	err = rtl9300_mdio_wait_ready(priv);
+	if (err)
+		goto out_err;
+
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_0, BIT(port));
+	if (err)
+		goto out_err;
+
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_2, FIELD_PREP(PHY_CTRL_INDATA, value));
+	if (err)
+		goto out_err;
+
+	val = FIELD_PREP(PHY_CTRL_REG_ADDR, regnum) |
+	      FIELD_PREP(PHY_CTRL_PARK_PAGE, 0x1f) |
+	      FIELD_PREP(PHY_CTRL_MAIN_PAGE, 0xfff) |
+	      PHY_CTRL_WRITE | PHY_CTRL_TYPE_C22 | PHY_CTRL_CMD;
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_1, val);
+	if (err)
+		goto out_err;
+
+	err = regmap_read_poll_timeout(regmap, SMI_ACCESS_PHY_CTRL_1,
+				       val, !(val & PHY_CTRL_CMD), 10, 100);
+	if (err)
+		goto out_err;
+
+	if (val & PHY_CTRL_FAIL) {
+		err = -ENXIO;
+		goto out_err;
+	}
+
+	mutex_unlock(&priv->lock);
+	return 0;
+
+out_err:
+	mutex_unlock(&priv->lock);
+	return err;
+}
+
+static int rtl9300_mdio_read_c45(struct mii_bus *bus, int phy_id, int dev_addr, int regnum)
+{
+	struct rtl9300_mdio_chan *chan = bus->priv;
+	struct rtl9300_mdio_priv *priv;
+	struct regmap *regmap;
+	int port;
+	u32 val;
+	int err;
+
+	priv = chan->priv;
+	regmap = priv->regmap;
+
+	port = rtl9300_mdio_phy_to_port(bus, phy_id);
+	if (port < 0)
+		return port;
+
+	mutex_lock(&priv->lock);
+	err = rtl9300_mdio_wait_ready(priv);
+	if (err)
+		goto out_err;
+
+	val = FIELD_PREP(PHY_CTRL_INDATA, port);
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_2, val);
+	if (err)
+		goto out_err;
+
+	val = FIELD_PREP(PHY_CTRL_MMD_DEVAD, dev_addr) |
+	      FIELD_PREP(PHY_CTRL_MMD_REG, regnum);
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_3, val);
+	if (err)
+		goto out_err;
+
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_1,
+			   PHY_CTRL_READ | PHY_CTRL_TYPE_C45 | PHY_CTRL_CMD);
+	if (err)
+		goto out_err;
+
+	err = rtl9300_mdio_wait_ready(priv);
+	if (err)
+		goto out_err;
+
+	err = regmap_read(regmap, SMI_ACCESS_PHY_CTRL_2, &val);
+	if (err)
+		goto out_err;
+
+	mutex_unlock(&priv->lock);
+	return FIELD_GET(PHY_CTRL_DATA, val);
+
+out_err:
+	mutex_unlock(&priv->lock);
+	return err;
+}
+
+static int rtl9300_mdio_write_c45(struct mii_bus *bus, int phy_id, int dev_addr,
+				  int regnum, u16 value)
+{
+	struct rtl9300_mdio_chan *chan = bus->priv;
+	struct rtl9300_mdio_priv *priv;
+	struct regmap *regmap;
+	int port;
+	u32 val;
+	int err;
+
+	priv = chan->priv;
+	regmap = priv->regmap;
+
+	port = rtl9300_mdio_phy_to_port(bus, phy_id);
+	if (port < 0)
+		return port;
+
+	mutex_lock(&priv->lock);
+	err = rtl9300_mdio_wait_ready(priv);
+	if (err)
+		goto out_err;
+
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_0, BIT(port));
+	if (err)
+		goto out_err;
+
+	val = FIELD_PREP(PHY_CTRL_INDATA, value);
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_2, val);
+	if (err)
+		goto out_err;
+
+	val = FIELD_PREP(PHY_CTRL_MMD_DEVAD, dev_addr) |
+	      FIELD_PREP(PHY_CTRL_MMD_REG, regnum);
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_3, val);
+	if (err)
+		goto out_err;
+
+	err = regmap_write(regmap, SMI_ACCESS_PHY_CTRL_1,
+			   PHY_CTRL_TYPE_C45 | PHY_CTRL_WRITE | PHY_CTRL_CMD);
+	if (err)
+		goto out_err;
+
+	err = regmap_read_poll_timeout(regmap, SMI_ACCESS_PHY_CTRL_1,
+				       val, !(val & PHY_CTRL_CMD), 10, 100);
+	if (err)
+		goto out_err;
+
+	if (val & PHY_CTRL_FAIL) {
+		err = -ENXIO;
+		goto out_err;
+	}
+
+	mutex_unlock(&priv->lock);
+	return 0;
+
+out_err:
+	mutex_unlock(&priv->lock);
+	return err;
+}
+
+static int rtl9300_mdiobus_init(struct rtl9300_mdio_priv *priv)
+{
+	u32 glb_ctrl_mask = 0, glb_ctrl_val = 0;
+	struct regmap *regmap = priv->regmap;
+	u32 port_addr[5] = { 0 };
+	u32 poll_sel[2] = { 0 };
+	int i, err;
+
+	/* Associate the port with the SMI interface and PHY */
+	for_each_set_bit(i, priv->valid_ports, MAX_PORTS) {
+		int pos;
+
+		pos = (i % 6) * 5;
+		port_addr[i / 6] |= (priv->smi_addr[i] & 0x1f) << pos;
+
+		pos = (i % 16) * 2;
+		poll_sel[i / 16] |= (priv->smi_bus[i] & 0x3) << pos;
+	}
+
+	/* Put the interfaces into C45 mode if required */
+	glb_ctrl_mask = GENMASK(19, 16);
+	for (i = 0; i < MAX_SMI_BUSSES; i++)
+		if (priv->smi_bus_is_c45[i])
+			glb_ctrl_val |= GLB_CTRL_INTF_SEL(i);
+
+	err = regmap_bulk_write(regmap, SMI_PORT0_5_ADDR_CTRL,
+				port_addr, 5);
+	if (err)
+		return err;
+
+	err = regmap_bulk_write(regmap, SMI_PORT0_15_POLLING_SEL,
+				poll_sel, 2);
+	if (err)
+		return err;
+
+	err = regmap_update_bits(regmap, SMI_GLB_CTRL,
+				 glb_ctrl_mask, glb_ctrl_val);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int rtl9300_mdiobus_probe_one(struct device *dev, struct rtl9300_mdio_priv *priv,
+				     struct fwnode_handle *node)
+{
+	struct rtl9300_mdio_chan *chan;
+	struct fwnode_handle *child;
+	struct mii_bus *bus;
+	u32 mdio_bus;
+	int err;
+
+	err = fwnode_property_read_u32(node, "reg", &mdio_bus);
+	if (err)
+		return err;
+
+	/* The MDIO accesses from the kernel work with the PHY polling unit in
+	 * the switch. We need to tell the PPU to operate either in GPHY (i.e.
+	 * clause 22) or 10GPHY mode (i.e. clause 45).
+	 *
+	 * We select 10GPHY mode if there is at least one PHY that declares
+	 * compatible = "ethernet-phy-ieee802.3-c45". This does mean we can't
+	 * support both c45 and c22 on the same MDIO bus.
+	 */
+	fwnode_for_each_child_node(node, child)
+		if (fwnode_device_is_compatible(child, "ethernet-phy-ieee802.3-c45"))
+			priv->smi_bus_is_c45[mdio_bus] = true;
+
+	bus = devm_mdiobus_alloc_size(dev, sizeof(*chan));
+	if (!bus)
+		return -ENOMEM;
+
+	bus->name = "Realtek Switch MDIO Bus";
+	if (priv->smi_bus_is_c45[mdio_bus]) {
+		bus->read_c45 = rtl9300_mdio_read_c45;
+		bus->write_c45 =  rtl9300_mdio_write_c45;
+	} else {
+		bus->read = rtl9300_mdio_read_c22;
+		bus->write = rtl9300_mdio_write_c22;
+	}
+	bus->parent = dev;
+	chan = bus->priv;
+	chan->mdio_bus = mdio_bus;
+	chan->priv = priv;
+
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d", dev_name(dev), mdio_bus);
+
+	err = devm_of_mdiobus_register(dev, bus, to_of_node(node));
+	if (err)
+		return dev_err_probe(dev, err, "cannot register MDIO bus\n");
+
+	return 0;
+}
+
+/* The mdio-controller is part of a switch block so we parse the sibling
+ * ethernet-ports node and build a mapping of the switch port to MDIO bus/addr
+ * based on the phy-handle.
+ */
+static int rtl9300_mdiobus_map_ports(struct device *dev)
+{
+	struct rtl9300_mdio_priv *priv = dev_get_drvdata(dev);
+	struct device *parent = dev->parent;
+	struct fwnode_handle *port;
+	int err;
+
+	struct fwnode_handle *ports __free(fwnode_handle) =
+		device_get_named_child_node(parent, "ethernet-ports");
+	if (!ports)
+		return dev_err_probe(dev, -EINVAL, "%pfwP missing ethernet-ports\n",
+				     dev_fwnode(parent));
+
+	fwnode_for_each_child_node(ports, port) {
+		struct device_node *mdio_dn;
+		u32 addr;
+		u32 bus;
+		u32 pn;
+
+		struct device_node *phy_dn __free(device_node) =
+			of_parse_phandle(to_of_node(port), "phy-handle", 0);
+		/* skip ports without phys */
+		if (!phy_dn)
+			continue;
+
+		mdio_dn = phy_dn->parent;
+		/* only map ports that are connected to this mdio-controller */
+		if (mdio_dn->parent != dev->of_node)
+			continue;
+
+		err = fwnode_property_read_u32(port, "reg", &pn);
+		if (err)
+			return err;
+
+		if (pn >= MAX_PORTS)
+			return dev_err_probe(dev, -EINVAL, "illegal port number %d\n", pn);
+
+		if (test_bit(pn, priv->valid_ports))
+			return dev_err_probe(dev, -EINVAL, "duplicated port number %d\n", pn);
+
+		err = of_property_read_u32(mdio_dn, "reg", &bus);
+		if (err)
+			return err;
+
+		if (bus >= MAX_SMI_BUSSES)
+			return dev_err_probe(dev, -EINVAL, "illegal smi bus number %d\n", bus);
+
+		err = of_property_read_u32(phy_dn, "reg", &addr);
+		if (err)
+			return err;
+
+		__set_bit(pn, priv->valid_ports);
+		priv->smi_bus[pn] = bus;
+		priv->smi_addr[pn] = addr;
+	}
+
+	return 0;
+}
+
+static int rtl9300_mdiobus_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rtl9300_mdio_priv *priv;
+	struct fwnode_handle *child;
+	int err;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	err = devm_mutex_init(dev, &priv->lock);
+	if (err)
+		return err;
+
+	priv->regmap = syscon_node_to_regmap(dev->parent->of_node);
+	if (IS_ERR(priv->regmap))
+		return PTR_ERR(priv->regmap);
+
+	platform_set_drvdata(pdev, priv);
+
+	err = rtl9300_mdiobus_map_ports(dev);
+	if (err)
+		return err;
+
+	device_for_each_child_node(dev, child) {
+		err = rtl9300_mdiobus_probe_one(dev, priv, child);
+		if (err)
+			return err;
+	}
+
+	err = rtl9300_mdiobus_init(priv);
+	if (err)
+		return dev_err_probe(dev, err, "failed to initialise MDIO bus controller\n");
+
+	return 0;
+}
+
+static const struct of_device_id rtl9300_mdio_ids[] = {
+	{ .compatible = "realtek,rtl9301-mdio" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, rtl9300_mdio_ids);
+
+static struct platform_driver rtl9300_mdio_driver = {
+	.probe = rtl9300_mdiobus_probe,
+	.driver = {
+		.name = "mdio-rtl9300",
+		.of_match_table = rtl9300_mdio_ids,
+	},
+};
+
+module_platform_driver(rtl9300_mdio_driver);
+
+MODULE_DESCRIPTION("RTL9300 MDIO driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/mdio/mdio-thunder.c b/drivers/net/mdio/mdio-thunder.c
index 1e1aa72b1eff..a3047f7258a7 100644
--- a/drivers/net/mdio/mdio-thunder.c
+++ b/drivers/net/mdio/mdio-thunder.c
@@ -40,16 +40,16 @@ static int thunder_mdiobus_pci_probe(struct pci_dev *pdev,
 		return err;
 	}
 
-	err = pci_request_regions(pdev, KBUILD_MODNAME);
+	err = pcim_request_all_regions(pdev, KBUILD_MODNAME);
 	if (err) {
-		dev_err(&pdev->dev, "pci_request_regions failed\n");
+		dev_err(&pdev->dev, "pcim_request_all_regions failed\n");
 		goto err_disable_device;
 	}
 
 	nexus->bar0 = pcim_iomap(pdev, 0, pci_resource_len(pdev, 0));
 	if (!nexus->bar0) {
 		err = -ENOMEM;
-		goto err_release_regions;
+		goto err_disable_device;
 	}
 
 	i = 0;
@@ -107,9 +107,6 @@ static int thunder_mdiobus_pci_probe(struct pci_dev *pdev,
 	}
 	return 0;
 
-err_release_regions:
-	pci_release_regions(pdev);
-
 err_disable_device:
 	pci_set_drvdata(pdev, NULL);
 	return err;
@@ -129,7 +126,6 @@ static void thunder_mdiobus_pci_remove(struct pci_dev *pdev)
 		mdiobus_unregister(bus->mii_bus);
 		oct_mdio_writeq(0, bus->register_base + SMI_EN);
 	}
-	pci_release_regions(pdev);
 	pci_set_drvdata(pdev, NULL);
 }
 
diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c
index 2f4fc664d2e1..98f667b121f7 100644
--- a/drivers/net/mdio/of_mdio.c
+++ b/drivers/net/mdio/of_mdio.c
@@ -458,7 +458,7 @@ int of_phy_register_fixed_link(struct device_node *np)
 	return -ENODEV;
 
 register_phy:
-	return PTR_ERR_OR_ZERO(fixed_phy_register(PHY_POLL, &status, np));
+	return PTR_ERR_OR_ZERO(fixed_phy_register(&status, np));
 }
 EXPORT_SYMBOL(of_phy_register_fixed_link);
 
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 0e0321a7ddd7..af545d42961c 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -29,6 +29,7 @@
 #include <net/pkt_cls.h>
 #include <net/rtnetlink.h>
 #include <net/udp_tunnel.h>
+#include <net/busy_poll.h>
 
 #include "netdevsim.h"
 
@@ -357,6 +358,7 @@ static int nsim_rcv(struct nsim_rq *rq, int budget)
 			break;
 
 		skb = skb_dequeue(&rq->skb_queue);
+		skb_mark_napi_id(skb, &rq->napi);
 		netif_receive_skb(skb);
 	}
 
@@ -879,11 +881,13 @@ static void nsim_setup(struct net_device *dev)
 			 NETIF_F_SG |
 			 NETIF_F_FRAGLIST |
 			 NETIF_F_HW_CSUM |
+			 NETIF_F_LRO |
 			 NETIF_F_TSO;
 	dev->hw_features |= NETIF_F_HW_TC |
 			    NETIF_F_SG |
 			    NETIF_F_FRAGLIST |
 			    NETIF_F_HW_CSUM |
+			    NETIF_F_LRO |
 			    NETIF_F_TSO;
 	dev->max_mtu = ETH_MAX_MTU;
 	dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD;
diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile
new file mode 100644
index 000000000000..229be66167e1
--- /dev/null
+++ b/drivers/net/ovpn/Makefile
@@ -0,0 +1,22 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# ovpn -- OpenVPN data channel offload in kernel space
+#
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+# Author:	Antonio Quartulli <antonio@openvpn.net>
+
+obj-$(CONFIG_OVPN) := ovpn.o
+ovpn-y += bind.o
+ovpn-y += crypto.o
+ovpn-y += crypto_aead.o
+ovpn-y += main.o
+ovpn-y += io.o
+ovpn-y += netlink.o
+ovpn-y += netlink-gen.o
+ovpn-y += peer.o
+ovpn-y += pktid.o
+ovpn-y += socket.o
+ovpn-y += stats.o
+ovpn-y += tcp.o
+ovpn-y += udp.o
diff --git a/drivers/net/ovpn/bind.c b/drivers/net/ovpn/bind.c
new file mode 100644
index 000000000000..24d2788a277e
--- /dev/null
+++ b/drivers/net/ovpn/bind.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2012-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/socket.h>
+
+#include "ovpnpriv.h"
+#include "bind.h"
+#include "peer.h"
+
+/**
+ * ovpn_bind_from_sockaddr - retrieve binding matching sockaddr
+ * @ss: the sockaddr to match
+ *
+ * Return: the bind matching the passed sockaddr if found, NULL otherwise
+ */
+struct ovpn_bind *ovpn_bind_from_sockaddr(const struct sockaddr_storage *ss)
+{
+	struct ovpn_bind *bind;
+	size_t sa_len;
+
+	if (ss->ss_family == AF_INET)
+		sa_len = sizeof(struct sockaddr_in);
+	else if (ss->ss_family == AF_INET6)
+		sa_len = sizeof(struct sockaddr_in6);
+	else
+		return ERR_PTR(-EAFNOSUPPORT);
+
+	bind = kzalloc(sizeof(*bind), GFP_ATOMIC);
+	if (unlikely(!bind))
+		return ERR_PTR(-ENOMEM);
+
+	memcpy(&bind->remote, ss, sa_len);
+
+	return bind;
+}
+
+/**
+ * ovpn_bind_reset - assign new binding to peer
+ * @peer: the peer whose binding has to be replaced
+ * @new: the new bind to assign
+ */
+void ovpn_bind_reset(struct ovpn_peer *peer, struct ovpn_bind *new)
+{
+	lockdep_assert_held(&peer->lock);
+
+	kfree_rcu(rcu_replace_pointer(peer->bind, new,
+				      lockdep_is_held(&peer->lock)), rcu);
+}
diff --git a/drivers/net/ovpn/bind.h b/drivers/net/ovpn/bind.h
new file mode 100644
index 000000000000..4e0b8398bfd9
--- /dev/null
+++ b/drivers/net/ovpn/bind.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2012-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNBIND_H_
+#define _NET_OVPN_OVPNBIND_H_
+
+#include <net/ip.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/rcupdate.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+
+struct ovpn_peer;
+
+/**
+ * union ovpn_sockaddr - basic transport layer address
+ * @in4: IPv4 address
+ * @in6: IPv6 address
+ */
+union ovpn_sockaddr {
+	struct sockaddr_in in4;
+	struct sockaddr_in6 in6;
+};
+
+/**
+ * struct ovpn_bind - remote peer binding
+ * @remote: the remote peer sockaddress
+ * @local: local endpoint used to talk to the peer
+ * @local.ipv4: local IPv4 used to talk to the peer
+ * @local.ipv6: local IPv6 used to talk to the peer
+ * @rcu: used to schedule RCU cleanup job
+ */
+struct ovpn_bind {
+	union ovpn_sockaddr remote;  /* remote sockaddr */
+
+	union {
+		struct in_addr ipv4;
+		struct in6_addr ipv6;
+	} local;
+
+	struct rcu_head rcu;
+};
+
+/**
+ * ovpn_bind_skb_src_match - match packet source with binding
+ * @bind: the binding to match
+ * @skb: the packet to match
+ *
+ * Return: true if the packet source matches the remote peer sockaddr
+ * in the binding
+ */
+static inline bool ovpn_bind_skb_src_match(const struct ovpn_bind *bind,
+					   const struct sk_buff *skb)
+{
+	const union ovpn_sockaddr *remote;
+
+	if (unlikely(!bind))
+		return false;
+
+	remote = &bind->remote;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		if (unlikely(remote->in4.sin_family != AF_INET))
+			return false;
+
+		if (unlikely(remote->in4.sin_addr.s_addr != ip_hdr(skb)->saddr))
+			return false;
+
+		if (unlikely(remote->in4.sin_port != udp_hdr(skb)->source))
+			return false;
+		break;
+	case htons(ETH_P_IPV6):
+		if (unlikely(remote->in6.sin6_family != AF_INET6))
+			return false;
+
+		if (unlikely(!ipv6_addr_equal(&remote->in6.sin6_addr,
+					      &ipv6_hdr(skb)->saddr)))
+			return false;
+
+		if (unlikely(remote->in6.sin6_port != udp_hdr(skb)->source))
+			return false;
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+struct ovpn_bind *ovpn_bind_from_sockaddr(const struct sockaddr_storage *sa);
+void ovpn_bind_reset(struct ovpn_peer *peer, struct ovpn_bind *bind);
+
+#endif /* _NET_OVPN_OVPNBIND_H_ */
diff --git a/drivers/net/ovpn/crypto.c b/drivers/net/ovpn/crypto.c
new file mode 100644
index 000000000000..90580e32052f
--- /dev/null
+++ b/drivers/net/ovpn/crypto.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/types.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <uapi/linux/ovpn.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "pktid.h"
+#include "crypto_aead.h"
+#include "crypto.h"
+
+static void ovpn_ks_destroy_rcu(struct rcu_head *head)
+{
+	struct ovpn_crypto_key_slot *ks;
+
+	ks = container_of(head, struct ovpn_crypto_key_slot, rcu);
+	ovpn_aead_crypto_key_slot_destroy(ks);
+}
+
+void ovpn_crypto_key_slot_release(struct kref *kref)
+{
+	struct ovpn_crypto_key_slot *ks;
+
+	ks = container_of(kref, struct ovpn_crypto_key_slot, refcount);
+	call_rcu(&ks->rcu, ovpn_ks_destroy_rcu);
+}
+
+/* can only be invoked when all peer references have been dropped (i.e. RCU
+ * release routine)
+ */
+void ovpn_crypto_state_release(struct ovpn_crypto_state *cs)
+{
+	struct ovpn_crypto_key_slot *ks;
+
+	ks = rcu_access_pointer(cs->slots[0]);
+	if (ks) {
+		RCU_INIT_POINTER(cs->slots[0], NULL);
+		ovpn_crypto_key_slot_put(ks);
+	}
+
+	ks = rcu_access_pointer(cs->slots[1]);
+	if (ks) {
+		RCU_INIT_POINTER(cs->slots[1], NULL);
+		ovpn_crypto_key_slot_put(ks);
+	}
+}
+
+/* removes the key matching the specified id from the crypto context */
+bool ovpn_crypto_kill_key(struct ovpn_crypto_state *cs, u8 key_id)
+{
+	struct ovpn_crypto_key_slot *ks = NULL;
+
+	spin_lock_bh(&cs->lock);
+	if (rcu_access_pointer(cs->slots[0])->key_id == key_id) {
+		ks = rcu_replace_pointer(cs->slots[0], NULL,
+					 lockdep_is_held(&cs->lock));
+	} else if (rcu_access_pointer(cs->slots[1])->key_id == key_id) {
+		ks = rcu_replace_pointer(cs->slots[1], NULL,
+					 lockdep_is_held(&cs->lock));
+	}
+	spin_unlock_bh(&cs->lock);
+
+	if (ks)
+		ovpn_crypto_key_slot_put(ks);
+
+	/* let the caller know if a key was actually killed */
+	return ks;
+}
+
+/* Reset the ovpn_crypto_state object in a way that is atomic
+ * to RCU readers.
+ */
+int ovpn_crypto_state_reset(struct ovpn_crypto_state *cs,
+			    const struct ovpn_peer_key_reset *pkr)
+{
+	struct ovpn_crypto_key_slot *old = NULL, *new;
+	u8 idx;
+
+	if (pkr->slot != OVPN_KEY_SLOT_PRIMARY &&
+	    pkr->slot != OVPN_KEY_SLOT_SECONDARY)
+		return -EINVAL;
+
+	new = ovpn_aead_crypto_key_slot_new(&pkr->key);
+	if (IS_ERR(new))
+		return PTR_ERR(new);
+
+	spin_lock_bh(&cs->lock);
+	idx = cs->primary_idx;
+	switch (pkr->slot) {
+	case OVPN_KEY_SLOT_PRIMARY:
+		old = rcu_replace_pointer(cs->slots[idx], new,
+					  lockdep_is_held(&cs->lock));
+		break;
+	case OVPN_KEY_SLOT_SECONDARY:
+		old = rcu_replace_pointer(cs->slots[!idx], new,
+					  lockdep_is_held(&cs->lock));
+		break;
+	}
+	spin_unlock_bh(&cs->lock);
+
+	if (old)
+		ovpn_crypto_key_slot_put(old);
+
+	return 0;
+}
+
+void ovpn_crypto_key_slot_delete(struct ovpn_crypto_state *cs,
+				 enum ovpn_key_slot slot)
+{
+	struct ovpn_crypto_key_slot *ks = NULL;
+	u8 idx;
+
+	if (slot != OVPN_KEY_SLOT_PRIMARY &&
+	    slot != OVPN_KEY_SLOT_SECONDARY) {
+		pr_warn("Invalid slot to release: %u\n", slot);
+		return;
+	}
+
+	spin_lock_bh(&cs->lock);
+	idx = cs->primary_idx;
+	switch (slot) {
+	case OVPN_KEY_SLOT_PRIMARY:
+		ks = rcu_replace_pointer(cs->slots[idx], NULL,
+					 lockdep_is_held(&cs->lock));
+		break;
+	case OVPN_KEY_SLOT_SECONDARY:
+		ks = rcu_replace_pointer(cs->slots[!idx], NULL,
+					 lockdep_is_held(&cs->lock));
+		break;
+	}
+	spin_unlock_bh(&cs->lock);
+
+	if (!ks) {
+		pr_debug("Key slot already released: %u\n", slot);
+		return;
+	}
+
+	pr_debug("deleting key slot %u, key_id=%u\n", slot, ks->key_id);
+	ovpn_crypto_key_slot_put(ks);
+}
+
+void ovpn_crypto_key_slots_swap(struct ovpn_crypto_state *cs)
+{
+	const struct ovpn_crypto_key_slot *old_primary, *old_secondary;
+	u8 idx;
+
+	spin_lock_bh(&cs->lock);
+	idx = cs->primary_idx;
+	old_primary = rcu_dereference_protected(cs->slots[idx],
+						lockdep_is_held(&cs->lock));
+	old_secondary = rcu_dereference_protected(cs->slots[!idx],
+						  lockdep_is_held(&cs->lock));
+	/* perform real swap by switching the index of the primary key */
+	WRITE_ONCE(cs->primary_idx, !cs->primary_idx);
+
+	pr_debug("key swapped: (old primary) %d <-> (new primary) %d\n",
+		 old_primary ? old_primary->key_id : -1,
+		 old_secondary ? old_secondary->key_id : -1);
+
+	spin_unlock_bh(&cs->lock);
+}
+
+/**
+ * ovpn_crypto_config_get - populate keyconf object with non-sensible key data
+ * @cs: the crypto state to extract the key data from
+ * @slot: the specific slot to inspect
+ * @keyconf: the output object to populate
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_crypto_config_get(struct ovpn_crypto_state *cs,
+			   enum ovpn_key_slot slot,
+			   struct ovpn_key_config *keyconf)
+{
+	struct ovpn_crypto_key_slot *ks;
+	int idx;
+
+	switch (slot) {
+	case OVPN_KEY_SLOT_PRIMARY:
+		idx = cs->primary_idx;
+		break;
+	case OVPN_KEY_SLOT_SECONDARY:
+		idx = !cs->primary_idx;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rcu_read_lock();
+	ks = rcu_dereference(cs->slots[idx]);
+	if (!ks) {
+		rcu_read_unlock();
+		return -ENOENT;
+	}
+
+	keyconf->cipher_alg = ovpn_aead_crypto_alg(ks);
+	keyconf->key_id = ks->key_id;
+	rcu_read_unlock();
+
+	return 0;
+}
diff --git a/drivers/net/ovpn/crypto.h b/drivers/net/ovpn/crypto.h
new file mode 100644
index 000000000000..0e284fec3a75
--- /dev/null
+++ b/drivers/net/ovpn/crypto.h
@@ -0,0 +1,145 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNCRYPTO_H_
+#define _NET_OVPN_OVPNCRYPTO_H_
+
+#include "pktid.h"
+#include "proto.h"
+
+/* info needed for both encrypt and decrypt directions */
+struct ovpn_key_direction {
+	const u8 *cipher_key;
+	size_t cipher_key_size;
+	const u8 *nonce_tail; /* only needed for GCM modes */
+	size_t nonce_tail_size; /* only needed for GCM modes */
+};
+
+/* all info for a particular symmetric key (primary or secondary) */
+struct ovpn_key_config {
+	enum ovpn_cipher_alg cipher_alg;
+	u8 key_id;
+	struct ovpn_key_direction encrypt;
+	struct ovpn_key_direction decrypt;
+};
+
+/* used to pass settings from netlink to the crypto engine */
+struct ovpn_peer_key_reset {
+	enum ovpn_key_slot slot;
+	struct ovpn_key_config key;
+};
+
+struct ovpn_crypto_key_slot {
+	u8 key_id;
+
+	struct crypto_aead *encrypt;
+	struct crypto_aead *decrypt;
+	u8 nonce_tail_xmit[OVPN_NONCE_TAIL_SIZE];
+	u8 nonce_tail_recv[OVPN_NONCE_TAIL_SIZE];
+
+	struct ovpn_pktid_recv pid_recv ____cacheline_aligned_in_smp;
+	struct ovpn_pktid_xmit pid_xmit ____cacheline_aligned_in_smp;
+	struct kref refcount;
+	struct rcu_head rcu;
+};
+
+struct ovpn_crypto_state {
+	struct ovpn_crypto_key_slot __rcu *slots[2];
+	u8 primary_idx;
+
+	/* protects primary and secondary slots */
+	spinlock_t lock;
+};
+
+static inline bool ovpn_crypto_key_slot_hold(struct ovpn_crypto_key_slot *ks)
+{
+	return kref_get_unless_zero(&ks->refcount);
+}
+
+static inline void ovpn_crypto_state_init(struct ovpn_crypto_state *cs)
+{
+	RCU_INIT_POINTER(cs->slots[0], NULL);
+	RCU_INIT_POINTER(cs->slots[1], NULL);
+	cs->primary_idx = 0;
+	spin_lock_init(&cs->lock);
+}
+
+static inline struct ovpn_crypto_key_slot *
+ovpn_crypto_key_id_to_slot(const struct ovpn_crypto_state *cs, u8 key_id)
+{
+	struct ovpn_crypto_key_slot *ks;
+	u8 idx;
+
+	if (unlikely(!cs))
+		return NULL;
+
+	rcu_read_lock();
+	idx = READ_ONCE(cs->primary_idx);
+	ks = rcu_dereference(cs->slots[idx]);
+	if (ks && ks->key_id == key_id) {
+		if (unlikely(!ovpn_crypto_key_slot_hold(ks)))
+			ks = NULL;
+		goto out;
+	}
+
+	ks = rcu_dereference(cs->slots[!idx]);
+	if (ks && ks->key_id == key_id) {
+		if (unlikely(!ovpn_crypto_key_slot_hold(ks)))
+			ks = NULL;
+		goto out;
+	}
+
+	/* when both key slots are occupied but no matching key ID is found, ks
+	 * has to be reset to NULL to avoid carrying a stale pointer
+	 */
+	ks = NULL;
+out:
+	rcu_read_unlock();
+
+	return ks;
+}
+
+static inline struct ovpn_crypto_key_slot *
+ovpn_crypto_key_slot_primary(const struct ovpn_crypto_state *cs)
+{
+	struct ovpn_crypto_key_slot *ks;
+
+	rcu_read_lock();
+	ks = rcu_dereference(cs->slots[cs->primary_idx]);
+	if (unlikely(ks && !ovpn_crypto_key_slot_hold(ks)))
+		ks = NULL;
+	rcu_read_unlock();
+
+	return ks;
+}
+
+void ovpn_crypto_key_slot_release(struct kref *kref);
+
+static inline void ovpn_crypto_key_slot_put(struct ovpn_crypto_key_slot *ks)
+{
+	kref_put(&ks->refcount, ovpn_crypto_key_slot_release);
+}
+
+int ovpn_crypto_state_reset(struct ovpn_crypto_state *cs,
+			    const struct ovpn_peer_key_reset *pkr);
+
+void ovpn_crypto_key_slot_delete(struct ovpn_crypto_state *cs,
+				 enum ovpn_key_slot slot);
+
+void ovpn_crypto_state_release(struct ovpn_crypto_state *cs);
+
+void ovpn_crypto_key_slots_swap(struct ovpn_crypto_state *cs);
+
+int ovpn_crypto_config_get(struct ovpn_crypto_state *cs,
+			   enum ovpn_key_slot slot,
+			   struct ovpn_key_config *keyconf);
+
+bool ovpn_crypto_kill_key(struct ovpn_crypto_state *cs, u8 key_id);
+
+#endif /* _NET_OVPN_OVPNCRYPTO_H_ */
diff --git a/drivers/net/ovpn/crypto_aead.c b/drivers/net/ovpn/crypto_aead.c
new file mode 100644
index 000000000000..2cca759feffa
--- /dev/null
+++ b/drivers/net/ovpn/crypto_aead.c
@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <crypto/aead.h>
+#include <linux/skbuff.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/udp.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "io.h"
+#include "pktid.h"
+#include "crypto_aead.h"
+#include "crypto.h"
+#include "peer.h"
+#include "proto.h"
+#include "skb.h"
+
+#define OVPN_AUTH_TAG_SIZE	16
+#define OVPN_AAD_SIZE		(OVPN_OPCODE_SIZE + OVPN_NONCE_WIRE_SIZE)
+
+#define ALG_NAME_AES		"gcm(aes)"
+#define ALG_NAME_CHACHAPOLY	"rfc7539(chacha20,poly1305)"
+
+static int ovpn_aead_encap_overhead(const struct ovpn_crypto_key_slot *ks)
+{
+	return  OVPN_OPCODE_SIZE +			/* OP header size */
+		sizeof(u32) +				/* Packet ID */
+		crypto_aead_authsize(ks->encrypt);	/* Auth Tag */
+}
+
+int ovpn_aead_encrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks,
+		      struct sk_buff *skb)
+{
+	const unsigned int tag_size = crypto_aead_authsize(ks->encrypt);
+	struct aead_request *req;
+	struct sk_buff *trailer;
+	struct scatterlist *sg;
+	int nfrags, ret;
+	u32 pktid, op;
+	u8 *iv;
+
+	ovpn_skb_cb(skb)->peer = peer;
+	ovpn_skb_cb(skb)->ks = ks;
+
+	/* Sample AEAD header format:
+	 * 48000001 00000005 7e7046bd 444a7e28 cc6387b1 64a4d6c1 380275a...
+	 * [ OP32 ] [seq # ] [             auth tag            ] [ payload ... ]
+	 *          [4-byte
+	 *          IV head]
+	 */
+
+	/* check that there's enough headroom in the skb for packet
+	 * encapsulation
+	 */
+	if (unlikely(skb_cow_head(skb, OVPN_HEAD_ROOM)))
+		return -ENOBUFS;
+
+	/* get number of skb frags and ensure that packet data is writable */
+	nfrags = skb_cow_data(skb, 0, &trailer);
+	if (unlikely(nfrags < 0))
+		return nfrags;
+
+	if (unlikely(nfrags + 2 > (MAX_SKB_FRAGS + 2)))
+		return -ENOSPC;
+
+	/* sg may be required by async crypto */
+	ovpn_skb_cb(skb)->sg = kmalloc(sizeof(*ovpn_skb_cb(skb)->sg) *
+				       (nfrags + 2), GFP_ATOMIC);
+	if (unlikely(!ovpn_skb_cb(skb)->sg))
+		return -ENOMEM;
+
+	sg = ovpn_skb_cb(skb)->sg;
+
+	/* sg table:
+	 * 0: op, wire nonce (AD, len=OVPN_OP_SIZE_V2+OVPN_NONCE_WIRE_SIZE),
+	 * 1, 2, 3, ..., n: payload,
+	 * n+1: auth_tag (len=tag_size)
+	 */
+	sg_init_table(sg, nfrags + 2);
+
+	/* build scatterlist to encrypt packet payload */
+	ret = skb_to_sgvec_nomark(skb, sg + 1, 0, skb->len);
+	if (unlikely(ret < 0)) {
+		netdev_err(peer->ovpn->dev,
+			   "encrypt: cannot map skb to sg: %d\n", ret);
+		return ret;
+	}
+
+	/* append auth_tag onto scatterlist */
+	__skb_push(skb, tag_size);
+	sg_set_buf(sg + ret + 1, skb->data, tag_size);
+
+	/* obtain packet ID, which is used both as a first
+	 * 4 bytes of nonce and last 4 bytes of associated data.
+	 */
+	ret = ovpn_pktid_xmit_next(&ks->pid_xmit, &pktid);
+	if (unlikely(ret < 0))
+		return ret;
+
+	/* iv may be required by async crypto */
+	ovpn_skb_cb(skb)->iv = kmalloc(OVPN_NONCE_SIZE, GFP_ATOMIC);
+	if (unlikely(!ovpn_skb_cb(skb)->iv))
+		return -ENOMEM;
+
+	iv = ovpn_skb_cb(skb)->iv;
+
+	/* concat 4 bytes packet id and 8 bytes nonce tail into 12 bytes
+	 * nonce
+	 */
+	ovpn_pktid_aead_write(pktid, ks->nonce_tail_xmit, iv);
+
+	/* make space for packet id and push it to the front */
+	__skb_push(skb, OVPN_NONCE_WIRE_SIZE);
+	memcpy(skb->data, iv, OVPN_NONCE_WIRE_SIZE);
+
+	/* add packet op as head of additional data */
+	op = ovpn_opcode_compose(OVPN_DATA_V2, ks->key_id, peer->id);
+	__skb_push(skb, OVPN_OPCODE_SIZE);
+	BUILD_BUG_ON(sizeof(op) != OVPN_OPCODE_SIZE);
+	*((__force __be32 *)skb->data) = htonl(op);
+
+	/* AEAD Additional data */
+	sg_set_buf(sg, skb->data, OVPN_AAD_SIZE);
+
+	req = aead_request_alloc(ks->encrypt, GFP_ATOMIC);
+	if (unlikely(!req))
+		return -ENOMEM;
+
+	ovpn_skb_cb(skb)->req = req;
+
+	/* setup async crypto operation */
+	aead_request_set_tfm(req, ks->encrypt);
+	aead_request_set_callback(req, 0, ovpn_encrypt_post, skb);
+	aead_request_set_crypt(req, sg, sg,
+			       skb->len - ovpn_aead_encap_overhead(ks), iv);
+	aead_request_set_ad(req, OVPN_AAD_SIZE);
+
+	/* encrypt it */
+	return crypto_aead_encrypt(req);
+}
+
+int ovpn_aead_decrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks,
+		      struct sk_buff *skb)
+{
+	const unsigned int tag_size = crypto_aead_authsize(ks->decrypt);
+	int ret, payload_len, nfrags;
+	unsigned int payload_offset;
+	struct aead_request *req;
+	struct sk_buff *trailer;
+	struct scatterlist *sg;
+	u8 *iv;
+
+	payload_offset = OVPN_AAD_SIZE + tag_size;
+	payload_len = skb->len - payload_offset;
+
+	ovpn_skb_cb(skb)->payload_offset = payload_offset;
+	ovpn_skb_cb(skb)->peer = peer;
+	ovpn_skb_cb(skb)->ks = ks;
+
+	/* sanity check on packet size, payload size must be >= 0 */
+	if (unlikely(payload_len < 0))
+		return -EINVAL;
+
+	/* Prepare the skb data buffer to be accessed up until the auth tag.
+	 * This is required because this area is directly mapped into the sg
+	 * list.
+	 */
+	if (unlikely(!pskb_may_pull(skb, payload_offset)))
+		return -ENODATA;
+
+	/* get number of skb frags and ensure that packet data is writable */
+	nfrags = skb_cow_data(skb, 0, &trailer);
+	if (unlikely(nfrags < 0))
+		return nfrags;
+
+	if (unlikely(nfrags + 2 > (MAX_SKB_FRAGS + 2)))
+		return -ENOSPC;
+
+	/* sg may be required by async crypto */
+	ovpn_skb_cb(skb)->sg = kmalloc(sizeof(*ovpn_skb_cb(skb)->sg) *
+				       (nfrags + 2), GFP_ATOMIC);
+	if (unlikely(!ovpn_skb_cb(skb)->sg))
+		return -ENOMEM;
+
+	sg = ovpn_skb_cb(skb)->sg;
+
+	/* sg table:
+	 * 0: op, wire nonce (AD, len=OVPN_OPCODE_SIZE+OVPN_NONCE_WIRE_SIZE),
+	 * 1, 2, 3, ..., n: payload,
+	 * n+1: auth_tag (len=tag_size)
+	 */
+	sg_init_table(sg, nfrags + 2);
+
+	/* packet op is head of additional data */
+	sg_set_buf(sg, skb->data, OVPN_AAD_SIZE);
+
+	/* build scatterlist to decrypt packet payload */
+	ret = skb_to_sgvec_nomark(skb, sg + 1, payload_offset, payload_len);
+	if (unlikely(ret < 0)) {
+		netdev_err(peer->ovpn->dev,
+			   "decrypt: cannot map skb to sg: %d\n", ret);
+		return ret;
+	}
+
+	/* append auth_tag onto scatterlist */
+	sg_set_buf(sg + ret + 1, skb->data + OVPN_AAD_SIZE, tag_size);
+
+	/* iv may be required by async crypto */
+	ovpn_skb_cb(skb)->iv = kmalloc(OVPN_NONCE_SIZE, GFP_ATOMIC);
+	if (unlikely(!ovpn_skb_cb(skb)->iv))
+		return -ENOMEM;
+
+	iv = ovpn_skb_cb(skb)->iv;
+
+	/* copy nonce into IV buffer */
+	memcpy(iv, skb->data + OVPN_OPCODE_SIZE, OVPN_NONCE_WIRE_SIZE);
+	memcpy(iv + OVPN_NONCE_WIRE_SIZE, ks->nonce_tail_recv,
+	       OVPN_NONCE_TAIL_SIZE);
+
+	req = aead_request_alloc(ks->decrypt, GFP_ATOMIC);
+	if (unlikely(!req))
+		return -ENOMEM;
+
+	ovpn_skb_cb(skb)->req = req;
+
+	/* setup async crypto operation */
+	aead_request_set_tfm(req, ks->decrypt);
+	aead_request_set_callback(req, 0, ovpn_decrypt_post, skb);
+	aead_request_set_crypt(req, sg, sg, payload_len + tag_size, iv);
+
+	aead_request_set_ad(req, OVPN_AAD_SIZE);
+
+	/* decrypt it */
+	return crypto_aead_decrypt(req);
+}
+
+/* Initialize a struct crypto_aead object */
+static struct crypto_aead *ovpn_aead_init(const char *title,
+					  const char *alg_name,
+					  const unsigned char *key,
+					  unsigned int keylen)
+{
+	struct crypto_aead *aead;
+	int ret;
+
+	aead = crypto_alloc_aead(alg_name, 0, 0);
+	if (IS_ERR(aead)) {
+		ret = PTR_ERR(aead);
+		pr_err("%s crypto_alloc_aead failed, err=%d\n", title, ret);
+		aead = NULL;
+		goto error;
+	}
+
+	ret = crypto_aead_setkey(aead, key, keylen);
+	if (ret) {
+		pr_err("%s crypto_aead_setkey size=%u failed, err=%d\n", title,
+		       keylen, ret);
+		goto error;
+	}
+
+	ret = crypto_aead_setauthsize(aead, OVPN_AUTH_TAG_SIZE);
+	if (ret) {
+		pr_err("%s crypto_aead_setauthsize failed, err=%d\n", title,
+		       ret);
+		goto error;
+	}
+
+	/* basic AEAD assumption */
+	if (crypto_aead_ivsize(aead) != OVPN_NONCE_SIZE) {
+		pr_err("%s IV size must be %d\n", title, OVPN_NONCE_SIZE);
+		ret = -EINVAL;
+		goto error;
+	}
+
+	pr_debug("********* Cipher %s (%s)\n", alg_name, title);
+	pr_debug("*** IV size=%u\n", crypto_aead_ivsize(aead));
+	pr_debug("*** req size=%u\n", crypto_aead_reqsize(aead));
+	pr_debug("*** block size=%u\n", crypto_aead_blocksize(aead));
+	pr_debug("*** auth size=%u\n", crypto_aead_authsize(aead));
+	pr_debug("*** alignmask=0x%x\n", crypto_aead_alignmask(aead));
+
+	return aead;
+
+error:
+	crypto_free_aead(aead);
+	return ERR_PTR(ret);
+}
+
+void ovpn_aead_crypto_key_slot_destroy(struct ovpn_crypto_key_slot *ks)
+{
+	if (!ks)
+		return;
+
+	crypto_free_aead(ks->encrypt);
+	crypto_free_aead(ks->decrypt);
+	kfree(ks);
+}
+
+struct ovpn_crypto_key_slot *
+ovpn_aead_crypto_key_slot_new(const struct ovpn_key_config *kc)
+{
+	struct ovpn_crypto_key_slot *ks = NULL;
+	const char *alg_name;
+	int ret;
+
+	/* validate crypto alg */
+	switch (kc->cipher_alg) {
+	case OVPN_CIPHER_ALG_AES_GCM:
+		alg_name = ALG_NAME_AES;
+		break;
+	case OVPN_CIPHER_ALG_CHACHA20_POLY1305:
+		alg_name = ALG_NAME_CHACHAPOLY;
+		break;
+	default:
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	if (kc->encrypt.nonce_tail_size != OVPN_NONCE_TAIL_SIZE ||
+	    kc->decrypt.nonce_tail_size != OVPN_NONCE_TAIL_SIZE)
+		return ERR_PTR(-EINVAL);
+
+	/* build the key slot */
+	ks = kmalloc(sizeof(*ks), GFP_KERNEL);
+	if (!ks)
+		return ERR_PTR(-ENOMEM);
+
+	ks->encrypt = NULL;
+	ks->decrypt = NULL;
+	kref_init(&ks->refcount);
+	ks->key_id = kc->key_id;
+
+	ks->encrypt = ovpn_aead_init("encrypt", alg_name,
+				     kc->encrypt.cipher_key,
+				     kc->encrypt.cipher_key_size);
+	if (IS_ERR(ks->encrypt)) {
+		ret = PTR_ERR(ks->encrypt);
+		ks->encrypt = NULL;
+		goto destroy_ks;
+	}
+
+	ks->decrypt = ovpn_aead_init("decrypt", alg_name,
+				     kc->decrypt.cipher_key,
+				     kc->decrypt.cipher_key_size);
+	if (IS_ERR(ks->decrypt)) {
+		ret = PTR_ERR(ks->decrypt);
+		ks->decrypt = NULL;
+		goto destroy_ks;
+	}
+
+	memcpy(ks->nonce_tail_xmit, kc->encrypt.nonce_tail,
+	       OVPN_NONCE_TAIL_SIZE);
+	memcpy(ks->nonce_tail_recv, kc->decrypt.nonce_tail,
+	       OVPN_NONCE_TAIL_SIZE);
+
+	/* init packet ID generation/validation */
+	ovpn_pktid_xmit_init(&ks->pid_xmit);
+	ovpn_pktid_recv_init(&ks->pid_recv);
+
+	return ks;
+
+destroy_ks:
+	ovpn_aead_crypto_key_slot_destroy(ks);
+	return ERR_PTR(ret);
+}
+
+enum ovpn_cipher_alg ovpn_aead_crypto_alg(struct ovpn_crypto_key_slot *ks)
+{
+	const char *alg_name;
+
+	if (!ks->encrypt)
+		return OVPN_CIPHER_ALG_NONE;
+
+	alg_name = crypto_tfm_alg_name(crypto_aead_tfm(ks->encrypt));
+
+	if (!strcmp(alg_name, ALG_NAME_AES))
+		return OVPN_CIPHER_ALG_AES_GCM;
+	else if (!strcmp(alg_name, ALG_NAME_CHACHAPOLY))
+		return OVPN_CIPHER_ALG_CHACHA20_POLY1305;
+	else
+		return OVPN_CIPHER_ALG_NONE;
+}
diff --git a/drivers/net/ovpn/crypto_aead.h b/drivers/net/ovpn/crypto_aead.h
new file mode 100644
index 000000000000..65a2ff307898
--- /dev/null
+++ b/drivers/net/ovpn/crypto_aead.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNAEAD_H_
+#define _NET_OVPN_OVPNAEAD_H_
+
+#include "crypto.h"
+
+#include <asm/types.h>
+#include <linux/skbuff.h>
+
+int ovpn_aead_encrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks,
+		      struct sk_buff *skb);
+int ovpn_aead_decrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks,
+		      struct sk_buff *skb);
+
+struct ovpn_crypto_key_slot *
+ovpn_aead_crypto_key_slot_new(const struct ovpn_key_config *kc);
+void ovpn_aead_crypto_key_slot_destroy(struct ovpn_crypto_key_slot *ks);
+
+enum ovpn_cipher_alg ovpn_aead_crypto_alg(struct ovpn_crypto_key_slot *ks);
+
+#endif /* _NET_OVPN_OVPNAEAD_H_ */
diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
new file mode 100644
index 000000000000..10d8afecec55
--- /dev/null
+++ b/drivers/net/ovpn/io.c
@@ -0,0 +1,458 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <crypto/aead.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <net/gro_cells.h>
+#include <net/gso.h>
+#include <net/ip.h>
+
+#include "ovpnpriv.h"
+#include "peer.h"
+#include "io.h"
+#include "bind.h"
+#include "crypto.h"
+#include "crypto_aead.h"
+#include "netlink.h"
+#include "proto.h"
+#include "tcp.h"
+#include "udp.h"
+#include "skb.h"
+#include "socket.h"
+
+const unsigned char ovpn_keepalive_message[OVPN_KEEPALIVE_SIZE] = {
+	0x2a, 0x18, 0x7b, 0xf3, 0x64, 0x1e, 0xb4, 0xcb,
+	0x07, 0xed, 0x2d, 0x0a, 0x98, 0x1f, 0xc7, 0x48
+};
+
+/**
+ * ovpn_is_keepalive - check if skb contains a keepalive message
+ * @skb: packet to check
+ *
+ * Assumes that the first byte of skb->data is defined.
+ *
+ * Return: true if skb contains a keepalive or false otherwise
+ */
+static bool ovpn_is_keepalive(struct sk_buff *skb)
+{
+	if (*skb->data != ovpn_keepalive_message[0])
+		return false;
+
+	if (skb->len != OVPN_KEEPALIVE_SIZE)
+		return false;
+
+	if (!pskb_may_pull(skb, OVPN_KEEPALIVE_SIZE))
+		return false;
+
+	return !memcmp(skb->data, ovpn_keepalive_message, OVPN_KEEPALIVE_SIZE);
+}
+
+/* Called after decrypt to write the IP packet to the device.
+ * This method is expected to manage/free the skb.
+ */
+static void ovpn_netdev_write(struct ovpn_peer *peer, struct sk_buff *skb)
+{
+	unsigned int pkt_len;
+	int ret;
+
+	/* we can't guarantee the packet wasn't corrupted before entering the
+	 * VPN, therefore we give other layers a chance to check that
+	 */
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* skb hash for transport packet no longer valid after decapsulation */
+	skb_clear_hash(skb);
+
+	/* post-decrypt scrub -- prepare to inject encapsulated packet onto the
+	 * interface, based on __skb_tunnel_rx() in dst.h
+	 */
+	skb->dev = peer->ovpn->dev;
+	skb_set_queue_mapping(skb, 0);
+	skb_scrub_packet(skb, true);
+
+	/* network header reset in ovpn_decrypt_post() */
+	skb_reset_transport_header(skb);
+	skb_reset_inner_headers(skb);
+
+	/* cause packet to be "received" by the interface */
+	pkt_len = skb->len;
+	ret = gro_cells_receive(&peer->ovpn->gro_cells, skb);
+	if (likely(ret == NET_RX_SUCCESS)) {
+		/* update RX stats with the size of decrypted packet */
+		ovpn_peer_stats_increment_rx(&peer->vpn_stats, pkt_len);
+		dev_dstats_rx_add(peer->ovpn->dev, pkt_len);
+	}
+}
+
+void ovpn_decrypt_post(void *data, int ret)
+{
+	struct ovpn_crypto_key_slot *ks;
+	unsigned int payload_offset = 0;
+	struct sk_buff *skb = data;
+	struct ovpn_socket *sock;
+	struct ovpn_peer *peer;
+	__be16 proto;
+	__be32 *pid;
+
+	/* crypto is happening asynchronously. this function will be called
+	 * again later by the crypto callback with a proper return code
+	 */
+	if (unlikely(ret == -EINPROGRESS))
+		return;
+
+	payload_offset = ovpn_skb_cb(skb)->payload_offset;
+	ks = ovpn_skb_cb(skb)->ks;
+	peer = ovpn_skb_cb(skb)->peer;
+
+	/* crypto is done, cleanup skb CB and its members */
+	kfree(ovpn_skb_cb(skb)->iv);
+	kfree(ovpn_skb_cb(skb)->sg);
+	aead_request_free(ovpn_skb_cb(skb)->req);
+
+	if (unlikely(ret < 0))
+		goto drop;
+
+	/* PID sits after the op */
+	pid = (__force __be32 *)(skb->data + OVPN_OPCODE_SIZE);
+	ret = ovpn_pktid_recv(&ks->pid_recv, ntohl(*pid), 0);
+	if (unlikely(ret < 0)) {
+		net_err_ratelimited("%s: PKT ID RX error for peer %u: %d\n",
+				    netdev_name(peer->ovpn->dev), peer->id,
+				    ret);
+		goto drop;
+	}
+
+	/* keep track of last received authenticated packet for keepalive */
+	WRITE_ONCE(peer->last_recv, ktime_get_real_seconds());
+
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (sock && sock->sock->sk->sk_protocol == IPPROTO_UDP)
+		/* check if this peer changed local or remote endpoint */
+		ovpn_peer_endpoints_update(peer, skb);
+	rcu_read_unlock();
+
+	/* point to encapsulated IP packet */
+	__skb_pull(skb, payload_offset);
+
+	/* check if this is a valid datapacket that has to be delivered to the
+	 * ovpn interface
+	 */
+	skb_reset_network_header(skb);
+	proto = ovpn_ip_check_protocol(skb);
+	if (unlikely(!proto)) {
+		/* check if null packet */
+		if (unlikely(!pskb_may_pull(skb, 1))) {
+			net_info_ratelimited("%s: NULL packet received from peer %u\n",
+					     netdev_name(peer->ovpn->dev),
+					     peer->id);
+			goto drop;
+		}
+
+		if (ovpn_is_keepalive(skb)) {
+			net_dbg_ratelimited("%s: ping received from peer %u\n",
+					    netdev_name(peer->ovpn->dev),
+					    peer->id);
+			/* we drop the packet, but this is not a failure */
+			consume_skb(skb);
+			goto drop_nocount;
+		}
+
+		net_info_ratelimited("%s: unsupported protocol received from peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		goto drop;
+	}
+	skb->protocol = proto;
+
+	/* perform Reverse Path Filtering (RPF) */
+	if (unlikely(!ovpn_peer_check_by_src(peer->ovpn, skb, peer))) {
+		if (skb->protocol == htons(ETH_P_IPV6))
+			net_dbg_ratelimited("%s: RPF dropped packet from peer %u, src: %pI6c\n",
+					    netdev_name(peer->ovpn->dev),
+					    peer->id, &ipv6_hdr(skb)->saddr);
+		else
+			net_dbg_ratelimited("%s: RPF dropped packet from peer %u, src: %pI4\n",
+					    netdev_name(peer->ovpn->dev),
+					    peer->id, &ip_hdr(skb)->saddr);
+		goto drop;
+	}
+
+	ovpn_netdev_write(peer, skb);
+	/* skb is passed to upper layer - don't free it */
+	skb = NULL;
+drop:
+	if (unlikely(skb))
+		dev_dstats_rx_dropped(peer->ovpn->dev);
+	kfree_skb(skb);
+drop_nocount:
+	if (likely(peer))
+		ovpn_peer_put(peer);
+	if (likely(ks))
+		ovpn_crypto_key_slot_put(ks);
+}
+
+/* RX path entry point: decrypt packet and forward it to the device */
+void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb)
+{
+	struct ovpn_crypto_key_slot *ks;
+	u8 key_id;
+
+	ovpn_peer_stats_increment_rx(&peer->link_stats, skb->len);
+
+	/* get the key slot matching the key ID in the received packet */
+	key_id = ovpn_key_id_from_skb(skb);
+	ks = ovpn_crypto_key_id_to_slot(&peer->crypto, key_id);
+	if (unlikely(!ks)) {
+		net_info_ratelimited("%s: no available key for peer %u, key-id: %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id,
+				     key_id);
+		dev_dstats_rx_dropped(peer->ovpn->dev);
+		kfree_skb(skb);
+		ovpn_peer_put(peer);
+		return;
+	}
+
+	memset(ovpn_skb_cb(skb), 0, sizeof(struct ovpn_cb));
+	ovpn_decrypt_post(skb, ovpn_aead_decrypt(peer, ks, skb));
+}
+
+void ovpn_encrypt_post(void *data, int ret)
+{
+	struct ovpn_crypto_key_slot *ks;
+	struct sk_buff *skb = data;
+	struct ovpn_socket *sock;
+	struct ovpn_peer *peer;
+	unsigned int orig_len;
+
+	/* encryption is happening asynchronously. This function will be
+	 * called later by the crypto callback with a proper return value
+	 */
+	if (unlikely(ret == -EINPROGRESS))
+		return;
+
+	ks = ovpn_skb_cb(skb)->ks;
+	peer = ovpn_skb_cb(skb)->peer;
+
+	/* crypto is done, cleanup skb CB and its members */
+	kfree(ovpn_skb_cb(skb)->iv);
+	kfree(ovpn_skb_cb(skb)->sg);
+	aead_request_free(ovpn_skb_cb(skb)->req);
+
+	if (unlikely(ret == -ERANGE)) {
+		/* we ran out of IVs and we must kill the key as it can't be
+		 * use anymore
+		 */
+		netdev_warn(peer->ovpn->dev,
+			    "killing key %u for peer %u\n", ks->key_id,
+			    peer->id);
+		if (ovpn_crypto_kill_key(&peer->crypto, ks->key_id))
+			/* let userspace know so that a new key must be negotiated */
+			ovpn_nl_key_swap_notify(peer, ks->key_id);
+
+		goto err;
+	}
+
+	if (unlikely(ret < 0))
+		goto err;
+
+	skb_mark_not_on_list(skb);
+	orig_len = skb->len;
+
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (unlikely(!sock))
+		goto err_unlock;
+
+	switch (sock->sock->sk->sk_protocol) {
+	case IPPROTO_UDP:
+		ovpn_udp_send_skb(peer, sock->sock, skb);
+		break;
+	case IPPROTO_TCP:
+		ovpn_tcp_send_skb(peer, sock->sock, skb);
+		break;
+	default:
+		/* no transport configured yet */
+		goto err_unlock;
+	}
+
+	ovpn_peer_stats_increment_tx(&peer->link_stats, orig_len);
+	/* keep track of last sent packet for keepalive */
+	WRITE_ONCE(peer->last_sent, ktime_get_real_seconds());
+	/* skb passed down the stack - don't free it */
+	skb = NULL;
+err_unlock:
+	rcu_read_unlock();
+err:
+	if (unlikely(skb))
+		dev_dstats_tx_dropped(peer->ovpn->dev);
+	if (likely(peer))
+		ovpn_peer_put(peer);
+	if (likely(ks))
+		ovpn_crypto_key_slot_put(ks);
+	kfree_skb(skb);
+}
+
+static bool ovpn_encrypt_one(struct ovpn_peer *peer, struct sk_buff *skb)
+{
+	struct ovpn_crypto_key_slot *ks;
+
+	/* get primary key to be used for encrypting data */
+	ks = ovpn_crypto_key_slot_primary(&peer->crypto);
+	if (unlikely(!ks))
+		return false;
+
+	/* take a reference to the peer because the crypto code may run async.
+	 * ovpn_encrypt_post() will release it upon completion
+	 */
+	if (unlikely(!ovpn_peer_hold(peer))) {
+		DEBUG_NET_WARN_ON_ONCE(1);
+		ovpn_crypto_key_slot_put(ks);
+		return false;
+	}
+
+	memset(ovpn_skb_cb(skb), 0, sizeof(struct ovpn_cb));
+	ovpn_encrypt_post(skb, ovpn_aead_encrypt(peer, ks, skb));
+	return true;
+}
+
+/* send skb to connected peer, if any */
+static void ovpn_send(struct ovpn_priv *ovpn, struct sk_buff *skb,
+		      struct ovpn_peer *peer)
+{
+	struct sk_buff *curr, *next;
+
+	/* this might be a GSO-segmented skb list: process each skb
+	 * independently
+	 */
+	skb_list_walk_safe(skb, curr, next) {
+		if (unlikely(!ovpn_encrypt_one(peer, curr))) {
+			dev_dstats_tx_dropped(ovpn->dev);
+			kfree_skb(curr);
+		}
+	}
+
+	ovpn_peer_put(peer);
+}
+
+/* Send user data to the network
+ */
+netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+	struct sk_buff *segments, *curr, *next;
+	struct sk_buff_head skb_list;
+	struct ovpn_peer *peer;
+	__be16 proto;
+	int ret;
+
+	/* reset netfilter state */
+	nf_reset_ct(skb);
+
+	/* verify IP header size in network packet */
+	proto = ovpn_ip_check_protocol(skb);
+	if (unlikely(!proto || skb->protocol != proto))
+		goto drop;
+
+	if (skb_is_gso(skb)) {
+		segments = skb_gso_segment(skb, 0);
+		if (IS_ERR(segments)) {
+			ret = PTR_ERR(segments);
+			net_err_ratelimited("%s: cannot segment payload packet: %d\n",
+					    netdev_name(dev), ret);
+			goto drop;
+		}
+
+		consume_skb(skb);
+		skb = segments;
+	}
+
+	/* from this moment on, "skb" might be a list */
+
+	__skb_queue_head_init(&skb_list);
+	skb_list_walk_safe(skb, curr, next) {
+		skb_mark_not_on_list(curr);
+
+		curr = skb_share_check(curr, GFP_ATOMIC);
+		if (unlikely(!curr)) {
+			net_err_ratelimited("%s: skb_share_check failed for payload packet\n",
+					    netdev_name(dev));
+			dev_dstats_tx_dropped(ovpn->dev);
+			continue;
+		}
+
+		__skb_queue_tail(&skb_list, curr);
+	}
+	skb_list.prev->next = NULL;
+
+	/* retrieve peer serving the destination IP of this packet */
+	peer = ovpn_peer_get_by_dst(ovpn, skb);
+	if (unlikely(!peer)) {
+		switch (skb->protocol) {
+		case htons(ETH_P_IP):
+			net_dbg_ratelimited("%s: no peer to send data to dst=%pI4\n",
+					    netdev_name(ovpn->dev),
+					    &ip_hdr(skb)->daddr);
+			break;
+		case htons(ETH_P_IPV6):
+			net_dbg_ratelimited("%s: no peer to send data to dst=%pI6c\n",
+					    netdev_name(ovpn->dev),
+					    &ipv6_hdr(skb)->daddr);
+			break;
+		}
+		goto drop;
+	}
+	/* dst was needed for peer selection - it can now be dropped */
+	skb_dst_drop(skb);
+
+	ovpn_peer_stats_increment_tx(&peer->vpn_stats, skb->len);
+	ovpn_send(ovpn, skb_list.next, peer);
+
+	return NETDEV_TX_OK;
+
+drop:
+	dev_dstats_tx_dropped(ovpn->dev);
+	skb_tx_error(skb);
+	kfree_skb_list(skb);
+	return NETDEV_TX_OK;
+}
+
+/**
+ * ovpn_xmit_special - encrypt and transmit an out-of-band message to peer
+ * @peer: peer to send the message to
+ * @data: message content
+ * @len: message length
+ *
+ * Assumes that caller holds a reference to peer, which will be
+ * passed to ovpn_send()
+ */
+void ovpn_xmit_special(struct ovpn_peer *peer, const void *data,
+		       const unsigned int len)
+{
+	struct ovpn_priv *ovpn;
+	struct sk_buff *skb;
+
+	ovpn = peer->ovpn;
+	if (unlikely(!ovpn)) {
+		ovpn_peer_put(peer);
+		return;
+	}
+
+	skb = alloc_skb(256 + len, GFP_ATOMIC);
+	if (unlikely(!skb)) {
+		ovpn_peer_put(peer);
+		return;
+	}
+
+	skb_reserve(skb, 128);
+	skb->priority = TC_PRIO_BESTEFFORT;
+	__skb_put_data(skb, data, len);
+
+	ovpn_send(ovpn, skb, peer);
+}
diff --git a/drivers/net/ovpn/io.h b/drivers/net/ovpn/io.h
new file mode 100644
index 000000000000..db9e10f9077c
--- /dev/null
+++ b/drivers/net/ovpn/io.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPN_H_
+#define _NET_OVPN_OVPN_H_
+
+/* DATA_V2 header size with AEAD encryption */
+#define OVPN_HEAD_ROOM (OVPN_OPCODE_SIZE + OVPN_NONCE_WIRE_SIZE +	   \
+			16 /* AEAD TAG length */ +			   \
+			max(sizeof(struct udphdr), sizeof(struct tcphdr)) +\
+			max(sizeof(struct ipv6hdr), sizeof(struct iphdr)))
+
+/* max padding required by encryption */
+#define OVPN_MAX_PADDING 16
+
+#define OVPN_KEEPALIVE_SIZE 16
+extern const unsigned char ovpn_keepalive_message[OVPN_KEEPALIVE_SIZE];
+
+netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev);
+
+void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb);
+void ovpn_xmit_special(struct ovpn_peer *peer, const void *data,
+		       const unsigned int len);
+
+void ovpn_encrypt_post(void *data, int ret);
+void ovpn_decrypt_post(void *data, int ret);
+
+#endif /* _NET_OVPN_OVPN_H_ */
diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
new file mode 100644
index 000000000000..1bb1afe766a4
--- /dev/null
+++ b/drivers/net/ovpn/main.c
@@ -0,0 +1,279 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ *		James Yonan <james@openvpn.net>
+ */
+
+#include <linux/ethtool.h>
+#include <linux/genetlink.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <net/gro_cells.h>
+#include <net/ip.h>
+#include <net/rtnetlink.h>
+#include <uapi/linux/if_arp.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "netlink.h"
+#include "io.h"
+#include "peer.h"
+#include "proto.h"
+#include "tcp.h"
+#include "udp.h"
+
+static void ovpn_priv_free(struct net_device *net)
+{
+	struct ovpn_priv *ovpn = netdev_priv(net);
+
+	kfree(ovpn->peers);
+}
+
+static int ovpn_mp_alloc(struct ovpn_priv *ovpn)
+{
+	struct in_device *dev_v4;
+	int i;
+
+	if (ovpn->mode != OVPN_MODE_MP)
+		return 0;
+
+	dev_v4 = __in_dev_get_rtnl(ovpn->dev);
+	if (dev_v4) {
+		/* disable redirects as Linux gets confused by ovpn
+		 * handling same-LAN routing.
+		 * This happens because a multipeer interface is used as
+		 * relay point between hosts in the same subnet, while
+		 * in a classic LAN this would not be needed because the
+		 * two hosts would be able to talk directly.
+		 */
+		IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false);
+		IPV4_DEVCONF_ALL(dev_net(ovpn->dev), SEND_REDIRECTS) = false;
+	}
+
+	/* the peer container is fairly large, therefore we allocate it only in
+	 * MP mode
+	 */
+	ovpn->peers = kzalloc(sizeof(*ovpn->peers), GFP_KERNEL);
+	if (!ovpn->peers)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(ovpn->peers->by_id); i++) {
+		INIT_HLIST_HEAD(&ovpn->peers->by_id[i]);
+		INIT_HLIST_NULLS_HEAD(&ovpn->peers->by_vpn_addr4[i], i);
+		INIT_HLIST_NULLS_HEAD(&ovpn->peers->by_vpn_addr6[i], i);
+		INIT_HLIST_NULLS_HEAD(&ovpn->peers->by_transp_addr[i], i);
+	}
+
+	return 0;
+}
+
+static int ovpn_net_init(struct net_device *dev)
+{
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+	int err = gro_cells_init(&ovpn->gro_cells, dev);
+
+	if (err < 0)
+		return err;
+
+	err = ovpn_mp_alloc(ovpn);
+	if (err < 0) {
+		gro_cells_destroy(&ovpn->gro_cells);
+		return err;
+	}
+
+	return 0;
+}
+
+static void ovpn_net_uninit(struct net_device *dev)
+{
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+
+	gro_cells_destroy(&ovpn->gro_cells);
+}
+
+static const struct net_device_ops ovpn_netdev_ops = {
+	.ndo_init		= ovpn_net_init,
+	.ndo_uninit		= ovpn_net_uninit,
+	.ndo_start_xmit		= ovpn_net_xmit,
+};
+
+static const struct device_type ovpn_type = {
+	.name = OVPN_FAMILY_NAME,
+};
+
+static const struct nla_policy ovpn_policy[IFLA_OVPN_MAX + 1] = {
+	[IFLA_OVPN_MODE] = NLA_POLICY_RANGE(NLA_U8, OVPN_MODE_P2P,
+					    OVPN_MODE_MP),
+};
+
+/**
+ * ovpn_dev_is_valid - check if the netdevice is of type 'ovpn'
+ * @dev: the interface to check
+ *
+ * Return: whether the netdevice is of type 'ovpn'
+ */
+bool ovpn_dev_is_valid(const struct net_device *dev)
+{
+	return dev->netdev_ops == &ovpn_netdev_ops;
+}
+
+static void ovpn_get_drvinfo(struct net_device *dev,
+			     struct ethtool_drvinfo *info)
+{
+	strscpy(info->driver, "ovpn", sizeof(info->driver));
+	strscpy(info->bus_info, "ovpn", sizeof(info->bus_info));
+}
+
+static const struct ethtool_ops ovpn_ethtool_ops = {
+	.get_drvinfo		= ovpn_get_drvinfo,
+	.get_link		= ethtool_op_get_link,
+	.get_ts_info		= ethtool_op_get_ts_info,
+};
+
+static void ovpn_setup(struct net_device *dev)
+{
+	netdev_features_t feat = NETIF_F_SG | NETIF_F_GSO |
+				 NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA;
+
+	dev->needs_free_netdev = true;
+
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS;
+
+	dev->ethtool_ops = &ovpn_ethtool_ops;
+	dev->netdev_ops = &ovpn_netdev_ops;
+
+	dev->priv_destructor = ovpn_priv_free;
+
+	dev->hard_header_len = 0;
+	dev->addr_len = 0;
+	dev->mtu = ETH_DATA_LEN - OVPN_HEAD_ROOM;
+	dev->min_mtu = IPV4_MIN_MTU;
+	dev->max_mtu = IP_MAX_MTU - OVPN_HEAD_ROOM;
+
+	dev->type = ARPHRD_NONE;
+	dev->flags = IFF_POINTOPOINT | IFF_NOARP;
+	dev->priv_flags |= IFF_NO_QUEUE;
+	/* when routing packets to a LAN behind a client, we rely on the
+	 * route entry that originally brought the packet into ovpn, so
+	 * don't release it
+	 */
+	netif_keep_dst(dev);
+
+	dev->lltx = true;
+	dev->features |= feat;
+	dev->hw_features |= feat;
+	dev->hw_enc_features |= feat;
+
+	dev->needed_headroom = ALIGN(OVPN_HEAD_ROOM, 4);
+	dev->needed_tailroom = OVPN_MAX_PADDING;
+
+	SET_NETDEV_DEVTYPE(dev, &ovpn_type);
+}
+
+static int ovpn_newlink(struct net_device *dev,
+			struct rtnl_newlink_params *params,
+			struct netlink_ext_ack *extack)
+{
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+	struct nlattr **data = params->data;
+	enum ovpn_mode mode = OVPN_MODE_P2P;
+
+	if (data && data[IFLA_OVPN_MODE]) {
+		mode = nla_get_u8(data[IFLA_OVPN_MODE]);
+		netdev_dbg(dev, "setting device mode: %u\n", mode);
+	}
+
+	ovpn->dev = dev;
+	ovpn->mode = mode;
+	spin_lock_init(&ovpn->lock);
+	INIT_DELAYED_WORK(&ovpn->keepalive_work, ovpn_peer_keepalive_work);
+
+	/* Set carrier explicitly after registration, this way state is
+	 * clearly defined.
+	 *
+	 * In case of MP interfaces we keep the carrier always on.
+	 *
+	 * Carrier for P2P interfaces is initially off and it is then
+	 * switched on and off when the remote peer is added or deleted.
+	 */
+	if (ovpn->mode == OVPN_MODE_MP)
+		netif_carrier_on(dev);
+	else
+		netif_carrier_off(dev);
+
+	return register_netdevice(dev);
+}
+
+static void ovpn_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+
+	cancel_delayed_work_sync(&ovpn->keepalive_work);
+	ovpn_peers_free(ovpn, NULL, OVPN_DEL_PEER_REASON_TEARDOWN);
+	unregister_netdevice_queue(dev, head);
+}
+
+static int ovpn_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+
+	if (nla_put_u8(skb, IFLA_OVPN_MODE, ovpn->mode))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static struct rtnl_link_ops ovpn_link_ops = {
+	.kind = "ovpn",
+	.netns_refund = false,
+	.priv_size = sizeof(struct ovpn_priv),
+	.setup = ovpn_setup,
+	.policy = ovpn_policy,
+	.maxtype = IFLA_OVPN_MAX,
+	.newlink = ovpn_newlink,
+	.dellink = ovpn_dellink,
+	.fill_info = ovpn_fill_info,
+};
+
+static int __init ovpn_init(void)
+{
+	int err = rtnl_link_register(&ovpn_link_ops);
+
+	if (err) {
+		pr_err("ovpn: can't register rtnl link ops: %d\n", err);
+		return err;
+	}
+
+	err = ovpn_nl_register();
+	if (err) {
+		pr_err("ovpn: can't register netlink family: %d\n", err);
+		goto unreg_rtnl;
+	}
+
+	ovpn_tcp_init();
+
+	return 0;
+
+unreg_rtnl:
+	rtnl_link_unregister(&ovpn_link_ops);
+	return err;
+}
+
+static __exit void ovpn_cleanup(void)
+{
+	ovpn_nl_unregister();
+	rtnl_link_unregister(&ovpn_link_ops);
+
+	rcu_barrier();
+}
+
+module_init(ovpn_init);
+module_exit(ovpn_cleanup);
+
+MODULE_DESCRIPTION("OpenVPN data channel offload (ovpn)");
+MODULE_AUTHOR("Antonio Quartulli <antonio@openvpn.net>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ovpn/main.h b/drivers/net/ovpn/main.h
new file mode 100644
index 000000000000..017cd0100765
--- /dev/null
+++ b/drivers/net/ovpn/main.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_MAIN_H_
+#define _NET_OVPN_MAIN_H_
+
+bool ovpn_dev_is_valid(const struct net_device *dev);
+
+#endif /* _NET_OVPN_MAIN_H_ */
diff --git a/drivers/net/ovpn/netlink-gen.c b/drivers/net/ovpn/netlink-gen.c
new file mode 100644
index 000000000000..58e1a4342378
--- /dev/null
+++ b/drivers/net/ovpn/netlink-gen.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/ovpn.yaml */
+/* YNL-GEN kernel source */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "netlink-gen.h"
+
+#include <uapi/linux/ovpn.h>
+
+/* Integer value ranges */
+static const struct netlink_range_validation ovpn_a_peer_id_range = {
+	.max	= 16777215ULL,
+};
+
+static const struct netlink_range_validation ovpn_a_keyconf_peer_id_range = {
+	.max	= 16777215ULL,
+};
+
+/* Common nested types */
+const struct nla_policy ovpn_keyconf_nl_policy[OVPN_A_KEYCONF_DECRYPT_DIR + 1] = {
+	[OVPN_A_KEYCONF_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_keyconf_peer_id_range),
+	[OVPN_A_KEYCONF_SLOT] = NLA_POLICY_MAX(NLA_U32, 1),
+	[OVPN_A_KEYCONF_KEY_ID] = NLA_POLICY_MAX(NLA_U32, 7),
+	[OVPN_A_KEYCONF_CIPHER_ALG] = NLA_POLICY_MAX(NLA_U32, 2),
+	[OVPN_A_KEYCONF_ENCRYPT_DIR] = NLA_POLICY_NESTED(ovpn_keydir_nl_policy),
+	[OVPN_A_KEYCONF_DECRYPT_DIR] = NLA_POLICY_NESTED(ovpn_keydir_nl_policy),
+};
+
+const struct nla_policy ovpn_keydir_nl_policy[OVPN_A_KEYDIR_NONCE_TAIL + 1] = {
+	[OVPN_A_KEYDIR_CIPHER_KEY] = NLA_POLICY_MAX_LEN(256),
+	[OVPN_A_KEYDIR_NONCE_TAIL] = NLA_POLICY_EXACT_LEN(OVPN_NONCE_TAIL_SIZE),
+};
+
+const struct nla_policy ovpn_peer_nl_policy[OVPN_A_PEER_LINK_TX_PACKETS + 1] = {
+	[OVPN_A_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_id_range),
+	[OVPN_A_PEER_REMOTE_IPV4] = { .type = NLA_BE32, },
+	[OVPN_A_PEER_REMOTE_IPV6] = NLA_POLICY_EXACT_LEN(16),
+	[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID] = { .type = NLA_U32, },
+	[OVPN_A_PEER_REMOTE_PORT] = NLA_POLICY_MIN(NLA_BE16, 1),
+	[OVPN_A_PEER_SOCKET] = { .type = NLA_U32, },
+	[OVPN_A_PEER_SOCKET_NETNSID] = { .type = NLA_S32, },
+	[OVPN_A_PEER_VPN_IPV4] = { .type = NLA_BE32, },
+	[OVPN_A_PEER_VPN_IPV6] = NLA_POLICY_EXACT_LEN(16),
+	[OVPN_A_PEER_LOCAL_IPV4] = { .type = NLA_BE32, },
+	[OVPN_A_PEER_LOCAL_IPV6] = NLA_POLICY_EXACT_LEN(16),
+	[OVPN_A_PEER_LOCAL_PORT] = NLA_POLICY_MIN(NLA_BE16, 1),
+	[OVPN_A_PEER_KEEPALIVE_INTERVAL] = { .type = NLA_U32, },
+	[OVPN_A_PEER_KEEPALIVE_TIMEOUT] = { .type = NLA_U32, },
+	[OVPN_A_PEER_DEL_REASON] = NLA_POLICY_MAX(NLA_U32, 4),
+	[OVPN_A_PEER_VPN_RX_BYTES] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_VPN_TX_BYTES] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_VPN_RX_PACKETS] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_VPN_TX_PACKETS] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_LINK_RX_BYTES] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_LINK_TX_BYTES] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_LINK_RX_PACKETS] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_LINK_TX_PACKETS] = { .type = NLA_UINT, },
+};
+
+/* OVPN_CMD_PEER_NEW - do */
+static const struct nla_policy ovpn_peer_new_nl_policy[OVPN_A_PEER + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy),
+};
+
+/* OVPN_CMD_PEER_SET - do */
+static const struct nla_policy ovpn_peer_set_nl_policy[OVPN_A_PEER + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy),
+};
+
+/* OVPN_CMD_PEER_GET - do */
+static const struct nla_policy ovpn_peer_get_do_nl_policy[OVPN_A_PEER + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy),
+};
+
+/* OVPN_CMD_PEER_GET - dump */
+static const struct nla_policy ovpn_peer_get_dump_nl_policy[OVPN_A_IFINDEX + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+};
+
+/* OVPN_CMD_PEER_DEL - do */
+static const struct nla_policy ovpn_peer_del_nl_policy[OVPN_A_PEER + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy),
+};
+
+/* OVPN_CMD_KEY_NEW - do */
+static const struct nla_policy ovpn_key_new_nl_policy[OVPN_A_KEYCONF + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy),
+};
+
+/* OVPN_CMD_KEY_GET - do */
+static const struct nla_policy ovpn_key_get_nl_policy[OVPN_A_KEYCONF + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy),
+};
+
+/* OVPN_CMD_KEY_SWAP - do */
+static const struct nla_policy ovpn_key_swap_nl_policy[OVPN_A_KEYCONF + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy),
+};
+
+/* OVPN_CMD_KEY_DEL - do */
+static const struct nla_policy ovpn_key_del_nl_policy[OVPN_A_KEYCONF + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy),
+};
+
+/* Ops table for ovpn */
+static const struct genl_split_ops ovpn_nl_ops[] = {
+	{
+		.cmd		= OVPN_CMD_PEER_NEW,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_peer_new_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_peer_new_nl_policy,
+		.maxattr	= OVPN_A_PEER,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_PEER_SET,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_peer_set_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_peer_set_nl_policy,
+		.maxattr	= OVPN_A_PEER,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_PEER_GET,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_peer_get_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_peer_get_do_nl_policy,
+		.maxattr	= OVPN_A_PEER,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_PEER_GET,
+		.dumpit		= ovpn_nl_peer_get_dumpit,
+		.policy		= ovpn_peer_get_dump_nl_policy,
+		.maxattr	= OVPN_A_IFINDEX,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= OVPN_CMD_PEER_DEL,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_peer_del_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_peer_del_nl_policy,
+		.maxattr	= OVPN_A_PEER,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_KEY_NEW,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_key_new_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_key_new_nl_policy,
+		.maxattr	= OVPN_A_KEYCONF,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_KEY_GET,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_key_get_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_key_get_nl_policy,
+		.maxattr	= OVPN_A_KEYCONF,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_KEY_SWAP,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_key_swap_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_key_swap_nl_policy,
+		.maxattr	= OVPN_A_KEYCONF,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_KEY_DEL,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_key_del_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_key_del_nl_policy,
+		.maxattr	= OVPN_A_KEYCONF,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+};
+
+static const struct genl_multicast_group ovpn_nl_mcgrps[] = {
+	[OVPN_NLGRP_PEERS] = { "peers", },
+};
+
+struct genl_family ovpn_nl_family __ro_after_init = {
+	.name		= OVPN_FAMILY_NAME,
+	.version	= OVPN_FAMILY_VERSION,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.module		= THIS_MODULE,
+	.split_ops	= ovpn_nl_ops,
+	.n_split_ops	= ARRAY_SIZE(ovpn_nl_ops),
+	.mcgrps		= ovpn_nl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(ovpn_nl_mcgrps),
+};
diff --git a/drivers/net/ovpn/netlink-gen.h b/drivers/net/ovpn/netlink-gen.h
new file mode 100644
index 000000000000..66a4e4a0a055
--- /dev/null
+++ b/drivers/net/ovpn/netlink-gen.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/ovpn.yaml */
+/* YNL-GEN kernel header */
+
+#ifndef _LINUX_OVPN_GEN_H
+#define _LINUX_OVPN_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/ovpn.h>
+
+/* Common nested types */
+extern const struct nla_policy ovpn_keyconf_nl_policy[OVPN_A_KEYCONF_DECRYPT_DIR + 1];
+extern const struct nla_policy ovpn_keydir_nl_policy[OVPN_A_KEYDIR_NONCE_TAIL + 1];
+extern const struct nla_policy ovpn_peer_nl_policy[OVPN_A_PEER_LINK_TX_PACKETS + 1];
+
+int ovpn_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+		     struct genl_info *info);
+void
+ovpn_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+		  struct genl_info *info);
+
+int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_peer_get_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_peer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int ovpn_nl_peer_del_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_key_new_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_key_get_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_key_swap_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info);
+
+enum {
+	OVPN_NLGRP_PEERS,
+};
+
+extern struct genl_family ovpn_nl_family;
+
+#endif /* _LINUX_OVPN_GEN_H */
diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c
new file mode 100644
index 000000000000..bea03913bfb1
--- /dev/null
+++ b/drivers/net/ovpn/netlink.c
@@ -0,0 +1,1258 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/types.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/ovpn.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "netlink.h"
+#include "netlink-gen.h"
+#include "bind.h"
+#include "crypto.h"
+#include "peer.h"
+#include "socket.h"
+
+MODULE_ALIAS_GENL_FAMILY(OVPN_FAMILY_NAME);
+
+/**
+ * ovpn_get_dev_from_attrs - retrieve the ovpn private data from the netdevice
+ *			     a netlink message is targeting
+ * @net: network namespace where to look for the interface
+ * @info: generic netlink info from the user request
+ * @tracker: tracker object to be used for the netdev reference acquisition
+ *
+ * Return: the ovpn private data, if found, or an error otherwise
+ */
+static struct ovpn_priv *
+ovpn_get_dev_from_attrs(struct net *net, const struct genl_info *info,
+			netdevice_tracker *tracker)
+{
+	struct ovpn_priv *ovpn;
+	struct net_device *dev;
+	int ifindex;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_IFINDEX))
+		return ERR_PTR(-EINVAL);
+
+	ifindex = nla_get_u32(info->attrs[OVPN_A_IFINDEX]);
+
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(net, ifindex);
+	if (!dev) {
+		rcu_read_unlock();
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "ifindex does not match any interface");
+		return ERR_PTR(-ENODEV);
+	}
+
+	if (!ovpn_dev_is_valid(dev)) {
+		rcu_read_unlock();
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "specified interface is not ovpn");
+		NL_SET_BAD_ATTR(info->extack, info->attrs[OVPN_A_IFINDEX]);
+		return ERR_PTR(-EINVAL);
+	}
+
+	ovpn = netdev_priv(dev);
+	netdev_hold(dev, tracker, GFP_ATOMIC);
+	rcu_read_unlock();
+
+	return ovpn;
+}
+
+int ovpn_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+		     struct genl_info *info)
+{
+	netdevice_tracker *tracker = (netdevice_tracker *)&info->user_ptr[1];
+	struct ovpn_priv *ovpn = ovpn_get_dev_from_attrs(genl_info_net(info),
+							 info, tracker);
+
+	if (IS_ERR(ovpn))
+		return PTR_ERR(ovpn);
+
+	info->user_ptr[0] = ovpn;
+
+	return 0;
+}
+
+void ovpn_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+		       struct genl_info *info)
+{
+	netdevice_tracker *tracker = (netdevice_tracker *)&info->user_ptr[1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+
+	if (ovpn)
+		netdev_put(ovpn->dev, tracker);
+}
+
+static bool ovpn_nl_attr_sockaddr_remote(struct nlattr **attrs,
+					 struct sockaddr_storage *ss)
+{
+	struct sockaddr_in6 *sin6;
+	struct sockaddr_in *sin;
+	struct in6_addr *in6;
+	__be16 port = 0;
+	__be32 *in;
+
+	ss->ss_family = AF_UNSPEC;
+
+	if (attrs[OVPN_A_PEER_REMOTE_PORT])
+		port = nla_get_be16(attrs[OVPN_A_PEER_REMOTE_PORT]);
+
+	if (attrs[OVPN_A_PEER_REMOTE_IPV4]) {
+		ss->ss_family = AF_INET;
+		in = nla_data(attrs[OVPN_A_PEER_REMOTE_IPV4]);
+	} else if (attrs[OVPN_A_PEER_REMOTE_IPV6]) {
+		ss->ss_family = AF_INET6;
+		in6 = nla_data(attrs[OVPN_A_PEER_REMOTE_IPV6]);
+	} else {
+		return false;
+	}
+
+	switch (ss->ss_family) {
+	case AF_INET6:
+		/* If this is a regular IPv6 just break and move on,
+		 * otherwise switch to AF_INET and extract the IPv4 accordingly
+		 */
+		if (!ipv6_addr_v4mapped(in6)) {
+			sin6 = (struct sockaddr_in6 *)ss;
+			sin6->sin6_port = port;
+			memcpy(&sin6->sin6_addr, in6, sizeof(*in6));
+			break;
+		}
+
+		/* v4-mapped-v6 address */
+		ss->ss_family = AF_INET;
+		in = &in6->s6_addr32[3];
+		fallthrough;
+	case AF_INET:
+		sin = (struct sockaddr_in *)ss;
+		sin->sin_port = port;
+		sin->sin_addr.s_addr = *in;
+		break;
+	}
+
+	return true;
+}
+
+static u8 *ovpn_nl_attr_local_ip(struct nlattr **attrs)
+{
+	u8 *addr6;
+
+	if (!attrs[OVPN_A_PEER_LOCAL_IPV4] && !attrs[OVPN_A_PEER_LOCAL_IPV6])
+		return NULL;
+
+	if (attrs[OVPN_A_PEER_LOCAL_IPV4])
+		return nla_data(attrs[OVPN_A_PEER_LOCAL_IPV4]);
+
+	addr6 = nla_data(attrs[OVPN_A_PEER_LOCAL_IPV6]);
+	/* this is an IPv4-mapped IPv6 address, therefore extract the actual
+	 * v4 address from the last 4 bytes
+	 */
+	if (ipv6_addr_v4mapped((struct in6_addr *)addr6))
+		return addr6 + 12;
+
+	return addr6;
+}
+
+static sa_family_t ovpn_nl_family_get(struct nlattr *addr4,
+				      struct nlattr *addr6)
+{
+	if (addr4)
+		return AF_INET;
+
+	if (addr6) {
+		if (ipv6_addr_v4mapped((struct in6_addr *)nla_data(addr6)))
+			return AF_INET;
+		return AF_INET6;
+	}
+
+	return AF_UNSPEC;
+}
+
+static int ovpn_nl_peer_precheck(struct ovpn_priv *ovpn,
+				 struct genl_info *info,
+				 struct nlattr **attrs)
+{
+	sa_family_t local_fam, remote_fam;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs,
+			      OVPN_A_PEER_ID))
+		return -EINVAL;
+
+	if (attrs[OVPN_A_PEER_REMOTE_IPV4] && attrs[OVPN_A_PEER_REMOTE_IPV6]) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "cannot specify both remote IPv4 or IPv6 address");
+		return -EINVAL;
+	}
+
+	if (!attrs[OVPN_A_PEER_REMOTE_IPV4] &&
+	    !attrs[OVPN_A_PEER_REMOTE_IPV6] && attrs[OVPN_A_PEER_REMOTE_PORT]) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "cannot specify remote port without IP address");
+		return -EINVAL;
+	}
+
+	if ((attrs[OVPN_A_PEER_REMOTE_IPV4] ||
+	     attrs[OVPN_A_PEER_REMOTE_IPV6]) &&
+	    !attrs[OVPN_A_PEER_REMOTE_PORT]) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "cannot specify remote IP address without port");
+		return -EINVAL;
+	}
+
+	if (!attrs[OVPN_A_PEER_REMOTE_IPV4] &&
+	    attrs[OVPN_A_PEER_LOCAL_IPV4]) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "cannot specify local IPv4 address without remote");
+		return -EINVAL;
+	}
+
+	if (!attrs[OVPN_A_PEER_REMOTE_IPV6] &&
+	    attrs[OVPN_A_PEER_LOCAL_IPV6]) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "cannot specify local IPV6 address without remote");
+		return -EINVAL;
+	}
+
+	/* check that local and remote address families are the same even
+	 * after parsing v4mapped IPv6 addresses.
+	 * (if addresses are not provided, family will be AF_UNSPEC and
+	 * the check is skipped)
+	 */
+	local_fam = ovpn_nl_family_get(attrs[OVPN_A_PEER_LOCAL_IPV4],
+				       attrs[OVPN_A_PEER_LOCAL_IPV6]);
+	remote_fam = ovpn_nl_family_get(attrs[OVPN_A_PEER_REMOTE_IPV4],
+					attrs[OVPN_A_PEER_REMOTE_IPV6]);
+	if (local_fam != AF_UNSPEC && remote_fam != AF_UNSPEC &&
+	    local_fam != remote_fam) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "mismatching local and remote address families");
+		return -EINVAL;
+	}
+
+	if (remote_fam != AF_INET6 && attrs[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID]) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "cannot specify scope id without remote IPv6 address");
+		return -EINVAL;
+	}
+
+	/* VPN IPs are needed only in MP mode for selecting the right peer */
+	if (ovpn->mode == OVPN_MODE_P2P && (attrs[OVPN_A_PEER_VPN_IPV4] ||
+					    attrs[OVPN_A_PEER_VPN_IPV6])) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "unexpected VPN IP in P2P mode");
+		return -EINVAL;
+	}
+
+	if ((attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL] &&
+	     !attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]) ||
+	    (!attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL] &&
+	     attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT])) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "keepalive interval and timeout are required together");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * ovpn_nl_peer_modify - modify the peer attributes according to the incoming msg
+ * @peer: the peer to modify
+ * @info: generic netlink info from the user request
+ * @attrs: the attributes from the user request
+ *
+ * Return: a negative error code in case of failure, 0 on success or 1 on
+ *	   success and the VPN IPs have been modified (requires rehashing in MP
+ *	   mode)
+ */
+static int ovpn_nl_peer_modify(struct ovpn_peer *peer, struct genl_info *info,
+			       struct nlattr **attrs)
+{
+	struct sockaddr_storage ss = {};
+	void *local_ip = NULL;
+	u32 interv, timeout;
+	bool rehash = false;
+	int ret;
+
+	spin_lock_bh(&peer->lock);
+
+	if (ovpn_nl_attr_sockaddr_remote(attrs, &ss)) {
+		/* we carry the local IP in a generic container.
+		 * ovpn_peer_reset_sockaddr() will properly interpret it
+		 * based on ss.ss_family
+		 */
+		local_ip = ovpn_nl_attr_local_ip(attrs);
+
+		/* set peer sockaddr */
+		ret = ovpn_peer_reset_sockaddr(peer, &ss, local_ip);
+		if (ret < 0) {
+			NL_SET_ERR_MSG_FMT_MOD(info->extack,
+					       "cannot set peer sockaddr: %d",
+					       ret);
+			goto err_unlock;
+		}
+		dst_cache_reset(&peer->dst_cache);
+	}
+
+	if (attrs[OVPN_A_PEER_VPN_IPV4]) {
+		rehash = true;
+		peer->vpn_addrs.ipv4.s_addr =
+			nla_get_in_addr(attrs[OVPN_A_PEER_VPN_IPV4]);
+	}
+
+	if (attrs[OVPN_A_PEER_VPN_IPV6]) {
+		rehash = true;
+		peer->vpn_addrs.ipv6 =
+			nla_get_in6_addr(attrs[OVPN_A_PEER_VPN_IPV6]);
+	}
+
+	/* when setting the keepalive, both parameters have to be configured */
+	if (attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL] &&
+	    attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]) {
+		interv = nla_get_u32(attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL]);
+		timeout = nla_get_u32(attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]);
+		ovpn_peer_keepalive_set(peer, interv, timeout);
+	}
+
+	netdev_dbg(peer->ovpn->dev,
+		   "modify peer id=%u endpoint=%pIScp VPN-IPv4=%pI4 VPN-IPv6=%pI6c\n",
+		   peer->id, &ss,
+		   &peer->vpn_addrs.ipv4.s_addr, &peer->vpn_addrs.ipv6);
+
+	spin_unlock_bh(&peer->lock);
+
+	return rehash ? 1 : 0;
+err_unlock:
+	spin_unlock_bh(&peer->lock);
+	return ret;
+}
+
+int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr *attrs[OVPN_A_PEER_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_socket *ovpn_sock;
+	struct socket *sock = NULL;
+	struct ovpn_peer *peer;
+	u32 sockfd, peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER],
+			       ovpn_peer_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	ret = ovpn_nl_peer_precheck(ovpn, info, attrs);
+	if (ret < 0)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs,
+			      OVPN_A_PEER_SOCKET))
+		return -EINVAL;
+
+	/* in MP mode VPN IPs are required for selecting the right peer */
+	if (ovpn->mode == OVPN_MODE_MP && !attrs[OVPN_A_PEER_VPN_IPV4] &&
+	    !attrs[OVPN_A_PEER_VPN_IPV6]) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "VPN IP must be provided in MP mode");
+		return -EINVAL;
+	}
+
+	peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]);
+	peer = ovpn_peer_new(ovpn, peer_id);
+	if (IS_ERR(peer)) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot create new peer object for peer %u: %ld",
+				       peer_id, PTR_ERR(peer));
+		return PTR_ERR(peer);
+	}
+
+	/* lookup the fd in the kernel table and extract the socket object */
+	sockfd = nla_get_u32(attrs[OVPN_A_PEER_SOCKET]);
+	/* sockfd_lookup() increases sock's refcounter */
+	sock = sockfd_lookup(sockfd, &ret);
+	if (!sock) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot lookup peer socket (fd=%u): %d",
+				       sockfd, ret);
+		ret = -ENOTSOCK;
+		goto peer_release;
+	}
+
+	/* Only when using UDP as transport protocol the remote endpoint
+	 * can be configured so that ovpn knows where to send packets to.
+	 */
+	if (sock->sk->sk_protocol == IPPROTO_UDP &&
+	    !attrs[OVPN_A_PEER_REMOTE_IPV4] &&
+	    !attrs[OVPN_A_PEER_REMOTE_IPV6]) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "missing remote IP address for UDP socket");
+		sockfd_put(sock);
+		ret = -EINVAL;
+		goto peer_release;
+	}
+
+	/* In case of TCP, the socket is connected to the peer and ovpn
+	 * will just send bytes over it, without the need to specify a
+	 * destination.
+	 */
+	if (sock->sk->sk_protocol == IPPROTO_TCP &&
+	    (attrs[OVPN_A_PEER_REMOTE_IPV4] ||
+	     attrs[OVPN_A_PEER_REMOTE_IPV6])) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "unexpected remote IP address with TCP socket");
+		sockfd_put(sock);
+		ret = -EINVAL;
+		goto peer_release;
+	}
+
+	ovpn_sock = ovpn_socket_new(sock, peer);
+	/* at this point we unconditionally drop the reference to the socket:
+	 * - in case of error, the socket has to be dropped
+	 * - if case of success, the socket is configured and let
+	 *   userspace own the reference, so that the latter can
+	 *   trigger the final close()
+	 */
+	sockfd_put(sock);
+	if (IS_ERR(ovpn_sock)) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot encapsulate socket: %ld",
+				       PTR_ERR(ovpn_sock));
+		ret = -ENOTSOCK;
+		goto peer_release;
+	}
+
+	rcu_assign_pointer(peer->sock, ovpn_sock);
+
+	ret = ovpn_nl_peer_modify(peer, info, attrs);
+	if (ret < 0)
+		goto sock_release;
+
+	ret = ovpn_peer_add(ovpn, peer);
+	if (ret < 0) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot add new peer (id=%u) to hashtable: %d",
+				       peer->id, ret);
+		goto sock_release;
+	}
+
+	return 0;
+
+sock_release:
+	ovpn_socket_release(peer);
+peer_release:
+	/* release right away because peer was not yet hashed, thus it is not
+	 * used in any context
+	 */
+	ovpn_peer_release(peer);
+
+	return ret;
+}
+
+int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr *attrs[OVPN_A_PEER_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_socket *sock;
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER],
+			       ovpn_peer_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	ret = ovpn_nl_peer_precheck(ovpn, info, attrs);
+	if (ret < 0)
+		return ret;
+
+	if (attrs[OVPN_A_PEER_SOCKET]) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "socket cannot be modified");
+		return -EINVAL;
+	}
+
+	peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot find peer with id %u", peer_id);
+		return -ENOENT;
+	}
+
+	/* when using a TCP socket the remote IP is not expected */
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (sock && sock->sock->sk->sk_protocol == IPPROTO_TCP &&
+	    (attrs[OVPN_A_PEER_REMOTE_IPV4] ||
+	     attrs[OVPN_A_PEER_REMOTE_IPV6])) {
+		rcu_read_unlock();
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "unexpected remote IP address with TCP socket");
+		ovpn_peer_put(peer);
+		return -EINVAL;
+	}
+	rcu_read_unlock();
+
+	spin_lock_bh(&ovpn->lock);
+	ret = ovpn_nl_peer_modify(peer, info, attrs);
+	if (ret < 0) {
+		spin_unlock_bh(&ovpn->lock);
+		ovpn_peer_put(peer);
+		return ret;
+	}
+
+	/* ret == 1 means that VPN IPv4/6 has been modified and rehashing
+	 * is required
+	 */
+	if (ret > 0)
+		ovpn_peer_hash_vpn_ip(peer);
+	spin_unlock_bh(&ovpn->lock);
+	ovpn_peer_put(peer);
+
+	return 0;
+}
+
+static int ovpn_nl_send_peer(struct sk_buff *skb, const struct genl_info *info,
+			     const struct ovpn_peer *peer, u32 portid, u32 seq,
+			     int flags)
+{
+	const struct ovpn_bind *bind;
+	struct ovpn_socket *sock;
+	int ret = -EMSGSIZE;
+	struct nlattr *attr;
+	__be16 local_port;
+	void *hdr;
+	int id;
+
+	hdr = genlmsg_put(skb, portid, seq, &ovpn_nl_family, flags,
+			  OVPN_CMD_PEER_GET);
+	if (!hdr)
+		return -ENOBUFS;
+
+	attr = nla_nest_start(skb, OVPN_A_PEER);
+	if (!attr)
+		goto err;
+
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (!sock) {
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+
+	if (!net_eq(genl_info_net(info), sock_net(sock->sock->sk))) {
+		id = peernet2id_alloc(genl_info_net(info),
+				      sock_net(sock->sock->sk),
+				      GFP_ATOMIC);
+		if (nla_put_s32(skb, OVPN_A_PEER_SOCKET_NETNSID, id))
+			goto err_unlock;
+	}
+	local_port = inet_sk(sock->sock->sk)->inet_sport;
+	rcu_read_unlock();
+
+	if (nla_put_u32(skb, OVPN_A_PEER_ID, peer->id))
+		goto err;
+
+	if (peer->vpn_addrs.ipv4.s_addr != htonl(INADDR_ANY))
+		if (nla_put_in_addr(skb, OVPN_A_PEER_VPN_IPV4,
+				    peer->vpn_addrs.ipv4.s_addr))
+			goto err;
+
+	if (!ipv6_addr_equal(&peer->vpn_addrs.ipv6, &in6addr_any))
+		if (nla_put_in6_addr(skb, OVPN_A_PEER_VPN_IPV6,
+				     &peer->vpn_addrs.ipv6))
+			goto err;
+
+	if (nla_put_u32(skb, OVPN_A_PEER_KEEPALIVE_INTERVAL,
+			peer->keepalive_interval) ||
+	    nla_put_u32(skb, OVPN_A_PEER_KEEPALIVE_TIMEOUT,
+			peer->keepalive_timeout))
+		goto err;
+
+	rcu_read_lock();
+	bind = rcu_dereference(peer->bind);
+	if (bind) {
+		if (bind->remote.in4.sin_family == AF_INET) {
+			if (nla_put_in_addr(skb, OVPN_A_PEER_REMOTE_IPV4,
+					    bind->remote.in4.sin_addr.s_addr) ||
+			    nla_put_net16(skb, OVPN_A_PEER_REMOTE_PORT,
+					  bind->remote.in4.sin_port) ||
+			    nla_put_in_addr(skb, OVPN_A_PEER_LOCAL_IPV4,
+					    bind->local.ipv4.s_addr))
+				goto err_unlock;
+		} else if (bind->remote.in4.sin_family == AF_INET6) {
+			if (nla_put_in6_addr(skb, OVPN_A_PEER_REMOTE_IPV6,
+					     &bind->remote.in6.sin6_addr) ||
+			    nla_put_u32(skb, OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID,
+					bind->remote.in6.sin6_scope_id) ||
+			    nla_put_net16(skb, OVPN_A_PEER_REMOTE_PORT,
+					  bind->remote.in6.sin6_port) ||
+			    nla_put_in6_addr(skb, OVPN_A_PEER_LOCAL_IPV6,
+					     &bind->local.ipv6))
+				goto err_unlock;
+		}
+	}
+	rcu_read_unlock();
+
+	if (nla_put_net16(skb, OVPN_A_PEER_LOCAL_PORT, local_port) ||
+	    /* VPN RX stats */
+	    nla_put_uint(skb, OVPN_A_PEER_VPN_RX_BYTES,
+			 atomic64_read(&peer->vpn_stats.rx.bytes)) ||
+	    nla_put_uint(skb, OVPN_A_PEER_VPN_RX_PACKETS,
+			 atomic64_read(&peer->vpn_stats.rx.packets)) ||
+	    /* VPN TX stats */
+	    nla_put_uint(skb, OVPN_A_PEER_VPN_TX_BYTES,
+			 atomic64_read(&peer->vpn_stats.tx.bytes)) ||
+	    nla_put_uint(skb, OVPN_A_PEER_VPN_TX_PACKETS,
+			 atomic64_read(&peer->vpn_stats.tx.packets)) ||
+	    /* link RX stats */
+	    nla_put_uint(skb, OVPN_A_PEER_LINK_RX_BYTES,
+			 atomic64_read(&peer->link_stats.rx.bytes)) ||
+	    nla_put_uint(skb, OVPN_A_PEER_LINK_RX_PACKETS,
+			 atomic64_read(&peer->link_stats.rx.packets)) ||
+	    /* link TX stats */
+	    nla_put_uint(skb, OVPN_A_PEER_LINK_TX_BYTES,
+			 atomic64_read(&peer->link_stats.tx.bytes)) ||
+	    nla_put_uint(skb, OVPN_A_PEER_LINK_TX_PACKETS,
+			 atomic64_read(&peer->link_stats.tx.packets)))
+		goto err;
+
+	nla_nest_end(skb, attr);
+	genlmsg_end(skb, hdr);
+
+	return 0;
+err_unlock:
+	rcu_read_unlock();
+err:
+	genlmsg_cancel(skb, hdr);
+	return ret;
+}
+
+int ovpn_nl_peer_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr *attrs[OVPN_A_PEER_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_peer *peer;
+	struct sk_buff *msg;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER],
+			       ovpn_peer_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs,
+			      OVPN_A_PEER_ID))
+		return -EINVAL;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot find peer with id %u", peer_id);
+		return -ENOENT;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ret = ovpn_nl_send_peer(msg, info, peer, info->snd_portid,
+				info->snd_seq, 0);
+	if (ret < 0) {
+		nlmsg_free(msg);
+		goto err;
+	}
+
+	ret = genlmsg_reply(msg, info);
+err:
+	ovpn_peer_put(peer);
+	return ret;
+}
+
+int ovpn_nl_peer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	const struct genl_info *info = genl_info_dump(cb);
+	int bkt, last_idx = cb->args[1], dumped = 0;
+	netdevice_tracker tracker;
+	struct ovpn_priv *ovpn;
+	struct ovpn_peer *peer;
+
+	ovpn = ovpn_get_dev_from_attrs(sock_net(cb->skb->sk), info, &tracker);
+	if (IS_ERR(ovpn))
+		return PTR_ERR(ovpn);
+
+	if (ovpn->mode == OVPN_MODE_P2P) {
+		/* if we already dumped a peer it means we are done */
+		if (last_idx)
+			goto out;
+
+		rcu_read_lock();
+		peer = rcu_dereference(ovpn->peer);
+		if (peer) {
+			if (ovpn_nl_send_peer(skb, info, peer,
+					      NETLINK_CB(cb->skb).portid,
+					      cb->nlh->nlmsg_seq,
+					      NLM_F_MULTI) == 0)
+				dumped++;
+		}
+		rcu_read_unlock();
+	} else {
+		rcu_read_lock();
+		hash_for_each_rcu(ovpn->peers->by_id, bkt, peer,
+				  hash_entry_id) {
+			/* skip already dumped peers that were dumped by
+			 * previous invocations
+			 */
+			if (last_idx > 0) {
+				last_idx--;
+				continue;
+			}
+
+			if (ovpn_nl_send_peer(skb, info, peer,
+					      NETLINK_CB(cb->skb).portid,
+					      cb->nlh->nlmsg_seq,
+					      NLM_F_MULTI) < 0)
+				break;
+
+			/* count peers being dumped during this invocation */
+			dumped++;
+		}
+		rcu_read_unlock();
+	}
+
+out:
+	netdev_put(ovpn->dev, &tracker);
+
+	/* sum up peers dumped in this message, so that at the next invocation
+	 * we can continue from where we left
+	 */
+	cb->args[1] += dumped;
+	return skb->len;
+}
+
+int ovpn_nl_peer_del_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr *attrs[OVPN_A_PEER_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER],
+			       ovpn_peer_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs,
+			      OVPN_A_PEER_ID))
+		return -EINVAL;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot find peer with id %u", peer_id);
+		return -ENOENT;
+	}
+
+	netdev_dbg(ovpn->dev, "del peer %u\n", peer->id);
+	ret = ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_USERSPACE);
+	ovpn_peer_put(peer);
+
+	return ret;
+}
+
+static int ovpn_nl_get_key_dir(struct genl_info *info, struct nlattr *key,
+			       enum ovpn_cipher_alg cipher,
+			       struct ovpn_key_direction *dir)
+{
+	struct nlattr *attrs[OVPN_A_KEYDIR_MAX + 1];
+	int ret;
+
+	ret = nla_parse_nested(attrs, OVPN_A_KEYDIR_MAX, key,
+			       ovpn_keydir_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	switch (cipher) {
+	case OVPN_CIPHER_ALG_AES_GCM:
+	case OVPN_CIPHER_ALG_CHACHA20_POLY1305:
+		if (NL_REQ_ATTR_CHECK(info->extack, key, attrs,
+				      OVPN_A_KEYDIR_CIPHER_KEY) ||
+		    NL_REQ_ATTR_CHECK(info->extack, key, attrs,
+				      OVPN_A_KEYDIR_NONCE_TAIL))
+			return -EINVAL;
+
+		dir->cipher_key = nla_data(attrs[OVPN_A_KEYDIR_CIPHER_KEY]);
+		dir->cipher_key_size = nla_len(attrs[OVPN_A_KEYDIR_CIPHER_KEY]);
+
+		/* These algorithms require a 96bit nonce,
+		 * Construct it by combining 4-bytes packet id and
+		 * 8-bytes nonce-tail from userspace
+		 */
+		dir->nonce_tail = nla_data(attrs[OVPN_A_KEYDIR_NONCE_TAIL]);
+		dir->nonce_tail_size = nla_len(attrs[OVPN_A_KEYDIR_NONCE_TAIL]);
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(info->extack, "unsupported cipher");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * ovpn_nl_key_new_doit - configure a new key for the specified peer
+ * @skb: incoming netlink message
+ * @info: genetlink metadata
+ *
+ * This function allows the user to install a new key in the peer crypto
+ * state.
+ * Each peer has two 'slots', namely 'primary' and 'secondary', where
+ * keys can be installed. The key in the 'primary' slot is used for
+ * encryption, while both keys can be used for decryption by matching the
+ * key ID carried in the incoming packet.
+ *
+ * The user is responsible for rotating keys when necessary. The user
+ * may fetch peer traffic statistics via netlink in order to better
+ * identify the right time to rotate keys.
+ * The renegotiation follows these steps:
+ * 1. a new key is computed by the user and is installed in the 'secondary'
+ *    slot
+ * 2. at user discretion (usually after a predetermined time) 'primary' and
+ *    'secondary' contents are swapped and the new key starts being used for
+ *    encryption, while the old key is kept around for decryption of late
+ *    packets.
+ *
+ * Return: 0 on success or a negative error code otherwise.
+ */
+int ovpn_nl_key_new_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr *attrs[OVPN_A_KEYCONF_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_peer_key_reset pkr;
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX,
+			       info->attrs[OVPN_A_KEYCONF],
+			       ovpn_keyconf_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_PEER_ID))
+		return -EINVAL;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_SLOT) ||
+	    NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_KEY_ID) ||
+	    NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_CIPHER_ALG) ||
+	    NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_ENCRYPT_DIR) ||
+	    NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_DECRYPT_DIR))
+		return -EINVAL;
+
+	pkr.slot = nla_get_u32(attrs[OVPN_A_KEYCONF_SLOT]);
+	pkr.key.key_id = nla_get_u32(attrs[OVPN_A_KEYCONF_KEY_ID]);
+	pkr.key.cipher_alg = nla_get_u32(attrs[OVPN_A_KEYCONF_CIPHER_ALG]);
+
+	ret = ovpn_nl_get_key_dir(info, attrs[OVPN_A_KEYCONF_ENCRYPT_DIR],
+				  pkr.key.cipher_alg, &pkr.key.encrypt);
+	if (ret < 0)
+		return ret;
+
+	ret = ovpn_nl_get_key_dir(info, attrs[OVPN_A_KEYCONF_DECRYPT_DIR],
+				  pkr.key.cipher_alg, &pkr.key.decrypt);
+	if (ret < 0)
+		return ret;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "no peer with id %u to set key for",
+				       peer_id);
+		return -ENOENT;
+	}
+
+	ret = ovpn_crypto_state_reset(&peer->crypto, &pkr);
+	if (ret < 0) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot install new key for peer %u",
+				       peer_id);
+		goto out;
+	}
+
+	netdev_dbg(ovpn->dev, "new key installed (id=%u) for peer %u\n",
+		   pkr.key.key_id, peer_id);
+out:
+	ovpn_peer_put(peer);
+	return ret;
+}
+
+static int ovpn_nl_send_key(struct sk_buff *skb, const struct genl_info *info,
+			    u32 peer_id, enum ovpn_key_slot slot,
+			    const struct ovpn_key_config *keyconf)
+{
+	struct nlattr *attr;
+	void *hdr;
+
+	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, &ovpn_nl_family,
+			  0, OVPN_CMD_KEY_GET);
+	if (!hdr)
+		return -ENOBUFS;
+
+	attr = nla_nest_start(skb, OVPN_A_KEYCONF);
+	if (!attr)
+		goto err;
+
+	if (nla_put_u32(skb, OVPN_A_KEYCONF_PEER_ID, peer_id))
+		goto err;
+
+	if (nla_put_u32(skb, OVPN_A_KEYCONF_SLOT, slot) ||
+	    nla_put_u32(skb, OVPN_A_KEYCONF_KEY_ID, keyconf->key_id) ||
+	    nla_put_u32(skb, OVPN_A_KEYCONF_CIPHER_ALG, keyconf->cipher_alg))
+		goto err;
+
+	nla_nest_end(skb, attr);
+	genlmsg_end(skb, hdr);
+
+	return 0;
+err:
+	genlmsg_cancel(skb, hdr);
+	return -EMSGSIZE;
+}
+
+int ovpn_nl_key_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr *attrs[OVPN_A_KEYCONF_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_key_config keyconf = { 0 };
+	enum ovpn_key_slot slot;
+	struct ovpn_peer *peer;
+	struct sk_buff *msg;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX,
+			       info->attrs[OVPN_A_KEYCONF],
+			       ovpn_keyconf_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_PEER_ID))
+		return -EINVAL;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_SLOT))
+		return -EINVAL;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot find peer with id %u", peer_id);
+		return -ENOENT;
+	}
+
+	slot = nla_get_u32(attrs[OVPN_A_KEYCONF_SLOT]);
+
+	ret = ovpn_crypto_config_get(&peer->crypto, slot, &keyconf);
+	if (ret < 0) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot extract key from slot %u for peer %u",
+				       slot, peer_id);
+		goto err;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ret = ovpn_nl_send_key(msg, info, peer->id, slot, &keyconf);
+	if (ret < 0) {
+		nlmsg_free(msg);
+		goto err;
+	}
+
+	ret = genlmsg_reply(msg, info);
+err:
+	ovpn_peer_put(peer);
+	return ret;
+}
+
+int ovpn_nl_key_swap_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct nlattr *attrs[OVPN_A_PEER_MAX + 1];
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX,
+			       info->attrs[OVPN_A_KEYCONF],
+			       ovpn_keyconf_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_PEER_ID))
+		return -EINVAL;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "no peer with id %u to swap keys for",
+				       peer_id);
+		return -ENOENT;
+	}
+
+	ovpn_crypto_key_slots_swap(&peer->crypto);
+	ovpn_peer_put(peer);
+
+	return 0;
+}
+
+int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr *attrs[OVPN_A_KEYCONF_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	enum ovpn_key_slot slot;
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX,
+			       info->attrs[OVPN_A_KEYCONF],
+			       ovpn_keyconf_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_PEER_ID))
+		return -EINVAL;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_SLOT))
+		return -EINVAL;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]);
+	slot = nla_get_u32(attrs[OVPN_A_KEYCONF_SLOT]);
+
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "no peer with id %u to delete key for",
+				       peer_id);
+		return -ENOENT;
+	}
+
+	ovpn_crypto_key_slot_delete(&peer->crypto, slot);
+	ovpn_peer_put(peer);
+
+	return 0;
+}
+
+/**
+ * ovpn_nl_peer_del_notify - notify userspace about peer being deleted
+ * @peer: the peer being deleted
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_nl_peer_del_notify(struct ovpn_peer *peer)
+{
+	struct ovpn_socket *sock;
+	struct sk_buff *msg;
+	struct nlattr *attr;
+	int ret = -EMSGSIZE;
+	void *hdr;
+
+	netdev_info(peer->ovpn->dev, "deleting peer with id %u, reason %d\n",
+		    peer->id, peer->delete_reason);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, 0, 0, &ovpn_nl_family, 0, OVPN_CMD_PEER_DEL_NTF);
+	if (!hdr) {
+		ret = -ENOBUFS;
+		goto err_free_msg;
+	}
+
+	if (nla_put_u32(msg, OVPN_A_IFINDEX, peer->ovpn->dev->ifindex))
+		goto err_cancel_msg;
+
+	attr = nla_nest_start(msg, OVPN_A_PEER);
+	if (!attr)
+		goto err_cancel_msg;
+
+	if (nla_put_u32(msg, OVPN_A_PEER_DEL_REASON, peer->delete_reason))
+		goto err_cancel_msg;
+
+	if (nla_put_u32(msg, OVPN_A_PEER_ID, peer->id))
+		goto err_cancel_msg;
+
+	nla_nest_end(msg, attr);
+
+	genlmsg_end(msg, hdr);
+
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (!sock) {
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+	genlmsg_multicast_netns(&ovpn_nl_family, sock_net(sock->sock->sk),
+				msg, 0, OVPN_NLGRP_PEERS, GFP_ATOMIC);
+	rcu_read_unlock();
+
+	return 0;
+
+err_unlock:
+	rcu_read_unlock();
+err_cancel_msg:
+	genlmsg_cancel(msg, hdr);
+err_free_msg:
+	nlmsg_free(msg);
+	return ret;
+}
+
+/**
+ * ovpn_nl_key_swap_notify - notify userspace peer's key must be renewed
+ * @peer: the peer whose key needs to be renewed
+ * @key_id: the ID of the key that needs to be renewed
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_nl_key_swap_notify(struct ovpn_peer *peer, u8 key_id)
+{
+	struct ovpn_socket *sock;
+	struct nlattr *k_attr;
+	struct sk_buff *msg;
+	int ret = -EMSGSIZE;
+	void *hdr;
+
+	netdev_info(peer->ovpn->dev, "peer with id %u must rekey - primary key unusable.\n",
+		    peer->id);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, 0, 0, &ovpn_nl_family, 0, OVPN_CMD_KEY_SWAP_NTF);
+	if (!hdr) {
+		ret = -ENOBUFS;
+		goto err_free_msg;
+	}
+
+	if (nla_put_u32(msg, OVPN_A_IFINDEX, peer->ovpn->dev->ifindex))
+		goto err_cancel_msg;
+
+	k_attr = nla_nest_start(msg, OVPN_A_KEYCONF);
+	if (!k_attr)
+		goto err_cancel_msg;
+
+	if (nla_put_u32(msg, OVPN_A_KEYCONF_PEER_ID, peer->id))
+		goto err_cancel_msg;
+
+	if (nla_put_u16(msg, OVPN_A_KEYCONF_KEY_ID, key_id))
+		goto err_cancel_msg;
+
+	nla_nest_end(msg, k_attr);
+	genlmsg_end(msg, hdr);
+
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (!sock) {
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+	genlmsg_multicast_netns(&ovpn_nl_family, sock_net(sock->sock->sk),
+				msg, 0, OVPN_NLGRP_PEERS, GFP_ATOMIC);
+	rcu_read_unlock();
+
+	return 0;
+err_unlock:
+	rcu_read_unlock();
+err_cancel_msg:
+	genlmsg_cancel(msg, hdr);
+err_free_msg:
+	nlmsg_free(msg);
+	return ret;
+}
+
+/**
+ * ovpn_nl_register - perform any needed registration in the NL subsustem
+ *
+ * Return: 0 on success, a negative error code otherwise
+ */
+int __init ovpn_nl_register(void)
+{
+	int ret = genl_register_family(&ovpn_nl_family);
+
+	if (ret) {
+		pr_err("ovpn: genl_register_family failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * ovpn_nl_unregister - undo any module wide netlink registration
+ */
+void ovpn_nl_unregister(void)
+{
+	genl_unregister_family(&ovpn_nl_family);
+}
diff --git a/drivers/net/ovpn/netlink.h b/drivers/net/ovpn/netlink.h
new file mode 100644
index 000000000000..8615dfc3c472
--- /dev/null
+++ b/drivers/net/ovpn/netlink.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_NETLINK_H_
+#define _NET_OVPN_NETLINK_H_
+
+int ovpn_nl_register(void);
+void ovpn_nl_unregister(void);
+
+int ovpn_nl_peer_del_notify(struct ovpn_peer *peer);
+int ovpn_nl_key_swap_notify(struct ovpn_peer *peer, u8 key_id);
+
+#endif /* _NET_OVPN_NETLINK_H_ */
diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h
new file mode 100644
index 000000000000..5898f6adada7
--- /dev/null
+++ b/drivers/net/ovpn/ovpnpriv.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNSTRUCT_H_
+#define _NET_OVPN_OVPNSTRUCT_H_
+
+#include <linux/workqueue.h>
+#include <net/gro_cells.h>
+#include <uapi/linux/if_link.h>
+#include <uapi/linux/ovpn.h>
+
+/**
+ * struct ovpn_peer_collection - container of peers for MultiPeer mode
+ * @by_id: table of peers index by ID
+ * @by_vpn_addr4: table of peers indexed by VPN IPv4 address (items can be
+ *		  rehashed on the fly due to peer IP change)
+ * @by_vpn_addr6: table of peers indexed by VPN IPv6 address (items can be
+ *		  rehashed on the fly due to peer IP change)
+ * @by_transp_addr: table of peers indexed by transport address (items can be
+ *		    rehashed on the fly due to peer IP change)
+ */
+struct ovpn_peer_collection {
+	DECLARE_HASHTABLE(by_id, 12);
+	struct hlist_nulls_head by_vpn_addr4[1 << 12];
+	struct hlist_nulls_head by_vpn_addr6[1 << 12];
+	struct hlist_nulls_head by_transp_addr[1 << 12];
+};
+
+/**
+ * struct ovpn_priv - per ovpn interface state
+ * @dev: the actual netdev representing the tunnel
+ * @mode: device operation mode (i.e. p2p, mp, ..)
+ * @lock: protect this object
+ * @peers: data structures holding multi-peer references
+ * @peer: in P2P mode, this is the only remote peer
+ * @gro_cells: pointer to the Generic Receive Offload cell
+ * @keepalive_work: struct used to schedule keepalive periodic job
+ */
+struct ovpn_priv {
+	struct net_device *dev;
+	enum ovpn_mode mode;
+	spinlock_t lock; /* protect writing to the ovpn_priv object */
+	struct ovpn_peer_collection *peers;
+	struct ovpn_peer __rcu *peer;
+	struct gro_cells gro_cells;
+	struct delayed_work keepalive_work;
+};
+
+#endif /* _NET_OVPN_OVPNSTRUCT_H_ */
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
new file mode 100644
index 000000000000..a1fd27b9c038
--- /dev/null
+++ b/drivers/net/ovpn/peer.c
@@ -0,0 +1,1364 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/skbuff.h>
+#include <linux/list.h>
+#include <linux/hashtable.h>
+#include <net/ip6_route.h>
+
+#include "ovpnpriv.h"
+#include "bind.h"
+#include "pktid.h"
+#include "crypto.h"
+#include "io.h"
+#include "main.h"
+#include "netlink.h"
+#include "peer.h"
+#include "socket.h"
+
+static void unlock_ovpn(struct ovpn_priv *ovpn,
+			 struct llist_head *release_list)
+	__releases(&ovpn->lock)
+{
+	struct ovpn_peer *peer;
+
+	spin_unlock_bh(&ovpn->lock);
+
+	llist_for_each_entry(peer, release_list->first, release_entry) {
+		ovpn_socket_release(peer);
+		ovpn_peer_put(peer);
+	}
+}
+
+/**
+ * ovpn_peer_keepalive_set - configure keepalive values for peer
+ * @peer: the peer to configure
+ * @interval: outgoing keepalive interval
+ * @timeout: incoming keepalive timeout
+ */
+void ovpn_peer_keepalive_set(struct ovpn_peer *peer, u32 interval, u32 timeout)
+{
+	time64_t now = ktime_get_real_seconds();
+
+	netdev_dbg(peer->ovpn->dev,
+		   "scheduling keepalive for peer %u: interval=%u timeout=%u\n",
+		   peer->id, interval, timeout);
+
+	peer->keepalive_interval = interval;
+	WRITE_ONCE(peer->last_sent, now);
+	peer->keepalive_xmit_exp = now + interval;
+
+	peer->keepalive_timeout = timeout;
+	WRITE_ONCE(peer->last_recv, now);
+	peer->keepalive_recv_exp = now + timeout;
+
+	/* now that interval and timeout have been changed, kick
+	 * off the worker so that the next delay can be recomputed
+	 */
+	mod_delayed_work(system_wq, &peer->ovpn->keepalive_work, 0);
+}
+
+/**
+ * ovpn_peer_keepalive_send - periodic worker sending keepalive packets
+ * @work: pointer to the work member of the related peer object
+ *
+ * NOTE: the reference to peer is not dropped because it gets inherited
+ * by ovpn_xmit_special()
+ */
+static void ovpn_peer_keepalive_send(struct work_struct *work)
+{
+	struct ovpn_peer *peer = container_of(work, struct ovpn_peer,
+					      keepalive_work);
+
+	local_bh_disable();
+	ovpn_xmit_special(peer, ovpn_keepalive_message,
+			  sizeof(ovpn_keepalive_message));
+	local_bh_enable();
+}
+
+/**
+ * ovpn_peer_new - allocate and initialize a new peer object
+ * @ovpn: the openvpn instance inside which the peer should be created
+ * @id: the ID assigned to this peer
+ *
+ * Return: a pointer to the new peer on success or an error code otherwise
+ */
+struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id)
+{
+	struct ovpn_peer *peer;
+	int ret;
+
+	/* alloc and init peer object */
+	peer = kzalloc(sizeof(*peer), GFP_KERNEL);
+	if (!peer)
+		return ERR_PTR(-ENOMEM);
+
+	peer->id = id;
+	peer->ovpn = ovpn;
+
+	peer->vpn_addrs.ipv4.s_addr = htonl(INADDR_ANY);
+	peer->vpn_addrs.ipv6 = in6addr_any;
+
+	RCU_INIT_POINTER(peer->bind, NULL);
+	ovpn_crypto_state_init(&peer->crypto);
+	spin_lock_init(&peer->lock);
+	kref_init(&peer->refcount);
+	ovpn_peer_stats_init(&peer->vpn_stats);
+	ovpn_peer_stats_init(&peer->link_stats);
+	INIT_WORK(&peer->keepalive_work, ovpn_peer_keepalive_send);
+
+	ret = dst_cache_init(&peer->dst_cache, GFP_KERNEL);
+	if (ret < 0) {
+		netdev_err(ovpn->dev,
+			   "cannot initialize dst cache for peer %u\n",
+			   peer->id);
+		kfree(peer);
+		return ERR_PTR(ret);
+	}
+
+	netdev_hold(ovpn->dev, &peer->dev_tracker, GFP_KERNEL);
+
+	return peer;
+}
+
+/**
+ * ovpn_peer_reset_sockaddr - recreate binding for peer
+ * @peer: peer to recreate the binding for
+ * @ss: sockaddr to use as remote endpoint for the binding
+ * @local_ip: local IP for the binding
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer,
+			     const struct sockaddr_storage *ss,
+			     const void *local_ip)
+{
+	struct ovpn_bind *bind;
+	size_t ip_len;
+
+	lockdep_assert_held(&peer->lock);
+
+	/* create new ovpn_bind object */
+	bind = ovpn_bind_from_sockaddr(ss);
+	if (IS_ERR(bind))
+		return PTR_ERR(bind);
+
+	if (local_ip) {
+		if (ss->ss_family == AF_INET) {
+			ip_len = sizeof(struct in_addr);
+		} else if (ss->ss_family == AF_INET6) {
+			ip_len = sizeof(struct in6_addr);
+		} else {
+			net_dbg_ratelimited("%s: invalid family %u for remote endpoint for peer %u\n",
+					    netdev_name(peer->ovpn->dev),
+					    ss->ss_family, peer->id);
+			kfree(bind);
+			return -EINVAL;
+		}
+
+		memcpy(&bind->local, local_ip, ip_len);
+	}
+
+	/* set binding */
+	ovpn_bind_reset(peer, bind);
+
+	return 0;
+}
+
+/* variable name __tbl2 needs to be different from __tbl1
+ * in the macro below to avoid confusing clang
+ */
+#define ovpn_get_hash_slot(_tbl, _key, _key_len) ({	\
+	typeof(_tbl) *__tbl2 = &(_tbl);			\
+	jhash(_key, _key_len, 0) % HASH_SIZE(*__tbl2);	\
+})
+
+#define ovpn_get_hash_head(_tbl, _key, _key_len) ({		\
+	typeof(_tbl) *__tbl1 = &(_tbl);				\
+	&(*__tbl1)[ovpn_get_hash_slot(*__tbl1, _key, _key_len)];\
+})
+
+/**
+ * ovpn_peer_endpoints_update - update remote or local endpoint for peer
+ * @peer: peer to update the remote endpoint for
+ * @skb: incoming packet to retrieve the source/destination address from
+ */
+void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb)
+{
+	struct hlist_nulls_head *nhead;
+	struct sockaddr_storage ss;
+	struct sockaddr_in6 *sa6;
+	bool reset_cache = false;
+	struct sockaddr_in *sa;
+	struct ovpn_bind *bind;
+	const void *local_ip;
+	size_t salen = 0;
+
+	spin_lock_bh(&peer->lock);
+	bind = rcu_dereference_protected(peer->bind,
+					 lockdep_is_held(&peer->lock));
+	if (unlikely(!bind))
+		goto unlock;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		/* float check */
+		if (unlikely(!ovpn_bind_skb_src_match(bind, skb))) {
+			/* unconditionally save local endpoint in case
+			 * of float, as it may have changed as well
+			 */
+			local_ip = &ip_hdr(skb)->daddr;
+			sa = (struct sockaddr_in *)&ss;
+			sa->sin_family = AF_INET;
+			sa->sin_addr.s_addr = ip_hdr(skb)->saddr;
+			sa->sin_port = udp_hdr(skb)->source;
+			salen = sizeof(*sa);
+			reset_cache = true;
+			break;
+		}
+
+		/* if no float happened, let's double check if the local endpoint
+		 * has changed
+		 */
+		if (unlikely(bind->local.ipv4.s_addr != ip_hdr(skb)->daddr)) {
+			net_dbg_ratelimited("%s: learning local IPv4 for peer %d (%pI4 -> %pI4)\n",
+					    netdev_name(peer->ovpn->dev),
+					    peer->id, &bind->local.ipv4.s_addr,
+					    &ip_hdr(skb)->daddr);
+			bind->local.ipv4.s_addr = ip_hdr(skb)->daddr;
+			reset_cache = true;
+		}
+		break;
+	case htons(ETH_P_IPV6):
+		/* float check */
+		if (unlikely(!ovpn_bind_skb_src_match(bind, skb))) {
+			/* unconditionally save local endpoint in case
+			 * of float, as it may have changed as well
+			 */
+			local_ip = &ipv6_hdr(skb)->daddr;
+			sa6 = (struct sockaddr_in6 *)&ss;
+			sa6->sin6_family = AF_INET6;
+			sa6->sin6_addr = ipv6_hdr(skb)->saddr;
+			sa6->sin6_port = udp_hdr(skb)->source;
+			sa6->sin6_scope_id = ipv6_iface_scope_id(&ipv6_hdr(skb)->saddr,
+								 skb->skb_iif);
+			salen = sizeof(*sa6);
+			reset_cache = true;
+			break;
+		}
+
+		/* if no float happened, let's double check if the local endpoint
+		 * has changed
+		 */
+		if (unlikely(!ipv6_addr_equal(&bind->local.ipv6,
+					      &ipv6_hdr(skb)->daddr))) {
+			net_dbg_ratelimited("%s: learning local IPv6 for peer %d (%pI6c -> %pI6c)\n",
+					    netdev_name(peer->ovpn->dev),
+					    peer->id, &bind->local.ipv6,
+					    &ipv6_hdr(skb)->daddr);
+			bind->local.ipv6 = ipv6_hdr(skb)->daddr;
+			reset_cache = true;
+		}
+		break;
+	default:
+		goto unlock;
+	}
+
+	if (unlikely(reset_cache))
+		dst_cache_reset(&peer->dst_cache);
+
+	/* if the peer did not float, we can bail out now */
+	if (likely(!salen))
+		goto unlock;
+
+	if (unlikely(ovpn_peer_reset_sockaddr(peer,
+					      (struct sockaddr_storage *)&ss,
+					      local_ip) < 0))
+		goto unlock;
+
+	net_dbg_ratelimited("%s: peer %d floated to %pIScp",
+			    netdev_name(peer->ovpn->dev), peer->id, &ss);
+
+	spin_unlock_bh(&peer->lock);
+
+	/* rehashing is required only in MP mode as P2P has one peer
+	 * only and thus there is no hashtable
+	 */
+	if (peer->ovpn->mode == OVPN_MODE_MP) {
+		spin_lock_bh(&peer->ovpn->lock);
+		spin_lock_bh(&peer->lock);
+		bind = rcu_dereference_protected(peer->bind,
+						 lockdep_is_held(&peer->lock));
+		if (unlikely(!bind)) {
+			spin_unlock_bh(&peer->lock);
+			spin_unlock_bh(&peer->ovpn->lock);
+			return;
+		}
+
+		/* This function may be invoked concurrently, therefore another
+		 * float may have happened in parallel: perform rehashing
+		 * using the peer->bind->remote directly as key
+		 */
+
+		switch (bind->remote.in4.sin_family) {
+		case AF_INET:
+			salen = sizeof(*sa);
+			break;
+		case AF_INET6:
+			salen = sizeof(*sa6);
+			break;
+		}
+
+		/* remove old hashing */
+		hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr);
+		/* re-add with new transport address */
+		nhead = ovpn_get_hash_head(peer->ovpn->peers->by_transp_addr,
+					   &bind->remote, salen);
+		hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead);
+		spin_unlock_bh(&peer->lock);
+		spin_unlock_bh(&peer->ovpn->lock);
+	}
+	return;
+unlock:
+	spin_unlock_bh(&peer->lock);
+}
+
+/**
+ * ovpn_peer_release_rcu - RCU callback performing last peer release steps
+ * @head: RCU member of the ovpn_peer
+ */
+static void ovpn_peer_release_rcu(struct rcu_head *head)
+{
+	struct ovpn_peer *peer = container_of(head, struct ovpn_peer, rcu);
+
+	/* this call will immediately free the dst_cache, therefore we
+	 * perform it in the RCU callback, when all contexts are done
+	 */
+	dst_cache_destroy(&peer->dst_cache);
+	kfree(peer);
+}
+
+/**
+ * ovpn_peer_release - release peer private members
+ * @peer: the peer to release
+ */
+void ovpn_peer_release(struct ovpn_peer *peer)
+{
+	ovpn_crypto_state_release(&peer->crypto);
+	spin_lock_bh(&peer->lock);
+	ovpn_bind_reset(peer, NULL);
+	spin_unlock_bh(&peer->lock);
+	call_rcu(&peer->rcu, ovpn_peer_release_rcu);
+	netdev_put(peer->ovpn->dev, &peer->dev_tracker);
+}
+
+/**
+ * ovpn_peer_release_kref - callback for kref_put
+ * @kref: the kref object belonging to the peer
+ */
+void ovpn_peer_release_kref(struct kref *kref)
+{
+	struct ovpn_peer *peer = container_of(kref, struct ovpn_peer, refcount);
+
+	ovpn_peer_release(peer);
+}
+
+/**
+ * ovpn_peer_skb_to_sockaddr - fill sockaddr with skb source address
+ * @skb: the packet to extract data from
+ * @ss: the sockaddr to fill
+ *
+ * Return: sockaddr length on success or -1 otherwise
+ */
+static int ovpn_peer_skb_to_sockaddr(struct sk_buff *skb,
+				     struct sockaddr_storage *ss)
+{
+	struct sockaddr_in6 *sa6;
+	struct sockaddr_in *sa4;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		sa4 = (struct sockaddr_in *)ss;
+		sa4->sin_family = AF_INET;
+		sa4->sin_addr.s_addr = ip_hdr(skb)->saddr;
+		sa4->sin_port = udp_hdr(skb)->source;
+		return sizeof(*sa4);
+	case htons(ETH_P_IPV6):
+		sa6 = (struct sockaddr_in6 *)ss;
+		sa6->sin6_family = AF_INET6;
+		sa6->sin6_addr = ipv6_hdr(skb)->saddr;
+		sa6->sin6_port = udp_hdr(skb)->source;
+		return sizeof(*sa6);
+	}
+
+	return -1;
+}
+
+/**
+ * ovpn_nexthop_from_skb4 - retrieve IPv4 nexthop for outgoing skb
+ * @skb: the outgoing packet
+ *
+ * Return: the IPv4 of the nexthop
+ */
+static __be32 ovpn_nexthop_from_skb4(struct sk_buff *skb)
+{
+	const struct rtable *rt = skb_rtable(skb);
+
+	if (rt && rt->rt_uses_gateway)
+		return rt->rt_gw4;
+
+	return ip_hdr(skb)->daddr;
+}
+
+/**
+ * ovpn_nexthop_from_skb6 - retrieve IPv6 nexthop for outgoing skb
+ * @skb: the outgoing packet
+ *
+ * Return: the IPv6 of the nexthop
+ */
+static struct in6_addr ovpn_nexthop_from_skb6(struct sk_buff *skb)
+{
+	const struct rt6_info *rt = skb_rt6_info(skb);
+
+	if (!rt || !(rt->rt6i_flags & RTF_GATEWAY))
+		return ipv6_hdr(skb)->daddr;
+
+	return rt->rt6i_gateway;
+}
+
+/**
+ * ovpn_peer_get_by_vpn_addr4 - retrieve peer by its VPN IPv4 address
+ * @ovpn: the openvpn instance to search
+ * @addr: VPN IPv4 to use as search key
+ *
+ * Refcounter is not increased for the returned peer.
+ *
+ * Return: the peer if found or NULL otherwise
+ */
+static struct ovpn_peer *ovpn_peer_get_by_vpn_addr4(struct ovpn_priv *ovpn,
+						    __be32 addr)
+{
+	struct hlist_nulls_head *nhead;
+	struct hlist_nulls_node *ntmp;
+	struct ovpn_peer *tmp;
+	unsigned int slot;
+
+begin:
+	slot = ovpn_get_hash_slot(ovpn->peers->by_vpn_addr4, &addr,
+				  sizeof(addr));
+	nhead = &ovpn->peers->by_vpn_addr4[slot];
+
+	hlist_nulls_for_each_entry_rcu(tmp, ntmp, nhead, hash_entry_addr4)
+		if (addr == tmp->vpn_addrs.ipv4.s_addr)
+			return tmp;
+
+	/* item may have moved during lookup - check nulls and restart
+	 * if that's the case
+	 */
+	if (get_nulls_value(ntmp) != slot)
+		goto begin;
+
+	return NULL;
+}
+
+/**
+ * ovpn_peer_get_by_vpn_addr6 - retrieve peer by its VPN IPv6 address
+ * @ovpn: the openvpn instance to search
+ * @addr: VPN IPv6 to use as search key
+ *
+ * Refcounter is not increased for the returned peer.
+ *
+ * Return: the peer if found or NULL otherwise
+ */
+static struct ovpn_peer *ovpn_peer_get_by_vpn_addr6(struct ovpn_priv *ovpn,
+						    struct in6_addr *addr)
+{
+	struct hlist_nulls_head *nhead;
+	struct hlist_nulls_node *ntmp;
+	struct ovpn_peer *tmp;
+	unsigned int slot;
+
+begin:
+	slot = ovpn_get_hash_slot(ovpn->peers->by_vpn_addr6, addr,
+				  sizeof(*addr));
+	nhead = &ovpn->peers->by_vpn_addr6[slot];
+
+	hlist_nulls_for_each_entry_rcu(tmp, ntmp, nhead, hash_entry_addr6)
+		if (ipv6_addr_equal(addr, &tmp->vpn_addrs.ipv6))
+			return tmp;
+
+	/* item may have moved during lookup - check nulls and restart
+	 * if that's the case
+	 */
+	if (get_nulls_value(ntmp) != slot)
+		goto begin;
+
+	return NULL;
+}
+
+/**
+ * ovpn_peer_transp_match - check if sockaddr and peer binding match
+ * @peer: the peer to get the binding from
+ * @ss: the sockaddr to match
+ *
+ * Return: true if sockaddr and binding match or false otherwise
+ */
+static bool ovpn_peer_transp_match(const struct ovpn_peer *peer,
+				   const struct sockaddr_storage *ss)
+{
+	struct ovpn_bind *bind = rcu_dereference(peer->bind);
+	struct sockaddr_in6 *sa6;
+	struct sockaddr_in *sa4;
+
+	if (unlikely(!bind))
+		return false;
+
+	if (ss->ss_family != bind->remote.in4.sin_family)
+		return false;
+
+	switch (ss->ss_family) {
+	case AF_INET:
+		sa4 = (struct sockaddr_in *)ss;
+		if (sa4->sin_addr.s_addr != bind->remote.in4.sin_addr.s_addr)
+			return false;
+		if (sa4->sin_port != bind->remote.in4.sin_port)
+			return false;
+		break;
+	case AF_INET6:
+		sa6 = (struct sockaddr_in6 *)ss;
+		if (!ipv6_addr_equal(&sa6->sin6_addr,
+				     &bind->remote.in6.sin6_addr))
+			return false;
+		if (sa6->sin6_port != bind->remote.in6.sin6_port)
+			return false;
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+/**
+ * ovpn_peer_get_by_transp_addr_p2p - get peer by transport address in a P2P
+ *                                    instance
+ * @ovpn: the openvpn instance to search
+ * @ss: the transport socket address
+ *
+ * Return: the peer if found or NULL otherwise
+ */
+static struct ovpn_peer *
+ovpn_peer_get_by_transp_addr_p2p(struct ovpn_priv *ovpn,
+				 struct sockaddr_storage *ss)
+{
+	struct ovpn_peer *tmp, *peer = NULL;
+
+	rcu_read_lock();
+	tmp = rcu_dereference(ovpn->peer);
+	if (likely(tmp && ovpn_peer_transp_match(tmp, ss) &&
+		   ovpn_peer_hold(tmp)))
+		peer = tmp;
+	rcu_read_unlock();
+
+	return peer;
+}
+
+/**
+ * ovpn_peer_get_by_transp_addr - retrieve peer by transport address
+ * @ovpn: the openvpn instance to search
+ * @skb: the skb to retrieve the source transport address from
+ *
+ * Return: a pointer to the peer if found or NULL otherwise
+ */
+struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn,
+					       struct sk_buff *skb)
+{
+	struct ovpn_peer *tmp, *peer = NULL;
+	struct sockaddr_storage ss = { 0 };
+	struct hlist_nulls_head *nhead;
+	struct hlist_nulls_node *ntmp;
+	unsigned int slot;
+	ssize_t sa_len;
+
+	sa_len = ovpn_peer_skb_to_sockaddr(skb, &ss);
+	if (unlikely(sa_len < 0))
+		return NULL;
+
+	if (ovpn->mode == OVPN_MODE_P2P)
+		return ovpn_peer_get_by_transp_addr_p2p(ovpn, &ss);
+
+	rcu_read_lock();
+begin:
+	slot = ovpn_get_hash_slot(ovpn->peers->by_transp_addr, &ss, sa_len);
+	nhead = &ovpn->peers->by_transp_addr[slot];
+
+	hlist_nulls_for_each_entry_rcu(tmp, ntmp, nhead,
+				       hash_entry_transp_addr) {
+		if (!ovpn_peer_transp_match(tmp, &ss))
+			continue;
+
+		if (!ovpn_peer_hold(tmp))
+			continue;
+
+		peer = tmp;
+		break;
+	}
+
+	/* item may have moved during lookup - check nulls and restart
+	 * if that's the case
+	 */
+	if (!peer && get_nulls_value(ntmp) != slot)
+		goto begin;
+	rcu_read_unlock();
+
+	return peer;
+}
+
+/**
+ * ovpn_peer_get_by_id_p2p - get peer by ID in a P2P instance
+ * @ovpn: the openvpn instance to search
+ * @peer_id: the ID of the peer to find
+ *
+ * Return: the peer if found or NULL otherwise
+ */
+static struct ovpn_peer *ovpn_peer_get_by_id_p2p(struct ovpn_priv *ovpn,
+						 u32 peer_id)
+{
+	struct ovpn_peer *tmp, *peer = NULL;
+
+	rcu_read_lock();
+	tmp = rcu_dereference(ovpn->peer);
+	if (likely(tmp && tmp->id == peer_id && ovpn_peer_hold(tmp)))
+		peer = tmp;
+	rcu_read_unlock();
+
+	return peer;
+}
+
+/**
+ * ovpn_peer_get_by_id - retrieve peer by ID
+ * @ovpn: the openvpn instance to search
+ * @peer_id: the unique peer identifier to match
+ *
+ * Return: a pointer to the peer if found or NULL otherwise
+ */
+struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id)
+{
+	struct ovpn_peer *tmp, *peer = NULL;
+	struct hlist_head *head;
+
+	if (ovpn->mode == OVPN_MODE_P2P)
+		return ovpn_peer_get_by_id_p2p(ovpn, peer_id);
+
+	head = ovpn_get_hash_head(ovpn->peers->by_id, &peer_id,
+				  sizeof(peer_id));
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp, head, hash_entry_id) {
+		if (tmp->id != peer_id)
+			continue;
+
+		if (!ovpn_peer_hold(tmp))
+			continue;
+
+		peer = tmp;
+		break;
+	}
+	rcu_read_unlock();
+
+	return peer;
+}
+
+static void ovpn_peer_remove(struct ovpn_peer *peer,
+			     enum ovpn_del_peer_reason reason,
+			     struct llist_head *release_list)
+{
+	lockdep_assert_held(&peer->ovpn->lock);
+
+	switch (peer->ovpn->mode) {
+	case OVPN_MODE_MP:
+		/* prevent double remove */
+		if (hlist_unhashed(&peer->hash_entry_id))
+			return;
+
+		hlist_del_init_rcu(&peer->hash_entry_id);
+		hlist_nulls_del_init_rcu(&peer->hash_entry_addr4);
+		hlist_nulls_del_init_rcu(&peer->hash_entry_addr6);
+		hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr);
+		break;
+	case OVPN_MODE_P2P:
+		/* prevent double remove */
+		if (peer != rcu_access_pointer(peer->ovpn->peer))
+			return;
+
+		RCU_INIT_POINTER(peer->ovpn->peer, NULL);
+		/* in P2P mode the carrier is switched off when the peer is
+		 * deleted so that third party protocols can react accordingly
+		 */
+		netif_carrier_off(peer->ovpn->dev);
+		break;
+	}
+
+	peer->delete_reason = reason;
+	ovpn_nl_peer_del_notify(peer);
+
+	/* append to provided list for later socket release and ref drop */
+	llist_add(&peer->release_entry, release_list);
+}
+
+/**
+ * ovpn_peer_get_by_dst - Lookup peer to send skb to
+ * @ovpn: the private data representing the current VPN session
+ * @skb: the skb to extract the destination address from
+ *
+ * This function takes a tunnel packet and looks up the peer to send it to
+ * after encapsulation. The skb is expected to be the in-tunnel packet, without
+ * any OpenVPN related header.
+ *
+ * Assume that the IP header is accessible in the skb data.
+ *
+ * Return: the peer if found or NULL otherwise.
+ */
+struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn,
+				       struct sk_buff *skb)
+{
+	struct ovpn_peer *peer = NULL;
+	struct in6_addr addr6;
+	__be32 addr4;
+
+	/* in P2P mode, no matter the destination, packets are always sent to
+	 * the single peer listening on the other side
+	 */
+	if (ovpn->mode == OVPN_MODE_P2P) {
+		rcu_read_lock();
+		peer = rcu_dereference(ovpn->peer);
+		if (unlikely(peer && !ovpn_peer_hold(peer)))
+			peer = NULL;
+		rcu_read_unlock();
+		return peer;
+	}
+
+	rcu_read_lock();
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		addr4 = ovpn_nexthop_from_skb4(skb);
+		peer = ovpn_peer_get_by_vpn_addr4(ovpn, addr4);
+		break;
+	case htons(ETH_P_IPV6):
+		addr6 = ovpn_nexthop_from_skb6(skb);
+		peer = ovpn_peer_get_by_vpn_addr6(ovpn, &addr6);
+		break;
+	}
+
+	if (unlikely(peer && !ovpn_peer_hold(peer)))
+		peer = NULL;
+	rcu_read_unlock();
+
+	return peer;
+}
+
+/**
+ * ovpn_nexthop_from_rt4 - look up the IPv4 nexthop for the given destination
+ * @ovpn: the private data representing the current VPN session
+ * @dest: the destination to be looked up
+ *
+ * Looks up in the IPv4 system routing table the IP of the nexthop to be used
+ * to reach the destination passed as argument. If no nexthop can be found, the
+ * destination itself is returned as it probably has to be used as nexthop.
+ *
+ * Return: the IP of the next hop if found or dest itself otherwise
+ */
+static __be32 ovpn_nexthop_from_rt4(struct ovpn_priv *ovpn, __be32 dest)
+{
+	struct rtable *rt;
+	struct flowi4 fl = {
+		.daddr = dest
+	};
+
+	rt = ip_route_output_flow(dev_net(ovpn->dev), &fl, NULL);
+	if (IS_ERR(rt)) {
+		net_dbg_ratelimited("%s: no route to host %pI4\n",
+				    netdev_name(ovpn->dev), &dest);
+		/* if we end up here this packet is probably going to be
+		 * thrown away later
+		 */
+		return dest;
+	}
+
+	if (!rt->rt_uses_gateway)
+		goto out;
+
+	dest = rt->rt_gw4;
+out:
+	ip_rt_put(rt);
+	return dest;
+}
+
+/**
+ * ovpn_nexthop_from_rt6 - look up the IPv6 nexthop for the given destination
+ * @ovpn: the private data representing the current VPN session
+ * @dest: the destination to be looked up
+ *
+ * Looks up in the IPv6 system routing table the IP of the nexthop to be used
+ * to reach the destination passed as argument. If no nexthop can be found, the
+ * destination itself is returned as it probably has to be used as nexthop.
+ *
+ * Return: the IP of the next hop if found or dest itself otherwise
+ */
+static struct in6_addr ovpn_nexthop_from_rt6(struct ovpn_priv *ovpn,
+					     struct in6_addr dest)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct dst_entry *entry;
+	struct rt6_info *rt;
+	struct flowi6 fl = {
+		.daddr = dest,
+	};
+
+	entry = ipv6_stub->ipv6_dst_lookup_flow(dev_net(ovpn->dev), NULL, &fl,
+						NULL);
+	if (IS_ERR(entry)) {
+		net_dbg_ratelimited("%s: no route to host %pI6c\n",
+				    netdev_name(ovpn->dev), &dest);
+		/* if we end up here this packet is probably going to be
+		 * thrown away later
+		 */
+		return dest;
+	}
+
+	rt = dst_rt6_info(entry);
+
+	if (!(rt->rt6i_flags & RTF_GATEWAY))
+		goto out;
+
+	dest = rt->rt6i_gateway;
+out:
+	dst_release((struct dst_entry *)rt);
+#endif
+	return dest;
+}
+
+/**
+ * ovpn_peer_check_by_src - check that skb source is routed via peer
+ * @ovpn: the openvpn instance to search
+ * @skb: the packet to extract source address from
+ * @peer: the peer to check against the source address
+ *
+ * Return: true if the peer is matching or false otherwise
+ */
+bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb,
+			    struct ovpn_peer *peer)
+{
+	bool match = false;
+	struct in6_addr addr6;
+	__be32 addr4;
+
+	if (ovpn->mode == OVPN_MODE_P2P) {
+		/* in P2P mode, no matter the destination, packets are always
+		 * sent to the single peer listening on the other side
+		 */
+		return peer == rcu_access_pointer(ovpn->peer);
+	}
+
+	/* This function performs a reverse path check, therefore we now
+	 * lookup the nexthop we would use if we wanted to route a packet
+	 * to the source IP. If the nexthop matches the sender we know the
+	 * latter is valid and we allow the packet to come in
+	 */
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		addr4 = ovpn_nexthop_from_rt4(ovpn, ip_hdr(skb)->saddr);
+		rcu_read_lock();
+		match = (peer == ovpn_peer_get_by_vpn_addr4(ovpn, addr4));
+		rcu_read_unlock();
+		break;
+	case htons(ETH_P_IPV6):
+		addr6 = ovpn_nexthop_from_rt6(ovpn, ipv6_hdr(skb)->saddr);
+		rcu_read_lock();
+		match = (peer == ovpn_peer_get_by_vpn_addr6(ovpn, &addr6));
+		rcu_read_unlock();
+		break;
+	}
+
+	return match;
+}
+
+void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer)
+{
+	struct hlist_nulls_head *nhead;
+
+	lockdep_assert_held(&peer->ovpn->lock);
+
+	/* rehashing makes sense only in multipeer mode */
+	if (peer->ovpn->mode != OVPN_MODE_MP)
+		return;
+
+	if (peer->vpn_addrs.ipv4.s_addr != htonl(INADDR_ANY)) {
+		/* remove potential old hashing */
+		hlist_nulls_del_init_rcu(&peer->hash_entry_addr4);
+
+		nhead = ovpn_get_hash_head(peer->ovpn->peers->by_vpn_addr4,
+					   &peer->vpn_addrs.ipv4,
+					   sizeof(peer->vpn_addrs.ipv4));
+		hlist_nulls_add_head_rcu(&peer->hash_entry_addr4, nhead);
+	}
+
+	if (!ipv6_addr_any(&peer->vpn_addrs.ipv6)) {
+		/* remove potential old hashing */
+		hlist_nulls_del_init_rcu(&peer->hash_entry_addr6);
+
+		nhead = ovpn_get_hash_head(peer->ovpn->peers->by_vpn_addr6,
+					   &peer->vpn_addrs.ipv6,
+					   sizeof(peer->vpn_addrs.ipv6));
+		hlist_nulls_add_head_rcu(&peer->hash_entry_addr6, nhead);
+	}
+}
+
+/**
+ * ovpn_peer_add_mp - add peer to related tables in a MP instance
+ * @ovpn: the instance to add the peer to
+ * @peer: the peer to add
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_peer_add_mp(struct ovpn_priv *ovpn, struct ovpn_peer *peer)
+{
+	struct sockaddr_storage sa = { 0 };
+	struct hlist_nulls_head *nhead;
+	struct sockaddr_in6 *sa6;
+	struct sockaddr_in *sa4;
+	struct ovpn_bind *bind;
+	struct ovpn_peer *tmp;
+	size_t salen;
+	int ret = 0;
+
+	spin_lock_bh(&ovpn->lock);
+	/* do not add duplicates */
+	tmp = ovpn_peer_get_by_id(ovpn, peer->id);
+	if (tmp) {
+		ovpn_peer_put(tmp);
+		ret = -EEXIST;
+		goto out;
+	}
+
+	bind = rcu_dereference_protected(peer->bind, true);
+	/* peers connected via TCP have bind == NULL */
+	if (bind) {
+		switch (bind->remote.in4.sin_family) {
+		case AF_INET:
+			sa4 = (struct sockaddr_in *)&sa;
+
+			sa4->sin_family = AF_INET;
+			sa4->sin_addr.s_addr = bind->remote.in4.sin_addr.s_addr;
+			sa4->sin_port = bind->remote.in4.sin_port;
+			salen = sizeof(*sa4);
+			break;
+		case AF_INET6:
+			sa6 = (struct sockaddr_in6 *)&sa;
+
+			sa6->sin6_family = AF_INET6;
+			sa6->sin6_addr = bind->remote.in6.sin6_addr;
+			sa6->sin6_port = bind->remote.in6.sin6_port;
+			salen = sizeof(*sa6);
+			break;
+		default:
+			ret = -EPROTONOSUPPORT;
+			goto out;
+		}
+
+		nhead = ovpn_get_hash_head(ovpn->peers->by_transp_addr, &sa,
+					   salen);
+		hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead);
+	}
+
+	hlist_add_head_rcu(&peer->hash_entry_id,
+			   ovpn_get_hash_head(ovpn->peers->by_id, &peer->id,
+					      sizeof(peer->id)));
+
+	ovpn_peer_hash_vpn_ip(peer);
+out:
+	spin_unlock_bh(&ovpn->lock);
+	return ret;
+}
+
+/**
+ * ovpn_peer_add_p2p - add peer to related tables in a P2P instance
+ * @ovpn: the instance to add the peer to
+ * @peer: the peer to add
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_peer_add_p2p(struct ovpn_priv *ovpn, struct ovpn_peer *peer)
+{
+	LLIST_HEAD(release_list);
+	struct ovpn_peer *tmp;
+
+	spin_lock_bh(&ovpn->lock);
+	/* in p2p mode it is possible to have a single peer only, therefore the
+	 * old one is released and substituted by the new one
+	 */
+	tmp = rcu_dereference_protected(ovpn->peer,
+					lockdep_is_held(&ovpn->lock));
+	if (tmp)
+		ovpn_peer_remove(tmp, OVPN_DEL_PEER_REASON_TEARDOWN,
+				 &release_list);
+
+	rcu_assign_pointer(ovpn->peer, peer);
+	/* in P2P mode the carrier is switched on when the peer is added */
+	netif_carrier_on(ovpn->dev);
+	unlock_ovpn(ovpn, &release_list);
+
+	return 0;
+}
+
+/**
+ * ovpn_peer_add - add peer to the related tables
+ * @ovpn: the openvpn instance the peer belongs to
+ * @peer: the peer object to add
+ *
+ * Assume refcounter was increased by caller
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer)
+{
+	switch (ovpn->mode) {
+	case OVPN_MODE_MP:
+		return ovpn_peer_add_mp(ovpn, peer);
+	case OVPN_MODE_P2P:
+		return ovpn_peer_add_p2p(ovpn, peer);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+/**
+ * ovpn_peer_del_mp - delete peer from related tables in a MP instance
+ * @peer: the peer to delete
+ * @reason: reason why the peer was deleted (sent to userspace)
+ * @release_list: list where delete peer should be appended
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_peer_del_mp(struct ovpn_peer *peer,
+			    enum ovpn_del_peer_reason reason,
+			    struct llist_head *release_list)
+{
+	struct ovpn_peer *tmp;
+	int ret = -ENOENT;
+
+	lockdep_assert_held(&peer->ovpn->lock);
+
+	tmp = ovpn_peer_get_by_id(peer->ovpn, peer->id);
+	if (tmp == peer) {
+		ovpn_peer_remove(peer, reason, release_list);
+		ret = 0;
+	}
+
+	if (tmp)
+		ovpn_peer_put(tmp);
+
+	return ret;
+}
+
+/**
+ * ovpn_peer_del_p2p - delete peer from related tables in a P2P instance
+ * @peer: the peer to delete
+ * @reason: reason why the peer was deleted (sent to userspace)
+ * @release_list: list where delete peer should be appended
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_peer_del_p2p(struct ovpn_peer *peer,
+			     enum ovpn_del_peer_reason reason,
+			     struct llist_head *release_list)
+{
+	struct ovpn_peer *tmp;
+
+	lockdep_assert_held(&peer->ovpn->lock);
+
+	tmp = rcu_dereference_protected(peer->ovpn->peer,
+					lockdep_is_held(&peer->ovpn->lock));
+	if (tmp != peer)
+		return -ENOENT;
+
+	ovpn_peer_remove(peer, reason, release_list);
+
+	return 0;
+}
+
+/**
+ * ovpn_peer_del - delete peer from related tables
+ * @peer: the peer object to delete
+ * @reason: reason for deleting peer (will be sent to userspace)
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason)
+{
+	LLIST_HEAD(release_list);
+	int ret = -EOPNOTSUPP;
+
+	spin_lock_bh(&peer->ovpn->lock);
+	switch (peer->ovpn->mode) {
+	case OVPN_MODE_MP:
+		ret = ovpn_peer_del_mp(peer, reason, &release_list);
+		break;
+	case OVPN_MODE_P2P:
+		ret = ovpn_peer_del_p2p(peer, reason, &release_list);
+		break;
+	default:
+		break;
+	}
+	unlock_ovpn(peer->ovpn, &release_list);
+
+	return ret;
+}
+
+/**
+ * ovpn_peer_release_p2p - release peer upon P2P device teardown
+ * @ovpn: the instance being torn down
+ * @sk: if not NULL, release peer only if it's using this specific socket
+ * @reason: the reason for releasing the peer
+ */
+static void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk,
+				  enum ovpn_del_peer_reason reason)
+{
+	struct ovpn_socket *ovpn_sock;
+	LLIST_HEAD(release_list);
+	struct ovpn_peer *peer;
+
+	spin_lock_bh(&ovpn->lock);
+	peer = rcu_dereference_protected(ovpn->peer,
+					 lockdep_is_held(&ovpn->lock));
+	if (!peer) {
+		spin_unlock_bh(&ovpn->lock);
+		return;
+	}
+
+	if (sk) {
+		ovpn_sock = rcu_access_pointer(peer->sock);
+		if (!ovpn_sock || ovpn_sock->sock->sk != sk) {
+			spin_unlock_bh(&ovpn->lock);
+			ovpn_peer_put(peer);
+			return;
+		}
+	}
+
+	ovpn_peer_remove(peer, reason, &release_list);
+	unlock_ovpn(ovpn, &release_list);
+}
+
+static void ovpn_peers_release_mp(struct ovpn_priv *ovpn, struct sock *sk,
+				  enum ovpn_del_peer_reason reason)
+{
+	struct ovpn_socket *ovpn_sock;
+	LLIST_HEAD(release_list);
+	struct ovpn_peer *peer;
+	struct hlist_node *tmp;
+	int bkt;
+
+	spin_lock_bh(&ovpn->lock);
+	hash_for_each_safe(ovpn->peers->by_id, bkt, tmp, peer, hash_entry_id) {
+		bool remove = true;
+
+		/* if a socket was passed as argument, skip all peers except
+		 * those using it
+		 */
+		if (sk) {
+			rcu_read_lock();
+			ovpn_sock = rcu_dereference(peer->sock);
+			remove = ovpn_sock && ovpn_sock->sock->sk == sk;
+			rcu_read_unlock();
+		}
+
+		if (remove)
+			ovpn_peer_remove(peer, reason, &release_list);
+	}
+	unlock_ovpn(ovpn, &release_list);
+}
+
+/**
+ * ovpn_peers_free - free all peers in the instance
+ * @ovpn: the instance whose peers should be released
+ * @sk: if not NULL, only peers using this socket are removed and the socket
+ *      is released immediately
+ * @reason: the reason for releasing all peers
+ */
+void ovpn_peers_free(struct ovpn_priv *ovpn, struct sock *sk,
+		     enum ovpn_del_peer_reason reason)
+{
+	switch (ovpn->mode) {
+	case OVPN_MODE_P2P:
+		ovpn_peer_release_p2p(ovpn, sk, reason);
+		break;
+	case OVPN_MODE_MP:
+		ovpn_peers_release_mp(ovpn, sk, reason);
+		break;
+	}
+}
+
+static time64_t ovpn_peer_keepalive_work_single(struct ovpn_peer *peer,
+						time64_t now,
+						struct llist_head *release_list)
+{
+	time64_t last_recv, last_sent, next_run1, next_run2;
+	unsigned long timeout, interval;
+	bool expired;
+
+	spin_lock_bh(&peer->lock);
+	/* we expect both timers to be configured at the same time,
+	 * therefore bail out if either is not set
+	 */
+	if (!peer->keepalive_timeout || !peer->keepalive_interval) {
+		spin_unlock_bh(&peer->lock);
+		return 0;
+	}
+
+	/* check for peer timeout */
+	expired = false;
+	timeout = peer->keepalive_timeout;
+	last_recv = READ_ONCE(peer->last_recv);
+	if (now < last_recv + timeout) {
+		peer->keepalive_recv_exp = last_recv + timeout;
+		next_run1 = peer->keepalive_recv_exp;
+	} else if (peer->keepalive_recv_exp > now) {
+		next_run1 = peer->keepalive_recv_exp;
+	} else {
+		expired = true;
+	}
+
+	if (expired) {
+		/* peer is dead -> kill it and move on */
+		spin_unlock_bh(&peer->lock);
+		netdev_dbg(peer->ovpn->dev, "peer %u expired\n",
+			   peer->id);
+		ovpn_peer_remove(peer, OVPN_DEL_PEER_REASON_EXPIRED,
+				 release_list);
+		return 0;
+	}
+
+	/* check for peer keepalive */
+	expired = false;
+	interval = peer->keepalive_interval;
+	last_sent = READ_ONCE(peer->last_sent);
+	if (now < last_sent + interval) {
+		peer->keepalive_xmit_exp = last_sent + interval;
+		next_run2 = peer->keepalive_xmit_exp;
+	} else if (peer->keepalive_xmit_exp > now) {
+		next_run2 = peer->keepalive_xmit_exp;
+	} else {
+		expired = true;
+		next_run2 = now + interval;
+	}
+	spin_unlock_bh(&peer->lock);
+
+	if (expired) {
+		/* a keepalive packet is required */
+		netdev_dbg(peer->ovpn->dev,
+			   "sending keepalive to peer %u\n",
+			   peer->id);
+		if (schedule_work(&peer->keepalive_work))
+			ovpn_peer_hold(peer);
+	}
+
+	if (next_run1 < next_run2)
+		return next_run1;
+
+	return next_run2;
+}
+
+static time64_t ovpn_peer_keepalive_work_mp(struct ovpn_priv *ovpn,
+					    time64_t now,
+					    struct llist_head *release_list)
+{
+	time64_t tmp_next_run, next_run = 0;
+	struct hlist_node *tmp;
+	struct ovpn_peer *peer;
+	int bkt;
+
+	lockdep_assert_held(&ovpn->lock);
+
+	hash_for_each_safe(ovpn->peers->by_id, bkt, tmp, peer, hash_entry_id) {
+		tmp_next_run = ovpn_peer_keepalive_work_single(peer, now,
+							       release_list);
+		if (!tmp_next_run)
+			continue;
+
+		/* the next worker run will be scheduled based on the shortest
+		 * required interval across all peers
+		 */
+		if (!next_run || tmp_next_run < next_run)
+			next_run = tmp_next_run;
+	}
+
+	return next_run;
+}
+
+static time64_t ovpn_peer_keepalive_work_p2p(struct ovpn_priv *ovpn,
+					     time64_t now,
+					     struct llist_head *release_list)
+{
+	struct ovpn_peer *peer;
+	time64_t next_run = 0;
+
+	lockdep_assert_held(&ovpn->lock);
+
+	peer = rcu_dereference_protected(ovpn->peer,
+					 lockdep_is_held(&ovpn->lock));
+	if (peer)
+		next_run = ovpn_peer_keepalive_work_single(peer, now,
+							   release_list);
+
+	return next_run;
+}
+
+/**
+ * ovpn_peer_keepalive_work - run keepalive logic on each known peer
+ * @work: pointer to the work member of the related ovpn object
+ *
+ * Each peer has two timers (if configured):
+ * 1. peer timeout: when no data is received for a certain interval,
+ *    the peer is considered dead and it gets killed.
+ * 2. peer keepalive: when no data is sent to a certain peer for a
+ *    certain interval, a special 'keepalive' packet is explicitly sent.
+ *
+ * This function iterates across the whole peer collection while
+ * checking the timers described above.
+ */
+void ovpn_peer_keepalive_work(struct work_struct *work)
+{
+	struct ovpn_priv *ovpn = container_of(work, struct ovpn_priv,
+					      keepalive_work.work);
+	time64_t next_run = 0, now = ktime_get_real_seconds();
+	LLIST_HEAD(release_list);
+
+	spin_lock_bh(&ovpn->lock);
+	switch (ovpn->mode) {
+	case OVPN_MODE_MP:
+		next_run = ovpn_peer_keepalive_work_mp(ovpn, now,
+						       &release_list);
+		break;
+	case OVPN_MODE_P2P:
+		next_run = ovpn_peer_keepalive_work_p2p(ovpn, now,
+							&release_list);
+		break;
+	}
+
+	/* prevent rearming if the interface is being destroyed */
+	if (next_run > 0) {
+		netdev_dbg(ovpn->dev,
+			   "scheduling keepalive work: now=%llu next_run=%llu delta=%llu\n",
+			   next_run, now, next_run - now);
+		schedule_delayed_work(&ovpn->keepalive_work,
+				      (next_run - now) * HZ);
+	}
+	unlock_ovpn(ovpn, &release_list);
+}
diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h
new file mode 100644
index 000000000000..a1423f2b09e0
--- /dev/null
+++ b/drivers/net/ovpn/peer.h
@@ -0,0 +1,163 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNPEER_H_
+#define _NET_OVPN_OVPNPEER_H_
+
+#include <net/dst_cache.h>
+#include <net/strparser.h>
+
+#include "crypto.h"
+#include "socket.h"
+#include "stats.h"
+
+/**
+ * struct ovpn_peer - the main remote peer object
+ * @ovpn: main openvpn instance this peer belongs to
+ * @dev_tracker: reference tracker for associated dev
+ * @id: unique identifier
+ * @vpn_addrs: IP addresses assigned over the tunnel
+ * @vpn_addrs.ipv4: IPv4 assigned to peer on the tunnel
+ * @vpn_addrs.ipv6: IPv6 assigned to peer on the tunnel
+ * @hash_entry_id: entry in the peer ID hashtable
+ * @hash_entry_addr4: entry in the peer IPv4 hashtable
+ * @hash_entry_addr6: entry in the peer IPv6 hashtable
+ * @hash_entry_transp_addr: entry in the peer transport address hashtable
+ * @sock: the socket being used to talk to this peer
+ * @tcp: keeps track of TCP specific state
+ * @tcp.strp: stream parser context (TCP only)
+ * @tcp.user_queue: received packets that have to go to userspace (TCP only)
+ * @tcp.out_queue: packets on hold while socket is taken by user (TCP only)
+ * @tcp.tx_in_progress: true if TX is already ongoing (TCP only)
+ * @tcp.out_msg.skb: packet scheduled for sending (TCP only)
+ * @tcp.out_msg.offset: offset where next send should start (TCP only)
+ * @tcp.out_msg.len: remaining data to send within packet (TCP only)
+ * @tcp.sk_cb.sk_data_ready: pointer to original cb (TCP only)
+ * @tcp.sk_cb.sk_write_space: pointer to original cb (TCP only)
+ * @tcp.sk_cb.prot: pointer to original prot object (TCP only)
+ * @tcp.sk_cb.ops: pointer to the original prot_ops object (TCP only)
+ * @crypto: the crypto configuration (ciphers, keys, etc..)
+ * @dst_cache: cache for dst_entry used to send to peer
+ * @bind: remote peer binding
+ * @keepalive_interval: seconds after which a new keepalive should be sent
+ * @keepalive_xmit_exp: future timestamp when next keepalive should be sent
+ * @last_sent: timestamp of the last successfully sent packet
+ * @keepalive_timeout: seconds after which an inactive peer is considered dead
+ * @keepalive_recv_exp: future timestamp when the peer should expire
+ * @last_recv: timestamp of the last authenticated received packet
+ * @vpn_stats: per-peer in-VPN TX/RX stats
+ * @link_stats: per-peer link/transport TX/RX stats
+ * @delete_reason: why peer was deleted (i.e. timeout, transport error, ..)
+ * @lock: protects binding to peer (bind) and keepalive* fields
+ * @refcount: reference counter
+ * @rcu: used to free peer in an RCU safe way
+ * @release_entry: entry for the socket release list
+ * @keepalive_work: used to schedule keepalive sending
+ */
+struct ovpn_peer {
+	struct ovpn_priv *ovpn;
+	netdevice_tracker dev_tracker;
+	u32 id;
+	struct {
+		struct in_addr ipv4;
+		struct in6_addr ipv6;
+	} vpn_addrs;
+	struct hlist_node hash_entry_id;
+	struct hlist_nulls_node hash_entry_addr4;
+	struct hlist_nulls_node hash_entry_addr6;
+	struct hlist_nulls_node hash_entry_transp_addr;
+	struct ovpn_socket __rcu *sock;
+
+	struct {
+		struct strparser strp;
+		struct sk_buff_head user_queue;
+		struct sk_buff_head out_queue;
+		bool tx_in_progress;
+
+		struct {
+			struct sk_buff *skb;
+			int offset;
+			int len;
+		} out_msg;
+
+		struct {
+			void (*sk_data_ready)(struct sock *sk);
+			void (*sk_write_space)(struct sock *sk);
+			struct proto *prot;
+			const struct proto_ops *ops;
+		} sk_cb;
+
+		struct work_struct defer_del_work;
+	} tcp;
+	struct ovpn_crypto_state crypto;
+	struct dst_cache dst_cache;
+	struct ovpn_bind __rcu *bind;
+	unsigned long keepalive_interval;
+	unsigned long keepalive_xmit_exp;
+	time64_t last_sent;
+	unsigned long keepalive_timeout;
+	unsigned long keepalive_recv_exp;
+	time64_t last_recv;
+	struct ovpn_peer_stats vpn_stats;
+	struct ovpn_peer_stats link_stats;
+	enum ovpn_del_peer_reason delete_reason;
+	spinlock_t lock; /* protects bind  and keepalive* */
+	struct kref refcount;
+	struct rcu_head rcu;
+	struct llist_node release_entry;
+	struct work_struct keepalive_work;
+};
+
+/**
+ * ovpn_peer_hold - increase reference counter
+ * @peer: the peer whose counter should be increased
+ *
+ * Return: true if the counter was increased or false if it was zero already
+ */
+static inline bool ovpn_peer_hold(struct ovpn_peer *peer)
+{
+	return kref_get_unless_zero(&peer->refcount);
+}
+
+void ovpn_peer_release(struct ovpn_peer *peer);
+void ovpn_peer_release_kref(struct kref *kref);
+
+/**
+ * ovpn_peer_put - decrease reference counter
+ * @peer: the peer whose counter should be decreased
+ */
+static inline void ovpn_peer_put(struct ovpn_peer *peer)
+{
+	kref_put(&peer->refcount, ovpn_peer_release_kref);
+}
+
+struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id);
+int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer);
+int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason);
+void ovpn_peers_free(struct ovpn_priv *ovpn, struct sock *sock,
+		     enum ovpn_del_peer_reason reason);
+
+struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn,
+					       struct sk_buff *skb);
+struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id);
+struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn,
+				       struct sk_buff *skb);
+void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer);
+bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb,
+			    struct ovpn_peer *peer);
+
+void ovpn_peer_keepalive_set(struct ovpn_peer *peer, u32 interval, u32 timeout);
+void ovpn_peer_keepalive_work(struct work_struct *work);
+
+void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb);
+int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer,
+			     const struct sockaddr_storage *ss,
+			     const void *local_ip);
+
+#endif /* _NET_OVPN_OVPNPEER_H_ */
diff --git a/drivers/net/ovpn/pktid.c b/drivers/net/ovpn/pktid.c
new file mode 100644
index 000000000000..2f29049897e3
--- /dev/null
+++ b/drivers/net/ovpn/pktid.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ *		James Yonan <james@openvpn.net>
+ */
+
+#include <linux/atomic.h>
+#include <linux/jiffies.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/types.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "pktid.h"
+
+void ovpn_pktid_xmit_init(struct ovpn_pktid_xmit *pid)
+{
+	atomic_set(&pid->seq_num, 1);
+}
+
+void ovpn_pktid_recv_init(struct ovpn_pktid_recv *pr)
+{
+	memset(pr, 0, sizeof(*pr));
+	spin_lock_init(&pr->lock);
+}
+
+/* Packet replay detection.
+ * Allows ID backtrack of up to REPLAY_WINDOW_SIZE - 1.
+ */
+int ovpn_pktid_recv(struct ovpn_pktid_recv *pr, u32 pkt_id, u32 pkt_time)
+{
+	const unsigned long now = jiffies;
+	int ret;
+
+	/* ID must not be zero */
+	if (unlikely(pkt_id == 0))
+		return -EINVAL;
+
+	spin_lock_bh(&pr->lock);
+
+	/* expire backtracks at or below pr->id after PKTID_RECV_EXPIRE time */
+	if (unlikely(time_after_eq(now, pr->expire)))
+		pr->id_floor = pr->id;
+
+	/* time changed? */
+	if (unlikely(pkt_time != pr->time)) {
+		if (pkt_time > pr->time) {
+			/* time moved forward, accept */
+			pr->base = 0;
+			pr->extent = 0;
+			pr->id = 0;
+			pr->time = pkt_time;
+			pr->id_floor = 0;
+		} else {
+			/* time moved backward, reject */
+			ret = -ETIME;
+			goto out;
+		}
+	}
+
+	if (likely(pkt_id == pr->id + 1)) {
+		/* well-formed ID sequence (incremented by 1) */
+		pr->base = REPLAY_INDEX(pr->base, -1);
+		pr->history[pr->base / 8] |= (1 << (pr->base % 8));
+		if (pr->extent < REPLAY_WINDOW_SIZE)
+			++pr->extent;
+		pr->id = pkt_id;
+	} else if (pkt_id > pr->id) {
+		/* ID jumped forward by more than one */
+		const unsigned int delta = pkt_id - pr->id;
+
+		if (delta < REPLAY_WINDOW_SIZE) {
+			unsigned int i;
+
+			pr->base = REPLAY_INDEX(pr->base, -delta);
+			pr->history[pr->base / 8] |= (1 << (pr->base % 8));
+			pr->extent += delta;
+			if (pr->extent > REPLAY_WINDOW_SIZE)
+				pr->extent = REPLAY_WINDOW_SIZE;
+			for (i = 1; i < delta; ++i) {
+				unsigned int newb = REPLAY_INDEX(pr->base, i);
+
+				pr->history[newb / 8] &= ~BIT(newb % 8);
+			}
+		} else {
+			pr->base = 0;
+			pr->extent = REPLAY_WINDOW_SIZE;
+			memset(pr->history, 0, sizeof(pr->history));
+			pr->history[0] = 1;
+		}
+		pr->id = pkt_id;
+	} else {
+		/* ID backtrack */
+		const unsigned int delta = pr->id - pkt_id;
+
+		if (delta > pr->max_backtrack)
+			pr->max_backtrack = delta;
+		if (delta < pr->extent) {
+			if (pkt_id > pr->id_floor) {
+				const unsigned int ri = REPLAY_INDEX(pr->base,
+								     delta);
+				u8 *p = &pr->history[ri / 8];
+				const u8 mask = (1 << (ri % 8));
+
+				if (*p & mask) {
+					ret = -EINVAL;
+					goto out;
+				}
+				*p |= mask;
+			} else {
+				ret = -EINVAL;
+				goto out;
+			}
+		} else {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	pr->expire = now + PKTID_RECV_EXPIRE;
+	ret = 0;
+out:
+	spin_unlock_bh(&pr->lock);
+	return ret;
+}
diff --git a/drivers/net/ovpn/pktid.h b/drivers/net/ovpn/pktid.h
new file mode 100644
index 000000000000..0262d026d15e
--- /dev/null
+++ b/drivers/net/ovpn/pktid.h
@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ *		James Yonan <james@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNPKTID_H_
+#define _NET_OVPN_OVPNPKTID_H_
+
+#include "proto.h"
+
+/* If no packets received for this length of time, set a backtrack floor
+ * at highest received packet ID thus far.
+ */
+#define PKTID_RECV_EXPIRE (30 * HZ)
+
+/* Packet-ID state for transmitter */
+struct ovpn_pktid_xmit {
+	atomic_t seq_num;
+};
+
+/* replay window sizing in bytes = 2^REPLAY_WINDOW_ORDER */
+#define REPLAY_WINDOW_ORDER 8
+
+#define REPLAY_WINDOW_BYTES BIT(REPLAY_WINDOW_ORDER)
+#define REPLAY_WINDOW_SIZE  (REPLAY_WINDOW_BYTES * 8)
+#define REPLAY_INDEX(base, i) (((base) + (i)) & (REPLAY_WINDOW_SIZE - 1))
+
+/* Packet-ID state for receiver.
+ * Other than lock member, can be zeroed to initialize.
+ */
+struct ovpn_pktid_recv {
+	/* "sliding window" bitmask of recent packet IDs received */
+	u8 history[REPLAY_WINDOW_BYTES];
+	/* bit position of deque base in history */
+	unsigned int base;
+	/* extent (in bits) of deque in history */
+	unsigned int extent;
+	/* expiration of history in jiffies */
+	unsigned long expire;
+	/* highest sequence number received */
+	u32 id;
+	/* highest time stamp received */
+	u32 time;
+	/* we will only accept backtrack IDs > id_floor */
+	u32 id_floor;
+	unsigned int max_backtrack;
+	/* protects entire pktd ID state */
+	spinlock_t lock;
+};
+
+/* Get the next packet ID for xmit */
+static inline int ovpn_pktid_xmit_next(struct ovpn_pktid_xmit *pid, u32 *pktid)
+{
+	const u32 seq_num = atomic_fetch_add_unless(&pid->seq_num, 1, 0);
+	/* when the 32bit space is over, we return an error because the packet
+	 * ID is used to create the cipher IV and we do not want to reuse the
+	 * same value more than once
+	 */
+	if (unlikely(!seq_num))
+		return -ERANGE;
+
+	*pktid = seq_num;
+
+	return 0;
+}
+
+/* Write 12-byte AEAD IV to dest */
+static inline void ovpn_pktid_aead_write(const u32 pktid,
+					 const u8 nt[],
+					 unsigned char *dest)
+{
+	*(__force __be32 *)(dest) = htonl(pktid);
+	BUILD_BUG_ON(4 + OVPN_NONCE_TAIL_SIZE != OVPN_NONCE_SIZE);
+	memcpy(dest + 4, nt, OVPN_NONCE_TAIL_SIZE);
+}
+
+void ovpn_pktid_xmit_init(struct ovpn_pktid_xmit *pid);
+void ovpn_pktid_recv_init(struct ovpn_pktid_recv *pr);
+
+int ovpn_pktid_recv(struct ovpn_pktid_recv *pr, u32 pkt_id, u32 pkt_time);
+
+#endif /* _NET_OVPN_OVPNPKTID_H_ */
diff --git a/drivers/net/ovpn/proto.h b/drivers/net/ovpn/proto.h
new file mode 100644
index 000000000000..b7d285b4d9c1
--- /dev/null
+++ b/drivers/net/ovpn/proto.h
@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ *		James Yonan <james@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_PROTO_H_
+#define _NET_OVPN_PROTO_H_
+
+#include "main.h"
+
+#include <linux/bitfield.h>
+#include <linux/skbuff.h>
+
+/* When the OpenVPN protocol is ran in AEAD mode, use
+ * the OpenVPN packet ID as the AEAD nonce:
+ *
+ *    00000005 521c3b01 4308c041
+ *    [seq # ] [  nonce_tail   ]
+ *    [     12-byte full IV    ] -> OVPN_NONCE_SIZE
+ *    [4-bytes                   -> OVPN_NONCE_WIRE_SIZE
+ *    on wire]
+ */
+
+/* nonce size (96bits) as required by AEAD ciphers */
+#define OVPN_NONCE_SIZE			12
+/* last 8 bytes of AEAD nonce: provided by userspace and usually derived
+ * from key material generated during TLS handshake
+ */
+#define OVPN_NONCE_TAIL_SIZE		8
+
+/* OpenVPN nonce size reduced by 8-byte nonce tail -- this is the
+ * size of the AEAD Associated Data (AD) sent over the wire
+ * and is normally the head of the IV
+ */
+#define OVPN_NONCE_WIRE_SIZE (OVPN_NONCE_SIZE - OVPN_NONCE_TAIL_SIZE)
+
+#define OVPN_OPCODE_SIZE		4 /* DATA_V2 opcode size */
+#define OVPN_OPCODE_KEYID_MASK		0x07000000
+#define OVPN_OPCODE_PKTTYPE_MASK	0xF8000000
+#define OVPN_OPCODE_PEERID_MASK		0x00FFFFFF
+
+/* packet opcodes of interest to us */
+#define OVPN_DATA_V1			6 /* data channel v1 packet */
+#define OVPN_DATA_V2			9 /* data channel v2 packet */
+
+#define OVPN_PEER_ID_UNDEF		0x00FFFFFF
+
+/**
+ * ovpn_opcode_from_skb - extract OP code from skb at specified offset
+ * @skb: the packet to extract the OP code from
+ * @offset: the offset in the data buffer where the OP code is located
+ *
+ * Note: this function assumes that the skb head was pulled enough
+ * to access the first 4 bytes.
+ *
+ * Return: the OP code
+ */
+static inline u8 ovpn_opcode_from_skb(const struct sk_buff *skb, u16 offset)
+{
+	u32 opcode = be32_to_cpu(*(__be32 *)(skb->data + offset));
+
+	return FIELD_GET(OVPN_OPCODE_PKTTYPE_MASK, opcode);
+}
+
+/**
+ * ovpn_peer_id_from_skb - extract peer ID from skb at specified offset
+ * @skb: the packet to extract the OP code from
+ * @offset: the offset in the data buffer where the OP code is located
+ *
+ * Note: this function assumes that the skb head was pulled enough
+ * to access the first 4 bytes.
+ *
+ * Return: the peer ID
+ */
+static inline u32 ovpn_peer_id_from_skb(const struct sk_buff *skb, u16 offset)
+{
+	u32 opcode = be32_to_cpu(*(__be32 *)(skb->data + offset));
+
+	return FIELD_GET(OVPN_OPCODE_PEERID_MASK, opcode);
+}
+
+/**
+ * ovpn_key_id_from_skb - extract key ID from the skb head
+ * @skb: the packet to extract the key ID code from
+ *
+ * Note: this function assumes that the skb head was pulled enough
+ * to access the first 4 bytes.
+ *
+ * Return: the key ID
+ */
+static inline u8 ovpn_key_id_from_skb(const struct sk_buff *skb)
+{
+	u32 opcode = be32_to_cpu(*(__be32 *)skb->data);
+
+	return FIELD_GET(OVPN_OPCODE_KEYID_MASK, opcode);
+}
+
+/**
+ * ovpn_opcode_compose - combine OP code, key ID and peer ID to wire format
+ * @opcode: the OP code
+ * @key_id: the key ID
+ * @peer_id: the peer ID
+ *
+ * Return: a 4 bytes integer obtained combining all input values following the
+ * OpenVPN wire format. This integer can then be written to the packet header.
+ */
+static inline u32 ovpn_opcode_compose(u8 opcode, u8 key_id, u32 peer_id)
+{
+	return FIELD_PREP(OVPN_OPCODE_PKTTYPE_MASK, opcode) |
+	       FIELD_PREP(OVPN_OPCODE_KEYID_MASK, key_id) |
+	       FIELD_PREP(OVPN_OPCODE_PEERID_MASK, peer_id);
+}
+
+#endif /* _NET_OVPN_OVPNPROTO_H_ */
diff --git a/drivers/net/ovpn/skb.h b/drivers/net/ovpn/skb.h
new file mode 100644
index 000000000000..64430880f1da
--- /dev/null
+++ b/drivers/net/ovpn/skb.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ *		James Yonan <james@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_SKB_H_
+#define _NET_OVPN_SKB_H_
+
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/skbuff.h>
+#include <linux/socket.h>
+#include <linux/types.h>
+
+struct ovpn_cb {
+	struct ovpn_peer *peer;
+	struct ovpn_crypto_key_slot *ks;
+	struct aead_request *req;
+	struct scatterlist *sg;
+	u8 *iv;
+	unsigned int payload_offset;
+	bool nosignal;
+};
+
+static inline struct ovpn_cb *ovpn_skb_cb(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(struct ovpn_cb) > sizeof(skb->cb));
+	return (struct ovpn_cb *)skb->cb;
+}
+
+/* Return IP protocol version from skb header.
+ * Return 0 if protocol is not IPv4/IPv6 or cannot be read.
+ */
+static inline __be16 ovpn_ip_check_protocol(struct sk_buff *skb)
+{
+	__be16 proto = 0;
+
+	/* skb could be non-linear,
+	 * make sure IP header is in non-fragmented part
+	 */
+	if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
+		return 0;
+
+	if (ip_hdr(skb)->version == 4) {
+		proto = htons(ETH_P_IP);
+	} else if (ip_hdr(skb)->version == 6) {
+		if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr)))
+			return 0;
+		proto = htons(ETH_P_IPV6);
+	}
+
+	return proto;
+}
+
+#endif /* _NET_OVPN_SKB_H_ */
diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c
new file mode 100644
index 000000000000..a83cbab72591
--- /dev/null
+++ b/drivers/net/ovpn/socket.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/udp.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "io.h"
+#include "peer.h"
+#include "socket.h"
+#include "tcp.h"
+#include "udp.h"
+
+static void ovpn_socket_release_kref(struct kref *kref)
+{
+	struct ovpn_socket *sock = container_of(kref, struct ovpn_socket,
+						refcount);
+
+	if (sock->sock->sk->sk_protocol == IPPROTO_UDP)
+		ovpn_udp_socket_detach(sock);
+	else if (sock->sock->sk->sk_protocol == IPPROTO_TCP)
+		ovpn_tcp_socket_detach(sock);
+}
+
+/**
+ * ovpn_socket_put - decrease reference counter
+ * @peer: peer whose socket reference counter should be decreased
+ * @sock: the RCU protected peer socket
+ *
+ * This function is only used internally. Users willing to release
+ * references to the ovpn_socket should use ovpn_socket_release()
+ *
+ * Return: true if the socket was released, false otherwise
+ */
+static bool ovpn_socket_put(struct ovpn_peer *peer, struct ovpn_socket *sock)
+{
+	return kref_put(&sock->refcount, ovpn_socket_release_kref);
+}
+
+/**
+ * ovpn_socket_release - release resources owned by socket user
+ * @peer: peer whose socket should be released
+ *
+ * This function should be invoked when the peer is being removed
+ * and wants to drop its link to the socket.
+ *
+ * In case of UDP, the detach routine will drop a reference to the
+ * ovpn netdev, pointed by the ovpn_socket.
+ *
+ * In case of TCP, releasing the socket will cause dropping
+ * the refcounter for the peer it is linked to, thus allowing the peer
+ * disappear as well.
+ *
+ * This function is expected to be invoked exactly once per peer
+ *
+ * NOTE: this function may sleep
+ */
+void ovpn_socket_release(struct ovpn_peer *peer)
+{
+	struct ovpn_socket *sock;
+	bool released;
+
+	might_sleep();
+
+	sock = rcu_replace_pointer(peer->sock, NULL, true);
+	/* release may be invoked after socket was detached */
+	if (!sock)
+		return;
+
+	/* sanity check: we should not end up here if the socket
+	 * was already closed
+	 */
+	if (!sock->sock->sk) {
+		DEBUG_NET_WARN_ON_ONCE(1);
+		return;
+	}
+
+	/* Drop the reference while holding the sock lock to avoid
+	 * concurrent ovpn_socket_new call to mess up with a partially
+	 * detached socket.
+	 *
+	 * Holding the lock ensures that a socket with refcnt 0 is fully
+	 * detached before it can be picked by a concurrent reader.
+	 */
+	lock_sock(sock->sock->sk);
+	released = ovpn_socket_put(peer, sock);
+	release_sock(sock->sock->sk);
+
+	/* align all readers with sk_user_data being NULL */
+	synchronize_rcu();
+
+	/* following cleanup should happen with lock released */
+	if (released) {
+		if (sock->sock->sk->sk_protocol == IPPROTO_UDP) {
+			netdev_put(sock->ovpn->dev, &sock->dev_tracker);
+		} else if (sock->sock->sk->sk_protocol == IPPROTO_TCP) {
+			/* wait for TCP jobs to terminate */
+			ovpn_tcp_socket_wait_finish(sock);
+			ovpn_peer_put(sock->peer);
+		}
+		/* we can call plain kfree() because we already waited one RCU
+		 * period due to synchronize_rcu()
+		 */
+		kfree(sock);
+	}
+}
+
+static bool ovpn_socket_hold(struct ovpn_socket *sock)
+{
+	return kref_get_unless_zero(&sock->refcount);
+}
+
+static int ovpn_socket_attach(struct ovpn_socket *sock, struct ovpn_peer *peer)
+{
+	if (sock->sock->sk->sk_protocol == IPPROTO_UDP)
+		return ovpn_udp_socket_attach(sock, peer->ovpn);
+	else if (sock->sock->sk->sk_protocol == IPPROTO_TCP)
+		return ovpn_tcp_socket_attach(sock, peer);
+
+	return -EOPNOTSUPP;
+}
+
+/**
+ * ovpn_socket_new - create a new socket and initialize it
+ * @sock: the kernel socket to embed
+ * @peer: the peer reachable via this socket
+ *
+ * Return: an openvpn socket on success or a negative error code otherwise
+ */
+struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
+{
+	struct ovpn_socket *ovpn_sock;
+	int ret;
+
+	lock_sock(sock->sk);
+
+	/* a TCP socket can only be owned by a single peer, therefore there
+	 * can't be any other user
+	 */
+	if (sock->sk->sk_protocol == IPPROTO_TCP && sock->sk->sk_user_data) {
+		ovpn_sock = ERR_PTR(-EBUSY);
+		goto sock_release;
+	}
+
+	/* a UDP socket can be shared across multiple peers, but we must make
+	 * sure it is not owned by something else
+	 */
+	if (sock->sk->sk_protocol == IPPROTO_UDP) {
+		u8 type = READ_ONCE(udp_sk(sock->sk)->encap_type);
+
+		/* socket owned by other encapsulation module */
+		if (type && type != UDP_ENCAP_OVPNINUDP) {
+			ovpn_sock = ERR_PTR(-EBUSY);
+			goto sock_release;
+		}
+
+		rcu_read_lock();
+		ovpn_sock = rcu_dereference_sk_user_data(sock->sk);
+		if (ovpn_sock) {
+			/* socket owned by another ovpn instance, we can't use it */
+			if (ovpn_sock->ovpn != peer->ovpn) {
+				ovpn_sock = ERR_PTR(-EBUSY);
+				rcu_read_unlock();
+				goto sock_release;
+			}
+
+			/* this socket is already owned by this instance,
+			 * therefore we can increase the refcounter and
+			 * use it as expected
+			 */
+			if (WARN_ON(!ovpn_socket_hold(ovpn_sock))) {
+				/* this should never happen because setting
+				 * the refcnt to 0 and detaching the socket
+				 * is expected to be atomic
+				 */
+				ovpn_sock = ERR_PTR(-EAGAIN);
+				rcu_read_unlock();
+				goto sock_release;
+			}
+
+			rcu_read_unlock();
+			goto sock_release;
+		}
+		rcu_read_unlock();
+	}
+
+	/* socket is not owned: attach to this ovpn instance */
+
+	ovpn_sock = kzalloc(sizeof(*ovpn_sock), GFP_KERNEL);
+	if (!ovpn_sock) {
+		ovpn_sock = ERR_PTR(-ENOMEM);
+		goto sock_release;
+	}
+
+	ovpn_sock->sock = sock;
+	kref_init(&ovpn_sock->refcount);
+
+	ret = ovpn_socket_attach(ovpn_sock, peer);
+	if (ret < 0) {
+		kfree(ovpn_sock);
+		ovpn_sock = ERR_PTR(ret);
+		goto sock_release;
+	}
+
+	/* TCP sockets are per-peer, therefore they are linked to their unique
+	 * peer
+	 */
+	if (sock->sk->sk_protocol == IPPROTO_TCP) {
+		INIT_WORK(&ovpn_sock->tcp_tx_work, ovpn_tcp_tx_work);
+		ovpn_sock->peer = peer;
+		ovpn_peer_hold(peer);
+	} else if (sock->sk->sk_protocol == IPPROTO_UDP) {
+		/* in UDP we only link the ovpn instance since the socket is
+		 * shared among multiple peers
+		 */
+		ovpn_sock->ovpn = peer->ovpn;
+		netdev_hold(peer->ovpn->dev, &ovpn_sock->dev_tracker,
+			    GFP_KERNEL);
+	}
+
+	rcu_assign_sk_user_data(sock->sk, ovpn_sock);
+sock_release:
+	release_sock(sock->sk);
+	return ovpn_sock;
+}
diff --git a/drivers/net/ovpn/socket.h b/drivers/net/ovpn/socket.h
new file mode 100644
index 000000000000..00d856b1a5d8
--- /dev/null
+++ b/drivers/net/ovpn/socket.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_SOCK_H_
+#define _NET_OVPN_SOCK_H_
+
+#include <linux/net.h>
+#include <linux/kref.h>
+#include <net/sock.h>
+
+struct ovpn_priv;
+struct ovpn_peer;
+
+/**
+ * struct ovpn_socket - a kernel socket referenced in the ovpn code
+ * @ovpn: ovpn instance owning this socket (UDP only)
+ * @dev_tracker: reference tracker for associated dev (UDP only)
+ * @peer: unique peer transmitting over this socket (TCP only)
+ * @sock: the low level sock object
+ * @refcount: amount of contexts currently referencing this object
+ * @work: member used to schedule release routine (it may block)
+ * @tcp_tx_work: work for deferring outgoing packet processing (TCP only)
+ */
+struct ovpn_socket {
+	union {
+		struct {
+			struct ovpn_priv *ovpn;
+			netdevice_tracker dev_tracker;
+		};
+		struct ovpn_peer *peer;
+	};
+
+	struct socket *sock;
+	struct kref refcount;
+	struct work_struct work;
+	struct work_struct tcp_tx_work;
+};
+
+struct ovpn_socket *ovpn_socket_new(struct socket *sock,
+				    struct ovpn_peer *peer);
+void ovpn_socket_release(struct ovpn_peer *peer);
+
+#endif /* _NET_OVPN_SOCK_H_ */
diff --git a/drivers/net/ovpn/stats.c b/drivers/net/ovpn/stats.c
new file mode 100644
index 000000000000..d637143473bb
--- /dev/null
+++ b/drivers/net/ovpn/stats.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/atomic.h>
+
+#include "stats.h"
+
+void ovpn_peer_stats_init(struct ovpn_peer_stats *ps)
+{
+	atomic64_set(&ps->rx.bytes, 0);
+	atomic64_set(&ps->rx.packets, 0);
+
+	atomic64_set(&ps->tx.bytes, 0);
+	atomic64_set(&ps->tx.packets, 0);
+}
diff --git a/drivers/net/ovpn/stats.h b/drivers/net/ovpn/stats.h
new file mode 100644
index 000000000000..53433d8b6c33
--- /dev/null
+++ b/drivers/net/ovpn/stats.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ *		Lev Stipakov <lev@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNSTATS_H_
+#define _NET_OVPN_OVPNSTATS_H_
+
+/* one stat */
+struct ovpn_peer_stat {
+	atomic64_t bytes;
+	atomic64_t packets;
+};
+
+/* rx and tx stats combined */
+struct ovpn_peer_stats {
+	struct ovpn_peer_stat rx;
+	struct ovpn_peer_stat tx;
+};
+
+void ovpn_peer_stats_init(struct ovpn_peer_stats *ps);
+
+static inline void ovpn_peer_stats_increment(struct ovpn_peer_stat *stat,
+					     const unsigned int n)
+{
+	atomic64_add(n, &stat->bytes);
+	atomic64_inc(&stat->packets);
+}
+
+static inline void ovpn_peer_stats_increment_rx(struct ovpn_peer_stats *stats,
+						const unsigned int n)
+{
+	ovpn_peer_stats_increment(&stats->rx, n);
+}
+
+static inline void ovpn_peer_stats_increment_tx(struct ovpn_peer_stats *stats,
+						const unsigned int n)
+{
+	ovpn_peer_stats_increment(&stats->tx, n);
+}
+
+#endif /* _NET_OVPN_OVPNSTATS_H_ */
diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c
new file mode 100644
index 000000000000..7c42d84987ad
--- /dev/null
+++ b/drivers/net/ovpn/tcp.c
@@ -0,0 +1,598 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/skbuff.h>
+#include <net/hotdata.h>
+#include <net/inet_common.h>
+#include <net/ipv6.h>
+#include <net/tcp.h>
+#include <net/transp_v6.h>
+#include <net/route.h>
+#include <trace/events/sock.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "io.h"
+#include "peer.h"
+#include "proto.h"
+#include "skb.h"
+#include "tcp.h"
+
+#define OVPN_TCP_DEPTH_NESTING	2
+#if OVPN_TCP_DEPTH_NESTING == SINGLE_DEPTH_NESTING
+#error "OVPN TCP requires its own lockdep subclass"
+#endif
+
+static struct proto ovpn_tcp_prot __ro_after_init;
+static struct proto_ops ovpn_tcp_ops __ro_after_init;
+static struct proto ovpn_tcp6_prot __ro_after_init;
+static struct proto_ops ovpn_tcp6_ops __ro_after_init;
+
+static int ovpn_tcp_parse(struct strparser *strp, struct sk_buff *skb)
+{
+	struct strp_msg *rxm = strp_msg(skb);
+	__be16 blen;
+	u16 len;
+	int err;
+
+	/* when packets are written to the TCP stream, they are prepended with
+	 * two bytes indicating the actual packet size.
+	 * Parse accordingly and return the actual size (including the size
+	 * header)
+	 */
+
+	if (skb->len < rxm->offset + 2)
+		return 0;
+
+	err = skb_copy_bits(skb, rxm->offset, &blen, sizeof(blen));
+	if (err < 0)
+		return err;
+
+	len = be16_to_cpu(blen);
+	if (len < 2)
+		return -EINVAL;
+
+	return len + 2;
+}
+
+/* queue skb for sending to userspace via recvmsg on the socket */
+static void ovpn_tcp_to_userspace(struct ovpn_peer *peer, struct sock *sk,
+				  struct sk_buff *skb)
+{
+	skb_set_owner_r(skb, sk);
+	memset(skb->cb, 0, sizeof(skb->cb));
+	skb_queue_tail(&peer->tcp.user_queue, skb);
+	peer->tcp.sk_cb.sk_data_ready(sk);
+}
+
+static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb)
+{
+	struct ovpn_peer *peer = container_of(strp, struct ovpn_peer, tcp.strp);
+	struct strp_msg *msg = strp_msg(skb);
+	size_t pkt_len = msg->full_len - 2;
+	size_t off = msg->offset + 2;
+	u8 opcode;
+
+	/* ensure skb->data points to the beginning of the openvpn packet */
+	if (!pskb_pull(skb, off)) {
+		net_warn_ratelimited("%s: packet too small for peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		goto err;
+	}
+
+	/* strparser does not trim the skb for us, therefore we do it now */
+	if (pskb_trim(skb, pkt_len) != 0) {
+		net_warn_ratelimited("%s: trimming skb failed for peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		goto err;
+	}
+
+	/* we need the first 4 bytes of data to be accessible
+	 * to extract the opcode and the key ID later on
+	 */
+	if (!pskb_may_pull(skb, OVPN_OPCODE_SIZE)) {
+		net_warn_ratelimited("%s: packet too small to fetch opcode for peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		goto err;
+	}
+
+	/* DATA_V2 packets are handled in kernel, the rest goes to user space */
+	opcode = ovpn_opcode_from_skb(skb, 0);
+	if (unlikely(opcode != OVPN_DATA_V2)) {
+		if (opcode == OVPN_DATA_V1) {
+			net_warn_ratelimited("%s: DATA_V1 detected on the TCP stream\n",
+					     netdev_name(peer->ovpn->dev));
+			goto err;
+		}
+
+		/* The packet size header must be there when sending the packet
+		 * to userspace, therefore we put it back
+		 */
+		skb_push(skb, 2);
+		ovpn_tcp_to_userspace(peer, strp->sk, skb);
+		return;
+	}
+
+	/* hold reference to peer as required by ovpn_recv().
+	 *
+	 * NOTE: in this context we should already be holding a reference to
+	 * this peer, therefore ovpn_peer_hold() is not expected to fail
+	 */
+	if (WARN_ON(!ovpn_peer_hold(peer)))
+		goto err;
+
+	ovpn_recv(peer, skb);
+	return;
+err:
+	dev_dstats_rx_dropped(peer->ovpn->dev);
+	kfree_skb(skb);
+	ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_TRANSPORT_ERROR);
+}
+
+static int ovpn_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			    int flags, int *addr_len)
+{
+	int err = 0, off, copied = 0, ret;
+	struct ovpn_socket *sock;
+	struct ovpn_peer *peer;
+	struct sk_buff *skb;
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!sock || !sock->peer || !ovpn_peer_hold(sock->peer))) {
+		rcu_read_unlock();
+		return -EBADF;
+	}
+	peer = sock->peer;
+	rcu_read_unlock();
+
+	skb = __skb_recv_datagram(sk, &peer->tcp.user_queue, flags, &off, &err);
+	if (!skb) {
+		if (err == -EAGAIN && sk->sk_shutdown & RCV_SHUTDOWN) {
+			ret = 0;
+			goto out;
+		}
+		ret = err;
+		goto out;
+	}
+
+	copied = len;
+	if (copied > skb->len)
+		copied = skb->len;
+	else if (copied < skb->len)
+		msg->msg_flags |= MSG_TRUNC;
+
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
+	if (unlikely(err)) {
+		kfree_skb(skb);
+		ret = err;
+		goto out;
+	}
+
+	if (flags & MSG_TRUNC)
+		copied = skb->len;
+	kfree_skb(skb);
+	ret = copied;
+out:
+	ovpn_peer_put(peer);
+	return ret;
+}
+
+void ovpn_tcp_socket_detach(struct ovpn_socket *ovpn_sock)
+{
+	struct ovpn_peer *peer = ovpn_sock->peer;
+	struct socket *sock = ovpn_sock->sock;
+
+	strp_stop(&peer->tcp.strp);
+	skb_queue_purge(&peer->tcp.user_queue);
+
+	/* restore CBs that were saved in ovpn_sock_set_tcp_cb() */
+	sock->sk->sk_data_ready = peer->tcp.sk_cb.sk_data_ready;
+	sock->sk->sk_write_space = peer->tcp.sk_cb.sk_write_space;
+	sock->sk->sk_prot = peer->tcp.sk_cb.prot;
+	sock->sk->sk_socket->ops = peer->tcp.sk_cb.ops;
+
+	rcu_assign_sk_user_data(sock->sk, NULL);
+}
+
+void ovpn_tcp_socket_wait_finish(struct ovpn_socket *sock)
+{
+	struct ovpn_peer *peer = sock->peer;
+
+	/* NOTE: we don't wait for peer->tcp.defer_del_work to finish:
+	 * either the worker is not running or this function
+	 * was invoked by that worker.
+	 */
+
+	cancel_work_sync(&sock->tcp_tx_work);
+	strp_done(&peer->tcp.strp);
+
+	skb_queue_purge(&peer->tcp.out_queue);
+	kfree_skb(peer->tcp.out_msg.skb);
+	peer->tcp.out_msg.skb = NULL;
+}
+
+static void ovpn_tcp_send_sock(struct ovpn_peer *peer, struct sock *sk)
+{
+	struct sk_buff *skb = peer->tcp.out_msg.skb;
+	int ret, flags;
+
+	if (!skb)
+		return;
+
+	if (peer->tcp.tx_in_progress)
+		return;
+
+	peer->tcp.tx_in_progress = true;
+
+	do {
+		flags = ovpn_skb_cb(skb)->nosignal ? MSG_NOSIGNAL : 0;
+		ret = skb_send_sock_locked_with_flags(sk, skb,
+						      peer->tcp.out_msg.offset,
+						      peer->tcp.out_msg.len,
+						      flags);
+		if (unlikely(ret < 0)) {
+			if (ret == -EAGAIN)
+				goto out;
+
+			net_warn_ratelimited("%s: TCP error to peer %u: %d\n",
+					     netdev_name(peer->ovpn->dev),
+					     peer->id, ret);
+
+			/* in case of TCP error we can't recover the VPN
+			 * stream therefore we abort the connection
+			 */
+			ovpn_peer_hold(peer);
+			schedule_work(&peer->tcp.defer_del_work);
+
+			/* we bail out immediately and keep tx_in_progress set
+			 * to true. This way we prevent more TX attempts
+			 * which would lead to more invocations of
+			 * schedule_work()
+			 */
+			return;
+		}
+
+		peer->tcp.out_msg.len -= ret;
+		peer->tcp.out_msg.offset += ret;
+	} while (peer->tcp.out_msg.len > 0);
+
+	if (!peer->tcp.out_msg.len) {
+		preempt_disable();
+		dev_dstats_tx_add(peer->ovpn->dev, skb->len);
+		preempt_enable();
+	}
+
+	kfree_skb(peer->tcp.out_msg.skb);
+	peer->tcp.out_msg.skb = NULL;
+	peer->tcp.out_msg.len = 0;
+	peer->tcp.out_msg.offset = 0;
+
+out:
+	peer->tcp.tx_in_progress = false;
+}
+
+void ovpn_tcp_tx_work(struct work_struct *work)
+{
+	struct ovpn_socket *sock;
+
+	sock = container_of(work, struct ovpn_socket, tcp_tx_work);
+
+	lock_sock(sock->sock->sk);
+	if (sock->peer)
+		ovpn_tcp_send_sock(sock->peer, sock->sock->sk);
+	release_sock(sock->sock->sk);
+}
+
+static void ovpn_tcp_send_sock_skb(struct ovpn_peer *peer, struct sock *sk,
+				   struct sk_buff *skb)
+{
+	if (peer->tcp.out_msg.skb)
+		ovpn_tcp_send_sock(peer, sk);
+
+	if (peer->tcp.out_msg.skb) {
+		dev_dstats_tx_dropped(peer->ovpn->dev);
+		kfree_skb(skb);
+		return;
+	}
+
+	peer->tcp.out_msg.skb = skb;
+	peer->tcp.out_msg.len = skb->len;
+	peer->tcp.out_msg.offset = 0;
+	ovpn_tcp_send_sock(peer, sk);
+}
+
+void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct socket *sock,
+		       struct sk_buff *skb)
+{
+	u16 len = skb->len;
+
+	*(__be16 *)__skb_push(skb, sizeof(u16)) = htons(len);
+
+	spin_lock_nested(&sock->sk->sk_lock.slock, OVPN_TCP_DEPTH_NESTING);
+	if (sock_owned_by_user(sock->sk)) {
+		if (skb_queue_len(&peer->tcp.out_queue) >=
+		    READ_ONCE(net_hotdata.max_backlog)) {
+			dev_dstats_tx_dropped(peer->ovpn->dev);
+			kfree_skb(skb);
+			goto unlock;
+		}
+		__skb_queue_tail(&peer->tcp.out_queue, skb);
+	} else {
+		ovpn_tcp_send_sock_skb(peer, sock->sk, skb);
+	}
+unlock:
+	spin_unlock(&sock->sk->sk_lock.slock);
+}
+
+static void ovpn_tcp_release(struct sock *sk)
+{
+	struct sk_buff_head queue;
+	struct ovpn_socket *sock;
+	struct ovpn_peer *peer;
+	struct sk_buff *skb;
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (!sock) {
+		rcu_read_unlock();
+		return;
+	}
+
+	peer = sock->peer;
+
+	/* during initialization this function is called before
+	 * assigning sock->peer
+	 */
+	if (unlikely(!peer || !ovpn_peer_hold(peer))) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+
+	__skb_queue_head_init(&queue);
+	skb_queue_splice_init(&peer->tcp.out_queue, &queue);
+
+	while ((skb = __skb_dequeue(&queue)))
+		ovpn_tcp_send_sock_skb(peer, sk, skb);
+
+	peer->tcp.sk_cb.prot->release_cb(sk);
+	ovpn_peer_put(peer);
+}
+
+static int ovpn_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+{
+	struct ovpn_socket *sock;
+	int ret, linear = PAGE_SIZE;
+	struct ovpn_peer *peer;
+	struct sk_buff *skb;
+
+	lock_sock(sk);
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!sock || !sock->peer || !ovpn_peer_hold(sock->peer))) {
+		rcu_read_unlock();
+		release_sock(sk);
+		return -EIO;
+	}
+	rcu_read_unlock();
+	peer = sock->peer;
+
+	if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_NOSIGNAL)) {
+		ret = -EOPNOTSUPP;
+		goto peer_free;
+	}
+
+	if (peer->tcp.out_msg.skb) {
+		ret = -EAGAIN;
+		goto peer_free;
+	}
+
+	if (size < linear)
+		linear = size;
+
+	skb = sock_alloc_send_pskb(sk, linear, size - linear,
+				   msg->msg_flags & MSG_DONTWAIT, &ret, 0);
+	if (!skb) {
+		net_err_ratelimited("%s: skb alloc failed: %d\n",
+				    netdev_name(peer->ovpn->dev), ret);
+		goto peer_free;
+	}
+
+	skb_put(skb, linear);
+	skb->len = size;
+	skb->data_len = size - linear;
+
+	ret = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+	if (ret) {
+		kfree_skb(skb);
+		net_err_ratelimited("%s: skb copy from iter failed: %d\n",
+				    netdev_name(peer->ovpn->dev), ret);
+		goto peer_free;
+	}
+
+	ovpn_skb_cb(skb)->nosignal = msg->msg_flags & MSG_NOSIGNAL;
+	ovpn_tcp_send_sock_skb(peer, sk, skb);
+	ret = size;
+peer_free:
+	release_sock(sk);
+	ovpn_peer_put(peer);
+	return ret;
+}
+
+static int ovpn_tcp_disconnect(struct sock *sk, int flags)
+{
+	return -EBUSY;
+}
+
+static void ovpn_tcp_data_ready(struct sock *sk)
+{
+	struct ovpn_socket *sock;
+
+	trace_sk_data_ready(sk);
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (likely(sock && sock->peer))
+		strp_data_ready(&sock->peer->tcp.strp);
+	rcu_read_unlock();
+}
+
+static void ovpn_tcp_write_space(struct sock *sk)
+{
+	struct ovpn_socket *sock;
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (likely(sock && sock->peer)) {
+		schedule_work(&sock->tcp_tx_work);
+		sock->peer->tcp.sk_cb.sk_write_space(sk);
+	}
+	rcu_read_unlock();
+}
+
+static void ovpn_tcp_build_protos(struct proto *new_prot,
+				  struct proto_ops *new_ops,
+				  const struct proto *orig_prot,
+				  const struct proto_ops *orig_ops);
+
+static void ovpn_tcp_peer_del_work(struct work_struct *work)
+{
+	struct ovpn_peer *peer = container_of(work, struct ovpn_peer,
+					      tcp.defer_del_work);
+
+	ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_TRANSPORT_ERROR);
+	ovpn_peer_put(peer);
+}
+
+/* Set TCP encapsulation callbacks */
+int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock,
+			   struct ovpn_peer *peer)
+{
+	struct socket *sock = ovpn_sock->sock;
+	struct strp_callbacks cb = {
+		.rcv_msg = ovpn_tcp_rcv,
+		.parse_msg = ovpn_tcp_parse,
+	};
+	int ret;
+
+	/* make sure no pre-existing encapsulation handler exists */
+	if (sock->sk->sk_user_data)
+		return -EBUSY;
+
+	/* only a fully connected socket is expected. Connection should be
+	 * handled in userspace
+	 */
+	if (sock->sk->sk_state != TCP_ESTABLISHED) {
+		net_err_ratelimited("%s: provided TCP socket is not in ESTABLISHED state: %d\n",
+				    netdev_name(peer->ovpn->dev),
+				    sock->sk->sk_state);
+		return -EINVAL;
+	}
+
+	ret = strp_init(&peer->tcp.strp, sock->sk, &cb);
+	if (ret < 0) {
+		DEBUG_NET_WARN_ON_ONCE(1);
+		return ret;
+	}
+
+	INIT_WORK(&peer->tcp.defer_del_work, ovpn_tcp_peer_del_work);
+
+	__sk_dst_reset(sock->sk);
+	skb_queue_head_init(&peer->tcp.user_queue);
+	skb_queue_head_init(&peer->tcp.out_queue);
+
+	/* save current CBs so that they can be restored upon socket release */
+	peer->tcp.sk_cb.sk_data_ready = sock->sk->sk_data_ready;
+	peer->tcp.sk_cb.sk_write_space = sock->sk->sk_write_space;
+	peer->tcp.sk_cb.prot = sock->sk->sk_prot;
+	peer->tcp.sk_cb.ops = sock->sk->sk_socket->ops;
+
+	/* assign our static CBs and prot/ops */
+	sock->sk->sk_data_ready = ovpn_tcp_data_ready;
+	sock->sk->sk_write_space = ovpn_tcp_write_space;
+
+	if (sock->sk->sk_family == AF_INET) {
+		sock->sk->sk_prot = &ovpn_tcp_prot;
+		sock->sk->sk_socket->ops = &ovpn_tcp_ops;
+	} else {
+		sock->sk->sk_prot = &ovpn_tcp6_prot;
+		sock->sk->sk_socket->ops = &ovpn_tcp6_ops;
+	}
+
+	/* avoid using task_frag */
+	sock->sk->sk_allocation = GFP_ATOMIC;
+	sock->sk->sk_use_task_frag = false;
+
+	/* enqueue the RX worker */
+	strp_check_rcv(&peer->tcp.strp);
+
+	return 0;
+}
+
+static void ovpn_tcp_close(struct sock *sk, long timeout)
+{
+	struct ovpn_socket *sock;
+	struct ovpn_peer *peer;
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (!sock || !sock->peer || !ovpn_peer_hold(sock->peer)) {
+		rcu_read_unlock();
+		return;
+	}
+	peer = sock->peer;
+	rcu_read_unlock();
+
+	ovpn_peer_del(sock->peer, OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT);
+	peer->tcp.sk_cb.prot->close(sk, timeout);
+	ovpn_peer_put(peer);
+}
+
+static __poll_t ovpn_tcp_poll(struct file *file, struct socket *sock,
+			      poll_table *wait)
+{
+	__poll_t mask = datagram_poll(file, sock, wait);
+	struct ovpn_socket *ovpn_sock;
+
+	rcu_read_lock();
+	ovpn_sock = rcu_dereference_sk_user_data(sock->sk);
+	if (ovpn_sock && ovpn_sock->peer &&
+	    !skb_queue_empty(&ovpn_sock->peer->tcp.user_queue))
+		mask |= EPOLLIN | EPOLLRDNORM;
+	rcu_read_unlock();
+
+	return mask;
+}
+
+static void ovpn_tcp_build_protos(struct proto *new_prot,
+				  struct proto_ops *new_ops,
+				  const struct proto *orig_prot,
+				  const struct proto_ops *orig_ops)
+{
+	memcpy(new_prot, orig_prot, sizeof(*new_prot));
+	memcpy(new_ops, orig_ops, sizeof(*new_ops));
+	new_prot->recvmsg = ovpn_tcp_recvmsg;
+	new_prot->sendmsg = ovpn_tcp_sendmsg;
+	new_prot->disconnect = ovpn_tcp_disconnect;
+	new_prot->close = ovpn_tcp_close;
+	new_prot->release_cb = ovpn_tcp_release;
+	new_ops->poll = ovpn_tcp_poll;
+}
+
+/* Initialize TCP static objects */
+void __init ovpn_tcp_init(void)
+{
+	ovpn_tcp_build_protos(&ovpn_tcp_prot, &ovpn_tcp_ops, &tcp_prot,
+			      &inet_stream_ops);
+
+#if IS_ENABLED(CONFIG_IPV6)
+	ovpn_tcp_build_protos(&ovpn_tcp6_prot, &ovpn_tcp6_ops, &tcpv6_prot,
+			      &inet6_stream_ops);
+#endif
+}
diff --git a/drivers/net/ovpn/tcp.h b/drivers/net/ovpn/tcp.h
new file mode 100644
index 000000000000..10aefa834cf3
--- /dev/null
+++ b/drivers/net/ovpn/tcp.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_TCP_H_
+#define _NET_OVPN_TCP_H_
+
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+
+#include "peer.h"
+#include "skb.h"
+#include "socket.h"
+
+void __init ovpn_tcp_init(void);
+
+int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock,
+			   struct ovpn_peer *peer);
+void ovpn_tcp_socket_detach(struct ovpn_socket *ovpn_sock);
+void ovpn_tcp_socket_wait_finish(struct ovpn_socket *sock);
+
+/* Prepare skb and enqueue it for sending to peer.
+ *
+ * Preparation consist in prepending the skb payload with its size.
+ * Required by the OpenVPN protocol in order to extract packets from
+ * the TCP stream on the receiver side.
+ */
+void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct socket *sock, struct sk_buff *skb);
+void ovpn_tcp_tx_work(struct work_struct *work);
+
+#endif /* _NET_OVPN_TCP_H_ */
diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c
new file mode 100644
index 000000000000..aef8c0406ec9
--- /dev/null
+++ b/drivers/net/ovpn/udp.c
@@ -0,0 +1,449 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/skbuff.h>
+#include <linux/socket.h>
+#include <linux/udp.h>
+#include <net/addrconf.h>
+#include <net/dst_cache.h>
+#include <net/route.h>
+#include <net/ipv6_stubs.h>
+#include <net/transp_v6.h>
+#include <net/udp.h>
+#include <net/udp_tunnel.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "bind.h"
+#include "io.h"
+#include "peer.h"
+#include "proto.h"
+#include "socket.h"
+#include "udp.h"
+
+/* Retrieve the corresponding ovpn object from a UDP socket
+ * rcu_read_lock must be held on entry
+ */
+static struct ovpn_socket *ovpn_socket_from_udp_sock(struct sock *sk)
+{
+	struct ovpn_socket *ovpn_sock;
+
+	if (unlikely(READ_ONCE(udp_sk(sk)->encap_type) != UDP_ENCAP_OVPNINUDP))
+		return NULL;
+
+	ovpn_sock = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!ovpn_sock))
+		return NULL;
+
+	/* make sure that sk matches our stored transport socket */
+	if (unlikely(!ovpn_sock->sock || sk != ovpn_sock->sock->sk))
+		return NULL;
+
+	return ovpn_sock;
+}
+
+/**
+ * ovpn_udp_encap_recv - Start processing a received UDP packet.
+ * @sk: socket over which the packet was received
+ * @skb: the received packet
+ *
+ * If the first byte of the payload is:
+ * - DATA_V2 the packet is accepted for further processing,
+ * - DATA_V1 the packet is dropped as not supported,
+ * - anything else the packet is forwarded to the UDP stack for
+ *   delivery to user space.
+ *
+ * Return:
+ *  0 if skb was consumed or dropped
+ * >0 if skb should be passed up to userspace as UDP (packet not consumed)
+ * <0 if skb should be resubmitted as proto -N (packet not consumed)
+ */
+static int ovpn_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+{
+	struct ovpn_socket *ovpn_sock;
+	struct ovpn_priv *ovpn;
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	u8 opcode;
+
+	ovpn_sock = ovpn_socket_from_udp_sock(sk);
+	if (unlikely(!ovpn_sock)) {
+		net_err_ratelimited("ovpn: %s invoked on non ovpn socket\n",
+				    __func__);
+		goto drop_noovpn;
+	}
+
+	ovpn = ovpn_sock->ovpn;
+	if (unlikely(!ovpn)) {
+		net_err_ratelimited("ovpn: cannot obtain ovpn object from UDP socket\n");
+		goto drop_noovpn;
+	}
+
+	/* Make sure the first 4 bytes of the skb data buffer after the UDP
+	 * header are accessible.
+	 * They are required to fetch the OP code, the key ID and the peer ID.
+	 */
+	if (unlikely(!pskb_may_pull(skb, sizeof(struct udphdr) +
+				    OVPN_OPCODE_SIZE))) {
+		net_dbg_ratelimited("%s: packet too small from UDP socket\n",
+				    netdev_name(ovpn->dev));
+		goto drop;
+	}
+
+	opcode = ovpn_opcode_from_skb(skb, sizeof(struct udphdr));
+	if (unlikely(opcode != OVPN_DATA_V2)) {
+		/* DATA_V1 is not supported */
+		if (opcode == OVPN_DATA_V1)
+			goto drop;
+
+		/* unknown or control packet: let it bubble up to userspace */
+		return 1;
+	}
+
+	peer_id = ovpn_peer_id_from_skb(skb, sizeof(struct udphdr));
+	/* some OpenVPN server implementations send data packets with the
+	 * peer-id set to UNDEF. In this case we skip the peer lookup by peer-id
+	 * and we try with the transport address
+	 */
+	if (peer_id == OVPN_PEER_ID_UNDEF)
+		peer = ovpn_peer_get_by_transp_addr(ovpn, skb);
+	else
+		peer = ovpn_peer_get_by_id(ovpn, peer_id);
+
+	if (unlikely(!peer))
+		goto drop;
+
+	/* pop off outer UDP header */
+	__skb_pull(skb, sizeof(struct udphdr));
+	ovpn_recv(peer, skb);
+	return 0;
+
+drop:
+	dev_dstats_rx_dropped(ovpn->dev);
+drop_noovpn:
+	kfree_skb(skb);
+	return 0;
+}
+
+/**
+ * ovpn_udp4_output - send IPv4 packet over udp socket
+ * @peer: the destination peer
+ * @bind: the binding related to the destination peer
+ * @cache: dst cache
+ * @sk: the socket to send the packet over
+ * @skb: the packet to send
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_udp4_output(struct ovpn_peer *peer, struct ovpn_bind *bind,
+			    struct dst_cache *cache, struct sock *sk,
+			    struct sk_buff *skb)
+{
+	struct rtable *rt;
+	struct flowi4 fl = {
+		.saddr = bind->local.ipv4.s_addr,
+		.daddr = bind->remote.in4.sin_addr.s_addr,
+		.fl4_sport = inet_sk(sk)->inet_sport,
+		.fl4_dport = bind->remote.in4.sin_port,
+		.flowi4_proto = sk->sk_protocol,
+		.flowi4_mark = sk->sk_mark,
+	};
+	int ret;
+
+	local_bh_disable();
+	rt = dst_cache_get_ip4(cache, &fl.saddr);
+	if (rt)
+		goto transmit;
+
+	if (unlikely(!inet_confirm_addr(sock_net(sk), NULL, 0, fl.saddr,
+					RT_SCOPE_HOST))) {
+		/* we may end up here when the cached address is not usable
+		 * anymore. In this case we reset address/cache and perform a
+		 * new look up
+		 */
+		fl.saddr = 0;
+		spin_lock_bh(&peer->lock);
+		bind->local.ipv4.s_addr = 0;
+		spin_unlock_bh(&peer->lock);
+		dst_cache_reset(cache);
+	}
+
+	rt = ip_route_output_flow(sock_net(sk), &fl, sk);
+	if (IS_ERR(rt) && PTR_ERR(rt) == -EINVAL) {
+		fl.saddr = 0;
+		spin_lock_bh(&peer->lock);
+		bind->local.ipv4.s_addr = 0;
+		spin_unlock_bh(&peer->lock);
+		dst_cache_reset(cache);
+
+		rt = ip_route_output_flow(sock_net(sk), &fl, sk);
+	}
+
+	if (IS_ERR(rt)) {
+		ret = PTR_ERR(rt);
+		net_dbg_ratelimited("%s: no route to host %pISpc: %d\n",
+				    netdev_name(peer->ovpn->dev),
+				    &bind->remote.in4,
+				    ret);
+		goto err;
+	}
+	dst_cache_set_ip4(cache, &rt->dst, fl.saddr);
+
+transmit:
+	udp_tunnel_xmit_skb(rt, sk, skb, fl.saddr, fl.daddr, 0,
+			    ip4_dst_hoplimit(&rt->dst), 0, fl.fl4_sport,
+			    fl.fl4_dport, false, sk->sk_no_check_tx);
+	ret = 0;
+err:
+	local_bh_enable();
+	return ret;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+/**
+ * ovpn_udp6_output - send IPv6 packet over udp socket
+ * @peer: the destination peer
+ * @bind: the binding related to the destination peer
+ * @cache: dst cache
+ * @sk: the socket to send the packet over
+ * @skb: the packet to send
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_udp6_output(struct ovpn_peer *peer, struct ovpn_bind *bind,
+			    struct dst_cache *cache, struct sock *sk,
+			    struct sk_buff *skb)
+{
+	struct dst_entry *dst;
+	int ret;
+
+	struct flowi6 fl = {
+		.saddr = bind->local.ipv6,
+		.daddr = bind->remote.in6.sin6_addr,
+		.fl6_sport = inet_sk(sk)->inet_sport,
+		.fl6_dport = bind->remote.in6.sin6_port,
+		.flowi6_proto = sk->sk_protocol,
+		.flowi6_mark = sk->sk_mark,
+		.flowi6_oif = bind->remote.in6.sin6_scope_id,
+	};
+
+	local_bh_disable();
+	dst = dst_cache_get_ip6(cache, &fl.saddr);
+	if (dst)
+		goto transmit;
+
+	if (unlikely(!ipv6_chk_addr(sock_net(sk), &fl.saddr, NULL, 0))) {
+		/* we may end up here when the cached address is not usable
+		 * anymore. In this case we reset address/cache and perform a
+		 * new look up
+		 */
+		fl.saddr = in6addr_any;
+		spin_lock_bh(&peer->lock);
+		bind->local.ipv6 = in6addr_any;
+		spin_unlock_bh(&peer->lock);
+		dst_cache_reset(cache);
+	}
+
+	dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sk), sk, &fl, NULL);
+	if (IS_ERR(dst)) {
+		ret = PTR_ERR(dst);
+		net_dbg_ratelimited("%s: no route to host %pISpc: %d\n",
+				    netdev_name(peer->ovpn->dev),
+				    &bind->remote.in6, ret);
+		goto err;
+	}
+	dst_cache_set_ip6(cache, dst, &fl.saddr);
+
+transmit:
+	/* user IPv6 packets may be larger than the transport interface
+	 * MTU (after encapsulation), however, since they are locally
+	 * generated we should ensure they get fragmented.
+	 * Setting the ignore_df flag to 1 will instruct ip6_fragment() to
+	 * fragment packets if needed.
+	 *
+	 * NOTE: this is not needed for IPv4 because we pass df=0 to
+	 * udp_tunnel_xmit_skb()
+	 */
+	skb->ignore_df = 1;
+	udp_tunnel6_xmit_skb(dst, sk, skb, skb->dev, &fl.saddr, &fl.daddr, 0,
+			     ip6_dst_hoplimit(dst), 0, fl.fl6_sport,
+			     fl.fl6_dport, udp_get_no_check6_tx(sk));
+	ret = 0;
+err:
+	local_bh_enable();
+	return ret;
+}
+#endif
+
+/**
+ * ovpn_udp_output - transmit skb using udp-tunnel
+ * @peer: the destination peer
+ * @cache: dst cache
+ * @sk: the socket to send the packet over
+ * @skb: the packet to send
+ *
+ * rcu_read_lock should be held on entry.
+ * On return, the skb is consumed.
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_udp_output(struct ovpn_peer *peer, struct dst_cache *cache,
+			   struct sock *sk, struct sk_buff *skb)
+{
+	struct ovpn_bind *bind;
+	int ret;
+
+	/* set sk to null if skb is already orphaned */
+	if (!skb->destructor)
+		skb->sk = NULL;
+
+	rcu_read_lock();
+	bind = rcu_dereference(peer->bind);
+	if (unlikely(!bind)) {
+		net_warn_ratelimited("%s: no bind for remote peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		ret = -ENODEV;
+		goto out;
+	}
+
+	switch (bind->remote.in4.sin_family) {
+	case AF_INET:
+		ret = ovpn_udp4_output(peer, bind, cache, sk, skb);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		ret = ovpn_udp6_output(peer, bind, cache, sk, skb);
+		break;
+#endif
+	default:
+		ret = -EAFNOSUPPORT;
+		break;
+	}
+
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * ovpn_udp_send_skb - prepare skb and send it over via UDP
+ * @peer: the destination peer
+ * @sock: the RCU protected peer socket
+ * @skb: the packet to send
+ */
+void ovpn_udp_send_skb(struct ovpn_peer *peer, struct socket *sock,
+		       struct sk_buff *skb)
+{
+	int ret = -1;
+
+	skb->dev = peer->ovpn->dev;
+	/* no checksum performed at this layer */
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* get socket info */
+	if (unlikely(!sock)) {
+		net_warn_ratelimited("%s: no sock for remote peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		goto out;
+	}
+
+	/* crypto layer -> transport (UDP) */
+	ret = ovpn_udp_output(peer, &peer->dst_cache, sock->sk, skb);
+out:
+	if (unlikely(ret < 0)) {
+		kfree_skb(skb);
+		return;
+	}
+}
+
+static void ovpn_udp_encap_destroy(struct sock *sk)
+{
+	struct ovpn_socket *sock;
+	struct ovpn_priv *ovpn;
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (!sock || !sock->ovpn) {
+		rcu_read_unlock();
+		return;
+	}
+	ovpn = sock->ovpn;
+	rcu_read_unlock();
+
+	ovpn_peers_free(ovpn, sk, OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT);
+}
+
+/**
+ * ovpn_udp_socket_attach - set udp-tunnel CBs on socket and link it to ovpn
+ * @ovpn_sock: socket to configure
+ * @ovpn: the openvp instance to link
+ *
+ * After invoking this function, the sock will be controlled by ovpn so that
+ * any incoming packet may be processed by ovpn first.
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
+			   struct ovpn_priv *ovpn)
+{
+	struct udp_tunnel_sock_cfg cfg = {
+		.encap_type = UDP_ENCAP_OVPNINUDP,
+		.encap_rcv = ovpn_udp_encap_recv,
+		.encap_destroy = ovpn_udp_encap_destroy,
+	};
+	struct socket *sock = ovpn_sock->sock;
+	struct ovpn_socket *old_data;
+	int ret;
+
+	/* make sure no pre-existing encapsulation handler exists */
+	rcu_read_lock();
+	old_data = rcu_dereference_sk_user_data(sock->sk);
+	if (!old_data) {
+		/* socket is currently unused - we can take it */
+		rcu_read_unlock();
+		setup_udp_tunnel_sock(sock_net(sock->sk), sock, &cfg);
+		return 0;
+	}
+
+	/* socket is in use. We need to understand if it's owned by this ovpn
+	 * instance or by something else.
+	 * In the former case, we can increase the refcounter and happily
+	 * use it, because the same UDP socket is expected to be shared among
+	 * different peers.
+	 *
+	 * Unlikely TCP, a single UDP socket can be used to talk to many remote
+	 * hosts and therefore openvpn instantiates one only for all its peers
+	 */
+	if ((READ_ONCE(udp_sk(sock->sk)->encap_type) == UDP_ENCAP_OVPNINUDP) &&
+	    old_data->ovpn == ovpn) {
+		netdev_dbg(ovpn->dev,
+			   "provided socket already owned by this interface\n");
+		ret = -EALREADY;
+	} else {
+		netdev_dbg(ovpn->dev,
+			   "provided socket already taken by other user\n");
+		ret = -EBUSY;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/**
+ * ovpn_udp_socket_detach - clean udp-tunnel status for this socket
+ * @ovpn_sock: the socket to clean
+ */
+void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock)
+{
+	struct udp_tunnel_sock_cfg cfg = { };
+
+	setup_udp_tunnel_sock(sock_net(ovpn_sock->sock->sk), ovpn_sock->sock,
+			      &cfg);
+}
diff --git a/drivers/net/ovpn/udp.h b/drivers/net/ovpn/udp.h
new file mode 100644
index 000000000000..9994eb6e0428
--- /dev/null
+++ b/drivers/net/ovpn/udp.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_UDP_H_
+#define _NET_OVPN_UDP_H_
+
+#include <net/sock.h>
+
+struct ovpn_peer;
+struct ovpn_priv;
+struct socket;
+
+int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
+			   struct ovpn_priv *ovpn);
+void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock);
+
+void ovpn_udp_send_skb(struct ovpn_peer *peer, struct socket *sock,
+		       struct sk_buff *skb);
+
+#endif /* _NET_OVPN_UDP_H_ */
diff --git a/drivers/net/pfcp.c b/drivers/net/pfcp.c
index f873a92d2445..28e6bc4a1f14 100644
--- a/drivers/net/pfcp.c
+++ b/drivers/net/pfcp.c
@@ -245,30 +245,21 @@ static int __net_init pfcp_net_init(struct net *net)
 	return 0;
 }
 
-static void __net_exit pfcp_net_exit(struct net *net)
+static void __net_exit pfcp_net_exit_rtnl(struct net *net,
+					  struct list_head *dev_to_kill)
 {
 	struct pfcp_net *pn = net_generic(net, pfcp_net_id);
 	struct pfcp_dev *pfcp, *pfcp_next;
-	struct net_device *dev;
-	LIST_HEAD(list);
-
-	rtnl_lock();
-	for_each_netdev(net, dev)
-		if (dev->rtnl_link_ops == &pfcp_link_ops)
-			pfcp_dellink(dev, &list);
 
 	list_for_each_entry_safe(pfcp, pfcp_next, &pn->pfcp_dev_list, list)
-		pfcp_dellink(pfcp->dev, &list);
-
-	unregister_netdevice_many(&list);
-	rtnl_unlock();
+		pfcp_dellink(pfcp->dev, dev_to_kill);
 }
 
 static struct pernet_operations pfcp_net_ops = {
-	.init	= pfcp_net_init,
-	.exit	= pfcp_net_exit,
-	.id	= &pfcp_net_id,
-	.size	= sizeof(struct pfcp_net),
+	.init = pfcp_net_init,
+	.exit_rtnl = pfcp_net_exit_rtnl,
+	.id = &pfcp_net_id,
+	.size = sizeof(struct pfcp_net),
 };
 
 static int __init pfcp_init(void)
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index d29f9f7fd2e1..a95cecabfe1b 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -5,7 +5,6 @@
 
 config PHYLINK
 	tristate
-	depends on NETDEVICES
 	select PHYLIB
 	select SWPHY
 	help
@@ -15,9 +14,7 @@ config PHYLINK
 
 menuconfig PHYLIB
 	tristate "PHY Device support and infrastructure"
-	depends on NETDEVICES
-	select MDIO_DEVICE
-	select MDIO_DEVRES
+	select MDIO_BUS
 	help
 	  Ethernet controllers are usually attached to PHY
 	  devices.  This option provides infrastructure for
@@ -79,6 +76,18 @@ config SFP
 
 comment "MII PHY device drivers"
 
+config AS21XXX_PHY
+	tristate "Aeonsemi AS21xxx PHYs"
+	help
+	  Currently supports the Aeonsemi AS21xxx PHY.
+
+	  These are C45 PHYs 10G that require all a generic firmware.
+
+	  Supported PHYs AS21011JB1, AS21011PB1, AS21010JB1, AS21010PB1,
+	  AS21511JB1, AS21511PB1, AS21510JB1, AS21510PB1, AS21210JB1,
+	  AS21210PB1 that all register with the PHY ID 0x7500 0x7500
+	  before the firmware is loaded.
+
 config AIR_EN8811H_PHY
 	tristate "Airoha EN8811H 2.5 Gigabit PHY"
 	help
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 23ce205ae91d..57933366fe54 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -3,30 +3,22 @@
 
 libphy-y			:= phy.o phy-c45.o phy-core.o phy_device.o \
 				   linkmode.o phy_link_topology.o \
-				   phy_package.o phy_caps.o
+				   phy_package.o phy_caps.o mdio_bus_provider.o
 mdio-bus-y			+= mdio_bus.o mdio_device.o
 
-ifdef CONFIG_MDIO_DEVICE
-obj-y				+= mdio-boardinfo.o
-endif
-
-# PHYLIB implies MDIO_DEVICE, in that case, we have a bunch of circular
-# dependencies that does not make it possible to split mdio-bus objects into a
-# dedicated loadable module, so we bundle them all together into libphy.ko
 ifdef CONFIG_PHYLIB
-libphy-y			+= $(mdio-bus-y)
-# the stubs are built-in whenever PHYLIB is built-in or module
-obj-y				+= stubs.o
-else
-obj-$(CONFIG_MDIO_DEVICE)	+= mdio-bus.o
+# built-in whenever PHYLIB is built-in or module
+obj-y				+= stubs.o mdio-boardinfo.o
 endif
-obj-$(CONFIG_MDIO_DEVRES)	+= mdio_devres.o
+
 libphy-$(CONFIG_SWPHY)		+= swphy.o
 libphy-$(CONFIG_LED_TRIGGER_PHY)	+= phy_led_triggers.o
 libphy-$(CONFIG_OPEN_ALLIANCE_HELPERS) += open_alliance_helpers.o
 
+obj-$(CONFIG_MDIO_BUS)		+= mdio-bus.o
 obj-$(CONFIG_PHYLINK)		+= phylink.o
 obj-$(CONFIG_PHYLIB)		+= libphy.o
+obj-$(CONFIG_PHYLIB)		+= mdio_devres.o
 
 obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += mii_timestamper.o
 
@@ -40,6 +32,7 @@ obj-$(CONFIG_AIR_EN8811H_PHY)   += air_en8811h.o
 obj-$(CONFIG_AMD_PHY)		+= amd.o
 obj-$(CONFIG_AMCC_QT2025_PHY)	+= qt2025.o
 obj-$(CONFIG_AQUANTIA_PHY)	+= aquantia/
+obj-$(CONFIG_AS21XXX_PHY)	+= as21xxx.o
 ifdef CONFIG_AX88796B_RUST_PHY
   obj-$(CONFIG_AX88796B_PHY)	+= ax88796b_rust.o
 else
diff --git a/drivers/net/phy/air_en8811h.c b/drivers/net/phy/air_en8811h.c
index e9fd24cb7270..57fbd8df9438 100644
--- a/drivers/net/phy/air_en8811h.c
+++ b/drivers/net/phy/air_en8811h.c
@@ -11,6 +11,7 @@
  * Copyright (C) 2023 Airoha Technology Corp.
  */
 
+#include <linux/clk-provider.h>
 #include <linux/phy.h>
 #include <linux/firmware.h>
 #include <linux/property.h>
@@ -115,6 +116,11 @@
 #define EN8811H_GPIO_OUTPUT		0xcf8b8
 #define   EN8811H_GPIO_OUTPUT_345		(BIT(3) | BIT(4) | BIT(5))
 
+#define EN8811H_HWTRAP1			0xcf914
+#define   EN8811H_HWTRAP1_CKO			BIT(12)
+#define EN8811H_CLK_CGM			0xcf958
+#define   EN8811H_CLK_CGM_CKO			BIT(26)
+
 #define EN8811H_FW_CTRL_1		0x0f0018
 #define   EN8811H_FW_CTRL_1_START		0x0
 #define   EN8811H_FW_CTRL_1_FINISH		0x1
@@ -142,10 +148,15 @@ struct led {
 	unsigned long state;
 };
 
+#define clk_hw_to_en8811h_priv(_hw)			\
+	container_of(_hw, struct en8811h_priv, hw)
+
 struct en8811h_priv {
-	u32		firmware_version;
-	bool		mcu_needs_restart;
-	struct led	led[EN8811H_LED_COUNT];
+	u32			firmware_version;
+	bool			mcu_needs_restart;
+	struct led		led[EN8811H_LED_COUNT];
+	struct clk_hw		hw;
+	struct phy_device	*phydev;
 };
 
 enum {
@@ -806,6 +817,86 @@ static int en8811h_led_hw_is_supported(struct phy_device *phydev, u8 index,
 	return 0;
 };
 
+static unsigned long en8811h_clk_recalc_rate(struct clk_hw *hw,
+					     unsigned long parent)
+{
+	struct en8811h_priv *priv = clk_hw_to_en8811h_priv(hw);
+	struct phy_device *phydev = priv->phydev;
+	u32 pbus_value;
+	int ret;
+
+	ret = air_buckpbus_reg_read(phydev, EN8811H_HWTRAP1, &pbus_value);
+	if (ret < 0)
+		return ret;
+
+	return (pbus_value & EN8811H_HWTRAP1_CKO) ? 50000000 : 25000000;
+}
+
+static int en8811h_clk_enable(struct clk_hw *hw)
+{
+	struct en8811h_priv *priv = clk_hw_to_en8811h_priv(hw);
+	struct phy_device *phydev = priv->phydev;
+
+	return air_buckpbus_reg_modify(phydev, EN8811H_CLK_CGM,
+				       EN8811H_CLK_CGM_CKO,
+				       EN8811H_CLK_CGM_CKO);
+}
+
+static void en8811h_clk_disable(struct clk_hw *hw)
+{
+	struct en8811h_priv *priv = clk_hw_to_en8811h_priv(hw);
+	struct phy_device *phydev = priv->phydev;
+
+	air_buckpbus_reg_modify(phydev, EN8811H_CLK_CGM,
+				EN8811H_CLK_CGM_CKO, 0);
+}
+
+static int en8811h_clk_is_enabled(struct clk_hw *hw)
+{
+	struct en8811h_priv *priv = clk_hw_to_en8811h_priv(hw);
+	struct phy_device *phydev = priv->phydev;
+	u32 pbus_value;
+	int ret;
+
+	ret = air_buckpbus_reg_read(phydev, EN8811H_CLK_CGM, &pbus_value);
+	if (ret < 0)
+		return ret;
+
+	return (pbus_value & EN8811H_CLK_CGM_CKO);
+}
+
+static const struct clk_ops en8811h_clk_ops = {
+	.recalc_rate	= en8811h_clk_recalc_rate,
+	.enable		= en8811h_clk_enable,
+	.disable	= en8811h_clk_disable,
+	.is_enabled	= en8811h_clk_is_enabled,
+};
+
+static int en8811h_clk_provider_setup(struct device *dev, struct clk_hw *hw)
+{
+	struct clk_init_data init;
+	int ret;
+
+	if (!IS_ENABLED(CONFIG_COMMON_CLK))
+		return 0;
+
+	init.name = devm_kasprintf(dev, GFP_KERNEL, "%s-cko",
+				   fwnode_get_name(dev_fwnode(dev)));
+	if (!init.name)
+		return -ENOMEM;
+
+	init.ops = &en8811h_clk_ops;
+	init.flags = 0;
+	init.num_parents = 0;
+	hw->init = &init;
+
+	ret = devm_clk_hw_register(dev, hw);
+	if (ret)
+		return ret;
+
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, hw);
+}
+
 static int en8811h_probe(struct phy_device *phydev)
 {
 	struct en8811h_priv *priv;
@@ -838,6 +929,12 @@ static int en8811h_probe(struct phy_device *phydev)
 		return ret;
 	}
 
+	priv->phydev = phydev;
+	/* Co-Clock Output */
+	ret = en8811h_clk_provider_setup(&phydev->mdio.dev, &priv->hw);
+	if (ret)
+		return ret;
+
 	/* Configure led gpio pins as output */
 	ret = air_buckpbus_reg_modify(phydev, EN8811H_GPIO_OUTPUT,
 				      EN8811H_GPIO_OUTPUT_345,
diff --git a/drivers/net/phy/aquantia/aquantia_main.c b/drivers/net/phy/aquantia/aquantia_main.c
index 08b1c9cc902b..77a48635d7bf 100644
--- a/drivers/net/phy/aquantia/aquantia_main.c
+++ b/drivers/net/phy/aquantia/aquantia_main.c
@@ -516,8 +516,7 @@ static int aqr105_read_status(struct phy_device *phydev)
 	if (!phydev->link || phydev->autoneg == AUTONEG_DISABLE)
 		return 0;
 
-	/**
-	 * The status register is not immediately correct on line side link up.
+	/* The status register is not immediately correct on line side link up.
 	 * Poll periodically until it reflects the correct ON state.
 	 * Only return fail for read error, timeout defaults to OFF state.
 	 */
@@ -634,8 +633,7 @@ static int aqr107_read_status(struct phy_device *phydev)
 	if (!phydev->link || phydev->autoneg == AUTONEG_DISABLE)
 		return 0;
 
-	/**
-	 * The status register is not immediately correct on line side link up.
+	/* The status register is not immediately correct on line side link up.
 	 * Poll periodically until it reflects the correct ON state.
 	 * Only return fail for read error, timeout defaults to OFF state.
 	 */
diff --git a/drivers/net/phy/as21xxx.c b/drivers/net/phy/as21xxx.c
new file mode 100644
index 000000000000..92697f43087d
--- /dev/null
+++ b/drivers/net/phy/as21xxx.c
@@ -0,0 +1,1087 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Aeonsemi AS21XXxX PHY Driver
+ *
+ * Author: Christian Marangi <ansuelsmth@gmail.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/firmware.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/phy.h>
+
+#define VEND1_GLB_REG_CPU_RESET_ADDR_LO_BASEADDR 0x3
+#define VEND1_GLB_REG_CPU_RESET_ADDR_HI_BASEADDR 0x4
+
+#define VEND1_GLB_REG_CPU_CTRL		0xe
+#define   VEND1_GLB_CPU_CTRL_MASK	GENMASK(4, 0)
+#define   VEND1_GLB_CPU_CTRL_LED_POLARITY_MASK GENMASK(12, 8)
+#define   VEND1_GLB_CPU_CTRL_LED_POLARITY(_n) FIELD_PREP(VEND1_GLB_CPU_CTRL_LED_POLARITY_MASK, \
+							 BIT(_n))
+
+#define VEND1_FW_START_ADDR		0x100
+
+#define VEND1_GLB_REG_MDIO_INDIRECT_ADDRCMD 0x101
+#define VEND1_GLB_REG_MDIO_INDIRECT_LOAD 0x102
+
+#define VEND1_GLB_REG_MDIO_INDIRECT_STATUS 0x103
+
+#define VEND1_PTP_CLK			0x142
+#define   VEND1_PTP_CLK_EN		BIT(6)
+
+/* 5 LED at step of 0x20
+ * FE: Fast-Ethernet (10/100)
+ * GE: Gigabit-Ethernet (1000)
+ * NG: New-Generation (2500/5000/10000)
+ */
+#define VEND1_LED_REG(_n)		(0x1800 + ((_n) * 0x10))
+#define   VEND1_LED_REG_A_EVENT		GENMASK(15, 11)
+#define VEND1_LED_CONF			0x1881
+#define   VEND1_LED_CONFG_BLINK		GENMASK(7, 0)
+
+#define VEND1_SPEED_STATUS		0x4002
+#define   VEND1_SPEED_MASK		GENMASK(7, 0)
+#define   VEND1_SPEED_10000		FIELD_PREP_CONST(VEND1_SPEED_MASK, 0x3)
+#define   VEND1_SPEED_5000		FIELD_PREP_CONST(VEND1_SPEED_MASK, 0x5)
+#define   VEND1_SPEED_2500		FIELD_PREP_CONST(VEND1_SPEED_MASK, 0x9)
+#define   VEND1_SPEED_1000		FIELD_PREP_CONST(VEND1_SPEED_MASK, 0x10)
+#define   VEND1_SPEED_100		FIELD_PREP_CONST(VEND1_SPEED_MASK, 0x20)
+#define   VEND1_SPEED_10		FIELD_PREP_CONST(VEND1_SPEED_MASK, 0x0)
+
+#define VEND1_IPC_CMD			0x5801
+#define   AEON_IPC_CMD_PARITY		BIT(15)
+#define   AEON_IPC_CMD_SIZE		GENMASK(10, 6)
+#define   AEON_IPC_CMD_OPCODE		GENMASK(5, 0)
+
+#define IPC_CMD_NOOP			0x0  /* Do nothing */
+#define IPC_CMD_INFO			0x1  /* Get Firmware Version */
+#define IPC_CMD_SYS_CPU			0x2  /* SYS_CPU */
+#define IPC_CMD_BULK_DATA		0xa  /* Pass bulk data in ipc registers. */
+#define IPC_CMD_BULK_WRITE		0xc  /* Write bulk data to memory */
+#define IPC_CMD_CFG_PARAM		0x1a /* Write config parameters to memory */
+#define IPC_CMD_NG_TESTMODE		0x1b /* Set NG test mode and tone */
+#define IPC_CMD_TEMP_MON		0x15 /* Temperature monitoring function */
+#define IPC_CMD_SET_LED			0x23 /* Set led */
+
+#define VEND1_IPC_STS			0x5802
+#define   AEON_IPC_STS_PARITY		BIT(15)
+#define   AEON_IPC_STS_SIZE		GENMASK(14, 10)
+#define   AEON_IPC_STS_OPCODE		GENMASK(9, 4)
+#define   AEON_IPC_STS_STATUS		GENMASK(3, 0)
+#define   AEON_IPC_STS_STATUS_RCVD	FIELD_PREP_CONST(AEON_IPC_STS_STATUS, 0x1)
+#define   AEON_IPC_STS_STATUS_PROCESS	FIELD_PREP_CONST(AEON_IPC_STS_STATUS, 0x2)
+#define   AEON_IPC_STS_STATUS_SUCCESS	FIELD_PREP_CONST(AEON_IPC_STS_STATUS, 0x4)
+#define   AEON_IPC_STS_STATUS_ERROR	FIELD_PREP_CONST(AEON_IPC_STS_STATUS, 0x8)
+#define   AEON_IPC_STS_STATUS_BUSY	FIELD_PREP_CONST(AEON_IPC_STS_STATUS, 0xe)
+#define   AEON_IPC_STS_STATUS_READY	FIELD_PREP_CONST(AEON_IPC_STS_STATUS, 0xf)
+
+#define VEND1_IPC_DATA0			0x5808
+#define VEND1_IPC_DATA1			0x5809
+#define VEND1_IPC_DATA2			0x580a
+#define VEND1_IPC_DATA3			0x580b
+#define VEND1_IPC_DATA4			0x580c
+#define VEND1_IPC_DATA5			0x580d
+#define VEND1_IPC_DATA6			0x580e
+#define VEND1_IPC_DATA7			0x580f
+#define VEND1_IPC_DATA(_n)		(VEND1_IPC_DATA0 + (_n))
+
+/* Sub command of CMD_INFO */
+#define IPC_INFO_VERSION		0x1
+
+/* Sub command of CMD_SYS_CPU */
+#define IPC_SYS_CPU_REBOOT		0x3
+#define IPC_SYS_CPU_IMAGE_OFST		0x4
+#define IPC_SYS_CPU_IMAGE_CHECK		0x5
+#define IPC_SYS_CPU_PHY_ENABLE		0x6
+
+/* Sub command of CMD_CFG_PARAM */
+#define IPC_CFG_PARAM_DIRECT		0x4
+
+/* CFG DIRECT sub command */
+#define IPC_CFG_PARAM_DIRECT_NG_PHYCTRL	0x1
+#define IPC_CFG_PARAM_DIRECT_CU_AN	0x2
+#define IPC_CFG_PARAM_DIRECT_SDS_PCS	0x3
+#define IPC_CFG_PARAM_DIRECT_AUTO_EEE	0x4
+#define IPC_CFG_PARAM_DIRECT_SDS_PMA	0x5
+#define IPC_CFG_PARAM_DIRECT_DPC_RA	0x6
+#define IPC_CFG_PARAM_DIRECT_DPC_PKT_CHK 0x7
+#define IPC_CFG_PARAM_DIRECT_DPC_SDS_WAIT_ETH 0x8
+#define IPC_CFG_PARAM_DIRECT_WDT	0x9
+#define IPC_CFG_PARAM_DIRECT_SDS_RESTART_AN 0x10
+#define IPC_CFG_PARAM_DIRECT_TEMP_MON	0x11
+#define IPC_CFG_PARAM_DIRECT_WOL	0x12
+
+/* Sub command of CMD_TEMP_MON */
+#define IPC_CMD_TEMP_MON_GET		0x4
+
+#define AS21XXX_MDIO_AN_C22		0xffe0
+
+#define PHY_ID_AS21XXX			0x75009410
+/* AS21xxx ID Legend
+ * AS21x1xxB1
+ *     ^ ^^
+ *     | |J: Supports SyncE/PTP
+ *     | |P: No SyncE/PTP support
+ *     | 1: Supports 2nd Serdes
+ *     | 2: Not 2nd Serdes support
+ *     0: 10G, 5G, 2.5G
+ *     5: 5G, 2.5G
+ *     2: 2.5G
+ */
+#define PHY_ID_AS21011JB1		0x75009402
+#define PHY_ID_AS21011PB1		0x75009412
+#define PHY_ID_AS21010JB1		0x75009422
+#define PHY_ID_AS21010PB1		0x75009432
+#define PHY_ID_AS21511JB1		0x75009442
+#define PHY_ID_AS21511PB1		0x75009452
+#define PHY_ID_AS21510JB1		0x75009462
+#define PHY_ID_AS21510PB1		0x75009472
+#define PHY_ID_AS21210JB1		0x75009482
+#define PHY_ID_AS21210PB1		0x75009492
+#define PHY_VENDOR_AEONSEMI		0x75009400
+
+#define AEON_MAX_LEDS			5
+#define AEON_IPC_DELAY			10000
+#define AEON_IPC_TIMEOUT		(AEON_IPC_DELAY * 100)
+#define AEON_IPC_DATA_NUM_REGISTERS	8
+#define AEON_IPC_DATA_MAX		(AEON_IPC_DATA_NUM_REGISTERS * sizeof(u16))
+
+#define AEON_BOOT_ADDR			0x1000
+#define AEON_CPU_BOOT_ADDR		0x2000
+#define AEON_CPU_CTRL_FW_LOAD		(BIT(4) | BIT(2) | BIT(1) | BIT(0))
+#define AEON_CPU_CTRL_FW_START		BIT(0)
+
+enum as21xxx_led_event {
+	VEND1_LED_REG_A_EVENT_ON_10 = 0x0,
+	VEND1_LED_REG_A_EVENT_ON_100,
+	VEND1_LED_REG_A_EVENT_ON_1000,
+	VEND1_LED_REG_A_EVENT_ON_2500,
+	VEND1_LED_REG_A_EVENT_ON_5000,
+	VEND1_LED_REG_A_EVENT_ON_10000,
+	VEND1_LED_REG_A_EVENT_ON_FE_GE,
+	VEND1_LED_REG_A_EVENT_ON_NG,
+	VEND1_LED_REG_A_EVENT_ON_FULL_DUPLEX,
+	VEND1_LED_REG_A_EVENT_ON_COLLISION,
+	VEND1_LED_REG_A_EVENT_BLINK_TX,
+	VEND1_LED_REG_A_EVENT_BLINK_RX,
+	VEND1_LED_REG_A_EVENT_BLINK_ACT,
+	VEND1_LED_REG_A_EVENT_ON_LINK,
+	VEND1_LED_REG_A_EVENT_ON_LINK_BLINK_ACT,
+	VEND1_LED_REG_A_EVENT_ON_LINK_BLINK_RX,
+	VEND1_LED_REG_A_EVENT_ON_FE_GE_BLINK_ACT,
+	VEND1_LED_REG_A_EVENT_ON_NG_BLINK_ACT,
+	VEND1_LED_REG_A_EVENT_ON_NG_BLINK_FE_GE,
+	VEND1_LED_REG_A_EVENT_ON_FD_BLINK_COLLISION,
+	VEND1_LED_REG_A_EVENT_ON,
+	VEND1_LED_REG_A_EVENT_OFF,
+};
+
+struct as21xxx_led_pattern_info {
+	unsigned int pattern;
+	u16 val;
+};
+
+struct as21xxx_priv {
+	bool parity_status;
+	/* Protect concurrent IPC access */
+	struct mutex ipc_lock;
+};
+
+static struct as21xxx_led_pattern_info as21xxx_led_supported_pattern[] = {
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_10),
+		.val = VEND1_LED_REG_A_EVENT_ON_10
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_100),
+		.val = VEND1_LED_REG_A_EVENT_ON_100
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_1000),
+		.val = VEND1_LED_REG_A_EVENT_ON_1000
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_2500),
+		.val = VEND1_LED_REG_A_EVENT_ON_2500
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_5000),
+		.val = VEND1_LED_REG_A_EVENT_ON_5000
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_10000),
+		.val = VEND1_LED_REG_A_EVENT_ON_10000
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK),
+		.val = VEND1_LED_REG_A_EVENT_ON_LINK
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_10) |
+			   BIT(TRIGGER_NETDEV_LINK_100) |
+			   BIT(TRIGGER_NETDEV_LINK_1000),
+		.val = VEND1_LED_REG_A_EVENT_ON_FE_GE
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_2500) |
+			   BIT(TRIGGER_NETDEV_LINK_5000) |
+			   BIT(TRIGGER_NETDEV_LINK_10000),
+		.val = VEND1_LED_REG_A_EVENT_ON_NG
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_FULL_DUPLEX),
+		.val = VEND1_LED_REG_A_EVENT_ON_FULL_DUPLEX
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_TX),
+		.val = VEND1_LED_REG_A_EVENT_BLINK_TX
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_RX),
+		.val = VEND1_LED_REG_A_EVENT_BLINK_RX
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_TX) |
+			   BIT(TRIGGER_NETDEV_RX),
+		.val = VEND1_LED_REG_A_EVENT_BLINK_ACT
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_10) |
+			   BIT(TRIGGER_NETDEV_LINK_100) |
+			   BIT(TRIGGER_NETDEV_LINK_1000) |
+			   BIT(TRIGGER_NETDEV_LINK_2500) |
+			   BIT(TRIGGER_NETDEV_LINK_5000) |
+			   BIT(TRIGGER_NETDEV_LINK_10000),
+		.val = VEND1_LED_REG_A_EVENT_ON_LINK
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_10) |
+			   BIT(TRIGGER_NETDEV_LINK_100) |
+			   BIT(TRIGGER_NETDEV_LINK_1000) |
+			   BIT(TRIGGER_NETDEV_LINK_2500) |
+			   BIT(TRIGGER_NETDEV_LINK_5000) |
+			   BIT(TRIGGER_NETDEV_LINK_10000) |
+			   BIT(TRIGGER_NETDEV_TX) |
+			   BIT(TRIGGER_NETDEV_RX),
+		.val = VEND1_LED_REG_A_EVENT_ON_LINK_BLINK_ACT
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_10) |
+			   BIT(TRIGGER_NETDEV_LINK_100) |
+			   BIT(TRIGGER_NETDEV_LINK_1000) |
+			   BIT(TRIGGER_NETDEV_LINK_2500) |
+			   BIT(TRIGGER_NETDEV_LINK_5000) |
+			   BIT(TRIGGER_NETDEV_LINK_10000) |
+			   BIT(TRIGGER_NETDEV_RX),
+		.val = VEND1_LED_REG_A_EVENT_ON_LINK_BLINK_RX
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_10) |
+			   BIT(TRIGGER_NETDEV_LINK_100) |
+			   BIT(TRIGGER_NETDEV_LINK_1000) |
+			   BIT(TRIGGER_NETDEV_TX) |
+			   BIT(TRIGGER_NETDEV_RX),
+		.val = VEND1_LED_REG_A_EVENT_ON_FE_GE_BLINK_ACT
+	},
+	{
+		.pattern = BIT(TRIGGER_NETDEV_LINK_2500) |
+			   BIT(TRIGGER_NETDEV_LINK_5000) |
+			   BIT(TRIGGER_NETDEV_LINK_10000) |
+			   BIT(TRIGGER_NETDEV_TX) |
+			   BIT(TRIGGER_NETDEV_RX),
+		.val = VEND1_LED_REG_A_EVENT_ON_NG_BLINK_ACT
+	}
+};
+
+static int aeon_firmware_boot(struct phy_device *phydev, const u8 *data,
+			      size_t size)
+{
+	int i, ret;
+	u16 val;
+
+	ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLB_REG_CPU_CTRL,
+			     VEND1_GLB_CPU_CTRL_MASK, AEON_CPU_CTRL_FW_LOAD);
+	if (ret)
+		return ret;
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_FW_START_ADDR,
+			    AEON_BOOT_ADDR);
+	if (ret)
+		return ret;
+
+	ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1,
+			     VEND1_GLB_REG_MDIO_INDIRECT_ADDRCMD,
+			     0x3ffc, 0xc000);
+	if (ret)
+		return ret;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+			   VEND1_GLB_REG_MDIO_INDIRECT_STATUS);
+	if (val > 1) {
+		phydev_err(phydev, "wrong origin mdio_indirect_status: %x\n", val);
+		return -EINVAL;
+	}
+
+	/* Firmware is always aligned to u16 */
+	for (i = 0; i < size; i += 2) {
+		val = data[i + 1] << 8 | data[i];
+
+		ret = phy_write_mmd(phydev, MDIO_MMD_VEND1,
+				    VEND1_GLB_REG_MDIO_INDIRECT_LOAD, val);
+		if (ret)
+			return ret;
+	}
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND1,
+			    VEND1_GLB_REG_CPU_RESET_ADDR_LO_BASEADDR,
+			    lower_16_bits(AEON_CPU_BOOT_ADDR));
+	if (ret)
+		return ret;
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND1,
+			    VEND1_GLB_REG_CPU_RESET_ADDR_HI_BASEADDR,
+			    upper_16_bits(AEON_CPU_BOOT_ADDR));
+	if (ret)
+		return ret;
+
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLB_REG_CPU_CTRL,
+			      VEND1_GLB_CPU_CTRL_MASK, AEON_CPU_CTRL_FW_START);
+}
+
+static int aeon_firmware_load(struct phy_device *phydev)
+{
+	struct device *dev = &phydev->mdio.dev;
+	const struct firmware *fw;
+	const char *fw_name;
+	int ret;
+
+	ret = of_property_read_string(dev->of_node, "firmware-name",
+				      &fw_name);
+	if (ret)
+		return ret;
+
+	ret = request_firmware(&fw, fw_name, dev);
+	if (ret) {
+		phydev_err(phydev, "failed to find FW file %s (%d)\n",
+			   fw_name, ret);
+		return ret;
+	}
+
+	ret = aeon_firmware_boot(phydev, fw->data, fw->size);
+
+	release_firmware(fw);
+
+	return ret;
+}
+
+static bool aeon_ipc_ready(u16 val, bool parity_status)
+{
+	u16 status;
+
+	if (FIELD_GET(AEON_IPC_STS_PARITY, val) != parity_status)
+		return false;
+
+	status = val & AEON_IPC_STS_STATUS;
+
+	return status != AEON_IPC_STS_STATUS_RCVD &&
+	       status != AEON_IPC_STS_STATUS_PROCESS &&
+	       status != AEON_IPC_STS_STATUS_BUSY;
+}
+
+static int aeon_ipc_wait_cmd(struct phy_device *phydev, bool parity_status)
+{
+	u16 val;
+
+	/* Exit condition logic:
+	 * - Wait for parity bit equal
+	 * - Wait for status success, error OR ready
+	 */
+	return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, VEND1_IPC_STS, val,
+					 aeon_ipc_ready(val, parity_status),
+					 AEON_IPC_DELAY, AEON_IPC_TIMEOUT, false);
+}
+
+static int aeon_ipc_send_cmd(struct phy_device *phydev,
+			     struct as21xxx_priv *priv,
+			     u16 cmd, u16 *ret_sts)
+{
+	bool curr_parity;
+	int ret;
+
+	/* The IPC sync by using a single parity bit.
+	 * Each CMD have alternately this bit set or clear
+	 * to understand correct flow and packet order.
+	 */
+	curr_parity = priv->parity_status;
+	if (priv->parity_status)
+		cmd |= AEON_IPC_CMD_PARITY;
+
+	/* Always update parity for next packet */
+	priv->parity_status = !priv->parity_status;
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_IPC_CMD, cmd);
+	if (ret)
+		return ret;
+
+	/* Wait for packet to be processed */
+	usleep_range(AEON_IPC_DELAY, AEON_IPC_DELAY + 5000);
+
+	/* With no ret_sts, ignore waiting for packet completion
+	 * (ipc parity bit sync)
+	 */
+	if (!ret_sts)
+		return 0;
+
+	ret = aeon_ipc_wait_cmd(phydev, curr_parity);
+	if (ret)
+		return ret;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_IPC_STS);
+	if (ret < 0)
+		return ret;
+
+	*ret_sts = ret;
+	if ((*ret_sts & AEON_IPC_STS_STATUS) != AEON_IPC_STS_STATUS_SUCCESS)
+		return -EINVAL;
+
+	return 0;
+}
+
+/* If data is NULL, return 0 or negative error.
+ * If data not NULL, return number of Bytes received from IPC or
+ * a negative error.
+ */
+static int aeon_ipc_send_msg(struct phy_device *phydev,
+			     u16 opcode, u16 *data, unsigned int data_len,
+			     u16 *ret_data)
+{
+	struct as21xxx_priv *priv = phydev->priv;
+	unsigned int ret_size;
+	u16 cmd, ret_sts;
+	int ret;
+	int i;
+
+	/* IPC have a max of 8 register to transfer data,
+	 * make sure we never exceed this.
+	 */
+	if (data_len > AEON_IPC_DATA_MAX)
+		return -EINVAL;
+
+	for (i = 0; i < data_len / sizeof(u16); i++)
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_IPC_DATA(i),
+			      data[i]);
+
+	cmd = FIELD_PREP(AEON_IPC_CMD_SIZE, data_len) |
+	      FIELD_PREP(AEON_IPC_CMD_OPCODE, opcode);
+
+	mutex_lock(&priv->ipc_lock);
+
+	ret = aeon_ipc_send_cmd(phydev, priv, cmd, &ret_sts);
+	if (ret) {
+		phydev_err(phydev, "failed to send ipc msg for %x: %d\n",
+			   opcode, ret);
+		goto out;
+	}
+
+	if (!data)
+		goto out;
+
+	if ((ret_sts & AEON_IPC_STS_STATUS) == AEON_IPC_STS_STATUS_ERROR) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* Prevent IPC from stack smashing the kernel.
+	 * We can't trust IPC to return a good value and we always
+	 * preallocate space for 16 Bytes.
+	 */
+	ret_size = FIELD_GET(AEON_IPC_STS_SIZE, ret_sts);
+	if (ret_size > AEON_IPC_DATA_MAX) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* Read data from IPC data register for ret_size value from IPC */
+	for (i = 0; i < DIV_ROUND_UP(ret_size, sizeof(u16)); i++) {
+		ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_IPC_DATA(i));
+		if (ret < 0)
+			goto out;
+
+		ret_data[i] = ret;
+	}
+
+	ret = ret_size;
+
+out:
+	mutex_unlock(&priv->ipc_lock);
+
+	return ret;
+}
+
+static int aeon_ipc_noop(struct phy_device *phydev,
+			 struct as21xxx_priv *priv, u16 *ret_sts)
+{
+	u16 cmd;
+
+	cmd = FIELD_PREP(AEON_IPC_CMD_SIZE, 0) |
+	      FIELD_PREP(AEON_IPC_CMD_OPCODE, IPC_CMD_NOOP);
+
+	return aeon_ipc_send_cmd(phydev, priv, cmd, ret_sts);
+}
+
+/* Logic to sync parity bit with IPC.
+ * We send 2 NOP cmd with same partity and we wait for IPC
+ * to handle the packet only for the second one. This way
+ * we make sure we are sync for every next cmd.
+ */
+static int aeon_ipc_sync_parity(struct phy_device *phydev,
+				struct as21xxx_priv *priv)
+{
+	u16 ret_sts;
+	int ret;
+
+	mutex_lock(&priv->ipc_lock);
+
+	/* Send NOP with no parity */
+	aeon_ipc_noop(phydev, priv, NULL);
+
+	/* Reset packet parity */
+	priv->parity_status = false;
+
+	/* Send second NOP with no parity */
+	ret = aeon_ipc_noop(phydev, priv, &ret_sts);
+
+	mutex_unlock(&priv->ipc_lock);
+
+	/* We expect to return -EINVAL */
+	if (ret != -EINVAL)
+		return ret;
+
+	if ((ret_sts & AEON_IPC_STS_STATUS) != AEON_IPC_STS_STATUS_READY) {
+		phydev_err(phydev, "Invalid IPC status on sync parity: %x\n",
+			   ret_sts);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int aeon_ipc_get_fw_version(struct phy_device *phydev)
+{
+	u16 ret_data[AEON_IPC_DATA_NUM_REGISTERS], data[1];
+	char fw_version[AEON_IPC_DATA_MAX + 1];
+	int ret;
+
+	data[0] = IPC_INFO_VERSION;
+
+	ret = aeon_ipc_send_msg(phydev, IPC_CMD_INFO, data,
+				sizeof(data), ret_data);
+	if (ret < 0)
+		return ret;
+
+	/* Make sure FW version is NULL terminated */
+	memcpy(fw_version, ret_data, ret);
+	fw_version[ret] = '\0';
+
+	phydev_info(phydev, "Firmware Version: %s\n", fw_version);
+
+	return 0;
+}
+
+static int aeon_dpc_ra_enable(struct phy_device *phydev)
+{
+	u16 data[2];
+
+	data[0] = IPC_CFG_PARAM_DIRECT;
+	data[1] = IPC_CFG_PARAM_DIRECT_DPC_RA;
+
+	return aeon_ipc_send_msg(phydev, IPC_CMD_CFG_PARAM, data,
+				 sizeof(data), NULL);
+}
+
+static int as21xxx_probe(struct phy_device *phydev)
+{
+	struct as21xxx_priv *priv;
+	int ret;
+
+	priv = devm_kzalloc(&phydev->mdio.dev,
+			    sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	phydev->priv = priv;
+
+	ret = devm_mutex_init(&phydev->mdio.dev,
+			      &priv->ipc_lock);
+	if (ret)
+		return ret;
+
+	ret = aeon_ipc_sync_parity(phydev, priv);
+	if (ret)
+		return ret;
+
+	ret = aeon_ipc_get_fw_version(phydev);
+	if (ret)
+		return ret;
+
+	/* Enable PTP clk if not already Enabled */
+	ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PTP_CLK,
+			       VEND1_PTP_CLK_EN);
+	if (ret)
+		return ret;
+
+	return aeon_dpc_ra_enable(phydev);
+}
+
+static int as21xxx_read_link(struct phy_device *phydev, int *bmcr)
+{
+	int status;
+
+	/* Normal C22 BMCR report inconsistent data, use
+	 * the mapped C22 in C45 to have more consistent link info.
+	 */
+	*bmcr = phy_read_mmd(phydev, MDIO_MMD_AN,
+			     AS21XXX_MDIO_AN_C22 + MII_BMCR);
+	if (*bmcr < 0)
+		return *bmcr;
+
+	/* Autoneg is being started, therefore disregard current
+	 * link status and report link as down.
+	 */
+	if (*bmcr & BMCR_ANRESTART) {
+		phydev->link = 0;
+		return 0;
+	}
+
+	status = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1);
+	if (status < 0)
+		return status;
+
+	phydev->link = !!(status & MDIO_STAT1_LSTATUS);
+
+	return 0;
+}
+
+static int as21xxx_read_c22_lpa(struct phy_device *phydev)
+{
+	int lpagb;
+
+	/* MII_STAT1000 are only filled in the mapped C22
+	 * in C45, use that to fill lpagb values and check.
+	 */
+	lpagb = phy_read_mmd(phydev, MDIO_MMD_AN,
+			     AS21XXX_MDIO_AN_C22 + MII_STAT1000);
+	if (lpagb < 0)
+		return lpagb;
+
+	if (lpagb & LPA_1000MSFAIL) {
+		int adv = phy_read_mmd(phydev, MDIO_MMD_AN,
+				       AS21XXX_MDIO_AN_C22 + MII_CTRL1000);
+
+		if (adv < 0)
+			return adv;
+
+		if (adv & CTL1000_ENABLE_MASTER)
+			phydev_err(phydev, "Master/Slave resolution failed, maybe conflicting manual settings?\n");
+		else
+			phydev_err(phydev, "Master/Slave resolution failed\n");
+		return -ENOLINK;
+	}
+
+	mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising,
+					lpagb);
+
+	return 0;
+}
+
+static int as21xxx_read_status(struct phy_device *phydev)
+{
+	int bmcr, old_link = phydev->link;
+	int ret;
+
+	ret = as21xxx_read_link(phydev, &bmcr);
+	if (ret)
+		return ret;
+
+	/* why bother the PHY if nothing can have changed */
+	if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link)
+		return 0;
+
+	phydev->speed = SPEED_UNKNOWN;
+	phydev->duplex = DUPLEX_UNKNOWN;
+	phydev->pause = 0;
+	phydev->asym_pause = 0;
+
+	if (phydev->autoneg == AUTONEG_ENABLE) {
+		ret = genphy_c45_read_lpa(phydev);
+		if (ret)
+			return ret;
+
+		ret = as21xxx_read_c22_lpa(phydev);
+		if (ret)
+			return ret;
+
+		phy_resolve_aneg_linkmode(phydev);
+	} else {
+		int speed;
+
+		linkmode_zero(phydev->lp_advertising);
+
+		speed = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				     VEND1_SPEED_STATUS);
+		if (speed < 0)
+			return speed;
+
+		switch (speed & VEND1_SPEED_STATUS) {
+		case VEND1_SPEED_10000:
+			phydev->speed = SPEED_10000;
+			phydev->duplex = DUPLEX_FULL;
+			break;
+		case VEND1_SPEED_5000:
+			phydev->speed = SPEED_5000;
+			phydev->duplex = DUPLEX_FULL;
+			break;
+		case VEND1_SPEED_2500:
+			phydev->speed = SPEED_2500;
+			phydev->duplex = DUPLEX_FULL;
+			break;
+		case VEND1_SPEED_1000:
+			phydev->speed = SPEED_1000;
+			if (bmcr & BMCR_FULLDPLX)
+				phydev->duplex = DUPLEX_FULL;
+			else
+				phydev->duplex = DUPLEX_HALF;
+			break;
+		case VEND1_SPEED_100:
+			phydev->speed = SPEED_100;
+			phydev->duplex = DUPLEX_FULL;
+			break;
+		case VEND1_SPEED_10:
+			phydev->speed = SPEED_10;
+			phydev->duplex = DUPLEX_FULL;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int as21xxx_led_brightness_set(struct phy_device *phydev,
+				      u8 index, enum led_brightness value)
+{
+	u16 val = VEND1_LED_REG_A_EVENT_OFF;
+
+	if (index > AEON_MAX_LEDS)
+		return -EINVAL;
+
+	if (value)
+		val = VEND1_LED_REG_A_EVENT_ON;
+
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND1,
+			      VEND1_LED_REG(index),
+			      VEND1_LED_REG_A_EVENT,
+			      FIELD_PREP(VEND1_LED_REG_A_EVENT, val));
+}
+
+static int as21xxx_led_hw_is_supported(struct phy_device *phydev, u8 index,
+				       unsigned long rules)
+{
+	int i;
+
+	if (index > AEON_MAX_LEDS)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(as21xxx_led_supported_pattern); i++)
+		if (rules == as21xxx_led_supported_pattern[i].pattern)
+			return 0;
+
+	return -EOPNOTSUPP;
+}
+
+static int as21xxx_led_hw_control_get(struct phy_device *phydev, u8 index,
+				      unsigned long *rules)
+{
+	int i, val;
+
+	if (index > AEON_MAX_LEDS)
+		return -EINVAL;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_LED_REG(index));
+	if (val < 0)
+		return val;
+
+	val = FIELD_GET(VEND1_LED_REG_A_EVENT, val);
+	for (i = 0; i < ARRAY_SIZE(as21xxx_led_supported_pattern); i++)
+		if (val == as21xxx_led_supported_pattern[i].val) {
+			*rules = as21xxx_led_supported_pattern[i].pattern;
+			return 0;
+		}
+
+	/* Should be impossible */
+	return -EINVAL;
+}
+
+static int as21xxx_led_hw_control_set(struct phy_device *phydev, u8 index,
+				      unsigned long rules)
+{
+	u16 val = 0;
+	int i;
+
+	if (index > AEON_MAX_LEDS)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(as21xxx_led_supported_pattern); i++)
+		if (rules == as21xxx_led_supported_pattern[i].pattern) {
+			val = as21xxx_led_supported_pattern[i].val;
+			break;
+		}
+
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND1,
+			      VEND1_LED_REG(index),
+			      VEND1_LED_REG_A_EVENT,
+			      FIELD_PREP(VEND1_LED_REG_A_EVENT, val));
+}
+
+static int as21xxx_led_polarity_set(struct phy_device *phydev, int index,
+				    unsigned long modes)
+{
+	bool led_active_low = false;
+	u16 mask, val = 0;
+	u32 mode;
+
+	if (index > AEON_MAX_LEDS)
+		return -EINVAL;
+
+	for_each_set_bit(mode, &modes, __PHY_LED_MODES_NUM) {
+		switch (mode) {
+		case PHY_LED_ACTIVE_LOW:
+			led_active_low = true;
+			break;
+		case PHY_LED_ACTIVE_HIGH: /* default mode */
+			led_active_low = false;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	mask = VEND1_GLB_CPU_CTRL_LED_POLARITY(index);
+	if (led_active_low)
+		val = VEND1_GLB_CPU_CTRL_LED_POLARITY(index);
+
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND1,
+			      VEND1_GLB_REG_CPU_CTRL,
+			      mask, val);
+}
+
+static int as21xxx_match_phy_device(struct phy_device *phydev,
+				    const struct phy_driver *phydrv)
+{
+	struct as21xxx_priv *priv;
+	u16 ret_sts;
+	u32 phy_id;
+	int ret;
+
+	/* Skip PHY that are not AS21xxx or already have firmware loaded */
+	if (phydev->c45_ids.device_ids[MDIO_MMD_PCS] != PHY_ID_AS21XXX)
+		return genphy_match_phy_device(phydev, phydrv);
+
+	/* Read PHY ID to handle firmware just loaded */
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MII_PHYSID1);
+	if (ret < 0)
+		return ret;
+	phy_id = ret << 16;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MII_PHYSID2);
+	if (ret < 0)
+		return ret;
+	phy_id |= ret;
+
+	/* With PHY ID not the generic AS21xxx one assume
+	 * the firmware just loaded
+	 */
+	if (phy_id != PHY_ID_AS21XXX)
+		return phy_id == phydrv->phy_id;
+
+	/* Allocate temp priv and load the firmware */
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	mutex_init(&priv->ipc_lock);
+
+	ret = aeon_firmware_load(phydev);
+	if (ret)
+		goto out;
+
+	/* Sync parity... */
+	ret = aeon_ipc_sync_parity(phydev, priv);
+	if (ret)
+		goto out;
+
+	/* ...and send a third NOOP cmd to wait for firmware finish loading */
+	ret = aeon_ipc_noop(phydev, priv, &ret_sts);
+	if (ret)
+		goto out;
+
+out:
+	mutex_destroy(&priv->ipc_lock);
+	kfree(priv);
+
+	/* Return can either be 0 or a negative error code.
+	 * Returning 0 here means THIS is NOT a suitable PHY.
+	 *
+	 * For the specific case of the generic Aeonsemi PHY ID that
+	 * needs the firmware the be loaded first to have a correct PHY ID,
+	 * this is OK as a matching PHY ID will be found right after.
+	 * This relies on the driver probe order where the first PHY driver
+	 * probed is the generic one.
+	 */
+	return ret;
+}
+
+static struct phy_driver as21xxx_drivers[] = {
+	{
+		/* PHY expose in C45 as 0x7500 0x9410
+		 * before firmware is loaded.
+		 * This driver entry must be attempted first to load
+		 * the firmware and thus update the ID registers.
+		 */
+		PHY_ID_MATCH_EXACT(PHY_ID_AS21XXX),
+		.name		= "Aeonsemi AS21xxx",
+		.match_phy_device = as21xxx_match_phy_device,
+	},
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_AS21011JB1),
+		.name		= "Aeonsemi AS21011JB1",
+		.probe		= as21xxx_probe,
+		.match_phy_device = as21xxx_match_phy_device,
+		.read_status	= as21xxx_read_status,
+		.led_brightness_set = as21xxx_led_brightness_set,
+		.led_hw_is_supported = as21xxx_led_hw_is_supported,
+		.led_hw_control_set = as21xxx_led_hw_control_set,
+		.led_hw_control_get = as21xxx_led_hw_control_get,
+		.led_polarity_set = as21xxx_led_polarity_set,
+	},
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_AS21011PB1),
+		.name		= "Aeonsemi AS21011PB1",
+		.probe		= as21xxx_probe,
+		.match_phy_device = as21xxx_match_phy_device,
+		.read_status	= as21xxx_read_status,
+		.led_brightness_set = as21xxx_led_brightness_set,
+		.led_hw_is_supported = as21xxx_led_hw_is_supported,
+		.led_hw_control_set = as21xxx_led_hw_control_set,
+		.led_hw_control_get = as21xxx_led_hw_control_get,
+		.led_polarity_set = as21xxx_led_polarity_set,
+	},
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_AS21010PB1),
+		.name		= "Aeonsemi AS21010PB1",
+		.probe		= as21xxx_probe,
+		.match_phy_device = as21xxx_match_phy_device,
+		.read_status	= as21xxx_read_status,
+		.led_brightness_set = as21xxx_led_brightness_set,
+		.led_hw_is_supported = as21xxx_led_hw_is_supported,
+		.led_hw_control_set = as21xxx_led_hw_control_set,
+		.led_hw_control_get = as21xxx_led_hw_control_get,
+		.led_polarity_set = as21xxx_led_polarity_set,
+	},
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_AS21010JB1),
+		.name		= "Aeonsemi AS21010JB1",
+		.probe		= as21xxx_probe,
+		.match_phy_device = as21xxx_match_phy_device,
+		.read_status	= as21xxx_read_status,
+		.led_brightness_set = as21xxx_led_brightness_set,
+		.led_hw_is_supported = as21xxx_led_hw_is_supported,
+		.led_hw_control_set = as21xxx_led_hw_control_set,
+		.led_hw_control_get = as21xxx_led_hw_control_get,
+		.led_polarity_set = as21xxx_led_polarity_set,
+	},
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_AS21210PB1),
+		.name		= "Aeonsemi AS21210PB1",
+		.probe		= as21xxx_probe,
+		.match_phy_device = as21xxx_match_phy_device,
+		.read_status	= as21xxx_read_status,
+		.led_brightness_set = as21xxx_led_brightness_set,
+		.led_hw_is_supported = as21xxx_led_hw_is_supported,
+		.led_hw_control_set = as21xxx_led_hw_control_set,
+		.led_hw_control_get = as21xxx_led_hw_control_get,
+		.led_polarity_set = as21xxx_led_polarity_set,
+	},
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_AS21510JB1),
+		.name		= "Aeonsemi AS21510JB1",
+		.probe		= as21xxx_probe,
+		.match_phy_device = as21xxx_match_phy_device,
+		.read_status	= as21xxx_read_status,
+		.led_brightness_set = as21xxx_led_brightness_set,
+		.led_hw_is_supported = as21xxx_led_hw_is_supported,
+		.led_hw_control_set = as21xxx_led_hw_control_set,
+		.led_hw_control_get = as21xxx_led_hw_control_get,
+		.led_polarity_set = as21xxx_led_polarity_set,
+	},
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_AS21510PB1),
+		.name		= "Aeonsemi AS21510PB1",
+		.probe		= as21xxx_probe,
+		.match_phy_device = as21xxx_match_phy_device,
+		.read_status	= as21xxx_read_status,
+		.led_brightness_set = as21xxx_led_brightness_set,
+		.led_hw_is_supported = as21xxx_led_hw_is_supported,
+		.led_hw_control_set = as21xxx_led_hw_control_set,
+		.led_hw_control_get = as21xxx_led_hw_control_get,
+		.led_polarity_set = as21xxx_led_polarity_set,
+	},
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_AS21511JB1),
+		.name		= "Aeonsemi AS21511JB1",
+		.probe		= as21xxx_probe,
+		.match_phy_device = as21xxx_match_phy_device,
+		.read_status	= as21xxx_read_status,
+		.led_brightness_set = as21xxx_led_brightness_set,
+		.led_hw_is_supported = as21xxx_led_hw_is_supported,
+		.led_hw_control_set = as21xxx_led_hw_control_set,
+		.led_hw_control_get = as21xxx_led_hw_control_get,
+		.led_polarity_set = as21xxx_led_polarity_set,
+	},
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_AS21210JB1),
+		.name		= "Aeonsemi AS21210JB1",
+		.probe		= as21xxx_probe,
+		.match_phy_device = as21xxx_match_phy_device,
+		.read_status	= as21xxx_read_status,
+		.led_brightness_set = as21xxx_led_brightness_set,
+		.led_hw_is_supported = as21xxx_led_hw_is_supported,
+		.led_hw_control_set = as21xxx_led_hw_control_set,
+		.led_hw_control_get = as21xxx_led_hw_control_get,
+		.led_polarity_set = as21xxx_led_polarity_set,
+	},
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_AS21511PB1),
+		.name		= "Aeonsemi AS21511PB1",
+		.probe		= as21xxx_probe,
+		.match_phy_device = as21xxx_match_phy_device,
+		.read_status	= as21xxx_read_status,
+		.led_brightness_set = as21xxx_led_brightness_set,
+		.led_hw_is_supported = as21xxx_led_hw_is_supported,
+		.led_hw_control_set = as21xxx_led_hw_control_set,
+		.led_hw_control_get = as21xxx_led_hw_control_get,
+		.led_polarity_set = as21xxx_led_polarity_set,
+	},
+};
+module_phy_driver(as21xxx_drivers);
+
+static struct mdio_device_id __maybe_unused as21xxx_tbl[] = {
+	{ PHY_ID_MATCH_VENDOR(PHY_VENDOR_AEONSEMI) },
+	{ }
+};
+MODULE_DEVICE_TABLE(mdio, as21xxx_tbl);
+
+MODULE_DESCRIPTION("Aeonsemi AS21xxx PHY driver");
+MODULE_AUTHOR("Christian Marangi <ansuelsmth@gmail.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c
index e81404bf8994..299f9a8f30f4 100644
--- a/drivers/net/phy/bcm87xx.c
+++ b/drivers/net/phy/bcm87xx.c
@@ -185,14 +185,10 @@ static irqreturn_t bcm87xx_handle_interrupt(struct phy_device *phydev)
 	return IRQ_HANDLED;
 }
 
-static int bcm8706_match_phy_device(struct phy_device *phydev)
+static int bcm87xx_match_phy_device(struct phy_device *phydev,
+				    const struct phy_driver *phydrv)
 {
-	return phydev->c45_ids.device_ids[4] == PHY_ID_BCM8706;
-}
-
-static int bcm8727_match_phy_device(struct phy_device *phydev)
-{
-	return phydev->c45_ids.device_ids[4] == PHY_ID_BCM8727;
+	return phydev->c45_ids.device_ids[4] == phydrv->phy_id;
 }
 
 static struct phy_driver bcm87xx_driver[] = {
@@ -206,7 +202,7 @@ static struct phy_driver bcm87xx_driver[] = {
 	.read_status	= bcm87xx_read_status,
 	.config_intr	= bcm87xx_config_intr,
 	.handle_interrupt = bcm87xx_handle_interrupt,
-	.match_phy_device = bcm8706_match_phy_device,
+	.match_phy_device = bcm87xx_match_phy_device,
 }, {
 	.phy_id		= PHY_ID_BCM8727,
 	.phy_id_mask	= 0xffffffff,
@@ -217,7 +213,7 @@ static struct phy_driver bcm87xx_driver[] = {
 	.read_status	= bcm87xx_read_status,
 	.config_intr	= bcm87xx_config_intr,
 	.handle_interrupt = bcm87xx_handle_interrupt,
-	.match_phy_device = bcm8727_match_phy_device,
+	.match_phy_device = bcm87xx_match_phy_device,
 } };
 
 module_phy_driver(bcm87xx_driver);
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 85e231451093..daab555721df 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -478,13 +478,6 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp,
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		/* Reject requests with unsupported flags */
-		if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-					PTP_RISING_EDGE |
-					PTP_FALLING_EDGE |
-					PTP_STRICT_FLAGS))
-			return -EOPNOTSUPP;
-
 		/* Reject requests to enable time stamping on both edges. */
 		if ((rq->extts.flags & PTP_STRICT_FLAGS) &&
 		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
@@ -513,9 +506,6 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp,
 		return 0;
 
 	case PTP_CLK_REQ_PEROUT:
-		/* Reject requests with unsupported flags */
-		if (rq->perout.flags)
-			return -EOPNOTSUPP;
 		if (rq->perout.index >= N_PER_OUT)
 			return -EINVAL;
 		return periodic_output(clock, rq, on, rq->perout.index);
@@ -1002,6 +992,9 @@ static void dp83640_clock_init(struct dp83640_clock *clock, struct mii_bus *bus)
 	clock->caps.n_per_out	= N_PER_OUT;
 	clock->caps.n_pins	= DP83640_N_PINS;
 	clock->caps.pps		= 0;
+	clock->caps.supported_extts_flags = PTP_RISING_EDGE |
+					    PTP_FALLING_EDGE |
+					    PTP_STRICT_FLAGS;
 	clock->caps.adjfine	= ptp_dp83640_adjfine;
 	clock->caps.adjtime	= ptp_dp83640_adjtime;
 	clock->caps.gettime64	= ptp_dp83640_gettime;
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index 14f361549638..01255dada600 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -33,6 +33,7 @@
 #define MII_DP83822_MLEDCR	0x25
 #define MII_DP83822_LDCTRL	0x403
 #define MII_DP83822_LEDCFG1	0x460
+#define MII_DP83822_IOCTRL	0x461
 #define MII_DP83822_IOCTRL1	0x462
 #define MII_DP83822_IOCTRL2	0x463
 #define MII_DP83822_GENCFG	0x465
@@ -118,6 +119,9 @@
 #define DP83822_LEDCFG1_LED1_CTRL	GENMASK(11, 8)
 #define DP83822_LEDCFG1_LED3_CTRL	GENMASK(7, 4)
 
+/* IOCTRL bits */
+#define DP83822_IOCTRL_MAC_IMPEDANCE_CTRL	GENMASK(4, 1)
+
 /* IOCTRL1 bits */
 #define DP83822_IOCTRL1_GPIO3_CTRL		GENMASK(10, 8)
 #define DP83822_IOCTRL1_GPIO3_CTRL_LED3		BIT(0)
@@ -202,6 +206,7 @@ struct dp83822_private {
 	u32 gpio2_clk_out;
 	bool led_pin_enable[DP83822_MAX_LED_PINS];
 	int tx_amplitude_100base_tx_index;
+	int mac_termination_index;
 };
 
 static int dp83822_config_wol(struct phy_device *phydev,
@@ -533,6 +538,12 @@ static int dp83822_config_init(struct phy_device *phydev)
 			       FIELD_PREP(DP83822_100BASE_TX_LINE_DRIVER_SWING,
 					  dp83822->tx_amplitude_100base_tx_index));
 
+	if (dp83822->mac_termination_index >= 0)
+		phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_IOCTRL,
+			       DP83822_IOCTRL_MAC_IMPEDANCE_CTRL,
+			       FIELD_PREP(DP83822_IOCTRL_MAC_IMPEDANCE_CTRL,
+					  dp83822->mac_termination_index));
+
 	err = dp83822_config_init_leds(phydev);
 	if (err)
 		return err;
@@ -730,12 +741,16 @@ static int dp83822_phy_reset(struct phy_device *phydev)
 	return phydev->drv->config_init(phydev);
 }
 
-#ifdef CONFIG_OF_MDIO
+#if IS_ENABLED(CONFIG_OF_MDIO)
 static const u32 tx_amplitude_100base_tx_gain[] = {
 	80, 82, 83, 85, 87, 88, 90, 92,
 	93, 95, 97, 98, 100, 102, 103, 105,
 };
 
+static const u32 mac_termination[] = {
+	99, 91, 84, 78, 73, 69, 65, 61, 58, 55, 53, 50, 48, 46, 44, 43,
+};
+
 static int dp83822_of_init_leds(struct phy_device *phydev)
 {
 	struct device_node *node = phydev->mdio.dev.of_node;
@@ -852,6 +867,23 @@ static int dp83822_of_init(struct phy_device *phydev)
 		}
 	}
 
+	ret = phy_get_mac_termination(phydev, dev, &val);
+	if (!ret) {
+		for (i = 0; i < ARRAY_SIZE(mac_termination); i++) {
+			if (mac_termination[i] == val) {
+				dp83822->mac_termination_index = i;
+				break;
+			}
+		}
+
+		if (dp83822->mac_termination_index < 0) {
+			phydev_err(phydev,
+				   "Invalid value for mac-termination-ohms property (%u)\n",
+				   val);
+			return -EINVAL;
+		}
+	}
+
 	return dp83822_of_init_leds(phydev);
 }
 
@@ -931,6 +963,7 @@ static int dp8382x_probe(struct phy_device *phydev)
 		return -ENOMEM;
 
 	dp83822->tx_amplitude_100base_tx_index = -1;
+	dp83822->mac_termination_index = -1;
 	phydev->priv = dp83822;
 
 	return 0;
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 063266cafe9c..deeefb962566 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -92,11 +92,6 @@
 #define DP83867_STRAP_STS1_RESERVED		BIT(11)
 
 /* STRAP_STS2 bits */
-#define DP83867_STRAP_STS2_CLK_SKEW_TX_MASK	GENMASK(6, 4)
-#define DP83867_STRAP_STS2_CLK_SKEW_TX_SHIFT	4
-#define DP83867_STRAP_STS2_CLK_SKEW_RX_MASK	GENMASK(2, 0)
-#define DP83867_STRAP_STS2_CLK_SKEW_RX_SHIFT	0
-#define DP83867_STRAP_STS2_CLK_SKEW_NONE	BIT(2)
 #define DP83867_STRAP_STS2_STRAP_FLD		BIT(10)
 
 /* PHY CTRL bits */
@@ -111,10 +106,8 @@
 /* RGMIIDCTL bits */
 #define DP83867_RGMII_TX_CLK_DELAY_MAX		0xf
 #define DP83867_RGMII_TX_CLK_DELAY_SHIFT	4
-#define DP83867_RGMII_TX_CLK_DELAY_INV	(DP83867_RGMII_TX_CLK_DELAY_MAX + 1)
 #define DP83867_RGMII_RX_CLK_DELAY_MAX		0xf
 #define DP83867_RGMII_RX_CLK_DELAY_SHIFT	0
-#define DP83867_RGMII_RX_CLK_DELAY_INV	(DP83867_RGMII_RX_CLK_DELAY_MAX + 1)
 
 /* IO_MUX_CFG bits */
 #define DP83867_IO_MUX_CFG_IO_IMPEDANCE_MASK	0x1f
@@ -506,48 +499,6 @@ static int dp83867_config_port_mirroring(struct phy_device *phydev)
 	return 0;
 }
 
-static int dp83867_verify_rgmii_cfg(struct phy_device *phydev)
-{
-	struct dp83867_private *dp83867 = phydev->priv;
-
-	/* Existing behavior was to use default pin strapping delay in rgmii
-	 * mode, but rgmii should have meant no delay.  Warn existing users.
-	 */
-	if (phydev->interface == PHY_INTERFACE_MODE_RGMII) {
-		const u16 val = phy_read_mmd(phydev, DP83867_DEVADDR,
-					     DP83867_STRAP_STS2);
-		const u16 txskew = (val & DP83867_STRAP_STS2_CLK_SKEW_TX_MASK) >>
-				   DP83867_STRAP_STS2_CLK_SKEW_TX_SHIFT;
-		const u16 rxskew = (val & DP83867_STRAP_STS2_CLK_SKEW_RX_MASK) >>
-				   DP83867_STRAP_STS2_CLK_SKEW_RX_SHIFT;
-
-		if (txskew != DP83867_STRAP_STS2_CLK_SKEW_NONE ||
-		    rxskew != DP83867_STRAP_STS2_CLK_SKEW_NONE)
-			phydev_warn(phydev,
-				    "PHY has delays via pin strapping, but phy-mode = 'rgmii'\n"
-				    "Should be 'rgmii-id' to use internal delays txskew:%x rxskew:%x\n",
-				    txskew, rxskew);
-	}
-
-	/* RX delay *must* be specified if internal delay of RX is used. */
-	if ((phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
-	     phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) &&
-	     dp83867->rx_id_delay == DP83867_RGMII_RX_CLK_DELAY_INV) {
-		phydev_err(phydev, "ti,rx-internal-delay must be specified\n");
-		return -EINVAL;
-	}
-
-	/* TX delay *must* be specified if internal delay of TX is used. */
-	if ((phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
-	     phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) &&
-	     dp83867->tx_id_delay == DP83867_RGMII_TX_CLK_DELAY_INV) {
-		phydev_err(phydev, "ti,tx-internal-delay must be specified\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 #if IS_ENABLED(CONFIG_OF_MDIO)
 static int dp83867_of_init_io_impedance(struct phy_device *phydev)
 {
@@ -631,7 +582,7 @@ static int dp83867_of_init(struct phy_device *phydev)
 	dp83867->sgmii_ref_clk_en = of_property_read_bool(of_node,
 							  "ti,sgmii-ref-clock-output-enable");
 
-	dp83867->rx_id_delay = DP83867_RGMII_RX_CLK_DELAY_INV;
+	dp83867->rx_id_delay = DP83867_RGMIIDCTL_2_00_NS;
 	ret = of_property_read_u32(of_node, "ti,rx-internal-delay",
 				   &dp83867->rx_id_delay);
 	if (!ret && dp83867->rx_id_delay > DP83867_RGMII_RX_CLK_DELAY_MAX) {
@@ -641,7 +592,7 @@ static int dp83867_of_init(struct phy_device *phydev)
 		return -EINVAL;
 	}
 
-	dp83867->tx_id_delay = DP83867_RGMII_TX_CLK_DELAY_INV;
+	dp83867->tx_id_delay = DP83867_RGMIIDCTL_2_00_NS;
 	ret = of_property_read_u32(of_node, "ti,tx-internal-delay",
 				   &dp83867->tx_id_delay);
 	if (!ret && dp83867->tx_id_delay > DP83867_RGMII_TX_CLK_DELAY_MAX) {
@@ -761,7 +712,6 @@ static int dp83867_config_init(struct phy_device *phydev)
 {
 	struct dp83867_private *dp83867 = phydev->priv;
 	int ret, val, bs;
-	u16 delay;
 
 	/* Force speed optimization for the PHY even if it strapped */
 	ret = phy_modify(phydev, DP83867_CFG2, DP83867_DOWNSHIFT_EN,
@@ -769,10 +719,6 @@ static int dp83867_config_init(struct phy_device *phydev)
 	if (ret)
 		return ret;
 
-	ret = dp83867_verify_rgmii_cfg(phydev);
-	if (ret)
-		return ret;
-
 	/* RX_DV/RX_CTRL strapped in mode 1 or mode 2 workaround */
 	if (dp83867->rxctrl_strap_quirk)
 		phy_clear_bits_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4,
@@ -836,13 +782,7 @@ static int dp83867_config_init(struct phy_device *phydev)
 		if (ret)
 			return ret;
 
-		/* If rgmii mode with no internal delay is selected, we do NOT use
-		 * aligned mode as one might expect.  Instead we use the PHY's default
-		 * based on pin strapping.  And the "mode 0" default is to *use*
-		 * internal delay with a value of 7 (2.00 ns).
-		 *
-		 * Set up RGMII delays
-		 */
+		/* Set up RGMII delays */
 		val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIICTL);
 
 		val &= ~(DP83867_RGMII_TX_CLK_DELAY_EN | DP83867_RGMII_RX_CLK_DELAY_EN);
@@ -857,15 +797,9 @@ static int dp83867_config_init(struct phy_device *phydev)
 
 		phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIICTL, val);
 
-		delay = 0;
-		if (dp83867->rx_id_delay != DP83867_RGMII_RX_CLK_DELAY_INV)
-			delay |= dp83867->rx_id_delay;
-		if (dp83867->tx_id_delay != DP83867_RGMII_TX_CLK_DELAY_INV)
-			delay |= dp83867->tx_id_delay <<
-				 DP83867_RGMII_TX_CLK_DELAY_SHIFT;
-
 		phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIIDCTL,
-			      delay);
+			      dp83867->rx_id_delay |
+			      (dp83867->tx_id_delay << DP83867_RGMII_TX_CLK_DELAY_SHIFT));
 	}
 
 	/* If specified, set io impedance */
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index ee7831a9849b..033656d574b8 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -131,7 +131,7 @@ int fixed_phy_set_link_update(struct phy_device *phydev,
 EXPORT_SYMBOL_GPL(fixed_phy_set_link_update);
 
 static int fixed_phy_add_gpiod(unsigned int irq, int phy_addr,
-			       struct fixed_phy_status *status,
+			       const struct fixed_phy_status *status,
 			       struct gpio_desc *gpiod)
 {
 	int ret;
@@ -160,10 +160,9 @@ static int fixed_phy_add_gpiod(unsigned int irq, int phy_addr,
 	return 0;
 }
 
-int fixed_phy_add(unsigned int irq, int phy_addr,
-		  struct fixed_phy_status *status)
+int fixed_phy_add(int phy_addr, const struct fixed_phy_status *status)
 {
-	return fixed_phy_add_gpiod(irq, phy_addr, status, NULL);
+	return fixed_phy_add_gpiod(PHY_POLL, phy_addr, status, NULL);
 }
 EXPORT_SYMBOL_GPL(fixed_phy_add);
 
@@ -223,12 +222,11 @@ static struct gpio_desc *fixed_phy_get_gpiod(struct device_node *np)
 }
 #endif
 
-static struct phy_device *__fixed_phy_register(unsigned int irq,
-					       struct fixed_phy_status *status,
-					       struct device_node *np,
-					       struct gpio_desc *gpiod)
+struct phy_device *fixed_phy_register(const struct fixed_phy_status *status,
+				      struct device_node *np)
 {
 	struct fixed_mdio_bus *fmb = &platform_fmb;
+	struct gpio_desc *gpiod;
 	struct phy_device *phy;
 	int phy_addr;
 	int ret;
@@ -237,18 +235,16 @@ static struct phy_device *__fixed_phy_register(unsigned int irq,
 		return ERR_PTR(-EPROBE_DEFER);
 
 	/* Check if we have a GPIO associated with this fixed phy */
-	if (!gpiod) {
-		gpiod = fixed_phy_get_gpiod(np);
-		if (IS_ERR(gpiod))
-			return ERR_CAST(gpiod);
-	}
+	gpiod = fixed_phy_get_gpiod(np);
+	if (IS_ERR(gpiod))
+		return ERR_CAST(gpiod);
 
 	/* Get the next available PHY address, up to PHY_MAX_ADDR */
 	phy_addr = ida_alloc_max(&phy_fixed_ida, PHY_MAX_ADDR - 1, GFP_KERNEL);
 	if (phy_addr < 0)
 		return ERR_PTR(phy_addr);
 
-	ret = fixed_phy_add_gpiod(irq, phy_addr, status, gpiod);
+	ret = fixed_phy_add_gpiod(PHY_POLL, phy_addr, status, gpiod);
 	if (ret < 0) {
 		ida_free(&phy_fixed_ida, phy_addr);
 		return ERR_PTR(ret);
@@ -306,24 +302,8 @@ static struct phy_device *__fixed_phy_register(unsigned int irq,
 
 	return phy;
 }
-
-struct phy_device *fixed_phy_register(unsigned int irq,
-				      struct fixed_phy_status *status,
-				      struct device_node *np)
-{
-	return __fixed_phy_register(irq, status, np, NULL);
-}
 EXPORT_SYMBOL_GPL(fixed_phy_register);
 
-struct phy_device *
-fixed_phy_register_with_gpiod(unsigned int irq,
-			      struct fixed_phy_status *status,
-			      struct gpio_desc *gpiod)
-{
-	return __fixed_phy_register(irq, status, NULL, gpiod);
-}
-EXPORT_SYMBOL_GPL(fixed_phy_register_with_gpiod);
-
 void fixed_phy_unregister(struct phy_device *phy)
 {
 	phy_device_remove(phy);
diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index bbcc7d2b54cd..c0c4f19cfb6a 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -520,12 +520,14 @@ static int ip101a_g_match_phy_device(struct phy_device *phydev, bool ip101a)
 	return ip101a == !ret;
 }
 
-static int ip101a_match_phy_device(struct phy_device *phydev)
+static int ip101a_match_phy_device(struct phy_device *phydev,
+				   const struct phy_driver *phydrv)
 {
 	return ip101a_g_match_phy_device(phydev, true);
 }
 
-static int ip101g_match_phy_device(struct phy_device *phydev)
+static int ip101g_match_phy_device(struct phy_device *phydev,
+				   const struct phy_driver *phydrv)
 {
 	return ip101a_g_match_phy_device(phydev, false);
 }
diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c
index 23e1f0521f54..f3d83b04c953 100644
--- a/drivers/net/phy/marvell-88q2xxx.c
+++ b/drivers/net/phy/marvell-88q2xxx.c
@@ -119,7 +119,6 @@
 #define MV88Q2XXX_LED_INDEX_GPIO			1
 
 struct mv88q2xxx_priv {
-	bool enable_temp;
 	bool enable_led0;
 };
 
@@ -482,49 +481,6 @@ static int mv88q2xxx_config_aneg(struct phy_device *phydev)
 	return phydev->drv->soft_reset(phydev);
 }
 
-static int mv88q2xxx_config_init(struct phy_device *phydev)
-{
-	struct mv88q2xxx_priv *priv = phydev->priv;
-	int ret;
-
-	/* The 88Q2XXX PHYs do have the extended ability register available, but
-	 * register MDIO_PMA_EXTABLE where they should signalize it does not
-	 * work according to specification. Therefore, we force it here.
-	 */
-	phydev->pma_extable = MDIO_PMA_EXTABLE_BT1;
-
-	/* Configure interrupt with default settings, output is driven low for
-	 * active interrupt and high for inactive.
-	 */
-	if (phy_interrupt_is_valid(phydev)) {
-		ret = phy_set_bits_mmd(phydev, MDIO_MMD_PCS,
-				       MDIO_MMD_PCS_MV_GPIO_INT_CTRL,
-				       MDIO_MMD_PCS_MV_GPIO_INT_CTRL_TRI_DIS);
-		if (ret < 0)
-			return ret;
-	}
-
-	/* Enable LED function and disable TX disable feature on LED/TX_ENABLE */
-	if (priv->enable_led0) {
-		ret = phy_clear_bits_mmd(phydev, MDIO_MMD_PCS,
-					 MDIO_MMD_PCS_MV_RESET_CTRL,
-					 MDIO_MMD_PCS_MV_RESET_CTRL_TX_DISABLE);
-		if (ret < 0)
-			return ret;
-	}
-
-	/* Enable temperature sense */
-	if (priv->enable_temp) {
-		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
-				     MDIO_MMD_PCS_MV_TEMP_SENSOR2,
-				     MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0);
-		if (ret < 0)
-			return ret;
-	}
-
-	return 0;
-}
-
 static int mv88q2xxx_get_sqi(struct phy_device *phydev)
 {
 	int ret;
@@ -667,6 +623,12 @@ static int mv88q2xxx_resume(struct phy_device *phydev)
 }
 
 #if IS_ENABLED(CONFIG_HWMON)
+static int mv88q2xxx_enable_temp_sense(struct phy_device *phydev)
+{
+	return phy_modify_mmd(phydev, MDIO_MMD_PCS, MDIO_MMD_PCS_MV_TEMP_SENSOR2,
+			      MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0);
+}
+
 static const struct hwmon_channel_info * const mv88q2xxx_hwmon_info[] = {
 	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_ALARM),
 	NULL
@@ -762,11 +724,13 @@ static const struct hwmon_chip_info mv88q2xxx_hwmon_chip_info = {
 
 static int mv88q2xxx_hwmon_probe(struct phy_device *phydev)
 {
-	struct mv88q2xxx_priv *priv = phydev->priv;
 	struct device *dev = &phydev->mdio.dev;
 	struct device *hwmon;
+	int ret;
 
-	priv->enable_temp = true;
+	ret = mv88q2xxx_enable_temp_sense(phydev);
+	if (ret < 0)
+		return ret;
 
 	hwmon = devm_hwmon_device_register_with_info(dev, NULL, phydev,
 						     &mv88q2xxx_hwmon_chip_info,
@@ -776,6 +740,11 @@ static int mv88q2xxx_hwmon_probe(struct phy_device *phydev)
 }
 
 #else
+static int mv88q2xxx_enable_temp_sense(struct phy_device *phydev)
+{
+	return 0;
+}
+
 static int mv88q2xxx_hwmon_probe(struct phy_device *phydev)
 {
 	return 0;
@@ -828,6 +797,7 @@ static int mv88q2xxx_leds_probe(struct phy_device *phydev)
 static int mv88q2xxx_probe(struct phy_device *phydev)
 {
 	struct mv88q2xxx_priv *priv;
+	int ret;
 
 	priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -835,22 +805,53 @@ static int mv88q2xxx_probe(struct phy_device *phydev)
 
 	phydev->priv = priv;
 
-	return 0;
+	ret = mv88q2xxx_leds_probe(phydev);
+	if (ret)
+		return ret;
+
+	return mv88q2xxx_hwmon_probe(phydev);
 }
 
-static int mv88q222x_probe(struct phy_device *phydev)
+static int mv88q2xxx_config_init(struct phy_device *phydev)
 {
+	struct mv88q2xxx_priv *priv = phydev->priv;
 	int ret;
 
-	ret = mv88q2xxx_probe(phydev);
-	if (ret)
-		return ret;
+	/* The 88Q2XXX PHYs do have the extended ability register available, but
+	 * register MDIO_PMA_EXTABLE where they should signalize it does not
+	 * work according to specification. Therefore, we force it here.
+	 */
+	phydev->pma_extable = MDIO_PMA_EXTABLE_BT1;
 
-	ret = mv88q2xxx_leds_probe(phydev);
-	if (ret)
+	/* Configure interrupt with default settings, output is driven low for
+	 * active interrupt and high for inactive.
+	 */
+	if (phy_interrupt_is_valid(phydev)) {
+		ret = phy_set_bits_mmd(phydev, MDIO_MMD_PCS,
+				       MDIO_MMD_PCS_MV_GPIO_INT_CTRL,
+				       MDIO_MMD_PCS_MV_GPIO_INT_CTRL_TRI_DIS);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* Enable LED function and disable TX disable feature on LED/TX_ENABLE */
+	if (priv->enable_led0) {
+		ret = phy_clear_bits_mmd(phydev, MDIO_MMD_PCS,
+					 MDIO_MMD_PCS_MV_RESET_CTRL,
+					 MDIO_MMD_PCS_MV_RESET_CTRL_TX_DISABLE);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* Enable temperature sense again. There might have been a hard reset
+	 * of the PHY and in this case the register content is restored to
+	 * defaults and we need to enable it again.
+	 */
+	ret = mv88q2xxx_enable_temp_sense(phydev);
+	if (ret < 0)
 		return ret;
 
-	return mv88q2xxx_hwmon_probe(phydev);
+	return 0;
 }
 
 static int mv88q2110_config_init(struct phy_device *phydev)
@@ -1118,7 +1119,7 @@ static struct phy_driver mv88q2xxx_driver[] = {
 		.phy_id_mask		= MARVELL_PHY_ID_MASK,
 		.name			= "mv88q2220",
 		.flags			= PHY_POLL_CABLE_TEST,
-		.probe			= mv88q222x_probe,
+		.probe			= mv88q2xxx_probe,
 		.get_features		= mv88q2xxx_get_features,
 		.config_aneg		= mv88q2xxx_config_aneg,
 		.aneg_done		= genphy_c45_aneg_done,
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 5354c8895163..13e81dff42c1 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -1264,7 +1264,8 @@ static int mv3310_get_number_of_ports(struct phy_device *phydev)
 	return ret + 1;
 }
 
-static int mv3310_match_phy_device(struct phy_device *phydev)
+static int mv3310_match_phy_device(struct phy_device *phydev,
+				   const struct phy_driver *phydrv)
 {
 	if ((phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] &
 	     MARVELL_PHY_ID_MASK) != MARVELL_PHY_ID_88X3310)
@@ -1273,7 +1274,8 @@ static int mv3310_match_phy_device(struct phy_device *phydev)
 	return mv3310_get_number_of_ports(phydev) == 1;
 }
 
-static int mv3340_match_phy_device(struct phy_device *phydev)
+static int mv3340_match_phy_device(struct phy_device *phydev,
+				   const struct phy_driver *phydrv)
 {
 	if ((phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] &
 	     MARVELL_PHY_ID_MASK) != MARVELL_PHY_ID_88X3310)
@@ -1297,12 +1299,14 @@ static int mv211x_match_phy_device(struct phy_device *phydev, bool has_5g)
 	return !!(val & MDIO_PCS_SPEED_5G) == has_5g;
 }
 
-static int mv2110_match_phy_device(struct phy_device *phydev)
+static int mv2110_match_phy_device(struct phy_device *phydev,
+				   const struct phy_driver *phydrv)
 {
 	return mv211x_match_phy_device(phydev, true);
 }
 
-static int mv2111_match_phy_device(struct phy_device *phydev)
+static int mv2111_match_phy_device(struct phy_device *phydev,
+				   const struct phy_driver *phydrv)
 {
 	return mv211x_match_phy_device(phydev, false);
 }
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index ede596c1a69d..a6bcb0fee863 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -8,17 +8,14 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/errno.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
 #include <linux/gpio/consumer.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
-#include <linux/micrel_phy.h>
 #include <linux/mii.h>
 #include <linux/mm.h>
 #include <linux/module.h>
@@ -27,7 +24,6 @@
 #include <linux/of_mdio.h>
 #include <linux/phy.h>
 #include <linux/reset.h>
-#include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
@@ -37,8 +33,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/mdio.h>
 
-#include "mdio-boardinfo.h"
-
 static int mdiobus_register_gpiod(struct mdio_device *mdiodev)
 {
 	/* Deassert the optional reset signal */
@@ -137,45 +131,6 @@ bool mdiobus_is_registered_device(struct mii_bus *bus, int addr)
 EXPORT_SYMBOL(mdiobus_is_registered_device);
 
 /**
- * mdiobus_alloc_size - allocate a mii_bus structure
- * @size: extra amount of memory to allocate for private storage.
- * If non-zero, then bus->priv is points to that memory.
- *
- * Description: called by a bus driver to allocate an mii_bus
- * structure to fill in.
- */
-struct mii_bus *mdiobus_alloc_size(size_t size)
-{
-	struct mii_bus *bus;
-	size_t aligned_size = ALIGN(sizeof(*bus), NETDEV_ALIGN);
-	size_t alloc_size;
-	int i;
-
-	/* If we alloc extra space, it should be aligned */
-	if (size)
-		alloc_size = aligned_size + size;
-	else
-		alloc_size = sizeof(*bus);
-
-	bus = kzalloc(alloc_size, GFP_KERNEL);
-	if (!bus)
-		return NULL;
-
-	bus->state = MDIOBUS_ALLOCATED;
-	if (size)
-		bus->priv = (void *)bus + aligned_size;
-
-	/* Initialise the interrupts to polling and 64-bit seqcounts */
-	for (i = 0; i < PHY_MAX_ADDR; i++) {
-		bus->irq[i] = PHY_POLL;
-		u64_stats_init(&bus->stats[i].syncp);
-	}
-
-	return bus;
-}
-EXPORT_SYMBOL(mdiobus_alloc_size);
-
-/**
  * mdiobus_release - mii_bus device release callback
  * @d: the target struct device that contains the mii_bus
  *
@@ -403,11 +358,12 @@ static const struct attribute_group *mdio_bus_groups[] = {
 	NULL,
 };
 
-static struct class mdio_bus_class = {
+const struct class mdio_bus_class = {
 	.name		= "mdio_bus",
 	.dev_release	= mdiobus_release,
 	.dev_groups	= mdio_bus_groups,
 };
+EXPORT_SYMBOL_GPL(mdio_bus_class);
 
 /**
  * mdio_find_bus - Given the name of a mdiobus, find the mii_bus.
@@ -451,422 +407,8 @@ struct mii_bus *of_mdio_find_bus(struct device_node *mdio_bus_np)
 	return d ? to_mii_bus(d) : NULL;
 }
 EXPORT_SYMBOL(of_mdio_find_bus);
-
-/* Walk the list of subnodes of a mdio bus and look for a node that
- * matches the mdio device's address with its 'reg' property. If
- * found, set the of_node pointer for the mdio device. This allows
- * auto-probed phy devices to be supplied with information passed in
- * via DT.
- * If a PHY package is found, PHY is searched also there.
- */
-static int of_mdiobus_find_phy(struct device *dev, struct mdio_device *mdiodev,
-			       struct device_node *np)
-{
-	struct device_node *child;
-
-	for_each_available_child_of_node(np, child) {
-		int addr;
-
-		if (of_node_name_eq(child, "ethernet-phy-package")) {
-			/* Validate PHY package reg presence */
-			if (!of_property_present(child, "reg")) {
-				of_node_put(child);
-				return -EINVAL;
-			}
-
-			if (!of_mdiobus_find_phy(dev, mdiodev, child)) {
-				/* The refcount for the PHY package will be
-				 * incremented later when PHY join the Package.
-				 */
-				of_node_put(child);
-				return 0;
-			}
-
-			continue;
-		}
-
-		addr = of_mdio_parse_addr(dev, child);
-		if (addr < 0)
-			continue;
-
-		if (addr == mdiodev->addr) {
-			device_set_node(dev, of_fwnode_handle(child));
-			/* The refcount on "child" is passed to the mdio
-			 * device. Do _not_ use of_node_put(child) here.
-			 */
-			return 0;
-		}
-	}
-
-	return -ENODEV;
-}
-
-static void of_mdiobus_link_mdiodev(struct mii_bus *bus,
-				    struct mdio_device *mdiodev)
-{
-	struct device *dev = &mdiodev->dev;
-
-	if (dev->of_node || !bus->dev.of_node)
-		return;
-
-	of_mdiobus_find_phy(dev, mdiodev, bus->dev.of_node);
-}
-#else /* !IS_ENABLED(CONFIG_OF_MDIO) */
-static inline void of_mdiobus_link_mdiodev(struct mii_bus *mdio,
-					   struct mdio_device *mdiodev)
-{
-}
 #endif
 
-/**
- * mdiobus_create_device - create a full MDIO device given
- * a mdio_board_info structure
- * @bus: MDIO bus to create the devices on
- * @bi: mdio_board_info structure describing the devices
- *
- * Returns 0 on success or < 0 on error.
- */
-static int mdiobus_create_device(struct mii_bus *bus,
-				 struct mdio_board_info *bi)
-{
-	struct mdio_device *mdiodev;
-	int ret = 0;
-
-	mdiodev = mdio_device_create(bus, bi->mdio_addr);
-	if (IS_ERR(mdiodev))
-		return -ENODEV;
-
-	strscpy(mdiodev->modalias, bi->modalias,
-		sizeof(mdiodev->modalias));
-	mdiodev->bus_match = mdio_device_bus_match;
-	mdiodev->dev.platform_data = (void *)bi->platform_data;
-
-	ret = mdio_device_register(mdiodev);
-	if (ret)
-		mdio_device_free(mdiodev);
-
-	return ret;
-}
-
-static struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr, bool c45)
-{
-	struct phy_device *phydev = ERR_PTR(-ENODEV);
-	struct fwnode_handle *fwnode;
-	char node_name[16];
-	int err;
-
-	phydev = get_phy_device(bus, addr, c45);
-	if (IS_ERR(phydev))
-		return phydev;
-
-	/* For DT, see if the auto-probed phy has a corresponding child
-	 * in the bus node, and set the of_node pointer in this case.
-	 */
-	of_mdiobus_link_mdiodev(bus, &phydev->mdio);
-
-	/* Search for a swnode for the phy in the swnode hierarchy of the bus.
-	 * If there is no swnode for the phy provided, just ignore it.
-	 */
-	if (dev_fwnode(&bus->dev) && !dev_fwnode(&phydev->mdio.dev)) {
-		snprintf(node_name, sizeof(node_name), "ethernet-phy@%d",
-			 addr);
-		fwnode = fwnode_get_named_child_node(dev_fwnode(&bus->dev),
-						     node_name);
-		if (fwnode)
-			device_set_node(&phydev->mdio.dev, fwnode);
-	}
-
-	err = phy_device_register(phydev);
-	if (err) {
-		phy_device_free(phydev);
-		return ERR_PTR(-ENODEV);
-	}
-
-	return phydev;
-}
-
-/**
- * mdiobus_scan_c22 - scan one address on a bus for C22 MDIO devices.
- * @bus: mii_bus to scan
- * @addr: address on bus to scan
- *
- * This function scans one address on the MDIO bus, looking for
- * devices which can be identified using a vendor/product ID in
- * registers 2 and 3. Not all MDIO devices have such registers, but
- * PHY devices typically do. Hence this function assumes anything
- * found is a PHY, or can be treated as a PHY. Other MDIO devices,
- * such as switches, will probably not be found during the scan.
- */
-struct phy_device *mdiobus_scan_c22(struct mii_bus *bus, int addr)
-{
-	return mdiobus_scan(bus, addr, false);
-}
-EXPORT_SYMBOL(mdiobus_scan_c22);
-
-/**
- * mdiobus_scan_c45 - scan one address on a bus for C45 MDIO devices.
- * @bus: mii_bus to scan
- * @addr: address on bus to scan
- *
- * This function scans one address on the MDIO bus, looking for
- * devices which can be identified using a vendor/product ID in
- * registers 2 and 3. Not all MDIO devices have such registers, but
- * PHY devices typically do. Hence this function assumes anything
- * found is a PHY, or can be treated as a PHY. Other MDIO devices,
- * such as switches, will probably not be found during the scan.
- */
-static struct phy_device *mdiobus_scan_c45(struct mii_bus *bus, int addr)
-{
-	return mdiobus_scan(bus, addr, true);
-}
-
-static int mdiobus_scan_bus_c22(struct mii_bus *bus)
-{
-	int i;
-
-	for (i = 0; i < PHY_MAX_ADDR; i++) {
-		if ((bus->phy_mask & BIT(i)) == 0) {
-			struct phy_device *phydev;
-
-			phydev = mdiobus_scan_c22(bus, i);
-			if (IS_ERR(phydev) && (PTR_ERR(phydev) != -ENODEV))
-				return PTR_ERR(phydev);
-		}
-	}
-	return 0;
-}
-
-static int mdiobus_scan_bus_c45(struct mii_bus *bus)
-{
-	int i;
-
-	for (i = 0; i < PHY_MAX_ADDR; i++) {
-		if ((bus->phy_mask & BIT(i)) == 0) {
-			struct phy_device *phydev;
-
-			/* Don't scan C45 if we already have a C22 device */
-			if (bus->mdio_map[i])
-				continue;
-
-			phydev = mdiobus_scan_c45(bus, i);
-			if (IS_ERR(phydev) && (PTR_ERR(phydev) != -ENODEV))
-				return PTR_ERR(phydev);
-		}
-	}
-	return 0;
-}
-
-/* There are some C22 PHYs which do bad things when where is a C45
- * transaction on the bus, like accepting a read themselves, and
- * stomping over the true devices reply, to performing a write to
- * themselves which was intended for another device. Now that C22
- * devices have been found, see if any of them are bad for C45, and if we
- * should skip the C45 scan.
- */
-static bool mdiobus_prevent_c45_scan(struct mii_bus *bus)
-{
-	int i;
-
-	for (i = 0; i < PHY_MAX_ADDR; i++) {
-		struct phy_device *phydev;
-		u32 oui;
-
-		phydev = mdiobus_get_phy(bus, i);
-		if (!phydev)
-			continue;
-		oui = phydev->phy_id >> 10;
-
-		if (oui == MICREL_OUI)
-			return true;
-	}
-	return false;
-}
-
-/**
- * __mdiobus_register - bring up all the PHYs on a given bus and attach them to bus
- * @bus: target mii_bus
- * @owner: module containing bus accessor functions
- *
- * Description: Called by a bus driver to bring up all the PHYs
- *   on a given bus, and attach them to the bus. Drivers should use
- *   mdiobus_register() rather than __mdiobus_register() unless they
- *   need to pass a specific owner module. MDIO devices which are not
- *   PHYs will not be brought up by this function. They are expected
- *   to be explicitly listed in DT and instantiated by of_mdiobus_register().
- *
- * Returns 0 on success or < 0 on error.
- */
-int __mdiobus_register(struct mii_bus *bus, struct module *owner)
-{
-	struct mdio_device *mdiodev;
-	struct gpio_desc *gpiod;
-	bool prevent_c45_scan;
-	int i, err;
-
-	if (!bus || !bus->name)
-		return -EINVAL;
-
-	/* An access method always needs both read and write operations */
-	if (!!bus->read != !!bus->write || !!bus->read_c45 != !!bus->write_c45)
-		return -EINVAL;
-
-	/* At least one method is mandatory */
-	if (!bus->read && !bus->read_c45)
-		return -EINVAL;
-
-	if (bus->parent && bus->parent->of_node)
-		bus->parent->of_node->fwnode.flags |=
-					FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD;
-
-	WARN(bus->state != MDIOBUS_ALLOCATED &&
-	     bus->state != MDIOBUS_UNREGISTERED,
-	     "%s: not in ALLOCATED or UNREGISTERED state\n", bus->id);
-
-	bus->owner = owner;
-	bus->dev.parent = bus->parent;
-	bus->dev.class = &mdio_bus_class;
-	bus->dev.groups = NULL;
-	dev_set_name(&bus->dev, "%s", bus->id);
-
-	/* If the bus state is allocated, we're registering a fresh bus
-	 * that may have a fwnode associated with it. Grab a reference
-	 * to the fwnode. This will be dropped when the bus is released.
-	 * If the bus was set to unregistered, it means that the bus was
-	 * previously registered, and we've already grabbed a reference.
-	 */
-	if (bus->state == MDIOBUS_ALLOCATED)
-		fwnode_handle_get(dev_fwnode(&bus->dev));
-
-	/* We need to set state to MDIOBUS_UNREGISTERED to correctly release
-	 * the device in mdiobus_free()
-	 *
-	 * State will be updated later in this function in case of success
-	 */
-	bus->state = MDIOBUS_UNREGISTERED;
-
-	err = device_register(&bus->dev);
-	if (err) {
-		pr_err("mii_bus %s failed to register\n", bus->id);
-		return -EINVAL;
-	}
-
-	mutex_init(&bus->mdio_lock);
-	mutex_init(&bus->shared_lock);
-
-	/* assert bus level PHY GPIO reset */
-	gpiod = devm_gpiod_get_optional(&bus->dev, "reset", GPIOD_OUT_HIGH);
-	if (IS_ERR(gpiod)) {
-		err = dev_err_probe(&bus->dev, PTR_ERR(gpiod),
-				    "mii_bus %s couldn't get reset GPIO\n",
-				    bus->id);
-		device_del(&bus->dev);
-		return err;
-	} else	if (gpiod) {
-		bus->reset_gpiod = gpiod;
-		fsleep(bus->reset_delay_us);
-		gpiod_set_value_cansleep(gpiod, 0);
-		if (bus->reset_post_delay_us > 0)
-			fsleep(bus->reset_post_delay_us);
-	}
-
-	if (bus->reset) {
-		err = bus->reset(bus);
-		if (err)
-			goto error_reset_gpiod;
-	}
-
-	if (bus->read) {
-		err = mdiobus_scan_bus_c22(bus);
-		if (err)
-			goto error;
-	}
-
-	prevent_c45_scan = mdiobus_prevent_c45_scan(bus);
-
-	if (!prevent_c45_scan && bus->read_c45) {
-		err = mdiobus_scan_bus_c45(bus);
-		if (err)
-			goto error;
-	}
-
-	mdiobus_setup_mdiodev_from_board_info(bus, mdiobus_create_device);
-
-	bus->state = MDIOBUS_REGISTERED;
-	dev_dbg(&bus->dev, "probed\n");
-	return 0;
-
-error:
-	for (i = 0; i < PHY_MAX_ADDR; i++) {
-		mdiodev = bus->mdio_map[i];
-		if (!mdiodev)
-			continue;
-
-		mdiodev->device_remove(mdiodev);
-		mdiodev->device_free(mdiodev);
-	}
-error_reset_gpiod:
-	/* Put PHYs in RESET to save power */
-	if (bus->reset_gpiod)
-		gpiod_set_value_cansleep(bus->reset_gpiod, 1);
-
-	device_del(&bus->dev);
-	return err;
-}
-EXPORT_SYMBOL(__mdiobus_register);
-
-void mdiobus_unregister(struct mii_bus *bus)
-{
-	struct mdio_device *mdiodev;
-	int i;
-
-	if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED))
-		return;
-	bus->state = MDIOBUS_UNREGISTERED;
-
-	for (i = 0; i < PHY_MAX_ADDR; i++) {
-		mdiodev = bus->mdio_map[i];
-		if (!mdiodev)
-			continue;
-
-		if (mdiodev->reset_gpio)
-			gpiod_put(mdiodev->reset_gpio);
-
-		mdiodev->device_remove(mdiodev);
-		mdiodev->device_free(mdiodev);
-	}
-
-	/* Put PHYs in RESET to save power */
-	if (bus->reset_gpiod)
-		gpiod_set_value_cansleep(bus->reset_gpiod, 1);
-
-	device_del(&bus->dev);
-}
-EXPORT_SYMBOL(mdiobus_unregister);
-
-/**
- * mdiobus_free - free a struct mii_bus
- * @bus: mii_bus to free
- *
- * This function releases the reference to the underlying device
- * object in the mii_bus.  If this is the last reference, the mii_bus
- * will be freed.
- */
-void mdiobus_free(struct mii_bus *bus)
-{
-	/* For compatibility with error handling in drivers. */
-	if (bus->state == MDIOBUS_ALLOCATED) {
-		kfree(bus);
-		return;
-	}
-
-	WARN(bus->state != MDIOBUS_UNREGISTERED,
-	     "%s: not in UNREGISTERED state\n", bus->id);
-	bus->state = MDIOBUS_RELEASED;
-
-	put_device(&bus->dev);
-}
-EXPORT_SYMBOL(mdiobus_free);
-
 static void mdiobus_stats_acct(struct mdio_bus_stats *stats, bool op, int ret)
 {
 	preempt_disable();
@@ -1446,7 +988,7 @@ const struct bus_type mdio_bus_type = {
 };
 EXPORT_SYMBOL(mdio_bus_type);
 
-int __init mdio_bus_init(void)
+static int __init mdio_bus_init(void)
 {
 	int ret;
 
@@ -1460,16 +1002,14 @@ int __init mdio_bus_init(void)
 	return ret;
 }
 
-#if IS_ENABLED(CONFIG_PHYLIB)
-void mdio_bus_exit(void)
+static void __exit mdio_bus_exit(void)
 {
 	class_unregister(&mdio_bus_class);
 	bus_unregister(&mdio_bus_type);
 }
-EXPORT_SYMBOL_GPL(mdio_bus_exit);
-#else
-module_init(mdio_bus_init);
-/* no module_exit, intentional */
+
+subsys_initcall(mdio_bus_init);
+module_exit(mdio_bus_exit);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MDIO bus/device layer");
-#endif
diff --git a/drivers/net/phy/mdio_bus_provider.c b/drivers/net/phy/mdio_bus_provider.c
new file mode 100644
index 000000000000..65850e36284d
--- /dev/null
+++ b/drivers/net/phy/mdio_bus_provider.c
@@ -0,0 +1,484 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* MDIO Bus provider interface
+ *
+ * Author: Andy Fleming
+ *
+ * Copyright (c) 2004 Freescale Semiconductor, Inc.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/gpio/consumer.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/micrel_phy.h>
+#include <linux/mii.h>
+#include <linux/mm.h>
+#include <linux/netdevice.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/phy.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/unistd.h>
+
+#include "mdio-boardinfo.h"
+
+/**
+ * mdiobus_alloc_size - allocate a mii_bus structure
+ * @size: extra amount of memory to allocate for private storage.
+ * If non-zero, then bus->priv is points to that memory.
+ *
+ * Description: called by a bus driver to allocate an mii_bus
+ * structure to fill in.
+ */
+struct mii_bus *mdiobus_alloc_size(size_t size)
+{
+	struct mii_bus *bus;
+	size_t aligned_size = ALIGN(sizeof(*bus), NETDEV_ALIGN);
+	size_t alloc_size;
+	int i;
+
+	/* If we alloc extra space, it should be aligned */
+	if (size)
+		alloc_size = aligned_size + size;
+	else
+		alloc_size = sizeof(*bus);
+
+	bus = kzalloc(alloc_size, GFP_KERNEL);
+	if (!bus)
+		return NULL;
+
+	bus->state = MDIOBUS_ALLOCATED;
+	if (size)
+		bus->priv = (void *)bus + aligned_size;
+
+	/* Initialise the interrupts to polling and 64-bit seqcounts */
+	for (i = 0; i < PHY_MAX_ADDR; i++) {
+		bus->irq[i] = PHY_POLL;
+		u64_stats_init(&bus->stats[i].syncp);
+	}
+
+	return bus;
+}
+EXPORT_SYMBOL(mdiobus_alloc_size);
+
+#if IS_ENABLED(CONFIG_OF_MDIO)
+/* Walk the list of subnodes of a mdio bus and look for a node that
+ * matches the mdio device's address with its 'reg' property. If
+ * found, set the of_node pointer for the mdio device. This allows
+ * auto-probed phy devices to be supplied with information passed in
+ * via DT.
+ * If a PHY package is found, PHY is searched also there.
+ */
+static int of_mdiobus_find_phy(struct device *dev, struct mdio_device *mdiodev,
+			       struct device_node *np)
+{
+	struct device_node *child;
+
+	for_each_available_child_of_node(np, child) {
+		int addr;
+
+		if (of_node_name_eq(child, "ethernet-phy-package")) {
+			/* Validate PHY package reg presence */
+			if (!of_property_present(child, "reg")) {
+				of_node_put(child);
+				return -EINVAL;
+			}
+
+			if (!of_mdiobus_find_phy(dev, mdiodev, child)) {
+				/* The refcount for the PHY package will be
+				 * incremented later when PHY join the Package.
+				 */
+				of_node_put(child);
+				return 0;
+			}
+
+			continue;
+		}
+
+		addr = of_mdio_parse_addr(dev, child);
+		if (addr < 0)
+			continue;
+
+		if (addr == mdiodev->addr) {
+			device_set_node(dev, of_fwnode_handle(child));
+			/* The refcount on "child" is passed to the mdio
+			 * device. Do _not_ use of_node_put(child) here.
+			 */
+			return 0;
+		}
+	}
+
+	return -ENODEV;
+}
+
+static void of_mdiobus_link_mdiodev(struct mii_bus *bus,
+				    struct mdio_device *mdiodev)
+{
+	struct device *dev = &mdiodev->dev;
+
+	if (dev->of_node || !bus->dev.of_node)
+		return;
+
+	of_mdiobus_find_phy(dev, mdiodev, bus->dev.of_node);
+}
+#endif
+
+/**
+ * mdiobus_create_device - create a full MDIO device given
+ * a mdio_board_info structure
+ * @bus: MDIO bus to create the devices on
+ * @bi: mdio_board_info structure describing the devices
+ *
+ * Returns 0 on success or < 0 on error.
+ */
+static int mdiobus_create_device(struct mii_bus *bus,
+				 struct mdio_board_info *bi)
+{
+	struct mdio_device *mdiodev;
+	int ret = 0;
+
+	mdiodev = mdio_device_create(bus, bi->mdio_addr);
+	if (IS_ERR(mdiodev))
+		return -ENODEV;
+
+	strscpy(mdiodev->modalias, bi->modalias,
+		sizeof(mdiodev->modalias));
+	mdiodev->bus_match = mdio_device_bus_match;
+	mdiodev->dev.platform_data = (void *)bi->platform_data;
+
+	ret = mdio_device_register(mdiodev);
+	if (ret)
+		mdio_device_free(mdiodev);
+
+	return ret;
+}
+
+static struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr, bool c45)
+{
+	struct phy_device *phydev = ERR_PTR(-ENODEV);
+	struct fwnode_handle *fwnode;
+	char node_name[16];
+	int err;
+
+	phydev = get_phy_device(bus, addr, c45);
+	if (IS_ERR(phydev))
+		return phydev;
+
+#if IS_ENABLED(CONFIG_OF_MDIO)
+	/* For DT, see if the auto-probed phy has a corresponding child
+	 * in the bus node, and set the of_node pointer in this case.
+	 */
+	of_mdiobus_link_mdiodev(bus, &phydev->mdio);
+#endif
+
+	/* Search for a swnode for the phy in the swnode hierarchy of the bus.
+	 * If there is no swnode for the phy provided, just ignore it.
+	 */
+	if (dev_fwnode(&bus->dev) && !dev_fwnode(&phydev->mdio.dev)) {
+		snprintf(node_name, sizeof(node_name), "ethernet-phy@%d",
+			 addr);
+		fwnode = fwnode_get_named_child_node(dev_fwnode(&bus->dev),
+						     node_name);
+		if (fwnode)
+			device_set_node(&phydev->mdio.dev, fwnode);
+	}
+
+	err = phy_device_register(phydev);
+	if (err) {
+		phy_device_free(phydev);
+		return ERR_PTR(-ENODEV);
+	}
+
+	return phydev;
+}
+
+/**
+ * mdiobus_scan_c22 - scan one address on a bus for C22 MDIO devices.
+ * @bus: mii_bus to scan
+ * @addr: address on bus to scan
+ *
+ * This function scans one address on the MDIO bus, looking for
+ * devices which can be identified using a vendor/product ID in
+ * registers 2 and 3. Not all MDIO devices have such registers, but
+ * PHY devices typically do. Hence this function assumes anything
+ * found is a PHY, or can be treated as a PHY. Other MDIO devices,
+ * such as switches, will probably not be found during the scan.
+ */
+struct phy_device *mdiobus_scan_c22(struct mii_bus *bus, int addr)
+{
+	return mdiobus_scan(bus, addr, false);
+}
+EXPORT_SYMBOL(mdiobus_scan_c22);
+
+/**
+ * mdiobus_scan_c45 - scan one address on a bus for C45 MDIO devices.
+ * @bus: mii_bus to scan
+ * @addr: address on bus to scan
+ *
+ * This function scans one address on the MDIO bus, looking for
+ * devices which can be identified using a vendor/product ID in
+ * registers 2 and 3. Not all MDIO devices have such registers, but
+ * PHY devices typically do. Hence this function assumes anything
+ * found is a PHY, or can be treated as a PHY. Other MDIO devices,
+ * such as switches, will probably not be found during the scan.
+ */
+static struct phy_device *mdiobus_scan_c45(struct mii_bus *bus, int addr)
+{
+	return mdiobus_scan(bus, addr, true);
+}
+
+static int mdiobus_scan_bus_c22(struct mii_bus *bus)
+{
+	int i;
+
+	for (i = 0; i < PHY_MAX_ADDR; i++) {
+		if ((bus->phy_mask & BIT(i)) == 0) {
+			struct phy_device *phydev;
+
+			phydev = mdiobus_scan_c22(bus, i);
+			if (IS_ERR(phydev) && (PTR_ERR(phydev) != -ENODEV))
+				return PTR_ERR(phydev);
+		}
+	}
+	return 0;
+}
+
+static int mdiobus_scan_bus_c45(struct mii_bus *bus)
+{
+	int i;
+
+	for (i = 0; i < PHY_MAX_ADDR; i++) {
+		if ((bus->phy_mask & BIT(i)) == 0) {
+			struct phy_device *phydev;
+
+			/* Don't scan C45 if we already have a C22 device */
+			if (bus->mdio_map[i])
+				continue;
+
+			phydev = mdiobus_scan_c45(bus, i);
+			if (IS_ERR(phydev) && (PTR_ERR(phydev) != -ENODEV))
+				return PTR_ERR(phydev);
+		}
+	}
+	return 0;
+}
+
+/* There are some C22 PHYs which do bad things when where is a C45
+ * transaction on the bus, like accepting a read themselves, and
+ * stomping over the true devices reply, to performing a write to
+ * themselves which was intended for another device. Now that C22
+ * devices have been found, see if any of them are bad for C45, and if we
+ * should skip the C45 scan.
+ */
+static bool mdiobus_prevent_c45_scan(struct mii_bus *bus)
+{
+	int i;
+
+	for (i = 0; i < PHY_MAX_ADDR; i++) {
+		struct phy_device *phydev;
+		u32 oui;
+
+		phydev = mdiobus_get_phy(bus, i);
+		if (!phydev)
+			continue;
+		oui = phydev->phy_id >> 10;
+
+		if (oui == MICREL_OUI)
+			return true;
+	}
+	return false;
+}
+
+/**
+ * __mdiobus_register - bring up all the PHYs on a given bus and attach them to bus
+ * @bus: target mii_bus
+ * @owner: module containing bus accessor functions
+ *
+ * Description: Called by a bus driver to bring up all the PHYs
+ *   on a given bus, and attach them to the bus. Drivers should use
+ *   mdiobus_register() rather than __mdiobus_register() unless they
+ *   need to pass a specific owner module. MDIO devices which are not
+ *   PHYs will not be brought up by this function. They are expected
+ *   to be explicitly listed in DT and instantiated by of_mdiobus_register().
+ *
+ * Returns 0 on success or < 0 on error.
+ */
+int __mdiobus_register(struct mii_bus *bus, struct module *owner)
+{
+	struct mdio_device *mdiodev;
+	struct gpio_desc *gpiod;
+	bool prevent_c45_scan;
+	int i, err;
+
+	if (!bus || !bus->name)
+		return -EINVAL;
+
+	/* An access method always needs both read and write operations */
+	if (!!bus->read != !!bus->write || !!bus->read_c45 != !!bus->write_c45)
+		return -EINVAL;
+
+	/* At least one method is mandatory */
+	if (!bus->read && !bus->read_c45)
+		return -EINVAL;
+
+	if (bus->parent && bus->parent->of_node)
+		bus->parent->of_node->fwnode.flags |=
+					FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD;
+
+	WARN(bus->state != MDIOBUS_ALLOCATED &&
+	     bus->state != MDIOBUS_UNREGISTERED,
+	     "%s: not in ALLOCATED or UNREGISTERED state\n", bus->id);
+
+	bus->owner = owner;
+	bus->dev.parent = bus->parent;
+	bus->dev.class = &mdio_bus_class;
+	bus->dev.groups = NULL;
+	dev_set_name(&bus->dev, "%s", bus->id);
+
+	/* If the bus state is allocated, we're registering a fresh bus
+	 * that may have a fwnode associated with it. Grab a reference
+	 * to the fwnode. This will be dropped when the bus is released.
+	 * If the bus was set to unregistered, it means that the bus was
+	 * previously registered, and we've already grabbed a reference.
+	 */
+	if (bus->state == MDIOBUS_ALLOCATED)
+		fwnode_handle_get(dev_fwnode(&bus->dev));
+
+	/* We need to set state to MDIOBUS_UNREGISTERED to correctly release
+	 * the device in mdiobus_free()
+	 *
+	 * State will be updated later in this function in case of success
+	 */
+	bus->state = MDIOBUS_UNREGISTERED;
+
+	err = device_register(&bus->dev);
+	if (err) {
+		pr_err("mii_bus %s failed to register\n", bus->id);
+		return -EINVAL;
+	}
+
+	mutex_init(&bus->mdio_lock);
+	mutex_init(&bus->shared_lock);
+
+	/* assert bus level PHY GPIO reset */
+	gpiod = devm_gpiod_get_optional(&bus->dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(gpiod)) {
+		err = dev_err_probe(&bus->dev, PTR_ERR(gpiod),
+				    "mii_bus %s couldn't get reset GPIO\n",
+				    bus->id);
+		device_del(&bus->dev);
+		return err;
+	} else	if (gpiod) {
+		bus->reset_gpiod = gpiod;
+		fsleep(bus->reset_delay_us);
+		gpiod_set_value_cansleep(gpiod, 0);
+		if (bus->reset_post_delay_us > 0)
+			fsleep(bus->reset_post_delay_us);
+	}
+
+	if (bus->reset) {
+		err = bus->reset(bus);
+		if (err)
+			goto error_reset_gpiod;
+	}
+
+	if (bus->read) {
+		err = mdiobus_scan_bus_c22(bus);
+		if (err)
+			goto error;
+	}
+
+	prevent_c45_scan = mdiobus_prevent_c45_scan(bus);
+
+	if (!prevent_c45_scan && bus->read_c45) {
+		err = mdiobus_scan_bus_c45(bus);
+		if (err)
+			goto error;
+	}
+
+	mdiobus_setup_mdiodev_from_board_info(bus, mdiobus_create_device);
+
+	bus->state = MDIOBUS_REGISTERED;
+	dev_dbg(&bus->dev, "probed\n");
+	return 0;
+
+error:
+	for (i = 0; i < PHY_MAX_ADDR; i++) {
+		mdiodev = bus->mdio_map[i];
+		if (!mdiodev)
+			continue;
+
+		mdiodev->device_remove(mdiodev);
+		mdiodev->device_free(mdiodev);
+	}
+error_reset_gpiod:
+	/* Put PHYs in RESET to save power */
+	if (bus->reset_gpiod)
+		gpiod_set_value_cansleep(bus->reset_gpiod, 1);
+
+	device_del(&bus->dev);
+	return err;
+}
+EXPORT_SYMBOL(__mdiobus_register);
+
+void mdiobus_unregister(struct mii_bus *bus)
+{
+	struct mdio_device *mdiodev;
+	int i;
+
+	if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED))
+		return;
+	bus->state = MDIOBUS_UNREGISTERED;
+
+	for (i = 0; i < PHY_MAX_ADDR; i++) {
+		mdiodev = bus->mdio_map[i];
+		if (!mdiodev)
+			continue;
+
+		if (mdiodev->reset_gpio)
+			gpiod_put(mdiodev->reset_gpio);
+
+		mdiodev->device_remove(mdiodev);
+		mdiodev->device_free(mdiodev);
+	}
+
+	/* Put PHYs in RESET to save power */
+	if (bus->reset_gpiod)
+		gpiod_set_value_cansleep(bus->reset_gpiod, 1);
+
+	device_del(&bus->dev);
+}
+EXPORT_SYMBOL(mdiobus_unregister);
+
+/**
+ * mdiobus_free - free a struct mii_bus
+ * @bus: mii_bus to free
+ *
+ * This function releases the reference to the underlying device
+ * object in the mii_bus.  If this is the last reference, the mii_bus
+ * will be freed.
+ */
+void mdiobus_free(struct mii_bus *bus)
+{
+	/* For compatibility with error handling in drivers. */
+	if (bus->state == MDIOBUS_ALLOCATED) {
+		kfree(bus);
+		return;
+	}
+
+	WARN(bus->state != MDIOBUS_UNREGISTERED,
+	     "%s: not in UNREGISTERED state\n", bus->id);
+	bus->state = MDIOBUS_RELEASED;
+
+	put_device(&bus->dev);
+}
+EXPORT_SYMBOL(mdiobus_free);
diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index e747ee63c665..cce3f405d1a4 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -45,6 +45,7 @@ int mdio_device_bus_match(struct device *dev, const struct device_driver *drv)
 
 	return strcmp(mdiodev->modalias, drv->name) == 0;
 }
+EXPORT_SYMBOL_GPL(mdio_device_bus_match);
 
 struct mdio_device *mdio_device_create(struct mii_bus *bus, int addr)
 {
diff --git a/drivers/net/phy/mediatek/Kconfig b/drivers/net/phy/mediatek/Kconfig
index 2a8ac5aed0f8..9f30a91be8dd 100644
--- a/drivers/net/phy/mediatek/Kconfig
+++ b/drivers/net/phy/mediatek/Kconfig
@@ -1,6 +1,14 @@
 # SPDX-License-Identifier: GPL-2.0-only
-config MTK_NET_PHYLIB
-	tristate
+config MEDIATEK_2P5GE_PHY
+	tristate "MediaTek 2.5Gb Ethernet PHYs"
+	depends on (ARM64 && ARCH_MEDIATEK) || COMPILE_TEST
+	select MTK_NET_PHYLIB
+	help
+	  Supports MediaTek SoC built-in 2.5Gb Ethernet PHYs.
+
+	  This will load necessary firmware and add appropriate time delay.
+	  Accelerate this procedure through internal pbus instead of MDIO
+	  bus. Certain link-up issues will also be fixed here.
 
 config MEDIATEK_GE_PHY
 	tristate "MediaTek Gigabit Ethernet PHYs"
@@ -15,8 +23,9 @@ config MEDIATEK_GE_PHY
 
 config MEDIATEK_GE_SOC_PHY
 	tristate "MediaTek SoC Ethernet PHYs"
-	depends on (ARM64 && ARCH_MEDIATEK) || COMPILE_TEST
-	depends on NVMEM_MTK_EFUSE
+	depends on ARM64 || COMPILE_TEST
+	depends on ARCH_AIROHA || (ARCH_MEDIATEK && NVMEM_MTK_EFUSE) || \
+		   COMPILE_TEST
 	select MTK_NET_PHYLIB
 	help
 	  Supports MediaTek SoC built-in Gigabit Ethernet PHYs.
@@ -25,3 +34,6 @@ config MEDIATEK_GE_SOC_PHY
 	  the MT7981 and MT7988 SoCs. These PHYs need calibration data
 	  present in the SoCs efuse and will dynamically calibrate VCM
 	  (common-mode voltage) during startup.
+
+config MTK_NET_PHYLIB
+	tristate
diff --git a/drivers/net/phy/mediatek/Makefile b/drivers/net/phy/mediatek/Makefile
index 814879d0abe5..ac57ecc799fc 100644
--- a/drivers/net/phy/mediatek/Makefile
+++ b/drivers/net/phy/mediatek/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_MTK_NET_PHYLIB)		+= mtk-phy-lib.o
+obj-$(CONFIG_MEDIATEK_2P5GE_PHY)	+= mtk-2p5ge.o
 obj-$(CONFIG_MEDIATEK_GE_PHY)		+= mtk-ge.o
 obj-$(CONFIG_MEDIATEK_GE_SOC_PHY)	+= mtk-ge-soc.o
+obj-$(CONFIG_MTK_NET_PHYLIB)		+= mtk-phy-lib.o
diff --git a/drivers/net/phy/mediatek/mtk-2p5ge.c b/drivers/net/phy/mediatek/mtk-2p5ge.c
new file mode 100644
index 000000000000..e147eab523ef
--- /dev/null
+++ b/drivers/net/phy/mediatek/mtk-2p5ge.c
@@ -0,0 +1,321 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <linux/bitfield.h>
+#include <linux/firmware.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/phy.h>
+
+#include "mtk.h"
+
+#define MTK_2P5GPHY_ID_MT7988		0x00339c11
+
+#define MT7988_2P5GE_PMB_FW		"mediatek/mt7988/i2p5ge-phy-pmb.bin"
+#define MT7988_2P5GE_PMB_FW_SIZE	0x20000
+#define MT7988_2P5GE_PMB_FW_BASE	0x0f100000
+#define MT7988_2P5GE_PMB_FW_LEN		0x20000
+#define MTK_2P5GPHY_MCU_CSR_BASE	0x0f0f0000
+#define MTK_2P5GPHY_MCU_CSR_LEN		0x20
+#define MD32_EN_CFG			0x18
+#define   MD32_EN			BIT(0)
+
+#define BASE100T_STATUS_EXTEND		0x10
+#define BASE1000T_STATUS_EXTEND		0x11
+#define EXTEND_CTRL_AND_STATUS		0x16
+
+#define PHY_AUX_CTRL_STATUS		0x1d
+#define   PHY_AUX_DPX_MASK		GENMASK(5, 5)
+#define   PHY_AUX_SPEED_MASK		GENMASK(4, 2)
+
+/* Registers on MDIO_MMD_VEND1 */
+#define MTK_PHY_LPI_PCS_DSP_CTRL		0x121
+#define   MTK_PHY_LPI_SIG_EN_LO_THRESH100_MASK	GENMASK(12, 8)
+
+#define MTK_PHY_HOST_CMD1		0x800e
+#define MTK_PHY_HOST_CMD2		0x800f
+/* Registers on Token Ring debug nodes */
+/* ch_addr = 0x0, node_addr = 0xf, data_addr = 0x3c */
+#define AUTO_NP_10XEN				BIT(6)
+
+enum {
+	PHY_AUX_SPD_10 = 0,
+	PHY_AUX_SPD_100,
+	PHY_AUX_SPD_1000,
+	PHY_AUX_SPD_2500,
+};
+
+static int mt798x_2p5ge_phy_load_fw(struct phy_device *phydev)
+{
+	struct device *dev = &phydev->mdio.dev;
+	void __iomem *mcu_csr_base, *pmb_addr;
+	const struct firmware *fw;
+	int ret, i;
+	u32 reg;
+
+	pmb_addr = ioremap(MT7988_2P5GE_PMB_FW_BASE, MT7988_2P5GE_PMB_FW_LEN);
+	if (!pmb_addr)
+		return -ENOMEM;
+	mcu_csr_base = ioremap(MTK_2P5GPHY_MCU_CSR_BASE,
+			       MTK_2P5GPHY_MCU_CSR_LEN);
+	if (!mcu_csr_base) {
+		ret = -ENOMEM;
+		goto free_pmb;
+	}
+
+	ret = request_firmware_direct(&fw, MT7988_2P5GE_PMB_FW, dev);
+	if (ret) {
+		dev_err(dev, "failed to load firmware: %s, ret: %d\n",
+			MT7988_2P5GE_PMB_FW, ret);
+		goto free;
+	}
+
+	if (fw->size != MT7988_2P5GE_PMB_FW_SIZE) {
+		dev_err(dev, "Firmware size 0x%zx != 0x%x\n",
+			fw->size, MT7988_2P5GE_PMB_FW_SIZE);
+		ret = -EINVAL;
+		goto release_fw;
+	}
+
+	reg = readw(mcu_csr_base + MD32_EN_CFG);
+	if (reg & MD32_EN) {
+		phy_set_bits(phydev, MII_BMCR, BMCR_RESET);
+		usleep_range(10000, 11000);
+	}
+	phy_set_bits(phydev, MII_BMCR, BMCR_PDOWN);
+
+	/* Write magic number to safely stall MCU */
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_HOST_CMD1, 0x1100);
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_HOST_CMD2, 0x00df);
+
+	for (i = 0; i < MT7988_2P5GE_PMB_FW_SIZE - 1; i += 4)
+		writel(*((uint32_t *)(fw->data + i)), pmb_addr + i);
+
+	writew(reg & ~MD32_EN, mcu_csr_base + MD32_EN_CFG);
+	writew(reg | MD32_EN, mcu_csr_base + MD32_EN_CFG);
+	phy_set_bits(phydev, MII_BMCR, BMCR_RESET);
+	/* We need a delay here to stabilize initialization of MCU */
+	usleep_range(7000, 8000);
+
+	dev_info(dev, "Firmware date code: %x/%x/%x, version: %x.%x\n",
+		 be16_to_cpu(*((__be16 *)(fw->data +
+					  MT7988_2P5GE_PMB_FW_SIZE - 8))),
+		 *(fw->data + MT7988_2P5GE_PMB_FW_SIZE - 6),
+		 *(fw->data + MT7988_2P5GE_PMB_FW_SIZE - 5),
+		 *(fw->data + MT7988_2P5GE_PMB_FW_SIZE - 2),
+		 *(fw->data + MT7988_2P5GE_PMB_FW_SIZE - 1));
+
+release_fw:
+	release_firmware(fw);
+free:
+	iounmap(mcu_csr_base);
+free_pmb:
+	iounmap(pmb_addr);
+
+	return ret;
+}
+
+static int mt798x_2p5ge_phy_config_init(struct phy_device *phydev)
+{
+	/* Check if PHY interface type is compatible */
+	if (phydev->interface != PHY_INTERFACE_MODE_INTERNAL)
+		return -ENODEV;
+
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_LPI_PCS_DSP_CTRL,
+		       MTK_PHY_LPI_SIG_EN_LO_THRESH100_MASK, 0);
+
+	/* Enable 16-bit next page exchange bit if 1000-BT isn't advertising */
+	mtk_tr_modify(phydev, 0x0, 0xf, 0x3c, AUTO_NP_10XEN,
+		      FIELD_PREP(AUTO_NP_10XEN, 0x1));
+
+	/* Enable HW auto downshift */
+	phy_modify_paged(phydev, MTK_PHY_PAGE_EXTENDED_1,
+			 MTK_PHY_AUX_CTRL_AND_STATUS,
+			 0, MTK_PHY_ENABLE_DOWNSHIFT);
+
+	return 0;
+}
+
+static int mt798x_2p5ge_phy_config_aneg(struct phy_device *phydev)
+{
+	bool changed = false;
+	u32 adv;
+	int ret;
+
+	ret = genphy_c45_an_config_aneg(phydev);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		changed = true;
+
+	/* Clause 45 doesn't define 1000BaseT support. Use Clause 22 instead in
+	 * our design.
+	 */
+	adv = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising);
+	ret = phy_modify_changed(phydev, MII_CTRL1000, ADVERTISE_1000FULL, adv);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		changed = true;
+
+	return genphy_c45_check_and_restart_aneg(phydev, changed);
+}
+
+static int mt798x_2p5ge_phy_get_features(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_c45_pma_read_abilities(phydev);
+	if (ret)
+		return ret;
+
+	/* This phy can't handle collision, and neither can (XFI)MAC it's
+	 * connected to. Although it can do HDX handshake, it doesn't support
+	 * CSMA/CD that HDX requires.
+	 */
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+			   phydev->supported);
+
+	return 0;
+}
+
+static int mt798x_2p5ge_phy_read_status(struct phy_device *phydev)
+{
+	int ret;
+
+	/* When MDIO_STAT1_LSTATUS is raised genphy_c45_read_link(), this phy
+	 * actually hasn't finished AN. So use CL22's link update function
+	 * instead.
+	 */
+	ret = genphy_update_link(phydev);
+	if (ret)
+		return ret;
+
+	phydev->speed = SPEED_UNKNOWN;
+	phydev->duplex = DUPLEX_UNKNOWN;
+	phydev->pause = 0;
+	phydev->asym_pause = 0;
+
+	/* We'll read link speed through vendor specific registers down below.
+	 * So remove phy_resolve_aneg_linkmode (AN on) & genphy_c45_read_pma
+	 * (AN off).
+	 */
+	if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) {
+		ret = genphy_c45_read_lpa(phydev);
+		if (ret < 0)
+			return ret;
+
+		/* Clause 45 doesn't define 1000BaseT support. Read the link
+		 * partner's 1G advertisement via Clause 22.
+		 */
+		ret = phy_read(phydev, MII_STAT1000);
+		if (ret < 0)
+			return ret;
+		mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, ret);
+	} else if (phydev->autoneg == AUTONEG_DISABLE) {
+		linkmode_zero(phydev->lp_advertising);
+	}
+
+	if (phydev->link) {
+		ret = phy_read(phydev, PHY_AUX_CTRL_STATUS);
+		if (ret < 0)
+			return ret;
+
+		switch (FIELD_GET(PHY_AUX_SPEED_MASK, ret)) {
+		case PHY_AUX_SPD_10:
+			phydev->speed = SPEED_10;
+			break;
+		case PHY_AUX_SPD_100:
+			phydev->speed = SPEED_100;
+			break;
+		case PHY_AUX_SPD_1000:
+			phydev->speed = SPEED_1000;
+			break;
+		case PHY_AUX_SPD_2500:
+			phydev->speed = SPEED_2500;
+			break;
+		}
+
+		phydev->duplex = DUPLEX_FULL;
+		phydev->rate_matching = RATE_MATCH_PAUSE;
+	}
+
+	return 0;
+}
+
+static int mt798x_2p5ge_phy_get_rate_matching(struct phy_device *phydev,
+					      phy_interface_t iface)
+{
+	return RATE_MATCH_PAUSE;
+}
+
+static int mt798x_2p5ge_phy_probe(struct phy_device *phydev)
+{
+	struct pinctrl *pinctrl;
+	int ret;
+
+	switch (phydev->drv->phy_id) {
+	case MTK_2P5GPHY_ID_MT7988:
+		/* This built-in 2.5GbE hardware only sets MDIO_DEVS_PMAPMD.
+		 * Set the rest by this driver since PCS/AN/VEND1/VEND2 MDIO
+		 * manageable devices actually exist.
+		 */
+		phydev->c45_ids.mmds_present |= MDIO_DEVS_PCS |
+						MDIO_DEVS_AN |
+						MDIO_DEVS_VEND1 |
+						MDIO_DEVS_VEND2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = mt798x_2p5ge_phy_load_fw(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* Setup LED */
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, MTK_PHY_LED0_ON_CTRL,
+			 MTK_PHY_LED_ON_POLARITY | MTK_PHY_LED_ON_LINK10 |
+			 MTK_PHY_LED_ON_LINK100 | MTK_PHY_LED_ON_LINK1000 |
+			 MTK_PHY_LED_ON_LINK2500);
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, MTK_PHY_LED1_ON_CTRL,
+			 MTK_PHY_LED_ON_FDX | MTK_PHY_LED_ON_HDX);
+
+	/* Switch pinctrl after setting polarity to avoid bogus blinking */
+	pinctrl = devm_pinctrl_get_select(&phydev->mdio.dev, "i2p5gbe-led");
+	if (IS_ERR(pinctrl))
+		dev_err(&phydev->mdio.dev, "Fail to set LED pins!\n");
+
+	return 0;
+}
+
+static struct phy_driver mtk_2p5gephy_driver[] = {
+	{
+		PHY_ID_MATCH_MODEL(MTK_2P5GPHY_ID_MT7988),
+		.name = "MediaTek MT7988 2.5GbE PHY",
+		.probe = mt798x_2p5ge_phy_probe,
+		.config_init = mt798x_2p5ge_phy_config_init,
+		.config_aneg = mt798x_2p5ge_phy_config_aneg,
+		.get_features = mt798x_2p5ge_phy_get_features,
+		.read_status = mt798x_2p5ge_phy_read_status,
+		.get_rate_matching = mt798x_2p5ge_phy_get_rate_matching,
+		.suspend = genphy_suspend,
+		.resume = genphy_resume,
+		.read_page = mtk_phy_read_page,
+		.write_page = mtk_phy_write_page,
+	},
+};
+
+module_phy_driver(mtk_2p5gephy_driver);
+
+static struct mdio_device_id __maybe_unused mtk_2p5ge_phy_tbl[] = {
+	{ PHY_ID_MATCH_VENDOR(0x00339c00) },
+	{ }
+};
+
+MODULE_DESCRIPTION("MediaTek 2.5Gb Ethernet PHY driver");
+MODULE_AUTHOR("SkyLake Huang <SkyLake.Huang@mediatek.com>");
+MODULE_LICENSE("GPL");
+
+MODULE_DEVICE_TABLE(mdio, mtk_2p5ge_phy_tbl);
+MODULE_FIRMWARE(MT7988_2P5GE_PMB_FW);
diff --git a/drivers/net/phy/mediatek/mtk-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c
index 175cf5239bba..a284e8435cb6 100644
--- a/drivers/net/phy/mediatek/mtk-ge-soc.c
+++ b/drivers/net/phy/mediatek/mtk-ge-soc.c
@@ -7,12 +7,16 @@
 #include <linux/pinctrl/consumer.h>
 #include <linux/phy.h>
 #include <linux/regmap.h>
+#include <linux/of.h>
 
 #include "../phylib.h"
 #include "mtk.h"
 
+#define MTK_PHY_MAX_LEDS			2
+
 #define MTK_GPHY_ID_MT7981			0x03a29461
 #define MTK_GPHY_ID_MT7988			0x03a29481
+#define MTK_GPHY_ID_AN7581			0x03a294c1
 
 #define MTK_EXT_PAGE_ACCESS			0x1f
 #define MTK_PHY_PAGE_STANDARD			0x0000
@@ -1319,6 +1323,7 @@ static int mt7988_phy_probe_shared(struct phy_device *phydev)
 {
 	struct device_node *np = dev_of_node(&phydev->mdio.bus->dev);
 	struct mtk_socphy_shared *shared = phy_package_get_priv(phydev);
+	struct device_node *pio_np;
 	struct regmap *regmap;
 	u32 reg;
 	int ret;
@@ -1336,7 +1341,13 @@ static int mt7988_phy_probe_shared(struct phy_device *phydev)
 	 * The 4 bits in TPBANK0 are kept as package shared data and are used to
 	 * set LED polarity for each of the LED0.
 	 */
-	regmap = syscon_regmap_lookup_by_phandle(np, "mediatek,pio");
+	pio_np = of_parse_phandle(np, "mediatek,pio", 0);
+	if (!pio_np)
+		return -ENODEV;
+
+	regmap = device_node_to_regmap(pio_np);
+	of_node_put(pio_np);
+
 	if (IS_ERR(regmap))
 		return PTR_ERR(regmap);
 
@@ -1406,6 +1417,52 @@ static int mt7981_phy_probe(struct phy_device *phydev)
 	return mt798x_phy_calibration(phydev);
 }
 
+static int an7581_phy_probe(struct phy_device *phydev)
+{
+	struct mtk_socphy_priv *priv;
+	struct pinctrl *pinctrl;
+
+	/* Toggle pinctrl to enable PHY LED */
+	pinctrl = devm_pinctrl_get_select(&phydev->mdio.dev, "gbe-led");
+	if (IS_ERR(pinctrl))
+		dev_err(&phydev->mdio.bus->dev,
+			"Failed to setup PHY LED pinctrl\n");
+
+	priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	phydev->priv = priv;
+
+	return 0;
+}
+
+static int an7581_phy_led_polarity_set(struct phy_device *phydev, int index,
+				       unsigned long modes)
+{
+	u16 val = 0;
+	u32 mode;
+
+	if (index >= MTK_PHY_MAX_LEDS)
+		return -EINVAL;
+
+	for_each_set_bit(mode, &modes, __PHY_LED_MODES_NUM) {
+		switch (mode) {
+		case PHY_LED_ACTIVE_LOW:
+			val = MTK_PHY_LED_ON_POLARITY;
+			break;
+		case PHY_LED_ACTIVE_HIGH:
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND2, index ?
+			      MTK_PHY_LED1_ON_CTRL : MTK_PHY_LED0_ON_CTRL,
+			      MTK_PHY_LED_ON_POLARITY, val);
+}
+
 static struct phy_driver mtk_socphy_driver[] = {
 	{
 		PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7981),
@@ -1441,6 +1498,17 @@ static struct phy_driver mtk_socphy_driver[] = {
 		.led_hw_control_set = mt798x_phy_led_hw_control_set,
 		.led_hw_control_get = mt798x_phy_led_hw_control_get,
 	},
+	{
+		PHY_ID_MATCH_EXACT(MTK_GPHY_ID_AN7581),
+		.name		= "Airoha AN7581 PHY",
+		.probe		= an7581_phy_probe,
+		.led_blink_set	= mt798x_phy_led_blink_set,
+		.led_brightness_set = mt798x_phy_led_brightness_set,
+		.led_hw_is_supported = mt798x_phy_led_hw_is_supported,
+		.led_hw_control_set = mt798x_phy_led_hw_control_set,
+		.led_hw_control_get = mt798x_phy_led_hw_control_get,
+		.led_polarity_set = an7581_phy_led_polarity_set,
+	},
 };
 
 module_phy_driver(mtk_socphy_driver);
@@ -1448,6 +1516,7 @@ module_phy_driver(mtk_socphy_driver);
 static const struct mdio_device_id __maybe_unused mtk_socphy_tbl[] = {
 	{ PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7981) },
 	{ PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7988) },
+	{ PHY_ID_MATCH_EXACT(MTK_GPHY_ID_AN7581) },
 	{ }
 };
 
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 24882d30f685..64aa03aed770 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -768,7 +768,8 @@ static int ksz8051_ksz8795_match_phy_device(struct phy_device *phydev,
 		return !ret;
 }
 
-static int ksz8051_match_phy_device(struct phy_device *phydev)
+static int ksz8051_match_phy_device(struct phy_device *phydev,
+				    const struct phy_driver *phydrv)
 {
 	return ksz8051_ksz8795_match_phy_device(phydev, true);
 }
@@ -888,7 +889,8 @@ static int ksz8061_config_init(struct phy_device *phydev)
 	return kszphy_config_init(phydev);
 }
 
-static int ksz8795_match_phy_device(struct phy_device *phydev)
+static int ksz8795_match_phy_device(struct phy_device *phydev,
+				    const struct phy_driver *phydrv)
 {
 	return ksz8051_ksz8795_match_phy_device(phydev, false);
 }
@@ -2027,12 +2029,6 @@ static int ksz9477_config_init(struct phy_device *phydev)
 			return err;
 	}
 
-	/* According to KSZ9477 Errata DS80000754C (Module 4) all EEE modes
-	 * in this switch shall be regarded as broken.
-	 */
-	if (phydev->dev_flags & MICREL_NO_EEE)
-		phy_disable_eee(phydev);
-
 	return kszphy_config_init(phydev);
 }
 
@@ -3236,10 +3232,6 @@ static int lan8814_ptp_perout(struct ptp_clock_info *ptpci,
 	int pulse_width;
 	int pin, event;
 
-	/* Reject requests with unsupported flags */
-	if (rq->perout.flags & ~PTP_PEROUT_DUTY_CYCLE)
-		return -EOPNOTSUPP;
-
 	mutex_lock(&shared->shared_lock);
 	event = rq->perout.index;
 	pin = ptp_find_pin(shared->ptp_clock, PTP_PF_PEROUT, event);
@@ -3406,11 +3398,6 @@ static int lan8814_ptp_extts(struct ptp_clock_info *ptpci,
 	struct phy_device *phydev = shared->phydev;
 	int pin;
 
-	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-				PTP_EXTTS_EDGES |
-				PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	pin = ptp_find_pin(shared->ptp_clock, PTP_PF_EXTTS,
 			   rq->extts.index);
 	if (pin == -1 || pin != LAN8814_PTP_EXTTS_NUM)
@@ -3917,6 +3904,10 @@ static int lan8814_ptp_probe_once(struct phy_device *phydev)
 	shared->ptp_clock_info.n_ext_ts = LAN8814_PTP_EXTTS_NUM;
 	shared->ptp_clock_info.n_pins = LAN8814_PTP_GPIO_NUM;
 	shared->ptp_clock_info.pps = 0;
+	shared->ptp_clock_info.supported_extts_flags = PTP_RISING_EDGE |
+						       PTP_FALLING_EDGE |
+						       PTP_STRICT_FLAGS;
+	shared->ptp_clock_info.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE;
 	shared->ptp_clock_info.pin_config = shared->pin_config;
 	shared->ptp_clock_info.n_per_out = LAN8814_PTP_PEROUT_NUM;
 	shared->ptp_clock_info.adjfine = lan8814_ptpci_adjfine;
@@ -5068,9 +5059,6 @@ static int lan8841_ptp_perout(struct ptp_clock_info *ptp,
 	int pin;
 	int ret;
 
-	if (rq->perout.flags & ~PTP_PEROUT_DUTY_CYCLE)
-		return -EOPNOTSUPP;
-
 	pin = ptp_find_pin(ptp_priv->ptp_clock, PTP_PF_PEROUT, rq->perout.index);
 	if (pin == -1 || pin >= LAN8841_PTP_GPIO_NUM)
 		return -EINVAL;
@@ -5314,6 +5302,7 @@ static struct ptp_clock_info lan8841_ptp_clock_info = {
 	.n_per_out      = LAN8841_PTP_GPIO_NUM,
 	.n_ext_ts       = LAN8841_PTP_GPIO_NUM,
 	.n_pins         = LAN8841_PTP_GPIO_NUM,
+	.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE,
 };
 
 #define LAN8841_OPERATION_MODE_STRAP_LOW_REGISTER 3
@@ -5705,7 +5694,6 @@ static struct phy_driver ksphy_driver[] = {
 	.handle_interrupt = kszphy_handle_interrupt,
 	.suspend	= genphy_suspend,
 	.resume		= ksz9477_resume,
-	.get_features	= ksz9477_get_features,
 } };
 
 module_phy_driver(ksphy_driver);
diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 0e17cc458efd..13570f628aa5 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -37,47 +37,6 @@ static int lan88xx_write_page(struct phy_device *phydev, int page)
 	return __phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, page);
 }
 
-static int lan88xx_phy_config_intr(struct phy_device *phydev)
-{
-	int rc;
-
-	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
-		/* unmask all source and clear them before enable */
-		rc = phy_write(phydev, LAN88XX_INT_MASK, 0x7FFF);
-		rc = phy_read(phydev, LAN88XX_INT_STS);
-		rc = phy_write(phydev, LAN88XX_INT_MASK,
-			       LAN88XX_INT_MASK_MDINTPIN_EN_ |
-			       LAN88XX_INT_MASK_LINK_CHANGE_);
-	} else {
-		rc = phy_write(phydev, LAN88XX_INT_MASK, 0);
-		if (rc)
-			return rc;
-
-		/* Ack interrupts after they have been disabled */
-		rc = phy_read(phydev, LAN88XX_INT_STS);
-	}
-
-	return rc < 0 ? rc : 0;
-}
-
-static irqreturn_t lan88xx_handle_interrupt(struct phy_device *phydev)
-{
-	int irq_status;
-
-	irq_status = phy_read(phydev, LAN88XX_INT_STS);
-	if (irq_status < 0) {
-		phy_error(phydev);
-		return IRQ_NONE;
-	}
-
-	if (!(irq_status & LAN88XX_INT_STS_LINK_CHANGE_))
-		return IRQ_NONE;
-
-	phy_trigger_machine(phydev);
-
-	return IRQ_HANDLED;
-}
-
 static int lan88xx_suspend(struct phy_device *phydev)
 {
 	struct lan88xx_priv *priv = phydev->priv;
@@ -515,6 +474,8 @@ static struct phy_driver microchip_phy_driver[] = {
 	/* This mask (0xfffffff2) is to differentiate from
 	 * LAN8742 (phy_id 0x0007c130 and 0x0007c131)
 	 * and allows future phy_id revisions.
+	 * These PHYs are integrated in LAN7800 and LAN7850 USB/Ethernet
+	 * controllers.
 	 */
 	.phy_id_mask	= 0xfffffff2,
 	.name		= "Microchip LAN88xx",
@@ -528,8 +489,9 @@ static struct phy_driver microchip_phy_driver[] = {
 	.config_aneg	= lan88xx_config_aneg,
 	.link_change_notify = lan88xx_link_change_notify,
 
-	.config_intr	= lan88xx_phy_config_intr,
-	.handle_interrupt = lan88xx_handle_interrupt,
+	/* Interrupt handling is broken, do not define related
+	 * functions to force polling.
+	 */
 
 	.suspend	= lan88xx_suspend,
 	.resume		= genphy_resume,
diff --git a/drivers/net/phy/microchip_rds_ptp.c b/drivers/net/phy/microchip_rds_ptp.c
index 3e6bf10cdeed..e6514ce04c29 100644
--- a/drivers/net/phy/microchip_rds_ptp.c
+++ b/drivers/net/phy/microchip_rds_ptp.c
@@ -224,10 +224,6 @@ static int mchp_rds_ptp_perout(struct ptp_clock_info *ptpci,
 	struct phy_device *phydev = clock->phydev;
 	int ret, event_pin, pulsewidth;
 
-	/* Reject requests with unsupported flags */
-	if (perout->flags & ~PTP_PEROUT_DUTY_CYCLE)
-		return -EOPNOTSUPP;
-
 	event_pin = ptp_find_pin(clock->ptp_clock, PTP_PF_PEROUT,
 				 perout->index);
 	if (event_pin != clock->event_pin)
@@ -1259,6 +1255,7 @@ struct mchp_rds_ptp_clock *mchp_rds_ptp_probe(struct phy_device *phydev, u8 mmd,
 	clock->caps.pps            = 0;
 	clock->caps.n_pins         = MCHP_RDS_PTP_N_PIN;
 	clock->caps.n_per_out      = MCHP_RDS_PTP_N_PEROUT;
+	clock->caps.supported_perout_flags = PTP_PEROUT_DUTY_CYCLE;
 	clock->caps.pin_config     = clock->pin_config;
 	clock->caps.adjfine        = mchp_rds_ptp_ltc_adjfine;
 	clock->caps.adjtime        = mchp_rds_ptp_ltc_adjtime;
diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 250a018d5546..4c6d905f0a9f 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -19,7 +19,6 @@
 
 #include "nxp-c45-tja11xx.h"
 
-#define PHY_ID_MASK			GENMASK(31, 4)
 /* Same id: TJA1103, TJA1104 */
 #define PHY_ID_TJA_1103			0x001BB010
 /* Same id: TJA1120, TJA1121 */
@@ -763,9 +762,6 @@ static int nxp_c45_perout_enable(struct nxp_c45_phy *priv,
 	struct phy_device *phydev = priv->phydev;
 	int pin;
 
-	if (perout->flags & ~PTP_PEROUT_PHASE)
-		return -EOPNOTSUPP;
-
 	pin = ptp_find_pin(priv->ptp_clock, PTP_PF_PEROUT, perout->index);
 	if (pin < 0)
 		return pin;
@@ -861,12 +857,6 @@ static int nxp_c45_extts_enable(struct nxp_c45_phy *priv,
 	const struct nxp_c45_phy_data *data = nxp_c45_get_data(priv->phydev);
 	int pin;
 
-	if (extts->flags & ~(PTP_ENABLE_FEATURE |
-			      PTP_RISING_EDGE |
-			      PTP_FALLING_EDGE |
-			      PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
 	/* Sampling on both edges is not supported */
 	if ((extts->flags & PTP_RISING_EDGE) &&
 	    (extts->flags & PTP_FALLING_EDGE) &&
@@ -962,6 +952,10 @@ static int nxp_c45_init_ptp_clock(struct nxp_c45_phy *priv)
 		.n_pins		= ARRAY_SIZE(nxp_c45_ptp_pins),
 		.n_ext_ts	= 1,
 		.n_per_out	= 1,
+		.supported_extts_flags = PTP_RISING_EDGE |
+					 PTP_FALLING_EDGE |
+					 PTP_STRICT_FLAGS,
+		.supported_perout_flags = PTP_PEROUT_PHASE,
 	};
 
 	priv->ptp_clock = ptp_clock_register(&priv->caps,
@@ -1971,28 +1965,24 @@ static int nxp_c45_macsec_ability(struct phy_device *phydev)
 	return macsec_ability;
 }
 
-static int tja1103_match_phy_device(struct phy_device *phydev)
+static int tja11xx_no_macsec_match_phy_device(struct phy_device *phydev,
+					      const struct phy_driver *phydrv)
 {
-	return phy_id_compare(phydev->phy_id, PHY_ID_TJA_1103, PHY_ID_MASK) &&
-	       !nxp_c45_macsec_ability(phydev);
-}
+	if (!phy_id_compare(phydev->phy_id, phydrv->phy_id,
+			    phydrv->phy_id_mask))
+		return 0;
 
-static int tja1104_match_phy_device(struct phy_device *phydev)
-{
-	return phy_id_compare(phydev->phy_id, PHY_ID_TJA_1103, PHY_ID_MASK) &&
-	       nxp_c45_macsec_ability(phydev);
+	return !nxp_c45_macsec_ability(phydev);
 }
 
-static int tja1120_match_phy_device(struct phy_device *phydev)
+static int tja11xx_macsec_match_phy_device(struct phy_device *phydev,
+					   const struct phy_driver *phydrv)
 {
-	return phy_id_compare(phydev->phy_id, PHY_ID_TJA_1120, PHY_ID_MASK) &&
-	       !nxp_c45_macsec_ability(phydev);
-}
+	if (!phy_id_compare(phydev->phy_id, phydrv->phy_id,
+			    phydrv->phy_id_mask))
+		return 0;
 
-static int tja1121_match_phy_device(struct phy_device *phydev)
-{
-	return phy_id_compare(phydev->phy_id, PHY_ID_TJA_1120, PHY_ID_MASK) &&
-	       nxp_c45_macsec_ability(phydev);
+	return nxp_c45_macsec_ability(phydev);
 }
 
 static const struct nxp_c45_regmap tja1120_regmap = {
@@ -2065,6 +2055,7 @@ static const struct nxp_c45_phy_data tja1120_phy_data = {
 
 static struct phy_driver nxp_c45_driver[] = {
 	{
+		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103),
 		.name			= "NXP C45 TJA1103",
 		.get_features		= nxp_c45_get_features,
 		.driver_data		= &tja1103_phy_data,
@@ -2086,9 +2077,10 @@ static struct phy_driver nxp_c45_driver[] = {
 		.get_sqi		= nxp_c45_get_sqi,
 		.get_sqi_max		= nxp_c45_get_sqi_max,
 		.remove			= nxp_c45_remove,
-		.match_phy_device	= tja1103_match_phy_device,
+		.match_phy_device	= tja11xx_no_macsec_match_phy_device,
 	},
 	{
+		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103),
 		.name			= "NXP C45 TJA1104",
 		.get_features		= nxp_c45_get_features,
 		.driver_data		= &tja1103_phy_data,
@@ -2110,9 +2102,10 @@ static struct phy_driver nxp_c45_driver[] = {
 		.get_sqi		= nxp_c45_get_sqi,
 		.get_sqi_max		= nxp_c45_get_sqi_max,
 		.remove			= nxp_c45_remove,
-		.match_phy_device	= tja1104_match_phy_device,
+		.match_phy_device	= tja11xx_macsec_match_phy_device,
 	},
 	{
+		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1120),
 		.name			= "NXP C45 TJA1120",
 		.get_features		= nxp_c45_get_features,
 		.driver_data		= &tja1120_phy_data,
@@ -2135,9 +2128,10 @@ static struct phy_driver nxp_c45_driver[] = {
 		.get_sqi		= nxp_c45_get_sqi,
 		.get_sqi_max		= nxp_c45_get_sqi_max,
 		.remove			= nxp_c45_remove,
-		.match_phy_device	= tja1120_match_phy_device,
+		.match_phy_device	= tja11xx_no_macsec_match_phy_device,
 	},
 	{
+		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1120),
 		.name			= "NXP C45 TJA1121",
 		.get_features		= nxp_c45_get_features,
 		.driver_data		= &tja1120_phy_data,
@@ -2160,7 +2154,7 @@ static struct phy_driver nxp_c45_driver[] = {
 		.get_sqi		= nxp_c45_get_sqi,
 		.get_sqi_max		= nxp_c45_get_sqi_max,
 		.remove			= nxp_c45_remove,
-		.match_phy_device	= tja1121_match_phy_device,
+		.match_phy_device	= tja11xx_macsec_match_phy_device,
 	},
 };
 
diff --git a/drivers/net/phy/nxp-tja11xx.c b/drivers/net/phy/nxp-tja11xx.c
index 07e94a2478ac..3c38a8ddae2f 100644
--- a/drivers/net/phy/nxp-tja11xx.c
+++ b/drivers/net/phy/nxp-tja11xx.c
@@ -651,12 +651,14 @@ static int tja1102_match_phy_device(struct phy_device *phydev, bool port0)
 	return !ret;
 }
 
-static int tja1102_p0_match_phy_device(struct phy_device *phydev)
+static int tja1102_p0_match_phy_device(struct phy_device *phydev,
+				       const struct phy_driver *phydrv)
 {
 	return tja1102_match_phy_device(phydev, true);
 }
 
-static int tja1102_p1_match_phy_device(struct phy_device *phydev)
+static int tja1102_p1_match_phy_device(struct phy_device *phydev,
+				       const struct phy_driver *phydrv)
 {
 	return tja1102_match_phy_device(phydev, false);
 }
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index cc1bfd22fb81..0f6f86252622 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -543,20 +543,26 @@ static int phy_scan_fixups(struct phy_device *phydev)
 	return 0;
 }
 
-static int phy_bus_match(struct device *dev, const struct device_driver *drv)
+/**
+ * genphy_match_phy_device - match a PHY device with a PHY driver
+ * @phydev: target phy_device struct
+ * @phydrv: target phy_driver struct
+ *
+ * Description: Checks whether the given PHY device matches the specified
+ * PHY driver. For Clause 45 PHYs, iterates over the available device
+ * identifiers and compares them against the driver's expected PHY ID,
+ * applying the provided mask. For Clause 22 PHYs, a direct ID comparison
+ * is performed.
+ *
+ * Return: 1 if the PHY device matches the driver, 0 otherwise.
+ */
+int genphy_match_phy_device(struct phy_device *phydev,
+			    const struct phy_driver *phydrv)
 {
-	struct phy_device *phydev = to_phy_device(dev);
-	const struct phy_driver *phydrv = to_phy_driver(drv);
-	const int num_ids = ARRAY_SIZE(phydev->c45_ids.device_ids);
-	int i;
-
-	if (!(phydrv->mdiodrv.flags & MDIO_DEVICE_IS_PHY))
-		return 0;
-
-	if (phydrv->match_phy_device)
-		return phydrv->match_phy_device(phydev);
-
 	if (phydev->is_c45) {
+		const int num_ids = ARRAY_SIZE(phydev->c45_ids.device_ids);
+		int i;
+
 		for (i = 1; i < num_ids; i++) {
 			if (phydev->c45_ids.device_ids[i] == 0xffffffff)
 				continue;
@@ -565,11 +571,27 @@ static int phy_bus_match(struct device *dev, const struct device_driver *drv)
 					   phydrv->phy_id, phydrv->phy_id_mask))
 				return 1;
 		}
+
 		return 0;
-	} else {
-		return phy_id_compare(phydev->phy_id, phydrv->phy_id,
-				      phydrv->phy_id_mask);
 	}
+
+	return phy_id_compare(phydev->phy_id, phydrv->phy_id,
+			      phydrv->phy_id_mask);
+}
+EXPORT_SYMBOL_GPL(genphy_match_phy_device);
+
+static int phy_bus_match(struct device *dev, const struct device_driver *drv)
+{
+	struct phy_device *phydev = to_phy_device(dev);
+	const struct phy_driver *phydrv = to_phy_driver(drv);
+
+	if (!(phydrv->mdiodrv.flags & MDIO_DEVICE_IS_PHY))
+		return 0;
+
+	if (phydrv->match_phy_device)
+		return phydrv->match_phy_device(phydev, phydrv);
+
+	return genphy_match_phy_device(phydev, phydrv);
 }
 
 static ssize_t
@@ -2975,6 +2997,21 @@ int phy_get_tx_amplitude_gain(struct phy_device *phydev, struct device *dev,
 }
 EXPORT_SYMBOL_GPL(phy_get_tx_amplitude_gain);
 
+/**
+ * phy_get_mac_termination - stores MAC termination in @val
+ * @phydev: phy_device struct
+ * @dev: pointer to the devices device struct
+ * @val: MAC termination
+ *
+ * Returns: 0 on success, < 0 on failure
+ */
+int phy_get_mac_termination(struct phy_device *phydev, struct device *dev,
+			    u32 *val)
+{
+	return phy_get_u32_property(dev, "mac-termination-ohms", val);
+}
+EXPORT_SYMBOL_GPL(phy_get_mac_termination);
+
 static int phy_led_set_brightness(struct led_classdev *led_cdev,
 				  enum led_brightness value)
 {
@@ -3236,18 +3273,6 @@ struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode)
 EXPORT_SYMBOL(fwnode_phy_find_device);
 
 /**
- * device_phy_find_device - For the given device, get the phy_device
- * @dev: Pointer to the given device
- *
- * Refer return conditions of fwnode_phy_find_device().
- */
-struct phy_device *device_phy_find_device(struct device *dev)
-{
-	return fwnode_phy_find_device(dev_fwnode(dev));
-}
-EXPORT_SYMBOL_GPL(device_phy_find_device);
-
-/**
  * fwnode_get_phy_node - Get the phy_node using the named reference.
  * @fwnode: Pointer to fwnode from which phy_node has to be obtained.
  *
@@ -3262,12 +3287,12 @@ struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode)
 
 	/* Only phy-handle is used for ACPI */
 	phy_node = fwnode_find_reference(fwnode, "phy-handle", 0);
-	if (is_acpi_node(fwnode) || !IS_ERR(phy_node))
+	if (!IS_ERR(phy_node) || is_acpi_node(fwnode))
 		return phy_node;
 	phy_node = fwnode_find_reference(fwnode, "phy", 0);
-	if (IS_ERR(phy_node))
-		phy_node = fwnode_find_reference(fwnode, "phy-device", 0);
-	return phy_node;
+	if (!IS_ERR(phy_node))
+		return phy_node;
+	return fwnode_find_reference(fwnode, "phy-device", 0);
 }
 EXPORT_SYMBOL_GPL(fwnode_get_phy_node);
 
@@ -3554,19 +3579,15 @@ static int __init phy_init(void)
 	phylib_register_stubs();
 	rtnl_unlock();
 
-	rc = mdio_bus_init();
-	if (rc)
-		goto err_ethtool_phy_ops;
-
 	rc = phy_caps_init();
 	if (rc)
-		goto err_mdio_bus;
+		goto err_ethtool_phy_ops;
 
 	features_init();
 
 	rc = phy_driver_register(&genphy_c45_driver, THIS_MODULE);
 	if (rc)
-		goto err_mdio_bus;
+		goto err_ethtool_phy_ops;
 
 	rc = phy_driver_register(&genphy_driver, THIS_MODULE);
 	if (rc)
@@ -3576,8 +3597,6 @@ static int __init phy_init(void)
 
 err_c45:
 	phy_driver_unregister(&genphy_c45_driver);
-err_mdio_bus:
-	mdio_bus_exit();
 err_ethtool_phy_ops:
 	rtnl_lock();
 	phylib_unregister_stubs();
@@ -3591,7 +3610,6 @@ static void __exit phy_exit(void)
 {
 	phy_driver_unregister(&genphy_c45_driver);
 	phy_driver_unregister(&genphy_driver);
-	mdio_bus_exit();
 	rtnl_lock();
 	phylib_unregister_stubs();
 	ethtool_set_ethtool_phy_ops(NULL);
diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c
index bd3c9554f6ac..60893691d4c3 100644
--- a/drivers/net/phy/phy_led_triggers.c
+++ b/drivers/net/phy/phy_led_triggers.c
@@ -93,9 +93,8 @@ int phy_led_triggers_register(struct phy_device *phy)
 	if (!phy->phy_num_led_triggers)
 		return 0;
 
-	phy->led_link_trigger = devm_kzalloc(&phy->mdio.dev,
-					     sizeof(*phy->led_link_trigger),
-					     GFP_KERNEL);
+	phy->led_link_trigger = kzalloc(sizeof(*phy->led_link_trigger),
+					GFP_KERNEL);
 	if (!phy->led_link_trigger) {
 		err = -ENOMEM;
 		goto out_clear;
@@ -105,10 +104,9 @@ int phy_led_triggers_register(struct phy_device *phy)
 	if (err)
 		goto out_free_link;
 
-	phy->phy_led_triggers = devm_kcalloc(&phy->mdio.dev,
-					    phy->phy_num_led_triggers,
-					    sizeof(struct phy_led_trigger),
-					    GFP_KERNEL);
+	phy->phy_led_triggers = kcalloc(phy->phy_num_led_triggers,
+					sizeof(struct phy_led_trigger),
+					GFP_KERNEL);
 	if (!phy->phy_led_triggers) {
 		err = -ENOMEM;
 		goto out_unreg_link;
@@ -129,11 +127,11 @@ int phy_led_triggers_register(struct phy_device *phy)
 out_unreg:
 	while (i--)
 		phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
-	devm_kfree(&phy->mdio.dev, phy->phy_led_triggers);
+	kfree(phy->phy_led_triggers);
 out_unreg_link:
 	phy_led_trigger_unregister(phy->led_link_trigger);
 out_free_link:
-	devm_kfree(&phy->mdio.dev, phy->led_link_trigger);
+	kfree(phy->led_link_trigger);
 	phy->led_link_trigger = NULL;
 out_clear:
 	phy->phy_num_led_triggers = 0;
@@ -147,8 +145,13 @@ void phy_led_triggers_unregister(struct phy_device *phy)
 
 	for (i = 0; i < phy->phy_num_led_triggers; i++)
 		phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
+	kfree(phy->phy_led_triggers);
+	phy->phy_led_triggers = NULL;
 
-	if (phy->led_link_trigger)
+	if (phy->led_link_trigger) {
 		phy_led_trigger_unregister(phy->led_link_trigger);
+		kfree(phy->led_link_trigger);
+		phy->led_link_trigger = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(phy_led_triggers_unregister);
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index b68369e2342b..0faa3d97e06b 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -24,13 +24,6 @@
 #include "sfp.h"
 #include "swphy.h"
 
-#define SUPPORTED_INTERFACES \
-	(SUPPORTED_TP | SUPPORTED_MII | SUPPORTED_FIBRE | \
-	 SUPPORTED_BNC | SUPPORTED_AUI | SUPPORTED_Backplane)
-#define ADVERTISED_INTERFACES \
-	(ADVERTISED_TP | ADVERTISED_MII | ADVERTISED_FIBRE | \
-	 ADVERTISED_BNC | ADVERTISED_AUI | ADVERTISED_Backplane)
-
 enum {
 	PHYLINK_DISABLE_STOPPED,
 	PHYLINK_DISABLE_LINK,
@@ -81,6 +74,7 @@ struct phylink {
 	unsigned int pcs_state;
 
 	bool link_failed;
+	bool suspend_link_up;
 	bool major_config_failed;
 	bool mac_supports_eee_ops;
 	bool mac_supports_eee;
@@ -2545,14 +2539,16 @@ void phylink_suspend(struct phylink *pl, bool mac_wol)
 		/* Stop the resolver bringing the link up */
 		__set_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state);
 
-		/* Disable the carrier, to prevent transmit timeouts,
-		 * but one would hope all packets have been sent. This
-		 * also means phylink_resolve() will do nothing.
-		 */
-		if (pl->netdev)
-			netif_carrier_off(pl->netdev);
-		else
+		pl->suspend_link_up = phylink_link_is_up(pl);
+		if (pl->suspend_link_up) {
+			/* Disable the carrier, to prevent transmit timeouts,
+			 * but one would hope all packets have been sent. This
+			 * also means phylink_resolve() will do nothing.
+			 */
+			if (pl->netdev)
+				netif_carrier_off(pl->netdev);
 			pl->old_link_state = false;
+		}
 
 		/* We do not call mac_link_down() here as we want the
 		 * link to remain up to receive the WoL packets.
@@ -2603,15 +2599,18 @@ void phylink_resume(struct phylink *pl)
 	if (test_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state)) {
 		/* Wake-on-Lan enabled, MAC handling */
 
-		/* Call mac_link_down() so we keep the overall state balanced.
-		 * Do this under the state_mutex lock for consistency. This
-		 * will cause a "Link Down" message to be printed during
-		 * resume, which is harmless - the true link state will be
-		 * printed when we run a resolve.
-		 */
-		mutex_lock(&pl->state_mutex);
-		phylink_link_down(pl);
-		mutex_unlock(&pl->state_mutex);
+		if (pl->suspend_link_up) {
+			/* Call mac_link_down() so we keep the overall state
+			 * balanced. Do this under the state_mutex lock for
+			 * consistency. This will cause a "Link Down" message
+			 * to be printed during resume, which is harmless -
+			 * the true link state will be printed when we run a
+			 * resolve.
+			 */
+			mutex_lock(&pl->state_mutex);
+			phylink_link_down(pl);
+			mutex_unlock(&pl->state_mutex);
+		}
 
 		/* Re-apply the link parameters so that all the settings get
 		 * restored to the MAC.
diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c
index 893c82479671..c3dcb6257430 100644
--- a/drivers/net/phy/realtek/realtek_main.c
+++ b/drivers/net/phy/realtek/realtek_main.c
@@ -10,6 +10,7 @@
 #include <linux/bitops.h>
 #include <linux/of.h>
 #include <linux/phy.h>
+#include <linux/netdevice.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/clk.h>
@@ -17,9 +18,15 @@
 
 #include "realtek.h"
 
-#define RTL821x_PHYSR				0x11
-#define RTL821x_PHYSR_DUPLEX			BIT(13)
-#define RTL821x_PHYSR_SPEED			GENMASK(15, 14)
+#define RTL8201F_IER				0x13
+
+#define RTL8201F_ISR				0x1e
+#define RTL8201F_ISR_ANERR			BIT(15)
+#define RTL8201F_ISR_DUPLEX			BIT(13)
+#define RTL8201F_ISR_LINK			BIT(11)
+#define RTL8201F_ISR_MASK			(RTL8201F_ISR_ANERR | \
+						 RTL8201F_ISR_DUPLEX | \
+						 RTL8201F_ISR_LINK)
 
 #define RTL821x_INER				0x12
 #define RTL8211B_INER_INIT			0x6400
@@ -29,15 +36,48 @@
 #define RTL821x_INSR				0x13
 
 #define RTL821x_EXT_PAGE_SELECT			0x1e
+
 #define RTL821x_PAGE_SELECT			0x1f
+#define RTL821x_SET_EXT_PAGE			0x07
+
+/* RTL8211E extension page 44/0x2c */
+#define RTL8211E_LEDCR_EXT_PAGE			0x2c
+#define RTL8211E_LEDCR1				0x1a
+#define RTL8211E_LEDCR1_ACT_TXRX		BIT(4)
+#define RTL8211E_LEDCR1_MASK			BIT(4)
+#define RTL8211E_LEDCR1_SHIFT			1
+
+#define RTL8211E_LEDCR2				0x1c
+#define RTL8211E_LEDCR2_LINK_1000		BIT(2)
+#define RTL8211E_LEDCR2_LINK_100		BIT(1)
+#define RTL8211E_LEDCR2_LINK_10			BIT(0)
+#define RTL8211E_LEDCR2_MASK			GENMASK(2, 0)
+#define RTL8211E_LEDCR2_SHIFT			4
+
+/* RTL8211E extension page 164/0xa4 */
+#define RTL8211E_RGMII_EXT_PAGE			0xa4
+#define RTL8211E_RGMII_DELAY			0x1c
+#define RTL8211E_CTRL_DELAY			BIT(13)
+#define RTL8211E_TX_DELAY			BIT(12)
+#define RTL8211E_RX_DELAY			BIT(11)
+#define RTL8211E_DELAY_MASK			GENMASK(13, 11)
 
+/* RTL8211F PHY configuration */
+#define RTL8211F_PHYCR_PAGE			0xa43
 #define RTL8211F_PHYCR1				0x18
+#define RTL8211F_ALDPS_PLL_OFF			BIT(1)
+#define RTL8211F_ALDPS_ENABLE			BIT(2)
+#define RTL8211F_ALDPS_XTAL_OFF			BIT(12)
+
 #define RTL8211F_PHYCR2				0x19
 #define RTL8211F_CLKOUT_EN			BIT(0)
 #define RTL8211F_PHYCR2_PHY_EEE_ENABLE		BIT(5)
 
+#define RTL8211F_INSR_PAGE			0xa43
 #define RTL8211F_INSR				0x1d
 
+/* RTL8211F LED configuration */
+#define RTL8211F_LEDCR_PAGE			0xd04
 #define RTL8211F_LEDCR				0x10
 #define RTL8211F_LEDCR_MODE			BIT(15)
 #define RTL8211F_LEDCR_ACT_TXRX			BIT(4)
@@ -47,25 +87,32 @@
 #define RTL8211F_LEDCR_MASK			GENMASK(4, 0)
 #define RTL8211F_LEDCR_SHIFT			5
 
+/* RTL8211F RGMII configuration */
+#define RTL8211F_RGMII_PAGE			0xd08
+
+#define RTL8211F_TXCR				0x11
 #define RTL8211F_TX_DELAY			BIT(8)
+
+#define RTL8211F_RXCR				0x15
 #define RTL8211F_RX_DELAY			BIT(3)
 
-#define RTL8211F_ALDPS_PLL_OFF			BIT(1)
-#define RTL8211F_ALDPS_ENABLE			BIT(2)
-#define RTL8211F_ALDPS_XTAL_OFF			BIT(12)
+/* RTL8211F WOL interrupt configuration */
+#define RTL8211F_INTBCR_PAGE			0xd40
+#define RTL8211F_INTBCR				0x16
+#define RTL8211F_INTBCR_INTB_PMEB		BIT(5)
 
-#define RTL8211E_CTRL_DELAY			BIT(13)
-#define RTL8211E_TX_DELAY			BIT(12)
-#define RTL8211E_RX_DELAY			BIT(11)
+/* RTL8211F WOL settings */
+#define RTL8211F_WOL_SETTINGS_PAGE		0xd8a
+#define RTL8211F_WOL_SETTINGS_EVENTS		16
+#define RTL8211F_WOL_EVENT_MAGIC		BIT(12)
+#define RTL8211F_WOL_SETTINGS_STATUS		17
+#define RTL8211F_WOL_STATUS_RESET		(BIT(15) | 0x1fff)
 
-#define RTL8201F_ISR				0x1e
-#define RTL8201F_ISR_ANERR			BIT(15)
-#define RTL8201F_ISR_DUPLEX			BIT(13)
-#define RTL8201F_ISR_LINK			BIT(11)
-#define RTL8201F_ISR_MASK			(RTL8201F_ISR_ANERR | \
-						 RTL8201F_ISR_DUPLEX | \
-						 RTL8201F_ISR_LINK)
-#define RTL8201F_IER				0x13
+/* RTL8211F Unique phyiscal and multicast address (WOL) */
+#define RTL8211F_PHYSICAL_ADDR_PAGE		0xd8c
+#define RTL8211F_PHYSICAL_ADDR_WORD0		16
+#define RTL8211F_PHYSICAL_ADDR_WORD1		17
+#define RTL8211F_PHYSICAL_ADDR_WORD2		18
 
 #define RTL822X_VND1_SERDES_OPTION			0x697a
 #define RTL822X_VND1_SERDES_OPTION_MODE_MASK		GENMASK(5, 0)
@@ -111,8 +158,10 @@
 #define RTL_8221B_VB_CG				0x001cc849
 #define RTL_8221B_VN_CG				0x001cc84a
 #define RTL_8251B				0x001cc862
+#define RTL_8261C				0x001cc890
 
-#define RTL8211F_LED_COUNT			3
+/* RTL8211E and RTL8211F support up to three LEDs */
+#define RTL8211x_LED_COUNT			3
 
 MODULE_DESCRIPTION("Realtek PHY driver");
 MODULE_AUTHOR("Johnson Leung");
@@ -123,6 +172,7 @@ struct rtl821x_priv {
 	u16 phycr2;
 	bool has_phycr2;
 	struct clk *clk;
+	u32 saved_wolopts;
 };
 
 static int rtl821x_read_page(struct phy_device *phydev)
@@ -135,6 +185,36 @@ static int rtl821x_write_page(struct phy_device *phydev, int page)
 	return __phy_write(phydev, RTL821x_PAGE_SELECT, page);
 }
 
+static int rtl821x_read_ext_page(struct phy_device *phydev, u16 ext_page,
+				 u32 regnum)
+{
+	int oldpage, ret = 0;
+
+	oldpage = phy_select_page(phydev, RTL821x_SET_EXT_PAGE);
+	if (oldpage >= 0) {
+		ret = __phy_write(phydev, RTL821x_EXT_PAGE_SELECT, ext_page);
+		if (ret == 0)
+			ret = __phy_read(phydev, regnum);
+	}
+
+	return phy_restore_page(phydev, oldpage, ret);
+}
+
+static int rtl821x_modify_ext_page(struct phy_device *phydev, u16 ext_page,
+				   u32 regnum, u16 mask, u16 set)
+{
+	int oldpage, ret = 0;
+
+	oldpage = phy_select_page(phydev, RTL821x_SET_EXT_PAGE);
+	if (oldpage >= 0) {
+		ret = __phy_write(phydev, RTL821x_EXT_PAGE_SELECT, ext_page);
+		if (ret == 0)
+			ret = __phy_modify(phydev, regnum, mask, set);
+	}
+
+	return phy_restore_page(phydev, oldpage, ret);
+}
+
 static int rtl821x_probe(struct phy_device *phydev)
 {
 	struct device *dev = &phydev->mdio.dev;
@@ -151,7 +231,7 @@ static int rtl821x_probe(struct phy_device *phydev)
 		return dev_err_probe(dev, PTR_ERR(priv->clk),
 				     "failed to get phy clock\n");
 
-	ret = phy_read_paged(phydev, 0xa43, RTL8211F_PHYCR1);
+	ret = phy_read_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR1);
 	if (ret < 0)
 		return ret;
 
@@ -161,7 +241,7 @@ static int rtl821x_probe(struct phy_device *phydev)
 
 	priv->has_phycr2 = !(phy_id == RTL_8211FVD_PHYID);
 	if (priv->has_phycr2) {
-		ret = phy_read_paged(phydev, 0xa43, RTL8211F_PHYCR2);
+		ret = phy_read_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR2);
 		if (ret < 0)
 			return ret;
 
@@ -197,7 +277,7 @@ static int rtl8211f_ack_interrupt(struct phy_device *phydev)
 {
 	int err;
 
-	err = phy_read_paged(phydev, 0xa43, RTL8211F_INSR);
+	err = phy_read_paged(phydev, RTL8211F_INSR_PAGE, RTL8211F_INSR);
 
 	return (err < 0) ? err : 0;
 }
@@ -340,7 +420,7 @@ static irqreturn_t rtl8211f_handle_interrupt(struct phy_device *phydev)
 {
 	int irq_status;
 
-	irq_status = phy_read_paged(phydev, 0xa43, RTL8211F_INSR);
+	irq_status = phy_read_paged(phydev, RTL8211F_INSR_PAGE, RTL8211F_INSR);
 	if (irq_status < 0) {
 		phy_error(phydev);
 		return IRQ_NONE;
@@ -354,6 +434,53 @@ static irqreturn_t rtl8211f_handle_interrupt(struct phy_device *phydev)
 	return IRQ_HANDLED;
 }
 
+static void rtl8211f_get_wol(struct phy_device *dev, struct ethtool_wolinfo *wol)
+{
+	wol->supported = WAKE_MAGIC;
+	if (phy_read_paged(dev, RTL8211F_WOL_SETTINGS_PAGE, RTL8211F_WOL_SETTINGS_EVENTS)
+	    & RTL8211F_WOL_EVENT_MAGIC)
+		wol->wolopts = WAKE_MAGIC;
+}
+
+static int rtl8211f_set_wol(struct phy_device *dev, struct ethtool_wolinfo *wol)
+{
+	const u8 *mac_addr = dev->attached_dev->dev_addr;
+	int oldpage;
+
+	oldpage = phy_save_page(dev);
+	if (oldpage < 0)
+		goto err;
+
+	if (wol->wolopts & WAKE_MAGIC) {
+		/* Store the device address for the magic packet */
+		rtl821x_write_page(dev, RTL8211F_PHYSICAL_ADDR_PAGE);
+		__phy_write(dev, RTL8211F_PHYSICAL_ADDR_WORD0, mac_addr[1] << 8 | (mac_addr[0]));
+		__phy_write(dev, RTL8211F_PHYSICAL_ADDR_WORD1, mac_addr[3] << 8 | (mac_addr[2]));
+		__phy_write(dev, RTL8211F_PHYSICAL_ADDR_WORD2, mac_addr[5] << 8 | (mac_addr[4]));
+
+		/* Enable magic packet matching and reset WOL status */
+		rtl821x_write_page(dev, RTL8211F_WOL_SETTINGS_PAGE);
+		__phy_write(dev, RTL8211F_WOL_SETTINGS_EVENTS, RTL8211F_WOL_EVENT_MAGIC);
+		__phy_write(dev, RTL8211F_WOL_SETTINGS_STATUS, RTL8211F_WOL_STATUS_RESET);
+
+		/* Enable the WOL interrupt */
+		rtl821x_write_page(dev, RTL8211F_INTBCR_PAGE);
+		__phy_set_bits(dev, RTL8211F_INTBCR, RTL8211F_INTBCR_INTB_PMEB);
+	} else {
+		/* Disable the WOL interrupt */
+		rtl821x_write_page(dev, RTL8211F_INTBCR_PAGE);
+		__phy_clear_bits(dev, RTL8211F_INTBCR, RTL8211F_INTBCR_INTB_PMEB);
+
+		/* Disable magic packet matching and reset WOL status */
+		rtl821x_write_page(dev, RTL8211F_WOL_SETTINGS_PAGE);
+		__phy_write(dev, RTL8211F_WOL_SETTINGS_EVENTS, 0);
+		__phy_write(dev, RTL8211F_WOL_SETTINGS_STATUS, RTL8211F_WOL_STATUS_RESET);
+	}
+
+err:
+	return phy_restore_page(dev, oldpage, 0);
+}
+
 static int rtl8211_config_aneg(struct phy_device *phydev)
 {
 	int ret;
@@ -390,7 +517,7 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 	u16 val_txdly, val_rxdly;
 	int ret;
 
-	ret = phy_modify_paged_changed(phydev, 0xa43, RTL8211F_PHYCR1,
+	ret = phy_modify_paged_changed(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR1,
 				       RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF,
 				       priv->phycr1);
 	if (ret < 0) {
@@ -424,7 +551,8 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 		return 0;
 	}
 
-	ret = phy_modify_paged_changed(phydev, 0xd08, 0x11, RTL8211F_TX_DELAY,
+	ret = phy_modify_paged_changed(phydev, RTL8211F_RGMII_PAGE,
+				       RTL8211F_TXCR, RTL8211F_TX_DELAY,
 				       val_txdly);
 	if (ret < 0) {
 		dev_err(dev, "Failed to update the TX delay register\n");
@@ -439,7 +567,8 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 			str_enabled_disabled(val_txdly));
 	}
 
-	ret = phy_modify_paged_changed(phydev, 0xd08, 0x15, RTL8211F_RX_DELAY,
+	ret = phy_modify_paged_changed(phydev, RTL8211F_RGMII_PAGE,
+				       RTL8211F_RXCR, RTL8211F_RX_DELAY,
 				       val_rxdly);
 	if (ret < 0) {
 		dev_err(dev, "Failed to update the RX delay register\n");
@@ -455,14 +584,15 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 	}
 
 	/* Disable PHY-mode EEE so LPI is passed to the MAC */
-	ret = phy_modify_paged(phydev, 0xa43, RTL8211F_PHYCR2,
+	ret = phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR2,
 			       RTL8211F_PHYCR2_PHY_EEE_ENABLE, 0);
 	if (ret)
 		return ret;
 
 	if (priv->has_phycr2) {
-		ret = phy_modify_paged(phydev, 0xa43, RTL8211F_PHYCR2,
-				       RTL8211F_CLKOUT_EN, priv->phycr2);
+		ret = phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE,
+				       RTL8211F_PHYCR2, RTL8211F_CLKOUT_EN,
+				       priv->phycr2);
 		if (ret < 0) {
 			dev_err(dev, "clkout configuration failed: %pe\n",
 				ERR_PTR(ret));
@@ -509,7 +639,7 @@ static int rtl821x_resume(struct phy_device *phydev)
 	return 0;
 }
 
-static int rtl8211f_led_hw_is_supported(struct phy_device *phydev, u8 index,
+static int rtl8211x_led_hw_is_supported(struct phy_device *phydev, u8 index,
 					unsigned long rules)
 {
 	const unsigned long mask = BIT(TRIGGER_NETDEV_LINK_10) |
@@ -528,9 +658,11 @@ static int rtl8211f_led_hw_is_supported(struct phy_device *phydev, u8 index,
 	 *      rates and Active indication always at all three 10+100+1000
 	 *      link rates.
 	 * This code currently uses mode B only.
+	 *
+	 * RTL8211E PHY LED has one mode, which works like RTL8211F mode B.
 	 */
 
-	if (index >= RTL8211F_LED_COUNT)
+	if (index >= RTL8211x_LED_COUNT)
 		return -EINVAL;
 
 	/* Filter out any other unsupported triggers. */
@@ -549,7 +681,7 @@ static int rtl8211f_led_hw_control_get(struct phy_device *phydev, u8 index,
 {
 	int val;
 
-	if (index >= RTL8211F_LED_COUNT)
+	if (index >= RTL8211x_LED_COUNT)
 		return -EINVAL;
 
 	val = phy_read_paged(phydev, 0xd04, RTL8211F_LEDCR);
@@ -560,17 +692,17 @@ static int rtl8211f_led_hw_control_get(struct phy_device *phydev, u8 index,
 	val &= RTL8211F_LEDCR_MASK;
 
 	if (val & RTL8211F_LEDCR_LINK_10)
-		set_bit(TRIGGER_NETDEV_LINK_10, rules);
+		__set_bit(TRIGGER_NETDEV_LINK_10, rules);
 
 	if (val & RTL8211F_LEDCR_LINK_100)
-		set_bit(TRIGGER_NETDEV_LINK_100, rules);
+		__set_bit(TRIGGER_NETDEV_LINK_100, rules);
 
 	if (val & RTL8211F_LEDCR_LINK_1000)
-		set_bit(TRIGGER_NETDEV_LINK_1000, rules);
+		__set_bit(TRIGGER_NETDEV_LINK_1000, rules);
 
 	if (val & RTL8211F_LEDCR_ACT_TXRX) {
-		set_bit(TRIGGER_NETDEV_RX, rules);
-		set_bit(TRIGGER_NETDEV_TX, rules);
+		__set_bit(TRIGGER_NETDEV_RX, rules);
+		__set_bit(TRIGGER_NETDEV_TX, rules);
 	}
 
 	return 0;
@@ -582,7 +714,7 @@ static int rtl8211f_led_hw_control_set(struct phy_device *phydev, u8 index,
 	const u16 mask = RTL8211F_LEDCR_MASK << (RTL8211F_LEDCR_SHIFT * index);
 	u16 reg = 0;
 
-	if (index >= RTL8211F_LED_COUNT)
+	if (index >= RTL8211x_LED_COUNT)
 		return -EINVAL;
 
 	if (test_bit(TRIGGER_NETDEV_LINK_10, &rules))
@@ -605,9 +737,86 @@ static int rtl8211f_led_hw_control_set(struct phy_device *phydev, u8 index,
 	return phy_modify_paged(phydev, 0xd04, RTL8211F_LEDCR, mask, reg);
 }
 
+static int rtl8211e_led_hw_control_get(struct phy_device *phydev, u8 index,
+				       unsigned long *rules)
+{
+	int ret;
+	u16 cr1, cr2;
+
+	if (index >= RTL8211x_LED_COUNT)
+		return -EINVAL;
+
+	ret = rtl821x_read_ext_page(phydev, RTL8211E_LEDCR_EXT_PAGE,
+				    RTL8211E_LEDCR1);
+	if (ret < 0)
+		return ret;
+
+	cr1 = ret >> RTL8211E_LEDCR1_SHIFT * index;
+	if (cr1 & RTL8211E_LEDCR1_ACT_TXRX) {
+		__set_bit(TRIGGER_NETDEV_RX, rules);
+		__set_bit(TRIGGER_NETDEV_TX, rules);
+	}
+
+	ret = rtl821x_read_ext_page(phydev, RTL8211E_LEDCR_EXT_PAGE,
+				    RTL8211E_LEDCR2);
+	if (ret < 0)
+		return ret;
+
+	cr2 = ret >> RTL8211E_LEDCR2_SHIFT * index;
+	if (cr2 & RTL8211E_LEDCR2_LINK_10)
+		__set_bit(TRIGGER_NETDEV_LINK_10, rules);
+
+	if (cr2 & RTL8211E_LEDCR2_LINK_100)
+		__set_bit(TRIGGER_NETDEV_LINK_100, rules);
+
+	if (cr2 & RTL8211E_LEDCR2_LINK_1000)
+		__set_bit(TRIGGER_NETDEV_LINK_1000, rules);
+
+	return ret;
+}
+
+static int rtl8211e_led_hw_control_set(struct phy_device *phydev, u8 index,
+				       unsigned long rules)
+{
+	const u16 cr1mask =
+		RTL8211E_LEDCR1_MASK << (RTL8211E_LEDCR1_SHIFT * index);
+	const u16 cr2mask =
+		RTL8211E_LEDCR2_MASK << (RTL8211E_LEDCR2_SHIFT * index);
+	u16 cr1 = 0, cr2 = 0;
+	int ret;
+
+	if (index >= RTL8211x_LED_COUNT)
+		return -EINVAL;
+
+	if (test_bit(TRIGGER_NETDEV_RX, &rules) ||
+	    test_bit(TRIGGER_NETDEV_TX, &rules)) {
+		cr1 |= RTL8211E_LEDCR1_ACT_TXRX;
+	}
+
+	cr1 <<= RTL8211E_LEDCR1_SHIFT * index;
+	ret = rtl821x_modify_ext_page(phydev, RTL8211E_LEDCR_EXT_PAGE,
+				      RTL8211E_LEDCR1, cr1mask, cr1);
+	if (ret < 0)
+		return ret;
+
+	if (test_bit(TRIGGER_NETDEV_LINK_10, &rules))
+		cr2 |= RTL8211E_LEDCR2_LINK_10;
+
+	if (test_bit(TRIGGER_NETDEV_LINK_100, &rules))
+		cr2 |= RTL8211E_LEDCR2_LINK_100;
+
+	if (test_bit(TRIGGER_NETDEV_LINK_1000, &rules))
+		cr2 |= RTL8211E_LEDCR2_LINK_1000;
+
+	cr2 <<= RTL8211E_LEDCR2_SHIFT * index;
+	ret = rtl821x_modify_ext_page(phydev, RTL8211E_LEDCR_EXT_PAGE,
+				      RTL8211E_LEDCR2, cr2mask, cr2);
+
+	return ret;
+}
+
 static int rtl8211e_config_init(struct phy_device *phydev)
 {
-	int ret = 0, oldpage;
 	u16 val;
 
 	/* enable TX/RX delay for rgmii-* modes, and disable them for rgmii. */
@@ -637,20 +846,9 @@ static int rtl8211e_config_init(struct phy_device *phydev)
 	 * 12 = RX Delay, 11 = TX Delay
 	 * 10:0 = Test && debug settings reserved by realtek
 	 */
-	oldpage = phy_select_page(phydev, 0x7);
-	if (oldpage < 0)
-		goto err_restore_page;
-
-	ret = __phy_write(phydev, RTL821x_EXT_PAGE_SELECT, 0xa4);
-	if (ret)
-		goto err_restore_page;
-
-	ret = __phy_modify(phydev, 0x1c, RTL8211E_CTRL_DELAY
-			   | RTL8211E_TX_DELAY | RTL8211E_RX_DELAY,
-			   val);
-
-err_restore_page:
-	return phy_restore_page(phydev, oldpage, ret);
+	return rtl821x_modify_ext_page(phydev, RTL8211E_RGMII_EXT_PAGE,
+				       RTL8211E_RGMII_DELAY,
+				       RTL8211E_DELAY_MASK, val);
 }
 
 static int rtl8211b_suspend(struct phy_device *phydev)
@@ -1117,13 +1315,15 @@ static bool rtlgen_supports_mmd(struct phy_device *phydev)
 	return val > 0;
 }
 
-static int rtlgen_match_phy_device(struct phy_device *phydev)
+static int rtlgen_match_phy_device(struct phy_device *phydev,
+				   const struct phy_driver *phydrv)
 {
 	return phydev->phy_id == RTL_GENERIC_PHYID &&
 	       !rtlgen_supports_2_5gbps(phydev);
 }
 
-static int rtl8226_match_phy_device(struct phy_device *phydev)
+static int rtl8226_match_phy_device(struct phy_device *phydev,
+				    const struct phy_driver *phydrv)
 {
 	return phydev->phy_id == RTL_GENERIC_PHYID &&
 	       rtlgen_supports_2_5gbps(phydev) &&
@@ -1139,32 +1339,38 @@ static int rtlgen_is_c45_match(struct phy_device *phydev, unsigned int id,
 		return !is_c45 && (id == phydev->phy_id);
 }
 
-static int rtl8221b_match_phy_device(struct phy_device *phydev)
+static int rtl8221b_match_phy_device(struct phy_device *phydev,
+				     const struct phy_driver *phydrv)
 {
 	return phydev->phy_id == RTL_8221B && rtlgen_supports_mmd(phydev);
 }
 
-static int rtl8221b_vb_cg_c22_match_phy_device(struct phy_device *phydev)
+static int rtl8221b_vb_cg_c22_match_phy_device(struct phy_device *phydev,
+					       const struct phy_driver *phydrv)
 {
 	return rtlgen_is_c45_match(phydev, RTL_8221B_VB_CG, false);
 }
 
-static int rtl8221b_vb_cg_c45_match_phy_device(struct phy_device *phydev)
+static int rtl8221b_vb_cg_c45_match_phy_device(struct phy_device *phydev,
+					       const struct phy_driver *phydrv)
 {
 	return rtlgen_is_c45_match(phydev, RTL_8221B_VB_CG, true);
 }
 
-static int rtl8221b_vn_cg_c22_match_phy_device(struct phy_device *phydev)
+static int rtl8221b_vn_cg_c22_match_phy_device(struct phy_device *phydev,
+					       const struct phy_driver *phydrv)
 {
 	return rtlgen_is_c45_match(phydev, RTL_8221B_VN_CG, false);
 }
 
-static int rtl8221b_vn_cg_c45_match_phy_device(struct phy_device *phydev)
+static int rtl8221b_vn_cg_c45_match_phy_device(struct phy_device *phydev,
+					       const struct phy_driver *phydrv)
 {
 	return rtlgen_is_c45_match(phydev, RTL_8221B_VN_CG, true);
 }
 
-static int rtl_internal_nbaset_match_phy_device(struct phy_device *phydev)
+static int rtl_internal_nbaset_match_phy_device(struct phy_device *phydev,
+						const struct phy_driver *phydrv)
 {
 	if (phydev->is_c45)
 		return false;
@@ -1173,6 +1379,7 @@ static int rtl_internal_nbaset_match_phy_device(struct phy_device *phydev)
 	case RTL_GENERIC_PHYID:
 	case RTL_8221B:
 	case RTL_8251B:
+	case RTL_8261C:
 	case 0x001cc841:
 		break;
 	default:
@@ -1182,7 +1389,8 @@ static int rtl_internal_nbaset_match_phy_device(struct phy_device *phydev)
 	return rtlgen_supports_2_5gbps(phydev) && !rtlgen_supports_mmd(phydev);
 }
 
-static int rtl8251b_c45_match_phy_device(struct phy_device *phydev)
+static int rtl8251b_c45_match_phy_device(struct phy_device *phydev,
+					 const struct phy_driver *phydrv)
 {
 	return rtlgen_is_c45_match(phydev, RTL_8251B, true);
 }
@@ -1392,6 +1600,9 @@ static struct phy_driver realtek_drvs[] = {
 		.resume		= genphy_resume,
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
+		.led_hw_is_supported = rtl8211x_led_hw_is_supported,
+		.led_hw_control_get = rtl8211e_led_hw_control_get,
+		.led_hw_control_set = rtl8211e_led_hw_control_set,
 	}, {
 		PHY_ID_MATCH_EXACT(0x001cc916),
 		.name		= "RTL8211F Gigabit Ethernet",
@@ -1400,12 +1611,14 @@ static struct phy_driver realtek_drvs[] = {
 		.read_status	= rtlgen_read_status,
 		.config_intr	= &rtl8211f_config_intr,
 		.handle_interrupt = rtl8211f_handle_interrupt,
+		.set_wol	= rtl8211f_set_wol,
+		.get_wol	= rtl8211f_get_wol,
 		.suspend	= rtl821x_suspend,
 		.resume		= rtl821x_resume,
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
 		.flags		= PHY_ALWAYS_CALL_SUSPEND,
-		.led_hw_is_supported = rtl8211f_led_hw_is_supported,
+		.led_hw_is_supported = rtl8211x_led_hw_is_supported,
 		.led_hw_control_get = rtl8211f_led_hw_control_get,
 		.led_hw_control_set = rtl8211f_led_hw_control_set,
 	}, {
diff --git a/drivers/net/phy/teranetics.c b/drivers/net/phy/teranetics.c
index 752d4bf7bb99..46c5ff7d7b56 100644
--- a/drivers/net/phy/teranetics.c
+++ b/drivers/net/phy/teranetics.c
@@ -67,7 +67,8 @@ static int teranetics_read_status(struct phy_device *phydev)
 	return 0;
 }
 
-static int teranetics_match_phy_device(struct phy_device *phydev)
+static int teranetics_match_phy_device(struct phy_device *phydev,
+				       const struct phy_driver *phydrv)
 {
 	return phydev->c45_ids.device_ids[3] == PHY_ID_TN2020;
 }
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 53463767cc43..def84e87e05b 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1131,6 +1131,8 @@ static const struct file_operations ppp_device_fops = {
 	.llseek		= noop_llseek,
 };
 
+static void ppp_nl_dellink(struct net_device *dev, struct list_head *head);
+
 static __net_init int ppp_init_net(struct net *net)
 {
 	struct ppp_net *pn = net_generic(net, ppp_net_id);
@@ -1146,28 +1148,20 @@ static __net_init int ppp_init_net(struct net *net)
 	return 0;
 }
 
-static __net_exit void ppp_exit_net(struct net *net)
+static __net_exit void ppp_exit_rtnl_net(struct net *net,
+					 struct list_head *dev_to_kill)
 {
 	struct ppp_net *pn = net_generic(net, ppp_net_id);
-	struct net_device *dev;
-	struct net_device *aux;
 	struct ppp *ppp;
-	LIST_HEAD(list);
 	int id;
 
-	rtnl_lock();
-	for_each_netdev_safe(net, dev, aux) {
-		if (dev->netdev_ops == &ppp_netdev_ops)
-			unregister_netdevice_queue(dev, &list);
-	}
-
 	idr_for_each_entry(&pn->units_idr, ppp, id)
-		/* Skip devices already unregistered by previous loop */
-		if (!net_eq(dev_net(ppp->dev), net))
-			unregister_netdevice_queue(ppp->dev, &list);
+		ppp_nl_dellink(ppp->dev, dev_to_kill);
+}
 
-	unregister_netdevice_many(&list);
-	rtnl_unlock();
+static __net_exit void ppp_exit_net(struct net *net)
+{
+	struct ppp_net *pn = net_generic(net, ppp_net_id);
 
 	mutex_destroy(&pn->all_ppp_mutex);
 	idr_destroy(&pn->units_idr);
@@ -1177,6 +1171,7 @@ static __net_exit void ppp_exit_net(struct net *net)
 
 static struct pernet_operations ppp_net_ops = {
 	.init = ppp_init_net,
+	.exit_rtnl = ppp_exit_rtnl_net,
 	.exit = ppp_exit_net,
 	.id   = &ppp_net_id,
 	.size = sizeof(struct ppp_net),
diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index d8fc0c79745d..b75ceb90359f 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -1778,8 +1778,8 @@ static void team_change_rx_flags(struct net_device *dev, int change)
 	struct team_port *port;
 	int inc;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(port, &team->port_list, list) {
+	mutex_lock(&team->lock);
+	list_for_each_entry(port, &team->port_list, list) {
 		if (change & IFF_PROMISC) {
 			inc = dev->flags & IFF_PROMISC ? 1 : -1;
 			dev_set_promiscuity(port->dev, inc);
@@ -1789,7 +1789,7 @@ static void team_change_rx_flags(struct net_device *dev, int change)
 			dev_set_allmulti(port->dev, inc);
 		}
 	}
-	rcu_read_unlock();
+	mutex_unlock(&team->lock);
 }
 
 static void team_set_rx_mode(struct net_device *dev)
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 3c360d4f0635..370b32fc2588 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -101,9 +101,7 @@ config USB_RTL8152
 	select MII
 	select PHYLIB
 	select CRC32
-	select CRYPTO
-	select CRYPTO_HASH
-	select CRYPTO_SHA256
+	select CRYPTO_LIB_SHA256
 	help
 	  This option adds support for Realtek RTL8152 based USB 2.0
 	  10/100 Ethernet adapters and RTL8153 based USB 3.0 10/100/1000
diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index ff5be2cbf17b..453a2cf82753 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -30,10 +30,13 @@ static int aqc111_read_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value,
 	ret = usbnet_read_cmd_nopm(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR |
 				   USB_RECIP_DEVICE, value, index, data, size);
 
-	if (unlikely(ret < 0))
+	if (unlikely(ret < size)) {
+		ret = ret < 0 ? ret : -ENODATA;
+
 		netdev_warn(dev->net,
 			    "Failed to read(0x%x) reg index 0x%04x: %d\n",
 			    cmd, index, ret);
+	}
 
 	return ret;
 }
@@ -46,10 +49,13 @@ static int aqc111_read_cmd(struct usbnet *dev, u8 cmd, u16 value,
 	ret = usbnet_read_cmd(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR |
 			      USB_RECIP_DEVICE, value, index, data, size);
 
-	if (unlikely(ret < 0))
+	if (unlikely(ret < size)) {
+		ret = ret < 0 ? ret : -ENODATA;
+
 		netdev_warn(dev->net,
 			    "Failed to read(0x%x) reg index 0x%04x: %d\n",
 			    cmd, index, ret);
+	}
 
 	return ret;
 }
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index e4f1663b6204..480bbc0f2d8f 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1554,10 +1554,12 @@ static void lan78xx_set_multicast(struct net_device *netdev)
 	schedule_work(&pdata->set_multicast);
 }
 
+static int lan78xx_configure_flowcontrol(struct lan78xx_net *dev,
+					 bool tx_pause, bool rx_pause);
+
 static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex,
 				      u16 lcladv, u16 rmtadv)
 {
-	u32 flow = 0, fct_flow = 0;
 	u8 cap;
 
 	if (dev->fc_autoneg)
@@ -1565,27 +1567,13 @@ static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex,
 	else
 		cap = dev->fc_request_control;
 
-	if (cap & FLOW_CTRL_TX)
-		flow |= (FLOW_CR_TX_FCEN_ | 0xFFFF);
-
-	if (cap & FLOW_CTRL_RX)
-		flow |= FLOW_CR_RX_FCEN_;
-
-	if (dev->udev->speed == USB_SPEED_SUPER)
-		fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_SS, FLOW_OFF_SS);
-	else if (dev->udev->speed == USB_SPEED_HIGH)
-		fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_HS, FLOW_OFF_HS);
-
 	netif_dbg(dev, link, dev->net, "rx pause %s, tx pause %s",
 		  (cap & FLOW_CTRL_RX ? "enabled" : "disabled"),
 		  (cap & FLOW_CTRL_TX ? "enabled" : "disabled"));
 
-	lan78xx_write_reg(dev, FCT_FLOW, fct_flow);
-
-	/* threshold value should be set before enabling flow */
-	lan78xx_write_reg(dev, FLOW, flow);
-
-	return 0;
+	return lan78xx_configure_flowcontrol(dev,
+					     cap & FLOW_CTRL_TX,
+					     cap & FLOW_CTRL_RX);
 }
 
 static void lan78xx_rx_urb_submit_all(struct lan78xx_net *dev);
@@ -1636,15 +1624,30 @@ exit_unlock:
 	return ret;
 }
 
+/**
+ * lan78xx_phy_int_ack - Acknowledge PHY interrupt
+ * @dev: pointer to the LAN78xx device structure
+ *
+ * This function acknowledges the PHY interrupt by setting the
+ * INT_STS_PHY_INT_ bit in the interrupt status register (INT_STS).
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+static int lan78xx_phy_int_ack(struct lan78xx_net *dev)
+{
+	return lan78xx_write_reg(dev, INT_STS, INT_STS_PHY_INT_);
+}
+
+static int lan78xx_configure_usb(struct lan78xx_net *dev, int speed);
+
 static int lan78xx_link_reset(struct lan78xx_net *dev)
 {
 	struct phy_device *phydev = dev->net->phydev;
 	struct ethtool_link_ksettings ecmd;
 	int ladv, radv, ret, link;
-	u32 buf;
 
 	/* clear LAN78xx interrupt status */
-	ret = lan78xx_write_reg(dev, INT_STS, INT_STS_PHY_INT_);
+	ret = lan78xx_phy_int_ack(dev);
 	if (unlikely(ret < 0))
 		return ret;
 
@@ -1667,36 +1670,9 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 
 		phy_ethtool_ksettings_get(phydev, &ecmd);
 
-		if (dev->udev->speed == USB_SPEED_SUPER) {
-			if (ecmd.base.speed == 1000) {
-				/* disable U2 */
-				ret = lan78xx_read_reg(dev, USB_CFG1, &buf);
-				if (ret < 0)
-					return ret;
-				buf &= ~USB_CFG1_DEV_U2_INIT_EN_;
-				ret = lan78xx_write_reg(dev, USB_CFG1, buf);
-				if (ret < 0)
-					return ret;
-				/* enable U1 */
-				ret = lan78xx_read_reg(dev, USB_CFG1, &buf);
-				if (ret < 0)
-					return ret;
-				buf |= USB_CFG1_DEV_U1_INIT_EN_;
-				ret = lan78xx_write_reg(dev, USB_CFG1, buf);
-				if (ret < 0)
-					return ret;
-			} else {
-				/* enable U1 & U2 */
-				ret = lan78xx_read_reg(dev, USB_CFG1, &buf);
-				if (ret < 0)
-					return ret;
-				buf |= USB_CFG1_DEV_U2_INIT_EN_;
-				buf |= USB_CFG1_DEV_U1_INIT_EN_;
-				ret = lan78xx_write_reg(dev, USB_CFG1, buf);
-				if (ret < 0)
-					return ret;
-			}
-		}
+		ret = lan78xx_configure_usb(dev, ecmd.base.speed);
+		if (ret < 0)
+			return ret;
 
 		ladv = phy_read(phydev, MII_ADVERTISE);
 		if (ladv < 0)
@@ -2508,48 +2484,323 @@ static void lan78xx_remove_irq_domain(struct lan78xx_net *dev)
 	dev->domain_data.irqdomain = NULL;
 }
 
-static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev)
+/**
+ * lan78xx_configure_usb - Configure USB link power settings
+ * @dev: pointer to the LAN78xx device structure
+ * @speed: negotiated Ethernet link speed (in Mbps)
+ *
+ * This function configures U1/U2 link power management for SuperSpeed
+ * USB devices based on the current Ethernet link speed. It uses the
+ * USB_CFG1 register to enable or disable U1 and U2 low-power states.
+ *
+ * Note: Only LAN7800 and LAN7801 support SuperSpeed (USB 3.x).
+ *       LAN7850 is a High-Speed-only (USB 2.0) device and is skipped.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+static int lan78xx_configure_usb(struct lan78xx_net *dev, int speed)
 {
-	u32 buf;
+	u32 mask, val;
 	int ret;
+
+	/* Only configure USB settings for SuperSpeed devices */
+	if (dev->udev->speed != USB_SPEED_SUPER)
+		return 0;
+
+	/* LAN7850 does not support USB 3.x */
+	if (dev->chipid == ID_REV_CHIP_ID_7850_) {
+		netdev_warn_once(dev->net, "Unexpected SuperSpeed for LAN7850 (USB 2.0 only)\n");
+		return 0;
+	}
+
+	switch (speed) {
+	case SPEED_1000:
+		/* Disable U2, enable U1 */
+		ret = lan78xx_update_reg(dev, USB_CFG1,
+					 USB_CFG1_DEV_U2_INIT_EN_, 0);
+		if (ret < 0)
+			return ret;
+
+		return lan78xx_update_reg(dev, USB_CFG1,
+					  USB_CFG1_DEV_U1_INIT_EN_,
+					  USB_CFG1_DEV_U1_INIT_EN_);
+
+	case SPEED_100:
+	case SPEED_10:
+		/* Enable both U1 and U2 */
+		mask = USB_CFG1_DEV_U1_INIT_EN_ | USB_CFG1_DEV_U2_INIT_EN_;
+		val = mask;
+		return lan78xx_update_reg(dev, USB_CFG1, mask, val);
+
+	default:
+		netdev_warn(dev->net, "Unsupported link speed: %d\n", speed);
+		return -EINVAL;
+	}
+}
+
+/**
+ * lan78xx_configure_flowcontrol - Set MAC and FIFO flow control configuration
+ * @dev: pointer to the LAN78xx device structure
+ * @tx_pause: enable transmission of pause frames
+ * @rx_pause: enable reception of pause frames
+ *
+ * This function configures the LAN78xx flow control settings by writing
+ * to the FLOW and FCT_FLOW registers. The pause time is set to the
+ * maximum allowed value (65535 quanta). FIFO thresholds are selected
+ * based on USB speed.
+ *
+ * The Pause Time field is measured in units of 512-bit times (quanta):
+ *   - At 1 Gbps: 1 quanta = 512 ns → max ~33.6 ms pause
+ *   - At 100 Mbps: 1 quanta = 5.12 µs → max ~335 ms pause
+ *   - At 10 Mbps: 1 quanta = 51.2 µs → max ~3.3 s pause
+ *
+ * Flow control thresholds (FCT_FLOW) are used to trigger pause/resume:
+ *   - RXUSED is the number of bytes used in the RX FIFO
+ *   - Flow is turned ON when RXUSED ≥ FLOW_ON threshold
+ *   - Flow is turned OFF when RXUSED ≤ FLOW_OFF threshold
+ *   - Both thresholds are encoded in units of 512 bytes (rounded up)
+ *
+ * Thresholds differ by USB speed because available USB bandwidth
+ * affects how fast packets can be drained from the RX FIFO:
+ *   - USB 3.x (SuperSpeed):
+ *       FLOW_ON  = 9216 bytes → 18 units
+ *       FLOW_OFF = 4096 bytes →  8 units
+ *   - USB 2.0 (High-Speed):
+ *       FLOW_ON  = 8704 bytes → 17 units
+ *       FLOW_OFF = 1024 bytes →  2 units
+ *
+ * Note: The FCT_FLOW register must be configured before enabling TX pause
+ *       (i.e., before setting FLOW_CR_TX_FCEN_), as required by the hardware.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+static int lan78xx_configure_flowcontrol(struct lan78xx_net *dev,
+					 bool tx_pause, bool rx_pause)
+{
+	/* Use maximum pause time: 65535 quanta (512-bit times) */
+	const u32 pause_time_quanta = 65535;
+	u32 fct_flow = 0;
+	u32 flow = 0;
+	int ret;
+
+	/* Prepare MAC flow control bits */
+	if (tx_pause)
+		flow |= FLOW_CR_TX_FCEN_ | pause_time_quanta;
+
+	if (rx_pause)
+		flow |= FLOW_CR_RX_FCEN_;
+
+	/* Select RX FIFO thresholds based on USB speed
+	 *
+	 * FCT_FLOW layout:
+	 *   bits [6:0]   FLOW_ON threshold (RXUSED ≥ ON → assert pause)
+	 *   bits [14:8]  FLOW_OFF threshold (RXUSED ≤ OFF → deassert pause)
+	 *   thresholds are expressed in units of 512 bytes
+	 */
+	switch (dev->udev->speed) {
+	case USB_SPEED_SUPER:
+		fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_SS, FLOW_OFF_SS);
+		break;
+	case USB_SPEED_HIGH:
+		fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_HS, FLOW_OFF_HS);
+		break;
+	default:
+		netdev_warn(dev->net, "Unsupported USB speed: %d\n",
+			    dev->udev->speed);
+		return -EINVAL;
+	}
+
+	/* Step 1: Write FIFO thresholds before enabling pause frames */
+	ret = lan78xx_write_reg(dev, FCT_FLOW, fct_flow);
+	if (ret < 0)
+		return ret;
+
+	/* Step 2: Enable MAC pause functionality */
+	return lan78xx_write_reg(dev, FLOW, flow);
+}
+
+/**
+ * lan78xx_register_fixed_phy() - Register a fallback fixed PHY
+ * @dev: LAN78xx device
+ *
+ * Registers a fixed PHY with 1 Gbps full duplex. This is used in special cases
+ * like EVB-KSZ9897-1, where LAN7801 acts as a USB-to-Ethernet interface to a
+ * switch without a visible PHY.
+ *
+ * Return: pointer to the registered fixed PHY, or ERR_PTR() on error.
+ */
+static struct phy_device *lan78xx_register_fixed_phy(struct lan78xx_net *dev)
+{
 	struct fixed_phy_status fphy_status = {
 		.link = 1,
 		.speed = SPEED_1000,
 		.duplex = DUPLEX_FULL,
 	};
+
+	netdev_info(dev->net,
+		    "No PHY found on LAN7801 – registering fixed PHY (e.g. EVB-KSZ9897-1)\n");
+
+	return fixed_phy_register(&fphy_status, NULL);
+}
+
+/**
+ * lan78xx_get_phy() - Probe or register PHY device and set interface mode
+ * @dev: LAN78xx device structure
+ *
+ * This function attempts to find a PHY on the MDIO bus. If no PHY is found
+ * and the chip is LAN7801, it registers a fixed PHY as fallback. It also
+ * sets dev->interface based on chip ID and detected PHY type.
+ *
+ * Return: a valid PHY device pointer, or ERR_PTR() on failure.
+ */
+static struct phy_device *lan78xx_get_phy(struct lan78xx_net *dev)
+{
 	struct phy_device *phydev;
 
+	/* Attempt to locate a PHY on the MDIO bus */
 	phydev = phy_find_first(dev->mdiobus);
-	if (!phydev) {
-		netdev_dbg(dev->net, "PHY Not Found!! Registering Fixed PHY\n");
-		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
-		if (IS_ERR(phydev)) {
-			netdev_err(dev->net, "No PHY/fixed_PHY found\n");
-			return NULL;
+
+	switch (dev->chipid) {
+	case ID_REV_CHIP_ID_7801_:
+		if (phydev) {
+			/* External RGMII PHY detected */
+			dev->interface = PHY_INTERFACE_MODE_RGMII_ID;
+			phydev->is_internal = false;
+
+			if (!phydev->drv)
+				netdev_warn(dev->net,
+					    "PHY driver not found – assuming RGMII delays are on PCB or strapped for the PHY\n");
+
+			return phydev;
 		}
-		netdev_dbg(dev->net, "Registered FIXED PHY\n");
+
 		dev->interface = PHY_INTERFACE_MODE_RGMII;
+		/* No PHY found – fallback to fixed PHY (e.g. KSZ switch board) */
+		return lan78xx_register_fixed_phy(dev);
+
+	case ID_REV_CHIP_ID_7800_:
+	case ID_REV_CHIP_ID_7850_:
+		if (!phydev)
+			return ERR_PTR(-ENODEV);
+
+		/* These use internal GMII-connected PHY */
+		dev->interface = PHY_INTERFACE_MODE_GMII;
+		phydev->is_internal = true;
+		return phydev;
+
+	default:
+		netdev_err(dev->net, "Unknown CHIP ID: 0x%08x\n", dev->chipid);
+		return ERR_PTR(-ENODEV);
+	}
+}
+
+/**
+ * lan78xx_mac_prepare_for_phy() - Preconfigure MAC-side interface settings
+ * @dev: LAN78xx device
+ *
+ * Configure MAC-side registers according to dev->interface, which should be
+ * set by lan78xx_get_phy().
+ *
+ * - For PHY_INTERFACE_MODE_RGMII:
+ *   Enable MAC-side TXC delay. This mode seems to be used in a special setup
+ *   without a real PHY, likely on EVB-KSZ9897-1. In that design, LAN7801 is
+ *   connected to the KSZ9897 switch, and the link timing is expected to be
+ *   hardwired (e.g. via strapping or board layout). No devicetree support is
+ *   assumed here.
+ *
+ * - For PHY_INTERFACE_MODE_RGMII_ID:
+ *   Disable MAC-side delay and rely on the PHY driver to provide delay.
+ *
+ * - For GMII, no MAC-specific config is needed.
+ *
+ * Return: 0 on success or a negative error code.
+ */
+static int lan78xx_mac_prepare_for_phy(struct lan78xx_net *dev)
+{
+	int ret;
+
+	switch (dev->interface) {
+	case PHY_INTERFACE_MODE_RGMII:
+		/* Enable MAC-side TX clock delay */
 		ret = lan78xx_write_reg(dev, MAC_RGMII_ID,
 					MAC_RGMII_ID_TXC_DELAY_EN_);
+		if (ret < 0)
+			return ret;
+
 		ret = lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00);
-		ret = lan78xx_read_reg(dev, HW_CFG, &buf);
-		buf |= HW_CFG_CLK125_EN_;
-		buf |= HW_CFG_REFCLK25_EN_;
-		ret = lan78xx_write_reg(dev, HW_CFG, buf);
-	} else {
-		if (!phydev->drv) {
-			netdev_err(dev->net, "no PHY driver found\n");
-			return NULL;
-		}
-		dev->interface = PHY_INTERFACE_MODE_RGMII_ID;
-		/* The PHY driver is responsible to configure proper RGMII
-		 * interface delays. Disable RGMII delays on MAC side.
-		 */
-		lan78xx_write_reg(dev, MAC_RGMII_ID, 0);
+		if (ret < 0)
+			return ret;
+
+		ret = lan78xx_update_reg(dev, HW_CFG,
+					 HW_CFG_CLK125_EN_ | HW_CFG_REFCLK25_EN_,
+					 HW_CFG_CLK125_EN_ | HW_CFG_REFCLK25_EN_);
+		if (ret < 0)
+			return ret;
+
+		break;
+
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		/* Disable MAC-side TXC delay, PHY provides it */
+		ret = lan78xx_write_reg(dev, MAC_RGMII_ID, 0);
+		if (ret < 0)
+			return ret;
+
+		break;
 
-		phydev->is_internal = false;
+	case PHY_INTERFACE_MODE_GMII:
+		/* No MAC-specific configuration required */
+		break;
+
+	default:
+		netdev_warn(dev->net, "Unsupported interface mode: %d\n",
+			    dev->interface);
+		break;
 	}
-	return phydev;
+
+	return 0;
+}
+
+/**
+ * lan78xx_configure_leds_from_dt() - Configure LED enables based on DT
+ * @dev: LAN78xx device
+ * @phydev: PHY device (must be valid)
+ *
+ * Reads "microchip,led-modes" property from the PHY's DT node and enables
+ * the corresponding number of LEDs by writing to HW_CFG.
+ *
+ * This helper preserves the original logic, enabling up to 4 LEDs.
+ * If the property is not present, this function does nothing.
+ *
+ * Return: 0 on success or a negative error code.
+ */
+static int lan78xx_configure_leds_from_dt(struct lan78xx_net *dev,
+					  struct phy_device *phydev)
+{
+	struct device_node *np = phydev->mdio.dev.of_node;
+	u32 reg;
+	int len, ret;
+
+	if (!np)
+		return 0;
+
+	len = of_property_count_elems_of_size(np, "microchip,led-modes",
+					      sizeof(u32));
+	if (len < 0)
+		return 0;
+
+	ret = lan78xx_read_reg(dev, HW_CFG, &reg);
+	if (ret < 0)
+		return ret;
+
+	reg &= ~(HW_CFG_LED0_EN_ | HW_CFG_LED1_EN_ |
+		 HW_CFG_LED2_EN_ | HW_CFG_LED3_EN_);
+
+	reg |= (len > 0) * HW_CFG_LED0_EN_ |
+	       (len > 1) * HW_CFG_LED1_EN_ |
+	       (len > 2) * HW_CFG_LED2_EN_ |
+	       (len > 3) * HW_CFG_LED3_EN_;
+
+	return lan78xx_write_reg(dev, HW_CFG, reg);
 }
 
 static int lan78xx_phy_init(struct lan78xx_net *dev)
@@ -2559,30 +2810,13 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 	u32 mii_adv;
 	struct phy_device *phydev;
 
-	switch (dev->chipid) {
-	case ID_REV_CHIP_ID_7801_:
-		phydev = lan7801_phy_init(dev);
-		if (!phydev) {
-			netdev_err(dev->net, "lan7801: PHY Init Failed");
-			return -EIO;
-		}
-		break;
-
-	case ID_REV_CHIP_ID_7800_:
-	case ID_REV_CHIP_ID_7850_:
-		phydev = phy_find_first(dev->mdiobus);
-		if (!phydev) {
-			netdev_err(dev->net, "no PHY found\n");
-			return -EIO;
-		}
-		phydev->is_internal = true;
-		dev->interface = PHY_INTERFACE_MODE_GMII;
-		break;
+	phydev = lan78xx_get_phy(dev);
+	if (IS_ERR(phydev))
+		return PTR_ERR(phydev);
 
-	default:
-		netdev_err(dev->net, "Unknown CHIP ID found\n");
-		return -EIO;
-	}
+	ret = lan78xx_mac_prepare_for_phy(dev);
+	if (ret < 0)
+		goto free_phy;
 
 	/* if phyirq is not set, use polling mode in phylib */
 	if (dev->domain_data.phyirq > 0)
@@ -2624,33 +2858,23 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 
 	phy_support_eee(phydev);
 
-	if (phydev->mdio.dev.of_node) {
-		u32 reg;
-		int len;
-
-		len = of_property_count_elems_of_size(phydev->mdio.dev.of_node,
-						      "microchip,led-modes",
-						      sizeof(u32));
-		if (len >= 0) {
-			/* Ensure the appropriate LEDs are enabled */
-			lan78xx_read_reg(dev, HW_CFG, &reg);
-			reg &= ~(HW_CFG_LED0_EN_ |
-				 HW_CFG_LED1_EN_ |
-				 HW_CFG_LED2_EN_ |
-				 HW_CFG_LED3_EN_);
-			reg |= (len > 0) * HW_CFG_LED0_EN_ |
-				(len > 1) * HW_CFG_LED1_EN_ |
-				(len > 2) * HW_CFG_LED2_EN_ |
-				(len > 3) * HW_CFG_LED3_EN_;
-			lan78xx_write_reg(dev, HW_CFG, reg);
-		}
-	}
+	ret = lan78xx_configure_leds_from_dt(dev, phydev);
+	if (ret)
+		goto free_phy;
 
 	genphy_config_aneg(phydev);
 
 	dev->fc_autoneg = phydev->autoneg;
 
 	return 0;
+
+free_phy:
+	if (phy_is_pseudo_fixed_link(phydev)) {
+		fixed_phy_unregister(phydev);
+		phy_device_free(phydev);
+	}
+
+	return ret;
 }
 
 static int lan78xx_set_rx_max_frame_length(struct lan78xx_net *dev, int size)
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 2cab046749a9..67f5d30ffcba 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -26,7 +26,7 @@
 #include <linux/atomic.h>
 #include <linux/acpi.h>
 #include <linux/firmware.h>
-#include <crypto/hash.h>
+#include <crypto/sha2.h>
 #include <linux/usb/r8152.h>
 #include <net/gso.h>
 
@@ -4628,48 +4628,16 @@ out:
 static long rtl8152_fw_verify_checksum(struct r8152 *tp,
 				       struct fw_header *fw_hdr, size_t size)
 {
-	unsigned char checksum[sizeof(fw_hdr->checksum)];
-	struct crypto_shash *alg;
-	struct shash_desc *sdesc;
-	size_t len;
-	long rc;
-
-	alg = crypto_alloc_shash("sha256", 0, 0);
-	if (IS_ERR(alg)) {
-		rc = PTR_ERR(alg);
-		goto out;
-	}
-
-	if (crypto_shash_digestsize(alg) != sizeof(fw_hdr->checksum)) {
-		rc = -EFAULT;
-		dev_err(&tp->intf->dev, "digestsize incorrect (%u)\n",
-			crypto_shash_digestsize(alg));
-		goto free_shash;
-	}
+	u8 checksum[sizeof(fw_hdr->checksum)];
 
-	len = sizeof(*sdesc) + crypto_shash_descsize(alg);
-	sdesc = kmalloc(len, GFP_KERNEL);
-	if (!sdesc) {
-		rc = -ENOMEM;
-		goto free_shash;
-	}
-	sdesc->tfm = alg;
-
-	len = size - sizeof(fw_hdr->checksum);
-	rc = crypto_shash_digest(sdesc, fw_hdr->version, len, checksum);
-	kfree(sdesc);
-	if (rc)
-		goto free_shash;
+	BUILD_BUG_ON(sizeof(checksum) != SHA256_DIGEST_SIZE);
+	sha256(fw_hdr->version, size - sizeof(checksum), checksum);
 
-	if (memcmp(fw_hdr->checksum, checksum, sizeof(fw_hdr->checksum))) {
+	if (memcmp(fw_hdr->checksum, checksum, sizeof(checksum))) {
 		dev_err(&tp->intf->dev, "checksum fail\n");
-		rc = -EFAULT;
+		return -EFAULT;
 	}
-
-free_shash:
-	crypto_free_shash(alg);
-out:
-	return rc;
+	return 0;
 }
 
 static long rtl8152_check_firmware(struct r8152 *tp, struct rtl_fw *rtl_fw)
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index bb0bf1415872..7b3739b29c8f 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -630,16 +630,6 @@ static const struct driver_info	zte_rndis_info = {
 	.tx_fixup =	rndis_tx_fixup,
 };
 
-static const struct driver_info	wwan_rndis_info = {
-	.description =	"Mobile Broadband RNDIS device",
-	.flags =	FLAG_WWAN | FLAG_POINTTOPOINT | FLAG_FRAMING_RN | FLAG_NO_SETINT,
-	.bind =		rndis_bind,
-	.unbind =	rndis_unbind,
-	.status =	rndis_status,
-	.rx_fixup =	rndis_rx_fixup,
-	.tx_fixup =	rndis_tx_fixup,
-};
-
 /*-------------------------------------------------------------------------*/
 
 static const struct usb_device_id	products [] = {
@@ -676,11 +666,9 @@ static const struct usb_device_id	products [] = {
 	USB_INTERFACE_INFO(USB_CLASS_WIRELESS_CONTROLLER, 1, 3),
 	.driver_info = (unsigned long) &rndis_info,
 }, {
-	/* Mobile Broadband Modem, seen in Novatel Verizon USB730L and
-	 * Telit FN990A (RNDIS)
-	 */
+	/* Novatel Verizon USB730L */
 	USB_INTERFACE_INFO(USB_CLASS_MISC, 4, 1),
-	.driver_info = (unsigned long)&wwan_rndis_info,
+	.driver_info = (unsigned long) &rndis_info,
 },
 	{ },		// END
 };
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 7bb53961c0ea..e58a0f1b5c5b 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -307,12 +307,10 @@ static void __veth_xdp_flush(struct veth_rq *rq)
 
 static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb)
 {
-	if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb))) {
-		dev_kfree_skb_any(skb);
-		return NET_RX_DROP;
-	}
+	if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb)))
+		return NETDEV_TX_BUSY; /* signal qdisc layer */
 
-	return NET_RX_SUCCESS;
+	return NET_RX_SUCCESS; /* same as NETDEV_TX_OK */
 }
 
 static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
@@ -346,11 +344,11 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
 	struct veth_rq *rq = NULL;
-	int ret = NETDEV_TX_OK;
+	struct netdev_queue *txq;
 	struct net_device *rcv;
 	int length = skb->len;
 	bool use_napi = false;
-	int rxq;
+	int ret, rxq;
 
 	rcu_read_lock();
 	rcv = rcu_dereference(priv->peer);
@@ -373,17 +371,45 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	skb_tx_timestamp(skb);
-	if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) {
+
+	ret = veth_forward_skb(rcv, skb, rq, use_napi);
+	switch (ret) {
+	case NET_RX_SUCCESS: /* same as NETDEV_TX_OK */
 		if (!use_napi)
 			dev_sw_netstats_tx_add(dev, 1, length);
 		else
 			__veth_xdp_flush(rq);
-	} else {
+		break;
+	case NETDEV_TX_BUSY:
+		/* If a qdisc is attached to our virtual device, returning
+		 * NETDEV_TX_BUSY is allowed.
+		 */
+		txq = netdev_get_tx_queue(dev, rxq);
+
+		if (qdisc_txq_has_no_queue(txq)) {
+			dev_kfree_skb_any(skb);
+			goto drop;
+		}
+		/* Restore Eth hdr pulled by dev_forward_skb/eth_type_trans */
+		__skb_push(skb, ETH_HLEN);
+		/* Depend on prior success packets started NAPI consumer via
+		 * __veth_xdp_flush(). Cancel TXQ stop if consumer stopped,
+		 * paired with empty check in veth_poll().
+		 */
+		netif_tx_stop_queue(txq);
+		smp_mb__after_atomic();
+		if (unlikely(__ptr_ring_empty(&rq->xdp_ring)))
+			netif_tx_wake_queue(txq);
+		break;
+	case NET_RX_DROP: /* same as NET_XMIT_DROP */
 drop:
 		atomic64_inc(&priv->dropped);
 		ret = NET_XMIT_DROP;
+		break;
+	default:
+		net_crit_ratelimited("%s(%s): Invalid return code(%d)",
+				     __func__, dev->name, ret);
 	}
-
 	rcu_read_unlock();
 
 	return ret;
@@ -874,9 +900,17 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 			struct veth_xdp_tx_bq *bq,
 			struct veth_stats *stats)
 {
+	struct veth_priv *priv = netdev_priv(rq->dev);
+	int queue_idx = rq->xdp_rxq.queue_index;
+	struct netdev_queue *peer_txq;
+	struct net_device *peer_dev;
 	int i, done = 0, n_xdpf = 0;
 	void *xdpf[VETH_XDP_BATCH];
 
+	/* NAPI functions as RCU section */
+	peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held());
+	peer_txq = netdev_get_tx_queue(peer_dev, queue_idx);
+
 	for (i = 0; i < budget; i++) {
 		void *ptr = __ptr_ring_consume(&rq->xdp_ring);
 
@@ -925,6 +959,9 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 	rq->stats.vs.xdp_packets += done;
 	u64_stats_update_end(&rq->stats.syncp);
 
+	if (unlikely(netif_tx_queue_stopped(peer_txq)))
+		netif_tx_wake_queue(peer_txq);
+
 	return done;
 }
 
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7e4617216a4b..e53ba600605a 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3342,7 +3342,8 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
+static void __virtnet_rx_pause(struct virtnet_info *vi,
+			       struct receive_queue *rq)
 {
 	bool running = netif_running(vi->dev);
 
@@ -3352,15 +3353,64 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
 	}
 }
 
-static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
+static void virtnet_rx_pause_all(struct virtnet_info *vi)
 {
-	bool running = netif_running(vi->dev);
+	int i;
 
-	if (!try_fill_recv(vi, rq, GFP_KERNEL))
-		schedule_delayed_work(&vi->refill, 0);
+	/*
+	 * Make sure refill_work does not run concurrently to
+	 * avoid napi_disable race which leads to deadlock.
+	 */
+	disable_delayed_refill(vi);
+	cancel_delayed_work_sync(&vi->refill);
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		__virtnet_rx_pause(vi, &vi->rq[i]);
+}
 
+static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
+{
+	/*
+	 * Make sure refill_work does not run concurrently to
+	 * avoid napi_disable race which leads to deadlock.
+	 */
+	disable_delayed_refill(vi);
+	cancel_delayed_work_sync(&vi->refill);
+	__virtnet_rx_pause(vi, rq);
+}
+
+static void __virtnet_rx_resume(struct virtnet_info *vi,
+				struct receive_queue *rq,
+				bool refill)
+{
+	bool running = netif_running(vi->dev);
+	bool schedule_refill = false;
+
+	if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))
+		schedule_refill = true;
 	if (running)
 		virtnet_napi_enable(rq);
+
+	if (schedule_refill)
+		schedule_delayed_work(&vi->refill, 0);
+}
+
+static void virtnet_rx_resume_all(struct virtnet_info *vi)
+{
+	int i;
+
+	enable_delayed_refill(vi);
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		if (i < vi->curr_queue_pairs)
+			__virtnet_rx_resume(vi, &vi->rq[i], true);
+		else
+			__virtnet_rx_resume(vi, &vi->rq[i], false);
+	}
+}
+
+static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
+{
+	enable_delayed_refill(vi);
+	__virtnet_rx_resume(vi, rq, true);
 }
 
 static int virtnet_rx_resize(struct virtnet_info *vi,
@@ -3681,8 +3731,10 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 succ:
 	vi->curr_queue_pairs = queue_pairs;
 	/* virtnet_open() will refill when device is going to up. */
-	if (dev->flags & IFF_UP)
+	spin_lock_bh(&vi->refill_lock);
+	if (dev->flags & IFF_UP && vi->refill_enabled)
 		schedule_delayed_work(&vi->refill, 0);
+	spin_unlock_bh(&vi->refill_lock);
 
 	return 0;
 }
@@ -5626,6 +5678,10 @@ static void virtnet_get_base_stats(struct net_device *dev,
 
 	if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED)
 		tx->hw_drop_ratelimits = 0;
+
+	netdev_stat_queue_sum(dev,
+			      dev->real_num_rx_queues, vi->max_queue_pairs, rx,
+			      dev->real_num_tx_queues, vi->max_queue_pairs, tx);
 }
 
 static const struct netdev_stat_ops virtnet_stat_ops = {
@@ -5838,8 +5894,10 @@ static int virtnet_xsk_pool_enable(struct net_device *dev,
 
 	hdr_dma = virtqueue_dma_map_single_attrs(sq->vq, &xsk_hdr, vi->hdr_len,
 						 DMA_TO_DEVICE, 0);
-	if (virtqueue_dma_mapping_error(sq->vq, hdr_dma))
-		return -ENOMEM;
+	if (virtqueue_dma_mapping_error(sq->vq, hdr_dma)) {
+		err = -ENOMEM;
+		goto err_free_buffs;
+	}
 
 	err = xsk_pool_dma_map(pool, dma_dev, 0);
 	if (err)
@@ -5867,6 +5925,8 @@ err_rq:
 err_xsk_map:
 	virtqueue_dma_unmap_single_attrs(rq->vq, hdr_dma, vi->hdr_len,
 					 DMA_TO_DEVICE, 0);
+err_free_buffs:
+	kvfree(rq->xsk_buffs);
 	return err;
 }
 
@@ -5959,12 +6019,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	if (prog)
 		bpf_prog_add(prog, vi->max_queue_pairs - 1);
 
+	virtnet_rx_pause_all(vi);
+
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_disable(&vi->rq[i]);
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_tx_disable(&vi->sq[i]);
-		}
 	}
 
 	if (!prog) {
@@ -5996,13 +6056,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		vi->xdp_enabled = false;
 	}
 
+	virtnet_rx_resume_all(vi);
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (old_prog)
 			bpf_prog_put(old_prog);
-		if (netif_running(dev)) {
-			virtnet_napi_enable(&vi->rq[i]);
+		if (netif_running(dev))
 			virtnet_napi_tx_enable(&vi->sq[i]);
-		}
 	}
 
 	return 0;
@@ -6014,11 +6073,10 @@ err:
 			rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);
 	}
 
+	virtnet_rx_resume_all(vi);
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_enable(&vi->rq[i]);
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_tx_enable(&vi->sq[i]);
-		}
 	}
 	if (prog)
 		bpf_prog_sub(prog, vi->max_queue_pairs - 1);
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 3df6aabc7e33..c676979c7ab9 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -3607,8 +3607,6 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu)
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	int err = 0;
 
-	WRITE_ONCE(netdev->mtu, new_mtu);
-
 	/*
 	 * Reset_work may be in the middle of resetting the device, wait for its
 	 * completion.
@@ -3622,6 +3620,7 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu)
 
 		/* we need to re-create the rx queue based on the new mtu */
 		vmxnet3_rq_destroy_all(adapter);
+		WRITE_ONCE(netdev->mtu, new_mtu);
 		vmxnet3_adjust_rx_ring_size(adapter);
 		err = vmxnet3_rq_create_all(adapter);
 		if (err) {
@@ -3638,6 +3637,8 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu)
 				   "Closing it\n", err);
 			goto out;
 		}
+	} else {
+		WRITE_ONCE(netdev->mtu, new_mtu);
 	}
 
 out:
diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c
index 616ecc38d172..5f470499e600 100644
--- a/drivers/net/vmxnet3/vmxnet3_xdp.c
+++ b/drivers/net/vmxnet3/vmxnet3_xdp.c
@@ -397,7 +397,7 @@ vmxnet3_process_xdp(struct vmxnet3_adapter *adapter,
 
 	xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq);
 	xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset,
-			 rbi->len, false);
+			 rcd->len, false);
 	xdp_buff_clear_frags_flag(&xdp);
 
 	xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog);
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 7168b33adadb..9a4beea6ee0c 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -343,15 +343,13 @@ unlock:
 static bool qdisc_tx_is_default(const struct net_device *dev)
 {
 	struct netdev_queue *txq;
-	struct Qdisc *qdisc;
 
 	if (dev->num_tx_queues > 1)
 		return false;
 
 	txq = netdev_get_tx_queue(dev, 0);
-	qdisc = rcu_access_pointer(txq->qdisc);
 
-	return !qdisc->enqueue;
+	return qdisc_txq_has_no_queue(txq);
 }
 
 /* Local traffic destined to local address. Reinsert the packet to rx
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 9ccc3f09f71b..a56d7239b127 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -15,6 +15,7 @@
 #include <linux/igmp.h>
 #include <linux/if_ether.h>
 #include <linux/ethtool.h>
+#include <linux/rhashtable.h>
 #include <net/arp.h>
 #include <net/ndisc.h>
 #include <net/gro.h>
@@ -63,8 +64,12 @@ static int vxlan_sock_add(struct vxlan_dev *vxlan);
 
 static void vxlan_vs_del_dev(struct vxlan_dev *vxlan);
 
-/* salt for hash table */
-static u32 vxlan_salt __read_mostly;
+static const struct rhashtable_params vxlan_fdb_rht_params = {
+	.head_offset = offsetof(struct vxlan_fdb, rhnode),
+	.key_offset = offsetof(struct vxlan_fdb, key),
+	.key_len = sizeof(struct vxlan_fdb_key),
+	.automatic_shrinking = true,
+};
 
 static inline bool vxlan_collect_metadata(struct vxlan_sock *vs)
 {
@@ -186,7 +191,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 		} else if (nh) {
 			ndm->ndm_family = nh_family;
 		}
-		send_eth = !is_zero_ether_addr(fdb->eth_addr);
+		send_eth = !is_zero_ether_addr(fdb->key.eth_addr);
 	} else
 		ndm->ndm_family	= AF_BRIDGE;
 	ndm->ndm_state = fdb->state;
@@ -201,7 +206,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 			peernet2id(dev_net(vxlan->dev), vxlan->net)))
 		goto nla_put_failure;
 
-	if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
+	if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->key.eth_addr))
 		goto nla_put_failure;
 	if (nh) {
 		if (nla_put_u32(skb, NDA_NH_ID, nh_id))
@@ -223,9 +228,9 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 			goto nla_put_failure;
 	}
 
-	if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && fdb->vni &&
+	if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && fdb->key.vni &&
 	    nla_put_u32(skb, NDA_SRC_VNI,
-			be32_to_cpu(fdb->vni)))
+			be32_to_cpu(fdb->key.vni)))
 		goto nla_put_failure;
 
 	ci.ndm_used	 = jiffies_to_clock_t(now - READ_ONCE(fdb->used));
@@ -293,8 +298,8 @@ static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan,
 	fdb_info->remote_port = rd->remote_port;
 	fdb_info->remote_vni = rd->remote_vni;
 	fdb_info->remote_ifindex = rd->remote_ifindex;
-	memcpy(fdb_info->eth_addr, fdb->eth_addr, ETH_ALEN);
-	fdb_info->vni = fdb->vni;
+	memcpy(fdb_info->eth_addr, fdb->key.eth_addr, ETH_ALEN);
+	fdb_info->vni = fdb->key.vni;
 	fdb_info->offloaded = rd->offloaded;
 	fdb_info->added_by_user = fdb->flags & NTF_VXLAN_ADDED_BY_USER;
 }
@@ -366,67 +371,42 @@ static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN])
 	};
 	struct vxlan_rdst remote = { };
 
-	memcpy(f.eth_addr, eth_addr, ETH_ALEN);
+	memcpy(f.key.eth_addr, eth_addr, ETH_ALEN);
 
 	vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL);
 }
 
-/* Hash Ethernet address */
-static u32 eth_hash(const unsigned char *addr)
-{
-	u64 value = get_unaligned((u64 *)addr);
-
-	/* only want 6 bytes */
-#ifdef __BIG_ENDIAN
-	value >>= 16;
-#else
-	value <<= 16;
-#endif
-	return hash_64(value, FDB_HASH_BITS);
-}
-
-u32 eth_vni_hash(const unsigned char *addr, __be32 vni)
+/* Look up Ethernet address in forwarding table */
+static struct vxlan_fdb *vxlan_find_mac_rcu(struct vxlan_dev *vxlan,
+					    const u8 *mac, __be32 vni)
 {
-	/* use 1 byte of OUI and 3 bytes of NIC */
-	u32 key = get_unaligned((u32 *)(addr + 2));
-
-	return jhash_2words(key, vni, vxlan_salt) & (FDB_HASH_SIZE - 1);
-}
+	struct vxlan_fdb_key key;
 
-u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni)
-{
-	if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)
-		return eth_vni_hash(mac, vni);
+	memset(&key, 0, sizeof(key));
+	memcpy(key.eth_addr, mac, sizeof(key.eth_addr));
+	if (!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA))
+		key.vni = vxlan->default_dst.remote_vni;
 	else
-		return eth_hash(mac);
-}
+		key.vni = vni;
 
-/* Hash chain to use given mac address */
-static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan,
-						const u8 *mac, __be32 vni)
-{
-	return &vxlan->fdb_head[fdb_head_index(vxlan, mac, vni)];
+	return rhashtable_lookup(&vxlan->fdb_hash_tbl, &key,
+				 vxlan_fdb_rht_params);
 }
 
-/* Look up Ethernet address in forwarding table */
-static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan,
-					  const u8 *mac, __be32 vni)
+static struct vxlan_fdb *vxlan_find_mac_tx(struct vxlan_dev *vxlan,
+					   const u8 *mac, __be32 vni)
 {
-	struct hlist_head *head = vxlan_fdb_head(vxlan, mac, vni);
 	struct vxlan_fdb *f;
 
-	hlist_for_each_entry_rcu(f, head, hlist) {
-		if (ether_addr_equal(mac, f->eth_addr)) {
-			if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) {
-				if (vni == f->vni)
-					return f;
-			} else {
-				return f;
-			}
-		}
+	f = vxlan_find_mac_rcu(vxlan, mac, vni);
+	if (f) {
+		unsigned long now = jiffies;
+
+		if (READ_ONCE(f->used) != now)
+			WRITE_ONCE(f->used, now);
 	}
 
-	return NULL;
+	return f;
 }
 
 static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
@@ -434,13 +414,11 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
 {
 	struct vxlan_fdb *f;
 
-	f = __vxlan_find_mac(vxlan, mac, vni);
-	if (f) {
-		unsigned long now = jiffies;
+	lockdep_assert_held_once(&vxlan->hash_lock);
 
-		if (READ_ONCE(f->used) != now)
-			WRITE_ONCE(f->used, now);
-	}
+	rcu_read_lock();
+	f = vxlan_find_mac_rcu(vxlan, mac, vni);
+	rcu_read_unlock();
 
 	return f;
 }
@@ -480,7 +458,7 @@ int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni,
 
 	rcu_read_lock();
 
-	f = __vxlan_find_mac(vxlan, eth_addr, vni);
+	f = vxlan_find_mac_rcu(vxlan, eth_addr, vni);
 	if (!f) {
 		rc = -ENOENT;
 		goto out;
@@ -517,32 +495,28 @@ int vxlan_fdb_replay(const struct net_device *dev, __be32 vni,
 	struct vxlan_dev *vxlan;
 	struct vxlan_rdst *rdst;
 	struct vxlan_fdb *f;
-	unsigned int h;
 	int rc = 0;
 
 	if (!netif_is_vxlan(dev))
 		return -EINVAL;
 	vxlan = netdev_priv(dev);
 
-	for (h = 0; h < FDB_HASH_SIZE; ++h) {
-		spin_lock_bh(&vxlan->hash_lock[h]);
-		hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) {
-			if (f->vni == vni) {
-				list_for_each_entry(rdst, &f->remotes, list) {
-					rc = vxlan_fdb_notify_one(nb, vxlan,
-								  f, rdst,
-								  extack);
-					if (rc)
-						goto unlock;
-				}
+	spin_lock_bh(&vxlan->hash_lock);
+	hlist_for_each_entry(f, &vxlan->fdb_list, fdb_node) {
+		if (f->key.vni == vni) {
+			list_for_each_entry(rdst, &f->remotes, list) {
+				rc = vxlan_fdb_notify_one(nb, vxlan, f, rdst,
+							  extack);
+				if (rc)
+					goto unlock;
 			}
 		}
-		spin_unlock_bh(&vxlan->hash_lock[h]);
 	}
+	spin_unlock_bh(&vxlan->hash_lock);
 	return 0;
 
 unlock:
-	spin_unlock_bh(&vxlan->hash_lock[h]);
+	spin_unlock_bh(&vxlan->hash_lock);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(vxlan_fdb_replay);
@@ -552,20 +526,19 @@ void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni)
 	struct vxlan_dev *vxlan;
 	struct vxlan_rdst *rdst;
 	struct vxlan_fdb *f;
-	unsigned int h;
 
 	if (!netif_is_vxlan(dev))
 		return;
 	vxlan = netdev_priv(dev);
 
-	for (h = 0; h < FDB_HASH_SIZE; ++h) {
-		spin_lock_bh(&vxlan->hash_lock[h]);
-		hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist)
-			if (f->vni == vni)
-				list_for_each_entry(rdst, &f->remotes, list)
-					rdst->offloaded = false;
-		spin_unlock_bh(&vxlan->hash_lock[h]);
+	spin_lock_bh(&vxlan->hash_lock);
+	hlist_for_each_entry(f, &vxlan->fdb_list, fdb_node) {
+		if (f->key.vni == vni) {
+			list_for_each_entry(rdst, &f->remotes, list)
+				rdst->offloaded = false;
+		}
 	}
+	spin_unlock_bh(&vxlan->hash_lock);
 
 }
 EXPORT_SYMBOL_GPL(vxlan_fdb_clear_offload);
@@ -610,10 +583,10 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
 	if (rd == NULL)
 		return -ENOMEM;
 
-	if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) {
-		kfree(rd);
-		return -ENOMEM;
-	}
+	/* The driver can work correctly without a dst cache, so do not treat
+	 * dst cache initialization errors as fatal.
+	 */
+	dst_cache_init(&rd->dst_cache, GFP_ATOMIC | __GFP_NOWARN);
 
 	rd->remote_ip = *ip;
 	rd->remote_port = port;
@@ -803,27 +776,20 @@ static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, const u8 *mac,
 	f = kmalloc(sizeof(*f), GFP_ATOMIC);
 	if (!f)
 		return NULL;
+	memset(&f->key, 0, sizeof(f->key));
 	f->state = state;
 	f->flags = ndm_flags;
 	f->updated = f->used = jiffies;
-	f->vni = src_vni;
+	f->key.vni = src_vni;
 	f->nh = NULL;
 	RCU_INIT_POINTER(f->vdev, vxlan);
 	INIT_LIST_HEAD(&f->nh_list);
 	INIT_LIST_HEAD(&f->remotes);
-	memcpy(f->eth_addr, mac, ETH_ALEN);
+	memcpy(f->key.eth_addr, mac, ETH_ALEN);
 
 	return f;
 }
 
-static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac,
-			     __be32 src_vni, struct vxlan_fdb *f)
-{
-	++vxlan->addrcnt;
-	hlist_add_head_rcu(&f->hlist,
-			   vxlan_fdb_head(vxlan, mac, src_vni));
-}
-
 static int vxlan_fdb_nh_update(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb,
 			       u32 nhid, struct netlink_ext_ack *extack)
 {
@@ -913,10 +879,27 @@ int vxlan_fdb_create(struct vxlan_dev *vxlan,
 	if (rc < 0)
 		goto errout;
 
+	rc = rhashtable_lookup_insert_fast(&vxlan->fdb_hash_tbl, &f->rhnode,
+					   vxlan_fdb_rht_params);
+	if (rc)
+		goto destroy_remote;
+
+	++vxlan->addrcnt;
+	hlist_add_head_rcu(&f->fdb_node, &vxlan->fdb_list);
+
 	*fdb = f;
 
 	return 0;
 
+destroy_remote:
+	if (rcu_access_pointer(f->nh)) {
+		list_del_rcu(&f->nh_list);
+		nexthop_put(rtnl_dereference(f->nh));
+	} else {
+		list_del(&rd->list);
+		dst_cache_destroy(&rd->dst_cache);
+		kfree(rd);
+	}
 errout:
 	kfree(f);
 	return rc;
@@ -953,7 +936,7 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
 {
 	struct vxlan_rdst *rd;
 
-	netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr);
+	netdev_dbg(vxlan->dev, "delete %pM\n", f->key.eth_addr);
 
 	--vxlan->addrcnt;
 	if (do_notify) {
@@ -966,7 +949,9 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
 						 swdev_notify, NULL);
 	}
 
-	hlist_del_rcu(&f->hlist);
+	hlist_del_init_rcu(&f->fdb_node);
+	rhashtable_remove_fast(&vxlan->fdb_hash_tbl, &f->rhnode,
+			       vxlan_fdb_rht_params);
 	list_del_rcu(&f->nh_list);
 	call_rcu(&f->rcu, vxlan_fdb_free);
 }
@@ -1024,8 +1009,8 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 
 	if ((flags & NLM_F_REPLACE)) {
 		/* Only change unicasts */
-		if (!(is_multicast_ether_addr(f->eth_addr) ||
-		      is_zero_ether_addr(f->eth_addr))) {
+		if (!(is_multicast_ether_addr(f->key.eth_addr) ||
+		      is_zero_ether_addr(f->key.eth_addr))) {
 			if (nhid) {
 				rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack);
 				if (rc < 0)
@@ -1041,8 +1026,8 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 		}
 	}
 	if ((flags & NLM_F_APPEND) &&
-	    (is_multicast_ether_addr(f->eth_addr) ||
-	     is_zero_ether_addr(f->eth_addr))) {
+	    (is_multicast_ether_addr(f->key.eth_addr) ||
+	     is_zero_ether_addr(f->key.eth_addr))) {
 		rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
 
 		if (rc < 0)
@@ -1101,7 +1086,6 @@ static int vxlan_fdb_update_create(struct vxlan_dev *vxlan,
 	if (rc < 0)
 		return rc;
 
-	vxlan_fdb_insert(vxlan, mac, src_vni, f);
 	rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH,
 			      swdev_notify, extack);
 	if (rc)
@@ -1125,7 +1109,7 @@ int vxlan_fdb_update(struct vxlan_dev *vxlan,
 {
 	struct vxlan_fdb *f;
 
-	f = __vxlan_find_mac(vxlan, mac, src_vni);
+	f = vxlan_find_mac(vxlan, mac, src_vni);
 	if (f) {
 		if (flags & NLM_F_EXCL) {
 			netdev_dbg(vxlan->dev,
@@ -1253,7 +1237,6 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	__be16 port;
 	__be32 src_vni, vni;
 	u32 ifindex, nhid;
-	u32 hash_index;
 	int err;
 
 	if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) {
@@ -1273,13 +1256,12 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family)
 		return -EAFNOSUPPORT;
 
-	hash_index = fdb_head_index(vxlan, addr, src_vni);
-	spin_lock_bh(&vxlan->hash_lock[hash_index]);
+	spin_lock_bh(&vxlan->hash_lock);
 	err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
 			       port, src_vni, vni, ifindex,
 			       ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER,
 			       nhid, true, extack);
-	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+	spin_unlock_bh(&vxlan->hash_lock);
 
 	if (!err)
 		*notified = true;
@@ -1296,7 +1278,7 @@ int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 	struct vxlan_fdb *f;
 	int err = -ENOENT;
 
-	f = __vxlan_find_mac(vxlan, addr, src_vni);
+	f = vxlan_find_mac(vxlan, addr, src_vni);
 	if (!f)
 		return err;
 
@@ -1330,7 +1312,6 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 	union vxlan_addr ip;
 	__be32 src_vni, vni;
 	u32 ifindex, nhid;
-	u32 hash_index;
 	__be16 port;
 	int err;
 
@@ -1339,11 +1320,10 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 	if (err)
 		return err;
 
-	hash_index = fdb_head_index(vxlan, addr, src_vni);
-	spin_lock_bh(&vxlan->hash_lock[hash_index]);
+	spin_lock_bh(&vxlan->hash_lock);
 	err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex,
 				 true);
-	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+	spin_unlock_bh(&vxlan->hash_lock);
 
 	if (!err)
 		*notified = true;
@@ -1358,52 +1338,46 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 {
 	struct ndo_fdb_dump_context *ctx = (void *)cb->ctx;
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	unsigned int h;
+	struct vxlan_fdb *f;
 	int err = 0;
 
-	for (h = 0; h < FDB_HASH_SIZE; ++h) {
-		struct vxlan_fdb *f;
-
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) {
-			struct vxlan_rdst *rd;
-
-			if (rcu_access_pointer(f->nh)) {
-				if (*idx < ctx->fdb_idx)
-					goto skip_nh;
-				err = vxlan_fdb_info(skb, vxlan, f,
-						     NETLINK_CB(cb->skb).portid,
-						     cb->nlh->nlmsg_seq,
-						     RTM_NEWNEIGH,
-						     NLM_F_MULTI, NULL);
-				if (err < 0) {
-					rcu_read_unlock();
-					goto out;
-				}
-skip_nh:
-				*idx += 1;
-				continue;
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(f, &vxlan->fdb_list, fdb_node) {
+		struct vxlan_rdst *rd;
+
+		if (rcu_access_pointer(f->nh)) {
+			if (*idx < ctx->fdb_idx)
+				goto skip_nh;
+			err = vxlan_fdb_info(skb, vxlan, f,
+					     NETLINK_CB(cb->skb).portid,
+					     cb->nlh->nlmsg_seq,
+					     RTM_NEWNEIGH, NLM_F_MULTI, NULL);
+			if (err < 0) {
+				rcu_read_unlock();
+				goto out;
 			}
+skip_nh:
+			*idx += 1;
+			continue;
+		}
 
-			list_for_each_entry_rcu(rd, &f->remotes, list) {
-				if (*idx < ctx->fdb_idx)
-					goto skip;
-
-				err = vxlan_fdb_info(skb, vxlan, f,
-						     NETLINK_CB(cb->skb).portid,
-						     cb->nlh->nlmsg_seq,
-						     RTM_NEWNEIGH,
-						     NLM_F_MULTI, rd);
-				if (err < 0) {
-					rcu_read_unlock();
-					goto out;
-				}
-skip:
-				*idx += 1;
+		list_for_each_entry_rcu(rd, &f->remotes, list) {
+			if (*idx < ctx->fdb_idx)
+				goto skip;
+
+			err = vxlan_fdb_info(skb, vxlan, f,
+					     NETLINK_CB(cb->skb).portid,
+					     cb->nlh->nlmsg_seq,
+					     RTM_NEWNEIGH, NLM_F_MULTI, rd);
+			if (err < 0) {
+				rcu_read_unlock();
+				goto out;
 			}
+skip:
+			*idx += 1;
 		}
-		rcu_read_unlock();
 	}
+	rcu_read_unlock();
 out:
 	return err;
 }
@@ -1427,7 +1401,7 @@ static int vxlan_fdb_get(struct sk_buff *skb,
 
 	rcu_read_lock();
 
-	f = __vxlan_find_mac(vxlan, addr, vni);
+	f = vxlan_find_mac_rcu(vxlan, addr, vni);
 	if (!f) {
 		NL_SET_ERR_MSG(extack, "Fdb entry not found");
 		err = -ENOENT;
@@ -1463,7 +1437,7 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 		ifindex = src_ifindex;
 #endif
 
-	f = __vxlan_find_mac(vxlan, src_mac, vni);
+	f = vxlan_find_mac_rcu(vxlan, src_mac, vni);
 	if (likely(f)) {
 		struct vxlan_rdst *rdst = first_remote_rcu(f);
 		unsigned long now = jiffies;
@@ -1491,10 +1465,8 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 		rdst->remote_ip = *src_ip;
 		vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL);
 	} else {
-		u32 hash_index = fdb_head_index(vxlan, src_mac, vni);
-
 		/* learned new entry */
-		spin_lock(&vxlan->hash_lock[hash_index]);
+		spin_lock(&vxlan->hash_lock);
 
 		/* close off race between vxlan_flush and incoming packets */
 		if (netif_running(dev))
@@ -1505,7 +1477,7 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 					 vni,
 					 vxlan->default_dst.remote_vni,
 					 ifindex, NTF_SELF, 0, true, NULL);
-		spin_unlock(&vxlan->hash_lock[hash_index]);
+		spin_unlock(&vxlan->hash_lock);
 	}
 
 	return SKB_NOT_DROPPED_YET;
@@ -1916,12 +1888,15 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 			goto out;
 		}
 
-		f = vxlan_find_mac(vxlan, n->ha, vni);
+		rcu_read_lock();
+		f = vxlan_find_mac_tx(vxlan, n->ha, vni);
 		if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
 			/* bridge-local neighbor */
 			neigh_release(n);
+			rcu_read_unlock();
 			goto out;
 		}
+		rcu_read_unlock();
 
 		reply = arp_create(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha,
 				n->ha, sha);
@@ -2080,7 +2055,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 			goto out;
 		}
 
-		f = vxlan_find_mac(vxlan, n->ha, vni);
+		f = vxlan_find_mac_tx(vxlan, n->ha, vni);
 		if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
 			/* bridge-local neighbor */
 			neigh_release(n);
@@ -2648,14 +2623,10 @@ static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev,
 	memset(&nh_rdst, 0, sizeof(struct vxlan_rdst));
 	hash = skb_get_hash(skb);
 
-	rcu_read_lock();
 	nh = rcu_dereference(f->nh);
-	if (!nh) {
-		rcu_read_unlock();
+	if (!nh)
 		goto drop;
-	}
 	do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst);
-	rcu_read_unlock();
 
 	if (likely(do_xmit))
 		vxlan_xmit_one(skb, dev, vni, &nh_rdst, did_rsc);
@@ -2782,7 +2753,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	eth = eth_hdr(skb);
-	f = vxlan_find_mac(vxlan, eth->h_dest, vni);
+	rcu_read_lock();
+	f = vxlan_find_mac_tx(vxlan, eth->h_dest, vni);
 	did_rsc = false;
 
 	if (f && (f->flags & NTF_ROUTER) && (vxlan->cfg.flags & VXLAN_F_RSC) &&
@@ -2790,11 +2762,11 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	     ntohs(eth->h_proto) == ETH_P_IPV6)) {
 		did_rsc = route_shortcircuit(dev, skb);
 		if (did_rsc)
-			f = vxlan_find_mac(vxlan, eth->h_dest, vni);
+			f = vxlan_find_mac_tx(vxlan, eth->h_dest, vni);
 	}
 
 	if (f == NULL) {
-		f = vxlan_find_mac(vxlan, all_zeros_mac, vni);
+		f = vxlan_find_mac_tx(vxlan, all_zeros_mac, vni);
 		if (f == NULL) {
 			if ((vxlan->cfg.flags & VXLAN_F_L2MISS) &&
 			    !is_multicast_ether_addr(eth->h_dest))
@@ -2804,7 +2776,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 			vxlan_vnifilter_count(vxlan, vni, NULL,
 					      VXLAN_VNI_STATS_TX_DROPS, 0);
 			kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET);
-			return NETDEV_TX_OK;
+			goto out;
 		}
 	}
 
@@ -2829,6 +2801,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 			kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET);
 	}
 
+out:
+	rcu_read_unlock();
 	return NETDEV_TX_OK;
 }
 
@@ -2837,38 +2811,36 @@ static void vxlan_cleanup(struct timer_list *t)
 {
 	struct vxlan_dev *vxlan = from_timer(vxlan, t, age_timer);
 	unsigned long next_timer = jiffies + FDB_AGE_INTERVAL;
-	unsigned int h;
+	struct vxlan_fdb *f;
 
 	if (!netif_running(vxlan->dev))
 		return;
 
-	for (h = 0; h < FDB_HASH_SIZE; ++h) {
-		struct hlist_node *p, *n;
-
-		spin_lock(&vxlan->hash_lock[h]);
-		hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
-			struct vxlan_fdb *f
-				= container_of(p, struct vxlan_fdb, hlist);
-			unsigned long timeout;
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(f, &vxlan->fdb_list, fdb_node) {
+		unsigned long timeout;
 
-			if (f->state & (NUD_PERMANENT | NUD_NOARP))
-				continue;
+		if (f->state & (NUD_PERMANENT | NUD_NOARP))
+			continue;
 
-			if (f->flags & NTF_EXT_LEARNED)
-				continue;
+		if (f->flags & NTF_EXT_LEARNED)
+			continue;
 
-			timeout = READ_ONCE(f->updated) + vxlan->cfg.age_interval * HZ;
-			if (time_before_eq(timeout, jiffies)) {
-				netdev_dbg(vxlan->dev,
-					   "garbage collect %pM\n",
-					   f->eth_addr);
+		timeout = READ_ONCE(f->updated) + vxlan->cfg.age_interval * HZ;
+		if (time_before_eq(timeout, jiffies)) {
+			spin_lock(&vxlan->hash_lock);
+			if (!hlist_unhashed(&f->fdb_node)) {
+				netdev_dbg(vxlan->dev, "garbage collect %pM\n",
+					   f->key.eth_addr);
 				f->state = NUD_STALE;
 				vxlan_fdb_destroy(vxlan, f, true, true);
-			} else if (time_before(timeout, next_timer))
-				next_timer = timeout;
+			}
+			spin_unlock(&vxlan->hash_lock);
+		} else if (time_before(timeout, next_timer)) {
+			next_timer = timeout;
 		}
-		spin_unlock(&vxlan->hash_lock[h]);
 	}
+	rcu_read_unlock();
 
 	mod_timer(&vxlan->age_timer, next_timer);
 }
@@ -2903,10 +2875,14 @@ static int vxlan_init(struct net_device *dev)
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	int err;
 
+	err = rhashtable_init(&vxlan->fdb_hash_tbl, &vxlan_fdb_rht_params);
+	if (err)
+		return err;
+
 	if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) {
 		err = vxlan_vnigroup_init(vxlan);
 		if (err)
-			return err;
+			goto err_rhashtable_destroy;
 	}
 
 	err = gro_cells_init(&vxlan->gro_cells, dev);
@@ -2925,21 +2901,11 @@ err_gro_cells_destroy:
 err_vnigroup_uninit:
 	if (vxlan->cfg.flags & VXLAN_F_VNIFILTER)
 		vxlan_vnigroup_uninit(vxlan);
+err_rhashtable_destroy:
+	rhashtable_destroy(&vxlan->fdb_hash_tbl);
 	return err;
 }
 
-static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
-{
-	struct vxlan_fdb *f;
-	u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, vni);
-
-	spin_lock_bh(&vxlan->hash_lock[hash_index]);
-	f = __vxlan_find_mac(vxlan, all_zeros_mac, vni);
-	if (f)
-		vxlan_fdb_destroy(vxlan, f, true, true);
-	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
-}
-
 static void vxlan_uninit(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
@@ -2951,7 +2917,7 @@ static void vxlan_uninit(struct net_device *dev)
 
 	gro_cells_destroy(&vxlan->gro_cells);
 
-	vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni);
+	rhashtable_destroy(&vxlan->fdb_hash_tbl);
 }
 
 /* Start ageing timer and join group when device is brought up */
@@ -2992,7 +2958,8 @@ struct vxlan_fdb_flush_desc {
 static bool vxlan_fdb_is_default_entry(const struct vxlan_fdb *f,
 				       const struct vxlan_dev *vxlan)
 {
-	return is_zero_ether_addr(f->eth_addr) && f->vni == vxlan->cfg.vni;
+	return is_zero_ether_addr(f->key.eth_addr) &&
+	       f->key.vni == vxlan->cfg.vni;
 }
 
 static bool vxlan_fdb_nhid_matches(const struct vxlan_fdb *f, u32 nhid)
@@ -3015,7 +2982,7 @@ static bool vxlan_fdb_flush_matches(const struct vxlan_fdb *f,
 	if (desc->ignore_default_entry && vxlan_fdb_is_default_entry(f, vxlan))
 		return false;
 
-	if (desc->src_vni && f->vni != desc->src_vni)
+	if (desc->src_vni && f->key.vni != desc->src_vni)
 		return false;
 
 	if (desc->nhid && !vxlan_fdb_nhid_matches(f, desc->nhid))
@@ -3071,33 +3038,32 @@ static void vxlan_flush(struct vxlan_dev *vxlan,
 			const struct vxlan_fdb_flush_desc *desc)
 {
 	bool match_remotes = vxlan_fdb_flush_should_match_remotes(desc);
-	unsigned int h;
-
-	for (h = 0; h < FDB_HASH_SIZE; ++h) {
-		struct hlist_node *p, *n;
+	struct vxlan_fdb *f;
 
-		spin_lock_bh(&vxlan->hash_lock[h]);
-		hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
-			struct vxlan_fdb *f
-				= container_of(p, struct vxlan_fdb, hlist);
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(f, &vxlan->fdb_list, fdb_node) {
+		if (!vxlan_fdb_flush_matches(f, vxlan, desc))
+			continue;
 
-			if (!vxlan_fdb_flush_matches(f, vxlan, desc))
-				continue;
+		spin_lock_bh(&vxlan->hash_lock);
+		if (hlist_unhashed(&f->fdb_node))
+			goto unlock;
 
-			if (match_remotes) {
-				bool destroy_fdb = false;
+		if (match_remotes) {
+			bool destroy_fdb = false;
 
-				vxlan_fdb_flush_match_remotes(f, vxlan, desc,
-							      &destroy_fdb);
+			vxlan_fdb_flush_match_remotes(f, vxlan, desc,
+						      &destroy_fdb);
 
-				if (!destroy_fdb)
-					continue;
-			}
-
-			vxlan_fdb_destroy(vxlan, f, true, true);
+			if (!destroy_fdb)
+				goto unlock;
 		}
-		spin_unlock_bh(&vxlan->hash_lock[h]);
+
+		vxlan_fdb_destroy(vxlan, f, true, true);
+unlock:
+		spin_unlock_bh(&vxlan->hash_lock);
 	}
+	rcu_read_unlock();
 }
 
 static const struct nla_policy vxlan_del_bulk_policy[NDA_MAX + 1] = {
@@ -3185,7 +3151,7 @@ static int vxlan_stop(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_fdb_flush_desc desc = {
-		/* Default entry is deleted at vxlan_uninit. */
+		/* Default entry is deleted at vxlan_dellink. */
 		.ignore_default_entry = true,
 		.state = 0,
 		.state_mask = NUD_PERMANENT | NUD_NOARP,
@@ -3348,7 +3314,6 @@ static void vxlan_offload_rx_ports(struct net_device *dev, bool push)
 static void vxlan_setup(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	unsigned int h;
 
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
@@ -3375,15 +3340,13 @@ static void vxlan_setup(struct net_device *dev)
 
 	dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS;
 	INIT_LIST_HEAD(&vxlan->next);
+	spin_lock_init(&vxlan->hash_lock);
 
 	timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE);
 
 	vxlan->dev = dev;
 
-	for (h = 0; h < FDB_HASH_SIZE; ++h) {
-		spin_lock_init(&vxlan->hash_lock[h]);
-		INIT_HLIST_HEAD(&vxlan->fdb_head[h]);
-	}
+	INIT_HLIST_HEAD(&vxlan->fdb_list);
 }
 
 static void vxlan_ether_setup(struct net_device *dev)
@@ -3960,8 +3923,6 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct net_device *remote_dev = NULL;
-	struct vxlan_fdb *f = NULL;
-	bool unregister = false;
 	struct vxlan_rdst *dst;
 	int err;
 
@@ -3972,72 +3933,54 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 
 	dev->ethtool_ops = &vxlan_ethtool_ops;
 
-	/* create an fdb entry for a valid default destination */
-	if (!vxlan_addr_any(&dst->remote_ip)) {
-		err = vxlan_fdb_create(vxlan, all_zeros_mac,
-				       &dst->remote_ip,
-				       NUD_REACHABLE | NUD_PERMANENT,
-				       vxlan->cfg.dst_port,
-				       dst->remote_vni,
-				       dst->remote_vni,
-				       dst->remote_ifindex,
-				       NTF_SELF, 0, &f, extack);
-		if (err)
-			return err;
-	}
-
 	err = register_netdevice(dev);
 	if (err)
-		goto errout;
-	unregister = true;
+		return err;
 
 	if (dst->remote_ifindex) {
 		remote_dev = __dev_get_by_index(net, dst->remote_ifindex);
 		if (!remote_dev) {
 			err = -ENODEV;
-			goto errout;
+			goto unregister;
 		}
 
 		err = netdev_upper_dev_link(remote_dev, dev, extack);
 		if (err)
-			goto errout;
+			goto unregister;
+
+		dst->remote_dev = remote_dev;
 	}
 
 	err = rtnl_configure_link(dev, NULL, 0, NULL);
 	if (err < 0)
 		goto unlink;
 
-	if (f) {
-		vxlan_fdb_insert(vxlan, all_zeros_mac, dst->remote_vni, f);
-
-		/* notify default fdb entry */
-		err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f),
-				       RTM_NEWNEIGH, true, extack);
-		if (err) {
-			vxlan_fdb_destroy(vxlan, f, false, false);
-			if (remote_dev)
-				netdev_upper_dev_unlink(remote_dev, dev);
-			goto unregister;
-		}
+	/* create an fdb entry for a valid default destination */
+	if (!vxlan_addr_any(&dst->remote_ip)) {
+		spin_lock_bh(&vxlan->hash_lock);
+		err = vxlan_fdb_update(vxlan, all_zeros_mac,
+				       &dst->remote_ip,
+				       NUD_REACHABLE | NUD_PERMANENT,
+				       NLM_F_EXCL | NLM_F_CREATE,
+				       vxlan->cfg.dst_port,
+				       dst->remote_vni,
+				       dst->remote_vni,
+				       dst->remote_ifindex,
+				       NTF_SELF, 0, true, extack);
+		spin_unlock_bh(&vxlan->hash_lock);
+		if (err)
+			goto unlink;
 	}
 
 	list_add(&vxlan->next, &vn->vxlan_list);
-	if (remote_dev)
-		dst->remote_dev = remote_dev;
+
 	return 0;
+
 unlink:
 	if (remote_dev)
 		netdev_upper_dev_unlink(remote_dev, dev);
-errout:
-	/* unregister_netdevice() destroys the default FDB entry with deletion
-	 * notification. But the addition notification was not sent yet, so
-	 * destroy the entry by hand here.
-	 */
-	if (f)
-		__vxlan_fdb_free(f);
 unregister:
-	if (unregister)
-		unregister_netdevice(dev);
+	unregister_netdevice(dev);
 	return err;
 }
 
@@ -4454,9 +4397,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 
 	/* handle default dst entry */
 	if (rem_ip_changed) {
-		u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni);
-
-		spin_lock_bh(&vxlan->hash_lock[hash_index]);
+		spin_lock_bh(&vxlan->hash_lock);
 		if (!vxlan_addr_any(&conf.remote_ip)) {
 			err = vxlan_fdb_update(vxlan, all_zeros_mac,
 					       &conf.remote_ip,
@@ -4467,7 +4408,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					       conf.remote_ifindex,
 					       NTF_SELF, 0, true, extack);
 			if (err) {
-				spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+				spin_unlock_bh(&vxlan->hash_lock);
 				netdev_adjacent_change_abort(dst->remote_dev,
 							     lowerdev, dev);
 				return err;
@@ -4481,7 +4422,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					   dst->remote_vni,
 					   dst->remote_ifindex,
 					   true);
-		spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+		spin_unlock_bh(&vxlan->hash_lock);
 
 		/* If vni filtering device, also update fdb entries of
 		 * all vnis that were using default remote ip
@@ -4518,10 +4459,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_fdb_flush_desc desc = {
-		/* Default entry is deleted at vxlan_uninit. */
-		.ignore_default_entry = true,
-	};
+	struct vxlan_fdb_flush_desc desc = {};
 
 	vxlan_flush(vxlan, &desc);
 
@@ -4784,13 +4722,10 @@ vxlan_fdb_offloaded_set(struct net_device *dev,
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_rdst *rdst;
 	struct vxlan_fdb *f;
-	u32 hash_index;
-
-	hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni);
 
-	spin_lock_bh(&vxlan->hash_lock[hash_index]);
+	spin_lock_bh(&vxlan->hash_lock);
 
-	f = __vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
+	f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	if (!f)
 		goto out;
 
@@ -4804,7 +4739,7 @@ vxlan_fdb_offloaded_set(struct net_device *dev,
 	rdst->offloaded = fdb_info->offloaded;
 
 out:
-	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+	spin_unlock_bh(&vxlan->hash_lock);
 }
 
 static int
@@ -4813,13 +4748,11 @@ vxlan_fdb_external_learn_add(struct net_device *dev,
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct netlink_ext_ack *extack;
-	u32 hash_index;
 	int err;
 
-	hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	extack = switchdev_notifier_info_to_extack(&fdb_info->info);
 
-	spin_lock_bh(&vxlan->hash_lock[hash_index]);
+	spin_lock_bh(&vxlan->hash_lock);
 	err = vxlan_fdb_update(vxlan, fdb_info->eth_addr, &fdb_info->remote_ip,
 			       NUD_REACHABLE,
 			       NLM_F_CREATE | NLM_F_REPLACE,
@@ -4829,7 +4762,7 @@ vxlan_fdb_external_learn_add(struct net_device *dev,
 			       fdb_info->remote_ifindex,
 			       NTF_USE | NTF_SELF | NTF_EXT_LEARNED,
 			       0, false, extack);
-	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+	spin_unlock_bh(&vxlan->hash_lock);
 
 	return err;
 }
@@ -4840,13 +4773,11 @@ vxlan_fdb_external_learn_del(struct net_device *dev,
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_fdb *f;
-	u32 hash_index;
 	int err = 0;
 
-	hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni);
-	spin_lock_bh(&vxlan->hash_lock[hash_index]);
+	spin_lock_bh(&vxlan->hash_lock);
 
-	f = __vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
+	f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	if (!f)
 		err = -ENOENT;
 	else if (f->flags & NTF_EXT_LEARNED)
@@ -4858,7 +4789,7 @@ vxlan_fdb_external_learn_del(struct net_device *dev,
 					 fdb_info->remote_ifindex,
 					 false);
 
-	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+	spin_unlock_bh(&vxlan->hash_lock);
 
 	return err;
 }
@@ -4907,18 +4838,15 @@ static void vxlan_fdb_nh_flush(struct nexthop *nh)
 {
 	struct vxlan_fdb *fdb;
 	struct vxlan_dev *vxlan;
-	u32 hash_index;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(fdb, &nh->fdb_list, nh_list) {
 		vxlan = rcu_dereference(fdb->vdev);
 		WARN_ON(!vxlan);
-		hash_index = fdb_head_index(vxlan, fdb->eth_addr,
-					    vxlan->default_dst.remote_vni);
-		spin_lock_bh(&vxlan->hash_lock[hash_index]);
-		if (!hlist_unhashed(&fdb->hlist))
+		spin_lock_bh(&vxlan->hash_lock);
+		if (!hlist_unhashed(&fdb->fdb_node))
 			vxlan_fdb_destroy(vxlan, fdb, false, false);
-		spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+		spin_unlock_bh(&vxlan->hash_lock);
 	}
 	rcu_read_unlock();
 }
@@ -4966,19 +4894,15 @@ static void __net_exit vxlan_destroy_tunnels(struct vxlan_net *vn,
 		vxlan_dellink(vxlan->dev, dev_to_kill);
 }
 
-static void __net_exit vxlan_exit_batch_rtnl(struct list_head *net_list,
-					     struct list_head *dev_to_kill)
+static void __net_exit vxlan_exit_rtnl(struct net *net,
+				       struct list_head *dev_to_kill)
 {
-	struct net *net;
-
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list) {
-		struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 
-		__unregister_nexthop_notifier(net, &vn->nexthop_notifier_block);
+	ASSERT_RTNL_NET(net);
 
-		vxlan_destroy_tunnels(vn, dev_to_kill);
-	}
+	__unregister_nexthop_notifier(net, &vn->nexthop_notifier_block);
+	vxlan_destroy_tunnels(vn, dev_to_kill);
 }
 
 static void __net_exit vxlan_exit_net(struct net *net)
@@ -4992,7 +4916,7 @@ static void __net_exit vxlan_exit_net(struct net *net)
 
 static struct pernet_operations vxlan_net_ops = {
 	.init = vxlan_init_net,
-	.exit_batch_rtnl = vxlan_exit_batch_rtnl,
+	.exit_rtnl = vxlan_exit_rtnl,
 	.exit = vxlan_exit_net,
 	.id   = &vxlan_net_id,
 	.size = sizeof(struct vxlan_net),
@@ -5002,8 +4926,6 @@ static int __init vxlan_init_module(void)
 {
 	int rc;
 
-	get_random_bytes(&vxlan_salt, sizeof(vxlan_salt));
-
 	rc = register_pernet_subsys(&vxlan_net_ops);
 	if (rc)
 		goto out1;
diff --git a/drivers/net/vxlan/vxlan_private.h b/drivers/net/vxlan/vxlan_private.h
index 76a351a997d5..d328aed9feef 100644
--- a/drivers/net/vxlan/vxlan_private.h
+++ b/drivers/net/vxlan/vxlan_private.h
@@ -24,18 +24,23 @@ struct vxlan_net {
 	struct notifier_block nexthop_notifier_block;
 };
 
+struct vxlan_fdb_key {
+	u8 eth_addr[ETH_ALEN];
+	__be32 vni;
+};
+
 /* Forwarding table entry */
 struct vxlan_fdb {
-	struct hlist_node hlist;	/* linked list of entries */
+	struct rhash_head rhnode;
 	struct rcu_head	  rcu;
 	unsigned long	  updated;	/* jiffies */
 	unsigned long	  used;
 	struct list_head  remotes;
-	u8		  eth_addr[ETH_ALEN];
+	struct vxlan_fdb_key key;
 	u16		  state;	/* see ndm_state */
-	__be32		  vni;
 	u16		  flags;	/* see ndm_flags and below */
 	struct list_head  nh_list;
+	struct hlist_node fdb_node;
 	struct nexthop __rcu *nh;
 	struct vxlan_dev  __rcu *vdev;
 };
diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c
index 6e6e9f05509a..186d0660669a 100644
--- a/drivers/net/vxlan/vxlan_vnifilter.c
+++ b/drivers/net/vxlan/vxlan_vnifilter.c
@@ -411,13 +411,12 @@ static int vxlan_vnifilter_dump(struct sk_buff *skb, struct netlink_callback *cb
 	struct tunnel_msg *tmsg;
 	struct net_device *dev;
 
-	if (cb->nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct tunnel_msg))) {
+	tmsg = nlmsg_payload(cb->nlh, sizeof(*tmsg));
+	if (!tmsg) {
 		NL_SET_ERR_MSG(cb->extack, "Invalid msg length");
 		return -EINVAL;
 	}
 
-	tmsg = nlmsg_data(cb->nlh);
-
 	if (tmsg->flags & ~TUNNEL_MSG_VALID_USER_FLAGS) {
 		NL_SET_ERR_MSG(cb->extack, "Invalid tunnelmsg flags in ancillary header");
 		return -EINVAL;
@@ -483,11 +482,9 @@ static int vxlan_update_default_fdb_entry(struct vxlan_dev *vxlan, __be32 vni,
 					  struct netlink_ext_ack *extack)
 {
 	struct vxlan_rdst *dst = &vxlan->default_dst;
-	u32 hash_index;
 	int err = 0;
 
-	hash_index = fdb_head_index(vxlan, all_zeros_mac, vni);
-	spin_lock_bh(&vxlan->hash_lock[hash_index]);
+	spin_lock_bh(&vxlan->hash_lock);
 	if (remote_ip && !vxlan_addr_any(remote_ip)) {
 		err = vxlan_fdb_update(vxlan, all_zeros_mac,
 				       remote_ip,
@@ -499,7 +496,7 @@ static int vxlan_update_default_fdb_entry(struct vxlan_dev *vxlan, __be32 vni,
 				       dst->remote_ifindex,
 				       NTF_SELF, 0, true, extack);
 		if (err) {
-			spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+			spin_unlock_bh(&vxlan->hash_lock);
 			return err;
 		}
 	}
@@ -512,7 +509,7 @@ static int vxlan_update_default_fdb_entry(struct vxlan_dev *vxlan, __be32 vni,
 				   dst->remote_ifindex,
 				   true);
 	}
-	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+	spin_unlock_bh(&vxlan->hash_lock);
 
 	return err;
 }
@@ -627,7 +624,8 @@ static void vxlan_vni_delete_group(struct vxlan_dev *vxlan,
 	 * default dst remote_ip previously added for this vni
 	 */
 	if (!vxlan_addr_any(&vninode->remote_ip) ||
-	    !vxlan_addr_any(&dst->remote_ip))
+	    !vxlan_addr_any(&dst->remote_ip)) {
+		spin_lock_bh(&vxlan->hash_lock);
 		__vxlan_fdb_delete(vxlan, all_zeros_mac,
 				   (vxlan_addr_any(&vninode->remote_ip) ?
 				   dst->remote_ip : vninode->remote_ip),
@@ -635,6 +633,8 @@ static void vxlan_vni_delete_group(struct vxlan_dev *vxlan,
 				   vninode->vni, vninode->vni,
 				   dst->remote_ifindex,
 				   true);
+		spin_unlock_bh(&vxlan->hash_lock);
+	}
 
 	if (vxlan->dev->flags & IFF_UP) {
 		if (vxlan_addr_multicast(&vninode->remote_ip) &&
diff --git a/drivers/net/wireless/ath/ath10k/ahb.c b/drivers/net/wireless/ath/ath10k/ahb.c
index db9f9ebcb62d..eb8b35b6224d 100644
--- a/drivers/net/wireless/ath/ath10k/ahb.c
+++ b/drivers/net/wireless/ath/ath10k/ahb.c
@@ -497,7 +497,7 @@ static int ath10k_ahb_resource_init(struct ath10k *ar)
 
 	ath10k_dbg(ar, ATH10K_DBG_BOOT, "irq: %d\n", ar_ahb->irq);
 
-	ath10k_dbg(ar, ATH10K_DBG_BOOT, "mem: 0x%pK mem_len: %lu gcc mem: 0x%pK tcsr_mem: 0x%pK\n",
+	ath10k_dbg(ar, ATH10K_DBG_BOOT, "mem: 0x%p mem_len: %lu gcc mem: 0x%p tcsr_mem: 0x%p\n",
 		   ar_ahb->mem, ar_ahb->mem_len,
 		   ar_ahb->gcc_mem, ar_ahb->tcsr_mem);
 	return 0;
diff --git a/drivers/net/wireless/ath/ath10k/bmi.c b/drivers/net/wireless/ath/ath10k/bmi.c
index 9a4f8e815412..48efdc71d54d 100644
--- a/drivers/net/wireless/ath/ath10k/bmi.c
+++ b/drivers/net/wireless/ath/ath10k/bmi.c
@@ -349,7 +349,7 @@ static int ath10k_bmi_lz_data_large(struct ath10k *ar, const void *buffer, u32 l
 	int ret;
 	size_t buf_len;
 
-	ath10k_dbg(ar, ATH10K_DBG_BMI, "large bmi lz data buffer 0x%pK length %d\n",
+	ath10k_dbg(ar, ATH10K_DBG_BMI, "large bmi lz data buffer 0x%p length %d\n",
 		   buffer, length);
 
 	if (ar->bmi.done_sent) {
@@ -395,7 +395,7 @@ int ath10k_bmi_lz_data(struct ath10k *ar, const void *buffer, u32 length)
 	u32 txlen;
 	int ret;
 
-	ath10k_dbg(ar, ATH10K_DBG_BMI, "bmi lz data buffer 0x%pK length %d\n",
+	ath10k_dbg(ar, ATH10K_DBG_BMI, "bmi lz data buffer 0x%p length %d\n",
 		   buffer, length);
 
 	if (ar->bmi.done_sent) {
@@ -461,7 +461,7 @@ int ath10k_bmi_fast_download(struct ath10k *ar,
 	int ret;
 
 	ath10k_dbg(ar, ATH10K_DBG_BMI,
-		   "bmi fast download address 0x%x buffer 0x%pK length %d\n",
+		   "bmi fast download address 0x%x buffer 0x%p length %d\n",
 		   address, buffer, length);
 
 	ret = ath10k_bmi_lz_stream_start(ar, address);
diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c
index afae4a8027f8..a89a7491a76c 100644
--- a/drivers/net/wireless/ath/ath10k/ce.c
+++ b/drivers/net/wireless/ath/ath10k/ce.c
@@ -80,7 +80,7 @@ static inline u32 shadow_sr_wr_ind_addr(struct ath10k *ar,
 
 static inline unsigned int
 ath10k_set_ring_byte(unsigned int offset,
-		     struct ath10k_hw_ce_regs_addr_map *addr_map)
+		     const struct ath10k_hw_ce_regs_addr_map *addr_map)
 {
 	return ((offset << addr_map->lsb) & addr_map->mask);
 }
@@ -203,7 +203,7 @@ static inline void ath10k_ce_src_ring_dmax_set(struct ath10k *ar,
 					       u32 ce_ctrl_addr,
 					       unsigned int n)
 {
-	struct ath10k_hw_ce_ctrl1 *ctrl_regs = ar->hw_ce_regs->ctrl1_regs;
+	const struct ath10k_hw_ce_ctrl1 *ctrl_regs = ar->hw_ce_regs->ctrl1_regs;
 
 	u32 ctrl1_addr = ath10k_ce_read32(ar, ce_ctrl_addr +
 					  ctrl_regs->addr);
@@ -217,7 +217,7 @@ static inline void ath10k_ce_src_ring_byte_swap_set(struct ath10k *ar,
 						    u32 ce_ctrl_addr,
 						    unsigned int n)
 {
-	struct ath10k_hw_ce_ctrl1 *ctrl_regs = ar->hw_ce_regs->ctrl1_regs;
+	const struct ath10k_hw_ce_ctrl1 *ctrl_regs = ar->hw_ce_regs->ctrl1_regs;
 
 	u32 ctrl1_addr = ath10k_ce_read32(ar, ce_ctrl_addr +
 					  ctrl_regs->addr);
@@ -231,7 +231,7 @@ static inline void ath10k_ce_dest_ring_byte_swap_set(struct ath10k *ar,
 						     u32 ce_ctrl_addr,
 						     unsigned int n)
 {
-	struct ath10k_hw_ce_ctrl1 *ctrl_regs = ar->hw_ce_regs->ctrl1_regs;
+	const struct ath10k_hw_ce_ctrl1 *ctrl_regs = ar->hw_ce_regs->ctrl1_regs;
 
 	u32 ctrl1_addr = ath10k_ce_read32(ar, ce_ctrl_addr +
 					  ctrl_regs->addr);
@@ -313,7 +313,7 @@ static inline void ath10k_ce_src_ring_highmark_set(struct ath10k *ar,
 						   u32 ce_ctrl_addr,
 						   unsigned int n)
 {
-	struct ath10k_hw_ce_dst_src_wm_regs *srcr_wm = ar->hw_ce_regs->wm_srcr;
+	const struct ath10k_hw_ce_dst_src_wm_regs *srcr_wm = ar->hw_ce_regs->wm_srcr;
 	u32 addr = ath10k_ce_read32(ar, ce_ctrl_addr + srcr_wm->addr);
 
 	ath10k_ce_write32(ar, ce_ctrl_addr + srcr_wm->addr,
@@ -325,7 +325,7 @@ static inline void ath10k_ce_src_ring_lowmark_set(struct ath10k *ar,
 						  u32 ce_ctrl_addr,
 						  unsigned int n)
 {
-	struct ath10k_hw_ce_dst_src_wm_regs *srcr_wm = ar->hw_ce_regs->wm_srcr;
+	const struct ath10k_hw_ce_dst_src_wm_regs *srcr_wm = ar->hw_ce_regs->wm_srcr;
 	u32 addr = ath10k_ce_read32(ar, ce_ctrl_addr + srcr_wm->addr);
 
 	ath10k_ce_write32(ar, ce_ctrl_addr + srcr_wm->addr,
@@ -337,7 +337,7 @@ static inline void ath10k_ce_dest_ring_highmark_set(struct ath10k *ar,
 						    u32 ce_ctrl_addr,
 						    unsigned int n)
 {
-	struct ath10k_hw_ce_dst_src_wm_regs *dstr_wm = ar->hw_ce_regs->wm_dstr;
+	const struct ath10k_hw_ce_dst_src_wm_regs *dstr_wm = ar->hw_ce_regs->wm_dstr;
 	u32 addr = ath10k_ce_read32(ar, ce_ctrl_addr + dstr_wm->addr);
 
 	ath10k_ce_write32(ar, ce_ctrl_addr + dstr_wm->addr,
@@ -349,7 +349,7 @@ static inline void ath10k_ce_dest_ring_lowmark_set(struct ath10k *ar,
 						   u32 ce_ctrl_addr,
 						   unsigned int n)
 {
-	struct ath10k_hw_ce_dst_src_wm_regs *dstr_wm = ar->hw_ce_regs->wm_dstr;
+	const struct ath10k_hw_ce_dst_src_wm_regs *dstr_wm = ar->hw_ce_regs->wm_dstr;
 	u32 addr = ath10k_ce_read32(ar, ce_ctrl_addr + dstr_wm->addr);
 
 	ath10k_ce_write32(ar, ce_ctrl_addr + dstr_wm->addr,
@@ -360,7 +360,7 @@ static inline void ath10k_ce_dest_ring_lowmark_set(struct ath10k *ar,
 static inline void ath10k_ce_copy_complete_inter_enable(struct ath10k *ar,
 							u32 ce_ctrl_addr)
 {
-	struct ath10k_hw_ce_host_ie *host_ie = ar->hw_ce_regs->host_ie;
+	const struct ath10k_hw_ce_host_ie *host_ie = ar->hw_ce_regs->host_ie;
 
 	u32 host_ie_addr = ath10k_ce_read32(ar, ce_ctrl_addr +
 					    ar->hw_ce_regs->host_ie_addr);
@@ -372,7 +372,7 @@ static inline void ath10k_ce_copy_complete_inter_enable(struct ath10k *ar,
 static inline void ath10k_ce_copy_complete_intr_disable(struct ath10k *ar,
 							u32 ce_ctrl_addr)
 {
-	struct ath10k_hw_ce_host_ie *host_ie = ar->hw_ce_regs->host_ie;
+	const struct ath10k_hw_ce_host_ie *host_ie = ar->hw_ce_regs->host_ie;
 
 	u32 host_ie_addr = ath10k_ce_read32(ar, ce_ctrl_addr +
 					    ar->hw_ce_regs->host_ie_addr);
@@ -384,7 +384,7 @@ static inline void ath10k_ce_copy_complete_intr_disable(struct ath10k *ar,
 static inline void ath10k_ce_watermark_intr_disable(struct ath10k *ar,
 						    u32 ce_ctrl_addr)
 {
-	struct ath10k_hw_ce_host_wm_regs *wm_regs = ar->hw_ce_regs->wm_regs;
+	const struct ath10k_hw_ce_host_wm_regs *wm_regs = ar->hw_ce_regs->wm_regs;
 
 	u32 host_ie_addr = ath10k_ce_read32(ar, ce_ctrl_addr +
 					    ar->hw_ce_regs->host_ie_addr);
@@ -396,7 +396,7 @@ static inline void ath10k_ce_watermark_intr_disable(struct ath10k *ar,
 static inline void ath10k_ce_error_intr_disable(struct ath10k *ar,
 						u32 ce_ctrl_addr)
 {
-	struct ath10k_hw_ce_misc_regs *misc_regs = ar->hw_ce_regs->misc_regs;
+	const struct ath10k_hw_ce_misc_regs *misc_regs = ar->hw_ce_regs->misc_regs;
 
 	u32 misc_ie_addr = ath10k_ce_read32(ar,
 			ce_ctrl_addr + ar->hw_ce_regs->misc_ie_addr);
@@ -410,7 +410,7 @@ static inline void ath10k_ce_engine_int_status_clear(struct ath10k *ar,
 						     u32 ce_ctrl_addr,
 						     unsigned int mask)
 {
-	struct ath10k_hw_ce_host_wm_regs *wm_regs = ar->hw_ce_regs->wm_regs;
+	const struct ath10k_hw_ce_host_wm_regs *wm_regs = ar->hw_ce_regs->wm_regs;
 
 	ath10k_ce_write32(ar, ce_ctrl_addr + wm_regs->addr, mask);
 }
@@ -1230,7 +1230,7 @@ void ath10k_ce_per_engine_service(struct ath10k *ar, unsigned int ce_id)
 {
 	struct ath10k_ce *ce = ath10k_ce_priv(ar);
 	struct ath10k_ce_pipe *ce_state = &ce->ce_states[ce_id];
-	struct ath10k_hw_ce_host_wm_regs *wm_regs = ar->hw_ce_regs->wm_regs;
+	const struct ath10k_hw_ce_host_wm_regs *wm_regs = ar->hw_ce_regs->wm_regs;
 	u32 ctrl_addr = ce_state->ctrl_addr;
 
 	/*
@@ -1388,7 +1388,7 @@ static int ath10k_ce_init_src_ring(struct ath10k *ar,
 	ath10k_ce_src_ring_highmark_set(ar, ctrl_addr, nentries);
 
 	ath10k_dbg(ar, ATH10K_DBG_BOOT,
-		   "boot init ce src ring id %d entries %d base_addr %pK\n",
+		   "boot init ce src ring id %d entries %d base_addr %p\n",
 		   ce_id, nentries, src_ring->base_addr_owner_space);
 
 	return 0;
@@ -1426,7 +1426,7 @@ static int ath10k_ce_init_dest_ring(struct ath10k *ar,
 	ath10k_ce_dest_ring_highmark_set(ar, ctrl_addr, nentries);
 
 	ath10k_dbg(ar, ATH10K_DBG_BOOT,
-		   "boot ce dest ring id %d entries %d base_addr %pK\n",
+		   "boot ce dest ring id %d entries %d base_addr %p\n",
 		   ce_id, nentries, dest_ring->base_addr_owner_space);
 
 	return 0;
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 6d336e39d673..fe3a8f4a1cc1 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -1200,7 +1200,7 @@ static int ath10k_download_fw(struct ath10k *ar)
 	}
 
 	ath10k_dbg(ar, ATH10K_DBG_BOOT,
-		   "boot uploading firmware image %pK len %d\n",
+		   "boot uploading firmware image %p len %d\n",
 		   data, data_len);
 
 	/* Check if device supports to download firmware via
@@ -1826,7 +1826,7 @@ static int ath10k_download_and_run_otp(struct ath10k *ar)
 
 	if (!ar->running_fw->fw_file.otp_data ||
 	    !ar->running_fw->fw_file.otp_len) {
-		ath10k_warn(ar, "Not running otp, calibration will be incorrect (otp-data %pK otp_len %zd)!\n",
+		ath10k_warn(ar, "Not running otp, calibration will be incorrect (otp-data %p otp_len %zd)!\n",
 			    ar->running_fw->fw_file.otp_data,
 			    ar->running_fw->fw_file.otp_len);
 		return 0;
diff --git a/drivers/net/wireless/ath/ath10k/htc.c b/drivers/net/wireless/ath/ath10k/htc.c
index a6e21ce90bad..2da08dfebd3e 100644
--- a/drivers/net/wireless/ath/ath10k/htc.c
+++ b/drivers/net/wireless/ath/ath10k/htc.c
@@ -34,7 +34,7 @@ static struct sk_buff *ath10k_htc_build_tx_ctrl_skb(void *ar)
 	skb_cb = ATH10K_SKB_CB(skb);
 	memset(skb_cb, 0, sizeof(*skb_cb));
 
-	ath10k_dbg(ar, ATH10K_DBG_HTC, "%s: skb %pK\n", __func__, skb);
+	ath10k_dbg(ar, ATH10K_DBG_HTC, "%s: skb %p\n", __func__, skb);
 	return skb;
 }
 
@@ -54,7 +54,7 @@ void ath10k_htc_notify_tx_completion(struct ath10k_htc_ep *ep,
 	struct ath10k *ar = ep->htc->ar;
 	struct ath10k_htc_hdr *hdr;
 
-	ath10k_dbg(ar, ATH10K_DBG_HTC, "%s: ep %d skb %pK\n", __func__,
+	ath10k_dbg(ar, ATH10K_DBG_HTC, "%s: ep %d skb %p\n", __func__,
 		   ep->eid, skb);
 
 	/* A corner case where the copy completion is reaching to host but still
@@ -515,7 +515,7 @@ void ath10k_htc_rx_completion_handler(struct ath10k *ar, struct sk_buff *skb)
 		/* zero length packet with trailer data, just drop these */
 		goto out;
 
-	ath10k_dbg(ar, ATH10K_DBG_HTC, "htc rx completion ep %d skb %pK\n",
+	ath10k_dbg(ar, ATH10K_DBG_HTC, "htc rx completion ep %d skb %p\n",
 		   eid, skb);
 	ep->ep_ops.ep_rx_complete(ar, skb);
 
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index 83eab7479f06..52981052e211 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -1373,7 +1373,7 @@ static void ath10k_process_rx(struct ath10k *ar, struct sk_buff *skb)
 	}
 
 	ath10k_dbg(ar, ATH10K_DBG_DATA,
-		   "rx skb %pK len %u peer %pM %s %s sn %u %s%s%s%s%s%s %srate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %i mic-err %i amsdu-more %i\n",
+		   "rx skb %p len %u peer %pM %s %s sn %u %s%s%s%s%s%s %srate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %i mic-err %i amsdu-more %i\n",
 		   skb,
 		   skb->len,
 		   ieee80211_get_SA(hdr),
diff --git a/drivers/net/wireless/ath/ath10k/hw.c b/drivers/net/wireless/ath/ath10k/hw.c
index 8fafe096adff..84b35a22fc23 100644
--- a/drivers/net/wireless/ath/ath10k/hw.c
+++ b/drivers/net/wireless/ath/ath10k/hw.c
@@ -212,40 +212,40 @@ const struct ath10k_hw_regs wcn3990_regs = {
 	.pcie_intr_fw_mask			= 0x00100000,
 };
 
-static struct ath10k_hw_ce_regs_addr_map wcn3990_src_ring = {
+static const struct ath10k_hw_ce_regs_addr_map wcn3990_src_ring = {
 	.msb	= 0x00000010,
 	.lsb	= 0x00000010,
 	.mask	= GENMASK(17, 17),
 };
 
-static struct ath10k_hw_ce_regs_addr_map wcn3990_dst_ring = {
+static const struct ath10k_hw_ce_regs_addr_map wcn3990_dst_ring = {
 	.msb	= 0x00000012,
 	.lsb	= 0x00000012,
 	.mask	= GENMASK(18, 18),
 };
 
-static struct ath10k_hw_ce_regs_addr_map wcn3990_dmax = {
+static const struct ath10k_hw_ce_regs_addr_map wcn3990_dmax = {
 	.msb	= 0x00000000,
 	.lsb	= 0x00000000,
 	.mask	= GENMASK(15, 0),
 };
 
-static struct ath10k_hw_ce_ctrl1 wcn3990_ctrl1 = {
+static const struct ath10k_hw_ce_ctrl1 wcn3990_ctrl1 = {
 	.addr		= 0x00000018,
 	.src_ring	= &wcn3990_src_ring,
 	.dst_ring	= &wcn3990_dst_ring,
 	.dmax		= &wcn3990_dmax,
 };
 
-static struct ath10k_hw_ce_regs_addr_map wcn3990_host_ie_cc = {
+static const struct ath10k_hw_ce_regs_addr_map wcn3990_host_ie_cc = {
 	.mask	= GENMASK(0, 0),
 };
 
-static struct ath10k_hw_ce_host_ie wcn3990_host_ie = {
+static const struct ath10k_hw_ce_host_ie wcn3990_host_ie = {
 	.copy_complete	= &wcn3990_host_ie_cc,
 };
 
-static struct ath10k_hw_ce_host_wm_regs wcn3990_wm_reg = {
+static const struct ath10k_hw_ce_host_wm_regs wcn3990_wm_reg = {
 	.dstr_lmask	= 0x00000010,
 	.dstr_hmask	= 0x00000008,
 	.srcr_lmask	= 0x00000004,
@@ -255,7 +255,7 @@ static struct ath10k_hw_ce_host_wm_regs wcn3990_wm_reg = {
 	.addr		= 0x00000030,
 };
 
-static struct ath10k_hw_ce_misc_regs wcn3990_misc_reg = {
+static const struct ath10k_hw_ce_misc_regs wcn3990_misc_reg = {
 	.axi_err	= 0x00000100,
 	.dstr_add_err	= 0x00000200,
 	.srcr_len_err	= 0x00000100,
@@ -266,19 +266,19 @@ static struct ath10k_hw_ce_misc_regs wcn3990_misc_reg = {
 	.addr		= 0x00000038,
 };
 
-static struct ath10k_hw_ce_regs_addr_map wcn3990_src_wm_low = {
+static const struct ath10k_hw_ce_regs_addr_map wcn3990_src_wm_low = {
 	.msb	= 0x00000000,
 	.lsb	= 0x00000010,
 	.mask	= GENMASK(31, 16),
 };
 
-static struct ath10k_hw_ce_regs_addr_map wcn3990_src_wm_high = {
+static const struct ath10k_hw_ce_regs_addr_map wcn3990_src_wm_high = {
 	.msb	= 0x0000000f,
 	.lsb	= 0x00000000,
 	.mask	= GENMASK(15, 0),
 };
 
-static struct ath10k_hw_ce_dst_src_wm_regs wcn3990_wm_src_ring = {
+static const struct ath10k_hw_ce_dst_src_wm_regs wcn3990_wm_src_ring = {
 	.addr		= 0x0000004c,
 	.low_rst	= 0x00000000,
 	.high_rst	= 0x00000000,
@@ -286,18 +286,18 @@ static struct ath10k_hw_ce_dst_src_wm_regs wcn3990_wm_src_ring = {
 	.wm_high	= &wcn3990_src_wm_high,
 };
 
-static struct ath10k_hw_ce_regs_addr_map wcn3990_dst_wm_low = {
+static const struct ath10k_hw_ce_regs_addr_map wcn3990_dst_wm_low = {
 	.lsb	= 0x00000010,
 	.mask	= GENMASK(31, 16),
 };
 
-static struct ath10k_hw_ce_regs_addr_map wcn3990_dst_wm_high = {
+static const struct ath10k_hw_ce_regs_addr_map wcn3990_dst_wm_high = {
 	.msb	= 0x0000000f,
 	.lsb	= 0x00000000,
 	.mask	= GENMASK(15, 0),
 };
 
-static struct ath10k_hw_ce_dst_src_wm_regs wcn3990_wm_dst_ring = {
+static const struct ath10k_hw_ce_dst_src_wm_regs wcn3990_wm_dst_ring = {
 	.addr		= 0x00000050,
 	.low_rst	= 0x00000000,
 	.high_rst	= 0x00000000,
@@ -305,7 +305,7 @@ static struct ath10k_hw_ce_dst_src_wm_regs wcn3990_wm_dst_ring = {
 	.wm_high	= &wcn3990_dst_wm_high,
 };
 
-static struct ath10k_hw_ce_ctrl1_upd wcn3990_ctrl1_upd = {
+static const struct ath10k_hw_ce_ctrl1_upd wcn3990_ctrl1_upd = {
 	.shift = 19,
 	.mask = 0x00080000,
 	.enable = 0x00000000,
@@ -344,25 +344,25 @@ const struct ath10k_hw_values wcn3990_values = {
 	.ce_desc_meta_data_lsb		= 4,
 };
 
-static struct ath10k_hw_ce_regs_addr_map qcax_src_ring = {
+static const struct ath10k_hw_ce_regs_addr_map qcax_src_ring = {
 	.msb	= 0x00000010,
 	.lsb	= 0x00000010,
 	.mask	= GENMASK(16, 16),
 };
 
-static struct ath10k_hw_ce_regs_addr_map qcax_dst_ring = {
+static const struct ath10k_hw_ce_regs_addr_map qcax_dst_ring = {
 	.msb	= 0x00000011,
 	.lsb	= 0x00000011,
 	.mask	= GENMASK(17, 17),
 };
 
-static struct ath10k_hw_ce_regs_addr_map qcax_dmax = {
+static const struct ath10k_hw_ce_regs_addr_map qcax_dmax = {
 	.msb	= 0x0000000f,
 	.lsb	= 0x00000000,
 	.mask	= GENMASK(15, 0),
 };
 
-static struct ath10k_hw_ce_ctrl1 qcax_ctrl1 = {
+static const struct ath10k_hw_ce_ctrl1 qcax_ctrl1 = {
 	.addr		= 0x00000010,
 	.hw_mask	= 0x0007ffff,
 	.sw_mask	= 0x0007ffff,
@@ -375,31 +375,31 @@ static struct ath10k_hw_ce_ctrl1 qcax_ctrl1 = {
 	.dmax		= &qcax_dmax,
 };
 
-static struct ath10k_hw_ce_regs_addr_map qcax_cmd_halt_status = {
+static const struct ath10k_hw_ce_regs_addr_map qcax_cmd_halt_status = {
 	.msb	= 0x00000003,
 	.lsb	= 0x00000003,
 	.mask	= GENMASK(3, 3),
 };
 
-static struct ath10k_hw_ce_cmd_halt qcax_cmd_halt = {
+static const struct ath10k_hw_ce_cmd_halt qcax_cmd_halt = {
 	.msb		= 0x00000000,
 	.mask		= GENMASK(0, 0),
 	.status_reset	= 0x00000000,
 	.status		= &qcax_cmd_halt_status,
 };
 
-static struct ath10k_hw_ce_regs_addr_map qcax_host_ie_cc = {
+static const struct ath10k_hw_ce_regs_addr_map qcax_host_ie_cc = {
 	.msb	= 0x00000000,
 	.lsb	= 0x00000000,
 	.mask	= GENMASK(0, 0),
 };
 
-static struct ath10k_hw_ce_host_ie qcax_host_ie = {
+static const struct ath10k_hw_ce_host_ie qcax_host_ie = {
 	.copy_complete_reset	= 0x00000000,
 	.copy_complete		= &qcax_host_ie_cc,
 };
 
-static struct ath10k_hw_ce_host_wm_regs qcax_wm_reg = {
+static const struct ath10k_hw_ce_host_wm_regs qcax_wm_reg = {
 	.dstr_lmask	= 0x00000010,
 	.dstr_hmask	= 0x00000008,
 	.srcr_lmask	= 0x00000004,
@@ -409,7 +409,7 @@ static struct ath10k_hw_ce_host_wm_regs qcax_wm_reg = {
 	.addr		= 0x00000030,
 };
 
-static struct ath10k_hw_ce_misc_regs qcax_misc_reg = {
+static const struct ath10k_hw_ce_misc_regs qcax_misc_reg = {
 	.axi_err	= 0x00000400,
 	.dstr_add_err	= 0x00000200,
 	.srcr_len_err	= 0x00000100,
@@ -420,19 +420,19 @@ static struct ath10k_hw_ce_misc_regs qcax_misc_reg = {
 	.addr		= 0x00000038,
 };
 
-static struct ath10k_hw_ce_regs_addr_map qcax_src_wm_low = {
+static const struct ath10k_hw_ce_regs_addr_map qcax_src_wm_low = {
 	.msb    = 0x0000001f,
 	.lsb	= 0x00000010,
 	.mask	= GENMASK(31, 16),
 };
 
-static struct ath10k_hw_ce_regs_addr_map qcax_src_wm_high = {
+static const struct ath10k_hw_ce_regs_addr_map qcax_src_wm_high = {
 	.msb	= 0x0000000f,
 	.lsb	= 0x00000000,
 	.mask	= GENMASK(15, 0),
 };
 
-static struct ath10k_hw_ce_dst_src_wm_regs qcax_wm_src_ring = {
+static const struct ath10k_hw_ce_dst_src_wm_regs qcax_wm_src_ring = {
 	.addr		= 0x0000004c,
 	.low_rst	= 0x00000000,
 	.high_rst	= 0x00000000,
@@ -440,18 +440,18 @@ static struct ath10k_hw_ce_dst_src_wm_regs qcax_wm_src_ring = {
 	.wm_high        = &qcax_src_wm_high,
 };
 
-static struct ath10k_hw_ce_regs_addr_map qcax_dst_wm_low = {
+static const struct ath10k_hw_ce_regs_addr_map qcax_dst_wm_low = {
 	.lsb	= 0x00000010,
 	.mask	= GENMASK(31, 16),
 };
 
-static struct ath10k_hw_ce_regs_addr_map qcax_dst_wm_high = {
+static const struct ath10k_hw_ce_regs_addr_map qcax_dst_wm_high = {
 	.msb	= 0x0000000f,
 	.lsb	= 0x00000000,
 	.mask	= GENMASK(15, 0),
 };
 
-static struct ath10k_hw_ce_dst_src_wm_regs qcax_wm_dst_ring = {
+static const struct ath10k_hw_ce_dst_src_wm_regs qcax_wm_dst_ring = {
 	.addr		= 0x00000050,
 	.low_rst	= 0x00000000,
 	.high_rst	= 0x00000000,
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index 442091c6dfd2..7ffa1fbe2874 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -289,19 +289,22 @@ struct ath10k_hw_ce_ctrl1 {
 	u32 sw_wr_mask;
 	u32 reset_mask;
 	u32 reset;
-	struct ath10k_hw_ce_regs_addr_map *src_ring;
-	struct ath10k_hw_ce_regs_addr_map *dst_ring;
-	struct ath10k_hw_ce_regs_addr_map *dmax; };
+	const struct ath10k_hw_ce_regs_addr_map *src_ring;
+	const struct ath10k_hw_ce_regs_addr_map *dst_ring;
+	const struct ath10k_hw_ce_regs_addr_map *dmax;
+};
 
 struct ath10k_hw_ce_cmd_halt {
 	u32 status_reset;
 	u32 msb;
 	u32 mask;
-	struct ath10k_hw_ce_regs_addr_map *status; };
+	const struct ath10k_hw_ce_regs_addr_map *status;
+};
 
 struct ath10k_hw_ce_host_ie {
 	u32 copy_complete_reset;
-	struct ath10k_hw_ce_regs_addr_map *copy_complete; };
+	const struct ath10k_hw_ce_regs_addr_map *copy_complete;
+};
 
 struct ath10k_hw_ce_host_wm_regs {
 	u32 dstr_lmask;
@@ -328,8 +331,9 @@ struct ath10k_hw_ce_dst_src_wm_regs {
 	u32 addr;
 	u32 low_rst;
 	u32 high_rst;
-	struct ath10k_hw_ce_regs_addr_map *wm_low;
-	struct ath10k_hw_ce_regs_addr_map *wm_high; };
+	const struct ath10k_hw_ce_regs_addr_map *wm_low;
+	const struct ath10k_hw_ce_regs_addr_map *wm_high;
+};
 
 struct ath10k_hw_ce_ctrl1_upd {
 	u32 shift;
@@ -355,14 +359,14 @@ struct ath10k_hw_ce_regs {
 	u32 ce_rri_low;
 	u32 ce_rri_high;
 	u32 host_ie_addr;
-	struct ath10k_hw_ce_host_wm_regs *wm_regs;
-	struct ath10k_hw_ce_misc_regs *misc_regs;
-	struct ath10k_hw_ce_ctrl1 *ctrl1_regs;
-	struct ath10k_hw_ce_cmd_halt *cmd_halt;
-	struct ath10k_hw_ce_host_ie *host_ie;
-	struct ath10k_hw_ce_dst_src_wm_regs *wm_srcr;
-	struct ath10k_hw_ce_dst_src_wm_regs *wm_dstr;
-	struct ath10k_hw_ce_ctrl1_upd *upd;
+	const struct ath10k_hw_ce_host_wm_regs *wm_regs;
+	const struct ath10k_hw_ce_misc_regs *misc_regs;
+	const struct ath10k_hw_ce_ctrl1 *ctrl1_regs;
+	const struct ath10k_hw_ce_cmd_halt *cmd_halt;
+	const struct ath10k_hw_ce_host_ie *host_ie;
+	const struct ath10k_hw_ce_dst_src_wm_regs *wm_srcr;
+	const struct ath10k_hw_ce_dst_src_wm_regs *wm_dstr;
+	const struct ath10k_hw_ce_ctrl1_upd *upd;
 };
 
 struct ath10k_hw_values {
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index c61b95a928da..8c7ffea0fa44 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -875,7 +875,7 @@ static void ath10k_peer_map_cleanup(struct ath10k *ar, struct ath10k_peer *peer)
 	 */
 	for (i = 0; i < ARRAY_SIZE(ar->peer_map); i++) {
 		if (ar->peer_map[i] == peer) {
-			ath10k_warn(ar, "removing stale peer_map entry for %pM (ptr %pK idx %d)\n",
+			ath10k_warn(ar, "removing stale peer_map entry for %pM (ptr %p idx %d)\n",
 				    peer->addr, peer, i);
 			ar->peer_map[i] = NULL;
 		}
@@ -4063,7 +4063,7 @@ static int ath10k_mac_tx(struct ath10k *ar,
 
 	if (!noque_offchan && info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) {
 		if (!ath10k_mac_tx_frm_has_freq(ar)) {
-			ath10k_dbg(ar, ATH10K_DBG_MAC, "mac queued offchannel skb %pK len %d\n",
+			ath10k_dbg(ar, ATH10K_DBG_MAC, "mac queued offchannel skb %p len %d\n",
 				   skb, skb->len);
 
 			skb_queue_tail(&ar->offchan_tx_queue, skb);
@@ -4126,7 +4126,7 @@ void ath10k_offchan_tx_work(struct work_struct *work)
 
 		mutex_lock(&ar->conf_mutex);
 
-		ath10k_dbg(ar, ATH10K_DBG_MAC, "mac offchannel skb %pK len %d\n",
+		ath10k_dbg(ar, ATH10K_DBG_MAC, "mac offchannel skb %p len %d\n",
 			   skb, skb->len);
 
 		hdr = (struct ieee80211_hdr *)skb->data;
@@ -4181,7 +4181,7 @@ void ath10k_offchan_tx_work(struct work_struct *work)
 		time_left =
 		wait_for_completion_timeout(&ar->offchan_tx_completed, 3 * HZ);
 		if (time_left == 0)
-			ath10k_warn(ar, "timed out waiting for offchannel skb %pK, len: %d\n",
+			ath10k_warn(ar, "timed out waiting for offchannel skb %p, len: %d\n",
 				    skb, skb->len);
 
 		if (!peer && tmp_peer_created) {
@@ -7604,7 +7604,7 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 		 * Existing station deletion.
 		 */
 		ath10k_dbg(ar, ATH10K_DBG_STA,
-			   "mac vdev %d peer delete %pM sta %pK (sta gone)\n",
+			   "mac vdev %d peer delete %pM sta %p (sta gone)\n",
 			   arvif->vdev_id, sta->addr, sta);
 
 		if (sta->tdls) {
@@ -7631,7 +7631,7 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 				continue;
 
 			if (peer->sta == sta) {
-				ath10k_warn(ar, "found sta peer %pM (ptr %pK id %d) entry on vdev %i after it was supposedly removed\n",
+				ath10k_warn(ar, "found sta peer %pM (ptr %p id %d) entry on vdev %i after it was supposedly removed\n",
 					    sta->addr, peer, i, arvif->vdev_id);
 				peer->sta = NULL;
 
@@ -8811,7 +8811,7 @@ ath10k_mac_op_add_chanctx(struct ieee80211_hw *hw,
 	struct ath10k *ar = hw->priv;
 
 	ath10k_dbg(ar, ATH10K_DBG_MAC,
-		   "mac chanctx add freq %u width %d ptr %pK\n",
+		   "mac chanctx add freq %u width %d ptr %p\n",
 		   ctx->def.chan->center_freq, ctx->def.width, ctx);
 
 	mutex_lock(&ar->conf_mutex);
@@ -8835,7 +8835,7 @@ ath10k_mac_op_remove_chanctx(struct ieee80211_hw *hw,
 	struct ath10k *ar = hw->priv;
 
 	ath10k_dbg(ar, ATH10K_DBG_MAC,
-		   "mac chanctx remove freq %u width %d ptr %pK\n",
+		   "mac chanctx remove freq %u width %d ptr %p\n",
 		   ctx->def.chan->center_freq, ctx->def.width, ctx);
 
 	mutex_lock(&ar->conf_mutex);
@@ -8900,7 +8900,7 @@ ath10k_mac_op_change_chanctx(struct ieee80211_hw *hw,
 	mutex_lock(&ar->conf_mutex);
 
 	ath10k_dbg(ar, ATH10K_DBG_MAC,
-		   "mac chanctx change freq %u width %d ptr %pK changed %x\n",
+		   "mac chanctx change freq %u width %d ptr %p changed %x\n",
 		   ctx->def.chan->center_freq, ctx->def.width, ctx, changed);
 
 	/* This shouldn't really happen because channel switching should use
@@ -8959,7 +8959,7 @@ ath10k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 	mutex_lock(&ar->conf_mutex);
 
 	ath10k_dbg(ar, ATH10K_DBG_MAC,
-		   "mac chanctx assign ptr %pK vdev_id %i\n",
+		   "mac chanctx assign ptr %p vdev_id %i\n",
 		   ctx, arvif->vdev_id);
 
 	if (WARN_ON(arvif->is_started)) {
@@ -9039,7 +9039,7 @@ ath10k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 	mutex_lock(&ar->conf_mutex);
 
 	ath10k_dbg(ar, ATH10K_DBG_MAC,
-		   "mac chanctx unassign ptr %pK vdev_id %i\n",
+		   "mac chanctx unassign ptr %p vdev_id %i\n",
 		   ctx, arvif->vdev_id);
 
 	WARN_ON(!arvif->is_started);
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index fb2c60ee433c..20ec0a6d0f71 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -3411,7 +3411,7 @@ static int ath10k_pci_claim(struct ath10k *ar)
 		goto err_region;
 	}
 
-	ath10k_dbg(ar, ATH10K_DBG_BOOT, "boot pci_mem 0x%pK\n", ar_pci->mem);
+	ath10k_dbg(ar, ATH10K_DBG_BOOT, "boot pci_mem 0x%p\n", ar_pci->mem);
 	return 0;
 
 err_region:
diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index 7ce74b4ef201..f3212eab56a1 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -1844,7 +1844,7 @@ static int ath10k_sdio_get_htt_tx_complete(struct ath10k *ar)
 	ret = ath10k_sdio_diag_read32(ar, addr, &val);
 	if (ret) {
 		ath10k_warn(ar,
-			    "unable to read hi_acs_flags for htt tx comple : %d\n", ret);
+			    "unable to read hi_acs_flags for htt tx complete: %d\n", ret);
 		return ret;
 	}
 
diff --git a/drivers/net/wireless/ath/ath10k/testmode.c b/drivers/net/wireless/ath/ath10k/testmode.c
index 7a9b9bbcdbfc..3fcefc55b74f 100644
--- a/drivers/net/wireless/ath/ath10k/testmode.c
+++ b/drivers/net/wireless/ath/ath10k/testmode.c
@@ -35,7 +35,7 @@ bool ath10k_tm_event_wmi(struct ath10k *ar, u32 cmd_id, struct sk_buff *skb)
 	int ret;
 
 	ath10k_dbg(ar, ATH10K_DBG_TESTMODE,
-		   "testmode event wmi cmd_id %d skb %pK skb->len %d\n",
+		   "testmode event wmi cmd_id %d skb %p skb->len %d\n",
 		   cmd_id, skb, skb->len);
 
 	ath10k_dbg_dump(ar, ATH10K_DBG_TESTMODE, NULL, "", skb->data, skb->len);
@@ -397,7 +397,7 @@ static int ath10k_tm_cmd_wmi(struct ath10k *ar, struct nlattr *tb[])
 	cmd_id = nla_get_u32(tb[ATH10K_TM_ATTR_WMI_CMDID]);
 
 	ath10k_dbg(ar, ATH10K_DBG_TESTMODE,
-		   "testmode cmd wmi cmd_id %d buf %pK buf_len %d\n",
+		   "testmode cmd wmi cmd_id %d buf %p buf_len %d\n",
 		   cmd_id, buf, buf_len);
 
 	ath10k_dbg_dump(ar, ATH10K_DBG_TESTMODE, NULL, "", buf, buf_len);
diff --git a/drivers/net/wireless/ath/ath10k/txrx.c b/drivers/net/wireless/ath/ath10k/txrx.c
index da3bc35e41aa..493bfb410aff 100644
--- a/drivers/net/wireless/ath/ath10k/txrx.c
+++ b/drivers/net/wireless/ath/ath10k/txrx.c
@@ -35,7 +35,7 @@ static void ath10k_report_offchan_tx(struct ath10k *ar, struct sk_buff *skb)
 	complete(&ar->offchan_tx_completed);
 	ar->offchan_tx_skb = NULL; /* just for sanity */
 
-	ath10k_dbg(ar, ATH10K_DBG_HTT, "completed offchannel skb %pK\n", skb);
+	ath10k_dbg(ar, ATH10K_DBG_HTT, "completed offchannel skb %p\n", skb);
 out:
 	spin_unlock_bh(&ar->data_lock);
 }
diff --git a/drivers/net/wireless/ath/ath10k/usb.c b/drivers/net/wireless/ath/ath10k/usb.c
index 3b51b7f52130..1732a4f98418 100644
--- a/drivers/net/wireless/ath/ath10k/usb.c
+++ b/drivers/net/wireless/ath/ath10k/usb.c
@@ -131,7 +131,7 @@ static void ath10k_usb_recv_complete(struct urb *urb)
 	int status = 0;
 
 	ath10k_dbg(ar, ATH10K_DBG_USB_BULK,
-		   "usb recv pipe %d stat %d len %d urb 0x%pK\n",
+		   "usb recv pipe %d stat %d len %d urb 0x%p\n",
 		   pipe->logical_pipe_num, urb->status, urb->actual_length,
 		   urb);
 
@@ -230,7 +230,7 @@ static void ath10k_usb_post_recv_transfers(struct ath10k *ar,
 				  ath10k_usb_recv_complete, urb_context);
 
 		ath10k_dbg(ar, ATH10K_DBG_USB_BULK,
-			   "usb bulk recv submit %d 0x%x ep 0x%2.2x len %d buf 0x%pK\n",
+			   "usb bulk recv submit %d 0x%x ep 0x%2.2x len %d buf 0x%p\n",
 			   recv_pipe->logical_pipe_num,
 			   recv_pipe->usb_pipe_handle, recv_pipe->ep_address,
 			   ATH10K_USB_RX_BUFFER_SIZE, urb_context->skb);
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 5e061f7525a6..df6a24f8f8d5 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -2029,7 +2029,7 @@ ath10k_wmi_op_gen_mgmt_tx(struct ath10k *ar, struct sk_buff *msdu)
 	ether_addr_copy(cmd->hdr.peer_macaddr.addr, ieee80211_get_DA(hdr));
 	memcpy(cmd->buf, msdu->data, msdu->len);
 
-	ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi mgmt tx skb %pK len %d ftype %02x stype %02x\n",
+	ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi mgmt tx skb %p len %d ftype %02x stype %02x\n",
 		   msdu, skb->len, fc & IEEE80211_FCTL_FTYPE,
 		   fc & IEEE80211_FCTL_STYPE);
 	trace_ath10k_tx_hdr(ar, skb->data, skb->len);
@@ -2637,7 +2637,7 @@ int ath10k_wmi_event_mgmt_rx(struct ath10k *ar, struct sk_buff *skb)
 		status->boottime_ns = ktime_get_boottime_ns();
 
 	ath10k_dbg(ar, ATH10K_DBG_MGMT,
-		   "event mgmt rx skb %pK len %d ftype %02x stype %02x\n",
+		   "event mgmt rx skb %p len %d ftype %02x stype %02x\n",
 		   skb, skb->len,
 		   fc & IEEE80211_FCTL_FTYPE, fc & IEEE80211_FCTL_STYPE);
 
diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index 2f862f8f10ca..fde1ce43c499 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -413,7 +413,7 @@ static int ath11k_ahb_power_up(struct ath11k_base *ab)
 	return ret;
 }
 
-static void ath11k_ahb_power_down(struct ath11k_base *ab)
+static void ath11k_ahb_power_down(struct ath11k_base *ab, bool is_suspend)
 {
 	struct ath11k_ahb *ab_ahb = ath11k_ahb_priv(ab);
 
@@ -1280,7 +1280,7 @@ static void ath11k_ahb_remove(struct platform_device *pdev)
 	struct ath11k_base *ab = platform_get_drvdata(pdev);
 
 	if (test_bit(ATH11K_FLAG_QMI_FAIL, &ab->dev_flags)) {
-		ath11k_ahb_power_down(ab);
+		ath11k_ahb_power_down(ab, false);
 		ath11k_debugfs_soc_destroy(ab);
 		ath11k_qmi_deinit_service(ab);
 		goto qmi_fail;
diff --git a/drivers/net/wireless/ath/ath11k/ce.c b/drivers/net/wireless/ath/ath11k/ce.c
index e66e86bdec20..9d8efec46508 100644
--- a/drivers/net/wireless/ath/ath11k/ce.c
+++ b/drivers/net/wireless/ath/ath11k/ce.c
@@ -393,11 +393,10 @@ static int ath11k_ce_completed_recv_next(struct ath11k_ce_pipe *pipe,
 		goto err;
 	}
 
+	/* Make sure descriptor is read after the head pointer. */
+	dma_rmb();
+
 	*nbytes = ath11k_hal_ce_dst_status_get_length(desc);
-	if (*nbytes == 0) {
-		ret = -EIO;
-		goto err;
-	}
 
 	*skb = pipe->dest_ring->skb[sw_index];
 	pipe->dest_ring->skb[sw_index] = NULL;
@@ -430,8 +429,8 @@ static void ath11k_ce_recv_process_cb(struct ath11k_ce_pipe *pipe)
 		dma_unmap_single(ab->dev, ATH11K_SKB_RXCB(skb)->paddr,
 				 max_nbytes, DMA_FROM_DEVICE);
 
-		if (unlikely(max_nbytes < nbytes)) {
-			ath11k_warn(ab, "rxed more than expected (nbytes %d, max %d)",
+		if (unlikely(max_nbytes < nbytes || nbytes == 0)) {
+			ath11k_warn(ab, "unexpected rx length (nbytes %d, max %d)",
 				    nbytes, max_nbytes);
 			dev_kfree_skb_any(skb);
 			continue;
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 3d39ff85ba94..2e9f8a5e61e4 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -907,12 +907,51 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 	},
 };
 
-static inline struct ath11k_pdev *ath11k_core_get_single_pdev(struct ath11k_base *ab)
-{
-	WARN_ON(!ab->hw_params.single_pdev_only);
-
-	return &ab->pdevs[0];
-}
+static const struct dmi_system_id ath11k_pm_quirk_table[] = {
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21J4"),
+		},
+	},
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21K4"),
+		},
+	},
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21K6"),
+		},
+	},
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21K8"),
+		},
+	},
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21KA"),
+		},
+	},
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21F9"),
+		},
+	},
+	{}
+};
 
 void ath11k_fw_stats_pdevs_free(struct list_head *head)
 {
@@ -972,23 +1011,33 @@ bool ath11k_core_coldboot_cal_support(struct ath11k_base *ab)
 		return ab->hw_params.coldboot_cal_mm;
 }
 
-int ath11k_core_suspend(struct ath11k_base *ab)
+/* Check if we need to continue with suspend/resume operation.
+ * Return:
+ *	a negative value: error happens and don't continue.
+ *	0:  no error but don't continue.
+ *	positive value: no error and do continue.
+ */
+static int ath11k_core_continue_suspend_resume(struct ath11k_base *ab)
 {
-	int ret;
-	struct ath11k_pdev *pdev;
 	struct ath11k *ar;
 
 	if (!ab->hw_params.supports_suspend)
 		return -EOPNOTSUPP;
 
 	/* so far single_pdev_only chips have supports_suspend as true
-	 * and only the first pdev is valid.
+	 * so pass 0 as a dummy pdev_id here.
 	 */
-	pdev = ath11k_core_get_single_pdev(ab);
-	ar = pdev->ar;
+	ar = ab->pdevs[0].ar;
 	if (!ar || ar->state != ATH11K_STATE_OFF)
 		return 0;
 
+	return 1;
+}
+
+static int ath11k_core_suspend_wow(struct ath11k_base *ab)
+{
+	int ret;
+
 	ret = ath11k_dp_rx_pktlog_stop(ab, true);
 	if (ret) {
 		ath11k_warn(ab, "failed to stop dp rx (and timer) pktlog during suspend: %d\n",
@@ -996,7 +1045,10 @@ int ath11k_core_suspend(struct ath11k_base *ab)
 		return ret;
 	}
 
-	ret = ath11k_mac_wait_tx_complete(ar);
+	/* So far only single_pdev_only devices can reach here,
+	 * so it is valid to handle the first, and the only, pdev.
+	 */
+	ret = ath11k_mac_wait_tx_complete(ab->pdevs[0].ar);
 	if (ret) {
 		ath11k_warn(ab, "failed to wait tx complete: %d\n", ret);
 		return ret;
@@ -1029,24 +1081,146 @@ int ath11k_core_suspend(struct ath11k_base *ab)
 
 	return 0;
 }
+
+static int ath11k_core_suspend_default(struct ath11k_base *ab)
+{
+	int ret;
+
+	ret = ath11k_dp_rx_pktlog_stop(ab, true);
+	if (ret) {
+		ath11k_warn(ab, "failed to stop dp rx (and timer) pktlog during suspend: %d\n",
+			    ret);
+		return ret;
+	}
+
+	/* So far only single_pdev_only devices can reach here,
+	 * so it is valid to handle the first, and the only, pdev.
+	 */
+	ret = ath11k_mac_wait_tx_complete(ab->pdevs[0].ar);
+	if (ret) {
+		ath11k_warn(ab, "failed to wait tx complete: %d\n", ret);
+		return ret;
+	}
+
+	ret = ath11k_dp_rx_pktlog_stop(ab, false);
+	if (ret) {
+		ath11k_warn(ab, "failed to stop dp rx pktlog during suspend: %d\n",
+			    ret);
+		return ret;
+	}
+
+	ath11k_ce_stop_shadow_timers(ab);
+	ath11k_dp_stop_shadow_timers(ab);
+
+	/* PM framework skips suspend_late/resume_early callbacks
+	 * if other devices report errors in their suspend callbacks.
+	 * However ath11k_core_resume() would still be called because
+	 * here we return success thus kernel put us on dpm_suspended_list.
+	 * Since we won't go through a power down/up cycle, there is
+	 * no chance to call complete(&ab->restart_completed) in
+	 * ath11k_core_restart(), making ath11k_core_resume() timeout.
+	 * So call it here to avoid this issue. This also works in case
+	 * no error happens thus suspend_late/resume_early get called,
+	 * because it will be reinitialized in ath11k_core_resume_early().
+	 */
+	complete(&ab->restart_completed);
+
+	return 0;
+}
+
+int ath11k_core_suspend(struct ath11k_base *ab)
+{
+	int ret;
+
+	ret = ath11k_core_continue_suspend_resume(ab);
+	if (ret <= 0)
+		return ret;
+
+	if (ab->actual_pm_policy == ATH11K_PM_WOW)
+		return ath11k_core_suspend_wow(ab);
+
+	return ath11k_core_suspend_default(ab);
+}
 EXPORT_SYMBOL(ath11k_core_suspend);
 
-int ath11k_core_resume(struct ath11k_base *ab)
+int ath11k_core_suspend_late(struct ath11k_base *ab)
 {
 	int ret;
-	struct ath11k_pdev *pdev;
+
+	ret = ath11k_core_continue_suspend_resume(ab);
+	if (ret <= 0)
+		return ret;
+
+	if (ab->actual_pm_policy == ATH11K_PM_WOW)
+		return 0;
+
+	ath11k_hif_irq_disable(ab);
+	ath11k_hif_ce_irq_disable(ab);
+
+	ath11k_hif_power_down(ab, true);
+
+	return 0;
+}
+EXPORT_SYMBOL(ath11k_core_suspend_late);
+
+int ath11k_core_resume_early(struct ath11k_base *ab)
+{
+	int ret;
+
+	ret = ath11k_core_continue_suspend_resume(ab);
+	if (ret <= 0)
+		return ret;
+
+	if (ab->actual_pm_policy == ATH11K_PM_WOW)
+		return 0;
+
+	reinit_completion(&ab->restart_completed);
+	ret = ath11k_hif_power_up(ab);
+	if (ret)
+		ath11k_warn(ab, "failed to power up hif during resume: %d\n", ret);
+
+	return ret;
+}
+EXPORT_SYMBOL(ath11k_core_resume_early);
+
+static int ath11k_core_resume_default(struct ath11k_base *ab)
+{
 	struct ath11k *ar;
+	long time_left;
+	int ret;
 
-	if (!ab->hw_params.supports_suspend)
-		return -EOPNOTSUPP;
+	time_left = wait_for_completion_timeout(&ab->restart_completed,
+						ATH11K_RESET_TIMEOUT_HZ);
+	if (time_left == 0) {
+		ath11k_warn(ab, "timeout while waiting for restart complete");
+		return -ETIMEDOUT;
+	}
 
-	/* so far signle_pdev_only chips have supports_suspend as true
-	 * and only the first pdev is valid.
+	/* So far only single_pdev_only devices can reach here,
+	 * so it is valid to handle the first, and the only, pdev.
 	 */
-	pdev = ath11k_core_get_single_pdev(ab);
-	ar = pdev->ar;
-	if (!ar || ar->state != ATH11K_STATE_OFF)
-		return 0;
+	ar = ab->pdevs[0].ar;
+	if (ab->hw_params.current_cc_support &&
+	    ar->alpha2[0] != 0 && ar->alpha2[1] != 0) {
+		ret = ath11k_reg_set_cc(ar);
+		if (ret) {
+			ath11k_warn(ab, "failed to set country code during resume: %d\n",
+				    ret);
+			return ret;
+		}
+	}
+
+	ret = ath11k_dp_rx_pktlog_start(ab);
+	if (ret)
+		ath11k_warn(ab, "failed to start rx pktlog during resume: %d\n",
+			    ret);
+
+	return ret;
+}
+
+static int ath11k_core_resume_wow(struct ath11k_base *ab)
+{
+	int ret;
 
 	ret = ath11k_hif_resume(ab);
 	if (ret) {
@@ -1072,6 +1246,20 @@ int ath11k_core_resume(struct ath11k_base *ab)
 
 	return 0;
 }
+
+int ath11k_core_resume(struct ath11k_base *ab)
+{
+	int ret;
+
+	ret = ath11k_core_continue_suspend_resume(ab);
+	if (ret <= 0)
+		return ret;
+
+	if (ab->actual_pm_policy == ATH11K_PM_WOW)
+		return ath11k_core_resume_wow(ab);
+
+	return ath11k_core_resume_default(ab);
+}
 EXPORT_SYMBOL(ath11k_core_resume);
 
 static void ath11k_core_check_cc_code_bdfext(const struct dmi_header *hdr, void *data)
@@ -2050,6 +2238,7 @@ err_hal_srng_deinit:
 void ath11k_core_halt(struct ath11k *ar)
 {
 	struct ath11k_base *ab = ar->ab;
+	struct list_head *pos, *n;
 
 	lockdep_assert_held(&ar->conf_mutex);
 
@@ -2065,7 +2254,12 @@ void ath11k_core_halt(struct ath11k *ar)
 
 	rcu_assign_pointer(ab->pdevs_active[ar->pdev_idx], NULL);
 	synchronize_rcu();
-	INIT_LIST_HEAD(&ar->arvifs);
+
+	spin_lock_bh(&ar->data_lock);
+	list_for_each_safe(pos, n, &ar->arvifs)
+		list_del_init(pos);
+	spin_unlock_bh(&ar->data_lock);
+
 	idr_init(&ar->txmgmt_idr);
 }
 
@@ -2205,6 +2399,8 @@ static void ath11k_core_restart(struct work_struct *work)
 
 	if (!ab->is_reset)
 		ath11k_core_post_reconfigure_recovery(ab);
+
+	complete(&ab->restart_completed);
 }
 
 static void ath11k_core_reset(struct work_struct *work)
@@ -2275,7 +2471,7 @@ static void ath11k_core_reset(struct work_struct *work)
 	ath11k_hif_irq_disable(ab);
 	ath11k_hif_ce_irq_disable(ab);
 
-	ath11k_hif_power_down(ab);
+	ath11k_hif_power_down(ab, false);
 	ath11k_hif_power_up(ab);
 
 	ath11k_dbg(ab, ATH11K_DBG_BOOT, "reset started\n");
@@ -2325,10 +2521,62 @@ int ath11k_core_pre_init(struct ath11k_base *ab)
 }
 EXPORT_SYMBOL(ath11k_core_pre_init);
 
+static int ath11k_core_pm_notify(struct notifier_block *nb,
+				 unsigned long action, void *nouse)
+{
+	struct ath11k_base *ab = container_of(nb, struct ath11k_base,
+					      pm_nb);
+
+	switch (action) {
+	case PM_SUSPEND_PREPARE:
+		ab->actual_pm_policy = ab->pm_policy;
+		break;
+	case PM_HIBERNATION_PREPARE:
+		ab->actual_pm_policy = ATH11K_PM_DEFAULT;
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static int ath11k_core_pm_notifier_register(struct ath11k_base *ab)
+{
+	ab->pm_nb.notifier_call = ath11k_core_pm_notify;
+	return register_pm_notifier(&ab->pm_nb);
+}
+
+void ath11k_core_pm_notifier_unregister(struct ath11k_base *ab)
+{
+	int ret;
+
+	ret = unregister_pm_notifier(&ab->pm_nb);
+	if (ret)
+		/* just warn here, there is nothing can be done in fail case */
+		ath11k_warn(ab, "failed to unregister PM notifier %d\n", ret);
+}
+EXPORT_SYMBOL(ath11k_core_pm_notifier_unregister);
+
 int ath11k_core_init(struct ath11k_base *ab)
 {
+	const struct dmi_system_id *dmi_id;
 	int ret;
 
+	dmi_id = dmi_first_match(ath11k_pm_quirk_table);
+	if (dmi_id)
+		ab->pm_policy = (kernel_ulong_t)dmi_id->driver_data;
+	else
+		ab->pm_policy = ATH11K_PM_DEFAULT;
+
+	ath11k_dbg(ab, ATH11K_DBG_BOOT, "pm policy %u\n", ab->pm_policy);
+
+	ret = ath11k_core_pm_notifier_register(ab);
+	if (ret) {
+		ath11k_err(ab, "failed to register PM notifier: %d\n", ret);
+		return ret;
+	}
+
 	ret = ath11k_core_soc_create(ab);
 	if (ret) {
 		ath11k_err(ab, "failed to create soc core: %d\n", ret);
@@ -2348,9 +2596,10 @@ void ath11k_core_deinit(struct ath11k_base *ab)
 
 	mutex_unlock(&ab->core_lock);
 
-	ath11k_hif_power_down(ab);
+	ath11k_hif_power_down(ab, false);
 	ath11k_mac_destroy(ab);
 	ath11k_core_soc_destroy(ab);
+	ath11k_core_pm_notifier_unregister(ab);
 }
 EXPORT_SYMBOL(ath11k_core_deinit);
 
@@ -2401,6 +2650,7 @@ struct ath11k_base *ath11k_core_alloc(struct device *dev, size_t priv_size,
 	timer_setup(&ab->rx_replenish_retry, ath11k_ce_rx_replenish_retry, 0);
 	init_completion(&ab->htc_suspend);
 	init_completion(&ab->wow.wakeup_completed);
+	init_completion(&ab->restart_completed);
 
 	ab->dev = dev;
 	ab->hif.bus = bus;
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 1a3d0de4afde..339d4fca1ed5 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -16,6 +16,7 @@
 #include <linux/rhashtable.h>
 #include <linux/average.h>
 #include <linux/firmware.h>
+#include <linux/suspend.h>
 
 #include "qmi.h"
 #include "htc.h"
@@ -892,6 +893,11 @@ struct ath11k_msi_config {
 	u16 hw_rev;
 };
 
+enum ath11k_pm_policy {
+	ATH11K_PM_DEFAULT,
+	ATH11K_PM_WOW,
+};
+
 /* Master structure to hold the hw data which may be used in core module */
 struct ath11k_base {
 	enum ath11k_hw_rev hw_rev;
@@ -1050,6 +1056,8 @@ struct ath11k_base {
 		DECLARE_BITMAP(fw_features, ATH11K_FW_FEATURE_COUNT);
 	} fw;
 
+	struct completion restart_completed;
+
 #ifdef CONFIG_NL80211_TESTMODE
 	struct {
 		u32 data_pos;
@@ -1058,6 +1066,10 @@ struct ath11k_base {
 	} testmode;
 #endif
 
+	enum ath11k_pm_policy pm_policy;
+	enum ath11k_pm_policy actual_pm_policy;
+	struct notifier_block pm_nb;
+
 	/* must be last */
 	u8 drv_priv[] __aligned(sizeof(void *));
 };
@@ -1249,8 +1261,10 @@ void ath11k_core_free_bdf(struct ath11k_base *ab, struct ath11k_board_data *bd);
 int ath11k_core_check_dt(struct ath11k_base *ath11k);
 int ath11k_core_check_smbios(struct ath11k_base *ab);
 void ath11k_core_halt(struct ath11k *ar);
+int ath11k_core_resume_early(struct ath11k_base *ab);
 int ath11k_core_resume(struct ath11k_base *ab);
 int ath11k_core_suspend(struct ath11k_base *ab);
+int ath11k_core_suspend_late(struct ath11k_base *ab);
 void ath11k_core_pre_reconfigure_recovery(struct ath11k_base *ab);
 bool ath11k_core_coldboot_cal_support(struct ath11k_base *ab);
 
@@ -1322,4 +1336,6 @@ static inline const char *ath11k_bus_str(enum ath11k_bus bus)
 	return "unknown";
 }
 
+void ath11k_core_pm_notifier_unregister(struct ath11k_base *ab);
+
 #endif /* _CORE_H_ */
diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 218ab41c0f3c..ea2959305dec 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -2637,7 +2637,7 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 	struct ath11k *ar;
 	struct hal_reo_dest_ring *desc;
 	enum hal_reo_dest_ring_push_reason push_reason;
-	u32 cookie;
+	u32 cookie, info0, rx_msdu_info0, rx_mpdu_info0;
 	int i;
 
 	for (i = 0; i < MAX_RADIOS; i++)
@@ -2650,11 +2650,14 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 try_again:
 	ath11k_hal_srng_access_begin(ab, srng);
 
+	/* Make sure descriptor is read after the head pointer. */
+	dma_rmb();
+
 	while (likely(desc =
 	      (struct hal_reo_dest_ring *)ath11k_hal_srng_dst_get_next_entry(ab,
 									     srng))) {
 		cookie = FIELD_GET(BUFFER_ADDR_INFO1_SW_COOKIE,
-				   desc->buf_addr_info.info1);
+				   READ_ONCE(desc->buf_addr_info.info1));
 		buf_id = FIELD_GET(DP_RXDMA_BUF_COOKIE_BUF_ID,
 				   cookie);
 		mac_id = FIELD_GET(DP_RXDMA_BUF_COOKIE_PDEV_ID, cookie);
@@ -2683,8 +2686,9 @@ try_again:
 
 		num_buffs_reaped[mac_id]++;
 
+		info0 = READ_ONCE(desc->info0);
 		push_reason = FIELD_GET(HAL_REO_DEST_RING_INFO0_PUSH_REASON,
-					desc->info0);
+					info0);
 		if (unlikely(push_reason !=
 			     HAL_REO_DEST_RING_PUSH_REASON_ROUTING_INSTRUCTION)) {
 			dev_kfree_skb_any(msdu);
@@ -2692,18 +2696,21 @@ try_again:
 			continue;
 		}
 
-		rxcb->is_first_msdu = !!(desc->rx_msdu_info.info0 &
+		rx_msdu_info0 = READ_ONCE(desc->rx_msdu_info.info0);
+		rx_mpdu_info0 = READ_ONCE(desc->rx_mpdu_info.info0);
+
+		rxcb->is_first_msdu = !!(rx_msdu_info0 &
 					 RX_MSDU_DESC_INFO0_FIRST_MSDU_IN_MPDU);
-		rxcb->is_last_msdu = !!(desc->rx_msdu_info.info0 &
+		rxcb->is_last_msdu = !!(rx_msdu_info0 &
 					RX_MSDU_DESC_INFO0_LAST_MSDU_IN_MPDU);
-		rxcb->is_continuation = !!(desc->rx_msdu_info.info0 &
+		rxcb->is_continuation = !!(rx_msdu_info0 &
 					   RX_MSDU_DESC_INFO0_MSDU_CONTINUATION);
 		rxcb->peer_id = FIELD_GET(RX_MPDU_DESC_META_DATA_PEER_ID,
-					  desc->rx_mpdu_info.meta_data);
+					  READ_ONCE(desc->rx_mpdu_info.meta_data));
 		rxcb->seq_no = FIELD_GET(RX_MPDU_DESC_INFO0_SEQ_NUM,
-					 desc->rx_mpdu_info.info0);
+					 rx_mpdu_info0);
 		rxcb->tid = FIELD_GET(HAL_REO_DEST_RING_INFO0_RX_QUEUE_NUM,
-				      desc->info0);
+				      info0);
 
 		rxcb->mac_id = mac_id;
 		__skb_queue_tail(&msdu_list[mac_id], msdu);
diff --git a/drivers/net/wireless/ath/ath11k/hal.c b/drivers/net/wireless/ath/ath11k/hal.c
index 61f4b6dd5380..8cb1505a5a0c 100644
--- a/drivers/net/wireless/ath/ath11k/hal.c
+++ b/drivers/net/wireless/ath/ath11k/hal.c
@@ -599,7 +599,7 @@ u32 ath11k_hal_ce_dst_status_get_length(void *buf)
 	struct hal_ce_srng_dst_status_desc *desc = buf;
 	u32 len;
 
-	len = FIELD_GET(HAL_CE_DST_STATUS_DESC_FLAGS_LEN, desc->flags);
+	len = FIELD_GET(HAL_CE_DST_STATUS_DESC_FLAGS_LEN, READ_ONCE(desc->flags));
 	desc->flags &= ~HAL_CE_DST_STATUS_DESC_FLAGS_LEN;
 
 	return len;
@@ -829,7 +829,7 @@ void ath11k_hal_srng_access_begin(struct ath11k_base *ab, struct hal_srng *srng)
 		srng->u.src_ring.cached_tp =
 			*(volatile u32 *)srng->u.src_ring.tp_addr;
 	} else {
-		srng->u.dst_ring.cached_hp = *srng->u.dst_ring.hp_addr;
+		srng->u.dst_ring.cached_hp = READ_ONCE(*srng->u.dst_ring.hp_addr);
 
 		/* Try to prefetch the next descriptor in the ring */
 		if (srng->flags & HAL_SRNG_FLAGS_CACHED)
diff --git a/drivers/net/wireless/ath/ath11k/hif.h b/drivers/net/wireless/ath/ath11k/hif.h
index 770c39ff99b4..cd9c4b838246 100644
--- a/drivers/net/wireless/ath/ath11k/hif.h
+++ b/drivers/net/wireless/ath/ath11k/hif.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2020 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _HIF_H_
@@ -18,7 +18,7 @@ struct ath11k_hif_ops {
 	int (*start)(struct ath11k_base *ab);
 	void (*stop)(struct ath11k_base *ab);
 	int (*power_up)(struct ath11k_base *ab);
-	void (*power_down)(struct ath11k_base *ab);
+	void (*power_down)(struct ath11k_base *ab, bool is_suspend);
 	int (*suspend)(struct ath11k_base *ab);
 	int (*resume)(struct ath11k_base *ab);
 	int (*map_service_to_pipe)(struct ath11k_base *ab, u16 service_id,
@@ -68,12 +68,18 @@ static inline void ath11k_hif_irq_disable(struct ath11k_base *ab)
 
 static inline int ath11k_hif_power_up(struct ath11k_base *ab)
 {
+	if (!ab->hif.ops->power_up)
+		return -EOPNOTSUPP;
+
 	return ab->hif.ops->power_up(ab);
 }
 
-static inline void ath11k_hif_power_down(struct ath11k_base *ab)
+static inline void ath11k_hif_power_down(struct ath11k_base *ab, bool is_suspend)
 {
-	ab->hif.ops->power_down(ab);
+	if (!ab->hif.ops->power_down)
+		return;
+
+	ab->hif.ops->power_down(ab, is_suspend);
 }
 
 static inline int ath11k_hif_suspend(struct ath11k_base *ab)
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 97816916abac..08d7b136851f 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -1531,8 +1531,14 @@ static int ath11k_mac_set_vif_params(struct ath11k_vif *arvif,
 
 static struct ath11k_vif *ath11k_mac_get_tx_arvif(struct ath11k_vif *arvif)
 {
-	if (arvif->vif->mbssid_tx_vif)
-		return ath11k_vif_to_arvif(arvif->vif->mbssid_tx_vif);
+	struct ieee80211_bss_conf *link_conf, *tx_bss_conf;
+
+	lockdep_assert_wiphy(arvif->ar->hw->wiphy);
+
+	link_conf = &arvif->vif->bss_conf;
+	tx_bss_conf = wiphy_dereference(arvif->ar->hw->wiphy, link_conf->tx_bss_conf);
+	if (tx_bss_conf)
+		return ath11k_vif_to_arvif(tx_bss_conf->vif);
 
 	return NULL;
 }
@@ -9966,12 +9972,17 @@ static int ath11k_mac_setup_iface_combinations(struct ath11k *ar)
 	struct ath11k_base *ab = ar->ab;
 	struct ieee80211_iface_combination *combinations;
 	struct ieee80211_iface_limit *limits;
-	int n_limits;
+	int n_limits, n_combos;
 	bool p2p;
 
 	p2p = ab->hw_params.interface_modes & BIT(NL80211_IFTYPE_P2P_DEVICE);
 
-	combinations = kzalloc(sizeof(*combinations), GFP_KERNEL);
+	if (ab->hw_params.support_dual_stations)
+		n_combos = 2;
+	else
+		n_combos = 1;
+
+	combinations = kcalloc(n_combos, sizeof(*combinations), GFP_KERNEL);
 	if (!combinations)
 		return -ENOMEM;
 
@@ -9986,7 +9997,9 @@ static int ath11k_mac_setup_iface_combinations(struct ath11k *ar)
 		return -ENOMEM;
 	}
 
+	limits[0].max = 1;
 	limits[0].types |= BIT(NL80211_IFTYPE_STATION);
+	limits[1].max = 16;
 	limits[1].types |= BIT(NL80211_IFTYPE_AP);
 	if (IS_ENABLED(CONFIG_MAC80211_MESH) &&
 	    ab->hw_params.interface_modes & BIT(NL80211_IFTYPE_MESH_POINT))
@@ -9996,25 +10009,24 @@ static int ath11k_mac_setup_iface_combinations(struct ath11k *ar)
 	combinations[0].n_limits = n_limits;
 	combinations[0].beacon_int_infra_match = true;
 	combinations[0].beacon_int_min_gcd = 100;
+	combinations[0].max_interfaces = 16;
+	combinations[0].num_different_channels = 1;
+	combinations[0].radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) |
+						BIT(NL80211_CHAN_WIDTH_20) |
+						BIT(NL80211_CHAN_WIDTH_40) |
+						BIT(NL80211_CHAN_WIDTH_80) |
+						BIT(NL80211_CHAN_WIDTH_80P80) |
+						BIT(NL80211_CHAN_WIDTH_160);
 
 	if (ab->hw_params.support_dual_stations) {
 		limits[0].max = 2;
-		limits[1].max = 1;
-
-		combinations[0].max_interfaces = ab->hw_params.num_vdevs;
-		combinations[0].num_different_channels = 2;
-	} else {
-		limits[0].max = 1;
-		limits[1].max = 16;
 
-		combinations[0].max_interfaces = 16;
-		combinations[0].num_different_channels = 1;
-		combinations[0].radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) |
-							BIT(NL80211_CHAN_WIDTH_20) |
-							BIT(NL80211_CHAN_WIDTH_40) |
-							BIT(NL80211_CHAN_WIDTH_80) |
-							BIT(NL80211_CHAN_WIDTH_80P80) |
-							BIT(NL80211_CHAN_WIDTH_160);
+		combinations[1].limits = limits;
+		combinations[1].n_limits = n_limits;
+		combinations[1].beacon_int_infra_match = true;
+		combinations[1].beacon_int_min_gcd = 100;
+		combinations[1].max_interfaces = ab->hw_params.num_vdevs;
+		combinations[1].num_different_channels = 2;
 	}
 
 	if (p2p) {
@@ -10025,7 +10037,7 @@ static int ath11k_mac_setup_iface_combinations(struct ath11k *ar)
 	}
 
 	ar->hw->wiphy->iface_combinations = combinations;
-	ar->hw->wiphy->n_iface_combinations = 1;
+	ar->hw->wiphy->n_iface_combinations = n_combos;
 
 	return 0;
 }
diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
index fc77eac83e95..acd76e9392d3 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.c
+++ b/drivers/net/wireless/ath/ath11k/mhi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2020 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/msi.h>
@@ -454,9 +454,17 @@ int ath11k_mhi_start(struct ath11k_pci *ab_pci)
 	return 0;
 }
 
-void ath11k_mhi_stop(struct ath11k_pci *ab_pci)
+void ath11k_mhi_stop(struct ath11k_pci *ab_pci, bool is_suspend)
 {
-	mhi_power_down(ab_pci->mhi_ctrl, true);
+	/* During suspend we need to use mhi_power_down_keep_dev()
+	 * workaround, otherwise ath11k_core_resume() will timeout
+	 * during resume.
+	 */
+	if (is_suspend)
+		mhi_power_down_keep_dev(ab_pci->mhi_ctrl, true);
+	else
+		mhi_power_down(ab_pci->mhi_ctrl, true);
+
 	mhi_unprepare_after_power_down(ab_pci->mhi_ctrl);
 }
 
diff --git a/drivers/net/wireless/ath/ath11k/mhi.h b/drivers/net/wireless/ath/ath11k/mhi.h
index 651470091bd5..5c5c2b03c81f 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.h
+++ b/drivers/net/wireless/ath/ath11k/mhi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2020 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022, 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #ifndef _ATH11K_MHI_H
 #define _ATH11K_MHI_H
@@ -18,7 +18,7 @@
 #define MHICTRL_RESET_MASK			0x2
 
 int ath11k_mhi_start(struct ath11k_pci *ar_pci);
-void ath11k_mhi_stop(struct ath11k_pci *ar_pci);
+void ath11k_mhi_stop(struct ath11k_pci *ar_pci, bool is_suspend);
 int ath11k_mhi_register(struct ath11k_pci *ar_pci);
 void ath11k_mhi_unregister(struct ath11k_pci *ar_pci);
 void ath11k_mhi_set_mhictrl_reset(struct ath11k_base *ab);
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index 412f4a134e4a..78444f8ea153 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -821,7 +821,7 @@ static int ath11k_pci_power_up(struct ath11k_base *ab)
 	return 0;
 }
 
-static void ath11k_pci_power_down(struct ath11k_base *ab)
+static void ath11k_pci_power_down(struct ath11k_base *ab, bool is_suspend)
 {
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
 
@@ -832,7 +832,7 @@ static void ath11k_pci_power_down(struct ath11k_base *ab)
 
 	ath11k_pci_msi_disable(ab_pci);
 
-	ath11k_mhi_stop(ab_pci);
+	ath11k_mhi_stop(ab_pci, is_suspend);
 	clear_bit(ATH11K_FLAG_DEVICE_INIT_DONE, &ab->dev_flags);
 	ath11k_pci_sw_reset(ab_pci->ab, false);
 }
@@ -929,7 +929,7 @@ static int ath11k_pci_probe(struct pci_dev *pdev,
 {
 	struct ath11k_base *ab;
 	struct ath11k_pci *ab_pci;
-	u32 soc_hw_version_major, soc_hw_version_minor, addr;
+	u32 soc_hw_version_major, soc_hw_version_minor;
 	int ret;
 	u32 sub_version;
 
@@ -955,8 +955,7 @@ static int ath11k_pci_probe(struct pci_dev *pdev,
 	 * from DT. If memory is reserved from DT for FW, ath11k driver need not
 	 * allocate memory.
 	 */
-	ret = of_property_read_u32(ab->dev->of_node, "memory-region", &addr);
-	if (!ret)
+	if (of_property_present(ab->dev->of_node, "memory-region"))
 		set_bit(ATH11K_FLAG_FIXED_MEM_RGN, &ab->dev_flags);
 
 	ret = ath11k_pci_claim(ab_pci, pdev);
@@ -1161,9 +1160,10 @@ static void ath11k_pci_remove(struct pci_dev *pdev)
 	ath11k_pci_set_irq_affinity_hint(ab_pci, NULL);
 
 	if (test_bit(ATH11K_FLAG_QMI_FAIL, &ab->dev_flags)) {
-		ath11k_pci_power_down(ab);
+		ath11k_pci_power_down(ab, false);
 		ath11k_debugfs_soc_destroy(ab);
 		ath11k_qmi_deinit_service(ab);
+		ath11k_core_pm_notifier_unregister(ab);
 		goto qmi_fail;
 	}
 
@@ -1192,7 +1192,7 @@ static void ath11k_pci_shutdown(struct pci_dev *pdev)
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
 
 	ath11k_pci_set_irq_affinity_hint(ab_pci, NULL);
-	ath11k_pci_power_down(ab);
+	ath11k_pci_power_down(ab, false);
 }
 
 static __maybe_unused int ath11k_pci_pm_suspend(struct device *dev)
@@ -1229,9 +1229,39 @@ static __maybe_unused int ath11k_pci_pm_resume(struct device *dev)
 	return ret;
 }
 
-static SIMPLE_DEV_PM_OPS(ath11k_pci_pm_ops,
-			 ath11k_pci_pm_suspend,
-			 ath11k_pci_pm_resume);
+static __maybe_unused int ath11k_pci_pm_suspend_late(struct device *dev)
+{
+	struct ath11k_base *ab = dev_get_drvdata(dev);
+	int ret;
+
+	ret = ath11k_core_suspend_late(ab);
+	if (ret)
+		ath11k_warn(ab, "failed to late suspend core: %d\n", ret);
+
+	/* Similar to ath11k_pci_pm_suspend(), we return success here
+	 * even error happens, to allow system suspend/hibernation survive.
+	 */
+	return 0;
+}
+
+static __maybe_unused int ath11k_pci_pm_resume_early(struct device *dev)
+{
+	struct ath11k_base *ab = dev_get_drvdata(dev);
+	int ret;
+
+	ret = ath11k_core_resume_early(ab);
+	if (ret)
+		ath11k_warn(ab, "failed to early resume core: %d\n", ret);
+
+	return ret;
+}
+
+static const struct dev_pm_ops __maybe_unused ath11k_pci_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(ath11k_pci_pm_suspend,
+				ath11k_pci_pm_resume)
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(ath11k_pci_pm_suspend_late,
+				     ath11k_pci_pm_resume_early)
+};
 
 static struct pci_driver ath11k_pci_driver = {
 	.name = "ath11k_pci",
diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index 4f8b08ed1bbc..2782f4723e41 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/elf.h>
@@ -1993,6 +1993,15 @@ static int ath11k_qmi_alloc_target_mem_chunk(struct ath11k_base *ab)
 			    chunk->prev_size == chunk->size)
 				continue;
 
+			if (ab->qmi.mem_seg_count <= ATH11K_QMI_FW_MEM_REQ_SEGMENT_CNT) {
+				ath11k_dbg(ab, ATH11K_DBG_QMI,
+					   "size/type mismatch (current %d %u) (prev %d %u), try later with small size\n",
+					    chunk->size, chunk->type,
+					    chunk->prev_size, chunk->prev_type);
+				ab->qmi.target_mem_delayed = true;
+				return 0;
+			}
+
 			/* cannot reuse the existing chunk */
 			dma_free_coherent(ab->dev, chunk->prev_size,
 					  chunk->vaddr, chunk->paddr);
@@ -2887,7 +2896,7 @@ int ath11k_qmi_fwreset_from_cold_boot(struct ath11k_base *ab)
 	}
 
 	/* reset the firmware */
-	ath11k_hif_power_down(ab);
+	ath11k_hif_power_down(ab, false);
 	ath11k_hif_power_up(ab);
 	ath11k_dbg(ab, ATH11K_DBG_QMI, "exit wait for cold boot done\n");
 	return 0;
diff --git a/drivers/net/wireless/ath/ath11k/testmode.c b/drivers/net/wireless/ath/ath11k/testmode.c
index 9be1cd742339..a9751ea2a0b7 100644
--- a/drivers/net/wireless/ath/ath11k/testmode.c
+++ b/drivers/net/wireless/ath/ath11k/testmode.c
@@ -107,7 +107,7 @@ static int ath11k_tm_process_event(struct ath11k_base *ab, u32 cmd_id,
 	u32 pdev_id;
 
 	ath11k_dbg(ab, ATH11K_DBG_TESTMODE,
-		   "event wmi cmd_id %d ftm event msg %pK datalen %d\n",
+		   "event wmi cmd_id %d ftm event msg %p datalen %d\n",
 		   cmd_id, ftm_msg, length);
 	ath11k_dbg_dump(ab, ATH11K_DBG_TESTMODE, NULL, "", ftm_msg, length);
 	pdev_id = DP_HW2SW_MACID(ftm_msg->seg_hdr.pdev_id);
diff --git a/drivers/net/wireless/ath/ath12k/Kconfig b/drivers/net/wireless/ath/ath12k/Kconfig
index 52a1bb19e3da..b3b15e1eb282 100644
--- a/drivers/net/wireless/ath/ath12k/Kconfig
+++ b/drivers/net/wireless/ath/ath12k/Kconfig
@@ -15,6 +15,14 @@ config ATH12K
 
 	  If you choose to build a module, it'll be called ath12k.
 
+config ATH12K_AHB
+	bool "QTI ath12k AHB support"
+	depends on ATH12K && REMOTEPROC
+	select QCOM_MDT_LOADER
+	select QCOM_SCM
+	help
+	  Enable support for Ath12k AHB bus chipsets, example IPQ5332.
+
 config ATH12K_DEBUG
 	bool "ath12k debugging"
 	depends on ATH12K
diff --git a/drivers/net/wireless/ath/ath12k/Makefile b/drivers/net/wireless/ath/ath12k/Makefile
index 60644cb42c76..d95ee525a6cd 100644
--- a/drivers/net/wireless/ath/ath12k/Makefile
+++ b/drivers/net/wireless/ath/ath12k/Makefile
@@ -23,6 +23,7 @@ ath12k-y += core.o \
 	    fw.o \
 	    p2p.o
 
+ath12k-$(CONFIG_ATH12K_AHB) += ahb.o
 ath12k-$(CONFIG_ATH12K_DEBUGFS) += debugfs.o debugfs_htt_stats.o debugfs_sta.o
 ath12k-$(CONFIG_ACPI) += acpi.o
 ath12k-$(CONFIG_ATH12K_TRACING) += trace.o
diff --git a/drivers/net/wireless/ath/ath12k/ahb.c b/drivers/net/wireless/ath/ath12k/ahb.c
new file mode 100644
index 000000000000..8d1a86e420a4
--- /dev/null
+++ b/drivers/net/wireless/ath/ath12k/ahb.c
@@ -0,0 +1,1155 @@
+// SPDX-License-Identifier: BSD-3-Clause-Clear
+/*
+ * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/firmware/qcom/qcom_scm.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/remoteproc.h>
+#include <linux/soc/qcom/mdt_loader.h>
+#include <linux/soc/qcom/smem_state.h>
+#include "ahb.h"
+#include "debug.h"
+#include "hif.h"
+
+static const struct of_device_id ath12k_ahb_of_match[] = {
+	{ .compatible = "qcom,ipq5332-wifi",
+	  .data = (void *)ATH12K_HW_IPQ5332_HW10,
+	},
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, ath12k_ahb_of_match);
+
+#define ATH12K_IRQ_CE0_OFFSET 4
+#define ATH12K_MAX_UPDS 1
+#define ATH12K_UPD_IRQ_WRD_LEN  18
+static const char ath12k_userpd_irq[][9] = {"spawn",
+				     "ready",
+				     "stop-ack"};
+
+static const char *irq_name[ATH12K_IRQ_NUM_MAX] = {
+	"misc-pulse1",
+	"misc-latch",
+	"sw-exception",
+	"watchdog",
+	"ce0",
+	"ce1",
+	"ce2",
+	"ce3",
+	"ce4",
+	"ce5",
+	"ce6",
+	"ce7",
+	"ce8",
+	"ce9",
+	"ce10",
+	"ce11",
+	"host2wbm-desc-feed",
+	"host2reo-re-injection",
+	"host2reo-command",
+	"host2rxdma-monitor-ring3",
+	"host2rxdma-monitor-ring2",
+	"host2rxdma-monitor-ring1",
+	"reo2ost-exception",
+	"wbm2host-rx-release",
+	"reo2host-status",
+	"reo2host-destination-ring4",
+	"reo2host-destination-ring3",
+	"reo2host-destination-ring2",
+	"reo2host-destination-ring1",
+	"rxdma2host-monitor-destination-mac3",
+	"rxdma2host-monitor-destination-mac2",
+	"rxdma2host-monitor-destination-mac1",
+	"ppdu-end-interrupts-mac3",
+	"ppdu-end-interrupts-mac2",
+	"ppdu-end-interrupts-mac1",
+	"rxdma2host-monitor-status-ring-mac3",
+	"rxdma2host-monitor-status-ring-mac2",
+	"rxdma2host-monitor-status-ring-mac1",
+	"host2rxdma-host-buf-ring-mac3",
+	"host2rxdma-host-buf-ring-mac2",
+	"host2rxdma-host-buf-ring-mac1",
+	"rxdma2host-destination-ring-mac3",
+	"rxdma2host-destination-ring-mac2",
+	"rxdma2host-destination-ring-mac1",
+	"host2tcl-input-ring4",
+	"host2tcl-input-ring3",
+	"host2tcl-input-ring2",
+	"host2tcl-input-ring1",
+	"wbm2host-tx-completions-ring4",
+	"wbm2host-tx-completions-ring3",
+	"wbm2host-tx-completions-ring2",
+	"wbm2host-tx-completions-ring1",
+	"tcl2host-status-ring",
+};
+
+enum ext_irq_num {
+	host2wbm_desc_feed = 16,
+	host2reo_re_injection,
+	host2reo_command,
+	host2rxdma_monitor_ring3,
+	host2rxdma_monitor_ring2,
+	host2rxdma_monitor_ring1,
+	reo2host_exception,
+	wbm2host_rx_release,
+	reo2host_status,
+	reo2host_destination_ring4,
+	reo2host_destination_ring3,
+	reo2host_destination_ring2,
+	reo2host_destination_ring1,
+	rxdma2host_monitor_destination_mac3,
+	rxdma2host_monitor_destination_mac2,
+	rxdma2host_monitor_destination_mac1,
+	ppdu_end_interrupts_mac3,
+	ppdu_end_interrupts_mac2,
+	ppdu_end_interrupts_mac1,
+	rxdma2host_monitor_status_ring_mac3,
+	rxdma2host_monitor_status_ring_mac2,
+	rxdma2host_monitor_status_ring_mac1,
+	host2rxdma_host_buf_ring_mac3,
+	host2rxdma_host_buf_ring_mac2,
+	host2rxdma_host_buf_ring_mac1,
+	rxdma2host_destination_ring_mac3,
+	rxdma2host_destination_ring_mac2,
+	rxdma2host_destination_ring_mac1,
+	host2tcl_input_ring4,
+	host2tcl_input_ring3,
+	host2tcl_input_ring2,
+	host2tcl_input_ring1,
+	wbm2host_tx_completions_ring4,
+	wbm2host_tx_completions_ring3,
+	wbm2host_tx_completions_ring2,
+	wbm2host_tx_completions_ring1,
+	tcl2host_status_ring,
+};
+
+static u32 ath12k_ahb_read32(struct ath12k_base *ab, u32 offset)
+{
+	if (ab->ce_remap && offset < HAL_SEQ_WCSS_CMEM_OFFSET)
+		return ioread32(ab->mem_ce + offset);
+	return ioread32(ab->mem + offset);
+}
+
+static void ath12k_ahb_write32(struct ath12k_base *ab, u32 offset,
+			       u32 value)
+{
+	if (ab->ce_remap && offset < HAL_SEQ_WCSS_CMEM_OFFSET)
+		iowrite32(value, ab->mem_ce + offset);
+	else
+		iowrite32(value, ab->mem + offset);
+}
+
+static void ath12k_ahb_cancel_workqueue(struct ath12k_base *ab)
+{
+	int i;
+
+	for (i = 0; i < ab->hw_params->ce_count; i++) {
+		struct ath12k_ce_pipe *ce_pipe = &ab->ce.ce_pipe[i];
+
+		if (ath12k_ce_get_attr_flags(ab, i) & CE_ATTR_DIS_INTR)
+			continue;
+
+		cancel_work_sync(&ce_pipe->intr_wq);
+	}
+}
+
+static void ath12k_ahb_ext_grp_disable(struct ath12k_ext_irq_grp *irq_grp)
+{
+	int i;
+
+	for (i = 0; i < irq_grp->num_irq; i++)
+		disable_irq_nosync(irq_grp->ab->irq_num[irq_grp->irqs[i]]);
+}
+
+static void __ath12k_ahb_ext_irq_disable(struct ath12k_base *ab)
+{
+	int i;
+
+	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
+		struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
+
+		ath12k_ahb_ext_grp_disable(irq_grp);
+		if (irq_grp->napi_enabled) {
+			napi_synchronize(&irq_grp->napi);
+			napi_disable(&irq_grp->napi);
+			irq_grp->napi_enabled = false;
+		}
+	}
+}
+
+static void ath12k_ahb_ext_grp_enable(struct ath12k_ext_irq_grp *irq_grp)
+{
+	int i;
+
+	for (i = 0; i < irq_grp->num_irq; i++)
+		enable_irq(irq_grp->ab->irq_num[irq_grp->irqs[i]]);
+}
+
+static void ath12k_ahb_setbit32(struct ath12k_base *ab, u8 bit, u32 offset)
+{
+	u32 val;
+
+	val = ath12k_ahb_read32(ab, offset);
+	ath12k_ahb_write32(ab, offset, val | BIT(bit));
+}
+
+static void ath12k_ahb_clearbit32(struct ath12k_base *ab, u8 bit, u32 offset)
+{
+	u32 val;
+
+	val = ath12k_ahb_read32(ab, offset);
+	ath12k_ahb_write32(ab, offset, val & ~BIT(bit));
+}
+
+static void ath12k_ahb_ce_irq_enable(struct ath12k_base *ab, u16 ce_id)
+{
+	const struct ce_attr *ce_attr;
+	const struct ce_ie_addr *ce_ie_addr = ab->hw_params->ce_ie_addr;
+	u32 ie1_reg_addr, ie2_reg_addr, ie3_reg_addr;
+
+	ie1_reg_addr = ce_ie_addr->ie1_reg_addr;
+	ie2_reg_addr = ce_ie_addr->ie2_reg_addr;
+	ie3_reg_addr = ce_ie_addr->ie3_reg_addr;
+
+	ce_attr = &ab->hw_params->host_ce_config[ce_id];
+	if (ce_attr->src_nentries)
+		ath12k_ahb_setbit32(ab, ce_id, ie1_reg_addr);
+
+	if (ce_attr->dest_nentries) {
+		ath12k_ahb_setbit32(ab, ce_id, ie2_reg_addr);
+		ath12k_ahb_setbit32(ab, ce_id + CE_HOST_IE_3_SHIFT,
+				    ie3_reg_addr);
+	}
+}
+
+static void ath12k_ahb_ce_irq_disable(struct ath12k_base *ab, u16 ce_id)
+{
+	const struct ce_attr *ce_attr;
+	const struct ce_ie_addr *ce_ie_addr = ab->hw_params->ce_ie_addr;
+	u32 ie1_reg_addr, ie2_reg_addr, ie3_reg_addr;
+
+	ie1_reg_addr = ce_ie_addr->ie1_reg_addr;
+	ie2_reg_addr = ce_ie_addr->ie2_reg_addr;
+	ie3_reg_addr = ce_ie_addr->ie3_reg_addr;
+
+	ce_attr = &ab->hw_params->host_ce_config[ce_id];
+	if (ce_attr->src_nentries)
+		ath12k_ahb_clearbit32(ab, ce_id, ie1_reg_addr);
+
+	if (ce_attr->dest_nentries) {
+		ath12k_ahb_clearbit32(ab, ce_id, ie2_reg_addr);
+		ath12k_ahb_clearbit32(ab, ce_id + CE_HOST_IE_3_SHIFT,
+				      ie3_reg_addr);
+	}
+}
+
+static void ath12k_ahb_sync_ce_irqs(struct ath12k_base *ab)
+{
+	int i;
+	int irq_idx;
+
+	for (i = 0; i < ab->hw_params->ce_count; i++) {
+		if (ath12k_ce_get_attr_flags(ab, i) & CE_ATTR_DIS_INTR)
+			continue;
+
+		irq_idx = ATH12K_IRQ_CE0_OFFSET + i;
+		synchronize_irq(ab->irq_num[irq_idx]);
+	}
+}
+
+static void ath12k_ahb_sync_ext_irqs(struct ath12k_base *ab)
+{
+	int i, j;
+	int irq_idx;
+
+	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
+		struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
+
+		for (j = 0; j < irq_grp->num_irq; j++) {
+			irq_idx = irq_grp->irqs[j];
+			synchronize_irq(ab->irq_num[irq_idx]);
+		}
+	}
+}
+
+static void ath12k_ahb_ce_irqs_enable(struct ath12k_base *ab)
+{
+	int i;
+
+	for (i = 0; i < ab->hw_params->ce_count; i++) {
+		if (ath12k_ce_get_attr_flags(ab, i) & CE_ATTR_DIS_INTR)
+			continue;
+		ath12k_ahb_ce_irq_enable(ab, i);
+	}
+}
+
+static void ath12k_ahb_ce_irqs_disable(struct ath12k_base *ab)
+{
+	int i;
+
+	for (i = 0; i < ab->hw_params->ce_count; i++) {
+		if (ath12k_ce_get_attr_flags(ab, i) & CE_ATTR_DIS_INTR)
+			continue;
+		ath12k_ahb_ce_irq_disable(ab, i);
+	}
+}
+
+static int ath12k_ahb_start(struct ath12k_base *ab)
+{
+	ath12k_ahb_ce_irqs_enable(ab);
+	ath12k_ce_rx_post_buf(ab);
+
+	return 0;
+}
+
+static void ath12k_ahb_ext_irq_enable(struct ath12k_base *ab)
+{
+	struct ath12k_ext_irq_grp *irq_grp;
+	int i;
+
+	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
+		irq_grp = &ab->ext_irq_grp[i];
+		if (!irq_grp->napi_enabled) {
+			napi_enable(&irq_grp->napi);
+			irq_grp->napi_enabled = true;
+		}
+		ath12k_ahb_ext_grp_enable(irq_grp);
+	}
+}
+
+static void ath12k_ahb_ext_irq_disable(struct ath12k_base *ab)
+{
+	__ath12k_ahb_ext_irq_disable(ab);
+	ath12k_ahb_sync_ext_irqs(ab);
+}
+
+static void ath12k_ahb_stop(struct ath12k_base *ab)
+{
+	if (!test_bit(ATH12K_FLAG_CRASH_FLUSH, &ab->dev_flags))
+		ath12k_ahb_ce_irqs_disable(ab);
+	ath12k_ahb_sync_ce_irqs(ab);
+	ath12k_ahb_cancel_workqueue(ab);
+	timer_delete_sync(&ab->rx_replenish_retry);
+	ath12k_ce_cleanup_pipes(ab);
+}
+
+static int ath12k_ahb_power_up(struct ath12k_base *ab)
+{
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+	char fw_name[ATH12K_USERPD_FW_NAME_LEN];
+	char fw2_name[ATH12K_USERPD_FW_NAME_LEN];
+	struct device *dev = ab->dev;
+	const struct firmware *fw, *fw2;
+	struct reserved_mem *rmem = NULL;
+	unsigned long time_left;
+	phys_addr_t mem_phys;
+	void *mem_region;
+	size_t mem_size;
+	u32 pasid;
+	int ret;
+
+	rmem = ath12k_core_get_reserved_mem(ab, 0);
+	if (!rmem)
+		return -ENODEV;
+
+	mem_phys = rmem->base;
+	mem_size = rmem->size;
+	mem_region = devm_memremap(dev, mem_phys, mem_size, MEMREMAP_WC);
+	if (IS_ERR(mem_region)) {
+		ath12k_err(ab, "unable to map memory region: %pa+%pa\n",
+			   &rmem->base, &rmem->size);
+		return PTR_ERR(mem_region);
+	}
+
+	snprintf(fw_name, sizeof(fw_name), "%s/%s/%s%d%s", ATH12K_FW_DIR,
+		 ab->hw_params->fw.dir, ATH12K_AHB_FW_PREFIX, ab_ahb->userpd_id,
+		 ATH12K_AHB_FW_SUFFIX);
+
+	ret = request_firmware(&fw, fw_name, dev);
+	if (ret < 0) {
+		ath12k_err(ab, "request_firmware failed\n");
+		return ret;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_AHB, "Booting fw image %s, size %zd\n", fw_name,
+		   fw->size);
+
+	if (!fw->size) {
+		ath12k_err(ab, "Invalid firmware size\n");
+		ret = -EINVAL;
+		goto err_fw;
+	}
+
+	pasid = (u32_encode_bits(ab_ahb->userpd_id, ATH12K_USERPD_ID_MASK)) |
+		ATH12K_AHB_UPD_SWID;
+
+	/* Load FW image to a reserved memory location */
+	ret = qcom_mdt_load(dev, fw, fw_name, pasid, mem_region, mem_phys, mem_size,
+			    &mem_phys);
+	if (ret) {
+		ath12k_err(ab, "Failed to load MDT segments: %d\n", ret);
+		goto err_fw;
+	}
+
+	snprintf(fw2_name, sizeof(fw2_name), "%s/%s/%s", ATH12K_FW_DIR,
+		 ab->hw_params->fw.dir, ATH12K_AHB_FW2);
+
+	ret = request_firmware(&fw2, fw2_name, dev);
+	if (ret < 0) {
+		ath12k_err(ab, "request_firmware failed\n");
+		goto err_fw;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_AHB, "Booting fw image %s, size %zd\n", fw2_name,
+		   fw2->size);
+
+	if (!fw2->size) {
+		ath12k_err(ab, "Invalid firmware size\n");
+		ret = -EINVAL;
+		goto err_fw2;
+	}
+
+	ret = qcom_mdt_load_no_init(dev, fw2, fw2_name, pasid, mem_region, mem_phys,
+				    mem_size, &mem_phys);
+	if (ret) {
+		ath12k_err(ab, "Failed to load MDT segments: %d\n", ret);
+		goto err_fw2;
+	}
+
+	/* Authenticate FW image using peripheral ID */
+	ret = qcom_scm_pas_auth_and_reset(pasid);
+	if (ret) {
+		ath12k_err(ab, "failed to boot the remote processor %d\n", ret);
+		goto err_fw2;
+	}
+
+	/* Instruct Q6 to spawn userPD thread */
+	ret = qcom_smem_state_update_bits(ab_ahb->spawn_state, BIT(ab_ahb->spawn_bit),
+					  BIT(ab_ahb->spawn_bit));
+	if (ret) {
+		ath12k_err(ab, "Failed to update spawn state %d\n", ret);
+		goto err_fw2;
+	}
+
+	time_left = wait_for_completion_timeout(&ab_ahb->userpd_spawned,
+						ATH12K_USERPD_SPAWN_TIMEOUT);
+	if (!time_left) {
+		ath12k_err(ab, "UserPD spawn wait timed out\n");
+		ret = -ETIMEDOUT;
+		goto err_fw2;
+	}
+
+	time_left = wait_for_completion_timeout(&ab_ahb->userpd_ready,
+						ATH12K_USERPD_READY_TIMEOUT);
+	if (!time_left) {
+		ath12k_err(ab, "UserPD ready wait timed out\n");
+		ret = -ETIMEDOUT;
+		goto err_fw2;
+	}
+
+	qcom_smem_state_update_bits(ab_ahb->spawn_state, BIT(ab_ahb->spawn_bit), 0);
+
+	ath12k_dbg(ab, ATH12K_DBG_AHB, "UserPD%d is now UP\n", ab_ahb->userpd_id);
+
+err_fw2:
+	release_firmware(fw2);
+err_fw:
+	release_firmware(fw);
+	return ret;
+}
+
+static void ath12k_ahb_power_down(struct ath12k_base *ab, bool is_suspend)
+{
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+	unsigned long time_left;
+	u32 pasid;
+	int ret;
+
+	qcom_smem_state_update_bits(ab_ahb->stop_state, BIT(ab_ahb->stop_bit),
+				    BIT(ab_ahb->stop_bit));
+
+	time_left = wait_for_completion_timeout(&ab_ahb->userpd_stopped,
+						ATH12K_USERPD_STOP_TIMEOUT);
+	if (!time_left) {
+		ath12k_err(ab, "UserPD stop wait timed out\n");
+		return;
+	}
+
+	qcom_smem_state_update_bits(ab_ahb->stop_state, BIT(ab_ahb->stop_bit), 0);
+
+	pasid = (u32_encode_bits(ab_ahb->userpd_id, ATH12K_USERPD_ID_MASK)) |
+		ATH12K_AHB_UPD_SWID;
+	/* Release the firmware */
+	ret = qcom_scm_pas_shutdown(pasid);
+	if (ret)
+		ath12k_err(ab, "scm pas shutdown failed for userPD%d: %d\n",
+			   ab_ahb->userpd_id, ret);
+}
+
+static void ath12k_ahb_init_qmi_ce_config(struct ath12k_base *ab)
+{
+	struct ath12k_qmi_ce_cfg *cfg = &ab->qmi.ce_cfg;
+
+	cfg->tgt_ce_len = ab->hw_params->target_ce_count;
+	cfg->tgt_ce = ab->hw_params->target_ce_config;
+	cfg->svc_to_ce_map_len = ab->hw_params->svc_to_ce_map_len;
+	cfg->svc_to_ce_map = ab->hw_params->svc_to_ce_map;
+	ab->qmi.service_ins_id = ab->hw_params->qmi_service_ins_id;
+}
+
+static void ath12k_ahb_ce_workqueue(struct work_struct *work)
+{
+	struct ath12k_ce_pipe *ce_pipe = from_work(ce_pipe, work, intr_wq);
+
+	ath12k_ce_per_engine_service(ce_pipe->ab, ce_pipe->pipe_num);
+
+	ath12k_ahb_ce_irq_enable(ce_pipe->ab, ce_pipe->pipe_num);
+}
+
+static irqreturn_t ath12k_ahb_ce_interrupt_handler(int irq, void *arg)
+{
+	struct ath12k_ce_pipe *ce_pipe = arg;
+
+	/* last interrupt received for this CE */
+	ce_pipe->timestamp = jiffies;
+
+	ath12k_ahb_ce_irq_disable(ce_pipe->ab, ce_pipe->pipe_num);
+
+	queue_work(system_bh_wq, &ce_pipe->intr_wq);
+
+	return IRQ_HANDLED;
+}
+
+static int ath12k_ahb_ext_grp_napi_poll(struct napi_struct *napi, int budget)
+{
+	struct ath12k_ext_irq_grp *irq_grp = container_of(napi,
+						struct ath12k_ext_irq_grp,
+						napi);
+	struct ath12k_base *ab = irq_grp->ab;
+	int work_done;
+
+	work_done = ath12k_dp_service_srng(ab, irq_grp, budget);
+	if (work_done < budget) {
+		napi_complete_done(napi, work_done);
+		ath12k_ahb_ext_grp_enable(irq_grp);
+	}
+
+	if (work_done > budget)
+		work_done = budget;
+
+	return work_done;
+}
+
+static irqreturn_t ath12k_ahb_ext_interrupt_handler(int irq, void *arg)
+{
+	struct ath12k_ext_irq_grp *irq_grp = arg;
+
+	/* last interrupt received for this group */
+	irq_grp->timestamp = jiffies;
+
+	ath12k_ahb_ext_grp_disable(irq_grp);
+
+	napi_schedule(&irq_grp->napi);
+
+	return IRQ_HANDLED;
+}
+
+static int ath12k_ahb_config_ext_irq(struct ath12k_base *ab)
+{
+	const struct ath12k_hw_ring_mask *ring_mask;
+	struct ath12k_ext_irq_grp *irq_grp;
+	const struct hal_ops *hal_ops;
+	int i, j, irq, irq_idx, ret;
+	u32 num_irq;
+
+	ring_mask = ab->hw_params->ring_mask;
+	hal_ops = ab->hw_params->hal_ops;
+	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
+		irq_grp = &ab->ext_irq_grp[i];
+		num_irq = 0;
+
+		irq_grp->ab = ab;
+		irq_grp->grp_id = i;
+
+		irq_grp->napi_ndev = alloc_netdev_dummy(0);
+		if (!irq_grp->napi_ndev)
+			return -ENOMEM;
+
+		netif_napi_add(irq_grp->napi_ndev, &irq_grp->napi,
+			       ath12k_ahb_ext_grp_napi_poll);
+
+		for (j = 0; j < ATH12K_EXT_IRQ_NUM_MAX; j++) {
+			/* For TX ring, ensure that the ring mask and the
+			 * tcl_to_wbm_rbm_map point to the same ring number.
+			 */
+			if (ring_mask->tx[i] &
+			    BIT(hal_ops->tcl_to_wbm_rbm_map[j].wbm_ring_num)) {
+				irq_grp->irqs[num_irq++] =
+					wbm2host_tx_completions_ring1 - j;
+			}
+
+			if (ring_mask->rx[i] & BIT(j)) {
+				irq_grp->irqs[num_irq++] =
+					reo2host_destination_ring1 - j;
+			}
+
+			if (ring_mask->rx_err[i] & BIT(j))
+				irq_grp->irqs[num_irq++] = reo2host_exception;
+
+			if (ring_mask->rx_wbm_rel[i] & BIT(j))
+				irq_grp->irqs[num_irq++] = wbm2host_rx_release;
+
+			if (ring_mask->reo_status[i] & BIT(j))
+				irq_grp->irqs[num_irq++] = reo2host_status;
+
+			if (ring_mask->rx_mon_dest[i] & BIT(j))
+				irq_grp->irqs[num_irq++] =
+					rxdma2host_monitor_destination_mac1;
+		}
+
+		irq_grp->num_irq = num_irq;
+
+		for (j = 0; j < irq_grp->num_irq; j++) {
+			irq_idx = irq_grp->irqs[j];
+
+			irq = platform_get_irq_byname(ab->pdev,
+						      irq_name[irq_idx]);
+			ab->irq_num[irq_idx] = irq;
+			irq_set_status_flags(irq, IRQ_NOAUTOEN | IRQ_DISABLE_UNLAZY);
+			ret = devm_request_irq(ab->dev, irq,
+					       ath12k_ahb_ext_interrupt_handler,
+					       IRQF_TRIGGER_RISING,
+					       irq_name[irq_idx], irq_grp);
+			if (ret)
+				ath12k_warn(ab, "failed request_irq for %d\n", irq);
+		}
+	}
+
+	return 0;
+}
+
+static int ath12k_ahb_config_irq(struct ath12k_base *ab)
+{
+	int irq, irq_idx, i;
+	int ret;
+
+	/* Configure CE irqs */
+	for (i = 0; i < ab->hw_params->ce_count; i++) {
+		struct ath12k_ce_pipe *ce_pipe = &ab->ce.ce_pipe[i];
+
+		if (ath12k_ce_get_attr_flags(ab, i) & CE_ATTR_DIS_INTR)
+			continue;
+
+		irq_idx = ATH12K_IRQ_CE0_OFFSET + i;
+
+		INIT_WORK(&ce_pipe->intr_wq, ath12k_ahb_ce_workqueue);
+		irq = platform_get_irq_byname(ab->pdev, irq_name[irq_idx]);
+		ret = devm_request_irq(ab->dev, irq, ath12k_ahb_ce_interrupt_handler,
+				       IRQF_TRIGGER_RISING, irq_name[irq_idx],
+				       ce_pipe);
+		if (ret)
+			return ret;
+
+		ab->irq_num[irq_idx] = irq;
+	}
+
+	/* Configure external interrupts */
+	ret = ath12k_ahb_config_ext_irq(ab);
+
+	return ret;
+}
+
+static int ath12k_ahb_map_service_to_pipe(struct ath12k_base *ab, u16 service_id,
+					  u8 *ul_pipe, u8 *dl_pipe)
+{
+	const struct service_to_pipe *entry;
+	bool ul_set = false, dl_set = false;
+	u32 pipedir;
+	int i;
+
+	for (i = 0; i < ab->hw_params->svc_to_ce_map_len; i++) {
+		entry = &ab->hw_params->svc_to_ce_map[i];
+
+		if (__le32_to_cpu(entry->service_id) != service_id)
+			continue;
+
+		pipedir = __le32_to_cpu(entry->pipedir);
+		if (pipedir == PIPEDIR_IN || pipedir == PIPEDIR_INOUT) {
+			WARN_ON(dl_set);
+			*dl_pipe = __le32_to_cpu(entry->pipenum);
+			dl_set = true;
+		}
+
+		if (pipedir == PIPEDIR_OUT || pipedir == PIPEDIR_INOUT) {
+			WARN_ON(ul_set);
+			*ul_pipe = __le32_to_cpu(entry->pipenum);
+			ul_set = true;
+		}
+	}
+
+	if (WARN_ON(!ul_set || !dl_set))
+		return -ENOENT;
+
+	return 0;
+}
+
+static const struct ath12k_hif_ops ath12k_ahb_hif_ops_ipq5332 = {
+	.start = ath12k_ahb_start,
+	.stop = ath12k_ahb_stop,
+	.read32 = ath12k_ahb_read32,
+	.write32 = ath12k_ahb_write32,
+	.irq_enable = ath12k_ahb_ext_irq_enable,
+	.irq_disable = ath12k_ahb_ext_irq_disable,
+	.map_service_to_pipe = ath12k_ahb_map_service_to_pipe,
+	.power_up = ath12k_ahb_power_up,
+	.power_down = ath12k_ahb_power_down,
+};
+
+static irqreturn_t ath12k_userpd_irq_handler(int irq, void *data)
+{
+	struct ath12k_base *ab = data;
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+
+	if (irq == ab_ahb->userpd_irq_num[ATH12K_USERPD_SPAWN_IRQ]) {
+		complete(&ab_ahb->userpd_spawned);
+	} else if (irq == ab_ahb->userpd_irq_num[ATH12K_USERPD_READY_IRQ]) {
+		complete(&ab_ahb->userpd_ready);
+	} else if (irq == ab_ahb->userpd_irq_num[ATH12K_USERPD_STOP_ACK_IRQ])	{
+		complete(&ab_ahb->userpd_stopped);
+	} else {
+		ath12k_err(ab, "Invalid userpd interrupt\n");
+		return IRQ_NONE;
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int ath12k_ahb_config_rproc_irq(struct ath12k_base *ab)
+{
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+	int i, ret;
+	char *upd_irq_name;
+
+	for (i = 0; i < ATH12K_USERPD_MAX_IRQ; i++) {
+		ab_ahb->userpd_irq_num[i] = platform_get_irq_byname(ab->pdev,
+								    ath12k_userpd_irq[i]);
+		if (ab_ahb->userpd_irq_num[i] < 0)
+			return ab_ahb->userpd_irq_num[i];
+
+		upd_irq_name = devm_kzalloc(&ab->pdev->dev, ATH12K_UPD_IRQ_WRD_LEN,
+					    GFP_KERNEL);
+		if (!upd_irq_name)
+			return -ENOMEM;
+
+		scnprintf(upd_irq_name, ATH12K_UPD_IRQ_WRD_LEN, "UserPD%u-%s",
+			  ab_ahb->userpd_id, ath12k_userpd_irq[i]);
+		ret = devm_request_threaded_irq(&ab->pdev->dev, ab_ahb->userpd_irq_num[i],
+						NULL, ath12k_userpd_irq_handler,
+						IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+						upd_irq_name, ab);
+		if (ret)
+			return dev_err_probe(&ab->pdev->dev, ret,
+					     "Request %s irq failed: %d\n",
+					     ath12k_userpd_irq[i], ret);
+	}
+
+	ab_ahb->spawn_state = devm_qcom_smem_state_get(&ab->pdev->dev, "spawn",
+						       &ab_ahb->spawn_bit);
+	if (IS_ERR(ab_ahb->spawn_state))
+		return dev_err_probe(&ab->pdev->dev, PTR_ERR(ab_ahb->spawn_state),
+				     "Failed to acquire spawn state\n");
+
+	ab_ahb->stop_state = devm_qcom_smem_state_get(&ab->pdev->dev, "stop",
+						      &ab_ahb->stop_bit);
+	if (IS_ERR(ab_ahb->stop_state))
+		return dev_err_probe(&ab->pdev->dev, PTR_ERR(ab_ahb->stop_state),
+				     "Failed to acquire stop state\n");
+
+	init_completion(&ab_ahb->userpd_spawned);
+	init_completion(&ab_ahb->userpd_ready);
+	init_completion(&ab_ahb->userpd_stopped);
+	return 0;
+}
+
+static int ath12k_ahb_root_pd_state_notifier(struct notifier_block *nb,
+					     const unsigned long event, void *data)
+{
+	struct ath12k_ahb *ab_ahb = container_of(nb, struct ath12k_ahb, root_pd_nb);
+	struct ath12k_base *ab = ab_ahb->ab;
+
+	if (event == ATH12K_RPROC_AFTER_POWERUP) {
+		ath12k_dbg(ab, ATH12K_DBG_AHB, "Root PD is UP\n");
+		complete(&ab_ahb->rootpd_ready);
+	}
+
+	return 0;
+}
+
+static int ath12k_ahb_register_rproc_notifier(struct ath12k_base *ab)
+{
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+
+	ab_ahb->root_pd_nb.notifier_call = ath12k_ahb_root_pd_state_notifier;
+	init_completion(&ab_ahb->rootpd_ready);
+
+	ab_ahb->root_pd_notifier = qcom_register_ssr_notifier(ab_ahb->tgt_rproc->name,
+							      &ab_ahb->root_pd_nb);
+	if (IS_ERR(ab_ahb->root_pd_notifier))
+		return PTR_ERR(ab_ahb->root_pd_notifier);
+
+	return 0;
+}
+
+static void ath12k_ahb_unregister_rproc_notifier(struct ath12k_base *ab)
+{
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+
+	if (!ab_ahb->root_pd_notifier) {
+		ath12k_err(ab, "Rproc notifier not registered\n");
+		return;
+	}
+
+	qcom_unregister_ssr_notifier(ab_ahb->root_pd_notifier,
+				     &ab_ahb->root_pd_nb);
+	ab_ahb->root_pd_notifier = NULL;
+}
+
+static int ath12k_ahb_get_rproc(struct ath12k_base *ab)
+{
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+	struct device *dev = ab->dev;
+	struct device_node *np;
+	struct rproc *prproc;
+
+	np = of_parse_phandle(dev->of_node, "qcom,rproc", 0);
+	if (!np) {
+		ath12k_err(ab, "failed to get q6_rproc handle\n");
+		return -ENOENT;
+	}
+
+	prproc = rproc_get_by_phandle(np->phandle);
+	of_node_put(np);
+	if (!prproc)
+		return dev_err_probe(&ab->pdev->dev, -EPROBE_DEFER,
+				     "failed to get rproc\n");
+
+	ab_ahb->tgt_rproc = prproc;
+
+	return 0;
+}
+
+static int ath12k_ahb_boot_root_pd(struct ath12k_base *ab)
+{
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+	unsigned long time_left;
+	int ret;
+
+	ret = rproc_boot(ab_ahb->tgt_rproc);
+	if (ret < 0) {
+		ath12k_err(ab, "RootPD boot failed\n");
+		return ret;
+	}
+
+	time_left = wait_for_completion_timeout(&ab_ahb->rootpd_ready,
+						ATH12K_ROOTPD_READY_TIMEOUT);
+	if (!time_left) {
+		ath12k_err(ab, "RootPD ready wait timed out\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static int ath12k_ahb_configure_rproc(struct ath12k_base *ab)
+{
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+	int ret;
+
+	ret = ath12k_ahb_get_rproc(ab);
+	if (ret < 0)
+		return ret;
+
+	ret = ath12k_ahb_register_rproc_notifier(ab);
+	if (ret < 0) {
+		ret = dev_err_probe(&ab->pdev->dev, ret,
+				    "failed to register rproc notifier\n");
+		goto err_put_rproc;
+	}
+
+	if (ab_ahb->tgt_rproc->state != RPROC_RUNNING) {
+		ret = ath12k_ahb_boot_root_pd(ab);
+		if (ret < 0) {
+			ath12k_err(ab, "failed to boot the remote processor Q6\n");
+			goto err_unreg_notifier;
+		}
+	}
+
+	return ath12k_ahb_config_rproc_irq(ab);
+
+err_unreg_notifier:
+	ath12k_ahb_unregister_rproc_notifier(ab);
+
+err_put_rproc:
+	rproc_put(ab_ahb->tgt_rproc);
+	return ret;
+}
+
+static void ath12k_ahb_deconfigure_rproc(struct ath12k_base *ab)
+{
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+
+	ath12k_ahb_unregister_rproc_notifier(ab);
+	rproc_put(ab_ahb->tgt_rproc);
+}
+
+static int ath12k_ahb_resource_init(struct ath12k_base *ab)
+{
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+	struct platform_device *pdev = ab->pdev;
+	struct resource *mem_res;
+	int ret;
+
+	ab->mem = devm_platform_get_and_ioremap_resource(pdev, 0, &mem_res);
+	if (IS_ERR(ab->mem)) {
+		ret = dev_err_probe(&pdev->dev, PTR_ERR(ab->mem), "ioremap error\n");
+		goto out;
+	}
+
+	ab->mem_len = resource_size(mem_res);
+
+	if (ab->hw_params->ce_remap) {
+		const struct ce_remap *ce_remap = ab->hw_params->ce_remap;
+		/* CE register space is moved out of WCSS and the space is not
+		 * contiguous, hence remapping the CE registers to a new space
+		 * for accessing them.
+		 */
+		ab->mem_ce = ioremap(ce_remap->base, ce_remap->size);
+		if (!ab->mem_ce) {
+			dev_err(&pdev->dev, "ce ioremap error\n");
+			ret = -ENOMEM;
+			goto err_mem_unmap;
+		}
+		ab->ce_remap = true;
+		ab->ce_remap_base_addr = HAL_IPQ5332_CE_WFSS_REG_BASE;
+	}
+
+	ab_ahb->xo_clk = devm_clk_get(ab->dev, "xo");
+	if (IS_ERR(ab_ahb->xo_clk)) {
+		ret = dev_err_probe(&pdev->dev, PTR_ERR(ab_ahb->xo_clk),
+				    "failed to get xo clock\n");
+		goto err_mem_ce_unmap;
+	}
+
+	ret = clk_prepare_enable(ab_ahb->xo_clk);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to enable gcc_xo_clk: %d\n", ret);
+		goto err_clock_deinit;
+	}
+
+	return 0;
+
+err_clock_deinit:
+	devm_clk_put(ab->dev, ab_ahb->xo_clk);
+
+err_mem_ce_unmap:
+	ab_ahb->xo_clk = NULL;
+	if (ab->hw_params->ce_remap)
+		iounmap(ab->mem_ce);
+
+err_mem_unmap:
+	ab->mem_ce = NULL;
+	devm_iounmap(ab->dev, ab->mem);
+
+out:
+	ab->mem = NULL;
+	return ret;
+}
+
+static void ath12k_ahb_resource_deinit(struct ath12k_base *ab)
+{
+	struct ath12k_ahb *ab_ahb = ath12k_ab_to_ahb(ab);
+
+	if (ab->mem)
+		devm_iounmap(ab->dev, ab->mem);
+
+	if (ab->mem_ce)
+		iounmap(ab->mem_ce);
+
+	ab->mem = NULL;
+	ab->mem_ce = NULL;
+
+	clk_disable_unprepare(ab_ahb->xo_clk);
+	devm_clk_put(ab->dev, ab_ahb->xo_clk);
+	ab_ahb->xo_clk = NULL;
+}
+
+static int ath12k_ahb_probe(struct platform_device *pdev)
+{
+	struct ath12k_base *ab;
+	const struct ath12k_hif_ops *hif_ops;
+	struct ath12k_ahb *ab_ahb;
+	enum ath12k_hw_rev hw_rev;
+	u32 addr, userpd_id;
+	int ret;
+
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to set 32-bit coherent dma\n");
+		return ret;
+	}
+
+	ab = ath12k_core_alloc(&pdev->dev, sizeof(struct ath12k_ahb),
+			       ATH12K_BUS_AHB);
+	if (!ab)
+		return -ENOMEM;
+
+	hw_rev = (enum ath12k_hw_rev)(kernel_ulong_t)of_device_get_match_data(&pdev->dev);
+	switch (hw_rev) {
+	case ATH12K_HW_IPQ5332_HW10:
+		hif_ops = &ath12k_ahb_hif_ops_ipq5332;
+		userpd_id = ATH12K_IPQ5332_USERPD_ID;
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		goto err_core_free;
+	}
+
+	ab->hif.ops = hif_ops;
+	ab->pdev = pdev;
+	ab->hw_rev = hw_rev;
+	platform_set_drvdata(pdev, ab);
+	ab_ahb = ath12k_ab_to_ahb(ab);
+	ab_ahb->ab = ab;
+	ab_ahb->userpd_id = userpd_id;
+
+	/* Set fixed_mem_region to true for platforms that support fixed memory
+	 * reservation from DT. If memory is reserved from DT for FW, ath12k driver
+	 * need not to allocate memory.
+	 */
+	if (!of_property_read_u32(ab->dev->of_node, "memory-region", &addr))
+		set_bit(ATH12K_FLAG_FIXED_MEM_REGION, &ab->dev_flags);
+
+	ret = ath12k_core_pre_init(ab);
+	if (ret)
+		goto err_core_free;
+
+	ret = ath12k_ahb_resource_init(ab);
+	if (ret)
+		goto err_core_free;
+
+	ret = ath12k_hal_srng_init(ab);
+	if (ret)
+		goto err_resource_deinit;
+
+	ret = ath12k_ce_alloc_pipes(ab);
+	if (ret) {
+		ath12k_err(ab, "failed to allocate ce pipes: %d\n", ret);
+		goto err_hal_srng_deinit;
+	}
+
+	ath12k_ahb_init_qmi_ce_config(ab);
+
+	ret = ath12k_ahb_configure_rproc(ab);
+	if (ret)
+		goto err_ce_free;
+
+	ret = ath12k_ahb_config_irq(ab);
+	if (ret) {
+		ath12k_err(ab, "failed to configure irq: %d\n", ret);
+		goto err_rproc_deconfigure;
+	}
+
+	ret = ath12k_core_init(ab);
+	if (ret) {
+		ath12k_err(ab, "failed to init core: %d\n", ret);
+		goto err_rproc_deconfigure;
+	}
+
+	return 0;
+
+err_rproc_deconfigure:
+	ath12k_ahb_deconfigure_rproc(ab);
+
+err_ce_free:
+	ath12k_ce_free_pipes(ab);
+
+err_hal_srng_deinit:
+	ath12k_hal_srng_deinit(ab);
+
+err_resource_deinit:
+	ath12k_ahb_resource_deinit(ab);
+
+err_core_free:
+	ath12k_core_free(ab);
+	platform_set_drvdata(pdev, NULL);
+
+	return ret;
+}
+
+static void ath12k_ahb_remove_prepare(struct ath12k_base *ab)
+{
+	unsigned long left;
+
+	if (test_bit(ATH12K_FLAG_RECOVERY, &ab->dev_flags)) {
+		left = wait_for_completion_timeout(&ab->driver_recovery,
+						   ATH12K_AHB_RECOVERY_TIMEOUT);
+		if (!left)
+			ath12k_warn(ab, "failed to receive recovery response completion\n");
+	}
+
+	set_bit(ATH12K_FLAG_UNREGISTERING, &ab->dev_flags);
+	cancel_work_sync(&ab->restart_work);
+	cancel_work_sync(&ab->qmi.event_work);
+}
+
+static void ath12k_ahb_free_resources(struct ath12k_base *ab)
+{
+	struct platform_device *pdev = ab->pdev;
+
+	ath12k_hal_srng_deinit(ab);
+	ath12k_ce_free_pipes(ab);
+	ath12k_ahb_resource_deinit(ab);
+	ath12k_ahb_deconfigure_rproc(ab);
+	ath12k_core_free(ab);
+	platform_set_drvdata(pdev, NULL);
+}
+
+static void ath12k_ahb_remove(struct platform_device *pdev)
+{
+	struct ath12k_base *ab = platform_get_drvdata(pdev);
+
+	if (test_bit(ATH12K_FLAG_QMI_FAIL, &ab->dev_flags)) {
+		ath12k_ahb_power_down(ab, false);
+		goto qmi_fail;
+	}
+
+	ath12k_ahb_remove_prepare(ab);
+	ath12k_core_hw_group_cleanup(ab->ag);
+qmi_fail:
+	ath12k_core_deinit(ab);
+	ath12k_ahb_free_resources(ab);
+}
+
+static struct platform_driver ath12k_ahb_driver = {
+	.driver         = {
+		.name   = "ath12k_ahb",
+		.of_match_table = ath12k_ahb_of_match,
+	},
+	.probe  = ath12k_ahb_probe,
+	.remove = ath12k_ahb_remove,
+};
+
+int ath12k_ahb_init(void)
+{
+	return platform_driver_register(&ath12k_ahb_driver);
+}
+
+void ath12k_ahb_exit(void)
+{
+	platform_driver_unregister(&ath12k_ahb_driver);
+}
diff --git a/drivers/net/wireless/ath/ath12k/ahb.h b/drivers/net/wireless/ath/ath12k/ahb.h
new file mode 100644
index 000000000000..d56244b20a6a
--- /dev/null
+++ b/drivers/net/wireless/ath/ath12k/ahb.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: BSD-3-Clause-Clear */
+/*
+ * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022-2025, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+#ifndef ATH12K_AHB_H
+#define ATH12K_AHB_H
+
+#include <linux/clk.h>
+#include <linux/remoteproc/qcom_rproc.h>
+#include "core.h"
+
+#define ATH12K_AHB_RECOVERY_TIMEOUT (3 * HZ)
+
+#define ATH12K_AHB_SMP2P_SMEM_MSG		GENMASK(15, 0)
+#define ATH12K_AHB_SMP2P_SMEM_SEQ_NO		GENMASK(31, 16)
+#define ATH12K_AHB_SMP2P_SMEM_VALUE_MASK	0xFFFFFFFF
+#define ATH12K_PCI_CE_WAKE_IRQ			2
+#define ATH12K_PCI_IRQ_CE0_OFFSET		3
+#define ATH12K_ROOTPD_READY_TIMEOUT		(5 * HZ)
+#define ATH12K_RPROC_AFTER_POWERUP		QCOM_SSR_AFTER_POWERUP
+#define ATH12K_AHB_FW_PREFIX			"q6_fw"
+#define ATH12K_AHB_FW_SUFFIX			".mdt"
+#define ATH12K_AHB_FW2				"iu_fw.mdt"
+#define ATH12K_AHB_UPD_SWID			0x12
+#define ATH12K_USERPD_SPAWN_TIMEOUT		(5 * HZ)
+#define ATH12K_USERPD_READY_TIMEOUT		(10 * HZ)
+#define ATH12K_USERPD_STOP_TIMEOUT		(5 * HZ)
+#define ATH12K_USERPD_ID_MASK			GENMASK(9, 8)
+#define ATH12K_USERPD_FW_NAME_LEN		35
+
+enum ath12k_ahb_smp2p_msg_id {
+	ATH12K_AHB_POWER_SAVE_ENTER = 1,
+	ATH12K_AHB_POWER_SAVE_EXIT,
+};
+
+enum ath12k_ahb_userpd_irq {
+	ATH12K_USERPD_SPAWN_IRQ,
+	ATH12K_USERPD_READY_IRQ,
+	ATH12K_USERPD_STOP_ACK_IRQ,
+	ATH12K_USERPD_MAX_IRQ,
+};
+
+struct ath12k_base;
+
+struct ath12k_ahb {
+	struct ath12k_base *ab;
+	struct rproc *tgt_rproc;
+	struct clk *xo_clk;
+	struct completion rootpd_ready;
+	struct notifier_block root_pd_nb;
+	void *root_pd_notifier;
+	struct qcom_smem_state *spawn_state;
+	struct qcom_smem_state *stop_state;
+	struct completion userpd_spawned;
+	struct completion userpd_ready;
+	struct completion userpd_stopped;
+	u32 userpd_id;
+	u32 spawn_bit;
+	u32 stop_bit;
+	int userpd_irq_num[ATH12K_USERPD_MAX_IRQ];
+};
+
+static inline struct ath12k_ahb *ath12k_ab_to_ahb(struct ath12k_base *ab)
+{
+	return (struct ath12k_ahb *)ab->drv_priv;
+}
+
+#ifdef CONFIG_ATH12K_AHB
+int ath12k_ahb_init(void);
+void ath12k_ahb_exit(void);
+#else
+static inline int ath12k_ahb_init(void)
+{
+	return 0;
+}
+
+static inline void ath12k_ahb_exit(void) {};
+#endif
+#endif
diff --git a/drivers/net/wireless/ath/ath12k/ce.c b/drivers/net/wireless/ath/ath12k/ce.c
index be0d669d31fc..47821a3b060b 100644
--- a/drivers/net/wireless/ath/ath12k/ce.c
+++ b/drivers/net/wireless/ath/ath12k/ce.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "dp_rx.h"
@@ -219,6 +219,96 @@ const struct ce_attr ath12k_host_ce_config_wcn7850[] = {
 
 };
 
+const struct ce_attr ath12k_host_ce_config_ipq5332[] = {
+	/* CE0: host->target HTC control and raw streams */
+	{
+		.flags = CE_ATTR_FLAGS,
+		.src_nentries = 16,
+		.src_sz_max = 2048,
+		.dest_nentries = 0,
+	},
+	/* CE1: target->host HTT + HTC control */
+	{
+		.flags = CE_ATTR_FLAGS,
+		.src_nentries = 0,
+		.src_sz_max = 2048,
+		.dest_nentries = 512,
+		.recv_cb = ath12k_htc_rx_completion_handler,
+	},
+	/* CE2: target->host WMI */
+	{
+		.flags = CE_ATTR_FLAGS,
+		.src_nentries = 0,
+		.src_sz_max = 2048,
+		.dest_nentries = 128,
+		.recv_cb = ath12k_htc_rx_completion_handler,
+	},
+	/* CE3: host->target WMI */
+	{
+		.flags = CE_ATTR_FLAGS,
+		.src_nentries = 32,
+		.src_sz_max = 2048,
+		.dest_nentries = 0,
+	},
+	/* CE4: host->target HTT */
+	{
+		.flags = CE_ATTR_FLAGS | CE_ATTR_DIS_INTR,
+		.src_nentries = 2048,
+		.src_sz_max = 256,
+		.dest_nentries = 0,
+	},
+	/* CE5: target -> host PKTLOG */
+	{
+		.flags = CE_ATTR_FLAGS,
+		.src_nentries = 0,
+		.src_sz_max = 2048,
+		.dest_nentries = 512,
+		.recv_cb = ath12k_dp_htt_htc_t2h_msg_handler,
+	},
+	/* CE6: Target autonomous HIF_memcpy */
+	{
+		.flags = CE_ATTR_FLAGS | CE_ATTR_DIS_INTR,
+		.src_nentries = 0,
+		.src_sz_max = 0,
+		.dest_nentries = 0,
+	},
+	/* CE7: CV Prefetch */
+	{
+		.flags = CE_ATTR_FLAGS | CE_ATTR_DIS_INTR,
+		.src_nentries = 0,
+		.src_sz_max = 0,
+		.dest_nentries = 0,
+	},
+	/* CE8: Target HIF memcpy (Generic HIF memcypy) */
+	{
+		.flags = CE_ATTR_FLAGS | CE_ATTR_DIS_INTR,
+		.src_nentries = 0,
+		.src_sz_max = 0,
+		.dest_nentries = 0,
+	},
+	/* CE9: WMI logging/CFR/Spectral/Radar */
+	{
+		.flags = CE_ATTR_FLAGS,
+		.src_nentries = 0,
+		.src_sz_max = 2048,
+		.dest_nentries = 128,
+	},
+	/* CE10: Unused */
+	{
+		.flags = CE_ATTR_FLAGS | CE_ATTR_DIS_INTR,
+		.src_nentries = 0,
+		.src_sz_max = 0,
+		.dest_nentries = 0,
+	},
+	/* CE11: Unused */
+	{
+		.flags = CE_ATTR_FLAGS | CE_ATTR_DIS_INTR,
+		.src_nentries = 0,
+		.src_sz_max = 0,
+		.dest_nentries = 0,
+	},
+};
+
 static int ath12k_ce_rx_buf_enqueue_pipe(struct ath12k_ce_pipe *pipe,
 					 struct sk_buff *skb, dma_addr_t paddr)
 {
@@ -343,11 +433,10 @@ static int ath12k_ce_completed_recv_next(struct ath12k_ce_pipe *pipe,
 		goto err;
 	}
 
+	/* Make sure descriptor is read after the head pointer. */
+	dma_rmb();
+
 	*nbytes = ath12k_hal_ce_dst_status_get_length(desc);
-	if (*nbytes == 0) {
-		ret = -EIO;
-		goto err;
-	}
 
 	*skb = pipe->dest_ring->skb[sw_index];
 	pipe->dest_ring->skb[sw_index] = NULL;
@@ -380,8 +469,8 @@ static void ath12k_ce_recv_process_cb(struct ath12k_ce_pipe *pipe)
 		dma_unmap_single(ab->dev, ATH12K_SKB_RXCB(skb)->paddr,
 				 max_nbytes, DMA_FROM_DEVICE);
 
-		if (unlikely(max_nbytes < nbytes)) {
-			ath12k_warn(ab, "rxed more than expected (nbytes %d, max %d)",
+		if (unlikely(max_nbytes < nbytes || nbytes == 0)) {
+			ath12k_warn(ab, "unexpected rx length (nbytes %d, max %d)",
 				    nbytes, max_nbytes);
 			dev_kfree_skb_any(skb);
 			continue;
diff --git a/drivers/net/wireless/ath/ath12k/ce.h b/drivers/net/wireless/ath/ath12k/ce.h
index 1a14b9fb86b8..57f75899ee03 100644
--- a/drivers/net/wireless/ath/ath12k/ce.h
+++ b/drivers/net/wireless/ath/ath12k/ce.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_CE_H
@@ -39,8 +39,8 @@
 #define PIPEDIR_INOUT_H2H	4 /* bidirectional, host to host */
 
 /* CE address/mask */
-#define CE_HOST_IE_ADDRESS	0x00A1803C
-#define CE_HOST_IE_2_ADDRESS	0x00A18040
+#define CE_HOST_IE_ADDRESS	0x75804C
+#define CE_HOST_IE_2_ADDRESS	0x758050
 #define CE_HOST_IE_3_ADDRESS	CE_HOST_IE_ADDRESS
 
 #define CE_HOST_IE_3_SHIFT	0xC
@@ -76,6 +76,17 @@ struct ce_pipe_config {
 	__le32 reserved;
 };
 
+struct ce_ie_addr {
+	u32 ie1_reg_addr;
+	u32 ie2_reg_addr;
+	u32 ie3_reg_addr;
+};
+
+struct ce_remap {
+	u32 base;
+	u32 size;
+};
+
 struct ce_attr {
 	/* CE_ATTR_* values */
 	unsigned int flags;
@@ -164,6 +175,7 @@ struct ath12k_ce {
 
 extern const struct ce_attr ath12k_host_ce_config_qcn9274[];
 extern const struct ce_attr ath12k_host_ce_config_wcn7850[];
+extern const struct ce_attr ath12k_host_ce_config_ipq5332[];
 
 void ath12k_ce_cleanup_pipes(struct ath12k_base *ab);
 void ath12k_ce_rx_replenish_retry(struct timer_list *t);
diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 0b2dec081c6e..31d851d8e688 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -10,15 +10,18 @@
 #include <linux/firmware.h>
 #include <linux/of.h>
 #include <linux/of_graph.h>
+#include "ahb.h"
 #include "core.h"
 #include "dp_tx.h"
 #include "dp_rx.h"
 #include "debug.h"
-#include "hif.h"
-#include "fw.h"
 #include "debugfs.h"
+#include "fw.h"
+#include "hif.h"
+#include "pci.h"
 #include "wow.h"
 
+static int ahb_err, pci_err;
 unsigned int ath12k_debug_mask;
 module_param_named(debug_mask, ath12k_debug_mask, uint, 0644);
 MODULE_PARM_DESC(debug_mask, "Debugging mask");
@@ -612,9 +615,74 @@ u32 ath12k_core_get_max_num_tids(struct ath12k_base *ab)
 	return TARGET_NUM_TIDS(SINGLE);
 }
 
+struct reserved_mem *ath12k_core_get_reserved_mem(struct ath12k_base *ab,
+						  int index)
+{
+	struct device *dev = ab->dev;
+	struct reserved_mem *rmem;
+	struct device_node *node;
+
+	node = of_parse_phandle(dev->of_node, "memory-region", index);
+	if (!node) {
+		ath12k_dbg(ab, ATH12K_DBG_BOOT,
+			   "failed to parse memory-region for index %d\n", index);
+		return NULL;
+	}
+
+	rmem = of_reserved_mem_lookup(node);
+	of_node_put(node);
+	if (!rmem) {
+		ath12k_dbg(ab, ATH12K_DBG_BOOT,
+			   "unable to get memory-region for index %d\n", index);
+		return NULL;
+	}
+
+	return rmem;
+}
+
+static inline
+void ath12k_core_to_group_ref_get(struct ath12k_base *ab)
+{
+	struct ath12k_hw_group *ag = ab->ag;
+
+	lockdep_assert_held(&ag->mutex);
+
+	if (ab->hw_group_ref) {
+		ath12k_dbg(ab, ATH12K_DBG_BOOT, "core already attached to group %d\n",
+			   ag->id);
+		return;
+	}
+
+	ab->hw_group_ref = true;
+	ag->num_started++;
+
+	ath12k_dbg(ab, ATH12K_DBG_BOOT, "core attached to group %d, num_started %d\n",
+		   ag->id, ag->num_started);
+}
+
+static inline
+void ath12k_core_to_group_ref_put(struct ath12k_base *ab)
+{
+	struct ath12k_hw_group *ag = ab->ag;
+
+	lockdep_assert_held(&ag->mutex);
+
+	if (!ab->hw_group_ref) {
+		ath12k_dbg(ab, ATH12K_DBG_BOOT, "core already de-attached from group %d\n",
+			   ag->id);
+		return;
+	}
+
+	ab->hw_group_ref = false;
+	ag->num_started--;
+
+	ath12k_dbg(ab, ATH12K_DBG_BOOT, "core de-attached from group %d, num_started %d\n",
+		   ag->id, ag->num_started);
+}
+
 static void ath12k_core_stop(struct ath12k_base *ab)
 {
-	ath12k_core_stopped(ab);
+	ath12k_core_to_group_ref_put(ab);
 
 	if (!test_bit(ATH12K_FLAG_CRASH_FLUSH, &ab->dev_flags))
 		ath12k_qmi_firmware_stop(ab);
@@ -629,7 +697,7 @@ static void ath12k_core_stop(struct ath12k_base *ab)
 	/* De-Init of components as needed */
 }
 
-static void ath12k_core_check_bdfext(const struct dmi_header *hdr, void *data)
+static void ath12k_core_check_cc_code_bdfext(const struct dmi_header *hdr, void *data)
 {
 	struct ath12k_base *ab = data;
 	const char *magic = ATH12K_SMBIOS_BDF_EXT_MAGIC;
@@ -651,6 +719,28 @@ static void ath12k_core_check_bdfext(const struct dmi_header *hdr, void *data)
 		return;
 	}
 
+	spin_lock_bh(&ab->base_lock);
+
+	switch (smbios->country_code_flag) {
+	case ATH12K_SMBIOS_CC_ISO:
+		ab->new_alpha2[0] = u16_get_bits(smbios->cc_code >> 8, 0xff);
+		ab->new_alpha2[1] = u16_get_bits(smbios->cc_code, 0xff);
+		ath12k_dbg(ab, ATH12K_DBG_BOOT, "boot smbios cc_code %c%c\n",
+			   ab->new_alpha2[0], ab->new_alpha2[1]);
+		break;
+	case ATH12K_SMBIOS_CC_WW:
+		ab->new_alpha2[0] = '0';
+		ab->new_alpha2[1] = '0';
+		ath12k_dbg(ab, ATH12K_DBG_BOOT, "boot smbios worldwide regdomain\n");
+		break;
+	default:
+		ath12k_dbg(ab, ATH12K_DBG_BOOT, "boot ignore smbios country code setting %d\n",
+			   smbios->country_code_flag);
+		break;
+	}
+
+	spin_unlock_bh(&ab->base_lock);
+
 	if (!smbios->bdf_enabled) {
 		ath12k_dbg(ab, ATH12K_DBG_BOOT, "bdf variant name not found.\n");
 		return;
@@ -690,7 +780,7 @@ static void ath12k_core_check_bdfext(const struct dmi_header *hdr, void *data)
 int ath12k_core_check_smbios(struct ath12k_base *ab)
 {
 	ab->qmi.target.bdf_ext[0] = '\0';
-	dmi_walk(ath12k_core_check_bdfext, ab);
+	dmi_walk(ath12k_core_check_cc_code_bdfext, ab);
 
 	if (ab->qmi.target.bdf_ext[0] == '\0')
 		return -ENODATA;
@@ -721,6 +811,8 @@ static int ath12k_core_soc_create(struct ath12k_base *ab)
 		goto err_qmi_deinit;
 	}
 
+	ath12k_debugfs_pdev_create(ab);
+
 	return 0;
 
 err_qmi_deinit:
@@ -851,9 +943,8 @@ static int ath12k_core_start(struct ath12k_base *ab)
 
 	ath12k_acpi_set_dsm_func(ab);
 
-	if (!test_bit(ATH12K_FLAG_RECOVERY, &ab->dev_flags))
-		/* Indicate the core start in the appropriate group */
-		ath12k_core_started(ab);
+	/* Indicate the core start in the appropriate group */
+	ath12k_core_to_group_ref_get(ab);
 
 	return 0;
 
@@ -891,6 +982,9 @@ static void ath12k_core_hw_group_stop(struct ath12k_hw_group *ag)
 		ab = ag->ab[i];
 		if (!ab)
 			continue;
+
+		clear_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags);
+
 		ath12k_core_device_cleanup(ab);
 	}
 
@@ -1026,6 +1120,8 @@ core_pdev_create:
 
 		mutex_lock(&ab->core_lock);
 
+		set_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags);
+
 		ret = ath12k_core_pdev_create(ab);
 		if (ret) {
 			ath12k_err(ab, "failed to create pdev core %d\n", ret);
@@ -1084,6 +1180,59 @@ bool ath12k_core_hw_group_start_ready(struct ath12k_hw_group *ag)
 	return (ag->num_started == ag->num_devices);
 }
 
+static void ath12k_fw_stats_pdevs_free(struct list_head *head)
+{
+	struct ath12k_fw_stats_pdev *i, *tmp;
+
+	list_for_each_entry_safe(i, tmp, head, list) {
+		list_del(&i->list);
+		kfree(i);
+	}
+}
+
+void ath12k_fw_stats_bcn_free(struct list_head *head)
+{
+	struct ath12k_fw_stats_bcn *i, *tmp;
+
+	list_for_each_entry_safe(i, tmp, head, list) {
+		list_del(&i->list);
+		kfree(i);
+	}
+}
+
+static void ath12k_fw_stats_vdevs_free(struct list_head *head)
+{
+	struct ath12k_fw_stats_vdev *i, *tmp;
+
+	list_for_each_entry_safe(i, tmp, head, list) {
+		list_del(&i->list);
+		kfree(i);
+	}
+}
+
+void ath12k_fw_stats_init(struct ath12k *ar)
+{
+	INIT_LIST_HEAD(&ar->fw_stats.vdevs);
+	INIT_LIST_HEAD(&ar->fw_stats.pdevs);
+	INIT_LIST_HEAD(&ar->fw_stats.bcn);
+	init_completion(&ar->fw_stats_complete);
+}
+
+void ath12k_fw_stats_free(struct ath12k_fw_stats *stats)
+{
+	ath12k_fw_stats_pdevs_free(&stats->pdevs);
+	ath12k_fw_stats_vdevs_free(&stats->vdevs);
+	ath12k_fw_stats_bcn_free(&stats->bcn);
+}
+
+void ath12k_fw_stats_reset(struct ath12k *ar)
+{
+	spin_lock_bh(&ar->data_lock);
+	ar->fw_stats.fw_stats_done = false;
+	ath12k_fw_stats_free(&ar->fw_stats);
+	spin_unlock_bh(&ar->data_lock);
+}
+
 static void ath12k_core_trigger_partner(struct ath12k_base *ab)
 {
 	struct ath12k_hw_group *ag = ab->ag;
@@ -1246,6 +1395,7 @@ static void ath12k_rfkill_work(struct work_struct *work)
 
 void ath12k_core_halt(struct ath12k *ar)
 {
+	struct list_head *pos, *n;
 	struct ath12k_base *ab = ar->ab;
 
 	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
@@ -1258,10 +1408,16 @@ void ath12k_core_halt(struct ath12k *ar)
 	cancel_delayed_work_sync(&ar->scan.timeout);
 	cancel_work_sync(&ar->regd_update_work);
 	cancel_work_sync(&ab->rfkill_work);
+	cancel_work_sync(&ab->update_11d_work);
 
 	rcu_assign_pointer(ab->pdevs_active[ar->pdev_idx], NULL);
 	synchronize_rcu();
-	INIT_LIST_HEAD(&ar->arvifs);
+
+	spin_lock_bh(&ar->data_lock);
+	list_for_each_safe(pos, n, &ar->arvifs)
+		list_del_init(pos);
+	spin_unlock_bh(&ar->data_lock);
+
 	idr_init(&ar->txmgmt_idr);
 }
 
@@ -1285,14 +1441,28 @@ static void ath12k_core_pre_reconfigure_recovery(struct ath12k_base *ab)
 		    ah->state == ATH12K_HW_STATE_TM)
 			continue;
 
+		wiphy_lock(ah->hw->wiphy);
+
+		/* If queue 0 is stopped, it is safe to assume that all
+		 * other queues are stopped by driver via
+		 * ieee80211_stop_queues() below. This means, there is
+		 * no need to stop it again and hence continue
+		 */
+		if (ieee80211_queue_stopped(ah->hw, 0)) {
+			wiphy_unlock(ah->hw->wiphy);
+			continue;
+		}
+
 		ieee80211_stop_queues(ah->hw);
 
 		for (j = 0; j < ah->num_radio; j++) {
 			ar = &ah->radio[j];
 
 			ath12k_mac_drain_tx(ar);
+			ar->state_11d = ATH12K_11D_IDLE;
+			complete(&ar->completed_11d_scan);
 			complete(&ar->scan.started);
-			complete(&ar->scan.completed);
+			complete_all(&ar->scan.completed);
 			complete(&ar->scan.on_channel);
 			complete(&ar->peer_assoc_done);
 			complete(&ar->peer_delete_done);
@@ -1306,13 +1476,47 @@ static void ath12k_core_pre_reconfigure_recovery(struct ath12k_base *ab)
 				     ath12k_mac_tx_mgmt_pending_free, ar);
 			idr_destroy(&ar->txmgmt_idr);
 			wake_up(&ar->txmgmt_empty_waitq);
+
+			ar->monitor_vdev_id = -1;
+			ar->monitor_vdev_created = false;
+			ar->monitor_started = false;
 		}
+
+		wiphy_unlock(ah->hw->wiphy);
 	}
 
 	wake_up(&ab->wmi_ab.tx_credits_wq);
 	wake_up(&ab->peer_mapping_wq);
 }
 
+static void ath12k_update_11d(struct work_struct *work)
+{
+	struct ath12k_base *ab = container_of(work, struct ath12k_base, update_11d_work);
+	struct ath12k *ar;
+	struct ath12k_pdev *pdev;
+	struct wmi_set_current_country_arg arg = {};
+	int ret, i;
+
+	spin_lock_bh(&ab->base_lock);
+	memcpy(&arg.alpha2, &ab->new_alpha2, 2);
+	spin_unlock_bh(&ab->base_lock);
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI, "update 11d new cc %c%c\n",
+		   arg.alpha2[0], arg.alpha2[1]);
+
+	for (i = 0; i < ab->num_radios; i++) {
+		pdev = &ab->pdevs[i];
+		ar = pdev->ar;
+
+		memcpy(&ar->alpha2, &arg.alpha2, 2);
+		ret = ath12k_wmi_send_set_current_country_cmd(ar, &arg);
+		if (ret)
+			ath12k_warn(ar->ab,
+				    "pdev id %d failed set current country code: %d\n",
+				    i, ret);
+	}
+}
+
 static void ath12k_core_post_reconfigure_recovery(struct ath12k_base *ab)
 {
 	struct ath12k_hw_group *ag = ab->ag;
@@ -1386,19 +1590,30 @@ static void ath12k_core_restart(struct work_struct *work)
 			ath12k_dbg(ab, ATH12K_DBG_BOOT, "reset success\n");
 		}
 
+		mutex_lock(&ag->mutex);
+
+		if (!ath12k_core_hw_group_start_ready(ag)) {
+			mutex_unlock(&ag->mutex);
+			goto exit_restart;
+		}
+
 		for (i = 0; i < ag->num_hw; i++) {
-			ah = ath12k_ag_to_ah(ab->ag, i);
+			ah = ath12k_ag_to_ah(ag, i);
 			ieee80211_restart_hw(ah->hw);
 		}
+
+		mutex_unlock(&ag->mutex);
 	}
 
+exit_restart:
 	complete(&ab->restart_completed);
 }
 
 static void ath12k_core_reset(struct work_struct *work)
 {
 	struct ath12k_base *ab = container_of(work, struct ath12k_base, reset_work);
-	int reset_count, fail_cont_count;
+	struct ath12k_hw_group *ag = ab->ag;
+	int reset_count, fail_cont_count, i;
 	long time_left;
 
 	if (!(test_bit(ATH12K_FLAG_QMI_FW_READY_COMPLETE, &ab->dev_flags))) {
@@ -1457,9 +1672,34 @@ static void ath12k_core_reset(struct work_struct *work)
 	ath12k_hif_ce_irq_disable(ab);
 
 	ath12k_hif_power_down(ab, false);
-	ath12k_hif_power_up(ab);
 
-	ath12k_dbg(ab, ATH12K_DBG_BOOT, "reset started\n");
+	/* prepare for power up */
+	ab->qmi.num_radios = U8_MAX;
+
+	mutex_lock(&ag->mutex);
+	ath12k_core_to_group_ref_put(ab);
+
+	if (ag->num_started > 0) {
+		ath12k_dbg(ab, ATH12K_DBG_BOOT,
+			   "waiting for %d partner device(s) to reset\n",
+			   ag->num_started);
+		mutex_unlock(&ag->mutex);
+		return;
+	}
+
+	/* Prepare MLO global memory region for power up */
+	ath12k_qmi_reset_mlo_mem(ag);
+
+	for (i = 0; i < ag->num_devices; i++) {
+		ab = ag->ab[i];
+		if (!ab)
+			continue;
+
+		ath12k_hif_power_up(ab);
+		ath12k_dbg(ab, ATH12K_DBG_BOOT, "reset started\n");
+	}
+
+	mutex_unlock(&ag->mutex);
 }
 
 int ath12k_core_pre_init(struct ath12k_base *ab)
@@ -1596,9 +1836,9 @@ static int ath12k_core_get_wsi_info(struct ath12k_hw_group *ag,
 		of_node_put(next_rx_endpoint);
 
 		device_count++;
-		if (device_count > ATH12K_MAX_SOCS) {
+		if (device_count > ATH12K_MAX_DEVICES) {
 			ath12k_warn(ab, "device count in DT %d is more than limit %d\n",
-				    device_count, ATH12K_MAX_SOCS);
+				    device_count, ATH12K_MAX_DEVICES);
 			of_node_put(next_wsi_dev);
 			return -EINVAL;
 		}
@@ -1774,7 +2014,7 @@ static void ath12k_core_hw_group_destroy(struct ath12k_hw_group *ag)
 	}
 }
 
-static void ath12k_core_hw_group_cleanup(struct ath12k_hw_group *ag)
+void ath12k_core_hw_group_cleanup(struct ath12k_hw_group *ag)
 {
 	struct ath12k_base *ab;
 	int i;
@@ -1843,20 +2083,18 @@ void ath12k_core_hw_group_set_mlo_capable(struct ath12k_hw_group *ag)
 
 	lockdep_assert_held(&ag->mutex);
 
-	/* If more than one devices are grouped, then inter MLO
-	 * functionality can work still independent of whether internally
-	 * each device supports single_chip_mlo or not.
-	 * Only when there is one device, then disable for WCN chipsets
-	 * till the required driver implementation is in place.
-	 */
 	if (ag->num_devices == 1) {
 		ab = ag->ab[0];
-
-		/* WCN chipsets does not advertise in firmware features
-		 * hence skip checking
-		 */
-		if (ab->hw_params->def_num_link)
+		/* QCN9274 firmware uses firmware IE for MLO advertisement */
+		if (ab->fw.fw_features_valid) {
+			ag->mlo_capable =
+				ath12k_fw_feature_supported(ab, ATH12K_FW_FEATURE_MLO);
 			return;
+		}
+
+		/* while WCN7850 firmware uses QMI single_chip_mlo_support bit */
+		ag->mlo_capable = ab->single_chip_mlo_support;
+		return;
 	}
 
 	ag->mlo_capable = true;
@@ -1869,7 +2107,7 @@ void ath12k_core_hw_group_set_mlo_capable(struct ath12k_hw_group *ag)
 		/* even if 1 device's firmware feature indicates MLO
 		 * unsupported, make MLO unsupported for the whole group
 		 */
-		if (!test_bit(ATH12K_FW_FEATURE_MLO, ab->fw.fw_features)) {
+		if (!ath12k_fw_feature_supported(ab, ATH12K_FW_FEATURE_MLO)) {
 			ag->mlo_capable = false;
 			return;
 		}
@@ -1922,10 +2160,9 @@ err:
 
 void ath12k_core_deinit(struct ath12k_base *ab)
 {
-	ath12k_core_panic_notifier_unregister(ab);
-	ath12k_core_hw_group_cleanup(ab->ag);
 	ath12k_core_hw_group_destroy(ab->ag);
 	ath12k_core_hw_group_unassign(ab);
+	ath12k_core_panic_notifier_unregister(ab);
 }
 
 void ath12k_core_free(struct ath12k_base *ab)
@@ -1966,6 +2203,7 @@ struct ath12k_base *ath12k_core_alloc(struct device *dev, size_t priv_size,
 	INIT_WORK(&ab->reset_work, ath12k_core_reset);
 	INIT_WORK(&ab->rfkill_work, ath12k_rfkill_work);
 	INIT_WORK(&ab->dump_work, ath12k_coredump_upload);
+	INIT_WORK(&ab->update_11d_work, ath12k_update_11d);
 
 	timer_setup(&ab->rx_replenish_retry, ath12k_ce_rx_replenish_retry, 0);
 	init_completion(&ab->htc_suspend);
@@ -1975,6 +2213,7 @@ struct ath12k_base *ath12k_core_alloc(struct device *dev, size_t priv_size,
 	ab->dev = dev;
 	ab->hif.bus = bus;
 	ab->qmi.num_radios = U8_MAX;
+	ab->single_chip_mlo_support = false;
 
 	/* Device index used to identify the devices in a group.
 	 *
@@ -1995,5 +2234,31 @@ err_sc_free:
 	return NULL;
 }
 
-MODULE_DESCRIPTION("Core module for Qualcomm Atheros 802.11be wireless LAN cards.");
+static int ath12k_init(void)
+{
+	ahb_err = ath12k_ahb_init();
+	if (ahb_err)
+		pr_warn("Failed to initialize ath12k AHB device: %d\n", ahb_err);
+
+	pci_err = ath12k_pci_init();
+	if (pci_err)
+		pr_warn("Failed to initialize ath12k PCI device: %d\n", pci_err);
+
+	/* If both failed, return one of the failures (arbitrary) */
+	return ahb_err && pci_err ? ahb_err : 0;
+}
+
+static void ath12k_exit(void)
+{
+	if (!pci_err)
+		ath12k_pci_exit();
+
+	if (!ahb_err)
+		ath12k_ahb_exit();
+}
+
+module_init(ath12k_init);
+module_exit(ath12k_exit);
+
+MODULE_DESCRIPTION("Driver support for Qualcomm Technologies 802.11be WLAN devices");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 3fac4f00d383..941db6e49d6e 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -14,8 +14,10 @@
 #include <linux/dmi.h>
 #include <linux/ctype.h>
 #include <linux/firmware.h>
+#include <linux/of_reserved_mem.h>
 #include <linux/panic_notifier.h>
 #include <linux/average.h>
+#include <linux/of.h>
 #include "qmi.h"
 #include "htc.h"
 #include "wmi.h"
@@ -62,8 +64,8 @@
 #define ATH12K_RECONFIGURE_TIMEOUT_HZ		(10 * HZ)
 #define ATH12K_RECOVER_START_TIMEOUT_HZ		(20 * HZ)
 
-#define ATH12K_MAX_SOCS 3
-#define ATH12K_GROUP_MAX_RADIO (ATH12K_MAX_SOCS * MAX_RADIOS)
+#define ATH12K_MAX_DEVICES 3
+#define ATH12K_GROUP_MAX_RADIO (ATH12K_MAX_DEVICES * MAX_RADIOS)
 #define ATH12K_INVALID_GROUP_ID  0xFF
 #define ATH12K_INVALID_DEVICE_ID 0xFF
 
@@ -147,7 +149,8 @@ struct ath12k_skb_rxcb {
 enum ath12k_hw_rev {
 	ATH12K_HW_QCN9274_HW10,
 	ATH12K_HW_QCN9274_HW20,
-	ATH12K_HW_WCN7850_HW20
+	ATH12K_HW_WCN7850_HW20,
+	ATH12K_HW_IPQ5332_HW10,
 };
 
 enum ath12k_firmware_mode {
@@ -160,6 +163,7 @@ enum ath12k_firmware_mode {
 
 #define ATH12K_IRQ_NUM_MAX 57
 #define ATH12K_EXT_IRQ_NUM_MAX	16
+#define ATH12K_MAX_TCL_RING_NUM	3
 
 struct ath12k_ext_irq_grp {
 	struct ath12k_base *ab;
@@ -172,9 +176,34 @@ struct ath12k_ext_irq_grp {
 	struct net_device *napi_ndev;
 };
 
+enum ath12k_smbios_cc_type {
+	/* disable country code setting from SMBIOS */
+	ATH12K_SMBIOS_CC_DISABLE = 0,
+
+	/* set country code by ANSI country name, based on ISO3166-1 alpha2 */
+	ATH12K_SMBIOS_CC_ISO = 1,
+
+	/* worldwide regdomain */
+	ATH12K_SMBIOS_CC_WW = 2,
+};
+
 struct ath12k_smbios_bdf {
 	struct dmi_header hdr;
-	u32 padding;
+	u8 features_disabled;
+
+	/* enum ath12k_smbios_cc_type */
+	u8 country_code_flag;
+
+	/* To set specific country, you need to set country code
+	 * flag=ATH12K_SMBIOS_CC_ISO first, then if country is United
+	 * States, then country code value = 0x5553 ("US",'U' = 0x55, 'S'=
+	 * 0x53). To set country to INDONESIA, then country code value =
+	 * 0x4944 ("IN", 'I'=0x49, 'D'=0x44). If country code flag =
+	 * ATH12K_SMBIOS_CC_WW, then you can use worldwide regulatory
+	 * setting.
+	 */
+	u16 cc_code;
+
 	u8 bdf_enabled;
 	u8 bdf_ext[];
 } __packed;
@@ -219,6 +248,12 @@ enum ath12k_scan_state {
 	ATH12K_SCAN_ABORTING,
 };
 
+enum ath12k_11d_state {
+	ATH12K_11D_IDLE,
+	ATH12K_11D_PREPARING,
+	ATH12K_11D_RUNNING,
+};
+
 enum ath12k_hw_group_flags {
 	ATH12K_GROUP_FLAG_REGISTERED,
 	ATH12K_GROUP_FLAG_UNREGISTER,
@@ -238,6 +273,7 @@ enum ath12k_dev_flags {
 	ATH12K_FLAG_EXT_IRQ_ENABLED,
 	ATH12K_FLAG_QMI_FW_READY_COMPLETE,
 	ATH12K_FLAG_FTM_SEGMENTED,
+	ATH12K_FLAG_FIXED_MEM_REGION,
 };
 
 struct ath12k_tx_conf {
@@ -295,14 +331,20 @@ struct ath12k_link_vif {
 	int txpower;
 	bool rsnie_present;
 	bool wpaie_present;
-	struct ieee80211_chanctx_conf chanctx;
 	u8 vdev_stats_id;
 	u32 punct_bitmap;
 	u8 link_id;
 	struct ath12k_vif *ahvif;
 	struct ath12k_rekey_data rekey_data;
+	struct ath12k_link_stats link_stats;
+	spinlock_t link_stats_lock; /* Protects updates to link_stats */
 
 	u8 current_cntdown_counter;
+
+	/* only used in station mode */
+	bool is_sta_assoc_link;
+
+	struct ath12k_reg_tpc_power_info reg_tpc_info;
 };
 
 struct ath12k_vif {
@@ -364,6 +406,8 @@ struct ath12k_vif_iter {
 #define HAL_RX_MAX_NSS		8
 #define HAL_RX_MAX_NUM_LEGACY_RATES 12
 
+#define ATH12K_SCAN_TIMEOUT_HZ (20 * HZ)
+
 struct ath12k_rx_peer_rate_stats {
 	u64 ht_mcs_count[HAL_RX_MAX_MCS_HT + 1];
 	u64 vht_mcs_count[HAL_RX_MAX_MCS_VHT + 1];
@@ -519,6 +563,12 @@ struct ath12k_link_sta {
 	u8 link_idx;
 };
 
+struct ath12k_reoq_buf {
+	void *vaddr;
+	dma_addr_t paddr_aligned;
+	u32 size;
+};
+
 struct ath12k_sta {
 	struct ath12k_vif *ahvif;
 	enum hal_pn_type pn_type;
@@ -531,13 +581,25 @@ struct ath12k_sta {
 	u8 num_peer;
 
 	enum ieee80211_sta_state state;
+
+	struct ath12k_reoq_buf reoq_bufs[IEEE80211_NUM_TIDS + 1];
 };
 
-#define ATH12K_MIN_5G_FREQ 4150
-#define ATH12K_MIN_6G_FREQ 5925
-#define ATH12K_MAX_6G_FREQ 7115
+#define ATH12K_HALF_20MHZ_BW	10
+#define ATH12K_2GHZ_MIN_CENTER	2412
+#define ATH12K_2GHZ_MAX_CENTER	2484
+#define ATH12K_5GHZ_MIN_CENTER	4900
+#define ATH12K_5GHZ_MAX_CENTER	5920
+#define ATH12K_6GHZ_MIN_CENTER	5935
+#define ATH12K_6GHZ_MAX_CENTER	7115
+#define ATH12K_MIN_2GHZ_FREQ	(ATH12K_2GHZ_MIN_CENTER - ATH12K_HALF_20MHZ_BW - 1)
+#define ATH12K_MAX_2GHZ_FREQ	(ATH12K_2GHZ_MAX_CENTER + ATH12K_HALF_20MHZ_BW + 1)
+#define ATH12K_MIN_5GHZ_FREQ	(ATH12K_5GHZ_MIN_CENTER - ATH12K_HALF_20MHZ_BW)
+#define ATH12K_MAX_5GHZ_FREQ	(ATH12K_5GHZ_MAX_CENTER + ATH12K_HALF_20MHZ_BW)
+#define ATH12K_MIN_6GHZ_FREQ	(ATH12K_6GHZ_MIN_CENTER - ATH12K_HALF_20MHZ_BW)
+#define ATH12K_MAX_6GHZ_FREQ	(ATH12K_6GHZ_MAX_CENTER + ATH12K_HALF_20MHZ_BW)
 #define ATH12K_NUM_CHANS 101
-#define ATH12K_MAX_5G_CHAN 173
+#define ATH12K_MAX_5GHZ_CHAN 173
 
 enum ath12k_hw_state {
 	ATH12K_HW_STATE_OFF,
@@ -728,7 +790,6 @@ struct ath12k {
 #endif
 
 	bool dfs_block_radar_events;
-	bool monitor_conf_enabled;
 	bool monitor_vdev_created;
 	bool monitor_started;
 	int monitor_vdev_id;
@@ -737,12 +798,22 @@ struct ath12k {
 
 	bool nlo_enabled;
 
+	/* Protected by wiphy::mtx lock. */
+	u32 vdev_id_11d_scan;
+	struct completion completed_11d_scan;
+	enum ath12k_11d_state state_11d;
+	u8 alpha2[REG_ALPHA2_LEN];
+	bool regdom_set_by_user;
+
 	struct completion fw_stats_complete;
 
 	struct completion mlo_setup_done;
 	u32 mlo_setup_status;
 	u8 ftm_msgref;
 	struct ath12k_fw_stats fw_stats;
+	unsigned long last_tx_power_update;
+
+	s8 max_allowed_tx_power;
 };
 
 struct ath12k_hw {
@@ -834,7 +905,7 @@ struct ath12k_board_data {
 	size_t len;
 };
 
-struct ath12k_soc_dp_tx_err_stats {
+struct ath12k_device_dp_tx_err_stats {
 	/* TCL Ring Descriptor unavailable */
 	u32 desc_na[DP_TCL_NUM_RING_MAX];
 	/* Other failures during dp_tx due to mem allocation failure
@@ -843,13 +914,25 @@ struct ath12k_soc_dp_tx_err_stats {
 	atomic_t misc_fail;
 };
 
-struct ath12k_soc_dp_stats {
+struct ath12k_device_dp_stats {
 	u32 err_ring_pkts;
 	u32 invalid_rbm;
 	u32 rxdma_error[HAL_REO_ENTR_RING_RXDMA_ECODE_MAX];
 	u32 reo_error[HAL_REO_DEST_RING_ERROR_CODE_MAX];
 	u32 hal_reo_error[DP_REO_DST_RING_MAX];
-	struct ath12k_soc_dp_tx_err_stats tx_err;
+	struct ath12k_device_dp_tx_err_stats tx_err;
+	u32 reo_rx[DP_REO_DST_RING_MAX][ATH12K_MAX_DEVICES];
+	u32 rx_wbm_rel_source[HAL_WBM_REL_SRC_MODULE_MAX][ATH12K_MAX_DEVICES];
+	u32 tqm_rel_reason[MAX_TQM_RELEASE_REASON];
+	u32 fw_tx_status[MAX_FW_TX_STATUS];
+	u32 tx_wbm_rel_source[HAL_WBM_REL_SRC_MODULE_MAX];
+	u32 tx_enqueued[DP_TCL_NUM_RING_MAX];
+	u32 tx_completed[DP_TCL_NUM_RING_MAX];
+};
+
+struct ath12k_reg_freq {
+	u32 start_freq;
+	u32 end_freq;
 };
 
 struct ath12k_mlo_memory {
@@ -873,7 +956,7 @@ struct ath12k_hw_group {
 	u8 num_probed;
 	u8 num_started;
 	unsigned long flags;
-	struct ath12k_base *ab[ATH12K_MAX_SOCS];
+	struct ath12k_base *ab[ATH12K_MAX_DEVICES];
 
 	/* protects access to this struct */
 	struct mutex mutex;
@@ -887,7 +970,7 @@ struct ath12k_hw_group {
 	struct ath12k_hw *ah[ATH12K_GROUP_MAX_RADIO];
 	u8 num_hw;
 	bool mlo_capable;
-	struct device_node *wsi_node[ATH12K_MAX_SOCS];
+	struct device_node *wsi_node[ATH12K_MAX_DEVICES];
 	struct ath12k_mlo_memory mlo_mem;
 	struct ath12k_hw_link hw_links[ATH12K_GROUP_MAX_RADIO];
 	bool hw_link_id_init_done;
@@ -923,6 +1006,10 @@ struct ath12k_base {
 	void __iomem *mem;
 	unsigned long mem_len;
 
+	void __iomem *mem_ce;
+	u32 ce_remap_base_addr;
+	bool ce_remap;
+
 	struct {
 		enum ath12k_bus bus;
 		const struct ath12k_hif_ops *ops;
@@ -991,9 +1078,11 @@ struct ath12k_base {
 	 */
 	struct ieee80211_regdomain *new_regd[MAX_RADIOS];
 
+	struct ath12k_reg_info *reg_info[MAX_RADIOS];
+
 	/* Current DFS Regulatory */
 	enum ath12k_dfs_region dfs_region;
-	struct ath12k_soc_dp_stats soc_stats;
+	struct ath12k_device_dp_stats device_stats;
 #ifdef CONFIG_ATH12K_DEBUGFS
 	struct dentry *debugfs_soc;
 #endif
@@ -1011,6 +1100,8 @@ struct ath12k_base {
 	/* continuous recovery fail count */
 	atomic_t fail_cont_count;
 	unsigned long reset_fail_timeout;
+	struct work_struct update_11d_work;
+	u8 new_alpha2[2];
 	struct {
 		/* protected by data_lock */
 		u32 fw_crash_counter;
@@ -1020,8 +1111,6 @@ struct ath12k_base {
 	struct ath12k_dbring_cap *db_caps;
 	u32 num_db_cap;
 
-	struct timer_list mon_reap_timer;
-
 	struct completion htc_suspend;
 
 	u64 fw_soc_drop_count;
@@ -1051,6 +1140,7 @@ struct ath12k_base {
 		size_t m3_len;
 
 		DECLARE_BITMAP(fw_features, ATH12K_FW_FEATURE_COUNT);
+		bool fw_features_valid;
 	} fw;
 
 	const struct hal_rx_ops *hal_rx_ops;
@@ -1087,6 +1177,14 @@ struct ath12k_base {
 	struct ath12k_wsi_info wsi_info;
 	enum ath12k_firmware_mode fw_mode;
 	struct ath12k_ftm_event_obj ftm_event_obj;
+	bool hw_group_ref;
+
+	/* Denote whether MLO is possible within the device */
+	bool single_chip_mlo_support;
+
+	struct ath12k_reg_freq reg_freq_2ghz;
+	struct ath12k_reg_freq reg_freq_5ghz;
+	struct ath12k_reg_freq reg_freq_6ghz;
 
 	/* must be last */
 	u8 drv_priv[] __aligned(sizeof(void *));
@@ -1185,6 +1283,7 @@ struct ath12k_fw_stats_pdev {
 };
 
 int ath12k_core_qmi_firmware_ready(struct ath12k_base *ab);
+void ath12k_core_hw_group_cleanup(struct ath12k_hw_group *ag);
 int ath12k_core_pre_init(struct ath12k_base *ab);
 int ath12k_core_init(struct ath12k_base *ath12k);
 void ath12k_core_deinit(struct ath12k_base *ath12k);
@@ -1215,6 +1314,12 @@ u32 ath12k_core_get_max_peers_per_radio(struct ath12k_base *ab);
 u32 ath12k_core_get_max_num_tids(struct ath12k_base *ab);
 
 void ath12k_core_hw_group_set_mlo_capable(struct ath12k_hw_group *ag);
+void ath12k_fw_stats_init(struct ath12k *ar);
+void ath12k_fw_stats_bcn_free(struct list_head *head);
+void ath12k_fw_stats_free(struct ath12k_fw_stats *stats);
+void ath12k_fw_stats_reset(struct ath12k *ar);
+struct reserved_mem *ath12k_core_get_reserved_mem(struct ath12k_base *ab,
+						  int index);
 
 static inline const char *ath12k_scan_state_str(enum ath12k_scan_state state)
 {
@@ -1275,8 +1380,16 @@ static inline void ath12k_core_create_firmware_path(struct ath12k_base *ab,
 						    const char *filename,
 						    void *buf, size_t buf_len)
 {
-	snprintf(buf, buf_len, "%s/%s/%s", ATH12K_FW_DIR,
-		 ab->hw_params->fw.dir, filename);
+	const char *fw_name = NULL;
+
+	of_property_read_string(ab->dev->of_node, "firmware-name", &fw_name);
+
+	if (fw_name && strncmp(filename, "board", 5))
+		snprintf(buf, buf_len, "%s/%s/%s/%s", ATH12K_FW_DIR,
+			 ab->hw_params->fw.dir, fw_name, filename);
+	else
+		snprintf(buf, buf_len, "%s/%s/%s", ATH12K_FW_DIR,
+			 ab->hw_params->fw.dir, filename);
 }
 
 static inline const char *ath12k_bus_str(enum ath12k_bus bus)
@@ -1284,6 +1397,8 @@ static inline const char *ath12k_bus_str(enum ath12k_bus bus)
 	switch (bus) {
 	case ATH12K_BUS_PCI:
 		return "pci";
+	case ATH12K_BUS_AHB:
+		return "ahb";
 	}
 
 	return "unknown";
@@ -1333,20 +1448,6 @@ static inline struct ath12k_hw_group *ath12k_ab_to_ag(struct ath12k_base *ab)
 	return ab->ag;
 }
 
-static inline void ath12k_core_started(struct ath12k_base *ab)
-{
-	lockdep_assert_held(&ab->ag->mutex);
-
-	ab->ag->num_started++;
-}
-
-static inline void ath12k_core_stopped(struct ath12k_base *ab)
-{
-	lockdep_assert_held(&ab->ag->mutex);
-
-	ab->ag->num_started--;
-}
-
 static inline struct ath12k_base *ath12k_ag_to_ab(struct ath12k_hw_group *ag,
 						  u8 device_id)
 {
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.c b/drivers/net/wireless/ath/ath12k/debugfs.c
index 57002215ddf1..dd624d73b8b2 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs.c
@@ -33,6 +33,76 @@ static const struct file_operations fops_simulate_radar = {
 	.open = simple_open
 };
 
+static ssize_t ath12k_read_simulate_fw_crash(struct file *file,
+					     char __user *user_buf,
+					     size_t count, loff_t *ppos)
+{
+	const char buf[] =
+		"To simulate firmware crash write one of the keywords to this file:\n"
+		"`assert` - send WMI_FORCE_FW_HANG_CMDID to firmware to cause assert.\n";
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf));
+}
+
+static ssize_t
+ath12k_write_simulate_fw_crash(struct file *file,
+			       const char __user *user_buf,
+			       size_t count, loff_t *ppos)
+{
+	struct ath12k_base *ab = file->private_data;
+	struct ath12k_pdev *pdev;
+	struct ath12k *ar = NULL;
+	char buf[32] = {0};
+	int i, ret;
+	ssize_t rc;
+
+	/* filter partial writes and invalid commands */
+	if (*ppos != 0 || count >= sizeof(buf) || count == 0)
+		return -EINVAL;
+
+	rc = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, user_buf, count);
+	if (rc < 0)
+		return rc;
+
+	/* drop the possible '\n' from the end */
+	if (buf[*ppos - 1] == '\n')
+		buf[*ppos - 1] = '\0';
+
+	for (i = 0; i < ab->num_radios; i++) {
+		pdev = &ab->pdevs[i];
+		ar = pdev->ar;
+		if (ar)
+			break;
+	}
+
+	if (!ar)
+		return -ENETDOWN;
+
+	if (!strcmp(buf, "assert")) {
+		ath12k_info(ab, "simulating firmware assert crash\n");
+		ret = ath12k_wmi_force_fw_hang_cmd(ar,
+						   ATH12K_WMI_FW_HANG_ASSERT_TYPE,
+						   ATH12K_WMI_FW_HANG_DELAY);
+	} else {
+		return -EINVAL;
+	}
+
+	if (ret) {
+		ath12k_warn(ab, "failed to simulate firmware crash: %d\n", ret);
+		return ret;
+	}
+
+	return count;
+}
+
+static const struct file_operations fops_simulate_fw_crash = {
+	.read = ath12k_read_simulate_fw_crash,
+	.write = ath12k_write_simulate_fw_crash,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
 static ssize_t ath12k_write_tpc_stats_type(struct file *file,
 					   const char __user *user_buf,
 					   size_t count, loff_t *ppos)
@@ -88,8 +158,8 @@ static int ath12k_get_tpc_ctl_mode_idx(struct wmi_tpc_stats_arg *tpc_stats,
 	u32 chan_freq = le32_to_cpu(tpc_stats->tpc_config.chan_freq);
 	u8 band;
 
-	band = ((chan_freq > ATH12K_MIN_6G_FREQ) ? NL80211_BAND_6GHZ :
-		((chan_freq > ATH12K_MIN_5G_FREQ) ? NL80211_BAND_5GHZ :
+	band = ((chan_freq > ATH12K_MIN_6GHZ_FREQ) ? NL80211_BAND_6GHZ :
+		((chan_freq > ATH12K_MIN_5GHZ_FREQ) ? NL80211_BAND_5GHZ :
 		NL80211_BAND_2GHZ));
 
 	if (band == NL80211_BAND_5GHZ || band == NL80211_BAND_6GHZ) {
@@ -833,137 +903,352 @@ static const struct file_operations fops_extd_rx_stats = {
 	.open = simple_open,
 };
 
-void ath12k_debugfs_soc_create(struct ath12k_base *ab)
+static int ath12k_open_link_stats(struct inode *inode, struct file *file)
 {
-	bool dput_needed;
-	char soc_name[64] = { 0 };
-	struct dentry *debugfs_ath12k;
+	struct ath12k_vif *ahvif = inode->i_private;
+	size_t len = 0, buf_len = (PAGE_SIZE * 2);
+	struct ath12k_link_stats linkstat;
+	struct ath12k_link_vif *arvif;
+	unsigned long links_map;
+	struct wiphy *wiphy;
+	int link_id, i;
+	char *buf;
 
-	debugfs_ath12k = debugfs_lookup("ath12k", NULL);
-	if (debugfs_ath12k) {
-		/* a dentry from lookup() needs dput() after we don't use it */
-		dput_needed = true;
-	} else {
-		debugfs_ath12k = debugfs_create_dir("ath12k", NULL);
-		if (IS_ERR_OR_NULL(debugfs_ath12k))
-			return;
-		dput_needed = false;
+	if (!ahvif)
+		return -EINVAL;
+
+	buf = kzalloc(buf_len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	wiphy = ahvif->ah->hw->wiphy;
+	wiphy_lock(wiphy);
+
+	links_map = ahvif->links_map;
+	for_each_set_bit(link_id, &links_map,
+			 IEEE80211_MLD_MAX_NUM_LINKS) {
+		arvif = rcu_dereference_protected(ahvif->link[link_id],
+						  lockdep_is_held(&wiphy->mtx));
+
+		spin_lock_bh(&arvif->link_stats_lock);
+		linkstat = arvif->link_stats;
+		spin_unlock_bh(&arvif->link_stats_lock);
+
+		len += scnprintf(buf + len, buf_len - len,
+				 "link[%d] Tx Unicast Frames Enqueued  = %d\n",
+				 link_id, linkstat.tx_enqueued);
+		len += scnprintf(buf + len, buf_len - len,
+				 "link[%d] Tx Broadcast Frames Enqueued = %d\n",
+				 link_id, linkstat.tx_bcast_mcast);
+		len += scnprintf(buf + len, buf_len - len,
+				 "link[%d] Tx Frames Completed = %d\n",
+				 link_id, linkstat.tx_completed);
+		len += scnprintf(buf + len, buf_len - len,
+				 "link[%d] Tx Frames Dropped = %d\n",
+				 link_id, linkstat.tx_dropped);
+
+		len += scnprintf(buf + len, buf_len - len,
+				 "link[%d] Tx Frame descriptor Encap Type = ",
+				 link_id);
+
+		len += scnprintf(buf + len, buf_len - len,
+					 " raw:%d",
+					 linkstat.tx_encap_type[0]);
+
+		len += scnprintf(buf + len, buf_len - len,
+					 " native_wifi:%d",
+					 linkstat.tx_encap_type[1]);
+
+		len += scnprintf(buf + len, buf_len - len,
+					 " ethernet:%d",
+					 linkstat.tx_encap_type[2]);
+
+		len += scnprintf(buf + len, buf_len - len,
+				 "\nlink[%d] Tx Frame descriptor Encrypt Type = ",
+				 link_id);
+
+		for (i = 0; i < HAL_ENCRYPT_TYPE_MAX; i++) {
+			len += scnprintf(buf + len, buf_len - len,
+					 " %d:%d", i,
+					 linkstat.tx_encrypt_type[i]);
+		}
+		len += scnprintf(buf + len, buf_len - len,
+				 "\nlink[%d] Tx Frame descriptor Type = buffer:%d extension:%d\n",
+				 link_id, linkstat.tx_desc_type[0],
+				 linkstat.tx_desc_type[1]);
+
+		len += scnprintf(buf + len, buf_len - len,
+				"------------------------------------------------------\n");
 	}
 
-	scnprintf(soc_name, sizeof(soc_name), "%s-%s", ath12k_bus_str(ab->hif.bus),
-		  dev_name(ab->dev));
+	wiphy_unlock(wiphy);
 
-	ab->debugfs_soc = debugfs_create_dir(soc_name, debugfs_ath12k);
+	file->private_data = buf;
 
-	if (dput_needed)
-		dput(debugfs_ath12k);
+	return 0;
 }
 
-void ath12k_debugfs_soc_destroy(struct ath12k_base *ab)
+static int ath12k_release_link_stats(struct inode *inode, struct file *file)
 {
-	debugfs_remove_recursive(ab->debugfs_soc);
-	ab->debugfs_soc = NULL;
-	/* We are not removing ath12k directory on purpose, even if it
-	 * would be empty. This simplifies the directory handling and it's
-	 * a minor cosmetic issue to leave an empty ath12k directory to
-	 * debugfs.
-	 */
+	kfree(file->private_data);
+	return 0;
 }
 
-static void ath12k_fw_stats_pdevs_free(struct list_head *head)
+static ssize_t ath12k_read_link_stats(struct file *file,
+				      char __user *user_buf,
+				      size_t count, loff_t *ppos)
 {
-	struct ath12k_fw_stats_pdev *i, *tmp;
+	const char *buf = file->private_data;
+	size_t len = strlen(buf);
 
-	list_for_each_entry_safe(i, tmp, head, list) {
-		list_del(&i->list);
-		kfree(i);
-	}
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
 }
 
-static void ath12k_fw_stats_bcn_free(struct list_head *head)
+static const struct file_operations ath12k_fops_link_stats = {
+	.open = ath12k_open_link_stats,
+	.release = ath12k_release_link_stats,
+	.read = ath12k_read_link_stats,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+void ath12k_debugfs_op_vif_add(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif)
 {
-	struct ath12k_fw_stats_bcn *i, *tmp;
+	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
 
-	list_for_each_entry_safe(i, tmp, head, list) {
-		list_del(&i->list);
-		kfree(i);
-	}
+	debugfs_create_file("link_stats", 0400, vif->debugfs_dir, ahvif,
+			    &ath12k_fops_link_stats);
 }
 
-static void ath12k_fw_stats_vdevs_free(struct list_head *head)
+static ssize_t ath12k_debugfs_dump_device_dp_stats(struct file *file,
+						   char __user *user_buf,
+						   size_t count, loff_t *ppos)
 {
-	struct ath12k_fw_stats_vdev *i, *tmp;
+	struct ath12k_base *ab = file->private_data;
+	struct ath12k_device_dp_stats *device_stats = &ab->device_stats;
+	int len = 0, i, j, ret;
+	struct ath12k *ar;
+	const int size = 4096;
+	static const char *rxdma_err[HAL_REO_ENTR_RING_RXDMA_ECODE_MAX] = {
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_OVERFLOW_ERR] = "Overflow",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_MPDU_LEN_ERR] = "MPDU len",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_FCS_ERR] = "FCS",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_DECRYPT_ERR] = "Decrypt",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_TKIP_MIC_ERR] = "TKIP MIC",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_UNECRYPTED_ERR] = "Unencrypt",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_MSDU_LEN_ERR] = "MSDU len",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_MSDU_LIMIT_ERR] = "MSDU limit",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_WIFI_PARSE_ERR] = "WiFi parse",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_AMSDU_PARSE_ERR] = "AMSDU parse",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_SA_TIMEOUT_ERR] = "SA timeout",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_DA_TIMEOUT_ERR] = "DA timeout",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_FLOW_TIMEOUT_ERR] = "Flow timeout",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_FLUSH_REQUEST_ERR] = "Flush req",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_AMSDU_FRAG_ERR] = "AMSDU frag",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_MULTICAST_ECHO_ERR] = "Multicast echo",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_AMSDU_MISMATCH_ERR] = "AMSDU mismatch",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_UNAUTH_WDS_ERR] = "Unauth WDS",
+		[HAL_REO_ENTR_RING_RXDMA_ECODE_GRPCAST_AMSDU_WDS_ERR] = "AMSDU or WDS"};
+
+	static const char *reo_err[HAL_REO_DEST_RING_ERROR_CODE_MAX] = {
+		[HAL_REO_DEST_RING_ERROR_CODE_DESC_ADDR_ZERO] = "Desc addr zero",
+		[HAL_REO_DEST_RING_ERROR_CODE_DESC_INVALID] = "Desc inval",
+		[HAL_REO_DEST_RING_ERROR_CODE_AMPDU_IN_NON_BA] =  "AMPDU in non BA",
+		[HAL_REO_DEST_RING_ERROR_CODE_NON_BA_DUPLICATE] = "Non BA dup",
+		[HAL_REO_DEST_RING_ERROR_CODE_BA_DUPLICATE] = "BA dup",
+		[HAL_REO_DEST_RING_ERROR_CODE_FRAME_2K_JUMP] = "Frame 2k jump",
+		[HAL_REO_DEST_RING_ERROR_CODE_BAR_2K_JUMP] = "BAR 2k jump",
+		[HAL_REO_DEST_RING_ERROR_CODE_FRAME_OOR] = "Frame OOR",
+		[HAL_REO_DEST_RING_ERROR_CODE_BAR_OOR] = "BAR OOR",
+		[HAL_REO_DEST_RING_ERROR_CODE_NO_BA_SESSION] = "No BA session",
+		[HAL_REO_DEST_RING_ERROR_CODE_FRAME_SN_EQUALS_SSN] = "Frame SN equal SSN",
+		[HAL_REO_DEST_RING_ERROR_CODE_PN_CHECK_FAILED] = "PN check fail",
+		[HAL_REO_DEST_RING_ERROR_CODE_2K_ERR_FLAG_SET] = "2k err",
+		[HAL_REO_DEST_RING_ERROR_CODE_PN_ERR_FLAG_SET] = "PN err",
+		[HAL_REO_DEST_RING_ERROR_CODE_DESC_BLOCKED] = "Desc blocked"};
+
+	static const char *wbm_rel_src[HAL_WBM_REL_SRC_MODULE_MAX] = {
+		[HAL_WBM_REL_SRC_MODULE_TQM] = "TQM",
+		[HAL_WBM_REL_SRC_MODULE_RXDMA] = "Rxdma",
+		[HAL_WBM_REL_SRC_MODULE_REO] = "Reo",
+		[HAL_WBM_REL_SRC_MODULE_FW] = "FW",
+		[HAL_WBM_REL_SRC_MODULE_SW] = "SW"};
+
+	char *buf __free(kfree) = kzalloc(size, GFP_KERNEL);
 
-	list_for_each_entry_safe(i, tmp, head, list) {
-		list_del(&i->list);
-		kfree(i);
-	}
-}
+	if (!buf)
+		return -ENOMEM;
 
-void ath12k_debugfs_fw_stats_reset(struct ath12k *ar)
-{
-	spin_lock_bh(&ar->data_lock);
-	ar->fw_stats.fw_stats_done = false;
-	ath12k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
-	ath12k_fw_stats_bcn_free(&ar->fw_stats.bcn);
-	ath12k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
-	spin_unlock_bh(&ar->data_lock);
-}
+	len += scnprintf(buf + len, size - len, "DEVICE RX STATS:\n\n");
+	len += scnprintf(buf + len, size - len, "err ring pkts: %u\n",
+			 device_stats->err_ring_pkts);
+	len += scnprintf(buf + len, size - len, "Invalid RBM: %u\n\n",
+			 device_stats->invalid_rbm);
+	len += scnprintf(buf + len, size - len, "RXDMA errors:\n");
 
-static int ath12k_debugfs_fw_stats_request(struct ath12k *ar,
-					   struct ath12k_fw_stats_req_params *param)
-{
-	struct ath12k_base *ab = ar->ab;
-	unsigned long timeout, time_left;
-	int ret;
+	for (i = 0; i < HAL_REO_ENTR_RING_RXDMA_ECODE_MAX; i++)
+		len += scnprintf(buf + len, size - len, "%s: %u\n",
+				 rxdma_err[i], device_stats->rxdma_error[i]);
 
-	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
+	len += scnprintf(buf + len, size - len, "\nREO errors:\n");
 
-	/* FW stats can get split when exceeding the stats data buffer limit.
-	 * In that case, since there is no end marking for the back-to-back
-	 * received 'update stats' event, we keep a 3 seconds timeout in case,
-	 * fw_stats_done is not marked yet
-	 */
-	timeout = jiffies + msecs_to_jiffies(3 * 1000);
+	for (i = 0; i < HAL_REO_DEST_RING_ERROR_CODE_MAX; i++)
+		len += scnprintf(buf + len, size - len, "%s: %u\n",
+				 reo_err[i], device_stats->reo_error[i]);
 
-	ath12k_debugfs_fw_stats_reset(ar);
+	len += scnprintf(buf + len, size - len, "\nHAL REO errors:\n");
 
-	reinit_completion(&ar->fw_stats_complete);
+	for (i = 0; i < DP_REO_DST_RING_MAX; i++)
+		len += scnprintf(buf + len, size - len,
+				 "ring%d: %u\n", i,
+				 device_stats->hal_reo_error[i]);
 
-	ret = ath12k_wmi_send_stats_request_cmd(ar, param->stats_id,
-						param->vdev_id, param->pdev_id);
+	len += scnprintf(buf + len, size - len, "\nDEVICE TX STATS:\n");
+	len += scnprintf(buf + len, size - len, "\nTCL Ring Full Failures:\n");
 
-	if (ret) {
-		ath12k_warn(ab, "could not request fw stats (%d)\n",
-			    ret);
-		return ret;
+	for (i = 0; i < DP_TCL_NUM_RING_MAX; i++)
+		len += scnprintf(buf + len, size - len, "ring%d: %u\n",
+				 i, device_stats->tx_err.desc_na[i]);
+
+	len += scnprintf(buf + len, size - len,
+			 "\nMisc Transmit Failures: %d\n",
+			 atomic_read(&device_stats->tx_err.misc_fail));
+
+	len += scnprintf(buf + len, size - len, "\ntx_wbm_rel_source:");
+
+	for (i = 0; i < HAL_WBM_REL_SRC_MODULE_MAX; i++)
+		len += scnprintf(buf + len, size - len, " %d:%u",
+				 i, device_stats->tx_wbm_rel_source[i]);
+
+	len += scnprintf(buf + len, size - len, "\n");
+
+	len += scnprintf(buf + len, size - len, "\ntqm_rel_reason:");
+
+	for (i = 0; i < MAX_TQM_RELEASE_REASON; i++)
+		len += scnprintf(buf + len, size - len, " %d:%u",
+				 i, device_stats->tqm_rel_reason[i]);
+
+	len += scnprintf(buf + len, size - len, "\n");
+
+	len += scnprintf(buf + len, size - len, "\nfw_tx_status:");
+
+	for (i = 0; i < MAX_FW_TX_STATUS; i++)
+		len += scnprintf(buf + len, size - len, " %d:%u",
+				 i, device_stats->fw_tx_status[i]);
+
+	len += scnprintf(buf + len, size - len, "\n");
+
+	len += scnprintf(buf + len, size - len, "\ntx_enqueued:");
+
+	for (i = 0; i < DP_TCL_NUM_RING_MAX; i++)
+		len += scnprintf(buf + len, size - len, " %d:%u", i,
+				 device_stats->tx_enqueued[i]);
+
+	len += scnprintf(buf + len, size - len, "\n");
+
+	len += scnprintf(buf + len, size - len, "\ntx_completed:");
+
+	for (i = 0; i < DP_TCL_NUM_RING_MAX; i++)
+		len += scnprintf(buf + len, size - len, " %d:%u",
+				 i, device_stats->tx_completed[i]);
+
+	len += scnprintf(buf + len, size - len, "\n");
+
+	for (i = 0; i < ab->num_radios; i++) {
+		ar = ath12k_mac_get_ar_by_pdev_id(ab, DP_SW2HW_MACID(i));
+		if (ar) {
+			len += scnprintf(buf + len, size - len,
+					"\nradio%d tx_pending: %u\n", i,
+					atomic_read(&ar->dp.num_tx_pending));
+		}
 	}
 
-	time_left = wait_for_completion_timeout(&ar->fw_stats_complete,
-						1 * HZ);
-	/* If the wait timed out, return -ETIMEDOUT */
-	if (!time_left)
-		return -ETIMEDOUT;
+	len += scnprintf(buf + len, size - len, "\nREO Rx Received:\n");
 
-	/* Firmware sends WMI_UPDATE_STATS_EVENTID back-to-back
-	 * when stats data buffer limit is reached. fw_stats_complete
-	 * is completed once host receives first event from firmware, but
-	 * still end might not be marked in the TLV.
-	 * Below loop is to confirm that firmware completed sending all the event
-	 * and fw_stats_done is marked true when end is marked in the TLV
-	 */
-	for (;;) {
-		if (time_after(jiffies, timeout))
-			break;
+	for (i = 0; i < DP_REO_DST_RING_MAX; i++) {
+		len += scnprintf(buf + len, size - len, "Ring%d:", i + 1);
 
-		spin_lock_bh(&ar->data_lock);
-		if (ar->fw_stats.fw_stats_done) {
-			spin_unlock_bh(&ar->data_lock);
-			break;
+		for (j = 0; j < ATH12K_MAX_DEVICES; j++) {
+			len += scnprintf(buf + len, size - len,
+					"\t%d:%u", j,
+					 device_stats->reo_rx[i][j]);
 		}
-		spin_unlock_bh(&ar->data_lock);
+
+		len += scnprintf(buf + len, size - len, "\n");
 	}
-	return 0;
+
+	len += scnprintf(buf + len, size - len, "\nRx WBM REL SRC Errors:\n");
+
+	for (i = 0; i < HAL_WBM_REL_SRC_MODULE_MAX; i++) {
+		len += scnprintf(buf + len, size - len, "%s:", wbm_rel_src[i]);
+
+		for (j = 0; j < ATH12K_MAX_DEVICES; j++) {
+			len += scnprintf(buf + len,
+					 size - len,
+					 "\t%d:%u", j,
+					 device_stats->rx_wbm_rel_source[i][j]);
+		}
+
+		len += scnprintf(buf + len, size - len, "\n");
+	}
+
+	ret = simple_read_from_buffer(user_buf, count, ppos, buf, len);
+
+	return ret;
+}
+
+static const struct file_operations fops_device_dp_stats = {
+	.read = ath12k_debugfs_dump_device_dp_stats,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+void ath12k_debugfs_pdev_create(struct ath12k_base *ab)
+{
+	debugfs_create_file("simulate_fw_crash", 0600, ab->debugfs_soc, ab,
+			    &fops_simulate_fw_crash);
+
+	debugfs_create_file("device_dp_stats", 0400, ab->debugfs_soc, ab,
+			    &fops_device_dp_stats);
+}
+
+void ath12k_debugfs_soc_create(struct ath12k_base *ab)
+{
+	bool dput_needed;
+	char soc_name[64] = { 0 };
+	struct dentry *debugfs_ath12k;
+
+	debugfs_ath12k = debugfs_lookup("ath12k", NULL);
+	if (debugfs_ath12k) {
+		/* a dentry from lookup() needs dput() after we don't use it */
+		dput_needed = true;
+	} else {
+		debugfs_ath12k = debugfs_create_dir("ath12k", NULL);
+		if (IS_ERR_OR_NULL(debugfs_ath12k))
+			return;
+		dput_needed = false;
+	}
+
+	scnprintf(soc_name, sizeof(soc_name), "%s-%s", ath12k_bus_str(ab->hif.bus),
+		  dev_name(ab->dev));
+
+	ab->debugfs_soc = debugfs_create_dir(soc_name, debugfs_ath12k);
+
+	if (dput_needed)
+		dput(debugfs_ath12k);
+}
+
+void ath12k_debugfs_soc_destroy(struct ath12k_base *ab)
+{
+	debugfs_remove_recursive(ab->debugfs_soc);
+	ab->debugfs_soc = NULL;
+	/* We are not removing ath12k directory on purpose, even if it
+	 * would be empty. This simplifies the directory handling and it's
+	 * a minor cosmetic issue to leave an empty ath12k directory to
+	 * debugfs.
+	 */
 }
 
 void
@@ -1022,10 +1307,6 @@ ath12k_debugfs_fw_stats_process(struct ath12k *ar,
 			num_bcn = 0;
 		}
 	}
-	if (stats->stats_id == WMI_REQUEST_PDEV_STAT) {
-		list_splice_tail_init(&stats->pdevs, &ar->fw_stats.pdevs);
-		ar->fw_stats.fw_stats_done = true;
-	}
 }
 
 static int ath12k_open_vdev_stats(struct inode *inode, struct file *file)
@@ -1052,7 +1333,7 @@ static int ath12k_open_vdev_stats(struct inode *inode, struct file *file)
 	param.vdev_id = 0;
 	param.stats_id = WMI_REQUEST_VDEV_STAT;
 
-	ret = ath12k_debugfs_fw_stats_request(ar, &param);
+	ret = ath12k_mac_get_fw_stats(ar, &param);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to request fw vdev stats: %d\n", ret);
 		return ret;
@@ -1117,7 +1398,7 @@ static int ath12k_open_bcn_stats(struct inode *inode, struct file *file)
 			continue;
 
 		param.vdev_id = arvif->vdev_id;
-		ret = ath12k_debugfs_fw_stats_request(ar, &param);
+		ret = ath12k_mac_get_fw_stats(ar, &param);
 		if (ret) {
 			ath12k_warn(ar->ab, "failed to request fw bcn stats: %d\n", ret);
 			return ret;
@@ -1184,7 +1465,7 @@ static int ath12k_open_pdev_stats(struct inode *inode, struct file *file)
 	param.vdev_id = 0;
 	param.stats_id = WMI_REQUEST_PDEV_STAT;
 
-	ret = ath12k_debugfs_fw_stats_request(ar, &param);
+	ret = ath12k_mac_get_fw_stats(ar, &param);
 	if (ret) {
 		ath12k_warn(ab, "failed to request fw pdev stats: %d\n", ret);
 		return ret;
@@ -1239,11 +1520,7 @@ void ath12k_debugfs_fw_stats_register(struct ath12k *ar)
 	debugfs_create_file("pdev_stats", 0600, fwstats_dir, ar,
 			    &fops_pdev_stats);
 
-	INIT_LIST_HEAD(&ar->fw_stats.vdevs);
-	INIT_LIST_HEAD(&ar->fw_stats.bcn);
-	INIT_LIST_HEAD(&ar->fw_stats.pdevs);
-
-	init_completion(&ar->fw_stats_complete);
+	ath12k_fw_stats_init(ar);
 }
 
 void ath12k_debugfs_register(struct ath12k *ar)
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.h b/drivers/net/wireless/ath/ath12k/debugfs.h
index d7041297d5d8..ebef7dace344 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs.h
@@ -14,7 +14,9 @@ void ath12k_debugfs_register(struct ath12k *ar);
 void ath12k_debugfs_unregister(struct ath12k *ar);
 void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
 				     struct ath12k_fw_stats *stats);
-void ath12k_debugfs_fw_stats_reset(struct ath12k *ar);
+void ath12k_debugfs_op_vif_add(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif);
+void ath12k_debugfs_pdev_create(struct ath12k_base *ab);
 
 static inline bool ath12k_debugfs_is_extd_rx_stats_enabled(struct ath12k *ar)
 {
@@ -129,10 +131,6 @@ static inline void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
 {
 }
 
-static inline void ath12k_debugfs_fw_stats_reset(struct ath12k *ar)
-{
-}
-
 static inline bool ath12k_debugfs_is_extd_rx_stats_enabled(struct ath12k *ar)
 {
 	return false;
@@ -142,6 +140,15 @@ static inline int ath12k_debugfs_rx_filter(struct ath12k *ar)
 {
 	return 0;
 }
+
+static inline void ath12k_debugfs_op_vif_add(struct ieee80211_hw *hw,
+					     struct ieee80211_vif *vif)
+{
+}
+
+static inline void ath12k_debugfs_pdev_create(struct ath12k_base *ab)
+{
+}
 #endif /* CONFIG_ATH12K_DEBUGFS */
 
 #endif /* _ATH12K_DEBUGFS_H_ */
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
index 1c0d5fa39a8d..aeaf970339d4 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
@@ -5377,6 +5377,9 @@ static ssize_t ath12k_write_htt_stats_type(struct file *file,
 	const int size = 32;
 	int num_args;
 
+	if (count > size)
+		return -EINVAL;
+
 	char *buf __free(kfree) = kzalloc(size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
index 50c36e6ea102..6317c6d4c043 100644
--- a/drivers/net/wireless/ath/ath12k/dp.c
+++ b/drivers/net/wireless/ath/ath12k/dp.c
@@ -168,6 +168,8 @@ static int ath12k_dp_srng_calculate_msi_group(struct ath12k_base *ab,
 		grp_mask = &ab->hw_params->ring_mask->reo_status[0];
 		break;
 	case HAL_RXDMA_MONITOR_STATUS:
+		grp_mask = &ab->hw_params->ring_mask->rx_mon_status[0];
+		break;
 	case HAL_RXDMA_MONITOR_DST:
 		grp_mask = &ab->hw_params->ring_mask->rx_mon_dest[0];
 		break;
@@ -274,12 +276,17 @@ int ath12k_dp_srng_setup(struct ath12k_base *ab, struct dp_srng *ring,
 		break;
 	case HAL_RXDMA_BUF:
 	case HAL_RXDMA_MONITOR_BUF:
-	case HAL_RXDMA_MONITOR_STATUS:
 		params.low_threshold = num_entries >> 3;
 		params.flags |= HAL_SRNG_FLAGS_LOW_THRESH_INTR_EN;
 		params.intr_batch_cntr_thres_entries = 0;
 		params.intr_timer_thres_us = HAL_SRNG_INT_TIMER_THRESHOLD_RX;
 		break;
+	case HAL_RXDMA_MONITOR_STATUS:
+		params.low_threshold = num_entries >> 3;
+		params.flags |= HAL_SRNG_FLAGS_LOW_THRESH_INTR_EN;
+		params.intr_batch_cntr_thres_entries = 1;
+		params.intr_timer_thres_us = HAL_SRNG_INT_TIMER_THRESHOLD_RX;
+		break;
 	case HAL_TX_MONITOR_DST:
 		params.low_threshold = DP_TX_MONITOR_BUF_SIZE_MAX >> 3;
 		params.flags |= HAL_SRNG_FLAGS_LOW_THRESH_INTR_EN;
@@ -354,7 +361,10 @@ u32 ath12k_dp_tx_get_vdev_bank_config(struct ath12k_base *ab,
 			u32_encode_bits(0, HAL_TX_BANK_CONFIG_EPD);
 
 	/* only valid if idx_lookup_override is not set in tcl_data_cmd */
-	bank_config |= u32_encode_bits(0, HAL_TX_BANK_CONFIG_INDEX_LOOKUP_EN);
+	if (ahvif->vdev_type == WMI_VDEV_TYPE_STA)
+		bank_config |= u32_encode_bits(1, HAL_TX_BANK_CONFIG_INDEX_LOOKUP_EN);
+	else
+		bank_config |= u32_encode_bits(0, HAL_TX_BANK_CONFIG_INDEX_LOOKUP_EN);
 
 	bank_config |= u32_encode_bits(arvif->hal_addr_search_flags & HAL_TX_ADDRX_EN,
 					HAL_TX_BANK_CONFIG_ADDRX_EN) |
@@ -919,6 +929,25 @@ int ath12k_dp_service_srng(struct ath12k_base *ab,
 			goto done;
 	}
 
+	if (ab->hw_params->ring_mask->rx_mon_status[grp_id]) {
+		ring_mask = ab->hw_params->ring_mask->rx_mon_status[grp_id];
+		for (i = 0; i < ab->num_radios; i++) {
+			for (j = 0; j < ab->hw_params->num_rxdma_per_pdev; j++) {
+				int id = i * ab->hw_params->num_rxdma_per_pdev + j;
+
+				if (ring_mask & BIT(id)) {
+					work_done =
+					ath12k_dp_mon_process_ring(ab, id, napi, budget,
+								   0);
+					budget -= work_done;
+					tot_work_done += work_done;
+					if (budget <= 0)
+						goto done;
+				}
+			}
+		}
+	}
+
 	if (ab->hw_params->ring_mask->rx_mon_dest[grp_id]) {
 		monitor_mode = ATH12K_DP_RX_MONITOR_MODE;
 		ring_mask = ab->hw_params->ring_mask->rx_mon_dest[grp_id];
@@ -982,11 +1011,6 @@ void ath12k_dp_pdev_free(struct ath12k_base *ab)
 {
 	int i;
 
-	if (!ab->mon_reap_timer.function)
-		return;
-
-	timer_delete_sync(&ab->mon_reap_timer);
-
 	for (i = 0; i < ab->num_radios; i++)
 		ath12k_dp_rx_pdev_free(ab, i);
 }
@@ -1024,27 +1048,6 @@ void ath12k_dp_hal_rx_desc_init(struct ath12k_base *ab)
 		ab->hal_rx_ops->rx_desc_get_desc_size();
 }
 
-static void ath12k_dp_service_mon_ring(struct timer_list *t)
-{
-	struct ath12k_base *ab = from_timer(ab, t, mon_reap_timer);
-	int i;
-
-	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++)
-		ath12k_dp_mon_process_ring(ab, i, NULL, DP_MON_SERVICE_BUDGET,
-					   ATH12K_DP_RX_MONITOR_MODE);
-
-	mod_timer(&ab->mon_reap_timer, jiffies +
-		  msecs_to_jiffies(ATH12K_MON_TIMER_INTERVAL));
-}
-
-static void ath12k_dp_mon_reap_timer_init(struct ath12k_base *ab)
-{
-	if (ab->hw_params->rxdma1_enable)
-		return;
-
-	timer_setup(&ab->mon_reap_timer, ath12k_dp_service_mon_ring, 0);
-}
-
 int ath12k_dp_pdev_alloc(struct ath12k_base *ab)
 {
 	struct ath12k *ar;
@@ -1055,8 +1058,6 @@ int ath12k_dp_pdev_alloc(struct ath12k_base *ab)
 	if (ret)
 		goto out;
 
-	ath12k_dp_mon_reap_timer_init(ab);
-
 	/* TODO: Per-pdev rx ring unlike tx ring which is mapped to different AC's */
 	for (i = 0; i < ab->num_radios; i++) {
 		ar = ab->pdevs[i].ar;
@@ -1107,11 +1108,8 @@ static void ath12k_dp_update_vdev_search(struct ath12k_link_vif *arvif)
 {
 	switch (arvif->ahvif->vdev_type) {
 	case WMI_VDEV_TYPE_STA:
-		/* TODO: Verify the search type and flags since ast hash
-		 * is not part of peer mapv3
-		 */
 		arvif->hal_addr_search_flags = HAL_TX_ADDRY_EN;
-		arvif->search_type = HAL_TX_ADDR_SEARCH_DEFAULT;
+		arvif->search_type = HAL_TX_ADDR_SEARCH_INDEX;
 		break;
 	case WMI_VDEV_TYPE_AP:
 	case WMI_VDEV_TYPE_IBSS:
@@ -1206,11 +1204,19 @@ static void ath12k_dp_cc_cleanup(struct ath12k_base *ab)
 			if (!skb)
 				continue;
 
+			skb_cb = ATH12K_SKB_CB(skb);
+			if (skb_cb->paddr_ext_desc) {
+				dma_unmap_single(ab->dev,
+						 skb_cb->paddr_ext_desc,
+						 tx_desc_info->skb_ext_desc->len,
+						 DMA_TO_DEVICE);
+				dev_kfree_skb_any(tx_desc_info->skb_ext_desc);
+			}
+
 			/* if we are unregistering, hw would've been destroyed and
 			 * ar is no longer valid.
 			 */
 			if (!(test_bit(ATH12K_FLAG_UNREGISTERING, &ab->dev_flags))) {
-				skb_cb = ATH12K_SKB_CB(skb);
 				ar = skb_cb->ar;
 
 				if (atomic_dec_and_test(&ar->dp.num_tx_pending))
@@ -1261,22 +1267,24 @@ static void ath12k_dp_reoq_lut_cleanup(struct ath12k_base *ab)
 	if (!ab->hw_params->reoq_lut_support)
 		return;
 
-	if (dp->reoq_lut.vaddr) {
+	if (dp->reoq_lut.vaddr_unaligned) {
 		ath12k_hif_write32(ab,
 				   HAL_SEQ_WCSS_UMAC_REO_REG +
 				   HAL_REO1_QDESC_LUT_BASE0(ab), 0);
-		dma_free_coherent(ab->dev, DP_REOQ_LUT_SIZE,
-				  dp->reoq_lut.vaddr, dp->reoq_lut.paddr);
-		dp->reoq_lut.vaddr = NULL;
+		dma_free_coherent(ab->dev, dp->reoq_lut.size,
+				  dp->reoq_lut.vaddr_unaligned,
+				  dp->reoq_lut.paddr_unaligned);
+		dp->reoq_lut.vaddr_unaligned = NULL;
 	}
 
-	if (dp->ml_reoq_lut.vaddr) {
+	if (dp->ml_reoq_lut.vaddr_unaligned) {
 		ath12k_hif_write32(ab,
 				   HAL_SEQ_WCSS_UMAC_REO_REG +
 				   HAL_REO1_QDESC_LUT_BASE1(ab), 0);
-		dma_free_coherent(ab->dev, DP_REOQ_LUT_SIZE,
-				  dp->ml_reoq_lut.vaddr, dp->ml_reoq_lut.paddr);
-		dp->ml_reoq_lut.vaddr = NULL;
+		dma_free_coherent(ab->dev, dp->ml_reoq_lut.size,
+				  dp->ml_reoq_lut.vaddr_unaligned,
+				  dp->ml_reoq_lut.paddr_unaligned);
+		dp->ml_reoq_lut.vaddr_unaligned = NULL;
 	}
 }
 
@@ -1608,39 +1616,67 @@ free:
 	return ret;
 }
 
+static int ath12k_dp_alloc_reoq_lut(struct ath12k_base *ab,
+				    struct ath12k_reo_q_addr_lut *lut)
+{
+	lut->size =  DP_REOQ_LUT_SIZE + HAL_REO_QLUT_ADDR_ALIGN - 1;
+	lut->vaddr_unaligned = dma_alloc_coherent(ab->dev, lut->size,
+						  &lut->paddr_unaligned,
+						  GFP_KERNEL | __GFP_ZERO);
+	if (!lut->vaddr_unaligned)
+		return -ENOMEM;
+
+	lut->vaddr = PTR_ALIGN(lut->vaddr_unaligned, HAL_REO_QLUT_ADDR_ALIGN);
+	lut->paddr = lut->paddr_unaligned +
+		     ((unsigned long)lut->vaddr - (unsigned long)lut->vaddr_unaligned);
+	return 0;
+}
+
 static int ath12k_dp_reoq_lut_setup(struct ath12k_base *ab)
 {
 	struct ath12k_dp *dp = &ab->dp;
+	u32 val;
+	int ret;
 
 	if (!ab->hw_params->reoq_lut_support)
 		return 0;
 
-	dp->reoq_lut.vaddr = dma_alloc_coherent(ab->dev,
-						DP_REOQ_LUT_SIZE,
-						&dp->reoq_lut.paddr,
-						GFP_KERNEL | __GFP_ZERO);
-	if (!dp->reoq_lut.vaddr) {
+	ret = ath12k_dp_alloc_reoq_lut(ab, &dp->reoq_lut);
+	if (ret) {
 		ath12k_warn(ab, "failed to allocate memory for reoq table");
-		return -ENOMEM;
+		return ret;
 	}
 
-	dp->ml_reoq_lut.vaddr = dma_alloc_coherent(ab->dev,
-						   DP_REOQ_LUT_SIZE,
-						   &dp->ml_reoq_lut.paddr,
-						   GFP_KERNEL | __GFP_ZERO);
-	if (!dp->ml_reoq_lut.vaddr) {
+	ret = ath12k_dp_alloc_reoq_lut(ab, &dp->ml_reoq_lut);
+	if (ret) {
 		ath12k_warn(ab, "failed to allocate memory for ML reoq table");
-		dma_free_coherent(ab->dev, DP_REOQ_LUT_SIZE,
-				  dp->reoq_lut.vaddr, dp->reoq_lut.paddr);
-		dp->reoq_lut.vaddr = NULL;
-		return -ENOMEM;
+		dma_free_coherent(ab->dev, dp->reoq_lut.size,
+				  dp->reoq_lut.vaddr_unaligned,
+				  dp->reoq_lut.paddr_unaligned);
+		dp->reoq_lut.vaddr_unaligned = NULL;
+		return ret;
 	}
 
+	/* Bits in the register have address [39:8] LUT base address to be
+	 * allocated such that LSBs are assumed to be zero. Also, current
+	 * design supports paddr up to 4 GB max hence it fits in 32 bit
+	 * register only
+	 */
+
 	ath12k_hif_write32(ab, HAL_SEQ_WCSS_UMAC_REO_REG + HAL_REO1_QDESC_LUT_BASE0(ab),
-			   dp->reoq_lut.paddr);
+			   dp->reoq_lut.paddr >> 8);
+
 	ath12k_hif_write32(ab, HAL_SEQ_WCSS_UMAC_REO_REG + HAL_REO1_QDESC_LUT_BASE1(ab),
 			   dp->ml_reoq_lut.paddr >> 8);
 
+	val = ath12k_hif_read32(ab, HAL_SEQ_WCSS_UMAC_REO_REG + HAL_REO1_QDESC_ADDR(ab));
+
+	ath12k_hif_write32(ab, HAL_SEQ_WCSS_UMAC_REO_REG + HAL_REO1_QDESC_ADDR(ab),
+			   val | HAL_REO_QDESC_ADDR_READ_LUT_ENABLE);
+
+	ath12k_hif_write32(ab, HAL_SEQ_WCSS_UMAC_REO_REG + HAL_REO1_QDESC_MAX_PEERID(ab),
+			   HAL_REO_QDESC_MAX_PEERID);
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index 75435a931548..a353333f83b6 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -7,6 +7,7 @@
 #ifndef ATH12K_DP_H
 #define ATH12K_DP_H
 
+#include "hal_desc.h"
 #include "hal_rx.h"
 #include "hw.h"
 
@@ -69,6 +70,16 @@ struct ath12k_pdev_mon_stats {
 	u32 dest_mpdu_drop;
 	u32 dup_mon_linkdesc_cnt;
 	u32 dup_mon_buf_cnt;
+	u32 dest_mon_stuck;
+	u32 dest_mon_not_reaped;
+};
+
+enum dp_mon_status_buf_state {
+	DP_MON_STATUS_MATCH,
+	DP_MON_STATUS_NO_DMA,
+	DP_MON_STATUS_LAG,
+	DP_MON_STATUS_LEAD,
+	DP_MON_STATUS_REPLINISH,
 };
 
 struct dp_link_desc_bank {
@@ -106,6 +117,8 @@ struct dp_mon_mpdu {
 	struct list_head list;
 	struct sk_buff *head;
 	struct sk_buff *tail;
+	u32 err_bitmap;
+	u8 decap_format;
 };
 
 #define DP_MON_MAX_STATUS_BUF 32
@@ -118,8 +131,11 @@ struct ath12k_mon_data {
 	u32 mon_last_buf_cookie;
 	u64 mon_last_linkdesc_paddr;
 	u16 chan_noise_floor;
+	u32 err_bitmap;
+	u8 decap_format;
 
 	struct ath12k_pdev_mon_stats rx_mon_stats;
+	enum dp_mon_status_buf_state buf_state;
 	/* lock for monitor data */
 	spinlock_t mon_lock;
 	struct sk_buff_head rx_status_q;
@@ -188,6 +204,14 @@ struct ath12k_pdev_dp {
 #define DP_RX_BUFFER_SIZE_LITE	1024
 #define DP_RX_BUFFER_ALIGN_SIZE	128
 
+#define RX_MON_STATUS_BASE_BUF_SIZE	2048
+#define RX_MON_STATUS_BUF_ALIGN		128
+#define RX_MON_STATUS_BUF_RESERVATION	128
+#define RX_MON_STATUS_BUF_SIZE		(RX_MON_STATUS_BASE_BUF_SIZE - \
+				 (RX_MON_STATUS_BUF_RESERVATION + \
+				  RX_MON_STATUS_BUF_ALIGN + \
+				  SKB_DATA_ALIGN(sizeof(struct skb_shared_info))))
+
 #define DP_RXDMA_BUF_COOKIE_BUF_ID	GENMASK(17, 0)
 #define DP_RXDMA_BUF_COOKIE_PDEV_ID	GENMASK(19, 18)
 
@@ -263,6 +287,9 @@ struct ath12k_pdev_dp {
 /* Invalid TX Bank ID value */
 #define DP_INVALID_BANK_ID -1
 
+#define MAX_TQM_RELEASE_REASON 15
+#define MAX_FW_TX_STATUS 7
+
 struct ath12k_dp_tx_bank_profile {
 	u8 is_configured;
 	u32 num_users;
@@ -293,11 +320,18 @@ struct ath12k_rx_desc_info {
 struct ath12k_tx_desc_info {
 	struct list_head list;
 	struct sk_buff *skb;
+	struct sk_buff *skb_ext_desc;
 	u32 desc_id; /* Cookie */
 	u8 mac_id;
 	u8 pool_id;
 };
 
+struct ath12k_tx_desc_params {
+	struct sk_buff *skb;
+	struct sk_buff *skb_ext_desc;
+	u8 mac_id;
+};
+
 struct ath12k_spt_info {
 	dma_addr_t paddr;
 	u64 *vaddr;
@@ -309,12 +343,26 @@ struct ath12k_reo_queue_ref {
 } __packed;
 
 struct ath12k_reo_q_addr_lut {
-	dma_addr_t paddr;
+	u32 *vaddr_unaligned;
 	u32 *vaddr;
+	dma_addr_t paddr_unaligned;
+	dma_addr_t paddr;
+	u32 size;
+};
+
+struct ath12k_link_stats {
+	u32 tx_enqueued;
+	u32 tx_completed;
+	u32 tx_bcast_mcast;
+	u32 tx_dropped;
+	u32 tx_encap_type[HAL_TCL_ENCAP_TYPE_MAX];
+	u32 tx_encrypt_type[HAL_ENCRYPT_TYPE_MAX];
+	u32 tx_desc_type[HAL_TCL_DESC_TYPE_MAX];
 };
 
 struct ath12k_dp {
 	struct ath12k_base *ab;
+	u32 mon_dest_ring_stuck_cnt;
 	u8 num_bank_profiles;
 	/* protects the access and update of bank_profiles */
 	spinlock_t tx_bank_lock;
@@ -367,6 +415,7 @@ struct ath12k_dp {
 	struct dp_srng rxdma_err_dst_ring[MAX_RXDMA_PER_PDEV];
 	struct dp_rxdma_mon_ring rxdma_mon_buf_ring;
 	struct dp_rxdma_mon_ring tx_mon_buf_ring;
+	struct dp_rxdma_mon_ring rx_mon_status_refill_ring[MAX_RXDMA_PER_PDEV];
 	struct ath12k_reo_q_addr_lut reoq_lut;
 	struct ath12k_reo_q_addr_lut ml_reoq_lut;
 };
@@ -1307,6 +1356,8 @@ struct htt_t2h_version_conf_msg {
 #define HTT_T2H_PEER_MAP_INFO1_MAC_ADDR_H16	GENMASK(15, 0)
 #define HTT_T2H_PEER_MAP_INFO1_HW_PEER_ID	GENMASK(31, 16)
 #define HTT_T2H_PEER_MAP_INFO2_AST_HASH_VAL	GENMASK(15, 0)
+#define HTT_T2H_PEER_MAP3_INFO2_HW_PEER_ID	GENMASK(15, 0)
+#define HTT_T2H_PEER_MAP3_INFO2_AST_HASH_VAL	GENMASK(31, 16)
 #define HTT_T2H_PEER_MAP_INFO2_NEXT_HOP_M	BIT(16)
 #define HTT_T2H_PEER_MAP_INFO2_NEXT_HOP_S	16
 
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index d22800e89485..28cadc4167f7 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -1416,6 +1416,40 @@ ath12k_dp_mon_hal_rx_parse_user_info(const struct hal_receive_user_info *rx_usr_
 	}
 }
 
+static void ath12k_dp_mon_parse_rx_msdu_end_err(u32 info, u32 *errmap)
+{
+	if (info & RX_MSDU_END_INFO13_FCS_ERR)
+		*errmap |= HAL_RX_MPDU_ERR_FCS;
+
+	if (info & RX_MSDU_END_INFO13_DECRYPT_ERR)
+		*errmap |= HAL_RX_MPDU_ERR_DECRYPT;
+
+	if (info & RX_MSDU_END_INFO13_TKIP_MIC_ERR)
+		*errmap |= HAL_RX_MPDU_ERR_TKIP_MIC;
+
+	if (info & RX_MSDU_END_INFO13_A_MSDU_ERROR)
+		*errmap |= HAL_RX_MPDU_ERR_AMSDU_ERR;
+
+	if (info & RX_MSDU_END_INFO13_OVERFLOW_ERR)
+		*errmap |= HAL_RX_MPDU_ERR_OVERFLOW;
+
+	if (info & RX_MSDU_END_INFO13_MSDU_LEN_ERR)
+		*errmap |= HAL_RX_MPDU_ERR_MSDU_LEN;
+
+	if (info & RX_MSDU_END_INFO13_MPDU_LEN_ERR)
+		*errmap |= HAL_RX_MPDU_ERR_MPDU_LEN;
+}
+
+static void
+ath12k_dp_mon_parse_status_msdu_end(struct ath12k_mon_data *pmon,
+				    const struct hal_rx_msdu_end *msdu_end)
+{
+	ath12k_dp_mon_parse_rx_msdu_end_err(__le32_to_cpu(msdu_end->info2),
+					    &pmon->err_bitmap);
+	pmon->decap_format = le32_get_bits(msdu_end->info1,
+					   RX_MSDU_END_INFO11_DECAP_FORMAT);
+}
+
 static enum hal_rx_mon_status
 ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 				  struct ath12k_mon_data *pmon,
@@ -1647,7 +1681,7 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 				u32_get_bits(info[0], HAL_RX_MPDU_START_INFO0_PPDU_ID);
 		}
 
-		break;
+		return HAL_RX_MON_STATUS_MPDU_START;
 	}
 	case HAL_RX_MSDU_START:
 		/* TODO: add msdu start parsing logic */
@@ -1655,6 +1689,7 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 	case HAL_MON_BUF_ADDR:
 		return HAL_RX_MON_STATUS_BUF_ADDR;
 	case HAL_RX_MSDU_END:
+		ath12k_dp_mon_parse_status_msdu_end(pmon, tlv_data);
 		return HAL_RX_MON_STATUS_MSDU_END;
 	case HAL_RX_MPDU_END:
 		return HAL_RX_MON_STATUS_MPDU_END;
@@ -1688,45 +1723,295 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 	return HAL_RX_MON_STATUS_PPDU_NOT_DONE;
 }
 
+static void
+ath12k_dp_mon_fill_rx_stats_info(struct ath12k *ar,
+				 struct hal_rx_mon_ppdu_info *ppdu_info,
+				 struct ieee80211_rx_status *rx_status)
+{
+	u32 center_freq = ppdu_info->freq;
+
+	rx_status->freq = center_freq;
+	rx_status->bw = ath12k_mac_bw_to_mac80211_bw(ppdu_info->bw);
+	rx_status->nss = ppdu_info->nss;
+	rx_status->rate_idx = 0;
+	rx_status->encoding = RX_ENC_LEGACY;
+	rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL;
+
+	if (center_freq >= ATH12K_MIN_6GHZ_FREQ &&
+	    center_freq <= ATH12K_MAX_6GHZ_FREQ) {
+		rx_status->band = NL80211_BAND_6GHZ;
+	} else if (center_freq >= ATH12K_MIN_2GHZ_FREQ &&
+		   center_freq <= ATH12K_MAX_2GHZ_FREQ) {
+		rx_status->band = NL80211_BAND_2GHZ;
+	} else if (center_freq >= ATH12K_MIN_5GHZ_FREQ &&
+		   center_freq <= ATH12K_MAX_5GHZ_FREQ) {
+		rx_status->band = NL80211_BAND_5GHZ;
+	} else {
+		rx_status->band = NUM_NL80211_BANDS;
+	}
+}
+
+static struct sk_buff
+*ath12k_dp_rx_alloc_mon_status_buf(struct ath12k_base *ab,
+				   struct dp_rxdma_mon_ring *rx_ring,
+				   int *buf_id)
+{
+	struct sk_buff *skb;
+	dma_addr_t paddr;
+
+	skb = dev_alloc_skb(RX_MON_STATUS_BUF_SIZE);
+
+	if (!skb)
+		goto fail_alloc_skb;
+
+	if (!IS_ALIGNED((unsigned long)skb->data,
+			RX_MON_STATUS_BUF_ALIGN)) {
+		skb_pull(skb, PTR_ALIGN(skb->data, RX_MON_STATUS_BUF_ALIGN) -
+			 skb->data);
+	}
+
+	paddr = dma_map_single(ab->dev, skb->data,
+			       skb->len + skb_tailroom(skb),
+			       DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(ab->dev, paddr)))
+		goto fail_free_skb;
+
+	spin_lock_bh(&rx_ring->idr_lock);
+	*buf_id = idr_alloc(&rx_ring->bufs_idr, skb, 0,
+			    rx_ring->bufs_max, GFP_ATOMIC);
+	spin_unlock_bh(&rx_ring->idr_lock);
+	if (*buf_id < 0)
+		goto fail_dma_unmap;
+
+	ATH12K_SKB_RXCB(skb)->paddr = paddr;
+	return skb;
+
+fail_dma_unmap:
+	dma_unmap_single(ab->dev, paddr, skb->len + skb_tailroom(skb),
+			 DMA_FROM_DEVICE);
+fail_free_skb:
+	dev_kfree_skb_any(skb);
+fail_alloc_skb:
+	return NULL;
+}
+
+static enum dp_mon_status_buf_state
+ath12k_dp_rx_mon_buf_done(struct ath12k_base *ab, struct hal_srng *srng,
+			  struct dp_rxdma_mon_ring *rx_ring)
+{
+	struct ath12k_skb_rxcb *rxcb;
+	struct hal_tlv_64_hdr *tlv;
+	struct sk_buff *skb;
+	void *status_desc;
+	dma_addr_t paddr;
+	u32 cookie;
+	int buf_id;
+	u8 rbm;
+
+	status_desc = ath12k_hal_srng_src_next_peek(ab, srng);
+	if (!status_desc)
+		return DP_MON_STATUS_NO_DMA;
+
+	ath12k_hal_rx_buf_addr_info_get(status_desc, &paddr, &cookie, &rbm);
+
+	buf_id = u32_get_bits(cookie, DP_RXDMA_BUF_COOKIE_BUF_ID);
+
+	spin_lock_bh(&rx_ring->idr_lock);
+	skb = idr_find(&rx_ring->bufs_idr, buf_id);
+	spin_unlock_bh(&rx_ring->idr_lock);
+
+	if (!skb)
+		return DP_MON_STATUS_NO_DMA;
+
+	rxcb = ATH12K_SKB_RXCB(skb);
+	dma_sync_single_for_cpu(ab->dev, rxcb->paddr,
+				skb->len + skb_tailroom(skb),
+				DMA_FROM_DEVICE);
+
+	tlv = (struct hal_tlv_64_hdr *)skb->data;
+	if (le64_get_bits(tlv->tl, HAL_TLV_HDR_TAG) != HAL_RX_STATUS_BUFFER_DONE)
+		return DP_MON_STATUS_NO_DMA;
+
+	return DP_MON_STATUS_REPLINISH;
+}
+
+static u32 ath12k_dp_mon_comp_ppduid(u32 msdu_ppdu_id, u32 *ppdu_id)
+{
+	u32 ret = 0;
+
+	if ((*ppdu_id < msdu_ppdu_id) &&
+	    ((msdu_ppdu_id - *ppdu_id) < DP_NOT_PPDU_ID_WRAP_AROUND)) {
+		/* Hold on mon dest ring, and reap mon status ring. */
+		*ppdu_id = msdu_ppdu_id;
+		ret = msdu_ppdu_id;
+	} else if ((*ppdu_id > msdu_ppdu_id) &&
+		((*ppdu_id - msdu_ppdu_id) > DP_NOT_PPDU_ID_WRAP_AROUND)) {
+		/* PPDU ID has exceeded the maximum value and will
+		 * restart from 0.
+		 */
+		*ppdu_id = msdu_ppdu_id;
+		ret = msdu_ppdu_id;
+	}
+	return ret;
+}
+
+static
+void ath12k_dp_mon_next_link_desc_get(struct hal_rx_msdu_link *msdu_link,
+				      dma_addr_t *paddr, u32 *sw_cookie, u8 *rbm,
+				      struct ath12k_buffer_addr **pp_buf_addr_info)
+{
+	struct ath12k_buffer_addr *buf_addr_info;
+
+	buf_addr_info = &msdu_link->buf_addr_info;
+
+	ath12k_hal_rx_buf_addr_info_get(buf_addr_info, paddr, sw_cookie, rbm);
+
+	*pp_buf_addr_info = buf_addr_info;
+}
+
+static void
+ath12k_dp_mon_fill_rx_rate(struct ath12k *ar,
+			   struct hal_rx_mon_ppdu_info *ppdu_info,
+			   struct ieee80211_rx_status *rx_status)
+{
+	struct ieee80211_supported_band *sband;
+	enum rx_msdu_start_pkt_type pkt_type;
+	u8 rate_mcs, nss, sgi;
+	bool is_cck;
+
+	pkt_type = ppdu_info->preamble_type;
+	rate_mcs = ppdu_info->rate;
+	nss = ppdu_info->nss;
+	sgi = ppdu_info->gi;
+
+	switch (pkt_type) {
+	case RX_MSDU_START_PKT_TYPE_11A:
+	case RX_MSDU_START_PKT_TYPE_11B:
+		is_cck = (pkt_type == RX_MSDU_START_PKT_TYPE_11B);
+		if (rx_status->band < NUM_NL80211_BANDS) {
+			sband = &ar->mac.sbands[rx_status->band];
+			rx_status->rate_idx = ath12k_mac_hw_rate_to_idx(sband, rate_mcs,
+									is_cck);
+		}
+		break;
+	case RX_MSDU_START_PKT_TYPE_11N:
+		rx_status->encoding = RX_ENC_HT;
+		if (rate_mcs > ATH12K_HT_MCS_MAX) {
+			ath12k_warn(ar->ab,
+				    "Received with invalid mcs in HT mode %d\n",
+				     rate_mcs);
+			break;
+		}
+		rx_status->rate_idx = rate_mcs + (8 * (nss - 1));
+		if (sgi)
+			rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
+		break;
+	case RX_MSDU_START_PKT_TYPE_11AC:
+		rx_status->encoding = RX_ENC_VHT;
+		rx_status->rate_idx = rate_mcs;
+		if (rate_mcs > ATH12K_VHT_MCS_MAX) {
+			ath12k_warn(ar->ab,
+				    "Received with invalid mcs in VHT mode %d\n",
+				     rate_mcs);
+			break;
+		}
+		if (sgi)
+			rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
+		break;
+	case RX_MSDU_START_PKT_TYPE_11AX:
+		rx_status->rate_idx = rate_mcs;
+		if (rate_mcs > ATH12K_HE_MCS_MAX) {
+			ath12k_warn(ar->ab,
+				    "Received with invalid mcs in HE mode %d\n",
+				    rate_mcs);
+			break;
+		}
+		rx_status->encoding = RX_ENC_HE;
+		rx_status->he_gi = ath12k_he_gi_to_nl80211_he_gi(sgi);
+		break;
+	case RX_MSDU_START_PKT_TYPE_11BE:
+		rx_status->rate_idx = rate_mcs;
+		if (rate_mcs > ATH12K_EHT_MCS_MAX) {
+			ath12k_warn(ar->ab,
+				    "Received with invalid mcs in EHT mode %d\n",
+				    rate_mcs);
+			break;
+		}
+		rx_status->encoding = RX_ENC_EHT;
+		rx_status->he_gi = ath12k_he_gi_to_nl80211_he_gi(sgi);
+		break;
+	default:
+		ath12k_dbg(ar->ab, ATH12K_DBG_DATA,
+			   "monitor receives invalid preamble type %d",
+			    pkt_type);
+		break;
+	}
+}
+
 static void ath12k_dp_mon_rx_msdus_set_payload(struct ath12k *ar,
 					       struct sk_buff *head_msdu,
 					       struct sk_buff *tail_msdu)
 {
-	u32 rx_pkt_offset, l2_hdr_offset;
+	u32 rx_pkt_offset, l2_hdr_offset, total_offset;
 
 	rx_pkt_offset = ar->ab->hal.hal_desc_sz;
 	l2_hdr_offset =
 		ath12k_dp_rx_h_l3pad(ar->ab, (struct hal_rx_desc *)tail_msdu->data);
-	skb_pull(head_msdu, rx_pkt_offset + l2_hdr_offset);
+
+	if (ar->ab->hw_params->rxdma1_enable)
+		total_offset = ATH12K_MON_RX_PKT_OFFSET;
+	else
+		total_offset = rx_pkt_offset + l2_hdr_offset;
+
+	skb_pull(head_msdu, total_offset);
 }
 
 static struct sk_buff *
 ath12k_dp_mon_rx_merg_msdus(struct ath12k *ar,
-			    struct sk_buff *head_msdu, struct sk_buff *tail_msdu,
-			    struct ieee80211_rx_status *rxs, bool *fcs_err)
+			    struct dp_mon_mpdu *mon_mpdu,
+			    struct hal_rx_mon_ppdu_info *ppdu_info,
+			    struct ieee80211_rx_status *rxs)
 {
 	struct ath12k_base *ab = ar->ab;
 	struct sk_buff *msdu, *mpdu_buf, *prev_buf, *head_frag_list;
-	struct hal_rx_desc *rx_desc, *tail_rx_desc;
-	u8 *hdr_desc, *dest, decap_format;
+	struct sk_buff *head_msdu, *tail_msdu;
+	struct hal_rx_desc *rx_desc;
+	u8 *hdr_desc, *dest, decap_format = mon_mpdu->decap_format;
 	struct ieee80211_hdr_3addr *wh;
-	u32 err_bitmap, frag_list_sum_len = 0;
+	struct ieee80211_channel *channel;
+	u32 frag_list_sum_len = 0;
+	u8 channel_num = ppdu_info->chan_num;
 
 	mpdu_buf = NULL;
+	head_msdu = mon_mpdu->head;
+	tail_msdu = mon_mpdu->tail;
 
-	if (!head_msdu)
+	if (!head_msdu || !tail_msdu)
 		goto err_merge_fail;
 
-	rx_desc = (struct hal_rx_desc *)head_msdu->data;
-	tail_rx_desc = (struct hal_rx_desc *)tail_msdu->data;
+	ath12k_dp_mon_fill_rx_stats_info(ar, ppdu_info, rxs);
+
+	if (unlikely(rxs->band == NUM_NL80211_BANDS ||
+		     !ath12k_ar_to_hw(ar)->wiphy->bands[rxs->band])) {
+		ath12k_dbg(ar->ab, ATH12K_DBG_DATA,
+			   "sband is NULL for status band %d channel_num %d center_freq %d pdev_id %d\n",
+			   rxs->band, channel_num, ppdu_info->freq, ar->pdev_idx);
 
-	err_bitmap = ath12k_dp_rx_h_mpdu_err(ab, tail_rx_desc);
-	if (err_bitmap & HAL_RX_MPDU_ERR_FCS)
-		*fcs_err = true;
+		spin_lock_bh(&ar->data_lock);
+		channel = ar->rx_channel;
+		if (channel) {
+			rxs->band = channel->band;
+			channel_num =
+				ieee80211_frequency_to_channel(channel->center_freq);
+		}
+		spin_unlock_bh(&ar->data_lock);
+	}
 
-	decap_format = ath12k_dp_rx_h_decap_type(ab, tail_rx_desc);
+	if (rxs->band < NUM_NL80211_BANDS)
+		rxs->freq = ieee80211_channel_to_frequency(channel_num,
+							   rxs->band);
 
-	ath12k_dp_rx_h_ppdu(ar, tail_rx_desc, rxs);
+	ath12k_dp_mon_fill_rx_rate(ar, ppdu_info, rxs);
 
 	if (decap_format == DP_RX_DECAP_TYPE_RAW) {
 		ath12k_dp_mon_rx_msdus_set_payload(ar, head_msdu, tail_msdu);
@@ -1736,7 +2021,7 @@ ath12k_dp_mon_rx_merg_msdus(struct ath12k *ar,
 		head_frag_list = NULL;
 
 		while (msdu) {
-			ath12k_dp_mon_rx_msdus_set_payload(ar, msdu, tail_msdu);
+			ath12k_dp_mon_rx_msdus_set_payload(ar, head_msdu, tail_msdu);
 
 			if (!head_frag_list)
 				head_frag_list = msdu;
@@ -1748,7 +2033,7 @@ ath12k_dp_mon_rx_merg_msdus(struct ath12k *ar,
 
 		prev_buf->next = NULL;
 
-		skb_trim(prev_buf, prev_buf->len - HAL_RX_FCS_LEN);
+		skb_trim(prev_buf, prev_buf->len);
 		if (head_frag_list) {
 			skb_shinfo(head_msdu)->frag_list = head_frag_list;
 			head_msdu->data_len = frag_list_sum_len;
@@ -1771,7 +2056,7 @@ ath12k_dp_mon_rx_merg_msdus(struct ath12k *ar,
 		msdu = head_msdu;
 
 		while (msdu) {
-			ath12k_dp_mon_rx_msdus_set_payload(ar, msdu, tail_msdu);
+			ath12k_dp_mon_rx_msdus_set_payload(ar, head_msdu, tail_msdu);
 			if (qos_pkt) {
 				dest = skb_push(msdu, sizeof(__le16));
 				if (!dest)
@@ -1954,7 +2239,8 @@ static void ath12k_dp_mon_update_radiotap(struct ath12k *ar,
 
 static void ath12k_dp_mon_rx_deliver_msdu(struct ath12k *ar, struct napi_struct *napi,
 					  struct sk_buff *msdu,
-					  struct ieee80211_rx_status *status)
+					  struct ieee80211_rx_status *status,
+					  u8 decap)
 {
 	static const struct ieee80211_radiotap_he known = {
 		.data1 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN |
@@ -1966,10 +2252,12 @@ static void ath12k_dp_mon_rx_deliver_msdu(struct ath12k *ar, struct napi_struct
 	struct ieee80211_sta *pubsta = NULL;
 	struct ath12k_peer *peer;
 	struct ath12k_skb_rxcb *rxcb = ATH12K_SKB_RXCB(msdu);
-	u8 decap = DP_RX_DECAP_TYPE_RAW;
+	struct ath12k_dp_rx_info rx_info;
 	bool is_mcbc = rxcb->is_mcbc;
 	bool is_eapol_tkip = rxcb->is_eapol;
 
+	status->link_valid = 0;
+
 	if ((status->encoding == RX_ENC_HE) && !(status->flag & RX_FLAG_RADIOTAP_HE) &&
 	    !(status->flag & RX_FLAG_SKIP_MONITOR)) {
 		he = skb_push(msdu, sizeof(known));
@@ -1977,10 +2265,9 @@ static void ath12k_dp_mon_rx_deliver_msdu(struct ath12k *ar, struct napi_struct
 		status->flag |= RX_FLAG_RADIOTAP_HE;
 	}
 
-	if (!(status->flag & RX_FLAG_ONLY_MONITOR))
-		decap = ath12k_dp_rx_h_decap_type(ar->ab, rxcb->rx_desc);
 	spin_lock_bh(&ar->ab->base_lock);
-	peer = ath12k_dp_rx_h_find_peer(ar->ab, msdu);
+	rx_info.addr2_present = false;
+	peer = ath12k_dp_rx_h_find_peer(ar->ab, msdu, &rx_info);
 	if (peer && peer->sta) {
 		pubsta = peer->sta;
 		if (pubsta->valid_links) {
@@ -2035,25 +2322,23 @@ static void ath12k_dp_mon_rx_deliver_msdu(struct ath12k *ar, struct napi_struct
 }
 
 static int ath12k_dp_mon_rx_deliver(struct ath12k *ar,
-				    struct sk_buff *head_msdu, struct sk_buff *tail_msdu,
+				    struct dp_mon_mpdu *mon_mpdu,
 				    struct hal_rx_mon_ppdu_info *ppduinfo,
 				    struct napi_struct *napi)
 {
 	struct ath12k_pdev_dp *dp = &ar->dp;
 	struct sk_buff *mon_skb, *skb_next, *header;
 	struct ieee80211_rx_status *rxs = &dp->rx_status;
-	bool fcs_err = false;
+	u8 decap = DP_RX_DECAP_TYPE_RAW;
 
-	mon_skb = ath12k_dp_mon_rx_merg_msdus(ar,
-					      head_msdu, tail_msdu,
-					      rxs, &fcs_err);
+	mon_skb = ath12k_dp_mon_rx_merg_msdus(ar, mon_mpdu, ppduinfo, rxs);
 	if (!mon_skb)
 		goto mon_deliver_fail;
 
 	header = mon_skb;
 	rxs->flag = 0;
 
-	if (fcs_err)
+	if (mon_mpdu->err_bitmap & HAL_RX_MPDU_ERR_FCS)
 		rxs->flag = RX_FLAG_FAILED_FCS_CRC;
 
 	do {
@@ -2070,8 +2355,12 @@ static int ath12k_dp_mon_rx_deliver(struct ath12k *ar,
 			rxs->flag |= RX_FLAG_ALLOW_SAME_PN;
 		}
 		rxs->flag |= RX_FLAG_ONLY_MONITOR;
+
+		if (!(rxs->flag & RX_FLAG_ONLY_MONITOR))
+			decap = mon_mpdu->decap_format;
+
 		ath12k_dp_mon_update_radiotap(ar, ppduinfo, mon_skb, rxs);
-		ath12k_dp_mon_rx_deliver_msdu(ar, napi, mon_skb, rxs);
+		ath12k_dp_mon_rx_deliver_msdu(ar, napi, mon_skb, rxs, decap);
 		mon_skb = skb_next;
 	} while (mon_skb);
 	rxs->flag = 0;
@@ -2079,7 +2368,7 @@ static int ath12k_dp_mon_rx_deliver(struct ath12k *ar,
 	return 0;
 
 mon_deliver_fail:
-	mon_skb = head_msdu;
+	mon_skb = mon_mpdu->head;
 	while (mon_skb) {
 		skb_next = mon_skb->next;
 		dev_kfree_skb_any(mon_skb);
@@ -2088,6 +2377,133 @@ mon_deliver_fail:
 	return -EINVAL;
 }
 
+static int ath12k_dp_pkt_set_pktlen(struct sk_buff *skb, u32 len)
+{
+	if (skb->len > len) {
+		skb_trim(skb, len);
+	} else {
+		if (skb_tailroom(skb) < len - skb->len) {
+			if ((pskb_expand_head(skb, 0,
+					      len - skb->len - skb_tailroom(skb),
+					      GFP_ATOMIC))) {
+				return -ENOMEM;
+			}
+		}
+		skb_put(skb, (len - skb->len));
+	}
+
+	return 0;
+}
+
+/* Hardware fill buffer with 128 bytes aligned. So need to reap it
+ * with 128 bytes aligned.
+ */
+#define RXDMA_DATA_DMA_BLOCK_SIZE 128
+
+static void
+ath12k_dp_mon_get_buf_len(struct hal_rx_msdu_desc_info *info,
+			  bool *is_frag, u32 *total_len,
+			  u32 *frag_len, u32 *msdu_cnt)
+{
+	if (info->msdu_flags & RX_MSDU_DESC_INFO0_MSDU_CONTINUATION) {
+		*is_frag = true;
+		*frag_len = (RX_MON_STATUS_BASE_BUF_SIZE -
+			     sizeof(struct hal_rx_desc)) &
+			     ~(RXDMA_DATA_DMA_BLOCK_SIZE - 1);
+		*total_len += *frag_len;
+	} else {
+		if (*is_frag)
+			*frag_len = info->msdu_len - *total_len;
+		else
+			*frag_len = info->msdu_len;
+
+		*msdu_cnt -= 1;
+	}
+}
+
+static int
+ath12k_dp_mon_parse_status_buf(struct ath12k *ar,
+			       struct ath12k_mon_data *pmon,
+			       const struct dp_mon_packet_info *packet_info)
+{
+	struct ath12k_base *ab = ar->ab;
+	struct dp_rxdma_mon_ring *buf_ring = &ab->dp.rxdma_mon_buf_ring;
+	struct sk_buff *msdu;
+	int buf_id;
+	u32 offset;
+
+	buf_id = u32_get_bits(packet_info->cookie, DP_RXDMA_BUF_COOKIE_BUF_ID);
+
+	spin_lock_bh(&buf_ring->idr_lock);
+	msdu = idr_remove(&buf_ring->bufs_idr, buf_id);
+	spin_unlock_bh(&buf_ring->idr_lock);
+
+	if (unlikely(!msdu)) {
+		ath12k_warn(ab, "mon dest desc with inval buf_id %d\n", buf_id);
+		return 0;
+	}
+
+	dma_unmap_single(ab->dev, ATH12K_SKB_RXCB(msdu)->paddr,
+			 msdu->len + skb_tailroom(msdu),
+			 DMA_FROM_DEVICE);
+
+	offset = packet_info->dma_length + ATH12K_MON_RX_DOT11_OFFSET;
+	if (ath12k_dp_pkt_set_pktlen(msdu, offset)) {
+		dev_kfree_skb_any(msdu);
+		goto dest_replenish;
+	}
+
+	if (!pmon->mon_mpdu->head)
+		pmon->mon_mpdu->head = msdu;
+	else
+		pmon->mon_mpdu->tail->next = msdu;
+
+	pmon->mon_mpdu->tail = msdu;
+
+dest_replenish:
+	ath12k_dp_mon_buf_replenish(ab, buf_ring, 1);
+
+	return 0;
+}
+
+static int
+ath12k_dp_mon_parse_rx_dest_tlv(struct ath12k *ar,
+				struct ath12k_mon_data *pmon,
+				enum hal_rx_mon_status hal_status,
+				const void *tlv_data)
+{
+	switch (hal_status) {
+	case HAL_RX_MON_STATUS_MPDU_START:
+		if (WARN_ON_ONCE(pmon->mon_mpdu))
+			break;
+
+		pmon->mon_mpdu = kzalloc(sizeof(*pmon->mon_mpdu), GFP_ATOMIC);
+		if (!pmon->mon_mpdu)
+			return -ENOMEM;
+		break;
+	case HAL_RX_MON_STATUS_BUF_ADDR:
+		return ath12k_dp_mon_parse_status_buf(ar, pmon, tlv_data);
+	case HAL_RX_MON_STATUS_MPDU_END:
+		/* If no MSDU then free empty MPDU */
+		if (pmon->mon_mpdu->tail) {
+			pmon->mon_mpdu->tail->next = NULL;
+			list_add_tail(&pmon->mon_mpdu->list, &pmon->dp_rx_mon_mpdu_list);
+		} else {
+			kfree(pmon->mon_mpdu);
+		}
+		pmon->mon_mpdu = NULL;
+		break;
+	case HAL_RX_MON_STATUS_MSDU_END:
+		pmon->mon_mpdu->decap_format = pmon->decap_format;
+		pmon->mon_mpdu->err_bitmap = pmon->err_bitmap;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static enum hal_rx_mon_status
 ath12k_dp_mon_parse_rx_dest(struct ath12k *ar, struct ath12k_mon_data *pmon,
 			    struct sk_buff *skb)
@@ -2114,14 +2530,20 @@ ath12k_dp_mon_parse_rx_dest(struct ath12k *ar, struct ath12k_mon_data *pmon,
 			tlv_len = le64_get_bits(tlv->tl, HAL_TLV_64_HDR_LEN);
 
 		hal_status = ath12k_dp_mon_rx_parse_status_tlv(ar, pmon, tlv);
+
+		if (ar->monitor_started && ar->ab->hw_params->rxdma1_enable &&
+		    ath12k_dp_mon_parse_rx_dest_tlv(ar, pmon, hal_status, tlv->value))
+			return HAL_RX_MON_STATUS_PPDU_DONE;
+
 		ptr += sizeof(*tlv) + tlv_len;
 		ptr = PTR_ALIGN(ptr, HAL_TLV_64_ALIGN);
 
-		if ((ptr - skb->data) >= DP_RX_BUFFER_SIZE)
+		if ((ptr - skb->data) > skb->len)
 			break;
 
 	} while ((hal_status == HAL_RX_MON_STATUS_PPDU_NOT_DONE) ||
 		 (hal_status == HAL_RX_MON_STATUS_BUF_ADDR) ||
+		 (hal_status == HAL_RX_MON_STATUS_MPDU_START) ||
 		 (hal_status == HAL_RX_MON_STATUS_MPDU_END) ||
 		 (hal_status == HAL_RX_MON_STATUS_MSDU_END));
 
@@ -2141,23 +2563,21 @@ ath12k_dp_mon_rx_parse_mon_status(struct ath12k *ar,
 	struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info;
 	struct dp_mon_mpdu *tmp;
 	struct dp_mon_mpdu *mon_mpdu = pmon->mon_mpdu;
-	struct sk_buff *head_msdu, *tail_msdu;
-	enum hal_rx_mon_status hal_status = HAL_RX_MON_STATUS_BUF_DONE;
+	enum hal_rx_mon_status hal_status;
 
-	ath12k_dp_mon_parse_rx_dest(ar, pmon, skb);
+	hal_status = ath12k_dp_mon_parse_rx_dest(ar, pmon, skb);
+	if (hal_status != HAL_RX_MON_STATUS_PPDU_DONE)
+		return hal_status;
 
 	list_for_each_entry_safe(mon_mpdu, tmp, &pmon->dp_rx_mon_mpdu_list, list) {
 		list_del(&mon_mpdu->list);
-		head_msdu = mon_mpdu->head;
-		tail_msdu = mon_mpdu->tail;
 
-		if (head_msdu && tail_msdu) {
-			ath12k_dp_mon_rx_deliver(ar, head_msdu,
-						 tail_msdu, ppdu_info, napi);
-		}
+		if (mon_mpdu->head && mon_mpdu->tail)
+			ath12k_dp_mon_rx_deliver(ar, mon_mpdu, ppdu_info, napi);
 
 		kfree(mon_mpdu);
 	}
+
 	return hal_status;
 }
 
@@ -2236,6 +2656,94 @@ fail_alloc_skb:
 	return -ENOMEM;
 }
 
+int ath12k_dp_mon_status_bufs_replenish(struct ath12k_base *ab,
+					struct dp_rxdma_mon_ring *rx_ring,
+					int req_entries)
+{
+	enum hal_rx_buf_return_buf_manager mgr =
+		ab->hw_params->hal_params->rx_buf_rbm;
+	int num_free, num_remain, buf_id;
+	struct ath12k_buffer_addr *desc;
+	struct hal_srng *srng;
+	struct sk_buff *skb;
+	dma_addr_t paddr;
+	u32 cookie;
+
+	req_entries = min(req_entries, rx_ring->bufs_max);
+
+	srng = &ab->hal.srng_list[rx_ring->refill_buf_ring.ring_id];
+
+	spin_lock_bh(&srng->lock);
+
+	ath12k_hal_srng_access_begin(ab, srng);
+
+	num_free = ath12k_hal_srng_src_num_free(ab, srng, true);
+	if (!req_entries && (num_free > (rx_ring->bufs_max * 3) / 4))
+		req_entries = num_free;
+
+	req_entries = min(num_free, req_entries);
+	num_remain = req_entries;
+
+	while (num_remain > 0) {
+		skb = dev_alloc_skb(RX_MON_STATUS_BUF_SIZE);
+		if (!skb)
+			break;
+
+		if (!IS_ALIGNED((unsigned long)skb->data,
+				RX_MON_STATUS_BUF_ALIGN)) {
+			skb_pull(skb,
+				 PTR_ALIGN(skb->data, RX_MON_STATUS_BUF_ALIGN) -
+				 skb->data);
+		}
+
+		paddr = dma_map_single(ab->dev, skb->data,
+				       skb->len + skb_tailroom(skb),
+				       DMA_FROM_DEVICE);
+		if (dma_mapping_error(ab->dev, paddr))
+			goto fail_free_skb;
+
+		spin_lock_bh(&rx_ring->idr_lock);
+		buf_id = idr_alloc(&rx_ring->bufs_idr, skb, 0,
+				   rx_ring->bufs_max * 3, GFP_ATOMIC);
+		spin_unlock_bh(&rx_ring->idr_lock);
+		if (buf_id < 0)
+			goto fail_dma_unmap;
+		cookie = u32_encode_bits(buf_id, DP_RXDMA_BUF_COOKIE_BUF_ID);
+
+		desc = ath12k_hal_srng_src_get_next_entry(ab, srng);
+		if (!desc)
+			goto fail_buf_unassign;
+
+		ATH12K_SKB_RXCB(skb)->paddr = paddr;
+
+		num_remain--;
+
+		ath12k_hal_rx_buf_addr_info_set(desc, paddr, cookie, mgr);
+	}
+
+	ath12k_hal_srng_access_end(ab, srng);
+
+	spin_unlock_bh(&srng->lock);
+
+	return req_entries - num_remain;
+
+fail_buf_unassign:
+	spin_lock_bh(&rx_ring->idr_lock);
+	idr_remove(&rx_ring->bufs_idr, buf_id);
+	spin_unlock_bh(&rx_ring->idr_lock);
+fail_dma_unmap:
+	dma_unmap_single(ab->dev, paddr, skb->len + skb_tailroom(skb),
+			 DMA_FROM_DEVICE);
+fail_free_skb:
+	dev_kfree_skb_any(skb);
+
+	ath12k_hal_srng_access_end(ab, srng);
+
+	spin_unlock_bh(&srng->lock);
+
+	return req_entries - num_remain;
+}
+
 static struct dp_mon_tx_ppdu_info *
 ath12k_dp_mon_tx_get_ppdu_info(struct ath12k_mon_data *pmon,
 			       unsigned int ppdu_id,
@@ -2838,16 +3346,13 @@ ath12k_dp_mon_tx_process_ppdu_info(struct ath12k *ar,
 				   struct dp_mon_tx_ppdu_info *tx_ppdu_info)
 {
 	struct dp_mon_mpdu *tmp, *mon_mpdu;
-	struct sk_buff *head_msdu, *tail_msdu;
 
 	list_for_each_entry_safe(mon_mpdu, tmp,
 				 &tx_ppdu_info->dp_tx_mon_mpdu_list, list) {
 		list_del(&mon_mpdu->list);
-		head_msdu = mon_mpdu->head;
-		tail_msdu = mon_mpdu->tail;
 
-		if (head_msdu)
-			ath12k_dp_mon_rx_deliver(ar, head_msdu, tail_msdu,
+		if (mon_mpdu->head)
+			ath12k_dp_mon_rx_deliver(ar, mon_mpdu,
 						 &tx_ppdu_info->rx_status, napi);
 
 		kfree(mon_mpdu);
@@ -2949,11 +3454,10 @@ static void ath12k_dp_mon_rx_update_peer_su_stats(struct ath12k *ar,
 	struct ath12k_rx_peer_stats *rx_stats = arsta->rx_stats;
 	u32 num_msdu;
 
-	if (!rx_stats)
-		return;
-
 	arsta->rssi_comb = ppdu_info->rssi_comb;
 	ewma_avg_rssi_add(&arsta->avg_rssi, ppdu_info->rssi_comb);
+	if (!rx_stats)
+		return;
 
 	num_msdu = ppdu_info->tcp_msdu_count + ppdu_info->tcp_ack_msdu_count +
 		   ppdu_info->udp_msdu_count + ppdu_info->other_msdu_count;
@@ -3126,14 +3630,12 @@ ath12k_dp_mon_rx_update_user_stats(struct ath12k *ar,
 
 	ahsta = ath12k_sta_to_ahsta(peer->sta);
 	arsta = &ahsta->deflink;
+	arsta->rssi_comb = ppdu_info->rssi_comb;
+	ewma_avg_rssi_add(&arsta->avg_rssi, ppdu_info->rssi_comb);
 	rx_stats = arsta->rx_stats;
-
 	if (!rx_stats)
 		return;
 
-	arsta->rssi_comb = ppdu_info->rssi_comb;
-	ewma_avg_rssi_add(&arsta->avg_rssi, ppdu_info->rssi_comb);
-
 	num_msdu = user_stats->tcp_msdu_count + user_stats->tcp_ack_msdu_count +
 		   user_stats->udp_msdu_count + user_stats->other_msdu_count;
 
@@ -3346,7 +3848,7 @@ move_next:
 		ath12k_dp_mon_rx_memset_ppdu_info(ppdu_info);
 
 	while ((skb = __skb_dequeue(&skb_list))) {
-		hal_status = ath12k_dp_mon_parse_rx_dest(ar, pmon, skb);
+		hal_status = ath12k_dp_mon_rx_parse_mon_status(ar, pmon, skb, napi);
 		if (hal_status != HAL_RX_MON_STATUS_PPDU_DONE) {
 			ppdu_info->ppdu_continuation = true;
 			dev_kfree_skb_any(skb);
@@ -3388,6 +3890,487 @@ free_skb:
 	return num_buffs_reaped;
 }
 
+static int ath12k_dp_rx_reap_mon_status_ring(struct ath12k_base *ab, int mac_id,
+					     int *budget, struct sk_buff_head *skb_list)
+{
+	const struct ath12k_hw_hal_params *hal_params;
+	int buf_id, srng_id, num_buffs_reaped = 0;
+	enum dp_mon_status_buf_state reap_status;
+	struct dp_rxdma_mon_ring *rx_ring;
+	struct ath12k_mon_data *pmon;
+	struct ath12k_skb_rxcb *rxcb;
+	struct hal_tlv_64_hdr *tlv;
+	void *rx_mon_status_desc;
+	struct hal_srng *srng;
+	struct ath12k_dp *dp;
+	struct sk_buff *skb;
+	struct ath12k *ar;
+	dma_addr_t paddr;
+	u32 cookie;
+	u8 rbm;
+
+	ar = ab->pdevs[ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id)].ar;
+	dp = &ab->dp;
+	pmon = &ar->dp.mon_data;
+	srng_id = ath12k_hw_mac_id_to_srng_id(ab->hw_params, mac_id);
+	rx_ring = &dp->rx_mon_status_refill_ring[srng_id];
+
+	srng = &ab->hal.srng_list[rx_ring->refill_buf_ring.ring_id];
+
+	spin_lock_bh(&srng->lock);
+
+	ath12k_hal_srng_access_begin(ab, srng);
+
+	while (*budget) {
+		*budget -= 1;
+		rx_mon_status_desc = ath12k_hal_srng_src_peek(ab, srng);
+		if (!rx_mon_status_desc) {
+			pmon->buf_state = DP_MON_STATUS_REPLINISH;
+			break;
+		}
+		ath12k_hal_rx_buf_addr_info_get(rx_mon_status_desc, &paddr,
+						&cookie, &rbm);
+		if (paddr) {
+			buf_id = u32_get_bits(cookie, DP_RXDMA_BUF_COOKIE_BUF_ID);
+
+			spin_lock_bh(&rx_ring->idr_lock);
+			skb = idr_find(&rx_ring->bufs_idr, buf_id);
+			spin_unlock_bh(&rx_ring->idr_lock);
+
+			if (!skb) {
+				ath12k_warn(ab, "rx monitor status with invalid buf_id %d\n",
+					    buf_id);
+				pmon->buf_state = DP_MON_STATUS_REPLINISH;
+				goto move_next;
+			}
+
+			rxcb = ATH12K_SKB_RXCB(skb);
+
+			dma_sync_single_for_cpu(ab->dev, rxcb->paddr,
+						skb->len + skb_tailroom(skb),
+						DMA_FROM_DEVICE);
+
+			tlv = (struct hal_tlv_64_hdr *)skb->data;
+			if (le64_get_bits(tlv->tl, HAL_TLV_HDR_TAG) !=
+					HAL_RX_STATUS_BUFFER_DONE) {
+				pmon->buf_state = DP_MON_STATUS_NO_DMA;
+				ath12k_warn(ab,
+					    "mon status DONE not set %llx, buf_id %d\n",
+					    le64_get_bits(tlv->tl, HAL_TLV_HDR_TAG),
+					    buf_id);
+				/* RxDMA status done bit might not be set even
+				 * though tp is moved by HW.
+				 */
+
+				/* If done status is missing:
+				 * 1. As per MAC team's suggestion,
+				 *    when HP + 1 entry is peeked and if DMA
+				 *    is not done and if HP + 2 entry's DMA done
+				 *    is set. skip HP + 1 entry and
+				 *    start processing in next interrupt.
+				 * 2. If HP + 2 entry's DMA done is not set,
+				 *    poll onto HP + 1 entry DMA done to be set.
+				 *    Check status for same buffer for next time
+				 *    dp_rx_mon_status_srng_process
+				 */
+				reap_status = ath12k_dp_rx_mon_buf_done(ab, srng,
+									rx_ring);
+				if (reap_status == DP_MON_STATUS_NO_DMA)
+					continue;
+
+				spin_lock_bh(&rx_ring->idr_lock);
+				idr_remove(&rx_ring->bufs_idr, buf_id);
+				spin_unlock_bh(&rx_ring->idr_lock);
+
+				dma_unmap_single(ab->dev, rxcb->paddr,
+						 skb->len + skb_tailroom(skb),
+						 DMA_FROM_DEVICE);
+
+				dev_kfree_skb_any(skb);
+				pmon->buf_state = DP_MON_STATUS_REPLINISH;
+				goto move_next;
+			}
+
+			spin_lock_bh(&rx_ring->idr_lock);
+			idr_remove(&rx_ring->bufs_idr, buf_id);
+			spin_unlock_bh(&rx_ring->idr_lock);
+
+			dma_unmap_single(ab->dev, rxcb->paddr,
+					 skb->len + skb_tailroom(skb),
+					 DMA_FROM_DEVICE);
+
+			if (ath12k_dp_pkt_set_pktlen(skb, RX_MON_STATUS_BUF_SIZE)) {
+				dev_kfree_skb_any(skb);
+				goto move_next;
+			}
+			__skb_queue_tail(skb_list, skb);
+		} else {
+			pmon->buf_state = DP_MON_STATUS_REPLINISH;
+		}
+move_next:
+		skb = ath12k_dp_rx_alloc_mon_status_buf(ab, rx_ring,
+							&buf_id);
+
+		if (!skb) {
+			ath12k_warn(ab, "failed to alloc buffer for status ring\n");
+			hal_params = ab->hw_params->hal_params;
+			ath12k_hal_rx_buf_addr_info_set(rx_mon_status_desc, 0, 0,
+							hal_params->rx_buf_rbm);
+			num_buffs_reaped++;
+			break;
+		}
+		rxcb = ATH12K_SKB_RXCB(skb);
+
+		cookie = u32_encode_bits(mac_id, DP_RXDMA_BUF_COOKIE_PDEV_ID) |
+			 u32_encode_bits(buf_id, DP_RXDMA_BUF_COOKIE_BUF_ID);
+
+		ath12k_hal_rx_buf_addr_info_set(rx_mon_status_desc, rxcb->paddr,
+						cookie,
+						ab->hw_params->hal_params->rx_buf_rbm);
+		ath12k_hal_srng_src_get_next_entry(ab, srng);
+		num_buffs_reaped++;
+	}
+	ath12k_hal_srng_access_end(ab, srng);
+	spin_unlock_bh(&srng->lock);
+
+	return num_buffs_reaped;
+}
+
+static u32
+ath12k_dp_rx_mon_mpdu_pop(struct ath12k *ar, int mac_id,
+			  void *ring_entry, struct sk_buff **head_msdu,
+			  struct sk_buff **tail_msdu,
+			  struct list_head *used_list,
+			  u32 *npackets, u32 *ppdu_id)
+{
+	struct ath12k_mon_data *pmon = (struct ath12k_mon_data *)&ar->dp.mon_data;
+	struct ath12k_buffer_addr *p_buf_addr_info, *p_last_buf_addr_info;
+	u32 msdu_ppdu_id = 0, msdu_cnt = 0, total_len = 0, frag_len = 0;
+	u32 rx_buf_size, rx_pkt_offset, sw_cookie;
+	bool is_frag, is_first_msdu, drop_mpdu = false;
+	struct hal_reo_entrance_ring *ent_desc =
+		(struct hal_reo_entrance_ring *)ring_entry;
+	u32 rx_bufs_used = 0, i = 0, desc_bank = 0;
+	struct hal_rx_desc *rx_desc, *tail_rx_desc;
+	struct hal_rx_msdu_link *msdu_link_desc;
+	struct sk_buff *msdu = NULL, *last = NULL;
+	struct ath12k_rx_desc_info *desc_info;
+	struct ath12k_buffer_addr buf_info;
+	struct hal_rx_msdu_list msdu_list;
+	struct ath12k_skb_rxcb *rxcb;
+	u16 num_msdus = 0;
+	dma_addr_t paddr;
+	u8 rbm;
+
+	ath12k_hal_rx_reo_ent_buf_paddr_get(ring_entry, &paddr,
+					    &sw_cookie,
+					    &p_last_buf_addr_info, &rbm,
+					    &msdu_cnt);
+
+	spin_lock_bh(&pmon->mon_lock);
+
+	if (le32_get_bits(ent_desc->info1,
+			  HAL_REO_ENTR_RING_INFO1_RXDMA_PUSH_REASON) ==
+			  HAL_REO_DEST_RING_PUSH_REASON_ERR_DETECTED) {
+		u8 rxdma_err = le32_get_bits(ent_desc->info1,
+					     HAL_REO_ENTR_RING_INFO1_RXDMA_ERROR_CODE);
+		if (rxdma_err == HAL_REO_ENTR_RING_RXDMA_ECODE_FLUSH_REQUEST_ERR ||
+		    rxdma_err == HAL_REO_ENTR_RING_RXDMA_ECODE_MPDU_LEN_ERR ||
+		    rxdma_err == HAL_REO_ENTR_RING_RXDMA_ECODE_OVERFLOW_ERR) {
+			drop_mpdu = true;
+			pmon->rx_mon_stats.dest_mpdu_drop++;
+		}
+	}
+
+	is_frag = false;
+	is_first_msdu = true;
+	rx_pkt_offset = sizeof(struct hal_rx_desc);
+
+	do {
+		if (pmon->mon_last_linkdesc_paddr == paddr) {
+			pmon->rx_mon_stats.dup_mon_linkdesc_cnt++;
+			spin_unlock_bh(&pmon->mon_lock);
+			return rx_bufs_used;
+		}
+
+		desc_bank = u32_get_bits(sw_cookie, DP_LINK_DESC_BANK_MASK);
+		msdu_link_desc =
+			ar->ab->dp.link_desc_banks[desc_bank].vaddr +
+			(paddr - ar->ab->dp.link_desc_banks[desc_bank].paddr);
+
+		ath12k_hal_rx_msdu_list_get(ar, msdu_link_desc, &msdu_list,
+					    &num_msdus);
+		desc_info = ath12k_dp_get_rx_desc(ar->ab,
+						  msdu_list.sw_cookie[num_msdus - 1]);
+		tail_rx_desc = (struct hal_rx_desc *)(desc_info->skb)->data;
+
+		for (i = 0; i < num_msdus; i++) {
+			u32 l2_hdr_offset;
+
+			if (pmon->mon_last_buf_cookie == msdu_list.sw_cookie[i]) {
+				ath12k_dbg(ar->ab, ATH12K_DBG_DATA,
+					   "i %d last_cookie %d is same\n",
+					   i, pmon->mon_last_buf_cookie);
+				drop_mpdu = true;
+				pmon->rx_mon_stats.dup_mon_buf_cnt++;
+				continue;
+			}
+
+			desc_info =
+				ath12k_dp_get_rx_desc(ar->ab, msdu_list.sw_cookie[i]);
+			msdu = desc_info->skb;
+
+			if (!msdu) {
+				ath12k_dbg(ar->ab, ATH12K_DBG_DATA,
+					   "msdu_pop: invalid msdu (%d/%d)\n",
+					   i + 1, num_msdus);
+				goto next_msdu;
+			}
+			rxcb = ATH12K_SKB_RXCB(msdu);
+			if (rxcb->paddr != msdu_list.paddr[i]) {
+				ath12k_dbg(ar->ab, ATH12K_DBG_DATA,
+					   "i %d paddr %lx != %lx\n",
+					   i, (unsigned long)rxcb->paddr,
+					   (unsigned long)msdu_list.paddr[i]);
+				drop_mpdu = true;
+				continue;
+			}
+			if (!rxcb->unmapped) {
+				dma_unmap_single(ar->ab->dev, rxcb->paddr,
+						 msdu->len +
+						 skb_tailroom(msdu),
+						 DMA_FROM_DEVICE);
+				rxcb->unmapped = 1;
+			}
+			if (drop_mpdu) {
+				ath12k_dbg(ar->ab, ATH12K_DBG_DATA,
+					   "i %d drop msdu %p *ppdu_id %x\n",
+					   i, msdu, *ppdu_id);
+				dev_kfree_skb_any(msdu);
+				msdu = NULL;
+				goto next_msdu;
+			}
+
+			rx_desc = (struct hal_rx_desc *)msdu->data;
+			l2_hdr_offset = ath12k_dp_rx_h_l3pad(ar->ab, tail_rx_desc);
+			if (is_first_msdu) {
+				if (!ath12k_dp_rxdesc_mpdu_valid(ar->ab, rx_desc)) {
+					drop_mpdu = true;
+					dev_kfree_skb_any(msdu);
+					msdu = NULL;
+					pmon->mon_last_linkdesc_paddr = paddr;
+					goto next_msdu;
+				}
+				msdu_ppdu_id =
+					ath12k_dp_rxdesc_get_ppduid(ar->ab, rx_desc);
+
+				if (ath12k_dp_mon_comp_ppduid(msdu_ppdu_id,
+							      ppdu_id)) {
+					spin_unlock_bh(&pmon->mon_lock);
+					return rx_bufs_used;
+				}
+				pmon->mon_last_linkdesc_paddr = paddr;
+				is_first_msdu = false;
+			}
+			ath12k_dp_mon_get_buf_len(&msdu_list.msdu_info[i],
+						  &is_frag, &total_len,
+						  &frag_len, &msdu_cnt);
+			rx_buf_size = rx_pkt_offset + l2_hdr_offset + frag_len;
+
+			if (ath12k_dp_pkt_set_pktlen(msdu, rx_buf_size)) {
+				dev_kfree_skb_any(msdu);
+				goto next_msdu;
+			}
+
+			if (!(*head_msdu))
+				*head_msdu = msdu;
+			else if (last)
+				last->next = msdu;
+
+			last = msdu;
+next_msdu:
+			pmon->mon_last_buf_cookie = msdu_list.sw_cookie[i];
+			rx_bufs_used++;
+			desc_info->skb = NULL;
+			list_add_tail(&desc_info->list, used_list);
+		}
+
+		ath12k_hal_rx_buf_addr_info_set(&buf_info, paddr, sw_cookie, rbm);
+
+		ath12k_dp_mon_next_link_desc_get(msdu_link_desc, &paddr,
+						 &sw_cookie, &rbm,
+						 &p_buf_addr_info);
+
+		ath12k_dp_rx_link_desc_return(ar->ab, &buf_info,
+					      HAL_WBM_REL_BM_ACT_PUT_IN_IDLE);
+
+		p_last_buf_addr_info = p_buf_addr_info;
+
+	} while (paddr && msdu_cnt);
+
+	spin_unlock_bh(&pmon->mon_lock);
+
+	if (last)
+		last->next = NULL;
+
+	*tail_msdu = msdu;
+
+	if (msdu_cnt == 0)
+		*npackets = 1;
+
+	return rx_bufs_used;
+}
+
+/* The destination ring processing is stuck if the destination is not
+ * moving while status ring moves 16 PPDU. The destination ring processing
+ * skips this destination ring PPDU as a workaround.
+ */
+#define MON_DEST_RING_STUCK_MAX_CNT 16
+
+static void ath12k_dp_rx_mon_dest_process(struct ath12k *ar, int mac_id,
+					  u32 quota, struct napi_struct *napi)
+{
+	struct ath12k_mon_data *pmon = (struct ath12k_mon_data *)&ar->dp.mon_data;
+	struct ath12k_pdev_mon_stats *rx_mon_stats;
+	u32 ppdu_id, rx_bufs_used = 0, ring_id;
+	u32 mpdu_rx_bufs_used, npackets = 0;
+	struct ath12k_dp *dp = &ar->ab->dp;
+	struct ath12k_base *ab = ar->ab;
+	void *ring_entry, *mon_dst_srng;
+	struct dp_mon_mpdu *tmp_mpdu;
+	LIST_HEAD(rx_desc_used_list);
+	struct hal_srng *srng;
+
+	ring_id = dp->rxdma_err_dst_ring[mac_id].ring_id;
+	srng = &ab->hal.srng_list[ring_id];
+
+	mon_dst_srng = &ab->hal.srng_list[ring_id];
+
+	spin_lock_bh(&srng->lock);
+
+	ath12k_hal_srng_access_begin(ab, mon_dst_srng);
+
+	ppdu_id = pmon->mon_ppdu_info.ppdu_id;
+	rx_mon_stats = &pmon->rx_mon_stats;
+
+	while ((ring_entry = ath12k_hal_srng_dst_peek(ar->ab, mon_dst_srng))) {
+		struct sk_buff *head_msdu, *tail_msdu;
+
+		head_msdu = NULL;
+		tail_msdu = NULL;
+
+		mpdu_rx_bufs_used = ath12k_dp_rx_mon_mpdu_pop(ar, mac_id, ring_entry,
+							      &head_msdu, &tail_msdu,
+							      &rx_desc_used_list,
+							      &npackets, &ppdu_id);
+
+		rx_bufs_used += mpdu_rx_bufs_used;
+
+		if (mpdu_rx_bufs_used) {
+			dp->mon_dest_ring_stuck_cnt = 0;
+		} else {
+			dp->mon_dest_ring_stuck_cnt++;
+			rx_mon_stats->dest_mon_not_reaped++;
+		}
+
+		if (dp->mon_dest_ring_stuck_cnt > MON_DEST_RING_STUCK_MAX_CNT) {
+			rx_mon_stats->dest_mon_stuck++;
+			ath12k_dbg(ar->ab, ATH12K_DBG_DATA,
+				   "status ring ppdu_id=%d dest ring ppdu_id=%d mon_dest_ring_stuck_cnt=%d dest_mon_not_reaped=%u dest_mon_stuck=%u\n",
+				   pmon->mon_ppdu_info.ppdu_id, ppdu_id,
+				   dp->mon_dest_ring_stuck_cnt,
+				   rx_mon_stats->dest_mon_not_reaped,
+				   rx_mon_stats->dest_mon_stuck);
+			spin_lock_bh(&pmon->mon_lock);
+			pmon->mon_ppdu_info.ppdu_id = ppdu_id;
+			spin_unlock_bh(&pmon->mon_lock);
+			continue;
+		}
+
+		if (ppdu_id != pmon->mon_ppdu_info.ppdu_id) {
+			spin_lock_bh(&pmon->mon_lock);
+			pmon->mon_ppdu_status = DP_PPDU_STATUS_START;
+			spin_unlock_bh(&pmon->mon_lock);
+			ath12k_dbg(ar->ab, ATH12K_DBG_DATA,
+				   "dest_rx: new ppdu_id %x != status ppdu_id %x dest_mon_not_reaped = %u dest_mon_stuck = %u\n",
+				   ppdu_id, pmon->mon_ppdu_info.ppdu_id,
+				   rx_mon_stats->dest_mon_not_reaped,
+				   rx_mon_stats->dest_mon_stuck);
+			break;
+		}
+
+		if (head_msdu && tail_msdu) {
+			tmp_mpdu = kzalloc(sizeof(*tmp_mpdu), GFP_ATOMIC);
+			if (!tmp_mpdu)
+				break;
+
+			tmp_mpdu->head = head_msdu;
+			tmp_mpdu->tail = tail_msdu;
+			tmp_mpdu->err_bitmap = pmon->err_bitmap;
+			tmp_mpdu->decap_format = pmon->decap_format;
+			ath12k_dp_mon_rx_deliver(ar, tmp_mpdu,
+						 &pmon->mon_ppdu_info, napi);
+			rx_mon_stats->dest_mpdu_done++;
+			kfree(tmp_mpdu);
+		}
+
+		ring_entry = ath12k_hal_srng_dst_get_next_entry(ar->ab,
+								mon_dst_srng);
+	}
+	ath12k_hal_srng_access_end(ar->ab, mon_dst_srng);
+
+	spin_unlock_bh(&srng->lock);
+
+	if (rx_bufs_used) {
+		rx_mon_stats->dest_ppdu_done++;
+		ath12k_dp_rx_bufs_replenish(ar->ab,
+					    &dp->rx_refill_buf_ring,
+					    &rx_desc_used_list,
+					    rx_bufs_used);
+	}
+}
+
+static int
+__ath12k_dp_mon_process_ring(struct ath12k *ar, int mac_id,
+			     struct napi_struct *napi, int *budget)
+{
+	struct ath12k_mon_data *pmon = (struct ath12k_mon_data *)&ar->dp.mon_data;
+	struct ath12k_pdev_mon_stats *rx_mon_stats = &pmon->rx_mon_stats;
+	struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info;
+	enum hal_rx_mon_status hal_status;
+	struct sk_buff_head skb_list;
+	int num_buffs_reaped;
+	struct sk_buff *skb;
+
+	__skb_queue_head_init(&skb_list);
+
+	num_buffs_reaped = ath12k_dp_rx_reap_mon_status_ring(ar->ab, mac_id,
+							     budget, &skb_list);
+	if (!num_buffs_reaped)
+		goto exit;
+
+	while ((skb = __skb_dequeue(&skb_list))) {
+		memset(ppdu_info, 0, sizeof(*ppdu_info));
+		ppdu_info->peer_id = HAL_INVALID_PEERID;
+
+		hal_status = ath12k_dp_mon_parse_rx_dest(ar, pmon, skb);
+
+		if (ar->monitor_started &&
+		    pmon->mon_ppdu_status == DP_PPDU_STATUS_START &&
+		    hal_status == HAL_TLV_STATUS_PPDU_DONE) {
+			rx_mon_stats->status_ppdu_done++;
+			pmon->mon_ppdu_status = DP_PPDU_STATUS_DONE;
+			ath12k_dp_rx_mon_dest_process(ar, mac_id, *budget, napi);
+			pmon->mon_ppdu_status = DP_PPDU_STATUS_START;
+		}
+
+		dev_kfree_skb_any(skb);
+	}
+
+exit:
+	return num_buffs_reaped;
+}
+
 int ath12k_dp_mon_process_ring(struct ath12k_base *ab, int mac_id,
 			       struct napi_struct *napi, int budget,
 			       enum dp_monitor_mode monitor_mode)
@@ -3398,6 +4381,10 @@ int ath12k_dp_mon_process_ring(struct ath12k_base *ab, int mac_id,
 	if (ab->hw_params->rxdma1_enable) {
 		if (monitor_mode == ATH12K_DP_RX_MONITOR_MODE)
 			num_buffs_reaped = ath12k_dp_mon_srng_process(ar, &budget, napi);
+	} else {
+		if (ar->monitor_started)
+			num_buffs_reaped =
+				__ath12k_dp_mon_process_ring(ar, mac_id, napi, &budget);
 	}
 
 	return num_buffs_reaped;
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.h b/drivers/net/wireless/ath/ath12k/dp_mon.h
index e4368eb42aca..e25595cbdcf3 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.h
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_DP_MON_H
@@ -9,6 +9,9 @@
 
 #include "core.h"
 
+#define ATH12K_MON_RX_DOT11_OFFSET	5
+#define ATH12K_MON_RX_PKT_OFFSET	8
+
 enum dp_monitor_mode {
 	ATH12K_DP_TX_MONITOR_MODE,
 	ATH12K_DP_RX_MONITOR_MODE
@@ -82,6 +85,9 @@ ath12k_dp_mon_rx_parse_mon_status(struct ath12k *ar,
 int ath12k_dp_mon_buf_replenish(struct ath12k_base *ab,
 				struct dp_rxdma_mon_ring *buf_ring,
 				int req_entries);
+int ath12k_dp_mon_status_bufs_replenish(struct ath12k_base *ab,
+					struct dp_rxdma_mon_ring *rx_ring,
+					int req_entries);
 int ath12k_dp_mon_process_ring(struct ath12k_base *ab, int mac_id,
 			       struct napi_struct *napi, int budget,
 			       enum dp_monitor_mode monitor_mode);
diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 75bf4211ad42..7e1a8f29c7b6 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -194,6 +194,22 @@ static void ath12k_dp_rxdesc_set_msdu_len(struct ath12k_base *ab,
 	ab->hal_rx_ops->rx_desc_set_msdu_len(desc, len);
 }
 
+u32 ath12k_dp_rxdesc_get_ppduid(struct ath12k_base *ab,
+				struct hal_rx_desc *rx_desc)
+{
+	return ab->hal_rx_ops->rx_desc_get_mpdu_ppdu_id(rx_desc);
+}
+
+bool ath12k_dp_rxdesc_mpdu_valid(struct ath12k_base *ab,
+				 struct hal_rx_desc *rx_desc)
+{
+	u32 tlv_tag;
+
+	tlv_tag = ab->hal_rx_ops->rx_desc_get_mpdu_start_tag(rx_desc);
+
+	return tlv_tag == HAL_RX_MPDU_START;
+}
+
 static bool ath12k_dp_rx_h_is_da_mcbc(struct ath12k_base *ab,
 				      struct hal_rx_desc *desc)
 {
@@ -228,12 +244,6 @@ static void ath12k_dp_rx_desc_get_crypto_header(struct ath12k_base *ab,
 	ab->hal_rx_ops->rx_desc_get_crypto_header(desc, crypto_hdr, enctype);
 }
 
-static u16 ath12k_dp_rxdesc_get_mpdu_frame_ctrl(struct ath12k_base *ab,
-						struct hal_rx_desc *desc)
-{
-	return ab->hal_rx_ops->rx_desc_get_mpdu_frame_ctl(desc);
-}
-
 static inline u8 ath12k_dp_rx_get_msdu_src_link(struct ath12k_base *ab,
 						struct hal_rx_desc *desc)
 {
@@ -420,9 +430,17 @@ static int ath12k_dp_rxdma_mon_buf_ring_free(struct ath12k_base *ab,
 static int ath12k_dp_rxdma_buf_free(struct ath12k_base *ab)
 {
 	struct ath12k_dp *dp = &ab->dp;
+	int i;
 
 	ath12k_dp_rxdma_mon_buf_ring_free(ab, &dp->rxdma_mon_buf_ring);
 
+	if (ab->hw_params->rxdma1_enable)
+		return 0;
+
+	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++)
+		ath12k_dp_rxdma_mon_buf_ring_free(ab,
+						  &dp->rx_mon_status_refill_ring[i]);
+
 	return 0;
 }
 
@@ -436,7 +454,12 @@ static int ath12k_dp_rxdma_mon_ring_buf_setup(struct ath12k_base *ab,
 		ath12k_hal_srng_get_entrysize(ab, ringtype);
 
 	rx_ring->bufs_max = num_entries;
-	ath12k_dp_mon_buf_replenish(ab, rx_ring, num_entries);
+
+	if (ringtype == HAL_RXDMA_MONITOR_STATUS)
+		ath12k_dp_mon_status_bufs_replenish(ab, rx_ring,
+						    num_entries);
+	else
+		ath12k_dp_mon_buf_replenish(ab, rx_ring, num_entries);
 
 	return 0;
 }
@@ -457,7 +480,8 @@ static int ath12k_dp_rxdma_ring_buf_setup(struct ath12k_base *ab,
 static int ath12k_dp_rxdma_buf_setup(struct ath12k_base *ab)
 {
 	struct ath12k_dp *dp = &ab->dp;
-	int ret;
+	struct dp_rxdma_mon_ring *mon_ring;
+	int ret, i;
 
 	ret = ath12k_dp_rxdma_ring_buf_setup(ab, &dp->rx_refill_buf_ring);
 	if (ret) {
@@ -470,9 +494,19 @@ static int ath12k_dp_rxdma_buf_setup(struct ath12k_base *ab)
 		ret = ath12k_dp_rxdma_mon_ring_buf_setup(ab,
 							 &dp->rxdma_mon_buf_ring,
 							 HAL_RXDMA_MONITOR_BUF);
-		if (ret) {
+		if (ret)
 			ath12k_warn(ab,
 				    "failed to setup HAL_RXDMA_MONITOR_BUF\n");
+		return ret;
+	}
+
+	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
+		mon_ring = &dp->rx_mon_status_refill_ring[i];
+		ret = ath12k_dp_rxdma_mon_ring_buf_setup(ab, mon_ring,
+							 HAL_RXDMA_MONITOR_STATUS);
+		if (ret) {
+			ath12k_warn(ab,
+				    "failed to setup HAL_RXDMA_MONITOR_STATUS\n");
 			return ret;
 		}
 	}
@@ -556,9 +590,9 @@ void ath12k_dp_rx_reo_cmd_list_cleanup(struct ath12k_base *ab)
 	spin_lock_bh(&dp->reo_cmd_lock);
 	list_for_each_entry_safe(cmd, tmp, &dp->reo_cmd_list, list) {
 		list_del(&cmd->list);
-		dma_unmap_single(ab->dev, cmd->data.paddr,
-				 cmd->data.size, DMA_BIDIRECTIONAL);
-		kfree(cmd->data.vaddr);
+		dma_unmap_single(ab->dev, cmd->data.qbuf.paddr_aligned,
+				 cmd->data.qbuf.size, DMA_BIDIRECTIONAL);
+		kfree(cmd->data.qbuf.vaddr);
 		kfree(cmd);
 	}
 
@@ -566,9 +600,9 @@ void ath12k_dp_rx_reo_cmd_list_cleanup(struct ath12k_base *ab)
 				 &dp->reo_cmd_cache_flush_list, list) {
 		list_del(&cmd_cache->list);
 		dp->reo_cmd_cache_flush_count--;
-		dma_unmap_single(ab->dev, cmd_cache->data.paddr,
-				 cmd_cache->data.size, DMA_BIDIRECTIONAL);
-		kfree(cmd_cache->data.vaddr);
+		dma_unmap_single(ab->dev, cmd_cache->data.qbuf.paddr_aligned,
+				 cmd_cache->data.qbuf.size, DMA_BIDIRECTIONAL);
+		kfree(cmd_cache->data.qbuf.vaddr);
 		kfree(cmd_cache);
 	}
 	spin_unlock_bh(&dp->reo_cmd_lock);
@@ -583,10 +617,10 @@ static void ath12k_dp_reo_cmd_free(struct ath12k_dp *dp, void *ctx,
 		ath12k_warn(dp->ab, "failed to flush rx tid hw desc, tid %d status %d\n",
 			    rx_tid->tid, status);
 
-	dma_unmap_single(dp->ab->dev, rx_tid->paddr, rx_tid->size,
+	dma_unmap_single(dp->ab->dev, rx_tid->qbuf.paddr_aligned, rx_tid->qbuf.size,
 			 DMA_BIDIRECTIONAL);
-	kfree(rx_tid->vaddr);
-	rx_tid->vaddr = NULL;
+	kfree(rx_tid->qbuf.vaddr);
+	rx_tid->qbuf.vaddr = NULL;
 }
 
 static int ath12k_dp_reo_cmd_send(struct ath12k_base *ab, struct ath12k_dp_rx_tid *rx_tid,
@@ -641,13 +675,13 @@ static void ath12k_dp_reo_cache_flush(struct ath12k_base *ab,
 	unsigned long tot_desc_sz, desc_sz;
 	int ret;
 
-	tot_desc_sz = rx_tid->size;
+	tot_desc_sz = rx_tid->qbuf.size;
 	desc_sz = ath12k_hal_reo_qdesc_size(0, HAL_DESC_REO_NON_QOS_TID);
 
 	while (tot_desc_sz > desc_sz) {
 		tot_desc_sz -= desc_sz;
-		cmd.addr_lo = lower_32_bits(rx_tid->paddr + tot_desc_sz);
-		cmd.addr_hi = upper_32_bits(rx_tid->paddr);
+		cmd.addr_lo = lower_32_bits(rx_tid->qbuf.paddr_aligned + tot_desc_sz);
+		cmd.addr_hi = upper_32_bits(rx_tid->qbuf.paddr_aligned);
 		ret = ath12k_dp_reo_cmd_send(ab, rx_tid,
 					     HAL_REO_CMD_FLUSH_CACHE, &cmd,
 					     NULL);
@@ -658,8 +692,8 @@ static void ath12k_dp_reo_cache_flush(struct ath12k_base *ab,
 	}
 
 	memset(&cmd, 0, sizeof(cmd));
-	cmd.addr_lo = lower_32_bits(rx_tid->paddr);
-	cmd.addr_hi = upper_32_bits(rx_tid->paddr);
+	cmd.addr_lo = lower_32_bits(rx_tid->qbuf.paddr_aligned);
+	cmd.addr_hi = upper_32_bits(rx_tid->qbuf.paddr_aligned);
 	cmd.flag = HAL_REO_CMD_FLG_NEED_STATUS;
 	ret = ath12k_dp_reo_cmd_send(ab, rx_tid,
 				     HAL_REO_CMD_FLUSH_CACHE,
@@ -667,10 +701,10 @@ static void ath12k_dp_reo_cache_flush(struct ath12k_base *ab,
 	if (ret) {
 		ath12k_err(ab, "failed to send HAL_REO_CMD_FLUSH_CACHE cmd, tid %d (%d)\n",
 			   rx_tid->tid, ret);
-		dma_unmap_single(ab->dev, rx_tid->paddr, rx_tid->size,
+		dma_unmap_single(ab->dev, rx_tid->qbuf.paddr_aligned, rx_tid->qbuf.size,
 				 DMA_BIDIRECTIONAL);
-		kfree(rx_tid->vaddr);
-		rx_tid->vaddr = NULL;
+		kfree(rx_tid->qbuf.vaddr);
+		rx_tid->qbuf.vaddr = NULL;
 	}
 }
 
@@ -729,10 +763,10 @@ static void ath12k_dp_rx_tid_del_func(struct ath12k_dp *dp, void *ctx,
 
 	return;
 free_desc:
-	dma_unmap_single(ab->dev, rx_tid->paddr, rx_tid->size,
+	dma_unmap_single(ab->dev, rx_tid->qbuf.paddr_aligned, rx_tid->qbuf.size,
 			 DMA_BIDIRECTIONAL);
-	kfree(rx_tid->vaddr);
-	rx_tid->vaddr = NULL;
+	kfree(rx_tid->qbuf.vaddr);
+	rx_tid->qbuf.vaddr = NULL;
 }
 
 static void ath12k_peer_rx_tid_qref_setup(struct ath12k_base *ab, u16 peer_id, u16 tid,
@@ -762,6 +796,7 @@ static void ath12k_peer_rx_tid_qref_setup(struct ath12k_base *ab, u16 peer_id, u
 	qref->info1 = u32_encode_bits(upper_32_bits(paddr),
 				      BUFFER_ADDR_INFO1_ADDR) |
 		      u32_encode_bits(tid, DP_REO_QREF_NUM);
+	ath12k_hal_reo_shared_qaddr_cache_clear(ab);
 }
 
 static void ath12k_peer_rx_tid_qref_reset(struct ath12k_base *ab, u16 peer_id, u16 tid)
@@ -801,8 +836,8 @@ void ath12k_dp_rx_peer_tid_delete(struct ath12k *ar,
 		return;
 
 	cmd.flag = HAL_REO_CMD_FLG_NEED_STATUS;
-	cmd.addr_lo = lower_32_bits(rx_tid->paddr);
-	cmd.addr_hi = upper_32_bits(rx_tid->paddr);
+	cmd.addr_lo = lower_32_bits(rx_tid->qbuf.paddr_aligned);
+	cmd.addr_hi = upper_32_bits(rx_tid->qbuf.paddr_aligned);
 	cmd.upd0 = HAL_REO_CMD_UPD0_VLD;
 	ret = ath12k_dp_reo_cmd_send(ar->ab, rx_tid,
 				     HAL_REO_CMD_UPDATE_RX_QUEUE, &cmd,
@@ -810,10 +845,10 @@ void ath12k_dp_rx_peer_tid_delete(struct ath12k *ar,
 	if (ret) {
 		ath12k_err(ar->ab, "failed to send HAL_REO_CMD_UPDATE_RX_QUEUE cmd, tid %d (%d)\n",
 			   tid, ret);
-		dma_unmap_single(ar->ab->dev, rx_tid->paddr, rx_tid->size,
-				 DMA_BIDIRECTIONAL);
-		kfree(rx_tid->vaddr);
-		rx_tid->vaddr = NULL;
+		dma_unmap_single(ar->ab->dev, rx_tid->qbuf.paddr_aligned,
+				 rx_tid->qbuf.size, DMA_BIDIRECTIONAL);
+		kfree(rx_tid->qbuf.vaddr);
+		rx_tid->qbuf.vaddr = NULL;
 	}
 
 	if (peer->mlo)
@@ -824,15 +859,10 @@ void ath12k_dp_rx_peer_tid_delete(struct ath12k *ar,
 	rx_tid->active = false;
 }
 
-/* TODO: it's strange (and ugly) that struct hal_reo_dest_ring is converted
- * to struct hal_wbm_release_ring, I couldn't figure out the logic behind
- * that.
- */
-static int ath12k_dp_rx_link_desc_return(struct ath12k_base *ab,
-					 struct hal_reo_dest_ring *ring,
-					 enum hal_wbm_rel_bm_act action)
+int ath12k_dp_rx_link_desc_return(struct ath12k_base *ab,
+				  struct ath12k_buffer_addr *buf_addr_info,
+				  enum hal_wbm_rel_bm_act action)
 {
-	struct hal_wbm_release_ring *link_desc = (struct hal_wbm_release_ring *)ring;
 	struct hal_wbm_release_ring *desc;
 	struct ath12k_dp *dp = &ab->dp;
 	struct hal_srng *srng;
@@ -850,7 +880,7 @@ static int ath12k_dp_rx_link_desc_return(struct ath12k_base *ab,
 		goto exit;
 	}
 
-	ath12k_hal_rx_msdu_link_desc_set(ab, desc, link_desc, action);
+	ath12k_hal_rx_msdu_link_desc_set(ab, desc, buf_addr_info, action);
 
 exit:
 	ath12k_hal_srng_access_end(ab, srng);
@@ -863,14 +893,17 @@ exit:
 static void ath12k_dp_rx_frags_cleanup(struct ath12k_dp_rx_tid *rx_tid,
 				       bool rel_link_desc)
 {
+	struct ath12k_buffer_addr *buf_addr_info;
 	struct ath12k_base *ab = rx_tid->ab;
 
 	lockdep_assert_held(&ab->base_lock);
 
 	if (rx_tid->dst_ring_desc) {
-		if (rel_link_desc)
-			ath12k_dp_rx_link_desc_return(ab, rx_tid->dst_ring_desc,
+		if (rel_link_desc) {
+			buf_addr_info = &rx_tid->dst_ring_desc->buf_addr_info;
+			ath12k_dp_rx_link_desc_return(ab, buf_addr_info,
 						      HAL_WBM_REL_BM_ACT_PUT_IN_IDLE);
+		}
 		kfree(rx_tid->dst_ring_desc);
 		rx_tid->dst_ring_desc = NULL;
 	}
@@ -909,8 +942,8 @@ static int ath12k_peer_rx_tid_reo_update(struct ath12k *ar,
 	struct ath12k_hal_reo_cmd cmd = {0};
 	int ret;
 
-	cmd.addr_lo = lower_32_bits(rx_tid->paddr);
-	cmd.addr_hi = upper_32_bits(rx_tid->paddr);
+	cmd.addr_lo = lower_32_bits(rx_tid->qbuf.paddr_aligned);
+	cmd.addr_hi = upper_32_bits(rx_tid->qbuf.paddr_aligned);
 	cmd.flag = HAL_REO_CMD_FLG_NEED_STATUS;
 	cmd.upd0 = HAL_REO_CMD_UPD0_BA_WINDOW_SIZE;
 	cmd.ba_window_size = ba_win_sz;
@@ -934,18 +967,67 @@ static int ath12k_peer_rx_tid_reo_update(struct ath12k *ar,
 	return 0;
 }
 
+static int ath12k_dp_rx_assign_reoq(struct ath12k_base *ab,
+				    struct ath12k_sta *ahsta,
+				    struct ath12k_dp_rx_tid *rx_tid,
+				    u16 ssn, enum hal_pn_type pn_type)
+{
+	u32 ba_win_sz = rx_tid->ba_win_sz;
+	struct ath12k_reoq_buf *buf;
+	void *vaddr, *vaddr_aligned;
+	dma_addr_t paddr_aligned;
+	u8 tid = rx_tid->tid;
+	u32 hw_desc_sz;
+	int ret;
+
+	buf = &ahsta->reoq_bufs[tid];
+	if (!buf->vaddr) {
+		/* TODO: Optimize the memory allocation for qos tid based on
+		 * the actual BA window size in REO tid update path.
+		 */
+		if (tid == HAL_DESC_REO_NON_QOS_TID)
+			hw_desc_sz = ath12k_hal_reo_qdesc_size(ba_win_sz, tid);
+		else
+			hw_desc_sz = ath12k_hal_reo_qdesc_size(DP_BA_WIN_SZ_MAX, tid);
+
+		vaddr = kzalloc(hw_desc_sz + HAL_LINK_DESC_ALIGN - 1, GFP_ATOMIC);
+		if (!vaddr)
+			return -ENOMEM;
+
+		vaddr_aligned = PTR_ALIGN(vaddr, HAL_LINK_DESC_ALIGN);
+
+		ath12k_hal_reo_qdesc_setup(vaddr_aligned, tid, ba_win_sz,
+					   ssn, pn_type);
+
+		paddr_aligned = dma_map_single(ab->dev, vaddr_aligned, hw_desc_sz,
+					       DMA_BIDIRECTIONAL);
+		ret = dma_mapping_error(ab->dev, paddr_aligned);
+		if (ret) {
+			kfree(vaddr);
+			return ret;
+		}
+
+		buf->vaddr = vaddr;
+		buf->paddr_aligned = paddr_aligned;
+		buf->size = hw_desc_sz;
+	}
+
+	rx_tid->qbuf = *buf;
+	rx_tid->active = true;
+
+	return 0;
+}
+
 int ath12k_dp_rx_peer_tid_setup(struct ath12k *ar, const u8 *peer_mac, int vdev_id,
 				u8 tid, u32 ba_win_sz, u16 ssn,
 				enum hal_pn_type pn_type)
 {
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_dp *dp = &ab->dp;
-	struct hal_rx_reo_queue *addr_aligned;
 	struct ath12k_peer *peer;
+	struct ath12k_sta *ahsta;
 	struct ath12k_dp_rx_tid *rx_tid;
-	u32 hw_desc_sz;
-	void *vaddr;
-	dma_addr_t paddr;
+	dma_addr_t paddr_aligned;
 	int ret;
 
 	spin_lock_bh(&ab->base_lock);
@@ -957,7 +1039,8 @@ int ath12k_dp_rx_peer_tid_setup(struct ath12k *ar, const u8 *peer_mac, int vdev_
 		return -ENOENT;
 	}
 
-	if (!peer->primary_link) {
+	if (ab->hw_params->dp_primary_link_only &&
+	    !peer->primary_link) {
 		spin_unlock_bh(&ab->base_lock);
 		return 0;
 	}
@@ -977,9 +1060,9 @@ int ath12k_dp_rx_peer_tid_setup(struct ath12k *ar, const u8 *peer_mac, int vdev_
 	}
 
 	rx_tid = &peer->rx_tid[tid];
+	paddr_aligned = rx_tid->qbuf.paddr_aligned;
 	/* Update the tid queue if it is already setup */
 	if (rx_tid->active) {
-		paddr = rx_tid->paddr;
 		ret = ath12k_peer_rx_tid_reo_update(ar, peer, rx_tid,
 						    ba_win_sz, ssn, true);
 		spin_unlock_bh(&ab->base_lock);
@@ -991,8 +1074,8 @@ int ath12k_dp_rx_peer_tid_setup(struct ath12k *ar, const u8 *peer_mac, int vdev_
 		if (!ab->hw_params->reoq_lut_support) {
 			ret = ath12k_wmi_peer_rx_reorder_queue_setup(ar, vdev_id,
 								     peer_mac,
-								     paddr, tid, 1,
-								     ba_win_sz);
+								     paddr_aligned, tid,
+								     1, ba_win_sz);
 			if (ret) {
 				ath12k_warn(ab, "failed to setup peer rx reorder queuefor tid %d: %d\n",
 					    tid, ret);
@@ -1007,61 +1090,34 @@ int ath12k_dp_rx_peer_tid_setup(struct ath12k *ar, const u8 *peer_mac, int vdev_
 
 	rx_tid->ba_win_sz = ba_win_sz;
 
-	/* TODO: Optimize the memory allocation for qos tid based on
-	 * the actual BA window size in REO tid update path.
-	 */
-	if (tid == HAL_DESC_REO_NON_QOS_TID)
-		hw_desc_sz = ath12k_hal_reo_qdesc_size(ba_win_sz, tid);
-	else
-		hw_desc_sz = ath12k_hal_reo_qdesc_size(DP_BA_WIN_SZ_MAX, tid);
-
-	vaddr = kzalloc(hw_desc_sz + HAL_LINK_DESC_ALIGN - 1, GFP_ATOMIC);
-	if (!vaddr) {
-		spin_unlock_bh(&ab->base_lock);
-		return -ENOMEM;
-	}
-
-	addr_aligned = PTR_ALIGN(vaddr, HAL_LINK_DESC_ALIGN);
-
-	ath12k_hal_reo_qdesc_setup(addr_aligned, tid, ba_win_sz,
-				   ssn, pn_type);
-
-	paddr = dma_map_single(ab->dev, addr_aligned, hw_desc_sz,
-			       DMA_BIDIRECTIONAL);
-
-	ret = dma_mapping_error(ab->dev, paddr);
+	ahsta = ath12k_sta_to_ahsta(peer->sta);
+	ret = ath12k_dp_rx_assign_reoq(ab, ahsta, rx_tid, ssn, pn_type);
 	if (ret) {
 		spin_unlock_bh(&ab->base_lock);
-		goto err_mem_free;
+		ath12k_warn(ab, "failed to assign reoq buf for rx tid %u\n", tid);
+		return ret;
 	}
 
-	rx_tid->vaddr = vaddr;
-	rx_tid->paddr = paddr;
-	rx_tid->size = hw_desc_sz;
-	rx_tid->active = true;
-
 	if (ab->hw_params->reoq_lut_support) {
 		/* Update the REO queue LUT at the corresponding peer id
 		 * and tid with qaddr.
 		 */
 		if (peer->mlo)
-			ath12k_peer_rx_tid_qref_setup(ab, peer->ml_id, tid, paddr);
+			ath12k_peer_rx_tid_qref_setup(ab, peer->ml_id, tid,
+						      paddr_aligned);
 		else
-			ath12k_peer_rx_tid_qref_setup(ab, peer->peer_id, tid, paddr);
+			ath12k_peer_rx_tid_qref_setup(ab, peer->peer_id, tid,
+						      paddr_aligned);
 
 		spin_unlock_bh(&ab->base_lock);
 	} else {
 		spin_unlock_bh(&ab->base_lock);
 		ret = ath12k_wmi_peer_rx_reorder_queue_setup(ar, vdev_id, peer_mac,
-							     paddr, tid, 1, ba_win_sz);
+							     paddr_aligned, tid, 1,
+							     ba_win_sz);
 	}
 
 	return ret;
-
-err_mem_free:
-	kfree(vaddr);
-
-	return ret;
 }
 
 int ath12k_dp_rx_ampdu_start(struct ath12k *ar,
@@ -1196,8 +1252,8 @@ int ath12k_dp_rx_peer_pn_replay_config(struct ath12k_link_vif *arvif,
 		rx_tid = &peer->rx_tid[tid];
 		if (!rx_tid->active)
 			continue;
-		cmd.addr_lo = lower_32_bits(rx_tid->paddr);
-		cmd.addr_hi = upper_32_bits(rx_tid->paddr);
+		cmd.addr_lo = lower_32_bits(rx_tid->qbuf.paddr_aligned);
+		cmd.addr_hi = upper_32_bits(rx_tid->qbuf.paddr_aligned);
 		ret = ath12k_dp_reo_cmd_send(ab, rx_tid,
 					     HAL_REO_CMD_UPDATE_RX_QUEUE,
 					     &cmd, NULL);
@@ -1784,8 +1840,12 @@ void ath12k_dp_htt_htc_t2h_msg_handler(struct ath12k_base *ab,
 					     HTT_T2H_PEER_MAP_INFO1_MAC_ADDR_H16);
 		ath12k_dp_get_mac_addr(le32_to_cpu(resp->peer_map_ev.mac_addr_l32),
 				       peer_mac_h16, mac_addr);
+		ast_hash = le32_get_bits(resp->peer_map_ev.info2,
+					 HTT_T2H_PEER_MAP3_INFO2_AST_HASH_VAL);
+		hw_peer_id = le32_get_bits(resp->peer_map_ev.info2,
+					   HTT_T2H_PEER_MAP3_INFO2_HW_PEER_ID);
 		ath12k_peer_map_event(ab, vdev_id, peer_id, mac_addr, ast_hash,
-				      peer_id);
+				      hw_peer_id);
 		break;
 	case HTT_T2H_MSG_TYPE_PEER_UNMAP:
 	case HTT_T2H_MSG_TYPE_PEER_UNMAP2:
@@ -1823,6 +1883,7 @@ static int ath12k_dp_rx_msdu_coalesce(struct ath12k *ar,
 	struct hal_rx_desc *ldesc;
 	int space_extra, rem_len, buf_len;
 	u32 hal_rx_desc_sz = ar->ab->hal.hal_desc_sz;
+	bool is_continuation;
 
 	/* As the msdu is spread across multiple rx buffers,
 	 * find the offset to the start of msdu for computing
@@ -1871,7 +1932,8 @@ static int ath12k_dp_rx_msdu_coalesce(struct ath12k *ar,
 	rem_len = msdu_len - buf_first_len;
 	while ((skb = __skb_dequeue(msdu_list)) != NULL && rem_len > 0) {
 		rxcb = ATH12K_SKB_RXCB(skb);
-		if (rxcb->is_continuation)
+		is_continuation = rxcb->is_continuation;
+		if (is_continuation)
 			buf_len = DP_RX_BUFFER_SIZE - hal_rx_desc_sz;
 		else
 			buf_len = rem_len;
@@ -1889,7 +1951,7 @@ static int ath12k_dp_rx_msdu_coalesce(struct ath12k *ar,
 		dev_kfree_skb_any(skb);
 
 		rem_len -= buf_len;
-		if (!rxcb->is_continuation)
+		if (!is_continuation)
 			break;
 	}
 
@@ -1914,21 +1976,14 @@ static struct sk_buff *ath12k_dp_rx_get_msdu_last_buf(struct sk_buff_head *msdu_
 	return NULL;
 }
 
-static void ath12k_dp_rx_h_csum_offload(struct ath12k *ar, struct sk_buff *msdu)
+static void ath12k_dp_rx_h_csum_offload(struct sk_buff *msdu,
+					struct ath12k_dp_rx_info *rx_info)
 {
-	struct ath12k_skb_rxcb *rxcb = ATH12K_SKB_RXCB(msdu);
-	struct ath12k_base *ab = ar->ab;
-	bool ip_csum_fail, l4_csum_fail;
-
-	ip_csum_fail = ath12k_dp_rx_h_ip_cksum_fail(ab, rxcb->rx_desc);
-	l4_csum_fail = ath12k_dp_rx_h_l4_cksum_fail(ab, rxcb->rx_desc);
-
-	msdu->ip_summed = (ip_csum_fail || l4_csum_fail) ?
-			  CHECKSUM_NONE : CHECKSUM_UNNECESSARY;
+	msdu->ip_summed = (rx_info->ip_csum_fail || rx_info->l4_csum_fail) ?
+			   CHECKSUM_NONE : CHECKSUM_UNNECESSARY;
 }
 
-static int ath12k_dp_rx_crypto_mic_len(struct ath12k *ar,
-				       enum hal_encrypt_type enctype)
+int ath12k_dp_rx_crypto_mic_len(struct ath12k *ar, enum hal_encrypt_type enctype)
 {
 	switch (enctype) {
 	case HAL_ENCRYPT_TYPE_OPEN:
@@ -2122,10 +2177,13 @@ static void ath12k_get_dot11_hdr_from_rx_desc(struct ath12k *ar,
 	struct hal_rx_desc *rx_desc = rxcb->rx_desc;
 	struct ath12k_base *ab = ar->ab;
 	size_t hdr_len, crypto_len;
-	struct ieee80211_hdr *hdr;
-	u16 qos_ctl;
-	__le16 fc;
-	u8 *crypto_hdr;
+	struct ieee80211_hdr hdr;
+	__le16 qos_ctl;
+	u8 *crypto_hdr, mesh_ctrl;
+
+	ath12k_dp_rx_desc_get_dot11_hdr(ab, rx_desc, &hdr);
+	hdr_len = ieee80211_hdrlen(hdr.frame_control);
+	mesh_ctrl = ath12k_dp_rx_h_mesh_ctl_present(ab, rx_desc);
 
 	if (!(status->flag & RX_FLAG_IV_STRIPPED)) {
 		crypto_len = ath12k_dp_rx_crypto_param_len(ar, enctype);
@@ -2133,27 +2191,21 @@ static void ath12k_get_dot11_hdr_from_rx_desc(struct ath12k *ar,
 		ath12k_dp_rx_desc_get_crypto_header(ab, rx_desc, crypto_hdr, enctype);
 	}
 
-	fc = cpu_to_le16(ath12k_dp_rxdesc_get_mpdu_frame_ctrl(ab, rx_desc));
-	hdr_len = ieee80211_hdrlen(fc);
 	skb_push(msdu, hdr_len);
-	hdr = (struct ieee80211_hdr *)msdu->data;
-	hdr->frame_control = fc;
-
-	/* Get wifi header from rx_desc */
-	ath12k_dp_rx_desc_get_dot11_hdr(ab, rx_desc, hdr);
+	memcpy(msdu->data, &hdr, min(hdr_len, sizeof(hdr)));
 
 	if (rxcb->is_mcbc)
 		status->flag &= ~RX_FLAG_PN_VALIDATED;
 
 	/* Add QOS header */
-	if (ieee80211_is_data_qos(hdr->frame_control)) {
-		qos_ctl = rxcb->tid;
-		if (ath12k_dp_rx_h_mesh_ctl_present(ab, rx_desc))
-			qos_ctl |= IEEE80211_QOS_CTL_MESH_CONTROL_PRESENT;
+	if (ieee80211_is_data_qos(hdr.frame_control)) {
+		struct ieee80211_hdr *qos_ptr = (struct ieee80211_hdr *)msdu->data;
 
-		/* TODO: Add other QoS ctl fields when required */
-		memcpy(msdu->data + (hdr_len - IEEE80211_QOS_CTL_LEN),
-		       &qos_ctl, IEEE80211_QOS_CTL_LEN);
+		qos_ctl = cpu_to_le16(rxcb->tid & IEEE80211_QOS_CTL_TID_MASK);
+		if (mesh_ctrl)
+			qos_ctl |= cpu_to_le16(IEEE80211_QOS_CTL_MESH_CONTROL_PRESENT);
+
+		memcpy(ieee80211_get_qos_ctl(qos_ptr), &qos_ctl, IEEE80211_QOS_CTL_LEN);
 	}
 }
 
@@ -2229,10 +2281,10 @@ static void ath12k_dp_rx_h_undecap(struct ath12k *ar, struct sk_buff *msdu,
 }
 
 struct ath12k_peer *
-ath12k_dp_rx_h_find_peer(struct ath12k_base *ab, struct sk_buff *msdu)
+ath12k_dp_rx_h_find_peer(struct ath12k_base *ab, struct sk_buff *msdu,
+			 struct ath12k_dp_rx_info *rx_info)
 {
 	struct ath12k_skb_rxcb *rxcb = ATH12K_SKB_RXCB(msdu);
-	struct hal_rx_desc *rx_desc = rxcb->rx_desc;
 	struct ath12k_peer *peer = NULL;
 
 	lockdep_assert_held(&ab->base_lock);
@@ -2243,40 +2295,41 @@ ath12k_dp_rx_h_find_peer(struct ath12k_base *ab, struct sk_buff *msdu)
 	if (peer)
 		return peer;
 
-	if (!rx_desc || !(ath12k_dp_rxdesc_mac_addr2_valid(ab, rx_desc)))
-		return NULL;
+	if (rx_info->addr2_present)
+		peer = ath12k_peer_find_by_addr(ab, rx_info->addr2);
 
-	peer = ath12k_peer_find_by_addr(ab,
-					ath12k_dp_rxdesc_get_mpdu_start_addr2(ab,
-									      rx_desc));
 	return peer;
 }
 
 static void ath12k_dp_rx_h_mpdu(struct ath12k *ar,
 				struct sk_buff *msdu,
 				struct hal_rx_desc *rx_desc,
-				struct ieee80211_rx_status *rx_status)
+				struct ath12k_dp_rx_info *rx_info)
 {
-	bool  fill_crypto_hdr;
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_skb_rxcb *rxcb;
 	enum hal_encrypt_type enctype;
 	bool is_decrypted = false;
 	struct ieee80211_hdr *hdr;
 	struct ath12k_peer *peer;
+	struct ieee80211_rx_status *rx_status = rx_info->rx_status;
 	u32 err_bitmap;
 
 	/* PN for multicast packets will be checked in mac80211 */
 	rxcb = ATH12K_SKB_RXCB(msdu);
-	fill_crypto_hdr = ath12k_dp_rx_h_is_da_mcbc(ar->ab, rx_desc);
-	rxcb->is_mcbc = fill_crypto_hdr;
+	rxcb->is_mcbc = rx_info->is_mcbc;
 
 	if (rxcb->is_mcbc)
-		rxcb->peer_id = ath12k_dp_rx_h_peer_id(ar->ab, rx_desc);
+		rxcb->peer_id = rx_info->peer_id;
 
 	spin_lock_bh(&ar->ab->base_lock);
-	peer = ath12k_dp_rx_h_find_peer(ar->ab, msdu);
+	peer = ath12k_dp_rx_h_find_peer(ar->ab, msdu, rx_info);
 	if (peer) {
+		/* resetting mcbc bit because mcbc packets are unicast
+		 * packets only for AP as STA sends unicast packets.
+		 */
+		rxcb->is_mcbc = rxcb->is_mcbc && !peer->ucast_ra_only;
+
 		if (rxcb->is_mcbc)
 			enctype = peer->sec_type_grp;
 		else
@@ -2305,7 +2358,7 @@ static void ath12k_dp_rx_h_mpdu(struct ath12k *ar,
 	if (is_decrypted) {
 		rx_status->flag |= RX_FLAG_DECRYPTED | RX_FLAG_MMIC_STRIPPED;
 
-		if (fill_crypto_hdr)
+		if (rx_info->is_mcbc)
 			rx_status->flag |= RX_FLAG_MIC_STRIPPED |
 					RX_FLAG_ICV_STRIPPED;
 		else
@@ -2313,37 +2366,28 @@ static void ath12k_dp_rx_h_mpdu(struct ath12k *ar,
 					   RX_FLAG_PN_VALIDATED;
 	}
 
-	ath12k_dp_rx_h_csum_offload(ar, msdu);
+	ath12k_dp_rx_h_csum_offload(msdu, rx_info);
 	ath12k_dp_rx_h_undecap(ar, msdu, rx_desc,
 			       enctype, rx_status, is_decrypted);
 
-	if (!is_decrypted || fill_crypto_hdr)
+	if (!is_decrypted || rx_info->is_mcbc)
 		return;
 
-	if (ath12k_dp_rx_h_decap_type(ar->ab, rx_desc) !=
-	    DP_RX_DECAP_TYPE_ETHERNET2_DIX) {
+	if (rx_info->decap_type != DP_RX_DECAP_TYPE_ETHERNET2_DIX) {
 		hdr = (void *)msdu->data;
 		hdr->frame_control &= ~__cpu_to_le16(IEEE80211_FCTL_PROTECTED);
 	}
 }
 
-static void ath12k_dp_rx_h_rate(struct ath12k *ar, struct hal_rx_desc *rx_desc,
-				struct ieee80211_rx_status *rx_status)
+static void ath12k_dp_rx_h_rate(struct ath12k *ar, struct ath12k_dp_rx_info *rx_info)
 {
-	struct ath12k_base *ab = ar->ab;
 	struct ieee80211_supported_band *sband;
-	enum rx_msdu_start_pkt_type pkt_type;
-	u8 bw;
-	u8 rate_mcs, nss;
-	u8 sgi;
+	struct ieee80211_rx_status *rx_status = rx_info->rx_status;
+	enum rx_msdu_start_pkt_type pkt_type = rx_info->pkt_type;
+	u8 bw = rx_info->bw, sgi = rx_info->sgi;
+	u8 rate_mcs = rx_info->rate_mcs, nss = rx_info->nss;
 	bool is_cck;
 
-	pkt_type = ath12k_dp_rx_h_pkt_type(ab, rx_desc);
-	bw = ath12k_dp_rx_h_rx_bw(ab, rx_desc);
-	rate_mcs = ath12k_dp_rx_h_rate_mcs(ab, rx_desc);
-	nss = ath12k_dp_rx_h_nss(ab, rx_desc);
-	sgi = ath12k_dp_rx_h_sgi(ab, rx_desc);
-
 	switch (pkt_type) {
 	case RX_MSDU_START_PKT_TYPE_11A:
 	case RX_MSDU_START_PKT_TYPE_11B:
@@ -2412,10 +2456,35 @@ static void ath12k_dp_rx_h_rate(struct ath12k *ar, struct hal_rx_desc *rx_desc,
 	}
 }
 
-void ath12k_dp_rx_h_ppdu(struct ath12k *ar, struct hal_rx_desc *rx_desc,
-			 struct ieee80211_rx_status *rx_status)
+void ath12k_dp_rx_h_fetch_info(struct ath12k_base *ab, struct hal_rx_desc *rx_desc,
+			       struct ath12k_dp_rx_info *rx_info)
 {
-	struct ath12k_base *ab = ar->ab;
+	rx_info->ip_csum_fail = ath12k_dp_rx_h_ip_cksum_fail(ab, rx_desc);
+	rx_info->l4_csum_fail = ath12k_dp_rx_h_l4_cksum_fail(ab, rx_desc);
+	rx_info->is_mcbc = ath12k_dp_rx_h_is_da_mcbc(ab, rx_desc);
+	rx_info->decap_type = ath12k_dp_rx_h_decap_type(ab, rx_desc);
+	rx_info->pkt_type = ath12k_dp_rx_h_pkt_type(ab, rx_desc);
+	rx_info->sgi = ath12k_dp_rx_h_sgi(ab, rx_desc);
+	rx_info->rate_mcs = ath12k_dp_rx_h_rate_mcs(ab, rx_desc);
+	rx_info->bw = ath12k_dp_rx_h_rx_bw(ab, rx_desc);
+	rx_info->nss = ath12k_dp_rx_h_nss(ab, rx_desc);
+	rx_info->tid = ath12k_dp_rx_h_tid(ab, rx_desc);
+	rx_info->peer_id = ath12k_dp_rx_h_peer_id(ab, rx_desc);
+	rx_info->phy_meta_data = ath12k_dp_rx_h_freq(ab, rx_desc);
+
+	if (ath12k_dp_rxdesc_mac_addr2_valid(ab, rx_desc)) {
+		ether_addr_copy(rx_info->addr2,
+				ath12k_dp_rxdesc_get_mpdu_start_addr2(ab, rx_desc));
+		rx_info->addr2_present = true;
+	}
+
+	ath12k_dbg_dump(ab, ATH12K_DBG_DATA, NULL, "rx_desc: ",
+			rx_desc, sizeof(*rx_desc));
+}
+
+void ath12k_dp_rx_h_ppdu(struct ath12k *ar, struct ath12k_dp_rx_info *rx_info)
+{
+	struct ieee80211_rx_status *rx_status = rx_info->rx_status;
 	u8 channel_num;
 	u32 center_freq, meta_data;
 	struct ieee80211_channel *channel;
@@ -2429,12 +2498,12 @@ void ath12k_dp_rx_h_ppdu(struct ath12k *ar, struct hal_rx_desc *rx_desc,
 
 	rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL;
 
-	meta_data = ath12k_dp_rx_h_freq(ab, rx_desc);
+	meta_data = rx_info->phy_meta_data;
 	channel_num = meta_data;
 	center_freq = meta_data >> 16;
 
-	if (center_freq >= ATH12K_MIN_6G_FREQ &&
-	    center_freq <= ATH12K_MAX_6G_FREQ) {
+	if (center_freq >= ATH12K_MIN_6GHZ_FREQ &&
+	    center_freq <= ATH12K_MAX_6GHZ_FREQ) {
 		rx_status->band = NL80211_BAND_6GHZ;
 		rx_status->freq = center_freq;
 	} else if (channel_num >= 1 && channel_num <= 14) {
@@ -2450,20 +2519,18 @@ void ath12k_dp_rx_h_ppdu(struct ath12k *ar, struct hal_rx_desc *rx_desc,
 				ieee80211_frequency_to_channel(channel->center_freq);
 		}
 		spin_unlock_bh(&ar->data_lock);
-		ath12k_dbg_dump(ar->ab, ATH12K_DBG_DATA, NULL, "rx_desc: ",
-				rx_desc, sizeof(*rx_desc));
 	}
 
 	if (rx_status->band != NL80211_BAND_6GHZ)
 		rx_status->freq = ieee80211_channel_to_frequency(channel_num,
 								 rx_status->band);
 
-	ath12k_dp_rx_h_rate(ar, rx_desc, rx_status);
+	ath12k_dp_rx_h_rate(ar, rx_info);
 }
 
 static void ath12k_dp_rx_deliver_msdu(struct ath12k *ar, struct napi_struct *napi,
 				      struct sk_buff *msdu,
-				      struct ieee80211_rx_status *status)
+				      struct ath12k_dp_rx_info *rx_info)
 {
 	struct ath12k_base *ab = ar->ab;
 	static const struct ieee80211_radiotap_he known = {
@@ -2476,6 +2543,7 @@ static void ath12k_dp_rx_deliver_msdu(struct ath12k *ar, struct napi_struct *nap
 	struct ieee80211_sta *pubsta;
 	struct ath12k_peer *peer;
 	struct ath12k_skb_rxcb *rxcb = ATH12K_SKB_RXCB(msdu);
+	struct ieee80211_rx_status *status = rx_info->rx_status;
 	u8 decap = DP_RX_DECAP_TYPE_RAW;
 	bool is_mcbc = rxcb->is_mcbc;
 	bool is_eapol = rxcb->is_eapol;
@@ -2488,10 +2556,10 @@ static void ath12k_dp_rx_deliver_msdu(struct ath12k *ar, struct napi_struct *nap
 	}
 
 	if (!(status->flag & RX_FLAG_ONLY_MONITOR))
-		decap = ath12k_dp_rx_h_decap_type(ab, rxcb->rx_desc);
+		decap = rx_info->decap_type;
 
 	spin_lock_bh(&ab->base_lock);
-	peer = ath12k_dp_rx_h_find_peer(ab, msdu);
+	peer = ath12k_dp_rx_h_find_peer(ab, msdu, rx_info);
 
 	pubsta = peer ? peer->sta : NULL;
 
@@ -2566,7 +2634,7 @@ static bool ath12k_dp_rx_check_nwifi_hdr_len_valid(struct ath12k_base *ab,
 	if ((likely(hdr_len <= DP_MAX_NWIFI_HDR_LEN)))
 		return true;
 
-	ab->soc_stats.invalid_rbm++;
+	ab->device_stats.invalid_rbm++;
 	WARN_ON_ONCE(1);
 	return false;
 }
@@ -2574,7 +2642,7 @@ static bool ath12k_dp_rx_check_nwifi_hdr_len_valid(struct ath12k_base *ab,
 static int ath12k_dp_rx_process_msdu(struct ath12k *ar,
 				     struct sk_buff *msdu,
 				     struct sk_buff_head *msdu_list,
-				     struct ieee80211_rx_status *rx_status)
+				     struct ath12k_dp_rx_info *rx_info)
 {
 	struct ath12k_base *ab = ar->ab;
 	struct hal_rx_desc *rx_desc, *lrx_desc;
@@ -2634,10 +2702,11 @@ static int ath12k_dp_rx_process_msdu(struct ath12k *ar,
 		goto free_out;
 	}
 
-	ath12k_dp_rx_h_ppdu(ar, rx_desc, rx_status);
-	ath12k_dp_rx_h_mpdu(ar, msdu, rx_desc, rx_status);
+	ath12k_dp_rx_h_fetch_info(ab, rx_desc, rx_info);
+	ath12k_dp_rx_h_ppdu(ar, rx_info);
+	ath12k_dp_rx_h_mpdu(ar, msdu, rx_desc, rx_info);
 
-	rx_status->flag |= RX_FLAG_SKIP_MONITOR | RX_FLAG_DUP_VALIDATED;
+	rx_info->rx_status->flag |= RX_FLAG_SKIP_MONITOR | RX_FLAG_DUP_VALIDATED;
 
 	return 0;
 
@@ -2657,12 +2726,16 @@ static void ath12k_dp_rx_process_received_packets(struct ath12k_base *ab,
 	struct ath12k *ar;
 	struct ath12k_hw_link *hw_links = ag->hw_links;
 	struct ath12k_base *partner_ab;
+	struct ath12k_dp_rx_info rx_info;
 	u8 hw_link_id, pdev_id;
 	int ret;
 
 	if (skb_queue_empty(msdu_list))
 		return;
 
+	rx_info.addr2_present = false;
+	rx_info.rx_status = &rx_status;
+
 	rcu_read_lock();
 
 	while ((msdu = __skb_dequeue(msdu_list))) {
@@ -2683,7 +2756,7 @@ static void ath12k_dp_rx_process_received_packets(struct ath12k_base *ab,
 			continue;
 		}
 
-		ret = ath12k_dp_rx_process_msdu(ar, msdu, msdu_list, &rx_status);
+		ret = ath12k_dp_rx_process_msdu(ar, msdu, msdu_list, &rx_info);
 		if (ret) {
 			ath12k_dbg(ab, ATH12K_DBG_DATA,
 				   "Unable to process msdu %d", ret);
@@ -2691,7 +2764,7 @@ static void ath12k_dp_rx_process_received_packets(struct ath12k_base *ab,
 			continue;
 		}
 
-		ath12k_dp_rx_deliver_msdu(ar, napi, msdu, &rx_status);
+		ath12k_dp_rx_deliver_msdu(ar, napi, msdu, &rx_info);
 	}
 
 	rcu_read_unlock();
@@ -2724,9 +2797,9 @@ int ath12k_dp_rx_process(struct ath12k_base *ab, int ring_id,
 			 struct napi_struct *napi, int budget)
 {
 	struct ath12k_hw_group *ag = ab->ag;
-	struct list_head rx_desc_used_list[ATH12K_MAX_SOCS];
+	struct list_head rx_desc_used_list[ATH12K_MAX_DEVICES];
 	struct ath12k_hw_link *hw_links = ag->hw_links;
-	int num_buffs_reaped[ATH12K_MAX_SOCS] = {};
+	int num_buffs_reaped[ATH12K_MAX_DEVICES] = {};
 	struct ath12k_rx_desc_info *desc_info;
 	struct ath12k_dp *dp = &ab->dp;
 	struct dp_rxdma_ring *rx_ring = &dp->rx_refill_buf_ring;
@@ -2743,7 +2816,7 @@ int ath12k_dp_rx_process(struct ath12k_base *ab, int ring_id,
 
 	__skb_queue_head_init(&msdu_list);
 
-	for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++)
+	for (device_id = 0; device_id < ATH12K_MAX_DEVICES; device_id++)
 		INIT_LIST_HEAD(&rx_desc_used_list[device_id]);
 
 	srng = &ab->hal.srng_list[dp->reo_dst_ring[ring_id].ring_id];
@@ -2804,13 +2877,14 @@ try_again:
 				 DMA_FROM_DEVICE);
 
 		num_buffs_reaped[device_id]++;
+		ab->device_stats.reo_rx[ring_id][ab->device_id]++;
 
 		push_reason = le32_get_bits(desc->info0,
 					    HAL_REO_DEST_RING_INFO0_PUSH_REASON);
 		if (push_reason !=
 		    HAL_REO_DEST_RING_PUSH_REASON_ROUTING_INSTRUCTION) {
 			dev_kfree_skb_any(msdu);
-			ab->soc_stats.hal_reo_error[ring_id]++;
+			ab->device_stats.hal_reo_error[ring_id]++;
 			continue;
 		}
 
@@ -2860,7 +2934,7 @@ try_again:
 	if (!total_msdu_reaped)
 		goto exit;
 
-	for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++) {
+	for (device_id = 0; device_id < ATH12K_MAX_DEVICES; device_id++) {
 		if (!num_buffs_reaped[device_id])
 			continue;
 
@@ -2984,6 +3058,7 @@ static int ath12k_dp_rx_h_verify_tkip_mic(struct ath12k *ar, struct ath12k_peer
 	struct ieee80211_rx_status *rxs = IEEE80211_SKB_RXCB(msdu);
 	struct ieee80211_key_conf *key_conf;
 	struct ieee80211_hdr *hdr;
+	struct ath12k_dp_rx_info rx_info;
 	u8 mic[IEEE80211_CCMP_MIC_LEN];
 	int head_len, tail_len, ret;
 	size_t data_len;
@@ -2994,6 +3069,9 @@ static int ath12k_dp_rx_h_verify_tkip_mic(struct ath12k *ar, struct ath12k_peer
 	if (ath12k_dp_rx_h_enctype(ab, rx_desc) != HAL_ENCRYPT_TYPE_TKIP_MIC)
 		return 0;
 
+	rx_info.addr2_present = false;
+	rx_info.rx_status = rxs;
+
 	hdr = (struct ieee80211_hdr *)(msdu->data + hal_rx_desc_sz);
 	hdr_len = ieee80211_hdrlen(hdr->frame_control);
 	head_len = hdr_len + hal_rx_desc_sz + IEEE80211_TKIP_IV_LEN;
@@ -3020,6 +3098,8 @@ mic_fail:
 	(ATH12K_SKB_RXCB(msdu))->is_first_msdu = true;
 	(ATH12K_SKB_RXCB(msdu))->is_last_msdu = true;
 
+	ath12k_dp_rx_h_fetch_info(ab, rx_desc, &rx_info);
+
 	rxs->flag |= RX_FLAG_MMIC_ERROR | RX_FLAG_MMIC_STRIPPED |
 		    RX_FLAG_IV_STRIPPED | RX_FLAG_DECRYPTED;
 	skb_pull(msdu, hal_rx_desc_sz);
@@ -3027,7 +3107,7 @@ mic_fail:
 	if (unlikely(!ath12k_dp_rx_check_nwifi_hdr_len_valid(ab, rx_desc, msdu)))
 		return -EINVAL;
 
-	ath12k_dp_rx_h_ppdu(ar, rx_desc, rxs);
+	ath12k_dp_rx_h_ppdu(ar, &rx_info);
 	ath12k_dp_rx_h_undecap(ar, msdu, rx_desc,
 			       HAL_ENCRYPT_TYPE_TKIP_MIC, rxs, true);
 	ieee80211_rx(ath12k_ar_to_hw(ar), msdu);
@@ -3242,8 +3322,15 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
 	reo_ent_ring->rx_mpdu_info.peer_meta_data =
 		reo_dest_ring->rx_mpdu_info.peer_meta_data;
 
-	reo_ent_ring->queue_addr_lo = cpu_to_le32(lower_32_bits(rx_tid->paddr));
-	queue_addr_hi = upper_32_bits(rx_tid->paddr);
+	if (ab->hw_params->reoq_lut_support) {
+		reo_ent_ring->queue_addr_lo = reo_dest_ring->rx_mpdu_info.peer_meta_data;
+		queue_addr_hi = 0;
+	} else {
+		reo_ent_ring->queue_addr_lo =
+				cpu_to_le32(lower_32_bits(rx_tid->qbuf.paddr_aligned));
+		queue_addr_hi = upper_32_bits(rx_tid->qbuf.paddr_aligned);
+	}
+
 	reo_ent_ring->info0 = le32_encode_bits(queue_addr_hi,
 					       HAL_REO_ENTR_RING_INFO0_QUEUE_ADDR_HI) |
 			      le32_encode_bits(dst_ind,
@@ -3439,7 +3526,7 @@ static int ath12k_dp_rx_frag_h_mpdu(struct ath12k *ar,
 			goto out_unlock;
 		}
 	} else {
-		ath12k_dp_rx_link_desc_return(ab, ring_desc,
+		ath12k_dp_rx_link_desc_return(ab, &ring_desc->buf_addr_info,
 					      HAL_WBM_REL_BM_ACT_PUT_IN_IDLE);
 	}
 
@@ -3552,7 +3639,7 @@ ath12k_dp_process_rx_err_buf(struct ath12k *ar, struct hal_reo_dest_ring *desc,
 
 	if (ath12k_dp_rx_frag_h_mpdu(ar, msdu, desc)) {
 		dev_kfree_skb_any(msdu);
-		ath12k_dp_rx_link_desc_return(ar->ab, desc,
+		ath12k_dp_rx_link_desc_return(ar->ab, &desc->buf_addr_info,
 					      HAL_WBM_REL_BM_ACT_PUT_IN_IDLE);
 	}
 exit:
@@ -3564,9 +3651,9 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi,
 			     int budget)
 {
 	struct ath12k_hw_group *ag = ab->ag;
-	struct list_head rx_desc_used_list[ATH12K_MAX_SOCS];
+	struct list_head rx_desc_used_list[ATH12K_MAX_DEVICES];
 	u32 msdu_cookies[HAL_NUM_RX_MSDUS_PER_LINK_DESC];
-	int num_buffs_reaped[ATH12K_MAX_SOCS] = {};
+	int num_buffs_reaped[ATH12K_MAX_DEVICES] = {};
 	struct dp_link_desc_bank *link_desc_banks;
 	enum hal_rx_buf_return_buf_manager rbm;
 	struct hal_rx_msdu_link *link_desc_va;
@@ -3588,7 +3675,7 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi,
 	tot_n_bufs_reaped = 0;
 	quota = budget;
 
-	for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++)
+	for (device_id = 0; device_id < ATH12K_MAX_DEVICES; device_id++)
 		INIT_LIST_HEAD(&rx_desc_used_list[device_id]);
 
 	reo_except = &ab->dp.reo_except_ring;
@@ -3602,7 +3689,7 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi,
 	while (budget &&
 	       (reo_desc = ath12k_hal_srng_dst_get_next_entry(ab, srng))) {
 		drop = false;
-		ab->soc_stats.err_ring_pkts++;
+		ab->device_stats.err_ring_pkts++;
 
 		ret = ath12k_hal_desc_reo_parse_err(ab, reo_desc, &paddr,
 						    &desc_bank);
@@ -3629,9 +3716,10 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi,
 		if (rbm != partner_ab->dp.idle_link_rbm &&
 		    rbm != HAL_RX_BUF_RBM_SW3_BM &&
 		    rbm != partner_ab->hw_params->hal_params->rx_buf_rbm) {
-			ab->soc_stats.invalid_rbm++;
+			ab->device_stats.invalid_rbm++;
 			ath12k_warn(ab, "invalid return buffer manager %d\n", rbm);
-			ath12k_dp_rx_link_desc_return(partner_ab, reo_desc,
+			ath12k_dp_rx_link_desc_return(partner_ab,
+						      &reo_desc->buf_addr_info,
 						      HAL_WBM_REL_BM_ACT_REL_MSDU);
 			continue;
 		}
@@ -3649,7 +3737,8 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi,
 			drop = true;
 
 			/* Return the link desc back to wbm idle list */
-			ath12k_dp_rx_link_desc_return(partner_ab, reo_desc,
+			ath12k_dp_rx_link_desc_return(partner_ab,
+						      &reo_desc->buf_addr_info,
 						      HAL_WBM_REL_BM_ACT_PUT_IN_IDLE);
 		}
 
@@ -3676,7 +3765,7 @@ exit:
 
 	spin_unlock_bh(&srng->lock);
 
-	for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++) {
+	for (device_id = 0; device_id < ATH12K_MAX_DEVICES; device_id++) {
 		if (!num_buffs_reaped[device_id])
 			continue;
 
@@ -3716,7 +3805,7 @@ static void ath12k_dp_rx_null_q_desc_sg_drop(struct ath12k *ar,
 }
 
 static int ath12k_dp_rx_h_null_q_desc(struct ath12k *ar, struct sk_buff *msdu,
-				      struct ieee80211_rx_status *status,
+				      struct ath12k_dp_rx_info *rx_info,
 				      struct sk_buff_head *msdu_list)
 {
 	struct ath12k_base *ab = ar->ab;
@@ -3772,11 +3861,11 @@ static int ath12k_dp_rx_h_null_q_desc(struct ath12k *ar, struct sk_buff *msdu,
 	if (unlikely(!ath12k_dp_rx_check_nwifi_hdr_len_valid(ab, desc, msdu)))
 		return -EINVAL;
 
-	ath12k_dp_rx_h_ppdu(ar, desc, status);
+	ath12k_dp_rx_h_fetch_info(ab, desc, rx_info);
+	ath12k_dp_rx_h_ppdu(ar, rx_info);
+	ath12k_dp_rx_h_mpdu(ar, msdu, desc, rx_info);
 
-	ath12k_dp_rx_h_mpdu(ar, msdu, desc, status);
-
-	rxcb->tid = ath12k_dp_rx_h_tid(ab, desc);
+	rxcb->tid = rx_info->tid;
 
 	/* Please note that caller will having the access to msdu and completing
 	 * rx with mac80211. Need not worry about cleaning up amsdu_list.
@@ -3786,17 +3875,17 @@ static int ath12k_dp_rx_h_null_q_desc(struct ath12k *ar, struct sk_buff *msdu,
 }
 
 static bool ath12k_dp_rx_h_reo_err(struct ath12k *ar, struct sk_buff *msdu,
-				   struct ieee80211_rx_status *status,
+				   struct ath12k_dp_rx_info *rx_info,
 				   struct sk_buff_head *msdu_list)
 {
 	struct ath12k_skb_rxcb *rxcb = ATH12K_SKB_RXCB(msdu);
 	bool drop = false;
 
-	ar->ab->soc_stats.reo_error[rxcb->err_code]++;
+	ar->ab->device_stats.reo_error[rxcb->err_code]++;
 
 	switch (rxcb->err_code) {
 	case HAL_REO_DEST_RING_ERROR_CODE_DESC_ADDR_ZERO:
-		if (ath12k_dp_rx_h_null_q_desc(ar, msdu, status, msdu_list))
+		if (ath12k_dp_rx_h_null_q_desc(ar, msdu, rx_info, msdu_list))
 			drop = true;
 		break;
 	case HAL_REO_DEST_RING_ERROR_CODE_PN_CHECK_FAILED:
@@ -3817,7 +3906,7 @@ static bool ath12k_dp_rx_h_reo_err(struct ath12k *ar, struct sk_buff *msdu,
 }
 
 static bool ath12k_dp_rx_h_tkip_mic_err(struct ath12k *ar, struct sk_buff *msdu,
-					struct ieee80211_rx_status *status)
+					struct ath12k_dp_rx_info *rx_info)
 {
 	struct ath12k_base *ab = ar->ab;
 	u16 msdu_len;
@@ -3831,24 +3920,33 @@ static bool ath12k_dp_rx_h_tkip_mic_err(struct ath12k *ar, struct sk_buff *msdu,
 
 	l3pad_bytes = ath12k_dp_rx_h_l3pad(ab, desc);
 	msdu_len = ath12k_dp_rx_h_msdu_len(ab, desc);
+
+	if ((hal_rx_desc_sz + l3pad_bytes + msdu_len) > DP_RX_BUFFER_SIZE) {
+		ath12k_dbg(ab, ATH12K_DBG_DATA,
+			   "invalid msdu len in tkip mic err %u\n", msdu_len);
+		ath12k_dbg_dump(ab, ATH12K_DBG_DATA, NULL, "", desc,
+				sizeof(*desc));
+		return true;
+	}
+
 	skb_put(msdu, hal_rx_desc_sz + l3pad_bytes + msdu_len);
 	skb_pull(msdu, hal_rx_desc_sz + l3pad_bytes);
 
 	if (unlikely(!ath12k_dp_rx_check_nwifi_hdr_len_valid(ab, desc, msdu)))
 		return true;
 
-	ath12k_dp_rx_h_ppdu(ar, desc, status);
+	ath12k_dp_rx_h_ppdu(ar, rx_info);
 
-	status->flag |= (RX_FLAG_MMIC_STRIPPED | RX_FLAG_MMIC_ERROR |
-			 RX_FLAG_DECRYPTED);
+	rx_info->rx_status->flag |= (RX_FLAG_MMIC_STRIPPED | RX_FLAG_MMIC_ERROR |
+				     RX_FLAG_DECRYPTED);
 
 	ath12k_dp_rx_h_undecap(ar, msdu, desc,
-			       HAL_ENCRYPT_TYPE_TKIP_MIC, status, false);
+			       HAL_ENCRYPT_TYPE_TKIP_MIC, rx_info->rx_status, false);
 	return false;
 }
 
 static bool ath12k_dp_rx_h_rxdma_err(struct ath12k *ar,  struct sk_buff *msdu,
-				     struct ieee80211_rx_status *status)
+				     struct ath12k_dp_rx_info *rx_info)
 {
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_skb_rxcb *rxcb = ATH12K_SKB_RXCB(msdu);
@@ -3856,14 +3954,15 @@ static bool ath12k_dp_rx_h_rxdma_err(struct ath12k *ar,  struct sk_buff *msdu,
 	bool drop = false;
 	u32 err_bitmap;
 
-	ar->ab->soc_stats.rxdma_error[rxcb->err_code]++;
+	ar->ab->device_stats.rxdma_error[rxcb->err_code]++;
 
 	switch (rxcb->err_code) {
 	case HAL_REO_ENTR_RING_RXDMA_ECODE_DECRYPT_ERR:
 	case HAL_REO_ENTR_RING_RXDMA_ECODE_TKIP_MIC_ERR:
 		err_bitmap = ath12k_dp_rx_h_mpdu_err(ab, rx_desc);
 		if (err_bitmap & HAL_RX_MPDU_ERR_TKIP_MIC) {
-			drop = ath12k_dp_rx_h_tkip_mic_err(ar, msdu, status);
+			ath12k_dp_rx_h_fetch_info(ab, rx_desc, rx_info);
+			drop = ath12k_dp_rx_h_tkip_mic_err(ar, msdu, rx_info);
 			break;
 		}
 		fallthrough;
@@ -3885,14 +3984,18 @@ static void ath12k_dp_rx_wbm_err(struct ath12k *ar,
 {
 	struct ath12k_skb_rxcb *rxcb = ATH12K_SKB_RXCB(msdu);
 	struct ieee80211_rx_status rxs = {0};
+	struct ath12k_dp_rx_info rx_info;
 	bool drop = true;
 
+	rx_info.addr2_present = false;
+	rx_info.rx_status = &rxs;
+
 	switch (rxcb->err_rel_src) {
 	case HAL_WBM_REL_SRC_MODULE_REO:
-		drop = ath12k_dp_rx_h_reo_err(ar, msdu, &rxs, msdu_list);
+		drop = ath12k_dp_rx_h_reo_err(ar, msdu, &rx_info, msdu_list);
 		break;
 	case HAL_WBM_REL_SRC_MODULE_RXDMA:
-		drop = ath12k_dp_rx_h_rxdma_err(ar, msdu, &rxs);
+		drop = ath12k_dp_rx_h_rxdma_err(ar, msdu, &rx_info);
 		break;
 	default:
 		/* msdu will get freed */
@@ -3904,13 +4007,13 @@ static void ath12k_dp_rx_wbm_err(struct ath12k *ar,
 		return;
 	}
 
-	ath12k_dp_rx_deliver_msdu(ar, napi, msdu, &rxs);
+	ath12k_dp_rx_deliver_msdu(ar, napi, msdu, &rx_info);
 }
 
 int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab,
 				 struct napi_struct *napi, int budget)
 {
-	struct list_head rx_desc_used_list[ATH12K_MAX_SOCS];
+	struct list_head rx_desc_used_list[ATH12K_MAX_DEVICES];
 	struct ath12k_hw_group *ag = ab->ag;
 	struct ath12k *ar;
 	struct ath12k_dp *dp = &ab->dp;
@@ -3921,9 +4024,10 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab,
 	struct sk_buff_head msdu_list, scatter_msdu_list;
 	struct ath12k_skb_rxcb *rxcb;
 	void *rx_desc;
-	int num_buffs_reaped[ATH12K_MAX_SOCS] = {};
+	int num_buffs_reaped[ATH12K_MAX_DEVICES] = {};
 	int total_num_buffs_reaped = 0;
 	struct ath12k_rx_desc_info *desc_info;
+	struct ath12k_device_dp_stats *device_stats = &ab->device_stats;
 	struct ath12k_hw_link *hw_links = ag->hw_links;
 	struct ath12k_base *partner_ab;
 	u8 hw_link_id, device_id;
@@ -3933,7 +4037,7 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab,
 	__skb_queue_head_init(&msdu_list);
 	__skb_queue_head_init(&scatter_msdu_list);
 
-	for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++)
+	for (device_id = 0; device_id < ATH12K_MAX_DEVICES; device_id++)
 		INIT_LIST_HEAD(&rx_desc_used_list[device_id]);
 
 	srng = &ab->hal.srng_list[dp->rx_rel_ring.ring_id];
@@ -4057,7 +4161,7 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab,
 	if (!total_num_buffs_reaped)
 		goto done;
 
-	for (device_id = 0; device_id < ATH12K_MAX_SOCS; device_id++) {
+	for (device_id = 0; device_id < ATH12K_MAX_DEVICES; device_id++) {
 		if (!num_buffs_reaped[device_id])
 			continue;
 
@@ -4097,6 +4201,12 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab,
 			dev_kfree_skb_any(msdu);
 			continue;
 		}
+
+		if (rxcb->err_rel_src < HAL_WBM_REL_SRC_MODULE_MAX) {
+			device_id = ar->ab->device_id;
+			device_stats->rx_wbm_rel_source[rxcb->err_rel_src][device_id]++;
+		}
+
 		ath12k_dp_rx_wbm_err(ar, napi, msdu, &msdu_list);
 	}
 	rcu_read_unlock();
@@ -4186,6 +4296,7 @@ void ath12k_dp_rx_process_reo_status(struct ath12k_base *ab)
 void ath12k_dp_rx_free(struct ath12k_base *ab)
 {
 	struct ath12k_dp *dp = &ab->dp;
+	struct dp_srng *srng;
 	int i;
 
 	ath12k_dp_srng_cleanup(ab, &dp->rx_refill_buf_ring.refill_buf_ring);
@@ -4193,6 +4304,10 @@ void ath12k_dp_rx_free(struct ath12k_base *ab)
 	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
 		if (ab->hw_params->rx_mac_buf_ring)
 			ath12k_dp_srng_cleanup(ab, &dp->rx_mac_buf_ring[i]);
+		if (!ab->hw_params->rxdma1_enable) {
+			srng = &dp->rx_mon_status_refill_ring[i].refill_buf_ring;
+			ath12k_dp_srng_cleanup(ab, srng);
+		}
 	}
 
 	for (i = 0; i < ab->hw_params->num_rxdma_dst_ring; i++)
@@ -4341,6 +4456,19 @@ int ath12k_dp_rx_htt_setup(struct ath12k_base *ab)
 				    ret);
 			return ret;
 		}
+	} else {
+		for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
+			ring_id =
+				dp->rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
+			ret = ath12k_dp_tx_htt_srng_setup(ab, ring_id, i,
+							  HAL_RXDMA_MONITOR_STATUS);
+			if (ret) {
+				ath12k_warn(ab,
+					    "failed to configure mon_status_refill_ring%d %d\n",
+					    i, ret);
+				return ret;
+			}
+		}
 	}
 
 	ret = ab->hw_params->hw_ops->rxdma_ring_sel_config(ab);
@@ -4355,6 +4483,7 @@ int ath12k_dp_rx_htt_setup(struct ath12k_base *ab)
 int ath12k_dp_rx_alloc(struct ath12k_base *ab)
 {
 	struct ath12k_dp *dp = &ab->dp;
+	struct dp_srng *srng;
 	int i, ret;
 
 	idr_init(&dp->rxdma_mon_buf_ring.bufs_idr);
@@ -4402,6 +4531,23 @@ int ath12k_dp_rx_alloc(struct ath12k_base *ab)
 			ath12k_warn(ab, "failed to setup HAL_RXDMA_MONITOR_BUF\n");
 			return ret;
 		}
+	} else {
+		for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
+			idr_init(&dp->rx_mon_status_refill_ring[i].bufs_idr);
+			spin_lock_init(&dp->rx_mon_status_refill_ring[i].idr_lock);
+		}
+
+		for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
+			srng = &dp->rx_mon_status_refill_ring[i].refill_buf_ring;
+			ret = ath12k_dp_srng_setup(ab, srng,
+						   HAL_RXDMA_MONITOR_STATUS, 0, i,
+						   DP_RXDMA_MON_STATUS_RING_SIZE);
+			if (ret) {
+				ath12k_warn(ab, "failed to setup mon status ring %d\n",
+					    i);
+				return ret;
+			}
+		}
 	}
 
 	ret = ath12k_dp_rxdma_buf_setup(ab);
@@ -4472,15 +4618,15 @@ int ath12k_dp_rx_pdev_mon_attach(struct ath12k *ar)
 		return ret;
 	}
 
-	/* if rxdma1_enable is false, no need to setup
-	 * rxdma_mon_desc_ring.
-	 */
-	if (!ar->ab->hw_params->rxdma1_enable)
-		return 0;
-
 	pmon->mon_last_linkdesc_paddr = 0;
 	pmon->mon_last_buf_cookie = DP_RX_DESC_COOKIE_MAX + 1;
 	spin_lock_init(&pmon->mon_lock);
 
+	if (!ar->ab->hw_params->rxdma1_enable)
+		return 0;
+
+	INIT_LIST_HEAD(&pmon->dp_rx_mon_mpdu_list);
+	pmon->mon_mpdu = NULL;
+
 	return 0;
 }
diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.h b/drivers/net/wireless/ath/ath12k/dp_rx.h
index 88e42365a9d8..e971a314bd2d 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.h
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.h
@@ -14,11 +14,9 @@
 
 struct ath12k_dp_rx_tid {
 	u8 tid;
-	u32 *vaddr;
-	dma_addr_t paddr;
-	u32 size;
 	u32 ba_win_sz;
 	bool active;
+	struct ath12k_reoq_buf qbuf;
 
 	/* Info related to rx fragments */
 	u32 cur_sn;
@@ -65,6 +63,24 @@ struct ath12k_dp_rx_rfc1042_hdr {
 	__be16 snap_type;
 } __packed;
 
+struct ath12k_dp_rx_info {
+	struct ieee80211_rx_status *rx_status;
+	u32 phy_meta_data;
+	u16 peer_id;
+	u8 decap_type;
+	u8 pkt_type;
+	u8 sgi;
+	u8 rate_mcs;
+	u8 bw;
+	u8 nss;
+	u8 addr2[ETH_ALEN];
+	u8 tid;
+	bool ip_csum_fail;
+	bool l4_csum_fail;
+	bool is_mcbc;
+	bool addr2_present;
+};
+
 static inline u32 ath12k_he_gi_to_nl80211_he_gi(u8 sgi)
 {
 	u32 ret = 0;
@@ -131,13 +147,13 @@ int ath12k_dp_rx_peer_frag_setup(struct ath12k *ar, const u8 *peer_mac, int vdev
 u8 ath12k_dp_rx_h_l3pad(struct ath12k_base *ab,
 			struct hal_rx_desc *desc);
 struct ath12k_peer *
-ath12k_dp_rx_h_find_peer(struct ath12k_base *ab, struct sk_buff *msdu);
+ath12k_dp_rx_h_find_peer(struct ath12k_base *ab, struct sk_buff *msdu,
+			 struct ath12k_dp_rx_info *rx_info);
 u8 ath12k_dp_rx_h_decap_type(struct ath12k_base *ab,
 			     struct hal_rx_desc *desc);
 u32 ath12k_dp_rx_h_mpdu_err(struct ath12k_base *ab,
 			    struct hal_rx_desc *desc);
-void ath12k_dp_rx_h_ppdu(struct ath12k *ar, struct hal_rx_desc *rx_desc,
-			 struct ieee80211_rx_status *rx_status);
+void ath12k_dp_rx_h_ppdu(struct ath12k *ar, struct ath12k_dp_rx_info *rx_info);
 int ath12k_dp_rxdma_ring_sel_config_qcn9274(struct ath12k_base *ab);
 int ath12k_dp_rxdma_ring_sel_config_wcn7850(struct ath12k_base *ab);
 
@@ -145,4 +161,17 @@ int ath12k_dp_htt_tlv_iter(struct ath12k_base *ab, const void *ptr, size_t len,
 			   int (*iter)(struct ath12k_base *ar, u16 tag, u16 len,
 				       const void *ptr, void *data),
 			   void *data);
+void ath12k_dp_rx_h_fetch_info(struct ath12k_base *ab,  struct hal_rx_desc *rx_desc,
+			       struct ath12k_dp_rx_info *rx_info);
+
+int ath12k_dp_rx_crypto_mic_len(struct ath12k *ar, enum hal_encrypt_type enctype);
+u32 ath12k_dp_rxdesc_get_ppduid(struct ath12k_base *ab,
+				struct hal_rx_desc *rx_desc);
+bool ath12k_dp_rxdesc_mpdu_valid(struct ath12k_base *ab,
+				 struct hal_rx_desc *rx_desc);
+int ath12k_dp_rx_link_desc_return(struct ath12k_base *ab,
+				  struct ath12k_buffer_addr *buf_addr_info,
+				  enum hal_wbm_rel_bm_act action);
+bool ath12k_dp_rxdesc_mpdu_valid(struct ath12k_base *ab,
+				 struct hal_rx_desc *rx_desc);
 #endif /* ATH12K_DP_RX_H */
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index ced232bf4aed..b6816b6c2c04 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -7,6 +7,7 @@
 #include "core.h"
 #include "dp_tx.h"
 #include "debug.h"
+#include "debugfs.h"
 #include "hw.h"
 #include "peer.h"
 #include "mac.h"
@@ -83,6 +84,7 @@ static void ath12k_dp_tx_release_txbuf(struct ath12k_dp *dp,
 				       u8 pool_id)
 {
 	spin_lock_bh(&dp->tx_desc_lock[pool_id]);
+	tx_desc->skb_ext_desc = NULL;
 	list_move_tail(&tx_desc->list, &dp->tx_desc_free_list[pool_id]);
 	spin_unlock_bh(&dp->tx_desc_lock[pool_id]);
 }
@@ -219,7 +221,8 @@ out:
 }
 
 int ath12k_dp_tx(struct ath12k *ar, struct ath12k_link_vif *arvif,
-		 struct sk_buff *skb, bool gsn_valid, int mcbc_gsn)
+		 struct sk_buff *skb, bool gsn_valid, int mcbc_gsn,
+		 bool is_mcast)
 {
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_dp *dp = &ab->dp;
@@ -229,7 +232,7 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_link_vif *arvif,
 	struct ath12k_skb_cb *skb_cb = ATH12K_SKB_CB(skb);
 	struct hal_tcl_data_cmd *hal_tcl_desc;
 	struct hal_tx_msdu_ext_desc *msg;
-	struct sk_buff *skb_ext_desc;
+	struct sk_buff *skb_ext_desc = NULL;
 	struct hal_srng *tcl_ring;
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	struct ath12k_vif *ahvif = arvif->ahvif;
@@ -347,7 +350,7 @@ tcl_ring_sel:
 	default:
 		/* TODO: Take care of other encap modes as well */
 		ret = -EINVAL;
-		atomic_inc(&ab->soc_stats.tx_err.misc_fail);
+		atomic_inc(&ab->device_stats.tx_err.misc_fail);
 		goto fail_remove_tx_buf;
 	}
 
@@ -370,7 +373,7 @@ tcl_ring_sel:
 map:
 	ti.paddr = dma_map_single(ab->dev, skb->data, skb->len, DMA_TO_DEVICE);
 	if (dma_mapping_error(ab->dev, ti.paddr)) {
-		atomic_inc(&ab->soc_stats.tx_err.misc_fail);
+		atomic_inc(&ab->device_stats.tx_err.misc_fail);
 		ath12k_warn(ab, "failed to DMA map data Tx buffer\n");
 		ret = -ENOMEM;
 		goto fail_remove_tx_buf;
@@ -415,23 +418,21 @@ map:
 			if (ret < 0) {
 				ath12k_dbg(ab, ATH12K_DBG_DP_TX,
 					   "Failed to add HTT meta data, dropping packet\n");
-				kfree_skb(skb_ext_desc);
-				goto fail_unmap_dma;
+				goto fail_free_ext_skb;
 			}
 		}
 
 		ti.paddr = dma_map_single(ab->dev, skb_ext_desc->data,
 					  skb_ext_desc->len, DMA_TO_DEVICE);
 		ret = dma_mapping_error(ab->dev, ti.paddr);
-		if (ret) {
-			kfree_skb(skb_ext_desc);
-			goto fail_unmap_dma;
-		}
+		if (ret)
+			goto fail_free_ext_skb;
 
 		ti.data_len = skb_ext_desc->len;
 		ti.type = HAL_TCL_DESC_TYPE_EXT_DESC;
 
 		skb_cb->paddr_ext_desc = ti.paddr;
+		tx_desc->skb_ext_desc = skb_ext_desc;
 	}
 
 	hal_ring_id = tx_ring->tcl_data_ring.ring_id;
@@ -447,7 +448,7 @@ map:
 		 * desc because the desc is directly enqueued onto hw queue.
 		 */
 		ath12k_hal_srng_access_end(ab, tcl_ring);
-		ab->soc_stats.tx_err.desc_na[ti.ring_id]++;
+		ab->device_stats.tx_err.desc_na[ti.ring_id]++;
 		spin_unlock_bh(&tcl_ring->lock);
 		ret = -ENOMEM;
 
@@ -462,9 +463,22 @@ map:
 			ring_selector++;
 		}
 
-		goto fail_unmap_dma;
+		goto fail_unmap_dma_ext;
 	}
 
+	spin_lock_bh(&arvif->link_stats_lock);
+	arvif->link_stats.tx_encap_type[ti.encap_type]++;
+	arvif->link_stats.tx_encrypt_type[ti.encrypt_type]++;
+	arvif->link_stats.tx_desc_type[ti.type]++;
+
+	if (is_mcast)
+		arvif->link_stats.tx_bcast_mcast++;
+	else
+		arvif->link_stats.tx_enqueued++;
+	spin_unlock_bh(&arvif->link_stats_lock);
+
+	ab->device_stats.tx_enqueued[ti.ring_id]++;
+
 	ath12k_hal_tx_cmd_desc_setup(ab, hal_tcl_desc, &ti);
 
 	ath12k_hal_srng_access_end(ab, tcl_ring);
@@ -478,16 +492,24 @@ map:
 
 	return 0;
 
-fail_unmap_dma:
-	dma_unmap_single(ab->dev, ti.paddr, ti.data_len, DMA_TO_DEVICE);
-
+fail_unmap_dma_ext:
 	if (skb_cb->paddr_ext_desc)
 		dma_unmap_single(ab->dev, skb_cb->paddr_ext_desc,
-				 sizeof(struct hal_tx_msdu_ext_desc),
+				 skb_ext_desc->len,
 				 DMA_TO_DEVICE);
+fail_free_ext_skb:
+	kfree_skb(skb_ext_desc);
+
+fail_unmap_dma:
+	dma_unmap_single(ab->dev, ti.paddr, ti.data_len, DMA_TO_DEVICE);
 
 fail_remove_tx_buf:
 	ath12k_dp_tx_release_txbuf(dp, tx_desc, pool_id);
+
+	spin_lock_bh(&arvif->link_stats_lock);
+	arvif->link_stats.tx_dropped++;
+	spin_unlock_bh(&arvif->link_stats_lock);
+
 	if (tcl_ring_retry)
 		goto tcl_ring_sel;
 
@@ -495,20 +517,23 @@ fail_remove_tx_buf:
 }
 
 static void ath12k_dp_tx_free_txbuf(struct ath12k_base *ab,
-				    struct sk_buff *msdu, u8 mac_id,
-				    struct dp_tx_ring *tx_ring)
+				    struct dp_tx_ring *tx_ring,
+				    struct ath12k_tx_desc_params *desc_params)
 {
 	struct ath12k *ar;
+	struct sk_buff *msdu = desc_params->skb;
 	struct ath12k_skb_cb *skb_cb;
-	u8 pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id);
+	u8 pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, desc_params->mac_id);
 
 	skb_cb = ATH12K_SKB_CB(msdu);
 	ar = ab->pdevs[pdev_id].ar;
 
 	dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
-	if (skb_cb->paddr_ext_desc)
+	if (skb_cb->paddr_ext_desc) {
 		dma_unmap_single(ab->dev, skb_cb->paddr_ext_desc,
-				 sizeof(struct hal_tx_msdu_ext_desc), DMA_TO_DEVICE);
+				 desc_params->skb_ext_desc->len, DMA_TO_DEVICE);
+		dev_kfree_skb_any(desc_params->skb_ext_desc);
+	}
 
 	ieee80211_free_txskb(ar->ah->hw, msdu);
 
@@ -518,26 +543,46 @@ static void ath12k_dp_tx_free_txbuf(struct ath12k_base *ab,
 
 static void
 ath12k_dp_tx_htt_tx_complete_buf(struct ath12k_base *ab,
-				 struct sk_buff *msdu,
+				 struct ath12k_tx_desc_params *desc_params,
 				 struct dp_tx_ring *tx_ring,
 				 struct ath12k_dp_htt_wbm_tx_status *ts)
 {
 	struct ieee80211_tx_info *info;
+	struct ath12k_link_vif *arvif;
 	struct ath12k_skb_cb *skb_cb;
+	struct ieee80211_vif *vif;
+	struct ath12k_vif *ahvif;
 	struct ath12k *ar;
+	struct sk_buff *msdu = desc_params->skb;
 
 	skb_cb = ATH12K_SKB_CB(msdu);
 	info = IEEE80211_SKB_CB(msdu);
 
 	ar = skb_cb->ar;
+	ab->device_stats.tx_completed[tx_ring->tcl_data_ring_id]++;
 
 	if (atomic_dec_and_test(&ar->dp.num_tx_pending))
 		wake_up(&ar->dp.tx_empty_waitq);
 
 	dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
-	if (skb_cb->paddr_ext_desc)
+	if (skb_cb->paddr_ext_desc) {
 		dma_unmap_single(ab->dev, skb_cb->paddr_ext_desc,
-				 sizeof(struct hal_tx_msdu_ext_desc), DMA_TO_DEVICE);
+				 desc_params->skb_ext_desc->len, DMA_TO_DEVICE);
+		dev_kfree_skb_any(desc_params->skb_ext_desc);
+	}
+
+	vif = skb_cb->vif;
+	if (vif) {
+		ahvif = ath12k_vif_to_ahvif(vif);
+		rcu_read_lock();
+		arvif = rcu_dereference(ahvif->link[skb_cb->link_id]);
+		if (arvif) {
+			spin_lock_bh(&arvif->link_stats_lock);
+			arvif->link_stats.tx_completed++;
+			spin_unlock_bh(&arvif->link_stats_lock);
+		}
+		rcu_read_unlock();
+	}
 
 	memset(&info->status, 0, sizeof(info->status));
 
@@ -560,10 +605,9 @@ ath12k_dp_tx_htt_tx_complete_buf(struct ath12k_base *ab,
 }
 
 static void
-ath12k_dp_tx_process_htt_tx_complete(struct ath12k_base *ab,
-				     void *desc, u8 mac_id,
-				     struct sk_buff *msdu,
-				     struct dp_tx_ring *tx_ring)
+ath12k_dp_tx_process_htt_tx_complete(struct ath12k_base *ab, void *desc,
+				     struct dp_tx_ring *tx_ring,
+				     struct ath12k_tx_desc_params *desc_params)
 {
 	struct htt_tx_wbm_completion *status_desc;
 	struct ath12k_dp_htt_wbm_tx_status ts = {0};
@@ -573,19 +617,21 @@ ath12k_dp_tx_process_htt_tx_complete(struct ath12k_base *ab,
 
 	wbm_status = le32_get_bits(status_desc->info0,
 				   HTT_TX_WBM_COMP_INFO0_STATUS);
+	ab->device_stats.fw_tx_status[wbm_status]++;
 
 	switch (wbm_status) {
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_OK:
 		ts.acked = (wbm_status == HAL_WBM_REL_HTT_TX_COMP_STATUS_OK);
 		ts.ack_rssi = le32_get_bits(status_desc->info2,
 					    HTT_TX_WBM_COMP_INFO2_ACK_RSSI);
-		ath12k_dp_tx_htt_tx_complete_buf(ab, msdu, tx_ring, &ts);
+		ath12k_dp_tx_htt_tx_complete_buf(ab, desc_params, tx_ring, &ts);
 		break;
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_DROP:
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_TTL:
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_REINJ:
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_INSPECT:
-		ath12k_dp_tx_free_txbuf(ab, msdu, mac_id, tx_ring);
+	case HAL_WBM_REL_HTT_TX_COMP_STATUS_VDEVID_MISMATCH:
+		ath12k_dp_tx_free_txbuf(ab, tx_ring, desc_params);
 		break;
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_MEC_NOTIFY:
 		/* This event is to be handled only when the driver decides to
@@ -593,7 +639,7 @@ ath12k_dp_tx_process_htt_tx_complete(struct ath12k_base *ab,
 		 */
 		break;
 	default:
-		ath12k_warn(ab, "Unknown htt tx status %d\n", wbm_status);
+		ath12k_warn(ab, "Unknown htt wbm tx status %d\n", wbm_status);
 		break;
 	}
 }
@@ -717,13 +763,18 @@ static void ath12k_dp_tx_update_txcompl(struct ath12k *ar, struct hal_tx_status
 }
 
 static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
-				       struct sk_buff *msdu,
-				       struct hal_tx_status *ts)
+				       struct ath12k_tx_desc_params *desc_params,
+				       struct hal_tx_status *ts,
+				       int ring)
 {
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_hw *ah = ar->ah;
 	struct ieee80211_tx_info *info;
+	struct ath12k_link_vif *arvif;
 	struct ath12k_skb_cb *skb_cb;
+	struct ieee80211_vif *vif;
+	struct ath12k_vif *ahvif;
+	struct sk_buff *msdu = desc_params->skb;
 
 	if (WARN_ON_ONCE(ts->buf_rel_source != HAL_WBM_REL_SRC_MODULE_TQM)) {
 		/* Must not happen */
@@ -731,11 +782,14 @@ static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
 	}
 
 	skb_cb = ATH12K_SKB_CB(msdu);
+	ab->device_stats.tx_completed[ring]++;
 
 	dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
-	if (skb_cb->paddr_ext_desc)
+	if (skb_cb->paddr_ext_desc) {
 		dma_unmap_single(ab->dev, skb_cb->paddr_ext_desc,
-				 sizeof(struct hal_tx_msdu_ext_desc), DMA_TO_DEVICE);
+				 desc_params->skb_ext_desc->len, DMA_TO_DEVICE);
+		dev_kfree_skb_any(desc_params->skb_ext_desc);
+	}
 
 	rcu_read_lock();
 
@@ -749,6 +803,17 @@ static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
 		goto exit;
 	}
 
+	vif = skb_cb->vif;
+	if (vif) {
+		ahvif = ath12k_vif_to_ahvif(vif);
+		arvif = rcu_dereference(ahvif->link[skb_cb->link_id]);
+		if (arvif) {
+			spin_lock_bh(&arvif->link_stats_lock);
+			arvif->link_stats.tx_completed++;
+			spin_unlock_bh(&arvif->link_stats_lock);
+		}
+	}
+
 	info = IEEE80211_SKB_CB(msdu);
 	memset(&info->status, 0, sizeof(info->status));
 
@@ -842,12 +907,14 @@ void ath12k_dp_tx_completion_handler(struct ath12k_base *ab, int ring_id)
 	int hal_ring_id = dp->tx_ring[ring_id].tcl_comp_ring.ring_id;
 	struct hal_srng *status_ring = &ab->hal.srng_list[hal_ring_id];
 	struct ath12k_tx_desc_info *tx_desc = NULL;
-	struct sk_buff *msdu;
 	struct hal_tx_status ts = { 0 };
+	struct ath12k_tx_desc_params desc_params;
 	struct dp_tx_ring *tx_ring = &dp->tx_ring[ring_id];
 	struct hal_wbm_release_ring *desc;
-	u8 mac_id, pdev_id;
+	u8 pdev_id;
 	u64 desc_va;
+	enum hal_wbm_rel_src_module buf_rel_source;
+	enum hal_wbm_tqm_rel_reason rel_status;
 
 	spin_lock_bh(&status_ring->lock);
 
@@ -900,28 +967,37 @@ void ath12k_dp_tx_completion_handler(struct ath12k_base *ab, int ring_id)
 			continue;
 		}
 
-		msdu = tx_desc->skb;
-		mac_id = tx_desc->mac_id;
+		desc_params.mac_id = tx_desc->mac_id;
+		desc_params.skb = tx_desc->skb;
+		desc_params.skb_ext_desc = tx_desc->skb_ext_desc;
+
+		/* Find the HAL_WBM_RELEASE_INFO0_REL_SRC_MODULE value */
+		buf_rel_source = le32_get_bits(tx_status->info0,
+					       HAL_WBM_RELEASE_INFO0_REL_SRC_MODULE);
+		ab->device_stats.tx_wbm_rel_source[buf_rel_source]++;
+
+		rel_status = le32_get_bits(tx_status->info0,
+					   HAL_WBM_COMPL_TX_INFO0_TQM_RELEASE_REASON);
+		ab->device_stats.tqm_rel_reason[rel_status]++;
 
 		/* Release descriptor as soon as extracting necessary info
 		 * to reduce contention
 		 */
 		ath12k_dp_tx_release_txbuf(dp, tx_desc, tx_desc->pool_id);
 		if (ts.buf_rel_source == HAL_WBM_REL_SRC_MODULE_FW) {
-			ath12k_dp_tx_process_htt_tx_complete(ab,
-							     (void *)tx_status,
-							     mac_id, msdu,
-							     tx_ring);
+			ath12k_dp_tx_process_htt_tx_complete(ab, (void *)tx_status,
+							     tx_ring, &desc_params);
 			continue;
 		}
 
-		pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id);
+		pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, desc_params.mac_id);
 		ar = ab->pdevs[pdev_id].ar;
 
 		if (atomic_dec_and_test(&ar->dp.num_tx_pending))
 			wake_up(&ar->dp.tx_empty_waitq);
 
-		ath12k_dp_tx_complete_msdu(ar, msdu, &ts);
+		ath12k_dp_tx_complete_msdu(ar, &desc_params, &ts,
+					   tx_ring->tcl_data_ring_id);
 	}
 }
 
@@ -1431,6 +1507,11 @@ int ath12k_dp_tx_htt_rx_monitor_mode_ring_config(struct ath12k *ar, bool reset)
 					HTT_RX_MON_MO_CTRL_FILTER_FLASG3 |
 					HTT_RX_MON_FP_DATA_FILTER_FLASG3 |
 					HTT_RX_MON_MO_DATA_FILTER_FLASG3;
+	} else {
+		tlv_filter = ath12k_mac_mon_status_filter_default;
+
+		if (ath12k_debugfs_is_extd_rx_stats_enabled(ar))
+			tlv_filter.rx_filter = ath12k_debugfs_rx_filter(ar);
 	}
 
 	if (ab->hw_params->rxdma1_enable) {
@@ -1448,6 +1529,44 @@ int ath12k_dp_tx_htt_rx_monitor_mode_ring_config(struct ath12k *ar, bool reset)
 				return ret;
 			}
 		}
+		return 0;
+	}
+
+	if (!reset) {
+		for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
+			ring_id = ab->dp.rx_mac_buf_ring[i].ring_id;
+			ret = ath12k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id,
+							       i,
+							       HAL_RXDMA_BUF,
+							       DP_RXDMA_REFILL_RING_SIZE,
+							       &tlv_filter);
+			if (ret) {
+				ath12k_err(ab,
+					   "failed to setup filter for mon rx buf %d\n",
+					   ret);
+				return ret;
+			}
+		}
+	}
+
+	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
+		ring_id = ab->dp.rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
+		if (!reset) {
+			tlv_filter.rx_filter =
+				HTT_RX_MON_FILTER_TLV_FLAGS_MON_STATUS_RING;
+		}
+
+		ret = ath12k_dp_tx_htt_rx_filter_setup(ab, ring_id,
+						       i,
+						       HAL_RXDMA_MONITOR_STATUS,
+						       RX_MON_STATUS_BUF_SIZE,
+						       &tlv_filter);
+		if (ret) {
+			ath12k_err(ab,
+				   "failed to setup filter for mon status buf %d\n",
+				   ret);
+			return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.h b/drivers/net/wireless/ath/ath12k/dp_tx.h
index a5904097dc34..10acdcf1fa8f 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.h
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.h
@@ -17,7 +17,8 @@ struct ath12k_dp_htt_wbm_tx_status {
 
 int ath12k_dp_tx_htt_h2t_ver_req_msg(struct ath12k_base *ab);
 int ath12k_dp_tx(struct ath12k *ar, struct ath12k_link_vif *arvif,
-		 struct sk_buff *skb, bool gsn_valid, int mcbc_gsn);
+		 struct sk_buff *skb, bool gsn_valid, int mcbc_gsn,
+		 bool is_mcast);
 void ath12k_dp_tx_completion_handler(struct ath12k_base *ab, int ring_id);
 
 int ath12k_dp_tx_htt_h2t_ppdu_stats_req(struct ath12k *ar, u32 mask);
diff --git a/drivers/net/wireless/ath/ath12k/fw.c b/drivers/net/wireless/ath/ath12k/fw.c
index 5be4b2d4a19d..5ac497f80cad 100644
--- a/drivers/net/wireless/ath/ath12k/fw.c
+++ b/drivers/net/wireless/ath/ath12k/fw.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
- * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
@@ -99,6 +99,8 @@ static int ath12k_fw_request_firmware_api_n(struct ath12k_base *ab,
 					__set_bit(i, ab->fw.fw_features);
 			}
 
+			ab->fw.fw_features_valid = true;
+
 			ath12k_dbg_dump(ab, ATH12K_DBG_BOOT, "features", "",
 					ab->fw.fw_features,
 					sizeof(ab->fw.fw_features));
@@ -169,3 +171,8 @@ void ath12k_fw_unmap(struct ath12k_base *ab)
 	release_firmware(ab->fw.fw);
 	memset(&ab->fw, 0, sizeof(ab->fw));
 }
+
+bool ath12k_fw_feature_supported(struct ath12k_base *ab, enum ath12k_fw_features feat)
+{
+	return ab->fw.fw_features_valid && test_bit(feat, ab->fw.fw_features);
+}
diff --git a/drivers/net/wireless/ath/ath12k/fw.h b/drivers/net/wireless/ath/ath12k/fw.h
index 273c003eff3b..7afaefed5086 100644
--- a/drivers/net/wireless/ath/ath12k/fw.h
+++ b/drivers/net/wireless/ath/ath12k/fw.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
- * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_FW_H
@@ -32,5 +32,6 @@ enum ath12k_fw_features {
 
 void ath12k_fw_map(struct ath12k_base *ab);
 void ath12k_fw_unmap(struct ath12k_base *ab);
+bool ath12k_fw_feature_supported(struct ath12k_base *ab, enum ath12k_fw_features feat);
 
 #endif /* ATH12K_FW_H */
diff --git a/drivers/net/wireless/ath/ath12k/hal.c b/drivers/net/wireless/ath/ath12k/hal.c
index cd59ff8e6c7b..a301898e5849 100644
--- a/drivers/net/wireless/ath/ath12k/hal.c
+++ b/drivers/net/wireless/ath/ath12k/hal.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/dma-mapping.h>
 #include "hal_tx.h"
@@ -154,7 +154,14 @@ static const struct hal_srng_config hw_srng_config_template[] = {
 		.ring_dir = HAL_SRNG_DIR_SRC,
 		.max_size = HAL_RXDMA_RING_MAX_SIZE_BE,
 	},
-	[HAL_RXDMA_MONITOR_STATUS] = { 0, },
+	[HAL_RXDMA_MONITOR_STATUS] = {
+		.start_ring_id = HAL_SRNG_RING_ID_WMAC1_SW2RXDMA1_STATBUF,
+		.max_rings = 1,
+		.entry_size = sizeof(struct hal_wbm_buffer_ring) >> 2,
+		.mac_type = ATH12K_HAL_SRNG_PMAC,
+		.ring_dir = HAL_SRNG_DIR_SRC,
+		.max_size = HAL_RXDMA_RING_MAX_SIZE_BE,
+	},
 	[HAL_RXDMA_MONITOR_DESC] = { 0, },
 	[HAL_RXDMA_DIR_BUF] = {
 		.start_ring_id = HAL_SRNG_RING_ID_RXDMA_DIR_BUF,
@@ -449,8 +456,8 @@ static u8 *ath12k_hw_qcn9274_rx_desc_mpdu_start_addr2(struct hal_rx_desc *desc)
 
 static bool ath12k_hw_qcn9274_rx_desc_is_da_mcbc(struct hal_rx_desc *desc)
 {
-	return __le32_to_cpu(desc->u.qcn9274.mpdu_start.info6) &
-	       RX_MPDU_START_INFO6_MCAST_BCAST;
+	return __le16_to_cpu(desc->u.qcn9274.msdu_end.info5) &
+	       RX_MSDU_END_INFO5_DA_IS_MCBC;
 }
 
 static void ath12k_hw_qcn9274_rx_desc_get_dot11_hdr(struct hal_rx_desc *desc,
@@ -511,11 +518,6 @@ static void ath12k_hw_qcn9274_rx_desc_get_crypto_hdr(struct hal_rx_desc *desc,
 	crypto_hdr[7] = HAL_RX_MPDU_INFO_PN_GET_BYTE2(desc->u.qcn9274.mpdu_start.pn[1]);
 }
 
-static u16 ath12k_hw_qcn9274_rx_desc_get_mpdu_frame_ctl(struct hal_rx_desc *desc)
-{
-	return __le16_to_cpu(desc->u.qcn9274.mpdu_start.frame_ctrl);
-}
-
 static int ath12k_hal_srng_create_config_qcn9274(struct ath12k_base *ab)
 {
 	struct ath12k_hal *hal = &ab->hal;
@@ -552,9 +554,9 @@ static int ath12k_hal_srng_create_config_qcn9274(struct ath12k_base *ab)
 	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_REO_REG + HAL_REO_STATUS_HP;
 
 	s = &hal->srng_config[HAL_TCL_DATA];
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_BASE_LSB;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_BASE_LSB(ab);
 	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_HP;
-	s->reg_size[0] = HAL_TCL2_RING_BASE_LSB - HAL_TCL1_RING_BASE_LSB;
+	s->reg_size[0] = HAL_TCL2_RING_BASE_LSB(ab) - HAL_TCL1_RING_BASE_LSB(ab);
 	s->reg_size[1] = HAL_TCL2_RING_HP - HAL_TCL1_RING_HP;
 
 	s = &hal->srng_config[HAL_TCL_CMD];
@@ -566,29 +568,29 @@ static int ath12k_hal_srng_create_config_qcn9274(struct ath12k_base *ab)
 	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL_STATUS_RING_HP;
 
 	s = &hal->srng_config[HAL_CE_SRC];
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG + HAL_CE_DST_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG + HAL_CE_DST_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab) + HAL_CE_DST_RING_BASE_LSB;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab) + HAL_CE_DST_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab);
 
 	s = &hal->srng_config[HAL_CE_DST];
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_RING_BASE_LSB;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
 
 	s = &hal->srng_config[HAL_CE_DST_STATUS];
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG +
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) +
 		HAL_CE_DST_STATUS_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_STATUS_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_STATUS_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
 
 	s = &hal->srng_config[HAL_WBM_IDLE_LINK];
 	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_WBM_REG + HAL_WBM_IDLE_LINK_RING_BASE_LSB(ab);
@@ -736,7 +738,6 @@ const struct hal_rx_ops hal_rx_qcn9274_ops = {
 	.rx_desc_is_da_mcbc = ath12k_hw_qcn9274_rx_desc_is_da_mcbc,
 	.rx_desc_get_dot11_hdr = ath12k_hw_qcn9274_rx_desc_get_dot11_hdr,
 	.rx_desc_get_crypto_header = ath12k_hw_qcn9274_rx_desc_get_crypto_hdr,
-	.rx_desc_get_mpdu_frame_ctl = ath12k_hw_qcn9274_rx_desc_get_mpdu_frame_ctl,
 	.dp_rx_h_msdu_done = ath12k_hw_qcn9274_dp_rx_h_msdu_done,
 	.dp_rx_h_l4_cksum_fail = ath12k_hw_qcn9274_dp_rx_h_l4_cksum_fail,
 	.dp_rx_h_ip_cksum_fail = ath12k_hw_qcn9274_dp_rx_h_ip_cksum_fail,
@@ -908,8 +909,8 @@ static u8 *ath12k_hw_qcn9274_compact_rx_desc_mpdu_start_addr2(struct hal_rx_desc
 
 static bool ath12k_hw_qcn9274_compact_rx_desc_is_da_mcbc(struct hal_rx_desc *desc)
 {
-	return __le32_to_cpu(desc->u.qcn9274_compact.mpdu_start.info6) &
-	       RX_MPDU_START_INFO6_MCAST_BCAST;
+	return __le16_to_cpu(desc->u.qcn9274_compact.msdu_end.info5) &
+	       RX_MSDU_END_INFO5_DA_IS_MCBC;
 }
 
 static void ath12k_hw_qcn9274_compact_rx_desc_get_dot11_hdr(struct hal_rx_desc *desc,
@@ -975,11 +976,6 @@ ath12k_hw_qcn9274_compact_rx_desc_get_crypto_hdr(struct hal_rx_desc *desc,
 		HAL_RX_MPDU_INFO_PN_GET_BYTE2(desc->u.qcn9274_compact.mpdu_start.pn[1]);
 }
 
-static u16 ath12k_hw_qcn9274_compact_rx_desc_get_mpdu_frame_ctl(struct hal_rx_desc *desc)
-{
-	return __le16_to_cpu(desc->u.qcn9274_compact.mpdu_start.frame_ctrl);
-}
-
 static bool ath12k_hw_qcn9274_compact_dp_rx_h_msdu_done(struct hal_rx_desc *desc)
 {
 	return !!le32_get_bits(desc->u.qcn9274_compact.msdu_end.info14,
@@ -1080,8 +1076,6 @@ const struct hal_rx_ops hal_rx_qcn9274_compact_ops = {
 	.rx_desc_is_da_mcbc = ath12k_hw_qcn9274_compact_rx_desc_is_da_mcbc,
 	.rx_desc_get_dot11_hdr = ath12k_hw_qcn9274_compact_rx_desc_get_dot11_hdr,
 	.rx_desc_get_crypto_header = ath12k_hw_qcn9274_compact_rx_desc_get_crypto_hdr,
-	.rx_desc_get_mpdu_frame_ctl =
-		ath12k_hw_qcn9274_compact_rx_desc_get_mpdu_frame_ctl,
 	.dp_rx_h_msdu_done = ath12k_hw_qcn9274_compact_dp_rx_h_msdu_done,
 	.dp_rx_h_l4_cksum_fail = ath12k_hw_qcn9274_compact_dp_rx_h_l4_cksum_fail,
 	.dp_rx_h_ip_cksum_fail = ath12k_hw_qcn9274_compact_dp_rx_h_ip_cksum_fail,
@@ -1330,11 +1324,6 @@ static void ath12k_hw_wcn7850_rx_desc_get_crypto_hdr(struct hal_rx_desc *desc,
 	crypto_hdr[7] = HAL_RX_MPDU_INFO_PN_GET_BYTE2(desc->u.wcn7850.mpdu_start.pn[1]);
 }
 
-static u16 ath12k_hw_wcn7850_rx_desc_get_mpdu_frame_ctl(struct hal_rx_desc *desc)
-{
-	return __le16_to_cpu(desc->u.wcn7850.mpdu_start.frame_ctrl);
-}
-
 static int ath12k_hal_srng_create_config_wcn7850(struct ath12k_base *ab)
 {
 	struct ath12k_hal *hal = &ab->hal;
@@ -1371,9 +1360,9 @@ static int ath12k_hal_srng_create_config_wcn7850(struct ath12k_base *ab)
 
 	s = &hal->srng_config[HAL_TCL_DATA];
 	s->max_rings = 5;
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_BASE_LSB;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_BASE_LSB(ab);
 	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_HP;
-	s->reg_size[0] = HAL_TCL2_RING_BASE_LSB - HAL_TCL1_RING_BASE_LSB;
+	s->reg_size[0] = HAL_TCL2_RING_BASE_LSB(ab) - HAL_TCL1_RING_BASE_LSB(ab);
 	s->reg_size[1] = HAL_TCL2_RING_HP - HAL_TCL1_RING_HP;
 
 	s = &hal->srng_config[HAL_TCL_CMD];
@@ -1386,31 +1375,31 @@ static int ath12k_hal_srng_create_config_wcn7850(struct ath12k_base *ab)
 
 	s = &hal->srng_config[HAL_CE_SRC];
 	s->max_rings = 12;
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG + HAL_CE_DST_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG + HAL_CE_DST_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab) + HAL_CE_DST_RING_BASE_LSB;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab) + HAL_CE_DST_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab);
 
 	s = &hal->srng_config[HAL_CE_DST];
 	s->max_rings = 12;
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_RING_BASE_LSB;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
 
 	s = &hal->srng_config[HAL_CE_DST_STATUS];
 	s->max_rings = 12;
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG +
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) +
 		HAL_CE_DST_STATUS_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_STATUS_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_STATUS_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
 
 	s = &hal->srng_config[HAL_WBM_IDLE_LINK];
 	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_WBM_REG + HAL_WBM_IDLE_LINK_RING_BASE_LSB(ab);
@@ -1555,7 +1544,6 @@ const struct hal_rx_ops hal_rx_wcn7850_ops = {
 	.rx_desc_is_da_mcbc = ath12k_hw_wcn7850_rx_desc_is_da_mcbc,
 	.rx_desc_get_dot11_hdr = ath12k_hw_wcn7850_rx_desc_get_dot11_hdr,
 	.rx_desc_get_crypto_header = ath12k_hw_wcn7850_rx_desc_get_crypto_hdr,
-	.rx_desc_get_mpdu_frame_ctl = ath12k_hw_wcn7850_rx_desc_get_mpdu_frame_ctl,
 	.dp_rx_h_msdu_done = ath12k_hw_wcn7850_dp_rx_h_msdu_done,
 	.dp_rx_h_l4_cksum_fail = ath12k_hw_wcn7850_dp_rx_h_l4_cksum_fail,
 	.dp_rx_h_ip_cksum_fail = ath12k_hw_wcn7850_dp_rx_h_ip_cksum_fail,
@@ -1756,7 +1744,7 @@ static void ath12k_hal_srng_src_hw_init(struct ath12k_base *ab,
 			      HAL_TCL1_RING_BASE_MSB_RING_BASE_ADDR_MSB) |
 	      u32_encode_bits((srng->entry_size * srng->num_entries),
 			      HAL_TCL1_RING_BASE_MSB_RING_SIZE);
-	ath12k_hif_write32(ab, reg_base + HAL_TCL1_RING_BASE_MSB_OFFSET, val);
+	ath12k_hif_write32(ab, reg_base + HAL_TCL1_RING_BASE_MSB_OFFSET(ab), val);
 
 	val = u32_encode_bits(srng->entry_size, HAL_REO1_RING_ID_ENTRY_SIZE);
 	ath12k_hif_write32(ab, reg_base + HAL_TCL1_RING_ID_OFFSET(ab), val);
@@ -1962,7 +1950,7 @@ u32 ath12k_hal_ce_dst_status_get_length(struct hal_ce_srng_dst_status_desc *desc
 {
 	u32 len;
 
-	len = le32_get_bits(desc->flags, HAL_CE_DST_STATUS_DESC_FLAGS_LEN);
+	len = le32_get_bits(READ_ONCE(desc->flags), HAL_CE_DST_STATUS_DESC_FLAGS_LEN);
 	desc->flags &= ~cpu_to_le32(HAL_CE_DST_STATUS_DESC_FLAGS_LEN);
 
 	return len;
@@ -2054,6 +2042,24 @@ int ath12k_hal_srng_src_num_free(struct ath12k_base *ab, struct hal_srng *srng,
 		return ((srng->ring_size - hp + tp) / srng->entry_size) - 1;
 }
 
+void *ath12k_hal_srng_src_next_peek(struct ath12k_base *ab,
+				    struct hal_srng *srng)
+{
+	void *desc;
+	u32 next_hp;
+
+	lockdep_assert_held(&srng->lock);
+
+	next_hp = (srng->u.src_ring.hp + srng->entry_size) % srng->ring_size;
+
+	if (next_hp == srng->u.src_ring.cached_tp)
+		return NULL;
+
+	desc = srng->ring_base_vaddr + next_hp;
+
+	return desc;
+}
+
 void *ath12k_hal_srng_src_get_next_entry(struct ath12k_base *ab,
 					 struct hal_srng *srng)
 {
@@ -2087,6 +2093,17 @@ void *ath12k_hal_srng_src_get_next_entry(struct ath12k_base *ab,
 	return desc;
 }
 
+void *ath12k_hal_srng_src_peek(struct ath12k_base *ab, struct hal_srng *srng)
+{
+	lockdep_assert_held(&srng->lock);
+
+	if (((srng->u.src_ring.hp + srng->entry_size) % srng->ring_size) ==
+	    srng->u.src_ring.cached_tp)
+		return NULL;
+
+	return srng->ring_base_vaddr + srng->u.src_ring.hp;
+}
+
 void *ath12k_hal_srng_src_reap_next(struct ath12k_base *ab,
 				    struct hal_srng *srng)
 {
@@ -2132,7 +2149,7 @@ void ath12k_hal_srng_access_begin(struct ath12k_base *ab, struct hal_srng *srng)
 		srng->u.src_ring.cached_tp =
 			*(volatile u32 *)srng->u.src_ring.tp_addr;
 	else
-		srng->u.dst_ring.cached_hp = *srng->u.dst_ring.hp_addr;
+		srng->u.dst_ring.cached_hp = READ_ONCE(*srng->u.dst_ring.hp_addr);
 }
 
 /* Update cached ring head/tail pointers to HW. ath12k_hal_srng_access_begin()
diff --git a/drivers/net/wireless/ath/ath12k/hal.h b/drivers/net/wireless/ath/ath12k/hal.h
index 94e2e8735958..0ee9c6b26dab 100644
--- a/drivers/net/wireless/ath/ath12k/hal.h
+++ b/drivers/net/wireless/ath/ath12k/hal.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_HAL_H
@@ -11,6 +11,7 @@
 #include "rx_desc.h"
 
 struct ath12k_base;
+#define HAL_CE_REMAP_REG_BASE	(ab->ce_remap_base_addr)
 
 #define HAL_LINK_DESC_SIZE			(32 << 2)
 #define HAL_LINK_DESC_ALIGN			128
@@ -21,6 +22,7 @@ struct ath12k_base;
 #define HAL_MAX_AVAIL_BLK_RES			3
 
 #define HAL_RING_BASE_ALIGN	8
+#define HAL_REO_QLUT_ADDR_ALIGN 256
 
 #define HAL_WBM_IDLE_SCATTER_BUF_SIZE_MAX	32704
 /* TODO: Check with hw team on the supported scatter buf size */
@@ -39,15 +41,21 @@ struct ath12k_base;
 #define HAL_OFFSET_FROM_HP_TO_TP		4
 
 #define HAL_SHADOW_REG(x) (HAL_SHADOW_BASE_ADDR + (4 * (x)))
+#define HAL_REO_QDESC_MAX_PEERID		8191
 
 /* WCSS Relative address */
+#define HAL_SEQ_WCSS_CMEM_OFFSET		0x00100000
 #define HAL_SEQ_WCSS_UMAC_OFFSET		0x00a00000
 #define HAL_SEQ_WCSS_UMAC_REO_REG		0x00a38000
 #define HAL_SEQ_WCSS_UMAC_TCL_REG		0x00a44000
-#define HAL_SEQ_WCSS_UMAC_CE0_SRC_REG		0x01b80000
-#define HAL_SEQ_WCSS_UMAC_CE0_DST_REG		0x01b81000
-#define HAL_SEQ_WCSS_UMAC_CE1_SRC_REG		0x01b82000
-#define HAL_SEQ_WCSS_UMAC_CE1_DST_REG		0x01b83000
+#define HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab) \
+	((ab)->hw_params->regs->hal_umac_ce0_src_reg_base)
+#define HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) \
+	((ab)->hw_params->regs->hal_umac_ce0_dest_reg_base)
+#define HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(ab) \
+	((ab)->hw_params->regs->hal_umac_ce1_src_reg_base)
+#define HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) \
+	((ab)->hw_params->regs->hal_umac_ce1_dest_reg_base)
 #define HAL_SEQ_WCSS_UMAC_WBM_REG		0x00a34000
 
 #define HAL_CE_WFSS_CE_REG_BASE			0x01b80000
@@ -57,8 +65,10 @@ struct ath12k_base;
 /* SW2TCL(x) R0 ring configuration address */
 #define HAL_TCL1_RING_CMN_CTRL_REG		0x00000020
 #define HAL_TCL1_RING_DSCP_TID_MAP		0x00000240
-#define HAL_TCL1_RING_BASE_LSB			0x00000900
-#define HAL_TCL1_RING_BASE_MSB			0x00000904
+#define HAL_TCL1_RING_BASE_LSB(ab) \
+	((ab)->hw_params->regs->hal_tcl1_ring_base_lsb)
+#define HAL_TCL1_RING_BASE_MSB(ab) \
+	((ab)->hw_params->regs->hal_tcl1_ring_base_msb)
 #define HAL_TCL1_RING_ID(ab)			((ab)->hw_params->regs->hal_tcl1_ring_id)
 #define HAL_TCL1_RING_MISC(ab) \
 	((ab)->hw_params->regs->hal_tcl1_ring_misc)
@@ -76,30 +86,31 @@ struct ath12k_base;
 	((ab)->hw_params->regs->hal_tcl1_ring_msi1_base_msb)
 #define HAL_TCL1_RING_MSI1_DATA(ab) \
 	((ab)->hw_params->regs->hal_tcl1_ring_msi1_data)
-#define HAL_TCL2_RING_BASE_LSB			0x00000978
+#define HAL_TCL2_RING_BASE_LSB(ab) \
+	((ab)->hw_params->regs->hal_tcl2_ring_base_lsb)
 #define HAL_TCL_RING_BASE_LSB(ab) \
 	((ab)->hw_params->regs->hal_tcl_ring_base_lsb)
 
-#define HAL_TCL1_RING_MSI1_BASE_LSB_OFFSET(ab)				\
-	(HAL_TCL1_RING_MSI1_BASE_LSB(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_MSI1_BASE_MSB_OFFSET(ab)				\
-	(HAL_TCL1_RING_MSI1_BASE_MSB(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_MSI1_DATA_OFFSET(ab)				\
-	(HAL_TCL1_RING_MSI1_DATA(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_BASE_MSB_OFFSET				\
-	(HAL_TCL1_RING_BASE_MSB - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_ID_OFFSET(ab)				\
-	(HAL_TCL1_RING_ID(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_CONSR_INT_SETUP_IX0_OFFSET(ab)			\
-	(HAL_TCL1_RING_CONSUMER_INT_SETUP_IX0(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_CONSR_INT_SETUP_IX1_OFFSET(ab) \
-		(HAL_TCL1_RING_CONSUMER_INT_SETUP_IX1(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_TP_ADDR_LSB_OFFSET(ab) \
-		(HAL_TCL1_RING_TP_ADDR_LSB(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_TP_ADDR_MSB_OFFSET(ab) \
-		(HAL_TCL1_RING_TP_ADDR_MSB(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_MISC_OFFSET(ab) \
-		(HAL_TCL1_RING_MISC(ab) - HAL_TCL1_RING_BASE_LSB)
+#define HAL_TCL1_RING_MSI1_BASE_LSB_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_MSI1_BASE_LSB(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_MSI1_BASE_MSB_OFFSET(ab)	({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_MSI1_BASE_MSB(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_MSI1_DATA_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_MSI1_DATA(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_BASE_MSB_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_BASE_MSB(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_ID_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_ID(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_CONSR_INT_SETUP_IX0_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_CONSUMER_INT_SETUP_IX0(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_CONSR_INT_SETUP_IX1_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_CONSUMER_INT_SETUP_IX1(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_TP_ADDR_LSB_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_TP_ADDR_LSB(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_TP_ADDR_MSB_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_TP_ADDR_MSB(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_MISC_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_MISC(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
 
 /* SW2TCL(x) R2 ring pointers (head/tail) address */
 #define HAL_TCL1_RING_HP			0x00002000
@@ -132,6 +143,8 @@ struct ath12k_base;
 #define HAL_REO1_DEST_RING_CTRL_IX_1		0x00000008
 #define HAL_REO1_DEST_RING_CTRL_IX_2		0x0000000c
 #define HAL_REO1_DEST_RING_CTRL_IX_3		0x00000010
+#define HAL_REO1_QDESC_ADDR(ab)		((ab)->hw_params->regs->hal_reo1_qdesc_addr)
+#define HAL_REO1_QDESC_MAX_PEERID(ab)	((ab)->hw_params->regs->hal_reo1_qdesc_max_peerid)
 #define HAL_REO1_SW_COOKIE_CFG0(ab)	((ab)->hw_params->regs->hal_reo1_sw_cookie_cfg0)
 #define HAL_REO1_SW_COOKIE_CFG1(ab)	((ab)->hw_params->regs->hal_reo1_sw_cookie_cfg1)
 #define HAL_REO1_QDESC_LUT_BASE0(ab)	((ab)->hw_params->regs->hal_reo1_qdesc_lut_base0)
@@ -319,6 +332,8 @@ struct ath12k_base;
 #define HAL_REO1_SW_COOKIE_CFG_ALIGN			BIT(18)
 #define HAL_REO1_SW_COOKIE_CFG_ENABLE			BIT(19)
 #define HAL_REO1_SW_COOKIE_CFG_GLOBAL_ENABLE		BIT(20)
+#define HAL_REO_QDESC_ADDR_READ_LUT_ENABLE		BIT(7)
+#define HAL_REO_QDESC_ADDR_READ_CLEAR_QDESC_ARRAY	BIT(6)
 
 /* CE ring bit field mask and shift */
 #define HAL_CE_DST_R0_DEST_CTRL_MAX_LEN			GENMASK(15, 0)
@@ -365,6 +380,9 @@ struct ath12k_base;
  * ath12k_hal_rx_desc_get_err().
  */
 
+#define HAL_IPQ5332_CE_WFSS_REG_BASE	0x740000
+#define HAL_IPQ5332_CE_SIZE		0x100000
+
 enum hal_srng_ring_id {
 	HAL_SRNG_RING_ID_REO2SW0 = 0,
 	HAL_SRNG_RING_ID_REO2SW1,
@@ -480,6 +498,7 @@ enum hal_srng_ring_id {
 
 	HAL_SRNG_RING_ID_WMAC1_SW2RXMON_BUF0 = HAL_SRNG_RING_ID_PMAC1_ID_START,
 
+	HAL_SRNG_RING_ID_WMAC1_SW2RXDMA1_STATBUF,
 	HAL_SRNG_RING_ID_WMAC1_RXDMA2SW0,
 	HAL_SRNG_RING_ID_WMAC1_RXDMA2SW1,
 	HAL_SRNG_RING_ID_WMAC1_RXMON2SW0 = HAL_SRNG_RING_ID_WMAC1_RXDMA2SW1,
@@ -1068,7 +1087,6 @@ struct hal_rx_ops {
 	bool (*rx_desc_is_da_mcbc)(struct hal_rx_desc *desc);
 	void (*rx_desc_get_dot11_hdr)(struct hal_rx_desc *desc,
 				      struct ieee80211_hdr *hdr);
-	u16 (*rx_desc_get_mpdu_frame_ctl)(struct hal_rx_desc *desc);
 	void (*rx_desc_get_crypto_header)(struct hal_rx_desc *desc,
 					  u8 *crypto_hdr,
 					  enum hal_encrypt_type enctype);
@@ -1126,6 +1144,7 @@ void ath12k_hal_srng_get_params(struct ath12k_base *ab, struct hal_srng *srng,
 				struct hal_srng_params *params);
 void *ath12k_hal_srng_dst_get_next_entry(struct ath12k_base *ab,
 					 struct hal_srng *srng);
+void *ath12k_hal_srng_src_peek(struct ath12k_base *ab, struct hal_srng *srng);
 void *ath12k_hal_srng_dst_peek(struct ath12k_base *ab, struct hal_srng *srng);
 int ath12k_hal_srng_dst_num_free(struct ath12k_base *ab, struct hal_srng *srng,
 				 bool sync_hw_ptr);
@@ -1133,6 +1152,8 @@ void *ath12k_hal_srng_src_get_next_reaped(struct ath12k_base *ab,
 					  struct hal_srng *srng);
 void *ath12k_hal_srng_src_reap_next(struct ath12k_base *ab,
 				    struct hal_srng *srng);
+void *ath12k_hal_srng_src_next_peek(struct ath12k_base *ab,
+				    struct hal_srng *srng);
 void *ath12k_hal_srng_src_get_next_entry(struct ath12k_base *ab,
 					 struct hal_srng *srng);
 int ath12k_hal_srng_src_num_free(struct ath12k_base *ab, struct hal_srng *srng,
@@ -1154,4 +1175,5 @@ int ath12k_hal_srng_update_shadow_config(struct ath12k_base *ab,
 void ath12k_hal_srng_shadow_config(struct ath12k_base *ab);
 void ath12k_hal_srng_shadow_update_hp_tp(struct ath12k_base *ab,
 					 struct hal_srng *srng);
+void ath12k_hal_reo_shared_qaddr_cache_clear(struct ath12k_base *ab);
 #endif
diff --git a/drivers/net/wireless/ath/ath12k/hal_desc.h b/drivers/net/wireless/ath/ath12k/hal_desc.h
index 3e8983b85de8..0173f731bfef 100644
--- a/drivers/net/wireless/ath/ath12k/hal_desc.h
+++ b/drivers/net/wireless/ath/ath12k/hal_desc.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include "core.h"
 
@@ -707,7 +707,7 @@ enum hal_rx_msdu_desc_reo_dest_ind {
 #define RX_MSDU_DESC_INFO0_DECAP_FORMAT		GENMASK(30, 29)
 
 #define HAL_RX_MSDU_PKT_LENGTH_GET(val)		\
-	(u32_get_bits((val), RX_MSDU_DESC_INFO0_MSDU_LENGTH))
+	(le32_get_bits((val), RX_MSDU_DESC_INFO0_MSDU_LENGTH))
 
 struct rx_msdu_desc {
 	__le32 info0;
@@ -1008,6 +1008,10 @@ enum hal_reo_entr_rxdma_ecode {
 	HAL_REO_ENTR_RING_RXDMA_ECODE_FLOW_TIMEOUT_ERR,
 	HAL_REO_ENTR_RING_RXDMA_ECODE_FLUSH_REQUEST_ERR,
 	HAL_REO_ENTR_RING_RXDMA_ECODE_AMSDU_FRAG_ERR,
+	HAL_REO_ENTR_RING_RXDMA_ECODE_MULTICAST_ECHO_ERR,
+	HAL_REO_ENTR_RING_RXDMA_ECODE_AMSDU_MISMATCH_ERR,
+	HAL_REO_ENTR_RING_RXDMA_ECODE_UNAUTH_WDS_ERR,
+	HAL_REO_ENTR_RING_RXDMA_ECODE_GRPCAST_AMSDU_WDS_ERR,
 	HAL_REO_ENTR_RING_RXDMA_ECODE_MAX,
 };
 
@@ -1284,11 +1288,13 @@ enum hal_tcl_encap_type {
 	HAL_TCL_ENCAP_TYPE_NATIVE_WIFI,
 	HAL_TCL_ENCAP_TYPE_ETHERNET,
 	HAL_TCL_ENCAP_TYPE_802_3 = 3,
+	HAL_TCL_ENCAP_TYPE_MAX
 };
 
 enum hal_tcl_desc_type {
 	HAL_TCL_DESC_TYPE_BUFFER,
 	HAL_TCL_DESC_TYPE_EXT_DESC,
+	HAL_TCL_DESC_TYPE_MAX,
 };
 
 enum hal_wbm_htt_tx_comp_status {
@@ -1298,6 +1304,7 @@ enum hal_wbm_htt_tx_comp_status {
 	HAL_WBM_REL_HTT_TX_COMP_STATUS_REINJ,
 	HAL_WBM_REL_HTT_TX_COMP_STATUS_INSPECT,
 	HAL_WBM_REL_HTT_TX_COMP_STATUS_MEC_NOTIFY,
+	HAL_WBM_REL_HTT_TX_COMP_STATUS_VDEVID_MISMATCH,
 	HAL_WBM_REL_HTT_TX_COMP_STATUS_MAX,
 };
 
@@ -1806,6 +1813,7 @@ enum hal_wbm_rel_src_module {
 	HAL_WBM_REL_SRC_MODULE_REO,
 	HAL_WBM_REL_SRC_MODULE_FW,
 	HAL_WBM_REL_SRC_MODULE_SW,
+	HAL_WBM_REL_SRC_MODULE_MAX,
 };
 
 enum hal_wbm_rel_desc_type {
@@ -1998,6 +2006,7 @@ struct hal_wbm_release_ring_cc_rx {
 #define HAL_WBM_RELEASE_INFO3_CONTINUATION		BIT(2)
 
 #define HAL_WBM_RELEASE_INFO5_LOOPING_COUNT		GENMASK(31, 28)
+#define HAL_ENCRYPT_TYPE_MAX 12
 
 struct hal_wbm_release_ring {
 	struct ath12k_buffer_addr buf_addr_info;
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.c b/drivers/net/wireless/ath/ath12k/hal_rx.c
index ac17d6223fa7..48aa48c48606 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.c
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "debug.h"
@@ -326,7 +326,7 @@ int ath12k_hal_desc_reo_parse_err(struct ath12k_base *ab,
 				    HAL_REO_DEST_RING_INFO0_PUSH_REASON);
 	err_code = le32_get_bits(desc->info0,
 				 HAL_REO_DEST_RING_INFO0_ERROR_CODE);
-	ab->soc_stats.reo_error[err_code]++;
+	ab->device_stats.reo_error[err_code]++;
 
 	if (push_reason != HAL_REO_DEST_RING_PUSH_REASON_ERR_DETECTED &&
 	    push_reason != HAL_REO_DEST_RING_PUSH_REASON_ROUTING_INSTRUCTION) {
@@ -381,7 +381,7 @@ int ath12k_hal_wbm_desc_parse_err(struct ath12k_base *ab, void *desc,
 		val = le32_get_bits(wbm_desc->buf_addr_info.info1,
 				    BUFFER_ADDR_INFO1_RET_BUF_MGR);
 		if (val != HAL_RX_BUF_RBM_SW3_BM) {
-			ab->soc_stats.invalid_rbm++;
+			ab->device_stats.invalid_rbm++;
 			return -EINVAL;
 		}
 
@@ -393,7 +393,7 @@ int ath12k_hal_wbm_desc_parse_err(struct ath12k_base *ab, void *desc,
 		val = le32_get_bits(wbm_cc_desc->info0,
 				    HAL_WBM_RELEASE_RX_CC_INFO0_RBM);
 		if (val != HAL_RX_BUF_RBM_SW3_BM) {
-			ab->soc_stats.invalid_rbm++;
+			ab->device_stats.invalid_rbm++;
 			return -EINVAL;
 		}
 
@@ -446,17 +446,97 @@ void ath12k_hal_rx_reo_ent_paddr_get(struct ath12k_base *ab,
 	*cookie = le32_get_bits(buff_addr->info1, BUFFER_ADDR_INFO1_SW_COOKIE);
 }
 
+void ath12k_hal_rx_reo_ent_buf_paddr_get(void *rx_desc, dma_addr_t *paddr,
+					 u32 *sw_cookie,
+					 struct ath12k_buffer_addr **pp_buf_addr,
+					 u8 *rbm, u32 *msdu_cnt)
+{
+	struct hal_reo_entrance_ring *reo_ent_ring =
+		(struct hal_reo_entrance_ring *)rx_desc;
+	struct ath12k_buffer_addr *buf_addr_info;
+	struct rx_mpdu_desc *rx_mpdu_desc_info_details;
+
+	rx_mpdu_desc_info_details =
+			(struct rx_mpdu_desc *)&reo_ent_ring->rx_mpdu_info;
+
+	*msdu_cnt = le32_get_bits(rx_mpdu_desc_info_details->info0,
+				  RX_MPDU_DESC_INFO0_MSDU_COUNT);
+
+	buf_addr_info = (struct ath12k_buffer_addr *)&reo_ent_ring->buf_addr_info;
+
+	*paddr = (((u64)le32_get_bits(buf_addr_info->info1,
+				      BUFFER_ADDR_INFO1_ADDR)) << 32) |
+			le32_get_bits(buf_addr_info->info0,
+				      BUFFER_ADDR_INFO0_ADDR);
+
+	*sw_cookie = le32_get_bits(buf_addr_info->info1,
+				   BUFFER_ADDR_INFO1_SW_COOKIE);
+	*rbm = le32_get_bits(buf_addr_info->info1,
+			     BUFFER_ADDR_INFO1_RET_BUF_MGR);
+
+	*pp_buf_addr = (void *)buf_addr_info;
+}
+
+void ath12k_hal_rx_msdu_list_get(struct ath12k *ar,
+				 struct hal_rx_msdu_link *link_desc,
+				 struct hal_rx_msdu_list *msdu_list,
+				 u16 *num_msdus)
+{
+	struct hal_rx_msdu_details *msdu_details = NULL;
+	struct rx_msdu_desc *msdu_desc_info = NULL;
+	u32 last = 0, first = 0;
+	u8 tmp = 0;
+	int i;
+
+	last = u32_encode_bits(last, RX_MSDU_DESC_INFO0_LAST_MSDU_IN_MPDU);
+	first = u32_encode_bits(first, RX_MSDU_DESC_INFO0_FIRST_MSDU_IN_MPDU);
+	msdu_details = &link_desc->msdu_link[0];
+
+	for (i = 0; i < HAL_RX_NUM_MSDU_DESC; i++) {
+		if (!i && le32_get_bits(msdu_details[i].buf_addr_info.info0,
+					BUFFER_ADDR_INFO0_ADDR) == 0)
+			break;
+		if (le32_get_bits(msdu_details[i].buf_addr_info.info0,
+				  BUFFER_ADDR_INFO0_ADDR) == 0) {
+			msdu_desc_info = &msdu_details[i - 1].rx_msdu_info;
+			msdu_desc_info->info0 |= cpu_to_le32(last);
+			break;
+		}
+		msdu_desc_info = &msdu_details[i].rx_msdu_info;
+
+		if (!i)
+			msdu_desc_info->info0 |= cpu_to_le32(first);
+		else if (i == (HAL_RX_NUM_MSDU_DESC - 1))
+			msdu_desc_info->info0 |= cpu_to_le32(last);
+		msdu_list->msdu_info[i].msdu_flags = le32_to_cpu(msdu_desc_info->info0);
+		msdu_list->msdu_info[i].msdu_len =
+			 HAL_RX_MSDU_PKT_LENGTH_GET(msdu_desc_info->info0);
+		msdu_list->sw_cookie[i] =
+			le32_get_bits(msdu_details[i].buf_addr_info.info1,
+				      BUFFER_ADDR_INFO1_SW_COOKIE);
+		tmp = le32_get_bits(msdu_details[i].buf_addr_info.info1,
+				    BUFFER_ADDR_INFO1_RET_BUF_MGR);
+		msdu_list->paddr[i] =
+			((u64)(le32_get_bits(msdu_details[i].buf_addr_info.info1,
+					     BUFFER_ADDR_INFO1_ADDR)) << 32) |
+			le32_get_bits(msdu_details[i].buf_addr_info.info0,
+				      BUFFER_ADDR_INFO0_ADDR);
+		msdu_list->rbm[i] = tmp;
+	}
+	*num_msdus = i;
+}
+
 void ath12k_hal_rx_msdu_link_desc_set(struct ath12k_base *ab,
-				      struct hal_wbm_release_ring *dst_desc,
-				      struct hal_wbm_release_ring *src_desc,
+				      struct hal_wbm_release_ring *desc,
+				      struct ath12k_buffer_addr *buf_addr_info,
 				      enum hal_wbm_rel_bm_act action)
 {
-	dst_desc->buf_addr_info = src_desc->buf_addr_info;
-	dst_desc->info0 |= le32_encode_bits(HAL_WBM_REL_SRC_MODULE_SW,
-					    HAL_WBM_RELEASE_INFO0_REL_SRC_MODULE) |
-			   le32_encode_bits(action, HAL_WBM_RELEASE_INFO0_BM_ACTION) |
-			   le32_encode_bits(HAL_WBM_REL_DESC_TYPE_MSDU_LINK,
-					    HAL_WBM_RELEASE_INFO0_DESC_TYPE);
+	desc->buf_addr_info = *buf_addr_info;
+	desc->info0 |= le32_encode_bits(HAL_WBM_REL_SRC_MODULE_SW,
+					HAL_WBM_RELEASE_INFO0_REL_SRC_MODULE) |
+		    le32_encode_bits(action, HAL_WBM_RELEASE_INFO0_BM_ACTION) |
+		    le32_encode_bits(HAL_WBM_REL_DESC_TYPE_MSDU_LINK,
+				     HAL_WBM_RELEASE_INFO0_DESC_TYPE);
 }
 
 void ath12k_hal_reo_status_queue_stats(struct ath12k_base *ab, struct hal_tlv_64_hdr *tlv,
@@ -851,3 +931,20 @@ void ath12k_hal_reo_hw_setup(struct ath12k_base *ab, u32 ring_hash_map)
 	ath12k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_3,
 			   ring_hash_map);
 }
+
+void ath12k_hal_reo_shared_qaddr_cache_clear(struct ath12k_base *ab)
+{
+	u32 val;
+
+	lockdep_assert_held(&ab->base_lock);
+	val = ath12k_hif_read32(ab, HAL_SEQ_WCSS_UMAC_REO_REG +
+				HAL_REO1_QDESC_ADDR(ab));
+
+	val |= u32_encode_bits(1, HAL_REO_QDESC_ADDR_READ_CLEAR_QDESC_ARRAY);
+	ath12k_hif_write32(ab, HAL_SEQ_WCSS_UMAC_REO_REG +
+			   HAL_REO1_QDESC_ADDR(ab), val);
+
+	val &= ~HAL_REO_QDESC_ADDR_READ_CLEAR_QDESC_ARRAY;
+	ath12k_hif_write32(ab, HAL_SEQ_WCSS_UMAC_REO_REG +
+			   HAL_REO1_QDESC_ADDR(ab), val);
+}
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index 6bdcd0867d86..a3ab588aae19 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -108,11 +108,12 @@ enum hal_rx_mon_status {
 	HAL_RX_MON_STATUS_PPDU_DONE,
 	HAL_RX_MON_STATUS_BUF_DONE,
 	HAL_RX_MON_STATUS_BUF_ADDR,
+	HAL_RX_MON_STATUS_MPDU_START,
 	HAL_RX_MON_STATUS_MPDU_END,
 	HAL_RX_MON_STATUS_MSDU_END,
 };
 
-#define HAL_RX_MAX_MPDU		256
+#define HAL_RX_MAX_MPDU				1024
 #define HAL_RX_NUM_WORDS_PER_PPDU_BITMAP	(HAL_RX_MAX_MPDU >> 5)
 
 struct hal_rx_user_status {
@@ -506,6 +507,18 @@ struct hal_rx_mpdu_start {
 	__le32 rsvd2[16];
 } __packed;
 
+struct hal_rx_msdu_end {
+	__le32 info0;
+	__le32 rsvd0[9];
+	__le16 info00;
+	__le16 info01;
+	__le32 rsvd00[8];
+	__le32 info1;
+	__le32 rsvd1[10];
+	__le32 info2;
+	__le32 rsvd2;
+} __packed;
+
 #define HAL_RX_PPDU_END_DURATION	GENMASK(23, 0)
 struct hal_rx_ppdu_end_duration {
 	__le32 rsvd0[9];
@@ -525,6 +538,7 @@ struct hal_rx_msdu_desc_info {
 #define HAL_RX_NUM_MSDU_DESC 6
 struct hal_rx_msdu_list {
 	struct hal_rx_msdu_desc_info msdu_info[HAL_RX_NUM_MSDU_DESC];
+	u64 paddr[HAL_RX_NUM_MSDU_DESC];
 	u32 sw_cookie[HAL_RX_NUM_MSDU_DESC];
 	u8 rbm[HAL_RX_NUM_MSDU_DESC];
 };
@@ -1128,8 +1142,8 @@ void ath12k_hal_rx_msdu_link_info_get(struct hal_rx_msdu_link *link, u32 *num_ms
 				      u32 *msdu_cookies,
 				      enum hal_rx_buf_return_buf_manager *rbm);
 void ath12k_hal_rx_msdu_link_desc_set(struct ath12k_base *ab,
-				      struct hal_wbm_release_ring *dst_desc,
-				      struct hal_wbm_release_ring *src_desc,
+				      struct hal_wbm_release_ring *desc,
+				      struct ath12k_buffer_addr *buf_addr_info,
 				      enum hal_wbm_rel_bm_act action);
 void ath12k_hal_rx_buf_addr_info_set(struct ath12k_buffer_addr *binfo,
 				     dma_addr_t paddr, u32 cookie, u8 manager);
@@ -1144,5 +1158,12 @@ int ath12k_hal_wbm_desc_parse_err(struct ath12k_base *ab, void *desc,
 void ath12k_hal_rx_reo_ent_paddr_get(struct ath12k_base *ab,
 				     struct ath12k_buffer_addr *buff_addr,
 				     dma_addr_t *paddr, u32 *cookie);
+void ath12k_hal_rx_reo_ent_buf_paddr_get(void *rx_desc, dma_addr_t *paddr, u32 *sw_cookie,
+					 struct ath12k_buffer_addr **pp_buf_addr,
+					 u8 *rbm, u32 *msdu_cnt);
+void ath12k_hal_rx_msdu_list_get(struct ath12k *ar,
+				 struct hal_rx_msdu_link *link_desc,
+				 struct hal_rx_msdu_list *msdu_list,
+				 u16 *num_msdus);
 
 #endif
diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index a106ebed7870..7e2cf0fb2085 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/types.h>
@@ -118,6 +118,10 @@ static const struct ath12k_hw_ops wcn7850_ops = {
 #define ATH12K_TX_MON_RING_MASK_0 0x1
 #define ATH12K_TX_MON_RING_MASK_1 0x2
 
+#define ATH12K_RX_MON_STATUS_RING_MASK_0 0x1
+#define ATH12K_RX_MON_STATUS_RING_MASK_1 0x2
+#define ATH12K_RX_MON_STATUS_RING_MASK_2 0x4
+
 /* Target firmware's Copy Engine configuration. */
 static const struct ce_pipe_config ath12k_target_ce_config_wlan_qcn9274[] = {
 	/* CE0: host->target HTC control and raw streams */
@@ -535,6 +539,217 @@ static const struct service_to_pipe ath12k_target_service_to_ce_map_wlan_wcn7850
 	},
 };
 
+static const struct ce_pipe_config ath12k_target_ce_config_wlan_ipq5332[] = {
+	/* host->target HTC control and raw streams */
+	{
+		.pipenum = __cpu_to_le32(0),
+		.pipedir = __cpu_to_le32(PIPEDIR_OUT),
+		.nentries = __cpu_to_le32(32),
+		.nbytes_max = __cpu_to_le32(2048),
+		.flags = __cpu_to_le32(CE_ATTR_FLAGS),
+		.reserved = __cpu_to_le32(0),
+	},
+	/* target->host HTT */
+	{
+		.pipenum = __cpu_to_le32(1),
+		.pipedir = __cpu_to_le32(PIPEDIR_IN),
+		.nentries = __cpu_to_le32(32),
+		.nbytes_max = __cpu_to_le32(2048),
+		.flags = __cpu_to_le32(CE_ATTR_FLAGS),
+		.reserved = __cpu_to_le32(0),
+	},
+	/* target->host WMI  + HTC control */
+	{
+		.pipenum = __cpu_to_le32(2),
+		.pipedir = __cpu_to_le32(PIPEDIR_IN),
+		.nentries = __cpu_to_le32(32),
+		.nbytes_max = __cpu_to_le32(2048),
+		.flags = __cpu_to_le32(CE_ATTR_FLAGS),
+		.reserved = __cpu_to_le32(0),
+	},
+	/* host->target WMI */
+	{
+		.pipenum = __cpu_to_le32(3),
+		.pipedir = __cpu_to_le32(PIPEDIR_OUT),
+		.nentries = __cpu_to_le32(32),
+		.nbytes_max = __cpu_to_le32(2048),
+		.flags = __cpu_to_le32(CE_ATTR_FLAGS),
+		.reserved = __cpu_to_le32(0),
+	},
+	/* host->target HTT */
+	{
+		.pipenum = __cpu_to_le32(4),
+		.pipedir = __cpu_to_le32(PIPEDIR_OUT),
+		.nentries = __cpu_to_le32(256),
+		.nbytes_max = __cpu_to_le32(256),
+		.flags = __cpu_to_le32(CE_ATTR_FLAGS | CE_ATTR_DIS_INTR),
+		.reserved = __cpu_to_le32(0),
+	},
+	/* Target -> host PKTLOG */
+	{
+		.pipenum = __cpu_to_le32(5),
+		.pipedir = __cpu_to_le32(PIPEDIR_IN),
+		.nentries = __cpu_to_le32(32),
+		.nbytes_max = __cpu_to_le32(2048),
+		.flags = __cpu_to_le32(CE_ATTR_FLAGS),
+		.reserved = __cpu_to_le32(0),
+	},
+	/* Reserved for target autonomous HIF_memcpy */
+	{
+		.pipenum = __cpu_to_le32(6),
+		.pipedir = __cpu_to_le32(PIPEDIR_INOUT),
+		.nentries = __cpu_to_le32(32),
+		.nbytes_max = __cpu_to_le32(16384),
+		.flags = __cpu_to_le32(CE_ATTR_FLAGS),
+		.reserved = __cpu_to_le32(0),
+	},
+	/* CE7 Reserved for CV Prefetch */
+	{
+		.pipenum = __cpu_to_le32(7),
+		.pipedir = __cpu_to_le32(PIPEDIR_OUT),
+		.nentries = __cpu_to_le32(32),
+		.nbytes_max = __cpu_to_le32(2048),
+		.flags = __cpu_to_le32(CE_ATTR_FLAGS),
+		.reserved = __cpu_to_le32(0),
+	},
+	/* CE8 Reserved for target generic HIF memcpy */
+	{
+		.pipenum = __cpu_to_le32(8),
+		.pipedir = __cpu_to_le32(PIPEDIR_INOUT),
+		.nentries = __cpu_to_le32(32),
+		.nbytes_max = __cpu_to_le32(16384),
+		.flags = __cpu_to_le32(CE_ATTR_FLAGS),
+		.reserved = __cpu_to_le32(0),
+	},
+	/* CE9 WMI logging/CFR/Spectral/Radar/ */
+	{
+		.pipenum = __cpu_to_le32(9),
+		.pipedir = __cpu_to_le32(PIPEDIR_IN),
+		.nentries = __cpu_to_le32(32),
+		.nbytes_max = __cpu_to_le32(2048),
+		.flags = __cpu_to_le32(CE_ATTR_FLAGS),
+		.reserved = __cpu_to_le32(0),
+	},
+	/* Unused TBD */
+	{
+		.pipenum = __cpu_to_le32(10),
+		.pipedir = __cpu_to_le32(PIPEDIR_NONE),
+		.nentries = __cpu_to_le32(0),
+		.nbytes_max = __cpu_to_le32(0),
+		.flags = __cpu_to_le32(0),
+		.reserved = __cpu_to_le32(0),
+	},
+	/* Unused TBD */
+	{
+		.pipenum = __cpu_to_le32(11),
+		.pipedir = __cpu_to_le32(PIPEDIR_NONE),
+		.nentries = __cpu_to_le32(0),
+		.nbytes_max = __cpu_to_le32(0),
+		.flags = __cpu_to_le32(0),
+		.reserved = __cpu_to_le32(0),
+	},
+};
+
+static const struct service_to_pipe ath12k_target_service_to_ce_map_wlan_ipq5332[] = {
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_WMI_DATA_VO),
+		__cpu_to_le32(PIPEDIR_OUT),
+		__cpu_to_le32(3),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_WMI_DATA_VO),
+		__cpu_to_le32(PIPEDIR_IN),
+		__cpu_to_le32(2),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_WMI_DATA_BK),
+		__cpu_to_le32(PIPEDIR_OUT),
+		__cpu_to_le32(3),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_WMI_DATA_BK),
+		__cpu_to_le32(PIPEDIR_IN),
+		__cpu_to_le32(2),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_WMI_DATA_BE),
+		__cpu_to_le32(PIPEDIR_OUT),
+		__cpu_to_le32(3),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_WMI_DATA_BE),
+		__cpu_to_le32(PIPEDIR_IN),
+		__cpu_to_le32(2),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_WMI_DATA_VI),
+		__cpu_to_le32(PIPEDIR_OUT),
+		__cpu_to_le32(3),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_WMI_DATA_VI),
+		__cpu_to_le32(PIPEDIR_IN),
+		__cpu_to_le32(2),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_WMI_CONTROL),
+		__cpu_to_le32(PIPEDIR_OUT),
+		__cpu_to_le32(3),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_WMI_CONTROL),
+		__cpu_to_le32(PIPEDIR_IN),
+		__cpu_to_le32(2),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_RSVD_CTRL),
+		__cpu_to_le32(PIPEDIR_OUT),
+		__cpu_to_le32(0),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_RSVD_CTRL),
+		__cpu_to_le32(PIPEDIR_IN),
+		__cpu_to_le32(1),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_TEST_RAW_STREAMS),
+		__cpu_to_le32(PIPEDIR_OUT),
+		__cpu_to_le32(0),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_TEST_RAW_STREAMS),
+		__cpu_to_le32(PIPEDIR_IN),
+		__cpu_to_le32(1),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_HTT_DATA_MSG),
+		__cpu_to_le32(PIPEDIR_OUT),
+		__cpu_to_le32(4),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_HTT_DATA_MSG),
+		__cpu_to_le32(PIPEDIR_IN),
+		__cpu_to_le32(1),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_PKT_LOG),
+		__cpu_to_le32(PIPEDIR_IN),
+		__cpu_to_le32(5),
+	},
+	{
+		__cpu_to_le32(ATH12K_HTC_SVC_ID_WMI_CONTROL_DIAG),
+		__cpu_to_le32(PIPEDIR_IN),
+		__cpu_to_le32(9),
+	},
+	/* (Additions here) */
+
+	{ /* must be last */
+		__cpu_to_le32(0),
+		__cpu_to_le32(0),
+		__cpu_to_le32(0),
+	},
+};
+
 static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_qcn9274 = {
 	.tx  = {
 		ATH12K_TX_RING_MASK_0,
@@ -577,6 +792,46 @@ static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_qcn9274 = {
 	},
 };
 
+static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_ipq5332 = {
+	.tx  = {
+		ATH12K_TX_RING_MASK_0,
+		ATH12K_TX_RING_MASK_1,
+		ATH12K_TX_RING_MASK_2,
+		ATH12K_TX_RING_MASK_3,
+	},
+	.rx_mon_dest = {
+		0, 0, 0, 0, 0, 0, 0, 0,
+		ATH12K_RX_MON_RING_MASK_0,
+	},
+	.rx = {
+		0, 0, 0, 0,
+		ATH12K_RX_RING_MASK_0,
+		ATH12K_RX_RING_MASK_1,
+		ATH12K_RX_RING_MASK_2,
+		ATH12K_RX_RING_MASK_3,
+	},
+	.rx_err = {
+		0, 0, 0,
+		ATH12K_RX_ERR_RING_MASK_0,
+	},
+	.rx_wbm_rel = {
+		0, 0, 0,
+		ATH12K_RX_WBM_REL_RING_MASK_0,
+	},
+	.reo_status = {
+		0, 0, 0,
+		ATH12K_REO_STATUS_RING_MASK_0,
+	},
+	.host2rxdma = {
+		0, 0, 0,
+		ATH12K_HOST2RXDMA_RING_MASK_0,
+	},
+	.tx_mon_dest = {
+		ATH12K_TX_MON_RING_MASK_0,
+		ATH12K_TX_MON_RING_MASK_1,
+	},
+};
+
 static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_wcn7850 = {
 	.tx  = {
 		ATH12K_TX_RING_MASK_0,
@@ -585,6 +840,12 @@ static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_wcn7850 = {
 	},
 	.rx_mon_dest = {
 	},
+	.rx_mon_status = {
+		0, 0, 0, 0,
+		ATH12K_RX_MON_STATUS_RING_MASK_0,
+		ATH12K_RX_MON_STATUS_RING_MASK_1,
+		ATH12K_RX_MON_STATUS_RING_MASK_2,
+	},
 	.rx = {
 		0, 0, 0,
 		ATH12K_RX_RING_MASK_0,
@@ -619,6 +880,9 @@ static const struct ath12k_hw_regs qcn9274_v1_regs = {
 	.hal_tcl1_ring_msi1_base_msb = 0x0000094c,
 	.hal_tcl1_ring_msi1_data = 0x00000950,
 	.hal_tcl_ring_base_lsb = 0x00000b58,
+	.hal_tcl1_ring_base_lsb = 0x00000900,
+	.hal_tcl1_ring_base_msb = 0x00000904,
+	.hal_tcl2_ring_base_lsb = 0x00000978,
 
 	/* TCL STATUS ring address */
 	.hal_tcl_status_ring_base_lsb = 0x00000d38,
@@ -681,6 +945,12 @@ static const struct ath12k_hw_regs qcn9274_v1_regs = {
 
 	/* REO status ring address */
 	.hal_reo_status_ring_base = 0x00000a84,
+
+	/* CE base address */
+	.hal_umac_ce0_src_reg_base = 0x01b80000,
+	.hal_umac_ce0_dest_reg_base = 0x01b81000,
+	.hal_umac_ce1_src_reg_base = 0x01b82000,
+	.hal_umac_ce1_dest_reg_base = 0x01b83000,
 };
 
 static const struct ath12k_hw_regs qcn9274_v2_regs = {
@@ -695,6 +965,9 @@ static const struct ath12k_hw_regs qcn9274_v2_regs = {
 	.hal_tcl1_ring_msi1_base_msb = 0x0000094c,
 	.hal_tcl1_ring_msi1_data = 0x00000950,
 	.hal_tcl_ring_base_lsb = 0x00000b58,
+	.hal_tcl1_ring_base_lsb = 0x00000900,
+	.hal_tcl1_ring_base_msb = 0x00000904,
+	.hal_tcl2_ring_base_lsb = 0x00000978,
 
 	/* TCL STATUS ring address */
 	.hal_tcl_status_ring_base_lsb = 0x00000d38,
@@ -734,6 +1007,8 @@ static const struct ath12k_hw_regs qcn9274_v2_regs = {
 	.hal_reo1_sw_cookie_cfg1 = 0x00000070,
 	.hal_reo1_qdesc_lut_base0 = 0x00000074,
 	.hal_reo1_qdesc_lut_base1 = 0x00000078,
+	.hal_reo1_qdesc_addr = 0x0000007c,
+	.hal_reo1_qdesc_max_peerid = 0x00000088,
 	.hal_reo1_ring_base_lsb = 0x00000500,
 	.hal_reo1_ring_base_msb = 0x00000504,
 	.hal_reo1_ring_id = 0x00000508,
@@ -761,6 +1036,100 @@ static const struct ath12k_hw_regs qcn9274_v2_regs = {
 
 	/* REO status ring address */
 	.hal_reo_status_ring_base = 0x00000aa0,
+
+	/* CE base address */
+	.hal_umac_ce0_src_reg_base = 0x01b80000,
+	.hal_umac_ce0_dest_reg_base = 0x01b81000,
+	.hal_umac_ce1_src_reg_base = 0x01b82000,
+	.hal_umac_ce1_dest_reg_base = 0x01b83000,
+};
+
+static const struct ath12k_hw_regs ipq5332_regs = {
+	/* SW2TCL(x) R0 ring configuration address */
+	.hal_tcl1_ring_id = 0x00000918,
+	.hal_tcl1_ring_misc = 0x00000920,
+	.hal_tcl1_ring_tp_addr_lsb = 0x0000092c,
+	.hal_tcl1_ring_tp_addr_msb = 0x00000930,
+	.hal_tcl1_ring_consumer_int_setup_ix0 = 0x00000940,
+	.hal_tcl1_ring_consumer_int_setup_ix1 = 0x00000944,
+	.hal_tcl1_ring_msi1_base_lsb = 0x00000958,
+	.hal_tcl1_ring_msi1_base_msb = 0x0000095c,
+	.hal_tcl1_ring_base_lsb = 0x00000910,
+	.hal_tcl1_ring_base_msb = 0x00000914,
+	.hal_tcl1_ring_msi1_data = 0x00000960,
+	.hal_tcl2_ring_base_lsb = 0x00000988,
+	.hal_tcl_ring_base_lsb = 0x00000b68,
+
+	/* TCL STATUS ring address */
+	.hal_tcl_status_ring_base_lsb = 0x00000d48,
+
+	/* REO DEST ring address */
+	.hal_reo2_ring_base = 0x00000578,
+	.hal_reo1_misc_ctrl_addr = 0x00000b9c,
+	.hal_reo1_sw_cookie_cfg0 = 0x0000006c,
+	.hal_reo1_sw_cookie_cfg1 = 0x00000070,
+	.hal_reo1_qdesc_lut_base0 = 0x00000074,
+	.hal_reo1_qdesc_lut_base1 = 0x00000078,
+	.hal_reo1_ring_base_lsb = 0x00000500,
+	.hal_reo1_ring_base_msb = 0x00000504,
+	.hal_reo1_ring_id = 0x00000508,
+	.hal_reo1_ring_misc = 0x00000510,
+	.hal_reo1_ring_hp_addr_lsb = 0x00000514,
+	.hal_reo1_ring_hp_addr_msb = 0x00000518,
+	.hal_reo1_ring_producer_int_setup = 0x00000524,
+	.hal_reo1_ring_msi1_base_lsb = 0x00000548,
+	.hal_reo1_ring_msi1_base_msb = 0x0000054C,
+	.hal_reo1_ring_msi1_data = 0x00000550,
+	.hal_reo1_aging_thres_ix0 = 0x00000B28,
+	.hal_reo1_aging_thres_ix1 = 0x00000B2C,
+	.hal_reo1_aging_thres_ix2 = 0x00000B30,
+	.hal_reo1_aging_thres_ix3 = 0x00000B34,
+
+	/* REO Exception ring address */
+	.hal_reo2_sw0_ring_base = 0x000008c0,
+
+	/* REO Reinject ring address */
+	.hal_sw2reo_ring_base = 0x00000320,
+	.hal_sw2reo1_ring_base = 0x00000398,
+
+	/* REO cmd ring address */
+	.hal_reo_cmd_ring_base = 0x000002A8,
+
+	/* REO status ring address */
+	.hal_reo_status_ring_base = 0x00000aa0,
+
+	/* WBM idle link ring address */
+	.hal_wbm_idle_ring_base_lsb = 0x00000d3c,
+	.hal_wbm_idle_ring_misc_addr = 0x00000d4c,
+	.hal_wbm_r0_idle_list_cntl_addr = 0x00000240,
+	.hal_wbm_r0_idle_list_size_addr = 0x00000244,
+	.hal_wbm_scattered_ring_base_lsb = 0x00000250,
+	.hal_wbm_scattered_ring_base_msb = 0x00000254,
+	.hal_wbm_scattered_desc_head_info_ix0 = 0x00000260,
+	.hal_wbm_scattered_desc_head_info_ix1   = 0x00000264,
+	.hal_wbm_scattered_desc_tail_info_ix0 = 0x00000270,
+	.hal_wbm_scattered_desc_tail_info_ix1 = 0x00000274,
+	.hal_wbm_scattered_desc_ptr_hp_addr = 0x0000027c,
+
+	/* SW2WBM release ring address */
+	.hal_wbm_sw_release_ring_base_lsb = 0x0000037c,
+
+	/* WBM2SW release ring address */
+	.hal_wbm0_release_ring_base_lsb = 0x00000e08,
+	.hal_wbm1_release_ring_base_lsb = 0x00000e80,
+
+	/* PPE release ring address */
+	.hal_ppe_rel_ring_base = 0x0000046c,
+
+	/* CE address */
+	.hal_umac_ce0_src_reg_base = 0x00740000 -
+		HAL_IPQ5332_CE_WFSS_REG_BASE,
+	.hal_umac_ce0_dest_reg_base = 0x00741000 -
+		HAL_IPQ5332_CE_WFSS_REG_BASE,
+	.hal_umac_ce1_src_reg_base = 0x00742000 -
+		HAL_IPQ5332_CE_WFSS_REG_BASE,
+	.hal_umac_ce1_dest_reg_base = 0x00743000 -
+		HAL_IPQ5332_CE_WFSS_REG_BASE,
 };
 
 static const struct ath12k_hw_regs wcn7850_regs = {
@@ -775,6 +1144,9 @@ static const struct ath12k_hw_regs wcn7850_regs = {
 	.hal_tcl1_ring_msi1_base_msb = 0x0000094c,
 	.hal_tcl1_ring_msi1_data = 0x00000950,
 	.hal_tcl_ring_base_lsb = 0x00000b58,
+	.hal_tcl1_ring_base_lsb = 0x00000900,
+	.hal_tcl1_ring_base_msb = 0x00000904,
+	.hal_tcl2_ring_base_lsb = 0x00000978,
 
 	/* TCL STATUS ring address */
 	.hal_tcl_status_ring_base_lsb = 0x00000d38,
@@ -837,6 +1209,12 @@ static const struct ath12k_hw_regs wcn7850_regs = {
 
 	/* REO status ring address */
 	.hal_reo_status_ring_base = 0x00000a84,
+
+	/* CE base address */
+	.hal_umac_ce0_src_reg_base = 0x01b80000,
+	.hal_umac_ce0_dest_reg_base = 0x01b81000,
+	.hal_umac_ce1_src_reg_base = 0x01b82000,
+	.hal_umac_ce1_dest_reg_base = 0x01b83000,
 };
 
 static const struct ath12k_hw_hal_params ath12k_hw_hal_params_qcn9274 = {
@@ -856,6 +1234,26 @@ static const struct ath12k_hw_hal_params ath12k_hw_hal_params_wcn7850 = {
 			    HAL_WBM_SW_COOKIE_CONV_CFG_WBM2SW4_EN,
 };
 
+static const struct ath12k_hw_hal_params ath12k_hw_hal_params_ipq5332 = {
+	.rx_buf_rbm = HAL_RX_BUF_RBM_SW3_BM,
+	.wbm2sw_cc_enable = HAL_WBM_SW_COOKIE_CONV_CFG_WBM2SW0_EN |
+			    HAL_WBM_SW_COOKIE_CONV_CFG_WBM2SW1_EN |
+			    HAL_WBM_SW_COOKIE_CONV_CFG_WBM2SW2_EN |
+			    HAL_WBM_SW_COOKIE_CONV_CFG_WBM2SW3_EN |
+			    HAL_WBM_SW_COOKIE_CONV_CFG_WBM2SW4_EN,
+};
+
+static const struct ce_ie_addr ath12k_ce_ie_addr_ipq5332 = {
+	.ie1_reg_addr = CE_HOST_IE_ADDRESS - HAL_IPQ5332_CE_WFSS_REG_BASE,
+	.ie2_reg_addr = CE_HOST_IE_2_ADDRESS - HAL_IPQ5332_CE_WFSS_REG_BASE,
+	.ie3_reg_addr = CE_HOST_IE_3_ADDRESS - HAL_IPQ5332_CE_WFSS_REG_BASE,
+};
+
+static const struct ce_remap ath12k_ce_remap_ipq5332 = {
+	.base = HAL_IPQ5332_CE_WFSS_REG_BASE,
+	.size = HAL_IPQ5332_CE_SIZE,
+};
+
 static const struct ath12k_hw_params ath12k_hw_params[] = {
 	{
 		.name = "qcn9274 hw1.0",
@@ -864,6 +1262,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 			.dir = "QCN9274/hw1.0",
 			.board_size = 256 * 1024,
 			.cal_offset = 128 * 1024,
+			.m3_loader = ath12k_m3_fw_loader_driver,
 		},
 		.max_radios = 1,
 		.single_pdev_only = false,
@@ -899,7 +1298,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.download_calib = true,
 		.supports_suspend = false,
 		.tcl_ring_retry = true,
-		.reoq_lut_support = false,
+		.reoq_lut_support = true,
 		.supports_shadow_regs = false,
 
 		.num_tcl_banks = 48,
@@ -932,6 +1331,14 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.iova_mask = 0,
 
 		.supports_aspm = false,
+
+		.ce_ie_addr = NULL,
+		.ce_remap = NULL,
+		.bdf_addr_offset = 0,
+
+		.current_cc_support = false,
+
+		.dp_primary_link_only = true,
 	},
 	{
 		.name = "wcn7850 hw2.0",
@@ -941,6 +1348,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 			.dir = "WCN7850/hw2.0",
 			.board_size = 256 * 1024,
 			.cal_offset = 256 * 1024,
+			.m3_loader = ath12k_m3_fw_loader_driver,
 		},
 
 		.max_radios = 1,
@@ -972,7 +1380,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 				   BIT(NL80211_IFTYPE_P2P_DEVICE) |
 				   BIT(NL80211_IFTYPE_P2P_CLIENT) |
 				   BIT(NL80211_IFTYPE_P2P_GO),
-		.supports_monitor = false,
+		.supports_monitor = true,
 
 		.idle_ps = true,
 		.download_calib = false,
@@ -1012,6 +1420,14 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.iova_mask = ATH12K_PCIE_MAX_PAYLOAD_SIZE - 1,
 
 		.supports_aspm = true,
+
+		.ce_ie_addr = NULL,
+		.ce_remap = NULL,
+		.bdf_addr_offset = 0,
+
+		.current_cc_support = true,
+
+		.dp_primary_link_only = false,
 	},
 	{
 		.name = "qcn9274 hw2.0",
@@ -1020,6 +1436,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 			.dir = "QCN9274/hw2.0",
 			.board_size = 256 * 1024,
 			.cal_offset = 128 * 1024,
+			.m3_loader = ath12k_m3_fw_loader_driver,
 		},
 		.max_radios = 2,
 		.single_pdev_only = false,
@@ -1049,7 +1466,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 					BIT(NL80211_IFTYPE_AP) |
 					BIT(NL80211_IFTYPE_MESH_POINT) |
 					BIT(NL80211_IFTYPE_AP_VLAN),
-		.supports_monitor = false,
+		.supports_monitor = true,
 
 		.idle_ps = false,
 		.download_calib = true,
@@ -1088,6 +1505,92 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.iova_mask = 0,
 
 		.supports_aspm = false,
+
+		.ce_ie_addr = NULL,
+		.ce_remap = NULL,
+		.bdf_addr_offset = 0,
+
+		.current_cc_support = false,
+
+		.dp_primary_link_only = true,
+	},
+	{
+		.name = "ipq5332 hw1.0",
+		.hw_rev = ATH12K_HW_IPQ5332_HW10,
+		.fw = {
+			.dir = "IPQ5332/hw1.0",
+			.board_size = 256 * 1024,
+			.cal_offset = 128 * 1024,
+			.m3_loader = ath12k_m3_fw_loader_remoteproc,
+		},
+		.max_radios = 1,
+		.single_pdev_only = false,
+		.qmi_service_ins_id = ATH12K_QMI_WLFW_SERVICE_INS_ID_V01_IPQ5332,
+		.internal_sleep_clock = false,
+
+		.hw_ops = &qcn9274_ops,
+		.regs = &ipq5332_regs,
+		.ring_mask = &ath12k_hw_ring_mask_ipq5332,
+
+		.host_ce_config = ath12k_host_ce_config_ipq5332,
+		.ce_count = 12,
+		.target_ce_config = ath12k_target_ce_config_wlan_ipq5332,
+		.target_ce_count = 12,
+		.svc_to_ce_map = ath12k_target_service_to_ce_map_wlan_ipq5332,
+		.svc_to_ce_map_len = 18,
+
+		.hal_params = &ath12k_hw_hal_params_ipq5332,
+
+		.rxdma1_enable = false,
+		.num_rxdma_per_pdev = 1,
+		.num_rxdma_dst_ring = 0,
+		.rx_mac_buf_ring = false,
+		.vdev_start_delay = false,
+
+		.interface_modes = BIT(NL80211_IFTYPE_STATION) |
+				   BIT(NL80211_IFTYPE_AP) |
+				   BIT(NL80211_IFTYPE_MESH_POINT),
+		.supports_monitor = false,
+
+		.idle_ps = false,
+		.download_calib = true,
+		.supports_suspend = false,
+		.tcl_ring_retry = true,
+		.reoq_lut_support = false,
+		.supports_shadow_regs = false,
+
+		.num_tcl_banks = 48,
+		.max_tx_ring = 4,
+
+		.wmi_init = &ath12k_wmi_init_qcn9274,
+
+		.hal_ops = &hal_qcn9274_ops,
+
+		.qmi_cnss_feature_bitmap = BIT(CNSS_QDSS_CFG_MISS_V01),
+
+		.rfkill_pin = 0,
+		.rfkill_cfg = 0,
+		.rfkill_on_level = 0,
+
+		.rddm_size = 0,
+
+		.def_num_link = 0,
+		.max_mlo_peer = 256,
+
+		.otp_board_id_register = 0,
+
+		.supports_sta_ps = false,
+
+		.acpi_guid = NULL,
+		.supports_dynamic_smps_6ghz = false,
+		.iova_mask = 0,
+		.supports_aspm = false,
+
+		.ce_ie_addr = &ath12k_ce_ie_addr_ipq5332,
+		.ce_remap = &ath12k_ce_remap_ipq5332,
+		.bdf_addr_offset = 0xC00000,
+
+		.dp_primary_link_only = true,
 	},
 };
 
diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
index 8d52182e28ae..0fbc17649df4 100644
--- a/drivers/net/wireless/ath/ath12k/hw.h
+++ b/drivers/net/wireless/ath/ath12k/hw.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_HW_H
@@ -97,6 +97,7 @@
 #define ATH12K_REGDB_FILE_NAME		"regdb.bin"
 
 #define ATH12K_PCIE_MAX_PAYLOAD_SIZE	128
+#define ATH12K_IPQ5332_USERPD_ID	1
 
 enum ath12k_hw_rate_cck {
 	ATH12K_HW_RATE_CCK_LP_11M = 0,
@@ -121,6 +122,7 @@ enum ath12k_hw_rate_ofdm {
 
 enum ath12k_bus {
 	ATH12K_BUS_PCI,
+	ATH12K_BUS_AHB,
 };
 
 #define ATH12K_EXT_IRQ_GRP_NUM_MAX 11
@@ -133,6 +135,7 @@ enum hal_encrypt_type;
 struct ath12k_hw_ring_mask {
 	u8 tx[ATH12K_EXT_IRQ_GRP_NUM_MAX];
 	u8 rx_mon_dest[ATH12K_EXT_IRQ_GRP_NUM_MAX];
+	u8 rx_mon_status[ATH12K_EXT_IRQ_GRP_NUM_MAX];
 	u8 rx[ATH12K_EXT_IRQ_GRP_NUM_MAX];
 	u8 rx_err[ATH12K_EXT_IRQ_GRP_NUM_MAX];
 	u8 rx_wbm_rel[ATH12K_EXT_IRQ_GRP_NUM_MAX];
@@ -146,6 +149,11 @@ struct ath12k_hw_hal_params {
 	u32	  wbm2sw_cc_enable;
 };
 
+enum ath12k_m3_fw_loaders {
+	ath12k_m3_fw_loader_driver,
+	ath12k_m3_fw_loader_remoteproc,
+};
+
 struct ath12k_hw_params {
 	const char *name;
 	u16 hw_rev;
@@ -154,6 +162,7 @@ struct ath12k_hw_params {
 		const char *dir;
 		size_t board_size;
 		size_t cal_offset;
+		enum ath12k_m3_fw_loaders m3_loader;
 	} fw;
 
 	u8 max_radios;
@@ -190,6 +199,7 @@ struct ath12k_hw_params {
 	bool reoq_lut_support:1;
 	bool supports_shadow_regs:1;
 	bool supports_aspm:1;
+	bool current_cc_support:1;
 
 	u32 num_tcl_banks;
 	u32 max_tx_ring;
@@ -220,6 +230,13 @@ struct ath12k_hw_params {
 	bool supports_dynamic_smps_6ghz;
 
 	u32 iova_mask;
+
+	const struct ce_ie_addr *ce_ie_addr;
+	const struct ce_remap *ce_remap;
+	u32 bdf_addr_offset;
+
+	/* setup REO queue, frag etc only for primary link peer */
+	bool dp_primary_link_only:1;
 };
 
 struct ath12k_hw_ops {
@@ -293,9 +310,15 @@ struct ath12k_hw_regs {
 	u32 hal_tcl1_ring_msi1_base_msb;
 	u32 hal_tcl1_ring_msi1_data;
 	u32 hal_tcl_ring_base_lsb;
+	u32 hal_tcl1_ring_base_lsb;
+	u32 hal_tcl1_ring_base_msb;
+	u32 hal_tcl2_ring_base_lsb;
 
 	u32 hal_tcl_status_ring_base_lsb;
 
+	u32 hal_reo1_qdesc_addr;
+	u32 hal_reo1_qdesc_max_peerid;
+
 	u32 hal_wbm_idle_ring_base_lsb;
 	u32 hal_wbm_idle_ring_misc_addr;
 	u32 hal_wbm_r0_idle_list_cntl_addr;
@@ -316,6 +339,11 @@ struct ath12k_hw_regs {
 	u32 pcie_qserdes_sysclk_en_sel;
 	u32 pcie_pcs_osc_dtct_config_base;
 
+	u32 hal_umac_ce0_src_reg_base;
+	u32 hal_umac_ce0_dest_reg_base;
+	u32 hal_umac_ce1_src_reg_base;
+	u32 hal_umac_ce1_dest_reg_base;
+
 	u32 hal_ppe_rel_ring_base;
 
 	u32 hal_reo2_ring_base;
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index dfa05f0ee6c9..88b59f3ff87a 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -229,7 +229,8 @@ ath12k_phymodes[NUM_NL80211_BANDS][ATH12K_CHAN_WIDTH_NUM] = {
 const struct htt_rx_ring_tlv_filter ath12k_mac_mon_status_filter_default = {
 	.rx_filter = HTT_RX_FILTER_TLV_FLAGS_MPDU_START |
 		     HTT_RX_FILTER_TLV_FLAGS_PPDU_END |
-		     HTT_RX_FILTER_TLV_FLAGS_PPDU_END_STATUS_DONE,
+		     HTT_RX_FILTER_TLV_FLAGS_PPDU_END_STATUS_DONE |
+		     HTT_RX_FILTER_TLV_FLAGS_PPDU_START_USER_INFO,
 	.pkt_filter_flags0 = HTT_RX_FP_MGMT_FILTER_FLAGS0,
 	.pkt_filter_flags1 = HTT_RX_FP_MGMT_FILTER_FLAGS1,
 	.pkt_filter_flags2 = HTT_RX_FP_CTRL_FILTER_FLASG2,
@@ -580,14 +581,22 @@ static int ath12k_mac_vif_link_chan(struct ieee80211_vif *vif, u8 link_id,
 	return 0;
 }
 
-static struct ath12k_link_vif *ath12k_mac_get_tx_arvif(struct ath12k_link_vif *arvif)
+static struct ath12k_link_vif *
+ath12k_mac_get_tx_arvif(struct ath12k_link_vif *arvif,
+			struct ieee80211_bss_conf *link_conf)
 {
+	struct ieee80211_bss_conf *tx_bss_conf;
+	struct ath12k *ar = arvif->ar;
 	struct ath12k_vif *tx_ahvif;
 
-	if (arvif->ahvif->vif->mbssid_tx_vif) {
-		tx_ahvif = ath12k_vif_to_ahvif(arvif->ahvif->vif->mbssid_tx_vif);
-		if (tx_ahvif)
-			return &tx_ahvif->deflink;
+	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
+
+	tx_bss_conf = wiphy_dereference(ath12k_ar_to_hw(ar)->wiphy,
+					link_conf->tx_bss_conf);
+	if (tx_bss_conf) {
+		tx_ahvif = ath12k_vif_to_ahvif(tx_bss_conf->vif);
+		return wiphy_dereference(tx_ahvif->ah->hw->wiphy,
+					 tx_ahvif->link[tx_bss_conf->link_id]);
 	}
 
 	return NULL;
@@ -874,12 +883,12 @@ static bool ath12k_mac_band_match(enum nl80211_band band1, enum WMI_HOST_WLAN_BA
 {
 	switch (band1) {
 	case NL80211_BAND_2GHZ:
-		if (band2 & WMI_HOST_WLAN_2G_CAP)
+		if (band2 & WMI_HOST_WLAN_2GHZ_CAP)
 			return true;
 		break;
 	case NL80211_BAND_5GHZ:
 	case NL80211_BAND_6GHZ:
-		if (band2 & WMI_HOST_WLAN_5G_CAP)
+		if (band2 & WMI_HOST_WLAN_5GHZ_CAP)
 			return true;
 		break;
 	default:
@@ -980,7 +989,7 @@ static int ath12k_mac_txpower_recalc(struct ath12k *ar)
 	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "txpower to set in hw %d\n",
 		   txpower / 2);
 
-	if ((pdev->cap.supported_bands & WMI_HOST_WLAN_2G_CAP) &&
+	if ((pdev->cap.supported_bands & WMI_HOST_WLAN_2GHZ_CAP) &&
 	    ar->txpower_limit_2g != txpower) {
 		param = WMI_PDEV_PARAM_TXPOWER_LIMIT2G;
 		ret = ath12k_wmi_pdev_set_param(ar, param,
@@ -990,7 +999,7 @@ static int ath12k_mac_txpower_recalc(struct ath12k *ar)
 		ar->txpower_limit_2g = txpower;
 	}
 
-	if ((pdev->cap.supported_bands & WMI_HOST_WLAN_5G_CAP) &&
+	if ((pdev->cap.supported_bands & WMI_HOST_WLAN_5GHZ_CAP) &&
 	    ar->txpower_limit_5g != txpower) {
 		param = WMI_PDEV_PARAM_TXPOWER_LIMIT5G;
 		ret = ath12k_wmi_pdev_set_param(ar, param,
@@ -1245,61 +1254,6 @@ static int ath12k_mac_monitor_vdev_stop(struct ath12k *ar)
 	return ret;
 }
 
-static int ath12k_mac_monitor_vdev_create(struct ath12k *ar)
-{
-	struct ath12k_pdev *pdev = ar->pdev;
-	struct ath12k_wmi_vdev_create_arg arg = {};
-	int bit, ret;
-	u8 tmp_addr[6];
-
-	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
-
-	if (ar->monitor_vdev_created)
-		return 0;
-
-	if (ar->ab->free_vdev_map == 0) {
-		ath12k_warn(ar->ab, "failed to find free vdev id for monitor vdev\n");
-		return -ENOMEM;
-	}
-
-	bit = __ffs64(ar->ab->free_vdev_map);
-
-	ar->monitor_vdev_id = bit;
-
-	arg.if_id = ar->monitor_vdev_id;
-	arg.type = WMI_VDEV_TYPE_MONITOR;
-	arg.subtype = WMI_VDEV_SUBTYPE_NONE;
-	arg.pdev_id = pdev->pdev_id;
-	arg.if_stats_id = ATH12K_INVAL_VDEV_STATS_ID;
-
-	if (pdev->cap.supported_bands & WMI_HOST_WLAN_2G_CAP) {
-		arg.chains[NL80211_BAND_2GHZ].tx = ar->num_tx_chains;
-		arg.chains[NL80211_BAND_2GHZ].rx = ar->num_rx_chains;
-	}
-
-	if (pdev->cap.supported_bands & WMI_HOST_WLAN_5G_CAP) {
-		arg.chains[NL80211_BAND_5GHZ].tx = ar->num_tx_chains;
-		arg.chains[NL80211_BAND_5GHZ].rx = ar->num_rx_chains;
-	}
-
-	ret = ath12k_wmi_vdev_create(ar, tmp_addr, &arg);
-	if (ret) {
-		ath12k_warn(ar->ab, "failed to request monitor vdev %i creation: %d\n",
-			    ar->monitor_vdev_id, ret);
-		ar->monitor_vdev_id = -1;
-		return ret;
-	}
-
-	ar->allocated_vdev_map |= 1LL << ar->monitor_vdev_id;
-	ar->ab->free_vdev_map &= ~(1LL << ar->monitor_vdev_id);
-	ar->num_created_vdevs++;
-	ar->monitor_vdev_created = true;
-	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac monitor vdev %d created\n",
-		   ar->monitor_vdev_id);
-
-	return 0;
-}
-
 static int ath12k_mac_monitor_vdev_delete(struct ath12k *ar)
 {
 	int ret;
@@ -1336,19 +1290,9 @@ static int ath12k_mac_monitor_vdev_delete(struct ath12k *ar)
 	return ret;
 }
 
-static void
-ath12k_mac_get_any_chandef_iter(struct ieee80211_hw *hw,
-				struct ieee80211_chanctx_conf *conf,
-				void *data)
-{
-	struct cfg80211_chan_def **def = data;
-
-	*def = &conf->def;
-}
-
 static int ath12k_mac_monitor_start(struct ath12k *ar)
 {
-	struct cfg80211_chan_def *chandef = NULL;
+	struct ath12k_mac_get_any_chanctx_conf_arg arg;
 	int ret;
 
 	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
@@ -1356,25 +1300,33 @@ static int ath12k_mac_monitor_start(struct ath12k *ar)
 	if (ar->monitor_started)
 		return 0;
 
+	arg.ar = ar;
+	arg.chanctx_conf = NULL;
 	ieee80211_iter_chan_contexts_atomic(ath12k_ar_to_hw(ar),
-					    ath12k_mac_get_any_chandef_iter,
-					    &chandef);
-	if (!chandef)
+					    ath12k_mac_get_any_chanctx_conf_iter,
+					    &arg);
+	if (!arg.chanctx_conf)
 		return 0;
 
-	ret = ath12k_mac_monitor_vdev_start(ar, ar->monitor_vdev_id, chandef);
+	ret = ath12k_mac_monitor_vdev_start(ar, ar->monitor_vdev_id,
+					    &arg.chanctx_conf->def);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to start monitor vdev: %d\n", ret);
-		ath12k_mac_monitor_vdev_delete(ar);
+		return ret;
+	}
+
+	ret = ath12k_dp_tx_htt_monitor_mode_ring_config(ar, false);
+	if (ret) {
+		ath12k_warn(ar->ab, "fail to set monitor filter: %d\n", ret);
 		return ret;
 	}
 
 	ar->monitor_started = true;
 	ar->num_started_vdevs++;
-	ret = ath12k_dp_tx_htt_monitor_mode_ring_config(ar, false);
-	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac monitor started ret %d\n", ret);
 
-	return ret;
+	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac monitor started\n");
+
+	return 0;
 }
 
 static int ath12k_mac_monitor_stop(struct ath12k *ar)
@@ -1440,58 +1392,9 @@ err:
 	return ret;
 }
 
-static int ath12k_mac_config(struct ath12k *ar, u32 changed)
-{
-	struct ieee80211_hw *hw = ath12k_ar_to_hw(ar);
-	struct ieee80211_conf *conf = &hw->conf;
-	int ret = 0;
-
-	lockdep_assert_wiphy(hw->wiphy);
-
-	if (changed & IEEE80211_CONF_CHANGE_MONITOR) {
-		ar->monitor_conf_enabled = conf->flags & IEEE80211_CONF_MONITOR;
-		if (ar->monitor_conf_enabled) {
-			if (ar->monitor_vdev_created)
-				return ret;
-			ret = ath12k_mac_monitor_vdev_create(ar);
-			if (ret)
-				return ret;
-			ret = ath12k_mac_monitor_start(ar);
-			if (ret)
-				goto err_mon_del;
-		} else {
-			if (!ar->monitor_vdev_created)
-				return ret;
-			ret = ath12k_mac_monitor_stop(ar);
-			if (ret)
-				return ret;
-			ath12k_mac_monitor_vdev_delete(ar);
-		}
-	}
-
-	return ret;
-
-err_mon_del:
-	ath12k_mac_monitor_vdev_delete(ar);
-	return ret;
-}
-
 static int ath12k_mac_op_config(struct ieee80211_hw *hw, u32 changed)
 {
-	struct ath12k_hw *ah = ath12k_hw_to_ah(hw);
-	struct ath12k *ar;
-	int ret;
-
-	lockdep_assert_wiphy(hw->wiphy);
-
-	ar = ath12k_ah_to_ar(ah, 0);
-
-	ret = ath12k_mac_config(ar, changed);
-	if (ret)
-		ath12k_warn(ar->ab, "failed to update config pdev idx %d: %d\n",
-			    ar->pdev_idx, ret);
-
-	return ret;
+	return 0;
 }
 
 static int ath12k_mac_setup_bcn_p2p_ie(struct ath12k_link_vif *arvif,
@@ -1715,7 +1618,7 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_link_vif *arvif)
 		return -ENOLINK;
 	}
 
-	tx_arvif = ath12k_mac_get_tx_arvif(arvif);
+	tx_arvif = ath12k_mac_get_tx_arvif(arvif, link_conf);
 	if (tx_arvif) {
 		if (tx_arvif != arvif && arvif->is_up)
 			return 0;
@@ -1785,6 +1688,7 @@ static void ath12k_control_beaconing(struct ath12k_link_vif *arvif,
 {
 	struct ath12k_wmi_vdev_up_params params = {};
 	struct ath12k_vif *ahvif = arvif->ahvif;
+	struct ieee80211_bss_conf *link_conf;
 	struct ath12k_link_vif *tx_arvif;
 	struct ath12k *ar = arvif->ar;
 	int ret;
@@ -1817,7 +1721,15 @@ static void ath12k_control_beaconing(struct ath12k_link_vif *arvif,
 	params.aid = ahvif->aid;
 	params.bssid = arvif->bssid;
 
-	tx_arvif = ath12k_mac_get_tx_arvif(arvif);
+	link_conf = ath12k_mac_get_link_bss_conf(arvif);
+	if (!link_conf) {
+		ath12k_warn(ar->ab,
+			    "unable to access bss link conf for link %u required to retrieve transmitting link conf\n",
+			    arvif->link_id);
+		return;
+	}
+
+	tx_arvif = ath12k_mac_get_tx_arvif(arvif, link_conf);
 	if (tx_arvif) {
 		params.tx_bssid = tx_arvif->bssid;
 		params.nontx_profile_idx = info->bssid_index;
@@ -3027,6 +2939,7 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar,
 	const struct ieee80211_sta_eht_cap *eht_cap;
 	const struct ieee80211_sta_he_cap *he_cap;
 	struct ieee80211_link_sta *link_sta;
+	struct ieee80211_bss_conf *link_conf;
 	u32 *rx_mcs, *tx_mcs;
 
 	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
@@ -3038,6 +2951,12 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar,
 		return;
 	}
 
+	link_conf = ath12k_mac_get_link_bss_conf(arvif);
+	if (!link_conf) {
+		ath12k_warn(ar->ab, "unable to access link_conf in peer assoc eht set\n");
+		return;
+	}
+
 	eht_cap = &link_sta->eht_cap;
 	he_cap = &link_sta->he_cap;
 	if (!he_cap->has_he || !eht_cap->has_eht)
@@ -3109,6 +3028,7 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar,
 	}
 
 	arg->punct_bitmap = ~arvif->punct_bitmap;
+	arg->eht_disable_mcs15 = link_conf->eht_disable_mcs15;
 }
 
 static void ath12k_peer_assoc_h_mlo(struct ath12k_link_sta *arsta,
@@ -3139,6 +3059,7 @@ static void ath12k_peer_assoc_h_mlo(struct ath12k_link_sta *arsta,
 	ml->ml_peer_id = ahsta->ml_peer_id;
 	ml->ieee_link_id = arsta->link_id;
 	ml->num_partner_links = 0;
+	ml->eml_cap = sta->eml_cap;
 	links = ahsta->links_map;
 
 	rcu_read_lock();
@@ -3377,6 +3298,11 @@ static void ath12k_bss_assoc(struct ath12k *ar,
 	if (ret)
 		ath12k_warn(ar->ab, "failed to set vdev %i OBSS PD parameters: %d\n",
 			    arvif->vdev_id, ret);
+
+	if (test_bit(WMI_TLV_SERVICE_11D_OFFLOAD, ar->ab->wmi_ab.svc_map) &&
+	    ahvif->vdev_type == WMI_VDEV_TYPE_STA &&
+	    ahvif->vdev_subtype == WMI_VDEV_SUBTYPE_NONE)
+		ath12k_mac_11d_scan_stop_all(ar->ab);
 }
 
 static void ath12k_bss_disassoc(struct ath12k *ar,
@@ -3450,7 +3376,10 @@ static void ath12k_recalculate_mgmt_rate(struct ath12k *ar,
 	}
 
 	sband = hw->wiphy->bands[def->chan->band];
-	basic_rate_idx = ffs(bss_conf->basic_rates) - 1;
+	if (bss_conf->basic_rates)
+		basic_rate_idx = __ffs(bss_conf->basic_rates);
+	else
+		basic_rate_idx = 0;
 	bitrate = sband->bitrates[basic_rate_idx].bitrate;
 
 	hw_rate_code = ath12k_mac_get_rate_hw_value(bitrate);
@@ -3495,6 +3424,9 @@ static void ath12k_mac_init_arvif(struct ath12k_vif *ahvif,
 	arvif->ahvif = ahvif;
 	arvif->link_id = _link_id;
 
+	/* Protects the datapath stats update on a per link basis */
+	spin_lock_init(&arvif->link_stats_lock);
+
 	INIT_LIST_HEAD(&arvif->list);
 	INIT_DELAYED_WORK(&arvif->connection_loss_work,
 			  ath12k_mac_vif_sta_connection_loss_work);
@@ -3534,6 +3466,11 @@ static void ath12k_mac_remove_link_interface(struct ieee80211_hw *hw,
 	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac remove link interface (vdev %d link id %d)",
 		   arvif->vdev_id, arvif->link_id);
 
+	if (test_bit(WMI_TLV_SERVICE_11D_OFFLOAD, ar->ab->wmi_ab.svc_map) &&
+	    ahvif->vdev_type == WMI_VDEV_TYPE_STA &&
+	    ahvif->vdev_subtype == WMI_VDEV_SUBTYPE_NONE)
+		ath12k_mac_11d_scan_stop(ar);
+
 	if (ahvif->vdev_type == WMI_VDEV_TYPE_AP) {
 		ret = ath12k_peer_delete(ar, arvif->vdev_id, arvif->bssid);
 		if (ret)
@@ -3556,23 +3493,18 @@ static struct ath12k_link_vif *ath12k_mac_assign_link_vif(struct ath12k_hw *ah,
 	if (arvif)
 		return arvif;
 
-	if (!vif->valid_links) {
-		/* Use deflink for Non-ML VIFs and mark the link id as 0
-		 */
-		link_id = 0;
+	/* If this is the first link arvif being created for an ML VIF
+	 * use the preallocated deflink memory except for scan arvifs
+	 */
+	if (!ahvif->links_map && link_id != ATH12K_DEFAULT_SCAN_LINK) {
 		arvif = &ahvif->deflink;
+
+		if (vif->type == NL80211_IFTYPE_STATION)
+			arvif->is_sta_assoc_link = true;
 	} else {
-		/* If this is the first link arvif being created for an ML VIF
-		 * use the preallocated deflink memory except for scan arvifs
-		 */
-		if (!ahvif->links_map && link_id != ATH12K_DEFAULT_SCAN_LINK) {
-			arvif = &ahvif->deflink;
-		} else {
-			arvif = (struct ath12k_link_vif *)
-			kzalloc(sizeof(struct ath12k_link_vif), GFP_KERNEL);
-			if (!arvif)
-				return NULL;
-		}
+		arvif = kzalloc(sizeof(*arvif), GFP_KERNEL);
+		if (!arvif)
+			return NULL;
 	}
 
 	ath12k_mac_init_arvif(ahvif, arvif, link_id);
@@ -3702,6 +3634,8 @@ static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw,
 	unsigned long links = ahvif->links_map;
 	struct ieee80211_bss_conf *info;
 	struct ath12k_link_vif *arvif;
+	struct ieee80211_sta *sta;
+	struct ath12k_sta *ahsta;
 	struct ath12k *ar;
 	u8 link_id;
 
@@ -3714,6 +3648,35 @@ static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changed & BSS_CHANGED_ASSOC) {
+		if (vif->cfg.assoc) {
+			/* only in station mode we can get here, so it's safe
+			 * to use ap_addr
+			 */
+			rcu_read_lock();
+			sta = ieee80211_find_sta(vif, vif->cfg.ap_addr);
+			if (!sta) {
+				rcu_read_unlock();
+				WARN_ONCE(1, "failed to find sta with addr %pM\n",
+					  vif->cfg.ap_addr);
+				return;
+			}
+
+			ahsta = ath12k_sta_to_ahsta(sta);
+			arvif = wiphy_dereference(hw->wiphy,
+						  ahvif->link[ahsta->assoc_link_id]);
+			rcu_read_unlock();
+
+			ar = arvif->ar;
+			/* there is no reason for which an assoc link's
+			 * bss info does not exist
+			 */
+			info = ath12k_mac_get_link_bss_conf(arvif);
+			ath12k_bss_assoc(ar, arvif, info);
+
+			/* exclude assoc link as it is done above */
+			links &= ~BIT(ahsta->assoc_link_id);
+		}
+
 		for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) {
 			arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]);
 			if (!arvif || !arvif->ar)
@@ -3789,6 +3752,18 @@ static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif)
 			    psmode, arvif->vdev_id, ret);
 }
 
+static bool ath12k_mac_supports_station_tpc(struct ath12k *ar,
+					    struct ath12k_vif *ahvif,
+					    const struct cfg80211_chan_def *chandef)
+{
+	return ath12k_wmi_supports_6ghz_cc_ext(ar) &&
+		test_bit(WMI_TLV_SERVICE_EXT_TPC_REG_SUPPORT, ar->ab->wmi_ab.svc_map) &&
+		ahvif->vdev_type == WMI_VDEV_TYPE_STA &&
+		ahvif->vdev_subtype == WMI_VDEV_SUBTYPE_NONE &&
+		chandef->chan &&
+		chandef->chan->band == NL80211_BAND_6GHZ;
+}
+
 static void ath12k_mac_bss_info_changed(struct ath12k *ar,
 					struct ath12k_link_vif *arvif,
 					struct ieee80211_bss_conf *info,
@@ -3983,12 +3958,16 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar,
 		band = def.chan->band;
 		mcast_rate = info->mcast_rate[band];
 
-		if (mcast_rate > 0)
+		if (mcast_rate > 0) {
 			rateidx = mcast_rate - 1;
-		else
-			rateidx = ffs(info->basic_rates) - 1;
+		} else {
+			if (info->basic_rates)
+				rateidx = __ffs(info->basic_rates);
+			else
+				rateidx = 0;
+		}
 
-		if (ar->pdev->cap.supported_bands & WMI_HOST_WLAN_5G_CAP)
+		if (ar->pdev->cap.supported_bands & WMI_HOST_WLAN_5GHZ_CAP)
 			rateidx += ATH12K_MAC_FIRST_OFDM_RATE_IDX;
 
 		bitrate = ath12k_legacy_rates[rateidx].bitrate;
@@ -4162,9 +4141,9 @@ ath12k_mac_select_scan_device(struct ieee80211_hw *hw,
 	 * split the hw request and perform multiple scans
 	 */
 
-	if (center_freq < ATH12K_MIN_5G_FREQ)
+	if (center_freq < ATH12K_MIN_5GHZ_FREQ)
 		band = NL80211_BAND_2GHZ;
-	else if (center_freq < ATH12K_MIN_6G_FREQ)
+	else if (center_freq < ATH12K_MIN_6GHZ_FREQ)
 		band = NL80211_BAND_5GHZ;
 	else
 		band = NL80211_BAND_6GHZ;
@@ -4194,7 +4173,7 @@ void __ath12k_mac_scan_finish(struct ath12k *ar)
 		fallthrough;
 	case ATH12K_SCAN_STARTING:
 		cancel_delayed_work(&ar->scan.timeout);
-		complete(&ar->scan.completed);
+		complete_all(&ar->scan.completed);
 		wiphy_work_queue(ar->ah->hw->wiphy, &ar->scan.vdev_clean_wk);
 		break;
 	}
@@ -4376,6 +4355,145 @@ static int ath12k_start_scan(struct ath12k *ar,
 	return 0;
 }
 
+int ath12k_mac_get_fw_stats(struct ath12k *ar,
+			    struct ath12k_fw_stats_req_params *param)
+{
+	struct ath12k_base *ab = ar->ab;
+	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
+	unsigned long timeout, time_left;
+	int ret;
+
+	guard(mutex)(&ah->hw_mutex);
+
+	if (ah->state != ATH12K_HW_STATE_ON)
+		return -ENETDOWN;
+
+	/* FW stats can get split when exceeding the stats data buffer limit.
+	 * In that case, since there is no end marking for the back-to-back
+	 * received 'update stats' event, we keep a 3 seconds timeout in case,
+	 * fw_stats_done is not marked yet
+	 */
+	timeout = jiffies + msecs_to_jiffies(3 * 1000);
+	ath12k_fw_stats_reset(ar);
+
+	reinit_completion(&ar->fw_stats_complete);
+
+	ret = ath12k_wmi_send_stats_request_cmd(ar, param->stats_id,
+						param->vdev_id, param->pdev_id);
+
+	if (ret) {
+		ath12k_warn(ab, "failed to request fw stats: %d\n", ret);
+		return ret;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI,
+		   "get fw stat pdev id %d vdev id %d stats id 0x%x\n",
+		   param->pdev_id, param->vdev_id, param->stats_id);
+
+	time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
+
+	if (!time_left) {
+		ath12k_warn(ab, "time out while waiting for get fw stats\n");
+		return -ETIMEDOUT;
+	}
+
+	/* Firmware sends WMI_UPDATE_STATS_EVENTID back-to-back
+	 * when stats data buffer limit is reached. fw_stats_complete
+	 * is completed once host receives first event from firmware, but
+	 * still end might not be marked in the TLV.
+	 * Below loop is to confirm that firmware completed sending all the event
+	 * and fw_stats_done is marked true when end is marked in the TLV.
+	 */
+	for (;;) {
+		if (time_after(jiffies, timeout))
+			break;
+		spin_lock_bh(&ar->data_lock);
+		if (ar->fw_stats.fw_stats_done) {
+			spin_unlock_bh(&ar->data_lock);
+			break;
+		}
+		spin_unlock_bh(&ar->data_lock);
+	}
+	return 0;
+}
+
+static int ath12k_mac_op_get_txpower(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif,
+				     unsigned int link_id,
+				     int *dbm)
+{
+	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
+	struct ath12k_fw_stats_req_params params = {};
+	struct ath12k_fw_stats_pdev *pdev;
+	struct ath12k_hw *ah = hw->priv;
+	struct ath12k_link_vif *arvif;
+	struct ath12k_base *ab;
+	struct ath12k *ar;
+	int ret;
+
+	/* Final Tx power is minimum of Target Power, CTL power, Regulatory
+	 * Power, PSD EIRP Power. We just know the Regulatory power from the
+	 * regulatory rules obtained. FW knows all these power and sets the min
+	 * of these. Hence, we request the FW pdev stats in which FW reports
+	 * the minimum of all vdev's channel Tx power.
+	 */
+	lockdep_assert_wiphy(hw->wiphy);
+
+	arvif = wiphy_dereference(ah->hw->wiphy, ahvif->link[link_id]);
+	if (!arvif || !arvif->ar)
+		return -EINVAL;
+
+	ar = arvif->ar;
+	ab = ar->ab;
+	if (ah->state != ATH12K_HW_STATE_ON)
+		goto err_fallback;
+
+	if (test_bit(ATH12K_FLAG_CAC_RUNNING, &ar->dev_flags))
+		return -EAGAIN;
+
+	/* Limit the requests to Firmware for fetching the tx power */
+	if (ar->chan_tx_pwr != ATH12K_PDEV_TX_POWER_INVALID &&
+	    time_before(jiffies,
+			msecs_to_jiffies(ATH12K_PDEV_TX_POWER_REFRESH_TIME_MSECS) +
+					 ar->last_tx_power_update))
+		goto send_tx_power;
+
+	params.pdev_id = ar->pdev->pdev_id;
+	params.vdev_id = arvif->vdev_id;
+	params.stats_id = WMI_REQUEST_PDEV_STAT;
+	ret = ath12k_mac_get_fw_stats(ar, &params);
+	if (ret) {
+		ath12k_warn(ab, "failed to request fw pdev stats: %d\n", ret);
+		goto err_fallback;
+	}
+
+	spin_lock_bh(&ar->data_lock);
+	pdev = list_first_entry_or_null(&ar->fw_stats.pdevs,
+					struct ath12k_fw_stats_pdev, list);
+	if (!pdev) {
+		spin_unlock_bh(&ar->data_lock);
+		goto err_fallback;
+	}
+
+	/* tx power reported by firmware is in units of 0.5 dBm */
+	ar->chan_tx_pwr = pdev->chan_tx_power / 2;
+	spin_unlock_bh(&ar->data_lock);
+	ar->last_tx_power_update = jiffies;
+
+send_tx_power:
+	*dbm = ar->chan_tx_pwr;
+	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "txpower fetched from firmware %d dBm\n",
+		   *dbm);
+	return 0;
+
+err_fallback:
+	/* We didn't get txpower from FW. Hence, relying on vif->bss_conf.txpower */
+	*dbm = vif->bss_conf.txpower;
+	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "txpower from firmware NaN, reported %d dBm\n",
+		   *dbm);
+	return 0;
+}
+
 static u8
 ath12k_mac_find_link_id_by_ar(struct ath12k_vif *ahvif, struct ath12k *ar)
 {
@@ -4429,7 +4547,7 @@ static int ath12k_mac_op_hw_scan(struct ieee80211_hw *hw,
 		return -EINVAL;
 
 	/* check if any of the links of ML VIF is already started on
-	 * radio(ar) correpsondig to given scan frequency and use it,
+	 * radio(ar) corresponding to given scan frequency and use it,
 	 * if not use scan link (link 15) for scan purpose.
 	 */
 	link_id = ath12k_mac_find_link_id_by_ar(ahvif, ar);
@@ -4538,10 +4656,16 @@ static int ath12k_mac_op_hw_scan(struct ieee80211_hw *hw,
 
 	ret = ath12k_start_scan(ar, arg);
 	if (ret) {
-		ath12k_warn(ar->ab, "failed to start hw scan: %d\n", ret);
+		if (ret == -EBUSY)
+			ath12k_dbg(ar->ab, ATH12K_DBG_MAC,
+				   "scan engine is busy 11d state %d\n", ar->state_11d);
+		else
+			ath12k_warn(ar->ab, "failed to start hw scan: %d\n", ret);
+
 		spin_lock_bh(&ar->data_lock);
 		ar->scan.state = ATH12K_SCAN_IDLE;
 		spin_unlock_bh(&ar->data_lock);
+		goto exit;
 	}
 
 	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac scan started");
@@ -4565,6 +4689,11 @@ exit:
 		kfree(arg);
 	}
 
+	if (ar->state_11d == ATH12K_11D_PREPARING &&
+	    ahvif->vdev_type == WMI_VDEV_TYPE_STA &&
+	    ahvif->vdev_subtype == WMI_VDEV_SUBTYPE_NONE)
+		ath12k_mac_11d_scan_start(ar, arvif->vdev_id);
+
 	return ret;
 }
 
@@ -4605,7 +4734,6 @@ static int ath12k_install_key(struct ath12k_link_vif *arvif,
 		.macaddr = macaddr,
 	};
 	struct ath12k_vif *ahvif = arvif->ahvif;
-	struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif);
 
 	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
 
@@ -4624,8 +4752,8 @@ static int ath12k_install_key(struct ath12k_link_vif *arvif,
 
 	switch (key->cipher) {
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 		arg.key_cipher = WMI_CIPHER_AES_CCM;
-		/* TODO: Re-check if flag is valid */
 		key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV_MGMT;
 		break;
 	case WLAN_CIPHER_SUITE_TKIP:
@@ -4633,12 +4761,10 @@ static int ath12k_install_key(struct ath12k_link_vif *arvif,
 		arg.key_txmic_len = 8;
 		arg.key_rxmic_len = 8;
 		break;
-	case WLAN_CIPHER_SUITE_CCMP_256:
-		arg.key_cipher = WMI_CIPHER_AES_CCM;
-		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		arg.key_cipher = WMI_CIPHER_AES_GCM;
+		key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV_MGMT;
 		break;
 	default:
 		ath12k_warn(ar->ab, "cipher %d is not supported\n", key->cipher);
@@ -4658,7 +4784,7 @@ install:
 	if (!wait_for_completion_timeout(&ar->install_key_done, 1 * HZ))
 		return -ETIMEDOUT;
 
-	if (ether_addr_equal(macaddr, vif->addr))
+	if (ether_addr_equal(macaddr, arvif->bssid))
 		ahvif->key_cipher = key->cipher;
 
 	return ar->install_key_status ? -EINVAL : 0;
@@ -5524,10 +5650,13 @@ static int ath12k_mac_station_add(struct ath12k *ar,
 			    ar->max_num_stations);
 		goto exit;
 	}
-	arsta->rx_stats = kzalloc(sizeof(*arsta->rx_stats), GFP_KERNEL);
-	if (!arsta->rx_stats) {
-		ret = -ENOMEM;
-		goto dec_num_station;
+
+	if (ath12k_debugfs_is_extd_rx_stats_enabled(ar) && !arsta->rx_stats) {
+		arsta->rx_stats = kzalloc(sizeof(*arsta->rx_stats), GFP_KERNEL);
+		if (!arsta->rx_stats) {
+			ret = -ENOMEM;
+			goto dec_num_station;
+		}
 	}
 
 	peer_param.vdev_id = arvif->vdev_id;
@@ -5669,12 +5798,15 @@ static int ath12k_mac_handle_link_sta_state(struct ieee80211_hw *hw,
 					    enum ieee80211_sta_state new_state)
 {
 	struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif);
+	struct ieee80211_bss_conf *link_conf;
 	struct ath12k *ar = arvif->ar;
+	struct ath12k_reg_info *reg_info;
+	struct ath12k_base *ab = ar->ab;
 	int ret = 0;
 
 	lockdep_assert_wiphy(hw->wiphy);
 
-	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac handle link %u sta %pM state %d -> %d\n",
+	ath12k_dbg(ab, ATH12K_DBG_MAC, "mac handle link %u sta %pM state %d -> %d\n",
 		   arsta->link_id, arsta->addr, old_state, new_state);
 
 	/* IEEE80211_STA_NONE -> IEEE80211_STA_NOTEXIST: Remove the station
@@ -5684,7 +5816,7 @@ static int ath12k_mac_handle_link_sta_state(struct ieee80211_hw *hw,
 	     new_state == IEEE80211_STA_NOTEXIST)) {
 		ret = ath12k_mac_station_remove(ar, arvif, arsta);
 		if (ret) {
-			ath12k_warn(ar->ab, "Failed to remove station: %pM for VDEV: %d\n",
+			ath12k_warn(ab, "Failed to remove station: %pM for VDEV: %d\n",
 				    arsta->addr, arvif->vdev_id);
 			goto exit;
 		}
@@ -5695,7 +5827,7 @@ static int ath12k_mac_handle_link_sta_state(struct ieee80211_hw *hw,
 	    new_state == IEEE80211_STA_NONE) {
 		ret = ath12k_mac_station_add(ar, arvif, arsta);
 		if (ret)
-			ath12k_warn(ar->ab, "Failed to add station: %pM for VDEV: %d\n",
+			ath12k_warn(ab, "Failed to add station: %pM for VDEV: %d\n",
 				    arsta->addr, arvif->vdev_id);
 
 	/* IEEE80211_STA_AUTH -> IEEE80211_STA_ASSOC: Send station assoc command for
@@ -5708,7 +5840,7 @@ static int ath12k_mac_handle_link_sta_state(struct ieee80211_hw *hw,
 		    vif->type == NL80211_IFTYPE_ADHOC)) {
 		ret = ath12k_mac_station_assoc(ar, arvif, arsta, false);
 		if (ret)
-			ath12k_warn(ar->ab, "Failed to associate station: %pM\n",
+			ath12k_warn(ab, "Failed to associate station: %pM\n",
 				    arsta->addr);
 
 	/* IEEE80211_STA_ASSOC -> IEEE80211_STA_AUTHORIZED: set peer status as
@@ -5717,9 +5849,21 @@ static int ath12k_mac_handle_link_sta_state(struct ieee80211_hw *hw,
 	} else if (old_state == IEEE80211_STA_ASSOC &&
 		   new_state == IEEE80211_STA_AUTHORIZED) {
 		ret = ath12k_mac_station_authorize(ar, arvif, arsta);
-		if (ret)
-			ath12k_warn(ar->ab, "Failed to authorize station: %pM\n",
+		if (ret) {
+			ath12k_warn(ab, "Failed to authorize station: %pM\n",
 				    arsta->addr);
+			goto exit;
+		}
+
+		if (ath12k_wmi_supports_6ghz_cc_ext(ar) &&
+		    arvif->ahvif->vdev_type == WMI_VDEV_TYPE_STA) {
+			link_conf = ath12k_mac_get_link_bss_conf(arvif);
+			reg_info = ab->reg_info[ar->pdev_idx];
+			ath12k_dbg(ab, ATH12K_DBG_MAC, "connection done, update reg rules\n");
+			ath12k_hw_to_ah(hw)->regd_updated = false;
+			ath12k_reg_handle_chan_list(ab, reg_info, arvif->ahvif->vdev_type,
+						    link_conf->power_type);
+		}
 
 	/* IEEE80211_STA_AUTHORIZED -> IEEE80211_STA_ASSOC: station may be in removal,
 	 * deauthorize it.
@@ -5738,7 +5882,7 @@ static int ath12k_mac_handle_link_sta_state(struct ieee80211_hw *hw,
 		    vif->type == NL80211_IFTYPE_ADHOC)) {
 		ret = ath12k_mac_station_disassoc(ar, arvif, arsta);
 		if (ret)
-			ath12k_warn(ar->ab, "Failed to disassociate station: %pM\n",
+			ath12k_warn(ab, "Failed to disassociate station: %pM\n",
 				    arsta->addr);
 	}
 
@@ -5802,6 +5946,17 @@ static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
 		 * link sta
 		 */
 		if (sta->mlo) {
+			/* For station mode, arvif->is_sta_assoc_link has been set when
+			 * vdev starts. Make sure the arvif/arsta pair have same setting
+			 */
+			if (vif->type == NL80211_IFTYPE_STATION &&
+			    !arsta->arvif->is_sta_assoc_link) {
+				ath12k_hw_warn(ah, "failed to verify assoc link setting with link id %u\n",
+					       link_id);
+				ret = -EINVAL;
+				goto exit;
+			}
+
 			arsta->is_assoc_link = true;
 			ahsta->assoc_link_id = link_id;
 		}
@@ -6475,7 +6630,7 @@ static void ath12k_mac_setup_ht_vht_cap(struct ath12k *ar,
 	rate_cap_tx_chainmask = ar->cfg_tx_chainmask >> cap->tx_chain_mask_shift;
 	rate_cap_rx_chainmask = ar->cfg_rx_chainmask >> cap->rx_chain_mask_shift;
 
-	if (cap->supported_bands & WMI_HOST_WLAN_2G_CAP) {
+	if (cap->supported_bands & WMI_HOST_WLAN_2GHZ_CAP) {
 		band = &ar->mac.sbands[NL80211_BAND_2GHZ];
 		ht_cap = cap->band[NL80211_BAND_2GHZ].ht_cap_info;
 		if (ht_cap_info)
@@ -6484,7 +6639,7 @@ static void ath12k_mac_setup_ht_vht_cap(struct ath12k *ar,
 						    rate_cap_rx_chainmask);
 	}
 
-	if (cap->supported_bands & WMI_HOST_WLAN_5G_CAP &&
+	if (cap->supported_bands & WMI_HOST_WLAN_5GHZ_CAP &&
 	    (ar->ab->hw_params->single_pdev_only ||
 	     !ar->supports_6ghz)) {
 		band = &ar->mac.sbands[NL80211_BAND_5GHZ];
@@ -6661,6 +6816,8 @@ static void ath12k_mac_copy_he_cap(struct ath12k_band_cap *band_cap,
 
 	switch (iftype) {
 	case NL80211_IFTYPE_AP:
+		he_cap_elem->mac_cap_info[2] &=
+			~IEEE80211_HE_MAC_CAP2_BCAST_TWT;
 		he_cap_elem->phy_cap_info[3] &=
 			~IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK;
 		he_cap_elem->phy_cap_info[9] |=
@@ -6893,7 +7050,7 @@ static void ath12k_mac_setup_sband_iftype_data(struct ath12k *ar,
 	enum nl80211_band band;
 	int count;
 
-	if (cap->supported_bands & WMI_HOST_WLAN_2G_CAP) {
+	if (cap->supported_bands & WMI_HOST_WLAN_2GHZ_CAP) {
 		band = NL80211_BAND_2GHZ;
 		count = ath12k_mac_copy_sband_iftype_data(ar, cap,
 							  ar->mac.iftype[band],
@@ -6903,7 +7060,7 @@ static void ath12k_mac_setup_sband_iftype_data(struct ath12k *ar,
 						 count);
 	}
 
-	if (cap->supported_bands & WMI_HOST_WLAN_5G_CAP) {
+	if (cap->supported_bands & WMI_HOST_WLAN_5GHZ_CAP) {
 		band = NL80211_BAND_5GHZ;
 		count = ath12k_mac_copy_sband_iftype_data(ar, cap,
 							  ar->mac.iftype[band],
@@ -6913,7 +7070,7 @@ static void ath12k_mac_setup_sband_iftype_data(struct ath12k *ar,
 						 count);
 	}
 
-	if (cap->supported_bands & WMI_HOST_WLAN_5G_CAP &&
+	if (cap->supported_bands & WMI_HOST_WLAN_5GHZ_CAP &&
 	    ar->supports_6ghz) {
 		band = NL80211_BAND_6GHZ;
 		count = ath12k_mac_copy_sband_iftype_data(ar, cap,
@@ -7041,14 +7198,17 @@ static int ath12k_mac_mgmt_tx_wmi(struct ath12k *ar, struct ath12k_link_vif *arv
 {
 	struct ath12k_base *ab = ar->ab;
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	struct ath12k_skb_cb *skb_cb = ATH12K_SKB_CB(skb);
 	struct ieee80211_tx_info *info;
+	enum hal_encrypt_type enctype;
+	unsigned int mic_len;
 	dma_addr_t paddr;
 	int buf_id;
 	int ret;
 
 	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
 
-	ATH12K_SKB_CB(skb)->ar = ar;
+	skb_cb->ar = ar;
 	spin_lock_bh(&ar->txmgmt_idr_lock);
 	buf_id = idr_alloc(&ar->txmgmt_idr, skb, 0,
 			   ATH12K_TX_MGMT_NUM_PENDING_MAX, GFP_ATOMIC);
@@ -7057,12 +7217,15 @@ static int ath12k_mac_mgmt_tx_wmi(struct ath12k *ar, struct ath12k_link_vif *arv
 		return -ENOSPC;
 
 	info = IEEE80211_SKB_CB(skb);
-	if (!(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)) {
+	if ((skb_cb->flags & ATH12K_SKB_CIPHER_SET) &&
+	    !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)) {
 		if ((ieee80211_is_action(hdr->frame_control) ||
 		     ieee80211_is_deauth(hdr->frame_control) ||
 		     ieee80211_is_disassoc(hdr->frame_control)) &&
 		     ieee80211_has_protected(hdr->frame_control)) {
-			skb_put(skb, IEEE80211_CCMP_MIC_LEN);
+			enctype = ath12k_dp_tx_get_encrypt_type(skb_cb->cipher);
+			mic_len = ath12k_dp_rx_crypto_mic_len(ar, enctype);
+			skb_put(skb, mic_len);
 		}
 	}
 
@@ -7073,7 +7236,7 @@ static int ath12k_mac_mgmt_tx_wmi(struct ath12k *ar, struct ath12k_link_vif *arv
 		goto err_free_idr;
 	}
 
-	ATH12K_SKB_CB(skb)->paddr = paddr;
+	skb_cb->paddr = paddr;
 
 	ret = ath12k_wmi_mgmt_send(ar, arvif->vdev_id, buf_id, skb);
 	if (ret) {
@@ -7084,7 +7247,7 @@ static int ath12k_mac_mgmt_tx_wmi(struct ath12k *ar, struct ath12k_link_vif *arv
 	return 0;
 
 err_unmap_buf:
-	dma_unmap_single(ab->dev, ATH12K_SKB_CB(skb)->paddr,
+	dma_unmap_single(ab->dev, skb_cb->paddr,
 			 skb->len, DMA_TO_DEVICE);
 err_free_idr:
 	spin_lock_bh(&ar->txmgmt_idr_lock);
@@ -7337,12 +7500,18 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw,
 	struct ath12k_peer *peer;
 	unsigned long links_map;
 	bool is_mcast = false;
+	bool is_dvlan = false;
 	struct ethhdr *eth;
 	bool is_prb_rsp;
 	u16 mcbc_gsn;
 	u8 link_id;
 	int ret;
 
+	if (ahvif->vdev_type == WMI_VDEV_TYPE_MONITOR) {
+		ieee80211_free_txskb(hw, skb);
+		return;
+	}
+
 	link_id = u32_get_bits(info->control.flags, IEEE80211_TX_CTRL_MLO_LINK);
 	memset(skb_cb, 0, sizeof(*skb_cb));
 	skb_cb->vif = vif;
@@ -7397,9 +7566,16 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw,
 	if (vif->type == NL80211_IFTYPE_AP && vif->p2p)
 		ath12k_mac_add_p2p_noa_ie(ar, vif, skb, is_prb_rsp);
 
-	if (!vif->valid_links || !is_mcast ||
+	/* Checking if it is a DVLAN frame */
+	if (!test_bit(ATH12K_FLAG_HW_CRYPTO_DISABLED, &ar->ab->dev_flags) &&
+	    !(skb_cb->flags & ATH12K_SKB_HW_80211_ENCAP) &&
+	    !(skb_cb->flags & ATH12K_SKB_CIPHER_SET) &&
+	    ieee80211_has_protected(hdr->frame_control))
+		is_dvlan = true;
+
+	if (!vif->valid_links || !is_mcast || is_dvlan ||
 	    test_bit(ATH12K_FLAG_RAW_MODE, &ar->ab->dev_flags)) {
-		ret = ath12k_dp_tx(ar, arvif, skb, false, 0);
+		ret = ath12k_dp_tx(ar, arvif, skb, false, 0, is_mcast);
 		if (unlikely(ret)) {
 			ath12k_warn(ar->ab, "failed to transmit frame %d\n", ret);
 			ieee80211_free_txskb(ar->ah->hw, skb);
@@ -7429,11 +7605,10 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw,
 								info_flags);
 
 			skb_cb = ATH12K_SKB_CB(msdu_copied);
-			info = IEEE80211_SKB_CB(msdu_copied);
 			skb_cb->link_id = link_id;
 
 			/* For open mode, skip peer find logic */
-			if (unlikely(ahvif->key_cipher == WMI_CIPHER_NONE))
+			if (unlikely(!ahvif->key_cipher))
 				goto skip_peer_find;
 
 			spin_lock_bh(&tmp_ar->ab->base_lock);
@@ -7452,7 +7627,6 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw,
 			if (key) {
 				skb_cb->cipher = key->cipher;
 				skb_cb->flags |= ATH12K_SKB_CIPHER_SET;
-				info->control.hw_key = key;
 
 				hdr = (struct ieee80211_hdr *)msdu_copied->data;
 				if (!ieee80211_has_protected(hdr->frame_control))
@@ -7463,7 +7637,7 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw,
 
 skip_peer_find:
 			ret = ath12k_dp_tx(tmp_ar, tmp_arvif,
-					   msdu_copied, true, mcbc_gsn);
+					   msdu_copied, true, mcbc_gsn, is_mcast);
 			if (unlikely(ret)) {
 				if (ret == -ENOMEM) {
 					/* Drops are expected during heavy multicast
@@ -7549,7 +7723,7 @@ static int ath12k_mac_start(struct ath12k *ar)
 					1, pdev->pdev_id);
 
 	if (ret) {
-		ath12k_err(ab, "failed to enable PMF QOS: (%d\n", ret);
+		ath12k_err(ab, "failed to enable PMF QOS: %d\n", ret);
 		goto err;
 	}
 
@@ -7594,12 +7768,13 @@ static int ath12k_mac_start(struct ath12k *ar)
 
 	/* TODO: Do we need to enable ANI? */
 
-	ath12k_reg_update_chan_list(ar);
+	ath12k_reg_update_chan_list(ar, false);
 
 	ar->num_started_vdevs = 0;
 	ar->num_created_vdevs = 0;
 	ar->num_peers = 0;
 	ar->allocated_vdev_map = 0;
+	ar->chan_tx_pwr = ATH12K_PDEV_TX_POWER_INVALID;
 
 	/* Configure monitor status ring with default rx_filter to get rx status
 	 * such as rssi, rx_duration.
@@ -7781,6 +7956,9 @@ static void ath12k_mac_stop(struct ath12k *ar)
 	wiphy_work_cancel(ath12k_ar_to_hw(ar)->wiphy, &ar->scan.vdev_clean_wk);
 	cancel_work_sync(&ar->regd_update_work);
 	cancel_work_sync(&ar->ab->rfkill_work);
+	cancel_work_sync(&ar->ab->update_11d_work);
+	ar->state_11d = ATH12K_11D_IDLE;
+	complete(&ar->completed_11d_scan);
 
 	spin_lock_bh(&ar->data_lock);
 	list_for_each_entry_safe(ppdu_stats, tmp, &ar->ppdu_stats_info, list) {
@@ -7854,7 +8032,7 @@ static int ath12k_mac_setup_vdev_params_mbssid(struct ath12k_link_vif *arvif,
 		return -ENOLINK;
 	}
 
-	tx_arvif = ath12k_mac_get_tx_arvif(arvif);
+	tx_arvif = ath12k_mac_get_tx_arvif(arvif, link_conf);
 	if (!tx_arvif)
 		return 0;
 
@@ -7903,15 +8081,15 @@ static int ath12k_mac_setup_vdev_create_arg(struct ath12k_link_vif *arvif,
 			return ret;
 	}
 
-	if (pdev->cap.supported_bands & WMI_HOST_WLAN_2G_CAP) {
+	if (pdev->cap.supported_bands & WMI_HOST_WLAN_2GHZ_CAP) {
 		arg->chains[NL80211_BAND_2GHZ].tx = ar->num_tx_chains;
 		arg->chains[NL80211_BAND_2GHZ].rx = ar->num_rx_chains;
 	}
-	if (pdev->cap.supported_bands & WMI_HOST_WLAN_5G_CAP) {
+	if (pdev->cap.supported_bands & WMI_HOST_WLAN_5GHZ_CAP) {
 		arg->chains[NL80211_BAND_5GHZ].tx = ar->num_tx_chains;
 		arg->chains[NL80211_BAND_5GHZ].rx = ar->num_rx_chains;
 	}
-	if (pdev->cap.supported_bands & WMI_HOST_WLAN_5G_CAP &&
+	if (pdev->cap.supported_bands & WMI_HOST_WLAN_5GHZ_CAP &&
 	    ar->supports_6ghz) {
 		arg->chains[NL80211_BAND_6GHZ].tx = ar->num_tx_chains;
 		arg->chains[NL80211_BAND_6GHZ].rx = ar->num_rx_chains;
@@ -7940,7 +8118,7 @@ ath12k_mac_prepare_he_mode(struct ath12k_pdev *pdev, u32 viftype)
 	u32 *hecap_phy_ptr = NULL;
 	u32 hemode;
 
-	if (pdev->cap.supported_bands & WMI_HOST_WLAN_2G_CAP)
+	if (pdev->cap.supported_bands & WMI_HOST_WLAN_2GHZ_CAP)
 		cap_band = &pdev_cap->band[NL80211_BAND_2GHZ];
 	else
 		cap_band = &pdev_cap->band[NL80211_BAND_5GHZ];
@@ -8071,44 +8249,121 @@ static void ath12k_mac_op_update_vif_offload(struct ieee80211_hw *hw,
 	ath12k_mac_update_vif_offload(&ahvif->deflink);
 }
 
-int ath12k_mac_vdev_create(struct ath12k *ar, struct ath12k_link_vif *arvif)
+static bool ath12k_mac_vif_ap_active_any(struct ath12k_base *ab)
 {
-	struct ath12k_hw *ah = ar->ah;
-	struct ath12k_base *ab = ar->ab;
-	struct ieee80211_hw *hw = ah->hw;
-	struct ath12k_vif *ahvif = arvif->ahvif;
-	struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif);
-	struct ath12k_wmi_vdev_create_arg vdev_arg = {0};
-	struct ath12k_wmi_peer_create_arg peer_param = {0};
-	struct ieee80211_bss_conf *link_conf;
-	u32 param_id, param_value;
-	u16 nss;
+	struct ath12k *ar;
+	struct ath12k_pdev *pdev;
+	struct ath12k_link_vif *arvif;
 	int i;
-	int ret, vdev_id;
-	u8 link_id;
 
-	lockdep_assert_wiphy(hw->wiphy);
+	for (i = 0; i < ab->num_radios; i++) {
+		pdev = &ab->pdevs[i];
+		ar = pdev->ar;
+		list_for_each_entry(arvif, &ar->arvifs, list) {
+			if (arvif->is_up &&
+			    arvif->ahvif->vdev_type == WMI_VDEV_TYPE_AP)
+				return true;
+		}
+	}
+	return false;
+}
 
-	/* If no link is active and scan vdev is requested
-	 * use a default link conf for scan address purpose.
-	 */
-	if (arvif->link_id == ATH12K_DEFAULT_SCAN_LINK && vif->valid_links)
-		link_id = ffs(vif->valid_links) - 1;
-	else
-		link_id = arvif->link_id;
+void ath12k_mac_11d_scan_start(struct ath12k *ar, u32 vdev_id)
+{
+	struct wmi_11d_scan_start_arg arg;
+	int ret;
 
-	link_conf = wiphy_dereference(hw->wiphy, vif->link_conf[link_id]);
-	if (!link_conf) {
-		ath12k_warn(ar->ab, "unable to access bss link conf in vdev create for vif %pM link %u\n",
-			    vif->addr, arvif->link_id);
-		return -ENOLINK;
+	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
+
+	if (ar->regdom_set_by_user)
+		goto fin;
+
+	if (ar->vdev_id_11d_scan != ATH12K_11D_INVALID_VDEV_ID)
+		goto fin;
+
+	if (!test_bit(WMI_TLV_SERVICE_11D_OFFLOAD, ar->ab->wmi_ab.svc_map))
+		goto fin;
+
+	if (ath12k_mac_vif_ap_active_any(ar->ab))
+		goto fin;
+
+	arg.vdev_id = vdev_id;
+	arg.start_interval_msec = 0;
+	arg.scan_period_msec = ATH12K_SCAN_11D_INTERVAL;
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_MAC,
+		   "mac start 11d scan for vdev %d\n", vdev_id);
+
+	ret = ath12k_wmi_send_11d_scan_start_cmd(ar, &arg);
+	if (ret) {
+		ath12k_warn(ar->ab, "failed to start 11d scan vdev %d ret: %d\n",
+			    vdev_id, ret);
+	} else {
+		ar->vdev_id_11d_scan = vdev_id;
+		if (ar->state_11d == ATH12K_11D_PREPARING)
+			ar->state_11d = ATH12K_11D_RUNNING;
 	}
 
-	memcpy(arvif->bssid, link_conf->addr, ETH_ALEN);
+fin:
+	if (ar->state_11d == ATH12K_11D_PREPARING) {
+		ar->state_11d = ATH12K_11D_IDLE;
+		complete(&ar->completed_11d_scan);
+	}
+}
 
-	arvif->ar = ar;
-	vdev_id = __ffs64(ab->free_vdev_map);
-	arvif->vdev_id = vdev_id;
+void ath12k_mac_11d_scan_stop(struct ath12k *ar)
+{
+	int ret;
+	u32 vdev_id;
+
+	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
+
+	if (!test_bit(WMI_TLV_SERVICE_11D_OFFLOAD, ar->ab->wmi_ab.svc_map))
+		return;
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac stop 11d for vdev %d\n",
+		   ar->vdev_id_11d_scan);
+
+	if (ar->state_11d == ATH12K_11D_PREPARING) {
+		ar->state_11d = ATH12K_11D_IDLE;
+		complete(&ar->completed_11d_scan);
+	}
+
+	if (ar->vdev_id_11d_scan != ATH12K_11D_INVALID_VDEV_ID) {
+		vdev_id = ar->vdev_id_11d_scan;
+
+		ret = ath12k_wmi_send_11d_scan_stop_cmd(ar, vdev_id);
+		if (ret) {
+			ath12k_warn(ar->ab,
+				    "failed to stopt 11d scan vdev %d ret: %d\n",
+				    vdev_id, ret);
+		} else {
+			ar->vdev_id_11d_scan = ATH12K_11D_INVALID_VDEV_ID;
+			ar->state_11d = ATH12K_11D_IDLE;
+			complete(&ar->completed_11d_scan);
+		}
+	}
+}
+
+void ath12k_mac_11d_scan_stop_all(struct ath12k_base *ab)
+{
+	struct ath12k *ar;
+	struct ath12k_pdev *pdev;
+	int i;
+
+	ath12k_dbg(ab, ATH12K_DBG_MAC, "mac stop soc 11d scan\n");
+
+	for (i = 0; i < ab->num_radios; i++) {
+		pdev = &ab->pdevs[i];
+		ar = pdev->ar;
+
+		ath12k_mac_11d_scan_stop(ar);
+	}
+}
+
+static void ath12k_mac_determine_vdev_type(struct ieee80211_vif *vif,
+					   struct ath12k_vif *ahvif)
+{
 	ahvif->vdev_subtype = WMI_VDEV_SUBTYPE_NONE;
 
 	switch (vif->type) {
@@ -8132,7 +8387,6 @@ int ath12k_mac_vdev_create(struct ath12k *ar, struct ath12k_link_vif *arvif)
 		break;
 	case NL80211_IFTYPE_MONITOR:
 		ahvif->vdev_type = WMI_VDEV_TYPE_MONITOR;
-		ar->monitor_vdev_id = vdev_id;
 		break;
 	case NL80211_IFTYPE_P2P_DEVICE:
 		ahvif->vdev_type = WMI_VDEV_TYPE_STA;
@@ -8142,6 +8396,53 @@ int ath12k_mac_vdev_create(struct ath12k *ar, struct ath12k_link_vif *arvif)
 		WARN_ON(1);
 		break;
 	}
+}
+
+int ath12k_mac_vdev_create(struct ath12k *ar, struct ath12k_link_vif *arvif)
+{
+	struct ath12k_hw *ah = ar->ah;
+	struct ath12k_base *ab = ar->ab;
+	struct ieee80211_hw *hw = ah->hw;
+	struct ath12k_vif *ahvif = arvif->ahvif;
+	struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif);
+	struct ath12k_wmi_vdev_create_arg vdev_arg = {0};
+	struct ath12k_wmi_peer_create_arg peer_param = {0};
+	struct ieee80211_bss_conf *link_conf = NULL;
+	u32 param_id, param_value;
+	u16 nss;
+	int i;
+	int ret, vdev_id;
+	u8 link_id;
+
+	lockdep_assert_wiphy(hw->wiphy);
+
+	/* In NO_VIRTUAL_MONITOR, its necessary to restrict only one monitor
+	 * interface in each radio
+	 */
+	if (vif->type == NL80211_IFTYPE_MONITOR && ar->monitor_vdev_created)
+		return -EINVAL;
+
+	link_id = arvif->link_id;
+
+	if (link_id < IEEE80211_MLD_MAX_NUM_LINKS) {
+		link_conf = wiphy_dereference(hw->wiphy, vif->link_conf[link_id]);
+		if (!link_conf) {
+			ath12k_warn(ar->ab, "unable to access bss link conf in vdev create for vif %pM link %u\n",
+				    vif->addr, arvif->link_id);
+			return -ENOLINK;
+		}
+	}
+
+	if (link_conf)
+		memcpy(arvif->bssid, link_conf->addr, ETH_ALEN);
+	else
+		memcpy(arvif->bssid, vif->addr, ETH_ALEN);
+
+	arvif->ar = ar;
+	vdev_id = __ffs64(ab->free_vdev_map);
+	arvif->vdev_id = vdev_id;
+	if (vif->type == NL80211_IFTYPE_MONITOR)
+		ar->monitor_vdev_id = vdev_id;
 
 	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev create id %d type %d subtype %d map %llx\n",
 		   arvif->vdev_id, ahvif->vdev_type, ahvif->vdev_subtype,
@@ -8205,6 +8506,7 @@ int ath12k_mac_vdev_create(struct ath12k *ar, struct ath12k_link_vif *arvif)
 				    arvif->vdev_id, ret);
 			goto err_peer_del;
 		}
+		ath12k_mac_11d_scan_stop_all(ar->ab);
 		break;
 	case WMI_VDEV_TYPE_STA:
 		param_id = WMI_STA_PS_PARAM_RX_WAKE_POLICY;
@@ -8243,12 +8545,26 @@ int ath12k_mac_vdev_create(struct ath12k *ar, struct ath12k_link_vif *arvif)
 				    arvif->vdev_id, ret);
 			goto err_peer_del;
 		}
+
+		if (test_bit(WMI_TLV_SERVICE_11D_OFFLOAD, ab->wmi_ab.svc_map) &&
+		    ahvif->vdev_type == WMI_VDEV_TYPE_STA &&
+		    ahvif->vdev_subtype == WMI_VDEV_SUBTYPE_NONE) {
+			reinit_completion(&ar->completed_11d_scan);
+			ar->state_11d = ATH12K_11D_PREPARING;
+		}
+		break;
+	case WMI_VDEV_TYPE_MONITOR:
+		ar->monitor_vdev_created = true;
 		break;
 	default:
 		break;
 	}
 
-	arvif->txpower = link_conf->txpower;
+	if (link_conf)
+		arvif->txpower = link_conf->txpower;
+	else
+		arvif->txpower = NL80211_TX_POWER_AUTOMATIC;
+
 	ret = ath12k_mac_txpower_recalc(ar);
 	if (ret)
 		goto err_peer_del;
@@ -8263,8 +8579,6 @@ int ath12k_mac_vdev_create(struct ath12k *ar, struct ath12k_link_vif *arvif)
 	}
 
 	ath12k_dp_vdev_tx_attach(ar, arvif);
-	if (vif->type != NL80211_IFTYPE_MONITOR && ar->monitor_conf_enabled)
-		ath12k_mac_monitor_vdev_create(ar);
 
 	return ret;
 
@@ -8289,6 +8603,11 @@ err_peer_del:
 	}
 
 err_vdev_del:
+	if (ahvif->vdev_type == WMI_VDEV_TYPE_MONITOR) {
+		ar->monitor_vdev_id = -1;
+		ar->monitor_vdev_created = false;
+	}
+
 	ath12k_wmi_vdev_delete(ar, arvif->vdev_id);
 	ar->num_created_vdevs--;
 	arvif->is_created = false;
@@ -8483,7 +8802,10 @@ static int ath12k_mac_op_add_interface(struct ieee80211_hw *hw,
 {
 	struct ath12k_hw *ah = ath12k_hw_to_ah(hw);
 	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
+	struct ath12k_reg_info *reg_info;
 	struct ath12k_link_vif *arvif;
+	struct ath12k_base *ab;
+	struct ath12k *ar;
 	int i;
 
 	lockdep_assert_wiphy(hw->wiphy);
@@ -8502,6 +8824,22 @@ static int ath12k_mac_op_add_interface(struct ieee80211_hw *hw,
 		vif->hw_queue[i] = ATH12K_HW_DEFAULT_QUEUE;
 
 	vif->driver_flags |= IEEE80211_VIF_SUPPORTS_UAPSD;
+
+	ath12k_mac_determine_vdev_type(vif, ahvif);
+
+	for_each_ar(ah, ar, i) {
+		if (!ath12k_wmi_supports_6ghz_cc_ext(ar))
+			continue;
+
+		ab = ar->ab;
+		reg_info = ab->reg_info[ar->pdev_idx];
+		ath12k_dbg(ab, ATH12K_DBG_MAC, "interface added to change reg rules\n");
+		ah->regd_updated = false;
+		ath12k_reg_handle_chan_list(ab, reg_info, ahvif->vdev_type,
+					    IEEE80211_REG_UNSET_AP);
+		break;
+	}
+
 	/* Defer vdev creation until assign_chanctx or hw_scan is initiated as driver
 	 * will not know if this interface is an ML vif at this point.
 	 */
@@ -8566,8 +8904,6 @@ static int ath12k_mac_vdev_delete(struct ath12k *ar, struct ath12k_link_vif *arv
 	if (ahvif->vdev_type == WMI_VDEV_TYPE_MONITOR) {
 		ar->monitor_vdev_id = -1;
 		ar->monitor_vdev_created = false;
-	} else if (ar->monitor_vdev_created && !ar->monitor_started) {
-		ret = ath12k_mac_monitor_vdev_delete(ar);
 	}
 
 	ath12k_dbg(ab, ATH12K_DBG_MAC, "vdev %pM deleted, vdev_id %d\n",
@@ -8798,6 +9134,7 @@ static int ath12k_mac_op_add_chanctx(struct ieee80211_hw *hw,
 	 */
 	ar->rx_channel = ctx->def.chan;
 	spin_unlock_bh(&ar->data_lock);
+	ar->chan_tx_pwr = ATH12K_PDEV_TX_POWER_INVALID;
 
 	return 0;
 }
@@ -8826,6 +9163,7 @@ static void ath12k_mac_op_remove_chanctx(struct ieee80211_hw *hw,
 	 */
 	ar->rx_channel = NULL;
 	spin_unlock_bh(&ar->data_lock);
+	ar->chan_tx_pwr = ATH12K_PDEV_TX_POWER_INVALID;
 }
 
 static enum wmi_phy_mode
@@ -8917,6 +9255,9 @@ ath12k_mac_mlo_get_vdev_args(struct ath12k_link_vif *arvif,
 	 * link vdevs which are advertised as partners below
 	 */
 	ml_arg->link_add = true;
+
+	ml_arg->assoc_link = arvif->is_sta_assoc_link;
+
 	partner_info = ml_arg->partner_info;
 
 	links = ahvif->links_map;
@@ -9055,6 +9396,15 @@ ath12k_mac_vdev_start_restart(struct ath12k_link_vif *arvif,
 		return ret;
 	}
 
+	/* TODO: For now we only set TPC power here. However when
+	 * channel changes, say CSA, it should be updated again.
+	 */
+	if (ath12k_mac_supports_station_tpc(ar, ahvif, chandef)) {
+		ath12k_mac_fill_reg_tpc_info(ar, arvif, ctx);
+		ath12k_wmi_send_vdev_set_tpc_power(ar, arvif->vdev_id,
+						   &arvif->reg_tpc_info);
+	}
+
 	ar->num_started_vdevs++;
 	ath12k_dbg(ab, ATH12K_DBG_MAC,  "vdev %pM started, vdev_id %d\n",
 		   ahvif->vif->addr, arvif->vdev_id);
@@ -9257,8 +9607,10 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,
 		arvif = wiphy_dereference(ath12k_ar_to_hw(ar)->wiphy,
 					  ahvif->link[link_id]);
 
-		if (vif->type == NL80211_IFTYPE_MONITOR)
+		if (vif->type == NL80211_IFTYPE_MONITOR) {
 			monitor_vif = true;
+			continue;
+		}
 
 		ath12k_dbg(ab, ATH12K_DBG_MAC,
 			   "mac chanctx switch vdev_id %i freq %u->%u width %d->%d\n",
@@ -9308,7 +9660,7 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,
 		params.aid = ahvif->aid;
 		params.bssid = arvif->bssid;
 
-		tx_arvif = ath12k_mac_get_tx_arvif(arvif);
+		tx_arvif = ath12k_mac_get_tx_arvif(arvif, link_conf);
 		if (tx_arvif) {
 			params.tx_bssid = tx_arvif->bssid;
 			params.nontx_profile_idx = link_conf->bssid_index;
@@ -9408,16 +9760,26 @@ static int ath12k_start_vdev_delay(struct ath12k *ar,
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_vif *ahvif = arvif->ahvif;
 	struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif);
+	struct ieee80211_chanctx_conf *chanctx;
+	struct ieee80211_bss_conf *link_conf;
 	int ret;
 
 	if (WARN_ON(arvif->is_started))
 		return -EBUSY;
 
-	ret = ath12k_mac_vdev_start(arvif, &arvif->chanctx);
+	link_conf = ath12k_mac_get_link_bss_conf(arvif);
+	if (!link_conf) {
+		ath12k_warn(ab, "failed to get link conf for vdev %u\n", arvif->vdev_id);
+		return -EINVAL;
+	}
+
+	chanctx	= wiphy_dereference(ath12k_ar_to_hw(arvif->ar)->wiphy,
+				    link_conf->chanctx_conf);
+	ret = ath12k_mac_vdev_start(arvif, chanctx);
 	if (ret) {
 		ath12k_warn(ab, "failed to start vdev %i addr %pM on freq %d: %d\n",
 			    arvif->vdev_id, vif->addr,
-			    arvif->chanctx.def.chan->center_freq, ret);
+			    chanctx->def.chan->center_freq, ret);
 		return ret;
 	}
 
@@ -9435,6 +9797,391 @@ static int ath12k_start_vdev_delay(struct ath12k *ar,
 	return 0;
 }
 
+static u8 ath12k_mac_get_num_pwr_levels(struct cfg80211_chan_def *chan_def)
+{
+	if (chan_def->chan->flags & IEEE80211_CHAN_PSD) {
+		switch (chan_def->width) {
+		case NL80211_CHAN_WIDTH_20:
+			return 1;
+		case NL80211_CHAN_WIDTH_40:
+			return 2;
+		case NL80211_CHAN_WIDTH_80:
+			return 4;
+		case NL80211_CHAN_WIDTH_160:
+			return 8;
+		case NL80211_CHAN_WIDTH_320:
+			return 16;
+		default:
+			return 1;
+		}
+	} else {
+		switch (chan_def->width) {
+		case NL80211_CHAN_WIDTH_20:
+			return 1;
+		case NL80211_CHAN_WIDTH_40:
+			return 2;
+		case NL80211_CHAN_WIDTH_80:
+			return 3;
+		case NL80211_CHAN_WIDTH_160:
+			return 4;
+		case NL80211_CHAN_WIDTH_320:
+			return 5;
+		default:
+			return 1;
+		}
+	}
+}
+
+static u16 ath12k_mac_get_6ghz_start_frequency(struct cfg80211_chan_def *chan_def)
+{
+	u16 diff_seq;
+
+	/* It is to get the lowest channel number's center frequency of the chan.
+	 * For example,
+	 * bandwidth=40 MHz, center frequency is 5965, lowest channel is 1
+	 * with center frequency 5955, its diff is 5965 - 5955 = 10.
+	 * bandwidth=80 MHz, center frequency is 5985, lowest channel is 1
+	 * with center frequency 5955, its diff is 5985 - 5955 = 30.
+	 * bandwidth=160 MHz, center frequency is 6025, lowest channel is 1
+	 * with center frequency 5955, its diff is 6025 - 5955 = 70.
+	 * bandwidth=320 MHz, center frequency is 6105, lowest channel is 1
+	 * with center frequency 5955, its diff is 6105 - 5955 = 70.
+	 */
+	switch (chan_def->width) {
+	case NL80211_CHAN_WIDTH_320:
+		diff_seq = 150;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		diff_seq = 70;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		diff_seq = 30;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		diff_seq = 10;
+		break;
+	default:
+		diff_seq = 0;
+	}
+
+	return chan_def->center_freq1 - diff_seq;
+}
+
+static u16 ath12k_mac_get_seg_freq(struct cfg80211_chan_def *chan_def,
+				   u16 start_seq, u8 seq)
+{
+	u16 seg_seq;
+
+	/* It is to get the center frequency of the specific bandwidth.
+	 * start_seq means the lowest channel number's center frequency.
+	 * seq 0/1/2/3 means 20 MHz/40 MHz/80 MHz/160 MHz.
+	 * For example,
+	 * lowest channel is 1, its center frequency 5955,
+	 * center frequency is 5955 when bandwidth=20 MHz, its diff is 5955 - 5955 = 0.
+	 * lowest channel is 1, its center frequency 5955,
+	 * center frequency is 5965 when bandwidth=40 MHz, its diff is 5965 - 5955 = 10.
+	 * lowest channel is 1, its center frequency 5955,
+	 * center frequency is 5985 when bandwidth=80 MHz, its diff is 5985 - 5955 = 30.
+	 * lowest channel is 1, its center frequency 5955,
+	 * center frequency is 6025 when bandwidth=160 MHz, its diff is 6025 - 5955 = 70.
+	 */
+	seg_seq = 10 * (BIT(seq) - 1);
+	return seg_seq + start_seq;
+}
+
+static void ath12k_mac_get_psd_channel(struct ath12k *ar,
+				       u16 step_freq,
+				       u16 *start_freq,
+				       u16 *center_freq,
+				       u8 i,
+				       struct ieee80211_channel **temp_chan,
+				       s8 *tx_power)
+{
+	/* It is to get the center frequency for each 20 MHz.
+	 * For example, if the chan is 160 MHz and center frequency is 6025,
+	 * then it include 8 channels, they are 1/5/9/13/17/21/25/29,
+	 * channel number 1's center frequency is 5955, it is parameter start_freq.
+	 * parameter i is the step of the 8 channels. i is 0~7 for the 8 channels.
+	 * the channel 1/5/9/13/17/21/25/29 maps i=0/1/2/3/4/5/6/7,
+	 * and maps its center frequency is 5955/5975/5995/6015/6035/6055/6075/6095,
+	 * the gap is 20 for each channel, parameter step_freq means the gap.
+	 * after get the center frequency of each channel, it is easy to find the
+	 * struct ieee80211_channel of it and get the max_reg_power.
+	 */
+	*center_freq = *start_freq + i * step_freq;
+	*temp_chan = ieee80211_get_channel(ar->ah->hw->wiphy, *center_freq);
+	*tx_power = (*temp_chan)->max_reg_power;
+}
+
+static void ath12k_mac_get_eirp_power(struct ath12k *ar,
+				      u16 *start_freq,
+				      u16 *center_freq,
+				      u8 i,
+				      struct ieee80211_channel **temp_chan,
+				      struct cfg80211_chan_def *def,
+				      s8 *tx_power)
+{
+	/* It is to get the center frequency for 20 MHz/40 MHz/80 MHz/
+	 * 160 MHz bandwidth, and then plus 10 to the center frequency,
+	 * it is the center frequency of a channel number.
+	 * For example, when configured channel number is 1.
+	 * center frequency is 5965 when bandwidth=40 MHz, after plus 10, it is 5975,
+	 * then it is channel number 5.
+	 * center frequency is 5985 when bandwidth=80 MHz, after plus 10, it is 5995,
+	 * then it is channel number 9.
+	 * center frequency is 6025 when bandwidth=160 MHz, after plus 10, it is 6035,
+	 * then it is channel number 17.
+	 * after get the center frequency of each channel, it is easy to find the
+	 * struct ieee80211_channel of it and get the max_reg_power.
+	 */
+	*center_freq = ath12k_mac_get_seg_freq(def, *start_freq, i);
+
+	/* For the 20 MHz, its center frequency is same with same channel */
+	if (i != 0)
+		*center_freq += 10;
+
+	*temp_chan = ieee80211_get_channel(ar->ah->hw->wiphy, *center_freq);
+	*tx_power = (*temp_chan)->max_reg_power;
+}
+
+void ath12k_mac_fill_reg_tpc_info(struct ath12k *ar,
+				  struct ath12k_link_vif *arvif,
+				  struct ieee80211_chanctx_conf *ctx)
+{
+	struct ath12k_base *ab = ar->ab;
+	struct ath12k_reg_tpc_power_info *reg_tpc_info = &arvif->reg_tpc_info;
+	struct ieee80211_bss_conf *bss_conf = ath12k_mac_get_link_bss_conf(arvif);
+	struct ieee80211_channel *chan, *temp_chan;
+	u8 pwr_lvl_idx, num_pwr_levels, pwr_reduction;
+	bool is_psd_power = false, is_tpe_present = false;
+	s8 max_tx_power[ATH12K_NUM_PWR_LEVELS],
+		psd_power, tx_power, eirp_power;
+	u16 start_freq, center_freq;
+
+	chan = ctx->def.chan;
+	start_freq = ath12k_mac_get_6ghz_start_frequency(&ctx->def);
+	pwr_reduction = bss_conf->pwr_reduction;
+
+	if (arvif->reg_tpc_info.num_pwr_levels) {
+		is_tpe_present = true;
+		num_pwr_levels = arvif->reg_tpc_info.num_pwr_levels;
+	} else {
+		num_pwr_levels = ath12k_mac_get_num_pwr_levels(&ctx->def);
+	}
+
+	for (pwr_lvl_idx = 0; pwr_lvl_idx < num_pwr_levels; pwr_lvl_idx++) {
+		/* STA received TPE IE*/
+		if (is_tpe_present) {
+			/* local power is PSD power*/
+			if (chan->flags & IEEE80211_CHAN_PSD) {
+				/* Connecting AP is psd power */
+				if (reg_tpc_info->is_psd_power) {
+					is_psd_power = true;
+					ath12k_mac_get_psd_channel(ar, 20,
+								   &start_freq,
+								   &center_freq,
+								   pwr_lvl_idx,
+								   &temp_chan,
+								   &tx_power);
+					psd_power = temp_chan->psd;
+					eirp_power = tx_power;
+					max_tx_power[pwr_lvl_idx] =
+						min_t(s8,
+						      psd_power,
+						      reg_tpc_info->tpe[pwr_lvl_idx]);
+				/* Connecting AP is not psd power */
+				} else {
+					ath12k_mac_get_eirp_power(ar,
+								  &start_freq,
+								  &center_freq,
+								  pwr_lvl_idx,
+								  &temp_chan,
+								  &ctx->def,
+								  &tx_power);
+					psd_power = temp_chan->psd;
+					/* convert psd power to EIRP power based
+					 * on channel width
+					 */
+					tx_power =
+						min_t(s8, tx_power,
+						      psd_power + 13 + pwr_lvl_idx * 3);
+					max_tx_power[pwr_lvl_idx] =
+						min_t(s8,
+						      tx_power,
+						      reg_tpc_info->tpe[pwr_lvl_idx]);
+				}
+			/* local power is not PSD power */
+			} else {
+				/* Connecting AP is psd power */
+				if (reg_tpc_info->is_psd_power) {
+					is_psd_power = true;
+					ath12k_mac_get_psd_channel(ar, 20,
+								   &start_freq,
+								   &center_freq,
+								   pwr_lvl_idx,
+								   &temp_chan,
+								   &tx_power);
+					eirp_power = tx_power;
+					max_tx_power[pwr_lvl_idx] =
+						reg_tpc_info->tpe[pwr_lvl_idx];
+				/* Connecting AP is not psd power */
+				} else {
+					ath12k_mac_get_eirp_power(ar,
+								  &start_freq,
+								  &center_freq,
+								  pwr_lvl_idx,
+								  &temp_chan,
+								  &ctx->def,
+								  &tx_power);
+					max_tx_power[pwr_lvl_idx] =
+						min_t(s8,
+						      tx_power,
+						      reg_tpc_info->tpe[pwr_lvl_idx]);
+				}
+			}
+		/* STA not received TPE IE */
+		} else {
+			/* local power is PSD power*/
+			if (chan->flags & IEEE80211_CHAN_PSD) {
+				is_psd_power = true;
+				ath12k_mac_get_psd_channel(ar, 20,
+							   &start_freq,
+							   &center_freq,
+							   pwr_lvl_idx,
+							   &temp_chan,
+							   &tx_power);
+				psd_power = temp_chan->psd;
+				eirp_power = tx_power;
+				max_tx_power[pwr_lvl_idx] = psd_power;
+			} else {
+				ath12k_mac_get_eirp_power(ar,
+							  &start_freq,
+							  &center_freq,
+							  pwr_lvl_idx,
+							  &temp_chan,
+							  &ctx->def,
+							  &tx_power);
+				max_tx_power[pwr_lvl_idx] = tx_power;
+			}
+		}
+
+		if (is_psd_power) {
+			/* If AP local power constraint is present */
+			if (pwr_reduction)
+				eirp_power = eirp_power - pwr_reduction;
+
+			/* If firmware updated max tx power is non zero, then take
+			 * the min of firmware updated ap tx power
+			 * and max power derived from above mentioned parameters.
+			 */
+			ath12k_dbg(ab, ATH12K_DBG_MAC,
+				   "eirp power : %d firmware report power : %d\n",
+				   eirp_power, ar->max_allowed_tx_power);
+			/* Firmware reports lower max_allowed_tx_power during vdev
+			 * start response. In case of 6 GHz, firmware is not aware
+			 * of EIRP power unless driver sets EIRP power through WMI
+			 * TPC command. So radio which does not support idle power
+			 * save can set maximum calculated EIRP power directly to
+			 * firmware through TPC command without min comparison with
+			 * vdev start response's max_allowed_tx_power.
+			 */
+			if (ar->max_allowed_tx_power && ab->hw_params->idle_ps)
+				eirp_power = min_t(s8,
+						   eirp_power,
+						   ar->max_allowed_tx_power);
+		} else {
+			/* If AP local power constraint is present */
+			if (pwr_reduction)
+				max_tx_power[pwr_lvl_idx] =
+					max_tx_power[pwr_lvl_idx] - pwr_reduction;
+			/* If firmware updated max tx power is non zero, then take
+			 * the min of firmware updated ap tx power
+			 * and max power derived from above mentioned parameters.
+			 */
+			if (ar->max_allowed_tx_power && ab->hw_params->idle_ps)
+				max_tx_power[pwr_lvl_idx] =
+					min_t(s8,
+					      max_tx_power[pwr_lvl_idx],
+					      ar->max_allowed_tx_power);
+		}
+		reg_tpc_info->chan_power_info[pwr_lvl_idx].chan_cfreq = center_freq;
+		reg_tpc_info->chan_power_info[pwr_lvl_idx].tx_power =
+			max_tx_power[pwr_lvl_idx];
+	}
+
+	reg_tpc_info->num_pwr_levels = num_pwr_levels;
+	reg_tpc_info->is_psd_power = is_psd_power;
+	reg_tpc_info->eirp_power = eirp_power;
+	reg_tpc_info->ap_power_type =
+		ath12k_reg_ap_pwr_convert(bss_conf->power_type);
+}
+
+static void ath12k_mac_parse_tx_pwr_env(struct ath12k *ar,
+					struct ath12k_link_vif *arvif)
+{
+	struct ieee80211_bss_conf *bss_conf = ath12k_mac_get_link_bss_conf(arvif);
+	struct ath12k_reg_tpc_power_info *tpc_info = &arvif->reg_tpc_info;
+	struct ieee80211_parsed_tpe_eirp *local_non_psd, *reg_non_psd;
+	struct ieee80211_parsed_tpe_psd *local_psd, *reg_psd;
+	struct ieee80211_parsed_tpe *tpe = &bss_conf->tpe;
+	enum wmi_reg_6g_client_type client_type;
+	struct ath12k_reg_info *reg_info;
+	struct ath12k_base *ab = ar->ab;
+	bool psd_valid, non_psd_valid;
+	int i;
+
+	reg_info = ab->reg_info[ar->pdev_idx];
+	client_type = reg_info->client_type;
+
+	local_psd = &tpe->psd_local[client_type];
+	reg_psd = &tpe->psd_reg_client[client_type];
+	local_non_psd = &tpe->max_local[client_type];
+	reg_non_psd = &tpe->max_reg_client[client_type];
+
+	psd_valid = local_psd->valid | reg_psd->valid;
+	non_psd_valid = local_non_psd->valid | reg_non_psd->valid;
+
+	if (!psd_valid && !non_psd_valid) {
+		ath12k_warn(ab,
+			    "no transmit power envelope match client power type %d\n",
+			    client_type);
+		return;
+	};
+
+	if (psd_valid) {
+		tpc_info->is_psd_power = true;
+
+		tpc_info->num_pwr_levels = max(local_psd->count,
+					       reg_psd->count);
+		if (tpc_info->num_pwr_levels > ATH12K_NUM_PWR_LEVELS)
+			tpc_info->num_pwr_levels = ATH12K_NUM_PWR_LEVELS;
+
+		for (i = 0; i < tpc_info->num_pwr_levels; i++) {
+			tpc_info->tpe[i] = min(local_psd->power[i],
+					       reg_psd->power[i]) / 2;
+			ath12k_dbg(ab, ATH12K_DBG_MAC,
+				   "TPE PSD power[%d] : %d\n",
+				   i, tpc_info->tpe[i]);
+		}
+	} else {
+		tpc_info->is_psd_power = false;
+		tpc_info->eirp_power = 0;
+
+		tpc_info->num_pwr_levels = max(local_non_psd->count,
+					       reg_non_psd->count);
+		if (tpc_info->num_pwr_levels > ATH12K_NUM_PWR_LEVELS)
+			tpc_info->num_pwr_levels = ATH12K_NUM_PWR_LEVELS;
+
+		for (i = 0; i < tpc_info->num_pwr_levels; i++) {
+			tpc_info->tpe[i] = min(local_non_psd->power[i],
+					       reg_non_psd->power[i]) / 2;
+			ath12k_dbg(ab, ATH12K_DBG_MAC,
+				   "non PSD power[%d] : %d\n",
+				   i, tpc_info->tpe[i]);
+		}
+	}
+}
+
 static int
 ath12k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 				 struct ieee80211_vif *vif,
@@ -9462,8 +10209,8 @@ ath12k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 
 	ar = ath12k_mac_assign_vif_to_vdev(hw, arvif, ctx);
 	if (!ar) {
-		ath12k_warn(arvif->ar->ab, "failed to assign chanctx for vif %pM link id %u link vif is already started",
-			    vif->addr, link_id);
+		ath12k_hw_warn(ah, "failed to assign chanctx for vif %pM link id %u link vif is already started",
+			       vif->addr, link_id);
 		return -EINVAL;
 	}
 
@@ -9473,6 +10220,11 @@ ath12k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 		   "mac chanctx assign ptr %p vdev_id %i\n",
 		   ctx, arvif->vdev_id);
 
+	if (ath12k_wmi_supports_6ghz_cc_ext(ar) &&
+	    ctx->def.chan->band == NL80211_BAND_6GHZ &&
+	    ahvif->vdev_type == WMI_VDEV_TYPE_STA)
+		ath12k_mac_parse_tx_pwr_env(ar, arvif);
+
 	arvif->punct_bitmap = ctx->def.punctured;
 
 	/* for some targets bss peer must be created before vdev_start */
@@ -9480,7 +10232,6 @@ ath12k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 	    ahvif->vdev_type != WMI_VDEV_TYPE_AP &&
 	    ahvif->vdev_type != WMI_VDEV_TYPE_MONITOR &&
 	    !ath12k_peer_exist_by_vdev_id(ab, arvif->vdev_id)) {
-		memcpy(&arvif->chanctx, ctx, sizeof(*ctx));
 		ret = 0;
 		goto out;
 	}
@@ -9492,8 +10243,10 @@ ath12k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 
 	if (ahvif->vdev_type == WMI_VDEV_TYPE_MONITOR) {
 		ret = ath12k_mac_monitor_start(ar);
-		if (ret)
+		if (ret) {
+			ath12k_mac_monitor_vdev_delete(ar);
 			goto out;
+		}
 
 		arvif->is_started = true;
 		goto out;
@@ -9507,9 +10260,6 @@ ath12k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	if (ahvif->vdev_type != WMI_VDEV_TYPE_MONITOR && ar->monitor_vdev_created)
-		ath12k_mac_monitor_start(ar);
-
 	arvif->is_started = true;
 
 	/* TODO: Setup ps and cts/rts protection */
@@ -9572,9 +10322,18 @@ ath12k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 	}
 	arvif->is_started = false;
 
-	if (ahvif->vdev_type != WMI_VDEV_TYPE_MONITOR &&
-	    ar->num_started_vdevs == 1 && ar->monitor_vdev_created)
-		ath12k_mac_monitor_stop(ar);
+	if (test_bit(WMI_TLV_SERVICE_11D_OFFLOAD, ab->wmi_ab.svc_map) &&
+	    ahvif->vdev_type == WMI_VDEV_TYPE_STA &&
+	    ahvif->vdev_subtype == WMI_VDEV_SUBTYPE_NONE &&
+	    ar->state_11d != ATH12K_11D_PREPARING) {
+		reinit_completion(&ar->completed_11d_scan);
+		ar->state_11d = ATH12K_11D_PREPARING;
+	}
+
+	if (ar->scan.arvif == arvif && ar->scan.state == ATH12K_SCAN_RUNNING) {
+		ath12k_scan_abort(ar);
+		ar->scan.arvif = NULL;
+	}
 }
 
 static int
@@ -10136,6 +10895,14 @@ ath12k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
 		ath12k_warn(ar->ab, "pdev %d successfully recovered\n",
 			    ar->pdev->pdev_id);
 
+		if (ar->ab->hw_params->current_cc_support &&
+		    ar->alpha2[0] != 0 && ar->alpha2[1] != 0) {
+			struct wmi_set_current_country_arg arg = {};
+
+			memcpy(&arg.alpha2, ar->alpha2, 2);
+			ath12k_wmi_send_set_current_country_cmd(ar, &arg);
+		}
+
 		if (ab->is_reset) {
 			recovery_count = atomic_inc_return(&ab->recovery_count);
 
@@ -10267,46 +11034,13 @@ static int ath12k_mac_op_get_survey(struct ieee80211_hw *hw, int idx,
 	return 0;
 }
 
-static int ath12k_mac_get_fw_stats(struct ath12k *ar, u32 pdev_id,
-				   u32 vdev_id, u32 stats_id)
-{
-	struct ath12k_base *ab = ar->ab;
-	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
-	unsigned long time_left;
-	int ret;
-
-	guard(mutex)(&ah->hw_mutex);
-
-	if (ah->state != ATH12K_HW_STATE_ON)
-		return -ENETDOWN;
-
-	reinit_completion(&ar->fw_stats_complete);
-
-	ret = ath12k_wmi_send_stats_request_cmd(ar, stats_id, vdev_id, pdev_id);
-
-	if (ret) {
-		ath12k_warn(ab, "failed to request fw stats: %d\n", ret);
-		return ret;
-	}
-
-	ath12k_dbg(ab, ATH12K_DBG_WMI,
-		   "get fw stat pdev id %d vdev id %d stats id 0x%x\n",
-		   pdev_id, vdev_id, stats_id);
-
-	time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
-
-	if (!time_left)
-		ath12k_warn(ab, "time out while waiting for get fw stats\n");
-
-	return ret;
-}
-
 static void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 					 struct ieee80211_vif *vif,
 					 struct ieee80211_sta *sta,
 					 struct station_info *sinfo)
 {
 	struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta);
+	struct ath12k_fw_stats_req_params params = {};
 	struct ath12k_link_sta *arsta;
 	struct ath12k *ar;
 	s8 signal;
@@ -10348,10 +11082,13 @@ static void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 	/* TODO: Use real NF instead of default one. */
 	signal = arsta->rssi_comb;
 
+	params.pdev_id = ar->pdev->pdev_id;
+	params.vdev_id = 0;
+	params.stats_id = WMI_REQUEST_VDEV_STAT;
+
 	if (!signal &&
 	    ahsta->ahvif->vdev_type == WMI_VDEV_TYPE_STA &&
-	    !(ath12k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0,
-				      WMI_REQUEST_VDEV_STAT)))
+	    !(ath12k_mac_get_fw_stats(ar, &params)))
 		signal = arsta->rssi_beacon;
 
 	if (signal) {
@@ -10411,7 +11148,7 @@ static int ath12k_mac_op_remain_on_channel(struct ieee80211_hw *hw,
 		return -EINVAL;
 
 	/* check if any of the links of ML VIF is already started on
-	 * radio(ar) correpsondig to given scan frequency and use it,
+	 * radio(ar) corresponding to given scan frequency and use it,
 	 * if not use deflink(link 0) for scan purpose.
 	 */
 
@@ -10595,6 +11332,7 @@ static const struct ieee80211_ops ath12k_ops = {
 	.assign_vif_chanctx		= ath12k_mac_op_assign_vif_chanctx,
 	.unassign_vif_chanctx		= ath12k_mac_op_unassign_vif_chanctx,
 	.switch_vif_chanctx		= ath12k_mac_op_switch_vif_chanctx,
+	.get_txpower			= ath12k_mac_op_get_txpower,
 	.set_rts_threshold		= ath12k_mac_op_set_rts_threshold,
 	.set_frag_threshold		= ath12k_mac_op_set_frag_threshold,
 	.set_bitrate_mask		= ath12k_mac_op_set_bitrate_mask,
@@ -10610,12 +11348,37 @@ static const struct ieee80211_ops ath12k_ops = {
 	.resume				= ath12k_wow_op_resume,
 	.set_wakeup			= ath12k_wow_op_set_wakeup,
 #endif
+#ifdef CONFIG_ATH12K_DEBUGFS
+	.vif_add_debugfs                = ath12k_debugfs_op_vif_add,
+#endif
 	CFG80211_TESTMODE_CMD(ath12k_tm_cmd)
 #ifdef CONFIG_ATH12K_DEBUGFS
 	.link_sta_add_debugfs           = ath12k_debugfs_link_sta_op_add,
 #endif
 };
 
+void ath12k_mac_update_freq_range(struct ath12k *ar,
+				  u32 freq_low, u32 freq_high)
+{
+	if (!(freq_low && freq_high))
+		return;
+
+	if (ar->freq_range.start_freq || ar->freq_range.end_freq) {
+		ar->freq_range.start_freq = min(ar->freq_range.start_freq,
+						MHZ_TO_KHZ(freq_low));
+		ar->freq_range.end_freq = max(ar->freq_range.end_freq,
+					      MHZ_TO_KHZ(freq_high));
+	} else {
+		ar->freq_range.start_freq = MHZ_TO_KHZ(freq_low);
+		ar->freq_range.end_freq = MHZ_TO_KHZ(freq_high);
+	}
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_MAC,
+		   "mac pdev %u freq limit updated. New range %u->%u MHz\n",
+		   ar->pdev->pdev_id, KHZ_TO_MHZ(ar->freq_range.start_freq),
+		   KHZ_TO_MHZ(ar->freq_range.end_freq));
+}
+
 static void ath12k_mac_update_ch_list(struct ath12k *ar,
 				      struct ieee80211_supported_band *band,
 				      u32 freq_low, u32 freq_high)
@@ -10630,9 +11393,6 @@ static void ath12k_mac_update_ch_list(struct ath12k *ar,
 		    band->channels[i].center_freq > freq_high)
 			band->channels[i].flags |= IEEE80211_CHAN_DISABLED;
 	}
-
-	ar->freq_range.start_freq = MHZ_TO_KHZ(freq_low);
-	ar->freq_range.end_freq = MHZ_TO_KHZ(freq_high);
 }
 
 static u32 ath12k_get_phy_id(struct ath12k *ar, u32 band)
@@ -10640,10 +11400,10 @@ static u32 ath12k_get_phy_id(struct ath12k *ar, u32 band)
 	struct ath12k_pdev *pdev = ar->pdev;
 	struct ath12k_pdev_cap *pdev_cap = &pdev->cap;
 
-	if (band == WMI_HOST_WLAN_2G_CAP)
+	if (band == WMI_HOST_WLAN_2GHZ_CAP)
 		return pdev_cap->band[NL80211_BAND_2GHZ].phy_id;
 
-	if (band == WMI_HOST_WLAN_5G_CAP)
+	if (band == WMI_HOST_WLAN_5GHZ_CAP)
 		return pdev_cap->band[NL80211_BAND_5GHZ].phy_id;
 
 	ath12k_warn(ar->ab, "unsupported phy cap:%d\n", band);
@@ -10657,18 +11417,19 @@ static int ath12k_mac_setup_channels_rates(struct ath12k *ar,
 {
 	struct ieee80211_supported_band *band;
 	struct ath12k_wmi_hal_reg_capabilities_ext_arg *reg_cap;
+	struct ath12k_base *ab = ar->ab;
+	u32 phy_id, freq_low, freq_high;
 	struct ath12k_hw *ah = ar->ah;
 	void *channels;
-	u32 phy_id;
 
 	BUILD_BUG_ON((ARRAY_SIZE(ath12k_2ghz_channels) +
 		      ARRAY_SIZE(ath12k_5ghz_channels) +
 		      ARRAY_SIZE(ath12k_6ghz_channels)) !=
 		     ATH12K_NUM_CHANS);
 
-	reg_cap = &ar->ab->hal_reg_cap[ar->pdev_idx];
+	reg_cap = &ab->hal_reg_cap[ar->pdev_idx];
 
-	if (supported_bands & WMI_HOST_WLAN_2G_CAP) {
+	if (supported_bands & WMI_HOST_WLAN_2GHZ_CAP) {
 		channels = kmemdup(ath12k_2ghz_channels,
 				   sizeof(ath12k_2ghz_channels),
 				   GFP_KERNEL);
@@ -10683,17 +11444,25 @@ static int ath12k_mac_setup_channels_rates(struct ath12k *ar,
 		band->bitrates = ath12k_g_rates;
 		bands[NL80211_BAND_2GHZ] = band;
 
-		if (ar->ab->hw_params->single_pdev_only) {
-			phy_id = ath12k_get_phy_id(ar, WMI_HOST_WLAN_2G_CAP);
-			reg_cap = &ar->ab->hal_reg_cap[phy_id];
+		if (ab->hw_params->single_pdev_only) {
+			phy_id = ath12k_get_phy_id(ar, WMI_HOST_WLAN_2GHZ_CAP);
+			reg_cap = &ab->hal_reg_cap[phy_id];
 		}
+
+		freq_low = max(reg_cap->low_2ghz_chan,
+			       ab->reg_freq_2ghz.start_freq);
+		freq_high = min(reg_cap->high_2ghz_chan,
+				ab->reg_freq_2ghz.end_freq);
+
 		ath12k_mac_update_ch_list(ar, band,
 					  reg_cap->low_2ghz_chan,
 					  reg_cap->high_2ghz_chan);
+
+		ath12k_mac_update_freq_range(ar, freq_low, freq_high);
 	}
 
-	if (supported_bands & WMI_HOST_WLAN_5G_CAP) {
-		if (reg_cap->high_5ghz_chan >= ATH12K_MIN_6G_FREQ) {
+	if (supported_bands & WMI_HOST_WLAN_5GHZ_CAP) {
+		if (reg_cap->high_5ghz_chan >= ATH12K_MIN_6GHZ_FREQ) {
 			channels = kmemdup(ath12k_6ghz_channels,
 					   sizeof(ath12k_6ghz_channels), GFP_KERNEL);
 			if (!channels) {
@@ -10709,13 +11478,21 @@ static int ath12k_mac_setup_channels_rates(struct ath12k *ar,
 			band->n_bitrates = ath12k_a_rates_size;
 			band->bitrates = ath12k_a_rates;
 			bands[NL80211_BAND_6GHZ] = band;
+
+			freq_low = max(reg_cap->low_5ghz_chan,
+				       ab->reg_freq_6ghz.start_freq);
+			freq_high = min(reg_cap->high_5ghz_chan,
+					ab->reg_freq_6ghz.end_freq);
+
 			ath12k_mac_update_ch_list(ar, band,
 						  reg_cap->low_5ghz_chan,
 						  reg_cap->high_5ghz_chan);
+
+			ath12k_mac_update_freq_range(ar, freq_low, freq_high);
 			ah->use_6ghz_regd = true;
 		}
 
-		if (reg_cap->low_5ghz_chan < ATH12K_MIN_6G_FREQ) {
+		if (reg_cap->low_5ghz_chan < ATH12K_MIN_6GHZ_FREQ) {
 			channels = kmemdup(ath12k_5ghz_channels,
 					   sizeof(ath12k_5ghz_channels),
 					   GFP_KERNEL);
@@ -10733,14 +11510,21 @@ static int ath12k_mac_setup_channels_rates(struct ath12k *ar,
 			band->bitrates = ath12k_a_rates;
 			bands[NL80211_BAND_5GHZ] = band;
 
-			if (ar->ab->hw_params->single_pdev_only) {
-				phy_id = ath12k_get_phy_id(ar, WMI_HOST_WLAN_5G_CAP);
-				reg_cap = &ar->ab->hal_reg_cap[phy_id];
+			if (ab->hw_params->single_pdev_only) {
+				phy_id = ath12k_get_phy_id(ar, WMI_HOST_WLAN_5GHZ_CAP);
+				reg_cap = &ab->hal_reg_cap[phy_id];
 			}
 
+			freq_low = max(reg_cap->low_5ghz_chan,
+				       ab->reg_freq_5ghz.start_freq);
+			freq_high = min(reg_cap->high_5ghz_chan,
+					ab->reg_freq_5ghz.end_freq);
+
 			ath12k_mac_update_ch_list(ar, band,
 						  reg_cap->low_5ghz_chan,
 						  reg_cap->high_5ghz_chan);
+
+			ath12k_mac_update_freq_range(ar, freq_low, freq_high);
 		}
 	}
 
@@ -10840,13 +11624,18 @@ ath12k_mac_setup_radio_iface_comb(struct ath12k *ar,
 	comb[0].limits = limits;
 	comb[0].n_limits = n_limits;
 	comb[0].max_interfaces = max_interfaces;
-	comb[0].num_different_channels = 1;
 	comb[0].beacon_int_infra_match = true;
 	comb[0].beacon_int_min_gcd = 100;
-	comb[0].radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) |
-					BIT(NL80211_CHAN_WIDTH_20) |
-					BIT(NL80211_CHAN_WIDTH_40) |
-					BIT(NL80211_CHAN_WIDTH_80);
+
+	if (ar->ab->hw_params->single_pdev_only) {
+		comb[0].num_different_channels = 2;
+	} else {
+		comb[0].num_different_channels = 1;
+		comb[0].radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) |
+						BIT(NL80211_CHAN_WIDTH_20) |
+						BIT(NL80211_CHAN_WIDTH_40) |
+						BIT(NL80211_CHAN_WIDTH_80);
+	}
 
 	return 0;
 }
@@ -11071,6 +11860,7 @@ static void ath12k_mac_hw_unregister(struct ath12k_hw *ah)
 	for_each_ar(ah, ar, i) {
 		cancel_work_sync(&ar->regd_update_work);
 		ath12k_debugfs_unregister(ar);
+		ath12k_fw_stats_reset(ar);
 	}
 
 	ieee80211_unregister_hw(hw);
@@ -11219,6 +12009,7 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
 	ieee80211_hw_set(hw, QUEUE_CONTROL);
 	ieee80211_hw_set(hw, SUPPORTS_TX_FRAG);
 	ieee80211_hw_set(hw, REPORTS_LOW_ACK);
+	ieee80211_hw_set(hw, NO_VIRTUAL_MONITOR);
 
 	if ((ht_cap & WMI_HT_CAP_ENABLED) || is_6ghz) {
 		ieee80211_hw_set(hw, AMPDU_AGGREGATION);
@@ -11347,11 +12138,22 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
 			goto err_unregister_hw;
 		}
 
+		if (ar->ab->hw_params->current_cc_support && ab->new_alpha2[0]) {
+			struct wmi_set_current_country_arg current_cc = {};
+
+			memcpy(&current_cc.alpha2, ab->new_alpha2, 2);
+			memcpy(&ar->alpha2, ab->new_alpha2, 2);
+			ret = ath12k_wmi_send_set_current_country_cmd(ar, &current_cc);
+			if (ret)
+				ath12k_warn(ar->ab,
+					    "failed set cc code for mac register: %d\n",
+					    ret);
+		}
+
+		ath12k_fw_stats_init(ar);
 		ath12k_debugfs_register(ar);
 	}
 
-	init_completion(&ar->fw_stats_complete);
-
 	return 0;
 
 err_unregister_hw:
@@ -11396,6 +12198,7 @@ static void ath12k_mac_setup(struct ath12k *ar)
 	ar->num_tx_chains = hweight32(pdev->cap.tx_chain_mask);
 	ar->num_rx_chains = hweight32(pdev->cap.rx_chain_mask);
 	ar->scan.arvif = NULL;
+	ar->vdev_id_11d_scan = ATH12K_11D_INVALID_VDEV_ID;
 
 	spin_lock_init(&ar->data_lock);
 	INIT_LIST_HEAD(&ar->arvifs);
@@ -11411,6 +12214,7 @@ static void ath12k_mac_setup(struct ath12k *ar)
 	init_completion(&ar->scan.completed);
 	init_completion(&ar->scan.on_channel);
 	init_completion(&ar->mlo_setup_done);
+	init_completion(&ar->completed_11d_scan);
 
 	INIT_DELAYED_WORK(&ar->scan.timeout, ath12k_scan_timeout_work);
 	wiphy_work_init(&ar->scan.vdev_clean_wk, ath12k_scan_vdev_clean_work);
@@ -11418,6 +12222,10 @@ static void ath12k_mac_setup(struct ath12k *ar)
 
 	wiphy_work_init(&ar->wmi_mgmt_tx_work, ath12k_mgmt_over_wmi_tx_work);
 	skb_queue_head_init(&ar->wmi_mgmt_tx_queue);
+
+	ar->monitor_vdev_id = -1;
+	ar->monitor_vdev_created = false;
+	ar->monitor_started = false;
 }
 
 static int __ath12k_mac_mlo_setup(struct ath12k *ar)
@@ -11572,7 +12380,6 @@ void ath12k_mac_mlo_teardown(struct ath12k_hw_group *ag)
 
 int ath12k_mac_register(struct ath12k_hw_group *ag)
 {
-	struct ath12k_base *ab = ag->ab[0];
 	struct ath12k_hw *ah;
 	int i;
 	int ret;
@@ -11585,8 +12392,6 @@ int ath12k_mac_register(struct ath12k_hw_group *ag)
 			goto err;
 	}
 
-	set_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags);
-
 	return 0;
 
 err:
@@ -11603,12 +12408,9 @@ err:
 
 void ath12k_mac_unregister(struct ath12k_hw_group *ag)
 {
-	struct ath12k_base *ab = ag->ab[0];
 	struct ath12k_hw *ah;
 	int i;
 
-	clear_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags);
-
 	for (i = ag->num_hw - 1; i >= 0; i--) {
 		ah = ath12k_ag_to_ah(ag, i);
 		if (!ah)
@@ -11722,6 +12524,7 @@ int ath12k_mac_allocate(struct ath12k_hw_group *ag)
 		if (!ab)
 			continue;
 
+		ath12k_debugfs_pdev_create(ab);
 		ath12k_mac_set_device_defaults(ab);
 		total_radio += ab->num_radios;
 	}
diff --git a/drivers/net/wireless/ath/ath12k/mac.h b/drivers/net/wireless/ath/ath12k/mac.h
index ae35b73312bf..e6e74b45bfa4 100644
--- a/drivers/net/wireless/ath/ath12k/mac.h
+++ b/drivers/net/wireless/ath/ath12k/mac.h
@@ -33,6 +33,9 @@ struct ath12k_generic_iter {
 #define ATH12K_KEEPALIVE_MAX_IDLE		3895
 #define ATH12K_KEEPALIVE_MAX_UNRESPONSIVE	3900
 
+#define ATH12K_PDEV_TX_POWER_INVALID		((u32)-1)
+#define ATH12K_PDEV_TX_POWER_REFRESH_TIME_MSECS	5000 /* msecs */
+
 /* FIXME: should these be in ieee80211.h? */
 #define IEEE80211_VHT_MCS_SUPPORT_0_11_MASK	GENMASK(23, 16)
 #define IEEE80211_DISABLE_VHT_MCS_SUPPORT_0_11	BIT(24)
@@ -64,8 +67,55 @@ struct ath12k_mac_get_any_chanctx_conf_arg {
 	struct ieee80211_chanctx_conf *chanctx_conf;
 };
 
+/**
+ * struct ath12k_chan_power_info - TPE containing power info per channel chunk
+ * @chan_cfreq: channel center freq (MHz)
+ * e.g.
+ * channel 37/20 MHz,  it is 6135
+ * channel 37/40 MHz,  it is 6125
+ * channel 37/80 MHz,  it is 6145
+ * channel 37/160 MHz, it is 6185
+ * @tx_power: transmit power (dBm)
+ */
+struct ath12k_chan_power_info {
+	u16 chan_cfreq;
+	s8 tx_power;
+};
+
+/* ath12k only deals with 320 MHz, so 16 subchannels */
+#define ATH12K_NUM_PWR_LEVELS  16
+
+/**
+ * struct ath12k_reg_tpc_power_info - regulatory TPC power info
+ * @is_psd_power: is PSD power or not
+ * @eirp_power: Maximum EIRP power (dBm), valid only if power is PSD
+ * @ap_power_type: type of power (SP/LPI/VLP)
+ * @num_pwr_levels: number of power levels
+ * @reg_max: Array of maximum TX power (dBm) per PSD value
+ * @ap_constraint_power: AP constraint power (dBm)
+ * @tpe: TPE values processed from TPE IE
+ * @chan_power_info: power info to send to firmware
+ */
+struct ath12k_reg_tpc_power_info {
+	bool is_psd_power;
+	u8 eirp_power;
+	enum wmi_reg_6g_ap_type ap_power_type;
+	u8 num_pwr_levels;
+	u8 reg_max[ATH12K_NUM_PWR_LEVELS];
+	u8 ap_constraint_power;
+	s8 tpe[ATH12K_NUM_PWR_LEVELS];
+	struct ath12k_chan_power_info chan_power_info[ATH12K_NUM_PWR_LEVELS];
+};
+
 extern const struct htt_rx_ring_tlv_filter ath12k_mac_mon_status_filter_default;
 
+#define ATH12K_SCAN_11D_INTERVAL		600000
+#define ATH12K_11D_INVALID_VDEV_ID		0xFFFF
+
+void ath12k_mac_11d_scan_start(struct ath12k *ar, u32 vdev_id);
+void ath12k_mac_11d_scan_stop(struct ath12k *ar);
+void ath12k_mac_11d_scan_stop_all(struct ath12k_base *ab);
+
 void ath12k_mac_destroy(struct ath12k_hw_group *ag);
 void ath12k_mac_unregister(struct ath12k_hw_group *ag);
 int ath12k_mac_register(struct ath12k_hw_group *ag);
@@ -115,4 +165,10 @@ struct ieee80211_bss_conf *ath12k_mac_get_link_bss_conf(struct ath12k_link_vif *
 struct ath12k *ath12k_get_ar_by_vif(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
 				    u8 link_id);
+int ath12k_mac_get_fw_stats(struct ath12k *ar, struct ath12k_fw_stats_req_params *param);
+void ath12k_mac_update_freq_range(struct ath12k *ar,
+				  u32 freq_low, u32 freq_high);
+void ath12k_mac_fill_reg_tpc_info(struct ath12k *ar,
+				  struct ath12k_link_vif *arvif,
+				  struct ieee80211_chanctx_conf *ctx);
 #endif
diff --git a/drivers/net/wireless/ath/ath12k/mhi.c b/drivers/net/wireless/ath/ath12k/mhi.c
index 2f6d14382ed7..08f44baf182a 100644
--- a/drivers/net/wireless/ath/ath12k/mhi.c
+++ b/drivers/net/wireless/ath/ath12k/mhi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2020-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/msi.h>
@@ -285,8 +285,11 @@ static void ath12k_mhi_op_status_cb(struct mhi_controller *mhi_cntrl,
 			break;
 		}
 
-		if (!(test_bit(ATH12K_FLAG_UNREGISTERING, &ab->dev_flags)))
+		if (!(test_bit(ATH12K_FLAG_UNREGISTERING, &ab->dev_flags))) {
+			set_bit(ATH12K_FLAG_CRASH_FLUSH, &ab->dev_flags);
+			set_bit(ATH12K_FLAG_RECOVERY, &ab->dev_flags);
 			queue_work(ab->workqueue_aux, &ab->reset_work);
+		}
 		break;
 	default:
 		break;
@@ -379,7 +382,7 @@ int ath12k_mhi_register(struct ath12k_pci *ab_pci)
 		mhi_ctrl->irq_flags = IRQF_SHARED | IRQF_NOBALANCING;
 
 	mhi_ctrl->iova_start = 0;
-	mhi_ctrl->iova_stop = 0xffffffff;
+	mhi_ctrl->iova_stop = ab_pci->dma_mask;
 	mhi_ctrl->sbl_size = SZ_512K;
 	mhi_ctrl->seg_len = SZ_512K;
 	mhi_ctrl->fbc_download = true;
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index b474696ac6d8..489d546390fc 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -17,7 +17,7 @@
 #include "debug.h"
 
 #define ATH12K_PCI_BAR_NUM		0
-#define ATH12K_PCI_DMA_MASK		32
+#define ATH12K_PCI_DMA_MASK		36
 
 #define ATH12K_PCI_IRQ_CE0_OFFSET		3
 
@@ -600,7 +600,8 @@ static int ath12k_pci_ext_irq_config(struct ath12k_base *ab)
 		    ab->hw_params->ring_mask->rx_wbm_rel[i] ||
 		    ab->hw_params->ring_mask->reo_status[i] ||
 		    ab->hw_params->ring_mask->host2rxdma[i] ||
-		    ab->hw_params->ring_mask->rx_mon_dest[i]) {
+		    ab->hw_params->ring_mask->rx_mon_dest[i] ||
+		    ab->hw_params->ring_mask->rx_mon_status[i]) {
 			num_irq = 1;
 		}
 
@@ -718,7 +719,7 @@ static void ath12k_pci_init_qmi_ce_config(struct ath12k_base *ab)
 	cfg->svc_to_ce_map_len = ab->hw_params->svc_to_ce_map_len;
 	ab->qmi.service_ins_id = ab->hw_params->qmi_service_ins_id;
 
-	if (test_bit(ATH12K_FW_FEATURE_MULTI_QRTR_ID, ab->fw.fw_features)) {
+	if (ath12k_fw_feature_supported(ab, ATH12K_FW_FEATURE_MULTI_QRTR_ID)) {
 		ab_pci->qmi_instance =
 			u32_encode_bits(pci_domain_nr(bus), DOMAIN_NUMBER_MASK) |
 			u32_encode_bits(bus->number, BUS_NUMBER_MASK);
@@ -877,13 +878,9 @@ static int ath12k_pci_claim(struct ath12k_pci *ab_pci, struct pci_dev *pdev)
 		goto disable_device;
 	}
 
-	ret = dma_set_mask_and_coherent(&pdev->dev,
-					DMA_BIT_MASK(ATH12K_PCI_DMA_MASK));
-	if (ret) {
-		ath12k_err(ab, "failed to set pci dma mask to %d: %d\n",
-			   ATH12K_PCI_DMA_MASK, ret);
-		goto release_region;
-	}
+	ab_pci->dma_mask = DMA_BIT_MASK(ATH12K_PCI_DMA_MASK);
+	dma_set_mask(&pdev->dev, ab_pci->dma_mask);
+	dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
 
 	pci_set_master(pdev);
 
@@ -1472,7 +1469,7 @@ int ath12k_pci_power_up(struct ath12k_base *ab)
 
 	ath12k_pci_msi_enable(ab_pci);
 
-	if (test_bit(ATH12K_FW_FEATURE_MULTI_QRTR_ID, ab->fw.fw_features))
+	if (ath12k_fw_feature_supported(ab, ATH12K_FW_FEATURE_MULTI_QRTR_ID))
 		ath12k_pci_update_qrtr_node_id(ab);
 
 	ret = ath12k_mhi_start(ab_pci);
@@ -1491,6 +1488,9 @@ void ath12k_pci_power_down(struct ath12k_base *ab, bool is_suspend)
 {
 	struct ath12k_pci *ab_pci = ath12k_pci_priv(ab);
 
+	if (!test_bit(ATH12K_PCI_FLAG_INIT_DONE, &ab_pci->flags))
+		return;
+
 	/* restore aspm in case firmware bootup fails */
 	ath12k_pci_aspm_restore(ab_pci);
 
@@ -1710,12 +1710,12 @@ err_hal_srng_deinit:
 err_mhi_unregister:
 	ath12k_mhi_unregister(ab_pci);
 
-err_pci_msi_free:
-	ath12k_pci_msi_free(ab_pci);
-
 err_irq_affinity_cleanup:
 	ath12k_pci_set_irq_affinity_hint(ab_pci, NULL);
 
+err_pci_msi_free:
+	ath12k_pci_msi_free(ab_pci);
+
 err_pci_free_region:
 	ath12k_pci_free_region(ab_pci);
 
@@ -1734,8 +1734,6 @@ static void ath12k_pci_remove(struct pci_dev *pdev)
 
 	if (test_bit(ATH12K_FLAG_QMI_FAIL, &ab->dev_flags)) {
 		ath12k_pci_power_down(ab, false);
-		ath12k_qmi_deinit_service(ab);
-		ath12k_core_hw_group_unassign(ab);
 		goto qmi_fail;
 	}
 
@@ -1743,9 +1741,10 @@ static void ath12k_pci_remove(struct pci_dev *pdev)
 
 	cancel_work_sync(&ab->reset_work);
 	cancel_work_sync(&ab->dump_work);
-	ath12k_core_deinit(ab);
+	ath12k_core_hw_group_cleanup(ab->ag);
 
 qmi_fail:
+	ath12k_core_deinit(ab);
 	ath12k_fw_unmap(ab);
 	ath12k_mhi_unregister(ab_pci);
 
@@ -1758,13 +1757,34 @@ qmi_fail:
 	ath12k_core_free(ab);
 }
 
+static void ath12k_pci_hw_group_power_down(struct ath12k_hw_group *ag)
+{
+	struct ath12k_base *ab;
+	int i;
+
+	if (!ag)
+		return;
+
+	mutex_lock(&ag->mutex);
+
+	for (i = 0; i < ag->num_devices; i++) {
+		ab = ag->ab[i];
+		if (!ab)
+			continue;
+
+		ath12k_pci_power_down(ab, false);
+	}
+
+	mutex_unlock(&ag->mutex);
+}
+
 static void ath12k_pci_shutdown(struct pci_dev *pdev)
 {
 	struct ath12k_base *ab = pci_get_drvdata(pdev);
 	struct ath12k_pci *ab_pci = ath12k_pci_priv(ab);
 
 	ath12k_pci_set_irq_affinity_hint(ab_pci, NULL);
-	ath12k_pci_power_down(ab, false);
+	ath12k_pci_hw_group_power_down(ab->ag);
 }
 
 static __maybe_unused int ath12k_pci_pm_suspend(struct device *dev)
@@ -1831,7 +1851,7 @@ static struct pci_driver ath12k_pci_driver = {
 	.driver.pm = &ath12k_pci_pm_ops,
 };
 
-static int ath12k_pci_init(void)
+int ath12k_pci_init(void)
 {
 	int ret;
 
@@ -1844,14 +1864,8 @@ static int ath12k_pci_init(void)
 
 	return 0;
 }
-module_init(ath12k_pci_init);
 
-static void ath12k_pci_exit(void)
+void ath12k_pci_exit(void)
 {
 	pci_unregister_driver(&ath12k_pci_driver);
 }
-
-module_exit(ath12k_pci_exit);
-
-MODULE_DESCRIPTION("Driver support for Qualcomm Technologies PCIe 802.11be WLAN devices");
-MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/ath/ath12k/pci.h b/drivers/net/wireless/ath/ath12k/pci.h
index 31584a7ad80e..0b4c459d6d8e 100644
--- a/drivers/net/wireless/ath/ath12k/pci.h
+++ b/drivers/net/wireless/ath/ath12k/pci.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #ifndef ATH12K_PCI_H
 #define ATH12K_PCI_H
@@ -116,6 +116,7 @@ struct ath12k_pci {
 	unsigned long irq_flags;
 	const struct ath12k_pci_ops *pci_ops;
 	u32 qmi_instance;
+	u64 dma_mask;
 };
 
 static inline struct ath12k_pci *ath12k_pci_priv(struct ath12k_base *ab)
@@ -145,4 +146,6 @@ void ath12k_pci_stop(struct ath12k_base *ab);
 int ath12k_pci_start(struct ath12k_base *ab);
 int ath12k_pci_power_up(struct ath12k_base *ab);
 void ath12k_pci_power_down(struct ath12k_base *ab, bool is_suspend);
+int ath12k_pci_init(void);
+void ath12k_pci_exit(void);
 #endif /* ATH12K_PCI_H */
diff --git a/drivers/net/wireless/ath/ath12k/peer.c b/drivers/net/wireless/ath/ath12k/peer.c
index 792cca8a3fb1..ec7236bbccc0 100644
--- a/drivers/net/wireless/ath/ath12k/peer.c
+++ b/drivers/net/wireless/ath/ath12k/peer.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
@@ -383,6 +383,9 @@ int ath12k_peer_create(struct ath12k *ar, struct ath12k_link_vif *arvif,
 		arvif->ast_idx = peer->hw_peer_id;
 	}
 
+	if (vif->type == NL80211_IFTYPE_AP)
+		peer->ucast_ra_only = true;
+
 	if (sta) {
 		ahsta = ath12k_sta_to_ahsta(sta);
 		arsta = wiphy_dereference(ath12k_ar_to_hw(ar)->wiphy,
diff --git a/drivers/net/wireless/ath/ath12k/peer.h b/drivers/net/wireless/ath/ath12k/peer.h
index 5870ee11a8c7..f3a5e054d2b5 100644
--- a/drivers/net/wireless/ath/ath12k/peer.h
+++ b/drivers/net/wireless/ath/ath12k/peer.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_PEER_H
@@ -62,6 +62,7 @@ struct ath12k_peer {
 
 	/* for reference to ath12k_link_sta */
 	u8 link_id;
+	bool ucast_ra_only;
 };
 
 struct ath12k_ml_peer {
diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c
index 348dbc81bad8..99e1fb2910d0 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.c
+++ b/drivers/net/wireless/ath/ath12k/qmi.c
@@ -11,6 +11,8 @@
 #include "debug.h"
 #include <linux/of.h>
 #include <linux/firmware.h>
+#include <linux/of_address.h>
+#include <linux/ioport.h>
 
 #define SLEEP_CLOCK_SELECT_INTERNAL_BIT	0x02
 #define HOST_CSTATE_BIT			0x04
@@ -2168,10 +2170,12 @@ int ath12k_qmi_host_cap_send(struct ath12k_base *ab)
 	req.bdf_support_valid = 1;
 	req.bdf_support = 1;
 
-	req.m3_support_valid = 1;
-	req.m3_support = 1;
-	req.m3_cache_support_valid = 1;
-	req.m3_cache_support = 1;
+	if (ab->hw_params->fw.m3_loader == ath12k_m3_fw_loader_driver) {
+		req.m3_support_valid = 1;
+		req.m3_support = 1;
+		req.m3_cache_support_valid = 1;
+		req.m3_cache_support = 1;
+	}
 
 	req.cal_done_valid = 1;
 	req.cal_done = ab->qmi.cal_done;
@@ -2264,6 +2268,9 @@ static void ath12k_qmi_phy_cap_send(struct ath12k_base *ab)
 		goto out;
 	}
 
+	if (resp.single_chip_mlo_support_valid && resp.single_chip_mlo_support)
+		ab->single_chip_mlo_support = true;
+
 	if (!resp.num_phy_valid) {
 		ret = -ENODATA;
 		goto out;
@@ -2272,7 +2279,8 @@ static void ath12k_qmi_phy_cap_send(struct ath12k_base *ab)
 	ab->qmi.num_radios = resp.num_phy;
 
 	ath12k_dbg(ab, ATH12K_DBG_QMI,
-		   "phy capability resp valid %d num_phy %d valid %d board_id %d\n",
+		   "phy capability resp valid %d single_chip_mlo_support %d valid %d num_phy %d valid %d board_id %d\n",
+		   resp.single_chip_mlo_support_valid, resp.single_chip_mlo_support,
 		   resp.num_phy_valid, resp.num_phy,
 		   resp.board_id_valid, resp.board_id);
 
@@ -2376,7 +2384,8 @@ int ath12k_qmi_respond_fw_mem_request(struct ath12k_base *ab)
 	 * failure to firmware and firmware then request multiple blocks of
 	 * small chunk size memory.
 	 */
-	if (ab->qmi.target_mem_delayed) {
+	if (!test_bit(ATH12K_FLAG_FIXED_MEM_REGION, &ab->dev_flags) &&
+	    ab->qmi.target_mem_delayed) {
 		delayed = true;
 		ath12k_dbg(ab, ATH12K_DBG_QMI, "qmi delays mem_request %d\n",
 			   ab->qmi.mem_seg_count);
@@ -2434,12 +2443,35 @@ out:
 	return ret;
 }
 
+void ath12k_qmi_reset_mlo_mem(struct ath12k_hw_group *ag)
+{
+	struct target_mem_chunk *mlo_chunk;
+	int i;
+
+	lockdep_assert_held(&ag->mutex);
+
+	if (!ag->mlo_mem.init_done || ag->num_started)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(ag->mlo_mem.chunk); i++) {
+		mlo_chunk = &ag->mlo_mem.chunk[i];
+
+		if (mlo_chunk->v.addr)
+			/* TODO: Mode 0 recovery is the default mode hence resetting the
+			 * whole memory region for now. Once Mode 1 support is added, this
+			 * needs to be handled properly
+			 */
+			memset(mlo_chunk->v.addr, 0, mlo_chunk->size);
+	}
+}
+
 static void ath12k_qmi_free_mlo_mem_chunk(struct ath12k_base *ab,
 					  struct target_mem_chunk *chunk,
 					  int idx)
 {
 	struct ath12k_hw_group *ag = ab->ag;
 	struct target_mem_chunk *mlo_chunk;
+	bool fixed_mem;
 
 	lockdep_assert_held(&ag->mutex);
 
@@ -2451,8 +2483,13 @@ static void ath12k_qmi_free_mlo_mem_chunk(struct ath12k_base *ab,
 		return;
 	}
 
+	fixed_mem = test_bit(ATH12K_FLAG_FIXED_MEM_REGION, &ab->dev_flags);
 	mlo_chunk = &ag->mlo_mem.chunk[idx];
-	if (mlo_chunk->v.addr) {
+
+	if (fixed_mem && mlo_chunk->v.ioaddr) {
+		iounmap(mlo_chunk->v.ioaddr);
+		mlo_chunk->v.ioaddr = NULL;
+	} else if (mlo_chunk->v.addr) {
 		dma_free_coherent(ab->dev,
 				  mlo_chunk->size,
 				  mlo_chunk->v.addr,
@@ -2462,7 +2499,10 @@ static void ath12k_qmi_free_mlo_mem_chunk(struct ath12k_base *ab,
 
 	mlo_chunk->paddr = 0;
 	mlo_chunk->size = 0;
-	chunk->v.addr = NULL;
+	if (fixed_mem)
+		chunk->v.ioaddr = NULL;
+	else
+		chunk->v.addr = NULL;
 	chunk->paddr = 0;
 	chunk->size = 0;
 }
@@ -2473,19 +2513,24 @@ static void ath12k_qmi_free_target_mem_chunk(struct ath12k_base *ab)
 	int i, mlo_idx;
 
 	for (i = 0, mlo_idx = 0; i < ab->qmi.mem_seg_count; i++) {
-		if (!ab->qmi.target_mem[i].v.addr)
-			continue;
-
 		if (ab->qmi.target_mem[i].type == MLO_GLOBAL_MEM_REGION_TYPE) {
 			ath12k_qmi_free_mlo_mem_chunk(ab,
 						      &ab->qmi.target_mem[i],
 						      mlo_idx++);
 		} else {
-			dma_free_coherent(ab->dev,
-					  ab->qmi.target_mem[i].prev_size,
-					  ab->qmi.target_mem[i].v.addr,
-					  ab->qmi.target_mem[i].paddr);
-			ab->qmi.target_mem[i].v.addr = NULL;
+			if (test_bit(ATH12K_FLAG_FIXED_MEM_REGION, &ab->dev_flags) &&
+			    ab->qmi.target_mem[i].v.ioaddr) {
+				iounmap(ab->qmi.target_mem[i].v.ioaddr);
+				ab->qmi.target_mem[i].v.ioaddr = NULL;
+			} else {
+				if (!ab->qmi.target_mem[i].v.addr)
+					continue;
+				dma_free_coherent(ab->dev,
+						  ab->qmi.target_mem[i].prev_size,
+						  ab->qmi.target_mem[i].v.addr,
+						  ab->qmi.target_mem[i].paddr);
+				ab->qmi.target_mem[i].v.addr = NULL;
+			}
 		}
 	}
 
@@ -2638,6 +2683,130 @@ err:
 	return ret;
 }
 
+static int ath12k_qmi_assign_target_mem_chunk(struct ath12k_base *ab)
+{
+	struct reserved_mem *rmem;
+	size_t avail_rmem_size;
+	int i, idx, ret;
+
+	for (i = 0, idx = 0; i < ab->qmi.mem_seg_count; i++) {
+		switch (ab->qmi.target_mem[i].type) {
+		case HOST_DDR_REGION_TYPE:
+			rmem = ath12k_core_get_reserved_mem(ab, 0);
+			if (!rmem) {
+				ret = -ENODEV;
+				goto out;
+			}
+
+			avail_rmem_size = rmem->size;
+			if (avail_rmem_size < ab->qmi.target_mem[i].size) {
+				ath12k_dbg(ab, ATH12K_DBG_QMI,
+					   "failed to assign mem type %u req size %u avail size %zu\n",
+					   ab->qmi.target_mem[i].type,
+					   ab->qmi.target_mem[i].size,
+					   avail_rmem_size);
+				ret = -EINVAL;
+				goto out;
+			}
+
+			ab->qmi.target_mem[idx].paddr = rmem->base;
+			ab->qmi.target_mem[idx].v.ioaddr =
+				ioremap(ab->qmi.target_mem[idx].paddr,
+					ab->qmi.target_mem[i].size);
+			if (!ab->qmi.target_mem[idx].v.ioaddr) {
+				ret = -EIO;
+				goto out;
+			}
+			ab->qmi.target_mem[idx].size = ab->qmi.target_mem[i].size;
+			ab->qmi.target_mem[idx].type = ab->qmi.target_mem[i].type;
+			idx++;
+			break;
+		case BDF_MEM_REGION_TYPE:
+			rmem = ath12k_core_get_reserved_mem(ab, 0);
+			if (!rmem) {
+				ret = -ENODEV;
+				goto out;
+			}
+
+			avail_rmem_size = rmem->size - ab->hw_params->bdf_addr_offset;
+			if (avail_rmem_size < ab->qmi.target_mem[i].size) {
+				ath12k_dbg(ab, ATH12K_DBG_QMI,
+					   "failed to assign mem type %u req size %u avail size %zu\n",
+					   ab->qmi.target_mem[i].type,
+					   ab->qmi.target_mem[i].size,
+					   avail_rmem_size);
+				ret = -EINVAL;
+				goto out;
+			}
+			ab->qmi.target_mem[idx].paddr =
+				rmem->base + ab->hw_params->bdf_addr_offset;
+			ab->qmi.target_mem[idx].v.ioaddr =
+				ioremap(ab->qmi.target_mem[idx].paddr,
+					ab->qmi.target_mem[i].size);
+			if (!ab->qmi.target_mem[idx].v.ioaddr) {
+				ret = -EIO;
+				goto out;
+			}
+			ab->qmi.target_mem[idx].size = ab->qmi.target_mem[i].size;
+			ab->qmi.target_mem[idx].type = ab->qmi.target_mem[i].type;
+			idx++;
+			break;
+		case CALDB_MEM_REGION_TYPE:
+			/* Cold boot calibration is not enabled in Ath12k. Hence,
+			 * assign paddr = 0.
+			 * Once cold boot calibration is enabled add support to
+			 * assign reserved memory from DT.
+			 */
+			ab->qmi.target_mem[idx].paddr = 0;
+			ab->qmi.target_mem[idx].v.ioaddr = NULL;
+			ab->qmi.target_mem[idx].size = ab->qmi.target_mem[i].size;
+			ab->qmi.target_mem[idx].type = ab->qmi.target_mem[i].type;
+			idx++;
+			break;
+		case M3_DUMP_REGION_TYPE:
+			rmem = ath12k_core_get_reserved_mem(ab, 1);
+			if (!rmem) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			avail_rmem_size = rmem->size;
+			if (avail_rmem_size < ab->qmi.target_mem[i].size) {
+				ath12k_dbg(ab, ATH12K_DBG_QMI,
+					   "failed to assign mem type %u req size %u avail size %zu\n",
+					   ab->qmi.target_mem[i].type,
+					   ab->qmi.target_mem[i].size,
+					   avail_rmem_size);
+				ret = -EINVAL;
+				goto out;
+			}
+
+			ab->qmi.target_mem[idx].paddr = rmem->base;
+			ab->qmi.target_mem[idx].v.ioaddr =
+				ioremap(ab->qmi.target_mem[idx].paddr,
+					ab->qmi.target_mem[i].size);
+			if (!ab->qmi.target_mem[idx].v.ioaddr) {
+				ret = -EIO;
+				goto out;
+			}
+			ab->qmi.target_mem[idx].size = ab->qmi.target_mem[i].size;
+			ab->qmi.target_mem[idx].type = ab->qmi.target_mem[i].type;
+			idx++;
+			break;
+		default:
+			ath12k_warn(ab, "qmi ignore invalid mem req type %u\n",
+				    ab->qmi.target_mem[i].type);
+			break;
+		}
+	}
+	ab->qmi.mem_seg_count = idx;
+
+	return 0;
+out:
+	ath12k_qmi_free_target_mem_chunk(ab);
+	return ret;
+}
+
 /* clang stack usage explodes if this is inlined */
 static noinline_for_stack
 int ath12k_qmi_request_target_cap(struct ath12k_base *ab)
@@ -2939,6 +3108,9 @@ static void ath12k_qmi_m3_free(struct ath12k_base *ab)
 {
 	struct m3_mem_region *m3_mem = &ab->qmi.m3_mem;
 
+	if (ab->hw_params->fw.m3_loader == ath12k_m3_fw_loader_remoteproc)
+		return;
+
 	if (!m3_mem->vaddr)
 		return;
 
@@ -3019,15 +3191,16 @@ int ath12k_qmi_wlanfw_m3_info_send(struct ath12k_base *ab)
 	struct qmi_txn txn;
 	int ret = 0;
 
-	ret = ath12k_qmi_m3_load(ab);
-	if (ret) {
-		ath12k_err(ab, "failed to load m3 firmware: %d", ret);
-		return ret;
+	if (ab->hw_params->fw.m3_loader == ath12k_m3_fw_loader_driver) {
+		ret = ath12k_qmi_m3_load(ab);
+		if (ret) {
+			ath12k_err(ab, "failed to load m3 firmware: %d", ret);
+			return ret;
+		}
+		req.addr = m3_mem->paddr;
+		req.size = m3_mem->size;
 	}
 
-	req.addr = m3_mem->paddr;
-	req.size = m3_mem->size;
-
 	ret = qmi_txn_init(&ab->qmi.handle, &txn,
 			   qmi_wlanfw_m3_info_resp_msg_v01_ei, &resp);
 	if (ret < 0)
@@ -3477,11 +3650,20 @@ static void ath12k_qmi_msg_mem_request_cb(struct qmi_handle *qmi_hdl,
 			   msg->mem_seg[i].type, msg->mem_seg[i].size);
 	}
 
-	ret = ath12k_qmi_alloc_target_mem_chunk(ab);
-	if (ret) {
-		ath12k_warn(ab, "qmi failed to alloc target memory: %d\n",
-			    ret);
-		return;
+	if (test_bit(ATH12K_FLAG_FIXED_MEM_REGION, &ab->dev_flags)) {
+		ret = ath12k_qmi_assign_target_mem_chunk(ab);
+		if (ret) {
+			ath12k_warn(ab, "failed to assign qmi target memory: %d\n",
+				    ret);
+			return;
+		}
+	} else {
+		ret = ath12k_qmi_alloc_target_mem_chunk(ab);
+		if (ret) {
+			ath12k_warn(ab, "qmi failed to alloc target memory: %d\n",
+				    ret);
+			return;
+		}
 	}
 
 	ath12k_qmi_driver_event_post(qmi, ATH12K_QMI_EVENT_REQUEST_MEM, NULL);
diff --git a/drivers/net/wireless/ath/ath12k/qmi.h b/drivers/net/wireless/ath/ath12k/qmi.h
index 45d7c3fcafdd..96e6c3daecfe 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.h
+++ b/drivers/net/wireless/ath/ath12k/qmi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_QMI_H
@@ -21,6 +21,7 @@
 #define ATH12K_QMI_WLFW_SERVICE_INS_ID_V01_WCN7850 0x1
 
 #define ATH12K_QMI_WLFW_SERVICE_INS_ID_V01_QCN9274	0x07
+#define ATH12K_QMI_WLFW_SERVICE_INS_ID_V01_IPQ5332	0x2
 #define ATH12K_QMI_WLANFW_MAX_TIMESTAMP_LEN_V01	32
 #define ATH12K_QMI_RESP_LEN_MAX			8192
 #define ATH12K_QMI_WLANFW_MAX_NUM_MEM_SEG_V01	52
@@ -41,6 +42,7 @@
 #define ATH12K_BOARD_ID_DEFAULT	0xFF
 
 struct ath12k_base;
+struct ath12k_hw_group;
 
 enum ath12k_qmi_file_type {
 	ATH12K_QMI_FILE_TYPE_BDF_GOLDEN	= 0,
@@ -621,5 +623,6 @@ void ath12k_qmi_deinit_service(struct ath12k_base *ab);
 int ath12k_qmi_init_service(struct ath12k_base *ab);
 void ath12k_qmi_free_resource(struct ath12k_base *ab);
 void ath12k_qmi_trigger_host_cap(struct ath12k_base *ab);
+void ath12k_qmi_reset_mlo_mem(struct ath12k_hw_group *ag);
 
 #endif
diff --git a/drivers/net/wireless/ath/ath12k/reg.c b/drivers/net/wireless/ath/ath12k/reg.c
index 439d61f284d8..2598b39d5d7e 100644
--- a/drivers/net/wireless/ath/ath12k/reg.c
+++ b/drivers/net/wireless/ath/ath12k/reg.c
@@ -1,11 +1,12 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/rtnetlink.h>
 #include "core.h"
 #include "debug.h"
+#include "mac.h"
 
 /* World regdom to be used in case default regd from fw is unavailable */
 #define ATH12K_2GHZ_CH01_11      REG_RULE(2412 - 10, 2462 + 10, 40, 0, 20, 0)
@@ -48,6 +49,7 @@ ath12k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request)
 {
 	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
 	struct ath12k_wmi_init_country_arg arg;
+	struct wmi_set_current_country_arg current_arg = {};
 	struct ath12k_hw *ah = ath12k_hw_to_ah(hw);
 	struct ath12k *ar = ath12k_ah_to_ar(ah, 0);
 	int ret, i;
@@ -55,6 +57,24 @@ ath12k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request)
 	ath12k_dbg(ar->ab, ATH12K_DBG_REG,
 		   "Regulatory Notification received for %s\n", wiphy_name(wiphy));
 
+	if (request->initiator == NL80211_REGDOM_SET_BY_DRIVER) {
+		ath12k_dbg(ar->ab, ATH12K_DBG_REG,
+			   "driver initiated regd update\n");
+		if (ah->state != ATH12K_HW_STATE_ON)
+			return;
+
+		for_each_ar(ah, ar, i) {
+			ret = ath12k_reg_update_chan_list(ar, true);
+			if (ret) {
+				ath12k_warn(ar->ab,
+					    "failed to update chan list for pdev %u, ret %d\n",
+					    i, ret);
+				break;
+			}
+		}
+		return;
+	}
+
 	/* Currently supporting only General User Hints. Cell base user
 	 * hints to be handled later.
 	 * Hints from other sources like Core, Beacons are not expected for
@@ -77,27 +97,38 @@ ath12k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request)
 		return;
 	}
 
-	/* Set the country code to the firmware and wait for
-	 * the WMI_REG_CHAN_LIST_CC EVENT for updating the
-	 * reg info
-	 */
-	arg.flags = ALPHA_IS_SET;
-	memcpy(&arg.cc_info.alpha2, request->alpha2, 2);
-	arg.cc_info.alpha2[2] = 0;
-
 	/* Allow fresh updates to wiphy regd */
 	ah->regd_updated = false;
 
 	/* Send the reg change request to all the radios */
 	for_each_ar(ah, ar, i) {
-		ret = ath12k_wmi_send_init_country_cmd(ar, &arg);
-		if (ret)
-			ath12k_warn(ar->ab,
-				    "INIT Country code set to fw failed : %d\n", ret);
+		if (ar->ab->hw_params->current_cc_support) {
+			memcpy(&current_arg.alpha2, request->alpha2, 2);
+			memcpy(&ar->alpha2, &current_arg.alpha2, 2);
+			ret = ath12k_wmi_send_set_current_country_cmd(ar, &current_arg);
+			if (ret)
+				ath12k_warn(ar->ab,
+					    "failed set current country code: %d\n", ret);
+		} else {
+			arg.flags = ALPHA_IS_SET;
+			memcpy(&arg.cc_info.alpha2, request->alpha2, 2);
+			arg.cc_info.alpha2[2] = 0;
+
+			ret = ath12k_wmi_send_init_country_cmd(ar, &arg);
+			if (ret)
+				ath12k_warn(ar->ab,
+					    "failed set INIT Country code: %d\n", ret);
+		}
+
+		wiphy_lock(wiphy);
+		ath12k_mac_11d_scan_stop(ar);
+		wiphy_unlock(wiphy);
+
+		ar->regdom_set_by_user = true;
 	}
 }
 
-int ath12k_reg_update_chan_list(struct ath12k *ar)
+int ath12k_reg_update_chan_list(struct ath12k *ar, bool wait)
 {
 	struct ieee80211_supported_band **bands;
 	struct ath12k_wmi_scan_chan_list_arg *arg;
@@ -106,7 +137,35 @@ int ath12k_reg_update_chan_list(struct ath12k *ar)
 	struct ath12k_wmi_channel_arg *ch;
 	enum nl80211_band band;
 	int num_channels = 0;
-	int i, ret;
+	int i, ret, left;
+
+	if (wait && ar->state_11d == ATH12K_11D_RUNNING) {
+		left = wait_for_completion_timeout(&ar->completed_11d_scan,
+						   ATH12K_SCAN_TIMEOUT_HZ);
+		if (!left) {
+			ath12k_dbg(ar->ab, ATH12K_DBG_REG,
+				   "failed to receive 11d scan complete: timed out\n");
+			ar->state_11d = ATH12K_11D_IDLE;
+		}
+		ath12k_dbg(ar->ab, ATH12K_DBG_REG,
+			   "reg 11d scan wait left time %d\n", left);
+	}
+
+	if (wait &&
+	    (ar->scan.state == ATH12K_SCAN_STARTING ||
+	    ar->scan.state == ATH12K_SCAN_RUNNING)) {
+		left = wait_for_completion_timeout(&ar->scan.completed,
+						   ATH12K_SCAN_TIMEOUT_HZ);
+		if (!left)
+			ath12k_dbg(ar->ab, ATH12K_DBG_REG,
+				   "failed to receive hw scan complete: timed out\n");
+
+		ath12k_dbg(ar->ab, ATH12K_DBG_REG,
+			   "reg hw scan wait left time %d\n", left);
+	}
+
+	if (ar->ah->state == ATH12K_HW_STATE_RESTARTING)
+		return 0;
 
 	bands = hw->wiphy->bands;
 	for (band = 0; band < NUM_NL80211_BANDS; band++) {
@@ -206,15 +265,57 @@ static void ath12k_copy_regd(struct ieee80211_regdomain *regd_orig,
 
 int ath12k_regd_update(struct ath12k *ar, bool init)
 {
+	struct ath12k_wmi_hal_reg_capabilities_ext_arg *reg_cap;
+	u32 phy_id, freq_low, freq_high, supported_bands;
 	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
 	struct ieee80211_hw *hw = ah->hw;
 	struct ieee80211_regdomain *regd, *regd_copy = NULL;
 	int ret, regd_len, pdev_id;
 	struct ath12k_base *ab;
-	int i;
 
 	ab = ar->ab;
 
+	supported_bands = ar->pdev->cap.supported_bands;
+	reg_cap = &ab->hal_reg_cap[ar->pdev_idx];
+
+	/* Possible that due to reg change, current limits for supported
+	 * frequency changed. Update it. As a first step, reset the
+	 * previous values and then compute and set the new values.
+	 */
+	ar->freq_range.start_freq = 0;
+	ar->freq_range.end_freq = 0;
+
+	if (supported_bands & WMI_HOST_WLAN_2GHZ_CAP) {
+		if (ab->hw_params->single_pdev_only) {
+			phy_id = ar->pdev->cap.band[WMI_HOST_WLAN_2GHZ_CAP].phy_id;
+			reg_cap = &ab->hal_reg_cap[phy_id];
+		}
+
+		freq_low = max(reg_cap->low_2ghz_chan, ab->reg_freq_2ghz.start_freq);
+		freq_high = min(reg_cap->high_2ghz_chan, ab->reg_freq_2ghz.end_freq);
+
+		ath12k_mac_update_freq_range(ar, freq_low, freq_high);
+	}
+
+	if (supported_bands & WMI_HOST_WLAN_5GHZ_CAP && !ar->supports_6ghz) {
+		if (ab->hw_params->single_pdev_only) {
+			phy_id = ar->pdev->cap.band[WMI_HOST_WLAN_5GHZ_CAP].phy_id;
+			reg_cap = &ab->hal_reg_cap[phy_id];
+		}
+
+		freq_low = max(reg_cap->low_5ghz_chan, ab->reg_freq_5ghz.start_freq);
+		freq_high = min(reg_cap->high_5ghz_chan, ab->reg_freq_5ghz.end_freq);
+
+		ath12k_mac_update_freq_range(ar, freq_low, freq_high);
+	}
+
+	if (supported_bands & WMI_HOST_WLAN_5GHZ_CAP && ar->supports_6ghz) {
+		freq_low = max(reg_cap->low_5ghz_chan, ab->reg_freq_6ghz.start_freq);
+		freq_high = min(reg_cap->high_5ghz_chan, ab->reg_freq_6ghz.end_freq);
+
+		ath12k_mac_update_freq_range(ar, freq_low, freq_high);
+	}
+
 	/* If one of the radios within ah has already updated the regd for
 	 * the wiphy, then avoid setting regd again
 	 */
@@ -275,11 +376,7 @@ int ath12k_regd_update(struct ath12k *ar, bool init)
 		goto err;
 	}
 
-	rtnl_lock();
-	wiphy_lock(hw->wiphy);
-	ret = regulatory_set_wiphy_regd_sync(hw->wiphy, regd_copy);
-	wiphy_unlock(hw->wiphy);
-	rtnl_unlock();
+	ret = regulatory_set_wiphy_regd(hw->wiphy, regd_copy);
 
 	kfree(regd_copy);
 
@@ -290,15 +387,7 @@ int ath12k_regd_update(struct ath12k *ar, bool init)
 		goto skip;
 
 	ah->regd_updated = true;
-	/* Apply the new regd to all the radios, this is expected to be received only once
-	 * since we check for ah->regd_updated and allow here only once.
-	 */
-	for_each_ar(ah, ar, i) {
-		ab = ar->ab;
-		ret = ath12k_reg_update_chan_list(ar);
-		if (ret)
-			goto err;
-	}
+
 skip:
 	return 0;
 err:
@@ -365,129 +454,6 @@ static u32 ath12k_map_fw_phy_flags(u32 phy_flags)
 	return flags;
 }
 
-static bool
-ath12k_reg_can_intersect(struct ieee80211_reg_rule *rule1,
-			 struct ieee80211_reg_rule *rule2)
-{
-	u32 start_freq1, end_freq1;
-	u32 start_freq2, end_freq2;
-
-	start_freq1 = rule1->freq_range.start_freq_khz;
-	start_freq2 = rule2->freq_range.start_freq_khz;
-
-	end_freq1 = rule1->freq_range.end_freq_khz;
-	end_freq2 = rule2->freq_range.end_freq_khz;
-
-	if ((start_freq1 >= start_freq2 &&
-	     start_freq1 < end_freq2) ||
-	    (start_freq2 > start_freq1 &&
-	     start_freq2 < end_freq1))
-		return true;
-
-	/* TODO: Should we restrict intersection feasibility
-	 *  based on min bandwidth of the intersected region also,
-	 *  say the intersected rule should have a  min bandwidth
-	 * of 20MHz?
-	 */
-
-	return false;
-}
-
-static void ath12k_reg_intersect_rules(struct ieee80211_reg_rule *rule1,
-				       struct ieee80211_reg_rule *rule2,
-				       struct ieee80211_reg_rule *new_rule)
-{
-	u32 start_freq1, end_freq1;
-	u32 start_freq2, end_freq2;
-	u32 freq_diff, max_bw;
-
-	start_freq1 = rule1->freq_range.start_freq_khz;
-	start_freq2 = rule2->freq_range.start_freq_khz;
-
-	end_freq1 = rule1->freq_range.end_freq_khz;
-	end_freq2 = rule2->freq_range.end_freq_khz;
-
-	new_rule->freq_range.start_freq_khz = max_t(u32, start_freq1,
-						    start_freq2);
-	new_rule->freq_range.end_freq_khz = min_t(u32, end_freq1, end_freq2);
-
-	freq_diff = new_rule->freq_range.end_freq_khz -
-			new_rule->freq_range.start_freq_khz;
-	max_bw = min_t(u32, rule1->freq_range.max_bandwidth_khz,
-		       rule2->freq_range.max_bandwidth_khz);
-	new_rule->freq_range.max_bandwidth_khz = min_t(u32, max_bw, freq_diff);
-
-	new_rule->power_rule.max_antenna_gain =
-		min_t(u32, rule1->power_rule.max_antenna_gain,
-		      rule2->power_rule.max_antenna_gain);
-
-	new_rule->power_rule.max_eirp = min_t(u32, rule1->power_rule.max_eirp,
-					      rule2->power_rule.max_eirp);
-
-	/* Use the flags of both the rules */
-	new_rule->flags = rule1->flags | rule2->flags;
-
-	/* To be safe, lts use the max cac timeout of both rules */
-	new_rule->dfs_cac_ms = max_t(u32, rule1->dfs_cac_ms,
-				     rule2->dfs_cac_ms);
-}
-
-static struct ieee80211_regdomain *
-ath12k_regd_intersect(struct ieee80211_regdomain *default_regd,
-		      struct ieee80211_regdomain *curr_regd)
-{
-	u8 num_old_regd_rules, num_curr_regd_rules, num_new_regd_rules;
-	struct ieee80211_reg_rule *old_rule, *curr_rule, *new_rule;
-	struct ieee80211_regdomain *new_regd = NULL;
-	u8 i, j, k;
-
-	num_old_regd_rules = default_regd->n_reg_rules;
-	num_curr_regd_rules = curr_regd->n_reg_rules;
-	num_new_regd_rules = 0;
-
-	/* Find the number of intersecting rules to allocate new regd memory */
-	for (i = 0; i < num_old_regd_rules; i++) {
-		old_rule = default_regd->reg_rules + i;
-		for (j = 0; j < num_curr_regd_rules; j++) {
-			curr_rule = curr_regd->reg_rules + j;
-
-			if (ath12k_reg_can_intersect(old_rule, curr_rule))
-				num_new_regd_rules++;
-		}
-	}
-
-	if (!num_new_regd_rules)
-		return NULL;
-
-	new_regd = kzalloc(sizeof(*new_regd) + (num_new_regd_rules *
-			sizeof(struct ieee80211_reg_rule)),
-			GFP_ATOMIC);
-
-	if (!new_regd)
-		return NULL;
-
-	/* We set the new country and dfs region directly and only trim
-	 * the freq, power, antenna gain by intersecting with the
-	 * default regdomain. Also MAX of the dfs cac timeout is selected.
-	 */
-	new_regd->n_reg_rules = num_new_regd_rules;
-	memcpy(new_regd->alpha2, curr_regd->alpha2, sizeof(new_regd->alpha2));
-	new_regd->dfs_region = curr_regd->dfs_region;
-	new_rule = new_regd->reg_rules;
-
-	for (i = 0, k = 0; i < num_old_regd_rules; i++) {
-		old_rule = default_regd->reg_rules + i;
-		for (j = 0; j < num_curr_regd_rules; j++) {
-			curr_rule = curr_regd->reg_rules + j;
-
-			if (ath12k_reg_can_intersect(old_rule, curr_rule))
-				ath12k_reg_intersect_rules(old_rule, curr_rule,
-							   (new_rule + k++));
-		}
-	}
-	return new_regd;
-}
-
 static const char *
 ath12k_reg_get_regdom_str(enum nl80211_dfs_regions dfs_region)
 {
@@ -524,13 +490,14 @@ ath12k_reg_adjust_bw(u16 start_freq, u16 end_freq, u16 max_bw)
 static void
 ath12k_reg_update_rule(struct ieee80211_reg_rule *reg_rule, u32 start_freq,
 		       u32 end_freq, u32 bw, u32 ant_gain, u32 reg_pwr,
-		       u32 reg_flags)
+		       s8 psd, u32 reg_flags)
 {
 	reg_rule->freq_range.start_freq_khz = MHZ_TO_KHZ(start_freq);
 	reg_rule->freq_range.end_freq_khz = MHZ_TO_KHZ(end_freq);
 	reg_rule->freq_range.max_bandwidth_khz = MHZ_TO_KHZ(bw);
 	reg_rule->power_rule.max_antenna_gain = DBI_TO_MBI(ant_gain);
 	reg_rule->power_rule.max_eirp = DBM_TO_MBM(reg_pwr);
+	reg_rule->psd = psd;
 	reg_rule->flags = reg_flags;
 }
 
@@ -552,7 +519,7 @@ ath12k_reg_update_weather_radar_band(struct ath12k_base *ab,
 	ath12k_reg_update_rule(regd->reg_rules + i, reg_rule->start_freq,
 			       ETSI_WEATHER_RADAR_BAND_LOW, bw,
 			       reg_rule->ant_gain, reg_rule->reg_power,
-			       flags);
+			       reg_rule->psd_eirp, flags);
 
 	ath12k_dbg(ab, ATH12K_DBG_REG,
 		   "\t%d. (%d - %d @ %d) (%d, %d) (%d ms) (FLAGS %d)\n",
@@ -574,7 +541,7 @@ ath12k_reg_update_weather_radar_band(struct ath12k_base *ab,
 	ath12k_reg_update_rule(regd->reg_rules + i,
 			       ETSI_WEATHER_RADAR_BAND_LOW, end_freq, bw,
 			       reg_rule->ant_gain, reg_rule->reg_power,
-			       flags);
+			       reg_rule->psd_eirp, flags);
 
 	regd->reg_rules[i].dfs_cac_ms = ETSI_WEATHER_RADAR_BAND_CAC_TIMEOUT;
 
@@ -599,7 +566,7 @@ ath12k_reg_update_weather_radar_band(struct ath12k_base *ab,
 	ath12k_reg_update_rule(regd->reg_rules + i, ETSI_WEATHER_RADAR_BAND_HIGH,
 			       reg_rule->end_freq, bw,
 			       reg_rule->ant_gain, reg_rule->reg_power,
-			       flags);
+			       reg_rule->psd_eirp, flags);
 
 	ath12k_dbg(ab, ATH12K_DBG_REG,
 		   "\t%d. (%d - %d @ %d) (%d, %d) (%d ms) (FLAGS %d)\n",
@@ -611,26 +578,77 @@ ath12k_reg_update_weather_radar_band(struct ath12k_base *ab,
 	*rule_idx = i;
 }
 
+static void ath12k_reg_update_freq_range(struct ath12k_reg_freq *reg_freq,
+					 struct ath12k_reg_rule *reg_rule)
+{
+	if (reg_freq->start_freq > reg_rule->start_freq)
+		reg_freq->start_freq = reg_rule->start_freq;
+
+	if (reg_freq->end_freq < reg_rule->end_freq)
+		reg_freq->end_freq = reg_rule->end_freq;
+}
+
+enum wmi_reg_6g_ap_type
+ath12k_reg_ap_pwr_convert(enum ieee80211_ap_reg_power power_type)
+{
+	switch (power_type) {
+	case IEEE80211_REG_LPI_AP:
+		return WMI_REG_INDOOR_AP;
+	case IEEE80211_REG_SP_AP:
+		return WMI_REG_STD_POWER_AP;
+	case IEEE80211_REG_VLP_AP:
+		return WMI_REG_VLP_AP;
+	default:
+		return WMI_REG_MAX_AP_TYPE;
+	}
+}
+
 struct ieee80211_regdomain *
 ath12k_reg_build_regd(struct ath12k_base *ab,
-		      struct ath12k_reg_info *reg_info, bool intersect)
+		      struct ath12k_reg_info *reg_info,
+		      enum wmi_vdev_type vdev_type,
+		      enum ieee80211_ap_reg_power power_type)
 {
-	struct ieee80211_regdomain *tmp_regd, *default_regd, *new_regd = NULL;
-	struct ath12k_reg_rule *reg_rule;
+	struct ieee80211_regdomain *new_regd = NULL;
+	struct ath12k_reg_rule *reg_rule, *reg_rule_6ghz;
+	u32 flags, reg_6ghz_number, max_bw_6ghz;
 	u8 i = 0, j = 0, k = 0;
 	u8 num_rules;
 	u16 max_bw;
-	u32 flags;
 	char alpha2[3];
 
 	num_rules = reg_info->num_5g_reg_rules + reg_info->num_2g_reg_rules;
 
-	/* FIXME: Currently taking reg rules for 6G only from Indoor AP mode list.
-	 * This can be updated to choose the combination dynamically based on AP
-	 * type and client type, after complete 6G regulatory support is added.
-	 */
-	if (reg_info->is_ext_reg_event)
-		num_rules += reg_info->num_6g_reg_rules_ap[WMI_REG_INDOOR_AP];
+	if (reg_info->is_ext_reg_event) {
+		if (vdev_type == WMI_VDEV_TYPE_STA) {
+			enum wmi_reg_6g_ap_type ap_type;
+
+			ap_type = ath12k_reg_ap_pwr_convert(power_type);
+			if (ap_type == WMI_REG_MAX_AP_TYPE)
+				ap_type = WMI_REG_INDOOR_AP;
+
+			reg_6ghz_number = reg_info->num_6g_reg_rules_cl
+					[ap_type][WMI_REG_DEFAULT_CLIENT];
+			if (reg_6ghz_number == 0) {
+				ap_type = WMI_REG_INDOOR_AP;
+				reg_6ghz_number = reg_info->num_6g_reg_rules_cl
+						[ap_type][WMI_REG_DEFAULT_CLIENT];
+			}
+
+			reg_rule_6ghz = reg_info->reg_rules_6g_client_ptr
+					[ap_type][WMI_REG_DEFAULT_CLIENT];
+			max_bw_6ghz = reg_info->max_bw_6g_client
+					[ap_type][WMI_REG_DEFAULT_CLIENT];
+		} else {
+			reg_6ghz_number = reg_info->num_6g_reg_rules_ap
+						[WMI_REG_INDOOR_AP];
+			reg_rule_6ghz =
+				reg_info->reg_rules_6g_ap_ptr[WMI_REG_INDOOR_AP];
+			max_bw_6ghz = reg_info->max_bw_6g_ap[WMI_REG_INDOOR_AP];
+		}
+
+		num_rules += reg_6ghz_number;
+	}
 
 	if (!num_rules)
 		goto ret;
@@ -639,21 +657,31 @@ ath12k_reg_build_regd(struct ath12k_base *ab,
 	if (reg_info->dfs_region == ATH12K_DFS_REG_ETSI)
 		num_rules += 2;
 
-	tmp_regd = kzalloc(sizeof(*tmp_regd) +
+	new_regd = kzalloc(sizeof(*new_regd) +
 			   (num_rules * sizeof(struct ieee80211_reg_rule)),
 			   GFP_ATOMIC);
-	if (!tmp_regd)
+	if (!new_regd)
 		goto ret;
 
-	memcpy(tmp_regd->alpha2, reg_info->alpha2, REG_ALPHA2_LEN + 1);
+	memcpy(new_regd->alpha2, reg_info->alpha2, REG_ALPHA2_LEN + 1);
 	memcpy(alpha2, reg_info->alpha2, REG_ALPHA2_LEN + 1);
 	alpha2[2] = '\0';
-	tmp_regd->dfs_region = ath12k_map_fw_dfs_region(reg_info->dfs_region);
+	new_regd->dfs_region = ath12k_map_fw_dfs_region(reg_info->dfs_region);
 
 	ath12k_dbg(ab, ATH12K_DBG_REG,
 		   "\r\nCountry %s, CFG Regdomain %s FW Regdomain %d, num_reg_rules %d\n",
-		   alpha2, ath12k_reg_get_regdom_str(tmp_regd->dfs_region),
+		   alpha2, ath12k_reg_get_regdom_str(new_regd->dfs_region),
 		   reg_info->dfs_region, num_rules);
+
+	/* Reset start and end frequency for each band
+	 */
+	ab->reg_freq_5ghz.start_freq = INT_MAX;
+	ab->reg_freq_5ghz.end_freq = 0;
+	ab->reg_freq_2ghz.start_freq = INT_MAX;
+	ab->reg_freq_2ghz.end_freq = 0;
+	ab->reg_freq_6ghz.start_freq = INT_MAX;
+	ab->reg_freq_6ghz.end_freq = 0;
+
 	/* Update reg_rules[] below. Firmware is expected to
 	 * send these rules in order(2G rules first and then 5G)
 	 */
@@ -664,6 +692,7 @@ ath12k_reg_build_regd(struct ath12k_base *ab,
 			max_bw = min_t(u16, reg_rule->max_bw,
 				       reg_info->max_bw_2g);
 			flags = 0;
+			ath12k_reg_update_freq_range(&ab->reg_freq_2ghz, reg_rule);
 		} else if (reg_info->num_5g_reg_rules &&
 			   (j < reg_info->num_5g_reg_rules)) {
 			reg_rule = reg_info->reg_rules_5g_ptr + j++;
@@ -677,13 +706,15 @@ ath12k_reg_build_regd(struct ath12k_base *ab,
 			 * per other BW rule flags we pass from here
 			 */
 			flags = NL80211_RRF_AUTO_BW;
-		} else if (reg_info->is_ext_reg_event &&
-			   reg_info->num_6g_reg_rules_ap[WMI_REG_INDOOR_AP] &&
-			(k < reg_info->num_6g_reg_rules_ap[WMI_REG_INDOOR_AP])) {
-			reg_rule = reg_info->reg_rules_6g_ap_ptr[WMI_REG_INDOOR_AP] + k++;
-			max_bw = min_t(u16, reg_rule->max_bw,
-				       reg_info->max_bw_6g_ap[WMI_REG_INDOOR_AP]);
+			ath12k_reg_update_freq_range(&ab->reg_freq_5ghz, reg_rule);
+		} else if (reg_info->is_ext_reg_event && reg_6ghz_number &&
+			   (k < reg_6ghz_number)) {
+			reg_rule = reg_rule_6ghz + k++;
+			max_bw = min_t(u16, reg_rule->max_bw, max_bw_6ghz);
 			flags = NL80211_RRF_AUTO_BW;
+			if (reg_rule->psd_flag)
+				flags |= NL80211_RRF_PSD;
+			ath12k_reg_update_freq_range(&ab->reg_freq_6ghz, reg_rule);
 		} else {
 			break;
 		}
@@ -691,11 +722,11 @@ ath12k_reg_build_regd(struct ath12k_base *ab,
 		flags |= ath12k_map_fw_reg_flags(reg_rule->flags);
 		flags |= ath12k_map_fw_phy_flags(reg_info->phybitmap);
 
-		ath12k_reg_update_rule(tmp_regd->reg_rules + i,
+		ath12k_reg_update_rule(new_regd->reg_rules + i,
 				       reg_rule->start_freq,
 				       reg_rule->end_freq, max_bw,
 				       reg_rule->ant_gain, reg_rule->reg_power,
-				       flags);
+				       reg_rule->psd_eirp, flags);
 
 		/* Update dfs cac timeout if the dfs domain is ETSI and the
 		 * new rule covers weather radar band.
@@ -706,7 +737,7 @@ ath12k_reg_build_regd(struct ath12k_base *ab,
 		    reg_info->dfs_region == ATH12K_DFS_REG_ETSI &&
 		    (reg_rule->end_freq > ETSI_WEATHER_RADAR_BAND_LOW &&
 		    reg_rule->start_freq < ETSI_WEATHER_RADAR_BAND_HIGH)){
-			ath12k_reg_update_weather_radar_band(ab, tmp_regd,
+			ath12k_reg_update_weather_radar_band(ab, new_regd,
 							     reg_rule, &i,
 							     flags, max_bw);
 			continue;
@@ -716,36 +747,19 @@ ath12k_reg_build_regd(struct ath12k_base *ab,
 			ath12k_dbg(ab, ATH12K_DBG_REG, "\t%d. (%d - %d @ %d) (%d, %d) (%d ms) (FLAGS %d) (%d, %d)\n",
 				   i + 1, reg_rule->start_freq, reg_rule->end_freq,
 				   max_bw, reg_rule->ant_gain, reg_rule->reg_power,
-				   tmp_regd->reg_rules[i].dfs_cac_ms,
+				   new_regd->reg_rules[i].dfs_cac_ms,
 				   flags, reg_rule->psd_flag, reg_rule->psd_eirp);
 		} else {
 			ath12k_dbg(ab, ATH12K_DBG_REG,
 				   "\t%d. (%d - %d @ %d) (%d, %d) (%d ms) (FLAGS %d)\n",
 				   i + 1, reg_rule->start_freq, reg_rule->end_freq,
 				   max_bw, reg_rule->ant_gain, reg_rule->reg_power,
-				   tmp_regd->reg_rules[i].dfs_cac_ms,
+				   new_regd->reg_rules[i].dfs_cac_ms,
 				   flags);
 		}
 	}
 
-	tmp_regd->n_reg_rules = i;
-
-	if (intersect) {
-		default_regd = ab->default_regd[reg_info->phy_id];
-
-		/* Get a new regd by intersecting the received regd with
-		 * our default regd.
-		 */
-		new_regd = ath12k_regd_intersect(default_regd, tmp_regd);
-		kfree(tmp_regd);
-		if (!new_regd) {
-			ath12k_warn(ab, "Unable to create intersected regdomain\n");
-			goto ret;
-		}
-	} else {
-		new_regd = tmp_regd;
-	}
-
+	new_regd->n_reg_rules = i;
 ret:
 	return new_regd;
 }
@@ -767,9 +781,109 @@ void ath12k_regd_update_work(struct work_struct *work)
 	}
 }
 
+void ath12k_reg_reset_reg_info(struct ath12k_reg_info *reg_info)
+{
+	u8 i, j;
+
+	if (!reg_info)
+		return;
+
+	kfree(reg_info->reg_rules_2g_ptr);
+	kfree(reg_info->reg_rules_5g_ptr);
+
+	if (reg_info->is_ext_reg_event) {
+		for (i = 0; i < WMI_REG_CURRENT_MAX_AP_TYPE; i++) {
+			kfree(reg_info->reg_rules_6g_ap_ptr[i]);
+
+			for (j = 0; j < WMI_REG_MAX_CLIENT_TYPE; j++)
+				kfree(reg_info->reg_rules_6g_client_ptr[i][j]);
+		}
+	}
+}
+
+enum ath12k_reg_status ath12k_reg_validate_reg_info(struct ath12k_base *ab,
+						    struct ath12k_reg_info *reg_info)
+{
+	int pdev_idx = reg_info->phy_id;
+
+	if (reg_info->status_code != REG_SET_CC_STATUS_PASS) {
+		/* In case of failure to set the requested country,
+		 * firmware retains the current regd. We print a failure info
+		 * and return from here.
+		 */
+		ath12k_warn(ab, "Failed to set the requested Country regulatory setting\n");
+		return ATH12K_REG_STATUS_DROP;
+	}
+
+	if (pdev_idx >= ab->num_radios) {
+		/* Process the event for phy0 only if single_pdev_only
+		 * is true. If pdev_idx is valid but not 0, discard the
+		 * event. Otherwise, it goes to fallback.
+		 */
+		if (ab->hw_params->single_pdev_only &&
+		    pdev_idx < ab->hw_params->num_rxdma_per_pdev)
+			return ATH12K_REG_STATUS_DROP;
+		else
+			return ATH12K_REG_STATUS_FALLBACK;
+	}
+
+	/* Avoid multiple overwrites to default regd, during core
+	 * stop-start after mac registration.
+	 */
+	if (ab->default_regd[pdev_idx] && !ab->new_regd[pdev_idx] &&
+	    !memcmp(ab->default_regd[pdev_idx]->alpha2,
+		    reg_info->alpha2, 2))
+		return ATH12K_REG_STATUS_DROP;
+
+	return ATH12K_REG_STATUS_VALID;
+}
+
+int ath12k_reg_handle_chan_list(struct ath12k_base *ab,
+				struct ath12k_reg_info *reg_info,
+				enum wmi_vdev_type vdev_type,
+				enum ieee80211_ap_reg_power power_type)
+{
+	struct ieee80211_regdomain *regd = NULL;
+	int pdev_idx = reg_info->phy_id;
+	struct ath12k *ar;
+
+	regd = ath12k_reg_build_regd(ab, reg_info, vdev_type, power_type);
+	if (!regd)
+		return -EINVAL;
+
+	spin_lock_bh(&ab->base_lock);
+	if (test_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags)) {
+		/* Once mac is registered, ar is valid and all CC events from
+		 * firmware is considered to be received due to user requests
+		 * currently.
+		 * Free previously built regd before assigning the newly
+		 * generated regd to ar. NULL pointer handling will be
+		 * taken care by kfree itself.
+		 */
+		ar = ab->pdevs[pdev_idx].ar;
+		kfree(ab->new_regd[pdev_idx]);
+		ab->new_regd[pdev_idx] = regd;
+		queue_work(ab->workqueue, &ar->regd_update_work);
+	} else {
+		/* Multiple events for the same *ar is not expected. But we
+		 * can still clear any previously stored default_regd if we
+		 * are receiving this event for the same radio by mistake.
+		 * NULL pointer handling will be taken care by kfree itself.
+		 */
+		kfree(ab->default_regd[pdev_idx]);
+		/* This regd would be applied during mac registration */
+		ab->default_regd[pdev_idx] = regd;
+	}
+	ab->dfs_region = reg_info->dfs_region;
+	spin_unlock_bh(&ab->base_lock);
+
+	return 0;
+}
+
 void ath12k_reg_init(struct ieee80211_hw *hw)
 {
 	hw->wiphy->regulatory_flags = REGULATORY_WIPHY_SELF_MANAGED;
+	hw->wiphy->flags |= WIPHY_FLAG_NOTIFY_REGDOM_BY_DRIVER;
 	hw->wiphy->reg_notifier = ath12k_reg_notifier;
 }
 
@@ -777,8 +891,18 @@ void ath12k_reg_free(struct ath12k_base *ab)
 {
 	int i;
 
+	mutex_lock(&ab->core_lock);
+	for (i = 0; i < MAX_RADIOS; i++) {
+		ath12k_reg_reset_reg_info(ab->reg_info[i]);
+		kfree(ab->reg_info[i]);
+		ab->reg_info[i] = NULL;
+	}
+
 	for (i = 0; i < ab->hw_params->max_radios; i++) {
 		kfree(ab->default_regd[i]);
 		kfree(ab->new_regd[i]);
+		ab->default_regd[i] = NULL;
+		ab->new_regd[i] = NULL;
 	}
+	mutex_unlock(&ab->core_lock);
 }
diff --git a/drivers/net/wireless/ath/ath12k/reg.h b/drivers/net/wireless/ath/ath12k/reg.h
index 75f80df2aa0c..8af8e9ba462e 100644
--- a/drivers/net/wireless/ath/ath12k/reg.h
+++ b/drivers/net/wireless/ath/ath12k/reg.h
@@ -92,13 +92,29 @@ enum ath12k_reg_phy_bitmap {
 	ATH12K_REG_PHY_BITMAP_NO11BE	= BIT(6),
 };
 
+enum ath12k_reg_status {
+	ATH12K_REG_STATUS_VALID,
+	ATH12K_REG_STATUS_DROP,
+	ATH12K_REG_STATUS_FALLBACK,
+};
+
 void ath12k_reg_init(struct ieee80211_hw *hw);
 void ath12k_reg_free(struct ath12k_base *ab);
 void ath12k_regd_update_work(struct work_struct *work);
 struct ieee80211_regdomain *ath12k_reg_build_regd(struct ath12k_base *ab,
 						  struct ath12k_reg_info *reg_info,
-						  bool intersect);
+						  enum wmi_vdev_type vdev_type,
+						  enum ieee80211_ap_reg_power power_type);
 int ath12k_regd_update(struct ath12k *ar, bool init);
-int ath12k_reg_update_chan_list(struct ath12k *ar);
+int ath12k_reg_update_chan_list(struct ath12k *ar, bool wait);
 
+void ath12k_reg_reset_reg_info(struct ath12k_reg_info *reg_info);
+int ath12k_reg_handle_chan_list(struct ath12k_base *ab,
+				struct ath12k_reg_info *reg_info,
+				enum wmi_vdev_type vdev_type,
+				enum ieee80211_ap_reg_power power_type);
+enum wmi_reg_6g_ap_type
+ath12k_reg_ap_pwr_convert(enum ieee80211_ap_reg_power power_type);
+enum ath12k_reg_status ath12k_reg_validate_reg_info(struct ath12k_base *ab,
+						    struct ath12k_reg_info *reg_info);
 #endif
diff --git a/drivers/net/wireless/ath/ath12k/testmode.c b/drivers/net/wireless/ath/ath12k/testmode.c
index 18d56a976dc7..fb6af7ccf71f 100644
--- a/drivers/net/wireless/ath/ath12k/testmode.c
+++ b/drivers/net/wireless/ath/ath12k/testmode.c
@@ -97,7 +97,7 @@ void ath12k_tm_process_event(struct ath12k_base *ab, u32 cmd_id,
 	u8 const *buf_pos;
 
 	ath12k_dbg(ab, ATH12K_DBG_TESTMODE,
-		   "testmode event wmi cmd_id %d ftm event msg %pK datalen %d\n",
+		   "testmode event wmi cmd_id %d ftm event msg %p datalen %d\n",
 		   cmd_id, ftm_msg, length);
 	ath12k_dbg_dump(ab, ATH12K_DBG_TESTMODE, NULL, "", ftm_msg, length);
 	pdev_id = DP_HW2SW_MACID(le32_to_cpu(ftm_msg->seg_hdr.pdev_id));
@@ -227,7 +227,7 @@ static int ath12k_tm_cmd_process_ftm(struct ath12k *ar, struct nlattr *tb[])
 	buf_len = nla_len(tb[ATH_TM_ATTR_DATA]);
 	cmd_id = WMI_PDEV_UTF_CMDID;
 	ath12k_dbg(ar->ab, ATH12K_DBG_TESTMODE,
-		   "testmode cmd wmi cmd_id %d buf %pK buf_len %d\n",
+		   "testmode cmd wmi cmd_id %d buf %p buf_len %d\n",
 		   cmd_id, buf, buf_len);
 	ath12k_dbg_dump(ar->ab, ATH12K_DBG_TESTMODE, NULL, "", buf, buf_len);
 	bufpos = buf;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 6d1ea5f3a791..60e2444fe08c 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -29,6 +29,7 @@ struct ath12k_wmi_svc_ready_parse {
 
 struct wmi_tlv_fw_stats_parse {
 	const struct wmi_stats_event *ev;
+	struct ath12k_fw_stats *stats;
 };
 
 struct ath12k_wmi_dma_ring_caps_parse {
@@ -177,6 +178,8 @@ static const struct ath12k_wmi_tlv_policy ath12k_wmi_tlv_policies[] = {
 		.min_len = sizeof(struct ath12k_wmi_p2p_noa_info) },
 	[WMI_TAG_P2P_NOA_EVENT] = {
 		.min_len = sizeof(struct wmi_p2p_noa_event) },
+	[WMI_TAG_11D_NEW_COUNTRY_EVENT] = {
+		.min_len = sizeof(struct wmi_11d_new_cc_event) },
 };
 
 __le32 ath12k_wmi_tlv_hdr(u32 cmd, u32 len)
@@ -520,10 +523,10 @@ ath12k_pull_mac_phy_cap_svc_ready_ext(struct ath12k_wmi_pdev *wmi_handle,
 	 * band to band for a single radio, need to see how this should be
 	 * handled.
 	 */
-	if (le32_to_cpu(mac_caps->supported_bands) & WMI_HOST_WLAN_2G_CAP) {
+	if (le32_to_cpu(mac_caps->supported_bands) & WMI_HOST_WLAN_2GHZ_CAP) {
 		pdev_cap->tx_chain_mask = le32_to_cpu(mac_caps->tx_chain_mask_2g);
 		pdev_cap->rx_chain_mask = le32_to_cpu(mac_caps->rx_chain_mask_2g);
-	} else if (le32_to_cpu(mac_caps->supported_bands) & WMI_HOST_WLAN_5G_CAP) {
+	} else if (le32_to_cpu(mac_caps->supported_bands) & WMI_HOST_WLAN_5GHZ_CAP) {
 		pdev_cap->vht_cap = le32_to_cpu(mac_caps->vht_cap_info_5g);
 		pdev_cap->vht_mcs = le32_to_cpu(mac_caps->vht_supp_mcs_5g);
 		pdev_cap->he_mcs = le32_to_cpu(mac_caps->he_supp_mcs_5g);
@@ -546,7 +549,7 @@ ath12k_pull_mac_phy_cap_svc_ready_ext(struct ath12k_wmi_pdev *wmi_handle,
 	pdev_cap->rx_chain_mask_shift =
 			find_first_bit((unsigned long *)&pdev_cap->rx_chain_mask, 32);
 
-	if (le32_to_cpu(mac_caps->supported_bands) & WMI_HOST_WLAN_2G_CAP) {
+	if (le32_to_cpu(mac_caps->supported_bands) & WMI_HOST_WLAN_2GHZ_CAP) {
 		cap_band = &pdev_cap->band[NL80211_BAND_2GHZ];
 		cap_band->phy_id = le32_to_cpu(mac_caps->phy_id);
 		cap_band->max_bw_supported = le32_to_cpu(mac_caps->max_bw_supported_2g);
@@ -566,7 +569,7 @@ ath12k_pull_mac_phy_cap_svc_ready_ext(struct ath12k_wmi_pdev *wmi_handle,
 				le32_to_cpu(mac_caps->he_ppet2g.ppet16_ppet8_ru3_ru0[i]);
 	}
 
-	if (le32_to_cpu(mac_caps->supported_bands) & WMI_HOST_WLAN_5G_CAP) {
+	if (le32_to_cpu(mac_caps->supported_bands) & WMI_HOST_WLAN_5GHZ_CAP) {
 		cap_band = &pdev_cap->band[NL80211_BAND_5GHZ];
 		cap_band->phy_id = le32_to_cpu(mac_caps->phy_id);
 		cap_band->max_bw_supported =
@@ -1037,14 +1040,32 @@ int ath12k_wmi_vdev_down(struct ath12k *ar, u8 vdev_id)
 static void ath12k_wmi_put_wmi_channel(struct ath12k_wmi_channel_params *chan,
 				       struct wmi_vdev_start_req_arg *arg)
 {
+	u32 center_freq1 = arg->band_center_freq1;
+
 	memset(chan, 0, sizeof(*chan));
 
 	chan->mhz = cpu_to_le32(arg->freq);
-	chan->band_center_freq1 = cpu_to_le32(arg->band_center_freq1);
-	if (arg->mode == MODE_11AC_VHT80_80)
+	chan->band_center_freq1 = cpu_to_le32(center_freq1);
+	if (arg->mode == MODE_11BE_EHT320) {
+		if (arg->freq > center_freq1)
+			chan->band_center_freq1 = cpu_to_le32(center_freq1 + 80);
+		else
+			chan->band_center_freq1 = cpu_to_le32(center_freq1 - 80);
+
+		chan->band_center_freq2 = cpu_to_le32(center_freq1);
+
+	} else if (arg->mode == MODE_11BE_EHT160) {
+		if (arg->freq > center_freq1)
+			chan->band_center_freq1 = cpu_to_le32(center_freq1 + 40);
+		else
+			chan->band_center_freq1 = cpu_to_le32(center_freq1 - 40);
+
+		chan->band_center_freq2 = cpu_to_le32(center_freq1);
+	} else if (arg->mode == MODE_11BE_EHT80_80) {
 		chan->band_center_freq2 = cpu_to_le32(arg->band_center_freq2);
-	else
+	} else {
 		chan->band_center_freq2 = 0;
+	}
 
 	chan->info |= le32_encode_bits(arg->mode, WMI_CHAN_INFO_MODE);
 	if (arg->passive)
@@ -2166,9 +2187,10 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 	struct sk_buff *skb;
 	struct wmi_tlv *tlv;
 	void *ptr;
-	u32 peer_legacy_rates_align;
-	u32 peer_ht_rates_align;
+	u32 peer_legacy_rates_align, eml_pad_delay, eml_trans_delay;
+	u32 peer_ht_rates_align, eml_trans_timeout;
 	int i, ret, len;
+	u16 eml_cap;
 	__le32 v;
 
 	peer_legacy_rates_align = roundup(arg->peer_legacy_rates.num_rates,
@@ -2340,6 +2362,24 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 	ml_params->logical_link_idx = cpu_to_le32(arg->ml.logical_link_idx);
 	ml_params->ml_peer_id = cpu_to_le32(arg->ml.ml_peer_id);
 	ml_params->ieee_link_id = cpu_to_le32(arg->ml.ieee_link_id);
+
+	eml_cap = arg->ml.eml_cap;
+	if (u16_get_bits(eml_cap, IEEE80211_EML_CAP_EMLSR_SUPP)) {
+		/* Padding delay */
+		eml_pad_delay = ieee80211_emlsr_pad_delay_in_us(eml_cap);
+		ml_params->emlsr_padding_delay_us = cpu_to_le32(eml_pad_delay);
+		/* Transition delay */
+		eml_trans_delay = ieee80211_emlsr_trans_delay_in_us(eml_cap);
+		ml_params->emlsr_trans_delay_us = cpu_to_le32(eml_trans_delay);
+		/* Transition timeout */
+		eml_trans_timeout = ieee80211_eml_trans_timeout_in_us(eml_cap);
+		ml_params->emlsr_trans_timeout_us =
+					cpu_to_le32(eml_trans_timeout);
+		ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "wmi peer %pM emlsr padding delay %u, trans delay %u trans timeout %u",
+			   arg->peer_mac, eml_pad_delay, eml_trans_delay,
+			   eml_trans_timeout);
+	}
+
 	ptr += sizeof(*ml_params);
 
 skip_ml_params:
@@ -2351,7 +2391,7 @@ skip_ml_params:
 
 	for (i = 0; i < arg->peer_eht_mcs_count; i++) {
 		eht_mcs = ptr;
-		eht_mcs->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_HE_RATE_SET,
+		eht_mcs->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_EHT_RATE_SET,
 							     sizeof(*eht_mcs));
 
 		eht_mcs->rx_mcs_set = cpu_to_le32(arg->peer_eht_rx_mcs_set[i]);
@@ -2359,6 +2399,10 @@ skip_ml_params:
 		ptr += sizeof(*eht_mcs);
 	}
 
+	/* Update MCS15 capability */
+	if (arg->eht_disable_mcs15)
+		cmd->peer_eht_ops = cpu_to_le32(IEEE80211_EHT_OPER_MCS15_DISABLE);
+
 	tlv = ptr;
 	len = arg->ml.enabled ? arg->ml.num_partner_links * sizeof(*partner_info) : 0;
 	/* fill ML Partner links */
@@ -2399,7 +2443,7 @@ skip_ml_params:
 
 send:
 	ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
-		   "wmi peer assoc vdev id %d assoc id %d peer mac %pM peer_flags %x rate_caps %x peer_caps %x listen_intval %d ht_caps %x max_mpdu %d nss %d phymode %d peer_mpdu_density %d vht_caps %x he cap_info %x he ops %x he cap_info_ext %x he phy %x %x %x peer_bw_rxnss_override %x peer_flags_ext %x eht mac_cap %x %x eht phy_cap %x %x %x\n",
+		   "wmi peer assoc vdev id %d assoc id %d peer mac %pM peer_flags %x rate_caps %x peer_caps %x listen_intval %d ht_caps %x max_mpdu %d nss %d phymode %d peer_mpdu_density %d vht_caps %x he cap_info %x he ops %x he cap_info_ext %x he phy %x %x %x peer_bw_rxnss_override %x peer_flags_ext %x eht mac_cap %x %x eht phy_cap %x %x %x peer_eht_ops %x\n",
 		   cmd->vdev_id, cmd->peer_associd, arg->peer_mac,
 		   cmd->peer_flags, cmd->peer_rate_caps, cmd->peer_caps,
 		   cmd->peer_listen_intval, cmd->peer_ht_caps,
@@ -2412,7 +2456,7 @@ send:
 		   cmd->peer_bw_rxnss_override, cmd->peer_flags_ext,
 		   cmd->peer_eht_cap_mac[0], cmd->peer_eht_cap_mac[1],
 		   cmd->peer_eht_cap_phy[0], cmd->peer_eht_cap_phy[1],
-		   cmd->peer_eht_cap_phy[2]);
+		   cmd->peer_eht_cap_phy[2], cmd->peer_eht_ops);
 
 	ret = ath12k_wmi_cmd_send(wmi, skb, WMI_PEER_ASSOC_CMDID);
 	if (ret) {
@@ -2591,7 +2635,10 @@ int ath12k_wmi_send_scan_start_cmd(struct ath12k *ar,
 	cmd->scan_id = cpu_to_le32(arg->scan_id);
 	cmd->scan_req_id = cpu_to_le32(arg->scan_req_id);
 	cmd->vdev_id = cpu_to_le32(arg->vdev_id);
-	cmd->scan_priority = cpu_to_le32(arg->scan_priority);
+	if (ar->state_11d == ATH12K_11D_PREPARING)
+		arg->scan_priority = WMI_SCAN_PRIORITY_MEDIUM;
+	else
+		arg->scan_priority = WMI_SCAN_PRIORITY_LOW;
 	cmd->notify_scan_events = cpu_to_le32(arg->notify_scan_events);
 
 	ath12k_wmi_copy_scan_event_cntrl_flags(cmd, arg);
@@ -3313,6 +3360,110 @@ out:
 	return ret;
 }
 
+int ath12k_wmi_send_set_current_country_cmd(struct ath12k *ar,
+					    struct wmi_set_current_country_arg *arg)
+{
+	struct ath12k_wmi_pdev *wmi = ar->wmi;
+	struct wmi_set_current_country_cmd *cmd;
+	struct sk_buff *skb;
+	int ret;
+
+	skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, sizeof(*cmd));
+	if (!skb)
+		return -ENOMEM;
+
+	cmd = (struct wmi_set_current_country_cmd *)skb->data;
+	cmd->tlv_header =
+		ath12k_wmi_tlv_cmd_hdr(WMI_TAG_SET_CURRENT_COUNTRY_CMD,
+				       sizeof(*cmd));
+
+	cmd->pdev_id = cpu_to_le32(ar->pdev->pdev_id);
+	memcpy(&cmd->new_alpha2, &arg->alpha2, sizeof(arg->alpha2));
+	ret = ath12k_wmi_cmd_send(wmi, skb, WMI_SET_CURRENT_COUNTRY_CMDID);
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
+		   "set current country pdev id %d alpha2 %c%c\n",
+		   ar->pdev->pdev_id,
+		   arg->alpha2[0],
+		   arg->alpha2[1]);
+
+	if (ret) {
+		ath12k_warn(ar->ab,
+			    "failed to send WMI_SET_CURRENT_COUNTRY_CMDID: %d\n", ret);
+		dev_kfree_skb(skb);
+	}
+
+	return ret;
+}
+
+int ath12k_wmi_send_11d_scan_start_cmd(struct ath12k *ar,
+				       struct wmi_11d_scan_start_arg *arg)
+{
+	struct ath12k_wmi_pdev *wmi = ar->wmi;
+	struct wmi_11d_scan_start_cmd *cmd;
+	struct sk_buff *skb;
+	int ret;
+
+	skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, sizeof(*cmd));
+	if (!skb)
+		return -ENOMEM;
+
+	cmd = (struct wmi_11d_scan_start_cmd *)skb->data;
+	cmd->tlv_header =
+		ath12k_wmi_tlv_cmd_hdr(WMI_TAG_11D_SCAN_START_CMD,
+				       sizeof(*cmd));
+
+	cmd->vdev_id = cpu_to_le32(arg->vdev_id);
+	cmd->scan_period_msec = cpu_to_le32(arg->scan_period_msec);
+	cmd->start_interval_msec = cpu_to_le32(arg->start_interval_msec);
+	ret = ath12k_wmi_cmd_send(wmi, skb, WMI_11D_SCAN_START_CMDID);
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
+		   "send 11d scan start vdev id %d period %d ms internal %d ms\n",
+		   arg->vdev_id, arg->scan_period_msec,
+		   arg->start_interval_msec);
+
+	if (ret) {
+		ath12k_warn(ar->ab,
+			    "failed to send WMI_11D_SCAN_START_CMDID: %d\n", ret);
+		dev_kfree_skb(skb);
+	}
+
+	return ret;
+}
+
+int ath12k_wmi_send_11d_scan_stop_cmd(struct ath12k *ar, u32 vdev_id)
+{
+	struct ath12k_wmi_pdev *wmi = ar->wmi;
+	struct wmi_11d_scan_stop_cmd *cmd;
+	struct sk_buff *skb;
+	int ret;
+
+	skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, sizeof(*cmd));
+	if (!skb)
+		return -ENOMEM;
+
+	cmd = (struct wmi_11d_scan_stop_cmd *)skb->data;
+	cmd->tlv_header =
+		ath12k_wmi_tlv_cmd_hdr(WMI_TAG_11D_SCAN_STOP_CMD,
+				       sizeof(*cmd));
+
+	cmd->vdev_id = cpu_to_le32(vdev_id);
+	ret = ath12k_wmi_cmd_send(wmi, skb, WMI_11D_SCAN_STOP_CMDID);
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
+		   "send 11d scan stop vdev id %d\n",
+		   cmd->vdev_id);
+
+	if (ret) {
+		ath12k_warn(ar->ab,
+			    "failed to send WMI_11D_SCAN_STOP_CMDID: %d\n", ret);
+		dev_kfree_skb(skb);
+	}
+
+	return ret;
+}
+
 int
 ath12k_wmi_send_twt_enable_cmd(struct ath12k *ar, u32 pdev_id)
 {
@@ -3646,15 +3797,15 @@ ath12k_fill_band_to_mac_param(struct ath12k_base  *soc,
 		arg[i].pdev_id = pdev->pdev_id;
 
 		switch (pdev->cap.supported_bands) {
-		case WMI_HOST_WLAN_2G_5G_CAP:
+		case WMI_HOST_WLAN_2GHZ_5GHZ_CAP:
 			arg[i].start_freq = hal_reg_cap->low_2ghz_chan;
 			arg[i].end_freq = hal_reg_cap->high_5ghz_chan;
 			break;
-		case WMI_HOST_WLAN_2G_CAP:
+		case WMI_HOST_WLAN_2GHZ_CAP:
 			arg[i].start_freq = hal_reg_cap->low_2ghz_chan;
 			arg[i].end_freq = hal_reg_cap->high_2ghz_chan;
 			break;
-		case WMI_HOST_WLAN_5G_CAP:
+		case WMI_HOST_WLAN_5GHZ_CAP:
 			arg[i].start_freq = hal_reg_cap->low_5ghz_chan;
 			arg[i].end_freq = hal_reg_cap->high_5ghz_chan;
 			break;
@@ -3665,7 +3816,8 @@ ath12k_fill_band_to_mac_param(struct ath12k_base  *soc,
 }
 
 static void
-ath12k_wmi_copy_resource_config(struct ath12k_wmi_resource_config_params *wmi_cfg,
+ath12k_wmi_copy_resource_config(struct ath12k_base *ab,
+				struct ath12k_wmi_resource_config_params *wmi_cfg,
 				struct ath12k_wmi_resource_config_arg *tg_cfg)
 {
 	wmi_cfg->num_vdevs = cpu_to_le32(tg_cfg->num_vdevs);
@@ -3732,6 +3884,9 @@ ath12k_wmi_copy_resource_config(struct ath12k_wmi_resource_config_params *wmi_cf
 					   WMI_RSRC_CFG_FLAGS2_RX_PEER_METADATA_VERSION);
 	wmi_cfg->host_service_flags = cpu_to_le32(tg_cfg->is_reg_cc_ext_event_supported <<
 				WMI_RSRC_CFG_HOST_SVC_FLAG_REG_CC_EXT_SUPPORT_BIT);
+	if (ab->hw_params->reoq_lut_support)
+		wmi_cfg->host_service_flags |=
+			cpu_to_le32(1 << WMI_RSRC_CFG_HOST_SVC_FLAG_REO_QREF_SUPPORT_BIT);
 	wmi_cfg->ema_max_vap_cnt = cpu_to_le32(tg_cfg->ema_max_vap_cnt);
 	wmi_cfg->ema_max_profile_period = cpu_to_le32(tg_cfg->ema_max_profile_period);
 	wmi_cfg->flags2 |= cpu_to_le32(WMI_RSRC_CFG_FLAGS2_CALC_NEXT_DTIM_COUNT_SET);
@@ -3772,7 +3927,7 @@ static int ath12k_init_cmd_send(struct ath12k_wmi_pdev *wmi,
 	ptr = skb->data + sizeof(*cmd);
 	cfg = ptr;
 
-	ath12k_wmi_copy_resource_config(cfg, &arg->res_cfg);
+	ath12k_wmi_copy_resource_config(ab, cfg, &arg->res_cfg);
 
 	cfg->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_RESOURCE_CONFIG,
 						 sizeof(*cfg));
@@ -4601,6 +4756,7 @@ static int ath12k_service_ready_ext_event(struct ath12k_base *ab,
 	return 0;
 
 err:
+	kfree(svc_rdy_ext.mac_phy_caps);
 	ath12k_wmi_free_dbring_caps(ab);
 	return ret;
 }
@@ -4699,7 +4855,7 @@ ath12k_wmi_tlv_mac_phy_caps_ext_parse(struct ath12k_base *ab,
 		bands = pdev->cap.supported_bands;
 	}
 
-	if (bands & WMI_HOST_WLAN_2G_CAP) {
+	if (bands & WMI_HOST_WLAN_2GHZ_CAP) {
 		ath12k_wmi_eht_caps_parse(pdev, NL80211_BAND_2GHZ,
 					  caps->eht_cap_mac_info_2ghz,
 					  caps->eht_cap_phy_info_2ghz,
@@ -4708,7 +4864,7 @@ ath12k_wmi_tlv_mac_phy_caps_ext_parse(struct ath12k_base *ab,
 					  caps->eht_cap_info_internal);
 	}
 
-	if (bands & WMI_HOST_WLAN_5G_CAP) {
+	if (bands & WMI_HOST_WLAN_5GHZ_CAP) {
 		ath12k_wmi_eht_caps_parse(pdev, NL80211_BAND_5GHZ,
 					  caps->eht_cap_mac_info_5ghz,
 					  caps->eht_cap_phy_info_5ghz,
@@ -4922,7 +5078,7 @@ static u8 ath12k_wmi_ignore_num_extra_rules(struct ath12k_wmi_reg_rule_ext_param
 	for (count = 0; count < num_reg_rules; count++) {
 		start_freq = le32_get_bits(rule[count].freq_info, REG_RULE_START_FREQ);
 
-		if (start_freq >= ATH12K_MIN_6G_FREQ)
+		if (start_freq >= ATH12K_MIN_6GHZ_FREQ)
 			num_invalid_5ghz_rules++;
 	}
 
@@ -4992,9 +5148,9 @@ static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab,
 	for (i = 0; i < WMI_REG_CURRENT_MAX_AP_TYPE; i++) {
 		num_6g_reg_rules_ap[i] = reg_info->num_6g_reg_rules_ap[i];
 
-		if (num_6g_reg_rules_ap[i] > MAX_6G_REG_RULES) {
+		if (num_6g_reg_rules_ap[i] > MAX_6GHZ_REG_RULES) {
 			ath12k_warn(ab, "Num 6G reg rules for AP mode(%d) exceeds max limit (num_6g_reg_rules_ap: %d, max_rules: %d)\n",
-				    i, num_6g_reg_rules_ap[i], MAX_6G_REG_RULES);
+				    i, num_6g_reg_rules_ap[i], MAX_6GHZ_REG_RULES);
 			kfree(tb);
 			return -EINVAL;
 		}
@@ -5015,9 +5171,9 @@ static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab,
 				reg_info->num_6g_reg_rules_cl[WMI_REG_VLP_AP][i];
 		total_reg_rules += num_6g_reg_rules_cl[WMI_REG_VLP_AP][i];
 
-		if (num_6g_reg_rules_cl[WMI_REG_INDOOR_AP][i] > MAX_6G_REG_RULES ||
-		    num_6g_reg_rules_cl[WMI_REG_STD_POWER_AP][i] > MAX_6G_REG_RULES ||
-		    num_6g_reg_rules_cl[WMI_REG_VLP_AP][i] >  MAX_6G_REG_RULES) {
+		if (num_6g_reg_rules_cl[WMI_REG_INDOOR_AP][i] > MAX_6GHZ_REG_RULES ||
+		    num_6g_reg_rules_cl[WMI_REG_STD_POWER_AP][i] > MAX_6GHZ_REG_RULES ||
+		    num_6g_reg_rules_cl[WMI_REG_VLP_AP][i] >  MAX_6GHZ_REG_RULES) {
 			ath12k_warn(ab, "Num 6g client reg rules exceeds max limit, for client(type: %d)\n",
 				    i);
 			kfree(tb);
@@ -5933,30 +6089,62 @@ static void ath12k_wmi_op_ep_tx_credits(struct ath12k_base *ab)
 	wake_up(&ab->wmi_ab.tx_credits_wq);
 }
 
-static void ath12k_wmi_htc_tx_complete(struct ath12k_base *ab,
-				       struct sk_buff *skb)
+static int ath12k_reg_11d_new_cc_event(struct ath12k_base *ab, struct sk_buff *skb)
 {
-	dev_kfree_skb(skb);
-}
+	const struct wmi_11d_new_cc_event *ev;
+	struct ath12k *ar;
+	struct ath12k_pdev *pdev;
+	const void **tb;
+	int ret, i;
 
-static bool ath12k_reg_is_world_alpha(char *alpha)
-{
-	if (alpha[0] == '0' && alpha[1] == '0')
-		return true;
+	tb = ath12k_wmi_tlv_parse_alloc(ab, skb, GFP_ATOMIC);
+	if (IS_ERR(tb)) {
+		ret = PTR_ERR(tb);
+		ath12k_warn(ab, "failed to parse tlv: %d\n", ret);
+		return ret;
+	}
+
+	ev = tb[WMI_TAG_11D_NEW_COUNTRY_EVENT];
+	if (!ev) {
+		kfree(tb);
+		ath12k_warn(ab, "failed to fetch 11d new cc ev");
+		return -EPROTO;
+	}
+
+	spin_lock_bh(&ab->base_lock);
+	memcpy(&ab->new_alpha2, &ev->new_alpha2, REG_ALPHA2_LEN);
+	spin_unlock_bh(&ab->base_lock);
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI, "wmi 11d new cc %c%c\n",
+		   ab->new_alpha2[0],
+		   ab->new_alpha2[1]);
+
+	kfree(tb);
+
+	for (i = 0; i < ab->num_radios; i++) {
+		pdev = &ab->pdevs[i];
+		ar = pdev->ar;
+		ar->state_11d = ATH12K_11D_IDLE;
+		ar->ah->regd_updated = false;
+		complete(&ar->completed_11d_scan);
+	}
+
+	queue_work(ab->workqueue, &ab->update_11d_work);
 
-	if (alpha[0] == 'n' && alpha[1] == 'a')
-		return true;
+	return 0;
+}
 
-	return false;
+static void ath12k_wmi_htc_tx_complete(struct ath12k_base *ab,
+				       struct sk_buff *skb)
+{
+	dev_kfree_skb(skb);
 }
 
 static int ath12k_reg_chan_list_event(struct ath12k_base *ab, struct sk_buff *skb)
 {
-	struct ath12k_reg_info *reg_info = NULL;
-	struct ieee80211_regdomain *regd = NULL;
-	bool intersect = false;
-	int ret = 0, pdev_idx, i, j;
-	struct ath12k *ar;
+	struct ath12k_reg_info *reg_info;
+	u8 pdev_idx;
+	int ret;
 
 	reg_info = kzalloc(sizeof(*reg_info), GFP_ATOMIC);
 	if (!reg_info) {
@@ -5965,86 +6153,52 @@ static int ath12k_reg_chan_list_event(struct ath12k_base *ab, struct sk_buff *sk
 	}
 
 	ret = ath12k_pull_reg_chan_list_ext_update_ev(ab, skb, reg_info);
-
 	if (ret) {
 		ath12k_warn(ab, "failed to extract regulatory info from received event\n");
-		goto fallback;
+		goto mem_free;
 	}
 
-	if (reg_info->status_code != REG_SET_CC_STATUS_PASS) {
-		/* In case of failure to set the requested ctry,
-		 * fw retains the current regd. We print a failure info
-		 * and return from here.
+	ret = ath12k_reg_validate_reg_info(ab, reg_info);
+	if (ret == ATH12K_REG_STATUS_FALLBACK) {
+		ath12k_warn(ab, "failed to validate reg info %d\n", ret);
+		/* firmware has successfully switches to new regd but host can not
+		 * continue, so free reginfo and fallback to old regd
 		 */
-		ath12k_warn(ab, "Failed to set the requested Country regulatory setting\n");
+		goto mem_free;
+	} else if (ret == ATH12K_REG_STATUS_DROP) {
+		/* reg info is valid but we will not store it and
+		 * not going to create new regd for it
+		 */
+		ret = ATH12K_REG_STATUS_VALID;
 		goto mem_free;
 	}
 
+	/* free old reg_info if it exist */
 	pdev_idx = reg_info->phy_id;
-
-	if (pdev_idx >= ab->num_radios) {
-		/* Process the event for phy0 only if single_pdev_only
-		 * is true. If pdev_idx is valid but not 0, discard the
-		 * event. Otherwise, it goes to fallback.
-		 */
-		if (ab->hw_params->single_pdev_only &&
-		    pdev_idx < ab->hw_params->num_rxdma_per_pdev)
-			goto mem_free;
-		else
-			goto fallback;
+	if (ab->reg_info[pdev_idx]) {
+		ath12k_reg_reset_reg_info(ab->reg_info[pdev_idx]);
+		kfree(ab->reg_info[pdev_idx]);
 	}
-
-	/* Avoid multiple overwrites to default regd, during core
-	 * stop-start after mac registration.
+	/* reg_info is valid, we store it for later use
+	 * even below regd build failed
 	 */
-	if (ab->default_regd[pdev_idx] && !ab->new_regd[pdev_idx] &&
-	    !memcmp(ab->default_regd[pdev_idx]->alpha2,
-		    reg_info->alpha2, 2))
-		goto mem_free;
+	ab->reg_info[pdev_idx] = reg_info;
 
-	/* Intersect new rules with default regd if a new country setting was
-	 * requested, i.e a default regd was already set during initialization
-	 * and the regd coming from this event has a valid country info.
-	 */
-	if (ab->default_regd[pdev_idx] &&
-	    !ath12k_reg_is_world_alpha((char *)
-		ab->default_regd[pdev_idx]->alpha2) &&
-	    !ath12k_reg_is_world_alpha((char *)reg_info->alpha2))
-		intersect = true;
-
-	regd = ath12k_reg_build_regd(ab, reg_info, intersect);
-	if (!regd) {
-		ath12k_warn(ab, "failed to build regd from reg_info\n");
+	ret = ath12k_reg_handle_chan_list(ab, reg_info, WMI_VDEV_TYPE_UNSPEC,
+					  IEEE80211_REG_UNSET_AP);
+	if (ret) {
+		ath12k_warn(ab, "failed to handle chan list %d\n", ret);
 		goto fallback;
 	}
 
-	spin_lock(&ab->base_lock);
-	if (test_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags)) {
-		/* Once mac is registered, ar is valid and all CC events from
-		 * fw is considered to be received due to user requests
-		 * currently.
-		 * Free previously built regd before assigning the newly
-		 * generated regd to ar. NULL pointer handling will be
-		 * taken care by kfree itself.
-		 */
-		ar = ab->pdevs[pdev_idx].ar;
-		kfree(ab->new_regd[pdev_idx]);
-		ab->new_regd[pdev_idx] = regd;
-		queue_work(ab->workqueue, &ar->regd_update_work);
-	} else {
-		/* Multiple events for the same *ar is not expected. But we
-		 * can still clear any previously stored default_regd if we
-		 * are receiving this event for the same radio by mistake.
-		 * NULL pointer handling will be taken care by kfree itself.
-		 */
-		kfree(ab->default_regd[pdev_idx]);
-		/* This regd would be applied during mac registration */
-		ab->default_regd[pdev_idx] = regd;
-	}
-	ab->dfs_region = reg_info->dfs_region;
-	spin_unlock(&ab->base_lock);
+	goto out;
+
+mem_free:
+	ath12k_reg_reset_reg_info(reg_info);
+	kfree(reg_info);
 
-	goto mem_free;
+	if (ret == ATH12K_REG_STATUS_VALID)
+		return ret;
 
 fallback:
 	/* Fallback to older reg (by sending previous country setting
@@ -6056,20 +6210,8 @@ fallback:
 	 */
 	/* TODO: This is rare, but still should also be handled */
 	WARN_ON(1);
-mem_free:
-	if (reg_info) {
-		kfree(reg_info->reg_rules_2g_ptr);
-		kfree(reg_info->reg_rules_5g_ptr);
-		if (reg_info->is_ext_reg_event) {
-			for (i = 0; i < WMI_REG_CURRENT_MAX_AP_TYPE; i++)
-				kfree(reg_info->reg_rules_6g_ap_ptr[i]);
-
-			for (j = 0; j < WMI_REG_CURRENT_MAX_AP_TYPE; j++)
-				for (i = 0; i < WMI_REG_MAX_CLIENT_TYPE; i++)
-					kfree(reg_info->reg_rules_6g_client_ptr[j][i]);
-		}
-		kfree(reg_info);
-	}
+
+out:
 	return ret;
 }
 
@@ -6225,13 +6367,14 @@ static void ath12k_vdev_start_resp_event(struct ath12k_base *ab, struct sk_buff
 	ar->last_wmi_vdev_start_status = 0;
 
 	status = le32_to_cpu(vdev_start_resp.status);
-
 	if (WARN_ON_ONCE(status)) {
 		ath12k_warn(ab, "vdev start resp error status %d (%s)\n",
 			    status, ath12k_wmi_vdev_resp_print(status));
 		ar->last_wmi_vdev_start_status = status;
 	}
 
+	ar->max_allowed_tx_power = (s8)le32_to_cpu(vdev_start_resp.max_allowed_tx_power);
+
 	complete(&ar->vdev_setup_done);
 
 	rcu_read_unlock();
@@ -6317,13 +6460,13 @@ static void ath12k_mgmt_rx_event(struct ath12k_base *ab, struct sk_buff *skb)
 	if (rx_ev.status & WMI_RX_STATUS_ERR_MIC)
 		status->flag |= RX_FLAG_MMIC_ERROR;
 
-	if (rx_ev.chan_freq >= ATH12K_MIN_6G_FREQ &&
-	    rx_ev.chan_freq <= ATH12K_MAX_6G_FREQ) {
+	if (rx_ev.chan_freq >= ATH12K_MIN_6GHZ_FREQ &&
+	    rx_ev.chan_freq <= ATH12K_MAX_6GHZ_FREQ) {
 		status->band = NL80211_BAND_6GHZ;
 		status->freq = rx_ev.chan_freq;
 	} else if (rx_ev.channel >= 1 && rx_ev.channel <= 14) {
 		status->band = NL80211_BAND_2GHZ;
-	} else if (rx_ev.channel >= 36 && rx_ev.channel <= ATH12K_MAX_5G_CHAN) {
+	} else if (rx_ev.channel >= 36 && rx_ev.channel <= ATH12K_MAX_5GHZ_CHAN) {
 		status->band = NL80211_BAND_5GHZ;
 	} else {
 		/* Shouldn't happen unless list of advertised channels to
@@ -7216,7 +7359,7 @@ void ath12k_wmi_fw_stats_dump(struct ath12k *ar,
 	else
 		buf[len] = 0;
 
-	ath12k_debugfs_fw_stats_reset(ar);
+	ath12k_fw_stats_reset(ar);
 }
 
 static void
@@ -7335,7 +7478,7 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 					      u16 len)
 {
 	const struct wmi_stats_event *ev = parse->ev;
-	struct ath12k_fw_stats stats = {0};
+	struct ath12k_fw_stats *stats = parse->stats;
 	struct ath12k *ar;
 	struct ath12k_link_vif *arvif;
 	struct ieee80211_sta *sta;
@@ -7344,18 +7487,18 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 	int i, ret = 0;
 	const void *data = ptr;
 
-	INIT_LIST_HEAD(&stats.vdevs);
-	INIT_LIST_HEAD(&stats.bcn);
-	INIT_LIST_HEAD(&stats.pdevs);
-
 	if (!ev) {
 		ath12k_warn(ab, "failed to fetch update stats ev");
 		return -EPROTO;
 	}
 
+	if (!stats)
+		return -EINVAL;
+
 	rcu_read_lock();
 
-	ar = ath12k_mac_get_ar_by_pdev_id(ab, le32_to_cpu(ev->pdev_id));
+	stats->pdev_id = le32_to_cpu(ev->pdev_id);
+	ar = ath12k_mac_get_ar_by_pdev_id(ab, stats->pdev_id);
 	if (!ar) {
 		ath12k_warn(ab, "invalid pdev id %d in update stats event\n",
 			    le32_to_cpu(ev->pdev_id));
@@ -7398,8 +7541,8 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 		if (!dst)
 			continue;
 		ath12k_wmi_pull_vdev_stats(src, dst);
-		stats.stats_id = WMI_REQUEST_VDEV_STAT;
-		list_add_tail(&dst->list, &stats.vdevs);
+		stats->stats_id = WMI_REQUEST_VDEV_STAT;
+		list_add_tail(&dst->list, &stats->vdevs);
 	}
 	for (i = 0; i < le32_to_cpu(ev->num_bcn_stats); i++) {
 		const struct ath12k_wmi_bcn_stats_params *src;
@@ -7417,8 +7560,8 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 		if (!dst)
 			continue;
 		ath12k_wmi_pull_bcn_stats(src, dst);
-		stats.stats_id = WMI_REQUEST_BCN_STAT;
-		list_add_tail(&dst->list, &stats.bcn);
+		stats->stats_id = WMI_REQUEST_BCN_STAT;
+		list_add_tail(&dst->list, &stats->bcn);
 	}
 	for (i = 0; i < le32_to_cpu(ev->num_pdev_stats); i++) {
 		const struct ath12k_wmi_pdev_stats_params *src;
@@ -7430,7 +7573,7 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 			goto exit;
 		}
 
-		stats.stats_id = WMI_REQUEST_PDEV_STAT;
+		stats->stats_id = WMI_REQUEST_PDEV_STAT;
 
 		data += sizeof(*src);
 		len -= sizeof(*src);
@@ -7442,11 +7585,9 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 		ath12k_wmi_pull_pdev_stats_base(&src->base, dst);
 		ath12k_wmi_pull_pdev_stats_tx(&src->tx, dst);
 		ath12k_wmi_pull_pdev_stats_rx(&src->rx, dst);
-		list_add_tail(&dst->list, &stats.pdevs);
+		list_add_tail(&dst->list, &stats->pdevs);
 	}
 
-	complete(&ar->fw_stats_complete);
-	ath12k_debugfs_fw_stats_process(ar, &stats);
 exit:
 	rcu_read_unlock();
 	return ret;
@@ -7472,16 +7613,74 @@ static int ath12k_wmi_tlv_fw_stats_parse(struct ath12k_base *ab,
 	return ret;
 }
 
+static int ath12k_wmi_pull_fw_stats(struct ath12k_base *ab, struct sk_buff *skb,
+				    struct ath12k_fw_stats *stats)
+{
+	struct wmi_tlv_fw_stats_parse parse = {};
+
+	stats->stats_id = 0;
+	parse.stats = stats;
+
+	return ath12k_wmi_tlv_iter(ab, skb->data, skb->len,
+				   ath12k_wmi_tlv_fw_stats_parse,
+				   &parse);
+}
+
 static void ath12k_update_stats_event(struct ath12k_base *ab, struct sk_buff *skb)
 {
+	struct ath12k_fw_stats stats = {};
+	struct ath12k *ar;
 	int ret;
-	struct wmi_tlv_fw_stats_parse parse = {};
 
-	ret = ath12k_wmi_tlv_iter(ab, skb->data, skb->len,
-				  ath12k_wmi_tlv_fw_stats_parse,
-				  &parse);
-	if (ret)
-		ath12k_warn(ab, "failed to parse fw stats %d\n", ret);
+	INIT_LIST_HEAD(&stats.pdevs);
+	INIT_LIST_HEAD(&stats.vdevs);
+	INIT_LIST_HEAD(&stats.bcn);
+
+	ret = ath12k_wmi_pull_fw_stats(ab, skb, &stats);
+	if (ret) {
+		ath12k_warn(ab, "failed to pull fw stats: %d\n", ret);
+		goto free;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI, "event update stats");
+
+	rcu_read_lock();
+	ar = ath12k_mac_get_ar_by_pdev_id(ab, stats.pdev_id);
+	if (!ar) {
+		rcu_read_unlock();
+		ath12k_warn(ab, "failed to get ar for pdev_id %d: %d\n",
+			    stats.pdev_id, ret);
+		goto free;
+	}
+
+	spin_lock_bh(&ar->data_lock);
+
+	/* WMI_REQUEST_PDEV_STAT can be requested via .get_txpower mac ops or via
+	 * debugfs fw stats. Therefore, processing it separately.
+	 */
+	if (stats.stats_id == WMI_REQUEST_PDEV_STAT) {
+		list_splice_tail_init(&stats.pdevs, &ar->fw_stats.pdevs);
+		ar->fw_stats.fw_stats_done = true;
+		goto complete;
+	}
+
+	/* WMI_REQUEST_VDEV_STAT and WMI_REQUEST_BCN_STAT are currently requested only
+	 * via debugfs fw stats. Hence, processing these in debugfs context.
+	 */
+	ath12k_debugfs_fw_stats_process(ar, &stats);
+
+complete:
+	complete(&ar->fw_stats_complete);
+	spin_unlock_bh(&ar->data_lock);
+	rcu_read_unlock();
+
+	/* Since the stats's pdev, vdev and beacon list are spliced and reinitialised
+	 * at this point, no need to free the individual list.
+	 */
+	return;
+
+free:
+	ath12k_fw_stats_free(&stats);
 }
 
 /* PDEV_CTL_FAILSAFE_CHECK_EVENT is received from FW when the frequency scanned
@@ -8640,6 +8839,9 @@ static void ath12k_wmi_op_rx(struct ath12k_base *ab, struct sk_buff *skb)
 	case WMI_HALPHY_STATS_CTRL_PATH_EVENTID:
 		ath12k_wmi_process_tpc_stats(ab, skb);
 		break;
+	case WMI_11D_NEW_COUNTRY_EVENTID:
+		ath12k_reg_11d_new_cc_event(ab, skb);
+		break;
 	/* add Unsupported events (rare) here */
 	case WMI_TBTTOFFSET_EXT_UPDATE_EVENTID:
 	case WMI_PEER_OPER_MODE_CHANGE_EVENTID:
@@ -9643,3 +9845,69 @@ int ath12k_wmi_mlo_teardown(struct ath12k *ar)
 
 	return 0;
 }
+
+bool ath12k_wmi_supports_6ghz_cc_ext(struct ath12k *ar)
+{
+	return test_bit(WMI_TLV_SERVICE_REG_CC_EXT_EVENT_SUPPORT,
+			ar->ab->wmi_ab.svc_map) && ar->supports_6ghz;
+}
+
+int ath12k_wmi_send_vdev_set_tpc_power(struct ath12k *ar,
+				       u32 vdev_id,
+				       struct ath12k_reg_tpc_power_info *param)
+{
+	struct wmi_vdev_set_tpc_power_cmd *cmd;
+	struct ath12k_wmi_pdev *wmi = ar->wmi;
+	struct wmi_vdev_ch_power_params *ch;
+	int i, ret, len, array_len;
+	struct sk_buff *skb;
+	struct wmi_tlv *tlv;
+	u8 *ptr;
+
+	array_len = sizeof(*ch) * param->num_pwr_levels;
+	len = sizeof(*cmd) + TLV_HDR_SIZE + array_len;
+
+	skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len);
+	if (!skb)
+		return -ENOMEM;
+
+	ptr = skb->data;
+
+	cmd = (struct wmi_vdev_set_tpc_power_cmd *)ptr;
+	cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_VDEV_SET_TPC_POWER_CMD,
+						 sizeof(*cmd));
+	cmd->vdev_id = cpu_to_le32(vdev_id);
+	cmd->psd_power = cpu_to_le32(param->is_psd_power);
+	cmd->eirp_power = cpu_to_le32(param->eirp_power);
+	cmd->power_type_6ghz = cpu_to_le32(param->ap_power_type);
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
+		   "tpc vdev id %d is psd power %d eirp power %d 6 ghz power type %d\n",
+		   vdev_id, param->is_psd_power, param->eirp_power, param->ap_power_type);
+
+	ptr += sizeof(*cmd);
+	tlv = (struct wmi_tlv *)ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT, array_len);
+
+	ptr += TLV_HDR_SIZE;
+	ch = (struct wmi_vdev_ch_power_params *)ptr;
+
+	for (i = 0; i < param->num_pwr_levels; i++, ch++) {
+		ch->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_VDEV_CH_POWER_INFO,
+							sizeof(*ch));
+		ch->chan_cfreq = cpu_to_le32(param->chan_power_info[i].chan_cfreq);
+		ch->tx_power = cpu_to_le32(param->chan_power_info[i].tx_power);
+
+		ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "tpc chan freq %d TX power %d\n",
+			   ch->chan_cfreq, ch->tx_power);
+	}
+
+	ret = ath12k_wmi_cmd_send(wmi, skb, WMI_VDEV_SET_TPC_POWER_CMDID);
+	if (ret) {
+		ath12k_warn(ar->ab, "failed to send WMI_VDEV_SET_TPC_POWER_CMDID\n");
+		dev_kfree_skb(skb);
+		return ret;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 1ba33e30ddd2..ac18f75e0449 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -26,6 +26,7 @@ struct ath12k_base;
 struct ath12k;
 struct ath12k_link_vif;
 struct ath12k_fw_stats;
+struct ath12k_reg_tpc_power_info;
 
 /* There is no signed version of __le32, so for a temporary solution come
  * up with our own version. The idea is from fs/ntfs/endian.h.
@@ -216,9 +217,9 @@ enum wmi_host_hw_mode_priority {
 };
 
 enum WMI_HOST_WLAN_BAND {
-	WMI_HOST_WLAN_2G_CAP	= 1,
-	WMI_HOST_WLAN_5G_CAP	= 2,
-	WMI_HOST_WLAN_2G_5G_CAP	= 3,
+	WMI_HOST_WLAN_2GHZ_CAP		= 1,
+	WMI_HOST_WLAN_5GHZ_CAP		= 2,
+	WMI_HOST_WLAN_2GHZ_5GHZ_CAP	= 3,
 };
 
 enum wmi_cmd_group {
@@ -386,6 +387,22 @@ enum wmi_tlv_cmd_id {
 	WMI_VDEV_SET_CUSTOM_AGGR_SIZE_CMDID,
 	WMI_VDEV_ENCRYPT_DECRYPT_DATA_REQ_CMDID,
 	WMI_VDEV_ADD_MAC_ADDR_TO_RX_FILTER_CMDID,
+	WMI_VDEV_SET_ARP_STAT_CMDID,
+	WMI_VDEV_GET_ARP_STAT_CMDID,
+	WMI_VDEV_GET_TX_POWER_CMDID,
+	WMI_VDEV_LIMIT_OFFCHAN_CMDID,
+	WMI_VDEV_SET_CUSTOM_SW_RETRY_TH_CMDID,
+	WMI_VDEV_CHAINMASK_CONFIG_CMDID,
+	WMI_VDEV_GET_BCN_RECEPTION_STATS_CMDID,
+	WMI_VDEV_GET_MWS_COEX_INFO_CMDID,
+	WMI_VDEV_DELETE_ALL_PEER_CMDID,
+	WMI_VDEV_BSS_MAX_IDLE_TIME_CMDID,
+	WMI_VDEV_AUDIO_SYNC_TRIGGER_CMDID,
+	WMI_VDEV_AUDIO_SYNC_QTIMER_CMDID,
+	WMI_VDEV_SET_PCL_CMDID,
+	WMI_VDEV_GET_BIG_DATA_CMDID,
+	WMI_VDEV_GET_BIG_DATA_P2_CMDID,
+	WMI_VDEV_SET_TPC_POWER_CMDID,
 	WMI_PEER_CREATE_CMDID = WMI_TLV_CMD(WMI_GRP_PEER),
 	WMI_PEER_DELETE_CMDID,
 	WMI_PEER_FLUSH_TIDS_CMDID,
@@ -1955,6 +1972,8 @@ enum wmi_tlv_tag {
 	WMI_TAG_TPC_STATS_REG_PWR_ALLOWED,
 	WMI_TAG_TPC_STATS_RATES_ARRAY,
 	WMI_TAG_TPC_STATS_CTL_PWR_TABLE_EVENT,
+	WMI_TAG_VDEV_SET_TPC_POWER_CMD = 0x3B5,
+	WMI_TAG_VDEV_CH_POWER_INFO,
 	WMI_TAG_EHT_RATE_SET = 0x3C4,
 	WMI_TAG_DCS_AWGN_INT_TYPE = 0x3C5,
 	WMI_TAG_MLO_TX_SEND_PARAMS,
@@ -2201,6 +2220,8 @@ enum wmi_tlv_service {
 
 	WMI_MAX_EXT_SERVICE = 256,
 
+	WMI_TLV_SERVICE_EXT_TPC_REG_SUPPORT = 280,
+
 	WMI_TLV_SERVICE_REG_CC_EXT_EVENT_SUPPORT = 281,
 
 	WMI_TLV_SERVICE_11BE = 289,
@@ -2461,6 +2482,7 @@ struct wmi_init_cmd {
 } __packed;
 
 #define WMI_RSRC_CFG_HOST_SVC_FLAG_REG_CC_EXT_SUPPORT_BIT 4
+#define WMI_RSRC_CFG_HOST_SVC_FLAG_REO_QREF_SUPPORT_BIT   12
 #define WMI_RSRC_CFG_FLAGS2_RX_PEER_METADATA_VERSION		GENMASK(5, 4)
 #define WMI_RSRC_CFG_FLAG1_BSS_CHANNEL_INFO_64	BIT(5)
 #define WMI_RSRC_CFG_FLAGS2_CALC_NEXT_DTIM_COUNT_SET      BIT(9)
@@ -2690,8 +2712,8 @@ enum wmi_channel_width {
  * 2 - index for 160 MHz, first 3 bytes valid
  * 3 - index for 320 MHz, first 3 bytes valid
  */
-#define WMI_MAX_EHT_SUPP_MCS_2G_SIZE  2
-#define WMI_MAX_EHT_SUPP_MCS_5G_SIZE  4
+#define WMI_MAX_EHT_SUPP_MCS_2GHZ_SIZE  2
+#define WMI_MAX_EHT_SUPP_MCS_5GHZ_SIZE  4
 
 #define WMI_EHTCAP_TXRX_MCS_NSS_IDX_80    0
 #define WMI_EHTCAP_TXRX_MCS_NSS_IDX_160   1
@@ -2730,8 +2752,8 @@ struct ath12k_wmi_caps_ext_params {
 	struct ath12k_wmi_ppe_threshold_params eht_ppet_2ghz;
 	struct ath12k_wmi_ppe_threshold_params eht_ppet_5ghz;
 	__le32 eht_cap_info_internal;
-	__le32 eht_supp_mcs_ext_2ghz[WMI_MAX_EHT_SUPP_MCS_2G_SIZE];
-	__le32 eht_supp_mcs_ext_5ghz[WMI_MAX_EHT_SUPP_MCS_5G_SIZE];
+	__le32 eht_supp_mcs_ext_2ghz[WMI_MAX_EHT_SUPP_MCS_2GHZ_SIZE];
+	__le32 eht_supp_mcs_ext_5ghz[WMI_MAX_EHT_SUPP_MCS_5GHZ_SIZE];
 	__le32 eml_capability;
 	__le32 mld_capability;
 } __packed;
@@ -3754,6 +3776,7 @@ struct peer_assoc_mlo_params {
 	u32 ieee_link_id;
 	u8 num_partner_links;
 	struct wmi_ml_partner_info partner_info[ATH12K_WMI_MLO_MAX_LINKS];
+	u16 eml_cap;
 };
 
 struct wmi_rate_set_arg {
@@ -3832,6 +3855,7 @@ struct ath12k_wmi_peer_assoc_arg {
 	u32 punct_bitmap;
 	bool is_assoc;
 	struct peer_assoc_mlo_params ml;
+	bool eht_disable_mcs15;
 };
 
 #define ATH12K_WMI_FLAG_MLO_ENABLED			BIT(0)
@@ -4026,6 +4050,28 @@ struct wmi_init_country_cmd {
 	} cc_info;
 } __packed;
 
+struct wmi_11d_scan_start_arg {
+	u32 vdev_id;
+	u32 scan_period_msec;
+	u32 start_interval_msec;
+};
+
+struct wmi_11d_scan_start_cmd {
+	__le32 tlv_header;
+	__le32 vdev_id;
+	__le32 scan_period_msec;
+	__le32 start_interval_msec;
+} __packed;
+
+struct wmi_11d_scan_stop_cmd {
+	__le32 tlv_header;
+	__le32 vdev_id;
+} __packed;
+
+struct wmi_11d_new_cc_event {
+	__le32 new_alpha2;
+} __packed;
+
 struct wmi_delba_send_cmd {
 	__le32 tlv_header;
 	__le32 vdev_id;
@@ -4108,7 +4154,17 @@ struct ath12k_wmi_eht_rate_set_params {
 
 #define MAX_REG_RULES 10
 #define REG_ALPHA2_LEN 2
-#define MAX_6G_REG_RULES 5
+#define MAX_6GHZ_REG_RULES 5
+
+struct wmi_set_current_country_arg {
+	u8 alpha2[REG_ALPHA2_LEN];
+};
+
+struct wmi_set_current_country_cmd {
+	__le32 tlv_header;
+	__le32 pdev_id;
+	__le32 new_alpha2;
+} __packed;
 
 enum wmi_start_event_param {
 	WMI_VDEV_START_RESP_EVENT = 0,
@@ -4129,6 +4185,7 @@ struct wmi_vdev_start_resp_event {
 	};
 	__le32 cfgd_tx_streams;
 	__le32 cfgd_rx_streams;
+	__le32 max_allowed_tx_power;
 } __packed;
 
 /* VDEV start response status codes */
@@ -4474,6 +4531,7 @@ struct ath12k_wmi_target_cap_arg {
 };
 
 enum wmi_vdev_type {
+	WMI_VDEV_TYPE_UNSPEC  = 0,
 	WMI_VDEV_TYPE_AP      = 1,
 	WMI_VDEV_TYPE_STA     = 2,
 	WMI_VDEV_TYPE_IBSS    = 3,
@@ -5904,6 +5962,41 @@ struct wmi_tpc_stats_arg {
 	struct wmi_tpc_ctl_pwr_table_arg ctl_array;
 };
 
+struct wmi_vdev_ch_power_params {
+	__le32 tlv_header;
+
+	/* Channel center frequency (MHz) */
+	__le32 chan_cfreq;
+
+	/* Unit: dBm, either PSD/EIRP power for this frequency or
+	 * incremental for non-PSD BW
+	 */
+	__le32 tx_power;
+} __packed;
+
+struct wmi_vdev_set_tpc_power_cmd {
+	__le32 tlv_header;
+	__le32 vdev_id;
+
+	/* Value: 0 or 1, is PSD power or not */
+	__le32 psd_power;
+
+	 /* Maximum EIRP power (dBm units), valid only if power is PSD */
+	__le32 eirp_power;
+
+	/* Type: WMI_6GHZ_REG_TYPE, used for halphy CTL lookup */
+	__le32 power_type_6ghz;
+
+	/* This fixed_param TLV is followed by the below TLVs:
+	 * num_pwr_levels of wmi_vdev_ch_power_info
+	 * For PSD power, it is the PSD/EIRP power of the frequency (20 MHz chunks).
+	 * For non-PSD power, the power values are for 20, 40, and till
+	 * BSS BW power levels.
+	 * The num_pwr_levels will be checked by sw how many elements present
+	 * in the variable-length array.
+	 */
+} __packed;
+
 void ath12k_wmi_init_qcn9274(struct ath12k_base *ab,
 			     struct ath12k_wmi_resource_config_arg *config);
 void ath12k_wmi_init_wcn7850(struct ath12k_base *ab,
@@ -5990,11 +6083,17 @@ int ath12k_wmi_send_bcn_offload_control_cmd(struct ath12k *ar,
 					    u32 vdev_id, u32 bcn_ctrl_op);
 int ath12k_wmi_send_init_country_cmd(struct ath12k *ar,
 				     struct ath12k_wmi_init_country_arg *arg);
+int
+ath12k_wmi_send_set_current_country_cmd(struct ath12k *ar,
+					struct wmi_set_current_country_arg *arg);
 int ath12k_wmi_peer_rx_reorder_queue_setup(struct ath12k *ar,
 					   int vdev_id, const u8 *addr,
 					   dma_addr_t paddr, u8 tid,
 					   u8 ba_window_size_valid,
 					   u32 ba_window_size);
+int ath12k_wmi_send_11d_scan_start_cmd(struct ath12k *ar,
+				       struct wmi_11d_scan_start_arg *arg);
+int ath12k_wmi_send_11d_scan_stop_cmd(struct ath12k *ar, u32 vdev_id);
 int
 ath12k_wmi_rx_reord_queue_remove(struct ath12k *ar,
 				 struct ath12k_wmi_rx_reorder_queue_remove_arg *arg);
@@ -6092,5 +6191,9 @@ int ath12k_wmi_mlo_teardown(struct ath12k *ar);
 void ath12k_wmi_fw_stats_dump(struct ath12k *ar,
 			      struct ath12k_fw_stats *fw_stats, u32 stats_id,
 			      char *buf);
+bool ath12k_wmi_supports_6ghz_cc_ext(struct ath12k *ar);
+int ath12k_wmi_send_vdev_set_tpc_power(struct ath12k *ar,
+				       u32 vdev_id,
+				       struct ath12k_reg_tpc_power_info *param);
 
 #endif
diff --git a/drivers/net/wireless/ath/ath9k/ahb.c b/drivers/net/wireless/ath/ath9k/ahb.c
index d4805e02b927..49b7ab26c477 100644
--- a/drivers/net/wireless/ath/ath9k/ahb.c
+++ b/drivers/net/wireless/ath/ath9k/ahb.c
@@ -74,7 +74,6 @@ static int ath_ahb_probe(struct platform_device *pdev)
 	void __iomem *mem;
 	struct ath_softc *sc;
 	struct ieee80211_hw *hw;
-	struct resource *res;
 	const struct platform_device_id *id = platform_get_device_id(pdev);
 	int irq;
 	int ret = 0;
@@ -86,16 +85,10 @@ static int ath_ahb_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res == NULL) {
-		dev_err(&pdev->dev, "no memory resource found\n");
-		return -ENXIO;
-	}
-
-	mem = devm_ioremap(&pdev->dev, res->start, resource_size(res));
-	if (mem == NULL) {
+	mem = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(mem)) {
 		dev_err(&pdev->dev, "ioremap failed\n");
-		return -ENOMEM;
+		return PTR_ERR(mem);
 	}
 
 	irq = platform_get_irq(pdev, 0);
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
index 547634f82183..81fa7cbad892 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
@@ -290,6 +290,9 @@ void ath9k_htc_swba(struct ath9k_htc_priv *priv,
 	struct ath_common *common = ath9k_hw_common(priv->ah);
 	int slot;
 
+	if (!priv->cur_beacon_conf.enable_beacon)
+		return;
+
 	if (swba->beacon_pending != 0) {
 		priv->beacon.bmisscnt++;
 		if (priv->beacon.bmisscnt > BSTUCK_THRESHOLD) {
diff --git a/drivers/net/wireless/ath/carl9170/fw.c b/drivers/net/wireless/ath/carl9170/fw.c
index 4c1aecd1163c..419f5530f885 100644
--- a/drivers/net/wireless/ath/carl9170/fw.c
+++ b/drivers/net/wireless/ath/carl9170/fw.c
@@ -15,7 +15,7 @@
 #include "fwcmd.h"
 #include "version.h"
 
-static const u8 otus_magic[4] = { OTUS_MAGIC };
+static const u8 otus_magic[4] __nonstring = { OTUS_MAGIC };
 
 static const void *carl9170_fw_find_desc(struct ar9170 *ar, const u8 descid[4],
 	const unsigned int len, const u8 compatible_revision)
diff --git a/drivers/net/wireless/ath/carl9170/tx.c b/drivers/net/wireless/ath/carl9170/tx.c
index 0226c31a6cae..b7717f9e1e9b 100644
--- a/drivers/net/wireless/ath/carl9170/tx.c
+++ b/drivers/net/wireless/ath/carl9170/tx.c
@@ -366,8 +366,7 @@ static void carl9170_tx_shift_bm(struct ar9170 *ar,
 	if (WARN_ON_ONCE(off >= CARL9170_BAW_BITS))
 		return;
 
-	if (!bitmap_empty(tid_info->bitmap, off))
-		off = find_first_bit(tid_info->bitmap, off);
+	off = min(off, find_first_bit(tid_info->bitmap, off));
 
 	tid_info->bsn += off;
 	tid_info->bsn &= 0x0fff;
diff --git a/drivers/net/wireless/ath/wcn36xx/testmode.c b/drivers/net/wireless/ath/wcn36xx/testmode.c
index e5142c052985..d7a2a483cbc4 100644
--- a/drivers/net/wireless/ath/wcn36xx/testmode.c
+++ b/drivers/net/wireless/ath/wcn36xx/testmode.c
@@ -56,7 +56,7 @@ static int wcn36xx_tm_cmd_ptt(struct wcn36xx *wcn, struct ieee80211_vif *vif,
 	msg = buf;
 
 	wcn36xx_dbg(WCN36XX_DBG_TESTMODE,
-		    "testmode cmd wmi msg_id 0x%04X msg_len %d buf %pK buf_len %d\n",
+		    "testmode cmd wmi msg_id 0x%04X msg_len %d buf %p buf_len %d\n",
 		   msg->msg_id, msg->msg_body_length,
 		   buf, buf_len);
 
diff --git a/drivers/net/wireless/ath/wil6210/txrx.h b/drivers/net/wireless/ath/wil6210/txrx.h
index 689f68d89a44..fff8b7f8abc5 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.h
+++ b/drivers/net/wireless/ath/wil6210/txrx.h
@@ -7,6 +7,7 @@
 #ifndef WIL6210_TXRX_H
 #define WIL6210_TXRX_H
 
+#include <net/sock.h>
 #include "wil6210.h"
 #include "txrx_edma.h"
 
@@ -616,8 +617,7 @@ static inline bool wil_need_txstat(struct sk_buff *skb)
 {
 	const u8 *da = wil_skb_get_da(skb);
 
-	return is_unicast_ether_addr(da) && skb->sk &&
-	       (skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS);
+	return is_unicast_ether_addr(da) && sk_requests_wifi_status(skb->sk);
 }
 
 static inline void wil_consume_skb(struct sk_buff *skb, bool acked)
diff --git a/drivers/net/wireless/atmel/at76c50x-usb.c b/drivers/net/wireless/atmel/at76c50x-usb.c
index 4f01189b7c4b..6842c2b02b39 100644
--- a/drivers/net/wireless/atmel/at76c50x-usb.c
+++ b/drivers/net/wireless/atmel/at76c50x-usb.c
@@ -2552,7 +2552,7 @@ static void at76_disconnect(struct usb_interface *interface)
 
 	wiphy_info(priv->hw->wiphy, "disconnecting\n");
 	at76_delete_device(priv);
-	usb_put_dev(priv->udev);
+	usb_put_dev(interface_to_usbdev(interface));
 	dev_info(&interface->dev, "disconnected\n");
 }
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 4b70845e1a26..dc2383faddd1 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -74,7 +74,6 @@
 #define VNDR_IE_HDR_SIZE		12
 #define VNDR_IE_PARSE_LIMIT		5
 
-#define	DOT11_MGMT_HDR_LEN		24	/* d11 management header len */
 #define	DOT11_BCN_PRB_FIXED_LEN		12	/* beacon/probe fixed length */
 
 #define BRCMF_SCAN_JOIN_ACTIVE_DWELL_TIME_MS	320
@@ -1945,17 +1944,22 @@ static s32 brcmf_set_wpa_version(struct net_device *ndev,
 	struct brcmf_cfg80211_profile *profile = ndev_to_prof(ndev);
 	struct brcmf_pub *drvr = ifp->drvr;
 	struct brcmf_cfg80211_security *sec;
-	s32 val = 0;
-	s32 err = 0;
+	s32 val;
+	s32 err;
 
-	if (sme->crypto.wpa_versions & NL80211_WPA_VERSION_1)
+	if (sme->crypto.wpa_versions & NL80211_WPA_VERSION_1) {
 		val = WPA_AUTH_PSK | WPA_AUTH_UNSPECIFIED;
-	else if (sme->crypto.wpa_versions & NL80211_WPA_VERSION_2)
-		val = WPA2_AUTH_PSK | WPA2_AUTH_UNSPECIFIED;
-	else if (sme->crypto.wpa_versions & NL80211_WPA_VERSION_3)
+	} else if (sme->crypto.wpa_versions & NL80211_WPA_VERSION_2) {
+		if (drvr->bus_if->fwvid == BRCMF_FWVENDOR_CYW &&
+		    sme->crypto.akm_suites[0] == WLAN_AKM_SUITE_SAE)
+			val = WPA3_AUTH_SAE_PSK;
+		else
+			val = WPA2_AUTH_PSK | WPA2_AUTH_UNSPECIFIED;
+	} else if (sme->crypto.wpa_versions & NL80211_WPA_VERSION_3) {
 		val = WPA3_AUTH_SAE_PSK;
-	else
+	} else {
 		val = WPA_AUTH_DISABLED;
+	}
 	brcmf_dbg(CONN, "setting wpa_auth to 0x%0x\n", val);
 	err = brcmf_fil_bsscfg_int_set(ifp, "wpa_auth", val);
 	if (err) {
@@ -2163,28 +2167,25 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme)
 		switch (sme->crypto.akm_suites[0]) {
 		case WLAN_AKM_SUITE_SAE:
 			val = WPA3_AUTH_SAE_PSK;
-			if (sme->crypto.sae_pwd) {
-				brcmf_dbg(INFO, "using SAE offload\n");
-				profile->use_fwsup = BRCMF_PROFILE_FWSUP_SAE;
-			}
 			break;
 		case WLAN_AKM_SUITE_FT_OVER_SAE:
 			val = WPA3_AUTH_SAE_PSK | WPA2_AUTH_FT;
 			profile->is_ft = true;
-			if (sme->crypto.sae_pwd) {
-				brcmf_dbg(INFO, "using SAE offload\n");
-				profile->use_fwsup = BRCMF_PROFILE_FWSUP_SAE;
-			}
 			break;
 		default:
 			bphy_err(drvr, "invalid akm suite (%d)\n",
 				 sme->crypto.akm_suites[0]);
 			return -EINVAL;
 		}
+		if (sme->crypto.sae_pwd) {
+			profile->use_fwsup = BRCMF_PROFILE_FWSUP_SAE;
+		}
 	}
 
 	if (profile->use_fwsup == BRCMF_PROFILE_FWSUP_1X)
 		brcmf_dbg(INFO, "using 1X offload\n");
+	if (profile->use_fwsup == BRCMF_PROFILE_FWSUP_SAE)
+		brcmf_dbg(INFO, "using SAE offload\n");
 
 	if (!brcmf_feat_is_enabled(ifp, BRCMF_FEAT_MFP))
 		goto skip_mfp_config;
@@ -2221,7 +2222,7 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme)
 	brcmf_fil_bsscfg_int_set(netdev_priv(ndev), "mfp", mfp);
 
 skip_mfp_config:
-	brcmf_dbg(CONN, "setting wpa_auth to %d\n", val);
+	brcmf_dbg(CONN, "setting wpa_auth to 0x%0x\n", val);
 	err = brcmf_fil_bsscfg_int_set(netdev_priv(ndev), "wpa_auth", val);
 	if (err) {
 		bphy_err(drvr, "could not set wpa_auth (%d)\n", err);
@@ -5509,7 +5510,7 @@ brcmf_cfg80211_update_mgmt_frame_registrations(struct wiphy *wiphy,
 }
 
 
-static int
+int
 brcmf_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 		       struct cfg80211_mgmt_tx_params *params, u64 *cookie)
 {
@@ -5616,6 +5617,7 @@ brcmf_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 exit:
 	return err;
 }
+BRCMF_EXPORT_SYMBOL_GPL(brcmf_cfg80211_mgmt_tx);
 
 static int brcmf_cfg80211_set_cqm_rssi_range_config(struct wiphy *wiphy,
 						    struct net_device *ndev,
@@ -6009,6 +6011,7 @@ struct brcmf_cfg80211_vif *brcmf_alloc_vif(struct brcmf_cfg80211_info *cfg,
 
 	vif->wdev.wiphy = cfg->wiphy;
 	vif->wdev.iftype = type;
+	init_completion(&vif->mgmt_tx);
 
 	brcmf_init_prof(&vif->profile);
 
@@ -6760,6 +6763,8 @@ static void brcmf_register_event_handlers(struct brcmf_cfg80211_info *cfg)
 	brcmf_fweh_register(cfg->pub, BRCMF_E_PSK_SUP,
 			    brcmf_notify_connect_status);
 	brcmf_fweh_register(cfg->pub, BRCMF_E_RSSI, brcmf_notify_rssi);
+
+	brcmf_fwvid_register_event_handlers(cfg->pub);
 }
 
 static void brcmf_deinit_priv_mem(struct brcmf_cfg80211_info *cfg)
@@ -7346,6 +7351,7 @@ brcmf_txrx_stypes[NUM_NL80211_IFTYPES] = {
 	[NL80211_IFTYPE_STATION] = {
 		.tx = 0xffff,
 		.rx = BIT(IEEE80211_STYPE_ACTION >> 4) |
+		      BIT(IEEE80211_STYPE_AUTH >> 4) |
 		      BIT(IEEE80211_STYPE_PROBE_REQ >> 4)
 	},
 	[NL80211_IFTYPE_P2P_CLIENT] = {
@@ -7653,6 +7659,8 @@ static int brcmf_setup_wiphy(struct wiphy *wiphy, struct brcmf_if *ifp)
 			wiphy_ext_feature_set(wiphy,
 					      NL80211_EXT_FEATURE_SAE_OFFLOAD_AP);
 	}
+	if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_SAE_EXT))
+		wiphy->features |= NL80211_FEATURE_SAE;
 	wiphy->mgmt_stypes = brcmf_txrx_stypes;
 	wiphy->max_remain_on_channel_duration = 5000;
 	if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_PNO)) {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
index 2abae8894614..b83485ec7b87 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
@@ -13,6 +13,8 @@
 #include "fwil_types.h"
 #include "p2p.h"
 
+#define	DOT11_MGMT_HDR_LEN		24	/* d11 management header len */
+
 #define BRCMF_SCAN_IE_LEN_MAX		2048
 
 #define WL_NUM_SCAN_MAX			10
@@ -142,6 +144,21 @@ enum brcmf_profile_fwauth {
 };
 
 /**
+ * enum brcmf_mgmt_tx_status - mgmt frame tx status
+ *
+ * @BRCMF_MGMT_TX_ACK: mgmt frame acked
+ * @BRCMF_MGMT_TX_NOACK: mgmt frame not acked
+ * @BRCMF_MGMT_TX_OFF_CHAN_COMPLETED: off-channel complete
+ * @BRCMF_MGMT_TX_SEND_FRAME: mgmt frame tx is in progres
+ */
+enum brcmf_mgmt_tx_status {
+	BRCMF_MGMT_TX_ACK,
+	BRCMF_MGMT_TX_NOACK,
+	BRCMF_MGMT_TX_OFF_CHAN_COMPLETED,
+	BRCMF_MGMT_TX_SEND_FRAME
+};
+
+/**
  * struct brcmf_cfg80211_profile - profile information.
  *
  * @bssid: bssid of joined/joining ibss.
@@ -211,6 +228,9 @@ struct vif_saved_ie {
  * @profile: profile information.
  * @sme_state: SME state using enum brcmf_vif_status bits.
  * @list: linked list.
+ * @mgmt_tx: completion for management frame transmit.
+ * @mgmt_tx_status: status of last management frame sent to firmware.
+ * @mgmt_tx_id:
  * @mgmt_rx_reg: registered rx mgmt frame types.
  * @mbss: Multiple BSS type, set if not first AP (not relevant for P2P).
  * @cqm_rssi_low: Lower RSSI limit for CQM monitoring
@@ -224,6 +244,9 @@ struct brcmf_cfg80211_vif {
 	unsigned long sme_state;
 	struct vif_saved_ie saved_ie;
 	struct list_head list;
+	struct completion mgmt_tx;
+	unsigned long mgmt_tx_status;
+	u32 mgmt_tx_id;
 	u16 mgmt_rx_reg;
 	bool mbss;
 	int is_11d;
@@ -468,5 +491,7 @@ void brcmf_abort_scanning(struct brcmf_cfg80211_info *cfg);
 void brcmf_cfg80211_free_netdev(struct net_device *ndev);
 
 int brcmf_set_wsec(struct brcmf_if *ifp, const u8 *key, u16 key_len, u16 flags);
+int brcmf_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
+			   struct cfg80211_mgmt_tx_params *params, u64 *cookie);
 
 #endif /* BRCMFMAC_CFG80211_H */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
index cfcf01eb0daa..75f101622db1 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
@@ -491,6 +491,7 @@ void __brcmf_dbg(u32 level, const char *func, const char *fmt, ...)
 	trace_brcmf_dbg(level, func, &vaf);
 	va_end(args);
 }
+BRCMF_EXPORT_SYMBOL_GPL(__brcmf_dbg);
 #endif
 
 static void brcmf_mp_attach(void)
@@ -561,8 +562,10 @@ struct brcmf_mp_device *brcmf_get_module_param(struct device *dev,
 	if (!found) {
 		/* No platform data for this device, try OF and DMI data */
 		brcmf_dmi_probe(settings, chip, chiprev);
-		if (brcmf_of_probe(dev, bus_type, settings) == -EPROBE_DEFER)
+		if (brcmf_of_probe(dev, bus_type, settings) == -EPROBE_DEFER) {
+			kfree(settings);
 			return ERR_PTR(-EPROBE_DEFER);
+		}
 		brcmf_acpi_probe(dev, bus_type, settings);
 	}
 	return settings;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index 3d63010ae079..04f41c09deca 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -1363,6 +1363,8 @@ int brcmf_attach(struct device *dev)
 	brcmf_fweh_register(drvr, BRCMF_E_PSM_WATCHDOG,
 			    brcmf_psm_watchdog_notify);
 
+	brcmf_fwvid_get_cfg80211_ops(drvr);
+
 	ret = brcmf_bus_started(drvr, drvr->ops);
 	if (ret != 0) {
 		bphy_err(drvr, "dongle is not responding: err=%d\n", ret);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c
index 9a4837881486..c9537fb597ce 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c
@@ -8,11 +8,21 @@
 #include <bus.h>
 #include <fwvid.h>
 #include <fwil.h>
+#include <fweh.h>
 
 #include "vops.h"
+#include "fwil_types.h"
 
+/* event definitions */
+#define BRCMF_CYW_E_EXT_AUTH_REQ	187
+#define BRCMF_CYW_E_EXT_AUTH_FRAME_RX	188
+#define BRCMF_CYW_E_MGMT_FRAME_TXS	189
+#define BRCMF_CYW_E_MGMT_FRAME_TXS_OC	190
 #define BRCMF_CYW_E_LAST		197
 
+#define MGMT_AUTH_FRAME_DWELL_TIME	4000
+#define MGMT_AUTH_FRAME_WAIT_TIME	(MGMT_AUTH_FRAME_DWELL_TIME + 100)
+
 static int brcmf_cyw_set_sae_pwd(struct brcmf_if *ifp,
 				 struct cfg80211_crypto_settings *crypto)
 {
@@ -39,6 +49,19 @@ static int brcmf_cyw_set_sae_pwd(struct brcmf_if *ifp,
 	return err;
 }
 
+static const struct brcmf_fweh_event_map brcmf_cyw_event_map = {
+	.items = {
+		{ BRCMF_E_EXT_AUTH_REQ, BRCMF_CYW_E_EXT_AUTH_REQ },
+		{ BRCMF_E_EXT_AUTH_FRAME_RX, BRCMF_CYW_E_EXT_AUTH_FRAME_RX },
+		{ BRCMF_E_MGMT_FRAME_TXSTATUS, BRCMF_CYW_E_MGMT_FRAME_TXS },
+		{
+			BRCMF_E_MGMT_FRAME_OFFCHAN_DONE,
+			BRCMF_CYW_E_MGMT_FRAME_TXS_OC
+		},
+	},
+	.n_items = 4
+};
+
 static int brcmf_cyw_alloc_fweh_info(struct brcmf_pub *drvr)
 {
 	struct brcmf_fweh_info *fweh;
@@ -49,11 +72,296 @@ static int brcmf_cyw_alloc_fweh_info(struct brcmf_pub *drvr)
 		return -ENOMEM;
 
 	fweh->num_event_codes = BRCMF_CYW_E_LAST;
+	fweh->event_map = &brcmf_cyw_event_map;
 	drvr->fweh = fweh;
 	return 0;
 }
 
+static int brcmf_cyw_activate_events(struct brcmf_if *ifp)
+{
+	struct brcmf_fweh_info *fweh = ifp->drvr->fweh;
+	struct brcmf_eventmsgs_ext *eventmask_msg;
+	u32 msglen;
+	int err;
+
+	msglen = sizeof(*eventmask_msg) + fweh->event_mask_len;
+	eventmask_msg = kzalloc(msglen, GFP_KERNEL);
+	if (!eventmask_msg)
+		return -ENOMEM;
+	eventmask_msg->ver = EVENTMSGS_VER;
+	eventmask_msg->command = CYW_EVENTMSGS_SET_MASK;
+	eventmask_msg->len = fweh->event_mask_len;
+	memcpy(eventmask_msg->mask, fweh->event_mask, fweh->event_mask_len);
+
+	err = brcmf_fil_iovar_data_set(ifp, "event_msgs_ext", eventmask_msg,
+				       msglen);
+	kfree(eventmask_msg);
+	return err;
+}
+
+static
+int brcmf_cyw_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
+		      struct cfg80211_mgmt_tx_params *params, u64 *cookie)
+{
+	struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
+	struct ieee80211_channel *chan = params->chan;
+	struct brcmf_pub *drvr = cfg->pub;
+	const u8 *buf = params->buf;
+	size_t len = params->len;
+	const struct ieee80211_mgmt *mgmt;
+	struct brcmf_cfg80211_vif *vif;
+	s32 err = 0;
+	bool ack = false;
+	s32 chan_nr;
+	u32 freq;
+	struct brcmf_mf_params_le *mf_params;
+	u32 mf_params_len;
+	s32 ready;
+
+	brcmf_dbg(TRACE, "Enter\n");
+
+	mgmt = (const struct ieee80211_mgmt *)buf;
+
+	if (!ieee80211_is_auth(mgmt->frame_control))
+		return brcmf_cfg80211_mgmt_tx(wiphy, wdev, params, cookie);
+
+	*cookie = 0;
+	vif = container_of(wdev, struct brcmf_cfg80211_vif, wdev);
+
+	reinit_completion(&vif->mgmt_tx);
+	clear_bit(BRCMF_MGMT_TX_ACK, &vif->mgmt_tx_status);
+	clear_bit(BRCMF_MGMT_TX_NOACK, &vif->mgmt_tx_status);
+	clear_bit(BRCMF_MGMT_TX_OFF_CHAN_COMPLETED,
+		  &vif->mgmt_tx_status);
+	mf_params_len = offsetof(struct brcmf_mf_params_le, data) +
+			(len - DOT11_MGMT_HDR_LEN);
+	mf_params = kzalloc(mf_params_len, GFP_KERNEL);
+	if (!mf_params)
+		return -ENOMEM;
+
+	mf_params->dwell_time = cpu_to_le32(MGMT_AUTH_FRAME_DWELL_TIME);
+	mf_params->len = cpu_to_le16(len - DOT11_MGMT_HDR_LEN);
+	mf_params->frame_control = mgmt->frame_control;
+
+	if (chan)
+		freq = chan->center_freq;
+	else
+		brcmf_fil_cmd_int_get(vif->ifp, BRCMF_C_GET_CHANNEL,
+				      &freq);
+	chan_nr = ieee80211_frequency_to_channel(freq);
+	mf_params->channel = cpu_to_le16(chan_nr);
+	memcpy(&mf_params->da[0], &mgmt->da[0], ETH_ALEN);
+	memcpy(&mf_params->bssid[0], &mgmt->bssid[0], ETH_ALEN);
+	mf_params->packet_id = cpu_to_le32(*cookie);
+	memcpy(mf_params->data, &buf[DOT11_MGMT_HDR_LEN],
+	       le16_to_cpu(mf_params->len));
+
+	brcmf_dbg(TRACE, "Auth frame, cookie=%d, fc=%04x, len=%d, channel=%d\n",
+		  le32_to_cpu(mf_params->packet_id),
+		  le16_to_cpu(mf_params->frame_control),
+		  le16_to_cpu(mf_params->len), chan_nr);
+
+	vif->mgmt_tx_id = le32_to_cpu(mf_params->packet_id);
+	set_bit(BRCMF_MGMT_TX_SEND_FRAME, &vif->mgmt_tx_status);
+
+	err = brcmf_fil_bsscfg_data_set(vif->ifp, "mgmt_frame",
+					mf_params, mf_params_len);
+	if (err) {
+		bphy_err(drvr, "Failed to send Auth frame: err=%d\n",
+			 err);
+		goto tx_status;
+	}
+
+	ready = wait_for_completion_timeout(&vif->mgmt_tx,
+					    MGMT_AUTH_FRAME_WAIT_TIME);
+	if (test_bit(BRCMF_MGMT_TX_ACK, &vif->mgmt_tx_status)) {
+		brcmf_dbg(TRACE, "TX Auth frame operation is success\n");
+		ack = true;
+	} else {
+		bphy_err(drvr, "TX Auth frame operation is %s: status=%ld)\n",
+			 ready ? "failed" : "timedout", vif->mgmt_tx_status);
+	}
+
+tx_status:
+	cfg80211_mgmt_tx_status(wdev, *cookie, buf, len, ack,
+				GFP_KERNEL);
+	kfree(mf_params);
+	return err;
+}
+
+static int
+brcmf_cyw_external_auth(struct wiphy *wiphy, struct net_device *dev,
+			struct cfg80211_external_auth_params *params)
+{
+	struct brcmf_if *ifp;
+	struct brcmf_pub *drvr;
+	struct brcmf_auth_req_status_le auth_status;
+	int ret = 0;
+
+	brcmf_dbg(TRACE, "Enter\n");
+
+	ifp = netdev_priv(dev);
+	drvr = ifp->drvr;
+	if (params->status == WLAN_STATUS_SUCCESS) {
+		auth_status.flags = cpu_to_le16(BRCMF_EXTAUTH_SUCCESS);
+	} else {
+		bphy_err(drvr, "External authentication failed: status=%d\n",
+			 params->status);
+		auth_status.flags = cpu_to_le16(BRCMF_EXTAUTH_FAIL);
+	}
+
+	memcpy(auth_status.peer_mac, params->bssid, ETH_ALEN);
+	params->ssid.ssid_len = min_t(u8, params->ssid.ssid_len,
+				      IEEE80211_MAX_SSID_LEN);
+	auth_status.ssid_len = cpu_to_le32(params->ssid.ssid_len);
+	memcpy(auth_status.ssid, params->ssid.ssid, params->ssid.ssid_len);
+
+	ret = brcmf_fil_iovar_data_set(ifp, "auth_status", &auth_status,
+				       sizeof(auth_status));
+	if (ret < 0)
+		bphy_err(drvr, "auth_status iovar failed: ret=%d\n", ret);
+
+	return ret;
+}
+
+static void brcmf_cyw_get_cfg80211_ops(struct brcmf_pub *drvr)
+{
+	drvr->ops->mgmt_tx = brcmf_cyw_mgmt_tx;
+	drvr->ops->external_auth = brcmf_cyw_external_auth;
+}
+
+static s32
+brcmf_cyw_notify_ext_auth_req(struct brcmf_if *ifp,
+			      const struct brcmf_event_msg *e, void *data)
+{
+	struct brcmf_pub *drvr = ifp->drvr;
+	struct cfg80211_external_auth_params params;
+	struct brcmf_auth_req_status_le *auth_req =
+		(struct brcmf_auth_req_status_le *)data;
+	s32 err = 0;
+
+	brcmf_dbg(INFO, "Enter: event %s (%d) received\n",
+		  brcmf_fweh_event_name(e->event_code), e->event_code);
+
+	if (e->datalen < sizeof(*auth_req)) {
+		bphy_err(drvr, "Event %s (%d) data too small. Ignore\n",
+			 brcmf_fweh_event_name(e->event_code), e->event_code);
+		return -EINVAL;
+	}
+
+	memset(&params, 0, sizeof(params));
+	params.action = NL80211_EXTERNAL_AUTH_START;
+	params.key_mgmt_suite = WLAN_AKM_SUITE_SAE;
+	params.status = WLAN_STATUS_SUCCESS;
+	params.ssid.ssid_len = min_t(u32, 32, le32_to_cpu(auth_req->ssid_len));
+	memcpy(params.ssid.ssid, auth_req->ssid, params.ssid.ssid_len);
+	memcpy(params.bssid, auth_req->peer_mac, ETH_ALEN);
+
+	err = cfg80211_external_auth_request(ifp->ndev, &params, GFP_KERNEL);
+	if (err)
+		bphy_err(drvr, "Ext Auth request to supplicant failed (%d)\n",
+			 err);
+
+	return err;
+}
+
+static s32
+brcmf_notify_auth_frame_rx(struct brcmf_if *ifp,
+			   const struct brcmf_event_msg *e, void *data)
+{
+	struct brcmf_pub *drvr = ifp->drvr;
+	struct brcmf_cfg80211_info *cfg = drvr->config;
+	struct wireless_dev *wdev;
+	u32 mgmt_frame_len = e->datalen - sizeof(struct brcmf_rx_mgmt_data);
+	struct brcmf_rx_mgmt_data *rxframe = (struct brcmf_rx_mgmt_data *)data;
+	u8 *frame = (u8 *)(rxframe + 1);
+	struct brcmu_chan ch;
+	struct ieee80211_mgmt *mgmt_frame;
+	s32 freq;
+
+	brcmf_dbg(INFO, "Enter: event %s (%d) received\n",
+		  brcmf_fweh_event_name(e->event_code), e->event_code);
+
+	if (e->datalen < sizeof(*rxframe)) {
+		bphy_err(drvr, "Event %s (%d) data too small. Ignore\n",
+			 brcmf_fweh_event_name(e->event_code), e->event_code);
+		return -EINVAL;
+	}
+
+	wdev = &ifp->vif->wdev;
+	WARN_ON(!wdev);
+
+	ch.chspec = be16_to_cpu(rxframe->chanspec);
+	cfg->d11inf.decchspec(&ch);
+
+	mgmt_frame = kzalloc(mgmt_frame_len, GFP_KERNEL);
+	if (!mgmt_frame)
+		return -ENOMEM;
+
+	mgmt_frame->frame_control = cpu_to_le16(IEEE80211_STYPE_AUTH);
+	memcpy(mgmt_frame->da, ifp->mac_addr, ETH_ALEN);
+	memcpy(mgmt_frame->sa, e->addr, ETH_ALEN);
+	brcmf_fil_cmd_data_get(ifp, BRCMF_C_GET_BSSID, mgmt_frame->bssid,
+			       ETH_ALEN);
+	frame += offsetof(struct ieee80211_mgmt, u);
+	memcpy(&mgmt_frame->u, frame,
+	       mgmt_frame_len - offsetof(struct ieee80211_mgmt, u));
+
+	freq = ieee80211_channel_to_frequency(ch.control_ch_num,
+					      ch.band == BRCMU_CHAN_BAND_2G ?
+					      NL80211_BAND_2GHZ :
+					      NL80211_BAND_5GHZ);
+
+	cfg80211_rx_mgmt(wdev, freq, 0, (u8 *)mgmt_frame, mgmt_frame_len,
+			 NL80211_RXMGMT_FLAG_EXTERNAL_AUTH);
+	kfree(mgmt_frame);
+	return 0;
+}
+
+static s32
+brcmf_notify_mgmt_tx_status(struct brcmf_if *ifp,
+			    const struct brcmf_event_msg *e, void *data)
+{
+	struct brcmf_cfg80211_vif *vif = ifp->vif;
+	u32 *packet_id = (u32 *)data;
+
+	brcmf_dbg(INFO, "Enter: event %s (%d), status=%d\n",
+		  brcmf_fweh_event_name(e->event_code), e->event_code,
+		  e->status);
+
+	if (!test_bit(BRCMF_MGMT_TX_SEND_FRAME, &vif->mgmt_tx_status) ||
+	    (*packet_id != vif->mgmt_tx_id))
+		return 0;
+
+	if (e->event_code == BRCMF_E_MGMT_FRAME_TXSTATUS) {
+		if (e->status == BRCMF_E_STATUS_SUCCESS)
+			set_bit(BRCMF_MGMT_TX_ACK, &vif->mgmt_tx_status);
+		else
+			set_bit(BRCMF_MGMT_TX_NOACK, &vif->mgmt_tx_status);
+	} else {
+		set_bit(BRCMF_MGMT_TX_OFF_CHAN_COMPLETED, &vif->mgmt_tx_status);
+	}
+
+	complete(&vif->mgmt_tx);
+	return 0;
+}
+
+static void brcmf_cyw_register_event_handlers(struct brcmf_pub *drvr)
+{
+	brcmf_fweh_register(drvr, BRCMF_E_EXT_AUTH_REQ,
+			    brcmf_cyw_notify_ext_auth_req);
+	brcmf_fweh_register(drvr, BRCMF_E_EXT_AUTH_FRAME_RX,
+			    brcmf_notify_auth_frame_rx);
+	brcmf_fweh_register(drvr, BRCMF_E_MGMT_FRAME_TXSTATUS,
+			    brcmf_notify_mgmt_tx_status);
+	brcmf_fweh_register(drvr, BRCMF_E_MGMT_FRAME_OFFCHAN_DONE,
+			    brcmf_notify_mgmt_tx_status);
+}
+
 const struct brcmf_fwvid_ops brcmf_cyw_ops = {
 	.set_sae_password = brcmf_cyw_set_sae_pwd,
 	.alloc_fweh_info = brcmf_cyw_alloc_fweh_info,
+	.activate_events = brcmf_cyw_activate_events,
+	.get_cfg80211_ops = brcmf_cyw_get_cfg80211_ops,
+	.register_event_handlers = brcmf_cyw_register_event_handlers,
 };
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/fwil_types.h
new file mode 100644
index 000000000000..08c69142495a
--- /dev/null
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/fwil_types.h
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: ISC
+/*
+ * Copyright (c) 2012 Broadcom Corporation
+ */
+
+#ifndef CYW_FWIL_TYPES_H_
+#define CYW_FWIL_TYPES_H_
+
+#include <fwil_types.h>
+
+enum brcmf_event_msgs_ext_command {
+	CYW_EVENTMSGS_NONE	= 0,
+	CYW_EVENTMSGS_SET_BIT	= 1,
+	CYW_EVENTMSGS_RESET_BIT	= 2,
+	CYW_EVENTMSGS_SET_MASK	= 3,
+};
+
+#define EVENTMSGS_VER 1
+#define EVENTMSGS_EXT_STRUCT_SIZE	offsetof(struct eventmsgs_ext, mask[0])
+
+/**
+ * struct brcmf_eventmsgs_ext - structure used with "eventmsgs_ext" iovar.
+ *
+ * @ver: version.
+ * @command: requested operation (see &enum event_msgs_ext_command).
+ * @len: length of the @mask array.
+ * @maxgetsize: indicates maximum mask size that may be returned by firmware
+ *	upon iovar GET.
+ * @mask: array where each bit represents firmware event.
+ */
+struct brcmf_eventmsgs_ext {
+	u8	ver;
+	u8	command;
+	u8	len;
+	u8	maxgetsize;
+	u8	mask[] __counted_by(len);
+};
+
+#define BRCMF_EXTAUTH_START		1
+#define BRCMF_EXTAUTH_ABORT		2
+#define BRCMF_EXTAUTH_FAIL		3
+#define BRCMF_EXTAUTH_SUCCESS		4
+
+/**
+ * struct brcmf_auth_req_status_le - external auth request and status update
+ *
+ * @flags: flags for external auth status
+ * @peer_mac: peer MAC address
+ * @ssid_len: length of ssid
+ * @ssid: ssid characters
+ * @pmkid: PMKSA identifier
+ */
+struct brcmf_auth_req_status_le {
+	__le16 flags;
+	u8 peer_mac[ETH_ALEN];
+	__le32 ssid_len;
+	u8 ssid[IEEE80211_MAX_SSID_LEN];
+	u8 pmkid[WLAN_PMKID_LEN];
+};
+
+/**
+ * struct brcmf_mf_params_le - management frame parameters for mgmt_frame iovar
+ *
+ * @version: version of the iovar
+ * @dwell_time: dwell duration in ms
+ * @len: length of frame data
+ * @frame_control: frame control
+ * @channel: channel
+ * @da: peer MAC address
+ * @bssid: BSS network identifier
+ * @packet_id: packet identifier
+ * @data: frame data
+ */
+struct brcmf_mf_params_le {
+	__le32 version;
+	__le32 dwell_time;
+	__le16 len;
+	__le16 frame_control;
+	__le16 channel;
+	u8 da[ETH_ALEN];
+	u8 bssid[ETH_ALEN];
+	__le32 packet_id;
+	u8 data[] __counted_by(len);
+};
+
+#endif /* CYW_FWIL_TYPES_H_ */
+
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
index 0d9ae197fa1e..488364ef8ff2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
@@ -42,8 +42,9 @@ static const struct brcmf_feat_fwcap brcmf_fwcap_map[] = {
 	{ BRCMF_FEAT_MONITOR_FLAG, "rtap" },
 	{ BRCMF_FEAT_MONITOR_FMT_RADIOTAP, "rtap" },
 	{ BRCMF_FEAT_DOT11H, "802.11h" },
-	{ BRCMF_FEAT_SAE, "sae" },
+	{ BRCMF_FEAT_SAE, "sae " },
 	{ BRCMF_FEAT_FWAUTH, "idauth" },
+	{ BRCMF_FEAT_SAE_EXT, "sae_ext" },
 };
 
 #ifdef DEBUG
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
index 7f4f0b3e4a7b..31f8695ca417 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
@@ -31,6 +31,7 @@
  * FWAUTH: Firmware authenticator
  * DUMP_OBSS: Firmware has capable to dump obss info to support ACS
  * SCAN_V2: Version 2 scan params
+ * SAE_EXT: SAE authentication handled by user-space supplicant
  */
 #define BRCMF_FEAT_LIST \
 	BRCMF_FEAT_DEF(MBSS) \
@@ -57,7 +58,8 @@
 	BRCMF_FEAT_DEF(DUMP_OBSS) \
 	BRCMF_FEAT_DEF(SCAN_V2) \
 	BRCMF_FEAT_DEF(PMKID_V2) \
-	BRCMF_FEAT_DEF(PMKID_V3)
+	BRCMF_FEAT_DEF(PMKID_V3) \
+	BRCMF_FEAT_DEF(SAE_EXT)
 
 /*
  * Quirks:
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
index f0b6a7607f16..c2d98ee6652f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
@@ -75,6 +75,7 @@ const char *brcmf_fweh_event_name(enum brcmf_fweh_event_code code)
 	return "nodebug";
 }
 #endif
+BRCMF_EXPORT_SYMBOL_GPL(brcmf_fweh_event_name);
 
 /**
  * brcmf_fweh_queue_event() - create and queue event.
@@ -405,6 +406,7 @@ int brcmf_fweh_register(struct brcmf_pub *drvr, enum brcmf_fweh_event_code code,
 		  brcmf_fweh_event_name(code));
 	return 0;
 }
+BRCMF_EXPORT_SYMBOL_GPL(brcmf_fweh_register);
 
 /**
  * brcmf_fweh_unregister() - remove handler for given code.
@@ -448,11 +450,14 @@ int brcmf_fweh_activate_events(struct brcmf_if *ifp)
 	brcmf_dbg(EVENT, "enable event IF\n");
 	setbit(fweh->event_mask, BRCMF_E_IF);
 
+	/* allow per-vendor method to activate firmware events */
+	if (!brcmf_fwvid_activate_events(ifp))
+		return 0;
+
 	err = brcmf_fil_iovar_data_set(ifp, "event_msgs", fweh->event_mask,
 				       fweh->event_mask_len);
 	if (err)
 		bphy_err(fweh->drvr, "Set event_msgs error (%d)\n", err);
-
 	return err;
 }
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h
index eed439b84010..e327dd58d29c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h
@@ -94,7 +94,11 @@ struct brcmf_cfg80211_info;
 	BRCMF_ENUM_DEF(FIFO_CREDIT_MAP, 74) \
 	BRCMF_ENUM_DEF(ACTION_FRAME_RX, 75) \
 	BRCMF_ENUM_DEF(TDLS_PEER_EVENT, 92) \
-	BRCMF_ENUM_DEF(BCMC_CREDIT_SUPPORT, 127)
+	BRCMF_ENUM_DEF(BCMC_CREDIT_SUPPORT, 127) \
+	BRCMF_ABSTRACT_ENUM_DEF(EXT_AUTH_REQ, 0) \
+	BRCMF_ABSTRACT_ENUM_DEF(EXT_AUTH_FRAME_RX, 1) \
+	BRCMF_ABSTRACT_ENUM_DEF(MGMT_FRAME_TXSTATUS, 2) \
+	BRCMF_ABSTRACT_ENUM_DEF(MGMT_FRAME_OFFCHAN_DONE, 3)
 
 #define BRCMF_ENUM_DEF(id, val) \
 	BRCMF_E_##id = (val),
@@ -337,7 +341,7 @@ struct brcmf_fweh_info {
 	struct list_head event_q;
 	uint event_mask_len;
 	u8 *event_mask;
-	struct brcmf_fweh_event_map *event_map;
+	const struct brcmf_fweh_event_map *event_map;
 	uint num_event_codes;
 	brcmf_fweh_handler_t evt_handler[] __counted_by(num_event_codes);
 };
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.h
index e6ac9fc341bc..f3e011d090f2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.h
@@ -15,6 +15,9 @@ struct brcmf_fwvid_ops {
 	void (*feat_attach)(struct brcmf_if *ifp);
 	int (*set_sae_password)(struct brcmf_if *ifp, struct cfg80211_crypto_settings *crypto);
 	int (*alloc_fweh_info)(struct brcmf_pub *drvr);
+	int (*activate_events)(struct brcmf_if *ifp);
+	void (*get_cfg80211_ops)(struct brcmf_pub *drvr);
+	void (*register_event_handlers)(struct brcmf_pub *drvr);
 };
 
 /* exported functions */
@@ -56,4 +59,30 @@ static inline int brcmf_fwvid_alloc_fweh_info(struct brcmf_pub *drvr)
 	return drvr->vops->alloc_fweh_info(drvr);
 }
 
+static inline int brcmf_fwvid_activate_events(struct brcmf_if *ifp)
+{
+	const struct brcmf_fwvid_ops *vops = ifp->drvr->vops;
+
+	if (!vops || !vops->activate_events)
+		return -EOPNOTSUPP;
+
+	return vops->activate_events(ifp);
+}
+
+static inline void brcmf_fwvid_get_cfg80211_ops(struct brcmf_pub *drvr)
+{
+	if (!drvr->vops || !drvr->vops->get_cfg80211_ops)
+		return;
+
+	drvr->vops->get_cfg80211_ops(drvr);
+}
+
+static inline void brcmf_fwvid_register_event_handlers(struct brcmf_pub *drvr)
+{
+	if (!drvr->vops || !drvr->vops->register_event_handlers)
+		return;
+
+	drvr->vops->register_event_handlers(drvr);
+}
+
 #endif /* FWVID_H_ */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
index 2821c27f317e..b056336d5da6 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -741,15 +741,19 @@ static int brcmf_usb_dl_cmd(struct brcmf_usbdev_info *devinfo, u8 cmd,
 			    void *buffer, int buflen)
 {
 	int ret;
-	char *tmpbuf;
+	char *tmpbuf = NULL;
 	u16 size;
 
-	if ((!devinfo) || (devinfo->ctl_urb == NULL))
-		return -EINVAL;
+	if (!devinfo || !devinfo->ctl_urb) {
+		ret = -EINVAL;
+		goto err;
+	}
 
 	tmpbuf = kmalloc(buflen, GFP_ATOMIC);
-	if (!tmpbuf)
-		return -ENOMEM;
+	if (!tmpbuf) {
+		ret = -ENOMEM;
+		goto err;
+	}
 
 	size = buflen;
 	devinfo->ctl_urb->transfer_buffer_length = size;
@@ -770,18 +774,23 @@ static int brcmf_usb_dl_cmd(struct brcmf_usbdev_info *devinfo, u8 cmd,
 	ret = usb_submit_urb(devinfo->ctl_urb, GFP_ATOMIC);
 	if (ret < 0) {
 		brcmf_err("usb_submit_urb failed %d\n", ret);
-		goto finalize;
+		goto err;
 	}
 
 	if (!brcmf_usb_ioctl_resp_wait(devinfo)) {
 		usb_kill_urb(devinfo->ctl_urb);
 		ret = -ETIMEDOUT;
+		goto err;
 	} else {
 		memcpy(buffer, tmpbuf, buflen);
 	}
 
-finalize:
 	kfree(tmpbuf);
+	return 0;
+
+err:
+	kfree(tmpbuf);
+	brcmf_err("dl cmd %u failed: err=%d\n", cmd, ret);
 	return ret;
 }
 
@@ -896,14 +905,16 @@ brcmf_usb_dl_writeimage(struct brcmf_usbdev_info *devinfo, u8 *fw, int fwlen)
 	}
 
 	/* 1) Prepare USB boot loader for runtime image */
-	brcmf_usb_dl_cmd(devinfo, DL_START, &state, sizeof(state));
+	err = brcmf_usb_dl_cmd(devinfo, DL_START, &state, sizeof(state));
+	if (err)
+		goto fail;
 
 	rdlstate = le32_to_cpu(state.state);
 	rdlbytes = le32_to_cpu(state.bytes);
 
 	/* 2) Check we are in the Waiting state */
 	if (rdlstate != DL_WAITING) {
-		brcmf_err("Failed to DL_START\n");
+		brcmf_err("Invalid DL state: %u\n", rdlstate);
 		err = -EINVAL;
 		goto fail;
 	}
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c
index 50d817485cf9..0cb64fc56783 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c
@@ -198,7 +198,7 @@
 #define	CST4313_SPROM_OTP_SEL_SHIFT		0
 
 /* 4313 Chip specific ChipControl register bits */
- /* 12 mA drive strengh for later 4313 */
+ /* 12 mA drive strength for later 4313 */
 #define CCTRL_4313_12MA_LED_DRIVE    0x00000007
 
 /* Manufacturer Ids */
@@ -453,7 +453,7 @@ ai_buscore_setup(struct si_info *sii, struct bcma_device *cc)
 	/* get chipcommon chipstatus */
 	sii->chipst = bcma_read32(cc, CHIPCREGOFFS(chipstatus));
 
-	/* get chipcommon capabilites */
+	/* get chipcommon capabilities */
 	sii->pub.cccaps = bcma_read32(cc, CHIPCREGOFFS(capabilities));
 
 	/* get pmu rev and caps */
@@ -657,7 +657,7 @@ u16 ai_clkctl_fast_pwrup_delay(struct si_pub *sih)
 }
 
 /*
- *  clock control policy function throught chipcommon
+ *  clock control policy function through chipcommon
  *
  *    set dynamic clk control mode (forceslow, forcefast, dynamic)
  *    returns true if we are forcing fast clock
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.h
index 90b6e3982d2c..e791dd07ca78 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.h
@@ -76,7 +76,7 @@
  * conventions for the use the flash space:
  */
 
-/* Minumum amount of flash we support */
+/* Minimum amount of flash we support */
 #define FLASH_MIN		0x00020000	/* Minimum flash size */
 
 #define	CC_SROM_OTP		0x800	/* SROM/OTP address space */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
index a767cbb79185..e1d707a7c964 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
@@ -479,7 +479,7 @@ void brcms_c_ampdu_reset_session(struct brcms_ampdu_session *session,
 
 /*
  * Preps the given packet for AMPDU based on the session data. If the
- * frame cannot be accomodated in the current session, -ENOSPC is
+ * frame cannot be accommodated in the current session, -ENOSPC is
  * returned.
  */
 int brcms_c_ampdu_add_frame(struct brcms_ampdu_session *session,
@@ -529,7 +529,7 @@ int brcms_c_ampdu_add_frame(struct brcms_ampdu_session *session,
 	}
 
 	/*
-	 * Now that we're sure this frame can be accomodated, update the
+	 * Now that we're sure this frame can be accommodated, update the
 	 * session information.
 	 */
 	session->ampdu_len += len;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c
index d1b9a18d0374..3878c4124e25 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/channel.c
@@ -445,7 +445,7 @@ brcms_c_channel_reg_limits(struct brcms_cm_info *wlc_cm, u16 chanspec,
 
 		/*
 		 * OFDM 40 MHz SISO has the same power as the corresponding
-		 * MCS0-7 rate unless overriden by the locale specific code.
+		 * MCS0-7 rate unless overridden by the locale specific code.
 		 * We set this value to 0 as a flag (presumably 0 dBm isn't
 		 * a possibility) and then copy the MCS0-7 value to the 40 MHz
 		 * value if it wasn't explicitly set.
@@ -479,7 +479,7 @@ brcms_c_channel_reg_limits(struct brcms_cm_info *wlc_cm, u16 chanspec,
 
 		/*
 		 * 20 MHz has the same power as the corresponding OFDM rate
-		 * unless overriden by the locale specific code.
+		 * unless overridden by the locale specific code.
 		 */
 		txpwr->mcs_20_siso[i] = txpwr->ofdm[i];
 		txpwr->mcs_40_siso[i] = 0;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
index 80c35027787a..c739bf7463b3 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
@@ -1348,7 +1348,7 @@ static void prep_ampdu_frame(struct dma_info *di, struct sk_buff *p)
 	ret = brcms_c_ampdu_add_frame(session, p);
 	if (ret == -ENOSPC) {
 		/*
-		 * AMPDU cannot accomodate this frame. Close out the in-
+		 * AMPDU cannot accommodate this frame. Close out the in-
 		 * progress AMPDU session and start a new one.
 		 */
 		ampdu_finalize(di);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
index 5b1d35601bbd..1c3d29dca424 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
@@ -48,9 +48,9 @@
 	FIF_BCN_PRBRESP_PROMISC | \
 	FIF_PSPOLL)
 
-#define CHAN2GHZ(channel, freqency, chflags)  { \
+#define CHAN2GHZ(channel, frequency, chflags)  { \
 	.band = NL80211_BAND_2GHZ, \
-	.center_freq = (freqency), \
+	.center_freq = (frequency), \
 	.hw_value = (channel), \
 	.flags = chflags, \
 	.max_antenna_gain = 0, \
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
index 2738d4d6c60a..c1a9c1e442ee 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
@@ -921,7 +921,7 @@ brcms_c_dotxstatus(struct brcms_c_info *wlc, struct tx_status *txs)
 		 * The "fallback limit" is the number of tx attempts a given
 		 * MPDU is sent at the "primary" rate. Tx attempts beyond that
 		 * limit are sent at the "secondary" rate.
-		 * A 'short frame' does not exceed RTS treshold.
+		 * A 'short frame' does not exceed RTS threshold.
 		 */
 		u16 sfbl,	/* Short Frame Rate Fallback Limit */
 		    lfbl,	/* Long Frame Rate Fallback Limit */
@@ -6259,7 +6259,7 @@ brcms_c_d11hdrs_mac80211(struct brcms_c_info *wlc, struct ieee80211_hw *hw,
 		}
 
 		/*
-		 * Currently only support same setting for primay and
+		 * Currently only support same setting for primary and
 		 * fallback rates. Unify flags for each rate into a
 		 * single value for the frame
 		 */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.h
index 9f76b880814e..b7ca0d9891c4 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.h
@@ -603,7 +603,7 @@ enum brcms_bss_type {
  * cur_etheraddr: h/w address
  * flags: BSSCFG flags; see below
  *
- * current_bss: BSS parms in ASSOCIATED state
+ * current_bss: BSS parameters in ASSOCIATED state
  *
  *
  * ID: 'unique' ID of this bsscfg, assigned at bsscfg allocation
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/pmu.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/pmu.c
index 71b80381f3ad..c9a29e626daa 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/pmu.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/pmu.c
@@ -31,7 +31,7 @@
 #define EXT_ILP_HZ 32768
 
 /*
- * Duration for ILP clock frequency measurment in milliseconds
+ * Duration for ILP clock frequency measurement in milliseconds
  *
  * remark: 1000 must be an integer multiple of this duration
  */
diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index 9546ceeaf5e3..3f476e333726 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -8,12 +8,23 @@ iwlwifi-objs		+= iwl-nvm-utils.o
 iwlwifi-objs		+= iwl-utils.o
 iwlwifi-objs		+= iwl-phy-db.o iwl-nvm-parse.o
 iwlwifi-objs		+= pcie/drv.o pcie/rx.o pcie/tx.o pcie/trans.o
-iwlwifi-objs		+= pcie/ctxt-info.o pcie/ctxt-info-gen3.o
+iwlwifi-objs		+= pcie/ctxt-info.o pcie/ctxt-info-v2.o
 iwlwifi-objs		+= pcie/trans-gen2.o pcie/tx-gen2.o
-iwlwifi-$(CONFIG_IWLDVM) += cfg/1000.o cfg/2000.o cfg/5000.o cfg/6000.o
-iwlwifi-$(CONFIG_IWLMVM) += cfg/7000.o cfg/8000.o cfg/9000.o cfg/22000.o
+
+CFLAGS_pcie/drv.o += -Wno-override-init
+
+# combined MAC/RF configurations
+iwlwifi-$(CONFIG_IWLDVM) += cfg/1000.o cfg/2000.o
+iwlwifi-$(CONFIG_IWLDVM) += cfg/5000.o cfg/6000.o
+iwlwifi-$(CONFIG_IWLMVM) += cfg/7000.o cfg/8000.o
+# MAC configurations
+iwlwifi-$(CONFIG_IWLMVM) += cfg/9000.o cfg/22000.o
 iwlwifi-$(CONFIG_IWLMVM) += cfg/ax210.o
 iwlwifi-$(CONFIG_IWLMLD) += cfg/bz.o cfg/sc.o cfg/dr.o
+# RF configurations
+iwlwifi-$(CONFIG_IWLMVM) += cfg/rf-jf.o cfg/rf-hr.o cfg/rf-gf.o
+iwlwifi-$(CONFIG_IWLMLD) += cfg/rf-fm.o cfg/rf-wh.o cfg/rf-pe.o
+
 iwlwifi-objs		+= iwl-dbg-tlv.o
 iwlwifi-objs		+= iwl-trans.o
 
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/1000.c b/drivers/net/wireless/intel/iwlwifi/cfg/1000.c
index f172ffd2a841..c029e595e7c2 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/1000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/1000.c
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2018 - 2020, 2023 Intel Corporation
+ * Copyright(c) 2018 - 2020, 2023, 2025 Intel Corporation
  *****************************************************************************/
 
 #include <linux/module.h>
@@ -29,7 +29,7 @@
 #define IWL100_MODULE_FIRMWARE(api) IWL100_FW_PRE "-" __stringify(api) ".ucode"
 
 
-static const struct iwl_base_params iwl1000_base_params = {
+static const struct iwl_family_base_params iwl1000_base = {
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
@@ -42,12 +42,6 @@ static const struct iwl_base_params iwl1000_base_params = {
 	.scd_chain_ext_wa = true,
 };
 
-static const struct iwl_ht_params iwl1000_ht_params = {
-	.ht_greenfield_support = true,
-	.use_rts_for_aggregation = true, /* use rts/cts protection */
-	.ht40_bands = BIT(NL80211_BAND_2GHZ),
-};
-
 static const struct iwl_eeprom_params iwl1000_eeprom_params = {
 	.regulatory_bands = {
 		EEPROM_REG_BAND_1_CHANNELS,
@@ -60,54 +54,67 @@ static const struct iwl_eeprom_params iwl1000_eeprom_params = {
 	}
 };
 
+const struct iwl_mac_cfg iwl1000_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_1000,
+	.base = &iwl1000_base,
+};
+
 #define IWL_DEVICE_1000						\
 	.fw_name_pre = IWL1000_FW_PRE,				\
 	.ucode_api_max = IWL1000_UCODE_API_MAX,			\
 	.ucode_api_min = IWL1000_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_1000,		\
 	.max_inst_size = IWLAGN_RTC_INST_SIZE,			\
 	.max_data_size = IWLAGN_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_1000_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_1000_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl1000_base_params,		\
 	.eeprom_params = &iwl1000_eeprom_params,		\
 	.led_mode = IWL_LED_BLINK
 
-const struct iwl_cfg iwl1000_bgn_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 1000 BGN",
+const struct iwl_rf_cfg iwl1000_bgn_cfg = {
 	IWL_DEVICE_1000,
-	.ht_params = &iwl1000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ),
+	},
 };
 
-const struct iwl_cfg iwl1000_bg_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 1000 BG",
+const char iwl1000_bgn_name[] = "Intel(R) Centrino(R) Wireless-N 1000 BGN";
+
+const struct iwl_rf_cfg iwl1000_bg_cfg = {
 	IWL_DEVICE_1000,
 };
 
+const char iwl1000_bg_name[] = "Intel(R) Centrino(R) Wireless-N 1000 BG";
+
 #define IWL_DEVICE_100						\
 	.fw_name_pre = IWL100_FW_PRE,				\
 	.ucode_api_max = IWL100_UCODE_API_MAX,			\
 	.ucode_api_min = IWL100_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_100,		\
 	.max_inst_size = IWLAGN_RTC_INST_SIZE,			\
 	.max_data_size = IWLAGN_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_1000_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_1000_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl1000_base_params,		\
 	.eeprom_params = &iwl1000_eeprom_params,		\
 	.led_mode = IWL_LED_RF_STATE,				\
 	.rx_with_siso_diversity = true
 
-const struct iwl_cfg iwl100_bgn_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 100 BGN",
+const struct iwl_rf_cfg iwl100_bgn_cfg = {
 	IWL_DEVICE_100,
-	.ht_params = &iwl1000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ),
+	},
 };
 
-const struct iwl_cfg iwl100_bg_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 100 BG",
+const char iwl100_bgn_name[] = "Intel(R) Centrino(R) Wireless-N 100 BGN";
+
+const struct iwl_rf_cfg iwl100_bg_cfg = {
 	IWL_DEVICE_100,
 };
 
+const char iwl100_bg_name[] = "Intel(R) Centrino(R) Wireless-N 100 BG";
+
 MODULE_FIRMWARE(IWL1000_MODULE_FIRMWARE(IWL1000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL100_MODULE_FIRMWARE(IWL100_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/2000.c b/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
index 6f3f26da0ad5..47554a5f406e 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2018 - 2020, 2023 Intel Corporation
+ * Copyright(c) 2018 - 2020, 2023, 2025 Intel Corporation
  *****************************************************************************/
 
 #include <linux/module.h>
@@ -40,7 +40,7 @@
 #define IWL135_FW_PRE "iwlwifi-135"
 #define IWL135_MODULE_FIRMWARE(api) IWL135_FW_PRE "-" __stringify(api) ".ucode"
 
-static const struct iwl_base_params iwl2000_base_params = {
+static const struct iwl_family_base_params iwl2000_base = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
@@ -54,7 +54,7 @@ static const struct iwl_base_params iwl2000_base_params = {
 };
 
 
-static const struct iwl_base_params iwl2030_base_params = {
+static const struct iwl_family_base_params iwl2030_base = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
@@ -67,12 +67,6 @@ static const struct iwl_base_params iwl2030_base_params = {
 	.scd_chain_ext_wa = true,
 };
 
-static const struct iwl_ht_params iwl2000_ht_params = {
-	.ht_greenfield_support = true,
-	.use_rts_for_aggregation = true, /* use rts/cts protection */
-	.ht40_bands = BIT(NL80211_BAND_2GHZ),
-};
-
 static const struct iwl_eeprom_params iwl20x0_eeprom_params = {
 	.regulatory_bands = {
 		EEPROM_REG_BAND_1_CHANNELS,
@@ -86,97 +80,119 @@ static const struct iwl_eeprom_params iwl20x0_eeprom_params = {
 	.enhanced_txpower = true,
 };
 
+const struct iwl_mac_cfg iwl2000_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_2000,
+	.base = &iwl2000_base,
+};
+
 #define IWL_DEVICE_2000						\
 	.fw_name_pre = IWL2000_FW_PRE,				\
 	.ucode_api_max = IWL2000_UCODE_API_MAX,			\
 	.ucode_api_min = IWL2000_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_2000,		\
 	.max_inst_size = IWL60_RTC_INST_SIZE,			\
 	.max_data_size = IWL60_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_2000_EEPROM_VERSION,			\
 	.nvm_calib_ver = EEPROM_2000_TX_POWER_VERSION,		\
-	.trans.base_params = &iwl2000_base_params,		\
 	.eeprom_params = &iwl20x0_eeprom_params,		\
 	.led_mode = IWL_LED_RF_STATE
 
 
-const struct iwl_cfg iwl2000_2bgn_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 2200 BGN",
+const struct iwl_rf_cfg iwl2000_2bgn_cfg = {
 	IWL_DEVICE_2000,
-	.ht_params = &iwl2000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ),
+	},
 };
 
-const struct iwl_cfg iwl2000_2bgn_d_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 2200D BGN",
-	IWL_DEVICE_2000,
-	.ht_params = &iwl2000_ht_params,
+const char iwl2000_2bgn_name[] = "Intel(R) Centrino(R) Wireless-N 2200 BGN";
+const char iwl2000_2bgn_d_name[] = "Intel(R) Centrino(R) Wireless-N 2200D BGN";
+
+const struct iwl_mac_cfg iwl2030_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_2030,
+	.base = &iwl2030_base,
 };
 
 #define IWL_DEVICE_2030						\
 	.fw_name_pre = IWL2030_FW_PRE,				\
 	.ucode_api_max = IWL2030_UCODE_API_MAX,			\
 	.ucode_api_min = IWL2030_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_2030,		\
 	.max_inst_size = IWL60_RTC_INST_SIZE,			\
 	.max_data_size = IWL60_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_2000_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_2000_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl2030_base_params,		\
 	.eeprom_params = &iwl20x0_eeprom_params,		\
 	.led_mode = IWL_LED_RF_STATE
 
-const struct iwl_cfg iwl2030_2bgn_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 2230 BGN",
+const struct iwl_rf_cfg iwl2030_2bgn_cfg = {
 	IWL_DEVICE_2030,
-	.ht_params = &iwl2000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ),
+	},
+};
+
+const char iwl2030_2bgn_name[] = "Intel(R) Centrino(R) Wireless-N 2230 BGN";
+
+const struct iwl_mac_cfg iwl105_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_105,
+	.base = &iwl2000_base,
 };
 
 #define IWL_DEVICE_105						\
 	.fw_name_pre = IWL105_FW_PRE,				\
 	.ucode_api_max = IWL105_UCODE_API_MAX,			\
 	.ucode_api_min = IWL105_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_105,		\
 	.max_inst_size = IWL60_RTC_INST_SIZE,			\
 	.max_data_size = IWL60_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_2000_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_2000_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl2000_base_params,		\
 	.eeprom_params = &iwl20x0_eeprom_params,		\
 	.led_mode = IWL_LED_RF_STATE,				\
 	.rx_with_siso_diversity = true
 
-const struct iwl_cfg iwl105_bgn_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 105 BGN",
+const struct iwl_rf_cfg iwl105_bgn_cfg = {
 	IWL_DEVICE_105,
-	.ht_params = &iwl2000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ),
+	},
 };
 
-const struct iwl_cfg iwl105_bgn_d_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 105D BGN",
-	IWL_DEVICE_105,
-	.ht_params = &iwl2000_ht_params,
+const char iwl105_bgn_name[] = "Intel(R) Centrino(R) Wireless-N 105 BGN";
+const char iwl105_bgn_d_name[] = "Intel(R) Centrino(R) Wireless-N 105D BGN";
+
+const struct iwl_mac_cfg iwl135_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_135,
+	.base = &iwl2030_base,
 };
 
 #define IWL_DEVICE_135						\
 	.fw_name_pre = IWL135_FW_PRE,				\
 	.ucode_api_max = IWL135_UCODE_API_MAX,			\
 	.ucode_api_min = IWL135_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_135,		\
 	.max_inst_size = IWL60_RTC_INST_SIZE,			\
 	.max_data_size = IWL60_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_2000_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_2000_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl2030_base_params,		\
 	.eeprom_params = &iwl20x0_eeprom_params,		\
 	.led_mode = IWL_LED_RF_STATE,				\
 	.rx_with_siso_diversity = true
 
-const struct iwl_cfg iwl135_bgn_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 135 BGN",
+const struct iwl_rf_cfg iwl135_bgn_cfg = {
 	IWL_DEVICE_135,
-	.ht_params = &iwl2000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ),
+	},
 };
 
+const char iwl135_bgn_name[] = "Intel(R) Centrino(R) Wireless-N 135 BGN";
+
 MODULE_FIRMWARE(IWL2000_MODULE_FIRMWARE(IWL2000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL2030_MODULE_FIRMWARE(IWL2030_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL105_MODULE_FIRMWARE(IWL105_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index 130b9a8aa7eb..52e0beebf9ce 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include <linux/module.h>
 #include <linux/stringify.h>
@@ -15,14 +15,7 @@
 /* Lowest firmware API version supported */
 #define IWL_22000_UCODE_API_MIN	77
 
-/* NVM versions */
-#define IWL_22000_NVM_VERSION		0x0a1d
-
 /* Memory offsets and lengths */
-#define IWL_22000_DCCM_OFFSET		0x800000 /* LMAC1 */
-#define IWL_22000_DCCM_LEN		0x10000 /* LMAC1 */
-#define IWL_22000_DCCM2_OFFSET		0x880000
-#define IWL_22000_DCCM2_LEN		0x8000
 #define IWL_22000_SMEM_OFFSET		0x400000
 #define IWL_22000_SMEM_LEN		0xD0000
 
@@ -44,11 +37,12 @@
 	IWL_QU_C_HR_B_FW_PRE "-" __stringify(api) ".ucode"
 #define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \
 	IWL_QU_B_JF_B_FW_PRE "-" __stringify(api) ".ucode"
+#define IWL_QU_C_JF_B_MODULE_FIRMWARE(api) \
+	IWL_QU_C_JF_B_FW_PRE "-" __stringify(api) ".ucode"
 #define IWL_CC_A_MODULE_FIRMWARE(api)			\
 	IWL_CC_A_FW_PRE "-" __stringify(api) ".ucode"
 
-static const struct iwl_base_params iwl_22000_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
+static const struct iwl_family_base_params iwl_22000_base = {
 	.num_of_queues = 512,
 	.max_tfd_queue_size = 256,
 	.shadow_ram_support = true,
@@ -57,155 +51,78 @@ static const struct iwl_base_params iwl_22000_base_params = {
 	.max_event_log_size = 512,
 	.shadow_reg_enable = true,
 	.pcie_l1_allowed = true,
-};
-
-const struct iwl_ht_params iwl_22000_ht_params = {
-	.stbc = true,
-	.ldpc = true,
-	.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ) |
-		      BIT(NL80211_BAND_6GHZ),
-};
-
-#define IWL_DEVICE_22000_COMMON						\
-	.ucode_api_min = IWL_22000_UCODE_API_MIN,			\
-	.led_mode = IWL_LED_RF_STATE,					\
-	.nvm_hw_section_num = 10,					\
-	.non_shared_ant = ANT_B,					\
-	.dccm_offset = IWL_22000_DCCM_OFFSET,				\
-	.dccm_len = IWL_22000_DCCM_LEN,					\
-	.dccm2_offset = IWL_22000_DCCM2_OFFSET,				\
-	.dccm2_len = IWL_22000_DCCM2_LEN,				\
-	.smem_offset = IWL_22000_SMEM_OFFSET,				\
-	.smem_len = IWL_22000_SMEM_LEN,					\
-	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,		\
-	.apmg_not_supported = true,					\
-	.trans.mq_rx_supported = true,					\
-	.vht_mu_mimo_supported = true,					\
-	.mac_addr_from_csr = 0x380,					\
-	.ht_params = &iwl_22000_ht_params,				\
-	.nvm_ver = IWL_22000_NVM_VERSION,				\
-	.trans.rf_id = true,						\
-	.trans.gen2 = true,						\
-	.nvm_type = IWL_NVM_EXT,					\
-	.dbgc_supported = true,						\
-	.min_umac_error_event_table = 0x400000,				\
-	.d3_debug_data_base_addr = 0x401000,				\
-	.d3_debug_data_length = 60 * 1024,				\
-	.mon_smem_regs = {						\
-		.write_ptr = {						\
-			.addr = LDBG_M2S_BUF_WPTR,			\
-			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,		\
-	},								\
-		.cycle_cnt = {						\
-			.addr = LDBG_M2S_BUF_WRAP_CNT,			\
-			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,		\
-		},							\
-	}
-
-#define IWL_DEVICE_22500						\
-	IWL_DEVICE_22000_COMMON,					\
-	.ucode_api_max = IWL_22000_UCODE_API_MAX,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_22000,			\
-	.trans.base_params = &iwl_22000_base_params,			\
-	.gp2_reg_addr = 0xa02c68,					\
-	.mon_dram_regs = {						\
-		.write_ptr = {						\
-			.addr = MON_BUFF_WRPTR_VER2,			\
-			.mask = 0xffffffff,				\
-		},							\
-		.cycle_cnt = {						\
-			.addr = MON_BUFF_CYCLE_CNT_VER2,		\
-			.mask = 0xffffffff,				\
-		},							\
-	}
-
-const struct iwl_cfg_trans_params iwl_qu_trans_cfg = {
+	.smem_offset = IWL_22000_SMEM_OFFSET,
+	.smem_len = IWL_22000_SMEM_LEN,
+	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,
+	.apmg_not_supported = true,
+	.mac_addr_from_csr = 0x380,
+	.min_umac_error_event_table = 0x400000,
+	.d3_debug_data_base_addr = 0x401000,
+	.d3_debug_data_length = 60 * 1024,
+	.mon_smem_regs = {
+		.write_ptr = {
+			.addr = LDBG_M2S_BUF_WPTR,
+			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,
+	},
+		.cycle_cnt = {
+			.addr = LDBG_M2S_BUF_WRAP_CNT,
+			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,
+		},
+	},
+	.gp2_reg_addr = 0xa02c68,
+	.mon_dram_regs = {
+		.write_ptr = {
+			.addr = MON_BUFF_WRPTR_VER2,
+			.mask = 0xffffffff,
+		},
+		.cycle_cnt = {
+			.addr = MON_BUFF_CYCLE_CNT_VER2,
+			.mask = 0xffffffff,
+		},
+	},
+	.ucode_api_min = IWL_22000_UCODE_API_MIN,
+	.ucode_api_max = IWL_22000_UCODE_API_MAX,
+};
+
+const struct iwl_mac_cfg iwl_qu_mac_cfg = {
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.device_family = IWL_DEVICE_FAMILY_22000,
-	.base_params = &iwl_22000_base_params,
+	.base = &iwl_22000_base,
 	.integrated = true,
 	.xtal_latency = 500,
 	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_200US,
 };
 
-const struct iwl_cfg_trans_params iwl_qu_medium_latency_trans_cfg = {
+const struct iwl_mac_cfg iwl_qu_medium_latency_mac_cfg = {
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.device_family = IWL_DEVICE_FAMILY_22000,
-	.base_params = &iwl_22000_base_params,
+	.base = &iwl_22000_base,
 	.integrated = true,
 	.xtal_latency = 1820,
 	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_1820US,
 };
 
-const struct iwl_cfg_trans_params iwl_qu_long_latency_trans_cfg = {
+const struct iwl_mac_cfg iwl_qu_long_latency_mac_cfg = {
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.device_family = IWL_DEVICE_FAMILY_22000,
-	.base_params = &iwl_22000_base_params,
+	.base = &iwl_22000_base,
 	.integrated = true,
 	.xtal_latency = 12000,
 	.low_latency_xtal = true,
 	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
 };
 
-/*
- * If the device doesn't support HE, no need to have that many buffers.
- * 22000 devices can split multiple frames into a single RB, so fewer are
- * needed; AX210 cannot (but use smaller RBs by default) - these sizes
- * were picked according to 8 MSDUs inside 256 A-MSDUs in an A-MPDU, with
- * additional overhead to account for processing time.
- */
-#define IWL_NUM_RBDS_NON_HE		512
-#define IWL_NUM_RBDS_22000_HE		2048
-
-/*
- * All JF radio modules are part of the 9000 series, but the MAC part
- * looks more like 22000.  That's why this device is here, but called
- * 9560 nevertheless.
- */
-const struct iwl_cfg iwl9560_qu_b0_jf_b0_cfg = {
-	.fw_name_pre = IWL_QU_B_JF_B_FW_PRE,
-	IWL_DEVICE_22500,
-	.num_rbds = IWL_NUM_RBDS_NON_HE,
-};
-
-const struct iwl_cfg iwl9560_qu_c0_jf_b0_cfg = {
-	.fw_name_pre = IWL_QU_C_JF_B_FW_PRE,
-	IWL_DEVICE_22500,
-	.num_rbds = IWL_NUM_RBDS_NON_HE,
-};
-
-const struct iwl_cfg iwl9560_quz_a0_jf_b0_cfg = {
-	.fw_name_pre = IWL_QUZ_A_JF_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_NON_HE,
-};
-
-const struct iwl_cfg_trans_params iwl_ax200_trans_cfg = {
+const struct iwl_mac_cfg iwl_ax200_mac_cfg = {
 	.device_family = IWL_DEVICE_FAMILY_22000,
-	.base_params = &iwl_22000_base_params,
+	.base = &iwl_22000_base,
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.bisr_workaround = 1,
 };
 
-const char iwl_ax101_name[] = "Intel(R) Wi-Fi 6 AX101";
-const char iwl_ax200_name[] = "Intel(R) Wi-Fi 6 AX200 160MHz";
-const char iwl_ax201_name[] = "Intel(R) Wi-Fi 6 AX201 160MHz";
-const char iwl_ax203_name[] = "Intel(R) Wi-Fi 6 AX203";
-
 const char iwl_ax200_killer_1650w_name[] =
 	"Killer(R) Wi-Fi 6 AX1650w 160MHz Wireless Network Adapter (200D2W)";
 const char iwl_ax200_killer_1650x_name[] =
@@ -215,213 +132,10 @@ const char iwl_ax201_killer_1650s_name[] =
 const char iwl_ax201_killer_1650i_name[] =
 	"Killer(R) Wi-Fi 6 AX1650i 160MHz Wireless Network Adapter (201NGW)";
 
-const struct iwl_cfg iwl_qu_b0_hr1_b0 = {
-	.fw_name_pre = IWL_QU_B_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.tx_with_siso_diversity = true,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg iwl_qu_b0_hr_b0 = {
-	.fw_name_pre = IWL_QU_B_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg iwl_ax201_cfg_qu_hr = {
-	.name = "Intel(R) Wi-Fi 6 AX201 160MHz",
-	.fw_name_pre = IWL_QU_B_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg iwl_qu_c0_hr1_b0 = {
-	.fw_name_pre = IWL_QU_C_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.tx_with_siso_diversity = true,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg iwl_qu_c0_hr_b0 = {
-	.fw_name_pre = IWL_QU_C_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg iwl_ax201_cfg_qu_c0_hr_b0 = {
-	.name = "Intel(R) Wi-Fi 6 AX201 160MHz",
-	.fw_name_pre = IWL_QU_C_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg iwl_quz_a0_hr1_b0 = {
-	.fw_name_pre = IWL_QUZ_A_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.tx_with_siso_diversity = true,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg iwl_ax201_cfg_quz_hr = {
-	.name = "Intel(R) Wi-Fi 6 AX201 160MHz",
-	.fw_name_pre = IWL_QUZ_A_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-         * This device doesn't support receiving BlockAck with a large bitmap
-         * so we need to restrict the size of transmitted aggregation to the
-         * HT size; mac80211 would otherwise pick the HE max (256) by default.
-         */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg iwl_ax1650s_cfg_quz_hr = {
-	.name = "Killer(R) Wi-Fi 6 AX1650s 160MHz Wireless Network Adapter (201D2W)",
-	.fw_name_pre = IWL_QUZ_A_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-         * This device doesn't support receiving BlockAck with a large bitmap
-         * so we need to restrict the size of transmitted aggregation to the
-         * HT size; mac80211 would otherwise pick the HE max (256) by default.
-         */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg iwl_ax1650i_cfg_quz_hr = {
-	.name = "Killer(R) Wi-Fi 6 AX1650i 160MHz Wireless Network Adapter (201NGW)",
-	.fw_name_pre = IWL_QUZ_A_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-         * This device doesn't support receiving BlockAck with a large bitmap
-         * so we need to restrict the size of transmitted aggregation to the
-         * HT size; mac80211 would otherwise pick the HE max (256) by default.
-         */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg iwl_ax200_cfg_cc = {
-	.fw_name_pre = IWL_CC_A_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0 = {
-	.name = "Killer(R) Wi-Fi 6 AX1650s 160MHz Wireless Network Adapter (201NGW)",
-	.fw_name_pre = IWL_QU_B_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0 = {
-	.name = "Killer(R) Wi-Fi 6 AX1650i 160MHz Wireless Network Adapter (201D2W)",
-	.fw_name_pre = IWL_QU_B_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg killer1650s_2ax_cfg_qu_c0_hr_b0 = {
-	.name = "Killer(R) Wi-Fi 6 AX1650s 160MHz Wireless Network Adapter (201NGW)",
-	.fw_name_pre = IWL_QU_C_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg killer1650i_2ax_cfg_qu_c0_hr_b0 = {
-	.name = "Killer(R) Wi-Fi 6 AX1650i 160MHz Wireless Network Adapter (201D2W)",
-	.fw_name_pre = IWL_QU_C_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
-const struct iwl_cfg iwl_cfg_quz_a0_hr_b0 = {
-	.fw_name_pre = IWL_QUZ_A_HR_B_FW_PRE,
-	IWL_DEVICE_22500,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
-	.num_rbds = IWL_NUM_RBDS_22000_HE,
-};
-
 MODULE_FIRMWARE(IWL_QU_B_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QU_C_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QU_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_QU_C_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QUZ_A_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QUZ_A_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_CC_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
index de7ede59a994..aaae3b1f5433 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2018 - 2020, 2023 Intel Corporation
+ * Copyright(c) 2018 - 2020, 2023, 2025 Intel Corporation
  *****************************************************************************/
 
 #include <linux/module.h>
@@ -30,7 +30,7 @@
 #define IWL5150_FW_PRE "iwlwifi-5150"
 #define IWL5150_MODULE_FIRMWARE(api) IWL5150_FW_PRE "-" __stringify(api) ".ucode"
 
-static const struct iwl_base_params iwl5000_base_params = {
+static const struct iwl_family_base_params iwl5000_base = {
 	.eeprom_size = IWLAGN_EEPROM_IMG_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
@@ -41,11 +41,6 @@ static const struct iwl_base_params iwl5000_base_params = {
 	.scd_chain_ext_wa = true,
 };
 
-static const struct iwl_ht_params iwl5000_ht_params = {
-	.ht_greenfield_support = true,
-	.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
-};
-
 static const struct iwl_eeprom_params iwl5000_eeprom_params = {
 	.regulatory_bands = {
 		EEPROM_REG_BAND_1_CHANNELS,
@@ -58,93 +53,107 @@ static const struct iwl_eeprom_params iwl5000_eeprom_params = {
 	},
 };
 
+const struct iwl_mac_cfg iwl5000_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_5000,
+	.base = &iwl5000_base,
+};
+
 #define IWL_DEVICE_5000						\
 	.fw_name_pre = IWL5000_FW_PRE,				\
 	.ucode_api_max = IWL5000_UCODE_API_MAX,			\
 	.ucode_api_min = IWL5000_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_5000,		\
 	.max_inst_size = IWLAGN_RTC_INST_SIZE,			\
 	.max_data_size = IWLAGN_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_5000_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_5000_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl5000_base_params,		\
 	.eeprom_params = &iwl5000_eeprom_params,		\
 	.led_mode = IWL_LED_BLINK
 
-const struct iwl_cfg iwl5300_agn_cfg = {
-	.name = "Intel(R) Ultimate N WiFi Link 5300 AGN",
+const struct iwl_rf_cfg iwl5300_agn_cfg = {
 	IWL_DEVICE_5000,
 	/* at least EEPROM 0x11A has wrong info */
 	.valid_tx_ant = ANT_ABC,	/* .cfg overwrite */
 	.valid_rx_ant = ANT_ABC,	/* .cfg overwrite */
-	.ht_params = &iwl5000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 };
 
-const struct iwl_cfg iwl5100_bgn_cfg = {
-	.name = "Intel(R) WiFi Link 5100 BGN",
-	IWL_DEVICE_5000,
-	.valid_tx_ant = ANT_B,		/* .cfg overwrite */
-	.valid_rx_ant = ANT_AB,		/* .cfg overwrite */
-	.ht_params = &iwl5000_ht_params,
-};
+const char iwl5300_agn_name[] = "Intel(R) Ultimate N WiFi Link 5300 AGN";
 
-const struct iwl_cfg iwl5100_abg_cfg = {
-	.name = "Intel(R) WiFi Link 5100 ABG",
+const struct iwl_rf_cfg iwl5100_n_cfg = {
 	IWL_DEVICE_5000,
 	.valid_tx_ant = ANT_B,		/* .cfg overwrite */
 	.valid_rx_ant = ANT_AB,		/* .cfg overwrite */
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 };
 
-const struct iwl_cfg iwl5100_agn_cfg = {
-	.name = "Intel(R) WiFi Link 5100 AGN",
+const char iwl5100_bgn_name[] = "Intel(R) WiFi Link 5100 BGN";
+
+const struct iwl_rf_cfg iwl5100_abg_cfg = {
 	IWL_DEVICE_5000,
 	.valid_tx_ant = ANT_B,		/* .cfg overwrite */
 	.valid_rx_ant = ANT_AB,		/* .cfg overwrite */
-	.ht_params = &iwl5000_ht_params,
 };
 
-const struct iwl_cfg iwl5350_agn_cfg = {
-	.name = "Intel(R) WiMAX/WiFi Link 5350 AGN",
+const char iwl5100_abg_name[] = "Intel(R) WiFi Link 5100 ABG";
+const char iwl5100_agn_name[] = "Intel(R) WiFi Link 5100 AGN";
+
+const struct iwl_rf_cfg iwl5350_agn_cfg = {
 	.fw_name_pre = IWL5000_FW_PRE,
 	.ucode_api_max = IWL5000_UCODE_API_MAX,
 	.ucode_api_min = IWL5000_UCODE_API_MIN,
-	.trans.device_family = IWL_DEVICE_FAMILY_5000,
 	.max_inst_size = IWLAGN_RTC_INST_SIZE,
 	.max_data_size = IWLAGN_RTC_DATA_SIZE,
 	.nvm_ver = EEPROM_5050_EEPROM_VERSION,
 	.nvm_calib_ver = EEPROM_5050_TX_POWER_VERSION,
-	.trans.base_params = &iwl5000_base_params,
 	.eeprom_params = &iwl5000_eeprom_params,
-	.ht_params = &iwl5000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 	.led_mode = IWL_LED_BLINK,
 	.internal_wimax_coex = true,
 };
 
+const char iwl5350_agn_name[] = "Intel(R) WiMAX/WiFi Link 5350 AGN";
+
+const struct iwl_mac_cfg iwl5150_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_5150,
+	.base = &iwl5000_base,
+};
+
 #define IWL_DEVICE_5150						\
 	.fw_name_pre = IWL5150_FW_PRE,				\
 	.ucode_api_max = IWL5150_UCODE_API_MAX,			\
 	.ucode_api_min = IWL5150_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_5150,		\
 	.max_inst_size = IWLAGN_RTC_INST_SIZE,			\
 	.max_data_size = IWLAGN_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_5050_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_5050_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl5000_base_params,		\
 	.eeprom_params = &iwl5000_eeprom_params,		\
 	.led_mode = IWL_LED_BLINK,				\
 	.internal_wimax_coex = true
 
-const struct iwl_cfg iwl5150_agn_cfg = {
-	.name = "Intel(R) WiMAX/WiFi Link 5150 AGN",
+const struct iwl_rf_cfg iwl5150_agn_cfg = {
 	IWL_DEVICE_5150,
-	.ht_params = &iwl5000_ht_params,
-
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 };
 
-const struct iwl_cfg iwl5150_abg_cfg = {
-	.name = "Intel(R) WiMAX/WiFi Link 5150 ABG",
+const char iwl5150_agn_name[] = "Intel(R) WiMAX/WiFi Link 5150 AGN";
+
+const struct iwl_rf_cfg iwl5150_abg_cfg = {
 	IWL_DEVICE_5150,
 };
 
+const char iwl5150_abg_name[] = "Intel(R) WiMAX/WiFi Link 5150 ABG";
+
 MODULE_FIRMWARE(IWL5000_MODULE_FIRMWARE(IWL5000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL5150_MODULE_FIRMWARE(IWL5150_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/6000.c b/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
index f013cf420569..ab13394896e0 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2018 - 2020, 2023 Intel Corporation
+ * Copyright(c) 2018 - 2020, 2023, 2025 Intel Corporation
  *****************************************************************************/
 
 #include <linux/module.h>
@@ -49,7 +49,7 @@
 #define IWL6030_FW_PRE "iwlwifi-6000g2b"
 #define IWL6030_MODULE_FIRMWARE(api) IWL6030_FW_PRE "-" __stringify(api) ".ucode"
 
-static const struct iwl_base_params iwl6000_base_params = {
+static const struct iwl_family_base_params iwl6000_base = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
@@ -62,7 +62,7 @@ static const struct iwl_base_params iwl6000_base_params = {
 	.scd_chain_ext_wa = true,
 };
 
-static const struct iwl_base_params iwl6050_base_params = {
+static const struct iwl_family_base_params iwl6050_base = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
@@ -75,7 +75,7 @@ static const struct iwl_base_params iwl6050_base_params = {
 	.scd_chain_ext_wa = true,
 };
 
-static const struct iwl_base_params iwl6000_g2_base_params = {
+static const struct iwl_family_base_params iwl6000_g2_base = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_2K,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.max_tfd_queue_size = 256,
@@ -88,12 +88,6 @@ static const struct iwl_base_params iwl6000_g2_base_params = {
 	.scd_chain_ext_wa = true,
 };
 
-static const struct iwl_ht_params iwl6000_ht_params = {
-	.ht_greenfield_support = true,
-	.use_rts_for_aggregation = true, /* use rts/cts protection */
-	.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
-};
-
 static const struct iwl_eeprom_params iwl6000_eeprom_params = {
 	.regulatory_bands = {
 		EEPROM_REG_BAND_1_CHANNELS,
@@ -107,141 +101,126 @@ static const struct iwl_eeprom_params iwl6000_eeprom_params = {
 	.enhanced_txpower = true,
 };
 
+const struct iwl_mac_cfg iwl6005_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_6005,
+	.base = &iwl6000_g2_base,
+};
+
 #define IWL_DEVICE_6005						\
 	.fw_name_pre = IWL6005_FW_PRE,				\
 	.ucode_api_max = IWL6000G2_UCODE_API_MAX,		\
 	.ucode_api_min = IWL6000G2_UCODE_API_MIN,		\
-	.trans.device_family = IWL_DEVICE_FAMILY_6005,		\
 	.max_inst_size = IWL60_RTC_INST_SIZE,			\
 	.max_data_size = IWL60_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_6005_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_6005_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl6000_g2_base_params,		\
 	.eeprom_params = &iwl6000_eeprom_params,		\
 	.led_mode = IWL_LED_RF_STATE
 
-const struct iwl_cfg iwl6005_2agn_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6205 AGN",
-	IWL_DEVICE_6005,
-	.ht_params = &iwl6000_ht_params,
-};
-
-const struct iwl_cfg iwl6005_2abg_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6205 ABG",
-	IWL_DEVICE_6005,
-};
-
-const struct iwl_cfg iwl6005_2bg_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6205 BG",
+const struct iwl_rf_cfg iwl6005_n_cfg = {
 	IWL_DEVICE_6005,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 };
 
-const struct iwl_cfg iwl6005_2agn_sff_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6205S AGN",
-	IWL_DEVICE_6005,
-	.ht_params = &iwl6000_ht_params,
-};
+const char iwl6005_2agn_name[] = "Intel(R) Centrino(R) Advanced-N 6205 AGN";
+const char iwl6005_2agn_sff_name[] = "Intel(R) Centrino(R) Advanced-N 6205S AGN";
+const char iwl6005_2agn_d_name[] = "Intel(R) Centrino(R) Advanced-N 6205D AGN";
+const char iwl6005_2agn_mow1_name[] = "Intel(R) Centrino(R) Advanced-N 6206 AGN";
+const char iwl6005_2agn_mow2_name[] = "Intel(R) Centrino(R) Advanced-N 6207 AGN";
 
-const struct iwl_cfg iwl6005_2agn_d_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6205D AGN",
+const struct iwl_rf_cfg iwl6005_non_n_cfg = {
 	IWL_DEVICE_6005,
-	.ht_params = &iwl6000_ht_params,
 };
 
-const struct iwl_cfg iwl6005_2agn_mow1_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6206 AGN",
-	IWL_DEVICE_6005,
-	.ht_params = &iwl6000_ht_params,
-};
+const char iwl6005_2abg_name[] = "Intel(R) Centrino(R) Advanced-N 6205 ABG";
+const char iwl6005_2bg_name[] = "Intel(R) Centrino(R) Advanced-N 6205 BG";
 
-const struct iwl_cfg iwl6005_2agn_mow2_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6207 AGN",
-	IWL_DEVICE_6005,
-	.ht_params = &iwl6000_ht_params,
+const struct iwl_mac_cfg iwl6030_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_6030,
+	.base = &iwl6000_g2_base,
 };
 
 #define IWL_DEVICE_6030						\
 	.fw_name_pre = IWL6030_FW_PRE,				\
 	.ucode_api_max = IWL6000G2_UCODE_API_MAX,		\
 	.ucode_api_min = IWL6000G2_UCODE_API_MIN,		\
-	.trans.device_family = IWL_DEVICE_FAMILY_6030,		\
 	.max_inst_size = IWL60_RTC_INST_SIZE,			\
 	.max_data_size = IWL60_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_6030_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_6030_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl6000_g2_base_params,		\
 	.eeprom_params = &iwl6000_eeprom_params,		\
 	.led_mode = IWL_LED_RF_STATE
 
-const struct iwl_cfg iwl6030_2agn_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6230 AGN",
+const struct iwl_rf_cfg iwl6030_n_cfg = {
 	IWL_DEVICE_6030,
-	.ht_params = &iwl6000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 };
 
-const struct iwl_cfg iwl6030_2abg_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6230 ABG",
-	IWL_DEVICE_6030,
-};
+const char iwl6030_2agn_name[] = "Intel(R) Centrino(R) Advanced-N 6230 AGN";
+const char iwl6030_2bgn_name[] = "Intel(R) Centrino(R) Advanced-N 6230 BGN";
+const char iwl1030_bgn_name[] = "Intel(R) Centrino(R) Wireless-N 1030 BGN";
+const char iwl1030_bg_name[] = "Intel(R) Centrino(R) Wireless-N 1030 BG";
 
-const struct iwl_cfg iwl6030_2bgn_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6230 BGN",
+const struct iwl_rf_cfg iwl6030_non_n_cfg = {
 	IWL_DEVICE_6030,
-	.ht_params = &iwl6000_ht_params,
 };
 
-const struct iwl_cfg iwl6030_2bg_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6230 BG",
-	IWL_DEVICE_6030,
-};
+const char iwl6030_2abg_name[] = "Intel(R) Centrino(R) Advanced-N 6230 ABG";
+const char iwl6030_2bg_name[] = "Intel(R) Centrino(R) Advanced-N 6230 BG";
 
 #define IWL_DEVICE_6035						\
 	.fw_name_pre = IWL6030_FW_PRE,				\
 	.ucode_api_max = IWL6035_UCODE_API_MAX,			\
 	.ucode_api_min = IWL6035_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_6030,		\
 	.max_inst_size = IWL60_RTC_INST_SIZE,			\
 	.max_data_size = IWL60_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_6030_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_6030_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl6000_g2_base_params,		\
 	.eeprom_params = &iwl6000_eeprom_params,		\
 	.led_mode = IWL_LED_RF_STATE
 
-const struct iwl_cfg iwl6035_2agn_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6235 AGN",
+const struct iwl_rf_cfg iwl6035_2agn_cfg = {
 	IWL_DEVICE_6035,
-	.ht_params = &iwl6000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 };
 
-const struct iwl_cfg iwl6035_2agn_sff_cfg = {
-	.name = "Intel(R) Centrino(R) Ultimate-N 6235 AGN",
-	IWL_DEVICE_6035,
-	.ht_params = &iwl6000_ht_params,
-};
+const char iwl6035_2agn_name[] = "Intel(R) Centrino(R) Advanced-N 6235 AGN";
+const char iwl6035_2agn_sff_name[] = "Intel(R) Centrino(R) Ultimate-N 6235 AGN";
 
-const struct iwl_cfg iwl1030_bgn_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 1030 BGN",
+const struct iwl_rf_cfg iwl130_bgn_cfg = {
 	IWL_DEVICE_6030,
-	.ht_params = &iwl6000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
+	.rx_with_siso_diversity = true,
 };
 
-const struct iwl_cfg iwl1030_bg_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 1030 BG",
-	IWL_DEVICE_6030,
-};
+const char iwl130_bgn_name[] = "Intel(R) Centrino(R) Wireless-N 130 BGN";
 
-const struct iwl_cfg iwl130_bgn_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 130 BGN",
+const struct iwl_rf_cfg iwl130_bg_cfg = {
 	IWL_DEVICE_6030,
-	.ht_params = &iwl6000_ht_params,
 	.rx_with_siso_diversity = true,
 };
 
-const struct iwl_cfg iwl130_bg_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N 130 BG",
-	IWL_DEVICE_6030,
-	.rx_with_siso_diversity = true,
+const char iwl130_bg_name[] = "Intel(R) Centrino(R) Wireless-N 130 BG";
+
+const struct iwl_mac_cfg iwl6000i_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_6000i,
+	.base = &iwl6000_base,
 };
 
 /*
@@ -251,101 +230,127 @@ const struct iwl_cfg iwl130_bg_cfg = {
 	.fw_name_pre = IWL6000_FW_PRE,				\
 	.ucode_api_max = IWL6000_UCODE_API_MAX,			\
 	.ucode_api_min = IWL6000_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_6000i,		\
 	.max_inst_size = IWL60_RTC_INST_SIZE,			\
 	.max_data_size = IWL60_RTC_DATA_SIZE,			\
 	.valid_tx_ant = ANT_BC,		/* .cfg overwrite */	\
 	.valid_rx_ant = ANT_BC,		/* .cfg overwrite */	\
 	.nvm_ver = EEPROM_6000_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_6000_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl6000_base_params,		\
 	.eeprom_params = &iwl6000_eeprom_params,		\
 	.led_mode = IWL_LED_BLINK
 
-const struct iwl_cfg iwl6000i_2agn_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6200 AGN",
+const struct iwl_rf_cfg iwl6000i_2agn_cfg = {
 	IWL_DEVICE_6000i,
-	.ht_params = &iwl6000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 };
 
-const struct iwl_cfg iwl6000i_2abg_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6200 ABG",
+const char iwl6000i_2agn_name[] = "Intel(R) Centrino(R) Advanced-N 6200 AGN";
+
+const struct iwl_rf_cfg iwl6000i_non_n_cfg = {
 	IWL_DEVICE_6000i,
 };
 
-const struct iwl_cfg iwl6000i_2bg_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N 6200 BG",
-	IWL_DEVICE_6000i,
+const char iwl6000i_2abg_name[] = "Intel(R) Centrino(R) Advanced-N 6200 ABG";
+const char iwl6000i_2bg_name[] = "Intel(R) Centrino(R) Advanced-N 6200 BG";
+
+const struct iwl_mac_cfg iwl6050_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_6050,
+	.base = &iwl6050_base,
 };
 
 #define IWL_DEVICE_6050						\
 	.fw_name_pre = IWL6050_FW_PRE,				\
 	.ucode_api_max = IWL6050_UCODE_API_MAX,			\
 	.ucode_api_min = IWL6050_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_6050,		\
 	.max_inst_size = IWL60_RTC_INST_SIZE,			\
 	.max_data_size = IWL60_RTC_DATA_SIZE,			\
 	.valid_tx_ant = ANT_AB,		/* .cfg overwrite */	\
 	.valid_rx_ant = ANT_AB,		/* .cfg overwrite */	\
 	.nvm_ver = EEPROM_6050_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_6050_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl6050_base_params,		\
 	.eeprom_params = &iwl6000_eeprom_params,		\
 	.led_mode = IWL_LED_BLINK,				\
 	.internal_wimax_coex = true
 
-const struct iwl_cfg iwl6050_2agn_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N + WiMAX 6250 AGN",
+const struct iwl_rf_cfg iwl6050_2agn_cfg = {
 	IWL_DEVICE_6050,
-	.ht_params = &iwl6000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 };
 
-const struct iwl_cfg iwl6050_2abg_cfg = {
-	.name = "Intel(R) Centrino(R) Advanced-N + WiMAX 6250 ABG",
+const char iwl6050_2agn_name[] = "Intel(R) Centrino(R) Advanced-N + WiMAX 6250 AGN";
+
+const struct iwl_rf_cfg iwl6050_2abg_cfg = {
 	IWL_DEVICE_6050,
 };
 
+const char iwl6050_2abg_name[] = "Intel(R) Centrino(R) Advanced-N + WiMAX 6250 ABG";
+
+const struct iwl_mac_cfg iwl6150_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_6150,
+	.base = &iwl6050_base,
+};
+
 #define IWL_DEVICE_6150						\
 	.fw_name_pre = IWL6050_FW_PRE,				\
 	.ucode_api_max = IWL6050_UCODE_API_MAX,			\
 	.ucode_api_min = IWL6050_UCODE_API_MIN,			\
-	.trans.device_family = IWL_DEVICE_FAMILY_6150,		\
 	.max_inst_size = IWL60_RTC_INST_SIZE,			\
 	.max_data_size = IWL60_RTC_DATA_SIZE,			\
 	.nvm_ver = EEPROM_6150_EEPROM_VERSION,		\
 	.nvm_calib_ver = EEPROM_6150_TX_POWER_VERSION,	\
-	.trans.base_params = &iwl6050_base_params,		\
 	.eeprom_params = &iwl6000_eeprom_params,		\
 	.led_mode = IWL_LED_BLINK,				\
 	.internal_wimax_coex = true
 
-const struct iwl_cfg iwl6150_bgn_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BGN",
+const struct iwl_rf_cfg iwl6150_bgn_cfg = {
 	IWL_DEVICE_6150,
-	.ht_params = &iwl6000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 };
 
-const struct iwl_cfg iwl6150_bg_cfg = {
-	.name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BG",
+const char iwl6150_bgn_name[] = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BGN";
+
+const struct iwl_rf_cfg iwl6150_bg_cfg = {
 	IWL_DEVICE_6150,
 };
 
-const struct iwl_cfg iwl6000_3agn_cfg = {
-	.name = "Intel(R) Centrino(R) Ultimate-N 6300 AGN",
+const char iwl6150_bg_name[] = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BG";
+
+const struct iwl_mac_cfg iwl6000_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_6000,
+	.base = &iwl6000_base,
+};
+
+const struct iwl_rf_cfg iwl6000_3agn_cfg = {
 	.fw_name_pre = IWL6000_FW_PRE,
 	.ucode_api_max = IWL6000_UCODE_API_MAX,
 	.ucode_api_min = IWL6000_UCODE_API_MIN,
-	.trans.device_family = IWL_DEVICE_FAMILY_6000,
 	.max_inst_size = IWL60_RTC_INST_SIZE,
 	.max_data_size = IWL60_RTC_DATA_SIZE,
 	.nvm_ver = EEPROM_6000_EEPROM_VERSION,
 	.nvm_calib_ver = EEPROM_6000_TX_POWER_VERSION,
-	.trans.base_params = &iwl6000_base_params,
 	.eeprom_params = &iwl6000_eeprom_params,
-	.ht_params = &iwl6000_ht_params,
+	.ht_params = {
+		.ht_greenfield_support = true,
+		.use_rts_for_aggregation = true, /* use rts/cts protection */
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 	.led_mode = IWL_LED_BLINK,
 };
 
+const char iwl6000_3agn_name[] = "Intel(R) Centrino(R) Ultimate-N 6300 AGN";
+
 MODULE_FIRMWARE(IWL6000_MODULE_FIRMWARE(IWL6000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL6050_MODULE_FIRMWARE(IWL6050_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL6005_MODULE_FIRMWARE(IWL6000G2_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
index 4e2afdedf4c6..f987ad3192c1 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2020, 2023 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2020, 2023, 2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015 Intel Deutschland GmbH
  */
@@ -49,7 +49,7 @@
 #define IWL7265D_FW_PRE "iwlwifi-7265D"
 #define IWL7265D_MODULE_FIRMWARE(api) IWL7265D_FW_PRE "-" __stringify(api) ".ucode"
 
-static const struct iwl_base_params iwl7000_base_params = {
+static const struct iwl_family_base_params iwl7000_base = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_16K,
 	.num_of_queues = 31,
 	.max_tfd_queue_size = 256,
@@ -60,6 +60,7 @@ static const struct iwl_base_params iwl7000_base_params = {
 	.shadow_reg_enable = true,
 	.pcie_l1_allowed = true,
 	.apmg_wake_up_wa = true,
+	.nvm_hw_section_num = 0,
 };
 
 static const struct iwl_tt_params iwl7000_high_temp_tt_params = {
@@ -84,16 +85,13 @@ static const struct iwl_tt_params iwl7000_high_temp_tt_params = {
 	.support_tx_backoff = true,
 };
 
-static const struct iwl_ht_params iwl7000_ht_params = {
-	.stbc = true,
-	.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+const struct iwl_mac_cfg iwl7000_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_7000,
+	.base = &iwl7000_base,
 };
 
 #define IWL_DEVICE_7000_COMMON					\
-	.trans.device_family = IWL_DEVICE_FAMILY_7000,		\
-	.trans.base_params = &iwl7000_base_params,		\
 	.led_mode = IWL_LED_RF_STATE,				\
-	.nvm_hw_section_num = 0,				\
 	.non_shared_ant = ANT_A,				\
 	.dccm_offset = IWL7000_DCCM_OFFSET
 
@@ -117,77 +115,52 @@ static const struct iwl_ht_params iwl7000_ht_params = {
 	.ucode_api_max = IWL7265D_UCODE_API_MAX,		\
 	.ucode_api_min = IWL7265D_UCODE_API_MIN
 
-const struct iwl_cfg iwl7260_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC 7260",
+const char iwl7260_2ac_name[] = "Intel(R) Dual Band Wireless AC 7260";
+const char iwl7260_2n_name[] = "Intel(R) Dual Band Wireless N 7260";
+const char iwl7260_n_name[] = "Intel(R) Wireless N 7260";
+const char iwl3160_2ac_name[] = "Intel(R) Dual Band Wireless AC 3160";
+const char iwl3160_2n_name[] = "Intel(R) Dual Band Wireless N 3160";
+const char iwl3160_n_name[] = "Intel(R) Wireless N 3160";
+const char iwl3165_2ac_name[] = "Intel(R) Dual Band Wireless-AC 3165";
+const char iwl3168_2ac_name[] = "Intel(R) Dual Band Wireless-AC 3168";
+const char iwl7265_2ac_name[] = "Intel(R) Dual Band Wireless-AC 7265";
+const char iwl7265_2n_name[] = "Intel(R) Dual Band Wireless-N 7265";
+const char iwl7265_n_name[] = "Intel(R) Wireless-N 7265";
+
+const struct iwl_rf_cfg iwl7260_cfg = {
 	.fw_name_pre = IWL7260_FW_PRE,
 	IWL_DEVICE_7000,
-	.ht_params = &iwl7000_ht_params,
+	.ht_params = {
+		.stbc = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 	.nvm_ver = IWL7260_NVM_VERSION,
 	.host_interrupt_operation_mode = true,
 	.lp_xtal_workaround = true,
 	.dccm_len = IWL7260_DCCM_LEN,
 };
 
-const struct iwl_cfg iwl7260_2ac_cfg_high_temp = {
-	.name = "Intel(R) Dual Band Wireless AC 7260",
+const struct iwl_rf_cfg iwl7260_high_temp_cfg = {
 	.fw_name_pre = IWL7260_FW_PRE,
 	IWL_DEVICE_7000,
-	.ht_params = &iwl7000_ht_params,
+	.ht_params = {
+		.stbc = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 	.nvm_ver = IWL7260_NVM_VERSION,
-	.high_temp = true,
 	.host_interrupt_operation_mode = true,
 	.lp_xtal_workaround = true,
 	.dccm_len = IWL7260_DCCM_LEN,
 	.thermal_params = &iwl7000_high_temp_tt_params,
 };
 
-const struct iwl_cfg iwl7260_2n_cfg = {
-	.name = "Intel(R) Dual Band Wireless N 7260",
-	.fw_name_pre = IWL7260_FW_PRE,
-	IWL_DEVICE_7000,
-	.ht_params = &iwl7000_ht_params,
-	.nvm_ver = IWL7260_NVM_VERSION,
-	.host_interrupt_operation_mode = true,
-	.lp_xtal_workaround = true,
-	.dccm_len = IWL7260_DCCM_LEN,
-};
-
-const struct iwl_cfg iwl7260_n_cfg = {
-	.name = "Intel(R) Wireless N 7260",
-	.fw_name_pre = IWL7260_FW_PRE,
-	IWL_DEVICE_7000,
-	.ht_params = &iwl7000_ht_params,
-	.nvm_ver = IWL7260_NVM_VERSION,
-	.host_interrupt_operation_mode = true,
-	.lp_xtal_workaround = true,
-	.dccm_len = IWL7260_DCCM_LEN,
-};
-
-const struct iwl_cfg iwl3160_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC 3160",
+const struct iwl_rf_cfg iwl3160_cfg = {
 	.fw_name_pre = IWL3160_FW_PRE,
 	IWL_DEVICE_7000,
-	.ht_params = &iwl7000_ht_params,
-	.nvm_ver = IWL3160_NVM_VERSION,
-	.host_interrupt_operation_mode = true,
-	.dccm_len = IWL3160_DCCM_LEN,
-};
-
-const struct iwl_cfg iwl3160_2n_cfg = {
-	.name = "Intel(R) Dual Band Wireless N 3160",
-	.fw_name_pre = IWL3160_FW_PRE,
-	IWL_DEVICE_7000,
-	.ht_params = &iwl7000_ht_params,
-	.nvm_ver = IWL3160_NVM_VERSION,
-	.host_interrupt_operation_mode = true,
-	.dccm_len = IWL3160_DCCM_LEN,
-};
-
-const struct iwl_cfg iwl3160_n_cfg = {
-	.name = "Intel(R) Wireless N 3160",
-	.fw_name_pre = IWL3160_FW_PRE,
-	IWL_DEVICE_7000,
-	.ht_params = &iwl7000_ht_params,
+	.ht_params = {
+		.stbc = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 	.nvm_ver = IWL3160_NVM_VERSION,
 	.host_interrupt_operation_mode = true,
 	.dccm_len = IWL3160_DCCM_LEN,
@@ -204,88 +177,52 @@ static const struct iwl_pwr_tx_backoff iwl7265_pwr_tx_backoffs[] = {
 	{0},
 };
 
-static const struct iwl_ht_params iwl7265_ht_params = {
-	.stbc = true,
-	.ldpc = true,
-	.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
-};
-
-const struct iwl_cfg iwl3165_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC 3165",
+const struct iwl_rf_cfg iwl3165_2ac_cfg = {
 	.fw_name_pre = IWL7265D_FW_PRE,
 	IWL_DEVICE_7005D,
-	.ht_params = &iwl7000_ht_params,
+	.ht_params = {
+		.stbc = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 	.nvm_ver = IWL3165_NVM_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
 };
 
-const struct iwl_cfg iwl3168_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC 3168",
+const struct iwl_rf_cfg iwl3168_2ac_cfg = {
 	.fw_name_pre = IWL3168_FW_PRE,
 	IWL_DEVICE_3008,
-	.ht_params = &iwl7000_ht_params,
+	.ht_params = {
+		.stbc = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 	.nvm_ver = IWL3168_NVM_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
 	.nvm_type = IWL_NVM_SDP,
 };
 
-const struct iwl_cfg iwl7265_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC 7265",
-	.fw_name_pre = IWL7265_FW_PRE,
-	IWL_DEVICE_7005,
-	.ht_params = &iwl7265_ht_params,
-	.nvm_ver = IWL7265_NVM_VERSION,
-	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
-	.dccm_len = IWL7265_DCCM_LEN,
-};
-
-const struct iwl_cfg iwl7265_2n_cfg = {
-	.name = "Intel(R) Dual Band Wireless N 7265",
-	.fw_name_pre = IWL7265_FW_PRE,
-	IWL_DEVICE_7005,
-	.ht_params = &iwl7265_ht_params,
-	.nvm_ver = IWL7265_NVM_VERSION,
-	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
-	.dccm_len = IWL7265_DCCM_LEN,
-};
-
-const struct iwl_cfg iwl7265_n_cfg = {
-	.name = "Intel(R) Wireless N 7265",
+const struct iwl_rf_cfg iwl7265_cfg = {
 	.fw_name_pre = IWL7265_FW_PRE,
 	IWL_DEVICE_7005,
-	.ht_params = &iwl7265_ht_params,
+	.ht_params = {
+		.stbc = true,
+		.ldpc = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 	.nvm_ver = IWL7265_NVM_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
 };
 
-const struct iwl_cfg iwl7265d_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC 7265",
-	.fw_name_pre = IWL7265D_FW_PRE,
-	IWL_DEVICE_7005D,
-	.ht_params = &iwl7265_ht_params,
-	.nvm_ver = IWL7265D_NVM_VERSION,
-	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
-	.dccm_len = IWL7265_DCCM_LEN,
-};
-
-const struct iwl_cfg iwl7265d_2n_cfg = {
-	.name = "Intel(R) Dual Band Wireless N 7265",
+const struct iwl_rf_cfg iwl7265d_cfg = {
 	.fw_name_pre = IWL7265D_FW_PRE,
 	IWL_DEVICE_7005D,
-	.ht_params = &iwl7265_ht_params,
-	.nvm_ver = IWL7265D_NVM_VERSION,
-	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
-	.dccm_len = IWL7265_DCCM_LEN,
-};
-
-const struct iwl_cfg iwl7265d_n_cfg = {
-	.name = "Intel(R) Wireless N 7265",
-	.fw_name_pre = IWL7265D_FW_PRE,
-	IWL_DEVICE_7005D,
-	.ht_params = &iwl7265_ht_params,
+	.ht_params = {
+		.stbc = true,
+		.ldpc = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 	.nvm_ver = IWL7265D_NVM_VERSION,
 	.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
 	.dccm_len = IWL7265_DCCM_LEN,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
index d09cf8d7dc01..b56574006ee0 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2014, 2018-2020, 2023 Intel Corporation
+ * Copyright (C) 2014, 2018-2020, 2023, 2025 Intel Corporation
  * Copyright (C) 2014-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016 Intel Deutschland GmbH
  */
@@ -35,9 +35,7 @@
 #define IWL8265_MODULE_FIRMWARE(api) \
 	IWL8265_FW_PRE "-" __stringify(api) ".ucode"
 
-#define DEFAULT_NVM_FILE_FAMILY_8000C		"nvmData-8000C"
-
-static const struct iwl_base_params iwl8000_base_params = {
+static const struct iwl_family_base_params iwl8000_base = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
 	.num_of_queues = 31,
 	.max_tfd_queue_size = 256,
@@ -47,12 +45,12 @@ static const struct iwl_base_params iwl8000_base_params = {
 	.max_event_log_size = 512,
 	.shadow_reg_enable = true,
 	.pcie_l1_allowed = true,
-};
-
-static const struct iwl_ht_params iwl8000_ht_params = {
-	.stbc = true,
-	.ldpc = true,
-	.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	.nvm_hw_section_num = 10,
+	.features = NETIF_F_RXCSUM,
+	.smem_offset = IWL8260_SMEM_OFFSET,
+	.smem_len = IWL8260_SMEM_LEN,
+	.apmg_not_supported = true,
+	.min_umac_error_event_table = 0x800000,
 };
 
 static const struct iwl_tt_params iwl8000_tt_params = {
@@ -76,30 +74,20 @@ static const struct iwl_tt_params iwl8000_tt_params = {
 	.support_tx_backoff = true,
 };
 
+const struct iwl_mac_cfg iwl8000_mac_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_8000,
+	.base = &iwl8000_base,
+};
+
 #define IWL_DEVICE_8000_COMMON						\
-	.trans.device_family = IWL_DEVICE_FAMILY_8000,			\
-	.trans.base_params = &iwl8000_base_params,			\
 	.led_mode = IWL_LED_RF_STATE,					\
-	.nvm_hw_section_num = 10,					\
-	.features = NETIF_F_RXCSUM,					\
 	.non_shared_ant = ANT_A,					\
 	.dccm_offset = IWL8260_DCCM_OFFSET,				\
 	.dccm_len = IWL8260_DCCM_LEN,					\
 	.dccm2_offset = IWL8260_DCCM2_OFFSET,				\
 	.dccm2_len = IWL8260_DCCM2_LEN,					\
-	.smem_offset = IWL8260_SMEM_OFFSET,				\
-	.smem_len = IWL8260_SMEM_LEN,					\
-	.default_nvm_file_C_step = DEFAULT_NVM_FILE_FAMILY_8000C,	\
 	.thermal_params = &iwl8000_tt_params,				\
-	.apmg_not_supported = true,					\
-	.nvm_type = IWL_NVM_EXT,					\
-	.dbgc_supported = true,						\
-	.min_umac_error_event_table = 0x800000
-
-#define IWL_DEVICE_8000							\
-	IWL_DEVICE_8000_COMMON,						\
-	.ucode_api_max = IWL8000_UCODE_API_MAX,				\
-	.ucode_api_min = IWL8000_UCODE_API_MIN				\
+	.nvm_type = IWL_NVM_EXT
 
 #define IWL_DEVICE_8260							\
 	IWL_DEVICE_8000_COMMON,						\
@@ -111,47 +99,39 @@ static const struct iwl_tt_params iwl8000_tt_params = {
 	.ucode_api_max = IWL8265_UCODE_API_MAX,				\
 	.ucode_api_min = IWL8265_UCODE_API_MIN				\
 
-const struct iwl_cfg iwl8260_2n_cfg = {
-	.name = "Intel(R) Dual Band Wireless N 8260",
-	.fw_name_pre = IWL8000_FW_PRE,
-	IWL_DEVICE_8260,
-	.ht_params = &iwl8000_ht_params,
-	.nvm_ver = IWL8000_NVM_VERSION,
-};
+const char iwl8260_2n_name[] = "Intel(R) Dual Band Wireless-N 8260";
+const char iwl8260_2ac_name[] = "Intel(R) Dual Band Wireless-AC 8260";
+const char iwl8265_2ac_name[] = "Intel(R) Dual Band Wireless-AC 8265";
+const char iwl8275_2ac_name[] = "Intel(R) Dual Band Wireless-AC 8275";
+const char iwl4165_2ac_name[] = "Intel(R) Dual Band Wireless-AC 4165";
 
-const struct iwl_cfg iwl8260_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC 8260",
+const char iwl_killer_1435i_name[] =
+	"Killer(R) Wireless-AC 1435i Wireless Network Adapter (8265D2W)";
+const char iwl_killer_1434_kix_name[] =
+	"Killer(R) Wireless-AC 1435-KIX Wireless Network Adapter (8265NGW)";
+
+const struct iwl_rf_cfg iwl8260_cfg = {
 	.fw_name_pre = IWL8000_FW_PRE,
 	IWL_DEVICE_8260,
-	.ht_params = &iwl8000_ht_params,
+	.ht_params = {
+		.stbc = true,
+		.ldpc = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 	.nvm_ver = IWL8000_NVM_VERSION,
 };
 
-const struct iwl_cfg iwl8265_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC 8265",
+const struct iwl_rf_cfg iwl8265_cfg = {
 	.fw_name_pre = IWL8265_FW_PRE,
 	IWL_DEVICE_8265,
-	.ht_params = &iwl8000_ht_params,
-	.nvm_ver = IWL8000_NVM_VERSION,
-	.vht_mu_mimo_supported = true,
-};
-
-const struct iwl_cfg iwl8275_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC 8275",
-	.fw_name_pre = IWL8265_FW_PRE,
-	IWL_DEVICE_8265,
-	.ht_params = &iwl8000_ht_params,
+	.ht_params = {
+		.stbc = true,
+		.ldpc = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
+	},
 	.nvm_ver = IWL8000_NVM_VERSION,
 	.vht_mu_mimo_supported = true,
 };
 
-const struct iwl_cfg iwl4165_2ac_cfg = {
-	.name = "Intel(R) Dual Band Wireless AC 4165",
-	.fw_name_pre = IWL8000_FW_PRE,
-	IWL_DEVICE_8000,
-	.ht_params = &iwl8000_ht_params,
-	.nvm_ver = IWL8000_NVM_VERSION,
-};
-
 MODULE_FIRMWARE(IWL8000_MODULE_FIRMWARE(IWL8000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL8265_MODULE_FIRMWARE(IWL8265_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
index 0130d9a9b78b..ac1fa291cf2f 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2021, 2023 Intel Corporation
+ * Copyright (C) 2018-2021, 2023, 2025 Intel Corporation
  */
 #include <linux/module.h>
 #include <linux/stringify.h>
@@ -15,14 +15,7 @@
 /* Lowest firmware API version supported */
 #define IWL9000_UCODE_API_MIN	30
 
-/* NVM versions */
-#define IWL9000_NVM_VERSION		0x0a1d
-
 /* Memory offsets and lengths */
-#define IWL9000_DCCM_OFFSET		0x800000
-#define IWL9000_DCCM_LEN		0x18000
-#define IWL9000_DCCM2_OFFSET		0x880000
-#define IWL9000_DCCM2_LEN		0x8000
 #define IWL9000_SMEM_OFFSET		0x400000
 #define IWL9000_SMEM_LEN		0x68000
 
@@ -33,7 +26,7 @@
 #define IWL9260_MODULE_FIRMWARE(api) \
 	IWL9260_FW_PRE "-" __stringify(api) ".ucode"
 
-static const struct iwl_base_params iwl9000_base_params = {
+static const struct iwl_family_base_params iwl9000_base = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
 	.num_of_queues = 31,
 	.max_tfd_queue_size = 256,
@@ -43,150 +36,69 @@ static const struct iwl_base_params iwl9000_base_params = {
 	.max_event_log_size = 512,
 	.shadow_reg_enable = true,
 	.pcie_l1_allowed = true,
-};
-
-static const struct iwl_ht_params iwl9000_ht_params = {
-	.stbc = true,
-	.ldpc = true,
-	.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
-};
-
-static const struct iwl_tt_params iwl9000_tt_params = {
-	.ct_kill_entry = 115,
-	.ct_kill_exit = 93,
-	.ct_kill_duration = 5,
-	.dynamic_smps_entry = 111,
-	.dynamic_smps_exit = 107,
-	.tx_protection_entry = 112,
-	.tx_protection_exit = 105,
-	.tx_backoff = {
-		{.temperature = 110, .backoff = 200},
-		{.temperature = 111, .backoff = 600},
-		{.temperature = 112, .backoff = 1200},
-		{.temperature = 113, .backoff = 2000},
-		{.temperature = 114, .backoff = 4000},
+	.smem_offset = IWL9000_SMEM_OFFSET,
+	.smem_len = IWL9000_SMEM_LEN,
+	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,
+	.apmg_not_supported = true,
+	.mac_addr_from_csr = 0x380,
+	.min_umac_error_event_table = 0x800000,
+	.d3_debug_data_base_addr = 0x401000,
+	.d3_debug_data_length = 92 * 1024,
+	.nvm_hw_section_num = 10,
+	.mon_smem_regs = {
+		.write_ptr = {
+			.addr = LDBG_M2S_BUF_WPTR,
+			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,
+		},
+		.cycle_cnt = {
+			.addr = LDBG_M2S_BUF_WRAP_CNT,
+			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,
+		},
+	},
+	.mon_dram_regs = {
+		.write_ptr = {
+			.addr = MON_BUFF_WRPTR_VER2,
+			.mask = 0xffffffff,
+		},
+		.cycle_cnt = {
+			.addr = MON_BUFF_CYCLE_CNT_VER2,
+			.mask = 0xffffffff,
+		},
 	},
-	.support_ct_kill = true,
-	.support_dynamic_smps = true,
-	.support_tx_protection = true,
-	.support_tx_backoff = true,
+	.ucode_api_max = IWL9000_UCODE_API_MAX,
+	.ucode_api_min = IWL9000_UCODE_API_MIN,
 };
 
-#define IWL_DEVICE_9000							\
-	.ucode_api_max = IWL9000_UCODE_API_MAX,				\
-	.ucode_api_min = IWL9000_UCODE_API_MIN,				\
-	.led_mode = IWL_LED_RF_STATE,					\
-	.nvm_hw_section_num = 10,					\
-	.non_shared_ant = ANT_B,					\
-	.dccm_offset = IWL9000_DCCM_OFFSET,				\
-	.dccm_len = IWL9000_DCCM_LEN,					\
-	.dccm2_offset = IWL9000_DCCM2_OFFSET,				\
-	.dccm2_len = IWL9000_DCCM2_LEN,					\
-	.smem_offset = IWL9000_SMEM_OFFSET,				\
-	.smem_len = IWL9000_SMEM_LEN,					\
-	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,		\
-	.thermal_params = &iwl9000_tt_params,				\
-	.apmg_not_supported = true,					\
-	.num_rbds = 512,						\
-	.vht_mu_mimo_supported = true,					\
-	.mac_addr_from_csr = 0x380,					\
-	.nvm_type = IWL_NVM_EXT,					\
-	.dbgc_supported = true,						\
-	.min_umac_error_event_table = 0x800000,				\
-	.d3_debug_data_base_addr = 0x401000,				\
-	.d3_debug_data_length = 92 * 1024,				\
-	.ht_params = &iwl9000_ht_params,				\
-	.nvm_ver = IWL9000_NVM_VERSION,					\
-	.mon_smem_regs = {						\
-		.write_ptr = {						\
-			.addr = LDBG_M2S_BUF_WPTR,			\
-			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,		\
-		},							\
-		.cycle_cnt = {						\
-			.addr = LDBG_M2S_BUF_WRAP_CNT,			\
-			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,		\
-		},							\
-	},								\
-	.mon_dram_regs = {						\
-		.write_ptr = {						\
-			.addr = MON_BUFF_WRPTR_VER2,			\
-			.mask = 0xffffffff,				\
-		},							\
-		.cycle_cnt = {						\
-			.addr = MON_BUFF_CYCLE_CNT_VER2,		\
-			.mask = 0xffffffff,				\
-		},							\
-	}
-
-const struct iwl_cfg_trans_params iwl9000_trans_cfg = {
+const struct iwl_mac_cfg iwl9000_mac_cfg = {
 	.device_family = IWL_DEVICE_FAMILY_9000,
-	.base_params = &iwl9000_base_params,
+	.base = &iwl9000_base,
 	.mq_rx_supported = true,
-	.rf_id = true,
 };
 
-const struct iwl_cfg_trans_params iwl9560_trans_cfg = {
+const struct iwl_mac_cfg iwl9560_mac_cfg = {
 	.device_family = IWL_DEVICE_FAMILY_9000,
-	.base_params = &iwl9000_base_params,
+	.base = &iwl9000_base,
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.integrated = true,
 	.xtal_latency = 650,
 };
 
-const struct iwl_cfg_trans_params iwl9560_long_latency_trans_cfg = {
+const struct iwl_mac_cfg iwl9560_long_latency_mac_cfg = {
 	.device_family = IWL_DEVICE_FAMILY_9000,
-	.base_params = &iwl9000_base_params,
+	.base = &iwl9000_base,
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.integrated = true,
 	.xtal_latency = 2820,
 };
 
-const struct iwl_cfg_trans_params iwl9560_shared_clk_trans_cfg = {
+const struct iwl_mac_cfg iwl9560_shared_clk_mac_cfg = {
 	.device_family = IWL_DEVICE_FAMILY_9000,
-	.base_params = &iwl9000_base_params,
+	.base = &iwl9000_base,
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.integrated = true,
 	.xtal_latency = 670,
 	.extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK
 };
 
-const char iwl9162_name[] = "Intel(R) Wireless-AC 9162";
-const char iwl9260_name[] = "Intel(R) Wireless-AC 9260";
-const char iwl9260_1_name[] = "Intel(R) Wireless-AC 9260-1";
-const char iwl9270_name[] = "Intel(R) Wireless-AC 9270";
-const char iwl9461_name[] = "Intel(R) Wireless-AC 9461";
-const char iwl9462_name[] = "Intel(R) Wireless-AC 9462";
-const char iwl9560_name[] = "Intel(R) Wireless-AC 9560";
-const char iwl9162_160_name[] = "Intel(R) Wireless-AC 9162 160MHz";
-const char iwl9260_160_name[] = "Intel(R) Wireless-AC 9260 160MHz";
-const char iwl9270_160_name[] = "Intel(R) Wireless-AC 9270 160MHz";
-const char iwl9461_160_name[] = "Intel(R) Wireless-AC 9461 160MHz";
-const char iwl9462_160_name[] = "Intel(R) Wireless-AC 9462 160MHz";
-const char iwl9560_160_name[] = "Intel(R) Wireless-AC 9560 160MHz";
-
-const char iwl9260_killer_1550_name[] =
-	"Killer (R) Wireless-AC 1550 Wireless Network Adapter (9260NGW) 160MHz";
-const char iwl9560_killer_1550i_name[] =
-	"Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)";
-const char iwl9560_killer_1550i_160_name[] =
-	"Killer(R) Wireless-AC 1550i Wireless Network Adapter (9560NGW) 160MHz";
-const char iwl9560_killer_1550s_name[] =
-	"Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)";
-const char iwl9560_killer_1550s_160_name[] =
-	"Killer(R) Wireless-AC 1550s Wireless Network Adapter (9560D2W) 160MHz";
-
-const struct iwl_cfg iwl9260_2ac_cfg = {
-	.fw_name_pre = IWL9260_FW_PRE,
-	IWL_DEVICE_9000,
-};
-
-const struct iwl_cfg iwl9560_2ac_cfg_soc = {
-	.fw_name_pre = IWL9000_FW_PRE,
-	IWL_DEVICE_9000,
-};
-
 MODULE_FIRMWARE(IWL9000_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL9260_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c
index e87b57b9e2c0..3bf9fdbe01c6 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include <linux/module.h>
 #include <linux/stringify.h>
@@ -15,14 +15,7 @@
 /* Lowest firmware API version supported */
 #define IWL_AX210_UCODE_API_MIN	77
 
-/* NVM versions */
-#define IWL_AX210_NVM_VERSION		0x0a1d
-
 /* Memory offsets and lengths */
-#define IWL_AX210_DCCM_OFFSET		0x800000 /* LMAC1 */
-#define IWL_AX210_DCCM_LEN		0x10000 /* LMAC1 */
-#define IWL_AX210_DCCM2_OFFSET		0x880000
-#define IWL_AX210_DCCM2_LEN		0x8000
 #define IWL_AX210_SMEM_OFFSET		0x400000
 #define IWL_AX210_SMEM_LEN		0xD0000
 
@@ -47,8 +40,7 @@
 #define IWL_MA_B_HR_B_FW_MODULE_FIRMWARE(api)		\
 	IWL_MA_B_HR_B_FW_PRE "-" __stringify(api) ".ucode"
 
-static const struct iwl_base_params iwl_ax210_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
+static const struct iwl_family_base_params iwl_ax210_base = {
 	.num_of_queues = 512,
 	.max_tfd_queue_size = 65536,
 	.shadow_ram_support = true,
@@ -57,74 +49,60 @@ static const struct iwl_base_params iwl_ax210_base_params = {
 	.max_event_log_size = 512,
 	.shadow_reg_enable = true,
 	.pcie_l1_allowed = true,
+	.smem_offset = IWL_AX210_SMEM_OFFSET,
+	.smem_len = IWL_AX210_SMEM_LEN,
+	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,
+	.apmg_not_supported = true,
+	.mac_addr_from_csr = 0x380,
+	.min_umac_error_event_table = 0x400000,
+	.d3_debug_data_base_addr = 0x401000,
+	.d3_debug_data_length = 60 * 1024,
+	.mon_smem_regs = {
+		.write_ptr = {
+			.addr = LDBG_M2S_BUF_WPTR,
+			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,
+		},
+		.cycle_cnt = {
+			.addr = LDBG_M2S_BUF_WRAP_CNT,
+			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,
+		},
+	},
+	.min_txq_size = 128,
+	.gp2_reg_addr = 0xd02c68,
+	.min_ba_txq_size = IWL_DEFAULT_QUEUE_SIZE_HE,
+	.mon_dram_regs = {
+		.write_ptr = {
+			.addr = DBGC_CUR_DBGBUF_STATUS,
+			.mask = DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK,
+		},
+		.cycle_cnt = {
+			.addr = DBGC_DBGBUF_WRAP_AROUND,
+			.mask = 0xffffffff,
+		},
+		.cur_frag = {
+			.addr = DBGC_CUR_DBGBUF_STATUS,
+			.mask = DBGC_CUR_DBGBUF_STATUS_IDX_MSK,
+		},
+	},
+	.ucode_api_min = IWL_AX210_UCODE_API_MIN,
+	.ucode_api_max = IWL_AX210_UCODE_API_MAX,
 };
 
-#define IWL_DEVICE_AX210_COMMON						\
-	.ucode_api_min = IWL_AX210_UCODE_API_MIN,			\
-	.led_mode = IWL_LED_RF_STATE,					\
-	.nvm_hw_section_num = 10,					\
-	.non_shared_ant = ANT_B,					\
-	.dccm_offset = IWL_AX210_DCCM_OFFSET,				\
-	.dccm_len = IWL_AX210_DCCM_LEN,					\
-	.dccm2_offset = IWL_AX210_DCCM2_OFFSET,				\
-	.dccm2_len = IWL_AX210_DCCM2_LEN,				\
-	.smem_offset = IWL_AX210_SMEM_OFFSET,				\
-	.smem_len = IWL_AX210_SMEM_LEN,					\
-	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,		\
-	.apmg_not_supported = true,					\
-	.trans.mq_rx_supported = true,					\
-	.vht_mu_mimo_supported = true,					\
-	.mac_addr_from_csr = 0x380,					\
-	.ht_params = &iwl_22000_ht_params,				\
-	.nvm_ver = IWL_AX210_NVM_VERSION,				\
-	.trans.rf_id = true,						\
-	.trans.gen2 = true,						\
-	.nvm_type = IWL_NVM_EXT,					\
-	.dbgc_supported = true,						\
-	.min_umac_error_event_table = 0x400000,				\
-	.d3_debug_data_base_addr = 0x401000,				\
-	.d3_debug_data_length = 60 * 1024,				\
-	.mon_smem_regs = {						\
-		.write_ptr = {						\
-			.addr = LDBG_M2S_BUF_WPTR,			\
-			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,		\
-	},								\
-		.cycle_cnt = {						\
-			.addr = LDBG_M2S_BUF_WRAP_CNT,			\
-			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,		\
-		},							\
-	}
-
-#define IWL_DEVICE_AX210						\
-	IWL_DEVICE_AX210_COMMON,					\
-	.ucode_api_max = IWL_AX210_UCODE_API_MAX,			\
-	.trans.umac_prph_offset = 0x300000,				\
-	.trans.device_family = IWL_DEVICE_FAMILY_AX210,			\
-	.trans.base_params = &iwl_ax210_base_params,			\
-	.min_txq_size = 128,						\
-	.gp2_reg_addr = 0xd02c68,					\
-	.min_ba_txq_size = IWL_DEFAULT_QUEUE_SIZE_HE,		\
-	.mon_dram_regs = {						\
-		.write_ptr = {						\
-			.addr = DBGC_CUR_DBGBUF_STATUS,			\
-			.mask = DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK,	\
-		},							\
-		.cycle_cnt = {						\
-			.addr = DBGC_DBGBUF_WRAP_AROUND,		\
-			.mask = 0xffffffff,				\
-		},							\
-		.cur_frag = {						\
-			.addr = DBGC_CUR_DBGBUF_STATUS,			\
-			.mask = DBGC_CUR_DBGBUF_STATUS_IDX_MSK,		\
-		},							\
-	}
+const struct iwl_mac_cfg iwl_ty_mac_cfg = {
+	.mq_rx_supported = true,
+	.gen2 = true,
+	.device_family = IWL_DEVICE_FAMILY_AX210,
+	.base = &iwl_ax210_base,
+	.umac_prph_offset = 0x300000,
+	/* TODO: the following values need to be checked */
+	.xtal_latency = 500,
+};
 
-const struct iwl_cfg_trans_params iwl_so_trans_cfg = {
+const struct iwl_mac_cfg iwl_so_mac_cfg = {
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.device_family = IWL_DEVICE_FAMILY_AX210,
-	.base_params = &iwl_ax210_base_params,
+	.base = &iwl_ax210_base,
 	.umac_prph_offset = 0x300000,
 	.integrated = true,
 	/* TODO: the following values need to be checked */
@@ -132,12 +110,11 @@ const struct iwl_cfg_trans_params iwl_so_trans_cfg = {
 	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_200US,
 };
 
-const struct iwl_cfg_trans_params iwl_so_long_latency_trans_cfg = {
+const struct iwl_mac_cfg iwl_so_long_latency_mac_cfg = {
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.device_family = IWL_DEVICE_FAMILY_AX210,
-	.base_params = &iwl_ax210_base_params,
+	.base = &iwl_ax210_base,
 	.umac_prph_offset = 0x300000,
 	.integrated = true,
 	.low_latency_xtal = true,
@@ -145,12 +122,11 @@ const struct iwl_cfg_trans_params iwl_so_long_latency_trans_cfg = {
 	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
 };
 
-const struct iwl_cfg_trans_params iwl_so_long_latency_imr_trans_cfg = {
+const struct iwl_mac_cfg iwl_so_long_latency_imr_mac_cfg = {
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.device_family = IWL_DEVICE_FAMILY_AX210,
-	.base_params = &iwl_ax210_base_params,
+	.base = &iwl_ax210_base,
 	.umac_prph_offset = 0x300000,
 	.integrated = true,
 	.low_latency_xtal = true,
@@ -159,107 +135,15 @@ const struct iwl_cfg_trans_params iwl_so_long_latency_imr_trans_cfg = {
 	.imr_enabled = true,
 };
 
-/*
- * If the device doesn't support HE, no need to have that many buffers.
- * AX210 devices can split multiple frames into a single RB, so fewer are
- * needed; AX210 cannot (but use smaller RBs by default) - these sizes
- * were picked according to 8 MSDUs inside 256 A-MSDUs in an A-MPDU, with
- * additional overhead to account for processing time.
- */
-#define IWL_NUM_RBDS_NON_HE		512
-#define IWL_NUM_RBDS_AX210_HE		4096
-
-const struct iwl_cfg_trans_params iwl_ma_trans_cfg = {
+const struct iwl_mac_cfg iwl_ma_mac_cfg = {
 	.device_family = IWL_DEVICE_FAMILY_AX210,
-	.base_params = &iwl_ax210_base_params,
+	.base = &iwl_ax210_base,
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.integrated = true,
 	.umac_prph_offset = 0x300000
 };
 
-const char iwl_ax211_name[] = "Intel(R) Wi-Fi 6E AX211 160MHz";
-const char iwl_ax231_name[] = "Intel(R) Wi-Fi 6E AX231 160MHz";
-const char iwl_ax411_name[] = "Intel(R) Wi-Fi 6E AX411 160MHz";
-
-const char iwl_ax210_killer_1675w_name[] =
-	"Killer(R) Wi-Fi 6E AX1675w 160MHz Wireless Network Adapter (210D2W)";
-const char iwl_ax210_killer_1675x_name[] =
-	"Killer(R) Wi-Fi 6E AX1675x 160MHz Wireless Network Adapter (210NGW)";
-const char iwl_ax211_killer_1675s_name[] =
-	"Killer(R) Wi-Fi 6E AX1675s 160MHz Wireless Network Adapter (211NGW)";
-const char iwl_ax211_killer_1675i_name[] =
-	"Killer(R) Wi-Fi 6E AX1675i 160MHz Wireless Network Adapter (211NGW)";
-const char iwl_ax411_killer_1690s_name[] =
-	"Killer(R) Wi-Fi 6E AX1690s 160MHz Wireless Network Adapter (411D2W)";
-const char iwl_ax411_killer_1690i_name[] =
-	"Killer(R) Wi-Fi 6E AX1690i 160MHz Wireless Network Adapter (411NGW)";
-
-const struct iwl_cfg iwlax210_2ax_cfg_so_jf_b0 = {
-	.name = "Intel(R) Wireless-AC 9560 160MHz",
-	.fw_name_pre = IWL_SO_A_JF_B_FW_PRE,
-	IWL_DEVICE_AX210,
-	.num_rbds = IWL_NUM_RBDS_NON_HE,
-};
-
-const struct iwl_cfg iwlax211_2ax_cfg_so_gf_a0 = {
-	.name = iwl_ax211_name,
-	.fw_name_pre = IWL_SO_A_GF_A_FW_PRE,
-	.uhb_supported = true,
-	IWL_DEVICE_AX210,
-	.num_rbds = IWL_NUM_RBDS_AX210_HE,
-};
-
-const struct iwl_cfg iwlax211_2ax_cfg_so_gf_a0_long = {
-	.name = iwl_ax211_name,
-	.fw_name_pre = IWL_SO_A_GF_A_FW_PRE,
-	.uhb_supported = true,
-	IWL_DEVICE_AX210,
-	.num_rbds = IWL_NUM_RBDS_AX210_HE,
-	.trans.xtal_latency = 12000,
-	.trans.low_latency_xtal = true,
-};
-
-const struct iwl_cfg iwlax210_2ax_cfg_ty_gf_a0 = {
-	.name = "Intel(R) Wi-Fi 6 AX210 160MHz",
-	.fw_name_pre = IWL_TY_A_GF_A_FW_PRE,
-	.uhb_supported = true,
-	IWL_DEVICE_AX210,
-	.num_rbds = IWL_NUM_RBDS_AX210_HE,
-};
-
-const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0 = {
-	.name = iwl_ax411_name,
-	.fw_name_pre = IWL_SO_A_GF4_A_FW_PRE,
-	.uhb_supported = true,
-	IWL_DEVICE_AX210,
-	.num_rbds = IWL_NUM_RBDS_AX210_HE,
-};
-
-const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0_long = {
-	.name = iwl_ax411_name,
-	.fw_name_pre = IWL_SO_A_GF4_A_FW_PRE,
-	.uhb_supported = true,
-	IWL_DEVICE_AX210,
-	.num_rbds = IWL_NUM_RBDS_AX210_HE,
-	.trans.xtal_latency = 12000,
-	.trans.low_latency_xtal = true,
-};
-
-const struct iwl_cfg iwl_cfg_ma = {
-	.fw_name_mac = "ma",
-	.uhb_supported = true,
-	IWL_DEVICE_AX210,
-	.num_rbds = IWL_NUM_RBDS_AX210_HE,
-};
-
-const struct iwl_cfg iwl_cfg_so_a0_hr_a0 = {
-	.fw_name_pre = IWL_SO_A_HR_B_FW_PRE,
-	IWL_DEVICE_AX210,
-	.num_rbds = IWL_NUM_RBDS_AX210_HE,
-};
-
 MODULE_FIRMWARE(IWL_SO_A_JF_B_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_SO_A_HR_B_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX));
 IWL_FW_AND_PNVM(IWL_SO_A_GF_A_FW_PRE, IWL_AX210_UCODE_API_MAX);
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
index f055255a7c93..05e45fff8b36 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
@@ -10,19 +10,12 @@
 #include "fw/api/txq.h"
 
 /* Highest firmware API version supported */
-#define IWL_BZ_UCODE_API_MAX	98
+#define IWL_BZ_UCODE_API_MAX	99
 
 /* Lowest firmware API version supported */
 #define IWL_BZ_UCODE_API_MIN	93
 
-/* NVM versions */
-#define IWL_BZ_NVM_VERSION		0x0a1d
-
 /* Memory offsets and lengths */
-#define IWL_BZ_DCCM_OFFSET		0x800000 /* LMAC1 */
-#define IWL_BZ_DCCM_LEN			0x10000 /* LMAC1 */
-#define IWL_BZ_DCCM2_OFFSET		0x880000
-#define IWL_BZ_DCCM2_LEN		0x8000
 #define IWL_BZ_SMEM_OFFSET		0x400000
 #define IWL_BZ_SMEM_LEN			0xD0000
 
@@ -38,13 +31,7 @@
 #define IWL_BZ_A_HR_B_MODULE_FIRMWARE(api) \
 	IWL_BZ_A_HR_B_FW_PRE "-" __stringify(api) ".ucode"
 
-#if !IS_ENABLED(CONFIG_IWLMVM)
-const char iwl_ax211_name[] = "Intel(R) Wi-Fi 6E AX211 160MHz";
-const char iwl_ax201_name[] = "Intel(R) Wi-Fi 6 AX201 160MHz";
-#endif
-
-static const struct iwl_base_params iwl_bz_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
+static const struct iwl_family_base_params iwl_bz_base = {
 	.num_of_queues = 512,
 	.max_tfd_queue_size = 65536,
 	.shadow_ram_support = true,
@@ -53,91 +40,55 @@ static const struct iwl_base_params iwl_bz_base_params = {
 	.max_event_log_size = 512,
 	.shadow_reg_enable = true,
 	.pcie_l1_allowed = true,
+	.smem_offset = IWL_BZ_SMEM_OFFSET,
+	.smem_len = IWL_BZ_SMEM_LEN,
+	.apmg_not_supported = true,
+	.mac_addr_from_csr = 0x30,
+	.min_umac_error_event_table = 0xD0000,
+	.d3_debug_data_base_addr = 0x401000,
+	.d3_debug_data_length = 60 * 1024,
+	.mon_smem_regs = {
+		.write_ptr = {
+			.addr = LDBG_M2S_BUF_WPTR,
+			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,
+	},
+		.cycle_cnt = {
+			.addr = LDBG_M2S_BUF_WRAP_CNT,
+			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,
+		},
+	},
+	.min_txq_size = 128,
+	.gp2_reg_addr = 0xd02c68,
+	.min_ba_txq_size = IWL_DEFAULT_QUEUE_SIZE_EHT,
+	.mon_dram_regs = {
+		.write_ptr = {
+			.addr = DBGC_CUR_DBGBUF_STATUS,
+			.mask = DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK,
+		},
+		.cycle_cnt = {
+			.addr = DBGC_DBGBUF_WRAP_AROUND,
+			.mask = 0xffffffff,
+		},
+		.cur_frag = {
+			.addr = DBGC_CUR_DBGBUF_STATUS,
+			.mask = DBGC_CUR_DBGBUF_STATUS_IDX_MSK,
+		},
+	},
+	.mon_dbgi_regs = {
+		.write_ptr = {
+			.addr = DBGI_SRAM_FIFO_POINTERS,
+			.mask = DBGI_SRAM_FIFO_POINTERS_WR_PTR_MSK,
+		},
+	},
+	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,
+	.ucode_api_max = IWL_BZ_UCODE_API_MAX,
+	.ucode_api_min = IWL_BZ_UCODE_API_MIN,
 };
 
-const struct iwl_ht_params iwl_bz_ht_params = {
-	.stbc = true,
-	.ldpc = true,
-	.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ) |
-		      BIT(NL80211_BAND_6GHZ),
-};
-
-#define IWL_DEVICE_BZ_COMMON						\
-	.ucode_api_max = IWL_BZ_UCODE_API_MAX,			\
-	.ucode_api_min = IWL_BZ_UCODE_API_MIN,			\
-	.led_mode = IWL_LED_RF_STATE,					\
-	.nvm_hw_section_num = 10,					\
-	.non_shared_ant = ANT_B,					\
-	.dccm_offset = IWL_BZ_DCCM_OFFSET,				\
-	.dccm_len = IWL_BZ_DCCM_LEN,					\
-	.dccm2_offset = IWL_BZ_DCCM2_OFFSET,				\
-	.dccm2_len = IWL_BZ_DCCM2_LEN,				\
-	.smem_offset = IWL_BZ_SMEM_OFFSET,				\
-	.smem_len = IWL_BZ_SMEM_LEN,					\
-	.apmg_not_supported = true,					\
-	.trans.mq_rx_supported = true,					\
-	.vht_mu_mimo_supported = true,					\
-	.mac_addr_from_csr = 0x30,					\
-	.nvm_ver = IWL_BZ_NVM_VERSION,				\
-	.trans.rf_id = true,						\
-	.trans.gen2 = true,						\
-	.nvm_type = IWL_NVM_EXT,					\
-	.dbgc_supported = true,						\
-	.min_umac_error_event_table = 0xD0000,				\
-	.d3_debug_data_base_addr = 0x401000,				\
-	.d3_debug_data_length = 60 * 1024,				\
-	.mon_smem_regs = {						\
-		.write_ptr = {						\
-			.addr = LDBG_M2S_BUF_WPTR,			\
-			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,		\
-	},								\
-		.cycle_cnt = {						\
-			.addr = LDBG_M2S_BUF_WRAP_CNT,			\
-			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,		\
-		},							\
-	},								\
-	.trans.umac_prph_offset = 0x300000,				\
-	.trans.device_family = IWL_DEVICE_FAMILY_BZ,			\
-	.trans.base_params = &iwl_bz_base_params,			\
-	.min_txq_size = 128,						\
-	.gp2_reg_addr = 0xd02c68,					\
-	.min_ba_txq_size = IWL_DEFAULT_QUEUE_SIZE_EHT,			\
-	.mon_dram_regs = {						\
-		.write_ptr = {						\
-			.addr = DBGC_CUR_DBGBUF_STATUS,			\
-			.mask = DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK,	\
-		},							\
-		.cycle_cnt = {						\
-			.addr = DBGC_DBGBUF_WRAP_AROUND,		\
-			.mask = 0xffffffff,				\
-		},							\
-		.cur_frag = {						\
-			.addr = DBGC_CUR_DBGBUF_STATUS,			\
-			.mask = DBGC_CUR_DBGBUF_STATUS_IDX_MSK,		\
-		},							\
-	},								\
-	.mon_dbgi_regs = {						\
-		.write_ptr = {						\
-			.addr = DBGI_SRAM_FIFO_POINTERS,		\
-			.mask = DBGI_SRAM_FIFO_POINTERS_WR_PTR_MSK,	\
-		},							\
-	}
-
-#define IWL_DEVICE_BZ							\
-	IWL_DEVICE_BZ_COMMON,						\
-	.ht_params = &iwl_bz_ht_params
-
-/*
- * This size was picked according to 8 MSDUs inside 512 A-MSDUs in an
- * A-MPDU, with additional overhead to account for processing time.
- */
-#define IWL_NUM_RBDS_BZ_EHT		(512 * 16)
-
-const struct iwl_cfg_trans_params iwl_bz_trans_cfg = {
+const struct iwl_mac_cfg iwl_bz_mac_cfg = {
 	.device_family = IWL_DEVICE_FAMILY_BZ,
-	.base_params = &iwl_bz_base_params,
+	.base = &iwl_bz_base,
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.integrated = true,
 	.umac_prph_offset = 0x300000,
@@ -146,38 +97,16 @@ const struct iwl_cfg_trans_params iwl_bz_trans_cfg = {
 	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
 };
 
-const struct iwl_cfg_trans_params iwl_gl_trans_cfg = {
+const struct iwl_mac_cfg iwl_gl_mac_cfg = {
 	.device_family = IWL_DEVICE_FAMILY_BZ,
-	.base_params = &iwl_bz_base_params,
+	.base = &iwl_bz_base,
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.umac_prph_offset = 0x300000,
 	.xtal_latency = 12000,
 	.low_latency_xtal = true,
 };
 
-const char iwl_fm_name[] = "Intel(R) Wi-Fi 7 BE201 320MHz";
-const char iwl_wh_name[] = "Intel(R) Wi-Fi 7 BE211 320MHz";
-const char iwl_gl_name[] = "Intel(R) Wi-Fi 7 BE200 320MHz";
-const char iwl_mtp_name[] = "Intel(R) Wi-Fi 7 BE202 160MHz";
-
-const struct iwl_cfg iwl_cfg_bz = {
-	.fw_name_mac = "bz",
-	.uhb_supported = true,
-	IWL_DEVICE_BZ,
-	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,
-	.num_rbds = IWL_NUM_RBDS_BZ_EHT,
-};
-
-const struct iwl_cfg iwl_cfg_gl = {
-	.fw_name_mac = "gl",
-	.uhb_supported = true,
-	IWL_DEVICE_BZ,
-	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,
-	.num_rbds = IWL_NUM_RBDS_BZ_EHT,
-};
-
 MODULE_FIRMWARE(IWL_BZ_A_HR_B_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX));
 IWL_FW_AND_PNVM(IWL_BZ_A_GF_A_FW_PRE, IWL_BZ_UCODE_API_MAX);
 IWL_FW_AND_PNVM(IWL_BZ_A_GF4_A_FW_PRE, IWL_BZ_UCODE_API_MAX);
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
index 282b9b846c3a..45e55cef42ea 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
@@ -9,35 +9,21 @@
 #include "fw/api/txq.h"
 
 /* Highest firmware API version supported */
-#define IWL_DR_UCODE_API_MAX	98
+#define IWL_DR_UCODE_API_MAX	99
 
 /* Lowest firmware API version supported */
-#define IWL_DR_UCODE_API_MIN	96
-
-/* NVM versions */
-#define IWL_DR_NVM_VERSION		0x0a1d
+#define IWL_DR_UCODE_API_MIN	97
 
 /* Memory offsets and lengths */
-#define IWL_DR_DCCM_OFFSET		0x800000 /* LMAC1 */
-#define IWL_DR_DCCM_LEN			0x10000 /* LMAC1 */
-#define IWL_DR_DCCM2_OFFSET		0x880000
-#define IWL_DR_DCCM2_LEN		0x8000
 #define IWL_DR_SMEM_OFFSET		0x400000
 #define IWL_DR_SMEM_LEN			0xD0000
 
 #define IWL_DR_A_PE_A_FW_PRE		"iwlwifi-dr-a0-pe-a0"
-#define IWL_BR_A_PET_A_FW_PRE		"iwlwifi-br-a0-petc-a0"
-#define IWL_BR_A_PE_A_FW_PRE		"iwlwifi-br-a0-pe-a0"
 
 #define IWL_DR_A_PE_A_FW_MODULE_FIRMWARE(api) \
 	IWL_DR_A_PE_A_FW_PRE "-" __stringify(api) ".ucode"
-#define IWL_BR_A_PET_A_FW_MODULE_FIRMWARE(api) \
-	IWL_BR_A_PET_A_FW_PRE "-" __stringify(api) ".ucode"
-#define IWL_BR_A_PE_A_FW_MODULE_FIRMWARE(api) \
-	IWL_BR_A_PE_A_FW_PRE "-" __stringify(api) ".ucode"
 
-static const struct iwl_base_params iwl_dr_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
+static const struct iwl_family_base_params iwl_dr_base = {
 	.num_of_queues = 512,
 	.max_tfd_queue_size = 65536,
 	.shadow_ram_support = true,
@@ -46,87 +32,55 @@ static const struct iwl_base_params iwl_dr_base_params = {
 	.max_event_log_size = 512,
 	.shadow_reg_enable = true,
 	.pcie_l1_allowed = true,
+	.smem_offset = IWL_DR_SMEM_OFFSET,
+	.smem_len = IWL_DR_SMEM_LEN,
+	.apmg_not_supported = true,
+	.mac_addr_from_csr = 0x30,
+	.min_umac_error_event_table = 0xD0000,
+	.d3_debug_data_base_addr = 0x401000,
+	.d3_debug_data_length = 60 * 1024,
+	.mon_smem_regs = {
+		.write_ptr = {
+			.addr = LDBG_M2S_BUF_WPTR,
+			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,
+		},
+		.cycle_cnt = {
+			.addr = LDBG_M2S_BUF_WRAP_CNT,
+			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,
+		},
+	},
+	.min_txq_size = 128,
+	.gp2_reg_addr = 0xd02c68,
+	.min_ba_txq_size = IWL_DEFAULT_QUEUE_SIZE_EHT,
+	.mon_dram_regs = {
+		.write_ptr = {
+			.addr = DBGC_CUR_DBGBUF_STATUS,
+			.mask = DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK,
+		},
+		.cycle_cnt = {
+			.addr = DBGC_DBGBUF_WRAP_AROUND,
+			.mask = 0xffffffff,
+		},
+		.cur_frag = {
+			.addr = DBGC_CUR_DBGBUF_STATUS,
+			.mask = DBGC_CUR_DBGBUF_STATUS_IDX_MSK,
+		},
+	},
+	.mon_dbgi_regs = {
+		.write_ptr = {
+			.addr = DBGI_SRAM_FIFO_POINTERS,
+			.mask = DBGI_SRAM_FIFO_POINTERS_WR_PTR_MSK,
+		},
+	},
+	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,
+	.ucode_api_max = IWL_DR_UCODE_API_MAX,
+	.ucode_api_min = IWL_DR_UCODE_API_MIN,
 };
 
-#define IWL_DEVICE_DR_COMMON						\
-	.ucode_api_max = IWL_DR_UCODE_API_MAX,			\
-	.ucode_api_min = IWL_DR_UCODE_API_MIN,			\
-	.led_mode = IWL_LED_RF_STATE,					\
-	.nvm_hw_section_num = 10,					\
-	.non_shared_ant = ANT_B,					\
-	.dccm_offset = IWL_DR_DCCM_OFFSET,				\
-	.dccm_len = IWL_DR_DCCM_LEN,					\
-	.dccm2_offset = IWL_DR_DCCM2_OFFSET,				\
-	.dccm2_len = IWL_DR_DCCM2_LEN,				\
-	.smem_offset = IWL_DR_SMEM_OFFSET,				\
-	.smem_len = IWL_DR_SMEM_LEN,					\
-	.apmg_not_supported = true,					\
-	.trans.mq_rx_supported = true,					\
-	.vht_mu_mimo_supported = true,					\
-	.mac_addr_from_csr = 0x30,					\
-	.nvm_ver = IWL_DR_NVM_VERSION,				\
-	.trans.rf_id = true,						\
-	.trans.gen2 = true,						\
-	.nvm_type = IWL_NVM_EXT,					\
-	.dbgc_supported = true,						\
-	.min_umac_error_event_table = 0xD0000,				\
-	.d3_debug_data_base_addr = 0x401000,				\
-	.d3_debug_data_length = 60 * 1024,				\
-	.mon_smem_regs = {						\
-		.write_ptr = {						\
-			.addr = LDBG_M2S_BUF_WPTR,			\
-			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,		\
-	},								\
-		.cycle_cnt = {						\
-			.addr = LDBG_M2S_BUF_WRAP_CNT,			\
-			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,		\
-		},							\
-	},								\
-	.trans.umac_prph_offset = 0x300000,				\
-	.trans.device_family = IWL_DEVICE_FAMILY_DR,			\
-	.trans.base_params = &iwl_dr_base_params,			\
-	.min_txq_size = 128,						\
-	.gp2_reg_addr = 0xd02c68,					\
-	.min_ba_txq_size = IWL_DEFAULT_QUEUE_SIZE_EHT,			\
-	.mon_dram_regs = {						\
-		.write_ptr = {						\
-			.addr = DBGC_CUR_DBGBUF_STATUS,			\
-			.mask = DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK,	\
-		},							\
-		.cycle_cnt = {						\
-			.addr = DBGC_DBGBUF_WRAP_AROUND,		\
-			.mask = 0xffffffff,				\
-		},							\
-		.cur_frag = {						\
-			.addr = DBGC_CUR_DBGBUF_STATUS,			\
-			.mask = DBGC_CUR_DBGBUF_STATUS_IDX_MSK,		\
-		},							\
-	},								\
-	.mon_dbgi_regs = {						\
-		.write_ptr = {						\
-			.addr = DBGI_SRAM_FIFO_POINTERS,		\
-			.mask = DBGI_SRAM_FIFO_POINTERS_WR_PTR_MSK,	\
-		},							\
-	}
-
-#define IWL_DEVICE_DR							\
-	IWL_DEVICE_DR_COMMON,						\
-	.uhb_supported = true,						\
-	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,		\
-	.num_rbds = IWL_NUM_RBDS_DR_EHT,				\
-	.ht_params = &iwl_bz_ht_params
-
-/*
- * This size was picked according to 8 MSDUs inside 512 A-MSDUs in an
- * A-MPDU, with additional overhead to account for processing time.
- */
-#define IWL_NUM_RBDS_DR_EHT		(512 * 16)
-
-const struct iwl_cfg_trans_params iwl_dr_trans_cfg = {
+const struct iwl_mac_cfg iwl_dr_mac_cfg = {
 	.device_family = IWL_DEVICE_FAMILY_DR,
-	.base_params = &iwl_dr_base_params,
+	.base = &iwl_dr_base,
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.integrated = true,
 	.umac_prph_offset = 0x300000,
@@ -135,31 +89,5 @@ const struct iwl_cfg_trans_params iwl_dr_trans_cfg = {
 	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
 };
 
-const char iwl_dr_name[] = "Intel(R) TBD Dr device";
-
-const struct iwl_cfg iwl_cfg_dr = {
-	.fw_name_mac = "dr",
-	IWL_DEVICE_DR,
-};
-
-const struct iwl_cfg_trans_params iwl_br_trans_cfg = {
-	.device_family = IWL_DEVICE_FAMILY_DR,
-	.base_params = &iwl_dr_base_params,
-	.mq_rx_supported = true,
-	.rf_id = true,
-	.gen2 = true,
-	.umac_prph_offset = 0x300000,
-	.xtal_latency = 12000,
-	.low_latency_xtal = true,
-};
-
-const char iwl_br_name[] = "Intel(R) TBD Br device";
-
-const struct iwl_cfg iwl_cfg_br = {
-	.fw_name_mac = "br",
-	IWL_DEVICE_DR,
-};
-
 MODULE_FIRMWARE(IWL_DR_A_PE_A_FW_MODULE_FIRMWARE(IWL_DR_UCODE_API_MAX));
-MODULE_FIRMWARE(IWL_BR_A_PET_A_FW_MODULE_FIRMWARE(IWL_DR_UCODE_API_MAX));
-MODULE_FIRMWARE(IWL_BR_A_PE_A_FW_MODULE_FIRMWARE(IWL_DR_UCODE_API_MAX));
+
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/rf-fm.c b/drivers/net/wireless/intel/iwlwifi/cfg/rf-fm.c
new file mode 100644
index 000000000000..456a666c8dfd
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/rf-fm.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2015-2017 Intel Deutschland GmbH
+ * Copyright (C) 2018-2025 Intel Corporation
+ */
+#include "iwl-config.h"
+
+/* NVM versions */
+#define IWL_FM_NVM_VERSION		0x0a1d
+
+#define IWL_DEVICE_FM							\
+	.ht_params = {							\
+		.stbc = true,						\
+		.ldpc = true,						\
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) |			\
+			      BIT(NL80211_BAND_5GHZ),			\
+	},								\
+	.led_mode = IWL_LED_RF_STATE,					\
+	.non_shared_ant = ANT_B,					\
+	.vht_mu_mimo_supported = true,					\
+	.uhb_supported = true,						\
+	.num_rbds = IWL_NUM_RBDS_EHT,					\
+	.nvm_ver = IWL_FM_NVM_VERSION,					\
+	.nvm_type = IWL_NVM_EXT
+
+const struct iwl_rf_cfg iwl_rf_fm = {
+	IWL_DEVICE_FM,
+};
+
+const struct iwl_rf_cfg iwl_rf_fm_160mhz = {
+	IWL_DEVICE_FM,
+	.bw_limit = 160,
+};
+
+const char iwl_killer_be1750s_name[] =
+	"Killer(R) Wi-Fi 7 BE1750s 320MHz Wireless Network Adapter (BE201D2W)";
+const char iwl_killer_be1750i_name[] =
+	"Killer(R) Wi-Fi 7 BE1750i 320MHz Wireless Network Adapter (BE201NGW)";
+const char iwl_killer_be1750w_name[] =
+	"Killer(TM) Wi-Fi 7 BE1750w 320MHz Wireless Network Adapter (BE200D2W)";
+const char iwl_killer_be1750x_name[] =
+	"Killer(TM) Wi-Fi 7 BE1750x 320MHz Wireless Network Adapter (BE200NGW)";
+const char iwl_killer_be1790s_name[] =
+	"Killer(R) Wi-Fi 7 BE1790s 320MHz Wireless Network Adapter (BE401D2W)";
+const char iwl_killer_be1790i_name[] =
+	"Killer(R) Wi-Fi 7 BE1790i 320MHz Wireless Network Adapter (BE401NGW)";
+
+const char iwl_be201_name[] = "Intel(R) Wi-Fi 7 BE201 320MHz";
+const char iwl_be200_name[] = "Intel(R) Wi-Fi 7 BE200 320MHz";
+const char iwl_be202_name[] = "Intel(R) Wi-Fi 7 BE202 160MHz";
+const char iwl_be401_name[] = "Intel(R) Wi-Fi 7 BE401 320MHz";
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/rf-gf.c b/drivers/net/wireless/intel/iwlwifi/cfg/rf-gf.c
new file mode 100644
index 000000000000..f55c286e83be
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/rf-gf.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2015-2017 Intel Deutschland GmbH
+ * Copyright (C) 2018-2025 Intel Corporation
+ */
+#include "iwl-config.h"
+
+/* NVM versions */
+#define IWL_GF_NVM_VERSION		0x0a1d
+
+const struct iwl_rf_cfg iwl_rf_gf = {
+	.uhb_supported = true,
+	.led_mode = IWL_LED_RF_STATE,
+	.non_shared_ant = ANT_B,
+	.vht_mu_mimo_supported = true,
+	.ht_params = {
+		.stbc = true,
+		.ldpc = true,
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) |
+			      BIT(NL80211_BAND_5GHZ),
+	},
+	.nvm_ver = IWL_GF_NVM_VERSION,
+	.nvm_type = IWL_NVM_EXT,
+	.num_rbds = IWL_NUM_RBDS_HE,
+};
+
+const char iwl_ax210_killer_1675w_name[] =
+	"Killer(R) Wi-Fi 6E AX1675w 160MHz Wireless Network Adapter (210D2W)";
+const char iwl_ax210_killer_1675x_name[] =
+	"Killer(R) Wi-Fi 6E AX1675x 160MHz Wireless Network Adapter (210NGW)";
+const char iwl_ax211_killer_1675s_name[] =
+	"Killer(R) Wi-Fi 6E AX1675s 160MHz Wireless Network Adapter (211D2W)";
+const char iwl_ax211_killer_1675i_name[] =
+	"Killer(R) Wi-Fi 6E AX1675i 160MHz Wireless Network Adapter (211NGW)";
+const char iwl_ax411_killer_1690s_name[] =
+	"Killer(R) Wi-Fi 6E AX1690s 160MHz Wireless Network Adapter (411D2W)";
+const char iwl_ax411_killer_1690i_name[] =
+	"Killer(R) Wi-Fi 6E AX1690i 160MHz Wireless Network Adapter (411NGW)";
+
+const char iwl_ax210_name[] = "Intel(R) Wi-Fi 6E AX210 160MHz";
+const char iwl_ax211_name[] = "Intel(R) Wi-Fi 6E AX211 160MHz";
+const char iwl_ax411_name[] = "Intel(R) Wi-Fi 6E AX411 160MHz";
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/rf-hr.c b/drivers/net/wireless/intel/iwlwifi/cfg/rf-hr.c
new file mode 100644
index 000000000000..db02664e3917
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/rf-hr.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2015-2017 Intel Deutschland GmbH
+ * Copyright (C) 2018-2025 Intel Corporation
+ */
+#include "iwl-config.h"
+
+/* NVM versions */
+#define IWL_HR_NVM_VERSION		0x0a1d
+
+#define IWL_DEVICE_HR							\
+	.led_mode = IWL_LED_RF_STATE,					\
+	.non_shared_ant = ANT_B,					\
+	.vht_mu_mimo_supported = true,					\
+	.ht_params = {							\
+		.stbc = true,						\
+		.ldpc = true,						\
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) |			\
+			      BIT(NL80211_BAND_5GHZ),			\
+	},								\
+	.num_rbds = IWL_NUM_RBDS_HE,					\
+	.nvm_ver = IWL_HR_NVM_VERSION,					\
+	.nvm_type = IWL_NVM_EXT
+
+const struct iwl_rf_cfg iwl_rf_hr1 = {
+	IWL_DEVICE_HR,
+	.tx_with_siso_diversity = true,
+};
+
+const struct iwl_rf_cfg iwl_rf_hr = {
+	IWL_DEVICE_HR,
+};
+
+const struct iwl_rf_cfg iwl_rf_hr_80mhz = {
+	IWL_DEVICE_HR,
+	.bw_limit = 80,
+};
+
+const char iwl_ax101_name[] = "Intel(R) Wi-Fi 6 AX101";
+const char iwl_ax200_name[] = "Intel(R) Wi-Fi 6 AX200 160MHz";
+const char iwl_ax201_name[] = "Intel(R) Wi-Fi 6 AX201 160MHz";
+const char iwl_ax203_name[] = "Intel(R) Wi-Fi 6 AX203";
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/rf-jf.c b/drivers/net/wireless/intel/iwlwifi/cfg/rf-jf.c
new file mode 100644
index 000000000000..467eaeae6deb
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/rf-jf.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2015-2017 Intel Deutschland GmbH
+ * Copyright (C) 2018-2021, 2023, 2025 Intel Corporation
+ */
+#include "iwl-config.h"
+
+/* NVM versions */
+#define IWL_JF_NVM_VERSION		0x0a1d
+
+/* Memory offsets and lengths */
+#define IWL9000_DCCM_OFFSET		0x800000
+#define IWL9000_DCCM_LEN		0x18000
+#define IWL9000_DCCM2_OFFSET		0x880000
+#define IWL9000_DCCM2_LEN		0x8000
+
+static const struct iwl_tt_params iwl_jf_tt_params = {
+	.ct_kill_entry = 115,
+	.ct_kill_exit = 93,
+	.ct_kill_duration = 5,
+	.dynamic_smps_entry = 111,
+	.dynamic_smps_exit = 107,
+	.tx_protection_entry = 112,
+	.tx_protection_exit = 105,
+	.tx_backoff = {
+		{.temperature = 110, .backoff = 200},
+		{.temperature = 111, .backoff = 600},
+		{.temperature = 112, .backoff = 1200},
+		{.temperature = 113, .backoff = 2000},
+		{.temperature = 114, .backoff = 4000},
+	},
+	.support_ct_kill = true,
+	.support_dynamic_smps = true,
+	.support_tx_protection = true,
+	.support_tx_backoff = true,
+};
+
+/* these values are ignored if not with Pu/Th MAC firmware, due to offload */
+#define IWL_DEVICE_JF_PU						\
+	.dccm_offset = IWL9000_DCCM_OFFSET,				\
+	.dccm_len = IWL9000_DCCM_LEN,					\
+	.dccm2_offset = IWL9000_DCCM2_OFFSET,				\
+	.dccm2_len = IWL9000_DCCM2_LEN,					\
+	.thermal_params = &iwl_jf_tt_params
+
+#define IWL_DEVICE_JF							\
+	IWL_DEVICE_JF_PU,						\
+	.led_mode = IWL_LED_RF_STATE,					\
+	.non_shared_ant = ANT_B,					\
+	.num_rbds = IWL_NUM_RBDS_NON_HE,				\
+	.vht_mu_mimo_supported = true,					\
+	.ht_params = {							\
+		.stbc = true,						\
+		.ldpc = true,						\
+		.ht40_bands = BIT(NL80211_BAND_2GHZ) |			\
+			      BIT(NL80211_BAND_5GHZ),			\
+	},								\
+	.nvm_ver = IWL_JF_NVM_VERSION,					\
+	.nvm_type = IWL_NVM_EXT
+
+const struct iwl_rf_cfg iwl_rf_jf = {
+	IWL_DEVICE_JF,
+};
+
+const struct iwl_rf_cfg iwl_rf_jf_80mhz = {
+	IWL_DEVICE_JF,
+	.bw_limit = 80,
+};
+
+const char iwl9260_name[] = "Intel(R) Wireless-AC 9260";
+const char iwl9461_name[] = "Intel(R) Wireless-AC 9461";
+const char iwl9462_name[] = "Intel(R) Wireless-AC 9462";
+const char iwl9560_name[] = "Intel(R) Wireless-AC 9560";
+const char iwl9260_160_name[] = "Intel(R) Wireless-AC 9260 160MHz";
+const char iwl9461_160_name[] = "Intel(R) Wireless-AC 9461 160MHz";
+const char iwl9462_160_name[] = "Intel(R) Wireless-AC 9462 160MHz";
+const char iwl9560_160_name[] = "Intel(R) Wireless-AC 9560 160MHz";
+
+const char iwl9260_killer_1550_name[] =
+	"Killer(R) Wireless-AC 1550 Wireless Network Adapter (9260NGW) 160MHz";
+const char iwl9560_killer_1550i_name[] =
+	"Killer(R) Wireless-AC 1550i Wireless Network Adapter (9560NGW) 160MHz";
+const char iwl9560_killer_1550s_name[] =
+	"Killer(R) Wireless-AC 1550s Wireless Network Adapter (9560D2W) 160MHz";
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/rf-pe.c b/drivers/net/wireless/intel/iwlwifi/cfg/rf-pe.c
new file mode 100644
index 000000000000..483f21659eff
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/rf-pe.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+#include "iwl-config.h"
+
+/* currently iwl_rf_wh/iwl_rf_wh_160mhz are just defines for the FM ones */
+
+const char iwl_killer_bn1850w2_name[] =
+	"Killer(R) Wi-Fi 8 BN1850w2 320MHz Wireless Network Adapter (BN201.D2W)";
+const char iwl_killer_bn1850i_name[] =
+	"Killer(R) Wi-Fi 8 BN1850i 320MHz Wireless Network Adapter (BN201.NGW)";
+
+const char iwl_bn201_name[] = "Intel(R) Wi-Fi 8 BN201";
+const char iwl_be221_name[] = "Intel(R) Wi-Fi 7 BE221";
+const char iwl_be223_name[] = "Intel(R) Wi-Fi 7 BE223";
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/rf-wh.c b/drivers/net/wireless/intel/iwlwifi/cfg/rf-wh.c
new file mode 100644
index 000000000000..97735175cb0e
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/rf-wh.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+#include "iwl-config.h"
+
+/* currently iwl_rf_wh/iwl_rf_wh_160mhz are just defines for the FM ones */
+
+const char iwl_killer_be1775s_name[] =
+	"Killer(R) Wi-Fi 7 BE1775s 320MHz Wireless Network Adapter (BE211D2W)";
+const char iwl_killer_be1775i_name[] =
+	"Killer(R) Wi-Fi 7 BE1775i 320MHz Wireless Network Adapter (BE211NGW)";
+
+const char iwl_be211_name[] = "Intel(R) Wi-Fi 7 BE211 320MHz";
+const char iwl_be213_name[] = "Intel(R) Wi-Fi 7 BE213 160MHz";
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
index 670031fd60dc..b2e4d4035296 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
@@ -10,19 +10,15 @@
 #include "fw/api/txq.h"
 
 /* Highest firmware API version supported */
-#define IWL_SC_UCODE_API_MAX	98
+#define IWL_SC_UCODE_API_MAX	99
 
 /* Lowest firmware API version supported */
-#define IWL_SC_UCODE_API_MIN	93
+#define IWL_SC_UCODE_API_MIN	97
 
 /* NVM versions */
 #define IWL_SC_NVM_VERSION		0x0a1d
 
 /* Memory offsets and lengths */
-#define IWL_SC_DCCM_OFFSET		0x800000 /* LMAC1 */
-#define IWL_SC_DCCM_LEN			0x10000 /* LMAC1 */
-#define IWL_SC_DCCM2_OFFSET		0x880000
-#define IWL_SC_DCCM2_LEN		0x8000
 #define IWL_SC_SMEM_OFFSET		0x400000
 #define IWL_SC_SMEM_LEN			0xD0000
 
@@ -43,8 +39,7 @@
 #define IWL_SC_A_HR_B_FW_MODULE_FIRMWARE(api) \
 	IWL_SC_A_HR_B_FW_PRE "-" __stringify(api) ".ucode"
 
-static const struct iwl_base_params iwl_sc_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
+static const struct iwl_family_base_params iwl_sc_base = {
 	.num_of_queues = 512,
 	.max_tfd_queue_size = 65536,
 	.shadow_ram_support = true,
@@ -53,87 +48,55 @@ static const struct iwl_base_params iwl_sc_base_params = {
 	.max_event_log_size = 512,
 	.shadow_reg_enable = true,
 	.pcie_l1_allowed = true,
+	.smem_offset = IWL_SC_SMEM_OFFSET,
+	.smem_len = IWL_SC_SMEM_LEN,
+	.apmg_not_supported = true,
+	.mac_addr_from_csr = 0x30,
+	.min_umac_error_event_table = 0xD0000,
+	.d3_debug_data_base_addr = 0x401000,
+	.d3_debug_data_length = 60 * 1024,
+	.mon_smem_regs = {
+		.write_ptr = {
+			.addr = LDBG_M2S_BUF_WPTR,
+			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,
+		},
+		.cycle_cnt = {
+			.addr = LDBG_M2S_BUF_WRAP_CNT,
+			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,
+		},
+	},
+	.min_txq_size = 128,
+	.gp2_reg_addr = 0xd02c68,
+	.min_ba_txq_size = IWL_DEFAULT_QUEUE_SIZE_EHT,
+	.mon_dram_regs = {
+		.write_ptr = {
+			.addr = DBGC_CUR_DBGBUF_STATUS,
+			.mask = DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK,
+		},
+		.cycle_cnt = {
+			.addr = DBGC_DBGBUF_WRAP_AROUND,
+			.mask = 0xffffffff,
+		},
+		.cur_frag = {
+			.addr = DBGC_CUR_DBGBUF_STATUS,
+			.mask = DBGC_CUR_DBGBUF_STATUS_IDX_MSK,
+		},
+	},
+	.mon_dbgi_regs = {
+		.write_ptr = {
+			.addr = DBGI_SRAM_FIFO_POINTERS,
+			.mask = DBGI_SRAM_FIFO_POINTERS_WR_PTR_MSK,
+		},
+	},
+	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,
+	.ucode_api_max = IWL_SC_UCODE_API_MAX,
+	.ucode_api_min = IWL_SC_UCODE_API_MIN,
 };
 
-#define IWL_DEVICE_BZ_COMMON						\
-	.ucode_api_max = IWL_SC_UCODE_API_MAX,			\
-	.ucode_api_min = IWL_SC_UCODE_API_MIN,			\
-	.led_mode = IWL_LED_RF_STATE,					\
-	.nvm_hw_section_num = 10,					\
-	.non_shared_ant = ANT_B,					\
-	.dccm_offset = IWL_SC_DCCM_OFFSET,				\
-	.dccm_len = IWL_SC_DCCM_LEN,					\
-	.dccm2_offset = IWL_SC_DCCM2_OFFSET,				\
-	.dccm2_len = IWL_SC_DCCM2_LEN,				\
-	.smem_offset = IWL_SC_SMEM_OFFSET,				\
-	.smem_len = IWL_SC_SMEM_LEN,					\
-	.apmg_not_supported = true,					\
-	.trans.mq_rx_supported = true,					\
-	.vht_mu_mimo_supported = true,					\
-	.mac_addr_from_csr = 0x30,					\
-	.nvm_ver = IWL_SC_NVM_VERSION,				\
-	.trans.rf_id = true,						\
-	.trans.gen2 = true,						\
-	.nvm_type = IWL_NVM_EXT,					\
-	.dbgc_supported = true,						\
-	.min_umac_error_event_table = 0xD0000,				\
-	.d3_debug_data_base_addr = 0x401000,				\
-	.d3_debug_data_length = 60 * 1024,				\
-	.mon_smem_regs = {						\
-		.write_ptr = {						\
-			.addr = LDBG_M2S_BUF_WPTR,			\
-			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,		\
-	},								\
-		.cycle_cnt = {						\
-			.addr = LDBG_M2S_BUF_WRAP_CNT,			\
-			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,		\
-		},							\
-	},								\
-	.trans.umac_prph_offset = 0x300000,				\
-	.trans.device_family = IWL_DEVICE_FAMILY_SC,			\
-	.trans.base_params = &iwl_sc_base_params,			\
-	.min_txq_size = 128,						\
-	.gp2_reg_addr = 0xd02c68,					\
-	.min_ba_txq_size = IWL_DEFAULT_QUEUE_SIZE_EHT,			\
-	.mon_dram_regs = {						\
-		.write_ptr = {						\
-			.addr = DBGC_CUR_DBGBUF_STATUS,			\
-			.mask = DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK,	\
-		},							\
-		.cycle_cnt = {						\
-			.addr = DBGC_DBGBUF_WRAP_AROUND,		\
-			.mask = 0xffffffff,				\
-		},							\
-		.cur_frag = {						\
-			.addr = DBGC_CUR_DBGBUF_STATUS,			\
-			.mask = DBGC_CUR_DBGBUF_STATUS_IDX_MSK,		\
-		},							\
-	},								\
-	.mon_dbgi_regs = {						\
-		.write_ptr = {						\
-			.addr = DBGI_SRAM_FIFO_POINTERS,		\
-			.mask = DBGI_SRAM_FIFO_POINTERS_WR_PTR_MSK,	\
-		},							\
-	}
-
-#define IWL_DEVICE_SC							\
-	IWL_DEVICE_BZ_COMMON,						\
-	.uhb_supported = true,						\
-	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,		\
-	.num_rbds = IWL_NUM_RBDS_SC_EHT,				\
-	.ht_params = &iwl_bz_ht_params
-
-/*
- * This size was picked according to 8 MSDUs inside 512 A-MSDUs in an
- * A-MPDU, with additional overhead to account for processing time.
- */
-#define IWL_NUM_RBDS_SC_EHT		(512 * 16)
-
-const struct iwl_cfg_trans_params iwl_sc_trans_cfg = {
+const struct iwl_mac_cfg iwl_sc_mac_cfg = {
 	.device_family = IWL_DEVICE_FAMILY_SC,
-	.base_params = &iwl_sc_base_params,
+	.base = &iwl_sc_base,
 	.mq_rx_supported = true,
-	.rf_id = true,
 	.gen2 = true,
 	.integrated = true,
 	.umac_prph_offset = 0x300000,
@@ -142,23 +105,6 @@ const struct iwl_cfg_trans_params iwl_sc_trans_cfg = {
 	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
 };
 
-const char iwl_sp_name[] = "Intel(R) Wi-Fi 7 BE213 160MHz";
-
-const struct iwl_cfg iwl_cfg_sc = {
-	.fw_name_mac = "sc",
-	IWL_DEVICE_SC,
-};
-
-const struct iwl_cfg iwl_cfg_sc2 = {
-	.fw_name_mac = "sc2",
-	IWL_DEVICE_SC,
-};
-
-const struct iwl_cfg iwl_cfg_sc2f = {
-	.fw_name_mac = "sc2f",
-	IWL_DEVICE_SC,
-};
-
 IWL_FW_AND_PNVM(IWL_SC_A_FM_B_FW_PRE, IWL_SC_UCODE_API_MAX);
 IWL_FW_AND_PNVM(IWL_SC_A_FM_C_FW_PRE, IWL_SC_UCODE_API_MAX);
 MODULE_FIRMWARE(IWL_SC_A_HR_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/agn.h b/drivers/net/wireless/intel/iwlwifi/dvm/agn.h
index a13add556a7b..1ebc7effcc2a 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/agn.h
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/agn.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2021, 2024 Intel Corporation
+ * Copyright (C) 2005-2014, 2021, 2024-2025 Intel Corporation
  */
 #ifndef __iwl_agn_h__
 #define __iwl_agn_h__
@@ -399,7 +399,7 @@ static inline void iwl_dvm_set_pmi(struct iwl_priv *priv, bool state)
  * later with iwl_free_nvm_data().
  */
 struct iwl_nvm_data *
-iwl_parse_eeprom_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+iwl_parse_eeprom_data(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg,
 		      const u8 *eeprom, size_t eeprom_size);
 
 int iwl_read_eeprom(struct iwl_trans *trans, u8 **eeprom, size_t *eeprom_size);
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/dvm/debugfs.c
index 2ed4b6e798ab..ec94c43ba28c 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/debugfs.c
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
- * Copyright (C) 2018 Intel Corporation
+ * Copyright (C) 2018, 2025 Intel Corporation
  *****************************************************************************/
 
 #include <linux/slab.h>
@@ -2097,7 +2097,8 @@ static ssize_t iwl_dbgfs_protection_mode_read(struct file *file,
 	char buf[40];
 	const size_t bufsz = sizeof(buf);
 
-	if (priv->cfg->ht_params)
+	/* HT devices also have at least one HT40 band */
+	if (priv->cfg->ht_params.ht40_bands)
 		pos += scnprintf(buf + pos, bufsz - pos,
 			 "use %s for aggregation\n",
 			 (priv->hw_params.use_rts_for_aggregation) ?
@@ -2117,7 +2118,8 @@ static ssize_t iwl_dbgfs_protection_mode_write(struct file *file,
 	int buf_size;
 	int rts;
 
-	if (!priv->cfg->ht_params)
+	/* HT devices also have at least one HT40 band */
+	if (!priv->cfg->ht_params.ht40_bands)
 		return -EINVAL;
 
 	memset(buf, 0, sizeof(buf));
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/dev.h b/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
index 4ac8b862ad41..25b24820466d 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
@@ -2,6 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2003 - 2014, 2020, 2023 Intel Corporation. All rights reserved.
+ * Copyright (C) 2025 Intel Corporation
  *****************************************************************************/
 /*
  * Please use this file (dev.h) for driver implementation definitions.
@@ -627,7 +628,7 @@ struct iwl_priv {
 
 	struct iwl_trans *trans;
 	struct device *dev;		/* for debug prints only */
-	const struct iwl_cfg *cfg;
+	const struct iwl_rf_cfg *cfg;
 	const struct iwl_fw *fw;
 	const struct iwl_dvm_cfg *lib;
 	unsigned long status;
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/devices.c b/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
index 48a8349680fc..3447ae0b160a 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
- * Copyright (C) 2019 Intel Corporation
+ * Copyright (C) 2019, 2025 Intel Corporation
  *****************************************************************************/
 
 #include <linux/units.h>
@@ -481,7 +481,7 @@ static void iwl6000_set_ct_threshold(struct iwl_priv *priv)
 /* NIC configuration for 6000 series */
 static void iwl6000_nic_config(struct iwl_priv *priv)
 {
-	switch (priv->trans->trans_cfg->device_family) {
+	switch (priv->trans->mac_cfg->device_family) {
 	case IWL_DEVICE_FAMILY_6005:
 	case IWL_DEVICE_FAMILY_6030:
 	case IWL_DEVICE_FAMILY_6000:
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c b/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c
index cdc05f7e75a6..2423125e5284 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/eeprom.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014, 2018-2019, 2021, 2024 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2019, 2021, 2024-2025 Intel Corporation
  */
 #include <linux/types.h>
 #include <linux/slab.h>
@@ -151,7 +151,7 @@ static u16 iwl_eeprom_query16(const u8 *eeprom, size_t eeprom_size, int offset)
 {
 	if (WARN_ON(offset + sizeof(u16) > eeprom_size))
 		return 0;
-	return le16_to_cpup((__le16 *)(eeprom + offset));
+	return le16_to_cpup((const __le16 *)(eeprom + offset));
 }
 
 static u32 eeprom_indirect_address(const u8 *eeprom, size_t eeprom_size,
@@ -204,8 +204,8 @@ static u32 eeprom_indirect_address(const u8 *eeprom, size_t eeprom_size,
 	return (address & ADDRESS_MSK) + (offset << 1);
 }
 
-static const u8 *iwl_eeprom_query_addr(const u8 *eeprom, size_t eeprom_size,
-				       u32 offset)
+static const void *iwl_eeprom_query_addr(const u8 *eeprom, size_t eeprom_size,
+					 u32 offset)
 {
 	u32 address = eeprom_indirect_address(eeprom, eeprom_size, offset);
 
@@ -218,10 +218,9 @@ static const u8 *iwl_eeprom_query_addr(const u8 *eeprom, size_t eeprom_size,
 static int iwl_eeprom_read_calib(const u8 *eeprom, size_t eeprom_size,
 				 struct iwl_nvm_data *data)
 {
-	struct iwl_eeprom_calib_hdr *hdr;
+	const struct iwl_eeprom_calib_hdr *hdr;
 
-	hdr = (void *)iwl_eeprom_query_addr(eeprom, eeprom_size,
-					    EEPROM_CALIB_ALL);
+	hdr = iwl_eeprom_query_addr(eeprom, eeprom_size, EEPROM_CALIB_ALL);
 	if (!hdr)
 		return -ENODATA;
 	data->calib_version = hdr->version;
@@ -295,7 +294,7 @@ struct iwl_eeprom_enhanced_txpwr {
 } __packed;
 
 static s8 iwl_get_max_txpwr_half_dbm(const struct iwl_nvm_data *data,
-				     struct iwl_eeprom_enhanced_txpwr *txp)
+				     const struct iwl_eeprom_enhanced_txpwr *txp)
 {
 	s8 result = 0; /* (.5 dBm) */
 
@@ -329,7 +328,7 @@ static s8 iwl_get_max_txpwr_half_dbm(const struct iwl_nvm_data *data,
 
 static void
 iwl_eeprom_enh_txp_read_element(struct iwl_nvm_data *data,
-				struct iwl_eeprom_enhanced_txpwr *txp,
+				const struct iwl_eeprom_enhanced_txpwr *txp,
 				int n_channels, s8 max_txpower_avg)
 {
 	int ch_idx;
@@ -360,20 +359,18 @@ static void iwl_eeprom_enhanced_txpower(struct device *dev,
 					const u8 *eeprom, size_t eeprom_size,
 					int n_channels)
 {
-	struct iwl_eeprom_enhanced_txpwr *txp_array, *txp;
+	const struct iwl_eeprom_enhanced_txpwr *txp_array, *txp;
 	int idx, entries;
-	__le16 *txp_len;
+	const __le16 *txp_len;
 	s8 max_txp_avg_halfdbm;
 
 	BUILD_BUG_ON(sizeof(struct iwl_eeprom_enhanced_txpwr) != 8);
 
 	/* the length is in 16-bit words, but we want entries */
-	txp_len = (__le16 *)iwl_eeprom_query_addr(eeprom, eeprom_size,
-						  EEPROM_TXP_SZ_OFFS);
+	txp_len = iwl_eeprom_query_addr(eeprom, eeprom_size, EEPROM_TXP_SZ_OFFS);
 	entries = le16_to_cpup(txp_len) * 2 / EEPROM_TXP_ENTRY_LEN;
 
-	txp_array = (void *)iwl_eeprom_query_addr(eeprom, eeprom_size,
-						  EEPROM_TXP_OFFS);
+	txp_array = iwl_eeprom_query_addr(eeprom, eeprom_size, EEPROM_TXP_OFFS);
 
 	for (idx = 0; idx < entries; idx++) {
 		txp = &txp_array[idx];
@@ -416,7 +413,7 @@ static void iwl_eeprom_enhanced_txpower(struct device *dev,
 	}
 }
 
-static void iwl_init_band_reference(const struct iwl_cfg *cfg,
+static void iwl_init_band_reference(const struct iwl_rf_cfg *cfg,
 				    const u8 *eeprom, size_t eeprom_size,
 				    int eeprom_band, int *eeprom_ch_count,
 				    const struct iwl_eeprom_channel **ch_info,
@@ -426,7 +423,7 @@ static void iwl_init_band_reference(const struct iwl_cfg *cfg,
 
 	offset |= INDIRECT_ADDRESS | INDIRECT_REGULATORY;
 
-	*ch_info = (void *)iwl_eeprom_query_addr(eeprom, eeprom_size, offset);
+	*ch_info = iwl_eeprom_query_addr(eeprom, eeprom_size, offset);
 
 	switch (eeprom_band) {
 	case 1:		/* 2.4GHz band */
@@ -510,7 +507,7 @@ static void iwl_mod_ht40_chan_info(struct device *dev,
 #define CHECK_AND_PRINT_I(x)	\
 	((eeprom_ch_info[ch_idx].flags & EEPROM_CHANNEL_##x) ? # x " " : "")
 
-static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
+static int iwl_init_channel_map(struct device *dev, const struct iwl_rf_cfg *cfg,
 				struct iwl_nvm_data *data,
 				const u8 *eeprom, size_t eeprom_size)
 {
@@ -749,7 +746,7 @@ static int iwl_nvm_is_otp(struct iwl_trans *trans)
 	u32 otpgp;
 
 	/* OTP only valid for CP/PP and after */
-	switch (trans->hw_rev & CSR_HW_REV_TYPE_MSK) {
+	switch (trans->info.hw_rev & CSR_HW_REV_TYPE_MSK) {
 	case CSR_HW_REV_TYPE_NONE:
 		IWL_ERR(trans, "Unknown hardware type\n");
 		return -EIO;
@@ -784,7 +781,7 @@ static int iwl_init_otp_access(struct iwl_trans *trans)
 	 * CSR auto clock gate disable bit -
 	 * this is only applicable for HW with OTP shadow RAM
 	 */
-	if (trans->trans_cfg->base_params->shadow_ram_support)
+	if (trans->mac_cfg->base->shadow_ram_support)
 		iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
 			    CSR_RESET_LINK_PWR_MGMT_DISABLED);
 
@@ -905,7 +902,7 @@ static int iwl_find_otp_image(struct iwl_trans *trans,
 		}
 		/* more in the link list, continue */
 		usedblocks++;
-	} while (usedblocks <= trans->trans_cfg->base_params->max_ll_items);
+	} while (usedblocks <= trans->mac_cfg->base->max_ll_items);
 
 	/* OTP has no valid blocks */
 	IWL_DEBUG_EEPROM(trans->dev, "OTP has no valid blocks\n");
@@ -938,7 +935,7 @@ int iwl_read_eeprom(struct iwl_trans *trans, u8 **eeprom, size_t *eeprom_size)
 	if (nvm_is_otp < 0)
 		return nvm_is_otp;
 
-	sz = trans->trans_cfg->base_params->eeprom_size;
+	sz = trans->mac_cfg->base->eeprom_size;
 	IWL_DEBUG_EEPROM(trans->dev, "NVM size = %d\n", sz);
 
 	e = kmalloc(sz, GFP_KERNEL);
@@ -973,7 +970,7 @@ int iwl_read_eeprom(struct iwl_trans *trans, u8 **eeprom, size_t *eeprom_size)
 			    CSR_OTP_GP_REG_ECC_CORR_STATUS_MSK |
 			    CSR_OTP_GP_REG_ECC_UNCORR_STATUS_MSK);
 		/* traversing the linked list if no shadow ram supported */
-		if (!trans->trans_cfg->base_params->shadow_ram_support) {
+		if (!trans->mac_cfg->base->shadow_ram_support) {
 			ret = iwl_find_otp_image(trans, &validblockaddr);
 			if (ret)
 				goto err_unlock;
@@ -1027,7 +1024,7 @@ int iwl_read_eeprom(struct iwl_trans *trans, u8 **eeprom, size_t *eeprom_size)
 	return ret;
 }
 
-static void iwl_init_sbands(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+static void iwl_init_sbands(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg,
 			    struct iwl_nvm_data *data,
 			    const u8 *eeprom, size_t eeprom_size)
 {
@@ -1062,7 +1059,7 @@ static void iwl_init_sbands(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 /* EEPROM data functions */
 struct iwl_nvm_data *
-iwl_parse_eeprom_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+iwl_parse_eeprom_data(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg,
 		      const u8 *eeprom, size_t eeprom_size)
 {
 	struct iwl_nvm_data *data;
@@ -1098,14 +1095,14 @@ iwl_parse_eeprom_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 				    EEPROM_RAW_TEMPERATURE);
 	if (!tmp)
 		goto err_free;
-	data->raw_temperature = *(__le16 *)tmp;
+	data->raw_temperature = *(const __le16 *)tmp;
 
 	tmp = iwl_eeprom_query_addr(eeprom, eeprom_size,
 				    EEPROM_KELVIN_TEMPERATURE);
 	if (!tmp)
 		goto err_free;
-	data->kelvin_temperature = *(__le16 *)tmp;
-	data->kelvin_voltage = *((__le16 *)tmp + 1);
+	data->kelvin_temperature = *(const __le16 *)tmp;
+	data->kelvin_voltage = *((const __le16 *)tmp + 1);
 
 	radio_cfg =
 		iwl_eeprom_query16(eeprom, eeprom_size, EEPROM_RADIO_CONFIG);
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/led.c b/drivers/net/wireless/intel/iwlwifi/dvm/led.c
index 5ca85d90a8d6..cec2ebdfd651 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/led.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/led.c
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
- * Copyright (C) 2019 Intel Corporation
+ * Copyright (C) 2019, 2025 Intel Corporation
  *****************************************************************************/
 
 
@@ -116,9 +116,9 @@ static int iwl_led_cmd(struct iwl_priv *priv,
 	}
 
 	led_cmd.on = iwl_blink_compensation(priv, on,
-				priv->trans->trans_cfg->base_params->led_compensation);
+				priv->trans->mac_cfg->base->led_compensation);
 	led_cmd.off = iwl_blink_compensation(priv, off,
-				priv->trans->trans_cfg->base_params->led_compensation);
+				priv->trans->mac_cfg->base->led_compensation);
 
 	ret = iwl_send_led_cmd(priv, &led_cmd);
 	if (!ret) {
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c
index 56d19a034c24..0771a46bd552 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
- * Copyright(C) 2018 - 2019, 2022 - 2024 Intel Corporation
+ * Copyright(C) 2018 - 2019, 2022 - 2025 Intel Corporation
  *
  * Portions of this file are derived from the ipw3945 project, as well
  * as portions of the ieee80211 subsystem header files.
@@ -96,7 +96,7 @@ int iwlagn_mac_setup_register(struct iwl_priv *priv,
 	ieee80211_hw_set(hw, SUPPORT_FAST_XMIT);
 	ieee80211_hw_set(hw, WANT_MONITOR_VIF);
 
-	if (priv->trans->max_skb_frags)
+	if (priv->trans->info.max_skb_frags)
 		hw->netdev_features = NETIF_F_HIGHDMA | NETIF_F_SG;
 
 	hw->offchannel_tx_hw_queue = IWL_AUX_QUEUE;
@@ -188,7 +188,7 @@ int iwlagn_mac_setup_register(struct iwl_priv *priv,
 		priv->hw->wiphy->bands[NL80211_BAND_5GHZ] =
 			&priv->nvm_data->bands[NL80211_BAND_5GHZ];
 
-	hw->wiphy->hw_version = priv->trans->hw_id;
+	hw->wiphy->hw_version = priv->trans->info.hw_id;
 
 	iwl_leds_init(priv);
 
@@ -549,7 +549,7 @@ static int iwlagn_mac_resume(struct ieee80211_hw *hw)
 
 	iwlagn_prepare_restart(priv);
 
-	memset((void *)&ctx->active, 0, sizeof(ctx->active));
+	memset((void *)(uintptr_t)&ctx->active, 0, sizeof(ctx->active));
 	iwl_connection_init_rx_config(priv, ctx);
 	iwlagn_set_rxon_chain(priv, ctx);
 
@@ -1091,7 +1091,7 @@ static void iwlagn_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		goto done;
 	}
 
-	scd_queues = BIT(priv->trans->trans_cfg->base_params->num_of_queues) - 1;
+	scd_queues = BIT(priv->trans->mac_cfg->base->num_of_queues) - 1;
 	scd_queues &= ~(BIT(IWL_IPAN_CMD_QUEUE_NUM) |
 			BIT(IWL_DEFAULT_CMD_QUEUE_NUM));
 
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index a27a72cc017a..1d619384c629 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2003 - 2014, 2018 - 2022 Intel Corporation. All rights reserved.
- * Copyright(c) 2024 Intel Corporation. All rights reserved.
+ * Copyright(c) 2024-2025 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Deutschland GmbH
  *
  * Portions of this file are derived from the ipw3945 project, as well
@@ -824,11 +824,11 @@ int iwl_alive_start(struct iwl_priv *priv)
 	iwlagn_send_tx_ant_config(priv, priv->nvm_data->valid_tx_ant);
 
 	if (iwl_is_associated_ctx(ctx) && !priv->wowlan) {
-		struct iwl_rxon_cmd *active_rxon =
-				(struct iwl_rxon_cmd *)&ctx->active;
+		struct iwl_rxon_cmd *active = (void *)(uintptr_t)&ctx->active;
+
 		/* apply any changes in staging */
 		ctx->staging.filter_flags |= RXON_FILTER_ASSOC_MSK;
-		active_rxon->filter_flags &= ~RXON_FILTER_ASSOC_MSK;
+		active->filter_flags &= ~RXON_FILTER_ASSOC_MSK;
 	} else {
 		struct iwl_rxon_context *tmp;
 		/* Initialize our rx_config data */
@@ -1137,9 +1137,10 @@ static void iwl_uninit_drv(struct iwl_priv *priv)
 
 static void iwl_set_hw_params(struct iwl_priv *priv)
 {
-	if (priv->cfg->ht_params)
+	/* there are no devices with HT but without HT40 on all bands */
+	if (priv->cfg->ht_params.ht40_bands)
 		priv->hw_params.use_rts_for_aggregation =
-			priv->cfg->ht_params->use_rts_for_aggregation;
+			priv->cfg->ht_params.use_rts_for_aggregation;
 
 	/* Device-specific setup */
 	priv->lib->set_hw_params(priv);
@@ -1173,8 +1174,9 @@ static int iwl_eeprom_init_hw_params(struct iwl_priv *priv)
 {
 	struct iwl_nvm_data *data = priv->nvm_data;
 
+	/* all HT devices also have HT40 on at least one band */
 	if (data->sku_cap_11n_enable &&
-	    !priv->cfg->ht_params) {
+	    !priv->cfg->ht_params.ht40_bands) {
 		IWL_ERR(priv, "Invalid 11n configuration\n");
 		return -EINVAL;
 	}
@@ -1224,7 +1226,7 @@ static int iwl_nvm_check_version(struct iwl_nvm_data *data,
 }
 
 static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
-						 const struct iwl_cfg *cfg,
+						 const struct iwl_rf_cfg *cfg,
 						 const struct iwl_fw *fw,
 						 struct dentry *dbgfs_dir)
 {
@@ -1233,7 +1235,6 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 	struct iwl_op_mode *op_mode;
 	u16 num_mac;
 	u32 ucode_flags;
-	struct iwl_trans_config trans_cfg = {};
 	static const u8 no_reclaim_cmds[] = {
 		REPLY_RX_PHY_CMD,
 		REPLY_RX_MPDU_CMD,
@@ -1248,7 +1249,8 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 	 ************************/
 	hw = iwl_alloc_all();
 	if (!hw) {
-		pr_err("%s: Cannot allocate network device\n", trans->name);
+		pr_err("%s: Cannot allocate network device\n",
+		       trans->info.name);
 		err = -ENOMEM;
 		goto out;
 	}
@@ -1261,7 +1263,7 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 	priv->cfg = cfg;
 	priv->fw = fw;
 
-	switch (priv->trans->trans_cfg->device_family) {
+	switch (priv->trans->mac_cfg->device_family) {
 	case IWL_DEVICE_FAMILY_1000:
 	case IWL_DEVICE_FAMILY_100:
 		priv->lib = &iwl_dvm_1000_cfg;
@@ -1309,52 +1311,50 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 	 * Populate the state variables that the transport layer needs
 	 * to know about.
 	 */
-	trans_cfg.op_mode = op_mode;
-	trans_cfg.no_reclaim_cmds = no_reclaim_cmds;
-	trans_cfg.n_no_reclaim_cmds = ARRAY_SIZE(no_reclaim_cmds);
+	BUILD_BUG_ON(sizeof(no_reclaim_cmds) >
+		     sizeof(trans->conf.no_reclaim_cmds));
+	memcpy(trans->conf.no_reclaim_cmds, no_reclaim_cmds,
+	       sizeof(no_reclaim_cmds));
 
 	switch (iwlwifi_mod_params.amsdu_size) {
 	case IWL_AMSDU_DEF:
 	case IWL_AMSDU_4K:
-		trans_cfg.rx_buf_size = IWL_AMSDU_4K;
+		trans->conf.rx_buf_size = IWL_AMSDU_4K;
 		break;
 	case IWL_AMSDU_8K:
-		trans_cfg.rx_buf_size = IWL_AMSDU_8K;
+		trans->conf.rx_buf_size = IWL_AMSDU_8K;
 		break;
 	case IWL_AMSDU_12K:
 	default:
-		trans_cfg.rx_buf_size = IWL_AMSDU_4K;
+		trans->conf.rx_buf_size = IWL_AMSDU_4K;
 		pr_err("Unsupported amsdu_size: %d\n",
 		       iwlwifi_mod_params.amsdu_size);
 	}
 
-	trans_cfg.command_groups = iwl_dvm_groups;
-	trans_cfg.command_groups_size = ARRAY_SIZE(iwl_dvm_groups);
+	trans->conf.command_groups = iwl_dvm_groups;
+	trans->conf.command_groups_size = ARRAY_SIZE(iwl_dvm_groups);
 
-	trans_cfg.cmd_fifo = IWLAGN_CMD_FIFO_NUM;
-	trans_cfg.cb_data_offs = offsetof(struct ieee80211_tx_info,
-					  driver_data[2]);
+	trans->conf.cmd_fifo = IWLAGN_CMD_FIFO_NUM;
+	trans->conf.cb_data_offs = offsetof(struct ieee80211_tx_info,
+					    driver_data[2]);
 
 	WARN_ON(sizeof(priv->transport_queue_stop) * BITS_PER_BYTE <
-		priv->trans->trans_cfg->base_params->num_of_queues);
+		priv->trans->mac_cfg->base->num_of_queues);
 
 	ucode_flags = fw->ucode_capa.flags;
 
 	if (ucode_flags & IWL_UCODE_TLV_FLAGS_PAN) {
 		priv->sta_key_max_num = STA_KEY_MAX_NUM_PAN;
-		trans_cfg.cmd_queue = IWL_IPAN_CMD_QUEUE_NUM;
+		trans->conf.cmd_queue = IWL_IPAN_CMD_QUEUE_NUM;
 	} else {
 		priv->sta_key_max_num = STA_KEY_MAX_NUM;
-		trans_cfg.cmd_queue = IWL_DEFAULT_CMD_QUEUE_NUM;
+		trans->conf.cmd_queue = IWL_DEFAULT_CMD_QUEUE_NUM;
 	}
 
-	/* Configure transport layer */
-	iwl_trans_configure(priv->trans, &trans_cfg);
+	trans->conf.rx_mpdu_cmd = REPLY_RX_MPDU_CMD;
+	trans->conf.rx_mpdu_cmd_hdr_size = sizeof(struct iwl_rx_mpdu_res_start);
 
-	trans->rx_mpdu_cmd = REPLY_RX_MPDU_CMD;
-	trans->rx_mpdu_cmd_hdr_size = sizeof(struct iwl_rx_mpdu_res_start);
-	trans->command_groups = trans_cfg.command_groups;
-	trans->command_groups_size = trans_cfg.command_groups_size;
+	iwl_trans_op_mode_enter(priv->trans, op_mode);
 
 	/* At this point both hw and priv are allocated. */
 
@@ -1378,18 +1378,18 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 	 * 2. Read REV register
 	 ***********************/
 	IWL_INFO(priv, "Detected %s, REV=0x%X\n",
-		priv->trans->name, priv->trans->hw_rev);
+		priv->trans->info.name, priv->trans->info.hw_rev);
 
 	err = iwl_trans_start_hw(priv->trans);
 	if (err)
-		goto out_free_hw;
+		goto out_leave_trans;
 
 	/* Read the EEPROM */
 	err = iwl_read_eeprom(priv->trans, &priv->eeprom_blob,
 			      &priv->eeprom_blob_size);
 	if (err) {
 		IWL_ERR(priv, "Unable to init EEPROM\n");
-		goto out_free_hw;
+		goto out_leave_trans;
 	}
 
 	/* Reset chip to save power until we load uCode during "up". */
@@ -1437,10 +1437,7 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 		 * packaging bug or due to the eeprom check above
 		 */
 		priv->sta_key_max_num = STA_KEY_MAX_NUM;
-		trans_cfg.cmd_queue = IWL_DEFAULT_CMD_QUEUE_NUM;
-
-		/* Configure transport layer again*/
-		iwl_trans_configure(priv->trans, &trans_cfg);
+		trans->conf.cmd_queue = IWL_DEFAULT_CMD_QUEUE_NUM;
 	}
 
 	/*******************
@@ -1508,6 +1505,8 @@ out_free_eeprom_blob:
 	kfree(priv->eeprom_blob);
 out_free_eeprom:
 	kfree(priv->nvm_data);
+out_leave_trans:
+	iwl_trans_op_mode_leave(priv->trans);
 out_free_hw:
 	ieee80211_free_hw(priv->hw);
 out:
@@ -1992,7 +1991,7 @@ static void iwl_nic_config(struct iwl_op_mode *op_mode)
 	/* SKU Control */
 	iwl_trans_set_bits_mask(priv->trans, CSR_HW_IF_CONFIG_REG,
 				CSR_HW_IF_CONFIG_REG_MSK_MAC_STEP_DASH,
-				CSR_HW_REV_STEP_DASH(priv->trans->hw_rev));
+				CSR_HW_REV_STEP_DASH(priv->trans->info.hw_rev));
 
 	/* write radio config values to register */
 	if (priv->nvm_data->radio_cfg_type <= EEPROM_RF_CONFIG_TYPE_MAX) {
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/power.c b/drivers/net/wireless/intel/iwlwifi/dvm/power.c
index 6d16a7105656..6b42d6e5f30f 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/power.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/power.c
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
- * Copyright (C) 2019 Intel Corporation
+ * Copyright (C) 2019, 2025 Intel Corporation
  *
  * Portions of this file are derived from the ipw3945 project, as well
  * as portions of the ieee80211 subsystem header files.
@@ -64,32 +64,32 @@ struct iwl_power_vec_entry {
 /* for DTIM period 0 through IWL_DTIM_RANGE_0_MAX */
 /* DTIM 0 - 2 */
 static const struct iwl_power_vec_entry range_0[IWL_POWER_NUM] = {
-	{{SLP, SLP_TOUT(200), SLP_TOUT(500), SLP_VEC(1, 1, 2, 2, 0xFF)}, 0},
-	{{SLP, SLP_TOUT(200), SLP_TOUT(300), SLP_VEC(1, 2, 2, 2, 0xFF)}, 0},
-	{{SLP, SLP_TOUT(50), SLP_TOUT(100), SLP_VEC(2, 2, 2, 2, 0xFF)}, 0},
-	{{SLP, SLP_TOUT(50), SLP_TOUT(25), SLP_VEC(2, 2, 4, 4, 0xFF)}, 1},
-	{{SLP, SLP_TOUT(25), SLP_TOUT(25), SLP_VEC(2, 2, 4, 6, 0xFF)}, 2}
+	{{SLP, SLP_TOUT(200), SLP_TOUT(500), SLP_VEC(1, 1, 2, 2, 0xFF), 0}, 0},
+	{{SLP, SLP_TOUT(200), SLP_TOUT(300), SLP_VEC(1, 2, 2, 2, 0xFF), 0}, 0},
+	{{SLP, SLP_TOUT(50), SLP_TOUT(100), SLP_VEC(2, 2, 2, 2, 0xFF), 0}, 0},
+	{{SLP, SLP_TOUT(50), SLP_TOUT(25), SLP_VEC(2, 2, 4, 4, 0xFF), 0}, 1},
+	{{SLP, SLP_TOUT(25), SLP_TOUT(25), SLP_VEC(2, 2, 4, 6, 0xFF), 0}, 2}
 };
 
 
 /* for DTIM period IWL_DTIM_RANGE_0_MAX + 1 through IWL_DTIM_RANGE_1_MAX */
 /* DTIM 3 - 10 */
 static const struct iwl_power_vec_entry range_1[IWL_POWER_NUM] = {
-	{{SLP, SLP_TOUT(200), SLP_TOUT(500), SLP_VEC(1, 2, 3, 4, 4)}, 0},
-	{{SLP, SLP_TOUT(200), SLP_TOUT(300), SLP_VEC(1, 2, 3, 4, 7)}, 0},
-	{{SLP, SLP_TOUT(50), SLP_TOUT(100), SLP_VEC(2, 4, 6, 7, 9)}, 0},
-	{{SLP, SLP_TOUT(50), SLP_TOUT(25), SLP_VEC(2, 4, 6, 9, 10)}, 1},
-	{{SLP, SLP_TOUT(25), SLP_TOUT(25), SLP_VEC(2, 4, 6, 10, 10)}, 2}
+	{{SLP, SLP_TOUT(200), SLP_TOUT(500), SLP_VEC(1, 2, 3, 4, 4), 0}, 0},
+	{{SLP, SLP_TOUT(200), SLP_TOUT(300), SLP_VEC(1, 2, 3, 4, 7), 0}, 0},
+	{{SLP, SLP_TOUT(50), SLP_TOUT(100), SLP_VEC(2, 4, 6, 7, 9), 0}, 0},
+	{{SLP, SLP_TOUT(50), SLP_TOUT(25), SLP_VEC(2, 4, 6, 9, 10), 0}, 1},
+	{{SLP, SLP_TOUT(25), SLP_TOUT(25), SLP_VEC(2, 4, 6, 10, 10), 0}, 2}
 };
 
 /* for DTIM period > IWL_DTIM_RANGE_1_MAX */
 /* DTIM 11 - */
 static const struct iwl_power_vec_entry range_2[IWL_POWER_NUM] = {
-	{{SLP, SLP_TOUT(200), SLP_TOUT(500), SLP_VEC(1, 2, 3, 4, 0xFF)}, 0},
-	{{SLP, SLP_TOUT(200), SLP_TOUT(300), SLP_VEC(2, 4, 6, 7, 0xFF)}, 0},
-	{{SLP, SLP_TOUT(50), SLP_TOUT(100), SLP_VEC(2, 7, 9, 9, 0xFF)}, 0},
-	{{SLP, SLP_TOUT(50), SLP_TOUT(25), SLP_VEC(2, 7, 9, 9, 0xFF)}, 0},
-	{{SLP, SLP_TOUT(25), SLP_TOUT(25), SLP_VEC(4, 7, 10, 10, 0xFF)}, 0}
+	{{SLP, SLP_TOUT(200), SLP_TOUT(500), SLP_VEC(1, 2, 3, 4, 0xFF), 0}, 0},
+	{{SLP, SLP_TOUT(200), SLP_TOUT(300), SLP_VEC(2, 4, 6, 7, 0xFF), 0}, 0},
+	{{SLP, SLP_TOUT(50), SLP_TOUT(100), SLP_VEC(2, 7, 9, 9, 0xFF), 0}, 0},
+	{{SLP, SLP_TOUT(50), SLP_TOUT(25), SLP_VEC(2, 7, 9, 9, 0xFF), 0}, 0},
+	{{SLP, SLP_TOUT(25), SLP_TOUT(25), SLP_VEC(4, 7, 10, 10, 0xFF), 0}, 0}
 };
 
 /* advance power management */
@@ -196,7 +196,7 @@ static void iwl_static_sleep_cmd(struct iwl_priv *priv,
 	else
 		cmd->flags &= ~IWL_POWER_SLEEP_OVER_DTIM_MSK;
 
-	if (priv->trans->trans_cfg->base_params->shadow_reg_enable)
+	if (priv->trans->mac_cfg->base->shadow_reg_enable)
 		cmd->flags |= IWL_POWER_SHADOW_REG_ENA;
 	else
 		cmd->flags &= ~IWL_POWER_SHADOW_REG_ENA;
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rx.c b/drivers/net/wireless/intel/iwlwifi/dvm/rx.c
index 7f67e602940c..5f8b60824043 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/rx.c
@@ -3,7 +3,7 @@
  *
  * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Deutschland GmbH
- * Copyright(c) 2018, 2020-2021 Intel Corporation
+ * Copyright(c) 2018, 2020-2021, 2025 Intel Corporation
  *
  * Portions of this file are derived from the ipw3945 project, as well
  * as portionhelp of the ieee80211 subsystem header files.
@@ -50,7 +50,7 @@ static void iwlagn_rx_csa(struct iwl_priv *priv, struct iwl_rx_cmd_buffer *rxb)
 	 * See iwlagn_mac_channel_switch.
 	 */
 	struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_BSS];
-	struct iwl_rxon_cmd *rxon = (void *)&ctx->active;
+	struct iwl_rxon_cmd *rxon = (void *)(uintptr_t)&ctx->active;
 
 	if (!test_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status))
 		return;
@@ -643,8 +643,8 @@ static void iwlagn_pass_packet_to_mac80211(struct iwl_priv *priv,
 	fraglen = len - hdrlen;
 
 	if (fraglen) {
-		int offset = (void *)hdr + hdrlen -
-			     rxb_addr(rxb) + rxb_offset(rxb);
+		int offset = (u8 *)hdr + hdrlen -
+			     (u8 *)rxb_addr(rxb) + rxb_offset(rxb);
 
 		skb_add_rx_frag(skb, 0, rxb_steal_page(rxb), offset,
 				fraglen, rxb->truesize);
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rxon.c b/drivers/net/wireless/intel/iwlwifi/dvm/rxon.c
index f80cce37e2c0..2d3c1627f283 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/rxon.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/rxon.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /******************************************************************************
  *
- * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2003 - 2014, 2025 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Deutschland GmbH
  *****************************************************************************/
 
@@ -341,7 +341,7 @@ static int iwlagn_rxon_disconn(struct iwl_priv *priv,
 			       struct iwl_rxon_context *ctx)
 {
 	int ret;
-	struct iwl_rxon_cmd *active = (void *)&ctx->active;
+	struct iwl_rxon_cmd *active = (void *)(uintptr_t)&ctx->active;
 
 	if (ctx->ctxid == IWL_RXON_CTX_BSS) {
 		ret = iwlagn_disable_bss(priv, ctx, &ctx->staging);
@@ -441,7 +441,7 @@ static int iwlagn_rxon_connect(struct iwl_priv *priv,
 			       struct iwl_rxon_context *ctx)
 {
 	int ret;
-	struct iwl_rxon_cmd *active = (void *)&ctx->active;
+	struct iwl_rxon_cmd *active = (void *)(uintptr_t)&ctx->active;
 
 	/* RXON timing must be before associated RXON */
 	if (ctx->ctxid == IWL_RXON_CTX_BSS) {
@@ -1023,7 +1023,7 @@ static void iwl_calc_basic_rates(struct iwl_priv *priv,
 int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx)
 {
 	/* cast away the const for active_rxon in this function */
-	struct iwl_rxon_cmd *active = (void *)&ctx->active;
+	struct iwl_rxon_cmd *active = (void *)(uintptr_t)&ctx->active;
 	bool new_assoc = !!(ctx->staging.filter_flags & RXON_FILTER_ASSOC_MSK);
 	int ret;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/tx.c b/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
index 111ed1873006..24fefa0e8148 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
@@ -3,7 +3,7 @@
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
  * Copyright (C) 2019 Intel Corporation
- * Copyright (C) 2023 Intel Corporation
+ * Copyright (C) 2023, 2025 Intel Corporation
  *****************************************************************************/
 
 #include <linux/kernel.h>
@@ -463,7 +463,7 @@ static int iwlagn_alloc_agg_txq(struct iwl_priv *priv, int mq)
 	int q;
 
 	for (q = IWLAGN_FIRST_AMPDU_QUEUE;
-	     q < priv->trans->trans_cfg->base_params->num_of_queues; q++) {
+	     q < priv->trans->mac_cfg->base->num_of_queues; q++) {
 		if (!test_and_set_bit(q, priv->agg_q_alloc)) {
 			priv->queue_to_mac80211[q] = mq;
 			return q;
@@ -1277,7 +1277,7 @@ void iwlagn_rx_reply_compressed_ba(struct iwl_priv *priv,
 	 * (in Tx queue's circular buffer) of first TFD/frame in window */
 	u16 ba_resp_scd_ssn = le16_to_cpu(ba_resp->scd_ssn);
 
-	if (scd_flow >= priv->trans->trans_cfg->base_params->num_of_queues) {
+	if (scd_flow >= priv->trans->mac_cfg->base->num_of_queues) {
 		IWL_ERR(priv,
 			"BUG_ON scd_flow is bigger than number of queues\n");
 		return;
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/ucode.c b/drivers/net/wireless/intel/iwlwifi/dvm/ucode.c
index bb13ca5d666c..ac90191a3973 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/ucode.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/ucode.c
@@ -3,6 +3,7 @@
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Deutschland GmbH
+ * Copyright (C) 2025 Intel Corporation
  *****************************************************************************/
 
 #include <linux/kernel.h>
@@ -222,7 +223,7 @@ static int iwl_alive_notify(struct iwl_priv *priv)
 	int ret;
 	int i;
 
-	iwl_trans_fw_alive(priv->trans, 0);
+	iwl_trans_fw_alive(priv->trans);
 
 	if (priv->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_PAN &&
 	    priv->nvm_data->sku_cap_ipan_enable) {
@@ -293,15 +294,10 @@ int iwl_load_ucode_wait_alive(struct iwl_priv *priv,
 {
 	struct iwl_notification_wait alive_wait;
 	struct iwl_alive_data alive_data;
-	const struct fw_img *fw;
 	int ret;
 	enum iwl_ucode_type old_type;
 	static const u16 alive_cmd[] = { REPLY_ALIVE };
 
-	fw = iwl_get_ucode_image(priv->fw, ucode_type);
-	if (WARN_ON(!fw))
-		return -EINVAL;
-
 	old_type = priv->cur_ucode;
 	priv->cur_ucode = ucode_type;
 	priv->ucode_loaded = false;
@@ -310,7 +306,7 @@ int iwl_load_ucode_wait_alive(struct iwl_priv *priv,
 				   alive_cmd, ARRAY_SIZE(alive_cmd),
 				   iwl_alive_fn, &alive_data);
 
-	ret = iwl_trans_start_fw(priv->trans, fw, false);
+	ret = iwl_trans_start_fw(priv->trans, priv->fw, ucode_type, false);
 	if (ret) {
 		priv->cur_ucode = old_type;
 		iwl_remove_notification(&priv->notif_wait, &alive_wait);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index efa7b673ebc7..bee7d92293b8 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2019-2024 Intel Corporation
+ * Copyright (C) 2019-2025 Intel Corporation
  */
 #include <linux/uuid.h>
 #include "iwl-drv.h"
@@ -847,12 +847,12 @@ int iwl_acpi_get_ppag_table(struct iwl_fw_runtime *fwrt)
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
-	/* try to read ppag table rev 3, 2 or 1 (all have the same data size) */
+	/* try to read ppag table rev 1 to 4 (all have the same data size) */
 	wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data,
 				ACPI_PPAG_WIFI_DATA_SIZE_V2, &tbl_rev);
 
 	if (!IS_ERR(wifi_pkg)) {
-		if (tbl_rev >= 1 && tbl_rev <= 3) {
+		if (tbl_rev >= 1 && tbl_rev <= 4) {
 			num_sub_bands = IWL_NUM_SUB_BANDS_V2;
 			IWL_DEBUG_RADIO(fwrt,
 					"Reading PPAG table (tbl_rev=%d)\n",
@@ -882,7 +882,7 @@ int iwl_acpi_get_ppag_table(struct iwl_fw_runtime *fwrt)
 	goto out_free;
 
 read_table:
-	fwrt->ppag_ver = tbl_rev;
+	fwrt->ppag_bios_rev = tbl_rev;
 	flags = &wifi_pkg->package.elements[1];
 
 	if (flags->type != ACPI_TYPE_INTEGER) {
@@ -891,7 +891,7 @@ read_table:
 	}
 
 	fwrt->ppag_flags = iwl_bios_get_ppag_flags(flags->integer.value,
-						   fwrt->ppag_ver);
+						   fwrt->ppag_bios_rev);
 
 	/*
 	 * read, verify gain values and save them into the PPAG table.
@@ -912,6 +912,7 @@ read_table:
 		}
 	}
 
+	fwrt->ppag_bios_source = BIOS_SOURCE_ACPI;
 	ret = 0;
 
 out_free:
@@ -919,40 +920,39 @@ out_free:
 	return ret;
 }
 
-void iwl_acpi_get_phy_filters(struct iwl_fw_runtime *fwrt,
-			      struct iwl_phy_specific_cfg *filters)
+int iwl_acpi_get_phy_filters(struct iwl_fw_runtime *fwrt)
 {
+	struct iwl_phy_specific_cfg *filters = &fwrt->phy_filters;
 	struct iwl_phy_specific_cfg tmp = {};
-	union acpi_object *wifi_pkg, *data;
+	union acpi_object *wifi_pkg, *data __free(kfree);
 	int tbl_rev, i;
 
 	data = iwl_acpi_get_object(fwrt->dev, ACPI_WPFC_METHOD);
 	if (IS_ERR(data))
-		return;
+		return PTR_ERR(data);
 
 	wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data,
 					 ACPI_WPFC_WIFI_DATA_SIZE,
 					 &tbl_rev);
 	if (IS_ERR(wifi_pkg))
-		goto out_free;
+		return PTR_ERR(wifi_pkg);
 
 	if (tbl_rev != 0)
-		goto out_free;
+		return -EINVAL;
 
 	BUILD_BUG_ON(ARRAY_SIZE(filters->filter_cfg_chains) !=
 		     ACPI_WPFC_WIFI_DATA_SIZE - 1);
 
 	for (i = 0; i < ARRAY_SIZE(filters->filter_cfg_chains); i++) {
 		if (wifi_pkg->package.elements[i + 1].type != ACPI_TYPE_INTEGER)
-			goto out_free;
+			return -EINVAL;
 		tmp.filter_cfg_chains[i] =
 			cpu_to_le32(wifi_pkg->package.elements[i + 1].integer.value);
 	}
 
 	IWL_DEBUG_RADIO(fwrt, "Loaded WPFC filter config from ACPI\n");
 	*filters = tmp;
-out_free:
-	kfree(data);
+	return 0;
 }
 IWL_EXPORT_SYMBOL(iwl_acpi_get_phy_filters);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h
index e50b93472dd2..68d8fb5f6357 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2023, 2025 Intel Corporation
  */
 #ifndef __iwl_fw_acpi__
 #define __iwl_fw_acpi__
@@ -180,8 +180,7 @@ int iwl_acpi_get_tas_table(struct iwl_fw_runtime *fwrt,
 
 int iwl_acpi_get_ppag_table(struct iwl_fw_runtime *fwrt);
 
-void iwl_acpi_get_phy_filters(struct iwl_fw_runtime *fwrt,
-			      struct iwl_phy_specific_cfg *filters);
+int iwl_acpi_get_phy_filters(struct iwl_fw_runtime *fwrt);
 
 void iwl_acpi_get_guid_lock_status(struct iwl_fw_runtime *fwrt);
 
@@ -244,8 +243,10 @@ static inline int iwl_acpi_get_ppag_table(struct iwl_fw_runtime *fwrt)
 	return -ENOENT;
 }
 
-/* macro since the second argument doesn't always exist */
-#define iwl_acpi_get_phy_filters(fwrt, filters) do { } while (0)
+static inline int iwl_acpi_get_phy_filters(struct iwl_fw_runtime *fwrt)
+{
+	return -ENOENT;
+}
 
 static inline void iwl_acpi_get_guid_lock_status(struct iwl_fw_runtime *fwrt)
 {
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
index 42360a8f23aa..3ce477c248ce 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
@@ -112,6 +112,16 @@ struct iwl_alive_ntf_v6 {
 	struct iwl_imr_alive_info imr;
 } __packed; /* UCODE_ALIVE_NTFY_API_S_VER_6 */
 
+struct iwl_alive_ntf {
+	__le16 status;
+	__le16 flags;
+	struct iwl_lmac_alive lmac_data[2];
+	struct iwl_umac_alive umac_data;
+	struct iwl_sku_id sku_id;
+	struct iwl_imr_alive_info imr;
+	__le64 platform_id;
+} __packed; /* UCODE_ALIVE_NTFY_API_S_VER_8 */
+
 /**
  * enum iwl_extended_cfg_flags - commands driver may send before
  *	finishing init flow
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index d43adb6f9220..1c86a858aaab 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -2,7 +2,7 @@
 /*
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022, 2024 Intel Corporation
+ * Copyright (C) 2018-2022, 2024-2025 Intel Corporation
  */
 #ifndef __iwl_fw_api_commands_h__
 #define __iwl_fw_api_commands_h__
@@ -145,8 +145,8 @@ enum iwl_legacy_cmds {
 	REMOVE_STA = 0x19,
 
 	/**
-	 * @TX_CMD: uses &struct iwl_tx_cmd or &struct iwl_tx_cmd_gen2 or
-	 *	&struct iwl_tx_cmd_gen3,
+	 * @TX_CMD: uses &struct iwl_tx_cmd_v6 or &struct iwl_tx_cmd_v9 or
+	 *	&struct iwl_tx_cmd,
 	 *	response in &struct iwl_tx_resp or
 	 *	&struct iwl_tx_resp_v3
 	 */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
index c139b965980d..9c88bb280609 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
@@ -98,7 +98,7 @@ enum iwl_data_path_subcmd_ids {
 
 	/**
 	 * @ESR_MODE_NOTIF: notification to recommend/force a wanted esr mode,
-	 *	uses &struct iwl_esr_mode_notif
+	 *	uses &struct iwl_esr_mode_notif or &struct iwl_esr_mode_notif_v1
 	 */
 	ESR_MODE_NOTIF = 0xF3,
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
index 4fab6c66994e..3173fa96cb48 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
@@ -527,8 +527,8 @@ enum iwl_fw_ini_time_point {
  * @IWL_FW_INI_APPLY_POLICY_OVERRIDE_DATA: override trigger data.
  *	Append otherwise
  * @IWL_FW_INI_APPLY_POLICY_DUMP_COMPLETE_CMD: send cmd once dump collected
- * @IWL_FW_INI_APPLY_POLICY_RESET_HANDSHAKE: perform reset handshake and
- *	split dump to before/after with region marking
+ * @IWL_FW_INI_APPLY_POLICY_SPLIT_DUMP_RESET: split this dump into regions
+ *	before and after the reset handshake
  */
 enum iwl_fw_ini_trigger_apply_policy {
 	IWL_FW_INI_APPLY_POLICY_MATCH_TIME_POINT	= BIT(0),
@@ -537,7 +537,7 @@ enum iwl_fw_ini_trigger_apply_policy {
 	IWL_FW_INI_APPLY_POLICY_OVERRIDE_CFG		= BIT(9),
 	IWL_FW_INI_APPLY_POLICY_OVERRIDE_DATA		= BIT(10),
 	IWL_FW_INI_APPLY_POLICY_DUMP_COMPLETE_CMD	= BIT(16),
-	IWL_FW_INI_APPLY_POLICY_RESET_HANDSHAKE		= BIT(17),
+	IWL_FW_INI_APPLY_POLICY_SPLIT_DUMP_RESET	= BIT(17),
 };
 
 /**
@@ -560,7 +560,7 @@ enum iwl_fw_ini_trigger_reset_fw_policy {
  * @IWL_FW_INI_DEBUG_DUMP_POLICY_MAX_LIMIT_600KB: mini dump only 600KB region dump
  * @IWL_FW_IWL_DEBUG_DUMP_POLICY_MAX_LIMIT_5MB: mini dump 5MB size dump
  * @IWL_FW_IWL_DEBUG_DUMP_POLICY_BEFORE_RESET: dump this region before reset
- *	handshake (if requested by %IWL_FW_INI_APPLY_POLICY_RESET_HANDSHAKE)
+ *	handshake (if requested by %IWL_FW_INI_APPLY_POLICY_SPLIT_DUMP_RESET)
  */
 enum iwl_fw_ini_dump_policy {
 	IWL_FW_INI_DEBUG_DUMP_POLICY_NO_LIMIT           = BIT(0),
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
index e1952fc6d149..33541f92c7c7 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
@@ -6,6 +6,11 @@
  */
 #ifndef __iwl_fw_api_location_h__
 #define __iwl_fw_api_location_h__
+#include <linux/ieee80211.h>
+#include <linux/if_ether.h>
+#include <linux/types.h>
+#include <linux/bits.h>
+#include "rs.h"
 
 /**
  * enum iwl_location_subcmd_ids - location group command IDs
@@ -1609,7 +1614,7 @@ struct iwl_tof_range_rsp_ap_entry_ntfy_v5 {
 } __packed; /* LOCATION_RANGE_RSP_AP_ETRY_NTFY_API_S_VER_5 */
 
 /**
- * struct iwl_tof_range_rsp_ap_entry_ntfy - AP parameters (response)
+ * struct iwl_tof_range_rsp_ap_entry_ntfy_v7 - AP parameters (response)
  * @bssid: BSSID of the AP
  * @measure_status: current APs measurement status, one of
  *	&enum iwl_tof_entry_status.
@@ -1645,7 +1650,7 @@ struct iwl_tof_range_rsp_ap_entry_ntfy_v5 {
  * @tx_pn: the last PN used for this responder Tx in case PMF is configured in
  *	LE byte order.
  */
-struct iwl_tof_range_rsp_ap_entry_ntfy {
+struct iwl_tof_range_rsp_ap_entry_ntfy_v7 {
 	u8 bssid[ETH_ALEN];
 	u8 measure_status;
 	u8 measure_bw;
@@ -1672,6 +1677,65 @@ struct iwl_tof_range_rsp_ap_entry_ntfy {
 } __packed; /* LOCATION_RANGE_RSP_AP_ETRY_NTFY_API_S_VER_6,
 	       LOCATION_RANGE_RSP_AP_ETRY_NTFY_API_S_VER_7 */
 
+/**
+ * struct iwl_tof_range_rsp_ap_entry_ntfy - AP parameters (response)
+ * @bssid: BSSID of the AP
+ * @measure_status: current APs measurement status, one of
+ *	&enum iwl_tof_entry_status.
+ * @measure_bw: Current AP Bandwidth: 0  20MHz, 1  40MHz, 2  80MHz
+ * @rtt: The Round Trip Time that took for the last measurement for
+ *	current AP [pSec]
+ * @rtt_variance: The Variance of the RTT values measured for current AP
+ * @rtt_spread: The Difference between the maximum and the minimum RTT
+ *	values measured for current AP in the current session [pSec]
+ * @rssi: RSSI as uploaded in the Channel Estimation notification
+ * @rssi_spread: The Difference between the maximum and the minimum RSSI values
+ *	measured for current AP in the current session
+ * @last_burst: 1 if no more FTM sessions are scheduled for this responder
+ * @refusal_period: refusal period in case of
+ *	@IWL_TOF_ENTRY_RESPONDER_CANNOT_COLABORATE [sec]
+ * @timestamp: The GP2 Clock [usec] where Channel Estimation notification was
+ *	uploaded by the LMAC
+ * @start_tsf: measurement start time in TSF of the mac specified in the range
+ *	request
+ * @reserved1: reserved, for backwards compatibility
+ * @t2t3_initiator: as calculated from the algo in the initiator
+ * @t1t4_responder: as calculated from the algo in the responder
+ * @common_calib: Calib val that was used in for this AP measurement
+ * @specific_calib: val that was used in for this AP measurement
+ * @papd_calib_output: The result of the tof papd calibration that was injected
+ *	into the algorithm.
+ * @rttConfidence: a value between 0 - 31 that represents the rtt accuracy.
+ * @reserved: for alignment
+ * @rx_pn: the last PN used for this responder Rx in case PMF is configured in
+ *	LE byte order.
+ * @tx_pn: the last PN used for this responder Tx in case PMF is configured in
+ *	LE byte order.
+ */
+struct iwl_tof_range_rsp_ap_entry_ntfy {
+	u8 bssid[ETH_ALEN];
+	u8 measure_status;
+	u8 measure_bw;
+	__le32 rtt;
+	__le32 rtt_variance;
+	__le32 rtt_spread;
+	s8 rssi;
+	u8 rssi_spread;
+	u8 last_burst;
+	u8 refusal_period;
+	__le32 timestamp;
+	__le32 start_tsf;
+	__le32 reserved1[2];
+	__le32 t2t3_initiator;
+	__le32 t1t4_responder;
+	__le16 common_calib;
+	__le16 specific_calib;
+	__le32 papd_calib_output;
+	u8 rttConfidence;
+	u8 reserved[3];
+	u8 rx_pn[IEEE80211_CCMP_PN_LEN];
+	u8 tx_pn[IEEE80211_CCMP_PN_LEN];
+} __packed; /* LOCATION_RANGE_RSP_AP_ETRY_NTFY_API_S_VER_8 */
 
 /**
  * enum iwl_tof_response_status - tof response status
@@ -1739,6 +1803,24 @@ struct iwl_tof_range_rsp_ntfy_v7 {
 } __packed; /* LOCATION_RANGE_RSP_NTFY_API_S_VER_7 */
 
 /**
+ * struct iwl_tof_range_rsp_ntfy_v9 - ranging response notification
+ * @request_id: A Token ID of the corresponding Range request
+ * @num_of_aps: Number of APs results
+ * @last_report: 1 if no more FTM sessions are scheduled, 0 otherwise.
+ * @reserved: reserved
+ * @ap: per-AP data
+ */
+struct iwl_tof_range_rsp_ntfy_v9 {
+	u8 request_id;
+	u8 num_of_aps;
+	u8 last_report;
+	u8 reserved;
+	struct iwl_tof_range_rsp_ap_entry_ntfy_v7 ap[IWL_TOF_MAX_APS];
+} __packed; /* LOCATION_RANGE_RSP_NTFY_API_S_VER_8,
+	     * LOCATION_RANGE_RSP_NTFY_API_S_VER_9
+	     */
+
+/**
  * struct iwl_tof_range_rsp_ntfy - ranging response notification
  * @request_id: A Token ID of the corresponding Range request
  * @num_of_aps: Number of APs results
@@ -1752,8 +1834,7 @@ struct iwl_tof_range_rsp_ntfy {
 	u8 last_report;
 	u8 reserved;
 	struct iwl_tof_range_rsp_ap_entry_ntfy ap[IWL_TOF_MAX_APS];
-} __packed; /* LOCATION_RANGE_RSP_NTFY_API_S_VER_8,
-	       LOCATION_RANGE_RSP_NTFY_API_S_VER_9 */
+} __packed; /* LOCATION_RANGE_RSP_NTFY_API_S_VER_10 */
 
 #define IWL_MVM_TOF_MCSI_BUF_SIZE  (245)
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index b511e3aa6bb2..b9f559dac39f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -311,8 +311,41 @@ enum iwl_mac_config_filter_flags {
 }; /* MAC_FILTER_FLAGS_MASK_E_VER_1 */
 
 /**
+ * struct iwl_mac_wifi_gen_support_v2 - parameters of iwl_mac_config_cmd
+ *	with support up to eht as in version 2 of the command
+ *
+ * @he_support: does this MAC support HE
+ * @he_ap_support: HE AP enabled, "pseudo HE", no trigger frame handling
+ * @eht_support: does this MAC support EHT. Requires he_support
+ */
+struct iwl_mac_wifi_gen_support_v2 {
+	__le16 he_support;
+	__le16 he_ap_support;
+	__le32 eht_support;
+} __packed;
+
+/**
+ * struct iwl_mac_wifi_gen_support - parameters of iwl_mac_config_cmd
+ *	with support up to uhr as in version 3 of the command
+ * ( MAC_CONTEXT_CONFIG_CMD = 0x8 )
+ *
+ * @he_support: does this MAC support HE
+ * @he_ap_support: HE AP enabled, "pseudo HE", no trigger frame handling
+ * @eht_support: does this MAC support EHT. Requires he_support
+ * @uhr_support: does this MAC support UHR. Requires eht_support
+ * @reserved: reserved for alignment and to match version 2's size
+ */
+struct iwl_mac_wifi_gen_support {
+	u8 he_support;
+	u8 he_ap_support;
+	u8 eht_support;
+	u8 uhr_support;
+	__le32 reserved;
+} __packed;
+
+/**
  * struct iwl_mac_config_cmd - command structure to configure MAC contexts in
- *	MLD API
+ *	MLD API for versions 2 and 3
  * ( MAC_CONTEXT_CONFIG_CMD = 0x8 )
  *
  * @id_and_color: ID and color of the MAC
@@ -321,9 +354,8 @@ enum iwl_mac_config_filter_flags {
  * @local_mld_addr: mld address
  * @reserved_for_local_mld_addr: reserved
  * @filter_flags: combination of &enum iwl_mac_config_filter_flags
- * @he_support: does this MAC support HE
- * @he_ap_support: HE AP enabled, "pseudo HE", no trigger frame handling
- * @eht_support: does this MAC support EHT. Requires he_support
+ * @wifi_gen_v2: he/eht parameters as in cmd version 2
+ * @wifi_gen: he/eht/uhr parameters as in cmd version 3
  * @nic_not_ack_enabled: mark that the NIC doesn't support receiving
  *	ACK-enabled AGG, (i.e. both BACK and non-BACK frames in single AGG).
  *	If the NIC is not ACK_ENABLED it may use the EOF-bit in first non-0
@@ -332,7 +364,6 @@ enum iwl_mac_config_filter_flags {
  * @p2p_dev: mac data for p2p device
  */
 struct iwl_mac_config_cmd {
-	/* COMMON_INDEX_HDR_API_S_VER_1 */
 	__le32 id_and_color;
 	__le32 action;
 	/* MAC_CONTEXT_TYPE_API_E */
@@ -340,16 +371,17 @@ struct iwl_mac_config_cmd {
 	u8 local_mld_addr[6];
 	__le16 reserved_for_local_mld_addr;
 	__le32 filter_flags;
-	__le16 he_support;
-	__le16 he_ap_support;
-	__le32 eht_support;
+	union {
+		struct iwl_mac_wifi_gen_support_v2 wifi_gen_v2;
+		struct iwl_mac_wifi_gen_support wifi_gen;
+	};
 	__le32 nic_not_ack_enabled;
 	/* MAC_CONTEXT_CONFIG_SPECIFIC_DATA_API_U_VER_2 */
 	union {
 		struct iwl_mac_client_data client;
 		struct iwl_mac_p2p_dev_data p2p_dev;
 	};
-} __packed; /* MAC_CONTEXT_CONFIG_CMD_API_S_VER_2 */
+} __packed; /* MAC_CONTEXT_CONFIG_CMD_API_S_VER_2_VER_3 */
 
 /**
  * enum iwl_link_ctx_modify_flags - indicate to the fw what fields are being
@@ -457,6 +489,24 @@ enum iwl_link_modify_bandwidth {
 };
 
 /**
+ * struct iwl_npca_params - NPCA parameters (non-primary channel access)
+ *
+ * @switch_delay: after switch, delay TX according to destination AP
+ * @switch_back_delay: switch back to control channel before OBSS frame end
+ * @min_dur_threshold: minimum PPDU time to switch to the non-primary
+ *	NPCA channel
+ * @flags: NPCA flags - bit 0: puncturing allowed, bit 1: new TX allowed
+ * @reserved: reserved for alignment purposes
+ */
+struct iwl_npca_params {
+	u8 switch_delay;
+	u8 switch_back_delay;
+	__le16 min_dur_threshold;
+	__le16 flags;
+	__le16 reserved;
+} __packed; /* NPCA_PARAM_API_S_VER_1 */
+
+/**
  * struct iwl_link_config_cmd - command structure to configure the LINK context
  *	in MLD API
  * ( LINK_CONFIG_CMD =0x9 )
@@ -513,6 +563,8 @@ enum iwl_link_modify_bandwidth {
  *	IEEE802.11REVme-D5.0
  * @ibss_bssid_addr: bssid for ibss
  * @reserved_for_ibss_bssid_addr: reserved
+ * @npca_params: NPCA parameters
+ * @prio_edca_params: priority EDCA parameters for enhanced QoS
  * @reserved3: reserved for future use
  */
 struct iwl_link_config_cmd {
@@ -560,8 +612,10 @@ struct iwl_link_config_cmd {
 	u8 ul_mu_data_disable;
 	u8 ibss_bssid_addr[6];
 	__le16 reserved_for_ibss_bssid_addr;
-	__le32 reserved3[8];
-} __packed; /* LINK_CONTEXT_CONFIG_CMD_API_S_VER_1, _VER_2, _VER_3, _VER_4, _VER_5, _VER_6 */
+	struct iwl_npca_params npca_params; /* since _VER_7 */
+	struct iwl_ac_qos prio_edca_params; /* since _VER_7 */
+	__le32 reserved3[4];
+} __packed; /* LINK_CONTEXT_CONFIG_CMD_API_S_VER_1, _VER_2, _VER_3, _VER_4, _VER_5, _VER_6, _VER_7 */
 
 /* Currently FW supports link ids in the range 0-3 and can have
  * at most two active links for each vif.
@@ -589,6 +643,62 @@ enum iwl_fw_sta_type {
 }; /* STATION_TYPE_E_VER_1 */
 
 /**
+ * struct iwl_sta_cfg_cmd_v1 - cmd structure to add a peer sta to the uCode's
+ *	station table
+ * ( STA_CONFIG_CMD = 0xA )
+ *
+ * @sta_id: index of station in uCode's station table
+ * @link_id: the id of the link that is used to communicate with this sta
+ * @peer_mld_address: the peers mld address
+ * @reserved_for_peer_mld_address: reserved
+ * @peer_link_address: the address of the link that is used to communicate
+ *	with this sta
+ * @reserved_for_peer_link_address: reserved
+ * @station_type: type of this station. See &enum iwl_fw_sta_type
+ * @assoc_id: for GO only
+ * @beamform_flags: beam forming controls
+ * @mfp: indicates whether the STA uses management frame protection or not.
+ * @mimo: indicates whether the sta uses mimo or not
+ * @mimo_protection: indicates whether the sta uses mimo protection or not
+ * @ack_enabled: indicates that the AP supports receiving ACK-
+ *	enabled AGG, i.e. both BACK and non-BACK frames in a single AGG
+ * @trig_rnd_alloc: indicates that trigger based random allocation
+ *	is enabled according to UORA element existence
+ * @tx_ampdu_spacing: minimum A-MPDU spacing:
+ *	4 - 2us density, 5 - 4us density, 6 - 8us density, 7 - 16us density
+ * @tx_ampdu_max_size: maximum A-MPDU length: 0 - 8K, 1 - 16K, 2 - 32K,
+ *	3 - 64K, 4 - 128K, 5 - 256K, 6 - 512K, 7 - 1024K.
+ * @sp_length: the size of the SP in actual number of frames
+ * @uapsd_acs:  4 LS bits are trigger enabled ACs, 4 MS bits are the deliver
+ *	enabled ACs.
+ * @pkt_ext: optional, exists according to PPE-present bit in the HE/EHT-PHY
+ *	capa
+ * @htc_flags: which features are supported in HTC
+ */
+struct iwl_sta_cfg_cmd_v1 {
+	__le32 sta_id;
+	__le32 link_id;
+	u8 peer_mld_address[ETH_ALEN];
+	__le16 reserved_for_peer_mld_address;
+	u8 peer_link_address[ETH_ALEN];
+	__le16 reserved_for_peer_link_address;
+	__le32 station_type;
+	__le32 assoc_id;
+	__le32 beamform_flags;
+	__le32 mfp;
+	__le32 mimo;
+	__le32 mimo_protection;
+	__le32 ack_enabled;
+	__le32 trig_rnd_alloc;
+	__le32 tx_ampdu_spacing;
+	__le32 tx_ampdu_max_size;
+	__le32 sp_length;
+	__le32 uapsd_acs;
+	struct iwl_he_pkt_ext_v2 pkt_ext;
+	__le32 htc_flags;
+} __packed; /* STA_CMD_API_S_VER_1 */
+
+/**
  * struct iwl_sta_cfg_cmd - cmd structure to add a peer sta to the uCode's
  *	station table
  * ( STA_CONFIG_CMD = 0xA )
@@ -620,6 +730,14 @@ enum iwl_fw_sta_type {
  * @pkt_ext: optional, exists according to PPE-present bit in the HE/EHT-PHY
  *	capa
  * @htc_flags: which features are supported in HTC
+ * @use_ldpc_x2_cw: Indicates whether to use LDPC with double CW
+ * @use_icf: Indicates whether to use ICF instead of RTS
+ * @dps_pad_time: DPS (Dynamic Power Save) padding delay resolution to ensure
+ *	proper timing alignment
+ * @dps_trans_delay: DPS minimal time that takes the peer to return to low power
+ * @mic_prep_pad_delay: MIC prep time padding
+ * @mic_compute_pad_delay: MIC compute time padding
+ * @reserved: Reserved for alignment
  */
 struct iwl_sta_cfg_cmd {
 	__le32 sta_id;
@@ -642,7 +760,14 @@ struct iwl_sta_cfg_cmd {
 	__le32 uapsd_acs;
 	struct iwl_he_pkt_ext_v2 pkt_ext;
 	__le32 htc_flags;
-} __packed; /* STA_CMD_API_S_VER_1 */
+	u8 use_ldpc_x2_cw;
+	u8 use_icf;
+	u8 dps_pad_time;
+	u8 dps_trans_delay;
+	u8 mic_prep_pad_delay;
+	u8 mic_compute_pad_delay;
+	u8 reserved[2];
+} __packed; /* STA_CMD_API_S_VER_2 */
 
 /**
  * struct iwl_aux_sta_cmd - command for AUX STA configuration
@@ -686,9 +811,9 @@ struct iwl_mvm_sta_disable_tx_cmd {
 
 /**
  * enum iwl_mvm_fw_esr_recommendation - FW recommendation code
- * @ESR_RECOMMEND_LEAVE: recommendation to leave esr
- * @ESR_FORCE_LEAVE: force exiting esr
- * @ESR_RECOMMEND_ENTER: recommendation to enter esr
+ * @ESR_RECOMMEND_LEAVE: recommendation to leave EMLSR
+ * @ESR_FORCE_LEAVE: force exiting EMLSR
+ * @ESR_RECOMMEND_ENTER: recommendation to enter EMLSR
  */
 enum iwl_mvm_fw_esr_recommendation {
 	ESR_RECOMMEND_LEAVE,
@@ -697,15 +822,46 @@ enum iwl_mvm_fw_esr_recommendation {
 }; /* ESR_MODE_RECOMMENDATION_CODE_API_E_VER_1 */
 
 /**
- * struct iwl_esr_mode_notif - FWs recommendation/force for esr mode
+ * struct iwl_esr_mode_notif_v1 - FW recommendation/force for EMLSR mode
  *
- * @action: the action to apply on esr state. See &iwl_mvm_fw_esr_recommendation
+ * @action: the action to apply on EMLSR state.
+ *	See &iwl_mvm_fw_esr_recommendation
  */
-struct iwl_esr_mode_notif {
+struct iwl_esr_mode_notif_v1 {
 	__le32 action;
 } __packed; /* ESR_MODE_RECOMMENDATION_NTFY_API_S_VER_1 */
 
 /**
+ * enum iwl_esr_leave_reason - reasons for leaving EMLSR mode
+ *
+ * @ESR_LEAVE_REASON_OMI_MU_UL_DISALLOWED: OMI MU UL disallowed
+ * @ESR_LEAVE_REASON_NO_TRIG_FOR_ESR_STA: No trigger for EMLSR station
+ * @ESR_LEAVE_REASON_NO_ESR_STA_IN_MU_DL: No EMLSR station in MU DL
+ * @ESR_LEAVE_REASON_BAD_ACTIV_FRAME_TH: Bad activation frame threshold
+ * @ESR_LEAVE_REASON_RTS_IN_DUAL_LISTEN: RTS in dual listen
+ */
+enum iwl_esr_leave_reason {
+	ESR_LEAVE_REASON_OMI_MU_UL_DISALLOWED	= BIT(0),
+	ESR_LEAVE_REASON_NO_TRIG_FOR_ESR_STA	= BIT(1),
+	ESR_LEAVE_REASON_NO_ESR_STA_IN_MU_DL	= BIT(2),
+	ESR_LEAVE_REASON_BAD_ACTIV_FRAME_TH	= BIT(3),
+	ESR_LEAVE_REASON_RTS_IN_DUAL_LISTEN	= BIT(4),
+};
+
+/**
+ * struct iwl_esr_mode_notif - FW recommendation/force for EMLSR mode
+ *
+ * @action: the action to apply on EMLSR state.
+ *	See &iwl_mvm_fw_esr_recommendation
+ * @leave_reason_mask: mask for various reasons to leave EMLSR mode.
+ *	See &iwl_esr_leave_reason
+ */
+struct iwl_esr_mode_notif {
+	__le32 action;
+	__le32 leave_reason_mask;
+} __packed; /* ESR_MODE_RECOMMENDATION_NTFY_API_S_VER_2 */
+
+/**
  * struct iwl_missed_beacons_notif - sent when by the firmware upon beacon loss
  *  ( MISSED_BEACONS_NOTIF = 0xF6 )
  * @link_id: fw link ID
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
index 26301c0b06a1..2a174c00b712 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2022, 2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2022, 2024-2025 Intel Corporation
  * Copyright (C) 2017 Intel Deutschland GmbH
  */
 #ifndef __iwl_fw_api_mac_h__
@@ -287,9 +287,9 @@ struct iwl_ac_qos {
 	__le16 cw_min;
 	__le16 cw_max;
 	u8 aifsn;
-	u8 fifos_mask;
+	u8 fifos_mask; /* not in use since _VER_3 */
 	__le16 edca_txop;
-} __packed; /* AC_QOS_API_S_VER_2 */
+} __packed; /* AC_QOS_API_S_VER_2, _VER_3 */
 
 /**
  * struct iwl_mac_ctx_cmd - command structure to configure MAC contexts
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h b/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h
index 4d8a12799c4d..4594a7c94bd6 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018, 2020-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018, 2020-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -146,6 +146,7 @@ struct iwl_phy_context_cmd_v1 {
  * @sbb_ctrl_channel_loc: location of the control channel
  * @puncture_mask: bitmap of punctured subchannels
  * @dsp_cfg_flags: set to 0
+ * @secondary_ctrl_chnl_loc: location of secondary control channel
  * @reserved: reserved to align to 64 bit
  */
 struct iwl_phy_context_cmd {
@@ -164,11 +165,13 @@ struct iwl_phy_context_cmd {
 		};
 	};
 	__le32 dsp_cfg_flags;
-	__le32 reserved;
+	u8 secondary_ctrl_chnl_loc;
+	u8 reserved[3];
 } __packed; /* PHY_CONTEXT_CMD_API_VER_3,
 	     * PHY_CONTEXT_CMD_API_VER_4,
 	     * PHY_CONTEXT_CMD_API_VER_5,
-	     * PHY_CONTEXT_CMD_API_VER_6
+	     * PHY_CONTEXT_CMD_API_VER_6,
+	     * PHY_CONTEXT_CMD_API_S_VER_7
 	     */
 
 #endif /* __iwl_fw_api_phy_ctxt_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
index 37ec26596ee7..23140205ccb9 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
@@ -1,12 +1,14 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
 #ifndef __iwl_fw_api_power_h__
 #define __iwl_fw_api_power_h__
 
+#include "nvm-reg.h"
+
 /* Power Management Commands, Responses, Notifications */
 
 /**
@@ -54,7 +56,7 @@ struct iwl_ltr_config_cmd_v1 {
  * @flags: See &enum iwl_ltr_config_flags
  * @static_long: static LTR Long register value.
  * @static_short: static LTR Short register value.
- * @ltr_cfg_values: LTR parameters table values (in usec) in folowing order:
+ * @ltr_cfg_values: LTR parameters table values (in usec) in following order:
  *	TX, RX, Short Idle, Long Idle. Used only if %LTR_CFG_FLAG_UPDATE_VALUES
  *	is set.
  * @ltr_short_idle_timeout: LTR Short Idle timeout (in usec). Used only if
@@ -89,6 +91,7 @@ struct iwl_ltr_config_cmd {
  * @POWER_FLAGS_LPRX_ENA_MSK: Low Power RX enable.
  * @POWER_FLAGS_UAPSD_MISBEHAVING_ENA_MSK: AP/GO's uAPSD misbehaving
  *		detection enablement
+ * @POWER_FLAGS_ENABLE_SMPS_MSK: SMPS is allowed for this vif
 */
 enum iwl_power_flags {
 	POWER_FLAGS_POWER_SAVE_ENA_MSK		= BIT(0),
@@ -99,6 +102,7 @@ enum iwl_power_flags {
 	POWER_FLAGS_ADVANCE_PM_ENA_MSK		= BIT(9),
 	POWER_FLAGS_LPRX_ENA_MSK		= BIT(11),
 	POWER_FLAGS_UAPSD_MISBEHAVING_ENA_MSK	= BIT(12),
+	POWER_FLAGS_ENABLE_SMPS_MSK		= BIT(14),
 };
 
 #define IWL_POWER_VEC_SIZE 5
@@ -216,7 +220,6 @@ struct iwl_mac_power_cmd {
 	/* CONTEXT_DESC_API_T_VER_1 */
 	__le32 id_and_color;
 
-	/* CLIENT_PM_POWER_TABLE_S_VER_1 */
 	__le16 flags;
 	__le16 keep_alive_seconds;
 	__le32 rx_data_timeout;
@@ -237,7 +240,7 @@ struct iwl_mac_power_cmd {
 	u8 heavy_rx_thld_percentage;
 	u8 limited_ps_threshold;
 	u8 reserved;
-} __packed;
+} __packed; /* CLIENT_PM_POWER_TABLE_S_VER_1, VER_2 */
 
 /*
  * struct iwl_uapsd_misbehaving_ap_notif - FW sends this notification when
@@ -628,28 +631,37 @@ enum iwl_ppag_flags {
 
 /**
  * union iwl_ppag_table_cmd - union for all versions of PPAG command
- * @v1: version 1
- * @v2: version 2
- * version 3, 4, 5 and 6 are the same structure as v2,
+ * @v1: command version 1 structure.
+ * @v2: command version from 2 to 6 are same structure as v2.
  *	but has a different format of the flags bitmap
+ * @v3: command version 7 structure.
  * @v1.flags: values from &enum iwl_ppag_flags
  * @v1.gain: table of antenna gain values per chain and sub-band
  * @v1.reserved: reserved
  * @v2.flags: values from &enum iwl_ppag_flags
  * @v2.gain: table of antenna gain values per chain and sub-band
- * @v2.reserved: reserved
+ * @v3.ppag_config_info: see @struct bios_value_u32
+ * @v3.gain: table of antenna gain values per chain and sub-band
+ * @v3.reserved: reserved
  */
 union iwl_ppag_table_cmd {
 	struct {
 		__le32 flags;
 		s8 gain[IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS_V1];
 		s8 reserved[2];
-	} v1;
+	} __packed v1; /* PER_PLAT_ANTENNA_GAIN_CMD_API_S_VER_1 */
 	struct {
 		__le32 flags;
 		s8 gain[IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS_V2];
 		s8 reserved[2];
-	} v2;
+	} __packed v2; /* PER_PLAT_ANTENNA_GAIN_CMD_API_S_VER_2, VER3, VER4,
+			* VER5, VER6
+			*/
+	struct {
+		struct bios_value_u32 ppag_config_info;
+		s8 gain[IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS_V2];
+		s8 reserved[2];
+	} __packed v3; /* PER_PLAT_ANTENNA_GAIN_CMD_API_S_VER_7 */
 } __packed;
 
 #define IWL_PPAG_CMD_V4_MASK (IWL_PPAG_ETSI_MASK | IWL_PPAG_CHINA_MASK)
@@ -657,6 +669,15 @@ union iwl_ppag_table_cmd {
 			      IWL_PPAG_ETSI_LPI_UHB_MASK | \
 			      IWL_PPAG_USA_LPI_UHB_MASK)
 
+#define IWL_PPAG_CMD_V6_MASK (IWL_PPAG_CMD_V5_MASK |		\
+			      IWL_PPAG_ETSI_VLP_UHB_MASK |	\
+			      IWL_PPAG_ETSI_SP_UHB_MASK |	\
+			      IWL_PPAG_USA_VLP_UHB_MASK |	\
+			      IWL_PPAG_USA_SP_UHB_MASK |	\
+			      IWL_PPAG_CANADA_LPI_UHB_MASK |	\
+			      IWL_PPAG_CANADA_VLP_UHB_MASK |	\
+			      IWL_PPAG_CANADA_SP_UHB_MASK)
+
 #define MCC_TO_SAR_OFFSET_TABLE_ROW_SIZE	26
 #define MCC_TO_SAR_OFFSET_TABLE_COL_SIZE	13
 
@@ -690,7 +711,7 @@ struct iwl_sar_offset_mapping_cmd {
  *      Roaming Energy Delta Threshold, otherwise use normal Energy Delta
  *      Threshold. Typical energy threshold is -72dBm.
  * @bf_temp_threshold: This threshold determines the type of temperature
- *	filtering (Slow or Fast) that is selected (Units are in Celsuis):
+ *	filtering (Slow or Fast) that is selected (Units are in Celsius):
  *	If the current temperature is above this threshold - Fast filter
  *	will be used, If the current temperature is below this threshold -
  *	Slow filter will be used.
@@ -698,12 +719,12 @@ struct iwl_sar_offset_mapping_cmd {
  *      calculated for this and the last passed beacon is greater than this
  *      threshold. Zero value means that the temperature change is ignored for
  *      beacon filtering; beacons will not be  forced to be sent to driver
- *      regardless of whether its temerature has been changed.
+ *      regardless of whether its temperature has been changed.
  * @bf_temp_slow_filter: Send Beacon to driver if delta in temperature values
  *      calculated for this and the last passed beacon is greater than this
  *      threshold. Zero value means that the temperature change is ignored for
  *      beacon filtering; beacons will not be forced to be sent to driver
- *      regardless of whether its temerature has been changed.
+ *      regardless of whether its temperature has been changed.
  * @bf_enable_beacon_filter: 1, beacon filtering is enabled; 0, disabled.
  * @bf_debug_flag: beacon filtering debug configuration
  * @bf_escape_timer: Send beacons to to driver if no beacons were passed
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
index c2f806cbab59..3222cbcbe1ab 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
@@ -1,11 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2022, 2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2022, 2024-2025 Intel Corporation
  * Copyright (C) 2017 Intel Deutschland GmbH
  */
 #ifndef __iwl_fw_api_rs_h__
 #define __iwl_fw_api_rs_h__
-
+#include <linux/bitfield.h>
+#include <linux/types.h>
+#include <linux/bits.h>
 #include "mac.h"
 
 /**
@@ -213,7 +215,8 @@ enum iwl_tlc_update_flags {
  * @sta_id: station id
  * @reserved: reserved
  * @flags: bitmap of notifications reported
- * @rate: current initial rate
+ * @rate: current initial rate, format depends on the notification
+ *	version
  * @amsdu_size: Max AMSDU size, in bytes
  * @amsdu_enabled: bitmap for per-TID AMSDU enablement
  */
@@ -224,7 +227,7 @@ struct iwl_tlc_update_notif {
 	__le32 rate;
 	__le32 amsdu_size;
 	__le32 amsdu_enabled;
-} __packed; /* TLC_MNG_UPDATE_NTFY_API_S_VER_2 */
+} __packed; /* TLC_MNG_UPDATE_NTFY_API_S_VER_2, _VER_3, _VER_4 */
 
 /**
  * enum iwl_tlc_debug_types - debug options
@@ -427,6 +430,7 @@ enum {
 
 /* Bit 4-5: (0) SISO, (1) MIMO2 (2) MIMO3 */
 #define RATE_VHT_MCS_RATE_CODE_MSK	0xf
+#define RATE_VHT_MCS_NSS_MSK		0x30
 
 /*
  * Legacy OFDM rate format for bits 7:0
@@ -541,7 +545,7 @@ enum {
 #define RATE_MCS_CTS_REQUIRED_POS  (31)
 #define RATE_MCS_CTS_REQUIRED_MSK  (0x1 << RATE_MCS_CTS_REQUIRED_POS)
 
-/* rate_n_flags bit field version 2
+/* rate_n_flags bit field version 2 and 3
  *
  * The 32-bit value has different layouts in the low 8 bits depending on the
  * format. There are three formats, HT, VHT and legacy (11abg, with subformats
@@ -553,23 +557,25 @@ enum {
  * (0) Legacy CCK (1) Legacy OFDM (2) High-throughput (HT)
  * (3) Very High-throughput (VHT) (4) High-efficiency (HE)
  * (5) Extremely High-throughput (EHT)
+ * (6) Ultra High Reliability (UHR) (v3 rate format only)
  */
 #define RATE_MCS_MOD_TYPE_POS		8
 #define RATE_MCS_MOD_TYPE_MSK		(0x7 << RATE_MCS_MOD_TYPE_POS)
-#define RATE_MCS_CCK_MSK		(0 << RATE_MCS_MOD_TYPE_POS)
-#define RATE_MCS_LEGACY_OFDM_MSK	(1 << RATE_MCS_MOD_TYPE_POS)
-#define RATE_MCS_HT_MSK			(2 << RATE_MCS_MOD_TYPE_POS)
-#define RATE_MCS_VHT_MSK		(3 << RATE_MCS_MOD_TYPE_POS)
-#define RATE_MCS_HE_MSK			(4 << RATE_MCS_MOD_TYPE_POS)
-#define RATE_MCS_EHT_MSK		(5 << RATE_MCS_MOD_TYPE_POS)
+#define RATE_MCS_MOD_TYPE_CCK		(0 << RATE_MCS_MOD_TYPE_POS)
+#define RATE_MCS_MOD_TYPE_LEGACY_OFDM	(1 << RATE_MCS_MOD_TYPE_POS)
+#define RATE_MCS_MOD_TYPE_HT		(2 << RATE_MCS_MOD_TYPE_POS)
+#define RATE_MCS_MOD_TYPE_VHT		(3 << RATE_MCS_MOD_TYPE_POS)
+#define RATE_MCS_MOD_TYPE_HE		(4 << RATE_MCS_MOD_TYPE_POS)
+#define RATE_MCS_MOD_TYPE_EHT		(5 << RATE_MCS_MOD_TYPE_POS)
+#define RATE_MCS_MOD_TYPE_UHR		(6 << RATE_MCS_MOD_TYPE_POS)
 
 /*
  * Legacy CCK rate format for bits 0:3:
  *
- * (0) 0xa - 1 Mbps
- * (1) 0x14 - 2 Mbps
- * (2) 0x37 - 5.5 Mbps
- * (3) 0x6e - 11 nbps
+ * (0) 1 Mbps
+ * (1) 2 Mbps
+ * (2) 5.5 Mbps
+ * (3) 11 Mbps
  *
  * Legacy OFDM rate format for bis 3:0:
  *
@@ -586,15 +592,19 @@ enum {
 #define RATE_LEGACY_RATE_MSK		0x7
 
 /*
- * HT, VHT, HE, EHT rate format for bits 3:0
- * 3-0: MCS
- *
+ * HT, VHT, HE, EHT, UHR rate format
+ * Version 2: (not applicable for UHR)
+ *   3-0: MCS
+ *   4: NSS==2 indicator
+ * Version 3:
+ *   4-0: MCS
+ *   5: NSS==2 indicator
  */
 #define RATE_HT_MCS_CODE_MSK		0x7
-#define RATE_MCS_NSS_POS		4
-#define RATE_MCS_NSS_MSK		(1 << RATE_MCS_NSS_POS)
-#define RATE_MCS_CODE_MSK		0xf
-#define RATE_HT_MCS_INDEX(r)		((((r) & RATE_MCS_NSS_MSK) >> 1) | \
+#define RATE_MCS_NSS_MSK_V2		0x10
+#define RATE_MCS_NSS_MSK		0x20
+#define RATE_MCS_CODE_MSK		0x1f
+#define RATE_HT_MCS_INDEX(r)		((((r) & RATE_MCS_NSS_MSK) >> 2) | \
 					 ((r) & RATE_HT_MCS_CODE_MSK))
 
 /* Bits 7-5: reserved */
@@ -810,11 +820,38 @@ struct iwl_lq_cmd {
 }; /* LINK_QUALITY_CMD_API_S_VER_1 */
 
 u8 iwl_fw_rate_idx_to_plcp(int idx);
-u32 iwl_new_rate_from_v1(u32 rate_v1);
 const struct iwl_rate_mcs_info *iwl_rate_mcs(int idx);
 const char *iwl_rs_pretty_ant(u8 ant);
 const char *iwl_rs_pretty_bw(int bw);
 int rs_pretty_print_rate(char *buf, int bufsz, const u32 rate);
 bool iwl_he_is_sgi(u32 rate_n_flags);
 
+static inline u32 iwl_v3_rate_from_v2_v3(__le32 rate, bool fw_v3)
+{
+	u32 val;
+
+	if (fw_v3)
+		return le32_to_cpu(rate);
+
+	val = le32_to_cpu(rate) & ~RATE_MCS_NSS_MSK_V2;
+	val |= u32_encode_bits(le32_get_bits(rate, RATE_MCS_NSS_MSK_V2),
+			       RATE_MCS_NSS_MSK);
+
+	return val;
+}
+
+static inline __le32 iwl_v3_rate_to_v2_v3(u32 rate, bool fw_v3)
+{
+	__le32 val;
+
+	if (fw_v3)
+		return cpu_to_le32(rate);
+
+	val = cpu_to_le32(rate & ~RATE_MCS_NSS_MSK);
+	val |= le32_encode_bits(u32_get_bits(rate, RATE_MCS_NSS_MSK),
+				RATE_MCS_NSS_MSK_V2);
+
+	return val;
+}
+
 #endif /* __iwl_fw_api_rs_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
index 691c879cb90d..7cf6d6ac7430 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -193,10 +193,11 @@ enum iwl_rx_mpdu_amsdu_info {
 	IWL_RX_MPDU_AMSDU_LAST_SUBFRAME		= 0x80,
 };
 
-#define RX_MPDU_BAND_POS 6
-#define RX_MPDU_BAND_MASK 0xC0
-#define BAND_IN_RX_STATUS(_val) \
-	(((_val) & RX_MPDU_BAND_MASK) >> RX_MPDU_BAND_POS)
+enum iwl_rx_mpdu_mac_phy_band {
+	IWL_RX_MPDU_MAC_PHY_BAND_MAC_MASK	= 0x0f,
+	IWL_RX_MPDU_MAC_PHY_BAND_PHY_MASK	= 0x30,
+	IWL_RX_MPDU_MAC_PHY_BAND_BAND_MASK	= 0xc0,
+};
 
 enum iwl_rx_l3_proto_values {
 	IWL_RX_L3_TYPE_NONE,
@@ -639,7 +640,9 @@ struct iwl_rx_mpdu_desc_v3 {
 	 */
 	__le32 reserved[1];
 } __packed; /* RX_MPDU_RES_START_API_S_VER_3,
-	       RX_MPDU_RES_START_API_S_VER_5 */
+	     * RX_MPDU_RES_START_API_S_VER_5,
+	     * RX_MPDU_RES_START_API_S_VER_6
+	     */
 
 /**
  * struct iwl_rx_mpdu_desc - RX MPDU descriptor
@@ -668,9 +671,10 @@ struct iwl_rx_mpdu_desc {
 	 */
 	__le16 phy_info;
 	/**
-	 * @mac_phy_idx: MAC/PHY index
+	 * @mac_phy_band: MAC ID, PHY ID, band;
+	 *	see &enum iwl_rx_mpdu_mac_phy_band
 	 */
-	u8 mac_phy_idx;
+	u8 mac_phy_band;
 	/* DW4 */
 	union {
 		struct {
@@ -722,8 +726,10 @@ struct iwl_rx_mpdu_desc {
 		struct iwl_rx_mpdu_desc_v3 v3;
 	};
 } __packed; /* RX_MPDU_RES_START_API_S_VER_3,
-	       RX_MPDU_RES_START_API_S_VER_4,
-	       RX_MPDU_RES_START_API_S_VER_5 */
+	     * RX_MPDU_RES_START_API_S_VER_4,
+	     * RX_MPDU_RES_START_API_S_VER_5,
+	     * RX_MPDU_RES_START_API_S_VER_6
+	     */
 
 #define IWL_RX_DESC_SIZE_V1 offsetofend(struct iwl_rx_mpdu_desc, v1)
 
@@ -819,7 +825,7 @@ struct iwl_rx_no_data {
  *	15:8 chain-B, measured at FINA time (FINA_ENERGY), 16:23 channel
  * @on_air_rise_time: GP2 during on air rise
  * @fr_time: frame time
- * @rate: rate/mcs of frame
+ * @rate: rate/mcs of frame, format depends on the notification version
  * @phy_info: &enum iwl_rx_phy_eht_data0 and &enum iwl_rx_phy_info_type
  * @rx_vec: DW-12:9 raw RX vectors from DSP according to modulation type.
  *	for VHT: OFDM_RX_VECTOR_SIGA1_OUT, OFDM_RX_VECTOR_SIGA2_OUT
@@ -835,9 +841,7 @@ struct iwl_rx_no_data_ver_3 {
 	__le32 rate;
 	__le32 phy_info[2];
 	__le32 rx_vec[4];
-} __packed; /* RX_NO_DATA_NTFY_API_S_VER_1,
-	       RX_NO_DATA_NTFY_API_S_VER_2
-	       RX_NO_DATA_NTFY_API_S_VER_3 */
+} __packed; /* RX_NO_DATA_NTFY_API_S_VER_3, _VER_4 */
 
 struct iwl_frame_release {
 	u8 baid;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h b/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h
index 0a9f14fb04be..00713a991879 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018, 2020 - 2021, 2023 - 2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018, 2020-2021, 2023-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -584,6 +584,9 @@ struct iwl_stats_ntfy_per_phy {
 	__le32 last_tx_ch_width_indx;
 } __packed; /* STATISTICS_NTFY_PER_PHY_API_S_VER_1 */
 
+/* unknown channel load (due to not being active on channel) */
+#define IWL_STATS_UNKNOWN_CHANNEL_LOAD	0xffffffff
+
 /**
  * struct iwl_stats_ntfy_per_sta
  *
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h
index cfa6532a3cdd..58d5a6ef633e 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018, 2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018, 2024-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -50,7 +50,7 @@ struct iwl_tdls_channel_switch_timing {
  */
 struct iwl_tdls_channel_switch_frame {
 	__le32 switch_time_offset;
-	struct iwl_tx_cmd tx_cmd;
+	struct iwl_tx_cmd_v6 tx_cmd;
 	u8 data[IWL_TDLS_CH_SW_FRAME_MAX_SIZE];
 } __packed; /* TDLS_STA_CHANNEL_SWITCH_FRAME_API_S_VER_1 */
 
@@ -131,7 +131,7 @@ struct iwl_tdls_config_cmd {
 	struct iwl_tdls_sta_info sta_info[IWL_TDLS_STA_COUNT];
 
 	__le32 pti_req_data_offset;
-	struct iwl_tx_cmd pti_req_tx_cmd;
+	struct iwl_tx_cmd_v6 pti_req_tx_cmd;
 	u8 pti_req_template[];
 } __packed; /* TDLS_CONFIG_CMD_API_S_VER_1 */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
index 0a39e4b6eb62..557832563f89 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
 #ifndef __iwl_fw_api_tx_h__
@@ -151,7 +151,7 @@ enum iwl_tx_cmd_sec_ctrl {
 #define IWL_LOW_RETRY_LIMIT			7
 
 /**
- * enum iwl_tx_offload_assist_flags_pos -  set %iwl_tx_cmd offload_assist values
+ * enum iwl_tx_offload_assist_flags_pos -  set %iwl_tx_cmd_v6 offload_assist values
  * @TX_CMD_OFFLD_IP_HDR: offset to start of IP header (in words)
  *	from mac header end. For normal case it is 4 words for SNAP.
  *	note: tx_cmd, mac header and pad are not counted in the offset.
@@ -181,7 +181,7 @@ enum iwl_tx_offload_assist_flags_pos {
 
 /* TODO: complete documentation for try_cnt and btkill_cnt */
 /**
- * struct iwl_tx_cmd - TX command struct to FW
+ * struct iwl_tx_cmd_v6 - TX command struct to FW
  * ( TX_CMD = 0x1c )
  * @len: in bytes of the payload, see below for details
  * @offload_assist: TX offload configuration
@@ -221,7 +221,7 @@ enum iwl_tx_offload_assist_flags_pos {
  * After the struct fields the MAC header is placed, plus any padding,
  * and then the actial payload.
  */
-struct iwl_tx_cmd {
+struct iwl_tx_cmd_v6 {
 	__le16 len;
 	__le16 offload_assist;
 	__le32 tx_flags;
@@ -258,7 +258,7 @@ struct iwl_dram_sec_info {
 } __packed; /* DRAM_SEC_INFO_API_S_VER_1 */
 
 /**
- * struct iwl_tx_cmd_gen2 - TX command struct to FW for 22000 devices
+ * struct iwl_tx_cmd_v9 - TX command struct to FW for 22000 devices
  * ( TX_CMD = 0x1c )
  * @len: in bytes of the payload, see below for details
  * @offload_assist: TX offload configuration
@@ -268,7 +268,7 @@ struct iwl_dram_sec_info {
  *	cleared. Combination of RATE_MCS_*
  * @hdr: 802.11 header
  */
-struct iwl_tx_cmd_gen2 {
+struct iwl_tx_cmd_v9 {
 	__le16 len;
 	__le16 offload_assist;
 	__le32 flags;
@@ -279,18 +279,18 @@ struct iwl_tx_cmd_gen2 {
 	       TX_CMD_API_S_VER_9 */
 
 /**
- * struct iwl_tx_cmd_gen3 - TX command struct to FW for AX210+ devices
+ * struct iwl_tx_cmd - TX command struct to FW for AX210+ devices
  * ( TX_CMD = 0x1c )
  * @len: in bytes of the payload, see below for details
  * @flags: combination of &enum iwl_tx_cmd_flags
  * @offload_assist: TX offload configuration
  * @dram_info: FW internal DRAM storage
  * @rate_n_flags: rate for *all* Tx attempts, if TX_CMD_FLG_STA_RATE_MSK is
- *	cleared. Combination of RATE_MCS_*
+ *	cleared. Combination of RATE_MCS_*; format depends on version
  * @reserved: reserved
  * @hdr: 802.11 header
  */
-struct iwl_tx_cmd_gen3 {
+struct iwl_tx_cmd {
 	__le16 len;
 	__le16 flags;
 	__le32 offload_assist;
@@ -298,7 +298,9 @@ struct iwl_tx_cmd_gen3 {
 	__le32 rate_n_flags;
 	u8 reserved[8];
 	struct ieee80211_hdr hdr[];
-} __packed; /* TX_CMD_API_S_VER_8, TX_CMD_API_S_VER_10 */
+} __packed; /* TX_CMD_API_S_VER_10,
+	     * TX_CMD_API_S_VER_11
+	     */
 
 /*
  * TX response related data
@@ -549,7 +551,7 @@ struct iwl_tx_resp_v3 {
  * @failure_rts: num of failures due to unsuccessful RTS
  * @failure_frame: num failures due to no ACK (unused for agg)
  * @initial_rate: for non-agg: rate of the successful Tx. For agg: rate of the
- *	Tx of all the batch. RATE_MCS_*
+ *	Tx of all the batch. RATE_MCS_*; format depends on command version
  * @wireless_media_time: for non-agg: RTS + CTS + frame tx attempts time + ACK.
  *	for agg: RTS + CTS + aggregation tx time + block-ack time.
  *	in usec.
@@ -600,8 +602,10 @@ struct iwl_tx_resp {
 	__le16 reserved2;
 	struct agg_tx_status status;
 } __packed; /* TX_RSP_API_S_VER_6,
-	       TX_RSP_API_S_VER_7,
-	       TX_RSP_API_S_VER_8 */
+	     * TX_RSP_API_S_VER_7,
+	     * TX_RSP_API_S_VER_8,
+	     * TX_RSP_API_S_VER_9
+	     */
 
 /**
  * struct iwl_mvm_ba_notif - notifies about reception of BA
@@ -701,7 +705,8 @@ enum iwl_mvm_ba_resp_flags {
  * @rts_retry_cnt: RTS retry count
  * @reserved: reserved (for alignment)
  * @wireless_time: Wireless-media time
- * @tx_rate: the rate the aggregation was sent at
+ * @tx_rate: the rate the aggregation was sent at. Format depends on command
+ *	version.
  * @tfd_cnt: number of TFD-Q elements
  * @ra_tid_cnt: number of RATID-Q elements
  * @tfd: array of TFD queue status updates. See &iwl_compressed_ba_tfd
@@ -730,7 +735,8 @@ struct iwl_compressed_ba_notif {
 		DECLARE_FLEX_ARRAY(struct iwl_compressed_ba_tfd, tfd);
 	};
 } __packed; /* COMPRESSED_BA_RES_API_S_VER_4,
-	       COMPRESSED_BA_RES_API_S_VER_5 */
+	       COMPRESSED_BA_RES_API_S_VER_6,
+	       COMPRESSED_BA_RES_API_S_VER_7 */
 
 /**
  * struct iwl_mac_beacon_cmd_v6 - beacon template command
@@ -742,7 +748,7 @@ struct iwl_compressed_ba_notif {
  * @frame: the template of the beacon frame
  */
 struct iwl_mac_beacon_cmd_v6 {
-	struct iwl_tx_cmd tx;
+	struct iwl_tx_cmd_v6 tx;
 	__le32 template_id;
 	__le32 tim_idx;
 	__le32 tim_size;
@@ -761,7 +767,7 @@ struct iwl_mac_beacon_cmd_v6 {
  * @frame: the template of the beacon frame
  */
 struct iwl_mac_beacon_cmd_v7 {
-	struct iwl_tx_cmd tx;
+	struct iwl_tx_cmd_v6 tx;
 	__le32 template_id;
 	__le32 tim_idx;
 	__le32 tim_size;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 03f639fbf9b6..ea739ebe7cb0 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -187,7 +187,7 @@ static void iwl_fw_dump_rxf(struct iwl_fw_runtime *fwrt,
 		/* Pull RXF2 */
 		iwl_fwrt_dump_rxf(fwrt, dump_data, cfg->rxfifo2_size,
 				  RXF_DIFF_FROM_PREV +
-				  fwrt->trans->trans_cfg->umac_prph_offset, 1);
+				  fwrt->trans->mac_cfg->umac_prph_offset, 1);
 		/* Pull LMAC2 RXF1 */
 		if (fwrt->smem_cfg.num_lmacs > 1)
 			iwl_fwrt_dump_rxf(fwrt, dump_data,
@@ -654,10 +654,10 @@ static void iwl_fw_prph_handler(struct iwl_fw_runtime *fwrt, void *ptr,
 {
 	u32 range_len;
 
-	if (fwrt->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+	if (fwrt->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		range_len = ARRAY_SIZE(iwl_prph_dump_addr_ax210);
 		handler(fwrt, iwl_prph_dump_addr_ax210, range_len, ptr);
-	} else if (fwrt->trans->trans_cfg->device_family >=
+	} else if (fwrt->trans->mac_cfg->device_family >=
 		   IWL_DEVICE_FAMILY_22000) {
 		range_len = ARRAY_SIZE(iwl_prph_dump_addr_22000);
 		handler(fwrt, iwl_prph_dump_addr_22000, range_len, ptr);
@@ -665,7 +665,7 @@ static void iwl_fw_prph_handler(struct iwl_fw_runtime *fwrt, void *ptr,
 		range_len = ARRAY_SIZE(iwl_prph_dump_addr_comm);
 		handler(fwrt, iwl_prph_dump_addr_comm, range_len, ptr);
 
-		if (fwrt->trans->trans_cfg->mq_rx_supported) {
+		if (fwrt->trans->mac_cfg->mq_rx_supported) {
 			range_len = ARRAY_SIZE(iwl_prph_dump_addr_9000);
 			handler(fwrt, iwl_prph_dump_addr_9000, range_len, ptr);
 		}
@@ -809,13 +809,14 @@ iwl_fw_error_dump_file(struct iwl_fw_runtime *fwrt,
 	const struct iwl_fw_dbg_mem_seg_tlv *fw_mem = fwrt->fw->dbg.mem_tlv;
 	struct iwl_fwrt_shared_mem_cfg *mem_cfg = &fwrt->smem_cfg;
 	u32 file_len, fifo_len = 0, prph_len = 0, radio_len = 0;
-	u32 smem_len = fwrt->fw->dbg.n_mem_tlv ? 0 : fwrt->trans->cfg->smem_len;
+	u32 smem_len = fwrt->fw->dbg.n_mem_tlv ? 0 : fwrt->trans->mac_cfg->base->smem_len;
 	u32 sram2_len = fwrt->fw->dbg.n_mem_tlv ?
 				0 : fwrt->trans->cfg->dccm2_len;
 	int i;
 
 	/* SRAM - include stack CCM if driver knows the values for it */
-	if (!fwrt->trans->cfg->dccm_offset || !fwrt->trans->cfg->dccm_len) {
+	if (!fwrt->trans->cfg->dccm_offset ||
+	    !fwrt->trans->cfg->dccm_len) {
 		const struct fw_img *img;
 
 		if (fwrt->cur_fw_img >= IWL_UCODE_TYPE_MAX)
@@ -838,7 +839,7 @@ iwl_fw_error_dump_file(struct iwl_fw_runtime *fwrt,
 			iwl_fw_prph_handler(fwrt, &prph_len,
 					    iwl_fw_get_prph_len);
 
-		if (fwrt->trans->trans_cfg->device_family ==
+		if (fwrt->trans->mac_cfg->device_family ==
 		    IWL_DEVICE_FAMILY_7000 &&
 		    iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_RADIO_REG))
 			radio_len = sizeof(*dump_data) + RADIO_REG_MAX_READ;
@@ -876,7 +877,7 @@ iwl_fw_error_dump_file(struct iwl_fw_runtime *fwrt,
 
 	if (iwl_fw_dbg_is_d3_debug_enabled(fwrt) && fwrt->dump.d3_debug_data) {
 		file_len += sizeof(*dump_data) +
-			fwrt->trans->cfg->d3_debug_data_length * 2;
+			fwrt->trans->mac_cfg->base->d3_debug_data_length * 2;
 	}
 
 	/* If we only want a monitor dump, reset the file length */
@@ -904,13 +905,14 @@ iwl_fw_error_dump_file(struct iwl_fw_runtime *fwrt,
 		dump_data->len = cpu_to_le32(sizeof(*dump_info));
 		dump_info = (void *)dump_data->data;
 		dump_info->hw_type =
-			cpu_to_le32(CSR_HW_REV_TYPE(fwrt->trans->hw_rev));
+			cpu_to_le32(CSR_HW_REV_TYPE(fwrt->trans->info.hw_rev));
 		dump_info->hw_step =
-			cpu_to_le32(fwrt->trans->hw_rev_step);
+			cpu_to_le32(fwrt->trans->info.hw_rev_step);
 		memcpy(dump_info->fw_human_readable, fwrt->fw->human_readable,
 		       sizeof(dump_info->fw_human_readable));
-		strscpy_pad(dump_info->dev_human_readable, fwrt->trans->name,
-			sizeof(dump_info->dev_human_readable));
+		strscpy_pad(dump_info->dev_human_readable,
+			    fwrt->trans->info.name,
+			    sizeof(dump_info->dev_human_readable));
 		strscpy_pad(dump_info->bus_human_readable, fwrt->dev->bus->name,
 			sizeof(dump_info->bus_human_readable));
 		dump_info->num_of_lmacs = fwrt->smem_cfg.num_lmacs;
@@ -996,7 +998,7 @@ iwl_fw_error_dump_file(struct iwl_fw_runtime *fwrt,
 		}
 
 		iwl_fw_dump_mem(fwrt, &dump_data, smem_len,
-				fwrt->trans->cfg->smem_offset,
+				fwrt->trans->mac_cfg->base->smem_offset,
 				IWL_FW_ERROR_DUMP_MEM_SMEM);
 
 		iwl_fw_dump_mem(fwrt, &dump_data, sram2_len,
@@ -1005,8 +1007,8 @@ iwl_fw_error_dump_file(struct iwl_fw_runtime *fwrt,
 	}
 
 	if (iwl_fw_dbg_is_d3_debug_enabled(fwrt) && fwrt->dump.d3_debug_data) {
-		u32 addr = fwrt->trans->cfg->d3_debug_data_base_addr;
-		size_t data_size = fwrt->trans->cfg->d3_debug_data_length;
+		u32 addr = fwrt->trans->mac_cfg->base->d3_debug_data_base_addr;
+		size_t data_size = fwrt->trans->mac_cfg->base->d3_debug_data_length;
 
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_D3_DEBUG_DATA);
 		dump_data->len = cpu_to_le32(data_size * 2);
@@ -1109,7 +1111,7 @@ static int iwl_dump_ini_prph_phy_iter_common(struct iwl_fw_runtime *fwrt,
 	range->internal_base_addr = cpu_to_le32(addr);
 	range->range_data_size = size;
 
-	if (fwrt->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
+	if (fwrt->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		indirect_wr_addr = WMAL_INDRCT_CMD1;
 
 	indirect_wr_addr += le32_to_cpu(offset);
@@ -1266,7 +1268,7 @@ static int iwl_dump_ini_paging_iter(struct iwl_fw_runtime *fwrt,
 	/* all paged index start from 1 to skip CSS section */
 	idx++;
 
-	if (!fwrt->trans->trans_cfg->gen2)
+	if (!fwrt->trans->mac_cfg->gen2)
 		return _iwl_dump_ini_paging_iter(fwrt, range_ptr, range_len, idx);
 
 	range = range_ptr;
@@ -1790,7 +1792,7 @@ iwl_dump_ini_mon_fill_header(struct iwl_fw_runtime *fwrt, u32 alloc_id,
 
 	data->write_ptr = iwl_get_mon_reg(fwrt, alloc_id,
 					  &addrs->write_ptr);
-	if (fwrt->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+	if (fwrt->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		u32 wrt_ptr = le32_to_cpu(data->write_ptr);
 
 		data->write_ptr = cpu_to_le32(wrt_ptr >> 2);
@@ -1817,7 +1819,7 @@ iwl_dump_ini_mon_dram_fill_header(struct iwl_fw_runtime *fwrt,
 	u32 alloc_id = le32_to_cpu(reg->dram_alloc_id);
 
 	return iwl_dump_ini_mon_fill_header(fwrt, alloc_id, mon_dump,
-					    &fwrt->trans->cfg->mon_dram_regs);
+					    &fwrt->trans->mac_cfg->base->mon_dram_regs);
 }
 
 static void *
@@ -1830,7 +1832,7 @@ iwl_dump_ini_mon_smem_fill_header(struct iwl_fw_runtime *fwrt,
 	u32 alloc_id = le32_to_cpu(reg->internal_buffer.alloc_id);
 
 	return iwl_dump_ini_mon_fill_header(fwrt, alloc_id, mon_dump,
-					    &fwrt->trans->cfg->mon_smem_regs);
+					    &fwrt->trans->mac_cfg->base->mon_smem_regs);
 }
 
 static void *
@@ -1844,7 +1846,7 @@ iwl_dump_ini_mon_dbgi_fill_header(struct iwl_fw_runtime *fwrt,
 					    /* no offset calculation later */
 					    IWL_FW_INI_ALLOCATION_ID_DBGC1,
 					    mon_dump,
-					    &fwrt->trans->cfg->mon_dbgi_regs);
+					    &fwrt->trans->mac_cfg->base->mon_dbgi_regs);
 }
 
 static void *
@@ -1909,7 +1911,7 @@ iwl_dump_ini_mem_block_ranges(struct iwl_fw_runtime *fwrt,
 static u32 iwl_dump_ini_paging_ranges(struct iwl_fw_runtime *fwrt,
 				      struct iwl_dump_ini_region_data *reg_data)
 {
-	if (fwrt->trans->trans_cfg->gen2) {
+	if (fwrt->trans->mac_cfg->gen2) {
 		if (fwrt->trans->init_dram.paging_cnt)
 			return fwrt->trans->init_dram.paging_cnt - 1;
 		else
@@ -2021,7 +2023,7 @@ iwl_dump_ini_paging_get_size(struct iwl_fw_runtime *fwrt,
 	/* start from 1 to skip CSS section */
 	for (i = 1; i <= iwl_dump_ini_paging_ranges(fwrt, reg_data); i++) {
 		size += range_header_len;
-		if (fwrt->trans->trans_cfg->gen2)
+		if (fwrt->trans->mac_cfg->gen2)
 			size += fwrt->trans->init_dram.paging[i].size;
 		else
 			size += fwrt->fw_paging_db[i].fw_paging_size;
@@ -2375,7 +2377,7 @@ static u32 iwl_dump_ini_info(struct iwl_fw_runtime *fwrt,
 	struct iwl_fw_ini_dump_cfg_name *cfg_name;
 	u32 size = sizeof(*tlv) + sizeof(*dump);
 	u32 num_of_cfg_names = 0;
-	u32 hw_type;
+	u32 hw_type, is_cdb, is_jacket;
 
 	list_for_each_entry(node, &fwrt->trans->dbg.debug_info_tlv_list, list) {
 		size += sizeof(*cfg_name);
@@ -2403,33 +2405,24 @@ static u32 iwl_dump_ini_info(struct iwl_fw_runtime *fwrt,
 	dump->ver_type = cpu_to_le32(fwrt->dump.fw_ver.type);
 	dump->ver_subtype = cpu_to_le32(fwrt->dump.fw_ver.subtype);
 
-	dump->hw_step = cpu_to_le32(fwrt->trans->hw_rev_step);
+	dump->hw_step = cpu_to_le32(fwrt->trans->info.hw_rev_step);
 
-	/*
-	 * Several HWs all have type == 0x42, so we'll override this value
-	 * according to the detected HW
-	 */
-	hw_type = CSR_HW_REV_TYPE(fwrt->trans->hw_rev);
-	if (hw_type == IWL_AX210_HW_TYPE) {
-		u32 prph_val = iwl_read_umac_prph(fwrt->trans, WFPM_OTP_CFG1_ADDR);
-		u32 is_jacket = !!(prph_val & WFPM_OTP_CFG1_IS_JACKET_BIT);
-		u32 is_cdb = !!(prph_val & WFPM_OTP_CFG1_IS_CDB_BIT);
-		u32 masked_bits = is_jacket | (is_cdb << 1);
+	hw_type = CSR_HW_REV_TYPE(fwrt->trans->info.hw_rev);
+
+	is_cdb = CSR_HW_RFID_IS_CDB(fwrt->trans->info.hw_rf_id);
+	is_jacket = !!(iwl_read_umac_prph(fwrt->trans, WFPM_OTP_CFG1_ADDR) &
+				WFPM_OTP_CFG1_IS_JACKET_BIT);
+
+	/* Use bits 12 and 13 to indicate jacket/CDB, respectively */
+	hw_type |= (is_jacket | (is_cdb << 1)) << IWL_JACKET_CDB_SHIFT;
 
-		/*
-		 * The HW type depends on certain bits in this case, so add
-		 * these bits to the HW type. We won't have collisions since we
-		 * add these bits after the highest possible bit in the mask.
-		 */
-		hw_type |= masked_bits << IWL_AX210_HW_TYPE_ADDITION_SHIFT;
-	}
 	dump->hw_type = cpu_to_le32(hw_type);
 
 	dump->rf_id_flavor =
-		cpu_to_le32(CSR_HW_RFID_FLAVOR(fwrt->trans->hw_rf_id));
-	dump->rf_id_dash = cpu_to_le32(CSR_HW_RFID_DASH(fwrt->trans->hw_rf_id));
-	dump->rf_id_step = cpu_to_le32(CSR_HW_RFID_STEP(fwrt->trans->hw_rf_id));
-	dump->rf_id_type = cpu_to_le32(CSR_HW_RFID_TYPE(fwrt->trans->hw_rf_id));
+		cpu_to_le32(CSR_HW_RFID_FLAVOR(fwrt->trans->info.hw_rf_id));
+	dump->rf_id_dash = cpu_to_le32(CSR_HW_RFID_DASH(fwrt->trans->info.hw_rf_id));
+	dump->rf_id_step = cpu_to_le32(CSR_HW_RFID_STEP(fwrt->trans->info.hw_rf_id));
+	dump->rf_id_type = cpu_to_le32(CSR_HW_RFID_TYPE(fwrt->trans->info.hw_rf_id));
 
 	dump->lmac_major = cpu_to_le32(fwrt->dump.fw_ver.lmac_major);
 	dump->lmac_minor = cpu_to_le32(fwrt->dump.fw_ver.lmac_minor);
@@ -2624,6 +2617,12 @@ enum iwl_dump_ini_region_selector {
 	IWL_INI_DUMP_LATE_REGIONS,
 };
 
+static bool iwl_dump_due_to_error(enum iwl_fw_ini_time_point tp_id)
+{
+	return tp_id == IWL_FW_INI_TIME_POINT_FW_ASSERT ||
+	       tp_id == IWL_FW_INI_TIME_POINT_FW_HW_ERROR;
+}
+
 static u32
 iwl_dump_ini_dump_regions(struct iwl_fw_runtime *fwrt,
 			  struct iwl_fwrt_dump_data *dump_data,
@@ -2689,8 +2688,7 @@ iwl_dump_ini_dump_regions(struct iwl_fw_runtime *fwrt,
 		 * debug data which also need to be collected.
 		 */
 		if (reg_type == IWL_FW_INI_REGION_DRAM_IMR) {
-			if (tp_id == IWL_FW_INI_TIME_POINT_FW_ASSERT ||
-			    tp_id == IWL_FW_INI_TIME_POINT_FW_HW_ERROR)
+			if (iwl_dump_due_to_error(tp_id))
 				imr_reg_data->reg_tlv =
 					fwrt->trans->dbg.active_regions[i];
 			else
@@ -2726,8 +2724,8 @@ static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
 	BUILD_BUG_ON((sizeof(trigger->regions_mask) * BITS_PER_BYTE) <
 		     ARRAY_SIZE(fwrt->trans->dbg.active_regions));
 
-	if (trigger->time_point &
-			cpu_to_le32(IWL_FW_INI_APPLY_POLICY_RESET_HANDSHAKE)) {
+	if (trigger->apply_policy &
+			cpu_to_le32(IWL_FW_INI_APPLY_POLICY_SPLIT_DUMP_RESET)) {
 		size += iwl_dump_ini_dump_regions(fwrt, dump_data, list, tp_id,
 						  regions_mask, &imr_reg_data,
 						  IWL_INI_DUMP_EARLY_REGIONS);
@@ -2736,6 +2734,10 @@ static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
 						  regions_mask, &imr_reg_data,
 						  IWL_INI_DUMP_LATE_REGIONS);
 	} else {
+		if (fw_has_capa(&fwrt->fw->ucode_capa,
+				IWL_UCODE_TLV_CAPA_RESET_DURING_ASSERT) &&
+		    iwl_dump_due_to_error(tp_id))
+			iwl_trans_pcie_fw_reset_handshake(fwrt->trans);
 		size += iwl_dump_ini_dump_regions(fwrt, dump_data, list, tp_id,
 						  regions_mask, &imr_reg_data,
 						  IWL_INI_DUMP_ALL_REGIONS);
@@ -3282,13 +3284,13 @@ void iwl_fw_error_dump_wk(struct work_struct *work)
 
 void iwl_fw_dbg_read_d3_debug_data(struct iwl_fw_runtime *fwrt)
 {
-	const struct iwl_cfg *cfg = fwrt->trans->cfg;
+	const struct iwl_mac_cfg *mac_cfg = fwrt->trans->mac_cfg;
 
 	if (!iwl_fw_dbg_is_d3_debug_enabled(fwrt))
 		return;
 
 	if (!fwrt->dump.d3_debug_data) {
-		fwrt->dump.d3_debug_data = kmalloc(cfg->d3_debug_data_length,
+		fwrt->dump.d3_debug_data = kmalloc(mac_cfg->base->d3_debug_data_length,
 						   GFP_KERNEL);
 		if (!fwrt->dump.d3_debug_data) {
 			IWL_ERR(fwrt,
@@ -3298,15 +3300,15 @@ void iwl_fw_dbg_read_d3_debug_data(struct iwl_fw_runtime *fwrt)
 	}
 
 	/* if the buffer holds previous debug data it is overwritten */
-	iwl_trans_read_mem_bytes(fwrt->trans, cfg->d3_debug_data_base_addr,
+	iwl_trans_read_mem_bytes(fwrt->trans, mac_cfg->base->d3_debug_data_base_addr,
 				 fwrt->dump.d3_debug_data,
-				 cfg->d3_debug_data_length);
+				 mac_cfg->base->d3_debug_data_length);
 
 	if (fwrt->sanitize_ops && fwrt->sanitize_ops->frob_mem)
 		fwrt->sanitize_ops->frob_mem(fwrt->sanitize_ctx,
-					     cfg->d3_debug_data_base_addr,
+					     mac_cfg->base->d3_debug_data_base_addr,
 					     fwrt->dump.d3_debug_data,
-					     cfg->d3_debug_data_length);
+					     mac_cfg->base->d3_debug_data_length);
 }
 IWL_EXPORT_SYMBOL(iwl_fw_dbg_read_d3_debug_data);
 
@@ -3341,7 +3343,7 @@ static int iwl_fw_dbg_suspend_resume_hcmd(struct iwl_trans *trans, bool suspend)
 static void iwl_fw_dbg_stop_recording(struct iwl_trans *trans,
 				      struct iwl_fw_dbg_params *params)
 {
-	if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_7000) {
+	if (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_7000) {
 		iwl_set_bits_prph(trans, MON_BUFF_SAMPLE_CTL, 0x100);
 		return;
 	}
@@ -3365,7 +3367,7 @@ static int iwl_fw_dbg_restart_recording(struct iwl_trans *trans,
 	if (!params)
 		return -EIO;
 
-	if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_7000) {
+	if (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_7000) {
 		iwl_clear_bits_prph(trans, MON_BUFF_SAMPLE_CTL, 0x100);
 		iwl_clear_bits_prph(trans, MON_BUFF_SAMPLE_CTL, 0x1);
 		iwl_set_bits_prph(trans, MON_BUFF_SAMPLE_CTL, 0x1);
@@ -3467,7 +3469,7 @@ void iwl_fw_disable_dbg_asserts(struct iwl_fw_runtime *fwrt)
 				  GENMASK(31, IWL_FW_DBG_DOMAIN_POS + 1));
 
 	/* supported starting from 9000 devices */
-	if (fwrt->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_9000)
+	if (fwrt->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_9000)
 		return;
 
 	if (fwrt->trans->dbg.yoyo_bin_loaded || (preset && preset != 1))
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index 35e30e5db462..8034c9ecba69 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2018-2019, 2021-2024 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2019, 2021-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -201,7 +201,7 @@ static inline bool iwl_fw_dbg_is_d3_debug_enabled(struct iwl_fw_runtime *fwrt)
 {
 	return fw_has_capa(&fwrt->fw->ucode_capa,
 			   IWL_UCODE_TLV_CAPA_D3_DEBUG) &&
-		fwrt->trans->cfg->d3_debug_data_length && fwrt->ops &&
+		fwrt->trans->mac_cfg->base->d3_debug_data_length && fwrt->ops &&
 		fwrt->ops->d3_debug_enable &&
 		fwrt->ops->d3_debug_enable(fwrt->ops_ctx) &&
 		iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_D3_DEBUG_DATA);
@@ -210,7 +210,7 @@ static inline bool iwl_fw_dbg_is_d3_debug_enabled(struct iwl_fw_runtime *fwrt)
 static inline bool iwl_fw_dbg_is_paging_enabled(struct iwl_fw_runtime *fwrt)
 {
 	return iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_PAGING) &&
-		!fwrt->trans->trans_cfg->gen2 &&
+		!fwrt->trans->mac_cfg->gen2 &&
 		fwrt->cur_fw_img < IWL_UCODE_TYPE_MAX &&
 		fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size &&
 		fwrt->fw_paging_db[0].fw_paging_block;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c
index f0c813d675f4..c70f2a20f7d5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c
@@ -311,7 +311,7 @@ static ssize_t iwl_dbgfs_fw_ver_read(struct iwl_fw_runtime *fwrt,
 	pos += scnprintf(pos, endpos - pos, "FW: %s\n",
 			 fwrt->fw->human_readable);
 	pos += scnprintf(pos, endpos - pos, "Device: %s\n",
-			 fwrt->trans->name);
+			 fwrt->trans->info.name);
 	pos += scnprintf(pos, endpos - pos, "Bus: %s\n",
 			 fwrt->dev->bus->name);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dump.c b/drivers/net/wireless/intel/iwlwifi/fw/dump.c
index c7b261c8ec96..3ec42a4ea801 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dump.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dump.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -417,10 +417,10 @@ static void iwl_fwrt_dump_iml_error_log(struct iwl_fw_runtime *fwrt)
 	struct iwl_trans *trans = fwrt->trans;
 	u32 error, data1;
 
-	if (fwrt->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
+	if (fwrt->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
 		error = UMAG_SB_CPU_2_STATUS;
 		data1 = UMAG_SB_CPU_1_STATUS;
-	} else if (fwrt->trans->trans_cfg->device_family >=
+	} else if (fwrt->trans->mac_cfg->device_family >=
 		   IWL_DEVICE_FAMILY_8000) {
 		error = SB_CPU_2_STATUS;
 		data1 = SB_CPU_1_STATUS;
@@ -439,7 +439,7 @@ static void iwl_fwrt_dump_iml_error_log(struct iwl_fw_runtime *fwrt)
 	IWL_ERR(fwrt, "0x%08X | IML/ROM data1\n",
 		iwl_read_umac_prph(trans, data1));
 
-	if (fwrt->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000)
+	if (fwrt->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_22000)
 		IWL_ERR(fwrt, "0x%08X | IML/ROM WFPM_AUTH_KEY_0\n",
 			iwl_read_umac_prph(trans, SB_MODIFY_CFG_FLAG));
 }
@@ -508,7 +508,7 @@ void iwl_fwrt_dump_error_logs(struct iwl_fw_runtime *fwrt)
 		iwl_fwrt_dump_rcm_error_log(fwrt, 1);
 	iwl_fwrt_dump_iml_error_log(fwrt);
 	iwl_fwrt_dump_fseq_regs(fwrt);
-	if (fwrt->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
+	if (fwrt->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
 		pc_data = fwrt->trans->dbg.pc_data;
 
 		if (!iwl_trans_grab_nic_access(fwrt->trans))
@@ -522,7 +522,7 @@ void iwl_fwrt_dump_error_logs(struct iwl_fw_runtime *fwrt)
 		iwl_trans_release_nic_access(fwrt->trans);
 	}
 
-	if (fwrt->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+	if (fwrt->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
 		u32 scratch = iwl_read32(fwrt->trans, CSR_FUNC_SCRATCH);
 
 		IWL_ERR(fwrt, "Function Scratch status:\n");
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
index 3af275133da0..cf41021d59ad 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2014, 2018-2025 Intel Corporation
  * Copyright (C) 2014-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -372,10 +372,7 @@ struct iwl_fw_ini_dump_cfg_name {
 	u8 cfg_name[IWL_FW_INI_MAX_CFG_NAME];
 } __packed;
 
-/* AX210's HW type */
-#define IWL_AX210_HW_TYPE 0x42
-/* How many bits to roll when adding to the HW type of AX210 HW */
-#define IWL_AX210_HW_TYPE_ADDITION_SHIFT 12
+#define IWL_JACKET_CDB_SHIFT 12
 
 /* struct iwl_fw_ini_dump_info - ini dump information
  * @version: dump version
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index 9860903ecd3f..5a1ec880ed72 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -102,6 +102,7 @@ enum iwl_ucode_tlv_type {
 	IWL_UCODE_TLV_SEC_TABLE_ADDR		= 66,
 	IWL_UCODE_TLV_D3_KEK_KCK_ADDR		= 67,
 	IWL_UCODE_TLV_CURRENT_PC		= 68,
+	IWL_UCODE_TLV_FSEQ_BIN_VERSION		= 72,
 
 	IWL_UCODE_TLV_FW_NUM_STATIONS		= IWL_UCODE_TLV_CONST_BASE + 0,
 	IWL_UCODE_TLV_FW_NUM_LINKS		= IWL_UCODE_TLV_CONST_BASE + 1,
@@ -402,6 +403,7 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t;
  * @IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_5G9_FOR_CA: supports (de)activating 5G9
  *	for CA from BIOS.
  * @IWL_UCODE_TLV_CAPA_UHB_CANADA_TAS_SUPPORT: supports %TAS_UHB_ALLOWED_CANADA
+ * @IWL_UCODE_TLV_CAPA_EXT_FSEQ_IMAGE_SUPPORT: external FSEQ image support
  *
  * @NUM_IWL_UCODE_TLV_CAPA: number of bits used
  */
@@ -504,6 +506,14 @@ enum iwl_ucode_tlv_capa {
 	IWL_UCODE_TLV_CAPA_MONITOR_PASSIVE_CHANS	= (__force iwl_ucode_tlv_capa_t)122,
 	IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_5G9_FOR_CA	= (__force iwl_ucode_tlv_capa_t)123,
 	IWL_UCODE_TLV_CAPA_UHB_CANADA_TAS_SUPPORT	= (__force iwl_ucode_tlv_capa_t)124,
+	IWL_UCODE_TLV_CAPA_EXT_FSEQ_IMAGE_SUPPORT	= (__force iwl_ucode_tlv_capa_t)125,
+
+	/* set 4 */
+	/**
+	 * @IWL_UCODE_TLV_CAPA_RESET_DURING_ASSERT: FW reset handshake is needed
+	 *	during assert handling even if the dump isn't split
+	 */
+	IWL_UCODE_TLV_CAPA_RESET_DURING_ASSERT		= (__force iwl_ucode_tlv_capa_t)(4 * 32 +  0),
 	NUM_IWL_UCODE_TLV_CAPA
 /*
  * This construction make both sparse (which cannot increment the previous
@@ -994,6 +1004,10 @@ struct iwl_fw_dump_exclude {
 	__le32 addr, size;
 };
 
+struct iwl_fw_fseq_bin_version {
+	__le32 major, minor;
+}; /* FW_TLV_FSEQ_BIN_VERSION_S */
+
 static inline size_t _iwl_tlv_array_len(const struct iwl_ucode_tlv *tlv,
 					size_t fixed_size, size_t var_size)
 {
@@ -1011,4 +1025,18 @@ static inline size_t _iwl_tlv_array_len(const struct iwl_ucode_tlv *tlv,
 
 #define iwl_tlv_array_len_with_size(_tlv_ptr, _struct_ptr, _size)	\
 	_iwl_tlv_array_len((_tlv_ptr), sizeof(*(_struct_ptr)), _size)
+
+/* external FSEQ file */
+#define IWL_FSEQ_FILE	"intel/fseq-%04x-%04x"
+#define IWL_FSEQ_MAGIC	"INTEL-CNV-FSEQ\n\0"
+
+struct iwl_fseq_file {
+	char magic[16];
+	char version[16];
+	__le32 bt_len;
+	__le32 wifi_len;
+	u8 reserved[8];
+	u8 data[];
+} __packed;
+
 #endif  /* __iwl_fw_file_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/init.c b/drivers/net/wireless/intel/iwlwifi/fw/init.c
index de87e0e3e072..d1d8058ad29f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/init.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/init.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2019-2021, 2024 Intel Corporation
+ * Copyright (C) 2019-2021, 2024-2025 Intel Corporation
  */
 #include "iwl-drv.h"
 #include "runtime.h"
@@ -72,7 +72,7 @@ int iwl_set_soc_latency(struct iwl_fw_runtime *fwrt)
 	 * values in VER_1, this is backwards-compatible with VER_2,
 	 * as long as we don't set any other bits.
 	 */
-	if (!fwrt->trans->trans_cfg->integrated)
+	if (!fwrt->trans->mac_cfg->integrated)
 		cmd.flags = cpu_to_le32(SOC_CONFIG_CMD_FLAGS_DISCRETE);
 
 	BUILD_BUG_ON(IWL_CFG_TRANS_LTR_DELAY_NONE !=
@@ -84,17 +84,17 @@ int iwl_set_soc_latency(struct iwl_fw_runtime *fwrt)
 	BUILD_BUG_ON(IWL_CFG_TRANS_LTR_DELAY_1820US !=
 		     SOC_FLAGS_LTR_APPLY_DELAY_1820);
 
-	if (fwrt->trans->trans_cfg->ltr_delay != IWL_CFG_TRANS_LTR_DELAY_NONE &&
-	    !WARN_ON(!fwrt->trans->trans_cfg->integrated))
-		cmd.flags |= le32_encode_bits(fwrt->trans->trans_cfg->ltr_delay,
+	if (fwrt->trans->mac_cfg->ltr_delay != IWL_CFG_TRANS_LTR_DELAY_NONE &&
+	    !WARN_ON(!fwrt->trans->mac_cfg->integrated))
+		cmd.flags |= le32_encode_bits(fwrt->trans->mac_cfg->ltr_delay,
 					      SOC_FLAGS_LTR_APPLY_DELAY_MASK);
 
 	if (iwl_fw_lookup_cmd_ver(fwrt->fw, SCAN_REQ_UMAC,
 				  IWL_FW_CMD_VER_UNKNOWN) >= 2 &&
-	    fwrt->trans->trans_cfg->low_latency_xtal)
+	    fwrt->trans->mac_cfg->low_latency_xtal)
 		cmd.flags |= cpu_to_le32(SOC_CONFIG_CMD_FLAGS_LOW_LATENCY);
 
-	cmd.latency = cpu_to_le32(fwrt->trans->trans_cfg->xtal_latency);
+	cmd.latency = cpu_to_le32(fwrt->trans->mac_cfg->xtal_latency);
 
 	ret = iwl_trans_send_cmd(fwrt->trans, &hcmd);
 	if (ret)
@@ -116,14 +116,14 @@ int iwl_configure_rxq(struct iwl_fw_runtime *fwrt)
 	 * The default queue is configured via context info, so if we
 	 * have a single queue, there's nothing to do here.
 	 */
-	if (fwrt->trans->num_rx_queues == 1)
+	if (fwrt->trans->info.num_rxqs == 1)
 		return 0;
 
-	if (fwrt->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_22000)
+	if (fwrt->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_22000)
 		return 0;
 
 	/* skip the default queue */
-	num_queues = fwrt->trans->num_rx_queues - 1;
+	num_queues = fwrt->trans->info.num_rxqs - 1;
 
 	size = struct_size(cmd, data, num_queues);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/paging.c b/drivers/net/wireless/intel/iwlwifi/fw/paging.c
index a7b7cae874a2..826409f6f710 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/paging.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/paging.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2019, 2021 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2019, 2021, 2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -267,7 +267,7 @@ int iwl_init_paging(struct iwl_fw_runtime *fwrt, enum iwl_ucode_type type)
 	const struct fw_img *fw = &fwrt->fw->img[type];
 	int ret;
 
-	if (fwrt->trans->trans_cfg->gen2)
+	if (fwrt->trans->mac_cfg->gen2)
 		return 0;
 
 	/*
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c
index 1195e708caa9..4f3c2f7f4f5b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright(c) 2020-2024 Intel Corporation
+ * Copyright(c) 2020-2025 Intel Corporation
  */
 
 #include "iwl-drv.h"
@@ -96,8 +96,8 @@ static int iwl_pnvm_handle_section(struct iwl_trans *trans, const u8 *data,
 				     "Got IWL_UCODE_TLV_HW_TYPE mac_type 0x%0x rf_id 0x%0x\n",
 				     mac_type, rf_id);
 
-			if (mac_type == CSR_HW_REV_TYPE(trans->hw_rev) &&
-			    rf_id == CSR_HW_RFID_TYPE(trans->hw_rf_id))
+			if (mac_type == CSR_HW_REV_TYPE(trans->info.hw_rev) &&
+			    rf_id == CSR_HW_RFID_TYPE(trans->info.hw_rf_id))
 				hw_match = true;
 			break;
 		case IWL_UCODE_TLV_SEC_RT: {
@@ -152,8 +152,8 @@ done:
 	if (!hw_match) {
 		IWL_DEBUG_FW(trans,
 			     "HW mismatch, skipping PNVM section (need mac_type 0x%x rf_id 0x%x)\n",
-			     CSR_HW_REV_TYPE(trans->hw_rev),
-			     CSR_HW_RFID_TYPE(trans->hw_rf_id));
+			     CSR_HW_REV_TYPE(trans->info.hw_rev),
+			     CSR_HW_RFID_TYPE(trans->info.hw_rf_id));
 		return -ENOENT;
 	}
 
@@ -167,7 +167,8 @@ done:
 
 static int iwl_pnvm_parse(struct iwl_trans *trans, const u8 *data,
 			  size_t len,
-			  struct iwl_pnvm_image *pnvm_data)
+			  struct iwl_pnvm_image *pnvm_data,
+			  __le32 sku_id[3])
 {
 	const struct iwl_ucode_tlv *tlv;
 
@@ -190,23 +191,23 @@ static int iwl_pnvm_parse(struct iwl_trans *trans, const u8 *data,
 		}
 
 		if (tlv_type == IWL_UCODE_TLV_PNVM_SKU) {
-			const struct iwl_sku_id *sku_id =
+			const struct iwl_sku_id *tlv_sku_id =
 				(const void *)(data + sizeof(*tlv));
 
 			IWL_DEBUG_FW(trans,
 				     "Got IWL_UCODE_TLV_PNVM_SKU len %d\n",
 				     tlv_len);
 			IWL_DEBUG_FW(trans, "sku_id 0x%0x 0x%0x 0x%0x\n",
-				     le32_to_cpu(sku_id->data[0]),
-				     le32_to_cpu(sku_id->data[1]),
-				     le32_to_cpu(sku_id->data[2]));
+				     le32_to_cpu(tlv_sku_id->data[0]),
+				     le32_to_cpu(tlv_sku_id->data[1]),
+				     le32_to_cpu(tlv_sku_id->data[2]));
 
 			data += sizeof(*tlv) + ALIGN(tlv_len, 4);
 			len -= ALIGN(tlv_len, 4);
 
 			trans->reduced_cap_sku = false;
-			rf_type = CSR_HW_RFID_TYPE(trans->hw_rf_id);
-			if ((trans->sku_id[0] & IWL_PNVM_REDUCED_CAP_BIT) &&
+			rf_type = CSR_HW_RFID_TYPE(trans->info.hw_rf_id);
+			if ((sku_id[0] & cpu_to_le32(IWL_PNVM_REDUCED_CAP_BIT)) &&
 			    rf_type == IWL_CFG_RF_TYPE_FM)
 				trans->reduced_cap_sku = true;
 
@@ -214,9 +215,9 @@ static int iwl_pnvm_parse(struct iwl_trans *trans, const u8 *data,
 				     "Reduced SKU device %d\n",
 				     trans->reduced_cap_sku);
 
-			if (trans->sku_id[0] == le32_to_cpu(sku_id->data[0]) &&
-			    trans->sku_id[1] == le32_to_cpu(sku_id->data[1]) &&
-			    trans->sku_id[2] == le32_to_cpu(sku_id->data[2])) {
+			if (sku_id[0] == tlv_sku_id->data[0] &&
+			    sku_id[1] == tlv_sku_id->data[1] &&
+			    sku_id[2] == tlv_sku_id->data[2]) {
 				int ret;
 
 				ret = iwl_pnvm_handle_section(trans, data, len,
@@ -263,13 +264,14 @@ static int iwl_pnvm_get_from_fs(struct iwl_trans *trans, u8 **data, size_t *len)
 	return 0;
 }
 
-static u8 *iwl_get_pnvm_image(struct iwl_trans *trans_p, size_t *len)
+static u8 *iwl_get_pnvm_image(struct iwl_trans *trans_p, size_t *len,
+			      __le32 sku_id[3])
 {
 	struct pnvm_sku_package *package;
 	u8 *image = NULL;
 
 	/* Get PNVM from BIOS for non-Intel SKU */
-	if (trans_p->sku_id[2]) {
+	if (sku_id[2]) {
 		package = iwl_uefi_get_pnvm(trans_p, len);
 		if (!IS_ERR_OR_NULL(package)) {
 			if (*len >= sizeof(*package)) {
@@ -294,8 +296,10 @@ static u8 *iwl_get_pnvm_image(struct iwl_trans *trans_p, size_t *len)
 	return image;
 }
 
-static void iwl_pnvm_load_pnvm_to_trans(struct iwl_trans *trans,
-					const struct iwl_ucode_capabilities *capa)
+static void
+iwl_pnvm_load_pnvm_to_trans(struct iwl_trans *trans,
+			    const struct iwl_ucode_capabilities *capa,
+			    __le32 sku_id[3])
 {
 	struct iwl_pnvm_image *pnvm_data = NULL;
 	u8 *data = NULL;
@@ -309,7 +313,7 @@ static void iwl_pnvm_load_pnvm_to_trans(struct iwl_trans *trans,
 	if (trans->pnvm_loaded)
 		goto set;
 
-	data = iwl_get_pnvm_image(trans, &length);
+	data = iwl_get_pnvm_image(trans, &length, sku_id);
 	if (!data) {
 		trans->fail_to_parse_pnvm_image = true;
 		return;
@@ -319,7 +323,7 @@ static void iwl_pnvm_load_pnvm_to_trans(struct iwl_trans *trans,
 	if (!pnvm_data)
 		goto free;
 
-	ret = iwl_pnvm_parse(trans, data, length, pnvm_data);
+	ret = iwl_pnvm_parse(trans, data, length, pnvm_data, sku_id);
 	if (ret) {
 		trans->fail_to_parse_pnvm_image = true;
 		goto free;
@@ -339,7 +343,8 @@ free:
 
 static void
 iwl_pnvm_load_reduce_power_to_trans(struct iwl_trans *trans,
-				    const struct iwl_ucode_capabilities *capa)
+				    const struct iwl_ucode_capabilities *capa,
+				    __le32 sku_id[3])
 {
 	struct iwl_pnvm_image *pnvm_data = NULL;
 	u8 *data = NULL;
@@ -362,7 +367,8 @@ iwl_pnvm_load_reduce_power_to_trans(struct iwl_trans *trans,
 	if (!pnvm_data)
 		goto free;
 
-	ret = iwl_uefi_reduce_power_parse(trans, data, length, pnvm_data);
+	ret = iwl_uefi_reduce_power_parse(trans, data, length, pnvm_data,
+					  sku_id);
 	if (ret) {
 		trans->failed_to_load_reduce_power_image = true;
 		goto free;
@@ -386,18 +392,19 @@ free:
 
 int iwl_pnvm_load(struct iwl_trans *trans,
 		  struct iwl_notif_wait_data *notif_wait,
-		  const struct iwl_ucode_capabilities *capa)
+		  const struct iwl_ucode_capabilities *capa,
+		  __le32 sku_id[3])
 {
 	struct iwl_notification_wait pnvm_wait;
 	static const u16 ntf_cmds[] = { WIDE_ID(REGULATORY_AND_NVM_GROUP,
 						PNVM_INIT_COMPLETE_NTFY) };
 
 	/* if the SKU_ID is empty, there's nothing to do */
-	if (!trans->sku_id[0] && !trans->sku_id[1] && !trans->sku_id[2])
+	if (!sku_id[0] && !sku_id[1] && !sku_id[2])
 		return 0;
 
-	iwl_pnvm_load_pnvm_to_trans(trans, capa);
-	iwl_pnvm_load_reduce_power_to_trans(trans, capa);
+	iwl_pnvm_load_pnvm_to_trans(trans, capa, sku_id);
+	iwl_pnvm_load_reduce_power_to_trans(trans, capa, sku_id);
 
 	iwl_init_notification_wait(notif_wait, &pnvm_wait,
 				   ntf_cmds, ARRAY_SIZE(ntf_cmds),
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h
index 1bac3466154c..9540926e8a0f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright(c) 2020-2023 Intel Corporation
+ * Copyright(c) 2020-2023, 2025 Intel Corporation
  */
 #ifndef __IWL_PNVM_H__
 #define __IWL_PNVM_H__
@@ -14,7 +14,8 @@
 
 int iwl_pnvm_load(struct iwl_trans *trans,
 		  struct iwl_notif_wait_data *notif_wait,
-		  const struct iwl_ucode_capabilities *capa);
+		  const struct iwl_ucode_capabilities *capa,
+		  __le32 sku_id[3]);
 
 static inline
 void iwl_pnvm_get_fs_name(struct iwl_trans *trans,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
index 6adcfa6e214a..74b90bd92c48 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2023 Intel Corporation
+ * Copyright (C) 2023, 2025 Intel Corporation
  */
 #include <linux/dmi.h>
 #include "iwl-drv.h"
@@ -34,6 +34,7 @@ IWL_BIOS_TABLE_LOADER(wrds_table);
 IWL_BIOS_TABLE_LOADER(ewrd_table);
 IWL_BIOS_TABLE_LOADER(wgds_table);
 IWL_BIOS_TABLE_LOADER(ppag_table);
+IWL_BIOS_TABLE_LOADER(phy_filters);
 IWL_BIOS_TABLE_LOADER_DATA(tas_table, struct iwl_tas_data);
 IWL_BIOS_TABLE_LOADER_DATA(pwr_limit, u64);
 IWL_BIOS_TABLE_LOADER_DATA(mcc, char);
@@ -180,9 +181,9 @@ bool iwl_sar_geo_support(struct iwl_fw_runtime *fwrt)
 	 */
 	return IWL_UCODE_SERIAL(fwrt->fw->ucode_ver) >= 38 ||
 		(IWL_UCODE_SERIAL(fwrt->fw->ucode_ver) == 17 &&
-		 fwrt->trans->hw_rev != CSR_HW_REV_TYPE_3160) ||
+		 fwrt->trans->info.hw_rev != CSR_HW_REV_TYPE_3160) ||
 		(IWL_UCODE_SERIAL(fwrt->fw->ucode_ver) == 29 &&
-		 ((fwrt->trans->hw_rev & CSR_HW_REV_TYPE_MSK) ==
+		 ((fwrt->trans->info.hw_rev & CSR_HW_REV_TYPE_MSK) ==
 		  CSR_HW_REV_TYPE_7265D));
 }
 IWL_EXPORT_SYMBOL(iwl_sar_geo_support);
@@ -313,7 +314,7 @@ int iwl_fill_ppag_table(struct iwl_fw_runtime *fwrt,
 	bool send_ppag_always;
 
 	/* many firmware images for JF lie about this */
-	if (CSR_HW_RFID_TYPE(fwrt->trans->hw_rf_id) ==
+	if (CSR_HW_RFID_TYPE(fwrt->trans->info.hw_rf_id) ==
 	    CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_JF))
 		return -EOPNOTSUPP;
 
@@ -338,31 +339,35 @@ int iwl_fill_ppag_table(struct iwl_fw_runtime *fwrt,
 		return -EINVAL;
 	}
 
-	/* The 'flags' field is the same in v1 and in v2 so we can just
-	 * use v1 to access it.
-	 */
-	cmd->v1.flags = cpu_to_le32(fwrt->ppag_flags);
-
 	IWL_DEBUG_RADIO(fwrt, "PPAG cmd ver is %d\n", cmd_ver);
 	if (cmd_ver == 1) {
 		num_sub_bands = IWL_NUM_SUB_BANDS_V1;
 		gain = cmd->v1.gain[0];
 		*cmd_size = sizeof(cmd->v1);
-		if (fwrt->ppag_ver >= 1) {
+		cmd->v1.flags = cpu_to_le32(fwrt->ppag_flags);
+		if (fwrt->ppag_bios_rev >= 1) {
 			/* in this case FW supports revision 0 */
 			IWL_DEBUG_RADIO(fwrt,
 					"PPAG table rev is %d, send truncated table\n",
-					fwrt->ppag_ver);
+					fwrt->ppag_bios_rev);
 		}
 	} else if (cmd_ver >= 2 && cmd_ver <= 6) {
 		num_sub_bands = IWL_NUM_SUB_BANDS_V2;
 		gain = cmd->v2.gain[0];
 		*cmd_size = sizeof(cmd->v2);
-		if (fwrt->ppag_ver == 0) {
+		cmd->v2.flags = cpu_to_le32(fwrt->ppag_flags);
+		if (fwrt->ppag_bios_rev == 0) {
 			/* in this case FW supports revisions 1,2 or 3 */
 			IWL_DEBUG_RADIO(fwrt,
 					"PPAG table rev is 0, send padded table\n");
 		}
+	} else if (cmd_ver == 7) {
+		num_sub_bands = IWL_NUM_SUB_BANDS_V2;
+		gain = cmd->v3.gain[0];
+		*cmd_size = sizeof(cmd->v3);
+		cmd->v3.ppag_config_info.table_source = fwrt->ppag_bios_source;
+		cmd->v3.ppag_config_info.table_revision = fwrt->ppag_bios_rev;
+		cmd->v3.ppag_config_info.value = cpu_to_le32(fwrt->ppag_flags);
 	} else {
 		IWL_DEBUG_RADIO(fwrt, "Unsupported PPAG command version\n");
 		return -EINVAL;
@@ -371,9 +376,11 @@ int iwl_fill_ppag_table(struct iwl_fw_runtime *fwrt,
 	/* ppag mode */
 	IWL_DEBUG_RADIO(fwrt,
 			"PPAG MODE bits were read from bios: %d\n",
-			le32_to_cpu(cmd->v1.flags));
+			fwrt->ppag_flags);
 
-	if (cmd_ver == 5)
+	if (cmd_ver == 6)
+		cmd->v1.flags &= cpu_to_le32(IWL_PPAG_CMD_V6_MASK);
+	else if (cmd_ver == 5)
 		cmd->v1.flags &= cpu_to_le32(IWL_PPAG_CMD_V5_MASK);
 	else if (cmd_ver < 5)
 		cmd->v1.flags &= cpu_to_le32(IWL_PPAG_CMD_V4_MASK);
@@ -381,16 +388,20 @@ int iwl_fill_ppag_table(struct iwl_fw_runtime *fwrt,
 	if ((cmd_ver == 1 &&
 	     !fw_has_capa(&fwrt->fw->ucode_capa,
 			  IWL_UCODE_TLV_CAPA_PPAG_CHINA_BIOS_SUPPORT)) ||
-	    (cmd_ver == 2 && fwrt->ppag_ver >= 2)) {
+	    (cmd_ver == 2 && fwrt->ppag_bios_rev >= 2)) {
 		cmd->v1.flags &= cpu_to_le32(IWL_PPAG_ETSI_MASK);
 		IWL_DEBUG_RADIO(fwrt, "masking ppag China bit\n");
 	} else {
 		IWL_DEBUG_RADIO(fwrt, "isn't masking ppag China bit\n");
 	}
 
+	/* The 'flags' field is the same in v1 and v2 so we can just
+	 * use v1 to access it.
+	 */
 	IWL_DEBUG_RADIO(fwrt,
 			"PPAG MODE bits going to be sent: %d\n",
-			le32_to_cpu(cmd->v1.flags));
+			(cmd_ver < 7) ? le32_to_cpu(cmd->v1.flags) :
+					le32_to_cpu(cmd->v3.ppag_config_info.value));
 
 	for (i = 0; i < IWL_NUM_CHAIN_LIMITS; i++) {
 		for (j = 0; j < num_sub_bands; j++) {
@@ -480,7 +491,7 @@ __le32 iwl_get_lari_config_bitmap(struct iwl_fw_runtime *fwrt)
 	u32 val;
 	__le32 config_bitmap = 0;
 
-	switch (CSR_HW_RFID_TYPE(fwrt->trans->hw_rf_id)) {
+	switch (CSR_HW_RFID_TYPE(fwrt->trans->info.hw_rf_id)) {
 	case IWL_CFG_RF_TYPE_HR1:
 	case IWL_CFG_RF_TYPE_HR2:
 	case IWL_CFG_RF_TYPE_JF1:
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
index 53693314d505..9bed3d573b1e 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2023-2024 Intel Corporation
+ * Copyright (C) 2023-2025 Intel Corporation
  */
 
 #ifndef __fw_regulatory_h__
@@ -224,10 +224,14 @@ int iwl_bios_get_dsm(struct iwl_fw_runtime *fwrt, enum iwl_dsm_funcs func,
 		     u32 *value);
 
 static inline u32 iwl_bios_get_ppag_flags(const u32 ppag_modes,
-					  const u8 ppag_ver)
+					  const u8 ppag_bios_rev)
 {
-	return ppag_modes & (ppag_ver < 3 ? IWL_PPAG_ETSI_CHINA_MASK :
-					    IWL_PPAG_REV3_MASK);
+	/* For revision 4 and above driver is pipe */
+	if (ppag_bios_rev >= 4)
+		return ppag_modes;
+
+	return ppag_modes & (ppag_bios_rev < 3 ? IWL_PPAG_ETSI_CHINA_MASK :
+						 IWL_PPAG_REV3_MASK);
 }
 
 bool iwl_puncturing_is_allowed_in_bios(u32 puncturing, u16 mcc);
@@ -236,22 +240,25 @@ bool iwl_puncturing_is_allowed_in_bios(u32 puncturing, u16 mcc);
 #define IWL_DSBR_PERMANENT_URM_MASK	BIT(9)
 
 int iwl_bios_get_dsbr(struct iwl_fw_runtime *fwrt, u32 *value);
+int iwl_bios_get_phy_filters(struct iwl_fw_runtime *fwrt);
 
 static inline void iwl_bios_setup_step(struct iwl_trans *trans,
 				       struct iwl_fw_runtime *fwrt)
 {
 	u32 dsbr;
 
-	if (!trans->trans_cfg->integrated)
+	if (!trans->mac_cfg->integrated)
 		return;
 
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_BZ)
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_BZ)
 		return;
 
 	if (iwl_bios_get_dsbr(fwrt, &dsbr))
 		dsbr = 0;
 
-	trans->dsbr_urm_fw_dependent = !!(dsbr & IWL_DSBR_FW_MODIFIED_URM_MASK);
-	trans->dsbr_urm_permanent = !!(dsbr & IWL_DSBR_PERMANENT_URM_MASK);
+	trans->conf.dsbr_urm_fw_dependent =
+		!!(dsbr & IWL_DSBR_FW_MODIFIED_URM_MASK);
+	trans->conf.dsbr_urm_permanent =
+		!!(dsbr & IWL_DSBR_PERMANENT_URM_MASK);
 }
 #endif /* __fw_regulatory_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/rs.c b/drivers/net/wireless/intel/iwlwifi/fw/rs.c
index 8f99e501629e..746f2acffb8f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/rs.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2021-2022 Intel Corporation
+ * Copyright (C) 2021-2022, 2025 Intel Corporation
  */
 
 #include <net/mac80211.h>
@@ -91,104 +91,6 @@ const char *iwl_rs_pretty_bw(int bw)
 }
 IWL_EXPORT_SYMBOL(iwl_rs_pretty_bw);
 
-static u32 iwl_legacy_rate_to_fw_idx(u32 rate_n_flags)
-{
-	int rate = rate_n_flags & RATE_LEGACY_RATE_MSK_V1;
-	int idx;
-	bool ofdm = !(rate_n_flags & RATE_MCS_CCK_MSK_V1);
-	int offset = ofdm ? IWL_FIRST_OFDM_RATE : 0;
-	int last = ofdm ? IWL_RATE_COUNT_LEGACY : IWL_FIRST_OFDM_RATE;
-
-	for (idx = offset; idx < last; idx++)
-		if (iwl_fw_rate_idx_to_plcp(idx) == rate)
-			return idx - offset;
-	return IWL_RATE_INVALID;
-}
-
-u32 iwl_new_rate_from_v1(u32 rate_v1)
-{
-	u32 rate_v2 = 0;
-	u32 dup = 0;
-
-	if (rate_v1 == 0)
-		return rate_v1;
-	/* convert rate */
-	if (rate_v1 & RATE_MCS_HT_MSK_V1) {
-		u32 nss = 0;
-
-		rate_v2 |= RATE_MCS_HT_MSK;
-		rate_v2 |=
-			rate_v1 & RATE_HT_MCS_RATE_CODE_MSK_V1;
-		nss = (rate_v1 & RATE_HT_MCS_MIMO2_MSK) >>
-			RATE_HT_MCS_NSS_POS_V1;
-		rate_v2 |= nss << RATE_MCS_NSS_POS;
-	} else if (rate_v1 & RATE_MCS_VHT_MSK_V1 ||
-		   rate_v1 & RATE_MCS_HE_MSK_V1) {
-		rate_v2 |= rate_v1 & RATE_VHT_MCS_RATE_CODE_MSK;
-
-		rate_v2 |= rate_v1 & RATE_MCS_NSS_MSK;
-
-		if (rate_v1 & RATE_MCS_HE_MSK_V1) {
-			u32 he_type_bits = rate_v1 & RATE_MCS_HE_TYPE_MSK_V1;
-			u32 he_type = he_type_bits >> RATE_MCS_HE_TYPE_POS_V1;
-			u32 he_106t = (rate_v1 & RATE_MCS_HE_106T_MSK_V1) >>
-				RATE_MCS_HE_106T_POS_V1;
-			u32 he_gi_ltf = (rate_v1 & RATE_MCS_HE_GI_LTF_MSK_V1) >>
-				RATE_MCS_HE_GI_LTF_POS;
-
-			if ((he_type_bits == RATE_MCS_HE_TYPE_SU ||
-			     he_type_bits == RATE_MCS_HE_TYPE_EXT_SU) &&
-			    he_gi_ltf == RATE_MCS_HE_SU_4_LTF)
-				/* the new rate have an additional bit to
-				 * represent the value 4 rather then using SGI
-				 * bit for this purpose - as it was done in the old
-				 * rate */
-				he_gi_ltf += (rate_v1 & RATE_MCS_SGI_MSK_V1) >>
-					RATE_MCS_SGI_POS_V1;
-
-			rate_v2 |= he_gi_ltf << RATE_MCS_HE_GI_LTF_POS;
-			rate_v2 |= he_type << RATE_MCS_HE_TYPE_POS;
-			rate_v2 |= he_106t << RATE_MCS_HE_106T_POS;
-			rate_v2 |= rate_v1 & RATE_HE_DUAL_CARRIER_MODE_MSK;
-			rate_v2 |= RATE_MCS_HE_MSK;
-		} else {
-			rate_v2 |= RATE_MCS_VHT_MSK;
-		}
-	/* if legacy format */
-	} else {
-		u32 legacy_rate = iwl_legacy_rate_to_fw_idx(rate_v1);
-
-		if (WARN_ON_ONCE(legacy_rate == IWL_RATE_INVALID))
-			legacy_rate = (rate_v1 & RATE_MCS_CCK_MSK_V1) ?
-				IWL_FIRST_CCK_RATE : IWL_FIRST_OFDM_RATE;
-
-		rate_v2 |= legacy_rate;
-		if (!(rate_v1 & RATE_MCS_CCK_MSK_V1))
-			rate_v2 |= RATE_MCS_LEGACY_OFDM_MSK;
-	}
-
-	/* convert flags */
-	if (rate_v1 & RATE_MCS_LDPC_MSK_V1)
-		rate_v2 |= RATE_MCS_LDPC_MSK;
-	rate_v2 |= (rate_v1 & RATE_MCS_CHAN_WIDTH_MSK_V1) |
-		(rate_v1 & RATE_MCS_ANT_AB_MSK) |
-		(rate_v1 & RATE_MCS_STBC_MSK) |
-		(rate_v1 & RATE_MCS_BF_MSK);
-
-	dup = (rate_v1 & RATE_MCS_DUP_MSK_V1) >> RATE_MCS_DUP_POS_V1;
-	if (dup) {
-		rate_v2 |= RATE_MCS_DUP_MSK;
-		rate_v2 |= dup << RATE_MCS_CHAN_WIDTH_POS;
-	}
-
-	if ((!(rate_v1 & RATE_MCS_HE_MSK_V1)) &&
-	    (rate_v1 & RATE_MCS_SGI_MSK_V1))
-		rate_v2 |= RATE_MCS_SGI_MSK;
-
-	return rate_v2;
-}
-IWL_EXPORT_SYMBOL(iwl_new_rate_from_v1);
-
 int rs_pretty_print_rate(char *buf, int bufsz, const u32 rate)
 {
 	char *type;
@@ -197,37 +99,40 @@ int rs_pretty_print_rate(char *buf, int bufsz, const u32 rate)
 	u32 bw = (rate & RATE_MCS_CHAN_WIDTH_MSK) >>
 		RATE_MCS_CHAN_WIDTH_POS;
 	u32 format = rate & RATE_MCS_MOD_TYPE_MSK;
+	int index = 0;
 	bool sgi;
 
-	if (format == RATE_MCS_CCK_MSK ||
-	    format == RATE_MCS_LEGACY_OFDM_MSK) {
-		int legacy_rate = rate & RATE_LEGACY_RATE_MSK;
-		int index = format == RATE_MCS_CCK_MSK ?
-			legacy_rate :
-			legacy_rate + IWL_FIRST_OFDM_RATE;
+	switch (format) {
+	case RATE_MCS_MOD_TYPE_LEGACY_OFDM:
+		index = IWL_FIRST_OFDM_RATE;
+		fallthrough;
+	case RATE_MCS_MOD_TYPE_CCK:
+		index += rate & RATE_LEGACY_RATE_MSK;
 
 		return scnprintf(buf, bufsz, "Legacy | ANT: %s Rate: %s Mbps",
 				 iwl_rs_pretty_ant(ant),
 				 iwl_rate_mcs(index)->mbps);
-	}
-
-	if (format ==  RATE_MCS_VHT_MSK)
+	case RATE_MCS_MOD_TYPE_VHT:
 		type = "VHT";
-	else if (format ==  RATE_MCS_HT_MSK)
+		break;
+	case RATE_MCS_MOD_TYPE_HT:
 		type = "HT";
-	else if (format == RATE_MCS_HE_MSK)
+		break;
+	case RATE_MCS_MOD_TYPE_HE:
 		type = "HE";
-	else if (format == RATE_MCS_EHT_MSK)
+		break;
+	case RATE_MCS_MOD_TYPE_EHT:
 		type = "EHT";
-	else
+		break;
+	default:
 		type = "Unknown"; /* shouldn't happen */
+	}
 
-	mcs = format == RATE_MCS_HT_MSK ?
+	mcs = format == RATE_MCS_MOD_TYPE_HT ?
 		RATE_HT_MCS_INDEX(rate) :
 		rate & RATE_MCS_CODE_MSK;
-	nss = ((rate & RATE_MCS_NSS_MSK)
-	       >> RATE_MCS_NSS_POS) + 1;
-	sgi = format == RATE_MCS_HE_MSK ?
+	nss = u32_get_bits(rate, RATE_MCS_NSS_MSK);
+	sgi = format == RATE_MCS_MOD_TYPE_HE ?
 		iwl_he_is_sgi(rate) :
 		rate & RATE_MCS_SGI_MSK;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index a9e6bba2419e..0444a736c2b2 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #ifndef __iwl_fw_runtime_h__
 #define __iwl_fw_runtime_h__
@@ -110,6 +110,9 @@ struct iwl_txf_iter_data {
  *	Only read the UEFI variables if locked.
  * @sar_profiles: sar profiles as read from WRDS/EWRD BIOS tables
  * @geo_profiles: geographic profiles as read from WGDS BIOS table
+ * @phy_filters: specific phy filters as read from WPFC BIOS table
+ * @ppag_bios_rev: PPAG BIOS revision
+ * @ppag_bios_source: see &enum bios_source
  */
 struct iwl_fw_runtime {
 	struct iwl_trans *trans;
@@ -178,12 +181,14 @@ struct iwl_fw_runtime {
 	bool geo_enabled;
 	struct iwl_ppag_chain ppag_chains[IWL_NUM_CHAIN_LIMITS];
 	u32 ppag_flags;
-	u8 ppag_ver;
+	u8 ppag_bios_rev;
+	u8 ppag_bios_source;
 	struct iwl_sar_offset_mapping_cmd sgom_table;
 	bool sgom_enabled;
 	struct iwl_mcc_allowed_ap_type_cmd uats_table;
 	bool uats_valid;
 	u8 uefi_tables_lock_status;
+	struct iwl_phy_specific_cfg phy_filters;
 };
 
 void iwl_fw_runtime_init(struct iwl_fw_runtime *fwrt, struct iwl_trans *trans,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/smem.c b/drivers/net/wireless/intel/iwlwifi/fw/smem.c
index 3f1272014daf..90fd69b4860c 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/smem.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/smem.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2021 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2021, 2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -102,7 +102,7 @@ void iwl_get_shared_mem_conf(struct iwl_fw_runtime *fwrt)
 	}
 
 	pkt = cmd.resp_pkt;
-	if (fwrt->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000)
+	if (fwrt->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_22000)
 		iwl_parse_shared_mem_22000(fwrt, pkt);
 	else
 		iwl_parse_shared_mem(fwrt, pkt);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
index 386aadbce2a2..48126ec6b94b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
@@ -219,7 +219,8 @@ done:
 
 int iwl_uefi_reduce_power_parse(struct iwl_trans *trans,
 				const u8 *data, size_t len,
-				struct iwl_pnvm_image *pnvm_data)
+				struct iwl_pnvm_image *pnvm_data,
+				__le32 sku_id[3])
 {
 	const struct iwl_ucode_tlv *tlv;
 
@@ -241,23 +242,23 @@ int iwl_uefi_reduce_power_parse(struct iwl_trans *trans,
 		}
 
 		if (tlv_type == IWL_UCODE_TLV_PNVM_SKU) {
-			const struct iwl_sku_id *sku_id =
+			const struct iwl_sku_id *tlv_sku_id =
 				(const void *)(data + sizeof(*tlv));
 
 			IWL_DEBUG_FW(trans,
 				     "Got IWL_UCODE_TLV_PNVM_SKU len %d\n",
 				     tlv_len);
 			IWL_DEBUG_FW(trans, "sku_id 0x%0x 0x%0x 0x%0x\n",
-				     le32_to_cpu(sku_id->data[0]),
-				     le32_to_cpu(sku_id->data[1]),
-				     le32_to_cpu(sku_id->data[2]));
+				     le32_to_cpu(tlv_sku_id->data[0]),
+				     le32_to_cpu(tlv_sku_id->data[1]),
+				     le32_to_cpu(tlv_sku_id->data[2]));
 
 			data += sizeof(*tlv) + ALIGN(tlv_len, 4);
 			len -= ALIGN(tlv_len, 4);
 
-			if (trans->sku_id[0] == le32_to_cpu(sku_id->data[0]) &&
-			    trans->sku_id[1] == le32_to_cpu(sku_id->data[1]) &&
-			    trans->sku_id[2] == le32_to_cpu(sku_id->data[2])) {
+			if (sku_id[0] == tlv_sku_id->data[0] &&
+			    sku_id[1] == tlv_sku_id->data[1] &&
+			    sku_id[2] == tlv_sku_id->data[2]) {
 				int ret = iwl_uefi_reduce_power_section(trans,
 								    data, len,
 								    pnvm_data);
@@ -310,11 +311,12 @@ static int iwl_uefi_step_parse(struct uefi_cnv_common_step_data *common_step_dat
 	if (common_step_data->revision != 1)
 		return -EINVAL;
 
-	trans->mbx_addr_0_step = (u32)common_step_data->revision |
+	trans->conf.mbx_addr_0_step =
+		(u32)common_step_data->revision |
 		(u32)common_step_data->cnvi_eq_channel << 8 |
 		(u32)common_step_data->cnvr_eq_channel << 16 |
 		(u32)common_step_data->radio1 << 24;
-	trans->mbx_addr_1_step = (u32)common_step_data->radio2;
+	trans->conf.mbx_addr_1_step = (u32)common_step_data->radio2;
 	return 0;
 }
 
@@ -323,7 +325,7 @@ void iwl_uefi_get_step_table(struct iwl_trans *trans)
 	struct uefi_cnv_common_step_data *data;
 	int ret;
 
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		return;
 
 	data = iwl_uefi_get_verified_variable_guid(trans, &IWL_EFI_WIFI_BT_GUID,
@@ -408,8 +410,8 @@ static int iwl_uefi_uats_parse(struct uefi_cnv_wlan_uats_data *uats_data,
 	return 0;
 }
 
-int iwl_uefi_get_uats_table(struct iwl_trans *trans,
-			    struct iwl_fw_runtime *fwrt)
+void iwl_uefi_get_uats_table(struct iwl_trans *trans,
+			     struct iwl_fw_runtime *fwrt)
 {
 	struct uefi_cnv_wlan_uats_data *data;
 	int ret;
@@ -417,17 +419,12 @@ int iwl_uefi_get_uats_table(struct iwl_trans *trans,
 	data = iwl_uefi_get_verified_variable(trans, IWL_UEFI_UATS_NAME,
 					      "UATS", sizeof(*data), NULL);
 	if (IS_ERR(data))
-		return -EINVAL;
+		return;
 
 	ret = iwl_uefi_uats_parse(data, fwrt);
-	if (ret < 0) {
+	if (ret < 0)
 		IWL_DEBUG_FW(trans, "Cannot read UATS table. rev is invalid\n");
-		kfree(data);
-		return ret;
-	}
-
 	kfree(data);
-	return 0;
 }
 IWL_EXPORT_SYMBOL(iwl_uefi_get_uats_table);
 
@@ -557,13 +554,14 @@ int iwl_uefi_get_ppag_table(struct iwl_fw_runtime *fwrt)
 		goto out;
 	}
 
-	fwrt->ppag_ver = data->revision;
+	fwrt->ppag_bios_rev = data->revision;
 	fwrt->ppag_flags = iwl_bios_get_ppag_flags(data->ppag_modes,
-						   fwrt->ppag_ver);
+						   fwrt->ppag_bios_rev);
 
 	BUILD_BUG_ON(sizeof(fwrt->ppag_chains) != sizeof(data->ppag_chains));
 	memcpy(&fwrt->ppag_chains, &data->ppag_chains,
 	       sizeof(data->ppag_chains));
+	fwrt->ppag_bios_source = BIOS_SOURCE_UEFI;
 out:
 	kfree(data);
 	return ret;
@@ -750,6 +748,10 @@ int iwl_uefi_get_dsm(struct iwl_fw_runtime *fwrt, enum iwl_dsm_funcs func,
 	}
 
 	*value = data->functions[func];
+
+	IWL_DEBUG_RADIO(fwrt,
+			"UEFI: DSM func=%d: value=%d\n", func, *value);
+
 	ret = 0;
 out:
 	kfree(data);
@@ -810,3 +812,31 @@ out:
 	kfree(data);
 	return ret;
 }
+
+int iwl_uefi_get_phy_filters(struct iwl_fw_runtime *fwrt)
+{
+	struct uefi_cnv_wpfc_data *data __free(kfree);
+	struct iwl_phy_specific_cfg *filters = &fwrt->phy_filters;
+
+	data = iwl_uefi_get_verified_variable(fwrt->trans, IWL_UEFI_WPFC_NAME,
+					      "WPFC", sizeof(*data), NULL);
+	if (IS_ERR(data))
+		return -EINVAL;
+
+	if (data->revision != 0) {
+		IWL_DEBUG_RADIO(fwrt, "Unsupported UEFI WPFC revision:%d\n",
+			data->revision);
+		return -EINVAL;
+	}
+
+	BUILD_BUG_ON(ARRAY_SIZE(filters->filter_cfg_chains) !=
+		     ARRAY_SIZE(data->chains));
+
+	for (int i = 0; i < ARRAY_SIZE(filters->filter_cfg_chains); i++) {
+		filters->filter_cfg_chains[i] = cpu_to_le32(data->chains[i]);
+		IWL_DEBUG_RADIO(fwrt, "WPFC: chain %d: %u\n", i, data->chains[i]);
+	}
+
+	IWL_DEBUG_RADIO(fwrt, "Loaded WPFC config from UEFI\n");
+	return 0;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
index eb3c05417da3..5a4c557e47c7 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
@@ -24,6 +24,7 @@
 #define IWL_UEFI_WBEM_NAME		L"UefiCnvWlanWBEM"
 #define IWL_UEFI_PUNCTURING_NAME	L"UefiCnvWlanPuncturing"
 #define IWL_UEFI_DSBR_NAME		L"UefiCnvCommonDSBR"
+#define IWL_UEFI_WPFC_NAME		L"WPFC"
 
 
 #define IWL_SGOM_MAP_SIZE		339
@@ -33,7 +34,7 @@
 #define IWL_UEFI_EWRD_REVISION		2
 #define IWL_UEFI_WGDS_REVISION		3
 #define IWL_UEFI_MIN_PPAG_REV		1
-#define IWL_UEFI_MAX_PPAG_REV		3
+#define IWL_UEFI_MAX_PPAG_REV		4
 #define IWL_UEFI_MIN_WTAS_REVISION	1
 #define IWL_UEFI_MAX_WTAS_REVISION	2
 #define IWL_UEFI_SPLC_REVISION		0
@@ -230,6 +231,18 @@ struct uefi_cnv_wlan_dsbr_data {
 	u32 config;
 } __packed;
 
+/**
+ * struct uefi_cnv_wpfc_data - BIOS Wi-Fi PHY filter Configuration
+ * @revision: the revision of the table
+ * @chains: configuration of each of the chains (a-d)
+ *
+ * specific PHY filter configuration
+ */
+struct uefi_cnv_wpfc_data {
+	u8 revision;
+	u32 chains[4];
+} __packed;
+
 /*
  * This is known to be broken on v4.19 and to work on v5.4.  Until we
  * figure out why this is the case and how to make it work, simply
@@ -240,7 +253,8 @@ void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len);
 u8 *iwl_uefi_get_reduced_power(struct iwl_trans *trans, size_t *len);
 int iwl_uefi_reduce_power_parse(struct iwl_trans *trans,
 				const u8 *data, size_t len,
-				struct iwl_pnvm_image *pnvm_data);
+				struct iwl_pnvm_image *pnvm_data,
+				__le32 sku_id[3]);
 void iwl_uefi_get_step_table(struct iwl_trans *trans);
 int iwl_uefi_handle_tlv_mem_desc(struct iwl_trans *trans, const u8 *data,
 				 u32 tlv_len, struct iwl_pnvm_image *pnvm_data);
@@ -258,10 +272,11 @@ int iwl_uefi_get_wbem(struct iwl_fw_runtime *fwrt, u32 *value);
 int iwl_uefi_get_dsm(struct iwl_fw_runtime *fwrt, enum iwl_dsm_funcs func,
 		     u32 *value);
 void iwl_uefi_get_sgom_table(struct iwl_trans *trans, struct iwl_fw_runtime *fwrt);
-int iwl_uefi_get_uats_table(struct iwl_trans *trans,
-			    struct iwl_fw_runtime *fwrt);
+void iwl_uefi_get_uats_table(struct iwl_trans *trans,
+			     struct iwl_fw_runtime *fwrt);
 int iwl_uefi_get_puncturing(struct iwl_fw_runtime *fwrt);
 int iwl_uefi_get_dsbr(struct iwl_fw_runtime *fwrt, u32 *value);
+int iwl_uefi_get_phy_filters(struct iwl_fw_runtime *fwrt);
 #else /* CONFIG_EFI */
 static inline void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len)
 {
@@ -271,7 +286,8 @@ static inline void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len)
 static inline int
 iwl_uefi_reduce_power_parse(struct iwl_trans *trans,
 			    const u8 *data, size_t len,
-			    struct iwl_pnvm_image *pnvm_data)
+			    struct iwl_pnvm_image *pnvm_data,
+			    __le32 sku_id[3])
 {
 	return -EOPNOTSUPP;
 }
@@ -352,11 +368,9 @@ void iwl_uefi_get_sgom_table(struct iwl_trans *trans, struct iwl_fw_runtime *fwr
 {
 }
 
-static inline
-int iwl_uefi_get_uats_table(struct iwl_trans *trans,
-			    struct iwl_fw_runtime *fwrt)
+static inline void
+iwl_uefi_get_uats_table(struct iwl_trans *trans, struct iwl_fw_runtime *fwrt)
 {
-	return 0;
 }
 
 static inline
@@ -370,5 +384,10 @@ int iwl_uefi_get_dsbr(struct iwl_fw_runtime *fwrt, u32 *value)
 {
 	return -ENOENT;
 }
+
+static inline int iwl_uefi_get_phy_filters(struct iwl_fw_runtime *fwrt)
+{
+	return -ENOENT;
+}
 #endif /* CONFIG_EFI */
 #endif /* __iwl_fw_uefi__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index b9bd89bfdd74..91f22ce36d74 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -115,7 +115,29 @@ static inline u8 num_of_ant(u8 mask)
 }
 
 /**
- * struct iwl_base_params - params not likely to change within a device family
+ * struct iwl_fw_mon_reg - FW monitor register info
+ * @addr: register address
+ * @mask: register mask
+ */
+struct iwl_fw_mon_reg {
+	u32 addr;
+	u32 mask;
+};
+
+/**
+ * struct iwl_fw_mon_regs - FW monitor registers
+ * @write_ptr: write pointer register
+ * @cycle_cnt: cycle count register
+ * @cur_frag: current fragment in use
+ */
+struct iwl_fw_mon_regs {
+	struct iwl_fw_mon_reg write_ptr;
+	struct iwl_fw_mon_reg cycle_cnt;
+	struct iwl_fw_mon_reg cur_frag;
+};
+
+/**
+ * struct iwl_family_base_params - base parameters for an entire family
  * @max_ll_items: max number of OTP blocks
  * @shadow_ram_support: shadow support for OTP memory
  * @led_compensation: compensate on the led on/off time per HW according
@@ -124,12 +146,34 @@ static inline u8 num_of_ant(u8 mask)
  * @wd_timeout: TX queues watchdog timeout
  * @max_event_log_size: size of event log buffer size for ucode event logging
  * @shadow_reg_enable: HW shadow register support
+ * @apmg_not_supported: there's no APMG
  * @apmg_wake_up_wa: should the MAC access REQ be asserted when a command
  *	is in flight. This is due to a HW bug in 7260, 3160 and 7265.
  * @scd_chain_ext_wa: should the chain extension feature in SCD be disabled.
  * @max_tfd_queue_size: max number of entries in tfd queue.
+ * @eeprom_size: EEPROM size
+ * @num_of_queues: number of HW TX queues supported
+ * @pcie_l1_allowed: PCIe L1 state is allowed
+ * @pll_cfg: PLL configuration needed
+ * @nvm_hw_section_num: the ID of the HW NVM section
+ * @features: hw features, any combination of feature_passlist
+ * @smem_offset: offset from which the SMEM begins
+ * @smem_len: the length of SMEM
+ * @mac_addr_from_csr: read HW address from CSR registers at this offset
+ * @d3_debug_data_base_addr: base address where D3 debug data is stored
+ * @d3_debug_data_length: length of the D3 debug data
+ * @min_ba_txq_size: minimum number of slots required in a TX queue used
+ *	for aggregation
+ * @min_txq_size: minimum number of slots required in a TX queue
+ * @gp2_reg_addr: GP2 (timer) register address
+ * @min_umac_error_event_table: minimum SMEM location of UMAC error table
+ * @mon_dbgi_regs: monitor DBGI registers
+ * @mon_dram_regs: monitor DRAM registers
+ * @mon_smem_regs: monitor SMEM registers
+ * @ucode_api_max: Highest version of uCode API supported by driver.
+ * @ucode_api_min: Lowest version of uCode API supported by driver.
  */
-struct iwl_base_params {
+struct iwl_family_base_params {
 	unsigned int wd_timeout;
 
 	u16 eeprom_size;
@@ -140,6 +184,7 @@ struct iwl_base_params {
 	   shadow_reg_enable:1,
 	   pcie_l1_allowed:1,
 	   apmg_wake_up_wa:1,
+	   apmg_not_supported:1,
 	   scd_chain_ext_wa:1;
 
 	u16 num_of_queues;	/* def: HW dependent */
@@ -147,6 +192,22 @@ struct iwl_base_params {
 
 	u8 max_ll_items;
 	u8 led_compensation;
+	u8 ucode_api_max;
+	u8 ucode_api_min;
+	u32 mac_addr_from_csr:10;
+	u8 nvm_hw_section_num;
+	netdev_features_t features;
+	u32 smem_offset;
+	u32 smem_len;
+	u32 min_umac_error_event_table;
+	u32 d3_debug_data_base_addr;
+	u32 d3_debug_data_length;
+	u32 min_txq_size;
+	u32 gp2_reg_addr;
+	u32 min_ba_txq_size;
+	const struct iwl_fw_mon_regs mon_dram_regs;
+	const struct iwl_fw_mon_regs mon_smem_regs;
+	const struct iwl_fw_mon_regs mon_dbgi_regs;
 };
 
 /*
@@ -238,7 +299,7 @@ struct iwl_pwr_tx_backoff {
 	u32 backoff;
 };
 
-enum iwl_cfg_trans_ltr_delay {
+enum iwl_mac_cfg_ltr_delay {
 	IWL_CFG_TRANS_LTR_DELAY_NONE	= 0,
 	IWL_CFG_TRANS_LTR_DELAY_200US	= 1,
 	IWL_CFG_TRANS_LTR_DELAY_2500US	= 2,
@@ -246,35 +307,33 @@ enum iwl_cfg_trans_ltr_delay {
 };
 
 /**
- * struct iwl_cfg_trans_params - information needed to start the trans
+ * struct iwl_mac_cfg - information about the MAC-specific device part
  *
  * These values are specific to the device ID and do not change when
  * multiple configs are used for a single device ID.  They values are
  * used, among other things, to boot the NIC so that the HW REV or
  * RFID can be read before deciding the remaining parameters to use.
  *
- * @base_params: pointer to basic parameters
+ * @base: pointer to basic parameters
  * @device_family: the device family
  * @umac_prph_offset: offset to add to UMAC periphery address
  * @xtal_latency: power up latency to get the xtal stabilized
  * @extra_phy_cfg_flags: extra configuration flags to pass to the PHY
- * @rf_id: need to read rf_id to determine the firmware image
  * @gen2: 22000 and on transport operation
  * @mq_rx_supported: multi-queue rx support
  * @integrated: discrete or integrated
  * @low_latency_xtal: use the low latency xtal if supported
  * @bisr_workaround: BISR hardware workaround (for 22260 series devices)
- * @ltr_delay: LTR delay parameter, &enum iwl_cfg_trans_ltr_delay.
+ * @ltr_delay: LTR delay parameter, &enum iwl_mac_cfg_ltr_delay.
  * @imr_enabled: use the IMR if supported.
  */
-struct iwl_cfg_trans_params {
-	const struct iwl_base_params *base_params;
+struct iwl_mac_cfg {
+	const struct iwl_family_base_params *base;
 	enum iwl_device_family device_family;
 	u32 umac_prph_offset;
 	u32 xtal_latency;
 	u32 extra_phy_cfg_flags;
-	u32 rf_id:1,
-	    gen2:1,
+	u32 gen2:1,
 	    mq_rx_supported:1,
 	    integrated:1,
 	    low_latency_xtal:1,
@@ -283,36 +342,21 @@ struct iwl_cfg_trans_params {
 	    imr_enabled:1;
 };
 
-/**
- * struct iwl_fw_mon_reg - FW monitor register info
- * @addr: register address
- * @mask: register mask
- */
-struct iwl_fw_mon_reg {
-	u32 addr;
-	u32 mask;
-};
-
-/**
- * struct iwl_fw_mon_regs - FW monitor registers
- * @write_ptr: write pointer register
- * @cycle_cnt: cycle count register
- * @cur_frag: current fragment in use
+/*
+ * These sizes were picked according to 8 MSDUs inside 64/256/612 A-MSDUs
+ * in an A-MPDU, with additional overhead to account for processing time.
+ * They will be doubled for MACs starting from So/Ty that don't support
+ * putting multiple frames into a single buffer.
  */
-struct iwl_fw_mon_regs {
-	struct iwl_fw_mon_reg write_ptr;
-	struct iwl_fw_mon_reg cycle_cnt;
-	struct iwl_fw_mon_reg cur_frag;
-};
+#define IWL_NUM_RBDS_NON_HE		(64 * 8)
+#define IWL_NUM_RBDS_HE			(256 * 8)
+#define IWL_NUM_RBDS_EHT		(512 * 8)
 
 /**
- * struct iwl_cfg
- * @trans: the trans-specific configuration part
- * @name: Official name of the device
+ * struct iwl_rf_cfg
  * @fw_name_pre: Firmware filename prefix. The api version and extension
  *	(.ucode) will be added to filename before loading from disk. The
  *	filename is constructed as <fw_name_pre>-<api>.ucode.
- * @fw_name_mac: MAC name for this config, the remaining pieces of the
  *	name will be generated dynamically
  * @ucode_api_max: Highest version of uCode API supported by driver.
  * @ucode_api_min: Lowest version of uCode API supported by driver.
@@ -323,34 +367,25 @@ struct iwl_fw_mon_regs {
  * @non_shared_ant: the antenna that is for WiFi only
  * @nvm_ver: NVM version
  * @nvm_calib_ver: NVM calibration version
+ * @bw_limit: bandwidth limit for this device, if non-zero
  * @ht_params: point to ht parameters
+ * @eeprom_params: EEPROM parameters (old devices)
+ * @thermal_params: Thermal throttling parameters
+ * @lp_xtal_workaround: low-power crystal workaround needed
  * @led_mode: 0=blinking, 1=On(RF On)/Off(RF Off)
  * @rx_with_siso_diversity: 1x1 device with rx antenna diversity
  * @tx_with_siso_diversity: 1x1 device with tx antenna diversity
  * @internal_wimax_coex: internal wifi/wimax combo device
- * @high_temp: Is this NIC is designated to be in high temperature.
  * @host_interrupt_operation_mode: device needs host interrupt operation
  *	mode set
- * @nvm_hw_section_num: the ID of the HW NVM section
- * @mac_addr_from_csr: read HW address from CSR registers at this offset
- * @features: hw features, any combination of feature_passlist
  * @pwr_tx_backoffs: translation table between power limits and backoffs
- * @max_tx_agg_size: max TX aggregation size of the ADDBA request/response
  * @dccm_offset: offset from which DCCM begins
  * @dccm_len: length of DCCM (including runtime stack CCM)
  * @dccm2_offset: offset from which the second DCCM begins
  * @dccm2_len: length of the second DCCM
- * @smem_offset: offset from which the SMEM begins
- * @smem_len: the length of SMEM
  * @vht_mu_mimo_supported: VHT MU-MIMO support
- * @cdb: CDB support
  * @nvm_type: see &enum iwl_nvm_type
- * @d3_debug_data_base_addr: base address where D3 debug data is stored
- * @d3_debug_data_length: length of the D3 debug data
- * @min_txq_size: minimum number of slots required in a TX queue
  * @uhb_supported: ultra high band channels supported
- * @min_ba_txq_size: minimum number of slots required in a TX queue which
- *	based on hardware support (HE - 256, EHT - 1K).
  * @num_rbds: number of receive buffer descriptors to use
  *	(only used for multi-queue capable devices)
  *
@@ -358,60 +393,38 @@ struct iwl_fw_mon_regs {
  * API differences in uCode shouldn't be handled here but through TLVs
  * and/or the uCode API version instead.
  */
-struct iwl_cfg {
-	struct iwl_cfg_trans_params trans;
+struct iwl_rf_cfg {
 	/* params specific to an individual device within a device family */
-	const char *name;
 	const char *fw_name_pre;
-	const char *fw_name_mac;
 	/* params likely to change within a device family */
-	const struct iwl_ht_params *ht_params;
+	const struct iwl_ht_params ht_params;
 	const struct iwl_eeprom_params *eeprom_params;
 	const struct iwl_pwr_tx_backoff *pwr_tx_backoffs;
-	const char *default_nvm_file_C_step;
 	const struct iwl_tt_params *thermal_params;
 	enum iwl_led_mode led_mode;
 	enum iwl_nvm_type nvm_type;
 	u32 max_data_size;
 	u32 max_inst_size;
-	netdev_features_t features;
 	u32 dccm_offset;
 	u32 dccm_len;
 	u32 dccm2_offset;
 	u32 dccm2_len;
-	u32 smem_offset;
-	u32 smem_len;
 	u16 nvm_ver;
 	u16 nvm_calib_ver;
+	u16 bw_limit;
 	u32 rx_with_siso_diversity:1,
 	    tx_with_siso_diversity:1,
 	    internal_wimax_coex:1,
 	    host_interrupt_operation_mode:1,
-	    high_temp:1,
-	    mac_addr_from_csr:10,
 	    lp_xtal_workaround:1,
-	    apmg_not_supported:1,
 	    vht_mu_mimo_supported:1,
-	    cdb:1,
-	    dbgc_supported:1,
 	    uhb_supported:1;
 	u8 valid_tx_ant;
 	u8 valid_rx_ant;
 	u8 non_shared_ant;
-	u8 nvm_hw_section_num;
-	u8 max_tx_agg_size;
 	u8 ucode_api_max;
 	u8 ucode_api_min;
 	u16 num_rbds;
-	u32 min_umac_error_event_table;
-	u32 d3_debug_data_base_addr;
-	u32 d3_debug_data_length;
-	u32 min_txq_size;
-	u32 gp2_reg_addr;
-	u32 min_ba_txq_size;
-	const struct iwl_fw_mon_regs mon_dram_regs;
-	const struct iwl_fw_mon_regs mon_smem_regs;
-	const struct iwl_fw_mon_regs mon_dbgi_regs;
 };
 
 #define IWL_CFG_ANY (~0)
@@ -419,8 +432,10 @@ struct iwl_cfg {
 #define IWL_CFG_MAC_TYPE_PU		0x31
 #define IWL_CFG_MAC_TYPE_TH		0x32
 #define IWL_CFG_MAC_TYPE_QU		0x33
+#define IWL_CFG_MAC_TYPE_CC		0x34
 #define IWL_CFG_MAC_TYPE_QUZ		0x35
 #define IWL_CFG_MAC_TYPE_SO		0x37
+#define IWL_CFG_MAC_TYPE_TY		0x42
 #define IWL_CFG_MAC_TYPE_SOF		0x43
 #define IWL_CFG_MAC_TYPE_MA		0x44
 #define IWL_CFG_MAC_TYPE_BZ		0x46
@@ -432,8 +447,6 @@ struct iwl_cfg {
 #define IWL_CFG_MAC_TYPE_BR		0x4C
 #define IWL_CFG_MAC_TYPE_DR		0x4D
 
-#define IWL_CFG_RF_TYPE_TH		0x105
-#define IWL_CFG_RF_TYPE_TH1		0x108
 #define IWL_CFG_RF_TYPE_JF2		0x105
 #define IWL_CFG_RF_TYPE_JF1		0x108
 #define IWL_CFG_RF_TYPE_HR2		0x10A
@@ -451,9 +464,6 @@ struct iwl_cfg {
 #define IWL_CFG_RF_ID_HR		0x7
 #define IWL_CFG_RF_ID_HR1		0x4
 
-#define IWL_CFG_BW_NO_LIM		(U16_MAX - 1)
-#define IWL_CFG_BW_ANY			U16_MAX
-
 #define IWL_CFG_CORES_BT		0x0
 #define IWL_CFG_CORES_BT_GNSS		0x5
 
@@ -468,51 +478,129 @@ struct iwl_cfg {
 #define IWL_SUBDEVICE_CORES(subdevice)	((u16)((subdevice) & 0x1C00) >> 10)
 
 struct iwl_dev_info {
+	const struct iwl_rf_cfg *cfg;
+	const char *name;
 	u16 device;
 	u16 subdevice;
-	u16 mac_type;
-	u16 rf_type;
-	u16 bw_limit;
-	u8 mac_step;
-	u8 rf_step;
-	u8 rf_id;
-	u8 cores;
-	u8 cdb;
-	u8 jacket;
-	const struct iwl_cfg *cfg;
-	const char *name;
+	u32 subdevice_m_l:4,
+	    subdevice_m_h:4,
+	    match_rf_type:1,
+	    rf_type:9,
+	    match_bw_limit:1,
+	    bw_limit:1,
+	    match_rf_step:1,
+	    rf_step:4,
+	    match_rf_id:1,
+	    rf_id:4,
+	    match_cdb:1,
+	    cdb:1;
 };
 
 #if IS_ENABLED(CONFIG_IWLWIFI_KUNIT_TESTS)
 extern const struct iwl_dev_info iwl_dev_info_table[];
 extern const unsigned int iwl_dev_info_table_size;
 const struct iwl_dev_info *
-iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
-		      u16 mac_type, u8 mac_step, u16 rf_type, u8 cdb,
-		      u8 jacket, u8 rf_id, u8 bw_limit, u8 cores, u8 rf_step);
+iwl_pci_find_dev_info(u16 device, u16 subsystem_device, u16 rf_type, u8 cdb,
+		      u8 rf_id, u8 bw_limit, u8 rf_step);
 extern const struct pci_device_id iwl_hw_card_ids[];
 #endif
 
 /*
  * This list declares the config structures for all devices.
  */
-extern const struct iwl_cfg_trans_params iwl9000_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl9560_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl9560_long_latency_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl9560_shared_clk_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_qu_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_qu_medium_latency_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_qu_long_latency_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_ax200_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_so_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_so_long_latency_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_so_long_latency_imr_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_ma_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_bz_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_gl_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_sc_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_dr_trans_cfg;
-extern const struct iwl_cfg_trans_params iwl_br_trans_cfg;
+extern const struct iwl_mac_cfg iwl1000_mac_cfg;
+extern const struct iwl_mac_cfg iwl5000_mac_cfg;
+extern const struct iwl_mac_cfg iwl2000_mac_cfg;
+extern const struct iwl_mac_cfg iwl2030_mac_cfg;
+extern const struct iwl_mac_cfg iwl105_mac_cfg;
+extern const struct iwl_mac_cfg iwl135_mac_cfg;
+extern const struct iwl_mac_cfg iwl5150_mac_cfg;
+extern const struct iwl_mac_cfg iwl6005_mac_cfg;
+extern const struct iwl_mac_cfg iwl6030_mac_cfg;
+extern const struct iwl_mac_cfg iwl6000i_mac_cfg;
+extern const struct iwl_mac_cfg iwl6050_mac_cfg;
+extern const struct iwl_mac_cfg iwl6150_mac_cfg;
+extern const struct iwl_mac_cfg iwl6000_mac_cfg;
+extern const struct iwl_mac_cfg iwl7000_mac_cfg;
+extern const struct iwl_mac_cfg iwl8000_mac_cfg;
+extern const struct iwl_mac_cfg iwl9000_mac_cfg;
+extern const struct iwl_mac_cfg iwl9560_mac_cfg;
+extern const struct iwl_mac_cfg iwl9560_long_latency_mac_cfg;
+extern const struct iwl_mac_cfg iwl9560_shared_clk_mac_cfg;
+extern const struct iwl_mac_cfg iwl_qu_mac_cfg;
+extern const struct iwl_mac_cfg iwl_qu_medium_latency_mac_cfg;
+extern const struct iwl_mac_cfg iwl_qu_long_latency_mac_cfg;
+extern const struct iwl_mac_cfg iwl_ax200_mac_cfg;
+extern const struct iwl_mac_cfg iwl_ty_mac_cfg;
+extern const struct iwl_mac_cfg iwl_so_mac_cfg;
+extern const struct iwl_mac_cfg iwl_so_long_latency_mac_cfg;
+extern const struct iwl_mac_cfg iwl_so_long_latency_imr_mac_cfg;
+extern const struct iwl_mac_cfg iwl_ma_mac_cfg;
+extern const struct iwl_mac_cfg iwl_bz_mac_cfg;
+extern const struct iwl_mac_cfg iwl_gl_mac_cfg;
+extern const struct iwl_mac_cfg iwl_sc_mac_cfg;
+extern const struct iwl_mac_cfg iwl_dr_mac_cfg;
+
+extern const char iwl1000_bgn_name[];
+extern const char iwl1000_bg_name[];
+extern const char iwl100_bgn_name[];
+extern const char iwl100_bg_name[];
+extern const char iwl2000_2bgn_name[];
+extern const char iwl2000_2bgn_d_name[];
+extern const char iwl2030_2bgn_name[];
+extern const char iwl105_bgn_name[];
+extern const char iwl105_bgn_d_name[];
+extern const char iwl135_bgn_name[];
+extern const char iwl5300_agn_name[];
+extern const char iwl5100_bgn_name[];
+extern const char iwl5100_abg_name[];
+extern const char iwl5100_agn_name[];
+extern const char iwl5350_agn_name[];
+extern const char iwl5150_agn_name[];
+extern const char iwl5150_abg_name[];
+extern const char iwl6005_2agn_name[];
+extern const char iwl6005_2abg_name[];
+extern const char iwl6005_2bg_name[];
+extern const char iwl6005_2agn_sff_name[];
+extern const char iwl6005_2agn_d_name[];
+extern const char iwl6005_2agn_mow1_name[];
+extern const char iwl6005_2agn_mow2_name[];
+extern const char iwl6030_2agn_name[];
+extern const char iwl6030_2abg_name[];
+extern const char iwl6030_2bgn_name[];
+extern const char iwl6030_2bg_name[];
+extern const char iwl6035_2agn_name[];
+extern const char iwl6035_2agn_sff_name[];
+extern const char iwl1030_bgn_name[];
+extern const char iwl1030_bg_name[];
+extern const char iwl130_bgn_name[];
+extern const char iwl130_bg_name[];
+extern const char iwl6000i_2agn_name[];
+extern const char iwl6000i_2abg_name[];
+extern const char iwl6000i_2bg_name[];
+extern const char iwl6050_2agn_name[];
+extern const char iwl6050_2abg_name[];
+extern const char iwl6150_bgn_name[];
+extern const char iwl6150_bg_name[];
+extern const char iwl6000_3agn_name[];
+extern const char iwl7260_2ac_name[];
+extern const char iwl7260_2n_name[];
+extern const char iwl7260_n_name[];
+extern const char iwl3160_2ac_name[];
+extern const char iwl3160_2n_name[];
+extern const char iwl3160_n_name[];
+extern const char iwl3165_2ac_name[];
+extern const char iwl3168_2ac_name[];
+extern const char iwl7265_2ac_name[];
+extern const char iwl7265_2n_name[];
+extern const char iwl7265_n_name[];
+extern const char iwl8260_2n_name[];
+extern const char iwl8260_2ac_name[];
+extern const char iwl8265_2ac_name[];
+extern const char iwl8275_2ac_name[];
+extern const char iwl4165_2ac_name[];
+extern const char iwl_killer_1435i_name[];
+extern const char iwl_killer_1434_kix_name[];
 extern const char iwl9162_name[];
 extern const char iwl9260_name[];
 extern const char iwl9260_1_name[];
@@ -545,130 +633,84 @@ extern const char iwl_ax211_killer_1675s_name[];
 extern const char iwl_ax211_killer_1675i_name[];
 extern const char iwl_ax411_killer_1690s_name[];
 extern const char iwl_ax411_killer_1690i_name[];
+extern const char iwl_ax210_name[];
 extern const char iwl_ax211_name[];
-extern const char iwl_ax231_name[];
 extern const char iwl_ax411_name[];
-extern const char iwl_fm_name[];
-extern const char iwl_wh_name[];
-extern const char iwl_sp_name[];
-extern const char iwl_gl_name[];
-extern const char iwl_mtp_name[];
-extern const char iwl_dr_name[];
-extern const char iwl_br_name[];
+extern const char iwl_killer_be1750s_name[];
+extern const char iwl_killer_be1750i_name[];
+extern const char iwl_killer_be1750w_name[];
+extern const char iwl_killer_be1750x_name[];
+extern const char iwl_killer_be1790s_name[];
+extern const char iwl_killer_be1790i_name[];
+extern const char iwl_be201_name[];
+extern const char iwl_be200_name[];
+extern const char iwl_be202_name[];
+extern const char iwl_be401_name[];
+extern const char iwl_be213_name[];
+extern const char iwl_killer_be1775s_name[];
+extern const char iwl_killer_be1775i_name[];
+extern const char iwl_be211_name[];
+extern const char iwl_killer_bn1850w2_name[];
+extern const char iwl_killer_bn1850i_name[];
+extern const char iwl_bn201_name[];
+extern const char iwl_be221_name[];
+extern const char iwl_be223_name[];
 #if IS_ENABLED(CONFIG_IWLDVM)
-extern const struct iwl_cfg iwl5300_agn_cfg;
-extern const struct iwl_cfg iwl5100_agn_cfg;
-extern const struct iwl_cfg iwl5350_agn_cfg;
-extern const struct iwl_cfg iwl5100_bgn_cfg;
-extern const struct iwl_cfg iwl5100_abg_cfg;
-extern const struct iwl_cfg iwl5150_agn_cfg;
-extern const struct iwl_cfg iwl5150_abg_cfg;
-extern const struct iwl_cfg iwl6005_2agn_cfg;
-extern const struct iwl_cfg iwl6005_2abg_cfg;
-extern const struct iwl_cfg iwl6005_2bg_cfg;
-extern const struct iwl_cfg iwl6005_2agn_sff_cfg;
-extern const struct iwl_cfg iwl6005_2agn_d_cfg;
-extern const struct iwl_cfg iwl6005_2agn_mow1_cfg;
-extern const struct iwl_cfg iwl6005_2agn_mow2_cfg;
-extern const struct iwl_cfg iwl1030_bgn_cfg;
-extern const struct iwl_cfg iwl1030_bg_cfg;
-extern const struct iwl_cfg iwl6030_2agn_cfg;
-extern const struct iwl_cfg iwl6030_2abg_cfg;
-extern const struct iwl_cfg iwl6030_2bgn_cfg;
-extern const struct iwl_cfg iwl6030_2bg_cfg;
-extern const struct iwl_cfg iwl6000i_2agn_cfg;
-extern const struct iwl_cfg iwl6000i_2abg_cfg;
-extern const struct iwl_cfg iwl6000i_2bg_cfg;
-extern const struct iwl_cfg iwl6000_3agn_cfg;
-extern const struct iwl_cfg iwl6050_2agn_cfg;
-extern const struct iwl_cfg iwl6050_2abg_cfg;
-extern const struct iwl_cfg iwl6150_bgn_cfg;
-extern const struct iwl_cfg iwl6150_bg_cfg;
-extern const struct iwl_cfg iwl1000_bgn_cfg;
-extern const struct iwl_cfg iwl1000_bg_cfg;
-extern const struct iwl_cfg iwl100_bgn_cfg;
-extern const struct iwl_cfg iwl100_bg_cfg;
-extern const struct iwl_cfg iwl130_bgn_cfg;
-extern const struct iwl_cfg iwl130_bg_cfg;
-extern const struct iwl_cfg iwl2000_2bgn_cfg;
-extern const struct iwl_cfg iwl2000_2bgn_d_cfg;
-extern const struct iwl_cfg iwl2030_2bgn_cfg;
-extern const struct iwl_cfg iwl6035_2agn_cfg;
-extern const struct iwl_cfg iwl6035_2agn_sff_cfg;
-extern const struct iwl_cfg iwl105_bgn_cfg;
-extern const struct iwl_cfg iwl105_bgn_d_cfg;
-extern const struct iwl_cfg iwl135_bgn_cfg;
+extern const struct iwl_rf_cfg iwl5300_agn_cfg;
+extern const struct iwl_rf_cfg iwl5350_agn_cfg;
+extern const struct iwl_rf_cfg iwl5100_n_cfg;
+extern const struct iwl_rf_cfg iwl5100_abg_cfg;
+extern const struct iwl_rf_cfg iwl5150_agn_cfg;
+extern const struct iwl_rf_cfg iwl5150_abg_cfg;
+extern const struct iwl_rf_cfg iwl6005_non_n_cfg;
+extern const struct iwl_rf_cfg iwl6005_n_cfg;
+extern const struct iwl_rf_cfg iwl6030_n_cfg;
+extern const struct iwl_rf_cfg iwl6030_non_n_cfg;
+extern const struct iwl_rf_cfg iwl6000i_2agn_cfg;
+extern const struct iwl_rf_cfg iwl6000i_non_n_cfg;
+extern const struct iwl_rf_cfg iwl6000i_non_n_cfg;
+extern const struct iwl_rf_cfg iwl6000_3agn_cfg;
+extern const struct iwl_rf_cfg iwl6050_2agn_cfg;
+extern const struct iwl_rf_cfg iwl6050_2abg_cfg;
+extern const struct iwl_rf_cfg iwl6150_bgn_cfg;
+extern const struct iwl_rf_cfg iwl6150_bg_cfg;
+extern const struct iwl_rf_cfg iwl1000_bgn_cfg;
+extern const struct iwl_rf_cfg iwl1000_bg_cfg;
+extern const struct iwl_rf_cfg iwl100_bgn_cfg;
+extern const struct iwl_rf_cfg iwl100_bg_cfg;
+extern const struct iwl_rf_cfg iwl130_bgn_cfg;
+extern const struct iwl_rf_cfg iwl130_bg_cfg;
+extern const struct iwl_rf_cfg iwl2000_2bgn_cfg;
+extern const struct iwl_rf_cfg iwl2030_2bgn_cfg;
+extern const struct iwl_rf_cfg iwl6035_2agn_cfg;
+extern const struct iwl_rf_cfg iwl105_bgn_cfg;
+extern const struct iwl_rf_cfg iwl135_bgn_cfg;
 #endif /* CONFIG_IWLDVM */
 #if IS_ENABLED(CONFIG_IWLMVM)
-extern const struct iwl_ht_params iwl_22000_ht_params;
-extern const struct iwl_cfg iwl7260_2ac_cfg;
-extern const struct iwl_cfg iwl7260_2ac_cfg_high_temp;
-extern const struct iwl_cfg iwl7260_2n_cfg;
-extern const struct iwl_cfg iwl7260_n_cfg;
-extern const struct iwl_cfg iwl3160_2ac_cfg;
-extern const struct iwl_cfg iwl3160_2n_cfg;
-extern const struct iwl_cfg iwl3160_n_cfg;
-extern const struct iwl_cfg iwl3165_2ac_cfg;
-extern const struct iwl_cfg iwl3168_2ac_cfg;
-extern const struct iwl_cfg iwl7265_2ac_cfg;
-extern const struct iwl_cfg iwl7265_2n_cfg;
-extern const struct iwl_cfg iwl7265_n_cfg;
-extern const struct iwl_cfg iwl7265d_2ac_cfg;
-extern const struct iwl_cfg iwl7265d_2n_cfg;
-extern const struct iwl_cfg iwl7265d_n_cfg;
-extern const struct iwl_cfg iwl8260_2n_cfg;
-extern const struct iwl_cfg iwl8260_2ac_cfg;
-extern const struct iwl_cfg iwl8265_2ac_cfg;
-extern const struct iwl_cfg iwl8275_2ac_cfg;
-extern const struct iwl_cfg iwl4165_2ac_cfg;
-extern const struct iwl_cfg iwl9260_2ac_cfg;
-extern const struct iwl_cfg iwl9560_qu_b0_jf_b0_cfg;
-extern const struct iwl_cfg iwl9560_qu_c0_jf_b0_cfg;
-extern const struct iwl_cfg iwl9560_quz_a0_jf_b0_cfg;
-extern const struct iwl_cfg iwl9560_2ac_cfg_soc;
-extern const struct iwl_cfg iwl_qu_b0_hr1_b0;
-extern const struct iwl_cfg iwl_qu_c0_hr1_b0;
-extern const struct iwl_cfg iwl_quz_a0_hr1_b0;
-extern const struct iwl_cfg iwl_qu_b0_hr_b0;
-extern const struct iwl_cfg iwl_qu_c0_hr_b0;
-extern const struct iwl_cfg iwl_ax200_cfg_cc;
-extern const struct iwl_cfg iwl_ax201_cfg_qu_hr;
-extern const struct iwl_cfg iwl_ax201_cfg_qu_c0_hr_b0;
-extern const struct iwl_cfg iwl_ax201_cfg_quz_hr;
-extern const struct iwl_cfg iwl_ax1650i_cfg_quz_hr;
-extern const struct iwl_cfg iwl_ax1650s_cfg_quz_hr;
-extern const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0;
-extern const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0;
-extern const struct iwl_cfg killer1650s_2ax_cfg_qu_c0_hr_b0;
-extern const struct iwl_cfg killer1650i_2ax_cfg_qu_c0_hr_b0;
-extern const struct iwl_cfg killer1650x_2ax_cfg;
-extern const struct iwl_cfg killer1650w_2ax_cfg;
-extern const struct iwl_cfg iwlax210_2ax_cfg_so_jf_b0;
-extern const struct iwl_cfg iwlax211_2ax_cfg_so_gf_a0;
-extern const struct iwl_cfg iwlax211_2ax_cfg_so_gf_a0_long;
-extern const struct iwl_cfg iwlax210_2ax_cfg_ty_gf_a0;
-extern const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0;
-extern const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0_long;
-
-extern const struct iwl_cfg iwl_cfg_ma;
-
-extern const struct iwl_cfg iwl_cfg_so_a0_hr_a0;
-extern const struct iwl_cfg iwl_cfg_quz_a0_hr_b0;
+extern const struct iwl_rf_cfg iwl7260_cfg;
+extern const struct iwl_rf_cfg iwl7260_high_temp_cfg;
+extern const struct iwl_rf_cfg iwl3160_cfg;
+extern const struct iwl_rf_cfg iwl3165_2ac_cfg;
+extern const struct iwl_rf_cfg iwl3168_2ac_cfg;
+extern const struct iwl_rf_cfg iwl7265_cfg;
+extern const struct iwl_rf_cfg iwl7265d_cfg;
+extern const struct iwl_rf_cfg iwl8260_cfg;
+extern const struct iwl_rf_cfg iwl8265_cfg;
+extern const struct iwl_rf_cfg iwl_rf_jf;
+extern const struct iwl_rf_cfg iwl_rf_jf_80mhz;
+extern const struct iwl_rf_cfg iwl_rf_hr1;
+extern const struct iwl_rf_cfg iwl_rf_hr;
+extern const struct iwl_rf_cfg iwl_rf_hr_80mhz;
+
+extern const struct iwl_rf_cfg iwl_rf_gf;
 #endif /* CONFIG_IWLMVM */
 
 #if IS_ENABLED(CONFIG_IWLMLD)
-extern const struct iwl_ht_params iwl_bz_ht_params;
-
-extern const struct iwl_ht_params iwl_bz_ht_params;
-
-extern const struct iwl_cfg iwl_cfg_bz;
-extern const struct iwl_cfg iwl_cfg_gl;
-
-extern const struct iwl_cfg iwl_cfg_sc;
-extern const struct iwl_cfg iwl_cfg_sc2;
-extern const struct iwl_cfg iwl_cfg_sc2f;
-extern const struct iwl_cfg iwl_cfg_dr;
-extern const struct iwl_cfg iwl_cfg_br;
+extern const struct iwl_rf_cfg iwl_rf_fm;
+extern const struct iwl_rf_cfg iwl_rf_fm_160mhz;
+#define iwl_rf_wh iwl_rf_fm
+#define iwl_rf_wh_160mhz iwl_rf_fm_160mhz
+#define iwl_rf_pe iwl_rf_fm
 #endif /* CONFIG_IWLMLD */
 
 #endif /* __IWL_CONFIG_H__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-v2.h
index 20563a32a21a..8c5c0ea46181 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-v2.h
@@ -2,8 +2,8 @@
 /*
  * Copyright (C) 2018, 2020-2025 Intel Corporation
  */
-#ifndef __iwl_context_info_file_gen3_h__
-#define __iwl_context_info_file_gen3_h__
+#ifndef __iwl_context_info_file_v2_h__
+#define __iwl_context_info_file_v2_h__
 
 #include "iwl-context-info.h"
 
@@ -58,6 +58,7 @@ enum iwl_prph_scratch_mtr_format {
  * @IWL_PRPH_SCRATCH_RB_SIZE_EXT_16K: 16kB RB size
  * @IWL_PRPH_SCRATCH_SCU_FORCE_ACTIVE: Indicate fw to set SCU_FORCE_ACTIVE
  *	upon reset.
+ * @IWL_PRPH_SCRATCH_TOP_RESET: request TOP reset
  */
 enum iwl_prph_scratch_flags {
 	IWL_PRPH_SCRATCH_IMR_DEBUG_EN		= BIT(1),
@@ -74,15 +75,18 @@ enum iwl_prph_scratch_flags {
 	IWL_PRPH_SCRATCH_RB_SIZE_EXT_12K	= 9 << 20,
 	IWL_PRPH_SCRATCH_RB_SIZE_EXT_16K	= 10 << 20,
 	IWL_PRPH_SCRATCH_SCU_FORCE_ACTIVE	= BIT(29),
+	IWL_PRPH_SCRATCH_TOP_RESET		= BIT(30),
 };
 
 /**
  * enum iwl_prph_scratch_ext_flags - PRPH scratch control ext flags
+ * @IWL_PRPH_SCRATCH_EXT_EXT_FSEQ: external FSEQ image provided
  * @IWL_PRPH_SCRATCH_EXT_URM_FW: switch to URM mode based on fw setting
  * @IWL_PRPH_SCRATCH_EXT_URM_PERM: switch to permanent URM mode
  * @IWL_PRPH_SCRATCH_EXT_32KHZ_CLK_VALID: use external 32 KHz clock
  */
 enum iwl_prph_scratch_ext_flags {
+	IWL_PRPH_SCRATCH_EXT_EXT_FSEQ		= BIT(0),
 	IWL_PRPH_SCRATCH_EXT_URM_FW		= BIT(4),
 	IWL_PRPH_SCRATCH_EXT_URM_PERM		= BIT(5),
 	IWL_PRPH_SCRATCH_EXT_32KHZ_CLK_VALID	= BIT(8),
@@ -202,6 +206,19 @@ struct iwl_prph_scratch_ctrl_cfg {
 	struct iwl_prph_scratch_step_cfg step_cfg;
 } __packed; /* PERIPH_SCRATCH_CTRL_CFG_S */
 
+#define IWL_NUM_DRAM_FSEQ_ENTRIES	8
+
+/**
+ * struct iwl_context_info_dram_fseq - images DRAM map (with fseq)
+ * each entry in the map represents a DRAM chunk of up to 32 KB
+ * @common: UMAC/LMAC/virtual images
+ * @fseq_img: FSEQ image DRAM map
+ */
+struct iwl_context_info_dram_fseq {
+	struct iwl_context_info_dram_nonfseq common;
+	__le64 fseq_img[IWL_NUM_DRAM_FSEQ_ENTRIES];
+} __packed; /* PERIPH_SCRATCH_DRAM_MAP_S */
+
 /**
  * struct iwl_prph_scratch - peripheral scratch mapping
  * @ctrl_cfg: control and configuration of prph scratch
@@ -215,7 +232,7 @@ struct iwl_prph_scratch {
 	__le32 fseq_override;
 	__le32 step_analog_params;
 	__le32 reserved[8];
-	struct iwl_context_info_dram dram;
+	struct iwl_context_info_dram_fseq dram;
 } __packed; /* PERIPH_SCRATCH_S */
 
 /**
@@ -233,7 +250,7 @@ struct iwl_prph_info {
 } __packed; /* PERIPH_INFO_S */
 
 /**
- * struct iwl_context_info_gen3 - device INIT configuration
+ * struct iwl_context_info_v2 - device INIT configuration
  * @version: version of the context information
  * @size: size of context information in DWs
  * @config: context in which the peripheral would execute - a subset of
@@ -276,7 +293,7 @@ struct iwl_prph_info {
  * @prph_scratch_size: the size of the peripheral scratch structure in DWs
  * @reserved: reserved
  */
-struct iwl_context_info_gen3 {
+struct iwl_context_info_v2 {
 	__le16 version;
 	__le16 size;
 	__le32 config;
@@ -306,22 +323,22 @@ struct iwl_context_info_gen3 {
 	__le32 reserved;
 } __packed; /* IPC_CONTEXT_INFO_S */
 
-int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
-				 const struct fw_img *fw);
-void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans, bool alive);
+int iwl_pcie_ctxt_info_v2_alloc(struct iwl_trans *trans,
+				const struct iwl_fw *fw,
+				const struct fw_img *img);
+void iwl_pcie_ctxt_info_v2_kick(struct iwl_trans *trans);
+void iwl_pcie_ctxt_info_v2_free(struct iwl_trans *trans, bool alive);
 
-int iwl_trans_pcie_ctx_info_gen3_load_pnvm(struct iwl_trans *trans,
-					   const struct iwl_pnvm_image *pnvm_payloads,
-					   const struct iwl_ucode_capabilities *capa);
-void iwl_trans_pcie_ctx_info_gen3_set_pnvm(struct iwl_trans *trans,
-					   const struct iwl_ucode_capabilities *capa);
+int iwl_trans_pcie_ctx_info_v2_load_pnvm(struct iwl_trans *trans,
+					 const struct iwl_pnvm_image *pnvm_payloads,
+					 const struct iwl_ucode_capabilities *capa);
+void iwl_trans_pcie_ctx_info_v2_set_pnvm(struct iwl_trans *trans,
+					 const struct iwl_ucode_capabilities *capa);
 int
-iwl_trans_pcie_ctx_info_gen3_load_reduce_power(struct iwl_trans *trans,
-					       const struct iwl_pnvm_image *payloads,
-					       const struct iwl_ucode_capabilities *capa);
+iwl_trans_pcie_ctx_info_v2_load_reduce_power(struct iwl_trans *trans,
+					     const struct iwl_pnvm_image *payloads,
+					     const struct iwl_ucode_capabilities *capa);
 void
-iwl_trans_pcie_ctx_info_gen3_set_reduce_power(struct iwl_trans *trans,
-					      const struct iwl_ucode_capabilities *capa);
-int iwl_trans_pcie_ctx_info_gen3_set_step(struct iwl_trans *trans,
-					  u32 mbx_addr_0_step, u32 mbx_addr_1_step);
-#endif /* __iwl_context_info_file_gen3_h__ */
+iwl_trans_pcie_ctx_info_v2_set_reduce_power(struct iwl_trans *trans,
+					    const struct iwl_ucode_capabilities *capa);
+#endif /* __iwl_context_info_file_v2_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h
index dfd44fabf237..7ae0fbdef208 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020, 2022, 2024 Intel Corporation
+ * Copyright (C) 2018-2020, 2022, 2024-2025 Intel Corporation
  */
 #ifndef __iwl_context_info_file_h__
 #define __iwl_context_info_file_h__
@@ -78,13 +78,13 @@ struct iwl_context_info_control {
 } __packed;
 
 /**
- * struct iwl_context_info_dram - images DRAM map
+ * struct iwl_context_info_dram_nonfseq - images DRAM map
  * each entry in the map represents a DRAM chunk of up to 32 KB
  * @umac_img: UMAC image DRAM map
  * @lmac_img: LMAC image DRAM map
  * @virtual_img: paged image DRAM map
  */
-struct iwl_context_info_dram {
+struct iwl_context_info_dram_nonfseq {
 	__le64 umac_img[IWL_MAX_DRAM_ENTRY];
 	__le64 lmac_img[IWL_MAX_DRAM_ENTRY];
 	__le64 virtual_img[IWL_MAX_DRAM_ENTRY];
@@ -177,16 +177,16 @@ struct iwl_context_info {
 	struct iwl_context_info_early_dbg_cfg edbg_cfg;
 	struct iwl_context_info_pnvm_cfg pnvm_cfg;
 	__le32 reserved2[16];
-	struct iwl_context_info_dram dram;
+	struct iwl_context_info_dram_nonfseq dram;
 	__le32 reserved3[16];
-} __packed;
+} __packed; /* BOOT_LOADER_CONTEXT_INFO_S */
 
-int iwl_pcie_ctxt_info_init(struct iwl_trans *trans, const struct fw_img *fw);
+int iwl_pcie_ctxt_info_init(struct iwl_trans *trans, const struct fw_img *img);
 void iwl_pcie_ctxt_info_free(struct iwl_trans *trans);
 void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans);
 int iwl_pcie_init_fw_sec(struct iwl_trans *trans,
 			 const struct fw_img *fw,
-			 struct iwl_context_info_dram *ctxt_dram);
+			 struct iwl_context_info_dram_nonfseq *ctxt_dram);
 void *iwl_pcie_ctxt_info_dma_alloc_coherent(struct iwl_trans *trans,
 					    size_t size,
 					    dma_addr_t *phys);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index be9e464c9b7b..0fd452cb94ae 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2016 Intel Deutschland GmbH
  */
@@ -107,6 +107,13 @@
 /* GIO Chicken Bits (PCI Express bus link power management) */
 #define CSR_GIO_CHICKEN_BITS    (CSR_BASE+0x100)
 
+#define CSR_IPC_STATE		(CSR_BASE + 0x110)
+#define CSR_IPC_STATE_RESET	0x00000030
+#define CSR_IPC_STATE_RESET_NONE		0
+#define CSR_IPC_STATE_RESET_SW_READY		1
+#define CSR_IPC_STATE_RESET_TOP_READY		2
+#define CSR_IPC_STATE_RESET_TOP_FOLLOWER	3
+
 #define CSR_IPC_SLEEP_CONTROL	(CSR_BASE + 0x114)
 #define CSR_IPC_SLEEP_CONTROL_SUSPEND	0x3
 #define CSR_IPC_SLEEP_CONTROL_RESUME	0
@@ -148,6 +155,7 @@
  * during a error FW error.
  */
 #define CSR_FUNC_SCRATCH_INIT_VALUE		(0x01010101)
+#define CSR_FUNC_SCRATCH_POWER_OFF_MASK		0xFFFF
 
 /* Bits for CSR_HW_IF_CONFIG_REG */
 #define CSR_HW_IF_CONFIG_REG_MSK_MAC_STEP_DASH	(0x0000000F)
@@ -193,17 +201,19 @@
 #define CSR_INT_BIT_RF_KILL      (1 << 7)  /* HW RFKILL switch GP_CNTRL[27] toggled */
 #define CSR_INT_BIT_CT_KILL      (1 << 6)  /* Critical temp (chip too hot) rfkill */
 #define CSR_INT_BIT_SW_RX        (1 << 3)  /* Rx, command responses */
+#define CSR_INT_BIT_RESET_DONE   (1 << 2)  /* reset handshake with firmware is done */
 #define CSR_INT_BIT_WAKEUP       (1 << 1)  /* NIC controller waking up (pwr mgmt) */
 #define CSR_INT_BIT_ALIVE        (1 << 0)  /* uCode interrupts once it initializes */
 
-#define CSR_INI_SET_MASK	(CSR_INT_BIT_FH_RX   | \
-				 CSR_INT_BIT_HW_ERR  | \
-				 CSR_INT_BIT_FH_TX   | \
-				 CSR_INT_BIT_SW_ERR  | \
-				 CSR_INT_BIT_RF_KILL | \
-				 CSR_INT_BIT_SW_RX   | \
-				 CSR_INT_BIT_WAKEUP  | \
-				 CSR_INT_BIT_ALIVE   | \
+#define CSR_INI_SET_MASK	(CSR_INT_BIT_FH_RX	| \
+				 CSR_INT_BIT_HW_ERR	| \
+				 CSR_INT_BIT_FH_TX	| \
+				 CSR_INT_BIT_SW_ERR	| \
+				 CSR_INT_BIT_RF_KILL	| \
+				 CSR_INT_BIT_SW_RX	| \
+				 CSR_INT_BIT_WAKEUP	| \
+				 CSR_INT_BIT_RESET_DONE	| \
+				 CSR_INT_BIT_ALIVE	| \
 				 CSR_INT_BIT_RX_PERIODIC)
 
 /* interrupt flags in FH (flow handler) (PCI busmaster DMA) */
@@ -640,7 +650,7 @@ enum msix_hw_int_causes {
  *                     HW address related registers                          *
  *****************************************************************************/
 
-#define CSR_ADDR_BASE(trans)			((trans)->cfg->mac_addr_from_csr)
+#define CSR_ADDR_BASE(trans)			((trans)->mac_cfg->base->mac_addr_from_csr)
 #define CSR_MAC_ADDR0_OTP(trans)		(CSR_ADDR_BASE(trans) + 0x00)
 #define CSR_MAC_ADDR1_OTP(trans)		(CSR_ADDR_BASE(trans) + 0x04)
 #define CSR_MAC_ADDR0_STRAP(trans)		(CSR_ADDR_BASE(trans) + 0x08)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index ce787326aa69..5c8f6dc9a3e0 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -503,7 +503,7 @@ void iwl_dbg_tlv_load_bin(struct device *dev, struct iwl_trans *trans)
 	int res;
 
 	if (!iwlwifi_mod_params.enable_ini ||
-	    trans->trans_cfg->device_family <= IWL_DEVICE_FAMILY_8000)
+	    trans->mac_cfg->device_family <= IWL_DEVICE_FAMILY_8000)
 		return;
 
 	res = firmware_request_nowarn(&fw, yoyo_bin, dev);
@@ -603,11 +603,11 @@ static int iwl_dbg_tlv_alloc_fragments(struct iwl_fw_runtime *fwrt,
 		return 0;
 
 	num_frags = le32_to_cpu(fw_mon_cfg->max_frags_num);
-	if (fwrt->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210) {
+	if (fwrt->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210) {
 		if (alloc_id != IWL_FW_INI_ALLOCATION_ID_DBGC1)
 			return -EIO;
 		num_frags = 1;
-	} else if (fwrt->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_BZ &&
+	} else if (fwrt->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_BZ &&
 			   alloc_id > IWL_FW_INI_ALLOCATION_ID_DBGC3) {
 		return -EIO;
 	}
@@ -1241,7 +1241,7 @@ iwl_dbg_tlv_tp_trigger(struct iwl_fw_runtime *fwrt, bool sync,
 
 		fwrt->trans->dbg.restart_required = false;
 
-		if (fwrt->trans->trans_cfg->device_family ==
+		if (fwrt->trans->mac_cfg->device_family ==
 		    IWL_DEVICE_FAMILY_9000) {
 			fwrt->trans->dbg.restart_required = true;
 		} else if (tp == IWL_FW_INI_TIME_POINT_FW_ASSERT &&
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.h b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.h
index 76166e1b10e5..99789c7cef3b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.h
@@ -3,7 +3,7 @@
  *
  * Copyright(c) 2009 - 2014 Intel Corporation. All rights reserved.
  * Copyright(C) 2016        Intel Deutschland GmbH
- * Copyright(c) 2018, 2023  Intel Corporation
+ * Copyright(c) 2018, 2023, 2025 Intel Corporation
  *****************************************************************************/
 
 #ifndef __IWLWIFI_DEVICE_TRACE
@@ -54,11 +54,11 @@ static inline size_t iwl_rx_trace_len(const struct iwl_trans *trans,
 	struct ieee80211_hdr *hdr = NULL;
 	size_t hdr_offset;
 
-	if (cmd->cmd != trans->rx_mpdu_cmd)
+	if (cmd->cmd != trans->conf.rx_mpdu_cmd)
 		return len;
 
 	hdr_offset = sizeof(struct iwl_cmd_header) +
-		     trans->rx_mpdu_cmd_hdr_size;
+		     trans->conf.rx_mpdu_cmd_hdr_size;
 
 	if (out_hdr_offset)
 		*out_hdr_offset = hdr_offset;
@@ -67,7 +67,8 @@ static inline size_t iwl_rx_trace_len(const struct iwl_trans *trans,
 	if (!ieee80211_is_data(hdr->frame_control))
 		return len;
 	/* maybe try to identify EAPOL frames? */
-	return sizeof(__le32) + sizeof(*cmd) + trans->rx_mpdu_cmd_hdr_size +
+	return sizeof(__le32) + sizeof(*cmd) +
+		trans->conf.rx_mpdu_cmd_hdr_size +
 		ieee80211_hdrlen(hdr->frame_control);
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index d36837501e08..9504a0cb8b13 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -176,25 +176,86 @@ static inline char iwl_drv_get_step(int step)
 
 static bool iwl_drv_is_wifi7_supported(struct iwl_trans *trans)
 {
-	return CSR_HW_RFID_TYPE(trans->hw_rf_id) >= IWL_CFG_RF_TYPE_FM;
+	return CSR_HW_RFID_TYPE(trans->info.hw_rf_id) >= IWL_CFG_RF_TYPE_FM;
 }
 
 const char *iwl_drv_get_fwname_pre(struct iwl_trans *trans, char *buf)
 {
 	char mac_step, rf_step;
-	const char *rf, *cdb;
+	const char *mac, *rf, *cdb;
 
 	if (trans->cfg->fw_name_pre)
 		return trans->cfg->fw_name_pre;
 
-	if (WARN_ON(!trans->cfg->fw_name_mac))
-		return "unconfigured";
+	mac_step = iwl_drv_get_step(trans->info.hw_rev_step);
 
-	mac_step = iwl_drv_get_step(trans->hw_rev_step);
+	switch (CSR_HW_REV_TYPE(trans->info.hw_rev)) {
+	case IWL_CFG_MAC_TYPE_PU:
+		mac = "9000-pu";
+		mac_step = 'b';
+		break;
+	case IWL_CFG_MAC_TYPE_TH:
+		mac = "9260-th";
+		mac_step = 'b';
+		break;
+	case IWL_CFG_MAC_TYPE_QU:
+		mac = "Qu";
+		break;
+	case IWL_CFG_MAC_TYPE_CC:
+		/* special case - no RF since it's fixed (discrete) */
+		scnprintf(buf, FW_NAME_PRE_BUFSIZE, "iwlwifi-cc-a0");
+		return buf;
+	case IWL_CFG_MAC_TYPE_QUZ:
+		mac = "QuZ";
+		/* all QuZ use A0 firmware */
+		mac_step = 'a';
+		break;
+	case IWL_CFG_MAC_TYPE_SO:
+	case IWL_CFG_MAC_TYPE_SOF:
+		mac = "so";
+		mac_step = 'a';
+		break;
+	case IWL_CFG_MAC_TYPE_TY:
+		mac = "ty";
+		mac_step = 'a';
+		break;
+	case IWL_CFG_MAC_TYPE_MA:
+		mac = "ma";
+		break;
+	case IWL_CFG_MAC_TYPE_BZ:
+	case IWL_CFG_MAC_TYPE_BZ_W:
+		mac = "bz";
+		break;
+	case IWL_CFG_MAC_TYPE_GL:
+		mac = "gl";
+		break;
+	case IWL_CFG_MAC_TYPE_SC:
+		mac = "sc";
+		break;
+	case IWL_CFG_MAC_TYPE_SC2:
+		mac = "sc2";
+		break;
+	case IWL_CFG_MAC_TYPE_SC2F:
+		mac = "sc2f";
+		break;
+	case IWL_CFG_MAC_TYPE_BR:
+		mac = "br";
+		break;
+	case IWL_CFG_MAC_TYPE_DR:
+		mac = "dr";
+		break;
+	default:
+		return "unknown-mac";
+	}
 
-	rf_step = iwl_drv_get_step(CSR_HW_RFID_STEP(trans->hw_rf_id));
+	rf_step = iwl_drv_get_step(CSR_HW_RFID_STEP(trans->info.hw_rf_id));
 
-	switch (CSR_HW_RFID_TYPE(trans->hw_rf_id)) {
+	switch (CSR_HW_RFID_TYPE(trans->info.hw_rf_id)) {
+	case IWL_CFG_RF_TYPE_JF1:
+	case IWL_CFG_RF_TYPE_JF2:
+		rf = "jf";
+		rf_step = 'b';
+		break;
 	case IWL_CFG_RF_TYPE_HR1:
 	case IWL_CFG_RF_TYPE_HR2:
 		rf = "hr";
@@ -202,29 +263,26 @@ const char *iwl_drv_get_fwname_pre(struct iwl_trans *trans, char *buf)
 		break;
 	case IWL_CFG_RF_TYPE_GF:
 		rf = "gf";
+		rf_step = 'a';
 		break;
 	case IWL_CFG_RF_TYPE_FM:
 		rf = "fm";
 		break;
 	case IWL_CFG_RF_TYPE_WH:
-		if (SILICON_Z_STEP ==
-		    CSR_HW_RFID_STEP(trans->hw_rf_id)) {
-			rf = "whtc";
-			rf_step = 'a';
-		} else {
-			rf = "wh";
-		}
+		rf = "wh";
+		break;
+	case IWL_CFG_RF_TYPE_PE:
+		rf = "pe";
 		break;
 	default:
 		return "unknown-rf";
 	}
 
-	cdb = CSR_HW_RFID_IS_CDB(trans->hw_rf_id) ? "4" : "";
+	cdb = CSR_HW_RFID_IS_CDB(trans->info.hw_rf_id) ? "4" : "";
 
 	scnprintf(buf, FW_NAME_PRE_BUFSIZE,
 		  "iwlwifi-%s-%c0-%s%s-%c0",
-		  trans->cfg->fw_name_mac, mac_step,
-		  rf, cdb, rf_step);
+		  mac, mac_step, rf, cdb, rf_step);
 
 	return buf;
 }
@@ -233,39 +291,64 @@ IWL_EXPORT_SYMBOL(iwl_drv_get_fwname_pre);
 static void iwl_req_fw_callback(const struct firmware *ucode_raw,
 				void *context);
 
+static void iwl_get_ucode_api_versions(struct iwl_trans *trans,
+				       unsigned int *api_min,
+				       unsigned int *api_max)
+{
+	const struct iwl_family_base_params *base = trans->mac_cfg->base;
+	const struct iwl_rf_cfg *cfg = trans->cfg;
+
+	if (!base->ucode_api_max) {
+		*api_min = cfg->ucode_api_min;
+		*api_max = cfg->ucode_api_max;
+		return;
+	}
+
+	if (!cfg->ucode_api_max) {
+		*api_min = base->ucode_api_min;
+		*api_max = base->ucode_api_max;
+		return;
+	}
+
+	*api_min = max(cfg->ucode_api_min, base->ucode_api_min);
+	*api_max = min(cfg->ucode_api_max, base->ucode_api_max);
+}
+
 static int iwl_request_firmware(struct iwl_drv *drv, bool first)
 {
-	const struct iwl_cfg *cfg = drv->trans->cfg;
 	char _fw_name_pre[FW_NAME_PRE_BUFSIZE];
+	unsigned int ucode_api_max, ucode_api_min;
 	const char *fw_name_pre;
 
-	if (drv->trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_9000 &&
-	    (drv->trans->hw_rev_step != SILICON_B_STEP &&
-	     drv->trans->hw_rev_step != SILICON_C_STEP)) {
+	iwl_get_ucode_api_versions(drv->trans, &ucode_api_min, &ucode_api_max);
+
+	if (drv->trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_9000 &&
+	    (drv->trans->info.hw_rev_step != SILICON_B_STEP &&
+	     drv->trans->info.hw_rev_step != SILICON_C_STEP)) {
 		IWL_ERR(drv,
 			"Only HW steps B and C are currently supported (0x%0x)\n",
-			drv->trans->hw_rev);
+			drv->trans->info.hw_rev);
 		return -EINVAL;
 	}
 
 	fw_name_pre = iwl_drv_get_fwname_pre(drv->trans, _fw_name_pre);
 
 	if (first)
-		drv->fw_index = cfg->ucode_api_max;
+		drv->fw_index = ucode_api_max;
 	else
 		drv->fw_index--;
 
-	if (drv->fw_index < cfg->ucode_api_min) {
+	if (drv->fw_index < ucode_api_min) {
 		IWL_ERR(drv, "no suitable firmware found!\n");
 
-		if (cfg->ucode_api_min == cfg->ucode_api_max) {
+		if (ucode_api_min == ucode_api_max) {
 			IWL_ERR(drv, "%s-%d is required\n", fw_name_pre,
-				cfg->ucode_api_max);
+				ucode_api_max);
 		} else {
 			IWL_ERR(drv, "minimum version required: %s-%d\n",
-				fw_name_pre, cfg->ucode_api_min);
+				fw_name_pre, ucode_api_min);
 			IWL_ERR(drv, "maximum version supported: %s-%d\n",
-				fw_name_pre, cfg->ucode_api_max);
+				fw_name_pre, ucode_api_max);
 		}
 
 		IWL_ERR(drv,
@@ -1235,7 +1318,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 
 			if (tlv_len != sizeof(*dbg_ptrs))
 				goto invalid_tlv_len;
-			if (drv->trans->trans_cfg->device_family <
+			if (drv->trans->mac_cfg->device_family <
 			    IWL_DEVICE_FAMILY_22000)
 				break;
 			drv->trans->dbg.umac_error_event_table =
@@ -1251,7 +1334,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 
 			if (tlv_len != sizeof(*dbg_ptrs))
 				goto invalid_tlv_len;
-			if (drv->trans->trans_cfg->device_family <
+			if (drv->trans->mac_cfg->device_family <
 			    IWL_DEVICE_FAMILY_22000)
 				break;
 			drv->trans->dbg.lmac_error_event_table[0] =
@@ -1373,7 +1456,7 @@ static int iwl_alloc_ucode(struct iwl_drv *drv,
 
 static int validate_sec_sizes(struct iwl_drv *drv,
 			      struct iwl_firmware_pieces *pieces,
-			      const struct iwl_cfg *cfg)
+			      const struct iwl_rf_cfg *cfg)
 {
 	IWL_DEBUG_INFO(drv, "f/w package hdr runtime inst size = %zd\n",
 		get_sec_size(pieces, IWL_UCODE_REGULAR,
@@ -1496,14 +1579,15 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 	struct iwlwifi_opmode_table *op;
 	int err;
 	struct iwl_firmware_pieces *pieces;
-	const unsigned int api_max = drv->trans->cfg->ucode_api_max;
-	const unsigned int api_min = drv->trans->cfg->ucode_api_min;
+	unsigned int api_min, api_max;
 	size_t trigger_tlv_sz[FW_DBG_TRIGGER_MAX];
 	u32 api_ver;
 	int i;
 	bool usniffer_images = false;
 	bool failure = true;
 
+	iwl_get_ucode_api_versions(drv->trans, &api_min, &api_max);
+
 	fw->ucode_capa.max_probe_length = IWL_DEFAULT_MAX_PROBE_LENGTH;
 	fw->ucode_capa.standard_phy_calibration_size =
 			IWL_DEFAULT_STANDARD_PHY_CALIBRATE_TBL_SIZE;
@@ -1697,14 +1781,14 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 		fw->init_evtlog_size = (pieces->init_evtlog_size - 16)/12;
 	else
 		fw->init_evtlog_size =
-			drv->trans->trans_cfg->base_params->max_event_log_size;
+			drv->trans->mac_cfg->base->max_event_log_size;
 	fw->init_errlog_ptr = pieces->init_errlog_ptr;
 	fw->inst_evtlog_ptr = pieces->inst_evtlog_ptr;
 	if (pieces->inst_evtlog_size)
 		fw->inst_evtlog_size = (pieces->inst_evtlog_size - 16)/12;
 	else
 		fw->inst_evtlog_size =
-			drv->trans->trans_cfg->base_params->max_event_log_size;
+			drv->trans->mac_cfg->base->max_event_log_size;
 	fw->inst_errlog_ptr = pieces->inst_errlog_ptr;
 
 	/*
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
index 854957bdf79d..595300a14639 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2020-2021, 2023 Intel Corporation
+ * Copyright (C) 2005-2014, 2020-2021, 2023, 2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  */
 #ifndef __iwl_drv_h__
@@ -53,7 +53,7 @@
 
 struct iwl_drv;
 struct iwl_trans;
-struct iwl_cfg;
+struct iwl_rf_cfg;
 /**
  * iwl_drv_start - start the drv
  *
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
index 5c8f1868db64..0f6de08b7473 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2018-2021, 2023-2024 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2021, 2023-2025 Intel Corporation
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
 #ifndef __iwl_fh_h__
@@ -71,7 +71,7 @@
 static inline unsigned int FH_MEM_CBBC_QUEUE(struct iwl_trans *trans,
 					     unsigned int chnl)
 {
-	if (trans->trans_cfg->gen2) {
+	if (trans->mac_cfg->gen2) {
 		WARN_ON_ONCE(chnl >= 64);
 		return TFH_TFDQ_CBB_TABLE + 8 * chnl;
 	}
@@ -378,14 +378,14 @@ static inline unsigned int FH_MEM_CBBC_QUEUE(struct iwl_trans *trans,
  * Once the RXF-to-DRAM DMA is active, this flag is immediately turned off.
  */
 #define RFH_GEN_STATUS		0xA09808
-#define RFH_GEN_STATUS_GEN3	0xA07824
+#define RFH_GEN_STATUS_AX210	0xA07824
 #define RBD_FETCH_IDLE	BIT(29)
 #define SRAM_DMA_IDLE	BIT(30)
 #define RXF_DMA_IDLE	BIT(31)
 
 /* DMA configuration */
 #define RFH_RXF_DMA_CFG		0xA09820
-#define RFH_RXF_DMA_CFG_GEN3	0xA07880
+#define RFH_RXF_DMA_CFG_AX210	0xA07880
 /* RB size */
 #define RFH_RXF_DMA_RB_SIZE_MASK (0x000F0000) /* bits 16-19 */
 #define RFH_RXF_DMA_RB_SIZE_POS 16
@@ -588,13 +588,12 @@ struct iwl_rb_status {
 
 
 #define TFD_QUEUE_SIZE_MAX      (256)
-#define TFD_QUEUE_SIZE_MAX_GEN3 (65536)
 /* cb size is the exponent - 3 */
 #define TFD_QUEUE_CB_SIZE(x)	(ilog2(x) - 3)
 #define TFD_QUEUE_SIZE_BC_DUP	(64)
 #define TFD_QUEUE_BC_SIZE	(TFD_QUEUE_SIZE_MAX + TFD_QUEUE_SIZE_BC_DUP)
-#define TFD_QUEUE_BC_SIZE_GEN3_AX210	1024
-#define TFD_QUEUE_BC_SIZE_GEN3_BZ	(1024 * 4)
+#define TFD_QUEUE_BC_SIZE_AX210	1024
+#define TFD_QUEUE_BC_SIZE_BZ	(1024 * 4)
 #define IWL_TX_DMA_MASK        DMA_BIT_MASK(36)
 #define IWL_NUM_OF_TBS		20
 #define IWL_TFH_NUM_TBS		25
@@ -717,30 +716,19 @@ struct iwl_tfh_tfd {
 /* Fixed (non-configurable) rx data from phy */
 
 /**
- * struct iwlagn_scd_bc_tbl - scheduler byte count table
+ * struct iwl_bc_tbl_entry - scheduler byte count table entry
  *	base physical address provided by SCD_DRAM_BASE_ADDR
  * For devices up to 22000:
  * @tfd_offset:
  *	For devices up to 22000:
  *		 0-12 - tx command byte count
  *		12-16 - station index
- *	For 22000:
+ *	For 22000 and on:
  *		 0-12 - tx command byte count
  *		12-13 - number of 64 byte chunks
  *		14-16 - reserved
  */
-struct iwlagn_scd_bc_tbl {
-	__le16 tfd_offset[TFD_QUEUE_BC_SIZE];
-} __packed;
-
-/**
- * struct iwl_gen3_bc_tbl_entry - scheduler byte count table entry gen3
- * For AX210 and on:
- * @tfd_offset: 0-12 - tx command byte count
- *		12-13 - number of 64 byte chunks
- *		14-16 - reserved
- */
-struct iwl_gen3_bc_tbl_entry {
+struct iwl_bc_tbl_entry {
 	__le16 tfd_offset;
 } __packed;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-io.c b/drivers/net/wireless/intel/iwlwifi/iwl-io.c
index 0653ca8b974a..80591809164e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-io.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-io.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2003-2014, 2018-2022, 2024 Intel Corporation
+ * Copyright (C) 2003-2014, 2018-2022, 2024-2025 Intel Corporation
  * Copyright (C) 2015-2016 Intel Deutschland GmbH
  */
 #include <linux/delay.h>
@@ -211,13 +211,13 @@ IWL_EXPORT_SYMBOL(iwl_clear_bits_prph);
 
 void iwl_force_nmi(struct iwl_trans *trans)
 {
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_9000)
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_9000)
 		iwl_write_prph_delay(trans, DEVICE_SET_NMI_REG,
 				     DEVICE_SET_NMI_VAL_DRV, 1);
-	else if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
+	else if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		iwl_write_umac_prph(trans, UREG_NIC_SET_NMI_DRIVER,
 				UREG_NIC_SET_NMI_DRIVER_NMI_FROM_DRIVER);
-	else if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_BZ)
+	else if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_BZ)
 		iwl_write_umac_prph(trans, UREG_DOORBELL_TO_ISR6,
 				    UREG_DOORBELL_TO_ISR6_NMI_BIT);
 	else
@@ -260,7 +260,7 @@ struct reg {
 static int iwl_dump_rfh(struct iwl_trans *trans, char **buf)
 {
 	int i, q;
-	int num_q = trans->num_rx_queues;
+	int num_q = trans->info.num_rxqs;
 	static const u32 rfh_tbl[] = {
 		RFH_RXF_DMA_CFG,
 		RFH_GEN_CFG,
@@ -368,7 +368,7 @@ int iwl_dump_fh(struct iwl_trans *trans, char **buf)
 		FH_TSSR_TX_ERROR_REG
 	};
 
-	if (trans->trans_cfg->mq_rx_supported)
+	if (trans->mac_cfg->mq_rx_supported)
 		return iwl_dump_rfh(trans, buf);
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
@@ -423,7 +423,7 @@ static void iwl_dump_host_monitor_block(struct iwl_trans *trans,
 
 static void iwl_dump_host_monitor(struct iwl_trans *trans)
 {
-	switch (trans->trans_cfg->device_family) {
+	switch (trans->mac_cfg->device_family) {
 	case IWL_DEVICE_FAMILY_22000:
 	case IWL_DEVICE_FAMILY_AX210:
 		IWL_ERR(trans, "CSR_RESET = 0x%x\n",
@@ -445,11 +445,11 @@ static void iwl_dump_host_monitor(struct iwl_trans *trans)
 
 int iwl_finish_nic_init(struct iwl_trans *trans)
 {
-	const struct iwl_cfg_trans_params *cfg_trans = trans->trans_cfg;
+	const struct iwl_mac_cfg *mac_cfg = trans->mac_cfg;
 	u32 poll_ready;
 	int err;
 
-	if (cfg_trans->bisr_workaround) {
+	if (mac_cfg->bisr_workaround) {
 		/* ensure the TOP FSM isn't still in previous reset */
 		mdelay(2);
 	}
@@ -458,7 +458,7 @@ int iwl_finish_nic_init(struct iwl_trans *trans)
 	 * Set "initialization complete" bit to move adapter from
 	 * D0U* --> D0A* (powered-up active) state.
 	 */
-	if (cfg_trans->device_family >= IWL_DEVICE_FAMILY_BZ) {
+	if (mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
 		iwl_set_bit(trans, CSR_GP_CNTRL,
 			    CSR_GP_CNTRL_REG_FLAG_BZ_MAC_ACCESS_REQ |
 			    CSR_GP_CNTRL_REG_FLAG_MAC_INIT);
@@ -469,7 +469,7 @@ int iwl_finish_nic_init(struct iwl_trans *trans)
 		poll_ready = CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY;
 	}
 
-	if (cfg_trans->device_family == IWL_DEVICE_FAMILY_8000)
+	if (mac_cfg->device_family == IWL_DEVICE_FAMILY_8000)
 		udelay(2);
 
 	/*
@@ -484,7 +484,7 @@ int iwl_finish_nic_init(struct iwl_trans *trans)
 		iwl_dump_host_monitor(trans);
 	}
 
-	if (cfg_trans->bisr_workaround) {
+	if (mac_cfg->bisr_workaround) {
 		/* ensure BISR shift has finished */
 		udelay(200);
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-io.h b/drivers/net/wireless/intel/iwlwifi/iwl-io.h
index 37b3bd62897e..f4833c5fe86e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-io.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-io.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2018-2021 Intel Corporation
+ * Copyright (C) 2018-2021, 2025 Intel Corporation
  */
 #ifndef __iwl_io_h__
 #define __iwl_io_h__
@@ -64,38 +64,38 @@ int iwl_dump_fh(struct iwl_trans *trans, char **buf);
  */
 static inline u32 iwl_umac_prph(struct iwl_trans *trans, u32 ofs)
 {
-	return ofs + trans->trans_cfg->umac_prph_offset;
+	return ofs + trans->mac_cfg->umac_prph_offset;
 }
 
 static inline u32 iwl_read_umac_prph_no_grab(struct iwl_trans *trans, u32 ofs)
 {
 	return iwl_read_prph_no_grab(trans, ofs +
-				     trans->trans_cfg->umac_prph_offset);
+				     trans->mac_cfg->umac_prph_offset);
 }
 
 static inline u32 iwl_read_umac_prph(struct iwl_trans *trans, u32 ofs)
 {
-	return iwl_read_prph(trans, ofs + trans->trans_cfg->umac_prph_offset);
+	return iwl_read_prph(trans, ofs + trans->mac_cfg->umac_prph_offset);
 }
 
 static inline void iwl_write_umac_prph_no_grab(struct iwl_trans *trans, u32 ofs,
 					       u32 val)
 {
-	iwl_write_prph_no_grab(trans,  ofs + trans->trans_cfg->umac_prph_offset,
+	iwl_write_prph_no_grab(trans,  ofs + trans->mac_cfg->umac_prph_offset,
 			       val);
 }
 
 static inline void iwl_write_umac_prph(struct iwl_trans *trans, u32 ofs,
 				       u32 val)
 {
-	iwl_write_prph(trans,  ofs + trans->trans_cfg->umac_prph_offset, val);
+	iwl_write_prph(trans,  ofs + trans->mac_cfg->umac_prph_offset, val);
 }
 
 static inline int iwl_poll_umac_prph_bit(struct iwl_trans *trans, u32 addr,
 					 u32 bits, u32 mask, int timeout)
 {
 	return iwl_poll_prph_bit(trans, addr +
-				 trans->trans_cfg->umac_prph_offset,
+				 trans->mac_cfg->umac_prph_offset,
 				 bits, mask, timeout);
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index cd1b0048bb6d..0592f0f59d1c 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -143,6 +143,9 @@ static struct ieee80211_rate iwl_cfg80211_rates[] = {
  * @NVM_CHANNEL_VALID: channel is usable for this SKU/geo
  * @NVM_CHANNEL_IBSS: usable as an IBSS channel and deprecated
  *	when %IWL_NVM_SBANDS_FLAGS_LAR enabled.
+ * @NVM_CHANNEL_ALLOW_20MHZ_ACTIVITY: active scanning allowed and
+ *	AP allowed only in 20 MHz. Valid only
+ *	when %IWL_NVM_SBANDS_FLAGS_LAR enabled.
  * @NVM_CHANNEL_ACTIVE: active scanning allowed and allows IBSS
  *	when %IWL_NVM_SBANDS_FLAGS_LAR enabled.
  * @NVM_CHANNEL_RADAR: radar detection required
@@ -159,20 +162,21 @@ static struct ieee80211_rate iwl_cfg80211_rates[] = {
  * @NVM_CHANNEL_AFC: client support connection to UHB AFC AP
  */
 enum iwl_nvm_channel_flags {
-	NVM_CHANNEL_VALID		= BIT(0),
-	NVM_CHANNEL_IBSS		= BIT(1),
-	NVM_CHANNEL_ACTIVE		= BIT(3),
-	NVM_CHANNEL_RADAR		= BIT(4),
-	NVM_CHANNEL_INDOOR_ONLY		= BIT(5),
-	NVM_CHANNEL_GO_CONCURRENT	= BIT(6),
-	NVM_CHANNEL_UNIFORM		= BIT(7),
-	NVM_CHANNEL_20MHZ		= BIT(8),
-	NVM_CHANNEL_40MHZ		= BIT(9),
-	NVM_CHANNEL_80MHZ		= BIT(10),
-	NVM_CHANNEL_160MHZ		= BIT(11),
-	NVM_CHANNEL_DC_HIGH		= BIT(12),
-	NVM_CHANNEL_VLP			= BIT(13),
-	NVM_CHANNEL_AFC			= BIT(14),
+	NVM_CHANNEL_VALID                   = BIT(0),
+	NVM_CHANNEL_IBSS                    = BIT(1),
+	NVM_CHANNEL_ALLOW_20MHZ_ACTIVITY    = BIT(2),
+	NVM_CHANNEL_ACTIVE                  = BIT(3),
+	NVM_CHANNEL_RADAR                   = BIT(4),
+	NVM_CHANNEL_INDOOR_ONLY             = BIT(5),
+	NVM_CHANNEL_GO_CONCURRENT           = BIT(6),
+	NVM_CHANNEL_UNIFORM                 = BIT(7),
+	NVM_CHANNEL_20MHZ                   = BIT(8),
+	NVM_CHANNEL_40MHZ                   = BIT(9),
+	NVM_CHANNEL_80MHZ                   = BIT(10),
+	NVM_CHANNEL_160MHZ                  = BIT(11),
+	NVM_CHANNEL_DC_HIGH                 = BIT(12),
+	NVM_CHANNEL_VLP                     = BIT(13),
+	NVM_CHANNEL_AFC                     = BIT(14),
 };
 
 /**
@@ -332,7 +336,7 @@ static inline void iwl_nvm_print_channel_flags(struct device *dev, u32 level,
 }
 
 static u32 iwl_get_channel_flags(u8 ch_num, int ch_idx, enum nl80211_band band,
-				 u32 nvm_flags, const struct iwl_cfg *cfg)
+				 u32 nvm_flags, const struct iwl_rf_cfg *cfg)
 {
 	u32 flags = IEEE80211_CHAN_NO_HT40;
 
@@ -399,7 +403,7 @@ static int iwl_init_channel_map(struct iwl_trans *trans,
 				const void * const nvm_ch_flags,
 				u32 sbands_flags, bool v4)
 {
-	const struct iwl_cfg *cfg = trans->cfg;
+	const struct iwl_rf_cfg *cfg = trans->cfg;
 	struct device *dev = trans->dev;
 	int ch_idx;
 	int n_channels = 0;
@@ -500,7 +504,7 @@ static void iwl_init_vht_hw_capab(struct iwl_trans *trans,
 				  struct ieee80211_sta_vht_cap *vht_cap,
 				  u8 tx_chains, u8 rx_chains)
 {
-	const struct iwl_cfg *cfg = trans->cfg;
+	const struct iwl_rf_cfg *cfg = trans->cfg;
 	int num_rx_ants = num_of_ant(rx_chains);
 	int num_tx_ants = num_of_ant(tx_chains);
 
@@ -513,7 +517,7 @@ static void iwl_init_vht_hw_capab(struct iwl_trans *trans,
 		       IEEE80211_VHT_MAX_AMPDU_1024K <<
 		       IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT;
 
-	if (!trans->cfg->ht_params->stbc)
+	if (!trans->cfg->ht_params.stbc)
 		vht_cap->cap &= ~IEEE80211_VHT_CAP_RXSTBC_MASK;
 
 	if (data->vht160_supported)
@@ -523,7 +527,7 @@ static void iwl_init_vht_hw_capab(struct iwl_trans *trans,
 	if (cfg->vht_mu_mimo_supported)
 		vht_cap->cap |= IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE;
 
-	if (cfg->ht_params->ldpc)
+	if (cfg->ht_params.ldpc)
 		vht_cap->cap |= IEEE80211_VHT_CAP_RXLDPC;
 
 	if (data->sku_cap_mimo_disabled) {
@@ -531,21 +535,21 @@ static void iwl_init_vht_hw_capab(struct iwl_trans *trans,
 		num_tx_ants = 1;
 	}
 
-	if (trans->cfg->ht_params->stbc && num_tx_ants > 1)
+	if (trans->cfg->ht_params.stbc && num_tx_ants > 1)
 		vht_cap->cap |= IEEE80211_VHT_CAP_TXSTBC;
 	else
 		vht_cap->cap |= IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN;
 
 	switch (iwlwifi_mod_params.amsdu_size) {
 	case IWL_AMSDU_DEF:
-		if (trans->trans_cfg->mq_rx_supported)
+		if (trans->mac_cfg->mq_rx_supported)
 			vht_cap->cap |=
 				IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454;
 		else
 			vht_cap->cap |= IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895;
 		break;
 	case IWL_AMSDU_2K:
-		if (trans->trans_cfg->mq_rx_supported)
+		if (trans->mac_cfg->mq_rx_supported)
 			vht_cap->cap |=
 				IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454;
 		else
@@ -916,8 +920,8 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 {
 	bool is_ap = iftype_data->types_mask & (BIT(NL80211_IFTYPE_AP) |
 						BIT(NL80211_IFTYPE_P2P_GO));
-	bool slow_pcie = (!trans->trans_cfg->integrated &&
-			  trans->pcie_link_speed < PCI_EXP_LNKSTA_CLS_8_0GB);
+	bool slow_pcie = (!trans->mac_cfg->integrated &&
+			  trans->info.pcie_link_speed < PCI_EXP_LNKSTA_CLS_8_0GB);
 
 	if (!data->sku_cap_11be_enable || iwlwifi_mod_params.disable_11be)
 		iftype_data->eht_cap.has_eht = false;
@@ -945,7 +949,7 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 		break;
 	case NL80211_BAND_6GHZ:
 		if (!trans->reduced_cap_sku &&
-		    trans->bw_limit >= 320) {
+		    (!trans->cfg->bw_limit || trans->cfg->bw_limit >= 320)) {
 			iftype_data->eht_cap.eht_cap_elem.phy_cap_info[0] |=
 				IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ;
 			iftype_data->eht_cap.eht_cap_elem.phy_cap_info[1] |=
@@ -1032,11 +1036,11 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 			cpu_to_le16(IEEE80211_HE_MCS_NOT_SUPPORTED << 2);
 	}
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210 && !is_ap)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210 && !is_ap)
 		iftype_data->he_cap.he_cap_elem.phy_cap_info[2] |=
 			IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO;
 
-	switch (CSR_HW_RFID_TYPE(trans->hw_rf_id)) {
+	switch (CSR_HW_RFID_TYPE(trans->info.hw_rf_id)) {
 	case IWL_CFG_RF_TYPE_GF:
 	case IWL_CFG_RF_TYPE_FM:
 	case IWL_CFG_RF_TYPE_WH:
@@ -1048,7 +1052,7 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 		break;
 	}
 
-	if (CSR_HW_REV_TYPE(trans->hw_rev) == IWL_CFG_MAC_TYPE_GL &&
+	if (CSR_HW_REV_TYPE(trans->info.hw_rev) == IWL_CFG_MAC_TYPE_GL &&
 	    iftype_data->eht_cap.has_eht) {
 		iftype_data->eht_cap.eht_cap_elem.mac_cap_info[0] &=
 			~(IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
@@ -1077,13 +1081,13 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 		iftype_data->he_cap.he_cap_elem.mac_cap_info[2] |=
 			IEEE80211_HE_MAC_CAP2_BCAST_TWT;
 
-	if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000 &&
+	if (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_22000 &&
 	    !is_ap) {
 		iftype_data->vendor_elems.data = iwl_vendor_caps;
 		iftype_data->vendor_elems.len = ARRAY_SIZE(iwl_vendor_caps);
 	}
 
-	if (!trans->cfg->ht_params->stbc) {
+	if (!trans->cfg->ht_params.stbc) {
 		iftype_data->he_cap.he_cap_elem.phy_cap_info[2] &=
 			~IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ;
 		iftype_data->he_cap.he_cap_elem.phy_cap_info[7] &=
@@ -1095,11 +1099,12 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 		iftype_data->eht_cap.eht_mcs_nss_supp.bw._320.rx_tx_mcs13_max_nss = 0;
 	}
 
-	if (trans->bw_limit < 160)
+	if (trans->cfg->bw_limit && trans->cfg->bw_limit < 160)
 		iftype_data->he_cap.he_cap_elem.phy_cap_info[0] &=
 			~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G;
 
-	if (trans->bw_limit < 320 || trans->reduced_cap_sku) {
+	if ((trans->cfg->bw_limit && trans->cfg->bw_limit < 320) ||
+	    trans->reduced_cap_sku) {
 		memset(&iftype_data->eht_cap.eht_mcs_nss_supp.bw._320, 0,
 		       sizeof(iftype_data->eht_cap.eht_mcs_nss_supp.bw._320));
 		iftype_data->eht_cap.eht_cap_elem.phy_cap_info[2] &=
@@ -1246,7 +1251,7 @@ static void iwl_init_sbands(struct iwl_trans *trans,
 			    n_used, n_channels);
 }
 
-static int iwl_get_sku(const struct iwl_cfg *cfg, const __le16 *nvm_sw,
+static int iwl_get_sku(const struct iwl_rf_cfg *cfg, const __le16 *nvm_sw,
 		       const __le16 *phy_sku)
 {
 	if (cfg->nvm_type != IWL_NVM_EXT)
@@ -1255,7 +1260,7 @@ static int iwl_get_sku(const struct iwl_cfg *cfg, const __le16 *nvm_sw,
 	return le32_to_cpup((const __le32 *)(phy_sku + SKU_FAMILY_8000));
 }
 
-static int iwl_get_nvm_version(const struct iwl_cfg *cfg, const __le16 *nvm_sw)
+static int iwl_get_nvm_version(const struct iwl_rf_cfg *cfg, const __le16 *nvm_sw)
 {
 	if (cfg->nvm_type != IWL_NVM_EXT)
 		return le16_to_cpup(nvm_sw + NVM_VERSION);
@@ -1264,7 +1269,7 @@ static int iwl_get_nvm_version(const struct iwl_cfg *cfg, const __le16 *nvm_sw)
 						     NVM_VERSION_EXT_NVM));
 }
 
-static int iwl_get_radio_cfg(const struct iwl_cfg *cfg, const __le16 *nvm_sw,
+static int iwl_get_radio_cfg(const struct iwl_rf_cfg *cfg, const __le16 *nvm_sw,
 			     const __le16 *phy_sku)
 {
 	if (cfg->nvm_type != IWL_NVM_EXT)
@@ -1274,7 +1279,7 @@ static int iwl_get_radio_cfg(const struct iwl_cfg *cfg, const __le16 *nvm_sw,
 
 }
 
-static int iwl_get_n_hw_addrs(const struct iwl_cfg *cfg, const __le16 *nvm_sw)
+static int iwl_get_n_hw_addrs(const struct iwl_rf_cfg *cfg, const __le16 *nvm_sw)
 {
 	int n_hw_addr;
 
@@ -1286,7 +1291,7 @@ static int iwl_get_n_hw_addrs(const struct iwl_cfg *cfg, const __le16 *nvm_sw)
 	return n_hw_addr & N_HW_ADDR_MASK;
 }
 
-static void iwl_set_radio_cfg(const struct iwl_cfg *cfg,
+static void iwl_set_radio_cfg(const struct iwl_rf_cfg *cfg,
 			      struct iwl_nvm_data *data,
 			      u32 radio_cfg)
 {
@@ -1345,7 +1350,7 @@ static void iwl_set_hw_address_from_csr(struct iwl_trans *trans,
 }
 
 static void iwl_set_hw_address_family_8000(struct iwl_trans *trans,
-					   const struct iwl_cfg *cfg,
+					   const struct iwl_rf_cfg *cfg,
 					   struct iwl_nvm_data *data,
 					   const __le16 *mac_override,
 					   const __be16 *nvm_hw)
@@ -1394,11 +1399,12 @@ static void iwl_set_hw_address_family_8000(struct iwl_trans *trans,
 }
 
 static int iwl_set_hw_address(struct iwl_trans *trans,
-			      const struct iwl_cfg *cfg,
+			      const struct iwl_rf_cfg *cfg,
 			      struct iwl_nvm_data *data, const __be16 *nvm_hw,
 			      const __le16 *mac_override)
 {
-	if (cfg->mac_addr_from_csr) {
+	const struct iwl_mac_cfg *mac_cfg = trans->mac_cfg;
+	if (mac_cfg->base->mac_addr_from_csr) {
 		iwl_set_hw_address_from_csr(trans, data);
 	} else if (cfg->nvm_type != IWL_NVM_EXT) {
 		const u8 *hw_addr = (const u8 *)(nvm_hw + HW_ADDR);
@@ -1428,7 +1434,7 @@ static int iwl_set_hw_address(struct iwl_trans *trans,
 }
 
 static bool
-iwl_nvm_no_wide_in_5ghz(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+iwl_nvm_no_wide_in_5ghz(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg,
 			const __be16 *nvm_hw)
 {
 	/*
@@ -1440,7 +1446,7 @@ iwl_nvm_no_wide_in_5ghz(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	 * in 5GHz otherwise the FW will throw a sysassert when we try
 	 * to use them.
 	 */
-	if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_7000) {
+	if (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_7000) {
 		/*
 		 * Unlike the other sections in the NVM, the hw
 		 * section uses big-endian.
@@ -1460,7 +1466,7 @@ iwl_nvm_no_wide_in_5ghz(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 }
 
 struct iwl_nvm_data *
-iwl_parse_mei_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+iwl_parse_mei_nvm_data(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg,
 		       const struct iwl_mei_nvm *mei_nvm,
 		       const struct iwl_fw *fw, u8 tx_ant, u8 rx_ant)
 {
@@ -1524,7 +1530,7 @@ iwl_parse_mei_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 IWL_EXPORT_SYMBOL(iwl_parse_mei_nvm_data);
 
 struct iwl_nvm_data *
-iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg,
 		   const struct iwl_fw *fw,
 		   const __be16 *nvm_hw, const __le16 *nvm_sw,
 		   const __le16 *nvm_calib, const __le16 *regulatory,
@@ -1624,7 +1630,7 @@ IWL_EXPORT_SYMBOL(iwl_parse_nvm_data);
 static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
 				       int ch_idx, u16 nvm_flags,
 				       struct iwl_reg_capa reg_capa,
-				       const struct iwl_cfg *cfg)
+				       const struct iwl_rf_cfg *cfg)
 {
 	u32 flags = NL80211_RRF_NO_HT40;
 
@@ -1659,6 +1665,10 @@ static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
 	if (nvm_flags & NVM_CHANNEL_INDOOR_ONLY)
 		flags |= NL80211_RRF_NO_OUTDOOR;
 
+	if (nvm_flags & NVM_CHANNEL_ALLOW_20MHZ_ACTIVITY &&
+	    flags & NL80211_RRF_NO_IR)
+		flags |= NL80211_RRF_ALLOW_20MHZ_ACTIVITY;
+
 	/* Set the GO concurrent flag only in case that NO_IR is set.
 	 * Otherwise it is meaningless
 	 */
@@ -1735,10 +1745,12 @@ static struct iwl_reg_capa iwl_get_reg_capa(u32 flags, u8 resp_ver)
 }
 
 struct ieee80211_regdomain *
-iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
+iwl_parse_nvm_mcc_info(struct iwl_trans *trans,
 		       int num_of_ch, __le32 *channels, u16 fw_mcc,
 		       u16 geo_info, u32 cap, u8 resp_ver)
 {
+	const struct iwl_rf_cfg *cfg = trans->cfg;
+	struct device *dev = trans->dev;
 	int ch_idx;
 	u16 ch_flags;
 	u32 reg_rule_flags, prev_reg_rule_flags = 0;
@@ -1993,8 +2005,8 @@ int iwl_read_external_nvm(struct iwl_trans *trans,
 			 le32_to_cpu(dword_buff[3]));
 
 		/* nvm file validation, dword_buff[2] holds the file version */
-		if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_8000 &&
-		    trans->hw_rev_step == SILICON_C_STEP &&
+		if (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_8000 &&
+		    trans->info.hw_rev_step == SILICON_C_STEP &&
 		    le32_to_cpu(dword_buff[2]) < 0xE4A) {
 			ret = -EFAULT;
 			goto out;
@@ -2061,7 +2073,7 @@ int iwl_read_external_nvm(struct iwl_trans *trans,
 			break;
 		}
 
-		iwl_nvm_fixups(trans->hw_id, section_id, temp, section_size);
+		iwl_nvm_fixups(trans->info.hw_id, section_id, temp, section_size);
 
 		kfree(nvm_sections[section_id].data);
 		nvm_sections[section_id].data = temp;
@@ -2164,7 +2176,7 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans,
 		!!(mac_flags & NVM_MAC_SKU_FLAGS_BAND_5_2_ENABLED);
 	nvm->sku_cap_mimo_disabled =
 		!!(mac_flags & NVM_MAC_SKU_FLAGS_MIMO_DISABLED);
-	if (CSR_HW_RFID_TYPE(trans->hw_rf_id) >= IWL_CFG_RF_TYPE_FM)
+	if (CSR_HW_RFID_TYPE(trans->info.hw_rf_id) >= IWL_CFG_RF_TYPE_FM)
 		nvm->sku_cap_11be_enable = true;
 
 	/* Initialize PHY sku data */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
index 0c6c3fb8c6dd..9ce9fa4e78fd 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2015, 2018-2024 Intel Corporation
+ * Copyright (C) 2005-2015, 2018-2025 Intel Corporation
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
 #ifndef __iwl_nvm_parse_h__
@@ -30,7 +30,7 @@ enum iwl_nvm_sbands_flags {
  * later with iwl_free_nvm_data().
  */
 struct iwl_nvm_data *
-iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg,
 		   const struct iwl_fw *fw,
 		   const __be16 *nvm_hw, const __le16 *nvm_sw,
 		   const __le16 *nvm_calib, const __le16 *regulatory,
@@ -46,9 +46,17 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
  * accordingly. An ERR_PTR is returned on error.
  * If not given to the regulatory core, the user is responsible for freeing
  * the regdomain returned here with kfree.
+ *
+ * @trans: the transport
+ * @num_of_ch: the number of channels
+ * @channels: channel map
+ * @fw_mcc: firmware country code
+ * @geo_info: geo info value
+ * @cap: capability
+ * @resp_ver: FW response version
  */
 struct ieee80211_regdomain *
-iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
+iwl_parse_nvm_mcc_info(struct iwl_trans *trans,
 		       int num_of_ch, __le32 *channels, u16 fw_mcc,
 		       u16 geo_info, u32 cap, u8 resp_ver);
 
@@ -87,7 +95,7 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans,
  * iwl_parse_mei_nvm_data - parse the mei_nvm_data and get an iwl_nvm_data
  */
 struct iwl_nvm_data *
-iwl_parse_mei_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+iwl_parse_mei_nvm_data(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg,
 		       const struct iwl_mei_nvm *mei_nvm,
 		       const struct iwl_fw *fw, u8 set_tx_ant, u8 set_rx_ant);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-utils.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-utils.c
index b3c25acd3691..ec312c90ff85 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-utils.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014, 2018-2021, 2023 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2021, 2023, 2025 Intel Corporation
  * Copyright (C) 2015 Intel Mobile Communications GmbH
  */
 #include <linux/types.h>
@@ -42,7 +42,7 @@ void iwl_init_ht_hw_capab(struct iwl_trans *trans,
 			  enum nl80211_band band,
 			  u8 tx_chains, u8 rx_chains)
 {
-	const struct iwl_cfg *cfg = trans->cfg;
+	const struct iwl_rf_cfg *cfg = trans->cfg;
 	int max_bit_rate = 0;
 
 	tx_chains = hweight8(tx_chains);
@@ -53,7 +53,8 @@ void iwl_init_ht_hw_capab(struct iwl_trans *trans,
 
 	if (!(data->sku_cap_11n_enable) ||
 	    (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_ALL) ||
-	    !cfg->ht_params) {
+	    /* there are no devices with HT but without HT40 entirely */
+	    !cfg->ht_params.ht40_bands) {
 		ht_info->ht_supported = false;
 		return;
 	}
@@ -64,17 +65,17 @@ void iwl_init_ht_hw_capab(struct iwl_trans *trans,
 	ht_info->ht_supported = true;
 	ht_info->cap = IEEE80211_HT_CAP_DSSSCCK40;
 
-	if (cfg->ht_params->stbc) {
+	if (cfg->ht_params.stbc) {
 		ht_info->cap |= (1 << IEEE80211_HT_CAP_RX_STBC_SHIFT);
 
 		if (tx_chains > 1)
 			ht_info->cap |= IEEE80211_HT_CAP_TX_STBC;
 	}
 
-	if (cfg->ht_params->ldpc)
+	if (cfg->ht_params.ldpc)
 		ht_info->cap |= IEEE80211_HT_CAP_LDPC_CODING;
 
-	if (trans->trans_cfg->mq_rx_supported ||
+	if (trans->mac_cfg->mq_rx_supported ||
 	    iwlwifi_mod_params.amsdu_size >= IWL_AMSDU_8K)
 		ht_info->cap |= IEEE80211_HT_CAP_MAX_AMSDU;
 
@@ -90,13 +91,13 @@ void iwl_init_ht_hw_capab(struct iwl_trans *trans,
 	if (rx_chains >= 3)
 		ht_info->mcs.rx_mask[2] = 0xFF;
 
-	if (cfg->ht_params->ht_greenfield_support)
+	if (cfg->ht_params.ht_greenfield_support)
 		ht_info->cap |= IEEE80211_HT_CAP_GRN_FLD;
 	ht_info->cap |= IEEE80211_HT_CAP_SGI_20;
 
 	max_bit_rate = MAX_BIT_RATE_20_MHZ;
 
-	if (cfg->ht_params->ht40_bands & BIT(band)) {
+	if (cfg->ht_params.ht40_bands & BIT(band)) {
 		ht_info->cap |= IEEE80211_HT_CAP_SUP_WIDTH_20_40;
 		ht_info->cap |= IEEE80211_HT_CAP_SGI_40;
 		max_bit_rate = MAX_BIT_RATE_40_MHZ;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
index 34eca1a568ea..5dc299296d6d 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2018-2021, 2024 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2021, 2024-2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015 Intel Deutschland GmbH
  */
@@ -17,7 +17,7 @@ struct sk_buff;
 struct iwl_device_cmd;
 struct iwl_rx_cmd_buffer;
 struct iwl_fw;
-struct iwl_cfg;
+struct iwl_rf_cfg;
 
 /**
  * DOC: Operational mode - what is it ?
@@ -52,12 +52,20 @@ struct iwl_cfg;
  *	any debug collection must happen synchronously as
  *	the device will be shut down
  * @IWL_ERR_TYPE_CMD_QUEUE_FULL: command queue was full
+ * @IWL_ERR_TYPE_TOP_RESET_BY_BT: TOP reset initiated by BT
+ * @IWL_ERR_TYPE_TOP_FATAL_ERROR: TOP fatal error
+ * @IWL_ERR_TYPE_TOP_RESET_FAILED: TOP reset failed
+ * @IWL_ERR_TYPE_DEBUGFS: error/reset indication from debugfs
  */
 enum iwl_fw_error_type {
 	IWL_ERR_TYPE_IRQ,
 	IWL_ERR_TYPE_NMI_FORCED,
 	IWL_ERR_TYPE_RESET_HS_TIMEOUT,
 	IWL_ERR_TYPE_CMD_QUEUE_FULL,
+	IWL_ERR_TYPE_TOP_RESET_BY_BT,
+	IWL_ERR_TYPE_TOP_FATAL_ERROR,
+	IWL_ERR_TYPE_TOP_RESET_FAILED,
+	IWL_ERR_TYPE_DEBUGFS,
 };
 
 /**
@@ -142,7 +150,7 @@ struct iwl_fw_error_dump_mode {
  */
 struct iwl_op_mode_ops {
 	struct iwl_op_mode *(*start)(struct iwl_trans *trans,
-				     const struct iwl_cfg *cfg,
+				     const struct iwl_rf_cfg *cfg,
 				     const struct iwl_fw *fw,
 				     struct dentry *dbgfs_dir);
 	void (*stop)(struct iwl_op_mode *op_mode);
@@ -242,6 +250,9 @@ static inline void iwl_op_mode_dump_error(struct iwl_op_mode *op_mode,
 {
 	might_sleep();
 
+	if (WARN_ON(mode->type == IWL_ERR_TYPE_TOP_RESET_BY_BT))
+		return;
+
 	if (op_mode->ops->dump_error)
 		op_mode->ops->dump_error(op_mode, mode);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index c1607b6d0759..8a40801cf0dd 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -15,12 +15,13 @@
 #include <linux/dmapool.h>
 #include "fw/api/commands.h"
 #include "pcie/internal.h"
-#include "iwl-context-info-gen3.h"
+#include "iwl-context-info-v2.h"
 
 struct iwl_trans_dev_restart_data {
 	struct list_head list;
 	unsigned int restart_count;
 	time64_t last_error;
+	bool backoff;
 	char name[];
 };
 
@@ -81,14 +82,14 @@ void iwl_trans_free_restart_list(void)
 
 struct iwl_trans_reprobe {
 	struct device *dev;
-	struct work_struct work;
+	struct delayed_work work;
 };
 
 static void iwl_trans_reprobe_wk(struct work_struct *wk)
 {
 	struct iwl_trans_reprobe *reprobe;
 
-	reprobe = container_of(wk, typeof(*reprobe), work);
+	reprobe = container_of(wk, typeof(*reprobe), work.work);
 
 	if (device_reprobe(reprobe->dev))
 		dev_err(reprobe->dev, "reprobe failed!\n");
@@ -97,6 +98,31 @@ static void iwl_trans_reprobe_wk(struct work_struct *wk)
 	module_put(THIS_MODULE);
 }
 
+static void iwl_trans_schedule_reprobe(struct iwl_trans *trans,
+				       unsigned int delay_ms)
+{
+	struct iwl_trans_reprobe *reprobe;
+
+	/*
+	 * get a module reference to avoid doing this while unloading
+	 * anyway and to avoid scheduling a work with code that's
+	 * being removed.
+	 */
+	if (!try_module_get(THIS_MODULE)) {
+		IWL_ERR(trans, "Module is being unloaded - abort\n");
+		return;
+	}
+
+	reprobe = kzalloc(sizeof(*reprobe), GFP_KERNEL);
+	if (!reprobe) {
+		module_put(THIS_MODULE);
+		return;
+	}
+	reprobe->dev = get_device(trans->dev);
+	INIT_DELAYED_WORK(&reprobe->work, iwl_trans_reprobe_wk);
+	schedule_delayed_work(&reprobe->work, msecs_to_jiffies(delay_ms));
+}
+
 #define IWL_TRANS_RESET_OK_TIME	7 /* seconds */
 
 static enum iwl_reset_mode
@@ -105,18 +131,46 @@ iwl_trans_determine_restart_mode(struct iwl_trans *trans)
 	struct iwl_trans_dev_restart_data *data;
 	enum iwl_reset_mode at_least = 0;
 	unsigned int index;
-	static const enum iwl_reset_mode escalation_list[] = {
+	static const enum iwl_reset_mode escalation_list_old[] = {
+		IWL_RESET_MODE_SW_RESET,
+		IWL_RESET_MODE_REPROBE,
+		IWL_RESET_MODE_REPROBE,
+		IWL_RESET_MODE_FUNC_RESET,
+		IWL_RESET_MODE_PROD_RESET,
+	};
+	static const enum iwl_reset_mode escalation_list_sc[] = {
 		IWL_RESET_MODE_SW_RESET,
 		IWL_RESET_MODE_REPROBE,
 		IWL_RESET_MODE_REPROBE,
 		IWL_RESET_MODE_FUNC_RESET,
-		/* FIXME: add TOP reset */
+		IWL_RESET_MODE_TOP_RESET,
 		IWL_RESET_MODE_PROD_RESET,
-		/* FIXME: add TOP reset */
+		IWL_RESET_MODE_TOP_RESET,
 		IWL_RESET_MODE_PROD_RESET,
-		/* FIXME: add TOP reset */
+		IWL_RESET_MODE_TOP_RESET,
 		IWL_RESET_MODE_PROD_RESET,
 	};
+	const enum iwl_reset_mode *escalation_list;
+	size_t escalation_list_size;
+
+	/* used by TOP fatal error/TOP reset */
+	if (trans->restart.mode.type == IWL_ERR_TYPE_TOP_RESET_FAILED)
+		return IWL_RESET_MODE_PROD_RESET;
+
+	if (trans->request_top_reset) {
+		trans->request_top_reset = 0;
+		if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_SC)
+			return IWL_RESET_MODE_TOP_RESET;
+		return IWL_RESET_MODE_PROD_RESET;
+	}
+
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_SC) {
+		escalation_list = escalation_list_sc;
+		escalation_list_size = ARRAY_SIZE(escalation_list_sc);
+	} else {
+		escalation_list = escalation_list_old;
+		escalation_list_size = ARRAY_SIZE(escalation_list_old);
+	}
 
 	if (trans->restart.during_reset)
 		at_least = IWL_RESET_MODE_REPROBE;
@@ -125,25 +179,39 @@ iwl_trans_determine_restart_mode(struct iwl_trans *trans)
 	if (!data)
 		return at_least;
 
-	if (ktime_get_boottime_seconds() - data->last_error >=
+	if (!data->backoff &&
+	    ktime_get_boottime_seconds() - data->last_error >=
 			IWL_TRANS_RESET_OK_TIME)
 		data->restart_count = 0;
 
 	index = data->restart_count;
-	if (index >= ARRAY_SIZE(escalation_list))
-		index = ARRAY_SIZE(escalation_list) - 1;
+	if (index >= escalation_list_size) {
+		index = escalation_list_size - 1;
+		if (!data->backoff) {
+			data->backoff = true;
+			return IWL_RESET_MODE_BACKOFF;
+		}
+		data->backoff = false;
+	}
 
 	return max(at_least, escalation_list[index]);
 }
 
+#define IWL_TRANS_TOP_FOLLOWER_WAIT	180 /* ms */
+
 #define IWL_TRANS_RESET_DELAY	(HZ * 60)
 
 static void iwl_trans_restart_wk(struct work_struct *wk)
 {
-	struct iwl_trans *trans = container_of(wk, typeof(*trans), restart.wk);
-	struct iwl_trans_reprobe *reprobe;
+	struct iwl_trans *trans = container_of(wk, typeof(*trans),
+					       restart.wk.work);
 	enum iwl_reset_mode mode;
 
+	if (trans->restart.mode.type == IWL_ERR_TYPE_TOP_RESET_BY_BT) {
+		iwl_trans_schedule_reprobe(trans, IWL_TRANS_TOP_FOLLOWER_WAIT);
+		return;
+	}
+
 	if (!trans->op_mode)
 		return;
 
@@ -168,35 +236,29 @@ static void iwl_trans_restart_wk(struct work_struct *wk)
 		return;
 
 	mode = iwl_trans_determine_restart_mode(trans);
+	if (mode == IWL_RESET_MODE_BACKOFF) {
+		IWL_ERR(trans, "Too many device errors - delay next reset\n");
+		queue_delayed_work(system_unbound_wq, &trans->restart.wk,
+				   IWL_TRANS_RESET_DELAY);
+		return;
+	}
 
 	iwl_trans_inc_restart_count(trans->dev);
 
 	switch (mode) {
+	case IWL_RESET_MODE_TOP_RESET:
+		trans->do_top_reset = 1;
+		IWL_ERR(trans, "Device error - TOP reset\n");
+		fallthrough;
 	case IWL_RESET_MODE_SW_RESET:
-		IWL_ERR(trans, "Device error - SW reset\n");
+		if (mode == IWL_RESET_MODE_SW_RESET)
+			IWL_ERR(trans, "Device error - SW reset\n");
 		iwl_trans_opmode_sw_reset(trans, trans->restart.mode.type);
 		break;
 	case IWL_RESET_MODE_REPROBE:
 		IWL_ERR(trans, "Device error - reprobe!\n");
 
-		/*
-		 * get a module reference to avoid doing this while unloading
-		 * anyway and to avoid scheduling a work with code that's
-		 * being removed.
-		 */
-		if (!try_module_get(THIS_MODULE)) {
-			IWL_ERR(trans, "Module is being unloaded - abort\n");
-			return;
-		}
-
-		reprobe = kzalloc(sizeof(*reprobe), GFP_KERNEL);
-		if (!reprobe) {
-			module_put(THIS_MODULE);
-			return;
-		}
-		reprobe->dev = get_device(trans->dev);
-		INIT_WORK(&reprobe->work, iwl_trans_reprobe_wk);
-		schedule_work(&reprobe->work);
+		iwl_trans_schedule_reprobe(trans, 0);
 		break;
 	default:
 		iwl_trans_pcie_reset(trans, mode);
@@ -206,7 +268,7 @@ static void iwl_trans_restart_wk(struct work_struct *wk)
 
 struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 				  struct device *dev,
-				  const struct iwl_cfg_trans_params *cfg_trans)
+				  const struct iwl_mac_cfg *mac_cfg)
 {
 	struct iwl_trans *trans;
 #ifdef CONFIG_LOCKDEP
@@ -217,7 +279,7 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 	if (!trans)
 		return NULL;
 
-	trans->trans_cfg = cfg_trans;
+	trans->mac_cfg = mac_cfg;
 
 #ifdef CONFIG_LOCKDEP
 	lockdep_init_map(&trans->sync_cmd_lockdep_map, "sync_cmd_lockdep_map",
@@ -225,9 +287,8 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 #endif
 
 	trans->dev = dev;
-	trans->num_rx_queues = 1;
 
-	INIT_WORK(&trans->restart.wk, iwl_trans_restart_wk);
+	INIT_DELAYED_WORK(&trans->restart.wk, iwl_trans_restart_wk);
 
 	return trans;
 }
@@ -236,14 +297,18 @@ int iwl_trans_init(struct iwl_trans *trans)
 {
 	int txcmd_size, txcmd_align;
 
-	if (!trans->trans_cfg->gen2) {
-		txcmd_size = sizeof(struct iwl_tx_cmd);
+	/* check if name/num_rx_queues were set as a proxy for info being set */
+	if (WARN_ON(!trans->info.name || !trans->info.num_rxqs))
+		return -EINVAL;
+
+	if (!trans->mac_cfg->gen2) {
+		txcmd_size = sizeof(struct iwl_tx_cmd_v6);
 		txcmd_align = sizeof(void *);
-	} else if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210) {
-		txcmd_size = sizeof(struct iwl_tx_cmd_gen2);
+	} else if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210) {
+		txcmd_size = sizeof(struct iwl_tx_cmd_v9);
 		txcmd_align = 64;
 	} else {
-		txcmd_size = sizeof(struct iwl_tx_cmd_gen3);
+		txcmd_size = sizeof(struct iwl_tx_cmd);
 		txcmd_align = 128;
 	}
 
@@ -251,7 +316,7 @@ int iwl_trans_init(struct iwl_trans *trans)
 	txcmd_size += 36; /* biggest possible 802.11 header */
 
 	/* Ensure device TX cmd cannot reach/cross a page boundary in gen2 */
-	if (WARN_ON(trans->trans_cfg->gen2 && txcmd_size >= txcmd_align))
+	if (WARN_ON(trans->mac_cfg->gen2 && txcmd_size >= txcmd_align))
 		return -EINVAL;
 
 	snprintf(trans->dev_cmd_pool_name, sizeof(trans->dev_cmd_pool_name),
@@ -263,15 +328,12 @@ int iwl_trans_init(struct iwl_trans *trans)
 	if (!trans->dev_cmd_pool)
 		return -ENOMEM;
 
-	/* Initialize the wait queue for commands */
-	init_waitqueue_head(&trans->wait_command_queue);
-
 	return 0;
 }
 
 void iwl_trans_free(struct iwl_trans *trans)
 {
-	cancel_work_sync(&trans->restart.wk);
+	cancel_delayed_work_sync(&trans->restart.wk);
 	kmem_cache_destroy(trans->dev_cmd_pool);
 }
 
@@ -283,17 +345,7 @@ int iwl_trans_send_cmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd)
 		     test_bit(STATUS_RFKILL_OPMODE, &trans->status)))
 		return -ERFKILL;
 
-	/*
-	 * We can't test IWL_MVM_STATUS_IN_D3 in mvm->status because this
-	 * bit is set early in the D3 flow, before we send all the commands
-	 * that configure the firmware for D3 operation (power, patterns, ...)
-	 * and we don't want to flag all those with CMD_SEND_IN_D3.
-	 * So use the system_pm_mode instead. The only command sent after
-	 * we set system_pm_mode is D3_CONFIG_CMD, which we now flag with
-	 * CMD_SEND_IN_D3.
-	 */
-	if (unlikely(trans->system_pm_mode == IWL_PLAT_PM_MODE_D3 &&
-		     !(cmd->flags & CMD_SEND_IN_D3)))
+	if (unlikely(test_bit(STATUS_SUSPENDED, &trans->status)))
 		return -EHOSTDOWN;
 
 	if (unlikely(test_bit(STATUS_FW_ERROR, &trans->status)))
@@ -306,7 +358,7 @@ int iwl_trans_send_cmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd)
 	if (!(cmd->flags & CMD_ASYNC))
 		lock_map_acquire_read(&trans->sync_cmd_lockdep_map);
 
-	if (trans->wide_cmd_header && !iwl_cmd_groupid(cmd->id)) {
+	if (trans->conf.wide_cmd_header && !iwl_cmd_groupid(cmd->id)) {
 		if (cmd->id != REPLY_ERROR)
 			cmd->id = DEF_ID(cmd->id);
 	}
@@ -350,11 +402,12 @@ const char *iwl_get_cmd_string(struct iwl_trans *trans, u32 id)
 	grp = iwl_cmd_groupid(id);
 	cmd = iwl_cmd_opcode(id);
 
-	if (!trans->command_groups || grp >= trans->command_groups_size ||
-	    !trans->command_groups[grp].arr)
+	if (!trans->conf.command_groups ||
+	    grp >= trans->conf.command_groups_size ||
+	    !trans->conf.command_groups[grp].arr)
 		return "UNKNOWN";
 
-	arr = &trans->command_groups[grp];
+	arr = &trans->conf.command_groups[grp];
 	ret = bsearch(&cmd, arr->arr, arr->size, size, iwl_hcmd_names_cmp);
 	if (!ret)
 		return "UNKNOWN";
@@ -362,37 +415,29 @@ const char *iwl_get_cmd_string(struct iwl_trans *trans, u32 id)
 }
 IWL_EXPORT_SYMBOL(iwl_get_cmd_string);
 
-int iwl_cmd_groups_verify_sorted(const struct iwl_trans_config *trans)
+void iwl_trans_op_mode_enter(struct iwl_trans *trans,
+			     struct iwl_op_mode *op_mode)
 {
-	int i, j;
-	const struct iwl_hcmd_arr *arr;
+	trans->op_mode = op_mode;
 
-	for (i = 0; i < trans->command_groups_size; i++) {
-		arr = &trans->command_groups[i];
-		if (!arr->arr)
-			continue;
-		for (j = 0; j < arr->size - 1; j++)
-			if (arr->arr[j].cmd_id > arr->arr[j + 1].cmd_id)
-				return -1;
-	}
-	return 0;
-}
-IWL_EXPORT_SYMBOL(iwl_cmd_groups_verify_sorted);
+	if (WARN_ON(trans->conf.n_no_reclaim_cmds > MAX_NO_RECLAIM_CMDS))
+		trans->conf.n_no_reclaim_cmds =
+			ARRAY_SIZE(trans->conf.no_reclaim_cmds);
 
-void iwl_trans_configure(struct iwl_trans *trans,
-			 const struct iwl_trans_config *trans_cfg)
-{
-	trans->op_mode = trans_cfg->op_mode;
+	WARN_ON_ONCE(!trans->conf.rx_mpdu_cmd);
 
-	iwl_trans_pcie_configure(trans, trans_cfg);
-	WARN_ON(iwl_cmd_groups_verify_sorted(trans_cfg));
+	iwl_trans_pcie_op_mode_enter(trans);
 }
-IWL_EXPORT_SYMBOL(iwl_trans_configure);
+IWL_EXPORT_SYMBOL(iwl_trans_op_mode_enter);
 
 int iwl_trans_start_hw(struct iwl_trans *trans)
 {
 	might_sleep();
 
+	clear_bit(STATUS_TRANS_RESET_IN_PROGRESS, &trans->status);
+	/* opmode may not resume if it detects errors */
+	clear_bit(STATUS_SUSPENDED, &trans->status);
+
 	return iwl_trans_pcie_start_hw(trans);
 }
 IWL_EXPORT_SYMBOL(iwl_trans_start_hw);
@@ -403,9 +448,10 @@ void iwl_trans_op_mode_leave(struct iwl_trans *trans)
 
 	iwl_trans_pcie_op_mode_leave(trans);
 
-	cancel_work_sync(&trans->restart.wk);
+	cancel_delayed_work_sync(&trans->restart.wk);
 
 	trans->op_mode = NULL;
+	memset(&trans->conf, 0, sizeof(trans->conf));
 
 	trans->state = IWL_TRANS_NO_FW;
 }
@@ -482,18 +528,31 @@ IWL_EXPORT_SYMBOL(iwl_trans_dump_data);
 
 int iwl_trans_d3_suspend(struct iwl_trans *trans, bool test, bool reset)
 {
+	int err;
+
 	might_sleep();
 
-	return iwl_trans_pcie_d3_suspend(trans, test, reset);
+	err = iwl_trans_pcie_d3_suspend(trans, test, reset);
+
+	if (!err)
+		set_bit(STATUS_SUSPENDED, &trans->status);
+
+	return err;
 }
 IWL_EXPORT_SYMBOL(iwl_trans_d3_suspend);
 
 int iwl_trans_d3_resume(struct iwl_trans *trans, enum iwl_d3_status *status,
 			bool test, bool reset)
 {
+	int err;
+
 	might_sleep();
 
-	return iwl_trans_pcie_d3_resume(trans, status, test, reset);
+	err = iwl_trans_pcie_d3_resume(trans, status, test, reset);
+
+	clear_bit(STATUS_SUSPENDED, &trans->status);
+
+	return err;
 }
 IWL_EXPORT_SYMBOL(iwl_trans_d3_resume);
 
@@ -540,38 +599,42 @@ void __releases(nic_access)
 iwl_trans_release_nic_access(struct iwl_trans *trans)
 {
 	iwl_trans_pcie_release_nic_access(trans);
-	__release(nic_access);
 }
 IWL_EXPORT_SYMBOL(iwl_trans_release_nic_access);
 
-void iwl_trans_fw_alive(struct iwl_trans *trans, u32 scd_addr)
+void iwl_trans_fw_alive(struct iwl_trans *trans)
 {
 	might_sleep();
 
 	trans->state = IWL_TRANS_FW_ALIVE;
 
-	if (trans->trans_cfg->gen2)
+	if (trans->mac_cfg->gen2)
 		iwl_trans_pcie_gen2_fw_alive(trans);
 	else
-		iwl_trans_pcie_fw_alive(trans, scd_addr);
+		iwl_trans_pcie_fw_alive(trans);
 }
 IWL_EXPORT_SYMBOL(iwl_trans_fw_alive);
 
-int iwl_trans_start_fw(struct iwl_trans *trans, const struct fw_img *fw,
-		       bool run_in_rfkill)
+int iwl_trans_start_fw(struct iwl_trans *trans, const struct iwl_fw *fw,
+		       enum iwl_ucode_type ucode_type, bool run_in_rfkill)
 {
+	const struct fw_img *img;
 	int ret;
 
 	might_sleep();
 
-	WARN_ON_ONCE(!trans->rx_mpdu_cmd);
+	img = iwl_get_ucode_image(fw, ucode_type);
+	if (!img)
+		return -EINVAL;
 
 	clear_bit(STATUS_FW_ERROR, &trans->status);
 
-	if (trans->trans_cfg->gen2)
-		ret = iwl_trans_pcie_gen2_start_fw(trans, fw, run_in_rfkill);
+	if (trans->mac_cfg->gen2)
+		ret = iwl_trans_pcie_gen2_start_fw(trans, fw, img,
+						   run_in_rfkill);
 	else
-		ret = iwl_trans_pcie_start_fw(trans, fw, run_in_rfkill);
+		ret = iwl_trans_pcie_start_fw(trans, fw, img,
+					      run_in_rfkill);
 
 	if (ret == 0)
 		trans->state = IWL_TRANS_FW_STARTED;
@@ -612,7 +675,7 @@ void iwl_trans_stop_device(struct iwl_trans *trans)
 		iwl_op_mode_dump_error(trans->op_mode, &mode);
 	}
 
-	if (trans->trans_cfg->gen2)
+	if (trans->mac_cfg->gen2)
 		iwl_trans_pcie_gen2_stop_device(trans);
 	else
 		iwl_trans_pcie_stop_device(trans);
@@ -631,7 +694,7 @@ int iwl_trans_tx(struct iwl_trans *trans, struct sk_buff *skb,
 		      "bad state = %d\n", trans->state))
 		return -EIO;
 
-	if (trans->trans_cfg->gen2)
+	if (trans->mac_cfg->gen2)
 		return iwl_txq_gen2_tx(trans, skb, dev_cmd, queue);
 
 	return iwl_trans_pcie_tx(trans, skb, dev_cmd, queue);
@@ -764,14 +827,14 @@ int iwl_trans_load_pnvm(struct iwl_trans *trans,
 			const struct iwl_pnvm_image *pnvm_data,
 			const struct iwl_ucode_capabilities *capa)
 {
-	return iwl_trans_pcie_ctx_info_gen3_load_pnvm(trans, pnvm_data, capa);
+	return iwl_trans_pcie_ctx_info_v2_load_pnvm(trans, pnvm_data, capa);
 }
 IWL_EXPORT_SYMBOL(iwl_trans_load_pnvm);
 
 void iwl_trans_set_pnvm(struct iwl_trans *trans,
 			const struct iwl_ucode_capabilities *capa)
 {
-	iwl_trans_pcie_ctx_info_gen3_set_pnvm(trans, capa);
+	iwl_trans_pcie_ctx_info_v2_set_pnvm(trans, capa);
 }
 IWL_EXPORT_SYMBOL(iwl_trans_set_pnvm);
 
@@ -779,7 +842,7 @@ int iwl_trans_load_reduce_power(struct iwl_trans *trans,
 				const struct iwl_pnvm_image *payloads,
 				const struct iwl_ucode_capabilities *capa)
 {
-	return iwl_trans_pcie_ctx_info_gen3_load_reduce_power(trans, payloads,
+	return iwl_trans_pcie_ctx_info_v2_load_reduce_power(trans, payloads,
 							      capa);
 }
 IWL_EXPORT_SYMBOL(iwl_trans_load_reduce_power);
@@ -787,6 +850,6 @@ IWL_EXPORT_SYMBOL(iwl_trans_load_reduce_power);
 void iwl_trans_set_reduce_power(struct iwl_trans *trans,
 				const struct iwl_ucode_capabilities *capa)
 {
-	iwl_trans_pcie_ctx_info_gen3_set_reduce_power(trans, capa);
+	iwl_trans_pcie_ctx_info_v2_set_reduce_power(trans, capa);
 }
 IWL_EXPORT_SYMBOL(iwl_trans_set_reduce_power);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 25fb4c50e38b..012b1e44bce3 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2018-2023, 2025 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -109,16 +109,12 @@ static inline u32 iwl_rx_packet_payload_len(const struct iwl_rx_packet *pkt)
  *	the response. The caller needs to call iwl_free_resp when done.
  * @CMD_SEND_IN_RFKILL: Send the command even if the NIC is in RF-kill.
  * @CMD_BLOCK_TXQS: Block TXQs while the comment is executing.
- * @CMD_SEND_IN_D3: Allow the command to be sent in D3 mode, relevant to
- *	SUSPEND and RESUME commands. We are in D3 mode when we set
- *	trans->system_pm_mode to IWL_PLAT_PM_MODE_D3.
  */
 enum CMD_MODE {
 	CMD_ASYNC		= BIT(0),
 	CMD_WANT_SKB		= BIT(1),
 	CMD_SEND_IN_RFKILL	= BIT(2),
 	CMD_BLOCK_TXQS		= BIT(3),
-	CMD_SEND_IN_D3          = BIT(4),
 };
 #define CMD_MODE_BITS 5
 
@@ -304,6 +300,10 @@ enum iwl_d3_status {
  *	via iwl_trans_finish_sw_reset()
  * @STATUS_RESET_PENDING: reset worker was scheduled, but didn't dump
  *	the firmware state yet
+ * @STATUS_TRANS_RESET_IN_PROGRESS: reset is still in progress, don't
+ *	attempt another reset yet
+ * @STATUS_SUSPENDED: device is suspended, don't send commands that
+ *	aren't marked accordingly
  */
 enum iwl_trans_status {
 	STATUS_SYNC_HCMD_ACTIVE,
@@ -317,6 +317,8 @@ enum iwl_trans_status {
 	STATUS_SUPPRESS_CMD_ERROR_ONCE,
 	STATUS_IN_SW_RESET,
 	STATUS_RESET_PENDING,
+	STATUS_TRANS_RESET_IN_PROGRESS,
+	STATUS_SUSPENDED,
 };
 
 static inline int
@@ -328,6 +330,7 @@ iwl_trans_get_rb_size_order(enum iwl_amsdu_size rb_size)
 	case IWL_AMSDU_4K:
 		return get_order(4 * 1024);
 	case IWL_AMSDU_8K:
+		return get_order(8 * 1024);
 	case IWL_AMSDU_12K:
 		return get_order(16 * 1024);
 	default:
@@ -387,7 +390,8 @@ struct iwl_dump_sanitize_ops {
 /**
  * struct iwl_trans_config - transport configuration
  *
- * @op_mode: pointer to the upper layer.
+ * These values should be set before iwl_trans_op_mode_enter().
+ *
  * @cmd_queue: the index of the command queue.
  *	Must be set before start_fw.
  * @cmd_fifo: the fifo for host commands
@@ -398,8 +402,6 @@ struct iwl_dump_sanitize_ops {
  * @n_no_reclaim_cmds: # of commands in list
  * @rx_buf_size: RX buffer size needed for A-MSDUs
  *	if unset 4k will be the RX buffer size
- * @bc_table_dword: set to true if the BC table expects the byte count to be
- *	in DWORD (as opposed to bytes)
  * @scd_set_active: should the transport configure the SCD for HCMD queue
  * @command_groups: array of command groups, each member is an array of the
  *	commands in the group; for debugging only
@@ -410,17 +412,24 @@ struct iwl_dump_sanitize_ops {
  * @queue_alloc_cmd_ver: queue allocation command version, set to 0
  *	for using the older SCD_QUEUE_CFG, set to the version of
  *	SCD_QUEUE_CONFIG_CMD otherwise.
+ * @wide_cmd_header: true when ucode supports wide command header format
+ * @rx_mpdu_cmd: MPDU RX command ID, must be assigned by opmode before
+ *	starting the firmware, used for tracing
+ * @rx_mpdu_cmd_hdr_size: used for tracing, amount of data before the
+ *	start of the 802.11 header in the @rx_mpdu_cmd
+ * @dsbr_urm_fw_dependent: switch to URM based on fw settings
+ * @dsbr_urm_permanent: switch to URM permanently
+ * @mbx_addr_0_step: step address data 0
+ * @mbx_addr_1_step: step address data 1
+ * @ext_32khz_clock_valid: if true, the external 32 KHz clock can be used
  */
 struct iwl_trans_config {
-	struct iwl_op_mode *op_mode;
-
 	u8 cmd_queue;
 	u8 cmd_fifo;
-	const u8 *no_reclaim_cmds;
-	unsigned int n_no_reclaim_cmds;
+	u8 n_no_reclaim_cmds;
+	u8 no_reclaim_cmds[MAX_NO_RECLAIM_CMDS];
 
 	enum iwl_amsdu_size rx_buf_size;
-	bool bc_table_dword;
 	bool scd_set_active;
 	const struct iwl_hcmd_arr *command_groups;
 	int command_groups_size;
@@ -428,6 +437,16 @@ struct iwl_trans_config {
 	u8 cb_data_offs;
 	bool fw_reset_handshake;
 	u8 queue_alloc_cmd_ver;
+
+	bool wide_cmd_header;
+	u8 rx_mpdu_cmd, rx_mpdu_cmd_hdr_size;
+
+	u8 dsbr_urm_fw_dependent:1,
+	   dsbr_urm_permanent:1,
+	   ext_32khz_clock_valid:1;
+
+	u32 mbx_addr_0_step;
+	u32 mbx_addr_1_step;
 };
 
 struct iwl_trans_dump_data {
@@ -513,23 +532,6 @@ enum iwl_trans_state {
  */
 
 /**
- * enum iwl_plat_pm_mode - platform power management mode
- *
- * This enumeration describes the device's platform power management
- * behavior when in system-wide suspend (i.e WoWLAN).
- *
- * @IWL_PLAT_PM_MODE_DISABLED: power management is disabled for this
- *	device.  In system-wide suspend mode, it means that the all
- *	connections will be closed automatically by mac80211 before
- *	the platform is suspended.
- * @IWL_PLAT_PM_MODE_D3: the device goes into D3 mode (i.e. WoWLAN).
- */
-enum iwl_plat_pm_mode {
-	IWL_PLAT_PM_MODE_DISABLED,
-	IWL_PLAT_PM_MODE_D3,
-};
-
-/**
  * enum iwl_ini_cfg_state
  * @IWL_INI_CFG_STATE_NOT_LOADED: no debug cfg was given
  * @IWL_INI_CFG_STATE_LOADED: debug cfg was found and loaded
@@ -819,108 +821,91 @@ struct iwl_txq {
 };
 
 /**
+ * struct iwl_trans_info - transport info for outside use
+ * @name: the device name
+ * @max_skb_frags: maximum number of fragments an SKB can have when transmitted.
+ *	0 indicates that frag SKBs (NETIF_F_SG) aren't supported.
+ * @hw_rev: the revision data of the HW
+ * @hw_rev_step: The mac step of the HW
+ * @hw_rf_id: the device RF ID
+ * @hw_cnv_id: the device CNV ID
+ * @hw_crf_id: the device CRF ID
+ * @hw_wfpm_id: the device wfpm ID
+ * @hw_id: the ID of the device / sub-device
+ *	Bits 0:15 represent the sub-device ID
+ *	Bits 16:31 represent the device ID.
+ * @pcie_link_speed: current PCIe link speed (%PCI_EXP_LNKSTA_CLS_*),
+ *	only valid for discrete (not integrated) NICs
+ * @num_rxqs: number of RX queues allocated by the transport
+ */
+struct iwl_trans_info {
+	const char *name;
+	u32 max_skb_frags;
+	u32 hw_rev;
+	u32 hw_rev_step;
+	u32 hw_rf_id;
+	u32 hw_crf_id;
+	u32 hw_cnv_id;
+	u32 hw_wfpm_id;
+	u32 hw_id;
+	u8 pcie_link_speed;
+	u8 num_rxqs;
+};
+
+/**
  * struct iwl_trans - transport common data
  *
  * @csme_own: true if we couldn't get ownership on the device
  * @op_mode: pointer to the op_mode
- * @trans_cfg: the trans-specific configuration part
+ * @mac_cfg: the trans-specific configuration part
  * @cfg: pointer to the configuration
  * @drv: pointer to iwl_drv
+ * @conf: configuration set by the opmode before enter
  * @state: current device state
  * @status: a bit-mask of transport status flags
  * @dev: pointer to struct device * that represents the device
- * @max_skb_frags: maximum number of fragments an SKB can have when transmitted.
- *	0 indicates that frag SKBs (NETIF_F_SG) aren't supported.
- * @hw_rf_id: a u32 with the device RF ID
- * @hw_cnv_id: a u32 with the device CNV ID
- * @hw_crf_id: a u32 with the device CRF ID
- * @hw_wfpm_id: a u32 with the device wfpm ID
- * @hw_id: a u32 with the ID of the device / sub-device.
- *	Set during transport allocation.
- * @hw_id_str: a string with info about HW ID. Set during transport allocation.
- * @sku_id: the SKU identifier (for PNVM matching)
+ * @info: device information for use by other layers
  * @pnvm_loaded: indicates PNVM was loaded
- * @hw_rev: the revision data of the HW
- * @hw_rev_step: The mac step of the HW
  * @pm_support: set to true in start_hw if link pm is supported
  * @ltr_enabled: set to true if the LTR is enabled
  * @fail_to_parse_pnvm_image: set to true if pnvm parsing failed
  * @reduce_power_loaded: indicates reduced power section was loaded
  * @failed_to_load_reduce_power_image: set to true if pnvm loading failed
- * @command_groups: pointer to command group name list array
- * @command_groups_size: array size of @command_groups
- * @wide_cmd_header: true when ucode supports wide command header format
- * @wait_command_queue: wait queue for sync commands
- * @num_rx_queues: number of RX queues allocated by the transport;
- *	the transport must set this before calling iwl_drv_start()
- * @iml_len: the length of the image loader
- * @iml: a pointer to the image loader itself
  * @dev_cmd_pool: pool for Tx cmd allocation - for internal use only.
  *	The user should use iwl_trans_{alloc,free}_tx_cmd.
  * @dev_cmd_pool_name: name for the TX command allocation pool
  * @dbgfs_dir: iwlwifi debugfs base dir for this device
  * @sync_cmd_lockdep_map: lockdep map for checking sync commands
- * @rx_mpdu_cmd: MPDU RX command ID, must be assigned by opmode before
- *	starting the firmware, used for tracing
- * @rx_mpdu_cmd_hdr_size: used for tracing, amount of data before the
- *	start of the 802.11 header in the @rx_mpdu_cmd
  * @dbg: additional debug data, see &struct iwl_trans_debug
  * @init_dram: FW initialization DMA data
- * @system_pm_mode: the system-wide power management mode in use.
- *	This mode is set dynamically, depending on the WoWLAN values
- *	configured from the userspace at runtime.
- * @name: the device name
- * @mbx_addr_0_step: step address data 0
- * @mbx_addr_1_step: step address data 1
- * @pcie_link_speed: current PCIe link speed (%PCI_EXP_LNKSTA_CLS_*),
- *	only valid for discrete (not integrated) NICs
- * @invalid_tx_cmd: invalid TX command buffer
  * @reduced_cap_sku: reduced capability supported SKU
- * @bw_limit: the max bandwidth
  * @step_urm: STEP is in URM, no support for MCS>9 in 320 MHz
  * @restart: restart worker data
  * @restart.wk: restart worker
  * @restart.mode: reset/restart error mode information
  * @restart.during_reset: error occurred during previous software reset
- * @me_recheck_wk: worker to recheck WiAMT/CSME presence
- * @me_present: WiAMT/CSME is detected as present (1), not present (0)
- *	or unknown (-1, so can still use it as a boolean safely)
  * @trans_specific: data for the specific transport this is allocated for/with
- * @dsbr_urm_fw_dependent: switch to URM based on fw settings
- * @dsbr_urm_permanent: switch to URM permanently
- * @ext_32khz_clock_valid: if true, the external 32 KHz clock can be used
+ * @request_top_reset: TOP reset was requested, used by the reset
+ *	worker that should be scheduled (with appropriate reason)
+ * @do_top_reset: indication to the (PCIe) transport/context-info
+ *	to do the TOP reset
  */
 struct iwl_trans {
 	bool csme_own;
 	struct iwl_op_mode *op_mode;
-	const struct iwl_cfg_trans_params *trans_cfg;
-	const struct iwl_cfg *cfg;
+	const struct iwl_mac_cfg *mac_cfg;
+	const struct iwl_rf_cfg *cfg;
 	struct iwl_drv *drv;
+	struct iwl_trans_config conf;
 	enum iwl_trans_state state;
 	unsigned long status;
 
 	struct device *dev;
-	u32 max_skb_frags;
-	u32 hw_rev;
-	u32 hw_rev_step;
-	u32 hw_rf_id;
-	u32 hw_crf_id;
-	u32 hw_cnv_id;
-	u32 hw_wfpm_id;
-	u32 hw_id;
-	char hw_id_str[52];
-	u32 sku_id[3];
+
+	const struct iwl_trans_info info;
 	bool reduced_cap_sku;
-	u16 bw_limit;
 	bool step_urm;
 
-	u8 dsbr_urm_fw_dependent:1,
-	   dsbr_urm_permanent:1;
-
-	bool ext_32khz_clock_valid;
-
-	u8 rx_mpdu_cmd, rx_mpdu_cmd_hdr_size;
-
 	bool pm_support;
 	bool ltr_enabled;
 	u8 pnvm_loaded:1;
@@ -928,16 +913,6 @@ struct iwl_trans {
 	u8 reduce_power_loaded:1;
 	u8 failed_to_load_reduce_power_image:1;
 
-	const struct iwl_hcmd_arr *command_groups;
-	int command_groups_size;
-	bool wide_cmd_header;
-
-	wait_queue_head_t wait_command_queue;
-	u8 num_rx_queues;
-
-	size_t iml_len;
-	u8 *iml;
-
 	/* The following fields are internal only */
 	struct kmem_cache *dev_cmd_pool;
 	char dev_cmd_pool_name[50];
@@ -951,24 +926,14 @@ struct iwl_trans {
 	struct iwl_trans_debug dbg;
 	struct iwl_self_init_dram init_dram;
 
-	enum iwl_plat_pm_mode system_pm_mode;
-
-	const char *name;
-	u32 mbx_addr_0_step;
-	u32 mbx_addr_1_step;
-
-	u8 pcie_link_speed;
-
-	struct iwl_dma_ptr invalid_tx_cmd;
-
 	struct {
-		struct work_struct wk;
+		struct delayed_work wk;
 		struct iwl_fw_error_dump_mode mode;
 		bool during_reset;
 	} restart;
 
-	struct delayed_work me_recheck_wk;
-	s8 me_present;
+	u8 request_top_reset:1,
+	   do_top_reset:1;
 
 	/* pointer to trans specific struct */
 	/*Ensure that this pointer will always be aligned to sizeof pointer */
@@ -976,19 +941,18 @@ struct iwl_trans {
 };
 
 const char *iwl_get_cmd_string(struct iwl_trans *trans, u32 id);
-int iwl_cmd_groups_verify_sorted(const struct iwl_trans_config *trans);
 
-void iwl_trans_configure(struct iwl_trans *trans,
-			 const struct iwl_trans_config *trans_cfg);
+void iwl_trans_op_mode_enter(struct iwl_trans *trans,
+			     struct iwl_op_mode *op_mode);
 
 int iwl_trans_start_hw(struct iwl_trans *trans);
 
 void iwl_trans_op_mode_leave(struct iwl_trans *trans);
 
-void iwl_trans_fw_alive(struct iwl_trans *trans, u32 scd_addr);
+void iwl_trans_fw_alive(struct iwl_trans *trans);
 
-int iwl_trans_start_fw(struct iwl_trans *trans, const struct fw_img *fw,
-		       bool run_in_rfkill);
+int iwl_trans_start_fw(struct iwl_trans *trans, const struct iwl_fw *fw,
+		       enum iwl_ucode_type ucode_type, bool run_in_rfkill);
 
 void iwl_trans_stop_device(struct iwl_trans *trans);
 
@@ -1151,6 +1115,9 @@ static inline void iwl_trans_schedule_reset(struct iwl_trans *trans,
 {
 	if (test_bit(STATUS_TRANS_DEAD, &trans->status))
 		return;
+	/* clear this on device init, not cleared on any unbind/reprobe */
+	if (test_and_set_bit(STATUS_TRANS_RESET_IN_PROGRESS, &trans->status))
+		return;
 
 	trans->restart.mode.type = type;
 	trans->restart.mode.context = IWL_ERR_CONTEXT_WORKER;
@@ -1163,7 +1130,7 @@ static inline void iwl_trans_schedule_reset(struct iwl_trans *trans,
 	 */
 	trans->restart.during_reset = test_bit(STATUS_IN_SW_RESET,
 					       &trans->status);
-	queue_work(system_unbound_wq, &trans->restart.wk);
+	queue_delayed_work(system_unbound_wq, &trans->restart.wk, 0);
 }
 
 static inline void iwl_trans_fw_error(struct iwl_trans *trans,
@@ -1188,6 +1155,9 @@ static inline void iwl_trans_opmode_sw_reset(struct iwl_trans *trans,
 
 	set_bit(STATUS_IN_SW_RESET, &trans->status);
 
+	if (WARN_ON(type == IWL_ERR_TYPE_TOP_RESET_BY_BT))
+		return;
+
 	if (!trans->op_mode->ops->sw_reset ||
 	    !trans->op_mode->ops->sw_reset(trans->op_mode, type))
 		clear_bit(STATUS_IN_SW_RESET, &trans->status);
@@ -1235,7 +1205,7 @@ static inline void iwl_trans_finish_sw_reset(struct iwl_trans *trans)
  *****************************************************/
 struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 			  struct device *dev,
-			  const struct iwl_cfg_trans_params *cfg_trans);
+			  const struct iwl_mac_cfg *cfg_trans);
 int iwl_trans_init(struct iwl_trans *trans);
 void iwl_trans_free(struct iwl_trans *trans);
 
@@ -1246,6 +1216,19 @@ static inline bool iwl_trans_is_hw_error_value(u32 val)
 
 void iwl_trans_free_restart_list(void);
 
+static inline u16 iwl_trans_get_num_rbds(struct iwl_trans *trans)
+{
+	u16 result = trans->cfg->num_rbds;
+
+	/*
+	 * Since AX210 family (So/Ty) the device cannot put mutliple
+	 * frames into the same buffer, so double the value for them.
+	 */
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+		return 2 * result;
+	return result;
+}
+
 /*****************************************************
  * PCIe handling
  *****************************************************/
@@ -1257,11 +1240,16 @@ enum iwl_reset_mode {
 	/* upper level modes: */
 	IWL_RESET_MODE_SW_RESET,
 	IWL_RESET_MODE_REPROBE,
+	/* TOP reset doesn't require PCIe remove */
+	IWL_RESET_MODE_TOP_RESET,
 	/* PCIE level modes: */
 	IWL_RESET_MODE_REMOVE_ONLY,
 	IWL_RESET_MODE_RESCAN,
 	IWL_RESET_MODE_FUNC_RESET,
 	IWL_RESET_MODE_PROD_RESET,
+
+	/* keep last - special backoff value */
+	IWL_RESET_MODE_BACKOFF,
 };
 
 void iwl_trans_pcie_reset(struct iwl_trans *trans, enum iwl_reset_mode mode);
@@ -1270,4 +1258,19 @@ void iwl_trans_pcie_fw_reset_handshake(struct iwl_trans *trans);
 int iwl_trans_pcie_send_hcmd(struct iwl_trans *trans,
 			     struct iwl_host_cmd *cmd);
 
+/* Internal helper */
+static inline void iwl_trans_set_info(struct iwl_trans *trans,
+				      struct iwl_trans_info *info)
+{
+	struct iwl_trans_info *write;
+
+	write = (void *)(uintptr_t)&trans->info;
+	*write = *info;
+}
+
+static inline u16 iwl_trans_get_device_id(struct iwl_trans *trans)
+{
+	return u32_get_bits(trans->info.hw_id, GENMASK(31, 16));
+}
+
 #endif /* __iwl_trans_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-utils.c b/drivers/net/wireless/intel/iwlwifi/iwl-utils.c
index b14ec98e28b6..c5b49851e4b9 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-utils.c
@@ -4,7 +4,6 @@
  */
 #include <net/gso.h>
 #include <linux/ieee80211.h>
-#include <net/gso.h>
 #include <net/ip.h>
 
 #include "iwl-drv.h"
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/agg.c b/drivers/net/wireless/intel/iwlwifi/mld/agg.c
index db9e0f04f4b7..bda488ae9eec 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/agg.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/agg.c
@@ -124,10 +124,12 @@ void iwl_mld_handle_bar_frame_release_notif(struct iwl_mld *mld,
 
 	rcu_read_lock();
 	baid_data = rcu_dereference(mld->fw_id_to_ba[baid]);
-	if (!IWL_FW_CHECK(mld, !baid_data,
-			  "Got valid BAID %d but not allocated, invalid BAR release!\n",
-			  baid))
+	if (!baid_data) {
+		IWL_DEBUG_HT(mld,
+			     "Got valid BAID %d but not allocated\n",
+			     baid);
 		goto out_unlock;
+	}
 
 	if (IWL_FW_CHECK(mld, tid != baid_data->tid ||
 			 sta_id > mld->fw->ucode_capa.num_stations ||
@@ -444,7 +446,7 @@ static void iwl_mld_init_reorder_buffer(struct iwl_mld *mld,
 					struct iwl_mld_baid_data *data,
 					u16 ssn)
 {
-	for (int i = 0; i < mld->trans->num_rx_queues; i++) {
+	for (int i = 0; i < mld->trans->info.num_rxqs; i++) {
 		struct iwl_mld_reorder_buffer *reorder_buf =
 			&data->reorder_buf[i];
 		struct iwl_mld_reorder_buf_entry *entries =
@@ -468,7 +470,7 @@ static void iwl_mld_free_reorder_buffer(struct iwl_mld *mld,
 	iwl_mld_sync_rx_queues(mld, IWL_MLD_RXQ_NOTIF_DEL_BA,
 			       &delba_data, sizeof(delba_data));
 
-	for (int i = 0; i < mld->trans->num_rx_queues; i++) {
+	for (int i = 0; i < mld->trans->info.num_rxqs; i++) {
 		struct iwl_mld_reorder_buffer *reorder_buf =
 			&data->reorder_buf[i];
 		struct iwl_mld_reorder_buf_entry *entries =
@@ -530,7 +532,7 @@ int iwl_mld_ampdu_rx_start(struct iwl_mld *mld, struct ieee80211_sta *sta,
 	 * before starting the BA session in the firmware
 	 */
 	baid_data = kzalloc(sizeof(*baid_data) +
-			    mld->trans->num_rx_queues * reorder_buf_size,
+			    mld->trans->info.num_rxqs * reorder_buf_size,
 			    GFP_KERNEL);
 	if (!baid_data)
 		return -ENOMEM;
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ap.c b/drivers/net/wireless/intel/iwlwifi/mld/ap.c
index 571eabd0b511..26511b49d89a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/ap.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/ap.c
@@ -11,6 +11,7 @@
 #include "tx.h"
 #include "power.h"
 #include "key.h"
+#include "phy.h"
 #include "iwl-utils.h"
 
 #include "fw/api/sta.h"
@@ -269,6 +270,7 @@ int iwl_mld_start_ap_ibss(struct ieee80211_hw *hw,
 {
 	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
 	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct ieee80211_chanctx_conf *ctx;
 	int ret;
 
 	if (vif->type == NL80211_IFTYPE_AP)
@@ -314,6 +316,13 @@ int iwl_mld_start_ap_ibss(struct ieee80211_hw *hw,
 		return iwl_mld_mac_fw_action(mld, mld->p2p_device_vif,
 					     FW_CTXT_ACTION_MODIFY);
 
+	/* When the channel context was added, the link is not yet active, so
+	 * min_def is always used. Update the PHY again here in case def should
+	 * actually be used.
+	 */
+	ctx = wiphy_dereference(mld->wiphy, link->chanctx_conf);
+	iwl_mld_update_phy_chandef(mld, ctx);
+
 	return 0;
 rm_bcast:
 	iwl_mld_remove_bcast_sta(mld, vif, link);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/coex.c b/drivers/net/wireless/intel/iwlwifi/mld/coex.c
index 5f262bd43f21..32c727b3b391 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/coex.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/coex.c
@@ -24,17 +24,13 @@ int iwl_mld_send_bt_init_conf(struct iwl_mld *mld)
 void iwl_mld_handle_bt_coex_notif(struct iwl_mld *mld,
 				  struct iwl_rx_packet *pkt)
 {
-	const struct iwl_bt_coex_profile_notif *notif = (void *)pkt->data;
+	const struct iwl_bt_coex_profile_notif *notif = (const void *)pkt->data;
 	const struct iwl_bt_coex_profile_notif zero_notif = {};
 	/* zeroed structure means that BT is OFF */
 	bool bt_is_active = memcmp(notif, &zero_notif, sizeof(*notif));
 
-	if (bt_is_active == mld->bt_is_active)
-		return;
-
+	mld->last_bt_notif = *notif;
 	IWL_DEBUG_INFO(mld, "BT was turned %s\n", bt_is_active ? "ON" : "OFF");
 
-	mld->bt_is_active = bt_is_active;
-
 	iwl_mld_emlsr_check_bt(mld);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/d3.c b/drivers/net/wireless/intel/iwlwifi/mld/d3.c
index 5a7207accd86..339b148d6793 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/d3.c
@@ -774,7 +774,7 @@ iwl_mld_update_ptk_rx_seq(struct iwl_mld *mld,
 		return;
 
 	for (int tid = 0; tid < IWL_MAX_TID_COUNT; tid++) {
-		for (int i = 1; i < mld->trans->num_rx_queues; i++)
+		for (int i = 1; i < mld->trans->info.num_rxqs; i++)
 			memcpy(mld_ptk_pn->q[i].pn[tid],
 			       wowlan_status->ptk.aes_seq[tid].ccmp.pn,
 			       IEEE80211_CCMP_PN_LEN);
@@ -1099,7 +1099,8 @@ iwl_mld_set_netdetect_info(struct iwl_mld *mld,
 		if (!match)
 			return;
 
-		netdetect_info->matches[netdetect_info->n_matches++] = match;
+		netdetect_info->matches[netdetect_info->n_matches] = match;
+		netdetect_info->n_matches++;
 
 		/* We inverted the order of the SSIDs in the scan
 		 * request, so invert the index here.
@@ -1116,9 +1117,11 @@ iwl_mld_set_netdetect_info(struct iwl_mld *mld,
 
 		for_each_set_bit(j,
 				 (unsigned long *)&matches[i].matching_channels[0],
-				 sizeof(matches[i].matching_channels))
-			match->channels[match->n_channels++] =
+				 sizeof(matches[i].matching_channels)) {
+			match->channels[match->n_channels] =
 				netdetect_cfg->channels[j]->center_freq;
+			match->n_channels++;
+		}
 	}
 }
 
@@ -1344,7 +1347,8 @@ int iwl_mld_no_wowlan_suspend(struct iwl_mld *mld)
 	if (ret) {
 		IWL_ERR(mld, "d3 suspend: trans_d3_suspend failed %d\n", ret);
 	} else {
-		mld->trans->system_pm_mode = IWL_PLAT_PM_MODE_D3;
+		/* Async notification might send hcmds, which is not allowed in suspend */
+		iwl_mld_cancel_async_notifications(mld);
 		mld->fw_status.in_d3 = true;
 	}
 
@@ -1369,7 +1373,6 @@ int iwl_mld_no_wowlan_resume(struct iwl_mld *mld)
 
 	IWL_DEBUG_WOWLAN(mld, "Starting the no wowlan resume flow\n");
 
-	mld->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
 	mld->fw_status.in_d3 = false;
 	iwl_fw_dbg_read_d3_debug_data(&mld->fwrt);
 
@@ -1434,7 +1437,7 @@ iwl_mld_suspend_set_ucast_pn(struct iwl_mld *mld, struct ieee80211_sta *sta,
 		ieee80211_get_key_rx_seq(key, tid, &seq);
 
 		/* and use the internal data for all queues */
-		for (int que = 1; que < mld->trans->num_rx_queues; que++) {
+		for (int que = 1; que < mld->trans->info.num_rxqs; que++) {
 			u8 *cur_pn = mld_ptk_pn->q[que].pn[tid];
 
 			if (memcmp(max_pn, cur_pn, IEEE80211_CCMP_PN_LEN) < 0)
@@ -1895,13 +1898,11 @@ int iwl_mld_wowlan_resume(struct iwl_mld *mld)
 	int link_id;
 	int ret;
 	bool fw_err = false;
-	bool keep_connection;
 
 	lockdep_assert_wiphy(mld->wiphy);
 
 	IWL_DEBUG_WOWLAN(mld, "Starting the wowlan resume flow\n");
 
-	mld->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
 	if (!mld->fw_status.in_d3) {
 		IWL_DEBUG_WOWLAN(mld,
 				 "Device_powered_off() was called during wowlan\n");
@@ -1965,7 +1966,7 @@ int iwl_mld_wowlan_resume(struct iwl_mld *mld)
 		iwl_mld_process_netdetect_res(mld, bss_vif, &resume_data);
 		mld->netdetect = false;
 	} else {
-		keep_connection =
+		bool keep_connection =
 			iwl_mld_process_wowlan_status(mld, bss_vif,
 						      resume_data.wowlan_status);
 
@@ -1973,11 +1974,10 @@ int iwl_mld_wowlan_resume(struct iwl_mld *mld)
 		if (keep_connection)
 			iwl_mld_unblock_emlsr(mld, bss_vif,
 					      IWL_MLD_EMLSR_BLOCKED_WOWLAN);
+		else
+			ieee80211_resume_disconnect(bss_vif);
 	}
 
-	if (!mld->netdetect && !keep_connection)
-		ieee80211_resume_disconnect(bss_vif);
-
 	goto out;
 
  err:
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
index 453ce2ba39d1..352da8aa7898 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
@@ -396,8 +396,8 @@ static ssize_t iwl_dbgfs_tas_get_status_read(struct iwl_mld *mld, char *buf,
 		.data[0] = &cmd,
 	};
 	struct iwl_dhc_tas_status_resp *resp = NULL;
+	u32 resp_len = 0;
 	ssize_t pos = 0;
-	u32 resp_len;
 	u32 status;
 	int ret;
 
@@ -546,6 +546,9 @@ iwl_mld_add_debugfs_files(struct iwl_mld *mld, struct dentry *debugfs_dir)
 #endif
 	MLD_DEBUGFS_ADD_FILE(inject_packet, debugfs_dir, 0200);
 
+	debugfs_create_bool("rx_ts_ptp", 0600, debugfs_dir,
+			    &mld->monitor.ptp_time);
+
 	/* Create a symlink with mac80211. It will be removed when mac80211
 	 * exits (before the opmode exits which removes the target.)
 	 */
@@ -949,8 +952,9 @@ void iwl_mld_add_vif_debugfs(struct ieee80211_hw *hw,
 	snprintf(name, sizeof(name), "%pd", vif->debugfs_dir);
 	snprintf(target, sizeof(target), "../../../%pd3/iwlmld",
 		 vif->debugfs_dir);
-	mld_vif->dbgfs_slink =
-		debugfs_create_symlink(name, mld->debugfs_dir, target);
+	if (!mld_vif->dbgfs_slink)
+		mld_vif->dbgfs_slink =
+			debugfs_create_symlink(name, mld->debugfs_dir, target);
 
 	if (iwlmld_mod_params.power_scheme != IWL_POWER_SCHEME_CAM &&
 	    vif->type == NL80211_IFTYPE_STATION) {
@@ -996,8 +1000,8 @@ void iwl_mld_add_link_debugfs(struct ieee80211_hw *hw,
 		mld_link_dir = debugfs_create_dir("iwlmld", dir);
 }
 
-static ssize_t iwl_dbgfs_fixed_rate_write(struct iwl_mld *mld, char *buf,
-					  size_t count, void *data)
+static ssize_t _iwl_dbgfs_fixed_rate_write(struct iwl_mld *mld, char *buf,
+					   size_t count, void *data, bool v3)
 {
 	struct ieee80211_link_sta *link_sta = data;
 	struct iwl_mld_link_sta *mld_link_sta;
@@ -1019,6 +1023,10 @@ static ssize_t iwl_dbgfs_fixed_rate_write(struct iwl_mld *mld, char *buf,
 	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
 		return -EIO;
 
+	/* input is in FW format (v2 or v3) so convert to v3 */
+	rate = iwl_v3_rate_from_v2_v3(cpu_to_le32(rate), v3);
+	rate = le32_to_cpu(iwl_v3_rate_to_v2_v3(rate, mld->fw_rates_ver_3));
+
 	ret = iwl_mld_send_tlc_dhc(mld, fw_sta_id,
 				   partial ? IWL_TLC_DEBUG_PARTIAL_FIXED_RATE :
 					     IWL_TLC_DEBUG_FIXED_RATE,
@@ -1032,6 +1040,18 @@ static ssize_t iwl_dbgfs_fixed_rate_write(struct iwl_mld *mld, char *buf,
 	return ret ? : count;
 }
 
+static ssize_t iwl_dbgfs_fixed_rate_write(struct iwl_mld *mld, char *buf,
+					  size_t count, void *data)
+{
+	return _iwl_dbgfs_fixed_rate_write(mld, buf, count, data, false);
+}
+
+static ssize_t iwl_dbgfs_fixed_rate_v3_write(struct iwl_mld *mld, char *buf,
+					     size_t count, void *data)
+{
+	return _iwl_dbgfs_fixed_rate_write(mld, buf, count, data, true);
+}
+
 static ssize_t iwl_dbgfs_tlc_dhc_write(struct iwl_mld *mld, char *buf,
 				       size_t count, void *data)
 {
@@ -1071,6 +1091,7 @@ static ssize_t iwl_dbgfs_tlc_dhc_write(struct iwl_mld *mld, char *buf,
 
 LINK_STA_WIPHY_DEBUGFS_WRITE_OPS(tlc_dhc, 64);
 LINK_STA_WIPHY_DEBUGFS_WRITE_OPS(fixed_rate, 64);
+LINK_STA_WIPHY_DEBUGFS_WRITE_OPS(fixed_rate_v3, 64);
 
 void iwl_mld_add_link_sta_debugfs(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif,
@@ -1078,5 +1099,6 @@ void iwl_mld_add_link_sta_debugfs(struct ieee80211_hw *hw,
 				  struct dentry *dir)
 {
 	LINK_STA_DEBUGFS_ADD_FILE(fixed_rate, dir, 0200);
+	LINK_STA_DEBUGFS_ADD_FILE(fixed_rate_v3, dir, 0200);
 	LINK_STA_DEBUGFS_ADD_FILE(tlc_dhc, dir, 0200);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/fw.c b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
index 62da137e1024..73ed8d5cab43 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
@@ -8,10 +8,10 @@
 #include "fw/api/alive.h"
 #include "fw/api/scan.h"
 #include "fw/api/rx.h"
+#include "phy.h"
 #include "fw/dbg.h"
 #include "fw/pnvm.h"
 #include "hcmd.h"
-#include "iwl-nvm-parse.h"
 #include "power.h"
 #include "mcc.h"
 #include "led.h"
@@ -49,7 +49,7 @@ static int iwl_mld_send_rss_cfg_cmd(struct iwl_mld *mld)
 	/* Do not direct RSS traffic to Q 0 which is our fallback queue */
 	for (int i = 0; i < ARRAY_SIZE(cmd.indirection_table); i++)
 		cmd.indirection_table[i] =
-			1 + (i % (mld->trans->num_rx_queues - 1));
+			1 + (i % (mld->trans->info.num_rxqs - 1));
 	netdev_rss_key_fill(cmd.secret_key, sizeof(cmd.secret_key));
 
 	return iwl_mld_send_cmd_pdu(mld, RSS_CONFIG_CMD, &cmd);
@@ -99,17 +99,23 @@ static void iwl_mld_alive_imr_data(struct iwl_trans *trans,
 	}
 }
 
+struct iwl_mld_alive_data {
+	__le32 sku_id[3];
+	bool valid;
+};
+
 static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 			 struct iwl_rx_packet *pkt, void *data)
 {
 	unsigned int pkt_len = iwl_rx_packet_payload_len(pkt);
+	unsigned int expected_sz;
 	struct iwl_mld *mld =
 		container_of(notif_wait, struct iwl_mld, notif_wait);
 	struct iwl_trans *trans = mld->trans;
 	u32 version = iwl_fw_lookup_notif_ver(mld->fw, LEGACY_GROUP,
 					      UCODE_ALIVE_NTFY, 0);
-	struct iwl_alive_ntf_v6 *palive;
-	bool *alive_valid = data;
+	struct iwl_mld_alive_data *alive_data = data;
+	struct iwl_alive_ntf *palive;
 	struct iwl_umac_alive *umac;
 	struct iwl_lmac_alive *lmac1;
 	struct iwl_lmac_alive *lmac2 = NULL;
@@ -117,7 +123,19 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 	u32 umac_error_table;
 	u16 status;
 
-	if (version < 6 || version > 7 || pkt_len != sizeof(*palive))
+	switch (version) {
+	case 6:
+	case 7:
+		expected_sz = sizeof(struct iwl_alive_ntf_v6);
+		break;
+	case 8:
+		expected_sz = sizeof(struct iwl_alive_ntf);
+		break;
+	default:
+		return false;
+	}
+
+	if (pkt_len != expected_sz)
 		return false;
 
 	palive = (void *)pkt->data;
@@ -129,12 +147,15 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 	lmac2 = &palive->lmac_data[1];
 	status = le16_to_cpu(palive->status);
 
-	trans->sku_id[0] = le32_to_cpu(palive->sku_id.data[0]);
-	trans->sku_id[1] = le32_to_cpu(palive->sku_id.data[1]);
-	trans->sku_id[2] = le32_to_cpu(palive->sku_id.data[2]);
+	BUILD_BUG_ON(sizeof(alive_data->sku_id) !=
+		     sizeof(palive->sku_id.data));
+	memcpy(alive_data->sku_id, palive->sku_id.data,
+	       sizeof(palive->sku_id.data));
 
 	IWL_DEBUG_FW(mld, "Got sku_id: 0x0%x 0x0%x 0x0%x\n",
-		     trans->sku_id[0], trans->sku_id[1], trans->sku_id[2]);
+		     le32_to_cpu(alive_data->sku_id[0]),
+		     le32_to_cpu(alive_data->sku_id[1]),
+		     le32_to_cpu(alive_data->sku_id[2]));
 
 	lmac_error_event_table =
 		le32_to_cpu(lmac1->dbg_ptrs.error_event_table_ptr);
@@ -147,13 +168,13 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 	umac_error_table = le32_to_cpu(umac->dbg_ptrs.error_info_addr) &
 		~FW_ADDR_CACHE_CONTROL;
 
-	if (umac_error_table >= trans->cfg->min_umac_error_event_table)
+	if (umac_error_table >= trans->mac_cfg->base->min_umac_error_event_table)
 		iwl_fw_umac_set_alive_err_table(trans, umac_error_table);
 	else
 		IWL_ERR(mld, "Not valid error log pointer 0x%08X\n",
 			umac_error_table);
 
-	*alive_valid = status == IWL_ALIVE_STATUS_OK;
+	alive_data->valid = status == IWL_ALIVE_STATUS_OK;
 
 	IWL_DEBUG_FW(mld,
 		     "Alive ucode status 0x%04x revision 0x%01X 0x%01X\n",
@@ -171,6 +192,10 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 		IWL_DEBUG_FW(mld, "FW alive flags 0x%x\n",
 			     le16_to_cpu(palive->flags));
 
+	if (version >= 8)
+		IWL_DEBUG_FW(mld, "platform_id 0x%llx\n",
+			     le64_to_cpu(palive->platform_id));
+
 	iwl_fwrt_update_fw_versions(&mld->fwrt, lmac1, umac);
 
 	return true;
@@ -208,24 +233,22 @@ static void iwl_mld_print_alive_notif_timeout(struct iwl_mld *mld)
 			pc_data->pc_address);
 }
 
-static int iwl_mld_load_fw_wait_alive(struct iwl_mld *mld)
+static int iwl_mld_load_fw_wait_alive(struct iwl_mld *mld,
+				      struct iwl_mld_alive_data *alive_data)
 {
-	const struct fw_img *fw =
-		iwl_get_ucode_image(mld->fw, IWL_UCODE_REGULAR);
 	static const u16 alive_cmd[] = { UCODE_ALIVE_NTFY };
 	struct iwl_notification_wait alive_wait;
-	bool alive_valid = false;
 	int ret;
 
 	lockdep_assert_wiphy(mld->wiphy);
 
 	iwl_init_notification_wait(&mld->notif_wait, &alive_wait,
 				   alive_cmd, ARRAY_SIZE(alive_cmd),
-				   iwl_alive_fn, &alive_valid);
+				   iwl_alive_fn, alive_data);
 
 	iwl_dbg_tlv_time_point(&mld->fwrt, IWL_FW_INI_TIME_POINT_EARLY, NULL);
 
-	ret = iwl_trans_start_fw(mld->trans, fw, true);
+	ret = iwl_trans_start_fw(mld->trans, mld->fw, IWL_UCODE_REGULAR, true);
 	if (ret) {
 		iwl_remove_notification(&mld->notif_wait, &alive_wait);
 		return ret;
@@ -239,28 +262,26 @@ static int iwl_mld_load_fw_wait_alive(struct iwl_mld *mld)
 			iwl_fw_dbg_error_collect(&mld->fwrt,
 						 FW_DBG_TRIGGER_ALIVE_TIMEOUT);
 		iwl_mld_print_alive_notif_timeout(mld);
-		goto alive_failure;
+		return ret;
 	}
 
-	if (!alive_valid) {
+	if (!alive_data->valid) {
 		IWL_ERR(mld, "Loaded firmware is not valid!\n");
-		ret = -EIO;
-		goto alive_failure;
+		return -EIO;
 	}
 
-	iwl_trans_fw_alive(mld->trans, 0);
+	iwl_trans_fw_alive(mld->trans);
 
 	return 0;
-
-alive_failure:
-	iwl_trans_stop_device(mld->trans);
-	return ret;
 }
 
 static int iwl_mld_run_fw_init_sequence(struct iwl_mld *mld)
 {
 	struct iwl_notification_wait init_wait;
-	struct iwl_init_extended_cfg_cmd init_cfg = {};
+	struct iwl_init_extended_cfg_cmd init_cfg = {
+		.init_flags = cpu_to_le32(BIT(IWL_INIT_PHY)),
+	};
+	struct iwl_mld_alive_data alive_data = {};
 	static const u16 init_complete[] = {
 		INIT_COMPLETE_NOTIF,
 	};
@@ -268,19 +289,15 @@ static int iwl_mld_run_fw_init_sequence(struct iwl_mld *mld)
 
 	lockdep_assert_wiphy(mld->wiphy);
 
-	ret = iwl_mld_load_fw_wait_alive(mld);
+	ret = iwl_mld_load_fw_wait_alive(mld, &alive_data);
 	if (ret)
 		return ret;
 
-	mld->trans->step_urm =
-		!!(iwl_read_umac_prph(mld->trans, CNVI_PMU_STEP_FLOW) &
-		   CNVI_PMU_STEP_FLOW_FORCE_URM);
-
 	ret = iwl_pnvm_load(mld->trans, &mld->notif_wait,
-			    &mld->fw->ucode_capa);
+			    &mld->fw->ucode_capa, alive_data.sku_id);
 	if (ret) {
 		IWL_ERR(mld, "Timeout waiting for PNVM load %d\n", ret);
-		goto init_failure;
+		return ret;
 	}
 
 	iwl_dbg_tlv_time_point(&mld->fwrt, IWL_FW_INI_TIME_POINT_AFTER_ALIVE,
@@ -298,31 +315,24 @@ static int iwl_mld_run_fw_init_sequence(struct iwl_mld *mld)
 	if (ret) {
 		IWL_ERR(mld, "Failed to send init config command: %d\n", ret);
 		iwl_remove_notification(&mld->notif_wait, &init_wait);
-		goto init_failure;
+		return ret;
+	}
+
+	ret = iwl_mld_send_phy_cfg_cmd(mld);
+	if (ret) {
+		IWL_ERR(mld, "Failed to send PHY config command: %d\n", ret);
+		iwl_remove_notification(&mld->notif_wait, &init_wait);
+		return ret;
 	}
 
 	ret = iwl_wait_notification(&mld->notif_wait, &init_wait,
 				    MLD_INIT_COMPLETE_TIMEOUT);
 	if (ret) {
 		IWL_ERR(mld, "Failed to get INIT_COMPLETE %d\n", ret);
-		goto init_failure;
-	}
-
-	if (!mld->nvm_data) {
-		mld->nvm_data = iwl_get_nvm(mld->trans, mld->fw, 0, 0);
-		if (IS_ERR(mld->nvm_data)) {
-			ret = PTR_ERR(mld->nvm_data);
-			mld->nvm_data = NULL;
-			IWL_ERR(mld, "Failed to read NVM: %d\n", ret);
-			goto init_failure;
-		}
+		return ret;
 	}
 
 	return 0;
-
-init_failure:
-	iwl_trans_stop_device(mld->trans);
-	return ret;
 }
 
 int iwl_mld_load_fw(struct iwl_mld *mld)
@@ -337,15 +347,18 @@ int iwl_mld_load_fw(struct iwl_mld *mld)
 
 	ret = iwl_mld_run_fw_init_sequence(mld);
 	if (ret)
-		return ret;
+		goto err;
 
 	ret = iwl_mld_init_mcc(mld);
 	if (ret)
-		return ret;
+		goto err;
 
 	mld->fw_status.running = true;
 
 	return 0;
+err:
+	iwl_mld_stop_fw(mld);
+	return ret;
 }
 
 void iwl_mld_stop_fw(struct iwl_mld *mld)
@@ -358,6 +371,11 @@ void iwl_mld_stop_fw(struct iwl_mld *mld)
 
 	iwl_trans_stop_device(mld->trans);
 
+	/* HW is stopped, no more coming RX. Cancel all notifications in
+	 * case they were sent just before stopping the HW.
+	 */
+	iwl_mld_cancel_async_notifications(mld);
+
 	mld->fw_status.running = false;
 }
 
@@ -519,7 +537,7 @@ int iwl_mld_start_fw(struct iwl_mld *mld)
 	ret = iwl_mld_load_fw(mld);
 	if (IWL_FW_CHECK(mld, ret, "Failed to start firmware %d\n", ret)) {
 		iwl_fw_dbg_error_collect(&mld->fwrt, FW_DBG_TRIGGER_DRIVER);
-		goto error;
+		return ret;
 	}
 
 	IWL_DEBUG_INFO(mld, "uCode started.\n");
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.c b/drivers/net/wireless/intel/iwlwifi/mld/iface.c
index e49e2260ac05..235b55e0fe59 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/iface.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.c
@@ -22,9 +22,17 @@ void iwl_mld_cleanup_vif(void *data, u8 *mac, struct ieee80211_vif *vif)
 	struct iwl_mld *mld = mld_vif->mld;
 	struct iwl_mld_link *link;
 
+	mld_vif->emlsr.blocked_reasons &= ~IWL_MLD_EMLSR_BLOCKED_ROC;
+
+	if (mld_vif->aux_sta.sta_id != IWL_INVALID_STA)
+		iwl_mld_free_internal_sta(mld, &mld_vif->aux_sta);
+
 	/* EMLSR is turned back on during recovery */
 	vif->driver_flags &= ~IEEE80211_VIF_EML_ACTIVE;
 
+	if (mld_vif->roc_activity != ROC_NUM_ACTIVITIES)
+		ieee80211_remain_on_channel_expired(mld->hw);
+
 	mld_vif->roc_activity = ROC_NUM_ACTIVITIES;
 
 	for_each_mld_vif_valid_link(mld_vif, link) {
@@ -103,6 +111,24 @@ static bool iwl_mld_is_nic_ack_enabled(struct iwl_mld *mld,
 			       IEEE80211_HE_MAC_CAP2_ACK_EN);
 }
 
+static void iwl_mld_set_he_support(struct iwl_mld *mld,
+				   struct ieee80211_vif *vif,
+				   struct iwl_mac_config_cmd *cmd,
+				   int cmd_ver)
+{
+	if (vif->type == NL80211_IFTYPE_AP) {
+		if (cmd_ver == 2)
+			cmd->wifi_gen_v2.he_ap_support = cpu_to_le16(1);
+		else
+			cmd->wifi_gen.he_ap_support = 1;
+	} else {
+		if (cmd_ver == 2)
+			cmd->wifi_gen_v2.he_support = cpu_to_le16(1);
+		else
+			cmd->wifi_gen.he_support = 1;
+	}
+}
+
 /* fill the common part for all interface types */
 static void iwl_mld_mac_cmd_fill_common(struct iwl_mld *mld,
 					struct ieee80211_vif *vif,
@@ -112,6 +138,9 @@ static void iwl_mld_mac_cmd_fill_common(struct iwl_mld *mld,
 	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
 	struct ieee80211_bss_conf *link_conf;
 	unsigned int link_id;
+	int cmd_ver = iwl_fw_lookup_cmd_ver(mld->fw,
+					    WIDE_ID(MAC_CONF_GROUP,
+						    MAC_CONFIG_CMD), 0);
 
 	lockdep_assert_wiphy(mld->wiphy);
 
@@ -138,12 +167,11 @@ static void iwl_mld_mac_cmd_fill_common(struct iwl_mld *mld,
 	 * and enable both when we have MLO.
 	 */
 	if (ieee80211_vif_is_mld(vif)) {
-		if (vif->type == NL80211_IFTYPE_AP)
-			cmd->he_ap_support = cpu_to_le16(1);
+		iwl_mld_set_he_support(mld, vif, cmd, cmd_ver);
+		if (cmd_ver == 2)
+			cmd->wifi_gen_v2.eht_support = cpu_to_le32(1);
 		else
-			cmd->he_support = cpu_to_le16(1);
-
-		cmd->eht_support = cpu_to_le32(1);
+			cmd->wifi_gen.eht_support = 1;
 		return;
 	}
 
@@ -151,10 +179,7 @@ static void iwl_mld_mac_cmd_fill_common(struct iwl_mld *mld,
 		if (!link_conf->he_support)
 			continue;
 
-		if (vif->type == NL80211_IFTYPE_AP)
-			cmd->he_ap_support = cpu_to_le16(1);
-		else
-			cmd->he_support = cpu_to_le16(1);
+		iwl_mld_set_he_support(mld, vif, cmd, cmd_ver);
 
 		/* EHT, if supported, was already set above */
 		break;
@@ -226,11 +251,6 @@ static void iwl_mld_fill_mac_cmd_sta(struct iwl_mld *mld,
 	if (vif->probe_req_reg && vif->cfg.assoc && vif->p2p)
 		cmd->filter_flags |=
 			cpu_to_le32(MAC_CFG_FILTER_ACCEPT_PROBE_REQ);
-
-	if (vif->p2p)
-		cmd->client.ctwin =
-			cpu_to_le32(vif->bss_conf.p2p_noa_attr.oppps_ctwindow &
-				    IEEE80211_P2P_OPPPS_CTWINDOW_MASK);
 }
 
 static void iwl_mld_fill_mac_cmd_ap(struct iwl_mld *mld,
@@ -393,6 +413,7 @@ iwl_mld_init_vif(struct iwl_mld *mld, struct ieee80211_vif *vif)
 		wiphy_delayed_work_init(&mld_vif->emlsr.tmp_non_bss_done_wk,
 					iwl_mld_emlsr_tmp_non_bss_done_wk);
 	}
+	iwl_mld_init_internal_sta(&mld_vif->aux_sta);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.h b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
index d1d56b081bf6..49e2ce65557d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/iface.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
@@ -10,6 +10,7 @@
 #include "link.h"
 #include "session-protect.h"
 #include "d3.h"
+#include "fw/api/time-event.h"
 
 enum iwl_mld_cca_40mhz_wa_status {
 	CCA_40_MHZ_WA_NONE,
@@ -59,6 +60,7 @@ enum iwl_mld_emlsr_blocked {
  *	loaded enough to justify EMLSR.
  * @IWL_MLD_EMLSR_EXIT_RFI: Exit EMLSR due to RFI
  * @IWL_MLD_EMLSR_EXIT_FW_REQUEST: Exit EMLSR because the FW requested it
+ * @IWL_MLD_EMLSR_EXIT_INVALID: internal exit reason due to invalid data
  */
 enum iwl_mld_emlsr_exit {
 	IWL_MLD_EMLSR_EXIT_BLOCK		= 0x1,
@@ -72,6 +74,7 @@ enum iwl_mld_emlsr_exit {
 	IWL_MLD_EMLSR_EXIT_CHAN_LOAD		= 0x100,
 	IWL_MLD_EMLSR_EXIT_RFI			= 0x200,
 	IWL_MLD_EMLSR_EXIT_FW_REQUEST		= 0x400,
+	IWL_MLD_EMLSR_EXIT_INVALID		= 0x800,
 };
 
 /**
@@ -123,8 +126,6 @@ struct iwl_mld_emlsr {
  *	Only valid for STA. (FIXME: needs to be per link)
  * @num_associated_stas: number of associated STAs. Relevant only for AP mode.
  * @ap_ibss_active: whether the AP/IBSS was started
- * @roc_activity: the id of the roc_activity running. Relevant for p2p device
- *	only. Set to %ROC_NUM_ACTIVITIES when not in use.
  * @cca_40mhz_workaround: When we are connected in 2.4 GHz and 40 MHz, and the
  *	environment is too loaded, we work around this by reconnecting to the
  *	same AP with 20 MHz. This manages the status of the workaround.
@@ -140,6 +141,9 @@ struct iwl_mld_emlsr {
  * @use_ps_poll: use ps_poll frames
  * @disable_bf: disable beacon filter
  * @dbgfs_slink: debugfs symlink for this interface
+ * @roc_activity: the id of the roc_activity running. Relevant for STA and
+ *	p2p device only. Set to %ROC_NUM_ACTIVITIES when not in use.
+ * @aux_sta: station used for remain on channel. Used in P2P device.
  */
 struct iwl_mld_vif {
 	/* Add here fields that need clean up on restart */
@@ -151,7 +155,6 @@ struct iwl_mld_vif {
 		struct ieee80211_key_conf __rcu *bigtks[2];
 		u8 num_associated_stas;
 		bool ap_ibss_active;
-		u32 roc_activity;
 		enum iwl_mld_cca_40mhz_wa_status cca_40mhz_workaround;
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 		bool beacon_inject_active;
@@ -166,7 +169,7 @@ struct iwl_mld_vif {
 
 	struct iwl_mld_emlsr emlsr;
 
-#if CONFIG_PM_SLEEP
+#ifdef CONFIG_PM_SLEEP
 	struct iwl_mld_wowlan_data wowlan_data;
 #endif
 #ifdef CONFIG_IWLWIFI_DEBUGFS
@@ -174,6 +177,8 @@ struct iwl_mld_vif {
 	bool disable_bf;
 	struct dentry *dbgfs_slink;
 #endif
+	enum iwl_roc_activity roc_activity;
+	struct iwl_mld_int_sta aux_sta;
 };
 
 static inline struct iwl_mld_vif *
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.c b/drivers/net/wireless/intel/iwlwifi/mld/link.c
index 82a4979a3af3..d0f56189ad3f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/link.c
@@ -580,7 +580,7 @@ iwl_mld_get_omi_bw_reduction_pointers(struct iwl_mld *mld,
 
 	*link_sta = NULL;
 
-	if (mld->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_SC)
+	if (mld->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_SC)
 		return NULL;
 
 	vif = iwl_mld_get_bss_vif(mld);
@@ -782,10 +782,11 @@ iwl_mld_init_link(struct iwl_mld *mld, struct ieee80211_bss_conf *link,
 
 	iwl_mld_init_internal_sta(&mld_link->bcast_sta);
 	iwl_mld_init_internal_sta(&mld_link->mcast_sta);
-	iwl_mld_init_internal_sta(&mld_link->aux_sta);
+	iwl_mld_init_internal_sta(&mld_link->mon_sta);
 
-	wiphy_delayed_work_init(&mld_link->rx_omi.finished_work,
-				iwl_mld_omi_bw_finished_work);
+	if (!mld->fw_status.in_hw_restart)
+		wiphy_delayed_work_init(&mld_link->rx_omi.finished_work,
+					iwl_mld_omi_bw_finished_work);
 
 	return iwl_mld_allocate_link_fw_id(mld, &mld_link->fw_id, link);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.h b/drivers/net/wireless/intel/iwlwifi/mld/link.h
index 42b7bdcbd741..39f04aae5579 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/link.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/link.h
@@ -39,7 +39,7 @@ struct iwl_probe_resp_data {
  * @vif: the vif this link belongs to
  * @bcast_sta: station used for broadcast packets. Used in AP, GO and IBSS.
  * @mcast_sta: station used for multicast packets. Used in AP, GO and IBSS.
- * @aux_sta: station used for remain on channel. Used in P2P device.
+ * @mon_sta: station used for TX injection in monitor interface.
  * @link_id: over the air link ID
  * @ap_early_keys: The firmware cannot install keys before bcast/mcast STAs,
  *	but higher layers work differently, so we store the keys here for
@@ -72,7 +72,7 @@ struct iwl_mld_link {
 	struct ieee80211_vif *vif;
 	struct iwl_mld_int_sta bcast_sta;
 	struct iwl_mld_int_sta mcast_sta;
-	struct iwl_mld_int_sta aux_sta;
+	struct iwl_mld_int_sta mon_sta;
 	u8 link_id;
 
 	struct {
@@ -89,7 +89,7 @@ struct iwl_mld_link {
 	struct iwl_probe_resp_data __rcu *probe_resp_data;
 };
 
-/* Cleanup function for struct iwl_mld_phy, will be called in restart */
+/* Cleanup function for struct iwl_mld_link, will be called in restart */
 static inline void
 iwl_mld_cleanup_link(struct iwl_mld *mld, struct iwl_mld_link *link)
 {
@@ -105,8 +105,8 @@ iwl_mld_cleanup_link(struct iwl_mld *mld, struct iwl_mld_link *link)
 		iwl_mld_free_internal_sta(mld, &link->bcast_sta);
 	if (link->mcast_sta.sta_id != IWL_INVALID_STA)
 		iwl_mld_free_internal_sta(mld, &link->mcast_sta);
-	if (link->aux_sta.sta_id != IWL_INVALID_STA)
-		iwl_mld_free_internal_sta(mld, &link->aux_sta);
+	if (link->mon_sta.sta_id != IWL_INVALID_STA)
+		iwl_mld_free_internal_sta(mld, &link->mon_sta);
 }
 
 /* Convert a percentage from [0,100] to [0,255] */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c b/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
index a4a612afb3b3..f7faa87b8ba6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
@@ -21,7 +21,7 @@ static bool iwl_mld_calc_low_latency(struct iwl_mld *mld,
 {
 	struct iwl_mld_low_latency *ll = &mld->low_latency;
 	bool global_low_latency = false;
-	u8 num_rx_q = mld->trans->num_rx_queues;
+	u8 num_rx_q = mld->trans->info.num_rxqs;
 
 	for (int mac_id = 0; mac_id < NUM_MAC_INDEX_DRIVER; mac_id++) {
 		u32 total_vo_vi_pkts = 0;
@@ -131,12 +131,12 @@ int iwl_mld_low_latency_init(struct iwl_mld *mld)
 	struct iwl_mld_low_latency *ll = &mld->low_latency;
 	unsigned long ts = jiffies;
 
-	ll->pkts_counters = kcalloc(mld->trans->num_rx_queues,
+	ll->pkts_counters = kcalloc(mld->trans->info.num_rxqs,
 				    sizeof(*ll->pkts_counters), GFP_KERNEL);
 	if (!ll->pkts_counters)
 		return -ENOMEM;
 
-	for (int q = 0; q < mld->trans->num_rx_queues; q++)
+	for (int q = 0; q < mld->trans->info.num_rxqs; q++)
 		spin_lock_init(&ll->pkts_counters[q].lock);
 
 	wiphy_delayed_work_init(&ll->work, iwl_mld_low_latency_wk);
@@ -167,7 +167,7 @@ void iwl_mld_low_latency_restart_cleanup(struct iwl_mld *mld)
 	memset(ll->window_start, 0, sizeof(ll->window_start));
 	memset(ll->result, 0, sizeof(ll->result));
 
-	for (int q = 0; q < mld->trans->num_rx_queues; q++)
+	for (int q = 0; q < mld->trans->info.num_rxqs; q++)
 		memset(ll->pkts_counters[q].vo_vi, 0,
 		       sizeof(ll->pkts_counters[q].vo_vi));
 }
@@ -276,7 +276,7 @@ void iwl_mld_low_latency_update_counters(struct iwl_mld *mld,
 		return;
 
 	if (WARN_ON_ONCE(fw_id >= ARRAY_SIZE(counters->vo_vi) ||
-			 queue >= mld->trans->num_rx_queues))
+			 queue >= mld->trans->info.num_rxqs))
 		return;
 
 	if (mld->low_latency.stopped)
@@ -324,7 +324,7 @@ void iwl_mld_low_latency_restart(struct iwl_mld *mld)
 		ll->window_start[mac] = 0;
 		low_latency |= ll->result[mac];
 
-		for (int q = 0; q < mld->trans->num_rx_queues; q++) {
+		for (int q = 0; q < mld->trans->info.num_rxqs; q++) {
 			spin_lock_bh(&ll->pkts_counters[q].lock);
 			ll->pkts_counters[q].vo_vi[mac] = 0;
 			spin_unlock_bh(&ll->pkts_counters[q].lock);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
index 6851064b82da..4ba050397632 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -243,7 +243,6 @@ static void iwl_mac_hw_set_flags(struct iwl_mld *mld)
 	ieee80211_hw_set(hw, TX_AMPDU_SETUP_IN_HW);
 	ieee80211_hw_set(hw, HAS_RATE_CONTROL);
 	ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
-	ieee80211_hw_set(hw, DISALLOW_PUNCTURING_5GHZ);
 	ieee80211_hw_set(hw, SINGLE_SCAN_ON_ALL_BANDS);
 	ieee80211_hw_set(hw, SUPPORTS_AMSDU_IN_AMPDU);
 	ieee80211_hw_set(hw, TDLS_WIDER_BW);
@@ -305,7 +304,7 @@ static void iwl_mac_hw_set_wiphy(struct iwl_mld *mld)
 
 	wiphy->max_remain_on_channel_duration = 10000;
 
-	wiphy->hw_version = mld->trans->hw_id;
+	wiphy->hw_version = mld->trans->info.hw_id;
 
 	wiphy->hw_timestamp_max_peers = 1;
 
@@ -351,9 +350,9 @@ static void iwl_mac_hw_set_misc(struct iwl_mld *mld)
 	hw->queues = IEEE80211_NUM_ACS;
 
 	hw->netdev_features = NETIF_F_HIGHDMA | NETIF_F_SG;
-	hw->netdev_features |= mld->cfg->features;
+	hw->netdev_features |= mld->trans->mac_cfg->base->features;
 
-	hw->max_tx_fragments = mld->trans->max_skb_frags;
+	hw->max_tx_fragments = mld->trans->info.max_skb_frags;
 	hw->max_listen_interval = IWL_MLD_CONN_LISTEN_INTERVAL;
 
 	hw->uapsd_max_sp_len = IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL;
@@ -376,6 +375,24 @@ static void iwl_mac_hw_set_misc(struct iwl_mld *mld)
 
 static int iwl_mld_hw_verify_preconditions(struct iwl_mld *mld)
 {
+	int ratecheck;
+
+	/* check for rates version 3 */
+	ratecheck =
+		(iwl_fw_lookup_cmd_ver(mld->fw, TX_CMD, 0) >= 11) +
+		(iwl_fw_lookup_notif_ver(mld->fw, DATA_PATH_GROUP,
+					 TLC_MNG_UPDATE_NOTIF, 0) >= 4) +
+		(iwl_fw_lookup_notif_ver(mld->fw, LEGACY_GROUP,
+					 REPLY_RX_MPDU_CMD, 0) >= 6) +
+		(iwl_fw_lookup_notif_ver(mld->fw, DATA_PATH_GROUP,
+					 RX_NO_DATA_NOTIF, 0) >= 4) +
+		(iwl_fw_lookup_notif_ver(mld->fw, LONG_GROUP, TX_CMD, 0) >= 9);
+
+	if (ratecheck != 0 && ratecheck != 5) {
+		IWL_ERR(mld, "Firmware has inconsistent rates\n");
+		return -EINVAL;
+	}
+
 	/* 11ax is expected to be enabled for all supported devices */
 	if (WARN_ON(!mld->nvm_data->sku_cap_11ax_enable))
 		return -EINVAL;
@@ -475,8 +492,8 @@ static
 int iwl_mld_mac80211_start(struct ieee80211_hw *hw)
 {
 	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
-	int ret;
 	bool in_d3 = false;
+	int ret = 0;
 
 	lockdep_assert_wiphy(mld->wiphy);
 
@@ -537,18 +554,10 @@ void iwl_mld_mac80211_stop(struct ieee80211_hw *hw, bool suspend)
 	/* if the suspend flow fails the fw is in error. Stop it here, and it
 	 * will be started upon wakeup
 	 */
-	if (!suspend || iwl_mld_no_wowlan_suspend(mld))
+	if (!suspend ||
+	    (IS_ENABLED(CONFIG_PM_SLEEP) && iwl_mld_no_wowlan_suspend(mld)))
 		iwl_mld_stop_fw(mld);
 
-	/* HW is stopped, no more coming RX. OTOH, the worker can't run as the
-	 * wiphy lock is held. Cancel it in case it was scheduled just before
-	 * we stopped the HW.
-	 */
-	wiphy_work_cancel(mld->wiphy, &mld->async_handlers_wk);
-
-	/* Empty out the list, as the worker won't do that */
-	iwl_mld_purge_async_handlers_list(mld);
-
 	/* Clear in_hw_restart flag when stopping the hw, as mac80211 won't
 	 * execute the restart.
 	 */
@@ -650,6 +659,7 @@ void iwl_mld_mac80211_remove_interface(struct ieee80211_hw *hw,
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 	debugfs_remove(iwl_mld_vif_from_mac80211(vif)->dbgfs_slink);
+	iwl_mld_vif_from_mac80211(vif)->dbgfs_slink = NULL;
 #endif
 
 	iwl_mld_rm_vif(mld, vif);
@@ -895,9 +905,8 @@ void iwl_mld_change_chanctx(struct ieee80211_hw *hw,
 			return;
 	}
 update:
-	phy->chandef = *chandef;
 
-	iwl_mld_phy_fw_action(mld, ctx, FW_CTXT_ACTION_MODIFY);
+	iwl_mld_update_phy_chandef(mld, ctx);
 }
 
 static u8
@@ -1029,12 +1038,19 @@ int iwl_mld_assign_vif_chanctx(struct ieee80211_hw *hw,
 		iwl_mld_send_ap_tx_power_constraint_cmd(mld, vif, link);
 
 	if (vif->type == NL80211_IFTYPE_MONITOR) {
-		/* TODO: task=sniffer add sniffer station */
+		ret = iwl_mld_add_mon_sta(mld, vif, link);
+		if (ret)
+			goto deactivate_link;
+
 		mld->monitor.p80 =
 			iwl_mld_chandef_get_primary_80(&vif->bss_conf.chanreq.oper);
 	}
 
 	return 0;
+
+deactivate_link:
+	if (mld_link->active)
+		iwl_mld_deactivate_link(mld, link);
 err:
 	RCU_INIT_POINTER(mld_link->chan_ctx, NULL);
 	return ret;
@@ -1060,7 +1076,8 @@ void iwl_mld_unassign_vif_chanctx(struct ieee80211_hw *hw,
 
 	iwl_mld_deactivate_link(mld, link);
 
-	/* TODO: task=sniffer remove sniffer station */
+	if (vif->type == NL80211_IFTYPE_MONITOR)
+		iwl_mld_remove_mon_sta(mld, vif, link);
 
 	if (n_active > 1) {
 		/* Indicate to mac80211 that EML is disabled */
@@ -1256,9 +1273,14 @@ iwl_mld_mac80211_link_info_changed(struct ieee80211_hw *hw,
 }
 
 static void
-iwl_mld_smps_wa(struct iwl_mld *mld, struct ieee80211_vif *vif, bool enable)
+iwl_mld_smps_workaround(struct iwl_mld *mld, struct ieee80211_vif *vif, bool enable)
 {
 	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	bool workaround_required =
+		iwl_fw_lookup_cmd_ver(mld->fw, MAC_PM_POWER_TABLE, 0) < 2;
+
+	if (!workaround_required)
+		return;
 
 	/* Send the device-level power commands since the
 	 * firmware checks the POWER_TABLE_CMD's POWER_SAVE_EN bit to
@@ -1305,7 +1327,7 @@ void iwl_mld_mac80211_vif_cfg_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changes & BSS_CHANGED_PS) {
-		iwl_mld_smps_wa(mld, vif, vif->cfg.ps);
+		iwl_mld_smps_workaround(mld, vif, vif->cfg.ps);
 		iwl_mld_update_mac_power(mld, vif, false);
 	}
 
@@ -1318,13 +1340,22 @@ iwl_mld_mac80211_hw_scan(struct ieee80211_hw *hw,
 			 struct ieee80211_scan_request *hw_req)
 {
 	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	int ret;
 
 	if (WARN_ON(!hw_req->req.n_channels ||
 		    hw_req->req.n_channels >
 		    mld->fw->ucode_capa.n_scan_channels))
 		return -EINVAL;
 
-	return iwl_mld_regular_scan_start(mld, vif, &hw_req->req, &hw_req->ies);
+	ret = iwl_mld_regular_scan_start(mld, vif, &hw_req->req, &hw_req->ies);
+	if (!ret) {
+		/* We will be busy with scanning, so the counters may not reflect the
+		 * reality. Stop checking the counters until the scan ends
+		 */
+		iwl_mld_start_ignoring_tpt_updates(mld);
+	}
+
+	return ret;
 }
 
 static void
@@ -1340,8 +1371,11 @@ iwl_mld_mac80211_cancel_hw_scan(struct ieee80211_hw *hw,
 	 * cancel scan before ieee80211_scan_work() could run.
 	 * To handle that, simply return if the scan is not running.
 	 */
-	if (mld->scan.status & IWL_MLD_SCAN_REGULAR)
+	if (mld->scan.status & IWL_MLD_SCAN_REGULAR) {
 		iwl_mld_scan_stop(mld, IWL_MLD_SCAN_REGULAR, true);
+		/* Scan is over, we can check again the tpt counters */
+		iwl_mld_stop_ignoring_tpt_updates(mld);
+	}
 }
 
 static int
@@ -1718,7 +1752,7 @@ static int iwl_mld_move_sta_state_up(struct iwl_mld *mld,
 						    FW_CTXT_ACTION_MODIFY);
 			if (ret)
 				return ret;
-			iwl_mld_smps_wa(mld, vif, vif->cfg.ps);
+			iwl_mld_smps_workaround(mld, vif, vif->cfg.ps);
 		}
 
 		/* MFP is set by default before the station is authorized.
@@ -1761,7 +1795,7 @@ static int iwl_mld_move_sta_state_down(struct iwl_mld *mld,
 						  &mld_vif->emlsr.check_tpt_wk);
 
 			iwl_mld_reset_cca_40mhz_workaround(mld, vif);
-			iwl_mld_smps_wa(mld, vif, true);
+			iwl_mld_smps_workaround(mld, vif, true);
 		}
 
 		/* once we move into assoc state, need to update the FW to
@@ -1943,6 +1977,7 @@ static void iwl_mld_sta_rc_update(struct ieee80211_hw *hw,
 	}
 }
 
+#ifdef CONFIG_PM_SLEEP
 static void iwl_mld_set_wakeup(struct ieee80211_hw *hw, bool enabled)
 {
 	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
@@ -1994,13 +2029,14 @@ static int iwl_mld_resume(struct ieee80211_hw *hw)
 
 	return 0;
 }
+#endif
 
 static int iwl_mld_alloc_ptk_pn(struct iwl_mld *mld,
 				struct iwl_mld_sta *mld_sta,
 				struct ieee80211_key_conf *key,
 				struct iwl_mld_ptk_pn **ptk_pn)
 {
-	u8 num_rx_queues = mld->trans->num_rx_queues;
+	u8 num_rx_queues = mld->trans->info.num_rxqs;
 	int keyidx = key->keyidx;
 	struct ieee80211_key_seq seq;
 
@@ -2456,15 +2492,17 @@ iwl_mld_change_vif_links(struct ieee80211_hw *hw,
 		added |= BIT(0);
 
 	for (int i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) {
-		if (removed & BIT(i))
+		if (removed & BIT(i) && !WARN_ON(!old[i]))
 			iwl_mld_remove_link(mld, old[i]);
 	}
 
 	for (int i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) {
 		if (added & BIT(i)) {
 			link_conf = link_conf_dereference_protected(vif, i);
-			if (WARN_ON(!link_conf))
-				return -EINVAL;
+			if (!link_conf) {
+				err = -EINVAL;
+				goto remove_added_links;
+			}
 
 			err = iwl_mld_add_link(mld, link_conf);
 			if (err)
@@ -2499,7 +2537,11 @@ remove_added_links:
 		iwl_mld_remove_link(mld, link_conf);
 	}
 
-	return err;
+	if (WARN_ON(!iwl_mld_error_before_recovery(mld)))
+		return err;
+
+	/* reconfig will fix us anyway */
+	return 0;
 }
 
 static int iwl_mld_change_sta_links(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mcc.c b/drivers/net/wireless/intel/iwlwifi/mld/mcc.c
index daca14e208bd..19cb562e7a73 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mcc.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mcc.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  */
 
 #include <net/cfg80211.h>
@@ -158,7 +158,7 @@ iwl_mld_get_regdomain(struct iwl_mld *mld,
 	}
 	IWL_DEBUG_LAR(mld, "MCC update response version: %d\n", resp_ver);
 
-	regd = iwl_parse_nvm_mcc_info(mld->trans->dev, mld->cfg,
+	regd = iwl_parse_nvm_mcc_info(mld->trans,
 				      __le32_to_cpu(resp->n_channels),
 				      resp->channels,
 				      __le16_to_cpu(resp->mcc),
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.c b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
index d4a99ae64074..8cdd960c5245 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
@@ -26,6 +26,8 @@
 #include "hcmd.h"
 #include "fw/api/location.h"
 
+#include "iwl-nvm-parse.h"
+
 #define DRV_DESCRIPTION "Intel(R) MLD wireless driver for Linux"
 MODULE_DESCRIPTION(DRV_DESCRIPTION);
 MODULE_LICENSE("GPL");
@@ -60,7 +62,7 @@ static void iwl_mld_hw_set_regulatory(struct iwl_mld *mld)
 
 VISIBLE_IF_IWLWIFI_KUNIT
 void iwl_construct_mld(struct iwl_mld *mld, struct iwl_trans *trans,
-		       const struct iwl_cfg *cfg, const struct iwl_fw *fw,
+		       const struct iwl_rf_cfg *cfg, const struct iwl_fw *fw,
 		       struct ieee80211_hw *hw, struct dentry *dbgfs_dir)
 {
 	mld->dev = trans->dev;
@@ -191,6 +193,7 @@ static const struct iwl_hcmd_names iwl_mld_system_names[] = {
 	HCMD_NAME(SOC_CONFIGURATION_CMD),
 	HCMD_NAME(INIT_EXTENDED_CFG_CMD),
 	HCMD_NAME(FW_ERROR_RECOVERY_CMD),
+	HCMD_NAME(RFI_CONFIG_CMD),
 	HCMD_NAME(RFI_GET_FREQ_TABLE_CMD),
 	HCMD_NAME(SYSTEM_STATISTICS_CMD),
 	HCMD_NAME(SYSTEM_STATISTICS_END_NOTIF),
@@ -286,7 +289,9 @@ static const struct iwl_hcmd_names iwl_mld_statistics_names[] = {
  * Access is done through binary search
  */
 static const struct iwl_hcmd_names iwl_mld_prot_offload_names[] = {
-	HCMD_NAME(STORED_BEACON_NTF),
+	HCMD_NAME(WOWLAN_WAKE_PKT_NOTIFICATION),
+	HCMD_NAME(WOWLAN_INFO_NOTIFICATION),
+	HCMD_NAME(D3_END_NOTIFICATION),
 };
 
 /* Please keep this array *SORTED* by hex value.
@@ -321,33 +326,40 @@ EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(global_iwl_mld_goups_size);
 static void
 iwl_mld_configure_trans(struct iwl_op_mode *op_mode)
 {
-	const struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
 	static const u8 no_reclaim_cmds[] = {TX_CMD};
-	struct iwl_trans_config trans_cfg = {
-		.op_mode = op_mode,
-		/* Rx is not supported yet, but add it to avoid warnings */
-		.rx_buf_size = iwl_amsdu_size_to_rxb_size(),
-		.command_groups = iwl_mld_groups,
-		.command_groups_size = ARRAY_SIZE(iwl_mld_groups),
-		.fw_reset_handshake = true,
-		.queue_alloc_cmd_ver =
-			iwl_fw_lookup_cmd_ver(mld->fw,
-					      WIDE_ID(DATA_PATH_GROUP,
-						      SCD_QUEUE_CONFIG_CMD),
-					      0),
-		.no_reclaim_cmds = no_reclaim_cmds,
-		.n_no_reclaim_cmds = ARRAY_SIZE(no_reclaim_cmds),
-		.cb_data_offs = offsetof(struct ieee80211_tx_info,
-					 driver_data[2]),
-	};
 	struct iwl_trans *trans = mld->trans;
+	u32 eckv_value;
 
-	trans->rx_mpdu_cmd = REPLY_RX_MPDU_CMD;
-	trans->iml = mld->fw->iml;
-	trans->iml_len = mld->fw->iml_len;
-	trans->wide_cmd_header = true;
+	iwl_bios_setup_step(trans, &mld->fwrt);
+	iwl_uefi_get_step_table(trans);
 
-	iwl_trans_configure(trans, &trans_cfg);
+	if (iwl_bios_get_eckv(&mld->fwrt, &eckv_value))
+		IWL_DEBUG_RADIO(mld, "ECKV table doesn't exist in BIOS\n");
+	else
+		trans->conf.ext_32khz_clock_valid = !!eckv_value;
+
+	trans->conf.rx_buf_size = iwl_amsdu_size_to_rxb_size();
+	trans->conf.command_groups = iwl_mld_groups;
+	trans->conf.command_groups_size = ARRAY_SIZE(iwl_mld_groups);
+	trans->conf.fw_reset_handshake = true;
+	trans->conf.queue_alloc_cmd_ver =
+		iwl_fw_lookup_cmd_ver(mld->fw, WIDE_ID(DATA_PATH_GROUP,
+						       SCD_QUEUE_CONFIG_CMD),
+				      0);
+	trans->conf.cb_data_offs = offsetof(struct ieee80211_tx_info,
+					    driver_data[2]);
+	BUILD_BUG_ON(sizeof(no_reclaim_cmds) >
+		     sizeof(trans->conf.no_reclaim_cmds));
+	memcpy(trans->conf.no_reclaim_cmds, no_reclaim_cmds,
+	       sizeof(no_reclaim_cmds));
+	trans->conf.n_no_reclaim_cmds = ARRAY_SIZE(no_reclaim_cmds);
+
+	trans->conf.rx_mpdu_cmd = REPLY_RX_MPDU_CMD;
+	trans->conf.rx_mpdu_cmd_hdr_size = sizeof(struct iwl_rx_mpdu_res_start);
+	trans->conf.wide_cmd_header = true;
+
+	iwl_trans_op_mode_enter(trans, op_mode);
 }
 
 /*
@@ -358,13 +370,12 @@ iwl_mld_configure_trans(struct iwl_op_mode *op_mode)
 
 #define NUM_FW_LOAD_RETRIES	3
 static struct iwl_op_mode *
-iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg,
 		      const struct iwl_fw *fw, struct dentry *dbgfs_dir)
 {
 	struct ieee80211_hw *hw;
 	struct iwl_op_mode *op_mode;
 	struct iwl_mld *mld;
-	u32 eckv_value;
 	int ret;
 
 	/* Allocate and initialize a new hardware device */
@@ -382,16 +393,13 @@ iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 	iwl_construct_mld(mld, trans, cfg, fw, hw, dbgfs_dir);
 
+	/* we'll verify later it matches between commands */
+	mld->fw_rates_ver_3 = iwl_fw_lookup_cmd_ver(mld->fw, TX_CMD, 0) >= 11;
+
 	iwl_mld_construct_fw_runtime(mld, trans, fw, dbgfs_dir);
 
 	iwl_mld_get_bios_tables(mld);
 	iwl_uefi_get_sgom_table(trans, &mld->fwrt);
-	iwl_uefi_get_step_table(trans);
-	if (iwl_bios_get_eckv(&mld->fwrt, &eckv_value))
-		IWL_DEBUG_RADIO(mld, "ECKV table doesn't exist in BIOS\n");
-	else
-		trans->ext_32khz_clock_valid = !!eckv_value;
-	iwl_bios_setup_step(trans, &mld->fwrt);
 	mld->bios_enable_puncturing = iwl_uefi_get_puncturing(&mld->fwrt);
 
 	iwl_mld_hw_set_regulatory(mld);
@@ -410,13 +418,25 @@ iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 			break;
 	}
 
+	if (!ret) {
+		mld->nvm_data = iwl_get_nvm(mld->trans, mld->fw, 0, 0);
+		if (IS_ERR(mld->nvm_data)) {
+			IWL_ERR(mld, "Failed to read NVM: %d\n", ret);
+			ret = PTR_ERR(mld->nvm_data);
+		}
+	}
+
 	if (ret) {
 		wiphy_unlock(mld->wiphy);
 		rtnl_unlock();
-		iwl_fw_flush_dumps(&mld->fwrt);
-		goto free_hw;
+		goto err;
 	}
 
+	/* We are about to stop the FW. Notifications may require an
+	 * operational FW, so handle them all here before we stop.
+	 */
+	wiphy_work_flush(mld->wiphy, &mld->async_handlers_wk);
+
 	iwl_mld_stop_fw(mld);
 
 	wiphy_unlock(mld->wiphy);
@@ -455,7 +475,8 @@ leds_exit:
 	iwl_mld_leds_exit(mld);
 free_nvm:
 	kfree(mld->nvm_data);
-free_hw:
+err:
+	iwl_trans_op_mode_leave(mld->trans);
 	ieee80211_free_hw(mld->hw);
 	return ERR_PTR(ret);
 }
@@ -468,8 +489,9 @@ iwl_op_mode_mld_stop(struct iwl_op_mode *op_mode)
 	iwl_mld_ptp_remove(mld);
 	iwl_mld_leds_exit(mld);
 
-	wiphy_lock(mld->wiphy);
 	iwl_mld_thermal_exit(mld);
+
+	wiphy_lock(mld->wiphy);
 	iwl_mld_low_latency_stop(mld);
 	iwl_mld_deinit_time_sync(mld);
 	wiphy_unlock(mld->wiphy);
@@ -657,6 +679,13 @@ static bool iwl_mld_sw_reset(struct iwl_op_mode *op_mode,
 {
 	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
 
+	/* SW reset can happen for TOP error w/o NIC error, so
+	 * also abort scan here and set in_hw_restart, when we
+	 * had a NIC error both were already done.
+	 */
+	iwl_mld_report_scan_aborted(mld);
+	mld->fw_status.in_hw_restart = true;
+
 	/* Do restart only in the following conditions are met:
 	 * - we consider the FW as running
 	 * - The trigger that brought us here is defined as one that requires
@@ -685,7 +714,6 @@ static void iwl_mld_device_powered_off(struct iwl_op_mode *op_mode)
 	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
 
 	wiphy_lock(mld->wiphy);
-	mld->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
 	iwl_mld_stop_fw(mld);
 	mld->fw_status.in_d3 = false;
 	wiphy_unlock(mld->wiphy);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.h b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
index 5eceaaf7696d..1a2c44f44eff 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
@@ -116,6 +116,7 @@
  * @monitor.ampdu_toggle: the state of the previous packet to track A-MPDU
  * @monitor.cur_aid: current association id tracked by the sniffer
  * @monitor.cur_bssid: current bssid tracked by the sniffer
+ * @monitor.ptp_time: set the Rx mactime using the device's PTP clock time
  * @monitor.p80: primary channel position relative to he whole bandwidth, in
  * steps of 80 MHz
  * @fw_id_to_link_sta: maps a fw id of a sta to the corresponding
@@ -126,7 +127,6 @@
  *	cleanup using iwl_mld_free_internal_sta
  * @netdetect: indicates the FW is in suspend mode with netdetect configured
  * @p2p_device_vif: points to the p2p device vif if exists
- * @bt_is_active: indicates that BT is active
  * @dev: pointer to device struct. For printing purposes
  * @trans: pointer to the transport layer
  * @cfg: pointer to the device configuration
@@ -154,6 +154,8 @@
  * @radio_kill: bitmap of radio kill status
  * @radio_kill.hw: radio is killed by hw switch
  * @radio_kill.ct: radio is killed because the device it too hot
+ * @power_budget_mw: maximum cTDP power budget as defined for this system and
+ *	device
  * @addresses: device MAC addresses.
  * @scan: instance of the scan object
  * @wowlan: WoWLAN support data.
@@ -174,6 +176,7 @@
  * @mcast_filter_cmd: pointer to the multicast filter command.
  * @mgmt_tx_ant: stores the last TX antenna index; used for setting
  *	TX rate_n_flags for non-STA mgmt frames (toggles on every TX failure).
+ * @fw_rates_ver_3: FW rates are in version 3
  * @low_latency: low-latency manager.
  * @tzone: thermal zone device's data
  * @cooling_dev: cooling device's related data
@@ -184,6 +187,7 @@
  * @ptp_data: data of the PTP clock
  * @time_sync: time sync data.
  * @ftm_initiator: FTM initiator data
+ * @last_bt_notif: last received BT Coex notif
  */
 struct iwl_mld {
 	/* Add here fields that need clean up on restart */
@@ -201,19 +205,20 @@ struct iwl_mld {
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 			__le16 cur_aid;
 			u8 cur_bssid[ETH_ALEN];
+			bool ptp_time;
 #endif
 		} monitor;
 #ifdef CONFIG_PM_SLEEP
 		bool netdetect;
 #endif /* CONFIG_PM_SLEEP */
 		struct ieee80211_vif *p2p_device_vif;
-		bool bt_is_active;
+		struct iwl_bt_coex_profile_notif last_bt_notif;
 	);
 	struct ieee80211_link_sta __rcu *fw_id_to_link_sta[IWL_STATION_COUNT_MAX];
 	/* And here fields that survive a fw restart */
 	struct device *dev;
 	struct iwl_trans *trans;
-	const struct iwl_cfg *cfg;
+	const struct iwl_rf_cfg *cfg;
 	const struct iwl_fw *fw;
 	struct ieee80211_hw *hw;
 	struct wiphy *wiphy;
@@ -241,6 +246,8 @@ struct iwl_mld {
 		    ct:1;
 	} radio_kill;
 
+	u32 power_budget_mw;
+
 	struct mac_address addresses[IWL_MLD_MAX_ADDRESSES];
 	struct iwl_mld_scan scan;
 #ifdef CONFIG_PM_SLEEP
@@ -266,6 +273,8 @@ struct iwl_mld {
 
 	u8 mgmt_tx_ant;
 
+	bool fw_rates_ver_3;
+
 	struct iwl_mld_low_latency low_latency;
 
 	bool ibss_manager;
@@ -286,7 +295,7 @@ struct iwl_mld {
 	memset((void *)&(_ptr)->zeroed_on_hw_restart, 0, \
 	       sizeof((_ptr)->zeroed_on_hw_restart))
 
-/* Cleanup function for struct iwl_mld_vif, will be called in restart */
+/* Cleanup function for struct iwl_mld, will be called in restart */
 static inline void
 iwl_cleanup_mld(struct iwl_mld *mld)
 {
@@ -298,11 +307,6 @@ iwl_cleanup_mld(struct iwl_mld *mld)
 #endif
 
 	iwl_mld_low_latency_restart_cleanup(mld);
-
-	/* Empty the list of async notification handlers so we won't process
-	 * notifications from the dead fw after the reconfig flow.
-	 */
-	iwl_mld_purge_async_handlers_list(mld);
 }
 
 enum iwl_power_scheme {
@@ -415,7 +419,7 @@ iwl_mld_legacy_hw_idx_to_mac80211_idx(u32 rate_n_flags,
 	int rate = rate_n_flags & RATE_LEGACY_RATE_MSK;
 	bool is_lb = band == NL80211_BAND_2GHZ;
 
-	if (format == RATE_MCS_LEGACY_OFDM_MSK)
+	if (format == RATE_MCS_MOD_TYPE_LEGACY_OFDM)
 		return is_lb ? rate + IWL_FIRST_OFDM_RATE : rate;
 
 	/* CCK is not allowed in 5 GHz */
@@ -487,7 +491,7 @@ iwl_mld_is_dup(struct iwl_mld *mld, struct ieee80211_sta *sta,
 	       struct ieee80211_rx_status *rx_status, int queue);
 
 void iwl_construct_mld(struct iwl_mld *mld, struct iwl_trans *trans,
-		       const struct iwl_cfg *cfg, const struct iwl_fw *fw,
+		       const struct iwl_rf_cfg *cfg, const struct iwl_fw *fw,
 		       struct ieee80211_hw *hw, struct dentry *dbgfs_dir);
 #endif
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
index a870e169e265..dba5379ed009 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -52,7 +52,8 @@ static void iwl_mld_print_emlsr_blocked(struct iwl_mld *mld, u32 mask)
 	HOW(BT_COEX)			\
 	HOW(CHAN_LOAD)			\
 	HOW(RFI)			\
-	HOW(FW_REQUEST)
+	HOW(FW_REQUEST)			\
+	HOW(INVALID)
 
 static const char *
 iwl_mld_get_emlsr_exit_string(enum iwl_mld_emlsr_exit exit)
@@ -325,23 +326,44 @@ static void
 iwl_mld_vif_iter_emlsr_mode_notif(void *data, u8 *mac,
 				  struct ieee80211_vif *vif)
 {
-	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
-	struct iwl_esr_mode_notif *notif = (void *)data;
+	const struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	enum iwl_mvm_fw_esr_recommendation action;
+	const struct iwl_esr_mode_notif *notif = NULL;
+
+	if (iwl_fw_lookup_notif_ver(mld_vif->mld->fw, DATA_PATH_GROUP,
+				    ESR_MODE_NOTIF, 0) > 1) {
+		notif = (void *)data;
+		action = le32_to_cpu(notif->action);
+	} else {
+		const struct iwl_esr_mode_notif_v1 *notif_v1 = (void *)data;
+
+		action = le32_to_cpu(notif_v1->action);
+	}
 
 	if (!iwl_mld_vif_has_emlsr_cap(vif))
 		return;
 
-	switch (le32_to_cpu(notif->action)) {
+	switch (action) {
 	case ESR_RECOMMEND_LEAVE:
+		if (notif)
+			IWL_DEBUG_INFO(mld_vif->mld,
+				       "FW recommend leave reason = 0x%x\n",
+				       le32_to_cpu(notif->leave_reason_mask));
+
 		iwl_mld_exit_emlsr(mld_vif->mld, vif,
 				   IWL_MLD_EMLSR_EXIT_FW_REQUEST,
 				   iwl_mld_get_primary_link(vif));
 		break;
-	case ESR_RECOMMEND_ENTER:
 	case ESR_FORCE_LEAVE:
+		if (notif)
+			IWL_DEBUG_INFO(mld_vif->mld,
+				       "FW force leave reason = 0x%x\n",
+				       le32_to_cpu(notif->leave_reason_mask));
+		fallthrough;
+	case ESR_RECOMMEND_ENTER:
 	default:
 		IWL_WARN(mld_vif->mld, "Unexpected EMLSR notification: %d\n",
-			 le32_to_cpu(notif->action));
+			 action);
 	}
 }
 
@@ -523,7 +545,7 @@ void iwl_mld_emlsr_check_tpt(struct wiphy *wiphy, struct wiphy_work *wk)
 	}
 
 	/* Sum up RX and TX MPDUs from the different queues/links */
-	for (int q = 0; q < mld->trans->num_rx_queues; q++) {
+	for (int q = 0; q < mld->trans->info.num_rxqs; q++) {
 		struct iwl_mld_per_q_mpdu_counter *queue_counter =
 			&mld_sta->mpdu_counters[q];
 
@@ -635,6 +657,42 @@ s8 iwl_mld_get_emlsr_rssi_thresh(struct iwl_mld *mld,
 #undef RSSI_THRESHOLD
 }
 
+#define IWL_MLD_BT_COEX_DISABLE_EMLSR_RSSI_THRESH	-69
+#define IWL_MLD_BT_COEX_ENABLE_EMLSR_RSSI_THRESH	-63
+#define IWL_MLD_BT_COEX_WIFI_LOSS_THRESH		7
+
+VISIBLE_IF_IWLWIFI_KUNIT
+bool
+iwl_mld_bt_allows_emlsr(struct iwl_mld *mld, struct ieee80211_bss_conf *link,
+			bool check_entry)
+{
+	int bt_penalty, rssi_thresh;
+	s32 link_rssi;
+
+	if (WARN_ON_ONCE(!link->bss))
+		return false;
+
+	link_rssi = MBM_TO_DBM(link->bss->signal);
+	rssi_thresh = check_entry ?
+		      IWL_MLD_BT_COEX_ENABLE_EMLSR_RSSI_THRESH :
+		      IWL_MLD_BT_COEX_DISABLE_EMLSR_RSSI_THRESH;
+	/* No valid RSSI - force to take low rssi */
+	if (!link_rssi)
+		link_rssi = rssi_thresh - 1;
+
+	if (link_rssi > rssi_thresh)
+		bt_penalty = max(mld->last_bt_notif.wifi_loss_mid_high_rssi[PHY_BAND_24][0],
+				 mld->last_bt_notif.wifi_loss_mid_high_rssi[PHY_BAND_24][1]);
+	else
+		bt_penalty = max(mld->last_bt_notif.wifi_loss_low_rssi[PHY_BAND_24][0],
+				 mld->last_bt_notif.wifi_loss_low_rssi[PHY_BAND_24][1]);
+
+	IWL_DEBUG_EHT(mld, "BT penalty for link-id %0X is %d\n",
+		      link->link_id, bt_penalty);
+	return bt_penalty < IWL_MLD_BT_COEX_WIFI_LOSS_THRESH;
+}
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_bt_allows_emlsr);
+
 static u32
 iwl_mld_emlsr_disallowed_with_link(struct iwl_mld *mld,
 				   struct ieee80211_vif *vif,
@@ -643,13 +701,14 @@ iwl_mld_emlsr_disallowed_with_link(struct iwl_mld *mld,
 {
 	struct wiphy *wiphy = mld->wiphy;
 	struct ieee80211_bss_conf *conf;
-	enum iwl_mld_emlsr_exit ret = 0;
+	u32 ret = 0;
 
 	conf = wiphy_dereference(wiphy, vif->link_conf[link->link_id]);
 	if (WARN_ON_ONCE(!conf))
-		return false;
+		return IWL_MLD_EMLSR_EXIT_INVALID;
 
-	if (link->chandef->chan->band == NL80211_BAND_2GHZ && mld->bt_is_active)
+	if (link->chandef->chan->band == NL80211_BAND_2GHZ &&
+	    !iwl_mld_bt_allows_emlsr(mld, conf, true))
 		ret |= IWL_MLD_EMLSR_EXIT_BT_COEX;
 
 	if (link->signal <
@@ -731,7 +790,7 @@ iwl_mld_get_min_chan_load_thresh(struct ieee80211_chanctx_conf *chanctx)
 	return 10;
 }
 
-VISIBLE_IF_IWLWIFI_KUNIT bool
+static bool
 iwl_mld_channel_load_allows_emlsr(struct iwl_mld *mld,
 				  struct ieee80211_vif *vif,
 				  const struct iwl_mld_link_sel_data *a,
@@ -772,8 +831,8 @@ iwl_mld_channel_load_allows_emlsr(struct iwl_mld *mld,
 	if (a->chandef->width <= b->chandef->width)
 		return true;
 
-	bw_a = nl80211_chan_width_to_mhz(a->chandef->width);
-	bw_b = nl80211_chan_width_to_mhz(b->chandef->width);
+	bw_a = cfg80211_chandef_get_width(a->chandef);
+	bw_b = cfg80211_chandef_get_width(b->chandef);
 	ratio = bw_a / bw_b;
 
 	switch (ratio) {
@@ -788,10 +847,9 @@ iwl_mld_channel_load_allows_emlsr(struct iwl_mld *mld,
 
 	return false;
 }
-EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_channel_load_allows_emlsr);
 
-static bool
-iwl_mld_valid_emlsr_pair(struct ieee80211_vif *vif,
+VISIBLE_IF_IWLWIFI_KUNIT u32
+iwl_mld_emlsr_pair_state(struct ieee80211_vif *vif,
 			 struct iwl_mld_link_sel_data *a,
 			 struct iwl_mld_link_sel_data *b)
 {
@@ -800,12 +858,36 @@ iwl_mld_valid_emlsr_pair(struct ieee80211_vif *vif,
 	u32 reason_mask = 0;
 
 	/* Per-link considerations */
-	if (iwl_mld_emlsr_disallowed_with_link(mld, vif, a, true) ||
-	    iwl_mld_emlsr_disallowed_with_link(mld, vif, b, false))
-		return false;
-
-	if (a->chandef->chan->band == b->chandef->chan->band)
-		reason_mask |= IWL_MLD_EMLSR_EXIT_EQUAL_BAND;
+	reason_mask = iwl_mld_emlsr_disallowed_with_link(mld, vif, a, true);
+	if (reason_mask)
+		return reason_mask;
+
+	reason_mask = iwl_mld_emlsr_disallowed_with_link(mld, vif, b, false);
+	if (reason_mask)
+		return reason_mask;
+
+	if (a->chandef->chan->band == b->chandef->chan->band) {
+		const struct cfg80211_chan_def *c_low = a->chandef;
+		const struct cfg80211_chan_def *c_high = b->chandef;
+		u32 c_low_upper_edge, c_high_lower_edge;
+
+		if (c_low->chan->center_freq > c_high->chan->center_freq)
+			swap(c_low, c_high);
+
+		c_low_upper_edge = c_low->chan->center_freq +
+				   cfg80211_chandef_get_width(c_low) / 2;
+		c_high_lower_edge = c_high->chan->center_freq -
+				    cfg80211_chandef_get_width(c_high) / 2;
+
+		if (a->chandef->chan->band == NL80211_BAND_5GHZ &&
+		    c_low_upper_edge <= 5330 && c_high_lower_edge >= 5490) {
+			/* This case is fine - HW/FW can deal with it, there's
+			 * enough separation between the two channels.
+			 */
+		} else {
+			reason_mask |= IWL_MLD_EMLSR_EXIT_EQUAL_BAND;
+		}
+	}
 	if (!iwl_mld_channel_load_allows_emlsr(mld, vif, a, b))
 		reason_mask |= IWL_MLD_EMLSR_EXIT_CHAN_LOAD;
 
@@ -818,11 +900,11 @@ iwl_mld_valid_emlsr_pair(struct ieee80211_vif *vif,
 			       nl80211_chan_width_to_mhz(a->chandef->width),
 			       nl80211_chan_width_to_mhz(b->chandef->width));
 		iwl_mld_print_emlsr_exit(mld, reason_mask);
-		return false;
 	}
 
-	return true;
+	return reason_mask;
 }
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_emlsr_pair_state);
 
 /* Calculation is done with fixed-point with a scaling factor of 1/256 */
 #define SCALE_FACTOR 256
@@ -850,7 +932,7 @@ unsigned int iwl_mld_get_emlsr_grade(struct iwl_mld *mld,
 
 	*primary_id = a->link_id;
 
-	if (!iwl_mld_valid_emlsr_pair(vif, a, b))
+	if (iwl_mld_emlsr_pair_state(vif, a, b))
 		return 0;
 
 	primary_conf = wiphy_dereference(wiphy, vif->link_conf[*primary_id]);
@@ -892,8 +974,11 @@ static void _iwl_mld_select_links(struct iwl_mld *mld,
 	n_data = iwl_mld_set_link_sel_data(mld, vif, data, usable_links,
 					   &best_idx);
 
-	if (WARN(!n_data, "Couldn't find a valid grade for any link!\n"))
+	if (!n_data) {
+		IWL_DEBUG_EHT(mld,
+			      "Couldn't find a valid grade for any link!\n");
 		return;
+	}
 
 	/* Default to selecting the single best link */
 	best_link = &data[best_idx];
@@ -961,27 +1046,41 @@ static void iwl_mld_emlsr_check_bt_iter(void *_data, u8 *mac,
 					struct ieee80211_vif *vif)
 {
 	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	const struct iwl_bt_coex_profile_notif zero_notif = {};
 	struct iwl_mld *mld = mld_vif->mld;
 	struct ieee80211_bss_conf *link;
 	unsigned int link_id;
+	const struct iwl_bt_coex_profile_notif *notif = &mld->last_bt_notif;
 
-	if (!mld->bt_is_active) {
-		iwl_mld_retry_emlsr(mld, vif);
+	if (!iwl_mld_vif_has_emlsr_cap(vif))
 		return;
-	}
 
-	/* BT is turned ON but we are not in EMLSR, nothing to do */
-	if (!iwl_mld_emlsr_active(vif))
+	/* zeroed structure means that BT is OFF */
+	if (!memcmp(notif, &zero_notif, sizeof(*notif))) {
+		iwl_mld_retry_emlsr(mld, vif);
 		return;
-
-	/* In EMLSR and BT is turned ON */
+	}
 
 	for_each_vif_active_link(vif, link, link_id) {
+		bool emlsr_active, emlsr_allowed;
+
 		if (WARN_ON(!link->chanreq.oper.chan))
 			continue;
 
-		if (link->chanreq.oper.chan->band == NL80211_BAND_2GHZ) {
-			iwl_mld_exit_emlsr(mld, vif, IWL_MLD_EMLSR_EXIT_BT_COEX,
+		if (link->chanreq.oper.chan->band != NL80211_BAND_2GHZ)
+			continue;
+
+		emlsr_active = iwl_mld_emlsr_active(vif);
+		emlsr_allowed = iwl_mld_bt_allows_emlsr(mld, link,
+							!emlsr_active);
+		if (emlsr_allowed && !emlsr_active) {
+			iwl_mld_retry_emlsr(mld, vif);
+			return;
+		}
+
+		if (!emlsr_allowed && emlsr_active) {
+			iwl_mld_exit_emlsr(mld, vif,
+					   IWL_MLD_EMLSR_EXIT_BT_COEX,
 					   iwl_mld_get_primary_link(vif));
 			return;
 		}
@@ -1074,3 +1173,69 @@ void iwl_mld_retry_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif)
 
 	iwl_mld_int_mlo_scan(mld, vif);
 }
+
+static void iwl_mld_ignore_tpt_iter(void *data, u8 *mac,
+				    struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld *mld = mld_vif->mld;
+	struct iwl_mld_sta *mld_sta;
+	bool *start = (void *)data;
+
+	/* check_tpt_wk is only used when TPT block isn't set */
+	if (mld_vif->emlsr.blocked_reasons & IWL_MLD_EMLSR_BLOCKED_TPT ||
+	    !IWL_MLD_AUTO_EML_ENABLE || !mld_vif->ap_sta)
+		return;
+
+	mld_sta = iwl_mld_sta_from_mac80211(mld_vif->ap_sta);
+
+	/* We only count for the AP sta in a MLO connection */
+	if (!mld_sta->mpdu_counters)
+		return;
+
+	if (*start) {
+		wiphy_delayed_work_cancel(mld_vif->mld->wiphy,
+					  &mld_vif->emlsr.check_tpt_wk);
+		IWL_DEBUG_EHT(mld, "TPT check disabled\n");
+		return;
+	}
+
+	/* Clear the counters so we start from the beginning */
+	for (int q = 0; q < mld->trans->info.num_rxqs; q++) {
+		struct iwl_mld_per_q_mpdu_counter *queue_counter =
+			&mld_sta->mpdu_counters[q];
+
+		spin_lock_bh(&queue_counter->lock);
+
+		memset(queue_counter->per_link, 0,
+		       sizeof(queue_counter->per_link));
+
+		spin_unlock_bh(&queue_counter->lock);
+	}
+
+	/* Schedule the check in 5 seconds */
+	wiphy_delayed_work_queue(mld_vif->mld->wiphy,
+				 &mld_vif->emlsr.check_tpt_wk,
+				 round_jiffies_relative(IWL_MLD_TPT_COUNT_WINDOW));
+	IWL_DEBUG_EHT(mld, "TPT check enabled\n");
+}
+
+void iwl_mld_start_ignoring_tpt_updates(struct iwl_mld *mld)
+{
+	bool start = true;
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_ignore_tpt_iter,
+						&start);
+}
+
+void iwl_mld_stop_ignoring_tpt_updates(struct iwl_mld *mld)
+{
+	bool start = false;
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_ignore_tpt_iter,
+						&start);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.h b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
index 4fb1fdbe3df9..9afa3d6ea649 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
@@ -37,7 +37,7 @@ static inline bool iwl_mld_vif_has_emlsr_cap(struct ieee80211_vif *vif)
 	return ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_STATION &&
 	       ieee80211_vif_is_mld(vif) &&
 	       vif->cfg.eml_cap & IEEE80211_EML_CAP_EMLSR_SUPP &&
-	       !CSR_HW_RFID_IS_CDB(mld_vif->mld->trans->hw_rf_id);
+	       !CSR_HW_RFID_IS_CDB(mld_vif->mld->trans->info.hw_rf_id);
 }
 
 static inline int
@@ -158,10 +158,16 @@ struct iwl_mld_link_sel_data {
 };
 
 #if IS_ENABLED(CONFIG_IWLWIFI_KUNIT_TESTS)
-bool iwl_mld_channel_load_allows_emlsr(struct iwl_mld *mld,
-				       struct ieee80211_vif *vif,
-				       const struct iwl_mld_link_sel_data *a,
-				       const struct iwl_mld_link_sel_data *b);
+u32 iwl_mld_emlsr_pair_state(struct ieee80211_vif *vif,
+			     struct iwl_mld_link_sel_data *a,
+			     struct iwl_mld_link_sel_data *b);
+
+bool iwl_mld_bt_allows_emlsr(struct iwl_mld *mld,
+			     struct ieee80211_bss_conf *link,
+			     bool entry_criteria);
 #endif
 
+void iwl_mld_start_ignoring_tpt_updates(struct iwl_mld *mld);
+void iwl_mld_stop_ignoring_tpt_updates(struct iwl_mld *mld);
+
 #endif /* __iwl_mld_mlo_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/notif.c b/drivers/net/wireless/intel/iwlwifi/mld/notif.c
index fc18cba8aaa8..c0e62d46aba6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/notif.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/notif.c
@@ -183,47 +183,6 @@ static void iwl_mld_handle_mu_mimo_grp_notif(struct iwl_mld *mld,
 }
 
 static void
-iwl_mld_handle_stored_beacon_notif(struct iwl_mld *mld,
-				   struct iwl_rx_packet *pkt)
-{
-	unsigned int pkt_len = iwl_rx_packet_payload_len(pkt);
-	struct iwl_stored_beacon_notif *sb = (void *)pkt->data;
-	struct ieee80211_rx_status rx_status = {};
-	struct sk_buff *skb;
-	u32 size = le32_to_cpu(sb->common.byte_count);
-
-	if (size == 0)
-		return;
-
-	if (pkt_len < struct_size(sb, data, size))
-		return;
-
-	skb = alloc_skb(size, GFP_ATOMIC);
-	if (!skb) {
-		IWL_ERR(mld, "alloc_skb failed\n");
-		return;
-	}
-
-	/* update rx_status according to the notification's metadata */
-	rx_status.mactime = le64_to_cpu(sb->common.tsf);
-	/* TSF as indicated by the firmware  is at INA time */
-	rx_status.flag |= RX_FLAG_MACTIME_PLCP_START;
-	rx_status.device_timestamp = le32_to_cpu(sb->common.system_time);
-	rx_status.band =
-		iwl_mld_phy_band_to_nl80211(le16_to_cpu(sb->common.band));
-	rx_status.freq =
-		ieee80211_channel_to_frequency(le16_to_cpu(sb->common.channel),
-					       rx_status.band);
-
-	/* copy the data */
-	skb_put_data(skb, sb->data, size);
-	memcpy(IEEE80211_SKB_RXCB(skb), &rx_status, sizeof(rx_status));
-
-	/* pass it as regular rx to mac80211 */
-	ieee80211_rx_napi(mld->hw, NULL, skb, NULL);
-}
-
-static void
 iwl_mld_handle_channel_switch_start_notif(struct iwl_mld *mld,
 					  struct iwl_rx_packet *pkt)
 {
@@ -345,12 +304,15 @@ CMD_VERSIONS(session_prot_notif,
 CMD_VERSIONS(missed_beacon_notif,
 	     CMD_VER_ENTRY(5, iwl_missed_beacons_notif))
 CMD_VERSIONS(tx_resp_notif,
-	     CMD_VER_ENTRY(8, iwl_tx_resp))
+	     CMD_VER_ENTRY(8, iwl_tx_resp)
+	     CMD_VER_ENTRY(9, iwl_tx_resp))
 CMD_VERSIONS(compressed_ba_notif,
 	     CMD_VER_ENTRY(5, iwl_compressed_ba_notif)
-	     CMD_VER_ENTRY(6, iwl_compressed_ba_notif))
+	     CMD_VER_ENTRY(6, iwl_compressed_ba_notif)
+	     CMD_VER_ENTRY(7, iwl_compressed_ba_notif))
 CMD_VERSIONS(tlc_notif,
-	     CMD_VER_ENTRY(3, iwl_tlc_update_notif))
+	     CMD_VER_ENTRY(3, iwl_tlc_update_notif)
+	     CMD_VER_ENTRY(4, iwl_tlc_update_notif))
 CMD_VERSIONS(mu_mimo_grp_notif,
 	     CMD_VER_ENTRY(1, iwl_mu_group_mgmt_notif))
 CMD_VERSIONS(channel_switch_start_notif,
@@ -361,8 +323,6 @@ CMD_VERSIONS(ct_kill_notif,
 	     CMD_VER_ENTRY(2, ct_kill_notif))
 CMD_VERSIONS(temp_notif,
 	     CMD_VER_ENTRY(2, iwl_dts_measurement_notif))
-CMD_VERSIONS(stored_beacon_notif,
-	     CMD_VER_ENTRY(4, iwl_stored_beacon_notif))
 CMD_VERSIONS(roc_notif,
 	     CMD_VER_ENTRY(1, iwl_roc_notif))
 CMD_VERSIONS(probe_resp_data_notif,
@@ -378,7 +338,8 @@ CMD_VERSIONS(bt_coex_notif,
 CMD_VERSIONS(beacon_notification,
 	     CMD_VER_ENTRY(6, iwl_extended_beacon_notif))
 CMD_VERSIONS(emlsr_mode_notif,
-	     CMD_VER_ENTRY(1, iwl_esr_mode_notif))
+	     CMD_VER_ENTRY(1, iwl_esr_mode_notif_v1)
+	     CMD_VER_ENTRY(2, iwl_esr_mode_notif))
 CMD_VERSIONS(emlsr_trans_fail_notif,
 	     CMD_VER_ENTRY(1, iwl_esr_trans_fail_notif))
 CMD_VERSIONS(uapsd_misbehaving_ap_notif,
@@ -473,8 +434,6 @@ const struct iwl_rx_handler iwl_mld_rx_handlers[] = {
 	RX_HANDLER_OF_ROC(MAC_CONF_GROUP, ROC_NOTIF, roc_notif)
 	RX_HANDLER_NO_OBJECT(DATA_PATH_GROUP, MU_GROUP_MGMT_NOTIF,
 			     mu_mimo_grp_notif, RX_HANDLER_SYNC)
-	RX_HANDLER_NO_OBJECT(PROT_OFFLOAD_GROUP, STORED_BEACON_NTF,
-			     stored_beacon_notif, RX_HANDLER_SYNC)
 	RX_HANDLER_OF_VIF(MAC_CONF_GROUP, PROBE_RESPONSE_DATA_NOTIF,
 			  probe_resp_data_notif)
 	RX_HANDLER_NO_OBJECT(PHY_OPS_GROUP, CT_KILL_NOTIFICATION,
@@ -646,7 +605,7 @@ void iwl_mld_rx_rss(struct iwl_op_mode *op_mode, struct napi_struct *napi,
 	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
 	u16 cmd_id = WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd);
 
-	if (unlikely(queue >= mld->trans->num_rx_queues))
+	if (unlikely(queue >= mld->trans->info.num_rxqs))
 		return;
 
 	if (likely(cmd_id == WIDE_ID(LEGACY_GROUP, REPLY_RX_MPDU_CMD)))
@@ -707,10 +666,14 @@ void iwl_mld_async_handlers_wk(struct wiphy *wiphy, struct wiphy_work *wk)
 	}
 }
 
-void iwl_mld_purge_async_handlers_list(struct iwl_mld *mld)
+void iwl_mld_cancel_async_notifications(struct iwl_mld *mld)
 {
 	struct iwl_async_handler_entry *entry, *tmp;
 
+	lockdep_assert_wiphy(mld->wiphy);
+
+	wiphy_work_cancel(mld->wiphy, &mld->async_handlers_wk);
+
 	spin_lock_bh(&mld->async_handlers_lock);
 	list_for_each_entry_safe(entry, tmp, &mld->async_handlers_list, list) {
 		iwl_mld_log_async_handler_op(mld, "Purged", &entry->rxb);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/notif.h b/drivers/net/wireless/intel/iwlwifi/mld/notif.h
index 2eaa1d4e138e..adcdd9dec192 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/notif.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/notif.h
@@ -15,7 +15,7 @@ void iwl_mld_rx_rss(struct iwl_op_mode *op_mode, struct napi_struct *napi,
 
 void iwl_mld_async_handlers_wk(struct wiphy *wiphy, struct wiphy_work *wk);
 
-void iwl_mld_purge_async_handlers_list(struct iwl_mld *mld);
+void iwl_mld_cancel_async_notifications(struct iwl_mld *mld);
 
 enum iwl_mld_object_type {
 	IWL_MLD_OBJECT_TYPE_NONE,
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/phy.c b/drivers/net/wireless/intel/iwlwifi/mld/phy.c
index 2fbc8090088b..d5a32ee56b92 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/phy.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/phy.c
@@ -50,6 +50,9 @@ static void iwl_mld_chanctx_usage_iter(void *_data, u8 *mac,
 		if (rcu_access_pointer(link_conf->chanctx_conf) != data->ctx)
 			continue;
 
+		if (vif->type == NL80211_IFTYPE_AP && link_conf->ftm_responder)
+			data->use_def = true;
+
 		if (iwl_mld_chanctx_fils_enabled(vif, data->ctx))
 			data->use_def = true;
 	}
@@ -153,3 +156,43 @@ int iwl_mld_phy_fw_action(struct iwl_mld *mld,
 
 	return ret;
 }
+
+static u32 iwl_mld_get_phy_config(struct iwl_mld *mld)
+{
+	u32 phy_config = ~(FW_PHY_CFG_TX_CHAIN |
+			   FW_PHY_CFG_RX_CHAIN);
+	u32 valid_rx_ant = iwl_mld_get_valid_rx_ant(mld);
+	u32 valid_tx_ant = iwl_mld_get_valid_tx_ant(mld);
+
+	phy_config |= valid_tx_ant << FW_PHY_CFG_TX_CHAIN_POS |
+		      valid_rx_ant << FW_PHY_CFG_RX_CHAIN_POS;
+
+	return mld->fw->phy_config & phy_config;
+}
+
+int iwl_mld_send_phy_cfg_cmd(struct iwl_mld *mld)
+{
+	const struct iwl_tlv_calib_ctrl *default_calib =
+		&mld->fw->default_calib[IWL_UCODE_REGULAR];
+	struct iwl_phy_cfg_cmd_v3 cmd = {
+		.phy_cfg = cpu_to_le32(iwl_mld_get_phy_config(mld)),
+		.calib_control.event_trigger = default_calib->event_trigger,
+		.calib_control.flow_trigger = default_calib->flow_trigger,
+		.phy_specific_cfg = mld->fwrt.phy_filters,
+	};
+
+	IWL_INFO(mld, "Sending Phy CFG command: 0x%x\n", cmd.phy_cfg);
+
+	return iwl_mld_send_cmd_pdu(mld, PHY_CONFIGURATION_CMD, &cmd);
+}
+
+void iwl_mld_update_phy_chandef(struct iwl_mld *mld,
+				struct ieee80211_chanctx_conf *ctx)
+{
+	struct iwl_mld_phy *phy = iwl_mld_phy_from_mac80211(ctx);
+	struct cfg80211_chan_def *chandef =
+		iwl_mld_get_chandef_from_chanctx(mld, ctx);
+
+	phy->chandef = *chandef;
+	iwl_mld_phy_fw_action(mld, ctx, FW_CTXT_ACTION_MODIFY);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/phy.h b/drivers/net/wireless/intel/iwlwifi/mld/phy.h
index 2212a89321b7..0deaf179f07c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/phy.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/phy.h
@@ -52,4 +52,9 @@ iwl_mld_get_chandef_from_chanctx(struct iwl_mld *mld,
 				 struct ieee80211_chanctx_conf *ctx);
 u8 iwl_mld_get_fw_ctrl_pos(const struct cfg80211_chan_def *chandef);
 
+int iwl_mld_send_phy_cfg_cmd(struct iwl_mld *mld);
+
+void iwl_mld_update_phy_chandef(struct iwl_mld *mld,
+				struct ieee80211_chanctx_conf *ctx);
+
 #endif /* __iwl_mld_phy_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/power.c b/drivers/net/wireless/intel/iwlwifi/mld/power.c
index 2f16c174b57e..8cc276041360 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/power.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/power.c
@@ -253,6 +253,9 @@ static void iwl_mld_power_build_cmd(struct iwl_mld *mld,
 
 	cmd->flags |= cpu_to_le16(POWER_FLAGS_POWER_MANAGEMENT_ENA_MSK);
 
+	if (iwl_fw_lookup_cmd_ver(mld->fw, MAC_PM_POWER_TABLE, 0) >= 2)
+		cmd->flags |= cpu_to_le16(POWER_FLAGS_ENABLE_SMPS_MSK);
+
 	/* firmware supports LPRX for beacons at rate 1 Mbps or 6 Mbps only */
 	if (link_conf->beacon_rate &&
 	    (link_conf->beacon_rate->bitrate == 10 ||
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ptp.c b/drivers/net/wireless/intel/iwlwifi/mld/ptp.c
index d5c3f853d96c..5ee38fc168c1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/ptp.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/ptp.c
@@ -21,7 +21,7 @@
 
 static int iwl_mld_get_systime(struct iwl_mld *mld, u32 *gp2)
 {
-	*gp2 = iwl_read_prph(mld->trans, mld->trans->cfg->gp2_reg_addr);
+	*gp2 = iwl_read_prph(mld->trans, mld->trans->mac_cfg->base->gp2_reg_addr);
 
 	if (*gp2 == 0x5a5a5a5a)
 		return -EINVAL;
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c b/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c
index a75af8c1e8ab..326c300470ea 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c
@@ -63,9 +63,9 @@ void iwl_mld_get_bios_tables(struct iwl_mld *mld)
 		/* we don't fail if the table is not available */
 	}
 
-	ret = iwl_uefi_get_uats_table(mld->trans, &mld->fwrt);
-	if (ret)
-		IWL_DEBUG_RADIO(mld, "failed to read UATS table (%d)\n", ret);
+	iwl_uefi_get_uats_table(mld->trans, &mld->fwrt);
+
+	iwl_bios_get_phy_filters(&mld->fwrt);
 }
 
 static int iwl_mld_geo_sar_init(struct iwl_mld *mld)
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/roc.c b/drivers/net/wireless/intel/iwlwifi/mld/roc.c
index b87faca23ceb..e85f45bce79a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/roc.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/roc.c
@@ -31,13 +31,54 @@ iwl_mld_vif_iter_emlsr_block_roc(void *data, u8 *mac, struct ieee80211_vif *vif)
 		*result = ret;
 }
 
+struct iwl_mld_roc_iter_data {
+	enum iwl_roc_activity activity;
+	struct ieee80211_vif *vif;
+	bool found;
+};
+
+static void iwl_mld_find_roc_vif_iter(void *data, u8 *mac,
+				      struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_roc_iter_data *roc_data = data;
+
+	if (mld_vif->roc_activity != roc_data->activity)
+		return;
+
+	/* The FW supports one ROC of each type simultaneously */
+	if (WARN_ON(roc_data->found)) {
+		roc_data->vif = NULL;
+		return;
+	}
+
+	roc_data->found = true;
+	roc_data->vif = vif;
+}
+
+static struct ieee80211_vif *
+iwl_mld_find_roc_vif(struct iwl_mld *mld, enum iwl_roc_activity activity)
+{
+	struct iwl_mld_roc_iter_data roc_data = {
+		.activity = activity,
+		.found = false,
+	};
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_find_roc_vif_iter,
+						&roc_data);
+
+	return roc_data.vif;
+}
+
 int iwl_mld_start_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		      struct ieee80211_channel *channel, int duration,
 		      enum ieee80211_roc_type type)
 {
 	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
 	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
-	struct iwl_mld_int_sta *aux_sta;
+	struct iwl_mld_int_sta *aux_sta = &mld_vif->aux_sta;
 	struct iwl_roc_req cmd = {
 		.action = cpu_to_le32(FW_CTXT_ACTION_ADD),
 	};
@@ -49,38 +90,40 @@ int iwl_mld_start_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	lockdep_assert_wiphy(mld->wiphy);
 
-	ieee80211_iterate_active_interfaces_mtx(mld->hw,
-						IEEE80211_IFACE_ITER_NORMAL,
-						iwl_mld_vif_iter_emlsr_block_roc,
-						&ret);
-	if (ret)
-		return ret;
-
-	/* TODO: task=Hotspot 2.0 */
-	if (vif->type != NL80211_IFTYPE_P2P_DEVICE) {
+	if (vif->type != NL80211_IFTYPE_P2P_DEVICE &&
+	    vif->type != NL80211_IFTYPE_STATION) {
 		IWL_ERR(mld, "NOT SUPPORTED: ROC on vif->type %d\n",
 			vif->type);
 
 		return -EOPNOTSUPP;
 	}
 
-	switch (type) {
-	case IEEE80211_ROC_TYPE_NORMAL:
-		activity = ROC_ACTIVITY_P2P_DISC;
-		break;
-	case IEEE80211_ROC_TYPE_MGMT_TX:
-		activity = ROC_ACTIVITY_P2P_NEG;
-		break;
-	default:
-		WARN_ONCE(1, "Got an invalid P2P ROC type\n");
-		return -EINVAL;
+	if (vif->type == NL80211_IFTYPE_P2P_DEVICE) {
+		switch (type) {
+		case IEEE80211_ROC_TYPE_NORMAL:
+			activity = ROC_ACTIVITY_P2P_DISC;
+			break;
+		case IEEE80211_ROC_TYPE_MGMT_TX:
+			activity = ROC_ACTIVITY_P2P_NEG;
+			break;
+		default:
+			WARN_ONCE(1, "Got an invalid P2P ROC type\n");
+			return -EINVAL;
+		}
+	} else {
+		activity = ROC_ACTIVITY_HOTSPOT;
 	}
 
-	if (WARN_ON(mld_vif->roc_activity != ROC_NUM_ACTIVITIES))
+	/* The FW supports one ROC of each type simultaneously */
+	if (WARN_ON(iwl_mld_find_roc_vif(mld, activity)))
 		return -EBUSY;
 
-	/* No MLO on P2P device */
-	aux_sta = &mld_vif->deflink.aux_sta;
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_vif_iter_emlsr_block_roc,
+						&ret);
+	if (ret)
+		return ret;
 
 	ret = iwl_mld_add_aux_sta(mld, aux_sta);
 	if (ret)
@@ -91,9 +134,6 @@ int iwl_mld_start_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	cmd.channel_info.channel = cpu_to_le32(channel->hw_value);
 	cmd.channel_info.band = iwl_mld_nl80211_band_to_fw(channel->band);
 	cmd.channel_info.width = IWL_PHY_CHANNEL_MODE20;
-	/* TODO: task=Hotspot 2.0, revisit those parameters when we add an ROC
-	 * on the BSS vif
-	 */
 	cmd.max_delay = cpu_to_le32(AUX_ROC_MAX_DELAY);
 	cmd.duration = cpu_to_le32(MSEC_TO_TU(duration));
 
@@ -105,6 +145,7 @@ int iwl_mld_start_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		IWL_ERR(mld, "Couldn't send the ROC_CMD\n");
 		return ret;
 	}
+
 	mld_vif->roc_activity = activity;
 
 	return 0;
@@ -136,9 +177,9 @@ static void iwl_mld_destroy_roc(struct iwl_mld *mld,
 	 * we can flush the Tx on the queues
 	 */
 
-	iwl_mld_flush_link_sta_txqs(mld, mld_vif->deflink.aux_sta.sta_id);
+	iwl_mld_flush_link_sta_txqs(mld, mld_vif->aux_sta.sta_id);
 
-	iwl_mld_remove_aux_sta(mld, vif, &vif->bss_conf);
+	iwl_mld_remove_aux_sta(mld, vif);
 }
 
 int iwl_mld_cancel_roc(struct ieee80211_hw *hw,
@@ -156,8 +197,8 @@ int iwl_mld_cancel_roc(struct ieee80211_hw *hw,
 
 	lockdep_assert_wiphy(mld->wiphy);
 
-	/* TODO: task=Hotspot 2.0 */
-	if (WARN_ON(vif->type != NL80211_IFTYPE_P2P_DEVICE))
+	if (WARN_ON(vif->type != NL80211_IFTYPE_P2P_DEVICE &&
+		    vif->type != NL80211_IFTYPE_STATION))
 		return -EOPNOTSUPP;
 
 	/* No roc activity running it's probably already done */
@@ -192,10 +233,10 @@ void iwl_mld_handle_roc_notif(struct iwl_mld *mld,
 {
 	const struct iwl_roc_notif *notif = (void *)pkt->data;
 	u32 activity = le32_to_cpu(notif->activity);
-	/* TODO: task=Hotspot 2.0 - roc can run on BSS */
-	struct ieee80211_vif *vif = mld->p2p_device_vif;
 	struct iwl_mld_vif *mld_vif;
+	struct ieee80211_vif *vif;
 
+	vif = iwl_mld_find_roc_vif(mld, activity);
 	if (WARN_ON(!vif))
 		return;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/rx.c b/drivers/net/wireless/intel/iwlwifi/mld/rx.c
index c4f189bcece2..ce0093d5c638 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/rx.c
@@ -33,17 +33,17 @@ struct iwl_mld_rx_phy_data {
 	u32 gp2_on_air_rise;
 	u16 phy_info;
 	u8 energy_a, energy_b;
-	u8 channel;
 };
 
 static void
-iwl_mld_fill_phy_data(struct iwl_rx_mpdu_desc *desc,
+iwl_mld_fill_phy_data(struct iwl_mld *mld,
+		      struct iwl_rx_mpdu_desc *desc,
 		      struct iwl_mld_rx_phy_data *phy_data)
 {
 	phy_data->phy_info = le16_to_cpu(desc->phy_info);
-	phy_data->rate_n_flags = le32_to_cpu(desc->v3.rate_n_flags);
+	phy_data->rate_n_flags = iwl_v3_rate_from_v2_v3(desc->v3.rate_n_flags,
+							mld->fw_rates_ver_3);
 	phy_data->gp2_on_air_rise = le32_to_cpu(desc->v3.gp2_on_air_rise);
-	phy_data->channel = desc->v3.channel;
 	phy_data->energy_a = desc->v3.energy_a;
 	phy_data->energy_b = desc->v3.energy_b;
 	phy_data->data0 = desc->v3.phy_data0;
@@ -1162,8 +1162,6 @@ static void iwl_mld_add_rtap_sniffer_config(struct iwl_mld *mld,
 
 static void iwl_mld_rx_fill_status(struct iwl_mld *mld, struct sk_buff *skb,
 				   struct iwl_mld_rx_phy_data *phy_data,
-				   struct iwl_rx_mpdu_desc *mpdu_desc,
-				   struct ieee80211_hdr *hdr,
 				   int queue)
 {
 	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
@@ -1172,47 +1170,15 @@ static void iwl_mld_rx_fill_status(struct iwl_mld *mld, struct sk_buff *skb,
 	u8 stbc = u32_get_bits(rate_n_flags, RATE_MCS_STBC_MSK);
 	bool is_sgi = rate_n_flags & RATE_MCS_SGI_MSK;
 
-	if (WARN_ON_ONCE(phy_data->with_data && (!mpdu_desc || !hdr)))
-		return;
-
-	/* Keep packets with CRC errors (and with overrun) for monitor mode
-	 * (otherwise the firmware discards them) but mark them as bad.
-	 */
-	if (phy_data->with_data &&
-	    (!(mpdu_desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_CRC_OK)) ||
-	     !(mpdu_desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_OVERRUN_OK)))) {
-		IWL_DEBUG_RX(mld, "Bad CRC or FIFO: 0x%08X.\n",
-			     le32_to_cpu(mpdu_desc->status));
-		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
-	}
-
 	phy_data->info_type = IWL_RX_PHY_INFO_TYPE_NONE;
 
-	if (phy_data->with_data &&
-	    likely(!(phy_data->phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD))) {
-		rx_status->mactime =
-			le64_to_cpu(mpdu_desc->v3.tsf_on_air_rise);
-
-		/* TSF as indicated by the firmware is at INA time */
-		rx_status->flag |= RX_FLAG_MACTIME_PLCP_START;
-	} else {
+	if (phy_data->phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD)
 		phy_data->info_type =
 			le32_get_bits(phy_data->data1,
 				      IWL_RX_PHY_DATA1_INFO_TYPE_MASK);
-	}
-
-	/* management stuff on default queue */
-	if (!queue && phy_data->with_data &&
-	    unlikely(ieee80211_is_beacon(hdr->frame_control) ||
-		     ieee80211_is_probe_resp(hdr->frame_control))) {
-		rx_status->boottime_ns = ktime_get_boottime_ns();
-
-		if (mld->scan.pass_all_sched_res == SCHED_SCAN_PASS_ALL_STATE_ENABLED)
-			mld->scan.pass_all_sched_res = SCHED_SCAN_PASS_ALL_STATE_FOUND;
-	}
 
 	/* set the preamble flag if appropriate */
-	if (format == RATE_MCS_CCK_MSK &&
+	if (format == RATE_MCS_MOD_TYPE_CCK &&
 	    phy_data->phy_info & IWL_RX_MPDU_PHY_SHORT_PREAMBLE)
 		rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 
@@ -1237,7 +1203,7 @@ static void iwl_mld_rx_fill_status(struct iwl_mld *mld, struct sk_buff *skb,
 	}
 
 	/* must be before L-SIG data */
-	if (format == RATE_MCS_HE_MSK)
+	if (format == RATE_MCS_MOD_TYPE_HE)
 		iwl_mld_rx_he(mld, skb, phy_data, queue);
 
 	iwl_mld_decode_lsig(skb, phy_data);
@@ -1245,40 +1211,53 @@ static void iwl_mld_rx_fill_status(struct iwl_mld *mld, struct sk_buff *skb,
 	rx_status->device_timestamp = phy_data->gp2_on_air_rise;
 
 	/* using TLV format and must be after all fixed len fields */
-	if (format == RATE_MCS_EHT_MSK)
+	if (format == RATE_MCS_MOD_TYPE_EHT)
 		iwl_mld_rx_eht(mld, skb, phy_data, queue);
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
-	if (unlikely(mld->monitor.on))
+	if (unlikely(mld->monitor.on)) {
 		iwl_mld_add_rtap_sniffer_config(mld, skb);
+
+		if (mld->monitor.ptp_time) {
+			u64 adj_time =
+			    iwl_mld_ptp_get_adj_time(mld,
+						     phy_data->gp2_on_air_rise *
+						     NSEC_PER_USEC);
+
+			rx_status->mactime = div64_u64(adj_time, NSEC_PER_USEC);
+			rx_status->flag |= RX_FLAG_MACTIME_IS_RTAP_TS64;
+			rx_status->flag &= ~RX_FLAG_MACTIME;
+		}
+	}
 #endif
 
-	if (format != RATE_MCS_CCK_MSK && is_sgi)
+	if (format != RATE_MCS_MOD_TYPE_CCK && is_sgi)
 		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
 	if (rate_n_flags & RATE_MCS_LDPC_MSK)
 		rx_status->enc_flags |= RX_ENC_FLAG_LDPC;
 
 	switch (format) {
-	case RATE_MCS_HT_MSK:
+	case RATE_MCS_MOD_TYPE_HT:
 		rx_status->encoding = RX_ENC_HT;
 		rx_status->rate_idx = RATE_HT_MCS_INDEX(rate_n_flags);
 		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
 		break;
-	case RATE_MCS_VHT_MSK:
-	case RATE_MCS_HE_MSK:
-	case RATE_MCS_EHT_MSK:
-		if (format == RATE_MCS_VHT_MSK) {
+	case RATE_MCS_MOD_TYPE_VHT:
+	case RATE_MCS_MOD_TYPE_HE:
+	case RATE_MCS_MOD_TYPE_EHT:
+		if (format == RATE_MCS_MOD_TYPE_VHT) {
 			rx_status->encoding = RX_ENC_VHT;
-		} else if (format == RATE_MCS_HE_MSK) {
+		} else if (format == RATE_MCS_MOD_TYPE_HE) {
 			rx_status->encoding = RX_ENC_HE;
 			rx_status->he_dcm =
 				!!(rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK);
-		} else if (format == RATE_MCS_EHT_MSK) {
+		} else if (format == RATE_MCS_MOD_TYPE_EHT) {
 			rx_status->encoding = RX_ENC_EHT;
 		}
 
-		rx_status->nss = u32_get_bits(rate_n_flags, RATE_MCS_NSS_MSK) + 1;
+		rx_status->nss = u32_get_bits(rate_n_flags,
+					      RATE_MCS_NSS_MSK) + 1;
 		rx_status->rate_idx = rate_n_flags & RATE_MCS_CODE_MSK;
 		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
 		break;
@@ -1735,15 +1714,11 @@ static void iwl_mld_rx_update_ampdu_ref(struct iwl_mld *mld,
 }
 
 static void
-iwl_mld_fill_rx_status_band_freq(struct iwl_mld_rx_phy_data *phy_data,
-				 struct iwl_rx_mpdu_desc *mpdu_desc,
-				 struct ieee80211_rx_status *rx_status)
+iwl_mld_fill_rx_status_band_freq(struct ieee80211_rx_status *rx_status,
+				 u8 band, u8 channel)
 {
-	enum nl80211_band band;
-
-	band = BAND_IN_RX_STATUS(mpdu_desc->mac_phy_idx);
 	rx_status->band = iwl_mld_phy_band_to_nl80211(band);
-	rx_status->freq = ieee80211_channel_to_frequency(phy_data->channel,
+	rx_status->freq = ieee80211_channel_to_frequency(channel,
 							 rx_status->band);
 }
 
@@ -1758,7 +1733,7 @@ void iwl_mld_rx_mpdu(struct iwl_mld *mld, struct napi_struct *napi,
 	struct sk_buff *skb;
 	size_t mpdu_desc_size = sizeof(*mpdu_desc);
 	bool drop = false;
-	u8 crypto_len = 0;
+	u8 crypto_len = 0, band;
 	u32 pkt_len = iwl_rx_packet_payload_len(pkt);
 	u32 mpdu_len;
 	enum iwl_mld_reorder_result reorder_res;
@@ -1788,7 +1763,7 @@ void iwl_mld_rx_mpdu(struct iwl_mld *mld, struct napi_struct *napi,
 
 	hdr = (void *)(pkt->data + mpdu_desc_size);
 
-	iwl_mld_fill_phy_data(mpdu_desc, &phy_data);
+	iwl_mld_fill_phy_data(mld, mpdu_desc, &phy_data);
 
 	if (mpdu_desc->mac_flags2 & IWL_RX_MPDU_MFLG2_PAD) {
 		/* If the device inserted padding it means that (it thought)
@@ -1802,7 +1777,11 @@ void iwl_mld_rx_mpdu(struct iwl_mld *mld, struct napi_struct *napi,
 	rx_status = IEEE80211_SKB_RXCB(skb);
 
 	/* this is needed early */
-	iwl_mld_fill_rx_status_band_freq(&phy_data, mpdu_desc, rx_status);
+	band = u8_get_bits(mpdu_desc->mac_phy_band,
+			   IWL_RX_MPDU_MAC_PHY_BAND_BAND_MASK);
+	iwl_mld_fill_rx_status_band_freq(rx_status, band,
+					 mpdu_desc->v3.channel);
+
 
 	rcu_read_lock();
 
@@ -1814,7 +1793,36 @@ void iwl_mld_rx_mpdu(struct iwl_mld *mld, struct napi_struct *napi,
 	if (!queue && (phy_data.phy_info & IWL_RX_MPDU_PHY_AMPDU))
 		iwl_mld_rx_update_ampdu_ref(mld, &phy_data, rx_status);
 
-	iwl_mld_rx_fill_status(mld, skb, &phy_data, mpdu_desc, hdr, queue);
+	/* Keep packets with CRC errors (and with overrun) for monitor mode
+	 * (otherwise the firmware discards them) but mark them as bad.
+	 */
+	if (!(mpdu_desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_CRC_OK)) ||
+	    !(mpdu_desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_OVERRUN_OK))) {
+		IWL_DEBUG_RX(mld, "Bad CRC or FIFO: 0x%08X.\n",
+			     le32_to_cpu(mpdu_desc->status));
+		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
+	}
+
+	if (likely(!(phy_data.phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD))) {
+		rx_status->mactime =
+			le64_to_cpu(mpdu_desc->v3.tsf_on_air_rise);
+
+		/* TSF as indicated by the firmware is at INA time */
+		rx_status->flag |= RX_FLAG_MACTIME_PLCP_START;
+	}
+
+	/* management stuff on default queue */
+	if (!queue && unlikely(ieee80211_is_beacon(hdr->frame_control) ||
+			       ieee80211_is_probe_resp(hdr->frame_control))) {
+		rx_status->boottime_ns = ktime_get_boottime_ns();
+
+		if (mld->scan.pass_all_sched_res ==
+				SCHED_SCAN_PASS_ALL_STATE_ENABLED)
+			mld->scan.pass_all_sched_res =
+				SCHED_SCAN_PASS_ALL_STATE_FOUND;
+	}
+
+	iwl_mld_rx_fill_status(mld, skb, &phy_data, queue);
 
 	if (iwl_mld_rx_crypto(mld, sta, hdr, rx_status, mpdu_desc, queue,
 			      le32_to_cpu(pkt->len_n_flags), &crypto_len))
@@ -1857,7 +1865,7 @@ void iwl_mld_sync_rx_queues(struct iwl_mld *mld,
 			    enum iwl_mld_internal_rxq_notif_type type,
 			    const void *notif_payload, u32 notif_payload_size)
 {
-	u8 num_rx_queues = mld->trans->num_rx_queues;
+	u8 num_rx_queues = mld->trans->info.num_rxqs;
 	struct {
 		struct iwl_rxq_sync_cmd sync_cmd;
 		struct iwl_mld_internal_rxq_notif notif;
@@ -1956,6 +1964,7 @@ void iwl_mld_rx_monitor_no_data(struct iwl_mld *mld, struct napi_struct *napi,
 	struct ieee80211_rx_status *rx_status;
 	struct sk_buff *skb;
 	u32 format, rssi;
+	u8 channel;
 
 	if (unlikely(mld->fw_status.in_hw_restart))
 		return;
@@ -1968,14 +1977,16 @@ void iwl_mld_rx_monitor_no_data(struct iwl_mld *mld, struct napi_struct *napi,
 	desc = (void *)pkt->data;
 
 	rssi = le32_to_cpu(desc->rssi);
+	channel = u32_get_bits(rssi, RX_NO_DATA_CHANNEL_MSK);
+
 	phy_data.energy_a = u32_get_bits(rssi, RX_NO_DATA_CHAIN_A_MSK);
 	phy_data.energy_b = u32_get_bits(rssi, RX_NO_DATA_CHAIN_B_MSK);
-	phy_data.channel = u32_get_bits(rssi, RX_NO_DATA_CHANNEL_MSK);
 	phy_data.data0 = desc->phy_info[0];
 	phy_data.data1 = desc->phy_info[1];
 	phy_data.phy_info = IWL_RX_MPDU_PHY_TSF_OVERLOAD;
 	phy_data.gp2_on_air_rise = le32_to_cpu(desc->on_air_rise_time);
-	phy_data.rate_n_flags = le32_to_cpu(desc->rate);
+	phy_data.rate_n_flags = iwl_v3_rate_from_v2_v3(desc->rate,
+						       mld->fw_rates_ver_3);
 	phy_data.with_data = false;
 
 	BUILD_BUG_ON(sizeof(phy_data.rx_vec) != sizeof(desc->rx_vec));
@@ -2018,13 +2029,13 @@ void iwl_mld_rx_monitor_no_data(struct iwl_mld *mld, struct napi_struct *napi,
 		break;
 	}
 
-	rx_status->band = phy_data.channel > 14 ? NL80211_BAND_5GHZ :
+	rx_status->band = channel > 14 ? NL80211_BAND_5GHZ :
 		NL80211_BAND_2GHZ;
 
-	rx_status->freq = ieee80211_channel_to_frequency(phy_data.channel,
+	rx_status->freq = ieee80211_channel_to_frequency(channel,
 							 rx_status->band);
 
-	iwl_mld_rx_fill_status(mld, skb, &phy_data, NULL, NULL, queue);
+	iwl_mld_rx_fill_status(mld, skb, &phy_data, queue);
 
 	/* No more radiotap info should be added after this point.
 	 * Mark it as mac header for upper layers to know where
@@ -2037,17 +2048,17 @@ void iwl_mld_rx_monitor_no_data(struct iwl_mld *mld, struct napi_struct *napi,
 	 * may be up to 8 spatial streams.
 	 */
 	switch (format) {
-	case RATE_MCS_VHT_MSK:
+	case RATE_MCS_MOD_TYPE_VHT:
 		rx_status->nss =
 			le32_get_bits(desc->rx_vec[0],
 				      RX_NO_DATA_RX_VEC0_VHT_NSTS_MSK) + 1;
 		break;
-	case RATE_MCS_HE_MSK:
+	case RATE_MCS_MOD_TYPE_HE:
 		rx_status->nss =
 			le32_get_bits(desc->rx_vec[0],
 				      RX_NO_DATA_RX_VEC0_HE_NSTS_MSK) + 1;
 		break;
-	case RATE_MCS_EHT_MSK:
+	case RATE_MCS_MOD_TYPE_EHT:
 		rx_status->nss =
 			le32_get_bits(desc->rx_vec[2],
 				      RX_NO_DATA_RX_VEC2_EHT_NSTS_MSK) + 1;
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/scan.c b/drivers/net/wireless/intel/iwlwifi/mld/scan.c
index 7ec04318ec2f..3fce7cd2d512 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/scan.c
@@ -1920,6 +1920,9 @@ void iwl_mld_handle_scan_complete_notif(struct iwl_mld *mld,
 			IWL_DEBUG_SCAN(mld, "Scan link is no longer valid\n");
 
 		ieee80211_scan_completed(mld->hw, &info);
+
+		/* Scan is over, we can check again the tpt counters */
+		iwl_mld_stop_ignoring_tpt_updates(mld);
 	} else if (mld->scan.uid_status[uid] == IWL_MLD_SCAN_SCHED) {
 		ieee80211_sched_scan_stopped(mld->hw);
 		mld->scan.pass_all_sched_res = SCHED_SCAN_PASS_ALL_STATE_DISABLED;
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/sta.c b/drivers/net/wireless/intel/iwlwifi/mld/sta.c
index 332a7aecec2d..8fb51209b4a6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/sta.c
@@ -401,9 +401,11 @@ static u32 iwl_mld_get_htc_flags(struct ieee80211_link_sta *link_sta)
 static int iwl_mld_send_sta_cmd(struct iwl_mld *mld,
 				const struct iwl_sta_cfg_cmd *cmd)
 {
-	int ret = iwl_mld_send_cmd_pdu(mld,
-				       WIDE_ID(MAC_CONF_GROUP, STA_CONFIG_CMD),
-				       cmd);
+	u32 cmd_id = WIDE_ID(MAC_CONF_GROUP, STA_CONFIG_CMD);
+	int cmd_len = iwl_fw_lookup_cmd_ver(mld->fw, cmd_id, 0) > 1 ?
+		      sizeof(*cmd) :
+		      sizeof(struct iwl_sta_cfg_cmd_v1);
+	int ret = iwl_mld_send_cmd_pdu(mld, cmd_id, cmd, cmd_len);
 	if (ret)
 		IWL_ERR(mld, "STA_CONFIG_CMD send failed, ret=0x%x\n", ret);
 	return ret;
@@ -660,7 +662,7 @@ iwl_mld_alloc_dup_data(struct iwl_mld *mld, struct iwl_mld_sta *mld_sta)
 	if (mld->fw_status.in_hw_restart)
 		return 0;
 
-	dup_data = kcalloc(mld->trans->num_rx_queues, sizeof(*dup_data),
+	dup_data = kcalloc(mld->trans->info.num_rxqs, sizeof(*dup_data),
 			   GFP_KERNEL);
 	if (!dup_data)
 		return -ENOMEM;
@@ -673,7 +675,7 @@ iwl_mld_alloc_dup_data(struct iwl_mld *mld, struct iwl_mld_sta *mld_sta)
 	 * This thus allows receiving a packet with seqno 0 and the
 	 * retry bit set as the very first packet on a new TID.
 	 */
-	for (int q = 0; q < mld->trans->num_rx_queues; q++)
+	for (int q = 0; q < mld->trans->info.num_rxqs; q++)
 		memset(dup_data[q].last_seq, 0xff,
 		       sizeof(dup_data[q].last_seq));
 	mld_sta->dup_data = dup_data;
@@ -695,13 +697,13 @@ static void iwl_mld_alloc_mpdu_counters(struct iwl_mld *mld,
 	    sta->tdls || !ieee80211_vif_is_mld(vif))
 		return;
 
-	mld_sta->mpdu_counters = kcalloc(mld->trans->num_rx_queues,
+	mld_sta->mpdu_counters = kcalloc(mld->trans->info.num_rxqs,
 					 sizeof(*mld_sta->mpdu_counters),
 					 GFP_KERNEL);
 	if (!mld_sta->mpdu_counters)
 		return;
 
-	for (int q = 0; q < mld->trans->num_rx_queues; q++)
+	for (int q = 0; q < mld->trans->info.num_rxqs; q++)
 		spin_lock_init(&mld_sta->mpdu_counters[q].lock);
 }
 
@@ -947,7 +949,7 @@ static int iwl_mld_allocate_internal_txq(struct iwl_mld *mld,
 	int queue, size;
 
 	size = max_t(u32, IWL_MGMT_QUEUE_SIZE,
-		     mld->trans->cfg->min_txq_size);
+		     mld->trans->mac_cfg->base->min_txq_size);
 
 	queue = iwl_trans_txq_alloc(mld->trans, 0, sta_mask, tid, size,
 				    IWL_WATCHDOG_DISABLED);
@@ -1087,6 +1089,24 @@ int iwl_mld_add_aux_sta(struct iwl_mld *mld,
 					0, NULL, IWL_MAX_TID_COUNT);
 }
 
+int iwl_mld_add_mon_sta(struct iwl_mld *mld,
+			struct ieee80211_vif *vif,
+			struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+
+	if (WARN_ON(!mld_link))
+		return -EINVAL;
+
+	if (WARN_ON(vif->type != NL80211_IFTYPE_MONITOR))
+		return -EINVAL;
+
+	return iwl_mld_add_internal_sta(mld, &mld_link->mon_sta,
+					STATION_TYPE_BCAST_MGMT,
+					mld_link->fw_id, NULL,
+					IWL_MAX_TID_COUNT);
+}
+
 static void iwl_mld_remove_internal_sta(struct iwl_mld *mld,
 					struct iwl_mld_int_sta *internal_sta,
 					bool flush, u8 tid)
@@ -1140,6 +1160,19 @@ void iwl_mld_remove_mcast_sta(struct iwl_mld *mld,
 }
 
 void iwl_mld_remove_aux_sta(struct iwl_mld *mld,
+			    struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	if (WARN_ON(vif->type != NL80211_IFTYPE_P2P_DEVICE &&
+		    vif->type != NL80211_IFTYPE_STATION))
+		return;
+
+	iwl_mld_remove_internal_sta(mld, &mld_vif->aux_sta, false,
+				    IWL_MAX_TID_COUNT);
+}
+
+void iwl_mld_remove_mon_sta(struct iwl_mld *mld,
 			    struct ieee80211_vif *vif,
 			    struct ieee80211_bss_conf *link)
 {
@@ -1148,11 +1181,10 @@ void iwl_mld_remove_aux_sta(struct iwl_mld *mld,
 	if (WARN_ON(!mld_link))
 		return;
 
-	/* TODO: Hotspot 2.0 */
-	if (WARN_ON(vif->type != NL80211_IFTYPE_P2P_DEVICE))
+	if (WARN_ON(vif->type != NL80211_IFTYPE_MONITOR))
 		return;
 
-	iwl_mld_remove_internal_sta(mld, &mld_link->aux_sta, false,
+	iwl_mld_remove_internal_sta(mld, &mld_link->mon_sta, false,
 				    IWL_MAX_TID_COUNT);
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/sta.h b/drivers/net/wireless/intel/iwlwifi/mld/sta.h
index ddcffd7b9fde..1897b121aae2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/sta.h
@@ -247,6 +247,10 @@ int iwl_mld_add_mcast_sta(struct iwl_mld *mld,
 int iwl_mld_add_aux_sta(struct iwl_mld *mld,
 			struct iwl_mld_int_sta *internal_sta);
 
+int iwl_mld_add_mon_sta(struct iwl_mld *mld,
+			struct ieee80211_vif *vif,
+			struct ieee80211_bss_conf *link);
+
 void iwl_mld_remove_bcast_sta(struct iwl_mld *mld,
 			      struct ieee80211_vif *vif,
 			      struct ieee80211_bss_conf *link);
@@ -256,6 +260,9 @@ void iwl_mld_remove_mcast_sta(struct iwl_mld *mld,
 			      struct ieee80211_bss_conf *link);
 
 void iwl_mld_remove_aux_sta(struct iwl_mld *mld,
+			    struct ieee80211_vif *vif);
+
+void iwl_mld_remove_mon_sta(struct iwl_mld *mld,
 			    struct ieee80211_vif *vif,
 			    struct ieee80211_bss_conf *link);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/stats.c b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
index 0715bbc31031..f633cb1cf510 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/stats.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
@@ -191,11 +191,12 @@ static void iwl_mld_sta_stats_fill_txrate(struct iwl_mld_sta *mld_sta,
 		break;
 	}
 
-	if (format == RATE_MCS_CCK_MSK || format == RATE_MCS_LEGACY_OFDM_MSK) {
+	if (format == RATE_MCS_MOD_TYPE_CCK ||
+	    format == RATE_MCS_MOD_TYPE_LEGACY_OFDM) {
 		int rate = u32_get_bits(rate_n_flags, RATE_LEGACY_RATE_MSK);
 
 		/* add the offset needed to get to the legacy ofdm indices */
-		if (format == RATE_MCS_LEGACY_OFDM_MSK)
+		if (format == RATE_MCS_MOD_TYPE_LEGACY_OFDM)
 			rate += IWL_FIRST_OFDM_RATE;
 
 		switch (rate) {
@@ -240,7 +241,7 @@ static void iwl_mld_sta_stats_fill_txrate(struct iwl_mld_sta *mld_sta,
 
 	rinfo->nss = u32_get_bits(rate_n_flags, RATE_MCS_NSS_MSK) + 1;
 
-	if (format == RATE_MCS_HT_MSK)
+	if (format == RATE_MCS_MOD_TYPE_HT)
 		rinfo->mcs = RATE_HT_MCS_INDEX(rate_n_flags);
 	else
 		rinfo->mcs = u32_get_bits(rate_n_flags, RATE_MCS_CODE_MSK);
@@ -249,10 +250,10 @@ static void iwl_mld_sta_stats_fill_txrate(struct iwl_mld_sta *mld_sta,
 		rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
 
 	switch (format) {
-	case RATE_MCS_EHT_MSK:
+	case RATE_MCS_MOD_TYPE_EHT:
 		rinfo->flags |= RATE_INFO_FLAGS_EHT_MCS;
 		break;
-	case RATE_MCS_HE_MSK:
+	case RATE_MCS_MOD_TYPE_HE:
 		gi_ltf = u32_get_bits(rate_n_flags, RATE_MCS_HE_GI_LTF_MSK);
 
 		rinfo->flags |= RATE_INFO_FLAGS_HE_MCS;
@@ -293,10 +294,10 @@ static void iwl_mld_sta_stats_fill_txrate(struct iwl_mld_sta *mld_sta,
 		if (rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK)
 			rinfo->he_dcm = 1;
 		break;
-	case RATE_MCS_HT_MSK:
+	case RATE_MCS_MOD_TYPE_HT:
 		rinfo->flags |= RATE_INFO_FLAGS_MCS;
 		break;
-	case RATE_MCS_VHT_MSK:
+	case RATE_MCS_MOD_TYPE_VHT:
 		rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS;
 		break;
 	}
@@ -467,12 +468,18 @@ static void iwl_mld_fill_chanctx_stats(struct ieee80211_hw *hw,
 
 	old_load = phy->avg_channel_load_not_by_us;
 	new_load = le32_to_cpu(per_phy[phy->fw_id].channel_load_not_by_us);
-	if (IWL_FW_CHECK(phy->mld, new_load > 100, "Invalid channel load %u\n",
-			 new_load))
+
+	if (IWL_FW_CHECK(phy->mld,
+			 new_load != IWL_STATS_UNKNOWN_CHANNEL_LOAD &&
+				new_load > 100,
+			 "Invalid channel load %u\n", new_load))
 		return;
 
-	/* give a weight of 0.5 for the old value */
-	phy->avg_channel_load_not_by_us = (new_load >> 1) + (old_load >> 1);
+	if (new_load != IWL_STATS_UNKNOWN_CHANNEL_LOAD) {
+		/* update giving a weight of 0.5 for the old value */
+		phy->avg_channel_load_not_by_us = (new_load >> 1) +
+						  (old_load >> 1);
+	}
 
 	iwl_mld_emlsr_check_chan_load(hw, phy, old_load);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/Makefile b/drivers/net/wireless/intel/iwlwifi/mld/tests/Makefile
index 36317feb923b..3e2ae6020613 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
-iwlmld-tests-y += module.o hcmd.o utils.o link.o rx.o agg.o link-selection.o
+iwlmld-tests-y += module.o hcmd.o utils.o link.o rx.o agg.o link-selection.o emlsr_with_bt.o
 
 ccflags-y += -I$(src)/../
 obj-$(CONFIG_IWLWIFI_KUNIT_TESTS) += iwlmld-tests.o
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/agg.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/agg.c
index 1fd664be1a7c..29b0248cec3d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/agg.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/agg.c
@@ -2,7 +2,7 @@
 /*
  * KUnit tests for channel helper functions
  *
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  */
 #include <kunit/test.h>
 #include <kunit/static_stub.h>
@@ -474,14 +474,14 @@ static struct iwl_rx_mpdu_desc *setup_mpdu_desc(void)
 	KUNIT_ALLOC_AND_ASSERT(test, mpdu_desc);
 
 	mpdu_desc->reorder_data |=
-		cpu_to_le32(FIELD_PREP(IWL_RX_MPDU_REORDER_BAID_MASK,
-				       param->rx_pkt.baid));
+		le32_encode_bits(param->rx_pkt.baid,
+				 IWL_RX_MPDU_REORDER_BAID_MASK);
 	mpdu_desc->reorder_data |=
-		cpu_to_le32(FIELD_PREP(IWL_RX_MPDU_REORDER_SN_MASK,
-				       param->rx_pkt.sn));
+		le32_encode_bits(param->rx_pkt.sn,
+				 IWL_RX_MPDU_REORDER_SN_MASK);
 	mpdu_desc->reorder_data |=
-		cpu_to_le32(FIELD_PREP(IWL_RX_MPDU_REORDER_NSSN_MASK,
-				       param->rx_pkt.nssn));
+		le32_encode_bits(param->rx_pkt.nssn,
+				 IWL_RX_MPDU_REORDER_NSSN_MASK);
 	if (param->rx_pkt.old_sn)
 		mpdu_desc->reorder_data |=
 			cpu_to_le32(IWL_RX_MPDU_REORDER_BA_OLD_SN);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/emlsr_with_bt.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/emlsr_with_bt.c
new file mode 100644
index 000000000000..91556ee5c142
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/emlsr_with_bt.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * KUnit tests for link selection functions
+ *
+ * Copyright (C) 2025 Intel Corporation
+ */
+#include <kunit/static_stub.h>
+
+#include "utils.h"
+#include "mld.h"
+#include "mlo.h"
+
+static const struct emlsr_with_bt_test_case {
+	const char *desc;
+	struct {
+		struct iwl_bt_coex_profile_notif notif;
+		s32 signal;
+		bool check_entry;
+	} input;
+	bool emlsr_allowed;
+} emlsr_with_bt_cases[] = {
+	{
+		.desc = "BT penalty(exit) with low rssi 4.5: emlsr allowed",
+		.input = {
+			.notif.wifi_loss_low_rssi[1] = {4, 5},
+			.notif.wifi_loss_mid_high_rssi[1] = {7, 9},
+			.signal = -69,
+			.check_entry = false,
+		},
+		.emlsr_allowed = true,
+	},
+	{
+		.desc = "BT penalty(exit) from high rssi 5: emlsr allowed",
+		.input = {
+			.notif.wifi_loss_low_rssi[1] = {7, 9},
+			.notif.wifi_loss_mid_high_rssi[1] = {5, 5},
+			.signal = -68,
+			.check_entry = false,
+		},
+		.emlsr_allowed = true,
+	},
+	{
+		.desc = "BT penalty(exit) with low rssi 8: emlsr not allowed",
+		.input = {
+			.notif.wifi_loss_low_rssi[1] = {7, 9},
+			.notif.wifi_loss_mid_high_rssi[1] = {4, 5},
+			.signal = -69,
+			.check_entry = false,
+		},
+		.emlsr_allowed = false,
+	},
+	{
+		.desc = "BT penalty(exit) from high rssi 9: emlsr not allowed",
+		.input = {
+			.notif.wifi_loss_low_rssi[1] = {4, 5},
+			.notif.wifi_loss_mid_high_rssi[1] = {9, 9},
+			.signal = -68,
+			.check_entry = false,
+		},
+		.emlsr_allowed = false,
+	},
+	{
+		.desc = "BT penalty(entry) with low rssi 4.5: emlsr allowed",
+		.input = {
+			.notif.wifi_loss_low_rssi[1] = {4, 5},
+			.notif.wifi_loss_mid_high_rssi[1] = {7, 9},
+			.signal = -63,
+			.check_entry = true,
+		},
+		.emlsr_allowed = true,
+	},
+	{
+		.desc = "BT penalty(entry) from high rssi 5: emlsr allowed",
+		.input = {
+			.notif.wifi_loss_low_rssi[1] = {7, 9},
+			.notif.wifi_loss_mid_high_rssi[1] = {5, 5},
+			.signal = -62,
+			.check_entry = false,
+		},
+		.emlsr_allowed = true,
+	},
+	{
+		.desc = "BT penalty(entry) with low rssi 8: emlsr not allowed",
+		.input = {
+			.notif.wifi_loss_low_rssi[1] = {7, 9},
+			.notif.wifi_loss_mid_high_rssi[1] = {4, 5},
+			.signal = -63,
+			.check_entry = false,
+		},
+		.emlsr_allowed = true,
+	},
+	{
+		.desc = "BT penalty(entry) from high rssi 9: emlsr not allowed",
+		.input = {
+			.notif.wifi_loss_low_rssi[1] = {4, 5},
+			.notif.wifi_loss_mid_high_rssi[1] = {9, 9},
+			.signal = -62,
+			.check_entry = true,
+		},
+		.emlsr_allowed = false,
+	},
+};
+
+KUNIT_ARRAY_PARAM_DESC(emlsr_with_bt, emlsr_with_bt_cases, desc);
+
+static void test_emlsr_with_bt(struct kunit *test)
+{
+	struct iwl_mld *mld = test->priv;
+	const struct emlsr_with_bt_test_case *test_param =
+		(const void *)(test->param_value);
+	struct ieee80211_vif *vif =
+		iwlmld_kunit_add_vif(true, NL80211_IFTYPE_STATION);
+	struct ieee80211_bss_conf *link = iwlmld_kunit_add_link(vif, 1);
+	bool actual_value = false;
+
+	KUNIT_ALLOC_AND_ASSERT(test, link->bss);
+
+	/* Extract test case parameters */
+	link->bss->signal = DBM_TO_MBM(test_param->input.signal);
+	memcpy(&mld->last_bt_notif, &test_param->input.notif,
+	       sizeof(struct iwl_bt_coex_profile_notif));
+
+	actual_value = iwl_mld_bt_allows_emlsr(mld, link,
+					       test_param->input.check_entry);
+	/* Assert that the returned value matches the expected emlsr_allowed */
+	KUNIT_EXPECT_EQ(test, actual_value, test_param->emlsr_allowed);
+}
+
+static struct kunit_case emlsr_with_bt_test_cases[] = {
+	KUNIT_CASE_PARAM(test_emlsr_with_bt, emlsr_with_bt_gen_params),
+	{},
+};
+
+static struct kunit_suite emlsr_with_bt = {
+	.name = "iwlmld-emlsr-with-bt-tests",
+	.test_cases = emlsr_with_bt_test_cases,
+	.init = iwlmld_kunit_test_init,
+};
+
+kunit_test_suite(emlsr_with_bt);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/hcmd.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/hcmd.c
index 4e189bf8b3fb..0e3b9417dd63 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/hcmd.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/hcmd.c
@@ -2,7 +2,7 @@
 /*
  * KUnit tests for channel helper functions
  *
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  */
 #include <kunit/test.h>
 
@@ -30,10 +30,10 @@ static void test_hcmd_names_sorted(struct kunit *test)
 static void test_hcmd_names_for_rx(struct kunit *test)
 {
 	static struct iwl_trans t = {
-		.command_groups = iwl_mld_groups,
+		.conf.command_groups = iwl_mld_groups,
 	};
 
-	t.command_groups_size = global_iwl_mld_goups_size;
+	t.conf.command_groups_size = global_iwl_mld_goups_size;
 
 	for (unsigned int i = 0; i < iwl_mld_rx_handlers_num; i++) {
 		const struct iwl_rx_handler *rxh;
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
index 295dcfd3f85d..94a037bec1fa 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
@@ -32,7 +32,7 @@ static const struct link_grading_test_case {
 		.desc = "channel util of 128 (50%)",
 		.input.link = {
 			.link_id = 0,
-			.chandef = &chandef_2ghz,
+			.chandef = &chandef_2ghz_20mhz,
 			.active = false,
 			.has_chan_util_elem = true,
 			.chan_util = 128,
@@ -43,7 +43,7 @@ static const struct link_grading_test_case {
 		.desc = "channel util of 180 (70%)",
 		.input.link = {
 			.link_id = 0,
-			.chandef = &chandef_2ghz,
+			.chandef = &chandef_2ghz_20mhz,
 			.active = false,
 			.has_chan_util_elem = true,
 			.chan_util = 180,
@@ -54,7 +54,7 @@ static const struct link_grading_test_case {
 		.desc = "channel util of 180 (70%), channel load by us of 10%",
 		.input.link = {
 			.link_id = 0,
-			.chandef = &chandef_2ghz,
+			.chandef = &chandef_2ghz_20mhz,
 			.has_chan_util_elem = true,
 			.chan_util = 180,
 			.active = true,
@@ -66,7 +66,7 @@ static const struct link_grading_test_case {
 		.desc = "no channel util element",
 		.input.link = {
 			.link_id = 0,
-			.chandef = &chandef_2ghz,
+			.chandef = &chandef_2ghz_20mhz,
 			.active = true,
 		},
 		.expected_grade = 120,
@@ -132,7 +132,7 @@ static void test_link_grading(struct kunit *test)
 	bool active = test_param->input.link.active;
 	u16 valid_links;
 	struct iwl_mld_kunit_link assoc_link = {
-		.band = test_param->input.link.chandef->chan->band,
+		.chandef = test_param->input.link.chandef,
 	};
 
 	/* If the link is not active, use a different link as the assoc link */
@@ -172,108 +172,150 @@ static struct kunit_suite link_selection = {
 
 kunit_test_suite(link_selection);
 
-static const struct channel_load_case {
+static const struct link_pair_case {
 	const char *desc;
+	const struct cfg80211_chan_def *chandef_a, *chandef_b;
 	bool low_latency_vif;
 	u32 chan_load_not_by_us;
-	enum nl80211_chan_width bw_a;
-	enum nl80211_chan_width bw_b;
 	bool primary_link_active;
-	bool expected_result;
-} channel_load_cases[] = {
+	u32 expected_result;
+} link_pair_cases[] = {
 	{
 		.desc = "Unequal bandwidth, primary link inactive, EMLSR not allowed",
 		.low_latency_vif = false,
 		.primary_link_active = false,
-		.bw_a = NL80211_CHAN_WIDTH_40,
-		.bw_b = NL80211_CHAN_WIDTH_20,
-		.expected_result = false,
+		.chandef_a = &chandef_5ghz_40mhz,
+		.chandef_b = &chandef_6ghz_20mhz,
+		.expected_result = IWL_MLD_EMLSR_EXIT_CHAN_LOAD,
 	},
 	{
 		.desc = "Equal bandwidths, sufficient channel load, EMLSR allowed",
 		.low_latency_vif = false,
 		.primary_link_active = true,
 		.chan_load_not_by_us = 11,
-		.bw_a = NL80211_CHAN_WIDTH_40,
-		.bw_b = NL80211_CHAN_WIDTH_40,
-		.expected_result = true,
+		.chandef_a = &chandef_5ghz_40mhz,
+		.chandef_b = &chandef_6ghz_40mhz,
+		.expected_result = 0,
 	},
 	{
 		.desc = "Equal bandwidths, insufficient channel load, EMLSR not allowed",
 		.low_latency_vif = false,
 		.primary_link_active = true,
 		.chan_load_not_by_us = 6,
-		.bw_a = NL80211_CHAN_WIDTH_80,
-		.bw_b = NL80211_CHAN_WIDTH_80,
-		.expected_result = false,
+		.chandef_a = &chandef_5ghz_80mhz,
+		.chandef_b = &chandef_6ghz_80mhz,
+		.expected_result = IWL_MLD_EMLSR_EXIT_CHAN_LOAD,
 	},
 	{
 		.desc = "Low latency VIF, sufficient channel load, EMLSR allowed",
 		.low_latency_vif = true,
 		.primary_link_active = true,
 		.chan_load_not_by_us = 6,
-		.bw_a = NL80211_CHAN_WIDTH_160,
-		.bw_b = NL80211_CHAN_WIDTH_160,
-		.expected_result = true,
+		.chandef_a = &chandef_5ghz_160mhz,
+		.chandef_b = &chandef_6ghz_160mhz,
+		.expected_result = 0,
 	},
 	{
 		.desc = "Different bandwidths (2x ratio), primary link load permits EMLSR",
 		.low_latency_vif = false,
 		.primary_link_active = true,
 		.chan_load_not_by_us = 30,
-		.bw_a = NL80211_CHAN_WIDTH_40,
-		.bw_b = NL80211_CHAN_WIDTH_20,
-		.expected_result = true,
+		.chandef_a = &chandef_5ghz_40mhz,
+		.chandef_b = &chandef_6ghz_20mhz,
+		.expected_result = 0,
 	},
 	{
 		.desc = "Different bandwidths (4x ratio), primary link load permits EMLSR",
 		.low_latency_vif = false,
 		.primary_link_active = true,
 		.chan_load_not_by_us = 45,
-		.bw_a = NL80211_CHAN_WIDTH_80,
-		.bw_b = NL80211_CHAN_WIDTH_20,
-		.expected_result = true,
+		.chandef_a = &chandef_5ghz_80mhz,
+		.chandef_b = &chandef_6ghz_20mhz,
+		.expected_result = 0,
 	},
 	{
 		.desc = "Different bandwidths (16x ratio), primary link load insufficient",
 		.low_latency_vif = false,
 		.primary_link_active = true,
 		.chan_load_not_by_us = 45,
-		.bw_a = NL80211_CHAN_WIDTH_320,
-		.bw_b = NL80211_CHAN_WIDTH_20,
-		.expected_result = false,
+		.chandef_a = &chandef_6ghz_320mhz,
+		.chandef_b = &chandef_5ghz_20mhz,
+		.expected_result = IWL_MLD_EMLSR_EXIT_CHAN_LOAD,
+	},
+	{
+		.desc = "Same band not allowed (2.4 GHz)",
+		.low_latency_vif = false,
+		.primary_link_active = true,
+		.chan_load_not_by_us = 30,
+		.chandef_a = &chandef_2ghz_20mhz,
+		.chandef_b = &chandef_2ghz_11_20mhz,
+		.expected_result = IWL_MLD_EMLSR_EXIT_EQUAL_BAND,
+	},
+	{
+		.desc = "Same band not allowed (5 GHz)",
+		.low_latency_vif = false,
+		.primary_link_active = true,
+		.chan_load_not_by_us = 30,
+		.chandef_a = &chandef_5ghz_40mhz,
+		.chandef_b = &chandef_5ghz_40mhz,
+		.expected_result = IWL_MLD_EMLSR_EXIT_EQUAL_BAND,
+	},
+	{
+		.desc = "Same band allowed (5 GHz separated)",
+		.low_latency_vif = false,
+		.primary_link_active = true,
+		.chan_load_not_by_us = 30,
+		.chandef_a = &chandef_5ghz_40mhz,
+		.chandef_b = &chandef_5ghz_120_40mhz,
+		.expected_result = 0,
+	},
+	{
+		.desc = "Same band not allowed (6 GHz)",
+		.low_latency_vif = false,
+		.primary_link_active = true,
+		.chan_load_not_by_us = 30,
+		.chandef_a = &chandef_6ghz_160mhz,
+		.chandef_b = &chandef_6ghz_221_160mhz,
+		.expected_result = IWL_MLD_EMLSR_EXIT_EQUAL_BAND,
 	},
 };
 
-KUNIT_ARRAY_PARAM_DESC(channel_load, channel_load_cases, desc);
+KUNIT_ARRAY_PARAM_DESC(link_pair, link_pair_cases, desc);
 
-static void test_iwl_mld_channel_load_allows_emlsr(struct kunit *test)
+static void test_iwl_mld_link_pair_allows_emlsr(struct kunit *test)
 {
-	const struct channel_load_case *params = test->param_value;
+	const struct link_pair_case *params = test->param_value;
 	struct iwl_mld *mld = test->priv;
 	struct ieee80211_vif *vif;
-	struct cfg80211_chan_def chandef_a, chandef_b;
-	struct iwl_mld_link_sel_data a = {.chandef = &chandef_a,
-					  .link_id = 4};
-	struct iwl_mld_link_sel_data b = {.chandef = &chandef_b,
-					  .link_id = 5};
+	struct ieee80211_bss_conf *link;
+	/* link A is the primary and link B is the secondary */
+	struct iwl_mld_link_sel_data a = {
+		.chandef = params->chandef_a,
+		.link_id = 4,
+	};
+	struct iwl_mld_link_sel_data b = {
+		.chandef = params->chandef_b,
+		.link_id = 5,
+	};
 	struct iwl_mld_kunit_link assoc_link = {
+		.chandef = params->primary_link_active ? a.chandef : b.chandef,
 		.id = params->primary_link_active ? a.link_id : b.link_id,
-		.bandwidth = params->primary_link_active ? params->bw_a : params->bw_b,
 	};
-	bool result;
+	u32 result;
 
 	vif = iwlmld_kunit_setup_mlo_assoc(BIT(a.link_id) | BIT(b.link_id),
 					   &assoc_link);
 
-	chandef_a.width = params->bw_a;
-	chandef_b.width = params->bw_b;
-
 	if (params->low_latency_vif)
 		iwl_mld_vif_from_mac80211(vif)->low_latency_causes = 1;
 
 	wiphy_lock(mld->wiphy);
 
+	link = wiphy_dereference(mld->wiphy, vif->link_conf[a.link_id]);
+	KUNIT_ALLOC_AND_ASSERT(test, link->bss);
+	link = wiphy_dereference(mld->wiphy, vif->link_conf[b.link_id]);
+	KUNIT_ALLOC_AND_ASSERT(test, link->bss);
+
 	/* Simulate channel load */
 	if (params->primary_link_active) {
 		struct iwl_mld_phy *phy =
@@ -282,22 +324,22 @@ static void test_iwl_mld_channel_load_allows_emlsr(struct kunit *test)
 		phy->avg_channel_load_not_by_us = params->chan_load_not_by_us;
 	}
 
-	result = iwl_mld_channel_load_allows_emlsr(mld, vif, &a, &b);
+	result = iwl_mld_emlsr_pair_state(vif, &a, &b);
 
 	wiphy_unlock(mld->wiphy);
 
 	KUNIT_EXPECT_EQ(test, result, params->expected_result);
 }
 
-static struct kunit_case channel_load_criteria_test_cases[] = {
-	KUNIT_CASE_PARAM(test_iwl_mld_channel_load_allows_emlsr, channel_load_gen_params),
+static struct kunit_case link_pair_criteria_test_cases[] = {
+	KUNIT_CASE_PARAM(test_iwl_mld_link_pair_allows_emlsr, link_pair_gen_params),
 	{}
 };
 
-static struct kunit_suite channel_load_criteria_tests = {
-	.name = "iwlmld_channel_load_allows_emlsr",
-	.test_cases = channel_load_criteria_test_cases,
+static struct kunit_suite link_pair_criteria_tests = {
+	.name = "iwlmld_link_pair_allows_emlsr",
+	.test_cases = link_pair_criteria_test_cases,
 	.init = iwlmld_kunit_test_init,
 };
 
-kunit_test_suite(channel_load_criteria_tests);
+kunit_test_suite(link_pair_criteria_tests);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/link.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/link.c
index 4a4eaa134bd3..69a0d67858bf 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/link.c
@@ -63,11 +63,11 @@ static void test_missed_beacon(struct kunit *test)
 	struct iwl_rx_packet *pkt;
 	struct iwl_mld_kunit_link link1 = {
 		.id = 0,
-		.band = NL80211_BAND_6GHZ,
+		.chandef = &chandef_6ghz_160mhz,
 	};
 	struct iwl_mld_kunit_link link2 = {
 		.id = 1,
-		.band = NL80211_BAND_5GHZ,
+		.chandef = &chandef_5ghz_80mhz,
 	};
 
 	kunit_activate_static_stub(test, ieee80211_connection_loss,
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
index 9712ee696509..26cf27be762d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
@@ -24,7 +24,7 @@ int iwlmld_kunit_test_init(struct kunit *test)
 {
 	struct iwl_mld *mld;
 	struct iwl_trans *trans;
-	const struct iwl_cfg *cfg;
+	const struct iwl_rf_cfg *cfg;
 	struct iwl_fw *fw;
 	struct ieee80211_hw *hw;
 
@@ -146,7 +146,7 @@ iwlmld_kunit_add_link(struct ieee80211_vif *vif, int link_id)
 }
 
 struct ieee80211_chanctx_conf *
-iwlmld_kunit_add_chanctx_from_def(struct cfg80211_chan_def *def)
+iwlmld_kunit_add_chanctx(const struct cfg80211_chan_def *def)
 {
 	struct kunit *test = kunit_get_current_test();
 	struct iwl_mld *mld = test->priv;
@@ -346,8 +346,7 @@ iwlmld_kunit_setup_assoc(bool mlo, struct iwl_mld_kunit_link *assoc_link)
 	else
 		link = &vif->bss_conf;
 
-	chan_ctx = iwlmld_kunit_add_chanctx(assoc_link->band,
-					    assoc_link->bandwidth);
+	chan_ctx = iwlmld_kunit_add_chanctx(assoc_link->chandef);
 
 	wiphy_lock(mld->wiphy);
 	iwlmld_kunit_assign_chanctx_to_link(vif, link, chan_ctx);
@@ -428,7 +427,7 @@ struct ieee80211_vif *iwlmld_kunit_assoc_emlsr(struct iwl_mld_kunit_link *link1,
 	link = wiphy_dereference(mld->wiphy, vif->link_conf[link2->id]);
 	KUNIT_EXPECT_NOT_NULL(test, link);
 
-	chan_ctx = iwlmld_kunit_add_chanctx(link2->band, link2->bandwidth);
+	chan_ctx = iwlmld_kunit_add_chanctx(link2->chandef);
 	iwlmld_kunit_assign_chanctx_to_link(vif, link, chan_ctx);
 
 	wiphy_unlock(mld->wiphy);
@@ -472,3 +471,33 @@ struct iwl_mld_phy *iwlmld_kunit_get_phy_of_link(struct ieee80211_vif *vif,
 
 	return iwl_mld_phy_from_mac80211(chanctx);
 }
+
+static const struct chandef_case {
+	const char *desc;
+	const struct cfg80211_chan_def *chandef;
+} chandef_cases[] = {
+#define CHANDEF(c, ...) { .desc = "chandef " #c " valid", .chandef = &c, },
+	CHANDEF_LIST
+#undef CHANDEF
+};
+
+KUNIT_ARRAY_PARAM_DESC(chandef, chandef_cases, desc);
+
+static void test_iwl_mld_chandef_valid(struct kunit *test)
+{
+	const struct chandef_case *params = test->param_value;
+
+	KUNIT_EXPECT_EQ(test, true, cfg80211_chandef_valid(params->chandef));
+}
+
+static struct kunit_case chandef_test_cases[] = {
+	KUNIT_CASE_PARAM(test_iwl_mld_chandef_valid, chandef_gen_params),
+	{}
+};
+
+static struct kunit_suite chandef_tests = {
+	.name = "iwlmld_valid_test_chandefs",
+	.test_cases = chandef_test_cases,
+};
+
+kunit_test_suite(chandef_tests);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
index d3723653cf1b..edf8eef4e81a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
@@ -14,9 +14,8 @@ struct iwl_mld;
 int iwlmld_kunit_test_init(struct kunit *test);
 
 struct iwl_mld_kunit_link {
+	const struct cfg80211_chan_def *chandef;
 	u8 id;
-	enum nl80211_band band;
-	enum nl80211_chan_width bandwidth;
 };
 
 enum nl80211_iftype;
@@ -42,50 +41,57 @@ static struct ieee80211_channel _name = {			\
 	.hw_value = (_freq),					\
 }
 
-#define CHANDEF(_name, _channel, _freq1, _width)		\
-__maybe_unused static struct cfg80211_chan_def _name = {	\
-	.chan = &(_channel),					\
-	.center_freq1 = (_freq1),				\
-	.width = (_width),					\
-}
-
 CHANNEL(chan_2ghz, NL80211_BAND_2GHZ, 2412);
+CHANNEL(chan_2ghz_11, NL80211_BAND_2GHZ, 2462);
 CHANNEL(chan_5ghz, NL80211_BAND_5GHZ, 5200);
+CHANNEL(chan_5ghz_120, NL80211_BAND_5GHZ, 5600);
 CHANNEL(chan_6ghz, NL80211_BAND_6GHZ, 6115);
+CHANNEL(chan_6ghz_221, NL80211_BAND_6GHZ, 7055);
 /* Feel free to add more */
+#undef CHANNEL
+
+#define CHANDEF_LIST \
+	CHANDEF(chandef_2ghz_20mhz, chan_2ghz, 2412,		\
+		NL80211_CHAN_WIDTH_20)				\
+	CHANDEF(chandef_2ghz_40mhz, chan_2ghz, 2422,		\
+		NL80211_CHAN_WIDTH_40)				\
+	CHANDEF(chandef_2ghz_11_20mhz, chan_2ghz_11, 2462,	\
+		NL80211_CHAN_WIDTH_20)				\
+	CHANDEF(chandef_5ghz_20mhz, chan_5ghz, 5200,		\
+		NL80211_CHAN_WIDTH_20)				\
+	CHANDEF(chandef_5ghz_40mhz, chan_5ghz, 5210,		\
+		NL80211_CHAN_WIDTH_40)				\
+	CHANDEF(chandef_5ghz_80mhz, chan_5ghz, 5210,		\
+		NL80211_CHAN_WIDTH_80)				\
+	CHANDEF(chandef_5ghz_160mhz, chan_5ghz, 5250,		\
+		NL80211_CHAN_WIDTH_160)				\
+	CHANDEF(chandef_5ghz_120_40mhz, chan_5ghz_120, 5610,	\
+		NL80211_CHAN_WIDTH_40)				\
+	CHANDEF(chandef_6ghz_20mhz, chan_6ghz, 6115,		\
+		NL80211_CHAN_WIDTH_20)				\
+	CHANDEF(chandef_6ghz_40mhz, chan_6ghz, 6125,		\
+		NL80211_CHAN_WIDTH_40)				\
+	CHANDEF(chandef_6ghz_80mhz, chan_6ghz, 6145,		\
+		NL80211_CHAN_WIDTH_80)				\
+	CHANDEF(chandef_6ghz_160mhz, chan_6ghz, 6185,		\
+		NL80211_CHAN_WIDTH_160)				\
+	CHANDEF(chandef_6ghz_320mhz, chan_6ghz, 6105,		\
+		NL80211_CHAN_WIDTH_320)				\
+	CHANDEF(chandef_6ghz_221_160mhz, chan_6ghz_221, 6985,	\
+		NL80211_CHAN_WIDTH_160)				\
+	/* Feel free to add more */
 
-CHANDEF(chandef_2ghz, chan_2ghz, 2412, NL80211_CHAN_WIDTH_20);
-CHANDEF(chandef_5ghz, chan_5ghz, 5200, NL80211_CHAN_WIDTH_40);
-CHANDEF(chandef_6ghz, chan_6ghz, 6115, NL80211_CHAN_WIDTH_160);
-/* Feel free to add more */
-
-//struct cfg80211_chan_def;
+#define CHANDEF(_name, _channel, _freq1, _width)		\
+__maybe_unused static const struct cfg80211_chan_def _name = {	\
+	.chan = &(_channel),					\
+	.center_freq1 = (_freq1),				\
+	.width = (_width),					\
+};
+CHANDEF_LIST
+#undef CHANDEF
 
 struct ieee80211_chanctx_conf *
-iwlmld_kunit_add_chanctx_from_def(struct cfg80211_chan_def *def);
-
-static inline struct ieee80211_chanctx_conf *
-iwlmld_kunit_add_chanctx(enum nl80211_band band, enum nl80211_chan_width width)
-{
-	struct cfg80211_chan_def chandef;
-
-	switch (band) {
-	case NL80211_BAND_2GHZ:
-		chandef = chandef_2ghz;
-		break;
-	case NL80211_BAND_5GHZ:
-		chandef = chandef_5ghz;
-		break;
-	default:
-	case NL80211_BAND_6GHZ:
-		chandef = chandef_6ghz;
-		break;
-	}
-
-	chandef.width = width;
-
-	return iwlmld_kunit_add_chanctx_from_def(&chandef);
-}
+iwlmld_kunit_add_chanctx(const struct cfg80211_chan_def *def);
 
 void iwlmld_kunit_assign_chanctx_to_link(struct ieee80211_vif *vif,
 					 struct ieee80211_bss_conf *link,
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/thermal.c b/drivers/net/wireless/intel/iwlwifi/mld/thermal.c
index 1909953a9be9..f8a8c35066be 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/thermal.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/thermal.c
@@ -13,6 +13,9 @@
 #include "mld.h"
 #include "hcmd.h"
 
+#define IWL_MLD_NUM_CTDP_STEPS		20
+#define IWL_MLD_MIN_CTDP_BUDGET_MW	150
+
 #define IWL_MLD_CT_KILL_DURATION (5 * HZ)
 
 void iwl_mld_handle_ct_kill_notif(struct iwl_mld *mld,
@@ -116,8 +119,8 @@ free_resp:
 
 static int compare_temps(const void *a, const void *b)
 {
-	return ((s16)le16_to_cpu(*(__le16 *)a) -
-		(s16)le16_to_cpu(*(__le16 *)b));
+	return ((s16)le16_to_cpu(*(const __le16 *)a) -
+		(s16)le16_to_cpu(*(const __le16 *)b));
 }
 
 struct iwl_trip_walk_data {
@@ -272,43 +275,27 @@ static void iwl_mld_thermal_zone_register(struct iwl_mld *mld)
 	}
 }
 
-/* budget in mWatt */
-static const u32 iwl_mld_cdev_budgets[] = {
-	2400,	/* cooling state 0 */
-	2000,	/* cooling state 1 */
-	1800,	/* cooling state 2 */
-	1600,	/* cooling state 3 */
-	1400,	/* cooling state 4 */
-	1200,	/* cooling state 5 */
-	1000,	/* cooling state 6 */
-	900,	/* cooling state 7 */
-	800,	/* cooling state 8 */
-	700,	/* cooling state 9 */
-	650,	/* cooling state 10 */
-	600,	/* cooling state 11 */
-	550,	/* cooling state 12 */
-	500,	/* cooling state 13 */
-	450,	/* cooling state 14 */
-	400,	/* cooling state 15 */
-	350,	/* cooling state 16 */
-	300,	/* cooling state 17 */
-	250,	/* cooling state 18 */
-	200,	/* cooling state 19 */
-	150,	/* cooling state 20 */
-};
-
 int iwl_mld_config_ctdp(struct iwl_mld *mld, u32 state,
 			enum iwl_ctdp_cmd_operation op)
 {
 	struct iwl_ctdp_cmd cmd = {
 		.operation = cpu_to_le32(op),
-		.budget = cpu_to_le32(iwl_mld_cdev_budgets[state]),
 		.window_size = 0,
 	};
+	u32 budget;
 	int ret;
 
 	lockdep_assert_wiphy(mld->wiphy);
 
+	/* Do a linear scale from IWL_MLD_MIN_CTDP_BUDGET_MW to the configured
+	 * maximum in the predefined number of steps.
+	 */
+	budget = ((mld->power_budget_mw - IWL_MLD_MIN_CTDP_BUDGET_MW) *
+		  (IWL_MLD_NUM_CTDP_STEPS - 1 - state)) /
+		 (IWL_MLD_NUM_CTDP_STEPS - 1) +
+		 IWL_MLD_MIN_CTDP_BUDGET_MW;
+	cmd.budget = cpu_to_le32(budget);
+
 	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(PHY_OPS_GROUP, CTDP_CONFIG_CMD),
 				   &cmd);
 
@@ -326,7 +313,7 @@ int iwl_mld_config_ctdp(struct iwl_mld *mld, u32 state,
 static int iwl_mld_tcool_get_max_state(struct thermal_cooling_device *cdev,
 				       unsigned long *state)
 {
-	*state = ARRAY_SIZE(iwl_mld_cdev_budgets) - 1;
+	*state = IWL_MLD_NUM_CTDP_STEPS - 1;
 
 	return 0;
 }
@@ -354,7 +341,7 @@ static int iwl_mld_tcool_set_cur_state(struct thermal_cooling_device *cdev,
 		goto unlock;
 	}
 
-	if (new_state >= ARRAY_SIZE(iwl_mld_cdev_budgets)) {
+	if (new_state >= IWL_MLD_NUM_CTDP_STEPS) {
 		ret = -EINVAL;
 		goto unlock;
 	}
@@ -417,10 +404,50 @@ static void iwl_mld_cooling_device_unregister(struct iwl_mld *mld)
 }
 #endif /* CONFIG_THERMAL */
 
+static u32 iwl_mld_ctdp_get_max_budget(struct iwl_mld *mld)
+{
+	u64 bios_power_budget = 0;
+	u32 default_power_budget;
+
+	switch (CSR_HW_RFID_TYPE(mld->trans->info.hw_rf_id)) {
+	case IWL_CFG_RF_TYPE_GF:
+		/* dual-radio devices have a higher budget */
+		if (CSR_HW_RFID_IS_CDB(mld->trans->info.hw_rf_id))
+			default_power_budget = 5200;
+		else
+			default_power_budget = 2880;
+		break;
+	case IWL_CFG_RF_TYPE_FM:
+		default_power_budget = 3450;
+		break;
+	case IWL_CFG_RF_TYPE_WH:
+	case IWL_CFG_RF_TYPE_PE:
+	default:
+		default_power_budget = 5550;
+		break;
+	}
+
+	iwl_bios_get_pwr_limit(&mld->fwrt, &bios_power_budget);
+
+	/* 32bit in UEFI, 16bit in ACPI; use BIOS value if it is in range */
+	if (bios_power_budget &&
+	    bios_power_budget != 0xffff && bios_power_budget != 0xffffffff &&
+	    bios_power_budget >= IWL_MLD_MIN_CTDP_BUDGET_MW &&
+	    bios_power_budget <= default_power_budget)
+		return (u32)bios_power_budget;
+
+	return default_power_budget;
+}
+
 void iwl_mld_thermal_initialize(struct iwl_mld *mld)
 {
+	lockdep_assert_not_held(&mld->wiphy->mtx);
+
 	wiphy_delayed_work_init(&mld->ct_kill_exit_wk, iwl_mld_exit_ctkill);
 
+	mld->power_budget_mw = iwl_mld_ctdp_get_max_budget(mld);
+	IWL_DEBUG_TEMP(mld, "cTDP power budget: %d mW\n", mld->power_budget_mw);
+
 #ifdef CONFIG_THERMAL
 	iwl_mld_cooling_device_register(mld);
 	iwl_mld_thermal_zone_register(mld);
@@ -429,7 +456,9 @@ void iwl_mld_thermal_initialize(struct iwl_mld *mld)
 
 void iwl_mld_thermal_exit(struct iwl_mld *mld)
 {
+	wiphy_lock(mld->wiphy);
 	wiphy_delayed_work_cancel(mld->wiphy, &mld->ct_kill_exit_wk);
+	wiphy_unlock(mld->wiphy);
 
 #ifdef CONFIG_THERMAL
 	iwl_mld_cooling_device_unregister(mld);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tlc.c b/drivers/net/wireless/intel/iwlwifi/mld/tlc.c
index f054cc921d9d..a9ca92c0455e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tlc.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tlc.c
@@ -44,7 +44,7 @@ iwl_mld_get_tlc_cmd_flags(struct iwl_mld *mld,
 	u16 flags = 0;
 
 	/* STBC flags */
-	if (mld->cfg->ht_params->stbc &&
+	if (mld->cfg->ht_params.stbc &&
 	    (hweight8(iwl_mld_get_valid_tx_ant(mld)) > 1)) {
 		if (he_cap->has_he && he_cap->he_cap_elem.phy_cap_info[2] &
 				      IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ)
@@ -56,7 +56,7 @@ iwl_mld_get_tlc_cmd_flags(struct iwl_mld *mld,
 	}
 
 	/* LDPC */
-	if (mld->cfg->ht_params->ldpc &&
+	if (mld->cfg->ht_params.ldpc &&
 	    ((ht_cap->cap & IEEE80211_HT_CAP_LDPC_CODING) ||
 	     (has_vht && (vht_cap->cap & IEEE80211_VHT_CAP_RXLDPC))))
 		flags |= IWL_TLC_MNG_CFG_FLAGS_LDPC_MSK;
@@ -658,7 +658,9 @@ void iwl_mld_handle_tlc_notif(struct iwl_mld *mld,
 		if (WARN_ON(!mld_link_sta))
 			return;
 
-		mld_link_sta->last_rate_n_flags = le32_to_cpu(notif->rate);
+		mld_link_sta->last_rate_n_flags =
+			iwl_v3_rate_from_v2_v3(notif->rate,
+					       mld->fw_rates_ver_3);
 
 		rs_pretty_print_rate(pretty_rate, sizeof(pretty_rate),
 				     mld_link_sta->last_rate_n_flags);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tx.c b/drivers/net/wireless/intel/iwlwifi/mld/tx.c
index 543abe72e465..3b4b575aadaa 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tx.c
@@ -76,14 +76,14 @@ static int iwl_mld_allocate_txq(struct iwl_mld *mld, struct ieee80211_txq *txq)
 	 */
 	unsigned int watchdog_timeout = txq->vif->type == NL80211_IFTYPE_AP ?
 				IWL_WATCHDOG_DISABLED :
-				mld->trans->trans_cfg->base_params->wd_timeout;
+				mld->trans->mac_cfg->base->wd_timeout;
 	int queue, size;
 
 	lockdep_assert_wiphy(mld->wiphy);
 
 	if (tid == IWL_MGMT_TID)
 		size = max_t(u32, IWL_MGMT_QUEUE_SIZE,
-			     mld->trans->cfg->min_txq_size);
+			     mld->trans->mac_cfg->base->min_txq_size);
 	else
 		size = iwl_mld_get_queue_size(mld, txq);
 
@@ -391,9 +391,9 @@ static u32 iwl_mld_mac80211_rate_idx_to_fw(struct iwl_mld *mld,
 
 	/* Set CCK or OFDM flag */
 	if (rate_idx <= IWL_LAST_CCK_RATE)
-		rate_flags |= RATE_MCS_CCK_MSK;
+		rate_flags |= RATE_MCS_MOD_TYPE_CCK;
 	else
-		rate_flags |= RATE_MCS_LEGACY_OFDM_MSK;
+		rate_flags |= RATE_MCS_MOD_TYPE_LEGACY_OFDM;
 
 	/* Legacy rates are indexed:
 	 * 0 - 3 for CCK and 0 - 7 for OFDM
@@ -425,47 +425,40 @@ static u32 iwl_mld_get_inject_tx_rate(struct iwl_mld *mld,
 	struct ieee80211_tx_rate *rate = &info->control.rates[0];
 	u32 result;
 
-	/* we only care about legacy/HT/VHT so far, so we can
-	 * build in v1 and use iwl_new_rate_from_v1()
-	 * FIXME: in newer devices we only support the new rates, build
-	 * the rate_n_flags in the new format here instead of using v1 and
-	 * converting it.
-	 */
-
 	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
 		u8 mcs = ieee80211_rate_get_vht_mcs(rate);
 		u8 nss = ieee80211_rate_get_vht_nss(rate);
 
-		result = RATE_MCS_VHT_MSK_V1;
-		result |= u32_encode_bits(mcs, RATE_VHT_MCS_RATE_CODE_MSK);
+		result = RATE_MCS_MOD_TYPE_VHT;
+		result |= u32_encode_bits(mcs, RATE_MCS_CODE_MSK);
 		result |= u32_encode_bits(nss, RATE_MCS_NSS_MSK);
 
 		if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
-			result |= RATE_MCS_SGI_MSK_V1;
+			result |= RATE_MCS_SGI_MSK;
 
 		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-			result |= u32_encode_bits(1, RATE_MCS_CHAN_WIDTH_MSK_V1);
+			result |= RATE_MCS_CHAN_WIDTH_40;
 		else if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
-			result |= u32_encode_bits(2, RATE_MCS_CHAN_WIDTH_MSK_V1);
+			result |= RATE_MCS_CHAN_WIDTH_80;
 		else if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH)
-			result |= u32_encode_bits(3, RATE_MCS_CHAN_WIDTH_MSK_V1);
-
-		result = iwl_new_rate_from_v1(result);
+			result |= RATE_MCS_CHAN_WIDTH_160;
 	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
-		result = RATE_MCS_HT_MSK_V1;
-		result |= u32_encode_bits(rate->idx,
-					  RATE_HT_MCS_RATE_CODE_MSK_V1 |
-					  RATE_HT_MCS_NSS_MSK_V1);
+		/* only MCS 0-15 are supported */
+		u8 mcs = rate->idx & 7;
+		u8 nss = rate->idx > 7;
+
+		result = RATE_MCS_MOD_TYPE_HT;
+		result |= u32_encode_bits(mcs, RATE_MCS_CODE_MSK);
+		result |= u32_encode_bits(nss, RATE_MCS_NSS_MSK);
+
 		if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
-			result |= RATE_MCS_SGI_MSK_V1;
+			result |= RATE_MCS_SGI_MSK;
 		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-			result |= u32_encode_bits(1, RATE_MCS_CHAN_WIDTH_MSK_V1);
+			result |= RATE_MCS_CHAN_WIDTH_40;
 		if (info->flags & IEEE80211_TX_CTL_LDPC)
-			result |= RATE_MCS_LDPC_MSK_V1;
+			result |= RATE_MCS_LDPC_MSK;
 		if (u32_get_bits(info->flags, IEEE80211_TX_CTL_STBC))
 			result |= RATE_MCS_STBC_MSK;
-
-		result = iwl_new_rate_from_v1(result);
 	} else {
 		result = iwl_mld_mac80211_rate_idx_to_fw(mld, info, rate->idx);
 	}
@@ -479,19 +472,23 @@ static u32 iwl_mld_get_inject_tx_rate(struct iwl_mld *mld,
 	return result;
 }
 
-static u32 iwl_mld_get_tx_rate_n_flags(struct iwl_mld *mld,
-				       struct ieee80211_tx_info *info,
-				       struct ieee80211_sta *sta, __le16 fc)
+static __le32 iwl_mld_get_tx_rate_n_flags(struct iwl_mld *mld,
+					  struct ieee80211_tx_info *info,
+					  struct ieee80211_sta *sta, __le16 fc)
 {
+	u32 rate;
+
 	if (unlikely(info->control.flags & IEEE80211_TX_CTRL_RATE_INJECT))
-		return iwl_mld_get_inject_tx_rate(mld, info, sta, fc);
+		rate = iwl_mld_get_inject_tx_rate(mld, info, sta, fc);
+	else
+		rate = iwl_mld_mac80211_rate_idx_to_fw(mld, info, -1) |
+		       iwl_mld_get_tx_ant(mld, info, sta, fc);
 
-	return iwl_mld_mac80211_rate_idx_to_fw(mld, info, -1) |
-		iwl_mld_get_tx_ant(mld, info, sta, fc);
+	return iwl_v3_rate_to_v2_v3(rate, mld->fw_rates_ver_3);
 }
 
 static void
-iwl_mld_fill_tx_cmd_hdr(struct iwl_tx_cmd_gen3 *tx_cmd,
+iwl_mld_fill_tx_cmd_hdr(struct iwl_tx_cmd *tx_cmd,
 			struct sk_buff *skb, bool amsdu)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
@@ -537,11 +534,11 @@ iwl_mld_fill_tx_cmd(struct iwl_mld *mld, struct sk_buff *skb,
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	struct iwl_mld_sta *mld_sta = sta ? iwl_mld_sta_from_mac80211(sta) :
 					    NULL;
-	struct iwl_tx_cmd_gen3 *tx_cmd;
+	struct iwl_tx_cmd *tx_cmd;
 	bool amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
 		     (*ieee80211_get_qos_ctl(hdr) &
 		      IEEE80211_QOS_CTL_A_MSDU_PRESENT);
-	u32 rate_n_flags = 0;
+	__le32 rate_n_flags = 0;
 	u16 flags = 0;
 
 	dev_tx_cmd->hdr.cmd = TX_CMD;
@@ -576,7 +573,7 @@ iwl_mld_fill_tx_cmd(struct iwl_mld *mld, struct sk_buff *skb,
 
 	tx_cmd->flags = cpu_to_le16(flags);
 
-	tx_cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
+	tx_cmd->rate_n_flags = rate_n_flags;
 }
 
 /* Caller of this need to check that info->control.vif is not NULL */
@@ -641,16 +638,36 @@ iwl_mld_get_tx_queue_id(struct iwl_mld *mld, struct ieee80211_txq *txq,
 	case NL80211_IFTYPE_P2P_DEVICE:
 		mld_vif = iwl_mld_vif_from_mac80211(info->control.vif);
 
-		if (mld_vif->roc_activity == ROC_NUM_ACTIVITIES) {
-			IWL_DEBUG_DROP(mld, "Drop tx outside ROC\n");
+		if (mld_vif->roc_activity != ROC_ACTIVITY_P2P_DISC &&
+		    mld_vif->roc_activity != ROC_ACTIVITY_P2P_NEG) {
+			IWL_DEBUG_DROP(mld,
+				       "Drop tx outside ROC with activity %d\n",
+				       mld_vif->roc_activity);
 			return IWL_MLD_INVALID_DROP_TX;
 		}
 
 		WARN_ON(!ieee80211_is_mgmt(fc));
 
-		return mld_vif->deflink.aux_sta.queue_id;
+		return mld_vif->aux_sta.queue_id;
+	case NL80211_IFTYPE_MONITOR:
+		mld_vif = iwl_mld_vif_from_mac80211(info->control.vif);
+		return mld_vif->deflink.mon_sta.queue_id;
+	case NL80211_IFTYPE_STATION:
+		mld_vif = iwl_mld_vif_from_mac80211(info->control.vif);
+
+		if (!(info->flags & IEEE80211_TX_CTL_TX_OFFCHAN)) {
+			IWL_DEBUG_DROP(mld, "Drop tx not off-channel\n");
+			return IWL_MLD_INVALID_DROP_TX;
+		}
+
+		if (mld_vif->roc_activity != ROC_ACTIVITY_HOTSPOT) {
+			IWL_DEBUG_DROP(mld, "Drop tx outside ROC\n");
+			return IWL_MLD_INVALID_DROP_TX;
+		}
+
+		WARN_ON(!ieee80211_is_mgmt(fc));
+		return mld_vif->aux_sta.queue_id;
 	default:
-		/* TODO: consider monitor (task=monitor) */
 		WARN_ONCE(1, "Unsupported vif type\n");
 		break;
 	}
@@ -831,7 +848,7 @@ static int iwl_mld_tx_tso_segment(struct iwl_mld *mld, struct sk_buff *skb,
 	 *	1 more for the potential data in the header
 	 */
 	if ((num_subframes * 2 + skb_shinfo(skb)->nr_frags + 1) >
-	    mld->trans->max_skb_frags)
+	    mld->trans->info.max_skb_frags)
 		num_subframes = 1;
 
 	if (num_subframes > 1)
@@ -977,11 +994,14 @@ void iwl_mld_tx_from_txq(struct iwl_mld *mld, struct ieee80211_txq *txq)
 	rcu_read_unlock();
 }
 
-static void iwl_mld_hwrate_to_tx_rate(u32 rate_n_flags,
+static void iwl_mld_hwrate_to_tx_rate(struct iwl_mld *mld,
+				      __le32 rate_n_flags_fw,
 				      struct ieee80211_tx_info *info)
 {
 	enum nl80211_band band = info->band;
 	struct ieee80211_tx_rate *tx_rate = &info->status.rates[0];
+	u32 rate_n_flags = iwl_v3_rate_from_v2_v3(rate_n_flags_fw,
+						  mld->fw_rates_ver_3);
 	u32 sgi = rate_n_flags & RATE_MCS_SGI_MSK;
 	u32 chan_width = rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK;
 	u32 format = rate_n_flags & RATE_MCS_MOD_TYPE_MSK;
@@ -1006,18 +1026,19 @@ static void iwl_mld_hwrate_to_tx_rate(u32 rate_n_flags,
 	}
 
 	switch (format) {
-	case RATE_MCS_HT_MSK:
+	case RATE_MCS_MOD_TYPE_HT:
 		tx_rate->flags |= IEEE80211_TX_RC_MCS;
 		tx_rate->idx = RATE_HT_MCS_INDEX(rate_n_flags);
 		break;
-	case RATE_MCS_VHT_MSK:
+	case RATE_MCS_MOD_TYPE_VHT:
 		ieee80211_rate_set_vht(tx_rate,
 				       rate_n_flags & RATE_MCS_CODE_MSK,
-				       FIELD_GET(RATE_MCS_NSS_MSK,
-						 rate_n_flags) + 1);
+				       u32_get_bits(rate_n_flags,
+						    RATE_MCS_NSS_MSK) + 1);
 		tx_rate->flags |= IEEE80211_TX_RC_VHT_MCS;
 		break;
-	case RATE_MCS_HE_MSK:
+	case RATE_MCS_MOD_TYPE_HE:
+	case RATE_MCS_MOD_TYPE_EHT:
 		/* mac80211 cannot do this without ieee80211_tx_status_ext()
 		 * but it only matters for radiotap
 		 */
@@ -1111,8 +1132,7 @@ void iwl_mld_handle_tx_resp_notif(struct iwl_mld *mld,
 			iwl_dbg_tlv_time_point(&mld->fwrt, tp, NULL);
 		}
 
-		iwl_mld_hwrate_to_tx_rate(le32_to_cpu(tx_resp->initial_rate),
-					  info);
+		iwl_mld_hwrate_to_tx_rate(mld, tx_resp->initial_rate, info);
 
 		if (likely(!iwl_mld_time_sync_frame(mld, skb, hdr->addr1)))
 			ieee80211_tx_status_skb(mld->hw, skb);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
index 21641d41a958..13cdc077d8d3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2013-2014, 2018-2020, 2022-2024 Intel Corporation
+ * Copyright (C) 2013-2014, 2018-2020, 2022-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  */
 #include <linux/ieee80211.h>
@@ -181,7 +181,7 @@ static int iwl_mvm_bt_coex_reduced_txp(struct iwl_mvm *mvm, u8 sta_id,
 	struct iwl_mvm_sta *mvmsta;
 	u32 value;
 
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 		return 0;
 
 	mvmsta = iwl_mvm_sta_from_staid_protected(mvm, sta_id);
@@ -569,7 +569,7 @@ static void iwl_mvm_bt_coex_notif_handle(struct iwl_mvm *mvm)
 					mvm->hw, IEEE80211_IFACE_ITER_NORMAL,
 					iwl_mvm_bt_notif_iterator, &data);
 
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		rcu_read_unlock();
 		return;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 3e8b7168af01..507c03198c92 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -300,7 +300,7 @@ static void iwl_mvm_wowlan_get_rsc_tsc_data(struct ieee80211_hw *hw,
 
 			for (i = 0; i < IWL_MAX_TID_COUNT; i++) {
 				pn = iwl_mvm_find_max_pn(key, ptk_pn, &seq, i,
-						mvm->trans->num_rx_queues);
+						mvm->trans->info.num_rxqs);
 				aes_sc[i].pn = cpu_to_le64((u64)pn[5] |
 							   ((u64)pn[4] << 8) |
 							   ((u64)pn[3] << 16) |
@@ -421,7 +421,7 @@ static void iwl_mvm_wowlan_get_rsc_v5_data(struct ieee80211_hw *hw,
 
 			for (i = 0; i < IWL_MAX_TID_COUNT; i++) {
 				pn = iwl_mvm_find_max_pn(key, ptk_pn, &seq, i,
-						mvm->trans->num_rx_queues);
+						mvm->trans->info.num_rxqs);
 				rsc[i] = cpu_to_le64((u64)pn[5] |
 						     ((u64)pn[4] << 8) |
 						     ((u64)pn[3] << 16) |
@@ -1266,7 +1266,7 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 	};
 	struct iwl_host_cmd d3_cfg_cmd = {
 		.id = D3_CONFIG_CMD,
-		.flags = CMD_WANT_SKB | CMD_SEND_IN_D3,
+		.flags = CMD_WANT_SKB,
 		.data[0] = &d3_cfg_cmd_data,
 		.len[0] = sizeof(d3_cfg_cmd_data),
 	};
@@ -1370,11 +1370,9 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 	 * recording before entering D3. In later devices the FW stops the
 	 * recording automatically.
 	 */
-	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_9000)
+	if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_9000)
 		iwl_fw_dbg_stop_restart_recording(&mvm->fwrt, NULL, true);
 
-	mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_D3;
-
 	/* must be last -- this switches firmware state */
 	ret = iwl_mvm_send_cmd(mvm, &d3_cfg_cmd);
 	if (ret)
@@ -1686,7 +1684,7 @@ static void iwl_mvm_set_aes_ptk_rx_seq(struct iwl_mvm *mvm,
 	for (tid = 0; tid < IWL_MAX_TID_COUNT; tid++) {
 		int i;
 
-		for (i = 1; i < mvm->trans->num_rx_queues; i++)
+		for (i = 1; i < mvm->trans->info.num_rxqs; i++)
 			memcpy(ptk_pn->q[i].pn[tid],
 			       status->ptk.aes.seq[tid].ccmp.pn,
 			       IEEE80211_CCMP_PN_LEN);
@@ -2825,7 +2823,7 @@ static bool iwl_mvm_query_wakeup_reasons(struct iwl_mvm *mvm,
 				status->qos_seq_ctr[i] + 0x10;
 	}
 
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
 		i = mvm->offload_tid;
 		iwl_trans_set_q_ptrs(mvm->trans,
 				     mvm_ap_sta->tid_data[i].txq_id,
@@ -3407,9 +3405,9 @@ static int iwl_mvm_resume_firmware(struct iwl_mvm *mvm, bool test)
 	int ret;
 	enum iwl_d3_status d3_status;
 	struct iwl_host_cmd cmd = {
-			.id = D0I3_END_CMD,
-			.flags = CMD_WANT_SKB | CMD_SEND_IN_D3,
-		};
+		.id = D0I3_END_CMD,
+		.flags = CMD_WANT_SKB,
+	};
 	bool reset = fw_has_capa(&mvm->fw->ucode_capa,
 				 IWL_UCODE_TLV_CAPA_CNSLDTD_D3_D0_IMG);
 
@@ -3427,7 +3425,7 @@ static int iwl_mvm_resume_firmware(struct iwl_mvm *mvm, bool test)
 	 * AX210 and above don't need the command since they have
 	 * the doorbell interrupt.
 	 */
-	if (mvm->trans->trans_cfg->device_family <= IWL_DEVICE_FAMILY_22000 &&
+	if (mvm->trans->mac_cfg->device_family <= IWL_DEVICE_FAMILY_22000 &&
 	    fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_D0I3_END_FIRST)) {
 		ret = iwl_mvm_send_cmd(mvm, &cmd);
 		if (ret < 0)
@@ -3564,9 +3562,6 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test)
 
 	iwl_mvm_unblock_esr(mvm, vif, IWL_MVM_ESR_BLOCKED_WOWLAN);
 
-	/* after the successful handshake, we're out of D3 */
-	mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
-
 	/* when reset is required we can't send these following commands */
 	if (d3_data.d3_end_flags & IWL_D0I3_RESET_REQUIRE)
 		goto query_wakeup_reasons;
@@ -3639,9 +3634,6 @@ out:
 	 */
 	set_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status);
 
-	/* regardless of what happened, we're now out of D3 */
-	mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
-
 	return 1;
 }
 
@@ -3679,8 +3671,7 @@ void iwl_mvm_fast_suspend(struct iwl_mvm *mvm)
 	set_bit(IWL_MVM_STATUS_IN_D3, &mvm->status);
 
 	WARN_ON(iwl_mvm_power_update_device(mvm));
-	mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_D3;
-	ret = iwl_mvm_send_cmd_pdu(mvm, D3_CONFIG_CMD, CMD_SEND_IN_D3,
+	ret = iwl_mvm_send_cmd_pdu(mvm, D3_CONFIG_CMD, 0,
 				   sizeof(d3_cfg_cmd_data), &d3_cfg_cmd_data);
 	if (ret)
 		IWL_ERR(mvm,
@@ -3735,7 +3726,6 @@ int iwl_mvm_fast_resume(struct iwl_mvm *mvm)
 
 out:
 	clear_bit(IWL_MVM_STATUS_IN_D3, &mvm->status);
-	mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
 	mvm->fast_resume = false;
 
 	return ret;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 671d3f8d79c1..86a87ea89916 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1277,7 +1277,7 @@ static ssize_t iwl_dbgfs_inject_packet_write(struct iwl_mvm *mvm,
 		return -EIO;
 
 	/* supporting only MQ RX */
-	if (!mvm->trans->trans_cfg->mq_rx_supported)
+	if (!mvm->trans->mac_cfg->mq_rx_supported)
 		return -EOPNOTSUPP;
 
 	rxb._page = alloc_pages(GFP_ATOMIC, 0);
@@ -1468,7 +1468,7 @@ static ssize_t iwl_dbgfs_fw_dbg_clear_write(struct iwl_mvm *mvm,
 					    char *buf, size_t count,
 					    loff_t *ppos)
 {
-	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_9000)
+	if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_9000)
 		return -EOPNOTSUPP;
 
 	/*
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 2b5a62604fc4..819e3228462a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -29,8 +29,8 @@
 #define MVM_UCODE_CALIB_TIMEOUT	(2 * HZ)
 
 struct iwl_mvm_alive_data {
+	__le32 sku_id[3];
 	bool valid;
-	u32 scd_base_addr;
 };
 
 static int iwl_send_tx_ant_cfg(struct iwl_mvm *mvm, u8 valid_tx_ant)
@@ -57,13 +57,13 @@ static int iwl_send_rss_cfg_cmd(struct iwl_mvm *mvm)
 			     BIT(IWL_RSS_HASH_TYPE_IPV6_PAYLOAD),
 	};
 
-	if (mvm->trans->num_rx_queues == 1)
+	if (mvm->trans->info.num_rxqs == 1)
 		return 0;
 
 	/* Do not direct RSS traffic to Q 0 which is our fallback queue */
 	for (i = 0; i < ARRAY_SIZE(cmd.indirection_table); i++)
 		cmd.indirection_table[i] =
-			1 + (i % (mvm->trans->num_rx_queues - 1));
+			1 + (i % (mvm->trans->info.num_rxqs - 1));
 	netdev_rss_key_fill(cmd.secret_key, sizeof(cmd.secret_key));
 
 	return iwl_mvm_send_cmd_pdu(mvm, RSS_CONFIG_CMD, 0, sizeof(cmd), &cmd);
@@ -114,7 +114,7 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 	u32 i;
 
 
-	if (version == 6) {
+	if (version >= 6) {
 		struct iwl_alive_ntf_v6 *palive;
 
 		if (pkt_len < sizeof(*palive))
@@ -157,6 +157,17 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 				}
 			}
 		}
+
+		if (version >= 8) {
+			const struct iwl_alive_ntf *palive_v8 =
+				(void *)pkt->data;
+
+			if (pkt_len < sizeof(*palive_v8))
+				return false;
+
+			IWL_DEBUG_FW(mvm, "platform id: 0x%llx\n",
+				     palive_v8->platform_id);
+		}
 	}
 
 	if (version >= 5) {
@@ -171,14 +182,15 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 		lmac2 = &palive->lmac_data[1];
 		status = le16_to_cpu(palive->status);
 
-		mvm->trans->sku_id[0] = le32_to_cpu(palive->sku_id.data[0]);
-		mvm->trans->sku_id[1] = le32_to_cpu(palive->sku_id.data[1]);
-		mvm->trans->sku_id[2] = le32_to_cpu(palive->sku_id.data[2]);
+		BUILD_BUG_ON(sizeof(palive->sku_id.data) !=
+			     sizeof(alive_data->sku_id));
+		memcpy(alive_data->sku_id, palive->sku_id.data,
+		       sizeof(palive->sku_id.data));
 
 		IWL_DEBUG_FW(mvm, "Got sku_id: 0x0%x 0x0%x 0x0%x\n",
-			     mvm->trans->sku_id[0],
-			     mvm->trans->sku_id[1],
-			     mvm->trans->sku_id[2]);
+			     le32_to_cpu(alive_data->sku_id[0]),
+			     le32_to_cpu(alive_data->sku_id[1]),
+			     le32_to_cpu(alive_data->sku_id[2]));
 	} else if (iwl_rx_packet_payload_len(pkt) == sizeof(struct iwl_alive_ntf_v4)) {
 		struct iwl_alive_ntf_v4 *palive;
 
@@ -221,7 +233,7 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 
 	if (umac_error_table) {
 		if (umac_error_table >=
-		    mvm->trans->cfg->min_umac_error_event_table) {
+		    mvm->trans->mac_cfg->base->min_umac_error_event_table) {
 			iwl_fw_umac_set_alive_err_table(mvm->trans,
 							umac_error_table);
 		} else {
@@ -233,7 +245,6 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 		}
 	}
 
-	alive_data->scd_base_addr = le32_to_cpu(lmac1->dbg_ptrs.scd_base_ptr);
 	alive_data->valid = status == IWL_ALIVE_STATUS_OK;
 
 	IWL_DEBUG_FW(mvm,
@@ -282,7 +293,7 @@ static void iwl_mvm_print_pd_notification(struct iwl_mvm *mvm)
 	IWL_ERR(mvm, #reg_name ": 0x%x\n", iwl_read_umac_prph(trans, reg_name))
 
 	struct iwl_trans *trans = mvm->trans;
-	enum iwl_device_family device_family = trans->trans_cfg->device_family;
+	enum iwl_device_family device_family = trans->mac_cfg->device_family;
 
 	if (device_family < IWL_DEVICE_FAMILY_8000)
 		return;
@@ -304,7 +315,6 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 {
 	struct iwl_notification_wait alive_wait;
 	struct iwl_mvm_alive_data alive_data = {};
-	const struct fw_img *fw;
 	int ret;
 	enum iwl_ucode_type old_type = mvm->fwrt.cur_fw_img;
 	static const u16 alive_cmd[] = { UCODE_ALIVE_NTFY };
@@ -317,11 +327,7 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	    iwl_fw_dbg_conf_usniffer(mvm->fw, FW_DBG_START_FROM_ALIVE) &&
 	    !(fw_has_capa(&mvm->fw->ucode_capa,
 			  IWL_UCODE_TLV_CAPA_USNIFFER_UNIFIED)))
-		fw = iwl_get_ucode_image(mvm->fw, IWL_UCODE_REGULAR_USNIFFER);
-	else
-		fw = iwl_get_ucode_image(mvm->fw, ucode_type);
-	if (WARN_ON(!fw))
-		return -EINVAL;
+		ucode_type = IWL_UCODE_REGULAR_USNIFFER;
 	iwl_fw_set_current_image(&mvm->fwrt, ucode_type);
 	clear_bit(IWL_MVM_STATUS_FIRMWARE_RUNNING, &mvm->status);
 
@@ -334,7 +340,8 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	 * For the unified firmware case, the ucode_type is not
 	 * INIT, but we still need to run it.
 	 */
-	ret = iwl_trans_start_fw(mvm->trans, fw, run_in_rfkill);
+	ret = iwl_trans_start_fw(mvm->trans, mvm->fw, ucode_type,
+				 run_in_rfkill);
 	if (ret) {
 		iwl_fw_set_current_image(&mvm->fwrt, old_type);
 		iwl_remove_notification(&mvm->notif_wait, &alive_wait);
@@ -348,7 +355,7 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	ret = iwl_wait_notification(&mvm->notif_wait, &alive_wait,
 				    MVM_UCODE_ALIVE_TIMEOUT);
 
-	if (mvm->trans->trans_cfg->device_family ==
+	if (mvm->trans->mac_cfg->device_family ==
 	    IWL_DEVICE_FAMILY_AX210) {
 		/* print these registers regardless of alive fail/success */
 		IWL_INFO(mvm, "WFPM_UMAC_PD_NOTIFICATION: 0x%x\n",
@@ -365,14 +372,14 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 		struct iwl_trans *trans = mvm->trans;
 
 		/* SecBoot info */
-		if (trans->trans_cfg->device_family >=
+		if (trans->mac_cfg->device_family >=
 					IWL_DEVICE_FAMILY_22000) {
 			IWL_ERR(mvm,
 				"SecBoot CPU1 Status: 0x%x, CPU2 Status: 0x%x\n",
 				iwl_read_umac_prph(trans, UMAG_SB_CPU_1_STATUS),
 				iwl_read_umac_prph(trans,
 						   UMAG_SB_CPU_2_STATUS));
-		} else if (trans->trans_cfg->device_family >=
+		} else if (trans->mac_cfg->device_family >=
 			   IWL_DEVICE_FAMILY_8000) {
 			IWL_ERR(mvm,
 				"SecBoot CPU1 Status: 0x%x, CPU2 Status: 0x%x\n",
@@ -383,7 +390,7 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 		iwl_mvm_print_pd_notification(mvm);
 
 		/* LMAC/UMAC PC info */
-		if (trans->trans_cfg->device_family >=
+		if (trans->mac_cfg->device_family >=
 					IWL_DEVICE_FAMILY_22000) {
 			pc_data = trans->dbg.pc_data;
 			for (count = 0; count < trans->dbg.num_pc;
@@ -391,7 +398,7 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 				IWL_ERR(mvm, "%s: 0x%x\n",
 					pc_data->pc_name,
 					pc_data->pc_address);
-		} else if (trans->trans_cfg->device_family >=
+		} else if (trans->mac_cfg->device_family >=
 					IWL_DEVICE_FAMILY_9000) {
 			IWL_ERR(mvm, "UMAC PC: 0x%x\n",
 				iwl_read_umac_prph(trans,
@@ -422,10 +429,10 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	/* if reached this point, Alive notification was received */
 	iwl_mei_alive_notif(true);
 
-	iwl_trans_fw_alive(mvm->trans, alive_data.scd_base_addr);
+	iwl_trans_fw_alive(mvm->trans);
 
 	ret = iwl_pnvm_load(mvm->trans, &mvm->notif_wait,
-			    &mvm->fw->ucode_capa);
+			    &mvm->fw->ucode_capa, alive_data.sku_id);
 	if (ret) {
 		IWL_ERR(mvm, "Timeout waiting for PNVM load!\n");
 		iwl_fw_set_current_image(&mvm->fwrt, old_type);
@@ -473,7 +480,7 @@ static void iwl_mvm_phy_filter_init(struct iwl_mvm *mvm,
 				    struct iwl_phy_specific_cfg *phy_filters)
 {
 #ifdef CONFIG_ACPI
-	*phy_filters = mvm->phy_filters;
+	*phy_filters = mvm->fwrt.phy_filters;
 #endif /* CONFIG_ACPI */
 }
 
@@ -490,7 +497,7 @@ static void iwl_mvm_uats_init(struct iwl_mvm *mvm)
 		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
 	};
 
-	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210) {
+	if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210) {
 		IWL_DEBUG_RADIO(mvm, "UATS feature is not supported\n");
 		return;
 	}
@@ -504,11 +511,10 @@ static void iwl_mvm_uats_init(struct iwl_mvm *mvm)
 		return;
 	}
 
-	ret = iwl_uefi_get_uats_table(mvm->trans, &mvm->fwrt);
-	if (ret < 0) {
-		IWL_DEBUG_FW(mvm, "failed to read UATS table (%d)\n", ret);
+	iwl_uefi_get_uats_table(mvm->trans, &mvm->fwrt);
+
+	if (!mvm->fwrt.uats_valid)
 		return;
-	}
 
 	ret = iwl_mvm_send_cmd(mvm, &cmd);
 	if (ret < 0)
@@ -578,7 +584,7 @@ static int iwl_send_phy_cfg_cmd(struct iwl_mvm *mvm)
 
 	/* set flags extra PHY configuration flags from the device's cfg */
 	phy_cfg_cmd.phy_cfg |=
-		cpu_to_le32(mvm->trans->trans_cfg->extra_phy_cfg_flags);
+		cpu_to_le32(mvm->trans->mac_cfg->extra_phy_cfg_flags);
 
 	phy_cfg_cmd.calib_control.event_trigger =
 		mvm->fw->default_calib[ucode_type].event_trigger;
@@ -617,7 +623,7 @@ static int iwl_run_unified_mvm_ucode(struct iwl_mvm *mvm)
 
 	mvm->rfkill_safe_init_done = false;
 
-	if (mvm->trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210) {
+	if (mvm->trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_AX210) {
 		sb_cfg = iwl_read_umac_prph(mvm->trans, SB_MODIFY_CFG_FLAG);
 		/* if needed, we'll reset this on our way out later */
 		mvm->fw_product_reset = sb_cfg == SB_CFG_RESIDES_IN_ROM;
@@ -651,11 +657,6 @@ static int iwl_run_unified_mvm_ucode(struct iwl_mvm *mvm)
 	iwl_dbg_tlv_time_point(&mvm->fwrt, IWL_FW_INI_TIME_POINT_AFTER_ALIVE,
 			       NULL);
 
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
-		mvm->trans->step_urm = !!(iwl_read_umac_prph(mvm->trans,
-							     CNVI_PMU_STEP_FLOW) &
-						CNVI_PMU_STEP_FLOW_FORCE_URM);
-
 	/* Send init config command to mark that we are sending NVM access
 	 * commands
 	 */
@@ -756,7 +757,7 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm)
 		goto remove_notif;
 	}
 
-	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_8000) {
+	if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_8000) {
 		ret = iwl_mvm_send_bt_init_conf(mvm);
 		if (ret)
 			goto remove_notif;
@@ -1270,7 +1271,7 @@ void iwl_mvm_get_bios_tables(struct iwl_mvm *mvm)
 		}
 	}
 
-	iwl_acpi_get_phy_filters(&mvm->fwrt, &mvm->phy_filters);
+	iwl_acpi_get_phy_filters(&mvm->fwrt);
 
 	if (iwl_bios_get_eckv(&mvm->fwrt, &mvm->ext_clock_valid))
 		IWL_DEBUG_RADIO(mvm, "ECKV table doesn't exist in BIOS\n");
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/led.c b/drivers/net/wireless/intel/iwlwifi/mvm/led.c
index 1ea7c44250d4..c3cc1ea3ccc9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/led.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/led.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2019 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2019, 2025 Intel Corporation
  * Copyright (C) 2017 Intel Deutschland GmbH
  */
 #include <linux/leds.h>
@@ -102,7 +102,7 @@ void iwl_mvm_leds_sync(struct iwl_mvm *mvm)
 	 * if we control through the register, we're doing it
 	 * even when the firmware isn't up, so no need to sync
 	 */
-	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_8000)
+	if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_8000)
 		return;
 
 	iwl_mvm_led_set(mvm, mvm->led.brightness > 0);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index bec18d197f31..9098a36530cc 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -938,12 +938,19 @@ u8 iwl_mvm_mac_ctxt_get_lowest_rate(struct iwl_mvm *mvm,
 
 u16 iwl_mvm_mac_ctxt_get_beacon_flags(const struct iwl_fw *fw, u8 rate_idx)
 {
-	u16 flags = iwl_mvm_mac80211_idx_to_hwrate(fw, rate_idx);
 	bool is_new_rate = iwl_fw_lookup_cmd_ver(fw, BEACON_TEMPLATE_CMD, 0) > 10;
+	u16 flags, cck_flag;
 
-	if (rate_idx <= IWL_FIRST_CCK_RATE)
-		flags |= is_new_rate ? IWL_MAC_BEACON_CCK
-			  : IWL_MAC_BEACON_CCK_V1;
+	if (is_new_rate) {
+		flags = iwl_mvm_mac80211_idx_to_hwrate(fw, rate_idx);
+		cck_flag = IWL_MAC_BEACON_CCK;
+	} else {
+		cck_flag = IWL_MAC_BEACON_CCK_V1;
+		flags = iwl_fw_rate_idx_to_plcp(rate_idx);
+	}
+
+	if (rate_idx <= IWL_LAST_CCK_RATE)
+		flags |= cck_flag;
 
 	return flags;
 }
@@ -969,7 +976,7 @@ u8 iwl_mvm_mac_ctxt_get_beacon_rate(struct iwl_mvm *mvm,
 static void iwl_mvm_mac_ctxt_set_tx(struct iwl_mvm *mvm,
 				    struct ieee80211_vif *vif,
 				    struct sk_buff *beacon,
-				    struct iwl_tx_cmd *tx)
+				    struct iwl_tx_cmd_v6 *tx)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	struct ieee80211_tx_info *info;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 1e916a0ce082..0f056a6641bd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -146,7 +146,7 @@ struct ieee80211_regdomain *iwl_mvm_get_regdomain(struct wiphy *wiphy,
 					   MCC_UPDATE_CMD, 0);
 	IWL_DEBUG_LAR(mvm, "MCC update response version: %d\n", resp_ver);
 
-	regd = iwl_parse_nvm_mcc_info(mvm->trans->dev, mvm->cfg,
+	regd = iwl_parse_nvm_mcc_info(mvm->trans,
 				      __le32_to_cpu(resp->n_channels),
 				      resp->channels,
 				      __le16_to_cpu(resp->mcc),
@@ -311,8 +311,8 @@ int iwl_mvm_op_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
 	/* This has been tested on those devices only */
-	if (mvm->trans->trans_cfg->device_family != IWL_DEVICE_FAMILY_9000 &&
-	    mvm->trans->trans_cfg->device_family != IWL_DEVICE_FAMILY_22000)
+	if (mvm->trans->mac_cfg->device_family != IWL_DEVICE_FAMILY_9000 &&
+	    mvm->trans->mac_cfg->device_family != IWL_DEVICE_FAMILY_22000)
 		return -EOPNOTSUPP;
 
 	if (!mvm->nvm_data)
@@ -391,7 +391,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	 * for older devices. We also don't see this issue on any newer
 	 * devices.
 	 */
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_9000)
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_9000)
 		ieee80211_hw_set(hw, TX_AMSDU);
 	ieee80211_hw_set(hw, TX_FRAG_LIST);
 
@@ -402,7 +402,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 
 	/* We want to use the mac80211's reorder buffer for 9000 */
 	if (iwl_mvm_has_new_rx_api(mvm) &&
-	    mvm->trans->trans_cfg->device_family > IWL_DEVICE_FAMILY_9000)
+	    mvm->trans->mac_cfg->device_family > IWL_DEVICE_FAMILY_9000)
 		ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
 
 	if (fw_has_capa(&mvm->fw->ucode_capa,
@@ -417,10 +417,10 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 		return -EINVAL;
 	}
 
-	if (mvm->trans->num_rx_queues > 1)
+	if (mvm->trans->info.num_rxqs > 1)
 		ieee80211_hw_set(hw, USES_RSS);
 
-	if (mvm->trans->max_skb_frags)
+	if (mvm->trans->info.max_skb_frags)
 		hw->netdev_features = NETIF_F_HIGHDMA | NETIF_F_SG;
 
 	hw->queues = IEEE80211_NUM_ACS;
@@ -441,7 +441,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 
 	hw->uapsd_queues = IWL_MVM_UAPSD_QUEUES;
 	hw->uapsd_max_sp_len = IWL_UAPSD_MAX_SP;
-	hw->max_tx_fragments = mvm->trans->max_skb_frags;
+	hw->max_tx_fragments = mvm->trans->info.max_skb_frags;
 
 	BUILD_BUG_ON(ARRAY_SIZE(mvm->ciphers) < ARRAY_SIZE(mvm_ciphers) + 6);
 	memcpy(mvm->ciphers, mvm_ciphers, sizeof(mvm_ciphers));
@@ -544,7 +544,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 		hw->wiphy->regulatory_flags |= REGULATORY_CUSTOM_REG |
 					       REGULATORY_DISABLE_BEACON_HINTS;
 
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 		wiphy_ext_feature_set(hw->wiphy,
 				      NL80211_EXT_FEATURE_DFS_CONCURRENT);
 
@@ -610,7 +610,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 		hw->wiphy->bands[NL80211_BAND_6GHZ] =
 			&mvm->nvm_data->bands[NL80211_BAND_6GHZ];
 
-	hw->wiphy->hw_version = mvm->trans->hw_id;
+	hw->wiphy->hw_version = mvm->trans->info.hw_id;
 
 	if (iwlmvm_mod_params.power_scheme != IWL_POWER_SCHEME_CAM)
 		hw->wiphy->flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
@@ -731,8 +731,6 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 
 	mvm->rts_threshold = IEEE80211_MAX_RTS_THRESHOLD;
 
-	ieee80211_hw_set(hw, DISALLOW_PUNCTURING_5GHZ);
-
 #ifdef CONFIG_PM_SLEEP
 	if ((unified || mvm->fw->img[IWL_UCODE_WOWLAN].num_sec) &&
 	    device_can_wakeup(mvm->trans->dev)) {
@@ -771,7 +769,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 		hw->wiphy->features |= NL80211_FEATURE_TDLS_CHANNEL_SWITCH;
 	}
 
-	hw->netdev_features |= mvm->cfg->features;
+	hw->netdev_features |= mvm->trans->mac_cfg->base->features;
 	if (!iwl_mvm_is_csum_supported(mvm))
 		hw->netdev_features &= ~IWL_CSUM_NETIF_FLAGS_MASK;
 
@@ -1379,7 +1377,7 @@ void __iwl_mvm_mac_stop(struct iwl_mvm *mvm, bool suspend)
 		iwl_mvm_rm_aux_sta(mvm);
 
 	if (suspend &&
-	    mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
+	    mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
 		iwl_mvm_fast_suspend(mvm);
 		/* From this point on, we won't touch the device */
 		iwl_mvm_mei_device_state(mvm, false);
@@ -1988,15 +1986,8 @@ static void iwl_mvm_mac_remove_interface(struct ieee80211_hw *hw,
 	 * interface is be handled as part of the stop_ap flow.
 	 */
 	if (vif->type == NL80211_IFTYPE_AP ||
-	    vif->type == NL80211_IFTYPE_ADHOC) {
-#ifdef CONFIG_NL80211_TESTMODE
-		if (vif == mvm->noa_vif) {
-			mvm->noa_vif = NULL;
-			mvm->noa_duration = 0;
-		}
-#endif
+	    vif->type == NL80211_IFTYPE_ADHOC)
 		goto out;
-	}
 
 	iwl_mvm_power_update_mac(mvm);
 
@@ -3059,7 +3050,7 @@ static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw,
 	 * context. For the newer, the beacon is a resource that belongs to a
 	 * MAC, so need to send beacon template after adding the mac.
 	 */
-	if (mvm->trans->trans_cfg->device_family > IWL_DEVICE_FAMILY_22000) {
+	if (mvm->trans->mac_cfg->device_family > IWL_DEVICE_FAMILY_22000) {
 		/* Add the mac context */
 		ret = iwl_mvm_mac_ctxt_add(mvm, vif);
 		if (ret)
@@ -4105,7 +4096,8 @@ void iwl_mvm_smps_workaround(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 
-	if (!iwl_mvm_has_rlc_offload(mvm))
+	if (!iwl_mvm_has_rlc_offload(mvm) ||
+	    iwl_fw_lookup_cmd_ver(mvm->fw, MAC_PM_POWER_TABLE, 0) >= 2)
 		return;
 
 	mvmvif->ps_disabled = !vif->cfg.ps;
@@ -4395,7 +4387,7 @@ static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
 
 	switch (key->cipher) {
 	case WLAN_CIPHER_SUITE_TKIP:
-		if (!mvm->trans->trans_cfg->gen2) {
+		if (!mvm->trans->mac_cfg->gen2) {
 			key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIC;
 			key->flags |= IEEE80211_KEY_FLAG_PUT_IV_SPACE;
 		} else if (vif->type == NL80211_IFTYPE_STATION) {
@@ -4512,7 +4504,7 @@ static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
 
 			WARN_ON(rcu_access_pointer(mvmsta->ptk_pn[keyidx]));
 			ptk_pn = kzalloc(struct_size(ptk_pn, q,
-						     mvm->trans->num_rx_queues),
+						     mvm->trans->info.num_rxqs),
 					 GFP_KERNEL);
 			if (!ptk_pn) {
 				ret = -ENOMEM;
@@ -4521,7 +4513,7 @@ static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
 
 			for (tid = 0; tid < IWL_MAX_TID_COUNT; tid++) {
 				ieee80211_get_key_rx_seq(key, tid, &seq);
-				for (q = 0; q < mvm->trans->num_rx_queues; q++)
+				for (q = 0; q < mvm->trans->info.num_rxqs; q++)
 					memcpy(ptk_pn->q[q].pn[tid],
 					       seq.ccmp.pn,
 					       IEEE80211_CCMP_PN_LEN);
@@ -5525,70 +5517,6 @@ static int iwl_mvm_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
 					       &mvm_sta->vif->bss_conf);
 }
 
-#ifdef CONFIG_NL80211_TESTMODE
-static const struct nla_policy iwl_mvm_tm_policy[IWL_MVM_TM_ATTR_MAX + 1] = {
-	[IWL_MVM_TM_ATTR_CMD] = { .type = NLA_U32 },
-	[IWL_MVM_TM_ATTR_NOA_DURATION] = { .type = NLA_U32 },
-	[IWL_MVM_TM_ATTR_BEACON_FILTER_STATE] = { .type = NLA_U32 },
-};
-
-static int __iwl_mvm_mac_testmode_cmd(struct iwl_mvm *mvm,
-				      struct ieee80211_vif *vif,
-				      void *data, int len)
-{
-	struct nlattr *tb[IWL_MVM_TM_ATTR_MAX + 1];
-	int err;
-	u32 noa_duration;
-
-	err = nla_parse_deprecated(tb, IWL_MVM_TM_ATTR_MAX, data, len,
-				   iwl_mvm_tm_policy, NULL);
-	if (err)
-		return err;
-
-	if (!tb[IWL_MVM_TM_ATTR_CMD])
-		return -EINVAL;
-
-	switch (nla_get_u32(tb[IWL_MVM_TM_ATTR_CMD])) {
-	case IWL_MVM_TM_CMD_SET_NOA:
-		if (!vif || vif->type != NL80211_IFTYPE_AP || !vif->p2p ||
-		    !vif->bss_conf.enable_beacon ||
-		    !tb[IWL_MVM_TM_ATTR_NOA_DURATION])
-			return -EINVAL;
-
-		noa_duration = nla_get_u32(tb[IWL_MVM_TM_ATTR_NOA_DURATION]);
-		if (noa_duration >= vif->bss_conf.beacon_int)
-			return -EINVAL;
-
-		mvm->noa_duration = noa_duration;
-		mvm->noa_vif = vif;
-
-		return iwl_mvm_update_quotas(mvm, true, NULL);
-	case IWL_MVM_TM_CMD_SET_BEACON_FILTER:
-		/* must be associated client vif - ignore authorized */
-		if (!vif || vif->type != NL80211_IFTYPE_STATION ||
-		    !vif->cfg.assoc || !vif->bss_conf.dtim_period ||
-		    !tb[IWL_MVM_TM_ATTR_BEACON_FILTER_STATE])
-			return -EINVAL;
-
-		if (nla_get_u32(tb[IWL_MVM_TM_ATTR_BEACON_FILTER_STATE]))
-			return iwl_mvm_enable_beacon_filter(mvm, vif);
-		return iwl_mvm_disable_beacon_filter(mvm, vif);
-	}
-
-	return -EOPNOTSUPP;
-}
-
-int iwl_mvm_mac_testmode_cmd(struct ieee80211_hw *hw,
-			     struct ieee80211_vif *vif,
-			     void *data, int len)
-{
-	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
-
-	guard(mvm)(mvm);
-	return __iwl_mvm_mac_testmode_cmd(mvm, vif, data, len);
-}
-#endif
-
 void iwl_mvm_channel_switch(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			    struct ieee80211_channel_switch *chsw)
 {
@@ -6140,12 +6068,12 @@ static void iwl_mvm_set_sta_rate(u32 rate_n_flags, struct rate_info *rinfo)
 		break;
 	}
 
-	if (format == RATE_MCS_CCK_MSK ||
-	    format == RATE_MCS_LEGACY_OFDM_MSK) {
+	if (format == RATE_MCS_MOD_TYPE_CCK ||
+	    format == RATE_MCS_MOD_TYPE_LEGACY_OFDM) {
 		int rate = u32_get_bits(rate_n_flags, RATE_LEGACY_RATE_MSK);
 
 		/* add the offset needed to get to the legacy ofdm indices */
-		if (format == RATE_MCS_LEGACY_OFDM_MSK)
+		if (format == RATE_MCS_MOD_TYPE_LEGACY_OFDM)
 			rate += IWL_FIRST_OFDM_RATE;
 
 		switch (rate) {
@@ -6190,7 +6118,7 @@ static void iwl_mvm_set_sta_rate(u32 rate_n_flags, struct rate_info *rinfo)
 
 	rinfo->nss = u32_get_bits(rate_n_flags,
 				  RATE_MCS_NSS_MSK) + 1;
-	rinfo->mcs = format == RATE_MCS_HT_MSK ?
+	rinfo->mcs = format == RATE_MCS_MOD_TYPE_HT ?
 		RATE_HT_MCS_INDEX(rate_n_flags) :
 		u32_get_bits(rate_n_flags, RATE_MCS_CODE_MSK);
 
@@ -6198,11 +6126,11 @@ static void iwl_mvm_set_sta_rate(u32 rate_n_flags, struct rate_info *rinfo)
 		rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
 
 	switch (format) {
-	case RATE_MCS_EHT_MSK:
+	case RATE_MCS_MOD_TYPE_EHT:
 		/* TODO: GI/LTF/RU. How does the firmware encode them? */
 		rinfo->flags |= RATE_INFO_FLAGS_EHT_MCS;
 		break;
-	case RATE_MCS_HE_MSK:
+	case RATE_MCS_MOD_TYPE_HE:
 		gi_ltf = u32_get_bits(rate_n_flags, RATE_MCS_HE_GI_LTF_MSK);
 
 		rinfo->flags |= RATE_INFO_FLAGS_HE_MCS;
@@ -6243,10 +6171,10 @@ static void iwl_mvm_set_sta_rate(u32 rate_n_flags, struct rate_info *rinfo)
 		if (rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK)
 			rinfo->he_dcm = 1;
 		break;
-	case RATE_MCS_HT_MSK:
+	case RATE_MCS_MOD_TYPE_HT:
 		rinfo->flags |= RATE_INFO_FLAGS_MCS;
 		break;
-	case RATE_MCS_VHT_MSK:
+	case RATE_MCS_MOD_TYPE_VHT:
 		rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS;
 		break;
 	}
@@ -6426,17 +6354,10 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
 				     bool sync,
 				     const void *data, u32 size)
 {
-	struct {
-		struct iwl_rxq_sync_cmd cmd;
-		struct iwl_mvm_internal_rxq_notif notif;
-	} __packed cmd = {
-		.cmd.rxq_mask = cpu_to_le32(BIT(mvm->trans->num_rx_queues) - 1),
-		.cmd.count =
-			cpu_to_le32(sizeof(struct iwl_mvm_internal_rxq_notif) +
-				    size),
-		.notif.type = type,
-		.notif.sync = sync,
-	};
+	DEFINE_RAW_FLEX(struct iwl_rxq_sync_cmd, cmd, payload,
+			sizeof(struct iwl_mvm_internal_rxq_notif));
+	struct iwl_mvm_internal_rxq_notif *notif =
+			(struct iwl_mvm_internal_rxq_notif *)cmd->payload;
 	struct iwl_host_cmd hcmd = {
 		.id = WIDE_ID(DATA_PATH_GROUP, TRIGGER_RX_QUEUES_NOTIF_CMD),
 		.data[0] = &cmd,
@@ -6447,16 +6368,22 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
 	};
 	int ret;
 
+	cmd->rxq_mask = cpu_to_le32(BIT(mvm->trans->info.num_rxqs) - 1);
+	cmd->count = cpu_to_le32(sizeof(struct iwl_mvm_internal_rxq_notif) +
+				 size);
+	notif->type = type;
+	notif->sync = sync;
+
 	/* size must be a multiple of DWORD */
-	if (WARN_ON(cmd.cmd.count & cpu_to_le32(3)))
+	if (WARN_ON(cmd->count & cpu_to_le32(3)))
 		return;
 
 	if (!iwl_mvm_has_new_rx_api(mvm))
 		return;
 
 	if (sync) {
-		cmd.notif.cookie = mvm->queue_sync_cookie;
-		mvm->queue_sync_state = (1 << mvm->trans->num_rx_queues) - 1;
+		notif->cookie = mvm->queue_sync_cookie;
+		mvm->queue_sync_state = (1 << mvm->trans->info.num_rxqs) - 1;
 	}
 
 	ret = iwl_mvm_send_cmd(mvm, &hcmd);
@@ -6649,8 +6576,6 @@ const struct ieee80211_ops iwl_mvm_hw_ops = {
 
 	.sync_rx_queues = iwl_mvm_sync_rx_queues,
 
-	CFG80211_TESTMODE_CMD(iwl_mvm_mac_testmode_cmd)
-
 #ifdef CONFIG_PM_SLEEP
 	/* look at d3.c */
 	.suspend = iwl_mvm_suspend,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
index bb7851042177..81ca9ff67be9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
@@ -1,17 +1,25 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2022 - 2024 Intel Corporation
+ * Copyright (C) 2022 - 2025 Intel Corporation
  */
 #include "mvm.h"
 
 static void iwl_mvm_mld_set_he_support(struct iwl_mvm *mvm,
 				       struct ieee80211_vif *vif,
-				       struct iwl_mac_config_cmd *cmd)
+				       struct iwl_mac_config_cmd *cmd,
+				       int cmd_ver)
 {
-	if (vif->type == NL80211_IFTYPE_AP)
-		cmd->he_ap_support = cpu_to_le16(1);
-	else
-		cmd->he_support = cpu_to_le16(1);
+	if (vif->type == NL80211_IFTYPE_AP) {
+		if (cmd_ver == 2)
+			cmd->wifi_gen_v2.he_ap_support = cpu_to_le16(1);
+		else
+			cmd->wifi_gen.he_ap_support = 1;
+	} else {
+		if (cmd_ver == 2)
+			cmd->wifi_gen_v2.he_support = cpu_to_le16(1);
+		else
+			cmd->wifi_gen.he_support = 1;
+	}
 }
 
 static void iwl_mvm_mld_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
@@ -22,6 +30,12 @@ static void iwl_mvm_mld_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	struct ieee80211_bss_conf *link_conf;
 	unsigned int link_id;
+	int cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw,
+					    WIDE_ID(MAC_CONF_GROUP,
+						    MAC_CONFIG_CMD), 0);
+
+	if (WARN_ON(cmd_ver < 1 && cmd_ver > 3))
+		return;
 
 	cmd->id_and_color = cpu_to_le32(mvmvif->id);
 	cmd->action = cpu_to_le32(action);
@@ -30,8 +44,8 @@ static void iwl_mvm_mld_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
 
 	memcpy(cmd->local_mld_addr, vif->addr, ETH_ALEN);
 
-	cmd->he_support = 0;
-	cmd->eht_support = 0;
+	cmd->wifi_gen_v2.he_support = 0;
+	cmd->wifi_gen_v2.eht_support = 0;
 
 	/* should be set by specific context type handler */
 	cmd->filter_flags = 0;
@@ -51,8 +65,11 @@ static void iwl_mvm_mld_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
 	 * and enable both when we have MLO.
 	 */
 	if (ieee80211_vif_is_mld(vif)) {
-		iwl_mvm_mld_set_he_support(mvm, vif, cmd);
-		cmd->eht_support = cpu_to_le32(1);
+		iwl_mvm_mld_set_he_support(mvm, vif, cmd, cmd_ver);
+		if (cmd_ver == 2)
+			cmd->wifi_gen_v2.eht_support = cpu_to_le32(1);
+		else
+			cmd->wifi_gen.eht_support = 1;
 		return;
 	}
 
@@ -63,16 +80,19 @@ static void iwl_mvm_mld_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
 			continue;
 
 		if (link_conf->he_support)
-			iwl_mvm_mld_set_he_support(mvm, vif, cmd);
+			iwl_mvm_mld_set_he_support(mvm, vif, cmd, cmd_ver);
 
-		/* it's not reasonable to have EHT without HE and FW API doesn't
+		/* It's not reasonable to have EHT without HE and FW API doesn't
 		 * support it. Ignore EHT in this case.
 		 */
 		if (!link_conf->he_support && link_conf->eht_support)
 			continue;
 
 		if (link_conf->eht_support) {
-			cmd->eht_support = cpu_to_le32(1);
+			if (cmd_ver == 2)
+				cmd->wifi_gen_v2.eht_support = cpu_to_le32(1);
+			else
+				cmd->wifi_gen.eht_support = 1;
 			break;
 		}
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 78d7153a0cfc..bf24f8cb673e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -150,19 +150,6 @@ static void iwl_mvm_mld_mac_remove_interface(struct ieee80211_hw *hw,
 
 	iwl_mvm_vif_dbgfs_rm_link(mvm, vif);
 
-	/* For AP/GO interface, the tear down of the resources allocated to the
-	 * interface is be handled as part of the stop_ap flow.
-	 */
-	if (vif->type == NL80211_IFTYPE_AP ||
-	    vif->type == NL80211_IFTYPE_ADHOC) {
-#ifdef CONFIG_NL80211_TESTMODE
-		if (vif == mvm->noa_vif) {
-			mvm->noa_vif = NULL;
-			mvm->noa_duration = 0;
-		}
-#endif
-	}
-
 	iwl_mvm_power_update_mac(mvm);
 
 	/* Before the interface removal, mac80211 would cancel the ROC, and the
@@ -1403,8 +1390,6 @@ const struct ieee80211_ops iwl_mvm_mld_hw_ops = {
 
 	.sync_rx_queues = iwl_mvm_sync_rx_queues,
 
-	CFG80211_TESTMODE_CMD(iwl_mvm_mac_testmode_cmd)
-
 #ifdef CONFIG_PM_SLEEP
 	/* look at d3.c */
 	.suspend = iwl_mvm_suspend,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
index 9dd670041137..e1010521c3ea 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2022-2024 Intel Corporation
+ * Copyright (C) 2022-2025 Intel Corporation
  */
 #include "mvm.h"
 #include "time-sync.h"
@@ -48,9 +48,13 @@ u32 iwl_mvm_sta_fw_id_mask(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 static int iwl_mvm_mld_send_sta_cmd(struct iwl_mvm *mvm,
 				    struct iwl_sta_cfg_cmd *cmd)
 {
+	u32 cmd_id = WIDE_ID(MAC_CONF_GROUP, STA_CONFIG_CMD);
+	int cmd_len = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id, 0) > 1 ?
+		      sizeof(*cmd) :
+		      sizeof(struct iwl_sta_cfg_cmd_v1);
 	int ret = iwl_mvm_send_cmd_pdu(mvm,
 				       WIDE_ID(MAC_CONF_GROUP, STA_CONFIG_CMD),
-				       0, sizeof(*cmd), cmd);
+				       0, cmd_len, cmd);
 	if (ret)
 		IWL_ERR(mvm, "STA_CONFIG_CMD send failed, ret=0x%x\n", ret);
 	return ret;
@@ -144,7 +148,7 @@ int iwl_mvm_mld_add_int_sta_with_queue(struct iwl_mvm *mvm,
 {
 	int ret, txq;
 	unsigned int wdg_timeout = _wdg_timeout ? *_wdg_timeout :
-		mvm->trans->trans_cfg->base_params->wd_timeout;
+		mvm->trans->mac_cfg->base->wd_timeout;
 
 	if (WARN_ON_ONCE(sta->sta_id == IWL_INVALID_STA))
 		return -ENOSPC;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index f6391c7a3e29..a4f412e750d0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -126,7 +126,7 @@ struct iwl_mvm_time_event_data {
  /* Power management */
 
 /**
- * enum iwl_power_scheme
+ * enum iwl_power_scheme - iwl power schemes
  * @IWL_POWER_SCHEME_CAM: Continuously Active Mode
  * @IWL_POWER_SCHEME_BPS: Balanced Power Save (default)
  * @IWL_POWER_SCHEME_LP: Low Power
@@ -664,6 +664,8 @@ enum iwl_mvm_sched_scan_pass_all_states {
  * @min_backoff: The minimal tx backoff due to power restrictions
  * @params: Parameters to configure the thermal throttling algorithm.
  * @throttle: Is thermal throttling is active?
+ * @power_budget_mw: maximum cTDP power budget as defined for this system and
+ *	device
  */
 struct iwl_mvm_tt_mgmt {
 	struct delayed_work ct_kill_exit;
@@ -672,6 +674,8 @@ struct iwl_mvm_tt_mgmt {
 	u32 min_backoff;
 	struct iwl_tt_params params;
 	bool throttle;
+
+	u32 power_budget_mw;
 };
 
 #ifdef CONFIG_THERMAL
@@ -999,7 +1003,7 @@ struct iwl_mvm {
 
 	struct iwl_trans *trans;
 	const struct iwl_fw *fw;
-	const struct iwl_cfg *cfg;
+	const struct iwl_rf_cfg *cfg;
 	struct iwl_phy_db *phy_db;
 	struct ieee80211_hw *hw;
 
@@ -1033,6 +1037,8 @@ struct iwl_mvm {
 
 	u8 cca_40mhz_workaround;
 
+	u8 fw_rates_ver;
+
 	u32 ampdu_ref;
 	bool ampdu_toggle;
 
@@ -1246,11 +1252,6 @@ struct iwl_mvm {
 
 	struct iwl_time_quota_cmd last_quota_cmd;
 
-#ifdef CONFIG_NL80211_TESTMODE
-	u32 noa_duration;
-	struct ieee80211_vif *noa_vif;
-#endif
-
 	/* Tx queues */
 	u16 aux_queue;
 	u16 snif_queue;
@@ -1348,10 +1349,6 @@ struct iwl_mvm {
 	__le16 cur_aid;
 	u8 cur_bssid[ETH_ALEN];
 
-#ifdef CONFIG_ACPI
-	struct iwl_phy_specific_cfg phy_filters;
-#endif
-
 	/* report rx timestamp in ptp clock time */
 	bool rx_ts_ptp;
 
@@ -1562,7 +1559,7 @@ static inline bool iwl_mvm_is_lar_supported(struct iwl_mvm *mvm)
 	 * Enable LAR only if it is supported by the FW (TLV) &&
 	 * enabled in the NVM
 	 */
-	if (mvm->cfg->nvm_type == IWL_NVM_EXT)
+	if (mvm->trans->cfg->nvm_type == IWL_NVM_EXT)
 		return nvm_lar && tlv_lar;
 	else
 		return tlv_lar;
@@ -1626,13 +1623,13 @@ static inline bool iwl_mvm_has_new_station_api(const struct iwl_fw *fw)
 static inline bool iwl_mvm_has_new_tx_api(struct iwl_mvm *mvm)
 {
 	/* TODO - replace with TLV once defined */
-	return mvm->trans->trans_cfg->gen2;
+	return mvm->trans->mac_cfg->gen2;
 }
 
 static inline bool iwl_mvm_has_unified_ucode(struct iwl_mvm *mvm)
 {
 	/* TODO - better define this */
-	return mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000;
+	return mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_22000;
 }
 
 static inline bool iwl_mvm_is_cdb_supported(struct iwl_mvm *mvm)
@@ -1657,7 +1654,7 @@ static inline bool iwl_mvm_cdb_scan_api(struct iwl_mvm *mvm)
 	 * but then there's a little bit of code in scan that won't make
 	 * any sense...
 	 */
-	return mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000;
+	return mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_22000;
 }
 
 static inline bool iwl_mvm_is_scan_ext_chan_supported(struct iwl_mvm *mvm)
@@ -1732,13 +1729,13 @@ static inline bool iwl_mvm_is_ctdp_supported(struct iwl_mvm *mvm)
 
 static inline bool iwl_mvm_is_esr_supported(struct iwl_trans *trans)
 {
-	if (CSR_HW_RFID_IS_CDB(trans->hw_rf_id))
+	if (CSR_HW_RFID_IS_CDB(trans->info.hw_rf_id))
 		return false;
 
-	switch (CSR_HW_RFID_TYPE(trans->hw_rf_id)) {
+	switch (CSR_HW_RFID_TYPE(trans->info.hw_rf_id)) {
 	case IWL_CFG_RF_TYPE_FM:
 		/* Step A doesn't support eSR */
-		return CSR_HW_RFID_STEP(trans->hw_rf_id);
+		return CSR_HW_RFID_STEP(trans->info.hw_rf_id);
 	case IWL_CFG_RF_TYPE_WH:
 	case IWL_CFG_RF_TYPE_PE:
 		return true;
@@ -1757,8 +1754,8 @@ static inline int iwl_mvm_max_active_links(struct iwl_mvm *mvm,
 
 	/* Check if HW supports eSR or STR */
 	if (iwl_mvm_is_esr_supported(trans) ||
-	    (CSR_HW_RFID_TYPE(trans->hw_rf_id) == IWL_CFG_RF_TYPE_FM &&
-	     CSR_HW_RFID_IS_CDB(trans->hw_rf_id)))
+	    (CSR_HW_RFID_TYPE(trans->info.hw_rf_id) == IWL_CFG_RF_TYPE_FM &&
+	     CSR_HW_RFID_IS_CDB(trans->info.hw_rf_id)))
 		return IWL_FW_MAX_ACTIVE_LINKS_NUM;
 
 	return 1;
@@ -1771,7 +1768,7 @@ extern const u8 iwl_mvm_ac_to_bz_tx_fifo[];
 static inline u8 iwl_mvm_mac_ac_to_tx_fifo(struct iwl_mvm *mvm,
 					   enum ieee80211_ac_numbers ac)
 {
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 		return iwl_mvm_ac_to_bz_tx_fifo[ac];
 	if (iwl_mvm_has_new_tx_api(mvm))
 		return iwl_mvm_ac_to_gen2_tx_fifo[ac];
@@ -1810,9 +1807,6 @@ int iwl_mvm_legacy_rate_to_mac80211_idx(u32 rate_n_flags,
 void iwl_mvm_hwrate_to_tx_rate(u32 rate_n_flags,
 			       enum nl80211_band band,
 			       struct ieee80211_tx_rate *r);
-void iwl_mvm_hwrate_to_tx_rate_v1(u32 rate_n_flags,
-				  enum nl80211_band band,
-				  struct ieee80211_tx_rate *r);
 u8 iwl_mvm_mac80211_idx_to_hwrate(const struct iwl_fw *fw, int rate_idx);
 u8 iwl_mvm_mac80211_ac_to_ucode_ac(enum ieee80211_ac_numbers ac);
 bool iwl_mvm_is_nic_ack_enabled(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
@@ -1843,9 +1837,9 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
 		       struct ieee80211_sta *sta);
 int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb);
 void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb,
-			struct iwl_tx_cmd *tx_cmd,
+			struct iwl_tx_cmd_v6 *tx_cmd,
 			struct ieee80211_tx_info *info, u8 sta_id);
-void iwl_mvm_set_tx_cmd_rate(struct iwl_mvm *mvm, struct iwl_tx_cmd *tx_cmd,
+void iwl_mvm_set_tx_cmd_rate(struct iwl_mvm *mvm, struct iwl_tx_cmd_v6 *tx_cmd,
 			    struct ieee80211_tx_info *info,
 			    struct ieee80211_sta *sta, __le16 fc);
 void iwl_mvm_mac_itxq_xmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq);
@@ -1876,7 +1870,7 @@ int iwl_mvm_set_sta_pkt_ext(struct iwl_mvm *mvm,
 void iwl_mvm_async_handlers_purge(struct iwl_mvm *mvm);
 
 static inline void iwl_mvm_set_tx_cmd_ccmp(struct ieee80211_tx_info *info,
-					   struct iwl_tx_cmd *tx_cmd)
+					   struct iwl_tx_cmd_v6 *tx_cmd)
 {
 	struct ieee80211_key_conf *keyconf = info->control.hw_key;
 
@@ -2138,6 +2132,10 @@ bool iwl_mvm_mld_valid_link_pair(struct ieee80211_vif *vif,
 				 const struct iwl_mvm_link_sel_data *b);
 
 s8 iwl_mvm_average_dbm_values(const struct iwl_umac_scan_channel_survey_notif *notif);
+
+
+extern const struct iwl_hcmd_arr iwl_mvm_groups[];
+extern const unsigned int iwl_mvm_groups_size;
 #endif
 
 /* AP and IBSS */
@@ -2459,7 +2457,7 @@ void iwl_mvm_vif_set_low_latency(struct iwl_mvm_vif *mvmvif, bool set,
  */
 static inline u32 iwl_mvm_flushable_queues(struct iwl_mvm *mvm)
 {
-	return ((BIT(mvm->trans->trans_cfg->base_params->num_of_queues) - 1) &
+	return ((BIT(mvm->trans->mac_cfg->base->num_of_queues) - 1) &
 		~BIT(IWL_MVM_DQA_CMD_QUEUE));
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
index 80ec59c58ae4..953218f1e025 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2019, 2021-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2019, 2021-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -120,7 +120,7 @@ static int iwl_nvm_read_chunk(struct iwl_mvm *mvm, u16 section,
 		} else {
 			IWL_DEBUG_EEPROM(mvm->trans->dev,
 					 "NVM access command failed with status %d (device: %s)\n",
-					 ret, mvm->trans->name);
+					 ret, mvm->trans->info.name);
 			ret = -ENODATA;
 		}
 		goto exit;
@@ -191,7 +191,7 @@ static int iwl_nvm_read_section(struct iwl_mvm *mvm, u16 section,
 	while (ret == length) {
 		/* Check no memory assumptions fail and cause an overflow */
 		if ((size_read + offset + length) >
-		    mvm->trans->trans_cfg->base_params->eeprom_size) {
+		    mvm->trans->mac_cfg->base->eeprom_size) {
 			IWL_ERR(mvm, "EEPROM size is too small for NVM\n");
 			return -ENOBUFS;
 		}
@@ -206,7 +206,7 @@ static int iwl_nvm_read_section(struct iwl_mvm *mvm, u16 section,
 		offset += ret;
 	}
 
-	iwl_nvm_fixups(mvm->trans->hw_id, section, data, offset);
+	iwl_nvm_fixups(mvm->trans->info.hw_id, section, data, offset);
 
 	IWL_DEBUG_EEPROM(mvm->trans->dev,
 			 "NVM section %d read completed\n", section);
@@ -226,7 +226,7 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm)
 	/* Checking for required sections */
 	if (mvm->trans->cfg->nvm_type == IWL_NVM) {
 		if (!mvm->nvm_sections[NVM_SECTION_TYPE_SW].data ||
-		    !mvm->nvm_sections[mvm->cfg->nvm_hw_section_num].data) {
+		    !mvm->nvm_sections[mvm->trans->mac_cfg->base->nvm_hw_section_num].data) {
 			IWL_ERR(mvm, "Can't parse empty OTP/NVM sections\n");
 			return NULL;
 		}
@@ -244,7 +244,7 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm)
 			return NULL;
 		}
 		/* MAC_OVERRIDE or at least HW section must exist */
-		if (!mvm->nvm_sections[mvm->cfg->nvm_hw_section_num].data &&
+		if (!mvm->nvm_sections[mvm->trans->mac_cfg->base->nvm_hw_section_num].data &&
 		    !mvm->nvm_sections[NVM_SECTION_TYPE_MAC_OVERRIDE].data) {
 			IWL_ERR(mvm,
 				"Can't parse mac_address, empty sections\n");
@@ -260,7 +260,7 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm)
 		}
 	}
 
-	hw = (const __be16 *)sections[mvm->cfg->nvm_hw_section_num].data;
+	hw = (const __be16 *)sections[mvm->trans->mac_cfg->base->nvm_hw_section_num].data;
 	sw = (const __le16 *)sections[NVM_SECTION_TYPE_SW].data;
 	calib = (const __le16 *)sections[NVM_SECTION_TYPE_CALIBRATION].data;
 	mac_override =
@@ -308,16 +308,15 @@ int iwl_nvm_init(struct iwl_mvm *mvm)
 	int ret, section;
 	u32 size_read = 0;
 	u8 *nvm_buffer, *temp;
-	const char *nvm_file_C = mvm->cfg->default_nvm_file_C_step;
 
-	if (WARN_ON_ONCE(mvm->cfg->nvm_hw_section_num >= NVM_MAX_NUM_SECTIONS))
+	if (WARN_ON_ONCE(mvm->trans->mac_cfg->base->nvm_hw_section_num >= NVM_MAX_NUM_SECTIONS))
 		return -EINVAL;
 
 	/* load NVM values from nic */
 	/* Read From FW NVM */
 	IWL_DEBUG_EEPROM(mvm->trans->dev, "Read from NVM\n");
 
-	nvm_buffer = kmalloc(mvm->trans->trans_cfg->base_params->eeprom_size,
+	nvm_buffer = kmalloc(mvm->trans->mac_cfg->base->eeprom_size,
 			     GFP_KERNEL);
 	if (!nvm_buffer)
 		return -ENOMEM;
@@ -338,7 +337,7 @@ int iwl_nvm_init(struct iwl_mvm *mvm)
 			break;
 		}
 
-		iwl_nvm_fixups(mvm->trans->hw_id, section, temp, ret);
+		iwl_nvm_fixups(mvm->trans->info.hw_id, section, temp, ret);
 
 		mvm->nvm_sections[section].data = temp;
 		mvm->nvm_sections[section].length = ret;
@@ -367,7 +366,7 @@ int iwl_nvm_init(struct iwl_mvm *mvm)
 			mvm->nvm_reg_blob.size  = ret;
 			break;
 		default:
-			if (section == mvm->cfg->nvm_hw_section_num) {
+			if (section == mvm->trans->mac_cfg->base->nvm_hw_section_num) {
 				mvm->nvm_hw_blob.data = temp;
 				mvm->nvm_hw_blob.size = ret;
 				break;
@@ -384,21 +383,8 @@ int iwl_nvm_init(struct iwl_mvm *mvm)
 		/* read External NVM file from the mod param */
 		ret = iwl_read_external_nvm(mvm->trans, mvm->nvm_file_name,
 					    mvm->nvm_sections);
-		if (ret) {
-			mvm->nvm_file_name = nvm_file_C;
-
-			if ((ret == -EFAULT || ret == -ENOENT) &&
-			    mvm->nvm_file_name) {
-				/* in case nvm file was failed try again */
-				ret = iwl_read_external_nvm(mvm->trans,
-							    mvm->nvm_file_name,
-							    mvm->nvm_sections);
-				if (ret)
-					return ret;
-			} else {
-				return ret;
-			}
-		}
+		if (ret)
+			return ret;
 	}
 
 	/* parse the relevant nvm sections */
@@ -554,7 +540,7 @@ int iwl_mvm_init_mcc(struct iwl_mvm *mvm)
 	struct ieee80211_regdomain *regd;
 	char mcc[3];
 
-	if (mvm->cfg->nvm_type == IWL_NVM_EXT) {
+	if (mvm->trans->cfg->nvm_type == IWL_NVM_EXT) {
 		tlv_lar = fw_has_capa(&mvm->fw->ucode_capa,
 				      IWL_UCODE_TLV_CAPA_LAR_SUPPORT);
 		nvm_lar = mvm->nvm_data->lar_enabled;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 76603ef02704..a2dc5c3b0596 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -92,11 +92,11 @@ static void iwl_mvm_nic_config(struct iwl_op_mode *op_mode)
 	IWL_DEBUG_INFO(mvm, "Radio type=0x%x-0x%x-0x%x\n", radio_cfg_type,
 		       radio_cfg_step, radio_cfg_dash);
 
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 		return;
 
 	/* SKU control */
-	reg_val = CSR_HW_REV_STEP_DASH(mvm->trans->hw_rev);
+	reg_val = CSR_HW_REV_STEP_DASH(mvm->trans->info.hw_rev);
 
 	/* radio configuration */
 	reg_val |= radio_cfg_type << CSR_HW_IF_CONFIG_REG_POS_PHY_TYPE;
@@ -114,7 +114,7 @@ static void iwl_mvm_nic_config(struct iwl_op_mode *op_mode)
 	 * unrelated errors. Need to further investigate this, but for now
 	 * we'll separate cases.
 	 */
-	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_8000)
+	if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_8000)
 		reg_val |= CSR_HW_IF_CONFIG_REG_BIT_RADIO_SI;
 
 	if (iwl_fw_dbg_is_d3_debug_enabled(&mvm->fwrt))
@@ -135,7 +135,7 @@ static void iwl_mvm_nic_config(struct iwl_op_mode *op_mode)
 	 * (PCIe power is lost before PERST# is asserted), causing ME FW
 	 * to lose ownership and not being able to obtain it back.
 	 */
-	if (!mvm->trans->cfg->apmg_not_supported)
+	if (!mvm->trans->mac_cfg->base->apmg_not_supported)
 		iwl_set_bits_mask_prph(mvm->trans, APMG_PS_CTRL_REG,
 				       APMG_PS_CTRL_EARLY_PWR_OFF_RESET_DIS,
 				       ~APMG_PS_CTRL_EARLY_PWR_OFF_RESET_DIS);
@@ -777,7 +777,8 @@ static const struct iwl_hcmd_names iwl_mvm_bt_coex_names[] = {
 	HCMD_NAME(PROFILE_NOTIF),
 };
 
-static const struct iwl_hcmd_arr iwl_mvm_groups[] = {
+VISIBLE_IF_IWLWIFI_KUNIT
+const struct iwl_hcmd_arr iwl_mvm_groups[] = {
 	[LEGACY_GROUP] = HCMD_ARR(iwl_mvm_legacy_names),
 	[LONG_GROUP] = HCMD_ARR(iwl_mvm_legacy_names),
 	[SYSTEM_GROUP] = HCMD_ARR(iwl_mvm_system_names),
@@ -793,6 +794,11 @@ static const struct iwl_hcmd_arr iwl_mvm_groups[] = {
 	[DEBUG_GROUP] = HCMD_ARR(iwl_mvm_debug_names),
 	[STATISTICS_GROUP] = HCMD_ARR(iwl_mvm_statistics_names),
 };
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mvm_groups);
+#if IS_ENABLED(CONFIG_IWLWIFI_KUNIT_TESTS)
+const unsigned int iwl_mvm_groups_size = ARRAY_SIZE(iwl_mvm_groups);
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mvm_groups_size);
+#endif
 
 /* this forward declaration can avoid to export the function */
 static void iwl_mvm_async_handlers_wk(struct work_struct *wk);
@@ -1272,13 +1278,12 @@ static void iwl_mvm_trig_link_selection(struct wiphy *wiphy,
 }
 
 static struct iwl_op_mode *
-iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg,
 		      const struct iwl_fw *fw, struct dentry *dbgfs_dir)
 {
 	struct ieee80211_hw *hw;
 	struct iwl_op_mode *op_mode;
 	struct iwl_mvm *mvm;
-	struct iwl_trans_config trans_cfg = {};
 	static const u8 no_reclaim_cmds[] = {
 		TX_CMD,
 	};
@@ -1286,6 +1291,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	size_t scan_size;
 	u32 min_backoff;
 	struct iwl_mvm_csme_conn_info *csme_conn_info __maybe_unused;
+	int ratecheck;
 	int err;
 
 	/*
@@ -1306,18 +1312,13 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	if (!hw)
 		return ERR_PTR(-ENOMEM);
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 		max_agg = 512;
 	else
 		max_agg = IEEE80211_MAX_AMPDU_BUF_HE;
 
 	hw->max_rx_aggregation_subframes = max_agg;
 
-	if (cfg->max_tx_agg_size)
-		hw->max_tx_aggregation_subframes = cfg->max_tx_agg_size;
-	else
-		hw->max_tx_aggregation_subframes = max_agg;
-
 	op_mode = hw->priv;
 
 	mvm = IWL_OP_MODE_GET_MVM(op_mode);
@@ -1337,19 +1338,58 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 	mvm->init_status = 0;
 
+	/* start with v1 rates */
+	mvm->fw_rates_ver = 1;
+
+	/* check for rates version 2 */
+	ratecheck =
+		(iwl_fw_lookup_cmd_ver(mvm->fw, TX_CMD, 0) >= 8) +
+		(iwl_fw_lookup_notif_ver(mvm->fw, DATA_PATH_GROUP,
+					 TLC_MNG_UPDATE_NOTIF, 0) >= 3) +
+		(iwl_fw_lookup_notif_ver(mvm->fw, LEGACY_GROUP,
+					 REPLY_RX_MPDU_CMD, 0) >= 4) +
+		(iwl_fw_lookup_notif_ver(mvm->fw, LONG_GROUP, TX_CMD, 0) >= 6);
+	if (ratecheck != 0 && ratecheck != 4) {
+		IWL_ERR(mvm, "Firmware has inconsistent rates\n");
+		err = -EINVAL;
+		goto out_free;
+	}
+	if (ratecheck == 4)
+		mvm->fw_rates_ver = 2;
+
+	/* check for rates version 3 */
+	ratecheck =
+		(iwl_fw_lookup_cmd_ver(mvm->fw, TX_CMD, 0) >= 11) +
+		(iwl_fw_lookup_notif_ver(mvm->fw, DATA_PATH_GROUP,
+					 TLC_MNG_UPDATE_NOTIF, 0) >= 4) +
+		(iwl_fw_lookup_notif_ver(mvm->fw, LEGACY_GROUP,
+					 REPLY_RX_MPDU_CMD, 0) >= 6) +
+		(iwl_fw_lookup_notif_ver(mvm->fw, DATA_PATH_GROUP,
+					 RX_NO_DATA_NOTIF, 0) >= 4) +
+		(iwl_fw_lookup_notif_ver(mvm->fw, LONG_GROUP, TX_CMD, 0) >= 9);
+	if (ratecheck != 0 && ratecheck != 5) {
+		IWL_ERR(mvm, "Firmware has inconsistent rates\n");
+		err = -EINVAL;
+		goto out_free;
+	}
+	if (ratecheck == 5)
+		mvm->fw_rates_ver = 3;
+
+	trans->conf.rx_mpdu_cmd = REPLY_RX_MPDU_CMD;
+
 	if (iwl_mvm_has_new_rx_api(mvm)) {
 		op_mode->ops = &iwl_mvm_ops_mq;
-		trans->rx_mpdu_cmd_hdr_size =
-			(trans->trans_cfg->device_family >=
+		trans->conf.rx_mpdu_cmd_hdr_size =
+			(trans->mac_cfg->device_family >=
 			 IWL_DEVICE_FAMILY_AX210) ?
 			sizeof(struct iwl_rx_mpdu_desc) :
 			IWL_RX_DESC_SIZE_V1;
 	} else {
 		op_mode->ops = &iwl_mvm_ops;
-		trans->rx_mpdu_cmd_hdr_size =
+		trans->conf.rx_mpdu_cmd_hdr_size =
 			sizeof(struct iwl_rx_mpdu_res_start);
 
-		if (WARN_ON(trans->num_rx_queues > 1)) {
+		if (WARN_ON(trans->info.num_rxqs > 1)) {
 			err = -EINVAL;
 			goto out_free;
 		}
@@ -1437,53 +1477,50 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	 * Populate the state variables that the transport layer needs
 	 * to know about.
 	 */
-	trans_cfg.op_mode = op_mode;
-	trans_cfg.no_reclaim_cmds = no_reclaim_cmds;
-	trans_cfg.n_no_reclaim_cmds = ARRAY_SIZE(no_reclaim_cmds);
+	BUILD_BUG_ON(sizeof(no_reclaim_cmds) >
+		     sizeof(trans->conf.no_reclaim_cmds));
+	memcpy(trans->conf.no_reclaim_cmds, no_reclaim_cmds,
+	       sizeof(no_reclaim_cmds));
+	trans->conf.n_no_reclaim_cmds = ARRAY_SIZE(no_reclaim_cmds);
 
-	trans_cfg.rx_buf_size = iwl_amsdu_size_to_rxb_size();
+	trans->conf.rx_buf_size = iwl_amsdu_size_to_rxb_size();
 
-	trans->wide_cmd_header = true;
-	trans_cfg.bc_table_dword =
-		mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210;
+	trans->conf.wide_cmd_header = true;
 
-	trans_cfg.command_groups = iwl_mvm_groups;
-	trans_cfg.command_groups_size = ARRAY_SIZE(iwl_mvm_groups);
+	trans->conf.command_groups = iwl_mvm_groups;
+	trans->conf.command_groups_size = ARRAY_SIZE(iwl_mvm_groups);
 
-	trans_cfg.cmd_queue = IWL_MVM_DQA_CMD_QUEUE;
-	trans_cfg.cmd_fifo = IWL_MVM_TX_FIFO_CMD;
-	trans_cfg.scd_set_active = true;
+	trans->conf.cmd_queue = IWL_MVM_DQA_CMD_QUEUE;
+	trans->conf.cmd_fifo = IWL_MVM_TX_FIFO_CMD;
+	trans->conf.scd_set_active = true;
 
-	trans_cfg.cb_data_offs = offsetof(struct ieee80211_tx_info,
-					  driver_data[2]);
+	trans->conf.cb_data_offs = offsetof(struct ieee80211_tx_info,
+					    driver_data[2]);
 
 	snprintf(mvm->hw->wiphy->fw_version,
 		 sizeof(mvm->hw->wiphy->fw_version),
 		 "%.31s", fw->fw_version);
 
-	trans_cfg.fw_reset_handshake = fw_has_capa(&mvm->fw->ucode_capa,
-						   IWL_UCODE_TLV_CAPA_FW_RESET_HANDSHAKE);
+	trans->conf.fw_reset_handshake =
+		fw_has_capa(&mvm->fw->ucode_capa,
+			    IWL_UCODE_TLV_CAPA_FW_RESET_HANDSHAKE);
 
-	trans_cfg.queue_alloc_cmd_ver =
+	trans->conf.queue_alloc_cmd_ver =
 		iwl_fw_lookup_cmd_ver(mvm->fw,
 				      WIDE_ID(DATA_PATH_GROUP,
 					      SCD_QUEUE_CONFIG_CMD),
 				      0);
 	mvm->sta_remove_requires_queue_remove =
-		trans_cfg.queue_alloc_cmd_ver > 0;
+		trans->conf.queue_alloc_cmd_ver > 0;
 
 	mvm->mld_api_is_used = iwl_mvm_has_mld_api(mvm->fw);
 
 	/* Configure transport layer */
-	iwl_trans_configure(mvm->trans, &trans_cfg);
+	iwl_trans_op_mode_enter(mvm->trans, op_mode);
 
-	trans->rx_mpdu_cmd = REPLY_RX_MPDU_CMD;
 	trans->dbg.dest_tlv = mvm->fw->dbg.dest_tlv;
 	trans->dbg.n_dest_reg = mvm->fw->dbg.n_dest_reg;
 
-	trans->iml = mvm->fw->iml;
-	trans->iml_len = mvm->fw->iml_len;
-
 	/* set up notification wait support */
 	iwl_notification_wait_init(&mvm->notif_wait);
 
@@ -2100,7 +2137,7 @@ static bool iwl_mvm_sw_reset(struct iwl_op_mode *op_mode,
 			mvm->fwrt.trans->dbg.restart_required = false;
 			ieee80211_restart_hw(mvm->hw);
 			return true;
-		} else if (mvm->trans->trans_cfg->device_family <= IWL_DEVICE_FAMILY_8000) {
+		} else if (mvm->trans->mac_cfg->device_family <= IWL_DEVICE_FAMILY_8000) {
 			ieee80211_restart_hw(mvm->hw);
 			return true;
 		}
@@ -2125,7 +2162,6 @@ static void iwl_op_mode_mvm_device_powered_off(struct iwl_op_mode *op_mode)
 
 	mutex_lock(&mvm->mutex);
 	clear_bit(IWL_MVM_STATUS_IN_D3, &mvm->status);
-	mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
 	iwl_mvm_stop_device(mvm);
 	mvm->fast_resume = false;
 	mutex_unlock(&mvm->mutex);
@@ -2165,7 +2201,7 @@ static void iwl_mvm_rx_mq_rss(struct iwl_op_mode *op_mode,
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	u16 cmd = WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd);
 
-	if (unlikely(queue >= mvm->trans->num_rx_queues))
+	if (unlikely(queue >= mvm->trans->info.num_rxqs))
 		return;
 
 	if (unlikely(cmd == WIDE_ID(LEGACY_GROUP, FRAME_RELEASE)))
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/power.c b/drivers/net/wireless/intel/iwlwifi/mvm/power.c
index a386b315e52f..0057fddf88f0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/power.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/power.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2019, 2021-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2019, 2021-2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -376,6 +376,9 @@ static void iwl_mvm_power_build_cmd(struct iwl_mvm *mvm,
 	if (!vif->cfg.ps || !mvmvif->pm_enabled)
 		return;
 
+	if (iwl_fw_lookup_cmd_ver(mvm->fw, MAC_PM_POWER_TABLE, 0) >= 2)
+		cmd->flags |= cpu_to_le16(POWER_FLAGS_ENABLE_SMPS_MSK);
+
 	if (iwl_mvm_vif_low_latency(mvmvif) && vif->p2p &&
 	    (!fw_has_capa(&mvm->fw->ucode_capa,
 			 IWL_UCODE_TLV_CAPA_SHORT_PM_TIMEOUTS) ||
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/quota.c b/drivers/net/wireless/intel/iwlwifi/mvm/quota.c
index aad2614af9ad..798a7e4bea83 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/quota.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/quota.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018, 2021-2022 Intel Corporation
+ * Copyright (C) 2012-2014, 2018, 2021-2022, 2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -86,45 +86,6 @@ static void iwl_mvm_quota_iterator(void *_data, u8 *mac,
 	}
 }
 
-static void iwl_mvm_adjust_quota_for_noa(struct iwl_mvm *mvm,
-					 struct iwl_time_quota_cmd *cmd)
-{
-#ifdef CONFIG_NL80211_TESTMODE
-	struct iwl_mvm_vif *mvmvif;
-	int i, phy_id = -1, beacon_int = 0;
-
-	if (!mvm->noa_duration || !mvm->noa_vif)
-		return;
-
-	mvmvif = iwl_mvm_vif_from_mac80211(mvm->noa_vif);
-	if (!mvmvif->ap_ibss_active)
-		return;
-
-	phy_id = mvmvif->deflink.phy_ctxt->id;
-	beacon_int = mvm->noa_vif->bss_conf.beacon_int;
-
-	for (i = 0; i < MAX_BINDINGS; i++) {
-		struct iwl_time_quota_data *data =
-					iwl_mvm_quota_cmd_get_quota(mvm, cmd,
-								    i);
-		u32 id_n_c = le32_to_cpu(data->id_and_color);
-		u32 id = (id_n_c & FW_CTXT_ID_MSK) >> FW_CTXT_ID_POS;
-		u32 quota = le32_to_cpu(data->quota);
-
-		if (id != phy_id)
-			continue;
-
-		quota *= (beacon_int - mvm->noa_duration);
-		quota /= beacon_int;
-
-		IWL_DEBUG_QUOTA(mvm, "quota: adjust for NoA from %d to %d\n",
-				le32_to_cpu(data->quota), quota);
-
-		data->quota = cpu_to_le32(quota);
-	}
-#endif
-}
-
 int iwl_mvm_update_quotas(struct iwl_mvm *mvm,
 			  bool force_update,
 			  struct ieee80211_vif *disabled_vif)
@@ -260,8 +221,6 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm,
 		}
 	}
 
-	iwl_mvm_adjust_quota_for_noa(mvm, &cmd);
-
 	/* check that we have non-zero quota for all valid bindings */
 	for (i = 0; i < MAX_BINDINGS; i++) {
 		qdata = iwl_mvm_quota_cmd_get_quota(mvm, &cmd, i);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
index de5ac000272e..89ac4c6b3e54 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include "rs.h"
 #include "fw-api.h"
@@ -72,7 +72,7 @@ static u16 rs_fw_get_config_flags(struct iwl_mvm *mvm,
 	u16 flags = 0;
 
 	/* get STBC flags */
-	if (mvm->cfg->ht_params->stbc &&
+	if (mvm->cfg->ht_params.stbc &&
 	    (num_of_ant(iwl_mvm_get_valid_tx_ant(mvm)) > 1)) {
 		if (he_cap->has_he && he_cap->he_cap_elem.phy_cap_info[2] &
 				      IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ)
@@ -83,7 +83,7 @@ static u16 rs_fw_get_config_flags(struct iwl_mvm *mvm,
 			flags |= IWL_TLC_MNG_CFG_FLAGS_STBC_MSK;
 	}
 
-	if (mvm->cfg->ht_params->ldpc &&
+	if (mvm->cfg->ht_params.ldpc &&
 	    ((ht_cap->cap & IEEE80211_HT_CAP_LDPC_CODING) ||
 	     (vht_ena && (vht_cap->cap & IEEE80211_VHT_CAP_RXLDPC))))
 		flags |= IWL_TLC_MNG_CFG_FLAGS_LDPC_MSK;
@@ -454,22 +454,11 @@ void iwl_mvm_tlc_update_notif(struct iwl_mvm *mvm,
 	if (flags & IWL_TLC_NOTIF_FLAG_RATE) {
 		char pretty_rate[100];
 
-		if (iwl_fw_lookup_notif_ver(mvm->fw, DATA_PATH_GROUP,
-					    TLC_MNG_UPDATE_NOTIF, 0) < 3) {
-			rs_pretty_print_rate_v1(pretty_rate,
-						sizeof(pretty_rate),
-						le32_to_cpu(notif->rate));
-			IWL_DEBUG_RATE(mvm,
-				       "Got rate in old format. Rate: %s. Converting.\n",
-				       pretty_rate);
-			lq_sta->last_rate_n_flags =
-				iwl_new_rate_from_v1(le32_to_cpu(notif->rate));
-		} else {
-			lq_sta->last_rate_n_flags = le32_to_cpu(notif->rate);
-		}
+		lq_sta->last_rate_n_flags =
+			iwl_mvm_v3_rate_from_fw(notif->rate, mvm->fw_rates_ver);
 		rs_pretty_print_rate(pretty_rate, sizeof(pretty_rate),
 				     lq_sta->last_rate_n_flags);
-		IWL_DEBUG_RATE(mvm, "new rate: %s\n", pretty_rate);
+		IWL_DEBUG_RATE(mvm, "rate: %s\n", pretty_rate);
 	}
 
 	if (flags & IWL_TLC_NOTIF_FLAG_AMSDU && !mvm_link_sta->orig_amsdu_len) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index 068c58e9c1eb..5802ed80a9ca 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -2,6 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2005 - 2014, 2018 - 2023 Intel Corporation. All rights reserved.
+ * Copyright(c) 2025 Intel Corporation
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *****************************************************************************/
@@ -895,7 +896,7 @@ static int rs_rate_from_ucode_rate(const u32 ucode_rate,
 			WARN_ON_ONCE(1);
 		}
 	} else if (ucode_rate & RATE_MCS_VHT_MSK_V1) {
-		nss = FIELD_GET(RATE_MCS_NSS_MSK, ucode_rate) + 1;
+		nss = FIELD_GET(RATE_VHT_MCS_NSS_MSK, ucode_rate) + 1;
 
 		if (nss == 1) {
 			rate->type = LQ_VHT_SISO;
@@ -909,7 +910,7 @@ static int rs_rate_from_ucode_rate(const u32 ucode_rate,
 			WARN_ON_ONCE(1);
 		}
 	} else if (ucode_rate & RATE_MCS_HE_MSK_V1) {
-		nss = FIELD_GET(RATE_MCS_NSS_MSK, ucode_rate) + 1;
+		nss = FIELD_GET(RATE_VHT_MCS_NSS_MSK, ucode_rate) + 1;
 
 		if (nss == 1) {
 			rate->type = LQ_HE_SISO;
@@ -2696,8 +2697,10 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta,
 	lq_sta = mvm_sta;
 
 	spin_lock_bh(&lq_sta->pers.lock);
-	iwl_mvm_hwrate_to_tx_rate_v1(lq_sta->last_rate_n_flags,
-				     info->band, &info->control.rates[0]);
+	iwl_mvm_hwrate_to_tx_rate(iwl_mvm_v3_rate_from_fw(
+					cpu_to_le32(lq_sta->last_rate_n_flags),
+					1),
+				  info->band, &info->control.rates[0]);
 	info->control.rates[0].count = 1;
 
 	/* Report the optimal rate based on rssi and STA caps if we haven't
@@ -2707,8 +2710,12 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta,
 		optimal_rate = rs_get_optimal_rate(mvm, lq_sta);
 		last_ucode_rate = ucode_rate_from_rs_rate(mvm,
 							  optimal_rate);
-		iwl_mvm_hwrate_to_tx_rate_v1(last_ucode_rate, info->band,
-					     &txrc->reported_rate);
+		last_ucode_rate =
+			iwl_mvm_v3_rate_from_fw(cpu_to_le32(last_ucode_rate),
+						1);
+		iwl_mvm_hwrate_to_tx_rate(last_ucode_rate, info->band,
+					  &txrc->reported_rate);
+		txrc->reported_rate.count = 1;
 	}
 	spin_unlock_bh(&lq_sta->pers.lock);
 }
@@ -2813,11 +2820,11 @@ static void rs_ht_init(struct iwl_mvm *mvm,
 	lq_sta->active_mimo2_rate &= ~((u16)0x2);
 	lq_sta->active_mimo2_rate <<= IWL_FIRST_OFDM_RATE;
 
-	if (mvm->cfg->ht_params->ldpc &&
+	if (mvm->cfg->ht_params.ldpc &&
 	    (ht_cap->cap & IEEE80211_HT_CAP_LDPC_CODING))
 		lq_sta->ldpc = true;
 
-	if (mvm->cfg->ht_params->stbc &&
+	if (mvm->cfg->ht_params.stbc &&
 	    (num_of_ant(iwl_mvm_get_valid_tx_ant(mvm)) > 1) &&
 	    (ht_cap->cap & IEEE80211_HT_CAP_RX_STBC))
 		lq_sta->stbc_capable = true;
@@ -2832,11 +2839,11 @@ static void rs_vht_init(struct iwl_mvm *mvm,
 {
 	rs_vht_set_enabled_rates(sta, vht_cap, lq_sta);
 
-	if (mvm->cfg->ht_params->ldpc &&
+	if (mvm->cfg->ht_params.ldpc &&
 	    (vht_cap->cap & IEEE80211_VHT_CAP_RXLDPC))
 		lq_sta->ldpc = true;
 
-	if (mvm->cfg->ht_params->stbc &&
+	if (mvm->cfg->ht_params.stbc &&
 	    (num_of_ant(iwl_mvm_get_valid_tx_ant(mvm)) > 1) &&
 	    (vht_cap->cap & IEEE80211_VHT_CAP_RXSTBC_MASK))
 		lq_sta->stbc_capable = true;
@@ -2887,10 +2894,10 @@ void iwl_mvm_update_frame_stats(struct iwl_mvm *mvm, u32 rate, bool agg)
 
 	if (rate & RATE_MCS_HT_MSK_V1) {
 		mvm->drv_rx_stats.ht_frames++;
-		nss = ((rate & RATE_HT_MCS_NSS_MSK_V1) >> RATE_HT_MCS_NSS_POS_V1) + 1;
+		nss = FIELD_GET(RATE_HT_MCS_MIMO2_MSK, rate) + 1;
 	} else if (rate & RATE_MCS_VHT_MSK_V1) {
 		mvm->drv_rx_stats.vht_frames++;
-		nss = FIELD_GET(RATE_MCS_NSS_MSK, rate) + 1;
+		nss = FIELD_GET(RATE_VHT_MCS_NSS_MSK, rate) + 1;
 	} else {
 		mvm->drv_rx_stats.legacy_frames++;
 	}
@@ -3304,7 +3311,7 @@ static void rs_build_rates_table_from_fixed(struct iwl_mvm *mvm,
 	if (num_of_ant(ant) == 1)
 		lq_cmd->single_stream_ant_msk = ant;
 
-	if (!mvm->trans->trans_cfg->gen2)
+	if (!mvm->trans->mac_cfg->gen2)
 		lq_cmd->agg_frame_cnt_limit = LINK_QUAL_AGG_FRAME_LIMIT_DEF;
 	else
 		lq_cmd->agg_frame_cnt_limit =
@@ -3673,16 +3680,15 @@ int rs_pretty_print_rate_v1(char *buf, int bufsz, const u32 rate)
 	if (rate & RATE_MCS_VHT_MSK_V1) {
 		type = "VHT";
 		mcs = rate & RATE_VHT_MCS_RATE_CODE_MSK;
-		nss = FIELD_GET(RATE_MCS_NSS_MSK, rate) + 1;
+		nss = FIELD_GET(RATE_VHT_MCS_NSS_MSK, rate) + 1;
 	} else if (rate & RATE_MCS_HT_MSK_V1) {
 		type = "HT";
 		mcs = rate & RATE_HT_MCS_INDEX_MSK_V1;
-		nss = ((rate & RATE_HT_MCS_NSS_MSK_V1)
-		       >> RATE_HT_MCS_NSS_POS_V1) + 1;
+		nss = FIELD_GET(RATE_HT_MCS_MIMO2_MSK, rate) + 1;
 	} else if (rate & RATE_MCS_HE_MSK_V1) {
 		type = "HE";
 		mcs = rate & RATE_VHT_MCS_RATE_CODE_MSK;
-		nss = FIELD_GET(RATE_MCS_NSS_MSK, rate) + 1;
+		nss = FIELD_GET(RATE_VHT_MCS_NSS_MSK, rate) + 1;
 	} else {
 		type = "Unknown"; /* shouldn't happen */
 	}
@@ -4172,3 +4178,167 @@ int iwl_mvm_tx_protection(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta,
 	else
 		return rs_drv_tx_protection(mvm, mvmsta, enable);
 }
+
+static u32 iwl_legacy_rate_to_fw_idx(u32 rate_n_flags)
+{
+	int rate = rate_n_flags & RATE_LEGACY_RATE_MSK_V1;
+	int idx;
+	bool ofdm = !(rate_n_flags & RATE_MCS_CCK_MSK_V1);
+	int offset = ofdm ? IWL_FIRST_OFDM_RATE : 0;
+	int last = ofdm ? IWL_RATE_COUNT_LEGACY : IWL_FIRST_OFDM_RATE;
+
+	for (idx = offset; idx < last; idx++)
+		if (iwl_fw_rate_idx_to_plcp(idx) == rate)
+			return idx - offset;
+	return IWL_RATE_INVALID;
+}
+
+u32 iwl_mvm_v3_rate_from_fw(__le32 rate, u8 rate_ver)
+{
+	u32 rate_v3 = 0, rate_v1;
+	u32 dup = 0;
+
+	if (rate_ver > 1)
+		return iwl_v3_rate_from_v2_v3(rate, rate_ver >= 3);
+
+	rate_v1 = le32_to_cpu(rate);
+	if (rate_v1 == 0)
+		return rate_v1;
+	/* convert rate */
+	if (rate_v1 & RATE_MCS_HT_MSK_V1) {
+		u32 nss;
+
+		rate_v3 |= RATE_MCS_MOD_TYPE_HT;
+		rate_v3 |=
+			rate_v1 & RATE_HT_MCS_RATE_CODE_MSK_V1;
+		nss = u32_get_bits(rate_v1, RATE_HT_MCS_MIMO2_MSK);
+		rate_v3 |= u32_encode_bits(nss, RATE_MCS_NSS_MSK);
+	} else if (rate_v1 & RATE_MCS_VHT_MSK_V1 ||
+		   rate_v1 & RATE_MCS_HE_MSK_V1) {
+		u32 nss = u32_get_bits(rate_v1, RATE_VHT_MCS_NSS_MSK);
+
+		rate_v3 |= rate_v1 & RATE_VHT_MCS_RATE_CODE_MSK;
+
+		rate_v3 |= u32_encode_bits(nss, RATE_MCS_NSS_MSK);
+
+		if (rate_v1 & RATE_MCS_HE_MSK_V1) {
+			u32 he_type_bits = rate_v1 & RATE_MCS_HE_TYPE_MSK_V1;
+			u32 he_type = he_type_bits >> RATE_MCS_HE_TYPE_POS_V1;
+			u32 he_106t = (rate_v1 & RATE_MCS_HE_106T_MSK_V1) >>
+				RATE_MCS_HE_106T_POS_V1;
+			u32 he_gi_ltf = (rate_v1 & RATE_MCS_HE_GI_LTF_MSK_V1) >>
+				RATE_MCS_HE_GI_LTF_POS;
+
+			if ((he_type_bits == RATE_MCS_HE_TYPE_SU ||
+			     he_type_bits == RATE_MCS_HE_TYPE_EXT_SU) &&
+			    he_gi_ltf == RATE_MCS_HE_SU_4_LTF)
+				/* the new rate have an additional bit to
+				 * represent the value 4 rather then using SGI
+				 * bit for this purpose - as it was done in the
+				 * old rate
+				 */
+				he_gi_ltf += (rate_v1 & RATE_MCS_SGI_MSK_V1) >>
+					RATE_MCS_SGI_POS_V1;
+
+			rate_v3 |= he_gi_ltf << RATE_MCS_HE_GI_LTF_POS;
+			rate_v3 |= he_type << RATE_MCS_HE_TYPE_POS;
+			rate_v3 |= he_106t << RATE_MCS_HE_106T_POS;
+			rate_v3 |= rate_v1 & RATE_HE_DUAL_CARRIER_MODE_MSK;
+			rate_v3 |= RATE_MCS_MOD_TYPE_HE;
+		} else {
+			rate_v3 |= RATE_MCS_MOD_TYPE_VHT;
+		}
+	/* if legacy format */
+	} else {
+		u32 legacy_rate = iwl_legacy_rate_to_fw_idx(rate_v1);
+
+		if (WARN_ON_ONCE(legacy_rate == IWL_RATE_INVALID))
+			legacy_rate = (rate_v1 & RATE_MCS_CCK_MSK_V1) ?
+				IWL_FIRST_CCK_RATE : IWL_FIRST_OFDM_RATE;
+
+		rate_v3 |= legacy_rate;
+		if (!(rate_v1 & RATE_MCS_CCK_MSK_V1))
+			rate_v3 |= RATE_MCS_MOD_TYPE_LEGACY_OFDM;
+	}
+
+	/* convert flags */
+	if (rate_v1 & RATE_MCS_LDPC_MSK_V1)
+		rate_v3 |= RATE_MCS_LDPC_MSK;
+	rate_v3 |= (rate_v1 & RATE_MCS_CHAN_WIDTH_MSK_V1) |
+		(rate_v1 & RATE_MCS_ANT_AB_MSK) |
+		(rate_v1 & RATE_MCS_STBC_MSK) |
+		(rate_v1 & RATE_MCS_BF_MSK);
+
+	dup = (rate_v1 & RATE_MCS_DUP_MSK_V1) >> RATE_MCS_DUP_POS_V1;
+	if (dup) {
+		rate_v3 |= RATE_MCS_DUP_MSK;
+		rate_v3 |= dup << RATE_MCS_CHAN_WIDTH_POS;
+	}
+
+	if ((!(rate_v1 & RATE_MCS_HE_MSK_V1)) &&
+	    (rate_v1 & RATE_MCS_SGI_MSK_V1))
+		rate_v3 |= RATE_MCS_SGI_MSK;
+
+	return rate_v3;
+}
+
+__le32 iwl_mvm_v3_rate_to_fw(u32 rate, u8 rate_ver)
+{
+	u32 result = 0;
+	int rate_idx;
+
+	if (rate_ver > 1)
+		return iwl_v3_rate_to_v2_v3(rate, rate_ver > 2);
+
+	switch (rate & RATE_MCS_MOD_TYPE_MSK) {
+	case RATE_MCS_MOD_TYPE_CCK:
+		result = RATE_MCS_CCK_MSK_V1;
+		fallthrough;
+	case RATE_MCS_MOD_TYPE_LEGACY_OFDM:
+		rate_idx = u32_get_bits(rate, RATE_LEGACY_RATE_MSK);
+		if (!(result & RATE_MCS_CCK_MSK_V1))
+			rate_idx += IWL_FIRST_OFDM_RATE;
+		result |= u32_encode_bits(iwl_fw_rate_idx_to_plcp(rate_idx),
+					  RATE_LEGACY_RATE_MSK_V1);
+		break;
+	case RATE_MCS_MOD_TYPE_HT:
+		result = RATE_MCS_HT_MSK_V1;
+		result |= u32_encode_bits(u32_get_bits(rate,
+						       RATE_HT_MCS_CODE_MSK),
+					  RATE_HT_MCS_RATE_CODE_MSK_V1);
+		result |= u32_encode_bits(u32_get_bits(rate,
+						       RATE_MCS_NSS_MSK),
+					  RATE_HT_MCS_MIMO2_MSK);
+		break;
+	case RATE_MCS_MOD_TYPE_VHT:
+		result = RATE_MCS_VHT_MSK_V1;
+		result |= u32_encode_bits(u32_get_bits(rate,
+						       RATE_VHT_MCS_NSS_MSK),
+					  RATE_MCS_CODE_MSK);
+		result |= u32_encode_bits(u32_get_bits(rate, RATE_MCS_NSS_MSK),
+					  RATE_VHT_MCS_NSS_MSK);
+		break;
+	case RATE_MCS_MOD_TYPE_HE: /* not generated */
+	default:
+		WARN_ONCE(1, "bad modulation type %d\n",
+			  u32_get_bits(rate, RATE_MCS_MOD_TYPE_MSK));
+		return 0;
+	}
+
+	if (rate & RATE_MCS_LDPC_MSK)
+		result |= RATE_MCS_LDPC_MSK_V1;
+	WARN_ON_ONCE(u32_get_bits(rate, RATE_MCS_CHAN_WIDTH_MSK) >
+			RATE_MCS_CHAN_WIDTH_160_VAL);
+	result |= (rate & RATE_MCS_CHAN_WIDTH_MSK_V1) |
+		  (rate & RATE_MCS_ANT_AB_MSK) |
+		  (rate & RATE_MCS_STBC_MSK) |
+		  (rate & RATE_MCS_BF_MSK);
+
+	/* not handling DUP since we don't use it */
+	WARN_ON_ONCE(rate & RATE_MCS_DUP_MSK);
+
+	if (rate & RATE_MCS_SGI_MSK)
+		result |= RATE_MCS_SGI_MSK_V1;
+
+	return cpu_to_le32(result);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
index ea81cb236d5c..69259ebb966b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
@@ -3,7 +3,7 @@
  *
  * Copyright(c) 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2017 Intel Deutschland GmbH
- * Copyright (C) 2003 - 2014, 2018 - 2024 Intel Corporation
+ * Copyright (C) 2003 - 2014, 2018 - 2025 Intel Corporation
  *****************************************************************************/
 
 #ifndef __rs_h__
@@ -424,6 +424,9 @@ void iwl_mvm_rate_control_unregister(void);
 
 struct iwl_mvm_sta;
 
+u32 iwl_mvm_v3_rate_from_fw(__le32 rate, u8 rate_ver);
+__le32 iwl_mvm_v3_rate_to_fw(u32 rate, u8 rate_ver);
+
 int iwl_mvm_tx_protection(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta,
 			  bool enable);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
index 2dbef7b46355..8eb0aa448c85 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -490,8 +490,6 @@ void iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct napi_struct *napi,
 	if (!(rate_n_flags & RATE_MCS_CCK_MSK_V1) &&
 	    rate_n_flags & RATE_MCS_SGI_MSK_V1)
 		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
-	if (rate_n_flags & RATE_HT_MCS_GF_MSK)
-		rx_status->enc_flags |= RX_ENC_FLAG_HT_GF;
 	if (rate_n_flags & RATE_MCS_LDPC_MSK_V1)
 		rx_status->enc_flags |= RX_ENC_FLAG_LDPC;
 	if (rate_n_flags & RATE_MCS_HT_MSK_V1) {
@@ -1001,7 +999,7 @@ static void iwl_mvm_update_esr_mode_tpt(struct iwl_mvm *mvm)
 	sec_link = mvmvif->link[sec_link]->fw_link_id;
 
 	/* Sum up RX and TX MPDUs from the different queues/links */
-	for (int q = 0; q < mvm->trans->num_rx_queues; q++) {
+	for (int q = 0; q < mvm->trans->info.num_rxqs; q++) {
 		spin_lock_bh(&mvmsta->mpdu_counters[q].lock);
 
 		/* The link IDs that doesn't exist will contain 0 */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 14ea89f931bb..077aadbf95db 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -171,7 +171,7 @@ static int iwl_mvm_create_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
 			      shdr->type != htons(ETH_P_PAE) &&
 			      shdr->type != htons(ETH_P_TDLS))))
 			skb->ip_summed = CHECKSUM_NONE;
-		else if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_BZ)
+		else if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_BZ)
 			/* mac80211 assumes full CSUM including SNAP header */
 			skb_postpush_rcsum(skb, shdr, sizeof(*shdr));
 	}
@@ -409,7 +409,7 @@ static int iwl_mvm_rx_crypto(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 		    !(status & IWL_RX_MPDU_RES_STATUS_TTAK_OK))
 			return 0;
 
-		if (mvm->trans->trans_cfg->gen2 &&
+		if (mvm->trans->mac_cfg->gen2 &&
 		    !(status & RX_MPDU_RES_STATUS_MIC_OK))
 			stats->flag |= RX_FLAG_MMIC_ERROR;
 
@@ -426,7 +426,7 @@ static int iwl_mvm_rx_crypto(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 
 		if (pkt_flags & FH_RSCSR_RADA_EN) {
 			stats->flag |= RX_FLAG_ICV_STRIPPED;
-			if (mvm->trans->trans_cfg->gen2)
+			if (mvm->trans->mac_cfg->gen2)
 				stats->flag |= RX_FLAG_MMIC_STRIPPED;
 		}
 
@@ -462,7 +462,7 @@ static void iwl_mvm_rx_csum(struct iwl_mvm *mvm,
 {
 	struct iwl_rx_mpdu_desc *desc = (void *)pkt->data;
 
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		if (pkt->len_n_flags & cpu_to_le32(FH_RSCSR_RPA_EN)) {
 			u16 hwsum = be16_to_cpu(desc->v3.raw_xsum);
 
@@ -744,7 +744,7 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
 	baid = (reorder & IWL_RX_MPDU_REORDER_BAID_MASK) >>
 		IWL_RX_MPDU_REORDER_BAID_SHIFT;
 
-	if (mvm->trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_9000)
+	if (mvm->trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_9000)
 		return false;
 
 	/*
@@ -1944,7 +1944,7 @@ static void iwl_mvm_rx_fill_status(struct iwl_mvm *mvm,
 	}
 
 	/* must be before L-SIG data */
-	if (format == RATE_MCS_HE_MSK)
+	if (format == RATE_MCS_MOD_TYPE_HE)
 		iwl_mvm_rx_he(mvm, skb, phy_data, queue);
 
 	iwl_mvm_decode_lsig(skb, phy_data);
@@ -1966,45 +1966,45 @@ static void iwl_mvm_rx_fill_status(struct iwl_mvm *mvm,
 				    phy_data->energy_a, phy_data->energy_b);
 
 	/* using TLV format and must be after all fixed len fields */
-	if (format == RATE_MCS_EHT_MSK)
+	if (format == RATE_MCS_MOD_TYPE_EHT)
 		iwl_mvm_rx_eht(mvm, skb, phy_data, queue);
 
 	if (unlikely(mvm->monitor_on))
 		iwl_mvm_add_rtap_sniffer_config(mvm, skb);
 
-	is_sgi = format == RATE_MCS_HE_MSK ?
+	is_sgi = format == RATE_MCS_MOD_TYPE_HE ?
 		iwl_he_is_sgi(rate_n_flags) :
 		rate_n_flags & RATE_MCS_SGI_MSK;
 
-	if (!(format == RATE_MCS_CCK_MSK) && is_sgi)
+	if (!(format == RATE_MCS_MOD_TYPE_CCK) && is_sgi)
 		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
 	if (rate_n_flags & RATE_MCS_LDPC_MSK)
 		rx_status->enc_flags |= RX_ENC_FLAG_LDPC;
 
 	switch (format) {
-	case RATE_MCS_VHT_MSK:
+	case RATE_MCS_MOD_TYPE_VHT:
 		rx_status->encoding = RX_ENC_VHT;
 		break;
-	case RATE_MCS_HE_MSK:
+	case RATE_MCS_MOD_TYPE_HE:
 		rx_status->encoding = RX_ENC_HE;
 		rx_status->he_dcm =
 			!!(rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK);
 		break;
-	case RATE_MCS_EHT_MSK:
+	case RATE_MCS_MOD_TYPE_EHT:
 		rx_status->encoding = RX_ENC_EHT;
 		break;
 	}
 
 	switch (format) {
-	case RATE_MCS_HT_MSK:
+	case RATE_MCS_MOD_TYPE_HT:
 		rx_status->encoding = RX_ENC_HT;
 		rx_status->rate_idx = RATE_HT_MCS_INDEX(rate_n_flags);
 		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
 		break;
-	case RATE_MCS_VHT_MSK:
-	case RATE_MCS_HE_MSK:
-	case RATE_MCS_EHT_MSK:
+	case RATE_MCS_MOD_TYPE_VHT:
+	case RATE_MCS_MOD_TYPE_HE:
+	case RATE_MCS_MOD_TYPE_EHT:
 		rx_status->nss =
 			u32_get_bits(rate_n_flags, RATE_MCS_NSS_MSK) + 1;
 		rx_status->rate_idx = rate_n_flags & RATE_MCS_CODE_MSK;
@@ -2048,7 +2048,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	if (unlikely(test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)))
 		return;
 
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 		desc_size = sizeof(*desc);
 	else
 		desc_size = IWL_RX_DESC_SIZE_V1;
@@ -2058,8 +2058,10 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		return;
 	}
 
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
-		phy_data.rate_n_flags = le32_to_cpu(desc->v3.rate_n_flags);
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+		phy_data.rate_n_flags =
+			iwl_mvm_v3_rate_from_fw(desc->v3.rate_n_flags,
+						mvm->fw_rates_ver);
 		phy_data.channel = desc->v3.channel;
 		phy_data.gp2_on_air_rise = le32_to_cpu(desc->v3.gp2_on_air_rise);
 		phy_data.energy_a = desc->v3.energy_a;
@@ -2072,7 +2074,9 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		phy_data.eht_d4 = desc->phy_eht_data4;
 		phy_data.d5 = desc->v3.phy_data5;
 	} else {
-		phy_data.rate_n_flags = le32_to_cpu(desc->v1.rate_n_flags);
+		phy_data.rate_n_flags =
+			iwl_mvm_v3_rate_from_fw(desc->v1.rate_n_flags,
+						mvm->fw_rates_ver);
 		phy_data.channel = desc->v1.channel;
 		phy_data.gp2_on_air_rise = le32_to_cpu(desc->v1.gp2_on_air_rise);
 		phy_data.energy_a = desc->v1.energy_a;
@@ -2084,13 +2088,6 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		phy_data.d3 = desc->v1.phy_data3;
 	}
 
-	if (iwl_fw_lookup_notif_ver(mvm->fw, LEGACY_GROUP,
-				    REPLY_RX_MPDU_CMD, 0) < 4) {
-		phy_data.rate_n_flags = iwl_new_rate_from_v1(phy_data.rate_n_flags);
-		IWL_DEBUG_DROP(mvm, "Got old format rate, converting. New rate: 0x%x\n",
-			       phy_data.rate_n_flags);
-	}
-
 	format = phy_data.rate_n_flags & RATE_MCS_MOD_TYPE_MSK;
 
 	len = le16_to_cpu(desc->mpdu_len);
@@ -2138,14 +2135,14 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	}
 
 	/* set the preamble flag if appropriate */
-	if (format == RATE_MCS_CCK_MSK &&
+	if (format == RATE_MCS_MOD_TYPE_CCK &&
 	    phy_data.phy_info & IWL_RX_MPDU_PHY_SHORT_PREAMBLE)
 		rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 
 	if (likely(!(phy_data.phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD))) {
 		u64 tsf_on_air_rise;
 
-		if (mvm->trans->trans_cfg->device_family >=
+		if (mvm->trans->mac_cfg->device_family >=
 		    IWL_DEVICE_FAMILY_AX210)
 			tsf_on_air_rise = le64_to_cpu(desc->v3.tsf_on_air_rise);
 		else
@@ -2157,7 +2154,8 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	}
 
 	if (iwl_mvm_is_band_in_rx_supported(mvm)) {
-		u8 band = BAND_IN_RX_STATUS(desc->mac_phy_idx);
+		u8 band = u8_get_bits(desc->mac_phy_band,
+				      IWL_RX_MPDU_MAC_PHY_BAND_BAND_MASK);
 
 		rx_status->band = iwl_mvm_nl80211_band_from_phy(band);
 	} else {
@@ -2303,7 +2301,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 
 			*qc &= ~IEEE80211_QOS_CTL_A_MSDU_PRESENT;
 
-			if (mvm->trans->trans_cfg->device_family ==
+			if (mvm->trans->mac_cfg->device_family ==
 			    IWL_DEVICE_FAMILY_9000) {
 				iwl_mvm_flip_address(hdr->addr3);
 
@@ -2349,7 +2347,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	if (!iwl_mvm_reorder(mvm, napi, queue, sta, skb, desc) &&
 	    likely(!iwl_mvm_time_sync_frame(mvm, skb, hdr->addr2)) &&
 	    likely(!iwl_mvm_mei_filter_scan(mvm, skb))) {
-		if (mvm->trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_9000 &&
+		if (mvm->trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_9000 &&
 		    (desc->mac_flags2 & IWL_RX_MPDU_MFLG2_AMSDU) &&
 		    !(desc->amsdu_info & IWL_RX_MPDU_AMSDU_LAST_SUBFRAME))
 			rx_status->flag |= RX_FLAG_AMSDU_MORE;
@@ -2383,7 +2381,6 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi,
 	phy_data.d1 = desc->phy_info[1];
 	phy_data.phy_info = IWL_RX_MPDU_PHY_TSF_OVERLOAD;
 	phy_data.gp2_on_air_rise = le32_to_cpu(desc->on_air_rise_time);
-	phy_data.rate_n_flags = le32_to_cpu(desc->rate);
 	phy_data.energy_a = u32_get_bits(rssi, RX_NO_DATA_CHAIN_A_MSK);
 	phy_data.energy_b = u32_get_bits(rssi, RX_NO_DATA_CHAIN_B_MSK);
 	phy_data.channel = u32_get_bits(rssi, RX_NO_DATA_CHANNEL_MSK);
@@ -2391,14 +2388,8 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi,
 	phy_data.rx_vec[0] = desc->rx_vec[0];
 	phy_data.rx_vec[1] = desc->rx_vec[1];
 
-	if (iwl_fw_lookup_notif_ver(mvm->fw, DATA_PATH_GROUP,
-				    RX_NO_DATA_NOTIF, 0) < 2) {
-		IWL_DEBUG_DROP(mvm, "Got an old rate format. Old rate: 0x%x\n",
-			       phy_data.rate_n_flags);
-		phy_data.rate_n_flags = iwl_new_rate_from_v1(phy_data.rate_n_flags);
-		IWL_DEBUG_DROP(mvm, " Rate after conversion to the new format: 0x%x\n",
-			       phy_data.rate_n_flags);
-	}
+	phy_data.rate_n_flags = iwl_mvm_v3_rate_from_fw(desc->rate,
+							mvm->fw_rates_ver);
 
 	format = phy_data.rate_n_flags & RATE_MCS_MOD_TYPE_MSK;
 
@@ -2411,7 +2402,7 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi,
 		phy_data.rx_vec[2] = desc->rx_vec[2];
 		phy_data.rx_vec[3] = desc->rx_vec[3];
 	} else {
-		if (format == RATE_MCS_EHT_MSK)
+		if (format == RATE_MCS_MOD_TYPE_EHT)
 			/* no support for EHT before version 3 API */
 			return;
 	}
@@ -2472,17 +2463,17 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi,
 	 * may be up to 8 spatial streams.
 	 */
 	switch (format) {
-	case RATE_MCS_VHT_MSK:
+	case RATE_MCS_MOD_TYPE_VHT:
 		rx_status->nss =
 			le32_get_bits(desc->rx_vec[0],
 				      RX_NO_DATA_RX_VEC0_VHT_NSTS_MSK) + 1;
 		break;
-	case RATE_MCS_HE_MSK:
+	case RATE_MCS_MOD_TYPE_HE:
 		rx_status->nss =
 			le32_get_bits(desc->rx_vec[0],
 				      RX_NO_DATA_RX_VEC0_HE_NSTS_MSK) + 1;
 		break;
-	case RATE_MCS_EHT_MSK:
+	case RATE_MCS_MOD_TYPE_EHT:
 		rx_status->nss =
 			le32_get_bits(desc->rx_vec[2],
 				      RX_NO_DATA_RX_VEC2_EHT_NSTS_MSK) + 1;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 78fd7faaed97..8ec4a007b4b0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2015, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2015, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -791,10 +791,10 @@ static int iwl_mvm_find_free_queue(struct iwl_mvm *mvm, u8 sta_id,
 
 	lockdep_assert_held(&mvm->mutex);
 
-	if (WARN(maxq >= mvm->trans->trans_cfg->base_params->num_of_queues,
+	if (WARN(maxq >= mvm->trans->mac_cfg->base->num_of_queues,
 		 "max queue %d >= num_of_queues (%d)", maxq,
-		 mvm->trans->trans_cfg->base_params->num_of_queues))
-		maxq = mvm->trans->trans_cfg->base_params->num_of_queues - 1;
+		 mvm->trans->mac_cfg->base->num_of_queues))
+		maxq = mvm->trans->mac_cfg->base->num_of_queues - 1;
 
 	/* This should not be hit with new TX path */
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
@@ -852,7 +852,7 @@ int iwl_mvm_tvqm_enable_txq(struct iwl_mvm *mvm,
 	if (tid == IWL_MAX_TID_COUNT) {
 		tid = IWL_MGMT_TID;
 		size = max_t(u32, IWL_MGMT_QUEUE_SIZE,
-			     mvm->trans->cfg->min_txq_size);
+			     mvm->trans->mac_cfg->base->min_txq_size);
 	} else {
 		size = iwl_mvm_get_queue_size(sta);
 	}
@@ -1765,7 +1765,7 @@ int iwl_mvm_sta_init(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		mvm_sta->deflink.sta_id = sta_id;
 		rcu_assign_pointer(mvm_sta->link[0], &mvm_sta->deflink);
 
-		if (!mvm->trans->trans_cfg->gen2)
+		if (!mvm->trans->mac_cfg->gen2)
 			mvm_sta->deflink.lq_sta.rs_drv.pers.max_agg_bufsize =
 				LINK_QUAL_AGG_FRAME_LIMIT_DEF;
 		else
@@ -1798,7 +1798,7 @@ int iwl_mvm_sta_init(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	if (iwl_mvm_has_new_rx_api(mvm)) {
 		int q;
 
-		dup_data = kcalloc(mvm->trans->num_rx_queues,
+		dup_data = kcalloc(mvm->trans->info.num_rxqs,
 				   sizeof(*dup_data), GFP_KERNEL);
 		if (!dup_data)
 			return -ENOMEM;
@@ -1811,7 +1811,7 @@ int iwl_mvm_sta_init(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		 * This thus allows receiving a packet with seqno 0 and the
 		 * retry bit set as the very first packet on a new TID.
 		 */
-		for (q = 0; q < mvm->trans->num_rx_queues; q++)
+		for (q = 0; q < mvm->trans->info.num_rxqs; q++)
 			memset(dup_data[q].last_seq, 0xff,
 			       sizeof(dup_data[q].last_seq));
 		mvm_sta->dup_data = dup_data;
@@ -1839,11 +1839,11 @@ int iwl_mvm_sta_init(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	if (vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
 	    !sta->tdls && ieee80211_vif_is_mld(vif)) {
 		mvm_sta->mpdu_counters =
-			kcalloc(mvm->trans->num_rx_queues,
+			kcalloc(mvm->trans->info.num_rxqs,
 				sizeof(*mvm_sta->mpdu_counters),
 				GFP_KERNEL);
 		if (mvm_sta->mpdu_counters)
-			for (int q = 0; q < mvm->trans->num_rx_queues; q++)
+			for (int q = 0; q < mvm->trans->info.num_rxqs; q++)
 				spin_lock_init(&mvm_sta->mpdu_counters[q].lock);
 	}
 
@@ -2189,7 +2189,7 @@ static void iwl_mvm_enable_aux_snif_queue(struct iwl_mvm *mvm, u16 queue,
 					  u8 sta_id, u8 fifo)
 {
 	unsigned int wdg_timeout =
-		mvm->trans->trans_cfg->base_params->wd_timeout;
+		mvm->trans->mac_cfg->base->wd_timeout;
 	struct iwl_trans_txq_scd_cfg cfg = {
 		.fifo = fifo,
 		.sta_id = sta_id,
@@ -2206,7 +2206,7 @@ static void iwl_mvm_enable_aux_snif_queue(struct iwl_mvm *mvm, u16 queue,
 static int iwl_mvm_enable_aux_snif_queue_tvqm(struct iwl_mvm *mvm, u8 sta_id)
 {
 	unsigned int wdg_timeout =
-		mvm->trans->trans_cfg->base_params->wd_timeout;
+		mvm->trans->mac_cfg->base->wd_timeout;
 
 	WARN_ON(!iwl_mvm_has_new_tx_api(mvm));
 
@@ -2717,7 +2717,7 @@ static void iwl_mvm_free_reorder(struct iwl_mvm *mvm,
 
 	iwl_mvm_sync_rxq_del_ba(mvm, data->baid);
 
-	for (i = 0; i < mvm->trans->num_rx_queues; i++) {
+	for (i = 0; i < mvm->trans->info.num_rxqs; i++) {
 		int j;
 		struct iwl_mvm_reorder_buffer *reorder_buf =
 			&data->reorder_buf[i];
@@ -2750,7 +2750,7 @@ static void iwl_mvm_init_reorder_buffer(struct iwl_mvm *mvm,
 {
 	int i;
 
-	for (i = 0; i < mvm->trans->num_rx_queues; i++) {
+	for (i = 0; i < mvm->trans->info.num_rxqs; i++) {
 		struct iwl_mvm_reorder_buffer *reorder_buf =
 			&data->reorder_buf[i];
 		struct iwl_mvm_reorder_buf_entry *entries =
@@ -2925,7 +2925,7 @@ int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 		 * before starting the BA session in the firmware
 		 */
 		baid_data = kzalloc(sizeof(*baid_data) +
-				    mvm->trans->num_rx_queues *
+				    mvm->trans->info.num_rxqs *
 				    reorder_buf_size,
 				    GFP_KERNEL);
 		if (!baid_data)
@@ -3177,7 +3177,7 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	 * to align the wrap around of ssn so we compare relevant values.
 	 */
 	normalized_ssn = tid_data->ssn;
-	if (mvm->trans->trans_cfg->gen2)
+	if (mvm->trans->mac_cfg->gen2)
 		normalized_ssn &= 0xff;
 
 	if (normalized_ssn == tid_data->next_reclaimed) {
@@ -4305,7 +4305,7 @@ u16 iwl_mvm_tid_queued(struct iwl_mvm *mvm, struct iwl_mvm_tid_data *tid_data)
 	 * In 22000 HW, the next_reclaimed index is only 8 bit, so we'll need
 	 * to align the wrap around of ssn so we compare relevant values.
 	 */
-	if (mvm->trans->trans_cfg->gen2)
+	if (mvm->trans->mac_cfg->gen2)
 		sn &= 0xff;
 
 	return ieee80211_sn_sub(sn, tid_data->next_reclaimed);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index 19c905b641e2..6b183f5e9bbc 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2016 Intel Deutschland GmbH
  */
@@ -225,8 +225,6 @@ struct iwl_mvm_vif;
  * @IWL_AGG_ON: aggregation session is up
  * @IWL_EMPTYING_HW_QUEUE_ADDBA: establishing a BA session - waiting for the
  *	HW queue to be empty from packets for this RA /TID.
- * @IWL_EMPTYING_HW_QUEUE_DELBA: tearing down a BA session - waiting for the
- *	HW queue to be empty from packets for this RA /TID.
  */
 enum iwl_mvm_agg_state {
 	IWL_AGG_OFF = 0,
@@ -234,7 +232,6 @@ enum iwl_mvm_agg_state {
 	IWL_AGG_STARTING,
 	IWL_AGG_ON,
 	IWL_EMPTYING_HW_QUEUE_ADDBA,
-	IWL_EMPTYING_HW_QUEUE_DELBA,
 };
 
 /**
@@ -262,7 +259,7 @@ struct iwl_mvm_tid_data {
 	u16 seq_number;
 	u16 next_reclaimed;
 	/* The rest is Tx AGG related */
-	u32 rate_n_flags;
+	__le32 rate_n_flags;
 	u8 lq_color;
 	bool amsdu_in_ampdu_allowed;
 	enum iwl_mvm_agg_state state;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tests/Makefile b/drivers/net/wireless/intel/iwlwifi/mvm/tests/Makefile
index 6bd56a28cffd..895d53f223e9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tests/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tests/Makefile
@@ -1,3 +1,3 @@
-iwlmvm-tests-y += module.o links.o scan.o
+iwlmvm-tests-y += module.o links.o scan.o hcmd.o
 
 obj-$(CONFIG_IWLWIFI_KUNIT_TESTS) += iwlmvm-tests.o
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tests/hcmd.c b/drivers/net/wireless/intel/iwlwifi/mvm/tests/hcmd.c
new file mode 100644
index 000000000000..1fee0320c756
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tests/hcmd.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * KUnit tests for channel helper functions
+ *
+ * Copyright (C) 2025 Intel Corporation
+ */
+#include <kunit/test.h>
+
+#include <iwl-trans.h>
+#include "../mvm.h"
+
+MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
+
+static void test_hcmd_names_sorted(struct kunit *test)
+{
+	for (int i = 0; i < iwl_mvm_groups_size; i++) {
+		const struct iwl_hcmd_arr *arr = &iwl_mvm_groups[i];
+
+		if (!arr->arr)
+			continue;
+
+		for (int j = 0; j < arr->size - 1; j++)
+			KUNIT_EXPECT_LE(test, arr->arr[j].cmd_id,
+					arr->arr[j + 1].cmd_id);
+	}
+}
+
+static struct kunit_case hcmd_names_cases[] = {
+	KUNIT_CASE(test_hcmd_names_sorted),
+	{},
+};
+
+static struct kunit_suite hcmd_names = {
+	.name = "iwlmvm-hcmd-names",
+	.test_cases = hcmd_names_cases,
+};
+
+kunit_test_suite(hcmd_names);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index 1a30bb1ff8ca..478408f802d9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -771,15 +771,17 @@ static void iwl_mvm_cancel_session_protection(struct iwl_mvm *mvm,
 
 static void iwl_mvm_roc_rm_cmd(struct iwl_mvm *mvm, u32 activity)
 {
-	struct iwl_roc_req_v5 roc_cmd = {
+	struct iwl_roc_req roc_cmd = {
 		.action = cpu_to_le32(FW_CTXT_ACTION_REMOVE),
 		.activity = cpu_to_le32(activity),
 	};
+	u8 ver = iwl_fw_lookup_cmd_ver(mvm->fw, WIDE_ID(MAC_CONF_GROUP, ROC_CMD), 0);
+	u16 cmd_len = ver < 6 ? sizeof(struct iwl_roc_req_v5) : sizeof(roc_cmd);
 	int ret;
 
 	lockdep_assert_held(&mvm->mutex);
 	ret = iwl_mvm_send_cmd_pdu(mvm, WIDE_ID(MAC_CONF_GROUP, ROC_CMD), 0,
-				   sizeof(roc_cmd), &roc_cmd);
+				   cmd_len, &roc_cmd);
 	if (ret)
 		IWL_ERR(mvm, "Couldn't send the ROC_CMD: %d\n", ret);
 }
@@ -1102,11 +1104,13 @@ int iwl_mvm_roc_add_cmd(struct iwl_mvm *mvm,
 {
 	int res;
 	u32 duration_tu, delay;
-	struct iwl_roc_req_v5 roc_req = {
+	struct iwl_roc_req roc_req = {
 		.action = cpu_to_le32(FW_CTXT_ACTION_ADD),
 		.activity = cpu_to_le32(activity),
 		.sta_id = cpu_to_le32(mvm->aux_sta.sta_id),
 	};
+	u8 ver = iwl_fw_lookup_cmd_ver(mvm->fw, WIDE_ID(MAC_CONF_GROUP, ROC_CMD), 0);
+	u16 cmd_len = ver < 6 ? sizeof(struct iwl_roc_req_v5) : sizeof(roc_req);
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 
 	lockdep_assert_held(&mvm->mutex);
@@ -1136,7 +1140,7 @@ int iwl_mvm_roc_add_cmd(struct iwl_mvm *mvm,
 	memcpy(roc_req.node_addr, vif->addr, ETH_ALEN);
 
 	res = iwl_mvm_send_cmd_pdu(mvm, WIDE_ID(MAC_CONF_GROUP, ROC_CMD),
-				   0, sizeof(roc_req), &roc_req);
+				   0, cmd_len, &roc_req);
 	if (!res)
 		mvmvif->roc_activity = activity;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
index c851290e75a2..53bab21ebae2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2019-2022, 2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2019-2022, 2024-2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2016 Intel Deutschland GmbH
  */
@@ -8,6 +8,9 @@
 
 #include "mvm.h"
 
+#define IWL_MVM_NUM_CTDP_STEPS		20
+#define IWL_MVM_MIN_CTDP_BUDGET_MW	150
+
 #define IWL_MVM_TEMP_NOTIF_WAIT_TIMEOUT	HZ
 
 void iwl_mvm_enter_ctkill(struct iwl_mvm *mvm)
@@ -479,43 +482,28 @@ static const struct iwl_tt_params iwl_mvm_default_tt_params = {
 	.support_tx_backoff = true,
 };
 
-/* budget in mWatt */
-static const u32 iwl_mvm_cdev_budgets[] = {
-	2400,	/* cooling state 0 */
-	2000,	/* cooling state 1 */
-	1800,	/* cooling state 2 */
-	1600,	/* cooling state 3 */
-	1400,	/* cooling state 4 */
-	1200,	/* cooling state 5 */
-	1000,	/* cooling state 6 */
-	900,	/* cooling state 7 */
-	800,	/* cooling state 8 */
-	700,	/* cooling state 9 */
-	650,	/* cooling state 10 */
-	600,	/* cooling state 11 */
-	550,	/* cooling state 12 */
-	500,	/* cooling state 13 */
-	450,	/* cooling state 14 */
-	400,	/* cooling state 15 */
-	350,	/* cooling state 16 */
-	300,	/* cooling state 17 */
-	250,	/* cooling state 18 */
-	200,	/* cooling state 19 */
-	150,	/* cooling state 20 */
-};
-
 int iwl_mvm_ctdp_command(struct iwl_mvm *mvm, u32 op, u32 state)
 {
 	struct iwl_ctdp_cmd cmd = {
 		.operation = cpu_to_le32(op),
-		.budget = cpu_to_le32(iwl_mvm_cdev_budgets[state]),
 		.window_size = 0,
 	};
+	u32 budget;
 	int ret;
 	u32 status;
 
 	lockdep_assert_held(&mvm->mutex);
 
+	/* Do a linear scale from IWL_MVM_MIN_CTDP_BUDGET_MW to the configured
+	 * maximum in the predefined number of steps.
+	 */
+	budget = ((mvm->thermal_throttle.power_budget_mw -
+		   IWL_MVM_MIN_CTDP_BUDGET_MW) *
+		  (IWL_MVM_NUM_CTDP_STEPS - 1 - state)) /
+		 (IWL_MVM_NUM_CTDP_STEPS - 1) +
+		 IWL_MVM_MIN_CTDP_BUDGET_MW;
+	cmd.budget = cpu_to_le32(budget);
+
 	status = 0;
 	ret = iwl_mvm_send_cmd_pdu_status(mvm, WIDE_ID(PHY_OPS_GROUP,
 						       CTDP_CONFIG_CMD),
@@ -552,8 +540,8 @@ int iwl_mvm_ctdp_command(struct iwl_mvm *mvm, u32 op, u32 state)
 #ifdef CONFIG_THERMAL
 static int compare_temps(const void *a, const void *b)
 {
-	return ((s16)le16_to_cpu(*(__le16 *)a) -
-		(s16)le16_to_cpu(*(__le16 *)b));
+	return ((s16)le16_to_cpu(*(const __le16 *)a) -
+		(s16)le16_to_cpu(*(const __le16 *)b));
 }
 
 struct iwl_trip_walk_data {
@@ -707,7 +695,7 @@ static void iwl_mvm_thermal_zone_register(struct iwl_mvm *mvm)
 static int iwl_mvm_tcool_get_max_state(struct thermal_cooling_device *cdev,
 				       unsigned long *state)
 {
-	*state = ARRAY_SIZE(iwl_mvm_cdev_budgets) - 1;
+	*state = IWL_MVM_NUM_CTDP_STEPS - 1;
 
 	return 0;
 }
@@ -733,7 +721,7 @@ static int iwl_mvm_tcool_set_cur_state(struct thermal_cooling_device *cdev,
 	    mvm->fwrt.cur_fw_img != IWL_UCODE_REGULAR)
 		return -EIO;
 
-	if (new_state >= ARRAY_SIZE(iwl_mvm_cdev_budgets))
+	if (new_state >= IWL_MVM_NUM_CTDP_STEPS)
 		return -EINVAL;
 
 	return iwl_mvm_ctdp_command(mvm, CTDP_CMD_OPERATION_START,
@@ -794,6 +782,47 @@ static void iwl_mvm_cooling_device_unregister(struct iwl_mvm *mvm)
 }
 #endif /* CONFIG_THERMAL */
 
+static u32 iwl_mvm_ctdp_get_max_budget(struct iwl_mvm *mvm)
+{
+	u64 bios_power_budget = 0;
+	u32 default_power_budget;
+
+	switch (CSR_HW_RFID_TYPE(mvm->trans->info.hw_rf_id)) {
+	case IWL_CFG_RF_TYPE_JF2:
+	case IWL_CFG_RF_TYPE_JF1:
+		default_power_budget = 2000;
+		break;
+	case IWL_CFG_RF_TYPE_HR2:
+	case IWL_CFG_RF_TYPE_HR1:
+		default_power_budget = 2400;
+		break;
+	case IWL_CFG_RF_TYPE_GF:
+		/* dual-radio devices have a higher budget */
+		if (CSR_HW_RFID_IS_CDB(mvm->trans->info.hw_rf_id))
+			default_power_budget = 5200;
+		else
+			default_power_budget = 2880;
+		break;
+	case IWL_CFG_RF_TYPE_FM:
+		default_power_budget = 3450;
+		break;
+	default:
+		default_power_budget = 5550;
+		break;
+	}
+
+	iwl_bios_get_pwr_limit(&mvm->fwrt, &bios_power_budget);
+
+	/* 32bit in UEFI, 16bit in ACPI; use BIOS value if it is in range */
+	if (bios_power_budget &&
+	    bios_power_budget != 0xffff && bios_power_budget != 0xffffffff &&
+	    bios_power_budget >= IWL_MVM_MIN_CTDP_BUDGET_MW &&
+	    bios_power_budget <= default_power_budget)
+		return (u32)bios_power_budget;
+
+	return default_power_budget;
+}
+
 void iwl_mvm_thermal_initialize(struct iwl_mvm *mvm, u32 min_backoff)
 {
 	struct iwl_mvm_tt_mgmt *tt = &mvm->thermal_throttle;
@@ -805,6 +834,8 @@ void iwl_mvm_thermal_initialize(struct iwl_mvm *mvm, u32 min_backoff)
 	else
 		tt->params = iwl_mvm_default_tt_params;
 
+	tt->power_budget_mw = iwl_mvm_ctdp_get_max_budget(mvm);
+	IWL_DEBUG_TEMP(mvm, "cTDP power budget: %d mW\n", tt->power_budget_mw);
 	tt->throttle = false;
 	tt->dynamic_smps = false;
 	tt->min_backoff = min_backoff;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index f67afb66ef2b..ac2cf1b8ce23 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -148,7 +148,7 @@ out:
  * Sets most of the Tx cmd's fields
  */
 void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb,
-			struct iwl_tx_cmd *tx_cmd,
+			struct iwl_tx_cmd_v6 *tx_cmd,
 			struct ieee80211_tx_info *info, u8 sta_id)
 {
 	struct ieee80211_hdr *hdr = (void *)skb->data;
@@ -283,14 +283,10 @@ static u32 iwl_mvm_convert_rate_idx(struct iwl_mvm *mvm,
 		 (rate_idx <= IWL_LAST_CCK_RATE);
 
 	/* Set CCK or OFDM flag */
-	if (iwl_fw_lookup_cmd_ver(mvm->fw, TX_CMD, 0) > 8) {
-		if (!is_cck)
-			rate_flags |= RATE_MCS_LEGACY_OFDM_MSK;
-		else
-			rate_flags |= RATE_MCS_CCK_MSK;
-	} else if (is_cck) {
-		rate_flags |= RATE_MCS_CCK_MSK_V1;
-	}
+	if (!is_cck)
+		rate_flags |= RATE_MCS_MOD_TYPE_LEGACY_OFDM;
+	else
+		rate_flags |= RATE_MCS_MOD_TYPE_CCK;
 
 	return (u32)rate_plcp | rate_flags;
 }
@@ -303,45 +299,35 @@ static u32 iwl_mvm_get_inject_tx_rate(struct iwl_mvm *mvm,
 	struct ieee80211_tx_rate *rate = &info->control.rates[0];
 	u32 result;
 
-	/*
-	 * we only care about legacy/HT/VHT so far, so we can
-	 * build in v1 and use iwl_new_rate_from_v1()
-	 */
-
 	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
 		u8 mcs = ieee80211_rate_get_vht_mcs(rate);
 		u8 nss = ieee80211_rate_get_vht_nss(rate);
 
-		result = RATE_MCS_VHT_MSK_V1;
+		result = RATE_MCS_MOD_TYPE_VHT;
 		result |= u32_encode_bits(mcs, RATE_VHT_MCS_RATE_CODE_MSK);
 		result |= u32_encode_bits(nss, RATE_MCS_NSS_MSK);
 		if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
-			result |= RATE_MCS_SGI_MSK_V1;
+			result |= RATE_MCS_SGI_MSK;
 		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-			result |= u32_encode_bits(1, RATE_MCS_CHAN_WIDTH_MSK_V1);
+			result |= RATE_MCS_CHAN_WIDTH_40;
 		else if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
-			result |= u32_encode_bits(2, RATE_MCS_CHAN_WIDTH_MSK_V1);
+			result |= RATE_MCS_CHAN_WIDTH_80;
 		else if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH)
-			result |= u32_encode_bits(3, RATE_MCS_CHAN_WIDTH_MSK_V1);
-
-		if (iwl_fw_lookup_notif_ver(mvm->fw, LONG_GROUP, TX_CMD, 0) > 6)
-			result = iwl_new_rate_from_v1(result);
+			result |= RATE_MCS_CHAN_WIDTH_160;
 	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
-		result = RATE_MCS_HT_MSK_V1;
-		result |= u32_encode_bits(rate->idx,
-					  RATE_HT_MCS_RATE_CODE_MSK_V1 |
-					  RATE_HT_MCS_NSS_MSK_V1);
+		result = RATE_MCS_MOD_TYPE_HT;
+		result |= u32_encode_bits(rate->idx & 0x7,
+					  RATE_HT_MCS_CODE_MSK);
+		result |= u32_encode_bits(rate->idx >> 3,
+					  RATE_MCS_NSS_MSK);
 		if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
-			result |= RATE_MCS_SGI_MSK_V1;
+			result |= RATE_MCS_SGI_MSK;
 		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-			result |= u32_encode_bits(1, RATE_MCS_CHAN_WIDTH_MSK_V1);
+			result |= RATE_MCS_CHAN_WIDTH_40;
 		if (info->flags & IEEE80211_TX_CTL_LDPC)
-			result |= RATE_MCS_LDPC_MSK_V1;
+			result |= RATE_MCS_LDPC_MSK;
 		if (u32_get_bits(info->flags, IEEE80211_TX_CTL_STBC))
 			result |= RATE_MCS_STBC_MSK;
-
-		if (iwl_fw_lookup_notif_ver(mvm->fw, LONG_GROUP, TX_CMD, 0) > 6)
-			result = iwl_new_rate_from_v1(result);
 	} else {
 		int rate_idx = info->control.rates[0].idx;
 
@@ -391,21 +377,25 @@ static u32 iwl_mvm_get_tx_rate(struct iwl_mvm *mvm,
 	return iwl_mvm_convert_rate_idx(mvm, info, rate_idx);
 }
 
-static u32 iwl_mvm_get_tx_rate_n_flags(struct iwl_mvm *mvm,
-				       struct ieee80211_tx_info *info,
-				       struct ieee80211_sta *sta, __le16 fc)
+static __le32 iwl_mvm_get_tx_rate_n_flags(struct iwl_mvm *mvm,
+					  struct ieee80211_tx_info *info,
+					  struct ieee80211_sta *sta, __le16 fc)
 {
+	u32 rate;
+
 	if (unlikely(info->control.flags & IEEE80211_TX_CTRL_RATE_INJECT))
-		return iwl_mvm_get_inject_tx_rate(mvm, info, sta, fc);
+		rate = iwl_mvm_get_inject_tx_rate(mvm, info, sta, fc);
+	else
+		rate = iwl_mvm_get_tx_rate(mvm, info, sta, fc) |
+		       iwl_mvm_get_tx_ant(mvm, info, sta, fc);
 
-	return iwl_mvm_get_tx_rate(mvm, info, sta, fc) |
-		iwl_mvm_get_tx_ant(mvm, info, sta, fc);
+	return iwl_mvm_v3_rate_to_fw(rate, mvm->fw_rates_ver);
 }
 
 /*
  * Sets the fields in the Tx cmd that are rate related
  */
-void iwl_mvm_set_tx_cmd_rate(struct iwl_mvm *mvm, struct iwl_tx_cmd *tx_cmd,
+void iwl_mvm_set_tx_cmd_rate(struct iwl_mvm *mvm, struct iwl_tx_cmd_v6 *tx_cmd,
 			    struct ieee80211_tx_info *info,
 			    struct ieee80211_sta *sta, __le16 fc)
 {
@@ -443,8 +433,7 @@ void iwl_mvm_set_tx_cmd_rate(struct iwl_mvm *mvm, struct iwl_tx_cmd *tx_cmd,
 	}
 
 	/* Set the rate in the TX cmd */
-	tx_cmd->rate_n_flags =
-		cpu_to_le32(iwl_mvm_get_tx_rate_n_flags(mvm, info, sta, fc));
+	tx_cmd->rate_n_flags = iwl_mvm_get_tx_rate_n_flags(mvm, info, sta, fc);
 }
 
 static inline void iwl_mvm_set_tx_cmd_pn(struct ieee80211_tx_info *info,
@@ -469,7 +458,7 @@ static inline void iwl_mvm_set_tx_cmd_pn(struct ieee80211_tx_info *info,
  */
 static void iwl_mvm_set_tx_cmd_crypto(struct iwl_mvm *mvm,
 				      struct ieee80211_tx_info *info,
-				      struct iwl_tx_cmd *tx_cmd,
+				      struct iwl_tx_cmd_v6 *tx_cmd,
 				      struct sk_buff *skb_frag,
 				      int hdrlen)
 {
@@ -543,7 +532,7 @@ static bool iwl_mvm_use_host_rate(struct iwl_mvm *mvm,
 	 * (since we don't necesarily know the link), but FW rate
 	 * selection was fixed.
 	 */
-	return mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_BZ;
+	return mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_BZ;
 }
 
 static void iwl_mvm_copy_hdr(void *cmd, const void *hdr, int hdrlen,
@@ -567,7 +556,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct iwl_device_tx_cmd *dev_cmd;
-	struct iwl_tx_cmd *tx_cmd;
+	struct iwl_tx_cmd_v6 *tx_cmd;
 
 	dev_cmd = iwl_trans_alloc_tx_cmd(mvm->trans);
 
@@ -577,7 +566,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 	dev_cmd->hdr.cmd = TX_CMD;
 
 	if (iwl_mvm_has_new_tx_api(mvm)) {
-		u32 rate_n_flags = 0;
+		__le32 rate_n_flags = 0;
 		u16 flags = 0;
 		struct iwl_mvm_sta *mvmsta = sta ?
 			iwl_mvm_sta_from_mac80211(sta) : NULL;
@@ -609,9 +598,9 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 			flags |= IWL_TX_FLAGS_HIGH_PRI;
 		}
 
-		if (mvm->trans->trans_cfg->device_family >=
+		if (mvm->trans->mac_cfg->device_family >=
 		    IWL_DEVICE_FAMILY_AX210) {
-			struct iwl_tx_cmd_gen3 *cmd = (void *)dev_cmd->payload;
+			struct iwl_tx_cmd *cmd = (void *)dev_cmd->payload;
 			u32 offload_assist = iwl_mvm_tx_csum(mvm, skb,
 							     info, amsdu);
 
@@ -624,9 +613,9 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 			iwl_mvm_copy_hdr(cmd->hdr, hdr, hdrlen, addr3_override);
 
 			cmd->flags = cpu_to_le16(flags);
-			cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
+			cmd->rate_n_flags = rate_n_flags;
 		} else {
-			struct iwl_tx_cmd_gen2 *cmd = (void *)dev_cmd->payload;
+			struct iwl_tx_cmd_v9 *cmd = (void *)dev_cmd->payload;
 			u16 offload_assist = iwl_mvm_tx_csum(mvm, skb,
 							     info, amsdu);
 
@@ -639,12 +628,12 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 			iwl_mvm_copy_hdr(cmd->hdr, hdr, hdrlen, addr3_override);
 
 			cmd->flags = cpu_to_le32(flags);
-			cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
+			cmd->rate_n_flags = rate_n_flags;
 		}
 		goto out;
 	}
 
-	tx_cmd = (struct iwl_tx_cmd *)dev_cmd->payload;
+	tx_cmd = (struct iwl_tx_cmd_v6 *)dev_cmd->payload;
 
 	if (info->control.hw_key)
 		iwl_mvm_set_tx_cmd_crypto(mvm, info, tx_cmd, skb, hdrlen);
@@ -1023,7 +1012,7 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb,
 	 *	1 more for the potential data in the header
 	 */
 	if ((num_subframes * 2 + skb_shinfo(skb)->nr_frags + 1) >
-	    mvm->trans->max_skb_frags)
+	    mvm->trans->info.max_skb_frags)
 		num_subframes = 1;
 
 	if (num_subframes > 1)
@@ -1185,7 +1174,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 		seq_number &= IEEE80211_SCTL_SEQ;
 
 		if (!iwl_mvm_has_new_tx_api(mvm)) {
-			struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
+			struct iwl_tx_cmd_v6 *tx_cmd = (void *)dev_cmd->payload;
 
 			hdr->seq_ctrl &= cpu_to_le16(IEEE80211_SCTL_FRAG);
 			hdr->seq_ctrl |= cpu_to_le16(seq_number);
@@ -1372,8 +1361,7 @@ static void iwl_mvm_check_ratid_empty(struct iwl_mvm *mvm,
 
 	lockdep_assert_held(&mvmsta->lock);
 
-	if ((tid_data->state == IWL_AGG_ON ||
-	     tid_data->state == IWL_EMPTYING_HW_QUEUE_DELBA) &&
+	if (tid_data->state == IWL_AGG_ON &&
 	    iwl_mvm_tid_queued(mvm, tid_data) == 0) {
 		/*
 		 * Now that this aggregation or DQA queue is empty tell
@@ -1388,7 +1376,7 @@ static void iwl_mvm_check_ratid_empty(struct iwl_mvm *mvm,
 	 * to align the wrap around of ssn so we compare relevant values.
 	 */
 	normalized_ssn = tid_data->ssn;
-	if (mvm->trans->trans_cfg->gen2)
+	if (mvm->trans->mac_cfg->gen2)
 		normalized_ssn &= 0xff;
 
 	if (normalized_ssn != tid_data->next_reclaimed)
@@ -1402,15 +1390,6 @@ static void iwl_mvm_check_ratid_empty(struct iwl_mvm *mvm,
 		tid_data->state = IWL_AGG_STARTING;
 		ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
-
-	case IWL_EMPTYING_HW_QUEUE_DELBA:
-		IWL_DEBUG_TX_QUEUES(mvm,
-				    "Can continue DELBA flow ssn = next_recl = %d\n",
-				    tid_data->next_reclaimed);
-		tid_data->state = IWL_AGG_OFF;
-		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
-		break;
-
 	default:
 		break;
 	}
@@ -1477,7 +1456,7 @@ void iwl_mvm_hwrate_to_tx_rate(u32 rate_n_flags,
 			       struct ieee80211_tx_rate *r)
 {
 	u32 format = rate_n_flags & RATE_MCS_MOD_TYPE_MSK;
-	u32 rate = format == RATE_MCS_HT_MSK ?
+	u32 rate = format == RATE_MCS_MOD_TYPE_HT ?
 		RATE_HT_MCS_INDEX(rate_n_flags) :
 		rate_n_flags & RATE_MCS_CODE_MSK;
 
@@ -1487,68 +1466,51 @@ void iwl_mvm_hwrate_to_tx_rate(u32 rate_n_flags,
 
 	if (rate_n_flags & RATE_MCS_SGI_MSK)
 		r->flags |= IEEE80211_TX_RC_SHORT_GI;
-	if (format ==  RATE_MCS_HT_MSK) {
+	switch (format) {
+	case RATE_MCS_MOD_TYPE_HT:
 		r->flags |= IEEE80211_TX_RC_MCS;
 		r->idx = rate;
-	} else if (format ==  RATE_MCS_VHT_MSK) {
+		break;
+	case RATE_MCS_MOD_TYPE_VHT:
 		ieee80211_rate_set_vht(r, rate,
 				       FIELD_GET(RATE_MCS_NSS_MSK,
 						 rate_n_flags) + 1);
 		r->flags |= IEEE80211_TX_RC_VHT_MCS;
-	} else if (format == RATE_MCS_HE_MSK) {
+		break;
+	case RATE_MCS_MOD_TYPE_HE:
+	case RATE_MCS_MOD_TYPE_EHT:
 		/* mac80211 cannot do this without ieee80211_tx_status_ext()
 		 * but it only matters for radiotap */
 		r->idx = 0;
-	} else {
+		break;
+	default:
 		r->idx = iwl_mvm_legacy_hw_idx_to_mac80211_idx(rate_n_flags,
 							       band);
 	}
 }
 
-void iwl_mvm_hwrate_to_tx_rate_v1(u32 rate_n_flags,
-				  enum nl80211_band band,
-				  struct ieee80211_tx_rate *r)
-{
-	if (rate_n_flags & RATE_HT_MCS_GF_MSK)
-		r->flags |= IEEE80211_TX_RC_GREEN_FIELD;
-
-	r->flags |=
-		iwl_mvm_get_hwrate_chan_width(rate_n_flags &
-					      RATE_MCS_CHAN_WIDTH_MSK_V1);
-
-	if (rate_n_flags & RATE_MCS_SGI_MSK_V1)
-		r->flags |= IEEE80211_TX_RC_SHORT_GI;
-	if (rate_n_flags & RATE_MCS_HT_MSK_V1) {
-		r->flags |= IEEE80211_TX_RC_MCS;
-		r->idx = rate_n_flags & RATE_HT_MCS_INDEX_MSK_V1;
-	} else if (rate_n_flags & RATE_MCS_VHT_MSK_V1) {
-		ieee80211_rate_set_vht(
-			r, rate_n_flags & RATE_VHT_MCS_RATE_CODE_MSK,
-			FIELD_GET(RATE_MCS_NSS_MSK, rate_n_flags) + 1);
-		r->flags |= IEEE80211_TX_RC_VHT_MCS;
-	} else {
-		r->idx = iwl_mvm_legacy_rate_to_mac80211_idx(rate_n_flags,
-							     band);
-	}
-}
-
 /*
  * translate ucode response to mac80211 tx status control values
  */
-static void iwl_mvm_hwrate_to_tx_status(const struct iwl_fw *fw,
-					u32 rate_n_flags,
+static void iwl_mvm_hwrate_to_tx_status(struct iwl_mvm *mvm,
+					__le32 rate_n_flags,
 					struct ieee80211_tx_info *info)
 {
 	struct ieee80211_tx_rate *r = &info->status.rates[0];
+	u32 rate;
 
-	if (iwl_fw_lookup_notif_ver(fw, LONG_GROUP,
-				    TX_CMD, 0) <= 6)
-		rate_n_flags = iwl_new_rate_from_v1(rate_n_flags);
+	/*
+	 * Technically this conversion is incorrect for BA status, however:
+	 *  - we only use the BA notif data for older firmware that have
+	 *    host rate scaling and don't use newer rate formats
+	 *  - the firmware API changed together for BA notif and TX CMD
+	 *    as well
+	 */
+	rate = iwl_mvm_v3_rate_from_fw(rate_n_flags, mvm->fw_rates_ver);
 
 	info->status.antenna =
-		((rate_n_flags & RATE_MCS_ANT_AB_MSK) >> RATE_MCS_ANT_POS);
-	iwl_mvm_hwrate_to_tx_rate(rate_n_flags,
-				  info->band, r);
+		((rate & RATE_MCS_ANT_AB_MSK) >> RATE_MCS_ANT_POS);
+	iwl_mvm_hwrate_to_tx_rate(rate, info->band, r);
 }
 
 static void iwl_mvm_tx_status_check_trigger(struct iwl_mvm *mvm,
@@ -1613,7 +1575,7 @@ static inline u32 iwl_mvm_get_scd_ssn(struct iwl_mvm *mvm,
 	u32 val = le32_to_cpup((__le32 *)iwl_mvm_get_agg_status(mvm, tx_resp) +
 			       tx_resp->frame_count);
 
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 		return val & 0xFFFF;
 	return val & 0xFFF;
 }
@@ -1700,9 +1662,7 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 
 		info->status.rates[0].count = tx_resp->failure_frame + 1;
 
-		iwl_mvm_hwrate_to_tx_status(mvm->fw,
-					    le32_to_cpu(tx_resp->initial_rate),
-					    info);
+		iwl_mvm_hwrate_to_tx_status(mvm, tx_resp->initial_rate, info);
 
 		/* Don't assign the converted initial_rate, because driver
 		 * TLC uses this and doesn't support the new FW rate
@@ -1944,7 +1904,7 @@ static void iwl_mvm_rx_tx_cmd_agg(struct iwl_mvm *mvm,
 
 	if (!WARN_ON_ONCE(!mvmsta)) {
 		mvmsta->tid_data[tid].rate_n_flags =
-			le32_to_cpu(tx_resp->initial_rate);
+			tx_resp->initial_rate;
 		mvmsta->tid_data[tid].tx_time =
 			le16_to_cpu(tx_resp->wireless_media_time);
 		mvmsta->tid_data[tid].lq_color =
@@ -1969,7 +1929,7 @@ void iwl_mvm_rx_tx_cmd(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 
 static void iwl_mvm_tx_reclaim(struct iwl_mvm *mvm, int sta_id, int tid,
 			       int txq, int index,
-			       struct ieee80211_tx_info *tx_info, u32 rate,
+			       struct ieee80211_tx_info *tx_info, __le32 rate,
 			       bool is_flush)
 {
 	struct sk_buff_head reclaimed_skbs;
@@ -2053,7 +2013,9 @@ static void iwl_mvm_tx_reclaim(struct iwl_mvm *mvm, int sta_id, int tid,
 	tx_info->status.status_driver_data[0] =
 		RS_DRV_DATA_PACK(tid_data->lq_color,
 				 tx_info->status.status_driver_data[0]);
-	tx_info->status.status_driver_data[1] = (void *)(uintptr_t)rate;
+	/* the value is only consumed for old FW that has v1 rates anyway */
+	tx_info->status.status_driver_data[1] =
+		(void *)(uintptr_t)le32_to_cpu(rate);
 
 	skb_queue_walk(&reclaimed_skbs, skb) {
 		struct ieee80211_hdr *hdr = (void *)skb->data;
@@ -2072,7 +2034,7 @@ static void iwl_mvm_tx_reclaim(struct iwl_mvm *mvm, int sta_id, int tid,
 			info->flags |= IEEE80211_TX_STAT_AMPDU;
 			memcpy(&info->status, &tx_info->status,
 			       sizeof(tx_info->status));
-			iwl_mvm_hwrate_to_tx_status(mvm->fw, rate, info);
+			iwl_mvm_hwrate_to_tx_status(mvm, rate, info);
 		}
 	}
 
@@ -2095,7 +2057,7 @@ static void iwl_mvm_tx_reclaim(struct iwl_mvm *mvm, int sta_id, int tid,
 			goto out;
 
 		tx_info->band = chanctx_conf->def.chan->band;
-		iwl_mvm_hwrate_to_tx_status(mvm->fw, rate, tx_info);
+		iwl_mvm_hwrate_to_tx_status(mvm, rate, tx_info);
 
 		IWL_DEBUG_TX_REPLY(mvm, "No reclaim. Update rs directly\n");
 		iwl_mvm_rs_tx_status(mvm, sta, tid, tx_info, false);
@@ -2184,7 +2146,7 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 					   (int)(le16_to_cpu(ba_tfd->q_num)),
 					   le16_to_cpu(ba_tfd->tfd_index),
 					   &ba_info,
-					   le32_to_cpu(ba_res->tx_rate), false);
+					   ba_res->tx_rate, false);
 		}
 
 		if (mvmsta) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index dd890dcd1505..62da0132f383 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -142,7 +142,7 @@ int iwl_mvm_legacy_hw_idx_to_mac80211_idx(u32 rate_n_flags,
 	int rate = rate_n_flags & RATE_LEGACY_RATE_MSK;
 	bool is_LB = band == NL80211_BAND_2GHZ;
 
-	if (format == RATE_MCS_LEGACY_OFDM_MSK)
+	if (format == RATE_MCS_MOD_TYPE_LEGACY_OFDM)
 		return is_LB ? rate + IWL_FIRST_OFDM_RATE :
 			rate;
 
@@ -169,15 +169,9 @@ int iwl_mvm_legacy_rate_to_mac80211_idx(u32 rate_n_flags,
 
 u8 iwl_mvm_mac80211_idx_to_hwrate(const struct iwl_fw *fw, int rate_idx)
 {
-	if (iwl_fw_lookup_cmd_ver(fw, TX_CMD, 0) > 8)
-		/* In the new rate legacy rates are indexed:
-		 * 0 - 3 for CCK and 0 - 7 for OFDM.
-		 */
-		return (rate_idx >= IWL_FIRST_OFDM_RATE ?
-			rate_idx - IWL_FIRST_OFDM_RATE :
-			rate_idx);
-
-	return iwl_fw_rate_idx_to_plcp(rate_idx);
+	return (rate_idx >= IWL_FIRST_OFDM_RATE ?
+		rate_idx - IWL_FIRST_OFDM_RATE :
+		rate_idx);
 }
 
 u8 iwl_mvm_mac80211_ac_to_ucode_ac(enum ieee80211_ac_numbers ac)
@@ -748,7 +742,7 @@ unsigned int iwl_mvm_get_wd_timeout(struct iwl_mvm *mvm,
 				    struct ieee80211_vif *vif)
 {
 	unsigned int default_timeout =
-		mvm->trans->trans_cfg->base_params->wd_timeout;
+		mvm->trans->mac_cfg->base->wd_timeout;
 
 	/*
 	 * We can't know when the station is asleep or awake, so we
@@ -1187,9 +1181,9 @@ u32 iwl_mvm_get_systime(struct iwl_mvm *mvm)
 {
 	u32 reg_addr = DEVICE_SYSTEM_TIME_REG;
 
-	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000 &&
-	    mvm->trans->cfg->gp2_reg_addr)
-		reg_addr = mvm->trans->cfg->gp2_reg_addr;
+	if (mvm->trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_22000 &&
+	    mvm->trans->mac_cfg->base->gp2_reg_addr)
+		reg_addr = mvm->trans->mac_cfg->base->gp2_reg_addr;
 
 	return iwl_read_prph(mvm->trans, reg_addr);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-v2.c
index 8aa7c455bdee..976fd1f58da4 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-v2.c
@@ -5,7 +5,7 @@
 #include <linux/dmi.h>
 #include "iwl-trans.h"
 #include "iwl-fh.h"
-#include "iwl-context-info-gen3.h"
+#include "iwl-context-info-v2.h"
 #include "internal.h"
 #include "iwl-prph.h"
 
@@ -97,11 +97,12 @@ out:
 		*control_flags |= IWL_PRPH_SCRATCH_EARLY_DEBUG_EN | dbg_flags;
 }
 
-int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
-				 const struct fw_img *fw)
+int iwl_pcie_ctxt_info_v2_alloc(struct iwl_trans *trans,
+				const struct iwl_fw *fw,
+				const struct fw_img *img)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_context_info_gen3 *ctxt_info_gen3;
+	struct iwl_context_info_v2 *ctxt_info_v2;
 	struct iwl_prph_scratch *prph_scratch;
 	struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl;
 	struct iwl_prph_info *prph_info;
@@ -109,9 +110,9 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 	u32 control_flags_ext = 0;
 	int ret;
 	int cmdq_size = max_t(u32, IWL_CMD_QUEUE_SIZE,
-			      trans->cfg->min_txq_size);
+			      trans->mac_cfg->base->min_txq_size);
 
-	switch (trans_pcie->rx_buf_size) {
+	switch (trans->conf.rx_buf_size) {
 	case IWL_AMSDU_DEF:
 		return -EINVAL;
 	case IWL_AMSDU_2K:
@@ -131,13 +132,13 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 		break;
 	}
 
-	if (trans->dsbr_urm_fw_dependent)
+	if (trans->conf.dsbr_urm_fw_dependent)
 		control_flags_ext |= IWL_PRPH_SCRATCH_EXT_URM_FW;
 
-	if (trans->dsbr_urm_permanent)
+	if (trans->conf.dsbr_urm_permanent)
 		control_flags_ext |= IWL_PRPH_SCRATCH_EXT_URM_PERM;
 
-	if (trans->ext_32khz_clock_valid)
+	if (trans->conf.ext_32khz_clock_valid)
 		control_flags_ext |= IWL_PRPH_SCRATCH_EXT_32KHZ_CLK_VALID;
 
 	/* Allocate prph scratch */
@@ -151,16 +152,16 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 
 	prph_sc_ctrl->version.version = 0;
 	prph_sc_ctrl->version.mac_id =
-		cpu_to_le16((u16)trans->hw_rev);
+		cpu_to_le16((u16)trans->info.hw_rev);
 	prph_sc_ctrl->version.size = cpu_to_le16(sizeof(*prph_scratch) / 4);
 
 	control_flags |= IWL_PRPH_SCRATCH_MTR_MODE;
 	control_flags |= IWL_PRPH_MTR_FORMAT_256B & IWL_PRPH_SCRATCH_MTR_FORMAT;
 
-	if (trans->trans_cfg->imr_enabled)
+	if (trans->mac_cfg->imr_enabled)
 		control_flags |= IWL_PRPH_SCRATCH_IMR_DEBUG_EN;
 
-	if (CSR_HW_REV_TYPE(trans->hw_rev) == IWL_CFG_MAC_TYPE_GL &&
+	if (CSR_HW_REV_TYPE(trans->info.hw_rev) == IWL_CFG_MAC_TYPE_GL &&
 	    iwl_is_force_scu_active_approved()) {
 		control_flags |= IWL_PRPH_SCRATCH_SCU_FORCE_ACTIVE;
 		IWL_DEBUG_FW(trans,
@@ -168,6 +169,11 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 			     IWL_PRPH_SCRATCH_SCU_FORCE_ACTIVE);
 	}
 
+	if (trans->do_top_reset) {
+		WARN_ON(trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_SC);
+		control_flags |= IWL_PRPH_SCRATCH_TOP_RESET;
+	}
+
 	/* initialize RX default queue */
 	prph_sc_ctrl->rbd_cfg.free_rbd_addr =
 		cpu_to_le64(trans_pcie->rxq->bd_dma);
@@ -178,15 +184,16 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 	prph_sc_ctrl->control.control_flags_ext = cpu_to_le32(control_flags_ext);
 
 	/* initialize the Step equalizer data */
-	prph_sc_ctrl->step_cfg.mbx_addr_0 = cpu_to_le32(trans->mbx_addr_0_step);
-	prph_sc_ctrl->step_cfg.mbx_addr_1 = cpu_to_le32(trans->mbx_addr_1_step);
+	prph_sc_ctrl->step_cfg.mbx_addr_0 =
+		cpu_to_le32(trans->conf.mbx_addr_0_step);
+	prph_sc_ctrl->step_cfg.mbx_addr_1 =
+		cpu_to_le32(trans->conf.mbx_addr_1_step);
 
 	/* allocate ucode sections in dram and set addresses */
-	ret = iwl_pcie_init_fw_sec(trans, fw, &prph_scratch->dram);
+	ret = iwl_pcie_init_fw_sec(trans, img, &prph_scratch->dram.common);
 	if (ret)
 		goto err_free_prph_scratch;
 
-
 	/* Allocate prph information
 	 * currently we don't assign to the prph info anything, but it would get
 	 * assigned later
@@ -206,42 +213,58 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 	}
 
 	/* Allocate context info */
-	ctxt_info_gen3 = dma_alloc_coherent(trans->dev,
-					    sizeof(*ctxt_info_gen3),
-					    &trans_pcie->ctxt_info_dma_addr,
-					    GFP_KERNEL);
-	if (!ctxt_info_gen3) {
+	ctxt_info_v2 = dma_alloc_coherent(trans->dev,
+					  sizeof(*ctxt_info_v2),
+					  &trans_pcie->ctxt_info_dma_addr,
+					  GFP_KERNEL);
+	if (!ctxt_info_v2) {
 		ret = -ENOMEM;
 		goto err_free_prph_info;
 	}
 
-	ctxt_info_gen3->prph_info_base_addr =
+	ctxt_info_v2->prph_info_base_addr =
 		cpu_to_le64(trans_pcie->prph_info_dma_addr);
-	ctxt_info_gen3->prph_scratch_base_addr =
+	ctxt_info_v2->prph_scratch_base_addr =
 		cpu_to_le64(trans_pcie->prph_scratch_dma_addr);
-	ctxt_info_gen3->prph_scratch_size =
-		cpu_to_le32(sizeof(*prph_scratch));
-	ctxt_info_gen3->cr_head_idx_arr_base_addr =
+
+	/*
+	 * This code assumes the FSEQ is last and we can make that
+	 * optional; old devices _should_ be fine with a bigger size,
+	 * but in simulation we check the size more precisely.
+	 */
+	BUILD_BUG_ON(offsetofend(typeof(*prph_scratch), dram.common) +
+		     sizeof(prph_scratch->dram.fseq_img) !=
+		     sizeof(*prph_scratch));
+	if (control_flags_ext & IWL_PRPH_SCRATCH_EXT_EXT_FSEQ)
+		ctxt_info_v2->prph_scratch_size =
+			cpu_to_le32(sizeof(*prph_scratch));
+	else
+		ctxt_info_v2->prph_scratch_size =
+			cpu_to_le32(offsetofend(typeof(*prph_scratch),
+						dram.common));
+
+	ctxt_info_v2->cr_head_idx_arr_base_addr =
 		cpu_to_le64(trans_pcie->rxq->rb_stts_dma);
-	ctxt_info_gen3->tr_tail_idx_arr_base_addr =
+	ctxt_info_v2->tr_tail_idx_arr_base_addr =
 		cpu_to_le64(trans_pcie->prph_info_dma_addr + PAGE_SIZE / 2);
-	ctxt_info_gen3->cr_tail_idx_arr_base_addr =
+	ctxt_info_v2->cr_tail_idx_arr_base_addr =
 		cpu_to_le64(trans_pcie->prph_info_dma_addr + 3 * PAGE_SIZE / 4);
-	ctxt_info_gen3->mtr_base_addr =
-		cpu_to_le64(trans_pcie->txqs.txq[trans_pcie->txqs.cmd.q_id]->dma_addr);
-	ctxt_info_gen3->mcr_base_addr =
+	ctxt_info_v2->mtr_base_addr =
+		cpu_to_le64(trans_pcie->txqs.txq[trans->conf.cmd_queue]->dma_addr);
+	ctxt_info_v2->mcr_base_addr =
 		cpu_to_le64(trans_pcie->rxq->used_bd_dma);
-	ctxt_info_gen3->mtr_size =
+	ctxt_info_v2->mtr_size =
 		cpu_to_le16(TFD_QUEUE_CB_SIZE(cmdq_size));
-	ctxt_info_gen3->mcr_size =
-		cpu_to_le16(RX_QUEUE_CB_SIZE(trans->cfg->num_rbds));
+	ctxt_info_v2->mcr_size =
+		cpu_to_le16(RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans)));
 
-	trans_pcie->ctxt_info_gen3 = ctxt_info_gen3;
+	trans_pcie->ctxt_info_v2 = ctxt_info_v2;
 	trans_pcie->prph_info = prph_info;
 	trans_pcie->prph_scratch = prph_scratch;
 
 	/* Allocate IML */
-	trans_pcie->iml = dma_alloc_coherent(trans->dev, trans->iml_len,
+	trans_pcie->iml_len = fw->iml_len;
+	trans_pcie->iml = dma_alloc_coherent(trans->dev, fw->iml_len,
 					     &trans_pcie->iml_dma_addr,
 					     GFP_KERNEL);
 	if (!trans_pcie->iml) {
@@ -249,27 +272,15 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 		goto err_free_ctxt_info;
 	}
 
-	memcpy(trans_pcie->iml, trans->iml, trans->iml_len);
-
-	iwl_enable_fw_load_int_ctx_info(trans);
-
-	/* kick FW self load */
-	iwl_write64(trans, CSR_CTXT_INFO_ADDR,
-		    trans_pcie->ctxt_info_dma_addr);
-	iwl_write64(trans, CSR_IML_DATA_ADDR,
-		    trans_pcie->iml_dma_addr);
-	iwl_write32(trans, CSR_IML_SIZE_ADDR, trans->iml_len);
-
-	iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL,
-		    CSR_AUTO_FUNC_BOOT_ENA);
+	memcpy(trans_pcie->iml, fw->iml, fw->iml_len);
 
 	return 0;
 
 err_free_ctxt_info:
-	dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info_gen3),
-			  trans_pcie->ctxt_info_gen3,
+	dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info_v2),
+			  trans_pcie->ctxt_info_v2,
 			  trans_pcie->ctxt_info_dma_addr);
-	trans_pcie->ctxt_info_gen3 = NULL;
+	trans_pcie->ctxt_info_v2 = NULL;
 err_free_prph_info:
 	dma_free_coherent(trans->dev, PAGE_SIZE, prph_info,
 			  trans_pcie->prph_info_dma_addr);
@@ -283,14 +294,31 @@ err_free_prph_scratch:
 
 }
 
-void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans, bool alive)
+void iwl_pcie_ctxt_info_v2_kick(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	iwl_enable_fw_load_int_ctx_info(trans, trans->do_top_reset);
+
+	/* kick FW self load */
+	iwl_write64(trans, CSR_CTXT_INFO_ADDR, trans_pcie->ctxt_info_dma_addr);
+	iwl_write64(trans, CSR_IML_DATA_ADDR, trans_pcie->iml_dma_addr);
+	iwl_write32(trans, CSR_IML_SIZE_ADDR, trans_pcie->iml_len);
+
+	iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL,
+		    CSR_AUTO_FUNC_BOOT_ENA);
+}
+
+void iwl_pcie_ctxt_info_v2_free(struct iwl_trans *trans, bool alive)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
 	if (trans_pcie->iml) {
-		dma_free_coherent(trans->dev, trans->iml_len, trans_pcie->iml,
+		dma_free_coherent(trans->dev, trans_pcie->iml_len,
+				  trans_pcie->iml,
 				  trans_pcie->iml_dma_addr);
 		trans_pcie->iml_dma_addr = 0;
+		trans_pcie->iml_len = 0;
 		trans_pcie->iml = NULL;
 	}
 
@@ -299,15 +327,15 @@ void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans, bool alive)
 	if (alive)
 		return;
 
-	if (!trans_pcie->ctxt_info_gen3)
+	if (!trans_pcie->ctxt_info_v2)
 		return;
 
-	/* ctxt_info_gen3 and prph_scratch are still needed for PNVM load */
-	dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info_gen3),
-			  trans_pcie->ctxt_info_gen3,
+	/* ctxt_info_v2 and prph_scratch are still needed for PNVM load */
+	dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info_v2),
+			  trans_pcie->ctxt_info_v2,
 			  trans_pcie->ctxt_info_dma_addr);
 	trans_pcie->ctxt_info_dma_addr = 0;
-	trans_pcie->ctxt_info_gen3 = NULL;
+	trans_pcie->ctxt_info_v2 = NULL;
 
 	dma_free_coherent(trans->dev, sizeof(*trans_pcie->prph_scratch),
 			  trans_pcie->prph_scratch,
@@ -322,9 +350,9 @@ void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans, bool alive)
 	trans_pcie->prph_info = NULL;
 }
 
-static int iwl_pcie_load_payloads_continuously(struct iwl_trans *trans,
-					       const struct iwl_pnvm_image *pnvm_data,
-					       struct iwl_dram_data *dram)
+static int iwl_pcie_load_payloads_contig(struct iwl_trans *trans,
+					 const struct iwl_pnvm_image *pnvm_data,
+					 struct iwl_dram_data *dram)
 {
 	u32 len, len0, len1;
 
@@ -411,9 +439,9 @@ static int iwl_pcie_load_payloads_segments
 
 }
 
-int iwl_trans_pcie_ctx_info_gen3_load_pnvm(struct iwl_trans *trans,
-					   const struct iwl_pnvm_image *pnvm_payloads,
-					   const struct iwl_ucode_capabilities *capa)
+int iwl_trans_pcie_ctx_info_v2_load_pnvm(struct iwl_trans *trans,
+					 const struct iwl_pnvm_image *pnvm_payloads,
+					 const struct iwl_ucode_capabilities *capa)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl =
@@ -428,7 +456,7 @@ int iwl_trans_pcie_ctx_info_gen3_load_pnvm(struct iwl_trans *trans,
 	if (WARN_ON(prph_sc_ctrl->pnvm_cfg.pnvm_size))
 		return -EBUSY;
 
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		return 0;
 
 	if (!pnvm_payloads->n_chunks) {
@@ -445,10 +473,8 @@ int iwl_trans_pcie_ctx_info_gen3_load_pnvm(struct iwl_trans *trans,
 			trans->pnvm_loaded = true;
 	} else {
 		/* save only in one DRAM section */
-		ret = iwl_pcie_load_payloads_continuously
-						(trans,
-						 pnvm_payloads,
-						 &dram_regions->drams[0]);
+		ret = iwl_pcie_load_payloads_contig(trans, pnvm_payloads,
+						    &dram_regions->drams[0]);
 		if (!ret) {
 			dram_regions->n_regions = 1;
 			trans->pnvm_loaded = true;
@@ -483,7 +509,7 @@ static void iwl_pcie_set_pnvm_segments(struct iwl_trans *trans)
 		cpu_to_le32(iwl_dram_regions_size(dram_regions));
 }
 
-static void iwl_pcie_set_continuous_pnvm(struct iwl_trans *trans)
+static void iwl_pcie_set_contig_pnvm(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl =
@@ -495,21 +521,21 @@ static void iwl_pcie_set_continuous_pnvm(struct iwl_trans *trans)
 		cpu_to_le32(trans_pcie->pnvm_data.drams[0].size);
 }
 
-void iwl_trans_pcie_ctx_info_gen3_set_pnvm(struct iwl_trans *trans,
-					   const struct iwl_ucode_capabilities *capa)
+void iwl_trans_pcie_ctx_info_v2_set_pnvm(struct iwl_trans *trans,
+					 const struct iwl_ucode_capabilities *capa)
 {
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		return;
 
 	if (fw_has_capa(capa, IWL_UCODE_TLV_CAPA_FRAGMENTED_PNVM_IMG))
 		iwl_pcie_set_pnvm_segments(trans);
 	else
-		iwl_pcie_set_continuous_pnvm(trans);
+		iwl_pcie_set_contig_pnvm(trans);
 }
 
-int iwl_trans_pcie_ctx_info_gen3_load_reduce_power(struct iwl_trans *trans,
-						   const struct iwl_pnvm_image *payloads,
-						   const struct iwl_ucode_capabilities *capa)
+int iwl_trans_pcie_ctx_info_v2_load_reduce_power(struct iwl_trans *trans,
+						 const struct iwl_pnvm_image *payloads,
+						 const struct iwl_ucode_capabilities *capa)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl =
@@ -521,7 +547,7 @@ int iwl_trans_pcie_ctx_info_gen3_load_reduce_power(struct iwl_trans *trans,
 	if (trans->reduce_power_loaded)
 		return 0;
 
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		return 0;
 
 	if (WARN_ON(prph_sc_ctrl->reduce_power_cfg.size))
@@ -541,10 +567,8 @@ int iwl_trans_pcie_ctx_info_gen3_load_reduce_power(struct iwl_trans *trans,
 			trans->reduce_power_loaded = true;
 	} else {
 		/* save only in one DRAM section */
-		ret = iwl_pcie_load_payloads_continuously
-						(trans,
-						 payloads,
-						 &dram_regions->drams[0]);
+		ret = iwl_pcie_load_payloads_contig(trans, payloads,
+						    &dram_regions->drams[0]);
 		if (!ret) {
 			dram_regions->n_regions = 1;
 			trans->reduce_power_loaded = true;
@@ -567,7 +591,7 @@ static void iwl_pcie_set_reduce_power_segments(struct iwl_trans *trans)
 		cpu_to_le32(iwl_dram_regions_size(dram_regions));
 }
 
-static void iwl_pcie_set_continuous_reduce_power(struct iwl_trans *trans)
+static void iwl_pcie_set_contig_reduce_power(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl =
@@ -580,15 +604,15 @@ static void iwl_pcie_set_continuous_reduce_power(struct iwl_trans *trans)
 }
 
 void
-iwl_trans_pcie_ctx_info_gen3_set_reduce_power(struct iwl_trans *trans,
-					      const struct iwl_ucode_capabilities *capa)
+iwl_trans_pcie_ctx_info_v2_set_reduce_power(struct iwl_trans *trans,
+					    const struct iwl_ucode_capabilities *capa)
 {
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		return;
 
 	if (fw_has_capa(capa, IWL_UCODE_TLV_CAPA_FRAGMENTED_PNVM_IMG))
 		iwl_pcie_set_reduce_power_segments(trans);
 	else
-		iwl_pcie_set_continuous_reduce_power(trans);
+		iwl_pcie_set_contig_reduce_power(trans);
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
index 344e4d5a1c6e..cb36baac14da 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include "iwl-trans.h"
 #include "iwl-fh.h"
@@ -83,7 +83,7 @@ void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans)
 
 int iwl_pcie_init_fw_sec(struct iwl_trans *trans,
 			 const struct fw_img *fw,
-			 struct iwl_context_info_dram *ctxt_dram)
+			 struct iwl_context_info_dram_nonfseq *ctxt_dram)
 {
 	struct iwl_self_init_dram *dram = &trans->init_dram;
 	int i, ret, lmac_cnt, umac_cnt, paging_cnt;
@@ -161,7 +161,7 @@ int iwl_pcie_init_fw_sec(struct iwl_trans *trans,
 }
 
 int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
-			    const struct fw_img *fw)
+			    const struct fw_img *img)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_context_info *ctxt_info;
@@ -180,11 +180,11 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 
 	ctxt_info->version.version = 0;
 	ctxt_info->version.mac_id =
-		cpu_to_le16((u16)trans->hw_rev);
+		cpu_to_le16((u16)trans->info.hw_rev);
 	/* size is in DWs */
 	ctxt_info->version.size = cpu_to_le16(sizeof(*ctxt_info) / 4);
 
-	switch (trans_pcie->rx_buf_size) {
+	switch (trans->conf.rx_buf_size) {
 	case IWL_AMSDU_2K:
 		rb_size = IWL_CTXT_INFO_RB_SIZE_2K;
 		break;
@@ -202,10 +202,10 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 		rb_size = IWL_CTXT_INFO_RB_SIZE_4K;
 	}
 
-	WARN_ON(RX_QUEUE_CB_SIZE(trans->cfg->num_rbds) > 12);
+	WARN_ON(RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans)) > 12);
 	control_flags = IWL_CTXT_INFO_TFD_FORMAT_LONG;
 	control_flags |=
-		u32_encode_bits(RX_QUEUE_CB_SIZE(trans->cfg->num_rbds),
+		u32_encode_bits(RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans)),
 				IWL_CTXT_INFO_RB_CB_SIZE);
 	control_flags |= u32_encode_bits(rb_size, IWL_CTXT_INFO_RB_SIZE);
 	ctxt_info->control.control_flags = cpu_to_le32(control_flags);
@@ -218,12 +218,12 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 
 	/* initialize TX command queue */
 	ctxt_info->hcmd_cfg.cmd_queue_addr =
-		cpu_to_le64(trans_pcie->txqs.txq[trans_pcie->txqs.cmd.q_id]->dma_addr);
+		cpu_to_le64(trans_pcie->txqs.txq[trans->conf.cmd_queue]->dma_addr);
 	ctxt_info->hcmd_cfg.cmd_queue_size =
 		TFD_QUEUE_CB_SIZE(IWL_CMD_QUEUE_SIZE);
 
 	/* allocate ucode sections in dram and set addresses */
-	ret = iwl_pcie_init_fw_sec(trans, fw, &ctxt_info->dram);
+	ret = iwl_pcie_init_fw_sec(trans, img, &ctxt_info->dram);
 	if (ret) {
 		dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info),
 				  ctxt_info, trans_pcie->ctxt_info_dma_addr);
@@ -232,7 +232,7 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 
 	trans_pcie->ctxt_info = ctxt_info;
 
-	iwl_enable_fw_load_int_ctx_info(trans);
+	iwl_enable_fw_load_int_ctx_info(trans, false);
 
 	/* Configure debug, if exists */
 	if (iwl_pcie_dbg_on(trans))
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 93446c374008..656f8b06c27b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -17,15 +17,13 @@
 #include "iwl-prph.h"
 #include "internal.h"
 
-#define TRANS_CFG_MARKER BIT(0)
 #define _IS_A(cfg, _struct) __builtin_types_compatible_p(typeof(cfg),	\
 							 struct _struct)
 extern int _invalid_type;
-#define _TRANS_CFG_MARKER(cfg)						\
-	(__builtin_choose_expr(_IS_A(cfg, iwl_cfg_trans_params),	\
-			       TRANS_CFG_MARKER,			\
-	 __builtin_choose_expr(_IS_A(cfg, iwl_cfg), 0, _invalid_type)))
-#define _ASSIGN_CFG(cfg) (_TRANS_CFG_MARKER(cfg) + (kernel_ulong_t)&(cfg))
+#define _TRANS_CFG_CHECK(cfg)						\
+	(__builtin_choose_expr(_IS_A(cfg, iwl_mac_cfg),	\
+			       0, _invalid_type))
+#define _ASSIGN_CFG(cfg) (_TRANS_CFG_CHECK(cfg) + (kernel_ulong_t)&(cfg))
 
 #define IWL_PCI_DEVICE(dev, subdev, cfg) \
 	.vendor = PCI_VENDOR_ID_INTEL,  .device = (dev), \
@@ -35,515 +33,518 @@ extern int _invalid_type;
 /* Hardware specific file defines the PCI IDs table for that hardware module */
 VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = {
 #if IS_ENABLED(CONFIG_IWLDVM)
-	{IWL_PCI_DEVICE(0x4232, 0x1201, iwl5100_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1301, iwl5100_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1204, iwl5100_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1304, iwl5100_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1205, iwl5100_bgn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1305, iwl5100_bgn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1206, iwl5100_abg_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1306, iwl5100_abg_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1221, iwl5100_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1321, iwl5100_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1224, iwl5100_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1324, iwl5100_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1225, iwl5100_bgn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1325, iwl5100_bgn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1226, iwl5100_abg_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4232, 0x1326, iwl5100_abg_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4237, 0x1211, iwl5100_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4237, 0x1311, iwl5100_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4237, 0x1214, iwl5100_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4237, 0x1314, iwl5100_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4237, 0x1215, iwl5100_bgn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4237, 0x1315, iwl5100_bgn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4237, 0x1216, iwl5100_abg_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4237, 0x1316, iwl5100_abg_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1201, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1301, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1204, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1304, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1205, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1305, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1206, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1306, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1221, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1321, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1224, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1324, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1225, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1325, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1226, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4232, 0x1326, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4237, 0x1211, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4237, 0x1311, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4237, 0x1214, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4237, 0x1314, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4237, 0x1215, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4237, 0x1315, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4237, 0x1216, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4237, 0x1316, iwl5000_mac_cfg)}, /* Half Mini Card */
 
 /* 5300 Series WiFi */
-	{IWL_PCI_DEVICE(0x4235, 0x1021, iwl5300_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4235, 0x1121, iwl5300_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4235, 0x1024, iwl5300_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4235, 0x1124, iwl5300_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4235, 0x1001, iwl5300_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4235, 0x1101, iwl5300_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4235, 0x1004, iwl5300_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4235, 0x1104, iwl5300_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4236, 0x1011, iwl5300_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4236, 0x1111, iwl5300_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x4236, 0x1014, iwl5300_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x4236, 0x1114, iwl5300_agn_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4235, 0x1021, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4235, 0x1121, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4235, 0x1024, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4235, 0x1124, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4235, 0x1001, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4235, 0x1101, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4235, 0x1004, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4235, 0x1104, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4236, 0x1011, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4236, 0x1111, iwl5000_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x4236, 0x1014, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x4236, 0x1114, iwl5000_mac_cfg)}, /* Half Mini Card */
 
 /* 5350 Series WiFi/WiMax */
-	{IWL_PCI_DEVICE(0x423A, 0x1001, iwl5350_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x423A, 0x1021, iwl5350_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x423B, 0x1011, iwl5350_agn_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x423A, 0x1001, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x423A, 0x1021, iwl5000_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x423B, 0x1011, iwl5000_mac_cfg)}, /* Mini Card */
 
 /* 5150 Series Wifi/WiMax */
-	{IWL_PCI_DEVICE(0x423C, 0x1201, iwl5150_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x423C, 0x1301, iwl5150_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x423C, 0x1206, iwl5150_abg_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x423C, 0x1306, iwl5150_abg_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x423C, 0x1221, iwl5150_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x423C, 0x1321, iwl5150_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x423C, 0x1326, iwl5150_abg_cfg)}, /* Half Mini Card */
-
-	{IWL_PCI_DEVICE(0x423D, 0x1211, iwl5150_agn_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x423D, 0x1311, iwl5150_agn_cfg)}, /* Half Mini Card */
-	{IWL_PCI_DEVICE(0x423D, 0x1216, iwl5150_abg_cfg)}, /* Mini Card */
-	{IWL_PCI_DEVICE(0x423D, 0x1316, iwl5150_abg_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x423C, 0x1201, iwl5150_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x423C, 0x1301, iwl5150_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x423C, 0x1206, iwl5150_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x423C, 0x1306, iwl5150_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x423C, 0x1221, iwl5150_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x423C, 0x1321, iwl5150_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x423C, 0x1326, iwl5150_mac_cfg)}, /* Half Mini Card */
+
+	{IWL_PCI_DEVICE(0x423D, 0x1211, iwl5150_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x423D, 0x1311, iwl5150_mac_cfg)}, /* Half Mini Card */
+	{IWL_PCI_DEVICE(0x423D, 0x1216, iwl5150_mac_cfg)}, /* Mini Card */
+	{IWL_PCI_DEVICE(0x423D, 0x1316, iwl5150_mac_cfg)}, /* Half Mini Card */
 
 /* 6x00 Series */
-	{IWL_PCI_DEVICE(0x422B, 0x1101, iwl6000_3agn_cfg)},
-	{IWL_PCI_DEVICE(0x422B, 0x1108, iwl6000_3agn_cfg)},
-	{IWL_PCI_DEVICE(0x422B, 0x1121, iwl6000_3agn_cfg)},
-	{IWL_PCI_DEVICE(0x422B, 0x1128, iwl6000_3agn_cfg)},
-	{IWL_PCI_DEVICE(0x422C, 0x1301, iwl6000i_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x422C, 0x1306, iwl6000i_2abg_cfg)},
-	{IWL_PCI_DEVICE(0x422C, 0x1307, iwl6000i_2bg_cfg)},
-	{IWL_PCI_DEVICE(0x422C, 0x1321, iwl6000i_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x422C, 0x1326, iwl6000i_2abg_cfg)},
-	{IWL_PCI_DEVICE(0x4238, 0x1111, iwl6000_3agn_cfg)},
-	{IWL_PCI_DEVICE(0x4238, 0x1118, iwl6000_3agn_cfg)},
-	{IWL_PCI_DEVICE(0x4239, 0x1311, iwl6000i_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x4239, 0x1316, iwl6000i_2abg_cfg)},
+	{IWL_PCI_DEVICE(0x422B, 0x1101, iwl6000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x422B, 0x1108, iwl6000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x422B, 0x1121, iwl6000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x422B, 0x1128, iwl6000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x422C, 0x1301, iwl6000i_mac_cfg)},
+	{IWL_PCI_DEVICE(0x422C, 0x1306, iwl6000i_mac_cfg)},
+	{IWL_PCI_DEVICE(0x422C, 0x1307, iwl6000i_mac_cfg)},
+	{IWL_PCI_DEVICE(0x422C, 0x1321, iwl6000i_mac_cfg)},
+	{IWL_PCI_DEVICE(0x422C, 0x1326, iwl6000i_mac_cfg)},
+	{IWL_PCI_DEVICE(0x4238, 0x1111, iwl6000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x4238, 0x1118, iwl6000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x4239, 0x1311, iwl6000i_mac_cfg)},
+	{IWL_PCI_DEVICE(0x4239, 0x1316, iwl6000i_mac_cfg)},
 
 /* 6x05 Series */
-	{IWL_PCI_DEVICE(0x0082, 0x1301, iwl6005_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0082, 0x1306, iwl6005_2abg_cfg)},
-	{IWL_PCI_DEVICE(0x0082, 0x1307, iwl6005_2bg_cfg)},
-	{IWL_PCI_DEVICE(0x0082, 0x1308, iwl6005_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0082, 0x1321, iwl6005_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0082, 0x1326, iwl6005_2abg_cfg)},
-	{IWL_PCI_DEVICE(0x0082, 0x1328, iwl6005_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0085, 0x1311, iwl6005_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0085, 0x1318, iwl6005_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0085, 0x1316, iwl6005_2abg_cfg)},
-	{IWL_PCI_DEVICE(0x0082, 0xC020, iwl6005_2agn_sff_cfg)},
-	{IWL_PCI_DEVICE(0x0085, 0xC220, iwl6005_2agn_sff_cfg)},
-	{IWL_PCI_DEVICE(0x0085, 0xC228, iwl6005_2agn_sff_cfg)},
-	{IWL_PCI_DEVICE(0x0082, 0x4820, iwl6005_2agn_d_cfg)},
-	{IWL_PCI_DEVICE(0x0082, 0x1304, iwl6005_2agn_mow1_cfg)},/* low 5GHz active */
-	{IWL_PCI_DEVICE(0x0082, 0x1305, iwl6005_2agn_mow2_cfg)},/* high 5GHz active */
+	{IWL_PCI_DEVICE(0x0082, 0x1301, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0082, 0x1306, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0082, 0x1307, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0082, 0x1308, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0082, 0x1321, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0082, 0x1326, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0082, 0x1328, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0085, 0x1311, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0085, 0x1318, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0085, 0x1316, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0082, 0xC020, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0085, 0xC220, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0085, 0xC228, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0082, 0x4820, iwl6005_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0082, 0x1304, iwl6005_mac_cfg)},/* low 5GHz active */
+	{IWL_PCI_DEVICE(0x0082, 0x1305, iwl6005_mac_cfg)},/* high 5GHz active */
 
 /* 6x30 Series */
-	{IWL_PCI_DEVICE(0x008A, 0x5305, iwl1030_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x008A, 0x5307, iwl1030_bg_cfg)},
-	{IWL_PCI_DEVICE(0x008A, 0x5325, iwl1030_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x008A, 0x5327, iwl1030_bg_cfg)},
-	{IWL_PCI_DEVICE(0x008B, 0x5315, iwl1030_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x008B, 0x5317, iwl1030_bg_cfg)},
-	{IWL_PCI_DEVICE(0x0090, 0x5211, iwl6030_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0090, 0x5215, iwl6030_2bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0090, 0x5216, iwl6030_2abg_cfg)},
-	{IWL_PCI_DEVICE(0x0091, 0x5201, iwl6030_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0091, 0x5205, iwl6030_2bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0091, 0x5206, iwl6030_2abg_cfg)},
-	{IWL_PCI_DEVICE(0x0091, 0x5207, iwl6030_2bg_cfg)},
-	{IWL_PCI_DEVICE(0x0091, 0x5221, iwl6030_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0091, 0x5225, iwl6030_2bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0091, 0x5226, iwl6030_2abg_cfg)},
+	{IWL_PCI_DEVICE(0x008A, 0x5305, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x008A, 0x5307, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x008A, 0x5325, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x008A, 0x5327, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x008B, 0x5315, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x008B, 0x5317, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0090, 0x5211, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0090, 0x5215, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0090, 0x5216, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0091, 0x5201, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0091, 0x5205, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0091, 0x5206, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0091, 0x5207, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0091, 0x5221, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0091, 0x5225, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0091, 0x5226, iwl6030_mac_cfg)},
 
 /* 6x50 WiFi/WiMax Series */
-	{IWL_PCI_DEVICE(0x0087, 0x1301, iwl6050_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0087, 0x1306, iwl6050_2abg_cfg)},
-	{IWL_PCI_DEVICE(0x0087, 0x1321, iwl6050_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0087, 0x1326, iwl6050_2abg_cfg)},
-	{IWL_PCI_DEVICE(0x0089, 0x1311, iwl6050_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x0089, 0x1316, iwl6050_2abg_cfg)},
+	{IWL_PCI_DEVICE(0x0087, 0x1301, iwl6050_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0087, 0x1306, iwl6050_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0087, 0x1321, iwl6050_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0087, 0x1326, iwl6050_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0089, 0x1311, iwl6050_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0089, 0x1316, iwl6050_mac_cfg)},
 
 /* 6150 WiFi/WiMax Series */
-	{IWL_PCI_DEVICE(0x0885, 0x1305, iwl6150_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0885, 0x1307, iwl6150_bg_cfg)},
-	{IWL_PCI_DEVICE(0x0885, 0x1325, iwl6150_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0885, 0x1327, iwl6150_bg_cfg)},
-	{IWL_PCI_DEVICE(0x0886, 0x1315, iwl6150_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0886, 0x1317, iwl6150_bg_cfg)},
+	{IWL_PCI_DEVICE(0x0885, 0x1305, iwl6150_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0885, 0x1307, iwl6150_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0885, 0x1325, iwl6150_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0885, 0x1327, iwl6150_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0886, 0x1315, iwl6150_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0886, 0x1317, iwl6150_mac_cfg)},
 
 /* 1000 Series WiFi */
-	{IWL_PCI_DEVICE(0x0083, 0x1205, iwl1000_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0083, 0x1305, iwl1000_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0083, 0x1225, iwl1000_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0083, 0x1325, iwl1000_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0084, 0x1215, iwl1000_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0084, 0x1315, iwl1000_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0083, 0x1206, iwl1000_bg_cfg)},
-	{IWL_PCI_DEVICE(0x0083, 0x1306, iwl1000_bg_cfg)},
-	{IWL_PCI_DEVICE(0x0083, 0x1226, iwl1000_bg_cfg)},
-	{IWL_PCI_DEVICE(0x0083, 0x1326, iwl1000_bg_cfg)},
-	{IWL_PCI_DEVICE(0x0084, 0x1216, iwl1000_bg_cfg)},
-	{IWL_PCI_DEVICE(0x0084, 0x1316, iwl1000_bg_cfg)},
+	{IWL_PCI_DEVICE(0x0083, 0x1205, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0083, 0x1305, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0083, 0x1225, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0083, 0x1325, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0084, 0x1215, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0084, 0x1315, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0083, 0x1206, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0083, 0x1306, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0083, 0x1226, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0083, 0x1326, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0084, 0x1216, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0084, 0x1316, iwl1000_mac_cfg)},
 
 /* 100 Series WiFi */
-	{IWL_PCI_DEVICE(0x08AE, 0x1005, iwl100_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x08AE, 0x1007, iwl100_bg_cfg)},
-	{IWL_PCI_DEVICE(0x08AF, 0x1015, iwl100_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x08AF, 0x1017, iwl100_bg_cfg)},
-	{IWL_PCI_DEVICE(0x08AE, 0x1025, iwl100_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x08AE, 0x1027, iwl100_bg_cfg)},
+	{IWL_PCI_DEVICE(0x08AE, 0x1005, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08AE, 0x1007, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08AF, 0x1015, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08AF, 0x1017, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08AE, 0x1025, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08AE, 0x1027, iwl1000_mac_cfg)},
 
 /* 130 Series WiFi */
-	{IWL_PCI_DEVICE(0x0896, 0x5005, iwl130_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0896, 0x5007, iwl130_bg_cfg)},
-	{IWL_PCI_DEVICE(0x0897, 0x5015, iwl130_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0897, 0x5017, iwl130_bg_cfg)},
-	{IWL_PCI_DEVICE(0x0896, 0x5025, iwl130_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0896, 0x5027, iwl130_bg_cfg)},
+	{IWL_PCI_DEVICE(0x0896, 0x5005, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0896, 0x5007, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0897, 0x5015, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0897, 0x5017, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0896, 0x5025, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0896, 0x5027, iwl1000_mac_cfg)},
 
 /* 2x00 Series */
-	{IWL_PCI_DEVICE(0x0890, 0x4022, iwl2000_2bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0891, 0x4222, iwl2000_2bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0890, 0x4422, iwl2000_2bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0890, 0x4822, iwl2000_2bgn_d_cfg)},
+	{IWL_PCI_DEVICE(0x0890, 0x4022, iwl2000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0891, 0x4222, iwl2000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0890, 0x4422, iwl2000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0890, 0x4822, iwl2000_mac_cfg)},
 
 /* 2x30 Series */
-	{IWL_PCI_DEVICE(0x0887, 0x4062, iwl2030_2bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0888, 0x4262, iwl2030_2bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0887, 0x4462, iwl2030_2bgn_cfg)},
+	{IWL_PCI_DEVICE(0x0887, 0x4062, iwl2030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0888, 0x4262, iwl2030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0887, 0x4462, iwl2030_mac_cfg)},
 
 /* 6x35 Series */
-	{IWL_PCI_DEVICE(0x088E, 0x4060, iwl6035_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x088E, 0x406A, iwl6035_2agn_sff_cfg)},
-	{IWL_PCI_DEVICE(0x088F, 0x4260, iwl6035_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x088F, 0x426A, iwl6035_2agn_sff_cfg)},
-	{IWL_PCI_DEVICE(0x088E, 0x4460, iwl6035_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x088E, 0x446A, iwl6035_2agn_sff_cfg)},
-	{IWL_PCI_DEVICE(0x088E, 0x4860, iwl6035_2agn_cfg)},
-	{IWL_PCI_DEVICE(0x088F, 0x5260, iwl6035_2agn_cfg)},
+	{IWL_PCI_DEVICE(0x088E, 0x4060, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x088E, 0x406A, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x088F, 0x4260, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x088F, 0x426A, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x088E, 0x4460, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x088E, 0x446A, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x088E, 0x4860, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x088F, 0x5260, iwl6030_mac_cfg)},
 
 /* 105 Series */
-	{IWL_PCI_DEVICE(0x0894, 0x0022, iwl105_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0895, 0x0222, iwl105_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0894, 0x0422, iwl105_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0894, 0x0822, iwl105_bgn_d_cfg)},
+	{IWL_PCI_DEVICE(0x0894, 0x0022, iwl105_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0895, 0x0222, iwl105_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0894, 0x0422, iwl105_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0894, 0x0822, iwl105_mac_cfg)},
 
 /* 135 Series */
-	{IWL_PCI_DEVICE(0x0892, 0x0062, iwl135_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0893, 0x0262, iwl135_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0892, 0x0462, iwl135_bgn_cfg)},
+	{IWL_PCI_DEVICE(0x0892, 0x0062, iwl135_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0893, 0x0262, iwl135_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0892, 0x0462, iwl135_mac_cfg)},
 #endif /* CONFIG_IWLDVM */
 
 #if IS_ENABLED(CONFIG_IWLMVM)
 /* 7260 Series */
-	{IWL_PCI_DEVICE(0x08B1, 0x4070, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4072, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4170, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4C60, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4C70, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4060, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x406A, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4160, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4062, iwl7260_n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4162, iwl7260_n_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0x4270, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0x4272, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0x4260, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0x426A, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0x4262, iwl7260_n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4470, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4472, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4460, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x446A, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4462, iwl7260_n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4870, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x486E, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4A70, iwl7260_2ac_cfg_high_temp)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4A6E, iwl7260_2ac_cfg_high_temp)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4A6C, iwl7260_2ac_cfg_high_temp)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4570, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4560, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0x4370, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0x4360, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x5070, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x5072, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x5170, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x5770, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4020, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x402A, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0x4220, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0x4420, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC070, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC072, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC170, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC060, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC06A, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC160, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC062, iwl7260_n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC162, iwl7260_n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC770, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC760, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0xC270, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xCC70, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xCC60, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0xC272, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0xC260, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0xC26A, iwl7260_n_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0xC262, iwl7260_n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC470, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC472, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC460, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC462, iwl7260_n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC570, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC560, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0xC370, iwl7260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC360, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC020, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC02A, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B2, 0xC220, iwl7260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B1, 0xC420, iwl7260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4070, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4072, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4170, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4C60, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4C70, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4060, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x406A, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4160, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4062, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4162, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4270, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4272, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4260, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x426A, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4262, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4470, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4472, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4460, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x446A, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4462, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4870, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x486E, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4A70, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4A6E, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4A6C, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4570, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4560, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4370, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4360, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x5070, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x5072, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x5170, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x5770, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4020, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x402A, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0x4220, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4420, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC070, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC072, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC170, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC060, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC06A, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC160, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC062, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC162, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC770, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC760, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC270, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xCC70, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xCC60, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC272, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC260, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC26A, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC262, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC470, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC472, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC460, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC462, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC570, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC560, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC370, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC360, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC020, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC02A, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B2, 0xC220, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xC420, iwl7000_mac_cfg)},
 
 /* 3160 Series */
-	{IWL_PCI_DEVICE(0x08B3, 0x0070, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x0072, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x0170, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x0172, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x0060, iwl3160_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x0062, iwl3160_n_cfg)},
-	{IWL_PCI_DEVICE(0x08B4, 0x0270, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B4, 0x0272, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x0470, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x0472, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B4, 0x0370, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x8070, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x8072, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x8170, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x8172, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x8060, iwl3160_2n_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x8062, iwl3160_n_cfg)},
-	{IWL_PCI_DEVICE(0x08B4, 0x8270, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B4, 0x8370, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B4, 0x8272, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x8470, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x8570, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x1070, iwl3160_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x08B3, 0x1170, iwl3160_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0070, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0072, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0170, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0172, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0060, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0062, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B4, 0x0270, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B4, 0x0272, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0470, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x0472, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B4, 0x0370, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8070, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8072, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8170, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8172, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8060, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8062, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B4, 0x8270, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B4, 0x8370, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B4, 0x8272, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8470, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x8570, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x1070, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x08B3, 0x1170, iwl7000_mac_cfg)},
 
 /* 3165 Series */
-	{IWL_PCI_DEVICE(0x3165, 0x4010, iwl3165_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x3165, 0x4012, iwl3165_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x3166, 0x4212, iwl3165_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x3165, 0x4410, iwl3165_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x3165, 0x4510, iwl3165_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x3165, 0x4110, iwl3165_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x3166, 0x4310, iwl3165_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x3166, 0x4210, iwl3165_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x3165, 0x8010, iwl3165_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x3165, 0x8110, iwl3165_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x4010, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x4012, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x3166, 0x4212, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x4410, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x4510, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x4110, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x3166, 0x4310, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x3166, 0x4210, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x8010, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x8110, iwl7000_mac_cfg)},
 
 /* 3168 Series */
-	{IWL_PCI_DEVICE(0x24FB, 0x2010, iwl3168_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FB, 0x2110, iwl3168_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FB, 0x2050, iwl3168_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FB, 0x2150, iwl3168_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FB, 0x0000, iwl3168_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24FB, 0x2010, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FB, 0x2110, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FB, 0x2050, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FB, 0x2150, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FB, 0x0000, iwl7000_mac_cfg)},
 
 /* 7265 Series */
-	{IWL_PCI_DEVICE(0x095A, 0x5010, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5110, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5100, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x5310, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x5302, iwl7265_n_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x5210, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5C10, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5012, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5412, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5410, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5510, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5400, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x1010, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5000, iwl7265_2n_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x500A, iwl7265_2n_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x5200, iwl7265_2n_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5002, iwl7265_n_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5102, iwl7265_n_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x5202, iwl7265_n_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x9010, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x9012, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x900A, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x9110, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x9112, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x9210, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x9200, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x9510, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x9310, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x9410, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5020, iwl7265_2n_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x502A, iwl7265_2n_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5420, iwl7265_2n_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5090, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5190, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5590, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x5290, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5490, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x5F10, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x5212, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x520A, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x9000, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x9400, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x9E10, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5010, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5110, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5100, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x5310, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x5302, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x5210, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5C10, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5012, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5412, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5410, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5510, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5400, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x1010, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5000, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x500A, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x5200, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5002, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5102, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x5202, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9010, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9012, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x900A, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9110, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9112, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x9210, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x9200, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9510, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x9310, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9410, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5020, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x502A, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5420, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5090, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5190, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5590, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x5290, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5490, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5F10, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x5212, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x520A, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9000, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9400, iwl7000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9E10, iwl7000_mac_cfg)},
 
 /* 8000 Series */
-	{IWL_PCI_DEVICE(0x24F3, 0x0010, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x1010, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x10B0, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0130, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x1130, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0132, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x1132, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0110, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x01F0, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0012, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x1012, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x1110, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0050, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0250, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x1050, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0150, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x1150, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F4, 0x0030, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F4, 0x1030, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0xC010, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0xC110, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0xD010, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0xC050, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0xD050, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0xD0B0, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0xB0B0, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x8010, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x8110, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x9010, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x9110, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F4, 0x8030, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F4, 0x9030, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F4, 0xC030, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F4, 0xD030, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x8130, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x9130, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x8132, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x9132, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x8050, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x8150, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x9050, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x9150, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0004, iwl8260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0044, iwl8260_2n_cfg)},
-	{IWL_PCI_DEVICE(0x24F5, 0x0010, iwl4165_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F6, 0x0030, iwl4165_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0810, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0910, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0850, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0950, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0930, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x0000, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F3, 0x4010, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0010, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0110, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x1110, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x1130, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0130, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x1010, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x10D0, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0050, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0150, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x9010, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x8110, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x8050, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x8010, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0810, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x9110, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x8130, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0910, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0930, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0950, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0850, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x1014, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x3E02, iwl8275_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x3E01, iwl8275_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x1012, iwl8275_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0012, iwl8275_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x0014, iwl8265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24FD, 0x9074, iwl8265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x1010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x10B0, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0130, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x1130, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0132, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x1132, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0110, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x01F0, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0012, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x1012, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x1110, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0050, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0250, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x1050, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0150, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x1150, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F4, 0x0030, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F4, 0x1030, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0xC010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0xC110, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0xD010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0xC050, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0xD050, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0xD0B0, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0xB0B0, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x8010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x8110, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x9010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x9110, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F4, 0x8030, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F4, 0x9030, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F4, 0xC030, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F4, 0xD030, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x8130, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x9130, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x8132, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x9132, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x8050, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x8150, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x9050, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x9150, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0004, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0044, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F5, 0x0010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F6, 0x0030, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0810, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0910, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0850, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0950, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0930, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0000, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x4010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0xC030, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0xD030, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0110, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x1110, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x1130, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0130, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x1010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x10D0, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0050, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0150, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x9010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x8110, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x8050, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x8010, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0810, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x9110, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x8130, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0910, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0930, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0950, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0850, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x1014, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x3E02, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x3E01, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x1012, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0012, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x0014, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x9074, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x1431, iwl8000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x24FD, 0x1432, iwl8000_mac_cfg)},
 
 /* 9000 Series */
-	{IWL_PCI_DEVICE(0x2526, PCI_ANY_ID, iwl9000_trans_cfg)},
-	{IWL_PCI_DEVICE(0x271B, PCI_ANY_ID, iwl9000_trans_cfg)},
-	{IWL_PCI_DEVICE(0x271C, PCI_ANY_ID, iwl9000_trans_cfg)},
-	{IWL_PCI_DEVICE(0x30DC, PCI_ANY_ID, iwl9560_long_latency_trans_cfg)},
-	{IWL_PCI_DEVICE(0x31DC, PCI_ANY_ID, iwl9560_shared_clk_trans_cfg)},
-	{IWL_PCI_DEVICE(0x9DF0, PCI_ANY_ID, iwl9560_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA370, PCI_ANY_ID, iwl9560_trans_cfg)},
+	{IWL_PCI_DEVICE(0x2526, PCI_ANY_ID, iwl9000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x271B, PCI_ANY_ID, iwl9000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x271C, PCI_ANY_ID, iwl9000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x30DC, PCI_ANY_ID, iwl9560_long_latency_mac_cfg)},
+	{IWL_PCI_DEVICE(0x31DC, PCI_ANY_ID, iwl9560_shared_clk_mac_cfg)},
+	{IWL_PCI_DEVICE(0x9DF0, PCI_ANY_ID, iwl9560_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA370, PCI_ANY_ID, iwl9560_mac_cfg)},
 
 /* Qu devices */
-	{IWL_PCI_DEVICE(0x02F0, PCI_ANY_ID, iwl_qu_trans_cfg)},
-	{IWL_PCI_DEVICE(0x06F0, PCI_ANY_ID, iwl_qu_trans_cfg)},
+	{IWL_PCI_DEVICE(0x02F0, PCI_ANY_ID, iwl_qu_mac_cfg)},
+	{IWL_PCI_DEVICE(0x06F0, PCI_ANY_ID, iwl_qu_mac_cfg)},
 
-	{IWL_PCI_DEVICE(0x34F0, PCI_ANY_ID, iwl_qu_medium_latency_trans_cfg)},
-	{IWL_PCI_DEVICE(0x3DF0, PCI_ANY_ID, iwl_qu_medium_latency_trans_cfg)},
-	{IWL_PCI_DEVICE(0x4DF0, PCI_ANY_ID, iwl_qu_medium_latency_trans_cfg)},
+	{IWL_PCI_DEVICE(0x34F0, PCI_ANY_ID, iwl_qu_medium_latency_mac_cfg)},
+	{IWL_PCI_DEVICE(0x3DF0, PCI_ANY_ID, iwl_qu_medium_latency_mac_cfg)},
+	{IWL_PCI_DEVICE(0x4DF0, PCI_ANY_ID, iwl_qu_medium_latency_mac_cfg)},
 
-	{IWL_PCI_DEVICE(0x43F0, PCI_ANY_ID, iwl_qu_long_latency_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA0F0, PCI_ANY_ID, iwl_qu_long_latency_trans_cfg)},
+	{IWL_PCI_DEVICE(0x43F0, PCI_ANY_ID, iwl_qu_long_latency_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA0F0, PCI_ANY_ID, iwl_qu_long_latency_mac_cfg)},
 
-	{IWL_PCI_DEVICE(0x2723, PCI_ANY_ID, iwl_ax200_trans_cfg)},
+	{IWL_PCI_DEVICE(0x2723, PCI_ANY_ID, iwl_ax200_mac_cfg)},
 
-/* So devices */
-	{IWL_PCI_DEVICE(0x2725, PCI_ANY_ID, iwl_so_trans_cfg)},
-	{IWL_PCI_DEVICE(0x7A70, PCI_ANY_ID, iwl_so_long_latency_imr_trans_cfg)},
-	{IWL_PCI_DEVICE(0x7AF0, PCI_ANY_ID, iwl_so_trans_cfg)},
-	{IWL_PCI_DEVICE(0x51F0, PCI_ANY_ID, iwl_so_long_latency_trans_cfg)},
-	{IWL_PCI_DEVICE(0x51F1, PCI_ANY_ID, iwl_so_long_latency_imr_trans_cfg)},
-	{IWL_PCI_DEVICE(0x54F0, PCI_ANY_ID, iwl_so_long_latency_trans_cfg)},
-	{IWL_PCI_DEVICE(0x7F70, PCI_ANY_ID, iwl_so_trans_cfg)},
+/* Ty/So devices */
+	{IWL_PCI_DEVICE(0x2725, PCI_ANY_ID, iwl_ty_mac_cfg)},
+	{IWL_PCI_DEVICE(0x7A70, PCI_ANY_ID, iwl_so_long_latency_imr_mac_cfg)},
+	{IWL_PCI_DEVICE(0x7AF0, PCI_ANY_ID, iwl_so_mac_cfg)},
+	{IWL_PCI_DEVICE(0x51F0, PCI_ANY_ID, iwl_so_long_latency_mac_cfg)},
+	{IWL_PCI_DEVICE(0x51F1, PCI_ANY_ID, iwl_so_long_latency_imr_mac_cfg)},
+	{IWL_PCI_DEVICE(0x54F0, PCI_ANY_ID, iwl_so_long_latency_mac_cfg)},
+	{IWL_PCI_DEVICE(0x7F70, PCI_ANY_ID, iwl_so_mac_cfg)},
 
 /* Ma devices */
-	{IWL_PCI_DEVICE(0x2729, PCI_ANY_ID, iwl_ma_trans_cfg)},
-	{IWL_PCI_DEVICE(0x7E40, PCI_ANY_ID, iwl_ma_trans_cfg)},
+	{IWL_PCI_DEVICE(0x2729, PCI_ANY_ID, iwl_ma_mac_cfg)},
+	{IWL_PCI_DEVICE(0x7E40, PCI_ANY_ID, iwl_ma_mac_cfg)},
 #endif /* CONFIG_IWLMVM */
 #if IS_ENABLED(CONFIG_IWLMLD)
 /* Bz devices */
-	{IWL_PCI_DEVICE(0x272b, PCI_ANY_ID, iwl_gl_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0000, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0090, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0094, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0098, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x009C, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x00C0, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x00C4, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x00E0, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x00E4, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x00E8, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x00EC, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0100, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0110, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0114, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0118, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x011C, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0310, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0314, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0510, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x0A10, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x1671, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x1672, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x1771, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x1772, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x1791, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x1792, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x4090, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x40C4, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x40E0, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x4110, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0xA840, 0x4314, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0x7740, PCI_ANY_ID, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0x4D40, PCI_ANY_ID, iwl_bz_trans_cfg)},
+	{IWL_PCI_DEVICE(0x272b, PCI_ANY_ID, iwl_gl_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0000, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0090, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0094, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0098, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x009C, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x00C0, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x00C4, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x00E0, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x00E4, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x00E8, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x00EC, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0100, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0110, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0114, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0118, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x011C, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0310, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0314, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0510, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x0A10, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x1671, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x1672, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x1771, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x1772, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x1791, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x1792, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x4090, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x40C4, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x40E0, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x4110, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x4314, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x1775, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0xA840, 0x1776, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0x7740, PCI_ANY_ID, iwl_bz_mac_cfg)},
+	{IWL_PCI_DEVICE(0x4D40, PCI_ANY_ID, iwl_bz_mac_cfg)},
 
 /* Sc devices */
-	{IWL_PCI_DEVICE(0xE440, PCI_ANY_ID, iwl_sc_trans_cfg)},
-	{IWL_PCI_DEVICE(0xE340, PCI_ANY_ID, iwl_sc_trans_cfg)},
-	{IWL_PCI_DEVICE(0xD340, PCI_ANY_ID, iwl_sc_trans_cfg)},
-	{IWL_PCI_DEVICE(0x6E70, PCI_ANY_ID, iwl_sc_trans_cfg)},
-
-/* Dr devices */
-	{IWL_PCI_DEVICE(0x272F, PCI_ANY_ID, iwl_dr_trans_cfg)},
+	{IWL_PCI_DEVICE(0xE440, PCI_ANY_ID, iwl_sc_mac_cfg)},
+	{IWL_PCI_DEVICE(0xE340, PCI_ANY_ID, iwl_sc_mac_cfg)},
+	{IWL_PCI_DEVICE(0xD340, PCI_ANY_ID, iwl_sc_mac_cfg)},
+	{IWL_PCI_DEVICE(0x6E70, PCI_ANY_ID, iwl_sc_mac_cfg)},
 #endif /* CONFIG_IWLMLD */
 
 	{0}
@@ -551,703 +552,518 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = {
 MODULE_DEVICE_TABLE(pci, iwl_hw_card_ids);
 EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_hw_card_ids);
 
-#define _IWL_DEV_INFO(_device, _subdevice, _mac_type, _mac_step, _rf_type, \
-		      _rf_id, _rf_step, _bw_limit, _cores, _cdb, _cfg, _name) \
-	{ .device = (_device), .subdevice = (_subdevice), .cfg = &(_cfg), \
-	  .name = _name, .mac_type = _mac_type, .rf_type = _rf_type, .rf_step = _rf_step, \
-	  .bw_limit = _bw_limit, .cores = _cores, .rf_id = _rf_id, \
-	  .mac_step = _mac_step, .cdb = _cdb, .jacket = IWL_CFG_ANY }
-
-#define IWL_DEV_INFO(_device, _subdevice, _cfg, _name) \
-	_IWL_DEV_INFO(_device, _subdevice, IWL_CFG_ANY, IWL_CFG_ANY,   \
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, \
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY, \
-		      _cfg, _name)
+#define _IWL_DEV_INFO(_cfg, _name, ...) {	\
+	.cfg = &_cfg,				\
+	.name = _name,				\
+	.device = IWL_CFG_ANY,			\
+	.subdevice = IWL_CFG_ANY,		\
+	.subdevice_m_h = 15,			\
+	__VA_ARGS__				\
+}
+#define IWL_DEV_INFO(_cfg, _name, ...)		\
+	_IWL_DEV_INFO(_cfg, _name, __VA_ARGS__)
+
+#define DEVICE(n)		.device = (n)
+#define SUBDEV(n)		.subdevice = (n)
+#define _LOWEST_BIT(n)		(__builtin_ffs(n) - 1)
+#define _BIT_ABOVE_MASK(n)	((n) + (1 << _LOWEST_BIT(n)))
+#define _HIGHEST_BIT(n)		(__builtin_ffs(_BIT_ABOVE_MASK(n)) - 2)
+#define _IS_POW2(n)		(((n) & ((n) - 1)) == 0)
+#define _IS_CONTIG(n)		_IS_POW2(_BIT_ABOVE_MASK(n))
+#define _CHECK_MASK(m)		BUILD_BUG_ON_ZERO(!_IS_CONTIG(m))
+#define SUBDEV_MASKED(v, m)	.subdevice = (v) + _CHECK_MASK(m),	\
+				.subdevice_m_l = _LOWEST_BIT(m),	\
+				.subdevice_m_h = _HIGHEST_BIT(m)
+#define RF_TYPE(n)		.match_rf_type = 1,			\
+				.rf_type = IWL_CFG_RF_TYPE_##n
+#define RF_STEP(n)		.match_rf_step = 1,			\
+				.rf_step = SILICON_##n##_STEP
+#define RF_ID(n)		.match_rf_id = 1,			\
+				.rf_id = IWL_CFG_RF_ID_##n
+#define NO_CDB			.match_cdb = 1, .cdb = 0
+#define CDB			.match_cdb = 1, .cdb = 1
+#define BW_NOT_LIMITED		.match_bw_limit = 1, .bw_limit = 0
+#define BW_LIMITED		.match_bw_limit = 1, .bw_limit = 1
 
 VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
+#if IS_ENABLED(CONFIG_IWLDVM)
+	IWL_DEV_INFO(iwl5100_n_cfg, iwl5100_agn_name,
+		     DEVICE(0x4232), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl5100_n_cfg, iwl5100_agn_name,
+		     DEVICE(0x4232), SUBDEV_MASKED(0x4, 0xF)),
+	IWL_DEV_INFO(iwl5100_n_cfg, iwl5100_bgn_name,
+		     DEVICE(0x4232), SUBDEV_MASKED(0x5, 0xF)),
+	IWL_DEV_INFO(iwl5100_abg_cfg, iwl5100_abg_name,
+		     DEVICE(0x4232), SUBDEV_MASKED(0x6, 0xF)),
+	IWL_DEV_INFO(iwl5100_n_cfg, iwl5100_agn_name,
+		     DEVICE(0x4237), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl5100_n_cfg, iwl5100_agn_name,
+		     DEVICE(0x4237), SUBDEV_MASKED(0x4, 0xF)),
+	IWL_DEV_INFO(iwl5100_n_cfg, iwl5100_bgn_name,
+		     DEVICE(0x4237), SUBDEV_MASKED(0x5, 0xF)),
+	IWL_DEV_INFO(iwl5100_abg_cfg, iwl5100_abg_name,
+		     DEVICE(0x4237), SUBDEV_MASKED(0x6, 0xF)),
+
+/* 5300 Series WiFi */
+	IWL_DEV_INFO(iwl5300_agn_cfg, iwl5300_agn_name,
+		     DEVICE(0x4235), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl5300_agn_cfg, iwl5300_agn_name,
+		     DEVICE(0x4235), SUBDEV_MASKED(0x4, 0xF)),
+	IWL_DEV_INFO(iwl5300_agn_cfg, iwl5300_agn_name,
+		     DEVICE(0x4236), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl5300_agn_cfg, iwl5300_agn_name,
+		     DEVICE(0x4236), SUBDEV_MASKED(0x4, 0xF)),
+
+/* 5350 Series WiFi/WiMax */
+	IWL_DEV_INFO(iwl5350_agn_cfg, iwl5350_agn_name,
+		     DEVICE(0x423A)),
+	IWL_DEV_INFO(iwl5350_agn_cfg, iwl5350_agn_name,
+		     DEVICE(0x423B)),
+
+/* 5150 Series Wifi/WiMax */
+	IWL_DEV_INFO(iwl5150_agn_cfg, iwl5150_agn_name,
+		     DEVICE(0x423C), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl5150_abg_cfg, iwl5150_abg_name,
+		     DEVICE(0x423C), SUBDEV_MASKED(0x6, 0xF)),
+
+	IWL_DEV_INFO(iwl5150_agn_cfg, iwl5150_agn_name,
+		     DEVICE(0x423D), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl5150_abg_cfg, iwl5150_abg_name,
+		     DEVICE(0x423D), SUBDEV_MASKED(0x6, 0xF)),
+
+/* 6x00 Series */
+	IWL_DEV_INFO(iwl6000_3agn_cfg, iwl6000_3agn_name,
+		     DEVICE(0x422B), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl6000_3agn_cfg, iwl6000_3agn_name,
+		     DEVICE(0x422B), SUBDEV_MASKED(0x8, 0xF)),
+	IWL_DEV_INFO(iwl6000i_2agn_cfg, iwl6000i_2agn_name,
+		     DEVICE(0x422C), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl6000i_non_n_cfg, iwl6000i_2abg_name,
+		     DEVICE(0x422C), SUBDEV_MASKED(0x6, 0xF)),
+	IWL_DEV_INFO(iwl6000i_non_n_cfg, iwl6000i_2bg_name,
+		     DEVICE(0x422C), SUBDEV_MASKED(0x7, 0xF)),
+	IWL_DEV_INFO(iwl6000_3agn_cfg, iwl6000_3agn_name,
+		     DEVICE(0x4238), SUBDEV(0x1111)),
+	IWL_DEV_INFO(iwl6000_3agn_cfg, iwl6000_3agn_name,
+		     DEVICE(0x4238), SUBDEV(0x1118)),
+	IWL_DEV_INFO(iwl6000i_2agn_cfg, iwl6000i_2agn_name,
+		     DEVICE(0x4239), SUBDEV(0x1311)),
+	IWL_DEV_INFO(iwl6000i_non_n_cfg, iwl6000i_2abg_name,
+		     DEVICE(0x4239), SUBDEV(0x1316)),
+
+/* 6x05 Series */
+	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_name,
+		     DEVICE(0x0082), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl6005_non_n_cfg, iwl6005_2abg_name,
+		     DEVICE(0x0082), SUBDEV_MASKED(0x6, 0xF)),
+	IWL_DEV_INFO(iwl6005_non_n_cfg, iwl6005_2bg_name,
+		     DEVICE(0x0082), SUBDEV_MASKED(0x7, 0xF)),
+	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_name,
+		     DEVICE(0x0082), SUBDEV_MASKED(0x8, 0xF)),
+
+	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_name,
+		     DEVICE(0x0085), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_name,
+		     DEVICE(0x0085), SUBDEV_MASKED(0x8, 0xF)),
+	IWL_DEV_INFO(iwl6005_non_n_cfg, iwl6005_2abg_name,
+		     DEVICE(0x0085), SUBDEV_MASKED(0x6, 0xF)),
+
+	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_sff_name,
+		     DEVICE(0x0082), SUBDEV_MASKED(0xC000, 0xF000)),
+	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_d_name,
+		     DEVICE(0x0082), SUBDEV(0x4820)),
+	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_mow1_name,
+		     DEVICE(0x0082), SUBDEV(0x1304)),/* low 5GHz active */
+	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_mow2_name,
+		     DEVICE(0x0082), SUBDEV(0x1305)),/* high 5GHz active */
+
+/* 6x30 Series */
+	IWL_DEV_INFO(iwl6030_n_cfg, iwl1030_bgn_name,
+		     DEVICE(0x008A), SUBDEV_MASKED(0x5, 0xF)),
+	IWL_DEV_INFO(iwl6030_non_n_cfg, iwl1030_bg_name,
+		     DEVICE(0x008A), SUBDEV_MASKED(0x7, 0xF)),
+	IWL_DEV_INFO(iwl6030_n_cfg, iwl1030_bgn_name,
+		     DEVICE(0x008B), SUBDEV(0x5315)),
+	IWL_DEV_INFO(iwl6030_non_n_cfg, iwl1030_bg_name,
+		     DEVICE(0x008B), SUBDEV(0x5317)),
+	IWL_DEV_INFO(iwl6030_n_cfg, iwl6030_2agn_name,
+		     DEVICE(0x0090), SUBDEV(0x5211)),
+	IWL_DEV_INFO(iwl6030_n_cfg, iwl6030_2bgn_name,
+		     DEVICE(0x0090), SUBDEV(0x5215)),
+	IWL_DEV_INFO(iwl6030_non_n_cfg, iwl6030_2abg_name,
+		     DEVICE(0x0090), SUBDEV(0x5216)),
+	IWL_DEV_INFO(iwl6030_n_cfg, iwl6030_2agn_name,
+		     DEVICE(0x0091), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl6030_n_cfg, iwl6030_2bgn_name,
+		     DEVICE(0x0091), SUBDEV_MASKED(0x5, 0xF)),
+	IWL_DEV_INFO(iwl6030_non_n_cfg, iwl6030_2abg_name,
+		     DEVICE(0x0091), SUBDEV_MASKED(0x6, 0xF)),
+	IWL_DEV_INFO(iwl6030_non_n_cfg, iwl6030_2bg_name,
+		     DEVICE(0x0091), SUBDEV(0x5207)),
+
+/* 6x50 WiFi/WiMax Series */
+	IWL_DEV_INFO(iwl6050_2agn_cfg, iwl6050_2agn_name,
+		     DEVICE(0x0087), SUBDEV_MASKED(0x1, 0xF)),
+	IWL_DEV_INFO(iwl6050_2abg_cfg, iwl6050_2abg_name,
+		     DEVICE(0x0087), SUBDEV_MASKED(0x6, 0xF)),
+	IWL_DEV_INFO(iwl6050_2agn_cfg, iwl6050_2agn_name,
+		     DEVICE(0x0089), SUBDEV(0x1311)),
+	IWL_DEV_INFO(iwl6050_2abg_cfg, iwl6050_2abg_name,
+		     DEVICE(0x0089), SUBDEV(0x1316)),
+
+/* 6150 WiFi/WiMax Series */
+	IWL_DEV_INFO(iwl6150_bgn_cfg, iwl6150_bgn_name,
+		     DEVICE(0x0885), SUBDEV_MASKED(0x5, 0xF)),
+	IWL_DEV_INFO(iwl6150_bg_cfg, iwl6150_bg_name,
+		     DEVICE(0x0885), SUBDEV_MASKED(0x7, 0xF)),
+	IWL_DEV_INFO(iwl6150_bgn_cfg, iwl6150_bgn_name,
+		     DEVICE(0x0886), SUBDEV(0x1315)),
+	IWL_DEV_INFO(iwl6150_bg_cfg, iwl6150_bg_name,
+		     DEVICE(0x0886), SUBDEV(0x1317)),
+
+/* 1000 Series WiFi */
+	IWL_DEV_INFO(iwl1000_bgn_cfg, iwl1000_bgn_name,
+		     DEVICE(0x0083), SUBDEV_MASKED(0x5, 0xF)),
+	IWL_DEV_INFO(iwl1000_bg_cfg, iwl1000_bg_name,
+		     DEVICE(0x0083), SUBDEV_MASKED(0x6, 0xF)),
+	IWL_DEV_INFO(iwl1000_bg_cfg, iwl1000_bg_name,
+		     DEVICE(0x0084), SUBDEV(0x1216)),
+	IWL_DEV_INFO(iwl1000_bg_cfg, iwl1000_bg_name,
+		     DEVICE(0x0084), SUBDEV(0x1316)),
+
+/* 100 Series WiFi */
+	IWL_DEV_INFO(iwl100_bgn_cfg, iwl100_bgn_name,
+		     DEVICE(0x08AE), SUBDEV_MASKED(0x5, 0xF)),
+	IWL_DEV_INFO(iwl100_bg_cfg, iwl100_bg_name,
+		     DEVICE(0x08AE), SUBDEV_MASKED(0x7, 0xF)),
+	IWL_DEV_INFO(iwl100_bgn_cfg, iwl100_bgn_name,
+		     DEVICE(0x08AF), SUBDEV(0x1015)),
+	IWL_DEV_INFO(iwl100_bg_cfg, iwl100_bg_name,
+		     DEVICE(0x08AF), SUBDEV(0x1017)),
+
+/* 130 Series WiFi */
+	IWL_DEV_INFO(iwl130_bgn_cfg, iwl130_bgn_name,
+		     DEVICE(0x0896), SUBDEV_MASKED(0x5, 0xF)),
+	IWL_DEV_INFO(iwl130_bg_cfg, iwl130_bg_name,
+		     DEVICE(0x0896), SUBDEV_MASKED(0x7, 0xF)),
+	IWL_DEV_INFO(iwl130_bgn_cfg, iwl130_bgn_name,
+		     DEVICE(0x0897), SUBDEV(0x5015)),
+	IWL_DEV_INFO(iwl130_bg_cfg, iwl130_bg_name,
+		     DEVICE(0x0897), SUBDEV(0x5017)),
+
+/* 2x00 Series */
+	IWL_DEV_INFO(iwl2000_2bgn_cfg, iwl2000_2bgn_name,
+		     DEVICE(0x0890), SUBDEV(0x4022)),
+	IWL_DEV_INFO(iwl2000_2bgn_cfg, iwl2000_2bgn_name,
+		     DEVICE(0x0891), SUBDEV(0x4222)),
+	IWL_DEV_INFO(iwl2000_2bgn_cfg, iwl2000_2bgn_name,
+		     DEVICE(0x0890), SUBDEV(0x4422)),
+	IWL_DEV_INFO(iwl2000_2bgn_cfg, iwl2000_2bgn_d_name,
+		     DEVICE(0x0890), SUBDEV(0x4822)),
+
+/* 2x30 Series */
+	IWL_DEV_INFO(iwl2030_2bgn_cfg, iwl2030_2bgn_name,
+		     DEVICE(0x0887)),
+	IWL_DEV_INFO(iwl2030_2bgn_cfg, iwl2030_2bgn_name,
+		     DEVICE(0x0888), SUBDEV(0x4262)),
+
+/* 6x35 Series */
+	IWL_DEV_INFO(iwl6035_2agn_cfg, iwl6035_2agn_name,
+		     DEVICE(0x088E), SUBDEV_MASKED(0x0, 0xF)),
+	IWL_DEV_INFO(iwl6035_2agn_cfg, iwl6035_2agn_sff_name,
+		     DEVICE(0x088E), SUBDEV_MASKED(0xA, 0xF)),
+	IWL_DEV_INFO(iwl6035_2agn_cfg, iwl6035_2agn_name,
+		     DEVICE(0x088F), SUBDEV_MASKED(0x0, 0xF)),
+	IWL_DEV_INFO(iwl6035_2agn_cfg, iwl6035_2agn_sff_name,
+		     DEVICE(0x088F), SUBDEV_MASKED(0xA, 0xF)),
+
+/* 105 Series */
+	IWL_DEV_INFO(iwl105_bgn_cfg, iwl105_bgn_name,
+		     DEVICE(0x0894)),
+	IWL_DEV_INFO(iwl105_bgn_cfg, iwl105_bgn_name,
+		     DEVICE(0x0895), SUBDEV(0x0222)),
+
+/* 135 Series */
+	IWL_DEV_INFO(iwl135_bgn_cfg, iwl135_bgn_name,
+		     DEVICE(0x0892)),
+	IWL_DEV_INFO(iwl135_bgn_cfg, iwl135_bgn_name,
+		     DEVICE(0x0893), SUBDEV(0x0262)),
+#endif /* CONFIG_IWLDVM */
+
 #if IS_ENABLED(CONFIG_IWLMVM)
-/* 9000 */
-	IWL_DEV_INFO(0x2526, 0x1550, iwl9260_2ac_cfg, iwl9260_killer_1550_name),
-	IWL_DEV_INFO(0x2526, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_name),
-	IWL_DEV_INFO(0x2526, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_name),
-	IWL_DEV_INFO(0x30DC, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_name),
-	IWL_DEV_INFO(0x30DC, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_name),
-	IWL_DEV_INFO(0x31DC, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_name),
-	IWL_DEV_INFO(0x31DC, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_name),
-	IWL_DEV_INFO(0xA370, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_name),
-	IWL_DEV_INFO(0xA370, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_name),
-	IWL_DEV_INFO(0x54F0, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_160_name),
-	IWL_DEV_INFO(0x54F0, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_name),
-	IWL_DEV_INFO(0x51F0, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_160_name),
-	IWL_DEV_INFO(0x51F0, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_160_name),
-	IWL_DEV_INFO(0x51F0, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name),
-	IWL_DEV_INFO(0x51F0, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
-	IWL_DEV_INFO(0x51F1, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
-	IWL_DEV_INFO(0x54F0, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name),
-	IWL_DEV_INFO(0x54F0, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
-	IWL_DEV_INFO(0x7A70, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name),
-	IWL_DEV_INFO(0x7A70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
-	IWL_DEV_INFO(0x7AF0, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name),
-	IWL_DEV_INFO(0x7AF0, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
-
-	IWL_DEV_INFO(0x271C, 0x0214, iwl9260_2ac_cfg, iwl9260_1_name),
-	IWL_DEV_INFO(0x7E40, 0x1691, iwl_cfg_ma, iwl_ax411_killer_1690s_name),
-	IWL_DEV_INFO(0x7E40, 0x1692, iwl_cfg_ma, iwl_ax411_killer_1690i_name),
-
-/* AX200 */
-	IWL_DEV_INFO(0x2723, IWL_CFG_ANY, iwl_ax200_cfg_cc, iwl_ax200_name),
-	IWL_DEV_INFO(0x2723, 0x1653, iwl_ax200_cfg_cc, iwl_ax200_killer_1650w_name),
-	IWL_DEV_INFO(0x2723, 0x1654, iwl_ax200_cfg_cc, iwl_ax200_killer_1650x_name),
-
-	/* Qu with Hr */
-	IWL_DEV_INFO(0x43F0, 0x0070, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x43F0, 0x0074, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x43F0, 0x0078, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x43F0, 0x007C, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x43F0, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0, iwl_ax201_killer_1650s_name),
-	IWL_DEV_INFO(0x43F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0, iwl_ax201_killer_1650i_name),
-	IWL_DEV_INFO(0x43F0, 0x2074, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x43F0, 0x4070, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0xA0F0, 0x0070, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0xA0F0, 0x0074, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0xA0F0, 0x0078, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0xA0F0, 0x007C, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0xA0F0, 0x0A10, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0xA0F0, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0, NULL),
-	IWL_DEV_INFO(0xA0F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0, NULL),
-	IWL_DEV_INFO(0xA0F0, 0x2074, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0xA0F0, 0x4070, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0xA0F0, 0x6074, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x02F0, 0x0070, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x02F0, 0x0074, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x02F0, 0x6074, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x02F0, 0x0078, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x02F0, 0x007C, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x02F0, 0x0310, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x02F0, 0x1651, iwl_ax1650s_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x02F0, 0x1652, iwl_ax1650i_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x02F0, 0x2074, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x02F0, 0x4070, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x06F0, 0x0070, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x06F0, 0x0074, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x06F0, 0x0078, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x06F0, 0x007C, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x06F0, 0x0310, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x06F0, 0x1651, iwl_ax1650s_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x06F0, 0x1652, iwl_ax1650i_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x06F0, 0x2074, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x06F0, 0x4070, iwl_ax201_cfg_quz_hr, NULL),
-	IWL_DEV_INFO(0x34F0, 0x0070, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x34F0, 0x0074, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x34F0, 0x0078, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x34F0, 0x007C, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x34F0, 0x0310, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x34F0, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0, NULL),
-	IWL_DEV_INFO(0x34F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0, NULL),
-	IWL_DEV_INFO(0x34F0, 0x2074, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x34F0, 0x4070, iwl_ax201_cfg_qu_hr, NULL),
-
-	IWL_DEV_INFO(0x3DF0, 0x0070, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x3DF0, 0x0074, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x3DF0, 0x0078, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x3DF0, 0x007C, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x3DF0, 0x0310, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x3DF0, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0, NULL),
-	IWL_DEV_INFO(0x3DF0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0, NULL),
-	IWL_DEV_INFO(0x3DF0, 0x2074, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x3DF0, 0x4070, iwl_ax201_cfg_qu_hr, NULL),
-
-	IWL_DEV_INFO(0x4DF0, 0x0070, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x4DF0, 0x0074, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x4DF0, 0x0078, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x4DF0, 0x007C, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x4DF0, 0x0310, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x4DF0, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0, NULL),
-	IWL_DEV_INFO(0x4DF0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0, NULL),
-	IWL_DEV_INFO(0x4DF0, 0x2074, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x4DF0, 0x4070, iwl_ax201_cfg_qu_hr, NULL),
-	IWL_DEV_INFO(0x4DF0, 0x6074, iwl_ax201_cfg_qu_hr, NULL),
-
-	/* So with HR */
-	IWL_DEV_INFO(0x2725, 0x0090, iwlax211_2ax_cfg_so_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0x0020, iwlax210_2ax_cfg_ty_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0x2020, iwlax210_2ax_cfg_ty_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0x0024, iwlax210_2ax_cfg_ty_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0x0310, iwlax210_2ax_cfg_ty_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0x0510, iwlax210_2ax_cfg_ty_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0x0A10, iwlax210_2ax_cfg_ty_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0xE020, iwlax210_2ax_cfg_ty_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0xE024, iwlax210_2ax_cfg_ty_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0x4020, iwlax210_2ax_cfg_ty_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0x6020, iwlax210_2ax_cfg_ty_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0x6024, iwlax210_2ax_cfg_ty_gf_a0, NULL),
-	IWL_DEV_INFO(0x2725, 0x1673, iwlax210_2ax_cfg_ty_gf_a0, iwl_ax210_killer_1675w_name),
-	IWL_DEV_INFO(0x2725, 0x1674, iwlax210_2ax_cfg_ty_gf_a0, iwl_ax210_killer_1675x_name),
-	IWL_DEV_INFO(0x7A70, 0x0090, iwlax211_2ax_cfg_so_gf_a0_long, NULL),
-	IWL_DEV_INFO(0x7A70, 0x0098, iwlax211_2ax_cfg_so_gf_a0_long, NULL),
-	IWL_DEV_INFO(0x7A70, 0x00B0, iwlax411_2ax_cfg_so_gf4_a0_long, NULL),
-	IWL_DEV_INFO(0x7A70, 0x0310, iwlax211_2ax_cfg_so_gf_a0_long, NULL),
-	IWL_DEV_INFO(0x7A70, 0x0510, iwlax211_2ax_cfg_so_gf_a0_long, NULL),
-	IWL_DEV_INFO(0x7A70, 0x0A10, iwlax211_2ax_cfg_so_gf_a0_long, NULL),
-	IWL_DEV_INFO(0x7AF0, 0x0090, iwlax211_2ax_cfg_so_gf_a0, NULL),
-	IWL_DEV_INFO(0x7AF0, 0x0098, iwlax211_2ax_cfg_so_gf_a0, NULL),
-	IWL_DEV_INFO(0x7AF0, 0x00B0, iwlax411_2ax_cfg_so_gf4_a0, NULL),
-	IWL_DEV_INFO(0x7AF0, 0x0310, iwlax211_2ax_cfg_so_gf_a0, NULL),
-	IWL_DEV_INFO(0x7AF0, 0x0510, iwlax211_2ax_cfg_so_gf_a0, NULL),
-	IWL_DEV_INFO(0x7AF0, 0x0A10, iwlax211_2ax_cfg_so_gf_a0, NULL),
-
-	/* So with JF */
-	IWL_DEV_INFO(0x7A70, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_160_name),
-	IWL_DEV_INFO(0x7A70, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_160_name),
-	IWL_DEV_INFO(0x7AF0, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_160_name),
-	IWL_DEV_INFO(0x7AF0, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_160_name),
-
-	/* SO with GF2 */
-	IWL_DEV_INFO(0x2726, 0x1671, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675s_name),
-	IWL_DEV_INFO(0x2726, 0x1672, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675i_name),
-	IWL_DEV_INFO(0x51F0, 0x1671, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675s_name),
-	IWL_DEV_INFO(0x51F0, 0x1672, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675i_name),
-	IWL_DEV_INFO(0x51F1, 0x1671, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675s_name),
-	IWL_DEV_INFO(0x51F1, 0x1672, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675i_name),
-	IWL_DEV_INFO(0x54F0, 0x1671, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675s_name),
-	IWL_DEV_INFO(0x54F0, 0x1672, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675i_name),
-	IWL_DEV_INFO(0x7A70, 0x1671, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675s_name),
-	IWL_DEV_INFO(0x7A70, 0x1672, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675i_name),
-	IWL_DEV_INFO(0x7AF0, 0x1671, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675s_name),
-	IWL_DEV_INFO(0x7AF0, 0x1672, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675i_name),
-	IWL_DEV_INFO(0x7F70, 0x1671, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675s_name),
-	IWL_DEV_INFO(0x7F70, 0x1672, iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_killer_1675i_name),
-
-	/* MA with GF2 */
-	IWL_DEV_INFO(0x7E40, 0x1671, iwl_cfg_ma, iwl_ax211_killer_1675s_name),
-	IWL_DEV_INFO(0x7E40, 0x1672, iwl_cfg_ma, iwl_ax211_killer_1675i_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_2ac_cfg_soc, iwl9461_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_2ac_cfg_soc, iwl9461_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_2ac_cfg_soc, iwl9462_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_2ac_cfg_soc, iwl9462_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_2ac_cfg_soc, iwl9560_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_2ac_cfg_soc, iwl9560_name),
-
-	_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
-		      iwl9260_2ac_cfg, iwl9270_160_name),
-	_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
-		      iwl9260_2ac_cfg, iwl9270_name),
-
-	_IWL_DEV_INFO(0x271B, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_TH1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9260_2ac_cfg, iwl9162_160_name),
-	_IWL_DEV_INFO(0x271B, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_TH1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9260_2ac_cfg, iwl9162_name),
-
-	_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9260_2ac_cfg, iwl9260_160_name),
-	_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9260_2ac_cfg, iwl9260_name),
-
-/* Qu with Jf */
-	/* Qu B step */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_b0_jf_b0_cfg, iwl9461_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_b0_jf_b0_cfg, iwl9461_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_b0_jf_b0_cfg, iwl9462_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_b0_jf_b0_cfg, iwl9462_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_b0_jf_b0_cfg, iwl9560_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_b0_jf_b0_cfg, iwl9560_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_b0_jf_b0_cfg, iwl9560_killer_1550s_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_b0_jf_b0_cfg, iwl9560_killer_1550i_name),
-
-	/* Qu C step */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_c0_jf_b0_cfg, iwl9461_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_c0_jf_b0_cfg, iwl9461_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_c0_jf_b0_cfg, iwl9462_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_c0_jf_b0_cfg, iwl9462_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_c0_jf_b0_cfg, iwl9560_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_c0_jf_b0_cfg, iwl9560_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_c0_jf_b0_cfg, iwl9560_killer_1550s_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_qu_c0_jf_b0_cfg, iwl9560_killer_1550i_name),
-
-	/* QuZ */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_quz_a0_jf_b0_cfg, iwl9461_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_quz_a0_jf_b0_cfg, iwl9461_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_quz_a0_jf_b0_cfg, iwl9462_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_quz_a0_jf_b0_cfg, iwl9462_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_quz_a0_jf_b0_cfg, iwl9560_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_quz_a0_jf_b0_cfg, iwl9560_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
-		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_quz_a0_jf_b0_cfg, iwl9560_killer_1550s_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
-		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwl9560_quz_a0_jf_b0_cfg, iwl9560_killer_1550i_name),
-
-/* Qu with Hr */
-	/* Qu B step */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_qu_b0_hr1_b0, iwl_ax101_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_qu_b0_hr_b0, iwl_ax203_name),
-
-	/* Qu C step */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
-		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_qu_c0_hr1_b0, iwl_ax101_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_qu_c0_hr_b0, iwl_ax203_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_qu_c0_hr_b0, iwl_ax201_name),
-
-	/* QuZ */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_quz_a0_hr1_b0, iwl_ax101_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QUZ, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_quz_a0_hr_b0, iwl_ax203_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_QUZ, SILICON_B_STEP,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_quz_a0_hr_b0, iwl_ax201_name),
-
-/* Ma */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_ma, iwl_ax201_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_ma, iwl_ax211_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_ma, iwl_ax231_name),
-
-/* So with Hr */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_so_a0_hr_a0, iwl_ax203_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_so_a0_hr_a0, iwl_ax101_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
-
-/* So-F with Hr */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_so_a0_hr_a0, iwl_ax203_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_so_a0_hr_a0, iwl_ax101_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
-
-/* So-F with Gf */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_CDB,
-		      iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_name),
-
-/* SoF with JF2 */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9560_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9560_name),
-
-/* SoF with JF */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9461_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9462_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9461_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9462_name),
-
-/* So with GF */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_CDB,
-		      iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_name),
-
-/* So with JF2 */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9560_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9560_name),
-
-/* So with JF */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9461_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9462_160_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9461_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
-		      iwlax210_2ax_cfg_so_jf_b0, iwl9462_name),
+/* 7260 Series */
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2ac_name,
+		     DEVICE(0x08B1)), // unlisted ones fall through to here
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0x4060)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0x406A)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0x4160)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_n_name,
+		     DEVICE(0x08B1), SUBDEV(0x4062)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_n_name,
+		     DEVICE(0x08B1), SUBDEV(0x4162)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0x4460)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0x446A)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_n_name,
+		     DEVICE(0x08B1), SUBDEV(0x4462)),
+	IWL_DEV_INFO(iwl7260_high_temp_cfg, iwl7260_2ac_name,
+		     DEVICE(0x08B1), SUBDEV(0x4A70)),
+	IWL_DEV_INFO(iwl7260_high_temp_cfg, iwl7260_2ac_name,
+		     DEVICE(0x08B1), SUBDEV(0x4A6E)),
+	IWL_DEV_INFO(iwl7260_high_temp_cfg, iwl7260_2ac_name,
+		     DEVICE(0x08B1), SUBDEV(0x4A6C)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0x4560)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0x4020)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0x402A)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0x4420)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC060)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC06A)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC160)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC062)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC162)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC760)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC460)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC462)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC560)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC360)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC020)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC02A)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B1), SUBDEV(0xC420)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2ac_name,
+		     DEVICE(0x08B2), SUBDEV(0x4270)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2ac_name,
+		     DEVICE(0x08B2), SUBDEV(0x4272)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B2), SUBDEV(0x4260)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B2), SUBDEV(0x426A)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_n_name,
+		     DEVICE(0x08B2), SUBDEV(0x4262)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2ac_name,
+		     DEVICE(0x08B2), SUBDEV(0x4370)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B2), SUBDEV(0x4360)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B2), SUBDEV(0x4220)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2ac_name,
+		     DEVICE(0x08B2), SUBDEV(0xC270)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2ac_name,
+		     DEVICE(0x08B2), SUBDEV(0xC272)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B2), SUBDEV(0xC260)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_n_name,
+		     DEVICE(0x08B2), SUBDEV(0xC26A)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_n_name,
+		     DEVICE(0x08B2), SUBDEV(0xC262)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2ac_name,
+		     DEVICE(0x08B2), SUBDEV(0xC370)),
+	IWL_DEV_INFO(iwl7260_cfg, iwl7260_2n_name,
+		     DEVICE(0x08B2), SUBDEV(0xC220)),
+
+/* 3160 Series */
+	IWL_DEV_INFO(iwl3160_cfg, iwl3160_2ac_name,
+		     DEVICE(0x08B3)),
+
+	IWL_DEV_INFO(iwl3160_cfg, iwl3160_n_name,
+		     DEVICE(0x08B3), SUBDEV_MASKED(0x62, 0xFF)),
+	IWL_DEV_INFO(iwl3160_cfg, iwl3160_2n_name,
+		     DEVICE(0x08B3), SUBDEV_MASKED(0x60, 0xFF)),
 
+	IWL_DEV_INFO(iwl3160_cfg, iwl3160_2ac_name,
+		     DEVICE(0x08B4)),
+
+/* 3165 Series */
+	IWL_DEV_INFO(iwl3165_2ac_cfg, iwl3165_2ac_name,
+		     DEVICE(0x3165)),
+	IWL_DEV_INFO(iwl3165_2ac_cfg, iwl3165_2ac_name,
+		     DEVICE(0x3166)),
+
+/* 3168 Series */
+	IWL_DEV_INFO(iwl3168_2ac_cfg, iwl3168_2ac_name,
+		     DEVICE(0x24FB)),
+
+/* 7265 Series */
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2ac_name,
+		     DEVICE(0x095A)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x5000)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x500A)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_n_name,
+		     DEVICE(0x095A), SUBDEV(0x5002)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_n_name,
+		     DEVICE(0x095A), SUBDEV(0x5102)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x5020)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x502A)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x5090)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x5190)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x5100)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x5400)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x5420)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x5490)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x5C10)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x5590)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x9000)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x900A)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095A), SUBDEV(0x9400)),
+
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2ac_name,
+		     DEVICE(0x095B)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095B), SUBDEV(0x520A)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_n_name,
+		     DEVICE(0x095B), SUBDEV(0x5302)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095B), SUBDEV(0x5200)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_n_name,
+		     DEVICE(0x095B), SUBDEV(0x5202)),
+	IWL_DEV_INFO(iwl7265_cfg, iwl7265_2n_name,
+		     DEVICE(0x095B), SUBDEV(0x9200)),
+
+/* 8000 Series */
+	IWL_DEV_INFO(iwl8260_cfg, iwl8260_2ac_name,
+		     DEVICE(0x24F3)),
+	IWL_DEV_INFO(iwl8260_cfg, iwl8260_2n_name,
+		     DEVICE(0x24F3), SUBDEV(0x0004)),
+	IWL_DEV_INFO(iwl8260_cfg, iwl8260_2n_name,
+		     DEVICE(0x24F3), SUBDEV(0x0044)),
+	IWL_DEV_INFO(iwl8265_cfg, iwl8265_2ac_name,
+		     DEVICE(0x24FD)),
+	IWL_DEV_INFO(iwl8265_cfg, iwl8275_2ac_name,
+		     DEVICE(0x24FD), SUBDEV(0x3E02)),
+	IWL_DEV_INFO(iwl8265_cfg, iwl8275_2ac_name,
+		     DEVICE(0x24FD), SUBDEV(0x3E01)),
+	IWL_DEV_INFO(iwl8265_cfg, iwl8275_2ac_name,
+		     DEVICE(0x24FD), SUBDEV(0x1012)),
+	IWL_DEV_INFO(iwl8265_cfg, iwl8275_2ac_name,
+		     DEVICE(0x24FD), SUBDEV(0x0012)),
+	IWL_DEV_INFO(iwl8265_cfg, iwl_killer_1435i_name,
+		     DEVICE(0x24FD), SUBDEV(0x1431)),
+	IWL_DEV_INFO(iwl8265_cfg, iwl_killer_1434_kix_name,
+		     DEVICE(0x24FD), SUBDEV(0x1432)),
+
+/* JF1 RF */
+	IWL_DEV_INFO(iwl_rf_jf, iwl9461_160_name,
+		     RF_TYPE(JF1)),
+	IWL_DEV_INFO(iwl_rf_jf_80mhz, iwl9461_name,
+		     RF_TYPE(JF1), BW_LIMITED),
+	IWL_DEV_INFO(iwl_rf_jf, iwl9462_160_name,
+		     RF_TYPE(JF1), RF_ID(JF1_DIV)),
+	IWL_DEV_INFO(iwl_rf_jf_80mhz, iwl9462_name,
+		     RF_TYPE(JF1), RF_ID(JF1_DIV), BW_LIMITED),
+/* JF2 RF */
+	IWL_DEV_INFO(iwl_rf_jf, iwl9260_160_name,
+		     RF_TYPE(JF2)),
+	IWL_DEV_INFO(iwl_rf_jf_80mhz, iwl9260_name,
+		     RF_TYPE(JF2), BW_LIMITED),
+	IWL_DEV_INFO(iwl_rf_jf, iwl9560_160_name,
+		     RF_TYPE(JF2), RF_ID(JF)),
+	IWL_DEV_INFO(iwl_rf_jf_80mhz, iwl9560_name,
+		     RF_TYPE(JF2), RF_ID(JF), BW_LIMITED),
+
+/* HR RF */
+	IWL_DEV_INFO(iwl_rf_hr, iwl_ax201_name, RF_TYPE(HR2)),
+	IWL_DEV_INFO(iwl_rf_hr_80mhz, iwl_ax101_name, RF_TYPE(HR1)),
+	IWL_DEV_INFO(iwl_rf_hr_80mhz, iwl_ax203_name, RF_TYPE(HR2), BW_LIMITED),
+	IWL_DEV_INFO(iwl_rf_hr, iwl_ax200_name, DEVICE(0x2723)),
+
+/* GF RF */
+	IWL_DEV_INFO(iwl_rf_gf, iwl_ax211_name, RF_TYPE(GF)),
+	IWL_DEV_INFO(iwl_rf_gf, iwl_ax411_name, RF_TYPE(GF), CDB),
+	IWL_DEV_INFO(iwl_rf_gf, iwl_ax210_name, DEVICE(0x2725)),
+
+/* Killer CRFs */
+	IWL_DEV_INFO(iwl_rf_jf, iwl9260_killer_1550_name, SUBDEV(0x1550)),
+	IWL_DEV_INFO(iwl_rf_jf, iwl9560_killer_1550s_name, SUBDEV(0x1551)),
+	IWL_DEV_INFO(iwl_rf_jf, iwl9560_killer_1550i_name, SUBDEV(0x1552)),
+
+	IWL_DEV_INFO(iwl_rf_hr, iwl_ax201_killer_1650s_name, SUBDEV(0x1651)),
+	IWL_DEV_INFO(iwl_rf_hr, iwl_ax201_killer_1650i_name, SUBDEV(0x1652)),
+
+	IWL_DEV_INFO(iwl_rf_gf, iwl_ax211_killer_1675s_name, SUBDEV(0x1671)),
+	IWL_DEV_INFO(iwl_rf_gf, iwl_ax211_killer_1675i_name, SUBDEV(0x1672)),
+	IWL_DEV_INFO(iwl_rf_gf, iwl_ax210_killer_1675w_name, SUBDEV(0x1673)),
+	IWL_DEV_INFO(iwl_rf_gf, iwl_ax210_killer_1675x_name, SUBDEV(0x1674)),
+	IWL_DEV_INFO(iwl_rf_gf, iwl_ax411_killer_1690s_name, SUBDEV(0x1691)),
+	IWL_DEV_INFO(iwl_rf_gf, iwl_ax411_killer_1690i_name, SUBDEV(0x1692)),
+
+/* Killer discrete */
+	IWL_DEV_INFO(iwl_rf_hr, iwl_ax200_killer_1650w_name,
+		     DEVICE(0x2723), SUBDEV(0x1653)),
+	IWL_DEV_INFO(iwl_rf_hr, iwl_ax200_killer_1650x_name,
+		     DEVICE(0x2723), SUBDEV(0x1654)),
 #endif /* CONFIG_IWLMVM */
 #if IS_ENABLED(CONFIG_IWLMLD)
-/* Bz */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_bz, iwl_ax201_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_bz, iwl_ax211_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_bz, iwl_fm_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_bz, iwl_wh_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_bz, iwl_ax201_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_bz, iwl_ax211_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_bz, iwl_fm_name),
-
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_bz, iwl_wh_name),
-
-/* Ga (Gl) */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_gl, iwl_gl_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
-		      iwl_cfg_gl, iwl_mtp_name),
-
-/* Sc */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc, iwl_ax211_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc, iwl_fm_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc, iwl_wh_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      160, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc, iwl_sp_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc2, iwl_ax211_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc2, iwl_fm_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc2, iwl_wh_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      160, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc2, iwl_sp_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc2f, iwl_ax211_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc2f, iwl_fm_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc2f, iwl_wh_name),
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
-		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      160, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc2f, iwl_sp_name),
-
-/* Dr */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_DR, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_dr, iwl_dr_name),
-
-/* Br */
-	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_MAC_TYPE_BR, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_br, iwl_br_name),
+/* FM RF */
+	IWL_DEV_INFO(iwl_rf_fm, iwl_be201_name, RF_TYPE(FM)),
+	IWL_DEV_INFO(iwl_rf_fm, iwl_be401_name, RF_TYPE(FM), CDB),
+	/* the discrete NICs got the RF B0, it's only for the name anyway */
+	IWL_DEV_INFO(iwl_rf_fm, iwl_be200_name, RF_TYPE(FM),
+		     DEVICE(0x272B), RF_STEP(B)),
+	IWL_DEV_INFO(iwl_rf_fm_160mhz, iwl_be202_name,
+		     RF_TYPE(FM), BW_LIMITED),
+
+/* Killer CRFs */
+	IWL_DEV_INFO(iwl_rf_fm, iwl_killer_be1750s_name, SUBDEV(0x1771)),
+	IWL_DEV_INFO(iwl_rf_fm, iwl_killer_be1750i_name, SUBDEV(0x1772)),
+	IWL_DEV_INFO(iwl_rf_fm, iwl_killer_be1790s_name, SUBDEV(0x1791)),
+	IWL_DEV_INFO(iwl_rf_fm, iwl_killer_be1790i_name, SUBDEV(0x1792)),
+
+/* Killer discrete */
+	IWL_DEV_INFO(iwl_rf_fm, iwl_killer_be1750w_name,
+		     DEVICE(0x272B), SUBDEV(0x1773)),
+	IWL_DEV_INFO(iwl_rf_fm, iwl_killer_be1750x_name,
+		     DEVICE(0x272B), SUBDEV(0x1774)),
+
+/* WH RF */
+	IWL_DEV_INFO(iwl_rf_wh, iwl_be211_name, RF_TYPE(WH)),
+	IWL_DEV_INFO(iwl_rf_wh_160mhz, iwl_be213_name, RF_TYPE(WH), BW_LIMITED),
+
+/* PE RF */
+	IWL_DEV_INFO(iwl_rf_pe, iwl_bn201_name, RF_TYPE(PE)),
+	IWL_DEV_INFO(iwl_rf_pe, iwl_be223_name, RF_TYPE(PE), SUBDEV(0x0524)),
+	IWL_DEV_INFO(iwl_rf_pe, iwl_be221_name, RF_TYPE(PE), SUBDEV(0x0324)),
+
+/* Killer */
+	IWL_DEV_INFO(iwl_rf_wh, iwl_killer_be1775s_name, SUBDEV(0x1776)),
+	IWL_DEV_INFO(iwl_rf_wh, iwl_killer_be1775i_name, SUBDEV(0x1775)),
+
+	IWL_DEV_INFO(iwl_rf_pe, iwl_killer_bn1850w2_name, SUBDEV(0x1851)),
+	IWL_DEV_INFO(iwl_rf_pe, iwl_killer_bn1850i_name, SUBDEV(0x1852)),
 #endif /* CONFIG_IWLMLD */
 };
 EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_dev_info_table);
@@ -1260,13 +1076,15 @@ EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_dev_info_table_size);
 /*
  * Read rf id and cdb info from prph register and store it
  */
-static void get_crf_id(struct iwl_trans *iwl_trans)
+static void get_crf_id(struct iwl_trans *iwl_trans,
+		       struct iwl_trans_info *info)
 {
 	u32 sd_reg_ver_addr;
+	u32 hw_wfpm_id;
 	u32 val = 0;
 	u8 step;
 
-	if (iwl_trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+	if (iwl_trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 		sd_reg_ver_addr = SD_REG_VER_GEN2;
 	else
 		sd_reg_ver_addr = SD_REG_VER;
@@ -1277,83 +1095,83 @@ static void get_crf_id(struct iwl_trans *iwl_trans)
 	iwl_write_umac_prph_no_grab(iwl_trans, WFPM_CTRL_REG, val);
 
 	/* Read crf info */
-	iwl_trans->hw_crf_id = iwl_read_prph_no_grab(iwl_trans, sd_reg_ver_addr);
+	info->hw_crf_id = iwl_read_prph_no_grab(iwl_trans, sd_reg_ver_addr);
 
 	/* Read cnv info */
-	iwl_trans->hw_cnv_id =
-		iwl_read_prph_no_grab(iwl_trans, CNVI_AUX_MISC_CHIP);
+	info->hw_cnv_id = iwl_read_prph_no_grab(iwl_trans, CNVI_AUX_MISC_CHIP);
 
 	/* For BZ-W, take B step also when A step is indicated */
-	if (CSR_HW_REV_TYPE(iwl_trans->hw_rev) == IWL_CFG_MAC_TYPE_BZ_W)
+	if (CSR_HW_REV_TYPE(info->hw_rev) == IWL_CFG_MAC_TYPE_BZ_W)
 		step = SILICON_B_STEP;
 
 	/* In BZ, the MAC step must be read from the CNVI aux register */
-	if (CSR_HW_REV_TYPE(iwl_trans->hw_rev) == IWL_CFG_MAC_TYPE_BZ) {
-		step = CNVI_AUX_MISC_CHIP_MAC_STEP(iwl_trans->hw_cnv_id);
+	if (CSR_HW_REV_TYPE(info->hw_rev) == IWL_CFG_MAC_TYPE_BZ) {
+		step = CNVI_AUX_MISC_CHIP_MAC_STEP(info->hw_cnv_id);
 
 		/* For BZ-U, take B step also when A step is indicated */
-		if ((CNVI_AUX_MISC_CHIP_PROD_TYPE(iwl_trans->hw_cnv_id) ==
+		if ((CNVI_AUX_MISC_CHIP_PROD_TYPE(info->hw_cnv_id) ==
 		    CNVI_AUX_MISC_CHIP_PROD_TYPE_BZ_U) &&
 		    step == SILICON_A_STEP)
 			step = SILICON_B_STEP;
 	}
 
-	if (CSR_HW_REV_TYPE(iwl_trans->hw_rev) == IWL_CFG_MAC_TYPE_BZ ||
-	    CSR_HW_REV_TYPE(iwl_trans->hw_rev) == IWL_CFG_MAC_TYPE_BZ_W) {
-		iwl_trans->hw_rev_step = step;
-		iwl_trans->hw_rev |= step;
+	if (CSR_HW_REV_TYPE(info->hw_rev) == IWL_CFG_MAC_TYPE_BZ ||
+	    CSR_HW_REV_TYPE(info->hw_rev) == IWL_CFG_MAC_TYPE_BZ_W) {
+		info->hw_rev_step = step;
+		info->hw_rev |= step;
 	}
 
 	/* Read cdb info (also contains the jacket info if needed in the future */
-	iwl_trans->hw_wfpm_id =
-		iwl_read_umac_prph_no_grab(iwl_trans, WFPM_OTP_CFG1_ADDR);
+	hw_wfpm_id = iwl_read_umac_prph_no_grab(iwl_trans, WFPM_OTP_CFG1_ADDR);
 	IWL_INFO(iwl_trans, "Detected crf-id 0x%x, cnv-id 0x%x wfpm id 0x%x\n",
-		 iwl_trans->hw_crf_id, iwl_trans->hw_cnv_id,
-		 iwl_trans->hw_wfpm_id);
+		 info->hw_crf_id, info->hw_cnv_id, hw_wfpm_id);
 }
 
 /*
  * In case that there is no OTP on the NIC, map the rf id and cdb info
  * from the prph registers.
  */
-static int map_crf_id(struct iwl_trans *iwl_trans)
+static int map_crf_id(struct iwl_trans *iwl_trans,
+		      struct iwl_trans_info *info)
 {
 	int ret = 0;
-	u32 val = iwl_trans->hw_crf_id;
+	u32 val = info->hw_crf_id;
 	u32 step_id = REG_CRF_ID_STEP(val);
 	u32 slave_id = REG_CRF_ID_SLAVE(val);
-	u32 jacket_id_cnv  = REG_CRF_ID_SLAVE(iwl_trans->hw_cnv_id);
-	u32 jacket_id_wfpm  = WFPM_OTP_CFG1_IS_JACKET(iwl_trans->hw_wfpm_id);
-	u32 cdb_id_wfpm  = WFPM_OTP_CFG1_IS_CDB(iwl_trans->hw_wfpm_id);
+	u32 jacket_id_cnv = REG_CRF_ID_SLAVE(info->hw_cnv_id);
+	u32 hw_wfpm_id = iwl_read_umac_prph_no_grab(iwl_trans,
+						    WFPM_OTP_CFG1_ADDR);
+	u32 jacket_id_wfpm = WFPM_OTP_CFG1_IS_JACKET(hw_wfpm_id);
+	u32 cdb_id_wfpm = WFPM_OTP_CFG1_IS_CDB(hw_wfpm_id);
 
 	/* Map between crf id to rf id */
 	switch (REG_CRF_ID_TYPE(val)) {
 	case REG_CRF_ID_TYPE_JF_1:
-		iwl_trans->hw_rf_id = (IWL_CFG_RF_TYPE_JF1 << 12);
+		info->hw_rf_id = (IWL_CFG_RF_TYPE_JF1 << 12);
 		break;
 	case REG_CRF_ID_TYPE_JF_2:
-		iwl_trans->hw_rf_id = (IWL_CFG_RF_TYPE_JF2 << 12);
+		info->hw_rf_id = (IWL_CFG_RF_TYPE_JF2 << 12);
 		break;
 	case REG_CRF_ID_TYPE_HR_NONE_CDB_1X1:
-		iwl_trans->hw_rf_id = (IWL_CFG_RF_TYPE_HR1 << 12);
+		info->hw_rf_id = (IWL_CFG_RF_TYPE_HR1 << 12);
 		break;
 	case REG_CRF_ID_TYPE_HR_NONE_CDB:
-		iwl_trans->hw_rf_id = (IWL_CFG_RF_TYPE_HR2 << 12);
+		info->hw_rf_id = (IWL_CFG_RF_TYPE_HR2 << 12);
 		break;
 	case REG_CRF_ID_TYPE_HR_CDB:
-		iwl_trans->hw_rf_id = (IWL_CFG_RF_TYPE_HR2 << 12);
+		info->hw_rf_id = (IWL_CFG_RF_TYPE_HR2 << 12);
 		break;
 	case REG_CRF_ID_TYPE_GF:
-		iwl_trans->hw_rf_id = (IWL_CFG_RF_TYPE_GF << 12);
+		info->hw_rf_id = (IWL_CFG_RF_TYPE_GF << 12);
 		break;
 	case REG_CRF_ID_TYPE_FM:
-		iwl_trans->hw_rf_id = (IWL_CFG_RF_TYPE_FM << 12);
+		info->hw_rf_id = (IWL_CFG_RF_TYPE_FM << 12);
 		break;
 	case REG_CRF_ID_TYPE_WHP:
-		iwl_trans->hw_rf_id = (IWL_CFG_RF_TYPE_WH << 12);
+		info->hw_rf_id = (IWL_CFG_RF_TYPE_WH << 12);
 		break;
 	case REG_CRF_ID_TYPE_PE:
-		iwl_trans->hw_rf_id = (IWL_CFG_RF_TYPE_PE << 12);
+		info->hw_rf_id = (IWL_CFG_RF_TYPE_PE << 12);
 		break;
 	default:
 		ret = -EIO;
@@ -1365,28 +1183,28 @@ static int map_crf_id(struct iwl_trans *iwl_trans)
 	}
 
 	/* Set Step-id */
-	iwl_trans->hw_rf_id |= (step_id << 8);
+	info->hw_rf_id |= (step_id << 8);
 
 	/* Set CDB capabilities */
 	if (cdb_id_wfpm || slave_id) {
-		iwl_trans->hw_rf_id += BIT(28);
+		info->hw_rf_id += BIT(28);
 		IWL_INFO(iwl_trans, "Adding cdb to rf id\n");
 	}
 
 	/* Set Jacket capabilities */
 	if (jacket_id_wfpm || jacket_id_cnv) {
-		iwl_trans->hw_rf_id += BIT(29);
+		info->hw_rf_id += BIT(29);
 		IWL_INFO(iwl_trans, "Adding jacket to rf id\n");
 	}
 
 	IWL_INFO(iwl_trans,
 		 "Detected rf-type 0x%x step-id 0x%x slave-id 0x%x from crf id 0x%x\n",
-		 REG_CRF_ID_TYPE(val), step_id, slave_id, iwl_trans->hw_rf_id);
+		 REG_CRF_ID_TYPE(val), step_id, slave_id, info->hw_rf_id);
 	IWL_INFO(iwl_trans,
 		 "Detected cdb-id 0x%x jacket-id 0x%x from wfpm id 0x%x\n",
-		 cdb_id_wfpm, jacket_id_wfpm, iwl_trans->hw_wfpm_id);
+		 cdb_id_wfpm, jacket_id_wfpm, hw_wfpm_id);
 	IWL_INFO(iwl_trans, "Detected jacket-id 0x%x from cnvi id 0x%x\n",
-		 jacket_id_cnv, iwl_trans->hw_cnv_id);
+		 jacket_id_cnv, info->hw_cnv_id);
 
 out:
 	return ret;
@@ -1396,9 +1214,8 @@ out:
 #define PCI_CFG_RETRY_TIMEOUT	0x041
 
 VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info *
-iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
-		      u16 mac_type, u8 mac_step, u16 rf_type, u8 cdb,
-		      u8 jacket, u8 rf_id, u8 bw_limit, u8 cores, u8 rf_step)
+iwl_pci_find_dev_info(u16 device, u16 subsystem_device, u16 rf_type, u8 cdb,
+		      u8 rf_id, u8 bw_limit, u8 rf_step)
 {
 	int num_devices = ARRAY_SIZE(iwl_dev_info_table);
 	int i;
@@ -1408,56 +1225,32 @@ iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
 
 	for (i = num_devices - 1; i >= 0; i--) {
 		const struct iwl_dev_info *dev_info = &iwl_dev_info_table[i];
+		u16 subdevice_mask;
 
 		if (dev_info->device != (u16)IWL_CFG_ANY &&
 		    dev_info->device != device)
 			continue;
 
-		if (dev_info->subdevice != (u16)IWL_CFG_ANY &&
-		    dev_info->subdevice != subsystem_device)
-			continue;
+		subdevice_mask = GENMASK(dev_info->subdevice_m_h,
+					 dev_info->subdevice_m_l);
 
-		if (dev_info->mac_type != (u16)IWL_CFG_ANY &&
-		    dev_info->mac_type != mac_type)
-			continue;
-
-		if (dev_info->mac_step != (u8)IWL_CFG_ANY &&
-		    dev_info->mac_step != mac_step)
-			continue;
-
-		if (dev_info->rf_type != (u16)IWL_CFG_ANY &&
-		    dev_info->rf_type != rf_type)
-			continue;
-
-		if (dev_info->cdb != (u8)IWL_CFG_ANY &&
-		    dev_info->cdb != cdb)
+		if (dev_info->subdevice != (u16)IWL_CFG_ANY &&
+		    dev_info->subdevice != (subsystem_device & subdevice_mask))
 			continue;
 
-		if (dev_info->jacket != (u8)IWL_CFG_ANY &&
-		    dev_info->jacket != jacket)
+		if (dev_info->match_rf_type && dev_info->rf_type != rf_type)
 			continue;
 
-		if (dev_info->rf_id != (u8)IWL_CFG_ANY &&
-		    dev_info->rf_id != rf_id)
+		if (dev_info->match_cdb && dev_info->cdb != cdb)
 			continue;
 
-		/*
-		 * Check that bw_limit have the same "boolean" value since
-		 * IWL_SUBDEVICE_BW_LIM can only return a boolean value and
-		 * dev_info->bw_limit encodes a non-boolean value.
-		 * dev_info->bw_limit == IWL_CFG_BW_NO_LIM must be equal to
-		 * !bw_limit to have a match.
-		 */
-		if (dev_info->bw_limit != IWL_CFG_BW_ANY &&
-		    (dev_info->bw_limit == IWL_CFG_BW_NO_LIM) == !!bw_limit)
+		if (dev_info->match_rf_id && dev_info->rf_id != rf_id)
 			continue;
 
-		if (dev_info->cores != (u8)IWL_CFG_ANY &&
-		    dev_info->cores != cores)
+		if (dev_info->match_bw_limit && dev_info->bw_limit != bw_limit)
 			continue;
 
-		if (dev_info->rf_step != (u8)IWL_CFG_ANY &&
-		    dev_info->rf_step != rf_step)
+		if (dev_info->match_rf_step && dev_info->rf_step != rf_step)
 			continue;
 
 		return dev_info;
@@ -1469,30 +1262,32 @@ EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_pci_find_dev_info);
 
 static void iwl_pcie_recheck_me_status(struct work_struct *wk)
 {
-	struct iwl_trans *trans = container_of(wk, typeof(*trans),
-					       me_recheck_wk.work);
+	struct iwl_trans_pcie *trans_pcie = container_of(wk,
+							 typeof(*trans_pcie),
+							 me_recheck_wk.work);
 	u32 val;
 
-	val = iwl_read32(trans, CSR_HW_IF_CONFIG_REG);
-	trans->me_present = !!(val & CSR_HW_IF_CONFIG_REG_IAMT_UP);
+	val = iwl_read32(trans_pcie->trans, CSR_HW_IF_CONFIG_REG);
+	trans_pcie->me_present = !!(val & CSR_HW_IF_CONFIG_REG_IAMT_UP);
 }
 
 static void iwl_pcie_check_me_status(struct iwl_trans *trans)
 {
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	u32 val;
 
-	trans->me_present = -1;
+	trans_pcie->me_present = -1;
 
-	INIT_DELAYED_WORK(&trans->me_recheck_wk,
+	INIT_DELAYED_WORK(&trans_pcie->me_recheck_wk,
 			  iwl_pcie_recheck_me_status);
 
 	/* we don't have a good way of determining this until BZ */
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_BZ)
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_BZ)
 		return;
 
 	val = iwl_read_prph(trans, CNVI_SCU_REG_FOR_ECO_1);
 	if (val & CNVI_SCU_REG_FOR_ECO_1_WIAMT_KNOWN) {
-		trans->me_present =
+		trans_pcie->me_present =
 			!!(val & CNVI_SCU_REG_FOR_ECO_1_WIAMT_PRESENT);
 		return;
 	}
@@ -1500,38 +1295,28 @@ static void iwl_pcie_check_me_status(struct iwl_trans *trans)
 	val = iwl_read32(trans, CSR_HW_IF_CONFIG_REG);
 	if (val & (CSR_HW_IF_CONFIG_REG_ME_OWN |
 		   CSR_HW_IF_CONFIG_REG_IAMT_UP)) {
-		trans->me_present = 1;
+		trans_pcie->me_present = 1;
 		return;
 	}
 
 	/* recheck again later, ME might still be initializing */
-	schedule_delayed_work(&trans->me_recheck_wk, HZ);
+	schedule_delayed_work(&trans_pcie->me_recheck_wk, HZ);
 }
 
 static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
-	const struct iwl_cfg_trans_params *trans;
-	const struct iwl_cfg *cfg_7265d __maybe_unused = NULL;
+	const struct iwl_mac_cfg *trans;
 	const struct iwl_dev_info *dev_info;
+	struct iwl_trans_info info = {
+		.hw_id = (pdev->device << 16) + pdev->subsystem_device,
+	};
 	struct iwl_trans *iwl_trans;
 	struct iwl_trans_pcie *trans_pcie;
 	int ret;
-	const struct iwl_cfg *cfg;
-
-	trans = (void *)(ent->driver_data & ~TRANS_CFG_MARKER);
 
-	/*
-	 * This is needed for backwards compatibility with the old
-	 * tables, so we don't need to change all the config structs
-	 * at the same time.  The cfg is used to compare with the old
-	 * full cfg structs.
-	 */
-	cfg = (void *)(ent->driver_data & ~TRANS_CFG_MARKER);
-
-	/* make sure trans is the first element in iwl_cfg */
-	BUILD_BUG_ON(offsetof(struct iwl_cfg, trans));
+	trans = (void *)ent->driver_data;
 
-	iwl_trans = iwl_trans_pcie_alloc(pdev, ent, trans);
+	iwl_trans = iwl_trans_pcie_alloc(pdev, trans, &info);
 	if (IS_ERR(iwl_trans))
 		return PTR_ERR(iwl_trans);
 
@@ -1540,6 +1325,9 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	iwl_trans_pcie_check_product_reset_status(pdev);
 	iwl_trans_pcie_check_product_reset_mode(pdev);
 
+	/* set the things we know so far for the grab NIC access */
+	iwl_trans_set_info(iwl_trans, &info);
+
 	/*
 	 * Let's try to grab NIC access early here. Sometimes, NICs may
 	 * fail to initialize, and if that happens it's better if we see
@@ -1553,7 +1341,7 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		if (ret)
 			goto out_free_trans;
 		if (iwl_trans_grab_nic_access(iwl_trans)) {
-			get_crf_id(iwl_trans);
+			get_crf_id(iwl_trans, &info);
 			/* all good */
 			iwl_trans_release_nic_access(iwl_trans);
 		} else {
@@ -1562,38 +1350,32 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	}
 
-	iwl_trans->hw_rf_id = iwl_read32(iwl_trans, CSR_HW_RF_ID);
+	info.hw_rf_id = iwl_read32(iwl_trans, CSR_HW_RF_ID);
 
 	/*
 	 * The RF_ID is set to zero in blank OTP so read version to
 	 * extract the RF_ID.
 	 * This is relevant only for family 9000 and up.
 	 */
-	if (iwl_trans->trans_cfg->rf_id &&
-	    iwl_trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_9000 &&
-	    !CSR_HW_RFID_TYPE(iwl_trans->hw_rf_id) && map_crf_id(iwl_trans)) {
+	if (iwl_trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_9000 &&
+	    !CSR_HW_RFID_TYPE(info.hw_rf_id) && map_crf_id(iwl_trans, &info)) {
 		ret = -EINVAL;
 		goto out_free_trans;
 	}
 
 	IWL_INFO(iwl_trans, "PCI dev %04x/%04x, rev=0x%x, rfid=0x%x\n",
 		 pdev->device, pdev->subsystem_device,
-		 iwl_trans->hw_rev, iwl_trans->hw_rf_id);
+		 info.hw_rev, info.hw_rf_id);
 
 	dev_info = iwl_pci_find_dev_info(pdev->device, pdev->subsystem_device,
-					 CSR_HW_REV_TYPE(iwl_trans->hw_rev),
-					 iwl_trans->hw_rev_step,
-					 CSR_HW_RFID_TYPE(iwl_trans->hw_rf_id),
-					 CSR_HW_RFID_IS_CDB(iwl_trans->hw_rf_id),
-					 CSR_HW_RFID_IS_JACKET(iwl_trans->hw_rf_id),
+					 CSR_HW_RFID_TYPE(info.hw_rf_id),
+					 CSR_HW_RFID_IS_CDB(info.hw_rf_id),
 					 IWL_SUBDEVICE_RF_ID(pdev->subsystem_device),
 					 IWL_SUBDEVICE_BW_LIM(pdev->subsystem_device),
-					 IWL_SUBDEVICE_CORES(pdev->subsystem_device),
-					 CSR_HW_RFID_STEP(iwl_trans->hw_rf_id));
+					 CSR_HW_RFID_STEP(info.hw_rf_id));
 	if (dev_info) {
 		iwl_trans->cfg = dev_info->cfg;
-		iwl_trans->name = dev_info->name;
-		iwl_trans->bw_limit = dev_info->bw_limit;
+		info.name = dev_info->name;
 	}
 
 #if IS_ENABLED(CONFIG_IWLMVM)
@@ -1604,82 +1386,41 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * all the parameters that the transport uses must, until that is
 	 * changed, be identical to the ones in the 7265D configuration.
 	 */
-	if (cfg == &iwl7265_2ac_cfg)
-		cfg_7265d = &iwl7265d_2ac_cfg;
-	else if (cfg == &iwl7265_2n_cfg)
-		cfg_7265d = &iwl7265d_2n_cfg;
-	else if (cfg == &iwl7265_n_cfg)
-		cfg_7265d = &iwl7265d_n_cfg;
-	if (cfg_7265d &&
-	    (iwl_trans->hw_rev & CSR_HW_REV_TYPE_MSK) == CSR_HW_REV_TYPE_7265D)
-		iwl_trans->cfg = cfg_7265d;
-
-	/*
-	 * This is a hack to switch from Qu B0 to Qu C0.  We need to
-	 * do this for all cfgs that use Qu B0, except for those using
-	 * Jf, which have already been moved to the new table.  The
-	 * rest must be removed once we convert Qu with Hr as well.
-	 */
-	if (iwl_trans->hw_rev == CSR_HW_REV_TYPE_QU_C0) {
-		if (iwl_trans->cfg == &iwl_ax201_cfg_qu_hr)
-			iwl_trans->cfg = &iwl_ax201_cfg_qu_c0_hr_b0;
-		else if (iwl_trans->cfg == &killer1650s_2ax_cfg_qu_b0_hr_b0)
-			iwl_trans->cfg = &killer1650s_2ax_cfg_qu_c0_hr_b0;
-		else if (iwl_trans->cfg == &killer1650i_2ax_cfg_qu_b0_hr_b0)
-			iwl_trans->cfg = &killer1650i_2ax_cfg_qu_c0_hr_b0;
-	}
-
-	/* same thing for QuZ... */
-	if (iwl_trans->hw_rev == CSR_HW_REV_TYPE_QUZ) {
-		if (iwl_trans->cfg == &iwl_ax201_cfg_qu_hr)
-			iwl_trans->cfg = &iwl_ax201_cfg_quz_hr;
-		else if (iwl_trans->cfg == &killer1650s_2ax_cfg_qu_b0_hr_b0)
-			iwl_trans->cfg = &iwl_ax1650s_cfg_quz_hr;
-		else if (iwl_trans->cfg == &killer1650i_2ax_cfg_qu_b0_hr_b0)
-			iwl_trans->cfg = &iwl_ax1650i_cfg_quz_hr;
-	}
-
+	if (iwl_trans->cfg == &iwl7265_cfg &&
+	    (info.hw_rev & CSR_HW_REV_TYPE_MSK) == CSR_HW_REV_TYPE_7265D)
+		iwl_trans->cfg = &iwl7265d_cfg;
 #endif
-	/*
-	 * If we didn't set the cfg yet, the PCI ID table entry should have
-	 * been a full config - if yes, use it, otherwise fail.
-	 */
 	if (!iwl_trans->cfg) {
-		if (ent->driver_data & TRANS_CFG_MARKER) {
-			pr_err("No config found for PCI dev %04x/%04x, rev=0x%x, rfid=0x%x\n",
-			       pdev->device, pdev->subsystem_device,
-			       iwl_trans->hw_rev, iwl_trans->hw_rf_id);
-			ret = -EINVAL;
-			goto out_free_trans;
-		}
-		iwl_trans->cfg = cfg;
+		pr_err("No config found for PCI dev %04x/%04x, rev=0x%x, rfid=0x%x\n",
+		       pdev->device, pdev->subsystem_device,
+		       info.hw_rev, info.hw_rf_id);
+		ret = -EINVAL;
+		goto out_free_trans;
 	}
 
-	/* if we don't have a name yet, copy name from the old cfg */
-	if (!iwl_trans->name)
-		iwl_trans->name = iwl_trans->cfg->name;
-
-	IWL_INFO(iwl_trans, "Detected %s\n", iwl_trans->name);
+	IWL_INFO(iwl_trans, "Detected %s\n", info.name);
 
-	if (iwl_trans->trans_cfg->mq_rx_supported) {
+	if (iwl_trans->mac_cfg->mq_rx_supported) {
 		if (WARN_ON(!iwl_trans->cfg->num_rbds)) {
 			ret = -EINVAL;
 			goto out_free_trans;
 		}
-		trans_pcie->num_rx_bufs = iwl_trans->cfg->num_rbds;
+		trans_pcie->num_rx_bufs = iwl_trans_get_num_rbds(iwl_trans);
 	} else {
 		trans_pcie->num_rx_bufs = RX_QUEUE_SIZE;
 	}
 
-	if (!iwl_trans->trans_cfg->integrated) {
+	if (!iwl_trans->mac_cfg->integrated) {
 		u16 link_status;
 
 		pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &link_status);
 
-		iwl_trans->pcie_link_speed =
+		info.pcie_link_speed =
 			u16_get_bits(link_status, PCI_EXP_LNKSTA_CLS);
 	}
 
+	iwl_trans_set_info(iwl_trans, &info);
+
 	ret = iwl_trans_init(iwl_trans);
 	if (ret)
 		goto out_free_trans;
@@ -1711,11 +1452,12 @@ out_free_trans:
 static void iwl_pci_remove(struct pci_dev *pdev)
 {
 	struct iwl_trans *trans = pci_get_drvdata(pdev);
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
 	if (!trans)
 		return;
 
-	cancel_delayed_work_sync(&trans->me_recheck_wk);
+	cancel_delayed_work_sync(&trans_pcie->me_recheck_wk);
 
 	iwl_drv_stop(trans->drv);
 
@@ -1761,7 +1503,7 @@ static int _iwl_pci_resume(struct device *device, bool restore)
 	 * Note: MAC (bits 0:7) will be cleared upon suspend even with wowlan,
 	 * so assume that any bits there mean that the device is usable.
 	 */
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ &&
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ &&
 	    !iwl_read32(trans, CSR_FUNC_SCRATCH))
 		device_was_powered_off = true;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 45460f93d24a..3b7c12fc4f9e 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -194,7 +194,7 @@ struct iwl_rb_allocator {
 static inline u16 iwl_get_closed_rb_stts(struct iwl_trans *trans,
 					 struct iwl_rxq *rxq)
 {
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		__le16 *rb_stts = rxq->rb_stts;
 
 		return le16_to_cpu(READ_ONCE(*rb_stts));
@@ -269,6 +269,7 @@ enum iwl_pcie_fw_reset_state {
 	FW_RESET_REQUESTED,
 	FW_RESET_OK,
 	FW_RESET_ERROR,
+	FW_RESET_TOP_REQUESTED,
 };
 
 /**
@@ -288,22 +289,14 @@ enum iwl_pcie_imr_status {
 /**
  * struct iwl_pcie_txqs - TX queues data
  *
- * @bc_table_dword: true if the BC table expects DWORD (as opposed to bytes)
- * @page_offs: offset from skb->cb to mac header page pointer
- * @dev_cmd_offs: offset from skb->cb to iwl_device_tx_cmd pointer
  * @queue_used: bit mask of used queues
  * @queue_stopped: bit mask of stopped queues
  * @txq: array of TXQ data structures representing the TXQs
  * @scd_bc_tbls: gen1 pointer to the byte count table of the scheduler
- * @queue_alloc_cmd_ver: queue allocation command version
  * @bc_pool: bytecount DMA allocations pool
  * @bc_tbl_size: bytecount table size
  * @tso_hdr_page: page allocated (per CPU) for A-MSDU headers when doing TSO
  *	(and similar usage)
- * @cmd: command queue data
- * @cmd.fifo: FIFO number
- * @cmd.q_id: queue ID
- * @cmd.wdg_timeout: watchdog timeout
  * @tfd: TFD data
  * @tfd.max_tbs: max number of buffers per TFD
  * @tfd.size: TFD size
@@ -315,26 +308,15 @@ struct iwl_pcie_txqs {
 	struct iwl_txq *txq[IWL_MAX_TVQM_QUEUES];
 	struct dma_pool *bc_pool;
 	size_t bc_tbl_size;
-	bool bc_table_dword;
-	u8 page_offs;
-	u8 dev_cmd_offs;
 	struct iwl_tso_hdr_page __percpu *tso_hdr_page;
 
 	struct {
-		u8 fifo;
-		u8 q_id;
-		unsigned int wdg_timeout;
-	} cmd;
-
-	struct {
 		u8 max_tbs;
 		u16 size;
 		u8 addr_size;
 	} tfd;
 
 	struct iwl_dma_ptr scd_bc_tbls;
-
-	u8 queue_alloc_cmd_ver;
 };
 
 /**
@@ -344,7 +326,7 @@ struct iwl_pcie_txqs {
  * @global_table: table mapping received VID from hw to rxb
  * @rba: allocator for RX replenishing
  * @ctxt_info: context information for FW self init
- * @ctxt_info_gen3: context information for gen3 devices
+ * @ctxt_info_v2: context information for v1 devices
  * @prph_info: prph info for self init
  * @prph_scratch: prph scratch for self init
  * @ctxt_info_dma_addr: dma addr of context information
@@ -352,6 +334,7 @@ struct iwl_pcie_txqs {
  * @prph_scratch_dma_addr: dma addr of prph scratch
  * @ctxt_info_dma_addr: dma addr of context information
  * @iml: image loader image virtual address
+ * @iml_len: image loader image size
  * @iml_dma_addr: image loader image DMA address
  * @trans: pointer to the generic transport area
  * @scd_base_addr: scheduler sram base address in SRAM
@@ -363,9 +346,6 @@ struct iwl_pcie_txqs {
  * @hw_base: pci hardware address support
  * @ucode_write_complete: indicates that the ucode has been copied.
  * @ucode_write_waitq: wait queue for uCode load
- * @cmd_queue - command queue number
- * @rx_buf_size: Rx buffer size
- * @scd_set_active: should the transport configure the SCD for HCMD queue
  * @rx_page_order: page order for receive buffer size
  * @rx_buf_bytes: RX buffer (RB) size in bytes
  * @reg_lock: protect hw register access
@@ -406,19 +386,20 @@ struct iwl_pcie_txqs {
  * @pcie_dbg_dumped_once: indicates PCIe regs were dumped already
  * @opmode_down: indicates opmode went away
  * @num_rx_bufs: number of RX buffers to allocate/use
- * @no_reclaim_cmds: special commands not using reclaim flow
- *	(firmware workaround)
- * @n_no_reclaim_cmds: number of special commands not using reclaim flow
  * @affinity_mask: IRQ affinity mask for each RX queue
  * @debug_rfkill: RF-kill debugging state, -1 for unset, 0/1 for radio
  *	enable/disable
- * @fw_reset_handshake: indicates FW reset handshake is needed
  * @fw_reset_state: state of FW reset handshake
  * @fw_reset_waitq: waitqueue for FW reset handshake
  * @is_down: indicates the NIC is down
  * @isr_stats: interrupt statistics
  * @napi_dev: (fake) netdev for NAPI registration
  * @txqs: transport tx queues data.
+ * @me_present: WiAMT/CSME is detected as present (1), not present (0)
+ *	or unknown (-1, so can still use it as a boolean safely)
+ * @me_recheck_wk: worker to recheck WiAMT/CSME presence
+ * @invalid_tx_cmd: invalid TX command buffer
+ * @wait_command_queue: wait queue for sync commands
  */
 struct iwl_trans_pcie {
 	struct iwl_rxq *rxq;
@@ -427,11 +408,12 @@ struct iwl_trans_pcie {
 	struct iwl_rb_allocator rba;
 	union {
 		struct iwl_context_info *ctxt_info;
-		struct iwl_context_info_gen3 *ctxt_info_gen3;
+		struct iwl_context_info_v2 *ctxt_info_v2;
 	};
 	struct iwl_prph_info *prph_info;
 	struct iwl_prph_scratch *prph_scratch;
 	void *iml;
+	size_t iml_len;
 	dma_addr_t ctxt_info_dma_addr;
 	dma_addr_t prph_info_dma_addr;
 	dma_addr_t prph_scratch_dma_addr;
@@ -470,12 +452,8 @@ struct iwl_trans_pcie {
 	wait_queue_head_t ucode_write_waitq;
 	wait_queue_head_t sx_waitq;
 
-	u8 n_no_reclaim_cmds;
-	u8 no_reclaim_cmds[MAX_NO_RECLAIM_CMDS];
 	u16 num_rx_bufs;
 
-	enum iwl_amsdu_size rx_buf_size;
-	bool scd_set_active;
 	bool pcie_dbg_dumped_once;
 	u32 rx_page_order;
 	u32 rx_buf_bytes;
@@ -510,7 +488,6 @@ struct iwl_trans_pcie {
 	void *base_rb_stts;
 	dma_addr_t base_rb_stts_dma;
 
-	bool fw_reset_handshake;
 	enum iwl_pcie_fw_reset_state fw_reset_state;
 	wait_queue_head_t fw_reset_waitq;
 	enum iwl_pcie_imr_status imr_status;
@@ -518,6 +495,13 @@ struct iwl_trans_pcie {
 	char rf_name[32];
 
 	struct iwl_pcie_txqs txqs;
+
+	s8 me_present;
+	struct delayed_work me_recheck_wk;
+
+	struct iwl_dma_ptr invalid_tx_cmd;
+
+	wait_queue_head_t wait_command_queue;
 };
 
 static inline struct iwl_trans_pcie *
@@ -552,16 +536,16 @@ iwl_trans_pcie_get_trans(struct iwl_trans_pcie *trans_pcie)
  */
 struct iwl_trans
 *iwl_trans_pcie_alloc(struct pci_dev *pdev,
-		      const struct pci_device_id *ent,
-		      const struct iwl_cfg_trans_params *cfg_trans);
+		      const struct iwl_mac_cfg *mac_cfg,
+		      struct iwl_trans_info *info);
 void iwl_trans_pcie_free(struct iwl_trans *trans);
 void iwl_trans_pcie_free_pnvm_dram_regions(struct iwl_dram_regions *dram_regions,
 					   struct device *dev);
 
-bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans);
-#define _iwl_trans_pcie_grab_nic_access(trans)			\
+bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans, bool silent);
+#define _iwl_trans_pcie_grab_nic_access(trans, silent)		\
 	__cond_lock(nic_access_nobh,				\
-		    likely(__iwl_trans_pcie_grab_nic_access(trans)))
+		    likely(__iwl_trans_pcie_grab_nic_access(trans, silent)))
 
 void iwl_trans_pcie_check_product_reset_status(struct pci_dev *pdev);
 void iwl_trans_pcie_check_product_reset_mode(struct pci_dev *pdev);
@@ -623,7 +607,7 @@ struct iwl_tso_page_info {
 				      IWL_TSO_PAGE_DATA_SIZE))
 
 int iwl_pcie_tx_init(struct iwl_trans *trans);
-void iwl_pcie_tx_start(struct iwl_trans *trans, u32 scd_base_addr);
+void iwl_pcie_tx_start(struct iwl_trans *trans);
 int iwl_pcie_tx_stop(struct iwl_trans *trans);
 void iwl_pcie_tx_free(struct iwl_trans *trans);
 bool iwl_trans_pcie_txq_enable(struct iwl_trans *trans, int queue, u16 ssn,
@@ -679,7 +663,7 @@ static inline void *iwl_txq_get_tfd(struct iwl_trans *trans,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
-	if (trans->trans_cfg->gen2)
+	if (trans->mac_cfg->gen2)
 		idx = iwl_txq_get_cmd_index(txq, idx);
 
 	return (u8 *)txq->tfds + trans_pcie->txqs.tfd.size * idx;
@@ -718,7 +702,7 @@ static inline void iwl_txq_stop(struct iwl_trans *trans, struct iwl_txq *txq)
 static inline int iwl_txq_inc_wrap(struct iwl_trans *trans, int index)
 {
 	return ++index &
-		(trans->trans_cfg->base_params->max_tfd_queue_size - 1);
+		(trans->mac_cfg->base->max_tfd_queue_size - 1);
 }
 
 /**
@@ -729,7 +713,7 @@ static inline int iwl_txq_inc_wrap(struct iwl_trans *trans, int index)
 static inline int iwl_txq_dec_wrap(struct iwl_trans *trans, int index)
 {
 	return --index &
-		(trans->trans_cfg->base_params->max_tfd_queue_size - 1);
+		(trans->mac_cfg->base->max_tfd_queue_size - 1);
 }
 
 void iwl_txq_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq);
@@ -752,10 +736,12 @@ int iwl_txq_gen2_set_tb(struct iwl_trans *trans,
 static inline void iwl_txq_set_tfd_invalid_gen2(struct iwl_trans *trans,
 						struct iwl_tfh_tfd *tfd)
 {
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
 	tfd->num_tbs = 0;
 
-	iwl_txq_gen2_set_tb(trans, tfd, trans->invalid_tx_cmd.dma,
-			    trans->invalid_tx_cmd.size);
+	iwl_txq_gen2_set_tb(trans, tfd, trans_pcie->invalid_tx_cmd.dma,
+			    trans_pcie->invalid_tx_cmd.size);
 }
 
 void iwl_txq_gen2_tfd_unmap(struct iwl_trans *trans,
@@ -782,7 +768,7 @@ static inline u16 iwl_txq_gen1_tfd_tb_get_len(struct iwl_trans *trans,
 	struct iwl_tfd *tfd;
 	struct iwl_tfd_tb *tb;
 
-	if (trans->trans_cfg->gen2) {
+	if (trans->mac_cfg->gen2) {
 		struct iwl_tfh_tfd *tfh_tfd = _tfd;
 		struct iwl_tfh_tb *tfh_tb = &tfh_tfd->tbs[idx];
 
@@ -940,11 +926,13 @@ static inline void iwl_enable_fw_load_int(struct iwl_trans *trans)
 	}
 }
 
-static inline void iwl_enable_fw_load_int_ctx_info(struct iwl_trans *trans)
+static inline void iwl_enable_fw_load_int_ctx_info(struct iwl_trans *trans,
+						   bool top_reset)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
-	IWL_DEBUG_ISR(trans, "Enabling ALIVE interrupt only\n");
+	IWL_DEBUG_ISR(trans, "Enabling %s interrupt only\n",
+		      top_reset ? "RESET" : "ALIVE");
 
 	if (!trans_pcie->msix_enabled) {
 		/*
@@ -954,11 +942,20 @@ static inline void iwl_enable_fw_load_int_ctx_info(struct iwl_trans *trans)
 		 * RX interrupt which will allow us to receive the ALIVE
 		 * notification (which is Rx) and continue the flow.
 		 */
-		trans_pcie->inta_mask =  CSR_INT_BIT_ALIVE | CSR_INT_BIT_FH_RX;
+		if (top_reset)
+			trans_pcie->inta_mask =  CSR_INT_BIT_RESET_DONE;
+		else
+			trans_pcie->inta_mask =  CSR_INT_BIT_ALIVE |
+						 CSR_INT_BIT_FH_RX;
 		iwl_write32(trans, CSR_INT_MASK, trans_pcie->inta_mask);
 	} else {
-		iwl_enable_hw_int_msk_msix(trans,
-					   MSIX_HW_INT_CAUSES_REG_ALIVE);
+		u32 val = top_reset ? MSIX_HW_INT_CAUSES_REG_RESET_DONE
+				    : MSIX_HW_INT_CAUSES_REG_ALIVE;
+
+		iwl_enable_hw_int_msk_msix(trans, val);
+
+		if (top_reset)
+			return;
 		/*
 		 * Leave all the FH causes enabled to get the ALIVE
 		 * notification.
@@ -1005,7 +1002,7 @@ static inline void iwl_enable_rfkill_int(struct iwl_trans *trans)
 					   MSIX_HW_INT_CAUSES_REG_RF_KILL);
 	}
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_9000) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_9000) {
 		/*
 		 * On 9000-series devices this bit isn't enabled by default, so
 		 * when we power down the device we need set the bit to allow it
@@ -1076,8 +1073,7 @@ static inline void iwl_trans_pcie_dbgfs_register(struct iwl_trans *trans) { }
 void iwl_pcie_rx_allocator_work(struct work_struct *data);
 
 /* common trans ops for all generations transports */
-void iwl_trans_pcie_configure(struct iwl_trans *trans,
-			      const struct iwl_trans_config *trans_cfg);
+void iwl_trans_pcie_op_mode_enter(struct iwl_trans *trans);
 int iwl_trans_pcie_start_hw(struct iwl_trans *trans);
 void iwl_trans_pcie_op_mode_leave(struct iwl_trans *trans);
 void iwl_trans_pcie_write8(struct iwl_trans *trans, u32 ofs, u8 val);
@@ -1105,12 +1101,16 @@ void iwl_trans_pcie_set_bits_mask(struct iwl_trans *trans, u32 reg,
 int iwl_trans_pcie_read_config32(struct iwl_trans *trans, u32 ofs,
 				 u32 *val);
 bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans);
-void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans);
+void __releases(nic_access_nobh)
+iwl_trans_pcie_release_nic_access(struct iwl_trans *trans);
+void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans, u8 max_power);
 
 /* transport gen 1 exported functions */
-void iwl_trans_pcie_fw_alive(struct iwl_trans *trans, u32 scd_addr);
+void iwl_trans_pcie_fw_alive(struct iwl_trans *trans);
 int iwl_trans_pcie_start_fw(struct iwl_trans *trans,
-			    const struct fw_img *fw, bool run_in_rfkill);
+			    const struct iwl_fw *fw,
+			    const struct fw_img *img,
+			    bool run_in_rfkill);
 void iwl_trans_pcie_stop_device(struct iwl_trans *trans);
 
 /* common functions that are used by gen2 transport */
@@ -1128,15 +1128,12 @@ int iwl_pcie_alloc_dma_ptr(struct iwl_trans *trans,
 void iwl_pcie_free_dma_ptr(struct iwl_trans *trans, struct iwl_dma_ptr *ptr);
 void iwl_pcie_apply_destination(struct iwl_trans *trans);
 
-/* common functions that are used by gen3 transport */
-void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans, u8 max_power);
-
 /* transport gen 2 exported functions */
 int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
-				 const struct fw_img *fw, bool run_in_rfkill);
+				 const struct iwl_fw *fw,
+				 const struct fw_img *img,
+				 bool run_in_rfkill);
 void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans);
-int iwl_trans_pcie_gen2_send_hcmd(struct iwl_trans *trans,
-				  struct iwl_host_cmd *cmd);
 void iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans);
 int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 			       struct iwl_host_cmd *cmd);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 4a4f8de4efe2..f0405eddc367 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -12,7 +12,8 @@
 #include "iwl-io.h"
 #include "internal.h"
 #include "iwl-op-mode.h"
-#include "iwl-context-info-gen3.h"
+#include "iwl-context-info-v2.h"
+#include "fw/dbg.h"
 
 /******************************************************************************
  *
@@ -143,12 +144,12 @@ static inline __le32 iwl_pcie_dma_addr2rbd_ptr(dma_addr_t dma_addr)
  */
 int iwl_pcie_rx_stop(struct iwl_trans *trans)
 {
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		/* TODO: remove this once fw does it */
-		iwl_write_umac_prph(trans, RFH_RXF_DMA_CFG_GEN3, 0);
-		return iwl_poll_umac_prph_bit(trans, RFH_GEN_STATUS_GEN3,
+		iwl_write_umac_prph(trans, RFH_RXF_DMA_CFG_AX210, 0);
+		return iwl_poll_umac_prph_bit(trans, RFH_GEN_STATUS_AX210,
 					      RXF_DMA_IDLE, RXF_DMA_IDLE, 1000);
-	} else if (trans->trans_cfg->mq_rx_supported) {
+	} else if (trans->mac_cfg->mq_rx_supported) {
 		iwl_write_prph(trans, RFH_RXF_DMA_CFG, 0);
 		return iwl_poll_prph_bit(trans, RFH_GEN_STATUS,
 					   RXF_DMA_IDLE, RXF_DMA_IDLE, 1000);
@@ -175,7 +176,7 @@ static void iwl_pcie_rxq_inc_wr_ptr(struct iwl_trans *trans,
 	 * 1. shadow registers aren't enabled
 	 * 2. there is a chance that the NIC is asleep
 	 */
-	if (!trans->trans_cfg->base_params->shadow_reg_enable &&
+	if (!trans->mac_cfg->base->shadow_reg_enable &&
 	    test_bit(STATUS_TPOWER_PMI, &trans->status)) {
 		reg = iwl_read32(trans, CSR_UCODE_DRV_GP1);
 
@@ -190,9 +191,9 @@ static void iwl_pcie_rxq_inc_wr_ptr(struct iwl_trans *trans,
 	}
 
 	rxq->write_actual = round_down(rxq->write, 8);
-	if (!trans->trans_cfg->mq_rx_supported)
+	if (!trans->mac_cfg->mq_rx_supported)
 		iwl_write32(trans, FH_RSCSR_CHNL0_WPTR, rxq->write_actual);
-	else if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	else if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 		iwl_write32(trans, HBUS_TARG_WRPTR, rxq->write_actual |
 			    HBUS_TARG_WRPTR_RX_Q(rxq->id));
 	else
@@ -205,7 +206,7 @@ static void iwl_pcie_rxq_check_wrptr(struct iwl_trans *trans)
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int i;
 
-	for (i = 0; i < trans->num_rx_queues; i++) {
+	for (i = 0; i < trans->info.num_rxqs; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
 		if (!rxq->need_update)
@@ -221,7 +222,7 @@ static void iwl_pcie_restock_bd(struct iwl_trans *trans,
 				struct iwl_rxq *rxq,
 				struct iwl_rx_mem_buffer *rxb)
 {
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		struct iwl_rx_transfer_desc *bd = rxq->bd;
 
 		BUILD_BUG_ON(sizeof(*bd) != 2 * sizeof(u64));
@@ -348,7 +349,7 @@ static void iwl_pcie_rxsq_restock(struct iwl_trans *trans,
 static
 void iwl_pcie_rxq_restock(struct iwl_trans *trans, struct iwl_rxq *rxq)
 {
-	if (trans->trans_cfg->mq_rx_supported)
+	if (trans->mac_cfg->mq_rx_supported)
 		iwl_pcie_rxmq_restock(trans, rxq);
 	else
 		iwl_pcie_rxsq_restock(trans, rxq);
@@ -362,8 +363,8 @@ static struct page *iwl_pcie_rx_alloc_page(struct iwl_trans *trans,
 					   u32 *offset, gfp_t priority)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	unsigned int rbsize = iwl_trans_get_rb_size(trans_pcie->rx_buf_size);
 	unsigned int allocsize = PAGE_SIZE << trans_pcie->rx_page_order;
+	unsigned int rbsize = trans_pcie->rx_buf_bytes;
 	struct page *page;
 	gfp_t gfp_mask = priority;
 
@@ -657,19 +658,19 @@ void iwl_pcie_rx_allocator_work(struct work_struct *data)
 
 static int iwl_pcie_free_bd_size(struct iwl_trans *trans)
 {
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 		return sizeof(struct iwl_rx_transfer_desc);
 
-	return trans->trans_cfg->mq_rx_supported ?
+	return trans->mac_cfg->mq_rx_supported ?
 			sizeof(__le64) : sizeof(__le32);
 }
 
 static int iwl_pcie_used_bd_size(struct iwl_trans *trans)
 {
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 		return sizeof(struct iwl_rx_completion_desc_bz);
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 		return sizeof(struct iwl_rx_completion_desc);
 
 	return sizeof(__le32);
@@ -701,7 +702,7 @@ static void iwl_pcie_free_rxq_dma(struct iwl_trans *trans,
 
 static size_t iwl_pcie_rb_stts_size(struct iwl_trans *trans)
 {
-	bool use_rx_td = (trans->trans_cfg->device_family >=
+	bool use_rx_td = (trans->mac_cfg->device_family >=
 			  IWL_DEVICE_FAMILY_AX210);
 
 	if (use_rx_td)
@@ -720,8 +721,8 @@ static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
 	int free_size;
 
 	spin_lock_init(&rxq->lock);
-	if (trans->trans_cfg->mq_rx_supported)
-		rxq->queue_size = trans->cfg->num_rbds;
+	if (trans->mac_cfg->mq_rx_supported)
+		rxq->queue_size = iwl_trans_get_num_rbds(trans);
 	else
 		rxq->queue_size = RX_QUEUE_SIZE;
 
@@ -736,7 +737,7 @@ static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
 	if (!rxq->bd)
 		goto err;
 
-	if (trans->trans_cfg->mq_rx_supported) {
+	if (trans->mac_cfg->mq_rx_supported) {
 		rxq->used_bd = dma_alloc_coherent(dev,
 						  iwl_pcie_used_bd_size(trans) *
 							rxq->queue_size,
@@ -753,7 +754,7 @@ static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
 	return 0;
 
 err:
-	for (i = 0; i < trans->num_rx_queues; i++) {
+	for (i = 0; i < trans->info.num_rxqs; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
 		iwl_pcie_free_rxq_dma(trans, rxq);
@@ -772,7 +773,7 @@ static int iwl_pcie_rx_alloc(struct iwl_trans *trans)
 	if (WARN_ON(trans_pcie->rxq))
 		return -EINVAL;
 
-	trans_pcie->rxq = kcalloc(trans->num_rx_queues, sizeof(struct iwl_rxq),
+	trans_pcie->rxq = kcalloc(trans->info.num_rxqs, sizeof(struct iwl_rxq),
 				  GFP_KERNEL);
 	trans_pcie->rx_pool = kcalloc(RX_POOL_SIZE(trans_pcie->num_rx_bufs),
 				      sizeof(trans_pcie->rx_pool[0]),
@@ -795,7 +796,7 @@ static int iwl_pcie_rx_alloc(struct iwl_trans *trans)
 	 */
 	trans_pcie->base_rb_stts =
 			dma_alloc_coherent(trans->dev,
-					   rb_stts_size * trans->num_rx_queues,
+					   rb_stts_size * trans->info.num_rxqs,
 					   &trans_pcie->base_rb_stts_dma,
 					   GFP_KERNEL);
 	if (!trans_pcie->base_rb_stts) {
@@ -803,7 +804,7 @@ static int iwl_pcie_rx_alloc(struct iwl_trans *trans)
 		goto err;
 	}
 
-	for (i = 0; i < trans->num_rx_queues; i++) {
+	for (i = 0; i < trans->info.num_rxqs; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
 		rxq->id = i;
@@ -816,7 +817,7 @@ static int iwl_pcie_rx_alloc(struct iwl_trans *trans)
 err:
 	if (trans_pcie->base_rb_stts) {
 		dma_free_coherent(trans->dev,
-				  rb_stts_size * trans->num_rx_queues,
+				  rb_stts_size * trans->info.num_rxqs,
 				  trans_pcie->base_rb_stts,
 				  trans_pcie->base_rb_stts_dma);
 		trans_pcie->base_rb_stts = NULL;
@@ -834,11 +835,10 @@ err:
 
 static void iwl_pcie_rx_hw_init(struct iwl_trans *trans, struct iwl_rxq *rxq)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	u32 rb_size;
 	const u32 rfdnlog = RX_QUEUE_SIZE_LOG; /* 256 RBDs */
 
-	switch (trans_pcie->rx_buf_size) {
+	switch (trans->conf.rx_buf_size) {
 	case IWL_AMSDU_4K:
 		rb_size = FH_RCSR_RX_CONFIG_REG_VAL_RB_SIZE_4K;
 		break;
@@ -906,7 +906,7 @@ static void iwl_pcie_rx_mq_hw_init(struct iwl_trans *trans)
 	u32 rb_size, enabled = 0;
 	int i;
 
-	switch (trans_pcie->rx_buf_size) {
+	switch (trans->conf.rx_buf_size) {
 	case IWL_AMSDU_2K:
 		rb_size = RFH_RXF_DMA_RB_SIZE_2K;
 		break;
@@ -932,7 +932,7 @@ static void iwl_pcie_rx_mq_hw_init(struct iwl_trans *trans)
 	/* disable free amd used rx queue operation */
 	iwl_write_prph_no_grab(trans, RFH_RXF_RXQ_ACTIVE, 0);
 
-	for (i = 0; i < trans->num_rx_queues; i++) {
+	for (i = 0; i < trans->info.num_rxqs; i++) {
 		/* Tell device where to find RBD free table in DRAM */
 		iwl_write_prph64_no_grab(trans,
 					 RFH_Q_FRBDCB_BA_LSB(i),
@@ -976,7 +976,7 @@ static void iwl_pcie_rx_mq_hw_init(struct iwl_trans *trans)
 			       RFH_GEN_CFG_VAL(DEFAULT_RXQ_NUM, 0) |
 			       RFH_GEN_CFG_SERVICE_DMA_SNOOP |
 			       RFH_GEN_CFG_VAL(RB_CHUNK_SIZE,
-					       trans->trans_cfg->integrated ?
+					       trans->mac_cfg->integrated ?
 					       RFH_GEN_CFG_RB_CHUNK_SIZE_64 :
 					       RFH_GEN_CFG_RB_CHUNK_SIZE_128));
 	/* Enable the relevant rx queues */
@@ -1072,7 +1072,7 @@ void iwl_pcie_rx_napi_sync(struct iwl_trans *trans)
 	if (unlikely(!trans_pcie->rxq))
 		return;
 
-	for (i = 0; i < trans->num_rx_queues; i++) {
+	for (i = 0; i < trans->info.num_rxqs; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
 		if (rxq && rxq->napi.poll)
@@ -1109,7 +1109,7 @@ static int _iwl_pcie_rx_init(struct iwl_trans *trans)
 	for (i = 0; i < RX_QUEUE_SIZE; i++)
 		def_rxq->queue[i] = NULL;
 
-	for (i = 0; i < trans->num_rx_queues; i++) {
+	for (i = 0; i < trans->info.num_rxqs; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
 		spin_lock_bh(&rxq->lock);
@@ -1122,7 +1122,7 @@ static int _iwl_pcie_rx_init(struct iwl_trans *trans)
 		rxq->write = 0;
 		rxq->write_actual = 0;
 		memset(rxq->rb_stts, 0,
-		       (trans->trans_cfg->device_family >=
+		       (trans->mac_cfg->device_family >=
 			IWL_DEVICE_FAMILY_AX210) ?
 		       sizeof(__le16) : sizeof(struct iwl_rb_status));
 
@@ -1144,9 +1144,9 @@ static int _iwl_pcie_rx_init(struct iwl_trans *trans)
 	}
 
 	/* move the pool to the default queue and allocator ownerships */
-	queue_size = trans->trans_cfg->mq_rx_supported ?
+	queue_size = trans->mac_cfg->mq_rx_supported ?
 			trans_pcie->num_rx_bufs - 1 : RX_QUEUE_SIZE;
-	allocator_pool_size = trans->num_rx_queues *
+	allocator_pool_size = trans->info.num_rxqs *
 		(RX_CLAIM_REQ_ALLOC - RX_POST_REQ_ALLOC);
 	num_alloc = queue_size + allocator_pool_size;
 
@@ -1175,7 +1175,7 @@ int iwl_pcie_rx_init(struct iwl_trans *trans)
 	if (ret)
 		return ret;
 
-	if (trans->trans_cfg->mq_rx_supported)
+	if (trans->mac_cfg->mq_rx_supported)
 		iwl_pcie_rx_mq_hw_init(trans);
 	else
 		iwl_pcie_rx_hw_init(trans, trans_pcie->rxq);
@@ -1223,14 +1223,14 @@ void iwl_pcie_rx_free(struct iwl_trans *trans)
 
 	if (trans_pcie->base_rb_stts) {
 		dma_free_coherent(trans->dev,
-				  rb_stts_size * trans->num_rx_queues,
+				  rb_stts_size * trans->info.num_rxqs,
 				  trans_pcie->base_rb_stts,
 				  trans_pcie->base_rb_stts_dma);
 		trans_pcie->base_rb_stts = NULL;
 		trans_pcie->base_rb_stts_dma = 0;
 	}
 
-	for (i = 0; i < trans->num_rx_queues; i++) {
+	for (i = 0; i < trans->info.num_rxqs; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
 		iwl_pcie_free_rxq_dma(trans, rxq);
@@ -1301,7 +1301,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 				int i)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = trans_pcie->txqs.txq[trans_pcie->txqs.cmd.q_id];
+	struct iwl_txq *txq = trans_pcie->txqs.txq[trans->conf.cmd_queue];
 	bool page_stolen = false;
 	int max_len = trans_pcie->rx_buf_bytes;
 	u32 offset = 0;
@@ -1368,8 +1368,8 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		if (reclaim && !pkt->hdr.group_id) {
 			int i;
 
-			for (i = 0; i < trans_pcie->n_no_reclaim_cmds; i++) {
-				if (trans_pcie->no_reclaim_cmds[i] ==
+			for (i = 0; i < trans->conf.n_no_reclaim_cmds; i++) {
+				if (trans->conf.no_reclaim_cmds[i] ==
 							pkt->hdr.cmd) {
 					reclaim = false;
 					break;
@@ -1408,7 +1408,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		}
 
 		page_stolen |= rxcb._page_stolen;
-		if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+		if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 			break;
 	}
 
@@ -1454,18 +1454,18 @@ static struct iwl_rx_mem_buffer *iwl_pcie_get_rxb(struct iwl_trans *trans,
 	BUILD_BUG_ON(sizeof(struct iwl_rx_completion_desc) != 32);
 	BUILD_BUG_ON(sizeof(struct iwl_rx_completion_desc_bz) != 4);
 
-	if (!trans->trans_cfg->mq_rx_supported) {
+	if (!trans->mac_cfg->mq_rx_supported) {
 		rxb = rxq->queue[i];
 		rxq->queue[i] = NULL;
 		return rxb;
 	}
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
 		struct iwl_rx_completion_desc_bz *cd = rxq->used_bd;
 
 		vid = le16_to_cpu(cd[i].rbid);
 		*join = cd[i].flags & IWL_RX_CD_FLAGS_FRAGMENTED;
-	} else if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+	} else if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		struct iwl_rx_completion_desc *cd = rxq->used_bd;
 
 		vid = le16_to_cpu(cd[i].rbid);
@@ -1648,7 +1648,7 @@ irqreturn_t iwl_pcie_irq_rx_msix_handler(int irq, void *dev_id)
 
 	trace_iwlwifi_dev_irq_msix(trans->dev, entry, false, 0, 0);
 
-	if (WARN_ON(entry->entry >= trans->num_rx_queues))
+	if (WARN_ON(entry->entry >= trans->info.num_rxqs))
 		return IRQ_NONE;
 
 	if (!trans_pcie->rxq) {
@@ -1683,18 +1683,18 @@ static void iwl_pcie_irq_handle_error(struct iwl_trans *trans)
 
 	/* W/A for WiFi/WiMAX coex and WiMAX own the RF */
 	if (trans->cfg->internal_wimax_coex &&
-	    !trans->cfg->apmg_not_supported &&
+	    !trans->mac_cfg->base->apmg_not_supported &&
 	    (!(iwl_read_prph(trans, APMG_CLK_CTRL_REG) &
 			     APMS_CLK_VAL_MRB_FUNC_MODE) ||
 	     (iwl_read_prph(trans, APMG_PS_CTRL_REG) &
 			    APMG_PS_CTRL_VAL_RESET_REQ))) {
 		clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status);
 		iwl_op_mode_wimax_active(trans->op_mode);
-		wake_up(&trans->wait_command_queue);
+		wake_up(&trans_pcie->wait_command_queue);
 		return;
 	}
 
-	for (i = 0; i < trans->trans_cfg->base_params->num_of_queues; i++) {
+	for (i = 0; i < trans->mac_cfg->base->num_of_queues; i++) {
 		if (!trans_pcie->txqs.txq[i])
 			continue;
 		timer_delete(&trans_pcie->txqs.txq[i]->stuck_timer);
@@ -1705,7 +1705,7 @@ static void iwl_pcie_irq_handle_error(struct iwl_trans *trans)
 	iwl_trans_fw_error(trans, IWL_ERR_TYPE_IRQ);
 
 	clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status);
-	wake_up(&trans->wait_command_queue);
+	wake_up(&trans_pcie->wait_command_queue);
 }
 
 static u32 iwl_pcie_int_cause_non_ict(struct iwl_trans *trans)
@@ -1820,7 +1820,7 @@ void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq)
 				       &trans->status))
 			IWL_DEBUG_RF_KILL(trans,
 					  "Rfkill while SYNC HCMD in flight\n");
-		wake_up(&trans->wait_command_queue);
+		wake_up(&trans_pcie->wait_command_queue);
 	} else {
 		clear_bit(STATUS_RFKILL_HW, &trans->status);
 		if (trans_pcie->opmode_down)
@@ -1828,6 +1828,54 @@ void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq)
 	}
 }
 
+static void iwl_trans_pcie_handle_reset_interrupt(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	u32 state;
+
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_SC) {
+		u32 val = iwl_read32(trans, CSR_IPC_STATE);
+
+		state = u32_get_bits(val, CSR_IPC_STATE_RESET);
+		IWL_DEBUG_ISR(trans, "IPC state = 0x%x/%d\n", val, state);
+	} else {
+		state = CSR_IPC_STATE_RESET_SW_READY;
+	}
+
+	switch (state) {
+	case CSR_IPC_STATE_RESET_SW_READY:
+		if (trans_pcie->fw_reset_state == FW_RESET_REQUESTED) {
+			IWL_DEBUG_ISR(trans, "Reset flow completed\n");
+			trans_pcie->fw_reset_state = FW_RESET_OK;
+			wake_up(&trans_pcie->fw_reset_waitq);
+			break;
+		}
+		fallthrough;
+	case CSR_IPC_STATE_RESET_TOP_READY:
+		/* FIXME: handle this case when requesting TOP reset */
+		fallthrough;
+	case CSR_IPC_STATE_RESET_NONE:
+		IWL_FW_CHECK_FAILED(trans,
+				    "Invalid reset interrupt (state=%d)!\n",
+				    state);
+		break;
+	case CSR_IPC_STATE_RESET_TOP_FOLLOWER:
+		if (trans_pcie->fw_reset_state == FW_RESET_REQUESTED) {
+			/* if we were in reset, wake that up */
+			IWL_INFO(trans,
+				 "TOP reset from BT while doing reset\n");
+			trans_pcie->fw_reset_state = FW_RESET_OK;
+			wake_up(&trans_pcie->fw_reset_waitq);
+		} else {
+			IWL_INFO(trans, "TOP reset from BT\n");
+			trans->state = IWL_TRANS_NO_FW;
+			iwl_trans_schedule_reset(trans,
+						 IWL_ERR_TYPE_TOP_RESET_BY_BT);
+		}
+		break;
+	}
+}
+
 irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 {
 	struct iwl_trans *trans = dev_id;
@@ -1936,7 +1984,7 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 	if (inta & CSR_INT_BIT_ALIVE) {
 		IWL_DEBUG_ISR(trans, "Alive interrupt\n");
 		isr_stats->alive++;
-		if (trans->trans_cfg->gen2) {
+		if (trans->mac_cfg->gen2) {
 			/*
 			 * We can restock, since firmware configured
 			 * the RFH
@@ -1947,6 +1995,11 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 		handled |= CSR_INT_BIT_ALIVE;
 	}
 
+	if (inta & CSR_INT_BIT_RESET_DONE) {
+		iwl_trans_pcie_handle_reset_interrupt(trans);
+		handled |= CSR_INT_BIT_RESET_DONE;
+	}
+
 	/* Safely ignore these bits for debug checks below */
 	inta &= ~(CSR_INT_BIT_SCD | CSR_INT_BIT_ALIVE);
 
@@ -1968,7 +2021,12 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 		IWL_ERR(trans, "Microcode SW error detected. "
 			" Restarting 0x%X.\n", inta);
 		isr_stats->sw++;
-		iwl_pcie_irq_handle_error(trans);
+		if (trans_pcie->fw_reset_state == FW_RESET_REQUESTED) {
+			trans_pcie->fw_reset_state = FW_RESET_ERROR;
+			wake_up(&trans_pcie->fw_reset_waitq);
+		} else {
+			iwl_pcie_irq_handle_error(trans);
+		}
 		handled |= CSR_INT_BIT_SW_ERR;
 	}
 
@@ -2074,7 +2132,7 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 			iwl_enable_rfkill_int(trans);
 		/* Re-enable the ALIVE / Rx interrupt if it occurred */
 		else if (handled & (CSR_INT_BIT_ALIVE | CSR_INT_BIT_FH_RX))
-			iwl_enable_fw_load_int_ctx_info(trans);
+			iwl_enable_fw_load_int_ctx_info(trans, false);
 		spin_unlock_bh(&trans_pcie->irq_lock);
 	}
 
@@ -2289,7 +2347,7 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 		}
 	}
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 		sw_err = inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR_BZ;
 	else
 		sw_err = inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR;
@@ -2297,9 +2355,13 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 	if (inta_hw & MSIX_HW_INT_CAUSES_REG_TOP_FATAL_ERR) {
 		IWL_ERR(trans, "TOP Fatal error detected, inta_hw=0x%x.\n",
 			inta_hw);
-		if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
-			iwl_trans_pcie_reset(trans,
-					     IWL_RESET_MODE_PROD_RESET);
+		if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+			trans->request_top_reset = 1;
+			iwl_op_mode_nic_error(trans->op_mode,
+					      IWL_ERR_TYPE_TOP_FATAL_ERROR);
+			iwl_trans_schedule_reset(trans,
+						 IWL_ERR_TYPE_TOP_FATAL_ERROR);
+		}
 	}
 
 	/* Error detected by uCode */
@@ -2338,7 +2400,7 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 	if (inta_hw & MSIX_HW_INT_CAUSES_REG_ALIVE) {
 		IWL_DEBUG_ISR(trans, "Alive interrupt\n");
 		isr_stats->alive++;
-		if (trans->trans_cfg->gen2) {
+		if (trans->mac_cfg->gen2) {
 			/* We can restock, since firmware configured the RFH */
 			iwl_pcie_rxmq_restock(trans, trans_pcie->rxq);
 		}
@@ -2388,11 +2450,8 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 		iwl_pcie_irq_handle_error(trans);
 	}
 
-	if (inta_hw & MSIX_HW_INT_CAUSES_REG_RESET_DONE) {
-		IWL_DEBUG_ISR(trans, "Reset flow completed\n");
-		trans_pcie->fw_reset_state = FW_RESET_OK;
-		wake_up(&trans_pcie->fw_reset_waitq);
-	}
+	if (inta_hw & MSIX_HW_INT_CAUSES_REG_RESET_DONE)
+		iwl_trans_pcie_handle_reset_interrupt(trans);
 
 	if (!polling)
 		iwl_pcie_clear_irq(trans, entry->entry);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index 3ece34e30d58..38ad719161e6 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -6,7 +6,7 @@
 #include "iwl-trans.h"
 #include "iwl-prph.h"
 #include "iwl-context-info.h"
-#include "iwl-context-info-gen3.h"
+#include "iwl-context-info-v2.h"
 #include "internal.h"
 #include "fw/dbg.h"
 
@@ -81,13 +81,13 @@ static void iwl_pcie_gen2_apm_stop(struct iwl_trans *trans, bool op_mode_leave)
 	/* Stop device's DMA activity */
 	iwl_pcie_apm_stop_master(trans);
 
-	iwl_trans_sw_reset(trans, false);
+	iwl_trans_pcie_sw_reset(trans, false);
 
 	/*
 	 * Clear "initialization complete" bit to move adapter from
 	 * D0A* (powered-up Active) --> D0U* (Uninitialized) state.
 	 */
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 		iwl_clear_bit(trans, CSR_GP_CNTRL,
 			      CSR_GP_CNTRL_REG_FLAG_MAC_INIT);
 	else
@@ -102,10 +102,10 @@ void iwl_trans_pcie_fw_reset_handshake(struct iwl_trans *trans)
 
 	trans_pcie->fw_reset_state = FW_RESET_REQUESTED;
 
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		iwl_write_umac_prph(trans, UREG_NIC_SET_NMI_DRIVER,
 				    UREG_NIC_SET_NMI_DRIVER_RESET_HANDSHAKE);
-	else if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210)
+	else if (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_AX210)
 		iwl_write_umac_prph(trans, UREG_DOORBELL_TO_ISR6,
 				    UREG_DOORBELL_TO_ISR6_RESET_HANDSHAKE);
 	else
@@ -117,13 +117,23 @@ void iwl_trans_pcie_fw_reset_handshake(struct iwl_trans *trans)
 				 trans_pcie->fw_reset_state != FW_RESET_REQUESTED,
 				 FW_RESET_TIMEOUT);
 	if (!ret || trans_pcie->fw_reset_state == FW_RESET_ERROR) {
-		u32 inta_hw = iwl_read32(trans, CSR_MSIX_HW_INT_CAUSES_AD);
+		bool reset_done;
+		u32 inta_hw;
+
+		if (trans_pcie->msix_enabled) {
+			inta_hw = iwl_read32(trans, CSR_MSIX_HW_INT_CAUSES_AD);
+			reset_done =
+				inta_hw & MSIX_HW_INT_CAUSES_REG_RESET_DONE;
+		} else {
+			inta_hw = iwl_read32(trans, CSR_INT_MASK);
+			reset_done = inta_hw & CSR_INT_BIT_RESET_DONE;
+		}
 
 		IWL_ERR(trans,
-			"timeout waiting for FW reset ACK (inta_hw=0x%x)\n",
-			inta_hw);
+			"timeout waiting for FW reset ACK (inta_hw=0x%x, reset_done %d)\n",
+			inta_hw, reset_done);
 
-		if (!(inta_hw & MSIX_HW_INT_CAUSES_REG_RESET_DONE)) {
+		if (!reset_done) {
 			struct iwl_fw_error_dump_mode mode = {
 				.type = IWL_ERR_TYPE_RESET_HS_TIMEOUT,
 				.context = IWL_ERR_CONTEXT_FROM_OPMODE,
@@ -147,8 +157,14 @@ static void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans)
 		return;
 
 	if (trans->state >= IWL_TRANS_FW_STARTED &&
-	    trans_pcie->fw_reset_handshake)
+	    trans->conf.fw_reset_handshake) {
+		/*
+		 * Reset handshake can dump firmware on timeout, but that
+		 * should assume that the firmware is already dead.
+		 */
+		trans->state = IWL_TRANS_NO_FW;
 		iwl_trans_pcie_fw_reset_handshake(trans);
+	}
 
 	trans_pcie->is_down = true;
 
@@ -175,8 +191,8 @@ static void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans)
 	}
 
 	iwl_pcie_ctxt_info_free_paging(trans);
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
-		iwl_pcie_ctxt_info_gen3_free(trans, false);
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+		iwl_pcie_ctxt_info_v2_free(trans, false);
 	else
 		iwl_pcie_ctxt_info_free(trans);
 
@@ -184,7 +200,7 @@ static void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans)
 	iwl_pcie_gen2_apm_stop(trans, false);
 
 	/* re-take ownership to prevent other users from stealing the device */
-	iwl_trans_sw_reset(trans, true);
+	iwl_trans_pcie_sw_reset(trans, true);
 
 	/*
 	 * Upon stop, the IVAR table gets erased, so msi-x won't
@@ -237,7 +253,7 @@ static int iwl_pcie_gen2_nic_init(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int queue_size = max_t(u32, IWL_CMD_QUEUE_SIZE,
-			       trans->cfg->min_txq_size);
+			       trans->mac_cfg->base->min_txq_size);
 	int ret;
 
 	/* TODO: most of the logic can be removed in A0 - but not in Z0 */
@@ -254,7 +270,7 @@ static int iwl_pcie_gen2_nic_init(struct iwl_trans *trans)
 		return -ENOMEM;
 
 	/* Allocate or reset and init all Tx and Command queues */
-	if (iwl_txq_gen2_init(trans, trans_pcie->txqs.cmd.q_id, queue_size))
+	if (iwl_txq_gen2_init(trans, trans->conf.cmd_queue, queue_size))
 		return -ENOMEM;
 
 	/* enable shadow regs in HW */
@@ -275,7 +291,7 @@ static void iwl_pcie_get_rf_name(struct iwl_trans *trans)
 	if (buf[0])
 		return;
 
-	switch (CSR_HW_RFID_TYPE(trans->hw_rf_id)) {
+	switch (CSR_HW_RFID_TYPE(trans->info.hw_rf_id)) {
 	case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_JF):
 		pos = scnprintf(buf, buflen, "JF");
 		break;
@@ -299,7 +315,7 @@ static void iwl_pcie_get_rf_name(struct iwl_trans *trans)
 		break;
 	case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_WP):
 		if (SILICON_Z_STEP ==
-		    CSR_HW_RFID_STEP(trans->hw_rf_id))
+		    CSR_HW_RFID_STEP(trans->info.hw_rf_id))
 			pos = scnprintf(buf, buflen, "WHTC");
 		else
 			pos = scnprintf(buf, buflen, "WH");
@@ -308,7 +324,7 @@ static void iwl_pcie_get_rf_name(struct iwl_trans *trans)
 		return;
 	}
 
-	switch (CSR_HW_RFID_TYPE(trans->hw_rf_id)) {
+	switch (CSR_HW_RFID_TYPE(trans->info.hw_rf_id)) {
 	case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_HR):
 	case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_HR1):
 	case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_HRCDB):
@@ -331,7 +347,7 @@ static void iwl_pcie_get_rf_name(struct iwl_trans *trans)
 	}
 
 	pos += scnprintf(buf + pos, buflen - pos, ", rfid=0x%x",
-			 trans->hw_rf_id);
+			 trans->info.hw_rf_id);
 
 	IWL_INFO(trans, "Detected RF %s\n", buf);
 
@@ -358,8 +374,8 @@ void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans)
 	/* now that we got alive we can free the fw image & the context info.
 	 * paging memory cannot be freed included since FW will still use it
 	 */
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
-		iwl_pcie_ctxt_info_gen3_free(trans, true);
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+		iwl_pcie_ctxt_info_v2_free(trans, true);
 	else
 		iwl_pcie_ctxt_info_free(trans);
 
@@ -373,6 +389,11 @@ void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans)
 
 	iwl_pcie_get_rf_name(trans);
 	mutex_unlock(&trans_pcie->mutex);
+
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+		trans->step_urm = !!(iwl_read_umac_prph(trans,
+							CNVI_PMU_STEP_FLOW) &
+					CNVI_PMU_STEP_FLOW_FORCE_URM);
 }
 
 static bool iwl_pcie_set_ltr(struct iwl_trans *trans)
@@ -392,21 +413,21 @@ static bool iwl_pcie_set_ltr(struct iwl_trans *trans)
 	 * initialize the LTR to ~250 usec (see ltr_val above).
 	 * The firmware initializes this again later (to a smaller value).
 	 */
-	if ((trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210 ||
-	     trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) &&
-	    !trans->trans_cfg->integrated) {
+	if ((trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_AX210 ||
+	     trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_22000) &&
+	    !trans->mac_cfg->integrated) {
 		iwl_write32(trans, CSR_LTR_LONG_VAL_AD, ltr_val);
 		return true;
 	}
 
-	if (trans->trans_cfg->integrated &&
-	    trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) {
+	if (trans->mac_cfg->integrated &&
+	    trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_22000) {
 		iwl_write_prph(trans, HPM_MAC_LTR_CSR, HPM_MAC_LRT_ENABLE_ALL);
 		iwl_write_prph(trans, HPM_UMAC_LTR, ltr_val);
 		return true;
 	}
 
-	if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210) {
+	if (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_AX210) {
 		/* First clear the interrupt, just in case */
 		iwl_write32(trans, CSR_MSIX_HW_INT_CAUSES_AD,
 			    MSIX_HW_INT_CAUSES_REG_IML);
@@ -463,16 +484,22 @@ static void iwl_pcie_spin_for_iml(struct iwl_trans *trans)
 }
 
 int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
-				 const struct fw_img *fw, bool run_in_rfkill)
+				 const struct iwl_fw *fw,
+				 const struct fw_img *img,
+				 bool run_in_rfkill)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	bool hw_rfkill, keep_ram_busy;
+	bool top_reset_done = false;
 	int ret;
 
+	mutex_lock(&trans_pcie->mutex);
+again:
 	/* This may fail if AMT took ownership of the device */
 	if (iwl_pcie_prepare_card_hw(trans)) {
 		IWL_WARN(trans, "Exit HW not ready\n");
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
 	iwl_enable_rfkill_int(trans);
@@ -489,8 +516,6 @@ int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 	/* Make sure it finished running */
 	iwl_pcie_synchronize_irqs(trans);
 
-	mutex_lock(&trans_pcie->mutex);
-
 	/* If platform's RF_KILL switch is NOT set to KILL */
 	hw_rfkill = iwl_pcie_check_hw_rf_kill(trans);
 	if (hw_rfkill && !run_in_rfkill) {
@@ -520,22 +545,37 @@ int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 		goto out;
 	}
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
-		ret = iwl_pcie_ctxt_info_gen3_init(trans, fw);
-	else
-		ret = iwl_pcie_ctxt_info_init(trans, fw);
-	if (ret)
-		goto out;
+	if (WARN_ON(trans->do_top_reset &&
+		    trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_SC))
+		return -EINVAL;
+
+	/* we need to wait later - set state */
+	if (trans->do_top_reset)
+		trans_pcie->fw_reset_state = FW_RESET_TOP_REQUESTED;
+
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+		if (!top_reset_done) {
+			ret = iwl_pcie_ctxt_info_v2_alloc(trans, fw, img);
+			if (ret)
+				goto out;
+		}
+
+		iwl_pcie_ctxt_info_v2_kick(trans);
+	} else {
+		ret = iwl_pcie_ctxt_info_init(trans, img);
+		if (ret)
+			goto out;
+	}
 
 	keep_ram_busy = !iwl_pcie_set_ltr(trans);
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
 		IWL_DEBUG_POWER(trans, "function scratch register value is 0x%08x\n",
 				iwl_read32(trans, CSR_FUNC_SCRATCH));
 		iwl_write32(trans, CSR_FUNC_SCRATCH, CSR_FUNC_SCRATCH_INIT_VALUE);
 		iwl_set_bit(trans, CSR_GP_CNTRL,
 			    CSR_GP_CNTRL_REG_FLAG_ROM_START);
-	} else if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+	} else if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1);
 	} else {
 		iwl_write_prph(trans, UREG_CPU_INIT_RUN, 1);
@@ -544,6 +584,38 @@ int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 	if (keep_ram_busy)
 		iwl_pcie_spin_for_iml(trans);
 
+	if (trans->do_top_reset) {
+		trans->do_top_reset = 0;
+
+#define FW_TOP_RESET_TIMEOUT	(HZ / 4)
+		ret = wait_event_timeout(trans_pcie->fw_reset_waitq,
+					 trans_pcie->fw_reset_state != FW_RESET_TOP_REQUESTED,
+					 FW_TOP_RESET_TIMEOUT);
+
+		if (trans_pcie->fw_reset_state != FW_RESET_OK) {
+			if (trans_pcie->fw_reset_state != FW_RESET_TOP_REQUESTED)
+				IWL_ERR(trans,
+					"TOP reset interrupted by error (state %d)!\n",
+					trans_pcie->fw_reset_state);
+			else
+				IWL_ERR(trans, "TOP reset timed out!\n");
+			iwl_op_mode_nic_error(trans->op_mode,
+					      IWL_ERR_TYPE_TOP_RESET_FAILED);
+			iwl_trans_schedule_reset(trans,
+						 IWL_ERR_TYPE_TOP_RESET_FAILED);
+			ret = -EIO;
+			goto out;
+		}
+
+		msleep(10);
+		IWL_INFO(trans, "TOP reset successful, reinit now\n");
+		/* now load the firmware again properly */
+		trans_pcie->prph_scratch->ctrl_cfg.control.control_flags &=
+			~cpu_to_le32(IWL_PRPH_SCRATCH_TOP_RESET);
+		top_reset_done = true;
+		goto again;
+	}
+
 	/* re-check RF-Kill state since we may have missed the interrupt */
 	hw_rfkill = iwl_pcie_check_hw_rf_kill(trans);
 	if (hw_rfkill && !run_in_rfkill)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index c917ed4c19bc..cc4d289b110d 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -28,7 +28,7 @@
 #include "mei/iwl-mei.h"
 #include "internal.h"
 #include "iwl-fh.h"
-#include "iwl-context-info-gen3.h"
+#include "iwl-context-info-v2.h"
 
 /* extended range in FW SRAM */
 #define IWL_FW_MEM_EXTENDED_START	0x40000
@@ -131,7 +131,7 @@ out:
 int iwl_trans_pcie_sw_reset(struct iwl_trans *trans, bool retake_ownership)
 {
 	/* Reset entire device - do controller reset (results in SHRD_HW_RST) */
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
 		iwl_set_bit(trans, CSR_GP_CNTRL,
 			    CSR_GP_CNTRL_REG_FLAG_SW_RESET);
 		usleep_range(10000, 20000);
@@ -237,7 +237,7 @@ static void iwl_trans_pcie_write_shr(struct iwl_trans *trans, u32 reg, u32 val)
 
 static void iwl_pcie_set_pwr(struct iwl_trans *trans, bool vaux)
 {
-	if (trans->cfg->apmg_not_supported)
+	if (trans->mac_cfg->base->apmg_not_supported)
 		return;
 
 	if (vaux && pci_pme_capable(to_pci_dev(trans->dev), PCI_D3cold))
@@ -293,7 +293,7 @@ static int iwl_pcie_apm_init(struct iwl_trans *trans)
 	 */
 
 	/* Disable L0S exit timer (platform NMI Work/Around) */
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_8000)
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_8000)
 		iwl_set_bit(trans, CSR_GIO_CHICKEN_BITS,
 			    CSR_GIO_CHICKEN_BITS_REG_BIT_DIS_L0S_EXIT_TIMER);
 
@@ -317,7 +317,7 @@ static int iwl_pcie_apm_init(struct iwl_trans *trans)
 	iwl_pcie_apm_config(trans);
 
 	/* Configure analog phase-lock-loop before activating to D0A */
-	if (trans->trans_cfg->base_params->pll_cfg)
+	if (trans->mac_cfg->base->pll_cfg)
 		iwl_set_bit(trans, CSR_ANA_PLL_CFG, CSR50_ANA_PLL_CFG_VAL);
 
 	ret = iwl_finish_nic_init(trans);
@@ -353,7 +353,7 @@ static int iwl_pcie_apm_init(struct iwl_trans *trans)
 	 * bits do not disable clocks.  This preserves any hardware
 	 * bits already set by default in "CLK_CTRL_REG" after reset.
 	 */
-	if (!trans->cfg->apmg_not_supported) {
+	if (!trans->mac_cfg->base->apmg_not_supported) {
 		iwl_write_prph(trans, APMG_CLK_EN_REG,
 			       APMG_CLK_VAL_DMA_CLK_RQT);
 		udelay(20);
@@ -469,7 +469,7 @@ void iwl_pcie_apm_stop_master(struct iwl_trans *trans)
 
 	/* stop device's busmaster DMA activity */
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
 		iwl_set_bit(trans, CSR_GP_CNTRL,
 			    CSR_GP_CNTRL_REG_FLAG_BUS_MASTER_DISABLE_REQ);
 
@@ -501,10 +501,10 @@ static void iwl_pcie_apm_stop(struct iwl_trans *trans, bool op_mode_leave)
 			iwl_pcie_apm_init(trans);
 
 		/* inform ME that we are leaving */
-		if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_7000)
+		if (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_7000)
 			iwl_set_bits_prph(trans, APMG_PCIDEV_STT_REG,
 					  APMG_PCIDEV_STT_VAL_WAKE_ME);
-		else if (trans->trans_cfg->device_family >=
+		else if (trans->mac_cfg->device_family >=
 			 IWL_DEVICE_FAMILY_8000) {
 			iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
 				    CSR_RESET_LINK_PWR_MGMT_DISABLED);
@@ -565,7 +565,7 @@ static int iwl_pcie_nic_init(struct iwl_trans *trans)
 		return -ENOMEM;
 	}
 
-	if (trans->trans_cfg->base_params->shadow_reg_enable) {
+	if (trans->mac_cfg->base->shadow_reg_enable) {
 		/* enable shadow regs in HW */
 		iwl_set_bit(trans, CSR_MAC_SHADOW_REG_CTRL, 0x800FFFFF);
 		IWL_DEBUG_INFO(trans, "Enabling shadow registers in device\n");
@@ -634,7 +634,7 @@ int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 				IWL_DEBUG_INFO(trans,
 					       "Couldn't prepare the card but SAP is connected\n");
 				trans->csme_own = true;
-				if (trans->trans_cfg->device_family !=
+				if (trans->mac_cfg->device_family !=
 				    IWL_DEVICE_FAMILY_9000)
 					IWL_ERR(trans,
 						"SAP not supported for this NIC family\n");
@@ -819,7 +819,7 @@ static int iwl_pcie_load_cpu_sections_8000(struct iwl_trans *trans,
 
 	iwl_enable_interrupts(trans);
 
-	if (trans->trans_cfg->gen2) {
+	if (trans->mac_cfg->gen2) {
 		if (cpu == 1)
 			iwl_write_prph(trans, UREG_UCODE_LOAD_STATUS,
 				       0xFFFF);
@@ -977,7 +977,7 @@ monitor:
 	if (dest->monitor_mode == EXTERNAL_MODE && fw_mon->size) {
 		iwl_write_prph(trans, le32_to_cpu(dest->base_reg),
 			       fw_mon->physical >> dest->base_shift);
-		if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_8000)
+		if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_8000)
 			iwl_write_prph(trans, le32_to_cpu(dest->end_reg),
 				       (fw_mon->physical + fw_mon->size -
 					256) >> dest->end_shift);
@@ -1153,7 +1153,7 @@ static void iwl_pcie_map_non_rx_causes(struct iwl_trans *trans)
 	 */
 	iwl_pcie_map_list(trans, causes_list_common,
 			  ARRAY_SIZE(causes_list_common), val);
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 		iwl_pcie_map_list(trans, causes_list_bz,
 				  ARRAY_SIZE(causes_list_bz), val);
 	else
@@ -1175,7 +1175,7 @@ static void iwl_pcie_map_rx_causes(struct iwl_trans *trans)
 	 * the other (N - 2) interrupt vectors.
 	 */
 	val = BIT(MSIX_FH_INT_CAUSES_Q(0));
-	for (idx = 1; idx < trans->num_rx_queues; idx++) {
+	for (idx = 1; idx < trans->info.num_rxqs; idx++) {
 		iwl_write8(trans, CSR_MSIX_RX_IVAR(idx),
 			   MSIX_FH_INT_CAUSES_Q(idx - offset));
 		val |= BIT(MSIX_FH_INT_CAUSES_Q(idx));
@@ -1196,7 +1196,7 @@ void iwl_pcie_conf_msix_hw(struct iwl_trans_pcie *trans_pcie)
 	struct iwl_trans *trans = trans_pcie->trans;
 
 	if (!trans_pcie->msix_enabled) {
-		if (trans->trans_cfg->mq_rx_supported &&
+		if (trans->mac_cfg->mq_rx_supported &&
 		    test_bit(STATUS_DEVICE_ENABLED, &trans->status))
 			iwl_write_umac_prph(trans, UREG_CHICK,
 					    UREG_CHICK_MSI_ENABLE);
@@ -1271,7 +1271,7 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool from_irq)
 		iwl_pcie_rx_stop(trans);
 
 		/* Power-down device's busmaster DMA clocks */
-		if (!trans->cfg->apmg_not_supported) {
+		if (!trans->mac_cfg->base->apmg_not_supported) {
 			iwl_write_prph(trans, APMG_CLK_DIS_REG,
 				       APMG_CLK_VAL_DMA_CLK_RQT);
 			udelay(5);
@@ -1279,7 +1279,7 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool from_irq)
 	}
 
 	/* Make sure (redundant) we've released our request to stay awake */
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 		iwl_clear_bit(trans, CSR_GP_CNTRL,
 			      CSR_GP_CNTRL_REG_FLAG_BZ_MAC_ACCESS_REQ);
 	else
@@ -1337,7 +1337,9 @@ void iwl_pcie_synchronize_irqs(struct iwl_trans *trans)
 }
 
 int iwl_trans_pcie_start_fw(struct iwl_trans *trans,
-			    const struct fw_img *fw, bool run_in_rfkill)
+			    const struct iwl_fw *fw,
+			    const struct fw_img *img,
+			    bool run_in_rfkill)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	bool hw_rfkill;
@@ -1408,10 +1410,10 @@ int iwl_trans_pcie_start_fw(struct iwl_trans *trans,
 	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
 
 	/* Load the given image to the HW */
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_8000)
-		ret = iwl_pcie_load_given_ucode_8000(trans, fw);
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_8000)
+		ret = iwl_pcie_load_given_ucode_8000(trans, img);
 	else
-		ret = iwl_pcie_load_given_ucode(trans, fw);
+		ret = iwl_pcie_load_given_ucode(trans, img);
 
 	/* re-check RF-Kill state since we may have missed the interrupt */
 	hw_rfkill = iwl_pcie_check_hw_rf_kill(trans);
@@ -1423,10 +1425,10 @@ out:
 	return ret;
 }
 
-void iwl_trans_pcie_fw_alive(struct iwl_trans *trans, u32 scd_addr)
+void iwl_trans_pcie_fw_alive(struct iwl_trans *trans)
 {
 	iwl_pcie_reset_ict(trans);
-	iwl_pcie_tx_start(trans, scd_addr);
+	iwl_pcie_tx_start(trans);
 }
 
 void iwl_trans_pcie_handle_stop_rfkill(struct iwl_trans *trans,
@@ -1485,7 +1487,7 @@ void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq)
 	IWL_WARN(trans, "reporting RF_KILL (radio %s)\n",
 		 state ? "disabled" : "enabled");
 	if (iwl_op_mode_hw_rf_kill(trans->op_mode, state) &&
-	    !WARN_ON(trans->trans_cfg->gen2))
+	    !WARN_ON(trans->mac_cfg->gen2))
 		_iwl_trans_pcie_stop_device(trans, from_irq);
 }
 
@@ -1505,7 +1507,7 @@ static void iwl_pcie_d3_complete_suspend(struct iwl_trans *trans,
 
 	iwl_pcie_synchronize_irqs(trans);
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
 		iwl_clear_bit(trans, CSR_GP_CNTRL,
 			      CSR_GP_CNTRL_REG_FLAG_BZ_MAC_ACCESS_REQ);
 		iwl_clear_bit(trans, CSR_GP_CNTRL,
@@ -1534,11 +1536,11 @@ static int iwl_pcie_d3_handshake(struct iwl_trans *trans, bool suspend)
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int ret;
 
-	if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210)
+	if (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_AX210)
 		iwl_write_umac_prph(trans, UREG_DOORBELL_TO_ISR6,
 				    suspend ? UREG_DOORBELL_TO_ISR6_SUSPEND :
 					      UREG_DOORBELL_TO_ISR6_RESUME);
-	else if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	else if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 		iwl_write32(trans, CSR_IPC_SLEEP_CONTROL,
 			    suspend ? CSR_IPC_SLEEP_CONTROL_SUSPEND :
 				      CSR_IPC_SLEEP_CONTROL_RESUME);
@@ -1593,7 +1595,7 @@ int iwl_trans_pcie_d3_resume(struct iwl_trans *trans,
 		goto out;
 	}
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 		iwl_set_bit(trans, CSR_GP_CNTRL,
 			    CSR_GP_CNTRL_REG_FLAG_BZ_MAC_ACCESS_REQ);
 	else
@@ -1653,17 +1655,18 @@ out:
 static void
 iwl_pcie_set_interrupt_capa(struct pci_dev *pdev,
 			    struct iwl_trans *trans,
-			    const struct iwl_cfg_trans_params *cfg_trans)
+			    const struct iwl_mac_cfg *mac_cfg,
+			    struct iwl_trans_info *info)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int max_irqs, num_irqs, i, ret;
 	u16 pci_cmd;
 	u32 max_rx_queues = IWL_MAX_RX_HW_QUEUES;
 
-	if (!cfg_trans->mq_rx_supported)
+	if (!mac_cfg->mq_rx_supported)
 		goto enable_msi;
 
-	if (cfg_trans->device_family <= IWL_DEVICE_FAMILY_9000)
+	if (mac_cfg->device_family <= IWL_DEVICE_FAMILY_9000)
 		max_rx_queues = IWL_9000_MAX_RX_HW_QUEUES;
 
 	max_irqs = min_t(u32, num_online_cpus() + 2, max_rx_queues);
@@ -1693,27 +1696,28 @@ iwl_pcie_set_interrupt_capa(struct pci_dev *pdev,
 	 * More than two interrupts: we will use fewer RSS queues.
 	 */
 	if (num_irqs <= max_irqs - 2) {
-		trans_pcie->trans->num_rx_queues = num_irqs + 1;
+		info->num_rxqs = num_irqs + 1;
 		trans_pcie->shared_vec_mask = IWL_SHARED_IRQ_NON_RX |
 			IWL_SHARED_IRQ_FIRST_RSS;
 	} else if (num_irqs == max_irqs - 1) {
-		trans_pcie->trans->num_rx_queues = num_irqs;
+		info->num_rxqs = num_irqs;
 		trans_pcie->shared_vec_mask = IWL_SHARED_IRQ_NON_RX;
 	} else {
-		trans_pcie->trans->num_rx_queues = num_irqs - 1;
+		info->num_rxqs = num_irqs - 1;
 	}
 
 	IWL_DEBUG_INFO(trans,
 		       "MSI-X enabled with rx queues %d, vec mask 0x%x\n",
-		       trans_pcie->trans->num_rx_queues, trans_pcie->shared_vec_mask);
+		       info->num_rxqs, trans_pcie->shared_vec_mask);
 
-	WARN_ON(trans_pcie->trans->num_rx_queues > IWL_MAX_RX_HW_QUEUES);
+	WARN_ON(info->num_rxqs > IWL_MAX_RX_HW_QUEUES);
 
 	trans_pcie->alloc_vecs = num_irqs;
 	trans_pcie->msix_enabled = true;
 	return;
 
 enable_msi:
+	info->num_rxqs = 1;
 	ret = pci_enable_msi(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "pci_enable_msi failed - %d\n", ret);
@@ -1726,14 +1730,15 @@ enable_msi:
 	}
 }
 
-static void iwl_pcie_irq_set_affinity(struct iwl_trans *trans)
+static void iwl_pcie_irq_set_affinity(struct iwl_trans *trans,
+				      struct iwl_trans_info *info)
 {
 #if defined(CONFIG_SMP)
 	int iter_rx_q, i, ret, cpu, offset;
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
 	i = trans_pcie->shared_vec_mask & IWL_SHARED_IRQ_FIRST_RSS ? 0 : 1;
-	iter_rx_q = trans_pcie->trans->num_rx_queues - 1 + i;
+	iter_rx_q = info->num_rxqs - 1 + i;
 	offset = 1 + i;
 	for (; i < iter_rx_q ; i++) {
 		/*
@@ -1753,7 +1758,8 @@ static void iwl_pcie_irq_set_affinity(struct iwl_trans *trans)
 }
 
 static int iwl_pcie_init_msix_handler(struct pci_dev *pdev,
-				      struct iwl_trans_pcie *trans_pcie)
+				      struct iwl_trans_pcie *trans_pcie,
+				      struct iwl_trans_info *info)
 {
 	int i;
 
@@ -1782,7 +1788,7 @@ static int iwl_pcie_init_msix_handler(struct pci_dev *pdev,
 			return ret;
 		}
 	}
-	iwl_pcie_irq_set_affinity(trans_pcie->trans);
+	iwl_pcie_irq_set_affinity(trans_pcie->trans, info);
 
 	return 0;
 }
@@ -1791,7 +1797,7 @@ static int iwl_trans_pcie_clear_persistence_bit(struct iwl_trans *trans)
 {
 	u32 hpm, wprot;
 
-	switch (trans->trans_cfg->device_family) {
+	switch (trans->mac_cfg->device_family) {
 	case IWL_DEVICE_FAMILY_9000:
 		wprot = PREG_PRPH_WPROT_9000;
 		break;
@@ -1860,8 +1866,8 @@ static int _iwl_trans_pcie_start_hw(struct iwl_trans *trans)
 	if (err)
 		return err;
 
-	if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000 &&
-	    trans->trans_cfg->integrated) {
+	if (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_22000 &&
+	    trans->mac_cfg->integrated) {
 		err = iwl_pcie_gen2_force_power_gating(trans);
 		if (err)
 			return err;
@@ -1936,7 +1942,7 @@ u32 iwl_trans_pcie_read32(struct iwl_trans *trans, u32 ofs)
 
 static u32 iwl_trans_pcie_prph_msk(struct iwl_trans *trans)
 {
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 		return 0x00FFFFFF;
 	else
 		return 0x000FFFFF;
@@ -1960,45 +1966,17 @@ void iwl_trans_pcie_write_prph(struct iwl_trans *trans, u32 addr, u32 val)
 	iwl_trans_pcie_write32(trans, HBUS_TARG_PRPH_WDAT, val);
 }
 
-void iwl_trans_pcie_configure(struct iwl_trans *trans,
-			      const struct iwl_trans_config *trans_cfg)
+void iwl_trans_pcie_op_mode_enter(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
 	/* free all first - we might be reconfigured for a different size */
 	iwl_pcie_free_rbs_pool(trans);
 
-	trans_pcie->txqs.cmd.q_id = trans_cfg->cmd_queue;
-	trans_pcie->txqs.cmd.fifo = trans_cfg->cmd_fifo;
-	trans_pcie->txqs.page_offs = trans_cfg->cb_data_offs;
-	trans_pcie->txqs.dev_cmd_offs = trans_cfg->cb_data_offs + sizeof(void *);
-	trans_pcie->txqs.queue_alloc_cmd_ver = trans_cfg->queue_alloc_cmd_ver;
-
-	if (WARN_ON(trans_cfg->n_no_reclaim_cmds > MAX_NO_RECLAIM_CMDS))
-		trans_pcie->n_no_reclaim_cmds = 0;
-	else
-		trans_pcie->n_no_reclaim_cmds = trans_cfg->n_no_reclaim_cmds;
-	if (trans_pcie->n_no_reclaim_cmds)
-		memcpy(trans_pcie->no_reclaim_cmds, trans_cfg->no_reclaim_cmds,
-		       trans_pcie->n_no_reclaim_cmds * sizeof(u8));
-
-	trans_pcie->rx_buf_size = trans_cfg->rx_buf_size;
 	trans_pcie->rx_page_order =
-		iwl_trans_get_rb_size_order(trans_pcie->rx_buf_size);
+		iwl_trans_get_rb_size_order(trans->conf.rx_buf_size);
 	trans_pcie->rx_buf_bytes =
-		iwl_trans_get_rb_size(trans_pcie->rx_buf_size);
-	trans_pcie->supported_dma_mask = DMA_BIT_MASK(12);
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
-		trans_pcie->supported_dma_mask = DMA_BIT_MASK(11);
-
-	trans_pcie->txqs.bc_table_dword = trans_cfg->bc_table_dword;
-	trans_pcie->scd_set_active = trans_cfg->scd_set_active;
-
-	trans->command_groups = trans_cfg->command_groups;
-	trans->command_groups_size = trans_cfg->command_groups_size;
-
-
-	trans_pcie->fw_reset_handshake = trans_cfg->fw_reset_handshake;
+		iwl_trans_get_rb_size(trans->conf.rx_buf_size);
 }
 
 void iwl_trans_pcie_free_pnvm_dram_regions(struct iwl_dram_regions *dram_regions,
@@ -2026,11 +2004,14 @@ void iwl_trans_pcie_free_pnvm_dram_regions(struct iwl_dram_regions *dram_regions
 
 static void iwl_pcie_free_invalid_tx_cmd(struct iwl_trans *trans)
 {
-	iwl_pcie_free_dma_ptr(trans, &trans->invalid_tx_cmd);
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	iwl_pcie_free_dma_ptr(trans, &trans_pcie->invalid_tx_cmd);
 }
 
 static int iwl_pcie_alloc_invalid_tx_cmd(struct iwl_trans *trans)
 {
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_cmd_header_wide bad_cmd = {
 		.cmd = INVALID_WR_PTR_CMD,
 		.group_id = DEBUG_GROUP,
@@ -2040,11 +2021,11 @@ static int iwl_pcie_alloc_invalid_tx_cmd(struct iwl_trans *trans)
 	};
 	int ret;
 
-	ret = iwl_pcie_alloc_dma_ptr(trans, &trans->invalid_tx_cmd,
+	ret = iwl_pcie_alloc_dma_ptr(trans, &trans_pcie->invalid_tx_cmd,
 				     sizeof(bad_cmd));
 	if (ret)
 		return ret;
-	memcpy(trans->invalid_tx_cmd.addr, &bad_cmd, sizeof(bad_cmd));
+	memcpy(trans_pcie->invalid_tx_cmd.addr, &bad_cmd, sizeof(bad_cmd));
 	return 0;
 }
 
@@ -2055,7 +2036,7 @@ void iwl_trans_pcie_free(struct iwl_trans *trans)
 
 	iwl_pcie_synchronize_irqs(trans);
 
-	if (trans->trans_cfg->gen2)
+	if (trans->mac_cfg->gen2)
 		iwl_txq_gen2_tx_free(trans);
 	else
 		iwl_pcie_tx_free(trans);
@@ -2348,18 +2329,20 @@ out:
 
 void iwl_trans_pcie_reset(struct iwl_trans *trans, enum iwl_reset_mode mode)
 {
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_trans_pcie_removal *removal;
 	char _msg = 0, *msg = &_msg;
 
-	if (WARN_ON(mode < IWL_RESET_MODE_REMOVE_ONLY))
+	if (WARN_ON(mode < IWL_RESET_MODE_REMOVE_ONLY ||
+		    mode == IWL_RESET_MODE_BACKOFF))
 		return;
 
 	if (test_bit(STATUS_TRANS_DEAD, &trans->status))
 		return;
 
-	if (trans->me_present && mode == IWL_RESET_MODE_PROD_RESET) {
+	if (trans_pcie->me_present && mode == IWL_RESET_MODE_PROD_RESET) {
 		mode = IWL_RESET_MODE_FUNC_RESET;
-		if (trans->me_present < 0)
+		if (trans_pcie->me_present < 0)
 			msg = " instead of product reset as ME may be present";
 		else
 			msg = " instead of product reset as ME is present";
@@ -2394,7 +2377,7 @@ void iwl_trans_pcie_reset(struct iwl_trans *trans, enum iwl_reset_mode mode)
 
 	removal->pdev = to_pci_dev(trans->dev);
 	removal->mode = mode;
-	removal->integrated = trans->trans_cfg->integrated;
+	removal->integrated = trans->mac_cfg->integrated;
 	INIT_WORK(&removal->work, iwl_trans_pcie_removal_wk);
 	pci_dev_get(removal->pdev);
 	schedule_work(&removal->work);
@@ -2405,7 +2388,7 @@ EXPORT_SYMBOL(iwl_trans_pcie_reset);
  * This version doesn't disable BHs but rather assumes they're
  * already disabled.
  */
-bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
+bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans, bool silent)
 {
 	int ret;
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -2422,7 +2405,7 @@ bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
 	if (trans_pcie->cmd_hold_nic_awake)
 		goto out;
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
 		write = CSR_GP_CNTRL_REG_FLAG_BZ_MAC_ACCESS_REQ;
 		mask = CSR_GP_CNTRL_REG_FLAG_MAC_STATUS;
 		poll = CSR_GP_CNTRL_REG_FLAG_MAC_STATUS;
@@ -2430,7 +2413,7 @@ bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
 
 	/* this bit wakes up the NIC */
 	__iwl_trans_pcie_set_bit(trans, CSR_GP_CNTRL, write);
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_8000)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_8000)
 		udelay(2);
 
 	/*
@@ -2457,6 +2440,11 @@ bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
 	if (unlikely(ret < 0)) {
 		u32 cntrl = iwl_read32(trans, CSR_GP_CNTRL);
 
+		if (silent) {
+			spin_unlock(&trans_pcie->reg_lock);
+			return false;
+		}
+
 		WARN_ONCE(1,
 			  "Timeout waiting for hardware access (CSR_GP_CNTRL 0x%08x)\n",
 			  cntrl);
@@ -2488,7 +2476,7 @@ bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
 	bool ret;
 
 	local_bh_disable();
-	ret = __iwl_trans_pcie_grab_nic_access(trans);
+	ret = __iwl_trans_pcie_grab_nic_access(trans, false);
 	if (ret) {
 		/* keep BHs disabled until iwl_trans_pcie_release_nic_access */
 		return ret;
@@ -2497,7 +2485,8 @@ bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
 	return false;
 }
 
-void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
+void __releases(nic_access_nobh)
+iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
@@ -2511,7 +2500,7 @@ void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
 
 	if (trans_pcie->cmd_hold_nic_awake)
 		goto out;
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 		__iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL,
 					   CSR_GP_CNTRL_REG_FLAG_BZ_MAC_ACCESS_REQ);
 	else
@@ -2524,6 +2513,7 @@ void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
 	 * scheduled on different CPUs (after we drop reg_lock).
 	 */
 out:
+	__release(nic_access_nobh);
 	spin_unlock_bh(&trans_pcie->reg_lock);
 }
 
@@ -2609,7 +2599,7 @@ int iwl_trans_pcie_rxq_dma_data(struct iwl_trans *trans, int queue,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
-	if (queue >= trans->num_rx_queues || !trans_pcie->rxq)
+	if (queue >= trans->info.num_rxqs || !trans_pcie->rxq)
 		return -EINVAL;
 
 	data->fr_bd_cb = trans_pcie->rxq[queue].bd_dma;
@@ -2690,10 +2680,10 @@ int iwl_trans_pcie_wait_txqs_empty(struct iwl_trans *trans, u32 txq_bm)
 
 	/* waiting for all the tx frames complete might take a while */
 	for (cnt = 0;
-	     cnt < trans->trans_cfg->base_params->num_of_queues;
+	     cnt < trans->mac_cfg->base->num_of_queues;
 	     cnt++) {
 
-		if (cnt == trans_pcie->txqs.cmd.q_id)
+		if (cnt == trans->conf.cmd_queue)
 			continue;
 		if (!test_bit(cnt, trans_pcie->txqs.queue_used))
 			continue;
@@ -2834,7 +2824,7 @@ static void *iwl_dbgfs_tx_queue_seq_start(struct seq_file *seq, loff_t *pos)
 	struct iwl_dbgfs_tx_queue_priv *priv = seq->private;
 	struct iwl_dbgfs_tx_queue_state *state;
 
-	if (*pos >= priv->trans->trans_cfg->base_params->num_of_queues)
+	if (*pos >= priv->trans->mac_cfg->base->num_of_queues)
 		return NULL;
 
 	state = kmalloc(sizeof(*state), GFP_KERNEL);
@@ -2852,7 +2842,7 @@ static void *iwl_dbgfs_tx_queue_seq_next(struct seq_file *seq,
 
 	*pos = ++state->pos;
 
-	if (*pos >= priv->trans->trans_cfg->base_params->num_of_queues)
+	if (*pos >= priv->trans->mac_cfg->base->num_of_queues)
 		return NULL;
 
 	return state;
@@ -2884,7 +2874,7 @@ static int iwl_dbgfs_tx_queue_seq_show(struct seq_file *seq, void *v)
 	else
 		seq_puts(seq, "(unallocated)");
 
-	if (state->pos == trans_pcie->txqs.cmd.q_id)
+	if (state->pos == trans->conf.cmd_queue)
 		seq_puts(seq, " (HCMD)");
 	seq_puts(seq, "\n");
 
@@ -2922,7 +2912,7 @@ static ssize_t iwl_dbgfs_rx_queue_read(struct file *file,
 	int pos = 0, i, ret;
 	size_t bufsz;
 
-	bufsz = sizeof(char) * 121 * trans->num_rx_queues;
+	bufsz = sizeof(char) * 121 * trans->info.num_rxqs;
 
 	if (!trans_pcie->rxq)
 		return -EAGAIN;
@@ -2931,9 +2921,11 @@ static ssize_t iwl_dbgfs_rx_queue_read(struct file *file,
 	if (!buf)
 		return -ENOMEM;
 
-	for (i = 0; i < trans->num_rx_queues && pos < bufsz; i++) {
+	for (i = 0; i < trans->info.num_rxqs && pos < bufsz; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
+		spin_lock_bh(&rxq->lock);
+
 		pos += scnprintf(buf + pos, bufsz - pos, "queue#: %2d\n",
 				 i);
 		pos += scnprintf(buf + pos, bufsz - pos, "\tread: %u\n",
@@ -2954,6 +2946,7 @@ static ssize_t iwl_dbgfs_rx_queue_read(struct file *file,
 			pos += scnprintf(buf + pos, bufsz - pos,
 					 "\tclosed_rb_num: Not Allocated\n");
 		}
+		spin_unlock_bh(&rxq->lock);
 	}
 	ret = simple_read_from_buffer(user_buf, count, ppos, buf, pos);
 	kfree(buf);
@@ -3258,8 +3251,9 @@ static ssize_t iwl_dbgfs_reset_write(struct file *file,
 {
 	struct iwl_trans *trans = file->private_data;
 	static const char * const modes[] = {
-		[IWL_RESET_MODE_SW_RESET] = "n/a",
-		[IWL_RESET_MODE_REPROBE] = "n/a",
+		[IWL_RESET_MODE_SW_RESET] = "sw",
+		[IWL_RESET_MODE_REPROBE] = "reprobe",
+		[IWL_RESET_MODE_TOP_RESET] = "top",
 		[IWL_RESET_MODE_REMOVE_ONLY] = "remove",
 		[IWL_RESET_MODE_RESCAN] = "rescan",
 		[IWL_RESET_MODE_FUNC_RESET] = "function",
@@ -3278,8 +3272,18 @@ static ssize_t iwl_dbgfs_reset_write(struct file *file,
 	if (mode < 0)
 		return mode;
 
-	if (mode < IWL_RESET_MODE_REMOVE_ONLY)
-		return -EINVAL;
+	if (mode < IWL_RESET_MODE_REMOVE_ONLY) {
+		if (!test_bit(STATUS_DEVICE_ENABLED, &trans->status))
+			return -EINVAL;
+		if (mode == IWL_RESET_MODE_TOP_RESET) {
+			if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_SC)
+				return -EINVAL;
+			trans->request_top_reset = 1;
+		}
+		iwl_op_mode_nic_error(trans->op_mode, IWL_ERR_TYPE_DEBUGFS);
+		iwl_trans_schedule_reset(trans, IWL_ERR_TYPE_DEBUGFS);
+		return count;
+	}
 
 	iwl_trans_pcie_reset(trans, mode);
 
@@ -3420,7 +3424,7 @@ static u32 iwl_trans_pcie_fh_regs_dump(struct iwl_trans *trans,
 	(*data)->len = cpu_to_le32(fh_regs_len);
 	val = (void *)(*data)->data;
 
-	if (!trans->trans_cfg->gen2)
+	if (!trans->mac_cfg->gen2)
 		for (i = FH_MEM_LOWER_BOUND; i < FH_MEM_UPPER_BOUND;
 		     i += sizeof(u32))
 			*val++ = cpu_to_le32(iwl_trans_pcie_read32(trans, i));
@@ -3467,7 +3471,7 @@ iwl_trans_pcie_dump_pointers(struct iwl_trans *trans,
 {
 	u32 base, base_high, write_ptr, write_ptr_val, wrap_cnt;
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		base = DBGC_CUR_DBGBUF_BASE_ADDR_LSB;
 		base_high = DBGC_CUR_DBGBUF_BASE_ADDR_MSB;
 		write_ptr = DBGC_CUR_DBGBUF_STATUS;
@@ -3487,7 +3491,7 @@ iwl_trans_pcie_dump_pointers(struct iwl_trans *trans,
 		cpu_to_le32(iwl_read_prph(trans, wrap_cnt));
 	fw_mon_data->fw_mon_base_ptr =
 		cpu_to_le32(iwl_read_prph(trans, base));
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		fw_mon_data->fw_mon_base_high_ptr =
 			cpu_to_le32(iwl_read_prph(trans, base_high));
 		write_ptr_val &= DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK;
@@ -3507,8 +3511,8 @@ iwl_trans_pcie_dump_monitor(struct iwl_trans *trans,
 
 	if (trans->dbg.dest_tlv ||
 	    (fw_mon->size &&
-	     (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_7000 ||
-	      trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210))) {
+	     (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_7000 ||
+	      trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210))) {
 		struct iwl_fw_error_dump_fw_mon *fw_mon_data;
 
 		(*data)->type = cpu_to_le32(IWL_FW_ERROR_DUMP_FW_MONITOR);
@@ -3531,14 +3535,14 @@ iwl_trans_pcie_dump_monitor(struct iwl_trans *trans,
 					IWL_LDBG_M2S_BUF_BA_MSK) <<
 				       trans->dbg.dest_tlv->base_shift;
 				base *= IWL_M2S_UNIT_SIZE;
-				base += trans->cfg->smem_offset;
+				base += trans->mac_cfg->base->smem_offset;
 			} else {
 				base = iwl_read_prph(trans, base) <<
 				       trans->dbg.dest_tlv->base_shift;
 			}
 
-			iwl_trans_read_mem(trans, base, fw_mon_data->data,
-					   monitor_len / sizeof(u32));
+			iwl_trans_pcie_read_mem(trans, base, fw_mon_data->data,
+						monitor_len / sizeof(u32));
 		} else if (trans->dbg.dest_tlv->monitor_mode == MARBH_MODE) {
 			monitor_len =
 				iwl_trans_pci_dump_marbh_monitor(trans,
@@ -3572,7 +3576,7 @@ static int iwl_trans_get_fw_monitor_len(struct iwl_trans *trans, u32 *len)
 			base = (cfg_reg & IWL_LDBG_M2S_BUF_BA_MSK) <<
 				trans->dbg.dest_tlv->base_shift;
 			base *= IWL_M2S_UNIT_SIZE;
-			base += trans->cfg->smem_offset;
+			base += trans->mac_cfg->base->smem_offset;
 
 			monitor_len =
 				(cfg_reg & IWL_LDBG_M2S_BUF_SIZE_MSK) >>
@@ -3588,7 +3592,7 @@ static int iwl_trans_get_fw_monitor_len(struct iwl_trans *trans, u32 *len)
 			      trans->dbg.dest_tlv->end_shift;
 
 			/* Make "end" point to the actual end */
-			if (trans->trans_cfg->device_family >=
+			if (trans->mac_cfg->device_family >=
 			    IWL_DEVICE_FAMILY_8000 ||
 			    trans->dbg.dest_tlv->monitor_mode == MARBH_MODE)
 				end += (1 << trans->dbg.dest_tlv->end_shift);
@@ -3609,13 +3613,13 @@ iwl_trans_pcie_dump_data(struct iwl_trans *trans, u32 dump_mask,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_fw_error_dump_data *data;
-	struct iwl_txq *cmdq = trans_pcie->txqs.txq[trans_pcie->txqs.cmd.q_id];
+	struct iwl_txq *cmdq = trans_pcie->txqs.txq[trans->conf.cmd_queue];
 	struct iwl_fw_error_dump_txcmd *txcmd;
 	struct iwl_trans_dump_data *dump_data;
 	u32 len, num_rbs = 0, monitor_len = 0;
 	int i, ptr;
 	bool dump_rbs = test_bit(STATUS_FW_ERROR, &trans->status) &&
-			!trans->trans_cfg->mq_rx_supported &&
+			!trans->mac_cfg->mq_rx_supported &&
 			dump_mask & BIT(IWL_FW_ERROR_DUMP_RB);
 
 	if (!dump_mask)
@@ -3640,7 +3644,7 @@ iwl_trans_pcie_dump_data(struct iwl_trans *trans, u32 dump_mask,
 
 	/* FH registers */
 	if (dump_mask & BIT(IWL_FW_ERROR_DUMP_FH_REGS)) {
-		if (trans->trans_cfg->gen2)
+		if (trans->mac_cfg->gen2)
 			len += sizeof(*data) +
 			       (iwl_umac_prph(trans, FH_MEM_UPPER_BOUND_GEN2) -
 				iwl_umac_prph(trans, FH_MEM_LOWER_BOUND_GEN2));
@@ -3654,15 +3658,18 @@ iwl_trans_pcie_dump_data(struct iwl_trans *trans, u32 dump_mask,
 		/* Dump RBs is supported only for pre-9000 devices (1 queue) */
 		struct iwl_rxq *rxq = &trans_pcie->rxq[0];
 		/* RBs */
+		spin_lock_bh(&rxq->lock);
 		num_rbs = iwl_get_closed_rb_stts(trans, rxq);
 		num_rbs = (num_rbs - rxq->read) & RX_QUEUE_MASK;
+		spin_unlock_bh(&rxq->lock);
+
 		len += num_rbs * (sizeof(*data) +
 				  sizeof(struct iwl_fw_error_dump_rb) +
 				  (PAGE_SIZE << trans_pcie->rx_page_order));
 	}
 
 	/* Paged memory for gen2 HW */
-	if (trans->trans_cfg->gen2 && dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING))
+	if (trans->mac_cfg->gen2 && dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING))
 		for (i = 0; i < trans->init_dram.paging_cnt; i++)
 			len += sizeof(*data) +
 			       sizeof(struct iwl_fw_error_dump_paging) +
@@ -3687,7 +3694,7 @@ iwl_trans_pcie_dump_data(struct iwl_trans *trans, u32 dump_mask,
 			u8 tfdidx;
 			u32 caplen, cmdlen;
 
-			if (trans->trans_cfg->gen2)
+			if (trans->mac_cfg->gen2)
 				tfdidx = idx;
 			else
 				tfdidx = ptr;
@@ -3727,7 +3734,7 @@ iwl_trans_pcie_dump_data(struct iwl_trans *trans, u32 dump_mask,
 		len += iwl_trans_pcie_dump_rbs(trans, &data, num_rbs);
 
 	/* Paged memory for gen2 HW */
-	if (trans->trans_cfg->gen2 &&
+	if (trans->mac_cfg->gen2 &&
 	    dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING)) {
 		for (i = 0; i < trans->init_dram.paging_cnt; i++) {
 			struct iwl_fw_error_dump_paging *paging;
@@ -3767,7 +3774,7 @@ void iwl_trans_pcie_sync_nmi(struct iwl_trans *trans)
 
 	if (trans_pcie->msix_enabled) {
 		inta_addr = CSR_MSIX_HW_INT_CAUSES_AD;
-		if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+		if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
 			sw_err_bit = MSIX_HW_INT_CAUSES_REG_SW_ERR_BZ;
 		else
 			sw_err_bit = MSIX_HW_INT_CAUSES_REG_SW_ERR;
@@ -3779,12 +3786,14 @@ void iwl_trans_pcie_sync_nmi(struct iwl_trans *trans)
 	iwl_trans_sync_nmi_with_addr(trans, inta_addr, sw_err_bit);
 }
 
-struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
-			       const struct pci_device_id *ent,
-			       const struct iwl_cfg_trans_params *cfg_trans)
+struct iwl_trans *
+iwl_trans_pcie_alloc(struct pci_dev *pdev,
+		     const struct iwl_mac_cfg *mac_cfg,
+		     struct iwl_trans_info *info)
 {
 	struct iwl_trans_pcie *trans_pcie, **priv;
 	struct iwl_trans *trans;
+	unsigned int bc_tbl_n_entries;
 	int ret, addr_size;
 	u32 bar0;
 
@@ -3801,13 +3810,16 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		return ERR_PTR(ret);
 
 	trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie), &pdev->dev,
-				cfg_trans);
+				mac_cfg);
 	if (!trans)
 		return ERR_PTR(-ENOMEM);
 
 	trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
-	if (trans->trans_cfg->gen2) {
+	/* Initialize the wait queue for commands */
+	init_waitqueue_head(&trans_pcie->wait_command_queue);
+
+	if (trans->mac_cfg->gen2) {
 		trans_pcie->txqs.tfd.addr_size = 64;
 		trans_pcie->txqs.tfd.max_tbs = IWL_TFH_NUM_TBS;
 		trans_pcie->txqs.tfd.size = sizeof(struct iwl_tfh_tfd);
@@ -3816,10 +3828,12 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		trans_pcie->txqs.tfd.max_tbs = IWL_NUM_OF_TBS;
 		trans_pcie->txqs.tfd.size = sizeof(struct iwl_tfd);
 	}
-	trans->max_skb_frags = IWL_TRANS_PCIE_MAX_FRAGS(trans_pcie);
 
-	/* Set a short watchdog for the command queue */
-	trans_pcie->txqs.cmd.wdg_timeout = IWL_DEF_WD_TIMEOUT;
+	trans_pcie->supported_dma_mask = (u32)DMA_BIT_MASK(12);
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+		trans_pcie->supported_dma_mask = (u32)DMA_BIT_MASK(11);
+
+	info->max_skb_frags = IWL_TRANS_PCIE_MAX_FRAGS(trans_pcie);
 
 	trans_pcie->txqs.tso_hdr_page = alloc_percpu(struct iwl_tso_hdr_page);
 	if (!trans_pcie->txqs.tso_hdr_page) {
@@ -3827,20 +3841,21 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		goto out_free_trans;
 	}
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
-		trans_pcie->txqs.bc_tbl_size =
-			sizeof(struct iwl_gen3_bc_tbl_entry) * TFD_QUEUE_BC_SIZE_GEN3_BZ;
-	else if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
-		trans_pcie->txqs.bc_tbl_size =
-			sizeof(struct iwl_gen3_bc_tbl_entry) * TFD_QUEUE_BC_SIZE_GEN3_AX210;
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+		bc_tbl_n_entries = TFD_QUEUE_BC_SIZE_BZ;
+	else if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+		bc_tbl_n_entries = TFD_QUEUE_BC_SIZE_AX210;
 	else
-		trans_pcie->txqs.bc_tbl_size = sizeof(struct iwlagn_scd_bc_tbl);
+		bc_tbl_n_entries = TFD_QUEUE_BC_SIZE;
+
+	trans_pcie->txqs.bc_tbl_size =
+		sizeof(struct iwl_bc_tbl_entry) * bc_tbl_n_entries;
 	/*
 	 * For gen2 devices, we use a single allocation for each byte-count
 	 * table, but they're pretty small (1k) so use a DMA pool that we
 	 * allocate here.
 	 */
-	if (trans->trans_cfg->gen2) {
+	if (trans->mac_cfg->gen2) {
 		trans_pcie->txqs.bc_pool =
 			dmam_pool_create("iwlwifi:bc", trans->dev,
 					 trans_pcie->txqs.bc_tbl_size,
@@ -3853,7 +3868,7 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 
 	/* Some things must not change even if the config does */
 	WARN_ON(trans_pcie->txqs.tfd.addr_size !=
-		(trans->trans_cfg->gen2 ? 64 : 36));
+		(trans->mac_cfg->gen2 ? 64 : 36));
 
 	/* Initialize NAPI here - it should be before registering to mac80211
 	 * in the opmode but after the HW struct is allocated.
@@ -3887,7 +3902,7 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 
 	trans_pcie->debug_rfkill = -1;
 
-	if (!cfg_trans->base_params->pcie_l1_allowed) {
+	if (!mac_cfg->base->pcie_l1_allowed) {
 		/*
 		 * W/A - seems to solve weird behavior. We need to remove this
 		 * if we don't want to stay in L1 all the time. This wastes a
@@ -3931,8 +3946,8 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	trans_pcie->pci_dev = pdev;
 	iwl_disable_interrupts(trans);
 
-	trans->hw_rev = iwl_read32(trans, CSR_HW_REV);
-	if (trans->hw_rev == 0xffffffff) {
+	info->hw_rev = iwl_read32(trans, CSR_HW_REV);
+	if (info->hw_rev == 0xffffffff) {
 		dev_err(&pdev->dev, "HW_REV=0xFFFFFFFF, PCI issues?\n");
 		ret = -EIO;
 		goto out_no_pci;
@@ -3944,17 +3959,14 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	 * "dash" value). To keep hw_rev backwards compatible - we'll store it
 	 * in the old format.
 	 */
-	if (cfg_trans->device_family >= IWL_DEVICE_FAMILY_8000)
-		trans->hw_rev_step = trans->hw_rev & 0xF;
+	if (mac_cfg->device_family >= IWL_DEVICE_FAMILY_8000)
+		info->hw_rev_step = info->hw_rev & 0xF;
 	else
-		trans->hw_rev_step = (trans->hw_rev & 0xC) >> 2;
+		info->hw_rev_step = (info->hw_rev & 0xC) >> 2;
 
-	IWL_DEBUG_INFO(trans, "HW REV: 0x%0x\n", trans->hw_rev);
+	IWL_DEBUG_INFO(trans, "HW REV: 0x%0x\n", info->hw_rev);
 
-	iwl_pcie_set_interrupt_capa(pdev, trans, cfg_trans);
-	trans->hw_id = (pdev->device << 16) + pdev->subsystem_device;
-	snprintf(trans->hw_id_str, sizeof(trans->hw_id_str),
-		 "PCI ID: 0x%04X:0x%04X", pdev->device, pdev->subsystem_device);
+	iwl_pcie_set_interrupt_capa(pdev, trans, mac_cfg, info);
 
 	init_waitqueue_head(&trans_pcie->sx_waitq);
 
@@ -3963,7 +3975,7 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		goto out_no_pci;
 
 	if (trans_pcie->msix_enabled) {
-		ret = iwl_pcie_init_msix_handler(pdev, trans_pcie);
+		ret = iwl_pcie_init_msix_handler(pdev, trans_pcie, info);
 		if (ret)
 			goto out_no_pci;
 	 } else {
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 71227fd3dac0..df0545f09da9 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -18,13 +18,12 @@
 static struct page *get_workaround_page(struct iwl_trans *trans,
 					struct sk_buff *skb)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_tso_page_info *info;
 	struct page **page_ptr;
 	struct page *ret;
 	dma_addr_t phys;
 
-	page_ptr = (void *)((u8 *)skb->cb + trans_pcie->txqs.page_offs);
+	page_ptr = (void *)((u8 *)skb->cb + trans->conf.cb_data_offs);
 
 	ret = alloc_page(GFP_ATOMIC);
 	if (!ret)
@@ -164,7 +163,7 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans,
 				    struct iwl_device_tx_cmd *dev_cmd)
 {
 #ifdef CONFIG_INET
-	struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload;
+	struct iwl_tx_cmd_v9 *tx_cmd = (void *)dev_cmd->payload;
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room;
 	unsigned int mss = skb_shinfo(skb)->gso_size;
@@ -491,21 +490,21 @@ struct iwl_tfh_tfd *iwl_txq_gen2_build_tfd(struct iwl_trans *trans,
 	bool amsdu;
 
 	/* There must be data left over for TB1 or this code must be changed */
-	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) < IWL_FIRST_TB_SIZE);
+	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_v9) < IWL_FIRST_TB_SIZE);
 	BUILD_BUG_ON(sizeof(struct iwl_cmd_header) +
-		     offsetofend(struct iwl_tx_cmd_gen2, dram_info) >
+		     offsetofend(struct iwl_tx_cmd_v9, dram_info) >
 		     IWL_FIRST_TB_SIZE);
-	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen3) < IWL_FIRST_TB_SIZE);
+	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd) < IWL_FIRST_TB_SIZE);
 	BUILD_BUG_ON(sizeof(struct iwl_cmd_header) +
-		     offsetofend(struct iwl_tx_cmd_gen3, dram_info) >
+		     offsetofend(struct iwl_tx_cmd, dram_info) >
 		     IWL_FIRST_TB_SIZE);
 
 	memset(tfd, 0, sizeof(*tfd));
 
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
-		len = sizeof(struct iwl_tx_cmd_gen2);
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
+		len = sizeof(struct iwl_tx_cmd_v9);
 	else
-		len = sizeof(struct iwl_tx_cmd_gen3);
+		len = sizeof(struct iwl_tx_cmd);
 
 	amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
 			(*ieee80211_get_qos_ctl(hdr) &
@@ -536,17 +535,17 @@ int iwl_txq_space(struct iwl_trans *trans, const struct iwl_txq *q)
 	 * If q->n_window is smaller than max_tfd_queue_size, there is no need
 	 * to reserve any queue entries for this purpose.
 	 */
-	if (q->n_window < trans->trans_cfg->base_params->max_tfd_queue_size)
+	if (q->n_window < trans->mac_cfg->base->max_tfd_queue_size)
 		max = q->n_window;
 	else
-		max = trans->trans_cfg->base_params->max_tfd_queue_size - 1;
+		max = trans->mac_cfg->base->max_tfd_queue_size - 1;
 
 	/*
 	 * max_tfd_queue_size is a power of 2, so the following is equivalent to
 	 * modulo by max_tfd_queue_size and is well defined.
 	 */
 	used = (q->write_ptr - q->read_ptr) &
-		(trans->trans_cfg->base_params->max_tfd_queue_size - 1);
+		(trans->mac_cfg->base->max_tfd_queue_size - 1);
 
 	if (WARN_ON(used > max))
 		return 0;
@@ -561,8 +560,8 @@ static void iwl_pcie_gen2_update_byte_tbl(struct iwl_trans *trans,
 					  struct iwl_txq *txq, u16 byte_cnt,
 					  int num_tbs)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
+	struct iwl_bc_tbl_entry *scd_bc_tbl = txq->bc_tbl.addr;
 	u8 filled_tfd_size, num_fetch_chunks;
 	u16 len = byte_cnt;
 	__le16 bc_ent;
@@ -582,24 +581,16 @@ static void iwl_pcie_gen2_update_byte_tbl(struct iwl_trans *trans,
 	 */
 	num_fetch_chunks = DIV_ROUND_UP(filled_tfd_size, 64) - 1;
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
-		struct iwl_gen3_bc_tbl_entry *scd_bc_tbl_gen3 = txq->bc_tbl.addr;
-
-		/* Starting from AX210, the HW expects bytes */
-		WARN_ON(trans_pcie->txqs.bc_table_dword);
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
 		WARN_ON(len > 0x3FFF);
 		bc_ent = cpu_to_le16(len | (num_fetch_chunks << 14));
-		scd_bc_tbl_gen3[idx].tfd_offset = bc_ent;
 	} else {
-		struct iwlagn_scd_bc_tbl *scd_bc_tbl = txq->bc_tbl.addr;
-
-		/* Before AX210, the HW expects DW */
-		WARN_ON(!trans_pcie->txqs.bc_table_dword);
 		len = DIV_ROUND_UP(len, 4);
 		WARN_ON(len > 0xFFF);
 		bc_ent = cpu_to_le16(len | (num_fetch_chunks << 12));
-		scd_bc_tbl->tfd_offset[idx] = bc_ent;
 	}
+
+	scd_bc_tbl[idx].tfd_offset = bc_ent;
 }
 
 static u8 iwl_txq_gen2_get_num_tbs(struct iwl_tfh_tfd *tfd)
@@ -756,7 +747,8 @@ int iwl_txq_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 			struct iwl_device_tx_cmd **dev_cmd_ptr;
 
 			dev_cmd_ptr = (void *)((u8 *)skb->cb +
-					       trans_pcie->txqs.dev_cmd_offs);
+					       trans->conf.cb_data_offs +
+					       sizeof(void *));
 
 			*dev_cmd_ptr = dev_cmd;
 			__skb_queue_tail(&txq->overflow_q, skb);
@@ -785,16 +777,16 @@ int iwl_txq_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 		return -1;
 	}
 
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
-		struct iwl_tx_cmd_gen3 *tx_cmd_gen3 =
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+		struct iwl_tx_cmd *tx_cmd =
 			(void *)dev_cmd->payload;
 
-		cmd_len = le16_to_cpu(tx_cmd_gen3->len);
+		cmd_len = le16_to_cpu(tx_cmd->len);
 	} else {
-		struct iwl_tx_cmd_gen2 *tx_cmd_gen2 =
+		struct iwl_tx_cmd_v9 *tx_cmd_v9 =
 			(void *)dev_cmd->payload;
 
-		cmd_len = le16_to_cpu(tx_cmd_gen2->len);
+		cmd_len = le16_to_cpu(tx_cmd_v9->len);
 	}
 
 	/* Set up entry for this TFD in Tx byte-count array */
@@ -832,7 +824,7 @@ static void iwl_txq_gen2_unmap(struct iwl_trans *trans, int txq_id)
 		IWL_DEBUG_TX_REPLY(trans, "Q %d Free %d\n",
 				   txq_id, txq->read_ptr);
 
-		if (txq_id != trans_pcie->txqs.cmd.q_id) {
+		if (txq_id != trans->conf.cmd_queue) {
 			int idx = iwl_txq_get_cmd_index(txq, txq->read_ptr);
 			struct iwl_cmd_meta *cmd_meta = &txq->entries[idx].meta;
 			struct sk_buff *skb = txq->entries[idx].skb;
@@ -906,7 +898,7 @@ static void iwl_txq_gen2_free(struct iwl_trans *trans, int txq_id)
 	iwl_txq_gen2_unmap(trans, txq_id);
 
 	/* De-alloc array of command/tx buffers */
-	if (txq_id == trans_pcie->txqs.cmd.q_id)
+	if (txq_id == trans->conf.cmd_queue)
 		for (i = 0; i < txq->n_window; i++) {
 			kfree_sensitive(txq->entries[i].cmd);
 			kfree_sensitive(txq->entries[i].free_buf);
@@ -1007,7 +999,7 @@ static int iwl_pcie_txq_alloc_response(struct iwl_trans *trans,
 
 	txq->id = qid;
 	trans_pcie->txqs.txq[qid] = txq;
-	wr_ptr &= (trans->trans_cfg->base_params->max_tfd_queue_size - 1);
+	wr_ptr &= (trans->mac_cfg->base->max_tfd_queue_size - 1);
 
 	/* Place first TFD at index corresponding to start sequence number */
 	txq->read_ptr = wr_ptr;
@@ -1043,8 +1035,8 @@ int iwl_txq_dyn_alloc(struct iwl_trans *trans, u32 flags, u32 sta_mask,
 	/* but must be power of 2 values for calculating read/write pointers */
 	size = rounddown_pow_of_two(size);
 
-	if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_BZ &&
-	    trans->hw_rev_step == SILICON_A_STEP) {
+	if (trans->mac_cfg->device_family == IWL_DEVICE_FAMILY_BZ &&
+	    trans->info.hw_rev_step == SILICON_A_STEP) {
 		size = 4096;
 		txq = iwl_txq_dyn_alloc_dma(trans, size, timeout);
 	} else {
@@ -1064,7 +1056,7 @@ int iwl_txq_dyn_alloc(struct iwl_trans *trans, u32 flags, u32 sta_mask,
 	if (IS_ERR(txq))
 		return PTR_ERR(txq);
 
-	if (trans_pcie->txqs.queue_alloc_cmd_ver == 0) {
+	if (trans->conf.queue_alloc_cmd_ver == 0) {
 		memset(&cmd.old, 0, sizeof(cmd.old));
 		cmd.old.tfdq_addr = cpu_to_le64(txq->dma_addr);
 		cmd.old.byte_cnt_addr = cpu_to_le64(txq->bc_tbl.dma);
@@ -1081,7 +1073,7 @@ int iwl_txq_dyn_alloc(struct iwl_trans *trans, u32 flags, u32 sta_mask,
 		hcmd.id = SCD_QUEUE_CFG;
 		hcmd.len[0] = sizeof(cmd.old);
 		hcmd.data[0] = &cmd.old;
-	} else if (trans_pcie->txqs.queue_alloc_cmd_ver == 3) {
+	} else if (trans->conf.queue_alloc_cmd_ver == 3) {
 		memset(&cmd.new, 0, sizeof(cmd.new));
 		cmd.new.operation = cpu_to_le32(IWL_SCD_QUEUE_ADD);
 		cmd.new.u.add.tfdq_dram_addr = cpu_to_le64(txq->dma_addr);
@@ -1176,7 +1168,7 @@ int iwl_txq_gen2_init(struct iwl_trans *trans, int txq_id, int queue_size)
 	}
 
 	ret = iwl_txq_init(trans, queue, queue_size,
-			   (txq_id == trans_pcie->txqs.cmd.q_id));
+			   (txq_id == trans->conf.cmd_queue));
 	if (ret) {
 		IWL_ERR(trans, "Tx %d queue alloc failed\n", txq_id);
 		goto error;
@@ -1206,7 +1198,7 @@ int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 			       struct iwl_host_cmd *cmd)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = trans_pcie->txqs.txq[trans_pcie->txqs.cmd.q_id];
+	struct iwl_txq *txq = trans_pcie->txqs.txq[trans->conf.cmd_queue];
 	struct iwl_device_cmd *out_cmd;
 	struct iwl_cmd_meta *out_meta;
 	void *dup_buf = NULL;
@@ -1323,7 +1315,7 @@ int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 		cpu_to_le16(cmd_size - sizeof(struct iwl_cmd_header_wide));
 	out_cmd->hdr_wide.reserved = 0;
 	out_cmd->hdr_wide.sequence =
-		cpu_to_le16(QUEUE_TO_SEQ(trans_pcie->txqs.cmd.q_id) |
+		cpu_to_le16(QUEUE_TO_SEQ(trans->conf.cmd_queue) |
 					 INDEX_TO_SEQ(txq->write_ptr));
 
 	cmd_pos = sizeof(struct iwl_cmd_header_wide);
@@ -1371,7 +1363,7 @@ int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 		     "Sending command %s (%.2x.%.2x), seq: 0x%04X, %d bytes at %d[%d]:%d\n",
 		     iwl_get_cmd_string(trans, cmd->id), group_id,
 		     out_cmd->hdr.cmd, le16_to_cpu(out_cmd->hdr.sequence),
-		     cmd_size, txq->write_ptr, idx, trans_pcie->txqs.cmd.q_id);
+		     cmd_size, txq->write_ptr, idx, trans->conf.cmd_queue);
 
 	/* start the TFD with the minimum copy bytes */
 	tb0_size = min_t(int, copy_size, IWL_FIRST_TB_SIZE);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index bb90bcfc6763..7abd7c7daa89 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -78,7 +78,6 @@ void iwl_pcie_free_dma_ptr(struct iwl_trans *trans, struct iwl_dma_ptr *ptr)
 static void iwl_pcie_txq_inc_wr_ptr(struct iwl_trans *trans,
 				    struct iwl_txq *txq)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	u32 reg = 0;
 	int txq_id = txq->id;
 
@@ -90,8 +89,8 @@ static void iwl_pcie_txq_inc_wr_ptr(struct iwl_trans *trans,
 	 * 2. NIC is woken up for CMD regardless of shadow outside this function
 	 * 3. there is a chance that the NIC is asleep
 	 */
-	if (!trans->trans_cfg->base_params->shadow_reg_enable &&
-	    txq_id != trans_pcie->txqs.cmd.q_id &&
+	if (!trans->mac_cfg->base->shadow_reg_enable &&
+	    txq_id != trans->conf.cmd_queue &&
 	    test_bit(STATUS_TPOWER_PMI, &trans->status)) {
 		/*
 		 * wake up nic if it's powered down ...
@@ -125,7 +124,7 @@ void iwl_pcie_txq_check_wrptrs(struct iwl_trans *trans)
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int i;
 
-	for (i = 0; i < trans->trans_cfg->base_params->num_of_queues; i++) {
+	for (i = 0; i < trans->mac_cfg->base->num_of_queues; i++) {
 		struct iwl_txq *txq = trans_pcie->txqs.txq[i];
 
 		if (!test_bit(i, trans_pcie->txqs.queue_used))
@@ -193,7 +192,7 @@ static void iwl_pcie_clear_cmd_in_flight(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
-	if (!trans->trans_cfg->base_params->apmg_wake_up_wa)
+	if (!trans->mac_cfg->base->apmg_wake_up_wa)
 		return;
 
 	spin_lock(&trans_pcie->reg_lock);
@@ -226,11 +225,10 @@ static void iwl_pcie_free_and_unmap_tso_page(struct iwl_trans *trans,
 void iwl_pcie_free_tso_pages(struct iwl_trans *trans, struct sk_buff *skb,
 			     struct iwl_cmd_meta *cmd_meta)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct page **page_ptr;
 	struct page *next;
 
-	page_ptr = (void *)((u8 *)skb->cb + trans_pcie->txqs.page_offs);
+	page_ptr = (void *)((u8 *)skb->cb + trans->conf.cb_data_offs);
 	next = *page_ptr;
 	*page_ptr = NULL;
 
@@ -280,10 +278,12 @@ iwl_txq_gen1_tfd_tb_get_addr(struct iwl_tfd *tfd, u8 idx)
 static void iwl_txq_set_tfd_invalid_gen1(struct iwl_trans *trans,
 					 struct iwl_tfd *tfd)
 {
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
 	tfd->num_tbs = 0;
 
-	iwl_pcie_gen1_tfd_set_tb(tfd, 0, trans->invalid_tx_cmd.dma,
-				 trans->invalid_tx_cmd.size);
+	iwl_pcie_gen1_tfd_set_tb(tfd, 0, trans_pcie->invalid_tx_cmd.dma,
+				 trans_pcie->invalid_tx_cmd.size);
 }
 
 static void iwl_txq_gen1_tfd_unmap(struct iwl_trans *trans,
@@ -355,7 +355,7 @@ static void iwl_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq,
 	/* We have only q->n_window txq->entries, but we use
 	 * TFD_QUEUE_SIZE_MAX tfds
 	 */
-	if (trans->trans_cfg->gen2)
+	if (trans->mac_cfg->gen2)
 		iwl_txq_gen2_tfd_unmap(trans, &txq->entries[idx].meta,
 				       iwl_txq_get_tfd(trans, txq, read_ptr));
 	else
@@ -394,7 +394,7 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id)
 		IWL_DEBUG_TX_REPLY(trans, "Q %d Free %d\n",
 				   txq_id, txq->read_ptr);
 
-		if (txq_id != trans_pcie->txqs.cmd.q_id) {
+		if (txq_id != trans->conf.cmd_queue) {
 			struct sk_buff *skb = txq->entries[txq->read_ptr].skb;
 			struct iwl_cmd_meta *cmd_meta =
 				&txq->entries[txq->read_ptr].meta;
@@ -408,7 +408,7 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id)
 		txq->read_ptr = iwl_txq_inc_wrap(trans, txq->read_ptr);
 
 		if (txq->read_ptr == txq->write_ptr &&
-		    txq_id == trans_pcie->txqs.cmd.q_id)
+		    txq_id == trans->conf.cmd_queue)
 			iwl_pcie_clear_cmd_in_flight(trans);
 	}
 
@@ -446,7 +446,7 @@ static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 	iwl_pcie_txq_unmap(trans, txq_id);
 
 	/* De-alloc array of command/tx buffers */
-	if (txq_id == trans_pcie->txqs.cmd.q_id)
+	if (txq_id == trans->conf.cmd_queue)
 		for (i = 0; i < txq->n_window; i++) {
 			kfree_sensitive(txq->entries[i].cmd);
 			kfree_sensitive(txq->entries[i].free_buf);
@@ -456,7 +456,7 @@ static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 	if (txq->tfds) {
 		dma_free_coherent(dev,
 				  trans_pcie->txqs.tfd.size *
-				  trans->trans_cfg->base_params->max_tfd_queue_size,
+				  trans->mac_cfg->base->max_tfd_queue_size,
 				  txq->tfds, txq->dma_addr);
 		txq->dma_addr = 0;
 		txq->tfds = NULL;
@@ -475,10 +475,10 @@ static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 	memset(txq, 0, sizeof(*txq));
 }
 
-void iwl_pcie_tx_start(struct iwl_trans *trans, u32 scd_base_addr)
+void iwl_pcie_tx_start(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	int nq = trans->trans_cfg->base_params->num_of_queues;
+	int nq = trans->mac_cfg->base->num_of_queues;
 	int chan;
 	u32 reg_val;
 	int clear_dwords = (SCD_TRANS_TBL_OFFSET_QUEUE(nq) -
@@ -493,13 +493,10 @@ void iwl_pcie_tx_start(struct iwl_trans *trans, u32 scd_base_addr)
 	trans_pcie->scd_base_addr =
 		iwl_read_prph(trans, SCD_SRAM_BASE_ADDR);
 
-	WARN_ON(scd_base_addr != 0 &&
-		scd_base_addr != trans_pcie->scd_base_addr);
-
 	/* reset context data, TX status and translation data */
-	iwl_trans_write_mem(trans, trans_pcie->scd_base_addr +
-				   SCD_CONTEXT_MEM_LOWER_BOUND,
-			    NULL, clear_dwords);
+	iwl_trans_pcie_write_mem(trans, trans_pcie->scd_base_addr +
+					SCD_CONTEXT_MEM_LOWER_BOUND,
+				 NULL, clear_dwords);
 
 	iwl_write_prph(trans, SCD_DRAM_BASE_ADDR,
 		       trans_pcie->txqs.scd_bc_tbls.dma >> 10);
@@ -507,12 +504,12 @@ void iwl_pcie_tx_start(struct iwl_trans *trans, u32 scd_base_addr)
 	/* The chain extension of the SCD doesn't work well. This feature is
 	 * enabled by default by the HW, so we need to disable it manually.
 	 */
-	if (trans->trans_cfg->base_params->scd_chain_ext_wa)
+	if (trans->mac_cfg->base->scd_chain_ext_wa)
 		iwl_write_prph(trans, SCD_CHAINEXT_EN, 0);
 
-	iwl_trans_ac_txq_enable(trans, trans_pcie->txqs.cmd.q_id,
-				trans_pcie->txqs.cmd.fifo,
-				trans_pcie->txqs.cmd.wdg_timeout);
+	iwl_trans_ac_txq_enable(trans, trans->conf.cmd_queue,
+				trans->conf.cmd_fifo,
+				IWL_DEF_WD_TIMEOUT);
 
 	/* Activate all Tx DMA/FIFO channels */
 	iwl_scd_activate_fifos(trans);
@@ -529,7 +526,7 @@ void iwl_pcie_tx_start(struct iwl_trans *trans, u32 scd_base_addr)
 			   reg_val | FH_TX_CHICKEN_BITS_SCD_AUTO_RETRY_EN);
 
 	/* Enable L1-Active */
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_8000)
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_8000)
 		iwl_clear_bits_prph(trans, APMG_PCIDEV_STT_REG,
 				    APMG_PCIDEV_STT_VAL_L1_ACT_DIS);
 }
@@ -543,13 +540,13 @@ void iwl_trans_pcie_tx_reset(struct iwl_trans *trans)
 	 * we should never get here in gen2 trans mode return early to avoid
 	 * having invalid accesses
 	 */
-	if (WARN_ON_ONCE(trans->trans_cfg->gen2))
+	if (WARN_ON_ONCE(trans->mac_cfg->gen2))
 		return;
 
-	for (txq_id = 0; txq_id < trans->trans_cfg->base_params->num_of_queues;
+	for (txq_id = 0; txq_id < trans->mac_cfg->base->num_of_queues;
 	     txq_id++) {
 		struct iwl_txq *txq = trans_pcie->txqs.txq[txq_id];
-		if (trans->trans_cfg->gen2)
+		if (trans->mac_cfg->gen2)
 			iwl_write_direct64(trans,
 					   FH_MEM_CBBC_QUEUE(trans, txq_id),
 					   txq->dma_addr);
@@ -571,7 +568,7 @@ void iwl_trans_pcie_tx_reset(struct iwl_trans *trans)
 	 * while we were in WoWLAN in which case SCD_SRAM_BASE_ADDR will
 	 * contain garbage.
 	 */
-	iwl_pcie_tx_start(trans, 0);
+	iwl_pcie_tx_start(trans);
 }
 
 static void iwl_pcie_tx_stop_fh(struct iwl_trans *trans)
@@ -633,7 +630,7 @@ int iwl_pcie_tx_stop(struct iwl_trans *trans)
 		return 0;
 
 	/* Unmap DMA from host system and free skb's */
-	for (txq_id = 0; txq_id < trans->trans_cfg->base_params->num_of_queues;
+	for (txq_id = 0; txq_id < trans->mac_cfg->base->num_of_queues;
 	     txq_id++)
 		iwl_pcie_txq_unmap(trans, txq_id);
 
@@ -656,7 +653,7 @@ void iwl_pcie_tx_free(struct iwl_trans *trans)
 	/* Tx queues */
 	if (trans_pcie->txq_memory) {
 		for (txq_id = 0;
-		     txq_id < trans->trans_cfg->base_params->num_of_queues;
+		     txq_id < trans->mac_cfg->base->num_of_queues;
 		     txq_id++) {
 			iwl_pcie_txq_free(trans, txq_id);
 			trans_pcie->txqs.txq[txq_id] = NULL;
@@ -678,7 +675,7 @@ void iwl_txq_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq)
 	bool active;
 	u8 fifo;
 
-	if (trans->trans_cfg->gen2) {
+	if (trans->mac_cfg->gen2) {
 		IWL_ERR(trans, "Queue %d is stuck %d %d\n", txq_id,
 			txq->read_ptr, txq->write_ptr);
 		/* TODO: access new SCD registers and dump them */
@@ -695,9 +692,9 @@ void iwl_txq_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq)
 		jiffies_to_msecs(txq->wd_timeout),
 		txq->read_ptr, txq->write_ptr,
 		iwl_read_prph(trans, SCD_QUEUE_RDPTR(txq_id)) &
-			(trans->trans_cfg->base_params->max_tfd_queue_size - 1),
+			(trans->mac_cfg->base->max_tfd_queue_size - 1),
 			iwl_read_prph(trans, SCD_QUEUE_WRPTR(txq_id)) &
-			(trans->trans_cfg->base_params->max_tfd_queue_size - 1),
+			(trans->mac_cfg->base->max_tfd_queue_size - 1),
 			iwl_read_direct32(trans, FH_TX_TRB_REG(fifo)));
 }
 
@@ -723,8 +720,8 @@ int iwl_pcie_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq,
 		       int slots_num, bool cmd_queue)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	size_t num_entries = trans->trans_cfg->gen2 ?
-		slots_num : trans->trans_cfg->base_params->max_tfd_queue_size;
+	size_t num_entries = trans->mac_cfg->gen2 ?
+		slots_num : trans->mac_cfg->base->max_tfd_queue_size;
 	size_t tfd_sz;
 	size_t tb0_buf_sz;
 	int i;
@@ -779,7 +776,7 @@ int iwl_pcie_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq,
 	for (i = 0; i < num_entries; i++) {
 		void *tfd = iwl_txq_get_tfd(trans, txq, i);
 
-		if (trans->trans_cfg->gen2)
+		if (trans->mac_cfg->gen2)
 			iwl_txq_set_tfd_invalid_gen2(trans, tfd);
 		else
 			iwl_txq_set_tfd_invalid_gen1(trans, tfd);
@@ -799,6 +796,8 @@ error:
 	return -ENOMEM;
 }
 
+#define BC_TABLE_SIZE	(sizeof(struct iwl_bc_tbl_entry) * TFD_QUEUE_BC_SIZE)
+
 /*
  * iwl_pcie_tx_alloc - allocate TX context
  * Allocate all Tx DMA structures and initialize them
@@ -808,12 +807,12 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 	int ret;
 	int txq_id, slots_num;
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	u16 bc_tbls_size = trans->trans_cfg->base_params->num_of_queues;
+	u16 bc_tbls_size = trans->mac_cfg->base->num_of_queues;
 
-	if (WARN_ON(trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210))
+	if (WARN_ON(trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_AX210))
 		return -EINVAL;
 
-	bc_tbls_size *= sizeof(struct iwlagn_scd_bc_tbl);
+	bc_tbls_size *= BC_TABLE_SIZE;
 
 	/*It is not allowed to alloc twice, so warn when this happens.
 	 * We cannot rely on the previous allocation, so free and fail */
@@ -837,7 +836,7 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 	}
 
 	trans_pcie->txq_memory =
-		kcalloc(trans->trans_cfg->base_params->num_of_queues,
+		kcalloc(trans->mac_cfg->base->num_of_queues,
 			sizeof(struct iwl_txq), GFP_KERNEL);
 	if (!trans_pcie->txq_memory) {
 		IWL_ERR(trans, "Not enough memory for txq\n");
@@ -846,16 +845,16 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 	}
 
 	/* Alloc and init all Tx queues, including the command queue (#4/#9) */
-	for (txq_id = 0; txq_id < trans->trans_cfg->base_params->num_of_queues;
+	for (txq_id = 0; txq_id < trans->mac_cfg->base->num_of_queues;
 	     txq_id++) {
-		bool cmd_queue = (txq_id == trans_pcie->txqs.cmd.q_id);
+		bool cmd_queue = (txq_id == trans->conf.cmd_queue);
 
 		if (cmd_queue)
 			slots_num = max_t(u32, IWL_CMD_QUEUE_SIZE,
-					  trans->cfg->min_txq_size);
+					  trans->mac_cfg->base->min_txq_size);
 		else
 			slots_num = max_t(u32, IWL_DEFAULT_QUEUE_SIZE,
-					  trans->cfg->min_ba_txq_size);
+					  trans->mac_cfg->base->min_ba_txq_size);
 		trans_pcie->txqs.txq[txq_id] = &trans_pcie->txq_memory[txq_id];
 		ret = iwl_pcie_txq_alloc(trans, trans_pcie->txqs.txq[txq_id],
 					 slots_num, cmd_queue);
@@ -905,7 +904,7 @@ int iwl_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
 		 int slots_num, bool cmd_queue)
 {
 	u32 tfd_queue_max_size =
-		trans->trans_cfg->base_params->max_tfd_queue_size;
+		trans->mac_cfg->base->max_tfd_queue_size;
 	int ret;
 
 	txq->need_update = false;
@@ -963,16 +962,16 @@ int iwl_pcie_tx_init(struct iwl_trans *trans)
 	spin_unlock_bh(&trans_pcie->irq_lock);
 
 	/* Alloc and init all Tx queues, including the command queue (#4/#9) */
-	for (txq_id = 0; txq_id < trans->trans_cfg->base_params->num_of_queues;
+	for (txq_id = 0; txq_id < trans->mac_cfg->base->num_of_queues;
 	     txq_id++) {
-		bool cmd_queue = (txq_id == trans_pcie->txqs.cmd.q_id);
+		bool cmd_queue = (txq_id == trans->conf.cmd_queue);
 
 		if (cmd_queue)
 			slots_num = max_t(u32, IWL_CMD_QUEUE_SIZE,
-					  trans->cfg->min_txq_size);
+					  trans->mac_cfg->base->min_txq_size);
 		else
 			slots_num = max_t(u32, IWL_DEFAULT_QUEUE_SIZE,
-					  trans->cfg->min_ba_txq_size);
+					  trans->mac_cfg->base->min_ba_txq_size);
 		ret = iwl_txq_init(trans, trans_pcie->txqs.txq[txq_id], slots_num,
 				   cmd_queue);
 		if (ret) {
@@ -991,7 +990,7 @@ int iwl_pcie_tx_init(struct iwl_trans *trans)
 	}
 
 	iwl_set_bits_prph(trans, SCD_GP_CTRL, SCD_GP_CTRL_AUTO_ACTIVE_MODE);
-	if (trans->trans_cfg->base_params->num_of_queues > 20)
+	if (trans->mac_cfg->base->num_of_queues > 20)
 		iwl_set_bits_prph(trans, SCD_GP_CTRL,
 				  SCD_GP_CTRL_ENABLE_31_QUEUES);
 
@@ -1012,7 +1011,7 @@ static int iwl_pcie_set_cmd_in_flight(struct iwl_trans *trans,
 	if (test_bit(STATUS_TRANS_DEAD, &trans->status))
 		return -ENODEV;
 
-	if (!trans->trans_cfg->base_params->apmg_wake_up_wa)
+	if (!trans->mac_cfg->base->apmg_wake_up_wa)
 		return 0;
 
 	/*
@@ -1021,7 +1020,7 @@ static int iwl_pcie_set_cmd_in_flight(struct iwl_trans *trans,
 	 * returned. This needs to be done only on NICs that have
 	 * apmg_wake_up_wa set (see above.)
 	 */
-	if (!_iwl_trans_pcie_grab_nic_access(trans))
+	if (!_iwl_trans_pcie_grab_nic_access(trans, false))
 		return -EIO;
 
 	/*
@@ -1090,12 +1089,12 @@ static void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx)
 	idx = iwl_txq_get_cmd_index(txq, idx);
 	r = iwl_txq_get_cmd_index(txq, txq->read_ptr);
 
-	if (idx >= trans->trans_cfg->base_params->max_tfd_queue_size ||
+	if (idx >= trans->mac_cfg->base->max_tfd_queue_size ||
 	    (!iwl_txq_used(txq, idx, txq->read_ptr, txq->write_ptr))) {
 		WARN_ONCE(test_bit(txq_id, trans_pcie->txqs.queue_used),
 			  "%s: Read index for DMA queue txq id (%d), index %d is out of range [0-%d] %d %d.\n",
 			  __func__, txq_id, idx,
-			  trans->trans_cfg->base_params->max_tfd_queue_size,
+			  trans->mac_cfg->base->max_tfd_queue_size,
 			  txq->write_ptr, txq->read_ptr);
 		return;
 	}
@@ -1164,15 +1163,15 @@ bool iwl_trans_pcie_txq_enable(struct iwl_trans *trans, int txq_id, u16 ssn,
 		fifo = cfg->fifo;
 
 		/* Disable the scheduler prior configuring the cmd queue */
-		if (txq_id == trans_pcie->txqs.cmd.q_id &&
-		    trans_pcie->scd_set_active)
+		if (txq_id == trans->conf.cmd_queue &&
+		    trans->conf.scd_set_active)
 			iwl_scd_enable_set_active(trans, 0);
 
 		/* Stop this Tx queue before configuring it */
 		iwl_scd_txq_set_inactive(trans, txq_id);
 
 		/* Set this queue as a chain-building queue unless it is CMD */
-		if (txq_id != trans_pcie->txqs.cmd.q_id)
+		if (txq_id != trans->conf.cmd_queue)
 			iwl_scd_txq_set_chain(trans, txq_id);
 
 		if (cfg->aggregate) {
@@ -1206,7 +1205,7 @@ bool iwl_trans_pcie_txq_enable(struct iwl_trans *trans, int txq_id, u16 ssn,
 		 * this sad hardware issue.
 		 * This bug has been fixed on devices 9000 and up.
 		 */
-		scd_bug = !trans->trans_cfg->mq_rx_supported &&
+		scd_bug = !trans->mac_cfg->mq_rx_supported &&
 			!((ssn - txq->write_ptr) & 0x3f) &&
 			(ssn != txq->write_ptr);
 		if (scd_bug)
@@ -1242,8 +1241,8 @@ bool iwl_trans_pcie_txq_enable(struct iwl_trans *trans, int txq_id, u16 ssn,
 			       SCD_QUEUE_STTS_REG_MSK);
 
 		/* enable the scheduler for this queue (only) */
-		if (txq_id == trans_pcie->txqs.cmd.q_id &&
-		    trans_pcie->scd_set_active)
+		if (txq_id == trans->conf.cmd_queue &&
+		    trans->conf.scd_set_active)
 			iwl_scd_enable_set_active(trans, BIT(txq_id));
 
 		IWL_DEBUG_TX_QUEUES(trans,
@@ -1293,8 +1292,9 @@ void iwl_trans_pcie_txq_disable(struct iwl_trans *trans, int txq_id,
 	if (configure_scd) {
 		iwl_scd_txq_set_inactive(trans, txq_id);
 
-		iwl_trans_write_mem(trans, stts_addr, (const void *)zero_val,
-				    ARRAY_SIZE(zero_val));
+		iwl_trans_pcie_write_mem(trans, stts_addr,
+					 (const void *)zero_val,
+					 ARRAY_SIZE(zero_val));
 	}
 
 	iwl_pcie_txq_unmap(trans, txq_id);
@@ -1310,10 +1310,10 @@ static void iwl_trans_pcie_block_txq_ptrs(struct iwl_trans *trans, bool block)
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int i;
 
-	for (i = 0; i < trans->trans_cfg->base_params->num_of_queues; i++) {
+	for (i = 0; i < trans->mac_cfg->base->num_of_queues; i++) {
 		struct iwl_txq *txq = trans_pcie->txqs.txq[i];
 
-		if (i == trans_pcie->txqs.cmd.q_id)
+		if (i == trans->conf.cmd_queue)
 			continue;
 
 		/* we skip the command queue (obviously) so it's OK to nest */
@@ -1346,7 +1346,7 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 			  struct iwl_host_cmd *cmd)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = trans_pcie->txqs.txq[trans_pcie->txqs.cmd.q_id];
+	struct iwl_txq *txq = trans_pcie->txqs.txq[trans->conf.cmd_queue];
 	struct iwl_device_cmd *out_cmd;
 	struct iwl_cmd_meta *out_meta;
 	void *dup_buf = NULL;
@@ -1361,7 +1361,7 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	u16 cmdlen[IWL_MAX_CMD_TBS_PER_TFD];
 	unsigned long flags;
 
-	if (WARN(!trans->wide_cmd_header &&
+	if (WARN(!trans->conf.wide_cmd_header &&
 		 group_id > IWL_ALWAYS_LONG_GROUP,
 		 "unsupported wide command %#x\n", cmd->id))
 		return -EINVAL;
@@ -1475,7 +1475,7 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 				    sizeof(struct iwl_cmd_header_wide));
 		out_cmd->hdr_wide.reserved = 0;
 		out_cmd->hdr_wide.sequence =
-			cpu_to_le16(QUEUE_TO_SEQ(trans_pcie->txqs.cmd.q_id) |
+			cpu_to_le16(QUEUE_TO_SEQ(trans->conf.cmd_queue) |
 						 INDEX_TO_SEQ(txq->write_ptr));
 
 		cmd_pos = sizeof(struct iwl_cmd_header_wide);
@@ -1483,7 +1483,7 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	} else {
 		out_cmd->hdr.cmd = iwl_cmd_opcode(cmd->id);
 		out_cmd->hdr.sequence =
-			cpu_to_le16(QUEUE_TO_SEQ(trans_pcie->txqs.cmd.q_id) |
+			cpu_to_le16(QUEUE_TO_SEQ(trans->conf.cmd_queue) |
 						 INDEX_TO_SEQ(txq->write_ptr));
 		out_cmd->hdr.group_id = 0;
 
@@ -1534,7 +1534,7 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 		     iwl_get_cmd_string(trans, cmd->id),
 		     group_id, out_cmd->hdr.cmd,
 		     le16_to_cpu(out_cmd->hdr.sequence),
-		     cmd_size, txq->write_ptr, idx, trans_pcie->txqs.cmd.q_id);
+		     cmd_size, txq->write_ptr, idx, trans->conf.cmd_queue);
 
 	/* start the TFD with the minimum copy bytes */
 	tb0_size = min_t(int, copy_size, IWL_FIRST_TB_SIZE);
@@ -1633,14 +1633,14 @@ void iwl_pcie_hcmd_complete(struct iwl_trans *trans,
 	struct iwl_device_cmd *cmd;
 	struct iwl_cmd_meta *meta;
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = trans_pcie->txqs.txq[trans_pcie->txqs.cmd.q_id];
+	struct iwl_txq *txq = trans_pcie->txqs.txq[trans->conf.cmd_queue];
 
 	/* If a Tx command is being handled and it isn't in the actual
 	 * command queue then there a command routing bug has been introduced
 	 * in the queue management code. */
-	if (WARN(txq_id != trans_pcie->txqs.cmd.q_id,
+	if (WARN(txq_id != trans->conf.cmd_queue,
 		 "wrong command queue %d (should be %d), sequence 0x%X readp=%d writep=%d\n",
-		 txq_id, trans_pcie->txqs.cmd.q_id, sequence, txq->read_ptr,
+		 txq_id, trans->conf.cmd_queue, sequence, txq->read_ptr,
 		 txq->write_ptr)) {
 		iwl_print_hex_error(trans, pkt, 32);
 		return;
@@ -1654,7 +1654,7 @@ void iwl_pcie_hcmd_complete(struct iwl_trans *trans,
 	group_id = cmd->hdr.group_id;
 	cmd_id = WIDE_ID(group_id, cmd->hdr.cmd);
 
-	if (trans->trans_cfg->gen2)
+	if (trans->mac_cfg->gen2)
 		iwl_txq_gen2_tfd_unmap(trans, meta,
 				       iwl_txq_get_tfd(trans, txq, index));
 	else
@@ -1683,7 +1683,7 @@ void iwl_pcie_hcmd_complete(struct iwl_trans *trans,
 		clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status);
 		IWL_DEBUG_INFO(trans, "Clearing HCMD_ACTIVE for command %s\n",
 			       iwl_get_cmd_string(trans, cmd_id));
-		wake_up(&trans->wait_command_queue);
+		wake_up(&trans_pcie->wait_command_queue);
 	}
 
 	meta->flags = 0;
@@ -1753,7 +1753,7 @@ static void *iwl_pcie_get_page_hdr(struct iwl_trans *trans,
 	dma_addr_t phys;
 	void *ret;
 
-	page_ptr = (void *)((u8 *)skb->cb + trans_pcie->txqs.page_offs);
+	page_ptr = (void *)((u8 *)skb->cb + trans->conf.cb_data_offs);
 
 	if (WARN_ON(*page_ptr))
 		return NULL;
@@ -1912,7 +1912,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
 				   u16 tb1_len)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
+	struct iwl_tx_cmd_v6 *tx_cmd = (void *)dev_cmd->payload;
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room;
 	unsigned int mss = skb_shinfo(skb)->gso_size;
@@ -2067,14 +2067,14 @@ static void iwl_txq_gen1_update_byte_cnt_tbl(struct iwl_trans *trans,
 					     int num_tbs)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwlagn_scd_bc_tbl *scd_bc_tbl;
+	struct iwl_bc_tbl_entry *scd_bc_tbl;
 	int write_ptr = txq->write_ptr;
 	int txq_id = txq->id;
 	u8 sec_ctl = 0;
 	u16 len = byte_cnt + IWL_TX_CRC_SIZE + IWL_TX_DELIMITER_SIZE;
 	__le16 bc_ent;
 	struct iwl_device_tx_cmd *dev_cmd = txq->entries[txq->write_ptr].cmd;
-	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
+	struct iwl_tx_cmd_v6 *tx_cmd = (void *)dev_cmd->payload;
 	u8 sta_id = tx_cmd->sta_id;
 
 	scd_bc_tbl = trans_pcie->txqs.scd_bc_tbls.addr;
@@ -2092,7 +2092,8 @@ static void iwl_txq_gen1_update_byte_cnt_tbl(struct iwl_trans *trans,
 		len += IEEE80211_WEP_IV_LEN + IEEE80211_WEP_ICV_LEN;
 		break;
 	}
-	if (trans_pcie->txqs.bc_table_dword)
+
+	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		len = DIV_ROUND_UP(len, 4);
 
 	if (WARN_ON(len > 0xFFF || write_ptr >= TFD_QUEUE_SIZE_MAX))
@@ -2100,10 +2101,10 @@ static void iwl_txq_gen1_update_byte_cnt_tbl(struct iwl_trans *trans,
 
 	bc_ent = cpu_to_le16(len | (sta_id << 12));
 
-	scd_bc_tbl[txq_id].tfd_offset[write_ptr] = bc_ent;
+	scd_bc_tbl[txq_id * BC_TABLE_SIZE + write_ptr].tfd_offset = bc_ent;
 
 	if (write_ptr < TFD_QUEUE_SIZE_BC_DUP)
-		scd_bc_tbl[txq_id].tfd_offset[TFD_QUEUE_SIZE_MAX + write_ptr] =
+		scd_bc_tbl[txq_id * BC_TABLE_SIZE + TFD_QUEUE_SIZE_MAX + write_ptr].tfd_offset =
 			bc_ent;
 }
 
@@ -2112,7 +2113,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct ieee80211_hdr *hdr;
-	struct iwl_tx_cmd *tx_cmd = (struct iwl_tx_cmd *)dev_cmd->payload;
+	struct iwl_tx_cmd_v6 *tx_cmd = (struct iwl_tx_cmd_v6 *)dev_cmd->payload;
 	struct iwl_cmd_meta *out_meta;
 	struct iwl_txq *txq;
 	dma_addr_t tb0_phys, tb1_phys, scratch_phys;
@@ -2153,7 +2154,8 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 			struct iwl_device_tx_cmd **dev_cmd_ptr;
 
 			dev_cmd_ptr = (void *)((u8 *)skb->cb +
-					       trans_pcie->txqs.dev_cmd_offs);
+					       trans->conf.cb_data_offs +
+					       sizeof(void *));
 
 			*dev_cmd_ptr = dev_cmd;
 			__skb_queue_tail(&txq->overflow_q, skb);
@@ -2184,7 +2186,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
 	tb0_phys = iwl_txq_get_first_tb_dma(txq, txq->write_ptr);
 	scratch_phys = tb0_phys + sizeof(struct iwl_cmd_header) +
-		       offsetof(struct iwl_tx_cmd, scratch);
+		       offsetof(struct iwl_tx_cmd_v6, scratch);
 
 	tx_cmd->dram_lsb_ptr = cpu_to_le32(scratch_phys);
 	tx_cmd->dram_msb_ptr = iwl_get_dma_hi_addr(scratch_phys);
@@ -2199,7 +2201,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	 * (This calculation modifies the TX command, so do it before the
 	 * setup of the first TB)
 	 */
-	len = sizeof(struct iwl_tx_cmd) + sizeof(struct iwl_cmd_header) +
+	len = sizeof(struct iwl_tx_cmd_v6) + sizeof(struct iwl_cmd_header) +
 	      hdr_len - IWL_FIRST_TB_SIZE;
 	/* do not align A-MSDU to dword as the subframe header aligns it */
 	amsdu = ieee80211_is_data_qos(fc) &&
@@ -2222,9 +2224,9 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 			       IWL_FIRST_TB_SIZE, true);
 
 	/* there must be data left over for TB1 or this code must be changed */
-	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd) < IWL_FIRST_TB_SIZE);
+	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_v6) < IWL_FIRST_TB_SIZE);
 	BUILD_BUG_ON(sizeof(struct iwl_cmd_header) +
-		     offsetofend(struct iwl_tx_cmd, scratch) >
+		     offsetofend(struct iwl_tx_cmd_v6, scratch) >
 		     IWL_FIRST_TB_SIZE);
 
 	/* map the data for TB1 */
@@ -2312,24 +2314,24 @@ static void iwl_txq_gen1_inval_byte_cnt_tbl(struct iwl_trans *trans,
 					    int read_ptr)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwlagn_scd_bc_tbl *scd_bc_tbl = trans_pcie->txqs.scd_bc_tbls.addr;
+	struct iwl_bc_tbl_entry *scd_bc_tbl = trans_pcie->txqs.scd_bc_tbls.addr;
 	int txq_id = txq->id;
 	u8 sta_id = 0;
 	__le16 bc_ent;
 	struct iwl_device_tx_cmd *dev_cmd = txq->entries[read_ptr].cmd;
-	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
+	struct iwl_tx_cmd_v6 *tx_cmd = (void *)dev_cmd->payload;
 
 	WARN_ON(read_ptr >= TFD_QUEUE_SIZE_MAX);
 
-	if (txq_id != trans_pcie->txqs.cmd.q_id)
+	if (txq_id != trans->conf.cmd_queue)
 		sta_id = tx_cmd->sta_id;
 
 	bc_ent = cpu_to_le16(1 | (sta_id << 12));
 
-	scd_bc_tbl[txq_id].tfd_offset[read_ptr] = bc_ent;
+	scd_bc_tbl[txq_id * BC_TABLE_SIZE + read_ptr].tfd_offset = bc_ent;
 
 	if (read_ptr < TFD_QUEUE_SIZE_BC_DUP)
-		scd_bc_tbl[txq_id].tfd_offset[TFD_QUEUE_SIZE_MAX + read_ptr] =
+		scd_bc_tbl[txq_id * BC_TABLE_SIZE + TFD_QUEUE_SIZE_MAX + read_ptr].tfd_offset =
 			bc_ent;
 }
 
@@ -2343,7 +2345,7 @@ void iwl_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 	int txq_read_ptr, txq_write_ptr;
 
 	/* This function is not meant to release cmd queue*/
-	if (WARN_ON(txq_id == trans_pcie->txqs.cmd.q_id))
+	if (WARN_ON(txq_id == trans->conf.cmd_queue))
 		return;
 
 	if (WARN_ON(!txq))
@@ -2385,7 +2387,7 @@ void iwl_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 		IWL_ERR(trans,
 			"%s: Read index for txq id (%d), last_to_free %d is out of range [0-%d] %d %d.\n",
 			__func__, txq_id, last_to_free,
-			trans->trans_cfg->base_params->max_tfd_queue_size,
+			trans->mac_cfg->base->max_tfd_queue_size,
 			txq_write_ptr, txq_read_ptr);
 
 		iwl_op_mode_time_point(trans->op_mode,
@@ -2414,7 +2416,7 @@ void iwl_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 		txq->entries[read_ptr].skb = NULL;
 
-		if (!trans->trans_cfg->gen2)
+		if (!trans->mac_cfg->gen2)
 			iwl_txq_gen1_inval_byte_cnt_tbl(trans, txq,
 							txq_read_ptr);
 
@@ -2456,7 +2458,8 @@ void iwl_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 			struct iwl_device_tx_cmd *dev_cmd_ptr;
 
 			dev_cmd_ptr = *(void **)((u8 *)skb->cb +
-						 trans_pcie->txqs.dev_cmd_offs);
+						 trans->conf.cb_data_offs +
+						 sizeof(void *));
 
 			/*
 			 * Note that we can very well be overflowing again.
@@ -2548,11 +2551,11 @@ next_queue:
 #define HOST_COMPLETE_TIMEOUT	(2 * HZ)
 
 static int iwl_trans_pcie_send_hcmd_sync(struct iwl_trans *trans,
-					 struct iwl_host_cmd *cmd)
+					 struct iwl_host_cmd *cmd,
+					 const char *cmd_str)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	const char *cmd_str = iwl_get_cmd_string(trans, cmd->id);
-	struct iwl_txq *txq = trans_pcie->txqs.txq[trans_pcie->txqs.cmd.q_id];
+	struct iwl_txq *txq = trans_pcie->txqs.txq[trans->conf.cmd_queue];
 	int cmd_idx;
 	int ret;
 
@@ -2565,7 +2568,7 @@ static int iwl_trans_pcie_send_hcmd_sync(struct iwl_trans *trans,
 
 	IWL_DEBUG_INFO(trans, "Setting HCMD_ACTIVE for command %s\n", cmd_str);
 
-	if (trans->trans_cfg->gen2)
+	if (trans->mac_cfg->gen2)
 		cmd_idx = iwl_pcie_gen2_enqueue_hcmd(trans, cmd);
 	else
 		cmd_idx = iwl_pcie_enqueue_hcmd(trans, cmd);
@@ -2578,7 +2581,7 @@ static int iwl_trans_pcie_send_hcmd_sync(struct iwl_trans *trans,
 		return ret;
 	}
 
-	ret = wait_event_timeout(trans->wait_command_queue,
+	ret = wait_event_timeout(trans_pcie->wait_command_queue,
 				 !test_bit(STATUS_SYNC_HCMD_ACTIVE,
 					   &trans->status),
 				 HOST_COMPLETE_TIMEOUT);
@@ -2594,7 +2597,7 @@ static int iwl_trans_pcie_send_hcmd_sync(struct iwl_trans *trans,
 			       cmd_str);
 		ret = -ETIMEDOUT;
 
-		iwl_trans_sync_nmi(trans);
+		iwl_trans_pcie_sync_nmi(trans);
 		goto cancel;
 	}
 
@@ -2645,6 +2648,8 @@ cancel:
 int iwl_trans_pcie_send_hcmd(struct iwl_trans *trans,
 			     struct iwl_host_cmd *cmd)
 {
+	const char *cmd_str = iwl_get_cmd_string(trans, cmd->id);
+
 	/* Make sure the NIC is still alive in the bus */
 	if (test_bit(STATUS_TRANS_DEAD, &trans->status))
 		return -ENODEV;
@@ -2656,20 +2661,16 @@ int iwl_trans_pcie_send_hcmd(struct iwl_trans *trans,
 		return -ERFKILL;
 	}
 
-	if (unlikely(trans->system_pm_mode == IWL_PLAT_PM_MODE_D3 &&
-		     !(cmd->flags & CMD_SEND_IN_D3))) {
-		IWL_DEBUG_WOWLAN(trans, "Dropping CMD 0x%x: D3\n", cmd->id);
-		return -EHOSTDOWN;
-	}
-
 	if (cmd->flags & CMD_ASYNC) {
 		int ret;
 
+		IWL_DEBUG_INFO(trans, "Sending async command %s\n", cmd_str);
+
 		/* An asynchronous command can not expect an SKB to be set. */
 		if (WARN_ON(cmd->flags & CMD_WANT_SKB))
 			return -EINVAL;
 
-		if (trans->trans_cfg->gen2)
+		if (trans->mac_cfg->gen2)
 			ret = iwl_pcie_gen2_enqueue_hcmd(trans, cmd);
 		else
 			ret = iwl_pcie_enqueue_hcmd(trans, cmd);
@@ -2683,6 +2684,5 @@ int iwl_trans_pcie_send_hcmd(struct iwl_trans *trans,
 		return 0;
 	}
 
-	return iwl_trans_pcie_send_hcmd_sync(trans, cmd);
+	return iwl_trans_pcie_send_hcmd_sync(trans, cmd, cmd_str);
 }
-IWL_EXPORT_SYMBOL(iwl_trans_pcie_send_hcmd);
diff --git a/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c b/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
index 7ef5e89c6af2..784433bb246a 100644
--- a/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
+++ b/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
@@ -13,10 +13,50 @@ MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
 
 static void iwl_pci_print_dev_info(const char *pfx, const struct iwl_dev_info *di)
 {
-	printk(KERN_DEBUG "%sdev=%.4x,subdev=%.4x,mac_type=%.4x,mac_step=%.4x,rf_type=%.4x,cdb=%d,jacket=%d,rf_id=%.2x,bw_limit=%d,cores=%.2x\n",
-	       pfx, di->device, di->subdevice, di->mac_type, di->mac_step,
-	       di->rf_type, di->cdb, di->jacket, di->rf_id, di->bw_limit,
-	       di->cores);
+	u16 subdevice_mask = GENMASK(di->subdevice_m_h, di->subdevice_m_l);
+	char buf[100] = {};
+	int pos = 0;
+
+	if (di->match_rf_type)
+		pos += scnprintf(buf + pos, sizeof(buf) - pos,
+				 " rf_type=%03x", di->rf_type);
+	else
+		pos += scnprintf(buf + pos, sizeof(buf) - pos,
+				 " rf_type=*");
+
+	if (di->match_bw_limit)
+		pos += scnprintf(buf + pos, sizeof(buf) - pos,
+				 " bw_limit=%d", di->bw_limit);
+	else
+		pos += scnprintf(buf + pos, sizeof(buf) - pos,
+				 " bw_limit=*");
+
+	if (di->match_rf_step)
+		pos += scnprintf(buf + pos, sizeof(buf) - pos,
+				 " rf_step=%c",
+				 di->rf_step == SILICON_Z_STEP ? 'Z' :
+				 	'A' + di->rf_step);
+	else
+		pos += scnprintf(buf + pos, sizeof(buf) - pos,
+				 " rf_step=*");
+
+	if (di->match_rf_id)
+		pos += scnprintf(buf + pos, sizeof(buf) - pos,
+				 " rf_id=0x%x", di->rf_id);
+	else
+		pos += scnprintf(buf + pos, sizeof(buf) - pos,
+				 " rf_id=*");
+
+	if (di->match_cdb)
+		pos += scnprintf(buf + pos, sizeof(buf) - pos,
+				 " cdb=%d", di->cdb);
+	else
+		pos += scnprintf(buf + pos, sizeof(buf) - pos,
+				 " cdb=*");
+
+
+	printk(KERN_DEBUG "%sdev=%04x subdev=%04x/%04x%s\n",
+	       pfx, di->device, di->subdevice, subdevice_mask, buf);
 }
 
 static void devinfo_table_order(struct kunit *test)
@@ -28,11 +68,9 @@ static void devinfo_table_order(struct kunit *test)
 		const struct iwl_dev_info *ret;
 
 		ret = iwl_pci_find_dev_info(di->device, di->subdevice,
-					    di->mac_type, di->mac_step,
 					    di->rf_type, di->cdb,
-					    di->jacket, di->rf_id,
-					    di->bw_limit != IWL_CFG_BW_NO_LIM,
-					    di->cores, di->rf_step);
+					    di->rf_id, di->bw_limit,
+					    di->rf_step);
 		if (!ret) {
 			iwl_pci_print_dev_info("No entry found for: ", di);
 			KUNIT_FAIL(test,
@@ -47,6 +85,92 @@ static void devinfo_table_order(struct kunit *test)
 	}
 }
 
+static void devinfo_names(struct kunit *test)
+{
+	int idx;
+
+	for (idx = 0; idx < iwl_dev_info_table_size; idx++) {
+		const struct iwl_dev_info *di = &iwl_dev_info_table[idx];
+
+		KUNIT_ASSERT_TRUE(test, di->name);
+	}
+}
+
+static void devinfo_no_cfg_dups(struct kunit *test)
+{
+	for (int i = 0; i < iwl_dev_info_table_size; i++) {
+		const struct iwl_rf_cfg *cfg_i = iwl_dev_info_table[i].cfg;
+
+		for (int j = 0; j < i; j++) {
+			const struct iwl_rf_cfg *cfg_j = iwl_dev_info_table[j].cfg;
+
+			if (cfg_i == cfg_j)
+				continue;
+
+			KUNIT_EXPECT_NE_MSG(test, memcmp(cfg_i, cfg_j,
+							 sizeof(*cfg_i)), 0,
+					    "identical configs: %ps and %ps\n",
+					    cfg_i, cfg_j);
+		}
+	}
+}
+
+static void devinfo_no_name_dups(struct kunit *test)
+{
+	for (int i = 0; i < iwl_dev_info_table_size; i++) {
+		for (int j = 0; j < i; j++) {
+			if (iwl_dev_info_table[i].name == iwl_dev_info_table[j].name)
+				continue;
+
+			KUNIT_EXPECT_NE_MSG(test,
+					    strcmp(iwl_dev_info_table[i].name,
+						   iwl_dev_info_table[j].name),
+					    0,
+					    "name dup: %ps/%ps",
+					    iwl_dev_info_table[i].name,
+					    iwl_dev_info_table[j].name);
+		}
+	}
+}
+
+static void devinfo_check_subdev_match(struct kunit *test)
+{
+	for (int i = 0; i < iwl_dev_info_table_size; i++) {
+		const struct iwl_dev_info *di = &iwl_dev_info_table[i];
+		u16 subdevice_mask = GENMASK(di->subdevice_m_h,
+					     di->subdevice_m_l);
+
+		/* if BW limit bit is matched then must have a limit */
+		if (di->match_bw_limit == 1 && di->bw_limit == 1)
+			KUNIT_EXPECT_NE(test, di->cfg->bw_limit, 0);
+
+		/* if subdevice is ANY we can have RF ID/BW limit */
+		if (di->subdevice == (u16)IWL_CFG_ANY)
+			continue;
+
+		/* same if the subdevice mask doesn't overlap them */
+		if (IWL_SUBDEVICE_RF_ID(subdevice_mask) == 0 &&
+		    IWL_SUBDEVICE_BW_LIM(subdevice_mask) == 0)
+			continue;
+
+		/* but otherwise they shouldn't be used */
+		KUNIT_EXPECT_EQ(test, (int)di->match_rf_id, 0);
+		KUNIT_EXPECT_EQ(test, (int)di->match_bw_limit, 0);
+	}
+}
+
+static void devinfo_check_killer_subdev(struct kunit *test)
+{
+	for (int i = 0; i < iwl_dev_info_table_size; i++) {
+		const struct iwl_dev_info *di = &iwl_dev_info_table[i];
+
+		if (!strstr(di->name, "Killer"))
+			continue;
+
+		KUNIT_EXPECT_NE(test, di->subdevice, (u16)IWL_CFG_ANY);
+	}
+}
+
 static void devinfo_pci_ids(struct kunit *test)
 {
 	struct pci_dev *dev;
@@ -69,9 +193,36 @@ static void devinfo_pci_ids(struct kunit *test)
 	}
 }
 
+static void devinfo_no_mac_cfg_dups(struct kunit *test)
+{
+	for (int i = 0; iwl_hw_card_ids[i].vendor; i++) {
+		const struct iwl_mac_cfg *cfg_i =
+			(void *)iwl_hw_card_ids[i].driver_data;
+
+		for (int j = 0; j < i; j++) {
+			const struct iwl_mac_cfg *cfg_j =
+				(void *)iwl_hw_card_ids[j].driver_data;
+
+			if (cfg_i == cfg_j)
+				continue;
+
+			KUNIT_EXPECT_NE_MSG(test, memcmp(cfg_j, cfg_i,
+							 sizeof(*cfg_i)), 0,
+					    "identical configs: %ps and %ps\n",
+					    cfg_i, cfg_j);
+		}
+	}
+}
+
 static struct kunit_case devinfo_test_cases[] = {
 	KUNIT_CASE(devinfo_table_order),
+	KUNIT_CASE(devinfo_names),
+	KUNIT_CASE(devinfo_no_cfg_dups),
+	KUNIT_CASE(devinfo_no_name_dups),
+	KUNIT_CASE(devinfo_check_subdev_match),
+	KUNIT_CASE(devinfo_check_killer_subdev),
 	KUNIT_CASE(devinfo_pci_ids),
+	KUNIT_CASE(devinfo_no_mac_cfg_dups),
 	{}
 };
 
diff --git a/drivers/net/wireless/intersil/p54/fwio.c b/drivers/net/wireless/intersil/p54/fwio.c
index 772084a9bd8d..3baf8ab01e22 100644
--- a/drivers/net/wireless/intersil/p54/fwio.c
+++ b/drivers/net/wireless/intersil/p54/fwio.c
@@ -231,6 +231,7 @@ int p54_download_eeprom(struct p54_common *priv, void *buf,
 
 	mutex_lock(&priv->eeprom_mutex);
 	priv->eeprom = buf;
+	priv->eeprom_slice_size = len;
 	eeprom_hdr = skb_put(skb, eeprom_hdr_size + len);
 
 	if (priv->fw_var < 0x509) {
@@ -253,6 +254,7 @@ int p54_download_eeprom(struct p54_common *priv, void *buf,
 		ret = -EBUSY;
 	}
 	priv->eeprom = NULL;
+	priv->eeprom_slice_size = 0;
 	mutex_unlock(&priv->eeprom_mutex);
 	return ret;
 }
diff --git a/drivers/net/wireless/intersil/p54/p54.h b/drivers/net/wireless/intersil/p54/p54.h
index 522656de4159..aeb5e40cc5ef 100644
--- a/drivers/net/wireless/intersil/p54/p54.h
+++ b/drivers/net/wireless/intersil/p54/p54.h
@@ -258,6 +258,7 @@ struct p54_common {
 
 	/* eeprom handling */
 	void *eeprom;
+	size_t eeprom_slice_size;
 	struct completion eeprom_comp;
 	struct mutex eeprom_mutex;
 };
diff --git a/drivers/net/wireless/intersil/p54/txrx.c b/drivers/net/wireless/intersil/p54/txrx.c
index 8414aa208655..2deb1bb54f24 100644
--- a/drivers/net/wireless/intersil/p54/txrx.c
+++ b/drivers/net/wireless/intersil/p54/txrx.c
@@ -496,14 +496,19 @@ static void p54_rx_eeprom_readback(struct p54_common *priv,
 		return ;
 
 	if (priv->fw_var >= 0x509) {
-		memcpy(priv->eeprom, eeprom->v2.data,
-		       le16_to_cpu(eeprom->v2.len));
+		if (le16_to_cpu(eeprom->v2.len) != priv->eeprom_slice_size)
+			return;
+
+		memcpy(priv->eeprom, eeprom->v2.data, priv->eeprom_slice_size);
 	} else {
-		memcpy(priv->eeprom, eeprom->v1.data,
-		       le16_to_cpu(eeprom->v1.len));
+		if (le16_to_cpu(eeprom->v1.len) != priv->eeprom_slice_size)
+			return;
+
+		memcpy(priv->eeprom, eeprom->v1.data, priv->eeprom_slice_size);
 	}
 
 	priv->eeprom = NULL;
+	priv->eeprom_slice_size = 0;
 	tmp = p54_find_and_unlink_skb(priv, hdr->req_id);
 	dev_kfree_skb_any(tmp);
 	complete(&priv->eeprom_comp);
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index a099fdaafa45..60c12328c2f3 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -1126,7 +1126,7 @@ mwifiex_change_vif_to_p2p(struct net_device *dev,
 			     HostCmd_ACT_GEN_SET, 0, NULL, true))
 		return -1;
 
-	if (mwifiex_sta_init_cmd(priv, false, false))
+	if (mwifiex_sta_init_cmd(priv, false))
 		return -1;
 
 	return 0;
@@ -1167,7 +1167,7 @@ mwifiex_change_vif_to_sta_adhoc(struct net_device *dev,
 	if (mwifiex_send_cmd(priv, HostCmd_CMD_SET_BSS_MODE,
 			     HostCmd_ACT_GEN_SET, 0, NULL, true))
 		return -1;
-	if (mwifiex_sta_init_cmd(priv, false, false))
+	if (mwifiex_sta_init_cmd(priv, false))
 		return -1;
 
 	return 0;
@@ -1204,7 +1204,7 @@ mwifiex_change_vif_to_ap(struct net_device *dev,
 	if (mwifiex_send_cmd(priv, HostCmd_CMD_SET_BSS_MODE,
 			     HostCmd_ACT_GEN_SET, 0, NULL, true))
 		return -1;
-	if (mwifiex_sta_init_cmd(priv, false, false))
+	if (mwifiex_sta_init_cmd(priv, false))
 		return -1;
 
 	return 0;
@@ -2906,16 +2906,12 @@ mwifiex_setup_ht_caps(struct ieee80211_sta_ht_cap *ht_info,
 		      struct mwifiex_private *priv)
 {
 	int rx_mcs_supp;
-	struct ieee80211_mcs_info mcs_set;
-	u8 *mcs = (u8 *)&mcs_set;
 	struct mwifiex_adapter *adapter = priv->adapter;
 
 	ht_info->ht_supported = true;
 	ht_info->ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K;
 	ht_info->ampdu_density = IEEE80211_HT_MPDU_DENSITY_NONE;
 
-	memset(&ht_info->mcs, 0, sizeof(ht_info->mcs));
-
 	/* Fill HT capability information */
 	if (ISSUPP_CHANWIDTH40(adapter->hw_dot_11n_dev_cap))
 		ht_info->cap |= IEEE80211_HT_CAP_SUP_WIDTH_20_40;
@@ -2961,17 +2957,15 @@ mwifiex_setup_ht_caps(struct ieee80211_sta_ht_cap *ht_info,
 	ht_info->cap |= IEEE80211_HT_CAP_SM_PS;
 
 	rx_mcs_supp = GET_RXMCSSUPP(adapter->user_dev_mcs_support);
+
+	memset(&ht_info->mcs, 0, sizeof(ht_info->mcs));
 	/* Set MCS for 1x1/2x2 */
-	memset(mcs, 0xff, rx_mcs_supp);
-	/* Clear all the other values */
-	memset(&mcs[rx_mcs_supp], 0,
-	       sizeof(struct ieee80211_mcs_info) - rx_mcs_supp);
+	memset(ht_info->mcs.rx_mask, 0xff, rx_mcs_supp);
+
 	if (priv->bss_mode == NL80211_IFTYPE_STATION ||
 	    ISSUPP_CHANWIDTH40(adapter->hw_dot_11n_dev_cap))
 		/* Set MCS32 for infra mode or ad-hoc mode with 40MHz support */
-		SETHT_MCS32(mcs_set.rx_mask);
-
-	memcpy((u8 *) &ht_info->mcs, mcs, sizeof(struct ieee80211_mcs_info));
+		SETHT_MCS32(ht_info->mcs.rx_mask);
 
 	ht_info->mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED;
 }
@@ -3013,7 +3007,6 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 			return ERR_PTR(-EFAULT);
 		}
 
-		priv->wdev.wiphy = wiphy;
 		priv->wdev.iftype = NL80211_IFTYPE_STATION;
 
 		if (type == NL80211_IFTYPE_UNSPECIFIED)
@@ -3022,8 +3015,6 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 			priv->bss_mode = type;
 
 		priv->bss_type = MWIFIEX_BSS_TYPE_STA;
-		priv->frame_type = MWIFIEX_DATA_FRAME_TYPE_ETH_II;
-		priv->bss_priority = 0;
 		priv->bss_role = MWIFIEX_BSS_ROLE_STA;
 
 		break;
@@ -3043,14 +3034,10 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 			return ERR_PTR(-EFAULT);
 		}
 
-		priv->wdev.wiphy = wiphy;
 		priv->wdev.iftype = NL80211_IFTYPE_AP;
 
 		priv->bss_type = MWIFIEX_BSS_TYPE_UAP;
-		priv->frame_type = MWIFIEX_DATA_FRAME_TYPE_ETH_II;
-		priv->bss_priority = 0;
 		priv->bss_role = MWIFIEX_BSS_ROLE_UAP;
-		priv->bss_started = 0;
 		priv->bss_mode = type;
 
 		break;
@@ -3070,7 +3057,6 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 			return ERR_PTR(-EFAULT);
 		}
 
-		priv->wdev.wiphy = wiphy;
 		/* At start-up, wpa_supplicant tries to change the interface
 		 * to NL80211_IFTYPE_STATION if it is not managed mode.
 		 */
@@ -3083,10 +3069,7 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 		 */
 		priv->bss_type = MWIFIEX_BSS_TYPE_P2P;
 
-		priv->frame_type = MWIFIEX_DATA_FRAME_TYPE_ETH_II;
-		priv->bss_priority = 0;
 		priv->bss_role = MWIFIEX_BSS_ROLE_STA;
-		priv->bss_started = 0;
 
 		if (mwifiex_cfg80211_init_p2p_client(priv)) {
 			memset(&priv->wdev, 0, sizeof(priv->wdev));
@@ -3100,6 +3083,11 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 		return ERR_PTR(-EINVAL);
 	}
 
+	priv->wdev.wiphy = wiphy;
+	priv->bss_priority = 0;
+	priv->bss_started = 0;
+	priv->frame_type = MWIFIEX_DATA_FRAME_TYPE_ETH_II;
+
 	dev = alloc_netdev_mqs(sizeof(struct mwifiex_private *), name,
 			       name_assign_type, ether_setup,
 			       IEEE80211_NUM_ACS, 1);
@@ -3122,7 +3110,7 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 		if (ret)
 			goto err_set_bss_mode;
 
-		ret = mwifiex_sta_init_cmd(priv, false, false);
+		ret = mwifiex_sta_init_cmd(priv, false);
 		if (ret)
 			goto err_sta_init;
 	}
@@ -4703,7 +4691,7 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
 	void *wdev_priv;
 	struct wiphy *wiphy;
 	struct mwifiex_private *priv = adapter->priv[MWIFIEX_BSS_TYPE_STA];
-	u8 *country_code;
+	const u8 *country_code;
 	u32 thr, retry;
 	struct cfg80211_ops *ops;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/cfp.c b/drivers/net/wireless/marvell/mwifiex/cfp.c
index d7fd79214bcf..686bf12b6c26 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfp.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfp.c
@@ -153,7 +153,7 @@ struct region_code_mapping {
 	u8 region[IEEE80211_COUNTRY_STRING_LEN] __nonstring;
 };
 
-static struct region_code_mapping region_code_mapping_t[] = {
+static const struct region_code_mapping region_code_mapping_t[] = {
 	{ 0x10, "US " }, /* US FCC */
 	{ 0x20, "CA " }, /* IC Canada */
 	{ 0x30, "FR " }, /* France */
@@ -165,7 +165,7 @@ static struct region_code_mapping region_code_mapping_t[] = {
 };
 
 /* This function converts integer code to region string */
-u8 *mwifiex_11d_code_2_region(u8 code)
+const u8 *mwifiex_11d_code_2_region(u8 code)
 {
 	u8 i;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
index 5573e2ded72f..3bf27efe4537 100644
--- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
@@ -159,11 +159,9 @@ static int mwifiex_cmd_host_cmd(struct mwifiex_private *priv,
  * sending. Afterwards, it logs the command ID and action for debugging
  * and sets up the command timeout timer.
  */
-static int mwifiex_dnld_cmd_to_fw(struct mwifiex_private *priv,
+static int mwifiex_dnld_cmd_to_fw(struct mwifiex_adapter *adapter,
 				  struct cmd_ctrl_node *cmd_node)
 {
-
-	struct mwifiex_adapter *adapter = priv->adapter;
 	int ret;
 	struct host_cmd_ds_command *host_cmd;
 	uint16_t cmd_code;
@@ -367,8 +365,7 @@ static int mwifiex_dnld_sleep_confirm_cmd(struct mwifiex_adapter *adapter)
 	    (test_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags) &&
 	     !adapter->sleep_period.period)) {
 		adapter->pm_wakeup_card_req = true;
-		mwifiex_hs_activated_event(mwifiex_get_priv
-				(adapter, MWIFIEX_BSS_ROLE_ANY), true);
+		mwifiex_hs_activated_event(adapter, true);
 	}
 
 	return ret;
@@ -473,8 +470,7 @@ void mwifiex_free_cmd_buffer(struct mwifiex_adapter *adapter)
 int mwifiex_process_event(struct mwifiex_adapter *adapter)
 {
 	int ret, i;
-	struct mwifiex_private *priv =
-		mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_ANY);
+	struct mwifiex_private *priv;
 	struct sk_buff *skb = adapter->event_skb;
 	u32 eventcause;
 	struct mwifiex_rxinfo *rx_info;
@@ -744,7 +740,6 @@ mwifiex_insert_cmd_to_pending_q(struct mwifiex_adapter *adapter,
  */
 int mwifiex_exec_next_cmd(struct mwifiex_adapter *adapter)
 {
-	struct mwifiex_private *priv;
 	struct cmd_ctrl_node *cmd_node;
 	int ret = 0;
 	struct host_cmd_ds_command *host_cmd;
@@ -768,7 +763,6 @@ int mwifiex_exec_next_cmd(struct mwifiex_adapter *adapter)
 				    struct cmd_ctrl_node, list);
 
 	host_cmd = (struct host_cmd_ds_command *) (cmd_node->cmd_skb->data);
-	priv = cmd_node->priv;
 
 	if (adapter->ps_state != PS_STATE_AWAKE) {
 		mwifiex_dbg(adapter, ERROR,
@@ -783,18 +777,17 @@ int mwifiex_exec_next_cmd(struct mwifiex_adapter *adapter)
 	spin_unlock_bh(&adapter->cmd_pending_q_lock);
 
 	spin_unlock_bh(&adapter->mwifiex_cmd_lock);
-	ret = mwifiex_dnld_cmd_to_fw(priv, cmd_node);
-	priv = mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_ANY);
+	ret = mwifiex_dnld_cmd_to_fw(adapter, cmd_node);
+
 	/* Any command sent to the firmware when host is in sleep
 	 * mode should de-configure host sleep. We should skip the
 	 * host sleep configuration command itself though
 	 */
-	if (priv && (host_cmd->command !=
-	     cpu_to_le16(HostCmd_CMD_802_11_HS_CFG_ENH))) {
+	if (host_cmd->command != cpu_to_le16(HostCmd_CMD_802_11_HS_CFG_ENH)) {
 		if (adapter->hs_activated) {
 			clear_bit(MWIFIEX_IS_HS_CONFIGURED,
 				  &adapter->work_flags);
-			mwifiex_hs_activated_event(priv, false);
+			mwifiex_hs_activated_event(adapter, false);
 		}
 	}
 
@@ -810,8 +803,7 @@ int mwifiex_exec_next_cmd(struct mwifiex_adapter *adapter)
 int mwifiex_process_cmdresp(struct mwifiex_adapter *adapter)
 {
 	struct host_cmd_ds_command *resp;
-	struct mwifiex_private *priv =
-		mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_ANY);
+	struct mwifiex_private *priv;
 	int ret = 0;
 	uint16_t orig_cmdresp_no;
 	uint16_t cmdresp_no;
@@ -900,18 +892,6 @@ int mwifiex_process_cmdresp(struct mwifiex_adapter *adapter)
 		ret = mwifiex_process_sta_cmdresp(priv, cmdresp_no, resp);
 	}
 
-	/* Check init command response */
-	if (adapter->hw_status == MWIFIEX_HW_STATUS_INITIALIZING) {
-		if (ret) {
-			mwifiex_dbg(adapter, ERROR,
-				    "%s: cmd %#x failed during\t"
-				    "initialization\n", __func__, cmdresp_no);
-			mwifiex_init_fw_complete(adapter);
-			return -1;
-		} else if (adapter->last_init_cmd == cmdresp_no)
-			adapter->hw_status = MWIFIEX_HW_STATUS_INIT_DONE;
-	}
-
 	if (adapter->curr_cmd) {
 		if (adapter->curr_cmd->wait_q_enabled)
 			adapter->cmd_wait_q.status = ret;
@@ -1030,10 +1010,6 @@ mwifiex_cmd_timeout_func(struct timer_list *t)
 			mwifiex_cancel_pending_ioctl(adapter);
 		}
 	}
-	if (adapter->hw_status == MWIFIEX_HW_STATUS_INITIALIZING) {
-		mwifiex_init_fw_complete(adapter);
-		return;
-	}
 
 	if (adapter->if_ops.device_dump)
 		adapter->if_ops.device_dump(adapter);
@@ -1160,27 +1136,27 @@ mwifiex_check_ps_cond(struct mwifiex_adapter *adapter)
  * This event is generated by the driver, with a blank event body.
  */
 void
-mwifiex_hs_activated_event(struct mwifiex_private *priv, u8 activated)
+mwifiex_hs_activated_event(struct mwifiex_adapter *adapter, u8 activated)
 {
 	if (activated) {
 		if (test_bit(MWIFIEX_IS_HS_CONFIGURED,
-			     &priv->adapter->work_flags)) {
-			priv->adapter->hs_activated = true;
-			mwifiex_update_rxreor_flags(priv->adapter,
+			     &adapter->work_flags)) {
+			adapter->hs_activated = true;
+			mwifiex_update_rxreor_flags(adapter,
 						    RXREOR_FORCE_NO_DROP);
-			mwifiex_dbg(priv->adapter, EVENT,
+			mwifiex_dbg(adapter, EVENT,
 				    "event: hs_activated\n");
-			priv->adapter->hs_activate_wait_q_woken = true;
+			adapter->hs_activate_wait_q_woken = true;
 			wake_up_interruptible(
-				&priv->adapter->hs_activate_wait_q);
+				&adapter->hs_activate_wait_q);
 		} else {
-			mwifiex_dbg(priv->adapter, EVENT,
+			mwifiex_dbg(adapter, EVENT,
 				    "event: HS not configured\n");
 		}
 	} else {
-		mwifiex_dbg(priv->adapter, EVENT,
+		mwifiex_dbg(adapter, EVENT,
 			    "event: hs_deactivated\n");
-		priv->adapter->hs_activated = false;
+		adapter->hs_activated = false;
 	}
 }
 
@@ -1204,7 +1180,7 @@ int mwifiex_ret_802_11_hs_cfg(struct mwifiex_private *priv,
 
 	if (phs_cfg->action == cpu_to_le16(HS_ACTIVATE) &&
 	    adapter->iface_type != MWIFIEX_USB) {
-		mwifiex_hs_activated_event(priv, true);
+		mwifiex_hs_activated_event(adapter, true);
 		return 0;
 	} else {
 		mwifiex_dbg(adapter, CMD,
@@ -1217,11 +1193,11 @@ int mwifiex_ret_802_11_hs_cfg(struct mwifiex_private *priv,
 	if (conditions != HS_CFG_CANCEL) {
 		set_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags);
 		if (adapter->iface_type == MWIFIEX_USB)
-			mwifiex_hs_activated_event(priv, true);
+			mwifiex_hs_activated_event(adapter, true);
 	} else {
 		clear_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags);
 		if (adapter->hs_activated)
-			mwifiex_hs_activated_event(priv, false);
+			mwifiex_hs_activated_event(adapter, false);
 	}
 
 	return 0;
@@ -1250,9 +1226,7 @@ mwifiex_process_hs_config(struct mwifiex_adapter *adapter)
 	adapter->hs_activated = false;
 	clear_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags);
 	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
-	mwifiex_hs_activated_event(mwifiex_get_priv(adapter,
-						    MWIFIEX_BSS_ROLE_ANY),
-				   false);
+	mwifiex_hs_activated_event(adapter, false);
 }
 EXPORT_SYMBOL_GPL(mwifiex_process_hs_config);
 
@@ -1302,9 +1276,7 @@ mwifiex_process_sleep_confirm_resp(struct mwifiex_adapter *adapter,
 	}
 	adapter->pm_wakeup_card_req = true;
 	if (test_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags))
-		mwifiex_hs_activated_event(mwifiex_get_priv
-						(adapter, MWIFIEX_BSS_ROLE_ANY),
-					   true);
+		mwifiex_hs_activated_event(adapter, true);
 	adapter->ps_state = PS_STATE_SLEEP;
 	cmd->command = cpu_to_le16(command);
 	cmd->seq_num = cpu_to_le16(seq_num);
diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c
index ce0d42e72e94..32c374e47794 100644
--- a/drivers/net/wireless/marvell/mwifiex/init.c
+++ b/drivers/net/wireless/marvell/mwifiex/init.c
@@ -480,14 +480,12 @@ int mwifiex_init_lock_list(struct mwifiex_adapter *adapter)
  *      - Initialize the private structure
  *      - Add BSS priority tables to the adapter structure
  *      - For each interface, send the init commands to firmware
- *      - Send the first command in command pending queue, if available
  */
 int mwifiex_init_fw(struct mwifiex_adapter *adapter)
 {
 	int ret;
 	struct mwifiex_private *priv;
 	u8 i, first_sta = true;
-	int is_cmd_pend_q_empty;
 
 	adapter->hw_status = MWIFIEX_HW_STATUS_INITIALIZING;
 
@@ -509,11 +507,10 @@ int mwifiex_init_fw(struct mwifiex_adapter *adapter)
 	}
 	if (adapter->mfg_mode) {
 		adapter->hw_status = MWIFIEX_HW_STATUS_READY;
-		ret = -EINPROGRESS;
 	} else {
 		for (i = 0; i < adapter->priv_num; i++) {
 			ret = mwifiex_sta_init_cmd(adapter->priv[i],
-						   first_sta, true);
+						   first_sta);
 			if (ret == -1)
 				return -1;
 
@@ -522,17 +519,15 @@ int mwifiex_init_fw(struct mwifiex_adapter *adapter)
 	}
 
 	spin_lock_bh(&adapter->cmd_pending_q_lock);
-	is_cmd_pend_q_empty = list_empty(&adapter->cmd_pending_q);
+	WARN_ON(!list_empty(&adapter->cmd_pending_q));
 	spin_unlock_bh(&adapter->cmd_pending_q_lock);
-	if (!is_cmd_pend_q_empty) {
-		/* Send the first command in queue and return */
-		if (mwifiex_main_process(adapter) != -1)
-			ret = -EINPROGRESS;
-	} else {
-		adapter->hw_status = MWIFIEX_HW_STATUS_READY;
-	}
 
-	return ret;
+	adapter->hw_status = MWIFIEX_HW_STATUS_READY;
+
+	if (adapter->if_ops.init_fw_port)
+		adapter->if_ops.init_fw_port(adapter);
+
+	return 0;
 }
 
 /*
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 0e1f53940401..7b50a88a18e5 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/suspend.h>
+#include <net/sock.h>
 
 #include "main.h"
 #include "wmm.h"
@@ -354,13 +355,6 @@ process_start:
 		if (adapter->cmd_resp_received) {
 			adapter->cmd_resp_received = false;
 			mwifiex_process_cmdresp(adapter);
-
-			/* call mwifiex back when init_fw is done */
-			if (adapter->hw_status == MWIFIEX_HW_STATUS_INIT_DONE) {
-				adapter->hw_status = MWIFIEX_HW_STATUS_READY;
-				mwifiex_init_fw_complete(adapter);
-				maybe_quirk_fw_disable_ds(adapter);
-			}
 		}
 
 		/* Check if we need to confirm Sleep Request
@@ -415,10 +409,7 @@ process_start:
 			if (adapter->hs_activated) {
 				clear_bit(MWIFIEX_IS_HS_CONFIGURED,
 					  &adapter->work_flags);
-				mwifiex_hs_activated_event
-					(mwifiex_get_priv
-					(adapter, MWIFIEX_BSS_ROLE_ANY),
-					false);
+				mwifiex_hs_activated_event(adapter, false);
 			}
 		}
 
@@ -438,10 +429,7 @@ process_start:
 			if (adapter->hs_activated) {
 				clear_bit(MWIFIEX_IS_HS_CONFIGURED,
 					  &adapter->work_flags);
-				mwifiex_hs_activated_event
-					(mwifiex_get_priv
-					 (adapter, MWIFIEX_BSS_ROLE_ANY),
-					 false);
+				mwifiex_hs_activated_event(adapter, false);
 			}
 		}
 
@@ -460,10 +448,7 @@ process_start:
 			if (adapter->hs_activated) {
 				clear_bit(MWIFIEX_IS_HS_CONFIGURED,
 					  &adapter->work_flags);
-				mwifiex_hs_activated_event
-					(mwifiex_get_priv
-					 (adapter, MWIFIEX_BSS_ROLE_ANY),
-					 false);
+				mwifiex_hs_activated_event(adapter, false);
 			}
 		}
 
@@ -587,21 +572,11 @@ static int _mwifiex_fw_dpc(const struct firmware *firmware, void *context)
 			goto err_dnld_fw;
 	}
 
-	adapter->init_wait_q_woken = false;
 	ret = mwifiex_init_fw(adapter);
-	if (ret == -1) {
+	if (ret == -1)
 		goto err_init_fw;
-	} else if (!ret) {
-		adapter->hw_status = MWIFIEX_HW_STATUS_READY;
-		goto done;
-	}
-	/* Wait for mwifiex_init to complete */
-	if (!adapter->mfg_mode) {
-		wait_event_interruptible(adapter->init_wait_q,
-					 adapter->init_wait_q_woken);
-		if (adapter->hw_status != MWIFIEX_HW_STATUS_READY)
-			goto err_init_fw;
-	}
+
+	maybe_quirk_fw_disable_ds(adapter);
 
 	if (!adapter->wiphy) {
 		if (mwifiex_register_cfg80211(adapter)) {
@@ -938,8 +913,7 @@ mwifiex_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	multicast = is_multicast_ether_addr(skb->data);
 
-	if (unlikely(!multicast && skb->sk &&
-		     skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS &&
+	if (unlikely(!multicast && sk_requests_wifi_status(skb->sk) &&
 		     priv->adapter->fw_api_ver == MWIFIEX_FW_V15))
 		skb = mwifiex_clone_skb_for_tx_status(priv,
 						      skb,
@@ -1558,7 +1532,6 @@ mwifiex_reinit_sw(struct mwifiex_adapter *adapter)
 
 	adapter->hw_status = MWIFIEX_HW_STATUS_INITIALIZING;
 	clear_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
-	init_waitqueue_head(&adapter->init_wait_q);
 	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 	adapter->hs_activated = false;
 	clear_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags);
@@ -1726,7 +1699,6 @@ mwifiex_add_card(void *card, struct completion *fw_done,
 
 	adapter->hw_status = MWIFIEX_HW_STATUS_INITIALIZING;
 	clear_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
-	init_waitqueue_head(&adapter->init_wait_q);
 	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 	adapter->hs_activated = false;
 	init_waitqueue_head(&adapter->hs_activate_wait_q);
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index 63f1c900e096..9ac36bef980e 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -239,7 +239,6 @@ struct mwifiex_dbg {
 enum MWIFIEX_HARDWARE_STATUS {
 	MWIFIEX_HW_STATUS_READY,
 	MWIFIEX_HW_STATUS_INITIALIZING,
-	MWIFIEX_HW_STATUS_INIT_DONE,
 	MWIFIEX_HW_STATUS_RESET,
 	MWIFIEX_HW_STATUS_NOT_READY
 };
@@ -865,8 +864,6 @@ struct mwifiex_adapter {
 	unsigned long work_flags;
 	u32 fw_release_number;
 	u8 intf_hdr_len;
-	u16 init_wait_q_woken;
-	wait_queue_head_t init_wait_q;
 	void *card;
 	struct mwifiex_if_ops if_ops;
 	atomic_t bypass_tx_pending;
@@ -919,7 +916,6 @@ struct mwifiex_adapter {
 	struct cmd_ctrl_node *curr_cmd;
 	/* spin lock for command */
 	spinlock_t mwifiex_cmd_lock;
-	u16 last_init_cmd;
 	struct timer_list cmd_timer;
 	struct list_head cmd_free_q;
 	/* spin lock for cmd_free_q */
@@ -1060,8 +1056,6 @@ void mwifiex_free_priv(struct mwifiex_private *priv);
 
 int mwifiex_init_fw(struct mwifiex_adapter *adapter);
 
-int mwifiex_init_fw_complete(struct mwifiex_adapter *adapter);
-
 void mwifiex_shutdown_drv(struct mwifiex_adapter *adapter);
 
 int mwifiex_dnld_fw(struct mwifiex_adapter *, struct mwifiex_fw_image *);
@@ -1125,7 +1119,7 @@ int mwifiex_ret_enh_power_mode(struct mwifiex_private *priv,
 			       struct host_cmd_ds_command *resp,
 			       struct mwifiex_ds_pm_cfg *pm_cfg);
 void mwifiex_process_hs_config(struct mwifiex_adapter *adapter);
-void mwifiex_hs_activated_event(struct mwifiex_private *priv,
+void mwifiex_hs_activated_event(struct mwifiex_adapter *adapter,
 					u8 activated);
 int mwifiex_set_hs_params(struct mwifiex_private *priv, u16 action,
 			  int cmd_type, struct mwifiex_ds_hs_cfg *hs_cfg);
@@ -1156,7 +1150,7 @@ void mwifiex_process_sta_txpd(struct mwifiex_private *priv,
 			      struct sk_buff *skb);
 void mwifiex_process_uap_txpd(struct mwifiex_private *priv,
 			      struct sk_buff *skb);
-int mwifiex_sta_init_cmd(struct mwifiex_private *, u8 first_sta, bool init);
+int mwifiex_sta_init_cmd(struct mwifiex_private *, u8 first_sta);
 int mwifiex_cmd_802_11_scan(struct host_cmd_ds_command *cmd,
 			    struct mwifiex_scan_cmd_config *scan_cfg);
 void mwifiex_queue_scan_cmd(struct mwifiex_private *priv,
@@ -1565,7 +1559,7 @@ int mwifiex_add_wowlan_magic_pkt_filter(struct mwifiex_adapter *adapter);
 int mwifiex_set_mgmt_ies(struct mwifiex_private *priv,
 			 struct cfg80211_beacon_data *data);
 int mwifiex_del_mgmt_ies(struct mwifiex_private *priv);
-u8 *mwifiex_11d_code_2_region(u8 code);
+const u8 *mwifiex_11d_code_2_region(u8 code);
 void mwifiex_uap_set_channel(struct mwifiex_private *priv,
 			     struct mwifiex_uap_bss_param *bss_cfg,
 			     struct cfg80211_chan_def chandef);
@@ -1598,7 +1592,6 @@ mwifiex_add_sta_entry(struct mwifiex_private *priv, const u8 *mac);
 struct mwifiex_sta_node *
 mwifiex_get_sta_entry(struct mwifiex_private *priv, const u8 *mac);
 u8 mwifiex_is_tdls_chan_switching(struct mwifiex_private *priv);
-u8 mwifiex_is_tdls_off_chan(struct mwifiex_private *priv);
 u8 mwifiex_is_send_cmd_allowed(struct mwifiex_private *priv);
 int mwifiex_send_tdls_data_frame(struct mwifiex_private *priv, const u8 *peer,
 				 u8 action_code, u8 dialog_token,
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c
index dd2a42e732f2..a760de191fce 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.c
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.c
@@ -2971,7 +2971,7 @@ static int mwifiex_init_pcie(struct mwifiex_adapter *adapter)
 		goto err_iomap2;
 	}
 
-	pr_notice("PCI memory map Virt0: %pK PCI memory map Virt2: %pK\n",
+	pr_notice("PCI memory map Virt0: %p PCI memory map Virt2: %p\n",
 		  card->pci_mmap, card->pci_mmap1);
 
 	ret = mwifiex_pcie_alloc_buffers(adapter);
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
index c4689f5a1acc..c93281f5a47c 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
@@ -157,7 +157,7 @@ mwifiex_cmd_802_11_get_log(struct host_cmd_ds_command *cmd)
  */
 static int mwifiex_cmd_tx_rate_cfg(struct mwifiex_private *priv,
 				   struct host_cmd_ds_command *cmd,
-				   u16 cmd_action, u16 *pbitmap_rates)
+				   u16 cmd_action, const u16 *pbitmap_rates)
 {
 	struct host_cmd_ds_tx_rate_cfg *rate_cfg = &cmd->params.tx_rate_cfg;
 	struct mwifiex_rate_scope *rate_scope;
@@ -174,34 +174,19 @@ static int mwifiex_cmd_tx_rate_cfg(struct mwifiex_private *priv,
 	rate_scope->type = cpu_to_le16(TLV_TYPE_RATE_SCOPE);
 	rate_scope->length = cpu_to_le16
 		(sizeof(*rate_scope) - sizeof(struct mwifiex_ie_types_header));
-	if (pbitmap_rates != NULL) {
-		rate_scope->hr_dsss_rate_bitmap = cpu_to_le16(pbitmap_rates[0]);
-		rate_scope->ofdm_rate_bitmap = cpu_to_le16(pbitmap_rates[1]);
-		for (i = 0; i < ARRAY_SIZE(rate_scope->ht_mcs_rate_bitmap); i++)
-			rate_scope->ht_mcs_rate_bitmap[i] =
-				cpu_to_le16(pbitmap_rates[2 + i]);
-		if (priv->adapter->fw_api_ver == MWIFIEX_FW_V15) {
-			for (i = 0;
-			     i < ARRAY_SIZE(rate_scope->vht_mcs_rate_bitmap);
-			     i++)
-				rate_scope->vht_mcs_rate_bitmap[i] =
-					cpu_to_le16(pbitmap_rates[10 + i]);
-		}
-	} else {
-		rate_scope->hr_dsss_rate_bitmap =
-			cpu_to_le16(priv->bitmap_rates[0]);
-		rate_scope->ofdm_rate_bitmap =
-			cpu_to_le16(priv->bitmap_rates[1]);
-		for (i = 0; i < ARRAY_SIZE(rate_scope->ht_mcs_rate_bitmap); i++)
-			rate_scope->ht_mcs_rate_bitmap[i] =
-				cpu_to_le16(priv->bitmap_rates[2 + i]);
-		if (priv->adapter->fw_api_ver == MWIFIEX_FW_V15) {
-			for (i = 0;
-			     i < ARRAY_SIZE(rate_scope->vht_mcs_rate_bitmap);
-			     i++)
-				rate_scope->vht_mcs_rate_bitmap[i] =
-					cpu_to_le16(priv->bitmap_rates[10 + i]);
-		}
+	if (!pbitmap_rates)
+		pbitmap_rates = priv->bitmap_rates;
+
+	rate_scope->hr_dsss_rate_bitmap = cpu_to_le16(pbitmap_rates[0]);
+	rate_scope->ofdm_rate_bitmap = cpu_to_le16(pbitmap_rates[1]);
+
+	for (i = 0; i < ARRAY_SIZE(rate_scope->ht_mcs_rate_bitmap); i++)
+		rate_scope->ht_mcs_rate_bitmap[i] = cpu_to_le16(pbitmap_rates[2 + i]);
+
+	if (priv->adapter->fw_api_ver == MWIFIEX_FW_V15) {
+		for (i = 0; i < ARRAY_SIZE(rate_scope->vht_mcs_rate_bitmap); i++)
+			rate_scope->vht_mcs_rate_bitmap[i] =
+				cpu_to_le16(pbitmap_rates[10 + i]);
 	}
 
 	rate_drop = (struct mwifiex_rate_drop_pattern *) ((u8 *) rate_scope +
@@ -2258,7 +2243,7 @@ int mwifiex_sta_prepare_cmd(struct mwifiex_private *priv, uint16_t cmd_no,
  *      - Set 11d control
  *      - Set MAC control (this must be the last command to initialize firmware)
  */
-int mwifiex_sta_init_cmd(struct mwifiex_private *priv, u8 first_sta, bool init)
+int mwifiex_sta_init_cmd(struct mwifiex_private *priv, u8 first_sta)
 {
 	struct mwifiex_adapter *adapter = priv->adapter;
 	int ret;
@@ -2433,11 +2418,5 @@ int mwifiex_sta_init_cmd(struct mwifiex_private *priv, u8 first_sta, bool init)
 	ret = mwifiex_send_cmd(priv, HostCmd_CMD_11N_CFG,
 			       HostCmd_ACT_GEN_SET, 0, &tx_cfg, true);
 
-	if (init) {
-		/* set last_init_cmd before sending the command */
-		priv->adapter->last_init_cmd = HostCmd_CMD_11N_CFG;
-		ret = -EINPROGRESS;
-	}
-
 	return ret;
 }
diff --git a/drivers/net/wireless/marvell/mwifiex/txrx.c b/drivers/net/wireless/marvell/mwifiex/txrx.c
index bd91678d26b4..f44e22f24511 100644
--- a/drivers/net/wireless/marvell/mwifiex/txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/txrx.c
@@ -24,8 +24,7 @@
 int mwifiex_handle_rx_packet(struct mwifiex_adapter *adapter,
 			     struct sk_buff *skb)
 {
-	struct mwifiex_private *priv =
-		mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_ANY);
+	struct mwifiex_private *priv;
 	struct rxpd *local_rx_pd;
 	struct mwifiex_rxinfo *rx_info = MWIFIEX_SKB_RXCB(skb);
 	int ret;
diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c
index 1f1f6280a0f2..4c5b1de0e936 100644
--- a/drivers/net/wireless/marvell/mwifiex/util.c
+++ b/drivers/net/wireless/marvell/mwifiex/util.c
@@ -116,24 +116,6 @@ static struct mwifiex_debug_data items[] = {
 static int num_of_items = ARRAY_SIZE(items);
 
 /*
- * Firmware initialization complete callback handler.
- *
- * This function wakes up the function waiting on the init
- * wait queue for the firmware initialization to complete.
- */
-int mwifiex_init_fw_complete(struct mwifiex_adapter *adapter)
-{
-
-	if (adapter->hw_status == MWIFIEX_HW_STATUS_READY)
-		if (adapter->if_ops.init_fw_port)
-			adapter->if_ops.init_fw_port(adapter);
-
-	adapter->init_wait_q_woken = true;
-	wake_up_interruptible(&adapter->init_wait_q);
-	return 0;
-}
-
-/*
  * This function sends init/shutdown command
  * to firmware.
  */
@@ -663,7 +645,7 @@ u8 mwifiex_is_tdls_chan_switching(struct mwifiex_private *priv)
 	return false;
 }
 
-u8 mwifiex_is_tdls_off_chan(struct mwifiex_private *priv)
+static u8 mwifiex_is_tdls_off_chan(struct mwifiex_private *priv)
 {
 	struct mwifiex_sta_node *sta_ptr;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/wmm.c b/drivers/net/wireless/marvell/mwifiex/wmm.c
index bcb61dab7dc8..1b1222c73728 100644
--- a/drivers/net/wireless/marvell/mwifiex/wmm.c
+++ b/drivers/net/wireless/marvell/mwifiex/wmm.c
@@ -1428,13 +1428,13 @@ mwifiex_dequeue_tx_packet(struct mwifiex_adapter *adapter)
 	}
 
 	if (!ptr->is_11n_enabled ||
-		ptr->ba_status ||
-		priv->wps.session_enable) {
+	    ptr->ba_status ||
+	    priv->wps.session_enable) {
 		if (ptr->is_11n_enabled &&
-			ptr->ba_status &&
-			ptr->amsdu_in_ampdu &&
-			mwifiex_is_amsdu_allowed(priv, tid) &&
-			mwifiex_is_11n_aggragation_possible(priv, ptr,
+		    ptr->ba_status &&
+		    ptr->amsdu_in_ampdu &&
+		    mwifiex_is_amsdu_allowed(priv, tid) &&
+		    mwifiex_is_11n_aggragation_possible(priv, ptr,
 							adapter->tx_buf_size))
 			mwifiex_11n_aggregate_pkt(priv, ptr, ptr_index);
 			/* ra_list_spinlock has been freed in
diff --git a/drivers/net/wireless/mediatek/mt76/channel.c b/drivers/net/wireless/mediatek/mt76/channel.c
index e7b839e74290..cc2d888e3f17 100644
--- a/drivers/net/wireless/mediatek/mt76/channel.c
+++ b/drivers/net/wireless/mediatek/mt76/channel.c
@@ -302,11 +302,13 @@ void mt76_put_vif_phy_link(struct mt76_phy *phy, struct ieee80211_vif *vif,
 			   struct mt76_vif_link *mlink)
 {
 	struct mt76_dev *dev = phy->dev;
-	struct mt76_vif_data *mvif = mlink->mvif;
+	struct mt76_vif_data *mvif;
 
 	if (IS_ERR_OR_NULL(mlink) || !mlink->offchannel)
 		return;
 
+	mvif = mlink->mvif;
+
 	rcu_assign_pointer(mvif->offchannel_link, NULL);
 	dev->drv->vif_link_remove(phy, vif, &vif->bss_conf, mlink);
 	kfree(mlink);
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 844af16ee551..35b4ec91979e 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -1011,6 +1011,7 @@ void mt76_dma_cleanup(struct mt76_dev *dev)
 	int i;
 
 	mt76_worker_disable(&dev->tx_worker);
+	napi_disable(&dev->tx_napi);
 	netif_napi_del(&dev->tx_napi);
 
 	for (i = 0; i < ARRAY_SIZE(dev->phys); i++) {
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index b88d7e10742e..45c8db939d55 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -449,8 +449,10 @@ mt76_phy_init(struct mt76_phy *phy, struct ieee80211_hw *hw)
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_AIRTIME_FAIRNESS);
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_AQL);
 
-	wiphy->available_antennas_tx = phy->antenna_mask;
-	wiphy->available_antennas_rx = phy->antenna_mask;
+	if (!wiphy->available_antennas_tx)
+		wiphy->available_antennas_tx = phy->antenna_mask;
+	if (!wiphy->available_antennas_rx)
+		wiphy->available_antennas_rx = phy->antenna_mask;
 
 	wiphy->sar_capa = &mt76_sar_capa;
 	phy->frp = devm_kcalloc(dev->dev, wiphy->sar_capa->num_freq_ranges,
@@ -1703,7 +1705,7 @@ s8 mt76_get_power_bound(struct mt76_phy *phy, s8 txpower)
 	int n_chains = hweight16(phy->chainmask);
 
 	txpower = mt76_get_sar_power(phy, phy->chandef.chan, txpower * 2);
-	txpower -= mt76_tx_power_nss_delta(n_chains);
+	txpower -= mt76_tx_power_path_delta(n_chains);
 
 	return txpower;
 }
@@ -1719,7 +1721,7 @@ int mt76_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		return -EINVAL;
 
 	n_chains = hweight16(phy->chainmask);
-	delta = mt76_tx_power_nss_delta(n_chains);
+	delta = mt76_tx_power_path_delta(n_chains);
 	*dbm = DIV_ROUND_UP(phy->txpower_cur + delta, 2);
 
 	return 0;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index d7cd467b812f..5f8d81cda6cd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -162,6 +162,16 @@ enum mt76_dfs_state {
 	MT_DFS_STATE_ACTIVE,
 };
 
+#define MT76_RNR_SCAN_MAX_BSSIDS       16
+struct mt76_scan_rnr_param {
+	u8 bssid[MT76_RNR_SCAN_MAX_BSSIDS][ETH_ALEN];
+	u8 channel[MT76_RNR_SCAN_MAX_BSSIDS];
+	u8 random_mac[ETH_ALEN];
+	u8 seq_num;
+	u8 bssid_num;
+	u32 sreq_flag;
+};
+
 struct mt76_queue_buf {
 	dma_addr_t addr;
 	u16 len:15,
@@ -941,6 +951,8 @@ struct mt76_dev {
 	char alpha2[3];
 	enum nl80211_dfs_regions region;
 
+	struct mt76_scan_rnr_param rnr;
+
 	u32 debugfs_reg;
 
 	u8 csa_complete;
@@ -1386,12 +1398,12 @@ static inline bool mt76_is_skb_pktid(u8 pktid)
 	return pktid >= MT_PACKET_ID_FIRST;
 }
 
-static inline u8 mt76_tx_power_nss_delta(u8 nss)
+static inline u8 mt76_tx_power_path_delta(u8 path)
 {
-	static const u8 nss_delta[4] = { 0, 6, 9, 12 };
-	u8 idx = nss - 1;
+	static const u8 path_delta[5] = { 0, 6, 9, 12, 14 };
+	u8 idx = path - 1;
 
-	return (idx < ARRAY_SIZE(nss_delta)) ? nss_delta[idx] : 0;
+	return (idx < ARRAY_SIZE(path_delta)) ? path_delta[idx] : 0;
 }
 
 static inline bool mt76_testmode_enabled(struct mt76_phy *phy)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
index 66ba3be27343..aae80005a3c1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
@@ -273,7 +273,7 @@ void mt7615_init_txpower(struct mt7615_dev *dev,
 			 struct ieee80211_supported_band *sband)
 {
 	int i, n_chains = hweight8(dev->mphy.antenna_mask), target_chains;
-	int delta_idx, delta = mt76_tx_power_nss_delta(n_chains);
+	int delta_idx, delta = mt76_tx_power_path_delta(n_chains);
 	u8 *eep = (u8 *)dev->mt76.eeprom.data;
 	enum nl80211_band band = sband->band;
 	struct mt76_power_limits limits;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
index b8fcd4eb3fbb..4064e193d4de 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
@@ -2067,7 +2067,7 @@ static void mt7615_mcu_set_txpower_sku(struct mt7615_phy *phy, u8 *sku)
 	};
 
 	tx_power = mt76_get_sar_power(mphy, mphy->chandef.chan, tx_power);
-	tx_power -= mt76_tx_power_nss_delta(n_chains);
+	tx_power -= mt76_tx_power_path_delta(n_chains);
 	tx_power = mt76_get_rate_power_limits(mphy, mphy->chandef.chan,
 					      &limits, tx_power);
 	mphy->txpower_cur = tx_power;
@@ -2084,8 +2084,8 @@ static void mt7615_mcu_set_txpower_sku(struct mt7615_phy *phy, u8 *sku)
 		int delta = 0;
 
 		if (i < n_chains - 1)
-			delta = mt76_tx_power_nss_delta(n_chains) -
-				mt76_tx_power_nss_delta(i + 1);
+			delta = mt76_tx_power_path_delta(n_chains) -
+				mt76_tx_power_path_delta(i + 1);
 		sku[MT_SKU_1SS_DELTA + i] = delta;
 	}
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac.h
index 455979476d11..192dcc374a64 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac.h
@@ -232,9 +232,14 @@ static inline bool is_mt7992(struct mt76_dev *dev)
 	return mt76_chip(dev) == 0x7992;
 }
 
+static inline bool is_mt7990(struct mt76_dev *dev)
+{
+	return mt76_chip(dev) == 0x7993;
+}
+
 static inline bool is_mt799x(struct mt76_dev *dev)
 {
-	return is_mt7996(dev) || is_mt7992(dev);
+	return is_mt7996(dev) || is_mt7992(dev) || is_mt7990(dev);
 }
 
 static inline bool is_mt7622(struct mt76_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
index 487ad716f872..1013cad57a7f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
@@ -273,6 +273,7 @@ enum tx_frag_idx {
 #define MT_TXD6_TX_RATE			GENMASK(21, 16)
 #define MT_TXD6_TIMESTAMP_OFS_EN	BIT(15)
 #define MT_TXD6_TIMESTAMP_OFS_IDX	GENMASK(14, 10)
+#define MT_TXD6_TID_ADDBA		GENMASK(10, 8)
 #define MT_TXD6_MSDU_CNT		GENMASK(9, 4)
 #define MT_TXD6_MSDU_CNT_V2		GENMASK(15, 10)
 #define MT_TXD6_DIS_MAT			BIT(3)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index bafcf5a279e2..cb13d0a76878 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -67,8 +67,7 @@ int mt76_connac_mcu_init_download(struct mt76_dev *dev, u32 addr, u32 len,
 	if ((!is_connac_v1(dev) && addr == MCU_PATCH_ADDRESS) ||
 	    (is_mt7921(dev) && addr == 0x900000) ||
 	    (is_mt7925(dev) && (addr == 0x900000 || addr == 0xe0002800)) ||
-	    (is_mt7996(dev) && addr == 0x900000) ||
-	    (is_mt7992(dev) && addr == 0x900000))
+	    (is_mt799x(dev) && addr == 0x900000))
 		cmd = MCU_CMD(PATCH_START_REQ);
 	else
 		cmd = MCU_CMD(TARGET_ADDRESS_LEN_REQ);
@@ -391,7 +390,7 @@ void mt76_connac_mcu_sta_basic_tlv(struct mt76_dev *dev, struct sk_buff *skb,
 		basic->conn_type = cpu_to_le32(CONNECTION_INFRA_BC);
 
 		if (vif->type == NL80211_IFTYPE_STATION &&
-		    link_conf && !is_zero_ether_addr(link_conf->bssid)) {
+		    !is_zero_ether_addr(link_conf->bssid)) {
 			memcpy(basic->peer_addr, link_conf->bssid, ETH_ALEN);
 			basic->aid = cpu_to_le16(vif->cfg.aid);
 		} else {
@@ -1667,6 +1666,44 @@ int mt76_connac_mcu_uni_add_bss(struct mt76_phy *phy,
 }
 EXPORT_SYMBOL_GPL(mt76_connac_mcu_uni_add_bss);
 
+void mt76_connac_mcu_build_rnr_scan_param(struct mt76_dev *mdev,
+					  struct cfg80211_scan_request *sreq)
+{
+	struct ieee80211_channel **scan_list = sreq->channels;
+	int i, bssid_index = 0;
+
+	/* clear 6G active Scan BSSID table */
+	memset(&mdev->rnr, 0, sizeof(mdev->rnr));
+
+	for (i = 0; i < sreq->n_6ghz_params; i++) {
+		u8 ch_idx = sreq->scan_6ghz_params[i].channel_idx;
+		int k = 0;
+
+		/* Remove the duplicated BSSID */
+		for (k = 0; k < bssid_index; k++) {
+			if (!memcmp(&mdev->rnr.bssid[k],
+				    sreq->scan_6ghz_params[i].bssid,
+				    ETH_ALEN))
+				break;
+		}
+
+		if (k == bssid_index &&
+		    bssid_index < MT76_RNR_SCAN_MAX_BSSIDS) {
+			memcpy(&mdev->rnr.bssid[bssid_index++],
+			       sreq->scan_6ghz_params[i].bssid, ETH_ALEN);
+			mdev->rnr.channel[k] = scan_list[ch_idx]->hw_value;
+		}
+	}
+
+	mdev->rnr.bssid_num = bssid_index;
+
+	if (sreq->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
+		memcpy(mdev->rnr.random_mac, sreq->mac_addr, ETH_ALEN);
+		mdev->rnr.sreq_flag = sreq->flags;
+	}
+}
+EXPORT_SYMBOL_GPL(mt76_connac_mcu_build_rnr_scan_param);
+
 #define MT76_CONNAC_SCAN_CHANNEL_TIME		60
 int mt76_connac_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 			    struct ieee80211_scan_request *scan_req)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
index 43237e518373..27daf419560a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
@@ -869,6 +869,7 @@ enum {
 #define NETWORK_WDS			BIT(21)
 
 #define SCAN_FUNC_RANDOM_MAC		BIT(0)
+#define SCAN_FUNC_RNR_SCAN		BIT(3)
 #define SCAN_FUNC_SPLIT_SCAN		BIT(5)
 
 #define CONNECTION_INFRA_STA		(STA_TYPE_STA | NETWORK_INFRA)
@@ -1065,6 +1066,7 @@ enum {
 	MCU_UNI_EVENT_WED_RRO = 0x57,
 	MCU_UNI_EVENT_PER_STA_INFO = 0x6d,
 	MCU_UNI_EVENT_ALL_STA_INFO = 0x6e,
+	MCU_UNI_EVENT_SDO = 0x83,
 };
 
 #define MCU_UNI_CMD_EVENT			BIT(1)
@@ -1182,6 +1184,11 @@ enum {
 #define MCU_UNI_CMD(_t)				(__MCU_CMD_FIELD_UNI |			\
 						 FIELD_PREP(__MCU_CMD_FIELD_ID,		\
 							    MCU_UNI_CMD_##_t))
+
+#define MCU_UNI_QUERY(_t)			(__MCU_CMD_FIELD_UNI | __MCU_CMD_FIELD_QUERY | \
+						 FIELD_PREP(__MCU_CMD_FIELD_ID,		\
+							    MCU_UNI_CMD_##_t))
+
 #define MCU_CE_CMD(_t)				(__MCU_CMD_FIELD_CE |			\
 						 FIELD_PREP(__MCU_CMD_FIELD_ID,		\
 							   MCU_CE_CMD_##_t))
@@ -1287,16 +1294,20 @@ enum {
 	MCU_UNI_CMD_EFUSE_CTRL = 0x2d,
 	MCU_UNI_CMD_RA = 0x2f,
 	MCU_UNI_CMD_MURU = 0x31,
+	MCU_UNI_CMD_TESTMODE_RX_STAT = 0x32,
 	MCU_UNI_CMD_BF = 0x33,
 	MCU_UNI_CMD_CHANNEL_SWITCH = 0x34,
 	MCU_UNI_CMD_THERMAL = 0x35,
 	MCU_UNI_CMD_VOW = 0x37,
 	MCU_UNI_CMD_FIXED_RATE_TABLE = 0x40,
+	MCU_UNI_CMD_TESTMODE_CTRL = 0x46,
 	MCU_UNI_CMD_RRO = 0x57,
 	MCU_UNI_CMD_OFFCH_SCAN_CTRL = 0x58,
 	MCU_UNI_CMD_PER_STA_INFO = 0x6d,
 	MCU_UNI_CMD_ALL_STA_INFO = 0x6e,
 	MCU_UNI_CMD_ASSERT_DUMP = 0x6f,
+	MCU_UNI_CMD_RADIO_STATUS = 0x80,
+	MCU_UNI_CMD_SDO = 0x88,
 };
 
 enum {
@@ -1369,6 +1380,7 @@ enum {
 	UNI_BSS_INFO_OFFLOAD = 25,
 	UNI_BSS_INFO_MLD = 26,
 	UNI_BSS_INFO_PM_DISABLE = 27,
+	UNI_BSS_INFO_EHT = 30,
 };
 
 enum {
@@ -1969,6 +1981,8 @@ int mt76_connac_mcu_start_patch(struct mt76_dev *dev);
 int mt76_connac_mcu_patch_sem_ctrl(struct mt76_dev *dev, bool get);
 int mt76_connac_mcu_start_firmware(struct mt76_dev *dev, u32 addr, u32 option);
 
+void mt76_connac_mcu_build_rnr_scan_param(struct mt76_dev *mdev,
+					  struct cfg80211_scan_request *sreq);
 int mt76_connac_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 			    struct ieee80211_scan_request *scan_req);
 int mt76_connac_mcu_cancel_hw_scan(struct mt76_phy *phy,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
index a82c75ba26e6..a683d53c7ceb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
@@ -174,7 +174,6 @@ static int mt76x02_poll_tx(struct napi_struct *napi, int budget)
 
 int mt76x02_dma_init(struct mt76x02_dev *dev)
 {
-	struct mt76_txwi_cache __maybe_unused *t;
 	int i, ret, fifo_size;
 	struct mt76_queue *q;
 	void *status_fifo;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index 84ef80ab4afb..96cecc576a98 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -17,6 +17,8 @@ static const struct usb_device_id mt76x2u_device_table[] = {
 	{ USB_DEVICE(0x057c, 0x8503) },	/* Avm FRITZ!WLAN AC860 */
 	{ USB_DEVICE(0x7392, 0xb711) },	/* Edimax EW 7722 UAC */
 	{ USB_DEVICE(0x0e8d, 0x7632) },	/* HC-M7662BU1 */
+	{ USB_DEVICE(0x0471, 0x2126) }, /* LiteOn WN4516R module, nonstandard USB connector */
+	{ USB_DEVICE(0x0471, 0x7600) }, /* LiteOn WN4519R module, nonstandard USB connector */
 	{ USB_DEVICE(0x2c4e, 0x0103) },	/* Mercury UD13 */
 	{ USB_DEVICE(0x0846, 0x9014) },	/* Netgear WNDA3100v3 */
 	{ USB_DEVICE(0x0846, 0x9053) },	/* Netgear A6210 */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
index 33a14365ec9b..3b5562811511 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
@@ -191,6 +191,7 @@ int mt76x2u_register_device(struct mt76x02_dev *dev)
 {
 	struct ieee80211_hw *hw = mt76_hw(dev);
 	struct mt76_usb *usb = &dev->mt76.usb;
+	bool vht;
 	int err;
 
 	INIT_DELAYED_WORK(&dev->cal_work, mt76x2u_phy_calibrate);
@@ -217,7 +218,17 @@ int mt76x2u_register_device(struct mt76x02_dev *dev)
 
 	/* check hw sg support in order to enable AMSDU */
 	hw->max_tx_fragments = dev->mt76.usb.sg_en ? MT_TX_SG_MAX_SIZE : 1;
-	err = mt76_register_device(&dev->mt76, true, mt76x02_rates,
+	switch (dev->mt76.rev) {
+	case 0x76320044:
+		/* these ASIC revisions do not support VHT */
+		vht = false;
+		break;
+	default:
+		vht = true;
+		break;
+	}
+
+	err = mt76_register_device(&dev->mt76, vht, mt76x02_rates,
 				   ARRAY_SIZE(mt76x02_rates));
 	if (err)
 		goto fail;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
index 192e8eff970b..b287b7d9394e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
@@ -211,13 +211,28 @@ static const struct file_operations mt7915_sys_recovery_ops = {
 static int
 mt7915_radar_trigger(void *data, u64 val)
 {
-	struct mt7915_dev *dev = data;
+#define RADAR_MAIN_CHAIN	1
+#define RADAR_BACKGROUND	2
+	struct mt7915_phy *phy = data;
+	struct mt7915_dev *dev = phy->dev;
+	int rdd_idx;
+
+	if (!val || val > RADAR_BACKGROUND)
+		return -EINVAL;
 
-	if (val > MT_RX_SEL2)
+	if (val == RADAR_BACKGROUND && !dev->rdd2_phy) {
+		dev_err(dev->mt76.dev, "Background radar is not enabled\n");
 		return -EINVAL;
+	}
+
+	rdd_idx = mt7915_get_rdd_idx(phy, val == RADAR_BACKGROUND);
+	if (rdd_idx < 0) {
+		dev_err(dev->mt76.dev, "No RDD found\n");
+		return -EINVAL;
+	}
 
 	return mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_RADAR_EMULATE,
-				       val, 0, 0);
+				       rdd_idx, 0, 0);
 }
 
 DEFINE_DEBUGFS_ATTRIBUTE(fops_radar_trigger, NULL,
@@ -445,6 +460,11 @@ mt7915_rdd_monitor(struct seq_file *s, void *data)
 
 	mutex_lock(&dev->mt76.mutex);
 
+	if (!mt7915_eeprom_has_background_radar(dev)) {
+		seq_puts(s, "no background radar capability\n");
+		goto out;
+	}
+
 	if (!cfg80211_chandef_valid(chandef)) {
 		ret = -EINVAL;
 		goto out;
@@ -1242,7 +1262,7 @@ int mt7915_init_debugfs(struct mt7915_phy *phy)
 	if (!dev->dbdc_support || phy->mt76->band_idx) {
 		debugfs_create_u32("dfs_hw_pattern", 0400, dir,
 				   &dev->hw_pattern);
-		debugfs_create_file("radar_trigger", 0200, dir, dev,
+		debugfs_create_file("radar_trigger", 0200, dir, phy,
 				    &fops_radar_trigger);
 		debugfs_create_devm_seqfile(dev->mt76.dev, "rdd_monitor", dir,
 					    mt7915_rdd_monitor);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
index 928e0b07a9bf..c0f3402d30bb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
@@ -147,7 +147,7 @@ static int mt7915_eeprom_load(struct mt7915_dev *dev)
 		/* read eeprom data from efuse */
 		block_num = DIV_ROUND_UP(eeprom_size, eeprom_blk_size);
 		for (i = 0; i < block_num; i++) {
-			ret = mt7915_mcu_get_eeprom(dev, i * eeprom_blk_size);
+			ret = mt7915_mcu_get_eeprom(dev, i * eeprom_blk_size, NULL);
 			if (ret < 0)
 				return ret;
 		}
@@ -361,6 +361,37 @@ s8 mt7915_eeprom_get_power_delta(struct mt7915_dev *dev, int band)
 	return val & MT_EE_RATE_DELTA_SIGN ? delta : -delta;
 }
 
+bool
+mt7915_eeprom_has_background_radar(struct mt7915_dev *dev)
+{
+	u8 val, buf[MT7915_EEPROM_BLOCK_SIZE];
+	u8 band_sel, tx_path, rx_path;
+	int offs = MT_EE_WIFI_CONF + 1;
+
+	switch (mt76_chip(&dev->mt76)) {
+	case 0x7915:
+		return true;
+	case 0x7906:
+		/* read efuse to check background radar capability */
+		if (mt7915_mcu_get_eeprom(dev, offs, buf))
+			break;
+
+		val = buf[offs % MT7915_EEPROM_BLOCK_SIZE];
+		band_sel = u8_get_bits(val, MT_EE_WIFI_CONF0_BAND_SEL);
+		tx_path = u8_get_bits(val, MT_EE_WIFI_CONF0_TX_PATH);
+		rx_path = u8_get_bits(val, MT_EE_WIFI_CONF0_RX_PATH);
+
+		return (band_sel == MT_EE_V2_BAND_SEL_5GHZ &&
+			tx_path == rx_path && rx_path == 2);
+	case 0x7981:
+	case 0x7986:
+	default:
+		break;
+	}
+
+	return false;
+}
+
 const u8 mt7915_sku_group_len[] = {
 	[SKU_CCK] = 4,
 	[SKU_OFDM] = 8,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h
index 509fb43d8a68..31aec0f40232 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h
@@ -55,6 +55,7 @@ enum mt7915_eeprom_field {
 #define MT_EE_CAL_DPD_SIZE_V2_7981		(102 * MT_EE_CAL_UNIT)	/* no 6g dpd data */
 
 #define MT_EE_WIFI_CONF0_TX_PATH		GENMASK(2, 0)
+#define MT_EE_WIFI_CONF0_RX_PATH		GENMASK(5, 3)
 #define MT_EE_WIFI_CONF0_BAND_SEL		GENMASK(7, 6)
 #define MT_EE_WIFI_CONF1_BAND_SEL		GENMASK(7, 6)
 #define MT_EE_WIFI_CONF_STREAM_NUM		GENMASK(7, 5)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index bee4beabc4eb..3e30ca5155d2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -285,7 +285,7 @@ static void __mt7915_init_txpower(struct mt7915_phy *phy,
 {
 	struct mt7915_dev *dev = phy->dev;
 	int i, n_chains = hweight16(phy->mt76->chainmask);
-	int nss_delta = mt76_tx_power_nss_delta(n_chains);
+	int path_delta = mt76_tx_power_path_delta(n_chains);
 	int pwr_delta = mt7915_eeprom_get_power_delta(dev, sband->band);
 	struct mt76_power_limits limits;
 
@@ -305,7 +305,7 @@ static void __mt7915_init_txpower(struct mt7915_phy *phy,
 		target_power = mt76_get_rate_power_limits(phy->mt76, chan,
 							  &limits,
 							  target_power);
-		target_power += nss_delta;
+		target_power += path_delta;
 		target_power = DIV_ROUND_UP(target_power, 2);
 		chan->max_power = min_t(int, chan->max_reg_power,
 					target_power);
@@ -392,9 +392,10 @@ mt7915_init_wiphy(struct mt7915_phy *phy)
 	if (!is_mt7915(&dev->mt76))
 		wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_STA_TX_PWR);
 
-	if (!mdev->dev->of_node ||
-	    !of_property_read_bool(mdev->dev->of_node,
-				   "mediatek,disable-radar-background"))
+	if (mt7915_eeprom_has_background_radar(phy->dev) &&
+	    (!mdev->dev->of_node ||
+	     !of_property_read_bool(mdev->dev->of_node,
+				    "mediatek,disable-radar-background")))
 		wiphy_ext_feature_set(wiphy,
 				      NL80211_EXT_FEATURE_RADAR_BACKGROUND);
 
@@ -924,8 +925,7 @@ mt7915_set_stream_he_txbf_caps(struct mt7915_phy *phy,
 
 	c = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US;
 	if (!is_mt7915(&dev->mt76))
-		c |= IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO |
-		     IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO;
+		c |= IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO;
 	elem->phy_cap_info[2] |= c;
 
 	c = IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE |
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 2ba6eb3038ce..9400e4af2a04 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -2035,16 +2035,15 @@ void mt7915_mac_work(struct work_struct *work)
 static void mt7915_dfs_stop_radar_detector(struct mt7915_phy *phy)
 {
 	struct mt7915_dev *dev = phy->dev;
+	int rdd_idx = mt7915_get_rdd_idx(phy, false);
 
-	if (phy->rdd_state & BIT(0))
-		mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_STOP, 0,
-					MT_RX_SEL0, 0);
-	if (phy->rdd_state & BIT(1))
-		mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_STOP, 1,
-					MT_RX_SEL0, 0);
+	if (rdd_idx < 0)
+		return;
+
+	mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_STOP, rdd_idx, 0, 0);
 }
 
-static int mt7915_dfs_start_rdd(struct mt7915_dev *dev, int chain)
+static int mt7915_dfs_start_rdd(struct mt7915_dev *dev, int rdd_idx)
 {
 	int err, region;
 
@@ -2061,52 +2060,38 @@ static int mt7915_dfs_start_rdd(struct mt7915_dev *dev, int chain)
 		break;
 	}
 
-	err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_START, chain,
-				      MT_RX_SEL0, region);
+	err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_START, rdd_idx, 0, region);
 	if (err < 0)
 		return err;
 
 	if (is_mt7915(&dev->mt76)) {
-		err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_SET_WF_ANT, chain,
+		err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_SET_WF_ANT, rdd_idx,
 					      0, dev->dbdc_support ? 2 : 0);
 		if (err < 0)
 			return err;
 	}
 
-	return mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_DET_MODE, chain,
-				       MT_RX_SEL0, 1);
+	return mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_DET_MODE, rdd_idx, 0, 1);
 }
 
 static int mt7915_dfs_start_radar_detector(struct mt7915_phy *phy)
 {
-	struct cfg80211_chan_def *chandef = &phy->mt76->chandef;
 	struct mt7915_dev *dev = phy->dev;
-	int err;
+	int err, rdd_idx;
+
+	rdd_idx = mt7915_get_rdd_idx(phy, false);
+	if (rdd_idx < 0)
+		return -EINVAL;
 
 	/* start CAC */
-	err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_CAC_START,
-				      phy->mt76->band_idx, MT_RX_SEL0, 0);
+	err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_CAC_START, rdd_idx, 0, 0);
 	if (err < 0)
 		return err;
 
-	err = mt7915_dfs_start_rdd(dev, phy->mt76->band_idx);
+	err = mt7915_dfs_start_rdd(dev, rdd_idx);
 	if (err < 0)
 		return err;
 
-	phy->rdd_state |= BIT(phy->mt76->band_idx);
-
-	if (!is_mt7915(&dev->mt76))
-		return 0;
-
-	if (chandef->width == NL80211_CHAN_WIDTH_160 ||
-	    chandef->width == NL80211_CHAN_WIDTH_80P80) {
-		err = mt7915_dfs_start_rdd(dev, 1);
-		if (err < 0)
-			return err;
-
-		phy->rdd_state |= BIT(1);
-	}
-
 	return 0;
 }
 
@@ -2148,12 +2133,12 @@ int mt7915_dfs_init_radar_detector(struct mt7915_phy *phy)
 {
 	struct mt7915_dev *dev = phy->dev;
 	enum mt76_dfs_state dfs_state, prev_state;
-	int err;
+	int err, rdd_idx = mt7915_get_rdd_idx(phy, false);
 
 	prev_state = phy->mt76->dfs_state;
 	dfs_state = mt76_phy_dfs_state(phy->mt76);
 
-	if (prev_state == dfs_state)
+	if (prev_state == dfs_state || rdd_idx < 0)
 		return 0;
 
 	if (prev_state == MT_DFS_STATE_UNKNOWN)
@@ -2177,8 +2162,7 @@ int mt7915_dfs_init_radar_detector(struct mt7915_phy *phy)
 	if (dfs_state == MT_DFS_STATE_CAC)
 		return 0;
 
-	err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_CAC_END,
-				      phy->mt76->band_idx, MT_RX_SEL0, 0);
+	err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_CAC_END, rdd_idx, 0, 0);
 	if (err < 0) {
 		phy->mt76->dfs_state = MT_DFS_STATE_UNKNOWN;
 		return err;
@@ -2188,15 +2172,13 @@ int mt7915_dfs_init_radar_detector(struct mt7915_phy *phy)
 	return 0;
 
 stop:
-	err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_NORMAL_START,
-				      phy->mt76->band_idx, MT_RX_SEL0, 0);
+	err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_NORMAL_START, rdd_idx, 0, 0);
 	if (err < 0)
 		return err;
 
 	if (is_mt7915(&dev->mt76)) {
 		err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_SET_WF_ANT,
-					      phy->mt76->band_idx, 0,
-					      dev->dbdc_support ? 2 : 0);
+					      rdd_idx, 0, dev->dbdc_support ? 2 : 0);
 		if (err < 0)
 			return err;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 3643c72bb68d..427542777abc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -303,17 +303,35 @@ mt7915_mcu_rx_radar_detected(struct mt7915_dev *dev, struct sk_buff *skb)
 {
 	struct mt76_phy *mphy = &dev->mt76.phy;
 	struct mt7915_mcu_rdd_report *r;
+	u32 sku;
 
 	r = (struct mt7915_mcu_rdd_report *)skb->data;
 
-	if (r->band_idx > MT_RX_SEL2)
+	switch (r->rdd_idx) {
+	case MT_RDD_IDX_BAND0:
+		break;
+	case MT_RDD_IDX_BAND1:
+		sku = mt7915_check_adie(dev, true);
+		/* the main phy is bound to band 1 for this sku */
+		if (is_mt7986(&dev->mt76) &&
+		    (sku == MT7975_ONE_ADIE || sku == MT7976_ONE_ADIE))
+			break;
+		mphy = dev->mt76.phys[MT_BAND1];
+		break;
+	case MT_RDD_IDX_BACKGROUND:
+		if (!dev->rdd2_phy)
+			return;
+		mphy = dev->rdd2_phy->mt76;
+		break;
+	default:
+		dev_err(dev->mt76.dev, "Unknown RDD idx %d\n", r->rdd_idx);
 		return;
+	}
 
-	if ((r->band_idx && !dev->phy.mt76->band_idx) &&
-	    dev->mt76.phys[MT_BAND1])
-		mphy = dev->mt76.phys[MT_BAND1];
+	if (!mphy)
+		return;
 
-	if (r->band_idx == MT_RX_SEL2)
+	if (r->rdd_idx == MT_RDD_IDX_BACKGROUND)
 		cfg80211_background_radar_event(mphy->hw->wiphy,
 						&dev->rdd2_chandef,
 						GFP_ATOMIC);
@@ -2697,11 +2715,14 @@ int mt7915_mcu_rdd_background_enable(struct mt7915_phy *phy,
 				     struct cfg80211_chan_def *chandef)
 {
 	struct mt7915_dev *dev = phy->dev;
-	int err, region;
+	int err, region, rdd_idx;
+
+	rdd_idx = mt7915_get_rdd_idx(phy, true);
+	if (rdd_idx < 0)
+		return -EINVAL;
 
 	if (!chandef) { /* disable offchain */
-		err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_STOP, MT_RX_SEL2,
-					      0, 0);
+		err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_STOP, rdd_idx, 0, 0);
 		if (err)
 			return err;
 
@@ -2727,8 +2748,7 @@ int mt7915_mcu_rdd_background_enable(struct mt7915_phy *phy,
 		break;
 	}
 
-	return mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_START, MT_RX_SEL2,
-				       0, region);
+	return mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_START, rdd_idx, 0, region);
 }
 
 int mt7915_mcu_set_chan_info(struct mt7915_phy *phy, int cmd)
@@ -2859,7 +2879,7 @@ int mt7915_mcu_set_eeprom(struct mt7915_dev *dev)
 				 &req, sizeof(req), true);
 }
 
-int mt7915_mcu_get_eeprom(struct mt7915_dev *dev, u32 offset)
+int mt7915_mcu_get_eeprom(struct mt7915_dev *dev, u32 offset, u8 *read_buf)
 {
 	struct mt7915_mcu_eeprom_info req = {
 		.addr = cpu_to_le32(round_down(offset,
@@ -2867,8 +2887,8 @@ int mt7915_mcu_get_eeprom(struct mt7915_dev *dev, u32 offset)
 	};
 	struct mt7915_mcu_eeprom_info *res;
 	struct sk_buff *skb;
+	u8 *buf = read_buf;
 	int ret;
-	u8 *buf;
 
 	ret = mt76_mcu_send_and_get_msg(&dev->mt76,
 					MCU_EXT_QUERY(EFUSE_ACCESS),
@@ -2877,8 +2897,10 @@ int mt7915_mcu_get_eeprom(struct mt7915_dev *dev, u32 offset)
 		return ret;
 
 	res = (struct mt7915_mcu_eeprom_info *)skb->data;
-	buf = dev->mt76.eeprom.data + le32_to_cpu(res->addr);
+	if (!buf)
+		buf = dev->mt76.eeprom.data + le32_to_cpu(res->addr);
 	memcpy(buf, res->data, MT7915_EEPROM_BLOCK_SIZE);
+
 	dev_kfree_skb(skb);
 
 	return 0;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
index 092ed504a8f2..086ad89ecd91 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
@@ -57,7 +57,7 @@ struct mt7915_mcu_bcc_notify {
 struct mt7915_mcu_rdd_report {
 	struct mt76_connac2_mcu_rxd_hdr rxd;
 
-	u8 band_idx;
+	u8 rdd_idx;
 	u8 long_detected;
 	u8 constant_prf_detected;
 	u8 staggered_prf_detected;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index 876f0692850a..9c4d5cea0c42 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -651,6 +651,9 @@ int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr,
 		wed->wlan.base = devm_ioremap(dev->mt76.dev,
 					      pci_resource_start(pci_dev, 0),
 					      pci_resource_len(pci_dev, 0));
+		if (!wed->wlan.base)
+			return -ENOMEM;
+
 		wed->wlan.phy_base = pci_resource_start(pci_dev, 0);
 		wed->wlan.wpdma_int = pci_resource_start(pci_dev, 0) +
 				      MT_INT_WED_SOURCE_CSR;
@@ -678,6 +681,9 @@ int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr,
 		wed->wlan.bus_type = MTK_WED_BUS_AXI;
 		wed->wlan.base = devm_ioremap(dev->mt76.dev, res->start,
 					      resource_size(res));
+		if (!wed->wlan.base)
+			return -ENOMEM;
+
 		wed->wlan.phy_base = res->start;
 		wed->wlan.wpdma_int = res->start + MT_INT_SOURCE_CSR;
 		wed->wlan.wpdma_mask = res->start + MT_INT_MASK_CSR;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index 533939f2b7ed..2e94347c46d6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -215,8 +215,6 @@ struct mt7915_phy {
 	s16 coverage_class;
 	u8 slottime;
 
-	u8 rdd_state;
-
 	u32 trb_ts;
 
 	u32 rx_ampdu_ts;
@@ -331,10 +329,10 @@ enum {
 	__MT_WFDMA_MAX,
 };
 
-enum {
-	MT_RX_SEL0,
-	MT_RX_SEL1,
-	MT_RX_SEL2, /* monitor chain */
+enum rdd_idx {
+	MT_RDD_IDX_BAND0,	/* RDD idx for band idx 0 (single-band) */
+	MT_RDD_IDX_BAND1,	/* RDD idx for band idx 1 */
+	MT_RDD_IDX_BACKGROUND,	/* RDD idx for background chain */
 };
 
 enum mt7915_rdd_cmd {
@@ -354,6 +352,18 @@ enum mt7915_rdd_cmd {
 	RDD_IRQ_OFF,
 };
 
+static inline int
+mt7915_get_rdd_idx(struct mt7915_phy *phy, bool is_background)
+{
+	if (!phy->mt76->cap.has_5ghz)
+		return -1;
+
+	if (is_background)
+		return MT_RDD_IDX_BACKGROUND;
+
+	return phy->mt76->band_idx;
+}
+
 static inline struct mt7915_phy *
 mt7915_hw_phy(struct ieee80211_hw *hw)
 {
@@ -425,6 +435,7 @@ int mt7915_eeprom_get_target_power(struct mt7915_dev *dev,
 				   struct ieee80211_channel *chan,
 				   u8 chain_idx);
 s8 mt7915_eeprom_get_power_delta(struct mt7915_dev *dev, int band);
+bool mt7915_eeprom_has_background_radar(struct mt7915_dev *dev);
 int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2);
 void mt7915_dma_prefetch(struct mt7915_dev *dev);
 void mt7915_dma_cleanup(struct mt7915_dev *dev);
@@ -473,7 +484,7 @@ int mt7915_mcu_set_fixed_rate_ctrl(struct mt7915_dev *dev,
 				   struct ieee80211_sta *sta,
 				   void *data, u32 field);
 int mt7915_mcu_set_eeprom(struct mt7915_dev *dev);
-int mt7915_mcu_get_eeprom(struct mt7915_dev *dev, u32 offset);
+int mt7915_mcu_get_eeprom(struct mt7915_dev *dev, u32 offset, u8 *read_buf);
 int mt7915_mcu_get_eeprom_free_block(struct mt7915_dev *dev, u8 *block_num);
 int mt7915_mcu_set_mac(struct mt7915_dev *dev, int band, bool enable,
 		       bool hdr_trans);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 826c48a2ee69..1fffa43379b2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -83,6 +83,11 @@ mt7921_init_he_caps(struct mt792x_phy *phy, enum nl80211_band band,
 			he_cap_elem->phy_cap_info[9] |=
 				IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU |
 				IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU;
+
+			if (is_mt7922(phy->mt76->dev)) {
+				he_cap_elem->phy_cap_info[0] |=
+					IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G;
+			}
 			break;
 		case NL80211_IFTYPE_STATION:
 			he_cap_elem->mac_cap_info[1] |=
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/Makefile b/drivers/net/wireless/mediatek/mt76/mt7925/Makefile
index d321e4ed732f..ade5e647c941 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/Makefile
@@ -5,5 +5,6 @@ obj-$(CONFIG_MT7925E) += mt7925e.o
 obj-$(CONFIG_MT7925U) += mt7925u.o
 
 mt7925-common-y := mac.o mcu.o main.o init.o debugfs.o
+mt7925-common-$(CONFIG_NL80211_TESTMODE) += testmode.o
 mt7925e-y := pci.o pci_mac.o pci_mcu.o
 mt7925u-y := usb.o
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/init.c b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
index 63cb08f4d87c..2a83ff59a968 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
@@ -89,7 +89,7 @@ void mt7925_regd_be_ctrl(struct mt792x_dev *dev, u8 *alpha2)
 		}
 
 		/* Check the last one */
-		if (rule->flag && BIT(0))
+		if (rule->flag & BIT(0))
 			break;
 
 		pos += sizeof(*rule);
@@ -322,6 +322,12 @@ static void mt7925_init_work(struct work_struct *work)
 		return;
 	}
 
+	ret = mt7925_mcu_set_thermal_protect(dev);
+	if (ret) {
+		dev_err(dev->mt76.dev, "thermal protection enable failed\n");
+		return;
+	}
+
 	/* we support chip reset now */
 	dev->hw_init_done = true;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 66f327781947..94b0099dcd41 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -334,6 +334,9 @@ int __mt7925_start(struct mt792x_phy *phy)
 	ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
 				     MT792x_WATCHDOG_TIME);
 
+	if (phy->chip_cap & MT792x_CHIP_CAP_WF_RF_PIN_CTRL_EVT_EN)
+		wiphy_rfkill_start_polling(mphy->hw->wiphy);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__mt7925_start);
@@ -1865,6 +1868,10 @@ mt7925_change_chanctx(struct ieee80211_hw *hw,
 			link_conf = mt792x_vif_to_bss_conf(vif, mconf->link_id);
 			mt7925_mcu_set_chctx(mvif->phy->mt76, &mconf->mt76,
 					     link_conf, ctx);
+
+			if (changed & IEEE80211_CHANCTX_CHANGE_PUNCTURING)
+				mt7925_mcu_set_eht_pp(mvif->phy->mt76, &mconf->mt76,
+						      link_conf, ctx);
 		}
 	}
 
@@ -1954,8 +1961,10 @@ static void mt7925_link_info_changed(struct ieee80211_hw *hw,
 	struct mt792x_phy *phy = mt792x_hw_phy(hw);
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 	struct mt792x_bss_conf *mconf;
+	struct ieee80211_bss_conf *link_conf;
 
 	mconf = mt792x_vif_to_link(mvif, info->link_id);
+	link_conf = mt792x_vif_to_bss_conf(vif, mconf->link_id);
 
 	mt792x_mutex_acquire(dev);
 
@@ -1997,6 +2006,10 @@ static void mt7925_link_info_changed(struct ieee80211_hw *hw,
 		mvif->mlo_pm_state = MT792x_MLO_CHANGED_PS;
 	}
 
+	if (changed & IEEE80211_CHANCTX_CHANGE_PUNCTURING)
+		mt7925_mcu_set_eht_pp(mvif->phy->mt76, &mconf->mt76,
+				      link_conf, NULL);
+
 	mt792x_mutex_release(dev);
 }
 
@@ -2195,6 +2208,18 @@ static void mt7925_unassign_vif_chanctx(struct ieee80211_hw *hw,
 	mutex_unlock(&dev->mt76.mutex);
 }
 
+static void mt7925_rfkill_poll(struct ieee80211_hw *hw)
+{
+	struct mt792x_phy *phy = mt792x_hw_phy(hw);
+	int ret;
+
+	mt792x_mutex_acquire(phy->dev);
+	ret = mt7925_mcu_wf_rf_pin_ctrl(phy);
+	mt792x_mutex_release(phy->dev);
+
+	wiphy_rfkill_set_hw_state(hw->wiphy, ret == 0);
+}
+
 const struct ieee80211_ops mt7925_ops = {
 	.tx = mt792x_tx,
 	.start = mt7925_start,
@@ -2234,6 +2259,8 @@ const struct ieee80211_ops mt7925_ops = {
 	.sta_statistics = mt792x_sta_statistics,
 	.sched_scan_start = mt7925_start_sched_scan,
 	.sched_scan_stop = mt7925_stop_sched_scan,
+	CFG80211_TESTMODE_CMD(mt7925_testmode_cmd)
+	CFG80211_TESTMODE_DUMP(mt7925_testmode_dump)
 #ifdef CONFIG_PM
 	.suspend = mt7925_suspend,
 	.resume = mt7925_resume,
@@ -2255,6 +2282,7 @@ const struct ieee80211_ops mt7925_ops = {
 	.link_info_changed = mt7925_link_info_changed,
 	.change_vif_links = mt7925_change_vif_links,
 	.change_sta_links = mt7925_change_sta_links,
+	.rfkill_poll = mt7925_rfkill_poll,
 };
 EXPORT_SYMBOL_GPL(mt7925_ops);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index e61da76b2097..b8542be0d945 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -783,7 +783,7 @@ int mt7925_mcu_fw_log_2_host(struct mt792x_dev *dev, u8 ctrl)
 	int ret;
 
 	ret = mt76_mcu_send_and_get_msg(&dev->mt76, MCU_UNI_CMD(WSYS_CONFIG),
-					&req, sizeof(req), false, NULL);
+					&req, sizeof(req), true, NULL);
 	return ret;
 }
 
@@ -974,6 +974,23 @@ int mt7925_mcu_set_deep_sleep(struct mt792x_dev *dev, bool enable)
 }
 EXPORT_SYMBOL_GPL(mt7925_mcu_set_deep_sleep);
 
+int mt7925_mcu_set_thermal_protect(struct mt792x_dev *dev)
+{
+	char cmd[64];
+	int ret = 0;
+
+	snprintf(cmd, sizeof(cmd), "ThermalProtGband %d %d %d %d %d %d %d %d %d %d",
+		 0, 100, 90, 80, 30, 1, 1, 115, 105, 5);
+	ret = mt7925_mcu_chip_config(dev, cmd);
+
+	snprintf(cmd, sizeof(cmd), "ThermalProtAband %d %d %d %d %d %d %d %d %d %d",
+		 1, 100, 90, 80, 30, 1, 1, 115, 105, 5);
+	ret |= mt7925_mcu_chip_config(dev, cmd);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt7925_mcu_set_thermal_protect);
+
 int mt7925_run_firmware(struct mt792x_dev *dev)
 {
 	int err;
@@ -1424,7 +1441,7 @@ int mt7925_mcu_set_eeprom(struct mt792x_dev *dev)
 	};
 
 	return mt76_mcu_send_and_get_msg(&dev->mt76, MCU_UNI_CMD(EFUSE_CTRL),
-					 &req, sizeof(req), false, NULL);
+					 &req, sizeof(req), true, NULL);
 }
 EXPORT_SYMBOL_GPL(mt7925_mcu_set_eeprom);
 
@@ -1924,14 +1941,14 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy,
 			mt7925_mcu_sta_mld_tlv(skb, info->vif, info->link_sta->sta);
 			mt7925_mcu_sta_eht_mld_tlv(skb, info->vif, info->link_sta->sta);
 		}
-
-		mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->link_sta);
 	}
 
 	if (!info->enable) {
 		mt7925_mcu_sta_remove_tlv(skb);
 		mt76_connac_mcu_add_tlv(skb, STA_REC_MLD_OFF,
 					sizeof(struct tlv));
+	} else {
+		mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->link_sta);
 	}
 
 	return mt76_mcu_skb_send_msg(dev, skb, info->cmd, true);
@@ -2046,8 +2063,6 @@ int mt7925_mcu_set_sniffer(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 		},
 	};
 
-	mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(SNIFFER), &req, sizeof(req), true);
-
 	return mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(SNIFFER), &req, sizeof(req),
 				 true);
 }
@@ -2298,6 +2313,40 @@ __mt7925_mcu_alloc_bss_req(struct mt76_dev *dev, struct mt76_vif_link *mvif, int
 	return skb;
 }
 
+static
+void mt7925_mcu_bss_eht_tlv(struct sk_buff *skb, struct mt76_phy *phy,
+			    struct ieee80211_bss_conf *link_conf,
+			    struct ieee80211_chanctx_conf *ctx)
+{
+	struct cfg80211_chan_def *chandef = ctx ? &ctx->def :
+						  &link_conf->chanreq.oper;
+
+	struct bss_eht_tlv *req;
+	struct tlv *tlv;
+
+	tlv = mt76_connac_mcu_add_tlv(skb, UNI_BSS_INFO_EHT, sizeof(*req));
+	req = (struct bss_eht_tlv *)tlv;
+	req->is_eth_dscb_present = chandef->punctured ? 1 : 0;
+	req->eht_dis_sub_chan_bitmap = cpu_to_le16(chandef->punctured);
+}
+
+int mt7925_mcu_set_eht_pp(struct mt76_phy *phy, struct mt76_vif_link *mvif,
+			  struct ieee80211_bss_conf *link_conf,
+			  struct ieee80211_chanctx_conf *ctx)
+{
+	struct sk_buff *skb;
+
+	skb = __mt7925_mcu_alloc_bss_req(phy->dev, mvif,
+					 MT7925_BSS_UPDATE_MAX_SIZE);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	mt7925_mcu_bss_eht_tlv(skb, phy, link_conf, ctx);
+
+	return mt76_mcu_skb_send_msg(phy->dev, skb,
+				     MCU_UNI_CMD(BSS_INFO_UPDATE), true);
+}
+
 int mt7925_mcu_set_chctx(struct mt76_phy *phy, struct mt76_vif_link *mvif,
 			 struct ieee80211_bss_conf *link_conf,
 			 struct ieee80211_chanctx_conf *ctx)
@@ -2764,7 +2813,7 @@ int mt7925_mcu_set_dbdc(struct mt76_phy *phy, bool enable)
 	conf->band = 0; /* unused */
 
 	err = mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SET_DBDC_PARMS),
-				    false);
+				    true);
 
 	return err;
 }
@@ -2779,7 +2828,6 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 	struct mt76_dev *mdev = phy->dev;
 	struct mt76_connac_mcu_scan_channel *chan;
 	struct sk_buff *skb;
-
 	struct scan_hdr_tlv *hdr;
 	struct scan_req_tlv *req;
 	struct scan_ssid_tlv *ssid;
@@ -2790,9 +2838,12 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 	struct tlv *tlv;
 	int max_len;
 
+	if (test_bit(MT76_HW_SCANNING, &phy->state))
+		return -EBUSY;
+
 	max_len = sizeof(*hdr) + sizeof(*req) + sizeof(*ssid) +
-				sizeof(*bssid) + sizeof(*chan_info) +
-				sizeof(*misc) + sizeof(*ie);
+		  sizeof(*bssid) * MT7925_RNR_SCAN_MAX_BSSIDS +
+		  sizeof(*chan_info) + sizeof(*misc) + sizeof(*ie);
 
 	skb = mt76_mcu_msg_alloc(mdev, NULL, max_len);
 	if (!skb)
@@ -2815,6 +2866,8 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 	for (i = 0; i < sreq->n_ssids; i++) {
 		if (!sreq->ssids[i].ssid_len)
 			continue;
+		if (i > MT7925_RNR_SCAN_MAX_BSSIDS)
+			break;
 
 		ssid->ssids[i].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len);
 		memcpy(ssid->ssids[i].ssid, sreq->ssids[i].ssid,
@@ -2824,10 +2877,31 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 	ssid->ssid_type = n_ssids ? BIT(2) : BIT(0);
 	ssid->ssids_num = n_ssids;
 
-	tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_BSSID, sizeof(*bssid));
-	bssid = (struct scan_bssid_tlv *)tlv;
+	if (sreq->n_6ghz_params) {
+		u8 j;
+
+		mt76_connac_mcu_build_rnr_scan_param(mdev, sreq);
+
+		for (j = 0; j < mdev->rnr.bssid_num; j++) {
+			if (j > MT7925_RNR_SCAN_MAX_BSSIDS)
+				break;
+
+			tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_BSSID,
+						      sizeof(*bssid));
+			bssid = (struct scan_bssid_tlv *)tlv;
 
-	memcpy(bssid->bssid, sreq->bssid, ETH_ALEN);
+			ether_addr_copy(bssid->bssid, mdev->rnr.bssid[j]);
+			bssid->match_ch = mdev->rnr.channel[j];
+			bssid->match_ssid_ind = MT7925_RNR_SCAN_MAX_BSSIDS;
+			bssid->match_short_ssid_ind = MT7925_RNR_SCAN_MAX_BSSIDS;
+		}
+		req->scan_func |= SCAN_FUNC_RNR_SCAN;
+	} else {
+		tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_BSSID, sizeof(*bssid));
+		bssid = (struct scan_bssid_tlv *)tlv;
+
+		ether_addr_copy(bssid->bssid, sreq->bssid);
+	}
 
 	tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_CHANNEL, sizeof(*chan_info));
 	chan_info = (struct scan_chan_info_tlv *)tlv;
@@ -2869,7 +2943,7 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 	}
 
 	err = mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SCAN_REQ),
-				    false);
+				    true);
 	if (err < 0)
 		clear_bit(MT76_HW_SCANNING, &phy->state);
 
@@ -2975,7 +3049,7 @@ int mt7925_mcu_sched_scan_req(struct mt76_phy *phy,
 	}
 
 	return mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SCAN_REQ),
-				     false);
+				     true);
 }
 EXPORT_SYMBOL_GPL(mt7925_mcu_sched_scan_req);
 
@@ -3011,7 +3085,7 @@ mt7925_mcu_sched_scan_enable(struct mt76_phy *phy,
 		clear_bit(MT76_HW_SCHED_SCANNING, &phy->state);
 
 	return mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SCAN_REQ),
-				     false);
+				     true);
 }
 
 int mt7925_mcu_cancel_hw_scan(struct mt76_phy *phy,
@@ -3050,7 +3124,7 @@ int mt7925_mcu_cancel_hw_scan(struct mt76_phy *phy,
 	}
 
 	return mt76_mcu_send_msg(phy->dev, MCU_UNI_CMD(SCAN_REQ),
-				 &req, sizeof(req), false);
+				 &req, sizeof(req), true);
 }
 EXPORT_SYMBOL_GPL(mt7925_mcu_cancel_hw_scan);
 
@@ -3155,7 +3229,7 @@ int mt7925_mcu_set_channel_domain(struct mt76_phy *phy)
 	memcpy(__skb_push(skb, sizeof(req)), &req, sizeof(req));
 
 	return mt76_mcu_skb_send_msg(dev, skb, MCU_UNI_CMD(SET_DOMAIN_INFO),
-				     false);
+				     true);
 }
 EXPORT_SYMBOL_GPL(mt7925_mcu_set_channel_domain);
 
@@ -3305,9 +3379,18 @@ int mt7925_mcu_fill_message(struct mt76_dev *mdev, struct sk_buff *skb,
 		else
 			uni_txd->option = MCU_CMD_UNI_EXT_ACK;
 
-		if (cmd == MCU_UNI_CMD(HIF_CTRL))
+		if (cmd == MCU_UNI_CMD(HIF_CTRL) ||
+		    cmd == MCU_UNI_CMD(CHIP_CONFIG))
 			uni_txd->option &= ~MCU_CMD_ACK;
 
+		if (mcu_cmd == MCU_UNI_CMD_TESTMODE_CTRL ||
+		    mcu_cmd == MCU_UNI_CMD_TESTMODE_RX_STAT) {
+			if (cmd & __MCU_CMD_FIELD_QUERY)
+				uni_txd->option = 0x2;
+			else
+				uni_txd->option = 0x6;
+		}
+
 		goto exit;
 	}
 
@@ -3599,6 +3682,43 @@ int mt7925_mcu_set_rate_txpower(struct mt76_phy *phy)
 	return 0;
 }
 
+int mt7925_mcu_wf_rf_pin_ctrl(struct mt792x_phy *phy)
+{
+#define UNI_CMD_RADIO_STATUS_GET	0
+	struct mt792x_dev *dev = phy->dev;
+	struct sk_buff *skb;
+	int ret;
+	struct {
+		__le16 tag;
+		__le16 len;
+		u8 rsv[4];
+	} __packed req = {
+		.tag = UNI_CMD_RADIO_STATUS_GET,
+		.len = cpu_to_le16(sizeof(req)),
+	};
+	struct mt7925_radio_status_event {
+		__le16 tag;
+		__le16 len;
+
+		u8 data;
+		u8 rsv[3];
+	} __packed *status;
+
+	ret = mt76_mcu_send_and_get_msg(&dev->mt76,
+					MCU_UNI_CMD(RADIO_STATUS),
+					&req, sizeof(req), true, &skb);
+	if (ret)
+		return ret;
+
+	skb_pull(skb, sizeof(struct tlv));
+	status = (struct mt7925_radio_status_event *)skb->data;
+	ret = status->data;
+
+	dev_kfree_skb(skb);
+
+	return ret;
+}
+
 int mt7925_mcu_set_rxfilter(struct mt792x_dev *dev, u32 fif,
 			    u8 bit_op, u32 bit_map)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
index 8ac43feb26d6..ee6fb16e83c5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
@@ -104,13 +104,6 @@ enum {
 	MT7925_TM_WIFISPECTRUM,
 };
 
-struct mt7925_rftest_cmd {
-	u8 action;
-	u8 rsv[3];
-	__le32 param0;
-	__le32 param1;
-} __packed;
-
 struct mt7925_rftest_evt {
 	__le32 param0;
 	__le32 param1;
@@ -196,6 +189,7 @@ enum {
 	UNI_SNIFFER_CONFIG,
 };
 
+#define MT7925_RNR_SCAN_MAX_BSSIDS	10
 struct scan_hdr_tlv {
 	/* fixed field */
 	u8 seq_num;
@@ -223,7 +217,7 @@ struct scan_req_tlv {
 	__le16 timeout_value;
 	__le16 probe_delay_time;
 	__le32 func_mask_ext;
-};
+} __packed;
 
 struct scan_ssid_tlv {
 	__le16 tag;
@@ -235,9 +229,10 @@ struct scan_ssid_tlv {
 		       * BIT(2) + ssid_type_ext BIT(0) specified SSID only
 		       */
 	u8 ssids_num;
-	u8 pad[2];
-	struct mt76_connac_mcu_scan_ssid ssids[4];
-};
+	u8 is_short_ssid;
+	u8 pad;
+	struct mt76_connac_mcu_scan_ssid ssids[MT7925_RNR_SCAN_MAX_BSSIDS];
+} __packed;
 
 struct scan_bssid_tlv {
 	__le16 tag;
@@ -247,8 +242,9 @@ struct scan_bssid_tlv {
 	u8 match_ch;
 	u8 match_ssid_ind;
 	u8 rcpi;
-	u8 pad[3];
-};
+	u8 match_short_ssid_ind;
+	u8 pad[2];
+} __packed;
 
 struct scan_chan_info_tlv {
 	__le16 tag;
@@ -264,7 +260,7 @@ struct scan_chan_info_tlv {
 	u8 channels_num; /* valid when channel_type is 4 */
 	u8 pad[2];
 	struct mt76_connac_mcu_scan_channel channels[64];
-};
+} __packed;
 
 struct scan_ie_tlv {
 	__le16 tag;
@@ -372,6 +368,19 @@ struct bss_mld_tlv {
 	u8 __rsv[3];
 } __packed;
 
+struct bss_eht_tlv {
+	__le16 tag;
+	__le16 len;
+	u8  is_eht_op_present;
+	u8  is_eth_dscb_present;
+	u8  eht_ctrl;
+	u8  eht_ccfs0;
+	u8  eht_ccfs1;
+	u8  pad1;
+	__le16 eht_dis_sub_chan_bitmap;
+	u8  pad2[4];
+} __packed;
+
 struct sta_rec_ba_uni {
 	__le16 tag;
 	__le16 len;
@@ -589,6 +598,47 @@ struct roc_acquire_tlv {
 	u8 rsv[3];
 } __packed;
 
+enum ENUM_CMD_TEST_CTRL_ACT {
+	CMD_TEST_CTRL_ACT_SWITCH_MODE = 0,
+	CMD_TEST_CTRL_ACT_SET_AT = 1,
+	CMD_TEST_CTRL_ACT_GET_AT = 2,
+	CMD_TEST_CTRL_ACT_SET_AT_ENG = 3,
+	CMD_TEST_CTRL_ACT_GET_AT_ENG = 4,
+	CMD_TEST_CTRL_ACT_NUM
+};
+
+enum ENUM_CMD_TEST_CTRL_ACT_SWITCH_MODE_OP {
+	CMD_TEST_CTRL_ACT_SWITCH_MODE_NORMAL = 0,
+	CMD_TEST_CTRL_ACT_SWITCH_MODE_RF_TEST = 1,
+	CMD_TEST_CTRL_ACT_SWITCH_MODE_ICAP = 2,
+	CMD_TEST_CTRL_ACT_SWITCH_MODE_NUM
+};
+
+union testmode_data {
+	__le32 op_mode;
+	__le32 channel_freq;
+	u8 rf_at_info[84];
+};
+
+union testmode_evt {
+	__le32 op_mode;
+	__le32 channel_freq;
+	u8 rf_at_info[1024];
+};
+
+struct uni_cmd_testmode_ctrl {
+	u16 tag;
+	u16 length;
+	u8 action;
+	u8 reserved[3];
+	union testmode_data data;
+} __packed;
+
+struct mt7925_rftest_cmd {
+	u8 padding[4];
+	struct uni_cmd_testmode_ctrl ctrl;
+} __packed;
+
 static inline enum connac3_mcu_cipher_type
 mt7925_mcu_get_cipher(int cipher)
 {
@@ -637,11 +687,15 @@ int mt7925_mcu_add_bss_info(struct mt792x_phy *phy,
 int mt7925_mcu_set_timing(struct mt792x_phy *phy,
 			  struct ieee80211_bss_conf *link_conf);
 int mt7925_mcu_set_deep_sleep(struct mt792x_dev *dev, bool enable);
+int mt7925_mcu_set_thermal_protect(struct mt792x_dev *dev);
 int mt7925_mcu_set_channel_domain(struct mt76_phy *phy);
 int mt7925_mcu_set_radio_en(struct mt792x_phy *phy, bool enable);
 int mt7925_mcu_set_chctx(struct mt76_phy *phy, struct mt76_vif_link *mvif,
 			 struct ieee80211_bss_conf *link_conf,
 			 struct ieee80211_chanctx_conf *ctx);
+int mt7925_mcu_set_eht_pp(struct mt76_phy *phy, struct mt76_vif_link *mvif,
+			  struct ieee80211_bss_conf *link_conf,
+			  struct ieee80211_chanctx_conf *ctx);
 int mt7925_mcu_set_rate_txpower(struct mt76_phy *phy);
 int mt7925_mcu_update_arp_filter(struct mt76_dev *dev,
 				 struct ieee80211_bss_conf *link_conf);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
index 4e50f2597ccd..1b165d0d8bd3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
@@ -365,5 +365,11 @@ int mt7925_mcu_wtbl_update_hdr_trans(struct mt792x_dev *dev,
 				     struct ieee80211_vif *vif,
 				     struct ieee80211_sta *sta,
 				     int link_id);
+int mt7925_mcu_wf_rf_pin_ctrl(struct mt792x_phy *phy);
+
+int mt7925_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			void *data, int len);
+int mt7925_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *msg,
+			 struct netlink_callback *cb, void *data, int len);
 
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
index c7b5dc1dbb34..89dc30f7c6b7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
@@ -31,6 +31,10 @@ static void mt7925e_unregister_device(struct mt792x_dev *dev)
 {
 	int i;
 	struct mt76_connac_pm *pm = &dev->pm;
+	struct ieee80211_hw *hw = mt76_hw(dev);
+
+	if (dev->phy.chip_cap & MT792x_CHIP_CAP_WF_RF_PIN_CTRL_EVT_EN)
+		wiphy_rfkill_stop_polling(hw->wiphy);
 
 	cancel_work_sync(&dev->init_work);
 	mt76_unregister_device(&dev->mt76);
@@ -490,9 +494,6 @@ static int mt7925_pci_suspend(struct device *device)
 
 	/* disable interrupt */
 	mt76_wr(dev, dev->irq_map->host_irq_enable, 0);
-	mt76_wr(dev, MT_WFDMA0_HOST_INT_DIS,
-		dev->irq_map->tx.all_complete_mask |
-		MT_INT_RX_DONE_ALL | MT_INT_MCU_CMD);
 
 	mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0x0);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/regs.h b/drivers/net/wireless/mediatek/mt76/mt7925/regs.h
index 985794a40c1a..547489092c29 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/regs.h
@@ -28,7 +28,7 @@
 #define MT_MDP_TO_HIF			0
 #define MT_MDP_TO_WM			1
 
-#define MT_WFDMA0_HOST_INT_ENA		MT_WFDMA0(0x228)
+#define MT_WFDMA0_HOST_INT_ENA		MT_WFDMA0(0x204)
 #define MT_WFDMA0_HOST_INT_DIS		MT_WFDMA0(0x22c)
 #define HOST_RX_DONE_INT_ENA4		BIT(12)
 #define HOST_RX_DONE_INT_ENA5		BIT(13)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/testmode.c b/drivers/net/wireless/mediatek/mt76/mt7925/testmode.c
new file mode 100644
index 000000000000..a3c97164ba21
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/testmode.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: ISC
+
+#include "mt7925.h"
+#include "mcu.h"
+
+#define MT7925_EVT_RSP_LEN 512
+
+enum mt7925_testmode_attr {
+	MT7925_TM_ATTR_UNSPEC,
+	MT7925_TM_ATTR_SET,
+	MT7925_TM_ATTR_QUERY,
+	MT7925_TM_ATTR_RSP,
+
+	/* keep last */
+	NUM_MT7925_TM_ATTRS,
+	MT7925_TM_ATTR_MAX = NUM_MT7925_TM_ATTRS - 1,
+};
+
+struct mt7925_tm_cmd {
+	u8 padding[4];
+	struct uni_cmd_testmode_ctrl c;
+} __packed;
+
+struct mt7925_tm_evt {
+	u32 param0;
+	u32 param1;
+} __packed;
+
+static const struct nla_policy mt7925_tm_policy[NUM_MT7925_TM_ATTRS] = {
+	[MT7925_TM_ATTR_SET] = NLA_POLICY_EXACT_LEN(sizeof(struct mt7925_tm_cmd)),
+	[MT7925_TM_ATTR_QUERY] = NLA_POLICY_EXACT_LEN(sizeof(struct mt7925_tm_cmd)),
+};
+
+static int
+mt7925_tm_set(struct mt792x_dev *dev, struct mt7925_tm_cmd *req)
+{
+	struct mt7925_rftest_cmd cmd;
+	struct mt7925_rftest_cmd *pcmd = &cmd;
+	bool testmode = false, normal = false;
+	struct mt76_connac_pm *pm = &dev->pm;
+	struct mt76_phy *phy = &dev->mphy;
+	int ret = -ENOTCONN;
+
+	memset(pcmd, 0, sizeof(*pcmd));
+	memcpy(pcmd, req, sizeof(struct mt7925_tm_cmd));
+
+	mutex_lock(&dev->mt76.mutex);
+
+	if (pcmd->ctrl.action == CMD_TEST_CTRL_ACT_SWITCH_MODE) {
+		if (pcmd->ctrl.data.op_mode == CMD_TEST_CTRL_ACT_SWITCH_MODE_NORMAL)
+			normal = true;
+		else
+			testmode = true;
+	}
+
+	if (testmode) {
+		/* Make sure testmode running on full power mode */
+		pm->enable = false;
+		cancel_delayed_work_sync(&pm->ps_work);
+		cancel_work_sync(&pm->wake_work);
+		__mt792x_mcu_drv_pmctrl(dev);
+
+		phy->test.state = MT76_TM_STATE_ON;
+	}
+
+	if (!mt76_testmode_enabled(phy))
+		goto out;
+
+	ret = mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(TESTMODE_CTRL), &cmd,
+				sizeof(cmd), false);
+
+	if (ret)
+		goto out;
+
+	if (normal) {
+		/* Switch back to the normal world */
+		phy->test.state = MT76_TM_STATE_OFF;
+		pm->enable = true;
+	}
+out:
+	mutex_unlock(&dev->mt76.mutex);
+
+	return ret;
+}
+
+static int
+mt7925_tm_query(struct mt792x_dev *dev, struct mt7925_tm_cmd *req,
+		char *evt_resp)
+{
+	struct mt7925_rftest_cmd cmd;
+	char *pcmd = (char *)&cmd;
+	struct sk_buff *skb = NULL;
+	int ret = 1;
+
+	memset(pcmd, 0, sizeof(*pcmd));
+	memcpy(pcmd + 4, (char *)&req->c, sizeof(struct uni_cmd_testmode_ctrl));
+
+	if (*((uint16_t *)req->padding) == MCU_UNI_CMD_TESTMODE_CTRL)
+		ret = mt76_mcu_send_and_get_msg(&dev->mt76, MCU_UNI_QUERY(TESTMODE_CTRL),
+						&cmd, sizeof(cmd), true, &skb);
+	else if (*((uint16_t *)req->padding) == MCU_UNI_CMD_TESTMODE_RX_STAT)
+		ret = mt76_mcu_send_and_get_msg(&dev->mt76, MCU_UNI_QUERY(TESTMODE_RX_STAT),
+						&cmd, sizeof(cmd), true, &skb);
+
+	if (ret)
+		goto out;
+
+	memcpy((char *)evt_resp, (char *)skb->data + 8, MT7925_EVT_RSP_LEN);
+
+out:
+	dev_kfree_skb(skb);
+
+	return ret;
+}
+
+int mt7925_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			void *data, int len)
+{
+	struct nlattr *tb[NUM_MT76_TM_ATTRS];
+	struct mt76_phy *mphy = hw->priv;
+	struct mt792x_phy *phy = mphy->priv;
+	int err;
+
+	if (!test_bit(MT76_STATE_RUNNING, &mphy->state) ||
+	    !(hw->conf.flags & IEEE80211_CONF_MONITOR))
+		return -ENOTCONN;
+
+	err = nla_parse_deprecated(tb, MT76_TM_ATTR_MAX, data, len,
+				   mt76_tm_policy, NULL);
+	if (err)
+		return err;
+
+	if (tb[MT76_TM_ATTR_DRV_DATA]) {
+		struct nlattr *drv_tb[NUM_MT7925_TM_ATTRS], *data;
+		int ret;
+
+		data = tb[MT76_TM_ATTR_DRV_DATA];
+		ret = nla_parse_nested_deprecated(drv_tb,
+						  MT7925_TM_ATTR_MAX,
+						  data, mt7925_tm_policy,
+						  NULL);
+		if (ret)
+			return ret;
+
+		data = drv_tb[MT7925_TM_ATTR_SET];
+		if (data)
+			return mt7925_tm_set(phy->dev, nla_data(data));
+	}
+
+	return -EINVAL;
+}
+
+int mt7925_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *msg,
+			 struct netlink_callback *cb, void *data, int len)
+{
+	struct nlattr *tb[NUM_MT76_TM_ATTRS];
+	struct mt76_phy *mphy = hw->priv;
+	struct mt792x_phy *phy = mphy->priv;
+	int err;
+
+	if (!test_bit(MT76_STATE_RUNNING, &mphy->state) ||
+	    !(hw->conf.flags & IEEE80211_CONF_MONITOR) ||
+	    !mt76_testmode_enabled(mphy))
+		return -ENOTCONN;
+
+	if (cb->args[2]++ > 0)
+		return -ENOENT;
+
+	err = nla_parse_deprecated(tb, MT76_TM_ATTR_MAX, data, len,
+				   mt76_tm_policy, NULL);
+	if (err)
+		return err;
+
+	if (tb[MT76_TM_ATTR_DRV_DATA]) {
+		struct nlattr *drv_tb[NUM_MT7925_TM_ATTRS], *data;
+		int ret;
+
+		data = tb[MT76_TM_ATTR_DRV_DATA];
+		ret = nla_parse_nested_deprecated(drv_tb,
+						  MT7925_TM_ATTR_MAX,
+						  data, mt7925_tm_policy,
+						  NULL);
+		if (ret)
+			return ret;
+
+		data = drv_tb[MT7925_TM_ATTR_QUERY];
+		if (data) {
+			char evt_resp[MT7925_EVT_RSP_LEN];
+
+			err = mt7925_tm_query(phy->dev, nla_data(data),
+					      evt_resp);
+			if (err)
+				return err;
+
+			return nla_put(msg, MT7925_TM_ATTR_RSP,
+				       sizeof(evt_resp), evt_resp);
+		}
+	}
+
+	return -EINVAL;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/coredump.c b/drivers/net/wireless/mediatek/mt76/mt7996/coredump.c
index ccab0d7b9be4..303d6e80a666 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/coredump.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/coredump.c
@@ -48,8 +48,8 @@ const struct mt7996_mem_region*
 mt7996_coredump_get_mem_layout(struct mt7996_dev *dev, u32 *num)
 {
 	switch (mt76_chip(&dev->mt76)) {
-	case 0x7990:
-	case 0x7991:
+	case MT7996_DEVICE_ID:
+	case MT7996_DEVICE_ID_2:
 		*num = ARRAY_SIZE(mt7996_mem_regions);
 		return &mt7996_mem_regions[0];
 	default:
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
index 4a28db17a287..0ab827f52fd7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
@@ -222,18 +222,27 @@ static const struct file_operations mt7996_sys_recovery_ops = {
 static int
 mt7996_radar_trigger(void *data, u64 val)
 {
+#define RADAR_MAIN_CHAIN	1
+#define RADAR_BACKGROUND	2
 	struct mt7996_dev *dev = data;
+	struct mt7996_phy *phy = mt7996_band_phy(dev, NL80211_BAND_5GHZ);
+	int rdd_idx;
 
-	if (val > MT_RX_SEL2)
+	if (!phy || !val || val > RADAR_BACKGROUND)
 		return -EINVAL;
 
-	if (val == MT_RX_SEL2 && !dev->rdd2_phy) {
+	if (val == RADAR_BACKGROUND && !dev->rdd2_phy) {
 		dev_err(dev->mt76.dev, "Background radar is not enabled\n");
 		return -EINVAL;
 	}
 
-	return mt7996_mcu_rdd_cmd(dev, RDD_RADAR_EMULATE,
-				  val, 0, 0);
+	rdd_idx = mt7996_get_rdd_idx(phy, val == RADAR_BACKGROUND);
+	if (rdd_idx < 0) {
+		dev_err(dev->mt76.dev, "No RDD found\n");
+		return -EINVAL;
+	}
+
+	return mt7996_mcu_rdd_cmd(dev, RDD_RADAR_EMULATE, rdd_idx, 0);
 }
 
 DEFINE_DEBUGFS_ATTRIBUTE(fops_radar_trigger, NULL,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
index 69a7d9b2e38b..c8bef0b2a144 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
@@ -55,20 +55,32 @@ static void mt7996_dma_config(struct mt7996_dev *dev)
 
 	/* rx queue */
 	RXQ_CONFIG(MT_RXQ_MCU, WFDMA0, MT_INT_RX_DONE_WM, MT7996_RXQ_MCU_WM);
+	/* for mt7990, RX ring 1 is for SDO instead */
 	RXQ_CONFIG(MT_RXQ_MCU_WA, WFDMA0, MT_INT_RX_DONE_WA, MT7996_RXQ_MCU_WA);
-
-	/* mt7996: band0 and band1, mt7992: band0 */
 	RXQ_CONFIG(MT_RXQ_MAIN, WFDMA0, MT_INT_RX_DONE_BAND0, MT7996_RXQ_BAND0);
-	RXQ_CONFIG(MT_RXQ_MAIN_WA, WFDMA0, MT_INT_RX_DONE_WA_MAIN, MT7996_RXQ_MCU_WA_MAIN);
+	if (mt7996_has_wa(dev))
+		RXQ_CONFIG(MT_RXQ_MAIN_WA, WFDMA0, MT_INT_RX_DONE_WA_MAIN,
+			   MT7996_RXQ_MCU_WA_MAIN);
 
-	if (is_mt7996(&dev->mt76)) {
+	switch (mt76_chip(&dev->mt76)) {
+	case MT7992_DEVICE_ID:
+		RXQ_CONFIG(MT_RXQ_BAND1_WA, WFDMA0, MT_INT_RX_DONE_WA_EXT, MT7996_RXQ_MCU_WA_EXT);
+		RXQ_CONFIG(MT_RXQ_BAND1, WFDMA0, MT_INT_RX_DONE_BAND1, MT7996_RXQ_BAND1);
+		break;
+	case MT7990_DEVICE_ID:
+		RXQ_CONFIG(MT_RXQ_BAND1, WFDMA0, MT_INT_RX_DONE_BAND1, MT7996_RXQ_BAND1);
+		RXQ_CONFIG(MT_RXQ_TXFREE_BAND0, WFDMA0,
+			   MT_INT_RX_TXFREE_BAND0_MT7990, MT7990_RXQ_TXFREE0);
+		if (dev->hif2)
+			RXQ_CONFIG(MT_RXQ_TXFREE_BAND1, WFDMA0,
+				   MT_INT_RX_TXFREE_BAND1_MT7990, MT7990_RXQ_TXFREE1);
+		break;
+	case MT7996_DEVICE_ID:
+	default:
 		/* mt7996 band2 */
-		RXQ_CONFIG(MT_RXQ_BAND2, WFDMA0, MT_INT_RX_DONE_BAND2, MT7996_RXQ_BAND2);
 		RXQ_CONFIG(MT_RXQ_BAND2_WA, WFDMA0, MT_INT_RX_DONE_WA_TRI, MT7996_RXQ_MCU_WA_TRI);
-	} else {
-		/* mt7992 band1 */
-		RXQ_CONFIG(MT_RXQ_BAND1, WFDMA0, MT_INT_RX_DONE_BAND1, MT7996_RXQ_BAND1);
-		RXQ_CONFIG(MT_RXQ_BAND1_WA, WFDMA0, MT_INT_RX_DONE_WA_EXT, MT7996_RXQ_MCU_WA_EXT);
+		RXQ_CONFIG(MT_RXQ_BAND2, WFDMA0, MT_INT_RX_DONE_BAND2, MT7996_RXQ_BAND2);
+		break;
 	}
 
 	if (dev->has_rro) {
@@ -104,9 +116,11 @@ static void mt7996_dma_config(struct mt7996_dev *dev)
 	}
 
 	/* mcu tx queue */
-	MCUQ_CONFIG(MT_MCUQ_WM, WFDMA0, MT_INT_TX_DONE_MCU_WM, MT7996_TXQ_MCU_WM);
-	MCUQ_CONFIG(MT_MCUQ_WA, WFDMA0, MT_INT_TX_DONE_MCU_WA, MT7996_TXQ_MCU_WA);
 	MCUQ_CONFIG(MT_MCUQ_FWDL, WFDMA0, MT_INT_TX_DONE_FWDL, MT7996_TXQ_FWDL);
+	MCUQ_CONFIG(MT_MCUQ_WM, WFDMA0, MT_INT_TX_DONE_MCU_WM, MT7996_TXQ_MCU_WM);
+	if (mt7996_has_wa(dev))
+		MCUQ_CONFIG(MT_MCUQ_WA, WFDMA0, MT_INT_TX_DONE_MCU_WA,
+			    MT7996_TXQ_MCU_WA);
 }
 
 static u32 __mt7996_dma_prefetch_base(u16 *base, u8 depth)
@@ -121,43 +135,62 @@ static u32 __mt7996_dma_prefetch_base(u16 *base, u8 depth)
 static void __mt7996_dma_prefetch(struct mt7996_dev *dev, u32 ofs)
 {
 	u16 base = 0;
-	u8 queue;
+	u8 queue, val;
 
 #define PREFETCH(_depth)	(__mt7996_dma_prefetch_base(&base, (_depth)))
 	/* prefetch SRAM wrapping boundary for tx/rx ring. */
-	mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_FWDL) + ofs, PREFETCH(0x2));
-	mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_WM) + ofs, PREFETCH(0x2));
+	/* Tx Command Rings */
+	val = is_mt7996(&dev->mt76) ? 2 : 4;
+	mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_FWDL) + ofs, PREFETCH(val));
+	mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_WM) + ofs, PREFETCH(val));
+	if (mt7996_has_wa(dev))
+		mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_WA) + ofs, PREFETCH(val));
+
+	/* Tx Data Rings */
 	mt76_wr(dev, MT_TXQ_EXT_CTRL(0) + ofs, PREFETCH(0x8));
-	mt76_wr(dev, MT_TXQ_EXT_CTRL(1) + ofs, PREFETCH(0x8));
-	mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_WA) + ofs, PREFETCH(0x2));
-	mt76_wr(dev, MT_TXQ_EXT_CTRL(2) + ofs, PREFETCH(0x8));
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MCU) + ofs, PREFETCH(0x2));
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MCU_WA) + ofs, PREFETCH(0x2));
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MAIN_WA) + ofs, PREFETCH(0x2));
-
-	queue = is_mt7996(&dev->mt76) ? MT_RXQ_BAND2_WA : MT_RXQ_BAND1_WA;
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(queue) + ofs, PREFETCH(0x2));
-
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MAIN) + ofs, PREFETCH(0x10));
+	if (!is_mt7996(&dev->mt76) || dev->hif2)
+		mt76_wr(dev, MT_TXQ_EXT_CTRL(1) + ofs, PREFETCH(0x8));
+	if (is_mt7996(&dev->mt76))
+		mt76_wr(dev, MT_TXQ_EXT_CTRL(2) + ofs, PREFETCH(0x8));
+
+	/* Rx Event Rings */
+	mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_MCU) + ofs, PREFETCH(val));
+	mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_MCU_WA) + ofs, PREFETCH(val));
+
+	/* Rx TxFreeDone From WA Rings */
+	if (mt7996_has_wa(dev)) {
+		mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_MAIN_WA) + ofs, PREFETCH(val));
+		queue = is_mt7996(&dev->mt76) ? MT_RXQ_BAND2_WA : MT_RXQ_BAND1_WA;
+		mt76_wr(dev, MT_RXQ_EXT_CTRL(queue) + ofs, PREFETCH(val));
+	}
 
+	/* Rx TxFreeDone From MAC Rings */
+	val = is_mt7996(&dev->mt76) ? 4 : 8;
+	if (is_mt7990(&dev->mt76) || (is_mt7996(&dev->mt76) && dev->has_rro))
+		mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_TXFREE_BAND0) + ofs, PREFETCH(val));
+	if (is_mt7990(&dev->mt76) && dev->hif2)
+		mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_TXFREE_BAND1) + ofs, PREFETCH(val));
+	else if (is_mt7996(&dev->mt76) && dev->has_rro)
+		mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_TXFREE_BAND2) + ofs, PREFETCH(val));
+
+	/* Rx Data Rings */
+	mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_MAIN) + ofs, PREFETCH(0x10));
 	queue = is_mt7996(&dev->mt76) ? MT_RXQ_BAND2 : MT_RXQ_BAND1;
-	mt76_wr(dev, MT_RXQ_BAND1_CTRL(queue) + ofs, PREFETCH(0x10));
+	mt76_wr(dev, MT_RXQ_EXT_CTRL(queue) + ofs, PREFETCH(0x10));
 
+	/* Rx RRO Rings */
 	if (dev->has_rro) {
-		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_RRO_BAND0) + ofs,
-			PREFETCH(0x10));
-		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_RRO_BAND2) + ofs,
-			PREFETCH(0x10));
-		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MSDU_PAGE_BAND0) + ofs,
-			PREFETCH(0x4));
-		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MSDU_PAGE_BAND1) + ofs,
-			PREFETCH(0x4));
-		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_MSDU_PAGE_BAND2) + ofs,
-			PREFETCH(0x4));
-		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_TXFREE_BAND0) + ofs,
-			PREFETCH(0x4));
-		mt76_wr(dev, MT_RXQ_BAND1_CTRL(MT_RXQ_TXFREE_BAND2) + ofs,
-			PREFETCH(0x4));
+		mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_RRO_BAND0) + ofs, PREFETCH(0x10));
+		queue = is_mt7996(&dev->mt76) ? MT_RXQ_RRO_BAND2 : MT_RXQ_RRO_BAND1;
+		mt76_wr(dev, MT_RXQ_EXT_CTRL(queue) + ofs, PREFETCH(0x10));
+
+		mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_MSDU_PAGE_BAND0) + ofs, PREFETCH(val));
+		if (is_mt7996(&dev->mt76)) {
+			mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_MSDU_PAGE_BAND1) + ofs,
+				PREFETCH(val));
+			mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_MSDU_PAGE_BAND2) + ofs,
+				PREFETCH(val));
+		}
 	}
 #undef PREFETCH
 
@@ -269,6 +302,9 @@ void mt7996_dma_start(struct mt7996_dev *dev, bool reset, bool wed_reset)
 		mtk_wed_device_start(wed, wed_irq_mask);
 	}
 
+	if (!mt7996_has_wa(dev))
+		irq_mask &= ~(MT_INT_RX(MT_RXQ_MAIN_WA) |
+			      MT_INT_RX(MT_RXQ_BAND1_WA));
 	irq_mask = reset ? MT_INT_MCU_CMD : irq_mask;
 
 	mt7996_irq_enable(dev, irq_mask);
@@ -474,12 +510,14 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 		return ret;
 
 	/* command to WA */
-	ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_WA,
-				  MT_MCUQ_ID(MT_MCUQ_WA),
-				  MT7996_TX_MCU_RING_SIZE,
-				  MT_MCUQ_RING_BASE(MT_MCUQ_WA));
-	if (ret)
-		return ret;
+	if (mt7996_has_wa(dev)) {
+		ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_WA,
+					  MT_MCUQ_ID(MT_MCUQ_WA),
+					  MT7996_TX_MCU_RING_SIZE,
+					  MT_MCUQ_RING_BASE(MT_MCUQ_WA));
+		if (ret)
+			return ret;
+	}
 
 	/* firmware download */
 	ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_FWDL,
@@ -493,16 +531,16 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU],
 			       MT_RXQ_ID(MT_RXQ_MCU),
 			       MT7996_RX_MCU_RING_SIZE,
-			       MT_RX_BUF_SIZE,
+			       MT7996_RX_MCU_BUF_SIZE,
 			       MT_RXQ_RING_BASE(MT_RXQ_MCU));
 	if (ret)
 		return ret;
 
-	/* event from WA */
+	/* event from WA, or SDO event for mt7990 */
 	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU_WA],
 			       MT_RXQ_ID(MT_RXQ_MCU_WA),
 			       MT7996_RX_MCU_RING_SIZE_WA,
-			       MT_RX_BUF_SIZE,
+			       MT7996_RX_MCU_BUF_SIZE,
 			       MT_RXQ_RING_BASE(MT_RXQ_MCU_WA));
 	if (ret)
 		return ret;
@@ -527,13 +565,41 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 		dev->mt76.q_rx[MT_RXQ_MAIN_WA].wed = wed;
 	}
 
-	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN_WA],
-			       MT_RXQ_ID(MT_RXQ_MAIN_WA),
-			       MT7996_RX_MCU_RING_SIZE,
-			       MT_RX_BUF_SIZE,
-			       MT_RXQ_RING_BASE(MT_RXQ_MAIN_WA));
-	if (ret)
-		return ret;
+	if (mt7996_has_wa(dev)) {
+		ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN_WA],
+				       MT_RXQ_ID(MT_RXQ_MAIN_WA),
+				       MT7996_RX_MCU_RING_SIZE,
+				       MT_RX_BUF_SIZE,
+				       MT_RXQ_RING_BASE(MT_RXQ_MAIN_WA));
+		if (ret)
+			return ret;
+	} else {
+		if (mtk_wed_device_active(wed)) {
+			dev->mt76.q_rx[MT_RXQ_TXFREE_BAND0].flags = MT_WED_Q_TXFREE;
+			dev->mt76.q_rx[MT_RXQ_TXFREE_BAND0].wed = wed;
+		}
+		ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_TXFREE_BAND0],
+				       MT_RXQ_ID(MT_RXQ_TXFREE_BAND0),
+				       MT7996_RX_MCU_RING_SIZE,
+				       MT7996_RX_BUF_SIZE,
+				       MT_RXQ_RING_BASE(MT_RXQ_TXFREE_BAND0));
+		if (ret)
+			return ret;
+	}
+
+	if (!mt7996_has_wa(dev) && dev->hif2) {
+		if (mtk_wed_device_active(wed)) {
+			dev->mt76.q_rx[MT_RXQ_TXFREE_BAND1].flags = MT_WED_Q_TXFREE;
+			dev->mt76.q_rx[MT_RXQ_TXFREE_BAND1].wed = wed;
+		}
+		ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_TXFREE_BAND1],
+				       MT_RXQ_ID(MT_RXQ_TXFREE_BAND1),
+				       MT7996_RX_MCU_RING_SIZE,
+				       MT7996_RX_BUF_SIZE,
+				       MT_RXQ_RING_BASE(MT_RXQ_TXFREE_BAND1));
+		if (ret)
+			return ret;
+	}
 
 	if (mt7996_band_valid(dev, MT_BAND2)) {
 		/* rx data queue for mt7996 band2 */
@@ -573,14 +639,16 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 			return ret;
 
 		/* tx free notify event from WA for mt7992 band1 */
-		rx_base = MT_RXQ_RING_BASE(MT_RXQ_BAND1_WA) + hif1_ofs;
-		ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_BAND1_WA],
-				       MT_RXQ_ID(MT_RXQ_BAND1_WA),
-				       MT7996_RX_MCU_RING_SIZE,
-				       MT_RX_BUF_SIZE,
-				       rx_base);
-		if (ret)
-			return ret;
+		if (mt7996_has_wa(dev)) {
+			rx_base = MT_RXQ_RING_BASE(MT_RXQ_BAND1_WA) + hif1_ofs;
+			ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_BAND1_WA],
+					       MT_RXQ_ID(MT_RXQ_BAND1_WA),
+					       MT7996_RX_MCU_RING_SIZE,
+					       MT_RX_BUF_SIZE,
+					       rx_base);
+			if (ret)
+				return ret;
+		}
 	}
 
 	if (mtk_wed_device_active(wed) && mtk_wed_get_rx_capa(wed) &&
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c
index 53dfac02f8af..87c6192b6384 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c
@@ -13,10 +13,12 @@ static int mt7996_check_eeprom(struct mt7996_dev *dev)
 	u16 val = get_unaligned_le16(eeprom);
 
 	switch (val) {
-	case 0x7990:
+	case MT7996_DEVICE_ID:
 		return is_mt7996(&dev->mt76) ? 0 : -EINVAL;
-	case 0x7992:
+	case MT7992_DEVICE_ID:
 		return is_mt7992(&dev->mt76) ? 0 : -EINVAL;
+	case MT7990_DEVICE_ID:
+		return is_mt7990(&dev->mt76) ? 0 : -EINVAL;
 	default:
 		return -EINVAL;
 	}
@@ -25,7 +27,7 @@ static int mt7996_check_eeprom(struct mt7996_dev *dev)
 static char *mt7996_eeprom_name(struct mt7996_dev *dev)
 {
 	switch (mt76_chip(&dev->mt76)) {
-	case 0x7992:
+	case MT7992_DEVICE_ID:
 		switch (dev->var.type) {
 		case MT7992_VAR_TYPE_23:
 			if (dev->var.fem == MT7996_FEM_INT)
@@ -39,7 +41,11 @@ static char *mt7996_eeprom_name(struct mt7996_dev *dev)
 				return MT7992_EEPROM_DEFAULT_MIX;
 			return MT7992_EEPROM_DEFAULT;
 		}
-	case 0x7990:
+	case MT7990_DEVICE_ID:
+		if (dev->var.fem == MT7996_FEM_INT)
+			return MT7990_EEPROM_DEFAULT_INT;
+		return MT7990_EEPROM_DEFAULT;
+	case MT7996_DEVICE_ID:
 	default:
 		switch (dev->var.type) {
 		case MT7996_VAR_TYPE_233:
@@ -304,6 +310,7 @@ int mt7996_eeprom_parse_hw_cap(struct mt7996_dev *dev, struct mt7996_phy *phy)
 		phy->has_aux_rx = true;
 
 	mphy->antenna_mask = BIT(nss) - 1;
+	phy->orig_antenna_mask = mphy->antenna_mask;
 	mphy->chainmask = (BIT(path) - 1) << dev->chainshift[band_idx];
 	phy->orig_chainmask = mphy->chainmask;
 	dev->chainmask |= mphy->chainmask;
@@ -370,3 +377,30 @@ s8 mt7996_eeprom_get_power_delta(struct mt7996_dev *dev, int band)
 
 	return val & MT_EE_RATE_DELTA_SIGN ? delta : -delta;
 }
+
+bool mt7996_eeprom_has_background_radar(struct mt7996_dev *dev)
+{
+	switch (mt76_chip(&dev->mt76)) {
+	case MT7996_DEVICE_ID:
+		if (dev->var.type == MT7996_VAR_TYPE_233)
+			return false;
+		break;
+	case MT7992_DEVICE_ID:
+		if (dev->var.type == MT7992_VAR_TYPE_23)
+			return false;
+		break;
+	case MT7990_DEVICE_ID: {
+		u8 path, rx_path, nss, *eeprom = dev->mt76.eeprom.data;
+
+		mt7996_eeprom_parse_stream(eeprom, MT_BAND1, &path, &rx_path, &nss);
+		/* Disable background radar capability in 3T3R */
+		if (path == 3 || rx_path == 3)
+			return false;
+		break;
+		}
+	default:
+		return false;
+	}
+
+	return true;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
index 6b660424aedc..a9599c286328 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
@@ -217,6 +217,9 @@ static int mt7996_thermal_init(struct mt7996_phy *phy)
 
 	name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7996_%s.%d",
 			      wiphy_name(wiphy), phy->mt76->band_idx);
+	if (!name)
+		return -ENOMEM;
+
 	snprintf(cname, sizeof(cname), "cooling_device%d", phy->mt76->band_idx);
 
 	cdev = thermal_cooling_device_register(name, phy, &mt7996_thermal_ops);
@@ -314,8 +317,8 @@ static void __mt7996_init_txpower(struct mt7996_phy *phy,
 				  struct ieee80211_supported_band *sband)
 {
 	struct mt7996_dev *dev = phy->dev;
-	int i, nss = hweight16(phy->mt76->chainmask);
-	int nss_delta = mt76_tx_power_nss_delta(nss);
+	int i, n_chains = hweight16(phy->mt76->chainmask);
+	int path_delta = mt76_tx_power_path_delta(n_chains);
 	int pwr_delta = mt7996_eeprom_get_power_delta(dev, sband->band);
 	struct mt76_power_limits limits;
 
@@ -327,7 +330,7 @@ static void __mt7996_init_txpower(struct mt7996_phy *phy,
 		target_power = mt76_get_rate_power_limits(phy->mt76, chan,
 							  &limits,
 							  target_power);
-		target_power += nss_delta;
+		target_power += path_delta;
 		target_power = DIV_ROUND_UP(target_power, 2);
 		chan->max_power = min_t(int, chan->max_reg_power,
 					target_power);
@@ -440,6 +443,9 @@ mt7996_init_wiphy(struct ieee80211_hw *hw, struct mtk_wed_device *wed)
 	hw->queues = 4;
 	hw->max_rx_aggregation_subframes = max_subframes;
 	hw->max_tx_aggregation_subframes = max_subframes;
+	if (is_mt7990(mdev) && dev->has_eht)
+		hw->max_tx_aggregation_subframes = 512;
+
 	hw->netdev_features = NETIF_F_RXCSUM;
 	if (mtk_wed_device_active(wed))
 		hw->netdev_features |= NETIF_F_HW_TC;
@@ -472,7 +478,7 @@ mt7996_init_wiphy(struct ieee80211_hw *hw, struct mtk_wed_device *wed)
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0);
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER);
 
-	if (mt7996_has_background_radar(dev) &&
+	if (mt7996_eeprom_has_background_radar(dev) &&
 	    (!mdev->dev->of_node ||
 	     !of_property_read_bool(mdev->dev->of_node,
 				    "mediatek,disable-radar-background")))
@@ -929,13 +935,13 @@ static int mt7996_variant_type_init(struct mt7996_dev *dev)
 	u8 var_type;
 
 	switch (mt76_chip(&dev->mt76)) {
-	case 0x7990:
+	case MT7996_DEVICE_ID:
 		if (val & MT_PAD_GPIO_2ADIE_TBTC)
 			var_type = MT7996_VAR_TYPE_233;
 		else
 			var_type = MT7996_VAR_TYPE_444;
 		break;
-	case 0x7992:
+	case MT7992_DEVICE_ID:
 		if (val & MT_PAD_GPIO_ADIE_SINGLE)
 			var_type = MT7992_VAR_TYPE_23;
 		else if (u32_get_bits(val, MT_PAD_GPIO_ADIE_COMB_7992))
@@ -943,6 +949,9 @@ static int mt7996_variant_type_init(struct mt7996_dev *dev)
 		else
 			return -EINVAL;
 		break;
+	case MT7990_DEVICE_ID:
+		var_type = MT7990_VAR_TYPE_23;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1061,10 +1070,10 @@ void mt7996_set_stream_vht_txbf_caps(struct mt7996_phy *phy)
 	*cap |= IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE |
 		IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE;
 
-	if (is_mt7996(phy->mt76->dev))
-		*cap |= FIELD_PREP(IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK, 3);
-	else
+	if (is_mt7992(phy->mt76->dev))
 		*cap |= FIELD_PREP(IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK, 4);
+	else
+		*cap |= FIELD_PREP(IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK, 3);
 
 	*cap &= ~(IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK |
 		  IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE |
@@ -1107,18 +1116,17 @@ mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy,
 	elem->phy_cap_info[7] &= ~IEEE80211_HE_PHY_CAP7_MAX_NC_MASK;
 
 	c = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US |
-	    IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO |
-	    IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO;
+	    IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO;
 	elem->phy_cap_info[2] |= c;
 
 	c = IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE;
 
-	if (is_mt7996(phy->mt76->dev))
-		c |= IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 |
-		     (IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 * non_2g);
-	else
+	if (is_mt7992(phy->mt76->dev))
 		c |= IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 |
 		     (IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5 * non_2g);
+	else
+		c |= IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 |
+		     (IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 * non_2g);
 
 	elem->phy_cap_info[4] |= c;
 
@@ -1318,6 +1326,9 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
 		u8_encode_bits(IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454,
 			       IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK);
 
+	eht_cap_elem->mac_cap_info[1] |=
+		IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK;
+
 	eht_cap_elem->phy_cap_info[0] =
 		IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI |
 		IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER |
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index d89c06f47997..0dbd4662bc84 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -647,6 +647,14 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q,
 		status->last_amsdu = amsdu_info == MT_RXD4_LAST_AMSDU_FRAME;
 	}
 
+	/* IEEE 802.11 fragmentation can only be applied to unicast frames.
+	 * Hence, drop fragments with multicast/broadcast RA.
+	 * This check fixes vulnerabilities, like CVE-2020-26145.
+	 */
+	if ((ieee80211_has_morefrags(fc) || seq_ctrl & IEEE80211_SCTL_FRAG) &&
+	    FIELD_GET(MT_RXD3_NORMAL_ADDR_TYPE, rxd3) != MT_RXD3_NORMAL_U2M)
+		return -EINVAL;
+
 	hdr_gap = (u8 *)rxd - skb->data + 2 * remove_pad;
 	if (hdr_trans && ieee80211_has_morefrags(fc)) {
 		if (mt7996_reverse_frag0_hdr_trans(skb, hdr_gap))
@@ -789,10 +797,13 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
 
 	if (ieee80211_is_action(fc) &&
 	    mgmt->u.action.category == WLAN_CATEGORY_BACK &&
-	    mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ)
+	    mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) {
+		if (is_mt7990(&dev->mt76))
+			txwi[6] |= cpu_to_le32(FIELD_PREP(MT_TXD6_TID_ADDBA, tid));
 		tid = MT_TX_ADDBA;
-	else if (ieee80211_is_mgmt(hdr->frame_control))
+	} else if (ieee80211_is_mgmt(hdr->frame_control)) {
 		tid = MT_TX_NORMAL;
+	}
 
 	val = FIELD_PREP(MT_TXD1_HDR_FORMAT, MT_HDR_FORMAT_802_11) |
 	      FIELD_PREP(MT_TXD1_HDR_INFO,
@@ -987,12 +998,32 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 	}
 }
 
+static bool
+mt7996_tx_use_mgmt(struct mt7996_dev *dev, struct sk_buff *skb)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+
+	if (ieee80211_is_mgmt(hdr->frame_control))
+		return true;
+
+	/* for SDO to bypass specific data frame */
+	if (!mt7996_has_wa(dev)) {
+		if (unlikely(skb->protocol == cpu_to_be16(ETH_P_PAE)))
+			return true;
+
+		if (ieee80211_has_a4(hdr->frame_control) &&
+		    !ieee80211_is_data_present(hdr->frame_control))
+			return true;
+	}
+
+	return false;
+}
+
 int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			  enum mt76_txq_id qid, struct mt76_wcid *wcid,
 			  struct ieee80211_sta *sta,
 			  struct mt76_tx_info *tx_info)
 {
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx_info->skb->data;
 	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx_info->skb);
 	struct ieee80211_key_conf *key = info->control.hw_key;
@@ -1017,8 +1048,11 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 		return id;
 
 	pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb);
-	mt7996_mac_write_txwi(dev, txwi_ptr, tx_info->skb, wcid, key,
-			      pid, qid, 0);
+	memset(txwi_ptr, 0, MT_TXD_SIZE);
+	/* Transmit non qos data by 802.11 header and need to fill txd by host*/
+	if (!is_8023 || pid >= MT_PACKET_ID_FIRST)
+		mt7996_mac_write_txwi(dev, txwi_ptr, tx_info->skb, wcid, key,
+				      pid, qid, 0);
 
 	txp = (struct mt76_connac_txp_common *)(txwi + MT_TXD_SIZE);
 	for (i = 0; i < nbuf; i++) {
@@ -1035,13 +1069,15 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	}
 	txp->fw.nbuf = nbuf;
 
-	txp->fw.flags =
-		cpu_to_le16(MT_CT_INFO_FROM_HOST | MT_CT_INFO_APPLY_TXD);
+	txp->fw.flags = cpu_to_le16(MT_CT_INFO_FROM_HOST);
+
+	if (!is_8023 || pid >= MT_PACKET_ID_FIRST)
+		txp->fw.flags |= cpu_to_le16(MT_CT_INFO_APPLY_TXD);
 
 	if (!key)
 		txp->fw.flags |= cpu_to_le16(MT_CT_INFO_NONE_CIPHER_FRAME);
 
-	if (!is_8023 && ieee80211_is_mgmt(hdr->frame_control))
+	if (!is_8023 && mt7996_tx_use_mgmt(dev, tx_info->skb))
 		txp->fw.flags |= cpu_to_le16(MT_CT_INFO_MGMT_FRAME);
 
 	if (vif) {
@@ -1179,6 +1215,7 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len)
 	void *end = data + len;
 	bool wake = false;
 	u16 total, count = 0;
+	u8 ver;
 
 	/* clean DMA queues and unmap buffers first */
 	mt76_queue_tx_cleanup(dev, dev->mphy.q_tx[MT_TXQ_PSD], false);
@@ -1192,7 +1229,8 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len)
 		mt76_queue_tx_cleanup(dev, phy3->q_tx[MT_TXQ_BE], false);
 	}
 
-	if (WARN_ON_ONCE(le32_get_bits(tx_free[1], MT_TXFREE1_VER) < 5))
+	ver = le32_get_bits(tx_free[1], MT_TXFREE1_VER);
+	if (WARN_ON_ONCE(ver < 5))
 		return;
 
 	total = le32_get_bits(tx_free[0], MT_TXFREE0_MSDU_CNT);
@@ -1214,11 +1252,16 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len)
 			wcid = rcu_dereference(dev->mt76.wcid[idx]);
 			sta = wcid_to_sta(wcid);
 			if (!sta)
-				continue;
+				goto next;
 
 			msta_link = container_of(wcid, struct mt7996_sta_link,
 						 wcid);
 			mt76_wcid_add_poll(&dev->mt76, &msta_link->wcid);
+next:
+			/* ver 7 has a new DW with pair = 1, skip it */
+			if (ver == 7 && ((void *)(cur_info + 1) < end) &&
+			    (le32_to_cpu(*(cur_info + 1)) & MT_TXFREE_INFO_PAIR))
+				cur_info++;
 			continue;
 		} else if (info & MT_TXFREE_INFO_HEADER) {
 			u32 tx_retries = 0, tx_failed = 0;
@@ -2411,16 +2454,15 @@ void mt7996_mac_work(struct work_struct *work)
 static void mt7996_dfs_stop_radar_detector(struct mt7996_phy *phy)
 {
 	struct mt7996_dev *dev = phy->dev;
+	int rdd_idx = mt7996_get_rdd_idx(phy, false);
+
+	if (rdd_idx < 0)
+		return;
 
-	if (phy->rdd_state & BIT(0))
-		mt7996_mcu_rdd_cmd(dev, RDD_STOP, 0,
-				   MT_RX_SEL0, 0);
-	if (phy->rdd_state & BIT(1))
-		mt7996_mcu_rdd_cmd(dev, RDD_STOP, 1,
-				   MT_RX_SEL0, 0);
+	mt7996_mcu_rdd_cmd(dev, RDD_STOP, rdd_idx, 0);
 }
 
-static int mt7996_dfs_start_rdd(struct mt7996_dev *dev, int chain)
+static int mt7996_dfs_start_rdd(struct mt7996_dev *dev, int rdd_idx)
 {
 	int err, region;
 
@@ -2437,44 +2479,30 @@ static int mt7996_dfs_start_rdd(struct mt7996_dev *dev, int chain)
 		break;
 	}
 
-	err = mt7996_mcu_rdd_cmd(dev, RDD_START, chain,
-				 MT_RX_SEL0, region);
+	err = mt7996_mcu_rdd_cmd(dev, RDD_START, rdd_idx, region);
 	if (err < 0)
 		return err;
 
-	return mt7996_mcu_rdd_cmd(dev, RDD_DET_MODE, chain,
-				 MT_RX_SEL0, 1);
+	return mt7996_mcu_rdd_cmd(dev, RDD_DET_MODE, rdd_idx, 1);
 }
 
 static int mt7996_dfs_start_radar_detector(struct mt7996_phy *phy)
 {
-	struct cfg80211_chan_def *chandef = &phy->mt76->chandef;
 	struct mt7996_dev *dev = phy->dev;
-	u8 band_idx = phy->mt76->band_idx;
-	int err;
+	int err, rdd_idx;
 
-	/* start CAC */
-	err = mt7996_mcu_rdd_cmd(dev, RDD_CAC_START, band_idx,
-				 MT_RX_SEL0, 0);
-	if (err < 0)
-		return err;
+	rdd_idx = mt7996_get_rdd_idx(phy, false);
+	if (rdd_idx < 0)
+		return -EINVAL;
 
-	err = mt7996_dfs_start_rdd(dev, band_idx);
+	/* start CAC */
+	err = mt7996_mcu_rdd_cmd(dev, RDD_CAC_START, rdd_idx, 0);
 	if (err < 0)
 		return err;
 
-	phy->rdd_state |= BIT(band_idx);
-
-	if (chandef->width == NL80211_CHAN_WIDTH_160 ||
-	    chandef->width == NL80211_CHAN_WIDTH_80P80) {
-		err = mt7996_dfs_start_rdd(dev, 1);
-		if (err < 0)
-			return err;
-
-		phy->rdd_state |= BIT(1);
-	}
+	err = mt7996_dfs_start_rdd(dev, rdd_idx);
 
-	return 0;
+	return err;
 }
 
 static int
@@ -2515,12 +2543,12 @@ int mt7996_dfs_init_radar_detector(struct mt7996_phy *phy)
 {
 	struct mt7996_dev *dev = phy->dev;
 	enum mt76_dfs_state dfs_state, prev_state;
-	int err;
+	int err, rdd_idx = mt7996_get_rdd_idx(phy, false);
 
 	prev_state = phy->mt76->dfs_state;
 	dfs_state = mt76_phy_dfs_state(phy->mt76);
 
-	if (prev_state == dfs_state)
+	if (prev_state == dfs_state || rdd_idx < 0)
 		return 0;
 
 	if (prev_state == MT_DFS_STATE_UNKNOWN)
@@ -2544,8 +2572,7 @@ int mt7996_dfs_init_radar_detector(struct mt7996_phy *phy)
 	if (dfs_state == MT_DFS_STATE_CAC)
 		return 0;
 
-	err = mt7996_mcu_rdd_cmd(dev, RDD_CAC_END,
-				 phy->mt76->band_idx, MT_RX_SEL0, 0);
+	err = mt7996_mcu_rdd_cmd(dev, RDD_CAC_END, rdd_idx, 0);
 	if (err < 0) {
 		phy->mt76->dfs_state = MT_DFS_STATE_UNKNOWN;
 		return err;
@@ -2555,8 +2582,7 @@ int mt7996_dfs_init_radar_detector(struct mt7996_phy *phy)
 	return 0;
 
 stop:
-	err = mt7996_mcu_rdd_cmd(dev, RDD_NORMAL_START,
-				 phy->mt76->band_idx, MT_RX_SEL0, 0);
+	err = mt7996_mcu_rdd_cmd(dev, RDD_NORMAL_START, rdd_idx, 0);
 	if (err < 0)
 		return err;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 91c64e3a0860..78ae9f5cb176 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -68,11 +68,13 @@ static int mt7996_start(struct ieee80211_hw *hw)
 
 static void mt7996_stop_phy(struct mt7996_phy *phy)
 {
-	struct mt7996_dev *dev = phy->dev;
+	struct mt7996_dev *dev;
 
 	if (!phy || !test_bit(MT76_STATE_RUNNING, &phy->mt76->state))
 		return;
 
+	dev = phy->dev;
+
 	cancel_delayed_work_sync(&phy->mt76->mac_work);
 
 	mutex_lock(&dev->mt76.mutex);
@@ -414,11 +416,13 @@ static void mt7996_phy_set_rxfilter(struct mt7996_phy *phy)
 
 static void mt7996_set_monitor(struct mt7996_phy *phy, bool enabled)
 {
-	struct mt7996_dev *dev = phy->dev;
+	struct mt7996_dev *dev;
 
 	if (!phy)
 		return;
 
+	dev = phy->dev;
+
 	if (enabled == !(phy->rxfilter & MT_WF_RFCR_DROP_OTHER_UC))
 		return;
 
@@ -684,7 +688,7 @@ mt7996_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	}
 
 	n_chains = hweight16(phy->mt76->chainmask);
-	delta = mt76_tx_power_nss_delta(n_chains);
+	delta = mt76_tx_power_path_delta(n_chains);
 	*dbm = DIV_ROUND_UP(phy->mt76->txpower_cur + delta, 2);
 
 	return 0;
@@ -987,7 +991,7 @@ mt7996_mac_sta_add_links(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 {
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	unsigned int link_id;
-	int err;
+	int err = 0;
 
 	for_each_set_bit(link_id, &new_links, IEEE80211_MLD_MAX_NUM_LINKS) {
 		struct ieee80211_bss_conf *link_conf;
@@ -998,16 +1002,22 @@ mt7996_mac_sta_add_links(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 			continue;
 
 		link_conf = link_conf_dereference_protected(vif, link_id);
-		if (!link_conf)
+		if (!link_conf) {
+			err = -EINVAL;
 			goto error_unlink;
+		}
 
 		link = mt7996_vif_link(dev, vif, link_id);
-		if (!link)
+		if (!link) {
+			err = -EINVAL;
 			goto error_unlink;
+		}
 
 		link_sta = link_sta_dereference_protected(sta, link_id);
-		if (!link_sta)
+		if (!link_sta) {
+			err = -EINVAL;
 			goto error_unlink;
+		}
 
 		err = mt7996_mac_sta_init_link(dev, link_conf, link_sta, link,
 					       link_id);
@@ -1244,7 +1254,7 @@ unlock:
 static int mt7996_set_rts_threshold(struct ieee80211_hw *hw, u32 val)
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
-	int i, ret;
+	int i, ret = 0;
 
 	mutex_lock(&dev->mt76.mutex);
 
@@ -1518,7 +1528,8 @@ mt7996_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 		u8 shift = dev->chainshift[band_idx];
 
 		phy->mt76->chainmask = tx_ant & phy->orig_chainmask;
-		phy->mt76->antenna_mask = phy->mt76->chainmask >> shift;
+		phy->mt76->antenna_mask = (phy->mt76->chainmask >> shift) &
+					  phy->orig_antenna_mask;
 
 		mt76_set_stream_caps(phy->mt76, true);
 		mt7996_set_stream_vht_txbf_caps(phy);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index ddd555942c73..f0adc0b4b8b6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -13,7 +13,7 @@
 #define fw_name(_dev, name, ...)	({			\
 	char *_fw;						\
 	switch (mt76_chip(&(_dev)->mt76)) {			\
-	case 0x7992:						\
+	case MT7992_DEVICE_ID:						\
 		switch ((_dev)->var.type) {			\
 		case MT7992_VAR_TYPE_23:			\
 			_fw = MT7992_##name##_23;		\
@@ -22,7 +22,10 @@
 			_fw = MT7992_##name;			\
 		}						\
 		break;						\
-	case 0x7990:						\
+	case MT7990_DEVICE_ID:					\
+		_fw = MT7990_##name;				\
+		break;						\
+	case MT7996_DEVICE_ID:						\
 	default:						\
 		switch ((_dev)->var.type) {			\
 		case MT7996_VAR_TYPE_233:			\
@@ -265,7 +268,7 @@ mt7996_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 
 	txd_len = cmd & __MCU_CMD_FIELD_UNI ? sizeof(*uni_txd) : sizeof(*mcu_txd);
 	txd = (__le32 *)skb_push(skb, txd_len);
-	if (test_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state))
+	if (test_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state) && mt7996_has_wa(dev))
 		qid = MT_MCUQ_WA;
 	else
 		qid = MT_MCUQ_WM;
@@ -335,8 +338,12 @@ exit:
 int mt7996_mcu_wa_cmd(struct mt7996_dev *dev, int cmd, u32 a1, u32 a2, u32 a3)
 {
 	struct {
+		u8 _rsv[4];
+
+		__le16 tag;
+		__le16 len;
 		__le32 args[3];
-	} req = {
+	} __packed req = {
 		.args = {
 			cpu_to_le32(a1),
 			cpu_to_le32(a2),
@@ -344,7 +351,16 @@ int mt7996_mcu_wa_cmd(struct mt7996_dev *dev, int cmd, u32 a1, u32 a2, u32 a3)
 		},
 	};
 
-	return mt76_mcu_send_msg(&dev->mt76, cmd, &req, sizeof(req), false);
+	if (mt7996_has_wa(dev))
+		return mt76_mcu_send_msg(&dev->mt76, cmd, &req.args,
+					 sizeof(req.args), false);
+
+	req.tag = cpu_to_le16(cmd == MCU_WA_PARAM_CMD(QUERY) ? UNI_CMD_SDO_QUERY :
+							       UNI_CMD_SDO_SET);
+	req.len = cpu_to_le16(sizeof(req) - 4);
+
+	return mt76_mcu_send_msg(&dev->mt76, MCU_WA_UNI_CMD(SDO), &req,
+				 sizeof(req), false);
 }
 
 static void
@@ -364,21 +380,27 @@ mt7996_mcu_rx_radar_detected(struct mt7996_dev *dev, struct sk_buff *skb)
 
 	r = (struct mt7996_mcu_rdd_report *)skb->data;
 
-	if (r->band_idx >= ARRAY_SIZE(dev->mt76.phys))
-		return;
-
-	if (r->band_idx == MT_RX_SEL2 && !dev->rdd2_phy)
-		return;
-
-	if (r->band_idx == MT_RX_SEL2)
+	switch (r->rdd_idx) {
+	case MT_RDD_IDX_BAND2:
+		mphy = dev->mt76.phys[MT_BAND2];
+		break;
+	case MT_RDD_IDX_BAND1:
+		mphy = dev->mt76.phys[MT_BAND1];
+		break;
+	case MT_RDD_IDX_BACKGROUND:
+		if (!dev->rdd2_phy)
+			return;
 		mphy = dev->rdd2_phy->mt76;
-	else
-		mphy = dev->mt76.phys[r->band_idx];
+		break;
+	default:
+		dev_err(dev->mt76.dev, "Unknown RDD idx %d\n", r->rdd_idx);
+		return;
+	}
 
 	if (!mphy)
 		return;
 
-	if (r->band_idx == MT_RX_SEL2)
+	if (r->rdd_idx == MT_RDD_IDX_BACKGROUND)
 		cfg80211_background_radar_event(mphy->hw->wiphy,
 						&dev->rdd2_chandef,
 						GFP_ATOMIC);
@@ -2242,9 +2264,6 @@ mt7996_mcu_sta_mld_setup_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 		if (!link)
 			continue;
 
-		if (!msta_link)
-			continue;
-
 		mld_setup_link->wcid = cpu_to_le16(msta_link->wcid.idx);
 		mld_setup_link->bss_idx = link->mt76.idx;
 		mld_setup_link++;
@@ -3011,6 +3030,9 @@ static int mt7996_load_ram(struct mt7996_dev *dev)
 	if (ret)
 		return ret;
 
+	if (!mt7996_has_wa(dev))
+		return 0;
+
 	ret = __mt7996_load_ram(dev, "DSP", fw_name(dev, FIRMWARE_DSP),
 				MT7996_RAM_TYPE_DSP);
 	if (ret)
@@ -3021,10 +3043,9 @@ static int mt7996_load_ram(struct mt7996_dev *dev)
 }
 
 static int
-mt7996_firmware_state(struct mt7996_dev *dev, bool wa)
+mt7996_firmware_state(struct mt7996_dev *dev, u8 fw_state)
 {
-	u32 state = FIELD_PREP(MT_TOP_MISC_FW_STATE,
-			       wa ? FW_STATE_RDY : FW_STATE_FW_DOWNLOAD);
+	u32 state = FIELD_PREP(MT_TOP_MISC_FW_STATE, fw_state);
 
 	if (!mt76_poll_msec(dev, MT_TOP_MISC, MT_TOP_MISC_FW_STATE,
 			    state, 1000)) {
@@ -3056,13 +3077,14 @@ mt7996_mcu_restart(struct mt76_dev *dev)
 
 static int mt7996_load_firmware(struct mt7996_dev *dev)
 {
+	u8 fw_state;
 	int ret;
 
 	/* make sure fw is download state */
-	if (mt7996_firmware_state(dev, false)) {
+	if (mt7996_firmware_state(dev, FW_STATE_FW_DOWNLOAD)) {
 		/* restart firmware once */
 		mt7996_mcu_restart(&dev->mt76);
-		ret = mt7996_firmware_state(dev, false);
+		ret = mt7996_firmware_state(dev, FW_STATE_FW_DOWNLOAD);
 		if (ret) {
 			dev_err(dev->mt76.dev,
 				"Firmware is not ready for download\n");
@@ -3078,7 +3100,8 @@ static int mt7996_load_firmware(struct mt7996_dev *dev)
 	if (ret)
 		return ret;
 
-	ret = mt7996_firmware_state(dev, true);
+	fw_state = mt7996_has_wa(dev) ? FW_STATE_RDY : FW_STATE_NORMAL_TRX;
+	ret = mt7996_firmware_state(dev, fw_state);
 	if (ret)
 		return ret;
 
@@ -3216,13 +3239,15 @@ int mt7996_mcu_init_firmware(struct mt7996_dev *dev)
 	if (ret)
 		return ret;
 
-	ret = mt7996_mcu_fw_log_2_host(dev, MCU_FW_LOG_WA, 0);
-	if (ret)
-		return ret;
+	if (mt7996_has_wa(dev)) {
+		ret = mt7996_mcu_fw_log_2_host(dev, MCU_FW_LOG_WA, 0);
+		if (ret)
+			return ret;
 
-	ret = mt7996_mcu_set_mwds(dev, 1);
-	if (ret)
-		return ret;
+		ret = mt7996_mcu_set_mwds(dev, 1);
+		if (ret)
+			return ret;
+	}
 
 	ret = mt7996_mcu_init_rx_airtime(dev);
 	if (ret)
@@ -3248,7 +3273,7 @@ int mt7996_mcu_init(struct mt7996_dev *dev)
 void mt7996_mcu_exit(struct mt7996_dev *dev)
 {
 	mt7996_mcu_restart(&dev->mt76);
-	if (mt7996_firmware_state(dev, false)) {
+	if (mt7996_firmware_state(dev, FW_STATE_FW_DOWNLOAD)) {
 		dev_err(dev->mt76.dev, "Failed to exit mcu\n");
 		goto out;
 	}
@@ -3535,11 +3560,10 @@ int mt7996_mcu_rdd_background_enable(struct mt7996_phy *phy,
 				     struct cfg80211_chan_def *chandef)
 {
 	struct mt7996_dev *dev = phy->dev;
-	int err, region;
+	int err, region, rdd_idx = mt7996_get_rdd_idx(phy, true);
 
 	if (!chandef) { /* disable offchain */
-		err = mt7996_mcu_rdd_cmd(dev, RDD_STOP, MT_RX_SEL2,
-					 0, 0);
+		err = mt7996_mcu_rdd_cmd(dev, RDD_STOP, rdd_idx, 0);
 		if (err)
 			return err;
 
@@ -3565,8 +3589,7 @@ int mt7996_mcu_rdd_background_enable(struct mt7996_phy *phy,
 		break;
 	}
 
-	return mt7996_mcu_rdd_cmd(dev, RDD_START, MT_RX_SEL2,
-				  0, region);
+	return mt7996_mcu_rdd_cmd(dev, RDD_START, rdd_idx, region);
 }
 
 int mt7996_mcu_set_chan_info(struct mt7996_phy *phy, u16 tag)
@@ -4433,8 +4456,7 @@ int mt7996_mcu_set_radio_en(struct mt7996_phy *phy, bool enable)
 				 &req, sizeof(req), true);
 }
 
-int mt7996_mcu_rdd_cmd(struct mt7996_dev *dev, int cmd, u8 index,
-		       u8 rx_sel, u8 val)
+int mt7996_mcu_rdd_cmd(struct mt7996_dev *dev, int cmd, u8 rdd_idx, u8 val)
 {
 	struct {
 		u8 _rsv[4];
@@ -4451,8 +4473,7 @@ int mt7996_mcu_rdd_cmd(struct mt7996_dev *dev, int cmd, u8 index,
 		.tag = cpu_to_le16(UNI_RDD_CTRL_PARM),
 		.len = cpu_to_le16(sizeof(req) - 4),
 		.ctrl = cmd,
-		.rdd_idx = index,
-		.rdd_rx_sel = rx_sel,
+		.rdd_idx = rdd_idx,
 		.val = val,
 	};
 
@@ -4742,7 +4763,26 @@ int mt7996_mcu_cp_support(struct mt7996_dev *dev, u8 mode)
 	    mode > mt76_connac_lmac_mapping(IEEE80211_AC_VO))
 		return -EINVAL;
 
+	if (!mt7996_has_wa(dev)) {
+		struct {
+			u8 _rsv[4];
+
+			__le16 tag;
+			__le16 len;
+			u8 cp_mode;
+			u8 rsv[3];
+		} __packed req = {
+			.tag = cpu_to_le16(UNI_CMD_SDO_CP_MODE),
+			.len = cpu_to_le16(sizeof(req) - 4),
+			.cp_mode = mode,
+		};
+
+		return mt76_mcu_send_msg(&dev->mt76, MCU_WA_UNI_CMD(SDO),
+					 &req, sizeof(req), false);
+	}
+
 	cp_mode = cpu_to_le32(mode);
+
 	return mt76_mcu_send_msg(&dev->mt76, MCU_WA_EXT_CMD(CP_SUPPORT),
 				 &cp_mode, sizeof(cp_mode), true);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
index 2ab6a53bee86..130ea95626d5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
@@ -69,7 +69,7 @@ struct mt7996_mcu_rdd_report {
 	__le16 tag;
 	__le16 len;
 
-	u8 band_idx;
+	u8 rdd_idx;
 	u8 long_detected;
 	u8 constant_prf_detected;
 	u8 staggered_prf_detected;
@@ -832,13 +832,13 @@ enum {
 					 sizeof(struct sta_rec_eht_mld) +	\
 					 sizeof(struct tlv))
 
-#define MT7996_MAX_BEACON_SIZE		1338
 #define MT7996_BEACON_UPDATE_SIZE	(sizeof(struct bss_req_hdr) +		\
 					 sizeof(struct bss_bcn_content_tlv) +	\
 					 4 + MT_TXD_SIZE +			\
 					 sizeof(struct bss_bcn_cntdwn_tlv) +	\
 					 sizeof(struct bss_bcn_mbss_tlv))
-#define MT7996_MAX_BSS_OFFLOAD_SIZE	(MT7996_MAX_BEACON_SIZE +		\
+#define MT7996_MAX_BSS_OFFLOAD_SIZE	2048
+#define MT7996_MAX_BEACON_SIZE		(MT7996_MAX_BSS_OFFLOAD_SIZE - \
 					 MT7996_BEACON_UPDATE_SIZE)
 
 enum {
@@ -938,6 +938,12 @@ enum {
 };
 
 enum {
+	UNI_CMD_SDO_SET = 1,
+	UNI_CMD_SDO_QUERY,
+	UNI_CMD_SDO_CP_MODE = 6,
+};
+
+enum {
 	MT7996_SEC_MODE_PLAIN,
 	MT7996_SEC_MODE_AES,
 	MT7996_SEC_MODE_SCRAMBLE,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
index 13b188e281bd..30b40f4a91be 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
@@ -54,6 +54,17 @@ static const u32 mt7996_offs[] = {
 	[MIB_BSCR7]		= 0x9e8,
 	[MIB_BSCR17]		= 0xa10,
 	[MIB_TRDR1]		= 0xa28,
+	[HIF_REMAP_L1]		= 0x24,
+	[HIF_REMAP_BASE_L1]	= 0x130000,
+	[HIF_REMAP_L2]		= 0x1b4,
+	[HIF_REMAP_BASE_L2]	= 0x1000,
+	[CBTOP1_PHY_END]	= 0x77ffffff,
+	[INFRA_MCU_END]		= 0x7c3fffff,
+	[WTBLON_WDUCR]		= 0x370,
+	[WTBL_UPDATE]		= 0x380,
+	[WTBL_ITCR]		= 0x3b0,
+	[WTBL_ITCR0]		= 0x3b8,
+	[WTBL_ITCR1]		= 0x3bc,
 };
 
 static const u32 mt7992_offs[] = {
@@ -80,6 +91,54 @@ static const u32 mt7992_offs[] = {
 	[MIB_BSCR7]		= 0xae4,
 	[MIB_BSCR17]		= 0xb0c,
 	[MIB_TRDR1]		= 0xb24,
+	[HIF_REMAP_L1]		= 0x8,
+	[HIF_REMAP_BASE_L1]	= 0x40000,
+	[HIF_REMAP_L2]		= 0x1b4,
+	[HIF_REMAP_BASE_L2]	= 0x1000,
+	[CBTOP1_PHY_END]	= 0x77ffffff,
+	[INFRA_MCU_END]		= 0x7c3fffff,
+	[WTBLON_WDUCR]		= 0x370,
+	[WTBL_UPDATE]		= 0x380,
+	[WTBL_ITCR]		= 0x3b0,
+	[WTBL_ITCR0]		= 0x3b8,
+	[WTBL_ITCR1]		= 0x3bc,
+};
+
+static const u32 mt7990_offs[] = {
+	[MIB_RVSR0]		= 0x800,
+	[MIB_RVSR1]		= 0x804,
+	[MIB_BTSCR5]		= 0x868,
+	[MIB_BTSCR6]		= 0x878,
+	[MIB_RSCR1]		= 0x890,
+	[MIB_RSCR27]		= 0xa38,
+	[MIB_RSCR28]		= 0xa3c,
+	[MIB_RSCR29]		= 0xa40,
+	[MIB_RSCR30]		= 0xa44,
+	[MIB_RSCR31]		= 0xa48,
+	[MIB_RSCR33]		= 0xa50,
+	[MIB_RSCR35]		= 0xa58,
+	[MIB_RSCR36]		= 0xa5c,
+	[MIB_BSCR0]		= 0xbb8,
+	[MIB_BSCR1]		= 0xbbc,
+	[MIB_BSCR2]		= 0xbc0,
+	[MIB_BSCR3]		= 0xbc4,
+	[MIB_BSCR4]		= 0xbc8,
+	[MIB_BSCR5]		= 0xbcc,
+	[MIB_BSCR6]		= 0xbd0,
+	[MIB_BSCR7]		= 0xbd4,
+	[MIB_BSCR17]		= 0xbfc,
+	[MIB_TRDR1]		= 0xc14,
+	[HIF_REMAP_L1]		= 0x8,
+	[HIF_REMAP_BASE_L1]	= 0x40000,
+	[HIF_REMAP_L2]		= 0x1b8,
+	[HIF_REMAP_BASE_L2]	= 0x110000,
+	[CBTOP1_PHY_END]	= 0x7fffffff,
+	[INFRA_MCU_END]		= 0x7cffffff,
+	[WTBLON_WDUCR]		= 0x400,
+	[WTBL_UPDATE]		= 0x410,
+	[WTBL_ITCR]		= 0x440,
+	[WTBL_ITCR0]		= 0x448,
+	[WTBL_ITCR1]		= 0x44c,
 };
 
 static const struct __map mt7996_reg_map[] = {
@@ -135,14 +194,83 @@ static const struct __map mt7996_reg_map[] = {
 	{ 0x0, 0x0, 0x0 }, /* imply end of search */
 };
 
+static const struct __map mt7990_reg_map[] = {
+	{0x54000000, 0x02000, 0x1000}, /* WFDMA_0 (PCIE0 MCU DMA0) */
+	{0x55000000, 0x03000, 0x1000}, /* WFDMA_1 (PCIE0 MCU DMA1) */
+	{0x56000000, 0x04000, 0x1000}, /* WFDMA_2 (Reserved) */
+	{0x57000000, 0x05000, 0x1000}, /* WFDMA_3 (MCU wrap CR) */
+	{0x58000000, 0x06000, 0x1000}, /* WFDMA_4 (PCIE1 MCU DMA0 (MEM_DMA)) */
+	{0x59000000, 0x07000, 0x1000}, /* WFDMA_5 (PCIE1 MCU DMA1) */
+	{0x820c0000, 0x08000, 0x4000}, /* WF_UMAC_TOP (PLE) */
+	{0x820c8000, 0x0c000, 0x2000}, /* WF_UMAC_TOP (PSE) */
+	{0x820cc000, 0x0e000, 0x2000}, /* WF_UMAC_TOP (PP) */
+	{0x820e0000, 0x20000, 0x0400}, /* WF_LMAC_TOP BN0 (WF_CFG) */
+	{0x820e1000, 0x20400, 0x0200}, /* WF_LMAC_TOP BN0 (WF_TRB) */
+	{0x820e2000, 0x20800, 0x0400}, /* WF_LMAC_TOP BN0 (WF_AGG) */
+	{0x820e3000, 0x20c00, 0x0400}, /* WF_LMAC_TOP BN0 (WF_ARB) */
+	{0x820e4000, 0x21000, 0x0400}, /* WF_LMAC_TOP BN0 (WF_TMAC) */
+	{0x820e5000, 0x21400, 0x0800}, /* WF_LMAC_TOP BN0 (WF_RMAC) */
+	{0x820ce000, 0x21c00, 0x0200}, /* WF_LMAC_TOP (WF_SEC) */
+	{0x820e7000, 0x21e00, 0x0200}, /* WF_LMAC_TOP BN0 (WF_DMA) */
+	{0x820cf000, 0x22000, 0x1000}, /* WF_LMAC_TOP (WF_PF) */
+	{0x820e9000, 0x23400, 0x0200}, /* WF_LMAC_TOP BN0 (WF_WTBLOFF) */
+	{0x820ea000, 0x24000, 0x0200}, /* WF_LMAC_TOP BN0 (WF_ETBF) */
+	{0x820eb000, 0x24200, 0x0400}, /* WF_LMAC_TOP BN0 (WF_LPON) */
+	{0x820ec000, 0x24600, 0x0200}, /* WF_LMAC_TOP BN0 (WF_INT) */
+	{0x820ed000, 0x24800, 0x0800}, /* WF_LMAC_TOP BN0 (WF_MIB) */
+	{0x820ca000, 0x26000, 0x2000}, /* WF_LMAC_TOP BN0 (WF_MUCOP) */
+	{0x820d0000, 0x30000, 0x10000}, /* WF_LMAC_TOP (WF_WTBLON) */
+	{0x00400000, 0x80000, 0x10000}, /* WF_MCU_SYSRAM */
+	{0x820f0000, 0xa0000, 0x0400}, /* WF_LMAC_TOP BN1 (WF_CFG) */
+	{0x820f1000, 0xa0600, 0x0200}, /* WF_LMAC_TOP BN1 (WF_TRB) */
+	{0x820f2000, 0xa0800, 0x0400}, /* WF_LMAC_TOP BN1 (WF_AGG) */
+	{0x820f3000, 0xa0c00, 0x0400}, /* WF_LMAC_TOP BN1 (WF_ARB) */
+	{0x820f4000, 0xa1000, 0x0400}, /* WF_LMAC_TOP BN1 (WF_TMAC) */
+	{0x820f5000, 0xa1400, 0x0800}, /* WF_LMAC_TOP BN1 (WF_RMAC) */
+	{0x820f7000, 0xa1e00, 0x0200}, /* WF_LMAC_TOP BN1 (WF_DMA) */
+	{0x820f9000, 0xa3400, 0x0200}, /* WF_LMAC_TOP BN1 (WF_WTBLOFF) */
+	{0x820fa000, 0xa4000, 0x0200}, /* WF_LMAC_TOP BN1 (WF_ETBF) */
+	{0x820fb000, 0xa4200, 0x0400}, /* WF_LMAC_TOP BN1 (WF_LPON) */
+	{0x820fc000, 0xa4600, 0x0200}, /* WF_LMAC_TOP BN1 (WF_INT) */
+	{0x820fd000, 0xa4800, 0x0800}, /* WF_LMAC_TOP BN1 (WF_MIB) */
+	{0x820cc000, 0xa5000, 0x2000}, /* WF_LMAC_TOP BN1 (WF_MUCOP) */
+	{0x820c4000, 0xa8000, 0x4000}, /* WF_LMAC_TOP (WF_UWTBL) */
+	{0x81030000, 0xae000, 0x100}, /* WFSYS_AON part 1 */
+	{0x81031000, 0xae100, 0x100}, /* WFSYS_AON part 2 */
+	{0x81032000, 0xae200, 0x100}, /* WFSYS_AON part 3 */
+	{0x81033000, 0xae300, 0x100}, /* WFSYS_AON part 4 */
+	{0x81034000, 0xae400, 0x100}, /* WFSYS_AON part 5 */
+	{0x80020000, 0xb0000, 0x10000}, /* WF_TOP_MISC_OFF */
+	{0x81020000, 0xc0000, 0x10000}, /* WF_TOP_MISC_ON */
+	{0x81040000, 0x120000, 0x1000}, /* WF_MCU_CFG_ON */
+	{0x81050000, 0x121000, 0x1000}, /* WF_MCU_EINT */
+	{0x81060000, 0x122000, 0x1000}, /* WF_MCU_GPT */
+	{0x81070000, 0x123000, 0x1000}, /* WF_MCU_WDT */
+	{0x80010000, 0x124000, 0x1000}, /* WF_AXIDMA */
+	{0x7c020000, 0xd0000, 0x10000}, /* CONN_INFRA, wfdma for from CODA flow use */
+	{0x7c060000, 0xe0000, 0x10000}, /* CONN_INFRA, conn_host_csr_top for from CODA flow use */
+	{0x20020000, 0xd0000, 0x10000}, /* CONN_INFRA, wfdma */
+	{0x20060000, 0xe0000, 0x10000}, /* CONN_INFRA, conn_host_csr_top */
+	{0x7c000000, 0xf0000, 0x10000}, /* CONN_INFRA */
+	{0x70020000, 0x1f0000, 0x9000}, /* PCIE remapping (AP2CONN) */
+	{0x0, 0x0, 0x0}, /* imply end of search */
+};
+
 static u32 mt7996_reg_map_l1(struct mt7996_dev *dev, u32 addr)
 {
 	u32 offset = FIELD_GET(MT_HIF_REMAP_L1_OFFSET, addr);
 	u32 base = FIELD_GET(MT_HIF_REMAP_L1_BASE, addr);
+	u32 l1_mask, val;
 
-	dev->bus_ops->rmw(&dev->mt76, MT_HIF_REMAP_L1,
-			  MT_HIF_REMAP_L1_MASK,
-			  FIELD_PREP(MT_HIF_REMAP_L1_MASK, base));
+	if (is_mt7996(&dev->mt76)) {
+		l1_mask = MT_HIF_REMAP_L1_MASK_7996;
+		val = FIELD_PREP(MT_HIF_REMAP_L1_MASK_7996, base);
+	} else {
+		l1_mask = MT_HIF_REMAP_L1_MASK;
+		val = FIELD_PREP(MT_HIF_REMAP_L1_MASK, base);
+	}
+
+	dev->bus_ops->rmw(&dev->mt76, MT_HIF_REMAP_L1, l1_mask, val);
 	/* use read to push write */
 	dev->bus_ops->rr(&dev->mt76, MT_HIF_REMAP_L1);
 
@@ -151,18 +279,41 @@ static u32 mt7996_reg_map_l1(struct mt7996_dev *dev, u32 addr)
 
 static u32 mt7996_reg_map_l2(struct mt7996_dev *dev, u32 addr)
 {
-	u32 offset = FIELD_GET(MT_HIF_REMAP_L2_OFFSET, addr);
-	u32 base = FIELD_GET(MT_HIF_REMAP_L2_BASE, addr);
+	u32 offset, base, l2_mask, val;
 
-	dev->bus_ops->rmw(&dev->mt76, MT_HIF_REMAP_L2,
-			  MT_HIF_REMAP_L2_MASK,
-			  FIELD_PREP(MT_HIF_REMAP_L2_MASK, base));
+	if (is_mt7990(&dev->mt76)) {
+		offset = FIELD_GET(MT_HIF_REMAP_L2_OFFSET_7990, addr);
+		base = FIELD_GET(MT_HIF_REMAP_L2_BASE_7990, addr);
+		l2_mask = MT_HIF_REMAP_L2_MASK_7990;
+		val = FIELD_PREP(MT_HIF_REMAP_L2_MASK_7990, base);
+	} else {
+		offset = FIELD_GET(MT_HIF_REMAP_L2_OFFSET, addr);
+		base = FIELD_GET(MT_HIF_REMAP_L2_BASE, addr);
+		l2_mask = MT_HIF_REMAP_L2_MASK;
+		val = FIELD_PREP(MT_HIF_REMAP_L2_MASK, base);
+	}
+
+	dev->bus_ops->rmw(&dev->mt76, MT_HIF_REMAP_L2, l2_mask, val);
 	/* use read to push write */
 	dev->bus_ops->rr(&dev->mt76, MT_HIF_REMAP_L2);
 
 	return MT_HIF_REMAP_BASE_L2 + offset;
 }
 
+static u32 mt7996_reg_map_cbtop(struct mt7996_dev *dev, u32 addr)
+{
+	u32 offset = FIELD_GET(MT_HIF_REMAP_CBTOP_OFFSET, addr);
+	u32 base = FIELD_GET(MT_HIF_REMAP_CBTOP_BASE, addr);
+
+	dev->bus_ops->rmw(&dev->mt76, MT_HIF_REMAP_CBTOP,
+			  MT_HIF_REMAP_CBTOP_MASK,
+			  FIELD_PREP(MT_HIF_REMAP_CBTOP_MASK, base));
+	/* use read to push write */
+	dev->bus_ops->rr(&dev->mt76, MT_HIF_REMAP_CBTOP);
+
+	return MT_HIF_REMAP_BASE_CBTOP + offset;
+}
+
 static u32 __mt7996_reg_addr(struct mt7996_dev *dev, u32 addr)
 {
 	int i;
@@ -193,17 +344,20 @@ static u32 __mt7996_reg_remap_addr(struct mt7996_dev *dev, u32 addr)
 	    (addr >= MT_WFSYS1_PHY_START && addr <= MT_WFSYS1_PHY_END))
 		return mt7996_reg_map_l1(dev, addr);
 
-	if (dev_is_pci(dev->mt76.dev) &&
-	    ((addr >= MT_CBTOP1_PHY_START && addr <= MT_CBTOP1_PHY_END) ||
-	    addr >= MT_CBTOP2_PHY_START))
-		return mt7996_reg_map_l1(dev, addr);
-
 	/* CONN_INFRA: covert to phyiscal addr and use layer 1 remap */
 	if (addr >= MT_INFRA_MCU_START && addr <= MT_INFRA_MCU_END) {
 		addr = addr - MT_INFRA_MCU_START + MT_INFRA_BASE;
 		return mt7996_reg_map_l1(dev, addr);
 	}
 
+	if (dev_is_pci(dev->mt76.dev) &&
+	    ((addr >= MT_CBTOP1_PHY_START && addr <= MT_CBTOP1_PHY_END) ||
+	    addr >= MT_CBTOP2_PHY_START)) {
+		if (is_mt7990(&dev->mt76))
+			return mt7996_reg_map_cbtop(dev, addr);
+		return mt7996_reg_map_l1(dev, addr);
+	}
+
 	return mt7996_reg_map_l2(dev, addr);
 }
 
@@ -323,6 +477,9 @@ int mt7996_mmio_wed_init(struct mt7996_dev *dev, void *pdev_ptr,
 	wed->wlan.base = devm_ioremap(dev->mt76.dev,
 				      pci_resource_start(pci_dev, 0),
 				      pci_resource_len(pci_dev, 0));
+	if (!wed->wlan.base)
+		return -ENOMEM;
+
 	wed->wlan.phy_base = pci_resource_start(pci_dev, 0);
 
 	if (hif2) {
@@ -350,7 +507,7 @@ int mt7996_mmio_wed_init(struct mt7996_dev *dev, void *pdev_ptr,
 				     MT_RXQ_RING_BASE(MT7996_RXQ_BAND0) +
 				     MT7996_RXQ_BAND0 * MT_RING_SIZE;
 
-		wed->wlan.id = 0x7991;
+		wed->wlan.id = MT7996_DEVICE_ID_2;
 		wed->wlan.tx_tbit[0] = ffs(MT_INT_TX_DONE_BAND2) - 1;
 	} else {
 		wed->wlan.hw_rro = dev->has_rro; /* default on */
@@ -443,18 +600,24 @@ static int mt7996_mmio_init(struct mt76_dev *mdev,
 	spin_lock_init(&dev->reg_lock);
 
 	switch (device_id) {
-	case 0x7990:
+	case MT7996_DEVICE_ID:
 		dev->reg.base = mt7996_reg_base;
 		dev->reg.offs_rev = mt7996_offs;
 		dev->reg.map = mt7996_reg_map;
 		dev->reg.map_size = ARRAY_SIZE(mt7996_reg_map);
 		break;
-	case 0x7992:
+	case MT7992_DEVICE_ID:
 		dev->reg.base = mt7996_reg_base;
 		dev->reg.offs_rev = mt7992_offs;
 		dev->reg.map = mt7996_reg_map;
 		dev->reg.map_size = ARRAY_SIZE(mt7996_reg_map);
 		break;
+	case MT7990_DEVICE_ID:
+		dev->reg.base = mt7996_reg_base;
+		dev->reg.offs_rev = mt7990_offs;
+		dev->reg.map = mt7990_reg_map;
+		dev->reg.map_size = ARRAY_SIZE(mt7990_reg_map);
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 43e646ed6094..1ad6bc046f7c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -14,7 +14,7 @@
 #define MT7996_MAX_RADIOS		3
 #define MT7996_MAX_INTERFACES		19	/* per-band */
 #define MT7996_MAX_WMM_SETS		4
-#define MT7996_WTBL_BMC_SIZE		(is_mt7992(&dev->mt76) ? 32 : 64)
+#define MT7996_WTBL_BMC_SIZE		(is_mt7996(&dev->mt76) ? 64 : 32)
 #define MT7996_WTBL_RESERVED		(mt7996_wtbl_size(dev) - 1)
 #define MT7996_WTBL_STA			(MT7996_WTBL_RESERVED - \
 					 mt7996_max_interface_num(dev))
@@ -29,6 +29,16 @@
 #define MT7996_RX_RING_SIZE		1536
 #define MT7996_RX_MCU_RING_SIZE		512
 #define MT7996_RX_MCU_RING_SIZE_WA	1024
+/* scatter-gather of mcu event is not supported in connac3 */
+#define MT7996_RX_MCU_BUF_SIZE		(2048 + \
+					 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
+#define MT7996_DEVICE_ID		0x7990
+#define MT7996_DEVICE_ID_2		0x7991
+#define MT7992_DEVICE_ID		0x7992
+#define MT7992_DEVICE_ID_2		0x799a
+#define MT7990_DEVICE_ID		0x7993
+#define MT7990_DEVICE_ID_2		0x799b
 
 #define MT7996_FIRMWARE_WA		"mediatek/mt7996/mt7996_wa.bin"
 #define MT7996_FIRMWARE_WM		"mediatek/mt7996/mt7996_wm.bin"
@@ -50,6 +60,11 @@
 #define MT7992_FIRMWARE_DSP_23		"mediatek/mt7996/mt7992_dsp_23.bin"
 #define MT7992_ROM_PATCH_23		"mediatek/mt7996/mt7992_rom_patch_23.bin"
 
+#define MT7990_FIRMWARE_WA		""
+#define MT7990_FIRMWARE_WM		"mediatek/mt7996/mt7990_wm.bin"
+#define MT7990_FIRMWARE_DSP		""
+#define MT7990_ROM_PATCH		"mediatek/mt7996/mt7990_rom_patch.bin"
+
 #define MT7996_EEPROM_DEFAULT		"mediatek/mt7996/mt7996_eeprom.bin"
 #define MT7996_EEPROM_DEFAULT_INT	"mediatek/mt7996/mt7996_eeprom_2i5i6i.bin"
 #define MT7996_EEPROM_DEFAULT_233	"mediatek/mt7996/mt7996_eeprom_233.bin"
@@ -61,6 +76,9 @@
 #define MT7992_EEPROM_DEFAULT_23	"mediatek/mt7996/mt7992_eeprom_23.bin"
 #define MT7992_EEPROM_DEFAULT_23_INT	"mediatek/mt7996/mt7992_eeprom_23_2i5i.bin"
 
+#define MT7990_EEPROM_DEFAULT		"mediatek/mt7996/mt7990_eeprom.bin"
+#define MT7990_EEPROM_DEFAULT_INT	"mediatek/mt7996/mt7990_eeprom_2i5i.bin"
+
 #define MT7996_EEPROM_SIZE		7680
 #define MT7996_EEPROM_BLOCK_SIZE	16
 #define MT7996_TOKEN_SIZE		16384
@@ -131,6 +149,10 @@ enum mt7992_var_type {
 	MT7992_VAR_TYPE_23,
 };
 
+enum mt7990_var_type {
+	MT7990_VAR_TYPE_23,
+};
+
 enum mt7996_fem_type {
 	MT7996_FEM_EXT,
 	MT7996_FEM_INT,
@@ -165,6 +187,8 @@ enum mt7996_rxq_id {
 	MT7996_RXQ_TXFREE1 = 9,
 	MT7996_RXQ_TXFREE2 = 7,
 	MT7996_RXQ_RRO_IND = 0,
+	MT7990_RXQ_TXFREE0 = 6,
+	MT7990_RXQ_TXFREE1 = 7,
 };
 
 struct mt7996_twt_flow {
@@ -281,8 +305,6 @@ struct mt7996_phy {
 	s16 coverage_class;
 	u8 slottime;
 
-	u8 rdd_state;
-
 	u16 beacon_rate;
 
 	u32 rx_ampdu_ts;
@@ -293,6 +315,7 @@ struct mt7996_phy {
 	struct mt76_channel_state state_ts;
 
 	u16 orig_chainmask;
+	u16 orig_antenna_mask;
 
 	bool has_aux_rx;
 	bool counter_reset;
@@ -405,10 +428,10 @@ enum {
 	__MT_WFDMA_MAX,
 };
 
-enum {
-	MT_RX_SEL0,
-	MT_RX_SEL1,
-	MT_RX_SEL2, /* monitor chain */
+enum rdd_idx {
+	MT_RDD_IDX_BAND2,	/* RDD idx for band idx 2 */
+	MT_RDD_IDX_BAND1,	/* RDD idx for band idx 1 */
+	MT_RDD_IDX_BACKGROUND,	/* RDD idx for background chain */
 };
 
 enum mt7996_rdd_cmd {
@@ -427,6 +450,21 @@ enum mt7996_rdd_cmd {
 	RDD_IRQ_OFF,
 };
 
+static inline int
+mt7996_get_rdd_idx(struct mt7996_phy *phy, bool is_background)
+{
+	if (!phy->mt76->cap.has_5ghz)
+		return -1;
+
+	if (is_background)
+		return MT_RDD_IDX_BACKGROUND;
+
+	if (phy->mt76->band_idx == MT_BAND2)
+		return MT_RDD_IDX_BAND2;
+
+	return MT_RDD_IDX_BAND1;
+}
+
 static inline struct mt7996_dev *
 mt7996_hw_dev(struct ieee80211_hw *hw)
 {
@@ -461,31 +499,12 @@ mt7996_phy3(struct mt7996_dev *dev)
 static inline bool
 mt7996_band_valid(struct mt7996_dev *dev, u8 band)
 {
-	if (is_mt7992(&dev->mt76))
+	if (!is_mt7996(&dev->mt76))
 		return band <= MT_BAND1;
 
 	return band <= MT_BAND2;
 }
 
-static inline bool
-mt7996_has_background_radar(struct mt7996_dev *dev)
-{
-	switch (mt76_chip(&dev->mt76)) {
-	case 0x7990:
-		if (dev->var.type == MT7996_VAR_TYPE_233)
-			return false;
-		break;
-	case 0x7992:
-		if (dev->var.type == MT7992_VAR_TYPE_23)
-			return false;
-		break;
-	default:
-		return false;
-	}
-
-	return true;
-}
-
 static inline struct mt7996_phy *
 mt7996_band_phy(struct mt7996_dev *dev, enum nl80211_band band)
 {
@@ -549,6 +568,7 @@ int mt7996_eeprom_parse_hw_cap(struct mt7996_dev *dev, struct mt7996_phy *phy);
 int mt7996_eeprom_get_target_power(struct mt7996_dev *dev,
 				   struct ieee80211_channel *chan);
 s8 mt7996_eeprom_get_power_delta(struct mt7996_dev *dev, int band);
+bool mt7996_eeprom_has_background_radar(struct mt7996_dev *dev);
 int mt7996_dma_init(struct mt7996_dev *dev);
 void mt7996_dma_reset(struct mt7996_dev *dev, bool force);
 void mt7996_dma_prefetch(struct mt7996_dev *dev);
@@ -637,8 +657,7 @@ int mt7996_mcu_get_temperature(struct mt7996_phy *phy);
 int mt7996_mcu_set_thermal_throttling(struct mt7996_phy *phy, u8 state);
 int mt7996_mcu_set_thermal_protect(struct mt7996_phy *phy, bool enable);
 int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy);
-int mt7996_mcu_rdd_cmd(struct mt7996_dev *dev, int cmd, u8 index,
-		       u8 rx_sel, u8 val);
+int mt7996_mcu_rdd_cmd(struct mt7996_dev *dev, int cmd, u8 rdd_idx, u8 val);
 int mt7996_mcu_rdd_background_enable(struct mt7996_phy *phy,
 				     struct cfg80211_chan_def *chandef);
 int mt7996_mcu_set_fixed_rate_table(struct mt7996_phy *phy, u8 table_idx,
@@ -704,6 +723,11 @@ static inline u16 mt7996_rx_chainmask(struct mt7996_phy *phy)
 	return tx_chainmask | (BIT(fls(tx_chainmask)) * phy->has_aux_rx);
 }
 
+static inline bool mt7996_has_wa(struct mt7996_dev *dev)
+{
+	return !is_mt7990(&dev->mt76);
+}
+
 void mt7996_mac_init(struct mt7996_dev *dev);
 u32 mt7996_mac_wtbl_lmac_addr(struct mt7996_dev *dev, u16 wcid, u8 dw);
 bool mt7996_mac_wtbl_update(struct mt7996_dev *dev, int idx, u32 mask);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/pci.c b/drivers/net/wireless/mediatek/mt76/mt7996/pci.c
index 04056181368a..19e99bc1c6c4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/pci.c
@@ -16,14 +16,16 @@ static DEFINE_SPINLOCK(hif_lock);
 static u32 hif_idx;
 
 static const struct pci_device_id mt7996_pci_device_table[] = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7990) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7992) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, MT7996_DEVICE_ID) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, MT7992_DEVICE_ID) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, MT7990_DEVICE_ID) },
 	{ },
 };
 
 static const struct pci_device_id mt7996_hif_device_table[] = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7991) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x799a) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, MT7996_DEVICE_ID_2) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, MT7992_DEVICE_ID_2) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, MT7990_DEVICE_ID_2) },
 	{ },
 };
 
@@ -63,8 +65,9 @@ static struct mt7996_hif *mt7996_pci_init_hif2(struct pci_dev *pdev)
 {
 	hif_idx++;
 
-	if (!pci_get_device(PCI_VENDOR_ID_MEDIATEK, 0x7991, NULL) &&
-	    !pci_get_device(PCI_VENDOR_ID_MEDIATEK, 0x799a, NULL))
+	if (!pci_get_device(PCI_VENDOR_ID_MEDIATEK, MT7996_DEVICE_ID_2, NULL) &&
+	    !pci_get_device(PCI_VENDOR_ID_MEDIATEK, MT7992_DEVICE_ID_2, NULL) &&
+	    !pci_get_device(PCI_VENDOR_ID_MEDIATEK, MT7990_DEVICE_ID_2, NULL))
 		return NULL;
 
 	writel(hif_idx | MT_PCIE_RECOG_ID_SEM,
@@ -121,7 +124,9 @@ static int mt7996_pci_probe(struct pci_dev *pdev,
 
 	mt76_pci_disable_aspm(pdev);
 
-	if (id->device == 0x7991 || id->device == 0x799a)
+	if (id->device == MT7996_DEVICE_ID_2 ||
+	    id->device == MT7992_DEVICE_ID_2 ||
+	    id->device == MT7990_DEVICE_ID_2)
 		return mt7996_pci_hif2_probe(pdev);
 
 	dev = mt7996_mmio_probe(&pdev->dev, pcim_iomap_table(pdev)[0],
@@ -256,3 +261,5 @@ MODULE_FIRMWARE(MT7992_FIRMWARE_WA);
 MODULE_FIRMWARE(MT7992_FIRMWARE_WM);
 MODULE_FIRMWARE(MT7992_FIRMWARE_DSP);
 MODULE_FIRMWARE(MT7992_ROM_PATCH);
+MODULE_FIRMWARE(MT7990_FIRMWARE_WM);
+MODULE_FIRMWARE(MT7990_ROM_PATCH);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/regs.h b/drivers/net/wireless/mediatek/mt76/mt7996/regs.h
index 1876a968c92d..e942c0058731 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/regs.h
@@ -64,6 +64,17 @@ enum offs_rev {
 	MIB_BSCR7,
 	MIB_BSCR17,
 	MIB_TRDR1,
+	HIF_REMAP_L1,
+	HIF_REMAP_BASE_L1,
+	HIF_REMAP_L2,
+	HIF_REMAP_BASE_L2,
+	CBTOP1_PHY_END,
+	INFRA_MCU_END,
+	WTBLON_WDUCR,
+	WTBL_UPDATE,
+	WTBL_ITCR,
+	WTBL_ITCR0,
+	WTBL_ITCR1,
 	__MT_OFFS_MAX,
 };
 
@@ -291,19 +302,19 @@ enum offs_rev {
 /* WTBLON TOP */
 #define MT_WTBLON_TOP_BASE			0x820d4000
 #define MT_WTBLON_TOP(ofs)			(MT_WTBLON_TOP_BASE + (ofs))
-#define MT_WTBLON_TOP_WDUCR			MT_WTBLON_TOP(0x370)
+#define MT_WTBLON_TOP_WDUCR			MT_WTBLON_TOP(__OFFS(WTBLON_WDUCR))
 #define MT_WTBLON_TOP_WDUCR_GROUP		GENMASK(4, 0)
 
-#define MT_WTBL_UPDATE				MT_WTBLON_TOP(0x380)
+#define MT_WTBL_UPDATE				MT_WTBLON_TOP(__OFFS(WTBL_UPDATE))
 #define MT_WTBL_UPDATE_WLAN_IDX			GENMASK(11, 0)
 #define MT_WTBL_UPDATE_ADM_COUNT_CLEAR		BIT(14)
 #define MT_WTBL_UPDATE_BUSY			BIT(31)
 
-#define MT_WTBL_ITCR				MT_WTBLON_TOP(0x3b0)
+#define MT_WTBL_ITCR				MT_WTBLON_TOP(__OFFS(WTBL_ITCR))
 #define MT_WTBL_ITCR_WR				BIT(16)
 #define MT_WTBL_ITCR_EXEC			BIT(31)
-#define MT_WTBL_ITDR0				MT_WTBLON_TOP(0x3b8)
-#define MT_WTBL_ITDR1				MT_WTBLON_TOP(0x3bc)
+#define MT_WTBL_ITDR0				MT_WTBLON_TOP(__OFFS(WTBL_ITCR0))
+#define MT_WTBL_ITDR1				MT_WTBLON_TOP(__OFFS(WTBL_ITCR1))
 #define MT_WTBL_SPE_IDX_SEL			BIT(6)
 
 /* WTBL */
@@ -483,7 +494,7 @@ enum offs_rev {
 
 #define MT_MCUQ_EXT_CTRL(q)			(MT_Q_BASE(q) +	0x600 +	\
 						 MT_MCUQ_ID(q) * 0x4)
-#define MT_RXQ_BAND1_CTRL(q)			(MT_Q_BASE(__RXQ(q)) + 0x680 +	\
+#define MT_RXQ_EXT_CTRL(q)			(MT_Q_BASE(__RXQ(q)) + 0x680 +	\
 						 MT_RXQ_ID(q) * 0x4)
 #define MT_TXQ_EXT_CTRL(q)			(MT_Q_BASE(__TXQ(q)) + 0x600 +	\
 						 MT_TXQ_ID(q) * 0x4)
@@ -504,6 +515,8 @@ enum offs_rev {
 #define MT_INT_RX_DONE_WA_TRI			BIT(3)
 #define MT_INT_RX_TXFREE_MAIN			BIT(17)
 #define MT_INT_RX_TXFREE_TRI			BIT(15)
+#define MT_INT_RX_TXFREE_BAND0_MT7990		BIT(14)
+#define MT_INT_RX_TXFREE_BAND1_MT7990		BIT(15)
 #define MT_INT_RX_DONE_BAND2_EXT		BIT(23)
 #define MT_INT_RX_TXFREE_EXT			BIT(26)
 #define MT_INT_MCU_CMD				BIT(29)
@@ -576,27 +589,39 @@ enum offs_rev {
 #define MT_MCU_CMD_WDT_MASK			GENMASK(31, 30)
 
 /* l1/l2 remap */
-#define MT_HIF_REMAP_L1				0x155024
-#define MT_HIF_REMAP_L1_MASK			GENMASK(31, 16)
+#define CONN_BUS_CR_VON_BASE			0x155000
+#define MT_HIF_REMAP_L1				(CONN_BUS_CR_VON_BASE + __OFFS(HIF_REMAP_L1))
+#define MT_HIF_REMAP_L1_MASK_7996		GENMASK(31, 16)
+#define MT_HIF_REMAP_L1_MASK			GENMASK(15, 0)
 #define MT_HIF_REMAP_L1_OFFSET			GENMASK(15, 0)
 #define MT_HIF_REMAP_L1_BASE			GENMASK(31, 16)
-#define MT_HIF_REMAP_BASE_L1			0x130000
+#define MT_HIF_REMAP_BASE_L1			__OFFS(HIF_REMAP_BASE_L1)
 
-#define MT_HIF_REMAP_L2				0x1b4
+#define MT_HIF_REMAP_L2				__OFFS(HIF_REMAP_L2)
 #define MT_HIF_REMAP_L2_MASK			GENMASK(19, 0)
 #define MT_HIF_REMAP_L2_OFFSET			GENMASK(11, 0)
 #define MT_HIF_REMAP_L2_BASE			GENMASK(31, 12)
-#define MT_HIF_REMAP_BASE_L2			0x1000
+#define MT_HIF_REMAP_L2_MASK_7990		GENMASK(15, 0)
+#define MT_HIF_REMAP_L2_OFFSET_7990		GENMASK(15, 0)
+#define MT_HIF_REMAP_L2_BASE_7990		GENMASK(31, 16)
+#define MT_HIF_REMAP_BASE_L2			__OFFS(HIF_REMAP_BASE_L2)
+
+/* for mt7990 only */
+#define MT_HIF_REMAP_CBTOP			0x1f6554
+#define MT_HIF_REMAP_CBTOP_MASK			GENMASK(15, 0)
+#define MT_HIF_REMAP_CBTOP_OFFSET		GENMASK(15, 0)
+#define MT_HIF_REMAP_CBTOP_BASE			GENMASK(31, 16)
+#define MT_HIF_REMAP_BASE_CBTOP			0x1c0000
 
 #define MT_INFRA_BASE				0x18000000
 #define MT_WFSYS0_PHY_START			0x18400000
 #define MT_WFSYS1_PHY_START			0x18800000
 #define MT_WFSYS1_PHY_END			0x18bfffff
 #define MT_CBTOP1_PHY_START			0x70000000
-#define MT_CBTOP1_PHY_END			0x77ffffff
+#define MT_CBTOP1_PHY_END			__OFFS(CBTOP1_PHY_END)
 #define MT_CBTOP2_PHY_START			0xf0000000
 #define MT_INFRA_MCU_START			0x7c000000
-#define MT_INFRA_MCU_END			0x7c3fffff
+#define MT_INFRA_MCU_END			__OFFS(INFRA_MCU_END)
 
 /* FW MODE SYNC */
 #define MT_FW_ASSERT_CNT			0x02208274
diff --git a/drivers/net/wireless/purelifi/plfxlc/mac.c b/drivers/net/wireless/purelifi/plfxlc/mac.c
index eae93efa6150..82d1bf7edba2 100644
--- a/drivers/net/wireless/purelifi/plfxlc/mac.c
+++ b/drivers/net/wireless/purelifi/plfxlc/mac.c
@@ -102,7 +102,6 @@ int plfxlc_mac_init_hw(struct ieee80211_hw *hw)
 void plfxlc_mac_release(struct plfxlc_mac *mac)
 {
 	plfxlc_chip_release(&mac->chip);
-	lockdep_assert_held(&mac->lock);
 }
 
 int plfxlc_op_start(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/purelifi/plfxlc/usb.c b/drivers/net/wireless/purelifi/plfxlc/usb.c
index 10d2e2124ff8..c2a1234b59db 100644
--- a/drivers/net/wireless/purelifi/plfxlc/usb.c
+++ b/drivers/net/wireless/purelifi/plfxlc/usb.c
@@ -503,8 +503,10 @@ int plfxlc_usb_wreq_async(struct plfxlc_usb *usb, const u8 *buffer,
 			  (void *)buffer, buffer_len, complete_fn, context);
 
 	r = usb_submit_urb(urb, GFP_ATOMIC);
-	if (r)
+	if (r) {
+		usb_free_urb(urb);
 		dev_err(&udev->dev, "Async write submit failed (%d)\n", r);
+	}
 
 	return r;
 }
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
index e5f553a1ea24..b7ea606bda08 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
@@ -9393,7 +9393,7 @@ static void rt2800_loft_search(struct rt2x00_dev *rt2x00dev, u8 ch_idx,
 				   p0, p1, pf, idx0, idx1, ibit);
 
 			if (bidx != 5 && pf <= p0 && pf < p1) {
-				idxf[iorq] = idxf[iorq];
+				/* no need to adjust idxf[] */;
 			} else if (p0 < p1) {
 				pf = p0;
 				idxf[iorq] = idx0 & 0x3F;
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index 7537f04b1930..819cf519e66e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -58,17 +58,6 @@ void rtl_rfreg_delay(struct ieee80211_hw *hw, enum radio_path rfpath, u32 addr,
 }
 EXPORT_SYMBOL(rtl_rfreg_delay);
 
-void rtl_bb_delay(struct ieee80211_hw *hw, u32 addr, u32 data)
-{
-	if (addr >= 0xf9 && addr <= 0xfe) {
-		rtl_addr_delay(addr);
-	} else {
-		rtl_set_bbreg(hw, addr, MASKDWORD, data);
-		udelay(1);
-	}
-}
-EXPORT_SYMBOL(rtl_bb_delay);
-
 static void rtl_fw_do_work(const struct firmware *firmware, void *context,
 			   bool is_wow)
 {
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.h b/drivers/net/wireless/realtek/rtlwifi/core.h
index 42c2d9e13bb8..45225d89ac5e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.h
+++ b/drivers/net/wireless/realtek/rtlwifi/core.h
@@ -58,7 +58,6 @@ void rtl_wowlan_fw_cb(const struct firmware *firmware, void *context);
 void rtl_addr_delay(u32 addr);
 void rtl_rfreg_delay(struct ieee80211_hw *hw, enum radio_path rfpath, u32 addr,
 		     u32 mask, u32 data);
-void rtl_bb_delay(struct ieee80211_hw *hw, u32 addr, u32 data);
 bool rtl_cmd_send_packet(struct ieee80211_hw *hw, struct sk_buff *skb);
 bool rtl_btc_status_false(void);
 void rtl_dm_diginit(struct ieee80211_hw *hw, u32 cur_igval);
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index 0eafc4d125f9..898f597f70a9 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -155,6 +155,16 @@ static void _rtl_pci_update_default_setting(struct ieee80211_hw *hw)
 	    ((u8)init_aspm) == (PCI_EXP_LNKCTL_ASPM_L0S |
 				PCI_EXP_LNKCTL_ASPM_L1 | PCI_EXP_LNKCTL_CCC))
 		ppsc->support_aspm = false;
+
+	/* RTL8723BE found on some ASUSTek laptops, such as F441U and
+	 * X555UQ with subsystem ID 11ad:1723 are known to output large
+	 * amounts of PCIe AER errors during and after boot up, causing
+	 * heavy lags, poor network throughput, and occasional lock-ups.
+	 */
+	if (rtlpriv->rtlhal.hw_type == HARDWARE_TYPE_RTL8723BE &&
+	    (rtlpci->pdev->subsystem_vendor == 0x11ad &&
+	     rtlpci->pdev->subsystem_device == 0x1723))
+		ppsc->support_aspm = false;
 }
 
 static bool _rtl_pci_platform_switch_device_pci_aspm(
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
index e07402e73ba3..68f890050afb 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
@@ -2055,11 +2055,6 @@ void rtl92d_phy_lc_calibrate(struct ieee80211_hw *hw, bool is2t)
 	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "LCK:Finish!!!\n");
 }
 
-void rtl92d_phy_ap_calibrate(struct ieee80211_hw *hw, s8 delta)
-{
-	return;
-}
-
 static bool _rtl92d_phy_set_sw_chnl_cmdarray(struct swchnlcmd *cmdtable,
 		u32 cmdtableidx, u32 cmdtablesz, enum swchnlcmd_id cmdid,
 		u32 para1, u32 para2, u32 msdelay)
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.h
index bbe9ef77225e..a9bfe54f2802 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.h
@@ -83,7 +83,6 @@ void rtl92d_phy_set_poweron(struct ieee80211_hw *hw);
 bool rtl92d_phy_check_poweroff(struct ieee80211_hw *hw);
 void rtl92d_phy_lc_calibrate(struct ieee80211_hw *hw, bool is2t);
 void rtl92d_update_bbrf_configuration(struct ieee80211_hw *hw);
-void rtl92d_phy_ap_calibrate(struct ieee80211_hw *hw, s8 delta);
 void rtl92d_phy_iq_calibrate(struct ieee80211_hw *hw);
 void rtl92d_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.c
index 289ec71ce3e5..8c2167cc1f13 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.c
@@ -2445,11 +2445,6 @@ void rtl92du_phy_lc_calibrate(struct ieee80211_hw *hw, bool is2t)
 	RTPRINT(rtlpriv, FINIT, INIT_IQK,  "LCK:Finish!!!\n");
 }
 
-void rtl92du_phy_ap_calibrate(struct ieee80211_hw *hw, s8 delta)
-{
-	/* Nothing to do. */
-}
-
 u8 rtl92du_phy_sw_chnl(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.h
index 090a6203db7e..a107a5a76beb 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/phy.h
@@ -24,7 +24,6 @@ void rtl92du_phy_set_poweron(struct ieee80211_hw *hw);
 bool rtl92du_phy_check_poweroff(struct ieee80211_hw *hw);
 void rtl92du_phy_lc_calibrate(struct ieee80211_hw *hw, bool is2t);
 void rtl92du_update_bbrf_configuration(struct ieee80211_hw *hw);
-void rtl92du_phy_ap_calibrate(struct ieee80211_hw *hw, s8 delta);
 void rtl92du_phy_iq_calibrate(struct ieee80211_hw *hw);
 void rtl92du_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel);
 void rtl92du_phy_init_pa_bias(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
index 73ef602bfb01..1e7f0cd1c86e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
@@ -2926,10 +2926,6 @@ void rtl92ee_phy_lc_calibrate(struct ieee80211_hw *hw)
 	rtlphy->lck_inprogress = false;
 }
 
-void rtl92ee_phy_ap_calibrate(struct ieee80211_hw *hw, s8 delta)
-{
-}
-
 void rtl92ee_phy_set_rfpath_switch(struct ieee80211_hw *hw, bool bmain)
 {
 	_rtl92ee_phy_set_rfpath_switch(hw, bmain, false);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.h
index 1a5dbc628379..ec4c26b81c48 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.h
@@ -119,7 +119,6 @@ void rtl92ee_phy_set_bw_mode(struct ieee80211_hw *hw,
 void rtl92ee_phy_sw_chnl_callback(struct ieee80211_hw *hw);
 u8 rtl92ee_phy_sw_chnl(struct ieee80211_hw *hw);
 void rtl92ee_phy_iq_calibrate(struct ieee80211_hw *hw, bool b_recovery);
-void rtl92ee_phy_ap_calibrate(struct ieee80211_hw *hw, s8 delta);
 void rtl92ee_phy_lc_calibrate(struct ieee80211_hw *hw);
 void rtl92ee_phy_set_rfpath_switch(struct ieee80211_hw *hw, bool bmain);
 bool rtl92ee_phy_config_rf_with_headerfile(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
index 9eddbada8af1..13a05066e8a6 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
@@ -4586,10 +4586,6 @@ void rtl8821ae_phy_lc_calibrate(struct ieee80211_hw *hw)
 {
 }
 
-void rtl8821ae_phy_ap_calibrate(struct ieee80211_hw *hw, s8 delta)
-{
-}
-
 void rtl8821ae_phy_set_rfpath_switch(struct ieee80211_hw *hw, bool bmain)
 {
 	_rtl8821ae_phy_set_rfpath_switch(hw, bmain);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.h
index 35b7d0f70125..90bf5462a3f8 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.h
@@ -214,7 +214,6 @@ void rtl8821ae_phy_iq_calibrate(struct ieee80211_hw *hw,
 				bool b_recovery);
 void rtl8812ae_phy_iq_calibrate(struct ieee80211_hw *hw,
 				bool b_recovery);
-void rtl8821ae_phy_ap_calibrate(struct ieee80211_hw *hw, s8 delta);
 void rtl8821ae_phy_lc_calibrate(struct ieee80211_hw *hw);
 void rtl8821ae_phy_set_rfpath_switch(struct ieee80211_hw *hw, bool bmain);
 bool rtl8812ae_phy_config_rf_with_headerfile(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c
index f5718e570011..d35ed56d6db9 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.c
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.c
@@ -1077,15 +1077,3 @@ void rtl_usb_disconnect(struct usb_interface *intf)
 	ieee80211_free_hw(hw);
 }
 EXPORT_SYMBOL(rtl_usb_disconnect);
-
-int rtl_usb_suspend(struct usb_interface *pusb_intf, pm_message_t message)
-{
-	return 0;
-}
-EXPORT_SYMBOL(rtl_usb_suspend);
-
-int rtl_usb_resume(struct usb_interface *pusb_intf)
-{
-	return 0;
-}
-EXPORT_SYMBOL(rtl_usb_resume);
diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.h b/drivers/net/wireless/realtek/rtlwifi/usb.h
index b66d6f9ae564..b873bbc9c4c2 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.h
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.h
@@ -138,7 +138,5 @@ int rtl_usb_probe(struct usb_interface *intf,
 		  const struct usb_device_id *id,
 		  const struct rtl_hal_cfg *rtl92cu_hal_cfg);
 void rtl_usb_disconnect(struct usb_interface *intf);
-int rtl_usb_suspend(struct usb_interface *pusb_intf, pm_message_t message);
-int rtl_usb_resume(struct usb_interface *pusb_intf);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw88/coex.c b/drivers/net/wireless/realtek/rtw88/coex.c
index c929db1e53ca..64904278ddad 100644
--- a/drivers/net/wireless/realtek/rtw88/coex.c
+++ b/drivers/net/wireless/realtek/rtw88/coex.c
@@ -309,7 +309,7 @@ static void rtw_coex_tdma_timer_base(struct rtw_dev *rtwdev, u8 type)
 {
 	struct rtw_coex *coex = &rtwdev->coex;
 	struct rtw_coex_stat *coex_stat = &coex->stat;
-	u8 para[2] = {0};
+	u8 para[6] = {};
 	u8 times;
 	u16 tbtt_interval = coex_stat->wl_beacon_interval;
 
diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c
index 6b563ac489a7..4fc78b882080 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.c
+++ b/drivers/net/wireless/realtek/rtw88/fw.c
@@ -1466,7 +1466,7 @@ void rtw_add_rsvd_page_sta(struct rtw_dev *rtwdev,
 int rtw_fw_write_data_rsvd_page(struct rtw_dev *rtwdev, u16 pg_addr,
 				u8 *buf, u32 size)
 {
-	u8 bckp[2];
+	u8 bckp[3];
 	u8 val;
 	u16 rsvd_pg_head;
 	u32 bcn_valid_addr;
@@ -1478,6 +1478,8 @@ int rtw_fw_write_data_rsvd_page(struct rtw_dev *rtwdev, u16 pg_addr,
 	if (!size)
 		return -EINVAL;
 
+	bckp[2] = rtw_read8(rtwdev, REG_BCN_CTRL);
+
 	if (rtw_chip_wcpu_11n(rtwdev)) {
 		rtw_write32_set(rtwdev, REG_DWBCN0_CTRL, BIT_BCN_VALID);
 	} else {
@@ -1491,6 +1493,9 @@ int rtw_fw_write_data_rsvd_page(struct rtw_dev *rtwdev, u16 pg_addr,
 	val |= BIT_ENSWBCN >> 8;
 	rtw_write8(rtwdev, REG_CR + 1, val);
 
+	rtw_write8(rtwdev, REG_BCN_CTRL,
+		   (bckp[2] & ~BIT_EN_BCN_FUNCTION) | BIT_DIS_TSF_UDT);
+
 	if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_PCIE) {
 		val = rtw_read8(rtwdev, REG_FWHW_TXQ_CTRL + 2);
 		bckp[1] = val;
@@ -1521,6 +1526,7 @@ restore:
 	rsvd_pg_head = rtwdev->fifo.rsvd_boundary;
 	rtw_write16(rtwdev, REG_FIFOPAGE_CTRL_2,
 		    rsvd_pg_head | BIT_BCN_VALID_V1);
+	rtw_write8(rtwdev, REG_BCN_CTRL, bckp[2]);
 	if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_PCIE)
 		rtw_write8(rtwdev, REG_FWHW_TXQ_CTRL + 2, bckp[1]);
 	rtw_write8(rtwdev, REG_CR + 1, bckp[0]);
diff --git a/drivers/net/wireless/realtek/rtw88/hci.h b/drivers/net/wireless/realtek/rtw88/hci.h
index 96aeda26014e..d4bee9c3ecfe 100644
--- a/drivers/net/wireless/realtek/rtw88/hci.h
+++ b/drivers/net/wireless/realtek/rtw88/hci.h
@@ -19,6 +19,8 @@ struct rtw_hci_ops {
 	void (*link_ps)(struct rtw_dev *rtwdev, bool enter);
 	void (*interface_cfg)(struct rtw_dev *rtwdev);
 	void (*dynamic_rx_agg)(struct rtw_dev *rtwdev, bool enable);
+	void (*write_firmware_page)(struct rtw_dev *rtwdev, u32 page,
+				    const u8 *data, u32 size);
 
 	int (*write_data_rsvd_page)(struct rtw_dev *rtwdev, u8 *buf, u32 size);
 	int (*write_data_h2c)(struct rtw_dev *rtwdev, u8 *buf, u32 size);
@@ -79,6 +81,12 @@ static inline void rtw_hci_dynamic_rx_agg(struct rtw_dev *rtwdev, bool enable)
 		rtwdev->hci.ops->dynamic_rx_agg(rtwdev, enable);
 }
 
+static inline void rtw_hci_write_firmware_page(struct rtw_dev *rtwdev, u32 page,
+					       const u8 *data, u32 size)
+{
+	rtwdev->hci.ops->write_firmware_page(rtwdev, page, data, size);
+}
+
 static inline int
 rtw_hci_write_data_rsvd_page(struct rtw_dev *rtwdev, u8 *buf, u32 size)
 {
diff --git a/drivers/net/wireless/realtek/rtw88/mac.c b/drivers/net/wireless/realtek/rtw88/mac.c
index 0491f501c138..f66d1b302dc5 100644
--- a/drivers/net/wireless/realtek/rtw88/mac.c
+++ b/drivers/net/wireless/realtek/rtw88/mac.c
@@ -856,8 +856,8 @@ fwdl_ready:
 	}
 }
 
-static void
-write_firmware_page(struct rtw_dev *rtwdev, u32 page, const u8 *data, u32 size)
+void rtw_write_firmware_page(struct rtw_dev *rtwdev, u32 page,
+			     const u8 *data, u32 size)
 {
 	u32 val32;
 	u32 block_nr;
@@ -887,6 +887,7 @@ write_firmware_page(struct rtw_dev *rtwdev, u32 page, const u8 *data, u32 size)
 		rtw_write32(rtwdev, write_addr, le32_to_cpu(remain_data));
 	}
 }
+EXPORT_SYMBOL(rtw_write_firmware_page);
 
 static int
 download_firmware_legacy(struct rtw_dev *rtwdev, const u8 *data, u32 size)
@@ -904,11 +905,13 @@ download_firmware_legacy(struct rtw_dev *rtwdev, const u8 *data, u32 size)
 	rtw_write8_set(rtwdev, REG_MCUFW_CTRL, BIT_FWDL_CHK_RPT);
 
 	for (page = 0; page < total_page; page++) {
-		write_firmware_page(rtwdev, page, data, DLFW_PAGE_SIZE_LEGACY);
+		rtw_hci_write_firmware_page(rtwdev, page, data,
+					    DLFW_PAGE_SIZE_LEGACY);
 		data += DLFW_PAGE_SIZE_LEGACY;
 	}
 	if (last_page_size)
-		write_firmware_page(rtwdev, page, data, last_page_size);
+		rtw_hci_write_firmware_page(rtwdev, page, data,
+					    last_page_size);
 
 	if (!check_hw_ready(rtwdev, REG_MCUFW_CTRL, BIT_FWDL_CHK_RPT, 1)) {
 		rtw_err(rtwdev, "failed to check download firmware report\n");
diff --git a/drivers/net/wireless/realtek/rtw88/mac.h b/drivers/net/wireless/realtek/rtw88/mac.h
index 6905e2747372..e92b1483728d 100644
--- a/drivers/net/wireless/realtek/rtw88/mac.h
+++ b/drivers/net/wireless/realtek/rtw88/mac.h
@@ -34,6 +34,8 @@ int rtw_pwr_seq_parser(struct rtw_dev *rtwdev,
 		       const struct rtw_pwr_seq_cmd * const *cmd_seq);
 int rtw_mac_power_on(struct rtw_dev *rtwdev);
 void rtw_mac_power_off(struct rtw_dev *rtwdev);
+void rtw_write_firmware_page(struct rtw_dev *rtwdev, u32 page,
+			     const u8 *data, u32 size);
 int rtw_download_firmware(struct rtw_dev *rtwdev, struct rtw_fw_state *fw);
 int rtw_mac_init(struct rtw_dev *rtwdev);
 void rtw_mac_flush_queues(struct rtw_dev *rtwdev, u32 queues, bool drop);
diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c
index 026fbf4ad9cc..77f9fbe1870c 100644
--- a/drivers/net/wireless/realtek/rtw88/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw88/mac80211.c
@@ -396,6 +396,8 @@ static void rtw_ops_bss_info_changed(struct ieee80211_hw *hw,
 			if (rtw_bf_support)
 				rtw_bf_assoc(rtwdev, vif, conf);
 
+			rtw_set_ampdu_factor(rtwdev, vif, conf);
+
 			rtw_fw_beacon_filter_config(rtwdev, true, vif);
 		} else {
 			rtw_leave_lps(rtwdev);
diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 959f56a3cc1a..c4de5d114eda 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -2242,7 +2242,8 @@ int rtw_register_hw(struct rtw_dev *rtwdev, struct ieee80211_hw *hw)
 	ieee80211_hw_set(hw, SUPPORTS_PS);
 	ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS);
 	ieee80211_hw_set(hw, SUPPORT_FAST_XMIT);
-	ieee80211_hw_set(hw, SUPPORTS_AMSDU_IN_AMPDU);
+	if (rtwdev->chip->amsdu_in_ampdu)
+		ieee80211_hw_set(hw, SUPPORTS_AMSDU_IN_AMPDU);
 	ieee80211_hw_set(hw, HAS_RATE_CONTROL);
 	ieee80211_hw_set(hw, TX_AMSDU);
 	ieee80211_hw_set(hw, SINGLE_SCAN_ON_ALL_BANDS);
@@ -2447,6 +2448,38 @@ void rtw_core_enable_beacon(struct rtw_dev *rtwdev, bool enable)
 	}
 }
 
+void rtw_set_ampdu_factor(struct rtw_dev *rtwdev, struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *bss_conf)
+{
+	const struct rtw_chip_ops *ops = rtwdev->chip->ops;
+	struct ieee80211_sta *sta;
+	u8 factor = 0xff;
+
+	if (!ops->set_ampdu_factor)
+		return;
+
+	rcu_read_lock();
+
+	sta = ieee80211_find_sta(vif, bss_conf->bssid);
+	if (!sta) {
+		rcu_read_unlock();
+		rtw_warn(rtwdev, "%s: failed to find station %pM\n",
+			 __func__, bss_conf->bssid);
+		return;
+	}
+
+	if (sta->deflink.vht_cap.vht_supported)
+		factor = u32_get_bits(sta->deflink.vht_cap.cap,
+				      IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK);
+	else if (sta->deflink.ht_cap.ht_supported)
+		factor = sta->deflink.ht_cap.ampdu_factor;
+
+	rcu_read_unlock();
+
+	if (factor != 0xff)
+		ops->set_ampdu_factor(rtwdev, factor);
+}
+
 MODULE_AUTHOR("Realtek Corporation");
 MODULE_DESCRIPTION("Realtek 802.11ac wireless core module");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index 02343e059fd9..b0f1fabe9554 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -878,6 +878,7 @@ struct rtw_chip_ops {
 			   u32 antenna_rx);
 	void (*cfg_ldo25)(struct rtw_dev *rtwdev, bool enable);
 	void (*efuse_grant)(struct rtw_dev *rtwdev, bool enable);
+	void (*set_ampdu_factor)(struct rtw_dev *rtwdev, u8 factor);
 	void (*false_alarm_statistics)(struct rtw_dev *rtwdev);
 	void (*phy_calibration)(struct rtw_dev *rtwdev);
 	void (*dpk_track)(struct rtw_dev *rtwdev);
@@ -1229,6 +1230,7 @@ struct rtw_chip_info {
 	u16 fw_fifo_addr[RTW_FW_FIFO_MAX];
 	const struct rtw_fwcd_segs *fwcd_segs;
 
+	bool amsdu_in_ampdu;
 	u8 usb_tx_agg_desc_num;
 	bool hw_feature_report;
 	u8 c2h_ra_report_size;
@@ -2272,4 +2274,6 @@ void rtw_update_channel(struct rtw_dev *rtwdev, u8 center_channel,
 void rtw_core_port_switch(struct rtw_dev *rtwdev, struct ieee80211_vif *vif);
 bool rtw_core_check_sta_active(struct rtw_dev *rtwdev);
 void rtw_core_enable_beacon(struct rtw_dev *rtwdev, bool enable);
+void rtw_set_ampdu_factor(struct rtw_dev *rtwdev, struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *bss_conf);
 #endif
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index bb4c4ccb31d4..7f2b6dc21f56 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -12,6 +12,7 @@
 #include "fw.h"
 #include "ps.h"
 #include "debug.h"
+#include "mac.h"
 
 static bool rtw_disable_msi;
 static bool rtw_pci_disable_aspm;
@@ -1602,6 +1603,7 @@ static const struct rtw_hci_ops rtw_pci_ops = {
 	.link_ps = rtw_pci_link_ps,
 	.interface_cfg = rtw_pci_interface_cfg,
 	.dynamic_rx_agg = NULL,
+	.write_firmware_page = rtw_write_firmware_page,
 
 	.read8 = rtw_pci_read8,
 	.read16 = rtw_pci_read16,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8703b.c b/drivers/net/wireless/realtek/rtw88/rtw8703b.c
index 1d232adbdd7e..9e6700c43a63 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8703b.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8703b.c
@@ -519,15 +519,6 @@ static const struct rtw_rqpn rqpn_table_8703b[] = {
 	 RTW_DMA_MAPPING_EXTRA, RTW_DMA_MAPPING_HIGH},
 };
 
-/* Default power index table for RTL8703B, used if EFUSE does not
- * contain valid data. Replaces EFUSE data from offset 0x10 (start of
- * txpwr_idx_table).
- */
-static const u8 rtw8703b_txpwr_idx_table[] = {
-	0x2D, 0x2D, 0x2D, 0x2D, 0x2D, 0x2D,
-	0x2D, 0x2D, 0x2D, 0x2D, 0x2D, 0x02
-};
-
 static void try_mac_from_devicetree(struct rtw_dev *rtwdev)
 {
 	struct device_node *node = rtwdev->dev->of_node;
@@ -544,15 +535,9 @@ static void try_mac_from_devicetree(struct rtw_dev *rtwdev)
 	}
 }
 
-#define DBG_EFUSE_FIX(rtwdev, name)					\
-	rtw_dbg(rtwdev, RTW_DBG_EFUSE, "Fixed invalid EFUSE value: "	\
-		# name "=0x%x\n", rtwdev->efuse.name)
-
 static int rtw8703b_read_efuse(struct rtw_dev *rtwdev, u8 *log_map)
 {
 	struct rtw_efuse *efuse = &rtwdev->efuse;
-	u8 *pwr = (u8 *)efuse->txpwr_idx_table;
-	bool valid = false;
 	int ret;
 
 	ret = rtw8723x_read_efuse(rtwdev, log_map);
@@ -562,51 +547,6 @@ static int rtw8703b_read_efuse(struct rtw_dev *rtwdev, u8 *log_map)
 	if (!is_valid_ether_addr(efuse->addr))
 		try_mac_from_devicetree(rtwdev);
 
-	/* If TX power index table in EFUSE is invalid, fall back to
-	 * built-in table.
-	 */
-	for (int i = 0; i < ARRAY_SIZE(rtw8703b_txpwr_idx_table); i++)
-		if (pwr[i] != 0xff) {
-			valid = true;
-			break;
-		}
-	if (!valid) {
-		for (int i = 0; i < ARRAY_SIZE(rtw8703b_txpwr_idx_table); i++)
-			pwr[i] = rtw8703b_txpwr_idx_table[i];
-		rtw_dbg(rtwdev, RTW_DBG_EFUSE,
-			"Replaced invalid EFUSE TX power index table.");
-		rtw8723x_debug_txpwr_limit(rtwdev,
-					   efuse->txpwr_idx_table, 2);
-	}
-
-	/* Override invalid antenna settings. */
-	if (efuse->bt_setting == 0xff) {
-		/* shared antenna */
-		efuse->bt_setting |= BIT(0);
-		/* RF path A */
-		efuse->bt_setting &= ~BIT(6);
-		DBG_EFUSE_FIX(rtwdev, bt_setting);
-	}
-
-	/* Override invalid board options: The coex code incorrectly
-	 * assumes that if bits 6 & 7 are set the board doesn't
-	 * support coex. Regd is also derived from rf_board_option and
-	 * should be 0 if there's no valid data.
-	 */
-	if (efuse->rf_board_option == 0xff) {
-		efuse->regd = 0;
-		efuse->rf_board_option &= GENMASK(5, 0);
-		DBG_EFUSE_FIX(rtwdev, rf_board_option);
-	}
-
-	/* Override invalid crystal cap setting, default comes from
-	 * vendor driver. Chip specific.
-	 */
-	if (efuse->crystal_cap == 0xff) {
-		efuse->crystal_cap = 0x20;
-		DBG_EFUSE_FIX(rtwdev, crystal_cap);
-	}
-
 	return 0;
 }
 
@@ -1904,6 +1844,7 @@ static const struct rtw_chip_ops rtw8703b_ops = {
 	.set_antenna		= NULL,
 	.cfg_ldo25		= rtw8723x_cfg_ldo25,
 	.efuse_grant		= rtw8723x_efuse_grant,
+	.set_ampdu_factor	= NULL,
 	.false_alarm_statistics	= rtw8723x_false_alarm_statistics,
 	.phy_calibration	= rtw8703b_phy_calibration,
 	.dpk_track		= NULL,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723cs.c b/drivers/net/wireless/realtek/rtw88/rtw8723cs.c
index 8d38d36be8c0..1f98d35a8dd1 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8723cs.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8723cs.c
@@ -19,7 +19,7 @@ static const struct sdio_device_id rtw_8723cs_id_table[] = {
 MODULE_DEVICE_TABLE(sdio, rtw_8723cs_id_table);
 
 static struct sdio_driver rtw_8723cs_driver = {
-	.name = "rtw8723cs",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8723cs_id_table,
 	.probe = rtw_sdio_probe,
 	.remove = rtw_sdio_remove,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723d.c b/drivers/net/wireless/realtek/rtw88/rtw8723d.c
index 87715bd54860..31876e708f9e 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8723d.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8723d.c
@@ -1404,6 +1404,7 @@ static const struct rtw_chip_ops rtw8723d_ops = {
 	.set_antenna		= NULL,
 	.cfg_ldo25		= rtw8723x_cfg_ldo25,
 	.efuse_grant		= rtw8723x_efuse_grant,
+	.set_ampdu_factor	= NULL,
 	.false_alarm_statistics	= rtw8723x_false_alarm_statistics,
 	.phy_calibration	= rtw8723d_phy_calibration,
 	.cck_pd_set		= rtw8723d_phy_cck_pd_set,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723de.c b/drivers/net/wireless/realtek/rtw88/rtw8723de.c
index abbaafa32851..87c8bc9d18a9 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8723de.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8723de.c
@@ -17,7 +17,7 @@ static const struct pci_device_id rtw_8723de_id_table[] = {
 MODULE_DEVICE_TABLE(pci, rtw_8723de_id_table);
 
 static struct pci_driver rtw_8723de_driver = {
-	.name = "rtw_8723de",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8723de_id_table,
 	.probe = rtw_pci_probe,
 	.remove = rtw_pci_remove,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723ds.c b/drivers/net/wireless/realtek/rtw88/rtw8723ds.c
index e5b6960ba0a0..206b77e5b98e 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8723ds.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8723ds.c
@@ -25,7 +25,7 @@ static const struct sdio_device_id rtw_8723ds_id_table[] =  {
 MODULE_DEVICE_TABLE(sdio, rtw_8723ds_id_table);
 
 static struct sdio_driver rtw_8723ds_driver = {
-	.name = "rtw_8723ds",
+	.name = KBUILD_MODNAME,
 	.probe = rtw_sdio_probe,
 	.remove = rtw_sdio_remove,
 	.id_table = rtw_8723ds_id_table,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723du.c b/drivers/net/wireless/realtek/rtw88/rtw8723du.c
index 322a805da76b..b661a26e0e22 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8723du.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8723du.c
@@ -24,7 +24,7 @@ static int rtw8723du_probe(struct usb_interface *intf,
 }
 
 static struct usb_driver rtw_8723du_driver = {
-	.name = "rtw_8723du",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8723du_id_table,
 	.probe = rtw8723du_probe,
 	.disconnect = rtw_usb_disconnect,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723x.c b/drivers/net/wireless/realtek/rtw88/rtw8723x.c
index 69f73cb5b4cd..4c77963fdd37 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8723x.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8723x.c
@@ -69,6 +69,9 @@ static void __rtw8723x_lck(struct rtw_dev *rtwdev)
 #define DBG_EFUSE_2BYTE(rtwdev, map, name)			\
 	rtw_dbg(rtwdev, RTW_DBG_EFUSE, # name "=0x%02x%02x\n",	\
 		(map)->name[0], (map)->name[1])
+#define DBG_EFUSE_FIX(rtwdev, name)					\
+	rtw_dbg(rtwdev, RTW_DBG_EFUSE, "Fixed invalid EFUSE value: "	\
+		# name "=0x%x\n", rtwdev->efuse.name)
 
 static void rtw8723xe_efuse_debug(struct rtw_dev *rtwdev,
 				  struct rtw8723x_efuse *map)
@@ -238,10 +241,21 @@ static void rtw8723xs_efuse_parsing(struct rtw_efuse *efuse,
 	ether_addr_copy(efuse->addr, map->s.mac_addr);
 }
 
+/* Default power index table for RTL8703B/RTL8723D, used if EFUSE does
+ * not contain valid data. Replaces EFUSE data from offset 0x10 (start
+ * of txpwr_idx_table).
+ */
+static const u8 rtw8723x_txpwr_idx_table[] = {
+	0x2D, 0x2D, 0x2D, 0x2D, 0x2D, 0x2D,
+	0x2D, 0x2D, 0x2D, 0x2D, 0x2D, 0x02
+};
+
 static int __rtw8723x_read_efuse(struct rtw_dev *rtwdev, u8 *log_map)
 {
 	struct rtw_efuse *efuse = &rtwdev->efuse;
+	u8 *pwr = (u8 *)efuse->txpwr_idx_table;
 	struct rtw8723x_efuse *map;
+	bool valid = false;
 	int i;
 
 	map = (struct rtw8723x_efuse *)log_map;
@@ -279,6 +293,51 @@ static int __rtw8723x_read_efuse(struct rtw_dev *rtwdev, u8 *log_map)
 		return -EOPNOTSUPP;
 	}
 
+	/* If TX power index table in EFUSE is invalid, fall back to
+	 * built-in table.
+	 */
+	for (i = 0; i < ARRAY_SIZE(rtw8723x_txpwr_idx_table); i++)
+		if (pwr[i] != 0xff) {
+			valid = true;
+			break;
+		}
+	if (!valid) {
+		for (i = 0; i < ARRAY_SIZE(rtw8723x_txpwr_idx_table); i++)
+			pwr[i] = rtw8723x_txpwr_idx_table[i];
+		rtw_dbg(rtwdev, RTW_DBG_EFUSE,
+			"Replaced invalid EFUSE TX power index table.");
+		rtw8723x_debug_txpwr_limit(rtwdev,
+					   efuse->txpwr_idx_table, 2);
+	}
+
+	/* Override invalid antenna settings. */
+	if (efuse->bt_setting == 0xff) {
+		/* shared antenna */
+		efuse->bt_setting |= BIT(0);
+		/* RF path A */
+		efuse->bt_setting &= ~BIT(6);
+		DBG_EFUSE_FIX(rtwdev, bt_setting);
+	}
+
+	/* Override invalid board options: The coex code incorrectly
+	 * assumes that if bits 6 & 7 are set the board doesn't
+	 * support coex. Regd is also derived from rf_board_option and
+	 * should be 0 if there's no valid data.
+	 */
+	if (efuse->rf_board_option == 0xff) {
+		efuse->regd = 0;
+		efuse->rf_board_option &= GENMASK(5, 0);
+		DBG_EFUSE_FIX(rtwdev, rf_board_option);
+	}
+
+	/* Override invalid crystal cap setting, default comes from
+	 * vendor driver. Chip specific.
+	 */
+	if (efuse->crystal_cap == 0xff) {
+		efuse->crystal_cap = 0x20;
+		DBG_EFUSE_FIX(rtwdev, crystal_cap);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8812a.c b/drivers/net/wireless/realtek/rtw88/rtw8812a.c
index f9ba2aa2928a..c2ef41767ff9 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8812a.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8812a.c
@@ -925,6 +925,7 @@ static const struct rtw_chip_ops rtw8812a_ops = {
 	.set_tx_power_index	= rtw88xxa_set_tx_power_index,
 	.cfg_ldo25		= rtw8812a_cfg_ldo25,
 	.efuse_grant		= rtw88xxa_efuse_grant,
+	.set_ampdu_factor	= NULL,
 	.false_alarm_statistics	= rtw88xxa_false_alarm_statistics,
 	.phy_calibration	= rtw8812a_phy_calibration,
 	.cck_pd_set		= rtw88xxa_phy_cck_pd_set,
@@ -1075,6 +1076,7 @@ const struct rtw_chip_info rtw8812a_hw_spec = {
 	.rfe_defs = rtw8812a_rfe_defs,
 	.rfe_defs_size = ARRAY_SIZE(rtw8812a_rfe_defs),
 	.rx_ldpc = false,
+	.amsdu_in_ampdu = true,
 	.hw_feature_report = false,
 	.c2h_ra_report_size = 4,
 	.old_datarate_fb_limit = true,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8812au.c b/drivers/net/wireless/realtek/rtw88/rtw8812au.c
index e18995f4cc78..dfea89670372 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8812au.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8812au.c
@@ -82,7 +82,7 @@ static const struct usb_device_id rtw_8812au_id_table[] = {
 MODULE_DEVICE_TABLE(usb, rtw_8812au_id_table);
 
 static struct usb_driver rtw_8812au_driver = {
-	.name = "rtw_8812au",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8812au_id_table,
 	.probe = rtw_usb_probe,
 	.disconnect = rtw_usb_disconnect,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8814a.c b/drivers/net/wireless/realtek/rtw88/rtw8814a.c
index cfd35d40d46e..44dd3090484b 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8814a.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8814a.c
@@ -1332,6 +1332,16 @@ static void rtw8814a_cfg_ldo25(struct rtw_dev *rtwdev, bool enable)
 {
 }
 
+/* Without this RTL8814A sends too many frames and (some?) 11n AP
+ * can't handle it, resulting in low TX speed. Other chips seem fine.
+ */
+static void rtw8814a_set_ampdu_factor(struct rtw_dev *rtwdev, u8 factor)
+{
+	factor = min_t(u8, factor, IEEE80211_VHT_MAX_AMPDU_256K);
+
+	rtw_write32(rtwdev, REG_AMPDU_MAX_LENGTH, (8192 << factor) - 1);
+}
+
 static void rtw8814a_false_alarm_statistics(struct rtw_dev *rtwdev)
 {
 	struct rtw_dm_info *dm_info = &rtwdev->dm_info;
@@ -2051,6 +2061,7 @@ static const struct rtw_chip_ops rtw8814a_ops = {
 	.set_antenna		= NULL,
 	.cfg_ldo25		= rtw8814a_cfg_ldo25,
 	.efuse_grant		= rtw8814a_efuse_grant,
+	.set_ampdu_factor	= rtw8814a_set_ampdu_factor,
 	.false_alarm_statistics	= rtw8814a_false_alarm_statistics,
 	.phy_calibration	= rtw8814a_phy_calibration,
 	.cck_pd_set		= rtw8814a_phy_cck_pd_set,
@@ -2189,6 +2200,7 @@ const struct rtw_chip_info rtw8814a_hw_spec = {
 	.rx_ldpc = true,
 	.max_power_index = 0x3f,
 	.ampdu_density = IEEE80211_HT_MPDU_DENSITY_2,
+	.amsdu_in_ampdu = false, /* RX speed is better without AMSDU */
 	.usb_tx_agg_desc_num = 3,
 	.hw_feature_report = false,
 	.c2h_ra_report_size = 6,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8814ae.c b/drivers/net/wireless/realtek/rtw88/rtw8814ae.c
index 54d2e20a7764..c7436f1c8d40 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8814ae.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8814ae.c
@@ -17,7 +17,7 @@ static const struct pci_device_id rtw_8814ae_id_table[] = {
 MODULE_DEVICE_TABLE(pci, rtw_8814ae_id_table);
 
 static struct pci_driver rtw_8814ae_driver = {
-	.name = "rtw_8814ae",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8814ae_id_table,
 	.probe = rtw_pci_probe,
 	.remove = rtw_pci_remove,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8814au.c b/drivers/net/wireless/realtek/rtw88/rtw8814au.c
index afe045fb84de..1a0886ec17dd 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8814au.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8814au.c
@@ -42,7 +42,7 @@ static const struct usb_device_id rtw_8814au_id_table[] = {
 MODULE_DEVICE_TABLE(usb, rtw_8814au_id_table);
 
 static struct usb_driver rtw_8814au_driver = {
-	.name = "rtw_8814au",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8814au_id_table,
 	.probe = rtw_usb_probe,
 	.disconnect = rtw_usb_disconnect,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821a.c b/drivers/net/wireless/realtek/rtw88/rtw8821a.c
index f68239b07319..413aec694c33 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821a.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821a.c
@@ -871,6 +871,7 @@ static const struct rtw_chip_ops rtw8821a_ops = {
 	.set_tx_power_index	= rtw88xxa_set_tx_power_index,
 	.cfg_ldo25		= rtw8821a_cfg_ldo25,
 	.efuse_grant		= rtw88xxa_efuse_grant,
+	.set_ampdu_factor	= NULL,
 	.false_alarm_statistics	= rtw88xxa_false_alarm_statistics,
 	.phy_calibration	= rtw8821a_phy_calibration,
 	.cck_pd_set		= rtw88xxa_phy_cck_pd_set,
@@ -1175,6 +1176,7 @@ const struct rtw_chip_info rtw8821a_hw_spec = {
 	.rfe_defs = rtw8821a_rfe_defs,
 	.rfe_defs_size = ARRAY_SIZE(rtw8821a_rfe_defs),
 	.rx_ldpc = false,
+	.amsdu_in_ampdu = true,
 	.hw_feature_report = false,
 	.c2h_ra_report_size = 4,
 	.old_datarate_fb_limit = true,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821au.c b/drivers/net/wireless/realtek/rtw88/rtw8821au.c
index a01744b64e8d..28c281b32978 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821au.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821au.c
@@ -66,7 +66,7 @@ static const struct usb_device_id rtw_8821au_id_table[] = {
 MODULE_DEVICE_TABLE(usb, rtw_8821au_id_table);
 
 static struct usb_driver rtw_8821au_driver = {
-	.name = "rtw_8821au",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8821au_id_table,
 	.probe = rtw_usb_probe,
 	.disconnect = rtw_usb_disconnect,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
index 0ade7f11cbd2..413130a30ca9 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
@@ -1668,6 +1668,7 @@ static const struct rtw_chip_ops rtw8821c_ops = {
 	.set_antenna		= NULL,
 	.set_tx_power_index	= rtw8821c_set_tx_power_index,
 	.cfg_ldo25		= rtw8821c_cfg_ldo25,
+	.set_ampdu_factor	= NULL,
 	.false_alarm_statistics	= rtw8821c_false_alarm_statistics,
 	.phy_calibration	= rtw8821c_phy_calibration,
 	.cck_pd_set		= rtw8821c_phy_cck_pd_set,
@@ -1990,6 +1991,7 @@ const struct rtw_chip_info rtw8821c_hw_spec = {
 	.band = RTW_BAND_2G | RTW_BAND_5G,
 	.page_size = TX_PAGE_SIZE,
 	.dig_min = 0x1c,
+	.amsdu_in_ampdu = true,
 	.usb_tx_agg_desc_num = 3,
 	.hw_feature_report = true,
 	.c2h_ra_report_size = 7,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821ce.c b/drivers/net/wireless/realtek/rtw88/rtw8821ce.c
index f3d971feda04..40637c079d99 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821ce.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821ce.c
@@ -21,7 +21,7 @@ static const struct pci_device_id rtw_8821ce_id_table[] = {
 MODULE_DEVICE_TABLE(pci, rtw_8821ce_id_table);
 
 static struct pci_driver rtw_8821ce_driver = {
-	.name = "rtw_8821ce",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8821ce_id_table,
 	.probe = rtw_pci_probe,
 	.remove = rtw_pci_remove,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821cs.c b/drivers/net/wireless/realtek/rtw88/rtw8821cs.c
index a359413369a4..6d94162213c6 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821cs.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821cs.c
@@ -20,7 +20,7 @@ static const struct sdio_device_id rtw_8821cs_id_table[] =  {
 MODULE_DEVICE_TABLE(sdio, rtw_8821cs_id_table);
 
 static struct sdio_driver rtw_8821cs_driver = {
-	.name = "rtw_8821cs",
+	.name = KBUILD_MODNAME,
 	.probe = rtw_sdio_probe,
 	.remove = rtw_sdio_remove,
 	.id_table = rtw_8821cs_id_table,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c
index a019f4085e73..7a0fffc359e2 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c
@@ -48,7 +48,7 @@ static int rtw_8821cu_probe(struct usb_interface *intf,
 }
 
 static struct usb_driver rtw_8821cu_driver = {
-	.name = "rtw_8821cu",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8821cu_id_table,
 	.probe = rtw_8821cu_probe,
 	.disconnect = rtw_usb_disconnect,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
index b4934da88e33..ab199eaea3c7 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
@@ -2158,6 +2158,7 @@ static const struct rtw_chip_ops rtw8822b_ops = {
 	.set_tx_power_index	= rtw8822b_set_tx_power_index,
 	.set_antenna		= rtw8822b_set_antenna,
 	.cfg_ldo25		= rtw8822b_cfg_ldo25,
+	.set_ampdu_factor	= NULL,
 	.false_alarm_statistics	= rtw8822b_false_alarm_statistics,
 	.phy_calibration	= rtw8822b_phy_calibration,
 	.pwr_track		= rtw8822b_pwr_track,
@@ -2531,6 +2532,7 @@ const struct rtw_chip_info rtw8822b_hw_spec = {
 	.band = RTW_BAND_2G | RTW_BAND_5G,
 	.page_size = TX_PAGE_SIZE,
 	.dig_min = 0x1c,
+	.amsdu_in_ampdu = true,
 	.usb_tx_agg_desc_num = 3,
 	.hw_feature_report = true,
 	.c2h_ra_report_size = 7,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822be.c b/drivers/net/wireless/realtek/rtw88/rtw8822be.c
index 4994950776cd..0bb9f70e7920 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822be.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822be.c
@@ -17,7 +17,7 @@ static const struct pci_device_id rtw_8822be_id_table[] = {
 MODULE_DEVICE_TABLE(pci, rtw_8822be_id_table);
 
 static struct pci_driver rtw_8822be_driver = {
-	.name = "rtw_8822be",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8822be_id_table,
 	.probe = rtw_pci_probe,
 	.remove = rtw_pci_remove,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822bs.c b/drivers/net/wireless/realtek/rtw88/rtw8822bs.c
index 31d8645f83bd..744781dcb419 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822bs.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822bs.c
@@ -20,7 +20,7 @@ static const struct sdio_device_id rtw_8822bs_id_table[] =  {
 MODULE_DEVICE_TABLE(sdio, rtw_8822bs_id_table);
 
 static struct sdio_driver rtw_8822bs_driver = {
-	.name = "rtw_8822bs",
+	.name = KBUILD_MODNAME,
 	.probe = rtw_sdio_probe,
 	.remove = rtw_sdio_remove,
 	.id_table = rtw_8822bs_id_table,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822bu.c b/drivers/net/wireless/realtek/rtw88/rtw8822bu.c
index 572d1f31832e..44e28e583964 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822bu.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822bu.c
@@ -77,6 +77,8 @@ static const struct usb_device_id rtw_8822bu_id_table[] = {
 	  .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* Mercusys MA30N */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3322, 0xff, 0xff, 0xff),
 	  .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* D-Link DWA-T185 rev. A1 */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0411, 0x03d1, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* BUFFALO WI-U2-866DM */
 	{},
 };
 MODULE_DEVICE_TABLE(usb, rtw_8822bu_id_table);
@@ -88,7 +90,7 @@ static int rtw8822bu_probe(struct usb_interface *intf,
 }
 
 static struct usb_driver rtw_8822bu_driver = {
-	.name = "rtw_8822bu",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8822bu_id_table,
 	.probe = rtw8822bu_probe,
 	.disconnect = rtw_usb_disconnect,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
index 5e53e0db177e..017d959de3ce 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
@@ -3951,7 +3951,8 @@ static void rtw8822c_dpk_cal_coef1(struct rtw_dev *rtwdev)
 	rtw_write32(rtwdev, REG_NCTL0, 0x00001148);
 	rtw_write32(rtwdev, REG_NCTL0, 0x00001149);
 
-	check_hw_ready(rtwdev, 0x2d9c, MASKBYTE0, 0x55);
+	if (!check_hw_ready(rtwdev, 0x2d9c, MASKBYTE0, 0x55))
+		rtw_warn(rtwdev, "DPK stuck, performance may be suboptimal");
 
 	rtw_write8(rtwdev, 0x1b10, 0x0);
 	rtw_write32_mask(rtwdev, REG_NCTL0, BIT_SUBPAGE, 0x0000000c);
@@ -4968,6 +4969,7 @@ static const struct rtw_chip_ops rtw8822c_ops = {
 	.set_tx_power_index	= rtw8822c_set_tx_power_index,
 	.set_antenna		= rtw8822c_set_antenna,
 	.cfg_ldo25		= rtw8822c_cfg_ldo25,
+	.set_ampdu_factor	= NULL,
 	.false_alarm_statistics	= rtw8822c_false_alarm_statistics,
 	.dpk_track		= rtw8822c_dpk_track,
 	.phy_calibration	= rtw8822c_phy_calibration,
@@ -5349,6 +5351,7 @@ const struct rtw_chip_info rtw8822c_hw_spec = {
 	.band = RTW_BAND_2G | RTW_BAND_5G,
 	.page_size = TX_PAGE_SIZE,
 	.dig_min = 0x20,
+	.amsdu_in_ampdu = true,
 	.usb_tx_agg_desc_num = 3,
 	.hw_feature_report = true,
 	.c2h_ra_report_size = 7,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822ce.c b/drivers/net/wireless/realtek/rtw88/rtw8822ce.c
index e26c6bc82936..9def732480af 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822ce.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822ce.c
@@ -21,7 +21,7 @@ static const struct pci_device_id rtw_8822ce_id_table[] = {
 MODULE_DEVICE_TABLE(pci, rtw_8822ce_id_table);
 
 static struct pci_driver rtw_8822ce_driver = {
-	.name = "rtw_8822ce",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8822ce_id_table,
 	.probe = rtw_pci_probe,
 	.remove = rtw_pci_remove,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822cs.c b/drivers/net/wireless/realtek/rtw88/rtw8822cs.c
index 975e81c824f2..322281e07eb8 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822cs.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822cs.c
@@ -20,7 +20,7 @@ static const struct sdio_device_id rtw_8822cs_id_table[] =  {
 MODULE_DEVICE_TABLE(sdio, rtw_8822cs_id_table);
 
 static struct sdio_driver rtw_8822cs_driver = {
-	.name = "rtw_8822cs",
+	.name = KBUILD_MODNAME,
 	.probe = rtw_sdio_probe,
 	.remove = rtw_sdio_remove,
 	.id_table = rtw_8822cs_id_table,
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822cu.c b/drivers/net/wireless/realtek/rtw88/rtw8822cu.c
index 157d5102a4b1..324fd5c8bfd4 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822cu.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822cu.c
@@ -32,7 +32,7 @@ static int rtw8822cu_probe(struct usb_interface *intf,
 }
 
 static struct usb_driver rtw_8822cu_driver = {
-	.name = "rtw_8822cu",
+	.name = KBUILD_MODNAME,
 	.id_table = rtw_8822cu_id_table,
 	.probe = rtw8822cu_probe,
 	.disconnect = rtw_usb_disconnect,
diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c
index 6209a49312f1..e733ed846123 100644
--- a/drivers/net/wireless/realtek/rtw88/sdio.c
+++ b/drivers/net/wireless/realtek/rtw88/sdio.c
@@ -10,6 +10,7 @@
 #include <linux/mmc/host.h>
 #include <linux/mmc/sdio_func.h>
 #include "main.h"
+#include "mac.h"
 #include "debug.h"
 #include "fw.h"
 #include "ps.h"
@@ -677,12 +678,22 @@ static void rtw_sdio_enable_rx_aggregation(struct rtw_dev *rtwdev)
 {
 	u8 size, timeout;
 
-	if (rtw_chip_wcpu_11n(rtwdev)) {
+	switch (rtwdev->chip->id) {
+	case RTW_CHIP_TYPE_8703B:
+	case RTW_CHIP_TYPE_8821A:
+	case RTW_CHIP_TYPE_8812A:
 		size = 0x6;
 		timeout = 0x6;
-	} else {
+		break;
+	case RTW_CHIP_TYPE_8723D:
+		size = 0xa;
+		timeout = 0x3;
+		rtw_write8_set(rtwdev, REG_RXDMA_AGG_PG_TH + 3, BIT(7));
+		break;
+	default:
 		size = 0xff;
 		timeout = 0x1;
+		break;
 	}
 
 	/* Make the firmware honor the size limit configured below */
@@ -718,10 +729,7 @@ static u8 rtw_sdio_get_tx_qsel(struct rtw_dev *rtwdev, struct sk_buff *skb,
 	case RTW_TX_QUEUE_H2C:
 		return TX_DESC_QSEL_H2C;
 	case RTW_TX_QUEUE_MGMT:
-		if (rtw_chip_wcpu_11n(rtwdev))
-			return TX_DESC_QSEL_HIGH;
-		else
-			return TX_DESC_QSEL_MGMT;
+		return TX_DESC_QSEL_MGMT;
 	case RTW_TX_QUEUE_HI0:
 		return TX_DESC_QSEL_HIGH;
 	default:
@@ -1157,6 +1165,7 @@ static const struct rtw_hci_ops rtw_sdio_ops = {
 	.link_ps = rtw_sdio_link_ps,
 	.interface_cfg = rtw_sdio_interface_cfg,
 	.dynamic_rx_agg = NULL,
+	.write_firmware_page = rtw_write_firmware_page,
 
 	.read8 = rtw_sdio_read8,
 	.read16 = rtw_sdio_read16,
@@ -1227,10 +1236,7 @@ static void rtw_sdio_process_tx_queue(struct rtw_dev *rtwdev,
 		return;
 	}
 
-	if (queue <= RTW_TX_QUEUE_VO)
-		rtw_sdio_indicate_tx_status(rtwdev, skb);
-	else
-		dev_kfree_skb_any(skb);
+	rtw_sdio_indicate_tx_status(rtwdev, skb);
 }
 
 static void rtw_sdio_tx_handler(struct work_struct *work)
@@ -1298,7 +1304,6 @@ static void rtw_sdio_deinit_tx(struct rtw_dev *rtwdev)
 	struct rtw_sdio *rtwsdio = (struct rtw_sdio *)rtwdev->priv;
 	int i;
 
-	flush_workqueue(rtwsdio->txwq);
 	destroy_workqueue(rtwsdio->txwq);
 	kfree(rtwsdio->tx_handler_data);
 
diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index c8092fa0d9f1..3b5126ffc81a 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -139,7 +139,7 @@ static void rtw_usb_write(struct rtw_dev *rtwdev, u32 addr, u32 val, int len)
 
 	ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
 			      RTW_USB_CMD_REQ, RTW_USB_CMD_WRITE,
-			      addr, 0, data, len, 30000);
+			      addr, 0, data, len, 500);
 	if (ret < 0 && ret != -ENODEV && count++ < 4)
 		rtw_err(rtwdev, "write register 0x%x failed with %d\n",
 			addr, ret);
@@ -165,6 +165,60 @@ static void rtw_usb_write32(struct rtw_dev *rtwdev, u32 addr, u32 val)
 	rtw_usb_write(rtwdev, addr, val, 4);
 }
 
+static void rtw_usb_write_firmware_page(struct rtw_dev *rtwdev, u32 page,
+					const u8 *data, u32 size)
+{
+	struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev);
+	struct usb_device *udev = rtwusb->udev;
+	u32 addr = FW_START_ADDR_LEGACY;
+	u8 *data_dup, *buf;
+	u32 n, block_size;
+	int ret;
+
+	switch (rtwdev->chip->id) {
+	case RTW_CHIP_TYPE_8723D:
+		block_size = 254;
+		break;
+	default:
+		block_size = 196;
+		break;
+	}
+
+	data_dup = kmemdup(data, size, GFP_KERNEL);
+	if (!data_dup)
+		return;
+
+	buf = data_dup;
+
+	rtw_write32_mask(rtwdev, REG_MCUFW_CTRL, BIT_ROM_PGE, page);
+
+	while (size > 0) {
+		if (size >= block_size)
+			n = block_size;
+		else if (size >= 8)
+			n = 8;
+		else
+			n = 1;
+
+		ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
+				      RTW_USB_CMD_REQ, RTW_USB_CMD_WRITE,
+				      addr, 0, buf, n, 500);
+		if (ret != n) {
+			if (ret != -ENODEV)
+				rtw_err(rtwdev,
+					"write 0x%x len %d failed: %d\n",
+					addr, n, ret);
+			break;
+		}
+
+		addr += n;
+		buf += n;
+		size -= n;
+	}
+
+	kfree(data_dup);
+}
+
 static int dma_mapping_to_ep(enum rtw_dma_mapping dma_mapping)
 {
 	switch (dma_mapping) {
@@ -866,6 +920,7 @@ static void rtw_usb_dynamic_rx_agg(struct rtw_dev *rtwdev, bool enable)
 	case RTW_CHIP_TYPE_8822C:
 	case RTW_CHIP_TYPE_8822B:
 	case RTW_CHIP_TYPE_8821C:
+	case RTW_CHIP_TYPE_8814A:
 		rtw_usb_dynamic_rx_agg_v1(rtwdev, enable);
 		break;
 	case RTW_CHIP_TYPE_8821A:
@@ -891,6 +946,7 @@ static const struct rtw_hci_ops rtw_usb_ops = {
 	.link_ps = rtw_usb_link_ps,
 	.interface_cfg = rtw_usb_interface_cfg,
 	.dynamic_rx_agg = rtw_usb_dynamic_rx_agg,
+	.write_firmware_page = rtw_usb_write_firmware_page,
 
 	.write8  = rtw_usb_write8,
 	.write16 = rtw_usb_write16,
@@ -948,7 +1004,6 @@ static void rtw_usb_deinit_rx(struct rtw_dev *rtwdev)
 
 	skb_queue_purge(&rtwusb->rx_queue);
 
-	flush_workqueue(rtwusb->rxwq);
 	destroy_workqueue(rtwusb->rxwq);
 
 	skb_queue_purge(&rtwusb->rx_free_queue);
@@ -977,7 +1032,6 @@ static void rtw_usb_deinit_tx(struct rtw_dev *rtwdev)
 {
 	struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev);
 
-	flush_workqueue(rtwusb->txwq);
 	destroy_workqueue(rtwusb->txwq);
 	rtw_usb_tx_queue_purge(rtwusb);
 }
@@ -1094,7 +1148,8 @@ static int rtw_usb_switch_mode_new(struct rtw_dev *rtwdev)
 
 static bool rtw_usb3_chip_old(u8 chip_id)
 {
-	return chip_id == RTW_CHIP_TYPE_8812A;
+	return chip_id == RTW_CHIP_TYPE_8812A ||
+	       chip_id == RTW_CHIP_TYPE_8814A;
 }
 
 static bool rtw_usb3_chip_new(u8 chip_id)
diff --git a/drivers/net/wireless/realtek/rtw89/acpi.c b/drivers/net/wireless/realtek/rtw89/acpi.c
index f5dedb12c129..581d6d4154d3 100644
--- a/drivers/net/wireless/realtek/rtw89/acpi.c
+++ b/drivers/net/wireless/realtek/rtw89/acpi.c
@@ -12,6 +12,121 @@ static const guid_t rtw89_guid = GUID_INIT(0xD2A8C3E8, 0x4B69, 0x4F00,
 					   0x82, 0xBD, 0xFE, 0x86,
 					   0x07, 0x80, 0x3A, 0xA7);
 
+static u32 rtw89_acpi_traversal_object(struct rtw89_dev *rtwdev,
+				       const union acpi_object *obj, u8 *pos)
+{
+	const union acpi_object *elm;
+	unsigned int i;
+	u32 sub_len;
+	u32 len = 0;
+	u8 *tmp;
+
+	switch (obj->type) {
+	case ACPI_TYPE_INTEGER:
+		if (pos)
+			pos[len] = obj->integer.value;
+
+		len++;
+		break;
+	case ACPI_TYPE_BUFFER:
+		if (unlikely(obj->buffer.length == 0)) {
+			rtw89_debug(rtwdev, RTW89_DBG_ACPI,
+				    "%s: invalid buffer type\n", __func__);
+			goto err;
+		}
+
+		if (pos)
+			memcpy(pos, obj->buffer.pointer, obj->buffer.length);
+
+		len += obj->buffer.length;
+		break;
+	case ACPI_TYPE_PACKAGE:
+		if (unlikely(obj->package.count == 0)) {
+			rtw89_debug(rtwdev, RTW89_DBG_ACPI,
+				    "%s: invalid package type\n", __func__);
+			goto err;
+		}
+
+		for (i = 0; i < obj->package.count; i++) {
+			elm = &obj->package.elements[i];
+			tmp = pos ? pos + len : NULL;
+
+			sub_len = rtw89_acpi_traversal_object(rtwdev, elm, tmp);
+			if (unlikely(sub_len == 0))
+				goto err;
+
+			len += sub_len;
+		}
+		break;
+	default:
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "%s: unhandled type: %d\n",
+			    __func__, obj->type);
+		goto err;
+	}
+
+	return len;
+
+err:
+	return 0;
+}
+
+static u32 rtw89_acpi_calculate_object_length(struct rtw89_dev *rtwdev,
+					      const union acpi_object *obj)
+{
+	return rtw89_acpi_traversal_object(rtwdev, obj, NULL);
+}
+
+static struct rtw89_acpi_data *
+rtw89_acpi_evaluate_method(struct rtw89_dev *rtwdev, const char *method)
+{
+	struct acpi_buffer buf = {ACPI_ALLOCATE_BUFFER, NULL};
+	struct rtw89_acpi_data *data = NULL;
+	acpi_handle root, handle;
+	union acpi_object *obj;
+	acpi_status status;
+	u32 len;
+
+	root = ACPI_HANDLE(rtwdev->dev);
+	if (!root) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI,
+			    "acpi (%s): failed to get root\n", method);
+		return NULL;
+	}
+
+	status = acpi_get_handle(root, (acpi_string)method, &handle);
+	if (ACPI_FAILURE(status)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI,
+			    "acpi (%s): failed to get handle\n", method);
+		return NULL;
+	}
+
+	status = acpi_evaluate_object(handle, NULL, NULL, &buf);
+	if (ACPI_FAILURE(status)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI,
+			    "acpi (%s): failed to evaluate object\n", method);
+		return NULL;
+	}
+
+	obj = buf.pointer;
+	len = rtw89_acpi_calculate_object_length(rtwdev, obj);
+	if (unlikely(len == 0)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI,
+			    "acpi (%s): failed to traversal obj len\n", method);
+		goto out;
+	}
+
+	data = kzalloc(struct_size(data, buf, len), GFP_KERNEL);
+	if (!data)
+		goto out;
+
+	data->len = len;
+	rtw89_acpi_traversal_object(rtwdev, obj, data->buf);
+
+out:
+	ACPI_FREE(obj);
+	return data;
+}
+
 static
 int rtw89_acpi_dsm_get_value(struct rtw89_dev *rtwdev, union acpi_object *obj,
 			     u8 *value)
@@ -121,6 +236,49 @@ int rtw89_acpi_dsm_get_policy_6ghz_sp(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
+static bool chk_acpi_policy_tas_sig(const struct rtw89_acpi_policy_tas *p)
+{
+	return p->signature[0] == 0x52 &&
+	       p->signature[1] == 0x54 &&
+	       p->signature[2] == 0x4B &&
+	       p->signature[3] == 0x05;
+}
+
+static int rtw89_acpi_dsm_get_policy_tas(struct rtw89_dev *rtwdev,
+					 union acpi_object *obj,
+					 struct rtw89_acpi_policy_tas **policy)
+{
+	const struct rtw89_acpi_policy_tas *ptr;
+	u32 buf_len;
+
+	if (obj->type != ACPI_TYPE_BUFFER) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI,
+			    "acpi: expect buffer but type: %d\n", obj->type);
+		return -EINVAL;
+	}
+
+	buf_len = obj->buffer.length;
+	if (buf_len < sizeof(*ptr)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "%s: invalid buffer length: %u\n",
+			    __func__, buf_len);
+		return -EINVAL;
+	}
+
+	ptr = (typeof(ptr))obj->buffer.pointer;
+	if (!chk_acpi_policy_tas_sig(ptr)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "%s: bad signature\n", __func__);
+		return -EINVAL;
+	}
+
+	*policy = kmemdup(ptr, sizeof(*ptr), GFP_KERNEL);
+	if (!*policy)
+		return -ENOMEM;
+
+	rtw89_hex_dump(rtwdev, RTW89_DBG_ACPI, "policy_tas: ", *policy,
+		       sizeof(*ptr));
+	return 0;
+}
+
 int rtw89_acpi_evaluate_dsm(struct rtw89_dev *rtwdev,
 			    enum rtw89_acpi_dsm_func func,
 			    struct rtw89_acpi_dsm_result *res)
@@ -142,6 +300,8 @@ int rtw89_acpi_evaluate_dsm(struct rtw89_dev *rtwdev,
 	else if (func == RTW89_ACPI_DSM_FUNC_6GHZ_SP_SUP)
 		ret = rtw89_acpi_dsm_get_policy_6ghz_sp(rtwdev, obj,
 							&res->u.policy_6ghz_sp);
+	else if (func == RTW89_ACPI_DSM_FUNC_TAS_EN)
+		ret = rtw89_acpi_dsm_get_policy_tas(rtwdev, obj, &res->u.policy_tas);
 	else
 		ret = rtw89_acpi_dsm_get_value(rtwdev, obj, &res->u.value);
 
@@ -152,46 +312,875 @@ int rtw89_acpi_evaluate_dsm(struct rtw89_dev *rtwdev,
 int rtw89_acpi_evaluate_rtag(struct rtw89_dev *rtwdev,
 			     struct rtw89_acpi_rtag_result *res)
 {
-	struct acpi_buffer buf = {ACPI_ALLOCATE_BUFFER, NULL};
-	acpi_handle root, handle;
-	union acpi_object *obj;
-	acpi_status status;
+	const struct rtw89_acpi_data *data;
 	u32 buf_len;
 	int ret = 0;
 
-	root = ACPI_HANDLE(rtwdev->dev);
-	if (!root)
-		return -EOPNOTSUPP;
-
-	status = acpi_get_handle(root, (acpi_string)"RTAG", &handle);
-	if (ACPI_FAILURE(status))
+	data = rtw89_acpi_evaluate_method(rtwdev, "RTAG");
+	if (!data)
 		return -EIO;
 
-	status = acpi_evaluate_object(handle, NULL, NULL, &buf);
-	if (ACPI_FAILURE(status))
-		return -EIO;
+	buf_len = data->len;
+	if (buf_len != sizeof(*res)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "%s: invalid buffer length: %u\n",
+			    __func__, buf_len);
+		ret = -EINVAL;
+		goto out;
+	}
 
-	obj = buf.pointer;
-	if (obj->type != ACPI_TYPE_BUFFER) {
+	*res = *(struct rtw89_acpi_rtag_result *)data->buf;
+
+	rtw89_hex_dump(rtwdev, RTW89_DBG_ACPI, "antenna_gain: ", res, sizeof(*res));
+
+out:
+	kfree(data);
+	return ret;
+}
+
+enum rtw89_acpi_sar_subband rtw89_acpi_sar_get_subband(struct rtw89_dev *rtwdev,
+						       u32 center_freq)
+{
+	switch (center_freq) {
+	default:
 		rtw89_debug(rtwdev, RTW89_DBG_ACPI,
-			    "acpi: expect buffer but type: %d\n", obj->type);
-		ret = -EINVAL;
+			    "center freq %u to ACPI SAR subband is unhandled\n",
+			    center_freq);
+		fallthrough;
+	case 2412 ... 2484:
+		return RTW89_ACPI_SAR_2GHZ_SUBBAND;
+	case 5180 ... 5240:
+		return RTW89_ACPI_SAR_5GHZ_SUBBAND_1;
+	case 5250 ... 5320:
+		return RTW89_ACPI_SAR_5GHZ_SUBBAND_2;
+	case 5500 ... 5720:
+		return RTW89_ACPI_SAR_5GHZ_SUBBAND_2E;
+	case 5745 ... 5885:
+		return RTW89_ACPI_SAR_5GHZ_SUBBAND_3_4;
+	case 5955 ... 6155:
+		return RTW89_ACPI_SAR_6GHZ_SUBBAND_5_L;
+	case 6175 ... 6415:
+		return RTW89_ACPI_SAR_6GHZ_SUBBAND_5_H;
+	case 6435 ... 6515:
+		return RTW89_ACPI_SAR_6GHZ_SUBBAND_6;
+	case 6535 ... 6695:
+		return RTW89_ACPI_SAR_6GHZ_SUBBAND_7_L;
+	case 6715 ... 6855:
+		return RTW89_ACPI_SAR_6GHZ_SUBBAND_7_H;
+
+	/* freq 6875 (ch 185, 20MHz) spans RTW89_ACPI_SAR_6GHZ_SUBBAND_7_H
+	 * and RTW89_ACPI_SAR_6GHZ_SUBBAND_8, so directly describe it with
+	 * struct rtw89_6ghz_span.
+	 */
+
+	case 6895 ... 7115:
+		return RTW89_ACPI_SAR_6GHZ_SUBBAND_8;
+	}
+}
+
+enum rtw89_band rtw89_acpi_sar_subband_to_band(struct rtw89_dev *rtwdev,
+					       enum rtw89_acpi_sar_subband subband)
+{
+	switch (subband) {
+	default:
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI,
+			    "ACPI SAR subband %u to band is unhandled\n", subband);
+		fallthrough;
+	case RTW89_ACPI_SAR_2GHZ_SUBBAND:
+		return RTW89_BAND_2G;
+	case RTW89_ACPI_SAR_5GHZ_SUBBAND_1:
+		return RTW89_BAND_5G;
+	case RTW89_ACPI_SAR_5GHZ_SUBBAND_2:
+		return RTW89_BAND_5G;
+	case RTW89_ACPI_SAR_5GHZ_SUBBAND_2E:
+		return RTW89_BAND_5G;
+	case RTW89_ACPI_SAR_5GHZ_SUBBAND_3_4:
+		return RTW89_BAND_5G;
+	case RTW89_ACPI_SAR_6GHZ_SUBBAND_5_L:
+		return RTW89_BAND_6G;
+	case RTW89_ACPI_SAR_6GHZ_SUBBAND_5_H:
+		return RTW89_BAND_6G;
+	case RTW89_ACPI_SAR_6GHZ_SUBBAND_6:
+		return RTW89_BAND_6G;
+	case RTW89_ACPI_SAR_6GHZ_SUBBAND_7_L:
+		return RTW89_BAND_6G;
+	case RTW89_ACPI_SAR_6GHZ_SUBBAND_7_H:
+		return RTW89_BAND_6G;
+	case RTW89_ACPI_SAR_6GHZ_SUBBAND_8:
+		return RTW89_BAND_6G;
+	}
+}
+
+static u8 rtw89_acpi_sar_rfpath_to_hp_antidx(enum rtw89_rf_path rfpath)
+{
+	switch (rfpath) {
+	default:
+	case RF_PATH_B:
+		return 0;
+	case RF_PATH_A:
+		return 1;
+	}
+}
+
+static u8 rtw89_acpi_sar_rfpath_to_rt_antidx(enum rtw89_rf_path rfpath)
+{
+	switch (rfpath) {
+	default:
+	case RF_PATH_A:
+		return 0;
+	case RF_PATH_B:
+		return 1;
+	}
+}
+
+static s16 rtw89_acpi_sar_normalize_hp_val(u8 v)
+{
+	static const u8 bias = 10;
+	static const u8 fct = 1;
+	u16 res;
+
+	BUILD_BUG_ON(fct > TXPWR_FACTOR_OF_RTW89_ACPI_SAR);
+
+	res = (bias << TXPWR_FACTOR_OF_RTW89_ACPI_SAR) +
+	      (v << (TXPWR_FACTOR_OF_RTW89_ACPI_SAR - fct));
+
+	return min_t(s32, res, MAX_VAL_OF_RTW89_ACPI_SAR);
+}
+
+static s16 rtw89_acpi_sar_normalize_rt_val(u8 v)
+{
+	static const u8 fct = 3;
+	u16 res;
+
+	BUILD_BUG_ON(fct > TXPWR_FACTOR_OF_RTW89_ACPI_SAR);
+
+	res = v << (TXPWR_FACTOR_OF_RTW89_ACPI_SAR - fct);
+
+	return min_t(s32, res, MAX_VAL_OF_RTW89_ACPI_SAR);
+}
+
+static
+void rtw89_acpi_sar_load_std_legacy(struct rtw89_dev *rtwdev,
+				    const struct rtw89_acpi_sar_recognition *rec,
+				    const void *content,
+				    struct rtw89_sar_entry_from_acpi *ent)
+{
+	const struct rtw89_acpi_sar_std_legacy *ptr = content;
+	enum rtw89_acpi_sar_subband subband;
+	enum rtw89_rf_path path;
+
+	for (subband = 0; subband < NUM_OF_RTW89_ACPI_SAR_SUBBAND; subband++) {
+		for (path = 0; path < NUM_OF_RTW89_ACPI_SAR_RF_PATH; path++) {
+			u8 antidx = rec->rfpath_to_antidx(path);
+
+			if (subband < RTW89_ACPI_SAR_SUBBAND_NR_LEGACY)
+				ent->v[subband][path] =
+					rec->normalize(ptr->v[antidx][subband]);
+			else
+				ent->v[subband][path] = MAX_VAL_OF_RTW89_ACPI_SAR;
+		}
+	}
+}
+
+static
+void rtw89_acpi_sar_load_std_has_6ghz(struct rtw89_dev *rtwdev,
+				      const struct rtw89_acpi_sar_recognition *rec,
+				      const void *content,
+				      struct rtw89_sar_entry_from_acpi *ent)
+{
+	const struct rtw89_acpi_sar_std_has_6ghz *ptr = content;
+	enum rtw89_acpi_sar_subband subband;
+	enum rtw89_rf_path path;
+
+	BUILD_BUG_ON(RTW89_ACPI_SAR_SUBBAND_NR_HAS_6GHZ != NUM_OF_RTW89_ACPI_SAR_SUBBAND);
+
+	for (subband = 0; subband < NUM_OF_RTW89_ACPI_SAR_SUBBAND; subband++) {
+		for (path = 0; path < NUM_OF_RTW89_ACPI_SAR_RF_PATH; path++) {
+			u8 antidx = rec->rfpath_to_antidx(path);
+
+			ent->v[subband][path] = rec->normalize(ptr->v[antidx][subband]);
+		}
+	}
+}
+
+static
+void rtw89_acpi_sar_load_sml_legacy(struct rtw89_dev *rtwdev,
+				    const struct rtw89_acpi_sar_recognition *rec,
+				    const void *content,
+				    struct rtw89_sar_entry_from_acpi *ent)
+{
+	const struct rtw89_acpi_sar_sml_legacy *ptr = content;
+	enum rtw89_acpi_sar_subband subband;
+	enum rtw89_rf_path path;
+
+	for (subband = 0; subband < NUM_OF_RTW89_ACPI_SAR_SUBBAND; subband++) {
+		for (path = 0; path < NUM_OF_RTW89_ACPI_SAR_RF_PATH; path++) {
+			u8 antidx = rec->rfpath_to_antidx(path);
+
+			if (subband < RTW89_ACPI_SAR_SUBBAND_NR_LEGACY)
+				ent->v[subband][path] =
+					rec->normalize(ptr->v[antidx][subband]);
+			else
+				ent->v[subband][path] = MAX_VAL_OF_RTW89_ACPI_SAR;
+		}
+	}
+}
+
+static
+void rtw89_acpi_sar_load_sml_has_6ghz(struct rtw89_dev *rtwdev,
+				      const struct rtw89_acpi_sar_recognition *rec,
+				      const void *content,
+				      struct rtw89_sar_entry_from_acpi *ent)
+{
+	const struct rtw89_acpi_sar_sml_has_6ghz *ptr = content;
+	enum rtw89_acpi_sar_subband subband;
+	enum rtw89_rf_path path;
+
+	BUILD_BUG_ON(RTW89_ACPI_SAR_SUBBAND_NR_HAS_6GHZ != NUM_OF_RTW89_ACPI_SAR_SUBBAND);
+
+	for (subband = 0; subband < NUM_OF_RTW89_ACPI_SAR_SUBBAND; subband++) {
+		for (path = 0; path < NUM_OF_RTW89_ACPI_SAR_RF_PATH; path++) {
+			u8 antidx = rec->rfpath_to_antidx(path);
+
+			ent->v[subband][path] = rec->normalize(ptr->v[antidx][subband]);
+		}
+	}
+}
+
+static s16 rtw89_acpi_geo_sar_normalize_delta(s8 delta)
+{
+	static const u8 fct = 1;
+
+	BUILD_BUG_ON(fct > TXPWR_FACTOR_OF_RTW89_ACPI_SAR);
+
+	return delta << (TXPWR_FACTOR_OF_RTW89_ACPI_SAR - fct);
+}
+
+static enum rtw89_acpi_geo_sar_regd_hp
+rtw89_acpi_geo_sar_regd_convert_hp_idx(enum rtw89_regulation_type regd)
+{
+	switch (regd) {
+	case RTW89_FCC:
+	case RTW89_IC:
+	case RTW89_NCC:
+	case RTW89_CHILE:
+	case RTW89_MEXICO:
+		return RTW89_ACPI_GEO_SAR_REGD_HP_FCC;
+	case RTW89_ETSI:
+	case RTW89_MKK:
+	case RTW89_ACMA:
+		return RTW89_ACPI_GEO_SAR_REGD_HP_ETSI;
+	default:
+	case RTW89_WW:
+	case RTW89_NA:
+	case RTW89_KCC:
+		return RTW89_ACPI_GEO_SAR_REGD_HP_WW;
+	}
+}
+
+static enum rtw89_acpi_geo_sar_regd_rt
+rtw89_acpi_geo_sar_regd_convert_rt_idx(enum rtw89_regulation_type regd)
+{
+	switch (regd) {
+	case RTW89_FCC:
+	case RTW89_NCC:
+	case RTW89_CHILE:
+	case RTW89_MEXICO:
+		return RTW89_ACPI_GEO_SAR_REGD_RT_FCC;
+	case RTW89_ETSI:
+	case RTW89_ACMA:
+		return RTW89_ACPI_GEO_SAR_REGD_RT_ETSI;
+	case RTW89_MKK:
+		return RTW89_ACPI_GEO_SAR_REGD_RT_MKK;
+	case RTW89_IC:
+		return RTW89_ACPI_GEO_SAR_REGD_RT_IC;
+	case RTW89_KCC:
+		return RTW89_ACPI_GEO_SAR_REGD_RT_KCC;
+	default:
+	case RTW89_WW:
+	case RTW89_NA:
+		return RTW89_ACPI_GEO_SAR_REGD_RT_WW;
+	}
+}
+
+static
+void rtw89_acpi_geo_sar_load_by_hp(struct rtw89_dev *rtwdev,
+				   const struct rtw89_acpi_geo_sar_hp_val *ptr,
+				   enum rtw89_rf_path path, s16 *val)
+{
+	u8 antidx = rtw89_acpi_sar_rfpath_to_hp_antidx(path);
+	s16 delta = rtw89_acpi_geo_sar_normalize_delta(ptr->delta[antidx]);
+	s16 max = rtw89_acpi_sar_normalize_hp_val(ptr->max);
+
+	*val = clamp_t(s32, (*val) + delta, MIN_VAL_OF_RTW89_ACPI_SAR, max);
+}
+
+static
+void rtw89_acpi_geo_sar_load_by_rt(struct rtw89_dev *rtwdev,
+				   const struct rtw89_acpi_geo_sar_rt_val *ptr,
+				   s16 *val)
+{
+	s16 delta = rtw89_acpi_geo_sar_normalize_delta(ptr->delta);
+	s16 max = rtw89_acpi_sar_normalize_rt_val(ptr->max);
+
+	*val = clamp_t(s32, (*val) + delta, MIN_VAL_OF_RTW89_ACPI_SAR, max);
+}
+
+static
+void rtw89_acpi_geo_sar_load_hp_legacy(struct rtw89_dev *rtwdev,
+				       const void *content,
+				       enum rtw89_regulation_type regd,
+				       struct rtw89_sar_entry_from_acpi *ent)
+{
+	const struct rtw89_acpi_geo_sar_hp_legacy *ptr = content;
+	const struct rtw89_acpi_geo_sar_hp_legacy_entry *ptr_ent;
+	const struct rtw89_acpi_geo_sar_hp_val *ptr_ent_val;
+	enum rtw89_acpi_geo_sar_regd_hp geo_idx =
+		rtw89_acpi_geo_sar_regd_convert_hp_idx(regd);
+	enum rtw89_acpi_sar_subband subband;
+	enum rtw89_rf_path path;
+	enum rtw89_band band;
+
+	ptr_ent = &ptr->entries[geo_idx];
+
+	for (subband = 0; subband < NUM_OF_RTW89_ACPI_SAR_SUBBAND; subband++) {
+		band = rtw89_acpi_sar_subband_to_band(rtwdev, subband);
+		switch (band) {
+		case RTW89_BAND_2G:
+			ptr_ent_val = &ptr_ent->val_2ghz;
+			break;
+		case RTW89_BAND_5G:
+			ptr_ent_val = &ptr_ent->val_5ghz;
+			break;
+		default:
+		case RTW89_BAND_6G:
+			ptr_ent_val = NULL;
+			break;
+		}
+
+		if (!ptr_ent_val)
+			continue;
+
+		for (path = 0; path < NUM_OF_RTW89_ACPI_SAR_RF_PATH; path++)
+			rtw89_acpi_geo_sar_load_by_hp(rtwdev, ptr_ent_val, path,
+						      &ent->v[subband][path]);
+	}
+}
+
+static
+void rtw89_acpi_geo_sar_load_hp_has_6ghz(struct rtw89_dev *rtwdev,
+					 const void *content,
+					 enum rtw89_regulation_type regd,
+					 struct rtw89_sar_entry_from_acpi *ent)
+{
+	const struct rtw89_acpi_geo_sar_hp_has_6ghz *ptr = content;
+	const struct rtw89_acpi_geo_sar_hp_has_6ghz_entry *ptr_ent;
+	const struct rtw89_acpi_geo_sar_hp_val *ptr_ent_val;
+	enum rtw89_acpi_geo_sar_regd_hp geo_idx =
+		rtw89_acpi_geo_sar_regd_convert_hp_idx(regd);
+	enum rtw89_acpi_sar_subband subband;
+	enum rtw89_rf_path path;
+	enum rtw89_band band;
+
+	ptr_ent = &ptr->entries[geo_idx];
+
+	for (subband = 0; subband < NUM_OF_RTW89_ACPI_SAR_SUBBAND; subband++) {
+		band = rtw89_acpi_sar_subband_to_band(rtwdev, subband);
+		switch (band) {
+		case RTW89_BAND_2G:
+			ptr_ent_val = &ptr_ent->val_2ghz;
+			break;
+		case RTW89_BAND_5G:
+			ptr_ent_val = &ptr_ent->val_5ghz;
+			break;
+		case RTW89_BAND_6G:
+			ptr_ent_val = &ptr_ent->val_6ghz;
+			break;
+		default:
+			ptr_ent_val = NULL;
+			break;
+		}
+
+		if (!ptr_ent_val)
+			continue;
+
+		for (path = 0; path < NUM_OF_RTW89_ACPI_SAR_RF_PATH; path++)
+			rtw89_acpi_geo_sar_load_by_hp(rtwdev, ptr_ent_val, path,
+						      &ent->v[subband][path]);
+	}
+}
+
+static
+void rtw89_acpi_geo_sar_load_rt_legacy(struct rtw89_dev *rtwdev,
+				       const void *content,
+				       enum rtw89_regulation_type regd,
+				       struct rtw89_sar_entry_from_acpi *ent)
+{
+	const struct rtw89_acpi_geo_sar_rt_legacy *ptr = content;
+	const struct rtw89_acpi_geo_sar_rt_legacy_entry *ptr_ent;
+	const struct rtw89_acpi_geo_sar_rt_val *ptr_ent_val;
+	enum rtw89_acpi_geo_sar_regd_rt geo_idx =
+		rtw89_acpi_geo_sar_regd_convert_rt_idx(regd);
+	enum rtw89_acpi_sar_subband subband;
+	enum rtw89_rf_path path;
+	enum rtw89_band band;
+
+	ptr_ent = &ptr->entries[geo_idx];
+
+	for (subband = 0; subband < NUM_OF_RTW89_ACPI_SAR_SUBBAND; subband++) {
+		band = rtw89_acpi_sar_subband_to_band(rtwdev, subband);
+		switch (band) {
+		case RTW89_BAND_2G:
+			ptr_ent_val = &ptr_ent->val_2ghz;
+			break;
+		case RTW89_BAND_5G:
+			ptr_ent_val = &ptr_ent->val_5ghz;
+			break;
+		default:
+		case RTW89_BAND_6G:
+			ptr_ent_val = NULL;
+			break;
+		}
+
+		if (!ptr_ent_val)
+			continue;
+
+		for (path = 0; path < NUM_OF_RTW89_ACPI_SAR_RF_PATH; path++)
+			rtw89_acpi_geo_sar_load_by_rt(rtwdev, ptr_ent_val,
+						      &ent->v[subband][path]);
+	}
+}
+
+static
+void rtw89_acpi_geo_sar_load_rt_has_6ghz(struct rtw89_dev *rtwdev,
+					 const void *content,
+					 enum rtw89_regulation_type regd,
+					 struct rtw89_sar_entry_from_acpi *ent)
+{
+	const struct rtw89_acpi_geo_sar_rt_has_6ghz *ptr = content;
+	const struct rtw89_acpi_geo_sar_rt_has_6ghz_entry *ptr_ent;
+	const struct rtw89_acpi_geo_sar_rt_val *ptr_ent_val;
+	enum rtw89_acpi_geo_sar_regd_rt geo_idx =
+		rtw89_acpi_geo_sar_regd_convert_rt_idx(regd);
+	enum rtw89_acpi_sar_subband subband;
+	enum rtw89_rf_path path;
+	enum rtw89_band band;
+
+	ptr_ent = &ptr->entries[geo_idx];
+
+	for (subband = 0; subband < NUM_OF_RTW89_ACPI_SAR_SUBBAND; subband++) {
+		band = rtw89_acpi_sar_subband_to_band(rtwdev, subband);
+		switch (band) {
+		case RTW89_BAND_2G:
+			ptr_ent_val = &ptr_ent->val_2ghz;
+			break;
+		case RTW89_BAND_5G:
+			ptr_ent_val = &ptr_ent->val_5ghz;
+			break;
+		case RTW89_BAND_6G:
+			ptr_ent_val = &ptr_ent->val_6ghz;
+			break;
+		default:
+			ptr_ent_val = NULL;
+			break;
+		}
+
+		if (!ptr_ent_val)
+			continue;
+
+		for (path = 0; path < NUM_OF_RTW89_ACPI_SAR_RF_PATH; path++)
+			rtw89_acpi_geo_sar_load_by_rt(rtwdev, ptr_ent_val,
+						      &ent->v[subband][path]);
+	}
+}
+
+#define RTW89_ACPI_GEO_SAR_DECL_HANDLER(type) \
+static const struct rtw89_acpi_geo_sar_handler \
+rtw89_acpi_geo_sar_handler_ ## type = { \
+	.data_size = RTW89_ACPI_GEO_SAR_SIZE_OF(type), \
+	.load = rtw89_acpi_geo_sar_load_ ## type, \
+}
+
+RTW89_ACPI_GEO_SAR_DECL_HANDLER(hp_legacy);
+RTW89_ACPI_GEO_SAR_DECL_HANDLER(hp_has_6ghz);
+RTW89_ACPI_GEO_SAR_DECL_HANDLER(rt_legacy);
+RTW89_ACPI_GEO_SAR_DECL_HANDLER(rt_has_6ghz);
+
+static const struct rtw89_acpi_sar_recognition rtw89_acpi_sar_recs[] = {
+	{
+		.id = {
+			.cid = RTW89_ACPI_SAR_CID_HP,
+			.rev = RTW89_ACPI_SAR_REV_LEGACY,
+			.size = RTW89_ACPI_SAR_SIZE_OF(std_legacy),
+		},
+		.geo = &rtw89_acpi_geo_sar_handler_hp_legacy,
+
+		.rfpath_to_antidx = rtw89_acpi_sar_rfpath_to_hp_antidx,
+		.normalize = rtw89_acpi_sar_normalize_hp_val,
+		.load = rtw89_acpi_sar_load_std_legacy,
+	},
+	{
+		.id = {
+			.cid = RTW89_ACPI_SAR_CID_HP,
+			.rev = RTW89_ACPI_SAR_REV_HAS_6GHZ,
+			.size = RTW89_ACPI_SAR_SIZE_OF(std_has_6ghz),
+		},
+		.geo = &rtw89_acpi_geo_sar_handler_hp_has_6ghz,
+
+		.rfpath_to_antidx = rtw89_acpi_sar_rfpath_to_hp_antidx,
+		.normalize = rtw89_acpi_sar_normalize_hp_val,
+		.load = rtw89_acpi_sar_load_std_has_6ghz,
+	},
+	{
+		.id = {
+			.cid = RTW89_ACPI_SAR_CID_RT,
+			.rev = RTW89_ACPI_SAR_REV_LEGACY,
+			.size = RTW89_ACPI_SAR_SIZE_OF(std_legacy),
+		},
+		.geo = &rtw89_acpi_geo_sar_handler_rt_legacy,
+
+		.rfpath_to_antidx = rtw89_acpi_sar_rfpath_to_rt_antidx,
+		.normalize = rtw89_acpi_sar_normalize_rt_val,
+		.load = rtw89_acpi_sar_load_std_legacy,
+	},
+	{
+		.id = {
+			.cid = RTW89_ACPI_SAR_CID_RT,
+			.rev = RTW89_ACPI_SAR_REV_HAS_6GHZ,
+			.size = RTW89_ACPI_SAR_SIZE_OF(std_has_6ghz),
+		},
+		.geo = &rtw89_acpi_geo_sar_handler_rt_has_6ghz,
+
+		.rfpath_to_antidx = rtw89_acpi_sar_rfpath_to_rt_antidx,
+		.normalize = rtw89_acpi_sar_normalize_rt_val,
+		.load = rtw89_acpi_sar_load_std_has_6ghz,
+	},
+	{
+		.id = {
+			.cid = RTW89_ACPI_SAR_CID_RT,
+			.rev = RTW89_ACPI_SAR_REV_LEGACY,
+			.size = RTW89_ACPI_SAR_SIZE_OF(sml_legacy),
+		},
+		.geo = &rtw89_acpi_geo_sar_handler_rt_legacy,
+
+		.rfpath_to_antidx = rtw89_acpi_sar_rfpath_to_rt_antidx,
+		.normalize = rtw89_acpi_sar_normalize_rt_val,
+		.load = rtw89_acpi_sar_load_sml_legacy,
+	},
+	{
+		.id = {
+			.cid = RTW89_ACPI_SAR_CID_RT,
+			.rev = RTW89_ACPI_SAR_REV_HAS_6GHZ,
+			.size = RTW89_ACPI_SAR_SIZE_OF(sml_has_6ghz),
+		},
+		.geo = &rtw89_acpi_geo_sar_handler_rt_has_6ghz,
+
+		.rfpath_to_antidx = rtw89_acpi_sar_rfpath_to_rt_antidx,
+		.normalize = rtw89_acpi_sar_normalize_rt_val,
+		.load = rtw89_acpi_sar_load_sml_has_6ghz,
+	},
+};
+
+struct rtw89_acpi_sar_rec_parm {
+	u32 pld_len;
+	u8 tbl_cnt;
+	u16 cid;
+	u8 rev;
+};
+
+static const struct rtw89_acpi_sar_recognition *
+rtw89_acpi_sar_recognize(struct rtw89_dev *rtwdev,
+			 const struct rtw89_acpi_sar_rec_parm *parm)
+{
+	const u32 tbl_len = parm->pld_len / parm->tbl_cnt;
+	const struct rtw89_acpi_sar_recognition *rec;
+	struct rtw89_acpi_sar_identifier id = {};
+
+	rtw89_debug(rtwdev, RTW89_DBG_ACPI,
+		    "%s: cid %u, rev %u, tbl len %u, tbl cnt %u\n",
+		    __func__, parm->cid, parm->rev, tbl_len, parm->tbl_cnt);
+
+	if (unlikely(parm->pld_len % parm->tbl_cnt)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "invalid pld len %u\n",
+			    parm->pld_len);
+		return NULL;
+	}
+
+	if (unlikely(tbl_len > RTW89_ACPI_SAR_SIZE_MAX)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "invalid tbl len %u\n",
+			    tbl_len);
+		return NULL;
+	}
+
+	if (unlikely(parm->tbl_cnt > MAX_NUM_OF_RTW89_ACPI_SAR_TBL)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "invalid tbl cnt %u\n",
+			    parm->tbl_cnt);
+		return NULL;
+	}
+
+	switch (parm->cid) {
+	case RTW89_ACPI_SAR_CID_HP:
+	case RTW89_ACPI_SAR_CID_RT:
+		id.cid = parm->cid;
+		break;
+	default:
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "invalid cid 0x%x\n",
+			    parm->cid);
+		return NULL;
+	}
+
+	switch (parm->rev) {
+	case RTW89_ACPI_SAR_REV_LEGACY:
+	case RTW89_ACPI_SAR_REV_HAS_6GHZ:
+		id.rev = parm->rev;
+		break;
+	default:
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "invalid rev %u\n",
+			    parm->rev);
+		return NULL;
+	}
+
+	id.size = tbl_len;
+	for (unsigned int i = 0; i < ARRAY_SIZE(rtw89_acpi_sar_recs); i++) {
+		rec = &rtw89_acpi_sar_recs[i];
+		if (memcmp(&rec->id, &id, sizeof(rec->id)) == 0)
+			return rec;
+	}
+
+	rtw89_debug(rtwdev, RTW89_DBG_ACPI, "failed to recognize\n");
+	return NULL;
+}
+
+static const struct rtw89_acpi_sar_recognition *
+rtw89_acpi_evaluate_static_sar(struct rtw89_dev *rtwdev,
+			       struct rtw89_sar_cfg_acpi *cfg)
+{
+	const struct rtw89_acpi_sar_recognition *rec = NULL;
+	const struct rtw89_acpi_static_sar_hdr *hdr;
+	struct rtw89_sar_entry_from_acpi tmp = {};
+	struct rtw89_acpi_sar_rec_parm parm = {};
+	struct rtw89_sar_table_from_acpi *tbl;
+	const struct rtw89_acpi_data *data;
+	u32 len;
+
+	data = rtw89_acpi_evaluate_method(rtwdev, RTW89_ACPI_METHOD_STATIC_SAR);
+	if (!data)
+		return NULL;
+
+	rtw89_debug(rtwdev, RTW89_DBG_ACPI, "acpi load static sar\n");
+
+	len = data->len;
+	if (len <= sizeof(*hdr)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "invalid buf len %u\n", len);
 		goto out;
 	}
 
-	buf_len = obj->buffer.length;
-	if (buf_len != sizeof(*res)) {
-		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "%s: invalid buffer length: %u\n",
-			    __func__, buf_len);
+	hdr = (typeof(hdr))data->buf;
+
+	parm.cid = le16_to_cpu(hdr->cid);
+	parm.rev = hdr->rev;
+	parm.tbl_cnt = 1;
+	parm.pld_len = len - sizeof(*hdr);
+
+	rec = rtw89_acpi_sar_recognize(rtwdev, &parm);
+	if (!rec)
+		goto out;
+
+	rec->load(rtwdev, rec, hdr->content, &tmp);
+
+	tbl = &cfg->tables[0];
+	for (u8 regd = 0; regd < RTW89_REGD_NUM; regd++)
+		tbl->entries[regd] = tmp;
+
+	cfg->valid_num = 1;
+
+out:
+	kfree(data);
+	return rec;
+}
+
+static const struct rtw89_acpi_sar_recognition *
+rtw89_acpi_evaluate_dynamic_sar(struct rtw89_dev *rtwdev,
+				struct rtw89_sar_cfg_acpi *cfg)
+{
+	const struct rtw89_acpi_sar_recognition *rec = NULL;
+	const struct rtw89_acpi_dynamic_sar_hdr *hdr;
+	struct rtw89_acpi_sar_rec_parm parm = {};
+	struct rtw89_sar_table_from_acpi *tbl;
+	const struct rtw89_acpi_data *data;
+	u32 len;
+
+	data = rtw89_acpi_evaluate_method(rtwdev, RTW89_ACPI_METHOD_DYNAMIC_SAR);
+	if (!data)
+		return NULL;
+
+	rtw89_debug(rtwdev, RTW89_DBG_ACPI, "acpi load dynamic sar\n");
+
+	len = data->len;
+	if (len <= sizeof(*hdr)) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "invalid buf len %u\n", len);
+		goto out;
+	}
+
+	hdr = (typeof(hdr))data->buf;
+
+	parm.cid = le16_to_cpu(hdr->cid);
+	parm.rev = hdr->rev;
+	parm.tbl_cnt = hdr->cnt;
+	parm.pld_len = len - sizeof(*hdr);
+
+	rec = rtw89_acpi_sar_recognize(rtwdev, &parm);
+	if (!rec)
+		goto out;
+
+	for (unsigned int i = 0; i < hdr->cnt; i++) {
+		const u8 *content = hdr->content + rec->id.size * i;
+		struct rtw89_sar_entry_from_acpi tmp = {};
+
+		rec->load(rtwdev, rec, content, &tmp);
+
+		tbl = &cfg->tables[i];
+		for (u8 regd = 0; regd < RTW89_REGD_NUM; regd++)
+			tbl->entries[regd] = tmp;
+	}
+
+	cfg->valid_num = hdr->cnt;
+
+out:
+	kfree(data);
+	return rec;
+}
+
+int rtw89_acpi_evaluate_dynamic_sar_indicator(struct rtw89_dev *rtwdev,
+					      struct rtw89_sar_cfg_acpi *cfg,
+					      bool *poll_changed)
+{
+	struct rtw89_sar_indicator_from_acpi *ind = &cfg->indicator;
+	struct rtw89_sar_indicator_from_acpi tmp = *ind;
+	const struct rtw89_acpi_data *data;
+	const u8 *tbl_base1_by_ant;
+	enum rtw89_rf_path path;
+	int ret = 0;
+	u32 len;
+
+	data = rtw89_acpi_evaluate_method(rtwdev, RTW89_ACPI_METHOD_DYNAMIC_SAR_INDICATOR);
+	if (!data)
+		return -EFAULT;
+
+	if (!poll_changed)
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "acpi load dynamic sar indicator\n");
+
+	len = data->len;
+	if (len != ind->fields) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "invalid buf len %u\n", len);
 		ret = -EINVAL;
 		goto out;
 	}
 
-	*res = *(struct rtw89_acpi_rtag_result *)obj->buffer.pointer;
+	tbl_base1_by_ant = data->buf;
 
-	rtw89_hex_dump(rtwdev, RTW89_DBG_ACPI, "antenna_gain: ", res, sizeof(*res));
+	for (path = 0; path < NUM_OF_RTW89_ACPI_SAR_RF_PATH; path++) {
+		u8 antidx = ind->rfpath_to_antidx(path);
+		u8 sel;
+
+		if (antidx >= ind->fields)
+			antidx = 0;
+
+		/* convert the table index from 1-based to 0-based */
+		sel = tbl_base1_by_ant[antidx] - 1;
+		if (sel >= cfg->valid_num)
+			sel = 0;
+
+		tmp.tblsel[path] = sel;
+	}
+
+	if (memcmp(ind, &tmp, sizeof(*ind)) == 0) {
+		if (poll_changed)
+			*poll_changed = false;
+	} else {
+		if (poll_changed)
+			*poll_changed = true;
+
+		*ind = tmp;
+	}
 
 out:
-	ACPI_FREE(obj);
+	kfree(data);
 	return ret;
 }
+
+static
+void rtw89_acpi_evaluate_geo_sar(struct rtw89_dev *rtwdev,
+				 const struct rtw89_acpi_geo_sar_handler *hdl,
+				 struct rtw89_sar_cfg_acpi *cfg)
+{
+	const struct rtw89_acpi_data *data;
+	u32 len;
+
+	data = rtw89_acpi_evaluate_method(rtwdev, RTW89_ACPI_METHOD_GEO_SAR);
+	if (!data)
+		return;
+
+	rtw89_debug(rtwdev, RTW89_DBG_ACPI, "acpi load geo sar\n");
+
+	len = data->len;
+	if (len != hdl->data_size) {
+		rtw89_debug(rtwdev, RTW89_DBG_ACPI, "invalid buf len %u (expected %u)\n",
+			    len, hdl->data_size);
+		goto out;
+	}
+
+	for (unsigned int i = 0; i < cfg->valid_num; i++)
+		for (u8 regd = 0; regd < RTW89_REGD_NUM; regd++)
+			hdl->load(rtwdev, data->buf, regd, &cfg->tables[i].entries[regd]);
+
+out:
+	kfree(data);
+}
+
+int rtw89_acpi_evaluate_sar(struct rtw89_dev *rtwdev,
+			    struct rtw89_sar_cfg_acpi *cfg)
+{
+	struct rtw89_sar_indicator_from_acpi *ind = &cfg->indicator;
+	const struct rtw89_acpi_sar_recognition *rec;
+	bool fetch_indicator = false;
+	int ret;
+
+	rec = rtw89_acpi_evaluate_static_sar(rtwdev, cfg);
+	if (rec)
+		goto recognized;
+
+	rec = rtw89_acpi_evaluate_dynamic_sar(rtwdev, cfg);
+	if (!rec)
+		return -ENOENT;
+
+	fetch_indicator = true;
+
+recognized:
+	rtw89_acpi_evaluate_geo_sar(rtwdev, rec->geo, cfg);
+
+	switch (rec->id.cid) {
+	case RTW89_ACPI_SAR_CID_HP:
+		cfg->downgrade_2tx = 3 << TXPWR_FACTOR_OF_RTW89_ACPI_SAR;
+		ind->fields = RTW89_ACPI_SAR_ANT_NR_STD;
+		break;
+	case RTW89_ACPI_SAR_CID_RT:
+		cfg->downgrade_2tx = 0;
+		ind->fields = 1;
+		break;
+	default:
+		return -EFAULT;
+	}
+
+	if (fetch_indicator) {
+		ind->rfpath_to_antidx = rec->rfpath_to_antidx;
+		ret = rtw89_acpi_evaluate_dynamic_sar_indicator(rtwdev, cfg, NULL);
+		if (ret)
+			fetch_indicator = false;
+	}
+
+	if (!fetch_indicator)
+		memset(ind->tblsel, 0, sizeof(ind->tblsel));
+
+	ind->enable_sync = fetch_indicator;
+	return 0;
+}
diff --git a/drivers/net/wireless/realtek/rtw89/acpi.h b/drivers/net/wireless/realtek/rtw89/acpi.h
index b43ab106e44d..8c918ee02d2e 100644
--- a/drivers/net/wireless/realtek/rtw89/acpi.h
+++ b/drivers/net/wireless/realtek/rtw89/acpi.h
@@ -7,6 +7,11 @@
 
 #include "core.h"
 
+struct rtw89_acpi_data {
+	u32 len;
+	u8 buf[] __counted_by(len);
+};
+
 enum rtw89_acpi_dsm_func {
 	RTW89_ACPI_DSM_FUNC_IDN_BAND_SUP = 2,
 	RTW89_ACPI_DSM_FUNC_6G_DIS = 3,
@@ -26,6 +31,13 @@ enum rtw89_acpi_policy_mode {
 	RTW89_ACPI_POLICY_ALLOW = 1,
 };
 
+enum rtw89_acpi_conf_tas {
+	RTW89_ACPI_CONF_TAS_US = BIT(0),
+	RTW89_ACPI_CONF_TAS_CA = BIT(1),
+	RTW89_ACPI_CONF_TAS_KR = BIT(2),
+	RTW89_ACPI_CONF_TAS_OTHERS = BIT(7),
+};
+
 struct rtw89_acpi_country_code {
 	/* below are allowed:
 	 * * ISO alpha2 country code
@@ -54,12 +66,21 @@ struct rtw89_acpi_policy_6ghz_sp {
 	u8 rsvd;
 } __packed;
 
+struct rtw89_acpi_policy_tas {
+	u8 signature[4];
+	u8 revision;
+	u8 enable;
+	u8 enabled_countries;
+	u8 rsvd[3];
+} __packed;
+
 struct rtw89_acpi_dsm_result {
 	union {
 		u8 value;
 		/* caller needs to free it after using */
 		struct rtw89_acpi_policy_6ghz *policy_6ghz;
 		struct rtw89_acpi_policy_6ghz_sp *policy_6ghz_sp;
+		struct rtw89_acpi_policy_tas *policy_tas;
 	} u;
 };
 
@@ -70,10 +91,179 @@ struct rtw89_acpi_rtag_result {
 	u8 ant_gain_table[RTW89_ANT_GAIN_CHAIN_NUM][RTW89_ANT_GAIN_SUBBAND_NR];
 } __packed;
 
+enum rtw89_acpi_sar_cid {
+	RTW89_ACPI_SAR_CID_HP = 0x5048,
+	RTW89_ACPI_SAR_CID_RT = 0x5452,
+};
+
+enum rtw89_acpi_sar_rev {
+	RTW89_ACPI_SAR_REV_LEGACY = 1,
+	RTW89_ACPI_SAR_REV_HAS_6GHZ = 2,
+};
+
+#define RTW89_ACPI_SAR_ANT_NR_STD 4
+#define RTW89_ACPI_SAR_ANT_NR_SML 2
+
+#define RTW89_ACPI_METHOD_STATIC_SAR "WRDS"
+#define RTW89_ACPI_METHOD_DYNAMIC_SAR "RWRD"
+#define RTW89_ACPI_METHOD_DYNAMIC_SAR_INDICATOR "RWSI"
+#define RTW89_ACPI_METHOD_GEO_SAR "RWGS"
+
+struct rtw89_acpi_sar_std_legacy {
+	u8 v[RTW89_ACPI_SAR_ANT_NR_STD][RTW89_ACPI_SAR_SUBBAND_NR_LEGACY];
+} __packed;
+
+struct rtw89_acpi_sar_std_has_6ghz {
+	u8 v[RTW89_ACPI_SAR_ANT_NR_STD][RTW89_ACPI_SAR_SUBBAND_NR_HAS_6GHZ];
+} __packed;
+
+struct rtw89_acpi_sar_sml_legacy {
+	u8 v[RTW89_ACPI_SAR_ANT_NR_SML][RTW89_ACPI_SAR_SUBBAND_NR_LEGACY];
+} __packed;
+
+struct rtw89_acpi_sar_sml_has_6ghz {
+	u8 v[RTW89_ACPI_SAR_ANT_NR_SML][RTW89_ACPI_SAR_SUBBAND_NR_HAS_6GHZ];
+} __packed;
+
+struct rtw89_acpi_static_sar_hdr {
+	__le16 cid;
+	u8 rev;
+	u8 content[];
+} __packed;
+
+struct rtw89_acpi_dynamic_sar_hdr {
+	__le16 cid;
+	u8 rev;
+	u8 cnt;
+	u8 content[];
+} __packed;
+
+struct rtw89_acpi_sar_identifier {
+	enum rtw89_acpi_sar_cid cid;
+	enum rtw89_acpi_sar_rev rev;
+	u8 size;
+};
+
+/* for rtw89_acpi_sar_identifier::size */
+#define RTW89_ACPI_SAR_SIZE_MAX U8_MAX
+#define RTW89_ACPI_SAR_SIZE_OF(type) \
+	(BUILD_BUG_ON_ZERO(sizeof(struct rtw89_acpi_sar_ ## type) > \
+			   RTW89_ACPI_SAR_SIZE_MAX) + \
+	 sizeof(struct rtw89_acpi_sar_ ## type))
+
+struct rtw89_acpi_sar_recognition {
+	struct rtw89_acpi_sar_identifier id;
+	const struct rtw89_acpi_geo_sar_handler *geo;
+
+	u8 (*rfpath_to_antidx)(enum rtw89_rf_path rfpath);
+	s16 (*normalize)(u8 v);
+	void (*load)(struct rtw89_dev *rtwdev,
+		     const struct rtw89_acpi_sar_recognition *rec,
+		     const void *content,
+		     struct rtw89_sar_entry_from_acpi *ent);
+};
+
+struct rtw89_acpi_geo_sar_hp_val {
+	u8 max;
+	s8 delta[RTW89_ACPI_SAR_ANT_NR_STD];
+} __packed;
+
+struct rtw89_acpi_geo_sar_hp_legacy_entry {
+	struct rtw89_acpi_geo_sar_hp_val val_2ghz;
+	struct rtw89_acpi_geo_sar_hp_val val_5ghz;
+} __packed;
+
+struct rtw89_acpi_geo_sar_hp_has_6ghz_entry {
+	struct rtw89_acpi_geo_sar_hp_val val_2ghz;
+	struct rtw89_acpi_geo_sar_hp_val val_5ghz;
+	struct rtw89_acpi_geo_sar_hp_val val_6ghz;
+} __packed;
+
+enum rtw89_acpi_geo_sar_regd_hp {
+	RTW89_ACPI_GEO_SAR_REGD_HP_FCC = 0,
+	RTW89_ACPI_GEO_SAR_REGD_HP_ETSI = 1,
+	RTW89_ACPI_GEO_SAR_REGD_HP_WW = 2,
+
+	RTW89_ACPI_GEO_SAR_REGD_NR_HP,
+};
+
+struct rtw89_acpi_geo_sar_hp_legacy {
+	struct rtw89_acpi_geo_sar_hp_legacy_entry
+		entries[RTW89_ACPI_GEO_SAR_REGD_NR_HP];
+} __packed;
+
+struct rtw89_acpi_geo_sar_hp_has_6ghz {
+	struct rtw89_acpi_geo_sar_hp_has_6ghz_entry
+		entries[RTW89_ACPI_GEO_SAR_REGD_NR_HP];
+} __packed;
+
+struct rtw89_acpi_geo_sar_rt_val {
+	u8 max;
+	s8 delta;
+} __packed;
+
+struct rtw89_acpi_geo_sar_rt_legacy_entry {
+	struct rtw89_acpi_geo_sar_rt_val val_2ghz;
+	struct rtw89_acpi_geo_sar_rt_val val_5ghz;
+} __packed;
+
+struct rtw89_acpi_geo_sar_rt_has_6ghz_entry {
+	struct rtw89_acpi_geo_sar_rt_val val_2ghz;
+	struct rtw89_acpi_geo_sar_rt_val val_5ghz;
+	struct rtw89_acpi_geo_sar_rt_val val_6ghz;
+} __packed;
+
+enum rtw89_acpi_geo_sar_regd_rt {
+	RTW89_ACPI_GEO_SAR_REGD_RT_FCC = 0,
+	RTW89_ACPI_GEO_SAR_REGD_RT_ETSI = 1,
+	RTW89_ACPI_GEO_SAR_REGD_RT_MKK = 2,
+	RTW89_ACPI_GEO_SAR_REGD_RT_IC = 3,
+	RTW89_ACPI_GEO_SAR_REGD_RT_KCC = 4,
+	RTW89_ACPI_GEO_SAR_REGD_RT_WW = 5,
+
+	RTW89_ACPI_GEO_SAR_REGD_NR_RT,
+};
+
+struct rtw89_acpi_geo_sar_rt_legacy {
+	struct rtw89_acpi_geo_sar_rt_legacy_entry
+		entries[RTW89_ACPI_GEO_SAR_REGD_NR_RT];
+} __packed;
+
+struct rtw89_acpi_geo_sar_rt_has_6ghz {
+	struct rtw89_acpi_geo_sar_rt_has_6ghz_entry
+		entries[RTW89_ACPI_GEO_SAR_REGD_NR_RT];
+} __packed;
+
+struct rtw89_acpi_geo_sar_handler {
+	u8 data_size;
+
+	void (*load)(struct rtw89_dev *rtwdev,
+		     const void *content,
+		     enum rtw89_regulation_type regd,
+		     struct rtw89_sar_entry_from_acpi *ent);
+};
+
+/* for rtw89_acpi_geo_sar_handler::data_size */
+#define RTW89_ACPI_GEO_SAR_SIZE_MAX U8_MAX
+#define RTW89_ACPI_GEO_SAR_SIZE_OF(type) \
+	(BUILD_BUG_ON_ZERO(sizeof(struct rtw89_acpi_geo_sar_ ## type) > \
+			   RTW89_ACPI_GEO_SAR_SIZE_MAX) + \
+	 sizeof(struct rtw89_acpi_geo_sar_ ## type))
+
+enum rtw89_acpi_sar_subband rtw89_acpi_sar_get_subband(struct rtw89_dev *rtwdev,
+						       u32 center_freq);
+enum rtw89_band rtw89_acpi_sar_subband_to_band(struct rtw89_dev *rtwdev,
+					       enum rtw89_acpi_sar_subband subband);
+
 int rtw89_acpi_evaluate_dsm(struct rtw89_dev *rtwdev,
 			    enum rtw89_acpi_dsm_func func,
 			    struct rtw89_acpi_dsm_result *res);
 int rtw89_acpi_evaluate_rtag(struct rtw89_dev *rtwdev,
 			     struct rtw89_acpi_rtag_result *res);
+int rtw89_acpi_evaluate_sar(struct rtw89_dev *rtwdev,
+			    struct rtw89_sar_cfg_acpi *cfg);
+int rtw89_acpi_evaluate_dynamic_sar_indicator(struct rtw89_dev *rtwdev,
+					      struct rtw89_sar_cfg_acpi *cfg,
+					      bool *changed);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/cam.c b/drivers/net/wireless/realtek/rtw89/cam.c
index eca3d767ff60..385a238fe5cc 100644
--- a/drivers/net/wireless/realtek/rtw89/cam.c
+++ b/drivers/net/wireless/realtek/rtw89/cam.c
@@ -6,6 +6,7 @@
 #include "debug.h"
 #include "fw.h"
 #include "mac.h"
+#include "ps.h"
 
 static struct sk_buff *
 rtw89_cam_get_sec_key_cmd(struct rtw89_dev *rtwdev,
@@ -469,11 +470,17 @@ int rtw89_cam_sec_key_add(struct rtw89_dev *rtwdev,
 	bool ext_key = false;
 	int ret;
 
+	if (ieee80211_vif_is_mld(vif) && !chip->hw_mlo_bmc_crypto &&
+	    !(key->flags & IEEE80211_KEY_FLAG_PAIRWISE))
+		return -EOPNOTSUPP;
+
 	switch (key->cipher) {
 	case WLAN_CIPHER_SUITE_WEP40:
+		rtw89_leave_ips_by_hwflags(rtwdev);
 		hw_key_type = RTW89_SEC_KEY_TYPE_WEP40;
 		break;
 	case WLAN_CIPHER_SUITE_WEP104:
+		rtw89_leave_ips_by_hwflags(rtwdev);
 		hw_key_type = RTW89_SEC_KEY_TYPE_WEP104;
 		break;
 	case WLAN_CIPHER_SUITE_TKIP:
diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index f60e93870b09..806f42429a29 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -189,9 +189,10 @@ void rtw89_config_entity_chandef(struct rtw89_dev *rtwdev,
 }
 
 void rtw89_config_roc_chandef(struct rtw89_dev *rtwdev,
-			      enum rtw89_chanctx_idx idx,
+			      struct rtw89_vif_link *rtwvif_link,
 			      const struct cfg80211_chan_def *chandef)
 {
+	enum rtw89_chanctx_idx idx = rtwvif_link->chanctx_idx;
 	struct rtw89_hal *hal = &rtwdev->hal;
 	enum rtw89_chanctx_idx cur;
 
@@ -205,6 +206,7 @@ void rtw89_config_roc_chandef(struct rtw89_dev *rtwdev,
 		}
 
 		hal->roc_chandef = *chandef;
+		hal->roc_link_index = rtw89_vif_link_inst_get_index(rtwvif_link);
 	} else {
 		cur = atomic_cmpxchg(&hal->roc_chanctx_idx, idx,
 				     RTW89_CHANCTX_IDLE);
@@ -339,11 +341,10 @@ const struct rtw89_chan *__rtw89_mgnt_chan_get(struct rtw89_dev *rtwdev,
 
 	roc_idx = atomic_read(&hal->roc_chanctx_idx);
 	if (roc_idx != RTW89_CHANCTX_IDLE) {
-		/* ROC is ongoing (given ROC runs on RTW89_ROC_BY_LINK_INDEX).
-		 * If @link_index is the same as RTW89_ROC_BY_LINK_INDEX, get
-		 * the ongoing ROC chanctx.
+		/* ROC is ongoing (given ROC runs on @hal->roc_link_index).
+		 * If @link_index is the same, get the ongoing ROC chanctx.
 		 */
-		if (link_index == RTW89_ROC_BY_LINK_INDEX)
+		if (link_index == hal->roc_link_index)
 			chanctx_idx = roc_idx;
 	}
 
@@ -358,12 +359,41 @@ dflt:
 }
 EXPORT_SYMBOL(__rtw89_mgnt_chan_get);
 
+static enum rtw89_mlo_dbcc_mode
+rtw89_entity_sel_mlo_dbcc_mode(struct rtw89_dev *rtwdev, u8 active_hws)
+{
+	if (rtwdev->chip->chip_gen != RTW89_CHIP_BE)
+		return MLO_DBCC_NOT_SUPPORT;
+
+	switch (active_hws) {
+	case BIT(0):
+		return MLO_2_PLUS_0_1RF;
+	case BIT(1):
+		return MLO_0_PLUS_2_1RF;
+	case BIT(0) | BIT(1):
+	default:
+		return MLO_1_PLUS_1_1RF;
+	}
+}
+
+static
+void rtw89_entity_recalc_mlo_dbcc_mode(struct rtw89_dev *rtwdev, u8 active_hws)
+{
+	enum rtw89_mlo_dbcc_mode mode;
+
+	mode = rtw89_entity_sel_mlo_dbcc_mode(rtwdev, active_hws);
+	rtwdev->mlo_dbcc_mode = mode;
+
+	rtw89_debug(rtwdev, RTW89_DBG_STATE, "recalc mlo dbcc mode to %d\n", mode);
+}
+
 static void rtw89_entity_recalc_mgnt_roles(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
 	struct rtw89_entity_mgnt *mgnt = &hal->entity_mgnt;
 	struct rtw89_vif_link *link;
 	struct rtw89_vif *role;
+	u8 active_hws = 0;
 	u8 pos = 0;
 	int i, j;
 
@@ -412,10 +442,13 @@ fill:
 				continue;
 
 			mgnt->chanctx_tbl[pos][i] = link->chanctx_idx;
+			active_hws |= BIT(i);
 		}
 
 		mgnt->active_roles[pos++] = role;
 	}
+
+	rtw89_entity_recalc_mlo_dbcc_mode(rtwdev, active_hws);
 }
 
 enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev)
@@ -557,7 +590,9 @@ static u32 rtw89_mcc_get_tbtt_ofst(struct rtw89_dev *rtwdev,
 	u64 sync_tsf = READ_ONCE(rtwvif_link->sync_bcn_tsf);
 	u32 remainder;
 
-	if (tsf < sync_tsf) {
+	if (role->is_go) {
+		sync_tsf = 0;
+	} else if (tsf < sync_tsf) {
 		rtw89_debug(rtwdev, RTW89_DBG_CHAN,
 			    "MCC get tbtt ofst: tsf might not update yet\n");
 		sync_tsf = 0;
@@ -691,19 +726,13 @@ static void rtw89_mcc_role_macid_sta_iter(void *data, struct ieee80211_sta *sta)
 	struct rtw89_vif *target = mcc_role->rtwvif_link->rtwvif;
 	struct rtw89_sta *rtwsta = sta_to_rtwsta(sta);
 	struct rtw89_vif *rtwvif = rtwsta->rtwvif;
-	struct rtw89_dev *rtwdev = rtwsta->rtwdev;
-	struct rtw89_sta_link *rtwsta_link;
+	u8 macid;
 
 	if (rtwvif != target)
 		return;
 
-	rtwsta_link = rtw89_sta_get_link_inst(rtwsta, 0);
-	if (unlikely(!rtwsta_link)) {
-		rtw89_err(rtwdev, "mcc sta macid: find no link on HW-0\n");
-		return;
-	}
-
-	rtw89_mcc_role_fw_macid_bitmap_set_bit(mcc_role, rtwsta_link->mac_id);
+	macid = rtw89_sta_get_main_macid(rtwsta);
+	rtw89_mcc_role_fw_macid_bitmap_set_bit(mcc_role, macid);
 }
 
 static void rtw89_mcc_fill_role_macid_bitmap(struct rtw89_dev *rtwdev,
@@ -747,9 +776,11 @@ static void rtw89_mcc_fill_role_limit(struct rtw89_dev *rtwdev,
 	int ret;
 	int i;
 
-	if (!mcc_role->is_go && !mcc_role->is_gc)
+	if (!mcc_role->is_gc)
 		return;
 
+	rtw89_p2p_noa_once_recalc(rtwvif_link);
+
 	rcu_read_lock();
 
 	bss_conf = rtw89_vif_rcu_dereference_link(rtwvif_link, true);
@@ -785,6 +816,9 @@ fill:
 	}
 
 	tsf_lmt = (tsf & GENMASK_ULL(63, 32)) | start_time;
+	if (tsf_lmt < tsf)
+		tsf_lmt += roundup_u64(tsf - tsf_lmt, interval);
+
 	max_toa_us = rtw89_mcc_get_tbtt_ofst(rtwdev, mcc_role, tsf_lmt);
 	max_dur_us = interval - duration;
 	max_tob_us = max_dur_us - max_toa_us;
@@ -929,6 +963,15 @@ static int rtw89_mcc_fill_all_roles(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
+static bool rtw89_mcc_can_courtesy(const struct rtw89_mcc_role *provider,
+				   const struct rtw89_mcc_role *receiver)
+{
+	if (provider->is_go || receiver->is_gc)
+		return false;
+
+	return true;
+}
+
 static void rtw89_mcc_assign_pattern(struct rtw89_dev *rtwdev,
 				     const struct rtw89_mcc_pattern *new)
 {
@@ -937,37 +980,44 @@ static void rtw89_mcc_assign_pattern(struct rtw89_dev *rtwdev,
 	struct rtw89_mcc_role *aux = &mcc->role_aux;
 	struct rtw89_mcc_config *config = &mcc->config;
 	struct rtw89_mcc_pattern *pattern = &config->pattern;
+	struct rtw89_mcc_courtesy_cfg *crtz;
 
 	rtw89_debug(rtwdev, RTW89_DBG_CHAN,
 		    "MCC assign pattern: ref {%d | %d}, aux {%d | %d}\n",
 		    new->tob_ref, new->toa_ref, new->tob_aux, new->toa_aux);
 
+	rtw89_debug(rtwdev, RTW89_DBG_CHAN, "MCC pattern plan: %d\n", new->plan);
+
 	*pattern = *new;
 	memset(&pattern->courtesy, 0, sizeof(pattern->courtesy));
 
-	if (pattern->tob_aux <= 0 || pattern->toa_aux <= 0) {
-		pattern->courtesy.macid_tgt = aux->rtwvif_link->mac_id;
-		pattern->courtesy.macid_src = ref->rtwvif_link->mac_id;
-		pattern->courtesy.slot_num = RTW89_MCC_DFLT_COURTESY_SLOT;
-		pattern->courtesy.enable = true;
-	} else if (pattern->tob_ref <= 0 || pattern->toa_ref <= 0) {
-		pattern->courtesy.macid_tgt = ref->rtwvif_link->mac_id;
-		pattern->courtesy.macid_src = aux->rtwvif_link->mac_id;
-		pattern->courtesy.slot_num = RTW89_MCC_DFLT_COURTESY_SLOT;
-		pattern->courtesy.enable = true;
+	if (RTW89_MCC_REQ_COURTESY(pattern, aux) && rtw89_mcc_can_courtesy(ref, aux)) {
+		crtz = &pattern->courtesy.ref;
+		ref->crtz = crtz;
+
+		crtz->macid_tgt = aux->rtwvif_link->mac_id;
+		crtz->slot_num = RTW89_MCC_DFLT_COURTESY_SLOT;
+
+		rtw89_debug(rtwdev, RTW89_DBG_CHAN,
+			    "MCC courtesy ref: tgt %d, slot %d\n",
+			    crtz->macid_tgt, crtz->slot_num);
+	} else {
+		ref->crtz = NULL;
 	}
 
-	rtw89_debug(rtwdev, RTW89_DBG_CHAN,
-		    "MCC pattern flags: plan %d, courtesy_en %d\n",
-		    pattern->plan, pattern->courtesy.enable);
+	if (RTW89_MCC_REQ_COURTESY(pattern, ref) && rtw89_mcc_can_courtesy(aux, ref)) {
+		crtz = &pattern->courtesy.aux;
+		aux->crtz = crtz;
 
-	if (!pattern->courtesy.enable)
-		return;
+		crtz->macid_tgt = ref->rtwvif_link->mac_id;
+		crtz->slot_num = RTW89_MCC_DFLT_COURTESY_SLOT;
 
-	rtw89_debug(rtwdev, RTW89_DBG_CHAN,
-		    "MCC pattern courtesy: tgt %d, src %d, slot %d\n",
-		    pattern->courtesy.macid_tgt, pattern->courtesy.macid_src,
-		    pattern->courtesy.slot_num);
+		rtw89_debug(rtwdev, RTW89_DBG_CHAN,
+			    "MCC courtesy aux: tgt %d, slot %d\n",
+			    crtz->macid_tgt, crtz->slot_num);
+	} else {
+		aux->crtz = NULL;
+	}
 }
 
 /* The follow-up roughly shows the relationship between the parameters
@@ -992,6 +1042,7 @@ static void __rtw89_mcc_calc_pattern_loose(struct rtw89_dev *rtwdev,
 	struct rtw89_mcc_role *ref = &mcc->role_ref;
 	struct rtw89_mcc_role *aux = &mcc->role_aux;
 	struct rtw89_mcc_config *config = &mcc->config;
+	u16 mcc_intvl = config->mcc_interval;
 	u16 bcn_ofst = config->beacon_offset;
 	u16 bt_dur_in_mid = 0;
 	u16 max_bcn_ofst;
@@ -1025,7 +1076,7 @@ calc:
 
 	res = bcn_ofst - bt_dur_in_mid;
 	upper = min_t(s16, ref->duration, res);
-	lower = 0;
+	lower = max_t(s16, 0, ref->duration - (mcc_intvl - bcn_ofst));
 
 	if (ref->limit.enable) {
 		upper = min_t(s16, upper, ref->limit.max_toa);
@@ -1136,6 +1187,107 @@ static int __rtw89_mcc_calc_pattern_strict(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
+static void __rtw89_mcc_fill_ptrn_anchor_ref(struct rtw89_dev *rtwdev,
+					     struct rtw89_mcc_pattern *ptrn,
+					     bool small_bcn_ofst)
+{
+	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
+	struct rtw89_mcc_role *ref = &mcc->role_ref;
+	struct rtw89_mcc_role *aux = &mcc->role_aux;
+	struct rtw89_mcc_config *config = &mcc->config;
+	u16 bcn_ofst = config->beacon_offset;
+	u16 ref_tob;
+	u16 ref_toa;
+
+	if (ref->limit.enable) {
+		ref_tob = ref->limit.max_tob;
+		ref_toa = ref->limit.max_toa;
+	} else {
+		ref_tob = ref->duration / 2;
+		ref_toa = ref->duration / 2;
+	}
+
+	if (small_bcn_ofst) {
+		ptrn->toa_ref = ref_toa;
+		ptrn->tob_ref = ref->duration - ptrn->toa_ref;
+	} else {
+		ptrn->tob_ref = ref_tob;
+		ptrn->toa_ref = ref->duration - ptrn->tob_ref;
+	}
+
+	ptrn->tob_aux = bcn_ofst - ptrn->toa_ref;
+	ptrn->toa_aux = aux->duration - ptrn->tob_aux;
+}
+
+static void __rtw89_mcc_fill_ptrn_anchor_aux(struct rtw89_dev *rtwdev,
+					     struct rtw89_mcc_pattern *ptrn,
+					     bool small_bcn_ofst)
+{
+	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
+	struct rtw89_mcc_role *ref = &mcc->role_ref;
+	struct rtw89_mcc_role *aux = &mcc->role_aux;
+	struct rtw89_mcc_config *config = &mcc->config;
+	u16 bcn_ofst = config->beacon_offset;
+	u16 aux_tob;
+	u16 aux_toa;
+
+	if (aux->limit.enable) {
+		aux_tob = aux->limit.max_tob;
+		aux_toa = aux->limit.max_toa;
+	} else {
+		aux_tob = aux->duration / 2;
+		aux_toa = aux->duration / 2;
+	}
+
+	if (small_bcn_ofst) {
+		ptrn->tob_aux = aux_tob;
+		ptrn->toa_aux = aux->duration - ptrn->tob_aux;
+	} else {
+		ptrn->toa_aux = aux_toa;
+		ptrn->tob_aux = aux->duration - ptrn->toa_aux;
+	}
+
+	ptrn->toa_ref = bcn_ofst - ptrn->tob_aux;
+	ptrn->tob_ref = ref->duration - ptrn->toa_ref;
+}
+
+static int __rtw89_mcc_calc_pattern_anchor(struct rtw89_dev *rtwdev,
+					   struct rtw89_mcc_pattern *ptrn,
+					   bool hdl_bt)
+{
+	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
+	struct rtw89_mcc_role *ref = &mcc->role_ref;
+	struct rtw89_mcc_role *aux = &mcc->role_aux;
+	struct rtw89_mcc_config *config = &mcc->config;
+	u16 mcc_intvl = config->mcc_interval;
+	u16 bcn_ofst = config->beacon_offset;
+	bool small_bcn_ofst;
+
+	if (bcn_ofst < RTW89_MCC_MIN_RX_BCN_TIME)
+		small_bcn_ofst = true;
+	else if (mcc_intvl - bcn_ofst < RTW89_MCC_MIN_RX_BCN_TIME)
+		small_bcn_ofst = false;
+	else
+		return -EPERM;
+
+	*ptrn = (typeof(*ptrn)){
+		.plan = hdl_bt ? RTW89_MCC_PLAN_TAIL_BT : RTW89_MCC_PLAN_NO_BT,
+	};
+
+	rtw89_debug(rtwdev, RTW89_DBG_CHAN,
+		    "MCC calc ptrn_ac: plan %d, bcn_ofst %d\n",
+		    ptrn->plan, bcn_ofst);
+
+	if (ref->is_go || ref->is_gc)
+		__rtw89_mcc_fill_ptrn_anchor_ref(rtwdev, ptrn, small_bcn_ofst);
+	else if (aux->is_go || aux->is_gc)
+		__rtw89_mcc_fill_ptrn_anchor_aux(rtwdev, ptrn, small_bcn_ofst);
+	else
+		__rtw89_mcc_fill_ptrn_anchor_ref(rtwdev, ptrn, small_bcn_ofst);
+
+	return 0;
+}
+
 static int rtw89_mcc_calc_pattern(struct rtw89_dev *rtwdev, bool hdl_bt)
 {
 	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
@@ -1189,6 +1341,10 @@ static int rtw89_mcc_calc_pattern(struct rtw89_dev *rtwdev, bool hdl_bt)
 			goto done;
 	}
 
+	ret = __rtw89_mcc_calc_pattern_anchor(rtwdev, &ptrn, hdl_bt);
+	if (!ret)
+		goto done;
+
 	__rtw89_mcc_calc_pattern_loose(rtwdev, &ptrn, hdl_bt);
 
 done:
@@ -1439,88 +1595,41 @@ static bool rtw89_mcc_duration_decision_on_bt(struct rtw89_dev *rtwdev)
 	return false;
 }
 
-static void rtw89_mcc_sync_tbtt(struct rtw89_dev *rtwdev,
-				struct rtw89_mcc_role *tgt,
-				struct rtw89_mcc_role *src,
-				bool ref_is_src)
-{
-	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
-	struct rtw89_mcc_config *config = &mcc->config;
-	u16 beacon_offset_us = ieee80211_tu_to_usec(config->beacon_offset);
-	u32 bcn_intvl_src_us = ieee80211_tu_to_usec(src->beacon_interval);
-	u32 cur_tbtt_ofst_src;
-	u32 tsf_ofst_tgt;
-	u32 remainder;
-	u64 tbtt_tgt;
-	u64 tsf_src;
-	int ret;
-
-	ret = rtw89_mac_port_get_tsf(rtwdev, src->rtwvif_link, &tsf_src);
-	if (ret) {
-		rtw89_warn(rtwdev, "MCC failed to get port tsf: %d\n", ret);
-		return;
-	}
-
-	cur_tbtt_ofst_src = rtw89_mcc_get_tbtt_ofst(rtwdev, src, tsf_src);
-
-	if (ref_is_src)
-		tbtt_tgt = tsf_src - cur_tbtt_ofst_src + beacon_offset_us;
-	else
-		tbtt_tgt = tsf_src - cur_tbtt_ofst_src +
-			   (bcn_intvl_src_us - beacon_offset_us);
-
-	div_u64_rem(tbtt_tgt, bcn_intvl_src_us, &remainder);
-	tsf_ofst_tgt = bcn_intvl_src_us - remainder;
-
-	config->sync.macid_tgt = tgt->rtwvif_link->mac_id;
-	config->sync.band_tgt = tgt->rtwvif_link->mac_idx;
-	config->sync.port_tgt = tgt->rtwvif_link->port;
-	config->sync.macid_src = src->rtwvif_link->mac_id;
-	config->sync.band_src = src->rtwvif_link->mac_idx;
-	config->sync.port_src = src->rtwvif_link->port;
-	config->sync.offset = tsf_ofst_tgt / 1024;
-	config->sync.enable = true;
-
-	rtw89_debug(rtwdev, RTW89_DBG_CHAN,
-		    "MCC sync tbtt: tgt %d, src %d, offset %d\n",
-		    config->sync.macid_tgt, config->sync.macid_src,
-		    config->sync.offset);
-
-	rtw89_mac_port_tsf_sync(rtwdev, tgt->rtwvif_link, src->rtwvif_link,
-				config->sync.offset);
-}
-
 static int rtw89_mcc_fill_start_tsf(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
 	struct rtw89_mcc_role *ref = &mcc->role_ref;
+	struct rtw89_mcc_role *aux = &mcc->role_aux;
 	struct rtw89_mcc_config *config = &mcc->config;
 	u32 bcn_intvl_ref_us = ieee80211_tu_to_usec(ref->beacon_interval);
-	u32 tob_ref_us = ieee80211_tu_to_usec(config->pattern.tob_ref);
-	struct rtw89_vif_link *rtwvif_link = ref->rtwvif_link;
+	s32 tob_ref_us = ieee80211_tu_to_usec(config->pattern.tob_ref);
 	u64 tsf, start_tsf;
 	u32 cur_tbtt_ofst;
 	u64 min_time;
+	u64 tsf_aux;
 	int ret;
 
-	ret = rtw89_mac_port_get_tsf(rtwdev, rtwvif_link, &tsf);
-	if (ret) {
-		rtw89_warn(rtwdev, "MCC failed to get port tsf: %d\n", ret);
+	if (rtw89_concurrent_via_mrc(rtwdev))
+		ret = __mrc_fw_req_tsf(rtwdev, &tsf, &tsf_aux);
+	else
+		ret = __mcc_fw_req_tsf(rtwdev, &tsf, &tsf_aux);
+
+	if (ret)
 		return ret;
-	}
 
 	min_time = tsf;
-	if (ref->is_go)
+	if (ref->is_go || aux->is_go)
 		min_time += ieee80211_tu_to_usec(RTW89_MCC_SHORT_TRIGGER_TIME);
 	else
 		min_time += ieee80211_tu_to_usec(RTW89_MCC_LONG_TRIGGER_TIME);
 
 	cur_tbtt_ofst = rtw89_mcc_get_tbtt_ofst(rtwdev, ref, tsf);
 	start_tsf = tsf - cur_tbtt_ofst + bcn_intvl_ref_us - tob_ref_us;
-	while (start_tsf < min_time)
-		start_tsf += bcn_intvl_ref_us;
+	if (start_tsf < min_time)
+		start_tsf += roundup_u64(min_time - start_tsf, bcn_intvl_ref_us);
 
 	config->start_tsf = start_tsf;
+	config->start_tsf_in_aux_domain = tsf_aux + start_tsf - tsf;
 	return 0;
 }
 
@@ -1537,13 +1646,11 @@ static int rtw89_mcc_fill_config(struct rtw89_dev *rtwdev)
 
 	switch (mcc->mode) {
 	case RTW89_MCC_MODE_GO_STA:
-		config->beacon_offset = RTW89_MCC_DFLT_BCN_OFST_TIME;
+		config->beacon_offset = rtw89_mcc_get_bcn_ofst(rtwdev);
 		if (ref->is_go) {
-			rtw89_mcc_sync_tbtt(rtwdev, ref, aux, false);
 			config->mcc_interval = ref->beacon_interval;
 			rtw89_mcc_set_duration_go_sta(rtwdev, ref, aux);
 		} else {
-			rtw89_mcc_sync_tbtt(rtwdev, aux, ref, true);
 			config->mcc_interval = aux->beacon_interval;
 			rtw89_mcc_set_duration_go_sta(rtwdev, aux, ref);
 		}
@@ -1573,10 +1680,8 @@ bottom:
 
 static int __mcc_fw_add_role(struct rtw89_dev *rtwdev, struct rtw89_mcc_role *role)
 {
+	const struct rtw89_mcc_courtesy_cfg *crtz = role->crtz;
 	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
-	struct rtw89_mcc_config *config = &mcc->config;
-	struct rtw89_mcc_pattern *pattern = &config->pattern;
-	struct rtw89_mcc_courtesy *courtesy = &pattern->courtesy;
 	struct rtw89_mcc_policy *policy = &role->policy;
 	struct rtw89_fw_mcc_add_req req = {};
 	const struct rtw89_chan *chan;
@@ -1599,9 +1704,9 @@ static int __mcc_fw_add_role(struct rtw89_dev *rtwdev, struct rtw89_mcc_role *ro
 	req.duration = role->duration;
 	req.btc_in_2g = false;
 
-	if (courtesy->enable && courtesy->macid_src == req.macid) {
-		req.courtesy_target = courtesy->macid_tgt;
-		req.courtesy_num = courtesy->slot_num;
+	if (crtz) {
+		req.courtesy_target = crtz->macid_tgt;
+		req.courtesy_num = crtz->slot_num;
 		req.courtesy_en = true;
 	}
 
@@ -1781,26 +1886,23 @@ static void __mrc_fw_add_courtesy(struct rtw89_dev *rtwdev,
 	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
 	struct rtw89_mcc_role *ref = &mcc->role_ref;
 	struct rtw89_mcc_role *aux = &mcc->role_aux;
-	struct rtw89_mcc_config *config = &mcc->config;
-	struct rtw89_mcc_pattern *pattern = &config->pattern;
-	struct rtw89_mcc_courtesy *courtesy = &pattern->courtesy;
 	struct rtw89_fw_mrc_add_slot_arg *slot_arg_src;
-	u8 slot_idx_tgt;
 
-	if (!courtesy->enable)
-		return;
-
-	if (courtesy->macid_src == ref->rtwvif_link->mac_id) {
+	if (ref->crtz) {
 		slot_arg_src = &arg->slots[ref->slot_idx];
-		slot_idx_tgt = aux->slot_idx;
-	} else {
-		slot_arg_src = &arg->slots[aux->slot_idx];
-		slot_idx_tgt = ref->slot_idx;
+
+		slot_arg_src->courtesy_target = aux->slot_idx;
+		slot_arg_src->courtesy_period = ref->crtz->slot_num;
+		slot_arg_src->courtesy_en = true;
 	}
 
-	slot_arg_src->courtesy_target = slot_idx_tgt;
-	slot_arg_src->courtesy_period = courtesy->slot_num;
-	slot_arg_src->courtesy_en = true;
+	if (aux->crtz) {
+		slot_arg_src = &arg->slots[aux->slot_idx];
+
+		slot_arg_src->courtesy_target = ref->slot_idx;
+		slot_arg_src->courtesy_period = aux->crtz->slot_num;
+		slot_arg_src->courtesy_en = true;
+	}
 }
 
 static int __mrc_fw_start(struct rtw89_dev *rtwdev, bool replace)
@@ -2000,30 +2102,24 @@ static void rtw89_mcc_handle_beacon_noa(struct rtw89_dev *rtwdev, bool enable)
 	struct rtw89_mcc_role *ref = &mcc->role_ref;
 	struct rtw89_mcc_role *aux = &mcc->role_aux;
 	struct rtw89_mcc_config *config = &mcc->config;
-	struct rtw89_mcc_pattern *pattern = &config->pattern;
-	struct rtw89_mcc_sync *sync = &config->sync;
 	struct ieee80211_p2p_noa_desc noa_desc = {};
-	u64 start_time = config->start_tsf;
 	u32 interval = config->mcc_interval;
 	struct rtw89_vif_link *rtwvif_go;
+	u64 start_time;
 	u32 duration;
 
 	if (mcc->mode != RTW89_MCC_MODE_GO_STA)
 		return;
 
 	if (ref->is_go) {
+		start_time = config->start_tsf;
 		rtwvif_go = ref->rtwvif_link;
 		start_time += ieee80211_tu_to_usec(ref->duration);
 		duration = config->mcc_interval - ref->duration;
 	} else if (aux->is_go) {
+		start_time = config->start_tsf_in_aux_domain;
 		rtwvif_go = aux->rtwvif_link;
-		start_time += ieee80211_tu_to_usec(pattern->tob_ref) +
-			      ieee80211_tu_to_usec(config->beacon_offset) +
-			      ieee80211_tu_to_usec(pattern->toa_aux);
 		duration = config->mcc_interval - aux->duration;
-
-		/* convert time domain from sta(ref) to GO(aux) */
-		start_time += ieee80211_tu_to_usec(sync->offset);
 	} else {
 		rtw89_debug(rtwdev, RTW89_DBG_CHAN,
 			    "MCC find no GO: skip updating beacon NoA\n");
@@ -2127,6 +2223,12 @@ static int rtw89_mcc_start(struct rtw89_dev *rtwdev)
 }
 
 struct rtw89_mcc_stop_sel {
+	struct {
+		const struct rtw89_vif_link *target;
+	} hint;
+
+	/* selection content */
+	bool filled;
 	u8 mac_id;
 	u8 slot_idx;
 };
@@ -2136,6 +2238,7 @@ static void rtw89_mcc_stop_sel_fill(struct rtw89_mcc_stop_sel *sel,
 {
 	sel->mac_id = mcc_role->rtwvif_link->mac_id;
 	sel->slot_idx = mcc_role->slot_idx;
+	sel->filled = true;
 }
 
 static int rtw89_mcc_stop_sel_iterator(struct rtw89_dev *rtwdev,
@@ -2145,23 +2248,41 @@ static int rtw89_mcc_stop_sel_iterator(struct rtw89_dev *rtwdev,
 {
 	struct rtw89_mcc_stop_sel *sel = data;
 
+	if (mcc_role->rtwvif_link == sel->hint.target) {
+		rtw89_mcc_stop_sel_fill(sel, mcc_role);
+		return 1; /* break iteration */
+	}
+
+	if (sel->filled)
+		return 0;
+
 	if (!mcc_role->rtwvif_link->chanctx_assigned)
 		return 0;
 
 	rtw89_mcc_stop_sel_fill(sel, mcc_role);
-	return 1; /* break iteration */
+	return 0;
 }
 
-static void rtw89_mcc_stop(struct rtw89_dev *rtwdev)
+static void rtw89_mcc_stop(struct rtw89_dev *rtwdev,
+			   const struct rtw89_chanctx_pause_parm *pause)
 {
+	struct rtw89_hal *hal = &rtwdev->hal;
 	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
 	struct rtw89_mcc_role *ref = &mcc->role_ref;
-	struct rtw89_mcc_stop_sel sel;
+	struct rtw89_mcc_stop_sel sel = {
+		.hint.target = pause ? pause->trigger : NULL,
+	};
 	int ret;
 
+	if (!pause) {
+		wiphy_delayed_work_cancel(rtwdev->hw->wiphy, &rtwdev->chanctx_work);
+		bitmap_zero(hal->changes, NUM_OF_RTW89_CHANCTX_CHANGES);
+	}
+
 	/* by default, stop at ref */
-	rtw89_mcc_stop_sel_fill(&sel, ref);
 	rtw89_iterate_mcc_roles(rtwdev, rtw89_mcc_stop_sel_iterator, &sel);
+	if (!sel.filled)
+		rtw89_mcc_stop_sel_fill(&sel, ref);
 
 	rtw89_debug(rtwdev, RTW89_DBG_CHAN, "MCC stop at <macid %d>\n", sel.mac_id);
 
@@ -2193,6 +2314,7 @@ static int rtw89_mcc_update(struct rtw89_dev *rtwdev)
 	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
 	struct rtw89_mcc_config *config = &mcc->config;
 	struct rtw89_mcc_config old_cfg = *config;
+	bool courtesy_changed;
 	bool sync_changed;
 	int ret;
 
@@ -2205,8 +2327,15 @@ static int rtw89_mcc_update(struct rtw89_dev *rtwdev)
 	if (ret)
 		return ret;
 
+	if (memcmp(&old_cfg.pattern.courtesy, &config->pattern.courtesy,
+		   sizeof(old_cfg.pattern.courtesy)) == 0)
+		courtesy_changed = false;
+	else
+		courtesy_changed = true;
+
 	if (old_cfg.pattern.plan != RTW89_MCC_PLAN_NO_BT ||
-	    config->pattern.plan != RTW89_MCC_PLAN_NO_BT) {
+	    config->pattern.plan != RTW89_MCC_PLAN_NO_BT ||
+	    courtesy_changed) {
 		if (rtw89_concurrent_via_mrc(rtwdev))
 			ret = __mrc_fw_start(rtwdev, true);
 		else
@@ -2238,7 +2367,7 @@ static void rtw89_mcc_track(struct rtw89_dev *rtwdev)
 	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
 	struct rtw89_mcc_config *config = &mcc->config;
 	struct rtw89_mcc_pattern *pattern = &config->pattern;
-	s16 tolerance;
+	u16 tolerance;
 	u16 bcn_ofst;
 	u16 diff;
 
@@ -2246,18 +2375,25 @@ static void rtw89_mcc_track(struct rtw89_dev *rtwdev)
 		return;
 
 	bcn_ofst = rtw89_mcc_get_bcn_ofst(rtwdev);
+	if (bcn_ofst == config->beacon_offset)
+		return;
+
 	if (bcn_ofst > config->beacon_offset) {
 		diff = bcn_ofst - config->beacon_offset;
 		if (pattern->tob_aux < 0)
 			tolerance = -pattern->tob_aux;
-		else
+		else if (pattern->toa_aux > 0)
 			tolerance = pattern->toa_aux;
+		else
+			return; /* no chance to improve */
 	} else {
 		diff = config->beacon_offset - bcn_ofst;
 		if (pattern->toa_aux < 0)
 			tolerance = -pattern->toa_aux;
-		else
+		else if (pattern->tob_aux > 0)
 			tolerance = pattern->tob_aux;
+		else
+			return; /* no chance to improve */
 	}
 
 	if (diff <= tolerance)
@@ -2504,7 +2640,7 @@ void rtw89_chanctx_track(struct rtw89_dev *rtwdev)
 }
 
 void rtw89_chanctx_pause(struct rtw89_dev *rtwdev,
-			 enum rtw89_chanctx_pause_reasons rsn)
+			 const struct rtw89_chanctx_pause_parm *pause_parm)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
 	enum rtw89_entity_mode mode;
@@ -2514,12 +2650,12 @@ void rtw89_chanctx_pause(struct rtw89_dev *rtwdev,
 	if (hal->entity_pause)
 		return;
 
-	rtw89_debug(rtwdev, RTW89_DBG_CHAN, "chanctx pause (rsn: %d)\n", rsn);
+	rtw89_debug(rtwdev, RTW89_DBG_CHAN, "chanctx pause (rsn: %d)\n", pause_parm->rsn);
 
 	mode = rtw89_get_entity_mode(rtwdev);
 	switch (mode) {
 	case RTW89_ENTITY_MODE_MCC:
-		rtw89_mcc_stop(rtwdev);
+		rtw89_mcc_stop(rtwdev, pause_parm);
 		break;
 	default:
 		break;
@@ -2744,7 +2880,7 @@ out:
 		cur = rtw89_get_entity_mode(rtwdev);
 		switch (cur) {
 		case RTW89_ENTITY_MODE_MCC:
-			rtw89_mcc_stop(rtwdev);
+			rtw89_mcc_stop(rtwdev, NULL);
 			break;
 		default:
 			break;
diff --git a/drivers/net/wireless/realtek/rtw89/chan.h b/drivers/net/wireless/realtek/rtw89/chan.h
index e6391f6f2aa7..2a25563593af 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.h
+++ b/drivers/net/wireless/realtek/rtw89/chan.h
@@ -31,6 +31,14 @@
 #define RTW89_MCC_DFLT_TX_NULL_EARLY 3
 #define RTW89_MCC_DFLT_COURTESY_SLOT 3
 
+#define RTW89_MCC_REQ_COURTESY_TIME 5
+#define RTW89_MCC_REQ_COURTESY(pattern, role)			\
+({								\
+	const struct rtw89_mcc_pattern *p = pattern;		\
+	p->tob_ ## role <= RTW89_MCC_REQ_COURTESY_TIME ||	\
+	p->toa_ ## role <= RTW89_MCC_REQ_COURTESY_TIME;		\
+})
+
 #define NUM_OF_RTW89_MCC_ROLES 2
 
 enum rtw89_chanctx_pause_reasons {
@@ -38,6 +46,11 @@ enum rtw89_chanctx_pause_reasons {
 	RTW89_CHANCTX_PAUSE_REASON_ROC,
 };
 
+struct rtw89_chanctx_pause_parm {
+	const struct rtw89_vif_link *trigger;
+	enum rtw89_chanctx_pause_reasons rsn;
+};
+
 struct rtw89_chanctx_cb_parm {
 	int (*cb)(struct rtw89_dev *rtwdev, void *data);
 	void *data;
@@ -95,7 +108,7 @@ void rtw89_config_entity_chandef(struct rtw89_dev *rtwdev,
 				 enum rtw89_chanctx_idx idx,
 				 const struct cfg80211_chan_def *chandef);
 void rtw89_config_roc_chandef(struct rtw89_dev *rtwdev,
-			      enum rtw89_chanctx_idx idx,
+			      struct rtw89_vif_link *rtwvif_link,
 			      const struct cfg80211_chan_def *chandef);
 void rtw89_entity_init(struct rtw89_dev *rtwdev);
 enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev);
@@ -105,7 +118,7 @@ void rtw89_queue_chanctx_change(struct rtw89_dev *rtwdev,
 				enum rtw89_chanctx_changes change);
 void rtw89_chanctx_track(struct rtw89_dev *rtwdev);
 void rtw89_chanctx_pause(struct rtw89_dev *rtwdev,
-			 enum rtw89_chanctx_pause_reasons rsn);
+			 const struct rtw89_chanctx_pause_parm *parm);
 void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev,
 			   const struct rtw89_chanctx_cb_parm *cb_parm);
 
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index cc9b014457ac..49447668cbf3 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -203,6 +203,23 @@ static const struct ieee80211_iface_combination rtw89_iface_combs[] = {
 	},
 };
 
+static const u8 rtw89_ext_capa_sta[] = {
+	[2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT,
+	[7] = WLAN_EXT_CAPA8_OPMODE_NOTIF,
+};
+
+static const struct wiphy_iftype_ext_capab rtw89_iftypes_ext_capa[] = {
+	{
+		.iftype = NL80211_IFTYPE_STATION,
+		.extended_capabilities = rtw89_ext_capa_sta,
+		.extended_capabilities_mask = rtw89_ext_capa_sta,
+		.extended_capabilities_len = sizeof(rtw89_ext_capa_sta),
+		/* relevant only if EHT is supported */
+		.eml_capabilities = 0,
+		.mld_capa_and_ops = 0,
+	},
+};
+
 #define RTW89_6GHZ_SPAN_HEAD 6145
 #define RTW89_6GHZ_SPAN_IDX(center_freq) \
 	((((int)(center_freq) - RTW89_6GHZ_SPAN_HEAD) / 5) / 2)
@@ -211,6 +228,8 @@ static const struct ieee80211_iface_combination rtw89_iface_combs[] = {
 	[RTW89_6GHZ_SPAN_IDX(center_freq)] = { \
 		.sar_subband_low = RTW89_SAR_6GHZ_ ## subband_l, \
 		.sar_subband_high = RTW89_SAR_6GHZ_ ## subband_h, \
+		.acpi_sar_subband_low = RTW89_ACPI_SAR_6GHZ_ ## subband_l, \
+		.acpi_sar_subband_high = RTW89_ACPI_SAR_6GHZ_ ## subband_h, \
 		.ant_gain_subband_low = RTW89_ANT_GAIN_6GHZ_ ## subband_l, \
 		.ant_gain_subband_high = RTW89_ANT_GAIN_6GHZ_ ## subband_h, \
 	}
@@ -639,9 +658,17 @@ out:
 static u8 rtw89_core_tx_get_mac_id(struct rtw89_dev *rtwdev,
 				   struct rtw89_core_tx_request *tx_req)
 {
+	struct rtw89_tx_desc_info *desc_info = &tx_req->desc_info;
 	struct rtw89_vif_link *rtwvif_link = tx_req->rtwvif_link;
 	struct rtw89_sta_link *rtwsta_link = tx_req->rtwsta_link;
 
+	if (desc_info->mlo && !desc_info->sw_mld) {
+		if (rtwsta_link)
+			return rtw89_sta_get_main_macid(rtwsta_link->rtwsta);
+		else
+			return rtw89_vif_get_main_macid(rtwvif_link->rtwvif);
+	}
+
 	if (!rtwsta_link)
 		return rtwvif_link->mac_id;
 
@@ -671,7 +698,7 @@ rtw89_core_tx_update_mgmt_info(struct rtw89_dev *rtwdev,
 	struct sk_buff *skb = tx_req->skb;
 	u8 qsel, ch_dma;
 
-	qsel = desc_info->hiq ? RTW89_TX_QSEL_B0_HI : RTW89_TX_QSEL_B0_MGMT;
+	qsel = rtw89_core_get_qsel_mgmt(rtwdev, tx_req);
 	ch_dma = rtw89_core_get_ch_dma(rtwdev, qsel);
 
 	desc_info->qsel = qsel;
@@ -1104,39 +1131,23 @@ int rtw89_h2c_tx(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
-int rtw89_core_tx_write(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
-			struct ieee80211_sta *sta, struct sk_buff *skb, int *qsel)
+static int rtw89_core_tx_write_link(struct rtw89_dev *rtwdev,
+				    struct rtw89_vif_link *rtwvif_link,
+				    struct rtw89_sta_link *rtwsta_link,
+				    struct sk_buff *skb, int *qsel, bool sw_mld)
 {
-	struct rtw89_sta *rtwsta = sta_to_rtwsta_safe(sta);
-	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
-	struct rtw89_core_tx_request tx_req = {0};
-	struct rtw89_sta_link *rtwsta_link = NULL;
-	struct rtw89_vif_link *rtwvif_link;
+	struct ieee80211_sta *sta = rtwsta_link_to_sta_safe(rtwsta_link);
+	struct ieee80211_vif *vif = rtwvif_link_to_vif(rtwvif_link);
+	struct rtw89_vif *rtwvif = rtwvif_link->rtwvif;
+	struct rtw89_core_tx_request tx_req = {};
 	int ret;
 
-	/* By default, driver writes tx via the link on HW-0. And then,
-	 * according to links' status, HW can change tx to another link.
-	 */
-
-	if (rtwsta) {
-		rtwsta_link = rtw89_sta_get_link_inst(rtwsta, 0);
-		if (unlikely(!rtwsta_link)) {
-			rtw89_err(rtwdev, "tx: find no sta link on HW-0\n");
-			return -ENOLINK;
-		}
-	}
-
-	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
-	if (unlikely(!rtwvif_link)) {
-		rtw89_err(rtwdev, "tx: find no vif link on HW-0\n");
-		return -ENOLINK;
-	}
-
 	tx_req.skb = skb;
 	tx_req.vif = vif;
 	tx_req.sta = sta;
 	tx_req.rtwvif_link = rtwvif_link;
 	tx_req.rtwsta_link = rtwsta_link;
+	tx_req.desc_info.sw_mld = sw_mld;
 
 	rtw89_traffic_stats_accu(rtwdev, &rtwdev->stats, skb, true);
 	rtw89_traffic_stats_accu(rtwdev, &rtwvif->stats, skb, true);
@@ -1155,6 +1166,33 @@ int rtw89_core_tx_write(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 	return 0;
 }
 
+int rtw89_core_tx_write(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
+			struct ieee80211_sta *sta, struct sk_buff *skb, int *qsel)
+{
+	struct rtw89_sta *rtwsta = sta_to_rtwsta_safe(sta);
+	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
+	struct rtw89_sta_link *rtwsta_link = NULL;
+	struct rtw89_vif_link *rtwvif_link;
+
+	if (rtwsta) {
+		rtwsta_link = rtw89_get_designated_link(rtwsta);
+		if (unlikely(!rtwsta_link)) {
+			rtw89_err(rtwdev, "tx: find no sta designated link\n");
+			return -ENOLINK;
+		}
+
+		rtwvif_link = rtwsta_link->rtwvif_link;
+	} else {
+		rtwvif_link = rtw89_get_designated_link(rtwvif);
+		if (unlikely(!rtwvif_link)) {
+			rtw89_err(rtwdev, "tx: find no vif designated link\n");
+			return -ENOLINK;
+		}
+	}
+
+	return rtw89_core_tx_write_link(rtwdev, rtwvif_link, rtwsta_link, skb, qsel, false);
+}
+
 static __le32 rtw89_build_txwd_body0(struct rtw89_tx_desc_info *desc_info)
 {
 	u32 dword = FIELD_PREP(RTW89_TXWD_BODY0_WP_OFFSET, desc_info->wp_offset) |
@@ -1382,7 +1420,9 @@ static __le32 rtw89_build_txwd_body2_v2(struct rtw89_tx_desc_info *desc_info)
 
 static __le32 rtw89_build_txwd_body3_v2(struct rtw89_tx_desc_info *desc_info)
 {
-	u32 dword = FIELD_PREP(BE_TXD_BODY3_WIFI_SEQ, desc_info->seq);
+	u32 dword = FIELD_PREP(BE_TXD_BODY3_WIFI_SEQ, desc_info->seq) |
+		    FIELD_PREP(BE_TXD_BODY3_MLO_FLAG, desc_info->mlo) |
+		    FIELD_PREP(BE_TXD_BODY3_IS_MLD_SW_EN, desc_info->sw_mld);
 
 	return cpu_to_le32(dword);
 }
@@ -1635,10 +1675,7 @@ static void rtw89_core_rx_process_phy_ppdu_iter(void *data,
 	u8 evm_pos = 0;
 	int i;
 
-	/* FIXME: For single link, taking link on HW-0 here is okay. But, when
-	 * enabling multiple active links, we should determine the right link.
-	 */
-	rtwsta_link = rtw89_sta_get_link_inst(rtwsta, 0);
+	rtwsta_link = rtw89_sta_get_link_inst(rtwsta, phy_ppdu->phy_idx);
 	if (unlikely(!rtwsta_link))
 		return;
 
@@ -2058,10 +2095,21 @@ static void rtw89_stats_trigger_frame(struct rtw89_dev *rtwdev,
 			break;
 
 		if (aid == vif->cfg.aid) {
-			enum nl80211_he_ru_alloc rua = rtw89_he_rua_to_ru_alloc(tf_rua >> 1);
+			enum nl80211_he_ru_alloc rua;
 
 			rtwvif->stats.rx_tf_acc++;
 			rtwdev->stats.rx_tf_acc++;
+
+			/* The following only required for HE trigger frame, but we
+			 * cannot use UL HE-SIG-A2 reserved subfield to identify it
+			 * since some 11ax APs will fill it with all 0s, which will
+			 * be misunderstood as EHT trigger frame.
+			 */
+			if (bss_conf->eht_support)
+				break;
+
+			rua = rtw89_he_rua_to_ru_alloc(tf_rua >> 1);
+
 			if (tf_bw == IEEE80211_TRIGGER_ULBW_160_80P80MHZ &&
 			    rua <= NL80211_RATE_INFO_HE_RU_ALLOC_106)
 				rtwvif_link->pwr_diff_en = true;
@@ -2152,8 +2200,10 @@ static void rtw89_vif_rx_stats_iter(void *data, u8 *mac,
 	struct rtw89_pkt_stat *pkt_stat = &rtwdev->phystat.cur_pkt_stat;
 	struct rtw89_rx_desc_info *desc_info = iter_data->desc_info;
 	struct sk_buff *skb = iter_data->skb;
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct rtw89_rx_phy_ppdu *phy_ppdu = iter_data->phy_ppdu;
+	bool is_mld = ieee80211_vif_is_mld(vif);
 	struct ieee80211_bss_conf *bss_conf;
 	struct rtw89_vif_link *rtwvif_link;
 	const u8 *bssid = iter_data->bssid;
@@ -2165,10 +2215,7 @@ static void rtw89_vif_rx_stats_iter(void *data, u8 *mac,
 
 	rcu_read_lock();
 
-	/* FIXME: For single link, taking link on HW-0 here is okay. But, when
-	 * enabling multiple active links, we should determine the right link.
-	 */
-	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
+	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, desc_info->bb_sel);
 	if (unlikely(!rtwvif_link))
 		goto out;
 
@@ -2184,6 +2231,11 @@ static void rtw89_vif_rx_stats_iter(void *data, u8 *mac,
 	if (!ether_addr_equal(bss_conf->bssid, bssid))
 		goto out;
 
+	if (is_mld) {
+		rx_status->link_valid = true;
+		rx_status->link_id = rtwvif_link->link_id;
+	}
+
 	if (ieee80211_is_beacon(hdr->frame_control)) {
 		if (vif->type == NL80211_IFTYPE_STATION &&
 		    !test_bit(RTW89_FLAG_WOWLAN, rtwdev->flags)) {
@@ -2482,7 +2534,8 @@ static void rtw89_core_rx_process_ppdu_sts(struct rtw89_dev *rtwdev,
 					     .len = skb->len,
 					     .to_self = desc_info->addr1_match,
 					     .rate = desc_info->data_rate,
-					     .mac_id = desc_info->mac_id};
+					     .mac_id = desc_info->mac_id,
+					     .phy_idx = desc_info->bb_sel};
 	int ret;
 
 	if (desc_info->mac_info_valid) {
@@ -2593,6 +2646,7 @@ void rtw89_core_query_rxdesc_v2(struct rtw89_dev *rtwdev,
 	desc_info->shift = le32_get_bits(rxd_s->dword0, BE_RXD_SHIFT_MASK);
 	desc_info->long_rxdesc = le32_get_bits(rxd_s->dword0, BE_RXD_LONG_RXD);
 	desc_info->pkt_type = le32_get_bits(rxd_s->dword0, BE_RXD_RPKT_TYPE_MASK);
+	desc_info->bb_sel = le32_get_bits(rxd_s->dword0, BE_RXD_BB_SEL);
 	if (desc_info->pkt_type == RTW89_CORE_RX_TYPE_PPDU_STAT)
 		desc_info->mac_info_valid = true;
 
@@ -2665,10 +2719,7 @@ void rtw89_core_stats_sta_rx_status_iter(void *data, struct ieee80211_sta *sta)
 	struct rtw89_sta_link *rtwsta_link;
 	u8 mac_id = iter_data->mac_id;
 
-	/* FIXME: For single link, taking link on HW-0 here is okay. But, when
-	 * enabling multiple active links, we should determine the right link.
-	 */
-	rtwsta_link = rtw89_sta_get_link_inst(rtwsta, 0);
+	rtwsta_link = rtw89_sta_get_link_inst(rtwsta, desc_info->bb_sel);
 	if (unlikely(!rtwsta_link))
 		return;
 
@@ -3117,9 +3168,9 @@ static bool rtw89_core_txq_agg_wait(struct rtw89_dev *rtwdev,
 	if (!rtwsta)
 		return false;
 
-	rtwsta_link = rtw89_sta_get_link_inst(rtwsta, 0);
+	rtwsta_link = rtw89_get_designated_link(rtwsta);
 	if (unlikely(!rtwsta_link)) {
-		rtw89_err(rtwdev, "agg wait: find no link on HW-0\n");
+		rtw89_err(rtwdev, "agg wait: find no designated link\n");
 		return false;
 	}
 
@@ -3284,8 +3335,10 @@ static int rtw89_core_send_nullfunc(struct rtw89_dev *rtwdev,
 {
 	struct ieee80211_vif *vif = rtwvif_link_to_vif(rtwvif_link);
 	int link_id = ieee80211_vif_is_mld(vif) ? rtwvif_link->link_id : -1;
+	struct rtw89_sta_link *rtwsta_link;
 	struct ieee80211_sta *sta;
 	struct ieee80211_hdr *hdr;
+	struct rtw89_sta *rtwsta;
 	struct sk_buff *skb;
 	int ret, qsel;
 
@@ -3298,6 +3351,7 @@ static int rtw89_core_send_nullfunc(struct rtw89_dev *rtwdev,
 		ret = -EINVAL;
 		goto out;
 	}
+	rtwsta = sta_to_rtwsta(sta);
 
 	skb = ieee80211_nullfunc_get(rtwdev->hw, vif, link_id, qos);
 	if (!skb) {
@@ -3309,7 +3363,13 @@ static int rtw89_core_send_nullfunc(struct rtw89_dev *rtwdev,
 	if (ps)
 		hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PM);
 
-	ret = rtw89_core_tx_write(rtwdev, vif, sta, skb, &qsel);
+	rtwsta_link = rtwsta->links[rtwvif_link->link_id];
+	if (unlikely(!rtwsta_link)) {
+		ret = -ENOLINK;
+		goto out;
+	}
+
+	ret = rtw89_core_tx_write_link(rtwdev, rtwvif_link, rtwsta_link, skb, &qsel, true);
 	if (ret) {
 		rtw89_warn(rtwdev, "nullfunc transmit failed: %d\n", ret);
 		dev_kfree_skb_any(skb);
@@ -3329,6 +3389,9 @@ out:
 void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	struct rtw89_chanctx_pause_parm pause_parm = {
+		.rsn = RTW89_CHANCTX_PAUSE_REASON_ROC,
+	};
 	struct ieee80211_hw *hw = rtwdev->hw;
 	struct rtw89_roc *roc = &rtwvif->roc;
 	struct rtw89_vif_link *rtwvif_link;
@@ -3342,14 +3405,16 @@ void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	rtw89_leave_ips_by_hwflags(rtwdev);
 	rtw89_leave_lps(rtwdev);
 
-	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, RTW89_ROC_BY_LINK_INDEX);
+	rtwvif_link = rtw89_get_designated_link(rtwvif);
 	if (unlikely(!rtwvif_link)) {
-		rtw89_err(rtwdev, "roc start: find no link on HW-%u\n",
-			  RTW89_ROC_BY_LINK_INDEX);
+		rtw89_err(rtwdev, "roc start: find no designated link\n");
 		return;
 	}
 
-	rtw89_chanctx_pause(rtwdev, RTW89_CHANCTX_PAUSE_REASON_ROC);
+	roc->link_id = rtwvif_link->link_id;
+
+	pause_parm.trigger = rtwvif_link;
+	rtw89_chanctx_pause(rtwdev, &pause_parm);
 
 	ret = rtw89_core_send_nullfunc(rtwdev, rtwvif_link, true, true);
 	if (ret)
@@ -3369,7 +3434,7 @@ void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	}
 
 	cfg80211_chandef_create(&roc_chan, &roc->chan, NL80211_CHAN_NO_HT);
-	rtw89_config_roc_chandef(rtwdev, rtwvif_link->chanctx_idx, &roc_chan);
+	rtw89_config_roc_chandef(rtwdev, rtwvif_link, &roc_chan);
 	rtw89_set_channel(rtwdev);
 
 	reg = rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, rtwvif_link->mac_idx);
@@ -3398,10 +3463,10 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	rtw89_leave_ips_by_hwflags(rtwdev);
 	rtw89_leave_lps(rtwdev);
 
-	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, RTW89_ROC_BY_LINK_INDEX);
+	rtwvif_link = rtwvif->links[roc->link_id];
 	if (unlikely(!rtwvif_link)) {
-		rtw89_err(rtwdev, "roc end: find no link on HW-%u\n",
-			  RTW89_ROC_BY_LINK_INDEX);
+		rtw89_err(rtwdev, "roc end: find no link (link id %u)\n",
+			  roc->link_id);
 		return;
 	}
 
@@ -3409,7 +3474,7 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	rtw89_write32_mask(rtwdev, reg, B_AX_RX_FLTR_CFG_MASK, rtwdev->hal.rx_fltr);
 
 	roc->state = RTW89_ROC_IDLE;
-	rtw89_config_roc_chandef(rtwdev, rtwvif_link->chanctx_idx, NULL);
+	rtw89_config_roc_chandef(rtwdev, rtwvif_link, NULL);
 	rtw89_chanctx_proceed(rtwdev, NULL);
 	ret = rtw89_core_send_nullfunc(rtwdev, rtwvif_link, true, false);
 	if (ret)
@@ -3577,6 +3642,98 @@ void rtw89_traffic_stats_init(struct rtw89_dev *rtwdev,
 	ewma_tp_init(&stats->rx_ewma_tp);
 }
 
+#define RTW89_MLSR_GOTO_2GHZ_THRESHOLD -53
+#define RTW89_MLSR_EXIT_2GHZ_THRESHOLD -38
+static void rtw89_core_mlsr_link_decision(struct rtw89_dev *rtwdev,
+					  struct rtw89_vif *rtwvif)
+{
+	unsigned int sel_link_id = IEEE80211_MLD_MAX_NUM_LINKS;
+	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
+	struct rtw89_vif_link *rtwvif_link;
+	const struct rtw89_chan *chan;
+	unsigned long usable_links;
+	unsigned int link_id;
+	u8 decided_bands;
+	u8 rssi;
+
+	rssi = ewma_rssi_read(&rtwdev->phystat.bcn_rssi);
+	if (unlikely(!rssi))
+		return;
+
+	if (RTW89_RSSI_RAW_TO_DBM(rssi) >= RTW89_MLSR_EXIT_2GHZ_THRESHOLD)
+		decided_bands = BIT(RTW89_BAND_5G) | BIT(RTW89_BAND_6G);
+	else if (RTW89_RSSI_RAW_TO_DBM(rssi) <= RTW89_MLSR_GOTO_2GHZ_THRESHOLD)
+		decided_bands = BIT(RTW89_BAND_2G);
+	else
+		return;
+
+	usable_links = ieee80211_vif_usable_links(vif);
+
+	rtwvif_link = rtw89_get_designated_link(rtwvif);
+	if (unlikely(!rtwvif_link))
+		goto select;
+
+	chan = rtw89_chan_get(rtwdev, rtwvif_link->chanctx_idx);
+	if (decided_bands & BIT(chan->band_type))
+		return;
+
+	usable_links &= ~BIT(rtwvif_link->link_id);
+
+select:
+	rcu_read_lock();
+
+	for_each_set_bit(link_id, &usable_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct ieee80211_bss_conf *link_conf;
+		struct ieee80211_channel *channel;
+		enum rtw89_band band;
+
+		link_conf = rcu_dereference(vif->link_conf[link_id]);
+		if (unlikely(!link_conf))
+			continue;
+
+		channel = link_conf->chanreq.oper.chan;
+		if (unlikely(!channel))
+			continue;
+
+		band = rtw89_nl80211_to_hw_band(channel->band);
+		if (decided_bands & BIT(band)) {
+			sel_link_id = link_id;
+			break;
+		}
+	}
+
+	rcu_read_unlock();
+
+	if (sel_link_id == IEEE80211_MLD_MAX_NUM_LINKS)
+		return;
+
+	rtw89_core_mlsr_switch(rtwdev, rtwvif, sel_link_id);
+}
+
+static void rtw89_core_mlo_track(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_hal *hal = &rtwdev->hal;
+	struct ieee80211_vif *vif;
+	struct rtw89_vif *rtwvif;
+
+	if (hal->disabled_dm_bitmap & BIT(RTW89_DM_MLO))
+		return;
+
+	rtw89_for_each_rtwvif(rtwdev, rtwvif) {
+		vif = rtwvif_to_vif(rtwvif);
+		if (!vif->cfg.assoc || !ieee80211_vif_is_mld(vif))
+			continue;
+
+		switch (rtwvif->mlo_mode) {
+		case RTW89_MLO_MODE_MLSR:
+			rtw89_core_mlsr_link_decision(rtwdev, rtwvif);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
 static void rtw89_track_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
@@ -3615,9 +3772,10 @@ static void rtw89_track_work(struct wiphy *wiphy, struct wiphy_work *work)
 	rtw89_phy_antdiv_track(rtwdev);
 	rtw89_phy_ul_tb_ctrl_track(rtwdev);
 	rtw89_phy_edcca_track(rtwdev);
-	rtw89_tas_track(rtwdev);
+	rtw89_sar_track(rtwdev);
 	rtw89_chanctx_track(rtwdev);
 	rtw89_core_rfkill_poll(rtwdev, false);
+	rtw89_core_mlo_track(rtwdev);
 
 	if (rtwdev->lps_enabled && !rtwdev->btc.lps)
 		rtw89_enter_lps_track(rtwdev);
@@ -3846,6 +4004,9 @@ int rtw89_core_sta_link_disassoc(struct rtw89_dev *rtwdev,
 	if (vif->type == NL80211_IFTYPE_STATION)
 		rtw89_fw_h2c_set_bcn_fltr_cfg(rtwdev, rtwvif_link, false);
 
+	if (rtwvif_link->wifi_role == RTW89_WIFI_ROLE_P2P_CLIENT)
+		rtw89_p2p_noa_once_deinit(rtwvif_link);
+
 	return 0;
 }
 
@@ -4361,17 +4522,18 @@ static void rtw89_init_eht_cap(struct rtw89_dev *rtwdev,
 
 #define RTW89_SBAND_IFTYPES_NR 2
 
-static void rtw89_init_he_eht_cap(struct rtw89_dev *rtwdev,
-				  enum nl80211_band band,
-				  struct ieee80211_supported_band *sband)
+static int rtw89_init_he_eht_cap(struct rtw89_dev *rtwdev,
+				 enum nl80211_band band,
+				 struct ieee80211_supported_band *sband)
 {
 	struct ieee80211_sband_iftype_data *iftype_data;
 	enum nl80211_iftype iftype;
 	int idx = 0;
 
-	iftype_data = kcalloc(RTW89_SBAND_IFTYPES_NR, sizeof(*iftype_data), GFP_KERNEL);
+	iftype_data = devm_kcalloc(rtwdev->dev, RTW89_SBAND_IFTYPES_NR,
+				   sizeof(*iftype_data), GFP_KERNEL);
 	if (!iftype_data)
-		return;
+		return -ENOMEM;
 
 	for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
 		switch (iftype) {
@@ -4396,77 +4558,75 @@ static void rtw89_init_he_eht_cap(struct rtw89_dev *rtwdev,
 	}
 
 	_ieee80211_set_sband_iftype_data(sband, iftype_data, idx);
+	return 0;
+}
+
+static struct ieee80211_supported_band *
+rtw89_core_sband_dup(struct rtw89_dev *rtwdev,
+		     const struct ieee80211_supported_band *sband)
+{
+	struct ieee80211_supported_band *dup;
+
+	dup = devm_kmemdup(rtwdev->dev, sband, sizeof(*sband), GFP_KERNEL);
+	if (!dup)
+		return NULL;
+
+	dup->channels = devm_kmemdup(rtwdev->dev, sband->channels,
+				     sizeof(*sband->channels) * sband->n_channels,
+				     GFP_KERNEL);
+	if (!dup->channels)
+		return NULL;
+
+	dup->bitrates = devm_kmemdup(rtwdev->dev, sband->bitrates,
+				     sizeof(*sband->bitrates) * sband->n_bitrates,
+				     GFP_KERNEL);
+	if (!dup->bitrates)
+		return NULL;
+
+	return dup;
 }
 
 static int rtw89_core_set_supported_band(struct rtw89_dev *rtwdev)
 {
 	struct ieee80211_hw *hw = rtwdev->hw;
-	struct ieee80211_supported_band *sband_2ghz = NULL, *sband_5ghz = NULL;
-	struct ieee80211_supported_band *sband_6ghz = NULL;
-	u32 size = sizeof(struct ieee80211_supported_band);
+	struct ieee80211_supported_band *sband;
 	u8 support_bands = rtwdev->chip->support_bands;
+	int ret;
 
 	if (support_bands & BIT(NL80211_BAND_2GHZ)) {
-		sband_2ghz = kmemdup(&rtw89_sband_2ghz, size, GFP_KERNEL);
-		if (!sband_2ghz)
-			goto err;
-		rtw89_init_ht_cap(rtwdev, &sband_2ghz->ht_cap);
-		rtw89_init_he_eht_cap(rtwdev, NL80211_BAND_2GHZ, sband_2ghz);
-		hw->wiphy->bands[NL80211_BAND_2GHZ] = sband_2ghz;
+		sband = rtw89_core_sband_dup(rtwdev, &rtw89_sband_2ghz);
+		if (!sband)
+			return -ENOMEM;
+		rtw89_init_ht_cap(rtwdev, &sband->ht_cap);
+		ret = rtw89_init_he_eht_cap(rtwdev, NL80211_BAND_2GHZ, sband);
+		if (ret)
+			return ret;
+		hw->wiphy->bands[NL80211_BAND_2GHZ] = sband;
 	}
 
 	if (support_bands & BIT(NL80211_BAND_5GHZ)) {
-		sband_5ghz = kmemdup(&rtw89_sband_5ghz, size, GFP_KERNEL);
-		if (!sband_5ghz)
-			goto err;
-		rtw89_init_ht_cap(rtwdev, &sband_5ghz->ht_cap);
-		rtw89_init_vht_cap(rtwdev, &sband_5ghz->vht_cap);
-		rtw89_init_he_eht_cap(rtwdev, NL80211_BAND_5GHZ, sband_5ghz);
-		hw->wiphy->bands[NL80211_BAND_5GHZ] = sband_5ghz;
+		sband = rtw89_core_sband_dup(rtwdev, &rtw89_sband_5ghz);
+		if (!sband)
+			return -ENOMEM;
+		rtw89_init_ht_cap(rtwdev, &sband->ht_cap);
+		rtw89_init_vht_cap(rtwdev, &sband->vht_cap);
+		ret = rtw89_init_he_eht_cap(rtwdev, NL80211_BAND_5GHZ, sband);
+		if (ret)
+			return ret;
+		hw->wiphy->bands[NL80211_BAND_5GHZ] = sband;
 	}
 
 	if (support_bands & BIT(NL80211_BAND_6GHZ)) {
-		sband_6ghz = kmemdup(&rtw89_sband_6ghz, size, GFP_KERNEL);
-		if (!sband_6ghz)
-			goto err;
-		rtw89_init_he_eht_cap(rtwdev, NL80211_BAND_6GHZ, sband_6ghz);
-		hw->wiphy->bands[NL80211_BAND_6GHZ] = sband_6ghz;
+		sband = rtw89_core_sband_dup(rtwdev, &rtw89_sband_6ghz);
+		if (!sband)
+			return -ENOMEM;
+		ret = rtw89_init_he_eht_cap(rtwdev, NL80211_BAND_6GHZ, sband);
+		if (ret)
+			return ret;
+		hw->wiphy->bands[NL80211_BAND_6GHZ] = sband;
 	}
 
 	return 0;
-
-err:
-	hw->wiphy->bands[NL80211_BAND_2GHZ] = NULL;
-	hw->wiphy->bands[NL80211_BAND_5GHZ] = NULL;
-	hw->wiphy->bands[NL80211_BAND_6GHZ] = NULL;
-	if (sband_2ghz)
-		kfree((__force void *)sband_2ghz->iftype_data);
-	if (sband_5ghz)
-		kfree((__force void *)sband_5ghz->iftype_data);
-	if (sband_6ghz)
-		kfree((__force void *)sband_6ghz->iftype_data);
-	kfree(sband_2ghz);
-	kfree(sband_5ghz);
-	kfree(sband_6ghz);
-	return -ENOMEM;
-}
-
-static void rtw89_core_clr_supported_band(struct rtw89_dev *rtwdev)
-{
-	struct ieee80211_hw *hw = rtwdev->hw;
-
-	if (hw->wiphy->bands[NL80211_BAND_2GHZ])
-		kfree((__force void *)hw->wiphy->bands[NL80211_BAND_2GHZ]->iftype_data);
-	if (hw->wiphy->bands[NL80211_BAND_5GHZ])
-		kfree((__force void *)hw->wiphy->bands[NL80211_BAND_5GHZ]->iftype_data);
-	if (hw->wiphy->bands[NL80211_BAND_6GHZ])
-		kfree((__force void *)hw->wiphy->bands[NL80211_BAND_6GHZ]->iftype_data);
-	kfree(hw->wiphy->bands[NL80211_BAND_2GHZ]);
-	kfree(hw->wiphy->bands[NL80211_BAND_5GHZ]);
-	kfree(hw->wiphy->bands[NL80211_BAND_6GHZ]);
-	hw->wiphy->bands[NL80211_BAND_2GHZ] = NULL;
-	hw->wiphy->bands[NL80211_BAND_5GHZ] = NULL;
-	hw->wiphy->bands[NL80211_BAND_6GHZ] = NULL;
 }
 
 static void rtw89_core_ppdu_sts_init(struct rtw89_dev *rtwdev)
@@ -4774,6 +4934,7 @@ struct rtw89_vif_link *rtw89_vif_set_link(struct rtw89_vif *rtwvif,
 
 	set_bit(index, rtwvif->links_inst_map);
 	rtwvif->links[link_id] = rtwvif_link;
+	list_add_tail(&rtwvif_link->dlink_schd, &rtwvif->dlink_pool);
 	return rtwvif_link;
 
 err:
@@ -4794,6 +4955,7 @@ void rtw89_vif_unset_link(struct rtw89_vif *rtwvif, unsigned int link_id)
 	index = rtw89_vif_link_inst_get_index(link);
 	clear_bit(index, rtwvif->links_inst_map);
 	*container = NULL;
+	list_del(&link->dlink_schd);
 }
 
 struct rtw89_sta_link *rtw89_sta_set_link(struct rtw89_sta *rtwsta,
@@ -4824,6 +4986,7 @@ struct rtw89_sta_link *rtw89_sta_set_link(struct rtw89_sta *rtwsta,
 
 	set_bit(index, rtwsta->links_inst_map);
 	rtwsta->links[link_id] = rtwsta_link;
+	list_add_tail(&rtwsta_link->dlink_schd, &rtwsta->dlink_pool);
 	return rtwsta_link;
 
 err:
@@ -4844,6 +5007,7 @@ void rtw89_sta_unset_link(struct rtw89_sta *rtwsta, unsigned int link_id)
 	index = rtw89_sta_link_inst_get_index(link);
 	clear_bit(index, rtwsta->links_inst_map);
 	*container = NULL;
+	list_del(&link->dlink_schd);
 }
 
 int rtw89_core_init(struct rtw89_dev *rtwdev)
@@ -4860,6 +5024,7 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 			continue;
 		INIT_LIST_HEAD(&rtwdev->scan_info.pkt_list[band]);
 	}
+	INIT_LIST_HEAD(&rtwdev->scan_info.chan_list);
 	INIT_WORK(&rtwdev->ba_work, rtw89_core_ba_work);
 	INIT_WORK(&rtwdev->txq_work, rtw89_core_txq_work);
 	INIT_DELAYED_WORK(&rtwdev->txq_reinvoke_work, rtw89_core_txq_reinvoke_work);
@@ -4880,6 +5045,7 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 	rtwdev->total_sta_assoc = 0;
 
 	rtw89_init_wait(&rtwdev->mcc.wait);
+	rtw89_init_wait(&rtwdev->mlo.wait);
 	rtw89_init_wait(&rtwdev->mac.fw_ofld_wait);
 	rtw89_init_wait(&rtwdev->wow.wait);
 	rtw89_init_wait(&rtwdev->mac.ps_wait);
@@ -4901,7 +5067,7 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE) {
 		rtwdev->dbcc_en = true;
 		rtwdev->mac.qta_mode = RTW89_QTA_DBCC;
-		rtwdev->mlo_dbcc_mode = MLO_2_PLUS_0_1RF;
+		rtwdev->mlo_dbcc_mode = MLO_1_PLUS_1_1RF;
 	}
 
 	rtwdev->bbs[RTW89_PHY_0].phy_idx = RTW89_PHY_0;
@@ -4919,7 +5085,7 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 
 	rtw89_ser_init(rtwdev);
 	rtw89_entity_init(rtwdev);
-	rtw89_tas_init(rtwdev);
+	rtw89_sar_init(rtwdev);
 	rtw89_phy_ant_gain_init(rtwdev);
 
 	return 0;
@@ -4945,9 +5111,6 @@ void rtw89_core_scan_start(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwv
 	struct rtw89_bb_ctx *bb = rtw89_get_bb_ctx(rtwdev, rtwvif_link->phy_idx);
 
 	rtwdev->scanning = true;
-	rtw89_leave_lps(rtwdev);
-	if (hw_scan)
-		rtw89_leave_ips_by_hwflags(rtwdev);
 
 	ether_addr_copy(rtwvif_link->mac_addr, mac_addr);
 	rtw89_btc_ntfy_scan_start(rtwdev, rtwvif_link->phy_idx, chan->band_type);
@@ -5062,6 +5225,76 @@ out:
 	rtw89_load_txpwr_table(rtwdev, rtwdev->rfe_parms->byr_tbl);
 }
 
+int rtw89_core_mlsr_switch(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+			   unsigned int link_id)
+{
+	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
+	u16 usable_links = ieee80211_vif_usable_links(vif);
+	u16 active_links = vif->active_links;
+	struct rtw89_vif_link *target, *cur;
+	int ret;
+
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
+	if (unlikely(!ieee80211_vif_is_mld(vif)))
+		return -EOPNOTSUPP;
+
+	if (unlikely(!(usable_links & BIT(link_id)))) {
+		rtw89_warn(rtwdev, "%s: link id %u is not usable\n", __func__,
+			   link_id);
+		return -ENOLINK;
+	}
+
+	if (active_links == BIT(link_id))
+		return 0;
+
+	rtw89_debug(rtwdev, RTW89_DBG_STATE, "%s: switch to link id %u MLSR\n",
+		    __func__, link_id);
+
+	rtw89_leave_lps(rtwdev);
+
+	ieee80211_stop_queues(rtwdev->hw);
+	flush_work(&rtwdev->txq_work);
+
+	cur = rtw89_get_designated_link(rtwvif);
+
+	ret = ieee80211_set_active_links(vif, active_links | BIT(link_id));
+	if (ret) {
+		rtw89_err(rtwdev, "%s: failed to activate link id %u\n",
+			  __func__, link_id);
+		goto wake_queue;
+	}
+
+	target = rtwvif->links[link_id];
+	if (unlikely(!target)) {
+		rtw89_err(rtwdev, "%s: failed to confirm link id %u\n",
+			  __func__, link_id);
+
+		ieee80211_set_active_links(vif, active_links);
+		ret = -EFAULT;
+		goto wake_queue;
+	}
+
+	if (likely(cur))
+		rtw89_fw_h2c_mlo_link_cfg(rtwdev, cur, false);
+
+	rtw89_fw_h2c_mlo_link_cfg(rtwdev, target, true);
+
+	ret = ieee80211_set_active_links(vif, BIT(link_id));
+	if (ret)
+		rtw89_err(rtwdev, "%s: failed to inactivate links 0x%x\n",
+			  __func__, active_links);
+
+	rtw89_chip_rfk_channel(rtwdev, target);
+
+	rtwvif->mlo_mode = RTW89_MLO_MODE_MLSR;
+
+wake_queue:
+	ieee80211_wake_queues(rtwdev->hw);
+
+	return ret;
+}
+
 static int rtw89_chip_efuse_info_setup(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
@@ -5305,8 +5538,11 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev)
 	if (chip->chip_gen == RTW89_CHIP_BE)
 		hw->wiphy->flags |= WIPHY_FLAG_DISABLE_WEXT;
 
-	if (rtwdev->support_mlo)
+	if (rtwdev->support_mlo) {
 		hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_MLO;
+		hw->wiphy->iftype_ext_capab = rtw89_iftypes_ext_capa;
+		hw->wiphy->num_iftype_ext_capab = ARRAY_SIZE(rtw89_iftypes_ext_capa);
+	}
 
 	hw->wiphy->features |= NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR;
 
@@ -5337,7 +5573,7 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev)
 	ret = rtw89_regd_setup(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to set up regd\n");
-		goto err_free_supported_band;
+		return ret;
 	}
 
 	hw->wiphy->sar_capa = &rtw89_sar_capa;
@@ -5345,7 +5581,7 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev)
 	ret = ieee80211_register_hw(hw);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to register hw\n");
-		goto err_free_supported_band;
+		return ret;
 	}
 
 	ret = rtw89_regd_init_hint(rtwdev);
@@ -5360,8 +5596,6 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev)
 
 err_unregister_hw:
 	ieee80211_unregister_hw(hw);
-err_free_supported_band:
-	rtw89_core_clr_supported_band(rtwdev);
 
 	return ret;
 }
@@ -5372,7 +5606,6 @@ static void rtw89_core_unregister_hw(struct rtw89_dev *rtwdev)
 
 	rtw89_rfkill_polling_deinit(rtwdev);
 	ieee80211_unregister_hw(hw);
-	rtw89_core_clr_supported_band(rtwdev);
 }
 
 int rtw89_core_register(struct rtw89_dev *rtwdev)
@@ -5440,13 +5673,13 @@ struct rtw89_dev *rtw89_alloc_ieee80211_hw(struct device *device,
 	if (!hw)
 		goto err;
 
-	/* TODO: When driver MLO arch. is done, determine whether to support MLO
-	 * according to the following conditions.
-	 * 1. run with chanctx_ops
-	 * 2. chip->support_link_num != 0
-	 * 3. FW feature supports AP_LINK_PS
+	/* Currently, our AP_LINK_PS handling only works for non-MLD softap
+	 * or MLD-single-link softap. If RTW89_MLD_NON_STA_LINK_NUM enlarges,
+	 * please tweak entire AP_LINKS_PS handling before supporting MLO.
 	 */
-	support_mlo = false;
+	support_mlo = !no_chanctx && chip->support_link_num &&
+		      RTW89_CHK_FW_FEATURE(NOTIFY_AP_INFO, &early_fw) &&
+		      RTW89_MLD_NON_STA_LINK_NUM == 1;
 
 	hw->wiphy->iface_combinations = rtw89_iface_combs;
 
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 4be05d6cad18..1c8f3b9b7c4c 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -798,6 +798,7 @@ struct rtw89_rx_phy_ppdu {
 	u8 rssi[RF_PATH_MAX];
 	u8 mac_id;
 	u8 chan_idx;
+	u8 phy_idx;
 	u8 ie;
 	u16 rate;
 	u8 rpl_avg;
@@ -1174,6 +1175,7 @@ struct rtw89_tx_desc_info {
 	bool ldpc;
 	bool upd_wlan_hdr;
 	bool mlo;
+	bool sw_mld;
 };
 
 struct rtw89_core_tx_request {
@@ -3379,6 +3381,7 @@ struct rtw89_sec_cam_entry {
 
 struct rtw89_sta_link {
 	struct rtw89_sta *rtwsta;
+	struct list_head dlink_schd;
 	unsigned int link_id;
 
 	u8 mac_id;
@@ -3445,14 +3448,13 @@ enum rtw89_roc_state {
 	RTW89_ROC_MGMT,
 };
 
-#define RTW89_ROC_BY_LINK_INDEX 0
-
 struct rtw89_roc {
 	struct ieee80211_channel chan;
 	struct wiphy_delayed_work roc_work;
 	enum ieee80211_roc_type type;
 	enum rtw89_roc_state state;
 	int duration;
+	unsigned int link_id;
 };
 
 #define RTW89_P2P_MAX_NOA_NUM 2
@@ -3483,8 +3485,17 @@ struct rtw89_p2p_noa_setter {
 	u8 noa_index;
 };
 
+struct rtw89_ps_noa_once_handler {
+	bool in_duration;
+	u64 tsf_begin;
+	u64 tsf_end;
+	struct wiphy_delayed_work set_work;
+	struct wiphy_delayed_work clr_work;
+};
+
 struct rtw89_vif_link {
 	struct rtw89_vif *rtwvif;
+	struct list_head dlink_schd;
 	unsigned int link_id;
 
 	bool chanctx_assigned; /* only valid when running with chanctx_ops */
@@ -3507,6 +3518,7 @@ struct rtw89_vif_link {
 	u8 hit_rule;
 	u8 last_noa_nr;
 	u64 sync_bcn_tsf;
+	bool rand_tsf_done;
 	bool trigger;
 	bool lsig_txop;
 	u8 tgt_ind;
@@ -3527,6 +3539,7 @@ struct rtw89_vif_link {
 	struct rtw89_phy_rate_pattern rate_pattern;
 	struct list_head general_pkt_list;
 	struct rtw89_p2p_noa_setter p2p_noa;
+	struct rtw89_ps_noa_once_handler noa_once;
 };
 
 enum rtw89_lv1_rcvy_step {
@@ -3986,7 +3999,11 @@ struct rtw89_rfe_parms {
 	struct rtw89_txpwr_rule_2ghz rule_2ghz;
 	struct rtw89_txpwr_rule_5ghz rule_5ghz;
 	struct rtw89_txpwr_rule_6ghz rule_6ghz;
+	struct rtw89_txpwr_rule_2ghz rule_da_2ghz;
+	struct rtw89_txpwr_rule_5ghz rule_da_5ghz;
+	struct rtw89_txpwr_rule_6ghz rule_da_6ghz;
 	struct rtw89_tx_shape tx_shape;
+	bool has_da;
 };
 
 struct rtw89_rfe_parms_conf {
@@ -4081,9 +4098,15 @@ struct rtw89_rfe_data {
 	struct rtw89_txpwr_lmt_2ghz_data lmt_2ghz;
 	struct rtw89_txpwr_lmt_5ghz_data lmt_5ghz;
 	struct rtw89_txpwr_lmt_6ghz_data lmt_6ghz;
+	struct rtw89_txpwr_lmt_2ghz_data da_lmt_2ghz;
+	struct rtw89_txpwr_lmt_5ghz_data da_lmt_5ghz;
+	struct rtw89_txpwr_lmt_6ghz_data da_lmt_6ghz;
 	struct rtw89_txpwr_lmt_ru_2ghz_data lmt_ru_2ghz;
 	struct rtw89_txpwr_lmt_ru_5ghz_data lmt_ru_5ghz;
 	struct rtw89_txpwr_lmt_ru_6ghz_data lmt_ru_6ghz;
+	struct rtw89_txpwr_lmt_ru_2ghz_data da_lmt_ru_2ghz;
+	struct rtw89_txpwr_lmt_ru_5ghz_data da_lmt_ru_5ghz;
+	struct rtw89_txpwr_lmt_ru_6ghz_data da_lmt_ru_6ghz;
 	struct rtw89_tx_shape_lmt_data tx_shape_lmt;
 	struct rtw89_tx_shape_lmt_ru_data tx_shape_lmt_ru;
 	struct rtw89_rfe_parms rfe_parms;
@@ -4284,12 +4307,14 @@ struct rtw89_chip_info {
 	bool support_rnr;
 	bool support_ant_gain;
 	bool support_tas;
+	bool support_sar_by_ant;
 	bool ul_tb_waveform_ctrl;
 	bool ul_tb_pwr_diff;
 	bool rx_freq_frome_ie;
 	bool hw_sec_hdr;
 	bool hw_mgmt_tx_encrypt;
 	bool hw_tkip_crypto;
+	bool hw_mlo_bmc_crypto;
 	u8 rf_path_num;
 	u8 tx_nss;
 	u8 rx_nss;
@@ -4494,6 +4519,7 @@ enum rtw89_fw_feature {
 	RTW89_FW_FEATURE_LPS_CH_INFO,
 	RTW89_FW_FEATURE_NO_PHYCAP_P1,
 	RTW89_FW_FEATURE_NO_POWER_DIFFERENCE,
+	RTW89_FW_FEATURE_BEACON_LOSS_COUNT_V1,
 };
 
 struct rtw89_fw_suit {
@@ -4606,6 +4632,7 @@ struct rtw89_cam_info {
 enum rtw89_sar_sources {
 	RTW89_SAR_SOURCE_NONE,
 	RTW89_SAR_SOURCE_COMMON,
+	RTW89_SAR_SOURCE_ACPI,
 
 	RTW89_SAR_SOURCE_NR,
 };
@@ -4630,8 +4657,62 @@ struct rtw89_sar_cfg_common {
 	s32 cfg[RTW89_SAR_SUBBAND_NR];
 };
 
+enum rtw89_acpi_sar_subband {
+	RTW89_ACPI_SAR_2GHZ_SUBBAND,
+	RTW89_ACPI_SAR_5GHZ_SUBBAND_1,   /* U-NII-1 */
+	RTW89_ACPI_SAR_5GHZ_SUBBAND_2,   /* U-NII-2 */
+	RTW89_ACPI_SAR_5GHZ_SUBBAND_2E,  /* U-NII-2-Extended */
+	RTW89_ACPI_SAR_5GHZ_SUBBAND_3_4, /* U-NII-3 and U-NII-4 */
+	RTW89_ACPI_SAR_6GHZ_SUBBAND_5_L, /* U-NII-5 lower part */
+	RTW89_ACPI_SAR_6GHZ_SUBBAND_5_H, /* U-NII-5 higher part */
+	RTW89_ACPI_SAR_6GHZ_SUBBAND_6,   /* U-NII-6 */
+	RTW89_ACPI_SAR_6GHZ_SUBBAND_7_L, /* U-NII-7 lower part */
+	RTW89_ACPI_SAR_6GHZ_SUBBAND_7_H, /* U-NII-7 higher part */
+	RTW89_ACPI_SAR_6GHZ_SUBBAND_8,   /* U-NII-8 */
+
+	NUM_OF_RTW89_ACPI_SAR_SUBBAND,
+	RTW89_ACPI_SAR_SUBBAND_NR_LEGACY = RTW89_ACPI_SAR_5GHZ_SUBBAND_3_4 + 1,
+	RTW89_ACPI_SAR_SUBBAND_NR_HAS_6GHZ = RTW89_ACPI_SAR_6GHZ_SUBBAND_8 + 1,
+};
+
+#define TXPWR_FACTOR_OF_RTW89_ACPI_SAR 3 /* unit: 0.125 dBm */
+#define MAX_VAL_OF_RTW89_ACPI_SAR S16_MAX
+#define MIN_VAL_OF_RTW89_ACPI_SAR S16_MIN
+#define MAX_NUM_OF_RTW89_ACPI_SAR_TBL 6
+#define NUM_OF_RTW89_ACPI_SAR_RF_PATH (RF_PATH_B + 1)
+
+struct rtw89_sar_entry_from_acpi {
+	s16 v[NUM_OF_RTW89_ACPI_SAR_SUBBAND][NUM_OF_RTW89_ACPI_SAR_RF_PATH];
+};
+
+struct rtw89_sar_table_from_acpi {
+	/* If this table is active, must fill all fields according to either
+	 * configuration in BIOS or some default values for SAR to work well.
+	 */
+	struct rtw89_sar_entry_from_acpi entries[RTW89_REGD_NUM];
+};
+
+struct rtw89_sar_indicator_from_acpi {
+	bool enable_sync;
+	unsigned int fields;
+	u8 (*rfpath_to_antidx)(enum rtw89_rf_path rfpath);
+
+	/* Select among @tables of container, rtw89_sar_cfg_acpi, by path.
+	 * Not design with pointers since addresses will be invalid after
+	 * sync content with local container instance.
+	 */
+	u8 tblsel[NUM_OF_RTW89_ACPI_SAR_RF_PATH];
+};
+
+struct rtw89_sar_cfg_acpi {
+	u8 downgrade_2tx;
+	unsigned int valid_num;
+	struct rtw89_sar_table_from_acpi tables[MAX_NUM_OF_RTW89_ACPI_SAR_TBL];
+	struct rtw89_sar_indicator_from_acpi indicator;
+};
+
 struct rtw89_sar_info {
-	/* used to decide how to acces SAR cfg union */
+	/* used to decide how to access SAR cfg union */
 	enum rtw89_sar_sources src;
 
 	/* reserved for different knids of SAR cfg struct.
@@ -4639,6 +4720,7 @@ struct rtw89_sar_info {
 	 */
 	union {
 		struct rtw89_sar_cfg_common cfg_common;
+		struct rtw89_sar_cfg_acpi cfg_acpi;
 	};
 };
 
@@ -4674,11 +4756,14 @@ struct rtw89_ant_gain_info {
 struct rtw89_6ghz_span {
 	enum rtw89_sar_subband sar_subband_low;
 	enum rtw89_sar_subband sar_subband_high;
+	enum rtw89_acpi_sar_subband acpi_sar_subband_low;
+	enum rtw89_acpi_sar_subband acpi_sar_subband_high;
 	enum rtw89_ant_gain_subband ant_gain_subband_low;
 	enum rtw89_ant_gain_subband ant_gain_subband_high;
 };
 
 #define RTW89_SAR_SPAN_VALID(span) ((span)->sar_subband_high)
+#define RTW89_ACPI_SAR_SPAN_VALID(span) ((span)->acpi_sar_subband_high)
 #define RTW89_ANT_GAIN_SPAN_VALID(span) ((span)->ant_gain_subband_high)
 
 enum rtw89_tas_state {
@@ -4692,6 +4777,7 @@ enum rtw89_tas_state {
 struct rtw89_tas_info {
 	u16 tx_ratio_history[RTW89_TAS_TX_RATIO_WINDOW];
 	u64 txpwr_history[RTW89_TAS_TXPWR_WINDOW];
+	u8 enabled_countries;
 	u8 txpwr_head_idx;
 	u8 txpwr_tail_idx;
 	u8 tx_ratio_idx;
@@ -4765,6 +4851,7 @@ enum rtw89_dm_type {
 	RTW89_DM_DYNAMIC_EDCCA,
 	RTW89_DM_THERMAL_PROTECT,
 	RTW89_DM_TAS,
+	RTW89_DM_MLO,
 };
 
 #define RTW89_THERMAL_PROT_LV_MAX 5
@@ -4786,6 +4873,7 @@ struct rtw89_hal {
 	bool no_mcs_12_13;
 
 	atomic_t roc_chanctx_idx;
+	u8 roc_link_index;
 
 	DECLARE_BITMAP(changes, NUM_OF_RTW89_CHANCTX_CHANGES);
 	DECLARE_BITMAP(entity_map, NUM_OF_RTW89_CHANCTX);
@@ -5207,6 +5295,8 @@ struct rtw89_regulatory_info {
 	const struct rtw89_regd *regd;
 	enum rtw89_reg_6ghz_power reg_6ghz_power;
 	struct rtw89_reg_6ghz_tpe reg_6ghz_tpe;
+	bool txpwr_uk_follow_etsi;
+
 	DECLARE_BITMAP(block_unii4, RTW89_REGD_MAX_COUNTRY_NUM);
 	DECLARE_BITMAP(block_6ghz, RTW89_REGD_MAX_COUNTRY_NUM);
 	DECLARE_BITMAP(block_6ghz_sp, RTW89_REGD_MAX_COUNTRY_NUM);
@@ -5360,9 +5450,10 @@ struct rtw89_early_h2c {
 struct rtw89_hw_scan_info {
 	struct rtw89_vif_link *scanning_vif;
 	struct list_head pkt_list[NUM_NL80211_BANDS];
+	struct list_head chan_list;
 	struct rtw89_chan op_chan;
+	bool connected;
 	bool abort;
-	u32 last_chan_idx;
 };
 
 enum rtw89_phy_bb_gain_band {
@@ -5574,6 +5665,8 @@ struct rtw89_mcc_role {
 	struct rtw89_mcc_policy policy;
 	struct rtw89_mcc_limit limit;
 
+	const struct rtw89_mcc_courtesy_cfg *crtz;
+
 	/* only valid when running with FW MRC mechanism */
 	u8 slot_idx;
 
@@ -5591,13 +5684,16 @@ struct rtw89_mcc_bt_role {
 	u16 duration; /* TU */
 };
 
-struct rtw89_mcc_courtesy {
-	bool enable;
+struct rtw89_mcc_courtesy_cfg {
 	u8 slot_num;
-	u8 macid_src;
 	u8 macid_tgt;
 };
 
+struct rtw89_mcc_courtesy {
+	struct rtw89_mcc_courtesy_cfg ref;
+	struct rtw89_mcc_courtesy_cfg aux;
+};
+
 enum rtw89_mcc_plan {
 	RTW89_MCC_PLAN_TAIL_BT,
 	RTW89_MCC_PLAN_MID_BT,
@@ -5631,6 +5727,7 @@ struct rtw89_mcc_config {
 	struct rtw89_mcc_pattern pattern;
 	struct rtw89_mcc_sync sync;
 	u64 start_tsf;
+	u64 start_tsf_in_aux_domain;
 	u16 mcc_interval; /* TU */
 	u16 beacon_offset; /* TU */
 };
@@ -5651,6 +5748,16 @@ struct rtw89_mcc_info {
 	struct rtw89_mcc_config config;
 };
 
+enum rtw89_mlo_mode {
+	RTW89_MLO_MODE_MLSR = 0,
+
+	NUM_OF_RTW89_MLO_MODE,
+};
+
+struct rtw89_mlo_info {
+	struct rtw89_wait_info wait;
+};
+
 struct rtw89_dev {
 	struct ieee80211_hw *hw;
 	struct device *dev;
@@ -5666,6 +5773,7 @@ struct rtw89_dev {
 	const struct rtw89_rfe_parms *rfe_parms;
 	struct rtw89_hal hal;
 	struct rtw89_mcc_info mcc;
+	struct rtw89_mlo_info mlo;
 	struct rtw89_mac_info mac;
 	struct rtw89_fw_info fw;
 	struct rtw89_hci_info hci;
@@ -5802,6 +5910,9 @@ struct rtw89_vif {
 	struct rtw89_roc roc;
 	bool offchan;
 
+	enum rtw89_mlo_mode mlo_mode;
+
+	struct list_head dlink_pool;
 	u8 links_inst_valid_num;
 	DECLARE_BITMAP(links_inst_map, __RTW89_MLD_MAX_LINK_NUM);
 	struct rtw89_vif_link *links[IEEE80211_MLD_MAX_NUM_LINKS];
@@ -5841,6 +5952,7 @@ struct rtw89_sta {
 
 	DECLARE_BITMAP(pairwise_sec_cam_map, RTW89_MAX_SEC_CAM_NUM);
 
+	struct list_head dlink_pool;
 	u8 links_inst_valid_num;
 	DECLARE_BITMAP(links_inst_map, __RTW89_MLD_MAX_LINK_NUM);
 	struct rtw89_sta_link *links[IEEE80211_MLD_MAX_NUM_LINKS];
@@ -5936,6 +6048,12 @@ rtw89_assoc_link_rcu_dereference(struct rtw89_dev *rtwdev, u8 macid)
 	return rcu_dereference(rtwdev->assoc_link_on_macid[macid]);
 }
 
+#define rtw89_get_designated_link(links_holder) \
+({ \
+	typeof(links_holder) p = links_holder; \
+	list_first_entry_or_null(&p->dlink_pool, typeof(*p->links_inst), dlink_schd); \
+})
+
 static inline int rtw89_hci_tx_write(struct rtw89_dev *rtwdev,
 				     struct rtw89_core_tx_request *tx_req)
 {
@@ -6825,9 +6943,14 @@ static inline void rtw89_load_txpwr_table(struct rtw89_dev *rtwdev,
 
 static inline u8 rtw89_regd_get(struct rtw89_dev *rtwdev, u8 band)
 {
-	const struct rtw89_regd *regd = rtwdev->regulatory.regd;
+	const struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	const struct rtw89_regd *regd = regulatory->regd;
+	u8 txpwr_regd = regd->txpwr_regd[band];
+
+	if (regulatory->txpwr_uk_follow_etsi && txpwr_regd == RTW89_UK)
+		return RTW89_ETSI;
 
-	return regd->txpwr_regd[band];
+	return txpwr_regd;
 }
 
 static inline void rtw89_ctrl_btg_bt_rx(struct rtw89_dev *rtwdev, bool en,
@@ -7185,6 +7308,7 @@ void rtw89_chip_cfg_txpwr_ul_tb_offset(struct rtw89_dev *rtwdev,
 bool rtw89_ra_report_to_bitrate(struct rtw89_dev *rtwdev, u8 rpt_rate, u16 *bitrate);
 int rtw89_regd_setup(struct rtw89_dev *rtwdev);
 int rtw89_regd_init_hint(struct rtw89_dev *rtwdev);
+const char *rtw89_regd_get_string(enum rtw89_regulation_type regd);
 void rtw89_traffic_stats_init(struct rtw89_dev *rtwdev,
 			      struct rtw89_traffic_stats *stats);
 int rtw89_wait_for_cond(struct rtw89_wait_info *wait, unsigned int cond);
@@ -7206,5 +7330,7 @@ void rtw89_core_update_p2p_ps(struct rtw89_dev *rtwdev,
 			      struct rtw89_vif_link *rtwvif_link,
 			      struct ieee80211_bss_conf *bss_conf);
 void rtw89_core_ntfy_btc_event(struct rtw89_dev *rtwdev, enum rtw89_btc_hmsg event);
+int rtw89_core_mlsr_switch(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+			   unsigned int link_id);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index f2c5753fd386..d6016fa107fb 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -85,6 +85,7 @@ struct rtw89_debugfs {
 	struct rtw89_debugfs_priv phy_info;
 	struct rtw89_debugfs_priv stations;
 	struct rtw89_debugfs_priv disable_dm;
+	struct rtw89_debugfs_priv mlo_mode;
 };
 
 struct rtw89_debugfs_iter_data {
@@ -854,45 +855,21 @@ static ssize_t __print_txpwr_map(struct rtw89_dev *rtwdev, char *buf, size_t buf
 	return p - buf;
 }
 
-#define case_REGD(_regd) \
-	case RTW89_ ## _regd: \
-		p += scnprintf(p, end - p, #_regd "\n"); \
-		break
-
 static int __print_regd(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
 			const struct rtw89_chan *chan)
 {
+	const struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
 	char *p = buf, *end = buf + bufsz;
 	u8 band = chan->band_type;
 	u8 regd = rtw89_regd_get(rtwdev, band);
 
-	switch (regd) {
-	default:
-		p += scnprintf(p, end - p, "UNKNOWN: %d\n", regd);
-		break;
-	case_REGD(WW);
-	case_REGD(ETSI);
-	case_REGD(FCC);
-	case_REGD(MKK);
-	case_REGD(NA);
-	case_REGD(IC);
-	case_REGD(KCC);
-	case_REGD(NCC);
-	case_REGD(CHILE);
-	case_REGD(ACMA);
-	case_REGD(MEXICO);
-	case_REGD(UKRAINE);
-	case_REGD(CN);
-	case_REGD(QATAR);
-	case_REGD(UK);
-	case_REGD(THAILAND);
-	}
+	p += scnprintf(p, end - p, "%s\n", rtw89_regd_get_string(regd));
+	p += scnprintf(p, end - p, "\t(txpwr UK follow ETSI: %s)\n",
+		       str_yes_no(regulatory->txpwr_uk_follow_etsi));
 
 	return p - buf;
 }
 
-#undef case_REGD
-
 struct dbgfs_txpwr_table {
 	const struct txpwr_map *byr;
 	const struct txpwr_map *lmt;
@@ -949,6 +926,7 @@ ssize_t rtw89_debug_priv_txpwr_table_get(struct rtw89_dev *rtwdev,
 					 char *buf, size_t bufsz)
 {
 	enum rtw89_chip_gen chip_gen = rtwdev->chip->chip_gen;
+	struct rtw89_sar_parm sar_parm = {};
 	const struct dbgfs_txpwr_table *tbl;
 	const struct rtw89_chan *chan;
 	char *p = buf, *end = buf + bufsz;
@@ -958,11 +936,12 @@ ssize_t rtw89_debug_priv_txpwr_table_get(struct rtw89_dev *rtwdev,
 
 	rtw89_leave_ps_mode(rtwdev);
 	chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	sar_parm.center_freq = chan->freq;
 
 	p += rtw89_debug_priv_txpwr_table_get_regd(rtwdev, p, end - p, chan);
 
 	p += scnprintf(p, end - p, "[SAR]\n");
-	p += rtw89_print_sar(rtwdev, p, end - p, chan->freq);
+	p += rtw89_print_sar(rtwdev, p, end - p, &sar_parm);
 
 	p += scnprintf(p, end - p, "[TAS]\n");
 	p += rtw89_print_tas(rtwdev, p, end - p);
@@ -3993,14 +3972,16 @@ static int rtw89_dump_pkt_offload(char *buf, size_t bufsz, struct list_head *pkt
 
 static int rtw89_vif_link_ids_get(struct rtw89_dev *rtwdev,
 				  char *buf, size_t bufsz, u8 *mac,
-				  struct rtw89_vif_link *rtwvif_link)
+				  struct rtw89_vif_link *rtwvif_link,
+				  bool designated)
 {
 	struct rtw89_bssid_cam_entry *bssid_cam = &rtwvif_link->bssid_cam;
 	char *p = buf, *end = buf + bufsz;
 
 	p += scnprintf(p, end - p, "    [%u] %pM\n", rtwvif_link->mac_id,
 		       rtwvif_link->mac_addr);
-	p += scnprintf(p, end - p, "\tlink_id=%u\n", rtwvif_link->link_id);
+	p += scnprintf(p, end - p, "\tlink_id=%u%s\n", rtwvif_link->link_id,
+		       designated ? " (*)" : "");
 	p += scnprintf(p, end - p, "\tbssid_cam_idx=%u\n",
 		       bssid_cam->bssid_cam_idx);
 	p += rtw89_dump_addr_cam(rtwdev, p, end - p, &rtwvif_link->addr_cam);
@@ -4017,15 +3998,19 @@ void rtw89_vif_ids_get_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
 		(struct rtw89_debugfs_iter_data *)data;
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 	struct rtw89_dev *rtwdev = rtwvif->rtwdev;
+	struct rtw89_vif_link *designated_link;
 	struct rtw89_vif_link *rtwvif_link;
 	size_t bufsz = iter_data->bufsz;
 	char *buf = iter_data->buf;
 	char *p = buf, *end = buf + bufsz;
 	unsigned int link_id;
 
+	designated_link = rtw89_get_designated_link(rtwvif);
+
 	p += scnprintf(p, end - p, "VIF %pM\n", rtwvif->mac_addr);
 	rtw89_vif_for_each_link(rtwvif, rtwvif_link, link_id)
-		p += rtw89_vif_link_ids_get(rtwdev, p, end - p, mac, rtwvif_link);
+		p += rtw89_vif_link_ids_get(rtwdev, p, end - p, mac, rtwvif_link,
+					    rtwvif_link == designated_link);
 
 	rtw89_debugfs_iter_data_next(iter_data, p, end - p, p - buf);
 }
@@ -4055,7 +4040,8 @@ static int rtw89_dump_ba_cam(struct rtw89_dev *rtwdev,
 
 static int rtw89_sta_link_ids_get(struct rtw89_dev *rtwdev,
 				  char *buf, size_t bufsz,
-				  struct rtw89_sta_link *rtwsta_link)
+				  struct rtw89_sta_link *rtwsta_link,
+				  bool designated)
 {
 	struct ieee80211_link_sta *link_sta;
 	char *p = buf, *end = buf + bufsz;
@@ -4069,7 +4055,8 @@ static int rtw89_sta_link_ids_get(struct rtw89_dev *rtwdev,
 
 	rcu_read_unlock();
 
-	p += scnprintf(p, end - p, "\tlink_id=%u\n", rtwsta_link->link_id);
+	p += scnprintf(p, end - p, "\tlink_id=%u%s\n", rtwsta_link->link_id,
+		       designated ? " (*)" : "");
 	p += rtw89_dump_addr_cam(rtwdev, p, end - p, &rtwsta_link->addr_cam);
 	p += rtw89_dump_ba_cam(rtwdev, p, end - p, rtwsta_link);
 
@@ -4082,16 +4069,20 @@ static void rtw89_sta_ids_get_iter(void *data, struct ieee80211_sta *sta)
 		(struct rtw89_debugfs_iter_data *)data;
 	struct rtw89_sta *rtwsta = sta_to_rtwsta(sta);
 	struct rtw89_dev *rtwdev = rtwsta->rtwdev;
+	struct rtw89_sta_link *designated_link;
 	struct rtw89_sta_link *rtwsta_link;
 	size_t bufsz = iter_data->bufsz;
 	char *buf = iter_data->buf;
 	char *p = buf, *end = buf + bufsz;
 	unsigned int link_id;
 
+	designated_link = rtw89_get_designated_link(rtwsta);
+
 	p += scnprintf(p, end - p, "STA %pM %s\n", sta->addr,
 		       sta->tdls ? "(TDLS)" : "");
 	rtw89_sta_for_each_link(rtwsta, rtwsta_link, link_id)
-		p += rtw89_sta_link_ids_get(rtwdev, p, end - p, rtwsta_link);
+		p += rtw89_sta_link_ids_get(rtwdev, p, end - p, rtwsta_link,
+					    rtwsta_link == designated_link);
 
 	rtw89_debugfs_iter_data_next(iter_data, p, end - p, p - buf);
 }
@@ -4146,6 +4137,35 @@ static ssize_t rtw89_debug_priv_stations_get(struct rtw89_dev *rtwdev,
 	return p - buf;
 }
 
+static void rtw89_debug_disable_dm_cfg_bmap(struct rtw89_dev *rtwdev, u32 new)
+{
+	struct rtw89_hal *hal = &rtwdev->hal;
+	u32 old = hal->disabled_dm_bitmap;
+
+	if (new == old)
+		return;
+
+	hal->disabled_dm_bitmap = new;
+
+	rtw89_debug(rtwdev, RTW89_DBG_STATE, "Disable DM: 0x%x -> 0x%x\n", old, new);
+}
+
+static void rtw89_debug_disable_dm_set_flag(struct rtw89_dev *rtwdev, u8 flag)
+{
+	struct rtw89_hal *hal = &rtwdev->hal;
+	u32 cur = hal->disabled_dm_bitmap;
+
+	rtw89_debug_disable_dm_cfg_bmap(rtwdev, cur | BIT(flag));
+}
+
+static void rtw89_debug_disable_dm_clr_flag(struct rtw89_dev *rtwdev, u8 flag)
+{
+	struct rtw89_hal *hal = &rtwdev->hal;
+	u32 cur = hal->disabled_dm_bitmap;
+
+	rtw89_debug_disable_dm_cfg_bmap(rtwdev, cur & ~BIT(flag));
+}
+
 #define DM_INFO(type) {RTW89_DM_ ## type, #type}
 
 static const struct rtw89_disabled_dm_info {
@@ -4155,6 +4175,7 @@ static const struct rtw89_disabled_dm_info {
 	DM_INFO(DYNAMIC_EDCCA),
 	DM_INFO(THERMAL_PROTECT),
 	DM_INFO(TAS),
+	DM_INFO(MLO),
 };
 
 static ssize_t
@@ -4188,7 +4209,6 @@ rtw89_debug_priv_disable_dm_set(struct rtw89_dev *rtwdev,
 				struct rtw89_debugfs_priv *debugfs_priv,
 				const char *buf, size_t count)
 {
-	struct rtw89_hal *hal = &rtwdev->hal;
 	u32 conf;
 	int ret;
 
@@ -4196,7 +4216,83 @@ rtw89_debug_priv_disable_dm_set(struct rtw89_dev *rtwdev,
 	if (ret)
 		return -EINVAL;
 
-	hal->disabled_dm_bitmap = conf;
+	rtw89_debug_disable_dm_cfg_bmap(rtwdev, conf);
+
+	return count;
+}
+
+static void rtw89_debug_mlo_mode_set_mlsr(struct rtw89_dev *rtwdev,
+					  unsigned int link_id)
+{
+	struct ieee80211_vif *vif;
+	struct rtw89_vif *rtwvif;
+
+	rtw89_for_each_rtwvif(rtwdev, rtwvif) {
+		vif = rtwvif_to_vif(rtwvif);
+		if (!ieee80211_vif_is_mld(vif))
+			continue;
+
+		rtw89_core_mlsr_switch(rtwdev, rtwvif, link_id);
+	}
+}
+
+static ssize_t
+rtw89_debug_priv_mlo_mode_get(struct rtw89_dev *rtwdev,
+			      struct rtw89_debugfs_priv *debugfs_priv,
+			      char *buf, size_t bufsz)
+{
+	bool mlo_dm_dis = rtwdev->hal.disabled_dm_bitmap & BIT(RTW89_DM_MLO);
+	char *p = buf, *end = buf + bufsz;
+	struct ieee80211_vif *vif;
+	struct rtw89_vif *rtwvif;
+	int count = 0;
+
+	p += scnprintf(p, end - p, "MLD(s) status: (MLO DM: %s)\n",
+		       str_disable_enable(mlo_dm_dis));
+
+	rtw89_for_each_rtwvif(rtwdev, rtwvif) {
+		vif = rtwvif_to_vif(rtwvif);
+		if (!ieee80211_vif_is_mld(vif))
+			continue;
+
+		p += scnprintf(p, end - p,
+			       "\t#%u: MLO mode %x, valid 0x%x, active 0x%x\n",
+			       count++, rtwvif->mlo_mode, vif->valid_links,
+			       vif->active_links);
+	}
+
+	if (count == 0)
+		p += scnprintf(p, end - p, "\t(None)\n");
+
+	return p - buf;
+}
+
+static ssize_t
+rtw89_debug_priv_mlo_mode_set(struct rtw89_dev *rtwdev,
+			      struct rtw89_debugfs_priv *debugfs_priv,
+			      const char *buf, size_t count)
+{
+	u8 num, mlo_mode;
+	u32 argv;
+
+	num = sscanf(buf, "%hhx %u", &mlo_mode, &argv);
+	if (num != 2)
+		return -EINVAL;
+
+	rtw89_debug_disable_dm_set_flag(rtwdev, RTW89_DM_MLO);
+
+	rtw89_debug(rtwdev, RTW89_DBG_STATE, "Set MLO mode to %x\n", mlo_mode);
+
+	switch (mlo_mode) {
+	case RTW89_MLO_MODE_MLSR:
+		rtw89_debug_mlo_mode_set_mlsr(rtwdev, argv);
+		break;
+	default:
+		rtw89_debug(rtwdev, RTW89_DBG_STATE, "Unsupported MLO mode\n");
+		rtw89_debug_disable_dm_clr_flag(rtwdev, RTW89_DM_MLO);
+
+		return -EOPNOTSUPP;
+	}
 
 	return count;
 }
@@ -4257,7 +4353,8 @@ static const struct rtw89_debugfs rtw89_debugfs_templ = {
 	.fw_log_manual = rtw89_debug_priv_set(fw_log_manual, WLOCK),
 	.phy_info = rtw89_debug_priv_get(phy_info),
 	.stations = rtw89_debug_priv_get(stations, RLOCK),
-	.disable_dm = rtw89_debug_priv_set_and_get(disable_dm),
+	.disable_dm = rtw89_debug_priv_set_and_get(disable_dm, RWLOCK),
+	.mlo_mode = rtw89_debug_priv_set_and_get(mlo_mode, RWLOCK),
 };
 
 #define rtw89_debugfs_add(name, mode, fopname, parent)				\
@@ -4302,6 +4399,7 @@ void rtw89_debugfs_add_sec1(struct rtw89_dev *rtwdev, struct dentry *debugfs_top
 	rtw89_debugfs_add_r(phy_info);
 	rtw89_debugfs_add_r(stations);
 	rtw89_debugfs_add_rw(disable_dm);
+	rtw89_debugfs_add_rw(mlo_mode);
 }
 
 void rtw89_debugfs_init(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 8643b17866f8..00b65b2995cf 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -15,6 +15,8 @@
 #include "util.h"
 #include "wow.h"
 
+static bool rtw89_is_any_vif_connected_or_connecting(struct rtw89_dev *rtwdev);
+
 struct rtw89_eapol_2_of_2 {
 	u8 gtkbody[14];
 	u8 key_des_ver;
@@ -554,7 +556,7 @@ const struct rtw89_mfw_hdr *rtw89_mfw_get_hdr_ptr(struct rtw89_dev *rtwdev,
 	if (sizeof(*mfw_hdr) > firmware->size)
 		return NULL;
 
-	mfw_hdr = (const struct rtw89_mfw_hdr *)firmware->data;
+	mfw_hdr = (const struct rtw89_mfw_hdr *)&firmware->data[0];
 
 	if (mfw_hdr->sig != RTW89_MFW_SIG)
 		return NULL;
@@ -850,6 +852,7 @@ static const struct __fw_feat_cfg fw_feat_tbl[] = {
 	__CFG_FW_FEAT(RTL8922A, lt, 0, 35, 49, 0, RFK_PRE_NOTIFY_V1),
 	__CFG_FW_FEAT(RTL8922A, lt, 0, 35, 51, 0, NO_PHYCAP_P1),
 	__CFG_FW_FEAT(RTL8922A, lt, 0, 35, 64, 0, NO_POWER_DIFFERENCE),
+	__CFG_FW_FEAT(RTL8922A, ge, 0, 35, 71, 0, BEACON_LOSS_COUNT_V1),
 };
 
 static void rtw89_fw_iterate_feature_cfg(struct rtw89_fw_info *fw,
@@ -1018,7 +1021,7 @@ int rtw89_build_phy_tbl_from_elm(struct rtw89_dev *rtwdev,
 	}
 
 	n_regs = le32_to_cpu(elm->size) / sizeof(tbl->regs[0]);
-	regs = kcalloc(n_regs, sizeof(tbl->regs[0]), GFP_KERNEL);
+	regs = kcalloc(n_regs, sizeof(*regs), GFP_KERNEL);
 	if (!regs)
 		goto out;
 
@@ -1298,6 +1301,18 @@ static const struct rtw89_fw_element_handler __fw_element_handlers[] = {
 		rtw89_fw_recognize_txpwr_from_elm,
 		{ .offset = offsetof(struct rtw89_rfe_data, lmt_6ghz.conf) }, NULL,
 	},
+	[RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_2GHZ] = {
+		rtw89_fw_recognize_txpwr_from_elm,
+		{ .offset = offsetof(struct rtw89_rfe_data, da_lmt_2ghz.conf) }, NULL,
+	},
+	[RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_5GHZ] = {
+		rtw89_fw_recognize_txpwr_from_elm,
+		{ .offset = offsetof(struct rtw89_rfe_data, da_lmt_5ghz.conf) }, NULL,
+	},
+	[RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_6GHZ] = {
+		rtw89_fw_recognize_txpwr_from_elm,
+		{ .offset = offsetof(struct rtw89_rfe_data, da_lmt_6ghz.conf) }, NULL,
+	},
 	[RTW89_FW_ELEMENT_ID_TXPWR_LMT_RU_2GHZ] = {
 		rtw89_fw_recognize_txpwr_from_elm,
 		{ .offset = offsetof(struct rtw89_rfe_data, lmt_ru_2ghz.conf) }, NULL,
@@ -1310,6 +1325,18 @@ static const struct rtw89_fw_element_handler __fw_element_handlers[] = {
 		rtw89_fw_recognize_txpwr_from_elm,
 		{ .offset = offsetof(struct rtw89_rfe_data, lmt_ru_6ghz.conf) }, NULL,
 	},
+	[RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_RU_2GHZ] = {
+		rtw89_fw_recognize_txpwr_from_elm,
+		{ .offset = offsetof(struct rtw89_rfe_data, da_lmt_ru_2ghz.conf) }, NULL,
+	},
+	[RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_RU_5GHZ] = {
+		rtw89_fw_recognize_txpwr_from_elm,
+		{ .offset = offsetof(struct rtw89_rfe_data, da_lmt_ru_5ghz.conf) }, NULL,
+	},
+	[RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_RU_6GHZ] = {
+		rtw89_fw_recognize_txpwr_from_elm,
+		{ .offset = offsetof(struct rtw89_rfe_data, da_lmt_ru_6ghz.conf) }, NULL,
+	},
 	[RTW89_FW_ELEMENT_ID_TX_SHAPE_LMT] = {
 		rtw89_fw_recognize_txpwr_from_elm,
 		{ .offset = offsetof(struct rtw89_rfe_data, tx_shape_lmt.conf) }, NULL,
@@ -2483,7 +2510,7 @@ int rtw89_fw_h2c_fw_log(struct rtw89_dev *rtwdev, bool enable)
 	if (enable)
 		comp = BIT(RTW89_FW_LOG_COMP_INIT) | BIT(RTW89_FW_LOG_COMP_TASK) |
 		       BIT(RTW89_FW_LOG_COMP_PS) | BIT(RTW89_FW_LOG_COMP_ERROR) |
-		       BIT(RTW89_FW_LOG_COMP_SCAN);
+		       BIT(RTW89_FW_LOG_COMP_MLO) | BIT(RTW89_FW_LOG_COMP_SCAN);
 
 	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, H2C_LOG_CFG_LEN);
 	if (!skb) {
@@ -3065,8 +3092,8 @@ static void __rtw89_fw_h2c_set_tx_path(struct rtw89_dev *rtwdev,
 		ntx_path = RF_A;
 		map_b = 0;
 	} else {
-		ntx_path = hal->antenna_tx ? hal->antenna_tx : RF_B;
-		map_b = hal->antenna_tx == RF_AB ? 1 : 0;
+		ntx_path = hal->antenna_tx ? hal->antenna_tx : RF_AB;
+		map_b = ntx_path == RF_AB ? 1 : 0;
 	}
 
 	SET_CMC_TBL_NTX_PATH_EN(skb->data, ntx_path);
@@ -4004,8 +4031,9 @@ out:
 int rtw89_fw_h2c_join_info(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link,
 			   struct rtw89_sta_link *rtwsta_link, bool dis_conn)
 {
-	struct sk_buff *skb;
 	u8 mac_id = rtwsta_link ? rtwsta_link->mac_id : rtwvif_link->mac_id;
+	struct ieee80211_vif *vif = rtwvif_link_to_vif(rtwvif_link);
+	bool is_mld = ieee80211_vif_is_mld(vif);
 	u8 self_role = rtwvif_link->self_role;
 	enum rtw89_fw_sta_type sta_type;
 	u8 net_type = rtwvif_link->net_type;
@@ -4013,6 +4041,9 @@ int rtw89_fw_h2c_join_info(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwv
 	struct rtw89_h2c_join *h2c;
 	u32 len = sizeof(*h2c);
 	bool format_v1 = false;
+	struct sk_buff *skb;
+	u8 main_mac_id;
+	bool init_ps;
 	int ret;
 
 	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE) {
@@ -4054,8 +4085,28 @@ int rtw89_fw_h2c_join_info(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwv
 	h2c_v1 = (struct rtw89_h2c_join_v1 *)skb->data;
 
 	sta_type = rtw89_fw_get_sta_type(rtwdev, rtwvif_link, rtwsta_link);
+	init_ps = rtwvif_link != rtw89_get_designated_link(rtwvif_link->rtwvif);
+
+	if (rtwsta_link)
+		main_mac_id = rtw89_sta_get_main_macid(rtwsta_link->rtwsta);
+	else
+		main_mac_id = rtw89_vif_get_main_macid(rtwvif_link->rtwvif);
+
+	h2c_v1->w1 = le32_encode_bits(sta_type, RTW89_H2C_JOININFO_W1_STA_TYPE) |
+		     le32_encode_bits(is_mld, RTW89_H2C_JOININFO_W1_IS_MLD) |
+		     le32_encode_bits(main_mac_id, RTW89_H2C_JOININFO_W1_MAIN_MACID) |
+		     le32_encode_bits(RTW89_H2C_JOININFO_MLO_MODE_MLSR,
+				      RTW89_H2C_JOININFO_W1_MLO_MODE) |
+		     le32_encode_bits(0, RTW89_H2C_JOININFO_W1_EMLSR_CAB) |
+		     le32_encode_bits(0, RTW89_H2C_JOININFO_W1_NSTR_EN) |
+		     le32_encode_bits(init_ps, RTW89_H2C_JOININFO_W1_INIT_PWR_STATE) |
+		     le32_encode_bits(IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US,
+				      RTW89_H2C_JOININFO_W1_EMLSR_PADDING) |
+		     le32_encode_bits(IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US,
+				      RTW89_H2C_JOININFO_W1_EMLSR_TRANS_DELAY) |
+		     le32_encode_bits(0, RTW89_H2C_JOININFO_W2_MACID_EXT) |
+		     le32_encode_bits(0, RTW89_H2C_JOININFO_W2_MAIN_MACID_EXT);
 
-	h2c_v1->w1 = le32_encode_bits(sta_type, RTW89_H2C_JOININFO_W1_STA_TYPE);
 	h2c_v1->w2 = 0;
 
 done:
@@ -4339,6 +4390,7 @@ int rtw89_fw_h2c_set_bcn_fltr_cfg(struct rtw89_dev *rtwdev,
 	struct rtw89_h2c_bcnfltr *h2c;
 	u32 len = sizeof(*h2c);
 	struct sk_buff *skb;
+	u8 max_cnt, cnt;
 	int ret;
 
 	if (!RTW89_CHK_FW_FEATURE(BEACON_FILTER, &rtwdev->fw))
@@ -4367,12 +4419,20 @@ int rtw89_fw_h2c_set_bcn_fltr_cfg(struct rtw89_dev *rtwdev,
 	skb_put(skb, len);
 	h2c = (struct rtw89_h2c_bcnfltr *)skb->data;
 
+	if (RTW89_CHK_FW_FEATURE(BEACON_LOSS_COUNT_V1, &rtwdev->fw))
+		max_cnt = BIT(7) - 1;
+	else
+		max_cnt = BIT(4) - 1;
+
+	cnt = min(RTW89_BCN_LOSS_CNT, max_cnt);
+
 	h2c->w0 = le32_encode_bits(connect, RTW89_H2C_BCNFLTR_W0_MON_RSSI) |
 		  le32_encode_bits(connect, RTW89_H2C_BCNFLTR_W0_MON_BCN) |
 		  le32_encode_bits(connect, RTW89_H2C_BCNFLTR_W0_MON_EN) |
 		  le32_encode_bits(RTW89_BCN_FLTR_OFFLOAD_MODE_DEFAULT,
 				   RTW89_H2C_BCNFLTR_W0_MODE) |
-		  le32_encode_bits(RTW89_BCN_LOSS_CNT, RTW89_H2C_BCNFLTR_W0_BCN_LOSS_CNT) |
+		  le32_encode_bits(cnt >> 4, RTW89_H2C_BCNFLTR_W0_BCN_LOSS_CNT_H3) |
+		  le32_encode_bits(cnt & 0xf, RTW89_H2C_BCNFLTR_W0_BCN_LOSS_CNT_L4) |
 		  le32_encode_bits(hyst, RTW89_H2C_BCNFLTR_W0_RSSI_HYST) |
 		  le32_encode_bits(thold + MAX_RSSI,
 				   RTW89_H2C_BCNFLTR_W0_RSSI_THRESHOLD) |
@@ -5298,12 +5358,12 @@ int rtw89_fw_h2c_add_pkt_offload(struct rtw89_dev *rtwdev, u8 *id,
 }
 
 static
-int rtw89_fw_h2c_scan_list_offload(struct rtw89_dev *rtwdev, int ch_num,
-				   struct list_head *chan_list)
+int rtw89_fw_h2c_scan_list_offload_ax(struct rtw89_dev *rtwdev, int ch_num,
+				      struct list_head *chan_list)
 {
 	struct rtw89_wait_info *wait = &rtwdev->mac.fw_ofld_wait;
 	struct rtw89_h2c_chinfo_elem *elem;
-	struct rtw89_mac_chinfo *ch_info;
+	struct rtw89_mac_chinfo_ax *ch_info;
 	struct rtw89_h2c_chinfo *h2c;
 	struct sk_buff *skb;
 	unsigned int cond;
@@ -5477,7 +5537,7 @@ int rtw89_fw_h2c_scan_list_offload_be(struct rtw89_dev *rtwdev, int ch_num,
 	return 0;
 }
 
-#define RTW89_SCAN_DELAY_TSF_UNIT 104800
+#define RTW89_SCAN_DELAY_TSF_UNIT 1000000
 int rtw89_fw_h2c_scan_offload_ax(struct rtw89_dev *rtwdev,
 				 struct rtw89_scan_option *option,
 				 struct rtw89_vif_link *rtwvif_link,
@@ -5741,7 +5801,7 @@ flex_member:
 					    RTW89_H2C_SCANOFLD_BE_OPCH_W2_PKTS_CTRL) |
 			   le32_encode_bits(0,
 					    RTW89_H2C_SCANOFLD_BE_OPCH_W2_SW_DEF) |
-			   le32_encode_bits(2,
+			   le32_encode_bits(rtw89_is_mlo_1_1(rtwdev) ? 1 : 2,
 					    RTW89_H2C_SCANOFLD_BE_OPCH_W2_SS);
 
 		opch->w3 = le32_encode_bits(RTW89_SCANOFLD_PKT_NONE,
@@ -6525,7 +6585,7 @@ void rtw89_fw_st_dbg_dump(struct rtw89_dev *rtwdev)
 	rtw89_fw_prog_cnt_dump(rtwdev);
 }
 
-static void rtw89_release_pkt_list(struct rtw89_dev *rtwdev)
+static void rtw89_hw_scan_release_pkt_list(struct rtw89_dev *rtwdev)
 {
 	struct list_head *pkt_list = rtwdev->scan_info.pkt_list;
 	struct rtw89_pktofld_info *info, *tmp;
@@ -6544,6 +6604,23 @@ static void rtw89_release_pkt_list(struct rtw89_dev *rtwdev)
 	}
 }
 
+static void rtw89_hw_scan_cleanup(struct rtw89_dev *rtwdev,
+				  struct rtw89_vif_link *rtwvif_link)
+{
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
+	struct rtw89_vif *rtwvif = rtwvif_link->rtwvif;
+
+	mac->free_chan_list(rtwdev);
+	rtw89_hw_scan_release_pkt_list(rtwdev);
+
+	rtwvif->scan_req = NULL;
+	rtwvif->scan_ies = NULL;
+	scan_info->scanning_vif = NULL;
+	scan_info->abort = false;
+	scan_info->connected = false;
+}
+
 static bool rtw89_is_6ghz_wildcard_probe_req(struct rtw89_dev *rtwdev,
 					     struct cfg80211_scan_request *req,
 					     struct rtw89_pktofld_info *info,
@@ -6612,7 +6689,8 @@ out:
 }
 
 static int rtw89_hw_scan_update_probe_req(struct rtw89_dev *rtwdev,
-					  struct rtw89_vif_link *rtwvif_link)
+					  struct rtw89_vif_link *rtwvif_link,
+					  const u8 *mac_addr)
 {
 	struct rtw89_vif *rtwvif = rtwvif_link->rtwvif;
 	struct cfg80211_scan_request *req = rtwvif->scan_req;
@@ -6621,7 +6699,7 @@ static int rtw89_hw_scan_update_probe_req(struct rtw89_dev *rtwdev,
 	int ret;
 
 	for (i = 0; i < num; i++) {
-		skb = ieee80211_probereq_get(rtwdev->hw, rtwvif_link->mac_addr,
+		skb = ieee80211_probereq_get(rtwdev->hw, mac_addr,
 					     req->ssids[i].ssid,
 					     req->ssids[i].ssid_len,
 					     req->ie_len);
@@ -6638,10 +6716,10 @@ static int rtw89_hw_scan_update_probe_req(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
-static int rtw89_update_6ghz_rnr_chan(struct rtw89_dev *rtwdev,
-				      struct ieee80211_scan_ies *ies,
-				      struct cfg80211_scan_request *req,
-				      struct rtw89_mac_chinfo *ch_info)
+static int rtw89_update_6ghz_rnr_chan_ax(struct rtw89_dev *rtwdev,
+					 struct ieee80211_scan_ies *ies,
+					 struct cfg80211_scan_request *req,
+					 struct rtw89_mac_chinfo_ax *ch_info)
 {
 	struct rtw89_vif_link *rtwvif_link = rtwdev->scan_info.scanning_vif;
 	struct list_head *pkt_list = rtwdev->scan_info.pkt_list;
@@ -6713,7 +6791,7 @@ out:
 
 static void rtw89_pno_scan_add_chan_ax(struct rtw89_dev *rtwdev,
 				       int chan_type, int ssid_num,
-				       struct rtw89_mac_chinfo *ch_info)
+				       struct rtw89_mac_chinfo_ax *ch_info)
 {
 	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
 	struct rtw89_pktofld_info *info;
@@ -6761,9 +6839,9 @@ static void rtw89_pno_scan_add_chan_ax(struct rtw89_dev *rtwdev,
 	}
 }
 
-static void rtw89_hw_scan_add_chan(struct rtw89_dev *rtwdev, int chan_type,
-				   int ssid_num,
-				   struct rtw89_mac_chinfo *ch_info)
+static void rtw89_hw_scan_add_chan_ax(struct rtw89_dev *rtwdev, int chan_type,
+				      int ssid_num,
+				      struct rtw89_mac_chinfo_ax *ch_info)
 {
 	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
 	struct rtw89_vif_link *rtwvif_link = rtwdev->scan_info.scanning_vif;
@@ -6794,7 +6872,7 @@ static void rtw89_hw_scan_add_chan(struct rtw89_dev *rtwdev, int chan_type,
 		}
 	}
 
-	ret = rtw89_update_6ghz_rnr_chan(rtwdev, ies, req, ch_info);
+	ret = rtw89_update_6ghz_rnr_chan_ax(rtwdev, ies, req, ch_info);
 	if (ret)
 		rtw89_warn(rtwdev, "RNR fails: %d\n", ret);
 
@@ -6950,7 +7028,7 @@ int rtw89_pno_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
 {
 	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
 	struct cfg80211_sched_scan_request *nd_config = rtw_wow->nd_config;
-	struct rtw89_mac_chinfo	*ch_info, *tmp;
+	struct rtw89_mac_chinfo_ax *ch_info, *tmp;
 	struct ieee80211_channel *channel;
 	struct list_head chan_list;
 	int list_len;
@@ -6984,7 +7062,7 @@ int rtw89_pno_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
 		rtw89_pno_scan_add_chan_ax(rtwdev, type, nd_config->n_match_sets, ch_info);
 		list_add_tail(&ch_info->list, &chan_list);
 	}
-	ret = rtw89_fw_h2c_scan_list_offload(rtwdev, list_len, &chan_list);
+	ret = rtw89_fw_h2c_scan_list_offload_ax(rtwdev, list_len, &chan_list);
 
 out:
 	list_for_each_entry_safe(ch_info, tmp, &chan_list, list) {
@@ -6995,24 +7073,24 @@ out:
 	return ret;
 }
 
-int rtw89_hw_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
-				   struct rtw89_vif_link *rtwvif_link, bool connected)
+int rtw89_hw_scan_prep_chan_list_ax(struct rtw89_dev *rtwdev,
+				    struct rtw89_vif_link *rtwvif_link)
 {
+	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
 	struct rtw89_vif *rtwvif = rtwvif_link->rtwvif;
 	struct cfg80211_scan_request *req = rtwvif->scan_req;
-	struct rtw89_mac_chinfo	*ch_info, *tmp;
+	struct rtw89_mac_chinfo_ax *ch_info, *tmp;
 	struct ieee80211_channel *channel;
 	struct list_head chan_list;
 	bool random_seq = req->flags & NL80211_SCAN_FLAG_RANDOM_SN;
-	int list_len, off_chan_time = 0;
 	enum rtw89_chan_type type;
-	int ret = 0;
+	int off_chan_time = 0;
+	int ret;
 	u32 idx;
 
 	INIT_LIST_HEAD(&chan_list);
-	for (idx = rtwdev->scan_info.last_chan_idx, list_len = 0;
-	     idx < req->n_channels && list_len < RTW89_SCAN_LIST_LIMIT_AX;
-	     idx++, list_len++) {
+
+	for (idx = 0; idx < req->n_channels; idx++) {
 		channel = req->channels[idx];
 		ch_info = kzalloc(sizeof(*ch_info), GFP_KERNEL);
 		if (!ch_info) {
@@ -7039,9 +7117,9 @@ int rtw89_hw_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
 			type = RTW89_CHAN_DFS;
 		else
 			type = RTW89_CHAN_ACTIVE;
-		rtw89_hw_scan_add_chan(rtwdev, type, req->n_ssids, ch_info);
+		rtw89_hw_scan_add_chan_ax(rtwdev, type, req->n_ssids, ch_info);
 
-		if (connected &&
+		if (scan_info->connected &&
 		    off_chan_time + ch_info->period > RTW89_OFF_CHAN_TIME) {
 			tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
 			if (!tmp) {
@@ -7053,16 +7131,16 @@ int rtw89_hw_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
 			type = RTW89_CHAN_OPERATE;
 			tmp->period = req->duration_mandatory ?
 				      req->duration : RTW89_CHANNEL_TIME;
-			rtw89_hw_scan_add_chan(rtwdev, type, 0, tmp);
+			rtw89_hw_scan_add_chan_ax(rtwdev, type, 0, tmp);
 			list_add_tail(&tmp->list, &chan_list);
 			off_chan_time = 0;
-			list_len++;
 		}
 		list_add_tail(&ch_info->list, &chan_list);
 		off_chan_time += ch_info->period;
 	}
-	rtwdev->scan_info.last_chan_idx = idx;
-	ret = rtw89_fw_h2c_scan_list_offload(rtwdev, list_len, &chan_list);
+
+	list_splice_tail(&chan_list, &scan_info->chan_list);
+	return 0;
 
 out:
 	list_for_each_entry_safe(ch_info, tmp, &chan_list, list) {
@@ -7073,6 +7151,46 @@ out:
 	return ret;
 }
 
+void rtw89_hw_scan_free_chan_list_ax(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
+	struct rtw89_mac_chinfo_ax *ch_info, *tmp;
+
+	list_for_each_entry_safe(ch_info, tmp, &scan_info->chan_list, list) {
+		list_del(&ch_info->list);
+		kfree(ch_info);
+	}
+}
+
+int rtw89_hw_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
+				   struct rtw89_vif_link *rtwvif_link)
+{
+	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
+	struct rtw89_mac_chinfo_ax *ch_info, *tmp;
+	unsigned int list_len = 0;
+	struct list_head list;
+	int ret;
+
+	INIT_LIST_HEAD(&list);
+
+	list_for_each_entry_safe(ch_info, tmp, &scan_info->chan_list, list) {
+		list_move_tail(&ch_info->list, &list);
+
+		list_len++;
+		if (list_len == RTW89_SCAN_LIST_LIMIT_AX)
+			break;
+	}
+
+	ret = rtw89_fw_h2c_scan_list_offload_ax(rtwdev, list_len, &list);
+
+	list_for_each_entry_safe(ch_info, tmp, &list, list) {
+		list_del(&ch_info->list);
+		kfree(ch_info);
+	}
+
+	return ret;
+}
+
 int rtw89_pno_scan_add_chan_list_be(struct rtw89_dev *rtwdev,
 				    struct rtw89_vif_link *rtwvif_link)
 {
@@ -7126,25 +7244,24 @@ out:
 	return ret;
 }
 
-int rtw89_hw_scan_add_chan_list_be(struct rtw89_dev *rtwdev,
-				   struct rtw89_vif_link *rtwvif_link, bool connected)
+int rtw89_hw_scan_prep_chan_list_be(struct rtw89_dev *rtwdev,
+				    struct rtw89_vif_link *rtwvif_link)
 {
+	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
 	struct rtw89_vif *rtwvif = rtwvif_link->rtwvif;
 	struct cfg80211_scan_request *req = rtwvif->scan_req;
 	struct rtw89_mac_chinfo_be *ch_info, *tmp;
 	struct ieee80211_channel *channel;
 	struct list_head chan_list;
 	enum rtw89_chan_type type;
-	int list_len, ret;
 	bool random_seq;
+	int ret;
 	u32 idx;
 
 	random_seq = !!(req->flags & NL80211_SCAN_FLAG_RANDOM_SN);
 	INIT_LIST_HEAD(&chan_list);
 
-	for (idx = rtwdev->scan_info.last_chan_idx, list_len = 0;
-	     idx < req->n_channels && list_len < RTW89_SCAN_LIST_LIMIT_BE;
-	     idx++, list_len++) {
+	for (idx = 0; idx < req->n_channels; idx++) {
 		channel = req->channels[idx];
 		ch_info = kzalloc(sizeof(*ch_info), GFP_KERNEL);
 		if (!ch_info) {
@@ -7174,9 +7291,8 @@ int rtw89_hw_scan_add_chan_list_be(struct rtw89_dev *rtwdev,
 		list_add_tail(&ch_info->list, &chan_list);
 	}
 
-	rtwdev->scan_info.last_chan_idx = idx;
-	ret = rtw89_fw_h2c_scan_list_offload_be(rtwdev, list_len, &chan_list,
-						rtwvif_link);
+	list_splice_tail(&chan_list, &scan_info->chan_list);
+	return 0;
 
 out:
 	list_for_each_entry_safe(ch_info, tmp, &chan_list, list) {
@@ -7187,51 +7303,182 @@ out:
 	return ret;
 }
 
+void rtw89_hw_scan_free_chan_list_be(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
+	struct rtw89_mac_chinfo_be *ch_info, *tmp;
+
+	list_for_each_entry_safe(ch_info, tmp, &scan_info->chan_list, list) {
+		list_del(&ch_info->list);
+		kfree(ch_info);
+	}
+}
+
+int rtw89_hw_scan_add_chan_list_be(struct rtw89_dev *rtwdev,
+				   struct rtw89_vif_link *rtwvif_link)
+{
+	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
+	struct rtw89_mac_chinfo_be *ch_info, *tmp;
+	unsigned int list_len = 0;
+	struct list_head list;
+	int ret;
+
+	INIT_LIST_HEAD(&list);
+
+	list_for_each_entry_safe(ch_info, tmp, &scan_info->chan_list, list) {
+		list_move_tail(&ch_info->list, &list);
+
+		list_len++;
+		if (list_len == RTW89_SCAN_LIST_LIMIT_BE)
+			break;
+	}
+
+	ret = rtw89_fw_h2c_scan_list_offload_be(rtwdev, list_len, &list,
+						rtwvif_link);
+
+	list_for_each_entry_safe(ch_info, tmp, &list, list) {
+		list_del(&ch_info->list);
+		kfree(ch_info);
+	}
+
+	return ret;
+}
+
 static int rtw89_hw_scan_prehandle(struct rtw89_dev *rtwdev,
-				   struct rtw89_vif_link *rtwvif_link, bool connected)
+				   struct rtw89_vif_link *rtwvif_link,
+				   const u8 *mac_addr)
 {
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	int ret;
 
-	ret = rtw89_hw_scan_update_probe_req(rtwdev, rtwvif_link);
+	ret = rtw89_hw_scan_update_probe_req(rtwdev, rtwvif_link, mac_addr);
 	if (ret) {
 		rtw89_err(rtwdev, "Update probe request failed\n");
 		goto out;
 	}
-	ret = mac->add_chan_list(rtwdev, rtwvif_link, connected);
+	ret = mac->prep_chan_list(rtwdev, rtwvif_link);
 out:
 	return ret;
 }
 
-void rtw89_hw_scan_start(struct rtw89_dev *rtwdev,
-			 struct rtw89_vif_link *rtwvif_link,
-			 struct ieee80211_scan_request *scan_req)
+static void rtw89_hw_scan_update_link_beacon_noa(struct rtw89_dev *rtwdev,
+						 struct rtw89_vif_link *rtwvif_link,
+						 u16 tu)
+{
+	struct ieee80211_p2p_noa_desc noa_desc = {};
+	u64 tsf;
+	int ret;
+
+	ret = rtw89_mac_port_get_tsf(rtwdev, rtwvif_link, &tsf);
+	if (ret) {
+		rtw89_warn(rtwdev, "%s: failed to get tsf\n", __func__);
+		return;
+	}
+
+	noa_desc.start_time = cpu_to_le32(tsf);
+	noa_desc.interval = cpu_to_le32(ieee80211_tu_to_usec(tu));
+	noa_desc.duration = cpu_to_le32(ieee80211_tu_to_usec(tu));
+	noa_desc.count = 1;
+
+	rtw89_p2p_noa_renew(rtwvif_link);
+	rtw89_p2p_noa_append(rtwvif_link, &noa_desc);
+	rtw89_chip_h2c_update_beacon(rtwdev, rtwvif_link);
+}
+
+static void rtw89_hw_scan_update_beacon_noa(struct rtw89_dev *rtwdev,
+					    const struct cfg80211_scan_request *req)
+{
+	const struct rtw89_entity_mgnt *mgnt = &rtwdev->hal.entity_mgnt;
+	const struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	struct rtw89_mac_chinfo_ax *chinfo_ax;
+	struct rtw89_mac_chinfo_be *chinfo_be;
+	struct rtw89_vif_link *rtwvif_link;
+	struct list_head *pos, *tmp;
+	struct ieee80211_vif *vif;
+	struct rtw89_vif *rtwvif;
+	u16 tu = 0;
+
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
+	list_for_each_safe(pos, tmp, &scan_info->chan_list) {
+		switch (chip->chip_gen) {
+		case RTW89_CHIP_AX:
+			chinfo_ax = list_entry(pos, typeof(*chinfo_ax), list);
+			tu += chinfo_ax->period;
+			break;
+		case RTW89_CHIP_BE:
+			chinfo_be = list_entry(pos, typeof(*chinfo_be), list);
+			tu += chinfo_be->period;
+			break;
+		default:
+			rtw89_warn(rtwdev, "%s: invalid chip gen %d\n",
+				   __func__, chip->chip_gen);
+			return;
+		}
+	}
+
+	if (unlikely(tu == 0)) {
+		rtw89_debug(rtwdev, RTW89_DBG_HW_SCAN,
+			    "%s: cannot estimate needed TU\n", __func__);
+		return;
+	}
+
+	list_for_each_entry(rtwvif, &mgnt->active_list, mgnt_entry) {
+		unsigned int link_id;
+
+		vif = rtwvif_to_vif(rtwvif);
+		if (vif->type != NL80211_IFTYPE_AP || !vif->p2p)
+			continue;
+
+		rtw89_vif_for_each_link(rtwvif, rtwvif_link, link_id)
+			rtw89_hw_scan_update_link_beacon_noa(rtwdev, rtwvif_link, tu);
+	}
+}
+
+int rtw89_hw_scan_start(struct rtw89_dev *rtwdev,
+			struct rtw89_vif_link *rtwvif_link,
+			struct ieee80211_scan_request *scan_req)
 {
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	enum rtw89_entity_mode mode = rtw89_get_entity_mode(rtwdev);
 	struct cfg80211_scan_request *req = &scan_req->req;
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
 						       rtwvif_link->chanctx_idx);
 	struct rtw89_vif *rtwvif = rtwvif_link->rtwvif;
+	struct rtw89_chanctx_pause_parm pause_parm = {
+		.rsn = RTW89_CHANCTX_PAUSE_REASON_HW_SCAN,
+		.trigger = rtwvif_link,
+	};
 	u32 rx_fltr = rtwdev->hal.rx_fltr;
 	u8 mac_addr[ETH_ALEN];
 	u32 reg;
+	int ret;
 
 	/* clone op and keep it during scan */
 	rtwdev->scan_info.op_chan = *chan;
 
+	rtwdev->scan_info.connected = rtw89_is_any_vif_connected_or_connecting(rtwdev);
 	rtwdev->scan_info.scanning_vif = rtwvif_link;
-	rtwdev->scan_info.last_chan_idx = 0;
 	rtwdev->scan_info.abort = false;
 	rtwvif->scan_ies = &scan_req->ies;
 	rtwvif->scan_req = req;
-	ieee80211_stop_queues(rtwdev->hw);
-	rtw89_mac_port_cfg_rx_sync(rtwdev, rtwvif_link, false);
 
 	if (req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)
 		get_random_mask_addr(mac_addr, req->mac_addr,
 				     req->mac_addr_mask);
 	else
 		ether_addr_copy(mac_addr, rtwvif_link->mac_addr);
+
+	ret = rtw89_hw_scan_prehandle(rtwdev, rtwvif_link, mac_addr);
+	if (ret) {
+		rtw89_hw_scan_cleanup(rtwdev, rtwvif_link);
+		return ret;
+	}
+
+	ieee80211_stop_queues(rtwdev->hw);
+	rtw89_mac_port_cfg_rx_sync(rtwdev, rtwvif_link, false);
+
 	rtw89_core_scan_start(rtwdev, rtwvif_link, mac_addr, true);
 
 	rx_fltr &= ~B_AX_A_BCN_CHK_EN;
@@ -7241,7 +7488,12 @@ void rtw89_hw_scan_start(struct rtw89_dev *rtwdev,
 	reg = rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, rtwvif_link->mac_idx);
 	rtw89_write32_mask(rtwdev, reg, B_AX_RX_FLTR_CFG_MASK, rx_fltr);
 
-	rtw89_chanctx_pause(rtwdev, RTW89_CHANCTX_PAUSE_REASON_HW_SCAN);
+	rtw89_chanctx_pause(rtwdev, &pause_parm);
+
+	if (mode == RTW89_ENTITY_MODE_MCC)
+		rtw89_hw_scan_update_beacon_noa(rtwdev, req);
+
+	return 0;
 }
 
 struct rtw89_hw_scan_complete_cb_data {
@@ -7252,20 +7504,16 @@ struct rtw89_hw_scan_complete_cb_data {
 static int rtw89_hw_scan_complete_cb(struct rtw89_dev *rtwdev, void *data)
 {
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
-	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
 	struct rtw89_hw_scan_complete_cb_data *cb_data = data;
 	struct rtw89_vif_link *rtwvif_link = cb_data->rtwvif_link;
 	struct cfg80211_scan_info info = {
 		.aborted = cb_data->aborted,
 	};
-	struct rtw89_vif *rtwvif;
 	u32 reg;
 
 	if (!rtwvif_link)
 		return -EINVAL;
 
-	rtwvif = rtwvif_link->rtwvif;
-
 	reg = rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, rtwvif_link->mac_idx);
 	rtw89_write32_mask(rtwdev, reg, B_AX_RX_FLTR_CFG_MASK, rtwdev->hal.rx_fltr);
 
@@ -7275,12 +7523,7 @@ static int rtw89_hw_scan_complete_cb(struct rtw89_dev *rtwdev, void *data)
 	rtw89_mac_port_cfg_rx_sync(rtwdev, rtwvif_link, true);
 	rtw89_mac_enable_beacon_for_ap_vifs(rtwdev, true);
 
-	rtw89_release_pkt_list(rtwdev);
-	rtwvif->scan_req = NULL;
-	rtwvif->scan_ies = NULL;
-	scan_info->last_chan_idx = 0;
-	scan_info->scanning_vif = NULL;
-	scan_info->abort = false;
+	rtw89_hw_scan_cleanup(rtwdev, rtwvif_link);
 
 	return 0;
 }
@@ -7355,11 +7598,11 @@ int rtw89_hw_scan_offload(struct rtw89_dev *rtwdev,
 	if (!rtwvif_link)
 		return -EINVAL;
 
-	connected = rtw89_is_any_vif_connected_or_connecting(rtwdev);
+	connected = rtwdev->scan_info.connected;
 	opt.enable = enable;
 	opt.target_ch_mode = connected;
 	if (enable) {
-		ret = rtw89_hw_scan_prehandle(rtwdev, rtwvif_link, connected);
+		ret = mac->add_chan_list(rtwdev, rtwvif_link);
 		if (ret)
 			goto out;
 	}
@@ -8719,6 +8962,47 @@ int rtw89_fw_h2c_ap_info_refcount(struct rtw89_dev *rtwdev, bool en)
 	return 0;
 }
 
+int rtw89_fw_h2c_mlo_link_cfg(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link,
+			      bool enable)
+{
+	struct rtw89_wait_info *wait = &rtwdev->mlo.wait;
+	struct rtw89_h2c_mlo_link_cfg *h2c;
+	u8 mac_id = rtwvif_link->mac_id;
+	u32 len = sizeof(*h2c);
+	struct sk_buff *skb;
+	unsigned int cond;
+	int ret;
+
+	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
+	if (!skb) {
+		rtw89_err(rtwdev, "failed to alloc skb for mlo link cfg\n");
+		return -ENOMEM;
+	}
+
+	skb_put(skb, len);
+	h2c = (struct rtw89_h2c_mlo_link_cfg *)skb->data;
+
+	h2c->w0 = le32_encode_bits(mac_id, RTW89_H2C_MLO_LINK_CFG_W0_MACID) |
+		  le32_encode_bits(enable, RTW89_H2C_MLO_LINK_CFG_W0_OPTION);
+
+	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
+			      H2C_CAT_MAC,
+			      H2C_CL_MLO,
+			      H2C_FUNC_MLO_LINK_CFG, 0, 0,
+			      len);
+
+	cond = RTW89_MLO_WAIT_COND(mac_id, H2C_FUNC_MLO_LINK_CFG);
+
+	ret = rtw89_h2c_tx_and_wait(rtwdev, skb, wait, cond);
+	if (ret) {
+		rtw89_err(rtwdev, "mlo link cfg (%s link id %u) failed: %d\n",
+			  str_enable_disable(enable), rtwvif_link->link_id, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static bool __fw_txpwr_entry_zero_ext(const void *ext_ptr, u8 ext_len)
 {
 	static const u8 zeros[U8_MAX] = {};
@@ -9106,6 +9390,26 @@ void rtw89_fw_load_tx_shape_lmt_ru(struct rtw89_tx_shape_lmt_ru_data *data)
 	}
 }
 
+static bool rtw89_fw_has_da_txpwr_table(struct rtw89_dev *rtwdev,
+					const struct rtw89_rfe_parms *parms)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+
+	if (chip->support_bands & BIT(NL80211_BAND_2GHZ) &&
+	    !(parms->rule_da_2ghz.lmt && parms->rule_da_2ghz.lmt_ru))
+		return false;
+
+	if (chip->support_bands & BIT(NL80211_BAND_5GHZ) &&
+	    !(parms->rule_da_5ghz.lmt && parms->rule_da_5ghz.lmt_ru))
+		return false;
+
+	if (chip->support_bands & BIT(NL80211_BAND_6GHZ) &&
+	    !(parms->rule_da_6ghz.lmt && parms->rule_da_6ghz.lmt_ru))
+		return false;
+
+	return true;
+}
+
 const struct rtw89_rfe_parms *
 rtw89_load_rfe_data_from_fw(struct rtw89_dev *rtwdev,
 			    const struct rtw89_rfe_parms *init)
@@ -9142,6 +9446,21 @@ rtw89_load_rfe_data_from_fw(struct rtw89_dev *rtwdev,
 		parms->rule_6ghz.lmt = &rfe_data->lmt_6ghz.v;
 	}
 
+	if (rtw89_txpwr_conf_valid(&rfe_data->da_lmt_2ghz.conf)) {
+		rtw89_fw_load_txpwr_lmt_2ghz(&rfe_data->da_lmt_2ghz);
+		parms->rule_da_2ghz.lmt = &rfe_data->da_lmt_2ghz.v;
+	}
+
+	if (rtw89_txpwr_conf_valid(&rfe_data->da_lmt_5ghz.conf)) {
+		rtw89_fw_load_txpwr_lmt_5ghz(&rfe_data->da_lmt_5ghz);
+		parms->rule_da_5ghz.lmt = &rfe_data->da_lmt_5ghz.v;
+	}
+
+	if (rtw89_txpwr_conf_valid(&rfe_data->da_lmt_6ghz.conf)) {
+		rtw89_fw_load_txpwr_lmt_6ghz(&rfe_data->da_lmt_6ghz);
+		parms->rule_da_6ghz.lmt = &rfe_data->da_lmt_6ghz.v;
+	}
+
 	if (rtw89_txpwr_conf_valid(&rfe_data->lmt_ru_2ghz.conf)) {
 		rtw89_fw_load_txpwr_lmt_ru_2ghz(&rfe_data->lmt_ru_2ghz);
 		parms->rule_2ghz.lmt_ru = &rfe_data->lmt_ru_2ghz.v;
@@ -9157,6 +9476,21 @@ rtw89_load_rfe_data_from_fw(struct rtw89_dev *rtwdev,
 		parms->rule_6ghz.lmt_ru = &rfe_data->lmt_ru_6ghz.v;
 	}
 
+	if (rtw89_txpwr_conf_valid(&rfe_data->da_lmt_ru_2ghz.conf)) {
+		rtw89_fw_load_txpwr_lmt_ru_2ghz(&rfe_data->da_lmt_ru_2ghz);
+		parms->rule_da_2ghz.lmt_ru = &rfe_data->da_lmt_ru_2ghz.v;
+	}
+
+	if (rtw89_txpwr_conf_valid(&rfe_data->da_lmt_ru_5ghz.conf)) {
+		rtw89_fw_load_txpwr_lmt_ru_5ghz(&rfe_data->da_lmt_ru_5ghz);
+		parms->rule_da_5ghz.lmt_ru = &rfe_data->da_lmt_ru_5ghz.v;
+	}
+
+	if (rtw89_txpwr_conf_valid(&rfe_data->da_lmt_ru_6ghz.conf)) {
+		rtw89_fw_load_txpwr_lmt_ru_6ghz(&rfe_data->da_lmt_ru_6ghz);
+		parms->rule_da_6ghz.lmt_ru = &rfe_data->da_lmt_ru_6ghz.v;
+	}
+
 	if (rtw89_txpwr_conf_valid(&rfe_data->tx_shape_lmt.conf)) {
 		rtw89_fw_load_tx_shape_lmt(&rfe_data->tx_shape_lmt);
 		parms->tx_shape.lmt = &rfe_data->tx_shape_lmt.v;
@@ -9167,5 +9501,7 @@ rtw89_load_rfe_data_from_fw(struct rtw89_dev *rtwdev,
 		parms->tx_shape.lmt_ru = &rfe_data->tx_shape_lmt_ru.v;
 	}
 
+	parms->has_da = rtw89_fw_has_da_txpwr_table(rtwdev, parms);
+
 	return parms;
 }
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 55255b48bdb7..0fcc824e41be 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -199,6 +199,7 @@ enum rtw89_fw_log_comp {
 	RTW89_FW_LOG_COMP_TWT,
 	RTW89_FW_LOG_COMP_RF,
 	RTW89_FW_LOG_COMP_MCC = 20,
+	RTW89_FW_LOG_COMP_MLO = 26,
 	RTW89_FW_LOG_COMP_SCAN = 28,
 };
 
@@ -333,9 +334,9 @@ struct rtw89_fw_macid_pause_sleep_grp {
 #define RTW89_SCAN_LIST_LIMIT_AX RTW89_SCAN_LIST_LIMIT(RTW89_MAC_CHINFO_SIZE)
 #define RTW89_SCAN_LIST_LIMIT_BE RTW89_SCAN_LIST_LIMIT(RTW89_MAC_CHINFO_SIZE_BE)
 
-#define RTW89_BCN_LOSS_CNT 10
+#define RTW89_BCN_LOSS_CNT 60
 
-struct rtw89_mac_chinfo {
+struct rtw89_mac_chinfo_ax {
 	u8 period;
 	u8 dwell_time;
 	u8 central_ch;
@@ -1636,6 +1637,8 @@ struct rtw89_h2c_join_v1 {
 #define RTW89_H2C_JOININFO_W1_IS_MLD BIT(3)
 #define RTW89_H2C_JOININFO_W1_MAIN_MACID GENMASK(11, 4)
 #define RTW89_H2C_JOININFO_W1_MLO_MODE BIT(12)
+#define RTW89_H2C_JOININFO_MLO_MODE_MLMR 0
+#define RTW89_H2C_JOININFO_MLO_MODE_MLSR 1
 #define RTW89_H2C_JOININFO_W1_EMLSR_CAB BIT(13)
 #define RTW89_H2C_JOININFO_W1_NSTR_EN BIT(14)
 #define RTW89_H2C_JOININFO_W1_INIT_PWR_STATE BIT(15)
@@ -2863,6 +2866,13 @@ struct rtw89_h2c_fwips {
 #define RTW89_H2C_FW_IPS_W0_MACID GENMASK(7, 0)
 #define RTW89_H2C_FW_IPS_W0_ENABLE BIT(8)
 
+struct rtw89_h2c_mlo_link_cfg {
+	__le32 w0;
+};
+
+#define RTW89_H2C_MLO_LINK_CFG_W0_MACID GENMASK(15, 0)
+#define RTW89_H2C_MLO_LINK_CFG_W0_OPTION GENMASK(19, 16)
+
 static inline void RTW89_SET_FWCMD_P2P_MACID(void *cmd, u32 val)
 {
 	le32p_replace_bits((__le32 *)cmd, val, GENMASK(7, 0));
@@ -3562,6 +3572,7 @@ struct rtw89_c2h_done_ack {
 #define RTW89_C2H_DONE_ACK_W2_CLASS GENMASK(7, 2)
 #define RTW89_C2H_DONE_ACK_W2_FUNC GENMASK(15, 8)
 #define RTW89_C2H_DONE_ACK_W2_H2C_RETURN GENMASK(23, 16)
+#define	RTW89_C2H_SCAN_DONE_ACK_RETURN GENMASK(5, 0)
 #define RTW89_C2H_DONE_ACK_W2_H2C_SEQ GENMASK(31, 24)
 
 #define RTW89_GET_MAC_C2H_REV_ACK_CAT(c2h) \
@@ -3620,6 +3631,19 @@ struct rtw89_c2h_ra_rpt {
 #define RTW89_C2H_RA_RPT_W3_MD_SEL_B2 BIT(15)
 #define RTW89_C2H_RA_RPT_W3_BW_B2 BIT(16)
 
+struct rtw89_c2h_fw_scan_rpt {
+	struct rtw89_c2h_hdr hdr;
+	u8 phy_idx;
+	u8 band;
+	u8 center_ch;
+	u8 ofdm_pd_idx; /* in unit of 2 dBm */
+#define PD_LOWER_BOUND_BASE 102
+	s8 cck_pd_idx;
+	u8 rsvd0;
+	u8 rsvd1;
+	u8 rsvd2;
+} __packed;
+
 /* For WiFi 6 chips:
  *   VHT, HE, HT-old: [6:4]: NSS, [3:0]: MCS
  *   HT-new: [6:5]: NA, [4:0]: MCS
@@ -3717,6 +3741,25 @@ static_assert(sizeof(struct rtw89_mac_mcc_tsf_rpt) <= RTW89_COMPLETION_BUF_SIZE)
 #define RTW89_GET_MAC_C2H_MCC_STATUS_RPT_TSF_HIGH(c2h) \
 	le32_get_bits(*((const __le32 *)(c2h) + 4), GENMASK(31, 0))
 
+struct rtw89_c2h_mlo_link_cfg_rpt {
+	struct rtw89_c2h_hdr hdr;
+	__le32 w2;
+} __packed;
+
+#define RTW89_C2H_MLO_LINK_CFG_RPT_W2_MACID GENMASK(15, 0)
+#define RTW89_C2H_MLO_LINK_CFG_RPT_W2_STATUS GENMASK(19, 16)
+
+enum rtw89_c2h_mlo_link_status {
+	RTW89_C2H_MLO_LINK_CFG_IDLE = 0,
+	RTW89_C2H_MLO_LINK_CFG_DONE = 1,
+	RTW89_C2H_MLO_LINK_CFG_ISSUE_NULL_FAIL = 2,
+	RTW89_C2H_MLO_LINK_CFG_TX_NULL_FAIL = 3,
+	RTW89_C2H_MLO_LINK_CFG_ROLE_NOT_EXIST = 4,
+	RTW89_C2H_MLO_LINK_CFG_NULL_1_TIMEOUT = 5,
+	RTW89_C2H_MLO_LINK_CFG_NULL_0_TIMEOUT = 6,
+	RTW89_C2H_MLO_LINK_CFG_RUNNING = 0xff,
+};
+
 struct rtw89_mac_mrc_tsf_rpt {
 	unsigned int num;
 	u64 tsfs[RTW89_MAC_MRC_MAX_REQ_TSF_NUM];
@@ -3813,7 +3856,8 @@ struct rtw89_h2c_bcnfltr {
 #define RTW89_H2C_BCNFLTR_W0_MON_BCN BIT(1)
 #define RTW89_H2C_BCNFLTR_W0_MON_EN BIT(2)
 #define RTW89_H2C_BCNFLTR_W0_MODE GENMASK(4, 3)
-#define RTW89_H2C_BCNFLTR_W0_BCN_LOSS_CNT GENMASK(11, 8)
+#define RTW89_H2C_BCNFLTR_W0_BCN_LOSS_CNT_H3 GENMASK(7, 5)
+#define RTW89_H2C_BCNFLTR_W0_BCN_LOSS_CNT_L4 GENMASK(11, 8)
 #define RTW89_H2C_BCNFLTR_W0_RSSI_HYST GENMASK(15, 12)
 #define RTW89_H2C_BCNFLTR_W0_RSSI_THRESHOLD GENMASK(23, 16)
 #define RTW89_H2C_BCNFLTR_W0_MAC_ID GENMASK(31, 24)
@@ -3891,6 +3935,12 @@ enum rtw89_fw_element_id {
 	RTW89_FW_ELEMENT_ID_TXPWR_TRK = 18,
 	RTW89_FW_ELEMENT_ID_RFKLOG_FMT = 19,
 	RTW89_FW_ELEMENT_ID_REGD = 20,
+	RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_2GHZ = 21,
+	RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_5GHZ = 22,
+	RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_6GHZ = 23,
+	RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_RU_2GHZ = 24,
+	RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_RU_5GHZ = 25,
+	RTW89_FW_ELEMENT_ID_TXPWR_DA_LMT_RU_6GHZ = 26,
 
 	RTW89_FW_ELEMENT_ID_NUM,
 };
@@ -4229,6 +4279,26 @@ enum rtw89_mcc_h2c_func {
 #define RTW89_MCC_WAIT_COND(group, func) \
 	((group) * NUM_OF_RTW89_MCC_H2C_FUNC + (func))
 
+/* CLASS 20 - MLO */
+#define H2C_CL_MLO                     0x14
+enum rtw89_mlo_h2c_func {
+	H2C_FUNC_MLO_TBL_CFG		= 0x0,
+	H2C_FUNC_MLO_STA_CFG		= 0x1,
+	H2C_FUNC_MLO_TTLM		= 0x2,
+	H2C_FUNC_MLO_DM_CFG		= 0x3,
+	H2C_FUNC_MLO_EMLSR_STA_CFG	= 0x4,
+	H2C_FUNC_MLO_MCMLO_RELINK_DROP	= 0x5,
+	H2C_FUNC_MLO_MCMLO_SN_SYNC	= 0x6,
+	H2C_FUNC_MLO_RELINK		= 0x7,
+	H2C_FUNC_MLO_LINK_CFG		= 0x8,
+	H2C_FUNC_MLO_DM_DBG		= 0x9,
+
+	NUM_OF_RTW89_MLO_H2C_FUNC,
+};
+
+#define RTW89_MLO_WAIT_COND(macid, func) \
+	((macid) * NUM_OF_RTW89_MLO_H2C_FUNC + (func))
+
 /* CLASS 24 - MRC */
 #define H2C_CL_MRC			0x18
 enum rtw89_mrc_h2c_func {
@@ -4715,9 +4785,9 @@ int rtw89_fw_msg_reg(struct rtw89_dev *rtwdev,
 		     struct rtw89_mac_c2h_info *c2h_info);
 int rtw89_fw_h2c_fw_log(struct rtw89_dev *rtwdev, bool enable);
 void rtw89_fw_st_dbg_dump(struct rtw89_dev *rtwdev);
-void rtw89_hw_scan_start(struct rtw89_dev *rtwdev,
-			 struct rtw89_vif_link *rtwvif_link,
-			 struct ieee80211_scan_request *scan_req);
+int rtw89_hw_scan_start(struct rtw89_dev *rtwdev,
+			struct rtw89_vif_link *rtwvif_link,
+			struct ieee80211_scan_request *scan_req);
 void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev,
 			    struct rtw89_vif_link *rtwvif_link,
 			    bool aborted);
@@ -4726,12 +4796,18 @@ int rtw89_hw_scan_offload(struct rtw89_dev *rtwdev,
 			  bool enable);
 void rtw89_hw_scan_abort(struct rtw89_dev *rtwdev,
 			 struct rtw89_vif_link *rtwvif_link);
+int rtw89_hw_scan_prep_chan_list_ax(struct rtw89_dev *rtwdev,
+				    struct rtw89_vif_link *rtwvif_link);
+void rtw89_hw_scan_free_chan_list_ax(struct rtw89_dev *rtwdev);
 int rtw89_hw_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
-				   struct rtw89_vif_link *rtwvif_link, bool connected);
+				   struct rtw89_vif_link *rtwvif_link);
 int rtw89_pno_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
 				    struct rtw89_vif_link *rtwvif_link);
+int rtw89_hw_scan_prep_chan_list_be(struct rtw89_dev *rtwdev,
+				    struct rtw89_vif_link *rtwvif_link);
+void rtw89_hw_scan_free_chan_list_be(struct rtw89_dev *rtwdev);
 int rtw89_hw_scan_add_chan_list_be(struct rtw89_dev *rtwdev,
-				   struct rtw89_vif_link *rtwvif_link, bool connected);
+				   struct rtw89_vif_link *rtwvif_link);
 int rtw89_pno_scan_add_chan_list_be(struct rtw89_dev *rtwdev,
 				    struct rtw89_vif_link *rtwvif_link);
 int rtw89_fw_h2c_trigger_cpu_exception(struct rtw89_dev *rtwdev);
@@ -4800,6 +4876,8 @@ int rtw89_fw_h2c_mrc_sync(struct rtw89_dev *rtwdev,
 int rtw89_fw_h2c_mrc_upd_duration(struct rtw89_dev *rtwdev,
 				  const struct rtw89_fw_mrc_upd_duration_arg *arg);
 int rtw89_fw_h2c_ap_info_refcount(struct rtw89_dev *rtwdev, bool en);
+int rtw89_fw_h2c_mlo_link_cfg(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link,
+			      bool enable);
 
 static inline void rtw89_fw_h2c_init_ba_cam(struct rtw89_dev *rtwdev)
 {
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index b4841f948ec1..9f0e30e75009 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -4631,11 +4631,17 @@ static void rtw89_mac_port_tsf_sync_rand(struct rtw89_dev *rtwdev,
 	if (rtwvif_link->net_type != RTW89_NET_TYPE_AP_MODE || rtwvif_link == rtwvif_src)
 		return;
 
+	if (rtwvif_link->rand_tsf_done)
+		goto out;
+
 	/* adjust offset randomly to avoid beacon conflict */
 	offset = offset - offset / 4 + get_random_u32() % (offset / 2);
 	rtw89_mac_port_tsf_sync(rtwdev, rtwvif_link, rtwvif_src,
 				(*n_offset) * offset);
 
+	rtwvif_link->rand_tsf_done = true;
+
+out:
 	(*n_offset)++;
 }
 
@@ -4866,6 +4872,8 @@ void rtw89_mac_set_he_tb(struct rtw89_dev *rtwdev,
 void rtw89_mac_stop_ap(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link)
 {
 	rtw89_mac_port_cfg_func_sw(rtwdev, rtwvif_link);
+
+	rtwvif_link->rand_tsf_done = false;
 }
 
 int rtw89_mac_add_vif(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link)
@@ -4899,11 +4907,11 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 	struct rtw89_vif_link *rtwvif_link = rtwdev->scan_info.scanning_vif;
 	struct rtw89_vif *rtwvif;
 	struct rtw89_chan new;
-	u32 last_chan = rtwdev->scan_info.last_chan_idx, report_tsf;
 	u16 actual_period, expect_period;
 	u8 reason, status, tx_fail, band;
 	u8 mac_idx, sw_def, fw_def;
 	u8 ver = U8_MAX;
+	u32 report_tsf;
 	u16 chan;
 	int ret;
 
@@ -4962,7 +4970,7 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 			return;
 
 		if (rtwvif_link && rtwvif->scan_req &&
-		    last_chan < rtwvif->scan_req->n_channels) {
+		    !list_empty(&rtwdev->scan_info.chan_list)) {
 			ret = rtw89_hw_scan_offload(rtwdev, rtwvif_link, true);
 			if (ret) {
 				rtw89_hw_scan_abort(rtwdev, rtwvif_link);
@@ -5017,7 +5025,8 @@ rtw89_mac_bcn_fltr_rpt(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_l
 
 	switch (type) {
 	case RTW89_BCN_FLTR_BEACON_LOSS:
-		if (!rtwdev->scanning && !rtwvif->offchan)
+		if (!rtwdev->scanning && !rtwvif->offchan &&
+		    !rtwvif_link->noa_once.in_duration)
 			ieee80211_connection_loss(vif);
 		else
 			rtw89_fw_h2c_set_bcn_fltr_cfg(rtwdev, rtwvif_link, true);
@@ -5110,12 +5119,14 @@ rtw89_mac_c2h_done_ack(struct rtw89_dev *rtwdev, struct sk_buff *skb_c2h, u32 le
 			return;
 		case H2C_FUNC_ADD_SCANOFLD_CH:
 			cond = RTW89_SCANOFLD_WAIT_COND_ADD_CH;
+			h2c_return &= RTW89_C2H_SCAN_DONE_ACK_RETURN;
 			break;
 		case H2C_FUNC_SCANOFLD:
 			cond = RTW89_SCANOFLD_WAIT_COND_START;
 			break;
 		case H2C_FUNC_SCANOFLD_BE:
 			cond = RTW89_SCANOFLD_BE_WAIT_COND_START;
+			h2c_return &= RTW89_C2H_SCAN_DONE_ACK_RETURN;
 			break;
 		}
 
@@ -5399,6 +5410,27 @@ rtw89_mac_c2h_wow_aoac_rpt(struct rtw89_dev *rtwdev, struct sk_buff *skb, u32 le
 }
 
 static void
+rtw89_mac_c2h_mlo_link_cfg_stat(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
+{
+	const struct rtw89_c2h_mlo_link_cfg_rpt *c2h_rpt;
+	struct rtw89_wait_info *wait = &rtwdev->mlo.wait;
+	struct rtw89_completion_data data = {};
+	unsigned int cond;
+	u16 mac_id;
+	u8 status;
+
+	c2h_rpt = (const struct rtw89_c2h_mlo_link_cfg_rpt *)c2h->data;
+
+	mac_id = le32_get_bits(c2h_rpt->w2, RTW89_C2H_MLO_LINK_CFG_RPT_W2_MACID);
+	status = le32_get_bits(c2h_rpt->w2, RTW89_C2H_MLO_LINK_CFG_RPT_W2_STATUS);
+
+	data.err = status == RTW89_C2H_MLO_LINK_CFG_ROLE_NOT_EXIST ||
+		   status == RTW89_C2H_MLO_LINK_CFG_RUNNING;
+	cond = RTW89_MLO_WAIT_COND(mac_id, H2C_FUNC_MLO_LINK_CFG);
+	rtw89_complete_cond(wait, cond, &data);
+}
+
+static void
 rtw89_mac_c2h_mrc_status_rpt(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
 {
 	struct rtw89_wait_info *wait = &rtwdev->mcc.wait;
@@ -5553,6 +5585,18 @@ void (* const rtw89_mac_c2h_mcc_handler[])(struct rtw89_dev *rtwdev,
 };
 
 static
+void (* const rtw89_mac_c2h_mlo_handler[])(struct rtw89_dev *rtwdev,
+					   struct sk_buff *c2h, u32 len) = {
+	[RTW89_MAC_C2H_FUNC_MLO_GET_TBL] = NULL,
+	[RTW89_MAC_C2H_FUNC_MLO_EMLSR_TRANS_DONE] = NULL,
+	[RTW89_MAC_C2H_FUNC_MLO_EMLSR_STA_CFG_DONE] = NULL,
+	[RTW89_MAC_C2H_FUNC_MCMLO_RELINK_RPT] = NULL,
+	[RTW89_MAC_C2H_FUNC_MCMLO_SN_SYNC_RPT] = NULL,
+	[RTW89_MAC_C2H_FUNC_MLO_LINK_CFG_STAT] = rtw89_mac_c2h_mlo_link_cfg_stat,
+	[RTW89_MAC_C2H_FUNC_MLO_DM_DBG_DUMP] = NULL,
+};
+
+static
 void (* const rtw89_mac_c2h_mrc_handler[])(struct rtw89_dev *rtwdev,
 					   struct sk_buff *c2h, u32 len) = {
 	[RTW89_MAC_C2H_FUNC_MRC_TSF_RPT] = rtw89_mac_c2h_mrc_tsf_rpt,
@@ -5621,6 +5665,8 @@ bool rtw89_mac_c2h_chk_atomic(struct rtw89_dev *rtwdev, struct sk_buff *c2h,
 		}
 	case RTW89_MAC_C2H_CLASS_MCC:
 		return true;
+	case RTW89_MAC_C2H_CLASS_MLO:
+		return true;
 	case RTW89_MAC_C2H_CLASS_MRC:
 		return true;
 	case RTW89_MAC_C2H_CLASS_WOW:
@@ -5654,6 +5700,10 @@ void rtw89_mac_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 		if (func < NUM_OF_RTW89_MAC_C2H_FUNC_MCC)
 			handler = rtw89_mac_c2h_mcc_handler[func];
 		break;
+	case RTW89_MAC_C2H_CLASS_MLO:
+		if (func < NUM_OF_RTW89_MAC_C2H_FUNC_MLO)
+			handler = rtw89_mac_c2h_mlo_handler[func];
+		break;
 	case RTW89_MAC_C2H_CLASS_MRC:
 		if (func < NUM_OF_RTW89_MAC_C2H_FUNC_MRC)
 			handler = rtw89_mac_c2h_mrc_handler[func];
@@ -6889,6 +6939,8 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_ax = {
 
 	.is_txq_empty = mac_is_txq_empty_ax,
 
+	.prep_chan_list = rtw89_hw_scan_prep_chan_list_ax,
+	.free_chan_list = rtw89_hw_scan_free_chan_list_ax,
 	.add_chan_list = rtw89_hw_scan_add_chan_list_ax,
 	.add_chan_list_pno = rtw89_pno_scan_add_chan_list_ax,
 	.scan_offload = rtw89_fw_h2c_scan_offload_ax,
diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index fd7935d24501..8013c852d5be 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -370,6 +370,7 @@ enum rtw89_mac_mem_sel {
 	RTW89_MAC_MEM_TXD_FIFO_0_V1,
 	RTW89_MAC_MEM_TXD_FIFO_1_V1,
 	RTW89_MAC_MEM_WD_PAGE,
+	RTW89_MAC_MEM_MLD_TBL,
 
 	/* keep last */
 	RTW89_MAC_MEM_NUM,
@@ -427,6 +428,18 @@ enum rtw89_mac_c2h_mcc_func {
 	NUM_OF_RTW89_MAC_C2H_FUNC_MCC,
 };
 
+enum rtw89_mac_c2h_mlo_func {
+	RTW89_MAC_C2H_FUNC_MLO_GET_TBL			= 0x0,
+	RTW89_MAC_C2H_FUNC_MLO_EMLSR_TRANS_DONE		= 0x1,
+	RTW89_MAC_C2H_FUNC_MLO_EMLSR_STA_CFG_DONE	= 0x2,
+	RTW89_MAC_C2H_FUNC_MCMLO_RELINK_RPT		= 0x3,
+	RTW89_MAC_C2H_FUNC_MCMLO_SN_SYNC_RPT		= 0x4,
+	RTW89_MAC_C2H_FUNC_MLO_LINK_CFG_STAT		= 0x5,
+	RTW89_MAC_C2H_FUNC_MLO_DM_DBG_DUMP		= 0x6,
+
+	NUM_OF_RTW89_MAC_C2H_FUNC_MLO,
+};
+
 enum rtw89_mac_c2h_mrc_func {
 	RTW89_MAC_C2H_FUNC_MRC_TSF_RPT = 0,
 	RTW89_MAC_C2H_FUNC_MRC_STATUS_RPT = 1,
@@ -453,6 +466,7 @@ enum rtw89_mac_c2h_class {
 	RTW89_MAC_C2H_CLASS_WOW = 0x3,
 	RTW89_MAC_C2H_CLASS_MCC = 0x4,
 	RTW89_MAC_C2H_CLASS_FWDBG = 0x5,
+	RTW89_MAC_C2H_CLASS_MLO = 0xc,
 	RTW89_MAC_C2H_CLASS_MRC = 0xe,
 	RTW89_MAC_C2H_CLASS_AP = 0x18,
 	RTW89_MAC_C2H_CLASS_MAX,
@@ -1031,8 +1045,11 @@ struct rtw89_mac_gen_def {
 
 	bool (*is_txq_empty)(struct rtw89_dev *rtwdev);
 
+	int (*prep_chan_list)(struct rtw89_dev *rtwdev,
+			      struct rtw89_vif_link *rtwvif_link);
+	void (*free_chan_list)(struct rtw89_dev *rtwdev);
 	int (*add_chan_list)(struct rtw89_dev *rtwdev,
-			     struct rtw89_vif_link *rtwvif_link, bool connected);
+			     struct rtw89_vif_link *rtwvif_link);
 	int (*add_chan_list_pno)(struct rtw89_dev *rtwdev,
 				 struct rtw89_vif_link *rtwvif_link);
 	int (*scan_offload)(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 4fded07d0bee..a47971003bd4 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -114,11 +114,14 @@ static int __rtw89_ops_add_iface_link(struct rtw89_dev *rtwdev,
 	wiphy_work_init(&rtwvif_link->update_beacon_work, rtw89_core_update_beacon_work);
 	INIT_LIST_HEAD(&rtwvif_link->general_pkt_list);
 
+	rtw89_p2p_noa_once_init(rtwvif_link);
+
 	rtwvif_link->hit_rule = 0;
 	rtwvif_link->bcn_hit_cond = 0;
 	rtwvif_link->chanctx_assigned = false;
 	rtwvif_link->chanctx_idx = RTW89_CHANCTX_0;
 	rtwvif_link->reg_6ghz_power = RTW89_REG_6GHZ_POWER_DFLT;
+	rtwvif_link->rand_tsf_done = false;
 
 	rcu_read_lock();
 
@@ -142,6 +145,8 @@ static void __rtw89_ops_remove_iface_link(struct rtw89_dev *rtwdev,
 
 	wiphy_work_cancel(rtwdev->hw->wiphy, &rtwvif_link->update_beacon_work);
 
+	rtw89_p2p_noa_once_deinit(rtwvif_link);
+
 	rtw89_leave_ps_mode(rtwdev);
 
 	rtw89_btc_ntfy_role_info(rtwdev, rtwvif_link, NULL, BTC_ROLE_STOP);
@@ -186,6 +191,7 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw,
 	if (!rtw89_rtwvif_in_list(rtwdev, rtwvif)) {
 		list_add_tail(&rtwvif->list, &rtwdev->rtwvifs_list);
 		INIT_LIST_HEAD(&rtwvif->mgnt_entry);
+		INIT_LIST_HEAD(&rtwvif->dlink_pool);
 	}
 
 	ether_addr_copy(rtwvif->mac_addr, vif->addr);
@@ -479,6 +485,8 @@ static int __rtw89_ops_sta_add(struct rtw89_dev *rtwdev,
 	int i;
 
 	if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls) {
+		rtwvif->mlo_mode = RTW89_MLO_MODE_MLSR;
+
 		/* for station mode, assign the mac_id from itself */
 		macid = rtw89_vif_get_main_macid(rtwvif);
 	} else {
@@ -494,6 +502,8 @@ static int __rtw89_ops_sta_add(struct rtw89_dev *rtwdev,
 	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
 		rtw89_core_txq_init(rtwdev, sta->txq[i]);
 
+	INIT_LIST_HEAD(&rtwsta->dlink_pool);
+
 	skb_queue_head_init(&rtwsta->roc_queue);
 	bitmap_zero(rtwsta->pairwise_sec_cam_map, RTW89_MAX_SEC_CAM_NUM);
 
@@ -1018,7 +1028,7 @@ static void rtw89_ops_sta_statistics(struct ieee80211_hw *hw,
 	struct rtw89_sta *rtwsta = sta_to_rtwsta(sta);
 	struct rtw89_sta_link *rtwsta_link;
 
-	rtwsta_link = rtw89_sta_get_link_inst(rtwsta, 0);
+	rtwsta_link = rtw89_get_designated_link(rtwsta);
 	if (unlikely(!rtwsta_link))
 		return;
 
@@ -1153,12 +1163,14 @@ static void rtw89_ops_sw_scan_start(struct ieee80211_hw *hw,
 
 	lockdep_assert_wiphy(hw->wiphy);
 
-	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
+	rtwvif_link = rtw89_get_designated_link(rtwvif);
 	if (unlikely(!rtwvif_link)) {
-		rtw89_err(rtwdev, "sw scan start: find no link on HW-0\n");
+		rtw89_err(rtwdev, "sw scan start: find no designated link\n");
 		return;
 	}
 
+	rtw89_leave_lps(rtwdev);
+
 	rtw89_core_scan_start(rtwdev, rtwvif_link, mac_addr, false);
 }
 
@@ -1171,9 +1183,9 @@ static void rtw89_ops_sw_scan_complete(struct ieee80211_hw *hw,
 
 	lockdep_assert_wiphy(hw->wiphy);
 
-	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
+	rtwvif_link = rtw89_get_designated_link(rtwvif);
 	if (unlikely(!rtwvif_link)) {
-		rtw89_err(rtwdev, "sw scan complete: find no link on HW-0\n");
+		rtw89_err(rtwdev, "sw scan complete: find no designated link\n");
 		return;
 	}
 
@@ -1205,13 +1217,19 @@ static int rtw89_ops_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	if (rtwdev->scanning || rtwvif->offchan)
 		return -EBUSY;
 
-	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
+	rtwvif_link = rtw89_get_designated_link(rtwvif);
 	if (unlikely(!rtwvif_link)) {
-		rtw89_err(rtwdev, "hw scan: find no link on HW-0\n");
+		rtw89_err(rtwdev, "hw scan: find no designated link\n");
 		return -ENOLINK;
 	}
 
-	rtw89_hw_scan_start(rtwdev, rtwvif_link, req);
+	rtw89_leave_lps(rtwdev);
+	rtw89_leave_ips_by_hwflags(rtwdev);
+
+	ret = rtw89_hw_scan_start(rtwdev, rtwvif_link, req);
+	if (ret)
+		return ret;
+
 	ret = rtw89_hw_scan_offload(rtwdev, rtwvif_link, true);
 	if (ret) {
 		rtw89_hw_scan_abort(rtwdev, rtwvif_link);
@@ -1236,9 +1254,9 @@ static void rtw89_ops_cancel_hw_scan(struct ieee80211_hw *hw,
 	if (!rtwdev->scanning)
 		return;
 
-	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
+	rtwvif_link = rtw89_get_designated_link(rtwvif);
 	if (unlikely(!rtwvif_link)) {
-		rtw89_err(rtwdev, "cancel hw scan: find no link on HW-0\n");
+		rtw89_err(rtwdev, "cancel hw scan: find no designated link\n");
 		return;
 	}
 
diff --git a/drivers/net/wireless/realtek/rtw89/mac_be.c b/drivers/net/wireless/realtek/rtw89/mac_be.c
index 99b82dc85ea3..8c9d326dc907 100644
--- a/drivers/net/wireless/realtek/rtw89/mac_be.c
+++ b/drivers/net/wireless/realtek/rtw89/mac_be.c
@@ -29,6 +29,7 @@ static const u32 rtw89_mac_mem_base_addrs_be[RTW89_MAC_MEM_NUM] = {
 	[RTW89_MAC_MEM_CPU_LOCAL]	= CPU_LOCAL_BASE_ADDR_BE,
 	[RTW89_MAC_MEM_BSSID_CAM]	= BSSID_CAM_BASE_ADDR_BE,
 	[RTW89_MAC_MEM_WD_PAGE]		= WD_PAGE_BASE_ADDR_BE,
+	[RTW89_MAC_MEM_MLD_TBL]		= MLD_TBL_BASE_ADDR_BE,
 };
 
 static const struct rtw89_port_reg rtw89_port_base_be = {
@@ -2636,6 +2637,8 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_be = {
 
 	.is_txq_empty = mac_is_txq_empty_be,
 
+	.prep_chan_list = rtw89_hw_scan_prep_chan_list_be,
+	.free_chan_list = rtw89_hw_scan_free_chan_list_be,
 	.add_chan_list = rtw89_hw_scan_add_chan_list_be,
 	.add_chan_list_pno = rtw89_pno_scan_add_chan_list_be,
 	.scan_offload = rtw89_fw_h2c_scan_offload_be,
diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c
index c2fe5a898dc7..064f6a940107 100644
--- a/drivers/net/wireless/realtek/rtw89/pci.c
+++ b/drivers/net/wireless/realtek/rtw89/pci.c
@@ -228,7 +228,7 @@ int rtw89_pci_sync_skb_for_device_and_validate_rx_info(struct rtw89_dev *rtwdev,
 						       struct sk_buff *skb)
 {
 	struct rtw89_pci_rx_info *rx_info = RTW89_PCI_RX_SKB_CB(skb);
-	int rx_tag_retry = 100;
+	int rx_tag_retry = 1000;
 	int ret;
 
 	do {
@@ -3105,17 +3105,26 @@ static bool rtw89_pci_is_dac_compatible_bridge(struct rtw89_dev *rtwdev)
 	return false;
 }
 
-static void rtw89_pci_cfg_dac(struct rtw89_dev *rtwdev)
+static int rtw89_pci_cfg_dac(struct rtw89_dev *rtwdev, bool force)
 {
 	struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv;
+	struct pci_dev *pdev = rtwpci->pdev;
+	int ret;
+	u8 val;
 
-	if (!rtwpci->enable_dac)
-		return;
+	if (!rtwpci->enable_dac && !force)
+		return 0;
 
 	if (!rtw89_pci_chip_is_manual_dac(rtwdev))
-		return;
+		return 0;
 
-	rtw89_pci_config_byte_set(rtwdev, RTW89_PCIE_L1_CTRL, RTW89_PCIE_BIT_EN_64BITS);
+	/* Configure DAC only via PCI config API, not DBI interfaces */
+	ret = pci_read_config_byte(pdev, RTW89_PCIE_L1_CTRL, &val);
+	if (ret)
+		return ret;
+
+	val |= RTW89_PCIE_BIT_EN_64BITS;
+	return pci_write_config_byte(pdev, RTW89_PCIE_L1_CTRL, val);
 }
 
 static int rtw89_pci_setup_mapping(struct rtw89_dev *rtwdev,
@@ -3133,13 +3142,16 @@ static int rtw89_pci_setup_mapping(struct rtw89_dev *rtwdev,
 	}
 
 	if (!rtw89_pci_is_dac_compatible_bridge(rtwdev))
-		goto no_dac;
+		goto try_dac_done;
 
 	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(36));
 	if (!ret) {
-		rtwpci->enable_dac = true;
-		rtw89_pci_cfg_dac(rtwdev);
-	} else {
+		ret = rtw89_pci_cfg_dac(rtwdev, true);
+		if (!ret) {
+			rtwpci->enable_dac = true;
+			goto try_dac_done;
+		}
+
 		ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		if (ret) {
 			rtw89_err(rtwdev,
@@ -3147,7 +3159,7 @@ static int rtw89_pci_setup_mapping(struct rtw89_dev *rtwdev,
 			goto err_release_regions;
 		}
 	}
-no_dac:
+try_dac_done:
 
 	resource_len = pci_resource_len(pdev, bar_id);
 	rtwpci->mmap = pci_iomap(pdev, bar_id, resource_len);
@@ -4302,7 +4314,7 @@ static void rtw89_pci_l2_hci_ldo(struct rtw89_dev *rtwdev)
 void rtw89_pci_basic_cfg(struct rtw89_dev *rtwdev, bool resume)
 {
 	if (resume)
-		rtw89_pci_cfg_dac(rtwdev);
+		rtw89_pci_cfg_dac(rtwdev, false);
 
 	rtw89_pci_disable_eq(rtwdev);
 	rtw89_pci_filter_out(rtwdev);
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index f4eee642e5ce..76a2e26d4a10 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -2034,19 +2034,10 @@ static s8 rtw89_phy_ant_gain_query(struct rtw89_dev *rtwdev,
 		   ant_gain->offset[path][subband_h]);
 }
 
-static s8 rtw89_phy_ant_gain_offset(struct rtw89_dev *rtwdev, u8 band, u32 center_freq)
+static s8 rtw89_phy_ant_gain_offset(struct rtw89_dev *rtwdev, u32 center_freq)
 {
-	struct rtw89_ant_gain_info *ant_gain = &rtwdev->ant_gain;
-	const struct rtw89_chip_info *chip = rtwdev->chip;
-	u8 regd = rtw89_regd_get(rtwdev, band);
 	s8 offset_patha, offset_pathb;
 
-	if (!chip->support_ant_gain)
-		return 0;
-
-	if (ant_gain->block_country || !(ant_gain->regd_enabled & BIT(regd)))
-		return 0;
-
 	offset_patha = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_A, center_freq);
 	offset_pathb = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_B, center_freq);
 
@@ -2056,18 +2047,31 @@ static s8 rtw89_phy_ant_gain_offset(struct rtw89_dev *rtwdev, u8 band, u32 cente
 	return max(offset_patha, offset_pathb);
 }
 
-s16 rtw89_phy_ant_gain_pwr_offset(struct rtw89_dev *rtwdev,
-				  const struct rtw89_chan *chan)
+static bool rtw89_can_apply_ant_gain(struct rtw89_dev *rtwdev, u8 band)
 {
+	const struct rtw89_rfe_parms *rfe_parms = rtwdev->rfe_parms;
 	struct rtw89_ant_gain_info *ant_gain = &rtwdev->ant_gain;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
-	u8 regd = rtw89_regd_get(rtwdev, chan->band_type);
-	s8 offset_patha, offset_pathb;
+	u8 regd = rtw89_regd_get(rtwdev, band);
 
 	if (!chip->support_ant_gain)
-		return 0;
+		return false;
 
 	if (ant_gain->block_country || !(ant_gain->regd_enabled & BIT(regd)))
+		return false;
+
+	if (!rfe_parms->has_da)
+		return false;
+
+	return true;
+}
+
+s16 rtw89_phy_ant_gain_pwr_offset(struct rtw89_dev *rtwdev,
+				  const struct rtw89_chan *chan)
+{
+	s8 offset_patha, offset_pathb;
+
+	if (!rtw89_can_apply_ant_gain(rtwdev, chan->band_type))
 		return 0;
 
 	if (RTW89_CHK_FW_FEATURE(NO_POWER_DIFFERENCE, &rtwdev->fw))
@@ -2083,14 +2087,10 @@ EXPORT_SYMBOL(rtw89_phy_ant_gain_pwr_offset);
 int rtw89_print_ant_gain(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
 			 const struct rtw89_chan *chan)
 {
-	struct rtw89_ant_gain_info *ant_gain = &rtwdev->ant_gain;
-	const struct rtw89_chip_info *chip = rtwdev->chip;
-	u8 regd = rtw89_regd_get(rtwdev, chan->band_type);
 	char *p = buf, *end = buf + bufsz;
 	s8 offset_patha, offset_pathb;
 
-	if (!(chip->support_ant_gain && (ant_gain->regd_enabled & BIT(regd))) ||
-	    ant_gain->block_country) {
+	if (!rtw89_can_apply_ant_gain(rtwdev, chan->band_type)) {
 		p += scnprintf(p, end - p, "no DAG is applied\n");
 		goto out;
 	}
@@ -2255,20 +2255,31 @@ s8 rtw89_phy_read_txpwr_limit(struct rtw89_dev *rtwdev, u8 band,
 			      u8 bw, u8 ntx, u8 rs, u8 bf, u8 ch)
 {
 	const struct rtw89_rfe_parms *rfe_parms = rtwdev->rfe_parms;
+	const struct rtw89_txpwr_rule_2ghz *rule_da_2ghz = &rfe_parms->rule_da_2ghz;
+	const struct rtw89_txpwr_rule_5ghz *rule_da_5ghz = &rfe_parms->rule_da_5ghz;
+	const struct rtw89_txpwr_rule_6ghz *rule_da_6ghz = &rfe_parms->rule_da_6ghz;
 	const struct rtw89_txpwr_rule_2ghz *rule_2ghz = &rfe_parms->rule_2ghz;
 	const struct rtw89_txpwr_rule_5ghz *rule_5ghz = &rfe_parms->rule_5ghz;
 	const struct rtw89_txpwr_rule_6ghz *rule_6ghz = &rfe_parms->rule_6ghz;
 	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
 	enum nl80211_band nl_band = rtw89_hw_to_nl80211_band(band);
+	bool has_ant_gain = rtw89_can_apply_ant_gain(rtwdev, band);
 	u32 freq = ieee80211_channel_to_frequency(ch, nl_band);
 	u8 ch_idx = rtw89_channel_to_idx(rtwdev, band, ch);
+	s8 lmt = 0, da_lmt = S8_MAX, sar, offset = 0;
 	u8 regd = rtw89_regd_get(rtwdev, band);
 	u8 reg6 = regulatory->reg_6ghz_power;
-	s8 lmt = 0, sar, offset;
+	struct rtw89_sar_parm sar_parm = {
+		.center_freq = freq,
+		.ntx = ntx,
+	};
 	s8 cstr;
 
 	switch (band) {
 	case RTW89_BAND_2G:
+		if (has_ant_gain)
+			da_lmt = (*rule_da_2ghz->lmt)[bw][ntx][rs][bf][regd][ch_idx];
+
 		lmt = (*rule_2ghz->lmt)[bw][ntx][rs][bf][regd][ch_idx];
 		if (lmt)
 			break;
@@ -2276,6 +2287,9 @@ s8 rtw89_phy_read_txpwr_limit(struct rtw89_dev *rtwdev, u8 band,
 		lmt = (*rule_2ghz->lmt)[bw][ntx][rs][bf][RTW89_WW][ch_idx];
 		break;
 	case RTW89_BAND_5G:
+		if (has_ant_gain)
+			da_lmt = (*rule_da_5ghz->lmt)[bw][ntx][rs][bf][regd][ch_idx];
+
 		lmt = (*rule_5ghz->lmt)[bw][ntx][rs][bf][regd][ch_idx];
 		if (lmt)
 			break;
@@ -2283,6 +2297,9 @@ s8 rtw89_phy_read_txpwr_limit(struct rtw89_dev *rtwdev, u8 band,
 		lmt = (*rule_5ghz->lmt)[bw][ntx][rs][bf][RTW89_WW][ch_idx];
 		break;
 	case RTW89_BAND_6G:
+		if (has_ant_gain)
+			da_lmt = (*rule_da_6ghz->lmt)[bw][ntx][rs][bf][regd][reg6][ch_idx];
+
 		lmt = (*rule_6ghz->lmt)[bw][ntx][rs][bf][regd][reg6][ch_idx];
 		if (lmt)
 			break;
@@ -2296,9 +2313,12 @@ s8 rtw89_phy_read_txpwr_limit(struct rtw89_dev *rtwdev, u8 band,
 		return 0;
 	}
 
-	offset = rtw89_phy_ant_gain_offset(rtwdev, band, freq);
-	lmt = rtw89_phy_txpwr_rf_to_mac(rtwdev, lmt + offset);
-	sar = rtw89_query_sar(rtwdev, freq);
+	da_lmt = da_lmt ?: S8_MAX;
+	if (da_lmt != S8_MAX)
+		offset = rtw89_phy_ant_gain_offset(rtwdev, freq);
+
+	lmt = rtw89_phy_txpwr_rf_to_mac(rtwdev, min(lmt + offset, da_lmt));
+	sar = rtw89_query_sar(rtwdev, &sar_parm);
 	cstr = rtw89_phy_get_tpe_constraint(rtwdev, band);
 
 	return min3(lmt, sar, cstr);
@@ -2515,20 +2535,31 @@ s8 rtw89_phy_read_txpwr_limit_ru(struct rtw89_dev *rtwdev, u8 band,
 				 u8 ru, u8 ntx, u8 ch)
 {
 	const struct rtw89_rfe_parms *rfe_parms = rtwdev->rfe_parms;
+	const struct rtw89_txpwr_rule_2ghz *rule_da_2ghz = &rfe_parms->rule_da_2ghz;
+	const struct rtw89_txpwr_rule_5ghz *rule_da_5ghz = &rfe_parms->rule_da_5ghz;
+	const struct rtw89_txpwr_rule_6ghz *rule_da_6ghz = &rfe_parms->rule_da_6ghz;
 	const struct rtw89_txpwr_rule_2ghz *rule_2ghz = &rfe_parms->rule_2ghz;
 	const struct rtw89_txpwr_rule_5ghz *rule_5ghz = &rfe_parms->rule_5ghz;
 	const struct rtw89_txpwr_rule_6ghz *rule_6ghz = &rfe_parms->rule_6ghz;
 	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
 	enum nl80211_band nl_band = rtw89_hw_to_nl80211_band(band);
+	bool has_ant_gain = rtw89_can_apply_ant_gain(rtwdev, band);
 	u32 freq = ieee80211_channel_to_frequency(ch, nl_band);
 	u8 ch_idx = rtw89_channel_to_idx(rtwdev, band, ch);
+	s8 lmt_ru = 0, da_lmt_ru = S8_MAX, sar, offset = 0;
 	u8 regd = rtw89_regd_get(rtwdev, band);
 	u8 reg6 = regulatory->reg_6ghz_power;
-	s8 lmt_ru = 0, sar, offset;
+	struct rtw89_sar_parm sar_parm = {
+		.center_freq = freq,
+		.ntx = ntx,
+	};
 	s8 cstr;
 
 	switch (band) {
 	case RTW89_BAND_2G:
+		if (has_ant_gain)
+			da_lmt_ru = (*rule_da_2ghz->lmt_ru)[ru][ntx][regd][ch_idx];
+
 		lmt_ru = (*rule_2ghz->lmt_ru)[ru][ntx][regd][ch_idx];
 		if (lmt_ru)
 			break;
@@ -2536,6 +2567,9 @@ s8 rtw89_phy_read_txpwr_limit_ru(struct rtw89_dev *rtwdev, u8 band,
 		lmt_ru = (*rule_2ghz->lmt_ru)[ru][ntx][RTW89_WW][ch_idx];
 		break;
 	case RTW89_BAND_5G:
+		if (has_ant_gain)
+			da_lmt_ru = (*rule_da_5ghz->lmt_ru)[ru][ntx][regd][ch_idx];
+
 		lmt_ru = (*rule_5ghz->lmt_ru)[ru][ntx][regd][ch_idx];
 		if (lmt_ru)
 			break;
@@ -2543,6 +2577,9 @@ s8 rtw89_phy_read_txpwr_limit_ru(struct rtw89_dev *rtwdev, u8 band,
 		lmt_ru = (*rule_5ghz->lmt_ru)[ru][ntx][RTW89_WW][ch_idx];
 		break;
 	case RTW89_BAND_6G:
+		if (has_ant_gain)
+			da_lmt_ru = (*rule_da_6ghz->lmt_ru)[ru][ntx][regd][reg6][ch_idx];
+
 		lmt_ru = (*rule_6ghz->lmt_ru)[ru][ntx][regd][reg6][ch_idx];
 		if (lmt_ru)
 			break;
@@ -2556,9 +2593,12 @@ s8 rtw89_phy_read_txpwr_limit_ru(struct rtw89_dev *rtwdev, u8 band,
 		return 0;
 	}
 
-	offset = rtw89_phy_ant_gain_offset(rtwdev, band, freq);
-	lmt_ru = rtw89_phy_txpwr_rf_to_mac(rtwdev, lmt_ru + offset);
-	sar = rtw89_query_sar(rtwdev, freq);
+	da_lmt_ru = da_lmt_ru ?: S8_MAX;
+	if (da_lmt_ru != S8_MAX)
+		offset = rtw89_phy_ant_gain_offset(rtwdev, freq);
+
+	lmt_ru = rtw89_phy_txpwr_rf_to_mac(rtwdev, min(lmt_ru + offset, da_lmt_ru));
+	sar = rtw89_query_sar(rtwdev, &sar_parm);
 	cstr = rtw89_phy_get_tpe_constraint(rtwdev, band);
 
 	return min3(lmt_ru, sar, cstr);
@@ -3015,6 +3055,35 @@ void (* const rtw89_phy_c2h_ra_handler[])(struct rtw89_dev *rtwdev,
 	[RTW89_PHY_C2H_FUNC_TXSTS] = NULL,
 };
 
+static void
+rtw89_phy_c2h_lowrt_rty(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
+{
+}
+
+static void
+rtw89_phy_c2h_fw_scan_rpt(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
+{
+	const struct rtw89_c2h_fw_scan_rpt *c2h_rpt =
+		(const struct rtw89_c2h_fw_scan_rpt *)c2h->data;
+
+	rtw89_debug(rtwdev, RTW89_DBG_DIG,
+		    "%s: band: %u, op_chan: %u, PD_low_bd(ofdm, cck): (-%d, %d), phy_idx: %u\n",
+		    __func__, c2h_rpt->band, c2h_rpt->center_ch,
+		    PD_LOWER_BOUND_BASE - (c2h_rpt->ofdm_pd_idx << 1),
+		    c2h_rpt->cck_pd_idx, c2h_rpt->phy_idx);
+}
+
+static
+void (* const rtw89_phy_c2h_dm_handler[])(struct rtw89_dev *rtwdev,
+					  struct sk_buff *c2h, u32 len) = {
+	[RTW89_PHY_C2H_DM_FUNC_FW_TEST] = NULL,
+	[RTW89_PHY_C2H_DM_FUNC_FW_TRIG_TX_RPT] = NULL,
+	[RTW89_PHY_C2H_DM_FUNC_SIGB] = NULL,
+	[RTW89_PHY_C2H_DM_FUNC_LOWRT_RTY] = rtw89_phy_c2h_lowrt_rty,
+	[RTW89_PHY_C2H_DM_FUNC_MCC_DIG] = NULL,
+	[RTW89_PHY_C2H_DM_FUNC_FW_SCAN] = rtw89_phy_c2h_fw_scan_rpt,
+};
+
 static void rtw89_phy_c2h_rfk_rpt_log(struct rtw89_dev *rtwdev,
 				      enum rtw89_phy_c2h_rfk_log_func func,
 				      void *content, u16 len)
@@ -3550,9 +3619,9 @@ void rtw89_phy_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 			handler = rtw89_phy_c2h_rfk_report_handler[func];
 		break;
 	case RTW89_PHY_C2H_CLASS_DM:
-		if (func == RTW89_PHY_C2H_DM_FUNC_LOWRT_RTY)
-			return;
-		fallthrough;
+		if (func < ARRAY_SIZE(rtw89_phy_c2h_dm_handler))
+			handler = rtw89_phy_c2h_dm_handler[func];
+		break;
 	default:
 		rtw89_info(rtwdev, "PHY c2h class %d not support\n", class);
 		return;
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index 518a100375fb..5b451f1cfaac 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -164,6 +164,7 @@ enum rtw89_phy_c2h_dm_func {
 	RTW89_PHY_C2H_DM_FUNC_SIGB,
 	RTW89_PHY_C2H_DM_FUNC_LOWRT_RTY,
 	RTW89_PHY_C2H_DM_FUNC_MCC_DIG,
+	RTW89_PHY_C2H_DM_FUNC_FW_SCAN = 0xc,
 	RTW89_PHY_C2H_DM_FUNC_NUM,
 };
 
@@ -935,6 +936,20 @@ static inline s8 rtw89_phy_txpwr_dbm_to_mac(struct rtw89_dev *rtwdev, s8 dbm)
 	return clamp_t(s16, dbm << chip->txpwr_factor_mac, -64, 63);
 }
 
+static inline s16 rtw89_phy_txpwr_mac_to_rf(struct rtw89_dev *rtwdev, s8 txpwr_mac)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+
+	return txpwr_mac << (chip->txpwr_factor_rf - chip->txpwr_factor_mac);
+}
+
+static inline s16 rtw89_phy_txpwr_mac_to_bb(struct rtw89_dev *rtwdev, s8 txpwr_mac)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+
+	return txpwr_mac << (chip->txpwr_factor_bb - chip->txpwr_factor_mac);
+}
+
 void rtw89_phy_ra_assoc(struct rtw89_dev *rtwdev, struct rtw89_sta_link *rtwsta_link);
 void rtw89_phy_ra_update(struct rtw89_dev *rtwdev);
 void rtw89_phy_ra_update_sta(struct rtw89_dev *rtwdev, struct ieee80211_sta *sta,
diff --git a/drivers/net/wireless/realtek/rtw89/phy_be.c b/drivers/net/wireless/realtek/rtw89/phy_be.c
index 37d8f254ae32..d321cf1fc485 100644
--- a/drivers/net/wireless/realtek/rtw89/phy_be.c
+++ b/drivers/net/wireless/realtek/rtw89/phy_be.c
@@ -362,7 +362,7 @@ static void rtw89_phy_bb_wrap_force_cr_init(struct rtw89_dev *rtwdev,
 	rtw89_write32_mask(rtwdev, addr, B_BE_PWR_FORCE_RU_ENON, 0);
 	rtw89_write32_mask(rtwdev, addr, B_BE_PWR_FORCE_RU_ON, 0);
 	addr = rtw89_mac_reg_by_idx(rtwdev, R_BE_PWR_FORCE_MACID, mac_idx);
-	rtw89_write32_mask(rtwdev, addr, B_BE_PWR_FORCE_MACID_ON, 0);
+	rtw89_write32_mask(rtwdev, addr, B_BE_PWR_FORCE_MACID_ALL, 0);
 	addr = rtw89_mac_reg_by_idx(rtwdev, R_BE_PWR_COEX_CTRL, mac_idx);
 	rtw89_write32_mask(rtwdev, addr, B_BE_PWR_FORCE_COEX_ON, 0);
 	addr = rtw89_mac_reg_by_idx(rtwdev, R_BE_PWR_RATE_CTRL, mac_idx);
diff --git a/drivers/net/wireless/realtek/rtw89/ps.c b/drivers/net/wireless/realtek/rtw89/ps.c
index ac46a7baa00d..8e4fe73e7d77 100644
--- a/drivers/net/wireless/realtek/rtw89/ps.c
+++ b/drivers/net/wireless/realtek/rtw89/ps.c
@@ -382,3 +382,150 @@ u8 rtw89_p2p_noa_fetch(struct rtw89_vif_link *rtwvif_link, void **data)
 	tail = ie->noa_desc + setter->noa_count;
 	return tail - *data;
 }
+
+static void rtw89_ps_noa_once_set_work(struct wiphy *wiphy, struct wiphy_work *work)
+{
+	struct rtw89_ps_noa_once_handler *noa_once =
+		container_of(work, struct rtw89_ps_noa_once_handler, set_work.work);
+
+	lockdep_assert_wiphy(wiphy);
+
+	noa_once->in_duration = true;
+}
+
+static void rtw89_ps_noa_once_clr_work(struct wiphy *wiphy, struct wiphy_work *work)
+{
+	struct rtw89_ps_noa_once_handler *noa_once =
+		container_of(work, struct rtw89_ps_noa_once_handler, clr_work.work);
+	struct rtw89_vif_link *rtwvif_link =
+		container_of(noa_once, struct rtw89_vif_link, noa_once);
+	struct rtw89_dev *rtwdev = rtwvif_link->rtwvif->rtwdev;
+
+	lockdep_assert_wiphy(wiphy);
+
+	rtw89_fw_h2c_set_bcn_fltr_cfg(rtwdev, rtwvif_link, true);
+	noa_once->in_duration = false;
+}
+
+void rtw89_p2p_noa_once_init(struct rtw89_vif_link *rtwvif_link)
+{
+	struct rtw89_ps_noa_once_handler *noa_once = &rtwvif_link->noa_once;
+
+	noa_once->in_duration = false;
+	noa_once->tsf_begin = 0;
+	noa_once->tsf_end = 0;
+
+	wiphy_delayed_work_init(&noa_once->set_work, rtw89_ps_noa_once_set_work);
+	wiphy_delayed_work_init(&noa_once->clr_work, rtw89_ps_noa_once_clr_work);
+}
+
+static void rtw89_p2p_noa_once_cancel(struct rtw89_vif_link *rtwvif_link)
+{
+	struct rtw89_ps_noa_once_handler *noa_once = &rtwvif_link->noa_once;
+	struct rtw89_dev *rtwdev = rtwvif_link->rtwvif->rtwdev;
+	struct wiphy *wiphy = rtwdev->hw->wiphy;
+
+	wiphy_delayed_work_cancel(wiphy, &noa_once->set_work);
+	wiphy_delayed_work_cancel(wiphy, &noa_once->clr_work);
+}
+
+void rtw89_p2p_noa_once_deinit(struct rtw89_vif_link *rtwvif_link)
+{
+	rtw89_p2p_noa_once_cancel(rtwvif_link);
+	rtw89_p2p_noa_once_init(rtwvif_link);
+}
+
+void rtw89_p2p_noa_once_recalc(struct rtw89_vif_link *rtwvif_link)
+{
+	struct rtw89_ps_noa_once_handler *noa_once = &rtwvif_link->noa_once;
+	struct rtw89_dev *rtwdev = rtwvif_link->rtwvif->rtwdev;
+	const struct ieee80211_p2p_noa_desc *noa_desc;
+	struct wiphy *wiphy = rtwdev->hw->wiphy;
+	struct ieee80211_bss_conf *bss_conf;
+	u64 tsf_begin = U64_MAX, tsf_end;
+	u64 set_delay_us = 0;
+	u64 clr_delay_us = 0;
+	u32 start_time;
+	u32 interval;
+	u32 duration;
+	u64 tsf;
+	int ret;
+	int i;
+
+	lockdep_assert_wiphy(wiphy);
+
+	ret = rtw89_mac_port_get_tsf(rtwdev, rtwvif_link, &tsf);
+	if (ret) {
+		rtw89_warn(rtwdev, "%s: failed to get tsf\n", __func__);
+		return;
+	}
+
+	rcu_read_lock();
+
+	bss_conf = rtw89_vif_rcu_dereference_link(rtwvif_link, true);
+
+	for (i = 0; i < ARRAY_SIZE(bss_conf->p2p_noa_attr.desc); i++) {
+		bool first = tsf_begin == U64_MAX;
+		u64 tmp;
+
+		noa_desc = &bss_conf->p2p_noa_attr.desc[i];
+		if (noa_desc->count == 0 || noa_desc->count == 255)
+			continue;
+
+		start_time = le32_to_cpu(noa_desc->start_time);
+		interval = le32_to_cpu(noa_desc->interval);
+		duration = le32_to_cpu(noa_desc->duration);
+
+		if (unlikely(duration == 0 ||
+			     (noa_desc->count > 1 && interval == 0)))
+			continue;
+
+		tmp = start_time + interval * (noa_desc->count - 1) + duration;
+		tmp = (tsf & GENMASK_ULL(63, 32)) + tmp;
+		if (unlikely(tmp <= tsf))
+			continue;
+		tsf_end = first ? tmp : max(tsf_end, tmp);
+
+		tmp = (tsf & GENMASK_ULL(63, 32)) | start_time;
+		tsf_begin = first ? tmp : min(tsf_begin, tmp);
+	}
+
+	rcu_read_unlock();
+
+	if (tsf_begin == U64_MAX)
+		return;
+
+	rtw89_p2p_noa_once_cancel(rtwvif_link);
+
+	if (noa_once->tsf_end > tsf) {
+		tsf_begin = min(tsf_begin, noa_once->tsf_begin);
+		tsf_end = max(tsf_end, noa_once->tsf_end);
+	}
+
+	clr_delay_us = min_t(u64, tsf_end - tsf, UINT_MAX);
+
+	if (tsf_begin <= tsf) {
+		noa_once->in_duration = true;
+		goto out;
+	}
+
+	set_delay_us = tsf_begin - tsf;
+	if (unlikely(set_delay_us > UINT_MAX)) {
+		rtw89_warn(rtwdev, "%s: unhandled begin\n", __func__);
+		set_delay_us = 0;
+		clr_delay_us = 0;
+		rtw89_fw_h2c_set_bcn_fltr_cfg(rtwdev, rtwvif_link, true);
+		noa_once->in_duration = false;
+	}
+
+out:
+	if (set_delay_us)
+		wiphy_delayed_work_queue(wiphy, &noa_once->set_work,
+					 usecs_to_jiffies(set_delay_us));
+	if (clr_delay_us)
+		wiphy_delayed_work_queue(wiphy, &noa_once->clr_work,
+					 usecs_to_jiffies(clr_delay_us));
+
+	noa_once->tsf_begin = tsf_begin;
+	noa_once->tsf_end = tsf_end;
+}
diff --git a/drivers/net/wireless/realtek/rtw89/ps.h b/drivers/net/wireless/realtek/rtw89/ps.h
index 2b88f254a32d..b2c43d44820d 100644
--- a/drivers/net/wireless/realtek/rtw89/ps.h
+++ b/drivers/net/wireless/realtek/rtw89/ps.h
@@ -22,6 +22,9 @@ void rtw89_p2p_noa_renew(struct rtw89_vif_link *rtwvif_link);
 void rtw89_p2p_noa_append(struct rtw89_vif_link *rtwvif_link,
 			  const struct ieee80211_p2p_noa_desc *desc);
 u8 rtw89_p2p_noa_fetch(struct rtw89_vif_link *rtwvif_link, void **data);
+void rtw89_p2p_noa_once_init(struct rtw89_vif_link *rtwvif_link);
+void rtw89_p2p_noa_once_deinit(struct rtw89_vif_link *rtwvif_link);
+void rtw89_p2p_noa_once_recalc(struct rtw89_vif_link *rtwvif_link);
 
 static inline void rtw89_leave_ips_by_hwflags(struct rtw89_dev *rtwdev)
 {
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index c776954ad360..f05c81ae5869 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -7601,7 +7601,15 @@
 #define B_BE_PWR_FORCE_RU_ON BIT(18)
 #define B_BE_PWR_FORCE_RU_ENON BIT(28)
 #define R_BE_PWR_FORCE_MACID 0x11A48
-#define B_BE_PWR_FORCE_MACID_ON BIT(9)
+#define B_BE_PWR_FORCE_MACID_DBM_ON BIT(9)
+#define B_BE_PWR_FORCE_MACID_DBM_VAL GENMASK(17, 10)
+#define B_BE_PWR_FORCE_MACID_EN_VAL BIT(18)
+#define B_BE_PWR_FORCE_MACID_EN_ON BIT(19)
+#define B_BE_PWR_FORCE_MACID_ALL \
+	(B_BE_PWR_FORCE_MACID_DBM_ON | \
+	 B_BE_PWR_FORCE_MACID_DBM_VAL | \
+	 B_BE_PWR_FORCE_MACID_EN_VAL | \
+	 B_BE_PWR_FORCE_MACID_EN_ON)
 
 #define R_BE_PWR_REG_CTRL 0x11A50
 #define B_BE_PWR_BT_EN BIT(23)
@@ -8737,8 +8745,10 @@
 #define B_DPD_GDIS BIT(13)
 #define B_IQK_RFC_ON BIT(1)
 #define R_TXPWRB 0x56CC
+#define R_P1_TXPWRB 0x76CC
 #define B_TXPWRB_ON BIT(28)
 #define B_TXPWRB_VAL GENMASK(27, 19)
+#define B_TXPWRB_MAX GENMASK(8, 0)
 #define R_DPD_OFT_EN 0x5800
 #define B_DPD_OFT_EN BIT(28)
 #define B_DPD_TSSI_CW GENMASK(26, 18)
@@ -9360,6 +9370,9 @@
 #define R_TSSI_PWR_P0 0xE610
 #define R_TSSI_PWR_P1 0xE710
 #define B_TSSI_CONT_EN BIT(3)
+#define R_P0_TXPWRB_BE 0xE61C
+#define R_P1_TXPWRB_BE 0xE71C
+#define B_TXPWRB_MAX_BE GENMASK(20, 12)
 #define R_TSSI_MAP_OFST_P0 0xE620
 #define R_TSSI_MAP_OFST_P1 0xE720
 #define B_TSSI_MAP_OFST_OFDM GENMASK(17, 9)
diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index 655323a79608..3ad14cab1f58 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -588,6 +588,38 @@ bottom:
 	kfree(sband);
 }
 
+#define RTW89_DEF_REGD_STR(regd) \
+	[RTW89_ ## regd] = #regd
+
+static const char * const rtw89_regd_string[] = {
+	RTW89_DEF_REGD_STR(WW),
+	RTW89_DEF_REGD_STR(ETSI),
+	RTW89_DEF_REGD_STR(FCC),
+	RTW89_DEF_REGD_STR(MKK),
+	RTW89_DEF_REGD_STR(NA),
+	RTW89_DEF_REGD_STR(IC),
+	RTW89_DEF_REGD_STR(KCC),
+	RTW89_DEF_REGD_STR(ACMA),
+	RTW89_DEF_REGD_STR(NCC),
+	RTW89_DEF_REGD_STR(MEXICO),
+	RTW89_DEF_REGD_STR(CHILE),
+	RTW89_DEF_REGD_STR(UKRAINE),
+	RTW89_DEF_REGD_STR(CN),
+	RTW89_DEF_REGD_STR(QATAR),
+	RTW89_DEF_REGD_STR(UK),
+	RTW89_DEF_REGD_STR(THAILAND),
+};
+
+static_assert(ARRAY_SIZE(rtw89_regd_string) == RTW89_REGD_NUM);
+
+const char *rtw89_regd_get_string(enum rtw89_regulation_type regd)
+{
+	if (regd < 0 || regd >= RTW89_REGD_NUM)
+		return "(unknown)";
+
+	return rtw89_regd_string[regd];
+}
+
 int rtw89_regd_setup(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
@@ -604,6 +636,7 @@ int rtw89_regd_setup(struct rtw89_dev *rtwdev)
 	}
 
 	regulatory->reg_6ghz_power = RTW89_REG_6GHZ_POWER_DFLT;
+	regulatory->txpwr_uk_follow_etsi = true;
 
 	if (!wiphy)
 		return -EINVAL;
@@ -726,11 +759,22 @@ static void rtw89_regd_apply_policy_tas(struct rtw89_dev *rtwdev)
 	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
 	const struct rtw89_regd *regd = regulatory->regd;
 	struct rtw89_tas_info *tas = &rtwdev->tas;
+	u8 tas_country;
 
 	if (!tas->enable)
 		return;
 
-	tas->block_regd = !test_bit(RTW89_REGD_FUNC_TAS, regd->func_bitmap);
+	if (memcmp("US", regd->alpha2, 2) == 0)
+		tas_country = RTW89_ACPI_CONF_TAS_US;
+	else if (memcmp("CA", regd->alpha2, 2) == 0)
+		tas_country = RTW89_ACPI_CONF_TAS_CA;
+	else if (memcmp("KR", regd->alpha2, 2) == 0)
+		tas_country = RTW89_ACPI_CONF_TAS_KR;
+	else
+		tas_country = RTW89_ACPI_CONF_TAS_OTHERS;
+
+	tas->block_regd = !(tas->enabled_countries & tas_country &&
+			    test_bit(RTW89_REGD_FUNC_TAS, regd->func_bitmap));
 }
 
 static void rtw89_regd_apply_policy_ant_gain(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 0d482cd57f6e..fafa200a9c8d 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2499,12 +2499,14 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.support_unii4		= true,
 	.support_ant_gain	= false,
 	.support_tas		= false,
+	.support_sar_by_ant	= false,
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
 	.rx_freq_frome_ie	= true,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt	= false,
 	.hw_tkip_crypto		= false,
+	.hw_mlo_bmc_crypto	= false,
 	.rf_path_num		= 1,
 	.tx_nss			= 1,
 	.rx_nss			= 1,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 286334e26c84..cd5987fc52d7 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2217,12 +2217,14 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.support_unii4		= false,
 	.support_ant_gain	= false,
 	.support_tas		= false,
+	.support_sar_by_ant	= false,
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= false,
 	.rx_freq_frome_ie	= true,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt	= false,
 	.hw_tkip_crypto		= false,
+	.hw_mlo_bmc_crypto	= false,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index eceb4fb9880d..dacdb384de2c 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -853,12 +853,14 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.support_unii4		= true,
 	.support_ant_gain	= true,
 	.support_tas		= false,
+	.support_sar_by_ant	= true,
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
 	.rx_freq_frome_ie	= true,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt	= false,
 	.hw_tkip_crypto		= false,
+	.hw_mlo_bmc_crypto	= false,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
index 99c9505b3cbd..0cf03f18cbb1 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
@@ -8,6 +8,7 @@
 #include "phy.h"
 #include "reg.h"
 #include "rtw8852b_common.h"
+#include "sar.h"
 #include "util.h"
 
 static const struct rtw89_reg3_def rtw8852bx_pmac_ht20_mcs7_tbl[] = {
@@ -1234,6 +1235,7 @@ static u32 rtw8852bx_bb_cal_txpwr_ref(struct rtw89_dev *rtwdev,
 	       u32_encode_bits(ref, B_DPD_REF);
 }
 
+/* @pwr_ofst (unit: 1/8 dBm): power of path A minus power of path B */
 static void rtw8852bx_set_txpwr_ref(struct rtw89_dev *rtwdev,
 				    enum rtw89_phy_idx phy_idx, s16 pwr_ofst)
 {
@@ -1336,6 +1338,27 @@ static void rtw8852bx_set_tx_shape(struct rtw89_dev *rtwdev,
 			       tx_shape_ofdm);
 }
 
+static s16 rtw8852bx_get_txpwr_sar_diff(struct rtw89_dev *rtwdev,
+					const struct rtw89_chan *chan)
+{
+	struct rtw89_sar_parm sar_parm = {
+		.center_freq = chan->freq,
+		.force_path = true,
+	};
+	s16 sar_bb_a, sar_bb_b;
+	s8 sar_mac;
+
+	sar_parm.path = RF_PATH_A;
+	sar_mac = rtw89_query_sar(rtwdev, &sar_parm);
+	sar_bb_a = rtw89_phy_txpwr_mac_to_bb(rtwdev, sar_mac);
+
+	sar_parm.path = RF_PATH_B;
+	sar_mac = rtw89_query_sar(rtwdev, &sar_parm);
+	sar_bb_b = rtw89_phy_txpwr_mac_to_bb(rtwdev, sar_mac);
+
+	return sar_bb_a - sar_bb_b;
+}
+
 static void rtw8852bx_set_txpwr_diff(struct rtw89_dev *rtwdev,
 				     const struct rtw89_chan *chan,
 				     enum rtw89_phy_idx phy_idx)
@@ -1343,6 +1366,7 @@ static void rtw8852bx_set_txpwr_diff(struct rtw89_dev *rtwdev,
 	s16 pwr_ofst;
 
 	pwr_ofst = rtw89_phy_ant_gain_pwr_offset(rtwdev, chan);
+	pwr_ofst += rtw8852bx_get_txpwr_sar_diff(rtwdev, chan);
 	rtw8852bx_set_txpwr_ref(rtwdev, phy_idx, pwr_ofst);
 }
 
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index bbf37442c492..289dce688d72 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -786,12 +786,14 @@ const struct rtw89_chip_info rtw8852bt_chip_info = {
 	.support_unii4		= true,
 	.support_ant_gain	= true,
 	.support_tas		= false,
+	.support_sar_by_ant	= true,
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
 	.rx_freq_frome_ie	= true,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt     = false,
 	.hw_tkip_crypto		= true,
+	.hw_mlo_bmc_crypto	= false,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 08bcdf246382..2a6143a8d256 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -15,7 +15,7 @@
 #include "sar.h"
 #include "util.h"
 
-#define RTW8852C_FW_FORMAT_MAX 1
+#define RTW8852C_FW_FORMAT_MAX 2
 #define RTW8852C_FW_BASENAME "rtw89/rtw8852c_fw"
 #define RTW8852C_MODULE_FIRMWARE \
 	RTW8852C_FW_BASENAME "-" __stringify(RTW8852C_FW_FORMAT_MAX) ".bin"
@@ -2079,6 +2079,31 @@ static void rtw8852c_set_txpwr_diff(struct rtw89_dev *rtwdev,
 	rtw8852c_set_txpwr_ref(rtwdev, phy_idx, pwr_ofst);
 }
 
+static void rtw8852c_set_txpwr_sar_diff(struct rtw89_dev *rtwdev,
+					const struct rtw89_chan *chan,
+					enum rtw89_phy_idx phy_idx)
+{
+	struct rtw89_sar_parm sar_parm = {
+		.center_freq = chan->freq,
+		.force_path = true,
+	};
+	s16 sar_rf;
+	s8 sar_mac;
+
+	if (phy_idx != RTW89_PHY_0)
+		return;
+
+	sar_parm.path = RF_PATH_A;
+	sar_mac = rtw89_query_sar(rtwdev, &sar_parm);
+	sar_rf = rtw89_phy_txpwr_mac_to_rf(rtwdev, sar_mac);
+	rtw89_phy_write32_mask(rtwdev, R_TXPWRB, B_TXPWRB_MAX, sar_rf);
+
+	sar_parm.path = RF_PATH_B;
+	sar_mac = rtw89_query_sar(rtwdev, &sar_parm);
+	sar_rf = rtw89_phy_txpwr_mac_to_rf(rtwdev, sar_mac);
+	rtw89_phy_write32_mask(rtwdev, R_P1_TXPWRB, B_TXPWRB_MAX, sar_rf);
+}
+
 static void rtw8852c_set_txpwr(struct rtw89_dev *rtwdev,
 			       const struct rtw89_chan *chan,
 			       enum rtw89_phy_idx phy_idx)
@@ -2089,6 +2114,7 @@ static void rtw8852c_set_txpwr(struct rtw89_dev *rtwdev,
 	rtw89_phy_set_txpwr_limit(rtwdev, chan, phy_idx);
 	rtw89_phy_set_txpwr_limit_ru(rtwdev, chan, phy_idx);
 	rtw8852c_set_txpwr_diff(rtwdev, chan, phy_idx);
+	rtw8852c_set_txpwr_sar_diff(rtwdev, chan, phy_idx);
 }
 
 static void rtw8852c_set_txpwr_ctrl(struct rtw89_dev *rtwdev,
@@ -3014,12 +3040,14 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.support_unii4		= true,
 	.support_ant_gain	= true,
 	.support_tas		= true,
+	.support_sar_by_ant	= true,
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= true,
 	.rx_freq_frome_ie	= false,
 	.hw_sec_hdr		= true,
 	.hw_mgmt_tx_encrypt	= true,
 	.hw_tkip_crypto		= true,
+	.hw_mlo_bmc_crypto	= false,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 8082592db84a..1d0f6e7df497 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -12,6 +12,7 @@
 #include "reg.h"
 #include "rtw8922a.h"
 #include "rtw8922a_rfk.h"
+#include "sar.h"
 #include "util.h"
 
 #define RTW8922A_FW_FORMAT_MAX 3
@@ -2070,7 +2071,8 @@ static void __rtw8922a_rfk_init_late(struct rtw89_dev *rtwdev,
 	rtw89_phy_rfk_pre_ntfy_and_wait(rtwdev, phy_idx, 5);
 
 	rtw89_phy_rfk_dack_and_wait(rtwdev, phy_idx, chan, 58);
-	rtw89_phy_rfk_rxdck_and_wait(rtwdev, phy_idx, chan, false, 32);
+	if (!test_bit(RTW89_FLAG_SER_HANDLING, rtwdev->flags))
+		rtw89_phy_rfk_rxdck_and_wait(rtwdev, phy_idx, chan, false, 128);
 }
 
 static void rtw8922a_rfk_init_late(struct rtw89_dev *rtwdev)
@@ -2233,6 +2235,31 @@ static void rtw8922a_set_tx_shape(struct rtw89_dev *rtwdev,
 		rtw8922a_bb_tx_triangular(rtwdev, true, phy_idx);
 }
 
+static void rtw8922a_set_txpwr_sar_diff(struct rtw89_dev *rtwdev,
+					const struct rtw89_chan *chan,
+					enum rtw89_phy_idx phy_idx)
+{
+	struct rtw89_sar_parm sar_parm = {
+		.center_freq = chan->freq,
+		.force_path = true,
+	};
+	s16 sar_rf;
+	s8 sar_mac;
+
+	if (phy_idx != RTW89_PHY_0)
+		return;
+
+	sar_parm.path = RF_PATH_A;
+	sar_mac = rtw89_query_sar(rtwdev, &sar_parm);
+	sar_rf = rtw89_phy_txpwr_mac_to_rf(rtwdev, sar_mac);
+	rtw89_phy_write32_mask(rtwdev, R_P0_TXPWRB_BE, B_TXPWRB_MAX_BE, sar_rf);
+
+	sar_parm.path = RF_PATH_B;
+	sar_mac = rtw89_query_sar(rtwdev, &sar_parm);
+	sar_rf = rtw89_phy_txpwr_mac_to_rf(rtwdev, sar_mac);
+	rtw89_phy_write32_mask(rtwdev, R_P1_TXPWRB_BE, B_TXPWRB_MAX_BE, sar_rf);
+}
+
 static void rtw8922a_set_txpwr(struct rtw89_dev *rtwdev,
 			       const struct rtw89_chan *chan,
 			       enum rtw89_phy_idx phy_idx)
@@ -2244,6 +2271,7 @@ static void rtw8922a_set_txpwr(struct rtw89_dev *rtwdev,
 	rtw89_phy_set_txpwr_limit_ru(rtwdev, chan, phy_idx);
 	rtw8922a_set_txpwr_diff(rtwdev, chan, phy_idx);
 	rtw8922a_set_txpwr_ref(rtwdev, phy_idx);
+	rtw8922a_set_txpwr_sar_diff(rtwdev, chan, phy_idx);
 }
 
 static void rtw8922a_set_txpwr_ctrl(struct rtw89_dev *rtwdev,
@@ -2823,12 +2851,14 @@ const struct rtw89_chip_info rtw8922a_chip_info = {
 	.support_unii4		= true,
 	.support_ant_gain	= true,
 	.support_tas		= false,
+	.support_sar_by_ant	= true,
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= false,
 	.rx_freq_frome_ie	= false,
 	.hw_sec_hdr		= true,
 	.hw_mgmt_tx_encrypt	= true,
 	.hw_tkip_crypto		= true,
+	.hw_mlo_bmc_crypto	= false,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c
index c4c93f836a2f..1659ea64ade1 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c
@@ -77,11 +77,6 @@ void rtw8922a_ctl_band_ch_bw(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 					     RR_CFGCH_BAND0 | RR_CFGCH_CH);
 			rf_reg[path][i] |= u32_encode_bits(central_ch, RR_CFGCH_CH);
 
-			if (band == RTW89_BAND_2G)
-				rtw89_write_rf(rtwdev, path, RR_SMD, RR_VCO2, 0x0);
-			else
-				rtw89_write_rf(rtwdev, path, RR_SMD, RR_VCO2, 0x1);
-
 			switch (band) {
 			case RTW89_BAND_2G:
 			default:
diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c
index 0b5af9528702..517b66022f18 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.c
+++ b/drivers/net/wireless/realtek/rtw89/sar.c
@@ -57,10 +57,12 @@ static enum rtw89_sar_subband rtw89_sar_get_subband(struct rtw89_dev *rtwdev,
 }
 
 static int rtw89_query_sar_config_common(struct rtw89_dev *rtwdev,
-					 u32 center_freq, s32 *cfg)
+					 const struct rtw89_sar_parm *sar_parm,
+					 s32 *cfg)
 {
 	struct rtw89_sar_cfg_common *rtwsar = &rtwdev->sar.cfg_common;
 	enum rtw89_sar_subband subband_l, subband_h;
+	u32 center_freq = sar_parm->center_freq;
 	const struct rtw89_6ghz_span *span;
 
 	span = rtw89_get_6ghz_span(rtwdev, center_freq);
@@ -90,6 +92,93 @@ static int rtw89_query_sar_config_common(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
+static const struct rtw89_sar_entry_from_acpi *
+rtw89_sar_cfg_acpi_get_ent(const struct rtw89_sar_cfg_acpi *rtwsar,
+			   enum rtw89_rf_path path,
+			   enum rtw89_regulation_type regd)
+{
+	const struct rtw89_sar_indicator_from_acpi *ind = &rtwsar->indicator;
+	const struct rtw89_sar_table_from_acpi *tbl;
+	u8 sel;
+
+	sel = ind->tblsel[path];
+	tbl = &rtwsar->tables[sel];
+
+	return &tbl->entries[regd];
+}
+
+static
+s32 rtw89_sar_cfg_acpi_get_min(const struct rtw89_sar_entry_from_acpi *ent,
+			       enum rtw89_rf_path path,
+			       enum rtw89_acpi_sar_subband subband_low,
+			       enum rtw89_acpi_sar_subband subband_high)
+{
+	return min(ent->v[subband_low][path], ent->v[subband_high][path]);
+}
+
+static int rtw89_query_sar_config_acpi(struct rtw89_dev *rtwdev,
+				       const struct rtw89_sar_parm *sar_parm,
+				       s32 *cfg)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	const struct rtw89_sar_cfg_acpi *rtwsar = &rtwdev->sar.cfg_acpi;
+	const struct rtw89_sar_entry_from_acpi *ent_a, *ent_b;
+	enum rtw89_acpi_sar_subband subband_l, subband_h;
+	u32 center_freq = sar_parm->center_freq;
+	const struct rtw89_6ghz_span *span;
+	enum rtw89_regulation_type regd;
+	enum rtw89_band band;
+	s32 cfg_a, cfg_b;
+
+	span = rtw89_get_6ghz_span(rtwdev, center_freq);
+
+	if (span && RTW89_ACPI_SAR_SPAN_VALID(span)) {
+		subband_l = span->acpi_sar_subband_low;
+		subband_h = span->acpi_sar_subband_high;
+	} else {
+		subband_l = rtw89_acpi_sar_get_subband(rtwdev, center_freq);
+		subband_h = subband_l;
+	}
+
+	band = rtw89_acpi_sar_subband_to_band(rtwdev, subband_l);
+	regd = rtw89_regd_get(rtwdev, band);
+
+	ent_a = rtw89_sar_cfg_acpi_get_ent(rtwsar, RF_PATH_A, regd);
+	ent_b = rtw89_sar_cfg_acpi_get_ent(rtwsar, RF_PATH_B, regd);
+
+	cfg_a = rtw89_sar_cfg_acpi_get_min(ent_a, RF_PATH_A, subband_l, subband_h);
+	cfg_b = rtw89_sar_cfg_acpi_get_min(ent_b, RF_PATH_B, subband_l, subband_h);
+
+	if (chip->support_sar_by_ant) {
+		/* With declaration of support_sar_by_ant, relax the general
+		 * SAR querying to return the maximum between paths. However,
+		 * expect chip has dealt with the corresponding SAR settings
+		 * by path. (To get SAR for a given path, chip can then query
+		 * with force_path.)
+		 */
+		if (sar_parm->force_path) {
+			switch (sar_parm->path) {
+			default:
+			case RF_PATH_A:
+				*cfg = cfg_a;
+				break;
+			case RF_PATH_B:
+				*cfg = cfg_b;
+				break;
+			}
+		} else {
+			*cfg = max(cfg_a, cfg_b);
+		}
+	} else {
+		*cfg = min(cfg_a, cfg_b);
+	}
+
+	if (sar_parm->ntx == RTW89_2TX)
+		*cfg -= rtwsar->downgrade_2tx;
+
+	return 0;
+}
+
 static const
 struct rtw89_sar_handler rtw89_sar_handlers[RTW89_SAR_SOURCE_NR] = {
 	[RTW89_SAR_SOURCE_COMMON] = {
@@ -97,6 +186,11 @@ struct rtw89_sar_handler rtw89_sar_handlers[RTW89_SAR_SOURCE_NR] = {
 		.txpwr_factor_sar = 2,
 		.query_sar_config = rtw89_query_sar_config_common,
 	},
+	[RTW89_SAR_SOURCE_ACPI] = {
+		.descr_sar_source = "RTW89_SAR_SOURCE_ACPI",
+		.txpwr_factor_sar = TXPWR_FACTOR_OF_RTW89_ACPI_SAR,
+		.query_sar_config = rtw89_query_sar_config_acpi,
+	},
 };
 
 #define rtw89_sar_set_src(_dev, _src, _cfg_name, _cfg_data)		\
@@ -175,7 +269,7 @@ static const char *rtw89_tas_state_str(enum rtw89_tas_state state)
 	}
 }
 
-s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq)
+s8 rtw89_query_sar(struct rtw89_dev *rtwdev, const struct rtw89_sar_parm *sar_parm)
 {
 	const enum rtw89_sar_sources src = rtwdev->sar.src;
 	/* its members are protected by rtw89_sar_set_src() */
@@ -191,7 +285,7 @@ s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq)
 	if (src == RTW89_SAR_SOURCE_NONE)
 		return RTW89_SAR_TXPWR_MAC_MAX;
 
-	ret = sar_hdl->query_sar_config(rtwdev, center_freq, &cfg);
+	ret = sar_hdl->query_sar_config(rtwdev, sar_parm, &cfg);
 	if (ret)
 		return RTW89_SAR_TXPWR_MAC_MAX;
 
@@ -215,9 +309,10 @@ s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq)
 
 	return rtw89_txpwr_sar_to_mac(rtwdev, fct, cfg);
 }
+EXPORT_SYMBOL(rtw89_query_sar);
 
 int rtw89_print_sar(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
-		    u32 center_freq)
+		    const struct rtw89_sar_parm *sar_parm)
 {
 	const enum rtw89_sar_sources src = rtwdev->sar.src;
 	/* its members are protected by rtw89_sar_set_src() */
@@ -238,7 +333,7 @@ int rtw89_print_sar(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
 	p += scnprintf(p, end - p, "source: %d (%s)\n", src,
 		       sar_hdl->descr_sar_source);
 
-	ret = sar_hdl->query_sar_config(rtwdev, center_freq, &cfg);
+	ret = sar_hdl->query_sar_config(rtwdev, sar_parm, &cfg);
 	if (ret) {
 		p += scnprintf(p, end - p, "config: return code: %d\n", ret);
 		p += scnprintf(p, end - p,
@@ -252,6 +347,8 @@ int rtw89_print_sar(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
 	p += scnprintf(p, end - p, "config: %d (unit: 1/%lu dBm)\n", cfg,
 		       BIT(fct));
 
+	p += scnprintf(p, end - p, "support different configs by antenna: %s\n",
+		       str_yes_no(rtwdev->chip->support_sar_by_ant));
 out:
 	return p - buf;
 }
@@ -286,16 +383,7 @@ out:
 static int rtw89_apply_sar_common(struct rtw89_dev *rtwdev,
 				  const struct rtw89_sar_cfg_common *sar)
 {
-	enum rtw89_sar_sources src;
-
-	lockdep_assert_wiphy(rtwdev->hw->wiphy);
-
-	src = rtwdev->sar.src;
-	if (src != RTW89_SAR_SOURCE_NONE && src != RTW89_SAR_SOURCE_COMMON) {
-		rtw89_warn(rtwdev, "SAR source: %d is in use", src);
-		return -EBUSY;
-	}
-
+	/* let common SAR have the highest priority; always apply it */
 	rtw89_sar_set_src(rtwdev, RTW89_SAR_SOURCE_COMMON, cfg_common, sar);
 	rtw89_core_set_chip_txpwr(rtwdev);
 	rtw89_tas_reset(rtwdev, false);
@@ -363,18 +451,92 @@ int rtw89_ops_set_sar_specs(struct ieee80211_hw *hw,
 	return rtw89_apply_sar_common(rtwdev, &sar_common);
 }
 
+static void rtw89_apply_sar_acpi(struct rtw89_dev *rtwdev,
+				 const struct rtw89_sar_cfg_acpi *sar)
+{
+	const struct rtw89_sar_table_from_acpi *tbl;
+	const struct rtw89_sar_entry_from_acpi *ent;
+	enum rtw89_sar_sources src;
+	unsigned int i, j, k;
+
+	src = rtwdev->sar.src;
+	if (src != RTW89_SAR_SOURCE_NONE) {
+		rtw89_warn(rtwdev, "SAR source: %d is in use", src);
+		return;
+	}
+
+	rtw89_debug(rtwdev, RTW89_DBG_SAR,
+		    "SAR-ACPI downgrade 2TX: %u (unit: 1/%lu dBm)\n",
+		    sar->downgrade_2tx, BIT(TXPWR_FACTOR_OF_RTW89_ACPI_SAR));
+
+	for (i = 0; i < sar->valid_num; i++) {
+		tbl = &sar->tables[i];
+
+		for (j = 0; j < RTW89_REGD_NUM; j++) {
+			ent = &tbl->entries[j];
+
+			rtw89_debug(rtwdev, RTW89_DBG_SAR,
+				    "SAR-ACPI-[%u] REGD-%s (unit: 1/%lu dBm)\n",
+				    i, rtw89_regd_get_string(j),
+				    BIT(TXPWR_FACTOR_OF_RTW89_ACPI_SAR));
+
+			for (k = 0; k < NUM_OF_RTW89_ACPI_SAR_SUBBAND; k++)
+				rtw89_debug(rtwdev, RTW89_DBG_SAR,
+					    "On subband %u, { %d, %d }\n", k,
+					    ent->v[k][RF_PATH_A], ent->v[k][RF_PATH_B]);
+		}
+	}
+
+	rtw89_sar_set_src(rtwdev, RTW89_SAR_SOURCE_ACPI, cfg_acpi, sar);
+
+	/* SAR via ACPI is only configured in the early initial phase, so
+	 * it does not seem necessary to reset txpwr related things here.
+	 */
+}
+
+static void rtw89_set_sar_from_acpi(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_sar_cfg_acpi *cfg;
+	int ret;
+
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return;
+
+	ret = rtw89_acpi_evaluate_sar(rtwdev, cfg);
+	if (ret) {
+		rtw89_debug(rtwdev, RTW89_DBG_SAR,
+			    "evaluating ACPI SAR returns %d\n", ret);
+		goto out;
+	}
+
+	if (unlikely(!cfg->valid_num)) {
+		rtw89_debug(rtwdev, RTW89_DBG_SAR, "no valid SAR table from ACPI\n");
+		goto out;
+	}
+
+	rtw89_apply_sar_acpi(rtwdev, cfg);
+
+out:
+	kfree(cfg);
+}
+
 static bool rtw89_tas_query_sar_config(struct rtw89_dev *rtwdev, s32 *cfg)
 {
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	const enum rtw89_sar_sources src = rtwdev->sar.src;
 	/* its members are protected by rtw89_sar_set_src() */
 	const struct rtw89_sar_handler *sar_hdl = &rtw89_sar_handlers[src];
+	struct rtw89_sar_parm sar_parm = {};
 	int ret;
 
 	if (src == RTW89_SAR_SOURCE_NONE)
 		return false;
 
-	ret = sar_hdl->query_sar_config(rtwdev, chan->freq, cfg);
+	sar_parm.center_freq = chan->freq;
+	ret = sar_hdl->query_sar_config(rtwdev, &sar_parm, cfg);
 	if (ret)
 		return false;
 
@@ -383,18 +545,27 @@ static bool rtw89_tas_query_sar_config(struct rtw89_dev *rtwdev, s32 *cfg)
 	return true;
 }
 
-static void rtw89_tas_state_update(struct rtw89_dev *rtwdev,
-				   enum rtw89_tas_state state)
+static bool __rtw89_tas_state_update(struct rtw89_dev *rtwdev,
+				     enum rtw89_tas_state state)
 {
 	struct rtw89_tas_info *tas = &rtwdev->tas;
 
 	if (tas->state == state)
-		return;
+		return false;
 
 	rtw89_debug(rtwdev, RTW89_DBG_SAR, "tas: switch state: %s -> %s\n",
 		    rtw89_tas_state_str(tas->state), rtw89_tas_state_str(state));
 
 	tas->state = state;
+	return true;
+}
+
+static void rtw89_tas_state_update(struct rtw89_dev *rtwdev,
+				   enum rtw89_tas_state state)
+{
+	if (!__rtw89_tas_state_update(rtwdev, state))
+		return;
+
 	rtw89_core_set_chip_txpwr(rtwdev);
 }
 
@@ -489,7 +660,7 @@ static void rtw89_tas_history_update(struct rtw89_dev *rtwdev)
 		    rtw89_linear_to_db_quarter(div_u64(txpwr, PERCENT)));
 }
 
-static void rtw89_tas_rolling_average(struct rtw89_dev *rtwdev)
+static bool rtw89_tas_rolling_average(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_tas_info *tas = &rtwdev->tas;
 	s32 dpr_on_threshold, dpr_off_threshold;
@@ -515,18 +686,18 @@ static void rtw89_tas_rolling_average(struct rtw89_dev *rtwdev)
 	else if (txpwr_avg < dpr_off_threshold)
 		state = RTW89_TAS_STATE_DPR_OFF;
 	else
-		return;
+		return false;
 
-	rtw89_tas_state_update(rtwdev, state);
+	return __rtw89_tas_state_update(rtwdev, state);
 }
 
-void rtw89_tas_init(struct rtw89_dev *rtwdev)
+static void rtw89_tas_init(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct rtw89_tas_info *tas = &rtwdev->tas;
+	const struct rtw89_acpi_policy_tas *ptr;
 	struct rtw89_acpi_dsm_result res = {};
 	int ret;
-	u8 val;
 
 	if (!chip->support_tas)
 		return;
@@ -538,8 +709,9 @@ void rtw89_tas_init(struct rtw89_dev *rtwdev)
 		return;
 	}
 
-	val = res.u.value;
-	switch (val) {
+	ptr = res.u.policy_tas;
+
+	switch (ptr->enable) {
 	case 0:
 		tas->enable = false;
 		break;
@@ -552,8 +724,13 @@ void rtw89_tas_init(struct rtw89_dev *rtwdev)
 
 	if (!tas->enable) {
 		rtw89_debug(rtwdev, RTW89_DBG_SAR, "TAS not enable\n");
-		return;
+		goto out;
 	}
+
+	tas->enabled_countries = ptr->enabled_countries;
+
+out:
+	kfree(ptr);
 }
 
 void rtw89_tas_reset(struct rtw89_dev *rtwdev, bool force)
@@ -598,29 +775,28 @@ void rtw89_tas_reset(struct rtw89_dev *rtwdev, bool force)
 		    "tas: band: %u, freq: %u\n", chan->band_type, chan->freq);
 }
 
-void rtw89_tas_track(struct rtw89_dev *rtwdev)
+static bool rtw89_tas_track(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_tas_info *tas = &rtwdev->tas;
 	struct rtw89_hal *hal = &rtwdev->hal;
 	s32 cfg;
 
 	if (hal->disabled_dm_bitmap & BIT(RTW89_DM_TAS))
-		return;
+		return false;
 
 	if (!rtw89_tas_is_active(rtwdev))
-		return;
+		return false;
 
-	if (!rtw89_tas_query_sar_config(rtwdev, &cfg) || tas->block_regd) {
-		rtw89_tas_state_update(rtwdev, RTW89_TAS_STATE_STATIC_SAR);
-		return;
-	}
+	if (!rtw89_tas_query_sar_config(rtwdev, &cfg) || tas->block_regd)
+		return __rtw89_tas_state_update(rtwdev, RTW89_TAS_STATE_STATIC_SAR);
 
 	if (tas->pause)
-		return;
+		return false;
 
 	rtw89_tas_window_update(rtwdev);
 	rtw89_tas_history_update(rtwdev);
-	rtw89_tas_rolling_average(rtwdev);
+
+	return rtw89_tas_rolling_average(rtwdev);
 }
 
 void rtw89_tas_scan(struct rtw89_dev *rtwdev, bool start)
@@ -667,3 +843,51 @@ void rtw89_tas_chanctx_cb(struct rtw89_dev *rtwdev,
 	}
 }
 EXPORT_SYMBOL(rtw89_tas_chanctx_cb);
+
+void rtw89_sar_init(struct rtw89_dev *rtwdev)
+{
+	rtw89_set_sar_from_acpi(rtwdev);
+	rtw89_tas_init(rtwdev);
+}
+
+static bool rtw89_sar_track_acpi(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_sar_cfg_acpi *cfg = &rtwdev->sar.cfg_acpi;
+	struct rtw89_sar_indicator_from_acpi *ind = &cfg->indicator;
+	const enum rtw89_sar_sources src = rtwdev->sar.src;
+	bool changed;
+	int ret;
+
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
+	if (src != RTW89_SAR_SOURCE_ACPI)
+		return false;
+
+	if (!ind->enable_sync)
+		return false;
+
+	ret = rtw89_acpi_evaluate_dynamic_sar_indicator(rtwdev, cfg, &changed);
+	if (likely(!ret))
+		return changed;
+
+	rtw89_debug(rtwdev, RTW89_DBG_SAR,
+		    "%s: failed to track indicator: %d; reset and disable\n",
+		    __func__, ret);
+
+	memset(ind->tblsel, 0, sizeof(ind->tblsel));
+	ind->enable_sync = false;
+	return true;
+}
+
+void rtw89_sar_track(struct rtw89_dev *rtwdev)
+{
+	unsigned int changes = 0;
+
+	changes += rtw89_sar_track_acpi(rtwdev);
+	changes += rtw89_tas_track(rtwdev);
+
+	if (!changes)
+		return;
+
+	rtw89_core_set_chip_txpwr(rtwdev);
+}
diff --git a/drivers/net/wireless/realtek/rtw89/sar.h b/drivers/net/wireless/realtek/rtw89/sar.h
index 0df1661db9a8..4b7f3d44f57b 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.h
+++ b/drivers/net/wireless/realtek/rtw89/sar.h
@@ -10,25 +10,34 @@
 #define RTW89_SAR_TXPWR_MAC_MAX 63
 #define RTW89_SAR_TXPWR_MAC_MIN -64
 
+struct rtw89_sar_parm {
+	u32 center_freq;
+	enum rtw89_ntx ntx;
+
+	bool force_path;
+	enum rtw89_rf_path path;
+};
+
 struct rtw89_sar_handler {
 	const char *descr_sar_source;
 	u8 txpwr_factor_sar;
-	int (*query_sar_config)(struct rtw89_dev *rtwdev, u32 center_freq, s32 *cfg);
+	int (*query_sar_config)(struct rtw89_dev *rtwdev,
+				const struct rtw89_sar_parm *sar_parm, s32 *cfg);
 };
 
 extern const struct cfg80211_sar_capa rtw89_sar_capa;
 
-s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq);
+s8 rtw89_query_sar(struct rtw89_dev *rtwdev, const struct rtw89_sar_parm *sar_parm);
 int rtw89_print_sar(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
-		    u32 center_freq);
+		    const struct rtw89_sar_parm *sar_parm);
 int rtw89_print_tas(struct rtw89_dev *rtwdev, char *buf, size_t bufsz);
 int rtw89_ops_set_sar_specs(struct ieee80211_hw *hw,
 			    const struct cfg80211_sar_specs *sar);
-void rtw89_tas_init(struct rtw89_dev *rtwdev);
 void rtw89_tas_reset(struct rtw89_dev *rtwdev, bool force);
-void rtw89_tas_track(struct rtw89_dev *rtwdev);
 void rtw89_tas_scan(struct rtw89_dev *rtwdev, bool start);
 void rtw89_tas_chanctx_cb(struct rtw89_dev *rtwdev,
 			  enum rtw89_chanctx_state state);
+void rtw89_sar_init(struct rtw89_dev *rtwdev);
+void rtw89_sar_track(struct rtw89_dev *rtwdev);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c
index 0740e303680c..811c91481441 100644
--- a/drivers/net/wireless/realtek/rtw89/ser.c
+++ b/drivers/net/wireless/realtek/rtw89/ser.c
@@ -309,6 +309,9 @@ static void ser_reset_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 		rtw89_core_release_bit_map(rtwdev->hw_port, rtwvif_link->port);
 		rtwvif_link->net_type = RTW89_NET_TYPE_NO_LINK;
 		rtwvif_link->trigger = false;
+		rtwvif_link->rand_tsf_done = false;
+
+		rtw89_p2p_noa_once_deinit(rtwvif_link);
 	}
 }
 
diff --git a/drivers/net/wireless/realtek/rtw89/txrx.h b/drivers/net/wireless/realtek/rtw89/txrx.h
index 70fe7cebc9d5..94f27a9ee9f7 100644
--- a/drivers/net/wireless/realtek/rtw89/txrx.h
+++ b/drivers/net/wireless/realtek/rtw89/txrx.h
@@ -712,6 +712,25 @@ static inline u8 rtw89_core_get_qsel(struct rtw89_dev *rtwdev, u8 tid)
 	}
 }
 
+static inline u8
+rtw89_core_get_qsel_mgmt(struct rtw89_dev *rtwdev, struct rtw89_core_tx_request *tx_req)
+{
+	struct rtw89_tx_desc_info *desc_info = &tx_req->desc_info;
+	struct rtw89_vif_link *rtwvif_link = tx_req->rtwvif_link;
+
+	if (desc_info->hiq) {
+		if (rtwvif_link->mac_idx == RTW89_MAC_1)
+			return RTW89_TX_QSEL_B1_HI;
+		else
+			return RTW89_TX_QSEL_B0_HI;
+	}
+
+	if (rtwvif_link->mac_idx == RTW89_MAC_1)
+		return RTW89_TX_QSEL_B1_MGMT;
+	else
+		return RTW89_TX_QSEL_B0_MGMT;
+}
+
 static inline u8 rtw89_core_get_ch_dma(struct rtw89_dev *rtwdev, u8 qsel)
 {
 	switch (qsel) {
@@ -719,12 +738,24 @@ static inline u8 rtw89_core_get_ch_dma(struct rtw89_dev *rtwdev, u8 qsel)
 		rtw89_warn(rtwdev, "Cannot map qsel to dma: %d\n", qsel);
 		fallthrough;
 	case RTW89_TX_QSEL_BE_0:
+	case RTW89_TX_QSEL_BE_1:
+	case RTW89_TX_QSEL_BE_2:
+	case RTW89_TX_QSEL_BE_3:
 		return RTW89_TXCH_ACH0;
 	case RTW89_TX_QSEL_BK_0:
+	case RTW89_TX_QSEL_BK_1:
+	case RTW89_TX_QSEL_BK_2:
+	case RTW89_TX_QSEL_BK_3:
 		return RTW89_TXCH_ACH1;
 	case RTW89_TX_QSEL_VI_0:
+	case RTW89_TX_QSEL_VI_1:
+	case RTW89_TX_QSEL_VI_2:
+	case RTW89_TX_QSEL_VI_3:
 		return RTW89_TXCH_ACH2;
 	case RTW89_TX_QSEL_VO_0:
+	case RTW89_TX_QSEL_VO_1:
+	case RTW89_TX_QSEL_VO_2:
+	case RTW89_TX_QSEL_VO_3:
 		return RTW89_TXCH_ACH3;
 	case RTW89_TX_QSEL_B0_MGMT:
 		return RTW89_TXCH_CH8;
diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c
index 17eee58503cb..34a0ab49bd7a 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.c
+++ b/drivers/net/wireless/realtek/rtw89/wow.c
@@ -1086,8 +1086,7 @@ static int rtw89_wow_set_wakeups(struct rtw89_dev *rtwdev,
 		rtw89_wow_init_pno(rtwdev, wowlan->nd_config);
 
 	rtw89_for_each_rtwvif(rtwdev, rtwvif) {
-		/* use the link on HW-0 to do wow flow */
-		rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
+		rtwvif_link = rtw89_get_designated_link(rtwvif);
 		if (!rtwvif_link)
 			continue;
 
diff --git a/drivers/net/wireless/ti/wl1251/tx.c b/drivers/net/wireless/ti/wl1251/tx.c
index 474b603c121c..adb4840b0489 100644
--- a/drivers/net/wireless/ti/wl1251/tx.c
+++ b/drivers/net/wireless/ti/wl1251/tx.c
@@ -342,8 +342,10 @@ void wl1251_tx_work(struct work_struct *work)
 	while ((skb = skb_dequeue(&wl->tx_queue))) {
 		if (!woken_up) {
 			ret = wl1251_ps_elp_wakeup(wl);
-			if (ret < 0)
+			if (ret < 0) {
+				skb_queue_head(&wl->tx_queue, skb);
 				goto out;
+			}
 			woken_up = true;
 		}
 
diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index cf3e976471c6..f6add19d1da1 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -1229,6 +1229,11 @@ static void mac80211_hwsim_set_tsf(struct ieee80211_hw *hw,
 	/* MLD not supported here */
 	u32 bcn_int = data->link_data[0].beacon_int;
 	u64 delta = abs(tsf - now);
+	struct ieee80211_bss_conf *conf;
+
+	conf = link_conf_dereference_protected(vif, data->link_data[0].link_id);
+	if (conf && !conf->enable_beacon)
+		return;
 
 	/* adjust after beaconing with new timestamp at old TBTT */
 	if (tsf > now) {
@@ -2273,7 +2278,7 @@ static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac,
 {
 	struct mac80211_hwsim_link_data *link_data = arg;
 	u32 link_id = link_data->link_id;
-	struct ieee80211_bss_conf *link_conf;
+	struct ieee80211_bss_conf *link_conf, *tx_bss_conf;
 	struct mac80211_hwsim_data *data =
 		container_of(link_data, struct mac80211_hwsim_data,
 			     link_data[link_id]);
@@ -2292,10 +2297,11 @@ static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac,
 	    vif->type != NL80211_IFTYPE_OCB)
 		return;
 
-	if (vif->mbssid_tx_vif && vif->mbssid_tx_vif != vif)
+	tx_bss_conf = rcu_access_pointer(link_conf->tx_bss_conf);
+	if (tx_bss_conf && tx_bss_conf != link_conf)
 		return;
 
-	if (vif->bss_conf.ema_ap) {
+	if (link_conf->ema_ap) {
 		struct ieee80211_ema_beacons *ema;
 		u8 i = 0;
 
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index fc52d5c4c69b..5091e1fa4a0d 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -985,20 +985,27 @@ static u32 xennet_run_xdp(struct netfront_queue *queue, struct page *pdata,
 	act = bpf_prog_run_xdp(prog, xdp);
 	switch (act) {
 	case XDP_TX:
-		get_page(pdata);
 		xdpf = xdp_convert_buff_to_frame(xdp);
+		if (unlikely(!xdpf)) {
+			trace_xdp_exception(queue->info->netdev, prog, act);
+			break;
+		}
+		get_page(pdata);
 		err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0);
-		if (unlikely(!err))
+		if (unlikely(err <= 0)) {
+			if (err < 0)
+				trace_xdp_exception(queue->info->netdev, prog, act);
 			xdp_return_frame_rx_napi(xdpf);
-		else if (unlikely(err < 0))
-			trace_xdp_exception(queue->info->netdev, prog, act);
+		}
 		break;
 	case XDP_REDIRECT:
 		get_page(pdata);
 		err = xdp_do_redirect(queue->info->netdev, xdp, prog);
 		*need_xdp_flush = true;
-		if (unlikely(err))
+		if (unlikely(err)) {
 			trace_xdp_exception(queue->info->netdev, prog, act);
+			xdp_return_buff(xdp);
+		}
 		break;
 	case XDP_PASS:
 	case XDP_DROP:
diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c
index aec356880adf..af0fa8bd970b 100644
--- a/drivers/nfc/s3fwrn5/core.c
+++ b/drivers/nfc/s3fwrn5/core.c
@@ -2,7 +2,7 @@
 /*
  * NCI based driver for Samsung S3FWRN5 NFC chip
  *
- * Copyright (C) 2015 Samsung Electrnoics
+ * Copyright (C) 2015 Samsung Electronics
  * Robert Baldyga <r.baldyga@samsung.com>
  */
 
diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c
index c20fdbac51c5..781cdbcac104 100644
--- a/drivers/nfc/s3fwrn5/firmware.c
+++ b/drivers/nfc/s3fwrn5/firmware.c
@@ -2,7 +2,7 @@
 /*
  * NCI based driver for Samsung S3FWRN5 NFC chip
  *
- * Copyright (C) 2015 Samsung Electrnoics
+ * Copyright (C) 2015 Samsung Electronics
  * Robert Baldyga <r.baldyga@samsung.com>
  */
 
diff --git a/drivers/nfc/s3fwrn5/firmware.h b/drivers/nfc/s3fwrn5/firmware.h
index 3a82ce5837fb..19f479aa6920 100644
--- a/drivers/nfc/s3fwrn5/firmware.h
+++ b/drivers/nfc/s3fwrn5/firmware.h
@@ -2,7 +2,7 @@
 /*
  * NCI based driver for Samsung S3FWRN5 NFC chip
  *
- * Copyright (C) 2015 Samsung Electrnoics
+ * Copyright (C) 2015 Samsung Electronics
  * Robert Baldyga <r.baldyga@samsung.com>
  */
 
diff --git a/drivers/nfc/s3fwrn5/i2c.c b/drivers/nfc/s3fwrn5/i2c.c
index 536c566e3f59..110d086cfe5b 100644
--- a/drivers/nfc/s3fwrn5/i2c.c
+++ b/drivers/nfc/s3fwrn5/i2c.c
@@ -2,7 +2,7 @@
 /*
  * I2C Link Layer for Samsung S3FWRN5 NCI based Driver
  *
- * Copyright (C) 2015 Samsung Electrnoics
+ * Copyright (C) 2015 Samsung Electronics
  * Robert Baldyga <r.baldyga@samsung.com>
  */
 
diff --git a/drivers/nfc/s3fwrn5/nci.c b/drivers/nfc/s3fwrn5/nci.c
index ca6828f55ba0..5a9de11bbece 100644
--- a/drivers/nfc/s3fwrn5/nci.c
+++ b/drivers/nfc/s3fwrn5/nci.c
@@ -2,7 +2,7 @@
 /*
  * NCI based driver for Samsung S3FWRN5 NFC chip
  *
- * Copyright (C) 2015 Samsung Electrnoics
+ * Copyright (C) 2015 Samsung Electronics
  * Robert Baldyga <r.baldyga@samsung.com>
  */
 
diff --git a/drivers/nfc/s3fwrn5/nci.h b/drivers/nfc/s3fwrn5/nci.h
index c2d906591e9e..bc4bce2bbc4d 100644
--- a/drivers/nfc/s3fwrn5/nci.h
+++ b/drivers/nfc/s3fwrn5/nci.h
@@ -2,7 +2,7 @@
 /*
  * NCI based driver for Samsung S3FWRN5 NFC chip
  *
- * Copyright (C) 2015 Samsung Electrnoics
+ * Copyright (C) 2015 Samsung Electronics
  * Robert Baldyga <r.baldyga@samsung.com>
  */
 
diff --git a/drivers/nfc/s3fwrn5/phy_common.c b/drivers/nfc/s3fwrn5/phy_common.c
index 81318478d5fd..deb2c039f0fd 100644
--- a/drivers/nfc/s3fwrn5/phy_common.c
+++ b/drivers/nfc/s3fwrn5/phy_common.c
@@ -2,9 +2,9 @@
 /*
  * Link Layer for Samsung S3FWRN5 NCI based Driver
  *
- * Copyright (C) 2015 Samsung Electrnoics
+ * Copyright (C) 2015 Samsung Electronics
  * Robert Baldyga <r.baldyga@samsung.com>
- * Copyright (C) 2020 Samsung Electrnoics
+ * Copyright (C) 2020 Samsung Electronics
  * Bongsu Jeon <bongsu.jeon@samsung.com>
  */
 
diff --git a/drivers/nfc/s3fwrn5/phy_common.h b/drivers/nfc/s3fwrn5/phy_common.h
index 99749c9294d1..9cef25436bf9 100644
--- a/drivers/nfc/s3fwrn5/phy_common.h
+++ b/drivers/nfc/s3fwrn5/phy_common.h
@@ -2,9 +2,9 @@
  *
  * Link Layer for Samsung S3FWRN5 NCI based Driver
  *
- * Copyright (C) 2015 Samsung Electrnoics
+ * Copyright (C) 2015 Samsung Electronics
  * Robert Baldyga <r.baldyga@samsung.com>
- * Copyright (C) 2020 Samsung Electrnoics
+ * Copyright (C) 2020 Samsung Electronics
  * Bongsu Jeon <bongsu.jeon@samsung.com>
  */
 
diff --git a/drivers/nfc/s3fwrn5/s3fwrn5.h b/drivers/nfc/s3fwrn5/s3fwrn5.h
index bb8f936d13a2..2b492236090b 100644
--- a/drivers/nfc/s3fwrn5/s3fwrn5.h
+++ b/drivers/nfc/s3fwrn5/s3fwrn5.h
@@ -2,7 +2,7 @@
 /*
  * NCI based driver for Samsung S3FWRN5 NFC chip
  *
- * Copyright (C) 2015 Samsung Electrnoics
+ * Copyright (C) 2015 Samsung Electronics
  * Robert Baldyga <r.baldyga@samsung.com>
  */
 
diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c
index 6b89d596ba9a..9ef8ef2d4363 100644
--- a/drivers/nfc/virtual_ncidev.c
+++ b/drivers/nfc/virtual_ncidev.c
@@ -2,7 +2,7 @@
 /*
  * Virtual NCI device simulation driver
  *
- * Copyright (C) 2020 Samsung Electrnoics
+ * Copyright (C) 2020 Samsung Electronics
  * Bongsu Jeon <bongsu.jeon@samsung.com>
  */
 
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index d47dfa80fb95..7dca58f0a237 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -84,9 +84,9 @@ config NVME_TCP
 	tristate "NVM Express over Fabrics TCP host driver"
 	depends on INET
 	depends on BLOCK
+	select CRC32
+	select NET_CRC32C
 	select NVME_FABRICS
-	select CRYPTO
-	select CRYPTO_CRC32C
 	help
 	  This provides support for the NVMe over Fabrics protocol using
 	  the TCP transport.  This allows you to use remote block devices
@@ -102,6 +102,7 @@ config NVME_TCP_TLS
 	depends on NVME_TCP
 	select NET_HANDSHAKE
 	select KEYS
+	select TLS
 	help
 	  Enables TLS encryption for NVMe TCP using the netlink handshake API.
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index cc23035148b4..6b04473c0ab7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2059,7 +2059,21 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
 		if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
 			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
 		else
-			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+			atomic_bs = (1 + ns->ctrl->awupf) * bs;
+
+		/*
+		 * Set subsystem atomic bs.
+		 */
+		if (ns->ctrl->subsys->atomic_bs) {
+			if (atomic_bs != ns->ctrl->subsys->atomic_bs) {
+				dev_err_ratelimited(ns->ctrl->device,
+					"%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n",
+					ns->disk ? ns->disk->disk_name : "?",
+					ns->ctrl->subsys->atomic_bs,
+					atomic_bs);
+			}
+		} else
+			ns->ctrl->subsys->atomic_bs = atomic_bs;
 
 		nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs);
 	}
@@ -2201,6 +2215,17 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	nvme_set_chunk_sectors(ns, id, &lim);
 	if (!nvme_update_disk_info(ns, id, &lim))
 		capacity = 0;
+
+	/*
+	 * Validate the max atomic write size fits within the subsystem's
+	 * atomic write capabilities.
+	 */
+	if (lim.atomic_write_hw_max > ns->ctrl->subsys->atomic_bs) {
+		blk_mq_unfreeze_queue(ns->disk->queue, memflags);
+		ret = -ENXIO;
+		goto out;
+	}
+
 	nvme_config_discard(ns, &lim);
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
 	    ns->head->ids.csi == NVME_CSI_ZNS)
@@ -3031,7 +3056,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 		kfree(subsys);
 		return -EINVAL;
 	}
-	subsys->awupf = le16_to_cpu(id->awupf);
 	nvme_mpath_default_iopolicy(subsys);
 
 	subsys->dev.class = &nvme_subsys_class;
@@ -3441,7 +3465,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 		dev_pm_qos_expose_latency_tolerance(ctrl->device);
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
 		dev_pm_qos_hide_latency_tolerance(ctrl->device);
-
+	ctrl->awupf = le16_to_cpu(id->awupf);
 out_free:
 	kfree(id);
 	return ret;
@@ -4295,6 +4319,15 @@ static void nvme_scan_work(struct work_struct *work)
 			nvme_scan_ns_sequential(ctrl);
 	}
 	mutex_unlock(&ctrl->scan_lock);
+
+	/* Requeue if we have missed AENs */
+	if (test_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events))
+		nvme_queue_scan(ctrl);
+#ifdef CONFIG_NVME_MULTIPATH
+	else if (ctrl->ana_log_buf)
+		/* Re-read the ANA log page to not miss updates */
+		queue_work(nvme_wq, &ctrl->ana_work);
+#endif
 }
 
 /*
@@ -4484,7 +4517,8 @@ static void nvme_fw_act_work(struct work_struct *work)
 		msleep(100);
 	}
 
-	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE))
+	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING) ||
+	    !nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE))
 		return;
 
 	nvme_unquiesce_io_queues(ctrl);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 89be5911b25d..cf0ef4745564 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -427,7 +427,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	struct nvme_ns *ns;
 
 	if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
-		return NULL;
+		return false;
 
 	list_for_each_entry_srcu(ns, &head->list, siblings,
 				 srcu_read_lock_held(&head->srcu)) {
@@ -638,7 +638,8 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 
 	blk_set_stacking_limits(&lim);
 	lim.dma_alignment = 3;
-	lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL;
+	lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT |
+		BLK_FEAT_POLL | BLK_FEAT_ATOMIC_WRITES;
 	if (head->ids.csi == NVME_CSI_ZNS)
 		lim.features |= BLK_FEAT_ZONED;
 
@@ -1051,6 +1052,13 @@ void nvme_mpath_add_sysfs_link(struct nvme_ns_head *head)
 
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
 		/*
+		 * Ensure that ns path disk node is already added otherwise we
+		 * may get invalid kobj name for target
+		 */
+		if (!test_bit(GD_ADDED, &ns->disk->state))
+			continue;
+
+		/*
 		 * Avoid creating link if it already exists for the given path.
 		 * When path ana state transitions from optimized to non-
 		 * optimized or vice-versa, the nvme_mpath_set_live() is
@@ -1065,13 +1073,6 @@ void nvme_mpath_add_sysfs_link(struct nvme_ns_head *head)
 		if (test_and_set_bit(NVME_NS_SYSFS_ATTR_LINK, &ns->flags))
 			continue;
 
-		/*
-		 * Ensure that ns path disk node is already added otherwise we
-		 * may get invalid kobj name for target
-		 */
-		if (!test_bit(GD_ADDED, &ns->disk->state))
-			continue;
-
 		target = disk_to_dev(ns->disk);
 		/*
 		 * Create sysfs link from head gendisk kobject @kobj to the
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 51e078642127..8fc4683418a3 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -410,6 +410,7 @@ struct nvme_ctrl {
 
 	enum nvme_ctrl_type cntrltype;
 	enum nvme_dctype dctype;
+	u16 awupf; /* 0's based value. */
 };
 
 static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
@@ -442,11 +443,11 @@ struct nvme_subsystem {
 	u8			cmic;
 	enum nvme_subsys_type	subtype;
 	u16			vendor_id;
-	u16			awupf;	/* 0's based awupf value. */
 	struct ida		ns_ida;
 #ifdef CONFIG_NVME_MULTIPATH
 	enum nvme_iopolicy	iopolicy;
 #endif
+	u32			atomic_bs;
 };
 
 /*
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index b178d52eac1b..f1dd804151b1 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -390,7 +390,7 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db,
  * as it only leads to a small amount of wasted memory for the lifetime of
  * the I/O.
  */
-static int nvme_pci_npages_prp(void)
+static __always_inline int nvme_pci_npages_prp(void)
 {
 	unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE;
 	unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE);
@@ -1202,7 +1202,9 @@ static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
 	WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
 
 	disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
+	spin_lock(&nvmeq->cq_poll_lock);
 	nvme_poll_cq(nvmeq, NULL);
+	spin_unlock(&nvmeq->cq_poll_lock);
 	enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
 }
 
@@ -3575,7 +3577,7 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
 
 	dev_info(dev->ctrl.device, "restart after slot reset\n");
 	pci_restore_state(pdev);
-	if (!nvme_try_sched_reset(&dev->ctrl))
+	if (nvme_try_sched_reset(&dev->ctrl))
 		nvme_unquiesce_io_queues(&dev->ctrl);
 	return PCI_ERS_RESULT_RECOVERED;
 }
@@ -3623,6 +3625,9 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1217, 0x8760), /* O2 Micro 64GB Steam Deck */
 		.driver_data = NVME_QUIRK_DMAPOOL_ALIGN_512, },
+	{ PCI_DEVICE(0x126f, 0x1001),	/* Silicon Motion generic */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x126f, 0x2262),	/* Silicon Motion generic */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_BOGUS_NID, },
@@ -3646,6 +3651,9 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x15b7, 0x5008),   /* Sandisk SN530 */
 		.driver_data = NVME_QUIRK_BROKEN_MSI },
+	{ PCI_DEVICE(0x15b7, 0x5009),   /* Sandisk SN550 */
+		.driver_data = NVME_QUIRK_BROKEN_MSI |
+				NVME_QUIRK_NO_DEEPEST_PS },
 	{ PCI_DEVICE(0x1987, 0x5012),	/* Phison E12 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1987, 0x5016),	/* Phison E16 */
@@ -3731,6 +3739,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
 	{ PCI_DEVICE(0x1e49, 0x0041),   /* ZHITAI TiPro7000 NVMe SSD */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
+	{ PCI_DEVICE(0x025e, 0xf1ac),   /* SOLIDIGM  P44 pro SSDPFKKW020X7  */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
 	{ PCI_DEVICE(0xc0a9, 0x540a),   /* Crucial P2 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1d97, 0x2263), /* Lexar NM610 */
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 26c459f0198d..8ae6cc2280ca 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/crc32.h>
 #include <linux/nvme-tcp.h>
 #include <linux/nvme-keyring.h>
 #include <net/sock.h>
@@ -16,7 +17,6 @@
 #include <net/tls_prot.h>
 #include <net/handshake.h>
 #include <linux/blk-mq.h>
-#include <crypto/hash.h>
 #include <net/busy_poll.h>
 #include <trace/events/sock.h>
 
@@ -168,8 +168,8 @@ struct nvme_tcp_queue {
 	bool			hdr_digest;
 	bool			data_digest;
 	bool			tls_enabled;
-	struct ahash_request	*rcv_hash;
-	struct ahash_request	*snd_hash;
+	u32			rcv_crc;
+	u32			snd_crc;
 	__le32			exp_ddgst;
 	__le32			recv_ddgst;
 	struct completion       tls_complete;
@@ -456,32 +456,38 @@ nvme_tcp_fetch_request(struct nvme_tcp_queue *queue)
 	return req;
 }
 
-static inline void nvme_tcp_ddgst_final(struct ahash_request *hash,
-		__le32 *dgst)
+#define NVME_TCP_CRC_SEED (~0)
+
+static inline void nvme_tcp_ddgst_update(u32 *crcp,
+		struct page *page, size_t off, size_t len)
 {
-	ahash_request_set_crypt(hash, NULL, (u8 *)dgst, 0);
-	crypto_ahash_final(hash);
+	page += off / PAGE_SIZE;
+	off %= PAGE_SIZE;
+	while (len) {
+		const void *vaddr = kmap_local_page(page);
+		size_t n = min(len, (size_t)PAGE_SIZE - off);
+
+		*crcp = crc32c(*crcp, vaddr + off, n);
+		kunmap_local(vaddr);
+		page++;
+		off = 0;
+		len -= n;
+	}
 }
 
-static inline void nvme_tcp_ddgst_update(struct ahash_request *hash,
-		struct page *page, off_t off, size_t len)
+static inline __le32 nvme_tcp_ddgst_final(u32 crc)
 {
-	struct scatterlist sg;
-
-	sg_init_table(&sg, 1);
-	sg_set_page(&sg, page, len, off);
-	ahash_request_set_crypt(hash, &sg, NULL, len);
-	crypto_ahash_update(hash);
+	return cpu_to_le32(~crc);
 }
 
-static inline void nvme_tcp_hdgst(struct ahash_request *hash,
-		void *pdu, size_t len)
+static inline __le32 nvme_tcp_hdgst(const void *pdu, size_t len)
 {
-	struct scatterlist sg;
+	return cpu_to_le32(~crc32c(NVME_TCP_CRC_SEED, pdu, len));
+}
 
-	sg_init_one(&sg, pdu, len);
-	ahash_request_set_crypt(hash, &sg, pdu + len, len);
-	crypto_ahash_digest(hash);
+static inline void nvme_tcp_set_hdgst(void *pdu, size_t len)
+{
+	*(__le32 *)(pdu + len) = nvme_tcp_hdgst(pdu, len);
 }
 
 static int nvme_tcp_verify_hdgst(struct nvme_tcp_queue *queue,
@@ -499,8 +505,7 @@ static int nvme_tcp_verify_hdgst(struct nvme_tcp_queue *queue,
 	}
 
 	recv_digest = *(__le32 *)(pdu + hdr->hlen);
-	nvme_tcp_hdgst(queue->rcv_hash, pdu, pdu_len);
-	exp_digest = *(__le32 *)(pdu + hdr->hlen);
+	exp_digest = nvme_tcp_hdgst(pdu, pdu_len);
 	if (recv_digest != exp_digest) {
 		dev_err(queue->ctrl->ctrl.device,
 			"header digest error: recv %#x expected %#x\n",
@@ -526,7 +531,7 @@ static int nvme_tcp_check_ddgst(struct nvme_tcp_queue *queue, void *pdu)
 		nvme_tcp_queue_id(queue));
 		return -EPROTO;
 	}
-	crypto_ahash_init(queue->rcv_hash);
+	queue->rcv_crc = NVME_TCP_CRC_SEED;
 
 	return 0;
 }
@@ -926,8 +931,8 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 				iov_iter_count(&req->iter));
 
 		if (queue->data_digest)
-			ret = skb_copy_and_hash_datagram_iter(skb, *offset,
-				&req->iter, recv_len, queue->rcv_hash);
+			ret = skb_copy_and_crc32c_datagram_iter(skb, *offset,
+				&req->iter, recv_len, &queue->rcv_crc);
 		else
 			ret = skb_copy_datagram_iter(skb, *offset,
 					&req->iter, recv_len);
@@ -945,7 +950,7 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 
 	if (!queue->data_remaining) {
 		if (queue->data_digest) {
-			nvme_tcp_ddgst_final(queue->rcv_hash, &queue->exp_ddgst);
+			queue->exp_ddgst = nvme_tcp_ddgst_final(queue->rcv_crc);
 			queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH;
 		} else {
 			if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
@@ -1147,7 +1152,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 			return ret;
 
 		if (queue->data_digest)
-			nvme_tcp_ddgst_update(queue->snd_hash, page,
+			nvme_tcp_ddgst_update(&queue->snd_crc, page,
 					offset, ret);
 
 		/*
@@ -1161,8 +1166,8 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 		/* fully successful last send in current PDU */
 		if (last && ret == len) {
 			if (queue->data_digest) {
-				nvme_tcp_ddgst_final(queue->snd_hash,
-					&req->ddgst);
+				req->ddgst =
+					nvme_tcp_ddgst_final(queue->snd_crc);
 				req->state = NVME_TCP_SEND_DDGST;
 				req->offset = 0;
 			} else {
@@ -1194,7 +1199,7 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
 		msg.msg_flags |= MSG_EOR;
 
 	if (queue->hdr_digest && !req->offset)
-		nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
+		nvme_tcp_set_hdgst(pdu, sizeof(*pdu));
 
 	bvec_set_virt(&bvec, (void *)pdu + req->offset, len);
 	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len);
@@ -1207,7 +1212,7 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
 		if (inline_data) {
 			req->state = NVME_TCP_SEND_DATA;
 			if (queue->data_digest)
-				crypto_ahash_init(queue->snd_hash);
+				queue->snd_crc = NVME_TCP_CRC_SEED;
 		} else {
 			nvme_tcp_done_send_req(queue);
 		}
@@ -1229,7 +1234,7 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
 	int ret;
 
 	if (queue->hdr_digest && !req->offset)
-		nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
+		nvme_tcp_set_hdgst(pdu, sizeof(*pdu));
 
 	if (!req->h2cdata_left)
 		msg.msg_flags |= MSG_SPLICE_PAGES;
@@ -1244,7 +1249,7 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
 	if (!len) {
 		req->state = NVME_TCP_SEND_DATA;
 		if (queue->data_digest)
-			crypto_ahash_init(queue->snd_hash);
+			queue->snd_crc = NVME_TCP_CRC_SEED;
 		return 1;
 	}
 	req->offset += ret;
@@ -1384,41 +1389,6 @@ static void nvme_tcp_io_work(struct work_struct *w)
 	queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
 }
 
-static void nvme_tcp_free_crypto(struct nvme_tcp_queue *queue)
-{
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(queue->rcv_hash);
-
-	ahash_request_free(queue->rcv_hash);
-	ahash_request_free(queue->snd_hash);
-	crypto_free_ahash(tfm);
-}
-
-static int nvme_tcp_alloc_crypto(struct nvme_tcp_queue *queue)
-{
-	struct crypto_ahash *tfm;
-
-	tfm = crypto_alloc_ahash("crc32c", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(tfm))
-		return PTR_ERR(tfm);
-
-	queue->snd_hash = ahash_request_alloc(tfm, GFP_KERNEL);
-	if (!queue->snd_hash)
-		goto free_tfm;
-	ahash_request_set_callback(queue->snd_hash, 0, NULL, NULL);
-
-	queue->rcv_hash = ahash_request_alloc(tfm, GFP_KERNEL);
-	if (!queue->rcv_hash)
-		goto free_snd_hash;
-	ahash_request_set_callback(queue->rcv_hash, 0, NULL, NULL);
-
-	return 0;
-free_snd_hash:
-	ahash_request_free(queue->snd_hash);
-free_tfm:
-	crypto_free_ahash(tfm);
-	return -ENOMEM;
-}
-
 static void nvme_tcp_free_async_req(struct nvme_tcp_ctrl *ctrl)
 {
 	struct nvme_tcp_request *async = &ctrl->async_req;
@@ -1451,9 +1421,6 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
 	if (!test_and_clear_bit(NVME_TCP_Q_ALLOCATED, &queue->flags))
 		return;
 
-	if (queue->hdr_digest || queue->data_digest)
-		nvme_tcp_free_crypto(queue);
-
 	page_frag_cache_drain(&queue->pf_cache);
 
 	noreclaim_flag = memalloc_noreclaim_save();
@@ -1803,6 +1770,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 		ret = PTR_ERR(sock_file);
 		goto err_destroy_mutex;
 	}
+
+	sk_net_refcnt_upgrade(queue->sock->sk);
 	nvme_tcp_reclassify_socket(queue->sock);
 
 	/* Single syn retry */
@@ -1865,21 +1834,13 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 
 	queue->hdr_digest = nctrl->opts->hdr_digest;
 	queue->data_digest = nctrl->opts->data_digest;
-	if (queue->hdr_digest || queue->data_digest) {
-		ret = nvme_tcp_alloc_crypto(queue);
-		if (ret) {
-			dev_err(nctrl->device,
-				"failed to allocate queue %d crypto\n", qid);
-			goto err_sock;
-		}
-	}
 
 	rcv_pdu_size = sizeof(struct nvme_tcp_rsp_pdu) +
 			nvme_tcp_hdgst_len(queue);
 	queue->pdu = kmalloc(rcv_pdu_size, GFP_KERNEL);
 	if (!queue->pdu) {
 		ret = -ENOMEM;
-		goto err_crypto;
+		goto err_sock;
 	}
 
 	dev_dbg(nctrl->device, "connecting queue %d\n",
@@ -1912,9 +1873,6 @@ err_init_connect:
 	kernel_sock_shutdown(queue->sock, SHUT_RDWR);
 err_rcv_pdu:
 	kfree(queue->pdu);
-err_crypto:
-	if (queue->hdr_digest || queue->data_digest)
-		nvme_tcp_free_crypto(queue);
 err_sock:
 	/* ->sock will be released by fput() */
 	fput(queue->sock->file);
@@ -1944,7 +1902,7 @@ static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue)
 	cancel_work_sync(&queue->io_work);
 }
 
-static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
+static void nvme_tcp_stop_queue_nowait(struct nvme_ctrl *nctrl, int qid)
 {
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
@@ -1963,6 +1921,31 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
 	mutex_unlock(&queue->queue_lock);
 }
 
+static void nvme_tcp_wait_queue(struct nvme_ctrl *nctrl, int qid)
+{
+	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
+	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
+	int timeout = 100;
+
+	while (timeout > 0) {
+		if (!test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags) ||
+		    !sk_wmem_alloc_get(queue->sock->sk))
+			return;
+		msleep(2);
+		timeout -= 2;
+	}
+	dev_warn(nctrl->device,
+		 "qid %d: timeout draining sock wmem allocation expired\n",
+		 qid);
+}
+
+static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
+{
+	nvme_tcp_stop_queue_nowait(nctrl, qid);
+	nvme_tcp_wait_queue(nctrl, qid);
+}
+
+
 static void nvme_tcp_setup_sock_ops(struct nvme_tcp_queue *queue)
 {
 	write_lock_bh(&queue->sock->sk->sk_callback_lock);
@@ -2030,7 +2013,9 @@ static void nvme_tcp_stop_io_queues(struct nvme_ctrl *ctrl)
 	int i;
 
 	for (i = 1; i < ctrl->queue_count; i++)
-		nvme_tcp_stop_queue(ctrl, i);
+		nvme_tcp_stop_queue_nowait(ctrl, i);
+	for (i = 1; i < ctrl->queue_count; i++)
+		nvme_tcp_wait_queue(ctrl, i);
 }
 
 static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl,
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index fb7446d6d682..4c253b433bf7 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -98,6 +98,7 @@ config NVME_TARGET_TCP_TLS
 	bool "NVMe over Fabrics TCP target TLS encryption support"
 	depends on NVME_TARGET_TCP
 	select NET_HANDSHAKE
+	select TLS
 	help
 	  Enables TLS encryption for the NVMe TCP target using the netlink handshake API.
 
diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c
index 0b0645ac5df4..9429b8218408 100644
--- a/drivers/nvme/target/auth.c
+++ b/drivers/nvme/target/auth.c
@@ -240,7 +240,7 @@ void nvmet_auth_sq_free(struct nvmet_sq *sq)
 {
 	cancel_delayed_work(&sq->auth_expired_work);
 #ifdef CONFIG_NVME_TARGET_TCP_TLS
-	sq->tls_key = 0;
+	sq->tls_key = NULL;
 #endif
 	kfree(sq->dhchap_c1);
 	sq->dhchap_c1 = NULL;
@@ -600,13 +600,12 @@ void nvmet_auth_insert_psk(struct nvmet_sq *sq)
 		pr_warn("%s: ctrl %d qid %d failed to refresh key, error %ld\n",
 			__func__, sq->ctrl->cntlid, sq->qid, PTR_ERR(tls_key));
 		tls_key = NULL;
-		kfree_sensitive(tls_psk);
 	}
 	if (sq->ctrl->tls_key)
 		key_put(sq->ctrl->tls_key);
 	sq->ctrl->tls_key = tls_key;
 #endif
-
+	kfree_sensitive(tls_psk);
 out_free_digest:
 	kfree_sensitive(digest);
 out_free_psk:
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 71f8d06998d6..245475c43127 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -324,6 +324,9 @@ int nvmet_enable_port(struct nvmet_port *port)
 
 	lockdep_assert_held(&nvmet_config_sem);
 
+	if (port->disc_addr.trtype == NVMF_TRTYPE_MAX)
+		return -EINVAL;
+
 	ops = nvmet_transports[port->disc_addr.trtype];
 	if (!ops) {
 		up_write(&nvmet_config_sem);
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 7318b736d414..7b50130f10f6 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -995,16 +995,6 @@ nvmet_fc_hostport_get(struct nvmet_fc_hostport *hostport)
 	return kref_get_unless_zero(&hostport->ref);
 }
 
-static void
-nvmet_fc_free_hostport(struct nvmet_fc_hostport *hostport)
-{
-	/* if LLDD not implemented, leave as NULL */
-	if (!hostport || !hostport->hosthandle)
-		return;
-
-	nvmet_fc_hostport_put(hostport);
-}
-
 static struct nvmet_fc_hostport *
 nvmet_fc_match_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 {
@@ -1028,33 +1018,24 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 	struct nvmet_fc_hostport *newhost, *match = NULL;
 	unsigned long flags;
 
+	/*
+	 * Caller holds a reference on tgtport.
+	 */
+
 	/* if LLDD not implemented, leave as NULL */
 	if (!hosthandle)
 		return NULL;
 
-	/*
-	 * take reference for what will be the newly allocated hostport if
-	 * we end up using a new allocation
-	 */
-	if (!nvmet_fc_tgtport_get(tgtport))
-		return ERR_PTR(-EINVAL);
-
 	spin_lock_irqsave(&tgtport->lock, flags);
 	match = nvmet_fc_match_hostport(tgtport, hosthandle);
 	spin_unlock_irqrestore(&tgtport->lock, flags);
 
-	if (match) {
-		/* no new allocation - release reference */
-		nvmet_fc_tgtport_put(tgtport);
+	if (match)
 		return match;
-	}
 
 	newhost = kzalloc(sizeof(*newhost), GFP_KERNEL);
-	if (!newhost) {
-		/* no new allocation - release reference */
-		nvmet_fc_tgtport_put(tgtport);
+	if (!newhost)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	spin_lock_irqsave(&tgtport->lock, flags);
 	match = nvmet_fc_match_hostport(tgtport, hosthandle);
@@ -1063,6 +1044,7 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 		kfree(newhost);
 		newhost = match;
 	} else {
+		nvmet_fc_tgtport_get(tgtport);
 		newhost->tgtport = tgtport;
 		newhost->hosthandle = hosthandle;
 		INIT_LIST_HEAD(&newhost->host_list);
@@ -1076,20 +1058,14 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 }
 
 static void
-nvmet_fc_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
-{
-	nvmet_fc_delete_target_assoc(assoc);
-	nvmet_fc_tgt_a_put(assoc);
-}
-
-static void
 nvmet_fc_delete_assoc_work(struct work_struct *work)
 {
 	struct nvmet_fc_tgt_assoc *assoc =
 		container_of(work, struct nvmet_fc_tgt_assoc, del_work);
 	struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
 
-	nvmet_fc_delete_assoc(assoc);
+	nvmet_fc_delete_target_assoc(assoc);
+	nvmet_fc_tgt_a_put(assoc);
 	nvmet_fc_tgtport_put(tgtport);
 }
 
@@ -1097,7 +1073,8 @@ static void
 nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
 {
 	nvmet_fc_tgtport_get(assoc->tgtport);
-	queue_work(nvmet_wq, &assoc->del_work);
+	if (!queue_work(nvmet_wq, &assoc->del_work))
+		nvmet_fc_tgtport_put(assoc->tgtport);
 }
 
 static bool
@@ -1143,6 +1120,7 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 		goto out_ida;
 
 	assoc->tgtport = tgtport;
+	nvmet_fc_tgtport_get(tgtport);
 	assoc->a_id = idx;
 	INIT_LIST_HEAD(&assoc->a_list);
 	kref_init(&assoc->ref);
@@ -1190,7 +1168,7 @@ nvmet_fc_target_assoc_free(struct kref *ref)
 	/* Send Disconnect now that all i/o has completed */
 	nvmet_fc_xmt_disconnect_assoc(assoc);
 
-	nvmet_fc_free_hostport(assoc->hostport);
+	nvmet_fc_hostport_put(assoc->hostport);
 	spin_lock_irqsave(&tgtport->lock, flags);
 	oldls = assoc->rcv_disconn;
 	spin_unlock_irqrestore(&tgtport->lock, flags);
@@ -1244,6 +1222,8 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc)
 	dev_info(tgtport->dev,
 		"{%d:%d} Association deleted\n",
 		tgtport->fc_target_port.port_num, assoc->a_id);
+
+	nvmet_fc_tgtport_put(tgtport);
 }
 
 static struct nvmet_fc_tgt_assoc *
@@ -1455,11 +1435,6 @@ nvmet_fc_free_tgtport(struct kref *ref)
 	struct nvmet_fc_tgtport *tgtport =
 		container_of(ref, struct nvmet_fc_tgtport, ref);
 	struct device *dev = tgtport->dev;
-	unsigned long flags;
-
-	spin_lock_irqsave(&nvmet_fc_tgtlock, flags);
-	list_del(&tgtport->tgt_list);
-	spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags);
 
 	nvmet_fc_free_ls_iodlist(tgtport);
 
@@ -1620,6 +1595,11 @@ int
 nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *target_port)
 {
 	struct nvmet_fc_tgtport *tgtport = targetport_to_tgtport(target_port);
+	unsigned long flags;
+
+	spin_lock_irqsave(&nvmet_fc_tgtlock, flags);
+	list_del(&tgtport->tgt_list);
+	spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags);
 
 	nvmet_fc_portentry_unbind_tgt(tgtport);
 
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index e1abb27927ff..641201e62c1b 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -208,6 +208,7 @@ struct fcloop_lport {
 	struct nvme_fc_local_port *localport;
 	struct list_head lport_list;
 	struct completion unreg_done;
+	refcount_t ref;
 };
 
 struct fcloop_lport_priv {
@@ -239,7 +240,7 @@ struct fcloop_nport {
 	struct fcloop_tport *tport;
 	struct fcloop_lport *lport;
 	struct list_head nport_list;
-	struct kref ref;
+	refcount_t ref;
 	u64 node_name;
 	u64 port_name;
 	u32 port_role;
@@ -274,7 +275,7 @@ struct fcloop_fcpreq {
 	u32				inistate;
 	bool				active;
 	bool				aborted;
-	struct kref			ref;
+	refcount_t			ref;
 	struct work_struct		fcp_rcv_work;
 	struct work_struct		abort_rcv_work;
 	struct work_struct		tio_done_work;
@@ -478,7 +479,7 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport,
 	if (targetport) {
 		tport = targetport->private;
 		spin_lock(&tport->lock);
-		list_add_tail(&tport->ls_list, &tls_req->ls_list);
+		list_add_tail(&tls_req->ls_list, &tport->ls_list);
 		spin_unlock(&tport->lock);
 		queue_work(nvmet_wq, &tport->ls_work);
 	}
@@ -534,24 +535,18 @@ fcloop_tgt_discovery_evt(struct nvmet_fc_target_port *tgtport)
 }
 
 static void
-fcloop_tfcp_req_free(struct kref *ref)
+fcloop_tfcp_req_put(struct fcloop_fcpreq *tfcp_req)
 {
-	struct fcloop_fcpreq *tfcp_req =
-		container_of(ref, struct fcloop_fcpreq, ref);
+	if (!refcount_dec_and_test(&tfcp_req->ref))
+		return;
 
 	kfree(tfcp_req);
 }
 
-static void
-fcloop_tfcp_req_put(struct fcloop_fcpreq *tfcp_req)
-{
-	kref_put(&tfcp_req->ref, fcloop_tfcp_req_free);
-}
-
 static int
 fcloop_tfcp_req_get(struct fcloop_fcpreq *tfcp_req)
 {
-	return kref_get_unless_zero(&tfcp_req->ref);
+	return refcount_inc_not_zero(&tfcp_req->ref);
 }
 
 static void
@@ -748,7 +743,7 @@ fcloop_fcp_req(struct nvme_fc_local_port *localport,
 	INIT_WORK(&tfcp_req->fcp_rcv_work, fcloop_fcp_recv_work);
 	INIT_WORK(&tfcp_req->abort_rcv_work, fcloop_fcp_abort_recv_work);
 	INIT_WORK(&tfcp_req->tio_done_work, fcloop_tgt_fcprqst_done_work);
-	kref_init(&tfcp_req->ref);
+	refcount_set(&tfcp_req->ref, 1);
 
 	queue_work(nvmet_wq, &tfcp_req->fcp_rcv_work);
 
@@ -1001,24 +996,39 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
 }
 
 static void
-fcloop_nport_free(struct kref *ref)
+fcloop_lport_put(struct fcloop_lport *lport)
 {
-	struct fcloop_nport *nport =
-		container_of(ref, struct fcloop_nport, ref);
+	unsigned long flags;
 
-	kfree(nport);
+	if (!refcount_dec_and_test(&lport->ref))
+		return;
+
+	spin_lock_irqsave(&fcloop_lock, flags);
+	list_del(&lport->lport_list);
+	spin_unlock_irqrestore(&fcloop_lock, flags);
+
+	kfree(lport);
+}
+
+static int
+fcloop_lport_get(struct fcloop_lport *lport)
+{
+	return refcount_inc_not_zero(&lport->ref);
 }
 
 static void
 fcloop_nport_put(struct fcloop_nport *nport)
 {
-	kref_put(&nport->ref, fcloop_nport_free);
+	if (!refcount_dec_and_test(&nport->ref))
+		return;
+
+	kfree(nport);
 }
 
 static int
 fcloop_nport_get(struct fcloop_nport *nport)
 {
-	return kref_get_unless_zero(&nport->ref);
+	return refcount_inc_not_zero(&nport->ref);
 }
 
 static void
@@ -1029,6 +1039,8 @@ fcloop_localport_delete(struct nvme_fc_local_port *localport)
 
 	/* release any threads waiting for the unreg to complete */
 	complete(&lport->unreg_done);
+
+	fcloop_lport_put(lport);
 }
 
 static void
@@ -1140,6 +1152,7 @@ fcloop_create_local_port(struct device *dev, struct device_attribute *attr,
 
 		lport->localport = localport;
 		INIT_LIST_HEAD(&lport->lport_list);
+		refcount_set(&lport->ref, 1);
 
 		spin_lock_irqsave(&fcloop_lock, flags);
 		list_add_tail(&lport->lport_list, &fcloop_lports);
@@ -1156,13 +1169,6 @@ out_free_lport:
 	return ret ? ret : count;
 }
 
-
-static void
-__unlink_local_port(struct fcloop_lport *lport)
-{
-	list_del(&lport->lport_list);
-}
-
 static int
 __wait_localport_unreg(struct fcloop_lport *lport)
 {
@@ -1175,8 +1181,6 @@ __wait_localport_unreg(struct fcloop_lport *lport)
 	if (!ret)
 		wait_for_completion(&lport->unreg_done);
 
-	kfree(lport);
-
 	return ret;
 }
 
@@ -1199,8 +1203,9 @@ fcloop_delete_local_port(struct device *dev, struct device_attribute *attr,
 	list_for_each_entry(tlport, &fcloop_lports, lport_list) {
 		if (tlport->localport->node_name == nodename &&
 		    tlport->localport->port_name == portname) {
+			if (!fcloop_lport_get(tlport))
+				break;
 			lport = tlport;
-			__unlink_local_port(lport);
 			break;
 		}
 	}
@@ -1210,6 +1215,7 @@ fcloop_delete_local_port(struct device *dev, struct device_attribute *attr,
 		return -ENOENT;
 
 	ret = __wait_localport_unreg(lport);
+	fcloop_lport_put(lport);
 
 	return ret ? ret : count;
 }
@@ -1249,7 +1255,7 @@ fcloop_alloc_nport(const char *buf, size_t count, bool remoteport)
 		newnport->port_role = opts->roles;
 	if (opts->mask & NVMF_OPT_FCADDR)
 		newnport->port_id = opts->fcaddr;
-	kref_init(&newnport->ref);
+	refcount_set(&newnport->ref, 1);
 
 	spin_lock_irqsave(&fcloop_lock, flags);
 
@@ -1637,17 +1643,17 @@ static void __exit fcloop_exit(void)
 	for (;;) {
 		lport = list_first_entry_or_null(&fcloop_lports,
 						typeof(*lport), lport_list);
-		if (!lport)
+		if (!lport || !fcloop_lport_get(lport))
 			break;
 
-		__unlink_local_port(lport);
-
 		spin_unlock_irqrestore(&fcloop_lock, flags);
 
 		ret = __wait_localport_unreg(lport);
 		if (ret)
 			pr_warn("%s: Failed deleting local port\n", __func__);
 
+		fcloop_lport_put(lport);
+
 		spin_lock_irqsave(&fcloop_lock, flags);
 	}
 
diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index 51c27b32248d..7123c855b5a6 100644
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -62,8 +62,7 @@ static DEFINE_MUTEX(nvmet_pci_epf_ports_mutex);
 #define NVMET_PCI_EPF_CQ_RETRY_INTERVAL	msecs_to_jiffies(1)
 
 enum nvmet_pci_epf_queue_flags {
-	NVMET_PCI_EPF_Q_IS_SQ = 0,	/* The queue is a submission queue */
-	NVMET_PCI_EPF_Q_LIVE,		/* The queue is live */
+	NVMET_PCI_EPF_Q_LIVE = 0,	/* The queue is live */
 	NVMET_PCI_EPF_Q_IRQ_ENABLED,	/* IRQ is enabled for this queue */
 };
 
@@ -596,9 +595,6 @@ static bool nvmet_pci_epf_should_raise_irq(struct nvmet_pci_epf_ctrl *ctrl,
 	struct nvmet_pci_epf_irq_vector *iv = cq->iv;
 	bool ret;
 
-	if (!test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
-		return false;
-
 	/* IRQ coalescing for the admin queue is not allowed. */
 	if (!cq->qid)
 		return true;
@@ -625,7 +621,8 @@ static void nvmet_pci_epf_raise_irq(struct nvmet_pci_epf_ctrl *ctrl,
 	struct pci_epf *epf = nvme_epf->epf;
 	int ret = 0;
 
-	if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags))
+	if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags) ||
+	    !test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
 		return;
 
 	mutex_lock(&ctrl->irq_lock);
@@ -636,14 +633,16 @@ static void nvmet_pci_epf_raise_irq(struct nvmet_pci_epf_ctrl *ctrl,
 	switch (nvme_epf->irq_type) {
 	case PCI_IRQ_MSIX:
 	case PCI_IRQ_MSI:
+		/*
+		 * If we fail to raise an MSI or MSI-X interrupt, it is likely
+		 * because the host is using legacy INTX IRQs (e.g. BIOS,
+		 * grub), but we can fallback to the INTX type only if the
+		 * endpoint controller supports this type.
+		 */
 		ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no,
 					nvme_epf->irq_type, cq->vector + 1);
-		if (!ret)
+		if (!ret || !nvme_epf->epc_features->intx_capable)
 			break;
-		/*
-		 * If we got an error, it is likely because the host is using
-		 * legacy IRQs (e.g. BIOS, grub).
-		 */
 		fallthrough;
 	case PCI_IRQ_INTX:
 		ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no,
@@ -656,7 +655,9 @@ static void nvmet_pci_epf_raise_irq(struct nvmet_pci_epf_ctrl *ctrl,
 	}
 
 	if (ret)
-		dev_err(ctrl->dev, "Failed to raise IRQ (err=%d)\n", ret);
+		dev_err_ratelimited(ctrl->dev,
+				    "CQ[%u]: Failed to raise IRQ (err=%d)\n",
+				    cq->qid, ret);
 
 unlock:
 	mutex_unlock(&ctrl->irq_lock);
@@ -1319,8 +1320,14 @@ static u16 nvmet_pci_epf_create_cq(struct nvmet_ctrl *tctrl,
 
 	set_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags);
 
-	dev_dbg(ctrl->dev, "CQ[%u]: %u entries of %zu B, IRQ vector %u\n",
-		cqid, qsize, cq->qes, cq->vector);
+	if (test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
+		dev_dbg(ctrl->dev,
+			"CQ[%u]: %u entries of %zu B, IRQ vector %u\n",
+			cqid, qsize, cq->qes, cq->vector);
+	else
+		dev_dbg(ctrl->dev,
+			"CQ[%u]: %u entries of %zu B, IRQ disabled\n",
+			cqid, qsize, cq->qes);
 
 	return NVME_SC_SUCCESS;
 
@@ -1344,7 +1351,8 @@ static u16 nvmet_pci_epf_delete_cq(struct nvmet_ctrl *tctrl, u16 cqid)
 
 	cancel_delayed_work_sync(&cq->work);
 	nvmet_pci_epf_drain_queue(cq);
-	nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector);
+	if (test_and_clear_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
+		nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector);
 	nvmet_pci_epf_mem_unmap(ctrl->nvme_epf, &cq->pci_map);
 
 	return NVME_SC_SUCCESS;
@@ -1533,7 +1541,6 @@ static void nvmet_pci_epf_init_queue(struct nvmet_pci_epf_ctrl *ctrl,
 
 	if (sq) {
 		queue = &ctrl->sq[qid];
-		set_bit(NVMET_PCI_EPF_Q_IS_SQ, &queue->flags);
 	} else {
 		queue = &ctrl->cq[qid];
 		INIT_DELAYED_WORK(&queue->work, nvmet_pci_epf_cq_work);
@@ -1648,16 +1655,17 @@ static int nvmet_pci_epf_process_sq(struct nvmet_pci_epf_ctrl *ctrl,
 {
 	struct nvmet_pci_epf_iod *iod;
 	int ret, n = 0;
+	u16 head = sq->head;
 
 	sq->tail = nvmet_pci_epf_bar_read32(ctrl, sq->db);
-	while (sq->head != sq->tail && (!ctrl->sq_ab || n < ctrl->sq_ab)) {
+	while (head != sq->tail && (!ctrl->sq_ab || n < ctrl->sq_ab)) {
 		iod = nvmet_pci_epf_alloc_iod(sq);
 		if (!iod)
 			break;
 
 		/* Get the NVMe command submitted by the host. */
 		ret = nvmet_pci_epf_transfer(ctrl, &iod->cmd,
-					     sq->pci_addr + sq->head * sq->qes,
+					     sq->pci_addr + head * sq->qes,
 					     sq->qes, DMA_FROM_DEVICE);
 		if (ret) {
 			/* Not much we can do... */
@@ -1666,12 +1674,13 @@ static int nvmet_pci_epf_process_sq(struct nvmet_pci_epf_ctrl *ctrl,
 		}
 
 		dev_dbg(ctrl->dev, "SQ[%u]: head %u, tail %u, command %s\n",
-			sq->qid, sq->head, sq->tail,
+			sq->qid, head, sq->tail,
 			nvmet_pci_epf_iod_name(iod));
 
-		sq->head++;
-		if (sq->head == sq->depth)
-			sq->head = 0;
+		head++;
+		if (head == sq->depth)
+			head = 0;
+		WRITE_ONCE(sq->head, head);
 		n++;
 
 		queue_work_on(WORK_CPU_UNBOUND, sq->iod_wq, &iod->work);
@@ -1761,8 +1770,17 @@ static void nvmet_pci_epf_cq_work(struct work_struct *work)
 		if (!iod)
 			break;
 
-		/* Post the IOD completion entry. */
+		/*
+		 * Post the IOD completion entry. If the IOD request was
+		 * executed (req->execute() called), the CQE is already
+		 * initialized. However, the IOD may have been failed before
+		 * that, leaving the CQE not properly initialized. So always
+		 * initialize it here.
+		 */
 		cqe = &iod->cqe;
+		cqe->sq_head = cpu_to_le16(READ_ONCE(iod->sq->head));
+		cqe->sq_id = cpu_to_le16(iod->sq->qid);
+		cqe->command_id = iod->cmd.common.command_id;
 		cqe->status = cpu_to_le16((iod->status << 1) | cq->phase);
 
 		dev_dbg(ctrl->dev,
@@ -1800,6 +1818,21 @@ static void nvmet_pci_epf_cq_work(struct work_struct *work)
 				   NVMET_PCI_EPF_CQ_RETRY_INTERVAL);
 }
 
+static void nvmet_pci_epf_clear_ctrl_config(struct nvmet_pci_epf_ctrl *ctrl)
+{
+	struct nvmet_ctrl *tctrl = ctrl->tctrl;
+
+	/* Initialize controller status. */
+	tctrl->csts = 0;
+	ctrl->csts = 0;
+	nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts);
+
+	/* Initialize controller configuration and start polling. */
+	tctrl->cc = 0;
+	ctrl->cc = 0;
+	nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CC, ctrl->cc);
+}
+
 static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 {
 	u64 pci_addr, asq, acq;
@@ -1865,18 +1898,20 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 	return 0;
 
 err:
-	ctrl->csts = 0;
+	nvmet_pci_epf_clear_ctrl_config(ctrl);
 	return -EINVAL;
 }
 
-static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
+static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl,
+				       bool shutdown)
 {
 	int qid;
 
 	if (!ctrl->enabled)
 		return;
 
-	dev_info(ctrl->dev, "Disabling controller\n");
+	dev_info(ctrl->dev, "%s controller\n",
+		 shutdown ? "Shutting down" : "Disabling");
 
 	ctrl->enabled = false;
 	cancel_delayed_work_sync(&ctrl->poll_sqs);
@@ -1893,6 +1928,11 @@ static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 	nvmet_pci_epf_delete_cq(ctrl->tctrl, 0);
 
 	ctrl->csts &= ~NVME_CSTS_RDY;
+	if (shutdown) {
+		ctrl->csts |= NVME_CSTS_SHST_CMPLT;
+		ctrl->cc &= ~NVME_CC_ENABLE;
+		nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CC, ctrl->cc);
+	}
 }
 
 static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
@@ -1919,12 +1959,10 @@ static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
 	}
 
 	if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc))
-		nvmet_pci_epf_disable_ctrl(ctrl);
+		nvmet_pci_epf_disable_ctrl(ctrl, false);
 
-	if (nvmet_cc_shn(new_cc) && !nvmet_cc_shn(old_cc)) {
-		nvmet_pci_epf_disable_ctrl(ctrl);
-		ctrl->csts |= NVME_CSTS_SHST_CMPLT;
-	}
+	if (nvmet_cc_shn(new_cc) && !nvmet_cc_shn(old_cc))
+		nvmet_pci_epf_disable_ctrl(ctrl, true);
 
 	if (!nvmet_cc_shn(new_cc) && nvmet_cc_shn(old_cc))
 		ctrl->csts &= ~NVME_CSTS_SHST_CMPLT;
@@ -1963,16 +2001,10 @@ static void nvmet_pci_epf_init_bar(struct nvmet_pci_epf_ctrl *ctrl)
 	/* Clear Controller Memory Buffer Supported (CMBS). */
 	ctrl->cap &= ~(0x1ULL << 57);
 
-	/* Controller configuration. */
-	ctrl->cc = tctrl->cc & (~NVME_CC_ENABLE);
-
-	/* Controller status. */
-	ctrl->csts = ctrl->tctrl->csts;
-
 	nvmet_pci_epf_bar_write64(ctrl, NVME_REG_CAP, ctrl->cap);
 	nvmet_pci_epf_bar_write32(ctrl, NVME_REG_VS, tctrl->subsys->ver);
-	nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts);
-	nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CC, ctrl->cc);
+
+	nvmet_pci_epf_clear_ctrl_config(ctrl);
 }
 
 static int nvmet_pci_epf_create_ctrl(struct nvmet_pci_epf *nvme_epf,
@@ -2070,14 +2102,22 @@ out_mempool_exit:
 
 static void nvmet_pci_epf_start_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 {
+
+	dev_info(ctrl->dev, "PCI link up\n");
+	ctrl->link_up = true;
+
 	schedule_delayed_work(&ctrl->poll_cc, NVMET_PCI_EPF_CC_POLL_INTERVAL);
 }
 
 static void nvmet_pci_epf_stop_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 {
+	dev_info(ctrl->dev, "PCI link down\n");
+	ctrl->link_up = false;
+
 	cancel_delayed_work_sync(&ctrl->poll_cc);
 
-	nvmet_pci_epf_disable_ctrl(ctrl);
+	nvmet_pci_epf_disable_ctrl(ctrl, false);
+	nvmet_pci_epf_clear_ctrl_config(ctrl);
 }
 
 static void nvmet_pci_epf_destroy_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
@@ -2300,10 +2340,8 @@ static int nvmet_pci_epf_epc_init(struct pci_epf *epf)
 	if (ret)
 		goto out_clear_bar;
 
-	if (!epc_features->linkup_notifier) {
-		ctrl->link_up = true;
+	if (!epc_features->linkup_notifier)
 		nvmet_pci_epf_start_ctrl(&nvme_epf->ctrl);
-	}
 
 	return 0;
 
@@ -2319,7 +2357,6 @@ static void nvmet_pci_epf_epc_deinit(struct pci_epf *epf)
 	struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
 	struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl;
 
-	ctrl->link_up = false;
 	nvmet_pci_epf_destroy_ctrl(ctrl);
 
 	nvmet_pci_epf_deinit_dma(nvme_epf);
@@ -2331,7 +2368,6 @@ static int nvmet_pci_epf_link_up(struct pci_epf *epf)
 	struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
 	struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl;
 
-	ctrl->link_up = true;
 	nvmet_pci_epf_start_ctrl(ctrl);
 
 	return 0;
@@ -2342,7 +2378,6 @@ static int nvmet_pci_epf_link_down(struct pci_epf *epf)
 	struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
 	struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl;
 
-	ctrl->link_up = false;
 	nvmet_pci_epf_stop_ctrl(ctrl);
 
 	return 0;
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index f2d0c920269b..12a5cb8641ca 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1560,6 +1560,9 @@ static void nvmet_tcp_restore_socket_callbacks(struct nvmet_tcp_queue *queue)
 {
 	struct socket *sock = queue->sock;
 
+	if (!queue->state_change)
+		return;
+
 	write_lock_bh(&sock->sk->sk_callback_lock);
 	sock->sk->sk_data_ready =  queue->data_ready;
 	sock->sk->sk_state_change = queue->state_change;
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index fff85bbf0ecd..e206efc29a00 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -594,9 +594,11 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem,
 	cell->nbits = info->nbits;
 	cell->np = info->np;
 
-	if (cell->nbits)
+	if (cell->nbits) {
 		cell->bytes = DIV_ROUND_UP(cell->nbits + cell->bit_offset,
 					   BITS_PER_BYTE);
+		cell->raw_len = ALIGN(cell->bytes, nvmem->word_size);
+	}
 
 	if (!IS_ALIGNED(cell->offset, nvmem->stride)) {
 		dev_err(&nvmem->dev,
@@ -605,6 +607,18 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem,
 		return -EINVAL;
 	}
 
+	if (!IS_ALIGNED(cell->raw_len, nvmem->word_size)) {
+		dev_err(&nvmem->dev,
+			"cell %s raw len %zd unaligned to nvmem word size %d\n",
+			cell->name ?: "<unknown>", cell->raw_len,
+			nvmem->word_size);
+
+		if (info->raw_len)
+			return -EINVAL;
+
+		cell->raw_len = ALIGN(cell->raw_len, nvmem->word_size);
+	}
+
 	return 0;
 }
 
@@ -837,7 +851,9 @@ static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_nod
 		if (addr && len == (2 * sizeof(u32))) {
 			info.bit_offset = be32_to_cpup(addr++);
 			info.nbits = be32_to_cpup(addr);
-			if (info.bit_offset >= BITS_PER_BYTE || info.nbits < 1) {
+			if (info.bit_offset >= BITS_PER_BYTE * info.bytes ||
+			    info.nbits < 1 ||
+			    info.bit_offset + info.nbits > BITS_PER_BYTE * info.bytes) {
 				dev_err(dev, "nvmem: invalid bits on %pOF\n", child);
 				of_node_put(child);
 				return -EINVAL;
@@ -1630,21 +1646,29 @@ EXPORT_SYMBOL_GPL(nvmem_cell_put);
 static void nvmem_shift_read_buffer_in_place(struct nvmem_cell_entry *cell, void *buf)
 {
 	u8 *p, *b;
-	int i, extra, bit_offset = cell->bit_offset;
+	int i, extra, bytes_offset;
+	int bit_offset = cell->bit_offset;
 
 	p = b = buf;
-	if (bit_offset) {
+
+	bytes_offset = bit_offset / BITS_PER_BYTE;
+	b += bytes_offset;
+	bit_offset %= BITS_PER_BYTE;
+
+	if (bit_offset % BITS_PER_BYTE) {
 		/* First shift */
-		*b++ >>= bit_offset;
+		*p = *b++ >> bit_offset;
 
 		/* setup rest of the bytes if any */
 		for (i = 1; i < cell->bytes; i++) {
 			/* Get bits from next byte and shift them towards msb */
-			*p |= *b << (BITS_PER_BYTE - bit_offset);
+			*p++ |= *b << (BITS_PER_BYTE - bit_offset);
 
-			p = b;
-			*b++ >>= bit_offset;
+			*p = *b++ >> bit_offset;
 		}
+	} else if (p != b) {
+		memmove(p, b, cell->bytes - bytes_offset);
+		p += cell->bytes - 1;
 	} else {
 		/* point to the msb */
 		p += cell->bytes - 1;
diff --git a/drivers/nvmem/qfprom.c b/drivers/nvmem/qfprom.c
index 116a39e804c7..a872c640b8c5 100644
--- a/drivers/nvmem/qfprom.c
+++ b/drivers/nvmem/qfprom.c
@@ -321,19 +321,32 @@ static int qfprom_reg_read(void *context,
 			unsigned int reg, void *_val, size_t bytes)
 {
 	struct qfprom_priv *priv = context;
-	u8 *val = _val;
-	int i = 0, words = bytes;
+	u32 *val = _val;
 	void __iomem *base = priv->qfpcorrected;
+	int words = DIV_ROUND_UP(bytes, sizeof(u32));
+	int i;
 
 	if (read_raw_data && priv->qfpraw)
 		base = priv->qfpraw;
 
-	while (words--)
-		*val++ = readb(base + reg + i++);
+	for (i = 0; i < words; i++)
+		*val++ = readl(base + reg + i * sizeof(u32));
 
 	return 0;
 }
 
+/* Align reads to word boundary */
+static void qfprom_fixup_dt_cell_info(struct nvmem_device *nvmem,
+				      struct nvmem_cell_info *cell)
+{
+	unsigned int byte_offset = cell->offset % sizeof(u32);
+
+	cell->bit_offset += byte_offset * BITS_PER_BYTE;
+	cell->offset -= byte_offset;
+	if (byte_offset && !cell->nbits)
+		cell->nbits = cell->bytes * BITS_PER_BYTE;
+}
+
 static void qfprom_runtime_disable(void *data)
 {
 	pm_runtime_disable(data);
@@ -358,10 +371,11 @@ static int qfprom_probe(struct platform_device *pdev)
 	struct nvmem_config econfig = {
 		.name = "qfprom",
 		.add_legacy_fixed_of_cells = true,
-		.stride = 1,
-		.word_size = 1,
+		.stride = 4,
+		.word_size = 4,
 		.id = NVMEM_DEVID_AUTO,
 		.reg_read = qfprom_reg_read,
+		.fixup_dt_cell_info = qfprom_fixup_dt_cell_info,
 	};
 	struct device *dev = &pdev->dev;
 	struct resource *res;
diff --git a/drivers/nvmem/rockchip-otp.c b/drivers/nvmem/rockchip-otp.c
index ebc3f0b24166..d88f12c53242 100644
--- a/drivers/nvmem/rockchip-otp.c
+++ b/drivers/nvmem/rockchip-otp.c
@@ -59,7 +59,6 @@
 #define RK3588_OTPC_AUTO_EN		0x08
 #define RK3588_OTPC_INT_ST		0x84
 #define RK3588_OTPC_DOUT0		0x20
-#define RK3588_NO_SECURE_OFFSET		0x300
 #define RK3588_NBYTES			4
 #define RK3588_BURST_NUM		1
 #define RK3588_BURST_SHIFT		8
@@ -69,6 +68,7 @@
 
 struct rockchip_data {
 	int size;
+	int read_offset;
 	const char * const *clks;
 	int num_clks;
 	nvmem_reg_read_t reg_read;
@@ -196,7 +196,7 @@ static int rk3588_otp_read(void *context, unsigned int offset,
 	addr_start = round_down(offset, RK3588_NBYTES) / RK3588_NBYTES;
 	addr_end = round_up(offset + bytes, RK3588_NBYTES) / RK3588_NBYTES;
 	addr_len = addr_end - addr_start;
-	addr_start += RK3588_NO_SECURE_OFFSET;
+	addr_start += otp->data->read_offset / RK3588_NBYTES;
 
 	buf = kzalloc(array_size(addr_len, RK3588_NBYTES), GFP_KERNEL);
 	if (!buf)
@@ -274,12 +274,21 @@ static const struct rockchip_data px30_data = {
 	.reg_read = px30_otp_read,
 };
 
+static const struct rockchip_data rk3576_data = {
+	.size = 0x100,
+	.read_offset = 0x700,
+	.clks = px30_otp_clocks,
+	.num_clks = ARRAY_SIZE(px30_otp_clocks),
+	.reg_read = rk3588_otp_read,
+};
+
 static const char * const rk3588_otp_clocks[] = {
 	"otp", "apb_pclk", "phy", "arb",
 };
 
 static const struct rockchip_data rk3588_data = {
 	.size = 0x400,
+	.read_offset = 0xc00,
 	.clks = rk3588_otp_clocks,
 	.num_clks = ARRAY_SIZE(rk3588_otp_clocks),
 	.reg_read = rk3588_otp_read,
@@ -295,6 +304,10 @@ static const struct of_device_id rockchip_otp_match[] = {
 		.data = &px30_data,
 	},
 	{
+		.compatible = "rockchip,rk3576-otp",
+		.data = &rk3576_data,
+	},
+	{
 		.compatible = "rockchip,rk3588-otp",
 		.data = &rk3588_data,
 	},
diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c
index 055518ee354d..e9e9aaa91770 100644
--- a/drivers/pci/hotplug/s390_pci_hpc.c
+++ b/drivers/pci/hotplug/s390_pci_hpc.c
@@ -59,7 +59,6 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
 
 	pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
 	if (pdev && pci_num_vf(pdev)) {
-		pci_dev_put(pdev);
 		rc = -EBUSY;
 		goto out;
 	}
diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c
index 6569ba3577fe..8b8848788618 100644
--- a/drivers/pci/msi/msi.c
+++ b/drivers/pci/msi/msi.c
@@ -615,6 +615,9 @@ void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc)
 		void __iomem *addr = pci_msix_desc_addr(desc);
 
 		desc->pci.msi_attrib.can_mask = 1;
+		/* Workaround for SUN NIU insanity, which requires write before read */
+		if (dev->dev_flags & PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST)
+			writel(0, addr + PCI_MSIX_ENTRY_DATA);
 		desc->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
 	}
 }
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 4d7c9f64ea24..e77d5b53c0ce 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5429,8 +5429,6 @@ static bool pci_bus_resettable(struct pci_bus *bus)
 		return false;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
-		if (!pci_reset_supported(dev))
-			return false;
 		if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET ||
 		    (dev->subordinate && !pci_bus_resettable(dev->subordinate)))
 			return false;
@@ -5507,8 +5505,6 @@ static bool pci_slot_resettable(struct pci_slot *slot)
 	list_for_each_entry(dev, &slot->bus->devices, bus_list) {
 		if (!dev->slot || dev->slot != slot)
 			continue;
-		if (!pci_reset_supported(dev))
-			return false;
 		if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET ||
 		    (dev->subordinate && !pci_bus_resettable(dev->subordinate)))
 			return false;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 8d610c17e0f2..94daca15a096 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1990,12 +1990,12 @@ static void quirk_huawei_pcie_sva(struct pci_dev *pdev)
 	    device_create_managed_software_node(&pdev->dev, properties, NULL))
 		pci_warn(pdev, "could not add stall property");
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa250, quirk_huawei_pcie_sva);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa251, quirk_huawei_pcie_sva);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa255, quirk_huawei_pcie_sva);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa256, quirk_huawei_pcie_sva);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa258, quirk_huawei_pcie_sva);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa259, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa250, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa251, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa255, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa256, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa258, quirk_huawei_pcie_sva);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa259, quirk_huawei_pcie_sva);
 
 /*
  * It's possible for the MSI to get corrupted if SHPC and ACPI are used
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 54d6f4fa3ce1..e994c546422c 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -187,6 +187,9 @@ static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head)
 			panic("%s: kzalloc() failed!\n", __func__);
 		tmp->res = r;
 		tmp->dev = dev;
+		tmp->start = r->start;
+		tmp->end = r->end;
+		tmp->flags = r->flags;
 
 		/* Fallback is smallest one or list is empty */
 		n = head;
@@ -545,6 +548,7 @@ assign:
 		pci_dbg(dev, "%s %pR: releasing\n", res_name, res);
 
 		release_resource(res);
+		restore_dev_resource(dev_res);
 	}
 	/* Restore start/end/flags from saved list */
 	list_for_each_entry(save_res, &save_head, list)
diff --git a/drivers/phy/phy-can-transceiver.c b/drivers/phy/phy-can-transceiver.c
index 2bec70615449..f59caff4b3d4 100644
--- a/drivers/phy/phy-can-transceiver.c
+++ b/drivers/phy/phy-can-transceiver.c
@@ -93,6 +93,16 @@ static const struct of_device_id can_transceiver_phy_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, can_transceiver_phy_ids);
 
+/* Temporary wrapper until the multiplexer subsystem supports optional muxes */
+static inline struct mux_state *
+devm_mux_state_get_optional(struct device *dev, const char *mux_name)
+{
+	if (!of_property_present(dev->of_node, "mux-states"))
+		return NULL;
+
+	return devm_mux_state_get(dev, mux_name);
+}
+
 static int can_transceiver_phy_probe(struct platform_device *pdev)
 {
 	struct phy_provider *phy_provider;
@@ -114,13 +124,11 @@ static int can_transceiver_phy_probe(struct platform_device *pdev)
 	match = of_match_node(can_transceiver_phy_ids, pdev->dev.of_node);
 	drvdata = match->data;
 
-	mux_state = devm_mux_state_get(dev, NULL);
-	if (IS_ERR(mux_state)) {
-		if (PTR_ERR(mux_state) == -EPROBE_DEFER)
-			return PTR_ERR(mux_state);
-	} else {
-		can_transceiver_phy->mux_state = mux_state;
-	}
+	mux_state = devm_mux_state_get_optional(dev, NULL);
+	if (IS_ERR(mux_state))
+		return PTR_ERR(mux_state);
+
+	can_transceiver_phy->mux_state = mux_state;
 
 	phy = devm_phy_create(dev, dev->of_node,
 			      &can_transceiver_phy_ops);
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
index 45b3b792696e..b33e2e2b5014 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
@@ -1754,7 +1754,8 @@ static void qmp_ufs_init_registers(struct qmp_ufs *qmp, const struct qmp_phy_cfg
 		qmp_ufs_init_all(qmp, &cfg->tbls_hs_overlay[i]);
 	}
 
-	qmp_ufs_init_all(qmp, &cfg->tbls_hs_b);
+	if (qmp->mode == PHY_MODE_UFS_HS_B)
+		qmp_ufs_init_all(qmp, &cfg->tbls_hs_b);
 }
 
 static int qmp_ufs_com_init(struct qmp_ufs *qmp)
diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index 775f4f973a6c..9fdf17e0848a 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -9,6 +9,7 @@
  * Copyright (C) 2014 Cogent Embedded, Inc.
  */
 
+#include <linux/cleanup.h>
 #include <linux/extcon-provider.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -107,7 +108,6 @@ struct rcar_gen3_phy {
 	struct rcar_gen3_chan *ch;
 	u32 int_enable_bits;
 	bool initialized;
-	bool otg_initialized;
 	bool powered;
 };
 
@@ -119,9 +119,8 @@ struct rcar_gen3_chan {
 	struct regulator *vbus;
 	struct reset_control *rstc;
 	struct work_struct work;
-	struct mutex lock;	/* protects rphys[...].powered */
+	spinlock_t lock;	/* protects access to hardware and driver data structure. */
 	enum usb_dr_mode dr_mode;
-	int irq;
 	u32 obint_enable_bits;
 	bool extcon_host;
 	bool is_otg_channel;
@@ -320,16 +319,15 @@ static bool rcar_gen3_is_any_rphy_initialized(struct rcar_gen3_chan *ch)
 	return false;
 }
 
-static bool rcar_gen3_needs_init_otg(struct rcar_gen3_chan *ch)
+static bool rcar_gen3_is_any_otg_rphy_initialized(struct rcar_gen3_chan *ch)
 {
-	int i;
-
-	for (i = 0; i < NUM_OF_PHYS; i++) {
-		if (ch->rphys[i].otg_initialized)
-			return false;
+	for (enum rcar_gen3_phy_index i = PHY_INDEX_BOTH_HC; i <= PHY_INDEX_EHCI;
+	     i++) {
+		if (ch->rphys[i].initialized)
+			return true;
 	}
 
-	return true;
+	return false;
 }
 
 static bool rcar_gen3_are_all_rphys_power_off(struct rcar_gen3_chan *ch)
@@ -351,7 +349,9 @@ static ssize_t role_store(struct device *dev, struct device_attribute *attr,
 	bool is_b_device;
 	enum phy_mode cur_mode, new_mode;
 
-	if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch))
+	guard(spinlock_irqsave)(&ch->lock);
+
+	if (!ch->is_otg_channel || !rcar_gen3_is_any_otg_rphy_initialized(ch))
 		return -EIO;
 
 	if (sysfs_streq(buf, "host"))
@@ -389,7 +389,7 @@ static ssize_t role_show(struct device *dev, struct device_attribute *attr,
 {
 	struct rcar_gen3_chan *ch = dev_get_drvdata(dev);
 
-	if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch))
+	if (!ch->is_otg_channel || !rcar_gen3_is_any_otg_rphy_initialized(ch))
 		return -EIO;
 
 	return sprintf(buf, "%s\n", rcar_gen3_is_host(ch) ? "host" :
@@ -402,6 +402,9 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch)
 	void __iomem *usb2_base = ch->base;
 	u32 val;
 
+	if (!ch->is_otg_channel || rcar_gen3_is_any_otg_rphy_initialized(ch))
+		return;
+
 	/* Should not use functions of read-modify-write a register */
 	val = readl(usb2_base + USB2_LINECTRL1);
 	val = (val & ~USB2_LINECTRL1_DP_RPD) | USB2_LINECTRL1_DPRPD_EN |
@@ -415,7 +418,7 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch)
 		val = readl(usb2_base + USB2_ADPCTRL);
 		writel(val | USB2_ADPCTRL_IDPULLUP, usb2_base + USB2_ADPCTRL);
 	}
-	msleep(20);
+	mdelay(20);
 
 	writel(0xffffffff, usb2_base + USB2_OBINTSTA);
 	writel(ch->obint_enable_bits, usb2_base + USB2_OBINTEN);
@@ -427,16 +430,27 @@ static irqreturn_t rcar_gen3_phy_usb2_irq(int irq, void *_ch)
 {
 	struct rcar_gen3_chan *ch = _ch;
 	void __iomem *usb2_base = ch->base;
-	u32 status = readl(usb2_base + USB2_OBINTSTA);
+	struct device *dev = ch->dev;
 	irqreturn_t ret = IRQ_NONE;
+	u32 status;
+
+	pm_runtime_get_noresume(dev);
+
+	if (pm_runtime_suspended(dev))
+		goto rpm_put;
 
-	if (status & ch->obint_enable_bits) {
-		dev_vdbg(ch->dev, "%s: %08x\n", __func__, status);
-		writel(ch->obint_enable_bits, usb2_base + USB2_OBINTSTA);
-		rcar_gen3_device_recognition(ch);
-		ret = IRQ_HANDLED;
+	scoped_guard(spinlock, &ch->lock) {
+		status = readl(usb2_base + USB2_OBINTSTA);
+		if (status & ch->obint_enable_bits) {
+			dev_vdbg(dev, "%s: %08x\n", __func__, status);
+			writel(ch->obint_enable_bits, usb2_base + USB2_OBINTSTA);
+			rcar_gen3_device_recognition(ch);
+			ret = IRQ_HANDLED;
+		}
 	}
 
+rpm_put:
+	pm_runtime_put_noidle(dev);
 	return ret;
 }
 
@@ -446,32 +460,23 @@ static int rcar_gen3_phy_usb2_init(struct phy *p)
 	struct rcar_gen3_chan *channel = rphy->ch;
 	void __iomem *usb2_base = channel->base;
 	u32 val;
-	int ret;
 
-	if (!rcar_gen3_is_any_rphy_initialized(channel) && channel->irq >= 0) {
-		INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work);
-		ret = request_irq(channel->irq, rcar_gen3_phy_usb2_irq,
-				  IRQF_SHARED, dev_name(channel->dev), channel);
-		if (ret < 0) {
-			dev_err(channel->dev, "No irq handler (%d)\n", channel->irq);
-			return ret;
-		}
-	}
+	guard(spinlock_irqsave)(&channel->lock);
 
 	/* Initialize USB2 part */
 	val = readl(usb2_base + USB2_INT_ENABLE);
 	val |= USB2_INT_ENABLE_UCOM_INTEN | rphy->int_enable_bits;
 	writel(val, usb2_base + USB2_INT_ENABLE);
-	writel(USB2_SPD_RSM_TIMSET_INIT, usb2_base + USB2_SPD_RSM_TIMSET);
-	writel(USB2_OC_TIMSET_INIT, usb2_base + USB2_OC_TIMSET);
-
-	/* Initialize otg part */
-	if (channel->is_otg_channel) {
-		if (rcar_gen3_needs_init_otg(channel))
-			rcar_gen3_init_otg(channel);
-		rphy->otg_initialized = true;
+
+	if (!rcar_gen3_is_any_rphy_initialized(channel)) {
+		writel(USB2_SPD_RSM_TIMSET_INIT, usb2_base + USB2_SPD_RSM_TIMSET);
+		writel(USB2_OC_TIMSET_INIT, usb2_base + USB2_OC_TIMSET);
 	}
 
+	/* Initialize otg part (only if we initialize a PHY with IRQs). */
+	if (rphy->int_enable_bits)
+		rcar_gen3_init_otg(channel);
+
 	rphy->initialized = true;
 
 	return 0;
@@ -484,10 +489,9 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p)
 	void __iomem *usb2_base = channel->base;
 	u32 val;
 
-	rphy->initialized = false;
+	guard(spinlock_irqsave)(&channel->lock);
 
-	if (channel->is_otg_channel)
-		rphy->otg_initialized = false;
+	rphy->initialized = false;
 
 	val = readl(usb2_base + USB2_INT_ENABLE);
 	val &= ~rphy->int_enable_bits;
@@ -495,9 +499,6 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p)
 		val &= ~USB2_INT_ENABLE_UCOM_INTEN;
 	writel(val, usb2_base + USB2_INT_ENABLE);
 
-	if (channel->irq >= 0 && !rcar_gen3_is_any_rphy_initialized(channel))
-		free_irq(channel->irq, channel);
-
 	return 0;
 }
 
@@ -509,16 +510,17 @@ static int rcar_gen3_phy_usb2_power_on(struct phy *p)
 	u32 val;
 	int ret = 0;
 
-	mutex_lock(&channel->lock);
-	if (!rcar_gen3_are_all_rphys_power_off(channel))
-		goto out;
-
 	if (channel->vbus) {
 		ret = regulator_enable(channel->vbus);
 		if (ret)
-			goto out;
+			return ret;
 	}
 
+	guard(spinlock_irqsave)(&channel->lock);
+
+	if (!rcar_gen3_are_all_rphys_power_off(channel))
+		goto out;
+
 	val = readl(usb2_base + USB2_USBCTR);
 	val |= USB2_USBCTR_PLL_RST;
 	writel(val, usb2_base + USB2_USBCTR);
@@ -528,7 +530,6 @@ static int rcar_gen3_phy_usb2_power_on(struct phy *p)
 out:
 	/* The powered flag should be set for any other phys anyway */
 	rphy->powered = true;
-	mutex_unlock(&channel->lock);
 
 	return 0;
 }
@@ -539,18 +540,20 @@ static int rcar_gen3_phy_usb2_power_off(struct phy *p)
 	struct rcar_gen3_chan *channel = rphy->ch;
 	int ret = 0;
 
-	mutex_lock(&channel->lock);
-	rphy->powered = false;
+	scoped_guard(spinlock_irqsave, &channel->lock) {
+		rphy->powered = false;
 
-	if (!rcar_gen3_are_all_rphys_power_off(channel))
-		goto out;
+		if (rcar_gen3_are_all_rphys_power_off(channel)) {
+			u32 val = readl(channel->base + USB2_USBCTR);
+
+			val |= USB2_USBCTR_PLL_RST;
+			writel(val, channel->base + USB2_USBCTR);
+		}
+	}
 
 	if (channel->vbus)
 		ret = regulator_disable(channel->vbus);
 
-out:
-	mutex_unlock(&channel->lock);
-
 	return ret;
 }
 
@@ -703,7 +706,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct rcar_gen3_chan *channel;
 	struct phy_provider *provider;
-	int ret = 0, i;
+	int ret = 0, i, irq;
 
 	if (!dev->of_node) {
 		dev_err(dev, "This driver needs device tree\n");
@@ -719,8 +722,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 		return PTR_ERR(channel->base);
 
 	channel->obint_enable_bits = USB2_OBINT_BITS;
-	/* get irq number here and request_irq for OTG in phy_init */
-	channel->irq = platform_get_irq_optional(pdev, 0);
 	channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node);
 	if (channel->dr_mode != USB_DR_MODE_UNKNOWN) {
 		channel->is_otg_channel = true;
@@ -763,7 +764,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 	if (phy_data->no_adp_ctrl)
 		channel->obint_enable_bits = USB2_OBINT_IDCHG_EN;
 
-	mutex_init(&channel->lock);
+	spin_lock_init(&channel->lock);
 	for (i = 0; i < NUM_OF_PHYS; i++) {
 		channel->rphys[i].phy = devm_phy_create(dev, NULL,
 							phy_data->phy_usb2_ops);
@@ -789,6 +790,20 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 		channel->vbus = NULL;
 	}
 
+	irq = platform_get_irq_optional(pdev, 0);
+	if (irq < 0 && irq != -ENXIO) {
+		ret = irq;
+		goto error;
+	} else if (irq > 0) {
+		INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work);
+		ret = devm_request_irq(dev, irq, rcar_gen3_phy_usb2_irq,
+				       IRQF_SHARED, dev_name(dev), channel);
+		if (ret < 0) {
+			dev_err(dev, "Failed to request irq (%d)\n", irq);
+			goto error;
+		}
+	}
+
 	provider = devm_of_phy_provider_register(dev, rcar_gen3_phy_usb2_xlate);
 	if (IS_ERR(provider)) {
 		dev_err(dev, "Failed to register PHY provider\n");
diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c b/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c
index 08c78c1bafc9..28a052e17366 100644
--- a/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c
+++ b/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c
@@ -1653,7 +1653,7 @@ static __maybe_unused int samsung_mipi_dcphy_runtime_resume(struct device *dev)
 		return ret;
 	}
 
-	clk_prepare_enable(samsung->ref_clk);
+	ret = clk_prepare_enable(samsung->ref_clk);
 	if (ret) {
 		dev_err(samsung->dev, "Failed to enable reference clock, %d\n", ret);
 		clk_disable_unprepare(samsung->pclk);
diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
index fe7c05748356..77236f012a1f 100644
--- a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
+++ b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
@@ -476,6 +476,8 @@ static const struct ropll_config ropll_tmds_cfg[] = {
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
 	{ 650000, 162, 162, 1, 1, 11, 1, 1, 1, 1, 1, 1, 1, 54, 0, 16, 4, 1,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
+	{ 502500, 84, 84, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 11, 1, 4, 5,
+	  4, 11, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
 	{ 337500, 0x70, 0x70, 1, 1, 0xf, 1, 1, 1, 1, 1, 1, 1, 0x2, 0, 0x01, 5,
 	  1, 1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
 	{ 400000, 100, 100, 1, 1, 11, 1, 1, 0, 1, 0, 1, 1, 0x9, 0, 0x05, 0,
diff --git a/drivers/phy/starfive/phy-jh7110-usb.c b/drivers/phy/starfive/phy-jh7110-usb.c
index cb5454fbe2c8..b505d89860b4 100644
--- a/drivers/phy/starfive/phy-jh7110-usb.c
+++ b/drivers/phy/starfive/phy-jh7110-usb.c
@@ -18,6 +18,8 @@
 #include <linux/usb/of.h>
 
 #define USB_125M_CLK_RATE		125000000
+#define USB_CLK_MODE_OFF		0x0
+#define USB_CLK_MODE_RX_NORMAL_PWR	BIT(1)
 #define USB_LS_KEEPALIVE_OFF		0x4
 #define USB_LS_KEEPALIVE_ENABLE		BIT(4)
 
@@ -78,6 +80,7 @@ static int jh7110_usb2_phy_init(struct phy *_phy)
 {
 	struct jh7110_usb2_phy *phy = phy_get_drvdata(_phy);
 	int ret;
+	unsigned int val;
 
 	ret = clk_set_rate(phy->usb_125m_clk, USB_125M_CLK_RATE);
 	if (ret)
@@ -87,6 +90,10 @@ static int jh7110_usb2_phy_init(struct phy *_phy)
 	if (ret)
 		return ret;
 
+	val = readl(phy->regs + USB_CLK_MODE_OFF);
+	val |= USB_CLK_MODE_RX_NORMAL_PWR;
+	writel(val, phy->regs + USB_CLK_MODE_OFF);
+
 	return 0;
 }
 
diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index fae6242aa730..23a23f2d64e5 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -237,6 +237,8 @@
 #define   DATA0_VAL_PD				BIT(1)
 #define   USE_XUSB_AO				BIT(4)
 
+#define TEGRA_UTMI_PAD_MAX 4
+
 #define TEGRA186_LANE(_name, _offset, _shift, _mask, _type)		\
 	{								\
 		.name = _name,						\
@@ -269,7 +271,7 @@ struct tegra186_xusb_padctl {
 
 	/* UTMI bias and tracking */
 	struct clk *usb2_trk_clk;
-	unsigned int bias_pad_enable;
+	DECLARE_BITMAP(utmi_pad_enabled, TEGRA_UTMI_PAD_MAX);
 
 	/* padctl context */
 	struct tegra186_xusb_padctl_context context;
@@ -603,12 +605,8 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl)
 	u32 value;
 	int err;
 
-	mutex_lock(&padctl->lock);
-
-	if (priv->bias_pad_enable++ > 0) {
-		mutex_unlock(&padctl->lock);
+	if (!bitmap_empty(priv->utmi_pad_enabled, TEGRA_UTMI_PAD_MAX))
 		return;
-	}
 
 	err = clk_prepare_enable(priv->usb2_trk_clk);
 	if (err < 0)
@@ -658,8 +656,6 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl)
 	} else {
 		clk_disable_unprepare(priv->usb2_trk_clk);
 	}
-
-	mutex_unlock(&padctl->lock);
 }
 
 static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl)
@@ -667,17 +663,8 @@ static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl)
 	struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
 	u32 value;
 
-	mutex_lock(&padctl->lock);
-
-	if (WARN_ON(priv->bias_pad_enable == 0)) {
-		mutex_unlock(&padctl->lock);
-		return;
-	}
-
-	if (--priv->bias_pad_enable > 0) {
-		mutex_unlock(&padctl->lock);
+	if (!bitmap_empty(priv->utmi_pad_enabled, TEGRA_UTMI_PAD_MAX))
 		return;
-	}
 
 	value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL1);
 	value |= USB2_PD_TRK;
@@ -690,13 +677,13 @@ static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl)
 		clk_disable_unprepare(priv->usb2_trk_clk);
 	}
 
-	mutex_unlock(&padctl->lock);
 }
 
 static void tegra186_utmi_pad_power_on(struct phy *phy)
 {
 	struct tegra_xusb_lane *lane = phy_get_drvdata(phy);
 	struct tegra_xusb_padctl *padctl = lane->pad->padctl;
+	struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
 	struct tegra_xusb_usb2_port *port;
 	struct device *dev = padctl->dev;
 	unsigned int index = lane->index;
@@ -705,9 +692,16 @@ static void tegra186_utmi_pad_power_on(struct phy *phy)
 	if (!phy)
 		return;
 
+	mutex_lock(&padctl->lock);
+	if (test_bit(index, priv->utmi_pad_enabled)) {
+		mutex_unlock(&padctl->lock);
+		return;
+	}
+
 	port = tegra_xusb_find_usb2_port(padctl, index);
 	if (!port) {
 		dev_err(dev, "no port found for USB2 lane %u\n", index);
+		mutex_unlock(&padctl->lock);
 		return;
 	}
 
@@ -724,18 +718,28 @@ static void tegra186_utmi_pad_power_on(struct phy *phy)
 	value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index));
 	value &= ~USB2_OTG_PD_DR;
 	padctl_writel(padctl, value, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index));
+
+	set_bit(index, priv->utmi_pad_enabled);
+	mutex_unlock(&padctl->lock);
 }
 
 static void tegra186_utmi_pad_power_down(struct phy *phy)
 {
 	struct tegra_xusb_lane *lane = phy_get_drvdata(phy);
 	struct tegra_xusb_padctl *padctl = lane->pad->padctl;
+	struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
 	unsigned int index = lane->index;
 	u32 value;
 
 	if (!phy)
 		return;
 
+	mutex_lock(&padctl->lock);
+	if (!test_bit(index, priv->utmi_pad_enabled)) {
+		mutex_unlock(&padctl->lock);
+		return;
+	}
+
 	dev_dbg(padctl->dev, "power down UTMI pad %u\n", index);
 
 	value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL0(index));
@@ -748,7 +752,11 @@ static void tegra186_utmi_pad_power_down(struct phy *phy)
 
 	udelay(2);
 
+	clear_bit(index, priv->utmi_pad_enabled);
+
 	tegra186_utmi_bias_pad_power_off(padctl);
+
+	mutex_unlock(&padctl->lock);
 }
 
 static int tegra186_xusb_padctl_vbus_override(struct tegra_xusb_padctl *padctl,
diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c
index 79d4814d758d..c89df95aa6ca 100644
--- a/drivers/phy/tegra/xusb.c
+++ b/drivers/phy/tegra/xusb.c
@@ -548,16 +548,16 @@ static int tegra_xusb_port_init(struct tegra_xusb_port *port,
 
 	err = dev_set_name(&port->dev, "%s-%u", name, index);
 	if (err < 0)
-		goto unregister;
+		goto put_device;
 
 	err = device_add(&port->dev);
 	if (err < 0)
-		goto unregister;
+		goto put_device;
 
 	return 0;
 
-unregister:
-	device_unregister(&port->dev);
+put_device:
+	put_device(&port->dev);
 	return err;
 }
 
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 842a1e6cbfc4..18de31328540 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -37,16 +37,16 @@ static inline const struct group_desc *imx_pinctrl_find_group_by_name(
 				struct pinctrl_dev *pctldev,
 				const char *name)
 {
-	const struct group_desc *grp = NULL;
+	const struct group_desc *grp;
 	int i;
 
 	for (i = 0; i < pctldev->num_groups; i++) {
 		grp = pinctrl_generic_get_group(pctldev, i);
 		if (grp && !strcmp(grp->grp.name, name))
-			break;
+			return grp;
 	}
 
-	return grp;
+	return NULL;
 }
 
 static void imx_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s,
diff --git a/drivers/pinctrl/mediatek/mtk-eint.c b/drivers/pinctrl/mediatek/mtk-eint.c
index ced4ee509b5b..b4eb2beab691 100644
--- a/drivers/pinctrl/mediatek/mtk-eint.c
+++ b/drivers/pinctrl/mediatek/mtk-eint.c
@@ -449,7 +449,7 @@ int mtk_eint_set_debounce(struct mtk_eint *eint, unsigned long eint_num,
 		return -EOPNOTSUPP;
 
 	virq = irq_find_mapping(eint->domain, eint_num);
-	eint_offset = (eint_num % 4) * 8;
+	eint_offset = (idx % 4) * 8;
 	d = irq_get_irq_data(virq);
 
 	set_offset = (idx / 4) * 4 + eint->regs->dbnc_set;
diff --git a/drivers/pinctrl/mediatek/pinctrl-airoha.c b/drivers/pinctrl/mediatek/pinctrl-airoha.c
index 547a798b71c8..5d84a778683d 100644
--- a/drivers/pinctrl/mediatek/pinctrl-airoha.c
+++ b/drivers/pinctrl/mediatek/pinctrl-airoha.c
@@ -6,6 +6,7 @@
  */
 
 #include <dt-bindings/pinctrl/mt65xx.h>
+#include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/cleanup.h>
 #include <linux/gpio/driver.h>
@@ -112,39 +113,19 @@
 #define REG_LAN_LED1_MAPPING			0x0280
 
 #define LAN4_LED_MAPPING_MASK			GENMASK(18, 16)
-#define LAN4_PHY4_LED_MAP			BIT(18)
-#define LAN4_PHY2_LED_MAP			BIT(17)
-#define LAN4_PHY1_LED_MAP			BIT(16)
-#define LAN4_PHY0_LED_MAP			0
-#define LAN4_PHY3_LED_MAP			GENMASK(17, 16)
+#define LAN4_PHY_LED_MAP(_n)			FIELD_PREP_CONST(LAN4_LED_MAPPING_MASK, (_n))
 
 #define LAN3_LED_MAPPING_MASK			GENMASK(14, 12)
-#define LAN3_PHY4_LED_MAP			BIT(14)
-#define LAN3_PHY2_LED_MAP			BIT(13)
-#define LAN3_PHY1_LED_MAP			BIT(12)
-#define LAN3_PHY0_LED_MAP			0
-#define LAN3_PHY3_LED_MAP			GENMASK(13, 12)
+#define LAN3_PHY_LED_MAP(_n)			FIELD_PREP_CONST(LAN3_LED_MAPPING_MASK, (_n))
 
 #define LAN2_LED_MAPPING_MASK			GENMASK(10, 8)
-#define LAN2_PHY4_LED_MAP			BIT(12)
-#define LAN2_PHY2_LED_MAP			BIT(11)
-#define LAN2_PHY1_LED_MAP			BIT(10)
-#define LAN2_PHY0_LED_MAP			0
-#define LAN2_PHY3_LED_MAP			GENMASK(11, 10)
+#define LAN2_PHY_LED_MAP(_n)			FIELD_PREP_CONST(LAN2_LED_MAPPING_MASK, (_n))
 
 #define LAN1_LED_MAPPING_MASK			GENMASK(6, 4)
-#define LAN1_PHY4_LED_MAP			BIT(6)
-#define LAN1_PHY2_LED_MAP			BIT(5)
-#define LAN1_PHY1_LED_MAP			BIT(4)
-#define LAN1_PHY0_LED_MAP			0
-#define LAN1_PHY3_LED_MAP			GENMASK(5, 4)
+#define LAN1_PHY_LED_MAP(_n)			FIELD_PREP_CONST(LAN1_LED_MAPPING_MASK, (_n))
 
 #define LAN0_LED_MAPPING_MASK			GENMASK(2, 0)
-#define LAN0_PHY4_LED_MAP			BIT(3)
-#define LAN0_PHY2_LED_MAP			BIT(2)
-#define LAN0_PHY1_LED_MAP			BIT(1)
-#define LAN0_PHY0_LED_MAP			0
-#define LAN0_PHY3_LED_MAP			GENMASK(2, 1)
+#define LAN0_PHY_LED_MAP(_n)			FIELD_PREP_CONST(LAN0_LED_MAPPING_MASK, (_n))
 
 /* CONF */
 #define REG_I2C_SDA_E2				0x001c
@@ -1476,8 +1457,8 @@ static const struct airoha_pinctrl_func_group phy1_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN1_LED_MAPPING_MASK,
-			LAN1_PHY1_LED_MAP
+			LAN0_LED_MAPPING_MASK,
+			LAN0_PHY_LED_MAP(0)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1491,8 +1472,8 @@ static const struct airoha_pinctrl_func_group phy1_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN2_LED_MAPPING_MASK,
-			LAN2_PHY1_LED_MAP
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY_LED_MAP(0)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1506,8 +1487,8 @@ static const struct airoha_pinctrl_func_group phy1_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN3_LED_MAPPING_MASK,
-			LAN3_PHY1_LED_MAP
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY_LED_MAP(0)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1521,8 +1502,8 @@ static const struct airoha_pinctrl_func_group phy1_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN4_LED_MAPPING_MASK,
-			LAN4_PHY1_LED_MAP
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY_LED_MAP(0)
 		},
 		.regmap_size = 2,
 	},
@@ -1540,8 +1521,8 @@ static const struct airoha_pinctrl_func_group phy2_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN1_LED_MAPPING_MASK,
-			LAN1_PHY2_LED_MAP
+			LAN0_LED_MAPPING_MASK,
+			LAN0_PHY_LED_MAP(1)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1555,8 +1536,8 @@ static const struct airoha_pinctrl_func_group phy2_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN2_LED_MAPPING_MASK,
-			LAN2_PHY2_LED_MAP
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY_LED_MAP(1)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1570,8 +1551,8 @@ static const struct airoha_pinctrl_func_group phy2_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN3_LED_MAPPING_MASK,
-			LAN3_PHY2_LED_MAP
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY_LED_MAP(1)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1585,8 +1566,8 @@ static const struct airoha_pinctrl_func_group phy2_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN4_LED_MAPPING_MASK,
-			LAN4_PHY2_LED_MAP
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY_LED_MAP(1)
 		},
 		.regmap_size = 2,
 	},
@@ -1604,8 +1585,8 @@ static const struct airoha_pinctrl_func_group phy3_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN1_LED_MAPPING_MASK,
-			LAN1_PHY3_LED_MAP
+			LAN0_LED_MAPPING_MASK,
+			LAN0_PHY_LED_MAP(2)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1619,8 +1600,8 @@ static const struct airoha_pinctrl_func_group phy3_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN2_LED_MAPPING_MASK,
-			LAN2_PHY3_LED_MAP
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY_LED_MAP(2)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1634,8 +1615,8 @@ static const struct airoha_pinctrl_func_group phy3_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN3_LED_MAPPING_MASK,
-			LAN3_PHY3_LED_MAP
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY_LED_MAP(2)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1649,8 +1630,8 @@ static const struct airoha_pinctrl_func_group phy3_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN4_LED_MAPPING_MASK,
-			LAN4_PHY3_LED_MAP
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY_LED_MAP(2)
 		},
 		.regmap_size = 2,
 	},
@@ -1668,8 +1649,8 @@ static const struct airoha_pinctrl_func_group phy4_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN1_LED_MAPPING_MASK,
-			LAN1_PHY4_LED_MAP
+			LAN0_LED_MAPPING_MASK,
+			LAN0_PHY_LED_MAP(3)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1683,8 +1664,8 @@ static const struct airoha_pinctrl_func_group phy4_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN2_LED_MAPPING_MASK,
-			LAN2_PHY4_LED_MAP
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY_LED_MAP(3)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1698,8 +1679,8 @@ static const struct airoha_pinctrl_func_group phy4_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN3_LED_MAPPING_MASK,
-			LAN3_PHY4_LED_MAP
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY_LED_MAP(3)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1713,8 +1694,8 @@ static const struct airoha_pinctrl_func_group phy4_led0_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED0_MAPPING,
-			LAN4_LED_MAPPING_MASK,
-			LAN4_PHY4_LED_MAP
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY_LED_MAP(3)
 		},
 		.regmap_size = 2,
 	},
@@ -1732,8 +1713,8 @@ static const struct airoha_pinctrl_func_group phy1_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN1_LED_MAPPING_MASK,
-			LAN1_PHY1_LED_MAP
+			LAN0_LED_MAPPING_MASK,
+			LAN0_PHY_LED_MAP(0)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1747,8 +1728,8 @@ static const struct airoha_pinctrl_func_group phy1_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN2_LED_MAPPING_MASK,
-			LAN2_PHY1_LED_MAP
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY_LED_MAP(0)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1762,8 +1743,8 @@ static const struct airoha_pinctrl_func_group phy1_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN3_LED_MAPPING_MASK,
-			LAN3_PHY1_LED_MAP
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY_LED_MAP(0)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1777,8 +1758,8 @@ static const struct airoha_pinctrl_func_group phy1_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN4_LED_MAPPING_MASK,
-			LAN4_PHY1_LED_MAP
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY_LED_MAP(0)
 		},
 		.regmap_size = 2,
 	},
@@ -1796,8 +1777,8 @@ static const struct airoha_pinctrl_func_group phy2_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN1_LED_MAPPING_MASK,
-			LAN1_PHY2_LED_MAP
+			LAN0_LED_MAPPING_MASK,
+			LAN0_PHY_LED_MAP(1)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1811,8 +1792,8 @@ static const struct airoha_pinctrl_func_group phy2_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN2_LED_MAPPING_MASK,
-			LAN2_PHY2_LED_MAP
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY_LED_MAP(1)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1826,8 +1807,8 @@ static const struct airoha_pinctrl_func_group phy2_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN3_LED_MAPPING_MASK,
-			LAN3_PHY2_LED_MAP
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY_LED_MAP(1)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1841,8 +1822,8 @@ static const struct airoha_pinctrl_func_group phy2_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN4_LED_MAPPING_MASK,
-			LAN4_PHY2_LED_MAP
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY_LED_MAP(1)
 		},
 		.regmap_size = 2,
 	},
@@ -1860,8 +1841,8 @@ static const struct airoha_pinctrl_func_group phy3_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN1_LED_MAPPING_MASK,
-			LAN1_PHY3_LED_MAP
+			LAN0_LED_MAPPING_MASK,
+			LAN0_PHY_LED_MAP(2)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1875,8 +1856,8 @@ static const struct airoha_pinctrl_func_group phy3_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN2_LED_MAPPING_MASK,
-			LAN2_PHY3_LED_MAP
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY_LED_MAP(2)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1890,8 +1871,8 @@ static const struct airoha_pinctrl_func_group phy3_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN3_LED_MAPPING_MASK,
-			LAN3_PHY3_LED_MAP
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY_LED_MAP(2)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1905,8 +1886,8 @@ static const struct airoha_pinctrl_func_group phy3_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN4_LED_MAPPING_MASK,
-			LAN4_PHY3_LED_MAP
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY_LED_MAP(2)
 		},
 		.regmap_size = 2,
 	},
@@ -1924,8 +1905,8 @@ static const struct airoha_pinctrl_func_group phy4_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN1_LED_MAPPING_MASK,
-			LAN1_PHY4_LED_MAP
+			LAN0_LED_MAPPING_MASK,
+			LAN0_PHY_LED_MAP(3)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1939,8 +1920,8 @@ static const struct airoha_pinctrl_func_group phy4_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN2_LED_MAPPING_MASK,
-			LAN2_PHY4_LED_MAP
+			LAN1_LED_MAPPING_MASK,
+			LAN1_PHY_LED_MAP(3)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1954,8 +1935,8 @@ static const struct airoha_pinctrl_func_group phy4_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN3_LED_MAPPING_MASK,
-			LAN3_PHY4_LED_MAP
+			LAN2_LED_MAPPING_MASK,
+			LAN2_PHY_LED_MAP(3)
 		},
 		.regmap_size = 2,
 	}, {
@@ -1969,8 +1950,8 @@ static const struct airoha_pinctrl_func_group phy4_led1_func_group[] = {
 		.regmap[1] = {
 			AIROHA_FUNC_MUX,
 			REG_LAN_LED1_MAPPING,
-			LAN4_LED_MAPPING_MASK,
-			LAN4_PHY4_LED_MAP
+			LAN3_LED_MAPPING_MASK,
+			LAN3_PHY_LED_MAP(3)
 		},
 		.regmap_size = 2,
 	},
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index 91edb539925a..8596f3541265 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -1015,9 +1015,15 @@ static int mtk_eint_init(struct mtk_pinctrl *pctl, struct platform_device *pdev)
 	if (!pctl->eint)
 		return -ENOMEM;
 
-	pctl->eint->base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(pctl->eint->base))
-		return PTR_ERR(pctl->eint->base);
+	pctl->eint->nbase = 1;
+	/* mtk-eint expects an array */
+	pctl->eint->base = devm_kzalloc(pctl->dev, sizeof(pctl->eint->base), GFP_KERNEL);
+	if (!pctl->eint->base)
+		return -ENOMEM;
+
+	pctl->eint->base[0] = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(pctl->eint->base[0]))
+		return PTR_ERR(pctl->eint->base[0]);
 
 	pctl->eint->irq = irq_of_parse_and_map(np, 0);
 	if (!pctl->eint->irq)
diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c
index 253a0cc57e39..e5a32a0532ee 100644
--- a/drivers/pinctrl/meson/pinctrl-meson.c
+++ b/drivers/pinctrl/meson/pinctrl-meson.c
@@ -487,7 +487,7 @@ static int meson_pinconf_get(struct pinctrl_dev *pcdev, unsigned int pin,
 	case PIN_CONFIG_BIAS_PULL_DOWN:
 	case PIN_CONFIG_BIAS_PULL_UP:
 		if (meson_pinconf_get_pull(pc, pin) == param)
-			arg = 1;
+			arg = 60000;
 		else
 			return -EINVAL;
 		break;
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 82f0cc43bbf4..0eb816395dc6 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -44,7 +44,6 @@
  * @pctrl:          pinctrl handle.
  * @chip:           gpiochip handle.
  * @desc:           pin controller descriptor
- * @restart_nb:     restart notifier block.
  * @irq:            parent irq for the TLMM irq_chip.
  * @intr_target_use_scm: route irq to application cpu using scm calls
  * @lock:           Spinlock to protect register resources as well
@@ -64,7 +63,6 @@ struct msm_pinctrl {
 	struct pinctrl_dev *pctrl;
 	struct gpio_chip chip;
 	struct pinctrl_desc desc;
-	struct notifier_block restart_nb;
 
 	int irq;
 
@@ -1471,10 +1469,9 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
 	return 0;
 }
 
-static int msm_ps_hold_restart(struct notifier_block *nb, unsigned long action,
-			       void *data)
+static int msm_ps_hold_restart(struct sys_off_data *data)
 {
-	struct msm_pinctrl *pctrl = container_of(nb, struct msm_pinctrl, restart_nb);
+	struct msm_pinctrl *pctrl = data->cb_data;
 
 	writel(0, pctrl->regs[0] + PS_HOLD_OFFSET);
 	mdelay(1000);
@@ -1485,7 +1482,11 @@ static struct msm_pinctrl *poweroff_pctrl;
 
 static void msm_ps_hold_poweroff(void)
 {
-	msm_ps_hold_restart(&poweroff_pctrl->restart_nb, 0, NULL);
+	struct sys_off_data data = {
+		.cb_data = poweroff_pctrl,
+	};
+
+	msm_ps_hold_restart(&data);
 }
 
 static void msm_pinctrl_setup_pm_reset(struct msm_pinctrl *pctrl)
@@ -1495,9 +1496,11 @@ static void msm_pinctrl_setup_pm_reset(struct msm_pinctrl *pctrl)
 
 	for (i = 0; i < pctrl->soc->nfunctions; i++)
 		if (!strcmp(func[i].name, "ps_hold")) {
-			pctrl->restart_nb.notifier_call = msm_ps_hold_restart;
-			pctrl->restart_nb.priority = 128;
-			if (register_restart_handler(&pctrl->restart_nb))
+			if (devm_register_sys_off_handler(pctrl->dev,
+							  SYS_OFF_MODE_RESTART,
+							  128,
+							  msm_ps_hold_restart,
+							  pctrl))
 				dev_err(pctrl->dev,
 					"failed to setup restart handler.\n");
 			poweroff_pctrl = pctrl;
@@ -1599,8 +1602,6 @@ void msm_pinctrl_remove(struct platform_device *pdev)
 	struct msm_pinctrl *pctrl = platform_get_drvdata(pdev);
 
 	gpiochip_remove(&pctrl->chip);
-
-	unregister_restart_handler(&pctrl->restart_nb);
 }
 EXPORT_SYMBOL(msm_pinctrl_remove);
 
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8750.c b/drivers/pinctrl/qcom/pinctrl-sm8750.c
index 1af11cd95fb0..b94fb4ee0ec3 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8750.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8750.c
@@ -46,7 +46,9 @@
 		.out_bit = 1,                                         \
 		.intr_enable_bit = 0,                                 \
 		.intr_status_bit = 0,                                 \
-		.intr_target_bit = 5,                                 \
+		.intr_wakeup_present_bit = 6,                         \
+		.intr_wakeup_enable_bit = 7,                          \
+		.intr_target_bit = 8,                                 \
 		.intr_target_kpss_val = 3,                            \
 		.intr_raw_status_bit = 4,                             \
 		.intr_polarity_bit = 1,                               \
diff --git a/drivers/platform/mellanox/mlxbf-bootctl.c b/drivers/platform/mellanox/mlxbf-bootctl.c
index b95dcb8d483c..c18a5b96de5c 100644
--- a/drivers/platform/mellanox/mlxbf-bootctl.c
+++ b/drivers/platform/mellanox/mlxbf-bootctl.c
@@ -333,9 +333,9 @@ static ssize_t secure_boot_fuse_state_show(struct device *dev,
 			else
 				status = valid ? "Invalid" : "Free";
 		}
-		buf_len += sysfs_emit(buf + buf_len, "%d:%s ", key, status);
+		buf_len += sysfs_emit_at(buf, buf_len, "%d:%s ", key, status);
 	}
-	buf_len += sysfs_emit(buf + buf_len, "\n");
+	buf_len += sysfs_emit_at(buf, buf_len, "\n");
 
 	return buf_len;
 }
diff --git a/drivers/platform/x86/amd/hsmp/acpi.c b/drivers/platform/x86/amd/hsmp/acpi.c
index c1eccb3c80c5..eaae044e4f82 100644
--- a/drivers/platform/x86/amd/hsmp/acpi.c
+++ b/drivers/platform/x86/amd/hsmp/acpi.c
@@ -27,9 +27,8 @@
 
 #include "hsmp.h"
 
-#define DRIVER_NAME		"amd_hsmp"
+#define DRIVER_NAME		"hsmp_acpi"
 #define DRIVER_VERSION		"2.3"
-#define ACPI_HSMP_DEVICE_HID	"AMDI0097"
 
 /* These are the strings specified in ACPI table */
 #define MSG_IDOFF_STR		"MsgIdOffset"
diff --git a/drivers/platform/x86/amd/hsmp/hsmp.h b/drivers/platform/x86/amd/hsmp/hsmp.h
index af8b21f821d6..d58d4f0c20d5 100644
--- a/drivers/platform/x86/amd/hsmp/hsmp.h
+++ b/drivers/platform/x86/amd/hsmp/hsmp.h
@@ -23,6 +23,7 @@
 
 #define HSMP_CDEV_NAME		"hsmp_cdev"
 #define HSMP_DEVNODE_NAME	"hsmp"
+#define ACPI_HSMP_DEVICE_HID    "AMDI0097"
 
 struct hsmp_mbaddr_info {
 	u32 base_addr;
diff --git a/drivers/platform/x86/amd/hsmp/plat.c b/drivers/platform/x86/amd/hsmp/plat.c
index b9782a078dbd..81931e808bbc 100644
--- a/drivers/platform/x86/amd/hsmp/plat.c
+++ b/drivers/platform/x86/amd/hsmp/plat.c
@@ -11,6 +11,7 @@
 
 #include <asm/amd_hsmp.h>
 
+#include <linux/acpi.h>
 #include <linux/build_bug.h>
 #include <linux/device.h>
 #include <linux/module.h>
@@ -266,7 +267,7 @@ static bool legacy_hsmp_support(void)
 		}
 	case 0x1A:
 		switch (boot_cpu_data.x86_model) {
-		case 0x00 ... 0x1F:
+		case 0x00 ... 0x0F:
 			return true;
 		default:
 			return false;
@@ -288,6 +289,9 @@ static int __init hsmp_plt_init(void)
 		return ret;
 	}
 
+	if (acpi_dev_present(ACPI_HSMP_DEVICE_HID, NULL, -1))
+		return -ENODEV;
+
 	hsmp_pdev = get_hsmp_pdev();
 	if (!hsmp_pdev)
 		return -ENOMEM;
diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index b4f49720c87f..2e3f6fc67c56 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -217,6 +217,13 @@ static const struct dmi_system_id fwbug_list[] = {
 			DMI_MATCH(DMI_BIOS_VERSION, "03.05"),
 		}
 	},
+	{
+		.ident = "MECHREVO Wujie 14X (GX4HRXL)",
+		.driver_data = &quirk_spurious_8042,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "WUJIE14-GX4HRXL"),
+		}
+	},
 	{}
 };
 
diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c
index d789d6cab794..0329fafe14eb 100644
--- a/drivers/platform/x86/amd/pmc/pmc.c
+++ b/drivers/platform/x86/amd/pmc/pmc.c
@@ -644,10 +644,9 @@ static void amd_pmc_s2idle_check(void)
 	struct smu_metrics table;
 	int rc;
 
-	/* CZN: Ensure that future s0i3 entry attempts at least 10ms passed */
-	if (pdev->cpu_id == AMD_CPU_ID_CZN && !get_metrics_table(pdev, &table) &&
-	    table.s0i3_last_entry_status)
-		usleep_range(10000, 20000);
+	/* Avoid triggering OVP */
+	if (!get_metrics_table(pdev, &table) && table.s0i3_last_entry_status)
+		msleep(2500);
 
 	/* Dump the IdleMask before we add to the STB */
 	amd_pmc_idlemask_read(pdev, pdev->dev, NULL);
diff --git a/drivers/platform/x86/amd/pmf/auto-mode.c b/drivers/platform/x86/amd/pmf/auto-mode.c
index 02ff68be10d0..a184922bba8d 100644
--- a/drivers/platform/x86/amd/pmf/auto-mode.c
+++ b/drivers/platform/x86/amd/pmf/auto-mode.c
@@ -120,9 +120,9 @@ static void amd_pmf_set_automode(struct amd_pmf_dev *dev, int idx,
 	amd_pmf_send_cmd(dev, SET_SPPT_APU_ONLY, false, pwr_ctrl->sppt_apu_only, NULL);
 	amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false, pwr_ctrl->stt_min, NULL);
 	amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
-			 pwr_ctrl->stt_skin_temp[STT_TEMP_APU], NULL);
+			 fixp_q88_fromint(pwr_ctrl->stt_skin_temp[STT_TEMP_APU]), NULL);
 	amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
-			 pwr_ctrl->stt_skin_temp[STT_TEMP_HS2], NULL);
+			 fixp_q88_fromint(pwr_ctrl->stt_skin_temp[STT_TEMP_HS2]), NULL);
 
 	if (is_apmf_func_supported(dev, APMF_FUNC_SET_FAN_IDX))
 		apmf_update_fan_idx(dev, config_store.mode_set[idx].fan_control.manual,
diff --git a/drivers/platform/x86/amd/pmf/cnqf.c b/drivers/platform/x86/amd/pmf/cnqf.c
index bc8899e15c91..207a0b33d8d3 100644
--- a/drivers/platform/x86/amd/pmf/cnqf.c
+++ b/drivers/platform/x86/amd/pmf/cnqf.c
@@ -81,10 +81,10 @@ static int amd_pmf_set_cnqf(struct amd_pmf_dev *dev, int src, int idx,
 	amd_pmf_send_cmd(dev, SET_SPPT, false, pc->sppt, NULL);
 	amd_pmf_send_cmd(dev, SET_SPPT_APU_ONLY, false, pc->sppt_apu_only, NULL);
 	amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false, pc->stt_min, NULL);
-	amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false, pc->stt_skin_temp[STT_TEMP_APU],
-			 NULL);
-	amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false, pc->stt_skin_temp[STT_TEMP_HS2],
-			 NULL);
+	amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
+			 fixp_q88_fromint(pc->stt_skin_temp[STT_TEMP_APU]), NULL);
+	amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
+			 fixp_q88_fromint(pc->stt_skin_temp[STT_TEMP_HS2]), NULL);
 
 	if (is_apmf_func_supported(dev, APMF_FUNC_SET_FAN_IDX))
 		apmf_update_fan_idx(dev,
diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
index a2cb2d5544f5..96821101ec77 100644
--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@@ -176,6 +176,20 @@ static void __maybe_unused amd_pmf_dump_registers(struct amd_pmf_dev *dev)
 	dev_dbg(dev->dev, "AMD_PMF_REGISTER_MESSAGE:%x\n", value);
 }
 
+/**
+ * fixp_q88_fromint: Convert integer to Q8.8
+ * @val: input value
+ *
+ * Converts an integer into binary fixed point format where 8 bits
+ * are used for integer and 8 bits are used for the decimal.
+ *
+ * Return: unsigned integer converted to Q8.8 format
+ */
+u32 fixp_q88_fromint(u32 val)
+{
+	return val << 8;
+}
+
 int amd_pmf_send_cmd(struct amd_pmf_dev *dev, u8 message, bool get, u32 arg, u32 *data)
 {
 	int rc;
diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h
index e6bdee68ccf3..45b60238d527 100644
--- a/drivers/platform/x86/amd/pmf/pmf.h
+++ b/drivers/platform/x86/amd/pmf/pmf.h
@@ -777,6 +777,7 @@ int apmf_install_handler(struct amd_pmf_dev *pmf_dev);
 int apmf_os_power_slider_update(struct amd_pmf_dev *dev, u8 flag);
 int amd_pmf_set_dram_addr(struct amd_pmf_dev *dev, bool alloc_buffer);
 int amd_pmf_notify_sbios_heartbeat_event_v2(struct amd_pmf_dev *dev, u8 flag);
+u32 fixp_q88_fromint(u32 val);
 
 /* SPS Layer */
 int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf);
diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c
index d3083383f11f..49e14ca94a9e 100644
--- a/drivers/platform/x86/amd/pmf/sps.c
+++ b/drivers/platform/x86/amd/pmf/sps.c
@@ -198,9 +198,11 @@ static void amd_pmf_update_slider_v2(struct amd_pmf_dev *dev, int idx)
 	amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false,
 			 apts_config_store.val[idx].stt_min_limit, NULL);
 	amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
-			 apts_config_store.val[idx].stt_skin_temp_limit_apu, NULL);
+			 fixp_q88_fromint(apts_config_store.val[idx].stt_skin_temp_limit_apu),
+			 NULL);
 	amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
-			 apts_config_store.val[idx].stt_skin_temp_limit_hs2, NULL);
+			 fixp_q88_fromint(apts_config_store.val[idx].stt_skin_temp_limit_hs2),
+			 NULL);
 }
 
 void amd_pmf_update_slider(struct amd_pmf_dev *dev, bool op, int idx,
@@ -217,9 +219,11 @@ void amd_pmf_update_slider(struct amd_pmf_dev *dev, bool op, int idx,
 		amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false,
 				 config_store.prop[src][idx].stt_min, NULL);
 		amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
-				 config_store.prop[src][idx].stt_skin_temp[STT_TEMP_APU], NULL);
+				 fixp_q88_fromint(config_store.prop[src][idx].stt_skin_temp[STT_TEMP_APU]),
+				 NULL);
 		amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
-				 config_store.prop[src][idx].stt_skin_temp[STT_TEMP_HS2], NULL);
+				 fixp_q88_fromint(config_store.prop[src][idx].stt_skin_temp[STT_TEMP_HS2]),
+				 NULL);
 	} else if (op == SLIDER_OP_GET) {
 		amd_pmf_send_cmd(dev, GET_SPL, true, ARG_NONE, &table->prop[src][idx].spl);
 		amd_pmf_send_cmd(dev, GET_FPPT, true, ARG_NONE, &table->prop[src][idx].fppt);
diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index a1e43873a07b..d3bd12ad036a 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -123,7 +123,8 @@ static void amd_pmf_apply_policies(struct amd_pmf_dev *dev, struct ta_pmf_enact_
 
 		case PMF_POLICY_STT_SKINTEMP_APU:
 			if (dev->prev_data->stt_skintemp_apu != val) {
-				amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false, val, NULL);
+				amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
+						 fixp_q88_fromint(val), NULL);
 				dev_dbg(dev->dev, "update STT_SKINTEMP_APU: %u\n", val);
 				dev->prev_data->stt_skintemp_apu = val;
 			}
@@ -131,7 +132,8 @@ static void amd_pmf_apply_policies(struct amd_pmf_dev *dev, struct ta_pmf_enact_
 
 		case PMF_POLICY_STT_SKINTEMP_HS2:
 			if (dev->prev_data->stt_skintemp_hs2 != val) {
-				amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false, val, NULL);
+				amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
+						 fixp_q88_fromint(val), NULL);
 				dev_dbg(dev->dev, "update STT_SKINTEMP_HS2: %u\n", val);
 				dev->prev_data->stt_skintemp_hs2 = val;
 			}
@@ -332,6 +334,11 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
 	return 0;
 }
 
+static inline bool amd_pmf_pb_valid(struct amd_pmf_dev *dev)
+{
+	return memchr_inv(dev->policy_buf, 0xff, dev->policy_sz);
+}
+
 #ifdef CONFIG_AMD_PMF_DEBUG
 static void amd_pmf_hex_dump_pb(struct amd_pmf_dev *dev)
 {
@@ -359,12 +366,22 @@ static ssize_t amd_pmf_get_pb_data(struct file *filp, const char __user *buf,
 	dev->policy_buf = new_policy_buf;
 	dev->policy_sz = length;
 
+	if (!amd_pmf_pb_valid(dev)) {
+		ret = -EINVAL;
+		goto cleanup;
+	}
+
 	amd_pmf_hex_dump_pb(dev);
 	ret = amd_pmf_start_policy_engine(dev);
 	if (ret < 0)
-		return ret;
+		goto cleanup;
 
 	return length;
+
+cleanup:
+	kfree(dev->policy_buf);
+	dev->policy_buf = NULL;
+	return ret;
 }
 
 static const struct file_operations pb_fops = {
@@ -526,6 +543,12 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 
 	memcpy_fromio(dev->policy_buf, dev->policy_base, dev->policy_sz);
 
+	if (!amd_pmf_pb_valid(dev)) {
+		dev_info(dev->dev, "No Smart PC policy present\n");
+		ret = -EINVAL;
+		goto err_free_policy;
+	}
+
 	amd_pmf_hex_dump_pb(dev);
 
 	dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL);
diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c
index d460dd194f19..a0a411b4f2d6 100644
--- a/drivers/platform/x86/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
@@ -426,11 +426,14 @@ static int asus_pega_lucid_set(struct asus_laptop *asus, int unit, bool enable)
 
 static int pega_acc_axis(struct asus_laptop *asus, int curr, char *method)
 {
+	unsigned long long val = (unsigned long long)curr;
+	acpi_status status;
 	int i, delta;
-	unsigned long long val;
-	for (i = 0; i < PEGA_ACC_RETRIES; i++) {
-		acpi_evaluate_integer(asus->handle, method, NULL, &val);
 
+	for (i = 0; i < PEGA_ACC_RETRIES; i++) {
+		status = acpi_evaluate_integer(asus->handle, method, NULL, &val);
+		if (ACPI_FAILURE(status))
+			continue;
 		/* The output is noisy.  From reading the ASL
 		 * dissassembly, timeout errors are returned with 1's
 		 * in the high word, and the lack of locking around
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 38ef778e8c19..47cc766624d7 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -304,6 +304,7 @@ struct asus_wmi {
 
 	u32 kbd_rgb_dev;
 	bool kbd_rgb_state_available;
+	bool oobe_state_available;
 
 	u8 throttle_thermal_policy_mode;
 	u32 throttle_thermal_policy_dev;
@@ -1826,7 +1827,7 @@ static int asus_wmi_led_init(struct asus_wmi *asus)
 			goto error;
 	}
 
-	if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_OOBE)) {
+	if (asus->oobe_state_available) {
 		/*
 		 * Disable OOBE state, so that e.g. the keyboard backlight
 		 * works.
@@ -4723,6 +4724,7 @@ static int asus_wmi_add(struct platform_device *pdev)
 	asus->egpu_enable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_EGPU);
 	asus->dgpu_disable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_DGPU);
 	asus->kbd_rgb_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_TUF_RGB_STATE);
+	asus->oobe_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_OOBE);
 	asus->ally_mcu_usb_switch = acpi_has_method(NULL, ASUS_USB0_PWR_EC0_CSEE)
 						&& dmi_check_system(asus_ally_mcu_quirk);
 
@@ -4777,7 +4779,8 @@ static int asus_wmi_add(struct platform_device *pdev)
 		goto fail_leds;
 
 	asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result);
-	if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
+	if ((result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) ==
+	    (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
 		asus->driver->wlan_ctrl_by_user = 1;
 
 	if (!(asus->driver->wlan_ctrl_by_user && ashs_present())) {
@@ -4970,6 +4973,13 @@ static int asus_hotk_restore(struct device *device)
 	}
 	if (!IS_ERR_OR_NULL(asus->kbd_led.dev))
 		kbd_led_update(asus);
+	if (asus->oobe_state_available) {
+		/*
+		 * Disable OOBE state, so that e.g. the keyboard backlight
+		 * works.
+		 */
+		asus_wmi_set_devstate(ASUS_WMI_DEVID_OOBE, 1, NULL);
+	}
 
 	if (asus_wmi_has_fnlock_key(asus))
 		asus_wmi_fnlock_update(asus);
diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c
index 3d3014b5adf0..08b82c151e07 100644
--- a/drivers/platform/x86/dell/alienware-wmi-wmax.c
+++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c
@@ -62,11 +62,43 @@ static struct awcc_quirks empty_quirks;
 
 static const struct dmi_system_id awcc_dmi_table[] __initconst = {
 	{
+		.ident = "Alienware Area-51m R2",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware Area-51m R2"),
+		},
+		.driver_data = &generic_quirks,
+	},
+	{
+		.ident = "Alienware m15 R7",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m15 R7"),
+		},
+		.driver_data = &generic_quirks,
+	},
+	{
+		.ident = "Alienware m16 R1",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1"),
+		},
+		.driver_data = &g_series_quirks,
+	},
+	{
 		.ident = "Alienware m16 R1 AMD",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"),
 		},
+		.driver_data = &g_series_quirks,
+	},
+	{
+		.ident = "Alienware m16 R2",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R2"),
+		},
 		.driver_data = &generic_quirks,
 	},
 	{
@@ -94,6 +126,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
 		.driver_data = &generic_quirks,
 	},
 	{
+		.ident = "Alienware x15 R2",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware x15 R2"),
+		},
+		.driver_data = &generic_quirks,
+	},
+	{
 		.ident = "Alienware x17 R2",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
@@ -126,6 +166,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
 		.driver_data = &g_series_quirks,
 	},
 	{
+		.ident = "Dell Inc. G16 7630",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Dell G16 7630"),
+		},
+		.driver_data = &g_series_quirks,
+	},
+	{
 		.ident = "Dell Inc. G3 3500",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
@@ -149,6 +197,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
 		},
 		.driver_data = &g_series_quirks,
 	},
+	{
+		.ident = "Dell Inc. G5 5505",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "G5 5505"),
+		},
+		.driver_data = &g_series_quirks,
+	},
 };
 
 enum WMAX_THERMAL_INFORMATION_OPERATIONS {
@@ -607,12 +663,10 @@ static int thermal_profile_probe(void *drvdata, unsigned long *choices)
 	for (u32 i = 0; i < sys_desc[3]; i++) {
 		ret = wmax_thermal_information(priv->wdev, WMAX_OPERATION_LIST_IDS,
 					       i + first_mode, &out_data);
-
-		if (ret == -EIO)
-			return ret;
-
 		if (ret == -EBADRQC)
 			break;
+		if (ret)
+			return ret;
 
 		if (!is_wmax_thermal_code(out_data))
 			continue;
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index 17a09b7784ed..ede483573fe0 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -1294,6 +1294,16 @@ static const struct key_entry ideapad_keymap[] = {
 	/* Specific to some newer models */
 	{ KE_KEY,	0x3e | IDEAPAD_WMI_KEY, { KEY_MICMUTE } },
 	{ KE_KEY,	0x3f | IDEAPAD_WMI_KEY, { KEY_RFKILL } },
+	/* Star- (User Assignable Key) */
+	{ KE_KEY,	0x44 | IDEAPAD_WMI_KEY, { KEY_PROG1 } },
+	/* Eye */
+	{ KE_KEY,	0x45 | IDEAPAD_WMI_KEY, { KEY_PROG3 } },
+	/* Performance toggle also Fn+Q, handled inside ideapad_wmi_notify() */
+	{ KE_KEY,	0x3d | IDEAPAD_WMI_KEY, { KEY_PROG4 } },
+	/* shift + prtsc */
+	{ KE_KEY,   0x2d | IDEAPAD_WMI_KEY, { KEY_CUT } },
+	{ KE_KEY,   0x29 | IDEAPAD_WMI_KEY, { KEY_TOUCHPAD_TOGGLE } },
+	{ KE_KEY,   0x2a | IDEAPAD_WMI_KEY, { KEY_ROOT_MENU } },
 
 	{ KE_END },
 };
@@ -2080,6 +2090,12 @@ static void ideapad_wmi_notify(struct wmi_device *wdev, union acpi_object *data)
 		dev_dbg(&wdev->dev, "WMI fn-key event: 0x%llx\n",
 			data->integer.value);
 
+		/* performance button triggered by 0x3d */
+		if (data->integer.value == 0x3d && priv->dytc) {
+			platform_profile_cycle();
+			break;
+		}
+
 		/* 0x02 FnLock, 0x03 Esc */
 		if (data->integer.value == 0x02 || data->integer.value == 0x03)
 			ideapad_fn_lock_led_notify(priv, data->integer.value == 0x02);
diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 88a1a9ff2f34..0b5e43444ed6 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -44,16 +44,17 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Alex Hung");
 
 static const struct acpi_device_id intel_hid_ids[] = {
-	{"INT33D5", 0},
-	{"INTC1051", 0},
-	{"INTC1054", 0},
-	{"INTC1070", 0},
-	{"INTC1076", 0},
-	{"INTC1077", 0},
-	{"INTC1078", 0},
-	{"INTC107B", 0},
-	{"INTC10CB", 0},
-	{"", 0},
+	{ "INT33D5" },
+	{ "INTC1051" },
+	{ "INTC1054" },
+	{ "INTC1070" },
+	{ "INTC1076" },
+	{ "INTC1077" },
+	{ "INTC1078" },
+	{ "INTC107B" },
+	{ "INTC10CB" },
+	{ "INTC10CC" },
+	{ }
 };
 MODULE_DEVICE_TABLE(acpi, intel_hid_ids);
 
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
index 40bbf8e45fa4..bdee5d00f30b 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
@@ -146,15 +146,13 @@ static int uncore_event_cpu_online(unsigned int cpu)
 {
 	struct uncore_data *data;
 	int target;
+	int ret;
 
 	/* Check if there is an online cpu in the package for uncore MSR */
 	target = cpumask_any_and(&uncore_cpu_mask, topology_die_cpumask(cpu));
 	if (target < nr_cpu_ids)
 		return 0;
 
-	/* Use this CPU on this die as a control CPU */
-	cpumask_set_cpu(cpu, &uncore_cpu_mask);
-
 	data = uncore_get_instance(cpu);
 	if (!data)
 		return 0;
@@ -163,7 +161,14 @@ static int uncore_event_cpu_online(unsigned int cpu)
 	data->die_id = topology_die_id(cpu);
 	data->domain_id = UNCORE_DOMAIN_ID_INVALID;
 
-	return uncore_freq_add_entry(data, cpu);
+	ret = uncore_freq_add_entry(data, cpu);
+	if (ret)
+		return ret;
+
+	/* Use this CPU on this die as a control CPU */
+	cpumask_set_cpu(cpu, &uncore_cpu_mask);
+
+	return 0;
 }
 
 static int uncore_event_cpu_offline(unsigned int cpu)
diff --git a/drivers/platform/x86/msi-wmi-platform.c b/drivers/platform/x86/msi-wmi-platform.c
index 9b5c7f8c79b0..dc5e9878cb68 100644
--- a/drivers/platform/x86/msi-wmi-platform.c
+++ b/drivers/platform/x86/msi-wmi-platform.c
@@ -10,6 +10,7 @@
 #include <linux/acpi.h>
 #include <linux/bits.h>
 #include <linux/bitfield.h>
+#include <linux/cleanup.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/device/driver.h>
@@ -17,6 +18,7 @@
 #include <linux/hwmon.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/printk.h>
 #include <linux/rwsem.h>
 #include <linux/types.h>
@@ -76,8 +78,13 @@ enum msi_wmi_platform_method {
 	MSI_PLATFORM_GET_WMI		= 0x1d,
 };
 
-struct msi_wmi_platform_debugfs_data {
+struct msi_wmi_platform_data {
 	struct wmi_device *wdev;
+	struct mutex wmi_lock;	/* Necessary when calling WMI methods */
+};
+
+struct msi_wmi_platform_debugfs_data {
+	struct msi_wmi_platform_data *data;
 	enum msi_wmi_platform_method method;
 	struct rw_semaphore buffer_lock;	/* Protects debugfs buffer */
 	size_t length;
@@ -132,8 +139,9 @@ static int msi_wmi_platform_parse_buffer(union acpi_object *obj, u8 *output, siz
 	return 0;
 }
 
-static int msi_wmi_platform_query(struct wmi_device *wdev, enum msi_wmi_platform_method method,
-				  u8 *input, size_t input_length, u8 *output, size_t output_length)
+static int msi_wmi_platform_query(struct msi_wmi_platform_data *data,
+				  enum msi_wmi_platform_method method, u8 *input,
+				  size_t input_length, u8 *output, size_t output_length)
 {
 	struct acpi_buffer out = { ACPI_ALLOCATE_BUFFER, NULL };
 	struct acpi_buffer in = {
@@ -147,9 +155,15 @@ static int msi_wmi_platform_query(struct wmi_device *wdev, enum msi_wmi_platform
 	if (!input_length || !output_length)
 		return -EINVAL;
 
-	status = wmidev_evaluate_method(wdev, 0x0, method, &in, &out);
-	if (ACPI_FAILURE(status))
-		return -EIO;
+	/*
+	 * The ACPI control method responsible for handling the WMI method calls
+	 * is not thread-safe. Because of this we have to do the locking ourself.
+	 */
+	scoped_guard(mutex, &data->wmi_lock) {
+		status = wmidev_evaluate_method(data->wdev, 0x0, method, &in, &out);
+		if (ACPI_FAILURE(status))
+			return -EIO;
+	}
 
 	obj = out.pointer;
 	if (!obj)
@@ -170,22 +184,22 @@ static umode_t msi_wmi_platform_is_visible(const void *drvdata, enum hwmon_senso
 static int msi_wmi_platform_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 				 int channel, long *val)
 {
-	struct wmi_device *wdev = dev_get_drvdata(dev);
+	struct msi_wmi_platform_data *data = dev_get_drvdata(dev);
 	u8 input[32] = { 0 };
 	u8 output[32];
-	u16 data;
+	u16 value;
 	int ret;
 
-	ret = msi_wmi_platform_query(wdev, MSI_PLATFORM_GET_FAN, input, sizeof(input), output,
+	ret = msi_wmi_platform_query(data, MSI_PLATFORM_GET_FAN, input, sizeof(input), output,
 				     sizeof(output));
 	if (ret < 0)
 		return ret;
 
-	data = get_unaligned_be16(&output[channel * 2 + 1]);
-	if (!data)
+	value = get_unaligned_be16(&output[channel * 2 + 1]);
+	if (!value)
 		*val = 0;
 	else
-		*val = 480000 / data;
+		*val = 480000 / value;
 
 	return 0;
 }
@@ -231,7 +245,7 @@ static ssize_t msi_wmi_platform_write(struct file *fp, const char __user *input,
 		return ret;
 
 	down_write(&data->buffer_lock);
-	ret = msi_wmi_platform_query(data->wdev, data->method, payload, data->length, data->buffer,
+	ret = msi_wmi_platform_query(data->data, data->method, payload, data->length, data->buffer,
 				     data->length);
 	up_write(&data->buffer_lock);
 
@@ -277,17 +291,17 @@ static void msi_wmi_platform_debugfs_remove(void *data)
 	debugfs_remove_recursive(dir);
 }
 
-static void msi_wmi_platform_debugfs_add(struct wmi_device *wdev, struct dentry *dir,
+static void msi_wmi_platform_debugfs_add(struct msi_wmi_platform_data *drvdata, struct dentry *dir,
 					 const char *name, enum msi_wmi_platform_method method)
 {
 	struct msi_wmi_platform_debugfs_data *data;
 	struct dentry *entry;
 
-	data = devm_kzalloc(&wdev->dev, sizeof(*data), GFP_KERNEL);
+	data = devm_kzalloc(&drvdata->wdev->dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return;
 
-	data->wdev = wdev;
+	data->data = drvdata;
 	data->method = method;
 	init_rwsem(&data->buffer_lock);
 
@@ -298,82 +312,82 @@ static void msi_wmi_platform_debugfs_add(struct wmi_device *wdev, struct dentry
 
 	entry = debugfs_create_file(name, 0600, dir, data, &msi_wmi_platform_debugfs_fops);
 	if (IS_ERR(entry))
-		devm_kfree(&wdev->dev, data);
+		devm_kfree(&drvdata->wdev->dev, data);
 }
 
-static void msi_wmi_platform_debugfs_init(struct wmi_device *wdev)
+static void msi_wmi_platform_debugfs_init(struct msi_wmi_platform_data *data)
 {
 	struct dentry *dir;
 	char dir_name[64];
 	int ret, method;
 
-	scnprintf(dir_name, ARRAY_SIZE(dir_name), "%s-%s", DRIVER_NAME, dev_name(&wdev->dev));
+	scnprintf(dir_name, ARRAY_SIZE(dir_name), "%s-%s", DRIVER_NAME, dev_name(&data->wdev->dev));
 
 	dir = debugfs_create_dir(dir_name, NULL);
 	if (IS_ERR(dir))
 		return;
 
-	ret = devm_add_action_or_reset(&wdev->dev, msi_wmi_platform_debugfs_remove, dir);
+	ret = devm_add_action_or_reset(&data->wdev->dev, msi_wmi_platform_debugfs_remove, dir);
 	if (ret < 0)
 		return;
 
 	for (method = MSI_PLATFORM_GET_PACKAGE; method <= MSI_PLATFORM_GET_WMI; method++)
-		msi_wmi_platform_debugfs_add(wdev, dir, msi_wmi_platform_debugfs_names[method - 1],
+		msi_wmi_platform_debugfs_add(data, dir, msi_wmi_platform_debugfs_names[method - 1],
 					     method);
 }
 
-static int msi_wmi_platform_hwmon_init(struct wmi_device *wdev)
+static int msi_wmi_platform_hwmon_init(struct msi_wmi_platform_data *data)
 {
 	struct device *hdev;
 
-	hdev = devm_hwmon_device_register_with_info(&wdev->dev, "msi_wmi_platform", wdev,
+	hdev = devm_hwmon_device_register_with_info(&data->wdev->dev, "msi_wmi_platform", data,
 						    &msi_wmi_platform_chip_info, NULL);
 
 	return PTR_ERR_OR_ZERO(hdev);
 }
 
-static int msi_wmi_platform_ec_init(struct wmi_device *wdev)
+static int msi_wmi_platform_ec_init(struct msi_wmi_platform_data *data)
 {
 	u8 input[32] = { 0 };
 	u8 output[32];
 	u8 flags;
 	int ret;
 
-	ret = msi_wmi_platform_query(wdev, MSI_PLATFORM_GET_EC, input, sizeof(input), output,
+	ret = msi_wmi_platform_query(data, MSI_PLATFORM_GET_EC, input, sizeof(input), output,
 				     sizeof(output));
 	if (ret < 0)
 		return ret;
 
 	flags = output[MSI_PLATFORM_EC_FLAGS_OFFSET];
 
-	dev_dbg(&wdev->dev, "EC RAM version %lu.%lu\n",
+	dev_dbg(&data->wdev->dev, "EC RAM version %lu.%lu\n",
 		FIELD_GET(MSI_PLATFORM_EC_MAJOR_MASK, flags),
 		FIELD_GET(MSI_PLATFORM_EC_MINOR_MASK, flags));
-	dev_dbg(&wdev->dev, "EC firmware version %.28s\n",
+	dev_dbg(&data->wdev->dev, "EC firmware version %.28s\n",
 		&output[MSI_PLATFORM_EC_VERSION_OFFSET]);
 
 	if (!(flags & MSI_PLATFORM_EC_IS_TIGERLAKE)) {
 		if (!force)
 			return -ENODEV;
 
-		dev_warn(&wdev->dev, "Loading on a non-Tigerlake platform\n");
+		dev_warn(&data->wdev->dev, "Loading on a non-Tigerlake platform\n");
 	}
 
 	return 0;
 }
 
-static int msi_wmi_platform_init(struct wmi_device *wdev)
+static int msi_wmi_platform_init(struct msi_wmi_platform_data *data)
 {
 	u8 input[32] = { 0 };
 	u8 output[32];
 	int ret;
 
-	ret = msi_wmi_platform_query(wdev, MSI_PLATFORM_GET_WMI, input, sizeof(input), output,
+	ret = msi_wmi_platform_query(data, MSI_PLATFORM_GET_WMI, input, sizeof(input), output,
 				     sizeof(output));
 	if (ret < 0)
 		return ret;
 
-	dev_dbg(&wdev->dev, "WMI interface version %u.%u\n",
+	dev_dbg(&data->wdev->dev, "WMI interface version %u.%u\n",
 		output[MSI_PLATFORM_WMI_MAJOR_OFFSET],
 		output[MSI_PLATFORM_WMI_MINOR_OFFSET]);
 
@@ -381,7 +395,8 @@ static int msi_wmi_platform_init(struct wmi_device *wdev)
 		if (!force)
 			return -ENODEV;
 
-		dev_warn(&wdev->dev, "Loading despite unsupported WMI interface version (%u.%u)\n",
+		dev_warn(&data->wdev->dev,
+			 "Loading despite unsupported WMI interface version (%u.%u)\n",
 			 output[MSI_PLATFORM_WMI_MAJOR_OFFSET],
 			 output[MSI_PLATFORM_WMI_MINOR_OFFSET]);
 	}
@@ -391,19 +406,31 @@ static int msi_wmi_platform_init(struct wmi_device *wdev)
 
 static int msi_wmi_platform_probe(struct wmi_device *wdev, const void *context)
 {
+	struct msi_wmi_platform_data *data;
 	int ret;
 
-	ret = msi_wmi_platform_init(wdev);
+	data = devm_kzalloc(&wdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->wdev = wdev;
+	dev_set_drvdata(&wdev->dev, data);
+
+	ret = devm_mutex_init(&wdev->dev, &data->wmi_lock);
+	if (ret < 0)
+		return ret;
+
+	ret = msi_wmi_platform_init(data);
 	if (ret < 0)
 		return ret;
 
-	ret = msi_wmi_platform_ec_init(wdev);
+	ret = msi_wmi_platform_ec_init(data);
 	if (ret < 0)
 		return ret;
 
-	msi_wmi_platform_debugfs_init(wdev);
+	msi_wmi_platform_debugfs_init(data);
 
-	return msi_wmi_platform_hwmon_init(wdev);
+	return msi_wmi_platform_hwmon_init(data);
 }
 
 static const struct wmi_device_id msi_wmi_platform_id_table[] = {
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 5790095c175e..92b21e49faf6 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -11478,6 +11478,8 @@ static int __must_check __init get_thinkpad_model_data(
 		tp->vendor = PCI_VENDOR_ID_IBM;
 	else if (dmi_name_in_vendors("LENOVO"))
 		tp->vendor = PCI_VENDOR_ID_LENOVO;
+	else if (dmi_name_in_vendors("NEC"))
+		tp->vendor = PCI_VENDOR_ID_LENOVO;
 	else
 		return 0;
 
diff --git a/drivers/platform/x86/x86-android-tablets/dmi.c b/drivers/platform/x86/x86-android-tablets/dmi.c
index 3e5fa3b6e2fd..278c6d151dc4 100644
--- a/drivers/platform/x86/x86-android-tablets/dmi.c
+++ b/drivers/platform/x86/x86-android-tablets/dmi.c
@@ -180,6 +180,18 @@ const struct dmi_system_id x86_android_tablet_ids[] __initconst = {
 		.driver_data = (void *)&peaq_c1010_info,
 	},
 	{
+		/* Vexia Edu Atla 10 tablet 5V version */
+		.matches = {
+			/* Having all 3 of these not set is somewhat unique */
+			DMI_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "To be filled by O.E.M."),
+			DMI_MATCH(DMI_BOARD_NAME, "To be filled by O.E.M."),
+			/* Above strings are too generic, also match on BIOS date */
+			DMI_MATCH(DMI_BIOS_DATE, "05/14/2015"),
+		},
+		.driver_data = (void *)&vexia_edu_atla10_5v_info,
+	},
+	{
 		/* Vexia Edu Atla 10 tablet 9V version */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
@@ -187,7 +199,7 @@ const struct dmi_system_id x86_android_tablet_ids[] __initconst = {
 			/* Above strings are too generic, also match on BIOS date */
 			DMI_MATCH(DMI_BIOS_DATE, "08/25/2014"),
 		},
-		.driver_data = (void *)&vexia_edu_atla10_info,
+		.driver_data = (void *)&vexia_edu_atla10_9v_info,
 	},
 	{
 		/* Whitelabel (sold as various brands) TM800A550L */
diff --git a/drivers/platform/x86/x86-android-tablets/other.c b/drivers/platform/x86/x86-android-tablets/other.c
index 1d93d9edb23f..f7bd9f863c85 100644
--- a/drivers/platform/x86/x86-android-tablets/other.c
+++ b/drivers/platform/x86/x86-android-tablets/other.c
@@ -599,62 +599,122 @@ const struct x86_dev_info whitelabel_tm800a550l_info __initconst = {
 };
 
 /*
- * Vexia EDU ATLA 10 tablet, Android 4.2 / 4.4 + Guadalinex Ubuntu tablet
+ * Vexia EDU ATLA 10 tablet 5V, Android 4.4 + Guadalinex Ubuntu tablet
+ * distributed to schools in the Spanish Andalucía region.
+ */
+static const struct property_entry vexia_edu_atla10_5v_touchscreen_props[] = {
+	PROPERTY_ENTRY_U32("hid-descr-addr", 0x0000),
+	PROPERTY_ENTRY_U32("post-reset-deassert-delay-ms", 120),
+	{ }
+};
+
+static const struct software_node vexia_edu_atla10_5v_touchscreen_node = {
+	.properties = vexia_edu_atla10_5v_touchscreen_props,
+};
+
+static const struct x86_i2c_client_info vexia_edu_atla10_5v_i2c_clients[] __initconst = {
+	{
+		/* kxcjk1013 accelerometer */
+		.board_info = {
+			.type = "kxcjk1013",
+			.addr = 0x0f,
+			.dev_name = "kxcjk1013",
+		},
+		.adapter_path = "\\_SB_.I2C3",
+	}, {
+		/*  touchscreen controller */
+		.board_info = {
+			.type = "hid-over-i2c",
+			.addr = 0x38,
+			.dev_name = "FTSC1000",
+			.swnode = &vexia_edu_atla10_5v_touchscreen_node,
+		},
+		.adapter_path = "\\_SB_.I2C4",
+		.irq_data = {
+			.type = X86_ACPI_IRQ_TYPE_APIC,
+			.index = 0x44,
+			.trigger = ACPI_LEVEL_SENSITIVE,
+			.polarity = ACPI_ACTIVE_HIGH,
+		},
+	}
+};
+
+static struct gpiod_lookup_table vexia_edu_atla10_5v_ft5416_gpios = {
+	.dev_id = "i2c-FTSC1000",
+	.table = {
+		GPIO_LOOKUP("INT33FC:01", 26, "reset", GPIO_ACTIVE_LOW),
+		{ }
+	},
+};
+
+static struct gpiod_lookup_table * const vexia_edu_atla10_5v_gpios[] = {
+	&vexia_edu_atla10_5v_ft5416_gpios,
+	NULL
+};
+
+const struct x86_dev_info vexia_edu_atla10_5v_info __initconst = {
+	.i2c_client_info = vexia_edu_atla10_5v_i2c_clients,
+	.i2c_client_count = ARRAY_SIZE(vexia_edu_atla10_5v_i2c_clients),
+	.gpiod_lookup_tables = vexia_edu_atla10_5v_gpios,
+};
+
+/*
+ * Vexia EDU ATLA 10 tablet 9V, Android 4.2 + Guadalinex Ubuntu tablet
  * distributed to schools in the Spanish Andalucía region.
  */
 static const char * const crystal_cove_pwrsrc_psy[] = { "crystal_cove_pwrsrc" };
 
-static const struct property_entry vexia_edu_atla10_ulpmc_props[] = {
+static const struct property_entry vexia_edu_atla10_9v_ulpmc_props[] = {
 	PROPERTY_ENTRY_STRING_ARRAY("supplied-from", crystal_cove_pwrsrc_psy),
 	{ }
 };
 
-static const struct software_node vexia_edu_atla10_ulpmc_node = {
-	.properties = vexia_edu_atla10_ulpmc_props,
+static const struct software_node vexia_edu_atla10_9v_ulpmc_node = {
+	.properties = vexia_edu_atla10_9v_ulpmc_props,
 };
 
-static const char * const vexia_edu_atla10_accel_mount_matrix[] = {
+static const char * const vexia_edu_atla10_9v_accel_mount_matrix[] = {
 	"0", "-1", "0",
 	"1", "0", "0",
 	"0", "0", "1"
 };
 
-static const struct property_entry vexia_edu_atla10_accel_props[] = {
-	PROPERTY_ENTRY_STRING_ARRAY("mount-matrix", vexia_edu_atla10_accel_mount_matrix),
+static const struct property_entry vexia_edu_atla10_9v_accel_props[] = {
+	PROPERTY_ENTRY_STRING_ARRAY("mount-matrix", vexia_edu_atla10_9v_accel_mount_matrix),
 	{ }
 };
 
-static const struct software_node vexia_edu_atla10_accel_node = {
-	.properties = vexia_edu_atla10_accel_props,
+static const struct software_node vexia_edu_atla10_9v_accel_node = {
+	.properties = vexia_edu_atla10_9v_accel_props,
 };
 
-static const struct property_entry vexia_edu_atla10_touchscreen_props[] = {
+static const struct property_entry vexia_edu_atla10_9v_touchscreen_props[] = {
 	PROPERTY_ENTRY_U32("hid-descr-addr", 0x0000),
 	PROPERTY_ENTRY_U32("post-reset-deassert-delay-ms", 120),
 	{ }
 };
 
-static const struct software_node vexia_edu_atla10_touchscreen_node = {
-	.properties = vexia_edu_atla10_touchscreen_props,
+static const struct software_node vexia_edu_atla10_9v_touchscreen_node = {
+	.properties = vexia_edu_atla10_9v_touchscreen_props,
 };
 
-static const struct property_entry vexia_edu_atla10_pmic_props[] = {
+static const struct property_entry vexia_edu_atla10_9v_pmic_props[] = {
 	PROPERTY_ENTRY_BOOL("linux,register-pwrsrc-power_supply"),
 	{ }
 };
 
-static const struct software_node vexia_edu_atla10_pmic_node = {
-	.properties = vexia_edu_atla10_pmic_props,
+static const struct software_node vexia_edu_atla10_9v_pmic_node = {
+	.properties = vexia_edu_atla10_9v_pmic_props,
 };
 
-static const struct x86_i2c_client_info vexia_edu_atla10_i2c_clients[] __initconst = {
+static const struct x86_i2c_client_info vexia_edu_atla10_9v_i2c_clients[] __initconst = {
 	{
 		/* I2C attached embedded controller, used to access fuel-gauge */
 		.board_info = {
 			.type = "vexia_atla10_ec",
 			.addr = 0x76,
 			.dev_name = "ulpmc",
-			.swnode = &vexia_edu_atla10_ulpmc_node,
+			.swnode = &vexia_edu_atla10_9v_ulpmc_node,
 		},
 		.adapter_path = "0000:00:18.1",
 	}, {
@@ -679,7 +739,7 @@ static const struct x86_i2c_client_info vexia_edu_atla10_i2c_clients[] __initcon
 			.type = "kxtj21009",
 			.addr = 0x0f,
 			.dev_name = "kxtj21009",
-			.swnode = &vexia_edu_atla10_accel_node,
+			.swnode = &vexia_edu_atla10_9v_accel_node,
 		},
 		.adapter_path = "0000:00:18.5",
 	}, {
@@ -688,7 +748,7 @@ static const struct x86_i2c_client_info vexia_edu_atla10_i2c_clients[] __initcon
 			.type = "hid-over-i2c",
 			.addr = 0x38,
 			.dev_name = "FTSC1000",
-			.swnode = &vexia_edu_atla10_touchscreen_node,
+			.swnode = &vexia_edu_atla10_9v_touchscreen_node,
 		},
 		.adapter_path = "0000:00:18.6",
 		.irq_data = {
@@ -703,7 +763,7 @@ static const struct x86_i2c_client_info vexia_edu_atla10_i2c_clients[] __initcon
 			.type = "intel_soc_pmic_crc",
 			.addr = 0x6e,
 			.dev_name = "intel_soc_pmic_crc",
-			.swnode = &vexia_edu_atla10_pmic_node,
+			.swnode = &vexia_edu_atla10_9v_pmic_node,
 		},
 		.adapter_path = "0000:00:18.7",
 		.irq_data = {
@@ -715,7 +775,7 @@ static const struct x86_i2c_client_info vexia_edu_atla10_i2c_clients[] __initcon
 	}
 };
 
-static const struct x86_serdev_info vexia_edu_atla10_serdevs[] __initconst = {
+static const struct x86_serdev_info vexia_edu_atla10_9v_serdevs[] __initconst = {
 	{
 		.ctrl.pci.devfn = PCI_DEVFN(0x1e, 3),
 		.ctrl_devname = "serial0",
@@ -723,7 +783,7 @@ static const struct x86_serdev_info vexia_edu_atla10_serdevs[] __initconst = {
 	},
 };
 
-static struct gpiod_lookup_table vexia_edu_atla10_ft5416_gpios = {
+static struct gpiod_lookup_table vexia_edu_atla10_9v_ft5416_gpios = {
 	.dev_id = "i2c-FTSC1000",
 	.table = {
 		GPIO_LOOKUP("INT33FC:00", 60, "reset", GPIO_ACTIVE_LOW),
@@ -731,12 +791,12 @@ static struct gpiod_lookup_table vexia_edu_atla10_ft5416_gpios = {
 	},
 };
 
-static struct gpiod_lookup_table * const vexia_edu_atla10_gpios[] = {
-	&vexia_edu_atla10_ft5416_gpios,
+static struct gpiod_lookup_table * const vexia_edu_atla10_9v_gpios[] = {
+	&vexia_edu_atla10_9v_ft5416_gpios,
 	NULL
 };
 
-static int __init vexia_edu_atla10_init(struct device *dev)
+static int __init vexia_edu_atla10_9v_init(struct device *dev)
 {
 	struct pci_dev *pdev;
 	int ret;
@@ -760,13 +820,13 @@ static int __init vexia_edu_atla10_init(struct device *dev)
 	return 0;
 }
 
-const struct x86_dev_info vexia_edu_atla10_info __initconst = {
-	.i2c_client_info = vexia_edu_atla10_i2c_clients,
-	.i2c_client_count = ARRAY_SIZE(vexia_edu_atla10_i2c_clients),
-	.serdev_info = vexia_edu_atla10_serdevs,
-	.serdev_count = ARRAY_SIZE(vexia_edu_atla10_serdevs),
-	.gpiod_lookup_tables = vexia_edu_atla10_gpios,
-	.init = vexia_edu_atla10_init,
+const struct x86_dev_info vexia_edu_atla10_9v_info __initconst = {
+	.i2c_client_info = vexia_edu_atla10_9v_i2c_clients,
+	.i2c_client_count = ARRAY_SIZE(vexia_edu_atla10_9v_i2c_clients),
+	.serdev_info = vexia_edu_atla10_9v_serdevs,
+	.serdev_count = ARRAY_SIZE(vexia_edu_atla10_9v_serdevs),
+	.gpiod_lookup_tables = vexia_edu_atla10_9v_gpios,
+	.init = vexia_edu_atla10_9v_init,
 	.use_pci = true,
 };
 
diff --git a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
index 63a38a0069ba..dcf8d49e3b5f 100644
--- a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
+++ b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
@@ -127,7 +127,8 @@ extern const struct x86_dev_info nextbook_ares8_info;
 extern const struct x86_dev_info nextbook_ares8a_info;
 extern const struct x86_dev_info peaq_c1010_info;
 extern const struct x86_dev_info whitelabel_tm800a550l_info;
-extern const struct x86_dev_info vexia_edu_atla10_info;
+extern const struct x86_dev_info vexia_edu_atla10_5v_info;
+extern const struct x86_dev_info vexia_edu_atla10_9v_info;
 extern const struct x86_dev_info xiaomi_mipad2_info;
 extern const struct dmi_system_id x86_android_tablet_ids[];
 
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index edb058c19c9c..439dd0bf8644 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -33,7 +33,7 @@ struct power_supply_attr {
 [POWER_SUPPLY_PROP_ ## _name] =			\
 {						\
 	.prop_name = #_name,			\
-	.attr_name = #_name "\0",		\
+	.attr_name = #_name,			\
 	.text_values = _text,			\
 	.text_values_len = _len,		\
 }
diff --git a/drivers/pps/generators/pps_gen_tio.c b/drivers/pps/generators/pps_gen_tio.c
index 1d5ffe055463..de00a85bfafa 100644
--- a/drivers/pps/generators/pps_gen_tio.c
+++ b/drivers/pps/generators/pps_gen_tio.c
@@ -230,7 +230,7 @@ static int pps_gen_tio_probe(struct platform_device *pdev)
 	hrtimer_setup(&tio->timer, hrtimer_callback, CLOCK_REALTIME,
 		      HRTIMER_MODE_ABS);
 	spin_lock_init(&tio->lock);
-	platform_set_drvdata(pdev, &tio);
+	platform_set_drvdata(pdev, tio);
 
 	return 0;
 }
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 07bf7f9aae01..204278eb215e 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -44,7 +44,7 @@ config PTP_1588_CLOCK_DTE
 	depends on PTP_1588_CLOCK
 	depends on NET && HAS_IOMEM
 	depends on ARCH_BCM_MOBILE || (ARCH_BCM_IPROC && !(ARCH_BCM_NSP || ARCH_BCM_5301X)) || COMPILE_TEST
-	default y
+	default y if ARCH_BCM_MOBILE || ARCH_BCM_IPROC
 	help
 	  This driver adds support for using the Digital timing engine
 	  (DTE) in the Broadcom SoC's as a PTP clock.
@@ -59,7 +59,7 @@ config PTP_1588_CLOCK_QORIQ
 	tristate "Freescale QorIQ 1588 timer as PTP clock"
 	depends on GIANFAR || FSL_DPAA_ETH || FSL_DPAA2_ETH || FSL_ENETC || FSL_ENETC_VF || COMPILE_TEST
 	depends on PTP_1588_CLOCK
-	default y
+	default y if GIANFAR || FSL_DPAA_ETH || FSL_DPAA2_ETH || FSL_ENETC || FSL_ENETC_VF
 	help
 	  This driver adds support for using the Freescale QorIQ 1588
 	  timer as a PTP clock. This clock is only useful if your PTP
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 4380e6ddb849..4bf421765d03 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -162,6 +162,7 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 {
 	struct ptp_clock *ptp =
 		container_of(pccontext->clk, struct ptp_clock, clock);
+	unsigned int i, pin_index, supported_extts_flags;
 	struct ptp_sys_offset_extended *extoff = NULL;
 	struct ptp_sys_offset_precise precise_offset;
 	struct system_device_crosststamp xtstamp;
@@ -172,7 +173,6 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 	struct ptp_clock_request req;
 	struct ptp_clock_caps caps;
 	struct ptp_clock_time *pct;
-	unsigned int i, pin_index;
 	struct ptp_pin_desc pd;
 	struct timespec64 ts;
 	int enable, err = 0;
@@ -240,6 +240,18 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 			err = -EINVAL;
 			break;
 		}
+		supported_extts_flags = ptp->info->supported_extts_flags;
+		/* The PTP_ENABLE_FEATURE flag is always supported. */
+		supported_extts_flags |= PTP_ENABLE_FEATURE;
+		/* If the driver does not support strictly checking flags, the
+		 * PTP_RISING_EDGE and PTP_FALLING_EDGE flags are merely
+		 * hints which are not enforced.
+		 */
+		if (!(supported_extts_flags & PTP_STRICT_FLAGS))
+			supported_extts_flags |= PTP_EXTTS_EDGES;
+		/* Reject unsupported flags */
+		if (req.extts.flags & ~supported_extts_flags)
+			return -EOPNOTSUPP;
 		req.type = PTP_CLK_REQ_EXTTS;
 		enable = req.extts.flags & PTP_ENABLE_FEATURE ? 1 : 0;
 		if (mutex_lock_interruptible(&ptp->pincfg_mux))
@@ -312,6 +324,8 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 			err = -EINVAL;
 			break;
 		}
+		if (req.perout.flags & ~ptp->info->supported_perout_flags)
+			return -EOPNOTSUPP;
 		req.type = PTP_CLK_REQ_PEROUT;
 		enable = req.perout.period.sec || req.perout.period.nsec;
 		if (mutex_lock_interruptible(&ptp->pincfg_mux))
diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c
index fbb3fa8fc60b..b8d4df8c6da2 100644
--- a/drivers/ptp/ptp_clockmatrix.c
+++ b/drivers/ptp/ptp_clockmatrix.c
@@ -283,18 +283,6 @@ static int idtcm_extts_enable(struct idtcm_channel *channel,
 	idtcm = channel->idtcm;
 	old_mask = idtcm->extts_mask;
 
-	/* Reject requests with unsupported flags */
-	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-				PTP_RISING_EDGE |
-				PTP_FALLING_EDGE |
-				PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
-	/* Reject requests to enable time stamping on falling edge */
-	if ((rq->extts.flags & PTP_ENABLE_FEATURE) &&
-	    (rq->extts.flags & PTP_FALLING_EDGE))
-		return -EOPNOTSUPP;
-
 	if (index >= MAX_TOD)
 		return -EINVAL;
 
@@ -2043,6 +2031,7 @@ static const struct ptp_clock_info idtcm_caps = {
 	.n_per_out	= 12,
 	.n_ext_ts	= MAX_TOD,
 	.n_pins		= MAX_REF_CLK,
+	.supported_extts_flags = PTP_RISING_EDGE | PTP_STRICT_FLAGS,
 	.adjphase	= &idtcm_adjphase,
 	.getmaxphase	= &idtcm_getmaxphase,
 	.adjfine	= &idtcm_adjfine,
@@ -2060,6 +2049,7 @@ static const struct ptp_clock_info idtcm_caps_deprecated = {
 	.n_per_out	= 12,
 	.n_ext_ts	= MAX_TOD,
 	.n_pins		= MAX_REF_CLK,
+	.supported_extts_flags = PTP_RISING_EDGE | PTP_STRICT_FLAGS,
 	.adjphase	= &idtcm_adjphase,
 	.getmaxphase    = &idtcm_getmaxphase,
 	.adjfine	= &idtcm_adjfine,
diff --git a/drivers/ptp/ptp_fc3.c b/drivers/ptp/ptp_fc3.c
index cfced36c70bc..70002500170e 100644
--- a/drivers/ptp/ptp_fc3.c
+++ b/drivers/ptp/ptp_fc3.c
@@ -592,6 +592,7 @@ static const struct ptp_clock_info idtfc3_caps = {
 	.max_adj	= MAX_FFO_PPB,
 	.n_per_out	= 1,
 	.n_ext_ts	= 1,
+	.supported_extts_flags = PTP_STRICT_FLAGS | PTP_EXT_OFFSET,
 	.adjphase	= &idtfc3_adjphase,
 	.adjfine	= &idtfc3_adjfine,
 	.adjtime	= &idtfc3_adjtime,
diff --git a/drivers/ptp/ptp_idt82p33.c b/drivers/ptp/ptp_idt82p33.c
index b2fd94d4f863..f01c50dfa44e 100644
--- a/drivers/ptp/ptp_idt82p33.c
+++ b/drivers/ptp/ptp_idt82p33.c
@@ -246,18 +246,6 @@ static int idt82p33_extts_enable(struct idt82p33_channel *channel,
 	idt82p33  = channel->idt82p33;
 	old_mask = idt82p33->extts_mask;
 
-	/* Reject requests with unsupported flags */
-	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
-				PTP_RISING_EDGE |
-				PTP_FALLING_EDGE |
-				PTP_STRICT_FLAGS))
-		return -EOPNOTSUPP;
-
-	/* Reject requests to enable time stamping on falling edge */
-	if ((rq->extts.flags & PTP_ENABLE_FEATURE) &&
-	    (rq->extts.flags & PTP_FALLING_EDGE))
-		return -EOPNOTSUPP;
-
 	if (index >= MAX_PHC_PLL)
 		return -EINVAL;
 
@@ -1187,6 +1175,9 @@ static void idt82p33_caps_init(u32 index, struct ptp_clock_info *caps,
 
 	caps->pin_config = pin_cfg;
 
+	caps->supported_extts_flags = PTP_RISING_EDGE |
+				      PTP_STRICT_FLAGS;
+
 	for (i = 0; i < max_pins; ++i) {
 		ppd = &pin_cfg[i];
 
diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index 7945c6be1f7c..ce804438c32d 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -315,6 +315,8 @@ struct ptp_ocp_serial_port {
 #define OCP_BOARD_ID_LEN		13
 #define OCP_SERIAL_LEN			6
 #define OCP_SMA_NUM			4
+#define OCP_SIGNAL_NUM			4
+#define OCP_FREQ_NUM			4
 
 enum {
 	PORT_GNSS,
@@ -342,8 +344,8 @@ struct ptp_ocp {
 	struct dcf_master_reg	__iomem *dcf_out;
 	struct dcf_slave_reg	__iomem *dcf_in;
 	struct tod_reg		__iomem *nmea_out;
-	struct frequency_reg	__iomem *freq_in[4];
-	struct ptp_ocp_ext_src	*signal_out[4];
+	struct frequency_reg	__iomem *freq_in[OCP_FREQ_NUM];
+	struct ptp_ocp_ext_src	*signal_out[OCP_SIGNAL_NUM];
 	struct ptp_ocp_ext_src	*pps;
 	struct ptp_ocp_ext_src	*ts0;
 	struct ptp_ocp_ext_src	*ts1;
@@ -378,10 +380,12 @@ struct ptp_ocp {
 	u32			utc_tai_offset;
 	u32			ts_window_adjust;
 	u64			fw_cap;
-	struct ptp_ocp_signal	signal[4];
+	struct ptp_ocp_signal	signal[OCP_SIGNAL_NUM];
 	struct ptp_ocp_sma_connector sma[OCP_SMA_NUM];
 	const struct ocp_sma_op *sma_op;
 	struct dpll_device *dpll;
+	int signals_nr;
+	int freq_in_nr;
 };
 
 #define OCP_REQ_TIMESTAMP	BIT(0)
@@ -2067,6 +2071,7 @@ ptp_ocp_signal_set(struct ptp_ocp *bp, int gen, struct ptp_ocp_signal *s)
 	if (!s->start) {
 		/* roundup() does not work on 32-bit systems */
 		s->start = DIV64_U64_ROUND_UP(start_ns, s->period);
+		s->start *= s->period;
 		s->start = ktime_add(s->start, s->phase);
 	}
 
@@ -2371,7 +2376,7 @@ ptp_ocp_attr_group_add(struct ptp_ocp *bp,
 		if (attr_tbl[i].cap & bp->fw_cap)
 			count++;
 
-	bp->attr_group = kcalloc(count + 1, sizeof(struct attribute_group *),
+	bp->attr_group = kcalloc(count + 1, sizeof(*bp->attr_group),
 				 GFP_KERNEL);
 	if (!bp->attr_group)
 		return -ENOMEM;
@@ -2577,12 +2582,60 @@ static const struct ocp_sma_op ocp_fb_sma_op = {
 	.set_output	= ptp_ocp_sma_fb_set_output,
 };
 
+static int
+ptp_ocp_sma_adva_set_output(struct ptp_ocp *bp, int sma_nr, u32 val)
+{
+	u32 reg, mask, shift;
+	unsigned long flags;
+	u32 __iomem *gpio;
+
+	gpio = sma_nr > 2 ? &bp->sma_map1->gpio2 : &bp->sma_map2->gpio2;
+	shift = sma_nr & 1 ? 0 : 16;
+
+	mask = 0xffff << (16 - shift);
+
+	spin_lock_irqsave(&bp->lock, flags);
+
+	reg = ioread32(gpio);
+	reg = (reg & mask) | (val << shift);
+
+	iowrite32(reg, gpio);
+
+	spin_unlock_irqrestore(&bp->lock, flags);
+
+	return 0;
+}
+
+static int
+ptp_ocp_sma_adva_set_inputs(struct ptp_ocp *bp, int sma_nr, u32 val)
+{
+	u32 reg, mask, shift;
+	unsigned long flags;
+	u32 __iomem *gpio;
+
+	gpio = sma_nr > 2 ? &bp->sma_map2->gpio1 : &bp->sma_map1->gpio1;
+	shift = sma_nr & 1 ? 0 : 16;
+
+	mask = 0xffff << (16 - shift);
+
+	spin_lock_irqsave(&bp->lock, flags);
+
+	reg = ioread32(gpio);
+	reg = (reg & mask) | (val << shift);
+
+	iowrite32(reg, gpio);
+
+	spin_unlock_irqrestore(&bp->lock, flags);
+
+	return 0;
+}
+
 static const struct ocp_sma_op ocp_adva_sma_op = {
 	.tbl		= { ptp_ocp_adva_sma_in, ptp_ocp_adva_sma_out },
 	.init		= ptp_ocp_sma_fb_init,
 	.get		= ptp_ocp_sma_fb_get,
-	.set_inputs	= ptp_ocp_sma_fb_set_inputs,
-	.set_output	= ptp_ocp_sma_fb_set_output,
+	.set_inputs	= ptp_ocp_sma_adva_set_inputs,
+	.set_output	= ptp_ocp_sma_adva_set_output,
 };
 
 static int
@@ -2648,6 +2701,8 @@ ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r)
 	bp->eeprom_map = fb_eeprom_map;
 	bp->fw_version = ioread32(&bp->image->version);
 	bp->sma_op = &ocp_fb_sma_op;
+	bp->signals_nr = 4;
+	bp->freq_in_nr = 4;
 
 	ptp_ocp_fb_set_version(bp);
 
@@ -2813,6 +2868,8 @@ ptp_ocp_art_board_init(struct ptp_ocp *bp, struct ocp_resource *r)
 	bp->fw_version = ioread32(&bp->reg->version);
 	bp->fw_tag = 2;
 	bp->sma_op = &ocp_art_sma_op;
+	bp->signals_nr = 4;
+	bp->freq_in_nr = 4;
 
 	/* Enable MAC serial port during initialisation */
 	iowrite32(1, &bp->board_config->mro50_serial_activate);
@@ -2839,6 +2896,8 @@ ptp_ocp_adva_board_init(struct ptp_ocp *bp, struct ocp_resource *r)
 	bp->flash_start = 0xA00000;
 	bp->eeprom_map = fb_eeprom_map;
 	bp->sma_op = &ocp_adva_sma_op;
+	bp->signals_nr = 2;
+	bp->freq_in_nr = 2;
 
 	version = ioread32(&bp->image->version);
 	/* if lower 16 bits are empty, this is the fw loader. */
@@ -3959,7 +4018,7 @@ _signal_summary_show(struct seq_file *s, struct ptp_ocp *bp, int nr)
 {
 	struct signal_reg __iomem *reg = bp->signal_out[nr]->mem;
 	struct ptp_ocp_signal *signal = &bp->signal[nr];
-	char label[8];
+	char label[16];
 	bool on;
 	u32 val;
 
@@ -3982,7 +4041,7 @@ static void
 _frequency_summary_show(struct seq_file *s, int nr,
 			struct frequency_reg __iomem *reg)
 {
-	char label[8];
+	char label[16];
 	bool on;
 	u32 val;
 
@@ -4126,11 +4185,11 @@ ptp_ocp_summary_show(struct seq_file *s, void *data)
 	}
 
 	if (bp->fw_cap & OCP_CAP_SIGNAL)
-		for (i = 0; i < 4; i++)
+		for (i = 0; i < bp->signals_nr; i++)
 			_signal_summary_show(s, bp, i);
 
 	if (bp->fw_cap & OCP_CAP_FREQ)
-		for (i = 0; i < 4; i++)
+		for (i = 0; i < bp->freq_in_nr; i++)
 			_frequency_summary_show(s, i, bp->freq_in[i]);
 
 	if (bp->irig_out) {
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index a40c511e0096..0387bd838487 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -322,7 +322,7 @@ static int __pwm_set_waveform(struct pwm_device *pwm,
 	const struct pwm_ops *ops = chip->ops;
 	char wfhw[WFHWSIZE];
 	struct pwm_waveform wf_rounded;
-	int err;
+	int err, ret_tohw;
 
 	BUG_ON(WFHWSIZE < ops->sizeof_wfhw);
 
@@ -332,16 +332,16 @@ static int __pwm_set_waveform(struct pwm_device *pwm,
 	if (!pwm_wf_valid(wf))
 		return -EINVAL;
 
-	err = __pwm_round_waveform_tohw(chip, pwm, wf, &wfhw);
-	if (err)
-		return err;
+	ret_tohw = __pwm_round_waveform_tohw(chip, pwm, wf, &wfhw);
+	if (ret_tohw < 0)
+		return ret_tohw;
 
 	if ((IS_ENABLED(CONFIG_PWM_DEBUG) || exact) && wf->period_length_ns) {
 		err = __pwm_round_waveform_fromhw(chip, pwm, &wfhw, &wf_rounded);
 		if (err)
 			return err;
 
-		if (IS_ENABLED(CONFIG_PWM_DEBUG) && !pwm_check_rounding(wf, &wf_rounded))
+		if (IS_ENABLED(CONFIG_PWM_DEBUG) && ret_tohw == 0 && !pwm_check_rounding(wf, &wf_rounded))
 			dev_err(&chip->dev, "Wrong rounding: requested %llu/%llu [+%llu], result %llu/%llu [+%llu]\n",
 				wf->duty_length_ns, wf->period_length_ns, wf->duty_offset_ns,
 				wf_rounded.duty_length_ns, wf_rounded.period_length_ns, wf_rounded.duty_offset_ns);
@@ -382,7 +382,8 @@ static int __pwm_set_waveform(struct pwm_device *pwm,
 				wf_rounded.duty_length_ns, wf_rounded.period_length_ns, wf_rounded.duty_offset_ns,
 				wf_set.duty_length_ns, wf_set.period_length_ns, wf_set.duty_offset_ns);
 	}
-	return 0;
+
+	return ret_tohw;
 }
 
 /**
diff --git a/drivers/pwm/pwm-axi-pwmgen.c b/drivers/pwm/pwm-axi-pwmgen.c
index 4259a0db9ff4..4337c8f5acf0 100644
--- a/drivers/pwm/pwm-axi-pwmgen.c
+++ b/drivers/pwm/pwm-axi-pwmgen.c
@@ -75,6 +75,7 @@ static int axi_pwmgen_round_waveform_tohw(struct pwm_chip *chip,
 {
 	struct axi_pwmgen_waveform *wfhw = _wfhw;
 	struct axi_pwmgen_ddata *ddata = axi_pwmgen_ddata_from_chip(chip);
+	int ret = 0;
 
 	if (wf->period_length_ns == 0) {
 		*wfhw = (struct axi_pwmgen_waveform){
@@ -91,12 +92,15 @@ static int axi_pwmgen_round_waveform_tohw(struct pwm_chip *chip,
 		if (wfhw->period_cnt == 0) {
 			/*
 			 * The specified period is too short for the hardware.
-			 * Let's round .duty_cycle down to 0 to get a (somewhat)
-			 * valid result.
+			 * So round up .period_cnt to 1 (i.e. the smallest
+			 * possible period). With .duty_cycle and .duty_offset
+			 * being less than or equal to .period, their rounded
+			 * value must be 0.
 			 */
 			wfhw->period_cnt = 1;
 			wfhw->duty_cycle_cnt = 0;
 			wfhw->duty_offset_cnt = 0;
+			ret = 1;
 		} else {
 			wfhw->duty_cycle_cnt = min_t(u64,
 						     mul_u64_u32_div(wf->duty_length_ns, ddata->clk_rate_hz, NSEC_PER_SEC),
@@ -111,7 +115,7 @@ static int axi_pwmgen_round_waveform_tohw(struct pwm_chip *chip,
 		pwm->hwpwm, wf->duty_length_ns, wf->period_length_ns, wf->duty_offset_ns,
 		ddata->clk_rate_hz, wfhw->period_cnt, wfhw->duty_cycle_cnt, wfhw->duty_offset_cnt);
 
-	return 0;
+	return ret;
 }
 
 static int axi_pwmgen_round_waveform_fromhw(struct pwm_chip *chip, struct pwm_device *pwm,
diff --git a/drivers/pwm/pwm-fsl-ftm.c b/drivers/pwm/pwm-fsl-ftm.c
index 2510c10ca473..c45a5fca4cbb 100644
--- a/drivers/pwm/pwm-fsl-ftm.c
+++ b/drivers/pwm/pwm-fsl-ftm.c
@@ -118,6 +118,9 @@ static unsigned int fsl_pwm_ticks_to_ns(struct fsl_pwm_chip *fpc,
 	unsigned long long exval;
 
 	rate = clk_get_rate(fpc->clk[fpc->period.clk_select]);
+	if (rate >> fpc->period.clk_ps == 0)
+		return 0;
+
 	exval = ticks;
 	exval *= 1000000000UL;
 	do_div(exval, rate >> fpc->period.clk_ps);
@@ -190,6 +193,9 @@ static unsigned int fsl_pwm_calculate_duty(struct fsl_pwm_chip *fpc,
 	unsigned int period = fpc->period.mod_period + 1;
 	unsigned int period_ns = fsl_pwm_ticks_to_ns(fpc, period);
 
+	if (!period_ns)
+		return 0;
+
 	duty = (unsigned long long)duty_ns * period;
 	do_div(duty, period_ns);
 
diff --git a/drivers/pwm/pwm-mediatek.c b/drivers/pwm/pwm-mediatek.c
index 01dfa0fab80a..7eaab5831499 100644
--- a/drivers/pwm/pwm-mediatek.c
+++ b/drivers/pwm/pwm-mediatek.c
@@ -121,21 +121,25 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	struct pwm_mediatek_chip *pc = to_pwm_mediatek_chip(chip);
 	u32 clkdiv = 0, cnt_period, cnt_duty, reg_width = PWMDWIDTH,
 	    reg_thres = PWMTHRES;
+	unsigned long clk_rate;
 	u64 resolution;
 	int ret;
 
 	ret = pwm_mediatek_clk_enable(chip, pwm);
-
 	if (ret < 0)
 		return ret;
 
+	clk_rate = clk_get_rate(pc->clk_pwms[pwm->hwpwm]);
+	if (!clk_rate)
+		return -EINVAL;
+
 	/* Make sure we use the bus clock and not the 26MHz clock */
 	if (pc->soc->has_ck_26m_sel)
 		writel(0, pc->regs + PWM_CK_26M_SEL);
 
 	/* Using resolution in picosecond gets accuracy higher */
 	resolution = (u64)NSEC_PER_SEC * 1000;
-	do_div(resolution, clk_get_rate(pc->clk_pwms[pwm->hwpwm]));
+	do_div(resolution, clk_rate);
 
 	cnt_period = DIV_ROUND_CLOSEST_ULL((u64)period_ns * 1000, resolution);
 	while (cnt_period > 8191) {
diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c
index 2261789cc27d..578dbdd2d5a7 100644
--- a/drivers/pwm/pwm-rcar.c
+++ b/drivers/pwm/pwm-rcar.c
@@ -8,6 +8,7 @@
  * - The hardware cannot generate a 0% duty cycle.
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
@@ -102,23 +103,24 @@ static void rcar_pwm_set_clock_control(struct rcar_pwm_chip *rp,
 	rcar_pwm_write(rp, value, RCAR_PWMCR);
 }
 
-static int rcar_pwm_set_counter(struct rcar_pwm_chip *rp, int div, int duty_ns,
-				int period_ns)
+static int rcar_pwm_set_counter(struct rcar_pwm_chip *rp, int div, u64 duty_ns,
+				u64 period_ns)
 {
-	unsigned long long one_cycle, tmp;	/* 0.01 nanoseconds */
+	unsigned long long tmp;
 	unsigned long clk_rate = clk_get_rate(rp->clk);
 	u32 cyc, ph;
 
-	one_cycle = NSEC_PER_SEC * 100ULL << div;
-	do_div(one_cycle, clk_rate);
+	/* div <= 24 == RCAR_PWM_MAX_DIVISION, so the shift doesn't overflow. */
+	tmp = mul_u64_u64_div_u64(period_ns, clk_rate, (u64)NSEC_PER_SEC << div);
+	if (tmp > FIELD_MAX(RCAR_PWMCNT_CYC0_MASK))
+		tmp = FIELD_MAX(RCAR_PWMCNT_CYC0_MASK);
 
-	tmp = period_ns * 100ULL;
-	do_div(tmp, one_cycle);
-	cyc = (tmp << RCAR_PWMCNT_CYC0_SHIFT) & RCAR_PWMCNT_CYC0_MASK;
+	cyc = FIELD_PREP(RCAR_PWMCNT_CYC0_MASK, tmp);
 
-	tmp = duty_ns * 100ULL;
-	do_div(tmp, one_cycle);
-	ph = tmp & RCAR_PWMCNT_PH0_MASK;
+	tmp = mul_u64_u64_div_u64(duty_ns, clk_rate, (u64)NSEC_PER_SEC << div);
+	if (tmp > FIELD_MAX(RCAR_PWMCNT_PH0_MASK))
+		tmp = FIELD_MAX(RCAR_PWMCNT_PH0_MASK);
+	ph = FIELD_PREP(RCAR_PWMCNT_PH0_MASK, tmp);
 
 	/* Avoid prohibited setting */
 	if (cyc == 0 || ph == 0)
diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index a59de4de18b6..ec2c05c9ee7a 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -103,22 +103,16 @@ static int stm32_pwm_round_waveform_tohw(struct pwm_chip *chip,
 		if (ret)
 			goto out;
 
-		/*
-		 * calculate the best value for ARR for the given PSC, refuse if
-		 * the resulting period gets bigger than the requested one.
-		 */
 		arr = mul_u64_u64_div_u64(wf->period_length_ns, rate,
 					  (u64)NSEC_PER_SEC * (wfhw->psc + 1));
 		if (arr <= wfhw->arr) {
 			/*
-			 * requested period is small than the currently
+			 * requested period is smaller than the currently
 			 * configured and unchangable period, report back the smallest
-			 * possible period, i.e. the current state; Initialize
-			 * ccr to anything valid.
+			 * possible period, i.e. the current state and return 1
+			 * to indicate the wrong rounding direction.
 			 */
-			wfhw->ccr = 0;
 			ret = 1;
-			goto out;
 		}
 
 	} else {
diff --git a/drivers/ras/amd/atl/internal.h b/drivers/ras/amd/atl/internal.h
index f9be26d25348..d096b58cd0ae 100644
--- a/drivers/ras/amd/atl/internal.h
+++ b/drivers/ras/amd/atl/internal.h
@@ -362,4 +362,7 @@ static inline void atl_debug_on_bad_intlv_mode(struct addr_ctx *ctx)
 	atl_debug(ctx, "Unrecognized interleave mode: %u", ctx->map.intlv_mode);
 }
 
+#define MI300_UMC_MCA_COL	GENMASK(5, 1)
+#define MI300_UMC_MCA_ROW13	BIT(23)
+
 #endif /* __AMD_ATL_INTERNAL_H__ */
diff --git a/drivers/ras/amd/atl/umc.c b/drivers/ras/amd/atl/umc.c
index dc8aa12f63c8..6e072b7667e9 100644
--- a/drivers/ras/amd/atl/umc.c
+++ b/drivers/ras/amd/atl/umc.c
@@ -229,7 +229,6 @@ int get_umc_info_mi300(void)
  * Additionally, the PC and Bank bits may be hashed. This must be accounted for before
  * reconstructing the normalized address.
  */
-#define MI300_UMC_MCA_COL	GENMASK(5, 1)
 #define MI300_UMC_MCA_BANK	GENMASK(9, 6)
 #define MI300_UMC_MCA_ROW	GENMASK(24, 10)
 #define MI300_UMC_MCA_PC	BIT(25)
@@ -320,7 +319,7 @@ static unsigned long convert_dram_to_norm_addr_mi300(unsigned long addr)
  * See amd_atl::convert_dram_to_norm_addr_mi300() for MI300 address formats.
  */
 #define MI300_NUM_COL		BIT(HWEIGHT(MI300_UMC_MCA_COL))
-static void retire_row_mi300(struct atl_err *a_err)
+static void _retire_row_mi300(struct atl_err *a_err)
 {
 	unsigned long addr;
 	struct page *p;
@@ -351,6 +350,22 @@ static void retire_row_mi300(struct atl_err *a_err)
 	}
 }
 
+/*
+ * In addition to the column bits, the row[13] bit should also be included when
+ * calculating addresses affected by a physical row.
+ *
+ * Instead of running through another loop over a single bit, just run through
+ * the column bits twice and flip the row[13] bit in-between.
+ *
+ * See MI300_UMC_MCA_ROW for the row bits in MCA_ADDR_UMC value.
+ */
+static void retire_row_mi300(struct atl_err *a_err)
+{
+	_retire_row_mi300(a_err);
+	a_err->addr ^= MI300_UMC_MCA_ROW13;
+	_retire_row_mi300(a_err);
+}
+
 void amd_retire_dram_row(struct atl_err *a_err)
 {
 	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
diff --git a/drivers/ras/amd/fmpm.c b/drivers/ras/amd/fmpm.c
index 90de737fbc90..8877c6ff64c4 100644
--- a/drivers/ras/amd/fmpm.c
+++ b/drivers/ras/amd/fmpm.c
@@ -250,6 +250,13 @@ static bool rec_has_valid_entries(struct fru_rec *rec)
 	return true;
 }
 
+/*
+ * Row retirement is done on MI300 systems, and some bits are 'don't
+ * care' for comparing addresses with unique physical rows.  This
+ * includes all column bits and the row[13] bit.
+ */
+#define MASK_ADDR(addr)	((addr) & ~(MI300_UMC_MCA_ROW13 | MI300_UMC_MCA_COL))
+
 static bool fpds_equal(struct cper_fru_poison_desc *old, struct cper_fru_poison_desc *new)
 {
 	/*
@@ -258,7 +265,7 @@ static bool fpds_equal(struct cper_fru_poison_desc *old, struct cper_fru_poison_
 	 *
 	 * Also, order the checks from most->least likely to fail to shortcut the code.
 	 */
-	if (old->addr != new->addr)
+	if (MASK_ADDR(old->addr) != MASK_ADDR(new->addr))
 		return false;
 
 	if (old->hw_id != new->hw_id)
diff --git a/drivers/regulator/max20086-regulator.c b/drivers/regulator/max20086-regulator.c
index 59eb23d467ec..198d45f8e884 100644
--- a/drivers/regulator/max20086-regulator.c
+++ b/drivers/regulator/max20086-regulator.c
@@ -132,7 +132,7 @@ static int max20086_regulators_register(struct max20086 *chip)
 
 static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on)
 {
-	struct of_regulator_match matches[MAX20086_MAX_REGULATORS] = { };
+	struct of_regulator_match *matches;
 	struct device_node *node;
 	unsigned int i;
 	int ret;
@@ -143,6 +143,11 @@ static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on)
 		return -ENODEV;
 	}
 
+	matches = devm_kcalloc(chip->dev, chip->info->num_outputs,
+			       sizeof(*matches), GFP_KERNEL);
+	if (!matches)
+		return -ENOMEM;
+
 	for (i = 0; i < chip->info->num_outputs; ++i)
 		matches[i].name = max20086_output_names[i];
 
diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c
index 775b056d795a..2c7e519a2254 100644
--- a/drivers/remoteproc/qcom_wcnss.c
+++ b/drivers/remoteproc/qcom_wcnss.c
@@ -456,7 +456,8 @@ static int wcnss_init_regulators(struct qcom_wcnss *wcnss,
 	if (wcnss->num_pds) {
 		info += wcnss->num_pds;
 		/* Handle single power domain case */
-		num_vregs += num_pd_vregs - wcnss->num_pds;
+		if (wcnss->num_pds < num_pd_vregs)
+			num_vregs += num_pd_vregs - wcnss->num_pds;
 	} else {
 		num_vregs += num_pd_vregs;
 	}
diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig
index 4bfe469c04aa..8c1c908d2c6e 100644
--- a/drivers/s390/block/Kconfig
+++ b/drivers/s390/block/Kconfig
@@ -5,7 +5,7 @@ comment "S/390 block device drivers"
 config DCSSBLK
 	def_tristate m
 	prompt "DCSSBLK support"
-	depends on S390 && BLOCK
+	depends on S390 && BLOCK && (DAX || DAX=n)
 	help
 	  Support for dcss block device
 
@@ -14,7 +14,6 @@ config DCSSBLK_DAX
 	depends on DCSSBLK
 	# requires S390 ZONE_DEVICE support
 	depends on BROKEN
-	select DAX
 	prompt "DCSSBLK DAX support"
 	help
 	  Enable DAX operation for the dcss block device
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 60ed70a39d2c..b7f15f303ea2 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -611,7 +611,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	ism->dev.parent = &pdev->dev;
 	ism->dev.release = ism_dev_release;
 	device_initialize(&ism->dev);
-	dev_set_name(&ism->dev, dev_name(&pdev->dev));
+	dev_set_name(&ism->dev, "%s", dev_name(&pdev->dev));
 	ret = device_add(&ism->dev);
 	if (ret)
 		goto err_dev;
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 21fa7ac849e5..4904b831c0a7 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -302,11 +302,17 @@ static struct airq_info *new_airq_info(int index)
 static unsigned long *get_airq_indicator(struct virtqueue *vqs[], int nvqs,
 					 u64 *first, void **airq_info)
 {
-	int i, j;
+	int i, j, queue_idx, highest_queue_idx = -1;
 	struct airq_info *info;
 	unsigned long *indicator_addr = NULL;
 	unsigned long bit, flags;
 
+	/* Array entries without an actual queue pointer must be ignored. */
+	for (i = 0; i < nvqs; i++) {
+		if (vqs[i])
+			highest_queue_idx++;
+	}
+
 	for (i = 0; i < MAX_AIRQ_AREAS && !indicator_addr; i++) {
 		mutex_lock(&airq_areas_lock);
 		if (!airq_areas[i])
@@ -316,7 +322,7 @@ static unsigned long *get_airq_indicator(struct virtqueue *vqs[], int nvqs,
 		if (!info)
 			return NULL;
 		write_lock_irqsave(&info->lock, flags);
-		bit = airq_iv_alloc(info->aiv, nvqs);
+		bit = airq_iv_alloc(info->aiv, highest_queue_idx + 1);
 		if (bit == -1UL) {
 			/* Not enough vacancies. */
 			write_unlock_irqrestore(&info->lock, flags);
@@ -325,8 +331,10 @@ static unsigned long *get_airq_indicator(struct virtqueue *vqs[], int nvqs,
 		*first = bit;
 		*airq_info = info;
 		indicator_addr = info->aiv->vector;
-		for (j = 0; j < nvqs; j++) {
-			airq_iv_set_ptr(info->aiv, bit + j,
+		for (j = 0, queue_idx = 0; j < nvqs; j++) {
+			if (!vqs[j])
+				continue;
+			airq_iv_set_ptr(info->aiv, bit + queue_idx++,
 					(unsigned long)vqs[j]);
 		}
 		write_unlock_irqrestore(&info->lock, flags);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 5cb1d3db4907..944cf2fb0561 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -935,8 +935,28 @@ static void hisi_sas_phyup_work_common(struct work_struct *work,
 		container_of(work, typeof(*phy), works[event]);
 	struct hisi_hba *hisi_hba = phy->hisi_hba;
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
+	struct asd_sas_port *sas_port = sas_phy->port;
+	struct hisi_sas_port *port = phy->port;
+	struct device *dev = hisi_hba->dev;
+	struct domain_device *port_dev;
 	int phy_no = sas_phy->id;
 
+	if (!test_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags) &&
+	    sas_port && port && (port->id != phy->port_id)) {
+		dev_info(dev, "phy%d's hw port id changed from %d to %llu\n",
+				phy_no, port->id, phy->port_id);
+		port_dev = sas_port->port_dev;
+		if (port_dev && !dev_is_expander(port_dev->dev_type)) {
+			/*
+			 * Set the device state to gone to block
+			 * sending IO to the device.
+			 */
+			set_bit(SAS_DEV_GONE, &port_dev->state);
+			hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
+			return;
+		}
+	}
+
 	phy->wait_phyup_cnt = 0;
 	if (phy->identify.target_port_protocols == SAS_PROTOCOL_SSP)
 		hisi_hba->hw->sl_notify_ssp(hisi_hba, phy_no);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index a1fc400ab4c3..1e9830940f84 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -2501,6 +2501,7 @@ static void prep_ata_v2_hw(struct hisi_hba *hisi_hba,
 	struct hisi_sas_port *port = to_hisi_sas_port(sas_port);
 	struct sas_ata_task *ata_task = &task->ata_task;
 	struct sas_tmf_task *tmf = slot->tmf;
+	int phy_id;
 	u8 *buf_cmd;
 	int has_data = 0, hdr_tag = 0;
 	u32 dw0, dw1 = 0, dw2 = 0;
@@ -2508,10 +2509,14 @@ static void prep_ata_v2_hw(struct hisi_hba *hisi_hba,
 	/* create header */
 	/* dw0 */
 	dw0 = port->id << CMD_HDR_PORT_OFF;
-	if (parent_dev && dev_is_expander(parent_dev->dev_type))
+	if (parent_dev && dev_is_expander(parent_dev->dev_type)) {
 		dw0 |= 3 << CMD_HDR_CMD_OFF;
-	else
+	} else {
+		phy_id = device->phy->identify.phy_identifier;
+		dw0 |= (1U << phy_id) << CMD_HDR_PHY_ID_OFF;
+		dw0 |= CMD_HDR_FORCE_PHY_MSK;
 		dw0 |= 4 << CMD_HDR_CMD_OFF;
+	}
 
 	if (tmf && ata_task->force_phy) {
 		dw0 |= CMD_HDR_FORCE_PHY_MSK;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 2684d6482067..08dac9ae2f10 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -359,6 +359,10 @@
 #define CMD_HDR_RESP_REPORT_MSK		(0x1 << CMD_HDR_RESP_REPORT_OFF)
 #define CMD_HDR_TLR_CTRL_OFF		6
 #define CMD_HDR_TLR_CTRL_MSK		(0x3 << CMD_HDR_TLR_CTRL_OFF)
+#define CMD_HDR_PHY_ID_OFF		8
+#define CMD_HDR_PHY_ID_MSK		(0x1ff << CMD_HDR_PHY_ID_OFF)
+#define CMD_HDR_FORCE_PHY_OFF		17
+#define CMD_HDR_FORCE_PHY_MSK		(0x1U << CMD_HDR_FORCE_PHY_OFF)
 #define CMD_HDR_PORT_OFF		18
 #define CMD_HDR_PORT_MSK		(0xf << CMD_HDR_PORT_OFF)
 #define CMD_HDR_PRIORITY_OFF		27
@@ -1429,15 +1433,21 @@ static void prep_ata_v3_hw(struct hisi_hba *hisi_hba,
 	struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
 	struct asd_sas_port *sas_port = device->port;
 	struct hisi_sas_port *port = to_hisi_sas_port(sas_port);
+	int phy_id;
 	u8 *buf_cmd;
 	int has_data = 0, hdr_tag = 0;
 	u32 dw1 = 0, dw2 = 0;
 
 	hdr->dw0 = cpu_to_le32(port->id << CMD_HDR_PORT_OFF);
-	if (parent_dev && dev_is_expander(parent_dev->dev_type))
+	if (parent_dev && dev_is_expander(parent_dev->dev_type)) {
 		hdr->dw0 |= cpu_to_le32(3 << CMD_HDR_CMD_OFF);
-	else
+	} else {
+		phy_id = device->phy->identify.phy_identifier;
+		hdr->dw0 |= cpu_to_le32((1U << phy_id)
+				<< CMD_HDR_PHY_ID_OFF);
+		hdr->dw0 |= CMD_HDR_FORCE_PHY_MSK;
 		hdr->dw0 |= cpu_to_le32(4U << CMD_HDR_CMD_OFF);
+	}
 
 	switch (task->data_dir) {
 	case DMA_TO_DEVICE:
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index 088cc40ae866..8ee2bfe47571 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -23,8 +23,8 @@
 /*
  * MegaRAID SAS Driver meta data
  */
-#define MEGASAS_VERSION				"07.727.03.00-rc1"
-#define MEGASAS_RELDATE				"Oct 03, 2023"
+#define MEGASAS_VERSION				"07.734.00.00-rc1"
+#define MEGASAS_RELDATE				"Apr 03, 2025"
 
 #define MEGASAS_MSIX_NAME_LEN			32
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index c20447b39cb9..5e33d411fa3d 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -2103,6 +2103,9 @@ static int megasas_sdev_configure(struct scsi_device *sdev,
 	/* This sdev property may change post OCR */
 	megasas_set_dynamic_target_properties(sdev, lim, is_target_prop);
 
+	if (!MEGASAS_IS_LOGICAL(sdev))
+		sdev->no_vpd_size = 1;
+
 	mutex_unlock(&instance->reset_mutex);
 
 	return 0;
@@ -3662,8 +3665,10 @@ megasas_complete_cmd(struct megasas_instance *instance, struct megasas_cmd *cmd,
 
 		case MFI_STAT_SCSI_IO_FAILED:
 		case MFI_STAT_LD_INIT_IN_PROGRESS:
-			cmd->scmd->result =
-			    (DID_ERROR << 16) | hdr->scsi_status;
+			if (hdr->scsi_status == 0xf0)
+				cmd->scmd->result = (DID_ERROR << 16) | SAM_STAT_CHECK_CONDITION;
+			else
+				cmd->scmd->result = (DID_ERROR << 16) | hdr->scsi_status;
 			break;
 
 		case MFI_STAT_SCSI_DONE_WITH_ERROR:
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 721860cb1ef6..a6794f49e9fa 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -2043,7 +2043,10 @@ map_cmd_status(struct fusion_context *fusion,
 
 	case MFI_STAT_SCSI_IO_FAILED:
 	case MFI_STAT_LD_INIT_IN_PROGRESS:
-		scmd->result = (DID_ERROR << 16) | ext_status;
+		if (ext_status == 0xf0)
+			scmd->result = (DID_ERROR << 16) | SAM_STAT_CHECK_CONDITION;
+		else
+			scmd->result = (DID_ERROR << 16) | ext_status;
 		break;
 
 	case MFI_STAT_SCSI_DONE_WITH_ERROR:
diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index 3fcb1ad3b070..1d7901a8f0e4 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -174,6 +174,9 @@ static void mpi3mr_print_event_data(struct mpi3mr_ioc *mrioc,
 	char *desc = NULL;
 	u16 event;
 
+	if (!(mrioc->logging_level & MPI3_DEBUG_EVENT))
+		return;
+
 	event = event_reply->event;
 
 	switch (event) {
@@ -451,6 +454,7 @@ int mpi3mr_process_admin_reply_q(struct mpi3mr_ioc *mrioc)
 		return 0;
 	}
 
+	atomic_set(&mrioc->admin_pend_isr, 0);
 	reply_desc = (struct mpi3_default_reply_descriptor *)mrioc->admin_reply_base +
 	    admin_reply_ci;
 
@@ -565,7 +569,7 @@ int mpi3mr_process_op_reply_q(struct mpi3mr_ioc *mrioc,
 		WRITE_ONCE(op_req_q->ci, le16_to_cpu(reply_desc->request_queue_ci));
 		mpi3mr_process_op_reply_desc(mrioc, reply_desc, &reply_dma,
 		    reply_qidx);
-		atomic_dec(&op_reply_q->pend_ios);
+
 		if (reply_dma)
 			mpi3mr_repost_reply_buf(mrioc, reply_dma);
 		num_op_reply++;
@@ -2925,6 +2929,7 @@ static int mpi3mr_setup_admin_qpair(struct mpi3mr_ioc *mrioc)
 	mrioc->admin_reply_ci = 0;
 	mrioc->admin_reply_ephase = 1;
 	atomic_set(&mrioc->admin_reply_q_in_use, 0);
+	atomic_set(&mrioc->admin_pend_isr, 0);
 
 	if (!mrioc->admin_req_base) {
 		mrioc->admin_req_base = dma_alloc_coherent(&mrioc->pdev->dev,
@@ -4653,6 +4658,7 @@ void mpi3mr_memset_buffers(struct mpi3mr_ioc *mrioc)
 	if (mrioc->admin_reply_base)
 		memset(mrioc->admin_reply_base, 0, mrioc->admin_reply_q_sz);
 	atomic_set(&mrioc->admin_reply_q_in_use, 0);
+	atomic_set(&mrioc->admin_pend_isr, 0);
 
 	if (mrioc->init_cmds.reply) {
 		memset(mrioc->init_cmds.reply, 0, sizeof(*mrioc->init_cmds.reply));
diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c
index dc4bd422b601..486db5b2f05d 100644
--- a/drivers/scsi/myrb.c
+++ b/drivers/scsi/myrb.c
@@ -891,7 +891,7 @@ static bool myrb_enable_mmio(struct myrb_hba *cb, mbox_mmio_init_t mmio_init_fn)
 		status = mmio_init_fn(pdev, base, &mbox);
 		if (status != MYRB_STATUS_SUCCESS) {
 			dev_err(&pdev->dev,
-				"Failed to enable mailbox, statux %02X\n",
+				"Failed to enable mailbox, status %02X\n",
 				status);
 			return false;
 		}
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index 183ce00aa671..f7067878b34f 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -766,6 +766,7 @@ static void pm8001_dev_gone_notify(struct domain_device *dev)
 			spin_lock_irqsave(&pm8001_ha->lock, flags);
 		}
 		PM8001_CHIP_DISP->dereg_dev_req(pm8001_ha, device_id);
+		pm8001_ha->phy[pm8001_dev->attached_phy].phy_attached = 0;
 		pm8001_free_dev(pm8001_dev);
 	} else {
 		pm8001_dbg(pm8001_ha, DISC, "Found dev has gone.\n");
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 53daf923ad8e..518a252eb6aa 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -707,26 +707,23 @@ void scsi_cdl_check(struct scsi_device *sdev)
  */
 int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
 {
-	struct scsi_mode_data data;
-	struct scsi_sense_hdr sshdr;
-	struct scsi_vpd *vpd;
-	bool is_ata = false;
 	char buf[64];
+	bool is_ata;
 	int ret;
 
 	if (!sdev->cdl_supported)
 		return -EOPNOTSUPP;
 
 	rcu_read_lock();
-	vpd = rcu_dereference(sdev->vpd_pg89);
-	if (vpd)
-		is_ata = true;
+	is_ata = rcu_dereference(sdev->vpd_pg89);
 	rcu_read_unlock();
 
 	/*
 	 * For ATA devices, CDL needs to be enabled with a SET FEATURES command.
 	 */
 	if (is_ata) {
+		struct scsi_mode_data data;
+		struct scsi_sense_hdr sshdr;
 		char *buf_data;
 		int len;
 
@@ -735,16 +732,30 @@ int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
 		if (ret)
 			return -EINVAL;
 
-		/* Enable CDL using the ATA feature page */
+		/* Enable or disable CDL using the ATA feature page */
 		len = min_t(size_t, sizeof(buf),
 			    data.length - data.header_length -
 			    data.block_descriptor_length);
 		buf_data = buf + data.header_length +
 			data.block_descriptor_length;
-		if (enable)
-			buf_data[4] = 0x02;
-		else
-			buf_data[4] = 0;
+
+		/*
+		 * If we want to enable CDL and CDL is already enabled on the
+		 * device, do nothing. This avoids needlessly resetting the CDL
+		 * statistics on the device as that is implied by the CDL enable
+		 * action. Similar to this, there is no need to do anything if
+		 * we want to disable CDL and CDL is already disabled.
+		 */
+		if (enable) {
+			if ((buf_data[4] & 0x03) == 0x02)
+				goto out;
+			buf_data[4] &= ~0x03;
+			buf_data[4] |= 0x02;
+		} else {
+			if ((buf_data[4] & 0x03) == 0x00)
+				goto out;
+			buf_data[4] &= ~0x03;
+		}
 
 		ret = scsi_mode_select(sdev, 1, 0, buf_data, len, 5 * HZ, 3,
 				       &data, &sshdr);
@@ -756,6 +767,7 @@ int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
 		}
 	}
 
+out:
 	sdev->cdl_enable = enable;
 
 	return 0;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 0d29470e86b0..1b43013d72c0 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1253,8 +1253,12 @@ EXPORT_SYMBOL_GPL(scsi_alloc_request);
  */
 static void scsi_cleanup_rq(struct request *rq)
 {
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+	cmd->flags = 0;
+
 	if (rq->rq_flags & RQF_DONTPREP) {
-		scsi_mq_uninit_cmd(blk_mq_rq_to_pdu(rq));
+		scsi_mq_uninit_cmd(cmd);
 		rq->rq_flags &= ~RQF_DONTPREP;
 	}
 }
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 9c347c64c315..0b8c91bf793f 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -3182,11 +3182,14 @@ iscsi_set_host_param(struct iscsi_transport *transport,
 	}
 
 	/* see similar check in iscsi_if_set_param() */
-	if (strlen(data) > ev->u.set_host_param.len)
-		return -EINVAL;
+	if (strlen(data) > ev->u.set_host_param.len) {
+		err = -EINVAL;
+		goto out;
+	}
 
 	err = transport->set_host_param(shost, ev->u.set_host_param.param,
 					data, ev->u.set_host_param.len);
+out:
 	scsi_host_put(shost);
 	return err;
 }
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index 64f6b22e8cc0..aeb58a9e6b7f 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -388,7 +388,7 @@ static void srp_reconnect_work(struct work_struct *work)
 			     "reconnect attempt %d failed (%d)\n",
 			     ++rport->failed_reconnects, res);
 		delay = rport->reconnect_delay *
-			min(100, max(1, rport->failed_reconnects - 10));
+			clamp(rport->failed_reconnects - 10, 1, 100);
 		if (delay > 0)
 			queue_delayed_work(system_long_wq,
 					   &rport->reconnect_work, delay * HZ);
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 7a447ff600d2..a8db66428f80 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -169,6 +169,7 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
 					unsigned int nr_zones, size_t *buflen)
 {
 	struct request_queue *q = sdkp->disk->queue;
+	unsigned int max_segments;
 	size_t bufsize;
 	void *buf;
 
@@ -180,12 +181,15 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
 	 * Furthermore, since the report zone command cannot be split, make
 	 * sure that the allocated buffer can always be mapped by limiting the
 	 * number of pages allocated to the HBA max segments limit.
+	 * Since max segments can be larger than the max inline bio vectors,
+	 * further limit the allocated buffer to BIO_MAX_INLINE_VECS.
 	 */
 	nr_zones = min(nr_zones, sdkp->zone_info.nr_zones);
 	bufsize = roundup((nr_zones + 1) * 64, SECTOR_SIZE);
 	bufsize = min_t(size_t, bufsize,
 			queue_max_hw_sectors(q) << SECTOR_SHIFT);
-	bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);
+	max_segments = min(BIO_MAX_INLINE_VECS, queue_max_segments(q));
+	bufsize = min_t(size_t, bufsize, max_segments << PAGE_SHIFT);
 
 	while (bufsize >= SECTOR_SIZE) {
 		buf = kvzalloc(bufsize, GFP_KERNEL | __GFP_NORETRY);
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 88135fdb8bd1..8a26eca4fdc9 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -19,6 +19,7 @@
 #include <linux/bcd.h>
 #include <linux/reboot.h>
 #include <linux/cciss_ioctl.h>
+#include <linux/crash_dump.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
@@ -5246,7 +5247,7 @@ static void pqi_calculate_io_resources(struct pqi_ctrl_info *ctrl_info)
 	ctrl_info->error_buffer_length =
 		ctrl_info->max_io_slots * PQI_ERROR_BUFFER_ELEMENT_LENGTH;
 
-	if (reset_devices)
+	if (is_kdump_kernel())
 		max_transfer_size = min(ctrl_info->max_transfer_size,
 			PQI_MAX_TRANSFER_SIZE_KDUMP);
 	else
@@ -5275,7 +5276,7 @@ static void pqi_calculate_queue_resources(struct pqi_ctrl_info *ctrl_info)
 	u16 num_elements_per_iq;
 	u16 num_elements_per_oq;
 
-	if (reset_devices) {
+	if (is_kdump_kernel()) {
 		num_queue_groups = 1;
 	} else {
 		int num_cpus;
@@ -8288,12 +8289,12 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
 	u32 product_id;
 
 	if (reset_devices) {
-		if (pqi_is_fw_triage_supported(ctrl_info)) {
+		if (is_kdump_kernel() && pqi_is_fw_triage_supported(ctrl_info)) {
 			rc = sis_wait_for_fw_triage_completion(ctrl_info);
 			if (rc)
 				return rc;
 		}
-		if (sis_is_ctrl_logging_supported(ctrl_info)) {
+		if (is_kdump_kernel() && sis_is_ctrl_logging_supported(ctrl_info)) {
 			sis_notify_kdump(ctrl_info);
 			rc = sis_wait_for_ctrl_logging_completion(ctrl_info);
 			if (rc)
@@ -8344,7 +8345,7 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
 	ctrl_info->product_id = (u8)product_id;
 	ctrl_info->product_revision = (u8)(product_id >> 8);
 
-	if (reset_devices) {
+	if (is_kdump_kernel()) {
 		if (ctrl_info->max_outstanding_requests >
 			PQI_MAX_OUTSTANDING_REQUESTS_KDUMP)
 				ctrl_info->max_outstanding_requests =
@@ -8480,7 +8481,7 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
 	if (rc)
 		return rc;
 
-	if (ctrl_info->ctrl_logging_supported && !reset_devices) {
+	if (ctrl_info->ctrl_logging_supported && !is_kdump_kernel()) {
 		pqi_host_setup_buffer(ctrl_info, &ctrl_info->ctrl_log_memory, PQI_CTRL_LOG_TOTAL_SIZE, PQI_CTRL_LOG_MIN_SIZE);
 		pqi_host_memory_update(ctrl_info, &ctrl_info->ctrl_log_memory, PQI_VENDOR_GENERAL_CTRL_LOG_MEMORY_UPDATE);
 	}
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 35db061ae3ec..2e6b2412d2c9 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1819,6 +1819,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 				return SCSI_MLQUEUE_DEVICE_BUSY;
 		}
 
+		payload->rangecount = 1;
 		payload->range.len = length;
 		payload->range.offset = offset_in_hvpg;
 
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 6f8a20014e76..39aecd34c641 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -122,6 +122,10 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
 	set_bit(SDW_GROUP13_DEV_NUM, bus->assigned);
 	set_bit(SDW_MASTER_DEV_NUM, bus->assigned);
 
+	ret = sdw_irq_create(bus, fwnode);
+	if (ret)
+		return ret;
+
 	/*
 	 * SDW is an enumerable bus, but devices can be powered off. So,
 	 * they won't be able to report as present.
@@ -138,6 +142,7 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
 
 	if (ret < 0) {
 		dev_err(bus->dev, "Finding slaves failed:%d\n", ret);
+		sdw_irq_delete(bus);
 		return ret;
 	}
 
@@ -156,10 +161,6 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
 	bus->params.curr_bank = SDW_BANK0;
 	bus->params.next_bank = SDW_BANK1;
 
-	ret = sdw_irq_create(bus, fwnode);
-	if (ret)
-		return ret;
-
 	return 0;
 }
 EXPORT_SYMBOL(sdw_bus_master_add);
diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c
index 5ea6399e6c9b..10a602d4843a 100644
--- a/drivers/soundwire/intel_auxdevice.c
+++ b/drivers/soundwire/intel_auxdevice.c
@@ -353,9 +353,6 @@ static int intel_link_probe(struct auxiliary_device *auxdev,
 	/* use generic bandwidth allocation algorithm */
 	sdw->cdns.bus.compute_params = sdw_compute_params;
 
-	/* avoid resuming from pm_runtime suspend if it's not required */
-	dev_pm_set_driver_flags(dev, DPM_FLAG_SMART_SUSPEND);
-
 	ret = sdw_bus_master_add(bus, dev, dev->fwnode);
 	if (ret) {
 		dev_err(dev, "sdw_bus_master_add fail: %d\n", ret);
@@ -640,7 +637,10 @@ static int __maybe_unused intel_suspend(struct device *dev)
 		return 0;
 	}
 
-	if (pm_runtime_suspended(dev)) {
+	/* Prevent runtime PM from racing with the code below. */
+	pm_runtime_disable(dev);
+
+	if (pm_runtime_status_suspended(dev)) {
 		dev_dbg(dev, "pm_runtime status: suspended\n");
 
 		clock_stop_quirks = sdw->link_res->clock_stop_quirks;
@@ -648,7 +648,7 @@ static int __maybe_unused intel_suspend(struct device *dev)
 		if ((clock_stop_quirks & SDW_INTEL_CLK_STOP_BUS_RESET) ||
 		    !clock_stop_quirks) {
 
-			if (pm_runtime_suspended(dev->parent)) {
+			if (pm_runtime_status_suspended(dev->parent)) {
 				/*
 				 * paranoia check: this should not happen with the .prepare
 				 * resume to full power
@@ -715,7 +715,6 @@ static int __maybe_unused intel_resume(struct device *dev)
 	struct sdw_cdns *cdns = dev_get_drvdata(dev);
 	struct sdw_intel *sdw = cdns_to_intel(cdns);
 	struct sdw_bus *bus = &cdns->bus;
-	int link_flags;
 	int ret;
 
 	if (bus->prop.hw_disabled || !sdw->startup_done) {
@@ -724,23 +723,6 @@ static int __maybe_unused intel_resume(struct device *dev)
 		return 0;
 	}
 
-	if (pm_runtime_suspended(dev)) {
-		dev_dbg(dev, "pm_runtime status was suspended, forcing active\n");
-
-		/* follow required sequence from runtime_pm.rst */
-		pm_runtime_disable(dev);
-		pm_runtime_set_active(dev);
-		pm_runtime_mark_last_busy(dev);
-		pm_runtime_enable(dev);
-
-		pm_runtime_resume(bus->dev);
-
-		link_flags = md_flags >> (bus->link_id * 8);
-
-		if (!(link_flags & SDW_INTEL_MASTER_DISABLE_PM_RUNTIME_IDLE))
-			pm_runtime_idle(dev);
-	}
-
 	ret = sdw_intel_link_power_up(sdw);
 	if (ret) {
 		dev_err(dev, "%s failed: %d\n", __func__, ret);
@@ -761,6 +743,14 @@ static int __maybe_unused intel_resume(struct device *dev)
 	}
 
 	/*
+	 * Runtime PM has been disabled in intel_suspend(), so set the status
+	 * to active because the device has just been resumed and re-enable
+	 * runtime PM.
+	 */
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
+	/*
 	 * after system resume, the pm_runtime suspend() may kick in
 	 * during the enumeration, before any children device force the
 	 * master device to remain active.  Using pm_runtime_get()
diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c
index 5c59fddb32c1..b5ecffcaf795 100644
--- a/drivers/spi/spi-fsl-qspi.c
+++ b/drivers/spi/spi-fsl-qspi.c
@@ -949,24 +949,20 @@ static int fsl_qspi_probe(struct platform_device *pdev)
 
 	ret = devm_add_action_or_reset(dev, fsl_qspi_cleanup, q);
 	if (ret)
-		goto err_destroy_mutex;
+		goto err_put_ctrl;
 
 	ret = devm_spi_register_controller(dev, ctlr);
 	if (ret)
-		goto err_destroy_mutex;
+		goto err_put_ctrl;
 
 	return 0;
 
-err_destroy_mutex:
-	mutex_destroy(&q->lock);
-
 err_disable_clk:
 	fsl_qspi_clk_disable_unprep(q);
 
 err_put_ctrl:
 	spi_controller_put(ctlr);
 
-	dev_err(dev, "Freescale QuadSPI probe failed\n");
 	return ret;
 }
 
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 832d6e9009eb..c93d80a4d734 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1695,9 +1695,12 @@ static int spi_imx_transfer_one(struct spi_controller *controller,
 				struct spi_device *spi,
 				struct spi_transfer *transfer)
 {
+	int ret;
 	struct spi_imx_data *spi_imx = spi_controller_get_devdata(spi->controller);
 
-	spi_imx_setupxfer(spi, transfer);
+	ret = spi_imx_setupxfer(spi, transfer);
+	if (ret < 0)
+		return ret;
 	transfer->effective_speed_hz = spi_imx->spi_bus_clk;
 
 	/* flush rxfifo before transfer */
diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c
index 31a878d9458d..7740f94847a8 100644
--- a/drivers/spi/spi-loopback-test.c
+++ b/drivers/spi/spi-loopback-test.c
@@ -420,7 +420,7 @@ MODULE_LICENSE("GPL");
 static void spi_test_print_hex_dump(char *pre, const void *ptr, size_t len)
 {
 	/* limit the hex_dump */
-	if (len < 1024) {
+	if (len <= 1024) {
 		print_hex_dump(KERN_INFO, pre,
 			       DUMP_PREFIX_OFFSET, 16, 1,
 			       ptr, len, 0);
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index a31a1db07aa4..5db0639d3b01 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -596,7 +596,11 @@ u64 spi_mem_calc_op_duration(struct spi_mem_op *op)
 	ns_per_cycles = 1000000000 / op->max_freq;
 	ncycles += ((op->cmd.nbytes * 8) / op->cmd.buswidth) / (op->cmd.dtr ? 2 : 1);
 	ncycles += ((op->addr.nbytes * 8) / op->addr.buswidth) / (op->addr.dtr ? 2 : 1);
-	ncycles += ((op->dummy.nbytes * 8) / op->dummy.buswidth) / (op->dummy.dtr ? 2 : 1);
+
+	/* Dummy bytes are optional for some SPI flash memory operations */
+	if (op->dummy.nbytes)
+		ncycles += ((op->dummy.nbytes * 8) / op->dummy.buswidth) / (op->dummy.dtr ? 2 : 1);
+
 	ncycles += ((op->data.nbytes * 8) / op->data.buswidth) / (op->data.dtr ? 2 : 1);
 
 	return ncycles * ns_per_cycles;
diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c
index 17eb67e19132..94948c8781e8 100644
--- a/drivers/spi/spi-qpic-snand.c
+++ b/drivers/spi/spi-qpic-snand.c
@@ -142,7 +142,7 @@ static void qcom_spi_set_read_loc_first(struct qcom_nand_controller *snandc,
 	else if (reg == NAND_READ_LOCATION_1)
 		snandc->regs->read_location1 = locreg_val;
 	else if (reg == NAND_READ_LOCATION_2)
-		snandc->regs->read_location1 = locreg_val;
+		snandc->regs->read_location2 = locreg_val;
 	else if (reg == NAND_READ_LOCATION_3)
 		snandc->regs->read_location3 = locreg_val;
 }
@@ -1307,8 +1307,7 @@ static int qcom_spi_send_cmdaddr(struct qcom_nand_controller *snandc,
 		snandc->qspi->addr1 = cpu_to_le32(s_op.addr1_reg << 16);
 		snandc->qspi->addr2 = cpu_to_le32(s_op.addr2_reg);
 		snandc->qspi->cmd = cpu_to_le32(cmd);
-		qcom_spi_block_erase(snandc);
-		return 0;
+		return qcom_spi_block_erase(snandc);
 	default:
 		break;
 	}
diff --git a/drivers/spi/spi-stm32-ospi.c b/drivers/spi/spi-stm32-ospi.c
index 668022098b1e..9ec9823409cc 100644
--- a/drivers/spi/spi-stm32-ospi.c
+++ b/drivers/spi/spi-stm32-ospi.c
@@ -960,6 +960,10 @@ err_pm_resume:
 err_pm_enable:
 	pm_runtime_force_suspend(ospi->dev);
 	mutex_destroy(&ospi->lock);
+	if (ospi->dma_chtx)
+		dma_release_channel(ospi->dma_chtx);
+	if (ospi->dma_chrx)
+		dma_release_channel(ospi->dma_chrx);
 
 	return ret;
 }
diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index fcbe864c9b7d..aa92fd5a35a9 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -264,6 +264,9 @@ static int sun4i_spi_transfer_one(struct spi_controller *host,
 	else
 		reg |= SUN4I_CTL_DHB;
 
+	/* Now that the settings are correct, enable the interface */
+	reg |= SUN4I_CTL_ENABLE;
+
 	sun4i_spi_write(sspi, SUN4I_CTL_REG, reg);
 
 	/* Ensure that we have a parent clock fast enough */
@@ -404,7 +407,7 @@ static int sun4i_spi_runtime_resume(struct device *dev)
 	}
 
 	sun4i_spi_write(sspi, SUN4I_CTL_REG,
-			SUN4I_CTL_ENABLE | SUN4I_CTL_MASTER | SUN4I_CTL_TP);
+			SUN4I_CTL_MASTER | SUN4I_CTL_TP);
 
 	return 0;
 
@@ -462,6 +465,7 @@ static int sun4i_spi_probe(struct platform_device *pdev)
 	sspi->host = host;
 	host->max_speed_hz = 100 * 1000 * 1000;
 	host->min_speed_hz = 3 * 1000;
+	host->use_gpio_descriptors = true;
 	host->set_cs = sun4i_spi_set_cs;
 	host->transfer_one = sun4i_spi_transfer_one;
 	host->num_chipselect = 4;
diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c
index 3822d7c8d8ed..795a8482c2c7 100644
--- a/drivers/spi/spi-tegra114.c
+++ b/drivers/spi/spi-tegra114.c
@@ -728,9 +728,9 @@ static int tegra_spi_set_hw_cs_timing(struct spi_device *spi)
 	u32 inactive_cycles;
 	u8 cs_state;
 
-	if (setup->unit != SPI_DELAY_UNIT_SCK ||
-	    hold->unit != SPI_DELAY_UNIT_SCK ||
-	    inactive->unit != SPI_DELAY_UNIT_SCK) {
+	if ((setup->value && setup->unit != SPI_DELAY_UNIT_SCK) ||
+	    (hold->value && hold->unit != SPI_DELAY_UNIT_SCK) ||
+	    (inactive->value && inactive->unit != SPI_DELAY_UNIT_SCK)) {
 		dev_err(&spi->dev,
 			"Invalid delay unit %d, should be SPI_DELAY_UNIT_SCK\n",
 			SPI_DELAY_UNIT_SCK);
diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c
index 08e49a876894..64e1b2f8a000 100644
--- a/drivers/spi/spi-tegra210-quad.c
+++ b/drivers/spi/spi-tegra210-quad.c
@@ -1117,9 +1117,9 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
 					(&tqspi->xfer_completion,
 					QSPI_DMA_TIMEOUT);
 
-			if (WARN_ON(ret == 0)) {
-				dev_err(tqspi->dev, "QSPI Transfer failed with timeout: %d\n",
-					ret);
+			if (WARN_ON_ONCE(ret == 0)) {
+				dev_err_ratelimited(tqspi->dev,
+						    "QSPI Transfer failed with timeout\n");
 				if (tqspi->is_curr_dma_xfer &&
 				    (tqspi->cur_direction & DATA_DIR_TX))
 					dmaengine_terminate_all
diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c
index 897cb8db5084..f9426a586653 100644
--- a/drivers/ssb/driver_gpio.c
+++ b/drivers/ssb/driver_gpio.c
@@ -148,8 +148,8 @@ static int ssb_gpio_irq_chipco_domain_init(struct ssb_bus *bus)
 	if (bus->bustype != SSB_BUSTYPE_SSB)
 		return 0;
 
-	bus->irq_domain = irq_domain_add_linear(NULL, chip->ngpio,
-						&irq_domain_simple_ops, chipco);
+	bus->irq_domain = irq_domain_create_linear(NULL, chip->ngpio, &irq_domain_simple_ops,
+						   chipco);
 	if (!bus->irq_domain) {
 		err = -ENODEV;
 		goto err_irq_domain;
@@ -347,8 +347,8 @@ static int ssb_gpio_irq_extif_domain_init(struct ssb_bus *bus)
 	if (bus->bustype != SSB_BUSTYPE_SSB)
 		return 0;
 
-	bus->irq_domain = irq_domain_add_linear(NULL, chip->ngpio,
-						&irq_domain_simple_ops, extif);
+	bus->irq_domain = irq_domain_create_linear(NULL, chip->ngpio, &irq_domain_simple_ops,
+						   extif);
 	if (!bus->irq_domain) {
 		err = -ENODEV;
 		goto err_irq_domain;
diff --git a/drivers/staging/axis-fifo/axis-fifo.c b/drivers/staging/axis-fifo/axis-fifo.c
index 7540c20090c7..351f983ef914 100644
--- a/drivers/staging/axis-fifo/axis-fifo.c
+++ b/drivers/staging/axis-fifo/axis-fifo.c
@@ -393,16 +393,14 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
 
 	bytes_available = ioread32(fifo->base_addr + XLLF_RLR_OFFSET);
 	if (!bytes_available) {
-		dev_err(fifo->dt_device, "received a packet of length 0 - fifo core will be reset\n");
-		reset_ip_core(fifo);
+		dev_err(fifo->dt_device, "received a packet of length 0\n");
 		ret = -EIO;
 		goto end_unlock;
 	}
 
 	if (bytes_available > len) {
-		dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu) - fifo core will be reset\n",
+		dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu)\n",
 			bytes_available, len);
-		reset_ip_core(fifo);
 		ret = -EINVAL;
 		goto end_unlock;
 	}
@@ -411,8 +409,7 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
 		/* this probably can't happen unless IP
 		 * registers were previously mishandled
 		 */
-		dev_err(fifo->dt_device, "received a packet that isn't word-aligned - fifo core will be reset\n");
-		reset_ip_core(fifo);
+		dev_err(fifo->dt_device, "received a packet that isn't word-aligned\n");
 		ret = -EIO;
 		goto end_unlock;
 	}
@@ -433,7 +430,6 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
 
 		if (copy_to_user(buf + copied * sizeof(u32), tmp_buf,
 				 copy * sizeof(u32))) {
-			reset_ip_core(fifo);
 			ret = -EFAULT;
 			goto end_unlock;
 		}
@@ -542,7 +538,6 @@ static ssize_t axis_fifo_write(struct file *f, const char __user *buf,
 
 		if (copy_from_user(tmp_buf, buf + copied * sizeof(u32),
 				   copy * sizeof(u32))) {
-			reset_ip_core(fifo);
 			ret = -EFAULT;
 			goto end_unlock;
 		}
@@ -775,9 +770,6 @@ static int axis_fifo_parse_dt(struct axis_fifo *fifo)
 		goto end;
 	}
 
-	/* IP sets TDFV to fifo depth - 4 so we will do the same */
-	fifo->tx_fifo_depth -= 4;
-
 	ret = get_dts_property(fifo, "xlnx,use-rx-data", &fifo->has_rx_fifo);
 	if (ret) {
 		dev_err(fifo->dt_device, "missing xlnx,use-rx-data property\n");
diff --git a/drivers/staging/iio/adc/ad7816.c b/drivers/staging/iio/adc/ad7816.c
index 6c14d7bcdd67..081b17f49863 100644
--- a/drivers/staging/iio/adc/ad7816.c
+++ b/drivers/staging/iio/adc/ad7816.c
@@ -136,7 +136,7 @@ static ssize_t ad7816_store_mode(struct device *dev,
 	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
 	struct ad7816_chip_info *chip = iio_priv(indio_dev);
 
-	if (strcmp(buf, "full")) {
+	if (strcmp(buf, "full") == 0) {
 		gpiod_set_value(chip->rdwr_pin, 1);
 		chip->mode = AD7816_FULL;
 	} else {
diff --git a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
index b839b50ac26a..fa7ea4ca4c36 100644
--- a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
+++ b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
@@ -1900,6 +1900,7 @@ static int bcm2835_mmal_probe(struct vchiq_device *device)
 				__func__, ret);
 			goto free_dev;
 		}
+		dev->v4l2_dev.dev = &device->dev;
 
 		/* setup v4l controls */
 		ret = bcm2835_mmal_init_controls(dev, &dev->ctrl_handler);
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 1244ef3aa86c..620ba6e0ab07 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -4263,8 +4263,8 @@ int iscsit_close_connection(
 	spin_unlock(&iscsit_global->ts_bitmap_lock);
 
 	iscsit_stop_timers_for_cmds(conn);
-	iscsit_stop_nopin_response_timer(conn);
 	iscsit_stop_nopin_timer(conn);
+	iscsit_stop_nopin_response_timer(conn);
 
 	if (conn->conn_transport->iscsit_wait_conn)
 		conn->conn_transport->iscsit_wait_conn(conn);
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
index a55aaa8cef42..2097aae39946 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
@@ -485,7 +485,7 @@ static const struct pci_device_id proc_thermal_pci_ids[] = {
 	{ PCI_DEVICE_DATA(INTEL, ADL_THERMAL, PROC_THERMAL_FEATURE_RAPL |
 	  PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_REQ) },
 	{ PCI_DEVICE_DATA(INTEL, LNLM_THERMAL, PROC_THERMAL_FEATURE_MSI_SUPPORT |
-	  PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_DLVR |
+	  PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_DVFS |
 	  PROC_THERMAL_FEATURE_WT_HINT | PROC_THERMAL_FEATURE_POWER_FLOOR) },
 	{ PCI_DEVICE_DATA(INTEL, MTLP_THERMAL, PROC_THERMAL_FEATURE_RAPL |
 	  PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_DLVR |
@@ -495,8 +495,9 @@ static const struct pci_device_id proc_thermal_pci_ids[] = {
 	{ PCI_DEVICE_DATA(INTEL, RPL_THERMAL, PROC_THERMAL_FEATURE_RAPL |
 	  PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_REQ) },
 	{ PCI_DEVICE_DATA(INTEL, PTL_THERMAL, PROC_THERMAL_FEATURE_RAPL |
-	  PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_MSI_SUPPORT |
-	  PROC_THERMAL_FEATURE_WT_HINT | PROC_THERMAL_FEATURE_POWER_FLOOR) },
+	  PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_DVFS |
+	  PROC_THERMAL_FEATURE_MSI_SUPPORT | PROC_THERMAL_FEATURE_WT_HINT |
+	  PROC_THERMAL_FEATURE_POWER_FLOOR) },
 	{ },
 };
 
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
index dad63f2d5f90..3a028b78d9af 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
@@ -166,15 +166,18 @@ static const struct mmio_reg adl_dvfs_mmio_regs[] = {
 	{ 0, 0x5A40, 1, 0x1, 0}, /* rfi_disable */
 };
 
+static const struct mapping_table *dlvr_mapping;
+static const struct mmio_reg *dlvr_mmio_regs_table;
+
 #define RFIM_SHOW(suffix, table)\
 static ssize_t suffix##_show(struct device *dev,\
 			      struct device_attribute *attr,\
 			      char *buf)\
 {\
-	const struct mapping_table *mapping = NULL;\
+	const struct mmio_reg *mmio_regs = dlvr_mmio_regs_table;\
+	const struct mapping_table *mapping = dlvr_mapping;\
 	struct proc_thermal_device *proc_priv;\
 	struct pci_dev *pdev = to_pci_dev(dev);\
-	const struct mmio_reg *mmio_regs;\
 	const char **match_strs;\
 	int ret, err;\
 	u32 reg_val;\
@@ -186,12 +189,6 @@ static ssize_t suffix##_show(struct device *dev,\
 		mmio_regs = adl_dvfs_mmio_regs;\
 	} else if (table == 2) { \
 		match_strs = (const char **)dlvr_strings;\
-		if (pdev->device == PCI_DEVICE_ID_INTEL_LNLM_THERMAL) {\
-			mmio_regs = lnl_dlvr_mmio_regs;\
-			mapping = lnl_dlvr_mapping;\
-		} else {\
-			mmio_regs = dlvr_mmio_regs;\
-		} \
 	} else {\
 		match_strs = (const char **)fivr_strings;\
 		mmio_regs = tgl_fivr_mmio_regs;\
@@ -214,12 +211,12 @@ static ssize_t suffix##_store(struct device *dev,\
 			       struct device_attribute *attr,\
 			       const char *buf, size_t count)\
 {\
-	const struct mapping_table *mapping = NULL;\
+	const struct mmio_reg *mmio_regs = dlvr_mmio_regs_table;\
+	const struct mapping_table *mapping = dlvr_mapping;\
 	struct proc_thermal_device *proc_priv;\
 	struct pci_dev *pdev = to_pci_dev(dev);\
 	unsigned int input;\
 	const char **match_strs;\
-	const struct mmio_reg *mmio_regs;\
 	int ret, err;\
 	u32 reg_val;\
 	u32 mask;\
@@ -230,12 +227,6 @@ static ssize_t suffix##_store(struct device *dev,\
 		mmio_regs = adl_dvfs_mmio_regs;\
 	} else if (table == 2) { \
 		match_strs = (const char **)dlvr_strings;\
-		if (pdev->device == PCI_DEVICE_ID_INTEL_LNLM_THERMAL) {\
-			mmio_regs = lnl_dlvr_mmio_regs;\
-			mapping = lnl_dlvr_mapping;\
-		} else {\
-			mmio_regs = dlvr_mmio_regs;\
-		} \
 	} else {\
 		match_strs = (const char **)fivr_strings;\
 		mmio_regs = tgl_fivr_mmio_regs;\
@@ -448,6 +439,16 @@ int proc_thermal_rfim_add(struct pci_dev *pdev, struct proc_thermal_device *proc
 	}
 
 	if (proc_priv->mmio_feature_mask & PROC_THERMAL_FEATURE_DLVR) {
+		switch (pdev->device) {
+		case PCI_DEVICE_ID_INTEL_LNLM_THERMAL:
+		case PCI_DEVICE_ID_INTEL_PTL_THERMAL:
+			dlvr_mmio_regs_table = lnl_dlvr_mmio_regs;
+			dlvr_mapping = lnl_dlvr_mapping;
+			break;
+		default:
+			dlvr_mmio_regs_table = dlvr_mmio_regs;
+			break;
+		}
 		ret = sysfs_create_group(&pdev->dev.kobj, &dlvr_attribute_group);
 		if (ret)
 			return ret;
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index 1b137e068444..3449945493ce 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -1746,6 +1746,12 @@ msm_serial_early_console_setup_dm(struct earlycon_device *device,
 	if (!device->port.membase)
 		return -ENODEV;
 
+	/* Disable DM / single-character modes */
+	msm_write(&device->port, 0, UARTDM_DMEN);
+	msm_write(&device->port, MSM_UART_CR_CMD_RESET_RX, MSM_UART_CR);
+	msm_write(&device->port, MSM_UART_CR_CMD_RESET_TX, MSM_UART_CR);
+	msm_write(&device->port, MSM_UART_CR_TX_ENABLE, MSM_UART_CR);
+
 	device->con->write = msm_serial_early_write_dm;
 	return 0;
 }
diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index 5904a2d4cefa..054a8e630ace 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -563,8 +563,11 @@ static void sifive_serial_break_ctl(struct uart_port *port, int break_state)
 static int sifive_serial_startup(struct uart_port *port)
 {
 	struct sifive_serial_port *ssp = port_to_sifive_serial_port(port);
+	unsigned long flags;
 
+	uart_port_lock_irqsave(&ssp->port, &flags);
 	__ssp_enable_rxwm(ssp);
+	uart_port_unlock_irqrestore(&ssp->port, flags);
 
 	return 0;
 }
@@ -572,9 +575,12 @@ static int sifive_serial_startup(struct uart_port *port)
 static void sifive_serial_shutdown(struct uart_port *port)
 {
 	struct sifive_serial_port *ssp = port_to_sifive_serial_port(port);
+	unsigned long flags;
 
+	uart_port_lock_irqsave(&ssp->port, &flags);
 	__ssp_disable_rxwm(ssp);
 	__ssp_disable_txwm(ssp);
+	uart_port_unlock_irqrestore(&ssp->port, flags);
 }
 
 /**
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 0bd6544e30a6..791e2f1f7c0b 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -193,13 +193,12 @@ int set_selection_user(const struct tiocl_selection __user *sel,
 		return -EFAULT;
 
 	/*
-	 * TIOCL_SELCLEAR, TIOCL_SELPOINTER and TIOCL_SELMOUSEREPORT are OK to
-	 * use without CAP_SYS_ADMIN as they do not modify the selection.
+	 * TIOCL_SELCLEAR and TIOCL_SELPOINTER are OK to use without
+	 * CAP_SYS_ADMIN as they do not modify the selection.
 	 */
 	switch (v.sel_mode) {
 	case TIOCL_SELCLEAR:
 	case TIOCL_SELPOINTER:
-	case TIOCL_SELMOUSEREPORT:
 		break;
 	default:
 		if (!capable(CAP_SYS_ADMIN))
diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 240ce135bbfb..f1294c29f484 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -677,13 +677,6 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
 	unsigned long flags;
 	int err;
 
-	if (!ufshcd_cmd_inflight(lrbp->cmd)) {
-		dev_err(hba->dev,
-			"%s: skip abort. cmd at tag %d already completed.\n",
-			__func__, tag);
-		return FAILED;
-	}
-
 	/* Skip task abort in case previous aborts failed and report failure */
 	if (lrbp->req_abort_skip) {
 		dev_err(hba->dev, "%s: skip abort. tag %d failed earlier\n",
@@ -692,6 +685,11 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
 	}
 
 	hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+	if (!hwq) {
+		dev_err(hba->dev, "%s: skip abort. cmd at tag %d already completed.\n",
+			__func__, tag);
+		return FAILED;
+	}
 
 	if (ufshcd_mcq_sqe_search(hba, hwq, tag)) {
 		/*
diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c
index 90b5ab60f5ae..634cf163f4cb 100644
--- a/drivers/ufs/core/ufs-sysfs.c
+++ b/drivers/ufs/core/ufs-sysfs.c
@@ -466,6 +466,56 @@ static ssize_t critical_health_show(struct device *dev,
 	return sysfs_emit(buf, "%d\n", hba->critical_health_count);
 }
 
+static ssize_t device_lvl_exception_count_show(struct device *dev,
+					       struct device_attribute *attr,
+					       char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	if (hba->dev_info.wspecversion < 0x410)
+		return -EOPNOTSUPP;
+
+	return sysfs_emit(buf, "%u\n", atomic_read(&hba->dev_lvl_exception_count));
+}
+
+static ssize_t device_lvl_exception_count_store(struct device *dev,
+						struct device_attribute *attr,
+						const char *buf, size_t count)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	unsigned int value;
+
+	if (kstrtouint(buf, 0, &value))
+		return -EINVAL;
+
+	/* the only supported usecase is to reset the dev_lvl_exception_count */
+	if (value)
+		return -EINVAL;
+
+	atomic_set(&hba->dev_lvl_exception_count, 0);
+
+	return count;
+}
+
+static ssize_t device_lvl_exception_id_show(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	u64 exception_id;
+	int err;
+
+	ufshcd_rpm_get_sync(hba);
+	err = ufshcd_read_device_lvl_exception_id(hba, &exception_id);
+	ufshcd_rpm_put_sync(hba);
+
+	if (err)
+		return err;
+
+	hba->dev_lvl_exception_id = exception_id;
+	return sysfs_emit(buf, "%llu\n", exception_id);
+}
+
 static DEVICE_ATTR_RW(rpm_lvl);
 static DEVICE_ATTR_RO(rpm_target_dev_state);
 static DEVICE_ATTR_RO(rpm_target_link_state);
@@ -479,6 +529,8 @@ static DEVICE_ATTR_RW(wb_flush_threshold);
 static DEVICE_ATTR_RW(rtc_update_ms);
 static DEVICE_ATTR_RW(pm_qos_enable);
 static DEVICE_ATTR_RO(critical_health);
+static DEVICE_ATTR_RW(device_lvl_exception_count);
+static DEVICE_ATTR_RO(device_lvl_exception_id);
 
 static struct attribute *ufs_sysfs_ufshcd_attrs[] = {
 	&dev_attr_rpm_lvl.attr,
@@ -494,6 +546,8 @@ static struct attribute *ufs_sysfs_ufshcd_attrs[] = {
 	&dev_attr_rtc_update_ms.attr,
 	&dev_attr_pm_qos_enable.attr,
 	&dev_attr_critical_health.attr,
+	&dev_attr_device_lvl_exception_count.attr,
+	&dev_attr_device_lvl_exception_id.attr,
 	NULL
 };
 
diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h
index 10b4a19a70f1..d0a2c963a27d 100644
--- a/drivers/ufs/core/ufshcd-priv.h
+++ b/drivers/ufs/core/ufshcd-priv.h
@@ -94,6 +94,7 @@ int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba,
 			     enum query_opcode desc_op);
 
 int ufshcd_wb_toggle(struct ufs_hba *hba, bool enable);
+int ufshcd_read_device_lvl_exception_id(struct ufs_hba *hba, u64 *exception_id);
 
 /* Wrapper functions for safely calling variant operations */
 static inline const char *ufshcd_get_var_name(struct ufs_hba *hba)
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 0534390c2a35..7735421e3991 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -278,6 +278,7 @@ static const struct ufs_dev_quirk ufs_fixups[] = {
 	  .model = UFS_ANY_MODEL,
 	  .quirk = UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM |
 		   UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE |
+		   UFS_DEVICE_QUIRK_PA_HIBER8TIME |
 		   UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS },
 	{ .wmanufacturerid = UFS_VENDOR_SKHYNIX,
 	  .model = UFS_ANY_MODEL,
@@ -3176,16 +3177,10 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
 	int err;
 
 retry:
-	time_left = wait_for_completion_timeout(hba->dev_cmd.complete,
+	time_left = wait_for_completion_timeout(&hba->dev_cmd.complete,
 						time_left);
 
 	if (likely(time_left)) {
-		/*
-		 * The completion handler called complete() and the caller of
-		 * this function still owns the @lrbp tag so the code below does
-		 * not trigger any race conditions.
-		 */
-		hba->dev_cmd.complete = NULL;
 		err = ufshcd_get_tr_ocs(lrbp, NULL);
 		if (!err)
 			err = ufshcd_dev_cmd_completion(hba, lrbp);
@@ -3199,7 +3194,6 @@ retry:
 			/* successfully cleared the command, retry if needed */
 			if (ufshcd_clear_cmd(hba, lrbp->task_tag) == 0)
 				err = -EAGAIN;
-			hba->dev_cmd.complete = NULL;
 			return err;
 		}
 
@@ -3215,11 +3209,9 @@ retry:
 			spin_lock_irqsave(&hba->outstanding_lock, flags);
 			pending = test_bit(lrbp->task_tag,
 					   &hba->outstanding_reqs);
-			if (pending) {
-				hba->dev_cmd.complete = NULL;
+			if (pending)
 				__clear_bit(lrbp->task_tag,
 					    &hba->outstanding_reqs);
-			}
 			spin_unlock_irqrestore(&hba->outstanding_lock, flags);
 
 			if (!pending) {
@@ -3237,8 +3229,6 @@ retry:
 			spin_lock_irqsave(&hba->outstanding_lock, flags);
 			pending = test_bit(lrbp->task_tag,
 					   &hba->outstanding_reqs);
-			if (pending)
-				hba->dev_cmd.complete = NULL;
 			spin_unlock_irqrestore(&hba->outstanding_lock, flags);
 
 			if (!pending) {
@@ -3272,13 +3262,9 @@ static void ufshcd_dev_man_unlock(struct ufs_hba *hba)
 static int ufshcd_issue_dev_cmd(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
 			  const u32 tag, int timeout)
 {
-	DECLARE_COMPLETION_ONSTACK(wait);
 	int err;
 
-	hba->dev_cmd.complete = &wait;
-
 	ufshcd_add_query_upiu_trace(hba, UFS_QUERY_SEND, lrbp->ucd_req_ptr);
-
 	ufshcd_send_command(hba, tag, hba->dev_cmd_queue);
 	err = ufshcd_wait_for_dev_cmd(hba, lrbp, timeout);
 
@@ -5585,12 +5571,12 @@ void ufshcd_compl_one_cqe(struct ufs_hba *hba, int task_tag,
 		ufshcd_release_scsi_cmd(hba, lrbp);
 		/* Do not touch lrbp after scsi done */
 		scsi_done(cmd);
-	} else if (hba->dev_cmd.complete) {
+	} else {
 		if (cqe) {
 			ocs = le32_to_cpu(cqe->status) & MASK_OCS;
 			lrbp->utr_descriptor_ptr->header.ocs = ocs;
 		}
-		complete(hba->dev_cmd.complete);
+		complete(&hba->dev_cmd.complete);
 	}
 }
 
@@ -5692,6 +5678,8 @@ static void ufshcd_mcq_compl_pending_transfer(struct ufs_hba *hba,
 			continue;
 
 		hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+		if (!hwq)
+			continue;
 
 		if (force_compl) {
 			ufshcd_mcq_compl_all_cqes_lock(hba, hwq);
@@ -6013,6 +6001,42 @@ out:
 				__func__, err);
 }
 
+int ufshcd_read_device_lvl_exception_id(struct ufs_hba *hba, u64 *exception_id)
+{
+	struct utp_upiu_query_v4_0 *upiu_resp;
+	struct ufs_query_req *request = NULL;
+	struct ufs_query_res *response = NULL;
+	int err;
+
+	if (hba->dev_info.wspecversion < 0x410)
+		return -EOPNOTSUPP;
+
+	ufshcd_hold(hba);
+	mutex_lock(&hba->dev_cmd.lock);
+
+	ufshcd_init_query(hba, &request, &response,
+			  UPIU_QUERY_OPCODE_READ_ATTR,
+			  QUERY_ATTR_IDN_DEV_LVL_EXCEPTION_ID, 0, 0);
+
+	request->query_func = UPIU_QUERY_FUNC_STANDARD_READ_REQUEST;
+
+	err = ufshcd_exec_dev_cmd(hba, DEV_CMD_TYPE_QUERY, QUERY_REQ_TIMEOUT);
+
+	if (err) {
+		dev_err(hba->dev, "%s: failed to read device level exception %d\n",
+			__func__, err);
+		goto out;
+	}
+
+	upiu_resp = (struct utp_upiu_query_v4_0 *)response;
+	*exception_id = get_unaligned_be64(&upiu_resp->osf3);
+out:
+	mutex_unlock(&hba->dev_cmd.lock);
+	ufshcd_release(hba);
+
+	return err;
+}
+
 static int __ufshcd_wb_toggle(struct ufs_hba *hba, bool set, enum flag_idn idn)
 {
 	u8 index;
@@ -6083,7 +6107,7 @@ int ufshcd_wb_toggle_buf_flush(struct ufs_hba *hba, bool enable)
 	return ret;
 }
 
-static bool ufshcd_wb_presrv_usrspc_keep_vcc_on(struct ufs_hba *hba,
+static bool ufshcd_wb_curr_buff_threshold_check(struct ufs_hba *hba,
 						u32 avail_buf)
 {
 	u32 cur_buf;
@@ -6165,15 +6189,13 @@ static bool ufshcd_wb_need_flush(struct ufs_hba *hba)
 	}
 
 	/*
-	 * The ufs device needs the vcc to be ON to flush.
 	 * With user-space reduction enabled, it's enough to enable flush
 	 * by checking only the available buffer. The threshold
 	 * defined here is > 90% full.
 	 * With user-space preserved enabled, the current-buffer
 	 * should be checked too because the wb buffer size can reduce
 	 * when disk tends to be full. This info is provided by current
-	 * buffer (dCurrentWriteBoosterBufferSize). There's no point in
-	 * keeping vcc on when current buffer is empty.
+	 * buffer (dCurrentWriteBoosterBufferSize).
 	 */
 	index = ufshcd_wb_get_query_index(hba);
 	ret = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR,
@@ -6188,7 +6210,7 @@ static bool ufshcd_wb_need_flush(struct ufs_hba *hba)
 	if (!hba->dev_info.b_presrv_uspc_en)
 		return avail_buf <= UFS_WB_BUF_REMAIN_PERCENT(10);
 
-	return ufshcd_wb_presrv_usrspc_keep_vcc_on(hba, avail_buf);
+	return ufshcd_wb_curr_buff_threshold_check(hba, avail_buf);
 }
 
 static void ufshcd_rpm_dev_flush_recheck_work(struct work_struct *work)
@@ -6240,6 +6262,11 @@ static void ufshcd_exception_event_handler(struct work_struct *work)
 		sysfs_notify(&hba->dev->kobj, NULL, "critical_health");
 	}
 
+	if (status & hba->ee_drv_mask & MASK_EE_DEV_LVL_EXCEPTION) {
+		atomic_inc(&hba->dev_lvl_exception_count);
+		sysfs_notify(&hba->dev->kobj, NULL, "device_lvl_exception_count");
+	}
+
 	ufs_debugfs_exception_event(hba, status);
 }
 
@@ -7238,8 +7265,6 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
 			err = -EINVAL;
 		}
 	}
-	ufshcd_add_query_upiu_trace(hba, err ? UFS_QUERY_ERR : UFS_QUERY_COMP,
-				    (struct utp_upiu_req *)lrbp->ucd_rsp_ptr);
 
 	return err;
 }
@@ -8139,6 +8164,22 @@ static void ufshcd_temp_notif_probe(struct ufs_hba *hba, const u8 *desc_buf)
 	}
 }
 
+static void ufshcd_device_lvl_exception_probe(struct ufs_hba *hba, u8 *desc_buf)
+{
+	u32 ext_ufs_feature;
+
+	if (hba->dev_info.wspecversion < 0x410)
+		return;
+
+	ext_ufs_feature = get_unaligned_be32(desc_buf +
+				DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP);
+	if (!(ext_ufs_feature & UFS_DEV_LVL_EXCEPTION_SUP))
+		return;
+
+	atomic_set(&hba->dev_lvl_exception_count, 0);
+	ufshcd_enable_ee(hba, MASK_EE_DEV_LVL_EXCEPTION);
+}
+
 static void ufshcd_set_rtt(struct ufs_hba *hba)
 {
 	struct ufs_dev_info *dev_info = &hba->dev_info;
@@ -8339,6 +8380,8 @@ static int ufs_get_device_desc(struct ufs_hba *hba)
 
 	ufs_init_rtc(hba, desc_buf);
 
+	ufshcd_device_lvl_exception_probe(hba, desc_buf);
+
 	/*
 	 * ufshcd_read_string_desc returns size of the string
 	 * reset the error value
@@ -8428,6 +8471,31 @@ out:
 	return ret;
 }
 
+/**
+ * ufshcd_quirk_override_pa_h8time - Ensures proper adjustment of PA_HIBERN8TIME.
+ * @hba: per-adapter instance
+ *
+ * Some UFS devices require specific adjustments to the PA_HIBERN8TIME parameter
+ * to ensure proper hibernation timing. This function retrieves the current
+ * PA_HIBERN8TIME value and increments it by 100us.
+ */
+static void ufshcd_quirk_override_pa_h8time(struct ufs_hba *hba)
+{
+	u32 pa_h8time;
+	int ret;
+
+	ret = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_HIBERN8TIME), &pa_h8time);
+	if (ret) {
+		dev_err(hba->dev, "Failed to get PA_HIBERN8TIME: %d\n", ret);
+		return;
+	}
+
+	/* Increment by 1 to increase hibernation time by 100 µs */
+	ret = ufshcd_dme_set(hba, UIC_ARG_MIB(PA_HIBERN8TIME), pa_h8time + 1);
+	if (ret)
+		dev_err(hba->dev, "Failed updating PA_HIBERN8TIME: %d\n", ret);
+}
+
 static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
 {
 	ufshcd_vops_apply_dev_quirks(hba);
@@ -8438,6 +8506,9 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
 
 	if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE)
 		ufshcd_quirk_tune_host_pa_tactivate(hba);
+
+	if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_HIBER8TIME)
+		ufshcd_quirk_override_pa_h8time(hba);
 }
 
 static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba)
@@ -10490,6 +10561,8 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 						UFS_SLEEP_PWR_MODE,
 						UIC_LINK_HIBERN8_STATE);
 
+	init_completion(&hba->dev_cmd.complete);
+
 	err = ufshcd_hba_init(hba);
 	if (err)
 		goto out_error;
diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index d7539cda97da..3e545af536e5 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -34,7 +34,7 @@
  * Exynos's Vendor specific registers for UFSHCI
  */
 #define HCI_TXPRDT_ENTRY_SIZE	0x00
-#define PRDT_PREFECT_EN		BIT(31)
+#define PRDT_PREFETCH_EN	BIT(31)
 #define HCI_RXPRDT_ENTRY_SIZE	0x04
 #define HCI_1US_TO_CNT_VAL	0x0C
 #define CNT_VAL_1US_MASK	0x3FF
@@ -92,11 +92,16 @@
 				 UIC_TRANSPORT_NO_CONNECTION_RX |\
 				 UIC_TRANSPORT_BAD_TC)
 
-/* FSYS UFS Shareability */
-#define UFS_WR_SHARABLE		BIT(2)
-#define UFS_RD_SHARABLE		BIT(1)
-#define UFS_SHARABLE		(UFS_WR_SHARABLE | UFS_RD_SHARABLE)
-#define UFS_SHAREABILITY_OFFSET	0x710
+/* UFS Shareability */
+#define UFS_EXYNOSAUTO_WR_SHARABLE	BIT(2)
+#define UFS_EXYNOSAUTO_RD_SHARABLE	BIT(1)
+#define UFS_EXYNOSAUTO_SHARABLE		(UFS_EXYNOSAUTO_WR_SHARABLE | \
+					 UFS_EXYNOSAUTO_RD_SHARABLE)
+#define UFS_GS101_WR_SHARABLE		BIT(1)
+#define UFS_GS101_RD_SHARABLE		BIT(0)
+#define UFS_GS101_SHARABLE		(UFS_GS101_WR_SHARABLE | \
+					 UFS_GS101_RD_SHARABLE)
+#define UFS_SHAREABILITY_OFFSET		0x710
 
 /* Multi-host registers */
 #define MHCTRL			0xC4
@@ -209,8 +214,8 @@ static int exynos_ufs_shareability(struct exynos_ufs *ufs)
 	/* IO Coherency setting */
 	if (ufs->sysreg) {
 		return regmap_update_bits(ufs->sysreg,
-					  ufs->shareability_reg_offset,
-					  UFS_SHARABLE, UFS_SHARABLE);
+					  ufs->iocc_offset,
+					  ufs->iocc_mask, ufs->iocc_val);
 	}
 
 	return 0;
@@ -957,6 +962,12 @@ static int exynos_ufs_phy_init(struct exynos_ufs *ufs)
 	}
 
 	phy_set_bus_width(generic_phy, ufs->avail_ln_rx);
+
+	if (generic_phy->power_count) {
+		phy_power_off(generic_phy);
+		phy_exit(generic_phy);
+	}
+
 	ret = phy_init(generic_phy);
 	if (ret) {
 		dev_err(hba->dev, "%s: phy init failed, ret = %d\n",
@@ -1049,9 +1060,14 @@ static int exynos_ufs_pre_link(struct ufs_hba *hba)
 	exynos_ufs_config_intr(ufs, DFES_DEF_L4_ERRS, UNIPRO_L4);
 	exynos_ufs_set_unipro_pclk_div(ufs);
 
+	exynos_ufs_setup_clocks(hba, true, PRE_CHANGE);
+
 	/* unipro */
 	exynos_ufs_config_unipro(ufs);
 
+	if (ufs->drv_data->pre_link)
+		ufs->drv_data->pre_link(ufs);
+
 	/* m-phy */
 	exynos_ufs_phy_init(ufs);
 	if (!(ufs->opts & EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR)) {
@@ -1059,11 +1075,6 @@ static int exynos_ufs_pre_link(struct ufs_hba *hba)
 		exynos_ufs_config_phy_cap_attr(ufs);
 	}
 
-	exynos_ufs_setup_clocks(hba, true, PRE_CHANGE);
-
-	if (ufs->drv_data->pre_link)
-		ufs->drv_data->pre_link(ufs);
-
 	return 0;
 }
 
@@ -1087,12 +1098,17 @@ static int exynos_ufs_post_link(struct ufs_hba *hba)
 	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
 	struct phy *generic_phy = ufs->phy;
 	struct exynos_ufs_uic_attr *attr = ufs->drv_data->uic_attr;
+	u32 val = ilog2(DATA_UNIT_SIZE);
 
 	exynos_ufs_establish_connt(ufs);
 	exynos_ufs_fit_aggr_timeout(ufs);
 
 	hci_writel(ufs, 0xa, HCI_DATA_REORDER);
-	hci_writel(ufs, ilog2(DATA_UNIT_SIZE), HCI_TXPRDT_ENTRY_SIZE);
+
+	if (hba->caps & UFSHCD_CAP_CRYPTO)
+		val |= PRDT_PREFETCH_EN;
+	hci_writel(ufs, val, HCI_TXPRDT_ENTRY_SIZE);
+
 	hci_writel(ufs, ilog2(DATA_UNIT_SIZE), HCI_RXPRDT_ENTRY_SIZE);
 	hci_writel(ufs, (1 << hba->nutrs) - 1, HCI_UTRL_NEXUS_TYPE);
 	hci_writel(ufs, (1 << hba->nutmrs) - 1, HCI_UTMRL_NEXUS_TYPE);
@@ -1168,12 +1184,22 @@ static int exynos_ufs_parse_dt(struct device *dev, struct exynos_ufs *ufs)
 		ufs->sysreg = NULL;
 	else {
 		if (of_property_read_u32_index(np, "samsung,sysreg", 1,
-					       &ufs->shareability_reg_offset)) {
+					       &ufs->iocc_offset)) {
 			dev_warn(dev, "can't get an offset from sysreg. Set to default value\n");
-			ufs->shareability_reg_offset = UFS_SHAREABILITY_OFFSET;
+			ufs->iocc_offset = UFS_SHAREABILITY_OFFSET;
 		}
 	}
 
+	ufs->iocc_mask = ufs->drv_data->iocc_mask;
+	/*
+	 * no 'dma-coherent' property means the descriptors are
+	 * non-cacheable so iocc shareability should be disabled.
+	 */
+	if (of_dma_is_coherent(dev->of_node))
+		ufs->iocc_val = ufs->iocc_mask;
+	else
+		ufs->iocc_val = 0;
+
 	ufs->pclk_avail_min = PCLK_AVAIL_MIN;
 	ufs->pclk_avail_max = PCLK_AVAIL_MAX;
 
@@ -1497,6 +1523,14 @@ out:
 	return ret;
 }
 
+static void exynos_ufs_exit(struct ufs_hba *hba)
+{
+	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
+
+	phy_power_off(ufs->phy);
+	phy_exit(ufs->phy);
+}
+
 static int exynos_ufs_host_reset(struct ufs_hba *hba)
 {
 	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
@@ -1667,6 +1701,12 @@ static void exynos_ufs_hibern8_notify(struct ufs_hba *hba,
 	}
 }
 
+static int gs101_ufs_suspend(struct exynos_ufs *ufs)
+{
+	hci_writel(ufs, 0 << 0, HCI_GPIO_OUT);
+	return 0;
+}
+
 static int exynos_ufs_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op,
 	enum ufs_notify_change_status status)
 {
@@ -1675,6 +1715,9 @@ static int exynos_ufs_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op,
 	if (status == PRE_CHANGE)
 		return 0;
 
+	if (ufs->drv_data->suspend)
+		ufs->drv_data->suspend(ufs);
+
 	if (!ufshcd_is_link_active(hba))
 		phy_power_off(ufs->phy);
 
@@ -1952,6 +1995,7 @@ static int gs101_ufs_pre_pwr_change(struct exynos_ufs *ufs,
 static const struct ufs_hba_variant_ops ufs_hba_exynos_ops = {
 	.name				= "exynos_ufs",
 	.init				= exynos_ufs_init,
+	.exit				= exynos_ufs_exit,
 	.hce_enable_notify		= exynos_ufs_hce_enable_notify,
 	.link_startup_notify		= exynos_ufs_link_startup_notify,
 	.pwr_change_notify		= exynos_ufs_pwr_change_notify,
@@ -1990,13 +2034,7 @@ static int exynos_ufs_probe(struct platform_device *pdev)
 
 static void exynos_ufs_remove(struct platform_device *pdev)
 {
-	struct ufs_hba *hba =  platform_get_drvdata(pdev);
-	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
-
 	ufshcd_pltfrm_remove(pdev);
-
-	phy_power_off(ufs->phy);
-	phy_exit(ufs->phy);
 }
 
 static struct exynos_ufs_uic_attr exynos7_uic_attr = {
@@ -2035,6 +2073,7 @@ static const struct exynos_ufs_drv_data exynosauto_ufs_drvs = {
 	.opts			= EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL |
 				  EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR |
 				  EXYNOS_UFS_OPT_BROKEN_RX_SEL_IDX,
+	.iocc_mask		= UFS_EXYNOSAUTO_SHARABLE,
 	.drv_init		= exynosauto_ufs_drv_init,
 	.post_hce_enable	= exynosauto_ufs_post_hce_enable,
 	.pre_link		= exynosauto_ufs_pre_link,
@@ -2136,10 +2175,12 @@ static const struct exynos_ufs_drv_data gs101_ufs_drvs = {
 	.opts			= EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR |
 				  EXYNOS_UFS_OPT_UFSPR_SECURE |
 				  EXYNOS_UFS_OPT_TIMER_TICK_SELECT,
+	.iocc_mask		= UFS_GS101_SHARABLE,
 	.drv_init		= gs101_ufs_drv_init,
 	.pre_link		= gs101_ufs_pre_link,
 	.post_link		= gs101_ufs_post_link,
 	.pre_pwr_change		= gs101_ufs_pre_pwr_change,
+	.suspend		= gs101_ufs_suspend,
 };
 
 static const struct of_device_id exynos_ufs_of_match[] = {
diff --git a/drivers/ufs/host/ufs-exynos.h b/drivers/ufs/host/ufs-exynos.h
index aac517276189..abe7e472759e 100644
--- a/drivers/ufs/host/ufs-exynos.h
+++ b/drivers/ufs/host/ufs-exynos.h
@@ -181,6 +181,7 @@ struct exynos_ufs_drv_data {
 	struct exynos_ufs_uic_attr *uic_attr;
 	unsigned int quirks;
 	unsigned int opts;
+	u32 iocc_mask;
 	/* SoC's specific operations */
 	int (*drv_init)(struct exynos_ufs *ufs);
 	int (*pre_link)(struct exynos_ufs *ufs);
@@ -191,6 +192,7 @@ struct exynos_ufs_drv_data {
 			       const struct ufs_pa_layer_attr *pwr);
 	int (*pre_hce_enable)(struct exynos_ufs *ufs);
 	int (*post_hce_enable)(struct exynos_ufs *ufs);
+	int (*suspend)(struct exynos_ufs *ufs);
 };
 
 struct ufs_phy_time_cfg {
@@ -230,7 +232,9 @@ struct exynos_ufs {
 	ktime_t entry_hibern8_t;
 	const struct exynos_ufs_drv_data *drv_data;
 	struct regmap *sysreg;
-	u32 shareability_reg_offset;
+	u32 iocc_offset;
+	u32 iocc_mask;
+	u32 iocc_val;
 
 	u32 opts;
 #define EXYNOS_UFS_OPT_HAS_APB_CLK_CTRL		BIT(0)
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 1b37449fbffc..c0761ccc1381 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -33,6 +33,10 @@
 	((((c) >> 16) & MCQ_QCFGPTR_MASK) * MCQ_QCFGPTR_UNIT)
 #define MCQ_QCFG_SIZE	0x40
 
+/* De-emphasis for gear-5 */
+#define DEEMPHASIS_3_5_dB	0x04
+#define NO_DEEMPHASIS		0x0
+
 enum {
 	TSTBUS_UAWM,
 	TSTBUS_UARM,
@@ -795,6 +799,23 @@ static int ufs_qcom_icc_update_bw(struct ufs_qcom_host *host)
 	return ufs_qcom_icc_set_bw(host, bw_table.mem_bw, bw_table.cfg_bw);
 }
 
+static void ufs_qcom_set_tx_hs_equalizer(struct ufs_hba *hba, u32 gear, u32 tx_lanes)
+{
+	u32 equalizer_val;
+	int ret, i;
+
+	/* Determine the equalizer value based on the gear */
+	equalizer_val = (gear == 5) ? DEEMPHASIS_3_5_dB : NO_DEEMPHASIS;
+
+	for (i = 0; i < tx_lanes; i++) {
+		ret = ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(TX_HS_EQUALIZER, i),
+				     equalizer_val);
+		if (ret)
+			dev_err(hba->dev, "%s: failed equalizer lane %d\n",
+				__func__, i);
+	}
+}
+
 static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba,
 				enum ufs_notify_change_status status,
 				const struct ufs_pa_layer_attr *dev_max_params,
@@ -846,6 +867,11 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba,
 						dev_req_params->gear_tx,
 						PA_INITIAL_ADAPT);
 		}
+
+		if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING)
+			ufs_qcom_set_tx_hs_equalizer(hba,
+					dev_req_params->gear_tx, dev_req_params->lane_tx);
+
 		break;
 	case POST_CHANGE:
 		if (ufs_qcom_cfg_timers(hba, false)) {
@@ -893,6 +919,16 @@ static int ufs_qcom_quirk_host_pa_saveconfigtime(struct ufs_hba *hba)
 			    (pa_vs_config_reg1 | (1 << 12)));
 }
 
+static void ufs_qcom_override_pa_tx_hsg1_sync_len(struct ufs_hba *hba)
+{
+	int err;
+
+	err = ufshcd_dme_peer_set(hba, UIC_ARG_MIB(PA_TX_HSG1_SYNC_LENGTH),
+				  PA_TX_HSG1_SYNC_LENGTH_VAL);
+	if (err)
+		dev_err(hba->dev, "Failed (%d) set PA_TX_HSG1_SYNC_LENGTH\n", err);
+}
+
 static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
 {
 	int err = 0;
@@ -900,6 +936,9 @@ static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
 	if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME)
 		err = ufs_qcom_quirk_host_pa_saveconfigtime(hba);
 
+	if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH)
+		ufs_qcom_override_pa_tx_hsg1_sync_len(hba);
+
 	return err;
 }
 
@@ -914,6 +953,10 @@ static struct ufs_dev_quirk ufs_qcom_dev_fixups[] = {
 	{ .wmanufacturerid = UFS_VENDOR_WDC,
 	  .model = UFS_ANY_MODEL,
 	  .quirk = UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE },
+	{ .wmanufacturerid = UFS_VENDOR_SAMSUNG,
+	  .model = UFS_ANY_MODEL,
+	  .quirk = UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH |
+		   UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING },
 	{}
 };
 
diff --git a/drivers/ufs/host/ufs-qcom.h b/drivers/ufs/host/ufs-qcom.h
index d0e6ec9128e7..05d4cb569c50 100644
--- a/drivers/ufs/host/ufs-qcom.h
+++ b/drivers/ufs/host/ufs-qcom.h
@@ -122,8 +122,11 @@ enum {
 				 TMRLUT_HW_CGC_EN | OCSC_HW_CGC_EN)
 
 /* QUniPro Vendor specific attributes */
+#define PA_TX_HSG1_SYNC_LENGTH	0x1552
 #define PA_VS_CONFIG_REG1	0x9000
 #define DME_VS_CORE_CLK_CTRL	0xD002
+#define TX_HS_EQUALIZER		0x0037
+
 /* bit and mask definitions for DME_VS_CORE_CLK_CTRL attribute */
 #define CLK_1US_CYCLES_MASK_V4				GENMASK(27, 16)
 #define CLK_1US_CYCLES_MASK				GENMASK(7, 0)
@@ -141,6 +144,21 @@ enum {
 #define UNIPRO_CORE_CLK_FREQ_201_5_MHZ         202
 #define UNIPRO_CORE_CLK_FREQ_403_MHZ           403
 
+/* TX_HSG1_SYNC_LENGTH attr value */
+#define PA_TX_HSG1_SYNC_LENGTH_VAL	0x4A
+
+/*
+ * Some ufs device vendors need a different TSync length.
+ * Enable this quirk to give an additional TX_HS_SYNC_LENGTH.
+ */
+#define UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH		BIT(16)
+
+/*
+ * Some ufs device vendors need a different Deemphasis setting.
+ * Enable this quirk to tune TX Deemphasis parameters.
+ */
+#define UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING	BIT(17)
+
 /* ICE allocator type to share AES engines among TX stream and RX stream */
 #define ICE_ALLOCATOR_TYPE 2
 
diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index 1b19b5647495..69c1df0f4ca5 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -131,15 +131,12 @@ static void hv_uio_rescind(struct vmbus_channel *channel)
 	vmbus_device_unregister(channel->device_obj);
 }
 
-/* Sysfs API to allow mmap of the ring buffers
+/* Function used for mmap of ring buffer sysfs interface.
  * The ring buffer is allocated as contiguous memory by vmbus_open
  */
-static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
-			    const struct bin_attribute *attr,
-			    struct vm_area_struct *vma)
+static int
+hv_uio_ring_mmap(struct vmbus_channel *channel, struct vm_area_struct *vma)
 {
-	struct vmbus_channel *channel
-		= container_of(kobj, struct vmbus_channel, kobj);
 	void *ring_buffer = page_address(channel->ringbuffer_page);
 
 	if (channel->state != CHANNEL_OPENED_STATE)
@@ -149,15 +146,6 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
 			       channel->ringbuffer_pagecount << PAGE_SHIFT);
 }
 
-static const struct bin_attribute ring_buffer_bin_attr = {
-	.attr = {
-		.name = "ring",
-		.mode = 0600,
-	},
-	.size = 2 * SZ_2M,
-	.mmap = hv_uio_ring_mmap,
-};
-
 /* Callback from VMBUS subsystem when new channel created. */
 static void
 hv_uio_new_channel(struct vmbus_channel *new_sc)
@@ -178,8 +166,7 @@ hv_uio_new_channel(struct vmbus_channel *new_sc)
 	/* Disable interrupts on sub channel */
 	new_sc->inbound.ring_buffer->interrupt_mask = 1;
 	set_channel_read_mode(new_sc, HV_CALL_ISR);
-
-	ret = sysfs_create_bin_file(&new_sc->kobj, &ring_buffer_bin_attr);
+	ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap);
 	if (ret) {
 		dev_err(device, "sysfs create ring bin file failed; %d\n", ret);
 		vmbus_close(new_sc);
@@ -350,10 +337,18 @@ hv_uio_probe(struct hv_device *dev,
 		goto fail_close;
 	}
 
-	ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr);
-	if (ret)
-		dev_notice(&dev->device,
-			   "sysfs create ring bin file failed; %d\n", ret);
+	/*
+	 * This internally calls sysfs_update_group, which returns a non-zero value if it executes
+	 * before sysfs_create_group. This is expected as the 'ring' will be created later in
+	 * vmbus_device_register() -> vmbus_add_channel_kobj(). Thus, no need to check the return
+	 * value and print warning.
+	 *
+	 * Creating/exposing sysfs in driver probe is not encouraged as it can lead to race
+	 * conditions with userspace. For backward compatibility, "ring" sysfs could not be removed
+	 * or decoupled from uio_hv_generic probe. Userspace programs can make use of inotify
+	 * APIs to make sure that ring is created.
+	 */
+	hv_create_ring_sysfs(channel, hv_uio_ring_mmap);
 
 	hv_set_drvdata(dev, pdata);
 
@@ -375,7 +370,7 @@ hv_uio_remove(struct hv_device *dev)
 	if (!pdata)
 		return;
 
-	sysfs_remove_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr);
+	hv_remove_ring_sysfs(dev->channel);
 	uio_unregister_device(&pdata->info);
 	hv_uio_cleanup(dev, pdata);
 
diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 694aa1457739..d9d8dc05b235 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -1963,6 +1963,7 @@ static irqreturn_t cdns3_device_thread_irq_handler(int irq, void *data)
 	unsigned int bit;
 	unsigned long reg;
 
+	local_bh_disable();
 	spin_lock_irqsave(&priv_dev->lock, flags);
 
 	reg = readl(&priv_dev->regs->usb_ists);
@@ -2004,6 +2005,7 @@ static irqreturn_t cdns3_device_thread_irq_handler(int irq, void *data)
 irqend:
 	writel(~0, &priv_dev->regs->ep_ien);
 	spin_unlock_irqrestore(&priv_dev->lock, flags);
+	local_bh_enable();
 
 	return ret;
 }
diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c
index 87f310841735..4824a10df07e 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.c
+++ b/drivers/usb/cdns3/cdnsp-gadget.c
@@ -139,6 +139,26 @@ static void cdnsp_clear_port_change_bit(struct cdnsp_device *pdev,
 	       (portsc & PORT_CHANGE_BITS), port_regs);
 }
 
+static void cdnsp_set_apb_timeout_value(struct cdnsp_device *pdev)
+{
+	struct cdns *cdns = dev_get_drvdata(pdev->dev);
+	__le32 __iomem *reg;
+	void __iomem *base;
+	u32 offset = 0;
+	u32 val;
+
+	if (!cdns->override_apb_timeout)
+		return;
+
+	base = &pdev->cap_regs->hc_capbase;
+	offset = cdnsp_find_next_ext_cap(base, offset, D_XEC_PRE_REGS_CAP);
+	reg = base + offset + REG_CHICKEN_BITS_3_OFFSET;
+
+	val  = le32_to_cpu(readl(reg));
+	val = CHICKEN_APB_TIMEOUT_SET(val, cdns->override_apb_timeout);
+	writel(cpu_to_le32(val), reg);
+}
+
 static void cdnsp_set_chicken_bits_2(struct cdnsp_device *pdev, u32 bit)
 {
 	__le32 __iomem *reg;
@@ -1773,6 +1793,8 @@ static void cdnsp_get_rev_cap(struct cdnsp_device *pdev)
 	reg += cdnsp_find_next_ext_cap(reg, 0, RTL_REV_CAP);
 	pdev->rev_cap  = reg;
 
+	pdev->rtl_revision = readl(&pdev->rev_cap->rtl_revision);
+
 	dev_info(pdev->dev, "Rev: %08x/%08x, eps: %08x, buff: %08x/%08x\n",
 		 readl(&pdev->rev_cap->ctrl_revision),
 		 readl(&pdev->rev_cap->rtl_revision),
@@ -1798,6 +1820,15 @@ static int cdnsp_gen_setup(struct cdnsp_device *pdev)
 	pdev->hci_version = HC_VERSION(pdev->hcc_params);
 	pdev->hcc_params = readl(&pdev->cap_regs->hcc_params);
 
+	/*
+	 * Override the APB timeout value to give the controller more time for
+	 * enabling UTMI clock and synchronizing APB and UTMI clock domains.
+	 * This fix is platform specific and is required to fixes issue with
+	 * reading incorrect value from PORTSC register after resuming
+	 * from L1 state.
+	 */
+	cdnsp_set_apb_timeout_value(pdev);
+
 	cdnsp_get_rev_cap(pdev);
 
 	/* Make sure the Device Controller is halted. */
diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h
index 84887dfea763..12534be52f39 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.h
+++ b/drivers/usb/cdns3/cdnsp-gadget.h
@@ -520,6 +520,9 @@ struct cdnsp_rev_cap {
 #define REG_CHICKEN_BITS_2_OFFSET	0x48
 #define CHICKEN_XDMA_2_TP_CACHE_DIS	BIT(28)
 
+#define REG_CHICKEN_BITS_3_OFFSET       0x4C
+#define CHICKEN_APB_TIMEOUT_SET(p, val) (((p) & ~GENMASK(21, 0)) | (val))
+
 /* XBUF Extended Capability ID. */
 #define XBUF_CAP_ID			0xCB
 #define XBUF_RX_TAG_MASK_0_OFFSET	0x1C
@@ -1357,6 +1360,7 @@ struct cdnsp_port {
  * @rev_cap: Controller Capabilities Registers.
  * @hcs_params1: Cached register copies of read-only HCSPARAMS1
  * @hcc_params: Cached register copies of read-only HCCPARAMS1
+ * @rtl_revision: Cached controller rtl revision.
  * @setup: Temporary buffer for setup packet.
  * @ep0_preq: Internal allocated request used during enumeration.
  * @ep0_stage: ep0 stage during enumeration process.
@@ -1411,6 +1415,8 @@ struct cdnsp_device {
 	__u32 hcs_params1;
 	__u32 hcs_params3;
 	__u32 hcc_params;
+	#define RTL_REVISION_NEW_LPM 0x2700
+	__u32 rtl_revision;
 	/* Lock used in interrupt thread context. */
 	spinlock_t lock;
 	struct usb_ctrlrequest setup;
diff --git a/drivers/usb/cdns3/cdnsp-pci.c b/drivers/usb/cdns3/cdnsp-pci.c
index a51144504ff3..8c361b8394e9 100644
--- a/drivers/usb/cdns3/cdnsp-pci.c
+++ b/drivers/usb/cdns3/cdnsp-pci.c
@@ -28,6 +28,8 @@
 #define PCI_DRIVER_NAME		"cdns-pci-usbssp"
 #define PLAT_DRIVER_NAME	"cdns-usbssp"
 
+#define CHICKEN_APB_TIMEOUT_VALUE       0x1C20
+
 static struct pci_dev *cdnsp_get_second_fun(struct pci_dev *pdev)
 {
 	/*
@@ -139,6 +141,14 @@ static int cdnsp_pci_probe(struct pci_dev *pdev,
 		cdnsp->otg_irq = pdev->irq;
 	}
 
+	/*
+	 * Cadence PCI based platform require some longer timeout for APB
+	 * to fixes domain clock synchronization issue after resuming
+	 * controller from L1 state.
+	 */
+	cdnsp->override_apb_timeout = CHICKEN_APB_TIMEOUT_VALUE;
+	pci_set_drvdata(pdev, cdnsp);
+
 	if (pci_is_enabled(func)) {
 		cdnsp->dev = dev;
 		cdnsp->gadget_init = cdnsp_gadget_init;
@@ -148,8 +158,6 @@ static int cdnsp_pci_probe(struct pci_dev *pdev,
 			goto free_cdnsp;
 	}
 
-	pci_set_drvdata(pdev, cdnsp);
-
 	device_wakeup_enable(&pdev->dev);
 	if (pci_dev_run_wake(pdev))
 		pm_runtime_put_noidle(&pdev->dev);
diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
index 46852529499d..fd06cb85c4ea 100644
--- a/drivers/usb/cdns3/cdnsp-ring.c
+++ b/drivers/usb/cdns3/cdnsp-ring.c
@@ -308,7 +308,8 @@ static bool cdnsp_ring_ep_doorbell(struct cdnsp_device *pdev,
 
 	writel(db_value, reg_addr);
 
-	cdnsp_force_l0_go(pdev);
+	if (pdev->rtl_revision < RTL_REVISION_NEW_LPM)
+		cdnsp_force_l0_go(pdev);
 
 	/* Doorbell was set. */
 	return true;
diff --git a/drivers/usb/cdns3/core.h b/drivers/usb/cdns3/core.h
index 921cccf1ca9d..801be9e61340 100644
--- a/drivers/usb/cdns3/core.h
+++ b/drivers/usb/cdns3/core.h
@@ -79,6 +79,8 @@ struct cdns3_platform_data {
  * @pdata: platform data from glue layer
  * @lock: spinlock structure
  * @xhci_plat_data: xhci private data structure pointer
+ * @override_apb_timeout: hold value of APB timeout. For value 0 the default
+ *                        value in CHICKEN_BITS_3 will be preserved.
  * @gadget_init: pointer to gadget initialization function
  */
 struct cdns {
@@ -117,6 +119,7 @@ struct cdns {
 	struct cdns3_platform_data	*pdata;
 	spinlock_t			lock;
 	struct xhci_plat_priv		*xhci_plat_data;
+	u32                             override_apb_timeout;
 
 	int (*gadget_init)(struct cdns *cdns);
 };
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 1a7fc638213e..4f8bfd242b59 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -336,6 +336,13 @@ static int ci_hdrc_imx_notify_event(struct ci_hdrc *ci, unsigned int event)
 	return ret;
 }
 
+static void ci_hdrc_imx_disable_regulator(void *arg)
+{
+	struct ci_hdrc_imx_data *data = arg;
+
+	regulator_disable(data->hsic_pad_regulator);
+}
+
 static int ci_hdrc_imx_probe(struct platform_device *pdev)
 {
 	struct ci_hdrc_imx_data *data;
@@ -394,6 +401,13 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 					"Failed to enable HSIC pad regulator\n");
 				goto err_put;
 			}
+			ret = devm_add_action_or_reset(dev,
+					ci_hdrc_imx_disable_regulator, data);
+			if (ret) {
+				dev_err(dev,
+					"Failed to add regulator devm action\n");
+				goto err_put;
+			}
 		}
 	}
 
@@ -432,11 +446,11 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 
 	ret = imx_get_clks(dev);
 	if (ret)
-		goto disable_hsic_regulator;
+		goto qos_remove_request;
 
 	ret = imx_prepare_enable_clks(dev);
 	if (ret)
-		goto disable_hsic_regulator;
+		goto qos_remove_request;
 
 	ret = clk_prepare_enable(data->clk_wakeup);
 	if (ret)
@@ -470,7 +484,11 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	    of_usb_get_phy_mode(np) == USBPHY_INTERFACE_MODE_ULPI) {
 		pdata.flags |= CI_HDRC_OVERRIDE_PHY_CONTROL;
 		data->override_phy_control = true;
-		usb_phy_init(pdata.usb_phy);
+		ret = usb_phy_init(pdata.usb_phy);
+		if (ret) {
+			dev_err(dev, "Failed to init phy\n");
+			goto err_clk;
+		}
 	}
 
 	if (pdata.flags & CI_HDRC_SUPPORTS_RUNTIME_PM)
@@ -479,7 +497,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	ret = imx_usbmisc_init(data->usbmisc_data);
 	if (ret) {
 		dev_err(dev, "usbmisc init failed, ret=%d\n", ret);
-		goto err_clk;
+		goto phy_shutdown;
 	}
 
 	data->ci_pdev = ci_hdrc_add_device(dev,
@@ -488,7 +506,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	if (IS_ERR(data->ci_pdev)) {
 		ret = PTR_ERR(data->ci_pdev);
 		dev_err_probe(dev, ret, "ci_hdrc_add_device failed\n");
-		goto err_clk;
+		goto phy_shutdown;
 	}
 
 	if (data->usbmisc_data) {
@@ -522,19 +540,20 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 
 disable_device:
 	ci_hdrc_remove_device(data->ci_pdev);
+phy_shutdown:
+	if (data->override_phy_control)
+		usb_phy_shutdown(data->phy);
 err_clk:
 	clk_disable_unprepare(data->clk_wakeup);
 err_wakeup_clk:
 	imx_disable_unprepare_clks(dev);
-disable_hsic_regulator:
-	if (data->hsic_pad_regulator)
-		/* don't overwrite original ret (cf. EPROBE_DEFER) */
-		regulator_disable(data->hsic_pad_regulator);
+qos_remove_request:
 	if (pdata.flags & CI_HDRC_PMQOS)
 		cpu_latency_qos_remove_request(&data->pm_qos_req);
 	data->ci_pdev = NULL;
 err_put:
-	put_device(data->usbmisc_data->dev);
+	if (data->usbmisc_data)
+		put_device(data->usbmisc_data->dev);
 	return ret;
 }
 
@@ -556,10 +575,9 @@ static void ci_hdrc_imx_remove(struct platform_device *pdev)
 		clk_disable_unprepare(data->clk_wakeup);
 		if (data->plat_data->flags & CI_HDRC_PMQOS)
 			cpu_latency_qos_remove_request(&data->pm_qos_req);
-		if (data->hsic_pad_regulator)
-			regulator_disable(data->hsic_pad_regulator);
 	}
-	put_device(data->usbmisc_data->dev);
+	if (data->usbmisc_data)
+		put_device(data->usbmisc_data->dev);
 }
 
 static void ci_hdrc_imx_shutdown(struct platform_device *pdev)
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 86ee39db013f..16e7fa4d488d 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -726,7 +726,7 @@ static int wdm_open(struct inode *inode, struct file *file)
 		rv = -EBUSY;
 		goto out;
 	}
-
+	smp_rmb(); /* ordered against wdm_wwan_port_stop() */
 	rv = usb_autopm_get_interface(desc->intf);
 	if (rv < 0) {
 		dev_err(&desc->intf->dev, "Error autopm - %d\n", rv);
@@ -829,6 +829,7 @@ static struct usb_class_driver wdm_class = {
 static int wdm_wwan_port_start(struct wwan_port *port)
 {
 	struct wdm_device *desc = wwan_port_get_drvdata(port);
+	int rv;
 
 	/* The interface is both exposed via the WWAN framework and as a
 	 * legacy usbmisc chardev. If chardev is already open, just fail
@@ -848,7 +849,15 @@ static int wdm_wwan_port_start(struct wwan_port *port)
 	wwan_port_txon(port);
 
 	/* Start getting events */
-	return usb_submit_urb(desc->validity, GFP_KERNEL);
+	rv = usb_submit_urb(desc->validity, GFP_KERNEL);
+	if (rv < 0) {
+		wwan_port_txoff(port);
+		desc->manage_power(desc->intf, 0);
+		/* this must be last lest we race with chardev open */
+		clear_bit(WDM_WWAN_IN_USE, &desc->flags);
+	}
+
+	return rv;
 }
 
 static void wdm_wwan_port_stop(struct wwan_port *port)
@@ -859,8 +868,10 @@ static void wdm_wwan_port_stop(struct wwan_port *port)
 	poison_urbs(desc);
 	desc->manage_power(desc->intf, 0);
 	clear_bit(WDM_READ, &desc->flags);
-	clear_bit(WDM_WWAN_IN_USE, &desc->flags);
 	unpoison_urbs(desc);
+	smp_wmb(); /* ordered against wdm_open() */
+	/* this must be last lest we open a poisoned device */
+	clear_bit(WDM_WWAN_IN_USE, &desc->flags);
 }
 
 static void wdm_wwan_port_tx_complete(struct urb *urb)
@@ -868,7 +879,7 @@ static void wdm_wwan_port_tx_complete(struct urb *urb)
 	struct sk_buff *skb = urb->context;
 	struct wdm_device *desc = skb_shinfo(skb)->destructor_arg;
 
-	usb_autopm_put_interface(desc->intf);
+	usb_autopm_put_interface_async(desc->intf);
 	wwan_port_txon(desc->wwanp);
 	kfree_skb(skb);
 }
@@ -898,7 +909,7 @@ static int wdm_wwan_port_tx(struct wwan_port *port, struct sk_buff *skb)
 	req->bRequestType = (USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE);
 	req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND;
 	req->wValue = 0;
-	req->wIndex = desc->inum;
+	req->wIndex = desc->inum; /* already converted */
 	req->wLength = cpu_to_le16(skb->len);
 
 	skb_shinfo(skb)->destructor_arg = desc;
diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index 34e46ef308ab..740d2d2b19fb 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -482,6 +482,7 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb)
 	u8 *buffer;
 	u8 tag;
 	int rv;
+	long wait_rv;
 
 	dev_dbg(dev, "Enter ioctl_read_stb iin_ep_present: %d\n",
 		data->iin_ep_present);
@@ -511,16 +512,17 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb)
 	}
 
 	if (data->iin_ep_present) {
-		rv = wait_event_interruptible_timeout(
+		wait_rv = wait_event_interruptible_timeout(
 			data->waitq,
 			atomic_read(&data->iin_data_valid) != 0,
 			file_data->timeout);
-		if (rv < 0) {
-			dev_dbg(dev, "wait interrupted %d\n", rv);
+		if (wait_rv < 0) {
+			dev_dbg(dev, "wait interrupted %ld\n", wait_rv);
+			rv = wait_rv;
 			goto exit;
 		}
 
-		if (rv == 0) {
+		if (wait_rv == 0) {
 			dev_dbg(dev, "wait timed out\n");
 			rv = -ETIMEDOUT;
 			goto exit;
@@ -539,6 +541,8 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb)
 
 	dev_dbg(dev, "stb:0x%02x received %d\n", (unsigned int)*stb, rv);
 
+	rv = 0;
+
  exit:
 	/* bump interrupt bTag */
 	data->iin_bTag += 1;
@@ -602,9 +606,9 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data,
 {
 	struct usbtmc_device_data *data = file_data->data;
 	struct device *dev = &data->intf->dev;
-	int rv;
 	u32 timeout;
 	unsigned long expire;
+	long wait_rv;
 
 	if (!data->iin_ep_present) {
 		dev_dbg(dev, "no interrupt endpoint present\n");
@@ -618,25 +622,24 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data,
 
 	mutex_unlock(&data->io_mutex);
 
-	rv = wait_event_interruptible_timeout(
-			data->waitq,
-			atomic_read(&file_data->srq_asserted) != 0 ||
-			atomic_read(&file_data->closing),
-			expire);
+	wait_rv = wait_event_interruptible_timeout(
+		data->waitq,
+		atomic_read(&file_data->srq_asserted) != 0 ||
+		atomic_read(&file_data->closing),
+		expire);
 
 	mutex_lock(&data->io_mutex);
 
 	/* Note! disconnect or close could be called in the meantime */
 	if (atomic_read(&file_data->closing) || data->zombie)
-		rv = -ENODEV;
+		return -ENODEV;
 
-	if (rv < 0) {
-		/* dev can be invalid now! */
-		pr_debug("%s - wait interrupted %d\n", __func__, rv);
-		return rv;
+	if (wait_rv < 0) {
+		dev_dbg(dev, "%s - wait interrupted %ld\n", __func__, wait_rv);
+		return wait_rv;
 	}
 
-	if (rv == 0) {
+	if (wait_rv == 0) {
 		dev_dbg(dev, "%s - wait timed out\n", __func__);
 		return -ETIMEDOUT;
 	}
@@ -830,6 +833,7 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data,
 	unsigned long expire;
 	int bufcount = 1;
 	int again = 0;
+	long wait_rv;
 
 	/* mutex already locked */
 
@@ -942,19 +946,24 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data,
 		if (!(flags & USBTMC_FLAG_ASYNC)) {
 			dev_dbg(dev, "%s: before wait time %lu\n",
 				__func__, expire);
-			retval = wait_event_interruptible_timeout(
+			wait_rv = wait_event_interruptible_timeout(
 				file_data->wait_bulk_in,
 				usbtmc_do_transfer(file_data),
 				expire);
 
-			dev_dbg(dev, "%s: wait returned %d\n",
-				__func__, retval);
+			dev_dbg(dev, "%s: wait returned %ld\n",
+				__func__, wait_rv);
+
+			if (wait_rv < 0) {
+				retval = wait_rv;
+				goto error;
+			}
 
-			if (retval <= 0) {
-				if (retval == 0)
-					retval = -ETIMEDOUT;
+			if (wait_rv == 0) {
+				retval = -ETIMEDOUT;
 				goto error;
 			}
+
 		}
 
 		urb = usb_get_from_anchor(&file_data->in_anchor);
@@ -1380,7 +1389,10 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
 	if (!buffer)
 		return -ENOMEM;
 
-	mutex_lock(&data->io_mutex);
+	retval = mutex_lock_interruptible(&data->io_mutex);
+	if (retval < 0)
+		goto exit_nolock;
+
 	if (data->zombie) {
 		retval = -ENODEV;
 		goto exit;
@@ -1503,6 +1515,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
 
 exit:
 	mutex_unlock(&data->io_mutex);
+exit_nolock:
 	kfree(buffer);
 	return retval;
 }
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 8efbacc5bc34..36d3df7d040c 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -369,6 +369,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0781, 0x5583), .driver_info = USB_QUIRK_NO_LPM },
 	{ USB_DEVICE(0x0781, 0x5591), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* SanDisk Corp. SanDisk 3.2Gen1 */
+	{ USB_DEVICE(0x0781, 0x55a3), .driver_info = USB_QUIRK_DELAY_INIT },
+
 	/* Realforce 87U Keyboard */
 	{ USB_DEVICE(0x0853, 0x011b), .driver_info = USB_QUIRK_NO_LPM },
 
@@ -383,6 +386,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0904, 0x6103), .driver_info =
 			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
 
+	/* Silicon Motion Flash Drive */
+	{ USB_DEVICE(0x090c, 0x1000), .driver_info = USB_QUIRK_DELAY_INIT },
+
 	/* Sound Devices USBPre2 */
 	{ USB_DEVICE(0x0926, 0x0202), .driver_info =
 			USB_QUIRK_ENDPOINT_IGNORE },
@@ -539,6 +545,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x2040, 0x7200), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
 
+	/* VLI disk */
+	{ USB_DEVICE(0x2109, 0x0711), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Raydium Touchscreen */
 	{ USB_DEVICE(0x2386, 0x3114), .driver_info = USB_QUIRK_NO_LPM },
 
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index aaa39e663f60..27eae4cf223d 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1164,6 +1164,9 @@ struct dwc3_scratchpad_array {
  * @gsbuscfg0_reqinfo: store GSBUSCFG0.DATRDREQINFO, DESRDREQINFO,
  *		       DATWRREQINFO, and DESWRREQINFO value passed from
  *		       glue driver.
+ * @wakeup_pending_funcs: Indicates whether any interface has requested for
+ *			 function wakeup in bitmap format where bit position
+ *			 represents interface_id.
  */
 struct dwc3 {
 	struct work_struct	drd_work;
@@ -1394,6 +1397,7 @@ struct dwc3 {
 	int			num_ep_resized;
 	struct dentry		*debug_root;
 	u32			gsbuscfg0_reqinfo;
+	u32			wakeup_pending_funcs;
 };
 
 #define INCRX_BURST_MODE 0
diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c
index a33a42ba0249..4ca7f6240d07 100644
--- a/drivers/usb/dwc3/dwc3-xilinx.c
+++ b/drivers/usb/dwc3/dwc3-xilinx.c
@@ -207,15 +207,13 @@ static int dwc3_xlnx_init_zynqmp(struct dwc3_xlnx *priv_data)
 
 skip_usb3_phy:
 	/* ulpi reset via gpio-modepin or gpio-framework driver */
-	reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(reset_gpio)) {
 		return dev_err_probe(dev, PTR_ERR(reset_gpio),
 				     "Failed to request reset GPIO\n");
 	}
 
 	if (reset_gpio) {
-		/* Toggle ulpi to reset the phy. */
-		gpiod_set_value_cansleep(reset_gpio, 1);
 		usleep_range(5000, 10000);
 		gpiod_set_value_cansleep(reset_gpio, 0);
 		usleep_range(5000, 10000);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 47e73c4ed62d..321361288935 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -276,8 +276,6 @@ int dwc3_send_gadget_generic_command(struct dwc3 *dwc, unsigned int cmd,
 	return ret;
 }
 
-static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async);
-
 /**
  * dwc3_send_gadget_ep_cmd - issue an endpoint command
  * @dep: the endpoint to which the command is going to be issued
@@ -2359,10 +2357,8 @@ static int dwc3_gadget_get_frame(struct usb_gadget *g)
 	return __dwc3_gadget_get_frame(dwc);
 }
 
-static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
+static int __dwc3_gadget_wakeup(struct dwc3 *dwc)
 {
-	int			retries;
-
 	int			ret;
 	u32			reg;
 
@@ -2390,8 +2386,7 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
 		return -EINVAL;
 	}
 
-	if (async)
-		dwc3_gadget_enable_linksts_evts(dwc, true);
+	dwc3_gadget_enable_linksts_evts(dwc, true);
 
 	ret = dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RECOV);
 	if (ret < 0) {
@@ -2410,27 +2405,8 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
 
 	/*
 	 * Since link status change events are enabled we will receive
-	 * an U0 event when wakeup is successful. So bail out.
+	 * an U0 event when wakeup is successful.
 	 */
-	if (async)
-		return 0;
-
-	/* poll until Link State changes to ON */
-	retries = 20000;
-
-	while (retries--) {
-		reg = dwc3_readl(dwc->regs, DWC3_DSTS);
-
-		/* in HS, means ON */
-		if (DWC3_DSTS_USBLNKST(reg) == DWC3_LINK_STATE_U0)
-			break;
-	}
-
-	if (DWC3_DSTS_USBLNKST(reg) != DWC3_LINK_STATE_U0) {
-		dev_err(dwc->dev, "failed to send remote wakeup\n");
-		return -EINVAL;
-	}
-
 	return 0;
 }
 
@@ -2451,7 +2427,7 @@ static int dwc3_gadget_wakeup(struct usb_gadget *g)
 		spin_unlock_irqrestore(&dwc->lock, flags);
 		return -EINVAL;
 	}
-	ret = __dwc3_gadget_wakeup(dwc, true);
+	ret = __dwc3_gadget_wakeup(dwc);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -2479,14 +2455,10 @@ static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id)
 	 */
 	link_state = dwc3_gadget_get_link_state(dwc);
 	if (link_state == DWC3_LINK_STATE_U3) {
-		ret = __dwc3_gadget_wakeup(dwc, false);
-		if (ret) {
-			spin_unlock_irqrestore(&dwc->lock, flags);
-			return -EINVAL;
-		}
-		dwc3_resume_gadget(dwc);
-		dwc->suspended = false;
-		dwc->link_state = DWC3_LINK_STATE_U0;
+		dwc->wakeup_pending_funcs |= BIT(intf_id);
+		ret = __dwc3_gadget_wakeup(dwc);
+		spin_unlock_irqrestore(&dwc->lock, flags);
+		return ret;
 	}
 
 	ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION,
@@ -4353,6 +4325,8 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
 {
 	enum dwc3_link_state	next = evtinfo & DWC3_LINK_STATE_MASK;
 	unsigned int		pwropt;
+	int			ret;
+	int			intf_id;
 
 	/*
 	 * WORKAROUND: DWC3 < 2.50a have an issue when configured without
@@ -4428,7 +4402,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
 
 	switch (next) {
 	case DWC3_LINK_STATE_U0:
-		if (dwc->gadget->wakeup_armed) {
+		if (dwc->gadget->wakeup_armed || dwc->wakeup_pending_funcs) {
 			dwc3_gadget_enable_linksts_evts(dwc, false);
 			dwc3_resume_gadget(dwc);
 			dwc->suspended = false;
@@ -4451,6 +4425,18 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
 	}
 
 	dwc->link_state = next;
+
+	/* Proceed with func wakeup if any interfaces that has requested */
+	while (dwc->wakeup_pending_funcs && (next == DWC3_LINK_STATE_U0)) {
+		intf_id = ffs(dwc->wakeup_pending_funcs) - 1;
+		ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION,
+						       DWC3_DGCMDPAR_DN_FUNC_WAKE |
+						       DWC3_DGCMDPAR_INTF_SEL(intf_id));
+		if (ret)
+			dev_err(dwc->dev, "Failed to send DN wake for intf %d\n", intf_id);
+
+		dwc->wakeup_pending_funcs &= ~BIT(intf_id);
+	}
 }
 
 static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc,
@@ -4617,6 +4603,12 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt)
 	if (!count)
 		return IRQ_NONE;
 
+	if (count > evt->length) {
+		dev_err_ratelimited(dwc->dev, "invalid count(%u) > evt->length(%u)\n",
+			count, evt->length);
+		return IRQ_NONE;
+	}
+
 	evt->count = count;
 	evt->flags |= DWC3_EVENT_PENDING;
 
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 869ad99afb48..8dbc132a505e 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2011,15 +2011,13 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 
 		if (f->get_status) {
 			status = f->get_status(f);
+
 			if (status < 0)
 				break;
-		} else {
-			/* Set D0 and D1 bits based on func wakeup capability */
-			if (f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP) {
-				status |= USB_INTRF_STAT_FUNC_RW_CAP;
-				if (f->func_wakeup_armed)
-					status |= USB_INTRF_STAT_FUNC_RW;
-			}
+
+			/* if D5 is not set, then device is not wakeup capable */
+			if (!(f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP))
+				status &= ~(USB_INTRF_STAT_FUNC_RW_CAP | USB_INTRF_STAT_FUNC_RW);
 		}
 
 		put_unaligned_le16(status & 0x0000ffff, req->buf);
diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c
index 80841de845b0..027226325039 100644
--- a/drivers/usb/gadget/function/f_ecm.c
+++ b/drivers/usb/gadget/function/f_ecm.c
@@ -892,6 +892,12 @@ static void ecm_resume(struct usb_function *f)
 	gether_resume(&ecm->port);
 }
 
+static int ecm_get_status(struct usb_function *f)
+{
+	return (f->func_wakeup_armed ? USB_INTRF_STAT_FUNC_RW : 0) |
+		USB_INTRF_STAT_FUNC_RW_CAP;
+}
+
 static void ecm_free(struct usb_function *f)
 {
 	struct f_ecm *ecm;
@@ -960,6 +966,7 @@ static struct usb_function *ecm_alloc(struct usb_function_instance *fi)
 	ecm->port.func.disable = ecm_disable;
 	ecm->port.func.free_func = ecm_free;
 	ecm->port.func.suspend = ecm_suspend;
+	ecm->port.func.get_status = ecm_get_status;
 	ecm->port.func.resume = ecm_resume;
 
 	return &ecm->port.func;
diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c
index 12e866fb311d..0a800ba53816 100644
--- a/drivers/usb/gadget/function/f_midi2.c
+++ b/drivers/usb/gadget/function/f_midi2.c
@@ -475,7 +475,7 @@ static void reply_ump_stream_ep_info(struct f_midi2_ep *ep)
 /* reply a UMP EP device info */
 static void reply_ump_stream_ep_device(struct f_midi2_ep *ep)
 {
-	struct snd_ump_stream_msg_devince_info rep = {
+	struct snd_ump_stream_msg_device_info rep = {
 		.type = UMP_MSG_TYPE_STREAM,
 		.status = UMP_STREAM_MSG_STATUS_DEVICE_INFO,
 		.manufacture_id = ep->info.manufacturer,
diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c
index c7fdbc55fb0b..2957316fd3d0 100644
--- a/drivers/usb/gadget/udc/tegra-xudc.c
+++ b/drivers/usb/gadget/udc/tegra-xudc.c
@@ -1749,6 +1749,10 @@ static int __tegra_xudc_ep_disable(struct tegra_xudc_ep *ep)
 		val = xudc_readl(xudc, CTRL);
 		val &= ~CTRL_RUN;
 		xudc_writel(xudc, val, CTRL);
+
+		val = xudc_readl(xudc, ST);
+		if (val & ST_RC)
+			xudc_writel(xudc, ST_RC, ST);
 	}
 
 	dev_info(xudc->dev, "ep %u disabled\n", ep->index);
diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c
index 900ea0d368e0..9f0a6b27e47c 100644
--- a/drivers/usb/host/ohci-pci.c
+++ b/drivers/usb/host/ohci-pci.c
@@ -165,6 +165,25 @@ static int ohci_quirk_amd700(struct usb_hcd *hcd)
 	return 0;
 }
 
+static int ohci_quirk_loongson(struct usb_hcd *hcd)
+{
+	struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
+
+	/*
+	 * Loongson's LS7A OHCI controller (rev 0x02) has a
+	 * flaw. MMIO register with offset 0x60/64 is treated
+	 * as legacy PS2-compatible keyboard/mouse interface.
+	 * Since OHCI only use 4KB BAR resource, LS7A OHCI's
+	 * 32KB BAR is wrapped around (the 2nd 4KB BAR space
+	 * is the same as the 1st 4KB internally). So add 4KB
+	 * offset (0x1000) to the OHCI registers as a quirk.
+	 */
+	if (pdev->revision == 0x2)
+		hcd->regs += SZ_4K;	/* SZ_4K = 0x1000 */
+
+	return 0;
+}
+
 static int ohci_quirk_qemu(struct usb_hcd *hcd)
 {
 	struct ohci_hcd *ohci = hcd_to_ohci(hcd);
@@ -225,6 +244,10 @@ static const struct pci_device_id ohci_pci_quirks[] = {
 		.driver_data = (unsigned long)ohci_quirk_amd700,
 	},
 	{
+		PCI_DEVICE(PCI_VENDOR_ID_LOONGSON, 0x7a24),
+		.driver_data = (unsigned long)ohci_quirk_loongson,
+	},
+	{
 		.vendor		= PCI_VENDOR_ID_APPLE,
 		.device		= 0x003f,
 		.subvendor	= PCI_SUBVENDOR_ID_REDHAT_QUMRANET,
diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c
index a7c934404ebc..62318291f566 100644
--- a/drivers/usb/host/uhci-platform.c
+++ b/drivers/usb/host/uhci-platform.c
@@ -121,7 +121,7 @@ static int uhci_hcd_platform_probe(struct platform_device *pdev)
 	}
 
 	/* Get and enable clock if any specified */
-	uhci->clk = devm_clk_get(&pdev->dev, NULL);
+	uhci->clk = devm_clk_get_optional(&pdev->dev, NULL);
 	if (IS_ERR(uhci->clk)) {
 		ret = PTR_ERR(uhci->clk);
 		goto err_rmr;
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index fd7895b24367..0d4ce5734165 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -823,6 +823,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc)
 {
 	dma_addr_t		deq;
 	union xhci_trb		*evt;
+	enum evtreturn		ret = EVT_DONE;
 	u32			ctrl, portsc;
 	bool			update_erdp = false;
 
@@ -909,6 +910,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc)
 			break;
 		case TRB_TYPE(TRB_TRANSFER):
 			dbc_handle_xfer_event(dbc, evt);
+			ret = EVT_XFER_DONE;
 			break;
 		default:
 			break;
@@ -927,7 +929,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc)
 		lo_hi_writeq(deq, &dbc->regs->erdp);
 	}
 
-	return EVT_DONE;
+	return ret;
 }
 
 static void xhci_dbc_handle_events(struct work_struct *work)
@@ -936,6 +938,7 @@ static void xhci_dbc_handle_events(struct work_struct *work)
 	struct xhci_dbc		*dbc;
 	unsigned long		flags;
 	unsigned int		poll_interval;
+	unsigned long		busypoll_timelimit;
 
 	dbc = container_of(to_delayed_work(work), struct xhci_dbc, event_work);
 	poll_interval = dbc->poll_interval;
@@ -954,11 +957,21 @@ static void xhci_dbc_handle_events(struct work_struct *work)
 			dbc->driver->disconnect(dbc);
 		break;
 	case EVT_DONE:
-		/* set fast poll rate if there are pending data transfers */
+		/*
+		 * Set fast poll rate if there are pending out transfers, or
+		 * a transfer was recently processed
+		 */
+		busypoll_timelimit = dbc->xfer_timestamp +
+			msecs_to_jiffies(DBC_XFER_INACTIVITY_TIMEOUT);
+
 		if (!list_empty(&dbc->eps[BULK_OUT].list_pending) ||
-		    !list_empty(&dbc->eps[BULK_IN].list_pending))
+		    time_is_after_jiffies(busypoll_timelimit))
 			poll_interval = 0;
 		break;
+	case EVT_XFER_DONE:
+		dbc->xfer_timestamp = jiffies;
+		poll_interval = 0;
+		break;
 	default:
 		dev_info(dbc->dev, "stop handling dbc events\n");
 		return;
diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h
index 9dc8f4d8077c..47ac72c2286d 100644
--- a/drivers/usb/host/xhci-dbgcap.h
+++ b/drivers/usb/host/xhci-dbgcap.h
@@ -96,6 +96,7 @@ struct dbc_ep {
 #define DBC_WRITE_BUF_SIZE		8192
 #define DBC_POLL_INTERVAL_DEFAULT	64	/* milliseconds */
 #define DBC_POLL_INTERVAL_MAX		5000	/* milliseconds */
+#define DBC_XFER_INACTIVITY_TIMEOUT	10	/* milliseconds */
 /*
  * Private structure for DbC hardware state:
  */
@@ -142,6 +143,7 @@ struct xhci_dbc {
 	enum dbc_state			state;
 	struct delayed_work		event_work;
 	unsigned int			poll_interval;	/* ms */
+	unsigned long			xfer_timestamp;
 	unsigned			resume_required:1;
 	struct dbc_ep			eps[2];
 
@@ -187,6 +189,7 @@ struct dbc_request {
 enum evtreturn {
 	EVT_ERR	= -1,
 	EVT_DONE,
+	EVT_XFER_DONE,
 	EVT_GSER,
 	EVT_DISC,
 };
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index c0f226584a40..486347776cb2 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -1878,9 +1878,10 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 	int max_ports, port_index;
 	int sret;
 	u32 next_state;
-	u32 temp, portsc;
+	u32 portsc;
 	struct xhci_hub *rhub;
 	struct xhci_port **ports;
+	bool disabled_irq = false;
 
 	rhub = xhci_get_rhub(hcd);
 	ports = rhub->ports;
@@ -1896,17 +1897,20 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 		return -ESHUTDOWN;
 	}
 
-	/* delay the irqs */
-	temp = readl(&xhci->op_regs->command);
-	temp &= ~CMD_EIE;
-	writel(temp, &xhci->op_regs->command);
-
 	/* bus specific resume for ports we suspended at bus_suspend */
-	if (hcd->speed >= HCD_USB3)
+	if (hcd->speed >= HCD_USB3) {
 		next_state = XDEV_U0;
-	else
+	} else {
 		next_state = XDEV_RESUME;
-
+		if (bus_state->bus_suspended) {
+			/*
+			 * prevent port event interrupts from interfering
+			 * with usb2 port resume process
+			 */
+			xhci_disable_interrupter(xhci->interrupters[0]);
+			disabled_irq = true;
+		}
+	}
 	port_index = max_ports;
 	while (port_index--) {
 		portsc = readl(ports[port_index]->addr);
@@ -1974,11 +1978,9 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 	(void) readl(&xhci->op_regs->command);
 
 	bus_state->next_statechange = jiffies + msecs_to_jiffies(5);
-	/* re-enable irqs */
-	temp = readl(&xhci->op_regs->command);
-	temp |= CMD_EIE;
-	writel(temp, &xhci->op_regs->command);
-	temp = readl(&xhci->op_regs->command);
+	/* re-enable interrupter */
+	if (disabled_irq)
+		xhci_enable_interrupter(xhci->interrupters[0]);
 
 	spin_unlock_irqrestore(&xhci->lock, flags);
 	return 0;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 5d64c297721c..423bf3649570 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -561,8 +561,8 @@ void xhci_ring_ep_doorbell(struct xhci_hcd *xhci,
 	 * pointer command pending because the device can choose to start any
 	 * stream once the endpoint is on the HW schedule.
 	 */
-	if (ep_state & (EP_STOP_CMD_PENDING | SET_DEQ_PENDING | EP_HALTED |
-			EP_CLEARING_TT | EP_STALLED))
+	if ((ep_state & EP_STOP_CMD_PENDING) || (ep_state & SET_DEQ_PENDING) ||
+	    (ep_state & EP_HALTED) || (ep_state & EP_CLEARING_TT))
 		return;
 
 	trace_xhci_ring_ep_doorbell(slot_id, DB_VALUE(ep_index, stream_id));
@@ -699,7 +699,7 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci,
 	int new_cycle;
 	dma_addr_t addr;
 	u64 hw_dequeue;
-	bool cycle_found = false;
+	bool hw_dequeue_found = false;
 	bool td_last_trb_found = false;
 	u32 trb_sct = 0;
 	int ret;
@@ -715,25 +715,24 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci,
 	hw_dequeue = xhci_get_hw_deq(xhci, dev, ep_index, stream_id);
 	new_seg = ep_ring->deq_seg;
 	new_deq = ep_ring->dequeue;
-	new_cycle = hw_dequeue & 0x1;
+	new_cycle = le32_to_cpu(td->end_trb->generic.field[3]) & TRB_CYCLE;
 
 	/*
-	 * We want to find the pointer, segment and cycle state of the new trb
-	 * (the one after current TD's end_trb). We know the cycle state at
-	 * hw_dequeue, so walk the ring until both hw_dequeue and end_trb are
-	 * found.
+	 * Walk the ring until both the next TRB and hw_dequeue are found (don't
+	 * move hw_dequeue back if it went forward due to a HW bug). Cycle state
+	 * is loaded from a known good TRB, track later toggles to maintain it.
 	 */
 	do {
-		if (!cycle_found && xhci_trb_virt_to_dma(new_seg, new_deq)
+		if (!hw_dequeue_found && xhci_trb_virt_to_dma(new_seg, new_deq)
 		    == (dma_addr_t)(hw_dequeue & ~0xf)) {
-			cycle_found = true;
+			hw_dequeue_found = true;
 			if (td_last_trb_found)
 				break;
 		}
 		if (new_deq == td->end_trb)
 			td_last_trb_found = true;
 
-		if (cycle_found && trb_is_link(new_deq) &&
+		if (td_last_trb_found && trb_is_link(new_deq) &&
 		    link_trb_toggles_cycle(new_deq))
 			new_cycle ^= 0x1;
 
@@ -745,7 +744,7 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci,
 			return -EINVAL;
 		}
 
-	} while (!cycle_found || !td_last_trb_found);
+	} while (!hw_dequeue_found || !td_last_trb_found);
 
 	/* Don't update the ring cycle state for the producer (us). */
 	addr = xhci_trb_virt_to_dma(new_seg, new_deq);
@@ -2573,9 +2572,6 @@ static void process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 
 		xhci_handle_halted_endpoint(xhci, ep, td, EP_SOFT_RESET);
 		return;
-	case COMP_STALL_ERROR:
-		ep->ep_state |= EP_STALLED;
-		break;
 	default:
 		/* do nothing */
 		break;
@@ -2916,7 +2912,7 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 			if (xhci_spurious_success_tx_event(xhci, ep_ring)) {
 				xhci_dbg(xhci, "Spurious event dma %pad, comp_code %u after %u\n",
 					 &ep_trb_dma, trb_comp_code, ep_ring->old_trb_comp_code);
-				ep_ring->old_trb_comp_code = trb_comp_code;
+				ep_ring->old_trb_comp_code = 0;
 				return 0;
 			}
 
@@ -3780,7 +3776,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		 * enqueue a No Op TRB, this can prevent the Setup and Data Stage
 		 * TRB to be breaked by the Link TRB.
 		 */
-		if (trb_is_link(ep_ring->enqueue + 1)) {
+		if (last_trb_on_seg(ep_ring->enq_seg, ep_ring->enqueue + 1)) {
 			field = TRB_TYPE(TRB_TR_NOOP) | ep_ring->cycle_state;
 			queue_trb(xhci, ep_ring, false, 0, 0,
 					TRB_INTR_TARGET(0), field);
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index b5c362c2051d..0c7af44d4dae 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -1364,6 +1364,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
 	tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion(tegra->padctl,
 								    tegra->otg_usb2_port);
 
+	pm_runtime_get_sync(tegra->dev);
 	if (tegra->host_mode) {
 		/* switch to host mode */
 		if (tegra->otg_usb3_port >= 0) {
@@ -1393,6 +1394,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
 		}
 
 		tegra_xhci_set_port_power(tegra, true, true);
+		pm_runtime_mark_last_busy(tegra->dev);
 
 	} else {
 		if (tegra->otg_usb3_port >= 0)
@@ -1400,6 +1402,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
 
 		tegra_xhci_set_port_power(tegra, true, false);
 	}
+	pm_runtime_put_autosuspend(tegra->dev);
 }
 
 #if IS_ENABLED(CONFIG_PM) || IS_ENABLED(CONFIG_PM_SLEEP)
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 0452b8d65832..90eb491267b5 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -322,7 +322,7 @@ static void xhci_zero_64b_regs(struct xhci_hcd *xhci)
 		xhci_info(xhci, "Fault detected\n");
 }
 
-static int xhci_enable_interrupter(struct xhci_interrupter *ir)
+int xhci_enable_interrupter(struct xhci_interrupter *ir)
 {
 	u32 iman;
 
@@ -335,7 +335,7 @@ static int xhci_enable_interrupter(struct xhci_interrupter *ir)
 	return 0;
 }
 
-static int xhci_disable_interrupter(struct xhci_interrupter *ir)
+int xhci_disable_interrupter(struct xhci_interrupter *ir)
 {
 	u32 iman;
 
@@ -1605,11 +1605,6 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
 		goto free_priv;
 	}
 
-	/* Class driver might not be aware ep halted due to async URB giveback */
-	if (*ep_state & EP_STALLED)
-		dev_dbg(&urb->dev->dev, "URB %p queued before clearing halt\n",
-			urb);
-
 	switch (usb_endpoint_type(&urb->ep->desc)) {
 
 	case USB_ENDPOINT_XFER_CONTROL:
@@ -1770,8 +1765,8 @@ static int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
 		goto done;
 	}
 
-	/* In these cases no commands are pending but the endpoint is stopped */
-	if (ep->ep_state & (EP_CLEARING_TT | EP_STALLED)) {
+	/* In this case no commands are pending but the endpoint is stopped */
+	if (ep->ep_state & EP_CLEARING_TT) {
 		/* and cancelled TDs can be given back right away */
 		xhci_dbg(xhci, "Invalidating TDs instantly on slot %d ep %d in state 0x%x\n",
 				urb->dev->slot_id, ep_index, ep->ep_state);
@@ -3209,11 +3204,8 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 
 	ep = &vdev->eps[ep_index];
 
-	spin_lock_irqsave(&xhci->lock, flags);
-
-	ep->ep_state &= ~EP_STALLED;
-
 	/* Bail out if toggle is already being cleared by a endpoint reset */
+	spin_lock_irqsave(&xhci->lock, flags);
 	if (ep->ep_state & EP_HARD_CLEAR_TOGGLE) {
 		ep->ep_state &= ~EP_HARD_CLEAR_TOGGLE;
 		spin_unlock_irqrestore(&xhci->lock, flags);
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 37860f1e3aba..242ab9fbc8ae 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -664,7 +664,7 @@ struct xhci_virt_ep {
 	unsigned int			err_count;
 	unsigned int			ep_state;
 #define SET_DEQ_PENDING		(1 << 0)
-#define EP_HALTED		(1 << 1)	/* Halted host ep handling */
+#define EP_HALTED		(1 << 1)	/* For stall handling */
 #define EP_STOP_CMD_PENDING	(1 << 2)	/* For URB cancellation */
 /* Transitioning the endpoint to using streams, don't enqueue URBs */
 #define EP_GETTING_STREAMS	(1 << 3)
@@ -675,7 +675,6 @@ struct xhci_virt_ep {
 #define EP_SOFT_CLEAR_TOGGLE	(1 << 7)
 /* usb_hub_clear_tt_buffer is in progress */
 #define EP_CLEARING_TT		(1 << 8)
-#define EP_STALLED		(1 << 9)	/* For stall handling */
 	/* ----  Related to URB cancellation ---- */
 	struct list_head	cancelled_td_list;
 	struct xhci_hcd		*xhci;
@@ -1891,6 +1890,8 @@ int xhci_alloc_tt_info(struct xhci_hcd *xhci,
 		struct usb_tt *tt, gfp_t mem_flags);
 int xhci_set_interrupter_moderation(struct xhci_interrupter *ir,
 				    u32 imod_interval);
+int xhci_enable_interrupter(struct xhci_interrupter *ir);
+int xhci_disable_interrupter(struct xhci_interrupter *ir);
 
 /* xHCI ring, segment, TRB, and TD functions */
 dma_addr_t xhci_trb_virt_to_dma(struct xhci_segment *seg, union xhci_trb *trb);
diff --git a/drivers/usb/misc/onboard_usb_dev.c b/drivers/usb/misc/onboard_usb_dev.c
index 75ac3c6aa92d..f5372dfa241a 100644
--- a/drivers/usb/misc/onboard_usb_dev.c
+++ b/drivers/usb/misc/onboard_usb_dev.c
@@ -569,8 +569,14 @@ static void onboard_dev_usbdev_disconnect(struct usb_device *udev)
 }
 
 static const struct usb_device_id onboard_dev_id_table[] = {
-	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB33{0,1,2}x/CYUSB230x 3.0 HUB */
-	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB33{0,1,2}x/CYUSB230x 2.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6500) }, /* CYUSB330x 3.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6502) }, /* CYUSB330x 2.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6503) }, /* CYUSB33{0,1}x 2.0 HUB, Vendor Mode */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB331x 3.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB331x 2.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6507) }, /* CYUSB332x 2.0 HUB, Vendor Mode */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6508) }, /* CYUSB332x 3.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x650a) }, /* CYUSB332x 2.0 HUB */
 	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6570) }, /* CY7C6563x 2.0 HUB */
 	{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0608) }, /* Genesys Logic GL850G USB 2.0 HUB */
 	{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0610) }, /* Genesys Logic GL852G USB 2.0 HUB */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 9b34e23b7091..6ac7a0a5cf07 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1093,6 +1093,8 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 1) },
 	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 2) },
 	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 3) },
+	/* Abacus Electrics */
+	{ USB_DEVICE(FTDI_VID, ABACUS_OPTICAL_PROBE_PID) },
 	{ }					/* Terminating entry */
 };
 
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 52be47d684ea..9acb6f837327 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -443,6 +443,11 @@
 #define LINX_FUTURE_2_PID   0xF44C	/* Linx future device */
 
 /*
+ * Abacus Electrics
+ */
+#define ABACUS_OPTICAL_PROBE_PID	0xf458 /* ABACUS ELECTRICS Optical Probe */
+
+/*
  * Oceanic product ids
  */
 #define FTDI_OCEANIC_PID	0xF460  /* Oceanic dive instrument */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 5cd26dac2069..27879cc57536 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -611,6 +611,7 @@ static void option_instat_callback(struct urb *urb);
 /* Sierra Wireless products */
 #define SIERRA_VENDOR_ID			0x1199
 #define SIERRA_PRODUCT_EM9191			0x90d3
+#define SIERRA_PRODUCT_EM9291			0x90e3
 
 /* UNISOC (Spreadtrum) products */
 #define UNISOC_VENDOR_ID			0x1782
@@ -2432,6 +2433,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x30) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff),			/* TCL IK512 MBIM */
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index 2c12449ff60c..a0afaf254d12 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -100,6 +100,11 @@ DEVICE(nokia, NOKIA_IDS);
 	{ USB_DEVICE(0x09d7, 0x0100) }	/* NovAtel FlexPack GPS */
 DEVICE_N(novatel_gps, NOVATEL_IDS, 3);
 
+/* OWON electronic test and measurement equipment driver */
+#define OWON_IDS()			\
+	{ USB_DEVICE(0x5345, 0x1234) } /* HDS200 oscilloscopes and others */
+DEVICE(owon, OWON_IDS);
+
 /* Siemens USB/MPI adapter */
 #define SIEMENS_IDS()			\
 	{ USB_DEVICE(0x908, 0x0004) }
@@ -134,6 +139,7 @@ static struct usb_serial_driver * const serial_drivers[] = {
 	&motorola_tetra_device,
 	&nokia_device,
 	&novatel_gps_device,
+	&owon_device,
 	&siemens_mpi_device,
 	&suunto_device,
 	&vivopay_device,
@@ -153,6 +159,7 @@ static const struct usb_device_id id_table[] = {
 	MOTOROLA_TETRA_IDS(),
 	NOKIA_IDS(),
 	NOVATEL_IDS(),
+	OWON_IDS(),
 	SIEMENS_IDS(),
 	SUUNTO_IDS(),
 	VIVOPAY_IDS(),
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 1f8c9b16a0fb..d460d71b4257 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -83,6 +83,13 @@ UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_REPORT_LUNS),
 
+/* Reported-by: Oliver Neukum <oneukum@suse.com> */
+UNUSUAL_DEV(0x125f, 0xa94a, 0x0160, 0x0160,
+		"ADATA",
+		"Portable HDD CH94",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
 /* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */
 UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999,
 		"Initio Corporation",
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 9c76c3d0c6cf..67a533e35150 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -1052,9 +1052,11 @@ struct typec_partner *typec_register_partner(struct typec_port *port,
 		partner->usb_mode = USB_MODE_USB3;
 	}
 
+	mutex_lock(&port->partner_link_lock);
 	ret = device_register(&partner->dev);
 	if (ret) {
 		dev_err(&port->dev, "failed to register partner (%d)\n", ret);
+		mutex_unlock(&port->partner_link_lock);
 		put_device(&partner->dev);
 		return ERR_PTR(ret);
 	}
@@ -1063,6 +1065,7 @@ struct typec_partner *typec_register_partner(struct typec_port *port,
 		typec_partner_link_device(partner, port->usb2_dev);
 	if (port->usb3_dev)
 		typec_partner_link_device(partner, port->usb3_dev);
+	mutex_unlock(&port->partner_link_lock);
 
 	return partner;
 }
@@ -1083,12 +1086,18 @@ void typec_unregister_partner(struct typec_partner *partner)
 
 	port = to_typec_port(partner->dev.parent);
 
-	if (port->usb2_dev)
+	mutex_lock(&port->partner_link_lock);
+	if (port->usb2_dev) {
 		typec_partner_unlink_device(partner, port->usb2_dev);
-	if (port->usb3_dev)
+		port->usb2_dev = NULL;
+	}
+	if (port->usb3_dev) {
 		typec_partner_unlink_device(partner, port->usb3_dev);
+		port->usb3_dev = NULL;
+	}
 
 	device_unregister(&partner->dev);
+	mutex_unlock(&port->partner_link_lock);
 }
 EXPORT_SYMBOL_GPL(typec_unregister_partner);
 
@@ -2041,10 +2050,11 @@ static struct typec_partner *typec_get_partner(struct typec_port *port)
 static void typec_partner_attach(struct typec_connector *con, struct device *dev)
 {
 	struct typec_port *port = container_of(con, struct typec_port, con);
-	struct typec_partner *partner = typec_get_partner(port);
+	struct typec_partner *partner;
 	struct usb_device *udev = to_usb_device(dev);
 	enum usb_mode usb_mode;
 
+	mutex_lock(&port->partner_link_lock);
 	if (udev->speed < USB_SPEED_SUPER) {
 		usb_mode = USB_MODE_USB2;
 		port->usb2_dev = dev;
@@ -2053,18 +2063,22 @@ static void typec_partner_attach(struct typec_connector *con, struct device *dev
 		port->usb3_dev = dev;
 	}
 
+	partner = typec_get_partner(port);
 	if (partner) {
 		typec_partner_set_usb_mode(partner, usb_mode);
 		typec_partner_link_device(partner, dev);
 		put_device(&partner->dev);
 	}
+	mutex_unlock(&port->partner_link_lock);
 }
 
 static void typec_partner_deattach(struct typec_connector *con, struct device *dev)
 {
 	struct typec_port *port = container_of(con, struct typec_port, con);
-	struct typec_partner *partner = typec_get_partner(port);
+	struct typec_partner *partner;
 
+	mutex_lock(&port->partner_link_lock);
+	partner = typec_get_partner(port);
 	if (partner) {
 		typec_partner_unlink_device(partner, dev);
 		put_device(&partner->dev);
@@ -2074,6 +2088,7 @@ static void typec_partner_deattach(struct typec_connector *con, struct device *d
 		port->usb2_dev = NULL;
 	else if (port->usb3_dev == dev)
 		port->usb3_dev = NULL;
+	mutex_unlock(&port->partner_link_lock);
 }
 
 /**
@@ -2614,6 +2629,7 @@ struct typec_port *typec_register_port(struct device *parent,
 
 	ida_init(&port->mode_ids);
 	mutex_init(&port->port_type_lock);
+	mutex_init(&port->partner_link_lock);
 
 	port->id = id;
 	port->ops = cap->ops;
diff --git a/drivers/usb/typec/class.h b/drivers/usb/typec/class.h
index b3076a24ad2e..db2fe96c48ff 100644
--- a/drivers/usb/typec/class.h
+++ b/drivers/usb/typec/class.h
@@ -59,6 +59,7 @@ struct typec_port {
 	enum typec_port_type		port_type;
 	enum usb_mode			usb_mode;
 	struct mutex			port_type_lock;
+	struct mutex			partner_link_lock;
 
 	enum typec_orientation		orientation;
 	struct typec_switch		*sw;
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index a99db4e025cd..8adf6f954633 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -5965,7 +5965,7 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1,
 	case SNK_TRY_WAIT_DEBOUNCE:
 		if (!tcpm_port_is_sink(port)) {
 			port->max_wait = 0;
-			tcpm_set_state(port, SRC_TRYWAIT, 0);
+			tcpm_set_state(port, SRC_TRYWAIT, PD_T_PD_DEBOUNCE);
 		}
 		break;
 	case SRC_TRY_WAIT:
diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c
index 420af5139c70..8aae80b457d7 100644
--- a/drivers/usb/typec/ucsi/displayport.c
+++ b/drivers/usb/typec/ucsi/displayport.c
@@ -54,7 +54,8 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo)
 	u8 cur = 0;
 	int ret;
 
-	mutex_lock(&dp->con->lock);
+	if (!ucsi_con_mutex_lock(dp->con))
+		return -ENOTCONN;
 
 	if (!dp->override && dp->initialized) {
 		const struct typec_altmode *p = typec_altmode_get_partner(alt);
@@ -100,7 +101,7 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo)
 	schedule_work(&dp->work);
 	ret = 0;
 err_unlock:
-	mutex_unlock(&dp->con->lock);
+	ucsi_con_mutex_unlock(dp->con);
 
 	return ret;
 }
@@ -112,7 +113,8 @@ static int ucsi_displayport_exit(struct typec_altmode *alt)
 	u64 command;
 	int ret = 0;
 
-	mutex_lock(&dp->con->lock);
+	if (!ucsi_con_mutex_lock(dp->con))
+		return -ENOTCONN;
 
 	if (!dp->override) {
 		const struct typec_altmode *p = typec_altmode_get_partner(alt);
@@ -144,7 +146,7 @@ static int ucsi_displayport_exit(struct typec_altmode *alt)
 	schedule_work(&dp->work);
 
 out_unlock:
-	mutex_unlock(&dp->con->lock);
+	ucsi_con_mutex_unlock(dp->con);
 
 	return ret;
 }
@@ -202,20 +204,21 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt,
 	int cmd = PD_VDO_CMD(header);
 	int svdm_version;
 
-	mutex_lock(&dp->con->lock);
+	if (!ucsi_con_mutex_lock(dp->con))
+		return -ENOTCONN;
 
 	if (!dp->override && dp->initialized) {
 		const struct typec_altmode *p = typec_altmode_get_partner(alt);
 
 		dev_warn(&p->dev,
 			 "firmware doesn't support alternate mode overriding\n");
-		mutex_unlock(&dp->con->lock);
+		ucsi_con_mutex_unlock(dp->con);
 		return -EOPNOTSUPP;
 	}
 
 	svdm_version = typec_altmode_get_svdm_version(alt);
 	if (svdm_version < 0) {
-		mutex_unlock(&dp->con->lock);
+		ucsi_con_mutex_unlock(dp->con);
 		return svdm_version;
 	}
 
@@ -259,7 +262,7 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt,
 		break;
 	}
 
-	mutex_unlock(&dp->con->lock);
+	ucsi_con_mutex_unlock(dp->con);
 
 	return 0;
 }
@@ -296,6 +299,8 @@ void ucsi_displayport_remove_partner(struct typec_altmode *alt)
 	if (!dp)
 		return;
 
+	cancel_work_sync(&dp->work);
+
 	dp->data.conf = 0;
 	dp->data.status = 0;
 	dp->initialized = false;
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index e8c7e9dc4930..01ce858a1a2b 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -1923,6 +1923,40 @@ void ucsi_set_drvdata(struct ucsi *ucsi, void *data)
 EXPORT_SYMBOL_GPL(ucsi_set_drvdata);
 
 /**
+ * ucsi_con_mutex_lock - Acquire the connector mutex
+ * @con: The connector interface to lock
+ *
+ * Returns true on success, false if the connector is disconnected
+ */
+bool ucsi_con_mutex_lock(struct ucsi_connector *con)
+{
+	bool mutex_locked = false;
+	bool connected = true;
+
+	while (connected && !mutex_locked) {
+		mutex_locked = mutex_trylock(&con->lock) != 0;
+		connected = UCSI_CONSTAT(con, CONNECTED);
+		if (connected && !mutex_locked)
+			msleep(20);
+	}
+
+	connected = connected && con->partner;
+	if (!connected && mutex_locked)
+		mutex_unlock(&con->lock);
+
+	return connected;
+}
+
+/**
+ * ucsi_con_mutex_unlock - Release the connector mutex
+ * @con: The connector interface to unlock
+ */
+void ucsi_con_mutex_unlock(struct ucsi_connector *con)
+{
+	mutex_unlock(&con->lock);
+}
+
+/**
  * ucsi_create - Allocate UCSI instance
  * @dev: Device interface to the PPM (Platform Policy Manager)
  * @ops: I/O routines
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index 3a2c1762bec1..9c5278a0c5d4 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -94,6 +94,8 @@ int ucsi_register(struct ucsi *ucsi);
 void ucsi_unregister(struct ucsi *ucsi);
 void *ucsi_get_drvdata(struct ucsi *ucsi);
 void ucsi_set_drvdata(struct ucsi *ucsi, void *data);
+bool ucsi_con_mutex_lock(struct ucsi_connector *con);
+void ucsi_con_mutex_unlock(struct ucsi_connector *con);
 
 void ucsi_connector_change(struct ucsi *ucsi, u8 num);
 
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 14437396d721..8f02f236b5b4 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -1815,7 +1815,7 @@ int vfio_config_init(struct vfio_pci_core_device *vdev)
 	}
 
 	if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx ||
-	    vdev->pdev->irq == IRQ_NOTCONNECTED)
+	    !vdev->pdev->irq || vdev->pdev->irq == IRQ_NOTCONNECTED)
 		vconfig[PCI_INTERRUPT_PIN] = 0;
 
 	ret = vfio_cap_init(vdev);
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 35f9046af315..6328c3a05bcd 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1646,14 +1646,14 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf,
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct vfio_pci_core_device *vdev = vma->vm_private_data;
-	unsigned long pfn, pgoff = vmf->pgoff - vma->vm_pgoff;
+	unsigned long addr = vmf->address & ~((PAGE_SIZE << order) - 1);
+	unsigned long pgoff = (addr - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long pfn = vma_to_pfn(vma) + pgoff;
 	vm_fault_t ret = VM_FAULT_SIGBUS;
 
-	pfn = vma_to_pfn(vma) + pgoff;
-
-	if (order && (pfn & ((1 << order) - 1) ||
-		      vmf->address & ((PAGE_SIZE << order) - 1) ||
-		      vmf->address + (PAGE_SIZE << order) > vma->vm_end)) {
+	if (order && (addr < vma->vm_start ||
+		      addr + (PAGE_SIZE << order) > vma->vm_end ||
+		      pfn & ((1 << order) - 1))) {
 		ret = VM_FAULT_FALLBACK;
 		goto out;
 	}
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index b9b9e9d40951..7cbfc7d718b3 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -755,10 +755,10 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 	int err;
 	int sent_pkts = 0;
 	bool sock_can_batch = (sock->sk->sk_sndbuf == INT_MAX);
+	bool busyloop_intr;
 
 	do {
-		bool busyloop_intr = false;
-
+		busyloop_intr = false;
 		if (nvq->done_idx == VHOST_NET_BATCH)
 			vhost_tx_batch(net, nvq, sock, &msg);
 
@@ -769,13 +769,10 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 			break;
 		/* Nothing new?  Wait for eventfd to tell us they refilled. */
 		if (head == vq->num) {
-			if (unlikely(busyloop_intr)) {
-				vhost_poll_queue(&vq->poll);
-			} else if (unlikely(vhost_enable_notify(&net->dev,
-								vq))) {
-				vhost_disable_notify(&net->dev, vq);
-				continue;
-			}
+			/* Kicks are disabled at this point, break loop and
+			 * process any remaining batched packets. Queue will
+			 * be re-enabled afterwards.
+			 */
 			break;
 		}
 
@@ -825,7 +822,22 @@ done:
 		++nvq->done_idx;
 	} while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len)));
 
+	/* Kicks are still disabled, dispatch any remaining batched msgs. */
 	vhost_tx_batch(net, nvq, sock, &msg);
+
+	if (unlikely(busyloop_intr))
+		/* If interrupted while doing busy polling, requeue the
+		 * handler to be fair handle_rx as well as other tasks
+		 * waiting on cpu.
+		 */
+		vhost_poll_queue(&vq->poll);
+	else
+		/* All of our work has been completed; however, before
+		 * leaving the TX handler, do one last check for work,
+		 * and requeue handler if necessary. If there is no work,
+		 * queue will be reenabled.
+		 */
+		vhost_net_busy_poll_try_queue(net, vq);
 }
 
 static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index f6f5a7ac7894..26bcf3a7f70c 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -627,6 +627,9 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 	int ret;
 
 	llnode = llist_del_all(&svq->completion_list);
+
+	mutex_lock(&svq->vq.mutex);
+
 	llist_for_each_entry_safe(cmd, t, llnode, tvc_completion_list) {
 		se_cmd = &cmd->tvc_se_cmd;
 
@@ -660,6 +663,8 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 		vhost_scsi_release_cmd_res(se_cmd);
 	}
 
+	mutex_unlock(&svq->vq.mutex);
+
 	if (signal)
 		vhost_signal(&svq->vs->dev, &svq->vq);
 }
@@ -994,39 +999,66 @@ static void vhost_scsi_target_queue_cmd(struct vhost_scsi_nexus *nexus,
 
 static void
 vhost_scsi_send_status(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
-		       int head, unsigned int out, u8 status)
+		       struct vhost_scsi_ctx *vc, u8 status)
 {
-	struct virtio_scsi_cmd_resp __user *resp;
 	struct virtio_scsi_cmd_resp rsp;
+	struct iov_iter iov_iter;
 	int ret;
 
 	memset(&rsp, 0, sizeof(rsp));
 	rsp.status = status;
-	resp = vq->iov[out].iov_base;
-	ret = __copy_to_user(resp, &rsp, sizeof(rsp));
-	if (!ret)
-		vhost_add_used_and_signal(&vs->dev, vq, head, 0);
+
+	iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in,
+		      sizeof(rsp));
+
+	ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
+
+	if (likely(ret == sizeof(rsp)))
+		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
 	else
 		pr_err("Faulted on virtio_scsi_cmd_resp\n");
 }
 
+#define TYPE_IO_CMD    0
+#define TYPE_CTRL_TMF  1
+#define TYPE_CTRL_AN   2
+
 static void
 vhost_scsi_send_bad_target(struct vhost_scsi *vs,
 			   struct vhost_virtqueue *vq,
-			   int head, unsigned out)
+			   struct vhost_scsi_ctx *vc, int type)
 {
-	struct virtio_scsi_cmd_resp __user *resp;
-	struct virtio_scsi_cmd_resp rsp;
+	union {
+		struct virtio_scsi_cmd_resp cmd;
+		struct virtio_scsi_ctrl_tmf_resp tmf;
+		struct virtio_scsi_ctrl_an_resp an;
+	} rsp;
+	struct iov_iter iov_iter;
+	size_t rsp_size;
 	int ret;
 
 	memset(&rsp, 0, sizeof(rsp));
-	rsp.response = VIRTIO_SCSI_S_BAD_TARGET;
-	resp = vq->iov[out].iov_base;
-	ret = __copy_to_user(resp, &rsp, sizeof(rsp));
-	if (!ret)
-		vhost_add_used_and_signal(&vs->dev, vq, head, 0);
+
+	if (type == TYPE_IO_CMD) {
+		rsp_size = sizeof(struct virtio_scsi_cmd_resp);
+		rsp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET;
+	} else if (type == TYPE_CTRL_TMF) {
+		rsp_size = sizeof(struct virtio_scsi_ctrl_tmf_resp);
+		rsp.tmf.response = VIRTIO_SCSI_S_BAD_TARGET;
+	} else {
+		rsp_size = sizeof(struct virtio_scsi_ctrl_an_resp);
+		rsp.an.response = VIRTIO_SCSI_S_BAD_TARGET;
+	}
+
+	iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in,
+		      rsp_size);
+
+	ret = copy_to_iter(&rsp, rsp_size, &iov_iter);
+
+	if (likely(ret == rsp_size))
+		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
 	else
-		pr_err("Faulted on virtio_scsi_cmd_resp\n");
+		pr_err("Faulted on virtio scsi type=%d\n", type);
 }
 
 static int
@@ -1390,9 +1422,9 @@ err:
 		if (ret == -ENXIO)
 			break;
 		else if (ret == -EIO)
-			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+			vhost_scsi_send_bad_target(vs, vq, &vc, TYPE_IO_CMD);
 		else if (ret == -ENOMEM)
-			vhost_scsi_send_status(vs, vq, vc.head, vc.out,
+			vhost_scsi_send_status(vs, vq, &vc,
 					       SAM_STAT_TASK_SET_FULL);
 	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
 out:
@@ -1432,8 +1464,11 @@ static void vhost_scsi_tmf_resp_work(struct vhost_work *work)
 	else
 		resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED;
 
+	mutex_lock(&tmf->svq->vq.mutex);
 	vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs,
 				 tmf->vq_desc, &tmf->resp_iov, resp_code);
+	mutex_unlock(&tmf->svq->vq.mutex);
+
 	vhost_scsi_release_tmf_res(tmf);
 }
 
@@ -1623,7 +1658,10 @@ err:
 		if (ret == -ENXIO)
 			break;
 		else if (ret == -EIO)
-			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+			vhost_scsi_send_bad_target(vs, vq, &vc,
+						   v_req.type == VIRTIO_SCSI_T_TMF ?
+						   TYPE_CTRL_TMF :
+						   TYPE_CTRL_AN);
 	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
 out:
 	mutex_unlock(&vq->mutex);
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 150753c3b578..95d5d7993e5b 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -407,6 +407,12 @@ static void virtio_dev_shutdown(struct device *_d)
 	if (!drv)
 		return;
 
+	/* If the driver has its own shutdown method, use that. */
+	if (drv->shutdown) {
+		drv->shutdown(dev);
+		return;
+	}
+
 	/*
 	 * Some devices get wedged if you kick them after they are
 	 * reset. Mark all vqs as broken to make sure we don't.
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 5eaade757860..d50fe030d825 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -247,7 +247,7 @@ virtio_pci_admin_cmd_dev_parts_objects_enable(struct virtio_device *virtio_dev)
 	sg_init_one(&data_sg, get_data, sizeof(*get_data));
 	sg_init_one(&result_sg, result, sizeof(*result));
 	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET);
-	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF);
 	cmd.data_sg = &data_sg;
 	cmd.result_sg = &result_sg;
 	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
@@ -305,7 +305,7 @@ static void virtio_pci_admin_cmd_cap_init(struct virtio_device *virtio_dev)
 
 	sg_init_one(&result_sg, data, sizeof(*data));
 	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY);
-	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF);
 	cmd.result_sg = &result_sg;
 
 	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index fdd2d2b07b5a..b784aab66867 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2650,7 +2650,7 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	if (vq->event_triggered)
-		vq->event_triggered = false;
+		data_race(vq->event_triggered = false);
 
 	return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) :
 				 virtqueue_enable_cb_delayed_split(_vq);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 1f65795cf5d7..ef56a2500ed6 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -217,6 +217,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * buffering it.
 	 */
 	if (dma_capable(dev, dev_addr, size, true) &&
+	    !dma_kmalloc_needs_bounce(dev, size, dir) &&
 	    !range_straddles_page_boundary(phys, size) &&
 		!xen_arch_need_swiotlb(dev, phys, dev_addr) &&
 		!is_swiotlb_force_bounce(dev))
diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h
index 13821e7e825e..9ac0427724a3 100644
--- a/drivers/xen/xenbus/xenbus.h
+++ b/drivers/xen/xenbus/xenbus.h
@@ -77,6 +77,7 @@ enum xb_req_state {
 struct xb_req_data {
 	struct list_head list;
 	wait_queue_head_t wq;
+	struct kref kref;
 	struct xsd_sockmsg msg;
 	uint32_t caller_req_id;
 	enum xsd_sockmsg_type type;
@@ -103,6 +104,7 @@ int xb_init_comms(void);
 void xb_deinit_comms(void);
 int xs_watch_msg(struct xs_watch_event *event);
 void xs_request_exit(struct xb_req_data *req);
+void xs_free_req(struct kref *kref);
 
 int xenbus_match(struct device *_dev, const struct device_driver *_drv);
 int xenbus_dev_probe(struct device *_dev);
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
index e5fda0256feb..82df2da1b880 100644
--- a/drivers/xen/xenbus/xenbus_comms.c
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -309,8 +309,8 @@ static int process_msg(void)
 			virt_wmb();
 			req->state = xb_req_state_got_reply;
 			req->cb(req);
-		} else
-			kfree(req);
+		}
+		kref_put(&req->kref, xs_free_req);
 	}
 
 	mutex_unlock(&xs_response_mutex);
@@ -386,14 +386,13 @@ static int process_writes(void)
 	state.req->msg.type = XS_ERROR;
 	state.req->err = err;
 	list_del(&state.req->list);
-	if (state.req->state == xb_req_state_aborted)
-		kfree(state.req);
-	else {
+	if (state.req->state != xb_req_state_aborted) {
 		/* write err, then update state */
 		virt_wmb();
 		state.req->state = xb_req_state_got_reply;
 		wake_up(&state.req->wq);
 	}
+	kref_put(&state.req->kref, xs_free_req);
 
 	mutex_unlock(&xb_write_mutex);
 
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 46f8916597e5..f5c21ba64df5 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -406,7 +406,7 @@ void xenbus_dev_queue_reply(struct xb_req_data *req)
 	mutex_unlock(&u->reply_mutex);
 
 	kfree(req->body);
-	kfree(req);
+	kref_put(&req->kref, xs_free_req);
 
 	kref_put(&u->kref, xenbus_file_free);
 
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 6d32ffb01136..86fe6e779056 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -966,9 +966,15 @@ static int __init xenbus_init(void)
 	if (xen_pv_domain())
 		xen_store_domain_type = XS_PV;
 	if (xen_hvm_domain())
+	{
 		xen_store_domain_type = XS_HVM;
-	if (xen_hvm_domain() && xen_initial_domain())
-		xen_store_domain_type = XS_LOCAL;
+		err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
+		if (err)
+			goto out_error;
+		xen_store_evtchn = (int)v;
+		if (!v && xen_initial_domain())
+			xen_store_domain_type = XS_LOCAL;
+	}
 	if (xen_pv_domain() && !xen_start_info->store_evtchn)
 		xen_store_domain_type = XS_LOCAL;
 	if (xen_pv_domain() && xen_start_info->store_evtchn)
@@ -987,10 +993,6 @@ static int __init xenbus_init(void)
 		xen_store_interface = gfn_to_virt(xen_store_gfn);
 		break;
 	case XS_HVM:
-		err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
-		if (err)
-			goto out_error;
-		xen_store_evtchn = (int)v;
 		err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
 		if (err)
 			goto out_error;
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index d32c726f7a12..dcf9182c8451 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -112,6 +112,12 @@ static void xs_suspend_exit(void)
 	wake_up_all(&xs_state_enter_wq);
 }
 
+void xs_free_req(struct kref *kref)
+{
+	struct xb_req_data *req = container_of(kref, struct xb_req_data, kref);
+	kfree(req);
+}
+
 static uint32_t xs_request_enter(struct xb_req_data *req)
 {
 	uint32_t rq_id;
@@ -237,6 +243,12 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg)
 	req->caller_req_id = req->msg.req_id;
 	req->msg.req_id = xs_request_enter(req);
 
+	/*
+	 * Take 2nd ref.  One for this thread, and the second for the
+	 * xenbus_thread.
+	 */
+	kref_get(&req->kref);
+
 	mutex_lock(&xb_write_mutex);
 	list_add_tail(&req->list, &xb_write_list);
 	notify = list_is_singular(&xb_write_list);
@@ -261,8 +273,8 @@ static void *xs_wait_for_reply(struct xb_req_data *req, struct xsd_sockmsg *msg)
 	if (req->state == xb_req_state_queued ||
 	    req->state == xb_req_state_wait_reply)
 		req->state = xb_req_state_aborted;
-	else
-		kfree(req);
+
+	kref_put(&req->kref, xs_free_req);
 	mutex_unlock(&xb_write_mutex);
 
 	return ret;
@@ -291,6 +303,7 @@ int xenbus_dev_request_and_reply(struct xsd_sockmsg *msg, void *par)
 	req->cb = xenbus_dev_queue_reply;
 	req->par = par;
 	req->user_req = true;
+	kref_init(&req->kref);
 
 	xs_send(req, msg);
 
@@ -319,6 +332,7 @@ static void *xs_talkv(struct xenbus_transaction t,
 	req->num_vecs = num_vecs;
 	req->cb = xs_wake_up;
 	req->user_req = false;
+	kref_init(&req->kref);
 
 	msg.req_id = 0;
 	msg.tx_id = t.id;
diff --git a/fs/Kconfig b/fs/Kconfig
index c718b2e2de0e..5b4847bd2fbb 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -368,6 +368,7 @@ config GRACE_PERIOD
 config LOCKD
 	tristate
 	depends on FILE_LOCKING
+	select CRC32
 	select GRACE_PERIOD
 
 config LOCKD_V4
diff --git a/fs/afs/Kconfig b/fs/afs/Kconfig
index fc8ba9142f2f..682bd8ec2c10 100644
--- a/fs/afs/Kconfig
+++ b/fs/afs/Kconfig
@@ -5,6 +5,7 @@ config AFS_FS
 	select AF_RXRPC
 	select DNS_RESOLVER
 	select NETFS_SUPPORT
+	select CRYPTO_KRB5
 	help
 	  If you say Y here, you will get an experimental Andrew File System
 	  driver. It currently only supports unsecured read-only AFS access.
diff --git a/fs/afs/Makefile b/fs/afs/Makefile
index 5efd7e13b304..b49b8fe682f3 100644
--- a/fs/afs/Makefile
+++ b/fs/afs/Makefile
@@ -8,6 +8,7 @@ kafs-y := \
 	addr_prefs.o \
 	callback.o \
 	cell.o \
+	cm_security.o \
 	cmservice.o \
 	dir.o \
 	dir_edit.o \
diff --git a/fs/afs/cm_security.c b/fs/afs/cm_security.c
new file mode 100644
index 000000000000..edcbd249d202
--- /dev/null
+++ b/fs/afs/cm_security.c
@@ -0,0 +1,340 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Cache manager security.
+ *
+ * Copyright (C) 2025 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/slab.h>
+#include <crypto/krb5.h>
+#include "internal.h"
+#include "afs_cm.h"
+#include "afs_fs.h"
+#include "protocol_yfs.h"
+#define RXRPC_TRACE_ONLY_DEFINE_ENUMS
+#include <trace/events/rxrpc.h>
+
+#define RXGK_SERVER_ENC_TOKEN 1036U // 0x40c
+#define xdr_round_up(x) (round_up((x), sizeof(__be32)))
+#define xdr_len_object(x) (4 + round_up((x), sizeof(__be32)))
+
+#ifdef CONFIG_RXGK
+static int afs_create_yfs_cm_token(struct sk_buff *challenge,
+				   struct afs_server *server);
+#endif
+
+/*
+ * Respond to an RxGK challenge, adding appdata.
+ */
+static int afs_respond_to_challenge(struct sk_buff *challenge)
+{
+#ifdef CONFIG_RXGK
+	struct krb5_buffer appdata = {};
+	struct afs_server *server;
+#endif
+	struct rxrpc_peer *peer;
+	unsigned long peer_data;
+	u16 service_id;
+	u8 security_index;
+
+	rxrpc_kernel_query_challenge(challenge, &peer, &peer_data,
+				     &service_id, &security_index);
+
+	_enter("%u,%u", service_id, security_index);
+
+	switch (service_id) {
+		/* We don't send CM_SERVICE RPCs, so don't expect a challenge
+		 * therefrom.
+		 */
+	case FS_SERVICE:
+	case VL_SERVICE:
+	case YFS_FS_SERVICE:
+	case YFS_VL_SERVICE:
+		break;
+	default:
+		pr_warn("Can't respond to unknown challenge %u:%u",
+			service_id, security_index);
+		return rxrpc_kernel_reject_challenge(challenge, RX_USER_ABORT, -EPROTO,
+						     afs_abort_unsupported_sec_class);
+	}
+
+	switch (security_index) {
+#ifdef CONFIG_RXKAD
+	case RXRPC_SECURITY_RXKAD:
+		return rxkad_kernel_respond_to_challenge(challenge);
+#endif
+
+#ifdef CONFIG_RXGK
+	case RXRPC_SECURITY_RXGK:
+		return rxgk_kernel_respond_to_challenge(challenge, &appdata);
+
+	case RXRPC_SECURITY_YFS_RXGK:
+		switch (service_id) {
+		case FS_SERVICE:
+		case YFS_FS_SERVICE:
+			server = (struct afs_server *)peer_data;
+			if (!server->cm_rxgk_appdata.data) {
+				mutex_lock(&server->cm_token_lock);
+				if (!server->cm_rxgk_appdata.data)
+					afs_create_yfs_cm_token(challenge, server);
+				mutex_unlock(&server->cm_token_lock);
+			}
+			if (server->cm_rxgk_appdata.data)
+				appdata = server->cm_rxgk_appdata;
+			break;
+		}
+		return rxgk_kernel_respond_to_challenge(challenge, &appdata);
+#endif
+
+	default:
+		return rxrpc_kernel_reject_challenge(challenge, RX_USER_ABORT, -EPROTO,
+						     afs_abort_unsupported_sec_class);
+	}
+}
+
+/*
+ * Process the OOB message queue, processing challenge packets.
+ */
+void afs_process_oob_queue(struct work_struct *work)
+{
+	struct afs_net *net = container_of(work, struct afs_net, rx_oob_work);
+	struct sk_buff *oob;
+	enum rxrpc_oob_type type;
+
+	while ((oob = rxrpc_kernel_dequeue_oob(net->socket, &type))) {
+		switch (type) {
+		case RXRPC_OOB_CHALLENGE:
+			afs_respond_to_challenge(oob);
+			break;
+		}
+		rxrpc_kernel_free_oob(oob);
+	}
+}
+
+#ifdef CONFIG_RXGK
+/*
+ * Create a securities keyring for the cache manager and attach a key to it for
+ * the RxGK tokens we want to use to secure the callback connection back from
+ * the fileserver.
+ */
+int afs_create_token_key(struct afs_net *net, struct socket *socket)
+{
+	const struct krb5_enctype *krb5;
+	struct key *ring;
+	key_ref_t key;
+	char K0[32], *desc;
+	int ret;
+
+	ring = keyring_alloc("kafs",
+			     GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(),
+			     KEY_POS_SEARCH | KEY_POS_WRITE |
+			     KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH,
+			     KEY_ALLOC_NOT_IN_QUOTA,
+			     NULL, NULL);
+	if (IS_ERR(ring))
+		return PTR_ERR(ring);
+
+	ret = rxrpc_sock_set_security_keyring(socket->sk, ring);
+	if (ret < 0)
+		goto out;
+
+	ret = -ENOPKG;
+	krb5 = crypto_krb5_find_enctype(KRB5_ENCTYPE_AES128_CTS_HMAC_SHA1_96);
+	if (!krb5)
+		goto out;
+
+	if (WARN_ON_ONCE(krb5->key_len > sizeof(K0)))
+		goto out;
+
+	ret = -ENOMEM;
+	desc = kasprintf(GFP_KERNEL, "%u:%u:%u:%u",
+			 YFS_CM_SERVICE, RXRPC_SECURITY_YFS_RXGK, 1, krb5->etype);
+	if (!desc)
+		goto out;
+
+	wait_for_random_bytes();
+	get_random_bytes(K0, krb5->key_len);
+
+	key = key_create(make_key_ref(ring, true),
+			 "rxrpc_s", desc,
+			 K0, krb5->key_len,
+			 KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH | KEY_USR_VIEW,
+			 KEY_ALLOC_NOT_IN_QUOTA);
+	kfree(desc);
+	if (IS_ERR(key)) {
+		ret = PTR_ERR(key);
+		goto out;
+	}
+
+	net->fs_cm_token_key = key_ref_to_ptr(key);
+	ret = 0;
+out:
+	key_put(ring);
+	return ret;
+}
+
+/*
+ * Create an YFS RxGK GSS token to use as a ticket to the specified fileserver.
+ */
+static int afs_create_yfs_cm_token(struct sk_buff *challenge,
+				   struct afs_server *server)
+{
+	const struct krb5_enctype *conn_krb5, *token_krb5;
+	const struct krb5_buffer *token_key;
+	struct crypto_aead *aead;
+	struct scatterlist sg;
+	struct afs_net *net = server->cell->net;
+	const struct key *key = net->fs_cm_token_key;
+	size_t keysize, uuidsize, authsize, toksize, encsize, contsize, adatasize, offset;
+	__be32 caps[1] = {
+		[0] = htonl(AFS_CAP_ERROR_TRANSLATION),
+	};
+	__be32 *xdr;
+	void *appdata, *K0, *encbase;
+	u32 enctype;
+	int ret;
+
+	if (!key)
+		return -ENOKEY;
+
+	/* Assume that the fileserver is happy to use the same encoding type as
+	 * we were told to use by the token obtained by the user.
+	 */
+	enctype = rxgk_kernel_query_challenge(challenge);
+
+	conn_krb5 = crypto_krb5_find_enctype(enctype);
+	if (!conn_krb5)
+		return -ENOPKG;
+	token_krb5 = key->payload.data[0];
+	token_key = (const struct krb5_buffer *)&key->payload.data[2];
+
+	/* struct rxgk_key {
+	 *	afs_uint32	enctype;
+	 *	opaque		key<>;
+	 * };
+	 */
+	keysize = 4 + xdr_len_object(conn_krb5->key_len);
+
+	/* struct RXGK_AuthName {
+	 *	afs_int32	kind;
+	 *	opaque		data<AUTHDATAMAX>;
+	 *	opaque		display<AUTHPRINTABLEMAX>;
+	 * };
+	 */
+	uuidsize = sizeof(server->uuid);
+	authsize = 4 + xdr_len_object(uuidsize) + xdr_len_object(0);
+
+	/* struct RXGK_Token {
+	 *	rxgk_key		K0;
+	 *	RXGK_Level		level;
+	 *	rxgkTime		starttime;
+	 *	afs_int32		lifetime;
+	 *	afs_int32		bytelife;
+	 *	rxgkTime		expirationtime;
+	 *	struct RXGK_AuthName	identities<>;
+	 * };
+	 */
+	toksize = keysize + 8 + 4 + 4 + 8 + xdr_len_object(authsize);
+
+	offset = 0;
+	encsize = crypto_krb5_how_much_buffer(token_krb5, KRB5_ENCRYPT_MODE, toksize, &offset);
+
+	/* struct RXGK_TokenContainer {
+	 *	afs_int32	kvno;
+	 *	afs_int32	enctype;
+	 *	opaque		encrypted_token<>;
+	 * };
+	 */
+	contsize = 4 + 4 + xdr_len_object(encsize);
+
+	/* struct YFSAppData {
+	 *	opr_uuid	initiatorUuid;
+	 *	opr_uuid	acceptorUuid;
+	 *	Capabilities	caps;
+	 *	afs_int32	enctype;
+	 *	opaque		callbackKey<>;
+	 *	opaque		callbackToken<>;
+	 * };
+	 */
+	adatasize = 16 + 16 +
+		xdr_len_object(sizeof(caps)) +
+		4 +
+		xdr_len_object(conn_krb5->key_len) +
+		xdr_len_object(contsize);
+
+	ret = -ENOMEM;
+	appdata = kzalloc(adatasize, GFP_KERNEL);
+	if (!appdata)
+		goto out;
+	xdr = appdata;
+
+	memcpy(xdr, &net->uuid, 16);		/* appdata.initiatorUuid */
+	xdr += 16 / 4;
+	memcpy(xdr, &server->uuid, 16);		/* appdata.acceptorUuid */
+	xdr += 16 / 4;
+	*xdr++ = htonl(ARRAY_SIZE(caps));	/* appdata.caps.len */
+	memcpy(xdr, &caps, sizeof(caps));	/* appdata.caps */
+	xdr += ARRAY_SIZE(caps);
+	*xdr++ = htonl(conn_krb5->etype);	/* appdata.enctype */
+
+	*xdr++ = htonl(conn_krb5->key_len);	/* appdata.callbackKey.len */
+	K0 = xdr;
+	get_random_bytes(K0, conn_krb5->key_len); /* appdata.callbackKey.data */
+	xdr += xdr_round_up(conn_krb5->key_len) / 4;
+
+	*xdr++ = htonl(contsize);		/* appdata.callbackToken.len */
+	*xdr++ = htonl(1);			/* cont.kvno */
+	*xdr++ = htonl(token_krb5->etype);	/* cont.enctype */
+	*xdr++ = htonl(encsize);		/* cont.encrypted_token.len */
+
+	encbase = xdr;
+	xdr += offset / 4;
+	*xdr++ = htonl(conn_krb5->etype);	/* token.K0.enctype */
+	*xdr++ = htonl(conn_krb5->key_len);	/* token.K0.key.len */
+	memcpy(xdr, K0, conn_krb5->key_len);	/* token.K0.key.data */
+	xdr += xdr_round_up(conn_krb5->key_len) / 4;
+
+	*xdr++ = htonl(RXRPC_SECURITY_ENCRYPT);	/* token.level */
+	*xdr++ = htonl(0);			/* token.starttime */
+	*xdr++ = htonl(0);			/* " */
+	*xdr++ = htonl(0);			/* token.lifetime */
+	*xdr++ = htonl(0);			/* token.bytelife */
+	*xdr++ = htonl(0);			/* token.expirationtime */
+	*xdr++ = htonl(0);			/* " */
+	*xdr++ = htonl(1);			/* token.identities.count */
+	*xdr++ = htonl(0);			/* token.identities[0].kind */
+	*xdr++ = htonl(uuidsize);		/* token.identities[0].data.len */
+	memcpy(xdr, &server->uuid, uuidsize);
+	xdr += xdr_round_up(uuidsize) / 4;
+	*xdr++ = htonl(0);			/* token.identities[0].display.len */
+
+	xdr = encbase + xdr_round_up(encsize);
+
+	if ((unsigned long)xdr - (unsigned long)appdata != adatasize)
+		pr_err("Appdata size incorrect %lx != %zx\n",
+		       (unsigned long)xdr - (unsigned long)appdata, adatasize);
+
+	aead = crypto_krb5_prepare_encryption(token_krb5, token_key, RXGK_SERVER_ENC_TOKEN,
+					      GFP_KERNEL);
+	if (IS_ERR(aead)) {
+		ret = PTR_ERR(aead);
+		goto out_token;
+	}
+
+	sg_init_one(&sg, encbase, encsize);
+	ret = crypto_krb5_encrypt(token_krb5, aead, &sg, 1, encsize, offset, toksize, false);
+	if (ret < 0)
+		goto out_aead;
+
+	server->cm_rxgk_appdata.len  = adatasize;
+	server->cm_rxgk_appdata.data = appdata;
+	appdata = NULL;
+
+out_aead:
+	crypto_free_aead(aead);
+out_token:
+	kfree(appdata);
+out:
+	return ret;
+}
+#endif /* CONFIG_RXGK */
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 691e0ae607a1..8c6130789fde 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -348,9 +348,9 @@ static int afs_dynroot_readdir(struct file *file, struct dir_context *ctx)
 	}
 
 	if ((unsigned long long)ctx->pos <= AFS_MAX_DYNROOT_CELL_INO) {
-		rcu_read_lock();
+		down_read(&net->cells_lock);
 		ret = afs_dynroot_readdir_cells(net, ctx);
-		rcu_read_unlock();
+		up_read(&net->cells_lock);
 	}
 	return ret;
 }
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 440b0e731093..1124ea4000cb 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -20,6 +20,7 @@
 #include <linux/uuid.h>
 #include <linux/mm_types.h>
 #include <linux/dns_resolver.h>
+#include <crypto/krb5.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/sock.h>
@@ -176,8 +177,10 @@ struct afs_call {
 	bool			intr;		/* T if interruptible */
 	bool			unmarshalling_error; /* T if an unmarshalling error occurred */
 	bool			responded;	/* Got a response from the call (may be abort) */
+	u8			security_ix;	/* Security class */
 	u16			service_id;	/* Actual service ID (after upgrade) */
 	unsigned int		debug_id;	/* Trace ID */
+	u32			enctype;	/* Security encoding type */
 	u32			operation_ID;	/* operation ID for an incoming call */
 	u32			count;		/* count for use in unmarshalling */
 	union {					/* place to extract temporary data */
@@ -281,6 +284,7 @@ struct afs_net {
 	struct socket		*socket;
 	struct afs_call		*spare_incoming_call;
 	struct work_struct	charge_preallocation_work;
+	struct work_struct	rx_oob_work;
 	struct mutex		socket_mutex;
 	atomic_t		nr_outstanding_calls;
 	atomic_t		nr_superblocks;
@@ -305,6 +309,7 @@ struct afs_net {
 	struct list_head	fs_probe_slow;	/* List of afs_server to probe at 5m intervals */
 	struct hlist_head	fs_proc;	/* procfs servers list */
 
+	struct key		*fs_cm_token_key; /* Key for creating CM tokens */
 	struct work_struct	fs_prober;
 	struct timer_list	fs_probe_timer;
 	atomic_t		servers_outstanding;
@@ -540,6 +545,8 @@ struct afs_server {
 	struct list_head	volumes;	/* RCU list of afs_server_entry objects */
 	struct work_struct	destroyer;	/* Work item to try and destroy a server */
 	struct timer_list	timer;		/* Management timer */
+	struct mutex		cm_token_lock;	/* Lock governing creation of appdata */
+	struct krb5_buffer	cm_rxgk_appdata; /* Appdata to be included in RESPONSE packet */
 	time64_t		unuse_time;	/* Time at which last unused */
 	unsigned long		flags;
 #define AFS_SERVER_FL_RESPONDING 0		/* The server is responding */
@@ -1059,6 +1066,19 @@ extern void __net_exit afs_cell_purge(struct afs_net *);
 extern bool afs_cm_incoming_call(struct afs_call *);
 
 /*
+ * cm_security.c
+ */
+void afs_process_oob_queue(struct work_struct *work);
+#ifdef CONFIG_RXGK
+int afs_create_token_key(struct afs_net *net, struct socket *socket);
+#else
+static inline int afs_create_token_key(struct afs_net *net, struct socket *socket)
+{
+	return 0;
+}
+#endif
+
+/*
  * dir.c
  */
 extern const struct file_operations afs_dir_file_operations;
diff --git a/fs/afs/main.c b/fs/afs/main.c
index c845c5daaeba..02475d415d88 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -73,6 +73,7 @@ static int __net_init afs_net_init(struct net *net_ns)
 	generate_random_uuid((unsigned char *)&net->uuid);
 
 	INIT_WORK(&net->charge_preallocation_work, afs_charge_preallocation);
+	INIT_WORK(&net->rx_oob_work, afs_process_oob_queue);
 	mutex_init(&net->socket_mutex);
 
 	net->cells = RB_ROOT;
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index b8180bf2281f..8f2b3a177690 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -8,6 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/errno.h>
+#include <crypto/krb5.h>
 #include "internal.h"
 #include "afs_fs.h"
 #include "protocol_uae.h"
@@ -103,6 +104,32 @@ int afs_abort_to_error(u32 abort_code)
 	case RXKADDATALEN:	return -EKEYREJECTED;
 	case RXKADILLEGALLEVEL:	return -EKEYREJECTED;
 
+	case RXGK_INCONSISTENCY:	return -EPROTO;
+	case RXGK_PACKETSHORT:		return -EPROTO;
+	case RXGK_BADCHALLENGE:		return -EPROTO;
+	case RXGK_SEALEDINCON:		return -EKEYREJECTED;
+	case RXGK_NOTAUTH:		return -EKEYREJECTED;
+	case RXGK_EXPIRED:		return -EKEYEXPIRED;
+	case RXGK_BADLEVEL:		return -EKEYREJECTED;
+	case RXGK_BADKEYNO:		return -EKEYREJECTED;
+	case RXGK_NOTRXGK:		return -EKEYREJECTED;
+	case RXGK_UNSUPPORTED:		return -EKEYREJECTED;
+	case RXGK_GSSERROR:		return -EKEYREJECTED;
+#ifdef RXGK_BADETYPE
+	case RXGK_BADETYPE:		return -ENOPKG;
+#endif
+#ifdef RXGK_BADTOKEN
+	case RXGK_BADTOKEN:		return -EKEYREJECTED;
+#endif
+#ifdef RXGK_BADETYPE
+	case RXGK_DATALEN:		return -EPROTO;
+#endif
+#ifdef RXGK_BADQOP
+	case RXGK_BADQOP:		return -EKEYREJECTED;
+#endif
+
+	case KRB5_PROG_KEYTYPE_NOSUPP:	return -ENOPKG;
+
 	case RXGEN_OPCODE:	return -ENOTSUPP;
 
 	default:		return -EREMOTEIO;
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index d5e480a33859..c1cadf8fb346 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -24,8 +24,17 @@ static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned
 static void afs_process_async_call(struct work_struct *);
 static void afs_rx_new_call(struct sock *, struct rxrpc_call *, unsigned long);
 static void afs_rx_discard_new_call(struct rxrpc_call *, unsigned long);
+static void afs_rx_attach(struct rxrpc_call *rxcall, unsigned long user_call_ID);
+static void afs_rx_notify_oob(struct sock *sk, struct sk_buff *oob);
 static int afs_deliver_cm_op_id(struct afs_call *);
 
+static const struct rxrpc_kernel_ops afs_rxrpc_callback_ops = {
+	.notify_new_call	= afs_rx_new_call,
+	.discard_new_call	= afs_rx_discard_new_call,
+	.user_attach_call	= afs_rx_attach,
+	.notify_oob		= afs_rx_notify_oob,
+};
+
 /* asynchronous incoming call initial processing */
 static const struct afs_call_type afs_RXCMxxxx = {
 	.name		= "CB.xxxx",
@@ -49,6 +58,7 @@ int afs_open_socket(struct afs_net *net)
 		goto error_1;
 
 	socket->sk->sk_allocation = GFP_NOFS;
+	socket->sk->sk_user_data = net;
 
 	/* bind the callback manager's address to make this a server socket */
 	memset(&srx, 0, sizeof(srx));
@@ -64,6 +74,14 @@ int afs_open_socket(struct afs_net *net)
 	if (ret < 0)
 		goto error_2;
 
+	ret = rxrpc_sock_set_manage_response(socket->sk, true);
+	if (ret < 0)
+		goto error_2;
+
+	ret = afs_create_token_key(net, socket);
+	if (ret < 0)
+		pr_err("Couldn't create RxGK CM key: %d\n", ret);
+
 	ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx));
 	if (ret == -EADDRINUSE) {
 		srx.transport.sin6.sin6_port = 0;
@@ -84,8 +102,7 @@ int afs_open_socket(struct afs_net *net)
 	 * it sends back to us.
 	 */
 
-	rxrpc_kernel_new_call_notification(socket, afs_rx_new_call,
-					   afs_rx_discard_new_call);
+	rxrpc_kernel_set_notifications(socket, &afs_rxrpc_callback_ops);
 
 	ret = kernel_listen(socket, INT_MAX);
 	if (ret < 0)
@@ -125,7 +142,9 @@ void afs_close_socket(struct afs_net *net)
 
 	kernel_sock_shutdown(net->socket, SHUT_RDWR);
 	flush_workqueue(afs_async_calls);
+	net->socket->sk->sk_user_data = NULL;
 	sock_release(net->socket);
+	key_put(net->fs_cm_token_key);
 
 	_debug("dework");
 	_leave("");
@@ -738,7 +757,6 @@ void afs_charge_preallocation(struct work_struct *work)
 
 		if (rxrpc_kernel_charge_accept(net->socket,
 					       afs_wake_up_async_call,
-					       afs_rx_attach,
 					       (unsigned long)call,
 					       GFP_KERNEL,
 					       call->debug_id) < 0)
@@ -800,10 +818,14 @@ static int afs_deliver_cm_op_id(struct afs_call *call)
 	if (!afs_cm_incoming_call(call))
 		return -ENOTSUPP;
 
+	call->security_ix = rxrpc_kernel_query_call_security(call->rxcall,
+							     &call->service_id,
+							     &call->enctype);
+
 	trace_afs_cb_call(call);
 	call->work.func = call->type->work;
 
-	/* pass responsibility for the remainer of this message off to the
+	/* pass responsibility for the remainder of this message off to the
 	 * cache manager op */
 	return call->type->deliver(call);
 }
@@ -952,3 +974,13 @@ noinline int afs_protocol_error(struct afs_call *call,
 		call->unmarshalling_error = true;
 	return -EBADMSG;
 }
+
+/*
+ * Wake up OOB notification processing.
+ */
+static void afs_rx_notify_oob(struct sock *sk, struct sk_buff *oob)
+{
+	struct afs_net *net = sk->sk_user_data;
+
+	schedule_work(&net->rx_oob_work);
+}
diff --git a/fs/afs/server.c b/fs/afs/server.c
index 8755f2703815..a97562f831eb 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -131,6 +131,7 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell, const uuid_t *
 	timer_setup(&server->timer, afs_server_timer, 0);
 	INIT_LIST_HEAD(&server->volumes);
 	init_waitqueue_head(&server->probe_wq);
+	mutex_init(&server->cm_token_lock);
 	INIT_LIST_HEAD(&server->probe_link);
 	INIT_HLIST_NODE(&server->proc_link);
 	spin_lock_init(&server->probe_lock);
@@ -396,6 +397,7 @@ static void afs_server_rcu(struct rcu_head *rcu)
 	afs_put_endpoint_state(rcu_access_pointer(server->endpoint_state),
 			       afs_estate_trace_put_server);
 	afs_put_cell(server->cell, afs_cell_trace_put_server);
+	kfree(server->cm_rxgk_appdata.data);
 	kfree(server);
 }
 
diff --git a/fs/bcachefs/Kconfig b/fs/bcachefs/Kconfig
index adcf425a9b88..07709b0d7688 100644
--- a/fs/bcachefs/Kconfig
+++ b/fs/bcachefs/Kconfig
@@ -15,10 +15,9 @@ config BCACHEFS_FS
 	select ZLIB_INFLATE
 	select ZSTD_COMPRESS
 	select ZSTD_DECOMPRESS
-	select CRYPTO
 	select CRYPTO_LIB_SHA256
-	select CRYPTO_CHACHA20
-	select CRYPTO_POLY1305
+	select CRYPTO_LIB_CHACHA
+	select CRYPTO_LIB_POLY1305
 	select KEYS
 	select RAID6_PQ
 	select XOR_BLOCKS
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index 7c930ef77380..7ec022e9361a 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -1422,8 +1422,30 @@ alloc_done:
 
 	wp->sectors_free = UINT_MAX;
 
-	open_bucket_for_each(c, &wp->ptrs, ob, i)
+	open_bucket_for_each(c, &wp->ptrs, ob, i) {
+		/*
+		 * Ensure proper write alignment - either due to misaligned
+		 * bucket sizes (from buggy bcachefs-tools), or writes that mix
+		 * logical/physical alignment:
+		 */
+		struct bch_dev *ca = ob_dev(c, ob);
+		u64 offset = bucket_to_sector(ca, ob->bucket) +
+			ca->mi.bucket_size -
+			ob->sectors_free;
+		unsigned align = round_up(offset, block_sectors(c)) - offset;
+
+		ob->sectors_free = max_t(int, 0, ob->sectors_free - align);
+
 		wp->sectors_free = min(wp->sectors_free, ob->sectors_free);
+	}
+
+	wp->sectors_free = rounddown(wp->sectors_free, block_sectors(c));
+
+	/* Did alignment use up space in an open_bucket? */
+	if (unlikely(!wp->sectors_free)) {
+		bch2_alloc_sectors_done(c, wp);
+		goto retry;
+	}
 
 	BUG_ON(!wp->sectors_free || wp->sectors_free == UINT_MAX);
 
diff --git a/fs/bcachefs/alloc_foreground.h b/fs/bcachefs/alloc_foreground.h
index 69ec6a012898..4c1e33cf57c0 100644
--- a/fs/bcachefs/alloc_foreground.h
+++ b/fs/bcachefs/alloc_foreground.h
@@ -110,7 +110,9 @@ static inline void bch2_alloc_sectors_done_inlined(struct bch_fs *c, struct writ
 	unsigned i;
 
 	open_bucket_for_each(c, &wp->ptrs, ob, i)
-		ob_push(c, !ob->sectors_free ? &ptrs : &keep, ob);
+		ob_push(c, ob->sectors_free < block_sectors(c)
+			? &ptrs
+			: &keep, ob);
 	wp->ptrs = keep;
 
 	mutex_unlock(&wp->lock);
diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index ff26bb515150..5f195d2280a4 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -192,7 +192,8 @@ static inline int bch2_backpointers_maybe_flush(struct btree_trans *trans,
 static int backpointer_target_not_found(struct btree_trans *trans,
 				  struct bkey_s_c_backpointer bp,
 				  struct bkey_s_c target_k,
-				  struct bkey_buf *last_flushed)
+				  struct bkey_buf *last_flushed,
+				  bool commit)
 {
 	struct bch_fs *c = trans->c;
 	struct printbuf buf = PRINTBUF;
@@ -228,18 +229,77 @@ static int backpointer_target_not_found(struct btree_trans *trans,
 		}
 
 	if (fsck_err(trans, backpointer_to_missing_ptr,
-		     "%s", buf.buf))
+		     "%s", buf.buf)) {
 		ret = bch2_backpointer_del(trans, bp.k->p);
+		if (ret || !commit)
+			goto out;
+
+		/*
+		 * Normally, on transaction commit from inside a transaction,
+		 * we'll return -BCH_ERR_transaction_restart_nested, since a
+		 * transaction commit invalidates pointers given out by peek().
+		 *
+		 * However, since we're updating a write buffer btree, if we
+		 * return a transaction restart and loop we won't see that the
+		 * backpointer has been deleted without an additional write
+		 * buffer flush - and those are expensive.
+		 *
+		 * So we're relying on the caller immediately advancing to the
+		 * next backpointer and starting a new transaction immediately
+		 * after backpointer_get_key() returns NULL:
+		 */
+		ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
+	}
+out:
 fsck_err:
 	printbuf_exit(&buf);
 	return ret;
 }
 
-struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans,
-					 struct bkey_s_c_backpointer bp,
-					 struct btree_iter *iter,
-					 unsigned iter_flags,
-					 struct bkey_buf *last_flushed)
+static struct btree *__bch2_backpointer_get_node(struct btree_trans *trans,
+						 struct bkey_s_c_backpointer bp,
+						 struct btree_iter *iter,
+						 struct bkey_buf *last_flushed,
+						 bool commit)
+{
+	struct bch_fs *c = trans->c;
+
+	BUG_ON(!bp.v->level);
+
+	bch2_trans_node_iter_init(trans, iter,
+				  bp.v->btree_id,
+				  bp.v->pos,
+				  0,
+				  bp.v->level - 1,
+				  0);
+	struct btree *b = bch2_btree_iter_peek_node(trans, iter);
+	if (IS_ERR_OR_NULL(b))
+		goto err;
+
+	BUG_ON(b->c.level != bp.v->level - 1);
+
+	if (extent_matches_bp(c, bp.v->btree_id, bp.v->level,
+			      bkey_i_to_s_c(&b->key), bp))
+		return b;
+
+	if (btree_node_will_make_reachable(b)) {
+		b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node);
+	} else {
+		int ret = backpointer_target_not_found(trans, bp, bkey_i_to_s_c(&b->key),
+						       last_flushed, commit);
+		b = ret ? ERR_PTR(ret) : NULL;
+	}
+err:
+	bch2_trans_iter_exit(trans, iter);
+	return b;
+}
+
+static struct bkey_s_c __bch2_backpointer_get_key(struct btree_trans *trans,
+						  struct bkey_s_c_backpointer bp,
+						  struct btree_iter *iter,
+						  unsigned iter_flags,
+						  struct bkey_buf *last_flushed,
+						  bool commit)
 {
 	struct bch_fs *c = trans->c;
 
@@ -277,10 +337,10 @@ struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans,
 	bch2_trans_iter_exit(trans, iter);
 
 	if (!bp.v->level) {
-		int ret = backpointer_target_not_found(trans, bp, k, last_flushed);
+		int ret = backpointer_target_not_found(trans, bp, k, last_flushed, commit);
 		return ret ? bkey_s_c_err(ret) : bkey_s_c_null;
 	} else {
-		struct btree *b = bch2_backpointer_get_node(trans, bp, iter, last_flushed);
+		struct btree *b = __bch2_backpointer_get_node(trans, bp, iter, last_flushed, commit);
 		if (b == ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node))
 			return bkey_s_c_null;
 		if (IS_ERR_OR_NULL(b))
@@ -295,35 +355,16 @@ struct btree *bch2_backpointer_get_node(struct btree_trans *trans,
 					struct btree_iter *iter,
 					struct bkey_buf *last_flushed)
 {
-	struct bch_fs *c = trans->c;
-
-	BUG_ON(!bp.v->level);
-
-	bch2_trans_node_iter_init(trans, iter,
-				  bp.v->btree_id,
-				  bp.v->pos,
-				  0,
-				  bp.v->level - 1,
-				  0);
-	struct btree *b = bch2_btree_iter_peek_node(trans, iter);
-	if (IS_ERR_OR_NULL(b))
-		goto err;
-
-	BUG_ON(b->c.level != bp.v->level - 1);
-
-	if (extent_matches_bp(c, bp.v->btree_id, bp.v->level,
-			      bkey_i_to_s_c(&b->key), bp))
-		return b;
+	return __bch2_backpointer_get_node(trans, bp, iter, last_flushed, true);
+}
 
-	if (btree_node_will_make_reachable(b)) {
-		b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node);
-	} else {
-		int ret = backpointer_target_not_found(trans, bp, bkey_i_to_s_c(&b->key), last_flushed);
-		b = ret ? ERR_PTR(ret) : NULL;
-	}
-err:
-	bch2_trans_iter_exit(trans, iter);
-	return b;
+struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans,
+					 struct bkey_s_c_backpointer bp,
+					 struct btree_iter *iter,
+					 unsigned iter_flags,
+					 struct bkey_buf *last_flushed)
+{
+	return __bch2_backpointer_get_key(trans, bp, iter, iter_flags, last_flushed, true);
 }
 
 static int bch2_check_backpointer_has_valid_bucket(struct btree_trans *trans, struct bkey_s_c k,
@@ -521,7 +562,7 @@ check_existing_bp:
 	struct bkey_s_c_backpointer other_bp = bkey_s_c_to_backpointer(bp_k);
 
 	struct bkey_s_c other_extent =
-		bch2_backpointer_get_key(trans, other_bp, &other_extent_iter, 0, NULL);
+		__bch2_backpointer_get_key(trans, other_bp, &other_extent_iter, 0, NULL, false);
 	ret = bkey_err(other_extent);
 	if (ret == -BCH_ERR_backpointer_to_overwritten_btree_node)
 		ret = 0;
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 5d9f208a1bb7..75f7408da173 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -788,6 +788,8 @@ struct bch_fs {
 		unsigned long	errors_silent[BITS_TO_LONGS(BCH_FSCK_ERR_MAX)];
 		u64		btrees_lost_data;
 	}			sb;
+	DARRAY(enum bcachefs_metadata_version)
+				incompat_versions_requested;
 
 #ifdef CONFIG_UNICODE
 	struct unicode_map	*cf_encoding;
@@ -981,8 +983,8 @@ struct bch_fs {
 	mempool_t		compress_workspace[BCH_COMPRESSION_OPT_NR];
 	size_t			zstd_workspace_size;
 
-	struct crypto_sync_skcipher *chacha20;
-	struct crypto_shash	*poly1305;
+	struct bch_key		chacha20_key;
+	bool			chacha20_key_set;
 
 	atomic64_t		key_version;
 
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index a3db328dee31..d6e4a496f02b 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -366,6 +366,10 @@ static inline void bkey_init(struct bkey *k)
 #define __BKEY_PADDED(key, pad)					\
 	struct bkey_i key; __u64 key ## _pad[pad]
 
+enum bch_bkey_type_flags {
+	BKEY_TYPE_strict_btree_checks	= BIT(0),
+};
+
 /*
  * - DELETED keys are used internally to mark keys that should be ignored but
  *   override keys in composition order.  Their version number is ignored.
@@ -383,46 +387,46 @@ static inline void bkey_init(struct bkey *k)
  *
  * - WHITEOUT: for hash table btrees
  */
-#define BCH_BKEY_TYPES()				\
-	x(deleted,		0)			\
-	x(whiteout,		1)			\
-	x(error,		2)			\
-	x(cookie,		3)			\
-	x(hash_whiteout,	4)			\
-	x(btree_ptr,		5)			\
-	x(extent,		6)			\
-	x(reservation,		7)			\
-	x(inode,		8)			\
-	x(inode_generation,	9)			\
-	x(dirent,		10)			\
-	x(xattr,		11)			\
-	x(alloc,		12)			\
-	x(quota,		13)			\
-	x(stripe,		14)			\
-	x(reflink_p,		15)			\
-	x(reflink_v,		16)			\
-	x(inline_data,		17)			\
-	x(btree_ptr_v2,		18)			\
-	x(indirect_inline_data,	19)			\
-	x(alloc_v2,		20)			\
-	x(subvolume,		21)			\
-	x(snapshot,		22)			\
-	x(inode_v2,		23)			\
-	x(alloc_v3,		24)			\
-	x(set,			25)			\
-	x(lru,			26)			\
-	x(alloc_v4,		27)			\
-	x(backpointer,		28)			\
-	x(inode_v3,		29)			\
-	x(bucket_gens,		30)			\
-	x(snapshot_tree,	31)			\
-	x(logged_op_truncate,	32)			\
-	x(logged_op_finsert,	33)			\
-	x(accounting,		34)			\
-	x(inode_alloc_cursor,	35)
+#define BCH_BKEY_TYPES()						\
+	x(deleted,		0,	0)				\
+	x(whiteout,		1,	0)				\
+	x(error,		2,	0)				\
+	x(cookie,		3,	0)				\
+	x(hash_whiteout,	4,	BKEY_TYPE_strict_btree_checks)	\
+	x(btree_ptr,		5,	BKEY_TYPE_strict_btree_checks)	\
+	x(extent,		6,	BKEY_TYPE_strict_btree_checks)	\
+	x(reservation,		7,	BKEY_TYPE_strict_btree_checks)	\
+	x(inode,		8,	BKEY_TYPE_strict_btree_checks)	\
+	x(inode_generation,	9,	BKEY_TYPE_strict_btree_checks)	\
+	x(dirent,		10,	BKEY_TYPE_strict_btree_checks)	\
+	x(xattr,		11,	BKEY_TYPE_strict_btree_checks)	\
+	x(alloc,		12,	BKEY_TYPE_strict_btree_checks)	\
+	x(quota,		13,	BKEY_TYPE_strict_btree_checks)	\
+	x(stripe,		14,	BKEY_TYPE_strict_btree_checks)	\
+	x(reflink_p,		15,	BKEY_TYPE_strict_btree_checks)	\
+	x(reflink_v,		16,	BKEY_TYPE_strict_btree_checks)	\
+	x(inline_data,		17,	BKEY_TYPE_strict_btree_checks)	\
+	x(btree_ptr_v2,		18,	BKEY_TYPE_strict_btree_checks)	\
+	x(indirect_inline_data,	19,	BKEY_TYPE_strict_btree_checks)	\
+	x(alloc_v2,		20,	BKEY_TYPE_strict_btree_checks)	\
+	x(subvolume,		21,	BKEY_TYPE_strict_btree_checks)	\
+	x(snapshot,		22,	BKEY_TYPE_strict_btree_checks)	\
+	x(inode_v2,		23,	BKEY_TYPE_strict_btree_checks)	\
+	x(alloc_v3,		24,	BKEY_TYPE_strict_btree_checks)	\
+	x(set,			25,	0)				\
+	x(lru,			26,	BKEY_TYPE_strict_btree_checks)	\
+	x(alloc_v4,		27,	BKEY_TYPE_strict_btree_checks)	\
+	x(backpointer,		28,	BKEY_TYPE_strict_btree_checks)	\
+	x(inode_v3,		29,	BKEY_TYPE_strict_btree_checks)	\
+	x(bucket_gens,		30,	BKEY_TYPE_strict_btree_checks)	\
+	x(snapshot_tree,	31,	BKEY_TYPE_strict_btree_checks)	\
+	x(logged_op_truncate,	32,	BKEY_TYPE_strict_btree_checks)	\
+	x(logged_op_finsert,	33,	BKEY_TYPE_strict_btree_checks)	\
+	x(accounting,		34,	BKEY_TYPE_strict_btree_checks)	\
+	x(inode_alloc_cursor,	35,	BKEY_TYPE_strict_btree_checks)
 
 enum bch_bkey_type {
-#define x(name, nr) KEY_TYPE_##name	= nr,
+#define x(name, nr, ...) KEY_TYPE_##name	= nr,
 	BCH_BKEY_TYPES()
 #undef x
 	KEY_TYPE_MAX,
@@ -863,6 +867,7 @@ LE64_BITMASK(BCH_SB_VERSION_INCOMPAT_ALLOWED,
 LE64_BITMASK(BCH_SB_SHARD_INUMS_NBITS,	struct bch_sb, flags[6],  0,  4);
 LE64_BITMASK(BCH_SB_WRITE_ERROR_TIMEOUT,struct bch_sb, flags[6],  4, 14);
 LE64_BITMASK(BCH_SB_CSUM_ERR_RETRY_NR,	struct bch_sb, flags[6], 14, 20);
+LE64_BITMASK(BCH_SB_CASEFOLD,		struct bch_sb, flags[6], 22, 23);
 
 static inline __u64 BCH_SB_COMPRESSION_TYPE(const struct bch_sb *sb)
 {
diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c
index 15c93576b5c2..00d05ccfaf73 100644
--- a/fs/bcachefs/bkey_methods.c
+++ b/fs/bcachefs/bkey_methods.c
@@ -21,7 +21,7 @@
 #include "xattr.h"
 
 const char * const bch2_bkey_types[] = {
-#define x(name, nr) #name,
+#define x(name, nr, ...) #name,
 	BCH_BKEY_TYPES()
 #undef x
 	NULL
@@ -115,7 +115,7 @@ static bool key_type_set_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_
 })
 
 const struct bkey_ops bch2_bkey_ops[] = {
-#define x(name, nr) [KEY_TYPE_##name]	= bch2_bkey_ops_##name,
+#define x(name, nr, ...) [KEY_TYPE_##name]	= bch2_bkey_ops_##name,
 	BCH_BKEY_TYPES()
 #undef x
 };
@@ -155,6 +155,12 @@ static u64 bch2_key_types_allowed[] = {
 #undef x
 };
 
+static const enum bch_bkey_type_flags bch2_bkey_type_flags[] = {
+#define x(name, nr, flags)	[KEY_TYPE_##name] = flags,
+	BCH_BKEY_TYPES()
+#undef x
+};
+
 const char *bch2_btree_node_type_str(enum btree_node_type type)
 {
 	return type == BKEY_TYPE_btree ? "internal btree node" : bch2_btree_id_str(type - 1);
@@ -177,8 +183,18 @@ int __bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k,
 	if (type >= BKEY_TYPE_NR)
 		return 0;
 
-	bkey_fsck_err_on(k.k->type < KEY_TYPE_MAX &&
-			 (type == BKEY_TYPE_btree || (from.flags & BCH_VALIDATE_commit)) &&
+	enum bch_bkey_type_flags bkey_flags = k.k->type < KEY_TYPE_MAX
+		? bch2_bkey_type_flags[k.k->type]
+		: 0;
+
+	bool strict_key_type_allowed =
+		(from.flags & BCH_VALIDATE_commit) ||
+		type == BKEY_TYPE_btree ||
+		(from.btree < BTREE_ID_NR &&
+		 (bkey_flags & BKEY_TYPE_strict_btree_checks));
+
+	bkey_fsck_err_on(strict_key_type_allowed &&
+			 k.k->type < KEY_TYPE_MAX &&
 			 !(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)),
 			 c, bkey_invalid_type_for_btree,
 			 "invalid key type for btree %s (%s)",
diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index 9b80201c7982..899891295797 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -852,7 +852,6 @@ out:
 	b->sib_u64s[1]		= 0;
 	b->whiteout_u64s	= 0;
 	bch2_btree_keys_init(b);
-	set_btree_node_accessed(b);
 
 	bch2_time_stats_update(&c->times[BCH_TIME_btree_node_mem_alloc],
 			       start_time);
@@ -1286,6 +1285,10 @@ lock_node:
 			six_unlock_read(&b->c.lock);
 			goto retry;
 		}
+
+		/* avoid atomic set bit if it's not needed: */
+		if (!btree_node_accessed(b))
+			set_btree_node_accessed(b);
 	}
 
 	/* XXX: waiting on IO with btree locks held: */
@@ -1301,10 +1304,6 @@ lock_node:
 		prefetch(p + L1_CACHE_BYTES * 2);
 	}
 
-	/* avoid atomic set bit if it's not needed: */
-	if (!btree_node_accessed(b))
-		set_btree_node_accessed(b);
-
 	if (unlikely(btree_node_read_error(b))) {
 		six_unlock_read(&b->c.lock);
 		b = ERR_PTR(-BCH_ERR_btree_node_read_err_cached);
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 7b98ba2dec64..37b69d89341f 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -47,6 +47,27 @@
 #define DROP_PREV_NODE		11
 #define DID_FILL_FROM_SCAN	12
 
+/*
+ * Returns true if it's a btree we can easily reconstruct, or otherwise won't
+ * cause data loss if it's missing:
+ */
+static bool btree_id_important(enum btree_id btree)
+{
+	if (btree_id_is_alloc(btree))
+		return false;
+
+	switch (btree) {
+	case BTREE_ID_quotas:
+	case BTREE_ID_snapshot_trees:
+	case BTREE_ID_logged_ops:
+	case BTREE_ID_rebalance_work:
+	case BTREE_ID_subvolume_children:
+		return false;
+	default:
+		return true;
+	}
+}
+
 static const char * const bch2_gc_phase_strs[] = {
 #define x(n)	#n,
 	GC_PHASES()
@@ -534,8 +555,10 @@ reconstruct_root:
 			r->error = 0;
 
 			if (!bch2_btree_has_scanned_nodes(c, i)) {
-				mustfix_fsck_err(trans, btree_root_unreadable_and_scan_found_nothing,
-						 "no nodes found for btree %s, continue?", buf.buf);
+				__fsck_err(trans,
+					   FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0),
+					   btree_root_unreadable_and_scan_found_nothing,
+					   "no nodes found for btree %s, continue?", buf.buf);
 				bch2_btree_root_alloc_fake_trans(trans, i, 0);
 			} else {
 				bch2_btree_root_alloc_fake_trans(trans, i, 1);
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 5fd4a58d2ad2..60782f3e5aec 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -41,6 +41,7 @@ void bch2_btree_node_io_unlock(struct btree *b)
 
 	clear_btree_node_write_in_flight_inner(b);
 	clear_btree_node_write_in_flight(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_write_in_flight);
 }
 
@@ -1400,6 +1401,7 @@ start:
 
 	printbuf_exit(&buf);
 	clear_btree_node_read_in_flight(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
 }
 
@@ -1595,6 +1597,7 @@ fsck_err:
 	printbuf_exit(&buf);
 
 	clear_btree_node_read_in_flight(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
 }
 
@@ -1721,6 +1724,7 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b,
 		set_btree_node_read_error(b);
 		bch2_btree_lost_data(c, b->c.btree_id);
 		clear_btree_node_read_in_flight(b);
+		smp_mb__after_atomic();
 		wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
 		printbuf_exit(&buf);
 		return;
@@ -2061,8 +2065,10 @@ static void __btree_node_write_done(struct bch_fs *c, struct btree *b, u64 start
 
 	if (new & (1U << BTREE_NODE_write_in_flight))
 		__bch2_btree_node_write(c, b, BTREE_WRITE_ALREADY_STARTED|type);
-	else
+	else {
+		smp_mb__after_atomic();
 		wake_up_bit(&b->flags, BTREE_NODE_write_in_flight);
+	}
 }
 
 static void btree_node_write_done(struct bch_fs *c, struct btree *b, u64 start_time)
@@ -2175,6 +2181,7 @@ static void btree_node_write_endio(struct bio *bio)
 	}
 
 	clear_btree_node_write_in_flight_inner(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_write_in_flight_inner);
 	INIT_WORK(&wb->work, btree_node_write_work);
 	queue_work(c->btree_io_complete_wq, &wb->work);
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index e34e9598ef25..a873ec1baf58 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -1971,6 +1971,12 @@ struct btree *bch2_btree_iter_next_node(struct btree_trans *trans, struct btree_
 		return NULL;
 	}
 
+	/*
+	 * We don't correctly handle nodes with extra intent locks here:
+	 * downgrade so we don't violate locking invariants
+	 */
+	bch2_btree_path_downgrade(trans, path);
+
 	if (!bch2_btree_node_relock(trans, path, path->level + 1)) {
 		__bch2_btree_path_unlock(trans, path);
 		path->l[path->level].b		= ERR_PTR(-BCH_ERR_no_btree_node_relock);
@@ -2577,7 +2583,10 @@ struct bkey_s_c bch2_btree_iter_peek_prev_min(struct btree_trans *trans, struct
 					      struct bpos end)
 {
 	if ((iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots)) &&
-	   !bkey_eq(iter->pos, POS_MAX)) {
+	   !bkey_eq(iter->pos, POS_MAX) &&
+	   !((iter->flags & BTREE_ITER_is_extents) &&
+	     iter->pos.offset == U64_MAX)) {
+
 		/*
 		 * bkey_start_pos(), for extents, is not monotonically
 		 * increasing until after filtering for snapshots:
@@ -2602,7 +2611,7 @@ struct bkey_s_c bch2_btree_iter_peek_prev_min(struct btree_trans *trans, struct
 
 	bch2_trans_verify_not_unlocked_or_in_restart(trans);
 	bch2_btree_iter_verify_entry_exit(iter);
-	EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && bpos_eq(end, POS_MIN));
+	EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && iter->pos.inode != end.inode);
 
 	int ret = trans_maybe_inject_restart(trans, _RET_IP_);
 	if (unlikely(ret)) {
@@ -2740,7 +2749,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
 	ret = trans_maybe_inject_restart(trans, _RET_IP_);
 	if (unlikely(ret)) {
 		k = bkey_s_c_err(ret);
-		goto out_no_locked;
+		goto out;
 	}
 
 	/* extents can't span inode numbers: */
@@ -2760,13 +2769,15 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
 	ret = bch2_btree_path_traverse(trans, iter->path, iter->flags);
 	if (unlikely(ret)) {
 		k = bkey_s_c_err(ret);
-		goto out_no_locked;
+		goto out;
 	}
 
 	struct btree_path *path = btree_iter_path(trans, iter);
 	if (unlikely(!btree_path_node(path, path->level)))
 		return bkey_s_c_null;
 
+	btree_path_set_should_be_locked(trans, path);
+
 	if ((iter->flags & BTREE_ITER_cached) ||
 	    !(iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots))) {
 		k = bkey_s_c_null;
@@ -2787,12 +2798,12 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
 			if (!bkey_err(k))
 				iter->k = *k.k;
 			/* We're not returning a key from iter->path: */
-			goto out_no_locked;
+			goto out;
 		}
 
-		k = bch2_btree_path_peek_slot(trans->paths + iter->path, &iter->k);
+		k = bch2_btree_path_peek_slot(btree_iter_path(trans, iter), &iter->k);
 		if (unlikely(!k.k))
-			goto out_no_locked;
+			goto out;
 
 		if (unlikely(k.k->type == KEY_TYPE_whiteout &&
 			     (iter->flags & BTREE_ITER_filter_snapshots) &&
@@ -2830,7 +2841,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
 		}
 
 		if (unlikely(bkey_err(k)))
-			goto out_no_locked;
+			goto out;
 
 		next = k.k ? bkey_start_pos(k.k) : POS_MAX;
 
@@ -2852,8 +2863,6 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
 		}
 	}
 out:
-	btree_path_set_should_be_locked(trans, btree_iter_path(trans, iter));
-out_no_locked:
 	bch2_btree_iter_verify_entry_exit(iter);
 	bch2_btree_iter_verify(trans, iter);
 	ret = bch2_btree_iter_verify_ret(trans, iter, k);
diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index d1ad1a7613c9..ade3b5addd75 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -288,7 +288,7 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id,
 			.size			= max_t(size_t, keys->size, 8) * 2,
 		};
 
-		new_keys.data = kvmalloc_array(new_keys.size, sizeof(new_keys.data[0]), GFP_KERNEL);
+		new_keys.data = bch2_kvmalloc(new_keys.size * sizeof(new_keys.data[0]), GFP_KERNEL);
 		if (!new_keys.data) {
 			bch_err(c, "%s: error allocating new key array (size %zu)",
 				__func__, new_keys.size);
@@ -644,8 +644,6 @@ void bch2_btree_and_journal_iter_init_node_iter(struct btree_trans *trans,
  */
 static int journal_sort_key_cmp(const void *_l, const void *_r)
 {
-	cond_resched();
-
 	const struct journal_key *l = _l;
 	const struct journal_key *r = _r;
 
@@ -689,7 +687,8 @@ void bch2_journal_keys_put(struct bch_fs *c)
 
 static void __journal_keys_sort(struct journal_keys *keys)
 {
-	sort(keys->data, keys->nr, sizeof(keys->data[0]), journal_sort_key_cmp, NULL);
+	sort_nonatomic(keys->data, keys->nr, sizeof(keys->data[0]),
+		       journal_sort_key_cmp, NULL);
 
 	cond_resched();
 
diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c
index 8c9fdb7263fe..86acf037590c 100644
--- a/fs/bcachefs/btree_node_scan.c
+++ b/fs/bcachefs/btree_node_scan.c
@@ -183,7 +183,7 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca,
 		return;
 
 	if (bch2_csum_type_is_encryption(BSET_CSUM_TYPE(&bn->keys))) {
-		if (!c->chacha20)
+		if (!c->chacha20_key_set)
 			return;
 
 		struct nonce nonce = btree_nonce(&bn->keys, 0);
@@ -398,7 +398,7 @@ int bch2_scan_for_btree_nodes(struct bch_fs *c)
 		bch2_print_string_as_lines(KERN_INFO, buf.buf);
 	}
 
-	sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_cookie, NULL);
+	sort_nonatomic(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_cookie, NULL);
 
 	dst = 0;
 	darray_for_each(f->nodes, i) {
@@ -418,7 +418,7 @@ int bch2_scan_for_btree_nodes(struct bch_fs *c)
 	}
 	f->nodes.nr = dst;
 
-	sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_pos, NULL);
+	sort_nonatomic(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_pos, NULL);
 
 	if (0 && c->opts.verbose) {
 		printbuf_reset(&buf);
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 55fbeeb8eaaa..00307356d7c8 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -1221,7 +1221,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 
 	ret = bch2_disk_reservation_get(c, &as->disk_res,
 			(nr_nodes[0] + nr_nodes[1]) * btree_sectors(c),
-			c->opts.metadata_replicas,
+			READ_ONCE(c->opts.metadata_replicas),
 			disk_res_flags);
 	if (ret)
 		goto err;
@@ -1389,7 +1389,7 @@ static void bch2_insert_fixup_btree_ptr(struct btree_update *as,
 	printbuf_exit(&buf);
 }
 
-static void
+static int
 bch2_btree_insert_keys_interior(struct btree_update *as,
 				struct btree_trans *trans,
 				struct btree_path *path,
@@ -1411,7 +1411,8 @@ bch2_btree_insert_keys_interior(struct btree_update *as,
 	     insert = bkey_next(insert))
 		bch2_insert_fixup_btree_ptr(as, trans, path, b, &node_iter, insert);
 
-	if (bch2_btree_node_check_topology(trans, b)) {
+	int ret = bch2_btree_node_check_topology(trans, b);
+	if (ret) {
 		struct printbuf buf = PRINTBUF;
 
 		for (struct bkey_i *k = keys->keys;
@@ -1421,11 +1422,15 @@ bch2_btree_insert_keys_interior(struct btree_update *as,
 			prt_newline(&buf);
 		}
 
-		panic("%s(): check_topology error: inserted keys\n%s", __func__, buf.buf);
+		bch2_fs_fatal_error(as->c, "%ps -> %s(): check_topology error %s: inserted keys\n%s",
+				    (void *) _RET_IP_, __func__, bch2_err_str(ret), buf.buf);
+		dump_stack();
+		return ret;
 	}
 
 	memmove_u64s_down(keys->keys, insert, keys->top_p - insert->_data);
 	keys->top_p -= insert->_data - keys->keys_p;
+	return 0;
 }
 
 static bool key_deleted_in_insert(struct keylist *insert_keys, struct bpos pos)
@@ -1559,11 +1564,11 @@ static void __btree_split_node(struct btree_update *as,
  * nodes that were coalesced, and thus in the middle of a child node post
  * coalescing:
  */
-static void btree_split_insert_keys(struct btree_update *as,
-				    struct btree_trans *trans,
-				    btree_path_idx_t path_idx,
-				    struct btree *b,
-				    struct keylist *keys)
+static int btree_split_insert_keys(struct btree_update *as,
+				   struct btree_trans *trans,
+				   btree_path_idx_t path_idx,
+				   struct btree *b,
+				   struct keylist *keys)
 {
 	struct btree_path *path = trans->paths + path_idx;
 
@@ -1573,8 +1578,12 @@ static void btree_split_insert_keys(struct btree_update *as,
 
 		bch2_btree_node_iter_init(&node_iter, b, &bch2_keylist_front(keys)->k.p);
 
-		bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys);
+		int ret = bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys);
+		if (ret)
+			return ret;
 	}
+
+	return 0;
 }
 
 static int btree_split(struct btree_update *as, struct btree_trans *trans,
@@ -1607,8 +1616,10 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
 		__btree_split_node(as, trans, b, n, keys);
 
 		if (keys) {
-			btree_split_insert_keys(as, trans, path, n1, keys);
-			btree_split_insert_keys(as, trans, path, n2, keys);
+			ret =   btree_split_insert_keys(as, trans, path, n1, keys) ?:
+				btree_split_insert_keys(as, trans, path, n2, keys);
+			if (ret)
+				goto err;
 			BUG_ON(!bch2_keylist_empty(keys));
 		}
 
@@ -1654,7 +1665,9 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
 			n3->sib_u64s[0] = U16_MAX;
 			n3->sib_u64s[1] = U16_MAX;
 
-			btree_split_insert_keys(as, trans, path, n3, &as->parent_keys);
+			ret = btree_split_insert_keys(as, trans, path, n3, &as->parent_keys);
+			if (ret)
+				goto err;
 		}
 	} else {
 		trace_and_count(c, btree_node_compact, trans, b);
@@ -1662,7 +1675,9 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
 		n1 = bch2_btree_node_alloc_replacement(as, trans, b);
 
 		if (keys) {
-			btree_split_insert_keys(as, trans, path, n1, keys);
+			ret = btree_split_insert_keys(as, trans, path, n1, keys);
+			if (ret)
+				goto err;
 			BUG_ON(!bch2_keylist_empty(keys));
 		}
 
@@ -1809,15 +1824,15 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t
 		goto split;
 	}
 
-	ret = bch2_btree_node_check_topology(trans, b);
+
+	ret =   bch2_btree_node_check_topology(trans, b) ?:
+		bch2_btree_insert_keys_interior(as, trans, path, b,
+					path->l[b->c.level].iter, keys);
 	if (ret) {
 		bch2_btree_node_unlock_write(trans, path, b);
 		return ret;
 	}
 
-	bch2_btree_insert_keys_interior(as, trans, path, b,
-					path->l[b->c.level].iter, keys);
-
 	trans_for_each_path_with_node(trans, b, linked, i)
 		bch2_btree_node_iter_peek(&linked->l[b->c.level].iter, b);
 
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index adbe576ec77e..0941fb2c026d 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -428,10 +428,10 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans)
 		 */
 		trace_and_count(c, write_buffer_flush_slowpath, trans, slowpath, wb->flushing.keys.nr);
 
-		sort(wb->flushing.keys.data,
-		     wb->flushing.keys.nr,
-		     sizeof(wb->flushing.keys.data[0]),
-		     wb_key_seq_cmp, NULL);
+		sort_nonatomic(wb->flushing.keys.data,
+			       wb->flushing.keys.nr,
+			       sizeof(wb->flushing.keys.data[0]),
+			       wb_key_seq_cmp, NULL);
 
 		darray_for_each(wb->flushing.keys, i) {
 			if (!i->journal_seq)
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index fea61e60a9ee..31fbc2716d8b 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -37,7 +37,8 @@ void bch2_dev_usage_read_fast(struct bch_dev *ca, struct bch_dev_usage *usage)
 void bch2_dev_usage_full_read_fast(struct bch_dev *ca, struct bch_dev_usage_full *usage)
 {
 	memset(usage, 0, sizeof(*usage));
-	acc_u64s_percpu((u64 *) usage, (u64 __percpu *) ca->usage, dev_usage_u64s());
+	acc_u64s_percpu((u64 *) usage, (u64 __percpu *) ca->usage,
+			sizeof(struct bch_dev_usage_full) / sizeof(u64));
 }
 
 static u64 reserve_factor(u64 r)
@@ -603,6 +604,13 @@ static int bch2_trigger_pointer(struct btree_trans *trans,
 	}
 
 	struct bpos bucket = PTR_BUCKET_POS(ca, &p.ptr);
+	if (!bucket_valid(ca, bucket.offset)) {
+		if (insert) {
+			bch2_dev_bucket_missing(ca, bucket.offset);
+			ret = -BCH_ERR_trigger_pointer;
+		}
+		goto err;
+	}
 
 	if (flags & BTREE_TRIGGER_transactional) {
 		struct bkey_i_alloc_v4 *a = bch2_trans_start_alloc_update(trans, bucket, 0);
@@ -1306,13 +1314,11 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
 	old_bucket_gens = rcu_dereference_protected(ca->bucket_gens, 1);
 
 	if (resize) {
-		bucket_gens->nbuckets = min(bucket_gens->nbuckets,
-					    old_bucket_gens->nbuckets);
-		bucket_gens->nbuckets_minus_first =
-			bucket_gens->nbuckets - bucket_gens->first_bucket;
+		u64 copy = min(bucket_gens->nbuckets,
+			       old_bucket_gens->nbuckets);
 		memcpy(bucket_gens->b,
 		       old_bucket_gens->b,
-		       bucket_gens->nbuckets);
+		       sizeof(bucket_gens->b[0]) * copy);
 	}
 
 	rcu_assign_pointer(ca->bucket_gens, bucket_gens);
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 1c38b165f48b..af1532de4a37 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -44,6 +44,7 @@ static inline void bucket_unlock(struct bucket *b)
 	BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte);
 
 	clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &b->lock);
+	smp_mb__after_atomic();
 	wake_up_bit((void *) &b->lock, BUCKET_LOCK_BITNR);
 }
 
@@ -242,11 +243,6 @@ static inline u64 dev_buckets_available(struct bch_dev *ca,
 
 /* Filesystem usage: */
 
-static inline unsigned dev_usage_u64s(void)
-{
-	return sizeof(struct bch_dev_usage) / sizeof(u64);
-}
-
 struct bch_fs_usage_short
 bch2_fs_usage_read_short(struct bch_fs *);
 
diff --git a/fs/bcachefs/checksum.c b/fs/bcachefs/checksum.c
index 3726689093e3..d0a34a097b80 100644
--- a/fs/bcachefs/checksum.c
+++ b/fs/bcachefs/checksum.c
@@ -7,17 +7,12 @@
 #include "super-io.h"
 
 #include <linux/crc32c.h>
-#include <linux/crypto.h>
 #include <linux/xxhash.h>
 #include <linux/key.h>
 #include <linux/random.h>
 #include <linux/ratelimit.h>
-#include <linux/scatterlist.h>
-#include <crypto/algapi.h>
 #include <crypto/chacha.h>
-#include <crypto/hash.h>
 #include <crypto/poly1305.h>
-#include <crypto/skcipher.h>
 #include <keys/user-type.h>
 
 /*
@@ -96,116 +91,40 @@ static void bch2_checksum_update(struct bch2_checksum_state *state, const void *
 	}
 }
 
-static inline int do_encrypt_sg(struct crypto_sync_skcipher *tfm,
-				struct nonce nonce,
-				struct scatterlist *sg, size_t len)
+static void bch2_chacha20_init(u32 state[CHACHA_STATE_WORDS],
+			       const struct bch_key *key, struct nonce nonce)
 {
-	SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm);
+	u32 key_words[CHACHA_KEY_SIZE / sizeof(u32)];
 
-	skcipher_request_set_sync_tfm(req, tfm);
-	skcipher_request_set_callback(req, 0, NULL, NULL);
-	skcipher_request_set_crypt(req, sg, sg, len, nonce.d);
+	BUILD_BUG_ON(sizeof(key_words) != sizeof(*key));
+	memcpy(key_words, key, sizeof(key_words));
+	le32_to_cpu_array(key_words, ARRAY_SIZE(key_words));
 
-	int ret = crypto_skcipher_encrypt(req);
-	if (ret)
-		pr_err("got error %i from crypto_skcipher_encrypt()", ret);
-
-	return ret;
-}
-
-static inline int do_encrypt(struct crypto_sync_skcipher *tfm,
-			      struct nonce nonce,
-			      void *buf, size_t len)
-{
-	if (!is_vmalloc_addr(buf)) {
-		struct scatterlist sg = {};
-
-		sg_mark_end(&sg);
-		sg_set_page(&sg, virt_to_page(buf), len, offset_in_page(buf));
-		return do_encrypt_sg(tfm, nonce, &sg, len);
-	} else {
-		DARRAY_PREALLOCATED(struct scatterlist, 4) sgl;
-		size_t sgl_len = 0;
-		int ret;
-
-		darray_init(&sgl);
-
-		while (len) {
-			unsigned offset = offset_in_page(buf);
-			struct scatterlist sg = {
-				.page_link	= (unsigned long) vmalloc_to_page(buf),
-				.offset		= offset,
-				.length		= min(len, PAGE_SIZE - offset),
-			};
+	BUILD_BUG_ON(sizeof(nonce) != CHACHA_IV_SIZE);
+	chacha_init(state, key_words, (const u8 *)nonce.d);
 
-			if (darray_push(&sgl, sg)) {
-				sg_mark_end(&darray_last(sgl));
-				ret = do_encrypt_sg(tfm, nonce, sgl.data, sgl_len);
-				if (ret)
-					goto err;
-
-				nonce = nonce_add(nonce, sgl_len);
-				sgl_len = 0;
-				sgl.nr = 0;
-				BUG_ON(darray_push(&sgl, sg));
-			}
-
-			buf += sg.length;
-			len -= sg.length;
-			sgl_len += sg.length;
-		}
-
-		sg_mark_end(&darray_last(sgl));
-		ret = do_encrypt_sg(tfm, nonce, sgl.data, sgl_len);
-err:
-		darray_exit(&sgl);
-		return ret;
-	}
+	memzero_explicit(key_words, sizeof(key_words));
 }
 
-int bch2_chacha_encrypt_key(struct bch_key *key, struct nonce nonce,
-			    void *buf, size_t len)
+static void bch2_chacha20(const struct bch_key *key, struct nonce nonce,
+			  void *data, size_t len)
 {
-	struct crypto_sync_skcipher *chacha20 =
-		crypto_alloc_sync_skcipher("chacha20", 0, 0);
-	int ret;
-
-	ret = PTR_ERR_OR_ZERO(chacha20);
-	if (ret) {
-		pr_err("error requesting chacha20 cipher: %s", bch2_err_str(ret));
-		return ret;
-	}
-
-	ret = crypto_skcipher_setkey(&chacha20->base,
-				     (void *) key, sizeof(*key));
-	if (ret) {
-		pr_err("error from crypto_skcipher_setkey(): %s", bch2_err_str(ret));
-		goto err;
-	}
+	u32 state[CHACHA_STATE_WORDS];
 
-	ret = do_encrypt(chacha20, nonce, buf, len);
-err:
-	crypto_free_sync_skcipher(chacha20);
-	return ret;
+	bch2_chacha20_init(state, key, nonce);
+	chacha20_crypt(state, data, data, len);
+	memzero_explicit(state, sizeof(state));
 }
 
-static int gen_poly_key(struct bch_fs *c, struct shash_desc *desc,
-			struct nonce nonce)
+static void bch2_poly1305_init(struct poly1305_desc_ctx *desc,
+			       struct bch_fs *c, struct nonce nonce)
 {
-	u8 key[POLY1305_KEY_SIZE];
-	int ret;
+	u8 key[POLY1305_KEY_SIZE] = { 0 };
 
 	nonce.d[3] ^= BCH_NONCE_POLY;
 
-	memset(key, 0, sizeof(key));
-	ret = do_encrypt(c->chacha20, nonce, key, sizeof(key));
-	if (ret)
-		return ret;
-
-	desc->tfm = c->poly1305;
-	crypto_shash_init(desc);
-	crypto_shash_update(desc, key, sizeof(key));
-	return 0;
+	bch2_chacha20(&c->chacha20_key, nonce, key, sizeof(key));
+	poly1305_init(desc, key);
 }
 
 struct bch_csum bch2_checksum(struct bch_fs *c, unsigned type,
@@ -230,14 +149,13 @@ struct bch_csum bch2_checksum(struct bch_fs *c, unsigned type,
 
 	case BCH_CSUM_chacha20_poly1305_80:
 	case BCH_CSUM_chacha20_poly1305_128: {
-		SHASH_DESC_ON_STACK(desc, c->poly1305);
+		struct poly1305_desc_ctx dctx;
 		u8 digest[POLY1305_DIGEST_SIZE];
 		struct bch_csum ret = { 0 };
 
-		gen_poly_key(c, desc, nonce);
-
-		crypto_shash_update(desc, data, len);
-		crypto_shash_final(desc, digest);
+		bch2_poly1305_init(&dctx, c, nonce);
+		poly1305_update(&dctx, data, len);
+		poly1305_final(&dctx, digest);
 
 		memcpy(&ret, digest, bch_crc_bytes[type]);
 		return ret;
@@ -253,11 +171,12 @@ int bch2_encrypt(struct bch_fs *c, unsigned type,
 	if (!bch2_csum_type_is_encryption(type))
 		return 0;
 
-	if (bch2_fs_inconsistent_on(!c->chacha20,
+	if (bch2_fs_inconsistent_on(!c->chacha20_key_set,
 				    c, "attempting to encrypt without encryption key"))
 		return -BCH_ERR_no_encryption_key;
 
-	return do_encrypt(c->chacha20, nonce, data, len);
+	bch2_chacha20(&c->chacha20_key, nonce, data, len);
+	return 0;
 }
 
 static struct bch_csum __bch2_checksum_bio(struct bch_fs *c, unsigned type,
@@ -296,26 +215,26 @@ static struct bch_csum __bch2_checksum_bio(struct bch_fs *c, unsigned type,
 
 	case BCH_CSUM_chacha20_poly1305_80:
 	case BCH_CSUM_chacha20_poly1305_128: {
-		SHASH_DESC_ON_STACK(desc, c->poly1305);
+		struct poly1305_desc_ctx dctx;
 		u8 digest[POLY1305_DIGEST_SIZE];
 		struct bch_csum ret = { 0 };
 
-		gen_poly_key(c, desc, nonce);
+		bch2_poly1305_init(&dctx, c, nonce);
 
 #ifdef CONFIG_HIGHMEM
 		__bio_for_each_segment(bv, bio, *iter, *iter) {
 			void *p = kmap_local_page(bv.bv_page) + bv.bv_offset;
 
-			crypto_shash_update(desc, p, bv.bv_len);
+			poly1305_update(&dctx, p, bv.bv_len);
 			kunmap_local(p);
 		}
 #else
 		__bio_for_each_bvec(bv, bio, *iter, *iter)
-			crypto_shash_update(desc,
+			poly1305_update(&dctx,
 				page_address(bv.bv_page) + bv.bv_offset,
 				bv.bv_len);
 #endif
-		crypto_shash_final(desc, digest);
+		poly1305_final(&dctx, digest);
 
 		memcpy(&ret, digest, bch_crc_bytes[type]);
 		return ret;
@@ -338,43 +257,33 @@ int __bch2_encrypt_bio(struct bch_fs *c, unsigned type,
 {
 	struct bio_vec bv;
 	struct bvec_iter iter;
-	DARRAY_PREALLOCATED(struct scatterlist, 4) sgl;
-	size_t sgl_len = 0;
+	u32 chacha_state[CHACHA_STATE_WORDS];
 	int ret = 0;
 
-	if (bch2_fs_inconsistent_on(!c->chacha20,
+	if (bch2_fs_inconsistent_on(!c->chacha20_key_set,
 				    c, "attempting to encrypt without encryption key"))
 		return -BCH_ERR_no_encryption_key;
 
-	darray_init(&sgl);
+	bch2_chacha20_init(chacha_state, &c->chacha20_key, nonce);
 
 	bio_for_each_segment(bv, bio, iter) {
-		struct scatterlist sg = {
-			.page_link	= (unsigned long) bv.bv_page,
-			.offset		= bv.bv_offset,
-			.length		= bv.bv_len,
-		};
-
-		if (darray_push(&sgl, sg)) {
-			sg_mark_end(&darray_last(sgl));
-			ret = do_encrypt_sg(c->chacha20, nonce, sgl.data, sgl_len);
-			if (ret)
-				goto err;
-
-			nonce = nonce_add(nonce, sgl_len);
-			sgl_len = 0;
-			sgl.nr = 0;
-
-			BUG_ON(darray_push(&sgl, sg));
+		void *p;
+
+		/*
+		 * chacha_crypt() assumes that the length is a multiple of
+		 * CHACHA_BLOCK_SIZE on any non-final call.
+		 */
+		if (!IS_ALIGNED(bv.bv_len, CHACHA_BLOCK_SIZE)) {
+			bch_err_ratelimited(c, "bio not aligned for encryption");
+			ret = -EIO;
+			break;
 		}
 
-		sgl_len += sg.length;
+		p = bvec_kmap_local(&bv);
+		chacha20_crypt(chacha_state, p, p, bv.bv_len);
+		kunmap_local(p);
 	}
-
-	sg_mark_end(&darray_last(sgl));
-	ret = do_encrypt_sg(c->chacha20, nonce, sgl.data, sgl_len);
-err:
-	darray_exit(&sgl);
+	memzero_explicit(chacha_state, sizeof(chacha_state));
 	return ret;
 }
 
@@ -650,10 +559,7 @@ int bch2_decrypt_sb_key(struct bch_fs *c,
 	}
 
 	/* decrypt real key: */
-	ret = bch2_chacha_encrypt_key(&user_key, bch2_sb_key_nonce(c),
-				      &sb_key, sizeof(sb_key));
-	if (ret)
-		goto err;
+	bch2_chacha20(&user_key, bch2_sb_key_nonce(c), &sb_key, sizeof(sb_key));
 
 	if (bch2_key_is_encrypted(&sb_key)) {
 		bch_err(c, "incorrect encryption key");
@@ -668,31 +574,6 @@ err:
 	return ret;
 }
 
-static int bch2_alloc_ciphers(struct bch_fs *c)
-{
-	if (c->chacha20)
-		return 0;
-
-	struct crypto_sync_skcipher *chacha20 = crypto_alloc_sync_skcipher("chacha20", 0, 0);
-	int ret = PTR_ERR_OR_ZERO(chacha20);
-	if (ret) {
-		bch_err(c, "error requesting chacha20 module: %s", bch2_err_str(ret));
-		return ret;
-	}
-
-	struct crypto_shash *poly1305 = crypto_alloc_shash("poly1305", 0, 0);
-	ret = PTR_ERR_OR_ZERO(poly1305);
-	if (ret) {
-		bch_err(c, "error requesting poly1305 module: %s", bch2_err_str(ret));
-		crypto_free_sync_skcipher(chacha20);
-		return ret;
-	}
-
-	c->chacha20	= chacha20;
-	c->poly1305	= poly1305;
-	return 0;
-}
-
 #if 0
 
 /*
@@ -797,35 +678,21 @@ err:
 
 void bch2_fs_encryption_exit(struct bch_fs *c)
 {
-	if (c->poly1305)
-		crypto_free_shash(c->poly1305);
-	if (c->chacha20)
-		crypto_free_sync_skcipher(c->chacha20);
+	memzero_explicit(&c->chacha20_key, sizeof(c->chacha20_key));
 }
 
 int bch2_fs_encryption_init(struct bch_fs *c)
 {
 	struct bch_sb_field_crypt *crypt;
-	struct bch_key key;
-	int ret = 0;
+	int ret;
 
 	crypt = bch2_sb_field_get(c->disk_sb.sb, crypt);
 	if (!crypt)
-		goto out;
+		return 0;
 
-	ret = bch2_alloc_ciphers(c);
+	ret = bch2_decrypt_sb_key(c, crypt, &c->chacha20_key);
 	if (ret)
-		goto out;
-
-	ret = bch2_decrypt_sb_key(c, crypt, &key);
-	if (ret)
-		goto out;
-
-	ret = crypto_skcipher_setkey(&c->chacha20->base,
-			(void *) &key.key, sizeof(key.key));
-	if (ret)
-		goto out;
-out:
-	memzero_explicit(&key, sizeof(key));
-	return ret;
+		return ret;
+	c->chacha20_key_set = true;
+	return 0;
 }
diff --git a/fs/bcachefs/checksum.h b/fs/bcachefs/checksum.h
index 4ac251c8fcd8..1310782d3ae9 100644
--- a/fs/bcachefs/checksum.h
+++ b/fs/bcachefs/checksum.h
@@ -69,7 +69,6 @@ static inline void bch2_csum_err_msg(struct printbuf *out,
 	bch2_csum_to_text(out, type, expected);
 }
 
-int bch2_chacha_encrypt_key(struct bch_key *, struct nonce, void *, size_t);
 int bch2_request_key(struct bch_sb *, struct bch_key *);
 #ifndef __KERNEL__
 int bch2_revoke_key(struct bch_sb *);
@@ -156,7 +155,7 @@ static inline bool bch2_checksum_type_valid(const struct bch_fs *c,
 	if (type >= BCH_CSUM_NR)
 		return false;
 
-	if (bch2_csum_type_is_encryption(type) && !c->chacha20)
+	if (bch2_csum_type_is_encryption(type) && !c->chacha20_key_set)
 		return false;
 
 	return true;
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index de02ebf847ec..b211c97238ab 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -607,7 +607,7 @@ void bch2_data_update_inflight_to_text(struct printbuf *out, struct data_update
 	prt_newline(out);
 	printbuf_indent_add(out, 2);
 	bch2_data_update_opts_to_text(out, m->op.c, &m->op.opts, &m->data_opts);
-	prt_printf(out, "read_done:\t\%u\n", m->read_done);
+	prt_printf(out, "read_done:\t%u\n", m->read_done);
 	bch2_write_op_to_text(out, &m->op);
 	printbuf_indent_sub(out, 2);
 }
diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c
index bf53a029f356..8a680e52c1ed 100644
--- a/fs/bcachefs/dirent.c
+++ b/fs/bcachefs/dirent.c
@@ -13,8 +13,8 @@
 
 #include <linux/dcache.h>
 
-static int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info,
-				const struct qstr *str, struct qstr *out_cf)
+int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info,
+		  const struct qstr *str, struct qstr *out_cf)
 {
 	*out_cf = (struct qstr) QSTR_INIT(NULL, 0);
 
@@ -35,18 +35,6 @@ static int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *
 #endif
 }
 
-static inline int bch2_maybe_casefold(struct btree_trans *trans,
-				      const struct bch_hash_info *info,
-				      const struct qstr *str, struct qstr *out_cf)
-{
-	if (likely(!info->cf_encoding)) {
-		*out_cf = *str;
-		return 0;
-	} else {
-		return bch2_casefold(trans, info, str, out_cf);
-	}
-}
-
 static unsigned bch2_dirent_name_bytes(struct bkey_s_c_dirent d)
 {
 	if (bkey_val_bytes(d.k) < offsetof(struct bch_dirent, d_name))
@@ -287,8 +275,8 @@ static void dirent_init_casefolded_name(struct bkey_i_dirent *dirent,
 	EBUG_ON(!dirent->v.d_casefold);
 	EBUG_ON(!cf_name->len);
 
-	dirent->v.d_cf_name_block.d_name_len = name->len;
-	dirent->v.d_cf_name_block.d_cf_name_len = cf_name->len;
+	dirent->v.d_cf_name_block.d_name_len = cpu_to_le16(name->len);
+	dirent->v.d_cf_name_block.d_cf_name_len = cpu_to_le16(cf_name->len);
 	memcpy(&dirent->v.d_cf_name_block.d_names[0], name->name, name->len);
 	memcpy(&dirent->v.d_cf_name_block.d_names[name->len], cf_name->name, cf_name->len);
 	memset(&dirent->v.d_cf_name_block.d_names[name->len + cf_name->len], 0,
@@ -697,7 +685,7 @@ static int bch2_dir_emit(struct dir_context *ctx, struct bkey_s_c_dirent d, subv
 		      vfs_d_type(d.v->d_type));
 	if (ret)
 		ctx->pos = d.k->p.offset + 1;
-	return ret;
+	return !ret;
 }
 
 int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx)
@@ -722,7 +710,7 @@ int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx)
 			if (ret2 > 0)
 				continue;
 
-			ret2 ?: drop_locks_do(trans, bch2_dir_emit(ctx, dirent, target));
+			ret2 ?: (bch2_trans_unlock(trans), bch2_dir_emit(ctx, dirent, target));
 		})));
 
 	bch2_bkey_buf_exit(&sk, c);
diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h
index 0880772b80a9..9838a7ba7ed1 100644
--- a/fs/bcachefs/dirent.h
+++ b/fs/bcachefs/dirent.h
@@ -23,6 +23,21 @@ struct bch_fs;
 struct bch_hash_info;
 struct bch_inode_info;
 
+int bch2_casefold(struct btree_trans *, const struct bch_hash_info *,
+		  const struct qstr *, struct qstr *);
+
+static inline int bch2_maybe_casefold(struct btree_trans *trans,
+				      const struct bch_hash_info *info,
+				      const struct qstr *str, struct qstr *out_cf)
+{
+	if (likely(!info->cf_encoding)) {
+		*out_cf = *str;
+		return 0;
+	} else {
+		return bch2_casefold(trans, info, str, out_cf);
+	}
+}
+
 struct qstr bch2_dirent_get_name(struct bkey_s_c_dirent d);
 
 static inline unsigned dirent_val_u64s(unsigned len, unsigned cf_len)
diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c
index b007319b72e9..1f0422bfae35 100644
--- a/fs/bcachefs/disk_accounting.c
+++ b/fs/bcachefs/disk_accounting.c
@@ -376,6 +376,19 @@ int bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accounting a,
 	return ret;
 }
 
+int bch2_accounting_mem_insert_locked(struct bch_fs *c, struct bkey_s_c_accounting a,
+			       enum bch_accounting_mode mode)
+{
+	struct bch_replicas_padded r;
+
+	if (mode != BCH_ACCOUNTING_read &&
+	    accounting_to_replicas(&r.e, a.k->p) &&
+	    !bch2_replicas_marked_locked(c, &r.e))
+		return -BCH_ERR_btree_insert_need_mark_replicas;
+
+	return __bch2_accounting_mem_insert(c, a);
+}
+
 static bool accounting_mem_entry_is_zero(struct accounting_mem_entry *e)
 {
 	for (unsigned i = 0; i < e->nr_counters; i++)
@@ -583,7 +596,7 @@ int bch2_gc_accounting_done(struct bch_fs *c)
 					accounting_key_init(&k_i.k, &acc_k, src_v, nr);
 					bch2_accounting_mem_mod_locked(trans,
 								bkey_i_to_s_c_accounting(&k_i.k),
-								BCH_ACCOUNTING_normal);
+								BCH_ACCOUNTING_normal, true);
 
 					preempt_disable();
 					struct bch_fs_usage_base *dst = this_cpu_ptr(c->usage);
@@ -612,7 +625,7 @@ static int accounting_read_key(struct btree_trans *trans, struct bkey_s_c k)
 
 	percpu_down_read(&c->mark_lock);
 	int ret = bch2_accounting_mem_mod_locked(trans, bkey_s_c_to_accounting(k),
-						 BCH_ACCOUNTING_read);
+						 BCH_ACCOUNTING_read, false);
 	percpu_up_read(&c->mark_lock);
 	return ret;
 }
diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h
index abb1f6206fe9..d557b99b3c0a 100644
--- a/fs/bcachefs/disk_accounting.h
+++ b/fs/bcachefs/disk_accounting.h
@@ -136,6 +136,7 @@ enum bch_accounting_mode {
 };
 
 int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, enum bch_accounting_mode);
+int bch2_accounting_mem_insert_locked(struct bch_fs *, struct bkey_s_c_accounting, enum bch_accounting_mode);
 void bch2_accounting_mem_gc(struct bch_fs *);
 
 static inline bool bch2_accounting_is_mem(struct disk_accounting_pos acc)
@@ -150,7 +151,8 @@ static inline bool bch2_accounting_is_mem(struct disk_accounting_pos acc)
  */
 static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans,
 						 struct bkey_s_c_accounting a,
-						 enum bch_accounting_mode mode)
+						 enum bch_accounting_mode mode,
+						 bool write_locked)
 {
 	struct bch_fs *c = trans->c;
 	struct bch_accounting_mem *acc = &c->accounting;
@@ -189,7 +191,11 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans,
 
 	while ((idx = eytzinger0_find(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]),
 				      accounting_pos_cmp, &a.k->p)) >= acc->k.nr) {
-		int ret = bch2_accounting_mem_insert(c, a, mode);
+		int ret = 0;
+		if (unlikely(write_locked))
+			ret = bch2_accounting_mem_insert_locked(c, a, mode);
+		else
+			ret = bch2_accounting_mem_insert(c, a, mode);
 		if (ret)
 			return ret;
 	}
@@ -206,7 +212,7 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans,
 static inline int bch2_accounting_mem_add(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc)
 {
 	percpu_down_read(&trans->c->mark_lock);
-	int ret = bch2_accounting_mem_mod_locked(trans, a, gc ? BCH_ACCOUNTING_gc : BCH_ACCOUNTING_normal);
+	int ret = bch2_accounting_mem_mod_locked(trans, a, gc ? BCH_ACCOUNTING_gc : BCH_ACCOUNTING_normal, false);
 	percpu_up_read(&trans->c->mark_lock);
 	return ret;
 }
@@ -259,7 +265,7 @@ static inline int bch2_accounting_trans_commit_hook(struct btree_trans *trans,
 	EBUG_ON(bversion_zero(a->k.bversion));
 
 	return likely(!(commit_flags & BCH_TRANS_COMMIT_skip_accounting_apply))
-		? bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal)
+		? bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal, false)
 		: 0;
 }
 
@@ -271,7 +277,7 @@ static inline void bch2_accounting_trans_commit_revert(struct btree_trans *trans
 		struct bkey_s_accounting a = accounting_i_to_s(a_i);
 
 		bch2_accounting_neg(a);
-		bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal);
+		bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal, false);
 		bch2_accounting_neg(a);
 	}
 }
diff --git a/fs/bcachefs/disk_groups.c b/fs/bcachefs/disk_groups.c
index 1186280b29e9..2ca3cbf12b71 100644
--- a/fs/bcachefs/disk_groups.c
+++ b/fs/bcachefs/disk_groups.c
@@ -470,23 +470,22 @@ inval:
 
 int __bch2_dev_group_set(struct bch_fs *c, struct bch_dev *ca, const char *name)
 {
-	struct bch_member *mi;
-	int ret, v = -1;
+	lockdep_assert_held(&c->sb_lock);
 
-	if (!strlen(name) || !strcmp(name, "none"))
-		return 0;
 
-	v = bch2_disk_path_find_or_create(&c->disk_sb, name);
-	if (v < 0)
-		return v;
+	if (!strlen(name) || !strcmp(name, "none")) {
+		struct bch_member *mi = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx);
+		SET_BCH_MEMBER_GROUP(mi, 0);
+	} else {
+		int v = bch2_disk_path_find_or_create(&c->disk_sb, name);
+		if (v < 0)
+			return v;
 
-	ret = bch2_sb_disk_groups_to_cpu(c);
-	if (ret)
-		return ret;
+		struct bch_member *mi = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx);
+		SET_BCH_MEMBER_GROUP(mi, v + 1);
+	}
 
-	mi = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx);
-	SET_BCH_MEMBER_GROUP(mi, v + 1);
-	return 0;
+	return bch2_sb_disk_groups_to_cpu(c);
 }
 
 int bch2_dev_group_set(struct bch_fs *c, struct bch_dev *ca, const char *name)
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index a396865e8b17..fff58b78327c 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -2204,10 +2204,10 @@ void bch2_fs_ec_stop(struct bch_fs *c)
 
 static bool bch2_fs_ec_flush_done(struct bch_fs *c)
 {
-	bool ret;
+	sched_annotate_sleep();
 
 	mutex_lock(&c->ec_stripe_new_lock);
-	ret = list_empty(&c->ec_stripe_new_list);
+	bool ret = list_empty(&c->ec_stripe_new_list);
 	mutex_unlock(&c->ec_stripe_new_lock);
 
 	return ret;
diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h
index 62d27e04d763..51893e1ee874 100644
--- a/fs/bcachefs/ec.h
+++ b/fs/bcachefs/ec.h
@@ -160,6 +160,7 @@ static inline void gc_stripe_unlock(struct gc_stripe *s)
 	BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte);
 
 	clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &s->lock);
+	smp_mb__after_atomic();
 	wake_up_bit((void *) &s->lock, BUCKET_LOCK_BITNR);
 }
 
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index c8696f01eb14..d9ebffa5b3a2 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -269,7 +269,7 @@
 	x(BCH_ERR_invalid_sb,		invalid_sb_downgrade)			\
 	x(BCH_ERR_invalid,		invalid_bkey)				\
 	x(BCH_ERR_operation_blocked,    nocow_lock_blocked)			\
-	x(EIO,				journal_shutdown)			\
+	x(EROFS,			journal_shutdown)			\
 	x(EIO,				journal_flush_err)			\
 	x(EIO,				journal_write_err)			\
 	x(EIO,				btree_node_read_err)			\
@@ -287,7 +287,7 @@
 	x(EIO,				mark_stripe)				\
 	x(EIO,				stripe_reconstruct)			\
 	x(EIO,				key_type_error)				\
-	x(EIO,				extent_poisened)			\
+	x(EIO,				extent_poisoned)			\
 	x(EIO,				missing_indirect_extent)		\
 	x(EIO,				invalidate_stripe_to_dev)		\
 	x(EIO,				no_encryption_key)			\
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index baf5dfb32298..6b8695b1349c 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -272,9 +272,6 @@ static struct fsck_err_state *fsck_err_get(struct bch_fs *c,
 {
 	struct fsck_err_state *s;
 
-	if (!test_bit(BCH_FS_fsck_running, &c->flags))
-		return NULL;
-
 	list_for_each_entry(s, &c->fsck_error_msgs, list)
 		if (s->id == id) {
 			/*
@@ -481,7 +478,9 @@ int __bch2_fsck_err(struct bch_fs *c,
 	} else if (!test_bit(BCH_FS_fsck_running, &c->flags)) {
 		if (c->opts.errors != BCH_ON_ERROR_continue ||
 		    !(flags & (FSCK_CAN_FIX|FSCK_CAN_IGNORE))) {
-			prt_str(out, ", shutting down");
+			prt_str_indented(out, ", shutting down\n"
+					 "error not marked as autofix and not in fsck\n"
+					 "run fsck, and forward to devs so error can be marked for self-healing");
 			inconsistent = true;
 			print = true;
 			ret = -BCH_ERR_fsck_errors_not_fixed;
@@ -639,14 +638,14 @@ int __bch2_bkey_fsck_err(struct bch_fs *c,
 	return ret;
 }
 
-void bch2_flush_fsck_errs(struct bch_fs *c)
+static void __bch2_flush_fsck_errs(struct bch_fs *c, bool print)
 {
 	struct fsck_err_state *s, *n;
 
 	mutex_lock(&c->fsck_error_msgs_lock);
 
 	list_for_each_entry_safe(s, n, &c->fsck_error_msgs, list) {
-		if (s->ratelimited && s->last_msg)
+		if (print && s->ratelimited && s->last_msg)
 			bch_err(c, "Saw %llu errors like:\n  %s", s->nr, s->last_msg);
 
 		list_del(&s->list);
@@ -657,6 +656,16 @@ void bch2_flush_fsck_errs(struct bch_fs *c)
 	mutex_unlock(&c->fsck_error_msgs_lock);
 }
 
+void bch2_flush_fsck_errs(struct bch_fs *c)
+{
+	__bch2_flush_fsck_errs(c, true);
+}
+
+void bch2_free_fsck_errs(struct bch_fs *c)
+{
+	__bch2_flush_fsck_errs(c, false);
+}
+
 int bch2_inum_offset_err_msg_trans(struct btree_trans *trans, struct printbuf *out,
 				    subvol_inum inum, u64 offset)
 {
diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h
index d0d024dc714b..4a364fd44abe 100644
--- a/fs/bcachefs/error.h
+++ b/fs/bcachefs/error.h
@@ -93,6 +93,7 @@ int __bch2_fsck_err(struct bch_fs *, struct btree_trans *,
 			_flags, BCH_FSCK_ERR_##_err_type, __VA_ARGS__)
 
 void bch2_flush_fsck_errs(struct bch_fs *);
+void bch2_free_fsck_errs(struct bch_fs *);
 
 #define fsck_err_wrap(_do)						\
 ({									\
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index ae7c7a177e10..e597fb9c9823 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -139,7 +139,7 @@ int bch2_bkey_pick_read_device(struct bch_fs *c, struct bkey_s_c k,
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
 
 	if (bch2_bkey_extent_ptrs_flags(ptrs) & BIT_ULL(BCH_EXTENT_FLAG_poisoned))
-		return -BCH_ERR_extent_poisened;
+		return -BCH_ERR_extent_poisoned;
 
 	rcu_read_lock();
 	const union bch_extent_entry *entry;
@@ -1056,8 +1056,9 @@ bch2_extent_has_ptr(struct bkey_s_c k1, struct extent_ptr_decoded p1, struct bke
 static bool want_cached_ptr(struct bch_fs *c, struct bch_io_opts *opts,
 			    struct bch_extent_ptr *ptr)
 {
-	if (!opts->promote_target ||
-	    !bch2_dev_in_target(c, ptr->dev, opts->promote_target))
+	unsigned target = opts->promote_target ?: opts->foreground_target;
+
+	if (target && !bch2_dev_in_target(c, ptr->dev, target))
 		return false;
 
 	struct bch_dev *ca = bch2_dev_rcu_noerror(c, ptr->dev);
diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index 19d4599918dc..e3a75dcca60c 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -225,11 +225,26 @@ static void bchfs_read(struct btree_trans *trans,
 
 		bch2_read_extent(trans, rbio, iter.pos,
 				 data_btree, k, offset_into_extent, flags);
-		swap(rbio->bio.bi_iter.bi_size, bytes);
+		/*
+		 * Careful there's a landmine here if bch2_read_extent() ever
+		 * starts returning transaction restarts here.
+		 *
+		 * We've changed rbio->bi_iter.bi_size to be "bytes we can read
+		 * from this extent" with the swap call, and we restore it
+		 * below. That restore needs to come before checking for
+		 * errors.
+		 *
+		 * But unlike __bch2_read(), we use the rbio bvec iter, not one
+		 * on the stack, so we can't do the restore right after the
+		 * bch2_read_extent() call: we don't own that iterator anymore
+		 * if BCH_READ_last_fragment is set, since we may have submitted
+		 * that rbio instead of cloning it.
+		 */
 
 		if (flags & BCH_READ_last_fragment)
 			break;
 
+		swap(rbio->bio.bi_iter.bi_size, bytes);
 		bio_advance(&rbio->bio, bytes);
 err:
 		if (ret &&
diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index 65c2c33d253d..9657144666b8 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -144,10 +144,25 @@ int __must_check bch2_write_inode_size(struct bch_fs *c,
 void __bch2_i_sectors_acct(struct bch_fs *c, struct bch_inode_info *inode,
 			   struct quota_res *quota_res, s64 sectors)
 {
-	bch2_fs_inconsistent_on((s64) inode->v.i_blocks + sectors < 0, c,
-				"inode %lu i_blocks underflow: %llu + %lli < 0 (ondisk %lli)",
-				inode->v.i_ino, (u64) inode->v.i_blocks, sectors,
-				inode->ei_inode.bi_sectors);
+	if (unlikely((s64) inode->v.i_blocks + sectors < 0)) {
+		struct printbuf buf = PRINTBUF;
+		bch2_log_msg_start(c, &buf);
+		prt_printf(&buf, "inode %lu i_blocks underflow: %llu + %lli < 0 (ondisk %lli)",
+			   inode->v.i_ino, (u64) inode->v.i_blocks, sectors,
+			   inode->ei_inode.bi_sectors);
+
+		bool repeat = false, print = false, suppress = false;
+		bch2_count_fsck_err(c, vfs_inode_i_blocks_underflow, buf.buf, &repeat, &print, &suppress);
+		if (print)
+			bch2_print_str(c, buf.buf);
+		printbuf_exit(&buf);
+
+		if (sectors < 0)
+			sectors = -inode->v.i_blocks;
+		else
+			sectors = 0;
+	}
+
 	inode->v.i_blocks += sectors;
 
 #ifdef CONFIG_BCACHEFS_QUOTA
@@ -502,11 +517,22 @@ int bchfs_truncate(struct mnt_idmap *idmap,
 		goto err;
 	}
 
-	bch2_fs_inconsistent_on(!inode->v.i_size && inode->v.i_blocks &&
-				!bch2_journal_error(&c->journal), c,
-				"inode %lu truncated to 0 but i_blocks %llu (ondisk %lli)",
-				inode->v.i_ino, (u64) inode->v.i_blocks,
-				inode->ei_inode.bi_sectors);
+	if (unlikely(!inode->v.i_size && inode->v.i_blocks &&
+		     !bch2_journal_error(&c->journal))) {
+		struct printbuf buf = PRINTBUF;
+		bch2_log_msg_start(c, &buf);
+		prt_printf(&buf,
+			   "inode %lu truncated to 0 but i_blocks %llu (ondisk %lli)",
+			   inode->v.i_ino, (u64) inode->v.i_blocks,
+			   inode->ei_inode.bi_sectors);
+
+		bool repeat = false, print = false, suppress = false;
+		bch2_count_fsck_err(c, vfs_inode_i_blocks_not_zero_at_truncate, buf.buf,
+				    &repeat, &print, &suppress);
+		if (print)
+			bch2_print_str(c, buf.buf);
+		printbuf_exit(&buf);
+	}
 
 	ret = bch2_setattr_nonsize(idmap, inode, iattr);
 err:
diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index c1553e44e049..a82dfce9e4ad 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -21,206 +21,6 @@
 #define FSOP_GOING_FLAGS_LOGFLUSH	0x1	/* flush log but not data */
 #define FSOP_GOING_FLAGS_NOLOGFLUSH	0x2	/* don't flush log nor data */
 
-struct flags_set {
-	unsigned		mask;
-	unsigned		flags;
-
-	unsigned		projid;
-
-	bool			set_projinherit;
-	bool			projinherit;
-};
-
-static int bch2_inode_flags_set(struct btree_trans *trans,
-				struct bch_inode_info *inode,
-				struct bch_inode_unpacked *bi,
-				void *p)
-{
-	struct bch_fs *c = inode->v.i_sb->s_fs_info;
-	/*
-	 * We're relying on btree locking here for exclusion with other ioctl
-	 * calls - use the flags in the btree (@bi), not inode->i_flags:
-	 */
-	struct flags_set *s = p;
-	unsigned newflags = s->flags;
-	unsigned oldflags = bi->bi_flags & s->mask;
-
-	if (((newflags ^ oldflags) & (BCH_INODE_append|BCH_INODE_immutable)) &&
-	    !capable(CAP_LINUX_IMMUTABLE))
-		return -EPERM;
-
-	if (!S_ISREG(bi->bi_mode) &&
-	    !S_ISDIR(bi->bi_mode) &&
-	    (newflags & (BCH_INODE_nodump|BCH_INODE_noatime)) != newflags)
-		return -EINVAL;
-
-	if ((newflags ^ oldflags) & BCH_INODE_casefolded) {
-#ifdef CONFIG_UNICODE
-		int ret = 0;
-		/* Not supported on individual files. */
-		if (!S_ISDIR(bi->bi_mode))
-			return -EOPNOTSUPP;
-
-		/*
-		 * Make sure the dir is empty, as otherwise we'd need to
-		 * rehash everything and update the dirent keys.
-		 */
-		ret = bch2_empty_dir_trans(trans, inode_inum(inode));
-		if (ret < 0)
-			return ret;
-
-		ret = bch2_request_incompat_feature(c,bcachefs_metadata_version_casefolding);
-		if (ret)
-			return ret;
-
-		bch2_check_set_feature(c, BCH_FEATURE_casefolding);
-#else
-		printk(KERN_ERR "Cannot use casefolding on a kernel without CONFIG_UNICODE\n");
-		return -EOPNOTSUPP;
-#endif
-	}
-
-	if (s->set_projinherit) {
-		bi->bi_fields_set &= ~(1 << Inode_opt_project);
-		bi->bi_fields_set |= ((int) s->projinherit << Inode_opt_project);
-	}
-
-	bi->bi_flags &= ~s->mask;
-	bi->bi_flags |= newflags;
-
-	bi->bi_ctime = timespec_to_bch2_time(c, current_time(&inode->v));
-	return 0;
-}
-
-static int bch2_ioc_getflags(struct bch_inode_info *inode, int __user *arg)
-{
-	unsigned flags = map_flags(bch_flags_to_uflags, inode->ei_inode.bi_flags);
-
-	return put_user(flags, arg);
-}
-
-static int bch2_ioc_setflags(struct bch_fs *c,
-			     struct file *file,
-			     struct bch_inode_info *inode,
-			     void __user *arg)
-{
-	struct flags_set s = { .mask = map_defined(bch_flags_to_uflags) };
-	unsigned uflags;
-	int ret;
-
-	if (get_user(uflags, (int __user *) arg))
-		return -EFAULT;
-
-	s.flags = map_flags_rev(bch_flags_to_uflags, uflags);
-	if (uflags)
-		return -EOPNOTSUPP;
-
-	ret = mnt_want_write_file(file);
-	if (ret)
-		return ret;
-
-	inode_lock(&inode->v);
-	if (!inode_owner_or_capable(file_mnt_idmap(file), &inode->v)) {
-		ret = -EACCES;
-		goto setflags_out;
-	}
-
-	mutex_lock(&inode->ei_update_lock);
-	ret   = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
-		bch2_write_inode(c, inode, bch2_inode_flags_set, &s,
-			       ATTR_CTIME);
-	mutex_unlock(&inode->ei_update_lock);
-
-setflags_out:
-	inode_unlock(&inode->v);
-	mnt_drop_write_file(file);
-	return ret;
-}
-
-static int bch2_ioc_fsgetxattr(struct bch_inode_info *inode,
-			       struct fsxattr __user *arg)
-{
-	struct fsxattr fa = { 0 };
-
-	fa.fsx_xflags = map_flags(bch_flags_to_xflags, inode->ei_inode.bi_flags);
-
-	if (inode->ei_inode.bi_fields_set & (1 << Inode_opt_project))
-		fa.fsx_xflags |= FS_XFLAG_PROJINHERIT;
-
-	fa.fsx_projid = inode->ei_qid.q[QTYP_PRJ];
-
-	if (copy_to_user(arg, &fa, sizeof(fa)))
-		return -EFAULT;
-
-	return 0;
-}
-
-static int fssetxattr_inode_update_fn(struct btree_trans *trans,
-				      struct bch_inode_info *inode,
-				      struct bch_inode_unpacked *bi,
-				      void *p)
-{
-	struct flags_set *s = p;
-
-	if (s->projid != bi->bi_project) {
-		bi->bi_fields_set |= 1U << Inode_opt_project;
-		bi->bi_project = s->projid;
-	}
-
-	return bch2_inode_flags_set(trans, inode, bi, p);
-}
-
-static int bch2_ioc_fssetxattr(struct bch_fs *c,
-			       struct file *file,
-			       struct bch_inode_info *inode,
-			       struct fsxattr __user *arg)
-{
-	struct flags_set s = { .mask = map_defined(bch_flags_to_xflags) };
-	struct fsxattr fa;
-	int ret;
-
-	if (copy_from_user(&fa, arg, sizeof(fa)))
-		return -EFAULT;
-
-	s.set_projinherit = true;
-	s.projinherit = (fa.fsx_xflags & FS_XFLAG_PROJINHERIT) != 0;
-	fa.fsx_xflags &= ~FS_XFLAG_PROJINHERIT;
-
-	s.flags = map_flags_rev(bch_flags_to_xflags, fa.fsx_xflags);
-	if (fa.fsx_xflags)
-		return -EOPNOTSUPP;
-
-	if (fa.fsx_projid >= U32_MAX)
-		return -EINVAL;
-
-	/*
-	 * inode fields accessible via the xattr interface are stored with a +1
-	 * bias, so that 0 means unset:
-	 */
-	s.projid = fa.fsx_projid + 1;
-
-	ret = mnt_want_write_file(file);
-	if (ret)
-		return ret;
-
-	inode_lock(&inode->v);
-	if (!inode_owner_or_capable(file_mnt_idmap(file), &inode->v)) {
-		ret = -EACCES;
-		goto err;
-	}
-
-	mutex_lock(&inode->ei_update_lock);
-	ret   = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
-		bch2_set_projid(c, inode, fa.fsx_projid) ?:
-		bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s,
-			       ATTR_CTIME);
-	mutex_unlock(&inode->ei_update_lock);
-err:
-	inode_unlock(&inode->v);
-	mnt_drop_write_file(file);
-	return ret;
-}
-
 static int bch2_reinherit_attrs_fn(struct btree_trans *trans,
 				   struct bch_inode_info *inode,
 				   struct bch_inode_unpacked *bi,
@@ -558,23 +358,6 @@ long bch2_fs_file_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	long ret;
 
 	switch (cmd) {
-	case FS_IOC_GETFLAGS:
-		ret = bch2_ioc_getflags(inode, (int __user *) arg);
-		break;
-
-	case FS_IOC_SETFLAGS:
-		ret = bch2_ioc_setflags(c, file, inode, (int __user *) arg);
-		break;
-
-	case FS_IOC_FSGETXATTR:
-		ret = bch2_ioc_fsgetxattr(inode, (void __user *) arg);
-		break;
-
-	case FS_IOC_FSSETXATTR:
-		ret = bch2_ioc_fssetxattr(c, file, inode,
-					  (void __user *) arg);
-		break;
-
 	case BCHFS_IOC_REINHERIT_ATTRS:
 		ret = bch2_ioc_reinherit_attrs(c, file, inode,
 					       (void __user *) arg);
diff --git a/fs/bcachefs/fs-ioctl.h b/fs/bcachefs/fs-ioctl.h
index ecd3bfdcde21..a657e4994b71 100644
--- a/fs/bcachefs/fs-ioctl.h
+++ b/fs/bcachefs/fs-ioctl.h
@@ -2,81 +2,6 @@
 #ifndef _BCACHEFS_FS_IOCTL_H
 #define _BCACHEFS_FS_IOCTL_H
 
-/* Inode flags: */
-
-/* bcachefs inode flags -> vfs inode flags: */
-static const __maybe_unused unsigned bch_flags_to_vfs[] = {
-	[__BCH_INODE_sync]		= S_SYNC,
-	[__BCH_INODE_immutable]		= S_IMMUTABLE,
-	[__BCH_INODE_append]		= S_APPEND,
-	[__BCH_INODE_noatime]		= S_NOATIME,
-	[__BCH_INODE_casefolded]	= S_CASEFOLD,
-};
-
-/* bcachefs inode flags -> FS_IOC_GETFLAGS: */
-static const __maybe_unused unsigned bch_flags_to_uflags[] = {
-	[__BCH_INODE_sync]		= FS_SYNC_FL,
-	[__BCH_INODE_immutable]		= FS_IMMUTABLE_FL,
-	[__BCH_INODE_append]		= FS_APPEND_FL,
-	[__BCH_INODE_nodump]		= FS_NODUMP_FL,
-	[__BCH_INODE_noatime]		= FS_NOATIME_FL,
-	[__BCH_INODE_casefolded]	= FS_CASEFOLD_FL,
-};
-
-/* bcachefs inode flags -> FS_IOC_FSGETXATTR: */
-static const __maybe_unused unsigned bch_flags_to_xflags[] = {
-	[__BCH_INODE_sync]	= FS_XFLAG_SYNC,
-	[__BCH_INODE_immutable]	= FS_XFLAG_IMMUTABLE,
-	[__BCH_INODE_append]	= FS_XFLAG_APPEND,
-	[__BCH_INODE_nodump]	= FS_XFLAG_NODUMP,
-	[__BCH_INODE_noatime]	= FS_XFLAG_NOATIME,
-	//[__BCH_INODE_PROJINHERIT] = FS_XFLAG_PROJINHERIT;
-};
-
-#define set_flags(_map, _in, _out)					\
-do {									\
-	unsigned _i;							\
-									\
-	for (_i = 0; _i < ARRAY_SIZE(_map); _i++)			\
-		if ((_in) & (1 << _i))					\
-			(_out) |= _map[_i];				\
-		else							\
-			(_out) &= ~_map[_i];				\
-} while (0)
-
-#define map_flags(_map, _in)						\
-({									\
-	unsigned _out = 0;						\
-									\
-	set_flags(_map, _in, _out);					\
-	_out;								\
-})
-
-#define map_flags_rev(_map, _in)					\
-({									\
-	unsigned _i, _out = 0;						\
-									\
-	for (_i = 0; _i < ARRAY_SIZE(_map); _i++)			\
-		if ((_in) & _map[_i]) {					\
-			(_out) |= 1 << _i;				\
-			(_in) &= ~_map[_i];				\
-		}							\
-	(_out);								\
-})
-
-#define map_defined(_map)						\
-({									\
-	unsigned _in = ~0;						\
-									\
-	map_flags_rev(_map, _in);					\
-})
-
-/* Set VFS inode flags from bcachefs inode: */
-static inline void bch2_inode_flags_to_vfs(struct bch_inode_info *inode)
-{
-	set_flags(bch_flags_to_vfs, inode->ei_inode.bi_flags, inode->v.i_flags);
-}
-
 long bch2_fs_file_ioctl(struct file *, unsigned, unsigned long);
 long bch2_compat_fs_ioctl(struct file *, unsigned, unsigned long);
 
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 5a41b1a8e54f..4b742e62255b 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -33,6 +33,7 @@
 #include <linux/backing-dev.h>
 #include <linux/exportfs.h>
 #include <linux/fiemap.h>
+#include <linux/fileattr.h>
 #include <linux/fs_context.h>
 #include <linux/module.h>
 #include <linux/pagemap.h>
@@ -51,6 +52,24 @@ static void bch2_vfs_inode_init(struct btree_trans *, subvol_inum,
 				struct bch_inode_unpacked *,
 				struct bch_subvolume *);
 
+/* Set VFS inode flags from bcachefs inode: */
+static inline void bch2_inode_flags_to_vfs(struct bch_fs *c, struct bch_inode_info *inode)
+{
+	static const __maybe_unused unsigned bch_flags_to_vfs[] = {
+		[__BCH_INODE_sync]		= S_SYNC,
+		[__BCH_INODE_immutable]		= S_IMMUTABLE,
+		[__BCH_INODE_append]		= S_APPEND,
+		[__BCH_INODE_noatime]		= S_NOATIME,
+	};
+
+	set_flags(bch_flags_to_vfs, inode->ei_inode.bi_flags, inode->v.i_flags);
+
+	if (bch2_inode_casefold(c, &inode->ei_inode))
+		inode->v.i_flags |= S_CASEFOLD;
+	else
+		inode->v.i_flags &= ~S_CASEFOLD;
+}
+
 void bch2_inode_update_after_write(struct btree_trans *trans,
 				   struct bch_inode_info *inode,
 				   struct bch_inode_unpacked *bi,
@@ -79,7 +98,7 @@ void bch2_inode_update_after_write(struct btree_trans *trans,
 
 	inode->ei_inode		= *bi;
 
-	bch2_inode_flags_to_vfs(inode);
+	bch2_inode_flags_to_vfs(c, inode);
 }
 
 int __must_check bch2_write_inode(struct bch_fs *c,
@@ -631,13 +650,18 @@ static struct bch_inode_info *bch2_lookup_trans(struct btree_trans *trans,
 			const struct qstr *name)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_iter dirent_iter = {};
 	subvol_inum inum = {};
 	struct printbuf buf = PRINTBUF;
 
+	struct qstr lookup_name;
+	int ret = bch2_maybe_casefold(trans, dir_hash_info, name, &lookup_name);
+	if (ret)
+		return ERR_PTR(ret);
+
+	struct btree_iter dirent_iter = {};
 	struct bkey_s_c k = bch2_hash_lookup(trans, &dirent_iter, bch2_dirent_hash_desc,
-					     dir_hash_info, dir, name, 0);
-	int ret = bkey_err(k);
+					     dir_hash_info, dir, &lookup_name, 0);
+	ret = bkey_err(k);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -825,6 +849,9 @@ int __bch2_unlink(struct inode *vdir, struct dentry *dentry,
 		 */
 		set_nlink(&inode->v, 0);
 	}
+
+	if (IS_CASEFOLDED(vdir))
+		d_invalidate(dentry);
 err:
 	bch2_trans_put(trans);
 	bch2_unlock_inodes(INODE_UPDATE_LOCK, dir, inode);
@@ -1235,10 +1262,20 @@ static int bch2_tmpfile(struct mnt_idmap *idmap,
 	return finish_open_simple(file, 0);
 }
 
+struct bch_fiemap_extent {
+	struct bkey_buf	kbuf;
+	unsigned	flags;
+};
+
 static int bch2_fill_extent(struct bch_fs *c,
 			    struct fiemap_extent_info *info,
-			    struct bkey_s_c k, unsigned flags)
+			    struct bch_fiemap_extent *fe)
 {
+	struct bkey_s_c k = bkey_i_to_s_c(fe->kbuf.k);
+	unsigned flags = fe->flags;
+
+	BUG_ON(!k.k->size);
+
 	if (bkey_extent_is_direct_data(k.k)) {
 		struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
 		const union bch_extent_entry *entry;
@@ -1291,110 +1328,225 @@ static int bch2_fill_extent(struct bch_fs *c,
 	}
 }
 
-static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info,
-		       u64 start, u64 len)
+/*
+ * Scan a range of an inode for data in pagecache.
+ *
+ * Intended to be retryable, so don't modify the output params until success is
+ * imminent.
+ */
+static int
+bch2_fiemap_hole_pagecache(struct inode *vinode, u64 *start, u64 *end,
+			   bool nonblock)
 {
-	struct bch_fs *c = vinode->i_sb->s_fs_info;
-	struct bch_inode_info *ei = to_bch_ei(vinode);
-	struct btree_trans *trans;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bkey_buf cur, prev;
-	bool have_extent = false;
-	int ret = 0;
+	loff_t	dstart, dend;
 
-	ret = fiemap_prep(&ei->v, info, start, &len, FIEMAP_FLAG_SYNC);
-	if (ret)
+	dstart = bch2_seek_pagecache_data(vinode, *start, *end, 0, nonblock);
+	if (dstart < 0)
+		return dstart;
+
+	if (dstart == *end) {
+		*start = dstart;
+		return 0;
+	}
+
+	dend = bch2_seek_pagecache_hole(vinode, dstart, *end, 0, nonblock);
+	if (dend < 0)
+		return dend;
+
+	/* race */
+	BUG_ON(dstart == dend);
+
+	*start = dstart;
+	*end = dend;
+	return 0;
+}
+
+/*
+ * Scan a range of pagecache that corresponds to a file mapping hole in the
+ * extent btree. If data is found, fake up an extent key so it looks like a
+ * delalloc extent to the rest of the fiemap processing code.
+ */
+static int
+bch2_next_fiemap_pagecache_extent(struct btree_trans *trans, struct bch_inode_info *inode,
+				  u64 start, u64 end, struct bch_fiemap_extent *cur)
+{
+	struct bch_fs		*c = trans->c;
+	struct bkey_i_extent	*delextent;
+	struct bch_extent_ptr	ptr = {};
+	loff_t			dstart = start << 9, dend = end << 9;
+	int			ret;
+
+	/*
+	 * We hold btree locks here so we cannot block on folio locks without
+	 * dropping trans locks first. Run a nonblocking scan for the common
+	 * case of no folios over holes and fall back on failure.
+	 *
+	 * Note that dropping locks like this is technically racy against
+	 * writeback inserting to the extent tree, but a non-sync fiemap scan is
+	 * fundamentally racy with writeback anyways. Therefore, just report the
+	 * range as delalloc regardless of whether we have to cycle trans locks.
+	 */
+	ret = bch2_fiemap_hole_pagecache(&inode->v, &dstart, &dend, true);
+	if (ret == -EAGAIN)
+		ret = drop_locks_do(trans,
+			bch2_fiemap_hole_pagecache(&inode->v, &dstart, &dend, false));
+	if (ret < 0)
 		return ret;
 
-	struct bpos end = POS(ei->v.i_ino, (start + len) >> 9);
-	if (start + len < start)
-		return -EINVAL;
+	/*
+	 * Create a fake extent key in the buffer. We have to add a dummy extent
+	 * pointer for the fill code to add an extent entry. It's explicitly
+	 * zeroed to reflect delayed allocation (i.e. phys offset 0).
+	 */
+	bch2_bkey_buf_realloc(&cur->kbuf, c, sizeof(*delextent) / sizeof(u64));
+	delextent = bkey_extent_init(cur->kbuf.k);
+	delextent->k.p = POS(inode->ei_inum.inum, dend >> 9);
+	delextent->k.size = (dend - dstart) >> 9;
+	bch2_bkey_append_ptr(&delextent->k_i, ptr);
 
-	start >>= 9;
+	cur->flags = FIEMAP_EXTENT_DELALLOC;
 
-	bch2_bkey_buf_init(&cur);
-	bch2_bkey_buf_init(&prev);
-	trans = bch2_trans_get(c);
+	return 0;
+}
+
+static int bch2_next_fiemap_extent(struct btree_trans *trans,
+				   struct bch_inode_info *inode,
+				   u64 start, u64 end,
+				   struct bch_fiemap_extent *cur)
+{
+	u32 snapshot;
+	int ret = bch2_subvolume_get_snapshot(trans, inode->ei_inum.subvol, &snapshot);
+	if (ret)
+		return ret;
 
+	struct btree_iter iter;
 	bch2_trans_iter_init(trans, &iter, BTREE_ID_extents,
-			     POS(ei->v.i_ino, start), 0);
+			     SPOS(inode->ei_inum.inum, start, snapshot), 0);
 
-	while (!ret || bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
-		enum btree_id data_btree = BTREE_ID_extents;
+	struct bkey_s_c k =
+		bch2_btree_iter_peek_max(trans, &iter, POS(inode->ei_inum.inum, end));
+	ret = bkey_err(k);
+	if (ret)
+		goto err;
 
-		bch2_trans_begin(trans);
+	u64 pagecache_end = k.k ? max(start, bkey_start_offset(k.k)) : end;
 
-		u32 snapshot;
-		ret = bch2_subvolume_get_snapshot(trans, ei->ei_inum.subvol, &snapshot);
-		if (ret)
-			continue;
+	ret = bch2_next_fiemap_pagecache_extent(trans, inode, start, pagecache_end, cur);
+	if (ret)
+		goto err;
 
-		bch2_btree_iter_set_snapshot(trans, &iter, snapshot);
+	struct bpos pagecache_start = bkey_start_pos(&cur->kbuf.k->k);
 
-		k = bch2_btree_iter_peek_max(trans, &iter, end);
-		ret = bkey_err(k);
+	/*
+	 * Does the pagecache or the btree take precedence?
+	 *
+	 * It _should_ be the pagecache, so that we correctly report delalloc
+	 * extents when dirty in the pagecache (we're COW, after all).
+	 *
+	 * But we'd have to add per-sector writeback tracking to
+	 * bch_folio_state, otherwise we report delalloc extents for clean
+	 * cached data in the pagecache.
+	 *
+	 * We should do this, but even then fiemap won't report stable mappings:
+	 * on bcachefs data moves around in the background (copygc, rebalance)
+	 * and we don't provide a way for userspace to lock that out.
+	 */
+	if (k.k &&
+	    bkey_le(bpos_max(iter.pos, bkey_start_pos(k.k)),
+		    pagecache_start)) {
+		bch2_bkey_buf_reassemble(&cur->kbuf, trans->c, k);
+		bch2_cut_front(iter.pos, cur->kbuf.k);
+		bch2_cut_back(POS(inode->ei_inum.inum, end), cur->kbuf.k);
+		cur->flags = 0;
+	} else if (k.k) {
+		bch2_cut_back(bkey_start_pos(k.k), cur->kbuf.k);
+	}
+
+	if (cur->kbuf.k->k.type == KEY_TYPE_reflink_p) {
+		unsigned sectors = cur->kbuf.k->k.size;
+		s64 offset_into_extent = 0;
+		enum btree_id data_btree = BTREE_ID_extents;
+		ret = bch2_read_indirect_extent(trans, &data_btree, &offset_into_extent,
+						&cur->kbuf);
 		if (ret)
-			continue;
+			goto err;
 
-		if (!k.k)
-			break;
+		struct bkey_i *k = cur->kbuf.k;
+		sectors = min_t(unsigned, sectors, k->k.size - offset_into_extent);
 
-		if (!bkey_extent_is_data(k.k) &&
-		    k.k->type != KEY_TYPE_reservation) {
-			bch2_btree_iter_advance(trans, &iter);
-			continue;
-		}
+		bch2_cut_front(POS(k->k.p.inode,
+				   bkey_start_offset(&k->k) + offset_into_extent),
+			       k);
+		bch2_key_resize(&k->k, sectors);
+		k->k.p = iter.pos;
+		k->k.p.offset += k->k.size;
+	}
+err:
+	bch2_trans_iter_exit(trans, &iter);
+	return ret;
+}
+
+static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info,
+		       u64 start, u64 len)
+{
+	struct bch_fs *c = vinode->i_sb->s_fs_info;
+	struct bch_inode_info *ei = to_bch_ei(vinode);
+	struct btree_trans *trans;
+	struct bch_fiemap_extent cur, prev;
+	int ret = 0;
+
+	ret = fiemap_prep(&ei->v, info, start, &len, 0);
+	if (ret)
+		return ret;
+
+	if (start + len < start)
+		return -EINVAL;
+
+	start >>= 9;
+	u64 end = (start + len) >> 9;
 
-		s64 offset_into_extent	= iter.pos.offset - bkey_start_offset(k.k);
-		unsigned sectors	= k.k->size - offset_into_extent;
+	bch2_bkey_buf_init(&cur.kbuf);
+	bch2_bkey_buf_init(&prev.kbuf);
+	bkey_init(&prev.kbuf.k->k);
 
-		bch2_bkey_buf_reassemble(&cur, c, k);
+	trans = bch2_trans_get(c);
 
-		ret = bch2_read_indirect_extent(trans, &data_btree,
-					&offset_into_extent, &cur);
+	while (start < end) {
+		ret = lockrestart_do(trans,
+			bch2_next_fiemap_extent(trans, ei, start, end, &cur));
 		if (ret)
-			continue;
+			goto err;
 
-		k = bkey_i_to_s_c(cur.k);
-		bch2_bkey_buf_realloc(&prev, c, k.k->u64s);
+		BUG_ON(bkey_start_offset(&cur.kbuf.k->k) < start);
+		BUG_ON(cur.kbuf.k->k.p.offset > end);
 
-		sectors = min_t(unsigned, sectors, k.k->size - offset_into_extent);
+		if (bkey_start_offset(&cur.kbuf.k->k) == end)
+			break;
 
-		bch2_cut_front(POS(k.k->p.inode,
-				   bkey_start_offset(k.k) +
-				   offset_into_extent),
-			       cur.k);
-		bch2_key_resize(&cur.k->k, sectors);
-		cur.k->k.p = iter.pos;
-		cur.k->k.p.offset += cur.k->k.size;
+		start = cur.kbuf.k->k.p.offset;
 
-		if (have_extent) {
+		if (!bkey_deleted(&prev.kbuf.k->k)) {
 			bch2_trans_unlock(trans);
-			ret = bch2_fill_extent(c, info,
-					bkey_i_to_s_c(prev.k), 0);
+			ret = bch2_fill_extent(c, info, &prev);
 			if (ret)
-				break;
+				goto err;
 		}
 
-		bkey_copy(prev.k, cur.k);
-		have_extent = true;
-
-		bch2_btree_iter_set_pos(trans, &iter,
-			POS(iter.pos.inode, iter.pos.offset + sectors));
+		bch2_bkey_buf_copy(&prev.kbuf, c, cur.kbuf.k);
+		prev.flags = cur.flags;
 	}
-	bch2_trans_iter_exit(trans, &iter);
 
-	if (!ret && have_extent) {
+	if (!bkey_deleted(&prev.kbuf.k->k)) {
 		bch2_trans_unlock(trans);
-		ret = bch2_fill_extent(c, info, bkey_i_to_s_c(prev.k),
-				       FIEMAP_EXTENT_LAST);
+		prev.flags |= FIEMAP_EXTENT_LAST;
+		ret = bch2_fill_extent(c, info, &prev);
 	}
-
+err:
 	bch2_trans_put(trans);
-	bch2_bkey_buf_exit(&cur, c);
-	bch2_bkey_buf_exit(&prev, c);
-	return ret < 0 ? ret : 0;
+	bch2_bkey_buf_exit(&cur.kbuf, c);
+	bch2_bkey_buf_exit(&prev.kbuf, c);
+
+	return bch2_err_class(ret < 0 ? ret : 0);
 }
 
 static const struct vm_operations_struct bch_vm_ops = {
@@ -1449,6 +1601,165 @@ static int bch2_open(struct inode *vinode, struct file *file)
 	return generic_file_open(vinode, file);
 }
 
+/* bcachefs inode flags -> FS_IOC_GETFLAGS: */
+static const __maybe_unused unsigned bch_flags_to_uflags[] = {
+	[__BCH_INODE_sync]		= FS_SYNC_FL,
+	[__BCH_INODE_immutable]		= FS_IMMUTABLE_FL,
+	[__BCH_INODE_append]		= FS_APPEND_FL,
+	[__BCH_INODE_nodump]		= FS_NODUMP_FL,
+	[__BCH_INODE_noatime]		= FS_NOATIME_FL,
+};
+
+/* bcachefs inode flags -> FS_IOC_FSGETXATTR: */
+static const __maybe_unused unsigned bch_flags_to_xflags[] = {
+	[__BCH_INODE_sync]	= FS_XFLAG_SYNC,
+	[__BCH_INODE_immutable]	= FS_XFLAG_IMMUTABLE,
+	[__BCH_INODE_append]	= FS_XFLAG_APPEND,
+	[__BCH_INODE_nodump]	= FS_XFLAG_NODUMP,
+	[__BCH_INODE_noatime]	= FS_XFLAG_NOATIME,
+};
+
+static int bch2_fileattr_get(struct dentry *dentry,
+			     struct fileattr *fa)
+{
+	struct bch_inode_info *inode = to_bch_ei(d_inode(dentry));
+	struct bch_fs *c = inode->v.i_sb->s_fs_info;
+
+	fileattr_fill_xflags(fa, map_flags(bch_flags_to_xflags, inode->ei_inode.bi_flags));
+
+	if (inode->ei_inode.bi_fields_set & (1 << Inode_opt_project))
+		fa->fsx_xflags |= FS_XFLAG_PROJINHERIT;
+
+	if (bch2_inode_casefold(c, &inode->ei_inode))
+		fa->flags |= FS_CASEFOLD_FL;
+
+	fa->fsx_projid = inode->ei_qid.q[QTYP_PRJ];
+	return 0;
+}
+
+struct flags_set {
+	unsigned		mask;
+	unsigned		flags;
+	unsigned		projid;
+	bool			set_project;
+	bool			set_casefold;
+	bool			casefold;
+};
+
+static int fssetxattr_inode_update_fn(struct btree_trans *trans,
+				      struct bch_inode_info *inode,
+				      struct bch_inode_unpacked *bi,
+				      void *p)
+{
+	struct bch_fs *c = trans->c;
+	struct flags_set *s = p;
+
+	/*
+	 * We're relying on btree locking here for exclusion with other ioctl
+	 * calls - use the flags in the btree (@bi), not inode->i_flags:
+	 */
+	if (!S_ISREG(bi->bi_mode) &&
+	    !S_ISDIR(bi->bi_mode) &&
+	    (s->flags & (BCH_INODE_nodump|BCH_INODE_noatime)) != s->flags)
+		return -EINVAL;
+
+	if (s->casefold != bch2_inode_casefold(c, bi)) {
+#ifdef CONFIG_UNICODE
+		int ret = 0;
+		/* Not supported on individual files. */
+		if (!S_ISDIR(bi->bi_mode))
+			return -EOPNOTSUPP;
+
+		/*
+		 * Make sure the dir is empty, as otherwise we'd need to
+		 * rehash everything and update the dirent keys.
+		 */
+		ret = bch2_empty_dir_trans(trans, inode_inum(inode));
+		if (ret < 0)
+			return ret;
+
+		ret = bch2_request_incompat_feature(c, bcachefs_metadata_version_casefolding);
+		if (ret)
+			return ret;
+
+		bch2_check_set_feature(c, BCH_FEATURE_casefolding);
+
+		bi->bi_casefold = s->casefold + 1;
+		bi->bi_fields_set |= BIT(Inode_opt_casefold);
+
+#else
+		printk(KERN_ERR "Cannot use casefolding on a kernel without CONFIG_UNICODE\n");
+		return -EOPNOTSUPP;
+#endif
+	}
+
+	if (s->set_project) {
+		bi->bi_project = s->projid;
+		bi->bi_fields_set |= BIT(Inode_opt_project);
+	}
+
+	bi->bi_flags &= ~s->mask;
+	bi->bi_flags |= s->flags;
+
+	bi->bi_ctime = timespec_to_bch2_time(c, current_time(&inode->v));
+	return 0;
+}
+
+static int bch2_fileattr_set(struct mnt_idmap *idmap,
+			     struct dentry *dentry,
+			     struct fileattr *fa)
+{
+	struct bch_inode_info *inode = to_bch_ei(d_inode(dentry));
+	struct bch_fs *c = inode->v.i_sb->s_fs_info;
+	struct flags_set s = {};
+	int ret;
+
+	if (fa->fsx_valid) {
+		fa->fsx_xflags &= ~FS_XFLAG_PROJINHERIT;
+
+		s.mask = map_defined(bch_flags_to_xflags);
+		s.flags |= map_flags_rev(bch_flags_to_xflags, fa->fsx_xflags);
+		if (fa->fsx_xflags)
+			return -EOPNOTSUPP;
+
+		if (fa->fsx_projid >= U32_MAX)
+			return -EINVAL;
+
+		/*
+		 * inode fields accessible via the xattr interface are stored with a +1
+		 * bias, so that 0 means unset:
+		 */
+		if ((inode->ei_inode.bi_project ||
+		     fa->fsx_projid) &&
+		    inode->ei_inode.bi_project != fa->fsx_projid + 1) {
+			s.projid = fa->fsx_projid + 1;
+			s.set_project = true;
+		}
+	}
+
+	if (fa->flags_valid) {
+		s.mask = map_defined(bch_flags_to_uflags);
+
+		s.set_casefold = true;
+		s.casefold = (fa->flags & FS_CASEFOLD_FL) != 0;
+		fa->flags &= ~FS_CASEFOLD_FL;
+
+		s.flags |= map_flags_rev(bch_flags_to_uflags, fa->flags);
+		if (fa->flags)
+			return -EOPNOTSUPP;
+	}
+
+	mutex_lock(&inode->ei_update_lock);
+	ret   = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
+		(s.set_project
+		 ? bch2_set_projid(c, inode, fa->fsx_projid)
+		 : 0) ?:
+		bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s,
+			       ATTR_CTIME);
+	mutex_unlock(&inode->ei_update_lock);
+	return ret;
+}
+
 static const struct file_operations bch_file_operations = {
 	.open		= bch2_open,
 	.llseek		= bch2_llseek,
@@ -1476,6 +1787,8 @@ static const struct inode_operations bch_file_inode_operations = {
 	.get_inode_acl	= bch2_get_acl,
 	.set_acl	= bch2_set_acl,
 #endif
+	.fileattr_get	= bch2_fileattr_get,
+	.fileattr_set	= bch2_fileattr_set,
 };
 
 static const struct inode_operations bch_dir_inode_operations = {
@@ -1496,6 +1809,8 @@ static const struct inode_operations bch_dir_inode_operations = {
 	.get_inode_acl	= bch2_get_acl,
 	.set_acl	= bch2_set_acl,
 #endif
+	.fileattr_get	= bch2_fileattr_get,
+	.fileattr_set	= bch2_fileattr_set,
 };
 
 static const struct file_operations bch_dir_file_operations = {
@@ -1518,6 +1833,8 @@ static const struct inode_operations bch_symlink_inode_operations = {
 	.get_inode_acl	= bch2_get_acl,
 	.set_acl	= bch2_set_acl,
 #endif
+	.fileattr_get	= bch2_fileattr_get,
+	.fileattr_set	= bch2_fileattr_set,
 };
 
 static const struct inode_operations bch_special_inode_operations = {
@@ -1528,6 +1845,8 @@ static const struct inode_operations bch_special_inode_operations = {
 	.get_inode_acl	= bch2_get_acl,
 	.set_acl	= bch2_set_acl,
 #endif
+	.fileattr_get	= bch2_fileattr_get,
+	.fileattr_set	= bch2_fileattr_set,
 };
 
 static const struct address_space_operations bch_address_space_operations = {
@@ -2185,10 +2504,9 @@ static int bch2_fs_get_tree(struct fs_context *fc)
 
 	bch2_opts_apply(&c->opts, opts);
 
-	/*
-	 * need to initialise sb and set c->vfs_sb _before_ starting fs,
-	 * for blk_holder_ops
-	 */
+	ret = bch2_fs_start(c);
+	if (ret)
+		goto err_stop_fs;
 
 	sb = sget(fc->fs_type, NULL, bch2_set_super, fc->sb_flags|SB_NOSEC, c);
 	ret = PTR_ERR_OR_ZERO(sb);
@@ -2250,9 +2568,10 @@ got_sb:
 
 	sb->s_shrink->seeks = 0;
 
-	ret = bch2_fs_start(c);
-	if (ret)
-		goto err_put_super;
+#ifdef CONFIG_UNICODE
+	sb->s_encoding = c->cf_encoding;
+#endif
+	generic_set_sb_d_ops(sb);
 
 	vinode = bch2_vfs_inode_get(c, BCACHEFS_ROOT_SUBVOL_INUM);
 	ret = PTR_ERR_OR_ZERO(vinode);
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 18308f3d64a1..71d428f376a5 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -321,6 +321,31 @@ static inline bool inode_should_reattach(struct bch_inode_unpacked *inode)
 	    inode->bi_subvol == BCACHEFS_ROOT_SUBVOL)
 		return false;
 
+	/*
+	 * Subvolume roots are special: older versions of subvolume roots may be
+	 * disconnected, it's only the newest version that matters.
+	 *
+	 * We only keep a single dirent pointing to a subvolume root, i.e.
+	 * older versions of snapshots will not have a different dirent pointing
+	 * to the same subvolume root.
+	 *
+	 * This is because dirents that point to subvolumes are only visible in
+	 * the parent subvolume - versioning is not needed - and keeping them
+	 * around would break fsck, because when we're crossing subvolumes we
+	 * don't have a consistent snapshot ID to do check the inode <-> dirent
+	 * relationships.
+	 *
+	 * Thus, a subvolume root that's been renamed after a snapshot will have
+	 * a disconnected older version - that's expected.
+	 *
+	 * Note that taking a snapshot always updates the root inode (to update
+	 * the dirent backpointer), so a subvolume root inode with
+	 * BCH_INODE_has_child_snapshot is never visible.
+	 */
+	if (inode->bi_subvol &&
+	    (inode->bi_flags & BCH_INODE_has_child_snapshot))
+		return false;
+
 	return !inode->bi_dir && !(inode->bi_flags & BCH_INODE_unlinked);
 }
 
@@ -1007,6 +1032,23 @@ static int check_inode_dirent_inode(struct btree_trans *trans,
 	if (ret && !bch2_err_matches(ret, ENOENT))
 		return ret;
 
+	if ((ret || dirent_points_to_inode_nowarn(d, inode)) &&
+	    inode->bi_subvol &&
+	    (inode->bi_flags & BCH_INODE_has_child_snapshot)) {
+		/* Older version of a renamed subvolume root: we won't have a
+		 * correct dirent for it. That's expected, see
+		 * inode_should_reattach().
+		 *
+		 * We don't clear the backpointer field when doing the rename
+		 * because there might be arbitrarily many versions in older
+		 * snapshots.
+		 */
+		inode->bi_dir = 0;
+		inode->bi_dir_offset = 0;
+		*write_inode = true;
+		goto out;
+	}
+
 	if (fsck_err_on(ret,
 			trans, inode_points_to_missing_dirent,
 			"inode points to missing dirent\n%s",
@@ -1027,7 +1069,7 @@ static int check_inode_dirent_inode(struct btree_trans *trans,
 		inode->bi_dir_offset = 0;
 		*write_inode = true;
 	}
-
+out:
 	ret = 0;
 fsck_err:
 	bch2_trans_iter_exit(trans, &dirent_iter);
@@ -2404,7 +2446,7 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter,
 		u32 parent = le32_to_cpu(s.v->fs_path_parent);
 
 		if (darray_u32_has(&subvol_path, parent)) {
-			if (fsck_err(c, subvol_loop, "subvolume loop"))
+			if (fsck_err(trans, subvol_loop, "subvolume loop"))
 				ret = reattach_subvol(trans, s);
 			break;
 		}
diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h
index f82cfbf460d0..c74af15b14f2 100644
--- a/fs/bcachefs/inode.h
+++ b/fs/bcachefs/inode.h
@@ -243,6 +243,14 @@ static inline unsigned bkey_inode_mode(struct bkey_s_c k)
 	}
 }
 
+static inline bool bch2_inode_casefold(struct bch_fs *c, const struct bch_inode_unpacked *bi)
+{
+	/* inode apts are stored with a +1 bias: 0 means "unset, use fs opt" */
+	return bi->bi_casefold
+		? bi->bi_casefold - 1
+		: c->opts.casefold;
+}
+
 /* i_nlink: */
 
 static inline unsigned nlink_bias(umode_t mode)
diff --git a/fs/bcachefs/inode_format.h b/fs/bcachefs/inode_format.h
index 117110af1e3f..87e193e8ed25 100644
--- a/fs/bcachefs/inode_format.h
+++ b/fs/bcachefs/inode_format.h
@@ -103,7 +103,8 @@ struct bch_inode_generation {
 	x(bi_parent_subvol,		32)	\
 	x(bi_nocow,			8)	\
 	x(bi_depth,			32)	\
-	x(bi_inodes_32bit,		8)
+	x(bi_inodes_32bit,		8)	\
+	x(bi_casefold,			8)
 
 /* subset of BCH_INODE_FIELDS */
 #define BCH_INODE_OPTS()			\
@@ -117,7 +118,8 @@ struct bch_inode_generation {
 	x(background_target,		16)	\
 	x(erasure_code,			16)	\
 	x(nocow,			8)	\
-	x(inodes_32bit,			8)
+	x(inodes_32bit,			8)	\
+	x(casefold,			8)
 
 enum inode_opt_id {
 #define x(name, ...)				\
@@ -137,8 +139,7 @@ enum inode_opt_id {
 	x(i_sectors_dirty,		6)	\
 	x(unlinked,			7)	\
 	x(backptr_untrusted,		8)	\
-	x(has_child_snapshot,		9)	\
-	x(casefolded,			10)
+	x(has_child_snapshot,		9)
 
 /* bits 20+ reserved for packed fields below: */
 
diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index 417bb0c7bbfa..def4a26a3b45 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -487,6 +487,8 @@ static void bch2_rbio_retry(struct work_struct *work)
 		.inum	= rbio->read_pos.inode,
 	};
 	struct bch_io_failures failed = { .nr = 0 };
+	int orig_error = rbio->ret;
+
 	struct btree_trans *trans = bch2_trans_get(c);
 
 	trace_io_read_retry(&rbio->bio);
@@ -519,7 +521,9 @@ static void bch2_rbio_retry(struct work_struct *work)
 	if (ret) {
 		rbio->ret = ret;
 		rbio->bio.bi_status = BLK_STS_IOERR;
-	} else {
+	} else if (orig_error != -BCH_ERR_data_read_retry_csum_err_maybe_userspace &&
+		   orig_error != -BCH_ERR_data_read_ptr_stale_race &&
+		   !failed.nr) {
 		struct printbuf buf = PRINTBUF;
 
 		lockrestart_do(trans,
@@ -977,7 +981,8 @@ retry_pick:
 		goto err;
 	}
 
-	if (unlikely(bch2_csum_type_is_encryption(pick.crc.csum_type)) && !c->chacha20) {
+	if (unlikely(bch2_csum_type_is_encryption(pick.crc.csum_type)) &&
+	    !c->chacha20_key_set) {
 		struct printbuf buf = PRINTBUF;
 		bch2_read_err_msg_trans(trans, &buf, orig, read_pos);
 		prt_printf(&buf, "attempting to read encrypted data without encryption key\n  ");
@@ -1344,14 +1349,16 @@ err:
 
 	bch2_trans_iter_exit(trans, &iter);
 
-	if (ret) {
-		struct printbuf buf = PRINTBUF;
-		lockrestart_do(trans,
-			bch2_inum_offset_err_msg_trans(trans, &buf, inum,
-						       bvec_iter.bi_sector << 9));
-		prt_printf(&buf, "read error: %s", bch2_err_str(ret));
-		bch_err_ratelimited(c, "%s", buf.buf);
-		printbuf_exit(&buf);
+	if (unlikely(ret)) {
+		if (ret != -BCH_ERR_extent_poisoned) {
+			struct printbuf buf = PRINTBUF;
+			lockrestart_do(trans,
+				       bch2_inum_offset_err_msg_trans(trans, &buf, inum,
+								      bvec_iter.bi_sector << 9));
+			prt_printf(&buf, "data read error: %s", bch2_err_str(ret));
+			bch_err_ratelimited(c, "%s", buf.buf);
+			printbuf_exit(&buf);
+		}
 
 		rbio->bio.bi_status	= BLK_STS_IOERR;
 		rbio->ret		= ret;
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index a418fa62f09d..c1237da079ed 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -255,6 +255,27 @@ static inline int bch2_extent_update_i_size_sectors(struct btree_trans *trans,
 	}
 
 	if (i_sectors_delta) {
+		s64 bi_sectors = le64_to_cpu(inode->v.bi_sectors);
+		if (unlikely(bi_sectors + i_sectors_delta < 0)) {
+			struct bch_fs *c = trans->c;
+			struct printbuf buf = PRINTBUF;
+			bch2_log_msg_start(c, &buf);
+			prt_printf(&buf, "inode %llu i_sectors underflow: %lli + %lli < 0",
+				   extent_iter->pos.inode, bi_sectors, i_sectors_delta);
+
+			bool repeat = false, print = false, suppress = false;
+			bch2_count_fsck_err(c, inode_i_sectors_underflow, buf.buf,
+					    &repeat, &print, &suppress);
+			if (print)
+				bch2_print_str(c, buf.buf);
+			printbuf_exit(&buf);
+
+			if (i_sectors_delta < 0)
+				i_sectors_delta = -bi_sectors;
+			else
+				i_sectors_delta = 0;
+		}
+
 		le64_add_cpu(&inode->v.bi_sectors, i_sectors_delta);
 		inode_update_flags = 0;
 	}
diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index d8f74b6d0a75..bb45d3634194 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -281,7 +281,24 @@ static void __journal_entry_close(struct journal *j, unsigned closed_val, bool t
 
 	sectors = vstruct_blocks_plus(buf->data, c->block_bits,
 				      buf->u64s_reserved) << c->block_bits;
-	BUG_ON(sectors > buf->sectors);
+	if (unlikely(sectors > buf->sectors)) {
+		struct printbuf err = PRINTBUF;
+		err.atomic++;
+
+		prt_printf(&err, "journal entry overran reserved space: %u > %u\n",
+			   sectors, buf->sectors);
+		prt_printf(&err, "buf u64s %u u64s reserved %u cur_entry_u64s %u block_bits %u\n",
+			   le32_to_cpu(buf->data->u64s), buf->u64s_reserved,
+			   j->cur_entry_u64s,
+			   c->block_bits);
+		prt_printf(&err, "fatal error - emergency read only");
+		bch2_journal_halt_locked(j);
+
+		bch_err(c, "%s", err.buf);
+		printbuf_exit(&err);
+		return;
+	}
+
 	buf->sectors = sectors;
 
 	/*
@@ -1462,8 +1479,6 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
 		j->last_empty_seq = cur_seq - 1; /* to match j->seq */
 
 	spin_lock(&j->lock);
-
-	set_bit(JOURNAL_running, &j->flags);
 	j->last_flush_write = jiffies;
 
 	j->reservations.idx = journal_cur_seq(j);
@@ -1474,6 +1489,21 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
 	return 0;
 }
 
+void bch2_journal_set_replay_done(struct journal *j)
+{
+	/*
+	 * journal_space_available must happen before setting JOURNAL_running
+	 * JOURNAL_running must happen before JOURNAL_replay_done
+	 */
+	spin_lock(&j->lock);
+	bch2_journal_space_available(j);
+
+	set_bit(JOURNAL_need_flush_write, &j->flags);
+	set_bit(JOURNAL_running, &j->flags);
+	set_bit(JOURNAL_replay_done, &j->flags);
+	spin_unlock(&j->lock);
+}
+
 /* init/exit: */
 
 void bch2_dev_journal_exit(struct bch_dev *ca)
diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h
index 47828771f9c2..641e20c05a14 100644
--- a/fs/bcachefs/journal.h
+++ b/fs/bcachefs/journal.h
@@ -437,12 +437,6 @@ static inline int bch2_journal_error(struct journal *j)
 
 struct bch_dev;
 
-static inline void bch2_journal_set_replay_done(struct journal *j)
-{
-	BUG_ON(!test_bit(JOURNAL_running, &j->flags));
-	set_bit(JOURNAL_replay_done, &j->flags);
-}
-
 void bch2_journal_unblock(struct journal *);
 void bch2_journal_block(struct journal *);
 struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *, u64, bool *);
@@ -459,6 +453,7 @@ void bch2_dev_journal_stop(struct journal *, struct bch_dev *);
 
 void bch2_fs_journal_stop(struct journal *);
 int bch2_fs_journal_start(struct journal *, u64);
+void bch2_journal_set_replay_done(struct journal *);
 
 void bch2_dev_journal_exit(struct bch_dev *);
 int bch2_dev_journal_init(struct bch_dev *, struct bch_sb *);
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 1b7961f4f609..ded18a94ed02 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -19,6 +19,7 @@
 
 #include <linux/ioprio.h>
 #include <linux/string_choices.h>
+#include <linux/sched/sysctl.h>
 
 void bch2_journal_pos_from_member_info_set(struct bch_fs *c)
 {
@@ -1262,7 +1263,8 @@ int bch2_journal_read(struct bch_fs *c,
 			degraded = true;
 	}
 
-	closure_sync(&jlist.cl);
+	while (closure_sync_timeout(&jlist.cl, sysctl_hung_task_timeout_secs * HZ / 2))
+		;
 
 	if (jlist.ret)
 		return jlist.ret;
@@ -1460,7 +1462,7 @@ fsck_err:
 
 static void journal_advance_devs_to_next_bucket(struct journal *j,
 						struct dev_alloc_list *devs,
-						unsigned sectors, u64 seq)
+						unsigned sectors, __le64 seq)
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 
@@ -1782,7 +1784,7 @@ static CLOSURE_CALLBACK(journal_write_submit)
 		struct bch_dev *ca = bch2_dev_get_ioref(c, ptr->dev, WRITE);
 		if (!ca) {
 			/* XXX: fix this */
-			bch_err(c, "missing device for journal write\n");
+			bch_err(c, "missing device %u for journal write", ptr->dev);
 			continue;
 		}
 
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index 5d1547aa118a..cc00b0fc40d8 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -17,6 +17,8 @@
 #include <linux/kthread.h>
 #include <linux/sched/mm.h>
 
+static bool __should_discard_bucket(struct journal *, struct journal_device *);
+
 /* Free space calculations: */
 
 static unsigned journal_space_from(struct journal_device *ja,
@@ -203,8 +205,7 @@ void bch2_journal_space_available(struct journal *j)
 		       ja->bucket_seq[ja->dirty_idx_ondisk] < j->last_seq_ondisk)
 			ja->dirty_idx_ondisk = (ja->dirty_idx_ondisk + 1) % ja->nr;
 
-		if (ja->discard_idx != ja->dirty_idx_ondisk)
-			can_discard = true;
+		can_discard |= __should_discard_bucket(j, ja);
 
 		max_entry_size = min_t(unsigned, max_entry_size, ca->mi.bucket_size);
 		nr_online++;
@@ -252,7 +253,10 @@ void bch2_journal_space_available(struct journal *j)
 
 	bch2_journal_set_watermark(j);
 out:
-	j->cur_entry_sectors	= !ret ? j->space[journal_space_discarded].next_entry : 0;
+	j->cur_entry_sectors	= !ret
+		? round_down(j->space[journal_space_discarded].next_entry,
+			     block_sectors(c))
+		: 0;
 	j->cur_entry_error	= ret;
 
 	if (!ret)
@@ -261,12 +265,19 @@ out:
 
 /* Discards - last part of journal reclaim: */
 
-static bool should_discard_bucket(struct journal *j, struct journal_device *ja)
+static bool __should_discard_bucket(struct journal *j, struct journal_device *ja)
 {
-	bool ret;
+	unsigned min_free = max(4, ja->nr / 8);
+
+	return bch2_journal_dev_buckets_available(j, ja, journal_space_discarded) <
+		min_free &&
+		ja->discard_idx != ja->dirty_idx_ondisk;
+}
 
+static bool should_discard_bucket(struct journal *j, struct journal_device *ja)
+{
 	spin_lock(&j->lock);
-	ret = ja->discard_idx != ja->dirty_idx_ondisk;
+	bool ret = __should_discard_bucket(j, ja);
 	spin_unlock(&j->lock);
 
 	return ret;
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index fc396b9fa754..dfdbb9259985 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -784,7 +784,8 @@ static int __bch2_move_data_phys(struct moving_context *ctxt,
 		goto err;
 
 	ret = bch2_btree_write_buffer_tryflush(trans);
-	bch_err_msg(c, ret, "flushing btree write buffer");
+	if (!bch2_err_matches(ret, EROFS))
+		bch_err_msg(c, ret, "flushing btree write buffer");
 	if (ret)
 		goto err;
 
diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index 159410c50861..96873372b516 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -356,6 +356,13 @@ static int bch2_copygc_thread(void *arg)
 
 	set_freezable();
 
+	/*
+	 * Data move operations can't run until after check_snapshots has
+	 * completed, and bch2_snapshot_is_ancestor() is available.
+	 */
+	kthread_wait_freezable(c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots ||
+			       kthread_should_stop());
+
 	bch2_move_stats_init(&move_stats, "copygc");
 	bch2_moving_ctxt_init(&ctxt, c, NULL, &move_stats,
 			      writepoint_ptr(&c->copygc_write_point),
diff --git a/fs/bcachefs/movinggc.h b/fs/bcachefs/movinggc.h
index ea181fef5bc9..d1885cf67a45 100644
--- a/fs/bcachefs/movinggc.h
+++ b/fs/bcachefs/movinggc.h
@@ -5,6 +5,15 @@
 unsigned long bch2_copygc_wait_amount(struct bch_fs *);
 void bch2_copygc_wait_to_text(struct printbuf *, struct bch_fs *);
 
+static inline void bch2_copygc_wakeup(struct bch_fs *c)
+{
+	rcu_read_lock();
+	struct task_struct *p = rcu_dereference(c->copygc_thread);
+	if (p)
+		wake_up_process(p);
+	rcu_read_unlock();
+}
+
 void bch2_copygc_stop(struct bch_fs *);
 int bch2_copygc_start(struct bch_fs *);
 void bch2_fs_copygc_init(struct bch_fs *);
diff --git a/fs/bcachefs/namei.c b/fs/bcachefs/namei.c
index 0d65ea96f7a2..52c58c6d53d2 100644
--- a/fs/bcachefs/namei.c
+++ b/fs/bcachefs/namei.c
@@ -47,10 +47,6 @@ int bch2_create_trans(struct btree_trans *trans,
 	if (ret)
 		goto err;
 
-	/* Inherit casefold state from parent. */
-	if (S_ISDIR(mode))
-		new_inode->bi_flags |= dir_u->bi_flags & BCH_INODE_casefolded;
-
 	if (!(flags & BCH_CREATE_SNAPSHOT)) {
 		/* Normal create path - allocate a new inode: */
 		bch2_inode_init_late(new_inode, now, uid, gid, mode, rdev, dir_u);
@@ -347,6 +343,9 @@ bool bch2_reinherit_attrs(struct bch_inode_unpacked *dst_u,
 	bool ret = false;
 
 	for (id = 0; id < Inode_opt_nr; id++) {
+		if (!S_ISDIR(dst_u->bi_mode) && id == Inode_opt_casefold)
+			continue;
+
 		/* Skip attributes that were explicitly set on this inode */
 		if (dst_u->bi_fields_set & (1 << id))
 			continue;
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index 4d06313076ff..dfb14810124c 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -228,6 +228,11 @@ enum fsck_err_opts {
 	  OPT_BOOL(),							\
 	  BCH_SB_ERASURE_CODE,		false,				\
 	  NULL,		"Enable erasure coding (DO NOT USE YET)")	\
+	x(casefold,			u8,				\
+	  OPT_FS|OPT_INODE|OPT_FORMAT,					\
+	  OPT_BOOL(),							\
+	  BCH_SB_CASEFOLD,		false,				\
+	  NULL,		"Dirent lookups are casefolded")		\
 	x(inodes_32bit,			u8,				\
 	  OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME,		\
 	  OPT_BOOL(),							\
diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index c63fa53f30d2..623273556aa9 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -262,7 +262,7 @@ int bch2_set_rebalance_needs_scan(struct bch_fs *c, u64 inum)
 	int ret = bch2_trans_commit_do(c, NULL, NULL,
 				       BCH_TRANS_COMMIT_no_enospc,
 			    bch2_set_rebalance_needs_scan_trans(trans, inum));
-	rebalance_wakeup(c);
+	bch2_rebalance_wakeup(c);
 	return ret;
 }
 
@@ -309,7 +309,7 @@ static int bch2_bkey_clear_needs_rebalance(struct btree_trans *trans,
 					   struct btree_iter *iter,
 					   struct bkey_s_c k)
 {
-	if (!bch2_bkey_rebalance_opts(k))
+	if (k.k->type == KEY_TYPE_reflink_v || !bch2_bkey_rebalance_opts(k))
 		return 0;
 
 	struct bkey_i *n = bch2_bkey_make_mut(trans, iter, &k, 0);
@@ -581,6 +581,13 @@ static int bch2_rebalance_thread(void *arg)
 
 	set_freezable();
 
+	/*
+	 * Data move operations can't run until after check_snapshots has
+	 * completed, and bch2_snapshot_is_ancestor() is available.
+	 */
+	kthread_wait_freezable(c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots ||
+			       kthread_should_stop());
+
 	bch2_moving_ctxt_init(&ctxt, c, NULL, &r->work_stats,
 			      writepoint_ptr(&c->rebalance_write_point),
 			      true);
@@ -664,7 +671,7 @@ void bch2_rebalance_stop(struct bch_fs *c)
 	c->rebalance.thread = NULL;
 
 	if (p) {
-		/* for sychronizing with rebalance_wakeup() */
+		/* for sychronizing with bch2_rebalance_wakeup() */
 		synchronize_rcu();
 
 		kthread_stop(p);
diff --git a/fs/bcachefs/rebalance.h b/fs/bcachefs/rebalance.h
index 62a3859d3823..e5e8eb4a2dd1 100644
--- a/fs/bcachefs/rebalance.h
+++ b/fs/bcachefs/rebalance.h
@@ -37,7 +37,7 @@ int bch2_set_rebalance_needs_scan_trans(struct btree_trans *, u64);
 int bch2_set_rebalance_needs_scan(struct bch_fs *, u64 inum);
 int bch2_set_fs_needs_rebalance(struct bch_fs *);
 
-static inline void rebalance_wakeup(struct bch_fs *c)
+static inline void bch2_rebalance_wakeup(struct bch_fs *c)
 {
 	struct task_struct *p;
 
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 79fd18a5a07c..d6c4ef819d40 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -18,6 +18,7 @@
 #include "journal_seq_blacklist.h"
 #include "logged_ops.h"
 #include "move.h"
+#include "movinggc.h"
 #include "namei.h"
 #include "quota.h"
 #include "rebalance.h"
@@ -389,9 +390,9 @@ int bch2_journal_replay(struct bch_fs *c)
 	 * Now, replay any remaining keys in the order in which they appear in
 	 * the journal, unpinning those journal entries as we go:
 	 */
-	sort(keys_sorted.data, keys_sorted.nr,
-	     sizeof(keys_sorted.data[0]),
-	     journal_sort_seq_cmp, NULL);
+	sort_nonatomic(keys_sorted.data, keys_sorted.nr,
+		       sizeof(keys_sorted.data[0]),
+		       journal_sort_seq_cmp, NULL);
 
 	darray_for_each(keys_sorted, kp) {
 		cond_resched();
@@ -1125,14 +1126,17 @@ int bch2_fs_initialize(struct bch_fs *c)
 	 * journal_res_get() will crash if called before this has
 	 * set up the journal.pin FIFO and journal.cur pointer:
 	 */
-	bch2_fs_journal_start(&c->journal, 1);
-	set_bit(BCH_FS_accounting_replay_done, &c->flags);
-	bch2_journal_set_replay_done(&c->journal);
+	ret = bch2_fs_journal_start(&c->journal, 1);
+	if (ret)
+		goto err;
 
 	ret = bch2_fs_read_write_early(c);
 	if (ret)
 		goto err;
 
+	set_bit(BCH_FS_accounting_replay_done, &c->flags);
+	bch2_journal_set_replay_done(&c->journal);
+
 	for_each_member_device(c, ca) {
 		ret = bch2_dev_usage_init(ca, false);
 		if (ret) {
@@ -1191,6 +1195,9 @@ int bch2_fs_initialize(struct bch_fs *c)
 
 	c->recovery_pass_done = BCH_RECOVERY_PASS_NR - 1;
 
+	bch2_copygc_wakeup(c);
+	bch2_rebalance_wakeup(c);
+
 	if (enabled_qtypes(c)) {
 		ret = bch2_fs_quota_read(c);
 		if (ret)
diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
index 593ff142530d..22f72bb5b853 100644
--- a/fs/bcachefs/recovery_passes.c
+++ b/fs/bcachefs/recovery_passes.c
@@ -12,6 +12,7 @@
 #include "journal.h"
 #include "lru.h"
 #include "logged_ops.h"
+#include "movinggc.h"
 #include "rebalance.h"
 #include "recovery.h"
 #include "recovery_passes.h"
@@ -262,49 +263,52 @@ int bch2_run_recovery_passes(struct bch_fs *c)
 	 */
 	c->opts.recovery_passes_exclude &= ~BCH_RECOVERY_PASS_set_may_go_rw;
 
-	while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns) && !ret) {
-		c->next_recovery_pass = c->curr_recovery_pass + 1;
+	spin_lock_irq(&c->recovery_pass_lock);
 
-		spin_lock_irq(&c->recovery_pass_lock);
+	while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns) && !ret) {
+		unsigned prev_done = c->recovery_pass_done;
 		unsigned pass = c->curr_recovery_pass;
 
+		c->next_recovery_pass = pass + 1;
+
 		if (c->opts.recovery_pass_last &&
-		    c->curr_recovery_pass > c->opts.recovery_pass_last) {
-			spin_unlock_irq(&c->recovery_pass_lock);
+		    c->curr_recovery_pass > c->opts.recovery_pass_last)
 			break;
-		}
 
-		if (!should_run_recovery_pass(c, pass)) {
-			c->curr_recovery_pass++;
-			c->recovery_pass_done = max(c->recovery_pass_done, pass);
+		if (should_run_recovery_pass(c, pass)) {
 			spin_unlock_irq(&c->recovery_pass_lock);
-			continue;
-		}
-		spin_unlock_irq(&c->recovery_pass_lock);
-
-		ret =   bch2_run_recovery_pass(c, pass) ?:
-			bch2_journal_flush(&c->journal);
-
-		if (!ret && !test_bit(BCH_FS_error, &c->flags))
-			bch2_clear_recovery_pass_required(c, pass);
-
-		spin_lock_irq(&c->recovery_pass_lock);
-		if (c->next_recovery_pass < c->curr_recovery_pass) {
-			/*
-			 * bch2_run_explicit_recovery_pass() was called: we
-			 * can't always catch -BCH_ERR_restart_recovery because
-			 * it may have been called from another thread (btree
-			 * node read completion)
-			 */
-			ret = 0;
-			c->recovery_passes_complete &= ~(~0ULL << c->curr_recovery_pass);
-		} else {
-			c->recovery_passes_complete |= BIT_ULL(pass);
-			c->recovery_pass_done = max(c->recovery_pass_done, pass);
+			ret =   bch2_run_recovery_pass(c, pass) ?:
+				bch2_journal_flush(&c->journal);
+
+			if (!ret && !test_bit(BCH_FS_error, &c->flags))
+				bch2_clear_recovery_pass_required(c, pass);
+			spin_lock_irq(&c->recovery_pass_lock);
+
+			if (c->next_recovery_pass < c->curr_recovery_pass) {
+				/*
+				 * bch2_run_explicit_recovery_pass() was called: we
+				 * can't always catch -BCH_ERR_restart_recovery because
+				 * it may have been called from another thread (btree
+				 * node read completion)
+				 */
+				ret = 0;
+				c->recovery_passes_complete &= ~(~0ULL << c->curr_recovery_pass);
+			} else {
+				c->recovery_passes_complete |= BIT_ULL(pass);
+				c->recovery_pass_done = max(c->recovery_pass_done, pass);
+			}
 		}
+
 		c->curr_recovery_pass = c->next_recovery_pass;
-		spin_unlock_irq(&c->recovery_pass_lock);
+
+		if (prev_done <= BCH_RECOVERY_PASS_check_snapshots &&
+		    c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots) {
+			bch2_copygc_wakeup(c);
+			bch2_rebalance_wakeup(c);
+		}
 	}
 
+	spin_unlock_irq(&c->recovery_pass_lock);
+
 	return ret;
 }
diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index acb5d845841e..badd0e17ada5 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -20,6 +20,10 @@
  * x(version, recovery_passes, errors...)
  */
 #define UPGRADE_TABLE()						\
+	x(snapshot_2,						\
+	  RECOVERY_PASS_ALL_FSCK,				\
+	  BCH_FSCK_ERR_subvol_root_wrong_bi_subvol,		\
+	  BCH_FSCK_ERR_subvol_not_master_and_not_snapshot)	\
 	x(backpointers,						\
 	  RECOVERY_PASS_ALL_FSCK)				\
 	x(inode_v3,						\
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index 5d43e3504386..3b69a924086f 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -46,7 +46,7 @@ enum bch_fsck_flags {
 	x(btree_node_unsupported_version,			 34,	0)		\
 	x(btree_node_bset_older_than_sb_min,			 35,	0)		\
 	x(btree_node_bset_newer_than_sb,			 36,	0)		\
-	x(btree_node_data_missing,				 37,	0)		\
+	x(btree_node_data_missing,				 37,	FSCK_AUTOFIX)	\
 	x(btree_node_bset_after_end,				 38,	0)		\
 	x(btree_node_replicas_sectors_written_mismatch,		 39,	0)		\
 	x(btree_node_replicas_data_mismatch,			 40,	0)		\
@@ -205,9 +205,9 @@ enum bch_fsck_flags {
 	x(snapshot_bad_depth,					184,	0)		\
 	x(snapshot_bad_skiplist,				185,	0)		\
 	x(subvol_pos_bad,					186,	0)		\
-	x(subvol_not_master_and_not_snapshot,			187,	0)		\
+	x(subvol_not_master_and_not_snapshot,			187,	FSCK_AUTOFIX)	\
 	x(subvol_to_missing_root,				188,	0)		\
-	x(subvol_root_wrong_bi_subvol,				189,	0)		\
+	x(subvol_root_wrong_bi_subvol,				189,	FSCK_AUTOFIX)	\
 	x(bkey_in_missing_snapshot,				190,	0)		\
 	x(inode_pos_inode_nonzero,				191,	0)		\
 	x(inode_pos_blockdev_range,				192,	0)		\
@@ -236,6 +236,9 @@ enum bch_fsck_flags {
 	x(inode_has_child_snapshots_wrong,			287,	0)		\
 	x(inode_unreachable,					210,	FSCK_AUTOFIX)	\
 	x(inode_journal_seq_in_future,				299,	FSCK_AUTOFIX)	\
+	x(inode_i_sectors_underflow,				312,	FSCK_AUTOFIX)	\
+	x(vfs_inode_i_blocks_underflow,				311,	FSCK_AUTOFIX)	\
+	x(vfs_inode_i_blocks_not_zero_at_truncate,		313,	FSCK_AUTOFIX)	\
 	x(deleted_inode_but_clean,				211,	FSCK_AUTOFIX)	\
 	x(deleted_inode_missing,				212,	FSCK_AUTOFIX)	\
 	x(deleted_inode_is_dir,					213,	FSCK_AUTOFIX)	\
@@ -290,8 +293,8 @@ enum bch_fsck_flags {
 	x(btree_node_bkey_bad_u64s,				260,	0)		\
 	x(btree_node_topology_empty_interior_node,		261,	0)		\
 	x(btree_ptr_v2_min_key_bad,				262,	0)		\
-	x(btree_root_unreadable_and_scan_found_nothing,		263,	0)		\
-	x(snapshot_node_missing,				264,	0)		\
+	x(btree_root_unreadable_and_scan_found_nothing,		263,	FSCK_AUTOFIX)	\
+	x(snapshot_node_missing,				264,	FSCK_AUTOFIX)	\
 	x(dup_backpointer_to_bad_csum_extent,			265,	0)		\
 	x(btree_bitmap_not_marked,				266,	FSCK_AUTOFIX)	\
 	x(sb_clean_entry_overrun,				267,	0)		\
@@ -317,7 +320,9 @@ enum bch_fsck_flags {
 	x(directory_size_mismatch,				303,	FSCK_AUTOFIX)	\
 	x(dirent_cf_name_too_big,				304,	0)		\
 	x(dirent_stray_data_after_cf_name,			305,	0)		\
-	x(MAX,							308,	0)
+	x(rebalance_work_incorrectly_set,			309,	FSCK_AUTOFIX)	\
+	x(rebalance_work_incorrectly_unset,			310,	FSCK_AUTOFIX)	\
+	x(MAX,							314,	0)
 
 enum bch_sb_error_id {
 #define x(t, n, ...) BCH_FSCK_ERR_##t = n,
diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index 116131f95815..72779912939b 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -15,9 +15,11 @@ void bch2_dev_missing(struct bch_fs *c, unsigned dev)
 		bch2_fs_inconsistent(c, "pointer to nonexistent device %u", dev);
 }
 
-void bch2_dev_bucket_missing(struct bch_fs *c, struct bpos bucket)
+void bch2_dev_bucket_missing(struct bch_dev *ca, u64 bucket)
 {
-	bch2_fs_inconsistent(c, "pointer to nonexistent bucket %llu:%llu", bucket.inode, bucket.offset);
+	bch2_fs_inconsistent(ca->fs,
+		"pointer to nonexistent bucket %llu on device %s (valid range %u-%llu)",
+		bucket, ca->name, ca->mi.first_bucket, ca->mi.nbuckets);
 }
 
 #define x(t, n, ...) [n] = #t,
diff --git a/fs/bcachefs/sb-members.h b/fs/bcachefs/sb-members.h
index 06bb41a3f360..42786657522c 100644
--- a/fs/bcachefs/sb-members.h
+++ b/fs/bcachefs/sb-members.h
@@ -249,20 +249,23 @@ static inline struct bch_dev *bch2_dev_tryget(struct bch_fs *c, unsigned dev)
 static inline struct bch_dev *bch2_dev_bucket_tryget_noerror(struct bch_fs *c, struct bpos bucket)
 {
 	struct bch_dev *ca = bch2_dev_tryget_noerror(c, bucket.inode);
-	if (ca && !bucket_valid(ca, bucket.offset)) {
+	if (ca && unlikely(!bucket_valid(ca, bucket.offset))) {
 		bch2_dev_put(ca);
 		ca = NULL;
 	}
 	return ca;
 }
 
-void bch2_dev_bucket_missing(struct bch_fs *, struct bpos);
+void bch2_dev_bucket_missing(struct bch_dev *, u64);
 
 static inline struct bch_dev *bch2_dev_bucket_tryget(struct bch_fs *c, struct bpos bucket)
 {
-	struct bch_dev *ca = bch2_dev_bucket_tryget_noerror(c, bucket);
-	if (!ca)
-		bch2_dev_bucket_missing(c, bucket);
+	struct bch_dev *ca = bch2_dev_tryget(c, bucket.inode);
+	if (ca && unlikely(!bucket_valid(ca, bucket.offset))) {
+		bch2_dev_bucket_missing(ca, bucket.offset);
+		bch2_dev_put(ca);
+		ca = NULL;
+	}
 	return ca;
 }
 
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index b7de29aed839..fec569c7deb1 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -396,7 +396,7 @@ u32 bch2_snapshot_tree_oldest_subvol(struct bch_fs *c, u32 snapshot_root)
 	u32 subvol = 0, s;
 
 	rcu_read_lock();
-	while (id) {
+	while (id && bch2_snapshot_exists(c, id)) {
 		s = snapshot_t(c, id)->subvol;
 
 		if (s && (!subvol || s < subvol))
diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h
index 09a354a26c3b..0c1a00539bd1 100644
--- a/fs/bcachefs/str_hash.h
+++ b/fs/bcachefs/str_hash.h
@@ -33,7 +33,7 @@ bch2_str_hash_opt_to_type(struct bch_fs *c, enum bch_str_hash_opts opt)
 
 struct bch_hash_info {
 	u8			type;
-	struct unicode_map 	*cf_encoding;
+	struct unicode_map	*cf_encoding;
 	/*
 	 * For crc32 or crc64 string hashes the first key value of
 	 * the siphash_key (k0) is used as the key.
@@ -44,11 +44,10 @@ struct bch_hash_info {
 static inline struct bch_hash_info
 bch2_hash_info_init(struct bch_fs *c, const struct bch_inode_unpacked *bi)
 {
-	/* XXX ick */
 	struct bch_hash_info info = {
 		.type = INODE_STR_HASH(bi),
 #ifdef CONFIG_UNICODE
-		.cf_encoding = !!(bi->bi_flags & BCH_INODE_casefolded) ? c->cf_encoding : NULL,
+		.cf_encoding = bch2_inode_casefold(c, bi) ? c->cf_encoding : NULL,
 #endif
 		.siphash_key = { .k0 = bi->bi_hash_seed }
 	};
diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c
index 5537283d0bea..d0209f7658bb 100644
--- a/fs/bcachefs/subvolume.c
+++ b/fs/bcachefs/subvolume.c
@@ -6,6 +6,7 @@
 #include "errcode.h"
 #include "error.h"
 #include "fs.h"
+#include "recovery_passes.h"
 #include "snapshot.h"
 #include "subvolume.h"
 
@@ -44,8 +45,8 @@ static int check_subvol(struct btree_trans *trans,
 	ret = bch2_snapshot_lookup(trans, snapid, &snapshot);
 
 	if (bch2_err_matches(ret, ENOENT))
-		bch_err(c, "subvolume %llu points to nonexistent snapshot %u",
-			k.k->p.offset, snapid);
+		return bch2_run_explicit_recovery_pass(c,
+					BCH_RECOVERY_PASS_reconstruct_snapshots) ?: ret;
 	if (ret)
 		return ret;
 
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index e27422b6d9c6..cb5d960aed92 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -73,14 +73,30 @@ int bch2_set_version_incompat(struct bch_fs *c, enum bcachefs_metadata_version v
 		? 0
 		: -BCH_ERR_may_not_use_incompat_feature;
 
+	mutex_lock(&c->sb_lock);
 	if (!ret) {
-		mutex_lock(&c->sb_lock);
 		SET_BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb,
 			max(BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb), version));
 		bch2_write_super(c);
-		mutex_unlock(&c->sb_lock);
+	} else {
+		darray_for_each(c->incompat_versions_requested, i)
+			if (version == *i)
+				goto out;
+
+		darray_push(&c->incompat_versions_requested, version);
+		struct printbuf buf = PRINTBUF;
+		prt_str(&buf, "requested incompat feature ");
+		bch2_version_to_text(&buf, version);
+		prt_str(&buf, " currently not enabled");
+		prt_printf(&buf, "\n  set version_upgrade=incompat to enable");
+
+		bch_notice(c, "%s", buf.buf);
+		printbuf_exit(&buf);
 	}
 
+out:
+	mutex_unlock(&c->sb_lock);
+
 	return ret;
 }
 
@@ -1086,7 +1102,8 @@ int bch2_write_super(struct bch_fs *c)
 		prt_str(&buf, ")");
 		bch2_fs_fatal_error(c, ": %s", buf.buf);
 		printbuf_exit(&buf);
-		return -BCH_ERR_sb_not_downgraded;
+		ret = -BCH_ERR_sb_not_downgraded;
+		goto out;
 	}
 
 	darray_for_each(online_devices, ca) {
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index a58edde43bee..84a37d971ffd 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -70,14 +70,10 @@
 #include <linux/percpu.h>
 #include <linux/random.h>
 #include <linux/sysfs.h>
-#include <crypto/hash.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Kent Overstreet <kent.overstreet@gmail.com>");
 MODULE_DESCRIPTION("bcachefs filesystem");
-MODULE_SOFTDEP("pre: chacha20");
-MODULE_SOFTDEP("pre: poly1305");
-MODULE_SOFTDEP("pre: xxhash");
 
 const char * const bch2_fs_flag_strs[] = {
 #define x(n)		#n,
@@ -381,6 +377,11 @@ void bch2_fs_read_only(struct bch_fs *c)
 		bch_verbose(c, "marking filesystem clean");
 		bch2_fs_mark_clean(c);
 	} else {
+		/* Make sure error counts/counters are persisted */
+		mutex_lock(&c->sb_lock);
+		bch2_write_super(c);
+		mutex_unlock(&c->sb_lock);
+
 		bch_verbose(c, "done going read-only, filesystem not clean");
 	}
 }
@@ -422,32 +423,6 @@ bool bch2_fs_emergency_read_only_locked(struct bch_fs *c)
 	return ret;
 }
 
-static int bch2_fs_read_write_late(struct bch_fs *c)
-{
-	int ret;
-
-	/*
-	 * Data move operations can't run until after check_snapshots has
-	 * completed, and bch2_snapshot_is_ancestor() is available.
-	 *
-	 * Ideally we'd start copygc/rebalance earlier instead of waiting for
-	 * all of recovery/fsck to complete:
-	 */
-	ret = bch2_copygc_start(c);
-	if (ret) {
-		bch_err(c, "error starting copygc thread");
-		return ret;
-	}
-
-	ret = bch2_rebalance_start(c);
-	if (ret) {
-		bch_err(c, "error starting rebalance thread");
-		return ret;
-	}
-
-	return 0;
-}
-
 static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 {
 	int ret;
@@ -470,29 +445,28 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 
 	clear_bit(BCH_FS_clean_shutdown, &c->flags);
 
+	__for_each_online_member(c, ca, BIT(BCH_MEMBER_STATE_rw), READ) {
+		bch2_dev_allocator_add(c, ca);
+		percpu_ref_reinit(&ca->io_ref[WRITE]);
+	}
+	bch2_recalc_capacity(c);
+
 	/*
 	 * First journal write must be a flush write: after a clean shutdown we
 	 * don't read the journal, so the first journal write may end up
 	 * overwriting whatever was there previously, and there must always be
 	 * at least one non-flush write in the journal or recovery will fail:
 	 */
+	spin_lock(&c->journal.lock);
 	set_bit(JOURNAL_need_flush_write, &c->journal.flags);
 	set_bit(JOURNAL_running, &c->journal.flags);
-
-	__for_each_online_member(c, ca, BIT(BCH_MEMBER_STATE_rw), READ) {
-		bch2_dev_allocator_add(c, ca);
-		percpu_ref_reinit(&ca->io_ref[WRITE]);
-	}
-	bch2_recalc_capacity(c);
+	bch2_journal_space_available(&c->journal);
+	spin_unlock(&c->journal.lock);
 
 	ret = bch2_fs_mark_dirty(c);
 	if (ret)
 		goto err;
 
-	spin_lock(&c->journal.lock);
-	bch2_journal_space_available(&c->journal);
-	spin_unlock(&c->journal.lock);
-
 	ret = bch2_journal_reclaim_start(&c->journal);
 	if (ret)
 		goto err;
@@ -508,10 +482,17 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 		atomic_long_inc(&c->writes[i]);
 	}
 #endif
-	if (!early) {
-		ret = bch2_fs_read_write_late(c);
-		if (ret)
-			goto err;
+
+	ret = bch2_copygc_start(c);
+	if (ret) {
+		bch_err_msg(c, ret, "error starting copygc thread");
+		goto err;
+	}
+
+	ret = bch2_rebalance_start(c);
+	if (ret) {
+		bch_err_msg(c, ret, "error starting rebalance thread");
+		goto err;
 	}
 
 	bch2_do_discards(c);
@@ -555,8 +536,13 @@ static void __bch2_fs_free(struct bch_fs *c)
 	for (unsigned i = 0; i < BCH_TIME_STAT_NR; i++)
 		bch2_time_stats_exit(&c->times[i]);
 
+#ifdef CONFIG_UNICODE
+	utf8_unload(c->cf_encoding);
+#endif
+
 	bch2_find_btree_nodes_exit(&c->found_btree_nodes);
 	bch2_free_pending_node_rewrites(c);
+	bch2_free_fsck_errs(c);
 	bch2_fs_accounting_exit(c);
 	bch2_fs_sb_errors_exit(c);
 	bch2_fs_counters_exit(c);
@@ -593,6 +579,7 @@ static void __bch2_fs_free(struct bch_fs *c)
 		free_percpu(c->online_reserved);
 	}
 
+	darray_exit(&c->incompat_versions_requested);
 	darray_exit(&c->btree_roots_extra);
 	free_percpu(c->pcpu);
 	free_percpu(c->usage);
@@ -845,25 +832,6 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 	if (ret)
 		goto err;
 
-#ifdef CONFIG_UNICODE
-	/* Default encoding until we can potentially have more as an option. */
-	c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING);
-	if (IS_ERR(c->cf_encoding)) {
-		printk(KERN_ERR "Cannot load UTF-8 encoding for filesystem. Version: %u.%u.%u",
-			unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
-			unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
-			unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
-		ret = -EINVAL;
-		goto err;
-	}
-#else
-	if (c->sb.features & BIT_ULL(BCH_FEATURE_casefolding)) {
-		printk(KERN_ERR "Cannot mount a filesystem with casefolding on a kernel without CONFIG_UNICODE\n");
-		ret = -EINVAL;
-		goto err;
-	}
-#endif
-
 	pr_uuid(&name, c->sb.user_uuid.b);
 	ret = name.allocation_failure ? -BCH_ERR_ENOMEM_fs_name_alloc : 0;
 	if (ret)
@@ -963,6 +931,29 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 	if (ret)
 		goto err;
 
+#ifdef CONFIG_UNICODE
+	/* Default encoding until we can potentially have more as an option. */
+	c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING);
+	if (IS_ERR(c->cf_encoding)) {
+		printk(KERN_ERR "Cannot load UTF-8 encoding for filesystem. Version: %u.%u.%u",
+			unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
+			unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
+			unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
+		ret = -EINVAL;
+		goto err;
+	}
+	bch_info(c, "Using encoding defined by superblock: utf8-%u.%u.%u",
+		 unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
+		 unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
+		 unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
+#else
+	if (c->sb.features & BIT_ULL(BCH_FEATURE_casefolding)) {
+		printk(KERN_ERR "Cannot mount a filesystem with casefolding on a kernel without CONFIG_UNICODE\n");
+		ret = -EINVAL;
+		goto err;
+	}
+#endif
+
 	for (i = 0; i < c->sb.nr_devices; i++) {
 		if (!bch2_member_exists(c->disk_sb.sb, i))
 			continue;
@@ -1002,12 +993,6 @@ static void print_mount_opts(struct bch_fs *c)
 	prt_str(&p, "starting version ");
 	bch2_version_to_text(&p, c->sb.version);
 
-	if (c->opts.read_only) {
-		prt_str(&p, " opts=");
-		first = false;
-		prt_printf(&p, "ro");
-	}
-
 	for (i = 0; i < bch2_opts_nr; i++) {
 		const struct bch_option *opt = &bch2_opt_table[i];
 		u64 v = bch2_opt_get_by_id(&c->opts, i);
@@ -1023,10 +1008,49 @@ static void print_mount_opts(struct bch_fs *c)
 		bch2_opt_to_text(&p, c, c->disk_sb.sb, opt, v, OPT_SHOW_MOUNT_STYLE);
 	}
 
+	if (c->sb.version_incompat_allowed != c->sb.version) {
+		prt_printf(&p, "\n  allowing incompatible features above ");
+		bch2_version_to_text(&p, c->sb.version_incompat_allowed);
+	}
+
 	bch_info(c, "%s", p.buf);
 	printbuf_exit(&p);
 }
 
+static bool bch2_fs_may_start(struct bch_fs *c)
+{
+	struct bch_dev *ca;
+	unsigned i, flags = 0;
+
+	if (c->opts.very_degraded)
+		flags |= BCH_FORCE_IF_DEGRADED|BCH_FORCE_IF_LOST;
+
+	if (c->opts.degraded)
+		flags |= BCH_FORCE_IF_DEGRADED;
+
+	if (!c->opts.degraded &&
+	    !c->opts.very_degraded) {
+		mutex_lock(&c->sb_lock);
+
+		for (i = 0; i < c->disk_sb.sb->nr_devices; i++) {
+			if (!bch2_member_exists(c->disk_sb.sb, i))
+				continue;
+
+			ca = bch2_dev_locked(c, i);
+
+			if (!bch2_dev_is_online(ca) &&
+			    (ca->mi.state == BCH_MEMBER_STATE_rw ||
+			     ca->mi.state == BCH_MEMBER_STATE_ro)) {
+				mutex_unlock(&c->sb_lock);
+				return false;
+			}
+		}
+		mutex_unlock(&c->sb_lock);
+	}
+
+	return bch2_have_enough_devs(c, bch2_online_devs(c), flags, true);
+}
+
 int bch2_fs_start(struct bch_fs *c)
 {
 	time64_t now = ktime_get_real_seconds();
@@ -1034,6 +1058,9 @@ int bch2_fs_start(struct bch_fs *c)
 
 	print_mount_opts(c);
 
+	if (!bch2_fs_may_start(c))
+		return -BCH_ERR_insufficient_devices_to_start;
+
 	down_write(&c->state_lock);
 	mutex_lock(&c->sb_lock);
 
@@ -1086,13 +1113,10 @@ int bch2_fs_start(struct bch_fs *c)
 	wake_up(&c->ro_ref_wait);
 
 	down_write(&c->state_lock);
-	if (c->opts.read_only) {
+	if (c->opts.read_only)
 		bch2_fs_read_only(c);
-	} else {
-		ret = !test_bit(BCH_FS_rw, &c->flags)
-			? bch2_fs_read_write(c)
-			: bch2_fs_read_write_late(c);
-	}
+	else if (!test_bit(BCH_FS_rw, &c->flags))
+		ret = bch2_fs_read_write(c);
 	up_write(&c->state_lock);
 
 err:
@@ -1504,7 +1528,7 @@ static int bch2_dev_attach_bdev(struct bch_fs *c, struct bch_sb_handle *sb)
 
 	printbuf_exit(&name);
 
-	rebalance_wakeup(c);
+	bch2_rebalance_wakeup(c);
 	return 0;
 }
 
@@ -1563,40 +1587,6 @@ bool bch2_dev_state_allowed(struct bch_fs *c, struct bch_dev *ca,
 	}
 }
 
-static bool bch2_fs_may_start(struct bch_fs *c)
-{
-	struct bch_dev *ca;
-	unsigned i, flags = 0;
-
-	if (c->opts.very_degraded)
-		flags |= BCH_FORCE_IF_DEGRADED|BCH_FORCE_IF_LOST;
-
-	if (c->opts.degraded)
-		flags |= BCH_FORCE_IF_DEGRADED;
-
-	if (!c->opts.degraded &&
-	    !c->opts.very_degraded) {
-		mutex_lock(&c->sb_lock);
-
-		for (i = 0; i < c->disk_sb.sb->nr_devices; i++) {
-			if (!bch2_member_exists(c->disk_sb.sb, i))
-				continue;
-
-			ca = bch2_dev_locked(c, i);
-
-			if (!bch2_dev_is_online(ca) &&
-			    (ca->mi.state == BCH_MEMBER_STATE_rw ||
-			     ca->mi.state == BCH_MEMBER_STATE_ro)) {
-				mutex_unlock(&c->sb_lock);
-				return false;
-			}
-		}
-		mutex_unlock(&c->sb_lock);
-	}
-
-	return bch2_have_enough_devs(c, bch2_online_devs(c), flags, true);
-}
-
 static void __bch2_dev_read_only(struct bch_fs *c, struct bch_dev *ca)
 {
 	bch2_dev_io_ref_stop(ca, WRITE);
@@ -1650,7 +1640,7 @@ int __bch2_dev_set_state(struct bch_fs *c, struct bch_dev *ca,
 	if (new_state == BCH_MEMBER_STATE_rw)
 		__bch2_dev_read_write(c, ca);
 
-	rebalance_wakeup(c);
+	bch2_rebalance_wakeup(c);
 
 	return ret;
 }
@@ -1767,7 +1757,8 @@ int bch2_dev_remove(struct bch_fs *c, struct bch_dev *ca, int flags)
 	up_write(&c->state_lock);
 	return 0;
 err:
-	if (ca->mi.state == BCH_MEMBER_STATE_rw &&
+	if (test_bit(BCH_FS_rw, &c->flags) &&
+	    ca->mi.state == BCH_MEMBER_STATE_rw &&
 	    !percpu_ref_is_zero(&ca->io_ref[READ]))
 		__bch2_dev_read_write(c, ca);
 	up_write(&c->state_lock);
@@ -2231,11 +2222,6 @@ struct bch_fs *bch2_fs_open(char * const *devices, unsigned nr_devices,
 	}
 	up_write(&c->state_lock);
 
-	if (!bch2_fs_may_start(c)) {
-		ret = -BCH_ERR_insufficient_devices_to_start;
-		goto err_print;
-	}
-
 	if (!c->opts.nostart) {
 		ret = bch2_fs_start(c);
 		if (ret)
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index e5f003c29369..82ee333ddd21 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -654,11 +654,10 @@ static ssize_t sysfs_opt_store(struct bch_fs *c,
 		bch2_set_rebalance_needs_scan(c, 0);
 
 	if (v && id == Opt_rebalance_enabled)
-		rebalance_wakeup(c);
+		bch2_rebalance_wakeup(c);
 
-	if (v && id == Opt_copygc_enabled &&
-	    c->copygc_thread)
-		wake_up_process(c->copygc_thread);
+	if (v && id == Opt_copygc_enabled)
+		bch2_copygc_wakeup(c);
 
 	if (id == Opt_discard && !ca) {
 		mutex_lock(&c->sb_lock);
diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c
index c265b102267a..782a05fe7656 100644
--- a/fs/bcachefs/tests.c
+++ b/fs/bcachefs/tests.c
@@ -342,6 +342,8 @@ static int test_iterate_slots_extents(struct bch_fs *c, u64 nr)
  */
 static int test_peek_end(struct bch_fs *c, u64 nr)
 {
+	delete_test_keys(c);
+
 	struct btree_trans *trans = bch2_trans_get(c);
 	struct btree_iter iter;
 	struct bkey_s_c k;
@@ -362,6 +364,8 @@ static int test_peek_end(struct bch_fs *c, u64 nr)
 
 static int test_peek_end_extents(struct bch_fs *c, u64 nr)
 {
+	delete_test_keys(c);
+
 	struct btree_trans *trans = bch2_trans_get(c);
 	struct btree_iter iter;
 	struct bkey_s_c k;
diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c
index dea73bc1cb51..314a24d15d4e 100644
--- a/fs/bcachefs/thread_with_file.c
+++ b/fs/bcachefs/thread_with_file.c
@@ -455,8 +455,10 @@ ssize_t bch2_stdio_redirect_vprintf(struct stdio_redirect *stdio, bool nonblocki
 	struct stdio_buf *buf = &stdio->output;
 	unsigned long flags;
 	ssize_t ret;
-
 again:
+	if (stdio->done)
+		return -EPIPE;
+
 	spin_lock_irqsave(&buf->lock, flags);
 	ret = bch2_darray_vprintf(&buf->buf, GFP_NOWAIT, fmt, args);
 	spin_unlock_irqrestore(&buf->lock, flags);
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index 6ba5071ab6dd..3e52c7f8ddd2 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -739,4 +739,42 @@ static inline void memcpy_swab(void *_dst, void *_src, size_t len)
 		*--dst = *src++;
 }
 
+#define set_flags(_map, _in, _out)					\
+do {									\
+	unsigned _i;							\
+									\
+	for (_i = 0; _i < ARRAY_SIZE(_map); _i++)			\
+		if ((_in) & (1 << _i))					\
+			(_out) |= _map[_i];				\
+		else							\
+			(_out) &= ~_map[_i];				\
+} while (0)
+
+#define map_flags(_map, _in)						\
+({									\
+	unsigned _out = 0;						\
+									\
+	set_flags(_map, _in, _out);					\
+	_out;								\
+})
+
+#define map_flags_rev(_map, _in)					\
+({									\
+	unsigned _i, _out = 0;						\
+									\
+	for (_i = 0; _i < ARRAY_SIZE(_map); _i++)			\
+		if ((_in) & _map[_i]) {					\
+			(_out) |= 1 << _i;				\
+			(_in) &= ~_map[_i];				\
+		}							\
+	(_out);								\
+})
+
+#define map_defined(_map)						\
+({									\
+	unsigned _in = ~0;						\
+									\
+	map_flags_rev(_map, _in);					\
+})
+
 #endif /* _BCACHEFS_UTIL_H */
diff --git a/fs/bcachefs/xattr_format.h b/fs/bcachefs/xattr_format.h
index c7916011ef34..67426e33d04e 100644
--- a/fs/bcachefs/xattr_format.h
+++ b/fs/bcachefs/xattr_format.h
@@ -13,7 +13,13 @@ struct bch_xattr {
 	__u8			x_type;
 	__u8			x_name_len;
 	__le16			x_val_len;
-	__u8			x_name[] __counted_by(x_name_len);
+	/*
+	 * x_name contains the name and value counted by
+	 * x_name_len + x_val_len. The introduction of
+	 * __counted_by(x_name_len) caused a false positive
+	 * detection of an out of bounds write.
+	 */
+	__u8			x_name[];
 } __packed __aligned(8);
 
 #endif /* _BCACHEFS_XATTR_FORMAT_H */
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 584fa89bc877..4c1ea6b52a53 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -830,6 +830,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL;
 	struct elf_phdr *elf_property_phdata = NULL;
 	unsigned long elf_brk;
+	bool brk_moved = false;
 	int retval, i;
 	unsigned long elf_entry;
 	unsigned long e_entry;
@@ -1097,15 +1098,19 @@ out_free_interp:
 			/* Calculate any requested alignment. */
 			alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
 
-			/*
-			 * There are effectively two types of ET_DYN
-			 * binaries: programs (i.e. PIE: ET_DYN with PT_INTERP)
-			 * and loaders (ET_DYN without PT_INTERP, since they
-			 * _are_ the ELF interpreter). The loaders must
-			 * be loaded away from programs since the program
-			 * may otherwise collide with the loader (especially
-			 * for ET_EXEC which does not have a randomized
-			 * position). For example to handle invocations of
+			/**
+			 * DOC: PIE handling
+			 *
+			 * There are effectively two types of ET_DYN ELF
+			 * binaries: programs (i.e. PIE: ET_DYN with
+			 * PT_INTERP) and loaders (i.e. static PIE: ET_DYN
+			 * without PT_INTERP, usually the ELF interpreter
+			 * itself). Loaders must be loaded away from programs
+			 * since the program may otherwise collide with the
+			 * loader (especially for ET_EXEC which does not have
+			 * a randomized position).
+			 *
+			 * For example, to handle invocations of
 			 * "./ld.so someprog" to test out a new version of
 			 * the loader, the subsequent program that the
 			 * loader loads must avoid the loader itself, so
@@ -1118,6 +1123,9 @@ out_free_interp:
 			 * ELF_ET_DYN_BASE and loaders are loaded into the
 			 * independently randomized mmap region (0 load_bias
 			 * without MAP_FIXED nor MAP_FIXED_NOREPLACE).
+			 *
+			 * See below for "brk" handling details, which is
+			 * also affected by program vs loader and ASLR.
 			 */
 			if (interpreter) {
 				/* On ET_DYN with PT_INTERP, we do the ASLR. */
@@ -1234,8 +1242,6 @@ out_free_interp:
 	start_data += load_bias;
 	end_data += load_bias;
 
-	current->mm->start_brk = current->mm->brk = ELF_PAGEALIGN(elf_brk);
-
 	if (interpreter) {
 		elf_entry = load_elf_interp(interp_elf_ex,
 					    interpreter,
@@ -1291,27 +1297,44 @@ out_free_interp:
 	mm->end_data = end_data;
 	mm->start_stack = bprm->p;
 
-	if ((current->flags & PF_RANDOMIZE) && (snapshot_randomize_va_space > 1)) {
+	/**
+	 * DOC: "brk" handling
+	 *
+	 * For architectures with ELF randomization, when executing a
+	 * loader directly (i.e. static PIE: ET_DYN without PT_INTERP),
+	 * move the brk area out of the mmap region and into the unused
+	 * ELF_ET_DYN_BASE region. Since "brk" grows up it may collide
+	 * early with the stack growing down or other regions being put
+	 * into the mmap region by the kernel (e.g. vdso).
+	 *
+	 * In the CONFIG_COMPAT_BRK case, though, everything is turned
+	 * off because we're not allowed to move the brk at all.
+	 */
+	if (!IS_ENABLED(CONFIG_COMPAT_BRK) &&
+	    IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
+	    elf_ex->e_type == ET_DYN && !interpreter) {
+		elf_brk = ELF_ET_DYN_BASE;
+		/* This counts as moving the brk, so let brk(2) know. */
+		brk_moved = true;
+	}
+	mm->start_brk = mm->brk = ELF_PAGEALIGN(elf_brk);
+
+	if ((current->flags & PF_RANDOMIZE) && snapshot_randomize_va_space > 1) {
 		/*
-		 * For architectures with ELF randomization, when executing
-		 * a loader directly (i.e. no interpreter listed in ELF
-		 * headers), move the brk area out of the mmap region
-		 * (since it grows up, and may collide early with the stack
-		 * growing down), and into the unused ELF_ET_DYN_BASE region.
+		 * If we didn't move the brk to ELF_ET_DYN_BASE (above),
+		 * leave a gap between .bss and brk.
 		 */
-		if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
-		    elf_ex->e_type == ET_DYN && !interpreter) {
-			mm->brk = mm->start_brk = ELF_ET_DYN_BASE;
-		} else {
-			/* Otherwise leave a gap between .bss and brk. */
+		if (!brk_moved)
 			mm->brk = mm->start_brk = mm->brk + PAGE_SIZE;
-		}
 
 		mm->brk = mm->start_brk = arch_randomize_brk(mm);
+		brk_moved = true;
+	}
+
 #ifdef compat_brk_randomized
+	if (brk_moved)
 		current->brk_randomized = 1;
 #endif
-	}
 
 	if (current->personality & MMAP_PAGE_ZERO) {
 		/* Why this, you ask???  Well SVr4 maps page 0 as read-only,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index e7f8ee5d48a4..7f11ef559be6 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -606,7 +606,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 	free_extent_map(em);
 
 	cb->nr_folios = DIV_ROUND_UP(compressed_len, PAGE_SIZE);
-	cb->compressed_folios = kcalloc(cb->nr_folios, sizeof(struct page *), GFP_NOFS);
+	cb->compressed_folios = kcalloc(cb->nr_folios, sizeof(struct folio *), GFP_NOFS);
 	if (!cb->compressed_folios) {
 		ret = BLK_STS_RESOURCE;
 		goto out_free_bio;
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index d6eef4bd9e9d..de23c4b3515e 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -94,8 +94,6 @@ static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
 				  struct btrfs_block_group *block_group)
 {
 	lockdep_assert_held(&discard_ctl->lock);
-	if (!btrfs_run_discard_work(discard_ctl))
-		return;
 
 	if (list_empty(&block_group->discard_list) ||
 	    block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED) {
@@ -118,6 +116,9 @@ static void add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
 	if (!btrfs_is_block_group_data_only(block_group))
 		return;
 
+	if (!btrfs_run_discard_work(discard_ctl))
+		return;
+
 	spin_lock(&discard_ctl->lock);
 	__add_to_discard_list(discard_ctl, block_group);
 	spin_unlock(&discard_ctl->lock);
@@ -244,6 +245,18 @@ again:
 		    block_group->used != 0) {
 			if (btrfs_is_block_group_data_only(block_group)) {
 				__add_to_discard_list(discard_ctl, block_group);
+				/*
+				 * The block group must have been moved to other
+				 * discard list even if discard was disabled in
+				 * the meantime or a transaction abort happened,
+				 * otherwise we can end up in an infinite loop,
+				 * always jumping into the 'again' label and
+				 * keep getting this block group over and over
+				 * in case there are no other block groups in
+				 * the discard lists.
+				 */
+				ASSERT(block_group->discard_index !=
+				       BTRFS_DISCARD_INDEX_UNUSED);
 			} else {
 				list_del_init(&block_group->discard_list);
 				btrfs_put_block_group(block_group);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3dd555db3d32..aa58e0663a5d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3853,7 +3853,6 @@ static int write_dev_supers(struct btrfs_device *device,
 			atomic_inc(&device->sb_write_errors);
 			continue;
 		}
-		ASSERT(folio_order(folio) == 0);
 
 		offset = offset_in_folio(folio, bytenr);
 		disk_super = folio_address(folio) + offset;
@@ -3926,7 +3925,6 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
 		/* If the folio has been removed, then we know it completed. */
 		if (IS_ERR(folio))
 			continue;
-		ASSERT(folio_order(folio) == 0);
 
 		/* Folio will be unlocked once the write completes. */
 		folio_wait_locked(folio);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 197f5e51c474..13bdd60da3c7 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2047,7 +2047,7 @@ static int submit_eb_subpage(struct folio *folio, struct writeback_control *wbc)
 			      subpage->bitmaps)) {
 			spin_unlock_irqrestore(&subpage->lock, flags);
 			spin_unlock(&folio->mapping->i_private_lock);
-			bit_start++;
+			bit_start += sectors_per_node;
 			continue;
 		}
 
@@ -3508,8 +3508,8 @@ static void btree_clear_folio_dirty_tag(struct folio *folio)
 	ASSERT(folio_test_locked(folio));
 	xa_lock_irq(&folio->mapping->i_pages);
 	if (!folio_test_dirty(folio))
-		__xa_clear_mark(&folio->mapping->i_pages,
-				folio_index(folio), PAGECACHE_TAG_DIRTY);
+		__xa_clear_mark(&folio->mapping->i_pages, folio->index,
+				PAGECACHE_TAG_DIRTY);
 	xa_unlock_irq(&folio->mapping->i_pages);
 }
 
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 2e261892c7bc..f5b28b5c4908 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -298,6 +298,8 @@ static inline int __pure num_extent_pages(const struct extent_buffer *eb)
  */
 static inline int __pure num_extent_folios(const struct extent_buffer *eb)
 {
+	if (!eb->folios[0])
+		return 0;
 	if (folio_order(eb->folios[0]))
 		return 1;
 	return num_extent_pages(eb);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 262a707d8990..71b8a825c447 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2104,15 +2104,20 @@ static void btrfs_punch_hole_lock_range(struct inode *inode,
 	 * will always return true.
 	 * So here we need to do extra page alignment for
 	 * filemap_range_has_page().
+	 *
+	 * And do not decrease page_lockend right now, as it can be 0.
 	 */
 	const u64 page_lockstart = round_up(lockstart, PAGE_SIZE);
-	const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE) - 1;
+	const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE);
 
 	while (1) {
 		truncate_pagecache_range(inode, lockstart, lockend);
 
 		lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			    cached_state);
+		/* The same page or adjacent pages. */
+		if (page_lockend <= page_lockstart)
+			break;
 		/*
 		 * We can't have ordered extents in the range, nor dirty/writeback
 		 * pages, because we have locked the inode's VFS lock in exclusive
@@ -2124,7 +2129,7 @@ static void btrfs_punch_hole_lock_range(struct inode *inode,
 		 * we do, unlock the range and retry.
 		 */
 		if (!filemap_range_has_page(inode->i_mapping, page_lockstart,
-					    page_lockend))
+					    page_lockend - 1))
 			break;
 
 		unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index bcca43046064..7baa2ed45198 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -300,6 +300,7 @@ enum {
 #define BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR		0ULL
 
 #define BTRFS_DEFAULT_COMMIT_INTERVAL	(30)
+#define BTRFS_WARNING_COMMIT_INTERVAL	(300)
 #define BTRFS_DEFAULT_MAX_INLINE	(2048)
 
 struct btrfs_dev_replace {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index cc67d1a2d611..90f5da3c520a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1109,6 +1109,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 	struct extent_state *cached = NULL;
 	struct extent_map *em;
 	int ret = 0;
+	bool free_pages = false;
 	u64 start = async_extent->start;
 	u64 end = async_extent->start + async_extent->ram_size - 1;
 
@@ -1129,7 +1130,10 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 	}
 
 	if (async_extent->compress_type == BTRFS_COMPRESS_NONE) {
+		ASSERT(!async_extent->folios);
+		ASSERT(async_extent->nr_folios == 0);
 		submit_uncompressed_range(inode, async_extent, locked_folio);
+		free_pages = true;
 		goto done;
 	}
 
@@ -1145,6 +1149,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 		 * fall back to uncompressed.
 		 */
 		submit_uncompressed_range(inode, async_extent, locked_folio);
+		free_pages = true;
 		goto done;
 	}
 
@@ -1186,6 +1191,8 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 done:
 	if (async_chunk->blkcg_css)
 		kthread_associate_blkcg(NULL);
+	if (free_pages)
+		free_async_extent_pages(async_extent);
 	kfree(async_extent);
 	return;
 
@@ -2129,12 +2136,13 @@ next_slot:
 
 		/*
 		 * If the found extent starts after requested offset, then
-		 * adjust extent_end to be right before this extent begins
+		 * adjust cur_offset to be right before this extent begins.
 		 */
 		if (found_key.offset > cur_offset) {
-			extent_end = found_key.offset;
-			extent_type = 0;
-			goto must_cow;
+			if (cow_start == (u64)-1)
+				cow_start = cur_offset;
+			cur_offset = found_key.offset;
+			goto next_slot;
 		}
 
 		/*
@@ -5681,8 +5689,10 @@ struct btrfs_inode *btrfs_iget(u64 ino, struct btrfs_root *root)
 		return inode;
 
 	path = btrfs_alloc_path();
-	if (!path)
+	if (!path) {
+		iget_failed(&inode->vfs_inode);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	ret = btrfs_read_locked_inode(inode, path);
 	btrfs_free_path(path);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a13d81bb56a0..63aeacc54945 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4902,6 +4902,8 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue
 
 	ret = btrfs_encoded_read(&kiocb, &data->iter, &data->args, &cached_state,
 				 &disk_bytenr, &disk_io_size);
+	if (ret == -EAGAIN)
+		goto out_acct;
 	if (ret < 0 && ret != -EIOCBQUEUED)
 		goto out_free;
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index f948f4f6431c..e17bcb034595 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3803,7 +3803,7 @@ out:
 	if (ret) {
 		if (inode)
 			iput(&inode->vfs_inode);
-		inode = ERR_PTR(ret);
+		return ERR_PTR(ret);
 	}
 	return &inode->vfs_inode;
 }
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 2c5edcee9450..c3b2e29e3e01 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1541,8 +1541,8 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
 	u64 extent_gen;
 	int ret;
 
-	if (unlikely(!extent_root)) {
-		btrfs_err(fs_info, "no valid extent root for scrub");
+	if (unlikely(!extent_root || !csum_root)) {
+		btrfs_err(fs_info, "no valid extent or csum root for scrub");
 		return -EUCLEAN;
 	}
 	memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) *
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 11dbd7be6a3b..c0a0b8b063d0 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -204,7 +204,7 @@ static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
 			   btrfs_blocks_per_folio(fs_info, folio);	\
 									\
 	btrfs_subpage_assert(fs_info, folio, start, len);		\
-	__start_bit = offset_in_page(start) >> fs_info->sectorsize_bits; \
+	__start_bit = offset_in_folio(folio, start) >> fs_info->sectorsize_bits; \
 	__start_bit += blocks_per_folio * btrfs_bitmap_nr_##name;	\
 	__start_bit;							\
 })
@@ -666,7 +666,7 @@ IMPLEMENT_BTRFS_PAGE_OPS(checked, folio_set_checked, folio_clear_checked,
 				btrfs_blocks_per_folio(fs_info, folio);	\
 	const struct btrfs_subpage *subpage = folio_get_private(folio);	\
 									\
-	ASSERT(blocks_per_folio < BITS_PER_LONG);			\
+	ASSERT(blocks_per_folio <= BITS_PER_LONG);			\
 	*dst = bitmap_read(subpage->bitmaps,				\
 			   blocks_per_folio * btrfs_bitmap_nr_##name,	\
 			   blocks_per_folio);				\
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 40709e2a44fc..7310e2fa8526 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -569,6 +569,10 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		break;
 	case Opt_commit_interval:
 		ctx->commit_interval = result.uint_32;
+		if (ctx->commit_interval > BTRFS_WARNING_COMMIT_INTERVAL) {
+			btrfs_warn(NULL, "excessive commit interval %u, use with care",
+				   ctx->commit_interval);
+		}
 		if (ctx->commit_interval == 0)
 			ctx->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
 		break;
@@ -1139,8 +1143,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 	subvol_name = btrfs_get_subvol_name_from_objectid(info,
 			btrfs_root_id(BTRFS_I(d_inode(dentry))->root));
 	if (!IS_ERR(subvol_name)) {
-		seq_puts(seq, ",subvol=");
-		seq_escape(seq, subvol_name, " \t\n\\");
+		seq_show_option(seq, "subvol", subvol_name);
 		kfree(subvol_name);
 	}
 	return 0;
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 43979891f7c8..2b66a6130269 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -2235,7 +2235,7 @@ int btrfs_verify_level_key(struct extent_buffer *eb,
 		btrfs_err(fs_info,
 "tree level mismatch detected, bytenr=%llu level expected=%u has=%u",
 			  eb->start, check->level, found_level);
-		return -EIO;
+		return -EUCLEAN;
 	}
 
 	if (!check->has_first_key)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c8c21c55be53..8e6b6fed7429 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -733,82 +733,6 @@ const u8 *btrfs_sb_fsid_ptr(const struct btrfs_super_block *sb)
 	return has_metadata_uuid ? sb->metadata_uuid : sb->fsid;
 }
 
-/*
- * We can have very weird soft links passed in.
- * One example is "/proc/self/fd/<fd>", which can be a soft link to
- * a block device.
- *
- * But it's never a good idea to use those weird names.
- * Here we check if the path (not following symlinks) is a good one inside
- * "/dev/".
- */
-static bool is_good_dev_path(const char *dev_path)
-{
-	struct path path = { .mnt = NULL, .dentry = NULL };
-	char *path_buf = NULL;
-	char *resolved_path;
-	bool is_good = false;
-	int ret;
-
-	if (!dev_path)
-		goto out;
-
-	path_buf = kmalloc(PATH_MAX, GFP_KERNEL);
-	if (!path_buf)
-		goto out;
-
-	/*
-	 * Do not follow soft link, just check if the original path is inside
-	 * "/dev/".
-	 */
-	ret = kern_path(dev_path, 0, &path);
-	if (ret)
-		goto out;
-	resolved_path = d_path(&path, path_buf, PATH_MAX);
-	if (IS_ERR(resolved_path))
-		goto out;
-	if (strncmp(resolved_path, "/dev/", strlen("/dev/")))
-		goto out;
-	is_good = true;
-out:
-	kfree(path_buf);
-	path_put(&path);
-	return is_good;
-}
-
-static int get_canonical_dev_path(const char *dev_path, char *canonical)
-{
-	struct path path = { .mnt = NULL, .dentry = NULL };
-	char *path_buf = NULL;
-	char *resolved_path;
-	int ret;
-
-	if (!dev_path) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	path_buf = kmalloc(PATH_MAX, GFP_KERNEL);
-	if (!path_buf) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	ret = kern_path(dev_path, LOOKUP_FOLLOW, &path);
-	if (ret)
-		goto out;
-	resolved_path = d_path(&path, path_buf, PATH_MAX);
-	if (IS_ERR(resolved_path)) {
-		ret = PTR_ERR(resolved_path);
-		goto out;
-	}
-	ret = strscpy(canonical, resolved_path, PATH_MAX);
-out:
-	kfree(path_buf);
-	path_put(&path);
-	return ret;
-}
-
 static bool is_same_device(struct btrfs_device *device, const char *new_path)
 {
 	struct path old = { .mnt = NULL, .dentry = NULL };
@@ -1513,23 +1437,12 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
 	bool new_device_added = false;
 	struct btrfs_device *device = NULL;
 	struct file *bdev_file;
-	char *canonical_path = NULL;
 	u64 bytenr;
 	dev_t devt;
 	int ret;
 
 	lockdep_assert_held(&uuid_mutex);
 
-	if (!is_good_dev_path(path)) {
-		canonical_path = kmalloc(PATH_MAX, GFP_KERNEL);
-		if (canonical_path) {
-			ret = get_canonical_dev_path(path, canonical_path);
-			if (ret < 0) {
-				kfree(canonical_path);
-				canonical_path = NULL;
-			}
-		}
-	}
 	/*
 	 * Avoid an exclusive open here, as the systemd-udev may initiate the
 	 * device scan which may race with the user's mount or mkfs command,
@@ -1574,8 +1487,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
 		goto free_disk_super;
 	}
 
-	device = device_list_add(canonical_path ? : path, disk_super,
-				 &new_device_added);
+	device = device_list_add(path, disk_super, &new_device_added);
 	if (!IS_ERR(device) && new_device_added)
 		btrfs_free_stale_devices(device->devt, device);
 
@@ -1584,7 +1496,6 @@ free_disk_super:
 
 error_bdev_put:
 	fput(bdev_file);
-	kfree(canonical_path);
 
 	return device;
 }
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index fb8b8b29c169..4a3e02b49f29 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1277,7 +1277,7 @@ struct zone_info {
 
 static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 				struct zone_info *info, unsigned long *active,
-				struct btrfs_chunk_map *map)
+				struct btrfs_chunk_map *map, bool new)
 {
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 	struct btrfs_device *device;
@@ -1307,6 +1307,8 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 		return 0;
 	}
 
+	ASSERT(!new || btrfs_dev_is_empty_zone(device, info->physical));
+
 	/* This zone will be used for allocation, so mark this zone non-empty. */
 	btrfs_dev_clear_zone_empty(device, info->physical);
 
@@ -1319,6 +1321,18 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 	 * to determine the allocation offset within the zone.
 	 */
 	WARN_ON(!IS_ALIGNED(info->physical, fs_info->zone_size));
+
+	if (new) {
+		sector_t capacity;
+
+		capacity = bdev_zone_capacity(device->bdev, info->physical >> SECTOR_SHIFT);
+		up_read(&dev_replace->rwsem);
+		info->alloc_offset = 0;
+		info->capacity = capacity << SECTOR_SHIFT;
+
+		return 0;
+	}
+
 	nofs_flag = memalloc_nofs_save();
 	ret = btrfs_get_dev_zone(device, info->physical, &zone);
 	memalloc_nofs_restore(nofs_flag);
@@ -1588,7 +1602,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	}
 
 	for (i = 0; i < map->num_stripes; i++) {
-		ret = btrfs_load_zone_info(fs_info, i, &zone_info[i], active, map);
+		ret = btrfs_load_zone_info(fs_info, i, &zone_info[i], active, map, new);
 		if (ret)
 			goto out;
 
@@ -1659,7 +1673,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		 * stripe.
 		 */
 		cache->alloc_offset = cache->zone_capacity;
-		ret = 0;
 	}
 
 out:
diff --git a/fs/buffer.c b/fs/buffer.c
index c7abb4a029dc..7ba1807145aa 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -176,18 +176,8 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 }
 EXPORT_SYMBOL(end_buffer_write_sync);
 
-/*
- * Various filesystems appear to want __find_get_block to be non-blocking.
- * But it's the page lock which protects the buffers.  To get around this,
- * we get exclusion from try_to_free_buffers with the blockdev mapping's
- * i_private_lock.
- *
- * Hack idea: for the blockdev mapping, i_private_lock contention
- * may be quite high.  This code could TryLock the page, and if that
- * succeeds, there is no need to take i_private_lock.
- */
 static struct buffer_head *
-__find_get_block_slow(struct block_device *bdev, sector_t block)
+__find_get_block_slow(struct block_device *bdev, sector_t block, bool atomic)
 {
 	struct address_space *bd_mapping = bdev->bd_mapping;
 	const int blkbits = bd_mapping->host->i_blkbits;
@@ -204,10 +194,28 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	if (IS_ERR(folio))
 		goto out;
 
-	spin_lock(&bd_mapping->i_private_lock);
+	/*
+	 * Folio lock protects the buffers. Callers that cannot block
+	 * will fallback to serializing vs try_to_free_buffers() via
+	 * the i_private_lock.
+	 */
+	if (atomic)
+		spin_lock(&bd_mapping->i_private_lock);
+	else
+		folio_lock(folio);
+
 	head = folio_buffers(folio);
 	if (!head)
 		goto out_unlock;
+	/*
+	 * Upon a noref migration, the folio lock serializes here;
+	 * otherwise bail.
+	 */
+	if (test_bit_acquire(BH_Migrate, &head->b_state)) {
+		WARN_ON(!atomic);
+		goto out_unlock;
+	}
+
 	bh = head;
 	do {
 		if (!buffer_mapped(bh))
@@ -236,7 +244,10 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 		       1 << blkbits);
 	}
 out_unlock:
-	spin_unlock(&bd_mapping->i_private_lock);
+	if (atomic)
+		spin_unlock(&bd_mapping->i_private_lock);
+	else
+		folio_unlock(folio);
 	folio_put(folio);
 out:
 	return ret;
@@ -656,7 +667,9 @@ EXPORT_SYMBOL(generic_buffers_fsync);
 void write_boundary_block(struct block_device *bdev,
 			sector_t bblock, unsigned blocksize)
 {
-	struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
+	struct buffer_head *bh;
+
+	bh = __find_get_block_nonatomic(bdev, bblock + 1, blocksize);
 	if (bh) {
 		if (buffer_dirty(bh))
 			write_dirty_buffer(bh, 0);
@@ -1207,10 +1220,8 @@ void mark_buffer_write_io_error(struct buffer_head *bh)
 	/* FIXME: do we need to set this in both places? */
 	if (bh->b_folio && bh->b_folio->mapping)
 		mapping_set_error(bh->b_folio->mapping, -EIO);
-	if (bh->b_assoc_map) {
+	if (bh->b_assoc_map)
 		mapping_set_error(bh->b_assoc_map, -EIO);
-		errseq_set(&bh->b_assoc_map->host->i_sb->s_wb_err, -EIO);
-	}
 }
 EXPORT_SYMBOL(mark_buffer_write_io_error);
 
@@ -1386,16 +1397,18 @@ lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
 /*
  * Perform a pagecache lookup for the matching buffer.  If it's there, refresh
  * it in the LRU and mark it as accessed.  If it is not present then return
- * NULL
+ * NULL. Atomic context callers may also return NULL if the buffer is being
+ * migrated; similarly the page is not marked accessed either.
  */
-struct buffer_head *
-__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
+static struct buffer_head *
+find_get_block_common(struct block_device *bdev, sector_t block,
+			unsigned size, bool atomic)
 {
 	struct buffer_head *bh = lookup_bh_lru(bdev, block, size);
 
 	if (bh == NULL) {
 		/* __find_get_block_slow will mark the page accessed */
-		bh = __find_get_block_slow(bdev, block);
+		bh = __find_get_block_slow(bdev, block, atomic);
 		if (bh)
 			bh_lru_install(bh);
 	} else
@@ -1403,8 +1416,23 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size)
 
 	return bh;
 }
+
+struct buffer_head *
+__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
+{
+	return find_get_block_common(bdev, block, size, true);
+}
 EXPORT_SYMBOL(__find_get_block);
 
+/* same as __find_get_block() but allows sleeping contexts */
+struct buffer_head *
+__find_get_block_nonatomic(struct block_device *bdev, sector_t block,
+			   unsigned size)
+{
+	return find_get_block_common(bdev, block, size, false);
+}
+EXPORT_SYMBOL(__find_get_block_nonatomic);
+
 /**
  * bdev_getblk - Get a buffer_head in a block device's buffer cache.
  * @bdev: The block device.
@@ -1422,7 +1450,12 @@ EXPORT_SYMBOL(__find_get_block);
 struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
 		unsigned size, gfp_t gfp)
 {
-	struct buffer_head *bh = __find_get_block(bdev, block, size);
+	struct buffer_head *bh;
+
+	if (gfpflags_allow_blocking(gfp))
+		bh = __find_get_block_nonatomic(bdev, block, size);
+	else
+		bh = __find_get_block(bdev, block, size);
 
 	might_alloc(gfp);
 	if (bh)
diff --git a/fs/cachefiles/key.c b/fs/cachefiles/key.c
index bf935e25bdbe..b48525680e73 100644
--- a/fs/cachefiles/key.c
+++ b/fs/cachefiles/key.c
@@ -8,7 +8,7 @@
 #include <linux/slab.h>
 #include "internal.h"
 
-static const char cachefiles_charmap[64] =
+static const char cachefiles_charmap[64] __nonstring =
 	"0123456789"			/* 0 - 9 */
 	"abcdefghijklmnopqrstuvwxyz"	/* 10 - 35 */
 	"ABCDEFGHIJKLMNOPQRSTUVWXYZ"	/* 36 - 61 */
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 6ac2bd555e86..06cd2963e41e 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -2367,7 +2367,7 @@ static int fill_fscrypt_truncate(struct inode *inode,
 
 	/* Try to writeback the dirty pagecaches */
 	if (issued & (CEPH_CAP_FILE_BUFFER)) {
-		loff_t lend = orig_pos + CEPH_FSCRYPT_BLOCK_SHIFT - 1;
+		loff_t lend = orig_pos + CEPH_FSCRYPT_BLOCK_SIZE - 1;
 
 		ret = filemap_write_and_wait_range(inode->i_mapping,
 						   orig_pos, lend);
diff --git a/fs/dax.c b/fs/dax.c
index af5045b0f476..676303419e9e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -396,6 +396,7 @@ static inline unsigned long dax_folio_put(struct folio *folio)
 	order = folio_order(folio);
 	if (!order)
 		return 0;
+	folio_reset_order(folio);
 
 	for (i = 0; i < (1UL << order); i++) {
 		struct dev_pagemap *pgmap = page_pgmap(&folio->page);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 42e4d6eeb29f..9c20d78e41f6 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -89,12 +89,12 @@ enum {
 };
 
 static const struct fs_parameter_spec devpts_param_specs[] = {
-	fsparam_u32	("gid",		Opt_gid),
+	fsparam_gid	("gid",		Opt_gid),
 	fsparam_s32	("max",		Opt_max),
 	fsparam_u32oct	("mode",	Opt_mode),
 	fsparam_flag	("newinstance",	Opt_newinstance),
 	fsparam_u32oct	("ptmxmode",	Opt_ptmxmode),
-	fsparam_u32	("uid",		Opt_uid),
+	fsparam_uid	("uid",		Opt_uid),
 	{}
 };
 
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 9581e9bf8192..767fb4acdc93 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -56,7 +56,7 @@ struct erofs_super_block {
 	union {
 		__le16 rootnid_2b;	/* nid of root directory */
 		__le16 blocks_hi;	/* (48BIT on) blocks count MSB */
-	} rb;
+	} __packed rb;
 	__le64 inos;            /* total valid ino # (== f_files - f_favail) */
 	__le64 epoch;		/* base seconds used for compact inodes */
 	__le32 fixed_nsec;	/* fixed nanoseconds for compact inodes */
@@ -148,7 +148,7 @@ union erofs_inode_i_nb {
 	__le16 nlink;		/* if EROFS_I_NLINK_1_BIT is unset */
 	__le16 blocks_hi;	/* total blocks count MSB */
 	__le16 startblk_hi;	/* starting block number MSB */
-};
+} __packed;
 
 /* 32-byte reduced form of an ondisk inode */
 struct erofs_inode_compact {
@@ -369,9 +369,9 @@ struct z_erofs_map_header {
 			 * bit 7   : pack the whole file into packed inode
 			 */
 			__u8	h_clusterbits;
-		};
+		} __packed;
 		__le16 h_extents_hi;	/* extent count MSB */
-	};
+	} __packed;
 };
 
 enum {
diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index bec4b56b3826..60c7cc4c105c 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -32,6 +32,8 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret)
 		ret = 0;
 	}
 	if (rq->bio.bi_end_io) {
+		if (ret < 0 && !rq->bio.bi_status)
+			rq->bio.bi_status = errno_to_blk_status(ret);
 		rq->bio.bi_end_io(&rq->bio);
 	} else {
 		bio_for_each_folio_all(fi, &rq->bio) {
@@ -148,10 +150,10 @@ io_retry:
 				io->rq->bio.bi_iter.bi_sector = io->dev.m_pa >> 9;
 				attached = 0;
 			}
-			if (!attached++)
-				erofs_onlinefolio_split(folio);
 			if (!bio_add_folio(&io->rq->bio, folio, len, cur))
 				goto io_retry;
+			if (!attached++)
+				erofs_onlinefolio_split(folio);
 			io->dev.m_pa += len;
 		}
 		cur += len;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index cadec6b1b554..da6ee7c39290 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -357,7 +357,6 @@ static void erofs_default_options(struct erofs_sb_info *sbi)
 enum {
 	Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum,
 	Opt_device, Opt_fsid, Opt_domain_id, Opt_directio,
-	Opt_err
 };
 
 static const struct constant_table erofs_param_cache_strategy[] = {
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 0671184d9cf1..b8e6b76c23d5 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -79,9 +79,6 @@ struct z_erofs_pcluster {
 	/* L: whether partial decompression or not */
 	bool partial;
 
-	/* L: indicate several pageofs_outs or not */
-	bool multibases;
-
 	/* L: whether extra buffer allocations are best-effort */
 	bool besteffort;
 
@@ -725,7 +722,6 @@ static int z_erofs_register_pcluster(struct z_erofs_frontend *fe)
 	lockref_init(&pcl->lockref); /* one ref for this request */
 	pcl->algorithmformat = map->m_algorithmformat;
 	pcl->pclustersize = map->m_plen;
-	pcl->pageofs_in = pageofs_in;
 	pcl->length = 0;
 	pcl->partial = true;
 	pcl->next = fe->head;
@@ -1047,8 +1043,6 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f,
 				break;
 
 			erofs_onlinefolio_split(folio);
-			if (f->pcl->pageofs_out != (map->m_la & ~PAGE_MASK))
-				f->pcl->multibases = true;
 			if (f->pcl->length < offset + end - map->m_la) {
 				f->pcl->length = offset + end - map->m_la;
 				f->pcl->pageofs_out = map->m_la & ~PAGE_MASK;
@@ -1094,7 +1088,6 @@ struct z_erofs_backend {
 	struct page *onstack_pages[Z_EROFS_ONSTACK_PAGES];
 	struct super_block *sb;
 	struct z_erofs_pcluster *pcl;
-
 	/* pages with the longest decompressed length for deduplication */
 	struct page **decompressed_pages;
 	/* pages to keep the compressed data */
@@ -1103,6 +1096,8 @@ struct z_erofs_backend {
 	struct list_head decompressed_secondary_bvecs;
 	struct page **pagepool;
 	unsigned int onstack_used, nr_pages;
+	/* indicate if temporary copies should be preserved for later use */
+	bool keepxcpy;
 };
 
 struct z_erofs_bvec_item {
@@ -1113,18 +1108,20 @@ struct z_erofs_bvec_item {
 static void z_erofs_do_decompressed_bvec(struct z_erofs_backend *be,
 					 struct z_erofs_bvec *bvec)
 {
+	int poff = bvec->offset + be->pcl->pageofs_out;
 	struct z_erofs_bvec_item *item;
-	unsigned int pgnr;
-
-	if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK) &&
-	    (bvec->end == PAGE_SIZE ||
-	     bvec->offset + bvec->end == be->pcl->length)) {
-		pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT;
-		DBG_BUGON(pgnr >= be->nr_pages);
-		if (!be->decompressed_pages[pgnr]) {
-			be->decompressed_pages[pgnr] = bvec->page;
+	struct page **page;
+
+	if (!(poff & ~PAGE_MASK) && (bvec->end == PAGE_SIZE ||
+			bvec->offset + bvec->end == be->pcl->length)) {
+		DBG_BUGON((poff >> PAGE_SHIFT) >= be->nr_pages);
+		page = be->decompressed_pages + (poff >> PAGE_SHIFT);
+		if (!*page) {
+			*page = bvec->page;
 			return;
 		}
+	} else {
+		be->keepxcpy = true;
 	}
 
 	/* (cold path) one pcluster is requested multiple times */
@@ -1290,7 +1287,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
 					.alg = pcl->algorithmformat,
 					.inplace_io = overlapped,
 					.partial_decoding = pcl->partial,
-					.fillgaps = pcl->multibases,
+					.fillgaps = be->keepxcpy,
 					.gfp = pcl->besteffort ? GFP_KERNEL :
 						GFP_NOWAIT | __GFP_NORETRY
 				 }, be->pagepool);
@@ -1347,7 +1344,6 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
 
 	pcl->length = 0;
 	pcl->partial = true;
-	pcl->multibases = false;
 	pcl->besteffort = false;
 	pcl->bvset.nextpage = NULL;
 	pcl->vcnt = 0;
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 8de50df05dfe..14ea47f954f5 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -559,7 +559,8 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
 			pos += sizeof(__le64);
 			lstart = 0;
 		} else {
-			lstart = map->m_la >> vi->z_lclusterbits;
+			lstart = round_down(map->m_la, 1 << vi->z_lclusterbits);
+			pos += (lstart >> vi->z_lclusterbits) * recsz;
 			pa = EROFS_NULL_ADDR;
 		}
 
@@ -614,7 +615,7 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
 		if (last && (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER)) {
 			map->m_flags |= EROFS_MAP_MAPPED | EROFS_MAP_FRAGMENT;
 			vi->z_fragmentoff = map->m_plen;
-			if (recsz >= offsetof(struct z_erofs_extent, pstart_lo))
+			if (recsz > offsetof(struct z_erofs_extent, pstart_lo))
 				vi->z_fragmentoff |= map->m_pa << 32;
 		} else if (map->m_plen) {
 			map->m_flags |= EROFS_MAP_MAPPED |
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 100376863a44..d4dbffdedd08 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1996,6 +1996,14 @@ static int ep_try_send_events(struct eventpoll *ep,
 	return res;
 }
 
+static int ep_schedule_timeout(ktime_t *to)
+{
+	if (to)
+		return ktime_after(*to, ktime_get());
+	else
+		return 1;
+}
+
 /**
  * ep_poll - Retrieves ready events, and delivers them to the caller-supplied
  *           event buffer.
@@ -2104,8 +2112,9 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		write_unlock_irq(&ep->lock);
 
 		if (!eavail)
-			timed_out = !schedule_hrtimeout_range(to, slack,
-							      HRTIMER_MODE_ABS);
+			timed_out = !ep_schedule_timeout(to) ||
+				!schedule_hrtimeout_range(to, slack,
+							  HRTIMER_MODE_ABS);
 		__set_current_state(TASK_RUNNING);
 
 		/*
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 87ee3a17bd29..e8c5525afc67 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -351,10 +351,9 @@ int ext4_check_blockref(const char *function, unsigned int line,
 {
 	__le32 *bref = p;
 	unsigned int blk;
+	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 
-	if (ext4_has_feature_journal(inode->i_sb) &&
-	    (inode->i_ino ==
-	     le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum)))
+	if (journal && inode == journal->j_inode)
 		return 0;
 
 	while (bref < p+max) {
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 38bc8d74f4cc..e7ecc7c8a729 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -691,7 +691,8 @@ static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
 	if (!bh || !buffer_uptodate(bh))
 		/*
 		 * If the block is not in the buffer cache, then it
-		 * must have been written out.
+		 * must have been written out, or, most unlikely, is
+		 * being migrated - false failure should be OK here.
 		 */
 		goto out;
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1dc09ed5d403..94c7d2d828a6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -386,10 +386,11 @@ static int __check_block_validity(struct inode *inode, const char *func,
 				unsigned int line,
 				struct ext4_map_blocks *map)
 {
-	if (ext4_has_feature_journal(inode->i_sb) &&
-	    (inode->i_ino ==
-	     le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum)))
+	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+
+	if (journal && inode == journal->j_inode)
 		return 0;
+
 	if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) {
 		ext4_error_inode(inode, func, line, map->m_pblk,
 				 "lblock %lu mapped to illegal pblock %llu "
@@ -4724,22 +4725,43 @@ static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val)
 		inode_set_iversion_queried(inode, val);
 }
 
-static const char *check_igot_inode(struct inode *inode, ext4_iget_flags flags)
-
+static int check_igot_inode(struct inode *inode, ext4_iget_flags flags,
+			    const char *function, unsigned int line)
 {
+	const char *err_str;
+
 	if (flags & EXT4_IGET_EA_INODE) {
-		if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
-			return "missing EA_INODE flag";
+		if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
+			err_str = "missing EA_INODE flag";
+			goto error;
+		}
 		if (ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
-		    EXT4_I(inode)->i_file_acl)
-			return "ea_inode with extended attributes";
+		    EXT4_I(inode)->i_file_acl) {
+			err_str = "ea_inode with extended attributes";
+			goto error;
+		}
 	} else {
-		if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
-			return "unexpected EA_INODE flag";
+		if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
+			/*
+			 * open_by_handle_at() could provide an old inode number
+			 * that has since been reused for an ea_inode; this does
+			 * not indicate filesystem corruption
+			 */
+			if (flags & EXT4_IGET_HANDLE)
+				return -ESTALE;
+			err_str = "unexpected EA_INODE flag";
+			goto error;
+		}
+	}
+	if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) {
+		err_str = "unexpected bad inode w/o EXT4_IGET_BAD";
+		goto error;
 	}
-	if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD))
-		return "unexpected bad inode w/o EXT4_IGET_BAD";
-	return NULL;
+	return 0;
+
+error:
+	ext4_error_inode(inode, function, line, 0, err_str);
+	return -EFSCORRUPTED;
 }
 
 struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
@@ -4751,7 +4773,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	struct ext4_inode_info *ei;
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 	struct inode *inode;
-	const char *err_str;
 	journal_t *journal = EXT4_SB(sb)->s_journal;
 	long ret;
 	loff_t size;
@@ -4780,10 +4801,10 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 	if (!(inode->i_state & I_NEW)) {
-		if ((err_str = check_igot_inode(inode, flags)) != NULL) {
-			ext4_error_inode(inode, function, line, 0, err_str);
+		ret = check_igot_inode(inode, flags, function, line);
+		if (ret) {
 			iput(inode);
-			return ERR_PTR(-EFSCORRUPTED);
+			return ERR_PTR(ret);
 		}
 		return inode;
 	}
@@ -5065,13 +5086,21 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 		ret = -EFSCORRUPTED;
 		goto bad_inode;
 	}
-	if ((err_str = check_igot_inode(inode, flags)) != NULL) {
-		ext4_error_inode(inode, function, line, 0, err_str);
-		ret = -EFSCORRUPTED;
-		goto bad_inode;
+	ret = check_igot_inode(inode, flags, function, line);
+	/*
+	 * -ESTALE here means there is nothing inherently wrong with the inode,
+	 * it's just not an inode we can return for an fhandle lookup.
+	 */
+	if (ret == -ESTALE) {
+		brelse(iloc.bh);
+		unlock_new_inode(inode);
+		iput(inode);
+		return ERR_PTR(-ESTALE);
 	}
-
+	if (ret)
+		goto bad_inode;
 	brelse(iloc.bh);
+
 	unlock_new_inode(inode);
 	return inode;
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 0d523e9fb3d5..1e98c5be4e0a 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3037,10 +3037,8 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	unsigned char blocksize_bits = min_t(unsigned char,
 					     sb->s_blocksize_bits,
 					     EXT4_MAX_BLOCK_LOG_SIZE);
-	struct sg {
-		struct ext4_group_info info;
-		ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2];
-	} sg;
+	DEFINE_RAW_FLEX(struct ext4_group_info, sg, bb_counters,
+			EXT4_MAX_BLOCK_LOG_SIZE + 2);
 
 	group--;
 	if (group == 0)
@@ -3048,7 +3046,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 			      " 2^0   2^1   2^2   2^3   2^4   2^5   2^6  "
 			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]\n");
 
-	i = (blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
+	i = (blocksize_bits + 2) * sizeof(sg->bb_counters[0]) +
 		sizeof(struct ext4_group_info);
 
 	grinfo = ext4_get_group_info(sb, group);
@@ -3068,14 +3066,14 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	 * We care only about free space counters in the group info and
 	 * these are safe to access even after the buddy has been unloaded
 	 */
-	memcpy(&sg, grinfo, i);
-	seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
-			sg.info.bb_fragments, sg.info.bb_first_free);
+	memcpy(sg, grinfo, i);
+	seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg->bb_free,
+			sg->bb_fragments, sg->bb_first_free);
 	for (i = 0; i <= 13; i++)
 		seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ?
-				sg.info.bb_counters[i] : 0);
+				sg->bb_counters[i] : 0);
 	seq_puts(seq, " ]");
-	if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info))
+	if (EXT4_MB_GRP_BBITMAP_CORRUPT(sg))
 		seq_puts(seq, " Block bitmap corrupted!");
 	seq_putc(seq, '\n');
 	return 0;
@@ -6644,7 +6642,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 		for (i = 0; i < count; i++) {
 			cond_resched();
 			if (is_metadata)
-				bh = sb_find_get_block(inode->i_sb, block + i);
+				bh = sb_find_get_block_nonatomic(inode->i_sb,
+								 block + i);
 			ext4_forget(handle, is_metadata, inode, bh, block + i);
 		}
 	}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index cb5cb33b1d91..e9712e64ec8f 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1971,7 +1971,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	 * split it in half by count; each resulting block will have at least
 	 * half the space free.
 	 */
-	if (i > 0)
+	if (i >= 0)
 		split = count - move;
 	else
 		split = count/2;
diff --git a/fs/file.c b/fs/file.c
index dc3f7e120e3e..3a3146664cf3 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -26,7 +26,7 @@
 
 #include "internal.h"
 
-bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
+static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
 {
 	/*
 	 * If the reference count was already in the dead zone, then this
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 2c7b24cb67ad..53c2626e90e7 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -1669,6 +1669,9 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
 	unsigned int virtqueue_size;
 	int err = -EIO;
 
+	if (!fsc->source)
+		return invalf(fsc, "No source specified");
+
 	/* This gets a reference on virtio_fs object. This ptr gets installed
 	 * in fc->iq->priv. Once fuse_conn is going away, it calls ->put()
 	 * to drop the reference to this object.
diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c
index 6add6ebfef89..cb823a8a6ba9 100644
--- a/fs/hfs/bnode.c
+++ b/fs/hfs/bnode.c
@@ -67,6 +67,12 @@ void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off)
 	else
 		key_len = tree->max_key_len + 1;
 
+	if (key_len > sizeof(hfs_btree_key) || key_len < 1) {
+		memset(key, 0, sizeof(hfs_btree_key));
+		pr_err("hfs: Invalid key length: %d\n", key_len);
+		return;
+	}
+
 	hfs_bnode_read(node, key, off, key_len);
 }
 
diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c
index 87974d5e6791..079ea80534f7 100644
--- a/fs/hfsplus/bnode.c
+++ b/fs/hfsplus/bnode.c
@@ -67,6 +67,12 @@ void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off)
 	else
 		key_len = tree->max_key_len + 2;
 
+	if (key_len > sizeof(hfsplus_btree_key) || key_len < 1) {
+		memset(key, 0, sizeof(hfsplus_btree_key));
+		pr_err("hfsplus: Invalid key length: %d\n", key_len);
+		return;
+	}
+
 	hfs_bnode_read(node, key, off, key_len);
 }
 
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 31553372b33a..5b08bd417b28 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -259,7 +259,7 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
 		}
 
 		/* truncate len if we find any trailing uptodate block(s) */
-		for ( ; i <= last; i++) {
+		while (++i <= last) {
 			if (ifs_block_is_uptodate(ifs, i)) {
 				plen -= (last - i + 1) * block_size;
 				last = i - 1;
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index 35768a63fb1d..421d247fae52 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -180,7 +180,7 @@ static struct dentry *isofs_fh_to_parent(struct super_block *sb,
 		return NULL;
 
 	return isofs_export_iget(sb,
-			fh_len > 2 ? ifid->parent_block : 0,
+			fh_len > 3 ? ifid->parent_block : 0,
 			ifid->parent_offset,
 			fh_len > 4 ? ifid->parent_generation : 0);
 }
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 0cf0fddbee81..1467f6790747 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -345,7 +345,8 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr,
 	bh = bh_in;
 
 	if (!bh) {
-		bh = __find_get_block(bdev, blocknr, journal->j_blocksize);
+		bh = __find_get_block_nonatomic(bdev, blocknr,
+						journal->j_blocksize);
 		if (bh)
 			BUFFER_TRACE(bh, "found on hash");
 	}
@@ -355,7 +356,8 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr,
 
 		/* If there is a different buffer_head lying around in
 		 * memory anywhere... */
-		bh2 = __find_get_block(bdev, blocknr, journal->j_blocksize);
+		bh2 = __find_get_block_nonatomic(bdev, blocknr,
+						 journal->j_blocksize);
 		if (bh2) {
 			/* ... and it has RevokeValid status... */
 			if (bh2 != bh && buffer_revokevalid(bh2))
@@ -464,7 +466,8 @@ void jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh)
 	 * state machine will get very upset later on. */
 	if (need_cancel) {
 		struct buffer_head *bh2;
-		bh2 = __find_get_block(bh->b_bdev, bh->b_blocknr, bh->b_size);
+		bh2 = __find_get_block_nonatomic(bh->b_bdev, bh->b_blocknr,
+						 bh->b_size);
 		if (bh2) {
 			if (bh2 != bh)
 				clear_buffer_revoked(bh2);
@@ -492,9 +495,9 @@ void jbd2_clear_buffer_revoked_flags(journal_t *journal)
 			struct jbd2_revoke_record_s *record;
 			struct buffer_head *bh;
 			record = (struct jbd2_revoke_record_s *)list_entry;
-			bh = __find_get_block(journal->j_fs_dev,
-					      record->blocknr,
-					      journal->j_blocksize);
+			bh = __find_get_block_nonatomic(journal->j_fs_dev,
+							record->blocknr,
+							journal->j_blocksize);
 			if (bh) {
 				clear_buffer_revoked(bh);
 				__brelse(bh);
diff --git a/fs/namei.c b/fs/namei.c
index 360a86ca1f02..84a0e0b0111c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -125,9 +125,9 @@
 
 #define EMBEDDED_NAME_MAX	(PATH_MAX - offsetof(struct filename, iname))
 
-static inline void initname(struct filename *name)
+static inline void initname(struct filename *name, const char __user *uptr)
 {
-	name->uptr = NULL;
+	name->uptr = uptr;
 	name->aname = NULL;
 	atomic_set(&name->refcnt, 1);
 }
@@ -210,7 +210,7 @@ getname_flags(const char __user *filename, int flags)
 			return ERR_PTR(-ENAMETOOLONG);
 		}
 	}
-	initname(result);
+	initname(result, filename);
 	audit_getname(result);
 	return result;
 }
@@ -268,7 +268,7 @@ struct filename *getname_kernel(const char * filename)
 		return ERR_PTR(-ENAMETOOLONG);
 	}
 	memcpy((char *)result->name, filename, len);
-	initname(result);
+	initname(result, NULL);
 	audit_getname(result);
 	return result;
 }
@@ -1665,27 +1665,20 @@ static struct dentry *lookup_dcache(const struct qstr *name,
 	return dentry;
 }
 
-/*
- * Parent directory has inode locked exclusive.  This is one
- * and only case when ->lookup() gets called on non in-lookup
- * dentries - as the matter of fact, this only gets called
- * when directory is guaranteed to have no in-lookup children
- * at all.
- * Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed.
- * Will return -EEXIST if name is found and LOOKUP_EXCL was passed.
- */
-struct dentry *lookup_one_qstr_excl(const struct qstr *name,
-				    struct dentry *base,
-				    unsigned int flags)
+static struct dentry *lookup_one_qstr_excl_raw(const struct qstr *name,
+					       struct dentry *base,
+					       unsigned int flags)
 {
-	struct dentry *dentry = lookup_dcache(name, base, flags);
+	struct dentry *dentry;
 	struct dentry *old;
-	struct inode *dir = base->d_inode;
+	struct inode *dir;
 
+	dentry = lookup_dcache(name, base, flags);
 	if (dentry)
-		goto found;
+		return dentry;
 
 	/* Don't create child dentry for a dead directory. */
+	dir = base->d_inode;
 	if (unlikely(IS_DEADDIR(dir)))
 		return ERR_PTR(-ENOENT);
 
@@ -1698,7 +1691,24 @@ struct dentry *lookup_one_qstr_excl(const struct qstr *name,
 		dput(dentry);
 		dentry = old;
 	}
-found:
+	return dentry;
+}
+
+/*
+ * Parent directory has inode locked exclusive.  This is one
+ * and only case when ->lookup() gets called on non in-lookup
+ * dentries - as the matter of fact, this only gets called
+ * when directory is guaranteed to have no in-lookup children
+ * at all.
+ * Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed.
+ * Will return -EEXIST if name is found and LOOKUP_EXCL was passed.
+ */
+struct dentry *lookup_one_qstr_excl(const struct qstr *name,
+				    struct dentry *base, unsigned int flags)
+{
+	struct dentry *dentry;
+
+	dentry = lookup_one_qstr_excl_raw(name, base, flags);
 	if (IS_ERR(dentry))
 		return dentry;
 	if (d_is_negative(dentry) && !(flags & LOOKUP_CREATE)) {
@@ -2742,23 +2752,48 @@ static int filename_parentat(int dfd, struct filename *name,
 /* does lookup, returns the object with parent locked */
 static struct dentry *__kern_path_locked(int dfd, struct filename *name, struct path *path)
 {
+	struct path parent_path __free(path_put) = {};
 	struct dentry *d;
 	struct qstr last;
 	int type, error;
 
-	error = filename_parentat(dfd, name, 0, path, &last, &type);
+	error = filename_parentat(dfd, name, 0, &parent_path, &last, &type);
 	if (error)
 		return ERR_PTR(error);
-	if (unlikely(type != LAST_NORM)) {
-		path_put(path);
+	if (unlikely(type != LAST_NORM))
 		return ERR_PTR(-EINVAL);
+	inode_lock_nested(parent_path.dentry->d_inode, I_MUTEX_PARENT);
+	d = lookup_one_qstr_excl(&last, parent_path.dentry, 0);
+	if (IS_ERR(d)) {
+		inode_unlock(parent_path.dentry->d_inode);
+		return d;
 	}
-	inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
-	d = lookup_one_qstr_excl(&last, path->dentry, 0);
+	path->dentry = no_free_ptr(parent_path.dentry);
+	path->mnt = no_free_ptr(parent_path.mnt);
+	return d;
+}
+
+struct dentry *kern_path_locked_negative(const char *name, struct path *path)
+{
+	struct path parent_path __free(path_put) = {};
+	struct filename *filename __free(putname) = getname_kernel(name);
+	struct dentry *d;
+	struct qstr last;
+	int type, error;
+
+	error = filename_parentat(AT_FDCWD, filename, 0, &parent_path, &last, &type);
+	if (error)
+		return ERR_PTR(error);
+	if (unlikely(type != LAST_NORM))
+		return ERR_PTR(-EINVAL);
+	inode_lock_nested(parent_path.dentry->d_inode, I_MUTEX_PARENT);
+	d = lookup_one_qstr_excl_raw(&last, parent_path.dentry, 0);
 	if (IS_ERR(d)) {
-		inode_unlock(path->dentry->d_inode);
-		path_put(path);
+		inode_unlock(parent_path.dentry->d_inode);
+		return d;
 	}
+	path->dentry = no_free_ptr(parent_path.dentry);
+	path->mnt = no_free_ptr(parent_path.mnt);
 	return d;
 }
 
diff --git a/fs/namespace.c b/fs/namespace.c
index 14935a0500a2..1b466c54a357 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -787,15 +787,11 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
 		return 0;
 	mnt = real_mount(bastard);
 	mnt_add_count(mnt, 1);
-	smp_mb();			// see mntput_no_expire()
+	smp_mb();		// see mntput_no_expire() and do_umount()
 	if (likely(!read_seqretry(&mount_lock, seq)))
 		return 0;
-	if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
-		mnt_add_count(mnt, -1);
-		return 1;
-	}
 	lock_mount_hash();
-	if (unlikely(bastard->mnt_flags & MNT_DOOMED)) {
+	if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) {
 		mnt_add_count(mnt, -1);
 		unlock_mount_hash();
 		return 1;
@@ -1830,6 +1826,8 @@ static inline void namespace_lock(void)
 	down_write(&namespace_sem);
 }
 
+DEFINE_GUARD(namespace_lock, struct rw_semaphore *, namespace_lock(), namespace_unlock())
+
 enum umount_tree_flags {
 	UMOUNT_SYNC = 1,
 	UMOUNT_PROPAGATE = 2,
@@ -2046,6 +2044,7 @@ static int do_umount(struct mount *mnt, int flags)
 			umount_tree(mnt, UMOUNT_PROPAGATE);
 		retval = 0;
 	} else {
+		smp_mb(); // paired with __legitimize_mnt()
 		shrink_submounts(mnt);
 		retval = -EBUSY;
 		if (!propagate_mount_busy(mnt, 2)) {
@@ -2383,7 +2382,7 @@ void dissolve_on_fput(struct vfsmount *mnt)
 			return;
 	}
 
-	scoped_guard(rwsem_write, &namespace_sem) {
+	scoped_guard(namespace_lock, &namespace_sem) {
 		ns = m->mnt_ns;
 		if (!must_dissolve(ns))
 			return;
@@ -2824,56 +2823,62 @@ static struct mountpoint *do_lock_mount(struct path *path, bool beneath)
 	struct vfsmount *mnt = path->mnt;
 	struct dentry *dentry;
 	struct mountpoint *mp = ERR_PTR(-ENOENT);
+	struct path under = {};
 
 	for (;;) {
-		struct mount *m;
+		struct mount *m = real_mount(mnt);
 
 		if (beneath) {
-			m = real_mount(mnt);
+			path_put(&under);
 			read_seqlock_excl(&mount_lock);
-			dentry = dget(m->mnt_mountpoint);
+			under.mnt = mntget(&m->mnt_parent->mnt);
+			under.dentry = dget(m->mnt_mountpoint);
 			read_sequnlock_excl(&mount_lock);
+			dentry = under.dentry;
 		} else {
 			dentry = path->dentry;
 		}
 
 		inode_lock(dentry->d_inode);
-		if (unlikely(cant_mount(dentry))) {
-			inode_unlock(dentry->d_inode);
-			goto out;
-		}
-
 		namespace_lock();
 
-		if (beneath && (!is_mounted(mnt) || m->mnt_mountpoint != dentry)) {
+		if (unlikely(cant_mount(dentry) || !is_mounted(mnt)))
+			break;		// not to be mounted on
+
+		if (beneath && unlikely(m->mnt_mountpoint != dentry ||
+				        &m->mnt_parent->mnt != under.mnt)) {
 			namespace_unlock();
 			inode_unlock(dentry->d_inode);
-			goto out;
+			continue;	// got moved
 		}
 
 		mnt = lookup_mnt(path);
-		if (likely(!mnt))
+		if (unlikely(mnt)) {
+			namespace_unlock();
+			inode_unlock(dentry->d_inode);
+			path_put(path);
+			path->mnt = mnt;
+			path->dentry = dget(mnt->mnt_root);
+			continue;	// got overmounted
+		}
+		mp = get_mountpoint(dentry);
+		if (IS_ERR(mp))
 			break;
-
-		namespace_unlock();
-		inode_unlock(dentry->d_inode);
-		if (beneath)
-			dput(dentry);
-		path_put(path);
-		path->mnt = mnt;
-		path->dentry = dget(mnt->mnt_root);
-	}
-
-	mp = get_mountpoint(dentry);
-	if (IS_ERR(mp)) {
-		namespace_unlock();
-		inode_unlock(dentry->d_inode);
+		if (beneath) {
+			/*
+			 * @under duplicates the references that will stay
+			 * at least until namespace_unlock(), so the path_put()
+			 * below is safe (and OK to do under namespace_lock -
+			 * we are not dropping the final references here).
+			 */
+			path_put(&under);
+		}
+		return mp;
 	}
-
-out:
+	namespace_unlock();
+	inode_unlock(dentry->d_inode);
 	if (beneath)
-		dput(dentry);
-
+		path_put(&under);
 	return mp;
 }
 
@@ -2884,14 +2889,11 @@ static inline struct mountpoint *lock_mount(struct path *path)
 
 static void unlock_mount(struct mountpoint *where)
 {
-	struct dentry *dentry = where->m_dentry;
-
+	inode_unlock(where->m_dentry->d_inode);
 	read_seqlock_excl(&mount_lock);
 	put_mountpoint(where);
 	read_sequnlock_excl(&mount_lock);
-
 	namespace_unlock();
-	inode_unlock(dentry->d_inode);
 }
 
 static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
@@ -3555,7 +3557,8 @@ static int can_move_mount_beneath(const struct path *from,
 	 * @mnt_from itself. This defeats the whole purpose of mounting
 	 * @mnt_from beneath @mnt_to.
 	 */
-	if (propagation_would_overmount(parent_mnt_to, mnt_from, mp))
+	if (check_mnt(mnt_from) &&
+	    propagation_would_overmount(parent_mnt_to, mnt_from, mp))
 		return -EINVAL;
 
 	return 0;
@@ -3713,15 +3716,14 @@ static int do_move_mount(struct path *old_path,
 	if (err)
 		goto out;
 
-	if (is_anon_ns(ns))
-		ns->mntns_flags &= ~MNTNS_PROPAGATING;
-
 	/* if the mount is moved, it should no longer be expire
 	 * automatically */
 	list_del_init(&old->mnt_expire);
 	if (attached)
 		put_mountpoint(old_mp);
 out:
+	if (is_anon_ns(ns))
+		ns->mntns_flags &= ~MNTNS_PROPAGATING;
 	unlock_mount(mp);
 	if (!err) {
 		if (attached) {
@@ -5189,8 +5191,8 @@ static void finish_mount_kattr(struct mount_kattr *kattr)
 		mnt_idmap_put(kattr->mnt_idmap);
 }
 
-static int copy_mount_setattr(struct mount_attr __user *uattr, size_t usize,
-			      struct mount_kattr *kattr)
+static int wants_mount_setattr(struct mount_attr __user *uattr, size_t usize,
+			       struct mount_kattr *kattr)
 {
 	int ret;
 	struct mount_attr attr;
@@ -5213,9 +5215,13 @@ static int copy_mount_setattr(struct mount_attr __user *uattr, size_t usize,
 	if (attr.attr_set == 0 &&
 	    attr.attr_clr == 0 &&
 	    attr.propagation == 0)
-		return 0;
+		return 0; /* Tell caller to not bother. */
+
+	ret = build_mount_kattr(&attr, usize, kattr);
+	if (ret < 0)
+		return ret;
 
-	return build_mount_kattr(&attr, usize, kattr);
+	return 1;
 }
 
 SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
@@ -5247,8 +5253,8 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
 	if (flags & AT_RECURSIVE)
 		kattr.kflags |= MOUNT_KATTR_RECURSE;
 
-	err = copy_mount_setattr(uattr, usize, &kattr);
-	if (err)
+	err = wants_mount_setattr(uattr, usize, &kattr);
+	if (err <= 0)
 		return err;
 
 	err = user_path_at(dfd, path, kattr.lookup_flags, &target);
@@ -5282,15 +5288,17 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename,
 		if (flags & AT_RECURSIVE)
 			kattr.kflags |= MOUNT_KATTR_RECURSE;
 
-		ret = copy_mount_setattr(uattr, usize, &kattr);
-		if (ret)
+		ret = wants_mount_setattr(uattr, usize, &kattr);
+		if (ret < 0)
 			return ret;
 
-		ret = do_mount_setattr(&file->f_path, &kattr);
-		if (ret)
-			return ret;
+		if (ret) {
+			ret = do_mount_setattr(&file->f_path, &kattr);
+			if (ret)
+				return ret;
 
-		finish_mount_kattr(&kattr);
+			finish_mount_kattr(&kattr);
+		}
 	}
 
 	fd = get_unused_fd_flags(flags & O_CLOEXEC);
diff --git a/fs/netfs/fscache_cache.c b/fs/netfs/fscache_cache.c
index 9397ed39b0b4..8f70f8da064b 100644
--- a/fs/netfs/fscache_cache.c
+++ b/fs/netfs/fscache_cache.c
@@ -372,7 +372,7 @@ void fscache_withdraw_cache(struct fscache_cache *cache)
 EXPORT_SYMBOL(fscache_withdraw_cache);
 
 #ifdef CONFIG_PROC_FS
-static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] = "-PAEW";
+static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] __nonstring = "-PAEW";
 
 /*
  * Generate a list of caches in /proc/fs/fscache/caches
diff --git a/fs/netfs/fscache_cookie.c b/fs/netfs/fscache_cookie.c
index d4d4b3a8b106..3d56fc73435f 100644
--- a/fs/netfs/fscache_cookie.c
+++ b/fs/netfs/fscache_cookie.c
@@ -29,7 +29,7 @@ static LIST_HEAD(fscache_cookie_lru);
 static DEFINE_SPINLOCK(fscache_cookie_lru_lock);
 DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out);
 static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker);
-static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAIFUWRD";
+static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] __nonstring = "-LCAIFUWRD";
 static unsigned int fscache_lru_cookie_timeout = 10 * HZ;
 
 void fscache_print_cookie(struct fscache_cookie *cookie, char prefix)
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 4e3e62040831..70ecc8f5f210 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -127,11 +127,13 @@ static int __init netfs_init(void)
 	if (mempool_init_slab_pool(&netfs_subrequest_pool, 100, netfs_subrequest_slab) < 0)
 		goto error_subreqpool;
 
+#ifdef CONFIG_PROC_FS
 	if (!proc_mkdir("fs/netfs", NULL))
 		goto error_proc;
 	if (!proc_create_seq("fs/netfs/requests", S_IFREG | 0444, NULL,
 			     &netfs_requests_seq_ops))
 		goto error_procfile;
+#endif
 #ifdef CONFIG_FSCACHE_STATS
 	if (!proc_create_single("fs/netfs/stats", S_IFREG | 0444, NULL,
 				netfs_stats_show))
@@ -144,9 +146,11 @@ static int __init netfs_init(void)
 	return 0;
 
 error_fscache:
+#ifdef CONFIG_PROC_FS
 error_procfile:
 	remove_proc_subtree("fs/netfs", NULL);
 error_proc:
+#endif
 	mempool_exit(&netfs_subrequest_pool);
 error_subreqpool:
 	kmem_cache_destroy(netfs_subrequest_slab);
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index d3f76101ad4b..07932ce9246c 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -2,6 +2,7 @@
 config NFS_FS
 	tristate "NFS client support"
 	depends on INET && FILE_LOCKING && MULTIUSER
+	select CRC32
 	select LOCKD
 	select SUNRPC
 	select NFS_COMMON
@@ -196,7 +197,6 @@ config NFS_USE_KERNEL_DNS
 config NFS_DEBUG
 	bool
 	depends on NFS_FS && SUNRPC_DEBUG
-	select CRC32
 	default y
 
 config NFS_DISABLE_UDP_SUPPORT
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 02c916a55020..6d63b958c4bb 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1105,6 +1105,8 @@ struct nfs_server *nfs_create_server(struct fs_context *fc)
 		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
 			server->namelen = NFS2_MAXNAMLEN;
 	}
+	/* Linux 'subtree_check' borkenness mandates this setting */
+	server->fh_expire_type = NFS_FH_VOL_RENAME;
 
 	if (!(fattr->valid & NFS_ATTR_FATTR)) {
 		error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh,
@@ -1200,6 +1202,10 @@ void nfs_clients_init(struct net *net)
 #if IS_ENABLED(CONFIG_NFS_V4)
 	idr_init(&nn->cb_ident_idr);
 #endif
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+	INIT_LIST_HEAD(&nn->nfs4_data_server_cache);
+	spin_lock_init(&nn->nfs4_data_server_lock);
+#endif
 	spin_lock_init(&nn->nfs_client_lock);
 	nn->boot_time = ktime_get_real();
 	memset(&nn->rpcstats, 0, sizeof(nn->rpcstats));
@@ -1216,6 +1222,9 @@ void nfs_clients_exit(struct net *net)
 	nfs_cleanup_cb_ident_idr(net);
 	WARN_ON_ONCE(!list_empty(&nn->nfs_client_list));
 	WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list));
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+	WARN_ON_ONCE(!list_empty(&nn->nfs4_data_server_cache));
+#endif
 }
 
 #ifdef CONFIG_PROC_FS
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index bd23fc736b39..d0e0b435a843 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2676,6 +2676,18 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data)
 	unblock_revalidate(new_dentry);
 }
 
+static bool nfs_rename_is_unsafe_cross_dir(struct dentry *old_dentry,
+					   struct dentry *new_dentry)
+{
+	struct nfs_server *server = NFS_SB(old_dentry->d_sb);
+
+	if (old_dentry->d_parent != new_dentry->d_parent)
+		return false;
+	if (server->fh_expire_type & NFS_FH_RENAME_UNSAFE)
+		return !(server->fh_expire_type & NFS_FH_NOEXPIRE_WITH_OPEN);
+	return true;
+}
+
 /*
  * RENAME
  * FIXME: Some nfsds, like the Linux user space nfsd, may generate a
@@ -2763,7 +2775,8 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 
 	}
 
-	if (S_ISREG(old_inode->i_mode))
+	if (S_ISREG(old_inode->i_mode) &&
+	    nfs_rename_is_unsafe_cross_dir(old_dentry, new_dentry))
 		nfs_sync_inode(old_inode);
 	task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry,
 				must_unblock ? nfs_unblock_rename : NULL);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index f32f8d7c9122..48d89716193a 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -757,7 +757,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 {
 	struct nfs_direct_req *dreq = hdr->dreq;
 	struct nfs_commit_info cinfo;
-	struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 	struct inode *inode = dreq->inode;
 	int flags = NFS_ODIRECT_DONE;
 
@@ -786,6 +785,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 	spin_unlock(&inode->i_lock);
 
 	while (!list_empty(&hdr->pages)) {
+		struct nfs_page *req;
 
 		req = nfs_list_entry(hdr->pages.next);
 		nfs_list_remove_request(req);
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index 4fa304fa5bc4..29d9234d5c08 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -76,6 +76,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	struct page *scratch;
 	struct list_head dsaddrs;
 	struct nfs4_pnfs_ds_addr *da;
+	struct net *net = server->nfs_client->cl_net;
 
 	/* set up xdr stream */
 	scratch = alloc_page(gfp_flags);
@@ -159,8 +160,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 
 		mp_count = be32_to_cpup(p); /* multipath count */
 		for (j = 0; j < mp_count; j++) {
-			da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
-						    &stream, gfp_flags);
+			da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
 			if (da)
 				list_add_tail(&da->da_node, &dsaddrs);
 		}
@@ -170,7 +170,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 			goto out_err_free_deviceid;
 		}
 
-		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags);
 		if (!dsaddr->ds_list[i])
 			goto out_err_drain_dsaddrs;
 		trace_fl_getdevinfo(server, &pdev->dev_id, dsaddr->ds_list[i]->ds_remotestr);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 61ad269c825f..e6909cafab68 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1329,7 +1329,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 					    hdr->args.offset, hdr->args.count,
 					    &hdr->res.op_status, OP_READ,
 					    task->tk_status);
-		trace_ff_layout_read_error(hdr);
+		trace_ff_layout_read_error(hdr, task->tk_status);
 	}
 
 	err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1502,7 +1502,7 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
 					    hdr->args.offset, hdr->args.count,
 					    &hdr->res.op_status, OP_WRITE,
 					    task->tk_status);
-		trace_ff_layout_write_error(hdr);
+		trace_ff_layout_write_error(hdr, task->tk_status);
 	}
 
 	err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1551,7 +1551,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 					    data->args.offset, data->args.count,
 					    &data->res.op_status, OP_COMMIT,
 					    task->tk_status);
-		trace_ff_layout_commit_error(data);
+		trace_ff_layout_commit_error(data, task->tk_status);
 	}
 
 	err = ff_layout_async_handle_error(task, NULL, data->ds_clp,
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e58bedfb1dcc..4a304cf17c4b 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -49,6 +49,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	struct nfs4_pnfs_ds_addr *da;
 	struct nfs4_ff_layout_ds *new_ds = NULL;
 	struct nfs4_ff_ds_version *ds_versions = NULL;
+	struct net *net = server->nfs_client->cl_net;
 	u32 mp_count;
 	u32 version_count;
 	__be32 *p;
@@ -80,8 +81,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 
 	for (i = 0; i < mp_count; i++) {
 		/* multipath ds */
-		da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
-					    &stream, gfp_flags);
+		da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
 		if (da)
 			list_add_tail(&da->da_node, &dsaddrs);
 	}
@@ -149,7 +149,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	new_ds->ds_versions = ds_versions;
 	new_ds->ds_versions_cnt = version_count;
 
-	new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+	new_ds->ds = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags);
 	if (!new_ds->ds)
 		goto out_err_drain_dsaddrs;
 
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index ec8d32d0e2e9..6655e5f32ec6 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -899,18 +899,11 @@ u64 nfs_timespec_to_change_attr(const struct timespec64 *ts)
 	return ((u64)ts->tv_sec << 30) + ts->tv_nsec;
 }
 
-#ifdef CONFIG_CRC32
 static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid)
 {
 	return ~crc32_le(0xFFFFFFFF, &stateid->other[0],
 				NFS4_STATEID_OTHER_SIZE);
 }
-#else
-static inline u32 nfs_stateid_hash(nfs4_stateid *stateid)
-{
-	return 0;
-}
-#endif
 
 static inline bool nfs_current_task_exiting(void)
 {
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 5c21caeae075..4ec952f9f47d 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -278,6 +278,7 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 		new = __nfs_local_open_fh(clp, cred, fh, nfl, mode);
 		if (IS_ERR(new))
 			return NULL;
+		rcu_read_lock();
 		/* try to swap in the pointer */
 		spin_lock(&clp->cl_uuid.lock);
 		nf = rcu_dereference_protected(*pnf, 1);
@@ -287,7 +288,6 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 			rcu_assign_pointer(*pnf, nf);
 		}
 		spin_unlock(&clp->cl_uuid.lock);
-		rcu_read_lock();
 	}
 	nf = nfs_local_file_get(nf);
 	rcu_read_unlock();
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index a68b21603ea9..6ba3ea39e928 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -31,7 +31,11 @@ struct nfs_net {
 	unsigned short nfs_callback_tcpport;
 	unsigned short nfs_callback_tcpport6;
 	int cb_users[NFS4_MAX_MINOR_VERSION + 1];
-#endif
+#endif /* CONFIG_NFS_V4 */
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+	struct list_head nfs4_data_server_cache;
+	spinlock_t nfs4_data_server_lock;
+#endif /* CONFIG_NFS_V4_1 */
 	struct nfs_netns_client *nfs_client;
 	spinlock_t nfs_client_lock;
 	ktime_t boot_time;
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 18d8f6529f61..a126eb31f62f 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -104,7 +104,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type, bool rcu)
 
 	switch (status) {
 		case 0:
-			status = nfs_refresh_inode(inode, res.fattr);
+			nfs_refresh_inode(inode, res.fattr);
 			break;
 		case -EPFNOSUPPORT:
 		case -EPROTONOSUPPORT:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 970f28dbf253..b1d2122bd5a7 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -671,6 +671,15 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server,
 	struct nfs_client *clp = server->nfs_client;
 	int ret;
 
+	if ((task->tk_rpc_status == -ENETDOWN ||
+	     task->tk_rpc_status == -ENETUNREACH) &&
+	    task->tk_flags & RPC_TASK_NETUNREACH_FATAL) {
+		exception->delay = 0;
+		exception->recovering = 0;
+		exception->retry = 0;
+		return -EIO;
+	}
+
 	ret = nfs4_do_handle_exception(server, errorcode, exception);
 	if (exception->delay) {
 		int ret2 = nfs4_exception_should_retrans(server, exception);
@@ -7074,10 +7083,18 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
 	struct nfs4_unlockdata *p;
 	struct nfs4_state *state = lsp->ls_state;
 	struct inode *inode = state->inode;
+	struct nfs_lock_context *l_ctx;
 
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (p == NULL)
 		return NULL;
+	l_ctx = nfs_get_lock_context(ctx);
+	if (!IS_ERR(l_ctx)) {
+		p->l_ctx = l_ctx;
+	} else {
+		kfree(p);
+		return NULL;
+	}
 	p->arg.fh = NFS_FH(inode);
 	p->arg.fl = &p->fl;
 	p->arg.seqid = seqid;
@@ -7085,7 +7102,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
 	p->lsp = lsp;
 	/* Ensure we don't close file until we're done freeing locks! */
 	p->ctx = get_nfs_open_context(ctx);
-	p->l_ctx = nfs_get_lock_context(ctx);
 	locks_init_lock(&p->fl);
 	locks_copy_lock(&p->fl, fl);
 	p->server = NFS_SERVER(inode);
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 351616c61df5..f9c291e2165c 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -148,16 +148,12 @@ static inline void nfs4_copy_sessionid(struct nfs4_sessionid *dst,
 	memcpy(dst->data, src->data, NFS4_MAX_SESSIONID_LEN);
 }
 
-#ifdef CONFIG_CRC32
 /*
  * nfs_session_id_hash - calculate the crc32 hash for the session id
  * @session - pointer to session
  */
 #define nfs_session_id_hash(sess_id) \
 	(~crc32_le(0xFFFFFFFF, &(sess_id)->data[0], sizeof((sess_id)->data)))
-#else
-#define nfs_session_id_hash(session) (0)
-#endif
 #else /* defined(CONFIG_NFS_V4_1) */
 
 static inline int nfs4_init_session(struct nfs_client *clp)
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index bc67fe6801b1..deab4c0e21a0 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -2051,13 +2051,15 @@ TRACE_EVENT(fl_getdevinfo,
 
 DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
 		TP_PROTO(
-			const struct nfs_pgio_header *hdr
+			const struct nfs_pgio_header *hdr,
+			int error
 		),
 
-		TP_ARGS(hdr),
+		TP_ARGS(hdr, error),
 
 		TP_STRUCT__entry(
 			__field(unsigned long, error)
+			__field(unsigned long, nfs_error)
 			__field(dev_t, dev)
 			__field(u32, fhandle)
 			__field(u64, fileid)
@@ -2073,7 +2075,8 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
 		TP_fast_assign(
 			const struct inode *inode = hdr->inode;
 
-			__entry->error = hdr->res.op_status;
+			__entry->error = -error;
+			__entry->nfs_error = hdr->res.op_status;
 			__entry->fhandle = nfs_fhandle_hash(hdr->args.fh);
 			__entry->fileid = NFS_FILEID(inode);
 			__entry->dev = inode->i_sb->s_dev;
@@ -2088,7 +2091,8 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
 
 		TP_printk(
 			"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s",
+			"offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s "
+			"nfs_error=%lu (%s)",
 			-__entry->error,
 			show_nfs4_status(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -2096,28 +2100,32 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
 			__entry->fhandle,
 			__entry->offset, __entry->count,
 			__entry->stateid_seq, __entry->stateid_hash,
-			__get_str(dstaddr)
+			__get_str(dstaddr), __entry->nfs_error,
+			show_nfs4_status(__entry->nfs_error)
 		)
 );
 
 #define DEFINE_NFS4_FLEXFILES_IO_EVENT(name) \
 	DEFINE_EVENT(nfs4_flexfiles_io_event, name, \
 			TP_PROTO( \
-				const struct nfs_pgio_header *hdr \
+				const struct nfs_pgio_header *hdr, \
+				int error \
 			), \
-			TP_ARGS(hdr))
+			TP_ARGS(hdr, error))
 DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_read_error);
 DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_write_error);
 
 TRACE_EVENT(ff_layout_commit_error,
 		TP_PROTO(
-			const struct nfs_commit_data *data
+			const struct nfs_commit_data *data,
+			int error
 		),
 
-		TP_ARGS(data),
+		TP_ARGS(data, error),
 
 		TP_STRUCT__entry(
 			__field(unsigned long, error)
+			__field(unsigned long, nfs_error)
 			__field(dev_t, dev)
 			__field(u32, fhandle)
 			__field(u64, fileid)
@@ -2131,7 +2139,8 @@ TRACE_EVENT(ff_layout_commit_error,
 		TP_fast_assign(
 			const struct inode *inode = data->inode;
 
-			__entry->error = data->res.op_status;
+			__entry->error = -error;
+			__entry->nfs_error = data->res.op_status;
 			__entry->fhandle = nfs_fhandle_hash(data->args.fh);
 			__entry->fileid = NFS_FILEID(inode);
 			__entry->dev = inode->i_sb->s_dev;
@@ -2142,14 +2151,15 @@ TRACE_EVENT(ff_layout_commit_error,
 
 		TP_printk(
 			"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%llu count=%u dstaddr=%s",
+			"offset=%llu count=%u dstaddr=%s nfs_error=%lu (%s)",
 			-__entry->error,
 			show_nfs4_status(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle,
 			__entry->offset, __entry->count,
-			__get_str(dstaddr)
+			__get_str(dstaddr), __entry->nfs_error,
+			show_nfs4_status(__entry->nfs_error)
 		)
 );
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 5f582713bf05..3adb7d0dbec7 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -745,6 +745,14 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 	return remaining;
 }
 
+static void pnfs_reset_return_info(struct pnfs_layout_hdr *lo)
+{
+	struct pnfs_layout_segment *lseg;
+
+	list_for_each_entry(lseg, &lo->plh_return_segs, pls_list)
+		pnfs_set_plh_return_info(lo, lseg->pls_range.iomode, 0);
+}
+
 static void
 pnfs_free_returned_lsegs(struct pnfs_layout_hdr *lo,
 		struct list_head *free_me,
@@ -1246,21 +1254,15 @@ static void pnfs_clear_layoutcommit(struct inode *inode,
 static void
 pnfs_layoutreturn_retry_later_locked(struct pnfs_layout_hdr *lo,
 				     const nfs4_stateid *arg_stateid,
-				     const struct pnfs_layout_range *range)
+				     const struct pnfs_layout_range *range,
+				     struct list_head *freeme)
 {
-	const struct pnfs_layout_segment *lseg;
-	u32 seq = be32_to_cpu(arg_stateid->seqid);
-
 	if (pnfs_layout_is_valid(lo) &&
-	    nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid)) {
-		list_for_each_entry(lseg, &lo->plh_return_segs, pls_list) {
-			if (pnfs_seqid_is_newer(lseg->pls_seq, seq) ||
-			    !pnfs_should_free_range(&lseg->pls_range, range))
-				continue;
-			pnfs_set_plh_return_info(lo, range->iomode, seq);
-			break;
-		}
-	}
+	    nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
+		pnfs_reset_return_info(lo);
+	else
+		pnfs_mark_layout_stateid_invalid(lo, freeme);
+	pnfs_clear_layoutreturn_waitbit(lo);
 }
 
 void pnfs_layoutreturn_retry_later(struct pnfs_layout_hdr *lo,
@@ -1268,11 +1270,12 @@ void pnfs_layoutreturn_retry_later(struct pnfs_layout_hdr *lo,
 				   const struct pnfs_layout_range *range)
 {
 	struct inode *inode = lo->plh_inode;
+	LIST_HEAD(freeme);
 
 	spin_lock(&inode->i_lock);
-	pnfs_layoutreturn_retry_later_locked(lo, arg_stateid, range);
-	pnfs_clear_layoutreturn_waitbit(lo);
+	pnfs_layoutreturn_retry_later_locked(lo, arg_stateid, range, &freeme);
 	spin_unlock(&inode->i_lock);
+	pnfs_free_lseg_list(&freeme);
 }
 
 void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
@@ -1292,6 +1295,7 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
 		pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq);
 		pnfs_free_returned_lsegs(lo, &freeme, range, seq);
 		pnfs_set_layout_stateid(lo, stateid, NULL, true);
+		pnfs_reset_return_info(lo);
 	} else
 		pnfs_mark_layout_stateid_invalid(lo, &freeme);
 out_unlock:
@@ -1661,6 +1665,18 @@ int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
 		/* Was there an RPC level error? If not, retry */
 		if (task->tk_rpc_status == 0)
 			break;
+		/*
+		 * Is there a fatal network level error?
+		 * If so release the layout, but flag the error.
+		 */
+		if ((task->tk_rpc_status == -ENETDOWN ||
+		     task->tk_rpc_status == -ENETUNREACH) &&
+		    task->tk_flags & RPC_TASK_NETUNREACH_FATAL) {
+			*ret = 0;
+			(*respp)->lrs_present = 0;
+			retval = -EIO;
+			break;
+		}
 		/* If the call was not sent, let caller handle it */
 		if (!RPC_WAS_SENT(task))
 			return 0;
@@ -1695,6 +1711,7 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
 	struct inode *inode = args->inode;
 	const nfs4_stateid *res_stateid = NULL;
 	struct nfs4_xdr_opaque_data *ld_private = args->ld_private;
+	LIST_HEAD(freeme);
 
 	switch (ret) {
 	case -NFS4ERR_BADSESSION:
@@ -1703,9 +1720,9 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
 	case -NFS4ERR_NOMATCHING_LAYOUT:
 		spin_lock(&inode->i_lock);
 		pnfs_layoutreturn_retry_later_locked(lo, &args->stateid,
-						     &args->range);
-		pnfs_clear_layoutreturn_waitbit(lo);
+						     &args->range, &freeme);
 		spin_unlock(&inode->i_lock);
+		pnfs_free_lseg_list(&freeme);
 		break;
 	case 0:
 		if (res->lrs_present)
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 30d2613e912b..91ff877185c8 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -60,6 +60,7 @@ struct nfs4_pnfs_ds {
 	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
 	char			*ds_remotestr;	/* comma sep list of addrs */
 	struct list_head	ds_addrs;
+	const struct net	*ds_net;
 	struct nfs_client	*ds_clp;
 	refcount_t		ds_count;
 	unsigned long		ds_state;
@@ -415,7 +416,8 @@ int pnfs_generic_commit_pagelist(struct inode *inode,
 int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max);
 void pnfs_generic_write_commit_done(struct rpc_task *task, void *data);
 void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
-struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
+struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(const struct net *net,
+				      struct list_head *dsaddrs,
 				      gfp_t gfp_flags);
 void nfs4_pnfs_v3_ds_connect_unload(void);
 int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index dbef837e871a..91ef486f40b9 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -16,6 +16,7 @@
 #include "nfs4session.h"
 #include "internal.h"
 #include "pnfs.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS
 
@@ -504,14 +505,14 @@ EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist);
 /*
  * Data server cache
  *
- * Data servers can be mapped to different device ids.
- * nfs4_pnfs_ds reference counting
+ * Data servers can be mapped to different device ids, but should
+ * never be shared between net namespaces.
+ *
+ * nfs4_pnfs_ds reference counting:
  *   - set to 1 on allocation
  *   - incremented when a device id maps a data server already in the cache.
  *   - decremented when deviceid is removed from the cache.
  */
-static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
-static LIST_HEAD(nfs4_data_server_cache);
 
 /* Debug routines */
 static void
@@ -604,11 +605,11 @@ _same_data_server_addrs_locked(const struct list_head *dsaddrs1,
  * Lookup DS by addresses.  nfs4_ds_cache_lock is held
  */
 static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(const struct list_head *dsaddrs)
+_data_server_lookup_locked(const struct nfs_net *nn, const struct list_head *dsaddrs)
 {
 	struct nfs4_pnfs_ds *ds;
 
-	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
+	list_for_each_entry(ds, &nn->nfs4_data_server_cache, ds_node)
 		if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
 			return ds;
 	return NULL;
@@ -653,10 +654,11 @@ static void destroy_ds(struct nfs4_pnfs_ds *ds)
 
 void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds)
 {
-	if (refcount_dec_and_lock(&ds->ds_count,
-				&nfs4_ds_cache_lock)) {
+	struct nfs_net *nn = net_generic(ds->ds_net, nfs_net_id);
+
+	if (refcount_dec_and_lock(&ds->ds_count, &nn->nfs4_data_server_lock)) {
 		list_del_init(&ds->ds_node);
-		spin_unlock(&nfs4_ds_cache_lock);
+		spin_unlock(&nn->nfs4_data_server_lock);
 		destroy_ds(ds);
 	}
 }
@@ -716,8 +718,9 @@ out_err:
  * uncached and return cached struct nfs4_pnfs_ds.
  */
 struct nfs4_pnfs_ds *
-nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
+nfs4_pnfs_ds_add(const struct net *net, struct list_head *dsaddrs, gfp_t gfp_flags)
 {
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
 	struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
 	char *remotestr;
 
@@ -733,16 +736,17 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
 	/* this is only used for debugging, so it's ok if its NULL */
 	remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
 
-	spin_lock(&nfs4_ds_cache_lock);
-	tmp_ds = _data_server_lookup_locked(dsaddrs);
+	spin_lock(&nn->nfs4_data_server_lock);
+	tmp_ds = _data_server_lookup_locked(nn, dsaddrs);
 	if (tmp_ds == NULL) {
 		INIT_LIST_HEAD(&ds->ds_addrs);
 		list_splice_init(dsaddrs, &ds->ds_addrs);
 		ds->ds_remotestr = remotestr;
 		refcount_set(&ds->ds_count, 1);
 		INIT_LIST_HEAD(&ds->ds_node);
+		ds->ds_net = net;
 		ds->ds_clp = NULL;
-		list_add(&ds->ds_node, &nfs4_data_server_cache);
+		list_add(&ds->ds_node, &nn->nfs4_data_server_cache);
 		dprintk("%s add new data server %s\n", __func__,
 			ds->ds_remotestr);
 	} else {
@@ -754,7 +758,7 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
 			refcount_read(&tmp_ds->ds_count));
 		ds = tmp_ds;
 	}
-	spin_unlock(&nfs4_ds_cache_lock);
+	spin_unlock(&nn->nfs4_data_server_lock);
 out:
 	return ds;
 }
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 792d3fed1b45..731a88f6313e 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -4,6 +4,7 @@ config NFSD
 	depends on INET
 	depends on FILE_LOCKING
 	depends on FSNOTIFY
+	select CRC32
 	select LOCKD
 	select SUNRPC
 	select EXPORTFS
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2041268b398a..59a693f22452 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5430,7 +5430,7 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 	queued = nfsd4_run_cb(&dp->dl_recall);
 	WARN_ON_ONCE(!queued);
 	if (!queued)
-		nfs4_put_stid(&dp->dl_stid);
+		refcount_dec(&dp->dl_stid.sc_count);
 }
 
 /* Called from break_lease() with flc_lock held. */
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 876152a91f12..5103c2f4d225 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -267,7 +267,6 @@ static inline bool fh_fsid_match(const struct knfsd_fh *fh1,
 	return true;
 }
 
-#ifdef CONFIG_CRC32
 /**
  * knfsd_fh_hash - calculate the crc32 hash for the filehandle
  * @fh - pointer to filehandle
@@ -279,12 +278,6 @@ static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh)
 {
 	return ~crc32_le(0xFFFFFFFF, fh->fh_raw, fh->fh_size);
 }
-#else
-static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh)
-{
-	return 0;
-}
-#endif
 
 /**
  * fh_clear_pre_post_attrs - Reset pre/post attributes
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index cb01ea81724d..d0bcf744c553 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -705,8 +705,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	int blocksize;
 	int err;
 
-	down_write(&nilfs->ns_sem);
-
 	blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE);
 	if (!blocksize) {
 		nilfs_err(sb, "unable to set blocksize");
@@ -779,7 +777,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	set_nilfs_init(nilfs);
 	err = 0;
  out:
-	up_write(&nilfs->ns_sem);
 	return err;
 
  failed_sbh:
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index f2d840ae4ded..87f861e9004f 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1961,12 +1961,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 		return -EINVAL;
 
 	if (mark_cmd == FAN_MARK_FLUSH) {
-		if (mark_type == FAN_MARK_MOUNT)
-			fsnotify_clear_vfsmount_marks_by_group(group);
-		else if (mark_type == FAN_MARK_FILESYSTEM)
-			fsnotify_clear_sb_marks_by_group(group);
-		else
-			fsnotify_clear_inode_marks_by_group(group);
+		fsnotify_clear_marks_by_group(group, obj_type);
 		return 0;
 	}
 
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index b8ac85b548c7..821cb7874685 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6918,6 +6918,7 @@ static int ocfs2_grab_folios(struct inode *inode, loff_t start, loff_t end,
 		if (IS_ERR(folios[numfolios])) {
 			ret = PTR_ERR(folios[numfolios]);
 			mlog_errno(ret);
+			folios[numfolios] = NULL;
 			goto out;
 		}
 
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index f1b4b3e611cb..e5f58ff2175f 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -174,7 +174,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
 	struct ocfs2_recovery_map *rm;
 
 	mutex_init(&osb->recovery_lock);
-	osb->disable_recovery = 0;
+	osb->recovery_state = OCFS2_REC_ENABLED;
 	osb->recovery_thread_task = NULL;
 	init_waitqueue_head(&osb->recovery_event);
 
@@ -190,31 +190,53 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
 	return 0;
 }
 
-/* we can't grab the goofy sem lock from inside wait_event, so we use
- * memory barriers to make sure that we'll see the null task before
- * being woken up */
 static int ocfs2_recovery_thread_running(struct ocfs2_super *osb)
 {
-	mb();
 	return osb->recovery_thread_task != NULL;
 }
 
-void ocfs2_recovery_exit(struct ocfs2_super *osb)
+static void ocfs2_recovery_disable(struct ocfs2_super *osb,
+				   enum ocfs2_recovery_state state)
 {
-	struct ocfs2_recovery_map *rm;
-
-	/* disable any new recovery threads and wait for any currently
-	 * running ones to exit. Do this before setting the vol_state. */
 	mutex_lock(&osb->recovery_lock);
-	osb->disable_recovery = 1;
+	/*
+	 * If recovery thread is not running, we can directly transition to
+	 * final state.
+	 */
+	if (!ocfs2_recovery_thread_running(osb)) {
+		osb->recovery_state = state + 1;
+		goto out_lock;
+	}
+	osb->recovery_state = state;
+	/* Wait for recovery thread to acknowledge state transition */
+	wait_event_cmd(osb->recovery_event,
+		       !ocfs2_recovery_thread_running(osb) ||
+				osb->recovery_state >= state + 1,
+		       mutex_unlock(&osb->recovery_lock),
+		       mutex_lock(&osb->recovery_lock));
+out_lock:
 	mutex_unlock(&osb->recovery_lock);
-	wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb));
 
-	/* At this point, we know that no more recovery threads can be
-	 * launched, so wait for any recovery completion work to
-	 * complete. */
+	/*
+	 * At this point we know that no more recovery work can be queued so
+	 * wait for any recovery completion work to complete.
+	 */
 	if (osb->ocfs2_wq)
 		flush_workqueue(osb->ocfs2_wq);
+}
+
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb)
+{
+	ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE);
+}
+
+void ocfs2_recovery_exit(struct ocfs2_super *osb)
+{
+	struct ocfs2_recovery_map *rm;
+
+	/* disable any new recovery threads and wait for any currently
+	 * running ones to exit. Do this before setting the vol_state. */
+	ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE);
 
 	/*
 	 * Now that recovery is shut down, and the osb is about to be
@@ -1249,7 +1271,7 @@ static int ocfs2_force_read_journal(struct inode *inode)
 		}
 
 		for (i = 0; i < p_blocks; i++, p_blkno++) {
-			bh = __find_get_block(osb->sb->s_bdev, p_blkno,
+			bh = __find_get_block_nonatomic(osb->sb->s_bdev, p_blkno,
 					osb->sb->s_blocksize);
 			/* block not cached. */
 			if (!bh)
@@ -1472,6 +1494,18 @@ static int __ocfs2_recovery_thread(void *arg)
 		}
 	}
 restart:
+	if (quota_enabled) {
+		mutex_lock(&osb->recovery_lock);
+		/* Confirm that recovery thread will no longer recover quotas */
+		if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) {
+			osb->recovery_state = OCFS2_REC_QUOTA_DISABLED;
+			wake_up(&osb->recovery_event);
+		}
+		if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED)
+			quota_enabled = 0;
+		mutex_unlock(&osb->recovery_lock);
+	}
+
 	status = ocfs2_super_lock(osb, 1);
 	if (status < 0) {
 		mlog_errno(status);
@@ -1569,27 +1603,29 @@ bail:
 
 	ocfs2_free_replay_slots(osb);
 	osb->recovery_thread_task = NULL;
-	mb(); /* sync with ocfs2_recovery_thread_running */
+	if (osb->recovery_state == OCFS2_REC_WANT_DISABLE)
+		osb->recovery_state = OCFS2_REC_DISABLED;
 	wake_up(&osb->recovery_event);
 
 	mutex_unlock(&osb->recovery_lock);
 
-	if (quota_enabled)
-		kfree(rm_quota);
+	kfree(rm_quota);
 
 	return status;
 }
 
 void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
 {
+	int was_set = -1;
+
 	mutex_lock(&osb->recovery_lock);
+	if (osb->recovery_state < OCFS2_REC_WANT_DISABLE)
+		was_set = ocfs2_recovery_map_set(osb, node_num);
 
 	trace_ocfs2_recovery_thread(node_num, osb->node_num,
-		osb->disable_recovery, osb->recovery_thread_task,
-		osb->disable_recovery ?
-		-1 : ocfs2_recovery_map_set(osb, node_num));
+		osb->recovery_state, osb->recovery_thread_task, was_set);
 
-	if (osb->disable_recovery)
+	if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE)
 		goto out;
 
 	if (osb->recovery_thread_task)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index e3c3a35dc5e0..6397170f302f 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -148,6 +148,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb);
 
 int ocfs2_recovery_init(struct ocfs2_super *osb);
 void ocfs2_recovery_exit(struct ocfs2_super *osb);
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb);
 
 int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
 void ocfs2_free_replay_slots(struct ocfs2_super *osb);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 51c52768132d..6aaa94c554c1 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -308,6 +308,21 @@ enum ocfs2_journal_trigger_type {
 void ocfs2_initialize_journal_triggers(struct super_block *sb,
 				       struct ocfs2_triggers triggers[]);
 
+enum ocfs2_recovery_state {
+	OCFS2_REC_ENABLED = 0,
+	OCFS2_REC_QUOTA_WANT_DISABLE,
+	/*
+	 * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for
+	 * ocfs2_recovery_disable_quota() to work.
+	 */
+	OCFS2_REC_QUOTA_DISABLED,
+	OCFS2_REC_WANT_DISABLE,
+	/*
+	 * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work
+	 */
+	OCFS2_REC_DISABLED,
+};
+
 struct ocfs2_journal;
 struct ocfs2_slot_info;
 struct ocfs2_recovery_map;
@@ -370,7 +385,7 @@ struct ocfs2_super
 	struct ocfs2_recovery_map *recovery_map;
 	struct ocfs2_replay_map *replay_map;
 	struct task_struct *recovery_thread_task;
-	int disable_recovery;
+	enum ocfs2_recovery_state recovery_state;
 	wait_queue_head_t checkpoint_event;
 	struct ocfs2_journal *journal;
 	unsigned long osb_commit_interval;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2956d888c131..e272429da3db 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -453,8 +453,7 @@ out:
 
 /* Sync changes in local quota file into global quota file and
  * reinitialize local quota file.
- * The function expects local quota file to be already locked and
- * s_umount locked in shared mode. */
+ * The function expects local quota file to be already locked. */
 static int ocfs2_recover_local_quota_file(struct inode *lqinode,
 					  int type,
 					  struct ocfs2_quota_recovery *rec)
@@ -588,7 +587,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 {
 	unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
 					      LOCAL_GROUP_QUOTA_SYSTEM_INODE };
-	struct super_block *sb = osb->sb;
 	struct ocfs2_local_disk_dqinfo *ldinfo;
 	struct buffer_head *bh;
 	handle_t *handle;
@@ -600,7 +598,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 	printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for "
 	       "slot %u\n", osb->dev_str, slot_num);
 
-	down_read(&sb->s_umount);
 	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (list_empty(&(rec->r_list[type])))
 			continue;
@@ -677,7 +674,6 @@ out_put:
 			break;
 	}
 out:
-	up_read(&sb->s_umount);
 	kfree(rec);
 	return status;
 }
@@ -843,8 +839,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type)
 	ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk);
 
 	/*
-	 * s_umount held in exclusive mode protects us against racing with
-	 * recovery thread...
+	 * ocfs2_dismount_volume() has already aborted quota recovery...
 	 */
 	if (oinfo->dqi_rec) {
 		ocfs2_free_quota_recovery(oinfo->dqi_rec);
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f7b483f0de2a..6ac4dcd54588 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -698,10 +698,12 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 
 	bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode,
 					       ac, cl);
-	if (PTR_ERR(bg_bh) == -ENOSPC)
+	if (PTR_ERR(bg_bh) == -ENOSPC) {
+		ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
 		bg_bh = ocfs2_block_group_alloc_discontig(handle,
 							  alloc_inode,
 							  ac, cl);
+	}
 	if (IS_ERR(bg_bh)) {
 		status = PTR_ERR(bg_bh);
 		bg_bh = NULL;
@@ -1794,6 +1796,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 {
 	int status;
 	u16 chain;
+	u32 contig_bits;
 	u64 next_group;
 	struct inode *alloc_inode = ac->ac_inode;
 	struct buffer_head *group_bh = NULL;
@@ -1819,10 +1822,21 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 	status = -ENOSPC;
 	/* for now, the chain search is a bit simplistic. We just use
 	 * the 1st group with any empty bits. */
-	while ((status = ac->ac_group_search(alloc_inode, group_bh,
-					     bits_wanted, min_bits,
-					     ac->ac_max_block,
-					     res)) == -ENOSPC) {
+	while (1) {
+		if (ac->ac_which == OCFS2_AC_USE_MAIN_DISCONTIG) {
+			contig_bits = le16_to_cpu(bg->bg_contig_free_bits);
+			if (!contig_bits)
+				contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap,
+						le16_to_cpu(bg->bg_bits), 0);
+			if (bits_wanted > contig_bits && contig_bits >= min_bits)
+				bits_wanted = contig_bits;
+		}
+
+		status = ac->ac_group_search(alloc_inode, group_bh,
+				bits_wanted, min_bits,
+				ac->ac_max_block, res);
+		if (status != -ENOSPC)
+			break;
 		if (!bg->bg_next_group)
 			break;
 
@@ -1982,6 +1996,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 	victim = ocfs2_find_victim_chain(cl);
 	ac->ac_chain = victim;
 
+search:
 	status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
 				    res, &bits_left);
 	if (!status) {
@@ -2022,6 +2037,16 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 		}
 	}
 
+	/* Chains can't supply the bits_wanted contiguous space.
+	 * We should switch to using every single bit when allocating
+	 * from the global bitmap. */
+	if (i == le16_to_cpu(cl->cl_next_free_rec) &&
+	    status == -ENOSPC && ac->ac_which == OCFS2_AC_USE_MAIN) {
+		ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
+		ac->ac_chain = victim;
+		goto search;
+	}
+
 set_hint:
 	if (status != -ENOSPC) {
 		/* If the next search of this group is not likely to
@@ -2365,7 +2390,8 @@ int __ocfs2_claim_clusters(handle_t *handle,
 	BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted);
 
 	BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL
-	       && ac->ac_which != OCFS2_AC_USE_MAIN);
+	       && ac->ac_which != OCFS2_AC_USE_MAIN
+	       && ac->ac_which != OCFS2_AC_USE_MAIN_DISCONTIG);
 
 	if (ac->ac_which == OCFS2_AC_USE_LOCAL) {
 		WARN_ON(min_clusters > 1);
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index b481b834857d..bcf2ed4a8631 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -29,6 +29,7 @@ struct ocfs2_alloc_context {
 #define OCFS2_AC_USE_MAIN  2
 #define OCFS2_AC_USE_INODE 3
 #define OCFS2_AC_USE_META  4
+#define OCFS2_AC_USE_MAIN_DISCONTIG  5
 	u32    ac_which;
 
 	/* these are used by the chain search */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 8bb5022f3082..3d2533950bae 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1812,6 +1812,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	/* Orphan scan should be stopped as early as possible */
 	ocfs2_orphan_scan_stop(osb);
 
+	/* Stop quota recovery so that we can disable quotas */
+	ocfs2_recovery_disable_quota(osb);
+
 	ocfs2_disable_quotas(osb);
 
 	/* All dquots should be freed by now */
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 5ac743c6bc2e..08a6f372a352 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -32,12 +32,13 @@ static int orangefs_writepage_locked(struct folio *folio,
 	len = i_size_read(inode);
 	if (folio->private) {
 		wr = folio->private;
-		WARN_ON(wr->pos >= len);
 		off = wr->pos;
-		if (off + wr->len > len)
+		if ((off + wr->len > len) && (off <= len))
 			wlen = len - off;
 		else
 			wlen = wr->len;
+		if (wlen == 0)
+			wlen = wr->len;
 	} else {
 		WARN_ON(1);
 		off = folio_pos(folio);
@@ -46,8 +47,6 @@ static int orangefs_writepage_locked(struct folio *folio,
 		if (wlen > len - off)
 			wlen = len - off;
 	}
-	/* Should've been handled in orangefs_invalidate_folio. */
-	WARN_ON(off == len || off + wlen > len);
 
 	WARN_ON(wlen == 0);
 	bvec_set_folio(&bv, folio, wlen, offset_in_folio(folio, off));
@@ -320,6 +319,8 @@ static int orangefs_write_begin(struct file *file,
 			wr->len += len;
 			goto okay;
 		} else {
+			wr->pos = pos;
+			wr->len = len;
 			ret = orangefs_launder_folio(folio);
 			if (ret)
 				return ret;
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 6f2f8f4cfbbc..aef942a758ce 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -541,8 +541,6 @@ int ovl_set_metacopy_xattr(struct ovl_fs *ofs, struct dentry *d,
 bool ovl_is_metacopy_dentry(struct dentry *dentry);
 char *ovl_get_redirect_xattr(struct ovl_fs *ofs, const struct path *path, int padding);
 int ovl_ensure_verity_loaded(struct path *path);
-int ovl_get_verity_xattr(struct ovl_fs *ofs, const struct path *path,
-			 u8 *digest_buf, int *buf_length);
 int ovl_validate_verity(struct ovl_fs *ofs,
 			struct path *metapath,
 			struct path *datapath);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index b63474d1b064..e19940d649ca 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1138,6 +1138,11 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (ctx->nr == ctx->nr_data) {
+		pr_err("at least one non-data lowerdir is required\n");
+		return ERR_PTR(-EINVAL);
+	}
+
 	err = -EINVAL;
 	for (i = 0; i < ctx->nr; i++) {
 		l = &ctx->lower[i];
diff --git a/fs/pnode.c b/fs/pnode.c
index 7a062a5de10e..fb77427df39e 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -150,7 +150,7 @@ static struct mount *propagation_next(struct mount *m,
 					 struct mount *origin)
 {
 	/* are there any slaves of this mount? */
-	if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list))
+	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
 		return first_slave(m);
 
 	while (1) {
@@ -174,7 +174,7 @@ static struct mount *skip_propagation_subtree(struct mount *m,
 	 * Advance m such that propagation_next will not return
 	 * the slaves of m.
 	 */
-	if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list))
+	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
 		m = last_slave(m);
 
 	return m;
@@ -185,7 +185,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin)
 	while (1) {
 		while (1) {
 			struct mount *next;
-			if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list))
+			if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
 				return first_slave(m);
 			next = next_peer(m);
 			if (m->mnt_group_id == origin->mnt_group_id) {
@@ -226,11 +226,15 @@ static int propagate_one(struct mount *m, struct mountpoint *dest_mp)
 	struct mount *child;
 	int type;
 	/* skip ones added by this propagate_mnt() */
-	if (IS_MNT_PROPAGATED(m))
+	if (IS_MNT_NEW(m))
 		return 0;
-	/* skip if mountpoint isn't covered by it */
+	/* skip if mountpoint isn't visible in m */
 	if (!is_subdir(dest_mp->m_dentry, m->mnt.mnt_root))
 		return 0;
+	/* skip if m is in the anon_ns we are emptying */
+	if (m->mnt_ns->mntns_flags & MNTNS_PROPAGATING)
+		return 0;
+
 	if (peers(m, last_dest)) {
 		type = CL_MAKE_SHARED;
 	} else {
@@ -380,9 +384,6 @@ bool propagation_would_overmount(const struct mount *from,
 	if (!IS_MNT_SHARED(from))
 		return false;
 
-	if (IS_MNT_PROPAGATED(to))
-		return false;
-
 	if (to->mnt.mnt_root != mp->m_dentry)
 		return false;
 
diff --git a/fs/pnode.h b/fs/pnode.h
index ddafe0d087ca..34b6247af01d 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -12,7 +12,7 @@
 
 #define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED)
 #define IS_MNT_SLAVE(m) ((m)->mnt_master)
-#define IS_MNT_PROPAGATED(m) (!(m)->mnt_ns || ((m)->mnt_ns->mntns_flags & MNTNS_PROPAGATING))
+#define IS_MNT_NEW(m) (!(m)->mnt_ns)
 #define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
 #define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
 #define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index fe738623cf1b..240d82c6f908 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -29,7 +29,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
 {
 	struct cached_fid *cfid;
 
-	spin_lock(&cfids->cfid_list_lock);
 	list_for_each_entry(cfid, &cfids->entries, entry) {
 		if (!strcmp(cfid->path, path)) {
 			/*
@@ -38,25 +37,20 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
 			 * being deleted due to a lease break.
 			 */
 			if (!cfid->time || !cfid->has_lease) {
-				spin_unlock(&cfids->cfid_list_lock);
 				return NULL;
 			}
 			kref_get(&cfid->refcount);
-			spin_unlock(&cfids->cfid_list_lock);
 			return cfid;
 		}
 	}
 	if (lookup_only) {
-		spin_unlock(&cfids->cfid_list_lock);
 		return NULL;
 	}
 	if (cfids->num_entries >= max_cached_dirs) {
-		spin_unlock(&cfids->cfid_list_lock);
 		return NULL;
 	}
 	cfid = init_cached_dir(path);
 	if (cfid == NULL) {
-		spin_unlock(&cfids->cfid_list_lock);
 		return NULL;
 	}
 	cfid->cfids = cfids;
@@ -74,7 +68,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
 	 */
 	cfid->has_lease = true;
 
-	spin_unlock(&cfids->cfid_list_lock);
 	return cfid;
 }
 
@@ -187,8 +180,10 @@ replay_again:
 	if (!utf16_path)
 		return -ENOMEM;
 
+	spin_lock(&cfids->cfid_list_lock);
 	cfid = find_or_create_cached_dir(cfids, path, lookup_only, tcon->max_cached_dirs);
 	if (cfid == NULL) {
+		spin_unlock(&cfids->cfid_list_lock);
 		kfree(utf16_path);
 		return -ENOENT;
 	}
@@ -197,7 +192,6 @@ replay_again:
 	 * Otherwise, it is either a new entry or laundromat worker removed it
 	 * from @cfids->entries.  Caller will put last reference if the latter.
 	 */
-	spin_lock(&cfids->cfid_list_lock);
 	if (cfid->has_lease && cfid->time) {
 		spin_unlock(&cfids->cfid_list_lock);
 		*ret_cfid = cfid;
diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c
index e69968e88fe7..35892df7335c 100644
--- a/fs/smb/client/cifsencrypt.c
+++ b/fs/smb/client/cifsencrypt.c
@@ -704,18 +704,12 @@ cifs_crypto_secmech_release(struct TCP_Server_Info *server)
 	cifs_free_hash(&server->secmech.md5);
 	cifs_free_hash(&server->secmech.sha512);
 
-	if (!SERVER_IS_CHAN(server)) {
-		if (server->secmech.enc) {
-			crypto_free_aead(server->secmech.enc);
-			server->secmech.enc = NULL;
-		}
-
-		if (server->secmech.dec) {
-			crypto_free_aead(server->secmech.dec);
-			server->secmech.dec = NULL;
-		}
-	} else {
+	if (server->secmech.enc) {
+		crypto_free_aead(server->secmech.enc);
 		server->secmech.enc = NULL;
+	}
+	if (server->secmech.dec) {
+		crypto_free_aead(server->secmech.dec);
 		server->secmech.dec = NULL;
 	}
 }
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 07c4688ec4c9..3b32116b0b49 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -625,10 +625,8 @@ struct smb_version_operations {
 	bool (*is_status_io_timeout)(char *buf);
 	/* Check for STATUS_NETWORK_NAME_DELETED */
 	bool (*is_network_name_deleted)(char *buf, struct TCP_Server_Info *srv);
-	int (*parse_reparse_point)(struct cifs_sb_info *cifs_sb,
-				   const char *full_path,
-				   struct kvec *rsp_iov,
-				   struct cifs_open_info_data *data);
+	struct reparse_data_buffer * (*get_reparse_point_buffer)(const struct kvec *rsp_iov,
+								 u32 *plen);
 	int (*create_reparse_symlink)(const unsigned int xid,
 				      struct inode *inode,
 				      struct dentry *dentry,
diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h
index 48d0d6f439cf..1b79fe07476f 100644
--- a/fs/smb/client/cifspdu.h
+++ b/fs/smb/client/cifspdu.h
@@ -1266,10 +1266,9 @@ typedef struct smb_com_query_information_rsp {
 typedef struct smb_com_setattr_req {
 	struct smb_hdr hdr; /* wct = 8 */
 	__le16 attr;
-	__le16 time_low;
-	__le16 time_high;
+	__le32 last_write_time;
 	__le16 reserved[5]; /* must be zero */
-	__u16  ByteCount;
+	__le16 ByteCount;
 	__u8   BufferFormat; /* 4 = ASCII */
 	unsigned char fileName[];
 } __attribute__((packed)) SETATTR_REQ;
@@ -2256,6 +2255,8 @@ typedef struct {
 #define FILE_SUPPORTS_ENCRYPTION	0x00020000
 #define FILE_SUPPORTS_OBJECT_IDS	0x00010000
 #define FILE_VOLUME_IS_COMPRESSED	0x00008000
+#define FILE_SUPPORTS_POSIX_UNLINK_RENAME 0x00000400
+#define FILE_RETURNS_CLEANUP_RESULT_INFO  0x00000200
 #define FILE_SUPPORTS_REMOTE_STORAGE	0x00000100
 #define FILE_SUPPORTS_REPARSE_POINTS	0x00000080
 #define FILE_SUPPORTS_SPARSE_FILES	0x00000040
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index cfcc07905bdf..ecf774a8f1ca 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -163,6 +163,8 @@ extern int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name,
 extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool);
 extern int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
 				  struct cifsFileInfo **ret_file);
+extern int cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode,
+				  struct file *file);
 extern unsigned int smbCalcSize(void *buf);
 extern int decode_negTokenInit(unsigned char *security_blob, int length,
 			struct TCP_Server_Info *server);
@@ -393,6 +395,10 @@ extern int CIFSSMBQFSUnixInfo(const unsigned int xid, struct cifs_tcon *tcon);
 extern int CIFSSMBQFSPosixInfo(const unsigned int xid, struct cifs_tcon *tcon,
 			struct kstatfs *FSData);
 
+extern int SMBSetInformation(const unsigned int xid, struct cifs_tcon *tcon,
+			     const char *fileName, __le32 attributes, __le64 write_time,
+			     const struct nls_table *nls_codepage,
+			     struct cifs_sb_info *cifs_sb);
 extern int CIFSSMBSetPathInfo(const unsigned int xid, struct cifs_tcon *tcon,
 			const char *fileName, const FILE_BASIC_INFO *data,
 			const struct nls_table *nls_codepage,
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 60cb264a01e5..f55457b4b82e 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -5171,6 +5171,63 @@ CIFSSMBSetFileSize(const unsigned int xid, struct cifs_tcon *tcon,
 	return rc;
 }
 
+int
+SMBSetInformation(const unsigned int xid, struct cifs_tcon *tcon,
+		  const char *fileName, __le32 attributes, __le64 write_time,
+		  const struct nls_table *nls_codepage,
+		  struct cifs_sb_info *cifs_sb)
+{
+	SETATTR_REQ *pSMB;
+	SETATTR_RSP *pSMBr;
+	struct timespec64 ts;
+	int bytes_returned;
+	int name_len;
+	int rc;
+
+	cifs_dbg(FYI, "In %s path %s\n", __func__, fileName);
+
+retry:
+	rc = smb_init(SMB_COM_SETATTR, 8, tcon, (void **) &pSMB,
+		      (void **) &pSMBr);
+	if (rc)
+		return rc;
+
+	if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
+		name_len =
+			cifsConvertToUTF16((__le16 *) pSMB->fileName,
+					   fileName, PATH_MAX, nls_codepage,
+					   cifs_remap(cifs_sb));
+		name_len++;     /* trailing null */
+		name_len *= 2;
+	} else {
+		name_len = copy_path_name(pSMB->fileName, fileName);
+	}
+	/* Only few attributes can be set by this command, others are not accepted by Win9x. */
+	pSMB->attr = cpu_to_le16(le32_to_cpu(attributes) &
+			(ATTR_READONLY | ATTR_HIDDEN | ATTR_SYSTEM | ATTR_ARCHIVE));
+	/* Zero write time value (in both NT and SETATTR formats) means to not change it. */
+	if (le64_to_cpu(write_time) != 0) {
+		ts = cifs_NTtimeToUnix(write_time);
+		pSMB->last_write_time = cpu_to_le32(ts.tv_sec);
+	}
+	pSMB->BufferFormat = 0x04;
+	name_len++; /* account for buffer type byte */
+	inc_rfc1001_len(pSMB, (__u16)name_len);
+	pSMB->ByteCount = cpu_to_le16(name_len);
+
+	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
+			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
+	if (rc)
+		cifs_dbg(FYI, "Send error in %s = %d\n", __func__, rc);
+
+	cifs_buf_release(pSMB);
+
+	if (rc == -EAGAIN)
+		goto retry;
+
+	return rc;
+}
+
 /* Some legacy servers such as NT4 require that the file times be set on
    an open handle, rather than by pathname - this is awkward due to
    potential access conflicts on the open, but it is unavoidable for these
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index f298e86a3c1f..6bf04d9a5491 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -300,7 +300,6 @@ cifs_abort_connection(struct TCP_Server_Info *server)
 			 server->ssocket->flags);
 		sock_release(server->ssocket);
 		server->ssocket = NULL;
-		put_net(cifs_net_ns(server));
 	}
 	server->sequence_number = 0;
 	server->session_estab = false;
@@ -1074,13 +1073,9 @@ clean_demultiplex_info(struct TCP_Server_Info *server)
 	msleep(125);
 	if (cifs_rdma_enabled(server))
 		smbd_destroy(server);
-
 	if (server->ssocket) {
 		sock_release(server->ssocket);
 		server->ssocket = NULL;
-
-		/* Release netns reference for the socket. */
-		put_net(cifs_net_ns(server));
 	}
 
 	if (!list_empty(&server->pending_mid_q)) {
@@ -1128,7 +1123,6 @@ clean_demultiplex_info(struct TCP_Server_Info *server)
 		 */
 	}
 
-	/* Release netns reference for this server. */
 	put_net(cifs_net_ns(server));
 	kfree(server->leaf_fullpath);
 	kfree(server->hostname);
@@ -1774,8 +1768,6 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx,
 
 	tcp_ses->ops = ctx->ops;
 	tcp_ses->vals = ctx->vals;
-
-	/* Grab netns reference for this server. */
 	cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns));
 
 	tcp_ses->sign = ctx->sign;
@@ -1903,7 +1895,6 @@ smbd_connected:
 out_err_crypto_release:
 	cifs_crypto_secmech_release(tcp_ses);
 
-	/* Release netns reference for this server. */
 	put_net(cifs_net_ns(tcp_ses));
 
 out_err:
@@ -1912,10 +1903,8 @@ out_err:
 			cifs_put_tcp_session(tcp_ses->primary_server, false);
 		kfree(tcp_ses->hostname);
 		kfree(tcp_ses->leaf_fullpath);
-		if (tcp_ses->ssocket) {
+		if (tcp_ses->ssocket)
 			sock_release(tcp_ses->ssocket);
-			put_net(cifs_net_ns(tcp_ses));
-		}
 		kfree(tcp_ses);
 	}
 	return ERR_PTR(rc);
@@ -2556,6 +2545,8 @@ static int match_tcon(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
 		return 0;
 	if (tcon->nodelete != ctx->nodelete)
 		return 0;
+	if (tcon->posix_extensions != ctx->linux_ext)
+		return 0;
 	return 1;
 }
 
@@ -3357,24 +3348,20 @@ generic_ip_connect(struct TCP_Server_Info *server)
 		socket = server->ssocket;
 	} else {
 		struct net *net = cifs_net_ns(server);
+		struct sock *sk;
 
-		rc = sock_create_kern(net, sfamily, SOCK_STREAM, IPPROTO_TCP, &server->ssocket);
+		rc = __sock_create(net, sfamily, SOCK_STREAM,
+				   IPPROTO_TCP, &server->ssocket, 1);
 		if (rc < 0) {
 			cifs_server_dbg(VFS, "Error %d creating socket\n", rc);
 			return rc;
 		}
 
-		/*
-		 * Grab netns reference for the socket.
-		 *
-		 * This reference will be released in several situations:
-		 * - In the failure path before the cifsd thread is started.
-		 * - In the all place where server->socket is released, it is
-		 *   also set to NULL.
-		 * - Ultimately in clean_demultiplex_info(), during the final
-		 *   teardown.
-		 */
-		get_net(net);
+		sk = server->ssocket->sk;
+		__netns_tracker_free(net, &sk->ns_tracker, false);
+		sk->sk_net_refcnt = 1;
+		get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
+		sock_inuse_add(net, 1);
 
 		/* BB other socket options to set KEEPALIVE, NODELAY? */
 		cifs_dbg(FYI, "Socket created\n");
@@ -3426,7 +3413,6 @@ generic_ip_connect(struct TCP_Server_Info *server)
 	if (rc < 0) {
 		cifs_dbg(FYI, "Error %d connecting to server\n", rc);
 		trace_smb3_connect_err(server->hostname, server->conn_id, &server->dstaddr, rc);
-		put_net(cifs_net_ns(server));
 		sock_release(socket);
 		server->ssocket = NULL;
 		return rc;
@@ -3767,28 +3753,7 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 		}
 	}
 
-	/*
-	 * Clamp the rsize/wsize mount arguments if they are too big for the server
-	 * and set the rsize/wsize to the negotiated values if not passed in by
-	 * the user on mount
-	 */
-	if ((cifs_sb->ctx->wsize == 0) ||
-	    (cifs_sb->ctx->wsize > server->ops->negotiate_wsize(tcon, ctx))) {
-		cifs_sb->ctx->wsize =
-			round_down(server->ops->negotiate_wsize(tcon, ctx), PAGE_SIZE);
-		/*
-		 * in the very unlikely event that the server sent a max write size under PAGE_SIZE,
-		 * (which would get rounded down to 0) then reset wsize to absolute minimum eg 4096
-		 */
-		if (cifs_sb->ctx->wsize == 0) {
-			cifs_sb->ctx->wsize = PAGE_SIZE;
-			cifs_dbg(VFS, "wsize too small, reset to minimum ie PAGE_SIZE, usually 4096\n");
-		}
-	}
-	if ((cifs_sb->ctx->rsize == 0) ||
-	    (cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx)))
-		cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx);
-
+	cifs_negotiate_iosize(server, cifs_sb->ctx, tcon);
 	/*
 	 * The cookie is initialized from volume info returned above.
 	 * Inside cifs_fscache_get_super_cookie it checks
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 8407fb108664..950aa4f912f5 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -160,10 +160,10 @@ static int cifs_prepare_read(struct netfs_io_subrequest *subreq)
 	server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses);
 	rdata->server = server;
 
-	if (cifs_sb->ctx->rsize == 0)
-		cifs_sb->ctx->rsize =
-			server->ops->negotiate_rsize(tlink_tcon(req->cfile->tlink),
-						     cifs_sb->ctx);
+	if (cifs_sb->ctx->rsize == 0) {
+		cifs_negotiate_rsize(server, cifs_sb->ctx,
+				     tlink_tcon(req->cfile->tlink));
+	}
 
 	rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
 					   &size, &rdata->credits);
@@ -1007,6 +1007,11 @@ int cifs_open(struct inode *inode, struct file *file)
 		} else {
 			_cifsFileInfo_put(cfile, true, false);
 		}
+	} else {
+		/* hard link on the defeered close file */
+		rc = cifs_get_hardlink_path(tcon, inode, file);
+		if (rc)
+			cifs_close_deferred_file(CIFS_I(inode));
 	}
 
 	if (server->oplocks)
@@ -2071,6 +2076,29 @@ cifs_move_llist(struct list_head *source, struct list_head *dest)
 		list_move(li, dest);
 }
 
+int
+cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode,
+				struct file *file)
+{
+	struct cifsFileInfo *open_file = NULL;
+	struct cifsInodeInfo *cinode = CIFS_I(inode);
+	int rc = 0;
+
+	spin_lock(&tcon->open_file_lock);
+	spin_lock(&cinode->open_file_lock);
+
+	list_for_each_entry(open_file, &cinode->openFileList, flist) {
+		if (file->f_flags == open_file->f_flags) {
+			rc = -EINVAL;
+			break;
+		}
+	}
+
+	spin_unlock(&cinode->open_file_lock);
+	spin_unlock(&tcon->open_file_lock);
+	return rc;
+}
+
 void
 cifs_free_llist(struct list_head *llist)
 {
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 2980941b9667..a634a34d4086 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1021,6 +1021,7 @@ static int smb3_reconfigure(struct fs_context *fc)
 	struct dentry *root = fc->root;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb);
 	struct cifs_ses *ses = cifs_sb_master_tcon(cifs_sb)->ses;
+	unsigned int rsize = ctx->rsize, wsize = ctx->wsize;
 	char *new_password = NULL, *new_password2 = NULL;
 	bool need_recon = false;
 	int rc;
@@ -1103,11 +1104,8 @@ static int smb3_reconfigure(struct fs_context *fc)
 	STEAL_STRING(cifs_sb, ctx, iocharset);
 
 	/* if rsize or wsize not passed in on remount, use previous values */
-	if (ctx->rsize == 0)
-		ctx->rsize = cifs_sb->ctx->rsize;
-	if (ctx->wsize == 0)
-		ctx->wsize = cifs_sb->ctx->wsize;
-
+	ctx->rsize = rsize ? CIFS_ALIGN_RSIZE(fc, rsize) : cifs_sb->ctx->rsize;
+	ctx->wsize = wsize ? CIFS_ALIGN_WSIZE(fc, wsize) : cifs_sb->ctx->wsize;
 
 	smb3_cleanup_fs_context_contents(cifs_sb->ctx);
 	rc = smb3_fs_context_dup(cifs_sb->ctx, ctx);
@@ -1312,7 +1310,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 				__func__);
 			goto cifs_parse_mount_err;
 		}
-		ctx->bsize = result.uint_32;
+		ctx->bsize = CIFS_ALIGN_BSIZE(fc, result.uint_32);
 		ctx->got_bsize = true;
 		break;
 	case Opt_rasize:
@@ -1336,24 +1334,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		ctx->rasize = result.uint_32;
 		break;
 	case Opt_rsize:
-		ctx->rsize = result.uint_32;
+		ctx->rsize = CIFS_ALIGN_RSIZE(fc, result.uint_32);
 		ctx->got_rsize = true;
 		ctx->vol_rsize = ctx->rsize;
 		break;
 	case Opt_wsize:
-		ctx->wsize = result.uint_32;
+		ctx->wsize = CIFS_ALIGN_WSIZE(fc, result.uint_32);
 		ctx->got_wsize = true;
-		if (ctx->wsize % PAGE_SIZE != 0) {
-			ctx->wsize = round_down(ctx->wsize, PAGE_SIZE);
-			if (ctx->wsize == 0) {
-				ctx->wsize = PAGE_SIZE;
-				cifs_dbg(VFS, "wsize too small, reset to minimum %ld\n", PAGE_SIZE);
-			} else {
-				cifs_dbg(VFS,
-					 "wsize rounded down to %d to multiple of PAGE_SIZE %ld\n",
-					 ctx->wsize, PAGE_SIZE);
-			}
-		}
 		ctx->vol_wsize = ctx->wsize;
 		break;
 	case Opt_acregmax:
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index d1d29249bcdb..9e83302ce4b8 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -20,6 +20,21 @@
 		cifs_dbg(VFS, fmt, ## __VA_ARGS__);	\
 	} while (0)
 
+static inline size_t cifs_io_align(struct fs_context *fc,
+				   const char *name, size_t size)
+{
+	if (!size || !IS_ALIGNED(size, PAGE_SIZE)) {
+		cifs_errorf(fc, "unaligned %s, making it a multiple of %lu bytes\n",
+			    name, PAGE_SIZE);
+		size = umax(round_down(size, PAGE_SIZE), PAGE_SIZE);
+	}
+	return size;
+}
+
+#define CIFS_ALIGN_WSIZE(_fc, _size) cifs_io_align(_fc, "wsize", _size)
+#define CIFS_ALIGN_RSIZE(_fc, _size) cifs_io_align(_fc, "rsize", _size)
+#define CIFS_ALIGN_BSIZE(_fc, _size) cifs_io_align(_fc, "bsize", _size)
+
 enum smb_version {
 	Smb_1 = 1,
 	Smb_20,
@@ -361,4 +376,36 @@ static inline void cifs_mount_unlock(void)
 	mutex_unlock(&cifs_mount_mutex);
 }
 
+static inline void cifs_negotiate_rsize(struct TCP_Server_Info *server,
+					struct smb3_fs_context *ctx,
+					struct cifs_tcon *tcon)
+{
+	unsigned int size;
+
+	size = umax(server->ops->negotiate_rsize(tcon, ctx), PAGE_SIZE);
+	if (ctx->rsize)
+		size = umax(umin(ctx->rsize, size), PAGE_SIZE);
+	ctx->rsize = round_down(size, PAGE_SIZE);
+}
+
+static inline void cifs_negotiate_wsize(struct TCP_Server_Info *server,
+					struct smb3_fs_context *ctx,
+					struct cifs_tcon *tcon)
+{
+	unsigned int size;
+
+	size = umax(server->ops->negotiate_wsize(tcon, ctx), PAGE_SIZE);
+	if (ctx->wsize)
+		size = umax(umin(ctx->wsize, size), PAGE_SIZE);
+	ctx->wsize = round_down(size, PAGE_SIZE);
+}
+
+static inline void cifs_negotiate_iosize(struct TCP_Server_Info *server,
+					 struct smb3_fs_context *ctx,
+					 struct cifs_tcon *tcon)
+{
+	cifs_negotiate_rsize(server, ctx, tcon);
+	cifs_negotiate_wsize(server, ctx, tcon);
+}
+
 #endif
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index a00a9d91d0da..75be4b46bc6f 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -1203,18 +1203,17 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
 			goto out;
 		}
 		break;
-	case IO_REPARSE_TAG_MOUNT_POINT:
-		cifs_create_junction_fattr(fattr, sb);
-		rc = 0;
-		goto out;
 	default:
 		/* Check for cached reparse point data */
 		if (data->symlink_target || data->reparse.buf) {
 			rc = 0;
-		} else if (iov && server->ops->parse_reparse_point) {
-			rc = server->ops->parse_reparse_point(cifs_sb,
-							      full_path,
-							      iov, data);
+		} else if (iov && server->ops->get_reparse_point_buffer) {
+			struct reparse_data_buffer *reparse_buf;
+			u32 reparse_len;
+
+			reparse_buf = server->ops->get_reparse_point_buffer(iov, &reparse_len);
+			rc = parse_reparse_point(reparse_buf, reparse_len,
+						 cifs_sb, full_path, data);
 			/*
 			 * If the reparse point was not handled but it is the
 			 * name surrogate which points to directory, then treat
@@ -1228,6 +1227,16 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
 				cifs_create_junction_fattr(fattr, sb);
 				goto out;
 			}
+			/*
+			 * If the reparse point is unsupported by the Linux SMB
+			 * client then let it process by the SMB server. So mask
+			 * the -EOPNOTSUPP error code. This will allow Linux SMB
+			 * client to send SMB OPEN request to server. If server
+			 * does not support this reparse point too then server
+			 * will return error during open the path.
+			 */
+			if (rc == -EOPNOTSUPP)
+				rc = 0;
 		}
 
 		if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc) {
diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index 2b9e9885dc42..bb25e77c5540 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -542,12 +542,12 @@ static int wsl_set_reparse_buf(struct reparse_data_buffer **buf,
 			kfree(symname_utf16);
 			return -ENOMEM;
 		}
-		/* Flag 0x02000000 is unknown, but all wsl symlinks have this value */
-		symlink_buf->Flags = cpu_to_le32(0x02000000);
-		/* PathBuffer is in UTF-8 but without trailing null-term byte */
+		/* Version field must be set to 2 (MS-FSCC 2.1.2.7) */
+		symlink_buf->Version = cpu_to_le32(2);
+		/* Target for Version 2 is in UTF-8 but without trailing null-term byte */
 		symname_utf8_len = utf16s_to_utf8s((wchar_t *)symname_utf16, symname_utf16_len/2,
 						   UTF16_LITTLE_ENDIAN,
-						   symlink_buf->PathBuffer,
+						   symlink_buf->Target,
 						   symname_utf8_maxlen);
 		*buf = (struct reparse_data_buffer *)symlink_buf;
 		buf_len = sizeof(struct reparse_wsl_symlink_data_buffer) + symname_utf8_len;
@@ -1016,29 +1016,36 @@ static int parse_reparse_wsl_symlink(struct reparse_wsl_symlink_data_buffer *buf
 				     struct cifs_open_info_data *data)
 {
 	int len = le16_to_cpu(buf->ReparseDataLength);
+	int data_offset = offsetof(typeof(*buf), Target) - offsetof(typeof(*buf), Version);
 	int symname_utf8_len;
 	__le16 *symname_utf16;
 	int symname_utf16_len;
 
-	if (len <= sizeof(buf->Flags)) {
+	if (len <= data_offset) {
 		cifs_dbg(VFS, "srv returned malformed wsl symlink buffer\n");
 		return -EIO;
 	}
 
-	/* PathBuffer is in UTF-8 but without trailing null-term byte */
-	symname_utf8_len = len - sizeof(buf->Flags);
+	/* MS-FSCC 2.1.2.7 defines layout of the Target field only for Version 2. */
+	if (le32_to_cpu(buf->Version) != 2) {
+		cifs_dbg(VFS, "srv returned unsupported wsl symlink version %u\n", le32_to_cpu(buf->Version));
+		return -EIO;
+	}
+
+	/* Target for Version 2 is in UTF-8 but without trailing null-term byte */
+	symname_utf8_len = len - data_offset;
 	/*
 	 * Check that buffer does not contain null byte
 	 * because Linux cannot process symlink with null byte.
 	 */
-	if (strnlen(buf->PathBuffer, symname_utf8_len) != symname_utf8_len) {
+	if (strnlen(buf->Target, symname_utf8_len) != symname_utf8_len) {
 		cifs_dbg(VFS, "srv returned null byte in wsl symlink target location\n");
 		return -EIO;
 	}
 	symname_utf16 = kzalloc(symname_utf8_len * 2, GFP_KERNEL);
 	if (!symname_utf16)
 		return -ENOMEM;
-	symname_utf16_len = utf8s_to_utf16s(buf->PathBuffer, symname_utf8_len,
+	symname_utf16_len = utf8s_to_utf16s(buf->Target, symname_utf8_len,
 					    UTF16_LITTLE_ENDIAN,
 					    (wchar_t *) symname_utf16, symname_utf8_len * 2);
 	if (symname_utf16_len < 0) {
@@ -1062,8 +1069,6 @@ int parse_reparse_point(struct reparse_data_buffer *buf,
 			const char *full_path,
 			struct cifs_open_info_data *data)
 {
-	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
-
 	data->reparse.buf = buf;
 
 	/* See MS-FSCC 2.1.2 */
@@ -1090,24 +1095,17 @@ int parse_reparse_point(struct reparse_data_buffer *buf,
 		}
 		return 0;
 	default:
-		cifs_tcon_dbg(VFS | ONCE, "unhandled reparse tag: 0x%08x\n",
-			      le32_to_cpu(buf->ReparseTag));
 		return -EOPNOTSUPP;
 	}
 }
 
-int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb,
-			     const char *full_path,
-			     struct kvec *rsp_iov,
-			     struct cifs_open_info_data *data)
+struct reparse_data_buffer *smb2_get_reparse_point_buffer(const struct kvec *rsp_iov,
+							  u32 *plen)
 {
-	struct reparse_data_buffer *buf;
 	struct smb2_ioctl_rsp *io = rsp_iov->iov_base;
-	u32 plen = le32_to_cpu(io->OutputCount);
-
-	buf = (struct reparse_data_buffer *)((u8 *)io +
-					     le32_to_cpu(io->OutputOffset));
-	return parse_reparse_point(buf, plen, cifs_sb, full_path, data);
+	*plen = le32_to_cpu(io->OutputCount);
+	return (struct reparse_data_buffer *)((u8 *)io +
+					      le32_to_cpu(io->OutputOffset));
 }
 
 static bool wsl_to_fattr(struct cifs_open_info_data *data,
@@ -1233,16 +1231,6 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
 	bool ok;
 
 	switch (tag) {
-	case IO_REPARSE_TAG_INTERNAL:
-		if (!(fattr->cf_cifsattrs & ATTR_DIRECTORY))
-			return false;
-		fallthrough;
-	case IO_REPARSE_TAG_DFS:
-	case IO_REPARSE_TAG_DFSR:
-	case IO_REPARSE_TAG_MOUNT_POINT:
-		/* See cifs_create_junction_fattr() */
-		fattr->cf_mode = S_IFDIR | 0711;
-		break;
 	case IO_REPARSE_TAG_LX_SYMLINK:
 	case IO_REPARSE_TAG_LX_FIFO:
 	case IO_REPARSE_TAG_AF_UNIX:
@@ -1262,7 +1250,14 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
 		fattr->cf_mode |= S_IFLNK;
 		break;
 	default:
-		return false;
+		if (!(fattr->cf_cifsattrs & ATTR_DIRECTORY))
+			return false;
+		if (!IS_REPARSE_TAG_NAME_SURROGATE(tag) &&
+		    tag != IO_REPARSE_TAG_INTERNAL)
+			return false;
+		/* See cifs_create_junction_fattr() */
+		fattr->cf_mode = S_IFDIR | 0711;
+		break;
 	}
 
 	fattr->cf_dtype = S_DT(fattr->cf_mode);
diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h
index c0be5ab45a78..08de853b36a8 100644
--- a/fs/smb/client/reparse.h
+++ b/fs/smb/client/reparse.h
@@ -135,9 +135,6 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode,
 int smb2_mknod_reparse(unsigned int xid, struct inode *inode,
 		       struct dentry *dentry, struct cifs_tcon *tcon,
 		       const char *full_path, umode_t mode, dev_t dev);
-int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb,
-			     const char *full_path,
-			     struct kvec *rsp_iov,
-			     struct cifs_open_info_data *data);
+struct reparse_data_buffer *smb2_get_reparse_point_buffer(const struct kvec *rsp_iov, u32 *len);
 
 #endif /* _CIFS_REPARSE_H */
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index f2ca5963cd9d..b3fa9ee26912 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -680,6 +680,22 @@ unicode_oslm_strings(char **pbcc_area, const struct nls_table *nls_cp)
 	*pbcc_area = bcc_ptr;
 }
 
+static void
+ascii_oslm_strings(char **pbcc_area, const struct nls_table *nls_cp)
+{
+	char *bcc_ptr = *pbcc_area;
+
+	strcpy(bcc_ptr, "Linux version ");
+	bcc_ptr += strlen("Linux version ");
+	strcpy(bcc_ptr, init_utsname()->release);
+	bcc_ptr += strlen(init_utsname()->release) + 1;
+
+	strcpy(bcc_ptr, CIFS_NETWORK_OPSYS);
+	bcc_ptr += strlen(CIFS_NETWORK_OPSYS) + 1;
+
+	*pbcc_area = bcc_ptr;
+}
+
 static void unicode_domain_string(char **pbcc_area, struct cifs_ses *ses,
 				   const struct nls_table *nls_cp)
 {
@@ -704,6 +720,25 @@ static void unicode_domain_string(char **pbcc_area, struct cifs_ses *ses,
 	*pbcc_area = bcc_ptr;
 }
 
+static void ascii_domain_string(char **pbcc_area, struct cifs_ses *ses,
+				const struct nls_table *nls_cp)
+{
+	char *bcc_ptr = *pbcc_area;
+	int len;
+
+	/* copy domain */
+	if (ses->domainName != NULL) {
+		len = strscpy(bcc_ptr, ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+		if (WARN_ON_ONCE(len < 0))
+			len = CIFS_MAX_DOMAINNAME_LEN - 1;
+		bcc_ptr += len;
+	} /* else we send a null domain name so server will default to its own domain */
+	*bcc_ptr = 0;
+	bcc_ptr++;
+
+	*pbcc_area = bcc_ptr;
+}
+
 static void unicode_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
 				   const struct nls_table *nls_cp)
 {
@@ -749,25 +784,10 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
 	*bcc_ptr = 0;
 	bcc_ptr++; /* account for null termination */
 
-	/* copy domain */
-	if (ses->domainName != NULL) {
-		len = strscpy(bcc_ptr, ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
-		if (WARN_ON_ONCE(len < 0))
-			len = CIFS_MAX_DOMAINNAME_LEN - 1;
-		bcc_ptr += len;
-	} /* else we send a null domain name so server will default to its own domain */
-	*bcc_ptr = 0;
-	bcc_ptr++;
-
 	/* BB check for overflow here */
 
-	strcpy(bcc_ptr, "Linux version ");
-	bcc_ptr += strlen("Linux version ");
-	strcpy(bcc_ptr, init_utsname()->release);
-	bcc_ptr += strlen(init_utsname()->release) + 1;
-
-	strcpy(bcc_ptr, CIFS_NETWORK_OPSYS);
-	bcc_ptr += strlen(CIFS_NETWORK_OPSYS) + 1;
+	ascii_domain_string(&bcc_ptr, ses, nls_cp);
+	ascii_oslm_strings(&bcc_ptr, nls_cp);
 
 	*pbcc_area = bcc_ptr;
 }
@@ -1570,7 +1590,7 @@ sess_auth_kerberos(struct sess_data *sess_data)
 	sess_data->iov[1].iov_len = msg->secblob_len;
 	pSMB->req.SecurityBlobLength = cpu_to_le16(sess_data->iov[1].iov_len);
 
-	if (ses->capabilities & CAP_UNICODE) {
+	if (pSMB->req.hdr.Flags2 & SMBFLG2_UNICODE) {
 		/* unicode strings must be word aligned */
 		if (!IS_ALIGNED(sess_data->iov[0].iov_len + sess_data->iov[1].iov_len, 2)) {
 			*bcc_ptr = 0;
@@ -1579,8 +1599,8 @@ sess_auth_kerberos(struct sess_data *sess_data)
 		unicode_oslm_strings(&bcc_ptr, sess_data->nls_cp);
 		unicode_domain_string(&bcc_ptr, ses, sess_data->nls_cp);
 	} else {
-		/* BB: is this right? */
-		ascii_ssetup_strings(&bcc_ptr, ses, sess_data->nls_cp);
+		ascii_oslm_strings(&bcc_ptr, sess_data->nls_cp);
+		ascii_domain_string(&bcc_ptr, ses, sess_data->nls_cp);
 	}
 
 	sess_data->iov[2].iov_len = (long) bcc_ptr -
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 26df807fbe7a..b27a182629ec 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -432,7 +432,7 @@ cifs_negotiate(const unsigned int xid,
 }
 
 static unsigned int
-cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
+smb1_negotiate_wsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
 {
 	__u64 unix_cap = le64_to_cpu(tcon->fsUnixInfo.Capability);
 	struct TCP_Server_Info *server = tcon->ses->server;
@@ -467,7 +467,7 @@ cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
 }
 
 static unsigned int
-cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
+smb1_negotiate_rsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
 {
 	__u64 unix_cap = le64_to_cpu(tcon->fsUnixInfo.Capability);
 	struct TCP_Server_Info *server = tcon->ses->server;
@@ -543,24 +543,104 @@ static int cifs_query_path_info(const unsigned int xid,
 				const char *full_path,
 				struct cifs_open_info_data *data)
 {
-	int rc;
+	int rc = -EOPNOTSUPP;
 	FILE_ALL_INFO fi = {};
+	struct cifs_search_info search_info = {};
+	bool non_unicode_wildcard = false;
 
 	data->reparse_point = false;
 	data->adjust_tz = false;
 
-	/* could do find first instead but this returns more info */
-	rc = CIFSSMBQPathInfo(xid, tcon, full_path, &fi, 0 /* not legacy */, cifs_sb->local_nls,
-			      cifs_remap(cifs_sb));
 	/*
-	 * BB optimize code so we do not make the above call when server claims
-	 * no NT SMB support and the above call failed at least once - set flag
-	 * in tcon or mount.
+	 * First try CIFSSMBQPathInfo() function which returns more info
+	 * (NumberOfLinks) than CIFSFindFirst() fallback function.
+	 * Some servers like Win9x do not support SMB_QUERY_FILE_ALL_INFO over
+	 * TRANS2_QUERY_PATH_INFORMATION, but supports it with filehandle over
+	 * TRANS2_QUERY_FILE_INFORMATION (function CIFSSMBQFileInfo(). But SMB
+	 * Open command on non-NT servers works only for files, does not work
+	 * for directories. And moreover Win9x SMB server returns bogus data in
+	 * SMB_QUERY_FILE_ALL_INFO Attributes field. So for non-NT servers,
+	 * do not even use CIFSSMBQPathInfo() or CIFSSMBQFileInfo() function.
+	 */
+	if (tcon->ses->capabilities & CAP_NT_SMBS)
+		rc = CIFSSMBQPathInfo(xid, tcon, full_path, &fi, 0 /* not legacy */,
+				      cifs_sb->local_nls, cifs_remap(cifs_sb));
+
+	/*
+	 * Non-UNICODE variant of fallback functions below expands wildcards,
+	 * so they cannot be used for querying paths with wildcard characters.
+	 */
+	if (rc && !(tcon->ses->capabilities & CAP_UNICODE) && strpbrk(full_path, "*?\"><"))
+		non_unicode_wildcard = true;
+
+	/*
+	 * Then fallback to CIFSFindFirst() which works also with non-NT servers
+	 * but does not does not provide NumberOfLinks.
+	 */
+	if ((rc == -EOPNOTSUPP || rc == -EINVAL) &&
+	    !non_unicode_wildcard) {
+		if (!(tcon->ses->capabilities & tcon->ses->server->vals->cap_nt_find))
+			search_info.info_level = SMB_FIND_FILE_INFO_STANDARD;
+		else
+			search_info.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO;
+		rc = CIFSFindFirst(xid, tcon, full_path, cifs_sb, NULL,
+				   CIFS_SEARCH_CLOSE_ALWAYS | CIFS_SEARCH_CLOSE_AT_END,
+				   &search_info, false);
+		if (rc == 0) {
+			if (!(tcon->ses->capabilities & tcon->ses->server->vals->cap_nt_find)) {
+				FIND_FILE_STANDARD_INFO *di;
+				int offset = tcon->ses->server->timeAdj;
+
+				di = (FIND_FILE_STANDARD_INFO *)search_info.srch_entries_start;
+				fi.CreationTime = cpu_to_le64(cifs_UnixTimeToNT(cnvrtDosUnixTm(
+						di->CreationDate, di->CreationTime, offset)));
+				fi.LastAccessTime = cpu_to_le64(cifs_UnixTimeToNT(cnvrtDosUnixTm(
+						di->LastAccessDate, di->LastAccessTime, offset)));
+				fi.LastWriteTime = cpu_to_le64(cifs_UnixTimeToNT(cnvrtDosUnixTm(
+						di->LastWriteDate, di->LastWriteTime, offset)));
+				fi.ChangeTime = fi.LastWriteTime;
+				fi.Attributes = cpu_to_le32(le16_to_cpu(di->Attributes));
+				fi.AllocationSize = cpu_to_le64(le32_to_cpu(di->AllocationSize));
+				fi.EndOfFile = cpu_to_le64(le32_to_cpu(di->DataSize));
+			} else {
+				FILE_FULL_DIRECTORY_INFO *di;
+
+				di = (FILE_FULL_DIRECTORY_INFO *)search_info.srch_entries_start;
+				fi.CreationTime = di->CreationTime;
+				fi.LastAccessTime = di->LastAccessTime;
+				fi.LastWriteTime = di->LastWriteTime;
+				fi.ChangeTime = di->ChangeTime;
+				fi.Attributes = di->ExtFileAttributes;
+				fi.AllocationSize = di->AllocationSize;
+				fi.EndOfFile = di->EndOfFile;
+				fi.EASize = di->EaSize;
+			}
+			fi.NumberOfLinks = cpu_to_le32(1);
+			fi.DeletePending = 0;
+			fi.Directory = !!(le32_to_cpu(fi.Attributes) & ATTR_DIRECTORY);
+			cifs_buf_release(search_info.ntwrk_buf_start);
+		} else if (!full_path[0]) {
+			/*
+			 * CIFSFindFirst() does not work on root path if the
+			 * root path was exported on the server from the top
+			 * level path (drive letter).
+			 */
+			rc = -EOPNOTSUPP;
+		}
+	}
+
+	/*
+	 * If everything failed then fallback to the legacy SMB command
+	 * SMB_COM_QUERY_INFORMATION which works with all servers, but
+	 * provide just few information.
 	 */
-	if ((rc == -EOPNOTSUPP) || (rc == -EINVAL)) {
+	if ((rc == -EOPNOTSUPP || rc == -EINVAL) && !non_unicode_wildcard) {
 		rc = SMBQueryInformation(xid, tcon, full_path, &fi, cifs_sb->local_nls,
 					 cifs_remap(cifs_sb));
 		data->adjust_tz = true;
+	} else if ((rc == -EOPNOTSUPP || rc == -EINVAL) && non_unicode_wildcard) {
+		/* Path with non-UNICODE wildcard character cannot exist. */
+		rc = -ENOENT;
 	}
 
 	if (!rc) {
@@ -568,6 +648,42 @@ static int cifs_query_path_info(const unsigned int xid,
 		data->reparse_point = le32_to_cpu(fi.Attributes) & ATTR_REPARSE;
 	}
 
+#ifdef CONFIG_CIFS_XATTR
+	/*
+	 * For WSL CHR and BLK reparse points it is required to fetch
+	 * EA $LXDEV which contains major and minor device numbers.
+	 */
+	if (!rc && data->reparse_point) {
+		struct smb2_file_full_ea_info *ea;
+
+		ea = (struct smb2_file_full_ea_info *)data->wsl.eas;
+		rc = CIFSSMBQAllEAs(xid, tcon, full_path, SMB2_WSL_XATTR_DEV,
+				    &ea->ea_data[SMB2_WSL_XATTR_NAME_LEN + 1],
+				    SMB2_WSL_XATTR_DEV_SIZE, cifs_sb);
+		if (rc == SMB2_WSL_XATTR_DEV_SIZE) {
+			ea->next_entry_offset = cpu_to_le32(0);
+			ea->flags = 0;
+			ea->ea_name_length = SMB2_WSL_XATTR_NAME_LEN;
+			ea->ea_value_length = cpu_to_le16(SMB2_WSL_XATTR_DEV_SIZE);
+			memcpy(&ea->ea_data[0], SMB2_WSL_XATTR_DEV, SMB2_WSL_XATTR_NAME_LEN + 1);
+			data->wsl.eas_len = sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 +
+					    SMB2_WSL_XATTR_DEV_SIZE;
+			rc = 0;
+		} else if (rc >= 0) {
+			/* It is an error if EA $LXDEV has wrong size. */
+			rc = -EINVAL;
+		} else {
+			/*
+			 * In all other cases ignore error if fetching
+			 * of EA $LXDEV failed. It is needed only for
+			 * WSL CHR and BLK reparse points and wsl_to_fattr()
+			 * handle the case when EA is missing.
+			 */
+			rc = 0;
+		}
+	}
+#endif
+
 	return rc;
 }
 
@@ -603,6 +719,13 @@ static int cifs_query_file_info(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc;
 	FILE_ALL_INFO fi = {};
 
+	/*
+	 * CIFSSMBQFileInfo() for non-NT servers returns bogus data in
+	 * Attributes fields. So do not use this command for non-NT servers.
+	 */
+	if (!(tcon->ses->capabilities & CAP_NT_SMBS))
+		return -EOPNOTSUPP;
+
 	if (cfile->symlink_target) {
 		data->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL);
 		if (!data->symlink_target)
@@ -773,6 +896,9 @@ smb_set_file_info(struct inode *inode, const char *full_path,
 	struct cifs_fid fid;
 	struct cifs_open_parms oparms;
 	struct cifsFileInfo *open_file;
+	FILE_BASIC_INFO new_buf;
+	struct cifs_open_info_data query_data;
+	__le64 write_time = buf->LastWriteTime;
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink = NULL;
@@ -780,20 +906,58 @@ smb_set_file_info(struct inode *inode, const char *full_path,
 
 	/* if the file is already open for write, just use that fileid */
 	open_file = find_writable_file(cinode, FIND_WR_FSUID_ONLY);
+
 	if (open_file) {
 		fid.netfid = open_file->fid.netfid;
 		netpid = open_file->pid;
 		tcon = tlink_tcon(open_file->tlink);
-		goto set_via_filehandle;
+	} else {
+		tlink = cifs_sb_tlink(cifs_sb);
+		if (IS_ERR(tlink)) {
+			rc = PTR_ERR(tlink);
+			tlink = NULL;
+			goto out;
+		}
+		tcon = tlink_tcon(tlink);
 	}
 
-	tlink = cifs_sb_tlink(cifs_sb);
-	if (IS_ERR(tlink)) {
-		rc = PTR_ERR(tlink);
-		tlink = NULL;
-		goto out;
+	/*
+	 * Non-NT servers interprets zero time value in SMB_SET_FILE_BASIC_INFO
+	 * over TRANS2_SET_FILE_INFORMATION as a valid time value. NT servers
+	 * interprets zero time value as do not change existing value on server.
+	 * API of ->set_file_info() callback expects that zero time value has
+	 * the NT meaning - do not change. Therefore if server is non-NT and
+	 * some time values in "buf" are zero, then fetch missing time values.
+	 */
+	if (!(tcon->ses->capabilities & CAP_NT_SMBS) &&
+	    (!buf->CreationTime || !buf->LastAccessTime ||
+	     !buf->LastWriteTime || !buf->ChangeTime)) {
+		rc = cifs_query_path_info(xid, tcon, cifs_sb, full_path, &query_data);
+		if (rc) {
+			if (open_file) {
+				cifsFileInfo_put(open_file);
+				open_file = NULL;
+			}
+			goto out;
+		}
+		/*
+		 * Original write_time from buf->LastWriteTime is preserved
+		 * as SMBSetInformation() interprets zero as do not change.
+		 */
+		new_buf = *buf;
+		buf = &new_buf;
+		if (!buf->CreationTime)
+			buf->CreationTime = query_data.fi.CreationTime;
+		if (!buf->LastAccessTime)
+			buf->LastAccessTime = query_data.fi.LastAccessTime;
+		if (!buf->LastWriteTime)
+			buf->LastWriteTime = query_data.fi.LastWriteTime;
+		if (!buf->ChangeTime)
+			buf->ChangeTime = query_data.fi.ChangeTime;
 	}
-	tcon = tlink_tcon(tlink);
+
+	if (open_file)
+		goto set_via_filehandle;
 
 	rc = CIFSSMBSetPathInfo(xid, tcon, full_path, buf, cifs_sb->local_nls,
 				cifs_sb);
@@ -814,8 +978,45 @@ smb_set_file_info(struct inode *inode, const char *full_path,
 		.fid = &fid,
 	};
 
-	cifs_dbg(FYI, "calling SetFileInfo since SetPathInfo for times not supported by this server\n");
-	rc = CIFS_open(xid, &oparms, &oplock, NULL);
+	if (S_ISDIR(inode->i_mode) && !(tcon->ses->capabilities & CAP_NT_SMBS)) {
+		/* Opening directory path is not possible on non-NT servers. */
+		rc = -EOPNOTSUPP;
+	} else {
+		/*
+		 * Use cifs_open_file() instead of CIFS_open() as the
+		 * cifs_open_file() selects the correct function which
+		 * works also on non-NT servers.
+		 */
+		rc = cifs_open_file(xid, &oparms, &oplock, NULL);
+		/*
+		 * Opening path for writing on non-NT servers is not
+		 * possible when the read-only attribute is already set.
+		 * Non-NT server in this case returns -EACCES. For those
+		 * servers the only possible way how to clear the read-only
+		 * bit is via SMB_COM_SETATTR command.
+		 */
+		if (rc == -EACCES &&
+		    (cinode->cifsAttrs & ATTR_READONLY) &&
+		     le32_to_cpu(buf->Attributes) != 0 && /* 0 = do not change attrs */
+		     !(le32_to_cpu(buf->Attributes) & ATTR_READONLY) &&
+		     !(tcon->ses->capabilities & CAP_NT_SMBS))
+			rc = -EOPNOTSUPP;
+	}
+
+	/* Fallback to SMB_COM_SETATTR command when absolutelty needed. */
+	if (rc == -EOPNOTSUPP) {
+		cifs_dbg(FYI, "calling SetInformation since SetPathInfo for attrs/times not supported by this server\n");
+		rc = SMBSetInformation(xid, tcon, full_path,
+				       buf->Attributes != 0 ? buf->Attributes : cpu_to_le32(cinode->cifsAttrs),
+				       write_time,
+				       cifs_sb->local_nls, cifs_sb);
+		if (rc == 0)
+			cinode->cifsAttrs = le32_to_cpu(buf->Attributes);
+		else
+			rc = -EACCES;
+		goto out;
+	}
+
 	if (rc != 0) {
 		if (rc == -EIO)
 			rc = -EINVAL;
@@ -823,6 +1024,7 @@ smb_set_file_info(struct inode *inode, const char *full_path,
 	}
 
 	netpid = current->tgid;
+	cifs_dbg(FYI, "calling SetFileInfo since SetPathInfo for attrs/times not supported by this server\n");
 
 set_via_filehandle:
 	rc = CIFSSMBSetFileInfo(xid, tcon, buf, fid.netfid, netpid);
@@ -833,6 +1035,21 @@ set_via_filehandle:
 		CIFSSMBClose(xid, tcon, fid.netfid);
 	else
 		cifsFileInfo_put(open_file);
+
+	/*
+	 * Setting the read-only bit is not honered on non-NT servers when done
+	 * via open-semantics. So for setting it, use SMB_COM_SETATTR command.
+	 * This command works only after the file is closed, so use it only when
+	 * operation was called without the filehandle.
+	 */
+	if (open_file == NULL &&
+	    !(tcon->ses->capabilities & CAP_NT_SMBS) &&
+	    le32_to_cpu(buf->Attributes) & ATTR_READONLY) {
+		SMBSetInformation(xid, tcon, full_path,
+				  buf->Attributes,
+				  0 /* do not change write time */,
+				  cifs_sb->local_nls, cifs_sb);
+	}
 out:
 	if (tlink != NULL)
 		cifs_put_tlink(tlink);
@@ -970,18 +1187,13 @@ static int cifs_query_symlink(const unsigned int xid,
 	return rc;
 }
 
-static int cifs_parse_reparse_point(struct cifs_sb_info *cifs_sb,
-				    const char *full_path,
-				    struct kvec *rsp_iov,
-				    struct cifs_open_info_data *data)
+static struct reparse_data_buffer *cifs_get_reparse_point_buffer(const struct kvec *rsp_iov,
+								 u32 *plen)
 {
-	struct reparse_data_buffer *buf;
 	TRANSACT_IOCTL_RSP *io = rsp_iov->iov_base;
-	u32 plen = le16_to_cpu(io->ByteCount);
-
-	buf = (struct reparse_data_buffer *)((__u8 *)&io->hdr.Protocol +
-					     le32_to_cpu(io->DataOffset));
-	return parse_reparse_point(buf, plen, cifs_sb, full_path, data);
+	*plen = le16_to_cpu(io->ByteCount);
+	return (struct reparse_data_buffer *)((__u8 *)&io->hdr.Protocol +
+					      le32_to_cpu(io->DataOffset));
 }
 
 static bool
@@ -1130,8 +1342,8 @@ struct smb_version_operations smb1_operations = {
 	.check_trans2 = cifs_check_trans2,
 	.need_neg = cifs_need_neg,
 	.negotiate = cifs_negotiate,
-	.negotiate_wsize = cifs_negotiate_wsize,
-	.negotiate_rsize = cifs_negotiate_rsize,
+	.negotiate_wsize = smb1_negotiate_wsize,
+	.negotiate_rsize = smb1_negotiate_rsize,
 	.sess_setup = CIFS_SessSetup,
 	.logoff = CIFSSMBLogoff,
 	.tree_connect = CIFSTCon,
@@ -1157,7 +1369,7 @@ struct smb_version_operations smb1_operations = {
 	.rename = CIFSSMBRename,
 	.create_hardlink = CIFSCreateHardLink,
 	.query_symlink = cifs_query_symlink,
-	.parse_reparse_point = cifs_parse_reparse_point,
+	.get_reparse_point_buffer = cifs_get_reparse_point_buffer,
 	.open = cifs_open_file,
 	.set_fid = cifs_set_fid,
 	.close = cifs_close_file,
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 57d9bfbadd97..2a3e46b8e15a 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -666,6 +666,8 @@ finished:
 		/* smb2_parse_contexts() fills idata->fi.IndexNumber */
 		rc = smb2_parse_contexts(server, &rsp_iov[0], &oparms->fid->epoch,
 					 oparms->fid->lease_key, &oplock, &idata->fi, NULL);
+		if (rc)
+			cifs_dbg(VFS, "rc: %d parsing context of compound op\n", rc);
 	}
 
 	for (i = 0; i < num_cmds; i++) {
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 41d8cd20b25f..2fe8eeb98535 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -4555,9 +4555,9 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
 			return rc;
 		}
 	} else {
-		if (unlikely(!server->secmech.dec))
-			return -EIO;
-
+		rc = smb3_crypto_aead_allocate(server);
+		if (unlikely(rc))
+			return rc;
 		tfm = server->secmech.dec;
 	}
 
@@ -5303,7 +5303,7 @@ struct smb_version_operations smb20_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.parse_reparse_point = smb2_parse_reparse_point,
+	.get_reparse_point_buffer = smb2_get_reparse_point_buffer,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
 	.create_reparse_symlink = smb2_create_reparse_symlink,
@@ -5406,7 +5406,7 @@ struct smb_version_operations smb21_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.parse_reparse_point = smb2_parse_reparse_point,
+	.get_reparse_point_buffer = smb2_get_reparse_point_buffer,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
 	.create_reparse_symlink = smb2_create_reparse_symlink,
@@ -5513,7 +5513,7 @@ struct smb_version_operations smb30_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.parse_reparse_point = smb2_parse_reparse_point,
+	.get_reparse_point_buffer = smb2_get_reparse_point_buffer,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
 	.create_reparse_symlink = smb2_create_reparse_symlink,
@@ -5629,7 +5629,7 @@ struct smb_version_operations smb311_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.parse_reparse_point = smb2_parse_reparse_point,
+	.get_reparse_point_buffer = smb2_get_reparse_point_buffer,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
 	.create_reparse_symlink = smb2_create_reparse_symlink,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 81e05db8e4d5..4e28632b5fd6 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -1252,15 +1252,8 @@ SMB2_negotiate(const unsigned int xid,
 			cifs_server_dbg(VFS, "Missing expected negotiate contexts\n");
 	}
 
-	if (server->cipher_type && !rc) {
-		if (!SERVER_IS_CHAN(server)) {
-			rc = smb3_crypto_aead_allocate(server);
-		} else {
-			/* For channels, just reuse the primary server crypto secmech. */
-			server->secmech.enc = server->primary_server->secmech.enc;
-			server->secmech.dec = server->primary_server->secmech.dec;
-		}
-	}
+	if (server->cipher_type && !rc)
+		rc = smb3_crypto_aead_allocate(server);
 neg_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -2928,6 +2921,7 @@ replay_again:
 		req->CreateContextsOffset = cpu_to_le32(
 			sizeof(struct smb2_create_req) +
 			iov[1].iov_len);
+		le32_add_cpu(&req->CreateContextsLength, iov[n_iov-1].iov_len);
 		pc_buf = iov[n_iov-1].iov_base;
 	}
 
@@ -2974,7 +2968,7 @@ replay_again:
 	/* Eventually save off posix specific response info and timestamps */
 
 err_free_rsp_buf:
-	free_rsp_buf(resp_buftype, rsp);
+	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	kfree(pc_buf);
 err_free_req:
 	cifs_small_buf_release(req);
@@ -4099,12 +4093,8 @@ static void cifs_renegotiate_iosize(struct TCP_Server_Info *server,
 		return;
 
 	spin_lock(&tcon->sb_list_lock);
-	list_for_each_entry(cifs_sb, &tcon->cifs_sb_list, tcon_sb_link) {
-		cifs_sb->ctx->rsize =
-			server->ops->negotiate_rsize(tcon, cifs_sb->ctx);
-		cifs_sb->ctx->wsize =
-			server->ops->negotiate_wsize(tcon, cifs_sb->ctx);
-	}
+	list_for_each_entry(cifs_sb, &tcon->cifs_sb_list, tcon_sb_link)
+		cifs_negotiate_iosize(server, cifs_sb->ctx, tcon);
 	spin_unlock(&tcon->sb_list_lock);
 }
 
diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h
index 764dca80c15c..f79a5165a7cc 100644
--- a/fs/smb/common/smb2pdu.h
+++ b/fs/smb/common/smb2pdu.h
@@ -1567,13 +1567,13 @@ struct reparse_nfs_data_buffer {
 	__u8	DataBuffer[];
 } __packed;
 
-/* For IO_REPARSE_TAG_LX_SYMLINK */
+/* For IO_REPARSE_TAG_LX_SYMLINK - see MS-FSCC 2.1.2.7 */
 struct reparse_wsl_symlink_data_buffer {
 	__le32	ReparseTag;
 	__le16	ReparseDataLength;
 	__u16	Reserved;
-	__le32	Flags;
-	__u8	PathBuffer[]; /* Variable Length UTF-8 string without nul-term */
+	__le32	Version; /* Always 2 */
+	__u8	Target[]; /* Variable Length UTF-8 string without nul-term */
 } __packed;
 
 struct validate_negotiate_info_req {
diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c
index 83caa3849749..b3d121052408 100644
--- a/fs/smb/server/auth.c
+++ b/fs/smb/server/auth.c
@@ -550,7 +550,19 @@ int ksmbd_krb5_authenticate(struct ksmbd_session *sess, char *in_blob,
 		retval = -ENOMEM;
 		goto out;
 	}
-	sess->user = user;
+
+	if (!sess->user) {
+		/* First successful authentication */
+		sess->user = user;
+	} else {
+		if (!ksmbd_compare_user(sess->user, user)) {
+			ksmbd_debug(AUTH, "different user tried to reuse session\n");
+			retval = -EPERM;
+			ksmbd_free_user(user);
+			goto out;
+		}
+		ksmbd_free_user(user);
+	}
 
 	memcpy(sess->sess_key, resp->payload, resp->session_key_len);
 	memcpy(out_blob, resp->payload + resp->session_key_len,
diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index c1f22c129111..83764c230e9d 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -39,8 +39,10 @@ void ksmbd_conn_free(struct ksmbd_conn *conn)
 	xa_destroy(&conn->sessions);
 	kvfree(conn->request_buf);
 	kfree(conn->preauth_info);
-	if (atomic_dec_and_test(&conn->refcnt))
+	if (atomic_dec_and_test(&conn->refcnt)) {
+		ksmbd_free_transport(conn->transport);
 		kfree(conn);
+	}
 }
 
 /**
diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c
index 3f45f28f6f0f..9dec4c2940bc 100644
--- a/fs/smb/server/mgmt/user_session.c
+++ b/fs/smb/server/mgmt/user_session.c
@@ -59,10 +59,12 @@ static void ksmbd_session_rpc_clear_list(struct ksmbd_session *sess)
 	struct ksmbd_session_rpc *entry;
 	long index;
 
+	down_write(&sess->rpc_lock);
 	xa_for_each(&sess->rpc_handle_list, index, entry) {
 		xa_erase(&sess->rpc_handle_list, index);
 		__session_rpc_close(sess, entry);
 	}
+	up_write(&sess->rpc_lock);
 
 	xa_destroy(&sess->rpc_handle_list);
 }
@@ -92,7 +94,7 @@ int ksmbd_session_rpc_open(struct ksmbd_session *sess, char *rpc_name)
 {
 	struct ksmbd_session_rpc *entry, *old;
 	struct ksmbd_rpc_command *resp;
-	int method;
+	int method, id;
 
 	method = __rpc_method(rpc_name);
 	if (!method)
@@ -102,26 +104,29 @@ int ksmbd_session_rpc_open(struct ksmbd_session *sess, char *rpc_name)
 	if (!entry)
 		return -ENOMEM;
 
+	down_read(&sess->rpc_lock);
 	entry->method = method;
-	entry->id = ksmbd_ipc_id_alloc();
-	if (entry->id < 0)
+	entry->id = id = ksmbd_ipc_id_alloc();
+	if (id < 0)
 		goto free_entry;
-	old = xa_store(&sess->rpc_handle_list, entry->id, entry, KSMBD_DEFAULT_GFP);
+	old = xa_store(&sess->rpc_handle_list, id, entry, KSMBD_DEFAULT_GFP);
 	if (xa_is_err(old))
 		goto free_id;
 
-	resp = ksmbd_rpc_open(sess, entry->id);
+	resp = ksmbd_rpc_open(sess, id);
 	if (!resp)
 		goto erase_xa;
 
+	up_read(&sess->rpc_lock);
 	kvfree(resp);
-	return entry->id;
+	return id;
 erase_xa:
 	xa_erase(&sess->rpc_handle_list, entry->id);
 free_id:
 	ksmbd_rpc_id_free(entry->id);
 free_entry:
 	kfree(entry);
+	up_read(&sess->rpc_lock);
 	return -EINVAL;
 }
 
@@ -129,9 +134,11 @@ void ksmbd_session_rpc_close(struct ksmbd_session *sess, int id)
 {
 	struct ksmbd_session_rpc *entry;
 
+	down_write(&sess->rpc_lock);
 	entry = xa_erase(&sess->rpc_handle_list, id);
 	if (entry)
 		__session_rpc_close(sess, entry);
+	up_write(&sess->rpc_lock);
 }
 
 int ksmbd_session_rpc_method(struct ksmbd_session *sess, int id)
@@ -439,6 +446,7 @@ static struct ksmbd_session *__session_create(int protocol)
 	sess->sequence_number = 1;
 	rwlock_init(&sess->tree_conns_lock);
 	atomic_set(&sess->refcnt, 2);
+	init_rwsem(&sess->rpc_lock);
 
 	ret = __init_smb2_session(sess);
 	if (ret)
diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h
index f21348381d59..c5749d6ec715 100644
--- a/fs/smb/server/mgmt/user_session.h
+++ b/fs/smb/server/mgmt/user_session.h
@@ -63,6 +63,7 @@ struct ksmbd_session {
 	rwlock_t			tree_conns_lock;
 
 	atomic_t			refcnt;
+	struct rw_semaphore		rpc_lock;
 };
 
 static inline int test_session_flag(struct ksmbd_session *sess, int bit)
diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index f103b1bd0400..03f606afad93 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -129,14 +129,6 @@ static void free_opinfo(struct oplock_info *opinfo)
 	kfree(opinfo);
 }
 
-static inline void opinfo_free_rcu(struct rcu_head *rcu_head)
-{
-	struct oplock_info *opinfo;
-
-	opinfo = container_of(rcu_head, struct oplock_info, rcu_head);
-	free_opinfo(opinfo);
-}
-
 struct oplock_info *opinfo_get(struct ksmbd_file *fp)
 {
 	struct oplock_info *opinfo;
@@ -157,8 +149,8 @@ static struct oplock_info *opinfo_get_list(struct ksmbd_inode *ci)
 	if (list_empty(&ci->m_op_list))
 		return NULL;
 
-	rcu_read_lock();
-	opinfo = list_first_or_null_rcu(&ci->m_op_list, struct oplock_info,
+	down_read(&ci->m_lock);
+	opinfo = list_first_entry(&ci->m_op_list, struct oplock_info,
 					op_entry);
 	if (opinfo) {
 		if (opinfo->conn == NULL ||
@@ -171,8 +163,7 @@ static struct oplock_info *opinfo_get_list(struct ksmbd_inode *ci)
 			}
 		}
 	}
-
-	rcu_read_unlock();
+	up_read(&ci->m_lock);
 
 	return opinfo;
 }
@@ -185,7 +176,7 @@ void opinfo_put(struct oplock_info *opinfo)
 	if (!atomic_dec_and_test(&opinfo->refcount))
 		return;
 
-	call_rcu(&opinfo->rcu_head, opinfo_free_rcu);
+	free_opinfo(opinfo);
 }
 
 static void opinfo_add(struct oplock_info *opinfo)
@@ -193,7 +184,7 @@ static void opinfo_add(struct oplock_info *opinfo)
 	struct ksmbd_inode *ci = opinfo->o_fp->f_ci;
 
 	down_write(&ci->m_lock);
-	list_add_rcu(&opinfo->op_entry, &ci->m_op_list);
+	list_add(&opinfo->op_entry, &ci->m_op_list);
 	up_write(&ci->m_lock);
 }
 
@@ -207,7 +198,7 @@ static void opinfo_del(struct oplock_info *opinfo)
 		write_unlock(&lease_list_lock);
 	}
 	down_write(&ci->m_lock);
-	list_del_rcu(&opinfo->op_entry);
+	list_del(&opinfo->op_entry);
 	up_write(&ci->m_lock);
 }
 
@@ -1347,8 +1338,8 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp,
 	ci = fp->f_ci;
 	op = opinfo_get(fp);
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(brk_op, &ci->m_op_list, op_entry) {
+	down_read(&ci->m_lock);
+	list_for_each_entry(brk_op, &ci->m_op_list, op_entry) {
 		if (brk_op->conn == NULL)
 			continue;
 
@@ -1358,7 +1349,6 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp,
 		if (ksmbd_conn_releasing(brk_op->conn))
 			continue;
 
-		rcu_read_unlock();
 		if (brk_op->is_lease && (brk_op->o_lease->state &
 		    (~(SMB2_LEASE_READ_CACHING_LE |
 				SMB2_LEASE_HANDLE_CACHING_LE)))) {
@@ -1388,9 +1378,8 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp,
 		oplock_break(brk_op, SMB2_OPLOCK_LEVEL_NONE, NULL);
 next:
 		opinfo_put(brk_op);
-		rcu_read_lock();
 	}
-	rcu_read_unlock();
+	up_read(&ci->m_lock);
 
 	if (op)
 		opinfo_put(op);
@@ -1507,7 +1496,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req)
 
 		if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) <
 		    sizeof(struct create_lease_v2) - 4)
-			return NULL;
+			goto err_out;
 
 		memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
 		lreq->req_state = lc->lcontext.LeaseState;
@@ -1523,7 +1512,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req)
 
 		if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) <
 		    sizeof(struct create_lease))
-			return NULL;
+			goto err_out;
 
 		memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
 		lreq->req_state = lc->lcontext.LeaseState;
@@ -1532,6 +1521,9 @@ struct lease_ctx_info *parse_lease_state(void *open_req)
 		lreq->version = 1;
 	}
 	return lreq;
+err_out:
+	kfree(lreq);
+	return NULL;
 }
 
 /**
diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h
index 3f64f0787263..9a56eaadd0dd 100644
--- a/fs/smb/server/oplock.h
+++ b/fs/smb/server/oplock.h
@@ -71,7 +71,6 @@ struct oplock_info {
 	struct list_head        lease_entry;
 	wait_queue_head_t oplock_q; /* Other server threads */
 	wait_queue_head_t oplock_brk; /* oplock breaking wait */
-	struct rcu_head		rcu_head;
 };
 
 struct lease_break_info {
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index d24d95d15d87..f2a2be8467c6 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -633,6 +633,11 @@ smb2_get_name(const char *src, const int maxlen, struct nls_table *local_nls)
 		return name;
 	}
 
+	if (*name == '\0') {
+		kfree(name);
+		return ERR_PTR(-EINVAL);
+	}
+
 	if (*name == '\\') {
 		pr_err("not allow directory name included leading slash\n");
 		kfree(name);
@@ -1445,7 +1450,7 @@ static int ntlm_authenticate(struct ksmbd_work *work,
 {
 	struct ksmbd_conn *conn = work->conn;
 	struct ksmbd_session *sess = work->sess;
-	struct channel *chann = NULL;
+	struct channel *chann = NULL, *old;
 	struct ksmbd_user *user;
 	u64 prev_id;
 	int sz, rc;
@@ -1557,7 +1562,12 @@ binding_session:
 				return -ENOMEM;
 
 			chann->conn = conn;
-			xa_store(&sess->ksmbd_chann_list, (long)conn, chann, KSMBD_DEFAULT_GFP);
+			old = xa_store(&sess->ksmbd_chann_list, (long)conn, chann,
+					KSMBD_DEFAULT_GFP);
+			if (xa_is_err(old)) {
+				kfree(chann);
+				return xa_err(old);
+			}
 		}
 	}
 
@@ -1602,9 +1612,6 @@ static int krb5_authenticate(struct ksmbd_work *work,
 	if (prev_sess_id && prev_sess_id != sess->id)
 		destroy_previous_session(conn, sess->user, prev_sess_id);
 
-	if (sess->state == SMB2_SESSION_VALID)
-		ksmbd_free_user(sess->user);
-
 	retval = ksmbd_krb5_authenticate(sess, in_blob, in_len,
 					 out_blob, &out_len);
 	if (retval) {
@@ -2247,10 +2254,6 @@ int smb2_session_logoff(struct ksmbd_work *work)
 	sess->state = SMB2_SESSION_EXPIRED;
 	up_write(&conn->session_lock);
 
-	if (sess->user) {
-		ksmbd_free_user(sess->user);
-		sess->user = NULL;
-	}
 	ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_SETUP);
 
 	rsp->StructureSize = cpu_to_le16(4);
diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h
index a3d8a905b07e..d742ba754348 100644
--- a/fs/smb/server/smb_common.h
+++ b/fs/smb/server/smb_common.h
@@ -72,6 +72,8 @@
 #define FILE_SUPPORTS_ENCRYPTION	0x00020000
 #define FILE_SUPPORTS_OBJECT_IDS	0x00010000
 #define FILE_VOLUME_IS_COMPRESSED	0x00008000
+#define FILE_SUPPORTS_POSIX_UNLINK_RENAME 0x00000400
+#define FILE_RETURNS_CLEANUP_RESULT_INFO  0x00000200
 #define FILE_SUPPORTS_REMOTE_STORAGE	0x00000100
 #define FILE_SUPPORTS_REPARSE_POINTS	0x00000080
 #define FILE_SUPPORTS_SPARSE_FILES	0x00000040
diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c
index 3f185ae60dc5..2a3e2b0ce557 100644
--- a/fs/smb/server/transport_ipc.c
+++ b/fs/smb/server/transport_ipc.c
@@ -310,7 +310,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req)
 	server_conf.signing = req->signing;
 	server_conf.tcp_port = req->tcp_port;
 	server_conf.ipc_timeout = req->ipc_timeout * HZ;
-	server_conf.deadtime = req->deadtime * SMB_ECHO_INTERVAL;
+	if (check_mul_overflow(req->deadtime, SMB_ECHO_INTERVAL,
+					&server_conf.deadtime)) {
+		ret = -EINVAL;
+		goto out;
+	}
 	server_conf.share_fake_fscaps = req->share_fake_fscaps;
 	ksmbd_init_domain(req->sub_auth);
 
@@ -337,6 +341,7 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req)
 	server_conf.bind_interfaces_only = req->bind_interfaces_only;
 	ret |= ksmbd_tcp_set_interfaces(KSMBD_STARTUP_CONFIG_INTERFACES(req),
 					req->ifc_list_sz);
+out:
 	if (ret) {
 		pr_err("Server configuration error: %s %s %s\n",
 		       req->netbios_name, req->server_string,
diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c
index 7f38a3c3f5bd..abedf510899a 100644
--- a/fs/smb/server/transport_tcp.c
+++ b/fs/smb/server/transport_tcp.c
@@ -93,17 +93,21 @@ static struct tcp_transport *alloc_transport(struct socket *client_sk)
 	return t;
 }
 
-static void free_transport(struct tcp_transport *t)
+void ksmbd_free_transport(struct ksmbd_transport *kt)
 {
-	kernel_sock_shutdown(t->sock, SHUT_RDWR);
-	sock_release(t->sock);
-	t->sock = NULL;
+	struct tcp_transport *t = TCP_TRANS(kt);
 
-	ksmbd_conn_free(KSMBD_TRANS(t)->conn);
+	sock_release(t->sock);
 	kfree(t->iov);
 	kfree(t);
 }
 
+static void free_transport(struct tcp_transport *t)
+{
+	kernel_sock_shutdown(t->sock, SHUT_RDWR);
+	ksmbd_conn_free(KSMBD_TRANS(t)->conn);
+}
+
 /**
  * kvec_array_init() - initialize a IO vector segment
  * @new:	IO vector to be initialized
diff --git a/fs/smb/server/transport_tcp.h b/fs/smb/server/transport_tcp.h
index 8c9aa624cfe3..1e51675ee1b2 100644
--- a/fs/smb/server/transport_tcp.h
+++ b/fs/smb/server/transport_tcp.h
@@ -8,6 +8,7 @@
 
 int ksmbd_tcp_set_interfaces(char *ifc_list, int ifc_list_sz);
 struct interface *ksmbd_find_netdev_name_iface_list(char *netdev_name);
+void ksmbd_free_transport(struct ksmbd_transport *kt);
 int ksmbd_tcp_init(void);
 void ksmbd_tcp_destroy(void);
 
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index 8554aa5a1059..482eba0f4dc1 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -426,6 +426,13 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos,
 		goto out;
 	}
 
+	if (v_len <= *pos) {
+		pr_err("stream write position %lld is out of bounds (stream length: %zd)\n",
+				*pos, v_len);
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (v_len < size) {
 		wbuf = kvzalloc(size, KSMBD_DEFAULT_GFP);
 		if (!wbuf) {
@@ -479,7 +486,8 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp,
 	int err = 0;
 
 	if (work->conn->connection_type) {
-		if (!(fp->daccess & (FILE_WRITE_DATA_LE | FILE_APPEND_DATA_LE))) {
+		if (!(fp->daccess & (FILE_WRITE_DATA_LE | FILE_APPEND_DATA_LE)) ||
+		    S_ISDIR(file_inode(fp->filp)->i_mode)) {
 			pr_err("no right to write(%pD)\n", fp->filp);
 			err = -EACCES;
 			goto out;
diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c
index 8d1f30dcba7e..dfed6fce8904 100644
--- a/fs/smb/server/vfs_cache.c
+++ b/fs/smb/server/vfs_cache.c
@@ -661,21 +661,40 @@ __close_file_table_ids(struct ksmbd_file_table *ft,
 		       bool (*skip)(struct ksmbd_tree_connect *tcon,
 				    struct ksmbd_file *fp))
 {
-	unsigned int			id;
-	struct ksmbd_file		*fp;
-	int				num = 0;
+	struct ksmbd_file *fp;
+	unsigned int id = 0;
+	int num = 0;
+
+	while (1) {
+		write_lock(&ft->lock);
+		fp = idr_get_next(ft->idr, &id);
+		if (!fp) {
+			write_unlock(&ft->lock);
+			break;
+		}
 
-	idr_for_each_entry(ft->idr, fp, id) {
-		if (skip(tcon, fp))
+		if (skip(tcon, fp) ||
+		    !atomic_dec_and_test(&fp->refcount)) {
+			id++;
+			write_unlock(&ft->lock);
 			continue;
+		}
 
 		set_close_state_blocked_works(fp);
+		idr_remove(ft->idr, fp->volatile_id);
+		fp->volatile_id = KSMBD_NO_FID;
+		write_unlock(&ft->lock);
+
+		down_write(&fp->f_ci->m_lock);
+		list_del_init(&fp->node);
+		up_write(&fp->f_ci->m_lock);
 
-		if (!atomic_dec_and_test(&fp->refcount))
-			continue;
 		__ksmbd_close_fd(ft, fp);
+
 		num++;
+		id++;
 	}
+
 	return num;
 }
 
@@ -713,12 +732,8 @@ static bool tree_conn_fd_check(struct ksmbd_tree_connect *tcon,
 
 static bool ksmbd_durable_scavenger_alive(void)
 {
-	mutex_lock(&durable_scavenger_lock);
-	if (!durable_scavenger_running) {
-		mutex_unlock(&durable_scavenger_lock);
+	if (!durable_scavenger_running)
 		return false;
-	}
-	mutex_unlock(&durable_scavenger_lock);
 
 	if (kthread_should_stop())
 		return false;
@@ -799,9 +814,7 @@ static int ksmbd_durable_scavenger(void *dummy)
 			break;
 	}
 
-	mutex_lock(&durable_scavenger_lock);
 	durable_scavenger_running = false;
-	mutex_unlock(&durable_scavenger_lock);
 
 	module_put(THIS_MODULE);
 
diff --git a/fs/splice.c b/fs/splice.c
index 90d464241f15..4d6df083e0c0 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -45,7 +45,7 @@
  * here if set to avoid blocking other users of this pipe if splice is
  * being done on it.
  */
-static noinline void noinline pipe_clear_nowait(struct file *file)
+static noinline void pipe_clear_nowait(struct file *file)
 {
 	fmode_t fmode = READ_ONCE(file->f_mode);
 
diff --git a/fs/stat.c b/fs/stat.c
index f13308bfdc98..3d9222807214 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -204,12 +204,25 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
 				  STATX_ATTR_DAX);
 
 	idmap = mnt_idmap(path->mnt);
-	if (inode->i_op->getattr)
-		return inode->i_op->getattr(idmap, path, stat,
-					    request_mask,
-					    query_flags);
+	if (inode->i_op->getattr) {
+		int ret;
+
+		ret = inode->i_op->getattr(idmap, path, stat, request_mask,
+				query_flags);
+		if (ret)
+			return ret;
+	} else {
+		generic_fillattr(idmap, request_mask, inode, stat);
+	}
+
+	/*
+	 * If this is a block device inode, override the filesystem attributes
+	 * with the block device specific parameters that need to be obtained
+	 * from the bdev backing inode.
+	 */
+	if (S_ISBLK(stat->mode))
+		bdev_statx(path, stat, request_mask);
 
-	generic_fillattr(idmap, request_mask, inode, stat);
 	return 0;
 }
 EXPORT_SYMBOL(vfs_getattr_nosec);
@@ -295,15 +308,6 @@ static int vfs_statx_path(struct path *path, int flags, struct kstat *stat,
 	if (path_mounted(path))
 		stat->attributes |= STATX_ATTR_MOUNT_ROOT;
 	stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT;
-
-	/*
-	 * If this is a block device inode, override the filesystem
-	 * attributes with the block device specific parameters that need to be
-	 * obtained from the bdev backing inode.
-	 */
-	if (S_ISBLK(stat->mode))
-		bdev_statx(path, stat, request_mask);
-
 	return 0;
 }
 
diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c
index 4f33a4a48886..b4071c9cf8c9 100644
--- a/fs/udf/truncate.c
+++ b/fs/udf/truncate.c
@@ -115,7 +115,7 @@ void udf_truncate_tail_extent(struct inode *inode)
 	}
 	/* This inode entry is in-memory only and thus we don't have to mark
 	 * the inode dirty */
-	if (ret == 0)
+	if (ret >= 0)
 		iinfo->i_lenExtents = inode->i_size;
 	brelse(epos.bh);
 }
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index d80f94346199..22f4bf956ba1 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 	user_uffdio_copy = (struct uffdio_copy __user *) arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_copy, user_uffdio_copy,
@@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 	user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
@@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
 	user_uffdio_continue = (struct uffdio_continue __user *)arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_continue, user_uffdio_continue,
@@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long
 	user_uffdio_poison = (struct uffdio_poison __user *)arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_poison->updated)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_poison, user_uffdio_poison,
@@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
 
 	user_uffdio_move = (struct uffdio_move __user *) arg;
 
-	if (atomic_read(&ctx->mmap_changing))
-		return -EAGAIN;
+	ret = -EAGAIN;
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_move->move)))
+			return -EFAULT;
+		goto out;
+	}
 
 	if (copy_from_user(&uffdio_move, user_uffdio_move,
 			   /* don't copy "move" last field */
diff --git a/fs/xattr.c b/fs/xattr.c
index 02bee149ad96..8ec5b0204bfd 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -703,7 +703,7 @@ static int path_setxattrat(int dfd, const char __user *pathname,
 		return error;
 
 	filename = getname_maybe_null(pathname, at_flags);
-	if (!filename) {
+	if (!filename && dfd >= 0) {
 		CLASS(fd, f)(dfd);
 		if (fd_empty(f))
 			error = -EBADF;
@@ -847,7 +847,7 @@ static ssize_t path_getxattrat(int dfd, const char __user *pathname,
 		return error;
 
 	filename = getname_maybe_null(pathname, at_flags);
-	if (!filename) {
+	if (!filename && dfd >= 0) {
 		CLASS(fd, f)(dfd);
 		if (fd_empty(f))
 			return -EBADF;
@@ -1428,6 +1428,15 @@ static bool xattr_is_trusted(const char *name)
 	return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
 }
 
+static bool xattr_is_maclabel(const char *name)
+{
+	const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
+
+	return !strncmp(name, XATTR_SECURITY_PREFIX,
+			XATTR_SECURITY_PREFIX_LEN) &&
+		security_ismaclabel(suffix);
+}
+
 /**
  * simple_xattr_list - list all xattr objects
  * @inode: inode from which to get the xattrs
@@ -1460,6 +1469,17 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 	if (err)
 		return err;
 
+	err = security_inode_listsecurity(inode, buffer, remaining_size);
+	if (err < 0)
+		return err;
+
+	if (buffer) {
+		if (remaining_size < err)
+			return -ERANGE;
+		buffer += err;
+	}
+	remaining_size -= err;
+
 	read_lock(&xattrs->lock);
 	for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) {
 		xattr = rb_entry(rbp, struct simple_xattr, rb_node);
@@ -1468,6 +1488,10 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 		if (!trusted && xattr_is_trusted(xattr->name))
 			continue;
 
+		/* skip MAC labels; these are provided by LSM above */
+		if (xattr_is_maclabel(xattr->name))
+			continue;
+
 		err = xattr_list_one(&buffer, &remaining_size, xattr->name);
 		if (err)
 			break;
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 8e7f1b324b3b..1a2b3f06fa71 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -105,6 +105,7 @@ xfs_buf_free(
 {
 	unsigned int		size = BBTOB(bp->b_length);
 
+	might_sleep();
 	trace_xfs_buf_free(bp, _RET_IP_);
 
 	ASSERT(list_empty(&bp->b_lru));
diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c
index b4ffd80b7cb6..dcbfa274e06d 100644
--- a/fs/xfs/xfs_buf_mem.c
+++ b/fs/xfs/xfs_buf_mem.c
@@ -165,7 +165,7 @@ xmbuf_map_backing_mem(
 	folio_set_dirty(folio);
 	folio_unlock(folio);
 
-	bp->b_addr = folio_address(folio);
+	bp->b_addr = folio_address(folio) + offset_in_folio(folio, pos);
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index edbc521870a1..b4e32f0860b7 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1186,9 +1186,8 @@ xfs_qm_dqflush_done(
 	if (test_bit(XFS_LI_IN_AIL, &lip->li_flags) &&
 	    (lip->li_lsn == qlip->qli_flush_lsn ||
 	     test_bit(XFS_LI_FAILED, &lip->li_flags))) {
-
 		spin_lock(&ailp->ail_lock);
-		xfs_clear_li_failed(lip);
+		clear_bit(XFS_LI_FAILED, &lip->li_flags);
 		if (lip->li_lsn == qlip->qli_flush_lsn) {
 			/* xfs_ail_update_finish() drops the AIL lock */
 			tail_lsn = xfs_ail_delete_one(ailp, lip);
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index a4bc1642fe56..414b27a86458 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -876,6 +876,7 @@ xfs_getfsmap_rtdev_rmapbt(
 	const struct xfs_fsmap		*keys,
 	struct xfs_getfsmap_info	*info)
 {
+	struct xfs_fsmap		key0 = *keys; /* struct copy */
 	struct xfs_mount		*mp = tp->t_mountp;
 	struct xfs_rtgroup		*rtg = NULL;
 	struct xfs_btree_cur		*bt_cur = NULL;
@@ -887,32 +888,46 @@ xfs_getfsmap_rtdev_rmapbt(
 	int				error = 0;
 
 	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart + mp->m_sb.sb_rblocks);
-	if (keys[0].fmr_physical >= eofs)
+	if (key0.fmr_physical >= eofs)
 		return 0;
 
+	/*
+	 * On zoned filesystems with an internal rt volume, the volume comes
+	 * immediately after the end of the data volume.  However, the
+	 * xfs_rtblock_t address space is relative to the start of the data
+	 * device, which means that the first @rtstart fsblocks do not actually
+	 * point anywhere.  If a fsmap query comes in with the low key starting
+	 * below @rtstart, report it as "owned by filesystem".
+	 */
 	rtstart_daddr = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart);
-	if (keys[0].fmr_physical < rtstart_daddr) {
+	if (xfs_has_zoned(mp) && key0.fmr_physical < rtstart_daddr) {
 		struct xfs_fsmap_irec		frec = {
 			.owner			= XFS_RMAP_OWN_FS,
 			.len_daddr		= rtstart_daddr,
 		};
 
-		/* Adjust the low key if we are continuing from where we left off. */
-		if (keys[0].fmr_length > 0) {
-			info->low_daddr = keys[0].fmr_physical + keys[0].fmr_length;
-			return 0;
+		/*
+		 * Adjust the start of the query range if we're picking up from
+		 * a previous round, and only emit the record if we haven't
+		 * already gone past.
+		 */
+		key0.fmr_physical += key0.fmr_length;
+		if (key0.fmr_physical < rtstart_daddr) {
+			error = xfs_getfsmap_helper(tp, info, &frec);
+			if (error)
+				return error;
+
+			key0.fmr_physical = rtstart_daddr;
 		}
 
-		/* Fabricate an rmap entry for space occupied by the data dev */
-		error = xfs_getfsmap_helper(tp, info, &frec);
-		if (error)
-			return error;
+		/* Zero the other fields to avoid further adjustments. */
+		key0.fmr_owner = 0;
+		key0.fmr_offset = 0;
+		key0.fmr_length = 0;
 	}
 
-	start_rtb = xfs_daddr_to_rtb(mp, rtstart_daddr + keys[0].fmr_physical);
-	end_rtb = xfs_daddr_to_rtb(mp, rtstart_daddr +
-			min(eofs - 1, keys[1].fmr_physical));
-
+	start_rtb = xfs_daddr_to_rtb(mp, key0.fmr_physical);
+	end_rtb = xfs_daddr_to_rtb(mp, min(eofs - 1, keys[1].fmr_physical));
 	info->missing_owner = XFS_FMR_OWN_FREE;
 
 	/*
@@ -920,12 +935,12 @@ xfs_getfsmap_rtdev_rmapbt(
 	 * low to the fsmap low key and max out the high key to the end
 	 * of the rtgroup.
 	 */
-	info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
-	error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
+	info->low.rm_offset = XFS_BB_TO_FSBT(mp, key0.fmr_offset);
+	error = xfs_fsmap_owner_to_rmap(&info->low, &key0);
 	if (error)
 		return error;
-	info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, keys[0].fmr_length);
-	xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
+	info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, key0.fmr_length);
+	xfs_getfsmap_set_irec_flags(&info->low, &key0);
 
 	/* Adjust the low key if we are continuing from where we left off. */
 	if (info->low.rm_blockcount == 0) {
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 40fc1bf900af..c6cb0b6b9e46 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -1089,13 +1089,7 @@ xfs_iflush_abort(
 	 * state. Whilst the inode is in the AIL, it should have a valid buffer
 	 * pointer for push operations to access - it is only safe to remove the
 	 * inode from the buffer once it has been removed from the AIL.
-	 *
-	 * We also clear the failed bit before removing the item from the AIL
-	 * as xfs_trans_ail_delete()->xfs_clear_li_failed() will release buffer
-	 * references the inode item owns and needs to hold until we've fully
-	 * aborted the inode log item and detached it from the buffer.
 	 */
-	clear_bit(XFS_LI_FAILED, &iip->ili_item.li_flags);
 	xfs_trans_ail_delete(&iip->ili_item, 0);
 
 	/*
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 6493bdb57351..980aabc49512 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -2888,7 +2888,7 @@ xlog_force_and_check_iclog(
  *
  *	1. the current iclog is active and has no data; the previous iclog
  *		is in the active or dirty state.
- *	2. the current iclog is drity, and the previous iclog is in the
+ *	2. the current iclog is dirty, and the previous iclog is in the
  *		active or dirty state.
  *
  * We may sleep if:
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 799b84220ebb..e5192c12e7ac 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -229,6 +229,7 @@ typedef struct xfs_mount {
 	bool			m_finobt_nores; /* no per-AG finobt resv. */
 	bool			m_update_sb;	/* sb needs update in mount */
 	unsigned int		m_max_open_zones;
+	unsigned int		m_zonegc_low_space;
 
 	/*
 	 * Bitsets of per-fs metadata that have been checked and/or are sick.
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index b2dd0c0bf509..4a11ddccc563 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1149,7 +1149,7 @@ xfs_init_percpu_counters(
 	return 0;
 
 free_freecounters:
-	while (--i > 0)
+	while (--i >= 0)
 		percpu_counter_destroy(&mp->m_free[i].count);
 	percpu_counter_destroy(&mp->m_delalloc_rtextents);
 free_delalloc:
@@ -2114,6 +2114,21 @@ xfs_fs_reconfigure(
 	if (error)
 		return error;
 
+	/* attr2 -> noattr2 */
+	if (xfs_has_noattr2(new_mp)) {
+		if (xfs_has_crc(mp)) {
+			xfs_warn(mp,
+			"attr2 is always enabled for a V5 filesystem - can't be changed.");
+			return -EINVAL;
+		}
+		mp->m_features &= ~XFS_FEAT_ATTR2;
+		mp->m_features |= XFS_FEAT_NOATTR2;
+	} else if (xfs_has_attr2(new_mp)) {
+		/* noattr2 -> attr2 */
+		mp->m_features &= ~XFS_FEAT_NOATTR2;
+		mp->m_features |= XFS_FEAT_ATTR2;
+	}
+
 	/* inode32 -> inode64 */
 	if (xfs_has_small_inums(mp) && !xfs_has_small_inums(new_mp)) {
 		mp->m_features &= ~XFS_FEAT_SMALL_INUMS;
@@ -2126,6 +2141,17 @@ xfs_fs_reconfigure(
 		mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount);
 	}
 
+	/*
+	 * Now that mp has been modified according to the remount options, we
+	 * do a final option validation with xfs_finish_flags() just like it is
+	 * just like it is done during mount. We cannot use
+	 * done during mount. We cannot use xfs_finish_flags() on new_mp as it
+	 * contains only the user given options.
+	 */
+	error = xfs_finish_flags(mp);
+	if (error)
+		return error;
+
 	/* ro -> rw */
 	if (xfs_is_readonly(mp) && !(flags & SB_RDONLY)) {
 		error = xfs_remount_rw(mp);
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index b7e82d85f043..7a5c5ef2db92 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -718,8 +718,40 @@ max_open_zones_show(
 }
 XFS_SYSFS_ATTR_RO(max_open_zones);
 
+static ssize_t
+zonegc_low_space_store(
+	struct kobject		*kobj,
+	const char		*buf,
+	size_t			count)
+{
+	int			ret;
+	unsigned int		val;
+
+	ret = kstrtouint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val > 100)
+		return -EINVAL;
+
+	zoned_to_mp(kobj)->m_zonegc_low_space = val;
+
+	return count;
+}
+
+static ssize_t
+zonegc_low_space_show(
+	struct kobject		*kobj,
+	char			*buf)
+{
+	return sysfs_emit(buf, "%u\n",
+			zoned_to_mp(kobj)->m_zonegc_low_space);
+}
+XFS_SYSFS_ATTR_RW(zonegc_low_space);
+
 static struct attribute *xfs_zoned_attrs[] = {
 	ATTR_LIST(max_open_zones),
+	ATTR_LIST(zonegc_low_space),
 	NULL,
 };
 ATTRIBUTE_GROUPS(xfs_zoned);
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 0fcb1828e598..67c328d23e4a 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -315,7 +315,7 @@ xfs_ail_splice(
 }
 
 /*
- * Delete the given item from the AIL.  Return a pointer to the item.
+ * Delete the given item from the AIL.
  */
 static void
 xfs_ail_delete(
@@ -777,26 +777,28 @@ xfs_ail_update_finish(
 }
 
 /*
- * xfs_trans_ail_update - bulk AIL insertion operation.
+ * xfs_trans_ail_update_bulk - bulk AIL insertion operation.
  *
- * @xfs_trans_ail_update takes an array of log items that all need to be
+ * @xfs_trans_ail_update_bulk takes an array of log items that all need to be
  * positioned at the same LSN in the AIL. If an item is not in the AIL, it will
- * be added.  Otherwise, it will be repositioned  by removing it and re-adding
- * it to the AIL. If we move the first item in the AIL, update the log tail to
- * match the new minimum LSN in the AIL.
+ * be added. Otherwise, it will be repositioned by removing it and re-adding
+ * it to the AIL.
  *
- * This function takes the AIL lock once to execute the update operations on
- * all the items in the array, and as such should not be called with the AIL
- * lock held. As a result, once we have the AIL lock, we need to check each log
- * item LSN to confirm it needs to be moved forward in the AIL.
+ * If we move the first item in the AIL, update the log tail to match the new
+ * minimum LSN in the AIL.
  *
- * To optimise the insert operation, we delete all the items from the AIL in
- * the first pass, moving them into a temporary list, then splice the temporary
- * list into the correct position in the AIL. This avoids needing to do an
- * insert operation on every item.
+ * This function should be called with the AIL lock held.
  *
- * This function must be called with the AIL lock held.  The lock is dropped
- * before returning.
+ * To optimise the insert operation, we add all items to a temporary list, then
+ * splice this list into the correct position in the AIL.
+ *
+ * Items that are already in the AIL are first deleted from their current
+ * location before being added to the temporary list.
+ *
+ * This avoids needing to do an insert operation on every item.
+ *
+ * The AIL lock is dropped by xfs_ail_update_finish() before returning to
+ * the caller.
  */
 void
 xfs_trans_ail_update_bulk(
@@ -909,10 +911,9 @@ xfs_trans_ail_delete(
 		return;
 	}
 
-	/* xfs_ail_update_finish() drops the AIL lock */
-	xfs_clear_li_failed(lip);
+	clear_bit(XFS_LI_FAILED, &lip->li_flags);
 	tail_lsn = xfs_ail_delete_one(ailp, lip);
-	xfs_ail_update_finish(ailp, tail_lsn);
+	xfs_ail_update_finish(ailp, tail_lsn);	/* drops the AIL lock */
 }
 
 int
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index bd841df93021..f945f0450b16 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -167,32 +167,4 @@ xfs_trans_ail_copy_lsn(
 }
 #endif
 
-static inline void
-xfs_clear_li_failed(
-	struct xfs_log_item	*lip)
-{
-	struct xfs_buf	*bp = lip->li_buf;
-
-	ASSERT(test_bit(XFS_LI_IN_AIL, &lip->li_flags));
-	lockdep_assert_held(&lip->li_ailp->ail_lock);
-
-	if (test_and_clear_bit(XFS_LI_FAILED, &lip->li_flags)) {
-		lip->li_buf = NULL;
-		xfs_buf_rele(bp);
-	}
-}
-
-static inline void
-xfs_set_li_failed(
-	struct xfs_log_item	*lip,
-	struct xfs_buf		*bp)
-{
-	lockdep_assert_held(&lip->li_ailp->ail_lock);
-
-	if (!test_and_set_bit(XFS_LI_FAILED, &lip->li_flags)) {
-		xfs_buf_hold(bp);
-		lip->li_buf = bp;
-	}
-}
-
 #endif	/* __XFS_TRANS_PRIV_H__ */
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 52af234936a2..d509e49b2aaa 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -1201,6 +1201,13 @@ xfs_mount_zones(
 	xfs_set_freecounter(mp, XC_FREE_RTEXTENTS,
 			iz.available + iz.reclaimable);
 
+	/*
+	 * The user may configure GC to free up a percentage of unused blocks.
+	 * By default this is 0. GC will always trigger at the minimum level
+	 * for keeping max_open_zones available for data placement.
+	 */
+	mp->m_zonegc_low_space = 0;
+
 	error = xfs_zone_gc_mount(mp);
 	if (error)
 		goto out_free_zone_info;
diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c
index c5136ea9bb1d..d613a4094db6 100644
--- a/fs/xfs/xfs_zone_gc.c
+++ b/fs/xfs/xfs_zone_gc.c
@@ -162,18 +162,36 @@ struct xfs_zone_gc_data {
 
 /*
  * We aim to keep enough zones free in stock to fully use the open zone limit
- * for data placement purposes.
+ * for data placement purposes. Additionally, the m_zonegc_low_space tunable
+ * can be set to make sure a fraction of the unused blocks are available for
+ * writing.
  */
 bool
 xfs_zoned_need_gc(
 	struct xfs_mount	*mp)
 {
+	s64			available, free, threshold;
+	s32			remainder;
+
 	if (!xfs_group_marked(mp, XG_TYPE_RTG, XFS_RTG_RECLAIMABLE))
 		return false;
-	if (xfs_estimate_freecounter(mp, XC_FREE_RTAVAILABLE) <
+
+	available = xfs_estimate_freecounter(mp, XC_FREE_RTAVAILABLE);
+
+	if (available <
 	    mp->m_groups[XG_TYPE_RTG].blocks *
 	    (mp->m_max_open_zones - XFS_OPEN_GC_ZONES))
 		return true;
+
+	free = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS);
+
+	threshold = div_s64_rem(free, 100, &remainder);
+	threshold = threshold * mp->m_zonegc_low_space +
+		    remainder * div_s64(mp->m_zonegc_low_space, 100);
+
+	if (available < threshold)
+		return true;
+
 	return false;
 }
 
@@ -789,7 +807,8 @@ xfs_zone_gc_write_chunk(
 {
 	struct xfs_zone_gc_data	*data = chunk->data;
 	struct xfs_mount	*mp = chunk->ip->i_mount;
-	unsigned int		folio_offset = chunk->bio.bi_io_vec->bv_offset;
+	phys_addr_t		bvec_paddr =
+		bvec_phys(bio_first_bvec_all(&chunk->bio));
 	struct xfs_gc_bio	*split_chunk;
 
 	if (chunk->bio.bi_status)
@@ -804,7 +823,7 @@ xfs_zone_gc_write_chunk(
 
 	bio_reset(&chunk->bio, mp->m_rtdev_targp->bt_bdev, REQ_OP_WRITE);
 	bio_add_folio_nofail(&chunk->bio, chunk->scratch->folio, chunk->len,
-			folio_offset);
+			offset_in_folio(chunk->scratch->folio, bvec_paddr));
 
 	while ((split_chunk = xfs_zone_gc_split_write(data, chunk)))
 		xfs_zone_gc_submit_write(data, split_chunk);
diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index 451f6276da49..2fc89704be17 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -66,7 +66,7 @@
  ******************************************************************************/
 
 struct acpi_table_header {
-	char signature[ACPI_NAMESEG_SIZE];	/* ASCII table signature */
+	char signature[ACPI_NAMESEG_SIZE] __nonstring;	/* ASCII table signature */
 	u32 length;		/* Length of table in bytes, including this header */
 	u8 revision;		/* ACPI Specification minor version number */
 	u8 checksum;		/* To make sum of entire table == 0 */
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 2aa83ee0ec98..a67988316d06 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -10,6 +10,7 @@
 
 #include <linux/atomic.h>
 #include <linux/crypto.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 
 /* Set this bit for virtual address instead of SG list. */
@@ -581,7 +582,10 @@ static inline struct ahash_request *ahash_request_alloc_noprof(
  * ahash_request_free() - zeroize and free the request data structure
  * @req: request data structure cipher handle to be freed
  */
-void ahash_request_free(struct ahash_request *req);
+static inline void ahash_request_free(struct ahash_request *req)
+{
+	kfree_sensitive(req);
+}
 
 static inline struct ahash_request *ahash_request_cast(
 	struct crypto_async_request *req)
diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 485e22cf517e..052ac7924af3 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -249,7 +249,7 @@ static inline struct crypto_shash *__crypto_shash_cast(struct crypto_tfm *tfm)
 
 static inline bool ahash_request_chained(struct ahash_request *req)
 {
-	return crypto_request_chained(&req->base);
+	return false;
 }
 
 static inline bool ahash_request_isvirt(struct ahash_request *req)
diff --git a/include/crypto/krb5.h b/include/crypto/krb5.h
index 62d998e62f47..71dd38f59be1 100644
--- a/include/crypto/krb5.h
+++ b/include/crypto/krb5.h
@@ -64,6 +64,11 @@ struct scatterlist;
 #define KEY_USAGE_SEED_INTEGRITY        (0x55)
 
 /*
+ * Standard Kerberos error codes.
+ */
+#define KRB5_PROG_KEYTYPE_NOSUPP		-1765328233
+
+/*
  * Mode of operation.
  */
 enum krb5_crypto_mode {
diff --git a/include/cxl/features.h b/include/cxl/features.h
index a3bb34694c06..5f7f842765a5 100644
--- a/include/cxl/features.h
+++ b/include/cxl/features.h
@@ -66,7 +66,7 @@ struct cxl_memdev;
 #ifdef CONFIG_CXL_FEATURES
 inline struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds);
 int devm_cxl_setup_features(struct cxl_dev_state *cxlds);
-int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd);
+int devm_cxl_setup_fwctl(struct device *host, struct cxl_memdev *cxlmd);
 #else
 static inline struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds)
 {
@@ -78,7 +78,8 @@ static inline int devm_cxl_setup_features(struct cxl_dev_state *cxlds)
 	return -EOPNOTSUPP;
 }
 
-static inline int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd)
+static inline int devm_cxl_setup_fwctl(struct device *host,
+				       struct cxl_memdev *cxlmd)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index 2bf893eabb4b..bcd54020d6ba 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -585,8 +585,7 @@ static inline bool drm_gem_object_is_shared_for_memory_stats(struct drm_gem_obje
  */
 static inline bool drm_gem_is_imported(const struct drm_gem_object *obj)
 {
-	/* The dma-buf's priv field points to the original GEM object. */
-	return obj->dma_buf && (obj->dma_buf->priv != obj);
+	return !!obj->import_attach;
 }
 
 #ifdef CONFIG_LOCKDEP
diff --git a/include/drm/drm_gpusvm.h b/include/drm/drm_gpusvm.h
index df120b4d1f83..eaf704d3d05e 100644
--- a/include/drm/drm_gpusvm.h
+++ b/include/drm/drm_gpusvm.h
@@ -89,6 +89,7 @@ struct drm_gpusvm_devmem_ops {
  * @ops: Pointer to the operations structure for GPU SVM device memory
  * @dpagemap: The struct drm_pagemap of the pages this allocation belongs to.
  * @size: Size of device memory allocation
+ * @timeslice_expiration: Timeslice expiration in jiffies
  */
 struct drm_gpusvm_devmem {
 	struct device *dev;
@@ -97,6 +98,7 @@ struct drm_gpusvm_devmem {
 	const struct drm_gpusvm_devmem_ops *ops;
 	struct drm_pagemap *dpagemap;
 	size_t size;
+	u64 timeslice_expiration;
 };
 
 /**
@@ -186,6 +188,31 @@ struct drm_gpusvm_notifier {
 };
 
 /**
+ * struct drm_gpusvm_range_flags - Structure representing a GPU SVM range flags
+ *
+ * @migrate_devmem: Flag indicating whether the range can be migrated to device memory
+ * @unmapped: Flag indicating if the range has been unmapped
+ * @partial_unmap: Flag indicating if the range has been partially unmapped
+ * @has_devmem_pages: Flag indicating if the range has devmem pages
+ * @has_dma_mapping: Flag indicating if the range has a DMA mapping
+ * @__flags: Flags for range in u16 form (used for READ_ONCE)
+ */
+struct drm_gpusvm_range_flags {
+	union {
+		struct {
+			/* All flags below must be set upon creation */
+			u16 migrate_devmem : 1;
+			/* All flags below must be set / cleared under notifier lock */
+			u16 unmapped : 1;
+			u16 partial_unmap : 1;
+			u16 has_devmem_pages : 1;
+			u16 has_dma_mapping : 1;
+		};
+		u16 __flags;
+	};
+};
+
+/**
  * struct drm_gpusvm_range - Structure representing a GPU SVM range
  *
  * @gpusvm: Pointer to the GPU SVM structure
@@ -198,11 +225,6 @@ struct drm_gpusvm_notifier {
  * @dpagemap: The struct drm_pagemap of the device pages we're dma-mapping.
  *            Note this is assuming only one drm_pagemap per range is allowed.
  * @flags: Flags for range
- * @flags.migrate_devmem: Flag indicating whether the range can be migrated to device memory
- * @flags.unmapped: Flag indicating if the range has been unmapped
- * @flags.partial_unmap: Flag indicating if the range has been partially unmapped
- * @flags.has_devmem_pages: Flag indicating if the range has devmem pages
- * @flags.has_dma_mapping: Flag indicating if the range has a DMA mapping
  *
  * This structure represents a GPU SVM range used for tracking memory ranges
  * mapped in a DRM device.
@@ -216,15 +238,7 @@ struct drm_gpusvm_range {
 	unsigned long notifier_seq;
 	struct drm_pagemap_device_addr *dma_addr;
 	struct drm_pagemap *dpagemap;
-	struct {
-		/* All flags below must be set upon creation */
-		u16 migrate_devmem : 1;
-		/* All flags below must be set / cleared under notifier lock */
-		u16 unmapped : 1;
-		u16 partial_unmap : 1;
-		u16 has_devmem_pages : 1;
-		u16 has_dma_mapping : 1;
-	} flags;
+	struct drm_gpusvm_range_flags flags;
 };
 
 /**
@@ -283,17 +297,22 @@ struct drm_gpusvm {
  * @check_pages_threshold: Check CPU pages for present if chunk is less than or
  *                         equal to threshold. If not present, reduce chunk
  *                         size.
+ * @timeslice_ms: The timeslice MS which in minimum time a piece of memory
+ *		  remains with either exclusive GPU or CPU access.
  * @in_notifier: entering from a MMU notifier
  * @read_only: operating on read-only memory
  * @devmem_possible: possible to use device memory
+ * @devmem_only: use only device memory
  *
  * Context that is DRM GPUSVM is operating in (i.e. user arguments).
  */
 struct drm_gpusvm_ctx {
 	unsigned long check_pages_threshold;
+	unsigned long timeslice_ms;
 	unsigned int in_notifier :1;
 	unsigned int read_only :1;
 	unsigned int devmem_possible :1;
+	unsigned int devmem_only :1;
 };
 
 int drm_gpusvm_init(struct drm_gpusvm *gpusvm,
diff --git a/include/drm/drm_kunit_helpers.h b/include/drm/drm_kunit_helpers.h
index 11d59ce0bac0..1c62d1d4458c 100644
--- a/include/drm/drm_kunit_helpers.h
+++ b/include/drm/drm_kunit_helpers.h
@@ -118,6 +118,9 @@ drm_kunit_helper_create_crtc(struct kunit *test,
 			     const struct drm_crtc_funcs *funcs,
 			     const struct drm_crtc_helper_funcs *helper_funcs);
 
+int drm_kunit_add_mode_destroy_action(struct kunit *test,
+				      struct drm_display_mode *mode);
+
 struct drm_display_mode *
 drm_kunit_display_mode_from_cea_vic(struct kunit *test, struct drm_device *dev,
 				    u8 video_code);
diff --git a/include/drm/intel/pciids.h b/include/drm/intel/pciids.h
index 4736ea525048..d212848d07f3 100644
--- a/include/drm/intel/pciids.h
+++ b/include/drm/intel/pciids.h
@@ -850,6 +850,7 @@
 	MACRO__(0xE20C, ## __VA_ARGS__), \
 	MACRO__(0xE20D, ## __VA_ARGS__), \
 	MACRO__(0xE210, ## __VA_ARGS__), \
+	MACRO__(0xE211, ## __VA_ARGS__), \
 	MACRO__(0xE212, ## __VA_ARGS__), \
 	MACRO__(0xE215, ## __VA_ARGS__), \
 	MACRO__(0xE216, ## __VA_ARGS__)
diff --git a/include/drm/ttm/ttm_backup.h b/include/drm/ttm/ttm_backup.h
index 24ad120b8827..c33cba111171 100644
--- a/include/drm/ttm/ttm_backup.h
+++ b/include/drm/ttm/ttm_backup.h
@@ -9,14 +9,12 @@
 #include <linux/mm_types.h>
 #include <linux/shmem_fs.h>
 
-struct ttm_backup;
-
 /**
  * ttm_backup_handle_to_page_ptr() - Convert handle to struct page pointer
  * @handle: The handle to convert.
  *
  * Converts an opaque handle received from the
- * struct ttm_backoup_ops::backup_page() function to an (invalid)
+ * ttm_backup_backup_page() function to an (invalid)
  * struct page pointer suitable for a struct page array.
  *
  * Return: An (invalid) struct page pointer.
@@ -45,8 +43,8 @@ static inline bool ttm_backup_page_ptr_is_handle(const struct page *page)
  *
  * Return: The handle that was previously used in
  * ttm_backup_handle_to_page_ptr() to obtain a struct page pointer, suitable
- * for use as argument in the struct ttm_backup_ops drop() or
- * copy_backed_up_page() functions.
+ * for use as argument in the struct ttm_backup_drop() or
+ * ttm_backup_copy_page() functions.
  */
 static inline unsigned long
 ttm_backup_page_ptr_to_handle(const struct page *page)
@@ -55,20 +53,20 @@ ttm_backup_page_ptr_to_handle(const struct page *page)
 	return (unsigned long)page >> 1;
 }
 
-void ttm_backup_drop(struct ttm_backup *backup, pgoff_t handle);
+void ttm_backup_drop(struct file *backup, pgoff_t handle);
 
-int ttm_backup_copy_page(struct ttm_backup *backup, struct page *dst,
+int ttm_backup_copy_page(struct file *backup, struct page *dst,
 			 pgoff_t handle, bool intr);
 
 s64
-ttm_backup_backup_page(struct ttm_backup *backup, struct page *page,
+ttm_backup_backup_page(struct file *backup, struct page *page,
 		       bool writeback, pgoff_t idx, gfp_t page_gfp,
 		       gfp_t alloc_gfp);
 
-void ttm_backup_fini(struct ttm_backup *backup);
+void ttm_backup_fini(struct file *backup);
 
 u64 ttm_backup_bytes_avail(void);
 
-struct ttm_backup *ttm_backup_shmem_create(loff_t size);
+struct file *ttm_backup_shmem_create(loff_t size);
 
 #endif
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 13cf47f3322f..406437ad674b 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -118,7 +118,7 @@ struct ttm_tt {
 	 * ttm_tt_create() callback is responsible for assigning
 	 * this field.
 	 */
-	struct ttm_backup *backup;
+	struct file *backup;
 	/**
 	 * @caching: The current caching state of the pages, see enum
 	 * ttm_caching.
diff --git a/include/keys/rxrpc-type.h b/include/keys/rxrpc-type.h
index 333c0f49a9cd..0ddbe197a261 100644
--- a/include/keys/rxrpc-type.h
+++ b/include/keys/rxrpc-type.h
@@ -9,6 +9,7 @@
 #define _KEYS_RXRPC_TYPE_H
 
 #include <linux/key.h>
+#include <crypto/krb5.h>
 
 /*
  * key type for AF_RXRPC keys
@@ -32,6 +33,21 @@ struct rxkad_key {
 };
 
 /*
+ * RxRPC key for YFS-RxGK (type-6 security)
+ */
+struct rxgk_key {
+	s64		begintime;	/* Time at which the ticket starts */
+	s64		endtime;	/* Time at which the ticket ends */
+	u64		lifetime;	/* Maximum lifespan of a connection (seconds) */
+	u64		bytelife;	/* Maximum number of bytes on a connection */
+	unsigned int	enctype;	/* Encoding type */
+	s8		level;		/* Negotiated security RXRPC_SECURITY_PLAIN/AUTH/ENCRYPT */
+	struct krb5_buffer key;		/* Master key, K0 */
+	struct krb5_buffer ticket;	/* Ticket to be passed to server */
+	u8		_key[];		/* Key storage */
+};
+
+/*
  * list of tokens attached to an rxrpc key
  */
 struct rxrpc_key_token {
@@ -40,6 +56,7 @@ struct rxrpc_key_token {
 	struct rxrpc_key_token *next;	/* the next token in the list */
 	union {
 		struct rxkad_key *kad;
+		struct rxgk_key *rxgk;
 	};
 };
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 8e7af9a03b41..e721148c95d0 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -249,6 +249,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode)
 {
 #ifdef CONFIG_LOCKDEP
 	WARN_ON_ONCE(debug_locks &&
+		     (inode->i_sb->s_iflags & SB_I_CGROUPWB) &&
 		     (!lockdep_is_held(&inode->i_lock) &&
 		      !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) &&
 		      !lockdep_is_held(&inode->i_wb->list_lock)));
diff --git a/include/linux/bio.h b/include/linux/bio.h
index cafc7c215de8..b786ec5bcc81 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -11,6 +11,7 @@
 #include <linux/uio.h>
 
 #define BIO_MAX_VECS		256U
+#define BIO_MAX_INLINE_VECS	UIO_MAXIOV
 
 struct queue_limits;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index e39c45bc0a97..9a1f0ee40b56 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -712,23 +712,6 @@ static inline bool blk_queue_is_zoned(struct request_queue *q)
 		(q->limits.features & BLK_FEAT_ZONED);
 }
 
-#ifdef CONFIG_BLK_DEV_ZONED
-static inline unsigned int disk_nr_zones(struct gendisk *disk)
-{
-	return disk->nr_zones;
-}
-bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
-#else /* CONFIG_BLK_DEV_ZONED */
-static inline unsigned int disk_nr_zones(struct gendisk *disk)
-{
-	return 0;
-}
-static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
-{
-	return false;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
-
 static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 {
 	if (!blk_queue_is_zoned(disk->queue))
@@ -736,11 +719,6 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 	return sector >> ilog2(disk->queue->limits.chunk_sectors);
 }
 
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	return disk_nr_zones(bdev->bd_disk);
-}
-
 static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 {
 	return bdev->bd_disk->queue->limits.max_open_zones;
@@ -847,6 +825,51 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
 		(sb->s_blocksize_bits - SECTOR_SHIFT);
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
+{
+	return disk->nr_zones;
+}
+bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
+
+/**
+ * disk_zone_capacity - returns the zone capacity of zone containing @sector
+ * @disk:	disk to work with
+ * @sector:	sector number within the querying zone
+ *
+ * Returns the zone capacity of a zone containing @sector. @sector can be any
+ * sector in the zone.
+ */
+static inline unsigned int disk_zone_capacity(struct gendisk *disk,
+					      sector_t sector)
+{
+	sector_t zone_sectors = disk->queue->limits.chunk_sectors;
+
+	if (sector + zone_sectors >= get_capacity(disk))
+		return disk->last_zone_capacity;
+	return disk->zone_capacity;
+}
+static inline unsigned int bdev_zone_capacity(struct block_device *bdev,
+					      sector_t pos)
+{
+	return disk_zone_capacity(bdev->bd_disk, pos);
+}
+#else /* CONFIG_BLK_DEV_ZONED */
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
+{
+	return 0;
+}
+static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
+{
+	return false;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
+
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
+{
+	return disk_nr_zones(bdev->bd_disk);
+}
+
 int bdev_disk_changed(struct gendisk *disk, bool invalidate);
 
 void put_disk(struct gendisk *disk);
@@ -1614,6 +1637,7 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
 	return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev);
 }
 
+int bdev_validate_blocksize(struct block_device *bdev, int block_size);
 int set_blocksize(struct file *file, int size);
 
 int lookup_bdev(const char *pathname, dev_t *dev);
@@ -1670,10 +1694,6 @@ int bd_prepare_to_claim(struct block_device *bdev, void *holder,
 		const struct blk_holder_ops *hops);
 void bd_abort_claiming(struct block_device *bdev, void *holder);
 
-/* just for blk-cgroup, don't use elsewhere */
-struct block_device *blkdev_get_no_open(dev_t dev);
-void blkdev_put_no_open(struct block_device *bdev);
-
 struct block_device *I_BDEV(struct inode *inode);
 struct block_device *file_bdev(struct file *bdev_file);
 bool disk_live(struct gendisk *disk);
@@ -1685,7 +1705,7 @@ int sync_blockdev(struct block_device *bdev);
 int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend);
 int sync_blockdev_nowait(struct block_device *bdev);
 void sync_bdevs(bool wait);
-void bdev_statx(struct path *, struct kstat *, u32);
+void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask);
 void printk_all_partitions(void);
 int __init early_lookup_bdev(const char *pathname, dev_t *dev);
 #else
@@ -1703,8 +1723,8 @@ static inline int sync_blockdev_nowait(struct block_device *bdev)
 static inline void sync_bdevs(bool wait)
 {
 }
-static inline void bdev_statx(struct path *path, struct kstat *stat,
-				u32 request_mask)
+static inline void bdev_statx(const struct path *path, struct kstat *stat,
+		u32 request_mask)
 {
 }
 static inline void printk_all_partitions(void)
diff --git a/include/linux/btf.h b/include/linux/btf.h
index ebc0c0c9b944..b2983706292f 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -522,6 +522,7 @@ bool btf_param_match_suffix(const struct btf *btf,
 			    const char *suffix);
 int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto,
 		       u32 arg_no);
+u32 btf_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, int off);
 
 struct bpf_verifier_log;
 
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index f0a4ad7839b6..0029ff880e27 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -34,6 +34,7 @@ enum bh_state_bits {
 	BH_Meta,	/* Buffer contains metadata */
 	BH_Prio,	/* Buffer should be submitted with REQ_PRIO */
 	BH_Defer_Completion, /* Defer AIO completion to workqueue */
+	BH_Migrate,     /* Buffer is being migrated (norefs) */
 
 	BH_PrivateStart,/* not a state bit, but the first bit available
 			 * for private allocation by other entities
@@ -222,6 +223,8 @@ void __wait_on_buffer(struct buffer_head *);
 wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
 struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
 			unsigned size);
+struct buffer_head *__find_get_block_nonatomic(struct block_device *bdev,
+			sector_t block, unsigned size);
 struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
 		unsigned size, gfp_t gfp);
 void __brelse(struct buffer_head *);
@@ -397,6 +400,12 @@ sb_find_get_block(struct super_block *sb, sector_t block)
 	return __find_get_block(sb->s_bdev, block, sb->s_blocksize);
 }
 
+static inline struct buffer_head *
+sb_find_get_block_nonatomic(struct super_block *sb, sector_t block)
+{
+	return __find_get_block_nonatomic(sb->s_bdev, block, sb->s_blocksize);
+}
+
 static inline void
 map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block)
 {
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 23492213ea35..492d23bec7be 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -38,6 +38,17 @@ enum can_termination_gpio {
 	CAN_TERMINATION_GPIO_MAX,
 };
 
+struct data_bittiming_params {
+	const struct can_bittiming_const *data_bittiming_const;
+	struct can_bittiming data_bittiming;
+	const struct can_tdc_const *tdc_const;
+	struct can_tdc tdc;
+	const u32 *data_bitrate_const;
+	unsigned int data_bitrate_const_cnt;
+	int (*do_set_data_bittiming)(struct net_device *dev);
+	int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv);
+};
+
 /*
  * CAN common private data
  */
@@ -45,16 +56,11 @@ struct can_priv {
 	struct net_device *dev;
 	struct can_device_stats can_stats;
 
-	const struct can_bittiming_const *bittiming_const,
-		*data_bittiming_const;
-	struct can_bittiming bittiming, data_bittiming;
-	const struct can_tdc_const *tdc_const;
-	struct can_tdc tdc;
-
+	const struct can_bittiming_const *bittiming_const;
+	struct can_bittiming bittiming;
+	struct data_bittiming_params fd;
 	unsigned int bitrate_const_cnt;
 	const u32 *bitrate_const;
-	const u32 *data_bitrate_const;
-	unsigned int data_bitrate_const_cnt;
 	u32 bitrate_max;
 	struct can_clock clock;
 
@@ -77,14 +83,12 @@ struct can_priv {
 	struct delayed_work restart_work;
 
 	int (*do_set_bittiming)(struct net_device *dev);
-	int (*do_set_data_bittiming)(struct net_device *dev);
 	int (*do_set_mode)(struct net_device *dev, enum can_mode mode);
 	int (*do_set_termination)(struct net_device *dev, u16 term);
 	int (*do_get_state)(const struct net_device *dev,
 			    enum can_state *state);
 	int (*do_get_berr_counter)(const struct net_device *dev,
 				   struct can_berr_counter *bec);
-	int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv);
 };
 
 static inline bool can_tdc_is_enabled(const struct can_priv *priv)
@@ -114,11 +118,11 @@ static inline bool can_tdc_is_enabled(const struct can_priv *priv)
  */
 static inline s32 can_get_relative_tdco(const struct can_priv *priv)
 {
-	const struct can_bittiming *dbt = &priv->data_bittiming;
+	const struct can_bittiming *dbt = &priv->fd.data_bittiming;
 	s32 sample_point_in_tc = (CAN_SYNC_SEG + dbt->prop_seg +
 				  dbt->phase_seg1) * dbt->brp;
 
-	return (s32)priv->tdc.tdco - sample_point_in_tc;
+	return (s32)priv->fd.tdc.tdco - sample_point_in_tc;
 }
 
 /* helper to define static CAN controller features at device creation time */
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index d55b30057a45..50b14a5661c7 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -490,9 +490,6 @@ extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *,
 					struct page **pages, u64 length,
 					u32 alignment, bool pages_from_pool,
 					bool own_pages);
-extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *,
-					unsigned int which,
-					struct ceph_pagelist *pagelist);
 #ifdef CONFIG_BLOCK
 void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
 				    unsigned int which,
@@ -509,9 +506,6 @@ void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
 void osd_req_op_extent_osd_iter(struct ceph_osd_request *osd_req,
 				unsigned int which, struct iov_iter *iter);
 
-extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *,
-					unsigned int which,
-					struct ceph_pagelist *pagelist);
 extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *,
 					unsigned int which,
 					struct page **pages, u64 length,
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index e3049543008b..3aa955102b34 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -78,6 +78,8 @@ extern ssize_t cpu_show_gds(struct device *dev,
 extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev,
 					       struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_indirect_target_selection(struct device *dev,
+						  struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 400fee6427a5..7a5b391dcc01 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -776,8 +776,8 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy,
 int cpufreq_generic_frequency_table_verify(struct cpufreq_policy_data *policy);
 
 int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
-				 unsigned int target_freq,
-				 unsigned int relation);
+				 unsigned int target_freq, unsigned int min,
+				 unsigned int max, unsigned int relation);
 int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy,
 		unsigned int freq);
 
@@ -840,12 +840,12 @@ static inline int cpufreq_table_find_index_dl(struct cpufreq_policy *policy,
 	return best;
 }
 
-/* Works only on sorted freq-tables */
-static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy,
-					     unsigned int target_freq,
-					     bool efficiencies)
+static inline int find_index_l(struct cpufreq_policy *policy,
+			       unsigned int target_freq,
+			       unsigned int min, unsigned int max,
+			       bool efficiencies)
 {
-	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	target_freq = clamp_val(target_freq, min, max);
 
 	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
 		return cpufreq_table_find_index_al(policy, target_freq,
@@ -855,6 +855,14 @@ static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy,
 						   efficiencies);
 }
 
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy,
+					     unsigned int target_freq,
+					     bool efficiencies)
+{
+	return find_index_l(policy, target_freq, policy->min, policy->max, efficiencies);
+}
+
 /* Find highest freq at or below target in a table in ascending order */
 static inline int cpufreq_table_find_index_ah(struct cpufreq_policy *policy,
 					      unsigned int target_freq,
@@ -908,12 +916,12 @@ static inline int cpufreq_table_find_index_dh(struct cpufreq_policy *policy,
 	return best;
 }
 
-/* Works only on sorted freq-tables */
-static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy,
-					     unsigned int target_freq,
-					     bool efficiencies)
+static inline int find_index_h(struct cpufreq_policy *policy,
+			       unsigned int target_freq,
+			       unsigned int min, unsigned int max,
+			       bool efficiencies)
 {
-	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	target_freq = clamp_val(target_freq, min, max);
 
 	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
 		return cpufreq_table_find_index_ah(policy, target_freq,
@@ -923,6 +931,14 @@ static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy,
 						   efficiencies);
 }
 
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy,
+					     unsigned int target_freq,
+					     bool efficiencies)
+{
+	return find_index_h(policy, target_freq, policy->min, policy->max, efficiencies);
+}
+
 /* Find closest freq to target in a table in ascending order */
 static inline int cpufreq_table_find_index_ac(struct cpufreq_policy *policy,
 					      unsigned int target_freq,
@@ -993,12 +1009,12 @@ static inline int cpufreq_table_find_index_dc(struct cpufreq_policy *policy,
 	return best;
 }
 
-/* Works only on sorted freq-tables */
-static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
-					     unsigned int target_freq,
-					     bool efficiencies)
+static inline int find_index_c(struct cpufreq_policy *policy,
+			       unsigned int target_freq,
+			       unsigned int min, unsigned int max,
+			       bool efficiencies)
 {
-	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	target_freq = clamp_val(target_freq, min, max);
 
 	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
 		return cpufreq_table_find_index_ac(policy, target_freq,
@@ -1008,7 +1024,17 @@ static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
 						   efficiencies);
 }
 
-static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy, int idx)
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
+					     unsigned int target_freq,
+					     bool efficiencies)
+{
+	return find_index_c(policy, target_freq, policy->min, policy->max, efficiencies);
+}
+
+static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy,
+					unsigned int min, unsigned int max,
+					int idx)
 {
 	unsigned int freq;
 
@@ -1017,11 +1043,13 @@ static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy, int idx)
 
 	freq = policy->freq_table[idx].frequency;
 
-	return freq == clamp_val(freq, policy->min, policy->max);
+	return freq == clamp_val(freq, min, max);
 }
 
 static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 						 unsigned int target_freq,
+						 unsigned int min,
+						 unsigned int max,
 						 unsigned int relation)
 {
 	bool efficiencies = policy->efficiencies_available &&
@@ -1032,29 +1060,26 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 	relation &= ~CPUFREQ_RELATION_E;
 
 	if (unlikely(policy->freq_table_sorted == CPUFREQ_TABLE_UNSORTED))
-		return cpufreq_table_index_unsorted(policy, target_freq,
-						    relation);
+		return cpufreq_table_index_unsorted(policy, target_freq, min,
+						    max, relation);
 retry:
 	switch (relation) {
 	case CPUFREQ_RELATION_L:
-		idx = cpufreq_table_find_index_l(policy, target_freq,
-						 efficiencies);
+		idx = find_index_l(policy, target_freq, min, max, efficiencies);
 		break;
 	case CPUFREQ_RELATION_H:
-		idx = cpufreq_table_find_index_h(policy, target_freq,
-						 efficiencies);
+		idx = find_index_h(policy, target_freq, min, max, efficiencies);
 		break;
 	case CPUFREQ_RELATION_C:
-		idx = cpufreq_table_find_index_c(policy, target_freq,
-						 efficiencies);
+		idx = find_index_c(policy, target_freq, min, max, efficiencies);
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
 	}
 
-	/* Limit frequency index to honor policy->min/max */
-	if (!cpufreq_is_in_limits(policy, idx) && efficiencies) {
+	/* Limit frequency index to honor min and max */
+	if (!cpufreq_is_in_limits(policy, min, max, idx) && efficiencies) {
 		efficiencies = false;
 		goto retry;
 	}
diff --git a/include/linux/crc32.h b/include/linux/crc32.h
index 69c2e8bb3782..7f7d0be8a0ac 100644
--- a/include/linux/crc32.h
+++ b/include/linux/crc32.h
@@ -76,29 +76,6 @@ static inline u32 crc32_le_combine(u32 crc1, u32 crc2, size_t len2)
 	return crc32_le_shift(crc1, len2) ^ crc2;
 }
 
-u32 crc32c_shift(u32 crc, size_t len);
-
-/**
- * crc32c_combine - Combine two crc32c check values into one. For two sequences
- *		    of bytes, seq1 and seq2 with lengths len1 and len2, crc32c()
- *		    check values were calculated for each, crc1 and crc2.
- *
- * @crc1: crc32c of the first block
- * @crc2: crc32c of the second block
- * @len2: length of the second block
- *
- * Return: The crc32c() check value of seq1 and seq2 concatenated, requiring
- *	   only crc1, crc2, and len2. Note: If seq_full denotes the concatenated
- *	   memory area of seq1 with seq2, and crc_full the crc32c() value of
- *	   seq_full, then crc_full == crc32c_combine(crc1, crc2, len2) when
- *	   crc_full was seeded with the same initializer as crc1, and crc2 seed
- *	   was 0. See also crc_combine_test().
- */
-static inline u32 crc32c_combine(u32 crc1, u32 crc2, size_t len2)
-{
-	return crc32c_shift(crc1, len2) ^ crc2;
-}
-
 #define crc32(seed, data, length)  crc32_le(seed, (unsigned char const *)(data), length)
 
 /*
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 8d1395f945bf..e9f07e37dd6f 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -173,65 +173,59 @@ struct dentry_operations {
  */
 
 /* d_flags entries */
-#define DCACHE_OP_HASH			BIT(0)
-#define DCACHE_OP_COMPARE		BIT(1)
-#define DCACHE_OP_REVALIDATE		BIT(2)
-#define DCACHE_OP_DELETE		BIT(3)
-#define DCACHE_OP_PRUNE			BIT(4)
-
-#define	DCACHE_DISCONNECTED		BIT(5)
-     /* This dentry is possibly not currently connected to the dcache tree, in
-      * which case its parent will either be itself, or will have this flag as
-      * well.  nfsd will not use a dentry with this bit set, but will first
-      * endeavour to clear the bit either by discovering that it is connected,
-      * or by performing lookup operations.   Any filesystem which supports
-      * nfsd_operations MUST have a lookup function which, if it finds a
-      * directory inode with a DCACHE_DISCONNECTED dentry, will d_move that
-      * dentry into place and return that dentry rather than the passed one,
-      * typically using d_splice_alias. */
-
-#define DCACHE_REFERENCED		BIT(6) /* Recently used, don't discard. */
-
-#define DCACHE_DONTCACHE		BIT(7) /* Purge from memory on final dput() */
-
-#define DCACHE_CANT_MOUNT		BIT(8)
-#define DCACHE_GENOCIDE			BIT(9)
-#define DCACHE_SHRINK_LIST		BIT(10)
-
-#define DCACHE_OP_WEAK_REVALIDATE	BIT(11)
-
-#define DCACHE_NFSFS_RENAMED		BIT(12)
-     /* this dentry has been "silly renamed" and has to be deleted on the last
-      * dput() */
-#define DCACHE_FSNOTIFY_PARENT_WATCHED	BIT(13)
-     /* Parent inode is watched by some fsnotify listener */
-
-#define DCACHE_DENTRY_KILLED		BIT(14)
-
-#define DCACHE_MOUNTED			BIT(15) /* is a mountpoint */
-#define DCACHE_NEED_AUTOMOUNT		BIT(16) /* handle automount on this dir */
-#define DCACHE_MANAGE_TRANSIT		BIT(17) /* manage transit from this dirent */
+enum dentry_flags {
+	DCACHE_OP_HASH			= BIT(0),
+	DCACHE_OP_COMPARE		= BIT(1),
+	DCACHE_OP_REVALIDATE		= BIT(2),
+	DCACHE_OP_DELETE		= BIT(3),
+	DCACHE_OP_PRUNE			= BIT(4),
+	/*
+	 * This dentry is possibly not currently connected to the dcache tree,
+	 * in which case its parent will either be itself, or will have this
+	 * flag as well.  nfsd will not use a dentry with this bit set, but will
+	 * first endeavour to clear the bit either by discovering that it is
+	 * connected, or by performing lookup operations.  Any filesystem which
+	 * supports nfsd_operations MUST have a lookup function which, if it
+	 * finds a directory inode with a DCACHE_DISCONNECTED dentry, will
+	 * d_move that dentry into place and return that dentry rather than the
+	 * passed one, typically using d_splice_alias.
+	 */
+	DCACHE_DISCONNECTED		= BIT(5),
+	DCACHE_REFERENCED		= BIT(6),	/* Recently used, don't discard. */
+	DCACHE_DONTCACHE		= BIT(7),	/* Purge from memory on final dput() */
+	DCACHE_CANT_MOUNT		= BIT(8),
+	DCACHE_GENOCIDE			= BIT(9),
+	DCACHE_SHRINK_LIST		= BIT(10),
+	DCACHE_OP_WEAK_REVALIDATE	= BIT(11),
+	/*
+	 * this dentry has been "silly renamed" and has to be deleted on the
+	 * last dput()
+	 */
+	DCACHE_NFSFS_RENAMED		= BIT(12),
+	DCACHE_FSNOTIFY_PARENT_WATCHED	= BIT(13),	/* Parent inode is watched by some fsnotify listener */
+	DCACHE_DENTRY_KILLED		= BIT(14),
+	DCACHE_MOUNTED			= BIT(15),	/* is a mountpoint */
+	DCACHE_NEED_AUTOMOUNT		= BIT(16),	/* handle automount on this dir */
+	DCACHE_MANAGE_TRANSIT		= BIT(17),	/* manage transit from this dirent */
+	DCACHE_LRU_LIST			= BIT(18),
+	DCACHE_ENTRY_TYPE		= (7 << 19),	/* bits 19..21 are for storing type: */
+	DCACHE_MISS_TYPE		= (0 << 19),	/* Negative dentry */
+	DCACHE_WHITEOUT_TYPE		= (1 << 19),	/* Whiteout dentry (stop pathwalk) */
+	DCACHE_DIRECTORY_TYPE		= (2 << 19),	/* Normal directory */
+	DCACHE_AUTODIR_TYPE		= (3 << 19),	/* Lookupless directory (presumed automount) */
+	DCACHE_REGULAR_TYPE		= (4 << 19),	/* Regular file type */
+	DCACHE_SPECIAL_TYPE		= (5 << 19),	/* Other file type */
+	DCACHE_SYMLINK_TYPE		= (6 << 19),	/* Symlink */
+	DCACHE_NOKEY_NAME		= BIT(22),	/* Encrypted name encoded without key */
+	DCACHE_OP_REAL			= BIT(23),
+	DCACHE_PAR_LOOKUP		= BIT(24),	/* being looked up (with parent locked shared) */
+	DCACHE_DENTRY_CURSOR		= BIT(25),
+	DCACHE_NORCU			= BIT(26),	/* No RCU delay for freeing */
+};
+
 #define DCACHE_MANAGED_DENTRY \
 	(DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT)
 
-#define DCACHE_LRU_LIST			BIT(18)
-
-#define DCACHE_ENTRY_TYPE		(7 << 19) /* bits 19..21 are for storing type: */
-#define DCACHE_MISS_TYPE		(0 << 19) /* Negative dentry */
-#define DCACHE_WHITEOUT_TYPE		(1 << 19) /* Whiteout dentry (stop pathwalk) */
-#define DCACHE_DIRECTORY_TYPE		(2 << 19) /* Normal directory */
-#define DCACHE_AUTODIR_TYPE		(3 << 19) /* Lookupless directory (presumed automount) */
-#define DCACHE_REGULAR_TYPE		(4 << 19) /* Regular file type */
-#define DCACHE_SPECIAL_TYPE		(5 << 19) /* Other file type */
-#define DCACHE_SYMLINK_TYPE		(6 << 19) /* Symlink */
-
-#define DCACHE_NOKEY_NAME		BIT(22) /* Encrypted name encoded without key */
-#define DCACHE_OP_REAL			BIT(23)
-
-#define DCACHE_PAR_LOOKUP		BIT(24) /* being looked up (with parent locked shared) */
-#define DCACHE_DENTRY_CURSOR		BIT(25)
-#define DCACHE_NORCU			BIT(26) /* No RCU delay for freeing */
-
 extern seqlock_t rename_lock;
 
 /*
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 325af611909f..0b61b8b996d4 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -2,79 +2,8 @@
 #ifndef _LINUX_DCCP_H
 #define _LINUX_DCCP_H
 
-
-#include <linux/in.h>
-#include <linux/interrupt.h>
-#include <linux/ktime.h>
-#include <linux/list.h>
-#include <linux/uio.h>
-#include <linux/workqueue.h>
-
-#include <net/inet_connection_sock.h>
-#include <net/inet_sock.h>
-#include <net/inet_timewait_sock.h>
-#include <net/tcp_states.h>
 #include <uapi/linux/dccp.h>
 
-enum dccp_state {
-	DCCP_OPEN	     = TCP_ESTABLISHED,
-	DCCP_REQUESTING	     = TCP_SYN_SENT,
-	DCCP_LISTEN	     = TCP_LISTEN,
-	DCCP_RESPOND	     = TCP_SYN_RECV,
-	/*
-	 * States involved in closing a DCCP connection:
-	 * 1) ACTIVE_CLOSEREQ is entered by a server sending a CloseReq.
-	 *
-	 * 2) CLOSING can have three different meanings (RFC 4340, 8.3):
-	 *  a. Client has performed active-close, has sent a Close to the server
-	 *     from state OPEN or PARTOPEN, and is waiting for the final Reset
-	 *     (in this case, SOCK_DONE == 1).
-	 *  b. Client is asked to perform passive-close, by receiving a CloseReq
-	 *     in (PART)OPEN state. It sends a Close and waits for final Reset
-	 *     (in this case, SOCK_DONE == 0).
-	 *  c. Server performs an active-close as in (a), keeps TIMEWAIT state.
-	 *
-	 * 3) The following intermediate states are employed to give passively
-	 *    closing nodes a chance to process their unread data:
-	 *    - PASSIVE_CLOSE    (from OPEN => CLOSED) and
-	 *    - PASSIVE_CLOSEREQ (from (PART)OPEN to CLOSING; case (b) above).
-	 */
-	DCCP_ACTIVE_CLOSEREQ = TCP_FIN_WAIT1,
-	DCCP_PASSIVE_CLOSE   = TCP_CLOSE_WAIT,	/* any node receiving a Close */
-	DCCP_CLOSING	     = TCP_CLOSING,
-	DCCP_TIME_WAIT	     = TCP_TIME_WAIT,
-	DCCP_CLOSED	     = TCP_CLOSE,
-	DCCP_NEW_SYN_RECV    = TCP_NEW_SYN_RECV,
-	DCCP_PARTOPEN	     = TCP_MAX_STATES,
-	DCCP_PASSIVE_CLOSEREQ,			/* clients receiving CloseReq */
-	DCCP_MAX_STATES
-};
-
-enum {
-	DCCPF_OPEN	      = TCPF_ESTABLISHED,
-	DCCPF_REQUESTING      = TCPF_SYN_SENT,
-	DCCPF_LISTEN	      = TCPF_LISTEN,
-	DCCPF_RESPOND	      = TCPF_SYN_RECV,
-	DCCPF_ACTIVE_CLOSEREQ = TCPF_FIN_WAIT1,
-	DCCPF_CLOSING	      = TCPF_CLOSING,
-	DCCPF_TIME_WAIT	      = TCPF_TIME_WAIT,
-	DCCPF_CLOSED	      = TCPF_CLOSE,
-	DCCPF_NEW_SYN_RECV    = TCPF_NEW_SYN_RECV,
-	DCCPF_PARTOPEN	      = (1 << DCCP_PARTOPEN),
-};
-
-static inline struct dccp_hdr *dccp_hdr(const struct sk_buff *skb)
-{
-	return (struct dccp_hdr *)skb_transport_header(skb);
-}
-
-static inline struct dccp_hdr *dccp_zeroed_hdr(struct sk_buff *skb, int headlen)
-{
-	skb_push(skb, headlen);
-	skb_reset_transport_header(skb);
-	return memset(skb_transport_header(skb), 0, headlen);
-}
-
 static inline struct dccp_hdr_ext *dccp_hdrx(const struct dccp_hdr *dh)
 {
 	return (struct dccp_hdr_ext *)((unsigned char *)dh + sizeof(*dh));
@@ -85,12 +14,6 @@ static inline unsigned int __dccp_basic_hdr_len(const struct dccp_hdr *dh)
 	return sizeof(*dh) + (dh->dccph_x ? sizeof(struct dccp_hdr_ext) : 0);
 }
 
-static inline unsigned int dccp_basic_hdr_len(const struct sk_buff *skb)
-{
-	const struct dccp_hdr *dh = dccp_hdr(skb);
-	return __dccp_basic_hdr_len(dh);
-}
-
 static inline __u64 dccp_hdr_seq(const struct dccp_hdr *dh)
 {
 	__u64 seq_nr =  ntohs(dh->dccph_seq);
@@ -103,222 +26,10 @@ static inline __u64 dccp_hdr_seq(const struct dccp_hdr *dh)
 	return seq_nr;
 }
 
-static inline struct dccp_hdr_request *dccp_hdr_request(struct sk_buff *skb)
-{
-	return (struct dccp_hdr_request *)(skb_transport_header(skb) +
-					   dccp_basic_hdr_len(skb));
-}
-
-static inline struct dccp_hdr_ack_bits *dccp_hdr_ack_bits(const struct sk_buff *skb)
-{
-	return (struct dccp_hdr_ack_bits *)(skb_transport_header(skb) +
-					    dccp_basic_hdr_len(skb));
-}
-
-static inline u64 dccp_hdr_ack_seq(const struct sk_buff *skb)
-{
-	const struct dccp_hdr_ack_bits *dhack = dccp_hdr_ack_bits(skb);
-	return ((u64)ntohs(dhack->dccph_ack_nr_high) << 32) + ntohl(dhack->dccph_ack_nr_low);
-}
-
-static inline struct dccp_hdr_response *dccp_hdr_response(struct sk_buff *skb)
-{
-	return (struct dccp_hdr_response *)(skb_transport_header(skb) +
-					    dccp_basic_hdr_len(skb));
-}
-
-static inline struct dccp_hdr_reset *dccp_hdr_reset(struct sk_buff *skb)
-{
-	return (struct dccp_hdr_reset *)(skb_transport_header(skb) +
-					 dccp_basic_hdr_len(skb));
-}
-
 static inline unsigned int __dccp_hdr_len(const struct dccp_hdr *dh)
 {
 	return __dccp_basic_hdr_len(dh) +
 	       dccp_packet_hdr_len(dh->dccph_type);
 }
 
-static inline unsigned int dccp_hdr_len(const struct sk_buff *skb)
-{
-	return __dccp_hdr_len(dccp_hdr(skb));
-}
-
-/**
- * struct dccp_request_sock  -  represent DCCP-specific connection request
- * @dreq_inet_rsk: structure inherited from
- * @dreq_iss: initial sequence number, sent on the first Response (RFC 4340, 7.1)
- * @dreq_gss: greatest sequence number sent (for retransmitted Responses)
- * @dreq_isr: initial sequence number received in the first Request
- * @dreq_gsr: greatest sequence number received (for retransmitted Request(s))
- * @dreq_service: service code present on the Request (there is just one)
- * @dreq_featneg: feature negotiation options for this connection
- * The following two fields are analogous to the ones in dccp_sock:
- * @dreq_timestamp_echo: last received timestamp to echo (13.1)
- * @dreq_timestamp_echo: the time of receiving the last @dreq_timestamp_echo
- */
-struct dccp_request_sock {
-	struct inet_request_sock dreq_inet_rsk;
-	__u64			 dreq_iss;
-	__u64			 dreq_gss;
-	__u64			 dreq_isr;
-	__u64			 dreq_gsr;
-	__be32			 dreq_service;
-	spinlock_t		 dreq_lock;
-	struct list_head	 dreq_featneg;
-	__u32			 dreq_timestamp_echo;
-	__u32			 dreq_timestamp_time;
-};
-
-static inline struct dccp_request_sock *dccp_rsk(const struct request_sock *req)
-{
-	return (struct dccp_request_sock *)req;
-}
-
-extern struct inet_timewait_death_row dccp_death_row;
-
-extern int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
-			      struct sk_buff *skb);
-
-struct dccp_options_received {
-	u64	dccpor_ndp:48;
-	u32	dccpor_timestamp;
-	u32	dccpor_timestamp_echo;
-	u32	dccpor_elapsed_time;
-};
-
-struct ccid;
-
-enum dccp_role {
-	DCCP_ROLE_UNDEFINED,
-	DCCP_ROLE_LISTEN,
-	DCCP_ROLE_CLIENT,
-	DCCP_ROLE_SERVER,
-};
-
-struct dccp_service_list {
-	__u32	dccpsl_nr;
-	__be32	dccpsl_list[];
-};
-
-#define DCCP_SERVICE_INVALID_VALUE htonl((__u32)-1)
-#define DCCP_SERVICE_CODE_IS_ABSENT		0
-
-static inline bool dccp_list_has_service(const struct dccp_service_list *sl,
-					const __be32 service)
-{
-	if (likely(sl != NULL)) {
-		u32 i = sl->dccpsl_nr;
-		while (i--)
-			if (sl->dccpsl_list[i] == service)
-				return true;
-	}
-	return false;
-}
-
-struct dccp_ackvec;
-
-/**
- * struct dccp_sock - DCCP socket state
- *
- * @dccps_swl - sequence number window low
- * @dccps_swh - sequence number window high
- * @dccps_awl - acknowledgement number window low
- * @dccps_awh - acknowledgement number window high
- * @dccps_iss - initial sequence number sent
- * @dccps_isr - initial sequence number received
- * @dccps_osr - first OPEN sequence number received
- * @dccps_gss - greatest sequence number sent
- * @dccps_gsr - greatest valid sequence number received
- * @dccps_gar - greatest valid ack number received on a non-Sync; initialized to %dccps_iss
- * @dccps_service - first (passive sock) or unique (active sock) service code
- * @dccps_service_list - second .. last service code on passive socket
- * @dccps_timestamp_echo - latest timestamp received on a TIMESTAMP option
- * @dccps_timestamp_time - time of receiving latest @dccps_timestamp_echo
- * @dccps_l_ack_ratio - feature-local Ack Ratio
- * @dccps_r_ack_ratio - feature-remote Ack Ratio
- * @dccps_l_seq_win - local Sequence Window (influences ack number validity)
- * @dccps_r_seq_win - remote Sequence Window (influences seq number validity)
- * @dccps_pcslen - sender   partial checksum coverage (via sockopt)
- * @dccps_pcrlen - receiver partial checksum coverage (via sockopt)
- * @dccps_send_ndp_count - local Send NDP Count feature (7.7.2)
- * @dccps_ndp_count - number of Non Data Packets since last data packet
- * @dccps_mss_cache - current value of MSS (path MTU minus header sizes)
- * @dccps_rate_last - timestamp for rate-limiting DCCP-Sync (RFC 4340, 7.5.4)
- * @dccps_featneg - tracks feature-negotiation state (mostly during handshake)
- * @dccps_hc_rx_ackvec - rx half connection ack vector
- * @dccps_hc_rx_ccid - CCID used for the receiver (or receiving half-connection)
- * @dccps_hc_tx_ccid - CCID used for the sender (or sending half-connection)
- * @dccps_options_received - parsed set of retrieved options
- * @dccps_qpolicy - TX dequeueing policy, one of %dccp_packet_dequeueing_policy
- * @dccps_tx_qlen - maximum length of the TX queue
- * @dccps_role - role of this sock, one of %dccp_role
- * @dccps_hc_rx_insert_options - receiver wants to add options when acking
- * @dccps_hc_tx_insert_options - sender wants to add options when sending
- * @dccps_server_timewait - server holds timewait state on close (RFC 4340, 8.3)
- * @dccps_sync_scheduled - flag which signals "send out-of-band message soon"
- * @dccps_xmitlet - tasklet scheduled by the TX CCID to dequeue data packets
- * @dccps_xmit_timer - used by the TX CCID to delay sending (rate-based pacing)
- * @dccps_syn_rtt - RTT sample from Request/Response exchange (in usecs)
- */
-struct dccp_sock {
-	/* inet_connection_sock has to be the first member of dccp_sock */
-	struct inet_connection_sock	dccps_inet_connection;
-#define dccps_syn_rtt			dccps_inet_connection.icsk_ack.lrcvtime
-	__u64				dccps_swl;
-	__u64				dccps_swh;
-	__u64				dccps_awl;
-	__u64				dccps_awh;
-	__u64				dccps_iss;
-	__u64				dccps_isr;
-	__u64				dccps_osr;
-	__u64				dccps_gss;
-	__u64				dccps_gsr;
-	__u64				dccps_gar;
-	__be32				dccps_service;
-	__u32				dccps_mss_cache;
-	struct dccp_service_list	*dccps_service_list;
-	__u32				dccps_timestamp_echo;
-	__u32				dccps_timestamp_time;
-	__u16				dccps_l_ack_ratio;
-	__u16				dccps_r_ack_ratio;
-	__u64				dccps_l_seq_win:48;
-	__u64				dccps_r_seq_win:48;
-	__u8				dccps_pcslen:4;
-	__u8				dccps_pcrlen:4;
-	__u8				dccps_send_ndp_count:1;
-	__u64				dccps_ndp_count:48;
-	unsigned long			dccps_rate_last;
-	struct list_head		dccps_featneg;
-	struct dccp_ackvec		*dccps_hc_rx_ackvec;
-	struct ccid			*dccps_hc_rx_ccid;
-	struct ccid			*dccps_hc_tx_ccid;
-	struct dccp_options_received	dccps_options_received;
-	__u8				dccps_qpolicy;
-	__u32				dccps_tx_qlen;
-	enum dccp_role			dccps_role:2;
-	__u8				dccps_hc_rx_insert_options:1;
-	__u8				dccps_hc_tx_insert_options:1;
-	__u8				dccps_server_timewait:1;
-	__u8				dccps_sync_scheduled:1;
-	struct tasklet_struct		dccps_xmitlet;
-	struct timer_list		dccps_xmit_timer;
-};
-
-#define dccp_sk(ptr)	container_of_const(ptr, struct dccp_sock, \
-					   dccps_inet_connection.icsk_inet.sk)
-
-static inline const char *dccp_role(const struct sock *sk)
-{
-	switch (dccp_sk(sk)->dccps_role) {
-	case DCCP_ROLE_UNDEFINED: return "undefined";
-	case DCCP_ROLE_LISTEN:	  return "listen";
-	case DCCP_ROLE_SERVER:	  return "server";
-	case DCCP_ROLE_CLIENT:	  return "client";
-	}
-	return NULL;
-}
-
-extern void dccp_syn_ack_timeout(const struct request_sock *req);
-
 #endif /* _LINUX_DCCP_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index b79925b1c433..85ab710ec0e7 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -629,10 +629,14 @@ static inline int dma_mmap_wc(struct device *dev,
 #else
 #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME)
 #define DEFINE_DMA_UNMAP_LEN(LEN_NAME)
-#define dma_unmap_addr(PTR, ADDR_NAME)           (0)
-#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL)  do { } while (0)
-#define dma_unmap_len(PTR, LEN_NAME)             (0)
-#define dma_unmap_len_set(PTR, LEN_NAME, VAL)    do { } while (0)
+#define dma_unmap_addr(PTR, ADDR_NAME)           \
+	({ typeof(PTR) __p __maybe_unused = PTR; 0; })
+#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL)  \
+	do { typeof(PTR) __p __maybe_unused = PTR; } while (0)
+#define dma_unmap_len(PTR, LEN_NAME)             \
+	({ typeof(PTR) __p __maybe_unused = PTR; 0; })
+#define dma_unmap_len_set(PTR, LEN_NAME, VAL)    \
+	do { typeof(PTR) __p __maybe_unused = PTR; } while (0)
 #endif
 
 #endif /* _LINUX_DMA_MAPPING_H */
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 8210ece94fa6..5e0dd333ad1f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -17,9 +17,14 @@
 #include <linux/compat.h>
 #include <linux/if_ether.h>
 #include <linux/netlink.h>
+#include <linux/timer_types.h>
 #include <uapi/linux/ethtool.h>
+#include <uapi/linux/ethtool_netlink_generated.h>
 #include <uapi/linux/net_tstamp.h>
 
+#define ETHTOOL_MM_MAX_VERIFY_TIME_MS		128
+#define ETHTOOL_MM_MAX_VERIFY_RETRIES		3
+
 struct compat_ethtool_rx_flow_spec {
 	u32		flow_type;
 	union ethtool_flow_union h_u;
@@ -718,6 +723,75 @@ struct ethtool_mm_stats {
 	u64 MACMergeHoldCount;
 };
 
+enum ethtool_mmsv_event {
+	ETHTOOL_MMSV_LP_SENT_VERIFY_MPACKET,
+	ETHTOOL_MMSV_LD_SENT_VERIFY_MPACKET,
+	ETHTOOL_MMSV_LP_SENT_RESPONSE_MPACKET,
+};
+
+/* MAC Merge verification mPacket type */
+enum ethtool_mpacket {
+	ETHTOOL_MPACKET_VERIFY,
+	ETHTOOL_MPACKET_RESPONSE,
+};
+
+struct ethtool_mmsv;
+
+/**
+ * struct ethtool_mmsv_ops - Operations for MAC Merge Software Verification
+ * @configure_tx: Driver callback for the event where the preemptible TX
+ *		  becomes active or inactive. Preemptible traffic
+ *		  classes must be committed to hardware only while
+ *		  preemptible TX is active.
+ * @configure_pmac: Driver callback for the event where the pMAC state
+ *		    changes as result of an administrative setting
+ *		    (ethtool) or a call to ethtool_mmsv_link_state_handle().
+ * @send_mpacket: Driver-provided method for sending a Verify or a Response
+ *		  mPacket.
+ */
+struct ethtool_mmsv_ops {
+	void (*configure_tx)(struct ethtool_mmsv *mmsv, bool tx_active);
+	void (*configure_pmac)(struct ethtool_mmsv *mmsv, bool pmac_enabled);
+	void (*send_mpacket)(struct ethtool_mmsv *mmsv, enum ethtool_mpacket mpacket);
+};
+
+/**
+ * struct ethtool_mmsv - MAC Merge Software Verification
+ * @ops: operations for MAC Merge Software Verification
+ * @dev: pointer to net_device structure
+ * @lock: serialize access to MAC Merge state between
+ *	  ethtool requests and link state updates.
+ * @status: current verification FSM state
+ * @verify_timer: timer for verification in local TX direction
+ * @verify_enabled: indicates if verification is enabled
+ * @verify_retries: number of retries for verification
+ * @pmac_enabled: indicates if the preemptible MAC is enabled
+ * @verify_time: time for verification in milliseconds
+ * @tx_enabled: indicates if transmission is enabled
+ */
+struct ethtool_mmsv {
+	const struct ethtool_mmsv_ops *ops;
+	struct net_device *dev;
+	spinlock_t lock;
+	enum ethtool_mm_verify_status status;
+	struct timer_list verify_timer;
+	bool verify_enabled;
+	int verify_retries;
+	bool pmac_enabled;
+	u32 verify_time;
+	bool tx_enabled;
+};
+
+void ethtool_mmsv_stop(struct ethtool_mmsv *mmsv);
+void ethtool_mmsv_link_state_handle(struct ethtool_mmsv *mmsv, bool up);
+void ethtool_mmsv_event_handle(struct ethtool_mmsv *mmsv,
+			       enum ethtool_mmsv_event event);
+void ethtool_mmsv_get_mm(struct ethtool_mmsv *mmsv,
+			 struct ethtool_mm_state *state);
+void ethtool_mmsv_set_mm(struct ethtool_mmsv *mmsv, struct ethtool_mm_cfg *cfg);
+void ethtool_mmsv_init(struct ethtool_mmsv *mmsv, struct net_device *dev,
+		       const struct ethtool_mmsv_ops *ops);
+
 /**
  * struct ethtool_rxfh_param - RXFH (RSS) parameters
  * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
@@ -757,6 +831,8 @@ struct ethtool_rxfh_param {
  * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags
  * @phc_index: device index of the associated PHC, or -1 if there is none
  * @phc_qualifier: qualifier of the associated PHC
+ * @phc_source: source device of the associated PHC
+ * @phc_phyindex: index of PHY device source of the associated PHC
  * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values
  * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values
  */
@@ -765,6 +841,8 @@ struct kernel_ethtool_ts_info {
 	u32 so_timestamping;
 	int phc_index;
 	enum hwtstamp_provider_qualifier phc_qualifier;
+	enum hwtstamp_source phc_source;
+	int phc_phyindex;
 	enum hwtstamp_tx_types tx_types;
 	enum hwtstamp_rx_filters rx_filters;
 };
@@ -926,10 +1004,11 @@ struct kernel_ethtool_ts_info {
  * @get_ts_info: Get the time stamping and PTP hardware clock capabilities.
  *	It may be called with RCU, or rtnl or reference on the device.
  *	Drivers supporting transmit time stamps in software should set this to
- *	ethtool_op_get_ts_info(). Drivers must not zero statistics which they
- *	don't report. The stats	structure is initialized to ETHTOOL_STAT_NOT_SET
- *	indicating driver does not report statistics.
- * @get_ts_stats: Query the device hardware timestamping statistics.
+ *	ethtool_op_get_ts_info().
+ * @get_ts_stats: Query the device hardware timestamping statistics. Drivers
+ *	must not zero statistics which they don't report. The stats structure
+ *	is initialized to ETHTOOL_STAT_NOT_SET indicating driver does not
+ *	report statistics.
  * @get_module_info: Get the size and type of the eeprom contained within
  *	a plug-in module.
  * @get_module_eeprom: Get the eeprom information from the plug-in module
@@ -1329,6 +1408,17 @@ extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...);
  */
 extern void ethtool_puts(u8 **data, const char *str);
 
+/**
+ * ethtool_cpy - Write possibly-not-NUL-terminated string to ethtool string data
+ * @data: Pointer to a pointer to the start of string to write into
+ * @str: NUL-byte padded char array of size ETH_GSTRING_LEN to copy from
+ */
+#define ethtool_cpy(data, str)	do {				\
+	BUILD_BUG_ON(sizeof(str) != ETH_GSTRING_LEN);		\
+	memcpy(*(data), str, ETH_GSTRING_LEN);			\
+	*(data) += ETH_GSTRING_LEN;				\
+} while (0)
+
 /* Link mode to forced speed capabilities maps */
 struct ethtool_forced_speed_map {
 	u32		speed;
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 65655a5d1be2..ca42d5e46ccc 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/moduleloader.h>
+#include <linux/cleanup.h>
 
 #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
 		!defined(CONFIG_KASAN_VMALLOC)
@@ -53,7 +54,7 @@ enum execmem_range_flags {
 	EXECMEM_ROX_CACHE	= (1 << 1),
 };
 
-#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX
+#if defined(CONFIG_ARCH_HAS_EXECMEM_ROX) && defined(CONFIG_EXECMEM)
 /**
  * execmem_fill_trapping_insns - set memory to contain instructions that
  *				 will trap
@@ -93,9 +94,15 @@ int execmem_make_temp_rw(void *ptr, size_t size);
  * Return: 0 on success or negative error code on failure.
  */
 int execmem_restore_rox(void *ptr, size_t size);
+
+/*
+ * Called from mark_readonly(), where the system transitions to ROX.
+ */
+void execmem_cache_make_ro(void);
 #else
 static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
 static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
+static inline void execmem_cache_make_ro(void) { }
 #endif
 
 /**
@@ -170,6 +177,8 @@ void *execmem_alloc(enum execmem_type type, size_t size);
  */
 void execmem_free(void *ptr);
 
+DEFINE_FREE(execmem, void *, if (_T) execmem_free(_T));
+
 #ifdef CONFIG_MMU
 /**
  * execmem_vmap - create virtual mapping for EXECMEM_MODULE_DATA memory
diff --git a/include/linux/file_ref.h b/include/linux/file_ref.h
index 7db62fbc0500..31551e4cb8f3 100644
--- a/include/linux/file_ref.h
+++ b/include/linux/file_ref.h
@@ -61,7 +61,6 @@ static inline void file_ref_init(file_ref_t *ref, unsigned long cnt)
 	atomic_long_set(&ref->refcnt, cnt - 1);
 }
 
-bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt);
 bool __file_ref_put(file_ref_t *ref, unsigned long cnt);
 
 /**
@@ -178,20 +177,14 @@ static __always_inline __must_check bool file_ref_put(file_ref_t *ref)
  */
 static __always_inline __must_check bool file_ref_put_close(file_ref_t *ref)
 {
-	long old, new;
+	long old;
 
 	old = atomic_long_read(&ref->refcnt);
-	do {
-		if (unlikely(old < 0))
-			return __file_ref_put_badval(ref, old);
-
-		if (old == FILE_REF_ONEREF)
-			new = FILE_REF_DEAD;
-		else
-			new = old - 1;
-	} while (!atomic_long_try_cmpxchg(&ref->refcnt, &old, new));
-
-	return new == FILE_REF_DEAD;
+	if (likely(old == FILE_REF_ONEREF)) {
+		if (likely(atomic_long_try_cmpxchg(&ref->refcnt, &old, FILE_REF_DEAD)))
+			return true;
+	}
+	return file_ref_put(ref);
 }
 
 /**
diff --git a/include/linux/firmware/cirrus/cs_dsp_test_utils.h b/include/linux/firmware/cirrus/cs_dsp_test_utils.h
index 4f87a908ab4f..ecd821ed8064 100644
--- a/include/linux/firmware/cirrus/cs_dsp_test_utils.h
+++ b/include/linux/firmware/cirrus/cs_dsp_test_utils.h
@@ -104,7 +104,6 @@ unsigned int cs_dsp_mock_num_dsp_words_to_num_packed_regs(unsigned int num_dsp_w
 unsigned int cs_dsp_mock_xm_header_get_alg_base_in_words(struct cs_dsp_test *priv,
 							 unsigned int alg_id,
 							 int mem_type);
-unsigned int cs_dsp_mock_xm_header_get_fw_version_from_regmap(struct cs_dsp_test *priv);
 unsigned int cs_dsp_mock_xm_header_get_fw_version(struct cs_dsp_mock_xm_header *header);
 void cs_dsp_mock_xm_header_drop_from_regmap_cache(struct cs_dsp_test *priv);
 int cs_dsp_mock_xm_header_write_to_regmap(struct cs_dsp_mock_xm_header *header);
diff --git a/include/linux/fsl/ntmp.h b/include/linux/fsl/ntmp.h
new file mode 100644
index 000000000000..916dc4fe7de3
--- /dev/null
+++ b/include/linux/fsl/ntmp.h
@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2025 NXP */
+#ifndef __NETC_NTMP_H
+#define __NETC_NTMP_H
+
+#include <linux/bitops.h>
+#include <linux/if_ether.h>
+
+struct maft_keye_data {
+	u8 mac_addr[ETH_ALEN];
+	__le16 resv;
+};
+
+struct maft_cfge_data {
+	__le16 si_bitmap;
+	__le16 resv;
+};
+
+struct netc_cbdr_regs {
+	void __iomem *pir;
+	void __iomem *cir;
+	void __iomem *mr;
+
+	void __iomem *bar0;
+	void __iomem *bar1;
+	void __iomem *lenr;
+};
+
+struct netc_tbl_vers {
+	u8 maft_ver;
+	u8 rsst_ver;
+};
+
+struct netc_cbdr {
+	struct device *dev;
+	struct netc_cbdr_regs regs;
+
+	int bd_num;
+	int next_to_use;
+	int next_to_clean;
+
+	int dma_size;
+	void *addr_base;
+	void *addr_base_align;
+	dma_addr_t dma_base;
+	dma_addr_t dma_base_align;
+
+	/* Serialize the order of command BD ring */
+	spinlock_t ring_lock;
+};
+
+struct ntmp_user {
+	int cbdr_num;	/* number of control BD ring */
+	struct device *dev;
+	struct netc_cbdr *ring;
+	struct netc_tbl_vers tbl;
+};
+
+struct maft_entry_data {
+	struct maft_keye_data keye;
+	struct maft_cfge_data cfge;
+};
+
+#if IS_ENABLED(CONFIG_NXP_NETC_LIB)
+int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev,
+		   const struct netc_cbdr_regs *regs);
+void ntmp_free_cbdr(struct netc_cbdr *cbdr);
+
+/* NTMP APIs */
+int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id,
+			struct maft_entry_data *maft);
+int ntmp_maft_query_entry(struct ntmp_user *user, u32 entry_id,
+			  struct maft_entry_data *maft);
+int ntmp_maft_delete_entry(struct ntmp_user *user, u32 entry_id);
+int ntmp_rsst_update_entry(struct ntmp_user *user, const u32 *table,
+			   int count);
+int ntmp_rsst_query_entry(struct ntmp_user *user,
+			  u32 *table, int count);
+#else
+static inline int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev,
+				 const struct netc_cbdr_regs *regs)
+{
+	return 0;
+}
+
+static inline void ntmp_free_cbdr(struct netc_cbdr *cbdr)
+{
+}
+
+static inline int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id,
+				      struct maft_entry_data *maft)
+{
+	return 0;
+}
+
+static inline int ntmp_maft_query_entry(struct ntmp_user *user, u32 entry_id,
+					struct maft_entry_data *maft)
+{
+	return 0;
+}
+
+static inline int ntmp_maft_delete_entry(struct ntmp_user *user, u32 entry_id)
+{
+	return 0;
+}
+
+static inline int ntmp_rsst_update_entry(struct ntmp_user *user,
+					 const u32 *table, int count)
+{
+	return 0;
+}
+
+static inline int ntmp_rsst_query_entry(struct ntmp_user *user,
+					u32 *table, int count)
+{
+	return 0;
+}
+
+#endif
+
+#endif
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 6cd8d1d28b8b..fc27b53c58c2 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -907,21 +907,6 @@ extern void fsnotify_wait_marks_destroyed(void);
 /* Clear all of the marks of a group attached to a given object type */
 extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
 					  unsigned int obj_type);
-/* run all the marks in a group, and clear all of the vfsmount marks */
-static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
-{
-	fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
-}
-/* run all the marks in a group, and clear all of the inode marks */
-static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
-{
-	fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE);
-}
-/* run all the marks in a group, and clear all of the sn marks */
-static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group)
-{
-	fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB);
-}
 extern void fsnotify_get_mark(struct fsnotify_mark *mark);
 extern void fsnotify_put_mark(struct fsnotify_mark *mark);
 extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 6fa0a268d538..097be89487bf 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -2,6 +2,11 @@
 /*
  * fwnode.h - Firmware device node object handle type definition.
  *
+ * This header file provides low-level data types and definitions for firmware
+ * and device property providers. The respective API header files supplied by
+ * them should contain all of the requisite data types and definitions for end
+ * users, so including it directly should not be necessary.
+ *
  * Copyright (C) 2015, Intel Corporation
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  */
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 1adcba3ddd76..1ef867bb8c44 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -345,7 +345,7 @@ static inline void hrtimer_update_function(struct hrtimer *timer,
 	if (WARN_ON_ONCE(!function))
 		return;
 #endif
-	timer->function = function;
+	ACCESS_PRIVATE(timer, function) = function;
 }
 
 /* Forward a hrtimer so it expires after now: */
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 675959fb97ba..b52ac40d5830 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1002,6 +1002,12 @@ struct vmbus_channel {
 
 	/* The max size of a packet on this channel */
 	u32 max_pkt_size;
+
+	/* function to mmap ring buffer memory to the channel's sysfs ring attribute */
+	int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma);
+
+	/* boolean to control visibility of sysfs for ring buffer */
+	bool ring_sysfs_visible;
 };
 
 #define lock_requestor(channel, flags)					\
@@ -1161,13 +1167,6 @@ extern int vmbus_sendpacket(struct vmbus_channel *channel,
 				  enum vmbus_packet_type type,
 				  u32 flags);
 
-extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
-					    struct hv_page_buffer pagebuffers[],
-					    u32 pagecount,
-					    void *buffer,
-					    u32 bufferlen,
-					    u64 requestid);
-
 extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 				     struct vmbus_packet_mpb_array *mpb,
 				     u32 desc_size,
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 508d466de1cc..420c7f9aa6ee 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1526,7 +1526,7 @@ struct ieee80211_mgmt {
 				struct {
 					u8 action_code;
 					u8 dialog_token;
-					u8 status_code;
+					__le16 status_code;
 					u8 variable[];
 				} __packed ttlm_res;
 				struct {
@@ -2325,6 +2325,7 @@ struct ieee80211_eht_cap_elem {
 #define IEEE80211_EHT_OPER_EHT_DEF_PE_DURATION	                0x04
 #define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_LIMIT         0x08
 #define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_EXP_MASK      0x30
+#define IEEE80211_EHT_OPER_MCS15_DISABLE                        0x40
 
 /**
  * struct ieee80211_eht_operation - eht operation element
@@ -4087,6 +4088,9 @@ enum ieee80211_tdls_actioncode {
 /* Defines support for enhanced multi-bssid advertisement*/
 #define WLAN_EXT_CAPA11_EMA_SUPPORT	BIT(3)
 
+/* Enable Beacon Protection */
+#define WLAN_EXT_CAPA11_BCN_PROTECT	BIT(4)
+
 /* TDLS specific payload type in the LLC/SNAP header */
 #define WLAN_TDLS_SNAP_RFTYPE	0x2
 
@@ -5615,6 +5619,80 @@ static inline bool ieee80211_tid_to_link_map_size_ok(const u8 *data, size_t len)
 	return len >= fixed + elem_len;
 }
 
+/**
+ * ieee80211_emlsr_pad_delay_in_us - Fetch the EMLSR Padding delay
+ *	in microseconds
+ * @eml_cap: EML capabilities field value from common info field of
+ *	the Multi-link element
+ * Return: the EMLSR Padding delay (in microseconds) encoded in the
+ *	EML Capabilities field
+ */
+
+static inline u32 ieee80211_emlsr_pad_delay_in_us(u16 eml_cap)
+{
+	/* IEEE Std 802.11be-2024 Table 9-417i—Encoding of the EMLSR
+	 * Padding Delay subfield.
+	 */
+	u32 pad_delay = u16_get_bits(eml_cap,
+				     IEEE80211_EML_CAP_EMLSR_PADDING_DELAY);
+
+	if (!pad_delay ||
+	    pad_delay > IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US)
+		return 0;
+
+	return 32 * (1 << (pad_delay - 1));
+}
+
+/**
+ * ieee80211_emlsr_trans_delay_in_us - Fetch the EMLSR Transition
+ *	delay in microseconds
+ * @eml_cap: EML capabilities field value from common info field of
+ *	the Multi-link element
+ * Return: the EMLSR Transition delay (in microseconds) encoded in the
+ *	EML Capabilities field
+ */
+
+static inline u32 ieee80211_emlsr_trans_delay_in_us(u16 eml_cap)
+{
+	/* IEEE Std 802.11be-2024 Table 9-417j—Encoding of the EMLSR
+	 * Transition Delay subfield.
+	 */
+	u32 trans_delay =
+		u16_get_bits(eml_cap,
+			     IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY);
+
+	/* invalid values also just use 0 */
+	if (!trans_delay ||
+	    trans_delay > IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US)
+		return 0;
+
+	return 16 * (1 << (trans_delay - 1));
+}
+
+/**
+ * ieee80211_eml_trans_timeout_in_us - Fetch the EMLSR Transition
+ *	timeout value in microseconds
+ * @eml_cap: EML capabilities field value from common info field of
+ *	the Multi-link element
+ * Return: the EMLSR Transition timeout (in microseconds) encoded in
+ *	the EML Capabilities field
+ */
+
+static inline u32 ieee80211_eml_trans_timeout_in_us(u16 eml_cap)
+{
+	/* IEEE Std 802.11be-2024 Table 9-417m—Encoding of the
+	 * Transition Timeout subfield.
+	 */
+	u8 timeout = u16_get_bits(eml_cap,
+				  IEEE80211_EML_CAP_TRANSITION_TIMEOUT);
+
+	/* invalid values also just use 0 */
+	if (!timeout || timeout > IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU)
+		return 0;
+
+	return 128 * (1 << (timeout - 1));
+}
+
 #define for_each_mle_subelement(_elem, _data, _len)			\
 	if (ieee80211_mle_size_ok(_data, _len))				\
 		for_each_element(_elem,					\
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ccce8a751e2a..3a8d35d41fda 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -440,10 +440,10 @@ static inline int __iommu_copy_struct_from_user(
 	void *dst_data, const struct iommu_user_data *src_data,
 	unsigned int data_type, size_t data_len, size_t min_len)
 {
-	if (src_data->type != data_type)
-		return -EINVAL;
 	if (WARN_ON(!dst_data || !src_data))
 		return -EINVAL;
+	if (src_data->type != data_type)
+		return -EINVAL;
 	if (src_data->len < min_len || data_len < src_data->len)
 		return -EINVAL;
 	return copy_struct_from_user(dst_data, data_len, src_data->uptr,
@@ -456,8 +456,8 @@ static inline int __iommu_copy_struct_from_user(
  *        include/uapi/linux/iommufd.h
  * @user_data: Pointer to a struct iommu_user_data for user space data info
  * @data_type: The data type of the @kdst. Must match with @user_data->type
- * @min_last: The last memember of the data structure @kdst points in the
- *            initial version.
+ * @min_last: The last member of the data structure @kdst points in the initial
+ *            version.
  * Return 0 for success, otherwise -error.
  */
 #define iommu_copy_struct_from_user(kdst, user_data, data_type, min_last) \
diff --git a/include/linux/irqchip/irq-davinci-aintc.h b/include/linux/irqchip/irq-davinci-aintc.h
deleted file mode 100644
index ea4e087fac98..000000000000
--- a/include/linux/irqchip/irq-davinci-aintc.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2019 Texas Instruments
- */
-
-#ifndef _LINUX_IRQ_DAVINCI_AINTC_
-#define _LINUX_IRQ_DAVINCI_AINTC_
-
-#include <linux/ioport.h>
-
-/**
- * struct davinci_aintc_config - configuration data for davinci-aintc driver.
- *
- * @reg: register range to map
- * @num_irqs: number of HW interrupts supported by the controller
- * @prios: an array of size num_irqs containing priority settings for
- *         each interrupt
- */
-struct davinci_aintc_config {
-	struct resource reg;
-	unsigned int num_irqs;
-	u8 *prios;
-};
-
-void davinci_aintc_init(const struct davinci_aintc_config *config);
-
-#endif /* _LINUX_IRQ_DAVINCI_AINTC_ */
diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h
index 1a0bc35839e3..16a2ee4f8310 100644
--- a/include/linux/local_lock.h
+++ b/include/linux/local_lock.h
@@ -52,44 +52,23 @@
 	__local_unlock_irqrestore(lock, flags)
 
 /**
- * localtry_lock_init - Runtime initialize a lock instance
- */
-#define localtry_lock_init(lock)		__localtry_lock_init(lock)
-
-/**
- * localtry_lock - Acquire a per CPU local lock
- * @lock:	The lock variable
- */
-#define localtry_lock(lock)		__localtry_lock(lock)
-
-/**
- * localtry_lock_irq - Acquire a per CPU local lock and disable interrupts
- * @lock:	The lock variable
- */
-#define localtry_lock_irq(lock)		__localtry_lock_irq(lock)
-
-/**
- * localtry_lock_irqsave - Acquire a per CPU local lock, save and disable
- *			 interrupts
- * @lock:	The lock variable
- * @flags:	Storage for interrupt flags
+ * local_lock_init - Runtime initialize a lock instance
  */
-#define localtry_lock_irqsave(lock, flags)				\
-	__localtry_lock_irqsave(lock, flags)
+#define local_trylock_init(lock)	__local_trylock_init(lock)
 
 /**
- * localtry_trylock - Try to acquire a per CPU local lock.
+ * local_trylock - Try to acquire a per CPU local lock
  * @lock:	The lock variable
  *
  * The function can be used in any context such as NMI or HARDIRQ. Due to
  * locking constrains it will _always_ fail to acquire the lock in NMI or
  * HARDIRQ context on PREEMPT_RT.
  */
-#define localtry_trylock(lock)		__localtry_trylock(lock)
+#define local_trylock(lock)		__local_trylock(lock)
 
 /**
- * localtry_trylock_irqsave - Try to acquire a per CPU local lock, save and disable
- *			      interrupts if acquired
+ * local_trylock_irqsave - Try to acquire a per CPU local lock, save and disable
+ *			   interrupts if acquired
  * @lock:	The lock variable
  * @flags:	Storage for interrupt flags
  *
@@ -97,29 +76,8 @@
  * locking constrains it will _always_ fail to acquire the lock in NMI or
  * HARDIRQ context on PREEMPT_RT.
  */
-#define localtry_trylock_irqsave(lock, flags)				\
-	__localtry_trylock_irqsave(lock, flags)
-
-/**
- * local_unlock - Release a per CPU local lock
- * @lock:	The lock variable
- */
-#define localtry_unlock(lock)		__localtry_unlock(lock)
-
-/**
- * local_unlock_irq - Release a per CPU local lock and enable interrupts
- * @lock:	The lock variable
- */
-#define localtry_unlock_irq(lock)		__localtry_unlock_irq(lock)
-
-/**
- * localtry_unlock_irqrestore - Release a per CPU local lock and restore
- *			      interrupt flags
- * @lock:	The lock variable
- * @flags:      Interrupt flags to restore
- */
-#define localtry_unlock_irqrestore(lock, flags)			\
-	__localtry_unlock_irqrestore(lock, flags)
+#define local_trylock_irqsave(lock, flags)			\
+	__local_trylock_irqsave(lock, flags)
 
 DEFINE_GUARD(local_lock, local_lock_t __percpu*,
 	     local_lock(_T),
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index 67bd13d142fa..8d5ac16a9b17 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -15,10 +15,11 @@ typedef struct {
 #endif
 } local_lock_t;
 
+/* local_trylock() and local_trylock_irqsave() only work with local_trylock_t */
 typedef struct {
 	local_lock_t	llock;
-	unsigned int	acquired;
-} localtry_lock_t;
+	u8		acquired;
+} local_trylock_t;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define LOCAL_LOCK_DEBUG_INIT(lockname)		\
@@ -29,6 +30,9 @@ typedef struct {
 	},						\
 	.owner = NULL,
 
+# define LOCAL_TRYLOCK_DEBUG_INIT(lockname)		\
+	.llock = { LOCAL_LOCK_DEBUG_INIT((lockname).llock) },
+
 static inline void local_lock_acquire(local_lock_t *l)
 {
 	lock_map_acquire(&l->dep_map);
@@ -56,6 +60,7 @@ static inline void local_lock_debug_init(local_lock_t *l)
 }
 #else /* CONFIG_DEBUG_LOCK_ALLOC */
 # define LOCAL_LOCK_DEBUG_INIT(lockname)
+# define LOCAL_TRYLOCK_DEBUG_INIT(lockname)
 static inline void local_lock_acquire(local_lock_t *l) { }
 static inline void local_trylock_acquire(local_lock_t *l) { }
 static inline void local_lock_release(local_lock_t *l) { }
@@ -63,7 +68,7 @@ static inline void local_lock_debug_init(local_lock_t *l) { }
 #endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
 #define INIT_LOCAL_LOCK(lockname)	{ LOCAL_LOCK_DEBUG_INIT(lockname) }
-#define INIT_LOCALTRY_LOCK(lockname)	{ .llock = { LOCAL_LOCK_DEBUG_INIT(lockname.llock) }}
+#define INIT_LOCAL_TRYLOCK(lockname)	{ LOCAL_TRYLOCK_DEBUG_INIT(lockname) }
 
 #define __local_lock_init(lock)					\
 do {								\
@@ -76,6 +81,8 @@ do {								\
 	local_lock_debug_init(lock);				\
 } while (0)
 
+#define __local_trylock_init(lock) __local_lock_init(lock.llock)
+
 #define __spinlock_nested_bh_init(lock)				\
 do {								\
 	static struct lock_class_key __key;			\
@@ -87,149 +94,117 @@ do {								\
 	local_lock_debug_init(lock);				\
 } while (0)
 
+#define __local_lock_acquire(lock)					\
+	do {								\
+		local_trylock_t *tl;					\
+		local_lock_t *l;					\
+									\
+		l = (local_lock_t *)this_cpu_ptr(lock);			\
+		tl = (local_trylock_t *)l;				\
+		_Generic((lock),					\
+			__percpu local_trylock_t *: ({			\
+				lockdep_assert(tl->acquired == 0);	\
+				WRITE_ONCE(tl->acquired, 1);		\
+			}),						\
+			__percpu local_lock_t *: (void)0);		\
+		local_lock_acquire(l);					\
+	} while (0)
+
 #define __local_lock(lock)					\
 	do {							\
 		preempt_disable();				\
-		local_lock_acquire(this_cpu_ptr(lock));		\
+		__local_lock_acquire(lock);			\
 	} while (0)
 
 #define __local_lock_irq(lock)					\
 	do {							\
 		local_irq_disable();				\
-		local_lock_acquire(this_cpu_ptr(lock));		\
+		__local_lock_acquire(lock);			\
 	} while (0)
 
 #define __local_lock_irqsave(lock, flags)			\
 	do {							\
 		local_irq_save(flags);				\
-		local_lock_acquire(this_cpu_ptr(lock));		\
-	} while (0)
-
-#define __local_unlock(lock)					\
-	do {							\
-		local_lock_release(this_cpu_ptr(lock));		\
-		preempt_enable();				\
+		__local_lock_acquire(lock);			\
 	} while (0)
 
-#define __local_unlock_irq(lock)				\
-	do {							\
-		local_lock_release(this_cpu_ptr(lock));		\
-		local_irq_enable();				\
-	} while (0)
-
-#define __local_unlock_irqrestore(lock, flags)			\
-	do {							\
-		local_lock_release(this_cpu_ptr(lock));		\
-		local_irq_restore(flags);			\
-	} while (0)
-
-#define __local_lock_nested_bh(lock)				\
-	do {							\
-		lockdep_assert_in_softirq();			\
-		local_lock_acquire(this_cpu_ptr(lock));	\
-	} while (0)
-
-#define __local_unlock_nested_bh(lock)				\
-	local_lock_release(this_cpu_ptr(lock))
-
-/* localtry_lock_t variants */
-
-#define __localtry_lock_init(lock)				\
-do {								\
-	__local_lock_init(&(lock)->llock);			\
-	WRITE_ONCE((lock)->acquired, 0);			\
-} while (0)
-
-#define __localtry_lock(lock)					\
-	do {							\
-		localtry_lock_t *lt;				\
-		preempt_disable();				\
-		lt = this_cpu_ptr(lock);			\
-		local_lock_acquire(&lt->llock);			\
-		WRITE_ONCE(lt->acquired, 1);			\
-	} while (0)
-
-#define __localtry_lock_irq(lock)				\
-	do {							\
-		localtry_lock_t *lt;				\
-		local_irq_disable();				\
-		lt = this_cpu_ptr(lock);			\
-		local_lock_acquire(&lt->llock);			\
-		WRITE_ONCE(lt->acquired, 1);			\
-	} while (0)
-
-#define __localtry_lock_irqsave(lock, flags)			\
-	do {							\
-		localtry_lock_t *lt;				\
-		local_irq_save(flags);				\
-		lt = this_cpu_ptr(lock);			\
-		local_lock_acquire(&lt->llock);			\
-		WRITE_ONCE(lt->acquired, 1);			\
-	} while (0)
-
-#define __localtry_trylock(lock)				\
+#define __local_trylock(lock)					\
 	({							\
-		localtry_lock_t *lt;				\
-		bool _ret;					\
+		local_trylock_t *tl;				\
 								\
 		preempt_disable();				\
-		lt = this_cpu_ptr(lock);			\
-		if (!READ_ONCE(lt->acquired)) {			\
-			WRITE_ONCE(lt->acquired, 1);		\
-			local_trylock_acquire(&lt->llock);	\
-			_ret = true;				\
-		} else {					\
-			_ret = false;				\
+		tl = this_cpu_ptr(lock);			\
+		if (READ_ONCE(tl->acquired)) {			\
 			preempt_enable();			\
+			tl = NULL;				\
+		} else {					\
+			WRITE_ONCE(tl->acquired, 1);		\
+			local_trylock_acquire(			\
+				(local_lock_t *)tl);		\
 		}						\
-		_ret;						\
+		!!tl;						\
 	})
 
-#define __localtry_trylock_irqsave(lock, flags)			\
+#define __local_trylock_irqsave(lock, flags)			\
 	({							\
-		localtry_lock_t *lt;				\
-		bool _ret;					\
+		local_trylock_t *tl;				\
 								\
 		local_irq_save(flags);				\
-		lt = this_cpu_ptr(lock);			\
-		if (!READ_ONCE(lt->acquired)) {			\
-			WRITE_ONCE(lt->acquired, 1);		\
-			local_trylock_acquire(&lt->llock);	\
-			_ret = true;				\
-		} else {					\
-			_ret = false;				\
+		tl = this_cpu_ptr(lock);			\
+		if (READ_ONCE(tl->acquired)) {			\
 			local_irq_restore(flags);		\
+			tl = NULL;				\
+		} else {					\
+			WRITE_ONCE(tl->acquired, 1);		\
+			local_trylock_acquire(			\
+				(local_lock_t *)tl);		\
 		}						\
-		_ret;						\
+		!!tl;						\
 	})
 
-#define __localtry_unlock(lock)					\
+#define __local_lock_release(lock)					\
+	do {								\
+		local_trylock_t *tl;					\
+		local_lock_t *l;					\
+									\
+		l = (local_lock_t *)this_cpu_ptr(lock);			\
+		tl = (local_trylock_t *)l;				\
+		local_lock_release(l);					\
+		_Generic((lock),					\
+			__percpu local_trylock_t *: ({			\
+				lockdep_assert(tl->acquired == 1);	\
+				WRITE_ONCE(tl->acquired, 0);		\
+			}),						\
+			__percpu local_lock_t *: (void)0);		\
+	} while (0)
+
+#define __local_unlock(lock)					\
 	do {							\
-		localtry_lock_t *lt;				\
-		lt = this_cpu_ptr(lock);			\
-		WRITE_ONCE(lt->acquired, 0);			\
-		local_lock_release(&lt->llock);			\
+		__local_lock_release(lock);			\
 		preempt_enable();				\
 	} while (0)
 
-#define __localtry_unlock_irq(lock)				\
+#define __local_unlock_irq(lock)				\
 	do {							\
-		localtry_lock_t *lt;				\
-		lt = this_cpu_ptr(lock);			\
-		WRITE_ONCE(lt->acquired, 0);			\
-		local_lock_release(&lt->llock);			\
+		__local_lock_release(lock);			\
 		local_irq_enable();				\
 	} while (0)
 
-#define __localtry_unlock_irqrestore(lock, flags)		\
+#define __local_unlock_irqrestore(lock, flags)			\
 	do {							\
-		localtry_lock_t *lt;				\
-		lt = this_cpu_ptr(lock);			\
-		WRITE_ONCE(lt->acquired, 0);			\
-		local_lock_release(&lt->llock);			\
+		__local_lock_release(lock);			\
 		local_irq_restore(flags);			\
 	} while (0)
 
+#define __local_lock_nested_bh(lock)				\
+	do {							\
+		lockdep_assert_in_softirq();			\
+		local_lock_acquire(this_cpu_ptr(lock));	\
+	} while (0)
+
+#define __local_unlock_nested_bh(lock)				\
+	local_lock_release(this_cpu_ptr(lock))
+
 #else /* !CONFIG_PREEMPT_RT */
 
 /*
@@ -237,16 +212,18 @@ do {								\
  * critical section while staying preemptible.
  */
 typedef spinlock_t local_lock_t;
-typedef spinlock_t localtry_lock_t;
+typedef spinlock_t local_trylock_t;
 
 #define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname))
-#define INIT_LOCALTRY_LOCK(lockname) INIT_LOCAL_LOCK(lockname)
+#define INIT_LOCAL_TRYLOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname))
 
 #define __local_lock_init(l)					\
 	do {							\
 		local_spin_lock_init((l));			\
 	} while (0)
 
+#define __local_trylock_init(l)			__local_lock_init(l)
+
 #define __local_lock(__lock)					\
 	do {							\
 		migrate_disable();				\
@@ -283,17 +260,7 @@ do {								\
 	spin_unlock(this_cpu_ptr((lock)));			\
 } while (0)
 
-/* localtry_lock_t variants */
-
-#define __localtry_lock_init(lock)			__local_lock_init(lock)
-#define __localtry_lock(lock)				__local_lock(lock)
-#define __localtry_lock_irq(lock)			__local_lock(lock)
-#define __localtry_lock_irqsave(lock, flags)		__local_lock_irqsave(lock, flags)
-#define __localtry_unlock(lock)				__local_unlock(lock)
-#define __localtry_unlock_irq(lock)			__local_unlock(lock)
-#define __localtry_unlock_irqrestore(lock, flags)	__local_unlock_irqrestore(lock, flags)
-
-#define __localtry_trylock(lock)				\
+#define __local_trylock(lock)					\
 	({							\
 		int __locked;					\
 								\
@@ -308,11 +275,11 @@ do {								\
 		__locked;					\
 	})
 
-#define __localtry_trylock_irqsave(lock, flags)			\
+#define __local_trylock_irqsave(lock, flags)			\
 	({							\
 		typecheck(unsigned long, flags);		\
 		flags = 0;					\
-		__localtry_trylock(lock);			\
+		__local_trylock(lock);				\
 	})
 
 #endif /* CONFIG_PREEMPT_RT */
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 591bf5b5e8dc..9af01bdd86d2 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -44,7 +44,6 @@
 #define MICREL_PHY_50MHZ_CLK	BIT(0)
 #define MICREL_PHY_FXEN		BIT(1)
 #define MICREL_KSZ8_P1_ERRATA	BIT(2)
-#define MICREL_NO_EEE		BIT(3)
 
 #define MICREL_KSZ9021_EXTREG_CTRL	0xB
 #define MICREL_KSZ9021_EXTREG_DATA_WRITE	0xC
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b7f13f087954..8dc012e84033 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1218,6 +1218,23 @@ static inline unsigned int folio_order(const struct folio *folio)
 	return folio_large_order(folio);
 }
 
+/**
+ * folio_reset_order - Reset the folio order and derived _nr_pages
+ * @folio: The folio.
+ *
+ * Reset the order and derived _nr_pages to 0. Must only be used in the
+ * process of splitting large folios.
+ */
+static inline void folio_reset_order(struct folio *folio)
+{
+	if (WARN_ON_ONCE(!folio_test_large(folio)))
+		return;
+	folio->_flags_1 &= ~0xffUL;
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+	folio->_nr_pages = 0;
+#endif
+}
+
 #include <linux/huge_mm.h>
 
 /*
@@ -4248,4 +4265,62 @@ int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
 #define VM_SEALED_SYSMAP	VM_NONE
 #endif
 
+/*
+ * DMA mapping IDs for page_pool
+ *
+ * When DMA-mapping a page, page_pool allocates an ID (from an xarray) and
+ * stashes it in the upper bits of page->pp_magic. We always want to be able to
+ * unambiguously identify page pool pages (using page_pool_page_is_pp()). Non-PP
+ * pages can have arbitrary kernel pointers stored in the same field as pp_magic
+ * (since it overlaps with page->lru.next), so we must ensure that we cannot
+ * mistake a valid kernel pointer with any of the values we write into this
+ * field.
+ *
+ * On architectures that set POISON_POINTER_DELTA, this is already ensured,
+ * since this value becomes part of PP_SIGNATURE; meaning we can just use the
+ * space between the PP_SIGNATURE value (without POISON_POINTER_DELTA), and the
+ * lowest bits of POISON_POINTER_DELTA. On arches where POISON_POINTER_DELTA is
+ * 0, we make sure that we leave the two topmost bits empty, as that guarantees
+ * we won't mistake a valid kernel pointer for a value we set, regardless of the
+ * VMSPLIT setting.
+ *
+ * Altogether, this means that the number of bits available is constrained by
+ * the size of an unsigned long (at the upper end, subtracting two bits per the
+ * above), and the definition of PP_SIGNATURE (with or without
+ * POISON_POINTER_DELTA).
+ */
+#define PP_DMA_INDEX_SHIFT (1 + __fls(PP_SIGNATURE - POISON_POINTER_DELTA))
+#if POISON_POINTER_DELTA > 0
+/* PP_SIGNATURE includes POISON_POINTER_DELTA, so limit the size of the DMA
+ * index to not overlap with that if set
+ */
+#define PP_DMA_INDEX_BITS MIN(32, __ffs(POISON_POINTER_DELTA) - PP_DMA_INDEX_SHIFT)
+#else
+/* Always leave out the topmost two; see above. */
+#define PP_DMA_INDEX_BITS MIN(32, BITS_PER_LONG - PP_DMA_INDEX_SHIFT - 2)
+#endif
+
+#define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \
+				  PP_DMA_INDEX_SHIFT)
+
+/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
+ * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
+ * the head page of compound page and bit 1 for pfmemalloc page, as well as the
+ * bits used for the DMA index. page_is_pfmemalloc() is checked in
+ * __page_pool_put_page() to avoid recycling the pfmemalloc page.
+ */
+#define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL)
+
+#ifdef CONFIG_PAGE_POOL
+static inline bool page_pool_page_is_pp(struct page *page)
+{
+	return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE;
+}
+#else
+static inline bool page_pool_page_is_pp(struct page *page)
+{
+	return false;
+}
+#endif
+
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 25e80b2ca7f4..6ccec1bf2896 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -967,6 +967,9 @@ struct zone {
 #ifdef CONFIG_UNACCEPTED_MEMORY
 	/* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */
 	struct list_head	unaccepted_pages;
+
+	/* To be called once the last page in the zone is accepted */
+	struct work_struct	unaccepted_cleanup;
 #endif
 
 	/* zone flags, see below */
@@ -1499,8 +1502,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 bool zone_watermark_ok(struct zone *z, unsigned int order,
 		unsigned long mark, int highest_zoneidx,
 		unsigned int alloc_flags);
-bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
-		unsigned long mark, int highest_zoneidx);
 /*
  * Memory initialization context, use to differentiate memory added by
  * the platform statically or via memory hotplug interface.
diff --git a/include/linux/module.h b/include/linux/module.h
index d94b196d5a34..8050f77c3b64 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -162,6 +162,8 @@ extern void cleanup_module(void);
 #define __INITRODATA_OR_MODULE __INITRODATA
 #endif /*CONFIG_MODULES*/
 
+struct module_kobject *lookup_or_create_module_kobject(const char *name);
+
 /* Generic info of form tag = "info" */
 #define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info)
 
@@ -584,6 +586,11 @@ struct module {
 	atomic_t refcnt;
 #endif
 
+#ifdef CONFIG_MITIGATION_ITS
+	int its_num_pages;
+	void **its_page_array;
+#endif
+
 #ifdef CONFIG_CONSTRUCTORS
 	/* Constructor functions. */
 	ctor_fn_t *ctors;
diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h
index 58a2401e4b55..0075f6e5c3da 100644
--- a/include/linux/mroute_base.h
+++ b/include/linux/mroute_base.h
@@ -262,6 +262,11 @@ struct mr_table {
 	int			mroute_reg_vif_num;
 };
 
+static inline bool mr_can_free_table(struct net *net)
+{
+	return !check_net(net) || !net_initialized(net);
+}
+
 #ifdef CONFIG_IP_MROUTE_COMMON
 void vif_device_init(struct vif_device *v,
 		     struct net_device *dev,
diff --git a/include/linux/namei.h b/include/linux/namei.h
index e3042176cdf4..bbaf55fb3101 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -62,6 +62,7 @@ extern struct dentry *kern_path_create(int, const char *, struct path *, unsigne
 extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int);
 extern void done_path_create(struct path *, struct dentry *);
 extern struct dentry *kern_path_locked(const char *, struct path *);
+extern struct dentry *kern_path_locked_negative(const char *, struct path *);
 extern struct dentry *user_path_locked_at(int , const char __user *, struct path *);
 int vfs_path_parent_lookup(struct filename *filename, unsigned int flags,
 			   struct path *parent, struct qstr *last, int *type,
diff --git a/include/linux/net.h b/include/linux/net.h
index 0ff950eecc6b..f8418d6e33e0 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -36,14 +36,13 @@ struct net;
  * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected.
  * Eventually all flags will be in sk->sk_wq->flags.
  */
-#define SOCKWQ_ASYNC_NOSPACE	0
-#define SOCKWQ_ASYNC_WAITDATA	1
-#define SOCK_NOSPACE		2
-#define SOCK_PASSCRED		3
-#define SOCK_PASSSEC		4
-#define SOCK_SUPPORT_ZC		5
-#define SOCK_CUSTOM_SOCKOPT	6
-#define SOCK_PASSPIDFD		7
+enum socket_flags {
+	SOCKWQ_ASYNC_NOSPACE,
+	SOCKWQ_ASYNC_WAITDATA,
+	SOCK_NOSPACE,
+	SOCK_SUPPORT_ZC,
+	SOCK_CUSTOM_SOCKOPT,
+};
 
 #ifndef ARCH_HAS_SOCKET_TYPES
 /**
diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h
deleted file mode 100644
index 13274c3def66..000000000000
--- a/include/linux/net/intel/iidc.h
+++ /dev/null
@@ -1,109 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2021, Intel Corporation. */
-
-#ifndef _IIDC_H_
-#define _IIDC_H_
-
-#include <linux/auxiliary_bus.h>
-#include <linux/dcbnl.h>
-#include <linux/device.h>
-#include <linux/if_ether.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
-
-enum iidc_event_type {
-	IIDC_EVENT_BEFORE_MTU_CHANGE,
-	IIDC_EVENT_AFTER_MTU_CHANGE,
-	IIDC_EVENT_BEFORE_TC_CHANGE,
-	IIDC_EVENT_AFTER_TC_CHANGE,
-	IIDC_EVENT_CRIT_ERR,
-	IIDC_EVENT_NBITS		/* must be last */
-};
-
-enum iidc_reset_type {
-	IIDC_PFR,
-	IIDC_CORER,
-	IIDC_GLOBR,
-};
-
-enum iidc_rdma_protocol {
-	IIDC_RDMA_PROTOCOL_IWARP = BIT(0),
-	IIDC_RDMA_PROTOCOL_ROCEV2 = BIT(1),
-};
-
-#define IIDC_MAX_USER_PRIORITY		8
-#define IIDC_MAX_DSCP_MAPPING		64
-#define IIDC_DSCP_PFC_MODE		0x1
-
-/* Struct to hold per RDMA Qset info */
-struct iidc_rdma_qset_params {
-	/* Qset TEID returned to the RDMA driver in
-	 * ice_add_rdma_qset and used by RDMA driver
-	 * for calls to ice_del_rdma_qset
-	 */
-	u32 teid;	/* Qset TEID */
-	u16 qs_handle; /* RDMA driver provides this */
-	u16 vport_id; /* VSI index */
-	u8 tc; /* TC branch the Qset should belong to */
-};
-
-struct iidc_qos_info {
-	u64 tc_ctx;
-	u8 rel_bw;
-	u8 prio_type;
-	u8 egress_virt_up;
-	u8 ingress_virt_up;
-};
-
-/* Struct to pass QoS info */
-struct iidc_qos_params {
-	struct iidc_qos_info tc_info[IEEE_8021QAZ_MAX_TCS];
-	u8 up2tc[IIDC_MAX_USER_PRIORITY];
-	u8 vport_relative_bw;
-	u8 vport_priority_type;
-	u8 num_tc;
-	u8 pfc_mode;
-	u8 dscp_map[IIDC_MAX_DSCP_MAPPING];
-};
-
-struct iidc_event {
-	DECLARE_BITMAP(type, IIDC_EVENT_NBITS);
-	u32 reg;
-};
-
-struct ice_pf;
-
-int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset);
-int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset);
-int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type);
-int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable);
-void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos);
-int ice_alloc_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry);
-void ice_free_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry);
-
-/* Structure representing auxiliary driver tailored information about the core
- * PCI dev, each auxiliary driver using the IIDC interface will have an
- * instance of this struct dedicated to it.
- */
-
-struct iidc_auxiliary_dev {
-	struct auxiliary_device adev;
-	struct ice_pf *pf;
-};
-
-/* structure representing the auxiliary driver. This struct is to be
- * allocated and populated by the auxiliary driver's owner. The core PCI
- * driver will access these ops by performing a container_of on the
- * auxiliary_device->dev.driver.
- */
-struct iidc_auxiliary_drv {
-	struct auxiliary_driver adrv;
-	/* This event_handler is meant to be a blocking call.  For instance,
-	 * when a BEFORE_MTU_CHANGE event comes in, the event_handler will not
-	 * return until the auxiliary driver is ready for the MTU change to
-	 * happen.
-	 */
-	void (*event_handler)(struct ice_pf *pf, struct iidc_event *event);
-};
-
-#endif /* _IIDC_H_*/
diff --git a/include/linux/net/intel/iidc_rdma.h b/include/linux/net/intel/iidc_rdma.h
new file mode 100644
index 000000000000..8baad1082042
--- /dev/null
+++ b/include/linux/net/intel/iidc_rdma.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Intel Corporation. */
+
+#ifndef _IIDC_RDMA_H_
+#define _IIDC_RDMA_H_
+
+#include <linux/auxiliary_bus.h>
+#include <linux/device.h>
+#include <linux/if_ether.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <net/dscp.h>
+
+enum iidc_rdma_event_type {
+	IIDC_RDMA_EVENT_BEFORE_MTU_CHANGE,
+	IIDC_RDMA_EVENT_AFTER_MTU_CHANGE,
+	IIDC_RDMA_EVENT_BEFORE_TC_CHANGE,
+	IIDC_RDMA_EVENT_AFTER_TC_CHANGE,
+	IIDC_RDMA_EVENT_WARN_RESET,
+	IIDC_RDMA_EVENT_CRIT_ERR,
+	IIDC_RDMA_EVENT_NBITS		/* must be last */
+};
+
+struct iidc_rdma_event {
+	DECLARE_BITMAP(type, IIDC_RDMA_EVENT_NBITS);
+	u32 reg;
+};
+
+enum iidc_rdma_reset_type {
+	IIDC_FUNC_RESET,
+	IIDC_DEV_RESET,
+};
+
+enum iidc_rdma_protocol {
+	IIDC_RDMA_PROTOCOL_IWARP = BIT(0),
+	IIDC_RDMA_PROTOCOL_ROCEV2 = BIT(1),
+};
+
+/* Structure to be populated by core LAN PCI driver */
+struct iidc_rdma_core_dev_info {
+	struct pci_dev *pdev; /* PCI device of corresponding to main function */
+	struct auxiliary_device *adev;
+	/* Current active RDMA protocol */
+	enum iidc_rdma_protocol rdma_protocol;
+	void *iidc_priv; /* elements unique to each driver */
+};
+
+/* Structure representing auxiliary driver tailored information about the core
+ * PCI dev, each auxiliary driver using the IIDC interface will have an
+ * instance of this struct dedicated to it.
+ */
+struct iidc_rdma_core_auxiliary_dev {
+	struct auxiliary_device adev;
+	struct iidc_rdma_core_dev_info *cdev_info;
+};
+
+/* structure representing the auxiliary driver. This struct is to be
+ * allocated and populated by the auxiliary driver's owner. The core PCI
+ * driver will access these ops by performing a container_of on the
+ * auxiliary_device->dev.driver.
+ */
+struct iidc_rdma_core_auxiliary_drv {
+	struct auxiliary_driver adrv;
+	void (*event_handler)(struct iidc_rdma_core_dev_info *cdev,
+			      struct iidc_rdma_event *event);
+};
+
+#endif /* _IIDC_RDMA_H_*/
diff --git a/include/linux/net/intel/iidc_rdma_ice.h b/include/linux/net/intel/iidc_rdma_ice.h
new file mode 100644
index 000000000000..b40eed0e13fe
--- /dev/null
+++ b/include/linux/net/intel/iidc_rdma_ice.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Intel Corporation. */
+
+#ifndef _IIDC_RDMA_ICE_H_
+#define _IIDC_RDMA_ICE_H_
+
+#include <linux/dcbnl.h>
+
+#define IIDC_MAX_USER_PRIORITY         8
+#define IIDC_DSCP_PFC_MODE             0x1
+
+/**
+ * struct iidc_rdma_qset_params - Struct to hold per RDMA Qset info
+ * @teid: TEID of the Qset node
+ * @qs_handle: SW index of the Qset, RDMA provides this
+ * @vport_id: VSI index
+ * @tc: Traffic Class branch the QSet should belong to
+ */
+struct iidc_rdma_qset_params {
+	/* Qset TEID returned to the RDMA driver in
+	 * ice_add_rdma_qset and used by RDMA driver
+	 * for calls to ice_del_rdma_qset
+	 */
+	u32 teid;
+	u16 qs_handle;
+	u16 vport_id;
+	u8 tc;
+};
+
+struct iidc_rdma_qos_info {
+	u64 tc_ctx;
+	u8 rel_bw;
+	u8 prio_type;
+	u8 egress_virt_up;
+	u8 ingress_virt_up;
+};
+
+/* Struct to pass QoS info */
+struct iidc_rdma_qos_params {
+	struct iidc_rdma_qos_info tc_info[IEEE_8021QAZ_MAX_TCS];
+	u8 up2tc[IIDC_MAX_USER_PRIORITY];
+	u8 vport_relative_bw;
+	u8 vport_priority_type;
+	u8 num_tc;
+	u8 pfc_mode;
+	u8 dscp_map[DSCP_MAX];
+};
+
+struct iidc_rdma_priv_dev_info {
+	u8 pf_id;
+	u16 vport_id;
+	struct net_device *netdev;
+	struct iidc_rdma_qos_params qos_info;
+	u8 __iomem *hw_addr;
+};
+
+int ice_add_rdma_qset(struct iidc_rdma_core_dev_info *cdev,
+		      struct iidc_rdma_qset_params *qset);
+int ice_del_rdma_qset(struct iidc_rdma_core_dev_info *cdev,
+		      struct iidc_rdma_qset_params *qset);
+int ice_rdma_request_reset(struct iidc_rdma_core_dev_info *cdev,
+			   enum iidc_rdma_reset_type reset_type);
+int ice_rdma_update_vsi_filter(struct iidc_rdma_core_dev_info *cdev, u16 vsi_id,
+			       bool enable);
+int ice_alloc_rdma_qvector(struct iidc_rdma_core_dev_info *cdev,
+			   struct msix_entry *entry);
+void ice_free_rdma_qvector(struct iidc_rdma_core_dev_info *cdev,
+			   struct msix_entry *entry);
+
+#endif /* _IIDC_RDMA_ICE_H_*/
diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h
index ff0758e88ea1..f4936d9c2b3c 100644
--- a/include/linux/net_tstamp.h
+++ b/include/linux/net_tstamp.h
@@ -4,6 +4,7 @@
 #define _LINUX_NET_TIMESTAMPING_H_
 
 #include <uapi/linux/net_tstamp.h>
+#include <uapi/linux/ethtool_netlink_generated.h>
 
 #define SOF_TIMESTAMPING_SOFTWARE_MASK	(SOF_TIMESTAMPING_RX_SOFTWARE | \
 					 SOF_TIMESTAMPING_TX_SOFTWARE | \
@@ -13,12 +14,6 @@
 					 SOF_TIMESTAMPING_TX_HARDWARE | \
 					 SOF_TIMESTAMPING_RAW_HARDWARE)
 
-enum hwtstamp_source {
-	HWTSTAMP_SOURCE_UNSPEC,
-	HWTSTAMP_SOURCE_NETDEV,
-	HWTSTAMP_SOURCE_PHYLIB,
-};
-
 /**
  * struct hwtstamp_provider_desc - hwtstamp provider description
  *
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 88dfb8aeed3c..ea9d335de130 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1776,6 +1776,7 @@ enum netdev_reg_state {
  *	@lltx:		device supports lockless Tx. Deprecated for real HW
  *			drivers. Mainly used by logical interfaces, such as
  *			bonding and tunnels
+ *	@netmem_tx:	device support netmem_tx.
  *
  *	@name:	This is the first field of the "visible" part of this structure
  *		(i.e. as seen by users in the "Space.c" file).  It is the name
@@ -1950,9 +1951,6 @@ enum netdev_reg_state {
  *
  *	@reg_state:		Register/unregister state machine
  *	@dismantle:		Device is going to be freed
- *	@rtnl_link_state:	This enum represents the phases of creating
- *				a new link
- *
  *	@needs_free_netdev:	Should unregister perform free_netdev?
  *	@priv_destructor:	Called from unregister
  *	@npinfo:		XXX: need comments on this one
@@ -2094,6 +2092,7 @@ struct net_device {
 	struct_group(priv_flags_fast,
 		unsigned long		priv_flags:32;
 		unsigned long		lltx:1;
+		unsigned long		netmem_tx:1;
 	);
 	const struct net_device_ops *netdev_ops;
 	const struct header_ops *header_ops;
@@ -2367,11 +2366,8 @@ struct net_device {
 
 	/** @moving_ns: device is changing netns, protected by @lock */
 	bool moving_ns;
-
-	enum {
-		RTNL_LINK_INITIALIZED,
-		RTNL_LINK_INITIALIZING,
-	} rtnl_link_state:16;
+	/** @rtnl_link_initializing: Device being created, suppress events */
+	bool rtnl_link_initializing;
 
 	bool needs_free_netdev;
 	void (*priv_destructor)(struct net_device *dev);
@@ -2530,7 +2526,7 @@ struct net_device {
 	 *	@net_shaper_hierarchy, @reg_state, @threaded
 	 *
 	 * Double protects:
-	 *	@up, @moving_ns, @nd_net, @xdp_flags
+	 *	@up, @moving_ns, @nd_net, @xdp_features
 	 *
 	 * Double ops protects:
 	 *	@real_num_rx_queues, @real_num_tx_queues
@@ -3276,7 +3272,7 @@ int call_netdevice_notifiers_info(unsigned long val,
 #define for_each_netdev_continue_rcu(net, d)		\
 	list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
 #define for_each_netdev_in_bond_rcu(bond, slave)	\
-		for_each_netdev_rcu(&init_net, slave)	\
+		for_each_netdev_rcu(dev_net_rcu(bond), slave)	\
 			if (netdev_master_upper_dev_get_rcu(slave) == (bond))
 #define net_device_entry(lh)	list_entry(lh, struct net_device, dev_list)
 
@@ -3511,7 +3507,12 @@ struct softnet_data {
 };
 
 DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
-DECLARE_PER_CPU(struct page_pool *, system_page_pool);
+
+struct page_pool_bh {
+	struct page_pool *pool;
+	local_lock_t bh_lock;
+};
+DECLARE_PER_CPU(struct page_pool_bh, system_page_pool);
 
 #ifndef CONFIG_PREEMPT_RT
 static inline int dev_recursion_level(void)
@@ -4982,6 +4983,7 @@ static inline void __dev_mc_unsync(struct net_device *dev,
 
 /* Functions used for secondary unicast and multicast support */
 void dev_set_rx_mode(struct net_device *dev);
+int netif_set_promiscuity(struct net_device *dev, int inc);
 int dev_set_promiscuity(struct net_device *dev, int inc);
 int netif_set_allmulti(struct net_device *dev, int inc, bool notify);
 int dev_set_allmulti(struct net_device *dev, int inc);
diff --git a/include/linux/netdevice_xmit.h b/include/linux/netdevice_xmit.h
index 38325e070296..848735b3a7c0 100644
--- a/include/linux/netdevice_xmit.h
+++ b/include/linux/netdevice_xmit.h
@@ -8,6 +8,9 @@ struct netdev_xmit {
 #ifdef CONFIG_NET_EGRESS
 	u8  skip_txqueue;
 #endif
+#if IS_ENABLED(CONFIG_NET_ACT_MIRRED)
+	u8 sched_mirred_nest;
+#endif
 };
 
 #endif
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index c3ae84a77e16..882e9c1b6c1d 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -63,7 +63,7 @@ netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg)
 }
 
 /* this can be increased when necessary - don't expose to userland */
-#define NETLINK_MAX_COOKIE_LEN	20
+#define NETLINK_MAX_COOKIE_LEN	8
 #define NETLINK_MAX_FMTMSG_LEN	80
 
 /**
@@ -212,6 +212,7 @@ static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack,
 {
 	if (!extack)
 		return;
+	BUILD_BUG_ON(sizeof(extack->cookie) < sizeof(cookie));
 	memcpy(extack->cookie, &cookie, sizeof(cookie));
 	extack->cookie_len = sizeof(cookie);
 }
diff --git a/include/linux/nfs.h b/include/linux/nfs.h
index 9ad727ddfedb..0906a0b40c6a 100644
--- a/include/linux/nfs.h
+++ b/include/linux/nfs.h
@@ -55,7 +55,6 @@ enum nfs3_stable_how {
 	NFS_INVALID_STABLE_HOW = -1
 };
 
-#ifdef CONFIG_CRC32
 /**
  * nfs_fhandle_hash - calculate the crc32 hash for the filehandle
  * @fh - pointer to filehandle
@@ -67,10 +66,4 @@ static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
 {
 	return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size);
 }
-#else /* CONFIG_CRC32 */
-static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
-{
-	return 0;
-}
-#endif /* CONFIG_CRC32 */
 #endif /* _LINUX_NFS_H */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 71319637a84e..ee03f3cef30c 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -213,6 +213,15 @@ struct nfs_server {
 	char			*fscache_uniq;	/* Uniquifier (or NULL) */
 #endif
 
+	/* The following #defines numerically match the NFSv4 equivalents */
+#define NFS_FH_NOEXPIRE_WITH_OPEN (0x1)
+#define NFS_FH_VOLATILE_ANY (0x2)
+#define NFS_FH_VOL_MIGRATION (0x4)
+#define NFS_FH_VOL_RENAME (0x8)
+#define NFS_FH_RENAME_UNSAFE (NFS_FH_VOLATILE_ANY | NFS_FH_VOL_RENAME)
+	u32			fh_expire_type;	/* V4 bitmask representing file
+						   handle volatility type for
+						   this filesystem */
 	u32			pnfs_blksize;	/* layout_blksize attr */
 #if IS_ENABLED(CONFIG_NFS_V4)
 	u32			attr_bitmask[3];/* V4 bitmask representing the set
@@ -236,9 +245,6 @@ struct nfs_server {
 	u32			acl_bitmask;	/* V4 bitmask representing the ACEs
 						   that are supported on this
 						   filesystem */
-	u32			fh_expire_type;	/* V4 bitmask representing file
-						   handle volatility type for
-						   this filesystem */
 	struct pnfs_layoutdriver_type  *pnfs_curr_ld; /* Active layout driver */
 	struct rpc_wait_queue	roc_rpcwaitq;
 	void			*pnfs_ld_data;	/* per mount point data */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 0e8e3fd77e96..51e2bd6405cd 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -245,6 +245,8 @@ enum pci_dev_flags {
 	PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 11),
 	/* Device does honor MSI masking despite saying otherwise */
 	PCI_DEV_FLAGS_HAS_MSI_MASKING = (__force pci_dev_flags_t) (1 << 12),
+	/* Device requires write to PCI_MSIX_ENTRY_DATA before any MSIX reads */
+	PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST = (__force pci_dev_flags_t) (1 << 13),
 };
 
 enum pci_irq_reroute_variant {
diff --git a/include/linux/pds/pds_adminq.h b/include/linux/pds/pds_adminq.h
index ddd111f04ca0..40ff0ec2b879 100644
--- a/include/linux/pds/pds_adminq.h
+++ b/include/linux/pds/pds_adminq.h
@@ -4,7 +4,7 @@
 #ifndef _PDS_CORE_ADMINQ_H_
 #define _PDS_CORE_ADMINQ_H_
 
-#define PDSC_ADMINQ_MAX_POLL_INTERVAL	256
+#define PDSC_ADMINQ_MAX_POLL_INTERVAL	256000	/* usecs */
 
 enum pds_core_adminq_flags {
 	PDS_AQ_FLAG_FASTPOLL	= BIT(1),	/* completion poll at 1ms */
@@ -463,7 +463,6 @@ struct pds_core_lif_getattr_cmd {
  * @rsvd:       Word boundary padding
  * @comp_index: Index in the descriptor ring for which this is the completion
  * @state:	LIF state (enum pds_core_lif_state)
- * @name:	LIF name string, 0 terminated
  * @features:	Features (enum pds_core_hw_features)
  * @rsvd2:      Word boundary padding
  * @color:	Color bit
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5a9bf15d4461..0069ba6866a4 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -823,7 +823,6 @@ struct perf_event {
 	struct irq_work			pending_disable_irq;
 	struct callback_head		pending_task;
 	unsigned int			pending_work;
-	struct rcuwait			pending_work_wait;
 
 	atomic_t			event_limit;
 
diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h
index c74077977830..8a7f4f802c57 100644
--- a/include/linux/pgalloc_tag.h
+++ b/include/linux/pgalloc_tag.h
@@ -188,6 +188,13 @@ static inline struct alloc_tag *__pgalloc_tag_get(struct page *page)
 	return tag;
 }
 
+static inline struct alloc_tag *pgalloc_tag_get(struct page *page)
+{
+	if (mem_alloc_profiling_enabled())
+		return __pgalloc_tag_get(page);
+	return NULL;
+}
+
 void pgalloc_tag_split(struct folio *folio, int old_order, int new_order);
 void pgalloc_tag_swap(struct folio *new, struct folio *old);
 
@@ -199,6 +206,7 @@ static inline void clear_page_tag_ref(struct page *page) {}
 static inline void alloc_tag_sec_init(void) {}
 static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) {}
 static inline void pgalloc_tag_swap(struct folio *new, struct folio *old) {}
+static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; }
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
 
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e2b705c14945..b50447ef1c92 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1511,8 +1511,9 @@ static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 
 /*
  * track_pfn_copy is called when a VM_PFNMAP VMA is about to get the page
- * tables copied during copy_page_range(). On success, stores the pfn to be
- * passed to untrack_pfn_copy().
+ * tables copied during copy_page_range(). Will store the pfn to be
+ * passed to untrack_pfn_copy() only if there is something to be untracked.
+ * Callers should initialize the pfn to 0.
  */
 static inline int track_pfn_copy(struct vm_area_struct *dst_vma,
 		struct vm_area_struct *src_vma, unsigned long *pfn)
@@ -1522,7 +1523,9 @@ static inline int track_pfn_copy(struct vm_area_struct *dst_vma,
 
 /*
  * untrack_pfn_copy is called when a VM_PFNMAP VMA failed to copy during
- * copy_page_range(), but after track_pfn_copy() was already called.
+ * copy_page_range(), but after track_pfn_copy() was already called. Can
+ * be called even if track_pfn_copy() did not actually track anything:
+ * handled internally.
  */
 static inline void untrack_pfn_copy(struct vm_area_struct *dst_vma,
 		unsigned long pfn)
diff --git a/include/linux/phy.h b/include/linux/phy.h
index a2bfae80c449..32b9da274115 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -990,7 +990,8 @@ struct phy_driver {
 	 * driver for the given phydev.	 If NULL, matching is based on
 	 * phy_id and phy_id_mask.
 	 */
-	int (*match_phy_device)(struct phy_device *phydev);
+	int (*match_phy_device)(struct phy_device *phydev,
+				const struct phy_driver *phydrv);
 
 	/**
 	 * @set_wol: Some devices (e.g. qnap TS-119P II) require PHY
@@ -1753,56 +1754,13 @@ int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum,
 struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 				     bool is_c45,
 				     struct phy_c45_device_ids *c45_ids);
-#if IS_ENABLED(CONFIG_PHYLIB)
 int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id);
 struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode);
 struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode);
-struct phy_device *device_phy_find_device(struct device *dev);
 struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode);
 struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45);
 int phy_device_register(struct phy_device *phy);
 void phy_device_free(struct phy_device *phydev);
-#else
-static inline int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id)
-{
-	return 0;
-}
-static inline
-struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode)
-{
-	return 0;
-}
-
-static inline
-struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode)
-{
-	return NULL;
-}
-
-static inline struct phy_device *device_phy_find_device(struct device *dev)
-{
-	return NULL;
-}
-
-static inline
-struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode)
-{
-	return NULL;
-}
-
-static inline
-struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45)
-{
-	return NULL;
-}
-
-static inline int phy_device_register(struct phy_device *phy)
-{
-	return 0;
-}
-
-static inline void phy_device_free(struct phy_device *phydev) { }
-#endif /* CONFIG_PHYLIB */
 void phy_device_remove(struct phy_device *phydev);
 int phy_get_c45_ids(struct phy_device *phydev);
 int phy_init_hw(struct phy_device *phydev);
@@ -1910,6 +1868,9 @@ char *phy_attached_info_irq(struct phy_device *phydev)
 	__malloc;
 void phy_attached_info(struct phy_device *phydev);
 
+int genphy_match_phy_device(struct phy_device *phydev,
+			    const struct phy_driver *phydrv);
+
 /* Clause 22 PHY */
 int genphy_read_abilities(struct phy_device *phydev);
 int genphy_setup_forced(struct phy_device *phydev);
@@ -2046,6 +2007,9 @@ int phy_get_tx_amplitude_gain(struct phy_device *phydev, struct device *dev,
 			      enum ethtool_link_mode_bit_indices linkmode,
 			      u32 *val);
 
+int phy_get_mac_termination(struct phy_device *phydev, struct device *dev,
+			    u32 *val);
+
 void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv,
 		       bool *tx_pause, bool *rx_pause);
 
@@ -2073,9 +2037,6 @@ int phy_ethtool_set_link_ksettings(struct net_device *ndev,
 				   const struct ethtool_link_ksettings *cmd);
 int phy_ethtool_nway_reset(struct net_device *ndev);
 
-int __init mdio_bus_init(void);
-void mdio_bus_exit(void);
-
 int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data);
 int phy_ethtool_get_sset_count(struct phy_device *phydev);
 int phy_ethtool_get_stats(struct phy_device *phydev,
@@ -2102,6 +2063,7 @@ int __phy_hwtstamp_set(struct phy_device *phydev,
 		       struct netlink_ext_ack *extack);
 
 extern const struct bus_type mdio_bus_type;
+extern const struct class mdio_bus_class;
 
 struct mdio_board_info {
 	const char	*bus_id;
@@ -2110,17 +2072,8 @@ struct mdio_board_info {
 	const void	*platform_data;
 };
 
-#if IS_ENABLED(CONFIG_MDIO_DEVICE)
 int mdiobus_register_board_info(const struct mdio_board_info *info,
 				unsigned int n);
-#else
-static inline int mdiobus_register_board_info(const struct mdio_board_info *i,
-					      unsigned int n)
-{
-	return 0;
-}
-#endif
-
 
 /**
  * phy_module_driver() - Helper macro for registering PHY drivers
diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h
index 1acafd86ab13..5399b9e41e35 100644
--- a/include/linux/phy_fixed.h
+++ b/include/linux/phy_fixed.h
@@ -13,43 +13,27 @@ struct fixed_phy_status {
 };
 
 struct device_node;
-struct gpio_desc;
 struct net_device;
 
 #if IS_ENABLED(CONFIG_FIXED_PHY)
 extern int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier);
-extern int fixed_phy_add(unsigned int irq, int phy_id,
-			 struct fixed_phy_status *status);
-extern struct phy_device *fixed_phy_register(unsigned int irq,
-					     struct fixed_phy_status *status,
-					     struct device_node *np);
-
-extern struct phy_device *
-fixed_phy_register_with_gpiod(unsigned int irq,
-			      struct fixed_phy_status *status,
-			      struct gpio_desc *gpiod);
+int fixed_phy_add(int phy_id, const struct fixed_phy_status *status);
+struct phy_device *fixed_phy_register(const struct fixed_phy_status *status,
+				      struct device_node *np);
 
 extern void fixed_phy_unregister(struct phy_device *phydev);
 extern int fixed_phy_set_link_update(struct phy_device *phydev,
 			int (*link_update)(struct net_device *,
 					   struct fixed_phy_status *));
 #else
-static inline int fixed_phy_add(unsigned int irq, int phy_id,
-				struct fixed_phy_status *status)
+static inline int fixed_phy_add(int phy_id,
+				const struct fixed_phy_status *status)
 {
 	return -ENODEV;
 }
-static inline struct phy_device *fixed_phy_register(unsigned int irq,
-						struct fixed_phy_status *status,
-						struct device_node *np)
-{
-	return ERR_PTR(-ENODEV);
-}
-
 static inline struct phy_device *
-fixed_phy_register_with_gpiod(unsigned int irq,
-			      struct fixed_phy_status *status,
-			      struct gpio_desc *gpiod)
+fixed_phy_register(const struct fixed_phy_status *status,
+		   struct device_node *np)
 {
 	return ERR_PTR(-ENODEV);
 }
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 1f5773ab5660..30659b615fca 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -361,23 +361,29 @@ int mac_finish(struct phylink_config *config, unsigned int mode,
 		phy_interface_t iface);
 
 /**
- * mac_link_down() - take the link down
+ * mac_link_down() - notification that the link has gone down
  * @config: a pointer to a &struct phylink_config.
  * @mode: link autonegotiation mode
  * @interface: link &typedef phy_interface_t mode
  *
- * If @mode is not an in-band negotiation mode (as defined by
- * phylink_autoneg_inband()), force the link down and disable any
- * Energy Efficient Ethernet MAC configuration. Interface type
- * selection must be done in mac_config().
+ * Notifies the MAC that the link has gone down. This will not be called
+ * unless mac_link_up() has been previously called.
+ *
+ * The MAC should stop processing packets for transmission and reception.
+ * phylink will have called netif_carrier_off() to notify the networking
+ * stack that the link has gone down, so MAC drivers should not make this
+ * call.
+ *
+ * If @mode is %MLO_AN_INBAND, then this function must not prevent the
+ * link coming up.
  */
 void mac_link_down(struct phylink_config *config, unsigned int mode,
 		   phy_interface_t interface);
 
 /**
- * mac_link_up() - allow the link to come up
+ * mac_link_up() - notification that the link has come up
  * @config: a pointer to a &struct phylink_config.
- * @phy: any attached phy
+ * @phy: any attached phy (deprecated - please use LPI interfaces)
  * @mode: link autonegotiation mode
  * @interface: link &typedef phy_interface_t mode
  * @speed: link speed
@@ -385,7 +391,10 @@ void mac_link_down(struct phylink_config *config, unsigned int mode,
  * @tx_pause: link transmit pause enablement status
  * @rx_pause: link receive pause enablement status
  *
- * Configure the MAC for an established link.
+ * Notifies the MAC that the link has come up, and the parameters of the
+ * link as seen from the MACs point of view. If mac_link_up() has been
+ * called previously, there will be an intervening call to mac_link_down()
+ * before this method will be subsequently called.
  *
  * @speed, @duplex, @tx_pause and @rx_pause indicate the finalised link
  * settings, and should be used to configure the MAC block appropriately
@@ -397,9 +406,9 @@ void mac_link_down(struct phylink_config *config, unsigned int mode,
  * that the user wishes to override the pause settings, and this should
  * be allowed when considering the implementation of this method.
  *
- * If in-band negotiation mode is disabled, allow the link to come up. If
- * @phy is non-%NULL, configure Energy Efficient Ethernet by calling
- * phy_init_eee() and perform appropriate MAC configuration for EEE.
+ * Once configured, the MAC may begin to process packets for transmission
+ * and reception.
+ *
  * Interface type selection must be done in mac_config().
  */
 void mac_link_up(struct phylink_config *config, struct phy_device *phy,
diff --git a/include/linux/platform_data/x86/intel_pmc_ipc.h b/include/linux/platform_data/x86/intel_pmc_ipc.h
index 6e603a8c075f..1d34435b7001 100644
--- a/include/linux/platform_data/x86/intel_pmc_ipc.h
+++ b/include/linux/platform_data/x86/intel_pmc_ipc.h
@@ -36,6 +36,7 @@ struct pmc_ipc_rbuf {
  */
 static inline int intel_pmc_ipc(struct pmc_ipc_cmd *ipc_cmd, struct pmc_ipc_rbuf *rbuf)
 {
+#ifdef CONFIG_ACPI
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object params[PMC_IPCS_PARAM_COUNT] = {
 		{.type = ACPI_TYPE_INTEGER,},
@@ -89,6 +90,9 @@ static inline int intel_pmc_ipc(struct pmc_ipc_cmd *ipc_cmd, struct pmc_ipc_rbuf
 	}
 
 	return 0;
+#else
+	return -ENODEV;
+#endif /* CONFIG_ACPI */
 }
 
 #endif /* INTEL_PMC_IPC_H */
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 331a9a996fa8..8ca2235f78d5 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -70,6 +70,10 @@
 #define KEY_DESTROY		0xbd
 
 /********** net/core/page_pool.c **********/
+/*
+ * page_pool uses additional free bits within this value to store data, see the
+ * definition of PP_DMA_INDEX_MASK in mm.h
+ */
 #define PP_SIGNATURE		(0x40 + POISON_POINTER_DELTA)
 
 /********** net/core/skbuff.c **********/
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 0d68d09bedd1..eced7e9bf69a 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -68,6 +68,22 @@ struct ptp_system_timestamp {
  * @n_per_out: The number of programmable periodic signals.
  * @n_pins:    The number of programmable pins.
  * @pps:       Indicates whether the clock supports a PPS callback.
+ *
+ * @supported_perout_flags:  The set of flags the driver supports for the
+ *                           PTP_PEROUT_REQUEST ioctl. The PTP core will
+ *                           reject a request with any flag not specified
+ *                           here.
+ *
+ * @supported_extts_flags:  The set of flags the driver supports for the
+ *                          PTP_EXTTS_REQUEST ioctl. The PTP core will use
+ *                          this list to reject unsupported requests.
+ *                          PTP_ENABLE_FEATURE is assumed and does not need to
+ *                          be included. If PTP_STRICT_FLAGS is *not* set,
+ *                          then both PTP_RISING_EDGE and PTP_FALLING_EDGE
+ *                          will be assumed. Note that PTP_STRICT_FLAGS must
+ *                          be set if the drivers wants to honor
+ *                          PTP_EXTTS_REQUEST2 and any future flags.
+ *
  * @pin_config: Array of length 'n_pins'. If the number of
  *              programmable pins is nonzero, then drivers must
  *              allocate and initialize this array.
@@ -174,6 +190,8 @@ struct ptp_clock_info {
 	int n_per_out;
 	int n_pins;
 	int pps;
+	unsigned int supported_perout_flags;
+	unsigned int supported_extts_flags;
 	struct ptp_pin_desc *pin_config;
 	int (*adjfine)(struct ptp_clock_info *ptp, long scaled_ppm);
 	int (*adjphase)(struct ptp_clock_info *ptp, s32 phase);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f1381aff0f89..5520524c93bf 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -274,7 +274,6 @@
 			 SKB_DATA_ALIGN(sizeof(struct sk_buff)) +	\
 			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
-struct ahash_request;
 struct net_device;
 struct scatterlist;
 struct pipe_inode_info;
@@ -481,9 +480,6 @@ enum {
 	/* generate software time stamp on packet tx completion */
 	SKBTX_COMPLETION_TSTAMP = 1 << 3,
 
-	/* generate wifi status information (where possible) */
-	SKBTX_WIFI_STATUS = 1 << 4,
-
 	/* determine hardware time stamp based on time or cycles */
 	SKBTX_HW_TSTAMP_NETDEV = 1 << 5,
 
@@ -1710,13 +1706,16 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
 extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops;
 
 struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
-				       struct ubuf_info *uarg);
+				       struct ubuf_info *uarg, bool devmem);
 
 void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
 
+struct net_devmem_dmabuf_binding;
+
 int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 			    struct sk_buff *skb, struct iov_iter *from,
-			    size_t length);
+			    size_t length,
+			    struct net_devmem_dmabuf_binding *binding);
 
 int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
 				struct iov_iter *from, size_t length);
@@ -1724,12 +1723,14 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
 static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb,
 					  struct msghdr *msg, int len)
 {
-	return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len);
+	return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len,
+				       NULL);
 }
 
 int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 			     struct msghdr *msg, int len,
-			     struct ubuf_info *uarg);
+			     struct ubuf_info *uarg,
+			     struct net_devmem_dmabuf_binding *binding);
 
 /* Internal */
 #define skb_shinfo(SKB)	((struct skb_shared_info *)(skb_end_pointer(SKB)))
@@ -3700,6 +3701,10 @@ static inline dma_addr_t __skb_frag_dma_map(struct device *dev,
 					    size_t offset, size_t size,
 					    enum dma_data_direction dir)
 {
+	if (skb_frag_is_net_iov(frag)) {
+		return netmem_to_net_iov(frag->netmem)->dma_addr + offset +
+		       frag->offset;
+	}
 	return dma_map_page(dev, skb_frag_page(frag),
 			    skb_frag_off(frag) + offset, size, dir);
 }
@@ -4128,9 +4133,8 @@ static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
 }
 int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen,
 				   struct msghdr *msg);
-int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset,
-			   struct iov_iter *to, int len,
-			   struct ahash_request *hash);
+int skb_copy_and_crc32c_datagram_iter(const struct sk_buff *skb, int offset,
+				      struct iov_iter *to, int len, u32 *crcp);
 int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 				 struct iov_iter *from, int len);
 int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm);
@@ -4145,6 +4149,8 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
 		    unsigned int flags);
 int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset,
 			 int len);
+int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb,
+				    int offset, int len, int flags);
 int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len);
 void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
 unsigned int skb_zerocopy_headlen(const struct sk_buff *from);
@@ -4184,17 +4190,9 @@ static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len)
 	return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT;
 }
 
-struct skb_checksum_ops {
-	__wsum (*update)(const void *mem, int len, __wsum wsum);
-	__wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len);
-};
-
-extern const struct skb_checksum_ops *crc32c_csum_stub __read_mostly;
-
-__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
-		      __wsum csum, const struct skb_checksum_ops *ops);
 __wsum skb_checksum(const struct sk_buff *skb, int offset, int len,
 		    __wsum csum);
+u32 skb_crc32c(const struct sk_buff *skb, int offset, int len, u32 crc);
 
 static inline void * __must_check
 __skb_header_pointer(const struct sk_buff *skb, int offset, int len,
diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h
index 0f3c58007488..9e49372ef1a0 100644
--- a/include/linux/skbuff_ref.h
+++ b/include/linux/skbuff_ref.h
@@ -17,7 +17,7 @@
  */
 static inline void __skb_frag_ref(skb_frag_t *frag)
 {
-	get_page(skb_frag_page(frag));
+	get_netmem(skb_frag_netmem(frag));
 }
 
 /**
@@ -40,7 +40,7 @@ static inline void skb_page_unref(netmem_ref netmem, bool recycle)
 	if (recycle && napi_pp_put_page(netmem))
 		return;
 #endif
-	put_page(netmem_to_page(netmem));
+	put_netmem(netmem);
 }
 
 /**
diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h
index a476648858a6..d8949a4ed0dc 100644
--- a/include/linux/soc/mediatek/mtk_wed.h
+++ b/include/linux/soc/mediatek/mtk_wed.h
@@ -192,7 +192,7 @@ struct mtk_wed_device {
 };
 
 struct mtk_wed_ops {
-	int (*attach)(struct mtk_wed_device *dev);
+	int (*attach)(struct mtk_wed_device *dev) __releases(RCU);
 	int (*tx_ring_setup)(struct mtk_wed_device *dev, int ring,
 			     void __iomem *regs, bool reset);
 	int (*rx_ring_setup)(struct mtk_wed_device *dev, int ring,
diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h
index 493d9de4e472..dc6ebaee3d18 100644
--- a/include/linux/soundwire/sdw_intel.h
+++ b/include/linux/soundwire/sdw_intel.h
@@ -365,7 +365,7 @@ struct sdw_intel_res {
  * on e.g. which machine driver to select (I2S mode, HDaudio or
  * SoundWire).
  */
-int sdw_intel_acpi_scan(acpi_handle *parent_handle,
+int sdw_intel_acpi_scan(acpi_handle parent_handle,
 			struct sdw_intel_acpi_info *info);
 
 void sdw_intel_process_wakeen_event(struct sdw_intel_ctx *ctx);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index c4ec8bb8144e..26ddf95d23f9 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -233,13 +233,14 @@ struct plat_stmmacenet_data {
 	u8 tx_sched_algorithm;
 	struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES];
 	struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES];
+	void (*get_interfaces)(struct stmmac_priv *priv, void *bsp_priv,
+			       unsigned long *interfaces);
 	int (*set_clk_tx_rate)(void *priv, struct clk *clk_tx_i,
 			       phy_interface_t interface, int speed);
 	void (*fix_mac_speed)(void *priv, int speed, unsigned int mode);
 	int (*fix_soc_reset)(void *priv, void __iomem *ioaddr);
 	int (*serdes_powerup)(struct net_device *ndev, void *priv);
 	void (*serdes_powerdown)(struct net_device *ndev, void *priv);
-	void (*speed_mode_2500)(struct net_device *ndev, void *priv);
 	int (*mac_finish)(struct net_device *ndev,
 			  void *priv,
 			  unsigned int mode,
@@ -276,7 +277,6 @@ struct plat_stmmacenet_data {
 	int mac_port_sel_speed;
 	int has_xgmac;
 	u8 vlan_fail_q;
-	unsigned long eee_usecs_rate;
 	struct pci_dev *pdev;
 	int int_snapshot_num;
 	int msi_mac_vec;
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 1669d95bb0f9..29f59d50dc73 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -340,7 +340,7 @@ struct tcp_sock {
 	} rcv_rtt_est;
 /* Receiver queue space */
 	struct {
-		u32	space;
+		int	space;
 		u32	seq;
 		u64	time;
 	} rcvq_space;
@@ -385,7 +385,8 @@ struct tcp_sock {
 		syn_fastopen:1,	/* SYN includes Fast Open option */
 		syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
 		syn_fastopen_ch:1, /* Active TFO re-enabling probe */
-		syn_data_acked:1;/* data in SYN is acked by SYN-ACK */
+		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
+		syn_fastopen_child:1; /* created TFO passive child socket */
 
 	u8	keepalive_probes; /* num of allowed keep alive probes	*/
 	u32	tcp_tx_delay;	/* delay (in usec) added to TX packets */
diff --git a/include/linux/tfrc.h b/include/linux/tfrc.h
deleted file mode 100644
index a5acc768085d..000000000000
--- a/include/linux/tfrc.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _LINUX_TFRC_H_
-#define _LINUX_TFRC_H_
-/*
- *  TFRC - Data Structures for the TCP-Friendly Rate Control congestion
- *         control mechanism as specified in RFC 3448.
- *
- *  Copyright (c) 2005 The University of Waikato, Hamilton, New Zealand.
- *  Copyright (c) 2005 Ian McDonald <iam4@cs.waikato.ac.nz>
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- *  Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
- */
-#include <linux/types.h>
-
-/** 	tfrc_rx_info    -    TFRC Receiver Data Structure
- *
- * 	@tfrcrx_x_recv:	receiver estimate of sending rate (3.2.2)
- * 	@tfrcrx_rtt:	round-trip-time (communicated by sender)
- * 	@tfrcrx_p:	current estimate of loss event rate (3.2.2)
- */
-struct tfrc_rx_info {
-  	__u32 tfrcrx_x_recv;
-	__u32 tfrcrx_rtt;
-  	__u32 tfrcrx_p;
-};
-
-/** 	tfrc_tx_info    -    TFRC Sender Data Structure
- *
- * 	@tfrctx_x:	computed transmit rate (4.3 (4))
- * 	@tfrctx_x_recv: receiver estimate of send rate (4.3)
- * 	@tfrctx_x_calc:	return value of throughput equation (3.1)
- * 	@tfrctx_rtt:	(moving average) estimate of RTT (4.3)
- * 	@tfrctx_p:	current loss event rate (5.4)
- * 	@tfrctx_rto:	estimate of RTO, equals 4*RTT (4.3)
- * 	@tfrctx_ipi:	inter-packet interval (4.6)
- *
- *  Note: X and X_recv are both maintained in units of 64 * bytes/second. This
- *        enables a finer resolution of sending rates and avoids problems with
- *        integer arithmetic; u32 is not sufficient as scaling consumes 6 bits.
- */
-struct tfrc_tx_info {
-	__u64 tfrctx_x;
-	__u64 tfrctx_x_recv;
-	__u32 tfrctx_x_calc;
-	__u32 tfrctx_rtt;
-	__u32 tfrctx_p;
-	__u32 tfrctx_rto;
-	__u32 tfrctx_ipi;
-};
-
-#endif /* _LINUX_TFRC_H_ */
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index e39d4d563b19..785048a3b3e6 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -51,7 +51,7 @@ struct tk_read_base {
  * @offs_real:			Offset clock monotonic -> clock realtime
  * @offs_boot:			Offset clock monotonic -> clock boottime
  * @offs_tai:			Offset clock monotonic -> clock tai
- * @tai_offset:			The current UTC to TAI offset in seconds
+ * @coarse_nsec:		The nanoseconds part for coarse time getters
  * @tkr_raw:			The readout base structure for CLOCK_MONOTONIC_RAW
  * @raw_sec:			CLOCK_MONOTONIC_RAW  time in seconds
  * @clock_was_set_seq:		The sequence number of clock was set events
@@ -76,6 +76,7 @@ struct tk_read_base {
  *				ntp shifted nano seconds.
  * @ntp_err_mult:		Multiplication factor for scaled math conversion
  * @skip_second_overflow:	Flag used to avoid updating NTP twice with same second
+ * @tai_offset:			The current UTC to TAI offset in seconds
  *
  * Note: For timespec(64) based interfaces wall_to_monotonic is what
  * we need to add to xtime (or xtime corrected for sub jiffy times)
@@ -100,7 +101,7 @@ struct tk_read_base {
  * which results in the following cacheline layout:
  *
  * 0:	seqcount, tkr_mono
- * 1:	xtime_sec ... tai_offset
+ * 1:	xtime_sec ... coarse_nsec
  * 2:	tkr_raw, raw_sec
  * 3,4: Internal variables
  *
@@ -121,7 +122,7 @@ struct timekeeper {
 	ktime_t			offs_real;
 	ktime_t			offs_boot;
 	ktime_t			offs_tai;
-	s32			tai_offset;
+	u32			coarse_nsec;
 
 	/* Cacheline 2: */
 	struct tk_read_base	tkr_raw;
@@ -144,6 +145,7 @@ struct timekeeper {
 	u32			ntp_error_shift;
 	u32			ntp_err_mult;
 	u32			skip_second_overflow;
+	s32			tai_offset;
 };
 
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index 6c3125300c00..a3d8305e88a5 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -224,7 +224,7 @@ enum tpm2_const {
 
 enum tpm2_timeouts {
 	TPM2_TIMEOUT_A          =    750,
-	TPM2_TIMEOUT_B          =   2000,
+	TPM2_TIMEOUT_B          =   4000,
 	TPM2_TIMEOUT_C          =    200,
 	TPM2_TIMEOUT_D          =     30,
 	TPM2_DURATION_SHORT     =     20,
@@ -257,6 +257,7 @@ enum tpm2_return_codes {
 	TPM2_RC_TESTING		= 0x090A, /* RC_WARN */
 	TPM2_RC_REFERENCE_H0	= 0x0910,
 	TPM2_RC_RETRY		= 0x0922,
+	TPM2_RC_SESSION_MEMORY	= 0x0903,
 };
 
 enum tpm2_command_codes {
@@ -437,6 +438,24 @@ static inline u32 tpm2_rc_value(u32 rc)
 	return (rc & BIT(7)) ? rc & 0xbf : rc;
 }
 
+/*
+ * Convert a return value from tpm_transmit_cmd() to POSIX error code.
+ */
+static inline ssize_t tpm_ret_to_err(ssize_t ret)
+{
+	if (ret < 0)
+		return ret;
+
+	switch (tpm2_rc_value(ret)) {
+	case TPM2_RC_SUCCESS:
+		return 0;
+	case TPM2_RC_SESSION_MEMORY:
+		return -ENOMEM;
+	default:
+		return -EFAULT;
+	}
+}
+
 #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE)
 
 extern int tpm_is_tpm2(struct tpm_chip *chip);
diff --git a/include/linux/udp.h b/include/linux/udp.h
index 895240177f4f..4e1a672af4c5 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -216,6 +216,9 @@ static inline void udp_allow_gso(struct sock *sk)
 #define udp_portaddr_for_each_entry(__sk, list) \
 	hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node)
 
+#define udp_portaddr_for_each_entry_from(__sk) \
+	hlist_for_each_entry_from(__sk, __sk_common.skc_portaddr_node)
+
 #define udp_portaddr_for_each_entry_rcu(__sk, list) \
 	hlist_for_each_entry_rcu(__sk, list, __sk_common.skc_portaddr_node)
 
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 49ece9e1888f..393d0622cc28 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -99,7 +99,13 @@ static inline const struct iovec *iter_iov(const struct iov_iter *iter)
 }
 
 #define iter_iov_addr(iter)	(iter_iov(iter)->iov_base + (iter)->iov_offset)
-#define iter_iov_len(iter)	(iter_iov(iter)->iov_len - (iter)->iov_offset)
+
+static inline size_t iter_iov_len(const struct iov_iter *i)
+{
+	if (i->iter_type == ITER_UBUF)
+		return i->count;
+	return iter_iov(i)->iov_len - i->iov_offset;
+}
 
 static inline enum iter_type iov_iter_type(const struct iov_iter *i)
 {
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 4d16c13d0df5..64cb4b04be7a 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -220,6 +220,8 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev);
  *    occurs.
  * @reset_done: optional function to call after transport specific reset
  *    operation has finished.
+ * @shutdown: synchronize with the device on shutdown. If provided, replaces
+ *    the virtio core implementation.
  */
 struct virtio_driver {
 	struct device_driver driver;
@@ -237,6 +239,7 @@ struct virtio_driver {
 	int (*restore)(struct virtio_device *dev);
 	int (*reset_prepare)(struct virtio_device *dev);
 	int (*reset_done)(struct virtio_device *dev);
+	void (*shutdown)(struct virtio_device *dev);
 };
 
 #define drv_to_virtio(__drv)	container_of_const(__drv, struct virtio_driver, driver)
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 31e9ffd936e3..5ca8d4dd149d 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -61,6 +61,7 @@ struct vm_struct {
 	unsigned int		nr_pages;
 	phys_addr_t		phys_addr;
 	const void		*caller;
+	unsigned long		requested_size;
 };
 
 struct vmap_area {
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index cf793d18e5df..0fb4c41c9bbf 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -16,6 +16,7 @@ struct sock;
 struct socket;
 struct rxrpc_call;
 struct rxrpc_peer;
+struct krb5_buffer;
 enum rxrpc_abort_reason;
 
 enum rxrpc_interruptibility {
@@ -24,23 +25,33 @@ enum rxrpc_interruptibility {
 	RXRPC_UNINTERRUPTIBLE,	/* Call should not be interruptible at all */
 };
 
+enum rxrpc_oob_type {
+	RXRPC_OOB_CHALLENGE,	/* Security challenge for a connection */
+};
+
 /*
  * Debug ID counter for tracing.
  */
 extern atomic_t rxrpc_debug_id;
 
+/*
+ * Operations table for rxrpc to call out to a kernel application (e.g. kAFS).
+ */
+struct rxrpc_kernel_ops {
+	void (*notify_new_call)(struct sock *sk, struct rxrpc_call *call,
+				unsigned long user_call_ID);
+	void (*discard_new_call)(struct rxrpc_call *call, unsigned long user_call_ID);
+	void (*user_attach_call)(struct rxrpc_call *call, unsigned long user_call_ID);
+	void (*notify_oob)(struct sock *sk, struct sk_buff *oob);
+};
+
 typedef void (*rxrpc_notify_rx_t)(struct sock *, struct rxrpc_call *,
 				  unsigned long);
 typedef void (*rxrpc_notify_end_tx_t)(struct sock *, struct rxrpc_call *,
 				      unsigned long);
-typedef void (*rxrpc_notify_new_call_t)(struct sock *, struct rxrpc_call *,
-					unsigned long);
-typedef void (*rxrpc_discard_new_call_t)(struct rxrpc_call *, unsigned long);
-typedef void (*rxrpc_user_attach_call_t)(struct rxrpc_call *, unsigned long);
 
-void rxrpc_kernel_new_call_notification(struct socket *,
-					rxrpc_notify_new_call_t,
-					rxrpc_discard_new_call_t);
+void rxrpc_kernel_set_notifications(struct socket *sock,
+				    const struct rxrpc_kernel_ops *app_ops);
 struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 					   struct rxrpc_peer *peer,
 					   struct key *key,
@@ -72,16 +83,33 @@ const struct sockaddr *rxrpc_kernel_remote_addr(const struct rxrpc_peer *peer);
 unsigned long rxrpc_kernel_set_peer_data(struct rxrpc_peer *peer, unsigned long app_data);
 unsigned long rxrpc_kernel_get_peer_data(const struct rxrpc_peer *peer);
 unsigned int rxrpc_kernel_get_srtt(const struct rxrpc_peer *);
-int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
-			       rxrpc_user_attach_call_t, unsigned long, gfp_t,
-			       unsigned int);
+int rxrpc_kernel_charge_accept(struct socket *sock, rxrpc_notify_rx_t notify_rx,
+			       unsigned long user_call_ID, gfp_t gfp,
+			       unsigned int debug_id);
 void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
 bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *);
-u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *);
-void rxrpc_kernel_set_max_life(struct socket *, struct rxrpc_call *,
-			       unsigned long);
 
 int rxrpc_sock_set_min_security_level(struct sock *sk, unsigned int val);
 int rxrpc_sock_set_security_keyring(struct sock *, struct key *);
+int rxrpc_sock_set_manage_response(struct sock *sk, bool set);
+
+enum rxrpc_oob_type rxrpc_kernel_query_oob(struct sk_buff *oob,
+					   struct rxrpc_peer **_peer,
+					   unsigned long *_peer_appdata);
+struct sk_buff *rxrpc_kernel_dequeue_oob(struct socket *sock,
+					 enum rxrpc_oob_type *_type);
+void rxrpc_kernel_free_oob(struct sk_buff *oob);
+void rxrpc_kernel_query_challenge(struct sk_buff *challenge,
+				  struct rxrpc_peer **_peer,
+				  unsigned long *_peer_appdata,
+				  u16 *_service_id, u8 *_security_index);
+int rxrpc_kernel_reject_challenge(struct sk_buff *challenge, u32 abort_code,
+				  int error, enum rxrpc_abort_reason why);
+int rxkad_kernel_respond_to_challenge(struct sk_buff *challenge);
+u32 rxgk_kernel_query_challenge(struct sk_buff *challenge);
+int rxgk_kernel_respond_to_challenge(struct sk_buff *challenge,
+				     struct krb5_buffer *appdata);
+u8 rxrpc_kernel_query_call_security(struct rxrpc_call *call,
+				    u16 *_service_id, u32 *_enctype);
 
 #endif /* _NET_RXRPC_H */
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index bbefde319f95..114299bd8b98 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -29,6 +29,7 @@
 #include <linux/poll.h>
 #include <net/sock.h>
 #include <linux/seq_file.h>
+#include <linux/ethtool.h>
 
 #define BT_SUBSYS_VERSION	2
 #define BT_SUBSYS_REVISION	22
@@ -448,6 +449,9 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status,
 			  hci_req_complete_t *req_complete,
 			  hci_req_complete_skb_t *req_complete_skb);
 
+int hci_ethtool_ts_info(unsigned int index, int sk_proto,
+			struct kernel_ethtool_ts_info *ts_info);
+
 #define HCI_REQ_START	BIT(0)
 #define HCI_REQ_SKB	BIT(1)
 
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index a8586c3058c7..82cbd54443ac 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -494,6 +494,7 @@ enum {
 #define HCI_EVENT_PKT		0x04
 #define HCI_ISODATA_PKT		0x05
 #define HCI_DIAG_PKT		0xf0
+#define HCI_DRV_PKT		0xf1
 #define HCI_VENDOR_PKT		0xff
 
 /* HCI packet types */
@@ -557,7 +558,8 @@ enum {
 #define ESCO_LINK	0x02
 /* Low Energy links do not have defined link type. Use invented one */
 #define LE_LINK		0x80
-#define ISO_LINK	0x82
+#define CIS_LINK	0x82
+#define BIS_LINK	0x83
 #define INVALID_LINK	0xff
 
 /* LMP features */
@@ -1931,6 +1933,8 @@ struct hci_cp_le_pa_create_sync {
 	__u8      sync_cte_type;
 } __packed;
 
+#define HCI_OP_LE_PA_CREATE_SYNC_CANCEL	0x2045
+
 #define HCI_OP_LE_PA_TERM_SYNC		0x2046
 struct hci_cp_le_pa_term_sync {
 	__le16    handle;
@@ -2830,7 +2834,7 @@ struct hci_evt_le_create_big_complete {
 	__le16  bis_handle[];
 } __packed;
 
-#define HCI_EVT_LE_BIG_SYNC_ESTABILISHED 0x1d
+#define HCI_EVT_LE_BIG_SYNC_ESTABLISHED 0x1d
 struct hci_evt_le_big_sync_estabilished {
 	__u8    status;
 	__u8    handle;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 5115da34f881..2b261e74e2c4 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -31,6 +31,7 @@
 #include <linux/rculist.h>
 
 #include <net/bluetooth/hci.h>
+#include <net/bluetooth/hci_drv.h>
 #include <net/bluetooth/hci_sync.h>
 #include <net/bluetooth/hci_sock.h>
 #include <net/bluetooth/coredump.h>
@@ -613,6 +614,8 @@ struct hci_dev {
 	struct list_head	monitored_devices;
 	bool			advmon_pend_notify;
 
+	struct hci_drv		*hci_drv;
+
 #if IS_ENABLED(CONFIG_BT_LEDS)
 	struct led_trigger	*power_led;
 #endif
@@ -996,7 +999,8 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c)
 	case ESCO_LINK:
 		h->sco_num++;
 		break;
-	case ISO_LINK:
+	case CIS_LINK:
+	case BIS_LINK:
 		h->iso_num++;
 		break;
 	}
@@ -1022,7 +1026,8 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c)
 	case ESCO_LINK:
 		h->sco_num--;
 		break;
-	case ISO_LINK:
+	case CIS_LINK:
+	case BIS_LINK:
 		h->iso_num--;
 		break;
 	}
@@ -1039,7 +1044,8 @@ static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type)
 	case SCO_LINK:
 	case ESCO_LINK:
 		return h->sco_num;
-	case ISO_LINK:
+	case CIS_LINK:
+	case BIS_LINK:
 		return h->iso_num;
 	default:
 		return 0;
@@ -1100,7 +1106,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (bacmp(&c->dst, ba) || c->type != ISO_LINK)
+		if (bacmp(&c->dst, ba) || c->type != BIS_LINK)
 			continue;
 
 		if (c->iso_qos.bcast.bis == bis) {
@@ -1113,10 +1119,8 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev,
 	return NULL;
 }
 
-static inline struct hci_conn *hci_conn_hash_lookup_sid(struct hci_dev *hdev,
-							__u8 sid,
-							bdaddr_t *dst,
-							__u8 dst_type)
+static inline struct hci_conn *
+hci_conn_hash_lookup_create_pa_sync(struct hci_dev *hdev)
 {
 	struct hci_conn_hash *h = &hdev->conn_hash;
 	struct hci_conn  *c;
@@ -1124,8 +1128,10 @@ static inline struct hci_conn *hci_conn_hash_lookup_sid(struct hci_dev *hdev,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type != ISO_LINK  || bacmp(&c->dst, dst) ||
-		    c->dst_type != dst_type || c->sid != sid)
+		if (c->type != BIS_LINK)
+			continue;
+
+		if (!test_bit(HCI_CONN_CREATE_PA_SYNC, &c->flags))
 			continue;
 
 		rcu_read_unlock();
@@ -1148,8 +1154,8 @@ hci_conn_hash_lookup_per_adv_bis(struct hci_dev *hdev,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (bacmp(&c->dst, ba) || c->type != ISO_LINK ||
-			!test_bit(HCI_CONN_PER_ADV, &c->flags))
+		if (bacmp(&c->dst, ba) || c->type != BIS_LINK ||
+		    !test_bit(HCI_CONN_PER_ADV, &c->flags))
 			continue;
 
 		if (c->iso_qos.bcast.big == big &&
@@ -1238,7 +1244,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY))
+		if (c->type != CIS_LINK)
 			continue;
 
 		/* Match CIG ID if set */
@@ -1270,7 +1276,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_cig(struct hci_dev *hdev,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY))
+		if (c->type != CIS_LINK)
 			continue;
 
 		if (handle == c->iso_qos.ucast.cig) {
@@ -1293,17 +1299,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type != ISO_LINK)
-			continue;
-
-		/* An ISO_LINK hcon with BDADDR_ANY as destination
-		 * address is a Broadcast connection. A Broadcast
-		 * slave connection is associated with a PA train,
-		 * so the sync_handle can be used to differentiate
-		 * from unicast.
-		 */
-		if (bacmp(&c->dst, BDADDR_ANY) &&
-		    c->sync_handle == HCI_SYNC_HANDLE_INVALID)
+		if (c->type != BIS_LINK)
 			continue;
 
 		if (handle == c->iso_qos.bcast.big) {
@@ -1327,7 +1323,7 @@ hci_conn_hash_lookup_big_sync_pend(struct hci_dev *hdev,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type != ISO_LINK)
+		if (c->type != BIS_LINK)
 			continue;
 
 		if (handle == c->iso_qos.bcast.big && num_bis == c->num_bis) {
@@ -1350,8 +1346,8 @@ hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle,  __u16 state)
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (bacmp(&c->dst, BDADDR_ANY) || c->type != ISO_LINK ||
-			c->state != state)
+		if (c->type != BIS_LINK || bacmp(&c->dst, BDADDR_ANY) ||
+		    c->state != state)
 			continue;
 
 		if (handle == c->iso_qos.bcast.big) {
@@ -1374,8 +1370,8 @@ hci_conn_hash_lookup_pa_sync_big_handle(struct hci_dev *hdev, __u8 big)
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type != ISO_LINK ||
-			!test_bit(HCI_CONN_PA_SYNC, &c->flags))
+		if (c->type != BIS_LINK ||
+		    !test_bit(HCI_CONN_PA_SYNC, &c->flags))
 			continue;
 
 		if (c->iso_qos.bcast.big == big) {
@@ -1397,7 +1393,7 @@ hci_conn_hash_lookup_pa_sync_handle(struct hci_dev *hdev, __u16 sync_handle)
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type != ISO_LINK)
+		if (c->type != BIS_LINK)
 			continue;
 
 		/* Ignore the listen hcon, we are looking
@@ -1524,8 +1520,6 @@ bool hci_setup_sync(struct hci_conn *conn, __u16 handle);
 void hci_sco_setup(struct hci_conn *conn, __u8 status);
 bool hci_iso_setup_path(struct hci_conn *conn);
 int hci_le_create_cis_pending(struct hci_dev *hdev);
-int hci_pa_create_sync_pending(struct hci_dev *hdev);
-int hci_le_big_create_sync_pending(struct hci_dev *hdev);
 int hci_conn_check_create_cis(struct hci_conn *conn);
 
 struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst,
@@ -1566,9 +1560,9 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
 				 __u8 data_len, __u8 *data);
 struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst,
 		       __u8 dst_type, __u8 sid, struct bt_iso_qos *qos);
-int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
-			   struct bt_iso_qos *qos,
-			   __u16 sync_handle, __u8 num_bis, __u8 bis[]);
+int hci_conn_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
+			     struct bt_iso_qos *qos, __u16 sync_handle,
+			     __u8 num_bis, __u8 bis[]);
 int hci_conn_check_link_mode(struct hci_conn *conn);
 int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level);
 int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type,
@@ -1800,6 +1794,7 @@ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list,
 void hci_uuids_clear(struct hci_dev *hdev);
 
 void hci_link_keys_clear(struct hci_dev *hdev);
+u8 *hci_conn_key_enc_size(struct hci_conn *conn);
 struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr);
 struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn,
 				  bdaddr_t *bdaddr, u8 *val, u8 type,
@@ -2013,7 +2008,8 @@ static inline int hci_proto_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	case ESCO_LINK:
 		return sco_connect_ind(hdev, bdaddr, flags);
 
-	case ISO_LINK:
+	case CIS_LINK:
+	case BIS_LINK:
 		return iso_connect_ind(hdev, bdaddr, flags);
 
 	default:
diff --git a/include/net/bluetooth/hci_drv.h b/include/net/bluetooth/hci_drv.h
new file mode 100644
index 000000000000..2f01c44f05ec
--- /dev/null
+++ b/include/net/bluetooth/hci_drv.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2025 Google Corporation
+ */
+
+#ifndef __HCI_DRV_H
+#define __HCI_DRV_H
+
+#include <linux/types.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci.h>
+
+struct hci_drv_cmd_hdr {
+	__le16	opcode;
+	__le16	len;
+} __packed;
+
+struct hci_drv_ev_hdr {
+	__le16	opcode;
+	__le16	len;
+} __packed;
+
+#define HCI_DRV_EV_CMD_STATUS	0x0000
+struct hci_drv_ev_cmd_status {
+	__le16	opcode;
+	__u8	status;
+} __packed;
+
+#define HCI_DRV_EV_CMD_COMPLETE	0x0001
+struct hci_drv_ev_cmd_complete {
+	__le16	opcode;
+	__u8	status;
+	__u8	data[];
+} __packed;
+
+#define HCI_DRV_STATUS_SUCCESS			0x00
+#define HCI_DRV_STATUS_UNSPECIFIED_ERROR	0x01
+#define HCI_DRV_STATUS_UNKNOWN_COMMAND		0x02
+#define HCI_DRV_STATUS_INVALID_PARAMETERS	0x03
+
+#define HCI_DRV_MAX_DRIVER_NAME_LENGTH	32
+
+/* Common commands that make sense on all drivers start from 0x0000 */
+#define HCI_DRV_OP_READ_INFO	0x0000
+#define HCI_DRV_READ_INFO_SIZE	0
+struct hci_drv_rp_read_info {
+	__u8	driver_name[HCI_DRV_MAX_DRIVER_NAME_LENGTH];
+	__le16	num_supported_commands;
+	__le16	supported_commands[];
+} __packed;
+
+/* Driver specific OGF (Opcode Group Field)
+ * Commands in this group may have different meanings across different drivers.
+ */
+#define HCI_DRV_OGF_DRIVER_SPECIFIC	0x01
+
+int hci_drv_cmd_status(struct hci_dev *hdev, u16 cmd, u8 status);
+int hci_drv_cmd_complete(struct hci_dev *hdev, u16 cmd, u8 status, void *rp,
+			 size_t rp_len);
+int hci_drv_process_cmd(struct hci_dev *hdev, struct sk_buff *cmd_skb);
+
+struct hci_drv_handler {
+	int (*func)(struct hci_dev *hdev, void *data, u16 data_len);
+	size_t data_len;
+};
+
+struct hci_drv {
+	size_t common_handler_count;
+	const struct hci_drv_handler *common_handlers;
+
+	size_t specific_handler_count;
+	const struct hci_drv_handler *specific_handlers;
+};
+
+#endif /* __HCI_DRV_H */
diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h
index 082f89531b88..bbd752494ef9 100644
--- a/include/net/bluetooth/hci_mon.h
+++ b/include/net/bluetooth/hci_mon.h
@@ -51,6 +51,8 @@ struct hci_mon_hdr {
 #define HCI_MON_CTRL_EVENT	17
 #define HCI_MON_ISO_TX_PKT	18
 #define HCI_MON_ISO_RX_PKT	19
+#define HCI_MON_DRV_TX_PKT	20
+#define HCI_MON_DRV_RX_PKT	21
 
 struct hci_mon_new_index {
 	__u8		type;
diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index 7e2cf0cca939..72558c826aa1 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -185,3 +185,6 @@ int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn);
 int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn);
 int hci_le_conn_update_sync(struct hci_dev *hdev, struct hci_conn *conn,
 			    struct hci_conn_params *params);
+
+int hci_connect_pa_sync(struct hci_dev *hdev, struct hci_conn *conn);
+int hci_connect_big_sync(struct hci_dev *hdev, struct hci_conn *conn);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index efbd79c67be2..d1848dc8ec99 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1097,43 +1097,6 @@ int cfg80211_chandef_primary(const struct cfg80211_chan_def *chandef,
 int nl80211_send_chandef(struct sk_buff *msg, const struct cfg80211_chan_def *chandef);
 
 /**
- * ieee80211_chanwidth_rate_flags - return rate flags for channel width
- * @width: the channel width of the channel
- *
- * In some channel types, not all rates may be used - for example CCK
- * rates may not be used in 5/10 MHz channels.
- *
- * Returns: rate flags which apply for this channel width
- */
-static inline enum ieee80211_rate_flags
-ieee80211_chanwidth_rate_flags(enum nl80211_chan_width width)
-{
-	switch (width) {
-	case NL80211_CHAN_WIDTH_5:
-		return IEEE80211_RATE_SUPPORTS_5MHZ;
-	case NL80211_CHAN_WIDTH_10:
-		return IEEE80211_RATE_SUPPORTS_10MHZ;
-	default:
-		break;
-	}
-	return 0;
-}
-
-/**
- * ieee80211_chandef_rate_flags - returns rate flags for a channel
- * @chandef: channel definition for the channel
- *
- * See ieee80211_chanwidth_rate_flags().
- *
- * Returns: rate flags which apply for this channel
- */
-static inline enum ieee80211_rate_flags
-ieee80211_chandef_rate_flags(struct cfg80211_chan_def *chandef)
-{
-	return ieee80211_chanwidth_rate_flags(chandef->width);
-}
-
-/**
  * ieee80211_chandef_max_power - maximum transmission power for the chandef
  *
  * In some regulations, the transmit power may depend on the configured channel
@@ -1300,11 +1263,13 @@ struct cfg80211_crypto_settings {
  * struct cfg80211_mbssid_config - AP settings for multi bssid
  *
  * @tx_wdev: pointer to the transmitted interface in the MBSSID set
+ * @tx_link_id: link ID of the transmitted profile in an MLD.
  * @index: index of this AP in the multi bssid group.
  * @ema: set to true if the beacons should be sent out in EMA mode.
  */
 struct cfg80211_mbssid_config {
 	struct wireless_dev *tx_wdev;
+	u8 tx_link_id;
 	u8 index;
 	bool ema;
 };
@@ -1770,6 +1735,9 @@ struct cfg80211_ttlm_params {
  * @supported_oper_classes_len: number of supported operating classes
  * @support_p2p_ps: information if station supports P2P PS mechanism
  * @airtime_weight: airtime scheduler weight for this station
+ * @eml_cap_present: Specifies if EML capabilities field (@eml_cap) is
+ *	present/updated
+ * @eml_cap: EML capabilities of this station
  * @link_sta_params: link related params.
  */
 struct station_parameters {
@@ -1794,6 +1762,8 @@ struct station_parameters {
 	u8 supported_oper_classes_len;
 	int support_p2p_ps;
 	u16 airtime_weight;
+	bool eml_cap_present;
+	u16 eml_cap;
 	struct link_station_parameters link_sta_params;
 };
 
diff --git a/include/net/checksum.h b/include/net/checksum.h
index 243f972267b8..e57986b173f8 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -99,12 +99,6 @@ csum_block_add(__wsum csum, __wsum csum2, int offset)
 }
 
 static __always_inline __wsum
-csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len)
-{
-	return csum_block_add(csum, csum2, offset);
-}
-
-static __always_inline __wsum
 csum_block_sub(__wsum csum, __wsum csum2, int offset)
 {
 	return csum_block_add(csum, ~csum2, offset);
@@ -115,12 +109,6 @@ static __always_inline __wsum csum_unfold(__sum16 n)
 	return (__force __wsum)n;
 }
 
-static __always_inline
-__wsum csum_partial_ext(const void *buff, int len, __wsum sum)
-{
-	return csum_partial(buff, len, sum);
-}
-
 #define CSUM_MANGLED_0 ((__force __sum16)0xffff)
 
 static __always_inline void csum_replace_by_diff(__sum16 *sum, __wsum diff)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index b8783126c1ed..0091f23a40f7 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -420,11 +420,11 @@ typedef u64 devlink_resource_occ_get_t(void *priv);
 
 #define __DEVLINK_PARAM_MAX_STRING_VALUE 32
 enum devlink_param_type {
-	DEVLINK_PARAM_TYPE_U8,
-	DEVLINK_PARAM_TYPE_U16,
-	DEVLINK_PARAM_TYPE_U32,
-	DEVLINK_PARAM_TYPE_STRING,
-	DEVLINK_PARAM_TYPE_BOOL,
+	DEVLINK_PARAM_TYPE_U8 = DEVLINK_VAR_ATTR_TYPE_U8,
+	DEVLINK_PARAM_TYPE_U16 = DEVLINK_VAR_ATTR_TYPE_U16,
+	DEVLINK_PARAM_TYPE_U32 = DEVLINK_VAR_ATTR_TYPE_U32,
+	DEVLINK_PARAM_TYPE_STRING = DEVLINK_VAR_ATTR_TYPE_STRING,
+	DEVLINK_PARAM_TYPE_BOOL = DEVLINK_VAR_ATTR_TYPE_FLAG,
 };
 
 union devlink_param_value {
diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index bea77934a235..bcf9d7467e1a 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -62,6 +62,7 @@
 	FN(NEIGH_FAILED)		\
 	FN(NEIGH_QUEUEFULL)		\
 	FN(NEIGH_DEAD)			\
+	FN(NEIGH_HH_FILLFAIL)		\
 	FN(TC_EGRESS)			\
 	FN(SECURITY_HOOK)		\
 	FN(QDISC_DROP)			\
@@ -348,6 +349,8 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_NEIGH_QUEUEFULL,
 	/** @SKB_DROP_REASON_NEIGH_DEAD: neigh entry is dead */
 	SKB_DROP_REASON_NEIGH_DEAD,
+	/** @SKB_DROP_REASON_NEIGH_HH_FILLFAIL: failed to fill the device hard header */
+	SKB_DROP_REASON_NEIGH_HH_FILLFAIL,
 	/** @SKB_DROP_REASON_TC_EGRESS: dropped in TC egress HOOK */
 	SKB_DROP_REASON_TC_EGRESS,
 	/** @SKB_DROP_REASON_SECURITY_HOOK: dropped due to security HOOK */
diff --git a/include/net/dsa.h b/include/net/dsa.h
index a0a9481c52c2..55e2d97f247e 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -1131,9 +1131,10 @@ struct dsa_switch_ops {
 	 * PTP functionality
 	 */
 	int	(*port_hwtstamp_get)(struct dsa_switch *ds, int port,
-				     struct ifreq *ifr);
+				     struct kernel_hwtstamp_config *config);
 	int	(*port_hwtstamp_set)(struct dsa_switch *ds, int port,
-				     struct ifreq *ifr);
+				     struct kernel_hwtstamp_config *config,
+				     struct netlink_ext_ack *extack);
 	void	(*port_txtstamp)(struct dsa_switch *ds, int port,
 				 struct sk_buff *skb);
 	bool	(*port_rxtstamp)(struct dsa_switch *ds, int port,
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 5927910ec06e..6e68e359ad18 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -45,6 +45,8 @@ struct fib_rule {
 	struct fib_rule_port_range	dport_range;
 	u16			sport_mask;
 	u16			dport_mask;
+	u8                      iif_is_l3_master;
+	u8                      oif_is_l3_master;
 	struct rcu_head		rcu;
 };
 
diff --git a/include/net/flow.h b/include/net/flow.h
index 335bbc52171c..a1839c278d87 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -38,6 +38,8 @@ struct flowi_common {
 	__u8	flowic_flags;
 #define FLOWI_FLAG_ANYSRC		0x01
 #define FLOWI_FLAG_KNOWN_NH		0x02
+#define FLOWI_FLAG_L3MDEV_OIF		0x04
+#define FLOWI_FLAG_ANY_SPORT		0x08
 	__u32	flowic_secid;
 	kuid_t  flowic_uid;
 	__u32		flowic_multipath_hash;
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 949641e92539..4564b5d348b1 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -175,14 +175,9 @@ struct inet_hashinfo {
 	bool				pernet;
 } ____cacheline_aligned_in_smp;
 
-static inline struct inet_hashinfo *tcp_or_dccp_get_hashinfo(const struct sock *sk)
+static inline struct inet_hashinfo *tcp_get_hashinfo(const struct sock *sk)
 {
-#if IS_ENABLED(CONFIG_IP_DCCP)
-	return sk->sk_prot->h.hashinfo ? :
-		sock_net(sk)->ipv4.tcp_death_row.hashinfo;
-#else
 	return sock_net(sk)->ipv4.tcp_death_row.hashinfo;
-#endif
 }
 
 static inline struct inet_listen_hashbucket *
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 7c87873ae211..88b0dd4d8e09 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -198,6 +198,7 @@ struct fib6_info {
 					fib6_destroying:1,
 					unused:4;
 
+	struct list_head		purge_link;
 	struct rcu_head			rcu;
 	struct nexthop			*nh;
 	struct fib6_nh			fib6_nh[];
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index e3864b74e92a..48bb3cf41469 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -574,7 +574,8 @@ static inline u32 fib_multipath_hash_from_keys(const struct net *net,
 
 int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope,
 		 struct netlink_ext_ack *extack);
-void fib_select_multipath(struct fib_result *res, int hash);
+void fib_select_multipath(struct fib_result *res, int hash,
+			  const struct flowi4 *fl4);
 void fib_select_path(struct net *net, struct fib_result *res,
 		     struct flowi4 *fl4, const struct sk_buff *skb);
 
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index a36a335cef9f..0c3d571a04a1 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -377,10 +377,9 @@ struct net *ip_tunnel_get_link_net(const struct net_device *dev);
 int ip_tunnel_get_iflink(const struct net_device *dev);
 int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 		       struct rtnl_link_ops *ops, char *devname);
-
-void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id,
-			   struct rtnl_link_ops *ops,
-			   struct list_head *dev_to_kill);
+void ip_tunnel_delete_net(struct net *net, unsigned int id,
+			  struct rtnl_link_ops *ops,
+			  struct list_head *dev_to_kill);
 
 void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		    const struct iphdr *tnl_params, const u8 protocol);
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index f7fe796e8429..1eb8dad18f7e 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -59,6 +59,20 @@ int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net,
 int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
 			  struct fib_lookup_arg *arg);
 
+static inline
+bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex)
+{
+	return !(fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF) &&
+	       fl->flowi_l3mdev == iifindex;
+}
+
+static inline
+bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex)
+{
+	return fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF &&
+	       fl->flowi_l3mdev == oifindex;
+}
+
 void l3mdev_update_flow(struct net *net, struct flowi *fl);
 
 int l3mdev_master_ifindex_rcu(const struct net_device *dev);
@@ -327,6 +341,19 @@ int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
 {
 	return 1;
 }
+
+static inline
+bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex)
+{
+	return false;
+}
+
+static inline
+bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex)
+{
+	return false;
+}
+
 static inline
 void l3mdev_update_flow(struct net *net, struct flowi *fl)
 {
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 39cd50300a18..c306ebe379a0 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -116,11 +116,9 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
 int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
 			   unsigned int num);
 int lwtunnel_valid_encap_type(u16 encap_type,
-			      struct netlink_ext_ack *extack,
-			      bool rtnl_is_held);
+			      struct netlink_ext_ack *extack);
 int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len,
-				   struct netlink_ext_ack *extack,
-				   bool rtnl_is_held);
+				   struct netlink_ext_ack *extack);
 int lwtunnel_build_state(struct net *net, u16 encap_type,
 			 struct nlattr *encap,
 			 unsigned int family, const void *cfg,
@@ -203,15 +201,14 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
 }
 
 static inline int lwtunnel_valid_encap_type(u16 encap_type,
-					    struct netlink_ext_ack *extack,
-					    bool rtnl_is_held)
+					    struct netlink_ext_ack *extack)
 {
 	NL_SET_ERR_MSG(extack, "CONFIG_LWTUNNEL is not enabled in this kernel");
 	return -EOPNOTSUPP;
 }
+
 static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len,
-						 struct netlink_ext_ack *extack,
-						 bool rtnl_is_held)
+						 struct netlink_ext_ack *extack)
 {
 	/* return 0 since we are not walking attr looking for
 	 * RTA_ENCAP_TYPE attribute on nexthops.
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index c498f685d01f..82617579d910 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -682,6 +682,9 @@ struct ieee80211_parsed_tpe {
  *	responder functionality.
  * @ftmr_params: configurable lci/civic parameter when enabling FTM responder.
  * @nontransmitted: this BSS is a nontransmitted BSS profile
+ * @tx_bss_conf: Pointer to the BSS configuration of transmitting interface
+ *	if MBSSID is enabled. This pointer is RCU-protected due to CSA finish
+ *	and BSS color change flows accessing it.
  * @transmitter_bssid: the address of transmitter AP
  * @bssid_index: index inside the multiple BSSID set
  * @bssid_indicator: 2^bssid_indicator is the maximum number of APs in set
@@ -741,6 +744,7 @@ struct ieee80211_parsed_tpe {
  * @eht_80mhz_full_bw_ul_mumimo: in AP-mode, does this BSS support the
  *	reception of an EHT TB PPDU on an RU that spans the entire PPDU
  *	bandwidth
+ * @eht_disable_mcs15: disable EHT-MCS 15 reception capability.
  * @bss_param_ch_cnt: in BSS-mode, the BSS params change count. This
  *	information is the latest known value. It can come from this link's
  *	beacon or from a beacon sent by another link.
@@ -804,6 +808,7 @@ struct ieee80211_bss_conf {
 	struct ieee80211_ftm_responder_params *ftmr_params;
 	/* Multiple BSSID data */
 	bool nontransmitted;
+	struct ieee80211_bss_conf __rcu *tx_bss_conf;
 	u8 transmitter_bssid[ETH_ALEN];
 	u8 bssid_index;
 	u8 bssid_indicator;
@@ -848,6 +853,8 @@ struct ieee80211_bss_conf {
 	bool eht_su_beamformee;
 	bool eht_mu_beamformer;
 	bool eht_80mhz_full_bw_ul_mumimo;
+	bool eht_disable_mcs15;
+
 	u8 bss_param_ch_cnt;
 	u8 bss_param_ch_cnt_link_id;
 };
@@ -2023,7 +2030,6 @@ enum ieee80211_neg_ttlm_res {
  * @txq: the multicast data TX queue
  * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see
  *	&enum ieee80211_offload_flags.
- * @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled.
  */
 struct ieee80211_vif {
 	enum nl80211_iftype type;
@@ -2052,8 +2058,6 @@ struct ieee80211_vif {
 	bool probe_req_reg;
 	bool rx_mcast_action_reg;
 
-	struct ieee80211_vif *mbssid_tx_vif;
-
 	/* must be last */
 	u8 drv_priv[] __aligned(sizeof(void *));
 };
@@ -2488,6 +2492,7 @@ struct ieee80211_link_sta {
  * @max_amsdu_subframes: indicates the maximal number of MSDUs in a single
  *	A-MSDU. Taken from the Extended Capabilities element. 0 means
  *	unlimited.
+ * @eml_cap: EML capabilities of this MLO station
  * @cur: currently valid data as aggregated from the active links
  *	For non MLO STA it will point to the deflink data. For MLO STA
  *	ieee80211_sta_recalc_aggregates() must be called to update it.
@@ -2522,6 +2527,7 @@ struct ieee80211_sta {
 	bool mlo;
 	bool spp_amsdu;
 	u8 max_amsdu_subframes;
+	u16 eml_cap;
 
 	struct ieee80211_sta_aggregates *cur;
 
@@ -5347,22 +5353,6 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif,
 			    int max_rates);
 
 /**
- * ieee80211_sta_set_expected_throughput - set the expected tpt for a station
- *
- * Call this function to notify mac80211 about a change in expected throughput
- * to a station. A driver for a device that does rate control in firmware can
- * call this function when the expected throughput estimate towards a station
- * changes. The information is used to tune the CoDel AQM applied to traffic
- * going towards that station (which can otherwise be too aggressive and cause
- * slow stations to starve).
- *
- * @pubsta: the station to set throughput for.
- * @thr: the current expected throughput in kbps.
- */
-void ieee80211_sta_set_expected_throughput(struct ieee80211_sta *pubsta,
-					   u32 thr);
-
-/**
  * ieee80211_tx_rate_update - transmit rate update callback
  *
  * Drivers should call this functions with a non-NULL pub sta
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index bfbad695951c..f7263fe2a2e4 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -101,18 +101,9 @@ struct mptcp_out_options {
 #define MPTCP_SCHED_MAX		128
 #define MPTCP_SCHED_BUF_MAX	(MPTCP_SCHED_NAME_MAX * MPTCP_SCHED_MAX)
 
-#define MPTCP_SUBFLOWS_MAX	8
-
-struct mptcp_sched_data {
-	u8	subflows;
-	struct mptcp_subflow_context *contexts[MPTCP_SUBFLOWS_MAX];
-};
-
 struct mptcp_sched_ops {
-	int (*get_send)(struct mptcp_sock *msk,
-			struct mptcp_sched_data *data);
-	int (*get_retrans)(struct mptcp_sock *msk,
-			   struct mptcp_sched_data *data);
+	int (*get_send)(struct mptcp_sock *msk);
+	int (*get_retrans)(struct mptcp_sock *msk);
 
 	char			name[MPTCP_SCHED_NAME_MAX];
 	struct module		*owner;
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index bd57d8fb54f1..025a7574b275 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -475,8 +475,8 @@ struct pernet_operations {
 	void (*exit)(struct net *net);
 	void (*exit_batch)(struct list_head *net_exit_list);
 	/* Following method is called with RTNL held. */
-	void (*exit_batch_rtnl)(struct list_head *net_exit_list,
-				struct list_head *dev_kill_list);
+	void (*exit_rtnl)(struct net *net,
+			  struct list_head *dev_kill_list);
 	unsigned int * const id;
 	const size_t size;
 };
diff --git a/include/net/netdev_lock.h b/include/net/netdev_lock.h
index 5706835a660c..3d3aef80beac 100644
--- a/include/net/netdev_lock.h
+++ b/include/net/netdev_lock.h
@@ -48,6 +48,22 @@ static inline void netdev_unlock_ops(struct net_device *dev)
 		netdev_unlock(dev);
 }
 
+static inline void netdev_lock_ops_to_full(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_assert_locked(dev);
+	else
+		netdev_lock(dev);
+}
+
+static inline void netdev_unlock_full_to_ops(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_assert_locked(dev);
+	else
+		netdev_unlock(dev);
+}
+
 static inline void netdev_ops_assert_locked(const struct net_device *dev)
 {
 	if (netdev_need_ops_lock(dev))
@@ -83,16 +99,15 @@ static inline void netdev_unlock_ops_compat(struct net_device *dev)
 static inline int netdev_lock_cmp_fn(const struct lockdep_map *a,
 				     const struct lockdep_map *b)
 {
-	/* Only lower devices currently grab the instance lock, so no
-	 * real ordering issues can occur. In the near future, only
-	 * hardware devices will grab instance lock which also does not
-	 * involve any ordering. Suppress lockdep ordering warnings
-	 * until (if) we start grabbing instance lock on pure SW
-	 * devices (bond/team/veth/etc).
-	 */
 	if (a == b)
 		return 0;
-	return -1;
+
+	/* Allow locking multiple devices only under rtnl_lock,
+	 * the exact order doesn't matter.
+	 * Note that upper devices don't lock their ops, so nesting
+	 * mostly happens in batched device removal for now.
+	 */
+	return lockdep_rtnl_is_held() ? -1 : 1;
 }
 
 #define netdev_lockdep_set_classes(dev)				\
@@ -114,6 +129,9 @@ static inline int netdev_lock_cmp_fn(const struct lockdep_map *a,
 				  &qdisc_xmit_lock_key);	\
 }
 
+#define netdev_lock_dereference(p, dev)				\
+	rcu_dereference_protected(p, lockdep_is_held(&(dev)->lock))
+
 int netdev_debug_event(struct notifier_block *nb, unsigned long event,
 		       void *ptr);
 
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index ea709b59d827..ba2eaf39089b 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -105,6 +105,12 @@ struct netdev_stat_ops {
 			       struct netdev_queue_stats_tx *tx);
 };
 
+void netdev_stat_queue_sum(struct net_device *netdev,
+			   int rx_start, int rx_end,
+			   struct netdev_queue_stats_rx *rx_sum,
+			   int tx_start, int tx_end,
+			   struct netdev_queue_stats_tx *tx_sum);
+
 /**
  * struct netdev_queue_mgmt_ops - netdev ops for queue management
  *
@@ -282,27 +288,27 @@ netdev_txq_completed_mb(struct netdev_queue *dev_queue,
 
 #define netif_subqueue_try_stop(dev, idx, get_desc, start_thrs)		\
 	({								\
-		struct netdev_queue *txq;				\
+		struct netdev_queue *_txq;				\
 									\
-		txq = netdev_get_tx_queue(dev, idx);			\
-		netif_txq_try_stop(txq, get_desc, start_thrs);		\
+		_txq = netdev_get_tx_queue(dev, idx);			\
+		netif_txq_try_stop(_txq, get_desc, start_thrs);		\
 	})
 
 #define netif_subqueue_maybe_stop(dev, idx, get_desc, stop_thrs, start_thrs) \
 	({								\
-		struct netdev_queue *txq;				\
+		struct netdev_queue *_txq;				\
 									\
-		txq = netdev_get_tx_queue(dev, idx);			\
-		netif_txq_maybe_stop(txq, get_desc, stop_thrs, start_thrs); \
+		_txq = netdev_get_tx_queue(dev, idx);			\
+		netif_txq_maybe_stop(_txq, get_desc, stop_thrs, start_thrs); \
 	})
 
 #define netif_subqueue_completed_wake(dev, idx, pkts, bytes,		\
 				      get_desc, start_thrs)		\
 	({								\
-		struct netdev_queue *txq;				\
+		struct netdev_queue *_txq;				\
 									\
-		txq = netdev_get_tx_queue(dev, idx);			\
-		netif_txq_completed_wake(txq, pkts, bytes,		\
+		_txq = netdev_get_tx_queue(dev, idx);			\
+		netif_txq_completed_wake(_txq, pkts, bytes,		\
 					 get_desc, start_thrs);		\
 	})
 
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 29e0db940382..90a560dc167a 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -321,7 +321,13 @@ enum nla_policy_validation {
  *    All other            Unused - but note that it's a union
  *
  * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN:
+ *    NLA_U8, NLA_U16,
+ *    NLA_U32, NLA_U64,
+ *    NLA_S8, NLA_S16,
+ *    NLA_S32, NLA_S64,
+ *    NLA_MSECS,
  *    NLA_BINARY           Validation function called for the attribute.
+ *
  *    All other            Unused - but note that it's a union
  *
  * Example:
@@ -612,6 +618,22 @@ static inline int nlmsg_len(const struct nlmsghdr *nlh)
 }
 
 /**
+ * nlmsg_payload - message payload if the data fits in the len
+ * @nlh: netlink message header
+ * @len: struct length
+ *
+ * Returns: The netlink message payload/data if the length is sufficient,
+ * otherwise NULL.
+ */
+static inline void *nlmsg_payload(const struct nlmsghdr *nlh, size_t len)
+{
+	if (nlh->nlmsg_len < nlmsg_msg_size(len))
+		return NULL;
+
+	return nlmsg_data(nlh);
+}
+
+/**
  * nlmsg_attrdata - head of attributes data
  * @nlh: netlink message header
  * @hdrlen: length of family specific header
diff --git a/include/net/netmem.h b/include/net/netmem.h
index c61d5b21e7b4..386164fb9c18 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -8,6 +8,7 @@
 #ifndef _NET_NETMEM_H
 #define _NET_NETMEM_H
 
+#include <linux/dma-mapping.h>
 #include <linux/mm.h>
 #include <net/net_debug.h>
 
@@ -20,8 +21,17 @@ DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers);
  */
 #define NET_IOV 0x01UL
 
+enum net_iov_type {
+	NET_IOV_DMABUF,
+	NET_IOV_IOURING,
+
+	/* Force size to unsigned long to make the NET_IOV_ASSERTS below pass.
+	 */
+	NET_IOV_MAX = ULONG_MAX
+};
+
 struct net_iov {
-	unsigned long __unused_padding;
+	enum net_iov_type type;
 	unsigned long pp_magic;
 	struct page_pool *pp;
 	struct net_iov_area *owner;
@@ -264,4 +274,26 @@ static inline unsigned long netmem_get_dma_addr(netmem_ref netmem)
 	return __netmem_clear_lsb(netmem)->dma_addr;
 }
 
+void get_netmem(netmem_ref netmem);
+void put_netmem(netmem_ref netmem);
+
+#define netmem_dma_unmap_addr_set(NETMEM, PTR, ADDR_NAME, VAL)   \
+	do {                                                     \
+		if (!netmem_is_net_iov(NETMEM))                  \
+			dma_unmap_addr_set(PTR, ADDR_NAME, VAL); \
+		else                                             \
+			dma_unmap_addr_set(PTR, ADDR_NAME, 0);   \
+	} while (0)
+
+static inline void netmem_dma_unmap_page_attrs(struct device *dev,
+					       dma_addr_t addr, size_t size,
+					       enum dma_data_direction dir,
+					       unsigned long attrs)
+{
+	if (!addr)
+		return;
+
+	dma_unmap_page_attrs(dev, addr, size, dir, attrs);
+}
+
 #endif /* _NET_NETMEM_H */
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 5f2cfd84570a..47dc70d8100a 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -72,6 +72,7 @@ struct netns_ipv6 {
 	struct rt6_statistics   *rt6_stats;
 	struct timer_list       ip6_fib_timer;
 	struct hlist_head       *fib_table_hash;
+	spinlock_t		fib_table_hash_lock;
 	struct fib6_table       *fib6_main_tbl;
 	struct list_head	fib6_walkers;
 	rwlock_t		fib6_walker_lock;
diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index d9fb44e8b321..572e69cda476 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -152,6 +152,8 @@ struct nexthop {
 	u8			protocol;   /* app managing this nh */
 	u8			nh_flags;
 	bool			is_group;
+	bool			dead;
+	spinlock_t		lock;       /* protect dead and f6i_list */
 
 	refcount_t		refcnt;
 	struct rcu_head		rcu;
diff --git a/include/net/p8022.h b/include/net/p8022.h
deleted file mode 100644
index a29e224ac498..000000000000
--- a/include/net/p8022.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NET_P8022_H
-#define _NET_P8022_H
-
-struct net_device;
-struct packet_type;
-struct sk_buff;
-
-struct datalink_proto *
-register_8022_client(unsigned char type,
-		     int (*func)(struct sk_buff *skb,
-				 struct net_device *dev,
-				 struct packet_type *pt,
-				 struct net_device *orig_dev));
-void unregister_8022_client(struct datalink_proto *proto);
-#endif
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 582a3d00cbe2..93f2c31baf9b 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -395,6 +395,12 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
 	page_pool_put_full_page(pool, page, true);
 }
 
+static inline void page_pool_recycle_direct_netmem(struct page_pool *pool,
+						   netmem_ref netmem)
+{
+	page_pool_put_full_netmem(pool, netmem, true);
+}
+
 #define PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA	\
 		(sizeof(dma_addr_t) > sizeof(unsigned long))
 
@@ -492,4 +498,9 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid)
 		page_pool_update_nid(pool, new_nid);
 }
 
+static inline bool page_pool_is_unreadable(struct page_pool *pool)
+{
+	return !!pool->mp_ops;
+}
+
 #endif /* _NET_PAGE_POOL_HELPERS_H */
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 36eb57d73abc..431b593de709 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -6,6 +6,7 @@
 #include <linux/dma-direction.h>
 #include <linux/ptr_ring.h>
 #include <linux/types.h>
+#include <linux/xarray.h>
 #include <net/netmem.h>
 
 #define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
@@ -33,6 +34,9 @@
 #define PP_FLAG_ALL		(PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV | \
 				 PP_FLAG_SYSTEM_POOL | PP_FLAG_ALLOW_UNREADABLE_NETMEM)
 
+/* Index limit to stay within PP_DMA_INDEX_BITS for DMA indices */
+#define PP_DMA_INDEX_LIMIT XA_LIMIT(1, BIT(PP_DMA_INDEX_BITS) - 1)
+
 /*
  * Fast allocation side cache array/stack
  *
@@ -221,6 +225,8 @@ struct page_pool {
 	void *mp_priv;
 	const struct memory_provider_ops *mp_ops;
 
+	struct xarray dma_mapped;
+
 #ifdef CONFIG_PAGE_POOL_STATS
 	/* recycle stats are per-cpu to avoid locking */
 	struct page_pool_recycle_stats __percpu *recycle_stats;
diff --git a/include/net/route.h b/include/net/route.h
index c605fd5ec0c0..8e39aa822cf9 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -326,6 +326,9 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst,
 	if (inet_test_bit(TRANSPARENT, sk))
 		flow_flags |= FLOWI_FLAG_ANYSRC;
 
+	if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !sport)
+		flow_flags |= FLOWI_FLAG_ANY_SPORT;
+
 	flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk),
 			   ip_sock_rt_scope(sk), protocol, flow_flags, dst,
 			   src, dport, sport, sk->sk_uid);
diff --git a/include/net/rps.h b/include/net/rps.h
index 507f4aa5d39b..d8ab3a08bcc4 100644
--- a/include/net/rps.h
+++ b/include/net/rps.h
@@ -123,6 +123,30 @@ static inline void sock_rps_record_flow(const struct sock *sk)
 #endif
 }
 
+static inline void sock_rps_delete_flow(const struct sock *sk)
+{
+#ifdef CONFIG_RPS
+	struct rps_sock_flow_table *table;
+	u32 hash, index;
+
+	if (!static_branch_unlikely(&rfs_needed))
+		return;
+
+	hash = READ_ONCE(sk->sk_rxhash);
+	if (!hash)
+		return;
+
+	rcu_read_lock();
+	table = rcu_dereference(net_hotdata.rps_sock_flow_table);
+	if (table) {
+		index = hash & table->mask;
+		if (READ_ONCE(table->ents[index]) != RPS_NO_CPU)
+			WRITE_ONCE(table->ents[index], RPS_NO_CPU);
+	}
+	rcu_read_unlock();
+#endif
+}
+
 static inline u32 rps_input_queue_tail_incr(struct softnet_data *sd)
 {
 #ifdef CONFIG_RPS
diff --git a/include/net/rstreason.h b/include/net/rstreason.h
index 69cb2e52b7da..979ac87b5d99 100644
--- a/include/net/rstreason.h
+++ b/include/net/rstreason.h
@@ -36,7 +36,7 @@
 /**
  * enum sk_rst_reason - the reasons of socket reset
  *
- * The reasons of sk reset, which are used in DCCP/TCP/MPTCP protocols.
+ * The reasons of sk reset, which are used in TCP/MPTCP protocols.
  *
  * There are three parts in order:
  * 1) skb drop reasons: relying on drop reasons for such as passive reset
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d48c657191cd..629368ab2787 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -803,6 +803,14 @@ static inline bool qdisc_tx_changing(const struct net_device *dev)
 	return false;
 }
 
+/* "noqueue" qdisc identified by not having any enqueue, see noqueue_init() */
+static inline bool qdisc_txq_has_no_queue(const struct netdev_queue *txq)
+{
+	struct Qdisc *qdisc = rcu_access_pointer(txq->qdisc);
+
+	return qdisc->enqueue == NULL;
+}
+
 /* Is the device using the noop qdisc on all queues?  */
 static inline bool qdisc_tx_is_noop(const struct net_device *dev)
 {
@@ -1031,6 +1039,21 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh)
 	return skb;
 }
 
+static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool direct)
+{
+	struct sk_buff *skb;
+
+	skb = __skb_dequeue(&sch->gso_skb);
+	if (skb) {
+		sch->q.qlen--;
+		return skb;
+	}
+	if (direct)
+		return __qdisc_dequeue_head(&sch->q);
+	else
+		return sch->dequeue(sch);
+}
+
 static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
 {
 	struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
diff --git a/include/net/scm.h b/include/net/scm.h
index 22bb49589fde..84c4707e78a5 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -102,123 +102,10 @@ static __inline__ int scm_send(struct socket *sock, struct msghdr *msg,
 	return __scm_send(sock, msg, scm);
 }
 
-#ifdef CONFIG_SECURITY_NETWORK
-static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm)
-{
-	struct lsm_context ctx;
-	int err;
-
-	if (test_bit(SOCK_PASSSEC, &sock->flags)) {
-		err = security_secid_to_secctx(scm->secid, &ctx);
-
-		if (err >= 0) {
-			put_cmsg(msg, SOL_SOCKET, SCM_SECURITY, ctx.len,
-				 ctx.context);
-			security_release_secctx(&ctx);
-		}
-	}
-}
-
-static inline bool scm_has_secdata(struct socket *sock)
-{
-	return test_bit(SOCK_PASSSEC, &sock->flags);
-}
-#else
-static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm)
-{ }
-
-static inline bool scm_has_secdata(struct socket *sock)
-{
-	return false;
-}
-#endif /* CONFIG_SECURITY_NETWORK */
-
-static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm)
-{
-	struct file *pidfd_file = NULL;
-	int len, pidfd;
-
-	/* put_cmsg() doesn't return an error if CMSG is truncated,
-	 * that's why we need to opencode these checks here.
-	 */
-	if (msg->msg_flags & MSG_CMSG_COMPAT)
-		len = sizeof(struct compat_cmsghdr) + sizeof(int);
-	else
-		len = sizeof(struct cmsghdr) + sizeof(int);
-
-	if (msg->msg_controllen < len) {
-		msg->msg_flags |= MSG_CTRUNC;
-		return;
-	}
-
-	if (!scm->pid)
-		return;
-
-	pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file);
-
-	if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) {
-		if (pidfd_file) {
-			put_unused_fd(pidfd);
-			fput(pidfd_file);
-		}
-
-		return;
-	}
-
-	if (pidfd_file)
-		fd_install(pidfd, pidfd_file);
-}
-
-static inline bool __scm_recv_common(struct socket *sock, struct msghdr *msg,
-				     struct scm_cookie *scm, int flags)
-{
-	if (!msg->msg_control) {
-		if (test_bit(SOCK_PASSCRED, &sock->flags) ||
-		    test_bit(SOCK_PASSPIDFD, &sock->flags) ||
-		    scm->fp || scm_has_secdata(sock))
-			msg->msg_flags |= MSG_CTRUNC;
-		scm_destroy(scm);
-		return false;
-	}
-
-	if (test_bit(SOCK_PASSCRED, &sock->flags)) {
-		struct user_namespace *current_ns = current_user_ns();
-		struct ucred ucreds = {
-			.pid = scm->creds.pid,
-			.uid = from_kuid_munged(current_ns, scm->creds.uid),
-			.gid = from_kgid_munged(current_ns, scm->creds.gid),
-		};
-		put_cmsg(msg, SOL_SOCKET, SCM_CREDENTIALS, sizeof(ucreds), &ucreds);
-	}
-
-	scm_passec(sock, msg, scm);
-
-	if (scm->fp)
-		scm_detach_fds(msg, scm);
-
-	return true;
-}
-
-static inline void scm_recv(struct socket *sock, struct msghdr *msg,
-			    struct scm_cookie *scm, int flags)
-{
-	if (!__scm_recv_common(sock, msg, scm, flags))
-		return;
-
-	scm_destroy_cred(scm);
-}
-
-static inline void scm_recv_unix(struct socket *sock, struct msghdr *msg,
-				 struct scm_cookie *scm, int flags)
-{
-	if (!__scm_recv_common(sock, msg, scm, flags))
-		return;
-
-	if (test_bit(SOCK_PASSPIDFD, &sock->flags))
-		scm_pidfd_recv(msg, scm);
-
-	scm_destroy_cred(scm);
-}
+void scm_recv(struct socket *sock, struct msghdr *msg,
+	      struct scm_cookie *scm, int flags);
+void scm_recv_unix(struct socket *sock, struct msghdr *msg,
+		   struct scm_cookie *scm, int flags);
 
 static inline int scm_recv_one_fd(struct file *f, int __user *ufd,
 				  unsigned int flags)
diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h
index 291465c25810..654d37ec0402 100644
--- a/include/net/sctp/checksum.h
+++ b/include/net/sctp/checksum.h
@@ -15,8 +15,6 @@
  *    Dinakaran Joseph
  *    Jon Grimm <jgrimm@us.ibm.com>
  *    Sridhar Samudrala <sri@us.ibm.com>
- *
- * Rewritten to use libcrc32c by:
  *    Vlad Yasevich <vladislav.yasevich@hp.com>
  */
 
@@ -25,39 +23,18 @@
 
 #include <linux/types.h>
 #include <linux/sctp.h>
-#include <linux/crc32c.h>
-#include <linux/crc32.h>
-
-static inline __wsum sctp_csum_update(const void *buff, int len, __wsum sum)
-{
-	return (__force __wsum)crc32c((__force __u32)sum, buff, len);
-}
-
-static inline __wsum sctp_csum_combine(__wsum csum, __wsum csum2,
-				       int offset, int len)
-{
-	return (__force __wsum)crc32c_combine((__force __u32)csum,
-					      (__force __u32)csum2, len);
-}
-
-static const struct skb_checksum_ops sctp_csum_ops = {
-	.update  = sctp_csum_update,
-	.combine = sctp_csum_combine,
-};
 
 static inline __le32 sctp_compute_cksum(const struct sk_buff *skb,
 					unsigned int offset)
 {
 	struct sctphdr *sh = (struct sctphdr *)(skb->data + offset);
 	__le32 old = sh->checksum;
-	__wsum new;
+	u32 new;
 
 	sh->checksum = 0;
-	new = ~__skb_checksum(skb, offset, skb->len - offset, ~(__wsum)0,
-			      &sctp_csum_ops);
+	new = ~skb_crc32c(skb, offset, skb->len - offset, ~0);
 	sh->checksum = old;
-
-	return cpu_to_le32((__force __u32)new);
+	return cpu_to_le32(new);
 }
 
 #endif /* __sctp_checksum_h__ */
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 64c42bd56bb2..3bfd261a53cc 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -161,7 +161,6 @@ const struct sctp_sm_table_entry *sctp_sm_lookup_event(
 					enum sctp_event_type event_type,
 					enum sctp_state state,
 					union sctp_subtype event_subtype);
-int sctp_chunk_iif(const struct sctp_chunk *);
 struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *,
 					     struct sctp_chunk *,
 					     gfp_t gfp);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index dcd288fa1bb6..1ad7ce71d0a7 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -2152,8 +2152,6 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *,
 				     const union sctp_addr *address,
 				     const gfp_t gfp,
 				     const int peer_state);
-void sctp_assoc_del_peer(struct sctp_association *asoc,
-			 const union sctp_addr *addr);
 void sctp_assoc_rm_peer(struct sctp_association *asoc,
 			 struct sctp_transport *peer);
 void sctp_assoc_control_transport(struct sctp_association *asoc,
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index 21e7fa2a1813..cddebafb9f77 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -16,9 +16,5 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
 		     __be16 sport, __be16 dport);
 u32 secure_tcpv6_ts_off(const struct net *net,
 			const __be32 *saddr, const __be32 *daddr);
-u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
-				__be16 sport, __be16 dport);
-u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
-				  __be16 sport, __be16 dport);
 
 #endif /* _NET_SECURE_SEQ */
diff --git a/include/net/sock.h b/include/net/sock.h
index 694f954258d4..92e7c1aae3cc 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -337,6 +337,12 @@ struct sk_filter;
   *	@sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
   *	@sk_txtime_report_errors: set report errors mode for SO_TXTIME
   *	@sk_txtime_unused: unused txtime flags
+  *	@sk_scm_recv_flags: all flags used by scm_recv()
+  *	@sk_scm_credentials: flagged by SO_PASSCRED to recv SCM_CREDENTIALS
+  *	@sk_scm_security: flagged by SO_PASSSEC to recv SCM_SECURITY
+  *	@sk_scm_pidfd: flagged by SO_PASSPIDFD to recv SCM_PIDFD
+  *	@sk_scm_rights: flagged by SO_PASSRIGHTS to recv SCM_RIGHTS
+  *	@sk_scm_unused: unused flags for scm_recv()
   *	@ns_tracker: tracker for netns reference
   *	@sk_user_frags: xarray of pages the user is holding a reference on.
   *	@sk_owner: reference to the real owner of the socket that calls
@@ -523,7 +529,17 @@ struct sock {
 #endif
 	int			sk_disconnects;
 
-	u8			sk_txrehash;
+	union {
+		u8		sk_txrehash;
+		u8		sk_scm_recv_flags;
+		struct {
+			u8	sk_scm_credentials : 1,
+				sk_scm_security : 1,
+				sk_scm_pidfd : 1,
+				sk_scm_rights : 1,
+				sk_scm_unused : 4;
+		};
+	};
 	u8			sk_clockid;
 	u8			sk_txtime_deadline_mode : 1,
 				sk_txtime_report_errors : 1,
@@ -1781,7 +1797,6 @@ void sk_free(struct sock *sk);
 void sk_net_refcnt_upgrade(struct sock *sk);
 void sk_destruct(struct sock *sk);
 struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
-void sk_free_unlock_clone(struct sock *sk);
 
 struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
 			     gfp_t priority);
@@ -1852,6 +1867,7 @@ struct sockcm_cookie {
 	u32 tsflags;
 	u32 ts_opt_id;
 	u32 priority;
+	u32 dmabuf_id;
 };
 
 static inline void sockcm_init(struct sockcm_cookie *sockc,
@@ -2605,8 +2621,8 @@ struct sock_skb_cb {
  * using skb->cb[] would keep using it directly and utilize its
  * alignment guarantee.
  */
-#define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \
-			    sizeof(struct sock_skb_cb)))
+#define SOCK_SKB_CB_OFFSET (sizeof_field(struct sk_buff, cb) - \
+			    sizeof(struct sock_skb_cb))
 
 #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \
 			    SOCK_SKB_CB_OFFSET))
@@ -2736,8 +2752,6 @@ static inline void _sock_tx_timestamp(struct sock *sk,
 				*tskey = atomic_inc_return(&sk->sk_tskey) - 1;
 		}
 	}
-	if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS)))
-		*tx_flags |= SKBTX_WIFI_STATUS;
 }
 
 static inline void sock_tx_timestamp(struct sock *sk,
@@ -2775,9 +2789,14 @@ static inline bool sk_is_udp(const struct sock *sk)
 	       sk->sk_protocol == IPPROTO_UDP;
 }
 
+static inline bool sk_is_unix(const struct sock *sk)
+{
+	return sk->sk_family == AF_UNIX;
+}
+
 static inline bool sk_is_stream_unix(const struct sock *sk)
 {
-	return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM;
+	return sk_is_unix(sk) && sk->sk_type == SOCK_STREAM;
 }
 
 static inline bool sk_is_vsock(const struct sock *sk)
@@ -2785,6 +2804,13 @@ static inline bool sk_is_vsock(const struct sock *sk)
 	return sk->sk_family == AF_VSOCK;
 }
 
+static inline bool sk_may_scm_recv(const struct sock *sk)
+{
+	return (IS_ENABLED(CONFIG_UNIX) && sk->sk_family == AF_UNIX) ||
+		sk->sk_family == AF_NETLINK ||
+		(IS_ENABLED(CONFIG_BT) && sk->sk_family == AF_BLUETOOTH);
+}
+
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
  * @sk: socket to eat this skb from
@@ -2824,6 +2850,12 @@ sk_is_refcounted(struct sock *sk)
 	return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE);
 }
 
+static inline bool
+sk_requests_wifi_status(struct sock *sk)
+{
+	return sk && sk_fullsock(sk) && sock_flag(sk, SOCK_WIFI_STATUS);
+}
+
 /* Checks if this SKB belongs to an HW offloaded socket
  * and whether any SW fallbacks are required based on dev.
  * Check decrypted mark in case skb_orphan() cleared socket.
diff --git a/include/net/strparser.h b/include/net/strparser.h
index 0a83010b3a64..0ed73e364faa 100644
--- a/include/net/strparser.h
+++ b/include/net/strparser.h
@@ -114,8 +114,6 @@ static inline void strp_pause(struct strparser *strp)
 
 /* May be called without holding lock for attached socket */
 void strp_unpause(struct strparser *strp);
-/* Must be called with process lock held (lock_sock) */
-void __strp_unpause(struct strparser *strp);
 
 static inline void save_strp_stats(struct strparser *strp,
 				   struct strp_aggr_stats *agg_stats)
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 288f06f23a80..2df3b8344eb5 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -215,7 +215,6 @@ static inline void udp_tunnel_encap_enable(struct sock *sk)
 	if (READ_ONCE(sk->sk_family) == PF_INET6)
 		ipv6_stub->udpv6_encap_enable();
 #endif
-	udp_tunnel_update_gro_rcv(sk, true);
 	udp_encap_enable();
 }
 
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 2dd23ee2bacd..e2f7ca045d3e 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -296,7 +296,7 @@ struct vxlan_dev {
 	struct vxlan_rdst default_dst;	/* default destination */
 
 	struct timer_list age_timer;
-	spinlock_t	  hash_lock[FDB_HASH_SIZE];
+	spinlock_t	  hash_lock;
 	unsigned int	  addrcnt;
 	struct gro_cells  gro_cells;
 
@@ -304,9 +304,10 @@ struct vxlan_dev {
 
 	struct vxlan_vni_group  __rcu *vnigrp;
 
-	struct hlist_head fdb_head[FDB_HASH_SIZE];
+	struct rhashtable fdb_hash_tbl;
 
 	struct rhashtable mdb_tbl;
+	struct hlist_head fdb_list;
 	struct hlist_head mdb_list;
 	unsigned int mdb_seq;
 };
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 20e41b5ff319..b40f1f96cb11 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -618,7 +618,10 @@ bool bpf_dev_bound_kfunc_id(u32 btf_id);
 void xdp_set_features_flag(struct net_device *dev, xdp_features_t val);
 void xdp_set_features_flag_locked(struct net_device *dev, xdp_features_t val);
 void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg);
+void xdp_features_set_redirect_target_locked(struct net_device *dev,
+					     bool support_sg);
 void xdp_features_clear_redirect_target(struct net_device *dev);
+void xdp_features_clear_redirect_target_locked(struct net_device *dev);
 #else
 static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; }
 static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; }
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index a58ae7589d12..e8bd6ddb7b12 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -71,9 +71,6 @@ struct xdp_sock {
 	 */
 	u32 tx_budget_spent;
 
-	/* Protects generic receive. */
-	spinlock_t rx_lock;
-
 	/* Statistics */
 	u64 rx_dropped;
 	u64 rx_queue_full;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 466423a1a70a..a21e276dbe44 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -247,7 +247,6 @@ struct xfrm_state {
 
 	/* Data for encapsulator */
 	struct xfrm_encap_tmpl	*encap;
-	struct sock __rcu	*encap_sk;
 
 	/* NAT keepalive */
 	u32			nat_keepalive_interval; /* seconds */
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 1dcd4d71468a..cac56e6b0869 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -53,6 +53,8 @@ struct xsk_buff_pool {
 	refcount_t users;
 	struct xdp_umem *umem;
 	struct work_struct work;
+	/* Protects generic receive in shared and non-shared umem mode. */
+	spinlock_t rx_lock;
 	struct list_head free_list;
 	struct list_head xskb_list;
 	u32 heads_cnt;
@@ -238,8 +240,8 @@ static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb,
 		return orig_addr;
 
 	offset = xskb->xdp.data - xskb->xdp.data_hard_start;
-	orig_addr -= offset;
 	offset += pool->headroom;
+	orig_addr -= offset;
 	return orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
 }
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index d42eae69d9a8..901353796fbb 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -4790,7 +4790,14 @@ void roce_del_all_netdev_gids(struct ib_device *ib_dev,
 
 struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile);
 
+#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
 int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs);
+#else
+static inline int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs)
+{
+	return 0;
+}
+#endif
 
 struct net_device *rdma_alloc_netdev(struct ib_device *device, u32 port_num,
 				     enum rdma_netdev_t type, const char *name,
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 6db7fc9dbaa4..48d6deb3efd7 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -1073,8 +1073,11 @@ int ocelot_vlan_prepare(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 		    bool untagged);
 int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid);
-int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr);
-int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr);
+void ocelot_hwstamp_get(struct ocelot *ocelot, int port,
+			struct kernel_hwtstamp_config *cfg);
+int ocelot_hwstamp_set(struct ocelot *ocelot, int port,
+		       struct kernel_hwtstamp_config *cfg,
+		       struct netlink_ext_ack *extack);
 int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port,
 				 struct sk_buff *skb,
 				 struct sk_buff **clone);
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 8becb4504887..8582d22f3818 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -1404,6 +1404,8 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s
 #define snd_pcm_lib_mmap_iomem	NULL
 #endif
 
+void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime);
+
 /**
  * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer
  * @dma: DMA number
diff --git a/include/sound/soc_sdw_utils.h b/include/sound/soc_sdw_utils.h
index 36a4a1e1d8ca..d8bd5d37131a 100644
--- a/include/sound/soc_sdw_utils.h
+++ b/include/sound/soc_sdw_utils.h
@@ -226,6 +226,7 @@ int asoc_sdw_cs_amp_init(struct snd_soc_card *card,
 			 bool playback);
 int asoc_sdw_cs_spk_feedback_rtd_init(struct snd_soc_pcm_runtime *rtd,
 				      struct snd_soc_dai *dai);
+int asoc_sdw_cs35l56_volume_limit(struct snd_soc_card *card, const char *name_prefix);
 
 /* MAXIM codec support */
 int asoc_sdw_maxim_init(struct snd_soc_card *card,
diff --git a/include/sound/ump_convert.h b/include/sound/ump_convert.h
index d099ae27f849..682499b871ea 100644
--- a/include/sound/ump_convert.h
+++ b/include/sound/ump_convert.h
@@ -19,7 +19,7 @@ struct ump_cvt_to_ump_bank {
 /* context for converting from MIDI1 byte stream to UMP packet */
 struct ump_cvt_to_ump {
 	/* MIDI1 intermediate buffer */
-	unsigned char buf[4];
+	unsigned char buf[6]; /* up to 6 bytes for SysEx */
 	int len;
 	int cmd_bytes;
 
diff --git a/include/sound/ump_msg.h b/include/sound/ump_msg.h
index 72f60ddfea75..9556b4755a1e 100644
--- a/include/sound/ump_msg.h
+++ b/include/sound/ump_msg.h
@@ -604,7 +604,7 @@ struct snd_ump_stream_msg_ep_info {
 } __packed;
 
 /* UMP Stream Message: Device Info Notification (128bit) */
-struct snd_ump_stream_msg_devince_info {
+struct snd_ump_stream_msg_device_info {
 #ifdef __BIG_ENDIAN_BITFIELD
 	/* 0 */
 	u32 type:4;
@@ -754,7 +754,7 @@ struct snd_ump_stream_msg_fb_name {
 union snd_ump_stream_msg {
 	struct snd_ump_stream_msg_ep_discovery ep_discovery;
 	struct snd_ump_stream_msg_ep_info ep_info;
-	struct snd_ump_stream_msg_devince_info device_info;
+	struct snd_ump_stream_msg_device_info device_info;
 	struct snd_ump_stream_msg_stream_cfg stream_cfg;
 	struct snd_ump_stream_msg_fb_discovery fb_discovery;
 	struct snd_ump_stream_msg_fb_info fb_info;
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 8857f5ea77d4..7f83d242c8e9 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -663,19 +663,26 @@ TRACE_EVENT(afs_cb_call,
 		    __field(unsigned int,		call)
 		    __field(u32,			op)
 		    __field(u16,			service_id)
+		    __field(u8,				security_ix)
+		    __field(u32,			enctype)
 			     ),
 
 	    TP_fast_assign(
 		    __entry->call	= call->debug_id;
 		    __entry->op		= call->operation_ID;
 		    __entry->service_id	= call->service_id;
+		    __entry->security_ix = call->security_ix;
+		    __entry->enctype	= call->enctype;
 			   ),
 
-	    TP_printk("c=%08x %s",
+	    TP_printk("c=%08x %s sv=%u sx=%u en=%u",
 		      __entry->call,
 		      __entry->service_id == 2501 ?
 		      __print_symbolic(__entry->op, yfs_cm_operations) :
-		      __print_symbolic(__entry->op, afs_cm_operations))
+		      __print_symbolic(__entry->op, afs_cm_operations),
+		      __entry->service_id,
+		      __entry->security_ix,
+		      __entry->enctype)
 	    );
 
 TRACE_EVENT(afs_call,
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 549ab3b41961..3efc00cc1bcd 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -1928,7 +1928,7 @@ DECLARE_EVENT_CLASS(btrfs__prelim_ref,
 	TP_PROTO(const struct btrfs_fs_info *fs_info,
 		 const struct prelim_ref *oldref,
 		 const struct prelim_ref *newref, u64 tree_size),
-	TP_ARGS(fs_info, newref, oldref, tree_size),
+	TP_ARGS(fs_info, oldref, newref, tree_size),
 
 	TP_STRUCT__entry_btrfs(
 		__field(	u64,  root_id		)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index cad50d91077e..378d2dfc7392 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -25,6 +25,7 @@
 	EM(afs_abort_probeuuid_negative,	"afs-probeuuid-neg")	\
 	EM(afs_abort_send_data_error,		"afs-send-data")	\
 	EM(afs_abort_unmarshal_error,		"afs-unmarshal")	\
+	EM(afs_abort_unsupported_sec_class,	"afs-unsup-sec-class")	\
 	/* rxperf errors */						\
 	EM(rxperf_abort_general_error,		"rxperf-error")		\
 	EM(rxperf_abort_oom,			"rxperf-oom")		\
@@ -68,6 +69,38 @@
 	EM(rxkad_abort_resp_tkt_sname,		"rxkad-resp-tk-sname")	\
 	EM(rxkad_abort_resp_unknown_tkt,	"rxkad-resp-unknown-tkt") \
 	EM(rxkad_abort_resp_version,		"rxkad-resp-version")	\
+	/* RxGK security errors */					\
+	EM(rxgk_abort_1_verify_mic_eproto,	"rxgk1-vfy-mic-eproto")	\
+	EM(rxgk_abort_2_decrypt_eproto,		"rxgk2-dec-eproto")	\
+	EM(rxgk_abort_2_short_data,		"rxgk2-short-data")	\
+	EM(rxgk_abort_2_short_encdata,		"rxgk2-short-encdata")	\
+	EM(rxgk_abort_2_short_header,		"rxgk2-short-hdr")	\
+	EM(rxgk_abort_bad_key_number,		"rxgk-bad-key-num")	\
+	EM(rxgk_abort_chall_key_expired,	"rxgk-chall-key-exp")	\
+	EM(rxgk_abort_chall_no_key,		"rxgk-chall-nokey")	\
+	EM(rxgk_abort_chall_short,		"rxgk-chall-short")	\
+	EM(rxgk_abort_resp_auth_dec,		"rxgk-resp-auth-dec")	\
+	EM(rxgk_abort_resp_bad_callid,		"rxgk-resp-bad-callid")	\
+	EM(rxgk_abort_resp_bad_nonce,		"rxgk-resp-bad-nonce")	\
+	EM(rxgk_abort_resp_bad_param,		"rxgk-resp-bad-param")	\
+	EM(rxgk_abort_resp_call_ctr,		"rxgk-resp-call-ctr")	\
+	EM(rxgk_abort_resp_call_state,		"rxgk-resp-call-state")	\
+	EM(rxgk_abort_resp_internal_error,	"rxgk-resp-int-error")	\
+	EM(rxgk_abort_resp_nopkg,		"rxgk-resp-nopkg")	\
+	EM(rxgk_abort_resp_short_applen,	"rxgk-resp-short-applen") \
+	EM(rxgk_abort_resp_short_auth,		"rxgk-resp-short-auth") \
+	EM(rxgk_abort_resp_short_call_list,	"rxgk-resp-short-callls") \
+	EM(rxgk_abort_resp_short_packet,	"rxgk-resp-short-packet") \
+	EM(rxgk_abort_resp_short_yfs_klen,	"rxgk-resp-short-yfs-klen") \
+	EM(rxgk_abort_resp_short_yfs_key,	"rxgk-resp-short-yfs-key") \
+	EM(rxgk_abort_resp_short_yfs_tkt,	"rxgk-resp-short-yfs-tkt") \
+	EM(rxgk_abort_resp_tok_dec,		"rxgk-resp-tok-dec")	\
+	EM(rxgk_abort_resp_tok_internal_error,	"rxgk-resp-tok-int-err") \
+	EM(rxgk_abort_resp_tok_keyerr,		"rxgk-resp-tok-keyerr")	\
+	EM(rxgk_abort_resp_tok_nokey,		"rxgk-resp-tok-nokey")	\
+	EM(rxgk_abort_resp_tok_nopkg,		"rxgk-resp-tok-nopkg")	\
+	EM(rxgk_abort_resp_tok_short,		"rxgk-resp-tok-short")	\
+	EM(rxgk_abort_resp_xdr_align,		"rxgk-resp-xdr-align")	\
 	/* rxrpc errors */						\
 	EM(rxrpc_abort_call_improper_term,	"call-improper-term")	\
 	EM(rxrpc_abort_call_reset,		"call-reset")		\
@@ -77,6 +110,7 @@
 	EM(rxrpc_abort_call_timeout,		"call-timeout")		\
 	EM(rxrpc_abort_no_service_key,		"no-serv-key")		\
 	EM(rxrpc_abort_nomem,			"nomem")		\
+	EM(rxrpc_abort_response_sendmsg,	"resp-sendmsg")		\
 	EM(rxrpc_abort_service_not_offered,	"serv-not-offered")	\
 	EM(rxrpc_abort_shut_down,		"shut-down")		\
 	EM(rxrpc_abort_unsupported_security,	"unsup-sec")		\
@@ -133,24 +167,33 @@
 	EM(rxrpc_skb_get_conn_secured,		"GET conn-secd") \
 	EM(rxrpc_skb_get_conn_work,		"GET conn-work") \
 	EM(rxrpc_skb_get_local_work,		"GET locl-work") \
+	EM(rxrpc_skb_get_post_oob,		"GET post-oob ") \
 	EM(rxrpc_skb_get_reject_work,		"GET rej-work ") \
 	EM(rxrpc_skb_get_to_recvmsg,		"GET to-recv  ") \
 	EM(rxrpc_skb_get_to_recvmsg_oos,	"GET to-recv-o") \
 	EM(rxrpc_skb_new_encap_rcv,		"NEW encap-rcv") \
 	EM(rxrpc_skb_new_error_report,		"NEW error-rpt") \
 	EM(rxrpc_skb_new_jumbo_subpacket,	"NEW jumbo-sub") \
+	EM(rxrpc_skb_new_response_rxgk,		"NEW resp-rxgk") \
+	EM(rxrpc_skb_new_response_rxkad,	"NEW resp-rxkd") \
 	EM(rxrpc_skb_new_unshared,		"NEW unshared ") \
 	EM(rxrpc_skb_put_call_rx,		"PUT call-rx  ") \
+	EM(rxrpc_skb_put_challenge,		"PUT challenge") \
 	EM(rxrpc_skb_put_conn_secured,		"PUT conn-secd") \
 	EM(rxrpc_skb_put_conn_work,		"PUT conn-work") \
 	EM(rxrpc_skb_put_error_report,		"PUT error-rep") \
 	EM(rxrpc_skb_put_input,			"PUT input    ") \
 	EM(rxrpc_skb_put_jumbo_subpacket,	"PUT jumbo-sub") \
+	EM(rxrpc_skb_put_oob,			"PUT oob      ") \
 	EM(rxrpc_skb_put_purge,			"PUT purge    ") \
+	EM(rxrpc_skb_put_purge_oob,		"PUT purge-oob") \
+	EM(rxrpc_skb_put_response,		"PUT response ") \
 	EM(rxrpc_skb_put_rotate,		"PUT rotate   ") \
 	EM(rxrpc_skb_put_unknown,		"PUT unknown  ") \
 	EM(rxrpc_skb_see_conn_work,		"SEE conn-work") \
+	EM(rxrpc_skb_see_oob_challenge,		"SEE oob-chall") \
 	EM(rxrpc_skb_see_recvmsg,		"SEE recvmsg  ") \
+	EM(rxrpc_skb_see_recvmsg_oob,		"SEE recvm-oob") \
 	EM(rxrpc_skb_see_reject,		"SEE reject   ") \
 	EM(rxrpc_skb_see_rotate,		"SEE rotate   ") \
 	E_(rxrpc_skb_see_version,		"SEE version  ")
@@ -216,9 +259,11 @@
 	EM(rxrpc_conn_free,			"FREE        ") \
 	EM(rxrpc_conn_get_activate_call,	"GET act-call") \
 	EM(rxrpc_conn_get_call_input,		"GET inp-call") \
+	EM(rxrpc_conn_get_challenge_input,	"GET inp-chal") \
 	EM(rxrpc_conn_get_conn_input,		"GET inp-conn") \
 	EM(rxrpc_conn_get_idle,			"GET idle    ") \
 	EM(rxrpc_conn_get_poke_abort,		"GET pk-abort") \
+	EM(rxrpc_conn_get_poke_response,	"GET response") \
 	EM(rxrpc_conn_get_poke_secured,		"GET secured ") \
 	EM(rxrpc_conn_get_poke_timer,		"GET poke    ") \
 	EM(rxrpc_conn_get_service_conn,		"GET svc-conn") \
@@ -226,10 +271,12 @@
 	EM(rxrpc_conn_new_service,		"NEW service ") \
 	EM(rxrpc_conn_put_call,			"PUT call    ") \
 	EM(rxrpc_conn_put_call_input,		"PUT inp-call") \
+	EM(rxrpc_conn_put_challenge_input,	"PUT inp-chal") \
 	EM(rxrpc_conn_put_conn_input,		"PUT inp-conn") \
 	EM(rxrpc_conn_put_discard_idle,		"PUT disc-idl") \
 	EM(rxrpc_conn_put_local_dead,		"PUT loc-dead") \
 	EM(rxrpc_conn_put_noreuse,		"PUT noreuse ") \
+	EM(rxrpc_conn_put_oob,			"PUT oob     ") \
 	EM(rxrpc_conn_put_poke,			"PUT poke    ") \
 	EM(rxrpc_conn_put_service_reaped,	"PUT svc-reap") \
 	EM(rxrpc_conn_put_unbundle,		"PUT unbundle") \
@@ -331,6 +378,7 @@
 	EM(rxrpc_recvmsg_full,			"FULL") \
 	EM(rxrpc_recvmsg_hole,			"HOLE") \
 	EM(rxrpc_recvmsg_next,			"NEXT") \
+	EM(rxrpc_recvmsg_oobq,			"OOBQ") \
 	EM(rxrpc_recvmsg_requeue,		"REQU") \
 	EM(rxrpc_recvmsg_return,		"RETN") \
 	EM(rxrpc_recvmsg_terminal,		"TERM") \
@@ -455,8 +503,9 @@
 	EM(rxrpc_tx_point_call_final_resend,	"CallFinalResend") \
 	EM(rxrpc_tx_point_conn_abort,		"ConnAbort") \
 	EM(rxrpc_tx_point_reject,		"Reject") \
+	EM(rxrpc_tx_point_rxgk_challenge,	"RxGKChall") \
 	EM(rxrpc_tx_point_rxkad_challenge,	"RxkadChall") \
-	EM(rxrpc_tx_point_rxkad_response,	"RxkadResp") \
+	EM(rxrpc_tx_point_response,		"Response") \
 	EM(rxrpc_tx_point_version_keepalive,	"VerKeepalive") \
 	E_(rxrpc_tx_point_version_reply,	"VerReply")
 
@@ -473,6 +522,7 @@
 
 #define rxrpc_txbuf_traces \
 	EM(rxrpc_txbuf_alloc_data,		"ALLOC DATA ")	\
+	EM(rxrpc_txbuf_alloc_response,		"ALLOC RESP ")	\
 	EM(rxrpc_txbuf_free,			"FREE       ")	\
 	EM(rxrpc_txbuf_get_buffer,		"GET BUFFER ")	\
 	EM(rxrpc_txbuf_get_trans,		"GET TRANS  ")	\
@@ -480,6 +530,7 @@
 	EM(rxrpc_txbuf_put_cleaned,		"PUT CLEANED")	\
 	EM(rxrpc_txbuf_put_nomem,		"PUT NOMEM  ")	\
 	EM(rxrpc_txbuf_put_rotated,		"PUT ROTATED")	\
+	EM(rxrpc_txbuf_put_response_tx,		"PUT RESP TX")	\
 	EM(rxrpc_txbuf_put_send_aborted,	"PUT SEND-X ")	\
 	EM(rxrpc_txbuf_put_trans,		"PUT TRANS  ")	\
 	EM(rxrpc_txbuf_see_lost,		"SEE LOST   ")	\
@@ -1150,6 +1201,39 @@ TRACE_EVENT(rxrpc_rx_conn_abort,
 		      __entry->abort_code)
 	    );
 
+TRACE_EVENT(rxrpc_tx_challenge,
+	    TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t serial,
+		     u32 version, u32 nonce),
+
+	    TP_ARGS(conn, serial, version, nonce),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	conn)
+		    __field(rxrpc_serial_t,	serial)
+		    __field(u32,		version)
+		    __field(u32,		nonce)
+		    __field(u16,		service_id)
+		    __field(u8,			security_ix)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->conn = conn->debug_id;
+		    __entry->serial = serial;
+		    __entry->version = version;
+		    __entry->nonce = nonce;
+		    __entry->service_id = conn->service_id;
+		    __entry->security_ix = conn->security_ix;
+			   ),
+
+	    TP_printk("C=%08x CHALLENGE r=%08x sv=%u+%u v=%x n=%x",
+		      __entry->conn,
+		      __entry->serial,
+		      __entry->service_id,
+		      __entry->security_ix,
+		      __entry->version,
+		      __entry->nonce)
+	    );
+
 TRACE_EVENT(rxrpc_rx_challenge,
 	    TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t serial,
 		     u32 version, u32 nonce, u32 min_level),
@@ -1162,6 +1246,8 @@ TRACE_EVENT(rxrpc_rx_challenge,
 		    __field(u32,		version)
 		    __field(u32,		nonce)
 		    __field(u32,		min_level)
+		    __field(u16,		service_id)
+		    __field(u8,			security_ix)
 			     ),
 
 	    TP_fast_assign(
@@ -1170,16 +1256,60 @@ TRACE_EVENT(rxrpc_rx_challenge,
 		    __entry->version = version;
 		    __entry->nonce = nonce;
 		    __entry->min_level = min_level;
+		    __entry->service_id = conn->service_id;
+		    __entry->security_ix = conn->security_ix;
 			   ),
 
-	    TP_printk("C=%08x CHALLENGE %08x v=%x n=%x ml=%x",
+	    TP_printk("C=%08x CHALLENGE r=%08x sv=%u+%u v=%x n=%x ml=%x",
 		      __entry->conn,
 		      __entry->serial,
+		      __entry->service_id,
+		      __entry->security_ix,
 		      __entry->version,
 		      __entry->nonce,
 		      __entry->min_level)
 	    );
 
+TRACE_EVENT(rxrpc_tx_response,
+	    TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t serial,
+		     struct rxrpc_skb_priv *rsp),
+
+	    TP_ARGS(conn, serial, rsp),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	conn)
+		    __field(rxrpc_serial_t,	serial)
+		    __field(rxrpc_serial_t,	challenge)
+		    __field(u32,		version)
+		    __field(u32,		kvno)
+		    __field(u16,		ticket_len)
+		    __field(u16,		appdata_len)
+		    __field(u16,		service_id)
+		    __field(u8,			security_ix)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->conn	= conn->debug_id;
+		    __entry->serial	= serial;
+		    __entry->challenge	= rsp->resp.challenge_serial;
+		    __entry->version	= rsp->resp.version;
+		    __entry->kvno	= rsp->resp.kvno;
+		    __entry->ticket_len = rsp->resp.ticket_len;
+		    __entry->service_id = conn->service_id;
+		    __entry->security_ix = conn->security_ix;
+			   ),
+
+	    TP_printk("C=%08x RESPONSE r=%08x cr=%08x sv=%u+%u v=%x kv=%x tl=%u",
+		      __entry->conn,
+		      __entry->serial,
+		      __entry->challenge,
+		      __entry->service_id,
+		      __entry->security_ix,
+		      __entry->version,
+		      __entry->kvno,
+		      __entry->ticket_len)
+	    );
+
 TRACE_EVENT(rxrpc_rx_response,
 	    TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t serial,
 		     u32 version, u32 kvno, u32 ticket_len),
@@ -1192,6 +1322,7 @@ TRACE_EVENT(rxrpc_rx_response,
 		    __field(u32,		version)
 		    __field(u32,		kvno)
 		    __field(u32,		ticket_len)
+		    __field(u8,			security_ix)
 			     ),
 
 	    TP_fast_assign(
@@ -1200,11 +1331,13 @@ TRACE_EVENT(rxrpc_rx_response,
 		    __entry->version = version;
 		    __entry->kvno = kvno;
 		    __entry->ticket_len = ticket_len;
+		    __entry->security_ix = conn->security_ix;
 			   ),
 
-	    TP_printk("C=%08x RESPONSE %08x v=%x kvno=%x tl=%x",
+	    TP_printk("C=%08x RESPONSE r=%08x sx=%u v=%x kvno=%x tl=%x",
 		      __entry->conn,
 		      __entry->serial,
+		      __entry->security_ix,
 		      __entry->version,
 		      __entry->kvno,
 		      __entry->ticket_len)
@@ -2668,6 +2801,30 @@ TRACE_EVENT(rxrpc_rack_timer,
 		      ktime_to_us(__entry->delay))
 	    );
 
+TRACE_EVENT(rxrpc_rxgk_rekey,
+	    TP_PROTO(struct rxrpc_connection *conn,
+		     unsigned int current_key, unsigned int requested_key),
+
+	    TP_ARGS(conn, current_key, requested_key),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	conn)
+		    __field(unsigned int,	current_key)
+		    __field(unsigned int,	requested_key)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->conn		= conn->debug_id;
+		    __entry->current_key	= current_key;
+		    __entry->requested_key	= requested_key;
+			   ),
+
+	    TP_printk("C=%08x cur=%x req=%x",
+		      __entry->conn,
+		      __entry->current_key,
+		      __entry->requested_key)
+	    );
+
 #undef EM
 #undef E_
 
diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index 3836de435d9d..b5310439536e 100644
--- a/include/trace/events/sock.h
+++ b/include/trace/events/sock.h
@@ -19,7 +19,6 @@
 /* The protocol traced by inet_sock_set_state */
 #define inet_protocol_names		\
 		EM(IPPROTO_TCP)			\
-		EM(IPPROTO_DCCP)		\
 		EM(IPPROTO_SCTP)		\
 		EMe(IPPROTO_MPTCP)
 
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 5d331383047b..de214f1dea58 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -21,7 +21,6 @@ TRACE_DEFINE_ENUM(SOCK_DGRAM);
 TRACE_DEFINE_ENUM(SOCK_RAW);
 TRACE_DEFINE_ENUM(SOCK_RDM);
 TRACE_DEFINE_ENUM(SOCK_SEQPACKET);
-TRACE_DEFINE_ENUM(SOCK_DCCP);
 TRACE_DEFINE_ENUM(SOCK_PACKET);
 
 #define show_socket_type(type)					\
@@ -31,7 +30,6 @@ TRACE_DEFINE_ENUM(SOCK_PACKET);
 		{ SOCK_RAW,		"RAW" },		\
 		{ SOCK_RDM,		"RDM" },		\
 		{ SOCK_SEQPACKET,	"SEQPACKET" },		\
-		{ SOCK_DCCP,		"DCCP" },		\
 		{ SOCK_PACKET,		"PACKET" })
 
 /* This list is known to be incomplete, add new enums as needed. */
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 75d3d53a3832..006c2116c8f6 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -213,6 +213,79 @@ DEFINE_EVENT(tcp_event_sk, tcp_rcv_space_adjust,
 	TP_ARGS(sk)
 );
 
+TRACE_EVENT(tcp_rcvbuf_grow,
+
+	TP_PROTO(struct sock *sk, int time),
+
+	TP_ARGS(sk, time),
+
+	TP_STRUCT__entry(
+		__field(int, time)
+		__field(__u32, rtt_us)
+		__field(__u32, copied)
+		__field(__u32, inq)
+		__field(__u32, space)
+		__field(__u32, ooo_space)
+		__field(__u32, rcvbuf)
+		__field(__u8, scaling_ratio)
+		__field(__u16, sport)
+		__field(__u16, dport)
+		__field(__u16, family)
+		__array(__u8, saddr, 4)
+		__array(__u8, daddr, 4)
+		__array(__u8, saddr_v6, 16)
+		__array(__u8, daddr_v6, 16)
+		__field(const void *, skaddr)
+		__field(__u64, sock_cookie)
+	),
+
+	TP_fast_assign(
+		struct inet_sock *inet = inet_sk(sk);
+		struct tcp_sock *tp = tcp_sk(sk);
+		__be32 *p32;
+
+		__entry->time = time;
+		__entry->rtt_us = tp->rcv_rtt_est.rtt_us >> 3;
+		__entry->copied = tp->copied_seq - tp->rcvq_space.seq;
+		__entry->inq = tp->rcv_nxt - tp->copied_seq;
+		__entry->space = tp->rcvq_space.space;
+		__entry->ooo_space = RB_EMPTY_ROOT(&tp->out_of_order_queue) ? 0 :
+				     TCP_SKB_CB(tp->ooo_last_skb)->end_seq -
+				     tp->rcv_nxt;
+
+		__entry->rcvbuf = sk->sk_rcvbuf;
+		__entry->scaling_ratio = tp->scaling_ratio;
+		__entry->sport = ntohs(inet->inet_sport);
+		__entry->dport = ntohs(inet->inet_dport);
+		__entry->family = sk->sk_family;
+
+		p32 = (__be32 *) __entry->saddr;
+		*p32 = inet->inet_saddr;
+
+		p32 = (__be32 *) __entry->daddr;
+		*p32 = inet->inet_daddr;
+
+		TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr,
+			       sk->sk_v6_rcv_saddr, sk->sk_v6_daddr);
+
+		__entry->skaddr = sk;
+		__entry->sock_cookie = sock_gen_cookie(sk);
+	),
+
+	TP_printk("time=%u rtt_us=%u copied=%u inq=%u space=%u ooo=%u scaling_ratio=%u rcvbuf=%u "
+		  "family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 "
+		  "saddrv6=%pI6c daddrv6=%pI6c skaddr=%p sock_cookie=%llx",
+		  __entry->time, __entry->rtt_us, __entry->copied,
+		  __entry->inq, __entry->space, __entry->ooo_space,
+		  __entry->scaling_ratio, __entry->rcvbuf,
+		  show_family_name(__entry->family),
+		  __entry->sport, __entry->dport,
+		  __entry->saddr, __entry->daddr,
+		  __entry->saddr_v6, __entry->daddr_v6,
+		  __entry->skaddr,
+		  __entry->sock_cookie)
+);
+
 TRACE_EVENT(tcp_retransmit_synack,
 
 	TP_PROTO(const struct sock *sk, const struct request_sock *req),
@@ -293,7 +366,7 @@ DECLARE_TRACE(tcp_cwnd_reduction_tp,
 
 TRACE_EVENT(tcp_probe,
 
-	TP_PROTO(struct sock *sk, struct sk_buff *skb),
+	TP_PROTO(struct sock *sk, const struct sk_buff *skb),
 
 	TP_ARGS(sk, skb),
 
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index aa5016ff3d91..f333a0ac4ee4 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -145,6 +145,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/include/uapi/cxl/features.h b/include/uapi/cxl/features.h
index d6db8984889f..490606d7694b 100644
--- a/include/uapi/cxl/features.h
+++ b/include/uapi/cxl/features.h
@@ -8,10 +8,19 @@
 #define _UAPI_CXL_FEATURES_H_
 
 #include <linux/types.h>
-#ifndef __KERNEL__
-#include <uuid/uuid.h>
-#else
+
+typedef unsigned char __uapi_uuid_t[16];
+
+#ifdef __KERNEL__
 #include <linux/uuid.h>
+/*
+ * Note, __uapi_uuid_t is 1-byte aligned on modern compilers and 4-byte
+ * aligned on others. Ensure that __uapi_uuid_t in a struct is placed at
+ * a 4-byte aligned offset, or the structure is packed, to ensure
+ * consistent padding.
+ */
+static_assert(sizeof(__uapi_uuid_t) == sizeof(uuid_t));
+#define __uapi_uuid_t uuid_t
 #endif
 
 /*
@@ -60,7 +69,7 @@ struct cxl_mbox_get_sup_feats_in {
  * Get Supported Features Supported Feature Entry
  */
 struct cxl_feat_entry {
-	uuid_t uuid;
+	__uapi_uuid_t uuid;
 	__le16 id;
 	__le16 get_feat_size;
 	__le16 set_feat_size;
@@ -110,7 +119,7 @@ struct cxl_mbox_get_sup_feats_out {
  * CXL spec r3.2 section 8.2.9.6.2 Table 8-99
  */
 struct cxl_mbox_get_feat_in {
-	uuid_t uuid;
+	__uapi_uuid_t uuid;
 	__le16 offset;
 	__le16 count;
 	__u8 selection;
@@ -143,7 +152,7 @@ enum cxl_get_feat_selection {
  */
 struct cxl_mbox_set_feat_in {
 	__struct_group(cxl_mbox_set_feat_hdr, hdr, /* no attrs */,
-		uuid_t uuid;
+		__uapi_uuid_t uuid;
 		__le32 flags;
 		__le16 offset;
 		__u8 version;
diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h
index 746c43bd3eb6..2f24103f4533 100644
--- a/include/uapi/drm/ivpu_accel.h
+++ b/include/uapi/drm/ivpu_accel.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #ifndef __UAPI_IVPU_DRM_H__
@@ -147,7 +147,7 @@ struct drm_ivpu_param {
 	 * platform type when executing on a simulator or emulator (read-only)
 	 *
 	 * %DRM_IVPU_PARAM_CORE_CLOCK_RATE:
-	 * Current PLL frequency (read-only)
+	 * Maximum frequency of the NPU data processing unit clock (read-only)
 	 *
 	 * %DRM_IVPU_PARAM_NUM_CONTEXTS:
 	 * Maximum number of simultaneously existing contexts (read-only)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 28705ae67784..fd404729b115 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4968,6 +4968,9 @@ union bpf_attr {
  * 		the netns switch takes place from ingress to ingress without
  * 		going through the CPU's backlog queue.
  *
+ * 		*skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during
+ * 		the netns switch.
+ *
  * 		The *flags* argument is reserved and must be 0. The helper is
  * 		currently only supported for tc BPF program types at the
  * 		ingress hook and for veth and netkit target device types. The
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 9401aa343673..a5ee0f13740a 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -385,6 +385,21 @@ enum devlink_linecard_state {
 	DEVLINK_LINECARD_STATE_MAX = __DEVLINK_LINECARD_STATE_MAX - 1
 };
 
+/* Variable attribute type. */
+enum devlink_var_attr_type {
+	/* Following values relate to the internal NLA_* values */
+	DEVLINK_VAR_ATTR_TYPE_U8 = 1,
+	DEVLINK_VAR_ATTR_TYPE_U16,
+	DEVLINK_VAR_ATTR_TYPE_U32,
+	DEVLINK_VAR_ATTR_TYPE_U64,
+	DEVLINK_VAR_ATTR_TYPE_STRING,
+	DEVLINK_VAR_ATTR_TYPE_FLAG,
+	DEVLINK_VAR_ATTR_TYPE_NUL_STRING = 10,
+	DEVLINK_VAR_ATTR_TYPE_BINARY,
+	__DEVLINK_VAR_ATTR_TYPE_CUSTOM_BASE = 0x80,
+	/* Any possible custom types, unrelated to NLA_* values go below */
+};
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 84833cca29fe..707c1844010c 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -2295,71 +2295,75 @@ static inline int ethtool_validate_duplex(__u8 duplex)
 #define	RXH_XFRM_SYM_OR_XOR	(1 << 1)
 #define	RXH_XFRM_NO_CHANGE	0xff
 
-/* L2-L4 network traffic flow types */
-#define	TCP_V4_FLOW	0x01	/* hash or spec (tcp_ip4_spec) */
-#define	UDP_V4_FLOW	0x02	/* hash or spec (udp_ip4_spec) */
-#define	SCTP_V4_FLOW	0x03	/* hash or spec (sctp_ip4_spec) */
-#define	AH_ESP_V4_FLOW	0x04	/* hash only */
-#define	TCP_V6_FLOW	0x05	/* hash or spec (tcp_ip6_spec; nfc only) */
-#define	UDP_V6_FLOW	0x06	/* hash or spec (udp_ip6_spec; nfc only) */
-#define	SCTP_V6_FLOW	0x07	/* hash or spec (sctp_ip6_spec; nfc only) */
-#define	AH_ESP_V6_FLOW	0x08	/* hash only */
-#define	AH_V4_FLOW	0x09	/* hash or spec (ah_ip4_spec) */
-#define	ESP_V4_FLOW	0x0a	/* hash or spec (esp_ip4_spec) */
-#define	AH_V6_FLOW	0x0b	/* hash or spec (ah_ip6_spec; nfc only) */
-#define	ESP_V6_FLOW	0x0c	/* hash or spec (esp_ip6_spec; nfc only) */
-#define	IPV4_USER_FLOW	0x0d	/* spec only (usr_ip4_spec) */
-#define	IP_USER_FLOW	IPV4_USER_FLOW
-#define	IPV6_USER_FLOW	0x0e	/* spec only (usr_ip6_spec; nfc only) */
-#define	IPV4_FLOW	0x10	/* hash only */
-#define	IPV6_FLOW	0x11	/* hash only */
-#define	ETHER_FLOW	0x12	/* spec only (ether_spec) */
-
-/* Used for GTP-U IPv4 and IPv6.
- * The format of GTP packets only includes
- * elements such as TEID and GTP version.
- * It is primarily intended for data communication of the UE.
- */
-#define GTPU_V4_FLOW 0x13	/* hash only */
-#define GTPU_V6_FLOW 0x14	/* hash only */
-
-/* Use for GTP-C IPv4 and v6.
- * The format of these GTP packets does not include TEID.
- * Primarily expected to be used for communication
- * to create sessions for UE data communication,
- * commonly referred to as CSR (Create Session Request).
- */
-#define GTPC_V4_FLOW 0x15	/* hash only */
-#define GTPC_V6_FLOW 0x16	/* hash only */
-
-/* Use for GTP-C IPv4 and v6.
- * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID.
- * After session creation, it becomes this packet.
- * This is mainly used for requests to realize UE handover.
- */
-#define GTPC_TEID_V4_FLOW 0x17	/* hash only */
-#define GTPC_TEID_V6_FLOW 0x18	/* hash only */
-
-/* Use for GTP-U and extended headers for the PSC (PDU Session Container).
- * The format of these GTP packets includes TEID and QFI.
- * In 5G communication using UPF (User Plane Function),
- * data communication with this extended header is performed.
- */
-#define GTPU_EH_V4_FLOW 0x19	/* hash only */
-#define GTPU_EH_V6_FLOW 0x1a	/* hash only */
-
-/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers.
- * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by
- * UL/DL included in the PSC.
- * There are differences in the data included based on Downlink/Uplink,
- * and can be used to distinguish packets.
- * The functions described so far are useful when you want to
- * handle communication from the mobile network in UPF, PGW, etc.
- */
-#define GTPU_UL_V4_FLOW 0x1b	/* hash only */
-#define GTPU_UL_V6_FLOW 0x1c	/* hash only */
-#define GTPU_DL_V4_FLOW 0x1d	/* hash only */
-#define GTPU_DL_V6_FLOW 0x1e	/* hash only */
+enum {
+	/* L2-L4 network traffic flow types */
+	TCP_V4_FLOW	= 0x01,	/* hash or spec (tcp_ip4_spec) */
+	UDP_V4_FLOW	= 0x02,	/* hash or spec (udp_ip4_spec) */
+	SCTP_V4_FLOW	= 0x03,	/* hash or spec (sctp_ip4_spec) */
+	AH_ESP_V4_FLOW	= 0x04,	/* hash only */
+	TCP_V6_FLOW	= 0x05,	/* hash or spec (tcp_ip6_spec; nfc only) */
+	UDP_V6_FLOW	= 0x06,	/* hash or spec (udp_ip6_spec; nfc only) */
+	SCTP_V6_FLOW	= 0x07,	/* hash or spec (sctp_ip6_spec; nfc only) */
+	AH_ESP_V6_FLOW	= 0x08,	/* hash only */
+	AH_V4_FLOW	= 0x09,	/* hash or spec (ah_ip4_spec) */
+	ESP_V4_FLOW	= 0x0a,	/* hash or spec (esp_ip4_spec) */
+	AH_V6_FLOW	= 0x0b,	/* hash or spec (ah_ip6_spec; nfc only) */
+	ESP_V6_FLOW	= 0x0c,	/* hash or spec (esp_ip6_spec; nfc only) */
+	IPV4_USER_FLOW	= 0x0d,	/* spec only (usr_ip4_spec) */
+	IP_USER_FLOW	= IPV4_USER_FLOW,
+	IPV6_USER_FLOW	= 0x0e, /* spec only (usr_ip6_spec; nfc only) */
+	IPV4_FLOW	= 0x10, /* hash only */
+	IPV6_FLOW	= 0x11, /* hash only */
+	ETHER_FLOW	= 0x12, /* spec only (ether_spec) */
+
+	/* Used for GTP-U IPv4 and IPv6.
+	 * The format of GTP packets only includes
+	 * elements such as TEID and GTP version.
+	 * It is primarily intended for data communication of the UE.
+	 */
+	GTPU_V4_FLOW	= 0x13,	/* hash only */
+	GTPU_V6_FLOW	= 0x14,	/* hash only */
+
+	/* Use for GTP-C IPv4 and v6.
+	 * The format of these GTP packets does not include TEID.
+	 * Primarily expected to be used for communication
+	 * to create sessions for UE data communication,
+	 * commonly referred to as CSR (Create Session Request).
+	 */
+	GTPC_V4_FLOW	= 0x15,	/* hash only */
+	GTPC_V6_FLOW	= 0x16,	/* hash only */
+
+	/* Use for GTP-C IPv4 and v6.
+	 * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID.
+	 * After session creation, it becomes this packet.
+	 * This is mainly used for requests to realize UE handover.
+	 */
+	GTPC_TEID_V4_FLOW	= 0x17,	/* hash only */
+	GTPC_TEID_V6_FLOW	= 0x18,	/* hash only */
+
+	/* Use for GTP-U and extended headers for the PSC (PDU Session Container).
+	 * The format of these GTP packets includes TEID and QFI.
+	 * In 5G communication using UPF (User Plane Function),
+	 * data communication with this extended header is performed.
+	 */
+	GTPU_EH_V4_FLOW	= 0x19,	/* hash only */
+	GTPU_EH_V6_FLOW	= 0x1a,	/* hash only */
+
+	/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers.
+	 * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by
+	 * UL/DL included in the PSC.
+	 * There are differences in the data included based on Downlink/Uplink,
+	 * and can be used to distinguish packets.
+	 * The functions described so far are useful when you want to
+	 * handle communication from the mobile network in UPF, PGW, etc.
+	 */
+	GTPU_UL_V4_FLOW	= 0x1b,	/* hash only */
+	GTPU_UL_V6_FLOW	= 0x1c,	/* hash only */
+	GTPU_DL_V4_FLOW	= 0x1d,	/* hash only */
+	GTPU_DL_V6_FLOW	= 0x1e,	/* hash only */
+
+	__FLOW_TYPE_COUNT,
+};
 
 /* Flag to enable additional fields in struct ethtool_rx_flow_spec */
 #define	FLOW_EXT	0x80000000
diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h
index fe24c3459ac0..9a02f579de22 100644
--- a/include/uapi/linux/ethtool_netlink_generated.h
+++ b/include/uapi/linux/ethtool_netlink_generated.h
@@ -31,17 +31,24 @@ enum ethtool_header_flags {
 	ETHTOOL_FLAG_STATS = 4,
 };
 
-enum {
-	ETHTOOL_PHY_UPSTREAM_TYPE_MAC,
-	ETHTOOL_PHY_UPSTREAM_TYPE_PHY,
-};
-
 enum ethtool_tcp_data_split {
 	ETHTOOL_TCP_DATA_SPLIT_UNKNOWN,
 	ETHTOOL_TCP_DATA_SPLIT_DISABLED,
 	ETHTOOL_TCP_DATA_SPLIT_ENABLED,
 };
 
+/**
+ * enum hwtstamp_source - Source of the hardware timestamp
+ * @HWTSTAMP_SOURCE_NETDEV: Hardware timestamp comes from a MAC or a device
+ *   which has MAC and PHY integrated
+ * @HWTSTAMP_SOURCE_PHYLIB: Hardware timestamp comes from one PHY device of the
+ *   network topology
+ */
+enum hwtstamp_source {
+	HWTSTAMP_SOURCE_NETDEV = 1,
+	HWTSTAMP_SOURCE_PHYLIB,
+};
+
 enum {
 	ETHTOOL_A_HEADER_UNSPEC,
 	ETHTOOL_A_HEADER_DEV_INDEX,
@@ -406,6 +413,8 @@ enum {
 	ETHTOOL_A_TSINFO_PHC_INDEX,
 	ETHTOOL_A_TSINFO_STATS,
 	ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER,
+	ETHTOOL_A_TSINFO_HWTSTAMP_SOURCE,
+	ETHTOOL_A_TSINFO_HWTSTAMP_PHYINDEX,
 
 	__ETHTOOL_A_TSINFO_CNT,
 	ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1)
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 2df6e4035d50..418c4be697ad 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __LINUX_FIB_RULES_H
-#define __LINUX_FIB_RULES_H
+#ifndef _UAPI__LINUX_FIB_RULES_H
+#define _UAPI__LINUX_FIB_RULES_H
 
 #include <linux/types.h>
 #include <linux/rtnetlink.h>
diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h
index 1c392dd95a5e..aa7958b4e41d 100644
--- a/include/uapi/linux/if_addr.h
+++ b/include/uapi/linux/if_addr.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __LINUX_IF_ADDR_H
-#define __LINUX_IF_ADDR_H
+#ifndef _UAPI__LINUX_IF_ADDR_H
+#define _UAPI__LINUX_IF_ADDR_H
 
 #include <linux/types.h>
 #include <linux/netlink.h>
diff --git a/include/uapi/linux/if_addrlabel.h b/include/uapi/linux/if_addrlabel.h
index d1f5974c76e1..e69db764fbba 100644
--- a/include/uapi/linux/if_addrlabel.h
+++ b/include/uapi/linux/if_addrlabel.h
@@ -8,8 +8,8 @@
  *	YOSHIFUJI Hideaki @ USAGI/WIDE <yoshfuji@linux-ipv6.org>
  */
 
-#ifndef __LINUX_IF_ADDRLABEL_H
-#define __LINUX_IF_ADDRLABEL_H
+#ifndef _UAPI__LINUX_IF_ADDRLABEL_H
+#define _UAPI__LINUX_IF_ADDRLABEL_H
 
 #include <linux/types.h>
 
diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h
index 0824fbc026a1..b35871cbeed7 100644
--- a/include/uapi/linux/if_alg.h
+++ b/include/uapi/linux/if_alg.h
@@ -11,8 +11,8 @@
  *
  */
 
-#ifndef _LINUX_IF_ALG_H
-#define _LINUX_IF_ALG_H
+#ifndef _UAPI_LINUX_IF_ALG_H
+#define _UAPI_LINUX_IF_ALG_H
 
 #include <linux/types.h>
 
@@ -58,4 +58,4 @@ struct af_alg_iv {
 #define ALG_OP_DECRYPT			0
 #define ALG_OP_ENCRYPT			1
 
-#endif	/* _LINUX_IF_ALG_H */
+#endif	/* _UAPI_LINUX_IF_ALG_H */
diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h
index b122cfac7128..473569eaf692 100644
--- a/include/uapi/linux/if_arcnet.h
+++ b/include/uapi/linux/if_arcnet.h
@@ -14,8 +14,8 @@
  *              2 of the License, or (at your option) any later version.
  */
 
-#ifndef _LINUX_IF_ARCNET_H
-#define _LINUX_IF_ARCNET_H
+#ifndef _UAPI_LINUX_IF_ARCNET_H
+#define _UAPI_LINUX_IF_ARCNET_H
 
 #include <linux/types.h>
 #include <linux/if_ether.h>
@@ -127,4 +127,4 @@ struct archdr {
 	} soft;
 };
 
-#endif				/* _LINUX_IF_ARCNET_H */
+#endif				/* _UAPI_LINUX_IF_ARCNET_H */
diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h
index d174914a837d..3bcc03f3aa4f 100644
--- a/include/uapi/linux/if_bonding.h
+++ b/include/uapi/linux/if_bonding.h
@@ -41,8 +41,8 @@
  *      - added definitions for various XOR hashing policies
  */
 
-#ifndef _LINUX_IF_BONDING_H
-#define _LINUX_IF_BONDING_H
+#ifndef _UAPI_LINUX_IF_BONDING_H
+#define _UAPI_LINUX_IF_BONDING_H
 
 #include <linux/if.h>
 #include <linux/types.h>
@@ -152,4 +152,4 @@ enum {
 };
 #define BOND_3AD_STAT_MAX (__BOND_3AD_STAT_MAX - 1)
 
-#endif /* _LINUX_IF_BONDING_H */
+#endif /* _UAPI_LINUX_IF_BONDING_H */
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index a5b743a2f775..73876c0e2bba 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -699,10 +699,11 @@ struct br_mdb_entry {
 #define MDB_TEMPORARY 0
 #define MDB_PERMANENT 1
 	__u8 state;
-#define MDB_FLAGS_OFFLOAD	(1 << 0)
-#define MDB_FLAGS_FAST_LEAVE	(1 << 1)
-#define MDB_FLAGS_STAR_EXCL	(1 << 2)
-#define MDB_FLAGS_BLOCKED	(1 << 3)
+#define MDB_FLAGS_OFFLOAD		(1 << 0)
+#define MDB_FLAGS_FAST_LEAVE		(1 << 1)
+#define MDB_FLAGS_STAR_EXCL		(1 << 2)
+#define MDB_FLAGS_BLOCKED		(1 << 3)
+#define MDB_FLAGS_OFFLOAD_FAILED	(1 << 4)
 	__u8 flags;
 	__u16 vid;
 	struct {
@@ -830,6 +831,7 @@ enum br_boolopt_id {
 	BR_BOOLOPT_NO_LL_LEARN,
 	BR_BOOLOPT_MCAST_VLAN_SNOOPING,
 	BR_BOOLOPT_MST_ENABLE,
+	BR_BOOLOPT_MDB_OFFLOAD_FAIL_NOTIFICATION,
 	BR_BOOLOPT_MAX
 };
 
diff --git a/include/uapi/linux/if_fc.h b/include/uapi/linux/if_fc.h
index 3e3173282cc3..ff5ab92d16c2 100644
--- a/include/uapi/linux/if_fc.h
+++ b/include/uapi/linux/if_fc.h
@@ -18,8 +18,8 @@
  *		as published by the Free Software Foundation; either version
  *		2 of the License, or (at your option) any later version.
  */
-#ifndef _LINUX_IF_FC_H
-#define _LINUX_IF_FC_H
+#ifndef _UAPI_LINUX_IF_FC_H
+#define _UAPI_LINUX_IF_FC_H
 
 #include <linux/types.h>
 
@@ -49,4 +49,4 @@ struct fcllc {
 	__be16 ethertype;		/* ether type field */
 };
 
-#endif	/* _LINUX_IF_FC_H */
+#endif	/* _UAPI_LINUX_IF_FC_H */
diff --git a/include/uapi/linux/if_hippi.h b/include/uapi/linux/if_hippi.h
index 785a1452a66c..42c4ffd11dae 100644
--- a/include/uapi/linux/if_hippi.h
+++ b/include/uapi/linux/if_hippi.h
@@ -20,8 +20,8 @@
  *		2 of the License, or (at your option) any later version.
  */
  
-#ifndef _LINUX_IF_HIPPI_H
-#define _LINUX_IF_HIPPI_H
+#ifndef _UAPI_LINUX_IF_HIPPI_H
+#define _UAPI_LINUX_IF_HIPPI_H
 
 #include <linux/types.h>
 #include <asm/byteorder.h>
@@ -151,4 +151,4 @@ struct hippi_hdr {
 	struct hippi_snap_hdr	snap;
 } __attribute__((packed));
 
-#endif	/* _LINUX_IF_HIPPI_H */
+#endif	/* _UAPI_LINUX_IF_HIPPI_H */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 318386cc5b0d..3ad2d5d98034 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1986,4 +1986,19 @@ enum {
 
 #define IFLA_DSA_MAX	(__IFLA_DSA_MAX - 1)
 
+/* OVPN section */
+
+enum ovpn_mode {
+	OVPN_MODE_P2P,
+	OVPN_MODE_MP,
+};
+
+enum {
+	IFLA_OVPN_UNSPEC,
+	IFLA_OVPN_MODE,
+	__IFLA_OVPN_MAX,
+};
+
+#define IFLA_OVPN_MAX	(__IFLA_OVPN_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */
diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index 1d2718dd9647..6cd1d7a41dfb 100644
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __LINUX_IF_PACKET_H
-#define __LINUX_IF_PACKET_H
+#ifndef _UAPI__LINUX_IF_PACKET_H
+#define _UAPI__LINUX_IF_PACKET_H
 
 #include <asm/byteorder.h>
 #include <linux/types.h>
diff --git a/include/uapi/linux/if_plip.h b/include/uapi/linux/if_plip.h
index 495a366112f2..054d86a9c6e6 100644
--- a/include/uapi/linux/if_plip.h
+++ b/include/uapi/linux/if_plip.h
@@ -9,8 +9,8 @@
  *
  */
  
-#ifndef _LINUX_IF_PLIP_H
-#define _LINUX_IF_PLIP_H
+#ifndef _UAPI_LINUX_IF_PLIP_H
+#define _UAPI_LINUX_IF_PLIP_H
 
 #include <linux/sockios.h>
 
diff --git a/include/uapi/linux/if_slip.h b/include/uapi/linux/if_slip.h
index 65937be53103..299bf7adc862 100644
--- a/include/uapi/linux/if_slip.h
+++ b/include/uapi/linux/if_slip.h
@@ -6,8 +6,8 @@
  *	KISS TNC driver.
  */
  
-#ifndef __LINUX_SLIP_H
-#define __LINUX_SLIP_H
+#ifndef _UAPI__LINUX_SLIP_H
+#define _UAPI__LINUX_SLIP_H
 
 #define		SL_MODE_SLIP		0
 #define		SL_MODE_CSLIP		1
diff --git a/include/uapi/linux/if_x25.h b/include/uapi/linux/if_x25.h
index 3a5938e38370..861cfa983db4 100644
--- a/include/uapi/linux/if_x25.h
+++ b/include/uapi/linux/if_x25.h
@@ -13,8 +13,8 @@
  *  GNU General Public License for more details.
  */
 
-#ifndef _IF_X25_H
-#define _IF_X25_H
+#ifndef _UAPI_IF_X25_H
+#define _UAPI_IF_X25_H
 
 #include <linux/types.h>
 
@@ -24,4 +24,4 @@
 #define X25_IFACE_DISCONNECT	0x02
 #define X25_IFACE_PARAMS	0x03
 
-#endif /* _IF_X25_H */
+#endif /* _UAPI_IF_X25_H */
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index 42869770776e..44f2bb93e7e6 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -7,8 +7,8 @@
  *	      Magnus Karlsson <magnus.karlsson@intel.com>
  */
 
-#ifndef _LINUX_IF_XDP_H
-#define _LINUX_IF_XDP_H
+#ifndef _UAPI_LINUX_IF_XDP_H
+#define _UAPI_LINUX_IF_XDP_H
 
 #include <linux/types.h>
 
@@ -180,4 +180,4 @@ struct xdp_desc {
 /* TX packet carries valid metadata. */
 #define XDP_TX_METADATA (1 << 1)
 
-#endif /* _LINUX_IF_XDP_H */
+#endif /* _UAPI_LINUX_IF_XDP_H */
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index ed2beb4def3f..8f1fc12bac46 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -1010,7 +1010,9 @@ struct io_uring_zcrx_ifq_reg {
 	__u64	region_ptr; /* struct io_uring_region_desc * */
 
 	struct io_uring_zcrx_offsets offsets;
-	__u64	__resv[4];
+	__u32	zcrx_id;
+	__u32	__resv2;
+	__u64	__resv[3];
 };
 
 #ifdef __cplusplus
diff --git a/include/uapi/linux/ip6_tunnel.h b/include/uapi/linux/ip6_tunnel.h
index 0245269b037c..85182a839d42 100644
--- a/include/uapi/linux/ip6_tunnel.h
+++ b/include/uapi/linux/ip6_tunnel.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _IP6_TUNNEL_H
-#define _IP6_TUNNEL_H
+#ifndef _UAPI_IP6_TUNNEL_H
+#define _UAPI_IP6_TUNNEL_H
 
 #include <linux/types.h>
 #include <linux/if.h>		/* For IFNAMSIZ. */
diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h
index d9d0cb827117..f030adc462ee 100644
--- a/include/uapi/linux/landlock.h
+++ b/include/uapi/linux/landlock.h
@@ -53,43 +53,70 @@ struct landlock_ruleset_attr {
 	__u64 scoped;
 };
 
-/*
- * sys_landlock_create_ruleset() flags:
+/**
+ * DOC: landlock_create_ruleset_flags
+ *
+ * **Flags**
  *
- * - %LANDLOCK_CREATE_RULESET_VERSION: Get the highest supported Landlock ABI
- *   version.
- * - %LANDLOCK_CREATE_RULESET_ERRATA: Get a bitmask of fixed issues.
+ * %LANDLOCK_CREATE_RULESET_VERSION
+ *     Get the highest supported Landlock ABI version (starting at 1).
+ *
+ * %LANDLOCK_CREATE_RULESET_ERRATA
+ *     Get a bitmask of fixed issues for the current Landlock ABI version.
  */
 /* clang-format off */
 #define LANDLOCK_CREATE_RULESET_VERSION			(1U << 0)
 #define LANDLOCK_CREATE_RULESET_ERRATA			(1U << 1)
 /* clang-format on */
 
-/*
- * sys_landlock_restrict_self() flags:
- *
- * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF: Do not create any log related to the
- *   enforced restrictions.  This should only be set by tools launching unknown
- *   or untrusted programs (e.g. a sandbox tool, container runtime, system
- *   service manager).  Because programs sandboxing themselves should fix any
- *   denied access, they should not set this flag to be aware of potential
- *   issues reported by system's logs (i.e. audit).
- * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON: Explicitly ask to continue
- *   logging denied access requests even after an :manpage:`execve(2)` call.
- *   This flag should only be set if all the programs than can legitimately be
- *   executed will not try to request a denied access (which could spam audit
- *   logs).
- * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF: Do not create any log related
- *   to the enforced restrictions coming from future nested domains created by
- *   the caller or its descendants.  This should only be set according to a
- *   runtime configuration (i.e. not hardcoded) by programs launching other
- *   unknown or untrusted programs that may create their own Landlock domains
- *   and spam logs.  The main use case is for container runtimes to enable users
- *   to mute buggy sandboxed programs for a specific container image.  Other use
- *   cases include sandboxer tools and init systems.  Unlike
- *   %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF,
- *   %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF does not impact the requested
- *   restriction (if any) but only the future nested domains.
+/**
+ * DOC: landlock_restrict_self_flags
+ *
+ * **Flags**
+ *
+ * By default, denied accesses originating from programs that sandbox themselves
+ * are logged via the audit subsystem. Such events typically indicate unexpected
+ * behavior, such as bugs or exploitation attempts. However, to avoid excessive
+ * logging, access requests denied by a domain not created by the originating
+ * program are not logged by default. The rationale is that programs should know
+ * their own behavior, but not necessarily the behavior of other programs.  This
+ * default configuration is suitable for most programs that sandbox themselves.
+ * For specific use cases, the following flags allow programs to modify this
+ * default logging behavior.
+ *
+ * The %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF and
+ * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON flags apply to the newly created
+ * Landlock domain.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
+ *     Disables logging of denied accesses originating from the thread creating
+ *     the Landlock domain, as well as its children, as long as they continue
+ *     running the same executable code (i.e., without an intervening
+ *     :manpage:`execve(2)` call). This is intended for programs that execute
+ *     unknown code without invoking :manpage:`execve(2)`, such as script
+ *     interpreters. Programs that only sandbox themselves should not set this
+ *     flag, so users can be notified of unauthorized access attempts via system
+ *     logs.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
+ *     Enables logging of denied accesses after an :manpage:`execve(2)` call,
+ *     providing visibility into unauthorized access attempts by newly executed
+ *     programs within the created Landlock domain. This flag is recommended
+ *     only when all potential executables in the domain are expected to comply
+ *     with the access restrictions, as excessive audit log entries could make
+ *     it more difficult to identify critical events.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
+ *     Disables logging of denied accesses originating from nested Landlock
+ *     domains created by the caller or its descendants. This flag should be set
+ *     according to runtime configuration, not hardcoded, to avoid suppressing
+ *     important security events. It is useful for container runtimes or
+ *     sandboxing tools that may launch programs which themselves create
+ *     Landlock domains and could otherwise generate excessive logs. Unlike
+ *     ``LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF``, this flag only affects
+ *     future nested domains, not the one being created. It can also be used
+ *     with a @ruleset_fd value of -1 to mute subdomain logs without creating a
+ *     domain.
  */
 /* clang-format off */
 #define LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF		(1U << 0)
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index 5e67a7eaf4a7..b851c36ad25d 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __LINUX_NEIGHBOUR_H
-#define __LINUX_NEIGHBOUR_H
+#ifndef _UAPI__LINUX_NEIGHBOUR_H
+#define _UAPI__LINUX_NEIGHBOUR_H
 
 #include <linux/types.h>
 #include <linux/netlink.h>
diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h
index 84f622a66a7a..9dd41c2f58a6 100644
--- a/include/uapi/linux/net_dropmon.h
+++ b/include/uapi/linux/net_dropmon.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __NET_DROPMON_H
-#define __NET_DROPMON_H
+#ifndef _UAPI__NET_DROPMON_H
+#define _UAPI__NET_DROPMON_H
 
 #include <linux/types.h>
 #include <linux/netlink.h>
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index 383213de612a..a93e6ea37fb3 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -7,8 +7,8 @@
  *
  */
 
-#ifndef _NET_TIMESTAMPING_H
-#define _NET_TIMESTAMPING_H
+#ifndef _UAPI_NET_TIMESTAMPING_H
+#define _UAPI_NET_TIMESTAMPING_H
 
 #include <linux/types.h>
 #include <linux/socket.h>   /* for SO_TIMESTAMPING */
@@ -216,4 +216,4 @@ struct sock_txtime {
 	__u32			flags;	/* as defined by enum txtime_flags */
 };
 
-#endif /* _NET_TIMESTAMPING_H */
+#endif /* _UAPI_NET_TIMESTAMPING_H */
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 7600bf62dbdf..7eb9571786b8 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -219,6 +219,7 @@ enum {
 	NETDEV_CMD_QSTATS_GET,
 	NETDEV_CMD_BIND_RX,
 	NETDEV_CMD_NAPI_SET,
+	NETDEV_CMD_BIND_TX,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 49c944e78463..7d6bc19a0153 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -394,6 +394,8 @@ enum nft_set_field_attributes {
  * @NFTA_SET_HANDLE: set handle (NLA_U64)
  * @NFTA_SET_EXPR: set expression (NLA_NESTED: nft_expr_attributes)
  * @NFTA_SET_EXPRESSIONS: list of expressions (NLA_NESTED: nft_list_attributes)
+ * @NFTA_SET_TYPE: set backend type (NLA_STRING)
+ * @NFTA_SET_COUNT: number of set elements (NLA_U32)
  */
 enum nft_set_attributes {
 	NFTA_SET_UNSPEC,
@@ -415,6 +417,8 @@ enum nft_set_attributes {
 	NFTA_SET_HANDLE,
 	NFTA_SET_EXPR,
 	NFTA_SET_EXPRESSIONS,
+	NFTA_SET_TYPE,
+	NFTA_SET_COUNT,
 	__NFTA_SET_MAX
 };
 #define NFTA_SET_MAX		(__NFTA_SET_MAX - 1)
diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
index dfa61be43d2f..ff28200204bb 100644
--- a/include/uapi/linux/netlink_diag.h
+++ b/include/uapi/linux/netlink_diag.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __NETLINK_DIAG_H__
-#define __NETLINK_DIAG_H__
+#ifndef _UAPI__NETLINK_DIAG_H__
+#define _UAPI__NETLINK_DIAG_H__
 
 #include <linux/types.h>
 
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index ddcc4cda74af..e9ccf43fe3c6 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -8036,6 +8036,11 @@ enum nl80211_sar_specs_attrs {
  *	Setting this flag is permitted only if the driver advertises EMA support
  *	by setting wiphy->ema_max_profile_periodicity to non-zero.
  *
+ * @NL80211_MBSSID_CONFIG_ATTR_TX_LINK_ID: Link ID of the transmitted profile.
+ *	This parameter is mandatory when NL80211_ATTR_MBSSID_CONFIG attributes
+ *	are sent for a non-transmitted profile and if the transmitted profile
+ *	is part of an MLD. For all other cases this parameter is unnecessary.
+ *
  * @__NL80211_MBSSID_CONFIG_ATTR_LAST: Internal
  * @NL80211_MBSSID_CONFIG_ATTR_MAX: highest attribute
  */
@@ -8047,6 +8052,7 @@ enum nl80211_mbssid_config_attributes {
 	NL80211_MBSSID_CONFIG_ATTR_INDEX,
 	NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX,
 	NL80211_MBSSID_CONFIG_ATTR_EMA,
+	NL80211_MBSSID_CONFIG_ATTR_TX_LINK_ID,
 
 	/* keep last */
 	__NL80211_MBSSID_CONFIG_ATTR_LAST,
diff --git a/include/uapi/linux/ovpn.h b/include/uapi/linux/ovpn.h
new file mode 100644
index 000000000000..680d1522dc87
--- /dev/null
+++ b/include/uapi/linux/ovpn.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/ovpn.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _UAPI_LINUX_OVPN_H
+#define _UAPI_LINUX_OVPN_H
+
+#define OVPN_FAMILY_NAME	"ovpn"
+#define OVPN_FAMILY_VERSION	1
+
+#define OVPN_NONCE_TAIL_SIZE	8
+
+enum ovpn_cipher_alg {
+	OVPN_CIPHER_ALG_NONE,
+	OVPN_CIPHER_ALG_AES_GCM,
+	OVPN_CIPHER_ALG_CHACHA20_POLY1305,
+};
+
+enum ovpn_del_peer_reason {
+	OVPN_DEL_PEER_REASON_TEARDOWN,
+	OVPN_DEL_PEER_REASON_USERSPACE,
+	OVPN_DEL_PEER_REASON_EXPIRED,
+	OVPN_DEL_PEER_REASON_TRANSPORT_ERROR,
+	OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT,
+};
+
+enum ovpn_key_slot {
+	OVPN_KEY_SLOT_PRIMARY,
+	OVPN_KEY_SLOT_SECONDARY,
+};
+
+enum {
+	OVPN_A_PEER_ID = 1,
+	OVPN_A_PEER_REMOTE_IPV4,
+	OVPN_A_PEER_REMOTE_IPV6,
+	OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID,
+	OVPN_A_PEER_REMOTE_PORT,
+	OVPN_A_PEER_SOCKET,
+	OVPN_A_PEER_SOCKET_NETNSID,
+	OVPN_A_PEER_VPN_IPV4,
+	OVPN_A_PEER_VPN_IPV6,
+	OVPN_A_PEER_LOCAL_IPV4,
+	OVPN_A_PEER_LOCAL_IPV6,
+	OVPN_A_PEER_LOCAL_PORT,
+	OVPN_A_PEER_KEEPALIVE_INTERVAL,
+	OVPN_A_PEER_KEEPALIVE_TIMEOUT,
+	OVPN_A_PEER_DEL_REASON,
+	OVPN_A_PEER_VPN_RX_BYTES,
+	OVPN_A_PEER_VPN_TX_BYTES,
+	OVPN_A_PEER_VPN_RX_PACKETS,
+	OVPN_A_PEER_VPN_TX_PACKETS,
+	OVPN_A_PEER_LINK_RX_BYTES,
+	OVPN_A_PEER_LINK_TX_BYTES,
+	OVPN_A_PEER_LINK_RX_PACKETS,
+	OVPN_A_PEER_LINK_TX_PACKETS,
+
+	__OVPN_A_PEER_MAX,
+	OVPN_A_PEER_MAX = (__OVPN_A_PEER_MAX - 1)
+};
+
+enum {
+	OVPN_A_KEYCONF_PEER_ID = 1,
+	OVPN_A_KEYCONF_SLOT,
+	OVPN_A_KEYCONF_KEY_ID,
+	OVPN_A_KEYCONF_CIPHER_ALG,
+	OVPN_A_KEYCONF_ENCRYPT_DIR,
+	OVPN_A_KEYCONF_DECRYPT_DIR,
+
+	__OVPN_A_KEYCONF_MAX,
+	OVPN_A_KEYCONF_MAX = (__OVPN_A_KEYCONF_MAX - 1)
+};
+
+enum {
+	OVPN_A_KEYDIR_CIPHER_KEY = 1,
+	OVPN_A_KEYDIR_NONCE_TAIL,
+
+	__OVPN_A_KEYDIR_MAX,
+	OVPN_A_KEYDIR_MAX = (__OVPN_A_KEYDIR_MAX - 1)
+};
+
+enum {
+	OVPN_A_IFINDEX = 1,
+	OVPN_A_PEER,
+	OVPN_A_KEYCONF,
+
+	__OVPN_A_MAX,
+	OVPN_A_MAX = (__OVPN_A_MAX - 1)
+};
+
+enum {
+	OVPN_CMD_PEER_NEW = 1,
+	OVPN_CMD_PEER_SET,
+	OVPN_CMD_PEER_GET,
+	OVPN_CMD_PEER_DEL,
+	OVPN_CMD_PEER_DEL_NTF,
+	OVPN_CMD_KEY_NEW,
+	OVPN_CMD_KEY_GET,
+	OVPN_CMD_KEY_SWAP,
+	OVPN_CMD_KEY_SWAP_NTF,
+	OVPN_CMD_KEY_DEL,
+
+	__OVPN_CMD_MAX,
+	OVPN_CMD_MAX = (__OVPN_CMD_MAX - 1)
+};
+
+#define OVPN_MCGRP_PEERS	"peers"
+
+#endif /* _UAPI_LINUX_OVPN_H */
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 2c32080416b5..28d94b11d1aa 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __LINUX_PKT_CLS_H
-#define __LINUX_PKT_CLS_H
+#ifndef _UAPI__LINUX_PKT_CLS_H
+#define _UAPI__LINUX_PKT_CLS_H
 
 #include <linux/types.h>
 #include <linux/pkt_sched.h>
@@ -697,6 +697,7 @@ enum {
 };
 
 #define TCA_FLOWER_KEY_CFM_OPT_MAX (__TCA_FLOWER_KEY_CFM_OPT_MAX - 1)
+#define TCA_FLOWER_KEY_CFM_MAX	   (__TCA_FLOWER_KEY_CFM_OPT_MAX - 1)
 
 #define TCA_FLOWER_MASK_FLAGS_RANGE	(1 << 0) /* Range-based match */
 
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 25a9a47001cd..3e41349f3fa2 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __LINUX_PKT_SCHED_H
-#define __LINUX_PKT_SCHED_H
+#ifndef _UAPI__LINUX_PKT_SCHED_H
+#define _UAPI__LINUX_PKT_SCHED_H
 
 #include <linux/const.h>
 #include <linux/types.h>
@@ -1182,6 +1182,7 @@ enum {
 	TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */
 	TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */
 	TCA_TAPRIO_PAD,
+	TCA_TAPRIO_ATTR_PAD = TCA_TAPRIO_PAD,
 	TCA_TAPRIO_ATTR_ADMIN_SCHED, /* The admin sched, only used in dump */
 	TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, /* s64 */
 	TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, /* s64 */
diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h
index 8f8dc7a937a4..d9735abd4c79 100644
--- a/include/uapi/linux/rxrpc.h
+++ b/include/uapi/linux/rxrpc.h
@@ -36,26 +36,33 @@ struct sockaddr_rxrpc {
 #define RXRPC_MIN_SECURITY_LEVEL	4	/* minimum security level */
 #define RXRPC_UPGRADEABLE_SERVICE	5	/* Upgrade service[0] -> service[1] */
 #define RXRPC_SUPPORTED_CMSG		6	/* Get highest supported control message type */
+#define RXRPC_MANAGE_RESPONSE		7	/* [clnt] Want to manage RESPONSE packets */
 
 /*
  * RxRPC control messages
  * - If neither abort or accept are specified, the message is a data message.
  * - terminal messages mean that a user call ID tag can be recycled
+ * - C/S/- indicate whether these are applicable to client, server or both
  * - s/r/- indicate whether these are applicable to sendmsg() and/or recvmsg()
  */
 enum rxrpc_cmsg_type {
-	RXRPC_USER_CALL_ID	= 1,	/* sr: user call ID specifier */
-	RXRPC_ABORT		= 2,	/* sr: abort request / notification [terminal] */
-	RXRPC_ACK		= 3,	/* -r: [Service] RPC op final ACK received [terminal] */
-	RXRPC_NET_ERROR		= 5,	/* -r: network error received [terminal] */
-	RXRPC_BUSY		= 6,	/* -r: server busy received [terminal] */
-	RXRPC_LOCAL_ERROR	= 7,	/* -r: local error generated [terminal] */
-	RXRPC_NEW_CALL		= 8,	/* -r: [Service] new incoming call notification */
-	RXRPC_EXCLUSIVE_CALL	= 10,	/* s-: Call should be on exclusive connection */
-	RXRPC_UPGRADE_SERVICE	= 11,	/* s-: Request service upgrade for client call */
-	RXRPC_TX_LENGTH		= 12,	/* s-: Total length of Tx data */
-	RXRPC_SET_CALL_TIMEOUT	= 13,	/* s-: Set one or more call timeouts */
-	RXRPC_CHARGE_ACCEPT	= 14,	/* s-: Charge the accept pool with a user call ID */
+	RXRPC_USER_CALL_ID	= 1,	/* -sr: User call ID specifier */
+	RXRPC_ABORT		= 2,	/* -sr: Abort request / notification [terminal] */
+	RXRPC_ACK		= 3,	/* S-r: RPC op final ACK received [terminal] */
+	RXRPC_NET_ERROR		= 5,	/* --r: Network error received [terminal] */
+	RXRPC_BUSY		= 6,	/* C-r: Server busy received [terminal] */
+	RXRPC_LOCAL_ERROR	= 7,	/* --r: Local error generated [terminal] */
+	RXRPC_NEW_CALL		= 8,	/* S-r: New incoming call notification */
+	RXRPC_EXCLUSIVE_CALL	= 10,	/* Cs-: Call should be on exclusive connection */
+	RXRPC_UPGRADE_SERVICE	= 11,	/* Cs-: Request service upgrade for client call */
+	RXRPC_TX_LENGTH		= 12,	/* -s-: Total length of Tx data */
+	RXRPC_SET_CALL_TIMEOUT	= 13,	/* -s-: Set one or more call timeouts */
+	RXRPC_CHARGE_ACCEPT	= 14,	/* Ss-: Charge the accept pool with a user call ID */
+	RXRPC_OOB_ID		= 15,	/* -sr: OOB message ID */
+	RXRPC_CHALLENGED	= 16,	/* C-r: Info on a received CHALLENGE */
+	RXRPC_RESPOND		= 17,	/* Cs-: Respond to a challenge */
+	RXRPC_RESPONDED		= 18,	/* S-r: Data received in RESPONSE */
+	RXRPC_RESP_RXGK_APPDATA	= 19,	/* Cs-: RESPONSE: RxGK app data to include */
 	RXRPC__SUPPORTED
 };
 
@@ -73,6 +80,7 @@ enum rxrpc_cmsg_type {
 #define RXRPC_SECURITY_RXKAD	2	/* kaserver or kerberos 4 */
 #define RXRPC_SECURITY_RXGK	4	/* gssapi-based */
 #define RXRPC_SECURITY_RXK5	5	/* kerberos 5 */
+#define RXRPC_SECURITY_YFS_RXGK	6	/* YFS gssapi-based */
 
 /*
  * RxRPC-level abort codes
@@ -118,4 +126,49 @@ enum rxrpc_cmsg_type {
 #define RXKADDATALEN		19270411	/* user data too long */
 #define RXKADILLEGALLEVEL	19270412	/* caller not authorised to use encrypted conns */
 
+/*
+ * RxGK GSSAPI security abort codes.
+ */
+#if 0 /* Original standard abort codes (used by OpenAFS) */
+#define RXGK_INCONSISTENCY	1233242880	/* Security module structure inconsistent */
+#define RXGK_PACKETSHORT	1233242881	/* Packet too short for security challenge */
+#define RXGK_BADCHALLENGE	1233242882	/* Invalid security challenge */
+#define RXGK_BADETYPE		1233242883	/* Invalid or impermissible encryption type */
+#define RXGK_BADLEVEL		1233242884	/* Invalid or impermissible security level */
+#define RXGK_BADKEYNO		1233242885	/* Key version number not found */
+#define RXGK_EXPIRED		1233242886	/* Token has expired */
+#define RXGK_NOTAUTH		1233242887	/* Caller not authorized */
+#define RXGK_BAD_TOKEN		1233242888	/* Security object was passed a bad token */
+#define RXGK_SEALED_INCON	1233242889	/* Sealed data inconsistent */
+#define RXGK_DATA_LEN		1233242890	/* User data too long */
+#define RXGK_BAD_QOP		1233242891	/* Inadequate quality of protection available */
+#else /* Revised standard abort codes (used by YFS) */
+#define RXGK_INCONSISTENCY	1233242880	/* Security module structure inconsistent */
+#define RXGK_PACKETSHORT	1233242881	/* Packet too short for security challenge */
+#define RXGK_BADCHALLENGE	1233242882	/* Security challenge/response failed */
+#define RXGK_SEALEDINCON	1233242883	/* Sealed data is inconsistent */
+#define RXGK_NOTAUTH		1233242884	/* Caller not authorised */
+#define RXGK_EXPIRED		1233242885	/* Authentication expired */
+#define RXGK_BADLEVEL		1233242886	/* Unsupported or not permitted security level */
+#define RXGK_BADKEYNO		1233242887	/* Bad transport key number */
+#define RXGK_NOTRXGK		1233242888	/* Security layer is not rxgk */
+#define RXGK_UNSUPPORTED	1233242889	/* Endpoint does not support rxgk */
+#define RXGK_GSSERROR		1233242890	/* GSSAPI mechanism error */
+#endif
+
+/*
+ * Challenge information in the RXRPC_CHALLENGED control message.
+ */
+struct rxrpc_challenge {
+	__u16		service_id;	/* The service ID of the connection (may be upgraded) */
+	__u8		security_index;	/* The security index of the connection */
+	__u8		pad;		/* Round out to a multiple of 4 bytes. */
+	/* ... The security class gets to append extra information ... */
+};
+
+struct rxgk_challenge {
+	struct rxrpc_challenge	base;
+	__u32			enctype;	/* Krb5 encoding type */
+};
+
 #endif /* _UAPI_LINUX_RXRPC_H */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index dc8fdc80e16b..bdac8c42fa82 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -184,6 +184,7 @@ enum tcp_fastopen_client_fail {
 #define TCPI_OPT_ECN_SEEN	16 /* we received at least one packet with ECT */
 #define TCPI_OPT_SYN_DATA	32 /* SYN-ACK acked data in SYN sent or rcvd */
 #define TCPI_OPT_USEC_TS	64 /* usec timestamps */
+#define TCPI_OPT_TFO_CHILD	128 /* child from a Fast Open option on SYN */
 
 /*
  * Sender's congestion state indicating normal or abnormal situations
diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
index d85d671deed3..edca3e430305 100644
--- a/include/uapi/linux/udp.h
+++ b/include/uapi/linux/udp.h
@@ -43,5 +43,6 @@ struct udphdr {
 #define UDP_ENCAP_GTP1U		5 /* 3GPP TS 29.060 */
 #define UDP_ENCAP_RXRPC		6
 #define TCP_ENCAP_ESPINTCP	7 /* Yikes, this is really xfrm encap types. */
+#define UDP_ENCAP_OVPNINUDP	8 /* OpenVPN traffic */
 
 #endif /* _UAPI_LINUX_UDP_H */
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index b95dd84eef2d..d4b3e2ae1314 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -28,10 +28,10 @@
 
 /* Set current process as the (exclusive) owner of this file descriptor.  This
  * must be called before any other vhost command.  Further calls to
- * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+ * VHOST_SET_OWNER fail until VHOST_RESET_OWNER is called. */
 #define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
 /* Give up ownership, and reset the device to default values.
- * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+ * Allows subsequent call to VHOST_SET_OWNER to succeed. */
 #define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
 
 /* Set up/modify memory layout */
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 8549d4571257..c691ac210ce2 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -246,6 +246,7 @@ struct virtio_pci_cfg_cap {
 #define VIRTIO_ADMIN_CMD_LIST_USE	0x1
 
 /* Admin command group type. */
+#define VIRTIO_ADMIN_GROUP_TYPE_SELF	0x0
 #define VIRTIO_ADMIN_GROUP_TYPE_SRIOV	0x1
 
 /* Transitional device admin command. */
diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h
index 8a24ed59ec46..1c47136d8715 100644
--- a/include/ufs/ufs.h
+++ b/include/ufs/ufs.h
@@ -180,7 +180,8 @@ enum attr_idn {
 	QUERY_ATTR_IDN_AVAIL_WB_BUFF_SIZE       = 0x1D,
 	QUERY_ATTR_IDN_WB_BUFF_LIFE_TIME_EST    = 0x1E,
 	QUERY_ATTR_IDN_CURR_WB_BUFF_SIZE        = 0x1F,
-	QUERY_ATTR_IDN_TIMESTAMP		= 0x30
+	QUERY_ATTR_IDN_TIMESTAMP		= 0x30,
+	QUERY_ATTR_IDN_DEV_LVL_EXCEPTION_ID     = 0x34,
 };
 
 /* Descriptor idn for Query requests */
@@ -390,6 +391,7 @@ enum {
 	UFS_DEV_EXT_TEMP_NOTIF		= BIT(6),
 	UFS_DEV_HPB_SUPPORT		= BIT(7),
 	UFS_DEV_WRITE_BOOSTER_SUP	= BIT(8),
+	UFS_DEV_LVL_EXCEPTION_SUP       = BIT(12),
 };
 #define UFS_DEV_HPB_SUPPORT_VERSION		0x310
 
@@ -419,6 +421,7 @@ enum {
 	MASK_EE_TOO_LOW_TEMP		= BIT(4),
 	MASK_EE_WRITEBOOSTER_EVENT	= BIT(5),
 	MASK_EE_PERFORMANCE_THROTTLING	= BIT(6),
+	MASK_EE_DEV_LVL_EXCEPTION       = BIT(7),
 	MASK_EE_HEALTH_CRITICAL		= BIT(9),
 };
 #define MASK_EE_URGENT_TEMP (MASK_EE_TOO_HIGH_TEMP | MASK_EE_TOO_LOW_TEMP)
diff --git a/include/ufs/ufs_quirks.h b/include/ufs/ufs_quirks.h
index 41ff44dfa1db..f52de5ed1b3b 100644
--- a/include/ufs/ufs_quirks.h
+++ b/include/ufs/ufs_quirks.h
@@ -107,4 +107,10 @@ struct ufs_dev_quirk {
  */
 #define UFS_DEVICE_QUIRK_DELAY_AFTER_LPM        (1 << 11)
 
+/*
+ * Some ufs devices may need more time to be in hibern8 before exiting.
+ * Enable this quirk to give it an additional 100us.
+ */
+#define UFS_DEVICE_QUIRK_PA_HIBER8TIME          (1 << 12)
+
 #endif /* UFS_QUIRKS_H_ */
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index e3909cc691b2..e928ed0265ff 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -246,7 +246,7 @@ struct ufs_query {
 struct ufs_dev_cmd {
 	enum dev_cmd_type type;
 	struct mutex lock;
-	struct completion *complete;
+	struct completion complete;
 	struct ufs_query query;
 };
 
@@ -968,6 +968,9 @@ enum ufshcd_mcq_opr {
  * @pm_qos_req: PM QoS request handle
  * @pm_qos_enabled: flag to check if pm qos is enabled
  * @critical_health_count: count of critical health exceptions
+ * @dev_lvl_exception_count: count of device level exceptions since last reset
+ * @dev_lvl_exception_id: vendor specific information about the
+ * device level exception event.
  */
 struct ufs_hba {
 	void __iomem *mmio_base;
@@ -1138,6 +1141,8 @@ struct ufs_hba {
 	bool pm_qos_enabled;
 
 	int critical_health_count;
+	atomic_t dev_lvl_exception_count;
+	u64 dev_lvl_exception_id;
 };
 
 /**
diff --git a/include/vdso/unaligned.h b/include/vdso/unaligned.h
index eee3d2a4dbe4..ff0c06b6513e 100644
--- a/include/vdso/unaligned.h
+++ b/include/vdso/unaligned.h
@@ -2,14 +2,14 @@
 #ifndef __VDSO_UNALIGNED_H
 #define __VDSO_UNALIGNED_H
 
-#define __get_unaligned_t(type, ptr) ({						\
-	const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);	\
-	__pptr->x;								\
+#define __get_unaligned_t(type, ptr) ({							\
+	const struct { type x; } __packed * __get_pptr = (typeof(__get_pptr))(ptr);	\
+	__get_pptr->x;									\
 })
 
-#define __put_unaligned_t(type, val, ptr) do {					\
-	struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);		\
-	__pptr->x = (val);							\
+#define __put_unaligned_t(type, val, ptr) do {						\
+	struct { type x; } __packed * __put_pptr = (typeof(__put_pptr))(ptr);		\
+	__put_pptr->x = (val);								\
 } while (0)
 
 #endif /* __VDSO_UNALIGNED_H */
diff --git a/init/Kconfig b/init/Kconfig
index dd2ea3b9a799..bf3a920064be 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -87,11 +87,6 @@ config CC_CAN_LINK
 	default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag)) if 64BIT
 	default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m32-flag))
 
-config CC_CAN_LINK_STATIC
-	bool
-	default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag) -static) if 64BIT
-	default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m32-flag) -static)
-
 # Fixed in GCC 14, 13.3, 12.4 and 11.5
 # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921
 config GCC_ASM_GOTO_OUTPUT_BROKEN
@@ -140,6 +135,9 @@ config LD_CAN_USE_KEEP_IN_OVERLAY
 config RUSTC_HAS_COERCE_POINTEE
 	def_bool RUSTC_VERSION >= 108400
 
+config RUSTC_HAS_UNNECESSARY_TRANSMUTES
+	def_bool RUSTC_VERSION >= 108800
+
 config PAHOLE_VERSION
 	int
 	default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE))
@@ -1555,6 +1553,16 @@ config SYSCTL_ARCH_UNALIGN_ALLOW
 	  the unaligned access emulation.
 	  see arch/parisc/kernel/unaligned.c for reference
 
+config SYSFS_SYSCALL
+	bool "Sysfs syscall support"
+	default n
+	help
+	  sys_sysfs is an obsolete system call no longer supported in libc.
+	  Note that disabling this option is more secure but might break
+	  compatibility with some systems.
+
+	  If unsure say N here.
+
 config HAVE_PCSPKR_PLATFORM
 	bool
 
@@ -1599,16 +1607,6 @@ config SGETMASK_SYSCALL
 
 	  If unsure, leave the default option here.
 
-config SYSFS_SYSCALL
-	bool "Sysfs syscall support" if EXPERT
-	default y
-	help
-	  sys_sysfs is an obsolete system call no longer supported in libc.
-	  Note that disabling this option is more secure but might break
-	  compatibility with some systems.
-
-	  If unsure say Y here.
-
 config FHANDLE
 	bool "open by fhandle syscalls" if EXPERT
 	select EXPORTFS
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index f60d0a9d505e..e0d6a59a89fa 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -86,13 +86,8 @@ static inline void napi_show_fdinfo(struct io_ring_ctx *ctx,
 }
 #endif
 
-/*
- * Caller holds a reference to the file already, we don't need to do
- * anything else to get an extra reference.
- */
-__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
+static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 {
-	struct io_ring_ctx *ctx = file->private_data;
 	struct io_overflow_cqe *ocqe;
 	struct io_rings *r = ctx->rings;
 	struct rusage sq_usage;
@@ -106,7 +101,6 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 	unsigned int sq_entries, cq_entries;
 	int sq_pid = -1, sq_cpu = -1;
 	u64 sq_total_time = 0, sq_work_time = 0;
-	bool has_lock;
 	unsigned int i;
 
 	if (ctx->flags & IORING_SETUP_CQE32)
@@ -123,11 +117,11 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 	seq_printf(m, "SqMask:\t0x%x\n", sq_mask);
 	seq_printf(m, "SqHead:\t%u\n", sq_head);
 	seq_printf(m, "SqTail:\t%u\n", sq_tail);
-	seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head);
+	seq_printf(m, "CachedSqHead:\t%u\n", data_race(ctx->cached_sq_head));
 	seq_printf(m, "CqMask:\t0x%x\n", cq_mask);
 	seq_printf(m, "CqHead:\t%u\n", cq_head);
 	seq_printf(m, "CqTail:\t%u\n", cq_tail);
-	seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail);
+	seq_printf(m, "CachedCqTail:\t%u\n", data_race(ctx->cached_cq_tail));
 	seq_printf(m, "SQEs:\t%u\n", sq_tail - sq_head);
 	sq_entries = min(sq_tail - sq_head, ctx->sq_entries);
 	for (i = 0; i < sq_entries; i++) {
@@ -176,15 +170,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 		seq_printf(m, "\n");
 	}
 
-	/*
-	 * Avoid ABBA deadlock between the seq lock and the io_uring mutex,
-	 * since fdinfo case grabs it in the opposite direction of normal use
-	 * cases. If we fail to get the lock, we just don't iterate any
-	 * structures that could be going away outside the io_uring mutex.
-	 */
-	has_lock = mutex_trylock(&ctx->uring_lock);
-
-	if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) {
+	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		struct io_sq_data *sq = ctx->sq_data;
 
 		/*
@@ -206,7 +192,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 	seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time);
 	seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time);
 	seq_printf(m, "UserFiles:\t%u\n", ctx->file_table.data.nr);
-	for (i = 0; has_lock && i < ctx->file_table.data.nr; i++) {
+	for (i = 0; i < ctx->file_table.data.nr; i++) {
 		struct file *f = NULL;
 
 		if (ctx->file_table.data.nodes[i])
@@ -218,7 +204,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 		}
 	}
 	seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.nr);
-	for (i = 0; has_lock && i < ctx->buf_table.nr; i++) {
+	for (i = 0; i < ctx->buf_table.nr; i++) {
 		struct io_mapped_ubuf *buf = NULL;
 
 		if (ctx->buf_table.nodes[i])
@@ -228,7 +214,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 		else
 			seq_printf(m, "%5u: <none>\n", i);
 	}
-	if (has_lock && !xa_empty(&ctx->personalities)) {
+	if (!xa_empty(&ctx->personalities)) {
 		unsigned long index;
 		const struct cred *cred;
 
@@ -238,7 +224,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 	}
 
 	seq_puts(m, "PollList:\n");
-	for (i = 0; has_lock && i < (1U << ctx->cancel_table.hash_bits); i++) {
+	for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) {
 		struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i];
 		struct io_kiocb *req;
 
@@ -247,9 +233,6 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 					task_work_pending(req->tctx->task));
 	}
 
-	if (has_lock)
-		mutex_unlock(&ctx->uring_lock);
-
 	seq_puts(m, "CqOverflowList:\n");
 	spin_lock(&ctx->completion_lock);
 	list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
@@ -262,4 +245,23 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 	spin_unlock(&ctx->completion_lock);
 	napi_show_fdinfo(ctx, m);
 }
+
+/*
+ * Caller holds a reference to the file already, we don't need to do
+ * anything else to get an extra reference.
+ */
+__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
+{
+	struct io_ring_ctx *ctx = file->private_data;
+
+	/*
+	 * Avoid ABBA deadlock between the seq lock and the io_uring mutex,
+	 * since fdinfo case grabs it in the opposite direction of normal use
+	 * cases.
+	 */
+	if (mutex_trylock(&ctx->uring_lock)) {
+		__io_uring_show_fdinfo(ctx, m);
+		mutex_unlock(&ctx->uring_lock);
+	}
+}
 #endif
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index c6209fe44cb1..541e65a1eebf 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -448,24 +448,6 @@ static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
 	return req->link;
 }
 
-static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
-{
-	if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT)))
-		return NULL;
-	return __io_prep_linked_timeout(req);
-}
-
-static noinline void __io_arm_ltimeout(struct io_kiocb *req)
-{
-	io_queue_linked_timeout(__io_prep_linked_timeout(req));
-}
-
-static inline void io_arm_ltimeout(struct io_kiocb *req)
-{
-	if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT))
-		__io_arm_ltimeout(req);
-}
-
 static void io_prep_async_work(struct io_kiocb *req)
 {
 	const struct io_issue_def *def = &io_issue_defs[req->opcode];
@@ -518,7 +500,6 @@ static void io_prep_async_link(struct io_kiocb *req)
 
 static void io_queue_iowq(struct io_kiocb *req)
 {
-	struct io_kiocb *link = io_prep_linked_timeout(req);
 	struct io_uring_task *tctx = req->tctx;
 
 	BUG_ON(!tctx);
@@ -543,8 +524,6 @@ static void io_queue_iowq(struct io_kiocb *req)
 
 	trace_io_uring_queue_async_work(req, io_wq_is_hashed(&req->work));
 	io_wq_enqueue(tctx->io_wq, &req->work);
-	if (link)
-		io_queue_linked_timeout(link);
 }
 
 static void io_req_queue_iowq_tw(struct io_kiocb *req, io_tw_token_t tw)
@@ -869,13 +848,26 @@ bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags)
 	struct io_ring_ctx *ctx = req->ctx;
 	bool posted;
 
+	/*
+	 * If multishot has already posted deferred completions, ensure that
+	 * those are flushed first before posting this one. If not, CQEs
+	 * could get reordered.
+	 */
+	if (!wq_list_empty(&ctx->submit_state.compl_reqs))
+		__io_submit_flush_completions(ctx);
+
 	lockdep_assert(!io_wq_current_is_worker());
 	lockdep_assert_held(&ctx->uring_lock);
 
-	__io_cq_lock(ctx);
-	posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+	if (!ctx->lockless_cq) {
+		spin_lock(&ctx->completion_lock);
+		posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+		spin_unlock(&ctx->completion_lock);
+	} else {
+		posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+	}
+
 	ctx->submit_state.cq_flush = true;
-	__io_cq_unlock_post(ctx);
 	return posted;
 }
 
@@ -1078,21 +1070,22 @@ static __cold void __io_fallback_tw(struct llist_node *node, bool sync)
 	while (node) {
 		req = container_of(node, struct io_kiocb, io_task_work.node);
 		node = node->next;
-		if (sync && last_ctx != req->ctx) {
+		if (last_ctx != req->ctx) {
 			if (last_ctx) {
-				flush_delayed_work(&last_ctx->fallback_work);
+				if (sync)
+					flush_delayed_work(&last_ctx->fallback_work);
 				percpu_ref_put(&last_ctx->refs);
 			}
 			last_ctx = req->ctx;
 			percpu_ref_get(&last_ctx->refs);
 		}
-		if (llist_add(&req->io_task_work.node,
-			      &req->ctx->fallback_llist))
-			schedule_delayed_work(&req->ctx->fallback_work, 1);
+		if (llist_add(&req->io_task_work.node, &last_ctx->fallback_llist))
+			schedule_delayed_work(&last_ctx->fallback_work, 1);
 	}
 
 	if (last_ctx) {
-		flush_delayed_work(&last_ctx->fallback_work);
+		if (sync)
+			flush_delayed_work(&last_ctx->fallback_work);
 		percpu_ref_put(&last_ctx->refs);
 	}
 }
@@ -1718,15 +1711,22 @@ static bool io_assign_file(struct io_kiocb *req, const struct io_issue_def *def,
 	return !!req->file;
 }
 
+#define REQ_ISSUE_SLOW_FLAGS	(REQ_F_CREDS | REQ_F_ARM_LTIMEOUT)
+
 static inline int __io_issue_sqe(struct io_kiocb *req,
 				 unsigned int issue_flags,
 				 const struct io_issue_def *def)
 {
 	const struct cred *creds = NULL;
+	struct io_kiocb *link = NULL;
 	int ret;
 
-	if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred()))
-		creds = override_creds(req->creds);
+	if (unlikely(req->flags & REQ_ISSUE_SLOW_FLAGS)) {
+		if ((req->flags & REQ_F_CREDS) && req->creds != current_cred())
+			creds = override_creds(req->creds);
+		if (req->flags & REQ_F_ARM_LTIMEOUT)
+			link = __io_prep_linked_timeout(req);
+	}
 
 	if (!def->audit_skip)
 		audit_uring_entry(req->opcode);
@@ -1736,8 +1736,12 @@ static inline int __io_issue_sqe(struct io_kiocb *req,
 	if (!def->audit_skip)
 		audit_uring_exit(!ret, ret);
 
-	if (creds)
-		revert_creds(creds);
+	if (unlikely(creds || link)) {
+		if (creds)
+			revert_creds(creds);
+		if (link)
+			io_queue_linked_timeout(link);
+	}
 
 	return ret;
 }
@@ -1763,7 +1767,6 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 
 	if (ret == IOU_ISSUE_SKIP_COMPLETE) {
 		ret = 0;
-		io_arm_ltimeout(req);
 
 		/* If the op doesn't have a file, we're not polling for it */
 		if ((req->ctx->flags & IORING_SETUP_IOPOLL) && def->iopoll_queue)
@@ -1818,8 +1821,6 @@ void io_wq_submit_work(struct io_wq_work *work)
 	else
 		req_ref_get(req);
 
-	io_arm_ltimeout(req);
-
 	/* either cancelled or io-wq is dying, so don't touch tctx->iowq */
 	if (atomic_read(&work->flags) & IO_WQ_WORK_CANCEL) {
 fail:
@@ -1935,15 +1936,11 @@ struct file *io_file_get_normal(struct io_kiocb *req, int fd)
 static void io_queue_async(struct io_kiocb *req, int ret)
 	__must_hold(&req->ctx->uring_lock)
 {
-	struct io_kiocb *linked_timeout;
-
 	if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) {
 		io_req_defer_failed(req, ret);
 		return;
 	}
 
-	linked_timeout = io_prep_linked_timeout(req);
-
 	switch (io_arm_poll_handler(req, 0)) {
 	case IO_APOLL_READY:
 		io_kbuf_recycle(req, 0);
@@ -1956,9 +1953,6 @@ static void io_queue_async(struct io_kiocb *req, int ret)
 	case IO_APOLL_OK:
 		break;
 	}
-
-	if (linked_timeout)
-		io_queue_linked_timeout(linked_timeout);
 }
 
 static inline void io_queue_sqe(struct io_kiocb *req)
diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index 76fcc79656b0..07f8a5cbd37e 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -116,7 +116,7 @@ static int io_region_init_ptr(struct io_mapped_region *mr)
 	void *ptr;
 
 	if (io_check_coalesce_buffer(mr->pages, mr->nr_pages, &ifd)) {
-		if (ifd.nr_folios == 1) {
+		if (ifd.nr_folios == 1 && !PageHighMem(mr->pages[0])) {
 			mr->ptr = page_address(mr->pages[0]);
 			return 0;
 		}
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index b36c8825550e..f80a77c4973f 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1032,10 +1032,33 @@ static int validate_fixed_range(u64 buf_addr, size_t len,
 	return 0;
 }
 
+static int io_import_kbuf(int ddir, struct iov_iter *iter,
+			  struct io_mapped_ubuf *imu, size_t len, size_t offset)
+{
+	size_t count = len + offset;
+
+	iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, count);
+	iov_iter_advance(iter, offset);
+
+	if (count < imu->len) {
+		const struct bio_vec *bvec = iter->bvec;
+
+		while (len > bvec->bv_len) {
+			len -= bvec->bv_len;
+			bvec++;
+		}
+		iter->nr_segs = 1 + bvec - iter->bvec;
+	}
+	return 0;
+}
+
 static int io_import_fixed(int ddir, struct iov_iter *iter,
 			   struct io_mapped_ubuf *imu,
 			   u64 buf_addr, size_t len)
 {
+	const struct bio_vec *bvec;
+	size_t folio_mask;
+	unsigned nr_segs;
 	size_t offset;
 	int ret;
 
@@ -1047,56 +1070,35 @@ static int io_import_fixed(int ddir, struct iov_iter *iter,
 	if (!(imu->dir & (1 << ddir)))
 		return -EFAULT;
 
-	/*
-	 * Might not be a start of buffer, set size appropriately
-	 * and advance us to the beginning.
-	 */
 	offset = buf_addr - imu->ubuf;
-	iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, offset + len);
 
-	if (offset) {
-		/*
-		 * Don't use iov_iter_advance() here, as it's really slow for
-		 * using the latter parts of a big fixed buffer - it iterates
-		 * over each segment manually. We can cheat a bit here for user
-		 * registered nodes, because we know that:
-		 *
-		 * 1) it's a BVEC iter, we set it up
-		 * 2) all bvecs are the same in size, except potentially the
-		 *    first and last bvec
-		 *
-		 * So just find our index, and adjust the iterator afterwards.
-		 * If the offset is within the first bvec (or the whole first
-		 * bvec, just use iov_iter_advance(). This makes it easier
-		 * since we can just skip the first segment, which may not
-		 * be folio_size aligned.
-		 */
-		const struct bio_vec *bvec = imu->bvec;
-
-		/*
-		 * Kernel buffer bvecs, on the other hand, don't necessarily
-		 * have the size property of user registered ones, so we have
-		 * to use the slow iter advance.
-		 */
-		if (offset < bvec->bv_len) {
-			iter->count -= offset;
-			iter->iov_offset = offset;
-		} else if (imu->is_kbuf) {
-			iov_iter_advance(iter, offset);
-		} else {
-			unsigned long seg_skip;
+	if (imu->is_kbuf)
+		return io_import_kbuf(ddir, iter, imu, len, offset);
 
-			/* skip first vec */
-			offset -= bvec->bv_len;
-			seg_skip = 1 + (offset >> imu->folio_shift);
+	/*
+	 * Don't use iov_iter_advance() here, as it's really slow for
+	 * using the latter parts of a big fixed buffer - it iterates
+	 * over each segment manually. We can cheat a bit here for user
+	 * registered nodes, because we know that:
+	 *
+	 * 1) it's a BVEC iter, we set it up
+	 * 2) all bvecs are the same in size, except potentially the
+	 *    first and last bvec
+	 */
+	folio_mask = (1UL << imu->folio_shift) - 1;
+	bvec = imu->bvec;
+	if (offset >= bvec->bv_len) {
+		unsigned long seg_skip;
 
-			iter->bvec += seg_skip;
-			iter->nr_segs -= seg_skip;
-			iter->count -= bvec->bv_len + offset;
-			iter->iov_offset = offset & ((1UL << imu->folio_shift) - 1);
-		}
+		/* skip first vec */
+		offset -= bvec->bv_len;
+		seg_skip = 1 + (offset >> imu->folio_shift);
+		bvec += seg_skip;
+		offset &= folio_mask;
 	}
-
+	nr_segs = (offset + len + bvec->bv_offset + folio_mask) >> imu->folio_shift;
+	iov_iter_bvec(iter, ddir, bvec, nr_segs, len);
+	iter->iov_offset = offset;
 	return 0;
 }
 
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index d037cc68e9d3..03c699493b5a 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -20,7 +20,7 @@
 #include "sqpoll.h"
 
 #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
-#define IORING_TW_CAP_ENTRIES_VALUE	8
+#define IORING_TW_CAP_ENTRIES_VALUE	32
 
 enum {
 	IO_SQ_THREAD_SHOULD_STOP = 0,
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index a9ea7d29cdd9..430ed620ddfe 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -254,6 +254,11 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 			return -EOPNOTSUPP;
 		issue_flags |= IO_URING_F_IOPOLL;
 		req->iopoll_completed = 0;
+		if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) {
+			/* make sure every req only blocks once */
+			req->flags &= ~REQ_F_IOPOLL_STATE;
+			req->iopoll_start = ktime_get_ns();
+		}
 	}
 
 	ret = file->f_op->uring_cmd(ioucmd, issue_flags);
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 0f46e0404c04..0c64129f5d50 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -26,6 +26,11 @@
 #include "zcrx.h"
 #include "rsrc.h"
 
+static inline struct io_zcrx_ifq *io_pp_to_ifq(struct page_pool *pp)
+{
+	return pp->mp_priv;
+}
+
 #define IO_DMA_ATTR (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
 
 static void __io_zcrx_unmap_area(struct io_zcrx_ifq *ifq,
@@ -46,14 +51,21 @@ static void __io_zcrx_unmap_area(struct io_zcrx_ifq *ifq,
 
 static void io_zcrx_unmap_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area)
 {
+	guard(mutex)(&ifq->dma_lock);
+
 	if (area->is_mapped)
 		__io_zcrx_unmap_area(ifq, area, area->nia.num_niovs);
+	area->is_mapped = false;
 }
 
 static int io_zcrx_map_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area)
 {
 	int i;
 
+	guard(mutex)(&ifq->dma_lock);
+	if (area->is_mapped)
+		return 0;
+
 	for (i = 0; i < area->nia.num_niovs; i++) {
 		struct net_iov *niov = &area->nia.niovs[i];
 		dma_addr_t dma;
@@ -247,6 +259,7 @@ static int io_zcrx_create_area(struct io_zcrx_ifq *ifq,
 		niov->owner = &area->nia;
 		area->freelist[i] = i;
 		atomic_set(&area->user_refs[i], 0);
+		niov->type = NET_IOV_IOURING;
 	}
 
 	area->free_count = nr_iovs;
@@ -275,6 +288,7 @@ static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx)
 	ifq->ctx = ctx;
 	spin_lock_init(&ifq->lock);
 	spin_lock_init(&ifq->rq_lock);
+	mutex_init(&ifq->dma_lock);
 	return ifq;
 }
 
@@ -324,6 +338,7 @@ static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq)
 		put_device(ifq->dev);
 
 	io_free_rbuf_ring(ifq);
+	mutex_destroy(&ifq->dma_lock);
 	kfree(ifq);
 }
 
@@ -354,7 +369,8 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 		return -EFAULT;
 	if (copy_from_user(&rd, u64_to_user_ptr(reg.region_ptr), sizeof(rd)))
 		return -EFAULT;
-	if (memchr_inv(&reg.__resv, 0, sizeof(reg.__resv)))
+	if (memchr_inv(&reg.__resv, 0, sizeof(reg.__resv)) ||
+	    reg.__resv2 || reg.zcrx_id)
 		return -EINVAL;
 	if (reg.if_rxq == -1 || !reg.rq_entries || reg.flags)
 		return -EINVAL;
@@ -394,10 +410,6 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 		goto err;
 	get_device(ifq->dev);
 
-	ret = io_zcrx_map_area(ifq, ifq->area);
-	if (ret)
-		goto err;
-
 	mp_param.mp_ops = &io_uring_pp_zc_ops;
 	mp_param.mp_priv = ifq;
 	ret = net_mp_open_rxq(ifq->netdev, reg.if_rxq, &mp_param);
@@ -585,7 +597,7 @@ static void io_zcrx_refill_slow(struct page_pool *pp, struct io_zcrx_ifq *ifq)
 
 static netmem_ref io_pp_zc_alloc_netmems(struct page_pool *pp, gfp_t gfp)
 {
-	struct io_zcrx_ifq *ifq = pp->mp_priv;
+	struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp);
 
 	/* pp should already be ensuring that */
 	if (unlikely(pp->alloc.count))
@@ -617,7 +629,8 @@ static bool io_pp_zc_release_netmem(struct page_pool *pp, netmem_ref netmem)
 
 static int io_pp_zc_init(struct page_pool *pp)
 {
-	struct io_zcrx_ifq *ifq = pp->mp_priv;
+	struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp);
+	int ret;
 
 	if (WARN_ON_ONCE(!ifq))
 		return -EINVAL;
@@ -630,13 +643,17 @@ static int io_pp_zc_init(struct page_pool *pp)
 	if (pp->p.dma_dir != DMA_FROM_DEVICE)
 		return -EOPNOTSUPP;
 
+	ret = io_zcrx_map_area(ifq, ifq->area);
+	if (ret)
+		return ret;
+
 	percpu_ref_get(&ifq->ctx->refs);
 	return 0;
 }
 
 static void io_pp_zc_destroy(struct page_pool *pp)
 {
-	struct io_zcrx_ifq *ifq = pp->mp_priv;
+	struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp);
 	struct io_zcrx_area *area = ifq->area;
 
 	if (WARN_ON_ONCE(area->free_count != area->nia.num_niovs))
@@ -665,6 +682,9 @@ static void io_pp_uninstall(void *mp_priv, struct netdev_rx_queue *rxq)
 	struct io_zcrx_ifq *ifq = mp_priv;
 
 	io_zcrx_drop_netdev(ifq);
+	if (ifq->area)
+		io_zcrx_unmap_area(ifq, ifq->area);
+
 	p->mp_ops = NULL;
 	p->mp_priv = NULL;
 }
@@ -790,8 +810,8 @@ static int io_zcrx_recv_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
 		return io_zcrx_copy_frag(req, ifq, frag, off, len);
 
 	niov = netmem_to_net_iov(frag->netmem);
-	if (niov->pp->mp_ops != &io_uring_pp_zc_ops ||
-	    niov->pp->mp_priv != ifq)
+	if (!niov->pp || niov->pp->mp_ops != &io_uring_pp_zc_ops ||
+	    io_pp_to_ifq(niov->pp) != ifq)
 		return -EFAULT;
 
 	if (!io_zcrx_queue_cqe(req, niov, ifq, off + skb_frag_off(frag), len))
diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
index 47f1c0e8c197..f2bc811f022c 100644
--- a/io_uring/zcrx.h
+++ b/io_uring/zcrx.h
@@ -38,6 +38,7 @@ struct io_zcrx_ifq {
 	struct net_device		*netdev;
 	netdevice_tracker		netdev_tracker;
 	spinlock_t			lock;
+	struct mutex			dma_lock;
 };
 
 #if defined(CONFIG_IO_URING_ZCRX)
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 367eaf2c78b7..0ebbbe37a60f 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -347,12 +347,17 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 /* Get path information necessary for adding watches. */
 static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 {
-	struct dentry *d = kern_path_locked(watch->path, parent);
+	struct dentry *d;
+
+	d = kern_path_locked_negative(watch->path, parent);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
-	/* update watch filter fields */
-	watch->dev = d->d_sb->s_dev;
-	watch->ino = d_backing_inode(d)->i_ino;
+
+	if (d_is_positive(d)) {
+		/* update watch filter fields */
+		watch->dev = d->d_sb->s_dev;
+		watch->ino = d_backing_inode(d)->i_ino;
+	}
 
 	inode_unlock(d_backing_inode(parent->dentry));
 	dput(d);
@@ -418,11 +423,10 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 	/* caller expects mutex locked */
 	mutex_lock(&audit_filter_mutex);
 
-	if (ret && ret != -ENOENT) {
+	if (ret) {
 		audit_put_watch(watch);
 		return ret;
 	}
-	ret = 0;
 
 	/* either find an old parent or attach a new one */
 	parent = audit_find_parent(d_backing_inode(parent_path.dentry));
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 24a26b4bb0b8..324c47ab377a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6391,8 +6391,8 @@ static bool is_int_ptr(struct btf *btf, const struct btf_type *t)
 	return btf_type_is_int(t);
 }
 
-static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto,
-			   int off)
+u32 btf_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto,
+		    int off)
 {
 	const struct btf_param *args;
 	const struct btf_type *t;
@@ -6672,7 +6672,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 			tname, off);
 		return false;
 	}
-	arg = get_ctx_arg_idx(btf, t, off);
+	arg = btf_ctx_arg_idx(btf, t, off);
 	args = (const struct btf_param *)(t + 1);
 	/* if (t == NULL) Fall back to default BPF prog with
 	 * MAX_BPF_FUNC_REG_ARGS u64 arguments.
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 5a5adc66b8e2..92b606d60020 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2189,7 +2189,7 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
 		b = &htab->buckets[i];
 		rcu_read_lock();
 		head = &b->head;
-		hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
+		hlist_nulls_for_each_entry_safe(elem, n, head, hash_node) {
 			key = elem->key;
 			if (is_percpu) {
 				/* current cpu value for percpu map */
diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c
index 2fdf3c978db1..774e5a538811 100644
--- a/kernel/bpf/preload/bpf_preload_kern.c
+++ b/kernel/bpf/preload/bpf_preload_kern.c
@@ -89,5 +89,6 @@ static void __exit fini(void)
 }
 late_initcall(load);
 module_exit(fini);
+MODULE_IMPORT_NS("BPF_INTERNAL");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Embedded BPF programs for introspection in bpffs");
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index d869f51ea93a..9a5f94371e50 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -9,13 +9,14 @@
 #include <linux/slab.h>
 #include <linux/btf_ids.h>
 #include "percpu_freelist.h"
+#include <asm/rqspinlock.h>
 
 #define QUEUE_STACK_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
 
 struct bpf_queue_stack {
 	struct bpf_map map;
-	raw_spinlock_t lock;
+	rqspinlock_t lock;
 	u32 head, tail;
 	u32 size; /* max_entries + 1 */
 
@@ -78,7 +79,7 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
 
 	qs->size = size;
 
-	raw_spin_lock_init(&qs->lock);
+	raw_res_spin_lock_init(&qs->lock);
 
 	return &qs->map;
 }
@@ -98,12 +99,8 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
 	int err = 0;
 	void *ptr;
 
-	if (in_nmi()) {
-		if (!raw_spin_trylock_irqsave(&qs->lock, flags))
-			return -EBUSY;
-	} else {
-		raw_spin_lock_irqsave(&qs->lock, flags);
-	}
+	if (raw_res_spin_lock_irqsave(&qs->lock, flags))
+		return -EBUSY;
 
 	if (queue_stack_map_is_empty(qs)) {
 		memset(value, 0, qs->map.value_size);
@@ -120,7 +117,7 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
 	}
 
 out:
-	raw_spin_unlock_irqrestore(&qs->lock, flags);
+	raw_res_spin_unlock_irqrestore(&qs->lock, flags);
 	return err;
 }
 
@@ -133,12 +130,8 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
 	void *ptr;
 	u32 index;
 
-	if (in_nmi()) {
-		if (!raw_spin_trylock_irqsave(&qs->lock, flags))
-			return -EBUSY;
-	} else {
-		raw_spin_lock_irqsave(&qs->lock, flags);
-	}
+	if (raw_res_spin_lock_irqsave(&qs->lock, flags))
+		return -EBUSY;
 
 	if (queue_stack_map_is_empty(qs)) {
 		memset(value, 0, qs->map.value_size);
@@ -157,7 +150,7 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
 		qs->head = index;
 
 out:
-	raw_spin_unlock_irqrestore(&qs->lock, flags);
+	raw_res_spin_unlock_irqrestore(&qs->lock, flags);
 	return err;
 }
 
@@ -203,12 +196,8 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
 	if (flags & BPF_NOEXIST || flags > BPF_EXIST)
 		return -EINVAL;
 
-	if (in_nmi()) {
-		if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags))
-			return -EBUSY;
-	} else {
-		raw_spin_lock_irqsave(&qs->lock, irq_flags);
-	}
+	if (raw_res_spin_lock_irqsave(&qs->lock, irq_flags))
+		return -EBUSY;
 
 	if (queue_stack_map_is_full(qs)) {
 		if (!replace) {
@@ -227,7 +216,7 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
 		qs->head = 0;
 
 out:
-	raw_spin_unlock_irqrestore(&qs->lock, irq_flags);
+	raw_res_spin_unlock_irqrestore(&qs->lock, irq_flags);
 	return err;
 }
 
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 1499d8caa9a3..719d73299397 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -11,6 +11,7 @@
 #include <linux/kmemleak.h>
 #include <uapi/linux/btf.h>
 #include <linux/btf_ids.h>
+#include <asm/rqspinlock.h>
 
 #define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE)
 
@@ -29,7 +30,7 @@ struct bpf_ringbuf {
 	u64 mask;
 	struct page **pages;
 	int nr_pages;
-	raw_spinlock_t spinlock ____cacheline_aligned_in_smp;
+	rqspinlock_t spinlock ____cacheline_aligned_in_smp;
 	/* For user-space producer ring buffers, an atomic_t busy bit is used
 	 * to synchronize access to the ring buffers in the kernel, rather than
 	 * the spinlock that is used for kernel-producer ring buffers. This is
@@ -173,7 +174,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
 	if (!rb)
 		return NULL;
 
-	raw_spin_lock_init(&rb->spinlock);
+	raw_res_spin_lock_init(&rb->spinlock);
 	atomic_set(&rb->busy, 0);
 	init_waitqueue_head(&rb->waitq);
 	init_irq_work(&rb->work, bpf_ringbuf_notify);
@@ -416,12 +417,8 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 
 	cons_pos = smp_load_acquire(&rb->consumer_pos);
 
-	if (in_nmi()) {
-		if (!raw_spin_trylock_irqsave(&rb->spinlock, flags))
-			return NULL;
-	} else {
-		raw_spin_lock_irqsave(&rb->spinlock, flags);
-	}
+	if (raw_res_spin_lock_irqsave(&rb->spinlock, flags))
+		return NULL;
 
 	pend_pos = rb->pending_pos;
 	prod_pos = rb->producer_pos;
@@ -446,7 +443,7 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 	 */
 	if (new_prod_pos - cons_pos > rb->mask ||
 	    new_prod_pos - pend_pos > rb->mask) {
-		raw_spin_unlock_irqrestore(&rb->spinlock, flags);
+		raw_res_spin_unlock_irqrestore(&rb->spinlock, flags);
 		return NULL;
 	}
 
@@ -458,7 +455,7 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 	/* pairs with consumer's smp_load_acquire() */
 	smp_store_release(&rb->producer_pos, new_prod_pos);
 
-	raw_spin_unlock_irqrestore(&rb->spinlock, flags);
+	raw_res_spin_unlock_irqrestore(&rb->spinlock, flags);
 
 	return (void *)hdr + BPF_RINGBUF_HDR_SZ;
 }
diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c
index b896c4a75a5c..338305c8852c 100644
--- a/kernel/bpf/rqspinlock.c
+++ b/kernel/bpf/rqspinlock.c
@@ -253,7 +253,7 @@ static noinline int check_timeout(rqspinlock_t *lock, u32 mask,
 	})
 #else
 #define RES_CHECK_TIMEOUT(ts, ret, mask)			      \
-	({ (ret) = check_timeout(&(ts)); })
+	({ (ret) = check_timeout((lock), (mask), &(ts)); })
 #endif
 
 /*
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9794446bc8c6..64c3393e8270 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1583,7 +1583,7 @@ struct bpf_map *bpf_map_get(u32 ufd)
 
 	return map;
 }
-EXPORT_SYMBOL(bpf_map_get);
+EXPORT_SYMBOL_NS(bpf_map_get, "BPF_INTERNAL");
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
@@ -3364,7 +3364,7 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 	bpf_link_inc(link);
 	return link;
 }
-EXPORT_SYMBOL(bpf_link_get_from_fd);
+EXPORT_SYMBOL_NS(bpf_link_get_from_fd, "BPF_INTERNAL");
 
 static void bpf_tracing_link_release(struct bpf_link *link)
 {
@@ -6020,7 +6020,7 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
 		return ____bpf_sys_bpf(cmd, attr, size);
 	}
 }
-EXPORT_SYMBOL(kern_sys_bpf);
+EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL");
 
 static const struct bpf_func_proto bpf_sys_bpf_proto = {
 	.func		= bpf_sys_bpf,
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 3caf2cd86e65..63e5b90da1f3 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -90,7 +90,7 @@
 DEFINE_MUTEX(cgroup_mutex);
 DEFINE_SPINLOCK(css_set_lock);
 
-#ifdef CONFIG_PROVE_RCU
+#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP)
 EXPORT_SYMBOL_GPL(cgroup_mutex);
 EXPORT_SYMBOL_GPL(css_set_lock);
 #endif
@@ -2353,9 +2353,37 @@ static struct file_system_type cgroup2_fs_type = {
 };
 
 #ifdef CONFIG_CPUSETS_V1
+enum cpuset_param {
+	Opt_cpuset_v2_mode,
+};
+
+static const struct fs_parameter_spec cpuset_fs_parameters[] = {
+	fsparam_flag  ("cpuset_v2_mode", Opt_cpuset_v2_mode),
+	{}
+};
+
+static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, cpuset_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_cpuset_v2_mode:
+		ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 static const struct fs_context_operations cpuset_fs_context_ops = {
 	.get_tree	= cgroup1_get_tree,
 	.free		= cgroup_fs_context_free,
+	.parse_param	= cpuset_parse_param,
 };
 
 /*
@@ -2392,6 +2420,7 @@ static int cpuset_init_fs_context(struct fs_context *fc)
 static struct file_system_type cpuset_fs_type = {
 	.name			= "cpuset",
 	.init_fs_context	= cpuset_init_fs_context,
+	.parameters		= cpuset_fs_parameters,
 	.fs_flags		= FS_USERNS_MOUNT,
 };
 #endif
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 306b60430091..24b70ea3e6ce 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1116,9 +1116,11 @@ void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 
 		if (top_cs) {
 			/*
-			 * Percpu kthreads in top_cpuset are ignored
+			 * PF_NO_SETAFFINITY tasks are ignored.
+			 * All per cpu kthreads should have PF_NO_SETAFFINITY
+			 * flag set, see kthread_set_per_cpu().
 			 */
-			if (kthread_is_per_cpu(task))
+			if (task->flags & PF_NO_SETAFFINITY)
 				continue;
 			cpumask_andnot(new_cpus, possible_mask, subpartitions_cpus);
 		} else {
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 3b2bdca9f1d4..77c8d9487a9a 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -336,16 +336,22 @@ static phys_addr_t dma_reserved_default_memory_size __initdata;
 
 static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
 {
-	if (!rmem->priv) {
-		struct dma_coherent_mem *mem;
+	struct dma_coherent_mem *mem = rmem->priv;
 
+	if (!mem) {
 		mem = dma_init_coherent_memory(rmem->base, rmem->base,
 					       rmem->size, true);
 		if (IS_ERR(mem))
 			return PTR_ERR(mem);
 		rmem->priv = mem;
 	}
-	dma_assign_coherent_memory(dev, rmem->priv);
+
+	/* Warn if the device potentially can't use the reserved memory */
+	if (mem->device_base + rmem->size - 1 >
+	    min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit))
+		dev_warn(dev, "reserved memory is beyond device's set DMA address range\n");
+
+	dma_assign_coherent_memory(dev, mem);
 	return 0;
 }
 
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 055da410ac71..8df0dfaaca18 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -64,8 +64,7 @@ struct cma *dma_contiguous_default_area;
  * Users, who want to set the size of global CMA area for their system
  * should use cma= kernel parameter.
  */
-static const phys_addr_t size_bytes __initconst =
-	(phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
+#define size_bytes ((phys_addr_t)CMA_SIZE_MBYTES * SZ_1M)
 static phys_addr_t  size_cmdline __initdata = -1;
 static phys_addr_t base_cmdline __initdata;
 static phys_addr_t limit_cmdline __initdata;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index cda127027e48..051a32988040 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -910,6 +910,19 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_set_coherent_mask);
 
+static bool __dma_addressing_limited(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
+			 dma_get_required_mask(dev))
+		return true;
+
+	if (unlikely(ops) || use_dma_iommu(dev))
+		return false;
+	return !dma_direct_all_ram_mapped(dev);
+}
+
 /**
  * dma_addressing_limited - return if the device is addressing limited
  * @dev:	device to check
@@ -920,15 +933,11 @@ EXPORT_SYMBOL(dma_set_coherent_mask);
  */
 bool dma_addressing_limited(struct device *dev)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	if (min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
-			 dma_get_required_mask(dev))
-		return true;
-
-	if (unlikely(ops) || use_dma_iommu(dev))
+	if (!__dma_addressing_limited(dev))
 		return false;
-	return !dma_direct_all_ram_mapped(dev);
+
+	dev_dbg(dev, "device is DMA addressing limited\n");
+	return true;
 }
 EXPORT_SYMBOL_GPL(dma_addressing_limited);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 128db74e9eab..95e703891b24 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3943,7 +3943,7 @@ static int merge_sched_in(struct perf_event *event, void *data)
 			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
 
 			if (*perf_event_fasync(event))
-				event->pending_kill = POLL_HUP;
+				event->pending_kill = POLL_ERR;
 
 			perf_event_wakeup(event);
 		} else {
@@ -5518,30 +5518,6 @@ static bool exclusive_event_installable(struct perf_event *event,
 
 static void perf_free_addr_filters(struct perf_event *event);
 
-static void perf_pending_task_sync(struct perf_event *event)
-{
-	struct callback_head *head = &event->pending_task;
-
-	if (!event->pending_work)
-		return;
-	/*
-	 * If the task is queued to the current task's queue, we
-	 * obviously can't wait for it to complete. Simply cancel it.
-	 */
-	if (task_work_cancel(current, head)) {
-		event->pending_work = 0;
-		local_dec(&event->ctx->nr_no_switch_fast);
-		return;
-	}
-
-	/*
-	 * All accesses related to the event are within the same RCU section in
-	 * perf_pending_task(). The RCU grace period before the event is freed
-	 * will make sure all those accesses are complete by then.
-	 */
-	rcuwait_wait_event(&event->pending_work_wait, !event->pending_work, TASK_UNINTERRUPTIBLE);
-}
-
 /* vs perf_event_alloc() error */
 static void __free_event(struct perf_event *event)
 {
@@ -5599,7 +5575,6 @@ static void _free_event(struct perf_event *event)
 {
 	irq_work_sync(&event->pending_irq);
 	irq_work_sync(&event->pending_disable_irq);
-	perf_pending_task_sync(event);
 
 	unaccount_event(event);
 
@@ -5692,10 +5667,17 @@ static void perf_remove_from_owner(struct perf_event *event)
 
 static void put_event(struct perf_event *event)
 {
+	struct perf_event *parent;
+
 	if (!atomic_long_dec_and_test(&event->refcount))
 		return;
 
+	parent = event->parent;
 	_free_event(event);
+
+	/* Matches the refcount bump in inherit_event() */
+	if (parent)
+		put_event(parent);
 }
 
 /*
@@ -5779,11 +5761,6 @@ again:
 		if (tmp == child) {
 			perf_remove_from_context(child, DETACH_GROUP);
 			list_move(&child->child_list, &free_list);
-			/*
-			 * This matches the refcount bump in inherit_event();
-			 * this can't be the last reference.
-			 */
-			put_event(event);
 		} else {
 			var = &ctx->refcount;
 		}
@@ -5809,7 +5786,8 @@ again:
 		void *var = &child->ctx->refcount;
 
 		list_del(&child->child_list);
-		free_event(child);
+		/* Last reference unless ->pending_task work is pending */
+		put_event(child);
 
 		/*
 		 * Wake any perf_event_free_task() waiting for this event to be
@@ -5820,7 +5798,11 @@ again:
 	}
 
 no_ctx:
-	put_event(event); /* Must be the 'last' reference */
+	/*
+	 * Last reference unless ->pending_task work is pending on this event
+	 * or any of its children.
+	 */
+	put_event(event);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(perf_event_release_kernel);
@@ -6093,7 +6075,7 @@ static __poll_t perf_poll(struct file *file, poll_table *wait)
 
 	if (unlikely(READ_ONCE(event->state) == PERF_EVENT_STATE_ERROR &&
 		     event->attr.pinned))
-		return events;
+		return EPOLLERR;
 
 	/*
 	 * Pin the event->rb by taking event->mmap_mutex; otherwise
@@ -7236,12 +7218,6 @@ static void perf_pending_task(struct callback_head *head)
 	int rctx;
 
 	/*
-	 * All accesses to the event must belong to the same implicit RCU read-side
-	 * critical section as the ->pending_work reset. See comment in
-	 * perf_pending_task_sync().
-	 */
-	rcu_read_lock();
-	/*
 	 * If we 'fail' here, that's OK, it means recursion is already disabled
 	 * and we won't recurse 'further'.
 	 */
@@ -7251,9 +7227,8 @@ static void perf_pending_task(struct callback_head *head)
 		event->pending_work = 0;
 		perf_sigtrap(event);
 		local_dec(&event->ctx->nr_no_switch_fast);
-		rcuwait_wake_up(&event->pending_work_wait);
 	}
-	rcu_read_unlock();
+	put_event(event);
 
 	if (rctx >= 0)
 		perf_swevent_put_recursion_context(rctx);
@@ -10248,6 +10223,7 @@ static int __perf_event_overflow(struct perf_event *event,
 		    !task_work_add(current, &event->pending_task, notify_mode)) {
 			event->pending_work = pending_id;
 			local_inc(&event->ctx->nr_no_switch_fast);
+			WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount));
 
 			event->pending_addr = 0;
 			if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR))
@@ -12610,7 +12586,6 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	init_irq_work(&event->pending_irq, perf_pending_irq);
 	event->pending_disable_irq = IRQ_WORK_INIT_HARD(perf_pending_disable);
 	init_task_work(&event->pending_task, perf_pending_task);
-	rcuwait_init(&event->pending_work_wait);
 
 	mutex_init(&event->mmap_mutex);
 	raw_spin_lock_init(&event->addr_filters.lock);
@@ -13747,8 +13722,7 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx)
 		 * Kick perf_poll() for is_event_hup();
 		 */
 		perf_event_wakeup(parent_event);
-		free_event(event);
-		put_event(parent_event);
+		put_event(event);
 		return;
 	}
 
@@ -13872,13 +13846,11 @@ static void perf_free_event(struct perf_event *event,
 	list_del_init(&event->child_list);
 	mutex_unlock(&parent->child_mutex);
 
-	put_event(parent);
-
 	raw_spin_lock_irq(&ctx->lock);
 	perf_group_detach(event);
 	list_del_event(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
-	free_event(event);
+	put_event(event);
 }
 
 /*
@@ -14016,6 +13988,9 @@ inherit_event(struct perf_event *parent_event,
 	if (IS_ERR(child_event))
 		return child_event;
 
+	get_ctx(child_ctx);
+	child_event->ctx = child_ctx;
+
 	pmu_ctx = find_get_pmu_context(child_event->pmu, child_ctx, child_event);
 	if (IS_ERR(pmu_ctx)) {
 		free_event(child_event);
@@ -14037,8 +14012,6 @@ inherit_event(struct perf_event *parent_event,
 		return NULL;
 	}
 
-	get_ctx(child_ctx);
-
 	/*
 	 * Make the child state follow the state of the parent event,
 	 * not its attr.disabled bit.  We hold the parent's mutex,
@@ -14059,7 +14032,6 @@ inherit_event(struct perf_event *parent_event,
 		local64_set(&hwc->period_left, sample_period);
 	}
 
-	child_event->ctx = child_ctx;
 	child_event->overflow_handler = parent_event->overflow_handler;
 	child_event->overflow_handler_context
 		= parent_event->overflow_handler_context;
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 615b4e6d22c7..8d783b5882b6 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1956,6 +1956,9 @@ static void free_ret_instance(struct uprobe_task *utask,
 	 * to-be-reused return instances for future uretprobes. If ri_timer()
 	 * happens to be running right now, though, we fallback to safety and
 	 * just perform RCU-delated freeing of ri.
+	 * Admittedly, this is a rather simple use of seqcount, but it nicely
+	 * abstracts away all the necessary memory barriers, so we use
+	 * a well-supported kernel primitive here.
 	 */
 	if (raw_seqcount_try_begin(&utask->ri_seqcount, seq)) {
 		/* immediate reuse of ri without RCU GP is OK */
@@ -2016,12 +2019,20 @@ static void ri_timer(struct timer_list *timer)
 	/* RCU protects return_instance from freeing. */
 	guard(rcu)();
 
-	write_seqcount_begin(&utask->ri_seqcount);
+	/*
+	 * See free_ret_instance() for notes on seqcount use.
+	 * We also employ raw API variants to avoid lockdep false-positive
+	 * warning complaining about enabled preemption. The timer can only be
+	 * invoked once for a uprobe_task. Therefore there can only be one
+	 * writer. The reader does not require an even sequence count to make
+	 * progress, so it is OK to remain preemptible on PREEMPT_RT.
+	 */
+	raw_write_seqcount_begin(&utask->ri_seqcount);
 
 	for_each_ret_instance_rcu(ri, utask->return_instances)
 		hprobe_expire(&ri->hprobe, false);
 
-	write_seqcount_end(&utask->ri_seqcount);
+	raw_write_seqcount_end(&utask->ri_seqcount);
 }
 
 static struct uprobe_task *alloc_utask(void)
diff --git a/kernel/fork.c b/kernel/fork.c
index c4b26cd8998b..168681fc4b25 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -498,10 +498,6 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 	vma_numab_state_init(new);
 	dup_anon_vma_name(orig, new);
 
-	/* track_pfn_copy() will later take care of copying internal state. */
-	if (unlikely(new->vm_flags & VM_PFNMAP))
-		untrack_pfn_clear(new);
-
 	return new;
 }
 
@@ -672,6 +668,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		tmp = vm_area_dup(mpnt);
 		if (!tmp)
 			goto fail_nomem;
+
+		/* track_pfn_copy() will later take care of copying internal state. */
+		if (unlikely(tmp->vm_flags & VM_PFNMAP))
+			untrack_pfn_clear(tmp);
+
 		retval = vma_dup_policy(mpnt, tmp);
 		if (retval)
 			goto fail_nomem_policy;
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 5c8d43cdb0a3..c05ba7ca00fa 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -761,7 +761,7 @@ static int msi_domain_translate(struct irq_domain *domain, struct irq_fwspec *fw
 static void msi_domain_debug_show(struct seq_file *m, struct irq_domain *d,
 				  struct irq_data *irqd, int ind)
 {
-	struct msi_desc *desc = irq_data_get_msi_desc(irqd);
+	struct msi_desc *desc = irqd ? irq_data_get_msi_desc(irqd) : NULL;
 
 	if (!desc)
 		return;
diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig
index d7762ef5949a..39278737bb68 100644
--- a/kernel/module/Kconfig
+++ b/kernel/module/Kconfig
@@ -192,6 +192,11 @@ config GENDWARFKSYMS
 	depends on !DEBUG_INFO_REDUCED && !DEBUG_INFO_SPLIT
 	# Requires ELF object files.
 	depends on !LTO
+	# To avoid conflicts with the discarded __gendwarfksyms_ptr symbols on
+	# X86, requires pahole before commit 47dcb534e253 ("btf_encoder: Stop
+	# indexing symbols for VARs") or after commit 9810758003ce ("btf_encoder:
+	# Verify 0 address DWARF variables are in ELF section").
+	depends on !X86 || !DEBUG_INFO_BTF || PAHOLE_VERSION < 128 || PAHOLE_VERSION > 129
 	help
 	  Calculate symbol versions from DWARF debugging information using
 	  gendwarfksyms. Requires DEBUG_INFO to be enabled.
diff --git a/kernel/padata.c b/kernel/padata.c
index b3d4eacc4f5d..7eee94166357 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -358,7 +358,8 @@ static void padata_reorder(struct parallel_data *pd)
 		 * To avoid UAF issue, add pd ref here, and put pd ref after reorder_work finish.
 		 */
 		padata_get_pd(pd);
-		queue_work(pinst->serial_wq, &pd->reorder_work);
+		if (!queue_work(pinst->serial_wq, &pd->reorder_work))
+			padata_put_pd(pd);
 	}
 }
 
diff --git a/kernel/params.c b/kernel/params.c
index 2509f216c9f3..b92d64161b75 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -760,38 +760,35 @@ void destroy_params(const struct kernel_param *params, unsigned num)
 			params[i].ops->free(params[i].arg);
 }
 
-static struct module_kobject * __init locate_module_kobject(const char *name)
+struct module_kobject __modinit * lookup_or_create_module_kobject(const char *name)
 {
 	struct module_kobject *mk;
 	struct kobject *kobj;
 	int err;
 
 	kobj = kset_find_obj(module_kset, name);
-	if (kobj) {
-		mk = to_module_kobject(kobj);
-	} else {
-		mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
-		BUG_ON(!mk);
-
-		mk->mod = THIS_MODULE;
-		mk->kobj.kset = module_kset;
-		err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL,
-					   "%s", name);
-#ifdef CONFIG_MODULES
-		if (!err)
-			err = sysfs_create_file(&mk->kobj, &module_uevent.attr);
-#endif
-		if (err) {
-			kobject_put(&mk->kobj);
-			pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n",
-				name, err);
-			return NULL;
-		}
+	if (kobj)
+		return to_module_kobject(kobj);
 
-		/* So that we hold reference in both cases. */
-		kobject_get(&mk->kobj);
+	mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
+	if (!mk)
+		return NULL;
+
+	mk->mod = THIS_MODULE;
+	mk->kobj.kset = module_kset;
+	err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name);
+	if (IS_ENABLED(CONFIG_MODULES) && !err)
+		err = sysfs_create_file(&mk->kobj, &module_uevent.attr);
+	if (err) {
+		kobject_put(&mk->kobj);
+		pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n",
+			name, err);
+		return NULL;
 	}
 
+	/* So that we hold reference in both cases. */
+	kobject_get(&mk->kobj);
+
 	return mk;
 }
 
@@ -802,7 +799,7 @@ static void __init kernel_add_sysfs_param(const char *name,
 	struct module_kobject *mk;
 	int err;
 
-	mk = locate_module_kobject(name);
+	mk = lookup_or_create_module_kobject(name);
 	if (!mk)
 		return;
 
@@ -873,7 +870,7 @@ static void __init version_sysfs_builtin(void)
 	int err;
 
 	for (vattr = __start___modver; vattr < __stop___modver; vattr++) {
-		mk = locate_module_kobject(vattr->module_name);
+		mk = lookup_or_create_module_kobject(vattr->module_name);
 		if (mk) {
 			err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
 			WARN_ON_ONCE(err);
@@ -946,7 +943,9 @@ struct kset *module_kset;
 static void module_kobj_release(struct kobject *kobj)
 {
 	struct module_kobject *mk = to_module_kobject(kobj);
-	complete(mk->kobj_completion);
+
+	if (mk->kobj_completion)
+		complete(mk->kobj_completion);
 }
 
 const struct kobj_type module_ktype = {
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 1a19d69b91ed..816f07f9d30f 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -81,9 +81,23 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 	if (!cpufreq_this_cpu_can_update(sg_policy->policy))
 		return false;
 
-	if (unlikely(sg_policy->limits_changed)) {
-		sg_policy->limits_changed = false;
-		sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+	if (unlikely(READ_ONCE(sg_policy->limits_changed))) {
+		WRITE_ONCE(sg_policy->limits_changed, false);
+		sg_policy->need_freq_update = true;
+
+		/*
+		 * The above limits_changed update must occur before the reads
+		 * of policy limits in cpufreq_driver_resolve_freq() or a policy
+		 * limits update might be missed, so use a memory barrier to
+		 * ensure it.
+		 *
+		 * This pairs with the write memory barrier in sugov_limits().
+		 */
+		smp_mb();
+
+		return true;
+	} else if (sg_policy->need_freq_update) {
+		/* ignore_dl_rate_limit() wants a new frequency to be found. */
 		return true;
 	}
 
@@ -95,10 +109,22 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 				   unsigned int next_freq)
 {
-	if (sg_policy->need_freq_update)
+	if (sg_policy->need_freq_update) {
 		sg_policy->need_freq_update = false;
-	else if (sg_policy->next_freq == next_freq)
+		/*
+		 * The policy limits have changed, but if the return value of
+		 * cpufreq_driver_resolve_freq() after applying the new limits
+		 * is still equal to the previously selected frequency, the
+		 * driver callback need not be invoked unless the driver
+		 * specifically wants that to happen on every update of the
+		 * policy limits.
+		 */
+		if (sg_policy->next_freq == next_freq &&
+		    !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
+			return false;
+	} else if (sg_policy->next_freq == next_freq) {
 		return false;
+	}
 
 	sg_policy->next_freq = next_freq;
 	sg_policy->last_freq_update_time = time;
@@ -365,7 +391,7 @@ static inline bool sugov_hold_freq(struct sugov_cpu *sg_cpu) { return false; }
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
 {
 	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
-		sg_cpu->sg_policy->limits_changed = true;
+		sg_cpu->sg_policy->need_freq_update = true;
 }
 
 static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
@@ -871,7 +897,16 @@ static void sugov_limits(struct cpufreq_policy *policy)
 		mutex_unlock(&sg_policy->work_lock);
 	}
 
-	sg_policy->limits_changed = true;
+	/*
+	 * The limits_changed update below must take place before the updates
+	 * of policy limits in cpufreq_set_policy() or a policy limits update
+	 * might be missed, so use a memory barrier to ensure it.
+	 *
+	 * This pairs with the memory barrier in sugov_should_update_freq().
+	 */
+	smp_wmb();
+
+	WRITE_ONCE(sg_policy->limits_changed, true);
 }
 
 struct cpufreq_governor schedutil_gov = {
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 66bcd40a28ca..f5133249fd4d 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -163,7 +163,7 @@ enum scx_ops_flags {
 	/*
 	 * CPU cgroup support flags
 	 */
-	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* cpu.weight */
+	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* DEPRECATED, will be removed on 6.18 */
 
 	SCX_OPS_ALL_FLAGS	= SCX_OPS_KEEP_BUILTIN_IDLE |
 				  SCX_OPS_ENQ_LAST |
@@ -1118,8 +1118,38 @@ static void scx_kf_disallow(u32 mask)
 	current->scx.kf_mask &= ~mask;
 }
 
-#define SCX_CALL_OP(mask, op, args...)						\
+/*
+ * Track the rq currently locked.
+ *
+ * This allows kfuncs to safely operate on rq from any scx ops callback,
+ * knowing which rq is already locked.
+ */
+static DEFINE_PER_CPU(struct rq *, locked_rq);
+
+static inline void update_locked_rq(struct rq *rq)
+{
+	/*
+	 * Check whether @rq is actually locked. This can help expose bugs
+	 * or incorrect assumptions about the context in which a kfunc or
+	 * callback is executed.
+	 */
+	if (rq)
+		lockdep_assert_rq_held(rq);
+	__this_cpu_write(locked_rq, rq);
+}
+
+/*
+ * Return the rq currently locked from an scx callback, or NULL if no rq is
+ * locked.
+ */
+static inline struct rq *scx_locked_rq(void)
+{
+	return __this_cpu_read(locked_rq);
+}
+
+#define SCX_CALL_OP(mask, op, rq, args...)					\
 do {										\
+	update_locked_rq(rq);							\
 	if (mask) {								\
 		scx_kf_allow(mask);						\
 		scx_ops.op(args);						\
@@ -1127,11 +1157,14 @@ do {										\
 	} else {								\
 		scx_ops.op(args);						\
 	}									\
+	update_locked_rq(NULL);							\
 } while (0)
 
-#define SCX_CALL_OP_RET(mask, op, args...)					\
+#define SCX_CALL_OP_RET(mask, op, rq, args...)					\
 ({										\
 	__typeof__(scx_ops.op(args)) __ret;					\
+										\
+	update_locked_rq(rq);							\
 	if (mask) {								\
 		scx_kf_allow(mask);						\
 		__ret = scx_ops.op(args);					\
@@ -1139,6 +1172,7 @@ do {										\
 	} else {								\
 		__ret = scx_ops.op(args);					\
 	}									\
+	update_locked_rq(NULL);							\
 	__ret;									\
 })
 
@@ -1153,31 +1187,31 @@ do {										\
  * scx_kf_allowed_on_arg_tasks() to test whether the invocation is allowed on
  * the specific task.
  */
-#define SCX_CALL_OP_TASK(mask, op, task, args...)				\
+#define SCX_CALL_OP_TASK(mask, op, rq, task, args...)				\
 do {										\
 	BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL);				\
 	current->scx.kf_tasks[0] = task;					\
-	SCX_CALL_OP(mask, op, task, ##args);					\
+	SCX_CALL_OP(mask, op, rq, task, ##args);				\
 	current->scx.kf_tasks[0] = NULL;					\
 } while (0)
 
-#define SCX_CALL_OP_TASK_RET(mask, op, task, args...)				\
+#define SCX_CALL_OP_TASK_RET(mask, op, rq, task, args...)			\
 ({										\
 	__typeof__(scx_ops.op(task, ##args)) __ret;				\
 	BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL);				\
 	current->scx.kf_tasks[0] = task;					\
-	__ret = SCX_CALL_OP_RET(mask, op, task, ##args);			\
+	__ret = SCX_CALL_OP_RET(mask, op, rq, task, ##args);			\
 	current->scx.kf_tasks[0] = NULL;					\
 	__ret;									\
 })
 
-#define SCX_CALL_OP_2TASKS_RET(mask, op, task0, task1, args...)			\
+#define SCX_CALL_OP_2TASKS_RET(mask, op, rq, task0, task1, args...)		\
 ({										\
 	__typeof__(scx_ops.op(task0, task1, ##args)) __ret;			\
 	BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL);				\
 	current->scx.kf_tasks[0] = task0;					\
 	current->scx.kf_tasks[1] = task1;					\
-	__ret = SCX_CALL_OP_RET(mask, op, task0, task1, ##args);		\
+	__ret = SCX_CALL_OP_RET(mask, op, rq, task0, task1, ##args);		\
 	current->scx.kf_tasks[0] = NULL;					\
 	current->scx.kf_tasks[1] = NULL;					\
 	__ret;									\
@@ -2172,7 +2206,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 	WARN_ON_ONCE(*ddsp_taskp);
 	*ddsp_taskp = p;
 
-	SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, p, enq_flags);
+	SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, rq, p, enq_flags);
 
 	*ddsp_taskp = NULL;
 	if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID)
@@ -2269,7 +2303,7 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags
 	add_nr_running(rq, 1);
 
 	if (SCX_HAS_OP(runnable) && !task_on_rq_migrating(p))
-		SCX_CALL_OP_TASK(SCX_KF_REST, runnable, p, enq_flags);
+		SCX_CALL_OP_TASK(SCX_KF_REST, runnable, rq, p, enq_flags);
 
 	if (enq_flags & SCX_ENQ_WAKEUP)
 		touch_core_sched(rq, p);
@@ -2283,7 +2317,7 @@ out:
 		__scx_add_event(SCX_EV_SELECT_CPU_FALLBACK, 1);
 }
 
-static void ops_dequeue(struct task_struct *p, u64 deq_flags)
+static void ops_dequeue(struct rq *rq, struct task_struct *p, u64 deq_flags)
 {
 	unsigned long opss;
 
@@ -2304,7 +2338,7 @@ static void ops_dequeue(struct task_struct *p, u64 deq_flags)
 		BUG();
 	case SCX_OPSS_QUEUED:
 		if (SCX_HAS_OP(dequeue))
-			SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, p, deq_flags);
+			SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, rq, p, deq_flags);
 
 		if (atomic_long_try_cmpxchg(&p->scx.ops_state, &opss,
 					    SCX_OPSS_NONE))
@@ -2337,7 +2371,7 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags
 		return true;
 	}
 
-	ops_dequeue(p, deq_flags);
+	ops_dequeue(rq, p, deq_flags);
 
 	/*
 	 * A currently running task which is going off @rq first gets dequeued
@@ -2353,11 +2387,11 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags
 	 */
 	if (SCX_HAS_OP(stopping) && task_current(rq, p)) {
 		update_curr_scx(rq);
-		SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, false);
+		SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, false);
 	}
 
 	if (SCX_HAS_OP(quiescent) && !task_on_rq_migrating(p))
-		SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, p, deq_flags);
+		SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, rq, p, deq_flags);
 
 	if (deq_flags & SCX_DEQ_SLEEP)
 		p->scx.flags |= SCX_TASK_DEQD_FOR_SLEEP;
@@ -2377,7 +2411,7 @@ static void yield_task_scx(struct rq *rq)
 	struct task_struct *p = rq->curr;
 
 	if (SCX_HAS_OP(yield))
-		SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, p, NULL);
+		SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, p, NULL);
 	else
 		p->scx.slice = 0;
 }
@@ -2387,7 +2421,7 @@ static bool yield_to_task_scx(struct rq *rq, struct task_struct *to)
 	struct task_struct *from = rq->curr;
 
 	if (SCX_HAS_OP(yield))
-		return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, from, to);
+		return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, from, to);
 	else
 		return false;
 }
@@ -2945,7 +2979,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 		 * emitted in switch_class().
 		 */
 		if (SCX_HAS_OP(cpu_acquire))
-			SCX_CALL_OP(SCX_KF_REST, cpu_acquire, cpu_of(rq), NULL);
+			SCX_CALL_OP(SCX_KF_REST, cpu_acquire, rq, cpu_of(rq), NULL);
 		rq->scx.cpu_released = false;
 	}
 
@@ -2990,7 +3024,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 	do {
 		dspc->nr_tasks = 0;
 
-		SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, cpu_of(rq),
+		SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, rq, cpu_of(rq),
 			    prev_on_scx ? prev : NULL);
 
 		flush_dispatch_buf(rq);
@@ -3104,7 +3138,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 		 * Core-sched might decide to execute @p before it is
 		 * dispatched. Call ops_dequeue() to notify the BPF scheduler.
 		 */
-		ops_dequeue(p, SCX_DEQ_CORE_SCHED_EXEC);
+		ops_dequeue(rq, p, SCX_DEQ_CORE_SCHED_EXEC);
 		dispatch_dequeue(rq, p);
 	}
 
@@ -3112,7 +3146,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 
 	/* see dequeue_task_scx() on why we skip when !QUEUED */
 	if (SCX_HAS_OP(running) && (p->scx.flags & SCX_TASK_QUEUED))
-		SCX_CALL_OP_TASK(SCX_KF_REST, running, p);
+		SCX_CALL_OP_TASK(SCX_KF_REST, running, rq, p);
 
 	clr_task_runnable(p, true);
 
@@ -3193,8 +3227,7 @@ static void switch_class(struct rq *rq, struct task_struct *next)
 				.task = next,
 			};
 
-			SCX_CALL_OP(SCX_KF_CPU_RELEASE,
-				    cpu_release, cpu_of(rq), &args);
+			SCX_CALL_OP(SCX_KF_CPU_RELEASE, cpu_release, rq, cpu_of(rq), &args);
 		}
 		rq->scx.cpu_released = true;
 	}
@@ -3207,7 +3240,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 
 	/* see dequeue_task_scx() on why we skip when !QUEUED */
 	if (SCX_HAS_OP(stopping) && (p->scx.flags & SCX_TASK_QUEUED))
-		SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, true);
+		SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, true);
 
 	if (p->scx.flags & SCX_TASK_QUEUED) {
 		set_task_runnable(rq, p);
@@ -3348,7 +3381,7 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
 	 * verifier.
 	 */
 	if (SCX_HAS_OP(core_sched_before) && !scx_rq_bypassing(task_rq(a)))
-		return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before,
+		return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before, NULL,
 					      (struct task_struct *)a,
 					      (struct task_struct *)b);
 	else
@@ -3385,7 +3418,7 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag
 		*ddsp_taskp = p;
 
 		cpu = SCX_CALL_OP_TASK_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU,
-					   select_cpu, p, prev_cpu, wake_flags);
+					   select_cpu, NULL, p, prev_cpu, wake_flags);
 		p->scx.selected_cpu = cpu;
 		*ddsp_taskp = NULL;
 		if (ops_cpu_valid(cpu, "from ops.select_cpu()"))
@@ -3430,8 +3463,8 @@ static void set_cpus_allowed_scx(struct task_struct *p,
 	 * designation pointless. Cast it away when calling the operation.
 	 */
 	if (SCX_HAS_OP(set_cpumask))
-		SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p,
-				 (struct cpumask *)p->cpus_ptr);
+		SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, NULL,
+				 p, (struct cpumask *)p->cpus_ptr);
 }
 
 static void handle_hotplug(struct rq *rq, bool online)
@@ -3444,9 +3477,9 @@ static void handle_hotplug(struct rq *rq, bool online)
 		scx_idle_update_selcpu_topology(&scx_ops);
 
 	if (online && SCX_HAS_OP(cpu_online))
-		SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, cpu);
+		SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, NULL, cpu);
 	else if (!online && SCX_HAS_OP(cpu_offline))
-		SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, cpu);
+		SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, NULL, cpu);
 	else
 		scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG,
 			     "cpu %d going %s, exiting scheduler", cpu,
@@ -3550,7 +3583,7 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued)
 		curr->scx.slice = 0;
 		touch_core_sched(rq, curr);
 	} else if (SCX_HAS_OP(tick)) {
-		SCX_CALL_OP_TASK(SCX_KF_REST, tick, curr);
+		SCX_CALL_OP_TASK(SCX_KF_REST, tick, rq, curr);
 	}
 
 	if (!curr->scx.slice)
@@ -3627,7 +3660,7 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool
 			.fork = fork,
 		};
 
-		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, p, &args);
+		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, NULL, p, &args);
 		if (unlikely(ret)) {
 			ret = ops_sanitize_err("init_task", ret);
 			return ret;
@@ -3668,9 +3701,10 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool
 
 static void scx_ops_enable_task(struct task_struct *p)
 {
+	struct rq *rq = task_rq(p);
 	u32 weight;
 
-	lockdep_assert_rq_held(task_rq(p));
+	lockdep_assert_rq_held(rq);
 
 	/*
 	 * Set the weight before calling ops.enable() so that the scheduler
@@ -3684,20 +3718,22 @@ static void scx_ops_enable_task(struct task_struct *p)
 	p->scx.weight = sched_weight_to_cgroup(weight);
 
 	if (SCX_HAS_OP(enable))
-		SCX_CALL_OP_TASK(SCX_KF_REST, enable, p);
+		SCX_CALL_OP_TASK(SCX_KF_REST, enable, rq, p);
 	scx_set_task_state(p, SCX_TASK_ENABLED);
 
 	if (SCX_HAS_OP(set_weight))
-		SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight);
+		SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight);
 }
 
 static void scx_ops_disable_task(struct task_struct *p)
 {
-	lockdep_assert_rq_held(task_rq(p));
+	struct rq *rq = task_rq(p);
+
+	lockdep_assert_rq_held(rq);
 	WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED);
 
 	if (SCX_HAS_OP(disable))
-		SCX_CALL_OP_TASK(SCX_KF_REST, disable, p);
+		SCX_CALL_OP_TASK(SCX_KF_REST, disable, rq, p);
 	scx_set_task_state(p, SCX_TASK_READY);
 }
 
@@ -3726,7 +3762,7 @@ static void scx_ops_exit_task(struct task_struct *p)
 	}
 
 	if (SCX_HAS_OP(exit_task))
-		SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, p, &args);
+		SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, task_rq(p), p, &args);
 	scx_set_task_state(p, SCX_TASK_NONE);
 }
 
@@ -3835,7 +3871,7 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p,
 
 	p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight));
 	if (SCX_HAS_OP(set_weight))
-		SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight);
+		SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight);
 }
 
 static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio)
@@ -3851,8 +3887,8 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p)
 	 * different scheduler class. Keep the BPF scheduler up-to-date.
 	 */
 	if (SCX_HAS_OP(set_cpumask))
-		SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p,
-				 (struct cpumask *)p->cpus_ptr);
+		SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, rq,
+				 p, (struct cpumask *)p->cpus_ptr);
 }
 
 static void switched_from_scx(struct rq *rq, struct task_struct *p)
@@ -3899,35 +3935,6 @@ bool scx_can_stop_tick(struct rq *rq)
 
 DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
 static bool scx_cgroup_enabled;
-static bool cgroup_warned_missing_weight;
-static bool cgroup_warned_missing_idle;
-
-static void scx_cgroup_warn_missing_weight(struct task_group *tg)
-{
-	if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
-	    cgroup_warned_missing_weight)
-		return;
-
-	if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent)
-		return;
-
-	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n",
-		scx_ops.name);
-	cgroup_warned_missing_weight = true;
-}
-
-static void scx_cgroup_warn_missing_idle(struct task_group *tg)
-{
-	if (!scx_cgroup_enabled || cgroup_warned_missing_idle)
-		return;
-
-	if (!tg->idle)
-		return;
-
-	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n",
-		scx_ops.name);
-	cgroup_warned_missing_idle = true;
-}
 
 int scx_tg_online(struct task_group *tg)
 {
@@ -3937,14 +3944,12 @@ int scx_tg_online(struct task_group *tg)
 
 	percpu_down_read(&scx_cgroup_rwsem);
 
-	scx_cgroup_warn_missing_weight(tg);
-
 	if (scx_cgroup_enabled) {
 		if (SCX_HAS_OP(cgroup_init)) {
 			struct scx_cgroup_init_args args =
 				{ .weight = tg->scx_weight };
 
-			ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
+			ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL,
 					      tg->css.cgroup, &args);
 			if (ret)
 				ret = ops_sanitize_err("cgroup_init", ret);
@@ -3966,7 +3971,7 @@ void scx_tg_offline(struct task_group *tg)
 	percpu_down_read(&scx_cgroup_rwsem);
 
 	if (SCX_HAS_OP(cgroup_exit) && (tg->scx_flags & SCX_TG_INITED))
-		SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, tg->css.cgroup);
+		SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, tg->css.cgroup);
 	tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED);
 
 	percpu_up_read(&scx_cgroup_rwsem);
@@ -3999,7 +4004,7 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset)
 			continue;
 
 		if (SCX_HAS_OP(cgroup_prep_move)) {
-			ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move,
+			ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move, NULL,
 					      p, from, css->cgroup);
 			if (ret)
 				goto err;
@@ -4013,8 +4018,8 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset)
 err:
 	cgroup_taskset_for_each(p, css, tset) {
 		if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
-			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
-				    p->scx.cgrp_moving_from, css->cgroup);
+			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL,
+				    p, p->scx.cgrp_moving_from, css->cgroup);
 		p->scx.cgrp_moving_from = NULL;
 	}
 
@@ -4032,8 +4037,8 @@ void scx_cgroup_move_task(struct task_struct *p)
 	 * cgrp_moving_from set.
 	 */
 	if (SCX_HAS_OP(cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from))
-		SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, p,
-			p->scx.cgrp_moving_from, tg_cgrp(task_group(p)));
+		SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, NULL,
+				 p, p->scx.cgrp_moving_from, tg_cgrp(task_group(p)));
 	p->scx.cgrp_moving_from = NULL;
 }
 
@@ -4052,8 +4057,8 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset)
 
 	cgroup_taskset_for_each(p, css, tset) {
 		if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
-			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
-				    p->scx.cgrp_moving_from, css->cgroup);
+			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL,
+				    p, p->scx.cgrp_moving_from, css->cgroup);
 		p->scx.cgrp_moving_from = NULL;
 	}
 out_unlock:
@@ -4066,7 +4071,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 
 	if (scx_cgroup_enabled && tg->scx_weight != weight) {
 		if (SCX_HAS_OP(cgroup_set_weight))
-			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight,
+			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
 				    tg_cgrp(tg), weight);
 		tg->scx_weight = weight;
 	}
@@ -4076,9 +4081,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 
 void scx_group_set_idle(struct task_group *tg, bool idle)
 {
-	percpu_down_read(&scx_cgroup_rwsem);
-	scx_cgroup_warn_missing_idle(tg);
-	percpu_up_read(&scx_cgroup_rwsem);
+	/* TODO: Implement ops->cgroup_set_idle() */
 }
 
 static void scx_cgroup_lock(void)
@@ -4257,7 +4260,7 @@ static void scx_cgroup_exit(void)
 			continue;
 		rcu_read_unlock();
 
-		SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, css->cgroup);
+		SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, css->cgroup);
 
 		rcu_read_lock();
 		css_put(css);
@@ -4272,9 +4275,6 @@ static int scx_cgroup_init(void)
 
 	percpu_rwsem_assert_held(&scx_cgroup_rwsem);
 
-	cgroup_warned_missing_weight = false;
-	cgroup_warned_missing_idle = false;
-
 	/*
 	 * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
 	 * cgroups and init, all online cgroups are initialized.
@@ -4284,9 +4284,6 @@ static int scx_cgroup_init(void)
 		struct task_group *tg = css_tg(css);
 		struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
 
-		scx_cgroup_warn_missing_weight(tg);
-		scx_cgroup_warn_missing_idle(tg);
-
 		if ((tg->scx_flags &
 		     (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
 			continue;
@@ -4300,7 +4297,7 @@ static int scx_cgroup_init(void)
 			continue;
 		rcu_read_unlock();
 
-		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
+		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL,
 				      css->cgroup, &args);
 		if (ret) {
 			css_put(css);
@@ -4623,7 +4620,7 @@ unlock:
 
 static void free_exit_info(struct scx_exit_info *ei)
 {
-	kfree(ei->dump);
+	kvfree(ei->dump);
 	kfree(ei->msg);
 	kfree(ei->bt);
 	kfree(ei);
@@ -4639,7 +4636,7 @@ static struct scx_exit_info *alloc_exit_info(size_t exit_dump_len)
 
 	ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL);
 	ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL);
-	ei->dump = kzalloc(exit_dump_len, GFP_KERNEL);
+	ei->dump = kvzalloc(exit_dump_len, GFP_KERNEL);
 
 	if (!ei->bt || !ei->msg || !ei->dump) {
 		free_exit_info(ei);
@@ -4797,7 +4794,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
 	}
 
 	if (scx_ops.exit)
-		SCX_CALL_OP(SCX_KF_UNLOCKED, exit, ei);
+		SCX_CALL_OP(SCX_KF_UNLOCKED, exit, NULL, ei);
 
 	cancel_delayed_work_sync(&scx_watchdog_work);
 
@@ -5004,7 +5001,7 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx,
 
 	if (SCX_HAS_OP(dump_task)) {
 		ops_dump_init(s, "    ");
-		SCX_CALL_OP(SCX_KF_REST, dump_task, dctx, p);
+		SCX_CALL_OP(SCX_KF_REST, dump_task, NULL, dctx, p);
 		ops_dump_exit();
 	}
 
@@ -5051,7 +5048,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 
 	if (SCX_HAS_OP(dump)) {
 		ops_dump_init(&s, "");
-		SCX_CALL_OP(SCX_KF_UNLOCKED, dump, &dctx);
+		SCX_CALL_OP(SCX_KF_UNLOCKED, dump, NULL, &dctx);
 		ops_dump_exit();
 	}
 
@@ -5108,7 +5105,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 		used = seq_buf_used(&ns);
 		if (SCX_HAS_OP(dump_cpu)) {
 			ops_dump_init(&ns, "  ");
-			SCX_CALL_OP(SCX_KF_REST, dump_cpu, &dctx, cpu, idle);
+			SCX_CALL_OP(SCX_KF_REST, dump_cpu, NULL, &dctx, cpu, idle);
 			ops_dump_exit();
 		}
 
@@ -5252,6 +5249,9 @@ static int validate_ops(const struct sched_ext_ops *ops)
 		return -EINVAL;
 	}
 
+	if (ops->flags & SCX_OPS_HAS_CGROUP_WEIGHT)
+		pr_warn("SCX_OPS_HAS_CGROUP_WEIGHT is deprecated and a noop\n");
+
 	return 0;
 }
 
@@ -5364,7 +5364,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	scx_idle_enable(ops);
 
 	if (scx_ops.init) {
-		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init);
+		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init, NULL);
 		if (ret) {
 			ret = ops_sanitize_err("init", ret);
 			cpus_read_unlock();
@@ -6827,6 +6827,12 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id,
 	BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) !=
 		     __alignof__(struct bpf_iter_scx_dsq));
 
+	/*
+	 * next() and destroy() will be called regardless of the return value.
+	 * Always clear $kit->dsq.
+	 */
+	kit->dsq = NULL;
+
 	if (flags & ~__SCX_DSQ_ITER_USER_FLAGS)
 		return -EINVAL;
 
@@ -7113,13 +7119,32 @@ __bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf)
 	}
 
 	if (ops_cpu_valid(cpu, NULL)) {
-		struct rq *rq = cpu_rq(cpu);
+		struct rq *rq = cpu_rq(cpu), *locked_rq = scx_locked_rq();
+		struct rq_flags rf;
+
+		/*
+		 * When called with an rq lock held, restrict the operation
+		 * to the corresponding CPU to prevent ABBA deadlocks.
+		 */
+		if (locked_rq && rq != locked_rq) {
+			scx_ops_error("Invalid target CPU %d", cpu);
+			return;
+		}
+
+		/*
+		 * If no rq lock is held, allow to operate on any CPU by
+		 * acquiring the corresponding rq lock.
+		 */
+		if (!locked_rq) {
+			rq_lock_irqsave(rq, &rf);
+			update_rq_clock(rq);
+		}
 
 		rq->scx.cpuperf_target = perf;
+		cpufreq_update_util(rq, 0);
 
-		rcu_read_lock_sched_notrace();
-		cpufreq_update_util(cpu_rq(cpu), 0);
-		rcu_read_unlock_sched_notrace();
+		if (!locked_rq)
+			rq_unlock_irqrestore(rq, &rf);
 	}
 }
 
@@ -7350,12 +7375,6 @@ BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids)
 BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE)
 BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE)
 BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE)
-BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE)
-BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_ACQUIRE)
-BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE)
-BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle)
-BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU)
-BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_cpu_rq)
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index cb343ca889e0..e67a19a071c1 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -674,7 +674,7 @@ void __scx_update_idle(struct rq *rq, bool idle, bool do_notify)
 	 * managed by put_prev_task_idle()/set_next_task_idle().
 	 */
 	if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq))
-		SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle);
+		SCX_CALL_OP(SCX_KF_REST, update_idle, rq, cpu_of(rq), idle);
 
 	/*
 	 * Update the idle masks:
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e43993a4e580..0fb9bf995a47 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7081,9 +7081,6 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		h_nr_idle = task_has_idle_policy(p);
 		if (task_sleep || task_delayed || !se->sched_delayed)
 			h_nr_runnable = 1;
-	} else {
-		cfs_rq = group_cfs_rq(se);
-		slice = cfs_rq_min_slice(cfs_rq);
 	}
 
 	for_each_sched_entity(se) {
@@ -7093,6 +7090,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 			if (p && &p->se == se)
 				return -1;
 
+			slice = cfs_rq_min_slice(cfs_rq);
 			break;
 		}
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 517ee2590a29..30899a8cc52c 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -366,7 +366,7 @@ static const struct debug_obj_descr hrtimer_debug_descr;
 
 static void *hrtimer_debug_hint(void *addr)
 {
-	return ((struct hrtimer *) addr)->function;
+	return ACCESS_PRIVATE((struct hrtimer *)addr, function);
 }
 
 /*
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index a47bcf71defc..9a3859443c04 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -509,6 +509,7 @@ void tick_resume(void)
 
 #ifdef CONFIG_SUSPEND
 static DEFINE_RAW_SPINLOCK(tick_freeze_lock);
+static DEFINE_WAIT_OVERRIDE_MAP(tick_freeze_map, LD_WAIT_SLEEP);
 static unsigned int tick_freeze_depth;
 
 /**
@@ -528,9 +529,22 @@ void tick_freeze(void)
 	if (tick_freeze_depth == num_online_cpus()) {
 		trace_suspend_resume(TPS("timekeeping_freeze"),
 				     smp_processor_id(), true);
+		/*
+		 * All other CPUs have their interrupts disabled and are
+		 * suspended to idle. Other tasks have been frozen so there
+		 * is no scheduling happening. This means that there is no
+		 * concurrency in the system at this point. Therefore it is
+		 * okay to acquire a sleeping lock on PREEMPT_RT, such as a
+		 * spinlock, because the lock cannot be held by other CPUs
+		 * or threads and acquiring it cannot block.
+		 *
+		 * Inform lockdep about the situation.
+		 */
+		lock_map_acquire_try(&tick_freeze_map);
 		system_state = SYSTEM_SUSPEND;
 		sched_clock_suspend();
 		timekeeping_suspend();
+		lock_map_release(&tick_freeze_map);
 	} else {
 		tick_suspend_local();
 	}
@@ -552,8 +566,16 @@ void tick_unfreeze(void)
 	raw_spin_lock(&tick_freeze_lock);
 
 	if (tick_freeze_depth == num_online_cpus()) {
+		/*
+		 * Similar to tick_freeze(). On resumption the first CPU may
+		 * acquire uncontended sleeping locks while other CPUs block on
+		 * tick_freeze_lock.
+		 */
+		lock_map_acquire_try(&tick_freeze_map);
 		timekeeping_resume();
 		sched_clock_resume();
+		lock_map_release(&tick_freeze_map);
+
 		system_state = SYSTEM_RUNNING;
 		trace_suspend_resume(TPS("timekeeping_freeze"),
 				     smp_processor_id(), false);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 1e67d076f195..a009c91f7b05 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -164,10 +164,34 @@ static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
 	return ts;
 }
 
+static inline struct timespec64 tk_xtime_coarse(const struct timekeeper *tk)
+{
+	struct timespec64 ts;
+
+	ts.tv_sec = tk->xtime_sec;
+	ts.tv_nsec = tk->coarse_nsec;
+	return ts;
+}
+
+/*
+ * Update the nanoseconds part for the coarse time keepers. They can't rely
+ * on xtime_nsec because xtime_nsec could be adjusted by a small negative
+ * amount when the multiplication factor of the clock is adjusted, which
+ * could cause the coarse clocks to go slightly backwards. See
+ * timekeeping_apply_adjustment(). Thus we keep a separate copy for the coarse
+ * clockids which only is updated when the clock has been set or  we have
+ * accumulated time.
+ */
+static inline void tk_update_coarse_nsecs(struct timekeeper *tk)
+{
+	tk->coarse_nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+}
+
 static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
 {
 	tk->xtime_sec = ts->tv_sec;
 	tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift;
+	tk_update_coarse_nsecs(tk);
 }
 
 static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
@@ -175,6 +199,7 @@ static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
 	tk->xtime_sec += ts->tv_sec;
 	tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift;
 	tk_normalize_xtime(tk);
+	tk_update_coarse_nsecs(tk);
 }
 
 static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
@@ -708,6 +733,7 @@ static void timekeeping_forward_now(struct timekeeper *tk)
 		tk_normalize_xtime(tk);
 		delta -= incr;
 	}
+	tk_update_coarse_nsecs(tk);
 }
 
 /**
@@ -804,8 +830,8 @@ EXPORT_SYMBOL_GPL(ktime_get_with_offset);
 ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned int seq;
 	ktime_t base, *offset = offsets[offs];
+	unsigned int seq;
 	u64 nsecs;
 
 	WARN_ON(timekeeping_suspended);
@@ -813,7 +839,7 @@ ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 		base = ktime_add(tk->tkr_mono.base, *offset);
-		nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+		nsecs = tk->coarse_nsec;
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -2161,7 +2187,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
 	struct timekeeper *real_tk = &tk_core.timekeeper;
 	unsigned int clock_set = 0;
 	int shift = 0, maxshift;
-	u64 offset;
+	u64 offset, orig_offset;
 
 	guard(raw_spinlock_irqsave)(&tk_core.lock);
 
@@ -2172,7 +2198,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
 	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
 				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
 				   tk->tkr_mono.clock->max_raw_delta);
-
+	orig_offset = offset;
 	/* Check if there's really nothing to do */
 	if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
 		return false;
@@ -2205,6 +2231,14 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
 	 */
 	clock_set |= accumulate_nsecs_to_secs(tk);
 
+	/*
+	 * To avoid inconsistencies caused adjtimex TK_ADV_FREQ calls
+	 * making small negative adjustments to the base xtime_nsec
+	 * value, only update the coarse clocks if we accumulated time
+	 */
+	if (orig_offset != offset)
+		tk_update_coarse_nsecs(tk);
+
 	timekeeping_update_from_shadow(&tk_core, clock_set);
 
 	return !!clock_set;
@@ -2248,7 +2282,7 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		*ts = tk_xtime(tk);
+		*ts = tk_xtime_coarse(tk);
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 }
 EXPORT_SYMBOL(ktime_get_coarse_real_ts64);
@@ -2271,7 +2305,7 @@ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts)
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		*ts = tk_xtime(tk);
+		*ts = tk_xtime_coarse(tk);
 		offset = tk_core.timekeeper.offs_real;
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -2350,12 +2384,12 @@ void ktime_get_coarse_ts64(struct timespec64 *ts)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		now = tk_xtime(tk);
+		now = tk_xtime_coarse(tk);
 		mono = tk->wall_to_monotonic;
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
 	set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec,
-				now.tv_nsec + mono.tv_nsec);
+				  now.tv_nsec + mono.tv_nsec);
 }
 EXPORT_SYMBOL(ktime_get_coarse_ts64);
 
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 01c2ab1e8971..32ef27c71b57 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -98,12 +98,12 @@ void update_vsyscall(struct timekeeper *tk)
 	/* CLOCK_REALTIME_COARSE */
 	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
 	vdso_ts->sec	= tk->xtime_sec;
-	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+	vdso_ts->nsec	= tk->coarse_nsec;
 
 	/* CLOCK_MONOTONIC_COARSE */
 	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE];
 	vdso_ts->sec	= tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
-	nsec		= tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+	nsec		= tk->coarse_nsec;
 	nsec		= nsec + tk->wall_to_monotonic.tv_nsec;
 	vdso_ts->sec	+= __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);
 
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 95c6e3473a76..ba7ff14f5339 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -454,7 +454,8 @@ static void fprobe_remove_node_in_module(struct module *mod, struct hlist_head *
 	struct fprobe_hlist_node *node;
 	int ret = 0;
 
-	hlist_for_each_entry_rcu(node, head, hlist) {
+	hlist_for_each_entry_rcu(node, head, hlist,
+				 lockdep_is_held(&fprobe_mutex)) {
 		if (!within_module(node->addr, mod))
 			continue;
 		if (delete_fprobe_node(node))
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1a48aedb5255..6981830c3128 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1297,6 +1297,8 @@ void ftrace_free_filter(struct ftrace_ops *ops)
 		return;
 	free_ftrace_hash(ops->func_hash->filter_hash);
 	free_ftrace_hash(ops->func_hash->notrace_hash);
+	ops->func_hash->filter_hash = EMPTY_HASH;
+	ops->func_hash->notrace_hash = EMPTY_HASH;
 }
 EXPORT_SYMBOL_GPL(ftrace_free_filter);
 
@@ -3256,6 +3258,31 @@ static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash,
 }
 
 /*
+ * Remove functions from @hash that are in @notrace_hash
+ */
+static void remove_hash(struct ftrace_hash *hash, struct ftrace_hash *notrace_hash)
+{
+	struct ftrace_func_entry *entry;
+	struct hlist_node *tmp;
+	int size;
+	int i;
+
+	/* If the notrace hash is empty, there's nothing to do */
+	if (ftrace_hash_empty(notrace_hash))
+		return;
+
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry_safe(entry, tmp, &hash->buckets[i], hlist) {
+			if (!__ftrace_lookup_ip(notrace_hash, entry->ip))
+				continue;
+			remove_hash_entry(hash, entry);
+			kfree(entry);
+		}
+	}
+}
+
+/*
  * Add to @hash only those that are in both @new_hash1 and @new_hash2
  *
  * The notrace_hash updates uses just the intersect_hash() function
@@ -3295,67 +3322,6 @@ static int intersect_hash(struct ftrace_hash **hash, struct ftrace_hash *new_has
 	return 0;
 }
 
-/* Return a new hash that has a union of all @ops->filter_hash entries */
-static struct ftrace_hash *append_hashes(struct ftrace_ops *ops)
-{
-	struct ftrace_hash *new_hash = NULL;
-	struct ftrace_ops *subops;
-	int size_bits;
-	int ret;
-
-	if (ops->func_hash->filter_hash)
-		size_bits = ops->func_hash->filter_hash->size_bits;
-	else
-		size_bits = FTRACE_HASH_DEFAULT_BITS;
-
-	list_for_each_entry(subops, &ops->subop_list, list) {
-		ret = append_hash(&new_hash, subops->func_hash->filter_hash, size_bits);
-		if (ret < 0) {
-			free_ftrace_hash(new_hash);
-			return NULL;
-		}
-		/* Nothing more to do if new_hash is empty */
-		if (ftrace_hash_empty(new_hash))
-			break;
-	}
-	/* Can't return NULL as that means this failed */
-	return new_hash ? : EMPTY_HASH;
-}
-
-/* Make @ops trace evenything except what all its subops do not trace */
-static struct ftrace_hash *intersect_hashes(struct ftrace_ops *ops)
-{
-	struct ftrace_hash *new_hash = NULL;
-	struct ftrace_ops *subops;
-	int size_bits;
-	int ret;
-
-	list_for_each_entry(subops, &ops->subop_list, list) {
-		struct ftrace_hash *next_hash;
-
-		if (!new_hash) {
-			size_bits = subops->func_hash->notrace_hash->size_bits;
-			new_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->notrace_hash);
-			if (!new_hash)
-				return NULL;
-			continue;
-		}
-		size_bits = new_hash->size_bits;
-		next_hash = new_hash;
-		new_hash = alloc_ftrace_hash(size_bits);
-		ret = intersect_hash(&new_hash, next_hash, subops->func_hash->notrace_hash);
-		free_ftrace_hash(next_hash);
-		if (ret < 0) {
-			free_ftrace_hash(new_hash);
-			return NULL;
-		}
-		/* Nothing more to do if new_hash is empty */
-		if (ftrace_hash_empty(new_hash))
-			break;
-	}
-	return new_hash;
-}
-
 static bool ops_equal(struct ftrace_hash *A, struct ftrace_hash *B)
 {
 	struct ftrace_func_entry *entry;
@@ -3427,6 +3393,95 @@ static int ftrace_update_ops(struct ftrace_ops *ops, struct ftrace_hash *filter_
 	return 0;
 }
 
+static int add_first_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **notrace_hash,
+			  struct ftrace_ops_hash *func_hash)
+{
+	/* If the filter hash is not empty, simply remove the nohash from it */
+	if (!ftrace_hash_empty(func_hash->filter_hash)) {
+		*filter_hash = copy_hash(func_hash->filter_hash);
+		if (!*filter_hash)
+			return -ENOMEM;
+		remove_hash(*filter_hash, func_hash->notrace_hash);
+		*notrace_hash = EMPTY_HASH;
+
+	} else {
+		*notrace_hash = copy_hash(func_hash->notrace_hash);
+		if (!*notrace_hash)
+			return -ENOMEM;
+		*filter_hash = EMPTY_HASH;
+	}
+	return 0;
+}
+
+static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **notrace_hash,
+			 struct ftrace_ops_hash *ops_hash, struct ftrace_ops_hash *subops_hash)
+{
+	int size_bits;
+	int ret;
+
+	/* If the subops trace all functions so must the main ops */
+	if (ftrace_hash_empty(ops_hash->filter_hash) ||
+	    ftrace_hash_empty(subops_hash->filter_hash)) {
+		*filter_hash = EMPTY_HASH;
+	} else {
+		/*
+		 * The main ops filter hash is not empty, so its
+		 * notrace_hash had better be, as the notrace hash
+		 * is only used for empty main filter hashes.
+		 */
+		WARN_ON_ONCE(!ftrace_hash_empty(ops_hash->notrace_hash));
+
+		size_bits = max(ops_hash->filter_hash->size_bits,
+				subops_hash->filter_hash->size_bits);
+
+		/* Copy the subops hash */
+		*filter_hash = alloc_and_copy_ftrace_hash(size_bits, subops_hash->filter_hash);
+		if (!*filter_hash)
+			return -ENOMEM;
+		/* Remove any notrace functions from the copy */
+		remove_hash(*filter_hash, subops_hash->notrace_hash);
+
+		ret = append_hash(filter_hash, ops_hash->filter_hash,
+				  size_bits);
+		if (ret < 0) {
+			free_ftrace_hash(*filter_hash);
+			*filter_hash = EMPTY_HASH;
+			return ret;
+		}
+	}
+
+	/*
+	 * Only process notrace hashes if the main filter hash is empty
+	 * (tracing all functions), otherwise the filter hash will just
+	 * remove the notrace hash functions, and the notrace hash is
+	 * not needed.
+	 */
+	if (ftrace_hash_empty(*filter_hash)) {
+		/*
+		 * Intersect the notrace functions. That is, if two
+		 * subops are not tracing a set of functions, the
+		 * main ops will only not trace the functions that are
+		 * in both subops, but has to trace the functions that
+		 * are only notrace in one of the subops, for the other
+		 * subops to be able to trace them.
+		 */
+		size_bits = max(ops_hash->notrace_hash->size_bits,
+				subops_hash->notrace_hash->size_bits);
+		*notrace_hash = alloc_ftrace_hash(size_bits);
+		if (!*notrace_hash)
+			return -ENOMEM;
+
+		ret = intersect_hash(notrace_hash, ops_hash->notrace_hash,
+				     subops_hash->notrace_hash);
+		if (ret < 0) {
+			free_ftrace_hash(*notrace_hash);
+			*notrace_hash = EMPTY_HASH;
+			return ret;
+		}
+	}
+	return 0;
+}
+
 /**
  * ftrace_startup_subops - enable tracing for subops of an ops
  * @ops: Manager ops (used to pick all the functions of its subops)
@@ -3439,11 +3494,10 @@ static int ftrace_update_ops(struct ftrace_ops *ops, struct ftrace_hash *filter_
  */
 int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
 {
-	struct ftrace_hash *filter_hash;
-	struct ftrace_hash *notrace_hash;
+	struct ftrace_hash *filter_hash = EMPTY_HASH;
+	struct ftrace_hash *notrace_hash = EMPTY_HASH;
 	struct ftrace_hash *save_filter_hash;
 	struct ftrace_hash *save_notrace_hash;
-	int size_bits;
 	int ret;
 
 	if (unlikely(ftrace_disabled))
@@ -3467,14 +3521,14 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
 
 	/* For the first subops to ops just enable it normally */
 	if (list_empty(&ops->subop_list)) {
-		/* Just use the subops hashes */
-		filter_hash = copy_hash(subops->func_hash->filter_hash);
-		notrace_hash = copy_hash(subops->func_hash->notrace_hash);
-		if (!filter_hash || !notrace_hash) {
-			free_ftrace_hash(filter_hash);
-			free_ftrace_hash(notrace_hash);
-			return -ENOMEM;
-		}
+
+		/* The ops was empty, should have empty hashes */
+		WARN_ON_ONCE(!ftrace_hash_empty(ops->func_hash->filter_hash));
+		WARN_ON_ONCE(!ftrace_hash_empty(ops->func_hash->notrace_hash));
+
+		ret = add_first_hash(&filter_hash, &notrace_hash, subops->func_hash);
+		if (ret < 0)
+			return ret;
 
 		save_filter_hash = ops->func_hash->filter_hash;
 		save_notrace_hash = ops->func_hash->notrace_hash;
@@ -3500,48 +3554,16 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
 
 	/*
 	 * Here there's already something attached. Here are the rules:
-	 *   o If either filter_hash is empty then the final stays empty
-	 *      o Otherwise, the final is a superset of both hashes
-	 *   o If either notrace_hash is empty then the final stays empty
-	 *      o Otherwise, the final is an intersection between the hashes
+	 *   If the new subops and main ops filter hashes are not empty:
+	 *     o Make a copy of the subops filter hash
+	 *     o Remove all functions in the nohash from it.
+	 *     o Add in the main hash filter functions
+	 *     o Remove any of these functions from the main notrace hash
 	 */
-	if (ftrace_hash_empty(ops->func_hash->filter_hash) ||
-	    ftrace_hash_empty(subops->func_hash->filter_hash)) {
-		filter_hash = EMPTY_HASH;
-	} else {
-		size_bits = max(ops->func_hash->filter_hash->size_bits,
-				subops->func_hash->filter_hash->size_bits);
-		filter_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->filter_hash);
-		if (!filter_hash)
-			return -ENOMEM;
-		ret = append_hash(&filter_hash, subops->func_hash->filter_hash,
-				  size_bits);
-		if (ret < 0) {
-			free_ftrace_hash(filter_hash);
-			return ret;
-		}
-	}
 
-	if (ftrace_hash_empty(ops->func_hash->notrace_hash) ||
-	    ftrace_hash_empty(subops->func_hash->notrace_hash)) {
-		notrace_hash = EMPTY_HASH;
-	} else {
-		size_bits = max(ops->func_hash->filter_hash->size_bits,
-				subops->func_hash->filter_hash->size_bits);
-		notrace_hash = alloc_ftrace_hash(size_bits);
-		if (!notrace_hash) {
-			free_ftrace_hash(filter_hash);
-			return -ENOMEM;
-		}
-
-		ret = intersect_hash(&notrace_hash, ops->func_hash->filter_hash,
-				     subops->func_hash->filter_hash);
-		if (ret < 0) {
-			free_ftrace_hash(filter_hash);
-			free_ftrace_hash(notrace_hash);
-			return ret;
-		}
-	}
+	ret = add_next_hash(&filter_hash, &notrace_hash, ops->func_hash, subops->func_hash);
+	if (ret < 0)
+		return ret;
 
 	list_add(&subops->list, &ops->subop_list);
 
@@ -3557,6 +3579,45 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
 	return ret;
 }
 
+static int rebuild_hashes(struct ftrace_hash **filter_hash, struct ftrace_hash **notrace_hash,
+			  struct ftrace_ops *ops)
+{
+	struct ftrace_ops_hash temp_hash;
+	struct ftrace_ops *subops;
+	bool first = true;
+	int ret;
+
+	temp_hash.filter_hash = EMPTY_HASH;
+	temp_hash.notrace_hash = EMPTY_HASH;
+
+	list_for_each_entry(subops, &ops->subop_list, list) {
+		*filter_hash = EMPTY_HASH;
+		*notrace_hash = EMPTY_HASH;
+
+		if (first) {
+			ret = add_first_hash(filter_hash, notrace_hash, subops->func_hash);
+			if (ret < 0)
+				return ret;
+			first = false;
+		} else {
+			ret = add_next_hash(filter_hash, notrace_hash,
+					    &temp_hash, subops->func_hash);
+			if (ret < 0) {
+				free_ftrace_hash(temp_hash.filter_hash);
+				free_ftrace_hash(temp_hash.notrace_hash);
+				return ret;
+			}
+		}
+
+		free_ftrace_hash(temp_hash.filter_hash);
+		free_ftrace_hash(temp_hash.notrace_hash);
+
+		temp_hash.filter_hash = *filter_hash;
+		temp_hash.notrace_hash = *notrace_hash;
+	}
+	return 0;
+}
+
 /**
  * ftrace_shutdown_subops - Remove a subops from a manager ops
  * @ops: A manager ops to remove @subops from
@@ -3571,8 +3632,8 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
  */
 int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
 {
-	struct ftrace_hash *filter_hash;
-	struct ftrace_hash *notrace_hash;
+	struct ftrace_hash *filter_hash = EMPTY_HASH;
+	struct ftrace_hash *notrace_hash = EMPTY_HASH;
 	int ret;
 
 	if (unlikely(ftrace_disabled))
@@ -3605,14 +3666,9 @@ int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, in
 	}
 
 	/* Rebuild the hashes without subops */
-	filter_hash = append_hashes(ops);
-	notrace_hash = intersect_hashes(ops);
-	if (!filter_hash || !notrace_hash) {
-		free_ftrace_hash(filter_hash);
-		free_ftrace_hash(notrace_hash);
-		list_add(&subops->list, &ops->subop_list);
-		return -ENOMEM;
-	}
+	ret = rebuild_hashes(&filter_hash, &notrace_hash, ops);
+	if (ret < 0)
+		return ret;
 
 	ret = ftrace_update_ops(ops, filter_hash, notrace_hash);
 	if (ret < 0) {
@@ -3628,11 +3684,11 @@ int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, in
 
 static int ftrace_hash_move_and_update_subops(struct ftrace_ops *subops,
 					      struct ftrace_hash **orig_subhash,
-					      struct ftrace_hash *hash,
-					      int enable)
+					      struct ftrace_hash *hash)
 {
 	struct ftrace_ops *ops = subops->managed;
-	struct ftrace_hash **orig_hash;
+	struct ftrace_hash *notrace_hash;
+	struct ftrace_hash *filter_hash;
 	struct ftrace_hash *save_hash;
 	struct ftrace_hash *new_hash;
 	int ret;
@@ -3649,24 +3705,18 @@ static int ftrace_hash_move_and_update_subops(struct ftrace_ops *subops,
 		return -ENOMEM;
 	}
 
-	/* Create a new_hash to hold the ops new functions */
-	if (enable) {
-		orig_hash = &ops->func_hash->filter_hash;
-		new_hash = append_hashes(ops);
-	} else {
-		orig_hash = &ops->func_hash->notrace_hash;
-		new_hash = intersect_hashes(ops);
+	ret = rebuild_hashes(&filter_hash, &notrace_hash, ops);
+	if (!ret) {
+		ret = ftrace_update_ops(ops, filter_hash, notrace_hash);
+		free_ftrace_hash(filter_hash);
+		free_ftrace_hash(notrace_hash);
 	}
 
-	/* Move the hash over to the new hash */
-	ret = __ftrace_hash_move_and_update_ops(ops, orig_hash, new_hash, enable);
-
-	free_ftrace_hash(new_hash);
-
 	if (ret) {
 		/* Put back the original hash */
-		free_ftrace_hash_rcu(*orig_subhash);
+		new_hash = *orig_subhash;
 		*orig_subhash = save_hash;
+		free_ftrace_hash_rcu(new_hash);
 	} else {
 		free_ftrace_hash_rcu(save_hash);
 	}
@@ -4890,7 +4940,7 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops,
 					   int enable)
 {
 	if (ops->flags & FTRACE_OPS_FL_SUBOP)
-		return ftrace_hash_move_and_update_subops(ops, orig_hash, hash, enable);
+		return ftrace_hash_move_and_update_subops(ops, orig_hash, hash);
 
 	/*
 	 * If this ops is not enabled, it could be sharing its filters
@@ -4909,7 +4959,7 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops,
 			list_for_each_entry(subops, &op->subop_list, list) {
 				if ((subops->flags & FTRACE_OPS_FL_ENABLED) &&
 				     subops->func_hash == ops->func_hash) {
-					return ftrace_hash_move_and_update_subops(subops, orig_hash, hash, enable);
+					return ftrace_hash_move_and_update_subops(subops, orig_hash, hash);
 				}
 			}
 		} while_for_each_ftrace_op(op);
@@ -5914,9 +5964,10 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 
 	/* Make a copy hash to place the new and the old entries in */
 	size = hash->count + direct_functions->count;
-	if (size > 32)
-		size = 32;
-	new_hash = alloc_ftrace_hash(fls(size));
+	size = fls(size);
+	if (size > FTRACE_HASH_MAX_BITS)
+		size = FTRACE_HASH_MAX_BITS;
+	new_hash = alloc_ftrace_hash(size);
 	if (!new_hash)
 		goto out_unlock;
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c0f877d39a24..3f9bf562beea 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1887,10 +1887,12 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 
 	head_page = cpu_buffer->head_page;
 
-	/* If both the head and commit are on the reader_page then we are done. */
-	if (head_page == cpu_buffer->reader_page &&
-	    head_page == cpu_buffer->commit_page)
+	/* If the commit_buffer is the reader page, update the commit page */
+	if (meta->commit_buffer == (unsigned long)cpu_buffer->reader_page->page) {
+		cpu_buffer->commit_page = cpu_buffer->reader_page;
+		/* Nothing more to do, the only page is the reader page */
 		goto done;
+	}
 
 	/* Iterate until finding the commit page */
 	for (i = 0; i < meta->nr_subbufs + 1; i++, rb_inc_page(&head_page)) {
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index 968c5c3b0246..e4077500a91d 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -225,7 +225,12 @@ bool rv_is_nested_monitor(struct rv_monitor_def *mdef)
  */
 bool rv_is_container_monitor(struct rv_monitor_def *mdef)
 {
-	struct rv_monitor_def *next = list_next_entry(mdef, list);
+	struct rv_monitor_def *next;
+
+	if (list_is_last(&mdef->list, &rv_monitors_list))
+		return false;
+
+	next = list_next_entry(mdef, list);
 
 	return next->parent == mdef->monitor || !mdef->monitor->enable;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index b581e388a9d9..5b8db27fb6ef 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6043,8 +6043,10 @@ unsigned long trace_adjust_address(struct trace_array *tr, unsigned long addr)
 	tscratch = tr->scratch;
 	/* if there is no tscrach, module_delta must be NULL. */
 	module_delta = READ_ONCE(tr->module_delta);
-	if (!module_delta || tscratch->entries[0].mod_addr > addr)
+	if (!module_delta || !tscratch->nr_entries ||
+	    tscratch->entries[0].mod_addr > addr) {
 		return addr + tr->text_delta;
+	}
 
 	/* Note that entries must be sorted. */
 	nr_entries = tscratch->nr_entries;
@@ -6821,13 +6823,14 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		/* Copy the data into the page, so we can start over. */
 		ret = trace_seq_to_buffer(&iter->seq,
 					  page_address(spd.pages[i]),
-					  trace_seq_used(&iter->seq));
+					  min((size_t)trace_seq_used(&iter->seq),
+						  PAGE_SIZE));
 		if (ret < 0) {
 			__free_page(spd.pages[i]);
 			break;
 		}
 		spd.partial[i].offset = 0;
-		spd.partial[i].len = trace_seq_used(&iter->seq);
+		spd.partial[i].len = ret;
 
 		trace_seq_init(&iter->seq);
 	}
@@ -9806,6 +9809,7 @@ static int instance_mkdir(const char *name)
 	return ret;
 }
 
+#ifdef CONFIG_MMU
 static u64 map_pages(unsigned long start, unsigned long size)
 {
 	unsigned long vmap_start, vmap_end;
@@ -9828,6 +9832,12 @@ static u64 map_pages(unsigned long start, unsigned long size)
 
 	return (u64)vmap_start;
 }
+#else
+static inline u64 map_pages(unsigned long start, unsigned long size)
+{
+	return 0;
+}
+#endif
 
 /**
  * trace_array_get_by_name - Create/Lookup a trace array, given its name.
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index a322e4f249a5..5d64a18cacac 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -16,7 +16,7 @@
 #include "trace_output.h"	/* for trace_event_sem */
 #include "trace_dynevent.h"
 
-static DEFINE_MUTEX(dyn_event_ops_mutex);
+DEFINE_MUTEX(dyn_event_ops_mutex);
 static LIST_HEAD(dyn_event_ops_list);
 
 bool trace_event_dyn_try_get_ref(struct trace_event_call *dyn_call)
@@ -116,6 +116,20 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type
 	return ret;
 }
 
+/*
+ * Locked version of event creation. The event creation must be protected by
+ * dyn_event_ops_mutex because of protecting trace_probe_log.
+ */
+int dyn_event_create(const char *raw_command, struct dyn_event_operations *type)
+{
+	int ret;
+
+	mutex_lock(&dyn_event_ops_mutex);
+	ret = type->create(raw_command);
+	mutex_unlock(&dyn_event_ops_mutex);
+	return ret;
+}
+
 static int create_dyn_event(const char *raw_command)
 {
 	struct dyn_event_operations *ops;
diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h
index 936477a111d3..beee3f8d7544 100644
--- a/kernel/trace/trace_dynevent.h
+++ b/kernel/trace/trace_dynevent.h
@@ -100,6 +100,7 @@ void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos);
 void dyn_event_seq_stop(struct seq_file *m, void *v);
 int dyn_events_release_all(struct dyn_event_operations *type);
 int dyn_event_release(const char *raw_command, struct dyn_event_operations *type);
+int dyn_event_create(const char *raw_command, struct dyn_event_operations *type);
 
 /*
  * for_each_dyn_event	-	iterate over the dyn_event list
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index ee40d4e6ad1c..4ef4df6623a8 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -80,11 +80,11 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ent,	graph_ent	)
 		__field_packed(	unsigned long,	graph_ent,	func		)
-		__field_packed(	unsigned long,	graph_ent,	depth		)
+		__field_packed(	unsigned int,	graph_ent,	depth		)
 		__dynamic_array(unsigned long,	args				)
 	),
 
-	F_printk("--> %ps (%lu)", (void *)__entry->func, __entry->depth)
+	F_printk("--> %ps (%u)", (void *)__entry->func, __entry->depth)
 );
 
 #ifdef CONFIG_FUNCTION_GRAPH_RETADDR
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index c08355c3ef32..916555f0de81 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -969,10 +969,13 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 			goto error;
 		}
 	}
+	trace_probe_log_clear();
 	return ret;
+
 parse_error:
 	ret = -EINVAL;
 error:
+	trace_probe_log_clear();
 	trace_event_probe_cleanup(ep);
 	return ret;
 }
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 0993dfc1c5c1..2048560264bb 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -808,7 +808,7 @@ static __always_inline char *test_string(char *str)
 	kstr = ubuf->buffer;
 
 	/* For safety, do not trust the string pointer */
-	if (!strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE))
+	if (strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE) < 0)
 		return NULL;
 	return kstr;
 }
@@ -827,7 +827,7 @@ static __always_inline char *test_ustring(char *str)
 
 	/* user space address? */
 	ustr = (char __user *)str;
-	if (!strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE))
+	if (strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE) < 0)
 		return NULL;
 
 	return kstr;
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 969f48742d72..33cfbd4ed76d 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -370,7 +370,6 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
 				union trace_synth_field *data = &entry->fields[n_u64];
 
 				trace_seq_printf(s, print_fmt, se->fields[i]->name,
-						 STR_VAR_LEN_MAX,
 						 (char *)entry + data->as_dynamic.offset,
 						 i == se->n_fields - 1 ? "" : " ");
 				n_u64++;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index b66b6d235d91..6e87ae2a1a66 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1560,7 +1560,7 @@ stacktrace_trigger(struct event_trigger_data *data,
 	struct trace_event_file *file = data->private_data;
 
 	if (file)
-		__trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP);
+		__trace_stack(file->tr, tracing_gen_ctx_dec(), STACK_SKIP);
 	else
 		trace_dump_stack(STACK_SKIP);
 }
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 98ccf3f00c51..4e37a0f6aaa3 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -633,11 +633,7 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip,
 
 static __always_inline void trace_stack(struct trace_array *tr)
 {
-	unsigned int trace_ctx;
-
-	trace_ctx = tracing_gen_ctx();
-
-	__trace_stack(tr, trace_ctx, FTRACE_STACK_SKIP);
+	__trace_stack(tr, tracing_gen_ctx_dec(), FTRACE_STACK_SKIP);
 }
 
 static void
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 2f077d4158e5..0c357a89c58e 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -880,8 +880,6 @@ static void print_graph_retval(struct trace_seq *s, struct ftrace_graph_ent_entr
 
 		if (print_retval || print_retaddr)
 			trace_seq_puts(s, " /*");
-		else
-			trace_seq_putc(s, '\n');
 	} else {
 		print_retaddr = false;
 		trace_seq_printf(s, "} /* %ps", func);
@@ -899,7 +897,7 @@ static void print_graph_retval(struct trace_seq *s, struct ftrace_graph_ent_entr
 	}
 
 	if (!entry || print_retval || print_retaddr)
-		trace_seq_puts(s, " */\n");
+		trace_seq_puts(s, " */");
 }
 
 #else
@@ -975,7 +973,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 		} else
 			trace_seq_puts(s, "();");
 	}
-	trace_seq_printf(s, "\n");
+	trace_seq_putc(s, '\n');
 
 	print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
 			cpu, iter->ent->pid, flags);
@@ -1313,10 +1311,11 @@ print_graph_return(struct ftrace_graph_ret_entry *retentry, struct trace_seq *s,
 		 * that if the funcgraph-tail option is enabled.
 		 */
 		if (func_match && !(flags & TRACE_GRAPH_PRINT_TAIL))
-			trace_seq_puts(s, "}\n");
+			trace_seq_puts(s, "}");
 		else
-			trace_seq_printf(s, "} /* %ps */\n", (void *)func);
+			trace_seq_printf(s, "} /* %ps */", (void *)func);
 	}
+	trace_seq_putc(s, '\n');
 
 	/* Overrun */
 	if (flags & TRACE_GRAPH_PRINT_OVERRUN)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 2703b96d8990..3e5c47b6d7b2 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1089,7 +1089,7 @@ static int create_or_delete_trace_kprobe(const char *raw_command)
 	if (raw_command[0] == '-')
 		return dyn_event_release(raw_command, &trace_kprobe_ops);
 
-	ret = trace_kprobe_create(raw_command);
+	ret = dyn_event_create(raw_command, &trace_kprobe_ops);
 	return ret == -ECANCELED ? -EINVAL : ret;
 }
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index fee40ffbd490..b9ab06c99543 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1042,11 +1042,12 @@ enum print_line_t print_event_fields(struct trace_iterator *iter,
 	struct trace_event_call *call;
 	struct list_head *head;
 
+	lockdep_assert_held_read(&trace_event_sem);
+
 	/* ftrace defined events have separate call structures */
 	if (event->type <= __TRACE_LAST_TYPE) {
 		bool found = false;
 
-		down_read(&trace_event_sem);
 		list_for_each_entry(call, &ftrace_events, list) {
 			if (call->event.type == event->type) {
 				found = true;
@@ -1056,7 +1057,6 @@ enum print_line_t print_event_fields(struct trace_iterator *iter,
 			if (call->event.type > __TRACE_LAST_TYPE)
 				break;
 		}
-		up_read(&trace_event_sem);
 		if (!found) {
 			trace_seq_printf(&iter->seq, "UNKNOWN TYPE %d\n", event->type);
 			goto out;
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 2eeecb6c95ee..424751cdf31f 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -154,9 +154,12 @@ fail:
 }
 
 static struct trace_probe_log trace_probe_log;
+extern struct mutex dyn_event_ops_mutex;
 
 void trace_probe_log_init(const char *subsystem, int argc, const char **argv)
 {
+	lockdep_assert_held(&dyn_event_ops_mutex);
+
 	trace_probe_log.subsystem = subsystem;
 	trace_probe_log.argc = argc;
 	trace_probe_log.argv = argv;
@@ -165,11 +168,15 @@ void trace_probe_log_init(const char *subsystem, int argc, const char **argv)
 
 void trace_probe_log_clear(void)
 {
+	lockdep_assert_held(&dyn_event_ops_mutex);
+
 	memset(&trace_probe_log, 0, sizeof(trace_probe_log));
 }
 
 void trace_probe_log_set_index(int index)
 {
+	lockdep_assert_held(&dyn_event_ops_mutex);
+
 	trace_probe_log.index = index;
 }
 
@@ -178,6 +185,8 @@ void __trace_probe_log_err(int offset, int err_type)
 	char *command, *p;
 	int i, len = 0, pos = 0;
 
+	lockdep_assert_held(&dyn_event_ops_mutex);
+
 	if (!trace_probe_log.argv)
 		return;
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 3386439ec9f6..35cf76c75dd7 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -741,7 +741,7 @@ static int create_or_delete_trace_uprobe(const char *raw_command)
 	if (raw_command[0] == '-')
 		return dyn_event_release(raw_command, &trace_uprobe_ops);
 
-	ret = trace_uprobe_create(raw_command);
+	ret = dyn_event_create(raw_command, &trace_uprobe_ops);
 	return ret == -ECANCELED ? -EINVAL : ret;
 }
 
diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index 2ef2e1b80091..2f844c279a3e 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(vhost_task_stop);
  * @arg: data to be passed to fn and handled_kill
  * @name: the thread's name
  *
- * This returns a specialized task for use by the vhost layer or NULL on
+ * This returns a specialized task for use by the vhost layer or ERR_PTR() on
  * failure. The returned task is inactive, and the caller must fire it up
  * through vhost_task_start().
  */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 9fe4d8dfe578..f9051ab610d5 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -3290,7 +3290,7 @@ config GCD_KUNIT_TEST
 config PRIME_NUMBERS_KUNIT_TEST
 	tristate "Prime number generator test" if !KUNIT_ALL_TESTS
 	depends on KUNIT
-	select PRIME_NUMBERS
+	depends on PRIME_NUMBERS
 	default KUNIT_ALL_TESTS
 	help
 	  This option enables the KUnit test suite for the {is,next}_prime_number
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index 4216b3a4ff21..f6ea0c5b5da3 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -118,7 +118,6 @@ config UBSAN_UNREACHABLE
 
 config UBSAN_INTEGER_WRAP
 	bool "Perform checking for integer arithmetic wrap-around"
-	default UBSAN
 	depends on !COMPILE_TEST
 	depends on $(cc-option,-fsanitize-undefined-ignore-overflow-pattern=all)
 	depends on $(cc-option,-fsanitize=signed-integer-overflow)
diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
index 1d893e313614..25ecc1334b67 100644
--- a/lib/alloc_tag.c
+++ b/lib/alloc_tag.c
@@ -422,11 +422,20 @@ static int vm_module_tags_populate(void)
 		unsigned long old_shadow_end = ALIGN(phys_end, MODULE_ALIGN);
 		unsigned long new_shadow_end = ALIGN(new_end, MODULE_ALIGN);
 		unsigned long more_pages;
-		unsigned long nr;
+		unsigned long nr = 0;
 
 		more_pages = ALIGN(new_end - phys_end, PAGE_SIZE) >> PAGE_SHIFT;
-		nr = alloc_pages_bulk_node(GFP_KERNEL | __GFP_NOWARN,
-					   NUMA_NO_NODE, more_pages, next_page);
+		while (nr < more_pages) {
+			unsigned long allocated;
+
+			allocated = alloc_pages_bulk_node(GFP_KERNEL | __GFP_NOWARN,
+				NUMA_NO_NODE, more_pages - nr, next_page + nr);
+
+			if (!allocated)
+				break;
+			nr += allocated;
+		}
+
 		if (nr < more_pages ||
 		    vmap_pages_range(phys_end, phys_end + (nr << PAGE_SHIFT), PAGE_KERNEL,
 				     next_page, PAGE_SHIFT) < 0) {
diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c
index 13da529e2e72..5738ae286b41 100644
--- a/lib/asn1_decoder.c
+++ b/lib/asn1_decoder.c
@@ -518,4 +518,5 @@ error:
 }
 EXPORT_SYMBOL_GPL(asn1_ber_decoder);
 
+MODULE_DESCRIPTION("Decoder for ASN.1 BER/DER/CER encoded bytestream");
 MODULE_LICENSE("GPL");
diff --git a/lib/crc32.c b/lib/crc32.c
index fddd424ff224..ade48bbb0083 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -119,12 +119,6 @@ u32 crc32_le_shift(u32 crc, size_t len)
 }
 EXPORT_SYMBOL(crc32_le_shift);
 
-u32 crc32c_shift(u32 crc, size_t len)
-{
-	return crc32_generic_shift(crc, len, CRC32C_POLY_LE);
-}
-EXPORT_SYMBOL(crc32c_shift);
-
 u32 crc32_be_base(u32 crc, const u8 *p, size_t len)
 {
 	while (len--)
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 8c7fdb7d8c8f..bc9391e55d57 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1191,7 +1191,7 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
 			return -ENOMEM;
 		p = *pages;
 		for (int k = 0; k < n; k++) {
-			struct folio *folio = page_folio(page);
+			struct folio *folio = page_folio(page + k);
 			p[k] = page + k;
 			if (!folio_test_slab(folio))
 				folio_get(folio);
diff --git a/lib/pldmfw/pldmfw.c b/lib/pldmfw/pldmfw.c
index 6264e2013f25..b45ceb725780 100644
--- a/lib/pldmfw/pldmfw.c
+++ b/lib/pldmfw/pldmfw.c
@@ -728,6 +728,9 @@ pldm_send_package_data(struct pldmfw_priv *data)
 	struct pldmfw_record *record = data->matching_record;
 	const struct pldmfw_ops *ops = data->context->ops;
 
+	if (!ops->send_package_data)
+		return 0;
+
 	return ops->send_package_data(data->context, record->package_data,
 				      record->package_data_len);
 }
@@ -755,6 +758,9 @@ pldm_send_component_tables(struct pldmfw_priv *data)
 		if (!test_bit(index, bitmap))
 			continue;
 
+		if (!data->context->ops->send_component_table)
+			continue;
+
 		/* determine whether this is the start, middle, end, or both
 		 * the start and end of the component tables
 		 */
diff --git a/lib/string.c b/lib/string.c
index eb4486ed40d2..b632c71df1a5 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -119,6 +119,7 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count)
 	if (count == 0 || WARN_ON_ONCE(count > INT_MAX))
 		return -E2BIG;
 
+#ifndef CONFIG_DCACHE_WORD_ACCESS
 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 	/*
 	 * If src is unaligned, don't cross a page boundary,
@@ -134,11 +135,13 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count)
 	if (((long) dest | (long) src) & (sizeof(long) - 1))
 		max = 0;
 #endif
+#endif
 
 	/*
-	 * read_word_at_a_time() below may read uninitialized bytes after the
-	 * trailing zero and use them in comparisons. Disable this optimization
-	 * under KMSAN to prevent false positive reports.
+	 * load_unaligned_zeropad() or read_word_at_a_time() below may read
+	 * uninitialized bytes after the trailing zero and use them in
+	 * comparisons. Disable this optimization under KMSAN to prevent
+	 * false positive reports.
 	 */
 	if (IS_ENABLED(CONFIG_KMSAN))
 		max = 0;
@@ -146,7 +149,11 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count)
 	while (max >= sizeof(unsigned long)) {
 		unsigned long c, data;
 
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+		c = load_unaligned_zeropad(src+res);
+#else
 		c = read_word_at_a_time(src+res);
+#endif
 		if (has_zero(c, &data, &constants)) {
 			data = prep_zero_mask(c, data, &constants);
 			data = create_zero_mask(data);
diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c
index 8772e5edaa4f..a4b6f52b9c57 100644
--- a/lib/test_ubsan.c
+++ b/lib/test_ubsan.c
@@ -77,18 +77,22 @@ static void test_ubsan_shift_out_of_bounds(void)
 
 static void test_ubsan_out_of_bounds(void)
 {
-	volatile int i = 4, j = 5, k = -1;
-	volatile char above[4] = { }; /* Protect surrounding memory. */
-	volatile int arr[4];
-	volatile char below[4] = { }; /* Protect surrounding memory. */
+	int i = 4, j = 4, k = -1;
+	volatile struct {
+		char above[4]; /* Protect surrounding memory. */
+		int arr[4];
+		char below[4]; /* Protect surrounding memory. */
+	} data;
 
-	above[0] = below[0];
+	OPTIMIZER_HIDE_VAR(i);
+	OPTIMIZER_HIDE_VAR(j);
+	OPTIMIZER_HIDE_VAR(k);
 
 	UBSAN_TEST(CONFIG_UBSAN_BOUNDS, "above");
-	arr[j] = i;
+	data.arr[j] = i;
 
 	UBSAN_TEST(CONFIG_UBSAN_BOUNDS, "below");
-	arr[k] = i;
+	data.arr[k] = i;
 }
 
 enum ubsan_test_enum {
diff --git a/lib/tests/crc_kunit.c b/lib/tests/crc_kunit.c
index 585c48b65cef..064c2d581557 100644
--- a/lib/tests/crc_kunit.c
+++ b/lib/tests/crc_kunit.c
@@ -391,17 +391,11 @@ static u64 crc32c_wrapper(u64 crc, const u8 *p, size_t len)
 	return crc32c(crc, p, len);
 }
 
-static u64 crc32c_combine_wrapper(u64 crc1, u64 crc2, size_t len2)
-{
-	return crc32c_combine(crc1, crc2, len2);
-}
-
 static const struct crc_variant crc_variant_crc32c = {
 	.bits = 32,
 	.le = true,
 	.poly = 0x82f63b78,
 	.func = crc32c_wrapper,
-	.combine_func = crc32c_combine_wrapper,
 };
 
 static void crc32c_test(struct kunit *test)
diff --git a/lib/tests/slub_kunit.c b/lib/tests/slub_kunit.c
index d47c472b0520..848b682a2d70 100644
--- a/lib/tests/slub_kunit.c
+++ b/lib/tests/slub_kunit.c
@@ -325,4 +325,5 @@ static struct kunit_suite test_suite = {
 };
 kunit_test_suite(test_suite);
 
+MODULE_DESCRIPTION("Kunit tests for slub allocator");
 MODULE_LICENSE("GPL");
diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
index 9308bcfb2ad5..dfb4f2358cab 100644
--- a/lib/ucs2_string.c
+++ b/lib/ucs2_string.c
@@ -165,4 +165,5 @@ ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
 }
 EXPORT_SYMBOL(ucs2_as_utf8);
 
+MODULE_DESCRIPTION("UCS2 string handling");
 MODULE_LICENSE("GPL v2");
diff --git a/lib/zlib_inflate/inflate_syms.c b/lib/zlib_inflate/inflate_syms.c
index 9720114c0672..b8996d90e8bc 100644
--- a/lib/zlib_inflate/inflate_syms.c
+++ b/lib/zlib_inflate/inflate_syms.c
@@ -18,4 +18,5 @@ EXPORT_SYMBOL(zlib_inflateEnd);
 EXPORT_SYMBOL(zlib_inflateReset);
 EXPORT_SYMBOL(zlib_inflateIncomp); 
 EXPORT_SYMBOL(zlib_inflate_blob);
+MODULE_DESCRIPTION("Data decompression using the deflation algorithm");
 MODULE_LICENSE("GPL");
diff --git a/mm/cma.c b/mm/cma.c
index b06d5fe73399..15632939f20a 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -35,7 +35,7 @@
 struct cma cma_areas[MAX_CMA_AREAS];
 unsigned int cma_area_count;
 
-static int __init __cma_declare_contiguous_nid(phys_addr_t base,
+static int __init __cma_declare_contiguous_nid(phys_addr_t *basep,
 			phys_addr_t size, phys_addr_t limit,
 			phys_addr_t alignment, unsigned int order_per_bit,
 			bool fixed, const char *name, struct cma **res_cma,
@@ -370,7 +370,7 @@ int __init cma_declare_contiguous_multi(phys_addr_t total_size,
 			phys_addr_t align, unsigned int order_per_bit,
 			const char *name, struct cma **res_cma, int nid)
 {
-	phys_addr_t start, end;
+	phys_addr_t start = 0, end;
 	phys_addr_t size, sizesum, sizeleft;
 	struct cma_init_memrange *mrp, *mlp, *failed;
 	struct cma_memrange *cmrp;
@@ -384,7 +384,7 @@ int __init cma_declare_contiguous_multi(phys_addr_t total_size,
 	/*
 	 * First, try it the normal way, producing just one range.
 	 */
-	ret = __cma_declare_contiguous_nid(0, total_size, 0, align,
+	ret = __cma_declare_contiguous_nid(&start, total_size, 0, align,
 			order_per_bit, false, name, res_cma, nid);
 	if (ret != -ENOMEM)
 		goto out;
@@ -580,7 +580,7 @@ int __init cma_declare_contiguous_nid(phys_addr_t base,
 {
 	int ret;
 
-	ret = __cma_declare_contiguous_nid(base, size, limit, alignment,
+	ret = __cma_declare_contiguous_nid(&base, size, limit, alignment,
 			order_per_bit, fixed, name, res_cma, nid);
 	if (ret != 0)
 		pr_err("Failed to reserve %ld MiB\n",
@@ -592,14 +592,14 @@ int __init cma_declare_contiguous_nid(phys_addr_t base,
 	return ret;
 }
 
-static int __init __cma_declare_contiguous_nid(phys_addr_t base,
+static int __init __cma_declare_contiguous_nid(phys_addr_t *basep,
 			phys_addr_t size, phys_addr_t limit,
 			phys_addr_t alignment, unsigned int order_per_bit,
 			bool fixed, const char *name, struct cma **res_cma,
 			int nid)
 {
 	phys_addr_t memblock_end = memblock_end_of_DRAM();
-	phys_addr_t highmem_start;
+	phys_addr_t highmem_start, base = *basep;
 	int ret;
 
 	/*
@@ -722,12 +722,15 @@ static int __init __cma_declare_contiguous_nid(phys_addr_t base,
 	}
 
 	ret = cma_init_reserved_mem(base, size, order_per_bit, name, res_cma);
-	if (ret)
+	if (ret) {
 		memblock_phys_free(base, size);
+		return ret;
+	}
 
 	(*res_cma)->nid = nid;
+	*basep = base;
 
-	return ret;
+	return 0;
 }
 
 static void cma_debug_show_areas(struct cma *cma)
diff --git a/mm/compaction.c b/mm/compaction.c
index 139f00c0308a..ca71fd3c3181 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -981,13 +981,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		}
 
 		if (PageHuge(page)) {
+			const unsigned int order = compound_order(page);
 			/*
 			 * skip hugetlbfs if we are not compacting for pages
 			 * bigger than its order. THPs and other compound pages
 			 * are handled below.
 			 */
 			if (!cc->alloc_contig) {
-				const unsigned int order = compound_order(page);
 
 				if (order <= MAX_PAGE_ORDER) {
 					low_pfn += (1UL << order) - 1;
@@ -1011,8 +1011,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 				 /* Do not report -EBUSY down the chain */
 				if (ret == -EBUSY)
 					ret = 0;
-				low_pfn += compound_nr(page) - 1;
-				nr_scanned += compound_nr(page) - 1;
+				low_pfn += (1UL << order) - 1;
+				nr_scanned += (1UL << order) - 1;
 				goto isolate_fail;
 			}
 
diff --git a/mm/execmem.c b/mm/execmem.c
index e6c4f5076ca8..6f7a2653b280 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -254,6 +254,34 @@ out_unlock:
 	return ptr;
 }
 
+static bool execmem_cache_rox = false;
+
+void execmem_cache_make_ro(void)
+{
+	struct maple_tree *free_areas = &execmem_cache.free_areas;
+	struct maple_tree *busy_areas = &execmem_cache.busy_areas;
+	MA_STATE(mas_free, free_areas, 0, ULONG_MAX);
+	MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX);
+	struct mutex *mutex = &execmem_cache.mutex;
+	void *area;
+
+	execmem_cache_rox = true;
+
+	mutex_lock(mutex);
+
+	mas_for_each(&mas_free, area, ULONG_MAX) {
+		unsigned long pages = mas_range_len(&mas_free) >> PAGE_SHIFT;
+		set_memory_ro(mas_free.index, pages);
+	}
+
+	mas_for_each(&mas_busy, area, ULONG_MAX) {
+		unsigned long pages = mas_range_len(&mas_busy) >> PAGE_SHIFT;
+		set_memory_ro(mas_busy.index, pages);
+	}
+
+	mutex_unlock(mutex);
+}
+
 static int execmem_cache_populate(struct execmem_range *range, size_t size)
 {
 	unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
@@ -274,9 +302,15 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
 	/* fill memory with instructions that will trap */
 	execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
 
-	err = set_memory_rox((unsigned long)p, vm->nr_pages);
-	if (err)
-		goto err_free_mem;
+	if (execmem_cache_rox) {
+		err = set_memory_rox((unsigned long)p, vm->nr_pages);
+		if (err)
+			goto err_free_mem;
+	} else {
+		err = set_memory_x((unsigned long)p, vm->nr_pages);
+		if (err)
+			goto err_free_mem;
+	}
 
 	err = execmem_cache_add(p, alloc_size);
 	if (err)
diff --git a/mm/filemap.c b/mm/filemap.c
index b5e784f34d98..7b90cbeb4a1a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2244,6 +2244,7 @@ unsigned filemap_get_folios_contig(struct address_space *mapping,
 			*start = folio->index + nr;
 			goto out;
 		}
+		xas_advance(&xas, folio_next_index(folio) - 1);
 		continue;
 put_folio:
 		folio_put(folio);
diff --git a/mm/gup.c b/mm/gup.c
index 92351e2fa876..84461d384ae2 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2207,8 +2207,8 @@ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
 	} while (start != end);
 	mmap_read_unlock(mm);
 
-	if (size > (unsigned long)uaddr - start)
-		return size - ((unsigned long)uaddr - start);
+	if (size > start - (unsigned long)uaddr)
+		return size - (start - (unsigned long)uaddr);
 	return 0;
 }
 EXPORT_SYMBOL(fault_in_safe_writeable);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2a47682d1ab7..47d76d03ce30 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3075,6 +3075,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
 			   pmd_t *pmd, bool freeze, struct folio *folio)
 {
+	bool pmd_migration = is_pmd_migration_entry(*pmd);
+
 	VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio));
 	VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
 	VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
@@ -3085,9 +3087,12 @@ void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
 	 * require a folio to check the PMD against. Otherwise, there
 	 * is a risk of replacing the wrong folio.
 	 */
-	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
-	    is_pmd_migration_entry(*pmd)) {
-		if (folio && folio != pmd_folio(*pmd))
+	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || pmd_migration) {
+		/*
+		 * Do not apply pmd_folio() to a migration entry; and folio lock
+		 * guarantees that it must be of the wrong folio anyway.
+		 */
+		if (folio && (pmd_migration || folio != pmd_folio(*pmd)))
 			return;
 		__split_huge_pmd_locked(vma, pmd, address, freeze);
 	}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 39f92aad7bd1..7ae38bfb9096 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2271,7 +2271,7 @@ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h,
 	 * as surplus_pages, otherwise it might confuse
 	 * persistent_huge_pages() momentarily.
 	 */
-	__prep_account_new_huge_page(h, nid);
+	__prep_account_new_huge_page(h, folio_nid(folio));
 
 	/*
 	 * We could have raced with the pool size change.
@@ -3010,7 +3010,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	struct hugepage_subpool *spool = subpool_vma(vma);
 	struct hstate *h = hstate_vma(vma);
 	struct folio *folio;
-	long retval, gbl_chg;
+	long retval, gbl_chg, gbl_reserve;
 	map_chg_state map_chg;
 	int ret, idx;
 	struct hugetlb_cgroup *h_cg = NULL;
@@ -3163,8 +3163,16 @@ out_uncharge_cgroup_reservation:
 		hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h),
 						    h_cg);
 out_subpool_put:
-	if (map_chg)
-		hugepage_subpool_put_pages(spool, 1);
+	/*
+	 * put page to subpool iff the quota of subpool's rsv_hpages is used
+	 * during hugepage_subpool_get_pages.
+	 */
+	if (map_chg && !gbl_chg) {
+		gbl_reserve = hugepage_subpool_put_pages(spool, 1);
+		hugetlb_acct_memory(h, -gbl_reserve);
+	}
+
+
 out_end_reservation:
 	if (map_chg != MAP_CHG_ENFORCED)
 		vma_end_reservation(h, vma, addr);
@@ -3825,6 +3833,7 @@ found:
 static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 			      nodemask_t *nodes_allowed)
 {
+	unsigned long persistent_free_count;
 	unsigned long min_count;
 	unsigned long allocated;
 	struct folio *folio;
@@ -3959,8 +3968,24 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 	 * though, we'll note that we're not allowed to exceed surplus
 	 * and won't grow the pool anywhere else. Not until one of the
 	 * sysctls are changed, or the surplus pages go out of use.
+	 *
+	 * min_count is the expected number of persistent pages, we
+	 * shouldn't calculate min_count by using
+	 * resv_huge_pages + persistent_huge_pages() - free_huge_pages,
+	 * because there may exist free surplus huge pages, and this will
+	 * lead to subtracting twice. Free surplus huge pages come from HVO
+	 * failing to restore vmemmap, see comments in the callers of
+	 * hugetlb_vmemmap_restore_folio(). Thus, we should calculate
+	 * persistent free count first.
 	 */
-	min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
+	persistent_free_count = h->free_huge_pages;
+	if (h->free_huge_pages > persistent_huge_pages(h)) {
+		if (h->free_huge_pages > h->surplus_huge_pages)
+			persistent_free_count -= h->surplus_huge_pages;
+		else
+			persistent_free_count = 0;
+	}
+	min_count = h->resv_huge_pages + persistent_huge_pages(h) - persistent_free_count;
 	min_count = max(count, min_count);
 	try_to_free_low(h, min_count, nodes_allowed);
 
@@ -4017,10 +4042,13 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
 
 	list_for_each_entry_safe(folio, next, src_list, lru) {
 		int i;
+		bool cma;
 
 		if (folio_test_hugetlb_vmemmap_optimized(folio))
 			continue;
 
+		cma = folio_test_hugetlb_cma(folio);
+
 		list_del(&folio->lru);
 
 		split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst));
@@ -4036,6 +4064,9 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
 
 			new_folio->mapping = NULL;
 			init_new_hugetlb_folio(dst, new_folio);
+			/* Copy the CMA flag so that it is freed correctly */
+			if (cma)
+				folio_set_hugetlb_cma(new_folio);
 			list_add(&new_folio->lru, &dst_list);
 		}
 	}
@@ -4630,7 +4661,7 @@ static void __init hugetlb_sysfs_init(void)
 		err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
 					 hstate_kobjs, &hstate_attr_group);
 		if (err)
-			pr_err("HugeTLB: Unable to add hstate %s", h->name);
+			pr_err("HugeTLB: Unable to add hstate %s\n", h->name);
 	}
 
 #ifdef CONFIG_NUMA
@@ -7216,7 +7247,7 @@ bool hugetlb_reserve_pages(struct inode *inode,
 					struct vm_area_struct *vma,
 					vm_flags_t vm_flags)
 {
-	long chg = -1, add = -1;
+	long chg = -1, add = -1, spool_resv, gbl_resv;
 	struct hstate *h = hstate_inode(inode);
 	struct hugepage_subpool *spool = subpool_inode(inode);
 	struct resv_map *resv_map;
@@ -7351,8 +7382,16 @@ bool hugetlb_reserve_pages(struct inode *inode,
 	return true;
 
 out_put_pages:
-	/* put back original number of pages, chg */
-	(void)hugepage_subpool_put_pages(spool, chg);
+	spool_resv = chg - gbl_reserve;
+	if (spool_resv) {
+		/* put sub pool's reservation back, chg - gbl_reserve */
+		gbl_resv = hugepage_subpool_put_pages(spool, spool_resv);
+		/*
+		 * subpool's reserved pages can not be put back due to race,
+		 * return to hstate.
+		 */
+		hugetlb_acct_memory(h, -gbl_resv);
+	}
 out_uncharge_cgroup:
 	hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h),
 					    chg * pages_per_huge_page(h), h_cg);
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 9a99dfa3c495..27245e86df25 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -238,11 +238,11 @@ static void vmemmap_remap_pte(pte_t *pte, unsigned long addr,
  * struct page, the special metadata (e.g. page->flags or page->mapping)
  * cannot copy to the tail struct page structs. The invalid value will be
  * checked in the free_tail_page_prepare(). In order to avoid the message
- * of "corrupted mapping in tail page". We need to reset at least 3 (one
- * head struct page struct and two tail struct page structs) struct page
+ * of "corrupted mapping in tail page". We need to reset at least 4 (one
+ * head struct page struct and three tail struct page structs) struct page
  * structs.
  */
-#define NR_RESET_STRUCT_PAGE		3
+#define NR_RESET_STRUCT_PAGE		4
 
 static inline void reset_struct_pages(struct page *start)
 {
diff --git a/mm/internal.h b/mm/internal.h
index 50c2f590b2d0..5c7a2b43ad76 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -248,11 +248,9 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 		pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
 		bool *any_writable, bool *any_young, bool *any_dirty)
 {
-	unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
-	const pte_t *end_ptep = start_ptep + max_nr;
 	pte_t expected_pte, *ptep;
 	bool writable, young, dirty;
-	int nr;
+	int nr, cur_nr;
 
 	if (any_writable)
 		*any_writable = false;
@@ -265,11 +263,15 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 	VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
 	VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio);
 
+	/* Limit max_nr to the actual remaining PFNs in the folio we could batch. */
+	max_nr = min_t(unsigned long, max_nr,
+		       folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte));
+
 	nr = pte_batch_hint(start_ptep, pte);
 	expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
 	ptep = start_ptep + nr;
 
-	while (ptep < end_ptep) {
+	while (nr < max_nr) {
 		pte = ptep_get(ptep);
 		if (any_writable)
 			writable = !!pte_write(pte);
@@ -282,14 +284,6 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 		if (!pte_same(pte, expected_pte))
 			break;
 
-		/*
-		 * Stop immediately once we reached the end of the folio. In
-		 * corner cases the next PFN might fall into a different
-		 * folio.
-		 */
-		if (pte_pfn(pte) >= folio_end_pfn)
-			break;
-
 		if (any_writable)
 			*any_writable |= writable;
 		if (any_young)
@@ -297,12 +291,13 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 		if (any_dirty)
 			*any_dirty |= dirty;
 
-		nr = pte_batch_hint(ptep, pte);
-		expected_pte = pte_advance_pfn(expected_pte, nr);
-		ptep += nr;
+		cur_nr = pte_batch_hint(ptep, pte);
+		expected_pte = pte_advance_pfn(expected_pte, cur_nr);
+		ptep += cur_nr;
+		nr += cur_nr;
 	}
 
-	return min(ptep - start_ptep, max_nr);
+	return min(nr, max_nr);
 }
 
 /**
diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c
index 3ea317837c2d..5f922dd38ffa 100644
--- a/mm/kasan/kasan_test_c.c
+++ b/mm/kasan/kasan_test_c.c
@@ -1567,6 +1567,7 @@ static void kasan_memcmp(struct kunit *test)
 static void kasan_strings(struct kunit *test)
 {
 	char *ptr;
+	char *src;
 	size_t size = 24;
 
 	/*
@@ -1578,6 +1579,25 @@ static void kasan_strings(struct kunit *test)
 	ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	src = kmalloc(KASAN_GRANULE_SIZE, GFP_KERNEL | __GFP_ZERO);
+	strscpy(src, "f0cacc1a0000000", KASAN_GRANULE_SIZE);
+
+	/*
+	 * Make sure that strscpy() does not trigger KASAN if it overreads into
+	 * poisoned memory.
+	 *
+	 * The expected size does not include the terminator '\0'
+	 * so it is (KASAN_GRANULE_SIZE - 2) ==
+	 * KASAN_GRANULE_SIZE - ("initial removed character" + "\0").
+	 */
+	KUNIT_EXPECT_EQ(test, KASAN_GRANULE_SIZE - 2,
+			strscpy(ptr, src + 1, KASAN_GRANULE_SIZE));
+
+	/* strscpy should fail if the first byte is unreadable. */
+	KUNIT_EXPECT_KASAN_FAIL(test, strscpy(ptr, src + KASAN_GRANULE_SIZE,
+					      KASAN_GRANULE_SIZE));
+
+	kfree(src);
 	kfree(ptr);
 
 	/*
@@ -2127,4 +2147,5 @@ static struct kunit_suite kasan_kunit_test_suite = {
 
 kunit_test_suite(kasan_kunit_test_suite);
 
+MODULE_DESCRIPTION("KUnit tests for checking KASAN bug-detection capabilities");
 MODULE_LICENSE("GPL");
diff --git a/mm/memblock.c b/mm/memblock.c
index 0a53db4d9f7b..0e9ebb8aa7fe 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -457,7 +457,14 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 				min(new_area_start, memblock.current_limit),
 				new_alloc_size, PAGE_SIZE);
 
-		new_array = addr ? __va(addr) : NULL;
+		if (addr) {
+			/* The memory may not have been accepted, yet. */
+			accept_memory(addr, new_alloc_size);
+
+			new_array = __va(addr);
+		} else {
+			new_array = NULL;
+		}
 	}
 	if (!addr) {
 		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
@@ -2183,11 +2190,14 @@ static void __init memmap_init_reserved_pages(void)
 	struct memblock_region *region;
 	phys_addr_t start, end;
 	int nid;
+	unsigned long max_reserved;
 
 	/*
 	 * set nid on all reserved pages and also treat struct
 	 * pages for the NOMAP regions as PageReserved
 	 */
+repeat:
+	max_reserved = memblock.reserved.max;
 	for_each_mem_region(region) {
 		nid = memblock_get_region_node(region);
 		start = region->base;
@@ -2196,8 +2206,15 @@ static void __init memmap_init_reserved_pages(void)
 		if (memblock_is_nomap(region))
 			reserve_bootmem_region(start, end, nid);
 
-		memblock_set_node(start, end, &memblock.reserved, nid);
+		memblock_set_node(start, region->size, &memblock.reserved, nid);
 	}
+	/*
+	 * 'max' is changed means memblock.reserved has been doubled its
+	 * array, which may result a new reserved region before current
+	 * 'start'. Now we should repeat the procedure to set its node id.
+	 */
+	if (max_reserved != memblock.reserved.max)
+		goto repeat;
 
 	/*
 	 * initialize struct pages for reserved regions that don't have
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index 8660908850dc..4a9cf27a70af 100644
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -620,7 +620,7 @@ void memcg1_swapout(struct folio *folio, swp_entry_t entry)
 		mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
 	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
 
-	swap_cgroup_record(folio, mem_cgroup_id(memcg), entry);
+	swap_cgroup_record(folio, mem_cgroup_id(swap_memcg), entry);
 
 	folio_unqueue_deferred_split(folio);
 	folio->memcg_data = 0;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 421740f1bcdc..c96c1f2b9cf5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1759,7 +1759,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
 }
 
 struct memcg_stock_pcp {
-	localtry_lock_t stock_lock;
+	local_trylock_t stock_lock;
 	struct mem_cgroup *cached; /* this never be root cgroup */
 	unsigned int nr_pages;
 
@@ -1774,7 +1774,7 @@ struct memcg_stock_pcp {
 #define FLUSHING_CACHED_CHARGE	0
 };
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock) = {
-	.stock_lock = INIT_LOCALTRY_LOCK(stock_lock),
+	.stock_lock = INIT_LOCAL_TRYLOCK(stock_lock),
 };
 static DEFINE_MUTEX(percpu_charge_mutex);
 
@@ -1805,11 +1805,10 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages,
 	if (nr_pages > MEMCG_CHARGE_BATCH)
 		return ret;
 
-	if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
-		if (!gfpflags_allow_spinning(gfp_mask))
-			return ret;
-		localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
-	}
+	if (gfpflags_allow_spinning(gfp_mask))
+		local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	else if (!local_trylock_irqsave(&memcg_stock.stock_lock, flags))
+		return ret;
 
 	stock = this_cpu_ptr(&memcg_stock);
 	stock_pages = READ_ONCE(stock->nr_pages);
@@ -1818,7 +1817,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages,
 		ret = true;
 	}
 
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	return ret;
 }
@@ -1857,14 +1856,14 @@ static void drain_local_stock(struct work_struct *dummy)
 	 * drain_stock races is that we always operate on local CPU stock
 	 * here with IRQ disabled
 	 */
-	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	old = drain_obj_stock(stock);
 	drain_stock(stock);
 	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
 
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 }
 
@@ -1894,7 +1893,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	unsigned long flags;
 
-	if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
+	if (!local_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
 		/*
 		 * In case of unlikely failure to lock percpu stock_lock
 		 * uncharge memcg directly.
@@ -1907,7 +1906,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 		return;
 	}
 	__refill_stock(memcg, nr_pages);
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 }
 
 /*
@@ -1964,9 +1963,9 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu)
 	stock = &per_cpu(memcg_stock, cpu);
 
 	/* drain_obj_stock requires stock_lock */
-	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 	old = drain_obj_stock(stock);
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	drain_stock(stock);
 	obj_cgroup_put(old);
@@ -2787,7 +2786,7 @@ static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 	unsigned long flags;
 	int *bytes;
 
-	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 	stock = this_cpu_ptr(&memcg_stock);
 
 	/*
@@ -2836,7 +2835,7 @@ static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 	if (nr)
 		__mod_objcg_mlstate(objcg, pgdat, idx, nr);
 
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 }
 
@@ -2846,7 +2845,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
 	unsigned long flags;
 	bool ret = false;
 
-	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) {
@@ -2854,7 +2853,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
 		ret = true;
 	}
 
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	return ret;
 }
@@ -2946,7 +2945,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 	unsigned long flags;
 	unsigned int nr_pages = 0;
 
-	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */
@@ -2960,7 +2959,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 		stock->nr_bytes &= (PAGE_SIZE - 1);
 	}
 
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 
 	if (nr_pages)
diff --git a/mm/memory.c b/mm/memory.c
index 2d8c265fc7d6..49199410805c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1361,7 +1361,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 	struct mm_struct *dst_mm = dst_vma->vm_mm;
 	struct mm_struct *src_mm = src_vma->vm_mm;
 	struct mmu_notifier_range range;
-	unsigned long next, pfn;
+	unsigned long next, pfn = 0;
 	bool is_cow;
 	int ret;
 
@@ -2938,11 +2938,11 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	if (fn) {
 		do {
 			if (create || !pte_none(ptep_get(pte))) {
-				err = fn(pte++, addr, data);
+				err = fn(pte, addr, data);
 				if (err)
 					break;
 			}
-		} while (addr += PAGE_SIZE, addr != end);
+		} while (pte++, addr += PAGE_SIZE, addr != end);
 	}
 	*mask |= PGTBL_PTE_MODIFIED;
 
@@ -3734,8 +3734,6 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
 		return false;
 
 	VM_WARN_ON_ONCE(folio_test_ksm(folio));
-	VM_WARN_ON_ONCE(folio_mapcount(folio) > folio_nr_pages(folio));
-	VM_WARN_ON_ONCE(folio_entire_mapcount(folio));
 
 	if (unlikely(folio_test_swapcache(folio))) {
 		/*
@@ -3753,13 +3751,15 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
 
 	/* Stabilize the mapcount vs. refcount and recheck. */
 	folio_lock_large_mapcount(folio);
-	VM_WARN_ON_ONCE(folio_large_mapcount(folio) < folio_ref_count(folio));
+	VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_ref_count(folio), folio);
 
 	if (folio_test_large_maybe_mapped_shared(folio))
 		goto unlock;
 	if (folio_large_mapcount(folio) != folio_ref_count(folio))
 		goto unlock;
 
+	VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_nr_pages(folio), folio);
+	VM_WARN_ON_ONCE_FOLIO(folio_entire_mapcount(folio), folio);
 	VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != vma->vm_mm->mm_id &&
 			folio_mm_id(folio, 1) != vma->vm_mm->mm_id);
 
diff --git a/mm/migrate.c b/mm/migrate.c
index f3ee6d8d5e2e..676d9cfc7059 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -845,9 +845,11 @@ static int __buffer_migrate_folio(struct address_space *mapping,
 		return -EAGAIN;
 
 	if (check_refs) {
-		bool busy;
+		bool busy, migrating;
 		bool invalidated = false;
 
+		migrating = test_and_set_bit_lock(BH_Migrate, &head->b_state);
+		VM_WARN_ON_ONCE(migrating);
 recheck_buffers:
 		busy = false;
 		spin_lock(&mapping->i_private_lock);
@@ -859,12 +861,12 @@ recheck_buffers:
 			}
 			bh = bh->b_this_page;
 		} while (bh != head);
+		spin_unlock(&mapping->i_private_lock);
 		if (busy) {
 			if (invalidated) {
 				rc = -EAGAIN;
 				goto unlock_buffers;
 			}
-			spin_unlock(&mapping->i_private_lock);
 			invalidate_bh_lrus();
 			invalidated = true;
 			goto recheck_buffers;
@@ -883,7 +885,7 @@ recheck_buffers:
 
 unlock_buffers:
 	if (check_refs)
-		spin_unlock(&mapping->i_private_lock);
+		clear_bit_unlock(BH_Migrate, &head->b_state);
 	bh = head;
 	do {
 		unlock_buffer(bh);
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 84f14fa12d0d..eedce9321e13 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1785,7 +1785,7 @@ static bool arch_has_descending_max_zone_pfns(void)
 	return IS_ENABLED(CONFIG_ARC) && !IS_ENABLED(CONFIG_ARC_HAS_PAE40);
 }
 
-static void set_high_memory(void)
+static void __init set_high_memory(void)
 {
 	phys_addr_t highmem = memblock_end_of_DRAM();
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fd6b865cb1ab..8c75433ff9a4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -290,7 +290,8 @@ EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
 static bool page_contains_unaccepted(struct page *page, unsigned int order);
-static bool cond_accept_memory(struct zone *zone, unsigned int order);
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+			       int alloc_flags);
 static bool __free_unaccepted(struct page *page);
 
 int page_group_by_mobility_disabled __read_mostly;
@@ -897,9 +898,7 @@ static inline bool page_expected_state(struct page *page,
 #ifdef CONFIG_MEMCG
 			page->memcg_data |
 #endif
-#ifdef CONFIG_PAGE_POOL
-			((page->pp_magic & ~0x3UL) == PP_SIGNATURE) |
-#endif
+			page_pool_page_is_pp(page) |
 			(page->flags & check_flags)))
 		return false;
 
@@ -926,10 +925,8 @@ static const char *page_bad_reason(struct page *page, unsigned long flags)
 	if (unlikely(page->memcg_data))
 		bad_reason = "page still charged to cgroup";
 #endif
-#ifdef CONFIG_PAGE_POOL
-	if (unlikely((page->pp_magic & ~0x3UL) == PP_SIGNATURE))
+	if (unlikely(page_pool_page_is_pp(page)))
 		bad_reason = "page_pool leak";
-#endif
 	return bad_reason;
 }
 
@@ -1151,14 +1148,9 @@ static inline void pgalloc_tag_sub(struct page *page, unsigned int nr)
 		__pgalloc_tag_sub(page, nr);
 }
 
-static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr)
+/* When tag is not NULL, assuming mem_alloc_profiling_enabled */
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr)
 {
-	struct alloc_tag *tag;
-
-	if (!mem_alloc_profiling_enabled())
-		return;
-
-	tag = __pgalloc_tag_get(page);
 	if (tag)
 		this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr);
 }
@@ -1168,7 +1160,7 @@ static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr)
 static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
 				   unsigned int nr) {}
 static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {}
-static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr) {}
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {}
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
 
@@ -1400,11 +1392,12 @@ static void free_one_page(struct zone *zone, struct page *page,
 	struct llist_head *llhead;
 	unsigned long flags;
 
-	if (!spin_trylock_irqsave(&zone->lock, flags)) {
-		if (unlikely(fpi_flags & FPI_TRYLOCK)) {
+	if (unlikely(fpi_flags & FPI_TRYLOCK)) {
+		if (!spin_trylock_irqsave(&zone->lock, flags)) {
 			add_page_to_zone_llist(zone, page, order);
 			return;
 		}
+	} else {
 		spin_lock_irqsave(&zone->lock, flags);
 	}
 
@@ -2182,23 +2175,15 @@ try_to_claim_block(struct zone *zone, struct page *page,
 }
 
 /*
- * Try finding a free buddy page on the fallback list.
- *
- * This will attempt to claim a whole pageblock for the requested type
- * to ensure grouping of such requests in the future.
- *
- * If a whole block cannot be claimed, steal an individual page, regressing to
- * __rmqueue_smallest() logic to at least break up as little contiguity as
- * possible.
+ * Try to allocate from some fallback migratetype by claiming the entire block,
+ * i.e. converting it to the allocation's start migratetype.
  *
  * The use of signed ints for order and current_order is a deliberate
  * deviation from the rest of this file, to make the for loop
  * condition simpler.
- *
- * Return the stolen page, or NULL if none can be found.
  */
 static __always_inline struct page *
-__rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
+__rmqueue_claim(struct zone *zone, int order, int start_migratetype,
 						unsigned int alloc_flags)
 {
 	struct free_area *area;
@@ -2236,14 +2221,29 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
 		page = try_to_claim_block(zone, page, current_order, order,
 					  start_migratetype, fallback_mt,
 					  alloc_flags);
-		if (page)
-			goto got_one;
+		if (page) {
+			trace_mm_page_alloc_extfrag(page, order, current_order,
+						    start_migratetype, fallback_mt);
+			return page;
+		}
 	}
 
-	if (alloc_flags & ALLOC_NOFRAGMENT)
-		return NULL;
+	return NULL;
+}
+
+/*
+ * Try to steal a single page from some fallback migratetype. Leave the rest of
+ * the block as its current migratetype, potentially causing fragmentation.
+ */
+static __always_inline struct page *
+__rmqueue_steal(struct zone *zone, int order, int start_migratetype)
+{
+	struct free_area *area;
+	int current_order;
+	struct page *page;
+	int fallback_mt;
+	bool claim_block;
 
-	/* No luck claiming pageblock. Find the smallest fallback page */
 	for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) {
 		area = &(zone->free_area[current_order]);
 		fallback_mt = find_suitable_fallback(area, current_order,
@@ -2253,25 +2253,28 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
 
 		page = get_page_from_free_area(area, fallback_mt);
 		page_del_and_expand(zone, page, order, current_order, fallback_mt);
-		goto got_one;
+		trace_mm_page_alloc_extfrag(page, order, current_order,
+					    start_migratetype, fallback_mt);
+		return page;
 	}
 
 	return NULL;
-
-got_one:
-	trace_mm_page_alloc_extfrag(page, order, current_order,
-		start_migratetype, fallback_mt);
-
-	return page;
 }
 
+enum rmqueue_mode {
+	RMQUEUE_NORMAL,
+	RMQUEUE_CMA,
+	RMQUEUE_CLAIM,
+	RMQUEUE_STEAL,
+};
+
 /*
  * Do the hard work of removing an element from the buddy allocator.
  * Call me with the zone->lock already held.
  */
 static __always_inline struct page *
 __rmqueue(struct zone *zone, unsigned int order, int migratetype,
-						unsigned int alloc_flags)
+	  unsigned int alloc_flags, enum rmqueue_mode *mode)
 {
 	struct page *page;
 
@@ -2290,16 +2293,48 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype,
 		}
 	}
 
-	page = __rmqueue_smallest(zone, order, migratetype);
-	if (unlikely(!page)) {
-		if (alloc_flags & ALLOC_CMA)
+	/*
+	 * First try the freelists of the requested migratetype, then try
+	 * fallbacks modes with increasing levels of fragmentation risk.
+	 *
+	 * The fallback logic is expensive and rmqueue_bulk() calls in
+	 * a loop with the zone->lock held, meaning the freelists are
+	 * not subject to any outside changes. Remember in *mode where
+	 * we found pay dirt, to save us the search on the next call.
+	 */
+	switch (*mode) {
+	case RMQUEUE_NORMAL:
+		page = __rmqueue_smallest(zone, order, migratetype);
+		if (page)
+			return page;
+		fallthrough;
+	case RMQUEUE_CMA:
+		if (alloc_flags & ALLOC_CMA) {
 			page = __rmqueue_cma_fallback(zone, order);
-
-		if (!page)
-			page = __rmqueue_fallback(zone, order, migratetype,
-						  alloc_flags);
+			if (page) {
+				*mode = RMQUEUE_CMA;
+				return page;
+			}
+		}
+		fallthrough;
+	case RMQUEUE_CLAIM:
+		page = __rmqueue_claim(zone, order, migratetype, alloc_flags);
+		if (page) {
+			/* Replenished preferred freelist, back to normal mode. */
+			*mode = RMQUEUE_NORMAL;
+			return page;
+		}
+		fallthrough;
+	case RMQUEUE_STEAL:
+		if (!(alloc_flags & ALLOC_NOFRAGMENT)) {
+			page = __rmqueue_steal(zone, order, migratetype);
+			if (page) {
+				*mode = RMQUEUE_STEAL;
+				return page;
+			}
+		}
 	}
-	return page;
+	return NULL;
 }
 
 /*
@@ -2311,17 +2346,19 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			unsigned long count, struct list_head *list,
 			int migratetype, unsigned int alloc_flags)
 {
+	enum rmqueue_mode rmqm = RMQUEUE_NORMAL;
 	unsigned long flags;
 	int i;
 
-	if (!spin_trylock_irqsave(&zone->lock, flags)) {
-		if (unlikely(alloc_flags & ALLOC_TRYLOCK))
+	if (unlikely(alloc_flags & ALLOC_TRYLOCK)) {
+		if (!spin_trylock_irqsave(&zone->lock, flags))
 			return 0;
+	} else {
 		spin_lock_irqsave(&zone->lock, flags);
 	}
 	for (i = 0; i < count; ++i) {
 		struct page *page = __rmqueue(zone, order, migratetype,
-								alloc_flags);
+					      alloc_flags, &rmqm);
 		if (unlikely(page == NULL))
 			break;
 
@@ -2937,15 +2974,18 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone,
 
 	do {
 		page = NULL;
-		if (!spin_trylock_irqsave(&zone->lock, flags)) {
-			if (unlikely(alloc_flags & ALLOC_TRYLOCK))
+		if (unlikely(alloc_flags & ALLOC_TRYLOCK)) {
+			if (!spin_trylock_irqsave(&zone->lock, flags))
 				return NULL;
+		} else {
 			spin_lock_irqsave(&zone->lock, flags);
 		}
 		if (alloc_flags & ALLOC_HIGHATOMIC)
 			page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
 		if (!page) {
-			page = __rmqueue(zone, order, migratetype, alloc_flags);
+			enum rmqueue_mode rmqm = RMQUEUE_NORMAL;
+
+			page = __rmqueue(zone, order, migratetype, alloc_flags, &rmqm);
 
 			/*
 			 * If the allocation fails, allow OOM handling and
@@ -3422,18 +3462,6 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 	return false;
 }
 
-bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
-			unsigned long mark, int highest_zoneidx)
-{
-	long free_pages = zone_page_state(z, NR_FREE_PAGES);
-
-	if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
-		free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
-
-	return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0,
-								free_pages);
-}
-
 #ifdef CONFIG_NUMA
 int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE;
 
@@ -3580,7 +3608,7 @@ retry:
 			}
 		}
 
-		cond_accept_memory(zone, order);
+		cond_accept_memory(zone, order, alloc_flags);
 
 		/*
 		 * Detect whether the number of free pages is below high
@@ -3607,7 +3635,7 @@ check_alloc_wmark:
 				       gfp_mask)) {
 			int ret;
 
-			if (cond_accept_memory(zone, order))
+			if (cond_accept_memory(zone, order, alloc_flags))
 				goto try_this_zone;
 
 			/*
@@ -3660,7 +3688,7 @@ try_this_zone:
 
 			return page;
 		} else {
-			if (cond_accept_memory(zone, order))
+			if (cond_accept_memory(zone, order, alloc_flags))
 				goto try_this_zone;
 
 			/* Try again if zone has deferred pages */
@@ -4813,7 +4841,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 			goto failed;
 		}
 
-		cond_accept_memory(zone, 0);
+		cond_accept_memory(zone, 0, alloc_flags);
 retry_this_zone:
 		mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages;
 		if (zone_watermark_fast(zone, 0,  mark,
@@ -4822,7 +4850,7 @@ retry_this_zone:
 			break;
 		}
 
-		if (cond_accept_memory(zone, 0))
+		if (cond_accept_memory(zone, 0, alloc_flags))
 			goto retry_this_zone;
 
 		/* Try again if zone has deferred pages */
@@ -5029,11 +5057,13 @@ static void ___free_pages(struct page *page, unsigned int order,
 {
 	/* get PageHead before we drop reference */
 	int head = PageHead(page);
+	/* get alloc tag in case the page is released by others */
+	struct alloc_tag *tag = pgalloc_tag_get(page);
 
 	if (put_page_testzero(page))
 		__free_frozen_pages(page, order, fpi_flags);
 	else if (!head) {
-		pgalloc_tag_sub_pages(page, (1 << order) - 1);
+		pgalloc_tag_sub_pages(tag, (1 << order) - 1);
 		while (order-- > 0)
 			__free_frozen_pages(page + (1 << order), order,
 					    fpi_flags);
@@ -7138,9 +7168,6 @@ bool has_managed_dma(void)
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
 
-/* Counts number of zones with unaccepted pages. */
-static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages);
-
 static bool lazy_accept = true;
 
 static int __init accept_memory_parse(char *p)
@@ -7167,11 +7194,7 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order)
 static void __accept_page(struct zone *zone, unsigned long *flags,
 			  struct page *page)
 {
-	bool last;
-
 	list_del(&page->lru);
-	last = list_empty(&zone->unaccepted_pages);
-
 	account_freepages(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
 	__mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES);
 	__ClearPageUnaccepted(page);
@@ -7180,9 +7203,6 @@ static void __accept_page(struct zone *zone, unsigned long *flags,
 	accept_memory(page_to_phys(page), PAGE_SIZE << MAX_PAGE_ORDER);
 
 	__free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL);
-
-	if (last)
-		static_branch_dec(&zones_with_unaccepted_pages);
 }
 
 void accept_page(struct page *page)
@@ -7219,20 +7239,17 @@ static bool try_to_accept_memory_one(struct zone *zone)
 	return true;
 }
 
-static inline bool has_unaccepted_memory(void)
-{
-	return static_branch_unlikely(&zones_with_unaccepted_pages);
-}
-
-static bool cond_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+			       int alloc_flags)
 {
 	long to_accept, wmark;
 	bool ret = false;
 
-	if (!has_unaccepted_memory())
+	if (list_empty(&zone->unaccepted_pages))
 		return false;
 
-	if (list_empty(&zone->unaccepted_pages))
+	/* Bailout, since try_to_accept_memory_one() needs to take a lock */
+	if (alloc_flags & ALLOC_TRYLOCK)
 		return false;
 
 	wmark = promo_wmark_pages(zone);
@@ -7265,22 +7282,17 @@ static bool __free_unaccepted(struct page *page)
 {
 	struct zone *zone = page_zone(page);
 	unsigned long flags;
-	bool first = false;
 
 	if (!lazy_accept)
 		return false;
 
 	spin_lock_irqsave(&zone->lock, flags);
-	first = list_empty(&zone->unaccepted_pages);
 	list_add_tail(&page->lru, &zone->unaccepted_pages);
 	account_freepages(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
 	__mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES);
 	__SetPageUnaccepted(page);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
-	if (first)
-		static_branch_inc(&zones_with_unaccepted_pages);
-
 	return true;
 }
 
@@ -7291,7 +7303,8 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order)
 	return false;
 }
 
-static bool cond_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+			       int alloc_flags)
 {
 	return false;
 }
@@ -7362,11 +7375,6 @@ struct page *try_alloc_pages_noprof(int nid, unsigned int order)
 	if (!pcp_allowed_order(order))
 		return NULL;
 
-#ifdef CONFIG_UNACCEPTED_MEMORY
-	/* Bailout, since try_to_accept_memory_one() needs to take a lock */
-	if (has_unaccepted_memory())
-		return NULL;
-#endif
 	/* Bailout, since _deferred_grow_zone() needs to take a lock */
 	if (deferred_pages_enabled())
 		return NULL;
diff --git a/mm/slub.c b/mm/slub.c
index b46f87662e71..be8b09e09d30 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1973,6 +1973,11 @@ static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
 #define OBJCGS_CLEAR_MASK	(__GFP_DMA | __GFP_RECLAIMABLE | \
 				__GFP_ACCOUNT | __GFP_NOFAIL)
 
+static inline void init_slab_obj_exts(struct slab *slab)
+{
+	slab->obj_exts = 0;
+}
+
 int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
 		        gfp_t gfp, bool new_slab)
 {
@@ -2023,8 +2028,7 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
 	return 0;
 }
 
-/* Should be called only if mem_alloc_profiling_enabled() */
-static noinline void free_slab_obj_exts(struct slab *slab)
+static inline void free_slab_obj_exts(struct slab *slab)
 {
 	struct slabobj_ext *obj_exts;
 
@@ -2044,20 +2048,12 @@ static noinline void free_slab_obj_exts(struct slab *slab)
 	slab->obj_exts = 0;
 }
 
-static inline bool need_slab_obj_ext(void)
-{
-	if (mem_alloc_profiling_enabled())
-		return true;
+#else /* CONFIG_SLAB_OBJ_EXT */
 
-	/*
-	 * CONFIG_MEMCG creates vector of obj_cgroup objects conditionally
-	 * inside memcg_slab_post_alloc_hook. No other users for now.
-	 */
-	return false;
+static inline void init_slab_obj_exts(struct slab *slab)
+{
 }
 
-#else /* CONFIG_SLAB_OBJ_EXT */
-
 static int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
 			       gfp_t gfp, bool new_slab)
 {
@@ -2068,11 +2064,6 @@ static inline void free_slab_obj_exts(struct slab *slab)
 {
 }
 
-static inline bool need_slab_obj_ext(void)
-{
-	return false;
-}
-
 #endif /* CONFIG_SLAB_OBJ_EXT */
 
 #ifdef CONFIG_MEM_ALLOC_PROFILING
@@ -2120,7 +2111,7 @@ __alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
 static inline void
 alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
 {
-	if (need_slab_obj_ext())
+	if (mem_alloc_profiling_enabled())
 		__alloc_tagging_slab_alloc_hook(s, object, flags);
 }
 
@@ -2592,8 +2583,12 @@ static __always_inline void account_slab(struct slab *slab, int order,
 static __always_inline void unaccount_slab(struct slab *slab, int order,
 					   struct kmem_cache *s)
 {
-	if (memcg_kmem_online() || need_slab_obj_ext())
-		free_slab_obj_exts(slab);
+	/*
+	 * The slab object extensions should now be freed regardless of
+	 * whether mem_alloc_profiling_enabled() or not because profiling
+	 * might have been disabled after slab->obj_exts got allocated.
+	 */
+	free_slab_obj_exts(slab);
 
 	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
 			    -(PAGE_SIZE << order));
@@ -2637,6 +2632,7 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	slab->objects = oo_objects(oo);
 	slab->inuse = 0;
 	slab->frozen = 0;
+	init_slab_obj_exts(slab);
 
 	account_slab(slab, oo_order(oo), s, flags);
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2eff8b51a945..412ccd6543b3 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1272,13 +1272,22 @@ int folio_alloc_swap(struct folio *folio, gfp_t gfp)
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);
 
-	/*
-	 * Should not even be attempting large allocations when huge
-	 * page swap is disabled. Warn and fail the allocation.
-	 */
-	if (order && (!IS_ENABLED(CONFIG_THP_SWAP) || size > SWAPFILE_CLUSTER)) {
-		VM_WARN_ON_ONCE(1);
-		return -EINVAL;
+	if (order) {
+		/*
+		 * Reject large allocation when THP_SWAP is disabled,
+		 * the caller should split the folio and try again.
+		 */
+		if (!IS_ENABLED(CONFIG_THP_SWAP))
+			return -EAGAIN;
+
+		/*
+		 * Allocation size should never exceed cluster size
+		 * (HPAGE_PMD_SIZE).
+		 */
+		if (size > SWAPFILE_CLUSTER) {
+			VM_WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
 	}
 
 	local_lock(&percpu_swap_cluster.lock);
@@ -3323,6 +3332,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	}
 
 	/*
+	 * The swap subsystem needs a major overhaul to support this.
+	 * It doesn't work yet so just disable it for now.
+	 */
+	if (mapping_min_folio_order(mapping) > 0) {
+		error = -EINVAL;
+		goto bad_swap_unlock_inode;
+	}
+
+	/*
 	 * Read the swap header.
 	 */
 	if (!mapping->a_ops->read_folio) {
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index fbf2cf62ab9f..e0db855c89b4 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1064,8 +1064,13 @@ static int move_present_pte(struct mm_struct *mm,
 	src_folio->index = linear_page_index(dst_vma, dst_addr);
 
 	orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot);
-	/* Follow mremap() behavior and treat the entry dirty after the move */
-	orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma);
+	/* Set soft dirty bit so userspace can notice the pte was moved */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	orig_dst_pte = pte_mksoft_dirty(orig_dst_pte);
+#endif
+	if (pte_dirty(orig_src_pte))
+		orig_dst_pte = pte_mkdirty(orig_dst_pte);
+	orig_dst_pte = pte_mkwrite(orig_dst_pte, dst_vma);
 
 	set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte);
 out:
@@ -1100,6 +1105,9 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 	}
 
 	orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte);
+#endif
 	set_pte_at(mm, dst_addr, dst_pte, orig_src_pte);
 	double_pt_unlock(dst_ptl, src_ptl);
 
@@ -1902,6 +1910,14 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi,
 					     unsigned long end)
 {
 	struct vm_area_struct *ret;
+	bool give_up_on_oom = false;
+
+	/*
+	 * If we are modifying only and not splitting, just give up on the merge
+	 * if OOM prevents us from merging successfully.
+	 */
+	if (start == vma->vm_start && end == vma->vm_end)
+		give_up_on_oom = true;
 
 	/* Reset ptes for the whole vma range if wr-protected */
 	if (userfaultfd_wp(vma))
@@ -1909,7 +1925,7 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi,
 
 	ret = vma_modify_flags_uffd(vmi, prev, vma, start, end,
 				    vma->vm_flags & ~__VM_UFFD_FLAGS,
-				    NULL_VM_UFFD_CTX);
+				    NULL_VM_UFFD_CTX, give_up_on_oom);
 
 	/*
 	 * In the vma_merge() successful mprotect-like case 8:
@@ -1960,7 +1976,8 @@ int userfaultfd_register_range(struct userfaultfd_ctx *ctx,
 		new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags;
 		vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end,
 					    new_flags,
-					    (struct vm_userfaultfd_ctx){ctx});
+					    (struct vm_userfaultfd_ctx){ctx},
+					    /* give_up_on_oom = */false);
 		if (IS_ERR(vma))
 			return PTR_ERR(vma);
 
diff --git a/mm/vma.c b/mm/vma.c
index 5cdc5612bfc1..839d12f02c88 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -666,6 +666,9 @@ static void vmg_adjust_set_range(struct vma_merge_struct *vmg)
 /*
  * Actually perform the VMA merge operation.
  *
+ * IMPORTANT: We guarantee that, should vmg->give_up_on_oom is set, to not
+ * modify any VMAs or cause inconsistent state should an OOM condition arise.
+ *
  * Returns 0 on success, or an error value on failure.
  */
 static int commit_merge(struct vma_merge_struct *vmg)
@@ -685,6 +688,12 @@ static int commit_merge(struct vma_merge_struct *vmg)
 
 	init_multi_vma_prep(&vp, vma, vmg);
 
+	/*
+	 * If vmg->give_up_on_oom is set, we're safe, because we don't actually
+	 * manipulate any VMAs until we succeed at preallocation.
+	 *
+	 * Past this point, we will not return an error.
+	 */
 	if (vma_iter_prealloc(vmg->vmi, vma))
 		return -ENOMEM;
 
@@ -915,7 +924,13 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
 		if (anon_dup)
 			unlink_anon_vmas(anon_dup);
 
-		vmg->state = VMA_MERGE_ERROR_NOMEM;
+		/*
+		 * We've cleaned up any cloned anon_vma's, no VMAs have been
+		 * modified, no harm no foul if the user requests that we not
+		 * report this and just give up, leaving the VMAs unmerged.
+		 */
+		if (!vmg->give_up_on_oom)
+			vmg->state = VMA_MERGE_ERROR_NOMEM;
 		return NULL;
 	}
 
@@ -926,7 +941,15 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
 abort:
 	vma_iter_set(vmg->vmi, start);
 	vma_iter_load(vmg->vmi);
-	vmg->state = VMA_MERGE_ERROR_NOMEM;
+
+	/*
+	 * This means we have failed to clone anon_vma's correctly, but no
+	 * actual changes to VMAs have occurred, so no harm no foul - if the
+	 * user doesn't want this reported and instead just wants to give up on
+	 * the merge, allow it.
+	 */
+	if (!vmg->give_up_on_oom)
+		vmg->state = VMA_MERGE_ERROR_NOMEM;
 	return NULL;
 }
 
@@ -1068,6 +1091,10 @@ int vma_expand(struct vma_merge_struct *vmg)
 		/* This should already have been checked by this point. */
 		VM_WARN_ON_VMG(!can_merge_remove_vma(next), vmg);
 		vma_start_write(next);
+		/*
+		 * In this case we don't report OOM, so vmg->give_up_on_mm is
+		 * safe.
+		 */
 		ret = dup_anon_vma(middle, next, &anon_dup);
 		if (ret)
 			return ret;
@@ -1090,9 +1117,15 @@ int vma_expand(struct vma_merge_struct *vmg)
 	return 0;
 
 nomem:
-	vmg->state = VMA_MERGE_ERROR_NOMEM;
 	if (anon_dup)
 		unlink_anon_vmas(anon_dup);
+	/*
+	 * If the user requests that we just give upon OOM, we are safe to do so
+	 * here, as commit merge provides this contract to us. Nothing has been
+	 * changed - no harm no foul, just don't report it.
+	 */
+	if (!vmg->give_up_on_oom)
+		vmg->state = VMA_MERGE_ERROR_NOMEM;
 	return -ENOMEM;
 }
 
@@ -1534,6 +1567,13 @@ static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg)
 	if (vmg_nomem(vmg))
 		return ERR_PTR(-ENOMEM);
 
+	/*
+	 * Split can fail for reasons other than OOM, so if the user requests
+	 * this it's probably a mistake.
+	 */
+	VM_WARN_ON(vmg->give_up_on_oom &&
+		   (vma->vm_start != start || vma->vm_end != end));
+
 	/* Split any preceding portion of the VMA. */
 	if (vma->vm_start < start) {
 		int err = split_vma(vmg->vmi, vma, start, 1);
@@ -1602,12 +1642,15 @@ struct vm_area_struct
 		       struct vm_area_struct *vma,
 		       unsigned long start, unsigned long end,
 		       unsigned long new_flags,
-		       struct vm_userfaultfd_ctx new_ctx)
+		       struct vm_userfaultfd_ctx new_ctx,
+		       bool give_up_on_oom)
 {
 	VMG_VMA_STATE(vmg, vmi, prev, vma, start, end);
 
 	vmg.flags = new_flags;
 	vmg.uffd_ctx = new_ctx;
+	if (give_up_on_oom)
+		vmg.give_up_on_oom = true;
 
 	return vma_modify(&vmg);
 }
diff --git a/mm/vma.h b/mm/vma.h
index 7356ca5a22d3..149926e8a6d1 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -114,6 +114,12 @@ struct vma_merge_struct {
 	 */
 	bool just_expand :1;
 
+	/*
+	 * If a merge is possible, but an OOM error occurs, give up and don't
+	 * execute the merge, returning NULL.
+	 */
+	bool give_up_on_oom :1;
+
 	/* Internal flags set during merge process: */
 
 	/*
@@ -255,7 +261,8 @@ __must_check struct vm_area_struct
 		       struct vm_area_struct *vma,
 		       unsigned long start, unsigned long end,
 		       unsigned long new_flags,
-		       struct vm_userfaultfd_ctx new_ctx);
+		       struct vm_userfaultfd_ctx new_ctx,
+		       bool give_up_on_oom);
 
 __must_check struct vm_area_struct
 *vma_merge_new_range(struct vma_merge_struct *vmg);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3ed720a787ec..2d7511654831 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1940,7 +1940,7 @@ static inline void setup_vmalloc_vm(struct vm_struct *vm,
 {
 	vm->flags = flags;
 	vm->addr = (void *)va->va_start;
-	vm->size = va_size(va);
+	vm->size = vm->requested_size = va_size(va);
 	vm->caller = caller;
 	va->vm = vm;
 }
@@ -3133,6 +3133,7 @@ struct vm_struct *__get_vm_area_node(unsigned long size,
 
 	area->flags = flags;
 	area->caller = caller;
+	area->requested_size = requested_size;
 
 	va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area);
 	if (IS_ERR(va)) {
@@ -4063,6 +4064,8 @@ EXPORT_SYMBOL(vzalloc_node_noprof);
  */
 void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 {
+	struct vm_struct *vm = NULL;
+	size_t alloced_size = 0;
 	size_t old_size = 0;
 	void *n;
 
@@ -4072,15 +4075,17 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 	}
 
 	if (p) {
-		struct vm_struct *vm;
-
 		vm = find_vm_area(p);
 		if (unlikely(!vm)) {
 			WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p);
 			return NULL;
 		}
 
-		old_size = get_vm_area_size(vm);
+		alloced_size = get_vm_area_size(vm);
+		old_size = vm->requested_size;
+		if (WARN(alloced_size < old_size,
+			 "vrealloc() has mismatched area vs requested sizes (%p)\n", p))
+			return NULL;
 	}
 
 	/*
@@ -4088,14 +4093,26 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 	 * would be a good heuristic for when to shrink the vm_area?
 	 */
 	if (size <= old_size) {
-		/* Zero out spare memory. */
-		if (want_init_on_alloc(flags))
+		/* Zero out "freed" memory. */
+		if (want_init_on_free())
 			memset((void *)p + size, 0, old_size - size);
+		vm->requested_size = size;
 		kasan_poison_vmalloc(p + size, old_size - size);
-		kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL);
 		return (void *)p;
 	}
 
+	/*
+	 * We already have the bytes available in the allocation; use them.
+	 */
+	if (size <= alloced_size) {
+		kasan_unpoison_vmalloc(p + old_size, size - old_size,
+				       KASAN_VMALLOC_PROT_NORMAL);
+		/* Zero out "alloced" memory. */
+		if (want_init_on_alloc(flags))
+			memset((void *)p + old_size, 0, size - old_size);
+		vm->requested_size = size;
+	}
+
 	/* TODO: Grow the vm_area, i.e. allocate and map additional pages. */
 	n = __vmalloc_noprof(size, flags);
 	if (!n)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b620d74b0f66..3783e45bfc92 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6736,6 +6736,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
 	 * meet watermarks.
 	 */
 	for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) {
+		enum zone_stat_item item;
 		unsigned long free_pages;
 
 		if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
@@ -6746,11 +6747,33 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
 		/*
 		 * In defrag_mode, watermarks must be met in whole
 		 * blocks to avoid polluting allocator fallbacks.
+		 *
+		 * However, kswapd usually cannot accomplish this on
+		 * its own and needs kcompactd support. Once it's
+		 * reclaimed a compaction gap, and kswapd_shrink_node
+		 * has dropped order, simply ensure there are enough
+		 * base pages for compaction, wake kcompactd & sleep.
 		 */
-		if (defrag_mode)
-			free_pages = zone_page_state(zone, NR_FREE_PAGES_BLOCKS);
+		if (defrag_mode && order)
+			item = NR_FREE_PAGES_BLOCKS;
 		else
-			free_pages = zone_page_state(zone, NR_FREE_PAGES);
+			item = NR_FREE_PAGES;
+
+		/*
+		 * When there is a high number of CPUs in the system,
+		 * the cumulative error from the vmstat per-cpu cache
+		 * can blur the line between the watermarks. In that
+		 * case, be safe and get an accurate snapshot.
+		 *
+		 * TODO: NR_FREE_PAGES_BLOCKS moves in steps of
+		 * pageblock_nr_pages, while the vmstat pcp threshold
+		 * is limited to 125. On many configurations that
+		 * counter won't actually be per-cpu cached. But keep
+		 * things simple for now; revisit when somebody cares.
+		 */
+		free_pages = zone_page_state(zone, item);
+		if (zone->percpu_drift_mark && free_pages < zone->percpu_drift_mark)
+			free_pages = zone_page_state_snapshot(zone, item);
 
 		if (__zone_watermark_ok(zone, order, mark, highest_zoneidx,
 					0, free_pages))
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 961b270f023c..d14a7e317ac8 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1243,19 +1243,19 @@ void zs_obj_write(struct zs_pool *pool, unsigned long handle,
 	class = zspage_class(pool, zspage);
 	off = offset_in_page(class->size * obj_idx);
 
-	if (off + class->size <= PAGE_SIZE) {
+	if (!ZsHugePage(zspage))
+		off += ZS_HANDLE_SIZE;
+
+	if (off + mem_len <= PAGE_SIZE) {
 		/* this object is contained entirely within a page */
 		void *dst = kmap_local_zpdesc(zpdesc);
 
-		if (!ZsHugePage(zspage))
-			off += ZS_HANDLE_SIZE;
 		memcpy(dst + off, handle_mem, mem_len);
 		kunmap_local(dst);
 	} else {
 		/* this object spans two pages */
 		size_t sizes[2];
 
-		off += ZS_HANDLE_SIZE;
 		sizes[0] = PAGE_SIZE - off;
 		sizes[1] = mem_len - sizes[0];
 
diff --git a/net/802/Makefile b/net/802/Makefile
index bfed80221b8b..99abc29d537c 100644
--- a/net/802/Makefile
+++ b/net/802/Makefile
@@ -3,12 +3,11 @@
 # Makefile for the Linux 802.x protocol layers.
 #
 
-# Check the p8022 selections against net/core/Makefile.
-obj-$(CONFIG_LLC)	+= p8022.o psnap.o
+obj-$(CONFIG_LLC)	+= psnap.o
 obj-$(CONFIG_NET_FC)	+=                 fc.o
 obj-$(CONFIG_FDDI)	+=                 fddi.o
 obj-$(CONFIG_HIPPI)	+=                 hippi.o
-obj-$(CONFIG_ATALK)	+= p8022.o psnap.o
+obj-$(CONFIG_ATALK)	+= psnap.o
 obj-$(CONFIG_STP)	+= stp.o
 obj-$(CONFIG_GARP)	+= garp.o
 obj-$(CONFIG_MRP)	+= mrp.o
diff --git a/net/802/p8022.c b/net/802/p8022.c
deleted file mode 100644
index 78c25168d7c9..000000000000
--- a/net/802/p8022.c
+++ /dev/null
@@ -1,64 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *	NET3:	Support for 802.2 demultiplexing off Ethernet
- *
- *		Demultiplex 802.2 encoded protocols. We match the entry by the
- *		SSAP/DSAP pair and then deliver to the registered datalink that
- *		matches. The control byte is ignored and handling of such items
- *		is up to the routine passed the frame.
- *
- *		Unlike the 802.3 datalink we have a list of 802.2 entries as
- *		there are multiple protocols to demux. The list is currently
- *		short (3 or 4 entries at most). The current demux assumes this.
- */
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <linux/slab.h>
-#include <net/datalink.h>
-#include <linux/mm.h>
-#include <linux/in.h>
-#include <linux/init.h>
-#include <net/llc.h>
-#include <net/p8022.h>
-
-static int p8022_request(struct datalink_proto *dl, struct sk_buff *skb,
-			 const unsigned char *dest)
-{
-	llc_build_and_send_ui_pkt(dl->sap, skb, dest, dl->sap->laddr.lsap);
-	return 0;
-}
-
-struct datalink_proto *register_8022_client(unsigned char type,
-					    int (*func)(struct sk_buff *skb,
-							struct net_device *dev,
-							struct packet_type *pt,
-							struct net_device *orig_dev))
-{
-	struct datalink_proto *proto;
-
-	proto = kmalloc(sizeof(*proto), GFP_ATOMIC);
-	if (proto) {
-		proto->type[0]		= type;
-		proto->header_length	= 3;
-		proto->request		= p8022_request;
-		proto->sap = llc_sap_open(type, func);
-		if (!proto->sap) {
-			kfree(proto);
-			proto = NULL;
-		}
-	}
-	return proto;
-}
-
-void unregister_8022_client(struct datalink_proto *proto)
-{
-	llc_sap_put(proto->sap);
-	kfree(proto);
-}
-
-EXPORT_SYMBOL(register_8022_client);
-EXPORT_SYMBOL(unregister_8022_client);
-
-MODULE_DESCRIPTION("Support for 802.2 demultiplexing off Ethernet");
-MODULE_LICENSE("GPL");
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 41be38264493..06908e37c3d9 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -23,7 +23,6 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/rculist.h>
-#include <net/p8022.h>
 #include <net/arp.h>
 #include <linux/rtnetlink.h>
 #include <linux/notifier.h>
diff --git a/net/Kconfig b/net/Kconfig
index c3fca69a7c83..5b71a52987d3 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -75,6 +75,10 @@ config NET_DEVMEM
 config NET_SHAPER
 	bool
 
+config NET_CRC32C
+	bool
+	select CRC32
+
 menu "Networking options"
 
 source "net/packet/Kconfig"
@@ -245,7 +249,6 @@ source "net/bridge/netfilter/Kconfig"
 
 endif
 
-source "net/dccp/Kconfig"
 source "net/sctp/Kconfig"
 source "net/rds/Kconfig"
 source "net/tipc/Kconfig"
diff --git a/net/Makefile b/net/Makefile
index 60ed5190eda8..aac960c41db6 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -42,7 +42,6 @@ obj-$(CONFIG_PHONET)		+= phonet/
 ifneq ($(CONFIG_VLAN_8021Q),)
 obj-y				+= 8021q/
 endif
-obj-$(CONFIG_IP_DCCP)		+= dccp/
 obj-$(CONFIG_IP_SCTP)		+= sctp/
 obj-$(CONFIG_RDS)		+= rds/
 obj-$(CONFIG_WIRELESS)		+= wireless/
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index f145f9662653..558d39dffc23 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -506,28 +506,32 @@ batadv_hardif_is_iface_up(const struct batadv_hard_iface *hard_iface)
 	return false;
 }
 
-static void batadv_check_known_mac_addr(const struct net_device *net_dev)
+static void batadv_check_known_mac_addr(const struct batadv_hard_iface *hard_iface)
 {
-	const struct batadv_hard_iface *hard_iface;
+	const struct net_device *mesh_iface = hard_iface->mesh_iface;
+	const struct batadv_hard_iface *tmp_hard_iface;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->if_status != BATADV_IF_ACTIVE &&
-		    hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)
+	if (!mesh_iface)
+		return;
+
+	list_for_each_entry(tmp_hard_iface, &batadv_hardif_list, list) {
+		if (tmp_hard_iface == hard_iface)
+			continue;
+
+		if (tmp_hard_iface->mesh_iface != mesh_iface)
 			continue;
 
-		if (hard_iface->net_dev == net_dev)
+		if (tmp_hard_iface->if_status == BATADV_IF_NOT_IN_USE)
 			continue;
 
-		if (!batadv_compare_eth(hard_iface->net_dev->dev_addr,
-					net_dev->dev_addr))
+		if (!batadv_compare_eth(tmp_hard_iface->net_dev->dev_addr,
+					hard_iface->net_dev->dev_addr))
 			continue;
 
 		pr_warn("The newly added mac address (%pM) already exists on: %s\n",
-			net_dev->dev_addr, hard_iface->net_dev->name);
+			hard_iface->net_dev->dev_addr, tmp_hard_iface->net_dev->name);
 		pr_warn("It is strongly recommended to keep mac addresses unique to avoid problems!\n");
 	}
-	rcu_read_unlock();
 }
 
 /**
@@ -725,7 +729,6 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 
 	kref_get(&hard_iface->refcount);
 
-	dev_hold(mesh_iface);
 	netdev_hold(mesh_iface, &hard_iface->meshif_dev_tracker, GFP_ATOMIC);
 	hard_iface->mesh_iface = mesh_iface;
 	bat_priv = netdev_priv(hard_iface->mesh_iface);
@@ -764,6 +767,8 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 			    hard_iface->net_dev->name, hardif_mtu,
 			    required_mtu);
 
+	batadv_check_known_mac_addr(hard_iface);
+
 	if (batadv_hardif_is_iface_up(hard_iface))
 		batadv_hardif_activate_interface(hard_iface);
 	else
@@ -902,7 +907,6 @@ batadv_hardif_add_interface(struct net_device *net_dev)
 
 	batadv_v_hardif_init(hard_iface);
 
-	batadv_check_known_mac_addr(hard_iface->net_dev);
 	kref_get(&hard_iface->refcount);
 	list_add_tail_rcu(&hard_iface->list, &batadv_hardif_list);
 	batadv_hardif_generation++;
@@ -989,7 +993,7 @@ static int batadv_hard_if_event(struct notifier_block *this,
 		if (hard_iface->if_status == BATADV_IF_NOT_IN_USE)
 			goto hardif_put;
 
-		batadv_check_known_mac_addr(hard_iface->net_dev);
+		batadv_check_known_mac_addr(hard_iface);
 
 		bat_priv = netdev_priv(hard_iface->mesh_iface);
 		bat_priv->algo_ops->iface.update_mac(hard_iface);
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index a08132888a3d..c0bc75513355 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -11,7 +11,7 @@
 #include <linux/build_bug.h>
 #include <linux/byteorder/generic.h>
 #include <linux/container_of.h>
-#include <linux/crc32c.h>
+#include <linux/crc32.h>
 #include <linux/device.h>
 #include <linux/errno.h>
 #include <linux/gfp.h>
@@ -69,8 +69,6 @@ unsigned int batadv_hardif_generation;
 static int (*batadv_rx_handler[256])(struct sk_buff *skb,
 				     struct batadv_hard_iface *recv_if);
 
-unsigned char batadv_broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
-
 struct workqueue_struct *batadv_event_workqueue;
 
 static void batadv_recv_handler_init(void);
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 67af435ee04e..692109be2210 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -13,7 +13,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2025.1"
+#define BATADV_SOURCE_VERSION "2025.2"
 #endif
 
 /* B.A.T.M.A.N. parameters */
@@ -235,7 +235,6 @@ static inline int batadv_print_vid(unsigned short vid)
 extern struct list_head batadv_hardif_list;
 extern unsigned int batadv_hardif_generation;
 
-extern unsigned char batadv_broadcast_addr[];
 extern struct workqueue_struct *batadv_event_workqueue;
 
 int batadv_mesh_init(struct net_device *mesh_iface);
diff --git a/net/batman-adv/mesh-interface.c b/net/batman-adv/mesh-interface.c
index 59e7b5aacbc9..5bbc366f974d 100644
--- a/net/batman-adv/mesh-interface.c
+++ b/net/batman-adv/mesh-interface.c
@@ -36,7 +36,6 @@
 #include <linux/stddef.h>
 #include <linux/string.h>
 #include <linux/types.h>
-#include <net/net_namespace.h>
 #include <net/netlink.h>
 #include <uapi/linux/batadv_packet.h>
 #include <uapi/linux/batman_adv.h>
@@ -77,18 +76,6 @@ int batadv_skb_head_push(struct sk_buff *skb, unsigned int len)
 	return 0;
 }
 
-static int batadv_interface_open(struct net_device *dev)
-{
-	netif_start_queue(dev);
-	return 0;
-}
-
-static int batadv_interface_release(struct net_device *dev)
-{
-	netif_stop_queue(dev);
-	return 0;
-}
-
 /**
  * batadv_sum_counter() - Sum the cpu-local counters for index 'idx'
  * @bat_priv: the bat priv with all the mesh interface information
@@ -890,8 +877,6 @@ out:
 
 static const struct net_device_ops batadv_netdev_ops = {
 	.ndo_init = batadv_meshif_init_late,
-	.ndo_open = batadv_interface_open,
-	.ndo_stop = batadv_interface_release,
 	.ndo_get_stats = batadv_interface_stats,
 	.ndo_vlan_rx_add_vid = batadv_interface_add_vid,
 	.ndo_vlan_rx_kill_vid = batadv_interface_kill_vid,
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 735ac8077821..9d72f4f15b3d 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -124,7 +124,9 @@ send_skb_err:
 int batadv_send_broadcast_skb(struct sk_buff *skb,
 			      struct batadv_hard_iface *hard_iface)
 {
-	return batadv_send_skb_packet(skb, hard_iface, batadv_broadcast_addr);
+	static const u8 broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+
+	return batadv_send_skb_packet(skb, hard_iface, broadcast_addr);
 }
 
 /**
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 4a3165920de1..8d0e04e770cb 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -14,7 +14,7 @@
 #include <linux/cache.h>
 #include <linux/compiler.h>
 #include <linux/container_of.h>
-#include <linux/crc32c.h>
+#include <linux/crc32.h>
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/etherdevice.h>
diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile
index 5a3835b7dfcd..a7eede7616d8 100644
--- a/net/bluetooth/Makefile
+++ b/net/bluetooth/Makefile
@@ -14,7 +14,8 @@ bluetooth_6lowpan-y := 6lowpan.o
 
 bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \
 	hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o lib.o \
-	ecdh_helper.o mgmt_util.o mgmt_config.o hci_codec.o eir.o hci_sync.o
+	ecdh_helper.o mgmt_util.o mgmt_config.o hci_codec.o eir.o hci_sync.o \
+	hci_drv.o
 
 bluetooth-$(CONFIG_DEV_COREDUMP) += coredump.o
 
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 0b4d0a8bd361..6ad2f72f53f4 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -34,6 +34,9 @@
 #include <net/bluetooth/bluetooth.h>
 #include <linux/proc_fs.h>
 
+#include <linux/ethtool.h>
+#include <linux/sockios.h>
+
 #include "leds.h"
 #include "selftest.h"
 
@@ -563,6 +566,86 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock,
 }
 EXPORT_SYMBOL(bt_sock_poll);
 
+static int bt_ethtool_get_ts_info(struct sock *sk, unsigned int index,
+				  void __user *useraddr)
+{
+	struct ethtool_ts_info info;
+	struct kernel_ethtool_ts_info ts_info = {};
+	int ret;
+
+	ret = hci_ethtool_ts_info(index, sk->sk_protocol, &ts_info);
+	if (ret == -ENODEV)
+		return ret;
+	else if (ret < 0)
+		return -EIO;
+
+	memset(&info, 0, sizeof(info));
+
+	info.cmd = ETHTOOL_GET_TS_INFO;
+	info.so_timestamping = ts_info.so_timestamping;
+	info.phc_index = ts_info.phc_index;
+	info.tx_types = ts_info.tx_types;
+	info.rx_filters = ts_info.rx_filters;
+
+	if (copy_to_user(useraddr, &info, sizeof(info)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int bt_ethtool(struct sock *sk, const struct ifreq *ifr,
+		      void __user *useraddr)
+{
+	unsigned int index;
+	u32 ethcmd;
+	int n;
+
+	if (copy_from_user(&ethcmd, useraddr, sizeof(ethcmd)))
+		return -EFAULT;
+
+	if (sscanf(ifr->ifr_name, "hci%u%n", &index, &n) != 1 ||
+	    n != strlen(ifr->ifr_name))
+		return -ENODEV;
+
+	switch (ethcmd) {
+	case ETHTOOL_GET_TS_INFO:
+		return bt_ethtool_get_ts_info(sk, index, useraddr);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int bt_dev_ioctl(struct socket *sock, unsigned int cmd, void __user *arg)
+{
+	struct sock *sk = sock->sk;
+	struct ifreq ifr = {};
+	void __user *data;
+	char *colon;
+	int ret = -ENOIOCTLCMD;
+
+	if (get_user_ifreq(&ifr, &data, arg))
+		return -EFAULT;
+
+	ifr.ifr_name[IFNAMSIZ - 1] = 0;
+	colon = strchr(ifr.ifr_name, ':');
+	if (colon)
+		*colon = 0;
+
+	switch (cmd) {
+	case SIOCETHTOOL:
+		ret = bt_ethtool(sk, &ifr, data);
+		break;
+	}
+
+	if (colon)
+		*colon = ':';
+
+	if (put_user_ifreq(&ifr, arg))
+		return -EFAULT;
+
+	return ret;
+}
+
 int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
 	struct sock *sk = sock->sk;
@@ -595,6 +678,10 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		err = put_user(amount, (int __user *)arg);
 		break;
 
+	case SIOCETHTOOL:
+		err = bt_dev_ioctl(sock, cmd, (void __user *)arg);
+		break;
+
 	default:
 		err = -ENOIOCTLCMD;
 		break;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 95972fd4c784..99efeed6a766 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -785,7 +785,7 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *c
 	d->sync_handle = conn->sync_handle;
 
 	if (test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags)) {
-		hci_conn_hash_list_flag(hdev, find_bis, ISO_LINK,
+		hci_conn_hash_list_flag(hdev, find_bis, BIS_LINK,
 					HCI_CONN_PA_SYNC, d);
 
 		if (!d->count)
@@ -795,7 +795,7 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *c
 	}
 
 	if (test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags)) {
-		hci_conn_hash_list_flag(hdev, find_bis, ISO_LINK,
+		hci_conn_hash_list_flag(hdev, find_bis, BIS_LINK,
 					HCI_CONN_BIG_SYNC, d);
 
 		if (!d->count)
@@ -885,9 +885,11 @@ static void cis_cleanup(struct hci_conn *conn)
 	/* Check if ISO connection is a CIS and remove CIG if there are
 	 * no other connections using it.
 	 */
-	hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_BOUND, &d);
-	hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_CONNECT, &d);
-	hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_CONNECTED, &d);
+	hci_conn_hash_list_state(hdev, find_cis, CIS_LINK, BT_BOUND, &d);
+	hci_conn_hash_list_state(hdev, find_cis, CIS_LINK, BT_CONNECT,
+				 &d);
+	hci_conn_hash_list_state(hdev, find_cis, CIS_LINK, BT_CONNECTED,
+				 &d);
 	if (d.count)
 		return;
 
@@ -910,7 +912,8 @@ static struct hci_conn *__hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t
 		if (!hdev->acl_mtu)
 			return ERR_PTR(-ECONNREFUSED);
 		break;
-	case ISO_LINK:
+	case CIS_LINK:
+	case BIS_LINK:
 		if (hdev->iso_mtu)
 			/* Dedicated ISO Buffer exists */
 			break;
@@ -974,7 +977,8 @@ static struct hci_conn *__hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t
 		hci_copy_identity_address(hdev, &conn->src, &conn->src_type);
 		conn->mtu = hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu;
 		break;
-	case ISO_LINK:
+	case CIS_LINK:
+	case BIS_LINK:
 		/* conn->src should reflect the local identity address */
 		hci_copy_identity_address(hdev, &conn->src, &conn->src_type);
 
@@ -1071,7 +1075,8 @@ static void hci_conn_cleanup_child(struct hci_conn *conn, u8 reason)
 		if (HCI_CONN_HANDLE_UNSET(conn->handle))
 			hci_conn_failed(conn, reason);
 		break;
-	case ISO_LINK:
+	case CIS_LINK:
+	case BIS_LINK:
 		if ((conn->state != BT_CONNECTED &&
 		    !test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) ||
 		    test_bit(HCI_CONN_BIG_CREATED, &conn->flags))
@@ -1146,7 +1151,8 @@ void hci_conn_del(struct hci_conn *conn)
 			hdev->acl_cnt += conn->sent;
 	} else {
 		/* Unacked ISO frames */
-		if (conn->type == ISO_LINK) {
+		if (conn->type == CIS_LINK ||
+		    conn->type == BIS_LINK) {
 			if (hdev->iso_pkts)
 				hdev->iso_cnt += conn->sent;
 			else if (hdev->le_pkts)
@@ -1532,7 +1538,7 @@ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst,
 		     memcmp(conn->le_per_adv_data, base, base_len)))
 		return ERR_PTR(-EADDRINUSE);
 
-	conn = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_MASTER);
+	conn = hci_conn_add_unset(hdev, BIS_LINK, dst, HCI_ROLE_MASTER);
 	if (IS_ERR(conn))
 		return conn;
 
@@ -1740,7 +1746,7 @@ static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos)
 	data.count = 0;
 
 	/* Create a BIS for each bound connection */
-	hci_conn_hash_list_state(hdev, bis_list, ISO_LINK,
+	hci_conn_hash_list_state(hdev, bis_list, BIS_LINK,
 				 BT_BOUND, &data);
 
 	cp.handle = qos->bcast.big;
@@ -1829,12 +1835,12 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos)
 		for (data.cig = 0x00; data.cig < 0xf0; data.cig++) {
 			data.count = 0;
 
-			hci_conn_hash_list_state(hdev, find_cis, ISO_LINK,
+			hci_conn_hash_list_state(hdev, find_cis, CIS_LINK,
 						 BT_CONNECT, &data);
 			if (data.count)
 				continue;
 
-			hci_conn_hash_list_state(hdev, find_cis, ISO_LINK,
+			hci_conn_hash_list_state(hdev, find_cis, CIS_LINK,
 						 BT_CONNECTED, &data);
 			if (!data.count)
 				break;
@@ -1884,7 +1890,8 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst,
 	cis = hci_conn_hash_lookup_cis(hdev, dst, dst_type, qos->ucast.cig,
 				       qos->ucast.cis);
 	if (!cis) {
-		cis = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_MASTER);
+		cis = hci_conn_add_unset(hdev, CIS_LINK, dst,
+					 HCI_ROLE_MASTER);
 		if (IS_ERR(cis))
 			return cis;
 		cis->cleanup = cis_cleanup;
@@ -1976,7 +1983,7 @@ bool hci_iso_setup_path(struct hci_conn *conn)
 
 int hci_conn_check_create_cis(struct hci_conn *conn)
 {
-	if (conn->type != ISO_LINK || !bacmp(&conn->dst, BDADDR_ANY))
+	if (conn->type != CIS_LINK)
 		return -EINVAL;
 
 	if (!conn->parent || conn->parent->state != BT_CONNECTED ||
@@ -2064,102 +2071,15 @@ static int create_big_sync(struct hci_dev *hdev, void *data)
 	return hci_le_create_big(conn, &conn->iso_qos);
 }
 
-static void create_pa_complete(struct hci_dev *hdev, void *data, int err)
-{
-	bt_dev_dbg(hdev, "");
-
-	if (err)
-		bt_dev_err(hdev, "Unable to create PA: %d", err);
-}
-
-static bool hci_conn_check_create_pa_sync(struct hci_conn *conn)
-{
-	if (conn->type != ISO_LINK || conn->sid == HCI_SID_INVALID)
-		return false;
-
-	return true;
-}
-
-static int create_pa_sync(struct hci_dev *hdev, void *data)
-{
-	struct hci_cp_le_pa_create_sync cp = {0};
-	struct hci_conn *conn;
-	int err = 0;
-
-	hci_dev_lock(hdev);
-
-	rcu_read_lock();
-
-	/* The spec allows only one pending LE Periodic Advertising Create
-	 * Sync command at a time. If the command is pending now, don't do
-	 * anything. We check for pending connections after each PA Sync
-	 * Established event.
-	 *
-	 * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
-	 * page 2493:
-	 *
-	 * If the Host issues this command when another HCI_LE_Periodic_
-	 * Advertising_Create_Sync command is pending, the Controller shall
-	 * return the error code Command Disallowed (0x0C).
-	 */
-	list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
-		if (test_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags))
-			goto unlock;
-	}
-
-	list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
-		if (hci_conn_check_create_pa_sync(conn)) {
-			struct bt_iso_qos *qos = &conn->iso_qos;
-
-			cp.options = qos->bcast.options;
-			cp.sid = conn->sid;
-			cp.addr_type = conn->dst_type;
-			bacpy(&cp.addr, &conn->dst);
-			cp.skip = cpu_to_le16(qos->bcast.skip);
-			cp.sync_timeout = cpu_to_le16(qos->bcast.sync_timeout);
-			cp.sync_cte_type = qos->bcast.sync_cte_type;
-
-			break;
-		}
-	}
-
-unlock:
-	rcu_read_unlock();
-
-	hci_dev_unlock(hdev);
-
-	if (bacmp(&cp.addr, BDADDR_ANY)) {
-		hci_dev_set_flag(hdev, HCI_PA_SYNC);
-		set_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);
-
-		err = __hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC,
-					    sizeof(cp), &cp, HCI_CMD_TIMEOUT);
-		if (!err)
-			err = hci_update_passive_scan_sync(hdev);
-
-		if (err) {
-			hci_dev_clear_flag(hdev, HCI_PA_SYNC);
-			clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);
-		}
-	}
-
-	return err;
-}
-
-int hci_pa_create_sync_pending(struct hci_dev *hdev)
-{
-	/* Queue start pa_create_sync and scan */
-	return hci_cmd_sync_queue(hdev, create_pa_sync,
-				  NULL, create_pa_complete);
-}
-
 struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst,
 				    __u8 dst_type, __u8 sid,
 				    struct bt_iso_qos *qos)
 {
 	struct hci_conn *conn;
 
-	conn = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_SLAVE);
+	bt_dev_dbg(hdev, "dst %pMR type %d sid %d", dst, dst_type, sid);
+
+	conn = hci_conn_add_unset(hdev, BIS_LINK, dst, HCI_ROLE_SLAVE);
 	if (IS_ERR(conn))
 		return conn;
 
@@ -2167,97 +2087,18 @@ struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst,
 	conn->dst_type = dst_type;
 	conn->sid = sid;
 	conn->state = BT_LISTEN;
+	conn->conn_timeout = msecs_to_jiffies(qos->bcast.sync_timeout * 10);
 
 	hci_conn_hold(conn);
 
-	hci_pa_create_sync_pending(hdev);
+	hci_connect_pa_sync(hdev, conn);
 
 	return conn;
 }
 
-static bool hci_conn_check_create_big_sync(struct hci_conn *conn)
-{
-	if (!conn->num_bis)
-		return false;
-
-	return true;
-}
-
-static void big_create_sync_complete(struct hci_dev *hdev, void *data, int err)
-{
-	bt_dev_dbg(hdev, "");
-
-	if (err)
-		bt_dev_err(hdev, "Unable to create BIG sync: %d", err);
-}
-
-static int big_create_sync(struct hci_dev *hdev, void *data)
-{
-	DEFINE_FLEX(struct hci_cp_le_big_create_sync, pdu, bis, num_bis, 0x11);
-	struct hci_conn *conn;
-
-	rcu_read_lock();
-
-	pdu->num_bis = 0;
-
-	/* The spec allows only one pending LE BIG Create Sync command at
-	 * a time. If the command is pending now, don't do anything. We
-	 * check for pending connections after each BIG Sync Established
-	 * event.
-	 *
-	 * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
-	 * page 2586:
-	 *
-	 * If the Host sends this command when the Controller is in the
-	 * process of synchronizing to any BIG, i.e. the HCI_LE_BIG_Sync_
-	 * Established event has not been generated, the Controller shall
-	 * return the error code Command Disallowed (0x0C).
-	 */
-	list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
-		if (test_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags))
-			goto unlock;
-	}
-
-	list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
-		if (hci_conn_check_create_big_sync(conn)) {
-			struct bt_iso_qos *qos = &conn->iso_qos;
-
-			set_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags);
-
-			pdu->handle = qos->bcast.big;
-			pdu->sync_handle = cpu_to_le16(conn->sync_handle);
-			pdu->encryption = qos->bcast.encryption;
-			memcpy(pdu->bcode, qos->bcast.bcode,
-			       sizeof(pdu->bcode));
-			pdu->mse = qos->bcast.mse;
-			pdu->timeout = cpu_to_le16(qos->bcast.timeout);
-			pdu->num_bis = conn->num_bis;
-			memcpy(pdu->bis, conn->bis, conn->num_bis);
-
-			break;
-		}
-	}
-
-unlock:
-	rcu_read_unlock();
-
-	if (!pdu->num_bis)
-		return 0;
-
-	return hci_send_cmd(hdev, HCI_OP_LE_BIG_CREATE_SYNC,
-			    struct_size(pdu, bis, pdu->num_bis), pdu);
-}
-
-int hci_le_big_create_sync_pending(struct hci_dev *hdev)
-{
-	/* Queue big_create_sync */
-	return hci_cmd_sync_queue_once(hdev, big_create_sync,
-				       NULL, big_create_sync_complete);
-}
-
-int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
-			   struct bt_iso_qos *qos,
-			   __u16 sync_handle, __u8 num_bis, __u8 bis[])
+int hci_conn_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
+			     struct bt_iso_qos *qos, __u16 sync_handle,
+			     __u8 num_bis, __u8 bis[])
 {
 	int err;
 
@@ -2274,9 +2115,10 @@ int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
 
 		hcon->num_bis = num_bis;
 		memcpy(hcon->bis, bis, num_bis);
+		hcon->conn_timeout = msecs_to_jiffies(qos->bcast.timeout * 10);
 	}
 
-	return hci_le_big_create_sync_pending(hdev);
+	return hci_connect_big_sync(hdev, hcon);
 }
 
 static void create_big_complete(struct hci_dev *hdev, void *data, int err)
@@ -2386,7 +2228,7 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
 	 * the start periodic advertising and create BIG commands have
 	 * been queued
 	 */
-	hci_conn_hash_list_state(hdev, bis_mark_per_adv, ISO_LINK,
+	hci_conn_hash_list_state(hdev, bis_mark_per_adv, BIS_LINK,
 				 BT_BOUND, &data);
 
 	/* Queue start periodic advertising and create BIG */
@@ -3072,6 +2914,7 @@ void hci_setup_tx_timestamp(struct sk_buff *skb, size_t key_offset,
 			    const struct sockcm_cookie *sockc)
 {
 	struct sock *sk = skb ? skb->sk : NULL;
+	int key;
 
 	/* This shall be called on a single skb of those generated by user
 	 * sendmsg(), and only when the sendmsg() does not return error to
@@ -3087,13 +2930,16 @@ void hci_setup_tx_timestamp(struct sk_buff *skb, size_t key_offset,
 
 	sock_tx_timestamp(sk, sockc, &skb_shinfo(skb)->tx_flags);
 
+	if (sk->sk_type == SOCK_STREAM)
+		key = atomic_add_return(key_offset, &sk->sk_tskey);
+
 	if (sockc->tsflags & SOF_TIMESTAMPING_OPT_ID &&
 	    sockc->tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) {
 		if (sockc->tsflags & SOCKCM_FLAG_TS_OPT_ID) {
 			skb_shinfo(skb)->tskey = sockc->ts_opt_id;
 		} else {
-			int key = atomic_add_return(key_offset, &sk->sk_tskey);
-
+			if (sk->sk_type != SOCK_STREAM)
+				key = atomic_inc_return(&sk->sk_tskey);
 			skb_shinfo(skb)->tskey = key - 1;
 		}
 	}
@@ -3114,7 +2960,8 @@ void hci_conn_tx_queue(struct hci_conn *conn, struct sk_buff *skb)
 	 * TODO: SCO support without flowctl (needs to be done in drivers)
 	 */
 	switch (conn->type) {
-	case ISO_LINK:
+	case CIS_LINK:
+	case BIS_LINK:
 	case ACL_LINK:
 	case LE_LINK:
 		break;
@@ -3186,3 +3033,60 @@ void hci_conn_tx_dequeue(struct hci_conn *conn)
 
 	kfree_skb(skb);
 }
+
+u8 *hci_conn_key_enc_size(struct hci_conn *conn)
+{
+	if (conn->type == ACL_LINK) {
+		struct link_key *key;
+
+		key = hci_find_link_key(conn->hdev, &conn->dst);
+		if (!key)
+			return NULL;
+
+		return &key->pin_len;
+	} else if (conn->type == LE_LINK) {
+		struct smp_ltk *ltk;
+
+		ltk = hci_find_ltk(conn->hdev, &conn->dst, conn->dst_type,
+				   conn->role);
+		if (!ltk)
+			return NULL;
+
+		return &ltk->enc_size;
+	}
+
+	return NULL;
+}
+
+int hci_ethtool_ts_info(unsigned int index, int sk_proto,
+			struct kernel_ethtool_ts_info *info)
+{
+	struct hci_dev *hdev;
+
+	hdev = hci_dev_get(index);
+	if (!hdev)
+		return -ENODEV;
+
+	info->so_timestamping =
+		SOF_TIMESTAMPING_RX_SOFTWARE |
+		SOF_TIMESTAMPING_SOFTWARE;
+	info->phc_index = -1;
+	info->tx_types = BIT(HWTSTAMP_TX_OFF);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE);
+
+	switch (sk_proto) {
+	case BTPROTO_ISO:
+	case BTPROTO_L2CAP:
+		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE;
+		info->so_timestamping |= SOF_TIMESTAMPING_TX_COMPLETION;
+		break;
+	case BTPROTO_SCO:
+		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE;
+		if (hci_dev_test_flag(hdev, HCI_SCO_FLOWCTL))
+			info->so_timestamping |= SOF_TIMESTAMPING_TX_COMPLETION;
+		break;
+	}
+
+	hci_dev_put(hdev);
+	return 0;
+}
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 5eb0600bbd03..3b49828160b7 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2898,12 +2898,13 @@ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb)
 		break;
 	case HCI_ACLDATA_PKT:
 		/* Detect if ISO packet has been sent as ACL */
-		if (hci_conn_num(hdev, ISO_LINK)) {
+		if (hci_conn_num(hdev, CIS_LINK) ||
+		    hci_conn_num(hdev, BIS_LINK)) {
 			__u16 handle = __le16_to_cpu(hci_acl_hdr(skb)->handle);
 			__u8 type;
 
 			type = hci_conn_lookup_type(hdev, hci_handle(handle));
-			if (type == ISO_LINK)
+			if (type == CIS_LINK || type == BIS_LINK)
 				hci_skb_pkt_type(skb) = HCI_ISODATA_PKT;
 		}
 		break;
@@ -2911,6 +2912,8 @@ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb)
 		break;
 	case HCI_ISODATA_PKT:
 		break;
+	case HCI_DRV_PKT:
+		break;
 	default:
 		kfree_skb(skb);
 		return -EINVAL;
@@ -3019,6 +3022,15 @@ static int hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 		return -EINVAL;
 	}
 
+	if (hci_skb_pkt_type(skb) == HCI_DRV_PKT) {
+		/* Intercept HCI Drv packet here and don't go with hdev->send
+		 * callback.
+		 */
+		err = hci_drv_process_cmd(hdev, skb);
+		kfree_skb(skb);
+		return err;
+	}
+
 	err = hdev->send(hdev, skb);
 	if (err < 0) {
 		bt_dev_err(hdev, "sending frame failed (%d)", err);
@@ -3345,7 +3357,8 @@ static inline void hci_quote_sent(struct hci_conn *conn, int num, int *quote)
 	case LE_LINK:
 		cnt = hdev->le_mtu ? hdev->le_cnt : hdev->acl_cnt;
 		break;
-	case ISO_LINK:
+	case CIS_LINK:
+	case BIS_LINK:
 		cnt = hdev->iso_mtu ? hdev->iso_cnt :
 			hdev->le_mtu ? hdev->le_cnt : hdev->acl_cnt;
 		break;
@@ -3359,7 +3372,7 @@ static inline void hci_quote_sent(struct hci_conn *conn, int num, int *quote)
 }
 
 static struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type,
-				     int *quote)
+				     __u8 type2, int *quote)
 {
 	struct hci_conn_hash *h = &hdev->conn_hash;
 	struct hci_conn *conn = NULL, *c;
@@ -3371,7 +3384,8 @@ static struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type != type || skb_queue_empty(&c->data_q))
+		if ((c->type != type && c->type != type2) ||
+		    skb_queue_empty(&c->data_q))
 			continue;
 
 		if (c->state != BT_CONNECTED && c->state != BT_CONFIG)
@@ -3579,7 +3593,7 @@ static void hci_sched_sco(struct hci_dev *hdev, __u8 type)
 	else
 		cnt = &hdev->sco_cnt;
 
-	while (*cnt && (conn = hci_low_sent(hdev, type, &quote))) {
+	while (*cnt && (conn = hci_low_sent(hdev, type, type, &quote))) {
 		while (quote-- && (skb = skb_dequeue(&conn->data_q))) {
 			BT_DBG("skb %p len %d", skb, skb->len);
 			hci_send_conn_frame(hdev, conn, skb);
@@ -3707,12 +3721,14 @@ static void hci_sched_iso(struct hci_dev *hdev)
 
 	BT_DBG("%s", hdev->name);
 
-	if (!hci_conn_num(hdev, ISO_LINK))
+	if (!hci_conn_num(hdev, CIS_LINK) &&
+	    !hci_conn_num(hdev, BIS_LINK))
 		return;
 
 	cnt = hdev->iso_pkts ? &hdev->iso_cnt :
 		hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt;
-	while (*cnt && (conn = hci_low_sent(hdev, ISO_LINK, &quote))) {
+	while (*cnt && (conn = hci_low_sent(hdev, CIS_LINK, BIS_LINK,
+					    &quote))) {
 		while (quote-- && (skb = skb_dequeue(&conn->data_q))) {
 			BT_DBG("skb %p len %d", skb, skb->len);
 			hci_send_conn_frame(hdev, conn, skb);
@@ -4057,10 +4073,13 @@ static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb)
 		return;
 	}
 
-	err = hci_send_frame(hdev, skb);
-	if (err < 0) {
-		hci_cmd_sync_cancel_sync(hdev, -err);
-		return;
+	if (hci_skb_opcode(skb) != HCI_OP_NOP) {
+		err = hci_send_frame(hdev, skb);
+		if (err < 0) {
+			hci_cmd_sync_cancel_sync(hdev, -err);
+			return;
+		}
+		atomic_dec(&hdev->cmd_cnt);
 	}
 
 	if (hdev->req_status == HCI_REQ_PEND &&
@@ -4068,8 +4087,6 @@ static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb)
 		kfree_skb(hdev->req_skb);
 		hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL);
 	}
-
-	atomic_dec(&hdev->cmd_cnt);
 }
 
 static void hci_cmd_work(struct work_struct *work)
diff --git a/net/bluetooth/hci_drv.c b/net/bluetooth/hci_drv.c
new file mode 100644
index 000000000000..3dd2d8a006b9
--- /dev/null
+++ b/net/bluetooth/hci_drv.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Google Corporation
+ */
+
+#include <linux/skbuff.h>
+#include <linux/types.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci.h>
+#include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/hci_drv.h>
+
+int hci_drv_cmd_status(struct hci_dev *hdev, u16 cmd, u8 status)
+{
+	struct hci_drv_ev_hdr *hdr;
+	struct hci_drv_ev_cmd_status *ev;
+	struct sk_buff *skb;
+
+	skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*ev), GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = skb_put(skb, sizeof(*hdr));
+	hdr->opcode = __cpu_to_le16(HCI_DRV_EV_CMD_STATUS);
+	hdr->len = __cpu_to_le16(sizeof(*ev));
+
+	ev = skb_put(skb, sizeof(*ev));
+	ev->opcode = __cpu_to_le16(cmd);
+	ev->status = status;
+
+	hci_skb_pkt_type(skb) = HCI_DRV_PKT;
+
+	return hci_recv_frame(hdev, skb);
+}
+EXPORT_SYMBOL(hci_drv_cmd_status);
+
+int hci_drv_cmd_complete(struct hci_dev *hdev, u16 cmd, u8 status, void *rp,
+			 size_t rp_len)
+{
+	struct hci_drv_ev_hdr *hdr;
+	struct hci_drv_ev_cmd_complete *ev;
+	struct sk_buff *skb;
+
+	skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*ev) + rp_len, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = skb_put(skb, sizeof(*hdr));
+	hdr->opcode = __cpu_to_le16(HCI_DRV_EV_CMD_COMPLETE);
+	hdr->len = __cpu_to_le16(sizeof(*ev) + rp_len);
+
+	ev = skb_put(skb, sizeof(*ev));
+	ev->opcode = __cpu_to_le16(cmd);
+	ev->status = status;
+
+	skb_put_data(skb, rp, rp_len);
+
+	hci_skb_pkt_type(skb) = HCI_DRV_PKT;
+
+	return hci_recv_frame(hdev, skb);
+}
+EXPORT_SYMBOL(hci_drv_cmd_complete);
+
+int hci_drv_process_cmd(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_drv_cmd_hdr *hdr;
+	const struct hci_drv_handler *handler = NULL;
+	u16 opcode, len, ogf, ocf;
+
+	hdr = skb_pull_data(skb, sizeof(*hdr));
+	if (!hdr)
+		return -EILSEQ;
+
+	opcode = __le16_to_cpu(hdr->opcode);
+	len = __le16_to_cpu(hdr->len);
+	if (len != skb->len)
+		return -EILSEQ;
+
+	ogf = hci_opcode_ogf(opcode);
+	ocf = hci_opcode_ocf(opcode);
+
+	if (!hdev->hci_drv)
+		return hci_drv_cmd_status(hdev, opcode,
+					  HCI_DRV_STATUS_UNKNOWN_COMMAND);
+
+	if (ogf != HCI_DRV_OGF_DRIVER_SPECIFIC) {
+		if (opcode < hdev->hci_drv->common_handler_count)
+			handler = &hdev->hci_drv->common_handlers[opcode];
+	} else {
+		if (ocf < hdev->hci_drv->specific_handler_count)
+			handler = &hdev->hci_drv->specific_handlers[ocf];
+	}
+
+	if (!handler || !handler->func)
+		return hci_drv_cmd_status(hdev, opcode,
+					  HCI_DRV_STATUS_UNKNOWN_COMMAND);
+
+	if (len != handler->data_len)
+		return hci_drv_cmd_status(hdev, opcode,
+					  HCI_DRV_STATUS_INVALID_PARAMETERS);
+
+	return handler->func(hdev, skb->data, len);
+}
+EXPORT_SYMBOL(hci_drv_process_cmd);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 1d8616f2e740..66052d6aaa1d 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -739,10 +739,17 @@ static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data,
 			   handle);
 		conn->enc_key_size = 0;
 	} else {
+		u8 *key_enc_size = hci_conn_key_enc_size(conn);
+
 		conn->enc_key_size = rp->key_size;
 		status = 0;
 
-		if (conn->enc_key_size < hdev->min_enc_key_size) {
+		/* Attempt to check if the key size is too small or if it has
+		 * been downgraded from the last time it was stored as part of
+		 * the link_key.
+		 */
+		if (conn->enc_key_size < hdev->min_enc_key_size ||
+		    (key_enc_size && conn->enc_key_size < *key_enc_size)) {
 			/* As slave role, the conn->state has been set to
 			 * BT_CONNECTED and l2cap conn req might not be received
 			 * yet, at this moment the l2cap layer almost does
@@ -755,6 +762,10 @@ static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data,
 			clear_bit(HCI_CONN_ENCRYPT, &conn->flags);
 			clear_bit(HCI_CONN_AES_CCM, &conn->flags);
 		}
+
+		/* Update the key encryption size with the connection one */
+		if (key_enc_size && *key_enc_size != conn->enc_key_size)
+			*key_enc_size = conn->enc_key_size;
 	}
 
 	hci_encrypt_cfm(conn, status);
@@ -3065,6 +3076,34 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, void *edata,
 	hci_dev_unlock(hdev);
 }
 
+static int hci_read_enc_key_size(struct hci_dev *hdev, struct hci_conn *conn)
+{
+	struct hci_cp_read_enc_key_size cp;
+	u8 *key_enc_size = hci_conn_key_enc_size(conn);
+
+	if (!read_key_size_capable(hdev)) {
+		conn->enc_key_size = HCI_LINK_KEY_SIZE;
+		return -EOPNOTSUPP;
+	}
+
+	bt_dev_dbg(hdev, "hcon %p", conn);
+
+	memset(&cp, 0, sizeof(cp));
+	cp.handle = cpu_to_le16(conn->handle);
+
+	/* If the key enc_size is already known, use it as conn->enc_key_size,
+	 * otherwise use hdev->min_enc_key_size so the likes of
+	 * l2cap_check_enc_key_size don't fail while waiting for
+	 * HCI_OP_READ_ENC_KEY_SIZE response.
+	 */
+	if (key_enc_size && *key_enc_size)
+		conn->enc_key_size = *key_enc_size;
+	else
+		conn->enc_key_size = hdev->min_enc_key_size;
+
+	return hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, sizeof(cp), &cp);
+}
+
 static void hci_conn_complete_evt(struct hci_dev *hdev, void *data,
 				  struct sk_buff *skb)
 {
@@ -3157,23 +3196,11 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data,
 		if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) &&
 		    ev->link_type == ACL_LINK) {
 			struct link_key *key;
-			struct hci_cp_read_enc_key_size cp;
 
 			key = hci_find_link_key(hdev, &ev->bdaddr);
 			if (key) {
 				set_bit(HCI_CONN_ENCRYPT, &conn->flags);
-
-				if (!read_key_size_capable(hdev)) {
-					conn->enc_key_size = HCI_LINK_KEY_SIZE;
-				} else {
-					cp.handle = cpu_to_le16(conn->handle);
-					if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE,
-							 sizeof(cp), &cp)) {
-						bt_dev_err(hdev, "sending read key size failed");
-						conn->enc_key_size = HCI_LINK_KEY_SIZE;
-					}
-				}
-
+				hci_read_enc_key_size(hdev, conn);
 				hci_encrypt_cfm(conn, ev->status);
 			}
 		}
@@ -3612,24 +3639,8 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data,
 
 	/* Try reading the encryption key size for encrypted ACL links */
 	if (!ev->status && ev->encrypt && conn->type == ACL_LINK) {
-		struct hci_cp_read_enc_key_size cp;
-
-		/* Only send HCI_Read_Encryption_Key_Size if the
-		 * controller really supports it. If it doesn't, assume
-		 * the default size (16).
-		 */
-		if (!read_key_size_capable(hdev)) {
-			conn->enc_key_size = HCI_LINK_KEY_SIZE;
+		if (hci_read_enc_key_size(hdev, conn))
 			goto notify;
-		}
-
-		cp.handle = cpu_to_le16(conn->handle);
-		if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE,
-				 sizeof(cp), &cp)) {
-			bt_dev_err(hdev, "sending read key size failed");
-			conn->enc_key_size = HCI_LINK_KEY_SIZE;
-			goto notify;
-		}
 
 		goto unlock;
 	}
@@ -3793,7 +3804,7 @@ static void hci_unbound_cis_failed(struct hci_dev *hdev, u8 cig, u8 status)
 	lockdep_assert_held(&hdev->lock);
 
 	list_for_each_entry_safe(conn, tmp, &hdev->conn_hash.list, list) {
-		if (conn->type != ISO_LINK || !bacmp(&conn->dst, BDADDR_ANY) ||
+		if (conn->type != CIS_LINK ||
 		    conn->state == BT_OPEN || conn->iso_qos.ucast.cig != cig)
 			continue;
 
@@ -4456,7 +4467,8 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data,
 
 			break;
 
-		case ISO_LINK:
+		case CIS_LINK:
+		case BIS_LINK:
 			if (hdev->iso_pkts) {
 				hdev->iso_cnt += count;
 				if (hdev->iso_cnt > hdev->iso_pkts)
@@ -6160,11 +6172,12 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 	 * event or send an immediate device found event if the data
 	 * should not be stored for later.
 	 */
-	if (!ext_adv &&	!has_pending_adv_report(hdev)) {
+	if (!has_pending_adv_report(hdev)) {
 		/* If the report will trigger a SCAN_REQ store it for
 		 * later merging.
 		 */
-		if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) {
+		if (!ext_adv && (type == LE_ADV_IND ||
+				 type == LE_ADV_SCAN_IND)) {
 			store_pending_adv_report(hdev, bdaddr, bdaddr_type,
 						 rssi, flags, data, len);
 			return;
@@ -6339,6 +6352,17 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data,
 			info->secondary_phy &= 0x1f;
 		}
 
+		/* Check if PA Sync is pending and if the hci_conn SID has not
+		 * been set update it.
+		 */
+		if (hci_dev_test_flag(hdev, HCI_PA_SYNC)) {
+			struct hci_conn *conn;
+
+			conn = hci_conn_hash_lookup_create_pa_sync(hdev);
+			if (conn && conn->sid == HCI_SID_INVALID)
+				conn->sid = info->sid;
+		}
+
 		if (legacy_evt_type != LE_ADV_INVALID) {
 			process_adv_report(hdev, legacy_evt_type, &info->bdaddr,
 					   info->bdaddr_type, NULL, 0,
@@ -6377,8 +6401,7 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data,
 
 	hci_dev_clear_flag(hdev, HCI_PA_SYNC);
 
-	conn = hci_conn_hash_lookup_sid(hdev, ev->sid, &ev->bdaddr,
-					ev->bdaddr_type);
+	conn = hci_conn_hash_lookup_create_pa_sync(hdev);
 	if (!conn) {
 		bt_dev_err(hdev,
 			   "Unable to find connection for dst %pMR sid 0x%2.2x",
@@ -6391,7 +6414,8 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data,
 	conn->sync_handle = le16_to_cpu(ev->handle);
 	conn->sid = HCI_SID_INVALID;
 
-	mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ISO_LINK, &flags);
+	mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, BIS_LINK,
+				      &flags);
 	if (!(mask & HCI_LM_ACCEPT)) {
 		hci_le_pa_term_sync(hdev, ev->handle);
 		goto unlock;
@@ -6401,7 +6425,7 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data,
 		goto unlock;
 
 	/* Add connection to indicate PA sync event */
-	pa_sync = hci_conn_add_unset(hdev, ISO_LINK, BDADDR_ANY,
+	pa_sync = hci_conn_add_unset(hdev, BIS_LINK, BDADDR_ANY,
 				     HCI_ROLE_SLAVE);
 
 	if (IS_ERR(pa_sync))
@@ -6417,9 +6441,6 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data,
 	}
 
 unlock:
-	/* Handle any other pending PA sync command */
-	hci_pa_create_sync_pending(hdev);
-
 	hci_dev_unlock(hdev);
 }
 
@@ -6435,7 +6456,7 @@ static void hci_le_per_adv_report_evt(struct hci_dev *hdev, void *data,
 
 	hci_dev_lock(hdev);
 
-	mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, ISO_LINK, &flags);
+	mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, BIS_LINK, &flags);
 	if (!(mask & HCI_LM_ACCEPT))
 		goto unlock;
 
@@ -6719,7 +6740,7 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data,
 		goto unlock;
 	}
 
-	if (conn->type != ISO_LINK) {
+	if (conn->type != CIS_LINK) {
 		bt_dev_err(hdev,
 			   "Invalid connection link type handle 0x%4.4x",
 			   handle);
@@ -6837,7 +6858,7 @@ static void hci_le_cis_req_evt(struct hci_dev *hdev, void *data,
 	if (!acl)
 		goto unlock;
 
-	mask = hci_proto_connect_ind(hdev, &acl->dst, ISO_LINK, &flags);
+	mask = hci_proto_connect_ind(hdev, &acl->dst, CIS_LINK, &flags);
 	if (!(mask & HCI_LM_ACCEPT)) {
 		hci_le_reject_cis(hdev, ev->cis_handle);
 		goto unlock;
@@ -6845,8 +6866,8 @@ static void hci_le_cis_req_evt(struct hci_dev *hdev, void *data,
 
 	cis = hci_conn_hash_lookup_handle(hdev, cis_handle);
 	if (!cis) {
-		cis = hci_conn_add(hdev, ISO_LINK, &acl->dst, HCI_ROLE_SLAVE,
-				   cis_handle);
+		cis = hci_conn_add(hdev, CIS_LINK, &acl->dst,
+				   HCI_ROLE_SLAVE, cis_handle);
 		if (IS_ERR(cis)) {
 			hci_le_reject_cis(hdev, ev->cis_handle);
 			goto unlock;
@@ -6931,7 +6952,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
 
 	bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
 
-	if (!hci_le_ev_skb_pull(hdev, skb, HCI_EVT_LE_BIG_SYNC_ESTABILISHED,
+	if (!hci_le_ev_skb_pull(hdev, skb, HCI_EVT_LE_BIG_SYNC_ESTABLISHED,
 				flex_array_size(ev, bis, ev->num_bis)))
 		return;
 
@@ -6961,7 +6982,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
 				bt_dev_dbg(hdev, "ignore too large handle %u", handle);
 				continue;
 			}
-			bis = hci_conn_add(hdev, ISO_LINK, BDADDR_ANY,
+			bis = hci_conn_add(hdev, BIS_LINK, BDADDR_ANY,
 					   HCI_ROLE_SLAVE, handle);
 			if (IS_ERR(bis))
 				continue;
@@ -7002,9 +7023,6 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
 		}
 
 unlock:
-	/* Handle any other pending BIG sync command */
-	hci_le_big_create_sync_pending(hdev);
-
 	hci_dev_unlock(hdev);
 }
 
@@ -7020,7 +7038,7 @@ static void hci_le_big_info_adv_report_evt(struct hci_dev *hdev, void *data,
 
 	hci_dev_lock(hdev);
 
-	mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, ISO_LINK, &flags);
+	mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, BIS_LINK, &flags);
 	if (!(mask & HCI_LM_ACCEPT))
 		goto unlock;
 
@@ -7126,8 +7144,8 @@ static const struct hci_le_ev {
 		     hci_le_create_big_complete_evt,
 		     sizeof(struct hci_evt_le_create_big_complete),
 		     HCI_MAX_EVENT_SIZE),
-	/* [0x1d = HCI_EV_LE_BIG_SYNC_ESTABILISHED] */
-	HCI_LE_EV_VL(HCI_EVT_LE_BIG_SYNC_ESTABILISHED,
+	/* [0x1d = HCI_EV_LE_BIG_SYNC_ESTABLISHED] */
+	HCI_LE_EV_VL(HCI_EVT_LE_BIG_SYNC_ESTABLISHED,
 		     hci_le_big_sync_established_evt,
 		     sizeof(struct hci_evt_le_big_sync_estabilished),
 		     HCI_MAX_EVENT_SIZE),
@@ -7150,7 +7168,8 @@ static void hci_le_meta_evt(struct hci_dev *hdev, void *data,
 
 	/* Only match event if command OGF is for LE */
 	if (hdev->req_skb &&
-	    hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) == 0x08 &&
+	   (hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) == 0x08 ||
+	    hci_skb_opcode(hdev->req_skb) == HCI_OP_NOP) &&
 	    hci_skb_event(hdev->req_skb) == ev->subevent) {
 		*opcode = hci_skb_opcode(hdev->req_skb);
 		hci_req_cmd_complete(hdev, *opcode, 0x00, req_complete,
@@ -7506,8 +7525,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		goto done;
 	}
 
+	hci_dev_lock(hdev);
 	kfree_skb(hdev->recv_event);
 	hdev->recv_event = skb_clone(skb, GFP_KERNEL);
+	hci_dev_unlock(hdev);
 
 	event = hdr->evt;
 	if (!event) {
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 022b86797acd..428ee5c7de7e 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -234,7 +234,8 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
 			if (hci_skb_pkt_type(skb) != HCI_EVENT_PKT &&
 			    hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT &&
 			    hci_skb_pkt_type(skb) != HCI_SCODATA_PKT &&
-			    hci_skb_pkt_type(skb) != HCI_ISODATA_PKT)
+			    hci_skb_pkt_type(skb) != HCI_ISODATA_PKT &&
+			    hci_skb_pkt_type(skb) != HCI_DRV_PKT)
 				continue;
 		} else {
 			/* Don't send frame to other channel types */
@@ -391,6 +392,12 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb)
 		else
 			opcode = cpu_to_le16(HCI_MON_ISO_TX_PKT);
 		break;
+	case HCI_DRV_PKT:
+		if (bt_cb(skb)->incoming)
+			opcode = cpu_to_le16(HCI_MON_DRV_RX_PKT);
+		else
+			opcode = cpu_to_le16(HCI_MON_DRV_TX_PKT);
+		break;
 	case HCI_DIAG_PKT:
 		opcode = cpu_to_le16(HCI_MON_VENDOR_DIAG);
 		break;
@@ -1860,7 +1867,8 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 		if (hci_skb_pkt_type(skb) != HCI_COMMAND_PKT &&
 		    hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT &&
 		    hci_skb_pkt_type(skb) != HCI_SCODATA_PKT &&
-		    hci_skb_pkt_type(skb) != HCI_ISODATA_PKT) {
+		    hci_skb_pkt_type(skb) != HCI_ISODATA_PKT &&
+		    hci_skb_pkt_type(skb) != HCI_DRV_PKT) {
 			err = -EINVAL;
 			goto drop;
 		}
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 609b035e5c90..62d1ff951ebe 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -2693,16 +2693,16 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev)
 
 	/* Force address filtering if PA Sync is in progress */
 	if (hci_dev_test_flag(hdev, HCI_PA_SYNC)) {
-		struct hci_cp_le_pa_create_sync *sent;
+		struct hci_conn *conn;
 
-		sent = hci_sent_cmd_data(hdev, HCI_OP_LE_PA_CREATE_SYNC);
-		if (sent) {
+		conn = hci_conn_hash_lookup_create_pa_sync(hdev);
+		if (conn) {
 			struct conn_params pa;
 
 			memset(&pa, 0, sizeof(pa));
 
-			bacpy(&pa.addr, &sent->addr);
-			pa.addr_type = sent->addr_type;
+			bacpy(&pa.addr, &conn->dst);
+			pa.addr_type = conn->dst_type;
 
 			/* Clear first since there could be addresses left
 			 * behind.
@@ -2860,7 +2860,7 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type,
 		if (sent) {
 			struct hci_conn *conn;
 
-			conn = hci_conn_hash_lookup_ba(hdev, ISO_LINK,
+			conn = hci_conn_hash_lookup_ba(hdev, BIS_LINK,
 						       &sent->bdaddr);
 			if (conn) {
 				struct bt_iso_qos *qos = &conn->iso_qos;
@@ -5477,7 +5477,7 @@ static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn,
 	if (conn->type == LE_LINK)
 		return hci_le_connect_cancel_sync(hdev, conn, reason);
 
-	if (conn->type == ISO_LINK) {
+	if (conn->type == CIS_LINK) {
 		/* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
 		 * page 1857:
 		 *
@@ -5490,9 +5490,10 @@ static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn,
 			return hci_disconnect_sync(hdev, conn, reason);
 
 		/* CIS with no Create CIS sent have nothing to cancel */
-		if (bacmp(&conn->dst, BDADDR_ANY))
-			return HCI_ERROR_LOCAL_HOST_TERM;
+		return HCI_ERROR_LOCAL_HOST_TERM;
+	}
 
+	if (conn->type == BIS_LINK) {
 		/* There is no way to cancel a BIS without terminating the BIG
 		 * which is done later on connection cleanup.
 		 */
@@ -5554,9 +5555,12 @@ static int hci_reject_conn_sync(struct hci_dev *hdev, struct hci_conn *conn,
 {
 	struct hci_cp_reject_conn_req cp;
 
-	if (conn->type == ISO_LINK)
+	if (conn->type == CIS_LINK)
 		return hci_le_reject_cis_sync(hdev, conn, reason);
 
+	if (conn->type == BIS_LINK)
+		return -EINVAL;
+
 	if (conn->type == SCO_LINK || conn->type == ESCO_LINK)
 		return hci_reject_sco_sync(hdev, conn, reason);
 
@@ -6895,3 +6899,182 @@ int hci_le_conn_update_sync(struct hci_dev *hdev, struct hci_conn *conn,
 	return __hci_cmd_sync_status(hdev, HCI_OP_LE_CONN_UPDATE,
 				     sizeof(cp), &cp, HCI_CMD_TIMEOUT);
 }
+
+static void create_pa_complete(struct hci_dev *hdev, void *data, int err)
+{
+	struct hci_conn *conn = data;
+	struct hci_conn *pa_sync;
+
+	bt_dev_dbg(hdev, "err %d", err);
+
+	if (err == -ECANCELED)
+		return;
+
+	hci_dev_lock(hdev);
+
+	hci_dev_clear_flag(hdev, HCI_PA_SYNC);
+
+	if (!hci_conn_valid(hdev, conn))
+		clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);
+
+	if (!err)
+		goto unlock;
+
+	/* Add connection to indicate PA sync error */
+	pa_sync = hci_conn_add_unset(hdev, BIS_LINK, BDADDR_ANY,
+				     HCI_ROLE_SLAVE);
+
+	if (IS_ERR(pa_sync))
+		goto unlock;
+
+	set_bit(HCI_CONN_PA_SYNC_FAILED, &pa_sync->flags);
+
+	/* Notify iso layer */
+	hci_connect_cfm(pa_sync, bt_status(err));
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
+static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data)
+{
+	struct hci_cp_le_pa_create_sync cp;
+	struct hci_conn *conn = data;
+	struct bt_iso_qos *qos = &conn->iso_qos;
+	int err;
+
+	if (!hci_conn_valid(hdev, conn))
+		return -ECANCELED;
+
+	if (conn->sync_handle != HCI_SYNC_HANDLE_INVALID)
+		return -EINVAL;
+
+	if (hci_dev_test_and_set_flag(hdev, HCI_PA_SYNC))
+		return -EBUSY;
+
+	/* Stop scanning if SID has not been set and active scanning is enabled
+	 * so we use passive scanning which will be scanning using the allow
+	 * list programmed to contain only the connection address.
+	 */
+	if (conn->sid == HCI_SID_INVALID &&
+	    hci_dev_test_flag(hdev, HCI_LE_SCAN)) {
+		hci_scan_disable_sync(hdev);
+		hci_dev_set_flag(hdev, HCI_LE_SCAN_INTERRUPTED);
+		hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+	}
+
+	/* Mark HCI_CONN_CREATE_PA_SYNC so hci_update_passive_scan_sync can
+	 * program the address in the allow list so PA advertisements can be
+	 * received.
+	 */
+	set_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);
+
+	hci_update_passive_scan_sync(hdev);
+
+	/* SID has not been set listen for HCI_EV_LE_EXT_ADV_REPORT to update
+	 * it.
+	 */
+	if (conn->sid == HCI_SID_INVALID)
+		__hci_cmd_sync_status_sk(hdev, HCI_OP_NOP, 0, NULL,
+					 HCI_EV_LE_EXT_ADV_REPORT,
+					 conn->conn_timeout, NULL);
+
+	memset(&cp, 0, sizeof(cp));
+	cp.options = qos->bcast.options;
+	cp.sid = conn->sid;
+	cp.addr_type = conn->dst_type;
+	bacpy(&cp.addr, &conn->dst);
+	cp.skip = cpu_to_le16(qos->bcast.skip);
+	cp.sync_timeout = cpu_to_le16(qos->bcast.sync_timeout);
+	cp.sync_cte_type = qos->bcast.sync_cte_type;
+
+	/* The spec allows only one pending LE Periodic Advertising Create
+	 * Sync command at a time so we forcefully wait for PA Sync Established
+	 * event since cmd_work can only schedule one command at a time.
+	 *
+	 * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
+	 * page 2493:
+	 *
+	 * If the Host issues this command when another HCI_LE_Periodic_
+	 * Advertising_Create_Sync command is pending, the Controller shall
+	 * return the error code Command Disallowed (0x0C).
+	 */
+	err = __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_PA_CREATE_SYNC,
+				       sizeof(cp), &cp,
+				       HCI_EV_LE_PA_SYNC_ESTABLISHED,
+				       conn->conn_timeout, NULL);
+	if (err == -ETIMEDOUT)
+		__hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC_CANCEL,
+				      0, NULL, HCI_CMD_TIMEOUT);
+
+	return err;
+}
+
+int hci_connect_pa_sync(struct hci_dev *hdev, struct hci_conn *conn)
+{
+	return hci_cmd_sync_queue_once(hdev, hci_le_pa_create_sync, conn,
+				       create_pa_complete);
+}
+
+static void create_big_complete(struct hci_dev *hdev, void *data, int err)
+{
+	struct hci_conn *conn = data;
+
+	bt_dev_dbg(hdev, "err %d", err);
+
+	if (err == -ECANCELED)
+		return;
+
+	if (hci_conn_valid(hdev, conn))
+		clear_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags);
+}
+
+static int hci_le_big_create_sync(struct hci_dev *hdev, void *data)
+{
+	DEFINE_FLEX(struct hci_cp_le_big_create_sync, cp, bis, num_bis, 0x11);
+	struct hci_conn *conn = data;
+	struct bt_iso_qos *qos = &conn->iso_qos;
+	int err;
+
+	if (!hci_conn_valid(hdev, conn))
+		return -ECANCELED;
+
+	set_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags);
+
+	memset(cp, 0, sizeof(*cp));
+	cp->handle = qos->bcast.big;
+	cp->sync_handle = cpu_to_le16(conn->sync_handle);
+	cp->encryption = qos->bcast.encryption;
+	memcpy(cp->bcode, qos->bcast.bcode, sizeof(cp->bcode));
+	cp->mse = qos->bcast.mse;
+	cp->timeout = cpu_to_le16(qos->bcast.timeout);
+	cp->num_bis = conn->num_bis;
+	memcpy(cp->bis, conn->bis, conn->num_bis);
+
+	/* The spec allows only one pending LE BIG Create Sync command at
+	 * a time, so we forcefully wait for BIG Sync Established event since
+	 * cmd_work can only schedule one command at a time.
+	 *
+	 * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
+	 * page 2586:
+	 *
+	 * If the Host sends this command when the Controller is in the
+	 * process of synchronizing to any BIG, i.e. the HCI_LE_BIG_Sync_
+	 * Established event has not been generated, the Controller shall
+	 * return the error code Command Disallowed (0x0C).
+	 */
+	err = __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_BIG_CREATE_SYNC,
+				       struct_size(cp, bis, cp->num_bis), cp,
+				       HCI_EVT_LE_BIG_SYNC_ESTABLISHED,
+				       conn->conn_timeout, NULL);
+	if (err == -ETIMEDOUT)
+		hci_le_big_terminate_sync(hdev, cp->handle);
+
+	return err;
+}
+
+int hci_connect_big_sync(struct hci_dev *hdev, struct hci_conn *conn)
+{
+	return hci_cmd_sync_queue_once(hdev, hci_le_big_create_sync, conn,
+				       create_big_complete);
+}
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 3501a991f1c6..6e2c752aaa8f 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -941,7 +941,7 @@ static int iso_sock_bind_bc(struct socket *sock, struct sockaddr *addr,
 
 	iso_pi(sk)->dst_type = sa->iso_bc->bc_bdaddr_type;
 
-	if (sa->iso_bc->bc_sid > 0x0f)
+	if (sa->iso_bc->bc_sid > 0x0f && sa->iso_bc->bc_sid != HCI_SID_INVALID)
 		return -EINVAL;
 
 	iso_pi(sk)->bc_sid = sa->iso_bc->bc_sid;
@@ -1330,6 +1330,7 @@ static int iso_sock_getname(struct socket *sock, struct sockaddr *addr,
 {
 	struct sockaddr_iso *sa = (struct sockaddr_iso *)addr;
 	struct sock *sk = sock->sk;
+	int len = sizeof(struct sockaddr_iso);
 
 	BT_DBG("sock %p, sk %p", sock, sk);
 
@@ -1338,12 +1339,20 @@ static int iso_sock_getname(struct socket *sock, struct sockaddr *addr,
 	if (peer) {
 		bacpy(&sa->iso_bdaddr, &iso_pi(sk)->dst);
 		sa->iso_bdaddr_type = iso_pi(sk)->dst_type;
+
+		if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) {
+			sa->iso_bc->bc_sid = iso_pi(sk)->bc_sid;
+			sa->iso_bc->bc_num_bis = iso_pi(sk)->bc_num_bis;
+			memcpy(sa->iso_bc->bc_bis, iso_pi(sk)->bc_bis,
+			       ISO_MAX_NUM_BIS);
+			len += sizeof(struct sockaddr_iso_bc);
+		}
 	} else {
 		bacpy(&sa->iso_bdaddr, &iso_pi(sk)->src);
 		sa->iso_bdaddr_type = iso_pi(sk)->src_type;
 	}
 
-	return sizeof(struct sockaddr_iso);
+	return len;
 }
 
 static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg,
@@ -1462,14 +1471,13 @@ static void iso_conn_big_sync(struct sock *sk)
 	lock_sock(sk);
 
 	if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) {
-		err = hci_le_big_create_sync(hdev, iso_pi(sk)->conn->hcon,
-					     &iso_pi(sk)->qos,
-					     iso_pi(sk)->sync_handle,
-					     iso_pi(sk)->bc_num_bis,
-					     iso_pi(sk)->bc_bis);
+		err = hci_conn_big_create_sync(hdev, iso_pi(sk)->conn->hcon,
+					       &iso_pi(sk)->qos,
+					       iso_pi(sk)->sync_handle,
+					       iso_pi(sk)->bc_num_bis,
+					       iso_pi(sk)->bc_bis);
 		if (err)
-			bt_dev_err(hdev, "hci_le_big_create_sync: %d",
-				   err);
+			bt_dev_err(hdev, "hci_big_create_sync: %d", err);
 	}
 
 	release_sock(sk);
@@ -1922,7 +1930,7 @@ static void iso_conn_ready(struct iso_conn *conn)
 					      hcon);
 		} else if (test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) {
 			ev = hci_recv_event_data(hcon->hdev,
-						 HCI_EVT_LE_BIG_SYNC_ESTABILISHED);
+						 HCI_EVT_LE_BIG_SYNC_ESTABLISHED);
 
 			/* Get reference to PA sync parent socket, if it exists */
 			parent = iso_get_sock(&hcon->src, &hcon->dst,
@@ -1989,11 +1997,13 @@ static void iso_conn_ready(struct iso_conn *conn)
 			hcon->dst_type = iso_pi(parent)->dst_type;
 		}
 
-		if (ev3) {
+		if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags)) {
 			iso_pi(sk)->qos = iso_pi(parent)->qos;
 			hcon->iso_qos = iso_pi(sk)->qos;
+			iso_pi(sk)->bc_sid = iso_pi(parent)->bc_sid;
 			iso_pi(sk)->bc_num_bis = iso_pi(parent)->bc_num_bis;
-			memcpy(iso_pi(sk)->bc_bis, iso_pi(parent)->bc_bis, ISO_MAX_NUM_BIS);
+			memcpy(iso_pi(sk)->bc_bis, iso_pi(parent)->bc_bis,
+			       ISO_MAX_NUM_BIS);
 			set_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags);
 		}
 
@@ -2030,6 +2040,9 @@ static bool iso_match_sid(struct sock *sk, void *data)
 {
 	struct hci_ev_le_pa_sync_established *ev = data;
 
+	if (iso_pi(sk)->bc_sid == HCI_SID_INVALID)
+		return true;
+
 	return ev->sid == iso_pi(sk)->bc_sid;
 }
 
@@ -2076,8 +2089,10 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 	if (ev1) {
 		sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_LISTEN,
 				  iso_match_sid, ev1);
-		if (sk && !ev1->status)
+		if (sk && !ev1->status) {
 			iso_pi(sk)->sync_handle = le16_to_cpu(ev1->handle);
+			iso_pi(sk)->bc_sid = ev1->sid;
+		}
 
 		goto done;
 	}
@@ -2113,12 +2128,11 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 
 			if (!test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) &&
 			    !test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) {
-				err = hci_le_big_create_sync(hdev,
-							     hcon,
-							     &iso_pi(sk)->qos,
-							     iso_pi(sk)->sync_handle,
-							     iso_pi(sk)->bc_num_bis,
-							     iso_pi(sk)->bc_bis);
+				err = hci_conn_big_create_sync(hdev, hcon,
+							       &iso_pi(sk)->qos,
+							       iso_pi(sk)->sync_handle,
+							       iso_pi(sk)->bc_num_bis,
+							       iso_pi(sk)->bc_bis);
 				if (err) {
 					bt_dev_err(hdev, "hci_le_big_create_sync: %d",
 						   err);
@@ -2205,7 +2219,7 @@ done:
 
 static void iso_connect_cfm(struct hci_conn *hcon, __u8 status)
 {
-	if (hcon->type != ISO_LINK) {
+	if (hcon->type != CIS_LINK && hcon->type != BIS_LINK) {
 		if (hcon->type != LE_LINK)
 			return;
 
@@ -2246,7 +2260,7 @@ static void iso_connect_cfm(struct hci_conn *hcon, __u8 status)
 
 static void iso_disconn_cfm(struct hci_conn *hcon, __u8 reason)
 {
-	if (hcon->type != ISO_LINK)
+	if (hcon->type != CIS_LINK && hcon->type != BIS_LINK)
 		return;
 
 	BT_DBG("hcon %p reason %d", hcon, reason);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index c7b66b2ea9f2..042d3ac3b4a3 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1411,7 +1411,8 @@ static void l2cap_request_info(struct l2cap_conn *conn)
 		       sizeof(req), &req);
 }
 
-static bool l2cap_check_enc_key_size(struct hci_conn *hcon)
+static bool l2cap_check_enc_key_size(struct hci_conn *hcon,
+				     struct l2cap_chan *chan)
 {
 	/* The minimum encryption key size needs to be enforced by the
 	 * host stack before establishing any L2CAP connections. The
@@ -1425,7 +1426,7 @@ static bool l2cap_check_enc_key_size(struct hci_conn *hcon)
 	int min_key_size = hcon->hdev->min_enc_key_size;
 
 	/* On FIPS security level, key size must be 16 bytes */
-	if (hcon->sec_level == BT_SECURITY_FIPS)
+	if (chan->sec_level == BT_SECURITY_FIPS)
 		min_key_size = 16;
 
 	return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) ||
@@ -1453,7 +1454,7 @@ static void l2cap_do_start(struct l2cap_chan *chan)
 	    !__l2cap_no_conn_pending(chan))
 		return;
 
-	if (l2cap_check_enc_key_size(conn->hcon))
+	if (l2cap_check_enc_key_size(conn->hcon, chan))
 		l2cap_start_connection(chan);
 	else
 		__set_chan_timer(chan, L2CAP_DISC_TIMEOUT);
@@ -1528,7 +1529,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
 				continue;
 			}
 
-			if (l2cap_check_enc_key_size(conn->hcon))
+			if (l2cap_check_enc_key_size(conn->hcon, chan))
 				l2cap_start_connection(chan);
 			else
 				l2cap_chan_close(chan, ECONNREFUSED);
@@ -3991,7 +3992,8 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd,
 
 	/* Check if the ACL is secure enough (if not SDP) */
 	if (psm != cpu_to_le16(L2CAP_PSM_SDP) &&
-	    !hci_conn_check_link_mode(conn->hcon)) {
+	    (!hci_conn_check_link_mode(conn->hcon) ||
+	    !l2cap_check_enc_key_size(conn->hcon, pchan))) {
 		conn->disc_reason = HCI_ERROR_AUTH_FAILURE;
 		result = L2CAP_CR_SEC_BLOCK;
 		goto response;
@@ -7351,7 +7353,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 		}
 
 		if (chan->state == BT_CONNECT) {
-			if (!status && l2cap_check_enc_key_size(hcon))
+			if (!status && l2cap_check_enc_key_size(hcon, chan))
 				l2cap_start_connection(chan);
 			else
 				__set_chan_timer(chan, L2CAP_DISC_TIMEOUT);
@@ -7361,7 +7363,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 			struct l2cap_conn_rsp rsp;
 			__u16 res, stat;
 
-			if (!status && l2cap_check_enc_key_size(hcon)) {
+			if (!status && l2cap_check_enc_key_size(hcon, chan)) {
 				if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) {
 					res = L2CAP_CR_PEND;
 					stat = L2CAP_CS_AUTHOR_PEND;
@@ -7414,6 +7416,9 @@ static int l2cap_recv_frag(struct l2cap_conn *conn, struct sk_buff *skb,
 			return -ENOMEM;
 		/* Init rx_len */
 		conn->rx_len = len;
+
+		skb_set_delivery_time(conn->rx_skb, skb->tstamp,
+				      skb->tstamp_type);
 	}
 
 	/* Copy as much as the rx_skb can hold */
@@ -7538,8 +7543,24 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
 		if (skb->len > len) {
 			BT_ERR("Frame is too long (len %u, expected len %d)",
 			       skb->len, len);
+			/* PTS test cases L2CAP/COS/CED/BI-14-C and BI-15-C
+			 * (Multiple Signaling Command in one PDU, Data
+			 * Truncated, BR/EDR) send a C-frame to the IUT with
+			 * PDU Length set to 8 and Channel ID set to the
+			 * correct signaling channel for the logical link.
+			 * The Information payload contains one L2CAP_ECHO_REQ
+			 * packet with Data Length set to 0 with 0 octets of
+			 * echo data and one invalid command packet due to
+			 * data truncated in PDU but present in HCI packet.
+			 *
+			 * Shorter the socket buffer to the PDU length to
+			 * allow to process valid commands from the PDU before
+			 * setting the socket unreliable.
+			 */
+			skb->len = len;
+			l2cap_recv_frame(conn, skb);
 			l2cap_conn_unreliable(conn, ECOMM);
-			goto drop;
+			goto unlock;
 		}
 
 		/* Append fragment into frame (with header) */
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index c1e1e529e26c..261926dccc7e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3221,7 +3221,8 @@ failed:
 static u8 link_to_bdaddr(u8 link_type, u8 addr_type)
 {
 	switch (link_type) {
-	case ISO_LINK:
+	case CIS_LINK:
+	case BIS_LINK:
 	case LE_LINK:
 		switch (addr_type) {
 		case ADDR_LE_DEV_PUBLIC:
@@ -7506,11 +7507,16 @@ static void add_device_complete(struct hci_dev *hdev, void *data, int err)
 	struct mgmt_cp_add_device *cp = cmd->param;
 
 	if (!err) {
+		struct hci_conn_params *params;
+
+		params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr,
+						le_addr_type(cp->addr.type));
+
 		device_added(cmd->sk, hdev, &cp->addr.bdaddr, cp->addr.type,
 			     cp->action);
 		device_flags_changed(NULL, hdev, &cp->addr.bdaddr,
 				     cp->addr.type, hdev->conn_flags,
-				     PTR_UINT(cmd->user_data));
+				     params ? params->flags : 0);
 	}
 
 	mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_ADD_DEVICE,
@@ -7613,8 +7619,6 @@ static int add_device(struct sock *sk, struct hci_dev *hdev,
 		goto unlock;
 	}
 
-	cmd->user_data = UINT_PTR(current_flags);
-
 	err = hci_cmd_sync_queue(hdev, add_device_sync, cmd,
 				 add_device_complete);
 	if (err < 0) {
diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c
index e5ff65e424b5..3713ff490c65 100644
--- a/net/bluetooth/mgmt_util.c
+++ b/net/bluetooth/mgmt_util.c
@@ -304,7 +304,7 @@ void mgmt_mesh_foreach(struct hci_dev *hdev,
 {
 	struct mgmt_mesh_tx *mesh_tx, *tmp;
 
-	list_for_each_entry_safe(mesh_tx, tmp, &hdev->mgmt_pending, list) {
+	list_for_each_entry_safe(mesh_tx, tmp, &hdev->mesh_pending, list) {
 		if (!sk || mesh_tx->sk == sk)
 			cb(mesh_tx, data);
 	}
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 183fcb362f9e..0adeafe11a36 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -284,6 +284,9 @@ int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on,
 	case BR_BOOLOPT_MST_ENABLE:
 		err = br_mst_set_enabled(br, on, extack);
 		break;
+	case BR_BOOLOPT_MDB_OFFLOAD_FAIL_NOTIFICATION:
+		br_opt_toggle(br, BROPT_MDB_OFFLOAD_FAIL_NOTIFICATION, on);
+		break;
 	default:
 		/* shouldn't be called with unsupported options */
 		WARN_ON(1);
@@ -302,6 +305,8 @@ int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt)
 		return br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED);
 	case BR_BOOLOPT_MST_ENABLE:
 		return br_opt_get(br, BROPT_MST_ENABLED);
+	case BR_BOOLOPT_MDB_OFFLOAD_FAIL_NOTIFICATION:
+		return br_opt_get(br, BROPT_MDB_OFFLOAD_FAIL_NOTIFICATION);
 	default:
 		/* shouldn't be called with unsupported options */
 		WARN_ON(1);
@@ -363,21 +368,20 @@ void br_opt_toggle(struct net_bridge *br, enum net_bridge_opts opt, bool on)
 		clear_bit(opt, &br->options);
 }
 
-static void __net_exit br_net_exit_batch_rtnl(struct list_head *net_list,
-					      struct list_head *dev_to_kill)
+static void __net_exit br_net_exit_rtnl(struct net *net,
+					struct list_head *dev_to_kill)
 {
 	struct net_device *dev;
-	struct net *net;
 
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list)
-		for_each_netdev(net, dev)
-			if (netif_is_bridge_master(dev))
-				br_dev_delete(dev, dev_to_kill);
+	ASSERT_RTNL_NET(net);
+
+	for_each_netdev(net, dev)
+		if (netif_is_bridge_master(dev))
+			br_dev_delete(dev, dev_to_kill);
 }
 
 static struct pernet_operations br_net_ops = {
-	.exit_batch_rtnl = br_net_exit_batch_rtnl,
+	.exit_rtnl = br_net_exit_rtnl,
 };
 
 static const struct stp_proto br_stp_proto = {
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 232133a0fd21..5f6ac9bf1527 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -189,7 +189,8 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
 		    br_multicast_querier_exists(brmctx, eth_hdr(skb), mdst)) {
 			if ((mdst && mdst->host_joined) ||
-			    br_multicast_is_router(brmctx, skb)) {
+			    br_multicast_is_router(brmctx, skb) ||
+			    br->dev->flags & IFF_ALLMULTI) {
 				local_rcv = true;
 				DEV_STATS_INC(br->dev, multicast);
 			}
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 722203b98ff7..400eb872b403 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -144,6 +144,8 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags)
 		e->flags |= MDB_FLAGS_STAR_EXCL;
 	if (flags & MDB_PG_FLAGS_BLOCKED)
 		e->flags |= MDB_FLAGS_BLOCKED;
+	if (flags & MDB_PG_FLAGS_OFFLOAD_FAILED)
+		e->flags |= MDB_FLAGS_OFFLOAD_FAILED;
 }
 
 static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip,
@@ -517,16 +519,17 @@ static size_t rtnl_mdb_nlmsg_size(const struct net_bridge_port_group *pg)
 	       rtnl_mdb_nlmsg_pg_size(pg);
 }
 
-void br_mdb_notify(struct net_device *dev,
-		   struct net_bridge_mdb_entry *mp,
-		   struct net_bridge_port_group *pg,
-		   int type)
+static void __br_mdb_notify(struct net_device *dev,
+			    struct net_bridge_mdb_entry *mp,
+			    struct net_bridge_port_group *pg,
+			    int type, bool notify_switchdev)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
 
-	br_switchdev_mdb_notify(dev, mp, pg, type);
+	if (notify_switchdev)
+		br_switchdev_mdb_notify(dev, mp, pg, type);
 
 	skb = nlmsg_new(rtnl_mdb_nlmsg_size(pg), GFP_ATOMIC);
 	if (!skb)
@@ -544,6 +547,21 @@ errout:
 	rtnl_set_sk_err(net, RTNLGRP_MDB, err);
 }
 
+void br_mdb_notify(struct net_device *dev,
+		   struct net_bridge_mdb_entry *mp,
+		   struct net_bridge_port_group *pg,
+		   int type)
+{
+	__br_mdb_notify(dev, mp, pg, type, true);
+}
+
+void br_mdb_flag_change_notify(struct net_device *dev,
+			       struct net_bridge_mdb_entry *mp,
+			       struct net_bridge_port_group *pg)
+{
+	__br_mdb_notify(dev, mp, pg, RTM_NEWMDB, false);
+}
+
 static int nlmsg_populate_rtr_fill(struct sk_buff *skb,
 				   struct net_device *dev,
 				   int ifindex, u16 vid, u32 pid,
diff --git a/net/bridge/br_mst.c b/net/bridge/br_mst.c
index 1820f09ff59c..3f24b4ee49c2 100644
--- a/net/bridge/br_mst.c
+++ b/net/bridge/br_mst.c
@@ -80,10 +80,10 @@ static void br_mst_vlan_set_state(struct net_bridge_vlan_group *vg,
 	if (br_vlan_get_state(v) == state)
 		return;
 
-	br_vlan_set_state(v, state);
-
 	if (v->vid == vg->pvid)
 		br_vlan_set_pvid_state(vg, state);
+
+	br_vlan_set_state(v, state);
 }
 
 int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state,
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index dcbf058de1e3..7e0b2362b9ee 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -2105,12 +2105,17 @@ static void __br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx)
 	}
 }
 
-void br_multicast_enable_port(struct net_bridge_port *port)
+static void br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx)
 {
-	struct net_bridge *br = port->br;
+	struct net_bridge *br = pmctx->port->br;
 
 	spin_lock_bh(&br->multicast_lock);
-	__br_multicast_enable_port_ctx(&port->multicast_ctx);
+	if (br_multicast_port_ctx_is_vlan(pmctx) &&
+	    !(pmctx->vlan->priv_flags & BR_VLFLAG_MCAST_ENABLED)) {
+		spin_unlock_bh(&br->multicast_lock);
+		return;
+	}
+	__br_multicast_enable_port_ctx(pmctx);
 	spin_unlock_bh(&br->multicast_lock);
 }
 
@@ -2137,11 +2142,67 @@ static void __br_multicast_disable_port_ctx(struct net_bridge_mcast_port *pmctx)
 	br_multicast_rport_del_notify(pmctx, del);
 }
 
+static void br_multicast_disable_port_ctx(struct net_bridge_mcast_port *pmctx)
+{
+	struct net_bridge *br = pmctx->port->br;
+
+	spin_lock_bh(&br->multicast_lock);
+	if (br_multicast_port_ctx_is_vlan(pmctx) &&
+	    !(pmctx->vlan->priv_flags & BR_VLFLAG_MCAST_ENABLED)) {
+		spin_unlock_bh(&br->multicast_lock);
+		return;
+	}
+
+	__br_multicast_disable_port_ctx(pmctx);
+	spin_unlock_bh(&br->multicast_lock);
+}
+
+static void br_multicast_toggle_port(struct net_bridge_port *port, bool on)
+{
+#if IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING)
+	if (br_opt_get(port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) {
+		struct net_bridge_vlan_group *vg;
+		struct net_bridge_vlan *vlan;
+
+		rcu_read_lock();
+		vg = nbp_vlan_group_rcu(port);
+		if (!vg) {
+			rcu_read_unlock();
+			return;
+		}
+
+		/* iterate each vlan, toggle vlan multicast context */
+		list_for_each_entry_rcu(vlan, &vg->vlan_list, vlist) {
+			struct net_bridge_mcast_port *pmctx =
+						&vlan->port_mcast_ctx;
+			u8 state = br_vlan_get_state(vlan);
+			/* enable vlan multicast context when state is
+			 * LEARNING or FORWARDING
+			 */
+			if (on && br_vlan_state_allowed(state, true))
+				br_multicast_enable_port_ctx(pmctx);
+			else
+				br_multicast_disable_port_ctx(pmctx);
+		}
+		rcu_read_unlock();
+		return;
+	}
+#endif
+	/* toggle port multicast context when vlan snooping is disabled */
+	if (on)
+		br_multicast_enable_port_ctx(&port->multicast_ctx);
+	else
+		br_multicast_disable_port_ctx(&port->multicast_ctx);
+}
+
+void br_multicast_enable_port(struct net_bridge_port *port)
+{
+	br_multicast_toggle_port(port, true);
+}
+
 void br_multicast_disable_port(struct net_bridge_port *port)
 {
-	spin_lock_bh(&port->br->multicast_lock);
-	__br_multicast_disable_port_ctx(&port->multicast_ctx);
-	spin_unlock_bh(&port->br->multicast_lock);
+	br_multicast_toggle_port(port, false);
 }
 
 static int __grp_src_delete_marked(struct net_bridge_port_group *pg)
@@ -4211,6 +4272,32 @@ static void __br_multicast_stop(struct net_bridge_mcast *brmctx)
 #endif
 }
 
+void br_multicast_update_vlan_mcast_ctx(struct net_bridge_vlan *v, u8 state)
+{
+#if IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING)
+	struct net_bridge *br;
+
+	if (!br_vlan_should_use(v))
+		return;
+
+	if (br_vlan_is_master(v))
+		return;
+
+	br = v->port->br;
+
+	if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED))
+		return;
+
+	if (br_vlan_state_allowed(state, true))
+		br_multicast_enable_port_ctx(&v->port_mcast_ctx);
+
+	/* Multicast is not disabled for the vlan when it goes in
+	 * blocking state because the timers will expire and stop by
+	 * themselves without sending more queries.
+	 */
+#endif
+}
+
 void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan, bool on)
 {
 	struct net_bridge *br;
@@ -4304,9 +4391,9 @@ int br_multicast_toggle_vlan_snooping(struct net_bridge *br, bool on,
 		__br_multicast_open(&br->multicast_ctx);
 	list_for_each_entry(p, &br->port_list, list) {
 		if (on)
-			br_multicast_disable_port(p);
+			br_multicast_disable_port_ctx(&p->multicast_ctx);
 		else
-			br_multicast_enable_port(p);
+			br_multicast_enable_port_ctx(&p->multicast_ctx);
 	}
 
 	list_for_each_entry(vlan, &vg->vlan_list, vlist)
diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c
index 98aea5485aae..a8c67035e23c 100644
--- a/net/bridge/br_nf_core.c
+++ b/net/bridge/br_nf_core.c
@@ -65,17 +65,14 @@ static struct dst_ops fake_dst_ops = {
  * ipt_REJECT needs it.  Future netfilter modules might
  * require us to fill additional fields.
  */
-static const u32 br_dst_default_metrics[RTAX_MAX] = {
-	[RTAX_MTU - 1] = 1500,
-};
-
 void br_netfilter_rtable_init(struct net_bridge *br)
 {
 	struct rtable *rt = &br->fake_rtable;
 
 	rcuref_init(&rt->dst.__rcuref, 1);
 	rt->dst.dev = br->dev;
-	dst_init_metrics(&rt->dst, br_dst_default_metrics, true);
+	dst_init_metrics(&rt->dst, br->metrics, false);
+	dst_metric_set(&rt->dst, RTAX_MTU, br->dev->mtu);
 	rt->dst.flags	= DST_NOXFRM | DST_FAKE_RTABLE;
 	rt->dst.ops = &fake_dst_ops;
 }
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index d5b3c5936a79..b159aae594c0 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -306,11 +306,12 @@ struct net_bridge_fdb_flush_desc {
 	u16				vlan_id;
 };
 
-#define MDB_PG_FLAGS_PERMANENT	BIT(0)
-#define MDB_PG_FLAGS_OFFLOAD	BIT(1)
-#define MDB_PG_FLAGS_FAST_LEAVE	BIT(2)
-#define MDB_PG_FLAGS_STAR_EXCL	BIT(3)
-#define MDB_PG_FLAGS_BLOCKED	BIT(4)
+#define MDB_PG_FLAGS_PERMANENT		BIT(0)
+#define MDB_PG_FLAGS_OFFLOAD		BIT(1)
+#define MDB_PG_FLAGS_FAST_LEAVE		BIT(2)
+#define MDB_PG_FLAGS_STAR_EXCL		BIT(3)
+#define MDB_PG_FLAGS_BLOCKED		BIT(4)
+#define MDB_PG_FLAGS_OFFLOAD_FAILED	BIT(5)
 
 #define PG_SRC_ENT_LIMIT	32
 
@@ -483,6 +484,7 @@ enum net_bridge_opts {
 	BROPT_VLAN_BRIDGE_BINDING,
 	BROPT_MCAST_VLAN_SNOOPING_ENABLED,
 	BROPT_MST_ENABLED,
+	BROPT_MDB_OFFLOAD_FAIL_NOTIFICATION,
 };
 
 struct net_bridge {
@@ -505,6 +507,7 @@ struct net_bridge {
 		struct rtable		fake_rtable;
 		struct rt6_info		fake_rt6_info;
 	};
+	u32				metrics[RTAX_MAX];
 #endif
 	u16				group_fwd_mask;
 	u16				group_fwd_mask_required;
@@ -1002,6 +1005,8 @@ int br_mdb_hash_init(struct net_bridge *br);
 void br_mdb_hash_fini(struct net_bridge *br);
 void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp,
 		   struct net_bridge_port_group *pg, int type);
+void br_mdb_flag_change_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp,
+			       struct net_bridge_port_group *pg);
 void br_rtr_notify(struct net_device *dev, struct net_bridge_mcast_port *pmctx,
 		   int type);
 void br_multicast_del_pg(struct net_bridge_mdb_entry *mp,
@@ -1051,6 +1056,7 @@ void br_multicast_port_ctx_init(struct net_bridge_port *port,
 				struct net_bridge_vlan *vlan,
 				struct net_bridge_mcast_port *pmctx);
 void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pmctx);
+void br_multicast_update_vlan_mcast_ctx(struct net_bridge_vlan *v, u8 state);
 void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan, bool on);
 int br_multicast_toggle_vlan_snooping(struct net_bridge *br, bool on,
 				      struct netlink_ext_ack *extack);
@@ -1342,6 +1348,22 @@ br_multicast_ctx_matches_vlan_snooping(const struct net_bridge_mcast *brmctx)
 
 	return !!(vlan_snooping_enabled == br_multicast_ctx_is_vlan(brmctx));
 }
+
+static inline void
+br_multicast_set_pg_offload_flags(struct net_bridge_port_group *p,
+				  bool offloaded)
+{
+	p->flags &= ~(MDB_PG_FLAGS_OFFLOAD | MDB_PG_FLAGS_OFFLOAD_FAILED);
+	p->flags |= (offloaded ? MDB_PG_FLAGS_OFFLOAD :
+		MDB_PG_FLAGS_OFFLOAD_FAILED);
+}
+
+static inline bool
+br_mdb_should_notify(const struct net_bridge *br, u8 changed_flags)
+{
+	return br_opt_get(br, BROPT_MDB_OFFLOAD_FAIL_NOTIFICATION) &&
+		(changed_flags & MDB_PG_FLAGS_OFFLOAD_FAILED);
+}
 #else
 static inline int br_multicast_rcv(struct net_bridge_mcast **brmctx,
 				   struct net_bridge_mcast_port **pmctx,
@@ -1501,6 +1523,11 @@ static inline void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pm
 {
 }
 
+static inline void br_multicast_update_vlan_mcast_ctx(struct net_bridge_vlan *v,
+						      u8 state)
+{
+}
+
 static inline void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan,
 						bool on)
 {
@@ -1861,7 +1888,9 @@ bool br_vlan_global_opts_can_enter_range(const struct net_bridge_vlan *v_curr,
 bool br_vlan_global_opts_fill(struct sk_buff *skb, u16 vid, u16 vid_range,
 			      const struct net_bridge_vlan *v_opts);
 
-/* vlan state manipulation helpers using *_ONCE to annotate lock-free access */
+/* vlan state manipulation helpers using *_ONCE to annotate lock-free access,
+ * while br_vlan_set_state() may access data protected by multicast_lock.
+ */
 static inline u8 br_vlan_get_state(const struct net_bridge_vlan *v)
 {
 	return READ_ONCE(v->state);
@@ -1870,6 +1899,7 @@ static inline u8 br_vlan_get_state(const struct net_bridge_vlan *v)
 static inline void br_vlan_set_state(struct net_bridge_vlan *v, u8 state)
 {
 	WRITE_ONCE(v->state, state);
+	br_multicast_update_vlan_mcast_ctx(v, state);
 }
 
 static inline u8 br_vlan_get_pvid_state(const struct net_bridge_vlan_group *vg)
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index 7b41ee8740cb..95d7355a0407 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -504,9 +504,10 @@ static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *pri
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port *port = data->port;
 	struct net_bridge *br = port->br;
+	u8 old_flags;
 
-	if (err)
-		goto err;
+	if (err == -EOPNOTSUPP)
+		goto out_free;
 
 	spin_lock_bh(&br->multicast_lock);
 	mp = br_mdb_ip_get(br, &data->ip);
@@ -516,11 +517,15 @@ static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *pri
 	     pp = &p->next) {
 		if (p->key.port != port)
 			continue;
-		p->flags |= MDB_PG_FLAGS_OFFLOAD;
+
+		old_flags = p->flags;
+		br_multicast_set_pg_offload_flags(p, !err);
+		if (br_mdb_should_notify(br, old_flags ^ p->flags))
+			br_mdb_flag_change_notify(br->dev, mp, p);
 	}
 out:
 	spin_unlock_bh(&br->multicast_lock);
-err:
+out_free:
 	kfree(priv);
 }
 
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index d9a69ec9affe..939a3aa78d5c 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -715,8 +715,8 @@ static int br_vlan_add_existing(struct net_bridge *br,
 				u16 flags, bool *changed,
 				struct netlink_ext_ack *extack)
 {
-	bool would_change = __vlan_flags_would_change(vlan, flags);
 	bool becomes_brentry = false;
+	bool would_change = false;
 	int err;
 
 	if (!br_vlan_is_brentry(vlan)) {
@@ -725,6 +725,8 @@ static int br_vlan_add_existing(struct net_bridge *br,
 			return -EINVAL;
 
 		becomes_brentry = true;
+	} else {
+		would_change = __vlan_flags_would_change(vlan, flags);
 	}
 
 	/* Master VLANs that aren't brentries weren't notified before,
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 816bb0fde718..6482de4d8750 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -60,19 +60,19 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 		struct ip_fraglist_iter iter;
 		struct sk_buff *frag;
 
-		if (first_len - hlen > mtu ||
-		    skb_headroom(skb) < ll_rs)
+		if (first_len - hlen > mtu)
 			goto blackhole;
 
-		if (skb_cloned(skb))
+		if (skb_cloned(skb) ||
+		    skb_headroom(skb) < ll_rs)
 			goto slow_path;
 
 		skb_walk_frags(skb, frag) {
-			if (frag->len > mtu ||
-			    skb_headroom(frag) < hlen + ll_rs)
+			if (frag->len > mtu)
 				goto blackhole;
 
-			if (skb_shared(frag))
+			if (skb_shared(frag) ||
+			    skb_headroom(frag) < hlen + ll_rs)
 				goto slow_path;
 		}
 
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 0bca1b9b3f70..6bc1cc4c94c5 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -58,6 +58,7 @@
 #include <linux/can/skb.h>
 #include <linux/can/bcm.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
 #include <net/sock.h>
 #include <net/net_namespace.h>
 
@@ -122,6 +123,7 @@ struct bcm_op {
 	struct canfd_frame last_sframe;
 	struct sock *sk;
 	struct net_device *rx_reg_dev;
+	spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */
 };
 
 struct bcm_sock {
@@ -217,7 +219,9 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, " / bound %s", bcm_proc_getifname(net, ifname, bo->ifindex));
 	seq_printf(m, " <<<\n");
 
-	list_for_each_entry(op, &bo->rx_ops, list) {
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(op, &bo->rx_ops, list) {
 
 		unsigned long reduction;
 
@@ -273,6 +277,9 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 		seq_printf(m, "# sent %ld\n", op->frames_abs);
 	}
 	seq_putc(m, '\n');
+
+	rcu_read_unlock();
+
 	return 0;
 }
 #endif /* CONFIG_PROC_FS */
@@ -285,13 +292,18 @@ static void bcm_can_tx(struct bcm_op *op)
 {
 	struct sk_buff *skb;
 	struct net_device *dev;
-	struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe;
+	struct canfd_frame *cf;
 	int err;
 
 	/* no target device? => exit */
 	if (!op->ifindex)
 		return;
 
+	/* read currframe under lock protection */
+	spin_lock_bh(&op->bcm_tx_lock);
+	cf = op->frames + op->cfsiz * op->currframe;
+	spin_unlock_bh(&op->bcm_tx_lock);
+
 	dev = dev_get_by_index(sock_net(op->sk), op->ifindex);
 	if (!dev) {
 		/* RFC: should this bcm_op remove itself here? */
@@ -312,6 +324,10 @@ static void bcm_can_tx(struct bcm_op *op)
 	skb->dev = dev;
 	can_skb_set_owner(skb, op->sk);
 	err = can_send(skb, 1);
+
+	/* update currframe and count under lock protection */
+	spin_lock_bh(&op->bcm_tx_lock);
+
 	if (!err)
 		op->frames_abs++;
 
@@ -320,6 +336,11 @@ static void bcm_can_tx(struct bcm_op *op)
 	/* reached last frame? */
 	if (op->currframe >= op->nframes)
 		op->currframe = 0;
+
+	if (op->count > 0)
+		op->count--;
+
+	spin_unlock_bh(&op->bcm_tx_lock);
 out:
 	dev_put(dev);
 }
@@ -430,7 +451,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
 	struct bcm_msg_head msg_head;
 
 	if (op->kt_ival1 && (op->count > 0)) {
-		op->count--;
+		bcm_can_tx(op);
 		if (!op->count && (op->flags & TX_COUNTEVT)) {
 
 			/* create notification to user */
@@ -445,7 +466,6 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
 
 			bcm_send_to_user(op, &msg_head, NULL, 0);
 		}
-		bcm_can_tx(op);
 
 	} else if (op->kt_ival2) {
 		bcm_can_tx(op);
@@ -843,7 +863,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
 						  REGMASK(op->can_id),
 						  bcm_rx_handler, op);
 
-			list_del(&op->list);
+			list_del_rcu(&op->list);
 			bcm_remove_op(op);
 			return 1; /* done */
 		}
@@ -863,7 +883,7 @@ static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh,
 	list_for_each_entry_safe(op, n, ops, list) {
 		if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
 		    (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
-			list_del(&op->list);
+			list_del_rcu(&op->list);
 			bcm_remove_op(op);
 			return 1; /* done */
 		}
@@ -956,6 +976,27 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		}
 		op->flags = msg_head->flags;
 
+		/* only lock for unlikely count/nframes/currframe changes */
+		if (op->nframes != msg_head->nframes ||
+		    op->flags & TX_RESET_MULTI_IDX ||
+		    op->flags & SETTIMER) {
+
+			spin_lock_bh(&op->bcm_tx_lock);
+
+			if (op->nframes != msg_head->nframes ||
+			    op->flags & TX_RESET_MULTI_IDX) {
+				/* potentially update changed nframes */
+				op->nframes = msg_head->nframes;
+				/* restart multiple frame transmission */
+				op->currframe = 0;
+			}
+
+			if (op->flags & SETTIMER)
+				op->count = msg_head->count;
+
+			spin_unlock_bh(&op->bcm_tx_lock);
+		}
+
 	} else {
 		/* insert new BCM operation for the given can_id */
 
@@ -963,9 +1004,14 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		if (!op)
 			return -ENOMEM;
 
+		spin_lock_init(&op->bcm_tx_lock);
 		op->can_id = msg_head->can_id;
 		op->cfsiz = CFSIZ(msg_head->flags);
 		op->flags = msg_head->flags;
+		op->nframes = msg_head->nframes;
+
+		if (op->flags & SETTIMER)
+			op->count = msg_head->count;
 
 		/* create array for CAN frames and copy the data */
 		if (msg_head->nframes > 1) {
@@ -1023,22 +1069,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 	} /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */
 
-	if (op->nframes != msg_head->nframes) {
-		op->nframes   = msg_head->nframes;
-		/* start multiple frame transmission with index 0 */
-		op->currframe = 0;
-	}
-
-	/* check flags */
-
-	if (op->flags & TX_RESET_MULTI_IDX) {
-		/* start multiple frame transmission with index 0 */
-		op->currframe = 0;
-	}
-
 	if (op->flags & SETTIMER) {
 		/* set timer values */
-		op->count = msg_head->count;
 		op->ival1 = msg_head->ival1;
 		op->ival2 = msg_head->ival2;
 		op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
@@ -1055,11 +1087,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		op->flags |= TX_ANNOUNCE;
 	}
 
-	if (op->flags & TX_ANNOUNCE) {
+	if (op->flags & TX_ANNOUNCE)
 		bcm_can_tx(op);
-		if (op->count)
-			op->count--;
-	}
 
 	if (op->flags & STARTTIMER)
 		bcm_tx_start_timer(op);
@@ -1272,7 +1301,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 					      bcm_rx_handler, op, "bcm", sk);
 		if (err) {
 			/* this bcm rx op is broken -> remove it */
-			list_del(&op->list);
+			list_del_rcu(&op->list);
 			bcm_remove_op(op);
 			return err;
 		}
diff --git a/net/can/gw.c b/net/can/gw.c
index ef93293c1fae..55eccb1c7620 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -130,7 +130,7 @@ struct cgw_job {
 	u32 handled_frames;
 	u32 dropped_frames;
 	u32 deleted_frames;
-	struct cf_mod mod;
+	struct cf_mod __rcu *cf_mod;
 	union {
 		/* CAN frame data source */
 		struct net_device *dev;
@@ -459,6 +459,7 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
 	struct cgw_job *gwj = (struct cgw_job *)data;
 	struct canfd_frame *cf;
 	struct sk_buff *nskb;
+	struct cf_mod *mod;
 	int modidx = 0;
 
 	/* process strictly Classic CAN or CAN FD frames */
@@ -506,7 +507,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
 	 * When there is at least one modification function activated,
 	 * we need to copy the skb as we want to modify skb->data.
 	 */
-	if (gwj->mod.modfunc[0])
+	mod = rcu_dereference(gwj->cf_mod);
+	if (mod->modfunc[0])
 		nskb = skb_copy(skb, GFP_ATOMIC);
 	else
 		nskb = skb_clone(skb, GFP_ATOMIC);
@@ -529,8 +531,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
 	cf = (struct canfd_frame *)nskb->data;
 
 	/* perform preprocessed modification functions if there are any */
-	while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx])
-		(*gwj->mod.modfunc[modidx++])(cf, &gwj->mod);
+	while (modidx < MAX_MODFUNCTIONS && mod->modfunc[modidx])
+		(*mod->modfunc[modidx++])(cf, mod);
 
 	/* Has the CAN frame been modified? */
 	if (modidx) {
@@ -546,11 +548,11 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
 		}
 
 		/* check for checksum updates */
-		if (gwj->mod.csumfunc.crc8)
-			(*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8);
+		if (mod->csumfunc.crc8)
+			(*mod->csumfunc.crc8)(cf, &mod->csum.crc8);
 
-		if (gwj->mod.csumfunc.xor)
-			(*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor);
+		if (mod->csumfunc.xor)
+			(*mod->csumfunc.xor)(cf, &mod->csum.xor);
 	}
 
 	/* clear the skb timestamp if not configured the other way */
@@ -581,9 +583,20 @@ static void cgw_job_free_rcu(struct rcu_head *rcu_head)
 {
 	struct cgw_job *gwj = container_of(rcu_head, struct cgw_job, rcu);
 
+	/* cgw_job::cf_mod is always accessed from the same cgw_job object within
+	 * the same RCU read section. Once cgw_job is scheduled for removal,
+	 * cf_mod can also be removed without mandating an additional grace period.
+	 */
+	kfree(rcu_access_pointer(gwj->cf_mod));
 	kmem_cache_free(cgw_cache, gwj);
 }
 
+/* Return cgw_job::cf_mod with RTNL protected section */
+static struct cf_mod *cgw_job_cf_mod(struct cgw_job *gwj)
+{
+	return rcu_dereference_protected(gwj->cf_mod, rtnl_is_locked());
+}
+
 static int cgw_notifier(struct notifier_block *nb,
 			unsigned long msg, void *ptr)
 {
@@ -616,6 +629,7 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type,
 {
 	struct rtcanmsg *rtcan;
 	struct nlmsghdr *nlh;
+	struct cf_mod *mod;
 
 	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtcan), flags);
 	if (!nlh)
@@ -650,82 +664,83 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type,
 			goto cancel;
 	}
 
+	mod = cgw_job_cf_mod(gwj);
 	if (gwj->flags & CGW_FLAGS_CAN_FD) {
 		struct cgw_fdframe_mod mb;
 
-		if (gwj->mod.modtype.and) {
-			memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf));
-			mb.modtype = gwj->mod.modtype.and;
+		if (mod->modtype.and) {
+			memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf));
+			mb.modtype = mod->modtype.and;
 			if (nla_put(skb, CGW_FDMOD_AND, sizeof(mb), &mb) < 0)
 				goto cancel;
 		}
 
-		if (gwj->mod.modtype.or) {
-			memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf));
-			mb.modtype = gwj->mod.modtype.or;
+		if (mod->modtype.or) {
+			memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf));
+			mb.modtype = mod->modtype.or;
 			if (nla_put(skb, CGW_FDMOD_OR, sizeof(mb), &mb) < 0)
 				goto cancel;
 		}
 
-		if (gwj->mod.modtype.xor) {
-			memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf));
-			mb.modtype = gwj->mod.modtype.xor;
+		if (mod->modtype.xor) {
+			memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf));
+			mb.modtype = mod->modtype.xor;
 			if (nla_put(skb, CGW_FDMOD_XOR, sizeof(mb), &mb) < 0)
 				goto cancel;
 		}
 
-		if (gwj->mod.modtype.set) {
-			memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf));
-			mb.modtype = gwj->mod.modtype.set;
+		if (mod->modtype.set) {
+			memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf));
+			mb.modtype = mod->modtype.set;
 			if (nla_put(skb, CGW_FDMOD_SET, sizeof(mb), &mb) < 0)
 				goto cancel;
 		}
 	} else {
 		struct cgw_frame_mod mb;
 
-		if (gwj->mod.modtype.and) {
-			memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf));
-			mb.modtype = gwj->mod.modtype.and;
+		if (mod->modtype.and) {
+			memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf));
+			mb.modtype = mod->modtype.and;
 			if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0)
 				goto cancel;
 		}
 
-		if (gwj->mod.modtype.or) {
-			memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf));
-			mb.modtype = gwj->mod.modtype.or;
+		if (mod->modtype.or) {
+			memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf));
+			mb.modtype = mod->modtype.or;
 			if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0)
 				goto cancel;
 		}
 
-		if (gwj->mod.modtype.xor) {
-			memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf));
-			mb.modtype = gwj->mod.modtype.xor;
+		if (mod->modtype.xor) {
+			memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf));
+			mb.modtype = mod->modtype.xor;
 			if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0)
 				goto cancel;
 		}
 
-		if (gwj->mod.modtype.set) {
-			memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf));
-			mb.modtype = gwj->mod.modtype.set;
+		if (mod->modtype.set) {
+			memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf));
+			mb.modtype = mod->modtype.set;
 			if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0)
 				goto cancel;
 		}
 	}
 
-	if (gwj->mod.uid) {
-		if (nla_put_u32(skb, CGW_MOD_UID, gwj->mod.uid) < 0)
+	if (mod->uid) {
+		if (nla_put_u32(skb, CGW_MOD_UID, mod->uid) < 0)
 			goto cancel;
 	}
 
-	if (gwj->mod.csumfunc.crc8) {
+	if (mod->csumfunc.crc8) {
 		if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN,
-			    &gwj->mod.csum.crc8) < 0)
+			    &mod->csum.crc8) < 0)
 			goto cancel;
 	}
 
-	if (gwj->mod.csumfunc.xor) {
+	if (mod->csumfunc.xor) {
 		if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN,
-			    &gwj->mod.csum.xor) < 0)
+			    &mod->csum.xor) < 0)
 			goto cancel;
 	}
 
@@ -1059,7 +1074,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct rtcanmsg *r;
 	struct cgw_job *gwj;
-	struct cf_mod mod;
+	struct cf_mod *mod;
 	struct can_can_gw ccgw;
 	u8 limhops = 0;
 	int err = 0;
@@ -1078,37 +1093,48 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh,
 	if (r->gwtype != CGW_TYPE_CAN_CAN)
 		return -EINVAL;
 
-	err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops);
+	mod = kmalloc(sizeof(*mod), GFP_KERNEL);
+	if (!mod)
+		return -ENOMEM;
+
+	err = cgw_parse_attr(nlh, mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops);
 	if (err < 0)
-		return err;
+		goto out_free_cf;
 
-	if (mod.uid) {
+	if (mod->uid) {
 		ASSERT_RTNL();
 
 		/* check for updating an existing job with identical uid */
 		hlist_for_each_entry(gwj, &net->can.cgw_list, list) {
-			if (gwj->mod.uid != mod.uid)
+			struct cf_mod *old_cf;
+
+			old_cf = cgw_job_cf_mod(gwj);
+			if (old_cf->uid != mod->uid)
 				continue;
 
 			/* interfaces & filters must be identical */
-			if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw)))
-				return -EINVAL;
+			if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) {
+				err = -EINVAL;
+				goto out_free_cf;
+			}
 
-			/* update modifications with disabled softirq & quit */
-			local_bh_disable();
-			memcpy(&gwj->mod, &mod, sizeof(mod));
-			local_bh_enable();
+			rcu_assign_pointer(gwj->cf_mod, mod);
+			kfree_rcu_mightsleep(old_cf);
 			return 0;
 		}
 	}
 
 	/* ifindex == 0 is not allowed for job creation */
-	if (!ccgw.src_idx || !ccgw.dst_idx)
-		return -ENODEV;
+	if (!ccgw.src_idx || !ccgw.dst_idx) {
+		err = -ENODEV;
+		goto out_free_cf;
+	}
 
 	gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL);
-	if (!gwj)
-		return -ENOMEM;
+	if (!gwj) {
+		err = -ENOMEM;
+		goto out_free_cf;
+	}
 
 	gwj->handled_frames = 0;
 	gwj->dropped_frames = 0;
@@ -1118,7 +1144,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh,
 	gwj->limit_hops = limhops;
 
 	/* insert already parsed information */
-	memcpy(&gwj->mod, &mod, sizeof(mod));
+	RCU_INIT_POINTER(gwj->cf_mod, mod);
 	memcpy(&gwj->ccgw, &ccgw, sizeof(ccgw));
 
 	err = -ENODEV;
@@ -1152,9 +1178,11 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh,
 	if (!err)
 		hlist_add_head_rcu(&gwj->list, &net->can.cgw_list);
 out:
-	if (err)
+	if (err) {
 		kmem_cache_free(cgw_cache, gwj);
-
+out_free_cf:
+		kfree(mod);
+	}
 	return err;
 }
 
@@ -1214,19 +1242,22 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	/* remove only the first matching entry */
 	hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) {
+		struct cf_mod *cf_mod;
+
 		if (gwj->flags != r->flags)
 			continue;
 
 		if (gwj->limit_hops != limhops)
 			continue;
 
+		cf_mod = cgw_job_cf_mod(gwj);
 		/* we have a match when uid is enabled and identical */
-		if (gwj->mod.uid || mod.uid) {
-			if (gwj->mod.uid != mod.uid)
+		if (cf_mod->uid || mod.uid) {
+			if (cf_mod->uid != mod.uid)
 				continue;
 		} else {
 			/* no uid => check for identical modifications */
-			if (memcmp(&gwj->mod, &mod, sizeof(mod)))
+			if (memcmp(cf_mod, &mod, sizeof(mod)))
 				continue;
 		}
 
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 17226b2341d0..6fefe7a68761 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -655,6 +655,7 @@ static int j1939_sk_release(struct socket *sock)
 	sock->sk = NULL;
 
 	release_sock(sk);
+	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	sock_put(sk);
 
 	return 0;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index b24afec24138..6664ea73ccf8 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -220,16 +220,6 @@ void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *osd_req,
 }
 EXPORT_SYMBOL(osd_req_op_extent_osd_data_pages);
 
-void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *osd_req,
-			unsigned int which, struct ceph_pagelist *pagelist)
-{
-	struct ceph_osd_data *osd_data;
-
-	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
-	ceph_osd_data_pagelist_init(osd_data, pagelist);
-}
-EXPORT_SYMBOL(osd_req_op_extent_osd_data_pagelist);
-
 #ifdef CONFIG_BLOCK
 void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
 				    unsigned int which,
@@ -297,19 +287,6 @@ static void osd_req_op_cls_request_info_pagelist(
 	ceph_osd_data_pagelist_init(osd_data, pagelist);
 }
 
-void osd_req_op_cls_request_data_pagelist(
-			struct ceph_osd_request *osd_req,
-			unsigned int which, struct ceph_pagelist *pagelist)
-{
-	struct ceph_osd_data *osd_data;
-
-	osd_data = osd_req_op_data(osd_req, which, cls, request_data);
-	ceph_osd_data_pagelist_init(osd_data, pagelist);
-	osd_req->r_ops[which].cls.indata_len += pagelist->length;
-	osd_req->r_ops[which].indata_len += pagelist->length;
-}
-EXPORT_SYMBOL(osd_req_op_cls_request_data_pagelist);
-
 void osd_req_op_cls_request_data_pages(struct ceph_osd_request *osd_req,
 			unsigned int which, struct page **pages, u64 length,
 			u32 alignment, bool pages_from_pool, bool own_pages)
diff --git a/net/core/datagram.c b/net/core/datagram.c
index f0634f0cb834..94cc4705e91d 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -52,6 +52,7 @@
 #include <linux/pagemap.h>
 #include <linux/iov_iter.h>
 #include <linux/indirect_call_wrapper.h>
+#include <linux/crc32.h>
 
 #include <net/protocol.h>
 #include <linux/skbuff.h>
@@ -61,7 +62,8 @@
 #include <net/tcp_states.h>
 #include <trace/events/skb.h>
 #include <net/busy_poll.h>
-#include <crypto/hash.h>
+
+#include "devmem.h"
 
 /*
  *	Is a socket 'connection oriented' ?
@@ -481,41 +483,37 @@ short_copy:
 	return 0;
 }
 
-static size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
-				    struct iov_iter *i)
+#ifdef CONFIG_NET_CRC32C
+static size_t crc32c_and_copy_to_iter(const void *addr, size_t bytes,
+				      void *_crcp, struct iov_iter *i)
 {
-#ifdef CONFIG_CRYPTO_HASH
-	struct ahash_request *hash = hashp;
-	struct scatterlist sg;
+	u32 *crcp = _crcp;
 	size_t copied;
 
 	copied = copy_to_iter(addr, bytes, i);
-	sg_init_one(&sg, addr, copied);
-	ahash_request_set_crypt(hash, &sg, NULL, copied);
-	crypto_ahash_update(hash);
+	*crcp = crc32c(*crcp, addr, copied);
 	return copied;
-#else
-	return 0;
-#endif
 }
 
 /**
- *	skb_copy_and_hash_datagram_iter - Copy datagram to an iovec iterator
- *          and update a hash.
+ *	skb_copy_and_crc32c_datagram_iter - Copy datagram to an iovec iterator
+ *		and update a CRC32C value.
  *	@skb: buffer to copy
  *	@offset: offset in the buffer to start copying from
  *	@to: iovec iterator to copy to
  *	@len: amount of data to copy from buffer to iovec
- *      @hash: hash request to update
+ *	@crcp: pointer to CRC32C value to update
+ *
+ *	Return: 0 on success, -EFAULT if there was a fault during copy.
  */
-int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset,
-			   struct iov_iter *to, int len,
-			   struct ahash_request *hash)
+int skb_copy_and_crc32c_datagram_iter(const struct sk_buff *skb, int offset,
+				      struct iov_iter *to, int len, u32 *crcp)
 {
 	return __skb_datagram_iter(skb, offset, to, len, true,
-			hash_and_copy_to_iter, hash);
+				   crc32c_and_copy_to_iter, crcp);
 }
-EXPORT_SYMBOL(skb_copy_and_hash_datagram_iter);
+EXPORT_SYMBOL(skb_copy_and_crc32c_datagram_iter);
+#endif /* CONFIG_NET_CRC32C */
 
 static size_t simple_copy_to_iter(const void *addr, size_t bytes,
 		void *data __always_unused, struct iov_iter *i)
@@ -691,9 +689,50 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
 	return 0;
 }
 
+static int
+zerocopy_fill_skb_from_devmem(struct sk_buff *skb, struct iov_iter *from,
+			      int length,
+			      struct net_devmem_dmabuf_binding *binding)
+{
+	int i = skb_shinfo(skb)->nr_frags;
+	size_t virt_addr, size, off;
+	struct net_iov *niov;
+
+	/* Devmem filling works by taking an IOVEC from the user where the
+	 * iov_addrs are interpreted as an offset in bytes into the dma-buf to
+	 * send from. We do not support other iter types.
+	 */
+	if (iov_iter_type(from) != ITER_IOVEC &&
+	    iov_iter_type(from) != ITER_UBUF)
+		return -EFAULT;
+
+	while (length && iov_iter_count(from)) {
+		if (i == MAX_SKB_FRAGS)
+			return -EMSGSIZE;
+
+		virt_addr = (size_t)iter_iov_addr(from);
+		niov = net_devmem_get_niov_at(binding, virt_addr, &off, &size);
+		if (!niov)
+			return -EFAULT;
+
+		size = min_t(size_t, size, length);
+		size = min_t(size_t, size, iter_iov_len(from));
+
+		get_netmem(net_iov_to_netmem(niov));
+		skb_add_rx_frag_netmem(skb, i, net_iov_to_netmem(niov), off,
+				       size, PAGE_SIZE);
+		iov_iter_advance(from, size);
+		length -= size;
+		i++;
+	}
+
+	return 0;
+}
+
 int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 			    struct sk_buff *skb, struct iov_iter *from,
-			    size_t length)
+			    size_t length,
+			    struct net_devmem_dmabuf_binding *binding)
 {
 	unsigned long orig_size = skb->truesize;
 	unsigned long truesize;
@@ -701,6 +740,8 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 
 	if (msg && msg->msg_ubuf && msg->sg_from_iter)
 		ret = msg->sg_from_iter(skb, from, length);
+	else if (binding)
+		ret = zerocopy_fill_skb_from_devmem(skb, from, length, binding);
 	else
 		ret = zerocopy_fill_skb_from_iter(skb, from, length);
 
@@ -734,7 +775,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 	if (skb_copy_datagram_from_iter(skb, 0, from, copy))
 		return -EFAULT;
 
-	return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U);
+	return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U, NULL);
 }
 EXPORT_SYMBOL(zerocopy_sg_from_iter);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index d0563ddff6ca..3eb4e945f312 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -462,7 +462,9 @@ EXPORT_PER_CPU_SYMBOL(softnet_data);
  * PP consumers must pay attention to run APIs in the appropriate context
  * (e.g. NAPI context).
  */
-DEFINE_PER_CPU(struct page_pool *, system_page_pool);
+DEFINE_PER_CPU(struct page_pool_bh, system_page_pool) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 #ifdef CONFIG_LOCKDEP
 /*
@@ -1572,6 +1574,8 @@ EXPORT_SYMBOL(netdev_features_change);
 
 void netif_state_change(struct net_device *dev)
 {
+	netdev_ops_assert_locked_or_invisible(dev);
+
 	if (dev->flags & IFF_UP) {
 		struct netdev_notifier_change_info change_info = {
 			.info.dev = dev,
@@ -3592,9 +3596,10 @@ out:
 }
 EXPORT_SYMBOL(skb_checksum_help);
 
+#ifdef CONFIG_NET_CRC32C
 int skb_crc32c_csum_help(struct sk_buff *skb)
 {
-	__le32 crc32c_csum;
+	u32 crc;
 	int ret = 0, offset, start;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -3622,15 +3627,14 @@ int skb_crc32c_csum_help(struct sk_buff *skb)
 	if (ret)
 		goto out;
 
-	crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start,
-						  skb->len - start, ~(__u32)0,
-						  crc32c_csum_stub));
-	*(__le32 *)(skb->data + offset) = crc32c_csum;
+	crc = ~skb_crc32c(skb, start, skb->len - start, ~0);
+	*(__le32 *)(skb->data + offset) = cpu_to_le32(crc);
 	skb_reset_csum_not_inet(skb);
 out:
 	return ret;
 }
 EXPORT_SYMBOL(skb_crc32c_csum_help);
+#endif /* CONFIG_NET_CRC32C */
 
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
@@ -3894,12 +3898,42 @@ sw_checksum:
 }
 EXPORT_SYMBOL(skb_csum_hwoffload_help);
 
+static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb,
+						    struct net_device *dev)
+{
+	struct skb_shared_info *shinfo;
+	struct net_iov *niov;
+
+	if (likely(skb_frags_readable(skb)))
+		goto out;
+
+	if (!dev->netmem_tx)
+		goto out_free;
+
+	shinfo = skb_shinfo(skb);
+
+	if (shinfo->nr_frags > 0) {
+		niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0]));
+		if (net_is_devmem_iov(niov) &&
+		    net_devmem_iov_binding(niov)->dev != dev)
+			goto out_free;
+	}
+
+out:
+	return skb;
+
+out_free:
+	kfree_skb(skb);
+	return NULL;
+}
+
 static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again)
 {
 	netdev_features_t features;
 
-	if (!skb_frags_readable(skb))
-		goto out_kfree_skb;
+	skb = validate_xmit_unreadable_skb(skb, dev);
+	if (unlikely(!skb))
+		goto out_null;
 
 	features = netif_skb_features(skb);
 	skb = validate_xmit_vlan(skb, features);
@@ -4781,6 +4815,7 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 	}
 
 use_local_napi:
+	DEBUG_NET_WARN_ON_ONCE(!list_empty(&napi->poll_list));
 	list_add_tail(&napi->poll_list, &sd->poll_list);
 	WRITE_ONCE(napi->list_owner, smp_processor_id());
 	/* If not called from net_rx_action()
@@ -5290,7 +5325,10 @@ netif_skb_check_for_xdp(struct sk_buff **pskb, const struct bpf_prog *prog)
 	struct sk_buff *skb = *pskb;
 	int err, hroom, troom;
 
-	if (!skb_cow_data_for_xdp(this_cpu_read(system_page_pool), pskb, prog))
+	local_lock_nested_bh(&system_page_pool.bh_lock);
+	err = skb_cow_data_for_xdp(this_cpu_read(system_page_pool.pool), pskb, prog);
+	local_unlock_nested_bh(&system_page_pool.bh_lock);
+	if (!err)
 		return 0;
 
 	/* In case we have to go down the path and also linearize,
@@ -7439,9 +7477,14 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 
 	work = __napi_poll(n, &do_repoll);
 
-	if (do_repoll)
+	if (do_repoll) {
+#if defined(CONFIG_DEBUG_NET)
+		if (unlikely(!napi_is_scheduled(n)))
+			pr_crit("repoll requested for device %s %ps but napi is not scheduled.\n",
+				n->dev->name, n->poll);
+#endif
 		list_add_tail(&n->poll_list, repoll);
-
+	}
 	netpoll_poll_unlock(have);
 
 	return work;
@@ -9241,23 +9284,20 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
 
 		dev_change_rx_flags(dev, IFF_PROMISC);
 	}
-	if (notify)
+	if (notify) {
+		/* The ops lock is only required to ensure consistent locking
+		 * for `NETDEV_CHANGE` notifiers. This function is sometimes
+		 * called without the lock, even for devices that are ops
+		 * locked, such as in `dev_uc_sync_multiple` when using
+		 * bonding or teaming.
+		 */
+		netdev_ops_assert_locked(dev);
 		__dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL);
+	}
 	return 0;
 }
 
-/**
- *	dev_set_promiscuity	- update promiscuity count on a device
- *	@dev: device
- *	@inc: modifier
- *
- *	Add or remove promiscuity from a device. While the count in the device
- *	remains above zero the interface remains promiscuous. Once it hits zero
- *	the device reverts back to normal filtering operation. A negative inc
- *	value is used to drop promiscuity on the device.
- *	Return 0 if successful or a negative errno code on error.
- */
-int dev_set_promiscuity(struct net_device *dev, int inc)
+int netif_set_promiscuity(struct net_device *dev, int inc)
 {
 	unsigned int old_flags = dev->flags;
 	int err;
@@ -9269,7 +9309,6 @@ int dev_set_promiscuity(struct net_device *dev, int inc)
 		dev_set_rx_mode(dev);
 	return err;
 }
-EXPORT_SYMBOL(dev_set_promiscuity);
 
 int netif_set_allmulti(struct net_device *dev, int inc, bool notify)
 {
@@ -10506,6 +10545,7 @@ static void netdev_sync_lower_features(struct net_device *upper,
 		if (!(features & feature) && (lower->features & feature)) {
 			netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
 				   &feature, lower->name);
+			netdev_lock_ops(lower);
 			lower->wanted_features &= ~feature;
 			__netdev_update_features(lower);
 
@@ -10514,6 +10554,7 @@ static void netdev_sync_lower_features(struct net_device *upper,
 					    &feature, lower->name);
 			else
 				netdev_features_change(lower);
+			netdev_unlock_ops(lower);
 		}
 	}
 }
@@ -11110,8 +11151,7 @@ int register_netdevice(struct net_device *dev)
 	 *	Prevent userspace races by waiting until the network
 	 *	device is fully setup before sending notifications.
 	 */
-	if (!dev->rtnl_link_ops ||
-	    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+	if (!(dev->rtnl_link_ops && dev->rtnl_link_initializing))
 		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL);
 
 out:
@@ -11987,15 +12027,24 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		BUG_ON(dev->reg_state != NETREG_REGISTERED);
 	}
 
-	/* If device is running, close it first. */
+	/* If device is running, close it first. Start with ops locked... */
 	list_for_each_entry(dev, head, unreg_list) {
-		list_add_tail(&dev->close_list, &close_head);
-		netdev_lock_ops(dev);
+		if (netdev_need_ops_lock(dev)) {
+			list_add_tail(&dev->close_list, &close_head);
+			netdev_lock(dev);
+		}
+	}
+	dev_close_many(&close_head, true);
+	/* ... now unlock them and go over the rest. */
+	list_for_each_entry(dev, head, unreg_list) {
+		if (netdev_need_ops_lock(dev))
+			netdev_unlock(dev);
+		else
+			list_add_tail(&dev->close_list, &close_head);
 	}
 	dev_close_many(&close_head, true);
 
 	list_for_each_entry(dev, head, unreg_list) {
-		netdev_unlock_ops(dev);
 		/* And unlink it from device chain. */
 		unlist_netdevice(dev);
 		netdev_lock(dev);
@@ -12010,9 +12059,9 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		struct sk_buff *skb = NULL;
 
 		/* Shutdown queueing discipline. */
+		netdev_lock_ops(dev);
 		dev_shutdown(dev);
 		dev_tcx_uninstall(dev);
-		netdev_lock_ops(dev);
 		dev_xdp_uninstall(dev);
 		dev_memory_provider_uninstall(dev);
 		netdev_unlock_ops(dev);
@@ -12025,8 +12074,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		 */
 		call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 
-		if (!dev->rtnl_link_ops ||
-		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+		if (!(dev->rtnl_link_ops && dev->rtnl_link_initializing))
 			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
 						     GFP_KERNEL, NULL, 0,
 						     portid, nlh);
@@ -12209,7 +12257,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	synchronize_net();
 
 	/* Shutdown queueing discipline. */
+	netdev_lock_ops(dev);
 	dev_shutdown(dev);
+	netdev_unlock_ops(dev);
 
 	/* Notify protocols, that we are about to destroy
 	 * this device. They should clean all the things.
@@ -12683,7 +12733,7 @@ static int net_page_pool_create(int cpuid)
 		return err;
 	}
 
-	per_cpu(system_page_pool, cpuid) = pp_ptr;
+	per_cpu(system_page_pool.pool, cpuid) = pp_ptr;
 #endif
 	return 0;
 }
@@ -12813,13 +12863,13 @@ out:
 		for_each_possible_cpu(i) {
 			struct page_pool *pp_ptr;
 
-			pp_ptr = per_cpu(system_page_pool, i);
+			pp_ptr = per_cpu(system_page_pool.pool, i);
 			if (!pp_ptr)
 				continue;
 
 			xdp_unreg_page_pool(pp_ptr);
 			page_pool_destroy(pp_ptr);
-			per_cpu(system_page_pool, i) = NULL;
+			per_cpu(system_page_pool.pool, i) = NULL;
 		}
 	}
 
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 90898cd540ce..f9a160ab596f 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -268,6 +268,29 @@ void dev_disable_lro(struct net_device *dev)
 EXPORT_SYMBOL(dev_disable_lro);
 
 /**
+ * dev_set_promiscuity() - update promiscuity count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * Add or remove promiscuity from a device. While the count in the device
+ * remains above zero the interface remains promiscuous. Once it hits zero
+ * the device reverts back to normal filtering operation. A negative inc
+ * value is used to drop promiscuity on the device.
+ * Return 0 if successful or a negative errno code on error.
+ */
+int dev_set_promiscuity(struct net_device *dev, int inc)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_set_promiscuity(dev, inc);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_set_promiscuity);
+
+/**
  * dev_set_allmulti() - update allmulti count on a device
  * @dev: device
  * @inc: modifier
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 6e27a47d0493..0dba26baae18 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -16,6 +16,7 @@
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
 #include <net/page_pool/memory_provider.h>
+#include <net/sock.h>
 #include <trace/events/page_pool.h>
 
 #include "devmem.h"
@@ -30,7 +31,7 @@ static const struct memory_provider_ops dmabuf_devmem_ops;
 
 bool net_is_devmem_iov(struct net_iov *niov)
 {
-	return niov->pp->mp_ops == &dmabuf_devmem_ops;
+	return niov->type == NET_IOV_DMABUF;
 }
 
 static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool,
@@ -52,8 +53,10 @@ static dma_addr_t net_devmem_get_dma_addr(const struct net_iov *niov)
 	       ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT);
 }
 
-void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
+void __net_devmem_dmabuf_binding_free(struct work_struct *wq)
 {
+	struct net_devmem_dmabuf_binding *binding = container_of(wq, typeof(*binding), unbind_w);
+
 	size_t size, avail;
 
 	gen_pool_for_each_chunk(binding->chunk_pool,
@@ -71,8 +74,10 @@ void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
 	dma_buf_detach(binding->dmabuf, binding->attachment);
 	dma_buf_put(binding->dmabuf);
 	xa_destroy(&binding->bound_rxqs);
+	kvfree(binding->tx_vec);
 	kfree(binding);
 }
+EXPORT_SYMBOL(__net_devmem_dmabuf_binding_free);
 
 struct net_iov *
 net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
@@ -117,6 +122,13 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 	unsigned long xa_idx;
 	unsigned int rxq_idx;
 
+	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
+
+	/* Ensure no tx net_devmem_lookup_dmabuf() are in flight after the
+	 * erase.
+	 */
+	synchronize_net();
+
 	if (binding->list.next)
 		list_del(&binding->list);
 
@@ -131,8 +143,6 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 		__net_mp_close_rxq(binding->dev, rxq_idx, &mp_params);
 	}
 
-	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
-
 	net_devmem_dmabuf_binding_put(binding);
 }
 
@@ -166,8 +176,9 @@ err_close_rxq:
 }
 
 struct net_devmem_dmabuf_binding *
-net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
-		       struct netlink_ext_ack *extack)
+net_devmem_bind_dmabuf(struct net_device *dev,
+		       enum dma_data_direction direction,
+		       unsigned int dmabuf_fd, struct netlink_ext_ack *extack)
 {
 	struct net_devmem_dmabuf_binding *binding;
 	static u32 id_alloc_next;
@@ -189,43 +200,48 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 	}
 
 	binding->dev = dev;
-
-	err = xa_alloc_cyclic(&net_devmem_dmabuf_bindings, &binding->id,
-			      binding, xa_limit_32b, &id_alloc_next,
-			      GFP_KERNEL);
-	if (err < 0)
-		goto err_free_binding;
-
 	xa_init_flags(&binding->bound_rxqs, XA_FLAGS_ALLOC);
 
 	refcount_set(&binding->ref, 1);
 
+	mutex_init(&binding->lock);
+
 	binding->dmabuf = dmabuf;
 
 	binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent);
 	if (IS_ERR(binding->attachment)) {
 		err = PTR_ERR(binding->attachment);
 		NL_SET_ERR_MSG(extack, "Failed to bind dmabuf to device");
-		goto err_free_id;
+		goto err_free_binding;
 	}
 
 	binding->sgt = dma_buf_map_attachment_unlocked(binding->attachment,
-						       DMA_FROM_DEVICE);
+						       direction);
 	if (IS_ERR(binding->sgt)) {
 		err = PTR_ERR(binding->sgt);
 		NL_SET_ERR_MSG(extack, "Failed to map dmabuf attachment");
 		goto err_detach;
 	}
 
+	if (direction == DMA_TO_DEVICE) {
+		binding->tx_vec = kvmalloc_array(dmabuf->size / PAGE_SIZE,
+						 sizeof(struct net_iov *),
+						 GFP_KERNEL);
+		if (!binding->tx_vec) {
+			err = -ENOMEM;
+			goto err_unmap;
+		}
+	}
+
 	/* For simplicity we expect to make PAGE_SIZE allocations, but the
 	 * binding can be much more flexible than that. We may be able to
 	 * allocate MTU sized chunks here. Leave that for future work...
 	 */
-	binding->chunk_pool =
-		gen_pool_create(PAGE_SHIFT, dev_to_node(&dev->dev));
+	binding->chunk_pool = gen_pool_create(PAGE_SHIFT,
+					      dev_to_node(&dev->dev));
 	if (!binding->chunk_pool) {
 		err = -ENOMEM;
-		goto err_unmap;
+		goto err_tx_vec;
 	}
 
 	virtual = 0;
@@ -266,27 +282,36 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 
 		for (i = 0; i < owner->area.num_niovs; i++) {
 			niov = &owner->area.niovs[i];
+			niov->type = NET_IOV_DMABUF;
 			niov->owner = &owner->area;
 			page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov),
 						      net_devmem_get_dma_addr(niov));
+			if (direction == DMA_TO_DEVICE)
+				binding->tx_vec[owner->area.base_virtual / PAGE_SIZE + i] = niov;
 		}
 
 		virtual += len;
 	}
 
+	err = xa_alloc_cyclic(&net_devmem_dmabuf_bindings, &binding->id,
+			      binding, xa_limit_32b, &id_alloc_next,
+			      GFP_KERNEL);
+	if (err < 0)
+		goto err_free_chunks;
+
 	return binding;
 
 err_free_chunks:
 	gen_pool_for_each_chunk(binding->chunk_pool,
 				net_devmem_dmabuf_free_chunk_owner, NULL);
 	gen_pool_destroy(binding->chunk_pool);
+err_tx_vec:
+	kvfree(binding->tx_vec);
 err_unmap:
 	dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt,
 					  DMA_FROM_DEVICE);
 err_detach:
 	dma_buf_detach(dmabuf, binding->attachment);
-err_free_id:
-	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
 err_free_binding:
 	kfree(binding);
 err_put_dmabuf:
@@ -294,6 +319,74 @@ err_put_dmabuf:
 	return ERR_PTR(err);
 }
 
+struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id)
+{
+	struct net_devmem_dmabuf_binding *binding;
+
+	rcu_read_lock();
+	binding = xa_load(&net_devmem_dmabuf_bindings, id);
+	if (binding) {
+		if (!net_devmem_dmabuf_binding_get(binding))
+			binding = NULL;
+	}
+	rcu_read_unlock();
+
+	return binding;
+}
+
+void net_devmem_get_net_iov(struct net_iov *niov)
+{
+	net_devmem_dmabuf_binding_get(net_devmem_iov_binding(niov));
+}
+
+void net_devmem_put_net_iov(struct net_iov *niov)
+{
+	net_devmem_dmabuf_binding_put(net_devmem_iov_binding(niov));
+}
+
+struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk,
+							 unsigned int dmabuf_id)
+{
+	struct net_devmem_dmabuf_binding *binding;
+	struct dst_entry *dst = __sk_dst_get(sk);
+	int err = 0;
+
+	binding = net_devmem_lookup_dmabuf(dmabuf_id);
+	if (!binding || !binding->tx_vec) {
+		err = -EINVAL;
+		goto out_err;
+	}
+
+	/* The dma-addrs in this binding are only reachable to the corresponding
+	 * net_device.
+	 */
+	if (!dst || !dst->dev || dst->dev->ifindex != binding->dev->ifindex) {
+		err = -ENODEV;
+		goto out_err;
+	}
+
+	return binding;
+
+out_err:
+	if (binding)
+		net_devmem_dmabuf_binding_put(binding);
+
+	return ERR_PTR(err);
+}
+
+struct net_iov *
+net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding,
+		       size_t virt_addr, size_t *off, size_t *size)
+{
+	if (virt_addr >= binding->dmabuf->size)
+		return NULL;
+
+	*off = virt_addr % PAGE_SIZE;
+	*size = PAGE_SIZE - *off;
+
+	return binding->tx_vec[virt_addr / PAGE_SIZE];
+}
+
 /*** "Dmabuf devmem memory provider" ***/
 
 int mp_dmabuf_devmem_init(struct page_pool *pool)
@@ -379,6 +472,11 @@ static void mp_dmabuf_devmem_uninstall(void *mp_priv,
 	xa_for_each(&binding->bound_rxqs, xa_idx, bound_rxq) {
 		if (bound_rxq == rxq) {
 			xa_erase(&binding->bound_rxqs, xa_idx);
+			if (xa_empty(&binding->bound_rxqs)) {
+				mutex_lock(&binding->lock);
+				binding->dev = NULL;
+				mutex_unlock(&binding->lock);
+			}
 			break;
 		}
 	}
diff --git a/net/core/devmem.h b/net/core/devmem.h
index 7fc158d52729..58d8d3c1b945 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -20,15 +20,25 @@ struct net_devmem_dmabuf_binding {
 	struct sg_table *sgt;
 	struct net_device *dev;
 	struct gen_pool *chunk_pool;
+	/* Protect dev */
+	struct mutex lock;
 
 	/* The user holds a ref (via the netlink API) for as long as they want
 	 * the binding to remain alive. Each page pool using this binding holds
-	 * a ref to keep the binding alive. Each allocated net_iov holds a
-	 * ref.
+	 * a ref to keep the binding alive. The page_pool does not release the
+	 * ref until all the net_iovs allocated from this binding are released
+	 * back to the page_pool.
 	 *
 	 * The binding undos itself and unmaps the underlying dmabuf once all
 	 * those refs are dropped and the binding is no longer desired or in
 	 * use.
+	 *
+	 * net_devmem_get_net_iov() on dmabuf net_iovs will increment this
+	 * reference, making sure that the binding remains alive until all the
+	 * net_iovs are no longer used. net_iovs allocated from this binding
+	 * that are stuck in the TX path for any reason (such as awaiting
+	 * retransmits) hold a reference to the binding until the skb holding
+	 * them is freed.
 	 */
 	refcount_t ref;
 
@@ -44,6 +54,14 @@ struct net_devmem_dmabuf_binding {
 	 * active.
 	 */
 	u32 id;
+
+	/* Array of net_iov pointers for this binding, sorted by virtual
+	 * address. This array is convenient to map the virtual addresses to
+	 * net_iovs in the TX path.
+	 */
+	struct net_iov **tx_vec;
+
+	struct work_struct unbind_w;
 };
 
 #if defined(CONFIG_NET_DEVMEM)
@@ -60,14 +78,17 @@ struct dmabuf_genpool_chunk_owner {
 	dma_addr_t base_dma_addr;
 };
 
-void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding);
+void __net_devmem_dmabuf_binding_free(struct work_struct *wq);
 struct net_devmem_dmabuf_binding *
-net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
-		       struct netlink_ext_ack *extack);
+net_devmem_bind_dmabuf(struct net_device *dev,
+		       enum dma_data_direction direction,
+		       unsigned int dmabuf_fd, struct netlink_ext_ack *extack);
+struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id);
 void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding);
 int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 				    struct net_devmem_dmabuf_binding *binding,
 				    struct netlink_ext_ack *extack);
+void net_devmem_bind_tx_release(struct sock *sk);
 
 static inline struct dmabuf_genpool_chunk_owner *
 net_devmem_iov_to_chunk_owner(const struct net_iov *niov)
@@ -96,10 +117,10 @@ static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
 	       ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT);
 }
 
-static inline void
+static inline bool
 net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding)
 {
-	refcount_inc(&binding->ref);
+	return refcount_inc_not_zero(&binding->ref);
 }
 
 static inline void
@@ -108,30 +129,57 @@ net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding)
 	if (!refcount_dec_and_test(&binding->ref))
 		return;
 
-	__net_devmem_dmabuf_binding_free(binding);
+	INIT_WORK(&binding->unbind_w, __net_devmem_dmabuf_binding_free);
+	schedule_work(&binding->unbind_w);
 }
 
+void net_devmem_get_net_iov(struct net_iov *niov);
+void net_devmem_put_net_iov(struct net_iov *niov);
+
 struct net_iov *
 net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding);
 void net_devmem_free_dmabuf(struct net_iov *ppiov);
 
 bool net_is_devmem_iov(struct net_iov *niov);
+struct net_devmem_dmabuf_binding *
+net_devmem_get_binding(struct sock *sk, unsigned int dmabuf_id);
+struct net_iov *
+net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding, size_t addr,
+		       size_t *off, size_t *size);
 
 #else
 struct net_devmem_dmabuf_binding;
 
 static inline void
-__net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
+net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding)
+{
+}
+
+static inline void net_devmem_get_net_iov(struct net_iov *niov)
+{
+}
+
+static inline void net_devmem_put_net_iov(struct net_iov *niov)
+{
+}
+
+static inline void __net_devmem_dmabuf_binding_free(struct work_struct *wq)
 {
 }
 
 static inline struct net_devmem_dmabuf_binding *
 net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+		       enum dma_data_direction direction,
 		       struct netlink_ext_ack *extack)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
+static inline struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id)
+{
+	return NULL;
+}
+
 static inline void
 net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 {
@@ -170,6 +218,25 @@ static inline bool net_is_devmem_iov(struct net_iov *niov)
 {
 	return false;
 }
+
+static inline struct net_devmem_dmabuf_binding *
+net_devmem_get_binding(struct sock *sk, unsigned int dmabuf_id)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline struct net_iov *
+net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding, size_t addr,
+		       size_t *off, size_t *size)
+{
+	return NULL;
+}
+
+static inline struct net_devmem_dmabuf_binding *
+net_devmem_iov_binding(const struct net_iov *niov)
+{
+	return NULL;
+}
 #endif
 
 #endif /* _NET_DEVMEM_H */
diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c
index 70c634b9e7b0..93a04d18e505 100644
--- a/net/core/dst_cache.c
+++ b/net/core/dst_cache.c
@@ -17,6 +17,7 @@
 struct dst_cache_pcpu {
 	unsigned long refresh_ts;
 	struct dst_entry *dst;
+	local_lock_t bh_lock;
 	u32 cookie;
 	union {
 		struct in_addr in_saddr;
@@ -65,10 +66,15 @@ fail:
 
 struct dst_entry *dst_cache_get(struct dst_cache *dst_cache)
 {
+	struct dst_entry *dst;
+
 	if (!dst_cache->cache)
 		return NULL;
 
-	return dst_cache_per_cpu_get(dst_cache, this_cpu_ptr(dst_cache->cache));
+	local_lock_nested_bh(&dst_cache->cache->bh_lock);
+	dst = dst_cache_per_cpu_get(dst_cache, this_cpu_ptr(dst_cache->cache));
+	local_unlock_nested_bh(&dst_cache->cache->bh_lock);
+	return dst;
 }
 EXPORT_SYMBOL_GPL(dst_cache_get);
 
@@ -80,12 +86,16 @@ struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr)
 	if (!dst_cache->cache)
 		return NULL;
 
+	local_lock_nested_bh(&dst_cache->cache->bh_lock);
 	idst = this_cpu_ptr(dst_cache->cache);
 	dst = dst_cache_per_cpu_get(dst_cache, idst);
-	if (!dst)
+	if (!dst) {
+		local_unlock_nested_bh(&dst_cache->cache->bh_lock);
 		return NULL;
+	}
 
 	*saddr = idst->in_saddr.s_addr;
+	local_unlock_nested_bh(&dst_cache->cache->bh_lock);
 	return dst_rtable(dst);
 }
 EXPORT_SYMBOL_GPL(dst_cache_get_ip4);
@@ -98,9 +108,11 @@ void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst,
 	if (!dst_cache->cache)
 		return;
 
+	local_lock_nested_bh(&dst_cache->cache->bh_lock);
 	idst = this_cpu_ptr(dst_cache->cache);
 	dst_cache_per_cpu_dst_set(idst, dst, 0);
 	idst->in_saddr.s_addr = saddr;
+	local_unlock_nested_bh(&dst_cache->cache->bh_lock);
 }
 EXPORT_SYMBOL_GPL(dst_cache_set_ip4);
 
@@ -113,10 +125,13 @@ void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
 	if (!dst_cache->cache)
 		return;
 
+	local_lock_nested_bh(&dst_cache->cache->bh_lock);
+
 	idst = this_cpu_ptr(dst_cache->cache);
 	dst_cache_per_cpu_dst_set(idst, dst,
 				  rt6_get_cookie(dst_rt6_info(dst)));
 	idst->in6_saddr = *saddr;
+	local_unlock_nested_bh(&dst_cache->cache->bh_lock);
 }
 EXPORT_SYMBOL_GPL(dst_cache_set_ip6);
 
@@ -129,12 +144,17 @@ struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache,
 	if (!dst_cache->cache)
 		return NULL;
 
+	local_lock_nested_bh(&dst_cache->cache->bh_lock);
+
 	idst = this_cpu_ptr(dst_cache->cache);
 	dst = dst_cache_per_cpu_get(dst_cache, idst);
-	if (!dst)
+	if (!dst) {
+		local_unlock_nested_bh(&dst_cache->cache->bh_lock);
 		return NULL;
+	}
 
 	*saddr = idst->in6_saddr;
+	local_unlock_nested_bh(&dst_cache->cache->bh_lock);
 	return dst;
 }
 EXPORT_SYMBOL_GPL(dst_cache_get_ip6);
@@ -142,10 +162,14 @@ EXPORT_SYMBOL_GPL(dst_cache_get_ip6);
 
 int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp)
 {
+	unsigned int i;
+
 	dst_cache->cache = alloc_percpu_gfp(struct dst_cache_pcpu,
 					    gfp | __GFP_ZERO);
 	if (!dst_cache->cache)
 		return -ENOMEM;
+	for_each_possible_cpu(i)
+		local_lock_init(&per_cpu_ptr(dst_cache->cache, i)->bh_lock);
 
 	dst_cache_reset(dst_cache);
 	return 0;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 4bc64d912a1c..8ca634964e36 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -257,6 +257,24 @@ static int nla_put_port_range(struct sk_buff *skb, int attrtype,
 	return nla_put(skb, attrtype, sizeof(*range), range);
 }
 
+static bool fib_rule_iif_match(const struct fib_rule *rule, int iifindex,
+			       const struct flowi *fl)
+{
+	u8 iif_is_l3_master = READ_ONCE(rule->iif_is_l3_master);
+
+	return iif_is_l3_master ? l3mdev_fib_rule_iif_match(fl, iifindex) :
+				  fl->flowi_iif == iifindex;
+}
+
+static bool fib_rule_oif_match(const struct fib_rule *rule, int oifindex,
+			       const struct flowi *fl)
+{
+	u8 oif_is_l3_master = READ_ONCE(rule->oif_is_l3_master);
+
+	return oif_is_l3_master ? l3mdev_fib_rule_oif_match(fl, oifindex) :
+				  fl->flowi_oif == oifindex;
+}
+
 static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 			  struct flowi *fl, int flags,
 			  struct fib_lookup_arg *arg)
@@ -264,11 +282,11 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 	int iifindex, oifindex, ret = 0;
 
 	iifindex = READ_ONCE(rule->iifindex);
-	if (iifindex && (iifindex != fl->flowi_iif))
+	if (iifindex && !fib_rule_iif_match(rule, iifindex, fl))
 		goto out;
 
 	oifindex = READ_ONCE(rule->oifindex);
-	if (oifindex && (oifindex != fl->flowi_oif))
+	if (oifindex && !fib_rule_oif_match(rule, oifindex, fl))
 		goto out;
 
 	if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
@@ -736,16 +754,20 @@ static int fib_nl2rule_rtnl(struct fib_rule *nlrule,
 		struct net_device *dev;
 
 		dev = __dev_get_by_name(nlrule->fr_net, nlrule->iifname);
-		if (dev)
+		if (dev) {
 			nlrule->iifindex = dev->ifindex;
+			nlrule->iif_is_l3_master = netif_is_l3_master(dev);
+		}
 	}
 
 	if (tb[FRA_OIFNAME]) {
 		struct net_device *dev;
 
 		dev = __dev_get_by_name(nlrule->fr_net, nlrule->oifname);
-		if (dev)
+		if (dev) {
 			nlrule->oifindex = dev->ifindex;
+			nlrule->oif_is_l3_master = netif_is_l3_master(dev);
+		}
 	}
 
 	return 0;
@@ -852,13 +874,14 @@ int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct netlink_ext_ack *extack, bool rtnl_held)
 {
 	struct fib_rule *rule = NULL, *r, *last = NULL;
-	struct fib_rule_hdr *frh = nlmsg_data(nlh);
 	int err = -EINVAL, unresolved = 0;
 	struct fib_rules_ops *ops = NULL;
 	struct nlattr *tb[FRA_MAX + 1];
 	bool user_priority = false;
+	struct fib_rule_hdr *frh;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) {
+	frh = nlmsg_payload(nlh, sizeof(*frh));
+	if (!frh) {
 		NL_SET_ERR_MSG(extack, "Invalid msg length");
 		goto errout;
 	}
@@ -980,13 +1003,14 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct netlink_ext_ack *extack, bool rtnl_held)
 {
 	struct fib_rule *rule = NULL, *nlrule = NULL;
-	struct fib_rule_hdr *frh = nlmsg_data(nlh);
 	struct fib_rules_ops *ops = NULL;
 	struct nlattr *tb[FRA_MAX+1];
 	bool user_priority = false;
+	struct fib_rule_hdr *frh;
 	int err = -EINVAL;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) {
+	frh = nlmsg_payload(nlh, sizeof(*frh));
+	if (!frh) {
 		NL_SET_ERR_MSG(extack, "Invalid msg length");
 		goto errout;
 	}
@@ -1238,12 +1262,12 @@ static int fib_valid_dumprule_req(const struct nlmsghdr *nlh,
 {
 	struct fib_rule_hdr *frh;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) {
+	frh = nlmsg_payload(nlh, sizeof(*frh));
+	if (!frh) {
 		NL_SET_ERR_MSG(extack, "Invalid header for fib rule dump request");
 		return -EINVAL;
 	}
 
-	frh = nlmsg_data(nlh);
 	if (frh->dst_len || frh->src_len || frh->tos || frh->table ||
 	    frh->res1 || frh->res2 || frh->action || frh->flags) {
 		NL_SET_ERR_MSG(extack,
@@ -1336,11 +1360,17 @@ static void attach_rules(struct list_head *rules, struct net_device *dev)
 
 	list_for_each_entry(rule, rules, list) {
 		if (rule->iifindex == -1 &&
-		    strcmp(dev->name, rule->iifname) == 0)
+		    strcmp(dev->name, rule->iifname) == 0) {
 			WRITE_ONCE(rule->iifindex, dev->ifindex);
+			WRITE_ONCE(rule->iif_is_l3_master,
+				   netif_is_l3_master(dev));
+		}
 		if (rule->oifindex == -1 &&
-		    strcmp(dev->name, rule->oifname) == 0)
+		    strcmp(dev->name, rule->oifname) == 0) {
 			WRITE_ONCE(rule->oifindex, dev->ifindex);
+			WRITE_ONCE(rule->oif_is_l3_master,
+				   netif_is_l3_master(dev));
+		}
 	}
 }
 
@@ -1349,10 +1379,14 @@ static void detach_rules(struct list_head *rules, struct net_device *dev)
 	struct fib_rule *rule;
 
 	list_for_each_entry(rule, rules, list) {
-		if (rule->iifindex == dev->ifindex)
+		if (rule->iifindex == dev->ifindex) {
 			WRITE_ONCE(rule->iifindex, -1);
-		if (rule->oifindex == dev->ifindex)
+			WRITE_ONCE(rule->iif_is_l3_master, false);
+		}
+		if (rule->oifindex == dev->ifindex) {
 			WRITE_ONCE(rule->oifindex, -1);
+			WRITE_ONCE(rule->oif_is_l3_master, false);
+		}
 	}
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index bc6828761a47..577a4504e26f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -218,24 +218,36 @@ BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
 	return 0;
 }
 
+static int bpf_skb_load_helper_convert_offset(const struct sk_buff *skb, int offset)
+{
+	if (likely(offset >= 0))
+		return offset;
+
+	if (offset >= SKF_NET_OFF)
+		return offset - SKF_NET_OFF + skb_network_offset(skb);
+
+	if (offset >= SKF_LL_OFF && skb_mac_header_was_set(skb))
+		return offset - SKF_LL_OFF + skb_mac_offset(skb);
+
+	return INT_MIN;
+}
+
 BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *,
 	   data, int, headlen, int, offset)
 {
-	u8 tmp, *ptr;
+	u8 tmp;
 	const int len = sizeof(tmp);
 
-	if (offset >= 0) {
-		if (headlen - offset >= len)
-			return *(u8 *)(data + offset);
-		if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
-			return tmp;
-	} else {
-		ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
-		if (likely(ptr))
-			return *(u8 *)ptr;
-	}
+	offset = bpf_skb_load_helper_convert_offset(skb, offset);
+	if (offset == INT_MIN)
+		return -EFAULT;
 
-	return -EFAULT;
+	if (headlen - offset >= len)
+		return *(u8 *)(data + offset);
+	if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+		return tmp;
+	else
+		return -EFAULT;
 }
 
 BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb,
@@ -248,21 +260,19 @@ BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb,
 BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *,
 	   data, int, headlen, int, offset)
 {
-	__be16 tmp, *ptr;
+	__be16 tmp;
 	const int len = sizeof(tmp);
 
-	if (offset >= 0) {
-		if (headlen - offset >= len)
-			return get_unaligned_be16(data + offset);
-		if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
-			return be16_to_cpu(tmp);
-	} else {
-		ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
-		if (likely(ptr))
-			return get_unaligned_be16(ptr);
-	}
+	offset = bpf_skb_load_helper_convert_offset(skb, offset);
+	if (offset == INT_MIN)
+		return -EFAULT;
 
-	return -EFAULT;
+	if (headlen - offset >= len)
+		return get_unaligned_be16(data + offset);
+	if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+		return be16_to_cpu(tmp);
+	else
+		return -EFAULT;
 }
 
 BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb,
@@ -275,21 +285,19 @@ BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb,
 BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *,
 	   data, int, headlen, int, offset)
 {
-	__be32 tmp, *ptr;
+	__be32 tmp;
 	const int len = sizeof(tmp);
 
-	if (likely(offset >= 0)) {
-		if (headlen - offset >= len)
-			return get_unaligned_be32(data + offset);
-		if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
-			return be32_to_cpu(tmp);
-	} else {
-		ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
-		if (likely(ptr))
-			return get_unaligned_be32(ptr);
-	}
+	offset = bpf_skb_load_helper_convert_offset(skb, offset);
+	if (offset == INT_MIN)
+		return -EFAULT;
 
-	return -EFAULT;
+	if (headlen - offset >= len)
+		return get_unaligned_be32(data + offset);
+	if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+		return be32_to_cpu(tmp);
+	else
+		return -EFAULT;
 }
 
 BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb,
@@ -2501,6 +2509,7 @@ int skb_do_redirect(struct sk_buff *skb)
 			goto out_drop;
 		skb->dev = dev;
 		dev_sw_netstats_rx_add(dev, skb->len);
+		skb_scrub_packet(skb, false);
 		return -EAGAIN;
 	}
 	return flags & BPF_F_NEIGH ?
diff --git a/net/core/lock_debug.c b/net/core/lock_debug.c
index 6fade574bc2a..9e9fb25314b9 100644
--- a/net/core/lock_debug.c
+++ b/net/core/lock_debug.c
@@ -18,10 +18,12 @@ int netdev_debug_event(struct notifier_block *nb, unsigned long event,
 
 	/* Keep enum and don't add default to trigger -Werror=switch */
 	switch (cmd) {
+	case NETDEV_XDP_FEAT_CHANGE:
+		netdev_assert_locked(dev);
+		fallthrough;
 	case NETDEV_CHANGE:
 	case NETDEV_REGISTER:
 	case NETDEV_UP:
-	case NETDEV_XDP_FEAT_CHANGE:
 		netdev_ops_assert_locked(dev);
 		fallthrough;
 	case NETDEV_DOWN:
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index e39a459540ec..f9d76d85d04f 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -149,8 +149,7 @@ int lwtunnel_build_state(struct net *net, u16 encap_type,
 }
 EXPORT_SYMBOL_GPL(lwtunnel_build_state);
 
-int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack,
-			      bool rtnl_is_held)
+int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack)
 {
 	const struct lwtunnel_encap_ops *ops;
 	int ret = -EINVAL;
@@ -167,12 +166,7 @@ int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack,
 		const char *encap_type_str = lwtunnel_encap_str(encap_type);
 
 		if (encap_type_str) {
-			if (rtnl_is_held)
-				__rtnl_unlock();
 			request_module("rtnl-lwt-%s", encap_type_str);
-			if (rtnl_is_held)
-				rtnl_lock();
-
 			ops = rcu_access_pointer(lwtun_encaps[encap_type]);
 		}
 	}
@@ -186,8 +180,7 @@ int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack,
 EXPORT_SYMBOL_GPL(lwtunnel_valid_encap_type);
 
 int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining,
-				   struct netlink_ext_ack *extack,
-				   bool rtnl_is_held)
+				   struct netlink_ext_ack *extack)
 {
 	struct rtnexthop *rtnh = (struct rtnexthop *)attr;
 	struct nlattr *nla_entype;
@@ -208,9 +201,7 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining,
 				}
 				encap_type = nla_get_u16(nla_entype);
 
-				if (lwtunnel_valid_encap_type(encap_type,
-							      extack,
-							      rtnl_is_held) != 0)
+				if (lwtunnel_valid_encap_type(encap_type, extack))
 					return -EOPNOTSUPP;
 			}
 		}
@@ -333,6 +324,8 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	struct dst_entry *dst;
 	int ret;
 
+	local_bh_disable();
+
 	if (dev_xmit_recursion()) {
 		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
 				     __func__);
@@ -348,8 +341,10 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
-	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
-		return 0;
+	    lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+		ret = 0;
+		goto out;
+	}
 
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
@@ -364,11 +359,13 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (ret == -EOPNOTSUPP)
 		goto drop;
 
-	return ret;
+	goto out;
 
 drop:
 	kfree_skb(skb);
 
+out:
+	local_bh_enable();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(lwtunnel_output);
@@ -380,6 +377,8 @@ int lwtunnel_xmit(struct sk_buff *skb)
 	struct dst_entry *dst;
 	int ret;
 
+	local_bh_disable();
+
 	if (dev_xmit_recursion()) {
 		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
 				     __func__);
@@ -396,8 +395,10 @@ int lwtunnel_xmit(struct sk_buff *skb)
 	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
-	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
-		return 0;
+	    lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+		ret = 0;
+		goto out;
+	}
 
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
@@ -412,11 +413,13 @@ int lwtunnel_xmit(struct sk_buff *skb)
 	if (ret == -EOPNOTSUPP)
 		goto drop;
 
-	return ret;
+	goto out;
 
 drop:
 	kfree_skb(skb);
 
+out:
+	local_bh_enable();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(lwtunnel_xmit);
@@ -428,6 +431,8 @@ int lwtunnel_input(struct sk_buff *skb)
 	struct dst_entry *dst;
 	int ret;
 
+	DEBUG_NET_WARN_ON_ONCE(!in_softirq());
+
 	if (dev_xmit_recursion()) {
 		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
 				     __func__);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index a07249b59ae1..a6e2c91ec3e7 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1517,7 +1517,7 @@ out:
 	return rc;
 out_kfree_skb:
 	rc = -EINVAL;
-	kfree_skb(skb);
+	kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_HH_FILLFAIL);
 	goto out;
 }
 EXPORT_SYMBOL(neigh_resolve_output);
@@ -1541,7 +1541,7 @@ int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb)
 		err = dev_queue_xmit(skb);
 	else {
 		err = -EINVAL;
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_HH_FILLFAIL);
 	}
 	return err;
 }
@@ -2430,12 +2430,12 @@ static int neightbl_valid_dump_info(const struct nlmsghdr *nlh,
 {
 	struct ndtmsg *ndtm;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndtm))) {
+	ndtm = nlmsg_payload(nlh, sizeof(*ndtm));
+	if (!ndtm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for neighbor table dump request");
 		return -EINVAL;
 	}
 
-	ndtm = nlmsg_data(nlh);
 	if (ndtm->ndtm_pad1  || ndtm->ndtm_pad2) {
 		NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor table dump request");
 		return -EINVAL;
@@ -2747,12 +2747,12 @@ static int neigh_valid_dump_req(const struct nlmsghdr *nlh,
 	if (strict_check) {
 		struct ndmsg *ndm;
 
-		if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+		ndm = nlmsg_payload(nlh, sizeof(*ndm));
+		if (!ndm) {
 			NL_SET_ERR_MSG(extack, "Invalid header for neighbor dump request");
 			return -EINVAL;
 		}
 
-		ndm = nlmsg_data(nlh);
 		if (ndm->ndm_pad1  || ndm->ndm_pad2  || ndm->ndm_ifindex ||
 		    ndm->ndm_state || ndm->ndm_type) {
 			NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor dump request");
@@ -2855,12 +2855,12 @@ static int neigh_valid_get_req(const struct nlmsghdr *nlh,
 	struct ndmsg *ndm;
 	int err, i;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+	ndm = nlmsg_payload(nlh, sizeof(*ndm));
+	if (!ndm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for neighbor get request");
 		return -EINVAL;
 	}
 
-	ndm = nlmsg_data(nlh);
 	if (ndm->ndm_pad1  || ndm->ndm_pad2  || ndm->ndm_state ||
 	    ndm->ndm_type) {
 		NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor get request");
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index b0dfdf791ece..42ee7fce3d95 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -163,16 +163,45 @@ static void ops_pre_exit_list(const struct pernet_operations *ops,
 	}
 }
 
+static void ops_exit_rtnl_list(const struct list_head *ops_list,
+			       const struct pernet_operations *ops,
+			       struct list_head *net_exit_list)
+{
+	const struct pernet_operations *saved_ops = ops;
+	LIST_HEAD(dev_kill_list);
+	struct net *net;
+
+	rtnl_lock();
+
+	list_for_each_entry(net, net_exit_list, exit_list) {
+		__rtnl_net_lock(net);
+
+		ops = saved_ops;
+		list_for_each_entry_continue_reverse(ops, ops_list, list) {
+			if (ops->exit_rtnl)
+				ops->exit_rtnl(net, &dev_kill_list);
+		}
+
+		__rtnl_net_unlock(net);
+	}
+
+	unregister_netdevice_many(&dev_kill_list);
+
+	rtnl_unlock();
+}
+
 static void ops_exit_list(const struct pernet_operations *ops,
 			  struct list_head *net_exit_list)
 {
-	struct net *net;
 	if (ops->exit) {
+		struct net *net;
+
 		list_for_each_entry(net, net_exit_list, exit_list) {
 			ops->exit(net);
 			cond_resched();
 		}
 	}
+
 	if (ops->exit_batch)
 		ops->exit_batch(net_exit_list);
 }
@@ -188,6 +217,56 @@ static void ops_free_list(const struct pernet_operations *ops,
 	}
 }
 
+static void ops_undo_list(const struct list_head *ops_list,
+			  const struct pernet_operations *ops,
+			  struct list_head *net_exit_list,
+			  bool expedite_rcu)
+{
+	const struct pernet_operations *saved_ops;
+	bool hold_rtnl = false;
+
+	if (!ops)
+		ops = list_entry(ops_list, typeof(*ops), list);
+
+	saved_ops = ops;
+
+	list_for_each_entry_continue_reverse(ops, ops_list, list) {
+		hold_rtnl |= !!ops->exit_rtnl;
+		ops_pre_exit_list(ops, net_exit_list);
+	}
+
+	/* Another CPU might be rcu-iterating the list, wait for it.
+	 * This needs to be before calling the exit() notifiers, so the
+	 * rcu_barrier() after ops_undo_list() isn't sufficient alone.
+	 * Also the pre_exit() and exit() methods need this barrier.
+	 */
+	if (expedite_rcu)
+		synchronize_rcu_expedited();
+	else
+		synchronize_rcu();
+
+	if (hold_rtnl)
+		ops_exit_rtnl_list(ops_list, saved_ops, net_exit_list);
+
+	ops = saved_ops;
+	list_for_each_entry_continue_reverse(ops, ops_list, list)
+		ops_exit_list(ops, net_exit_list);
+
+	ops = saved_ops;
+	list_for_each_entry_continue_reverse(ops, ops_list, list)
+		ops_free_list(ops, net_exit_list);
+}
+
+static void ops_undo_single(struct pernet_operations *ops,
+			    struct list_head *net_exit_list)
+{
+	LIST_HEAD(ops_list);
+
+	list_add(&ops->list, &ops_list);
+	ops_undo_list(&ops_list, NULL, net_exit_list, false);
+	list_del(&ops->list);
+}
+
 /* should be called with nsid_lock held */
 static int alloc_netid(struct net *net, struct net *peer, int reqid)
 {
@@ -351,9 +430,8 @@ static __net_init void preinit_net(struct net *net, struct user_namespace *user_
 static __net_init int setup_net(struct net *net)
 {
 	/* Must be called with pernet_ops_rwsem held */
-	const struct pernet_operations *ops, *saved_ops;
+	const struct pernet_operations *ops;
 	LIST_HEAD(net_exit_list);
-	LIST_HEAD(dev_kill_list);
 	int error = 0;
 
 	preempt_disable();
@@ -376,29 +454,7 @@ out_undo:
 	 * for the pernet modules whose init functions did not fail.
 	 */
 	list_add(&net->exit_list, &net_exit_list);
-	saved_ops = ops;
-	list_for_each_entry_continue_reverse(ops, &pernet_list, list)
-		ops_pre_exit_list(ops, &net_exit_list);
-
-	synchronize_rcu();
-
-	ops = saved_ops;
-	rtnl_lock();
-	list_for_each_entry_continue_reverse(ops, &pernet_list, list) {
-		if (ops->exit_batch_rtnl)
-			ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list);
-	}
-	unregister_netdevice_many(&dev_kill_list);
-	rtnl_unlock();
-
-	ops = saved_ops;
-	list_for_each_entry_continue_reverse(ops, &pernet_list, list)
-		ops_exit_list(ops, &net_exit_list);
-
-	ops = saved_ops;
-	list_for_each_entry_continue_reverse(ops, &pernet_list, list)
-		ops_free_list(ops, &net_exit_list);
-
+	ops_undo_list(&pernet_list, ops, &net_exit_list, false);
 	rcu_barrier();
 	goto out;
 }
@@ -594,11 +650,9 @@ struct task_struct *cleanup_net_task;
 
 static void cleanup_net(struct work_struct *work)
 {
-	const struct pernet_operations *ops;
-	struct net *net, *tmp, *last;
 	struct llist_node *net_kill_list;
+	struct net *net, *tmp, *last;
 	LIST_HEAD(net_exit_list);
-	LIST_HEAD(dev_kill_list);
 
 	cleanup_net_task = current;
 
@@ -629,33 +683,7 @@ static void cleanup_net(struct work_struct *work)
 		list_add_tail(&net->exit_list, &net_exit_list);
 	}
 
-	/* Run all of the network namespace pre_exit methods */
-	list_for_each_entry_reverse(ops, &pernet_list, list)
-		ops_pre_exit_list(ops, &net_exit_list);
-
-	/*
-	 * Another CPU might be rcu-iterating the list, wait for it.
-	 * This needs to be before calling the exit() notifiers, so
-	 * the rcu_barrier() below isn't sufficient alone.
-	 * Also the pre_exit() and exit() methods need this barrier.
-	 */
-	synchronize_rcu_expedited();
-
-	rtnl_lock();
-	list_for_each_entry_reverse(ops, &pernet_list, list) {
-		if (ops->exit_batch_rtnl)
-			ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list);
-	}
-	unregister_netdevice_many(&dev_kill_list);
-	rtnl_unlock();
-
-	/* Run all of the network namespace exit methods */
-	list_for_each_entry_reverse(ops, &pernet_list, list)
-		ops_exit_list(ops, &net_exit_list);
-
-	/* Free the net generic variables */
-	list_for_each_entry_reverse(ops, &pernet_list, list)
-		ops_free_list(ops, &net_exit_list);
+	ops_undo_list(&pernet_list, NULL, &net_exit_list, true);
 
 	up_read(&pernet_ops_rwsem);
 
@@ -1239,31 +1267,13 @@ void __init net_ns_init(void)
 	rtnl_register_many(net_ns_rtnl_msg_handlers);
 }
 
-static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list)
-{
-	ops_pre_exit_list(ops, net_exit_list);
-	synchronize_rcu();
-
-	if (ops->exit_batch_rtnl) {
-		LIST_HEAD(dev_kill_list);
-
-		rtnl_lock();
-		ops->exit_batch_rtnl(net_exit_list, &dev_kill_list);
-		unregister_netdevice_many(&dev_kill_list);
-		rtnl_unlock();
-	}
-	ops_exit_list(ops, net_exit_list);
-
-	ops_free_list(ops, net_exit_list);
-}
-
 #ifdef CONFIG_NET_NS
 static int __register_pernet_operations(struct list_head *list,
 					struct pernet_operations *ops)
 {
+	LIST_HEAD(net_exit_list);
 	struct net *net;
 	int error;
-	LIST_HEAD(net_exit_list);
 
 	list_add_tail(&ops->list, list);
 	if (ops->init || ops->id) {
@@ -1282,21 +1292,21 @@ static int __register_pernet_operations(struct list_head *list,
 out_undo:
 	/* If I have an error cleanup all namespaces I initialized */
 	list_del(&ops->list);
-	free_exit_list(ops, &net_exit_list);
+	ops_undo_single(ops, &net_exit_list);
 	return error;
 }
 
 static void __unregister_pernet_operations(struct pernet_operations *ops)
 {
-	struct net *net;
 	LIST_HEAD(net_exit_list);
+	struct net *net;
 
-	list_del(&ops->list);
 	/* See comment in __register_pernet_operations() */
 	for_each_net(net)
 		list_add_tail(&net->exit_list, &net_exit_list);
 
-	free_exit_list(ops, &net_exit_list);
+	list_del(&ops->list);
+	ops_undo_single(ops, &net_exit_list);
 }
 
 #else
@@ -1318,8 +1328,9 @@ static void __unregister_pernet_operations(struct pernet_operations *ops)
 		list_del(&ops->list);
 	} else {
 		LIST_HEAD(net_exit_list);
+
 		list_add(&init_net.exit_list, &net_exit_list);
-		free_exit_list(ops, &net_exit_list);
+		ops_undo_single(ops, &net_exit_list);
 	}
 }
 
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 739f7b6506a6..4fc44587f493 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -99,6 +99,12 @@ static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_IRQ_SUSPE
 	[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, },
 };
 
+/* NETDEV_CMD_BIND_TX - do */
+static const struct nla_policy netdev_bind_tx_nl_policy[NETDEV_A_DMABUF_FD + 1] = {
+	[NETDEV_A_DMABUF_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+	[NETDEV_A_DMABUF_FD] = { .type = NLA_U32, },
+};
+
 /* Ops table for netdev */
 static const struct genl_split_ops netdev_nl_ops[] = {
 	{
@@ -190,6 +196,13 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.maxattr	= NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
+	{
+		.cmd		= NETDEV_CMD_BIND_TX,
+		.doit		= netdev_nl_bind_tx_doit,
+		.policy		= netdev_bind_tx_nl_policy,
+		.maxattr	= NETDEV_A_DMABUF_FD,
+		.flags		= GENL_CMD_CAP_DO,
+	},
 };
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 17d39fd64c94..cf3fad74511f 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -34,6 +34,7 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
 				struct netlink_callback *cb);
 int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info);
 
 enum {
 	NETDEV_NLGRP_MGMT,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index b64c614a00c4..762570dcda61 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -702,25 +702,66 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp,
 	return 0;
 }
 
+/**
+ * netdev_stat_queue_sum() - add up queue stats from range of queues
+ * @netdev:	net_device
+ * @rx_start:	index of the first Rx queue to query
+ * @rx_end:	index after the last Rx queue (first *not* to query)
+ * @rx_sum:	output Rx stats, should be already initialized
+ * @tx_start:	index of the first Tx queue to query
+ * @tx_end:	index after the last Tx queue (first *not* to query)
+ * @tx_sum:	output Tx stats, should be already initialized
+ *
+ * Add stats from [start, end) range of queue IDs to *x_sum structs.
+ * The sum structs must be already initialized. Usually this
+ * helper is invoked from the .get_base_stats callbacks of drivers
+ * to account for stats of disabled queues. In that case the ranges
+ * are usually [netdev->real_num_*x_queues, netdev->num_*x_queues).
+ */
+void netdev_stat_queue_sum(struct net_device *netdev,
+			   int rx_start, int rx_end,
+			   struct netdev_queue_stats_rx *rx_sum,
+			   int tx_start, int tx_end,
+			   struct netdev_queue_stats_tx *tx_sum)
+{
+	const struct netdev_stat_ops *ops;
+	struct netdev_queue_stats_rx rx;
+	struct netdev_queue_stats_tx tx;
+	int i;
+
+	ops = netdev->stat_ops;
+
+	for (i = rx_start; i < rx_end; i++) {
+		memset(&rx, 0xff, sizeof(rx));
+		if (ops->get_queue_stats_rx)
+			ops->get_queue_stats_rx(netdev, i, &rx);
+		netdev_nl_stats_add(rx_sum, &rx, sizeof(rx));
+	}
+	for (i = tx_start; i < tx_end; i++) {
+		memset(&tx, 0xff, sizeof(tx));
+		if (ops->get_queue_stats_tx)
+			ops->get_queue_stats_tx(netdev, i, &tx);
+		netdev_nl_stats_add(tx_sum, &tx, sizeof(tx));
+	}
+}
+EXPORT_SYMBOL(netdev_stat_queue_sum);
+
 static int
 netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
 			  const struct genl_info *info)
 {
-	struct netdev_queue_stats_rx rx_sum, rx;
-	struct netdev_queue_stats_tx tx_sum, tx;
-	const struct netdev_stat_ops *ops;
+	struct netdev_queue_stats_rx rx_sum;
+	struct netdev_queue_stats_tx tx_sum;
 	void *hdr;
-	int i;
 
-	ops = netdev->stat_ops;
 	/* Netdev can't guarantee any complete counters */
-	if (!ops->get_base_stats)
+	if (!netdev->stat_ops->get_base_stats)
 		return 0;
 
 	memset(&rx_sum, 0xff, sizeof(rx_sum));
 	memset(&tx_sum, 0xff, sizeof(tx_sum));
 
-	ops->get_base_stats(netdev, &rx_sum, &tx_sum);
+	netdev->stat_ops->get_base_stats(netdev, &rx_sum, &tx_sum);
 
 	/* The op was there, but nothing reported, don't bother */
 	if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) &&
@@ -733,18 +774,8 @@ netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
 	if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex))
 		goto nla_put_failure;
 
-	for (i = 0; i < netdev->real_num_rx_queues; i++) {
-		memset(&rx, 0xff, sizeof(rx));
-		if (ops->get_queue_stats_rx)
-			ops->get_queue_stats_rx(netdev, i, &rx);
-		netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx));
-	}
-	for (i = 0; i < netdev->real_num_tx_queues; i++) {
-		memset(&tx, 0xff, sizeof(tx));
-		if (ops->get_queue_stats_tx)
-			ops->get_queue_stats_tx(netdev, i, &tx);
-		netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx));
-	}
+	netdev_stat_queue_sum(netdev, 0, netdev->real_num_rx_queues, &rx_sum,
+			      0, netdev->real_num_tx_queues, &tx_sum);
 
 	if (netdev_nl_stats_write_rx(rsp, &rx_sum) ||
 	    netdev_nl_stats_write_tx(rsp, &tx_sum))
@@ -860,20 +891,24 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 
 	mutex_lock(&priv->lock);
 
+	err = 0;
 	netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex);
-	if (!netdev || !netif_device_present(netdev)) {
+	if (!netdev) {
 		err = -ENODEV;
 		goto err_unlock_sock;
 	}
-
-	if (!netdev_need_ops_lock(netdev)) {
+	if (!netif_device_present(netdev))
+		err = -ENODEV;
+	else if (!netdev_need_ops_lock(netdev))
 		err = -EOPNOTSUPP;
+	if (err) {
 		NL_SET_BAD_ATTR(info->extack,
 				info->attrs[NETDEV_A_DEV_IFINDEX]);
 		goto err_unlock;
 	}
 
-	binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack);
+	binding = net_devmem_bind_dmabuf(netdev, DMA_FROM_DEVICE, dmabuf_fd,
+					 info->extack);
 	if (IS_ERR(binding)) {
 		err = PTR_ERR(binding);
 		goto err_unlock;
@@ -934,6 +969,83 @@ err_genlmsg_free:
 	return err;
 }
 
+int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net_devmem_dmabuf_binding *binding;
+	struct netdev_nl_sock *priv;
+	struct net_device *netdev;
+	u32 ifindex, dmabuf_fd;
+	struct sk_buff *rsp;
+	int err = 0;
+	void *hdr;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX) ||
+	    GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_FD))
+		return -EINVAL;
+
+	ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]);
+	dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]);
+
+	priv = genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk);
+	if (IS_ERR(priv))
+		return PTR_ERR(priv);
+
+	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!rsp)
+		return -ENOMEM;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr) {
+		err = -EMSGSIZE;
+		goto err_genlmsg_free;
+	}
+
+	mutex_lock(&priv->lock);
+
+	netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex);
+	if (!netdev) {
+		err = -ENODEV;
+		goto err_unlock_sock;
+	}
+
+	if (!netif_device_present(netdev)) {
+		err = -ENODEV;
+		goto err_unlock_netdev;
+	}
+
+	if (!netdev->netmem_tx) {
+		err = -EOPNOTSUPP;
+		NL_SET_ERR_MSG(info->extack,
+			       "Driver does not support netmem TX");
+		goto err_unlock_netdev;
+	}
+
+	binding = net_devmem_bind_dmabuf(netdev, DMA_TO_DEVICE, dmabuf_fd,
+					 info->extack);
+	if (IS_ERR(binding)) {
+		err = PTR_ERR(binding);
+		goto err_unlock_netdev;
+	}
+
+	list_add(&binding->list, &priv->bindings);
+
+	nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id);
+	genlmsg_end(rsp, hdr);
+
+	netdev_unlock(netdev);
+	mutex_unlock(&priv->lock);
+
+	return genlmsg_reply(rsp, info);
+
+err_unlock_netdev:
+	netdev_unlock(netdev);
+err_unlock_sock:
+	mutex_unlock(&priv->lock);
+err_genlmsg_free:
+	nlmsg_free(rsp);
+	return err;
+}
+
 void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv)
 {
 	INIT_LIST_HEAD(&priv->bindings);
@@ -944,14 +1056,25 @@ void netdev_nl_sock_priv_destroy(struct netdev_nl_sock *priv)
 {
 	struct net_devmem_dmabuf_binding *binding;
 	struct net_devmem_dmabuf_binding *temp;
+	netdevice_tracker dev_tracker;
 	struct net_device *dev;
 
 	mutex_lock(&priv->lock);
 	list_for_each_entry_safe(binding, temp, &priv->bindings, list) {
+		mutex_lock(&binding->lock);
 		dev = binding->dev;
+		if (!dev) {
+			mutex_unlock(&binding->lock);
+			net_devmem_unbind_dmabuf(binding);
+			continue;
+		}
+		netdev_hold(dev, &dev_tracker, GFP_KERNEL);
+		mutex_unlock(&binding->lock);
+
 		netdev_lock(dev);
 		net_devmem_unbind_dmabuf(binding);
 		netdev_unlock(dev);
+		netdev_put(dev, &dev_tracker);
 	}
 	mutex_unlock(&priv->lock);
 }
@@ -963,10 +1086,14 @@ static int netdev_genl_netdevice_event(struct notifier_block *nb,
 
 	switch (event) {
 	case NETDEV_REGISTER:
+		netdev_lock_ops_to_full(netdev);
 		netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_ADD_NTF);
+		netdev_unlock_full_to_ops(netdev);
 		break;
 	case NETDEV_UNREGISTER:
+		netdev_lock(netdev);
 		netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_DEL_NTF);
+		netdev_unlock(netdev);
 		break;
 	case NETDEV_XDP_FEAT_CHANGE:
 		netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_CHANGE_NTF);
diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h
index 7eadb8393e00..cd95394399b4 100644
--- a/net/core/netmem_priv.h
+++ b/net/core/netmem_priv.h
@@ -5,7 +5,7 @@
 
 static inline unsigned long netmem_get_pp_magic(netmem_ref netmem)
 {
-	return __netmem_clear_lsb(netmem)->pp_magic;
+	return __netmem_clear_lsb(netmem)->pp_magic & ~PP_DMA_INDEX_MASK;
 }
 
 static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic)
@@ -15,9 +15,16 @@ static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic)
 
 static inline void netmem_clear_pp_magic(netmem_ref netmem)
 {
+	WARN_ON_ONCE(__netmem_clear_lsb(netmem)->pp_magic & PP_DMA_INDEX_MASK);
+
 	__netmem_clear_lsb(netmem)->pp_magic = 0;
 }
 
+static inline bool netmem_is_pp(netmem_ref netmem)
+{
+	return (netmem_get_pp_magic(netmem) & PP_MAGIC_MASK) == PP_SIGNATURE;
+}
+
 static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool)
 {
 	__netmem_clear_lsb(netmem)->pp = pool;
@@ -28,4 +35,28 @@ static inline void netmem_set_dma_addr(netmem_ref netmem,
 {
 	__netmem_clear_lsb(netmem)->dma_addr = dma_addr;
 }
+
+static inline unsigned long netmem_get_dma_index(netmem_ref netmem)
+{
+	unsigned long magic;
+
+	if (WARN_ON_ONCE(netmem_is_net_iov(netmem)))
+		return 0;
+
+	magic = __netmem_clear_lsb(netmem)->pp_magic;
+
+	return (magic & PP_DMA_INDEX_MASK) >> PP_DMA_INDEX_SHIFT;
+}
+
+static inline void netmem_set_dma_index(netmem_ref netmem,
+					unsigned long id)
+{
+	unsigned long magic;
+
+	if (WARN_ON_ONCE(netmem_is_net_iov(netmem)))
+		return;
+
+	magic = netmem_get_pp_magic(netmem) | (id << PP_DMA_INDEX_SHIFT);
+	__netmem_clear_lsb(netmem)->pp_magic = magic;
+}
 #endif
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 7745ad924ae2..974f3eef2efa 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -276,8 +276,7 @@ static int page_pool_init(struct page_pool *pool,
 	/* Driver calling page_pool_create() also call page_pool_destroy() */
 	refcount_set(&pool->user_cnt, 1);
 
-	if (pool->dma_map)
-		get_device(pool->p.dev);
+	xa_init_flags(&pool->dma_mapped, XA_FLAGS_ALLOC1);
 
 	if (pool->slow.flags & PP_FLAG_ALLOW_UNREADABLE_NETMEM) {
 		netdev_assert_locked(pool->slow.netdev);
@@ -320,9 +319,7 @@ free_ptr_ring:
 static void page_pool_uninit(struct page_pool *pool)
 {
 	ptr_ring_cleanup(&pool->ring, NULL);
-
-	if (pool->dma_map)
-		put_device(pool->p.dev);
+	xa_destroy(&pool->dma_mapped);
 
 #ifdef CONFIG_PAGE_POOL_STATS
 	if (!pool->system)
@@ -463,13 +460,21 @@ page_pool_dma_sync_for_device(const struct page_pool *pool,
 			      netmem_ref netmem,
 			      u32 dma_sync_size)
 {
-	if (pool->dma_sync && dma_dev_need_sync(pool->p.dev))
-		__page_pool_dma_sync_for_device(pool, netmem, dma_sync_size);
+	if (pool->dma_sync && dma_dev_need_sync(pool->p.dev)) {
+		rcu_read_lock();
+		/* re-check under rcu_read_lock() to sync with page_pool_scrub() */
+		if (pool->dma_sync)
+			__page_pool_dma_sync_for_device(pool, netmem,
+							dma_sync_size);
+		rcu_read_unlock();
+	}
 }
 
-static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)
+static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem, gfp_t gfp)
 {
 	dma_addr_t dma;
+	int err;
+	u32 id;
 
 	/* Setup DMA mapping: use 'struct page' area for storing DMA-addr
 	 * since dma_addr_t can be either 32 or 64 bits and does not always fit
@@ -483,15 +488,30 @@ static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)
 	if (dma_mapping_error(pool->p.dev, dma))
 		return false;
 
-	if (page_pool_set_dma_addr_netmem(netmem, dma))
+	if (page_pool_set_dma_addr_netmem(netmem, dma)) {
+		WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
 		goto unmap_failed;
+	}
 
+	if (in_softirq())
+		err = xa_alloc(&pool->dma_mapped, &id, netmem_to_page(netmem),
+			       PP_DMA_INDEX_LIMIT, gfp);
+	else
+		err = xa_alloc_bh(&pool->dma_mapped, &id, netmem_to_page(netmem),
+				  PP_DMA_INDEX_LIMIT, gfp);
+	if (err) {
+		WARN_ONCE(err != -ENOMEM, "couldn't track DMA mapping, please report to netdev@");
+		goto unset_failed;
+	}
+
+	netmem_set_dma_index(netmem, id);
 	page_pool_dma_sync_for_device(pool, netmem, pool->p.max_len);
 
 	return true;
 
+unset_failed:
+	page_pool_set_dma_addr_netmem(netmem, 0);
 unmap_failed:
-	WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
 	dma_unmap_page_attrs(pool->p.dev, dma,
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
 			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
@@ -508,7 +528,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
 	if (unlikely(!page))
 		return NULL;
 
-	if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page_to_netmem(page)))) {
+	if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page_to_netmem(page), gfp))) {
 		put_page(page);
 		return NULL;
 	}
@@ -554,7 +574,7 @@ static noinline netmem_ref __page_pool_alloc_pages_slow(struct page_pool *pool,
 	 */
 	for (i = 0; i < nr_pages; i++) {
 		netmem = pool->alloc.cache[i];
-		if (dma_map && unlikely(!page_pool_dma_map(pool, netmem))) {
+		if (dma_map && unlikely(!page_pool_dma_map(pool, netmem, gfp))) {
 			put_page(netmem_to_page(netmem));
 			continue;
 		}
@@ -656,6 +676,8 @@ void page_pool_clear_pp_info(netmem_ref netmem)
 static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 							 netmem_ref netmem)
 {
+	struct page *old, *page = netmem_to_page(netmem);
+	unsigned long id;
 	dma_addr_t dma;
 
 	if (!pool->dma_map)
@@ -664,6 +686,17 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 		 */
 		return;
 
+	id = netmem_get_dma_index(netmem);
+	if (!id)
+		return;
+
+	if (in_softirq())
+		old = xa_cmpxchg(&pool->dma_mapped, id, page, NULL, 0);
+	else
+		old = xa_cmpxchg_bh(&pool->dma_mapped, id, page, NULL, 0);
+	if (old != page)
+		return;
+
 	dma = page_pool_get_dma_addr_netmem(netmem);
 
 	/* When page is unmapped, it cannot be returned to our pool */
@@ -671,6 +704,7 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
 			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
 	page_pool_set_dma_addr_netmem(netmem, 0);
+	netmem_set_dma_index(netmem, 0);
 }
 
 /* Disconnects a page (from a page_pool).  API users can have a need
@@ -805,6 +839,10 @@ static bool page_pool_napi_local(const struct page_pool *pool)
 	const struct napi_struct *napi;
 	u32 cpuid;
 
+	/* On PREEMPT_RT the softirq can be preempted by the consumer */
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		return false;
+
 	if (unlikely(!in_softirq()))
 		return false;
 
@@ -1080,8 +1118,29 @@ static void page_pool_empty_alloc_cache_once(struct page_pool *pool)
 
 static void page_pool_scrub(struct page_pool *pool)
 {
+	unsigned long id;
+	void *ptr;
+
 	page_pool_empty_alloc_cache_once(pool);
-	pool->destroy_cnt++;
+	if (!pool->destroy_cnt++ && pool->dma_map) {
+		if (pool->dma_sync) {
+			/* Disable page_pool_dma_sync_for_device() */
+			pool->dma_sync = false;
+
+			/* Make sure all concurrent returns that may see the old
+			 * value of dma_sync (and thus perform a sync) have
+			 * finished before doing the unmapping below. Skip the
+			 * wait if the device doesn't actually need syncing, or
+			 * if there are no outstanding mapped pages.
+			 */
+			if (dma_dev_need_sync(pool->p.dev) &&
+			    !xa_empty(&pool->dma_mapped))
+				synchronize_net();
+		}
+
+		xa_for_each(&pool->dma_mapped, id, ptr)
+			__page_pool_release_page_dma(pool, page_to_netmem(ptr));
+	}
 
 	/* No more consumers should exist, but producers could still
 	 * be in-flight.
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index fe7fdefab994..0ebe5461d4d9 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -177,7 +177,7 @@
 #define MAX_IMIX_ENTRIES 20
 #define IMIX_PRECISION 100 /* Precision of IMIX distribution */
 
-#define func_enter() pr_debug("entering %s\n", __func__);
+#define func_enter() pr_debug("entering %s\n", __func__)
 
 #define PKT_FLAGS							\
 	pf(IPV6)		/* Interface in IPV6 Mode */		\
@@ -227,12 +227,12 @@ static char *pkt_flag_names[] = {
 
 /* Xmit modes */
 #define M_START_XMIT		0	/* Default normal TX */
-#define M_NETIF_RECEIVE 	1	/* Inject packets into stack */
+#define M_NETIF_RECEIVE		1	/* Inject packets into stack */
 #define M_QUEUE_XMIT		2	/* Inject packet into qdisc */
 
 /* If lock -- protects updating of if_list */
-#define   if_lock(t)           mutex_lock(&(t->if_lock));
-#define   if_unlock(t)           mutex_unlock(&(t->if_lock));
+#define   if_lock(t)      mutex_lock(&(t->if_lock))
+#define   if_unlock(t)    mutex_unlock(&(t->if_lock))
 
 /* Used to help with determining the pkts on receive */
 #define PKTGEN_MAGIC 0xbe9be955
@@ -283,7 +283,8 @@ struct pktgen_dev {
 	int pkt_overhead;	/* overhead for MPLS, VLANs, IPSEC etc */
 	int nfrags;
 	int removal_mark;	/* non-zero => the device is marked for
-				 * removal by worker thread */
+				 * removal by worker thread
+				 */
 
 	struct page *page;
 	u64 delay;		/* nano-seconds */
@@ -346,10 +347,12 @@ struct pktgen_dev {
 	__u16 udp_dst_max;	/* exclusive, dest UDP port */
 
 	/* DSCP + ECN */
-	__u8 tos;            /* six MSB of (former) IPv4 TOS
-				are for dscp codepoint */
-	__u8 traffic_class;  /* ditto for the (former) Traffic Class in IPv6
-				(see RFC 3260, sec. 4) */
+	__u8 tos;		/* six MSB of (former) IPv4 TOS
+				 * are for dscp codepoint
+				 */
+	__u8 traffic_class;	/* ditto for the (former) Traffic Class in IPv6
+				 * (see RFC 3260, sec. 4)
+				 */
 
 	/* IMIX */
 	unsigned int n_imix_entries;
@@ -389,12 +392,12 @@ struct pktgen_dev {
 
 	__u8 hh[14];
 	/* = {
-	   0x00, 0x80, 0xC8, 0x79, 0xB3, 0xCB,
-
-	   We fill in SRC address later
-	   0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	   0x08, 0x00
-	   };
+	 * 0x00, 0x80, 0xC8, 0x79, 0xB3, 0xCB,
+	 *
+	 * We fill in SRC address later
+	 * 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	 * 0x08, 0x00
+	 * };
 	 */
 	__u16 pad;		/* pad out the hh struct to an even 16 bytes */
 
@@ -458,7 +461,8 @@ struct pktgen_thread {
 	char result[512];
 
 	/* Field for thread to receive "posted" events terminate,
-	   stop ifs etc. */
+	 * stop ifs etc.
+	 */
 
 	u32 control;
 	int cpu;
@@ -472,8 +476,7 @@ struct pktgen_thread {
 #define FIND   0
 
 static const char version[] =
-	"Packet Generator for packet performance testing. "
-	"Version: " VERSION "\n";
+	"Packet Generator for packet performance testing. Version: " VERSION "\n";
 
 static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i);
 static int pktgen_add_device(struct pktgen_thread *t, const char *ifname);
@@ -624,8 +627,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 	seq_printf(seq, "%pM\n", pkt_dev->dst_mac);
 
 	seq_printf(seq,
-		   "     udp_src_min: %d  udp_src_max: %d"
-		   "  udp_dst_min: %d  udp_dst_max: %d\n",
+		   "     udp_src_min: %d  udp_src_max: %d  udp_dst_min: %d  udp_dst_max: %d\n",
 		   pkt_dev->udp_src_min, pkt_dev->udp_src_max,
 		   pkt_dev->udp_dst_min, pkt_dev->udp_dst_max);
 
@@ -754,6 +756,7 @@ static ssize_t hex32_arg(const char __user *user_buffer, size_t maxlen,
 	for (; i < maxlen; i++) {
 		int value;
 		char c;
+
 		if (get_user(c, &user_buffer[i]))
 			return -EFAULT;
 		value = hex_to_bin(c);
@@ -773,6 +776,7 @@ static ssize_t count_trail_chars(const char __user *user_buffer, size_t maxlen)
 
 	for (i = 0; i < maxlen; i++) {
 		char c;
+
 		if (get_user(c, &user_buffer[i]))
 			return -EFAULT;
 		switch (c) {
@@ -799,6 +803,7 @@ static ssize_t num_arg(const char __user *user_buffer, size_t maxlen,
 
 	for (i = 0; i < maxlen; i++) {
 		char c;
+
 		if (get_user(c, &user_buffer[i]))
 			return -EFAULT;
 		if ((c >= '0') && (c <= '9')) {
@@ -816,6 +821,7 @@ static ssize_t strn_len(const char __user *user_buffer, size_t maxlen)
 
 	for (i = 0; i < maxlen; i++) {
 		char c;
+
 		if (get_user(c, &user_buffer[i]))
 			return -EFAULT;
 		switch (c) {
@@ -974,8 +980,8 @@ static __u32 pktgen_read_flag(const char *f, bool *disable)
 }
 
 static ssize_t pktgen_if_write(struct file *file,
-			       const char __user * user_buffer, size_t count,
-			       loff_t * offset)
+			       const char __user *user_buffer, size_t count,
+			       loff_t *offset)
 {
 	struct seq_file *seq = file->private_data;
 	struct pktgen_dev *pkt_dev = seq->private;
@@ -1307,9 +1313,9 @@ static ssize_t pktgen_if_write(struct file *file,
 				put_page(pkt_dev->page);
 				pkt_dev->page = NULL;
 			}
-		}
-		else
+		} else {
 			sprintf(pg_result, "ERROR: node not possible");
+		}
 		return count;
 	}
 	if (!strcmp(name, "xmit_mode")) {
@@ -1413,8 +1419,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			return -EFAULT;
 		buf[len] = 0;
 		if (strcmp(buf, pkt_dev->dst_min) != 0) {
-			memset(pkt_dev->dst_min, 0, sizeof(pkt_dev->dst_min));
-			strcpy(pkt_dev->dst_min, buf);
+			strscpy_pad(pkt_dev->dst_min, buf);
 			pkt_dev->daddr_min = in_aton(pkt_dev->dst_min);
 			pkt_dev->cur_daddr = pkt_dev->daddr_min;
 		}
@@ -1434,8 +1439,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			return -EFAULT;
 		buf[len] = 0;
 		if (strcmp(buf, pkt_dev->dst_max) != 0) {
-			memset(pkt_dev->dst_max, 0, sizeof(pkt_dev->dst_max));
-			strcpy(pkt_dev->dst_max, buf);
+			strscpy_pad(pkt_dev->dst_max, buf);
 			pkt_dev->daddr_max = in_aton(pkt_dev->dst_max);
 			pkt_dev->cur_daddr = pkt_dev->daddr_max;
 		}
@@ -1544,8 +1548,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			return -EFAULT;
 		buf[len] = 0;
 		if (strcmp(buf, pkt_dev->src_min) != 0) {
-			memset(pkt_dev->src_min, 0, sizeof(pkt_dev->src_min));
-			strcpy(pkt_dev->src_min, buf);
+			strscpy_pad(pkt_dev->src_min, buf);
 			pkt_dev->saddr_min = in_aton(pkt_dev->src_min);
 			pkt_dev->cur_saddr = pkt_dev->saddr_min;
 		}
@@ -1565,8 +1568,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			return -EFAULT;
 		buf[len] = 0;
 		if (strcmp(buf, pkt_dev->src_max) != 0) {
-			memset(pkt_dev->src_max, 0, sizeof(pkt_dev->src_max));
-			strcpy(pkt_dev->src_max, buf);
+			strscpy_pad(pkt_dev->src_max, buf);
 			pkt_dev->saddr_max = in_aton(pkt_dev->src_max);
 			pkt_dev->cur_saddr = pkt_dev->saddr_max;
 		}
@@ -1909,8 +1911,8 @@ static int pktgen_thread_show(struct seq_file *seq, void *v)
 }
 
 static ssize_t pktgen_thread_write(struct file *file,
-				   const char __user * user_buffer,
-				   size_t count, loff_t * offset)
+				   const char __user *user_buffer,
+				   size_t count, loff_t *offset)
 {
 	struct seq_file *seq = file->private_data;
 	struct pktgen_thread *t = seq->private;
@@ -1962,6 +1964,7 @@ static ssize_t pktgen_thread_write(struct file *file,
 
 	if (!strcmp(name, "add_device")) {
 		char f[32];
+
 		memset(f, 0, 32);
 		max = min(sizeof(f) - 1, count - i);
 		len = strn_len(&user_buffer[i], max);
@@ -2397,13 +2400,14 @@ static inline int f_pick(struct pktgen_dev *pkt_dev)
 
 /* If there was already an IPSEC SA, we keep it as is, else
  * we go look for it ...
-*/
+ */
 #define DUMMY_MARK 0
 static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow)
 {
 #ifdef CONFIG_XFRM
 	struct xfrm_state *x = pkt_dev->flows[flow].x;
 	struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id);
+
 	if (!x) {
 
 		if (pkt_dev->spi) {
@@ -2436,6 +2440,7 @@ static void set_cur_queue_map(struct pktgen_dev *pkt_dev)
 
 	else if (pkt_dev->queue_map_min <= pkt_dev->queue_map_max) {
 		__u16 t;
+
 		if (pkt_dev->flags & F_QUEUE_MAP_RND) {
 			t = get_random_u32_inclusive(pkt_dev->queue_map_min,
 						     pkt_dev->queue_map_max);
@@ -2517,6 +2522,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 
 	if (pkt_dev->flags & F_MPLS_RND) {
 		unsigned int i;
+
 		for (i = 0; i < pkt_dev->nr_labels; i++)
 			if (pkt_dev->labels[i] & MPLS_STACK_BOTTOM)
 				pkt_dev->labels[i] = MPLS_STACK_BOTTOM |
@@ -2561,6 +2567,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 		imx = ntohl(pkt_dev->saddr_max);
 		if (imn < imx) {
 			__u32 t;
+
 			if (pkt_dev->flags & F_IPSRC_RND)
 				t = get_random_u32_inclusive(imn, imx - 1);
 			else {
@@ -2581,6 +2588,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 			if (imn < imx) {
 				__u32 t;
 				__be32 s;
+
 				if (pkt_dev->flags & F_IPDST_RND) {
 
 					do {
@@ -2628,6 +2636,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 
 	if (pkt_dev->min_pkt_size < pkt_dev->max_pkt_size) {
 		__u32 t;
+
 		if (pkt_dev->flags & F_TXSIZE_RND) {
 			t = get_random_u32_inclusive(pkt_dev->min_pkt_size,
 						     pkt_dev->max_pkt_size - 1);
@@ -2694,7 +2703,8 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev)
 	if (!x)
 		return 0;
 	/* XXX: we dont support tunnel mode for now until
-	 * we resolve the dst issue */
+	 * we resolve the dst issue
+	 */
 	if ((x->props.mode != XFRM_MODE_TRANSPORT) && (pkt_dev->spi == 0))
 		return 0;
 
@@ -2729,8 +2739,10 @@ static void free_SAs(struct pktgen_dev *pkt_dev)
 	if (pkt_dev->cflows) {
 		/* let go of the SAs if we have them */
 		int i;
+
 		for (i = 0; i < pkt_dev->cflows; i++) {
 			struct xfrm_state *x = pkt_dev->flows[i].x;
+
 			if (x) {
 				xfrm_state_put(x);
 				pkt_dev->flows[i].x = NULL;
@@ -2745,6 +2757,7 @@ static int process_ipsec(struct pktgen_dev *pkt_dev,
 	if (pkt_dev->flags & F_IPSEC) {
 		struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x;
 		int nhead = 0;
+
 		if (x) {
 			struct ethhdr *eth;
 			struct iphdr *iph;
@@ -2788,6 +2801,7 @@ err:
 static void mpls_push(__be32 *mpls, struct pktgen_dev *pkt_dev)
 {
 	unsigned int i;
+
 	for (i = 0; i < pkt_dev->nr_labels; i++)
 		*mpls++ = pkt_dev->labels[i] & ~MPLS_STACK_BOTTOM;
 
@@ -2900,7 +2914,7 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
 			skb->dev = dev;
 		}
 	} else {
-		 skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT);
+		skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT);
 	}
 
 	/* the caller pre-fetches from skb->data and reserves for the mac hdr */
@@ -2981,7 +2995,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
 	skb->priority = pkt_dev->skb_priority;
 
 	memcpy(eth, pkt_dev->hh, 12);
-	*(__be16 *) & eth[12] = protocol;
+	*(__be16 *)&eth[12] = protocol;
 
 	/* Eth + IPh + UDPh + mpls */
 	datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8 -
@@ -3210,11 +3224,11 @@ static void pktgen_run(struct pktgen_thread *t)
 
 			set_pkt_overhead(pkt_dev);
 
-			strcpy(pkt_dev->result, "Starting");
+			strscpy(pkt_dev->result, "Starting");
 			pkt_dev->running = 1;	/* Cranke yeself! */
 			started++;
 		} else
-			strcpy(pkt_dev->result, "Error starting");
+			strscpy(pkt_dev->result, "Error starting");
 	}
 	rcu_read_unlock();
 	if (started)
@@ -3473,6 +3487,7 @@ static void pktgen_rem_thread(struct pktgen_thread *t)
 static void pktgen_resched(struct pktgen_dev *pkt_dev)
 {
 	ktime_t idle_start = ktime_get();
+
 	schedule();
 	pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_get(), idle_start));
 }
@@ -3788,7 +3803,8 @@ static int add_dev_to_thread(struct pktgen_thread *t,
 	 * userspace on another CPU than the kthread.  The if_lock()
 	 * is used here to sync with concurrent instances of
 	 * _rem_dev_from_if_list() invoked via kthread, which is also
-	 * updating the if_list */
+	 * updating the if_list
+	 */
 	if_lock(t);
 
 	if (pkt_dev->pg_thread) {
@@ -3826,7 +3842,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
 	if (!pkt_dev)
 		return -ENOMEM;
 
-	strcpy(pkt_dev->odevname, ifname);
+	strscpy(pkt_dev->odevname, ifname);
 	pkt_dev->flows = vzalloc_node(array_size(MAX_CFLOWS,
 						 sizeof(struct flow_state)),
 				      node);
@@ -3983,7 +3999,8 @@ static int pktgen_remove_device(struct pktgen_thread *t,
 
 	/* Remove proc before if_list entry, because add_device uses
 	 * list to determine if interface already exist, avoid race
-	 * with proc_create_data() */
+	 * with proc_create_data()
+	 */
 	proc_remove(pkt_dev->entry);
 
 	/* And update the thread if_list */
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 39a5b72e861f..8a914b37ef6e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2390,12 +2390,12 @@ static int rtnl_valid_dump_ifinfo_req(const struct nlmsghdr *nlh,
 	if (strict_check) {
 		struct ifinfomsg *ifm;
 
-		if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+		ifm = nlmsg_payload(nlh, sizeof(*ifm));
+		if (!ifm) {
 			NL_SET_ERR_MSG(extack, "Invalid header for link dump");
 			return -EINVAL;
 		}
 
-		ifm = nlmsg_data(nlh);
 		if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
 		    ifm->ifi_change) {
 			NL_SET_ERR_MSG(extack, "Invalid values in header for link dump request");
@@ -3580,7 +3580,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
 int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm,
 			u32 portid, const struct nlmsghdr *nlh)
 {
-	unsigned int old_flags;
+	unsigned int old_flags, changed;
 	int err;
 
 	old_flags = dev->flags;
@@ -3591,12 +3591,13 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm,
 			return err;
 	}
 
-	if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
-		__dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags), portid, nlh);
-	} else {
-		dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-		__dev_notify_flags(dev, old_flags, ~0U, portid, nlh);
+	changed = old_flags ^ dev->flags;
+	if (dev->rtnl_link_initializing) {
+		dev->rtnl_link_initializing = false;
+		changed = ~0U;
 	}
+
+	__dev_notify_flags(dev, old_flags, changed, portid, nlh);
 	return 0;
 }
 EXPORT_SYMBOL(rtnl_configure_link);
@@ -3654,7 +3655,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 
 	dev_net_set(dev, net);
 	dev->rtnl_link_ops = ops;
-	dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
+	dev->rtnl_link_initializing = true;
 
 	if (tb[IFLA_MTU]) {
 		u32 mtu = nla_get_u32(tb[IFLA_MTU]);
@@ -3676,11 +3677,8 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 				nla_len(tb[IFLA_BROADCAST]));
 	if (tb[IFLA_TXQLEN])
 		dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);
-	if (tb[IFLA_OPERSTATE]) {
-		netdev_lock_ops(dev);
+	if (tb[IFLA_OPERSTATE])
 		set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
-		netdev_unlock_ops(dev);
-	}
 	if (tb[IFLA_LINKMODE])
 		dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);
 	if (tb[IFLA_GROUP])
@@ -4086,7 +4084,8 @@ static int rtnl_valid_getlink_req(struct sk_buff *skb,
 	struct ifinfomsg *ifm;
 	int i, err;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+	ifm = nlmsg_payload(nlh, sizeof(*ifm));
+	if (!ifm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for get link");
 		return -EINVAL;
 	}
@@ -4095,7 +4094,6 @@ static int rtnl_valid_getlink_req(struct sk_buff *skb,
 		return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFLA_MAX,
 					      ifla_policy, extack);
 
-	ifm = nlmsg_data(nlh);
 	if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
 	    ifm->ifi_change) {
 		NL_SET_ERR_MSG(extack, "Invalid values in header for get link request");
@@ -4886,12 +4884,12 @@ static int valid_fdb_dump_strict(const struct nlmsghdr *nlh,
 	struct ndmsg *ndm;
 	int err, i;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+	ndm = nlmsg_payload(nlh, sizeof(*ndm));
+	if (!ndm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for fdb dump request");
 		return -EINVAL;
 	}
 
-	ndm = nlmsg_data(nlh);
 	if (ndm->ndm_pad1  || ndm->ndm_pad2  || ndm->ndm_state ||
 	    ndm->ndm_flags || ndm->ndm_type) {
 		NL_SET_ERR_MSG(extack, "Invalid values in header for fdb dump request");
@@ -5054,12 +5052,12 @@ static int valid_fdb_get_strict(const struct nlmsghdr *nlh,
 	struct ndmsg *ndm;
 	int err, i;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+	ndm = nlmsg_payload(nlh, sizeof(*ndm));
+	if (!ndm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for fdb get request");
 		return -EINVAL;
 	}
 
-	ndm = nlmsg_data(nlh);
 	if (ndm->ndm_pad1  || ndm->ndm_pad2  || ndm->ndm_state ||
 	    ndm->ndm_type) {
 		NL_SET_ERR_MSG(extack, "Invalid values in header for fdb get request");
@@ -5326,12 +5324,12 @@ static int valid_bridge_getlink_req(const struct nlmsghdr *nlh,
 	if (strict_check) {
 		struct ifinfomsg *ifm;
 
-		if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+		ifm = nlmsg_payload(nlh, sizeof(*ifm));
+		if (!ifm) {
 			NL_SET_ERR_MSG(extack, "Invalid header for bridge link dump");
 			return -EINVAL;
 		}
 
-		ifm = nlmsg_data(nlh);
 		if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
 		    ifm->ifi_change || ifm->ifi_index) {
 			NL_SET_ERR_MSG(extack, "Invalid values in header for bridge link dump request");
@@ -6223,7 +6221,8 @@ static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check,
 {
 	struct if_stats_msg *ifsm;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifsm))) {
+	ifsm = nlmsg_payload(nlh, sizeof(*ifsm));
+	if (!ifsm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for stats dump");
 		return -EINVAL;
 	}
@@ -6231,8 +6230,6 @@ static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check,
 	if (!strict_check)
 		return 0;
 
-	ifsm = nlmsg_data(nlh);
-
 	/* only requests using strict checks can pass data to influence
 	 * the dump. The legacy exception is filter_mask.
 	 */
@@ -6460,12 +6457,12 @@ static int rtnl_mdb_valid_dump_req(const struct nlmsghdr *nlh,
 {
 	struct br_port_msg *bpm;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*bpm))) {
+	bpm = nlmsg_payload(nlh, sizeof(*bpm));
+	if (!bpm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for mdb dump request");
 		return -EINVAL;
 	}
 
-	bpm = nlmsg_data(nlh);
 	if (bpm->ifindex) {
 		NL_SET_ERR_MSG(extack, "Filtering by device index is not supported for mdb dump request");
 		return -EINVAL;
diff --git a/net/core/scm.c b/net/core/scm.c
index 733c0cbd393d..0225bd94170f 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -404,3 +404,125 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl)
 	return new_fpl;
 }
 EXPORT_SYMBOL(scm_fp_dup);
+
+#ifdef CONFIG_SECURITY_NETWORK
+static void scm_passec(struct sock *sk, struct msghdr *msg, struct scm_cookie *scm)
+{
+	struct lsm_context ctx;
+	int err;
+
+	if (sk->sk_scm_security) {
+		err = security_secid_to_secctx(scm->secid, &ctx);
+
+		if (err >= 0) {
+			put_cmsg(msg, SOL_SOCKET, SCM_SECURITY, ctx.len,
+				 ctx.context);
+
+			security_release_secctx(&ctx);
+		}
+	}
+}
+
+static bool scm_has_secdata(struct sock *sk)
+{
+	return sk->sk_scm_security;
+}
+#else
+static void scm_passec(struct sock *sk, struct msghdr *msg, struct scm_cookie *scm)
+{
+}
+
+static bool scm_has_secdata(struct sock *sk)
+{
+	return false;
+}
+#endif
+
+static void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm)
+{
+	struct file *pidfd_file = NULL;
+	int len, pidfd;
+
+	/* put_cmsg() doesn't return an error if CMSG is truncated,
+	 * that's why we need to opencode these checks here.
+	 */
+	if (msg->msg_flags & MSG_CMSG_COMPAT)
+		len = sizeof(struct compat_cmsghdr) + sizeof(int);
+	else
+		len = sizeof(struct cmsghdr) + sizeof(int);
+
+	if (msg->msg_controllen < len) {
+		msg->msg_flags |= MSG_CTRUNC;
+		return;
+	}
+
+	if (!scm->pid)
+		return;
+
+	pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file);
+
+	if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) {
+		if (pidfd_file) {
+			put_unused_fd(pidfd);
+			fput(pidfd_file);
+		}
+
+		return;
+	}
+
+	if (pidfd_file)
+		fd_install(pidfd, pidfd_file);
+}
+
+static bool __scm_recv_common(struct sock *sk, struct msghdr *msg,
+			      struct scm_cookie *scm, int flags)
+{
+	if (!msg->msg_control) {
+		if (sk->sk_scm_credentials || sk->sk_scm_pidfd ||
+		    scm->fp || scm_has_secdata(sk))
+			msg->msg_flags |= MSG_CTRUNC;
+
+		scm_destroy(scm);
+		return false;
+	}
+
+	if (sk->sk_scm_credentials) {
+		struct user_namespace *current_ns = current_user_ns();
+		struct ucred ucreds = {
+			.pid = scm->creds.pid,
+			.uid = from_kuid_munged(current_ns, scm->creds.uid),
+			.gid = from_kgid_munged(current_ns, scm->creds.gid),
+		};
+
+		put_cmsg(msg, SOL_SOCKET, SCM_CREDENTIALS, sizeof(ucreds), &ucreds);
+	}
+
+	scm_passec(sk, msg, scm);
+
+	if (scm->fp)
+		scm_detach_fds(msg, scm);
+
+	return true;
+}
+
+void scm_recv(struct socket *sock, struct msghdr *msg,
+	      struct scm_cookie *scm, int flags)
+{
+	if (!__scm_recv_common(sock->sk, msg, scm, flags))
+		return;
+
+	scm_destroy_cred(scm);
+}
+EXPORT_SYMBOL(scm_recv);
+
+void scm_recv_unix(struct socket *sock, struct msghdr *msg,
+		   struct scm_cookie *scm, int flags)
+{
+	if (!__scm_recv_common(sock->sk, msg, scm, flags))
+		return;
+
+	if (sock->sk->sk_scm_pidfd)
+		scm_pidfd_recv(msg, scm);
+
+	scm_destroy_cred(scm);
+}
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 568779d5a0ef..9a3965680451 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -156,45 +156,3 @@ u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
 }
 EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
 #endif
-
-#if IS_ENABLED(CONFIG_IP_DCCP)
-u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
-				__be16 sport, __be16 dport)
-{
-	u64 seq;
-	net_secret_init();
-	seq = siphash_3u32((__force u32)saddr, (__force u32)daddr,
-			   (__force u32)sport << 16 | (__force u32)dport,
-			   &net_secret);
-	seq += ktime_get_real_ns();
-	seq &= (1ull << 48) - 1;
-	return seq;
-}
-EXPORT_SYMBOL(secure_dccp_sequence_number);
-
-#if IS_ENABLED(CONFIG_IPV6)
-u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
-				  __be16 sport, __be16 dport)
-{
-	const struct {
-		struct in6_addr saddr;
-		struct in6_addr daddr;
-		__be16 sport;
-		__be16 dport;
-	} __aligned(SIPHASH_ALIGNMENT) combined = {
-		.saddr = *(struct in6_addr *)saddr,
-		.daddr = *(struct in6_addr *)daddr,
-		.sport = sport,
-		.dport = dport
-	};
-	u64 seq;
-	net_secret_init();
-	seq = siphash(&combined, offsetofend(typeof(combined), dport),
-		      &net_secret);
-	seq += ktime_get_real_ns();
-	seq &= (1ull << 48) - 1;
-	return seq;
-}
-EXPORT_SYMBOL(secure_dccpv6_sequence_number);
-#endif
-#endif
diff --git a/net/core/selftests.c b/net/core/selftests.c
index e99ae983fca9..35f807ea9952 100644
--- a/net/core/selftests.c
+++ b/net/core/selftests.c
@@ -100,10 +100,10 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
 	ehdr->h_proto = htons(ETH_P_IP);
 
 	if (attr->tcp) {
+		memset(thdr, 0, sizeof(*thdr));
 		thdr->source = htons(attr->sport);
 		thdr->dest = htons(attr->dport);
 		thdr->doff = sizeof(struct tcphdr) / 4;
-		thdr->check = 0;
 	} else {
 		uhdr->source = htons(attr->sport);
 		uhdr->dest = htons(attr->dport);
@@ -144,10 +144,18 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
 	attr->id = net_test_next_id;
 	shdr->id = net_test_next_id++;
 
-	if (attr->size)
-		skb_put(skb, attr->size);
-	if (attr->max_size && attr->max_size > skb->len)
-		skb_put(skb, attr->max_size - skb->len);
+	if (attr->size) {
+		void *payload = skb_put(skb, attr->size);
+
+		memset(payload, 0, attr->size);
+	}
+
+	if (attr->max_size && attr->max_size > skb->len) {
+		size_t pad_len = attr->max_size - skb->len;
+		void *pad = skb_put(skb, pad_len);
+
+		memset(pad, 0, pad_len);
+	}
 
 	skb->csum = 0;
 	skb->ip_summed = CHECKSUM_PARTIAL;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6cbf77bc61fc..85fc82f72d26 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -64,6 +64,7 @@
 #include <linux/mpls.h>
 #include <linux/kcov.h>
 #include <linux/iov_iter.h>
+#include <linux/crc32.h>
 
 #include <net/protocol.h>
 #include <net/dst.h>
@@ -89,6 +90,7 @@
 #include <linux/textsearch.h>
 
 #include "dev.h"
+#include "devmem.h"
 #include "netmem_priv.h"
 #include "sock_destructor.h"
 
@@ -893,11 +895,6 @@ static void skb_clone_fraglist(struct sk_buff *skb)
 		skb_get(list);
 }
 
-static bool is_pp_netmem(netmem_ref netmem)
-{
-	return (netmem_get_pp_magic(netmem) & ~0x3UL) == PP_SIGNATURE;
-}
-
 int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
 		    unsigned int headroom)
 {
@@ -995,14 +992,7 @@ bool napi_pp_put_page(netmem_ref netmem)
 {
 	netmem = netmem_compound_head(netmem);
 
-	/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
-	 * in order to preserve any existing bits, such as bit 0 for the
-	 * head page of compound page and bit 1 for pfmemalloc page, so
-	 * mask those bits for freeing side when doing below checking,
-	 * and page_is_pfmemalloc() is checked in __page_pool_put_page()
-	 * to avoid recycling the pfmemalloc page.
-	 */
-	if (unlikely(!is_pp_netmem(netmem)))
+	if (unlikely(!netmem_is_pp(netmem)))
 		return false;
 
 	page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false);
@@ -1042,7 +1032,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb)
 
 	for (i = 0; i < shinfo->nr_frags; i++) {
 		head_netmem = netmem_compound_head(shinfo->frags[i].netmem);
-		if (likely(is_pp_netmem(head_netmem)))
+		if (likely(netmem_is_pp(head_netmem)))
 			page_pool_ref_netmem(head_netmem);
 		else
 			page_ref_inc(netmem_to_page(head_netmem));
@@ -1666,7 +1656,8 @@ void mm_unaccount_pinned_pages(struct mmpin *mmp)
 }
 EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages);
 
-static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
+static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size,
+					    bool devmem)
 {
 	struct ubuf_info_msgzc *uarg;
 	struct sk_buff *skb;
@@ -1681,7 +1672,7 @@ static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
 	uarg = (void *)skb->cb;
 	uarg->mmp.user = NULL;
 
-	if (mm_account_pinned_pages(&uarg->mmp, size)) {
+	if (likely(!devmem) && mm_account_pinned_pages(&uarg->mmp, size)) {
 		kfree_skb(skb);
 		return NULL;
 	}
@@ -1704,7 +1695,7 @@ static inline struct sk_buff *skb_from_uarg(struct ubuf_info_msgzc *uarg)
 }
 
 struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
-				       struct ubuf_info *uarg)
+				       struct ubuf_info *uarg, bool devmem)
 {
 	if (uarg) {
 		struct ubuf_info_msgzc *uarg_zc;
@@ -1734,7 +1725,8 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
 
 		next = (u32)atomic_read(&sk->sk_zckey);
 		if ((u32)(uarg_zc->id + uarg_zc->len) == next) {
-			if (mm_account_pinned_pages(&uarg_zc->mmp, size))
+			if (likely(!devmem) &&
+			    mm_account_pinned_pages(&uarg_zc->mmp, size))
 				return NULL;
 			uarg_zc->len++;
 			uarg_zc->bytelen = bytelen;
@@ -1749,7 +1741,7 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
 	}
 
 new_alloc:
-	return msg_zerocopy_alloc(sk, size);
+	return msg_zerocopy_alloc(sk, size, devmem);
 }
 EXPORT_SYMBOL_GPL(msg_zerocopy_realloc);
 
@@ -1853,7 +1845,8 @@ EXPORT_SYMBOL_GPL(msg_zerocopy_ubuf_ops);
 
 int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 			     struct msghdr *msg, int len,
-			     struct ubuf_info *uarg)
+			     struct ubuf_info *uarg,
+			     struct net_devmem_dmabuf_binding *binding)
 {
 	int err, orig_len = skb->len;
 
@@ -1872,7 +1865,8 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 			return -EEXIST;
 	}
 
-	err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len);
+	err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len,
+				      binding);
 	if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) {
 		struct sock *save_sk = skb->sk;
 
@@ -3239,7 +3233,7 @@ static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg)
 
 typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg);
 static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
-			   int len, sendmsg_func sendmsg)
+			   int len, sendmsg_func sendmsg, int flags)
 {
 	unsigned int orig_len = len;
 	struct sk_buff *head = skb;
@@ -3257,7 +3251,7 @@ do_frag_list:
 		kv.iov_base = skb->data + offset;
 		kv.iov_len = slen;
 		memset(&msg, 0, sizeof(msg));
-		msg.msg_flags = MSG_DONTWAIT;
+		msg.msg_flags = MSG_DONTWAIT | flags;
 
 		iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen);
 		ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
@@ -3294,7 +3288,8 @@ do_frag_list:
 		while (slen) {
 			struct bio_vec bvec;
 			struct msghdr msg = {
-				.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT,
+				.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT |
+					     flags,
 			};
 
 			bvec_set_page(&bvec, skb_frag_page(frag), slen,
@@ -3340,14 +3335,21 @@ error:
 int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset,
 			 int len)
 {
-	return __skb_send_sock(sk, skb, offset, len, sendmsg_locked);
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, 0);
 }
 EXPORT_SYMBOL_GPL(skb_send_sock_locked);
 
+int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb,
+				    int offset, int len, int flags)
+{
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, flags);
+}
+EXPORT_SYMBOL_GPL(skb_send_sock_locked_with_flags);
+
 /* Send skb data on a socket. Socket must be unlocked. */
 int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len)
 {
-	return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked);
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked, 0);
 }
 
 /**
@@ -3443,8 +3445,7 @@ fault:
 EXPORT_SYMBOL(skb_store_bits);
 
 /* Checksum skb data. */
-__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
-		      __wsum csum, const struct skb_checksum_ops *ops)
+__wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset;
@@ -3455,8 +3456,7 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		csum = INDIRECT_CALL_1(ops->update, csum_partial_ext,
-				       skb->data + offset, copy, csum);
+		csum = csum_partial(skb->data + offset, copy, csum);
 		if ((len -= copy) == 0)
 			return csum;
 		offset += copy;
@@ -3486,13 +3486,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 					      skb_frag_off(frag) + offset - start,
 					      copy, p, p_off, p_len, copied) {
 				vaddr = kmap_atomic(p);
-				csum2 = INDIRECT_CALL_1(ops->update,
-							csum_partial_ext,
-							vaddr + p_off, p_len, 0);
+				csum2 = csum_partial(vaddr + p_off, p_len, 0);
 				kunmap_atomic(vaddr);
-				csum = INDIRECT_CALL_1(ops->combine,
-						       csum_block_add_ext, csum,
-						       csum2, pos, p_len);
+				csum = csum_block_add(csum, csum2, pos);
 				pos += p_len;
 			}
 
@@ -3513,10 +3509,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 			__wsum csum2;
 			if (copy > len)
 				copy = len;
-			csum2 = __skb_checksum(frag_iter, offset - start,
-					       copy, 0, ops);
-			csum = INDIRECT_CALL_1(ops->combine, csum_block_add_ext,
-					       csum, csum2, pos, copy);
+			csum2 = skb_checksum(frag_iter, offset - start, copy,
+					     0);
+			csum = csum_block_add(csum, csum2, pos);
 			if ((len -= copy) == 0)
 				return csum;
 			offset += copy;
@@ -3528,18 +3523,6 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 
 	return csum;
 }
-EXPORT_SYMBOL(__skb_checksum);
-
-__wsum skb_checksum(const struct sk_buff *skb, int offset,
-		    int len, __wsum csum)
-{
-	const struct skb_checksum_ops ops = {
-		.update  = csum_partial_ext,
-		.combine = csum_block_add_ext,
-	};
-
-	return __skb_checksum(skb, offset, len, csum, &ops);
-}
 EXPORT_SYMBOL(skb_checksum);
 
 /* Both of above in one bottle. */
@@ -3632,6 +3615,78 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
 }
 EXPORT_SYMBOL(skb_copy_and_csum_bits);
 
+#ifdef CONFIG_NET_CRC32C
+u32 skb_crc32c(const struct sk_buff *skb, int offset, int len, u32 crc)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
+
+	if (copy > 0) {
+		copy = min(copy, len);
+		crc = crc32c(crc, skb->data + offset, copy);
+		len -= copy;
+		if (len == 0)
+			return crc;
+		offset += copy;
+	}
+
+	if (WARN_ON_ONCE(!skb_frags_readable(skb)))
+		return 0;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_frag_size(frag);
+		copy = end - offset;
+		if (copy > 0) {
+			u32 p_off, p_len, copied;
+			struct page *p;
+			u8 *vaddr;
+
+			copy = min(copy, len);
+			skb_frag_foreach_page(frag,
+					      skb_frag_off(frag) + offset - start,
+					      copy, p, p_off, p_len, copied) {
+				vaddr = kmap_atomic(p);
+				crc = crc32c(crc, vaddr + p_off, p_len);
+				kunmap_atomic(vaddr);
+			}
+			len -= copy;
+			if (len == 0)
+				return crc;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		copy = end - offset;
+		if (copy > 0) {
+			copy = min(copy, len);
+			crc = skb_crc32c(frag_iter, offset - start, copy, crc);
+			len -= copy;
+			if (len == 0)
+				return crc;
+			offset += copy;
+		}
+		start = end;
+	}
+	BUG_ON(len);
+
+	return crc;
+}
+EXPORT_SYMBOL(skb_crc32c);
+#endif /* CONFIG_NET_CRC32C */
+
 __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 {
 	__sum16 sum;
@@ -3691,32 +3746,6 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(__skb_checksum_complete);
 
-static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum)
-{
-	net_warn_ratelimited(
-		"%s: attempt to compute crc32c without libcrc32c.ko\n",
-		__func__);
-	return 0;
-}
-
-static __wsum warn_crc32c_csum_combine(__wsum csum, __wsum csum2,
-				       int offset, int len)
-{
-	net_warn_ratelimited(
-		"%s: attempt to compute crc32c without libcrc32c.ko\n",
-		__func__);
-	return 0;
-}
-
-static const struct skb_checksum_ops default_crc32c_ops = {
-	.update  = warn_crc32c_csum_update,
-	.combine = warn_crc32c_csum_combine,
-};
-
-const struct skb_checksum_ops *crc32c_csum_stub __read_mostly =
-	&default_crc32c_ops;
-EXPORT_SYMBOL(crc32c_csum_stub);
-
  /**
  *	skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy()
  *	@from: source buffer
@@ -7317,3 +7346,32 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes,
 	return false;
 }
 EXPORT_SYMBOL(csum_and_copy_from_iter_full);
+
+void get_netmem(netmem_ref netmem)
+{
+	struct net_iov *niov;
+
+	if (netmem_is_net_iov(netmem)) {
+		niov = netmem_to_net_iov(netmem);
+		if (net_is_devmem_iov(niov))
+			net_devmem_get_net_iov(netmem_to_net_iov(netmem));
+		return;
+	}
+	get_page(netmem_to_page(netmem));
+}
+EXPORT_SYMBOL(get_netmem);
+
+void put_netmem(netmem_ref netmem)
+{
+	struct net_iov *niov;
+
+	if (netmem_is_net_iov(netmem)) {
+		niov = netmem_to_net_iov(netmem);
+		if (net_is_devmem_iov(niov))
+			net_devmem_put_net_iov(netmem_to_net_iov(netmem));
+		return;
+	}
+
+	put_page(netmem_to_page(netmem));
+}
+EXPORT_SYMBOL(put_netmem);
diff --git a/net/core/sock.c b/net/core/sock.c
index e54449c9ab0b..0cb52e590094 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1220,15 +1220,6 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 			return 0;
 		}
 		return -EPERM;
-	case SO_PASSSEC:
-		assign_bit(SOCK_PASSSEC, &sock->flags, valbool);
-		return 0;
-	case SO_PASSCRED:
-		assign_bit(SOCK_PASSCRED, &sock->flags, valbool);
-		return 0;
-	case SO_PASSPIDFD:
-		assign_bit(SOCK_PASSPIDFD, &sock->flags, valbool);
-		return 0;
 	case SO_TYPE:
 	case SO_PROTOCOL:
 	case SO_DOMAIN:
@@ -1276,6 +1267,8 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		return 0;
 		}
 	case SO_TXREHASH:
+		if (!sk_is_tcp(sk))
+			return -EOPNOTSUPP;
 		if (val < -1 || val > 1)
 			return -EINVAL;
 		if ((u8)val == SOCK_TXREHASH_DEFAULT)
@@ -1557,6 +1550,33 @@ set_sndbuf:
 		sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
 		break;
 
+	case SO_PASSCRED:
+		if (sk_may_scm_recv(sk))
+			sk->sk_scm_credentials = valbool;
+		else
+			ret = -EOPNOTSUPP;
+		break;
+
+	case SO_PASSSEC:
+		if (IS_ENABLED(CONFIG_SECURITY_NETWORK) && sk_may_scm_recv(sk))
+			sk->sk_scm_security = valbool;
+		else
+			ret = -EOPNOTSUPP;
+		break;
+
+	case SO_PASSPIDFD:
+		if (sk_is_unix(sk))
+			sk->sk_scm_pidfd = valbool;
+		else
+			ret = -EOPNOTSUPP;
+		break;
+
+	case SO_PASSRIGHTS:
+		if (sk_is_unix(sk))
+			sk->sk_scm_rights = valbool;
+		else
+			ret = -EOPNOTSUPP;
+		break;
 
 	case SO_INCOMING_CPU:
 		reuseport_update_incoming_cpu(sk, val);
@@ -1853,11 +1873,24 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_PASSCRED:
-		v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
+		if (!sk_may_scm_recv(sk))
+			return -EOPNOTSUPP;
+
+		v.val = sk->sk_scm_credentials;
 		break;
 
 	case SO_PASSPIDFD:
-		v.val = !!test_bit(SOCK_PASSPIDFD, &sock->flags);
+		if (!sk_is_unix(sk))
+			return -EOPNOTSUPP;
+
+		v.val = sk->sk_scm_pidfd;
+		break;
+
+	case SO_PASSRIGHTS:
+		if (!sk_is_unix(sk))
+			return -EOPNOTSUPP;
+
+		v.val = sk->sk_scm_rights;
 		break;
 
 	case SO_PEERCRED:
@@ -1954,7 +1987,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_PASSSEC:
-		v.val = !!test_bit(SOCK_PASSSEC, &sock->flags);
+		if (!IS_ENABLED(CONFIG_SECURITY_NETWORK) || !sk_may_scm_recv(sk))
+			return -EOPNOTSUPP;
+
+		v.val = sk->sk_scm_security;
 		break;
 
 	case SO_PEERSEC:
@@ -2102,6 +2138,9 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_TXREHASH:
+		if (!sk_is_tcp(sk))
+			return -EOPNOTSUPP;
+
 		/* Paired with WRITE_ONCE() in sk_setsockopt() */
 		v.val = READ_ONCE(sk->sk_txrehash);
 		break;
@@ -2494,17 +2533,14 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		if (!is_charged)
 			RCU_INIT_POINTER(newsk->sk_filter, NULL);
-		sk_free_unlock_clone(newsk);
-		newsk = NULL;
-		goto out;
+
+		goto free;
 	}
+
 	RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL);
 
-	if (bpf_sk_storage_clone(sk, newsk)) {
-		sk_free_unlock_clone(newsk);
-		newsk = NULL;
-		goto out;
-	}
+	if (bpf_sk_storage_clone(sk, newsk))
+		goto free;
 
 	/* Clear sk_user_data if parent had the pointer tagged
 	 * as not suitable for copying when cloning.
@@ -2534,18 +2570,17 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		net_enable_timestamp();
 out:
 	return newsk;
-}
-EXPORT_SYMBOL_GPL(sk_clone_lock);
-
-void sk_free_unlock_clone(struct sock *sk)
-{
+free:
 	/* It is still raw copy of parent, so invalidate
-	 * destructor and make plain sk_free() */
-	sk->sk_destruct = NULL;
-	bh_unlock_sock(sk);
-	sk_free(sk);
+	 * destructor and make plain sk_free()
+	 */
+	newsk->sk_destruct = NULL;
+	bh_unlock_sock(newsk);
+	sk_free(newsk);
+	newsk = NULL;
+	goto out;
 }
-EXPORT_SYMBOL_GPL(sk_free_unlock_clone);
+EXPORT_SYMBOL_GPL(sk_clone_lock);
 
 static u32 sk_dst_gso_max_size(struct sock *sk, struct dst_entry *dst)
 {
@@ -3022,6 +3057,11 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
 			return -EPERM;
 		sockc->priority = *(u32 *)CMSG_DATA(cmsg);
 		break;
+	case SCM_DEVMEM_DMABUF:
+		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
+			return -EINVAL;
+		sockc->dmabuf_id = *(u32 *)CMSG_DATA(cmsg);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -4004,7 +4044,7 @@ static int assign_proto_idx(struct proto *prot)
 {
 	prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR);
 
-	if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) {
+	if (unlikely(prot->inuse_idx == PROTO_INUSE_NR)) {
 		pr_err("PROTO_INUSE_NR exhausted\n");
 		return -ENOSPC;
 	}
@@ -4015,7 +4055,7 @@ static int assign_proto_idx(struct proto *prot)
 
 static void release_proto_idx(struct proto *prot)
 {
-	if (prot->inuse_idx != PROTO_INUSE_NR - 1)
+	if (prot->inuse_idx != PROTO_INUSE_NR)
 		clear_bit(prot->inuse_idx, proto_inuse_idx);
 }
 #else
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index a08eed9b9142..b23594c767f2 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -264,8 +264,6 @@ static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	switch (nlh->nlmsg_type) {
 	case TCPDIAG_GETSOCK:
-	case DCCPDIAG_GETSOCK:
-
 		if (!rcu_access_pointer(inet_rcv_compat))
 			sock_load_diag_module(AF_INET, 0);
 
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 3cd0db9c9d2d..e6f22ba61c1e 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -438,8 +438,8 @@ void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type,
 		netmem = netmem_compound_head(netmem);
 		if (napi_direct && xdp_return_frame_no_direct())
 			napi_direct = false;
-		/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
-		 * as mem->type knows this a page_pool page
+		/* No need to check netmem_is_pp() as mem->type knows this a
+		 * page_pool page
 		 */
 		page_pool_put_full_netmem(netmem_get_pp(netmem), netmem,
 					  napi_direct);
@@ -698,23 +698,24 @@ static noinline bool xdp_copy_frags_from_zc(struct sk_buff *skb,
 	nr_frags = xinfo->nr_frags;
 
 	for (u32 i = 0; i < nr_frags; i++) {
-		u32 len = skb_frag_size(&xinfo->frags[i]);
+		const skb_frag_t *frag = &xinfo->frags[i];
+		u32 len = skb_frag_size(frag);
 		u32 offset, truesize = len;
-		netmem_ref netmem;
+		struct page *page;
 
-		netmem = page_pool_dev_alloc_netmem(pp, &offset, &truesize);
-		if (unlikely(!netmem)) {
+		page = page_pool_dev_alloc(pp, &offset, &truesize);
+		if (unlikely(!page)) {
 			sinfo->nr_frags = i;
 			return false;
 		}
 
-		memcpy(__netmem_address(netmem),
-		       __netmem_address(xinfo->frags[i].netmem),
+		memcpy(page_address(page) + offset,
+		       skb_frag_page(frag) + skb_frag_off(frag),
 		       LARGEST_ALIGN(len));
-		__skb_fill_netmem_desc_noacc(sinfo, i, netmem, offset, len);
+		__skb_fill_page_desc_noacc(sinfo, i, page, offset, len);
 
 		tsize += truesize;
-		pfmemalloc |= netmem_is_pfmemalloc(netmem);
+		pfmemalloc |= page_is_pfmemalloc(page);
 	}
 
 	xdp_update_skb_shared_info(skb, nr_frags, xinfo->xdp_frags_size,
@@ -738,25 +739,27 @@ static noinline bool xdp_copy_frags_from_zc(struct sk_buff *skb,
  */
 struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp)
 {
-	struct page_pool *pp = this_cpu_read(system_page_pool);
 	const struct xdp_rxq_info *rxq = xdp->rxq;
 	u32 len = xdp->data_end - xdp->data_meta;
 	u32 truesize = xdp->frame_sz;
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
+	struct page_pool *pp;
 	int metalen;
 	void *data;
 
 	if (!IS_ENABLED(CONFIG_PAGE_POOL))
 		return NULL;
 
+	local_lock_nested_bh(&system_page_pool.bh_lock);
+	pp = this_cpu_read(system_page_pool.pool);
 	data = page_pool_dev_alloc_va(pp, &truesize);
 	if (unlikely(!data))
-		return NULL;
+		goto out;
 
 	skb = napi_build_skb(data, truesize);
 	if (unlikely(!skb)) {
 		page_pool_free_va(pp, data, true);
-		return NULL;
+		goto out;
 	}
 
 	skb_mark_for_recycle(skb);
@@ -775,13 +778,16 @@ struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp)
 	if (unlikely(xdp_buff_has_frags(xdp)) &&
 	    unlikely(!xdp_copy_frags_from_zc(skb, xdp, pp))) {
 		napi_consume_skb(skb, true);
-		return NULL;
+		skb = NULL;
+		goto out;
 	}
 
 	xsk_buff_free(xdp);
 
 	skb->protocol = eth_type_trans(skb, rxq->dev);
 
+out:
+	local_unlock_nested_bh(&system_page_pool.bh_lock);
 	return skb;
 }
 EXPORT_SYMBOL_GPL(xdp_build_skb_from_zc);
@@ -1014,21 +1020,38 @@ void xdp_set_features_flag(struct net_device *dev, xdp_features_t val)
 }
 EXPORT_SYMBOL_GPL(xdp_set_features_flag);
 
-void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg)
+void xdp_features_set_redirect_target_locked(struct net_device *dev,
+					     bool support_sg)
 {
 	xdp_features_t val = (dev->xdp_features | NETDEV_XDP_ACT_NDO_XMIT);
 
 	if (support_sg)
 		val |= NETDEV_XDP_ACT_NDO_XMIT_SG;
-	xdp_set_features_flag(dev, val);
+	xdp_set_features_flag_locked(dev, val);
+}
+EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target_locked);
+
+void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg)
+{
+	netdev_lock(dev);
+	xdp_features_set_redirect_target_locked(dev, support_sg);
+	netdev_unlock(dev);
 }
 EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target);
 
-void xdp_features_clear_redirect_target(struct net_device *dev)
+void xdp_features_clear_redirect_target_locked(struct net_device *dev)
 {
 	xdp_features_t val = dev->xdp_features;
 
 	val &= ~(NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG);
-	xdp_set_features_flag(dev, val);
+	xdp_set_features_flag_locked(dev, val);
+}
+EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target_locked);
+
+void xdp_features_clear_redirect_target(struct net_device *dev)
+{
+	netdev_lock(dev);
+	xdp_features_clear_redirect_target_locked(dev);
+	netdev_unlock(dev);
 }
 EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);
diff --git a/net/dccp/Kconfig b/net/dccp/Kconfig
deleted file mode 100644
index 0c7d2f66ba27..000000000000
--- a/net/dccp/Kconfig
+++ /dev/null
@@ -1,46 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-menuconfig IP_DCCP
-	tristate "The DCCP Protocol"
-	depends on INET
-	help
-	  Datagram Congestion Control Protocol (RFC 4340)
-
-	  From https://www.ietf.org/rfc/rfc4340.txt:
-
-	  The Datagram Congestion Control Protocol (DCCP) is a transport
-	  protocol that implements bidirectional, unicast connections of
-	  congestion-controlled, unreliable datagrams. It should be suitable
-	  for use by applications such as streaming media, Internet telephony,
-	  and on-line games.
-
-	  To compile this protocol support as a module, choose M here: the
-	  module will be called dccp.
-
-	  If in doubt, say N.
-
-if IP_DCCP
-
-config INET_DCCP_DIAG
-	depends on INET_DIAG
-	def_tristate y if (IP_DCCP = y && INET_DIAG = y)
-	def_tristate m
-
-source "net/dccp/ccids/Kconfig"
-
-menu "DCCP Kernel Hacking"
-	depends on DEBUG_KERNEL=y
-
-config IP_DCCP_DEBUG
-	bool "DCCP debug messages"
-	help
-	  Only use this if you're hacking DCCP.
-
-	  When compiling DCCP as a module, this debugging output can be toggled
-	  by setting the parameter dccp_debug of the `dccp' module to 0 or 1.
-
-	  Just say N.
-
-
-endmenu
-
-endif # IP_DDCP
diff --git a/net/dccp/Makefile b/net/dccp/Makefile
deleted file mode 100644
index 5b4ff37bc806..000000000000
--- a/net/dccp/Makefile
+++ /dev/null
@@ -1,30 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_IP_DCCP) += dccp.o dccp_ipv4.o
-
-dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o \
-	  qpolicy.o
-#
-# CCID algorithms to be used by dccp.ko
-#
-# CCID-2 is default (RFC 4340, p. 77) and has Ack Vectors as dependency
-dccp-y += ccids/ccid2.o ackvec.o
-dccp-$(CONFIG_IP_DCCP_CCID3)	+= ccids/ccid3.o
-dccp-$(CONFIG_IP_DCCP_TFRC_LIB) += ccids/lib/tfrc.o		\
-				   ccids/lib/tfrc_equation.o	\
-				   ccids/lib/packet_history.o	\
-				   ccids/lib/loss_interval.o
-
-dccp_ipv4-y := ipv4.o
-
-# build dccp_ipv6 as module whenever either IPv6 or DCCP is a module
-obj-$(subst y,$(CONFIG_IP_DCCP),$(CONFIG_IPV6)) += dccp_ipv6.o
-dccp_ipv6-y := ipv6.o
-
-obj-$(CONFIG_INET_DCCP_DIAG) += dccp_diag.o
-
-dccp-$(CONFIG_SYSCTL) += sysctl.o
-
-dccp_diag-y := diag.o
-
-# build with local directory for trace.h
-CFLAGS_proto.o := -I$(src)
diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c
deleted file mode 100644
index 1cba001bb4c8..000000000000
--- a/net/dccp/ackvec.c
+++ /dev/null
@@ -1,403 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  net/dccp/ackvec.c
- *
- *  An implementation of Ack Vectors for the DCCP protocol
- *  Copyright (c) 2007 University of Aberdeen, Scotland, UK
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
- */
-#include "dccp.h"
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-
-static struct kmem_cache *dccp_ackvec_slab;
-static struct kmem_cache *dccp_ackvec_record_slab;
-
-struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority)
-{
-	struct dccp_ackvec *av = kmem_cache_zalloc(dccp_ackvec_slab, priority);
-
-	if (av != NULL) {
-		av->av_buf_head	= av->av_buf_tail = DCCPAV_MAX_ACKVEC_LEN - 1;
-		INIT_LIST_HEAD(&av->av_records);
-	}
-	return av;
-}
-
-static void dccp_ackvec_purge_records(struct dccp_ackvec *av)
-{
-	struct dccp_ackvec_record *cur, *next;
-
-	list_for_each_entry_safe(cur, next, &av->av_records, avr_node)
-		kmem_cache_free(dccp_ackvec_record_slab, cur);
-	INIT_LIST_HEAD(&av->av_records);
-}
-
-void dccp_ackvec_free(struct dccp_ackvec *av)
-{
-	if (likely(av != NULL)) {
-		dccp_ackvec_purge_records(av);
-		kmem_cache_free(dccp_ackvec_slab, av);
-	}
-}
-
-/**
- * dccp_ackvec_update_records  -  Record information about sent Ack Vectors
- * @av:		Ack Vector records to update
- * @seqno:	Sequence number of the packet carrying the Ack Vector just sent
- * @nonce_sum:	The sum of all buffer nonces contained in the Ack Vector
- */
-int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seqno, u8 nonce_sum)
-{
-	struct dccp_ackvec_record *avr;
-
-	avr = kmem_cache_alloc(dccp_ackvec_record_slab, GFP_ATOMIC);
-	if (avr == NULL)
-		return -ENOBUFS;
-
-	avr->avr_ack_seqno  = seqno;
-	avr->avr_ack_ptr    = av->av_buf_head;
-	avr->avr_ack_ackno  = av->av_buf_ackno;
-	avr->avr_ack_nonce  = nonce_sum;
-	avr->avr_ack_runlen = dccp_ackvec_runlen(av->av_buf + av->av_buf_head);
-	/*
-	 * When the buffer overflows, we keep no more than one record. This is
-	 * the simplest way of disambiguating sender-Acks dating from before the
-	 * overflow from sender-Acks which refer to after the overflow; a simple
-	 * solution is preferable here since we are handling an exception.
-	 */
-	if (av->av_overflow)
-		dccp_ackvec_purge_records(av);
-	/*
-	 * Since GSS is incremented for each packet, the list is automatically
-	 * arranged in descending order of @ack_seqno.
-	 */
-	list_add(&avr->avr_node, &av->av_records);
-
-	dccp_pr_debug("Added Vector, ack_seqno=%llu, ack_ackno=%llu (rl=%u)\n",
-		      (unsigned long long)avr->avr_ack_seqno,
-		      (unsigned long long)avr->avr_ack_ackno,
-		      avr->avr_ack_runlen);
-	return 0;
-}
-
-static struct dccp_ackvec_record *dccp_ackvec_lookup(struct list_head *av_list,
-						     const u64 ackno)
-{
-	struct dccp_ackvec_record *avr;
-	/*
-	 * Exploit that records are inserted in descending order of sequence
-	 * number, start with the oldest record first. If @ackno is `before'
-	 * the earliest ack_ackno, the packet is too old to be considered.
-	 */
-	list_for_each_entry_reverse(avr, av_list, avr_node) {
-		if (avr->avr_ack_seqno == ackno)
-			return avr;
-		if (before48(ackno, avr->avr_ack_seqno))
-			break;
-	}
-	return NULL;
-}
-
-/*
- * Buffer index and length computation using modulo-buffersize arithmetic.
- * Note that, as pointers move from right to left, head is `before' tail.
- */
-static inline u16 __ackvec_idx_add(const u16 a, const u16 b)
-{
-	return (a + b) % DCCPAV_MAX_ACKVEC_LEN;
-}
-
-static inline u16 __ackvec_idx_sub(const u16 a, const u16 b)
-{
-	return __ackvec_idx_add(a, DCCPAV_MAX_ACKVEC_LEN - b);
-}
-
-u16 dccp_ackvec_buflen(const struct dccp_ackvec *av)
-{
-	if (unlikely(av->av_overflow))
-		return DCCPAV_MAX_ACKVEC_LEN;
-	return __ackvec_idx_sub(av->av_buf_tail, av->av_buf_head);
-}
-
-/**
- * dccp_ackvec_update_old  -  Update previous state as per RFC 4340, 11.4.1
- * @av:		non-empty buffer to update
- * @distance:   negative or zero distance of @seqno from buf_ackno downward
- * @seqno:	the (old) sequence number whose record is to be updated
- * @state:	state in which packet carrying @seqno was received
- */
-static void dccp_ackvec_update_old(struct dccp_ackvec *av, s64 distance,
-				   u64 seqno, enum dccp_ackvec_states state)
-{
-	u16 ptr = av->av_buf_head;
-
-	BUG_ON(distance > 0);
-	if (unlikely(dccp_ackvec_is_empty(av)))
-		return;
-
-	do {
-		u8 runlen = dccp_ackvec_runlen(av->av_buf + ptr);
-
-		if (distance + runlen >= 0) {
-			/*
-			 * Only update the state if packet has not been received
-			 * yet. This is OK as per the second table in RFC 4340,
-			 * 11.4.1; i.e. here we are using the following table:
-			 *                     RECEIVED
-			 *                      0   1   3
-			 *              S     +---+---+---+
-			 *              T   0 | 0 | 0 | 0 |
-			 *              O     +---+---+---+
-			 *              R   1 | 1 | 1 | 1 |
-			 *              E     +---+---+---+
-			 *              D   3 | 0 | 1 | 3 |
-			 *                    +---+---+---+
-			 * The "Not Received" state was set by reserve_seats().
-			 */
-			if (av->av_buf[ptr] == DCCPAV_NOT_RECEIVED)
-				av->av_buf[ptr] = state;
-			else
-				dccp_pr_debug("Not changing %llu state to %u\n",
-					      (unsigned long long)seqno, state);
-			break;
-		}
-
-		distance += runlen + 1;
-		ptr	  = __ackvec_idx_add(ptr, 1);
-
-	} while (ptr != av->av_buf_tail);
-}
-
-/* Mark @num entries after buf_head as "Not yet received". */
-static void dccp_ackvec_reserve_seats(struct dccp_ackvec *av, u16 num)
-{
-	u16 start = __ackvec_idx_add(av->av_buf_head, 1),
-	    len	  = DCCPAV_MAX_ACKVEC_LEN - start;
-
-	/* check for buffer wrap-around */
-	if (num > len) {
-		memset(av->av_buf + start, DCCPAV_NOT_RECEIVED, len);
-		start = 0;
-		num  -= len;
-	}
-	if (num)
-		memset(av->av_buf + start, DCCPAV_NOT_RECEIVED, num);
-}
-
-/**
- * dccp_ackvec_add_new  -  Record one or more new entries in Ack Vector buffer
- * @av:		 container of buffer to update (can be empty or non-empty)
- * @num_packets: number of packets to register (must be >= 1)
- * @seqno:	 sequence number of the first packet in @num_packets
- * @state:	 state in which packet carrying @seqno was received
- */
-static void dccp_ackvec_add_new(struct dccp_ackvec *av, u32 num_packets,
-				u64 seqno, enum dccp_ackvec_states state)
-{
-	u32 num_cells = num_packets;
-
-	if (num_packets > DCCPAV_BURST_THRESH) {
-		u32 lost_packets = num_packets - 1;
-
-		DCCP_WARN("Warning: large burst loss (%u)\n", lost_packets);
-		/*
-		 * We received 1 packet and have a loss of size "num_packets-1"
-		 * which we squeeze into num_cells-1 rather than reserving an
-		 * entire byte for each lost packet.
-		 * The reason is that the vector grows in O(burst_length); when
-		 * it grows too large there will no room left for the payload.
-		 * This is a trade-off: if a few packets out of the burst show
-		 * up later, their state will not be changed; it is simply too
-		 * costly to reshuffle/reallocate/copy the buffer each time.
-		 * Should such problems persist, we will need to switch to a
-		 * different underlying data structure.
-		 */
-		for (num_packets = num_cells = 1; lost_packets; ++num_cells) {
-			u8 len = min_t(u32, lost_packets, DCCPAV_MAX_RUNLEN);
-
-			av->av_buf_head = __ackvec_idx_sub(av->av_buf_head, 1);
-			av->av_buf[av->av_buf_head] = DCCPAV_NOT_RECEIVED | len;
-
-			lost_packets -= len;
-		}
-	}
-
-	if (num_cells + dccp_ackvec_buflen(av) >= DCCPAV_MAX_ACKVEC_LEN) {
-		DCCP_CRIT("Ack Vector buffer overflow: dropping old entries");
-		av->av_overflow = true;
-	}
-
-	av->av_buf_head = __ackvec_idx_sub(av->av_buf_head, num_packets);
-	if (av->av_overflow)
-		av->av_buf_tail = av->av_buf_head;
-
-	av->av_buf[av->av_buf_head] = state;
-	av->av_buf_ackno	    = seqno;
-
-	if (num_packets > 1)
-		dccp_ackvec_reserve_seats(av, num_packets - 1);
-}
-
-/**
- * dccp_ackvec_input  -  Register incoming packet in the buffer
- * @av: Ack Vector to register packet to
- * @skb: Packet to register
- */
-void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb)
-{
-	u64 seqno = DCCP_SKB_CB(skb)->dccpd_seq;
-	enum dccp_ackvec_states state = DCCPAV_RECEIVED;
-
-	if (dccp_ackvec_is_empty(av)) {
-		dccp_ackvec_add_new(av, 1, seqno, state);
-		av->av_tail_ackno = seqno;
-
-	} else {
-		s64 num_packets = dccp_delta_seqno(av->av_buf_ackno, seqno);
-		u8 *current_head = av->av_buf + av->av_buf_head;
-
-		if (num_packets == 1 &&
-		    dccp_ackvec_state(current_head) == state &&
-		    dccp_ackvec_runlen(current_head) < DCCPAV_MAX_RUNLEN) {
-
-			*current_head   += 1;
-			av->av_buf_ackno = seqno;
-
-		} else if (num_packets > 0) {
-			dccp_ackvec_add_new(av, num_packets, seqno, state);
-		} else {
-			dccp_ackvec_update_old(av, num_packets, seqno, state);
-		}
-	}
-}
-
-/**
- * dccp_ackvec_clear_state  -  Perform house-keeping / garbage-collection
- * @av: Ack Vector record to clean
- * @ackno: last Ack Vector which has been acknowledged
- *
- * This routine is called when the peer acknowledges the receipt of Ack Vectors
- * up to and including @ackno. While based on section A.3 of RFC 4340, here
- * are additional precautions to prevent corrupted buffer state. In particular,
- * we use tail_ackno to identify outdated records; it always marks the earliest
- * packet of group (2) in 11.4.2.
- */
-void dccp_ackvec_clear_state(struct dccp_ackvec *av, const u64 ackno)
-{
-	struct dccp_ackvec_record *avr, *next;
-	u8 runlen_now, eff_runlen;
-	s64 delta;
-
-	avr = dccp_ackvec_lookup(&av->av_records, ackno);
-	if (avr == NULL)
-		return;
-	/*
-	 * Deal with outdated acknowledgments: this arises when e.g. there are
-	 * several old records and the acks from the peer come in slowly. In
-	 * that case we may still have records that pre-date tail_ackno.
-	 */
-	delta = dccp_delta_seqno(av->av_tail_ackno, avr->avr_ack_ackno);
-	if (delta < 0)
-		goto free_records;
-	/*
-	 * Deal with overlapping Ack Vectors: don't subtract more than the
-	 * number of packets between tail_ackno and ack_ackno.
-	 */
-	eff_runlen = delta < avr->avr_ack_runlen ? delta : avr->avr_ack_runlen;
-
-	runlen_now = dccp_ackvec_runlen(av->av_buf + avr->avr_ack_ptr);
-	/*
-	 * The run length of Ack Vector cells does not decrease over time. If
-	 * the run length is the same as at the time the Ack Vector was sent, we
-	 * free the ack_ptr cell. That cell can however not be freed if the run
-	 * length has increased: in this case we need to move the tail pointer
-	 * backwards (towards higher indices), to its next-oldest neighbour.
-	 */
-	if (runlen_now > eff_runlen) {
-
-		av->av_buf[avr->avr_ack_ptr] -= eff_runlen + 1;
-		av->av_buf_tail = __ackvec_idx_add(avr->avr_ack_ptr, 1);
-
-		/* This move may not have cleared the overflow flag. */
-		if (av->av_overflow)
-			av->av_overflow = (av->av_buf_head == av->av_buf_tail);
-	} else {
-		av->av_buf_tail	= avr->avr_ack_ptr;
-		/*
-		 * We have made sure that avr points to a valid cell within the
-		 * buffer. This cell is either older than head, or equals head
-		 * (empty buffer): in both cases we no longer have any overflow.
-		 */
-		av->av_overflow	= 0;
-	}
-
-	/*
-	 * The peer has acknowledged up to and including ack_ackno. Hence the
-	 * first packet in group (2) of 11.4.2 is the successor of ack_ackno.
-	 */
-	av->av_tail_ackno = ADD48(avr->avr_ack_ackno, 1);
-
-free_records:
-	list_for_each_entry_safe_from(avr, next, &av->av_records, avr_node) {
-		list_del(&avr->avr_node);
-		kmem_cache_free(dccp_ackvec_record_slab, avr);
-	}
-}
-
-/*
- *	Routines to keep track of Ack Vectors received in an skb
- */
-int dccp_ackvec_parsed_add(struct list_head *head, u8 *vec, u8 len, u8 nonce)
-{
-	struct dccp_ackvec_parsed *new = kmalloc(sizeof(*new), GFP_ATOMIC);
-
-	if (new == NULL)
-		return -ENOBUFS;
-	new->vec   = vec;
-	new->len   = len;
-	new->nonce = nonce;
-
-	list_add_tail(&new->node, head);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(dccp_ackvec_parsed_add);
-
-void dccp_ackvec_parsed_cleanup(struct list_head *parsed_chunks)
-{
-	struct dccp_ackvec_parsed *cur, *next;
-
-	list_for_each_entry_safe(cur, next, parsed_chunks, node)
-		kfree(cur);
-	INIT_LIST_HEAD(parsed_chunks);
-}
-EXPORT_SYMBOL_GPL(dccp_ackvec_parsed_cleanup);
-
-int __init dccp_ackvec_init(void)
-{
-	dccp_ackvec_slab = KMEM_CACHE(dccp_ackvec, SLAB_HWCACHE_ALIGN);
-	if (dccp_ackvec_slab == NULL)
-		goto out_err;
-
-	dccp_ackvec_record_slab = KMEM_CACHE(dccp_ackvec_record, SLAB_HWCACHE_ALIGN);
-	if (dccp_ackvec_record_slab == NULL)
-		goto out_destroy_slab;
-
-	return 0;
-
-out_destroy_slab:
-	kmem_cache_destroy(dccp_ackvec_slab);
-	dccp_ackvec_slab = NULL;
-out_err:
-	DCCP_CRIT("Unable to create Ack Vector slab cache");
-	return -ENOBUFS;
-}
-
-void dccp_ackvec_exit(void)
-{
-	kmem_cache_destroy(dccp_ackvec_slab);
-	dccp_ackvec_slab = NULL;
-	kmem_cache_destroy(dccp_ackvec_record_slab);
-	dccp_ackvec_record_slab = NULL;
-}
diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h
deleted file mode 100644
index d2c4220fb377..000000000000
--- a/net/dccp/ackvec.h
+++ /dev/null
@@ -1,136 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-#ifndef _ACKVEC_H
-#define _ACKVEC_H
-/*
- *  net/dccp/ackvec.h
- *
- *  An implementation of Ack Vectors for the DCCP protocol
- *  Copyright (c) 2007 University of Aberdeen, Scotland, UK
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@mandriva.com>
- */
-
-#include <linux/dccp.h>
-#include <linux/compiler.h>
-#include <linux/list.h>
-#include <linux/types.h>
-
-/*
- * Ack Vector buffer space is static, in multiples of %DCCP_SINGLE_OPT_MAXLEN,
- * the maximum size of a single Ack Vector. Setting %DCCPAV_NUM_ACKVECS to 1
- * will be sufficient for most cases of low Ack Ratios, using a value of 2 gives
- * more headroom if Ack Ratio is higher or when the sender acknowledges slowly.
- * The maximum value is bounded by the u16 types for indices and functions.
- */
-#define DCCPAV_NUM_ACKVECS	2
-#define DCCPAV_MAX_ACKVEC_LEN	(DCCP_SINGLE_OPT_MAXLEN * DCCPAV_NUM_ACKVECS)
-
-/* Estimated minimum average Ack Vector length - used for updating MPS */
-#define DCCPAV_MIN_OPTLEN	16
-
-/* Threshold for coping with large bursts of losses */
-#define DCCPAV_BURST_THRESH	(DCCPAV_MAX_ACKVEC_LEN / 8)
-
-enum dccp_ackvec_states {
-	DCCPAV_RECEIVED =	0x00,
-	DCCPAV_ECN_MARKED =	0x40,
-	DCCPAV_RESERVED =	0x80,
-	DCCPAV_NOT_RECEIVED =	0xC0
-};
-#define DCCPAV_MAX_RUNLEN	0x3F
-
-static inline u8 dccp_ackvec_runlen(const u8 *cell)
-{
-	return *cell & DCCPAV_MAX_RUNLEN;
-}
-
-static inline u8 dccp_ackvec_state(const u8 *cell)
-{
-	return *cell & ~DCCPAV_MAX_RUNLEN;
-}
-
-/**
- * struct dccp_ackvec - Ack Vector main data structure
- *
- * This implements a fixed-size circular buffer within an array and is largely
- * based on Appendix A of RFC 4340.
- *
- * @av_buf:	   circular buffer storage area
- * @av_buf_head:   head index; begin of live portion in @av_buf
- * @av_buf_tail:   tail index; first index _after_ the live portion in @av_buf
- * @av_buf_ackno:  highest seqno of acknowledgeable packet recorded in @av_buf
- * @av_tail_ackno: lowest  seqno of acknowledgeable packet recorded in @av_buf
- * @av_buf_nonce:  ECN nonce sums, each covering subsequent segments of up to
- *		   %DCCP_SINGLE_OPT_MAXLEN cells in the live portion of @av_buf
- * @av_overflow:   if 1 then buf_head == buf_tail indicates buffer wraparound
- * @av_records:	   list of %dccp_ackvec_record (Ack Vectors sent previously)
- */
-struct dccp_ackvec {
-	u8			av_buf[DCCPAV_MAX_ACKVEC_LEN];
-	u16			av_buf_head;
-	u16			av_buf_tail;
-	u64			av_buf_ackno:48;
-	u64			av_tail_ackno:48;
-	bool			av_buf_nonce[DCCPAV_NUM_ACKVECS];
-	u8			av_overflow:1;
-	struct list_head	av_records;
-};
-
-/**
- * struct dccp_ackvec_record - Records information about sent Ack Vectors
- *
- * These list entries define the additional information which the HC-Receiver
- * keeps about recently-sent Ack Vectors; again refer to RFC 4340, Appendix A.
- *
- * @avr_node:	    the list node in @av_records
- * @avr_ack_seqno:  sequence number of the packet the Ack Vector was sent on
- * @avr_ack_ackno:  the Ack number that this record/Ack Vector refers to
- * @avr_ack_ptr:    pointer into @av_buf where this record starts
- * @avr_ack_runlen: run length of @avr_ack_ptr at the time of sending
- * @avr_ack_nonce:  the sum of @av_buf_nonce's at the time this record was sent
- *
- * The list as a whole is sorted in descending order by @avr_ack_seqno.
- */
-struct dccp_ackvec_record {
-	struct list_head avr_node;
-	u64		 avr_ack_seqno:48;
-	u64		 avr_ack_ackno:48;
-	u16		 avr_ack_ptr;
-	u8		 avr_ack_runlen;
-	u8		 avr_ack_nonce:1;
-};
-
-int dccp_ackvec_init(void);
-void dccp_ackvec_exit(void);
-
-struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority);
-void dccp_ackvec_free(struct dccp_ackvec *av);
-
-void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb);
-int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seq, u8 sum);
-void dccp_ackvec_clear_state(struct dccp_ackvec *av, const u64 ackno);
-u16 dccp_ackvec_buflen(const struct dccp_ackvec *av);
-
-static inline bool dccp_ackvec_is_empty(const struct dccp_ackvec *av)
-{
-	return av->av_overflow == 0 && av->av_buf_head == av->av_buf_tail;
-}
-
-/**
- * struct dccp_ackvec_parsed  -  Record offsets of Ack Vectors in skb
- * @vec:	start of vector (offset into skb)
- * @len:	length of @vec
- * @nonce:	whether @vec had an ECN nonce of 0 or 1
- * @node:	FIFO - arranged in descending order of ack_ackno
- *
- * This structure is used by CCIDs to access Ack Vectors in a received skb.
- */
-struct dccp_ackvec_parsed {
-	u8		 *vec,
-			 len,
-			 nonce:1;
-	struct list_head node;
-};
-
-int dccp_ackvec_parsed_add(struct list_head *head, u8 *vec, u8 len, u8 nonce);
-void dccp_ackvec_parsed_cleanup(struct list_head *parsed_chunks);
-#endif /* _ACKVEC_H */
diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c
deleted file mode 100644
index 6beac5d348e2..000000000000
--- a/net/dccp/ccid.c
+++ /dev/null
@@ -1,219 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  net/dccp/ccid.c
- *
- *  An implementation of the DCCP protocol
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- *
- *  CCID infrastructure
- */
-
-#include <linux/slab.h>
-
-#include "ccid.h"
-#include "ccids/lib/tfrc.h"
-
-static struct ccid_operations *ccids[] = {
-	&ccid2_ops,
-#ifdef CONFIG_IP_DCCP_CCID3
-	&ccid3_ops,
-#endif
-};
-
-static struct ccid_operations *ccid_by_number(const u8 id)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(ccids); i++)
-		if (ccids[i]->ccid_id == id)
-			return ccids[i];
-	return NULL;
-}
-
-/* check that up to @array_len members in @ccid_array are supported */
-bool ccid_support_check(u8 const *ccid_array, u8 array_len)
-{
-	while (array_len > 0)
-		if (ccid_by_number(ccid_array[--array_len]) == NULL)
-			return false;
-	return true;
-}
-
-/**
- * ccid_get_builtin_ccids  -  Populate a list of built-in CCIDs
- * @ccid_array: pointer to copy into
- * @array_len: value to return length into
- *
- * This function allocates memory - caller must see that it is freed after use.
- */
-int ccid_get_builtin_ccids(u8 **ccid_array, u8 *array_len)
-{
-	*ccid_array = kmalloc(ARRAY_SIZE(ccids), gfp_any());
-	if (*ccid_array == NULL)
-		return -ENOBUFS;
-
-	for (*array_len = 0; *array_len < ARRAY_SIZE(ccids); *array_len += 1)
-		(*ccid_array)[*array_len] = ccids[*array_len]->ccid_id;
-	return 0;
-}
-
-int ccid_getsockopt_builtin_ccids(struct sock *sk, int len,
-				  char __user *optval, int __user *optlen)
-{
-	u8 *ccid_array, array_len;
-	int err = 0;
-
-	if (ccid_get_builtin_ccids(&ccid_array, &array_len))
-		return -ENOBUFS;
-
-	if (put_user(array_len, optlen))
-		err = -EFAULT;
-	else if (len > 0 && copy_to_user(optval, ccid_array,
-					 len > array_len ? array_len : len))
-		err = -EFAULT;
-
-	kfree(ccid_array);
-	return err;
-}
-
-static __printf(3, 4) struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...)
-{
-	struct kmem_cache *slab;
-	va_list args;
-
-	va_start(args, fmt);
-	vsnprintf(slab_name_fmt, CCID_SLAB_NAME_LENGTH, fmt, args);
-	va_end(args);
-
-	slab = kmem_cache_create(slab_name_fmt, sizeof(struct ccid) + obj_size, 0,
-				 SLAB_HWCACHE_ALIGN, NULL);
-	return slab;
-}
-
-static void ccid_kmem_cache_destroy(struct kmem_cache *slab)
-{
-	kmem_cache_destroy(slab);
-}
-
-static int __init ccid_activate(struct ccid_operations *ccid_ops)
-{
-	int err = -ENOBUFS;
-
-	ccid_ops->ccid_hc_rx_slab =
-			ccid_kmem_cache_create(ccid_ops->ccid_hc_rx_obj_size,
-					       ccid_ops->ccid_hc_rx_slab_name,
-					       "ccid%u_hc_rx_sock",
-					       ccid_ops->ccid_id);
-	if (ccid_ops->ccid_hc_rx_slab == NULL)
-		goto out;
-
-	ccid_ops->ccid_hc_tx_slab =
-			ccid_kmem_cache_create(ccid_ops->ccid_hc_tx_obj_size,
-					       ccid_ops->ccid_hc_tx_slab_name,
-					       "ccid%u_hc_tx_sock",
-					       ccid_ops->ccid_id);
-	if (ccid_ops->ccid_hc_tx_slab == NULL)
-		goto out_free_rx_slab;
-
-	pr_info("DCCP: Activated CCID %d (%s)\n",
-		ccid_ops->ccid_id, ccid_ops->ccid_name);
-	err = 0;
-out:
-	return err;
-out_free_rx_slab:
-	ccid_kmem_cache_destroy(ccid_ops->ccid_hc_rx_slab);
-	ccid_ops->ccid_hc_rx_slab = NULL;
-	goto out;
-}
-
-static void ccid_deactivate(struct ccid_operations *ccid_ops)
-{
-	ccid_kmem_cache_destroy(ccid_ops->ccid_hc_tx_slab);
-	ccid_ops->ccid_hc_tx_slab = NULL;
-	ccid_kmem_cache_destroy(ccid_ops->ccid_hc_rx_slab);
-	ccid_ops->ccid_hc_rx_slab = NULL;
-
-	pr_info("DCCP: Deactivated CCID %d (%s)\n",
-		ccid_ops->ccid_id, ccid_ops->ccid_name);
-}
-
-struct ccid *ccid_new(const u8 id, struct sock *sk, bool rx)
-{
-	struct ccid_operations *ccid_ops = ccid_by_number(id);
-	struct ccid *ccid = NULL;
-
-	if (ccid_ops == NULL)
-		goto out;
-
-	ccid = kmem_cache_alloc(rx ? ccid_ops->ccid_hc_rx_slab :
-				     ccid_ops->ccid_hc_tx_slab, gfp_any());
-	if (ccid == NULL)
-		goto out;
-	ccid->ccid_ops = ccid_ops;
-	if (rx) {
-		memset(ccid + 1, 0, ccid_ops->ccid_hc_rx_obj_size);
-		if (ccid->ccid_ops->ccid_hc_rx_init != NULL &&
-		    ccid->ccid_ops->ccid_hc_rx_init(ccid, sk) != 0)
-			goto out_free_ccid;
-	} else {
-		memset(ccid + 1, 0, ccid_ops->ccid_hc_tx_obj_size);
-		if (ccid->ccid_ops->ccid_hc_tx_init != NULL &&
-		    ccid->ccid_ops->ccid_hc_tx_init(ccid, sk) != 0)
-			goto out_free_ccid;
-	}
-out:
-	return ccid;
-out_free_ccid:
-	kmem_cache_free(rx ? ccid_ops->ccid_hc_rx_slab :
-			ccid_ops->ccid_hc_tx_slab, ccid);
-	ccid = NULL;
-	goto out;
-}
-
-void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk)
-{
-	if (ccid != NULL) {
-		if (ccid->ccid_ops->ccid_hc_rx_exit != NULL)
-			ccid->ccid_ops->ccid_hc_rx_exit(sk);
-		kmem_cache_free(ccid->ccid_ops->ccid_hc_rx_slab, ccid);
-	}
-}
-
-void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk)
-{
-	if (ccid != NULL) {
-		if (ccid->ccid_ops->ccid_hc_tx_exit != NULL)
-			ccid->ccid_ops->ccid_hc_tx_exit(sk);
-		kmem_cache_free(ccid->ccid_ops->ccid_hc_tx_slab, ccid);
-	}
-}
-
-int __init ccid_initialize_builtins(void)
-{
-	int i, err = tfrc_lib_init();
-
-	if (err)
-		return err;
-
-	for (i = 0; i < ARRAY_SIZE(ccids); i++) {
-		err = ccid_activate(ccids[i]);
-		if (err)
-			goto unwind_registrations;
-	}
-	return 0;
-
-unwind_registrations:
-	while(--i >= 0)
-		ccid_deactivate(ccids[i]);
-	tfrc_lib_exit();
-	return err;
-}
-
-void ccid_cleanup_builtins(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(ccids); i++)
-		ccid_deactivate(ccids[i]);
-	tfrc_lib_exit();
-}
diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h
deleted file mode 100644
index 105f3734dadb..000000000000
--- a/net/dccp/ccid.h
+++ /dev/null
@@ -1,262 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-#ifndef _CCID_H
-#define _CCID_H
-/*
- *  net/dccp/ccid.h
- *
- *  An implementation of the DCCP protocol
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- *
- *  CCID infrastructure
- */
-
-#include <net/sock.h>
-#include <linux/compiler.h>
-#include <linux/dccp.h>
-#include <linux/list.h>
-#include <linux/module.h>
-
-/* maximum value for a CCID (RFC 4340, 19.5) */
-#define CCID_MAX		255
-#define CCID_SLAB_NAME_LENGTH	32
-
-struct tcp_info;
-
-/**
- *  struct ccid_operations  -  Interface to Congestion-Control Infrastructure
- *
- *  @ccid_id: numerical CCID ID (up to %CCID_MAX, cf. table 5 in RFC 4340, 10.)
- *  @ccid_ccmps: the CCMPS including network/transport headers (0 when disabled)
- *  @ccid_name: alphabetical identifier string for @ccid_id
- *  @ccid_hc_{r,t}x_slab: memory pool for the receiver/sender half-connection
- *  @ccid_hc_{r,t}x_obj_size: size of the receiver/sender half-connection socket
- *
- *  @ccid_hc_{r,t}x_init: CCID-specific initialisation routine (before startup)
- *  @ccid_hc_{r,t}x_exit: CCID-specific cleanup routine (before destruction)
- *  @ccid_hc_rx_packet_recv: implements the HC-receiver side
- *  @ccid_hc_{r,t}x_parse_options: parsing routine for CCID/HC-specific options
- *  @ccid_hc_{r,t}x_insert_options: insert routine for CCID/HC-specific options
- *  @ccid_hc_tx_packet_recv: implements feedback processing for the HC-sender
- *  @ccid_hc_tx_send_packet: implements the sending part of the HC-sender
- *  @ccid_hc_tx_packet_sent: does accounting for packets in flight by HC-sender
- *  @ccid_hc_{r,t}x_get_info: INET_DIAG information for HC-receiver/sender
- *  @ccid_hc_{r,t}x_getsockopt: socket options specific to HC-receiver/sender
- */
-struct ccid_operations {
-	unsigned char		ccid_id;
-	__u32			ccid_ccmps;
-	const char		*ccid_name;
-	struct kmem_cache	*ccid_hc_rx_slab,
-				*ccid_hc_tx_slab;
-	char			ccid_hc_rx_slab_name[CCID_SLAB_NAME_LENGTH];
-	char			ccid_hc_tx_slab_name[CCID_SLAB_NAME_LENGTH];
-	__u32			ccid_hc_rx_obj_size,
-				ccid_hc_tx_obj_size;
-	/* Interface Routines */
-	int		(*ccid_hc_rx_init)(struct ccid *ccid, struct sock *sk);
-	int		(*ccid_hc_tx_init)(struct ccid *ccid, struct sock *sk);
-	void		(*ccid_hc_rx_exit)(struct sock *sk);
-	void		(*ccid_hc_tx_exit)(struct sock *sk);
-	void		(*ccid_hc_rx_packet_recv)(struct sock *sk,
-						  struct sk_buff *skb);
-	int		(*ccid_hc_rx_parse_options)(struct sock *sk, u8 pkt,
-						    u8 opt, u8 *val, u8 len);
-	int		(*ccid_hc_rx_insert_options)(struct sock *sk,
-						     struct sk_buff *skb);
-	void		(*ccid_hc_tx_packet_recv)(struct sock *sk,
-						  struct sk_buff *skb);
-	int		(*ccid_hc_tx_parse_options)(struct sock *sk, u8 pkt,
-						    u8 opt, u8 *val, u8 len);
-	int		(*ccid_hc_tx_send_packet)(struct sock *sk,
-						  struct sk_buff *skb);
-	void		(*ccid_hc_tx_packet_sent)(struct sock *sk,
-						  unsigned int len);
-	void		(*ccid_hc_rx_get_info)(struct sock *sk,
-					       struct tcp_info *info);
-	void		(*ccid_hc_tx_get_info)(struct sock *sk,
-					       struct tcp_info *info);
-	int		(*ccid_hc_rx_getsockopt)(struct sock *sk,
-						 const int optname, int len,
-						 u32 __user *optval,
-						 int __user *optlen);
-	int		(*ccid_hc_tx_getsockopt)(struct sock *sk,
-						 const int optname, int len,
-						 u32 __user *optval,
-						 int __user *optlen);
-};
-
-extern struct ccid_operations ccid2_ops;
-#ifdef CONFIG_IP_DCCP_CCID3
-extern struct ccid_operations ccid3_ops;
-#endif
-
-int ccid_initialize_builtins(void);
-void ccid_cleanup_builtins(void);
-
-struct ccid {
-	struct ccid_operations *ccid_ops;
-	char		       ccid_priv[];
-};
-
-static inline void *ccid_priv(const struct ccid *ccid)
-{
-	return (void *)ccid->ccid_priv;
-}
-
-bool ccid_support_check(u8 const *ccid_array, u8 array_len);
-int ccid_get_builtin_ccids(u8 **ccid_array, u8 *array_len);
-int ccid_getsockopt_builtin_ccids(struct sock *sk, int len,
-				  char __user *, int __user *);
-
-struct ccid *ccid_new(const u8 id, struct sock *sk, bool rx);
-
-static inline int ccid_get_current_rx_ccid(struct dccp_sock *dp)
-{
-	struct ccid *ccid = dp->dccps_hc_rx_ccid;
-
-	if (ccid == NULL || ccid->ccid_ops == NULL)
-		return -1;
-	return ccid->ccid_ops->ccid_id;
-}
-
-static inline int ccid_get_current_tx_ccid(struct dccp_sock *dp)
-{
-	struct ccid *ccid = dp->dccps_hc_tx_ccid;
-
-	if (ccid == NULL || ccid->ccid_ops == NULL)
-		return -1;
-	return ccid->ccid_ops->ccid_id;
-}
-
-void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk);
-void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk);
-
-/*
- * Congestion control of queued data packets via CCID decision.
- *
- * The TX CCID performs its congestion-control by indicating whether and when a
- * queued packet may be sent, using the return code of ccid_hc_tx_send_packet().
- * The following modes are supported via the symbolic constants below:
- * - timer-based pacing    (CCID returns a delay value in milliseconds);
- * - autonomous dequeueing (CCID internally schedules dccps_xmitlet).
- */
-
-enum ccid_dequeueing_decision {
-	CCID_PACKET_SEND_AT_ONCE =	 0x00000,  /* "green light": no delay */
-	CCID_PACKET_DELAY_MAX =		 0x0FFFF,  /* maximum delay in msecs  */
-	CCID_PACKET_DELAY =		 0x10000,  /* CCID msec-delay mode */
-	CCID_PACKET_WILL_DEQUEUE_LATER = 0x20000,  /* CCID autonomous mode */
-	CCID_PACKET_ERR =		 0xF0000,  /* error condition */
-};
-
-static inline int ccid_packet_dequeue_eval(const int return_code)
-{
-	if (return_code < 0)
-		return CCID_PACKET_ERR;
-	if (return_code == 0)
-		return CCID_PACKET_SEND_AT_ONCE;
-	if (return_code <= CCID_PACKET_DELAY_MAX)
-		return CCID_PACKET_DELAY;
-	return return_code;
-}
-
-static inline int ccid_hc_tx_send_packet(struct ccid *ccid, struct sock *sk,
-					 struct sk_buff *skb)
-{
-	if (ccid->ccid_ops->ccid_hc_tx_send_packet != NULL)
-		return ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb);
-	return CCID_PACKET_SEND_AT_ONCE;
-}
-
-static inline void ccid_hc_tx_packet_sent(struct ccid *ccid, struct sock *sk,
-					  unsigned int len)
-{
-	if (ccid->ccid_ops->ccid_hc_tx_packet_sent != NULL)
-		ccid->ccid_ops->ccid_hc_tx_packet_sent(sk, len);
-}
-
-static inline void ccid_hc_rx_packet_recv(struct ccid *ccid, struct sock *sk,
-					  struct sk_buff *skb)
-{
-	if (ccid->ccid_ops->ccid_hc_rx_packet_recv != NULL)
-		ccid->ccid_ops->ccid_hc_rx_packet_recv(sk, skb);
-}
-
-static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk,
-					  struct sk_buff *skb)
-{
-	if (ccid->ccid_ops->ccid_hc_tx_packet_recv != NULL)
-		ccid->ccid_ops->ccid_hc_tx_packet_recv(sk, skb);
-}
-
-/**
- * ccid_hc_tx_parse_options  -  Parse CCID-specific options sent by the receiver
- * @pkt: type of packet that @opt appears on (RFC 4340, 5.1)
- * @opt: the CCID-specific option type (RFC 4340, 5.8 and 10.3)
- * @val: value of @opt
- * @len: length of @val in bytes
- */
-static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk,
-					   u8 pkt, u8 opt, u8 *val, u8 len)
-{
-	if (!ccid || !ccid->ccid_ops->ccid_hc_tx_parse_options)
-		return 0;
-	return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len);
-}
-
-/**
- * ccid_hc_rx_parse_options  -  Parse CCID-specific options sent by the sender
- * Arguments are analogous to ccid_hc_tx_parse_options()
- */
-static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk,
-					   u8 pkt, u8 opt, u8 *val, u8 len)
-{
-	if (!ccid || !ccid->ccid_ops->ccid_hc_rx_parse_options)
-		return 0;
-	return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len);
-}
-
-static inline int ccid_hc_rx_insert_options(struct ccid *ccid, struct sock *sk,
-					    struct sk_buff *skb)
-{
-	if (ccid->ccid_ops->ccid_hc_rx_insert_options != NULL)
-		return ccid->ccid_ops->ccid_hc_rx_insert_options(sk, skb);
-	return 0;
-}
-
-static inline void ccid_hc_rx_get_info(struct ccid *ccid, struct sock *sk,
-				       struct tcp_info *info)
-{
-	if (ccid->ccid_ops->ccid_hc_rx_get_info != NULL)
-		ccid->ccid_ops->ccid_hc_rx_get_info(sk, info);
-}
-
-static inline void ccid_hc_tx_get_info(struct ccid *ccid, struct sock *sk,
-				       struct tcp_info *info)
-{
-	if (ccid->ccid_ops->ccid_hc_tx_get_info != NULL)
-		ccid->ccid_ops->ccid_hc_tx_get_info(sk, info);
-}
-
-static inline int ccid_hc_rx_getsockopt(struct ccid *ccid, struct sock *sk,
-					const int optname, int len,
-					u32 __user *optval, int __user *optlen)
-{
-	int rc = -ENOPROTOOPT;
-	if (ccid != NULL && ccid->ccid_ops->ccid_hc_rx_getsockopt != NULL)
-		rc = ccid->ccid_ops->ccid_hc_rx_getsockopt(sk, optname, len,
-						 optval, optlen);
-	return rc;
-}
-
-static inline int ccid_hc_tx_getsockopt(struct ccid *ccid, struct sock *sk,
-					const int optname, int len,
-					u32 __user *optval, int __user *optlen)
-{
-	int rc = -ENOPROTOOPT;
-	if (ccid != NULL && ccid->ccid_ops->ccid_hc_tx_getsockopt != NULL)
-		rc = ccid->ccid_ops->ccid_hc_tx_getsockopt(sk, optname, len,
-						 optval, optlen);
-	return rc;
-}
-#endif /* _CCID_H */
diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig
deleted file mode 100644
index e3d388c33d25..000000000000
--- a/net/dccp/ccids/Kconfig
+++ /dev/null
@@ -1,55 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-menu "DCCP CCIDs Configuration"
-
-config IP_DCCP_CCID2_DEBUG
-	bool "CCID-2 debugging messages"
-	help
-	  Enable CCID-2 specific debugging messages.
-
-	  The debugging output can additionally be toggled by setting the
-	  ccid2_debug parameter to 0 or 1.
-
-	  If in doubt, say N.
-
-config IP_DCCP_CCID3
-	bool "CCID-3 (TCP-Friendly)"
-	default IP_DCCP = y || IP_DCCP = m
-	help
-	  CCID-3 denotes TCP-Friendly Rate Control (TFRC), an equation-based
-	  rate-controlled congestion control mechanism.  TFRC is designed to
-	  be reasonably fair when competing for bandwidth with TCP-like flows,
-	  where a flow is "reasonably fair" if its sending rate is generally
-	  within a factor of two of the sending rate of a TCP flow under the
-	  same conditions.  However, TFRC has a much lower variation of
-	  throughput over time compared with TCP, which makes CCID-3 more
-	  suitable than CCID-2 for applications such streaming media where a
-	  relatively smooth sending rate is of importance.
-
-	  CCID-3 is further described in RFC 4342,
-	  https://www.ietf.org/rfc/rfc4342.txt
-
-	  The TFRC congestion control algorithms were initially described in
-	  RFC 5348.
-
-	  This text was extracted from RFC 4340 (sec. 10.2),
-	  https://www.ietf.org/rfc/rfc4340.txt
-
-	  If in doubt, say N.
-
-config IP_DCCP_CCID3_DEBUG
-	bool "CCID-3 debugging messages"
-	depends on IP_DCCP_CCID3
-	help
-	  Enable CCID-3 specific debugging messages.
-
-	  The debugging output can additionally be toggled by setting the
-	  ccid3_debug parameter to 0 or 1.
-
-	  If in doubt, say N.
-
-config IP_DCCP_TFRC_LIB
-	def_bool y if IP_DCCP_CCID3
-
-config IP_DCCP_TFRC_DEBUG
-	def_bool y if IP_DCCP_CCID3_DEBUG
-endmenu
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
deleted file mode 100644
index d6b30700af67..000000000000
--- a/net/dccp/ccids/ccid2.c
+++ /dev/null
@@ -1,794 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  Copyright (c) 2005, 2006 Andrea Bittau <a.bittau@cs.ucl.ac.uk>
- *
- *  Changes to meet Linux coding standards, and DCCP infrastructure fixes.
- *
- *  Copyright (c) 2006 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-
-/*
- * This implementation should follow RFC 4341
- */
-#include <linux/slab.h>
-#include "../feat.h"
-#include "ccid2.h"
-
-
-#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
-static bool ccid2_debug;
-#define ccid2_pr_debug(format, a...)	DCCP_PR_DEBUG(ccid2_debug, format, ##a)
-#else
-#define ccid2_pr_debug(format, a...)
-#endif
-
-static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hc)
-{
-	struct ccid2_seq *seqp;
-	int i;
-
-	/* check if we have space to preserve the pointer to the buffer */
-	if (hc->tx_seqbufc >= (sizeof(hc->tx_seqbuf) /
-			       sizeof(struct ccid2_seq *)))
-		return -ENOMEM;
-
-	/* allocate buffer and initialize linked list */
-	seqp = kmalloc_array(CCID2_SEQBUF_LEN, sizeof(struct ccid2_seq),
-			     gfp_any());
-	if (seqp == NULL)
-		return -ENOMEM;
-
-	for (i = 0; i < (CCID2_SEQBUF_LEN - 1); i++) {
-		seqp[i].ccid2s_next = &seqp[i + 1];
-		seqp[i + 1].ccid2s_prev = &seqp[i];
-	}
-	seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = seqp;
-	seqp->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1];
-
-	/* This is the first allocation.  Initiate the head and tail.  */
-	if (hc->tx_seqbufc == 0)
-		hc->tx_seqh = hc->tx_seqt = seqp;
-	else {
-		/* link the existing list with the one we just created */
-		hc->tx_seqh->ccid2s_next = seqp;
-		seqp->ccid2s_prev = hc->tx_seqh;
-
-		hc->tx_seqt->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1];
-		seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = hc->tx_seqt;
-	}
-
-	/* store the original pointer to the buffer so we can free it */
-	hc->tx_seqbuf[hc->tx_seqbufc] = seqp;
-	hc->tx_seqbufc++;
-
-	return 0;
-}
-
-static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
-{
-	if (ccid2_cwnd_network_limited(ccid2_hc_tx_sk(sk)))
-		return CCID_PACKET_WILL_DEQUEUE_LATER;
-	return CCID_PACKET_SEND_AT_ONCE;
-}
-
-static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val)
-{
-	u32 max_ratio = DIV_ROUND_UP(ccid2_hc_tx_sk(sk)->tx_cwnd, 2);
-
-	/*
-	 * Ensure that Ack Ratio does not exceed ceil(cwnd/2), which is (2) from
-	 * RFC 4341, 6.1.2. We ignore the statement that Ack Ratio 2 is always
-	 * acceptable since this causes starvation/deadlock whenever cwnd < 2.
-	 * The same problem arises when Ack Ratio is 0 (ie. Ack Ratio disabled).
-	 */
-	if (val == 0 || val > max_ratio) {
-		DCCP_WARN("Limiting Ack Ratio (%u) to %u\n", val, max_ratio);
-		val = max_ratio;
-	}
-	dccp_feat_signal_nn_change(sk, DCCPF_ACK_RATIO,
-				   min_t(u32, val, DCCPF_ACK_RATIO_MAX));
-}
-
-static void ccid2_check_l_ack_ratio(struct sock *sk)
-{
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-
-	/*
-	 * After a loss, idle period, application limited period, or RTO we
-	 * need to check that the ack ratio is still less than the congestion
-	 * window. Otherwise, we will send an entire congestion window of
-	 * packets and got no response because we haven't sent ack ratio
-	 * packets yet.
-	 * If the ack ratio does need to be reduced, we reduce it to half of
-	 * the congestion window (or 1 if that's zero) instead of to the
-	 * congestion window. This prevents problems if one ack is lost.
-	 */
-	if (dccp_feat_nn_get(sk, DCCPF_ACK_RATIO) > hc->tx_cwnd)
-		ccid2_change_l_ack_ratio(sk, hc->tx_cwnd/2 ? : 1U);
-}
-
-static void ccid2_change_l_seq_window(struct sock *sk, u64 val)
-{
-	dccp_feat_signal_nn_change(sk, DCCPF_SEQUENCE_WINDOW,
-				   clamp_val(val, DCCPF_SEQ_WMIN,
-						  DCCPF_SEQ_WMAX));
-}
-
-static void dccp_tasklet_schedule(struct sock *sk)
-{
-	struct tasklet_struct *t = &dccp_sk(sk)->dccps_xmitlet;
-
-	if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
-		sock_hold(sk);
-		__tasklet_schedule(t);
-	}
-}
-
-static void ccid2_hc_tx_rto_expire(struct timer_list *t)
-{
-	struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer);
-	struct sock *sk = hc->sk;
-	const bool sender_was_blocked = ccid2_cwnd_network_limited(hc);
-
-	bh_lock_sock(sk);
-	if (sock_owned_by_user(sk)) {
-		sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + HZ / 5);
-		goto out;
-	}
-
-	ccid2_pr_debug("RTO_EXPIRE\n");
-
-	if (sk->sk_state == DCCP_CLOSED)
-		goto out;
-
-	/* back-off timer */
-	hc->tx_rto <<= 1;
-	if (hc->tx_rto > DCCP_RTO_MAX)
-		hc->tx_rto = DCCP_RTO_MAX;
-
-	/* adjust pipe, cwnd etc */
-	hc->tx_ssthresh = hc->tx_cwnd / 2;
-	if (hc->tx_ssthresh < 2)
-		hc->tx_ssthresh = 2;
-	hc->tx_cwnd	= 1;
-	hc->tx_pipe	= 0;
-
-	/* clear state about stuff we sent */
-	hc->tx_seqt = hc->tx_seqh;
-	hc->tx_packets_acked = 0;
-
-	/* clear ack ratio state. */
-	hc->tx_rpseq    = 0;
-	hc->tx_rpdupack = -1;
-	ccid2_change_l_ack_ratio(sk, 1);
-
-	/* if we were blocked before, we may now send cwnd=1 packet */
-	if (sender_was_blocked)
-		dccp_tasklet_schedule(sk);
-	/* restart backed-off timer */
-	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
-out:
-	bh_unlock_sock(sk);
-	sock_put(sk);
-}
-
-/*
- *	Congestion window validation (RFC 2861).
- */
-static bool ccid2_do_cwv = true;
-module_param(ccid2_do_cwv, bool, 0644);
-MODULE_PARM_DESC(ccid2_do_cwv, "Perform RFC2861 Congestion Window Validation");
-
-/**
- * ccid2_update_used_window  -  Track how much of cwnd is actually used
- * @hc: socket to update window
- * @new_wnd: new window values to add into the filter
- *
- * This is done in addition to CWV. The sender needs to have an idea of how many
- * packets may be in flight, to set the local Sequence Window value accordingly
- * (RFC 4340, 7.5.2). The CWV mechanism is exploited to keep track of the
- * maximum-used window. We use an EWMA low-pass filter to filter out noise.
- */
-static void ccid2_update_used_window(struct ccid2_hc_tx_sock *hc, u32 new_wnd)
-{
-	hc->tx_expected_wnd = (3 * hc->tx_expected_wnd + new_wnd) / 4;
-}
-
-/* This borrows the code of tcp_cwnd_application_limited() */
-static void ccid2_cwnd_application_limited(struct sock *sk, const u32 now)
-{
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-	/* don't reduce cwnd below the initial window (IW) */
-	u32 init_win = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache),
-	    win_used = max(hc->tx_cwnd_used, init_win);
-
-	if (win_used < hc->tx_cwnd) {
-		hc->tx_ssthresh = max(hc->tx_ssthresh,
-				     (hc->tx_cwnd >> 1) + (hc->tx_cwnd >> 2));
-		hc->tx_cwnd = (hc->tx_cwnd + win_used) >> 1;
-	}
-	hc->tx_cwnd_used  = 0;
-	hc->tx_cwnd_stamp = now;
-
-	ccid2_check_l_ack_ratio(sk);
-}
-
-/* This borrows the code of tcp_cwnd_restart() */
-static void ccid2_cwnd_restart(struct sock *sk, const u32 now)
-{
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-	u32 cwnd = hc->tx_cwnd, restart_cwnd,
-	    iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache);
-	s32 delta = now - hc->tx_lsndtime;
-
-	hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2));
-
-	/* don't reduce cwnd below the initial window (IW) */
-	restart_cwnd = min(cwnd, iwnd);
-
-	while ((delta -= hc->tx_rto) >= 0 && cwnd > restart_cwnd)
-		cwnd >>= 1;
-	hc->tx_cwnd = max(cwnd, restart_cwnd);
-	hc->tx_cwnd_stamp = now;
-	hc->tx_cwnd_used  = 0;
-
-	ccid2_check_l_ack_ratio(sk);
-}
-
-static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-	const u32 now = ccid2_jiffies32;
-	struct ccid2_seq *next;
-
-	/* slow-start after idle periods (RFC 2581, RFC 2861) */
-	if (ccid2_do_cwv && !hc->tx_pipe &&
-	    (s32)(now - hc->tx_lsndtime) >= hc->tx_rto)
-		ccid2_cwnd_restart(sk, now);
-
-	hc->tx_lsndtime = now;
-	hc->tx_pipe    += 1;
-
-	/* see whether cwnd was fully used (RFC 2861), update expected window */
-	if (ccid2_cwnd_network_limited(hc)) {
-		ccid2_update_used_window(hc, hc->tx_cwnd);
-		hc->tx_cwnd_used  = 0;
-		hc->tx_cwnd_stamp = now;
-	} else {
-		if (hc->tx_pipe > hc->tx_cwnd_used)
-			hc->tx_cwnd_used = hc->tx_pipe;
-
-		ccid2_update_used_window(hc, hc->tx_cwnd_used);
-
-		if (ccid2_do_cwv && (s32)(now - hc->tx_cwnd_stamp) >= hc->tx_rto)
-			ccid2_cwnd_application_limited(sk, now);
-	}
-
-	hc->tx_seqh->ccid2s_seq   = dp->dccps_gss;
-	hc->tx_seqh->ccid2s_acked = 0;
-	hc->tx_seqh->ccid2s_sent  = now;
-
-	next = hc->tx_seqh->ccid2s_next;
-	/* check if we need to alloc more space */
-	if (next == hc->tx_seqt) {
-		if (ccid2_hc_tx_alloc_seq(hc)) {
-			DCCP_CRIT("packet history - out of memory!");
-			/* FIXME: find a more graceful way to bail out */
-			return;
-		}
-		next = hc->tx_seqh->ccid2s_next;
-		BUG_ON(next == hc->tx_seqt);
-	}
-	hc->tx_seqh = next;
-
-	ccid2_pr_debug("cwnd=%d pipe=%d\n", hc->tx_cwnd, hc->tx_pipe);
-
-	/*
-	 * FIXME: The code below is broken and the variables have been removed
-	 * from the socket struct. The `ackloss' variable was always set to 0,
-	 * and with arsent there are several problems:
-	 *  (i) it doesn't just count the number of Acks, but all sent packets;
-	 *  (ii) it is expressed in # of packets, not # of windows, so the
-	 *  comparison below uses the wrong formula: Appendix A of RFC 4341
-	 *  comes up with the number K = cwnd / (R^2 - R) of consecutive windows
-	 *  of data with no lost or marked Ack packets. If arsent were the # of
-	 *  consecutive Acks received without loss, then Ack Ratio needs to be
-	 *  decreased by 1 when
-	 *	      arsent >=  K * cwnd / R  =  cwnd^2 / (R^3 - R^2)
-	 *  where cwnd / R is the number of Acks received per window of data
-	 *  (cf. RFC 4341, App. A). The problems are that
-	 *  - arsent counts other packets as well;
-	 *  - the comparison uses a formula different from RFC 4341;
-	 *  - computing a cubic/quadratic equation each time is too complicated.
-	 *  Hence a different algorithm is needed.
-	 */
-#if 0
-	/* Ack Ratio.  Need to maintain a concept of how many windows we sent */
-	hc->tx_arsent++;
-	/* We had an ack loss in this window... */
-	if (hc->tx_ackloss) {
-		if (hc->tx_arsent >= hc->tx_cwnd) {
-			hc->tx_arsent  = 0;
-			hc->tx_ackloss = 0;
-		}
-	} else {
-		/* No acks lost up to now... */
-		/* decrease ack ratio if enough packets were sent */
-		if (dp->dccps_l_ack_ratio > 1) {
-			/* XXX don't calculate denominator each time */
-			int denom = dp->dccps_l_ack_ratio * dp->dccps_l_ack_ratio -
-				    dp->dccps_l_ack_ratio;
-
-			denom = hc->tx_cwnd * hc->tx_cwnd / denom;
-
-			if (hc->tx_arsent >= denom) {
-				ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio - 1);
-				hc->tx_arsent = 0;
-			}
-		} else {
-			/* we can't increase ack ratio further [1] */
-			hc->tx_arsent = 0; /* or maybe set it to cwnd*/
-		}
-	}
-#endif
-
-	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
-
-#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
-	do {
-		struct ccid2_seq *seqp = hc->tx_seqt;
-
-		while (seqp != hc->tx_seqh) {
-			ccid2_pr_debug("out seq=%llu acked=%d time=%u\n",
-				       (unsigned long long)seqp->ccid2s_seq,
-				       seqp->ccid2s_acked, seqp->ccid2s_sent);
-			seqp = seqp->ccid2s_next;
-		}
-	} while (0);
-	ccid2_pr_debug("=========\n");
-#endif
-}
-
-/**
- * ccid2_rtt_estimator - Sample RTT and compute RTO using RFC2988 algorithm
- * @sk: socket to perform estimator on
- * @mrtt: measured RTT
- *
- * This code is almost identical with TCP's tcp_rtt_estimator(), since
- * - it has a higher sampling frequency (recommended by RFC 1323),
- * - the RTO does not collapse into RTT due to RTTVAR going towards zero,
- * - it is simple (cf. more complex proposals such as Eifel timer or research
- *   which suggests that the gain should be set according to window size),
- * - in tests it was found to work well with CCID2 [gerrit].
- */
-static void ccid2_rtt_estimator(struct sock *sk, const long mrtt)
-{
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-	long m = mrtt ? : 1;
-
-	if (hc->tx_srtt == 0) {
-		/* First measurement m */
-		hc->tx_srtt = m << 3;
-		hc->tx_mdev = m << 1;
-
-		hc->tx_mdev_max = max(hc->tx_mdev, tcp_rto_min(sk));
-		hc->tx_rttvar   = hc->tx_mdev_max;
-
-		hc->tx_rtt_seq  = dccp_sk(sk)->dccps_gss;
-	} else {
-		/* Update scaled SRTT as SRTT += 1/8 * (m - SRTT) */
-		m -= (hc->tx_srtt >> 3);
-		hc->tx_srtt += m;
-
-		/* Similarly, update scaled mdev with regard to |m| */
-		if (m < 0) {
-			m = -m;
-			m -= (hc->tx_mdev >> 2);
-			/*
-			 * This neutralises RTO increase when RTT < SRTT - mdev
-			 * (see P. Sarolahti, A. Kuznetsov,"Congestion Control
-			 * in Linux TCP", USENIX 2002, pp. 49-62).
-			 */
-			if (m > 0)
-				m >>= 3;
-		} else {
-			m -= (hc->tx_mdev >> 2);
-		}
-		hc->tx_mdev += m;
-
-		if (hc->tx_mdev > hc->tx_mdev_max) {
-			hc->tx_mdev_max = hc->tx_mdev;
-			if (hc->tx_mdev_max > hc->tx_rttvar)
-				hc->tx_rttvar = hc->tx_mdev_max;
-		}
-
-		/*
-		 * Decay RTTVAR at most once per flight, exploiting that
-		 *  1) pipe <= cwnd <= Sequence_Window = W  (RFC 4340, 7.5.2)
-		 *  2) AWL = GSS-W+1 <= GAR <= GSS          (RFC 4340, 7.5.1)
-		 * GAR is a useful bound for FlightSize = pipe.
-		 * AWL is probably too low here, as it over-estimates pipe.
-		 */
-		if (after48(dccp_sk(sk)->dccps_gar, hc->tx_rtt_seq)) {
-			if (hc->tx_mdev_max < hc->tx_rttvar)
-				hc->tx_rttvar -= (hc->tx_rttvar -
-						  hc->tx_mdev_max) >> 2;
-			hc->tx_rtt_seq  = dccp_sk(sk)->dccps_gss;
-			hc->tx_mdev_max = tcp_rto_min(sk);
-		}
-	}
-
-	/*
-	 * Set RTO from SRTT and RTTVAR
-	 * As in TCP, 4 * RTTVAR >= TCP_RTO_MIN, giving a minimum RTO of 200 ms.
-	 * This agrees with RFC 4341, 5:
-	 *	"Because DCCP does not retransmit data, DCCP does not require
-	 *	 TCP's recommended minimum timeout of one second".
-	 */
-	hc->tx_rto = (hc->tx_srtt >> 3) + hc->tx_rttvar;
-
-	if (hc->tx_rto > DCCP_RTO_MAX)
-		hc->tx_rto = DCCP_RTO_MAX;
-}
-
-static void ccid2_new_ack(struct sock *sk, struct ccid2_seq *seqp,
-			  unsigned int *maxincr)
-{
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-	struct dccp_sock *dp = dccp_sk(sk);
-	int r_seq_used = hc->tx_cwnd / dp->dccps_l_ack_ratio;
-
-	if (hc->tx_cwnd < dp->dccps_l_seq_win &&
-	    r_seq_used < dp->dccps_r_seq_win) {
-		if (hc->tx_cwnd < hc->tx_ssthresh) {
-			if (*maxincr > 0 && ++hc->tx_packets_acked >= 2) {
-				hc->tx_cwnd += 1;
-				*maxincr    -= 1;
-				hc->tx_packets_acked = 0;
-			}
-		} else if (++hc->tx_packets_acked >= hc->tx_cwnd) {
-			hc->tx_cwnd += 1;
-			hc->tx_packets_acked = 0;
-		}
-	}
-
-	/*
-	 * Adjust the local sequence window and the ack ratio to allow about
-	 * 5 times the number of packets in the network (RFC 4340 7.5.2)
-	 */
-	if (r_seq_used * CCID2_WIN_CHANGE_FACTOR >= dp->dccps_r_seq_win)
-		ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio * 2);
-	else if (r_seq_used * CCID2_WIN_CHANGE_FACTOR < dp->dccps_r_seq_win/2)
-		ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio / 2 ? : 1U);
-
-	if (hc->tx_cwnd * CCID2_WIN_CHANGE_FACTOR >= dp->dccps_l_seq_win)
-		ccid2_change_l_seq_window(sk, dp->dccps_l_seq_win * 2);
-	else if (hc->tx_cwnd * CCID2_WIN_CHANGE_FACTOR < dp->dccps_l_seq_win/2)
-		ccid2_change_l_seq_window(sk, dp->dccps_l_seq_win / 2);
-
-	/*
-	 * FIXME: RTT is sampled several times per acknowledgment (for each
-	 * entry in the Ack Vector), instead of once per Ack (as in TCP SACK).
-	 * This causes the RTT to be over-estimated, since the older entries
-	 * in the Ack Vector have earlier sending times.
-	 * The cleanest solution is to not use the ccid2s_sent field at all
-	 * and instead use DCCP timestamps: requires changes in other places.
-	 */
-	ccid2_rtt_estimator(sk, ccid2_jiffies32 - seqp->ccid2s_sent);
-}
-
-static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp)
-{
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-
-	if ((s32)(seqp->ccid2s_sent - hc->tx_last_cong) < 0) {
-		ccid2_pr_debug("Multiple losses in an RTT---treating as one\n");
-		return;
-	}
-
-	hc->tx_last_cong = ccid2_jiffies32;
-
-	hc->tx_cwnd      = hc->tx_cwnd / 2 ? : 1U;
-	hc->tx_ssthresh  = max(hc->tx_cwnd, 2U);
-
-	ccid2_check_l_ack_ratio(sk);
-}
-
-static int ccid2_hc_tx_parse_options(struct sock *sk, u8 packet_type,
-				     u8 option, u8 *optval, u8 optlen)
-{
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-
-	switch (option) {
-	case DCCPO_ACK_VECTOR_0:
-	case DCCPO_ACK_VECTOR_1:
-		return dccp_ackvec_parsed_add(&hc->tx_av_chunks, optval, optlen,
-					      option - DCCPO_ACK_VECTOR_0);
-	}
-	return 0;
-}
-
-static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-	const bool sender_was_blocked = ccid2_cwnd_network_limited(hc);
-	struct dccp_ackvec_parsed *avp;
-	u64 ackno, seqno;
-	struct ccid2_seq *seqp;
-	int done = 0;
-	unsigned int maxincr = 0;
-
-	/* check reverse path congestion */
-	seqno = DCCP_SKB_CB(skb)->dccpd_seq;
-
-	/* XXX this whole "algorithm" is broken.  Need to fix it to keep track
-	 * of the seqnos of the dupacks so that rpseq and rpdupack are correct
-	 * -sorbo.
-	 */
-	/* need to bootstrap */
-	if (hc->tx_rpdupack == -1) {
-		hc->tx_rpdupack = 0;
-		hc->tx_rpseq    = seqno;
-	} else {
-		/* check if packet is consecutive */
-		if (dccp_delta_seqno(hc->tx_rpseq, seqno) == 1)
-			hc->tx_rpseq = seqno;
-		/* it's a later packet */
-		else if (after48(seqno, hc->tx_rpseq)) {
-			hc->tx_rpdupack++;
-
-			/* check if we got enough dupacks */
-			if (hc->tx_rpdupack >= NUMDUPACK) {
-				hc->tx_rpdupack = -1; /* XXX lame */
-				hc->tx_rpseq    = 0;
-#ifdef __CCID2_COPES_GRACEFULLY_WITH_ACK_CONGESTION_CONTROL__
-				/*
-				 * FIXME: Ack Congestion Control is broken; in
-				 * the current state instabilities occurred with
-				 * Ack Ratios greater than 1; causing hang-ups
-				 * and long RTO timeouts. This needs to be fixed
-				 * before opening up dynamic changes. -- gerrit
-				 */
-				ccid2_change_l_ack_ratio(sk, 2 * dp->dccps_l_ack_ratio);
-#endif
-			}
-		}
-	}
-
-	/* check forward path congestion */
-	if (dccp_packet_without_ack(skb))
-		return;
-
-	/* still didn't send out new data packets */
-	if (hc->tx_seqh == hc->tx_seqt)
-		goto done;
-
-	ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
-	if (after48(ackno, hc->tx_high_ack))
-		hc->tx_high_ack = ackno;
-
-	seqp = hc->tx_seqt;
-	while (before48(seqp->ccid2s_seq, ackno)) {
-		seqp = seqp->ccid2s_next;
-		if (seqp == hc->tx_seqh) {
-			seqp = hc->tx_seqh->ccid2s_prev;
-			break;
-		}
-	}
-
-	/*
-	 * In slow-start, cwnd can increase up to a maximum of Ack Ratio/2
-	 * packets per acknowledgement. Rounding up avoids that cwnd is not
-	 * advanced when Ack Ratio is 1 and gives a slight edge otherwise.
-	 */
-	if (hc->tx_cwnd < hc->tx_ssthresh)
-		maxincr = DIV_ROUND_UP(dp->dccps_l_ack_ratio, 2);
-
-	/* go through all ack vectors */
-	list_for_each_entry(avp, &hc->tx_av_chunks, node) {
-		/* go through this ack vector */
-		for (; avp->len--; avp->vec++) {
-			u64 ackno_end_rl = SUB48(ackno,
-						 dccp_ackvec_runlen(avp->vec));
-
-			ccid2_pr_debug("ackvec %llu |%u,%u|\n",
-				       (unsigned long long)ackno,
-				       dccp_ackvec_state(avp->vec) >> 6,
-				       dccp_ackvec_runlen(avp->vec));
-			/* if the seqno we are analyzing is larger than the
-			 * current ackno, then move towards the tail of our
-			 * seqnos.
-			 */
-			while (after48(seqp->ccid2s_seq, ackno)) {
-				if (seqp == hc->tx_seqt) {
-					done = 1;
-					break;
-				}
-				seqp = seqp->ccid2s_prev;
-			}
-			if (done)
-				break;
-
-			/* check all seqnos in the range of the vector
-			 * run length
-			 */
-			while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) {
-				const u8 state = dccp_ackvec_state(avp->vec);
-
-				/* new packet received or marked */
-				if (state != DCCPAV_NOT_RECEIVED &&
-				    !seqp->ccid2s_acked) {
-					if (state == DCCPAV_ECN_MARKED)
-						ccid2_congestion_event(sk,
-								       seqp);
-					else
-						ccid2_new_ack(sk, seqp,
-							      &maxincr);
-
-					seqp->ccid2s_acked = 1;
-					ccid2_pr_debug("Got ack for %llu\n",
-						       (unsigned long long)seqp->ccid2s_seq);
-					hc->tx_pipe--;
-				}
-				if (seqp == hc->tx_seqt) {
-					done = 1;
-					break;
-				}
-				seqp = seqp->ccid2s_prev;
-			}
-			if (done)
-				break;
-
-			ackno = SUB48(ackno_end_rl, 1);
-		}
-		if (done)
-			break;
-	}
-
-	/* The state about what is acked should be correct now
-	 * Check for NUMDUPACK
-	 */
-	seqp = hc->tx_seqt;
-	while (before48(seqp->ccid2s_seq, hc->tx_high_ack)) {
-		seqp = seqp->ccid2s_next;
-		if (seqp == hc->tx_seqh) {
-			seqp = hc->tx_seqh->ccid2s_prev;
-			break;
-		}
-	}
-	done = 0;
-	while (1) {
-		if (seqp->ccid2s_acked) {
-			done++;
-			if (done == NUMDUPACK)
-				break;
-		}
-		if (seqp == hc->tx_seqt)
-			break;
-		seqp = seqp->ccid2s_prev;
-	}
-
-	/* If there are at least 3 acknowledgements, anything unacknowledged
-	 * below the last sequence number is considered lost
-	 */
-	if (done == NUMDUPACK) {
-		struct ccid2_seq *last_acked = seqp;
-
-		/* check for lost packets */
-		while (1) {
-			if (!seqp->ccid2s_acked) {
-				ccid2_pr_debug("Packet lost: %llu\n",
-					       (unsigned long long)seqp->ccid2s_seq);
-				/* XXX need to traverse from tail -> head in
-				 * order to detect multiple congestion events in
-				 * one ack vector.
-				 */
-				ccid2_congestion_event(sk, seqp);
-				hc->tx_pipe--;
-			}
-			if (seqp == hc->tx_seqt)
-				break;
-			seqp = seqp->ccid2s_prev;
-		}
-
-		hc->tx_seqt = last_acked;
-	}
-
-	/* trim acked packets in tail */
-	while (hc->tx_seqt != hc->tx_seqh) {
-		if (!hc->tx_seqt->ccid2s_acked)
-			break;
-
-		hc->tx_seqt = hc->tx_seqt->ccid2s_next;
-	}
-
-	/* restart RTO timer if not all outstanding data has been acked */
-	if (hc->tx_pipe == 0)
-		sk_stop_timer(sk, &hc->tx_rtotimer);
-	else
-		sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
-done:
-	/* check if incoming Acks allow pending packets to be sent */
-	if (sender_was_blocked && !ccid2_cwnd_network_limited(hc))
-		dccp_tasklet_schedule(sk);
-	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
-}
-
-static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
-{
-	struct ccid2_hc_tx_sock *hc = ccid_priv(ccid);
-	struct dccp_sock *dp = dccp_sk(sk);
-	u32 max_ratio;
-
-	/* RFC 4341, 5: initialise ssthresh to arbitrarily high (max) value */
-	hc->tx_ssthresh = ~0U;
-
-	/* Use larger initial windows (RFC 4341, section 5). */
-	hc->tx_cwnd = rfc3390_bytes_to_packets(dp->dccps_mss_cache);
-	hc->tx_expected_wnd = hc->tx_cwnd;
-
-	/* Make sure that Ack Ratio is enabled and within bounds. */
-	max_ratio = DIV_ROUND_UP(hc->tx_cwnd, 2);
-	if (dp->dccps_l_ack_ratio == 0 || dp->dccps_l_ack_ratio > max_ratio)
-		dp->dccps_l_ack_ratio = max_ratio;
-
-	/* XXX init ~ to window size... */
-	if (ccid2_hc_tx_alloc_seq(hc))
-		return -ENOMEM;
-
-	hc->tx_rto	 = DCCP_TIMEOUT_INIT;
-	hc->tx_rpdupack  = -1;
-	hc->tx_last_cong = hc->tx_lsndtime = hc->tx_cwnd_stamp = ccid2_jiffies32;
-	hc->tx_cwnd_used = 0;
-	hc->sk		 = sk;
-	timer_setup(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire, 0);
-	INIT_LIST_HEAD(&hc->tx_av_chunks);
-	return 0;
-}
-
-static void ccid2_hc_tx_exit(struct sock *sk)
-{
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-	int i;
-
-	sk_stop_timer(sk, &hc->tx_rtotimer);
-
-	for (i = 0; i < hc->tx_seqbufc; i++)
-		kfree(hc->tx_seqbuf[i]);
-	hc->tx_seqbufc = 0;
-	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
-}
-
-static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
-{
-	struct ccid2_hc_rx_sock *hc = ccid2_hc_rx_sk(sk);
-
-	if (!dccp_data_packet(skb))
-		return;
-
-	if (++hc->rx_num_data_pkts >= dccp_sk(sk)->dccps_r_ack_ratio) {
-		dccp_send_ack(sk);
-		hc->rx_num_data_pkts = 0;
-	}
-}
-
-struct ccid_operations ccid2_ops = {
-	.ccid_id		  = DCCPC_CCID2,
-	.ccid_name		  = "TCP-like",
-	.ccid_hc_tx_obj_size	  = sizeof(struct ccid2_hc_tx_sock),
-	.ccid_hc_tx_init	  = ccid2_hc_tx_init,
-	.ccid_hc_tx_exit	  = ccid2_hc_tx_exit,
-	.ccid_hc_tx_send_packet	  = ccid2_hc_tx_send_packet,
-	.ccid_hc_tx_packet_sent	  = ccid2_hc_tx_packet_sent,
-	.ccid_hc_tx_parse_options = ccid2_hc_tx_parse_options,
-	.ccid_hc_tx_packet_recv	  = ccid2_hc_tx_packet_recv,
-	.ccid_hc_rx_obj_size	  = sizeof(struct ccid2_hc_rx_sock),
-	.ccid_hc_rx_packet_recv	  = ccid2_hc_rx_packet_recv,
-};
-
-#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
-module_param(ccid2_debug, bool, 0644);
-MODULE_PARM_DESC(ccid2_debug, "Enable CCID-2 debug messages");
-#endif
diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h
deleted file mode 100644
index 330c7b4ec001..000000000000
--- a/net/dccp/ccids/ccid2.h
+++ /dev/null
@@ -1,121 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk>
- */
-#ifndef _DCCP_CCID2_H_
-#define _DCCP_CCID2_H_
-
-#include <linux/timer.h>
-#include <linux/types.h>
-#include "../ccid.h"
-#include "../dccp.h"
-
-/*
- * CCID-2 timestamping faces the same issues as TCP timestamping.
- * Hence we reuse/share as much of the code as possible.
- */
-#define ccid2_jiffies32	((u32)jiffies)
-
-/* NUMDUPACK parameter from RFC 4341, p. 6 */
-#define NUMDUPACK	3
-
-struct ccid2_seq {
-	u64			ccid2s_seq;
-	u32			ccid2s_sent;
-	int			ccid2s_acked;
-	struct ccid2_seq	*ccid2s_prev;
-	struct ccid2_seq	*ccid2s_next;
-};
-
-#define CCID2_SEQBUF_LEN 1024
-#define CCID2_SEQBUF_MAX 128
-
-/*
- * Multiple of congestion window to keep the sequence window at
- * (RFC 4340 7.5.2)
- */
-#define CCID2_WIN_CHANGE_FACTOR 5
-
-/**
- * struct ccid2_hc_tx_sock - CCID2 TX half connection
- * @tx_{cwnd,ssthresh,pipe}: as per RFC 4341, section 5
- * @tx_packets_acked:	     Ack counter for deriving cwnd growth (RFC 3465)
- * @tx_srtt:		     smoothed RTT estimate, scaled by 2^3
- * @tx_mdev:		     smoothed RTT variation, scaled by 2^2
- * @tx_mdev_max:	     maximum of @mdev during one flight
- * @tx_rttvar:		     moving average/maximum of @mdev_max
- * @tx_rto:		     RTO value deriving from SRTT and RTTVAR (RFC 2988)
- * @tx_rtt_seq:		     to decay RTTVAR at most once per flight
- * @tx_cwnd_used:	     actually used cwnd, W_used of RFC 2861
- * @tx_expected_wnd:	     moving average of @tx_cwnd_used
- * @tx_cwnd_stamp:	     to track idle periods in CWV
- * @tx_lsndtime:	     last time (in jiffies) a data packet was sent
- * @tx_rpseq:		     last consecutive seqno
- * @tx_rpdupack:	     dupacks since rpseq
- * @tx_av_chunks:	     list of Ack Vectors received on current skb
- */
-struct ccid2_hc_tx_sock {
-	u32			tx_cwnd;
-	u32			tx_ssthresh;
-	u32			tx_pipe;
-	u32			tx_packets_acked;
-	struct ccid2_seq	*tx_seqbuf[CCID2_SEQBUF_MAX];
-	int			tx_seqbufc;
-	struct ccid2_seq	*tx_seqh;
-	struct ccid2_seq	*tx_seqt;
-
-	/* RTT measurement: variables/principles are the same as in TCP */
-	u32			tx_srtt,
-				tx_mdev,
-				tx_mdev_max,
-				tx_rttvar,
-				tx_rto;
-	u64			tx_rtt_seq:48;
-	struct timer_list	tx_rtotimer;
-	struct sock		*sk;
-
-	/* Congestion Window validation (optional, RFC 2861) */
-	u32			tx_cwnd_used,
-				tx_expected_wnd,
-				tx_cwnd_stamp,
-				tx_lsndtime;
-
-	u64			tx_rpseq;
-	int			tx_rpdupack;
-	u32			tx_last_cong;
-	u64			tx_high_ack;
-	struct list_head	tx_av_chunks;
-};
-
-static inline bool ccid2_cwnd_network_limited(struct ccid2_hc_tx_sock *hc)
-{
-	return hc->tx_pipe >= hc->tx_cwnd;
-}
-
-/*
- * Convert RFC 3390 larger initial window into an equivalent number of packets.
- * This is based on the numbers specified in RFC 5681, 3.1.
- */
-static inline u32 rfc3390_bytes_to_packets(const u32 smss)
-{
-	return smss <= 1095 ? 4 : (smss > 2190 ? 2 : 3);
-}
-
-/**
- * struct ccid2_hc_rx_sock  -  Receiving end of CCID-2 half-connection
- * @rx_num_data_pkts: number of data packets received since last feedback
- */
-struct ccid2_hc_rx_sock {
-	u32	rx_num_data_pkts;
-};
-
-static inline struct ccid2_hc_tx_sock *ccid2_hc_tx_sk(const struct sock *sk)
-{
-	return ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid);
-}
-
-static inline struct ccid2_hc_rx_sock *ccid2_hc_rx_sk(const struct sock *sk)
-{
-	return ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid);
-}
-#endif /* _DCCP_CCID2_H_ */
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
deleted file mode 100644
index f349d16dd8f6..000000000000
--- a/net/dccp/ccids/ccid3.c
+++ /dev/null
@@ -1,866 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  Copyright (c) 2007   The University of Aberdeen, Scotland, UK
- *  Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand.
- *  Copyright (c) 2005-7 Ian McDonald <ian.mcdonald@jandi.co.nz>
- *
- *  An implementation of the DCCP protocol
- *
- *  This code has been developed by the University of Waikato WAND
- *  research group. For further information please see https://www.wand.net.nz/
- *
- *  This code also uses code from Lulea University, rereleased as GPL by its
- *  authors:
- *  Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
- *
- *  Changes to meet Linux coding standards, to make it meet latest ccid3 draft
- *  and to make it work as a loadable module in the DCCP stack written by
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>.
- *
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-#include "../dccp.h"
-#include "ccid3.h"
-
-#include <linux/unaligned.h>
-
-#ifdef CONFIG_IP_DCCP_CCID3_DEBUG
-static bool ccid3_debug;
-#define ccid3_pr_debug(format, a...)	DCCP_PR_DEBUG(ccid3_debug, format, ##a)
-#else
-#define ccid3_pr_debug(format, a...)
-#endif
-
-/*
- *	Transmitter Half-Connection Routines
- */
-#ifdef CONFIG_IP_DCCP_CCID3_DEBUG
-static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state)
-{
-	static const char *const ccid3_state_names[] = {
-	[TFRC_SSTATE_NO_SENT]  = "NO_SENT",
-	[TFRC_SSTATE_NO_FBACK] = "NO_FBACK",
-	[TFRC_SSTATE_FBACK]    = "FBACK",
-	};
-
-	return ccid3_state_names[state];
-}
-#endif
-
-static void ccid3_hc_tx_set_state(struct sock *sk,
-				  enum ccid3_hc_tx_states state)
-{
-	struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
-	enum ccid3_hc_tx_states oldstate = hc->tx_state;
-
-	ccid3_pr_debug("%s(%p) %-8.8s -> %s\n",
-		       dccp_role(sk), sk, ccid3_tx_state_name(oldstate),
-		       ccid3_tx_state_name(state));
-	WARN_ON(state == oldstate);
-	hc->tx_state = state;
-}
-
-/*
- * Compute the initial sending rate X_init in the manner of RFC 3390:
- *
- *	X_init  =  min(4 * s, max(2 * s, 4380 bytes)) / RTT
- *
- * Note that RFC 3390 uses MSS, RFC 4342 refers to RFC 3390, and rfc3448bis
- * (rev-02) clarifies the use of RFC 3390 with regard to the above formula.
- * For consistency with other parts of the code, X_init is scaled by 2^6.
- */
-static inline u64 rfc3390_initial_rate(struct sock *sk)
-{
-	const struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
-	const __u32 w_init = clamp_t(__u32, 4380U, 2 * hc->tx_s, 4 * hc->tx_s);
-
-	return scaled_div(w_init << 6, hc->tx_rtt);
-}
-
-/**
- * ccid3_update_send_interval  -  Calculate new t_ipi = s / X_inst
- * @hc: socket to have the send interval updated
- *
- * This respects the granularity of X_inst (64 * bytes/second).
- */
-static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc)
-{
-	hc->tx_t_ipi = scaled_div32(((u64)hc->tx_s) << 6, hc->tx_x);
-
-	DCCP_BUG_ON(hc->tx_t_ipi == 0);
-	ccid3_pr_debug("t_ipi=%u, s=%u, X=%u\n", hc->tx_t_ipi,
-		       hc->tx_s, (unsigned int)(hc->tx_x >> 6));
-}
-
-static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now)
-{
-	u32 delta = ktime_us_delta(now, hc->tx_t_last_win_count);
-
-	return delta / hc->tx_rtt;
-}
-
-/**
- * ccid3_hc_tx_update_x  -  Update allowed sending rate X
- * @sk: socket to be updated
- * @stamp: most recent time if available - can be left NULL.
- *
- * This function tracks draft rfc3448bis, check there for latest details.
- *
- * Note: X and X_recv are both stored in units of 64 * bytes/second, to support
- *       fine-grained resolution of sending rates. This requires scaling by 2^6
- *       throughout the code. Only X_calc is unscaled (in bytes/second).
- *
- */
-static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp)
-{
-	struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
-	__u64 min_rate = 2 * hc->tx_x_recv;
-	const __u64 old_x = hc->tx_x;
-	ktime_t now = stamp ? *stamp : ktime_get_real();
-
-	/*
-	 * Handle IDLE periods: do not reduce below RFC3390 initial sending rate
-	 * when idling [RFC 4342, 5.1]. Definition of idling is from rfc3448bis:
-	 * a sender is idle if it has not sent anything over a 2-RTT-period.
-	 * For consistency with X and X_recv, min_rate is also scaled by 2^6.
-	 */
-	if (ccid3_hc_tx_idle_rtt(hc, now) >= 2) {
-		min_rate = rfc3390_initial_rate(sk);
-		min_rate = max(min_rate, 2 * hc->tx_x_recv);
-	}
-
-	if (hc->tx_p > 0) {
-
-		hc->tx_x = min(((__u64)hc->tx_x_calc) << 6, min_rate);
-		hc->tx_x = max(hc->tx_x, (((__u64)hc->tx_s) << 6) / TFRC_T_MBI);
-
-	} else if (ktime_us_delta(now, hc->tx_t_ld) - (s64)hc->tx_rtt >= 0) {
-
-		hc->tx_x = min(2 * hc->tx_x, min_rate);
-		hc->tx_x = max(hc->tx_x,
-			       scaled_div(((__u64)hc->tx_s) << 6, hc->tx_rtt));
-		hc->tx_t_ld = now;
-	}
-
-	if (hc->tx_x != old_x) {
-		ccid3_pr_debug("X_prev=%u, X_now=%u, X_calc=%u, "
-			       "X_recv=%u\n", (unsigned int)(old_x >> 6),
-			       (unsigned int)(hc->tx_x >> 6), hc->tx_x_calc,
-			       (unsigned int)(hc->tx_x_recv >> 6));
-
-		ccid3_update_send_interval(hc);
-	}
-}
-
-/**
- *	ccid3_hc_tx_update_s - Track the mean packet size `s'
- *	@hc: socket to be updated
- *	@len: DCCP packet payload size in bytes
- *
- *	cf. RFC 4342, 5.3 and  RFC 3448, 4.1
- */
-static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hc, int len)
-{
-	const u16 old_s = hc->tx_s;
-
-	hc->tx_s = tfrc_ewma(hc->tx_s, len, 9);
-
-	if (hc->tx_s != old_s)
-		ccid3_update_send_interval(hc);
-}
-
-/*
- *	Update Window Counter using the algorithm from [RFC 4342, 8.1].
- *	As elsewhere, RTT > 0 is assumed by using dccp_sample_rtt().
- */
-static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hc,
-						ktime_t now)
-{
-	u32 delta = ktime_us_delta(now, hc->tx_t_last_win_count),
-	    quarter_rtts = (4 * delta) / hc->tx_rtt;
-
-	if (quarter_rtts > 0) {
-		hc->tx_t_last_win_count = now;
-		hc->tx_last_win_count  += min(quarter_rtts, 5U);
-		hc->tx_last_win_count  &= 0xF;		/* mod 16 */
-	}
-}
-
-static void ccid3_hc_tx_no_feedback_timer(struct timer_list *t)
-{
-	struct ccid3_hc_tx_sock *hc = from_timer(hc, t, tx_no_feedback_timer);
-	struct sock *sk = hc->sk;
-	unsigned long t_nfb = USEC_PER_SEC / 5;
-
-	bh_lock_sock(sk);
-	if (sock_owned_by_user(sk)) {
-		/* Try again later. */
-		/* XXX: set some sensible MIB */
-		goto restart_timer;
-	}
-
-	ccid3_pr_debug("%s(%p, state=%s) - entry\n", dccp_role(sk), sk,
-		       ccid3_tx_state_name(hc->tx_state));
-
-	/* Ignore and do not restart after leaving the established state */
-	if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN))
-		goto out;
-
-	/* Reset feedback state to "no feedback received" */
-	if (hc->tx_state == TFRC_SSTATE_FBACK)
-		ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK);
-
-	/*
-	 * Determine new allowed sending rate X as per draft rfc3448bis-00, 4.4
-	 * RTO is 0 if and only if no feedback has been received yet.
-	 */
-	if (hc->tx_t_rto == 0 || hc->tx_p == 0) {
-
-		/* halve send rate directly */
-		hc->tx_x = max(hc->tx_x / 2,
-			       (((__u64)hc->tx_s) << 6) / TFRC_T_MBI);
-		ccid3_update_send_interval(hc);
-	} else {
-		/*
-		 *  Modify the cached value of X_recv
-		 *
-		 *  If (X_calc > 2 * X_recv)
-		 *    X_recv = max(X_recv / 2, s / (2 * t_mbi));
-		 *  Else
-		 *    X_recv = X_calc / 4;
-		 *
-		 *  Note that X_recv is scaled by 2^6 while X_calc is not
-		 */
-		if (hc->tx_x_calc > (hc->tx_x_recv >> 5))
-			hc->tx_x_recv =
-				max(hc->tx_x_recv / 2,
-				    (((__u64)hc->tx_s) << 6) / (2*TFRC_T_MBI));
-		else {
-			hc->tx_x_recv = hc->tx_x_calc;
-			hc->tx_x_recv <<= 4;
-		}
-		ccid3_hc_tx_update_x(sk, NULL);
-	}
-	ccid3_pr_debug("Reduced X to %llu/64 bytes/sec\n",
-			(unsigned long long)hc->tx_x);
-
-	/*
-	 * Set new timeout for the nofeedback timer.
-	 * See comments in packet_recv() regarding the value of t_RTO.
-	 */
-	if (unlikely(hc->tx_t_rto == 0))	/* no feedback received yet */
-		t_nfb = TFRC_INITIAL_TIMEOUT;
-	else
-		t_nfb = max(hc->tx_t_rto, 2 * hc->tx_t_ipi);
-
-restart_timer:
-	sk_reset_timer(sk, &hc->tx_no_feedback_timer,
-			   jiffies + usecs_to_jiffies(t_nfb));
-out:
-	bh_unlock_sock(sk);
-	sock_put(sk);
-}
-
-/**
- * ccid3_hc_tx_send_packet  -  Delay-based dequeueing of TX packets
- * @sk: socket to send packet from
- * @skb: next packet candidate to send on @sk
- *
- * This function uses the convention of ccid_packet_dequeue_eval() and
- * returns a millisecond-delay value between 0 and t_mbi = 64000 msec.
- */
-static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
-	ktime_t now = ktime_get_real();
-	s64 delay;
-
-	/*
-	 * This function is called only for Data and DataAck packets. Sending
-	 * zero-sized Data(Ack)s is theoretically possible, but for congestion
-	 * control this case is pathological - ignore it.
-	 */
-	if (unlikely(skb->len == 0))
-		return -EBADMSG;
-
-	if (hc->tx_state == TFRC_SSTATE_NO_SENT) {
-		sk_reset_timer(sk, &hc->tx_no_feedback_timer, (jiffies +
-			       usecs_to_jiffies(TFRC_INITIAL_TIMEOUT)));
-		hc->tx_last_win_count	= 0;
-		hc->tx_t_last_win_count = now;
-
-		/* Set t_0 for initial packet */
-		hc->tx_t_nom = now;
-
-		hc->tx_s = skb->len;
-
-		/*
-		 * Use initial RTT sample when available: recommended by erratum
-		 * to RFC 4342. This implements the initialisation procedure of
-		 * draft rfc3448bis, section 4.2. Remember, X is scaled by 2^6.
-		 */
-		if (dp->dccps_syn_rtt) {
-			ccid3_pr_debug("SYN RTT = %uus\n", dp->dccps_syn_rtt);
-			hc->tx_rtt  = dp->dccps_syn_rtt;
-			hc->tx_x    = rfc3390_initial_rate(sk);
-			hc->tx_t_ld = now;
-		} else {
-			/*
-			 * Sender does not have RTT sample:
-			 * - set fallback RTT (RFC 4340, 3.4) since a RTT value
-			 *   is needed in several parts (e.g.  window counter);
-			 * - set sending rate X_pps = 1pps as per RFC 3448, 4.2.
-			 */
-			hc->tx_rtt = DCCP_FALLBACK_RTT;
-			hc->tx_x   = hc->tx_s;
-			hc->tx_x <<= 6;
-		}
-		ccid3_update_send_interval(hc);
-
-		ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK);
-
-	} else {
-		delay = ktime_us_delta(hc->tx_t_nom, now);
-		ccid3_pr_debug("delay=%ld\n", (long)delay);
-		/*
-		 *	Scheduling of packet transmissions (RFC 5348, 8.3)
-		 *
-		 * if (t_now > t_nom - delta)
-		 *       // send the packet now
-		 * else
-		 *       // send the packet in (t_nom - t_now) milliseconds.
-		 */
-		if (delay >= TFRC_T_DELTA)
-			return (u32)delay / USEC_PER_MSEC;
-
-		ccid3_hc_tx_update_win_count(hc, now);
-	}
-
-	/* prepare to send now (add options etc.) */
-	dp->dccps_hc_tx_insert_options = 1;
-	DCCP_SKB_CB(skb)->dccpd_ccval  = hc->tx_last_win_count;
-
-	/* set the nominal send time for the next following packet */
-	hc->tx_t_nom = ktime_add_us(hc->tx_t_nom, hc->tx_t_ipi);
-	return CCID_PACKET_SEND_AT_ONCE;
-}
-
-static void ccid3_hc_tx_packet_sent(struct sock *sk, unsigned int len)
-{
-	struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
-
-	ccid3_hc_tx_update_s(hc, len);
-
-	if (tfrc_tx_hist_add(&hc->tx_hist, dccp_sk(sk)->dccps_gss))
-		DCCP_CRIT("packet history - out of memory!");
-}
-
-static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
-{
-	struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
-	struct tfrc_tx_hist_entry *acked;
-	ktime_t now;
-	unsigned long t_nfb;
-	u32 r_sample;
-
-	/* we are only interested in ACKs */
-	if (!(DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_ACK ||
-	      DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_DATAACK))
-		return;
-	/*
-	 * Locate the acknowledged packet in the TX history.
-	 *
-	 * Returning "entry not found" here can for instance happen when
-	 *  - the host has not sent out anything (e.g. a passive server),
-	 *  - the Ack is outdated (packet with higher Ack number was received),
-	 *  - it is a bogus Ack (for a packet not sent on this connection).
-	 */
-	acked = tfrc_tx_hist_find_entry(hc->tx_hist, dccp_hdr_ack_seq(skb));
-	if (acked == NULL)
-		return;
-	/* For the sake of RTT sampling, ignore/remove all older entries */
-	tfrc_tx_hist_purge(&acked->next);
-
-	/* Update the moving average for the RTT estimate (RFC 3448, 4.3) */
-	now	  = ktime_get_real();
-	r_sample  = dccp_sample_rtt(sk, ktime_us_delta(now, acked->stamp));
-	hc->tx_rtt = tfrc_ewma(hc->tx_rtt, r_sample, 9);
-
-	/*
-	 * Update allowed sending rate X as per draft rfc3448bis-00, 4.2/3
-	 */
-	if (hc->tx_state == TFRC_SSTATE_NO_FBACK) {
-		ccid3_hc_tx_set_state(sk, TFRC_SSTATE_FBACK);
-
-		if (hc->tx_t_rto == 0) {
-			/*
-			 * Initial feedback packet: Larger Initial Windows (4.2)
-			 */
-			hc->tx_x    = rfc3390_initial_rate(sk);
-			hc->tx_t_ld = now;
-
-			ccid3_update_send_interval(hc);
-
-			goto done_computing_x;
-		} else if (hc->tx_p == 0) {
-			/*
-			 * First feedback after nofeedback timer expiry (4.3)
-			 */
-			goto done_computing_x;
-		}
-	}
-
-	/* Update sending rate (step 4 of [RFC 3448, 4.3]) */
-	if (hc->tx_p > 0)
-		hc->tx_x_calc = tfrc_calc_x(hc->tx_s, hc->tx_rtt, hc->tx_p);
-	ccid3_hc_tx_update_x(sk, &now);
-
-done_computing_x:
-	ccid3_pr_debug("%s(%p), RTT=%uus (sample=%uus), s=%u, "
-			       "p=%u, X_calc=%u, X_recv=%u, X=%u\n",
-			       dccp_role(sk), sk, hc->tx_rtt, r_sample,
-			       hc->tx_s, hc->tx_p, hc->tx_x_calc,
-			       (unsigned int)(hc->tx_x_recv >> 6),
-			       (unsigned int)(hc->tx_x >> 6));
-
-	/* unschedule no feedback timer */
-	sk_stop_timer(sk, &hc->tx_no_feedback_timer);
-
-	/*
-	 * As we have calculated new ipi, delta, t_nom it is possible
-	 * that we now can send a packet, so wake up dccp_wait_for_ccid
-	 */
-	sk->sk_write_space(sk);
-
-	/*
-	 * Update timeout interval for the nofeedback timer. In order to control
-	 * rate halving on networks with very low RTTs (<= 1 ms), use per-route
-	 * tunable RTAX_RTO_MIN value as the lower bound.
-	 */
-	hc->tx_t_rto = max_t(u32, 4 * hc->tx_rtt,
-				  USEC_PER_SEC/HZ * tcp_rto_min(sk));
-	/*
-	 * Schedule no feedback timer to expire in
-	 * max(t_RTO, 2 * s/X)  =  max(t_RTO, 2 * t_ipi)
-	 */
-	t_nfb = max(hc->tx_t_rto, 2 * hc->tx_t_ipi);
-
-	ccid3_pr_debug("%s(%p), Scheduled no feedback timer to "
-		       "expire in %lu jiffies (%luus)\n",
-		       dccp_role(sk), sk, usecs_to_jiffies(t_nfb), t_nfb);
-
-	sk_reset_timer(sk, &hc->tx_no_feedback_timer,
-			   jiffies + usecs_to_jiffies(t_nfb));
-}
-
-static int ccid3_hc_tx_parse_options(struct sock *sk, u8 packet_type,
-				     u8 option, u8 *optval, u8 optlen)
-{
-	struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
-	__be32 opt_val;
-
-	switch (option) {
-	case TFRC_OPT_RECEIVE_RATE:
-	case TFRC_OPT_LOSS_EVENT_RATE:
-		/* Must be ignored on Data packets, cf. RFC 4342 8.3 and 8.5 */
-		if (packet_type == DCCP_PKT_DATA)
-			break;
-		if (unlikely(optlen != 4)) {
-			DCCP_WARN("%s(%p), invalid len %d for %u\n",
-				  dccp_role(sk), sk, optlen, option);
-			return -EINVAL;
-		}
-		opt_val = ntohl(get_unaligned((__be32 *)optval));
-
-		if (option == TFRC_OPT_RECEIVE_RATE) {
-			/* Receive Rate is kept in units of 64 bytes/second */
-			hc->tx_x_recv = opt_val;
-			hc->tx_x_recv <<= 6;
-
-			ccid3_pr_debug("%s(%p), RECEIVE_RATE=%u\n",
-				       dccp_role(sk), sk, opt_val);
-		} else {
-			/* Update the fixpoint Loss Event Rate fraction */
-			hc->tx_p = tfrc_invert_loss_event_rate(opt_val);
-
-			ccid3_pr_debug("%s(%p), LOSS_EVENT_RATE=%u\n",
-				       dccp_role(sk), sk, opt_val);
-		}
-	}
-	return 0;
-}
-
-static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk)
-{
-	struct ccid3_hc_tx_sock *hc = ccid_priv(ccid);
-
-	hc->tx_state = TFRC_SSTATE_NO_SENT;
-	hc->tx_hist  = NULL;
-	hc->sk	     = sk;
-	timer_setup(&hc->tx_no_feedback_timer,
-		    ccid3_hc_tx_no_feedback_timer, 0);
-	return 0;
-}
-
-static void ccid3_hc_tx_exit(struct sock *sk)
-{
-	struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
-
-	sk_stop_timer(sk, &hc->tx_no_feedback_timer);
-	tfrc_tx_hist_purge(&hc->tx_hist);
-}
-
-static void ccid3_hc_tx_get_info(struct sock *sk, struct tcp_info *info)
-{
-	info->tcpi_rto = ccid3_hc_tx_sk(sk)->tx_t_rto;
-	info->tcpi_rtt = ccid3_hc_tx_sk(sk)->tx_rtt;
-}
-
-static int ccid3_hc_tx_getsockopt(struct sock *sk, const int optname, int len,
-				  u32 __user *optval, int __user *optlen)
-{
-	const struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
-	struct tfrc_tx_info tfrc;
-	const void *val;
-
-	switch (optname) {
-	case DCCP_SOCKOPT_CCID_TX_INFO:
-		if (len < sizeof(tfrc))
-			return -EINVAL;
-		memset(&tfrc, 0, sizeof(tfrc));
-		tfrc.tfrctx_x	   = hc->tx_x;
-		tfrc.tfrctx_x_recv = hc->tx_x_recv;
-		tfrc.tfrctx_x_calc = hc->tx_x_calc;
-		tfrc.tfrctx_rtt	   = hc->tx_rtt;
-		tfrc.tfrctx_p	   = hc->tx_p;
-		tfrc.tfrctx_rto	   = hc->tx_t_rto;
-		tfrc.tfrctx_ipi	   = hc->tx_t_ipi;
-		len = sizeof(tfrc);
-		val = &tfrc;
-		break;
-	default:
-		return -ENOPROTOOPT;
-	}
-
-	if (put_user(len, optlen) || copy_to_user(optval, val, len))
-		return -EFAULT;
-
-	return 0;
-}
-
-/*
- *	Receiver Half-Connection Routines
- */
-
-/* CCID3 feedback types */
-enum ccid3_fback_type {
-	CCID3_FBACK_NONE = 0,
-	CCID3_FBACK_INITIAL,
-	CCID3_FBACK_PERIODIC,
-	CCID3_FBACK_PARAM_CHANGE
-};
-
-#ifdef CONFIG_IP_DCCP_CCID3_DEBUG
-static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state)
-{
-	static const char *const ccid3_rx_state_names[] = {
-	[TFRC_RSTATE_NO_DATA] = "NO_DATA",
-	[TFRC_RSTATE_DATA]    = "DATA",
-	};
-
-	return ccid3_rx_state_names[state];
-}
-#endif
-
-static void ccid3_hc_rx_set_state(struct sock *sk,
-				  enum ccid3_hc_rx_states state)
-{
-	struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
-	enum ccid3_hc_rx_states oldstate = hc->rx_state;
-
-	ccid3_pr_debug("%s(%p) %-8.8s -> %s\n",
-		       dccp_role(sk), sk, ccid3_rx_state_name(oldstate),
-		       ccid3_rx_state_name(state));
-	WARN_ON(state == oldstate);
-	hc->rx_state = state;
-}
-
-static void ccid3_hc_rx_send_feedback(struct sock *sk,
-				      const struct sk_buff *skb,
-				      enum ccid3_fback_type fbtype)
-{
-	struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
-	struct dccp_sock *dp = dccp_sk(sk);
-	ktime_t now = ktime_get();
-	s64 delta = 0;
-
-	switch (fbtype) {
-	case CCID3_FBACK_INITIAL:
-		hc->rx_x_recv = 0;
-		hc->rx_pinv   = ~0U;   /* see RFC 4342, 8.5 */
-		break;
-	case CCID3_FBACK_PARAM_CHANGE:
-		/*
-		 * When parameters change (new loss or p > p_prev), we do not
-		 * have a reliable estimate for R_m of [RFC 3448, 6.2] and so
-		 * need to  reuse the previous value of X_recv. However, when
-		 * X_recv was 0 (due to early loss), this would kill X down to
-		 * s/t_mbi (i.e. one packet in 64 seconds).
-		 * To avoid such drastic reduction, we approximate X_recv as
-		 * the number of bytes since last feedback.
-		 * This is a safe fallback, since X is bounded above by X_calc.
-		 */
-		if (hc->rx_x_recv > 0)
-			break;
-		fallthrough;
-	case CCID3_FBACK_PERIODIC:
-		delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback);
-		if (delta <= 0)
-			delta = 1;
-		hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta);
-		break;
-	default:
-		return;
-	}
-
-	ccid3_pr_debug("Interval %lldusec, X_recv=%u, 1/p=%u\n", delta,
-		       hc->rx_x_recv, hc->rx_pinv);
-
-	hc->rx_tstamp_last_feedback = now;
-	hc->rx_last_counter	    = dccp_hdr(skb)->dccph_ccval;
-	hc->rx_bytes_recv	    = 0;
-
-	dp->dccps_hc_rx_insert_options = 1;
-	dccp_send_ack(sk);
-}
-
-static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb)
-{
-	const struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
-	__be32 x_recv, pinv;
-
-	if (!(sk->sk_state == DCCP_OPEN || sk->sk_state == DCCP_PARTOPEN))
-		return 0;
-
-	if (dccp_packet_without_ack(skb))
-		return 0;
-
-	x_recv = htonl(hc->rx_x_recv);
-	pinv   = htonl(hc->rx_pinv);
-
-	if (dccp_insert_option(skb, TFRC_OPT_LOSS_EVENT_RATE,
-			       &pinv, sizeof(pinv)) ||
-	    dccp_insert_option(skb, TFRC_OPT_RECEIVE_RATE,
-			       &x_recv, sizeof(x_recv)))
-		return -1;
-
-	return 0;
-}
-
-/**
- * ccid3_first_li  -  Implements [RFC 5348, 6.3.1]
- * @sk: socket to calculate loss interval for
- *
- * Determine the length of the first loss interval via inverse lookup.
- * Assume that X_recv can be computed by the throughput equation
- *		    s
- *	X_recv = --------
- *		 R * fval
- * Find some p such that f(p) = fval; return 1/p (scaled).
- */
-static u32 ccid3_first_li(struct sock *sk)
-{
-	struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
-	u32 x_recv, p;
-	s64 delta;
-	u64 fval;
-
-	if (hc->rx_rtt == 0) {
-		DCCP_WARN("No RTT estimate available, using fallback RTT\n");
-		hc->rx_rtt = DCCP_FALLBACK_RTT;
-	}
-
-	delta = ktime_us_delta(ktime_get(), hc->rx_tstamp_last_feedback);
-	if (delta <= 0)
-		delta = 1;
-	x_recv = scaled_div32(hc->rx_bytes_recv, delta);
-	if (x_recv == 0) {		/* would also trigger divide-by-zero */
-		DCCP_WARN("X_recv==0\n");
-		if (hc->rx_x_recv == 0) {
-			DCCP_BUG("stored value of X_recv is zero");
-			return ~0U;
-		}
-		x_recv = hc->rx_x_recv;
-	}
-
-	fval = scaled_div(hc->rx_s, hc->rx_rtt);
-	fval = scaled_div32(fval, x_recv);
-	p = tfrc_calc_x_reverse_lookup(fval);
-
-	ccid3_pr_debug("%s(%p), receive rate=%u bytes/s, implied "
-		       "loss rate=%u\n", dccp_role(sk), sk, x_recv, p);
-
-	return p == 0 ? ~0U : scaled_div(1, p);
-}
-
-static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
-{
-	struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
-	enum ccid3_fback_type do_feedback = CCID3_FBACK_NONE;
-	const u64 ndp = dccp_sk(sk)->dccps_options_received.dccpor_ndp;
-	const bool is_data_packet = dccp_data_packet(skb);
-
-	if (unlikely(hc->rx_state == TFRC_RSTATE_NO_DATA)) {
-		if (is_data_packet) {
-			const u32 payload = skb->len - dccp_hdr(skb)->dccph_doff * 4;
-			do_feedback = CCID3_FBACK_INITIAL;
-			ccid3_hc_rx_set_state(sk, TFRC_RSTATE_DATA);
-			hc->rx_s = payload;
-			/*
-			 * Not necessary to update rx_bytes_recv here,
-			 * since X_recv = 0 for the first feedback packet (cf.
-			 * RFC 3448, 6.3) -- gerrit
-			 */
-		}
-		goto update_records;
-	}
-
-	if (tfrc_rx_hist_duplicate(&hc->rx_hist, skb))
-		return; /* done receiving */
-
-	if (is_data_packet) {
-		const u32 payload = skb->len - dccp_hdr(skb)->dccph_doff * 4;
-		/*
-		 * Update moving-average of s and the sum of received payload bytes
-		 */
-		hc->rx_s = tfrc_ewma(hc->rx_s, payload, 9);
-		hc->rx_bytes_recv += payload;
-	}
-
-	/*
-	 * Perform loss detection and handle pending losses
-	 */
-	if (tfrc_rx_handle_loss(&hc->rx_hist, &hc->rx_li_hist,
-				skb, ndp, ccid3_first_li, sk)) {
-		do_feedback = CCID3_FBACK_PARAM_CHANGE;
-		goto done_receiving;
-	}
-
-	if (tfrc_rx_hist_loss_pending(&hc->rx_hist))
-		return; /* done receiving */
-
-	/*
-	 * Handle data packets: RTT sampling and monitoring p
-	 */
-	if (unlikely(!is_data_packet))
-		goto update_records;
-
-	if (!tfrc_lh_is_initialised(&hc->rx_li_hist)) {
-		const u32 sample = tfrc_rx_hist_sample_rtt(&hc->rx_hist, skb);
-		/*
-		 * Empty loss history: no loss so far, hence p stays 0.
-		 * Sample RTT values, since an RTT estimate is required for the
-		 * computation of p when the first loss occurs; RFC 3448, 6.3.1.
-		 */
-		if (sample != 0)
-			hc->rx_rtt = tfrc_ewma(hc->rx_rtt, sample, 9);
-
-	} else if (tfrc_lh_update_i_mean(&hc->rx_li_hist, skb)) {
-		/*
-		 * Step (3) of [RFC 3448, 6.1]: Recompute I_mean and, if I_mean
-		 * has decreased (resp. p has increased), send feedback now.
-		 */
-		do_feedback = CCID3_FBACK_PARAM_CHANGE;
-	}
-
-	/*
-	 * Check if the periodic once-per-RTT feedback is due; RFC 4342, 10.3
-	 */
-	if (SUB16(dccp_hdr(skb)->dccph_ccval, hc->rx_last_counter) > 3)
-		do_feedback = CCID3_FBACK_PERIODIC;
-
-update_records:
-	tfrc_rx_hist_add_packet(&hc->rx_hist, skb, ndp);
-
-done_receiving:
-	if (do_feedback)
-		ccid3_hc_rx_send_feedback(sk, skb, do_feedback);
-}
-
-static int ccid3_hc_rx_init(struct ccid *ccid, struct sock *sk)
-{
-	struct ccid3_hc_rx_sock *hc = ccid_priv(ccid);
-
-	hc->rx_state = TFRC_RSTATE_NO_DATA;
-	tfrc_lh_init(&hc->rx_li_hist);
-	return tfrc_rx_hist_alloc(&hc->rx_hist);
-}
-
-static void ccid3_hc_rx_exit(struct sock *sk)
-{
-	struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
-
-	tfrc_rx_hist_purge(&hc->rx_hist);
-	tfrc_lh_cleanup(&hc->rx_li_hist);
-}
-
-static void ccid3_hc_rx_get_info(struct sock *sk, struct tcp_info *info)
-{
-	info->tcpi_ca_state = ccid3_hc_rx_sk(sk)->rx_state;
-	info->tcpi_options  |= TCPI_OPT_TIMESTAMPS;
-	info->tcpi_rcv_rtt  = ccid3_hc_rx_sk(sk)->rx_rtt;
-}
-
-static int ccid3_hc_rx_getsockopt(struct sock *sk, const int optname, int len,
-				  u32 __user *optval, int __user *optlen)
-{
-	const struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
-	struct tfrc_rx_info rx_info;
-	const void *val;
-
-	switch (optname) {
-	case DCCP_SOCKOPT_CCID_RX_INFO:
-		if (len < sizeof(rx_info))
-			return -EINVAL;
-		rx_info.tfrcrx_x_recv = hc->rx_x_recv;
-		rx_info.tfrcrx_rtt    = hc->rx_rtt;
-		rx_info.tfrcrx_p      = tfrc_invert_loss_event_rate(hc->rx_pinv);
-		len = sizeof(rx_info);
-		val = &rx_info;
-		break;
-	default:
-		return -ENOPROTOOPT;
-	}
-
-	if (put_user(len, optlen) || copy_to_user(optval, val, len))
-		return -EFAULT;
-
-	return 0;
-}
-
-struct ccid_operations ccid3_ops = {
-	.ccid_id		   = DCCPC_CCID3,
-	.ccid_name		   = "TCP-Friendly Rate Control",
-	.ccid_hc_tx_obj_size	   = sizeof(struct ccid3_hc_tx_sock),
-	.ccid_hc_tx_init	   = ccid3_hc_tx_init,
-	.ccid_hc_tx_exit	   = ccid3_hc_tx_exit,
-	.ccid_hc_tx_send_packet	   = ccid3_hc_tx_send_packet,
-	.ccid_hc_tx_packet_sent	   = ccid3_hc_tx_packet_sent,
-	.ccid_hc_tx_packet_recv	   = ccid3_hc_tx_packet_recv,
-	.ccid_hc_tx_parse_options  = ccid3_hc_tx_parse_options,
-	.ccid_hc_rx_obj_size	   = sizeof(struct ccid3_hc_rx_sock),
-	.ccid_hc_rx_init	   = ccid3_hc_rx_init,
-	.ccid_hc_rx_exit	   = ccid3_hc_rx_exit,
-	.ccid_hc_rx_insert_options = ccid3_hc_rx_insert_options,
-	.ccid_hc_rx_packet_recv	   = ccid3_hc_rx_packet_recv,
-	.ccid_hc_rx_get_info	   = ccid3_hc_rx_get_info,
-	.ccid_hc_tx_get_info	   = ccid3_hc_tx_get_info,
-	.ccid_hc_rx_getsockopt	   = ccid3_hc_rx_getsockopt,
-	.ccid_hc_tx_getsockopt	   = ccid3_hc_tx_getsockopt,
-};
-
-#ifdef CONFIG_IP_DCCP_CCID3_DEBUG
-module_param(ccid3_debug, bool, 0644);
-MODULE_PARM_DESC(ccid3_debug, "Enable CCID-3 debug messages");
-#endif
diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h
deleted file mode 100644
index 02e0fc9f6334..000000000000
--- a/net/dccp/ccids/ccid3.h
+++ /dev/null
@@ -1,148 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand.
- *  Copyright (c) 2007   The University of Aberdeen, Scotland, UK
- *
- *  An implementation of the DCCP protocol
- *
- *  This code has been developed by the University of Waikato WAND
- *  research group. For further information please see https://www.wand.net.nz/
- *  or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz
- *
- *  This code also uses code from Lulea University, rereleased as GPL by its
- *  authors:
- *  Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
- *
- *  Changes to meet Linux coding standards, to make it meet latest ccid3 draft
- *  and to make it work as a loadable module in the DCCP stack written by
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>.
- *
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-#ifndef _DCCP_CCID3_H_
-#define _DCCP_CCID3_H_
-
-#include <linux/ktime.h>
-#include <linux/list.h>
-#include <linux/types.h>
-#include <linux/tfrc.h>
-#include "lib/tfrc.h"
-#include "../ccid.h"
-
-/* Two seconds as per RFC 5348, 4.2 */
-#define TFRC_INITIAL_TIMEOUT	   (2 * USEC_PER_SEC)
-
-/* Parameter t_mbi from [RFC 3448, 4.3]: backoff interval in seconds */
-#define TFRC_T_MBI		   64
-
-/*
- * The t_delta parameter (RFC 5348, 8.3): delays of less than %USEC_PER_MSEC are
- * rounded down to 0, since sk_reset_timer() here uses millisecond granularity.
- * Hence we can use a constant t_delta = %USEC_PER_MSEC when HZ >= 500. A coarse
- * resolution of HZ < 500 means that the error is below one timer tick (t_gran)
- * when using the constant t_delta  =  t_gran / 2  =  %USEC_PER_SEC / (2 * HZ).
- */
-#if (HZ >= 500)
-# define TFRC_T_DELTA		   USEC_PER_MSEC
-#else
-# define TFRC_T_DELTA		   (USEC_PER_SEC / (2 * HZ))
-#endif
-
-enum ccid3_options {
-	TFRC_OPT_LOSS_EVENT_RATE = 192,
-	TFRC_OPT_LOSS_INTERVALS	 = 193,
-	TFRC_OPT_RECEIVE_RATE	 = 194,
-};
-
-/* TFRC sender states */
-enum ccid3_hc_tx_states {
-	TFRC_SSTATE_NO_SENT = 1,
-	TFRC_SSTATE_NO_FBACK,
-	TFRC_SSTATE_FBACK,
-};
-
-/**
- * struct ccid3_hc_tx_sock - CCID3 sender half-connection socket
- * @tx_x:		  Current sending rate in 64 * bytes per second
- * @tx_x_recv:		  Receive rate in 64 * bytes per second
- * @tx_x_calc:		  Calculated rate in bytes per second
- * @tx_rtt:		  Estimate of current round trip time in usecs
- * @tx_p:		  Current loss event rate (0-1) scaled by 1000000
- * @tx_s:		  Packet size in bytes
- * @tx_t_rto:		  Nofeedback Timer setting in usecs
- * @tx_t_ipi:		  Interpacket (send) interval (RFC 3448, 4.6) in usecs
- * @tx_state:		  Sender state, one of %ccid3_hc_tx_states
- * @tx_last_win_count:	  Last window counter sent
- * @tx_t_last_win_count:  Timestamp of earliest packet
- *			  with last_win_count value sent
- * @tx_no_feedback_timer: Handle to no feedback timer
- * @tx_t_ld:		  Time last doubled during slow start
- * @tx_t_nom:		  Nominal send time of next packet
- * @tx_hist:		  Packet history
- */
-struct ccid3_hc_tx_sock {
-	u64				tx_x;
-	u64				tx_x_recv;
-	u32				tx_x_calc;
-	u32				tx_rtt;
-	u32				tx_p;
-	u32				tx_t_rto;
-	u32				tx_t_ipi;
-	u16				tx_s;
-	enum ccid3_hc_tx_states		tx_state:8;
-	u8				tx_last_win_count;
-	ktime_t				tx_t_last_win_count;
-	struct timer_list		tx_no_feedback_timer;
-	struct sock			*sk;
-	ktime_t				tx_t_ld;
-	ktime_t				tx_t_nom;
-	struct tfrc_tx_hist_entry	*tx_hist;
-};
-
-static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk)
-{
-	struct ccid3_hc_tx_sock *hctx = ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid);
-	BUG_ON(hctx == NULL);
-	return hctx;
-}
-
-/* TFRC receiver states */
-enum ccid3_hc_rx_states {
-	TFRC_RSTATE_NO_DATA = 1,
-	TFRC_RSTATE_DATA,
-};
-
-/**
- * struct ccid3_hc_rx_sock - CCID3 receiver half-connection socket
- * @rx_last_counter:	     Tracks window counter (RFC 4342, 8.1)
- * @rx_state:		     Receiver state, one of %ccid3_hc_rx_states
- * @rx_bytes_recv:	     Total sum of DCCP payload bytes
- * @rx_x_recv:		     Receiver estimate of send rate (RFC 3448, sec. 4.3)
- * @rx_rtt:		     Receiver estimate of RTT
- * @rx_tstamp_last_feedback: Time at which last feedback was sent
- * @rx_hist:		     Packet history (loss detection + RTT sampling)
- * @rx_li_hist:		     Loss Interval database
- * @rx_s:		     Received packet size in bytes
- * @rx_pinv:		     Inverse of Loss Event Rate (RFC 4342, sec. 8.5)
- */
-struct ccid3_hc_rx_sock {
-	u8				rx_last_counter:4;
-	enum ccid3_hc_rx_states		rx_state:8;
-	u32				rx_bytes_recv;
-	u32				rx_x_recv;
-	u32				rx_rtt;
-	ktime_t				rx_tstamp_last_feedback;
-	struct tfrc_rx_hist		rx_hist;
-	struct tfrc_loss_hist		rx_li_hist;
-	u16				rx_s;
-#define rx_pinv				rx_li_hist.i_mean
-};
-
-static inline struct ccid3_hc_rx_sock *ccid3_hc_rx_sk(const struct sock *sk)
-{
-	struct ccid3_hc_rx_sock *hcrx = ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid);
-	BUG_ON(hcrx == NULL);
-	return hcrx;
-}
-
-#endif /* _DCCP_CCID3_H_ */
diff --git a/net/dccp/ccids/lib/loss_interval.c b/net/dccp/ccids/lib/loss_interval.c
deleted file mode 100644
index da95319842bb..000000000000
--- a/net/dccp/ccids/lib/loss_interval.c
+++ /dev/null
@@ -1,184 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  Copyright (c) 2007   The University of Aberdeen, Scotland, UK
- *  Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand.
- *  Copyright (c) 2005-7 Ian McDonald <ian.mcdonald@jandi.co.nz>
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-#include <net/sock.h>
-#include "tfrc.h"
-
-static struct kmem_cache  *tfrc_lh_slab  __read_mostly;
-/* Loss Interval weights from [RFC 3448, 5.4], scaled by 10 */
-static const int tfrc_lh_weights[NINTERVAL] = { 10, 10, 10, 10, 8, 6, 4, 2 };
-
-/* implements LIFO semantics on the array */
-static inline u8 LIH_INDEX(const u8 ctr)
-{
-	return LIH_SIZE - 1 - (ctr % LIH_SIZE);
-}
-
-/* the `counter' index always points at the next entry to be populated */
-static inline struct tfrc_loss_interval *tfrc_lh_peek(struct tfrc_loss_hist *lh)
-{
-	return lh->counter ? lh->ring[LIH_INDEX(lh->counter - 1)] : NULL;
-}
-
-/* given i with 0 <= i <= k, return I_i as per the rfc3448bis notation */
-static inline u32 tfrc_lh_get_interval(struct tfrc_loss_hist *lh, const u8 i)
-{
-	BUG_ON(i >= lh->counter);
-	return lh->ring[LIH_INDEX(lh->counter - i - 1)]->li_length;
-}
-
-/*
- *	On-demand allocation and de-allocation of entries
- */
-static struct tfrc_loss_interval *tfrc_lh_demand_next(struct tfrc_loss_hist *lh)
-{
-	if (lh->ring[LIH_INDEX(lh->counter)] == NULL)
-		lh->ring[LIH_INDEX(lh->counter)] = kmem_cache_alloc(tfrc_lh_slab,
-								    GFP_ATOMIC);
-	return lh->ring[LIH_INDEX(lh->counter)];
-}
-
-void tfrc_lh_cleanup(struct tfrc_loss_hist *lh)
-{
-	if (!tfrc_lh_is_initialised(lh))
-		return;
-
-	for (lh->counter = 0; lh->counter < LIH_SIZE; lh->counter++)
-		if (lh->ring[LIH_INDEX(lh->counter)] != NULL) {
-			kmem_cache_free(tfrc_lh_slab,
-					lh->ring[LIH_INDEX(lh->counter)]);
-			lh->ring[LIH_INDEX(lh->counter)] = NULL;
-		}
-}
-
-static void tfrc_lh_calc_i_mean(struct tfrc_loss_hist *lh)
-{
-	u32 i_i, i_tot0 = 0, i_tot1 = 0, w_tot = 0;
-	int i, k = tfrc_lh_length(lh) - 1; /* k is as in rfc3448bis, 5.4 */
-
-	if (k <= 0)
-		return;
-
-	for (i = 0; i <= k; i++) {
-		i_i = tfrc_lh_get_interval(lh, i);
-
-		if (i < k) {
-			i_tot0 += i_i * tfrc_lh_weights[i];
-			w_tot  += tfrc_lh_weights[i];
-		}
-		if (i > 0)
-			i_tot1 += i_i * tfrc_lh_weights[i-1];
-	}
-
-	lh->i_mean = max(i_tot0, i_tot1) / w_tot;
-}
-
-/**
- * tfrc_lh_update_i_mean  -  Update the `open' loss interval I_0
- * @lh: histogram to update
- * @skb: received socket triggering loss interval update
- *
- * For recomputing p: returns `true' if p > p_prev  <=>  1/p < 1/p_prev
- */
-u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *skb)
-{
-	struct tfrc_loss_interval *cur = tfrc_lh_peek(lh);
-	u32 old_i_mean = lh->i_mean;
-	s64 len;
-
-	if (cur == NULL)			/* not initialised */
-		return 0;
-
-	len = dccp_delta_seqno(cur->li_seqno, DCCP_SKB_CB(skb)->dccpd_seq) + 1;
-
-	if (len - (s64)cur->li_length <= 0)	/* duplicate or reordered */
-		return 0;
-
-	if (SUB16(dccp_hdr(skb)->dccph_ccval, cur->li_ccval) > 4)
-		/*
-		 * Implements RFC 4342, 10.2:
-		 * If a packet S (skb) exists whose seqno comes `after' the one
-		 * starting the current loss interval (cur) and if the modulo-16
-		 * distance from C(cur) to C(S) is greater than 4, consider all
-		 * subsequent packets as belonging to a new loss interval. This
-		 * test is necessary since CCVal may wrap between intervals.
-		 */
-		cur->li_is_closed = 1;
-
-	if (tfrc_lh_length(lh) == 1)		/* due to RFC 3448, 6.3.1 */
-		return 0;
-
-	cur->li_length = len;
-	tfrc_lh_calc_i_mean(lh);
-
-	return lh->i_mean < old_i_mean;
-}
-
-/* Determine if `new_loss' does begin a new loss interval [RFC 4342, 10.2] */
-static inline u8 tfrc_lh_is_new_loss(struct tfrc_loss_interval *cur,
-				     struct tfrc_rx_hist_entry *new_loss)
-{
-	return	dccp_delta_seqno(cur->li_seqno, new_loss->tfrchrx_seqno) > 0 &&
-		(cur->li_is_closed || SUB16(new_loss->tfrchrx_ccval, cur->li_ccval) > 4);
-}
-
-/**
- * tfrc_lh_interval_add  -  Insert new record into the Loss Interval database
- * @lh:		   Loss Interval database
- * @rh:		   Receive history containing a fresh loss event
- * @calc_first_li: Caller-dependent routine to compute length of first interval
- * @sk:		   Used by @calc_first_li in caller-specific way (subtyping)
- *
- * Updates I_mean and returns 1 if a new interval has in fact been added to @lh.
- */
-int tfrc_lh_interval_add(struct tfrc_loss_hist *lh, struct tfrc_rx_hist *rh,
-			 u32 (*calc_first_li)(struct sock *), struct sock *sk)
-{
-	struct tfrc_loss_interval *cur = tfrc_lh_peek(lh), *new;
-
-	if (cur != NULL && !tfrc_lh_is_new_loss(cur, tfrc_rx_hist_loss_prev(rh)))
-		return 0;
-
-	new = tfrc_lh_demand_next(lh);
-	if (unlikely(new == NULL)) {
-		DCCP_CRIT("Cannot allocate/add loss record.");
-		return 0;
-	}
-
-	new->li_seqno	  = tfrc_rx_hist_loss_prev(rh)->tfrchrx_seqno;
-	new->li_ccval	  = tfrc_rx_hist_loss_prev(rh)->tfrchrx_ccval;
-	new->li_is_closed = 0;
-
-	if (++lh->counter == 1)
-		lh->i_mean = new->li_length = (*calc_first_li)(sk);
-	else {
-		cur->li_length = dccp_delta_seqno(cur->li_seqno, new->li_seqno);
-		new->li_length = dccp_delta_seqno(new->li_seqno,
-				  tfrc_rx_hist_last_rcv(rh)->tfrchrx_seqno) + 1;
-		if (lh->counter > (2*LIH_SIZE))
-			lh->counter -= LIH_SIZE;
-
-		tfrc_lh_calc_i_mean(lh);
-	}
-	return 1;
-}
-
-int __init tfrc_li_init(void)
-{
-	tfrc_lh_slab = kmem_cache_create("tfrc_li_hist",
-					 sizeof(struct tfrc_loss_interval), 0,
-					 SLAB_HWCACHE_ALIGN, NULL);
-	return tfrc_lh_slab == NULL ? -ENOBUFS : 0;
-}
-
-void tfrc_li_exit(void)
-{
-	if (tfrc_lh_slab != NULL) {
-		kmem_cache_destroy(tfrc_lh_slab);
-		tfrc_lh_slab = NULL;
-	}
-}
diff --git a/net/dccp/ccids/lib/loss_interval.h b/net/dccp/ccids/lib/loss_interval.h
deleted file mode 100644
index c3d95f85e43b..000000000000
--- a/net/dccp/ccids/lib/loss_interval.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _DCCP_LI_HIST_
-#define _DCCP_LI_HIST_
-/*
- *  Copyright (c) 2007   The University of Aberdeen, Scotland, UK
- *  Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand.
- *  Copyright (c) 2005-7 Ian McDonald <ian.mcdonald@jandi.co.nz>
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-#include <linux/ktime.h>
-#include <linux/list.h>
-#include <linux/slab.h>
-
-/*
- * Number of loss intervals (RFC 4342, 8.6.1). The history size is one more than
- * NINTERVAL, since the `open' interval I_0 is always stored as the first entry.
- */
-#define NINTERVAL	8
-#define LIH_SIZE	(NINTERVAL + 1)
-
-/**
- *  tfrc_loss_interval  -  Loss history record for TFRC-based protocols
- *  @li_seqno:		Highest received seqno before the start of loss
- *  @li_ccval:		The CCVal belonging to @li_seqno
- *  @li_is_closed:	Whether @li_seqno is older than 1 RTT
- *  @li_length:		Loss interval sequence length
- */
-struct tfrc_loss_interval {
-	u64		 li_seqno:48,
-			 li_ccval:4,
-			 li_is_closed:1;
-	u32		 li_length;
-};
-
-/**
- *  tfrc_loss_hist  -  Loss record database
- *  @ring:	Circular queue managed in LIFO manner
- *  @counter:	Current count of entries (can be more than %LIH_SIZE)
- *  @i_mean:	Current Average Loss Interval [RFC 3448, 5.4]
- */
-struct tfrc_loss_hist {
-	struct tfrc_loss_interval	*ring[LIH_SIZE];
-	u8				counter;
-	u32				i_mean;
-};
-
-static inline void tfrc_lh_init(struct tfrc_loss_hist *lh)
-{
-	memset(lh, 0, sizeof(struct tfrc_loss_hist));
-}
-
-static inline u8 tfrc_lh_is_initialised(struct tfrc_loss_hist *lh)
-{
-	return lh->counter > 0;
-}
-
-static inline u8 tfrc_lh_length(struct tfrc_loss_hist *lh)
-{
-	return min(lh->counter, (u8)LIH_SIZE);
-}
-
-struct tfrc_rx_hist;
-
-int tfrc_lh_interval_add(struct tfrc_loss_hist *, struct tfrc_rx_hist *,
-			 u32 (*first_li)(struct sock *), struct sock *);
-u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *);
-void tfrc_lh_cleanup(struct tfrc_loss_hist *lh);
-
-#endif /* _DCCP_LI_HIST_ */
diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c
deleted file mode 100644
index 0cdda3c66fb5..000000000000
--- a/net/dccp/ccids/lib/packet_history.c
+++ /dev/null
@@ -1,439 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  Copyright (c) 2007   The University of Aberdeen, Scotland, UK
- *  Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand.
- *
- *  An implementation of the DCCP protocol
- *
- *  This code has been developed by the University of Waikato WAND
- *  research group. For further information please see https://www.wand.net.nz/
- *  or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz
- *
- *  This code also uses code from Lulea University, rereleased as GPL by its
- *  authors:
- *  Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
- *
- *  Changes to meet Linux coding standards, to make it meet latest ccid3 draft
- *  and to make it work as a loadable module in the DCCP stack written by
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>.
- *
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-
-#include <linux/string.h>
-#include <linux/slab.h>
-#include "packet_history.h"
-#include "../../dccp.h"
-
-/*
- * Transmitter History Routines
- */
-static struct kmem_cache *tfrc_tx_hist_slab;
-
-int __init tfrc_tx_packet_history_init(void)
-{
-	tfrc_tx_hist_slab = kmem_cache_create("tfrc_tx_hist",
-					      sizeof(struct tfrc_tx_hist_entry),
-					      0, SLAB_HWCACHE_ALIGN, NULL);
-	return tfrc_tx_hist_slab == NULL ? -ENOBUFS : 0;
-}
-
-void tfrc_tx_packet_history_exit(void)
-{
-	if (tfrc_tx_hist_slab != NULL) {
-		kmem_cache_destroy(tfrc_tx_hist_slab);
-		tfrc_tx_hist_slab = NULL;
-	}
-}
-
-int tfrc_tx_hist_add(struct tfrc_tx_hist_entry **headp, u64 seqno)
-{
-	struct tfrc_tx_hist_entry *entry = kmem_cache_alloc(tfrc_tx_hist_slab, gfp_any());
-
-	if (entry == NULL)
-		return -ENOBUFS;
-	entry->seqno = seqno;
-	entry->stamp = ktime_get_real();
-	entry->next  = *headp;
-	*headp	     = entry;
-	return 0;
-}
-
-void tfrc_tx_hist_purge(struct tfrc_tx_hist_entry **headp)
-{
-	struct tfrc_tx_hist_entry *head = *headp;
-
-	while (head != NULL) {
-		struct tfrc_tx_hist_entry *next = head->next;
-
-		kmem_cache_free(tfrc_tx_hist_slab, head);
-		head = next;
-	}
-
-	*headp = NULL;
-}
-
-/*
- *	Receiver History Routines
- */
-static struct kmem_cache *tfrc_rx_hist_slab;
-
-int __init tfrc_rx_packet_history_init(void)
-{
-	tfrc_rx_hist_slab = kmem_cache_create("tfrc_rxh_cache",
-					      sizeof(struct tfrc_rx_hist_entry),
-					      0, SLAB_HWCACHE_ALIGN, NULL);
-	return tfrc_rx_hist_slab == NULL ? -ENOBUFS : 0;
-}
-
-void tfrc_rx_packet_history_exit(void)
-{
-	if (tfrc_rx_hist_slab != NULL) {
-		kmem_cache_destroy(tfrc_rx_hist_slab);
-		tfrc_rx_hist_slab = NULL;
-	}
-}
-
-static inline void tfrc_rx_hist_entry_from_skb(struct tfrc_rx_hist_entry *entry,
-					       const struct sk_buff *skb,
-					       const u64 ndp)
-{
-	const struct dccp_hdr *dh = dccp_hdr(skb);
-
-	entry->tfrchrx_seqno = DCCP_SKB_CB(skb)->dccpd_seq;
-	entry->tfrchrx_ccval = dh->dccph_ccval;
-	entry->tfrchrx_type  = dh->dccph_type;
-	entry->tfrchrx_ndp   = ndp;
-	entry->tfrchrx_tstamp = ktime_get_real();
-}
-
-void tfrc_rx_hist_add_packet(struct tfrc_rx_hist *h,
-			     const struct sk_buff *skb,
-			     const u64 ndp)
-{
-	struct tfrc_rx_hist_entry *entry = tfrc_rx_hist_last_rcv(h);
-
-	tfrc_rx_hist_entry_from_skb(entry, skb, ndp);
-}
-
-/* has the packet contained in skb been seen before? */
-int tfrc_rx_hist_duplicate(struct tfrc_rx_hist *h, struct sk_buff *skb)
-{
-	const u64 seq = DCCP_SKB_CB(skb)->dccpd_seq;
-	int i;
-
-	if (dccp_delta_seqno(tfrc_rx_hist_loss_prev(h)->tfrchrx_seqno, seq) <= 0)
-		return 1;
-
-	for (i = 1; i <= h->loss_count; i++)
-		if (tfrc_rx_hist_entry(h, i)->tfrchrx_seqno == seq)
-			return 1;
-
-	return 0;
-}
-
-static void tfrc_rx_hist_swap(struct tfrc_rx_hist *h, const u8 a, const u8 b)
-{
-	const u8 idx_a = tfrc_rx_hist_index(h, a),
-		 idx_b = tfrc_rx_hist_index(h, b);
-
-	swap(h->ring[idx_a], h->ring[idx_b]);
-}
-
-/*
- * Private helper functions for loss detection.
- *
- * In the descriptions, `Si' refers to the sequence number of entry number i,
- * whose NDP count is `Ni' (lower case is used for variables).
- * Note: All __xxx_loss functions expect that a test against duplicates has been
- *       performed already: the seqno of the skb must not be less than the seqno
- *       of loss_prev; and it must not equal that of any valid history entry.
- */
-static void __do_track_loss(struct tfrc_rx_hist *h, struct sk_buff *skb, u64 n1)
-{
-	u64 s0 = tfrc_rx_hist_loss_prev(h)->tfrchrx_seqno,
-	    s1 = DCCP_SKB_CB(skb)->dccpd_seq;
-
-	if (!dccp_loss_free(s0, s1, n1)) {	/* gap between S0 and S1 */
-		h->loss_count = 1;
-		tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_entry(h, 1), skb, n1);
-	}
-}
-
-static void __one_after_loss(struct tfrc_rx_hist *h, struct sk_buff *skb, u32 n2)
-{
-	u64 s0 = tfrc_rx_hist_loss_prev(h)->tfrchrx_seqno,
-	    s1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_seqno,
-	    s2 = DCCP_SKB_CB(skb)->dccpd_seq;
-
-	if (likely(dccp_delta_seqno(s1, s2) > 0)) {	/* S1  <  S2 */
-		h->loss_count = 2;
-		tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_entry(h, 2), skb, n2);
-		return;
-	}
-
-	/* S0  <  S2  <  S1 */
-
-	if (dccp_loss_free(s0, s2, n2)) {
-		u64 n1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_ndp;
-
-		if (dccp_loss_free(s2, s1, n1)) {
-			/* hole is filled: S0, S2, and S1 are consecutive */
-			h->loss_count = 0;
-			h->loss_start = tfrc_rx_hist_index(h, 1);
-		} else
-			/* gap between S2 and S1: just update loss_prev */
-			tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_loss_prev(h), skb, n2);
-
-	} else {	/* gap between S0 and S2 */
-		/*
-		 * Reorder history to insert S2 between S0 and S1
-		 */
-		tfrc_rx_hist_swap(h, 0, 3);
-		h->loss_start = tfrc_rx_hist_index(h, 3);
-		tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_entry(h, 1), skb, n2);
-		h->loss_count = 2;
-	}
-}
-
-/* return 1 if a new loss event has been identified */
-static int __two_after_loss(struct tfrc_rx_hist *h, struct sk_buff *skb, u32 n3)
-{
-	u64 s0 = tfrc_rx_hist_loss_prev(h)->tfrchrx_seqno,
-	    s1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_seqno,
-	    s2 = tfrc_rx_hist_entry(h, 2)->tfrchrx_seqno,
-	    s3 = DCCP_SKB_CB(skb)->dccpd_seq;
-
-	if (likely(dccp_delta_seqno(s2, s3) > 0)) {	/* S2  <  S3 */
-		h->loss_count = 3;
-		tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_entry(h, 3), skb, n3);
-		return 1;
-	}
-
-	/* S3  <  S2 */
-
-	if (dccp_delta_seqno(s1, s3) > 0) {		/* S1  <  S3  <  S2 */
-		/*
-		 * Reorder history to insert S3 between S1 and S2
-		 */
-		tfrc_rx_hist_swap(h, 2, 3);
-		tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_entry(h, 2), skb, n3);
-		h->loss_count = 3;
-		return 1;
-	}
-
-	/* S0  <  S3  <  S1 */
-
-	if (dccp_loss_free(s0, s3, n3)) {
-		u64 n1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_ndp;
-
-		if (dccp_loss_free(s3, s1, n1)) {
-			/* hole between S0 and S1 filled by S3 */
-			u64 n2 = tfrc_rx_hist_entry(h, 2)->tfrchrx_ndp;
-
-			if (dccp_loss_free(s1, s2, n2)) {
-				/* entire hole filled by S0, S3, S1, S2 */
-				h->loss_start = tfrc_rx_hist_index(h, 2);
-				h->loss_count = 0;
-			} else {
-				/* gap remains between S1 and S2 */
-				h->loss_start = tfrc_rx_hist_index(h, 1);
-				h->loss_count = 1;
-			}
-
-		} else /* gap exists between S3 and S1, loss_count stays at 2 */
-			tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_loss_prev(h), skb, n3);
-
-		return 0;
-	}
-
-	/*
-	 * The remaining case:  S0  <  S3  <  S1  <  S2;  gap between S0 and S3
-	 * Reorder history to insert S3 between S0 and S1.
-	 */
-	tfrc_rx_hist_swap(h, 0, 3);
-	h->loss_start = tfrc_rx_hist_index(h, 3);
-	tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_entry(h, 1), skb, n3);
-	h->loss_count = 3;
-
-	return 1;
-}
-
-/* recycle RX history records to continue loss detection if necessary */
-static void __three_after_loss(struct tfrc_rx_hist *h)
-{
-	/*
-	 * At this stage we know already that there is a gap between S0 and S1
-	 * (since S0 was the highest sequence number received before detecting
-	 * the loss). To recycle the loss record, it is	thus only necessary to
-	 * check for other possible gaps between S1/S2 and between S2/S3.
-	 */
-	u64 s1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_seqno,
-	    s2 = tfrc_rx_hist_entry(h, 2)->tfrchrx_seqno,
-	    s3 = tfrc_rx_hist_entry(h, 3)->tfrchrx_seqno;
-	u64 n2 = tfrc_rx_hist_entry(h, 2)->tfrchrx_ndp,
-	    n3 = tfrc_rx_hist_entry(h, 3)->tfrchrx_ndp;
-
-	if (dccp_loss_free(s1, s2, n2)) {
-
-		if (dccp_loss_free(s2, s3, n3)) {
-			/* no gap between S2 and S3: entire hole is filled */
-			h->loss_start = tfrc_rx_hist_index(h, 3);
-			h->loss_count = 0;
-		} else {
-			/* gap between S2 and S3 */
-			h->loss_start = tfrc_rx_hist_index(h, 2);
-			h->loss_count = 1;
-		}
-
-	} else {	/* gap between S1 and S2 */
-		h->loss_start = tfrc_rx_hist_index(h, 1);
-		h->loss_count = 2;
-	}
-}
-
-/**
- *  tfrc_rx_handle_loss  -  Loss detection and further processing
- *  @h:		    The non-empty RX history object
- *  @lh:	    Loss Intervals database to update
- *  @skb:	    Currently received packet
- *  @ndp:	    The NDP count belonging to @skb
- *  @calc_first_li: Caller-dependent computation of first loss interval in @lh
- *  @sk:	    Used by @calc_first_li (see tfrc_lh_interval_add)
- *
- *  Chooses action according to pending loss, updates LI database when a new
- *  loss was detected, and does required post-processing. Returns 1 when caller
- *  should send feedback, 0 otherwise.
- *  Since it also takes care of reordering during loss detection and updates the
- *  records accordingly, the caller should not perform any more RX history
- *  operations when loss_count is greater than 0 after calling this function.
- */
-int tfrc_rx_handle_loss(struct tfrc_rx_hist *h,
-			struct tfrc_loss_hist *lh,
-			struct sk_buff *skb, const u64 ndp,
-			u32 (*calc_first_li)(struct sock *), struct sock *sk)
-{
-	int is_new_loss = 0;
-
-	if (h->loss_count == 0) {
-		__do_track_loss(h, skb, ndp);
-	} else if (h->loss_count == 1) {
-		__one_after_loss(h, skb, ndp);
-	} else if (h->loss_count != 2) {
-		DCCP_BUG("invalid loss_count %d", h->loss_count);
-	} else if (__two_after_loss(h, skb, ndp)) {
-		/*
-		 * Update Loss Interval database and recycle RX records
-		 */
-		is_new_loss = tfrc_lh_interval_add(lh, h, calc_first_li, sk);
-		__three_after_loss(h);
-	}
-	return is_new_loss;
-}
-
-int tfrc_rx_hist_alloc(struct tfrc_rx_hist *h)
-{
-	int i;
-
-	for (i = 0; i <= TFRC_NDUPACK; i++) {
-		h->ring[i] = kmem_cache_alloc(tfrc_rx_hist_slab, GFP_ATOMIC);
-		if (h->ring[i] == NULL)
-			goto out_free;
-	}
-
-	h->loss_count = h->loss_start = 0;
-	return 0;
-
-out_free:
-	while (i-- != 0) {
-		kmem_cache_free(tfrc_rx_hist_slab, h->ring[i]);
-		h->ring[i] = NULL;
-	}
-	return -ENOBUFS;
-}
-
-void tfrc_rx_hist_purge(struct tfrc_rx_hist *h)
-{
-	int i;
-
-	for (i = 0; i <= TFRC_NDUPACK; ++i)
-		if (h->ring[i] != NULL) {
-			kmem_cache_free(tfrc_rx_hist_slab, h->ring[i]);
-			h->ring[i] = NULL;
-		}
-}
-
-/**
- * tfrc_rx_hist_rtt_last_s - reference entry to compute RTT samples against
- * @h:	The non-empty RX history object
- */
-static inline struct tfrc_rx_hist_entry *
-			tfrc_rx_hist_rtt_last_s(const struct tfrc_rx_hist *h)
-{
-	return h->ring[0];
-}
-
-/**
- * tfrc_rx_hist_rtt_prev_s - previously suitable (wrt rtt_last_s) RTT-sampling entry
- * @h:	The non-empty RX history object
- */
-static inline struct tfrc_rx_hist_entry *
-			tfrc_rx_hist_rtt_prev_s(const struct tfrc_rx_hist *h)
-{
-	return h->ring[h->rtt_sample_prev];
-}
-
-/**
- * tfrc_rx_hist_sample_rtt  -  Sample RTT from timestamp / CCVal
- * @h: receive histogram
- * @skb: packet containing timestamp.
- *
- * Based on ideas presented in RFC 4342, 8.1. Returns 0 if it was not able
- * to compute a sample with given data - calling function should check this.
- */
-u32 tfrc_rx_hist_sample_rtt(struct tfrc_rx_hist *h, const struct sk_buff *skb)
-{
-	u32 sample = 0,
-	    delta_v = SUB16(dccp_hdr(skb)->dccph_ccval,
-			    tfrc_rx_hist_rtt_last_s(h)->tfrchrx_ccval);
-
-	if (delta_v < 1 || delta_v > 4) {	/* unsuitable CCVal delta */
-		if (h->rtt_sample_prev == 2) {	/* previous candidate stored */
-			sample = SUB16(tfrc_rx_hist_rtt_prev_s(h)->tfrchrx_ccval,
-				       tfrc_rx_hist_rtt_last_s(h)->tfrchrx_ccval);
-			if (sample)
-				sample = 4 / sample *
-				         ktime_us_delta(tfrc_rx_hist_rtt_prev_s(h)->tfrchrx_tstamp,
-							tfrc_rx_hist_rtt_last_s(h)->tfrchrx_tstamp);
-			else    /*
-				 * FIXME: This condition is in principle not
-				 * possible but occurs when CCID is used for
-				 * two-way data traffic. I have tried to trace
-				 * it, but the cause does not seem to be here.
-				 */
-				DCCP_BUG("please report to dccp@vger.kernel.org"
-					 " => prev = %u, last = %u",
-					 tfrc_rx_hist_rtt_prev_s(h)->tfrchrx_ccval,
-					 tfrc_rx_hist_rtt_last_s(h)->tfrchrx_ccval);
-		} else if (delta_v < 1) {
-			h->rtt_sample_prev = 1;
-			goto keep_ref_for_next_time;
-		}
-
-	} else if (delta_v == 4) /* optimal match */
-		sample = ktime_to_us(net_timedelta(tfrc_rx_hist_rtt_last_s(h)->tfrchrx_tstamp));
-	else {			 /* suboptimal match */
-		h->rtt_sample_prev = 2;
-		goto keep_ref_for_next_time;
-	}
-
-	if (unlikely(sample > DCCP_SANE_RTT_MAX)) {
-		DCCP_WARN("RTT sample %u too large, using max\n", sample);
-		sample = DCCP_SANE_RTT_MAX;
-	}
-
-	h->rtt_sample_prev = 0;	       /* use current entry as next reference */
-keep_ref_for_next_time:
-
-	return sample;
-}
diff --git a/net/dccp/ccids/lib/packet_history.h b/net/dccp/ccids/lib/packet_history.h
deleted file mode 100644
index 159cc9326eab..000000000000
--- a/net/dccp/ccids/lib/packet_history.h
+++ /dev/null
@@ -1,142 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  Packet RX/TX history data structures and routines for TFRC-based protocols.
- *
- *  Copyright (c) 2007   The University of Aberdeen, Scotland, UK
- *  Copyright (c) 2005-6 The University of Waikato, Hamilton, New Zealand.
- *
- *  This code has been developed by the University of Waikato WAND
- *  research group. For further information please see https://www.wand.net.nz/
- *  or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz
- *
- *  This code also uses code from Lulea University, rereleased as GPL by its
- *  authors:
- *  Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
- *
- *  Changes to meet Linux coding standards, to make it meet latest ccid3 draft
- *  and to make it work as a loadable module in the DCCP stack written by
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>.
- *
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-
-#ifndef _DCCP_PKT_HIST_
-#define _DCCP_PKT_HIST_
-
-#include <linux/list.h>
-#include <linux/slab.h>
-#include "tfrc.h"
-
-/**
- *  tfrc_tx_hist_entry  -  Simple singly-linked TX history list
- *  @next:  next oldest entry (LIFO order)
- *  @seqno: sequence number of this entry
- *  @stamp: send time of packet with sequence number @seqno
- */
-struct tfrc_tx_hist_entry {
-	struct tfrc_tx_hist_entry *next;
-	u64			  seqno;
-	ktime_t			  stamp;
-};
-
-static inline struct tfrc_tx_hist_entry *
-	tfrc_tx_hist_find_entry(struct tfrc_tx_hist_entry *head, u64 seqno)
-{
-	while (head != NULL && head->seqno != seqno)
-		head = head->next;
-	return head;
-}
-
-int tfrc_tx_hist_add(struct tfrc_tx_hist_entry **headp, u64 seqno);
-void tfrc_tx_hist_purge(struct tfrc_tx_hist_entry **headp);
-
-/* Subtraction a-b modulo-16, respects circular wrap-around */
-#define SUB16(a, b) (((a) + 16 - (b)) & 0xF)
-
-/* Number of packets to wait after a missing packet (RFC 4342, 6.1) */
-#define TFRC_NDUPACK 3
-
-/**
- * tfrc_rx_hist_entry - Store information about a single received packet
- * @tfrchrx_seqno:	DCCP packet sequence number
- * @tfrchrx_ccval:	window counter value of packet (RFC 4342, 8.1)
- * @tfrchrx_ndp:	the NDP count (if any) of the packet
- * @tfrchrx_tstamp:	actual receive time of packet
- */
-struct tfrc_rx_hist_entry {
-	u64		 tfrchrx_seqno:48,
-			 tfrchrx_ccval:4,
-			 tfrchrx_type:4;
-	u64		 tfrchrx_ndp:48;
-	ktime_t		 tfrchrx_tstamp;
-};
-
-/**
- * tfrc_rx_hist  -  RX history structure for TFRC-based protocols
- * @ring:		Packet history for RTT sampling and loss detection
- * @loss_count:		Number of entries in circular history
- * @loss_start:		Movable index (for loss detection)
- * @rtt_sample_prev:	Used during RTT sampling, points to candidate entry
- */
-struct tfrc_rx_hist {
-	struct tfrc_rx_hist_entry *ring[TFRC_NDUPACK + 1];
-	u8			  loss_count:2,
-				  loss_start:2;
-#define rtt_sample_prev		  loss_start
-};
-
-/**
- * tfrc_rx_hist_index - index to reach n-th entry after loss_start
- */
-static inline u8 tfrc_rx_hist_index(const struct tfrc_rx_hist *h, const u8 n)
-{
-	return (h->loss_start + n) & TFRC_NDUPACK;
-}
-
-/**
- * tfrc_rx_hist_last_rcv - entry with highest-received-seqno so far
- */
-static inline struct tfrc_rx_hist_entry *
-			tfrc_rx_hist_last_rcv(const struct tfrc_rx_hist *h)
-{
-	return h->ring[tfrc_rx_hist_index(h, h->loss_count)];
-}
-
-/**
- * tfrc_rx_hist_entry - return the n-th history entry after loss_start
- */
-static inline struct tfrc_rx_hist_entry *
-			tfrc_rx_hist_entry(const struct tfrc_rx_hist *h, const u8 n)
-{
-	return h->ring[tfrc_rx_hist_index(h, n)];
-}
-
-/**
- * tfrc_rx_hist_loss_prev - entry with highest-received-seqno before loss was detected
- */
-static inline struct tfrc_rx_hist_entry *
-			tfrc_rx_hist_loss_prev(const struct tfrc_rx_hist *h)
-{
-	return h->ring[h->loss_start];
-}
-
-/* indicate whether previously a packet was detected missing */
-static inline bool tfrc_rx_hist_loss_pending(const struct tfrc_rx_hist *h)
-{
-	return h->loss_count > 0;
-}
-
-void tfrc_rx_hist_add_packet(struct tfrc_rx_hist *h, const struct sk_buff *skb,
-			     const u64 ndp);
-
-int tfrc_rx_hist_duplicate(struct tfrc_rx_hist *h, struct sk_buff *skb);
-
-struct tfrc_loss_hist;
-int tfrc_rx_handle_loss(struct tfrc_rx_hist *h, struct tfrc_loss_hist *lh,
-			struct sk_buff *skb, const u64 ndp,
-			u32 (*first_li)(struct sock *sk), struct sock *sk);
-u32 tfrc_rx_hist_sample_rtt(struct tfrc_rx_hist *h, const struct sk_buff *skb);
-int tfrc_rx_hist_alloc(struct tfrc_rx_hist *h);
-void tfrc_rx_hist_purge(struct tfrc_rx_hist *h);
-
-#endif /* _DCCP_PKT_HIST_ */
diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c
deleted file mode 100644
index d7f265e1f50c..000000000000
--- a/net/dccp/ccids/lib/tfrc.c
+++ /dev/null
@@ -1,46 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * TFRC library initialisation
- *
- * Copyright (c) 2007 The University of Aberdeen, Scotland, UK
- * Copyright (c) 2007 Arnaldo Carvalho de Melo <acme@redhat.com>
- */
-#include <linux/moduleparam.h>
-#include "tfrc.h"
-
-#ifdef CONFIG_IP_DCCP_TFRC_DEBUG
-bool tfrc_debug;
-module_param(tfrc_debug, bool, 0644);
-MODULE_PARM_DESC(tfrc_debug, "Enable TFRC debug messages");
-#endif
-
-int __init tfrc_lib_init(void)
-{
-	int rc = tfrc_li_init();
-
-	if (rc)
-		goto out;
-
-	rc = tfrc_tx_packet_history_init();
-	if (rc)
-		goto out_free_loss_intervals;
-
-	rc = tfrc_rx_packet_history_init();
-	if (rc)
-		goto out_free_tx_history;
-	return 0;
-
-out_free_tx_history:
-	tfrc_tx_packet_history_exit();
-out_free_loss_intervals:
-	tfrc_li_exit();
-out:
-	return rc;
-}
-
-void tfrc_lib_exit(void)
-{
-	tfrc_rx_packet_history_exit();
-	tfrc_tx_packet_history_exit();
-	tfrc_li_exit();
-}
diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h
deleted file mode 100644
index 0a63e8750cc5..000000000000
--- a/net/dccp/ccids/lib/tfrc.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _TFRC_H_
-#define _TFRC_H_
-/*
- *  Copyright (c) 2007   The University of Aberdeen, Scotland, UK
- *  Copyright (c) 2005-6 The University of Waikato, Hamilton, New Zealand.
- *  Copyright (c) 2005-6 Ian McDonald <ian.mcdonald@jandi.co.nz>
- *  Copyright (c) 2005   Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- *  Copyright (c) 2003   Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
- */
-#include <linux/types.h>
-#include <linux/math64.h>
-#include "../../dccp.h"
-
-/* internal includes that this library exports: */
-#include "loss_interval.h"
-#include "packet_history.h"
-
-#ifdef CONFIG_IP_DCCP_TFRC_DEBUG
-extern bool tfrc_debug;
-#define tfrc_pr_debug(format, a...)	DCCP_PR_DEBUG(tfrc_debug, format, ##a)
-#else
-#define tfrc_pr_debug(format, a...)
-#endif
-
-/* integer-arithmetic divisions of type (a * 1000000)/b */
-static inline u64 scaled_div(u64 a, u64 b)
-{
-	BUG_ON(b == 0);
-	return div64_u64(a * 1000000, b);
-}
-
-static inline u32 scaled_div32(u64 a, u64 b)
-{
-	u64 result = scaled_div(a, b);
-
-	if (result > UINT_MAX) {
-		DCCP_CRIT("Overflow: %llu/%llu > UINT_MAX",
-			  (unsigned long long)a, (unsigned long long)b);
-		return UINT_MAX;
-	}
-	return result;
-}
-
-/**
- * tfrc_ewma  -  Exponentially weighted moving average
- * @weight: Weight to be used as damping factor, in units of 1/10
- */
-static inline u32 tfrc_ewma(const u32 avg, const u32 newval, const u8 weight)
-{
-	return avg ? (weight * avg + (10 - weight) * newval) / 10 : newval;
-}
-
-u32 tfrc_calc_x(u16 s, u32 R, u32 p);
-u32 tfrc_calc_x_reverse_lookup(u32 fvalue);
-u32 tfrc_invert_loss_event_rate(u32 loss_event_rate);
-
-int tfrc_tx_packet_history_init(void);
-void tfrc_tx_packet_history_exit(void);
-int tfrc_rx_packet_history_init(void);
-void tfrc_rx_packet_history_exit(void);
-
-int tfrc_li_init(void);
-void tfrc_li_exit(void);
-
-#ifdef CONFIG_IP_DCCP_TFRC_LIB
-int tfrc_lib_init(void);
-void tfrc_lib_exit(void);
-#else
-#define tfrc_lib_init() (0)
-#define tfrc_lib_exit()
-#endif
-#endif /* _TFRC_H_ */
diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c
deleted file mode 100644
index 92a8c6bea316..000000000000
--- a/net/dccp/ccids/lib/tfrc_equation.c
+++ /dev/null
@@ -1,702 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  Copyright (c) 2005 The University of Waikato, Hamilton, New Zealand.
- *  Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz>
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- *  Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
- */
-
-#include <linux/module.h>
-#include "../../dccp.h"
-#include "tfrc.h"
-
-#define TFRC_CALC_X_ARRSIZE 500
-#define TFRC_CALC_X_SPLIT   50000	/* 0.05 * 1000000, details below */
-#define TFRC_SMALLEST_P	    (TFRC_CALC_X_SPLIT/TFRC_CALC_X_ARRSIZE)
-
-/*
-  TFRC TCP Reno Throughput Equation Lookup Table for f(p)
-
-  The following two-column lookup table implements a part of the TCP throughput
-  equation from [RFC 3448, sec. 3.1]:
-
-				     s
-  X_calc  =  --------------------------------------------------------------
-	     R * sqrt(2*b*p/3) + (3 * t_RTO * sqrt(3*b*p/8) * (p + 32*p^3))
-
-  Where:
-	X      is the transmit rate in bytes/second
-	s      is the packet size in bytes
-	R      is the round trip time in seconds
-	p      is the loss event rate, between 0 and 1.0, of the number of loss
-		      events as a fraction of the number of packets transmitted
-	t_RTO  is the TCP retransmission timeout value in seconds
-	b      is the number of packets acknowledged by a single TCP ACK
-
-  We can assume that b = 1 and t_RTO is 4 * R. The equation now becomes:
-
-				     s
-  X_calc  =  -------------------------------------------------------
-	     R * sqrt(p*2/3) + (12 * R * sqrt(p*3/8) * (p + 32*p^3))
-
-  which we can break down into:
-
-		      s
-	X_calc  =  ---------
-		    R * f(p)
-
-  where f(p) is given for 0 < p <= 1 by:
-
-	f(p)  =  sqrt(2*p/3) + 12 * sqrt(3*p/8) *  (p + 32*p^3)
-
-  Since this is kernel code, floating-point arithmetic is avoided in favour of
-  integer arithmetic. This means that nearly all fractional parameters are
-  scaled by 1000000:
-    * the parameters p and R
-    * the return result f(p)
-  The lookup table therefore actually tabulates the following function g(q):
-
-	g(q)  =  1000000 * f(q/1000000)
-
-  Hence, when p <= 1, q must be less than or equal to 1000000. To achieve finer
-  granularity for the practically more relevant case of small values of p (up to
-  5%), the second column is used; the first one ranges up to 100%.  This split
-  corresponds to the value of q = TFRC_CALC_X_SPLIT. At the same time this also
-  determines the smallest resolution possible with this lookup table:
-
-    TFRC_SMALLEST_P   =  TFRC_CALC_X_SPLIT / TFRC_CALC_X_ARRSIZE
-
-  The entire table is generated by:
-    for(i=0; i < TFRC_CALC_X_ARRSIZE; i++) {
-	lookup[i][0]  =  g((i+1) * 1000000/TFRC_CALC_X_ARRSIZE);
-	lookup[i][1]  =  g((i+1) * TFRC_CALC_X_SPLIT/TFRC_CALC_X_ARRSIZE);
-    }
-
-  With the given configuration, we have, with M = TFRC_CALC_X_ARRSIZE-1,
-    lookup[0][0]  =  g(1000000/(M+1))		= 1000000 * f(0.2%)
-    lookup[M][0]  =  g(1000000)			= 1000000 * f(100%)
-    lookup[0][1]  =  g(TFRC_SMALLEST_P)		= 1000000 * f(0.01%)
-    lookup[M][1]  =  g(TFRC_CALC_X_SPLIT)	= 1000000 * f(5%)
-
-  In summary, the two columns represent f(p) for the following ranges:
-    * The first column is for   0.002  <= p <= 1.0
-    * The second column is for  0.0001 <= p <= 0.05
-  Where the columns overlap, the second (finer-grained) is given preference,
-  i.e. the first column is used only for p >= 0.05.
- */
-static const u32 tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE][2] = {
-	{     37172,   8172 },
-	{     53499,  11567 },
-	{     66664,  14180 },
-	{     78298,  16388 },
-	{     89021,  18339 },
-	{     99147,  20108 },
-	{    108858,  21738 },
-	{    118273,  23260 },
-	{    127474,  24693 },
-	{    136520,  26052 },
-	{    145456,  27348 },
-	{    154316,  28589 },
-	{    163130,  29783 },
-	{    171919,  30935 },
-	{    180704,  32049 },
-	{    189502,  33130 },
-	{    198328,  34180 },
-	{    207194,  35202 },
-	{    216114,  36198 },
-	{    225097,  37172 },
-	{    234153,  38123 },
-	{    243294,  39055 },
-	{    252527,  39968 },
-	{    261861,  40864 },
-	{    271305,  41743 },
-	{    280866,  42607 },
-	{    290553,  43457 },
-	{    300372,  44293 },
-	{    310333,  45117 },
-	{    320441,  45929 },
-	{    330705,  46729 },
-	{    341131,  47518 },
-	{    351728,  48297 },
-	{    362501,  49066 },
-	{    373460,  49826 },
-	{    384609,  50577 },
-	{    395958,  51320 },
-	{    407513,  52054 },
-	{    419281,  52780 },
-	{    431270,  53499 },
-	{    443487,  54211 },
-	{    455940,  54916 },
-	{    468635,  55614 },
-	{    481581,  56306 },
-	{    494785,  56991 },
-	{    508254,  57671 },
-	{    521996,  58345 },
-	{    536019,  59014 },
-	{    550331,  59677 },
-	{    564939,  60335 },
-	{    579851,  60988 },
-	{    595075,  61636 },
-	{    610619,  62279 },
-	{    626491,  62918 },
-	{    642700,  63553 },
-	{    659253,  64183 },
-	{    676158,  64809 },
-	{    693424,  65431 },
-	{    711060,  66050 },
-	{    729073,  66664 },
-	{    747472,  67275 },
-	{    766266,  67882 },
-	{    785464,  68486 },
-	{    805073,  69087 },
-	{    825103,  69684 },
-	{    845562,  70278 },
-	{    866460,  70868 },
-	{    887805,  71456 },
-	{    909606,  72041 },
-	{    931873,  72623 },
-	{    954614,  73202 },
-	{    977839,  73778 },
-	{   1001557,  74352 },
-	{   1025777,  74923 },
-	{   1050508,  75492 },
-	{   1075761,  76058 },
-	{   1101544,  76621 },
-	{   1127867,  77183 },
-	{   1154739,  77741 },
-	{   1182172,  78298 },
-	{   1210173,  78852 },
-	{   1238753,  79405 },
-	{   1267922,  79955 },
-	{   1297689,  80503 },
-	{   1328066,  81049 },
-	{   1359060,  81593 },
-	{   1390684,  82135 },
-	{   1422947,  82675 },
-	{   1455859,  83213 },
-	{   1489430,  83750 },
-	{   1523671,  84284 },
-	{   1558593,  84817 },
-	{   1594205,  85348 },
-	{   1630518,  85878 },
-	{   1667543,  86406 },
-	{   1705290,  86932 },
-	{   1743770,  87457 },
-	{   1782994,  87980 },
-	{   1822973,  88501 },
-	{   1863717,  89021 },
-	{   1905237,  89540 },
-	{   1947545,  90057 },
-	{   1990650,  90573 },
-	{   2034566,  91087 },
-	{   2079301,  91600 },
-	{   2124869,  92111 },
-	{   2171279,  92622 },
-	{   2218543,  93131 },
-	{   2266673,  93639 },
-	{   2315680,  94145 },
-	{   2365575,  94650 },
-	{   2416371,  95154 },
-	{   2468077,  95657 },
-	{   2520707,  96159 },
-	{   2574271,  96660 },
-	{   2628782,  97159 },
-	{   2684250,  97658 },
-	{   2740689,  98155 },
-	{   2798110,  98651 },
-	{   2856524,  99147 },
-	{   2915944,  99641 },
-	{   2976382, 100134 },
-	{   3037850, 100626 },
-	{   3100360, 101117 },
-	{   3163924, 101608 },
-	{   3228554, 102097 },
-	{   3294263, 102586 },
-	{   3361063, 103073 },
-	{   3428966, 103560 },
-	{   3497984, 104045 },
-	{   3568131, 104530 },
-	{   3639419, 105014 },
-	{   3711860, 105498 },
-	{   3785467, 105980 },
-	{   3860253, 106462 },
-	{   3936229, 106942 },
-	{   4013410, 107422 },
-	{   4091808, 107902 },
-	{   4171435, 108380 },
-	{   4252306, 108858 },
-	{   4334431, 109335 },
-	{   4417825, 109811 },
-	{   4502501, 110287 },
-	{   4588472, 110762 },
-	{   4675750, 111236 },
-	{   4764349, 111709 },
-	{   4854283, 112182 },
-	{   4945564, 112654 },
-	{   5038206, 113126 },
-	{   5132223, 113597 },
-	{   5227627, 114067 },
-	{   5324432, 114537 },
-	{   5422652, 115006 },
-	{   5522299, 115474 },
-	{   5623389, 115942 },
-	{   5725934, 116409 },
-	{   5829948, 116876 },
-	{   5935446, 117342 },
-	{   6042439, 117808 },
-	{   6150943, 118273 },
-	{   6260972, 118738 },
-	{   6372538, 119202 },
-	{   6485657, 119665 },
-	{   6600342, 120128 },
-	{   6716607, 120591 },
-	{   6834467, 121053 },
-	{   6953935, 121514 },
-	{   7075025, 121976 },
-	{   7197752, 122436 },
-	{   7322131, 122896 },
-	{   7448175, 123356 },
-	{   7575898, 123815 },
-	{   7705316, 124274 },
-	{   7836442, 124733 },
-	{   7969291, 125191 },
-	{   8103877, 125648 },
-	{   8240216, 126105 },
-	{   8378321, 126562 },
-	{   8518208, 127018 },
-	{   8659890, 127474 },
-	{   8803384, 127930 },
-	{   8948702, 128385 },
-	{   9095861, 128840 },
-	{   9244875, 129294 },
-	{   9395760, 129748 },
-	{   9548529, 130202 },
-	{   9703198, 130655 },
-	{   9859782, 131108 },
-	{  10018296, 131561 },
-	{  10178755, 132014 },
-	{  10341174, 132466 },
-	{  10505569, 132917 },
-	{  10671954, 133369 },
-	{  10840345, 133820 },
-	{  11010757, 134271 },
-	{  11183206, 134721 },
-	{  11357706, 135171 },
-	{  11534274, 135621 },
-	{  11712924, 136071 },
-	{  11893673, 136520 },
-	{  12076536, 136969 },
-	{  12261527, 137418 },
-	{  12448664, 137867 },
-	{  12637961, 138315 },
-	{  12829435, 138763 },
-	{  13023101, 139211 },
-	{  13218974, 139658 },
-	{  13417071, 140106 },
-	{  13617407, 140553 },
-	{  13819999, 140999 },
-	{  14024862, 141446 },
-	{  14232012, 141892 },
-	{  14441465, 142339 },
-	{  14653238, 142785 },
-	{  14867346, 143230 },
-	{  15083805, 143676 },
-	{  15302632, 144121 },
-	{  15523842, 144566 },
-	{  15747453, 145011 },
-	{  15973479, 145456 },
-	{  16201939, 145900 },
-	{  16432847, 146345 },
-	{  16666221, 146789 },
-	{  16902076, 147233 },
-	{  17140429, 147677 },
-	{  17381297, 148121 },
-	{  17624696, 148564 },
-	{  17870643, 149007 },
-	{  18119154, 149451 },
-	{  18370247, 149894 },
-	{  18623936, 150336 },
-	{  18880241, 150779 },
-	{  19139176, 151222 },
-	{  19400759, 151664 },
-	{  19665007, 152107 },
-	{  19931936, 152549 },
-	{  20201564, 152991 },
-	{  20473907, 153433 },
-	{  20748982, 153875 },
-	{  21026807, 154316 },
-	{  21307399, 154758 },
-	{  21590773, 155199 },
-	{  21876949, 155641 },
-	{  22165941, 156082 },
-	{  22457769, 156523 },
-	{  22752449, 156964 },
-	{  23049999, 157405 },
-	{  23350435, 157846 },
-	{  23653774, 158287 },
-	{  23960036, 158727 },
-	{  24269236, 159168 },
-	{  24581392, 159608 },
-	{  24896521, 160049 },
-	{  25214642, 160489 },
-	{  25535772, 160929 },
-	{  25859927, 161370 },
-	{  26187127, 161810 },
-	{  26517388, 162250 },
-	{  26850728, 162690 },
-	{  27187165, 163130 },
-	{  27526716, 163569 },
-	{  27869400, 164009 },
-	{  28215234, 164449 },
-	{  28564236, 164889 },
-	{  28916423, 165328 },
-	{  29271815, 165768 },
-	{  29630428, 166208 },
-	{  29992281, 166647 },
-	{  30357392, 167087 },
-	{  30725779, 167526 },
-	{  31097459, 167965 },
-	{  31472452, 168405 },
-	{  31850774, 168844 },
-	{  32232445, 169283 },
-	{  32617482, 169723 },
-	{  33005904, 170162 },
-	{  33397730, 170601 },
-	{  33792976, 171041 },
-	{  34191663, 171480 },
-	{  34593807, 171919 },
-	{  34999428, 172358 },
-	{  35408544, 172797 },
-	{  35821174, 173237 },
-	{  36237335, 173676 },
-	{  36657047, 174115 },
-	{  37080329, 174554 },
-	{  37507197, 174993 },
-	{  37937673, 175433 },
-	{  38371773, 175872 },
-	{  38809517, 176311 },
-	{  39250924, 176750 },
-	{  39696012, 177190 },
-	{  40144800, 177629 },
-	{  40597308, 178068 },
-	{  41053553, 178507 },
-	{  41513554, 178947 },
-	{  41977332, 179386 },
-	{  42444904, 179825 },
-	{  42916290, 180265 },
-	{  43391509, 180704 },
-	{  43870579, 181144 },
-	{  44353520, 181583 },
-	{  44840352, 182023 },
-	{  45331092, 182462 },
-	{  45825761, 182902 },
-	{  46324378, 183342 },
-	{  46826961, 183781 },
-	{  47333531, 184221 },
-	{  47844106, 184661 },
-	{  48358706, 185101 },
-	{  48877350, 185541 },
-	{  49400058, 185981 },
-	{  49926849, 186421 },
-	{  50457743, 186861 },
-	{  50992759, 187301 },
-	{  51531916, 187741 },
-	{  52075235, 188181 },
-	{  52622735, 188622 },
-	{  53174435, 189062 },
-	{  53730355, 189502 },
-	{  54290515, 189943 },
-	{  54854935, 190383 },
-	{  55423634, 190824 },
-	{  55996633, 191265 },
-	{  56573950, 191706 },
-	{  57155606, 192146 },
-	{  57741621, 192587 },
-	{  58332014, 193028 },
-	{  58926806, 193470 },
-	{  59526017, 193911 },
-	{  60129666, 194352 },
-	{  60737774, 194793 },
-	{  61350361, 195235 },
-	{  61967446, 195677 },
-	{  62589050, 196118 },
-	{  63215194, 196560 },
-	{  63845897, 197002 },
-	{  64481179, 197444 },
-	{  65121061, 197886 },
-	{  65765563, 198328 },
-	{  66414705, 198770 },
-	{  67068508, 199213 },
-	{  67726992, 199655 },
-	{  68390177, 200098 },
-	{  69058085, 200540 },
-	{  69730735, 200983 },
-	{  70408147, 201426 },
-	{  71090343, 201869 },
-	{  71777343, 202312 },
-	{  72469168, 202755 },
-	{  73165837, 203199 },
-	{  73867373, 203642 },
-	{  74573795, 204086 },
-	{  75285124, 204529 },
-	{  76001380, 204973 },
-	{  76722586, 205417 },
-	{  77448761, 205861 },
-	{  78179926, 206306 },
-	{  78916102, 206750 },
-	{  79657310, 207194 },
-	{  80403571, 207639 },
-	{  81154906, 208084 },
-	{  81911335, 208529 },
-	{  82672880, 208974 },
-	{  83439562, 209419 },
-	{  84211402, 209864 },
-	{  84988421, 210309 },
-	{  85770640, 210755 },
-	{  86558080, 211201 },
-	{  87350762, 211647 },
-	{  88148708, 212093 },
-	{  88951938, 212539 },
-	{  89760475, 212985 },
-	{  90574339, 213432 },
-	{  91393551, 213878 },
-	{  92218133, 214325 },
-	{  93048107, 214772 },
-	{  93883493, 215219 },
-	{  94724314, 215666 },
-	{  95570590, 216114 },
-	{  96422343, 216561 },
-	{  97279594, 217009 },
-	{  98142366, 217457 },
-	{  99010679, 217905 },
-	{  99884556, 218353 },
-	{ 100764018, 218801 },
-	{ 101649086, 219250 },
-	{ 102539782, 219698 },
-	{ 103436128, 220147 },
-	{ 104338146, 220596 },
-	{ 105245857, 221046 },
-	{ 106159284, 221495 },
-	{ 107078448, 221945 },
-	{ 108003370, 222394 },
-	{ 108934074, 222844 },
-	{ 109870580, 223294 },
-	{ 110812910, 223745 },
-	{ 111761087, 224195 },
-	{ 112715133, 224646 },
-	{ 113675069, 225097 },
-	{ 114640918, 225548 },
-	{ 115612702, 225999 },
-	{ 116590442, 226450 },
-	{ 117574162, 226902 },
-	{ 118563882, 227353 },
-	{ 119559626, 227805 },
-	{ 120561415, 228258 },
-	{ 121569272, 228710 },
-	{ 122583219, 229162 },
-	{ 123603278, 229615 },
-	{ 124629471, 230068 },
-	{ 125661822, 230521 },
-	{ 126700352, 230974 },
-	{ 127745083, 231428 },
-	{ 128796039, 231882 },
-	{ 129853241, 232336 },
-	{ 130916713, 232790 },
-	{ 131986475, 233244 },
-	{ 133062553, 233699 },
-	{ 134144966, 234153 },
-	{ 135233739, 234608 },
-	{ 136328894, 235064 },
-	{ 137430453, 235519 },
-	{ 138538440, 235975 },
-	{ 139652876, 236430 },
-	{ 140773786, 236886 },
-	{ 141901190, 237343 },
-	{ 143035113, 237799 },
-	{ 144175576, 238256 },
-	{ 145322604, 238713 },
-	{ 146476218, 239170 },
-	{ 147636442, 239627 },
-	{ 148803298, 240085 },
-	{ 149976809, 240542 },
-	{ 151156999, 241000 },
-	{ 152343890, 241459 },
-	{ 153537506, 241917 },
-	{ 154737869, 242376 },
-	{ 155945002, 242835 },
-	{ 157158929, 243294 },
-	{ 158379673, 243753 },
-	{ 159607257, 244213 },
-	{ 160841704, 244673 },
-	{ 162083037, 245133 },
-	{ 163331279, 245593 },
-	{ 164586455, 246054 },
-	{ 165848586, 246514 },
-	{ 167117696, 246975 },
-	{ 168393810, 247437 },
-	{ 169676949, 247898 },
-	{ 170967138, 248360 },
-	{ 172264399, 248822 },
-	{ 173568757, 249284 },
-	{ 174880235, 249747 },
-	{ 176198856, 250209 },
-	{ 177524643, 250672 },
-	{ 178857621, 251136 },
-	{ 180197813, 251599 },
-	{ 181545242, 252063 },
-	{ 182899933, 252527 },
-	{ 184261908, 252991 },
-	{ 185631191, 253456 },
-	{ 187007807, 253920 },
-	{ 188391778, 254385 },
-	{ 189783129, 254851 },
-	{ 191181884, 255316 },
-	{ 192588065, 255782 },
-	{ 194001698, 256248 },
-	{ 195422805, 256714 },
-	{ 196851411, 257181 },
-	{ 198287540, 257648 },
-	{ 199731215, 258115 },
-	{ 201182461, 258582 },
-	{ 202641302, 259050 },
-	{ 204107760, 259518 },
-	{ 205581862, 259986 },
-	{ 207063630, 260454 },
-	{ 208553088, 260923 },
-	{ 210050262, 261392 },
-	{ 211555174, 261861 },
-	{ 213067849, 262331 },
-	{ 214588312, 262800 },
-	{ 216116586, 263270 },
-	{ 217652696, 263741 },
-	{ 219196666, 264211 },
-	{ 220748520, 264682 },
-	{ 222308282, 265153 },
-	{ 223875978, 265625 },
-	{ 225451630, 266097 },
-	{ 227035265, 266569 },
-	{ 228626905, 267041 },
-	{ 230226576, 267514 },
-	{ 231834302, 267986 },
-	{ 233450107, 268460 },
-	{ 235074016, 268933 },
-	{ 236706054, 269407 },
-	{ 238346244, 269881 },
-	{ 239994613, 270355 },
-	{ 241651183, 270830 },
-	{ 243315981, 271305 }
-};
-
-/* return largest index i such that fval <= lookup[i][small] */
-static inline u32 tfrc_binsearch(u32 fval, u8 small)
-{
-	u32 try, low = 0, high = TFRC_CALC_X_ARRSIZE - 1;
-
-	while (low < high) {
-		try = (low + high) / 2;
-		if (fval <= tfrc_calc_x_lookup[try][small])
-			high = try;
-		else
-			low  = try + 1;
-	}
-	return high;
-}
-
-/**
- * tfrc_calc_x - Calculate the send rate as per section 3.1 of RFC3448
- * @s: packet size          in bytes
- * @R: RTT                  scaled by 1000000   (i.e., microseconds)
- * @p: loss ratio estimate  scaled by 1000000
- *
- * Returns X_calc           in bytes per second (not scaled).
- */
-u32 tfrc_calc_x(u16 s, u32 R, u32 p)
-{
-	u16 index;
-	u32 f;
-	u64 result;
-
-	/* check against invalid parameters and divide-by-zero   */
-	BUG_ON(p >  1000000);		/* p must not exceed 100%   */
-	BUG_ON(p == 0);			/* f(0) = 0, divide by zero */
-	if (R == 0) {			/* possible  divide by zero */
-		DCCP_CRIT("WARNING: RTT is 0, returning maximum X_calc.");
-		return ~0U;
-	}
-
-	if (p <= TFRC_CALC_X_SPLIT)		{     /* 0.0000 < p <= 0.05   */
-		if (p < TFRC_SMALLEST_P) {	      /* 0.0000 < p <  0.0001 */
-			DCCP_WARN("Value of p (%d) below resolution. "
-				  "Substituting %d\n", p, TFRC_SMALLEST_P);
-			index = 0;
-		} else				      /* 0.0001 <= p <= 0.05  */
-			index =  p/TFRC_SMALLEST_P - 1;
-
-		f = tfrc_calc_x_lookup[index][1];
-
-	} else {				      /* 0.05   <  p <= 1.00  */
-		index = p/(1000000/TFRC_CALC_X_ARRSIZE) - 1;
-
-		f = tfrc_calc_x_lookup[index][0];
-	}
-
-	/*
-	 * Compute X = s/(R*f(p)) in bytes per second.
-	 * Since f(p) and R are both scaled by 1000000, we need to multiply by
-	 * 1000000^2. To avoid overflow, the result is computed in two stages.
-	 * This works under almost all reasonable operational conditions, for a
-	 * wide range of parameters. Yet, should some strange combination of
-	 * parameters result in overflow, the use of scaled_div32 will catch
-	 * this and return UINT_MAX - which is a logically adequate consequence.
-	 */
-	result = scaled_div(s, R);
-	return scaled_div32(result, f);
-}
-
-/**
- *  tfrc_calc_x_reverse_lookup  -  try to find p given f(p)
- *  @fvalue: function value to match, scaled by 1000000
- *
- *  Returns closest match for p, also scaled by 1000000
- */
-u32 tfrc_calc_x_reverse_lookup(u32 fvalue)
-{
-	int index;
-
-	if (fvalue == 0)	/* f(p) = 0  whenever  p = 0 */
-		return 0;
-
-	/* Error cases. */
-	if (fvalue < tfrc_calc_x_lookup[0][1]) {
-		DCCP_WARN("fvalue %u smaller than resolution\n", fvalue);
-		return TFRC_SMALLEST_P;
-	}
-	if (fvalue > tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][0]) {
-		DCCP_WARN("fvalue %u exceeds bounds!\n", fvalue);
-		return 1000000;
-	}
-
-	if (fvalue <= tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][1]) {
-		index = tfrc_binsearch(fvalue, 1);
-		return (index + 1) * TFRC_CALC_X_SPLIT / TFRC_CALC_X_ARRSIZE;
-	}
-
-	/* else ... it must be in the coarse-grained column */
-	index = tfrc_binsearch(fvalue, 0);
-	return (index + 1) * 1000000 / TFRC_CALC_X_ARRSIZE;
-}
-
-/**
- * tfrc_invert_loss_event_rate  -  Compute p so that 10^6 corresponds to 100%
- * @loss_event_rate: loss event rate to invert
- * When @loss_event_rate is large, there is a chance that p is truncated to 0.
- * To avoid re-entering slow-start in that case, we set p = TFRC_SMALLEST_P > 0.
- */
-u32 tfrc_invert_loss_event_rate(u32 loss_event_rate)
-{
-	if (loss_event_rate == UINT_MAX)		/* see RFC 4342, 8.5 */
-		return 0;
-	if (unlikely(loss_event_rate == 0))		/* map 1/0 into 100% */
-		return 1000000;
-	return max_t(u32, scaled_div(1, loss_event_rate), TFRC_SMALLEST_P);
-}
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
deleted file mode 100644
index 1f748ed1279d..000000000000
--- a/net/dccp/dccp.h
+++ /dev/null
@@ -1,483 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-#ifndef _DCCP_H
-#define _DCCP_H
-/*
- *  net/dccp/dccp.h
- *
- *  An implementation of the DCCP protocol
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- *  Copyright (c) 2005-6 Ian McDonald <ian.mcdonald@jandi.co.nz>
- */
-
-#include <linux/dccp.h>
-#include <linux/ktime.h>
-#include <net/snmp.h>
-#include <net/sock.h>
-#include <net/tcp.h>
-#include "ackvec.h"
-
-/*
- * 	DCCP - specific warning and debugging macros.
- */
-#define DCCP_WARN(fmt, ...)						\
-	net_warn_ratelimited("%s: " fmt, __func__, ##__VA_ARGS__)
-#define DCCP_CRIT(fmt, a...) printk(KERN_CRIT fmt " at %s:%d/%s()\n", ##a, \
-					 __FILE__, __LINE__, __func__)
-#define DCCP_BUG(a...)       do { DCCP_CRIT("BUG: " a); dump_stack(); } while(0)
-#define DCCP_BUG_ON(cond)    do { if (unlikely((cond) != 0))		   \
-				     DCCP_BUG("\"%s\" holds (exception!)", \
-					      __stringify(cond));          \
-			     } while (0)
-
-#define DCCP_PRINTK(enable, fmt, args...)	do { if (enable)	     \
-							printk(fmt, ##args); \
-						} while(0)
-#define DCCP_PR_DEBUG(enable, fmt, a...)	DCCP_PRINTK(enable, KERN_DEBUG \
-						  "%s: " fmt, __func__, ##a)
-
-#ifdef CONFIG_IP_DCCP_DEBUG
-extern bool dccp_debug;
-#define dccp_pr_debug(format, a...)	  DCCP_PR_DEBUG(dccp_debug, format, ##a)
-#define dccp_pr_debug_cat(format, a...)   DCCP_PRINTK(dccp_debug, format, ##a)
-#define dccp_debug(fmt, a...)		  dccp_pr_debug_cat(KERN_DEBUG fmt, ##a)
-#else
-#define dccp_pr_debug(format, a...)	  do {} while (0)
-#define dccp_pr_debug_cat(format, a...)	  do {} while (0)
-#define dccp_debug(format, a...)	  do {} while (0)
-#endif
-
-extern struct inet_hashinfo dccp_hashinfo;
-
-DECLARE_PER_CPU(unsigned int, dccp_orphan_count);
-
-void dccp_time_wait(struct sock *sk, int state, int timeo);
-
-/*
- *  Set safe upper bounds for header and option length. Since Data Offset is 8
- *  bits (RFC 4340, sec. 5.1), the total header length can never be more than
- *  4 * 255 = 1020 bytes. The largest possible header length is 28 bytes (X=1):
- *    - DCCP-Response with ACK Subheader and 4 bytes of Service code      OR
- *    - DCCP-Reset    with ACK Subheader and 4 bytes of Reset Code fields
- *  Hence a safe upper bound for the maximum option length is 1020-28 = 992
- */
-#define MAX_DCCP_SPECIFIC_HEADER (255 * sizeof(uint32_t))
-#define DCCP_MAX_PACKET_HDR 28
-#define DCCP_MAX_OPT_LEN (MAX_DCCP_SPECIFIC_HEADER - DCCP_MAX_PACKET_HDR)
-#define MAX_DCCP_HEADER (MAX_DCCP_SPECIFIC_HEADER + MAX_HEADER)
-
-/* Upper bound for initial feature-negotiation overhead (padded to 32 bits) */
-#define DCCP_FEATNEG_OVERHEAD	 (32 * sizeof(uint32_t))
-
-#define DCCP_TIMEWAIT_LEN (60 * HZ) /* how long to wait to destroy TIME-WAIT
-				     * state, about 60 seconds */
-
-/* RFC 1122, 4.2.3.1 initial RTO value */
-#define DCCP_TIMEOUT_INIT ((unsigned int)(3 * HZ))
-
-/*
- * The maximum back-off value for retransmissions. This is needed for
- *  - retransmitting client-Requests (sec. 8.1.1),
- *  - retransmitting Close/CloseReq when closing (sec. 8.3),
- *  - feature-negotiation retransmission (sec. 6.6.3),
- *  - Acks in client-PARTOPEN state (sec. 8.1.5).
- */
-#define DCCP_RTO_MAX ((unsigned int)(64 * HZ))
-
-/*
- * RTT sampling: sanity bounds and fallback RTT value from RFC 4340, section 3.4
- */
-#define DCCP_SANE_RTT_MIN	100
-#define DCCP_FALLBACK_RTT	(USEC_PER_SEC / 5)
-#define DCCP_SANE_RTT_MAX	(3 * USEC_PER_SEC)
-
-/* sysctl variables for DCCP */
-extern int  sysctl_dccp_request_retries;
-extern int  sysctl_dccp_retries1;
-extern int  sysctl_dccp_retries2;
-extern int  sysctl_dccp_tx_qlen;
-extern int  sysctl_dccp_sync_ratelimit;
-
-/*
- *	48-bit sequence number arithmetic (signed and unsigned)
- */
-#define INT48_MIN	  0x800000000000LL		/* 2^47	    */
-#define UINT48_MAX	  0xFFFFFFFFFFFFLL		/* 2^48 - 1 */
-#define COMPLEMENT48(x)	 (0x1000000000000LL - (x))	/* 2^48 - x */
-#define TO_SIGNED48(x)	 (((x) < INT48_MIN)? (x) : -COMPLEMENT48( (x)))
-#define TO_UNSIGNED48(x) (((x) >= 0)?	     (x) :  COMPLEMENT48(-(x)))
-#define ADD48(a, b)	 (((a) + (b)) & UINT48_MAX)
-#define SUB48(a, b)	 ADD48((a), COMPLEMENT48(b))
-
-static inline void dccp_inc_seqno(u64 *seqno)
-{
-	*seqno = ADD48(*seqno, 1);
-}
-
-/* signed mod-2^48 distance: pos. if seqno1 < seqno2, neg. if seqno1 > seqno2 */
-static inline s64 dccp_delta_seqno(const u64 seqno1, const u64 seqno2)
-{
-	u64 delta = SUB48(seqno2, seqno1);
-
-	return TO_SIGNED48(delta);
-}
-
-/* is seq1 < seq2 ? */
-static inline int before48(const u64 seq1, const u64 seq2)
-{
-	return (s64)((seq2 << 16) - (seq1 << 16)) > 0;
-}
-
-/* is seq1 > seq2 ? */
-#define after48(seq1, seq2)	before48(seq2, seq1)
-
-/* is seq2 <= seq1 <= seq3 ? */
-static inline int between48(const u64 seq1, const u64 seq2, const u64 seq3)
-{
-	return (seq3 << 16) - (seq2 << 16) >= (seq1 << 16) - (seq2 << 16);
-}
-
-/**
- * dccp_loss_count - Approximate the number of lost data packets in a burst loss
- * @s1:  last known sequence number before the loss ('hole')
- * @s2:  first sequence number seen after the 'hole'
- * @ndp: NDP count on packet with sequence number @s2
- */
-static inline u64 dccp_loss_count(const u64 s1, const u64 s2, const u64 ndp)
-{
-	s64 delta = dccp_delta_seqno(s1, s2);
-
-	WARN_ON(delta < 0);
-	delta -= ndp + 1;
-
-	return delta > 0 ? delta : 0;
-}
-
-/**
- * dccp_loss_free - Evaluate condition for data loss from RFC 4340, 7.7.1
- */
-static inline bool dccp_loss_free(const u64 s1, const u64 s2, const u64 ndp)
-{
-	return dccp_loss_count(s1, s2, ndp) == 0;
-}
-
-enum {
-	DCCP_MIB_NUM = 0,
-	DCCP_MIB_ACTIVEOPENS,			/* ActiveOpens */
-	DCCP_MIB_ESTABRESETS,			/* EstabResets */
-	DCCP_MIB_CURRESTAB,			/* CurrEstab */
-	DCCP_MIB_OUTSEGS,			/* OutSegs */
-	DCCP_MIB_OUTRSTS,
-	DCCP_MIB_ABORTONTIMEOUT,
-	DCCP_MIB_TIMEOUTS,
-	DCCP_MIB_ABORTFAILED,
-	DCCP_MIB_PASSIVEOPENS,
-	DCCP_MIB_ATTEMPTFAILS,
-	DCCP_MIB_OUTDATAGRAMS,
-	DCCP_MIB_INERRS,
-	DCCP_MIB_OPTMANDATORYERROR,
-	DCCP_MIB_INVALIDOPT,
-	__DCCP_MIB_MAX
-};
-
-#define DCCP_MIB_MAX	__DCCP_MIB_MAX
-struct dccp_mib {
-	unsigned long	mibs[DCCP_MIB_MAX];
-};
-
-DECLARE_SNMP_STAT(struct dccp_mib, dccp_statistics);
-#define DCCP_INC_STATS(field)	SNMP_INC_STATS(dccp_statistics, field)
-#define __DCCP_INC_STATS(field)	__SNMP_INC_STATS(dccp_statistics, field)
-#define DCCP_DEC_STATS(field)	SNMP_DEC_STATS(dccp_statistics, field)
-
-/*
- * 	Checksumming routines
- */
-static inline unsigned int dccp_csum_coverage(const struct sk_buff *skb)
-{
-	const struct dccp_hdr* dh = dccp_hdr(skb);
-
-	if (dh->dccph_cscov == 0)
-		return skb->len;
-	return (dh->dccph_doff + dh->dccph_cscov - 1) * sizeof(u32);
-}
-
-static inline void dccp_csum_outgoing(struct sk_buff *skb)
-{
-	unsigned int cov = dccp_csum_coverage(skb);
-
-	if (cov >= skb->len)
-		dccp_hdr(skb)->dccph_cscov = 0;
-
-	skb->csum = skb_checksum(skb, 0, (cov > skb->len)? skb->len : cov, 0);
-}
-
-void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb);
-
-int dccp_retransmit_skb(struct sock *sk);
-
-void dccp_send_ack(struct sock *sk);
-void dccp_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
-			 struct request_sock *rsk);
-
-void dccp_send_sync(struct sock *sk, const u64 seq,
-		    const enum dccp_pkt_type pkt_type);
-
-/*
- * TX Packet Dequeueing Interface
- */
-void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb);
-bool dccp_qpolicy_full(struct sock *sk);
-void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb);
-struct sk_buff *dccp_qpolicy_top(struct sock *sk);
-struct sk_buff *dccp_qpolicy_pop(struct sock *sk);
-bool dccp_qpolicy_param_ok(struct sock *sk, __be32 param);
-
-/*
- * TX Packet Output and TX Timers
- */
-void dccp_write_xmit(struct sock *sk);
-void dccp_write_space(struct sock *sk);
-void dccp_flush_write_queue(struct sock *sk, long *time_budget);
-
-void dccp_init_xmit_timers(struct sock *sk);
-static inline void dccp_clear_xmit_timers(struct sock *sk)
-{
-	inet_csk_clear_xmit_timers(sk);
-}
-
-unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu);
-
-const char *dccp_packet_name(const int type);
-
-void dccp_set_state(struct sock *sk, const int state);
-void dccp_done(struct sock *sk);
-
-int dccp_reqsk_init(struct request_sock *rq, struct dccp_sock const *dp,
-		    struct sk_buff const *skb);
-
-int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
-
-struct sock *dccp_create_openreq_child(const struct sock *sk,
-				       const struct request_sock *req,
-				       const struct sk_buff *skb);
-
-int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
-
-struct sock *dccp_v4_request_recv_sock(const struct sock *sk, struct sk_buff *skb,
-				       struct request_sock *req,
-				       struct dst_entry *dst,
-				       struct request_sock *req_unhash,
-				       bool *own_req);
-struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
-			    struct request_sock *req);
-
-int dccp_child_process(struct sock *parent, struct sock *child,
-		       struct sk_buff *skb);
-int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
-			   struct dccp_hdr *dh, unsigned int len);
-int dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
-			 const struct dccp_hdr *dh, const unsigned int len);
-
-void dccp_destruct_common(struct sock *sk);
-int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized);
-void dccp_destroy_sock(struct sock *sk);
-
-void dccp_close(struct sock *sk, long timeout);
-struct sk_buff *dccp_make_response(const struct sock *sk, struct dst_entry *dst,
-				   struct request_sock *req);
-
-int dccp_connect(struct sock *sk);
-int dccp_disconnect(struct sock *sk, int flags);
-int dccp_getsockopt(struct sock *sk, int level, int optname,
-		    char __user *optval, int __user *optlen);
-int dccp_setsockopt(struct sock *sk, int level, int optname,
-		    sockptr_t optval, unsigned int optlen);
-int dccp_ioctl(struct sock *sk, int cmd, int *karg);
-int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
-int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
-		 int *addr_len);
-void dccp_shutdown(struct sock *sk, int how);
-int inet_dccp_listen(struct socket *sock, int backlog);
-__poll_t dccp_poll(struct file *file, struct socket *sock,
-		       poll_table *wait);
-int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
-void dccp_req_err(struct sock *sk, u64 seq);
-
-struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *skb);
-int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code);
-void dccp_send_close(struct sock *sk, const int active);
-int dccp_invalid_packet(struct sk_buff *skb);
-u32 dccp_sample_rtt(struct sock *sk, long delta);
-
-static inline bool dccp_bad_service_code(const struct sock *sk,
-					const __be32 service)
-{
-	const struct dccp_sock *dp = dccp_sk(sk);
-
-	if (dp->dccps_service == service)
-		return false;
-	return !dccp_list_has_service(dp->dccps_service_list, service);
-}
-
-/**
- * dccp_skb_cb  -  DCCP per-packet control information
- * @dccpd_type: one of %dccp_pkt_type (or unknown)
- * @dccpd_ccval: CCVal field (5.1), see e.g. RFC 4342, 8.1
- * @dccpd_reset_code: one of %dccp_reset_codes
- * @dccpd_reset_data: Data1..3 fields (depend on @dccpd_reset_code)
- * @dccpd_opt_len: total length of all options (5.8) in the packet
- * @dccpd_seq: sequence number
- * @dccpd_ack_seq: acknowledgment number subheader field value
- *
- * This is used for transmission as well as for reception.
- */
-struct dccp_skb_cb {
-	union {
-		struct inet_skb_parm	h4;
-#if IS_ENABLED(CONFIG_IPV6)
-		struct inet6_skb_parm	h6;
-#endif
-	} header;
-	__u8  dccpd_type:4;
-	__u8  dccpd_ccval:4;
-	__u8  dccpd_reset_code,
-	      dccpd_reset_data[3];
-	__u16 dccpd_opt_len;
-	__u64 dccpd_seq;
-	__u64 dccpd_ack_seq;
-};
-
-#define DCCP_SKB_CB(__skb) ((struct dccp_skb_cb *)&((__skb)->cb[0]))
-
-/* RFC 4340, sec. 7.7 */
-static inline int dccp_non_data_packet(const struct sk_buff *skb)
-{
-	const __u8 type = DCCP_SKB_CB(skb)->dccpd_type;
-
-	return type == DCCP_PKT_ACK	 ||
-	       type == DCCP_PKT_CLOSE	 ||
-	       type == DCCP_PKT_CLOSEREQ ||
-	       type == DCCP_PKT_RESET	 ||
-	       type == DCCP_PKT_SYNC	 ||
-	       type == DCCP_PKT_SYNCACK;
-}
-
-/* RFC 4340, sec. 7.7 */
-static inline int dccp_data_packet(const struct sk_buff *skb)
-{
-	const __u8 type = DCCP_SKB_CB(skb)->dccpd_type;
-
-	return type == DCCP_PKT_DATA	 ||
-	       type == DCCP_PKT_DATAACK  ||
-	       type == DCCP_PKT_REQUEST  ||
-	       type == DCCP_PKT_RESPONSE;
-}
-
-static inline int dccp_packet_without_ack(const struct sk_buff *skb)
-{
-	const __u8 type = DCCP_SKB_CB(skb)->dccpd_type;
-
-	return type == DCCP_PKT_DATA || type == DCCP_PKT_REQUEST;
-}
-
-#define DCCP_PKT_WITHOUT_ACK_SEQ (UINT48_MAX << 2)
-
-static inline void dccp_hdr_set_seq(struct dccp_hdr *dh, const u64 gss)
-{
-	struct dccp_hdr_ext *dhx = (struct dccp_hdr_ext *)((void *)dh +
-							   sizeof(*dh));
-	dh->dccph_seq2 = 0;
-	dh->dccph_seq = htons((gss >> 32) & 0xfffff);
-	dhx->dccph_seq_low = htonl(gss & 0xffffffff);
-}
-
-static inline void dccp_hdr_set_ack(struct dccp_hdr_ack_bits *dhack,
-				    const u64 gsr)
-{
-	dhack->dccph_reserved1 = 0;
-	dhack->dccph_ack_nr_high = htons(gsr >> 32);
-	dhack->dccph_ack_nr_low  = htonl(gsr & 0xffffffff);
-}
-
-static inline void dccp_update_gsr(struct sock *sk, u64 seq)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-
-	if (after48(seq, dp->dccps_gsr))
-		dp->dccps_gsr = seq;
-	/* Sequence validity window depends on remote Sequence Window (7.5.1) */
-	dp->dccps_swl = SUB48(ADD48(dp->dccps_gsr, 1), dp->dccps_r_seq_win / 4);
-	/*
-	 * Adjust SWL so that it is not below ISR. In contrast to RFC 4340,
-	 * 7.5.1 we perform this check beyond the initial handshake: W/W' are
-	 * always > 32, so for the first W/W' packets in the lifetime of a
-	 * connection we always have to adjust SWL.
-	 * A second reason why we are doing this is that the window depends on
-	 * the feature-remote value of Sequence Window: nothing stops the peer
-	 * from updating this value while we are busy adjusting SWL for the
-	 * first W packets (we would have to count from scratch again then).
-	 * Therefore it is safer to always make sure that the Sequence Window
-	 * is not artificially extended by a peer who grows SWL downwards by
-	 * continually updating the feature-remote Sequence-Window.
-	 * If sequence numbers wrap it is bad luck. But that will take a while
-	 * (48 bit), and this measure prevents Sequence-number attacks.
-	 */
-	if (before48(dp->dccps_swl, dp->dccps_isr))
-		dp->dccps_swl = dp->dccps_isr;
-	dp->dccps_swh = ADD48(dp->dccps_gsr, (3 * dp->dccps_r_seq_win) / 4);
-}
-
-static inline void dccp_update_gss(struct sock *sk, u64 seq)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-
-	dp->dccps_gss = seq;
-	/* Ack validity window depends on local Sequence Window value (7.5.1) */
-	dp->dccps_awl = SUB48(ADD48(dp->dccps_gss, 1), dp->dccps_l_seq_win);
-	/* Adjust AWL so that it is not below ISS - see comment above for SWL */
-	if (before48(dp->dccps_awl, dp->dccps_iss))
-		dp->dccps_awl = dp->dccps_iss;
-	dp->dccps_awh = dp->dccps_gss;
-}
-
-static inline int dccp_ackvec_pending(const struct sock *sk)
-{
-	return dccp_sk(sk)->dccps_hc_rx_ackvec != NULL &&
-	       !dccp_ackvec_is_empty(dccp_sk(sk)->dccps_hc_rx_ackvec);
-}
-
-static inline int dccp_ack_pending(const struct sock *sk)
-{
-	return dccp_ackvec_pending(sk) || inet_csk_ack_scheduled(sk);
-}
-
-int dccp_feat_signal_nn_change(struct sock *sk, u8 feat, u64 nn_val);
-int dccp_feat_finalise_settings(struct dccp_sock *dp);
-int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq);
-int dccp_feat_insert_opts(struct dccp_sock*, struct dccp_request_sock*,
-			  struct sk_buff *skb);
-int dccp_feat_activate_values(struct sock *sk, struct list_head *fn);
-void dccp_feat_list_purge(struct list_head *fn_list);
-
-int dccp_insert_options(struct sock *sk, struct sk_buff *skb);
-int dccp_insert_options_rsk(struct dccp_request_sock *, struct sk_buff *);
-u32 dccp_timestamp(void);
-void dccp_timestamping_init(void);
-int dccp_insert_option(struct sk_buff *skb, unsigned char option,
-		       const void *value, unsigned char len);
-
-#ifdef CONFIG_SYSCTL
-int dccp_sysctl_init(void);
-void dccp_sysctl_exit(void);
-#else
-static inline int dccp_sysctl_init(void)
-{
-	return 0;
-}
-
-static inline void dccp_sysctl_exit(void)
-{
-}
-#endif
-
-#endif /* _DCCP_H */
diff --git a/net/dccp/diag.c b/net/dccp/diag.c
deleted file mode 100644
index f5019d95c3ae..000000000000
--- a/net/dccp/diag.c
+++ /dev/null
@@ -1,85 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  net/dccp/diag.c
- *
- *  An implementation of the DCCP protocol
- *  Arnaldo Carvalho de Melo <acme@mandriva.com>
- */
-
-
-#include <linux/module.h>
-#include <linux/inet_diag.h>
-
-#include "ccid.h"
-#include "dccp.h"
-
-static void dccp_get_info(struct sock *sk, struct tcp_info *info)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	const struct inet_connection_sock *icsk = inet_csk(sk);
-
-	memset(info, 0, sizeof(*info));
-
-	info->tcpi_state	= sk->sk_state;
-	info->tcpi_retransmits	= icsk->icsk_retransmits;
-	info->tcpi_probes	= icsk->icsk_probes_out;
-	info->tcpi_backoff	= icsk->icsk_backoff;
-	info->tcpi_pmtu		= icsk->icsk_pmtu_cookie;
-
-	if (dp->dccps_hc_rx_ackvec != NULL)
-		info->tcpi_options |= TCPI_OPT_SACK;
-
-	if (dp->dccps_hc_rx_ccid != NULL)
-		ccid_hc_rx_get_info(dp->dccps_hc_rx_ccid, sk, info);
-
-	if (dp->dccps_hc_tx_ccid != NULL)
-		ccid_hc_tx_get_info(dp->dccps_hc_tx_ccid, sk, info);
-}
-
-static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
-			       void *_info)
-{
-	r->idiag_rqueue = r->idiag_wqueue = 0;
-
-	if (_info != NULL)
-		dccp_get_info(sk, _info);
-}
-
-static void dccp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
-			   const struct inet_diag_req_v2 *r)
-{
-	inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r);
-}
-
-static int dccp_diag_dump_one(struct netlink_callback *cb,
-			      const struct inet_diag_req_v2 *req)
-{
-	return inet_diag_dump_one_icsk(&dccp_hashinfo, cb, req);
-}
-
-static const struct inet_diag_handler dccp_diag_handler = {
-	.owner		 = THIS_MODULE,
-	.dump		 = dccp_diag_dump,
-	.dump_one	 = dccp_diag_dump_one,
-	.idiag_get_info	 = dccp_diag_get_info,
-	.idiag_type	 = IPPROTO_DCCP,
-	.idiag_info_size = sizeof(struct tcp_info),
-};
-
-static int __init dccp_diag_init(void)
-{
-	return inet_diag_register(&dccp_diag_handler);
-}
-
-static void __exit dccp_diag_fini(void)
-{
-	inet_diag_unregister(&dccp_diag_handler);
-}
-
-module_init(dccp_diag_init);
-module_exit(dccp_diag_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>");
-MODULE_DESCRIPTION("DCCP inet_diag handler");
-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-33 /* AF_INET - IPPROTO_DCCP */);
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
deleted file mode 100644
index f7554dcdaaba..000000000000
--- a/net/dccp/feat.c
+++ /dev/null
@@ -1,1581 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  net/dccp/feat.c
- *
- *  Feature negotiation for the DCCP protocol (RFC 4340, section 6)
- *
- *  Copyright (c) 2008 Gerrit Renker <gerrit@erg.abdn.ac.uk>
- *  Rewrote from scratch, some bits from earlier code by
- *  Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk>
- *
- *  ASSUMPTIONS
- *  -----------
- *  o Feature negotiation is coordinated with connection setup (as in TCP), wild
- *    changes of parameters of an established connection are not supported.
- *  o Changing non-negotiable (NN) values is supported in state OPEN/PARTOPEN.
- *  o All currently known SP features have 1-byte quantities. If in the future
- *    extensions of RFCs 4340..42 define features with item lengths larger than
- *    one byte, a feature-specific extension of the code will be required.
- */
-#include <linux/module.h>
-#include <linux/slab.h>
-#include "ccid.h"
-#include "feat.h"
-
-/* feature-specific sysctls - initialised to the defaults from RFC 4340, 6.4 */
-unsigned long	sysctl_dccp_sequence_window __read_mostly = 100;
-int		sysctl_dccp_rx_ccid	    __read_mostly = 2,
-		sysctl_dccp_tx_ccid	    __read_mostly = 2;
-
-/*
- * Feature activation handlers.
- *
- * These all use an u64 argument, to provide enough room for NN/SP features. At
- * this stage the negotiated values have been checked to be within their range.
- */
-static int dccp_hdlr_ccid(struct sock *sk, u64 ccid, bool rx)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct ccid *new_ccid = ccid_new(ccid, sk, rx);
-
-	if (new_ccid == NULL)
-		return -ENOMEM;
-
-	if (rx) {
-		ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
-		dp->dccps_hc_rx_ccid = new_ccid;
-	} else {
-		ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
-		dp->dccps_hc_tx_ccid = new_ccid;
-	}
-	return 0;
-}
-
-static int dccp_hdlr_seq_win(struct sock *sk, u64 seq_win, bool rx)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-
-	if (rx) {
-		dp->dccps_r_seq_win = seq_win;
-		/* propagate changes to update SWL/SWH */
-		dccp_update_gsr(sk, dp->dccps_gsr);
-	} else {
-		dp->dccps_l_seq_win = seq_win;
-		/* propagate changes to update AWL */
-		dccp_update_gss(sk, dp->dccps_gss);
-	}
-	return 0;
-}
-
-static int dccp_hdlr_ack_ratio(struct sock *sk, u64 ratio, bool rx)
-{
-	if (rx)
-		dccp_sk(sk)->dccps_r_ack_ratio = ratio;
-	else
-		dccp_sk(sk)->dccps_l_ack_ratio = ratio;
-	return 0;
-}
-
-static int dccp_hdlr_ackvec(struct sock *sk, u64 enable, bool rx)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-
-	if (rx) {
-		if (enable && dp->dccps_hc_rx_ackvec == NULL) {
-			dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(gfp_any());
-			if (dp->dccps_hc_rx_ackvec == NULL)
-				return -ENOMEM;
-		} else if (!enable) {
-			dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
-			dp->dccps_hc_rx_ackvec = NULL;
-		}
-	}
-	return 0;
-}
-
-static int dccp_hdlr_ndp(struct sock *sk, u64 enable, bool rx)
-{
-	if (!rx)
-		dccp_sk(sk)->dccps_send_ndp_count = (enable > 0);
-	return 0;
-}
-
-/*
- * Minimum Checksum Coverage is located at the RX side (9.2.1). This means that
- * `rx' holds when the sending peer informs about his partial coverage via a
- * ChangeR() option. In the other case, we are the sender and the receiver
- * announces its coverage via ChangeL() options. The policy here is to honour
- * such communication by enabling the corresponding partial coverage - but only
- * if it has not been set manually before; the warning here means that all
- * packets will be dropped.
- */
-static int dccp_hdlr_min_cscov(struct sock *sk, u64 cscov, bool rx)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-
-	if (rx)
-		dp->dccps_pcrlen = cscov;
-	else {
-		if (dp->dccps_pcslen == 0)
-			dp->dccps_pcslen = cscov;
-		else if (cscov > dp->dccps_pcslen)
-			DCCP_WARN("CsCov %u too small, peer requires >= %u\n",
-				  dp->dccps_pcslen, (u8)cscov);
-	}
-	return 0;
-}
-
-static const struct {
-	u8			feat_num;		/* DCCPF_xxx */
-	enum dccp_feat_type	rxtx;			/* RX or TX  */
-	enum dccp_feat_type	reconciliation;		/* SP or NN  */
-	u8			default_value;		/* as in 6.4 */
-	int (*activation_hdlr)(struct sock *sk, u64 val, bool rx);
-/*
- *    Lookup table for location and type of features (from RFC 4340/4342)
- *  +--------------------------+----+-----+----+----+---------+-----------+
- *  | Feature                  | Location | Reconc. | Initial |  Section  |
- *  |                          | RX | TX  | SP | NN |  Value  | Reference |
- *  +--------------------------+----+-----+----+----+---------+-----------+
- *  | DCCPF_CCID               |    |  X  | X  |    |   2     | 10        |
- *  | DCCPF_SHORT_SEQNOS       |    |  X  | X  |    |   0     |  7.6.1    |
- *  | DCCPF_SEQUENCE_WINDOW    |    |  X  |    | X  | 100     |  7.5.2    |
- *  | DCCPF_ECN_INCAPABLE      | X  |     | X  |    |   0     | 12.1      |
- *  | DCCPF_ACK_RATIO          |    |  X  |    | X  |   2     | 11.3      |
- *  | DCCPF_SEND_ACK_VECTOR    | X  |     | X  |    |   0     | 11.5      |
- *  | DCCPF_SEND_NDP_COUNT     |    |  X  | X  |    |   0     |  7.7.2    |
- *  | DCCPF_MIN_CSUM_COVER     | X  |     | X  |    |   0     |  9.2.1    |
- *  | DCCPF_DATA_CHECKSUM      | X  |     | X  |    |   0     |  9.3.1    |
- *  | DCCPF_SEND_LEV_RATE      | X  |     | X  |    |   0     | 4342/8.4  |
- *  +--------------------------+----+-----+----+----+---------+-----------+
- */
-} dccp_feat_table[] = {
-	{ DCCPF_CCID,		 FEAT_AT_TX, FEAT_SP, 2,   dccp_hdlr_ccid     },
-	{ DCCPF_SHORT_SEQNOS,	 FEAT_AT_TX, FEAT_SP, 0,   NULL },
-	{ DCCPF_SEQUENCE_WINDOW, FEAT_AT_TX, FEAT_NN, 100, dccp_hdlr_seq_win  },
-	{ DCCPF_ECN_INCAPABLE,	 FEAT_AT_RX, FEAT_SP, 0,   NULL },
-	{ DCCPF_ACK_RATIO,	 FEAT_AT_TX, FEAT_NN, 2,   dccp_hdlr_ack_ratio},
-	{ DCCPF_SEND_ACK_VECTOR, FEAT_AT_RX, FEAT_SP, 0,   dccp_hdlr_ackvec   },
-	{ DCCPF_SEND_NDP_COUNT,  FEAT_AT_TX, FEAT_SP, 0,   dccp_hdlr_ndp      },
-	{ DCCPF_MIN_CSUM_COVER,  FEAT_AT_RX, FEAT_SP, 0,   dccp_hdlr_min_cscov},
-	{ DCCPF_DATA_CHECKSUM,	 FEAT_AT_RX, FEAT_SP, 0,   NULL },
-	{ DCCPF_SEND_LEV_RATE,	 FEAT_AT_RX, FEAT_SP, 0,   NULL },
-};
-#define DCCP_FEAT_SUPPORTED_MAX		ARRAY_SIZE(dccp_feat_table)
-
-/**
- * dccp_feat_index  -  Hash function to map feature number into array position
- * @feat_num: feature to hash, one of %dccp_feature_numbers
- *
- * Returns consecutive array index or -1 if the feature is not understood.
- */
-static int dccp_feat_index(u8 feat_num)
-{
-	/* The first 9 entries are occupied by the types from RFC 4340, 6.4 */
-	if (feat_num > DCCPF_RESERVED && feat_num <= DCCPF_DATA_CHECKSUM)
-		return feat_num - 1;
-
-	/*
-	 * Other features: add cases for new feature types here after adding
-	 * them to the above table.
-	 */
-	switch (feat_num) {
-	case DCCPF_SEND_LEV_RATE:
-			return DCCP_FEAT_SUPPORTED_MAX - 1;
-	}
-	return -1;
-}
-
-static u8 dccp_feat_type(u8 feat_num)
-{
-	int idx = dccp_feat_index(feat_num);
-
-	if (idx < 0)
-		return FEAT_UNKNOWN;
-	return dccp_feat_table[idx].reconciliation;
-}
-
-static int dccp_feat_default_value(u8 feat_num)
-{
-	int idx = dccp_feat_index(feat_num);
-	/*
-	 * There are no default values for unknown features, so encountering a
-	 * negative index here indicates a serious problem somewhere else.
-	 */
-	DCCP_BUG_ON(idx < 0);
-
-	return idx < 0 ? 0 : dccp_feat_table[idx].default_value;
-}
-
-/*
- *	Debugging and verbose-printing section
- */
-static const char *dccp_feat_fname(const u8 feat)
-{
-	static const char *const feature_names[] = {
-		[DCCPF_RESERVED]	= "Reserved",
-		[DCCPF_CCID]		= "CCID",
-		[DCCPF_SHORT_SEQNOS]	= "Allow Short Seqnos",
-		[DCCPF_SEQUENCE_WINDOW]	= "Sequence Window",
-		[DCCPF_ECN_INCAPABLE]	= "ECN Incapable",
-		[DCCPF_ACK_RATIO]	= "Ack Ratio",
-		[DCCPF_SEND_ACK_VECTOR]	= "Send ACK Vector",
-		[DCCPF_SEND_NDP_COUNT]	= "Send NDP Count",
-		[DCCPF_MIN_CSUM_COVER]	= "Min. Csum Coverage",
-		[DCCPF_DATA_CHECKSUM]	= "Send Data Checksum",
-	};
-	if (feat > DCCPF_DATA_CHECKSUM && feat < DCCPF_MIN_CCID_SPECIFIC)
-		return feature_names[DCCPF_RESERVED];
-
-	if (feat ==  DCCPF_SEND_LEV_RATE)
-		return "Send Loss Event Rate";
-	if (feat >= DCCPF_MIN_CCID_SPECIFIC)
-		return "CCID-specific";
-
-	return feature_names[feat];
-}
-
-static const char *const dccp_feat_sname[] = {
-	"DEFAULT", "INITIALISING", "CHANGING", "UNSTABLE", "STABLE",
-};
-
-#ifdef CONFIG_IP_DCCP_DEBUG
-static const char *dccp_feat_oname(const u8 opt)
-{
-	switch (opt) {
-	case DCCPO_CHANGE_L:  return "Change_L";
-	case DCCPO_CONFIRM_L: return "Confirm_L";
-	case DCCPO_CHANGE_R:  return "Change_R";
-	case DCCPO_CONFIRM_R: return "Confirm_R";
-	}
-	return NULL;
-}
-
-static void dccp_feat_printval(u8 feat_num, dccp_feat_val const *val)
-{
-	u8 i, type = dccp_feat_type(feat_num);
-
-	if (val == NULL || (type == FEAT_SP && val->sp.vec == NULL))
-		dccp_pr_debug_cat("(NULL)");
-	else if (type == FEAT_SP)
-		for (i = 0; i < val->sp.len; i++)
-			dccp_pr_debug_cat("%s%u", i ? " " : "", val->sp.vec[i]);
-	else if (type == FEAT_NN)
-		dccp_pr_debug_cat("%llu", (unsigned long long)val->nn);
-	else
-		dccp_pr_debug_cat("unknown type %u", type);
-}
-
-static void dccp_feat_printvals(u8 feat_num, u8 *list, u8 len)
-{
-	u8 type = dccp_feat_type(feat_num);
-	dccp_feat_val fval = { .sp.vec = list, .sp.len = len };
-
-	if (type == FEAT_NN)
-		fval.nn = dccp_decode_value_var(list, len);
-	dccp_feat_printval(feat_num, &fval);
-}
-
-static void dccp_feat_print_entry(struct dccp_feat_entry const *entry)
-{
-	dccp_debug("   * %s %s = ", entry->is_local ? "local" : "remote",
-				    dccp_feat_fname(entry->feat_num));
-	dccp_feat_printval(entry->feat_num, &entry->val);
-	dccp_pr_debug_cat(", state=%s %s\n", dccp_feat_sname[entry->state],
-			  entry->needs_confirm ? "(Confirm pending)" : "");
-}
-
-#define dccp_feat_print_opt(opt, feat, val, len, mandatory)	do {	      \
-	dccp_pr_debug("%s(%s, ", dccp_feat_oname(opt), dccp_feat_fname(feat));\
-	dccp_feat_printvals(feat, val, len);				      \
-	dccp_pr_debug_cat(") %s\n", mandatory ? "!" : "");	} while (0)
-
-#define dccp_feat_print_fnlist(fn_list)  {		\
-	const struct dccp_feat_entry *___entry;		\
-							\
-	dccp_pr_debug("List Dump:\n");			\
-	list_for_each_entry(___entry, fn_list, node)	\
-		dccp_feat_print_entry(___entry);	\
-}
-#else	/* ! CONFIG_IP_DCCP_DEBUG */
-#define dccp_feat_print_opt(opt, feat, val, len, mandatory)
-#define dccp_feat_print_fnlist(fn_list)
-#endif
-
-static int __dccp_feat_activate(struct sock *sk, const int idx,
-				const bool is_local, dccp_feat_val const *fval)
-{
-	bool rx;
-	u64 val;
-
-	if (idx < 0 || idx >= DCCP_FEAT_SUPPORTED_MAX)
-		return -1;
-	if (dccp_feat_table[idx].activation_hdlr == NULL)
-		return 0;
-
-	if (fval == NULL) {
-		val = dccp_feat_table[idx].default_value;
-	} else if (dccp_feat_table[idx].reconciliation == FEAT_SP) {
-		if (fval->sp.vec == NULL) {
-			/*
-			 * This can happen when an empty Confirm is sent
-			 * for an SP (i.e. known) feature. In this case
-			 * we would be using the default anyway.
-			 */
-			DCCP_CRIT("Feature #%d undefined: using default", idx);
-			val = dccp_feat_table[idx].default_value;
-		} else {
-			val = fval->sp.vec[0];
-		}
-	} else {
-		val = fval->nn;
-	}
-
-	/* Location is RX if this is a local-RX or remote-TX feature */
-	rx = (is_local == (dccp_feat_table[idx].rxtx == FEAT_AT_RX));
-
-	dccp_debug("   -> activating %s %s, %sval=%llu\n", rx ? "RX" : "TX",
-		   dccp_feat_fname(dccp_feat_table[idx].feat_num),
-		   fval ? "" : "default ",  (unsigned long long)val);
-
-	return dccp_feat_table[idx].activation_hdlr(sk, val, rx);
-}
-
-/**
- * dccp_feat_activate  -  Activate feature value on socket
- * @sk: fully connected DCCP socket (after handshake is complete)
- * @feat_num: feature to activate, one of %dccp_feature_numbers
- * @local: whether local (1) or remote (0) @feat_num is meant
- * @fval: the value (SP or NN) to activate, or NULL to use the default value
- *
- * For general use this function is preferable over __dccp_feat_activate().
- */
-static int dccp_feat_activate(struct sock *sk, u8 feat_num, bool local,
-			      dccp_feat_val const *fval)
-{
-	return __dccp_feat_activate(sk, dccp_feat_index(feat_num), local, fval);
-}
-
-/* Test for "Req'd" feature (RFC 4340, 6.4) */
-static inline int dccp_feat_must_be_understood(u8 feat_num)
-{
-	return	feat_num == DCCPF_CCID || feat_num == DCCPF_SHORT_SEQNOS ||
-		feat_num == DCCPF_SEQUENCE_WINDOW;
-}
-
-/* copy constructor, fval must not already contain allocated memory */
-static int dccp_feat_clone_sp_val(dccp_feat_val *fval, u8 const *val, u8 len)
-{
-	fval->sp.len = len;
-	if (fval->sp.len > 0) {
-		fval->sp.vec = kmemdup(val, len, gfp_any());
-		if (fval->sp.vec == NULL) {
-			fval->sp.len = 0;
-			return -ENOMEM;
-		}
-	}
-	return 0;
-}
-
-static void dccp_feat_val_destructor(u8 feat_num, dccp_feat_val *val)
-{
-	if (unlikely(val == NULL))
-		return;
-	if (dccp_feat_type(feat_num) == FEAT_SP)
-		kfree(val->sp.vec);
-	memset(val, 0, sizeof(*val));
-}
-
-static struct dccp_feat_entry *
-	      dccp_feat_clone_entry(struct dccp_feat_entry const *original)
-{
-	struct dccp_feat_entry *new;
-	u8 type = dccp_feat_type(original->feat_num);
-
-	if (type == FEAT_UNKNOWN)
-		return NULL;
-
-	new = kmemdup(original, sizeof(struct dccp_feat_entry), gfp_any());
-	if (new == NULL)
-		return NULL;
-
-	if (type == FEAT_SP && dccp_feat_clone_sp_val(&new->val,
-						      original->val.sp.vec,
-						      original->val.sp.len)) {
-		kfree(new);
-		return NULL;
-	}
-	return new;
-}
-
-static void dccp_feat_entry_destructor(struct dccp_feat_entry *entry)
-{
-	if (entry != NULL) {
-		dccp_feat_val_destructor(entry->feat_num, &entry->val);
-		kfree(entry);
-	}
-}
-
-/*
- * List management functions
- *
- * Feature negotiation lists rely on and maintain the following invariants:
- * - each feat_num in the list is known, i.e. we know its type and default value
- * - each feat_num/is_local combination is unique (old entries are overwritten)
- * - SP values are always freshly allocated
- * - list is sorted in increasing order of feature number (faster lookup)
- */
-static struct dccp_feat_entry *dccp_feat_list_lookup(struct list_head *fn_list,
-						     u8 feat_num, bool is_local)
-{
-	struct dccp_feat_entry *entry;
-
-	list_for_each_entry(entry, fn_list, node) {
-		if (entry->feat_num == feat_num && entry->is_local == is_local)
-			return entry;
-		else if (entry->feat_num > feat_num)
-			break;
-	}
-	return NULL;
-}
-
-/**
- * dccp_feat_entry_new  -  Central list update routine (called by all others)
- * @head:  list to add to
- * @feat:  feature number
- * @local: whether the local (1) or remote feature with number @feat is meant
- *
- * This is the only constructor and serves to ensure the above invariants.
- */
-static struct dccp_feat_entry *
-	      dccp_feat_entry_new(struct list_head *head, u8 feat, bool local)
-{
-	struct dccp_feat_entry *entry;
-
-	list_for_each_entry(entry, head, node)
-		if (entry->feat_num == feat && entry->is_local == local) {
-			dccp_feat_val_destructor(entry->feat_num, &entry->val);
-			return entry;
-		} else if (entry->feat_num > feat) {
-			head = &entry->node;
-			break;
-		}
-
-	entry = kmalloc(sizeof(*entry), gfp_any());
-	if (entry != NULL) {
-		entry->feat_num = feat;
-		entry->is_local = local;
-		list_add_tail(&entry->node, head);
-	}
-	return entry;
-}
-
-/**
- * dccp_feat_push_change  -  Add/overwrite a Change option in the list
- * @fn_list: feature-negotiation list to update
- * @feat: one of %dccp_feature_numbers
- * @local: whether local (1) or remote (0) @feat_num is meant
- * @mandatory: whether to use Mandatory feature negotiation options
- * @fval: pointer to NN/SP value to be inserted (will be copied)
- */
-static int dccp_feat_push_change(struct list_head *fn_list, u8 feat, u8 local,
-				 u8 mandatory, dccp_feat_val *fval)
-{
-	struct dccp_feat_entry *new = dccp_feat_entry_new(fn_list, feat, local);
-
-	if (new == NULL)
-		return -ENOMEM;
-
-	new->feat_num	     = feat;
-	new->is_local	     = local;
-	new->state	     = FEAT_INITIALISING;
-	new->needs_confirm   = false;
-	new->empty_confirm   = false;
-	new->val	     = *fval;
-	new->needs_mandatory = mandatory;
-
-	return 0;
-}
-
-/**
- * dccp_feat_push_confirm  -  Add a Confirm entry to the FN list
- * @fn_list: feature-negotiation list to add to
- * @feat: one of %dccp_feature_numbers
- * @local: whether local (1) or remote (0) @feat_num is being confirmed
- * @fval: pointer to NN/SP value to be inserted or NULL
- *
- * Returns 0 on success, a Reset code for further processing otherwise.
- */
-static int dccp_feat_push_confirm(struct list_head *fn_list, u8 feat, u8 local,
-				  dccp_feat_val *fval)
-{
-	struct dccp_feat_entry *new = dccp_feat_entry_new(fn_list, feat, local);
-
-	if (new == NULL)
-		return DCCP_RESET_CODE_TOO_BUSY;
-
-	new->feat_num	     = feat;
-	new->is_local	     = local;
-	new->state	     = FEAT_STABLE;	/* transition in 6.6.2 */
-	new->needs_confirm   = true;
-	new->empty_confirm   = (fval == NULL);
-	new->val.nn	     = 0;		/* zeroes the whole structure */
-	if (!new->empty_confirm)
-		new->val     = *fval;
-	new->needs_mandatory = false;
-
-	return 0;
-}
-
-static int dccp_push_empty_confirm(struct list_head *fn_list, u8 feat, u8 local)
-{
-	return dccp_feat_push_confirm(fn_list, feat, local, NULL);
-}
-
-static inline void dccp_feat_list_pop(struct dccp_feat_entry *entry)
-{
-	list_del(&entry->node);
-	dccp_feat_entry_destructor(entry);
-}
-
-void dccp_feat_list_purge(struct list_head *fn_list)
-{
-	struct dccp_feat_entry *entry, *next;
-
-	list_for_each_entry_safe(entry, next, fn_list, node)
-		dccp_feat_entry_destructor(entry);
-	INIT_LIST_HEAD(fn_list);
-}
-EXPORT_SYMBOL_GPL(dccp_feat_list_purge);
-
-/* generate @to as full clone of @from - @to must not contain any nodes */
-int dccp_feat_clone_list(struct list_head const *from, struct list_head *to)
-{
-	struct dccp_feat_entry *entry, *new;
-
-	INIT_LIST_HEAD(to);
-	list_for_each_entry(entry, from, node) {
-		new = dccp_feat_clone_entry(entry);
-		if (new == NULL)
-			goto cloning_failed;
-		list_add_tail(&new->node, to);
-	}
-	return 0;
-
-cloning_failed:
-	dccp_feat_list_purge(to);
-	return -ENOMEM;
-}
-
-/**
- * dccp_feat_valid_nn_length  -  Enforce length constraints on NN options
- * @feat_num: feature to return length of, one of %dccp_feature_numbers
- *
- * Length is between 0 and %DCCP_OPTVAL_MAXLEN. Used for outgoing packets only,
- * incoming options are accepted as long as their values are valid.
- */
-static u8 dccp_feat_valid_nn_length(u8 feat_num)
-{
-	if (feat_num == DCCPF_ACK_RATIO)	/* RFC 4340, 11.3 and 6.6.8 */
-		return 2;
-	if (feat_num == DCCPF_SEQUENCE_WINDOW)	/* RFC 4340, 7.5.2 and 6.5  */
-		return 6;
-	return 0;
-}
-
-static u8 dccp_feat_is_valid_nn_val(u8 feat_num, u64 val)
-{
-	switch (feat_num) {
-	case DCCPF_ACK_RATIO:
-		return val <= DCCPF_ACK_RATIO_MAX;
-	case DCCPF_SEQUENCE_WINDOW:
-		return val >= DCCPF_SEQ_WMIN && val <= DCCPF_SEQ_WMAX;
-	}
-	return 0;	/* feature unknown - so we can't tell */
-}
-
-/* check that SP values are within the ranges defined in RFC 4340 */
-static u8 dccp_feat_is_valid_sp_val(u8 feat_num, u8 val)
-{
-	switch (feat_num) {
-	case DCCPF_CCID:
-		return val == DCCPC_CCID2 || val == DCCPC_CCID3;
-	/* Type-check Boolean feature values: */
-	case DCCPF_SHORT_SEQNOS:
-	case DCCPF_ECN_INCAPABLE:
-	case DCCPF_SEND_ACK_VECTOR:
-	case DCCPF_SEND_NDP_COUNT:
-	case DCCPF_DATA_CHECKSUM:
-	case DCCPF_SEND_LEV_RATE:
-		return val < 2;
-	case DCCPF_MIN_CSUM_COVER:
-		return val < 16;
-	}
-	return 0;			/* feature unknown */
-}
-
-static u8 dccp_feat_sp_list_ok(u8 feat_num, u8 const *sp_list, u8 sp_len)
-{
-	if (sp_list == NULL || sp_len < 1)
-		return 0;
-	while (sp_len--)
-		if (!dccp_feat_is_valid_sp_val(feat_num, *sp_list++))
-			return 0;
-	return 1;
-}
-
-/**
- * dccp_feat_insert_opts  -  Generate FN options from current list state
- * @skb: next sk_buff to be sent to the peer
- * @dp: for client during handshake and general negotiation
- * @dreq: used by the server only (all Changes/Confirms in LISTEN/RESPOND)
- */
-int dccp_feat_insert_opts(struct dccp_sock *dp, struct dccp_request_sock *dreq,
-			  struct sk_buff *skb)
-{
-	struct list_head *fn = dreq ? &dreq->dreq_featneg : &dp->dccps_featneg;
-	struct dccp_feat_entry *pos, *next;
-	u8 opt, type, len, *ptr, nn_in_nbo[DCCP_OPTVAL_MAXLEN];
-	bool rpt;
-
-	/* put entries into @skb in the order they appear in the list */
-	list_for_each_entry_safe_reverse(pos, next, fn, node) {
-		opt  = dccp_feat_genopt(pos);
-		type = dccp_feat_type(pos->feat_num);
-		rpt  = false;
-
-		if (pos->empty_confirm) {
-			len = 0;
-			ptr = NULL;
-		} else {
-			if (type == FEAT_SP) {
-				len = pos->val.sp.len;
-				ptr = pos->val.sp.vec;
-				rpt = pos->needs_confirm;
-			} else if (type == FEAT_NN) {
-				len = dccp_feat_valid_nn_length(pos->feat_num);
-				ptr = nn_in_nbo;
-				dccp_encode_value_var(pos->val.nn, ptr, len);
-			} else {
-				DCCP_BUG("unknown feature %u", pos->feat_num);
-				return -1;
-			}
-		}
-		dccp_feat_print_opt(opt, pos->feat_num, ptr, len, 0);
-
-		if (dccp_insert_fn_opt(skb, opt, pos->feat_num, ptr, len, rpt))
-			return -1;
-		if (pos->needs_mandatory && dccp_insert_option_mandatory(skb))
-			return -1;
-
-		if (skb->sk->sk_state == DCCP_OPEN &&
-		    (opt == DCCPO_CONFIRM_R || opt == DCCPO_CONFIRM_L)) {
-			/*
-			 * Confirms don't get retransmitted (6.6.3) once the
-			 * connection is in state OPEN
-			 */
-			dccp_feat_list_pop(pos);
-		} else {
-			/*
-			 * Enter CHANGING after transmitting the Change
-			 * option (6.6.2).
-			 */
-			if (pos->state == FEAT_INITIALISING)
-				pos->state = FEAT_CHANGING;
-		}
-	}
-	return 0;
-}
-
-/**
- * __feat_register_nn  -  Register new NN value on socket
- * @fn: feature-negotiation list to register with
- * @feat: an NN feature from %dccp_feature_numbers
- * @mandatory: use Mandatory option if 1
- * @nn_val: value to register (restricted to 4 bytes)
- *
- * Note that NN features are local by definition (RFC 4340, 6.3.2).
- */
-static int __feat_register_nn(struct list_head *fn, u8 feat,
-			      u8 mandatory, u64 nn_val)
-{
-	dccp_feat_val fval = { .nn = nn_val };
-
-	if (dccp_feat_type(feat) != FEAT_NN ||
-	    !dccp_feat_is_valid_nn_val(feat, nn_val))
-		return -EINVAL;
-
-	/* Don't bother with default values, they will be activated anyway. */
-	if (nn_val - (u64)dccp_feat_default_value(feat) == 0)
-		return 0;
-
-	return dccp_feat_push_change(fn, feat, 1, mandatory, &fval);
-}
-
-/**
- * __feat_register_sp  -  Register new SP value/list on socket
- * @fn: feature-negotiation list to register with
- * @feat: an SP feature from %dccp_feature_numbers
- * @is_local: whether the local (1) or the remote (0) @feat is meant
- * @mandatory: use Mandatory option if 1
- * @sp_val: SP value followed by optional preference list
- * @sp_len: length of @sp_val in bytes
- */
-static int __feat_register_sp(struct list_head *fn, u8 feat, u8 is_local,
-			      u8 mandatory, u8 const *sp_val, u8 sp_len)
-{
-	dccp_feat_val fval;
-
-	if (dccp_feat_type(feat) != FEAT_SP ||
-	    !dccp_feat_sp_list_ok(feat, sp_val, sp_len))
-		return -EINVAL;
-
-	/* Avoid negotiating alien CCIDs by only advertising supported ones */
-	if (feat == DCCPF_CCID && !ccid_support_check(sp_val, sp_len))
-		return -EOPNOTSUPP;
-
-	if (dccp_feat_clone_sp_val(&fval, sp_val, sp_len))
-		return -ENOMEM;
-
-	if (dccp_feat_push_change(fn, feat, is_local, mandatory, &fval)) {
-		kfree(fval.sp.vec);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-/**
- * dccp_feat_register_sp  -  Register requests to change SP feature values
- * @sk: client or listening socket
- * @feat: one of %dccp_feature_numbers
- * @is_local: whether the local (1) or remote (0) @feat is meant
- * @list: array of preferred values, in descending order of preference
- * @len: length of @list in bytes
- */
-int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local,
-			  u8 const *list, u8 len)
-{	 /* any changes must be registered before establishing the connection */
-	if (sk->sk_state != DCCP_CLOSED)
-		return -EISCONN;
-	if (dccp_feat_type(feat) != FEAT_SP)
-		return -EINVAL;
-	return __feat_register_sp(&dccp_sk(sk)->dccps_featneg, feat, is_local,
-				  0, list, len);
-}
-
-/**
- * dccp_feat_nn_get  -  Query current/pending value of NN feature
- * @sk: DCCP socket of an established connection
- * @feat: NN feature number from %dccp_feature_numbers
- *
- * For a known NN feature, returns value currently being negotiated, or
- * current (confirmed) value if no negotiation is going on.
- */
-u64 dccp_feat_nn_get(struct sock *sk, u8 feat)
-{
-	if (dccp_feat_type(feat) == FEAT_NN) {
-		struct dccp_sock *dp = dccp_sk(sk);
-		struct dccp_feat_entry *entry;
-
-		entry = dccp_feat_list_lookup(&dp->dccps_featneg, feat, 1);
-		if (entry != NULL)
-			return entry->val.nn;
-
-		switch (feat) {
-		case DCCPF_ACK_RATIO:
-			return dp->dccps_l_ack_ratio;
-		case DCCPF_SEQUENCE_WINDOW:
-			return dp->dccps_l_seq_win;
-		}
-	}
-	DCCP_BUG("attempt to look up unsupported feature %u", feat);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(dccp_feat_nn_get);
-
-/**
- * dccp_feat_signal_nn_change  -  Update NN values for an established connection
- * @sk: DCCP socket of an established connection
- * @feat: NN feature number from %dccp_feature_numbers
- * @nn_val: the new value to use
- *
- * This function is used to communicate NN updates out-of-band.
- */
-int dccp_feat_signal_nn_change(struct sock *sk, u8 feat, u64 nn_val)
-{
-	struct list_head *fn = &dccp_sk(sk)->dccps_featneg;
-	dccp_feat_val fval = { .nn = nn_val };
-	struct dccp_feat_entry *entry;
-
-	if (sk->sk_state != DCCP_OPEN && sk->sk_state != DCCP_PARTOPEN)
-		return 0;
-
-	if (dccp_feat_type(feat) != FEAT_NN ||
-	    !dccp_feat_is_valid_nn_val(feat, nn_val))
-		return -EINVAL;
-
-	if (nn_val == dccp_feat_nn_get(sk, feat))
-		return 0;	/* already set or negotiation under way */
-
-	entry = dccp_feat_list_lookup(fn, feat, 1);
-	if (entry != NULL) {
-		dccp_pr_debug("Clobbering existing NN entry %llu -> %llu\n",
-			      (unsigned long long)entry->val.nn,
-			      (unsigned long long)nn_val);
-		dccp_feat_list_pop(entry);
-	}
-
-	inet_csk_schedule_ack(sk);
-	return dccp_feat_push_change(fn, feat, 1, 0, &fval);
-}
-EXPORT_SYMBOL_GPL(dccp_feat_signal_nn_change);
-
-/*
- *	Tracking features whose value depend on the choice of CCID
- *
- * This is designed with an extension in mind so that a list walk could be done
- * before activating any features. However, the existing framework was found to
- * work satisfactorily up until now, the automatic verification is left open.
- * When adding new CCIDs, add a corresponding dependency table here.
- */
-static const struct ccid_dependency *dccp_feat_ccid_deps(u8 ccid, bool is_local)
-{
-	static const struct ccid_dependency ccid2_dependencies[2][2] = {
-		/*
-		 * CCID2 mandates Ack Vectors (RFC 4341, 4.): as CCID is a TX
-		 * feature and Send Ack Vector is an RX feature, `is_local'
-		 * needs to be reversed.
-		 */
-		{	/* Dependencies of the receiver-side (remote) CCID2 */
-			{
-				.dependent_feat	= DCCPF_SEND_ACK_VECTOR,
-				.is_local	= true,
-				.is_mandatory	= true,
-				.val		= 1
-			},
-			{ 0, 0, 0, 0 }
-		},
-		{	/* Dependencies of the sender-side (local) CCID2 */
-			{
-				.dependent_feat	= DCCPF_SEND_ACK_VECTOR,
-				.is_local	= false,
-				.is_mandatory	= true,
-				.val		= 1
-			},
-			{ 0, 0, 0, 0 }
-		}
-	};
-	static const struct ccid_dependency ccid3_dependencies[2][5] = {
-		{	/*
-			 * Dependencies of the receiver-side CCID3
-			 */
-			{	/* locally disable Ack Vectors */
-				.dependent_feat	= DCCPF_SEND_ACK_VECTOR,
-				.is_local	= true,
-				.is_mandatory	= false,
-				.val		= 0
-			},
-			{	/* see below why Send Loss Event Rate is on */
-				.dependent_feat	= DCCPF_SEND_LEV_RATE,
-				.is_local	= true,
-				.is_mandatory	= true,
-				.val		= 1
-			},
-			{	/* NDP Count is needed as per RFC 4342, 6.1.1 */
-				.dependent_feat	= DCCPF_SEND_NDP_COUNT,
-				.is_local	= false,
-				.is_mandatory	= true,
-				.val		= 1
-			},
-			{ 0, 0, 0, 0 },
-		},
-		{	/*
-			 * CCID3 at the TX side: we request that the HC-receiver
-			 * will not send Ack Vectors (they will be ignored, so
-			 * Mandatory is not set); we enable Send Loss Event Rate
-			 * (Mandatory since the implementation does not support
-			 * the Loss Intervals option of RFC 4342, 8.6).
-			 * The last two options are for peer's information only.
-			*/
-			{
-				.dependent_feat	= DCCPF_SEND_ACK_VECTOR,
-				.is_local	= false,
-				.is_mandatory	= false,
-				.val		= 0
-			},
-			{
-				.dependent_feat	= DCCPF_SEND_LEV_RATE,
-				.is_local	= false,
-				.is_mandatory	= true,
-				.val		= 1
-			},
-			{	/* this CCID does not support Ack Ratio */
-				.dependent_feat	= DCCPF_ACK_RATIO,
-				.is_local	= true,
-				.is_mandatory	= false,
-				.val		= 0
-			},
-			{	/* tell receiver we are sending NDP counts */
-				.dependent_feat	= DCCPF_SEND_NDP_COUNT,
-				.is_local	= true,
-				.is_mandatory	= false,
-				.val		= 1
-			},
-			{ 0, 0, 0, 0 }
-		}
-	};
-	switch (ccid) {
-	case DCCPC_CCID2:
-		return ccid2_dependencies[is_local];
-	case DCCPC_CCID3:
-		return ccid3_dependencies[is_local];
-	default:
-		return NULL;
-	}
-}
-
-/**
- * dccp_feat_propagate_ccid - Resolve dependencies of features on choice of CCID
- * @fn: feature-negotiation list to update
- * @id: CCID number to track
- * @is_local: whether TX CCID (1) or RX CCID (0) is meant
- *
- * This function needs to be called after registering all other features.
- */
-static int dccp_feat_propagate_ccid(struct list_head *fn, u8 id, bool is_local)
-{
-	const struct ccid_dependency *table = dccp_feat_ccid_deps(id, is_local);
-	int i, rc = (table == NULL);
-
-	for (i = 0; rc == 0 && table[i].dependent_feat != DCCPF_RESERVED; i++)
-		if (dccp_feat_type(table[i].dependent_feat) == FEAT_SP)
-			rc = __feat_register_sp(fn, table[i].dependent_feat,
-						    table[i].is_local,
-						    table[i].is_mandatory,
-						    &table[i].val, 1);
-		else
-			rc = __feat_register_nn(fn, table[i].dependent_feat,
-						    table[i].is_mandatory,
-						    table[i].val);
-	return rc;
-}
-
-/**
- * dccp_feat_finalise_settings  -  Finalise settings before starting negotiation
- * @dp: client or listening socket (settings will be inherited)
- *
- * This is called after all registrations (socket initialisation, sysctls, and
- * sockopt calls), and before sending the first packet containing Change options
- * (ie. client-Request or server-Response), to ensure internal consistency.
- */
-int dccp_feat_finalise_settings(struct dccp_sock *dp)
-{
-	struct list_head *fn = &dp->dccps_featneg;
-	struct dccp_feat_entry *entry;
-	int i = 2, ccids[2] = { -1, -1 };
-
-	/*
-	 * Propagating CCIDs:
-	 * 1) not useful to propagate CCID settings if this host advertises more
-	 *    than one CCID: the choice of CCID  may still change - if this is
-	 *    the client, or if this is the server and the client sends
-	 *    singleton CCID values.
-	 * 2) since is that propagate_ccid changes the list, we defer changing
-	 *    the sorted list until after the traversal.
-	 */
-	list_for_each_entry(entry, fn, node)
-		if (entry->feat_num == DCCPF_CCID && entry->val.sp.len == 1)
-			ccids[entry->is_local] = entry->val.sp.vec[0];
-	while (i--)
-		if (ccids[i] > 0 && dccp_feat_propagate_ccid(fn, ccids[i], i))
-			return -1;
-	dccp_feat_print_fnlist(fn);
-	return 0;
-}
-
-/**
- * dccp_feat_server_ccid_dependencies  -  Resolve CCID-dependent features
- * @dreq: server socket to resolve
- *
- * It is the server which resolves the dependencies once the CCID has been
- * fully negotiated. If no CCID has been negotiated, it uses the default CCID.
- */
-int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq)
-{
-	struct list_head *fn = &dreq->dreq_featneg;
-	struct dccp_feat_entry *entry;
-	u8 is_local, ccid;
-
-	for (is_local = 0; is_local <= 1; is_local++) {
-		entry = dccp_feat_list_lookup(fn, DCCPF_CCID, is_local);
-
-		if (entry != NULL && !entry->empty_confirm)
-			ccid = entry->val.sp.vec[0];
-		else
-			ccid = dccp_feat_default_value(DCCPF_CCID);
-
-		if (dccp_feat_propagate_ccid(fn, ccid, is_local))
-			return -1;
-	}
-	return 0;
-}
-
-/* Select the first entry in @servlist that also occurs in @clilist (6.3.1) */
-static int dccp_feat_preflist_match(u8 *servlist, u8 slen, u8 *clilist, u8 clen)
-{
-	u8 c, s;
-
-	for (s = 0; s < slen; s++)
-		for (c = 0; c < clen; c++)
-			if (servlist[s] == clilist[c])
-				return servlist[s];
-	return -1;
-}
-
-/**
- * dccp_feat_prefer  -  Move preferred entry to the start of array
- * @preferred_value: entry to move to start of array
- * @array: array of preferred entries
- * @array_len: size of the array
- *
- * Reorder the @array_len elements in @array so that @preferred_value comes
- * first. Returns >0 to indicate that @preferred_value does occur in @array.
- */
-static u8 dccp_feat_prefer(u8 preferred_value, u8 *array, u8 array_len)
-{
-	u8 i, does_occur = 0;
-
-	if (array != NULL) {
-		for (i = 0; i < array_len; i++)
-			if (array[i] == preferred_value) {
-				array[i] = array[0];
-				does_occur++;
-			}
-		if (does_occur)
-			array[0] = preferred_value;
-	}
-	return does_occur;
-}
-
-/**
- * dccp_feat_reconcile  -  Reconcile SP preference lists
- *  @fv: SP list to reconcile into
- *  @arr: received SP preference list
- *  @len: length of @arr in bytes
- *  @is_server: whether this side is the server (and @fv is the server's list)
- *  @reorder: whether to reorder the list in @fv after reconciling with @arr
- * When successful, > 0 is returned and the reconciled list is in @fval.
- * A value of 0 means that negotiation failed (no shared entry).
- */
-static int dccp_feat_reconcile(dccp_feat_val *fv, u8 *arr, u8 len,
-			       bool is_server, bool reorder)
-{
-	int rc;
-
-	if (!fv->sp.vec || !arr) {
-		DCCP_CRIT("NULL feature value or array");
-		return 0;
-	}
-
-	if (is_server)
-		rc = dccp_feat_preflist_match(fv->sp.vec, fv->sp.len, arr, len);
-	else
-		rc = dccp_feat_preflist_match(arr, len, fv->sp.vec, fv->sp.len);
-
-	if (!reorder)
-		return rc;
-	if (rc < 0)
-		return 0;
-
-	/*
-	 * Reorder list: used for activating features and in dccp_insert_fn_opt.
-	 */
-	return dccp_feat_prefer(rc, fv->sp.vec, fv->sp.len);
-}
-
-/**
- * dccp_feat_change_recv  -  Process incoming ChangeL/R options
- * @fn: feature-negotiation list to update
- * @is_mandatory: whether the Change was preceded by a Mandatory option
- * @opt: %DCCPO_CHANGE_L or %DCCPO_CHANGE_R
- * @feat: one of %dccp_feature_numbers
- * @val: NN value or SP value/preference list
- * @len: length of @val in bytes
- * @server: whether this node is the server (1) or the client (0)
- */
-static u8 dccp_feat_change_recv(struct list_head *fn, u8 is_mandatory, u8 opt,
-				u8 feat, u8 *val, u8 len, const bool server)
-{
-	u8 defval, type = dccp_feat_type(feat);
-	const bool local = (opt == DCCPO_CHANGE_R);
-	struct dccp_feat_entry *entry;
-	dccp_feat_val fval;
-
-	if (len == 0 || type == FEAT_UNKNOWN)		/* 6.1 and 6.6.8 */
-		goto unknown_feature_or_value;
-
-	dccp_feat_print_opt(opt, feat, val, len, is_mandatory);
-
-	/*
-	 *	Negotiation of NN features: Change R is invalid, so there is no
-	 *	simultaneous negotiation; hence we do not look up in the list.
-	 */
-	if (type == FEAT_NN) {
-		if (local || len > sizeof(fval.nn))
-			goto unknown_feature_or_value;
-
-		/* 6.3.2: "The feature remote MUST accept any valid value..." */
-		fval.nn = dccp_decode_value_var(val, len);
-		if (!dccp_feat_is_valid_nn_val(feat, fval.nn))
-			goto unknown_feature_or_value;
-
-		return dccp_feat_push_confirm(fn, feat, local, &fval);
-	}
-
-	/*
-	 *	Unidirectional/simultaneous negotiation of SP features (6.3.1)
-	 */
-	entry = dccp_feat_list_lookup(fn, feat, local);
-	if (entry == NULL) {
-		/*
-		 * No particular preferences have been registered. We deal with
-		 * this situation by assuming that all valid values are equally
-		 * acceptable, and apply the following checks:
-		 * - if the peer's list is a singleton, we accept a valid value;
-		 * - if we are the server, we first try to see if the peer (the
-		 *   client) advertises the default value. If yes, we use it,
-		 *   otherwise we accept the preferred value;
-		 * - else if we are the client, we use the first list element.
-		 */
-		if (dccp_feat_clone_sp_val(&fval, val, 1))
-			return DCCP_RESET_CODE_TOO_BUSY;
-
-		if (len > 1 && server) {
-			defval = dccp_feat_default_value(feat);
-			if (dccp_feat_preflist_match(&defval, 1, val, len) > -1)
-				fval.sp.vec[0] = defval;
-		} else if (!dccp_feat_is_valid_sp_val(feat, fval.sp.vec[0])) {
-			kfree(fval.sp.vec);
-			goto unknown_feature_or_value;
-		}
-
-		/* Treat unsupported CCIDs like invalid values */
-		if (feat == DCCPF_CCID && !ccid_support_check(fval.sp.vec, 1)) {
-			kfree(fval.sp.vec);
-			goto not_valid_or_not_known;
-		}
-
-		if (dccp_feat_push_confirm(fn, feat, local, &fval)) {
-			kfree(fval.sp.vec);
-			return DCCP_RESET_CODE_TOO_BUSY;
-		}
-
-		return 0;
-	} else if (entry->state == FEAT_UNSTABLE) {	/* 6.6.2 */
-		return 0;
-	}
-
-	if (dccp_feat_reconcile(&entry->val, val, len, server, true)) {
-		entry->empty_confirm = false;
-	} else if (is_mandatory) {
-		return DCCP_RESET_CODE_MANDATORY_ERROR;
-	} else if (entry->state == FEAT_INITIALISING) {
-		/*
-		 * Failed simultaneous negotiation (server only): try to `save'
-		 * the connection by checking whether entry contains the default
-		 * value for @feat. If yes, send an empty Confirm to signal that
-		 * the received Change was not understood - which implies using
-		 * the default value.
-		 * If this also fails, we use Reset as the last resort.
-		 */
-		WARN_ON(!server);
-		defval = dccp_feat_default_value(feat);
-		if (!dccp_feat_reconcile(&entry->val, &defval, 1, server, true))
-			return DCCP_RESET_CODE_OPTION_ERROR;
-		entry->empty_confirm = true;
-	}
-	entry->needs_confirm   = true;
-	entry->needs_mandatory = false;
-	entry->state	       = FEAT_STABLE;
-	return 0;
-
-unknown_feature_or_value:
-	if (!is_mandatory)
-		return dccp_push_empty_confirm(fn, feat, local);
-
-not_valid_or_not_known:
-	return is_mandatory ? DCCP_RESET_CODE_MANDATORY_ERROR
-			    : DCCP_RESET_CODE_OPTION_ERROR;
-}
-
-/**
- * dccp_feat_confirm_recv  -  Process received Confirm options
- * @fn: feature-negotiation list to update
- * @is_mandatory: whether @opt was preceded by a Mandatory option
- * @opt: %DCCPO_CONFIRM_L or %DCCPO_CONFIRM_R
- * @feat: one of %dccp_feature_numbers
- * @val: NN value or SP value/preference list
- * @len: length of @val in bytes
- * @server: whether this node is server (1) or client (0)
- */
-static u8 dccp_feat_confirm_recv(struct list_head *fn, u8 is_mandatory, u8 opt,
-				 u8 feat, u8 *val, u8 len, const bool server)
-{
-	u8 *plist, plen, type = dccp_feat_type(feat);
-	const bool local = (opt == DCCPO_CONFIRM_R);
-	struct dccp_feat_entry *entry = dccp_feat_list_lookup(fn, feat, local);
-
-	dccp_feat_print_opt(opt, feat, val, len, is_mandatory);
-
-	if (entry == NULL) {	/* nothing queued: ignore or handle error */
-		if (is_mandatory && type == FEAT_UNKNOWN)
-			return DCCP_RESET_CODE_MANDATORY_ERROR;
-
-		if (!local && type == FEAT_NN)		/* 6.3.2 */
-			goto confirmation_failed;
-		return 0;
-	}
-
-	if (entry->state != FEAT_CHANGING)		/* 6.6.2 */
-		return 0;
-
-	if (len == 0) {
-		if (dccp_feat_must_be_understood(feat))	/* 6.6.7 */
-			goto confirmation_failed;
-		/*
-		 * Empty Confirm during connection setup: this means reverting
-		 * to the `old' value, which in this case is the default. Since
-		 * we handle default values automatically when no other values
-		 * have been set, we revert to the old value by removing this
-		 * entry from the list.
-		 */
-		dccp_feat_list_pop(entry);
-		return 0;
-	}
-
-	if (type == FEAT_NN) {
-		if (len > sizeof(entry->val.nn))
-			goto confirmation_failed;
-
-		if (entry->val.nn == dccp_decode_value_var(val, len))
-			goto confirmation_succeeded;
-
-		DCCP_WARN("Bogus Confirm for non-existing value\n");
-		goto confirmation_failed;
-	}
-
-	/*
-	 * Parsing SP Confirms: the first element of @val is the preferred
-	 * SP value which the peer confirms, the remainder depends on @len.
-	 * Note that only the confirmed value need to be a valid SP value.
-	 */
-	if (!dccp_feat_is_valid_sp_val(feat, *val))
-		goto confirmation_failed;
-
-	if (len == 1) {		/* peer didn't supply a preference list */
-		plist = val;
-		plen  = len;
-	} else {		/* preferred value + preference list */
-		plist = val + 1;
-		plen  = len - 1;
-	}
-
-	/* Check whether the peer got the reconciliation right (6.6.8) */
-	if (dccp_feat_reconcile(&entry->val, plist, plen, server, 0) != *val) {
-		DCCP_WARN("Confirm selected the wrong value %u\n", *val);
-		return DCCP_RESET_CODE_OPTION_ERROR;
-	}
-	entry->val.sp.vec[0] = *val;
-
-confirmation_succeeded:
-	entry->state = FEAT_STABLE;
-	return 0;
-
-confirmation_failed:
-	DCCP_WARN("Confirmation failed\n");
-	return is_mandatory ? DCCP_RESET_CODE_MANDATORY_ERROR
-			    : DCCP_RESET_CODE_OPTION_ERROR;
-}
-
-/**
- * dccp_feat_handle_nn_established  -  Fast-path reception of NN options
- * @sk:		socket of an established DCCP connection
- * @mandatory:	whether @opt was preceded by a Mandatory option
- * @opt:	%DCCPO_CHANGE_L | %DCCPO_CONFIRM_R (NN only)
- * @feat:	NN number, one of %dccp_feature_numbers
- * @val:	NN value
- * @len:	length of @val in bytes
- *
- * This function combines the functionality of change_recv/confirm_recv, with
- * the following differences (reset codes are the same):
- *    - cleanup after receiving the Confirm;
- *    - values are directly activated after successful parsing;
- *    - deliberately restricted to NN features.
- * The restriction to NN features is essential since SP features can have non-
- * predictable outcomes (depending on the remote configuration), and are inter-
- * dependent (CCIDs for instance cause further dependencies).
- */
-static u8 dccp_feat_handle_nn_established(struct sock *sk, u8 mandatory, u8 opt,
-					  u8 feat, u8 *val, u8 len)
-{
-	struct list_head *fn = &dccp_sk(sk)->dccps_featneg;
-	const bool local = (opt == DCCPO_CONFIRM_R);
-	struct dccp_feat_entry *entry;
-	u8 type = dccp_feat_type(feat);
-	dccp_feat_val fval;
-
-	dccp_feat_print_opt(opt, feat, val, len, mandatory);
-
-	/* Ignore non-mandatory unknown and non-NN features */
-	if (type == FEAT_UNKNOWN) {
-		if (local && !mandatory)
-			return 0;
-		goto fast_path_unknown;
-	} else if (type != FEAT_NN) {
-		return 0;
-	}
-
-	/*
-	 * We don't accept empty Confirms, since in fast-path feature
-	 * negotiation the values are enabled immediately after sending
-	 * the Change option.
-	 * Empty Changes on the other hand are invalid (RFC 4340, 6.1).
-	 */
-	if (len == 0 || len > sizeof(fval.nn))
-		goto fast_path_unknown;
-
-	if (opt == DCCPO_CHANGE_L) {
-		fval.nn = dccp_decode_value_var(val, len);
-		if (!dccp_feat_is_valid_nn_val(feat, fval.nn))
-			goto fast_path_unknown;
-
-		if (dccp_feat_push_confirm(fn, feat, local, &fval) ||
-		    dccp_feat_activate(sk, feat, local, &fval))
-			return DCCP_RESET_CODE_TOO_BUSY;
-
-		/* set the `Ack Pending' flag to piggyback a Confirm */
-		inet_csk_schedule_ack(sk);
-
-	} else if (opt == DCCPO_CONFIRM_R) {
-		entry = dccp_feat_list_lookup(fn, feat, local);
-		if (entry == NULL || entry->state != FEAT_CHANGING)
-			return 0;
-
-		fval.nn = dccp_decode_value_var(val, len);
-		/*
-		 * Just ignore a value that doesn't match our current value.
-		 * If the option changes twice within two RTTs, then at least
-		 * one CONFIRM will be received for the old value after a
-		 * new CHANGE was sent.
-		 */
-		if (fval.nn != entry->val.nn)
-			return 0;
-
-		/* Only activate after receiving the Confirm option (6.6.1). */
-		dccp_feat_activate(sk, feat, local, &fval);
-
-		/* It has been confirmed - so remove the entry */
-		dccp_feat_list_pop(entry);
-
-	} else {
-		DCCP_WARN("Received illegal option %u\n", opt);
-		goto fast_path_failed;
-	}
-	return 0;
-
-fast_path_unknown:
-	if (!mandatory)
-		return dccp_push_empty_confirm(fn, feat, local);
-
-fast_path_failed:
-	return mandatory ? DCCP_RESET_CODE_MANDATORY_ERROR
-			 : DCCP_RESET_CODE_OPTION_ERROR;
-}
-
-/**
- * dccp_feat_parse_options  -  Process Feature-Negotiation Options
- * @sk: for general use and used by the client during connection setup
- * @dreq: used by the server during connection setup
- * @mandatory: whether @opt was preceded by a Mandatory option
- * @opt: %DCCPO_CHANGE_L | %DCCPO_CHANGE_R | %DCCPO_CONFIRM_L | %DCCPO_CONFIRM_R
- * @feat: one of %dccp_feature_numbers
- * @val: value contents of @opt
- * @len: length of @val in bytes
- *
- * Returns 0 on success, a Reset code for ending the connection otherwise.
- */
-int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
-			    u8 mandatory, u8 opt, u8 feat, u8 *val, u8 len)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct list_head *fn = dreq ? &dreq->dreq_featneg : &dp->dccps_featneg;
-	bool server = false;
-
-	switch (sk->sk_state) {
-	/*
-	 *	Negotiation during connection setup
-	 */
-	case DCCP_LISTEN:
-		server = true;
-		fallthrough;
-	case DCCP_REQUESTING:
-		switch (opt) {
-		case DCCPO_CHANGE_L:
-		case DCCPO_CHANGE_R:
-			return dccp_feat_change_recv(fn, mandatory, opt, feat,
-						     val, len, server);
-		case DCCPO_CONFIRM_R:
-		case DCCPO_CONFIRM_L:
-			return dccp_feat_confirm_recv(fn, mandatory, opt, feat,
-						      val, len, server);
-		}
-		break;
-	/*
-	 *	Support for exchanging NN options on an established connection.
-	 */
-	case DCCP_OPEN:
-	case DCCP_PARTOPEN:
-		return dccp_feat_handle_nn_established(sk, mandatory, opt, feat,
-						       val, len);
-	}
-	return 0;	/* ignore FN options in all other states */
-}
-
-/**
- * dccp_feat_init  -  Seed feature negotiation with host-specific defaults
- * @sk: Socket to initialize.
- *
- * This initialises global defaults, depending on the value of the sysctls.
- * These can later be overridden by registering changes via setsockopt calls.
- * The last link in the chain is finalise_settings, to make sure that between
- * here and the start of actual feature negotiation no inconsistencies enter.
- *
- * All features not appearing below use either defaults or are otherwise
- * later adjusted through dccp_feat_finalise_settings().
- */
-int dccp_feat_init(struct sock *sk)
-{
-	struct list_head *fn = &dccp_sk(sk)->dccps_featneg;
-	u8 on = 1, off = 0;
-	int rc;
-	struct {
-		u8 *val;
-		u8 len;
-	} tx, rx;
-
-	/* Non-negotiable (NN) features */
-	rc = __feat_register_nn(fn, DCCPF_SEQUENCE_WINDOW, 0,
-				    sysctl_dccp_sequence_window);
-	if (rc)
-		return rc;
-
-	/* Server-priority (SP) features */
-
-	/* Advertise that short seqnos are not supported (7.6.1) */
-	rc = __feat_register_sp(fn, DCCPF_SHORT_SEQNOS, true, true, &off, 1);
-	if (rc)
-		return rc;
-
-	/* RFC 4340 12.1: "If a DCCP is not ECN capable, ..." */
-	rc = __feat_register_sp(fn, DCCPF_ECN_INCAPABLE, true, true, &on, 1);
-	if (rc)
-		return rc;
-
-	/*
-	 * We advertise the available list of CCIDs and reorder according to
-	 * preferences, to avoid failure resulting from negotiating different
-	 * singleton values (which always leads to failure).
-	 * These settings can still (later) be overridden via sockopts.
-	 */
-	if (ccid_get_builtin_ccids(&tx.val, &tx.len))
-		return -ENOBUFS;
-	if (ccid_get_builtin_ccids(&rx.val, &rx.len)) {
-		kfree(tx.val);
-		return -ENOBUFS;
-	}
-
-	if (!dccp_feat_prefer(sysctl_dccp_tx_ccid, tx.val, tx.len) ||
-	    !dccp_feat_prefer(sysctl_dccp_rx_ccid, rx.val, rx.len))
-		goto free_ccid_lists;
-
-	rc = __feat_register_sp(fn, DCCPF_CCID, true, false, tx.val, tx.len);
-	if (rc)
-		goto free_ccid_lists;
-
-	rc = __feat_register_sp(fn, DCCPF_CCID, false, false, rx.val, rx.len);
-
-free_ccid_lists:
-	kfree(tx.val);
-	kfree(rx.val);
-	return rc;
-}
-
-int dccp_feat_activate_values(struct sock *sk, struct list_head *fn_list)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct dccp_feat_entry *cur, *next;
-	int idx;
-	dccp_feat_val *fvals[DCCP_FEAT_SUPPORTED_MAX][2] = {
-		 [0 ... DCCP_FEAT_SUPPORTED_MAX-1] = { NULL, NULL }
-	};
-
-	list_for_each_entry(cur, fn_list, node) {
-		/*
-		 * An empty Confirm means that either an unknown feature type
-		 * or an invalid value was present. In the first case there is
-		 * nothing to activate, in the other the default value is used.
-		 */
-		if (cur->empty_confirm)
-			continue;
-
-		idx = dccp_feat_index(cur->feat_num);
-		if (idx < 0) {
-			DCCP_BUG("Unknown feature %u", cur->feat_num);
-			goto activation_failed;
-		}
-		if (cur->state != FEAT_STABLE) {
-			DCCP_CRIT("Negotiation of %s %s failed in state %s",
-				  cur->is_local ? "local" : "remote",
-				  dccp_feat_fname(cur->feat_num),
-				  dccp_feat_sname[cur->state]);
-			goto activation_failed;
-		}
-		fvals[idx][cur->is_local] = &cur->val;
-	}
-
-	/*
-	 * Activate in decreasing order of index, so that the CCIDs are always
-	 * activated as the last feature. This avoids the case where a CCID
-	 * relies on the initialisation of one or more features that it depends
-	 * on (e.g. Send NDP Count, Send Ack Vector, and Ack Ratio features).
-	 */
-	for (idx = DCCP_FEAT_SUPPORTED_MAX; --idx >= 0;)
-		if (__dccp_feat_activate(sk, idx, 0, fvals[idx][0]) ||
-		    __dccp_feat_activate(sk, idx, 1, fvals[idx][1])) {
-			DCCP_CRIT("Could not activate %d", idx);
-			goto activation_failed;
-		}
-
-	/* Clean up Change options which have been confirmed already */
-	list_for_each_entry_safe(cur, next, fn_list, node)
-		if (!cur->needs_confirm)
-			dccp_feat_list_pop(cur);
-
-	dccp_pr_debug("Activation OK\n");
-	return 0;
-
-activation_failed:
-	/*
-	 * We clean up everything that may have been allocated, since
-	 * it is difficult to track at which stage negotiation failed.
-	 * This is ok, since all allocation functions below are robust
-	 * against NULL arguments.
-	 */
-	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
-	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
-	dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
-	dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
-	dp->dccps_hc_rx_ackvec = NULL;
-	return -1;
-}
diff --git a/net/dccp/feat.h b/net/dccp/feat.h
deleted file mode 100644
index 57d9c026aa3f..000000000000
--- a/net/dccp/feat.h
+++ /dev/null
@@ -1,133 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-#ifndef _DCCP_FEAT_H
-#define _DCCP_FEAT_H
-/*
- *  net/dccp/feat.h
- *
- *  Feature negotiation for the DCCP protocol (RFC 4340, section 6)
- *  Copyright (c) 2008 Gerrit Renker <gerrit@erg.abdn.ac.uk>
- *  Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk>
- */
-#include <linux/types.h>
-#include "dccp.h"
-
-/*
- * Known limit values
- */
-/* Ack Ratio takes 2-byte integer values (11.3) */
-#define DCCPF_ACK_RATIO_MAX	0xFFFF
-/* Wmin=32 and Wmax=2^46-1 from 7.5.2 */
-#define DCCPF_SEQ_WMIN		32
-#define DCCPF_SEQ_WMAX		0x3FFFFFFFFFFFull
-/* Maximum number of SP values that fit in a single (Confirm) option */
-#define DCCP_FEAT_MAX_SP_VALS	(DCCP_SINGLE_OPT_MAXLEN - 2)
-
-enum dccp_feat_type {
-	FEAT_AT_RX   = 1,	/* located at RX side of half-connection  */
-	FEAT_AT_TX   = 2,	/* located at TX side of half-connection  */
-	FEAT_SP      = 4,	/* server-priority reconciliation (6.3.1) */
-	FEAT_NN	     = 8,	/* non-negotiable reconciliation (6.3.2)  */
-	FEAT_UNKNOWN = 0xFF	/* not understood or invalid feature	  */
-};
-
-enum dccp_feat_state {
-	FEAT_DEFAULT = 0,	/* using default values from 6.4 */
-	FEAT_INITIALISING,	/* feature is being initialised  */
-	FEAT_CHANGING,		/* Change sent but not confirmed yet */
-	FEAT_UNSTABLE,		/* local modification in state CHANGING */
-	FEAT_STABLE		/* both ends (think they) agree */
-};
-
-/**
- * dccp_feat_val  -  Container for SP or NN feature values
- * @nn:     single NN value
- * @sp.vec: single SP value plus optional preference list
- * @sp.len: length of @sp.vec in bytes
- */
-typedef union {
-	u64 nn;
-	struct {
-		u8	*vec;
-		u8	len;
-	}   sp;
-} dccp_feat_val;
-
-/**
- * struct feat_entry  -  Data structure to perform feature negotiation
- * @val: feature's current value (SP features may have preference list)
- * @state: feature's current state
- * @feat_num: one of %dccp_feature_numbers
- * @needs_mandatory: whether Mandatory options should be sent
- * @needs_confirm: whether to send a Confirm instead of a Change
- * @empty_confirm: whether to send an empty Confirm (depends on @needs_confirm)
- * @is_local: feature location (1) or feature-remote (0)
- * @node: list pointers, entries arranged in FIFO order
- */
-struct dccp_feat_entry {
-	dccp_feat_val           val;
-	enum dccp_feat_state    state:8;
-	u8                      feat_num;
-
-	bool			needs_mandatory,
-				needs_confirm,
-				empty_confirm,
-				is_local;
-
-	struct list_head	node;
-};
-
-static inline u8 dccp_feat_genopt(struct dccp_feat_entry *entry)
-{
-	if (entry->needs_confirm)
-		return entry->is_local ? DCCPO_CONFIRM_L : DCCPO_CONFIRM_R;
-	return entry->is_local ? DCCPO_CHANGE_L : DCCPO_CHANGE_R;
-}
-
-/**
- * struct ccid_dependency  -  Track changes resulting from choosing a CCID
- * @dependent_feat: one of %dccp_feature_numbers
- * @is_local: local (1) or remote (0) @dependent_feat
- * @is_mandatory: whether presence of @dependent_feat is mission-critical or not
- * @val: corresponding default value for @dependent_feat (u8 is sufficient here)
- */
-struct ccid_dependency {
-	u8	dependent_feat;
-	bool	is_local:1,
-		is_mandatory:1;
-	u8	val;
-};
-
-/*
- * Sysctls to seed defaults for feature negotiation
- */
-extern unsigned long sysctl_dccp_sequence_window;
-extern int	     sysctl_dccp_rx_ccid;
-extern int	     sysctl_dccp_tx_ccid;
-
-int dccp_feat_init(struct sock *sk);
-int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local,
-			  u8 const *list, u8 len);
-int dccp_feat_parse_options(struct sock *, struct dccp_request_sock *,
-			    u8 mand, u8 opt, u8 feat, u8 *val, u8 len);
-int dccp_feat_clone_list(struct list_head const *, struct list_head *);
-
-/*
- * Encoding variable-length options and their maximum length.
- *
- * This affects NN options (SP options are all u8) and other variable-length
- * options (see table 3 in RFC 4340). The limit is currently given the Sequence
- * Window NN value (sec. 7.5.2) and the NDP count (sec. 7.7) option, all other
- * options consume less than 6 bytes (timestamps are 4 bytes).
- * When updating this constant (e.g. due to new internet drafts / RFCs), make
- * sure that you also update all code which refers to it.
- */
-#define DCCP_OPTVAL_MAXLEN	6
-
-void dccp_encode_value_var(const u64 value, u8 *to, const u8 len);
-u64 dccp_decode_value_var(const u8 *bf, const u8 len);
-u64 dccp_feat_nn_get(struct sock *sk, u8 feat);
-
-int dccp_insert_option_mandatory(struct sk_buff *skb);
-int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat, u8 *val, u8 len,
-		       bool repeat_first);
-#endif /* _DCCP_FEAT_H */
diff --git a/net/dccp/input.c b/net/dccp/input.c
deleted file mode 100644
index 2cbb757a894f..000000000000
--- a/net/dccp/input.c
+++ /dev/null
@@ -1,739 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  net/dccp/input.c
- *
- *  An implementation of the DCCP protocol
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-
-#include <linux/dccp.h>
-#include <linux/skbuff.h>
-#include <linux/slab.h>
-
-#include <net/sock.h>
-
-#include "ackvec.h"
-#include "ccid.h"
-#include "dccp.h"
-
-/* rate-limit for syncs in reply to sequence-invalid packets; RFC 4340, 7.5.4 */
-int sysctl_dccp_sync_ratelimit	__read_mostly = HZ / 8;
-
-static void dccp_enqueue_skb(struct sock *sk, struct sk_buff *skb)
-{
-	__skb_pull(skb, dccp_hdr(skb)->dccph_doff * 4);
-	__skb_queue_tail(&sk->sk_receive_queue, skb);
-	skb_set_owner_r(skb, sk);
-	sk->sk_data_ready(sk);
-}
-
-static void dccp_fin(struct sock *sk, struct sk_buff *skb)
-{
-	/*
-	 * On receiving Close/CloseReq, both RD/WR shutdown are performed.
-	 * RFC 4340, 8.3 says that we MAY send further Data/DataAcks after
-	 * receiving the closing segment, but there is no guarantee that such
-	 * data will be processed at all.
-	 */
-	sk->sk_shutdown = SHUTDOWN_MASK;
-	sock_set_flag(sk, SOCK_DONE);
-	dccp_enqueue_skb(sk, skb);
-}
-
-static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb)
-{
-	int queued = 0;
-
-	switch (sk->sk_state) {
-	/*
-	 * We ignore Close when received in one of the following states:
-	 *  - CLOSED		(may be a late or duplicate packet)
-	 *  - PASSIVE_CLOSEREQ	(the peer has sent a CloseReq earlier)
-	 *  - RESPOND		(already handled by dccp_check_req)
-	 */
-	case DCCP_CLOSING:
-		/*
-		 * Simultaneous-close: receiving a Close after sending one. This
-		 * can happen if both client and server perform active-close and
-		 * will result in an endless ping-pong of crossing and retrans-
-		 * mitted Close packets, which only terminates when one of the
-		 * nodes times out (min. 64 seconds). Quicker convergence can be
-		 * achieved when one of the nodes acts as tie-breaker.
-		 * This is ok as both ends are done with data transfer and each
-		 * end is just waiting for the other to acknowledge termination.
-		 */
-		if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT)
-			break;
-		fallthrough;
-	case DCCP_REQUESTING:
-	case DCCP_ACTIVE_CLOSEREQ:
-		dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED);
-		dccp_done(sk);
-		break;
-	case DCCP_OPEN:
-	case DCCP_PARTOPEN:
-		/* Give waiting application a chance to read pending data */
-		queued = 1;
-		dccp_fin(sk, skb);
-		dccp_set_state(sk, DCCP_PASSIVE_CLOSE);
-		fallthrough;
-	case DCCP_PASSIVE_CLOSE:
-		/*
-		 * Retransmitted Close: we have already enqueued the first one.
-		 */
-		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
-	}
-	return queued;
-}
-
-static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb)
-{
-	int queued = 0;
-
-	/*
-	 *   Step 7: Check for unexpected packet types
-	 *      If (S.is_server and P.type == CloseReq)
-	 *	  Send Sync packet acknowledging P.seqno
-	 *	  Drop packet and return
-	 */
-	if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT) {
-		dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_PKT_SYNC);
-		return queued;
-	}
-
-	/* Step 13: process relevant Client states < CLOSEREQ */
-	switch (sk->sk_state) {
-	case DCCP_REQUESTING:
-		dccp_send_close(sk, 0);
-		dccp_set_state(sk, DCCP_CLOSING);
-		break;
-	case DCCP_OPEN:
-	case DCCP_PARTOPEN:
-		/* Give waiting application a chance to read pending data */
-		queued = 1;
-		dccp_fin(sk, skb);
-		dccp_set_state(sk, DCCP_PASSIVE_CLOSEREQ);
-		fallthrough;
-	case DCCP_PASSIVE_CLOSEREQ:
-		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
-	}
-	return queued;
-}
-
-static u16 dccp_reset_code_convert(const u8 code)
-{
-	static const u16 error_code[] = {
-	[DCCP_RESET_CODE_CLOSED]	     = 0,	/* normal termination */
-	[DCCP_RESET_CODE_UNSPECIFIED]	     = 0,	/* nothing known */
-	[DCCP_RESET_CODE_ABORTED]	     = ECONNRESET,
-
-	[DCCP_RESET_CODE_NO_CONNECTION]	     = ECONNREFUSED,
-	[DCCP_RESET_CODE_CONNECTION_REFUSED] = ECONNREFUSED,
-	[DCCP_RESET_CODE_TOO_BUSY]	     = EUSERS,
-	[DCCP_RESET_CODE_AGGRESSION_PENALTY] = EDQUOT,
-
-	[DCCP_RESET_CODE_PACKET_ERROR]	     = ENOMSG,
-	[DCCP_RESET_CODE_BAD_INIT_COOKIE]    = EBADR,
-	[DCCP_RESET_CODE_BAD_SERVICE_CODE]   = EBADRQC,
-	[DCCP_RESET_CODE_OPTION_ERROR]	     = EILSEQ,
-	[DCCP_RESET_CODE_MANDATORY_ERROR]    = EOPNOTSUPP,
-	};
-
-	return code >= DCCP_MAX_RESET_CODES ? 0 : error_code[code];
-}
-
-static void dccp_rcv_reset(struct sock *sk, struct sk_buff *skb)
-{
-	u16 err = dccp_reset_code_convert(dccp_hdr_reset(skb)->dccph_reset_code);
-
-	sk->sk_err = err;
-
-	/* Queue the equivalent of TCP fin so that dccp_recvmsg exits the loop */
-	dccp_fin(sk, skb);
-
-	if (err && !sock_flag(sk, SOCK_DEAD))
-		sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
-	dccp_time_wait(sk, DCCP_TIME_WAIT, 0);
-}
-
-static void dccp_handle_ackvec_processing(struct sock *sk, struct sk_buff *skb)
-{
-	struct dccp_ackvec *av = dccp_sk(sk)->dccps_hc_rx_ackvec;
-
-	if (av == NULL)
-		return;
-	if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
-		dccp_ackvec_clear_state(av, DCCP_SKB_CB(skb)->dccpd_ack_seq);
-	dccp_ackvec_input(av, skb);
-}
-
-static void dccp_deliver_input_to_ccids(struct sock *sk, struct sk_buff *skb)
-{
-	const struct dccp_sock *dp = dccp_sk(sk);
-
-	/* Don't deliver to RX CCID when node has shut down read end. */
-	if (!(sk->sk_shutdown & RCV_SHUTDOWN))
-		ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb);
-	/*
-	 * Until the TX queue has been drained, we can not honour SHUT_WR, since
-	 * we need received feedback as input to adjust congestion control.
-	 */
-	if (sk->sk_write_queue.qlen > 0 || !(sk->sk_shutdown & SEND_SHUTDOWN))
-		ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb);
-}
-
-static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb)
-{
-	const struct dccp_hdr *dh = dccp_hdr(skb);
-	struct dccp_sock *dp = dccp_sk(sk);
-	u64 lswl, lawl, seqno = DCCP_SKB_CB(skb)->dccpd_seq,
-			ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
-
-	/*
-	 *   Step 5: Prepare sequence numbers for Sync
-	 *     If P.type == Sync or P.type == SyncAck,
-	 *	  If S.AWL <= P.ackno <= S.AWH and P.seqno >= S.SWL,
-	 *	     / * P is valid, so update sequence number variables
-	 *		 accordingly.  After this update, P will pass the tests
-	 *		 in Step 6.  A SyncAck is generated if necessary in
-	 *		 Step 15 * /
-	 *	     Update S.GSR, S.SWL, S.SWH
-	 *	  Otherwise,
-	 *	     Drop packet and return
-	 */
-	if (dh->dccph_type == DCCP_PKT_SYNC ||
-	    dh->dccph_type == DCCP_PKT_SYNCACK) {
-		if (between48(ackno, dp->dccps_awl, dp->dccps_awh) &&
-		    dccp_delta_seqno(dp->dccps_swl, seqno) >= 0)
-			dccp_update_gsr(sk, seqno);
-		else
-			return -1;
-	}
-
-	/*
-	 *   Step 6: Check sequence numbers
-	 *      Let LSWL = S.SWL and LAWL = S.AWL
-	 *      If P.type == CloseReq or P.type == Close or P.type == Reset,
-	 *	  LSWL := S.GSR + 1, LAWL := S.GAR
-	 *      If LSWL <= P.seqno <= S.SWH
-	 *	     and (P.ackno does not exist or LAWL <= P.ackno <= S.AWH),
-	 *	  Update S.GSR, S.SWL, S.SWH
-	 *	  If P.type != Sync,
-	 *	     Update S.GAR
-	 */
-	lswl = dp->dccps_swl;
-	lawl = dp->dccps_awl;
-
-	if (dh->dccph_type == DCCP_PKT_CLOSEREQ ||
-	    dh->dccph_type == DCCP_PKT_CLOSE ||
-	    dh->dccph_type == DCCP_PKT_RESET) {
-		lswl = ADD48(dp->dccps_gsr, 1);
-		lawl = dp->dccps_gar;
-	}
-
-	if (between48(seqno, lswl, dp->dccps_swh) &&
-	    (ackno == DCCP_PKT_WITHOUT_ACK_SEQ ||
-	     between48(ackno, lawl, dp->dccps_awh))) {
-		dccp_update_gsr(sk, seqno);
-
-		if (dh->dccph_type != DCCP_PKT_SYNC &&
-		    ackno != DCCP_PKT_WITHOUT_ACK_SEQ &&
-		    after48(ackno, dp->dccps_gar))
-			dp->dccps_gar = ackno;
-	} else {
-		unsigned long now = jiffies;
-		/*
-		 *   Step 6: Check sequence numbers
-		 *      Otherwise,
-		 *         If P.type == Reset,
-		 *            Send Sync packet acknowledging S.GSR
-		 *         Otherwise,
-		 *            Send Sync packet acknowledging P.seqno
-		 *      Drop packet and return
-		 *
-		 *   These Syncs are rate-limited as per RFC 4340, 7.5.4:
-		 *   at most 1 / (dccp_sync_rate_limit * HZ) Syncs per second.
-		 */
-		if (time_before(now, (dp->dccps_rate_last +
-				      sysctl_dccp_sync_ratelimit)))
-			return -1;
-
-		DCCP_WARN("Step 6 failed for %s packet, "
-			  "(LSWL(%llu) <= P.seqno(%llu) <= S.SWH(%llu)) and "
-			  "(P.ackno %s or LAWL(%llu) <= P.ackno(%llu) <= S.AWH(%llu), "
-			  "sending SYNC...\n",  dccp_packet_name(dh->dccph_type),
-			  (unsigned long long) lswl, (unsigned long long) seqno,
-			  (unsigned long long) dp->dccps_swh,
-			  (ackno == DCCP_PKT_WITHOUT_ACK_SEQ) ? "doesn't exist"
-							      : "exists",
-			  (unsigned long long) lawl, (unsigned long long) ackno,
-			  (unsigned long long) dp->dccps_awh);
-
-		dp->dccps_rate_last = now;
-
-		if (dh->dccph_type == DCCP_PKT_RESET)
-			seqno = dp->dccps_gsr;
-		dccp_send_sync(sk, seqno, DCCP_PKT_SYNC);
-		return -1;
-	}
-
-	return 0;
-}
-
-static int __dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
-				  const struct dccp_hdr *dh, const unsigned int len)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-
-	switch (dccp_hdr(skb)->dccph_type) {
-	case DCCP_PKT_DATAACK:
-	case DCCP_PKT_DATA:
-		/*
-		 * FIXME: schedule DATA_DROPPED (RFC 4340, 11.7.2) if and when
-		 * - sk_shutdown == RCV_SHUTDOWN, use Code 1, "Not Listening"
-		 * - sk_receive_queue is full, use Code 2, "Receive Buffer"
-		 */
-		dccp_enqueue_skb(sk, skb);
-		return 0;
-	case DCCP_PKT_ACK:
-		goto discard;
-	case DCCP_PKT_RESET:
-		/*
-		 *  Step 9: Process Reset
-		 *	If P.type == Reset,
-		 *		Tear down connection
-		 *		S.state := TIMEWAIT
-		 *		Set TIMEWAIT timer
-		 *		Drop packet and return
-		 */
-		dccp_rcv_reset(sk, skb);
-		return 0;
-	case DCCP_PKT_CLOSEREQ:
-		if (dccp_rcv_closereq(sk, skb))
-			return 0;
-		goto discard;
-	case DCCP_PKT_CLOSE:
-		if (dccp_rcv_close(sk, skb))
-			return 0;
-		goto discard;
-	case DCCP_PKT_REQUEST:
-		/* Step 7
-		 *   or (S.is_server and P.type == Response)
-		 *   or (S.is_client and P.type == Request)
-		 *   or (S.state >= OPEN and P.type == Request
-		 *	and P.seqno >= S.OSR)
-		 *    or (S.state >= OPEN and P.type == Response
-		 *	and P.seqno >= S.OSR)
-		 *    or (S.state == RESPOND and P.type == Data),
-		 *  Send Sync packet acknowledging P.seqno
-		 *  Drop packet and return
-		 */
-		if (dp->dccps_role != DCCP_ROLE_LISTEN)
-			goto send_sync;
-		goto check_seq;
-	case DCCP_PKT_RESPONSE:
-		if (dp->dccps_role != DCCP_ROLE_CLIENT)
-			goto send_sync;
-check_seq:
-		if (dccp_delta_seqno(dp->dccps_osr,
-				     DCCP_SKB_CB(skb)->dccpd_seq) >= 0) {
-send_sync:
-			dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq,
-				       DCCP_PKT_SYNC);
-		}
-		break;
-	case DCCP_PKT_SYNC:
-		dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq,
-			       DCCP_PKT_SYNCACK);
-		/*
-		 * From RFC 4340, sec. 5.7
-		 *
-		 * As with DCCP-Ack packets, DCCP-Sync and DCCP-SyncAck packets
-		 * MAY have non-zero-length application data areas, whose
-		 * contents receivers MUST ignore.
-		 */
-		goto discard;
-	}
-
-	DCCP_INC_STATS(DCCP_MIB_INERRS);
-discard:
-	__kfree_skb(skb);
-	return 0;
-}
-
-int dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
-			 const struct dccp_hdr *dh, const unsigned int len)
-{
-	if (dccp_check_seqno(sk, skb))
-		goto discard;
-
-	if (dccp_parse_options(sk, NULL, skb))
-		return 1;
-
-	dccp_handle_ackvec_processing(sk, skb);
-	dccp_deliver_input_to_ccids(sk, skb);
-
-	return __dccp_rcv_established(sk, skb, dh, len);
-discard:
-	__kfree_skb(skb);
-	return 0;
-}
-
-EXPORT_SYMBOL_GPL(dccp_rcv_established);
-
-static int dccp_rcv_request_sent_state_process(struct sock *sk,
-					       struct sk_buff *skb,
-					       const struct dccp_hdr *dh,
-					       const unsigned int len)
-{
-	/*
-	 *  Step 4: Prepare sequence numbers in REQUEST
-	 *     If S.state == REQUEST,
-	 *	  If (P.type == Response or P.type == Reset)
-	 *		and S.AWL <= P.ackno <= S.AWH,
-	 *	     / * Set sequence number variables corresponding to the
-	 *		other endpoint, so P will pass the tests in Step 6 * /
-	 *	     Set S.GSR, S.ISR, S.SWL, S.SWH
-	 *	     / * Response processing continues in Step 10; Reset
-	 *		processing continues in Step 9 * /
-	*/
-	if (dh->dccph_type == DCCP_PKT_RESPONSE) {
-		const struct inet_connection_sock *icsk = inet_csk(sk);
-		struct dccp_sock *dp = dccp_sk(sk);
-		long tstamp = dccp_timestamp();
-
-		if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
-			       dp->dccps_awl, dp->dccps_awh)) {
-			dccp_pr_debug("invalid ackno: S.AWL=%llu, "
-				      "P.ackno=%llu, S.AWH=%llu\n",
-				      (unsigned long long)dp->dccps_awl,
-			   (unsigned long long)DCCP_SKB_CB(skb)->dccpd_ack_seq,
-				      (unsigned long long)dp->dccps_awh);
-			goto out_invalid_packet;
-		}
-
-		/*
-		 * If option processing (Step 8) failed, return 1 here so that
-		 * dccp_v4_do_rcv() sends a Reset. The Reset code depends on
-		 * the option type and is set in dccp_parse_options().
-		 */
-		if (dccp_parse_options(sk, NULL, skb))
-			return 1;
-
-		/* Obtain usec RTT sample from SYN exchange (used by TFRC). */
-		if (likely(dp->dccps_options_received.dccpor_timestamp_echo))
-			dp->dccps_syn_rtt = dccp_sample_rtt(sk, 10 * (tstamp -
-			    dp->dccps_options_received.dccpor_timestamp_echo));
-
-		/* Stop the REQUEST timer */
-		inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
-		WARN_ON(sk->sk_send_head == NULL);
-		kfree_skb(sk->sk_send_head);
-		sk->sk_send_head = NULL;
-
-		/*
-		 * Set ISR, GSR from packet. ISS was set in dccp_v{4,6}_connect
-		 * and GSS in dccp_transmit_skb(). Setting AWL/AWH and SWL/SWH
-		 * is done as part of activating the feature values below, since
-		 * these settings depend on the local/remote Sequence Window
-		 * features, which were undefined or not confirmed until now.
-		 */
-		dp->dccps_gsr = dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq;
-
-		dccp_sync_mss(sk, icsk->icsk_pmtu_cookie);
-
-		/*
-		 *    Step 10: Process REQUEST state (second part)
-		 *       If S.state == REQUEST,
-		 *	  / * If we get here, P is a valid Response from the
-		 *	      server (see Step 4), and we should move to
-		 *	      PARTOPEN state. PARTOPEN means send an Ack,
-		 *	      don't send Data packets, retransmit Acks
-		 *	      periodically, and always include any Init Cookie
-		 *	      from the Response * /
-		 *	  S.state := PARTOPEN
-		 *	  Set PARTOPEN timer
-		 *	  Continue with S.state == PARTOPEN
-		 *	  / * Step 12 will send the Ack completing the
-		 *	      three-way handshake * /
-		 */
-		dccp_set_state(sk, DCCP_PARTOPEN);
-
-		/*
-		 * If feature negotiation was successful, activate features now;
-		 * an activation failure means that this host could not activate
-		 * one ore more features (e.g. insufficient memory), which would
-		 * leave at least one feature in an undefined state.
-		 */
-		if (dccp_feat_activate_values(sk, &dp->dccps_featneg))
-			goto unable_to_proceed;
-
-		/* Make sure socket is routed, for correct metrics. */
-		icsk->icsk_af_ops->rebuild_header(sk);
-
-		if (!sock_flag(sk, SOCK_DEAD)) {
-			sk->sk_state_change(sk);
-			sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
-		}
-
-		if (sk->sk_write_pending || inet_csk_in_pingpong_mode(sk) ||
-		    icsk->icsk_accept_queue.rskq_defer_accept) {
-			/* Save one ACK. Data will be ready after
-			 * several ticks, if write_pending is set.
-			 *
-			 * It may be deleted, but with this feature tcpdumps
-			 * look so _wonderfully_ clever, that I was not able
-			 * to stand against the temptation 8)     --ANK
-			 */
-			/*
-			 * OK, in DCCP we can as well do a similar trick, its
-			 * even in the draft, but there is no need for us to
-			 * schedule an ack here, as dccp_sendmsg does this for
-			 * us, also stated in the draft. -acme
-			 */
-			__kfree_skb(skb);
-			return 0;
-		}
-		dccp_send_ack(sk);
-		return -1;
-	}
-
-out_invalid_packet:
-	/* dccp_v4_do_rcv will send a reset */
-	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
-	return 1;
-
-unable_to_proceed:
-	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_ABORTED;
-	/*
-	 * We mark this socket as no longer usable, so that the loop in
-	 * dccp_sendmsg() terminates and the application gets notified.
-	 */
-	dccp_set_state(sk, DCCP_CLOSED);
-	sk->sk_err = ECOMM;
-	return 1;
-}
-
-static int dccp_rcv_respond_partopen_state_process(struct sock *sk,
-						   struct sk_buff *skb,
-						   const struct dccp_hdr *dh,
-						   const unsigned int len)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	u32 sample = dp->dccps_options_received.dccpor_timestamp_echo;
-	int queued = 0;
-
-	switch (dh->dccph_type) {
-	case DCCP_PKT_RESET:
-		inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
-		break;
-	case DCCP_PKT_DATA:
-		if (sk->sk_state == DCCP_RESPOND)
-			break;
-		fallthrough;
-	case DCCP_PKT_DATAACK:
-	case DCCP_PKT_ACK:
-		/*
-		 * FIXME: we should be resetting the PARTOPEN (DELACK) timer
-		 * here but only if we haven't used the DELACK timer for
-		 * something else, like sending a delayed ack for a TIMESTAMP
-		 * echo, etc, for now were not clearing it, sending an extra
-		 * ACK when there is nothing else to do in DELACK is not a big
-		 * deal after all.
-		 */
-
-		/* Stop the PARTOPEN timer */
-		if (sk->sk_state == DCCP_PARTOPEN)
-			inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
-
-		/* Obtain usec RTT sample from SYN exchange (used by TFRC). */
-		if (likely(sample)) {
-			long delta = dccp_timestamp() - sample;
-
-			dp->dccps_syn_rtt = dccp_sample_rtt(sk, 10 * delta);
-		}
-
-		dp->dccps_osr = DCCP_SKB_CB(skb)->dccpd_seq;
-		dccp_set_state(sk, DCCP_OPEN);
-
-		if (dh->dccph_type == DCCP_PKT_DATAACK ||
-		    dh->dccph_type == DCCP_PKT_DATA) {
-			__dccp_rcv_established(sk, skb, dh, len);
-			queued = 1; /* packet was queued
-				       (by __dccp_rcv_established) */
-		}
-		break;
-	}
-
-	return queued;
-}
-
-int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
-			   struct dccp_hdr *dh, unsigned int len)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
-	const int old_state = sk->sk_state;
-	bool acceptable;
-	int queued = 0;
-
-	/*
-	 *  Step 3: Process LISTEN state
-	 *
-	 *     If S.state == LISTEN,
-	 *	 If P.type == Request or P contains a valid Init Cookie option,
-	 *	      (* Must scan the packet's options to check for Init
-	 *		 Cookies.  Only Init Cookies are processed here,
-	 *		 however; other options are processed in Step 8.  This
-	 *		 scan need only be performed if the endpoint uses Init
-	 *		 Cookies *)
-	 *	      (* Generate a new socket and switch to that socket *)
-	 *	      Set S := new socket for this port pair
-	 *	      S.state = RESPOND
-	 *	      Choose S.ISS (initial seqno) or set from Init Cookies
-	 *	      Initialize S.GAR := S.ISS
-	 *	      Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init
-	 *	      Cookies Continue with S.state == RESPOND
-	 *	      (* A Response packet will be generated in Step 11 *)
-	 *	 Otherwise,
-	 *	      Generate Reset(No Connection) unless P.type == Reset
-	 *	      Drop packet and return
-	 */
-	if (sk->sk_state == DCCP_LISTEN) {
-		if (dh->dccph_type == DCCP_PKT_REQUEST) {
-			/* It is possible that we process SYN packets from backlog,
-			 * so we need to make sure to disable BH and RCU right there.
-			 */
-			rcu_read_lock();
-			local_bh_disable();
-			acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0;
-			local_bh_enable();
-			rcu_read_unlock();
-			if (!acceptable)
-				return 1;
-			consume_skb(skb);
-			return 0;
-		}
-		if (dh->dccph_type == DCCP_PKT_RESET)
-			goto discard;
-
-		/* Caller (dccp_v4_do_rcv) will send Reset */
-		dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
-		return 1;
-	} else if (sk->sk_state == DCCP_CLOSED) {
-		dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
-		return 1;
-	}
-
-	/* Step 6: Check sequence numbers (omitted in LISTEN/REQUEST state) */
-	if (sk->sk_state != DCCP_REQUESTING && dccp_check_seqno(sk, skb))
-		goto discard;
-
-	/*
-	 *   Step 7: Check for unexpected packet types
-	 *      If (S.is_server and P.type == Response)
-	 *	    or (S.is_client and P.type == Request)
-	 *	    or (S.state == RESPOND and P.type == Data),
-	 *	  Send Sync packet acknowledging P.seqno
-	 *	  Drop packet and return
-	 */
-	if ((dp->dccps_role != DCCP_ROLE_CLIENT &&
-	     dh->dccph_type == DCCP_PKT_RESPONSE) ||
-	    (dp->dccps_role == DCCP_ROLE_CLIENT &&
-	     dh->dccph_type == DCCP_PKT_REQUEST) ||
-	    (sk->sk_state == DCCP_RESPOND && dh->dccph_type == DCCP_PKT_DATA)) {
-		dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNC);
-		goto discard;
-	}
-
-	/*  Step 8: Process options */
-	if (dccp_parse_options(sk, NULL, skb))
-		return 1;
-
-	/*
-	 *  Step 9: Process Reset
-	 *	If P.type == Reset,
-	 *		Tear down connection
-	 *		S.state := TIMEWAIT
-	 *		Set TIMEWAIT timer
-	 *		Drop packet and return
-	 */
-	if (dh->dccph_type == DCCP_PKT_RESET) {
-		dccp_rcv_reset(sk, skb);
-		return 0;
-	} else if (dh->dccph_type == DCCP_PKT_CLOSEREQ) {	/* Step 13 */
-		if (dccp_rcv_closereq(sk, skb))
-			return 0;
-		goto discard;
-	} else if (dh->dccph_type == DCCP_PKT_CLOSE) {		/* Step 14 */
-		if (dccp_rcv_close(sk, skb))
-			return 0;
-		goto discard;
-	}
-
-	switch (sk->sk_state) {
-	case DCCP_REQUESTING:
-		queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len);
-		if (queued >= 0)
-			return queued;
-
-		__kfree_skb(skb);
-		return 0;
-
-	case DCCP_PARTOPEN:
-		/* Step 8: if using Ack Vectors, mark packet acknowledgeable */
-		dccp_handle_ackvec_processing(sk, skb);
-		dccp_deliver_input_to_ccids(sk, skb);
-		fallthrough;
-	case DCCP_RESPOND:
-		queued = dccp_rcv_respond_partopen_state_process(sk, skb,
-								 dh, len);
-		break;
-	}
-
-	if (dh->dccph_type == DCCP_PKT_ACK ||
-	    dh->dccph_type == DCCP_PKT_DATAACK) {
-		switch (old_state) {
-		case DCCP_PARTOPEN:
-			sk->sk_state_change(sk);
-			sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
-			break;
-		}
-	} else if (unlikely(dh->dccph_type == DCCP_PKT_SYNC)) {
-		dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNCACK);
-		goto discard;
-	}
-
-	if (!queued) {
-discard:
-		__kfree_skb(skb);
-	}
-	return 0;
-}
-
-EXPORT_SYMBOL_GPL(dccp_rcv_state_process);
-
-/**
- *  dccp_sample_rtt  -  Validate and finalise computation of RTT sample
- *  @sk:	socket structure
- *  @delta:	number of microseconds between packet and acknowledgment
- *
- *  The routine is kept generic to work in different contexts. It should be
- *  called immediately when the ACK used for the RTT sample arrives.
- */
-u32 dccp_sample_rtt(struct sock *sk, long delta)
-{
-	/* dccpor_elapsed_time is either zeroed out or set and > 0 */
-	delta -= dccp_sk(sk)->dccps_options_received.dccpor_elapsed_time * 10;
-
-	if (unlikely(delta <= 0)) {
-		DCCP_WARN("unusable RTT sample %ld, using min\n", delta);
-		return DCCP_SANE_RTT_MIN;
-	}
-	if (unlikely(delta > DCCP_SANE_RTT_MAX)) {
-		DCCP_WARN("RTT sample %ld too large, using max\n", delta);
-		return DCCP_SANE_RTT_MAX;
-	}
-
-	return delta;
-}
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
deleted file mode 100644
index 2045ddac0fe9..000000000000
--- a/net/dccp/ipv4.c
+++ /dev/null
@@ -1,1101 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  net/dccp/ipv4.c
- *
- *  An implementation of the DCCP protocol
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-
-#include <linux/dccp.h>
-#include <linux/icmp.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/random.h>
-
-#include <net/icmp.h>
-#include <net/inet_common.h>
-#include <net/inet_dscp.h>
-#include <net/inet_hashtables.h>
-#include <net/inet_sock.h>
-#include <net/protocol.h>
-#include <net/sock.h>
-#include <net/timewait_sock.h>
-#include <net/tcp_states.h>
-#include <net/xfrm.h>
-#include <net/secure_seq.h>
-#include <net/netns/generic.h>
-#include <net/rstreason.h>
-
-#include "ackvec.h"
-#include "ccid.h"
-#include "dccp.h"
-#include "feat.h"
-
-struct dccp_v4_pernet {
-	struct sock *v4_ctl_sk;
-};
-
-static unsigned int dccp_v4_pernet_id __read_mostly;
-
-/*
- * The per-net v4_ctl_sk socket is used for responding to
- * the Out-of-the-blue (OOTB) packets. A control sock will be created
- * for this socket at the initialization time.
- */
-
-int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
-{
-	const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
-	struct inet_sock *inet = inet_sk(sk);
-	struct dccp_sock *dp = dccp_sk(sk);
-	__be16 orig_sport, orig_dport;
-	__be32 daddr, nexthop;
-	struct flowi4 *fl4;
-	struct rtable *rt;
-	int err;
-	struct ip_options_rcu *inet_opt;
-
-	dp->dccps_role = DCCP_ROLE_CLIENT;
-
-	if (addr_len < sizeof(struct sockaddr_in))
-		return -EINVAL;
-
-	if (usin->sin_family != AF_INET)
-		return -EAFNOSUPPORT;
-
-	nexthop = daddr = usin->sin_addr.s_addr;
-
-	inet_opt = rcu_dereference_protected(inet->inet_opt,
-					     lockdep_sock_is_held(sk));
-	if (inet_opt != NULL && inet_opt->opt.srr) {
-		if (daddr == 0)
-			return -EINVAL;
-		nexthop = inet_opt->opt.faddr;
-	}
-
-	orig_sport = inet->inet_sport;
-	orig_dport = usin->sin_port;
-	fl4 = &inet->cork.fl.u.ip4;
-	rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
-			      sk->sk_bound_dev_if, IPPROTO_DCCP, orig_sport,
-			      orig_dport, sk);
-	if (IS_ERR(rt))
-		return PTR_ERR(rt);
-
-	if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
-		ip_rt_put(rt);
-		return -ENETUNREACH;
-	}
-
-	if (inet_opt == NULL || !inet_opt->opt.srr)
-		daddr = fl4->daddr;
-
-	if (inet->inet_saddr == 0) {
-		err = inet_bhash2_update_saddr(sk,  &fl4->saddr, AF_INET);
-		if (err) {
-			ip_rt_put(rt);
-			return err;
-		}
-	} else {
-		sk_rcv_saddr_set(sk, inet->inet_saddr);
-	}
-
-	inet->inet_dport = usin->sin_port;
-	sk_daddr_set(sk, daddr);
-
-	inet_csk(sk)->icsk_ext_hdr_len = 0;
-	if (inet_opt)
-		inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
-	/*
-	 * Socket identity is still unknown (sport may be zero).
-	 * However we set state to DCCP_REQUESTING and not releasing socket
-	 * lock select source port, enter ourselves into the hash tables and
-	 * complete initialization after this.
-	 */
-	dccp_set_state(sk, DCCP_REQUESTING);
-	err = inet_hash_connect(&dccp_death_row, sk);
-	if (err != 0)
-		goto failure;
-
-	rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
-			       inet->inet_sport, inet->inet_dport, sk);
-	if (IS_ERR(rt)) {
-		err = PTR_ERR(rt);
-		rt = NULL;
-		goto failure;
-	}
-	/* OK, now commit destination to socket.  */
-	sk_setup_caps(sk, &rt->dst);
-
-	dp->dccps_iss = secure_dccp_sequence_number(inet->inet_saddr,
-						    inet->inet_daddr,
-						    inet->inet_sport,
-						    inet->inet_dport);
-	atomic_set(&inet->inet_id, get_random_u16());
-
-	err = dccp_connect(sk);
-	rt = NULL;
-	if (err != 0)
-		goto failure;
-out:
-	return err;
-failure:
-	/*
-	 * This unhashes the socket and releases the local port, if necessary.
-	 */
-	dccp_set_state(sk, DCCP_CLOSED);
-	inet_bhash2_reset_saddr(sk);
-	ip_rt_put(rt);
-	sk->sk_route_caps = 0;
-	inet->inet_dport = 0;
-	goto out;
-}
-EXPORT_SYMBOL_GPL(dccp_v4_connect);
-
-/*
- * This routine does path mtu discovery as defined in RFC1191.
- */
-static inline void dccp_do_pmtu_discovery(struct sock *sk,
-					  const struct iphdr *iph,
-					  u32 mtu)
-{
-	struct dst_entry *dst;
-	const struct inet_sock *inet = inet_sk(sk);
-	const struct dccp_sock *dp = dccp_sk(sk);
-
-	/* We are not interested in DCCP_LISTEN and request_socks (RESPONSEs
-	 * send out by Linux are always < 576bytes so they should go through
-	 * unfragmented).
-	 */
-	if (sk->sk_state == DCCP_LISTEN)
-		return;
-
-	dst = inet_csk_update_pmtu(sk, mtu);
-	if (!dst)
-		return;
-
-	/* Something is about to be wrong... Remember soft error
-	 * for the case, if this connection will not able to recover.
-	 */
-	if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
-		WRITE_ONCE(sk->sk_err_soft, EMSGSIZE);
-
-	mtu = dst_mtu(dst);
-
-	if (inet->pmtudisc != IP_PMTUDISC_DONT &&
-	    ip_sk_accept_pmtu(sk) &&
-	    inet_csk(sk)->icsk_pmtu_cookie > mtu) {
-		dccp_sync_mss(sk, mtu);
-
-		/*
-		 * From RFC 4340, sec. 14.1:
-		 *
-		 *	DCCP-Sync packets are the best choice for upward
-		 *	probing, since DCCP-Sync probes do not risk application
-		 *	data loss.
-		 */
-		dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
-	} /* else let the usual retransmit timer handle it */
-}
-
-static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk)
-{
-	struct dst_entry *dst = __sk_dst_check(sk, 0);
-
-	if (dst)
-		dst->ops->redirect(dst, sk, skb);
-}
-
-void dccp_req_err(struct sock *sk, u64 seq)
-	{
-	struct request_sock *req = inet_reqsk(sk);
-	struct net *net = sock_net(sk);
-
-	/*
-	 * ICMPs are not backlogged, hence we cannot get an established
-	 * socket here.
-	 */
-	if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) {
-		__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
-	} else {
-		/*
-		 * Still in RESPOND, just remove it silently.
-		 * There is no good way to pass the error to the newly
-		 * created socket, and POSIX does not want network
-		 * errors returned from accept().
-		 */
-		inet_csk_reqsk_queue_drop(req->rsk_listener, req);
-	}
-	reqsk_put(req);
-}
-EXPORT_SYMBOL(dccp_req_err);
-
-/*
- * This routine is called by the ICMP module when it gets some sort of error
- * condition. If err < 0 then the socket should be closed and the error
- * returned to the user. If err > 0 it's just the icmp type << 8 | icmp code.
- * After adjustment header points to the first 8 bytes of the tcp header. We
- * need to find the appropriate port.
- *
- * The locking strategy used here is very "optimistic". When someone else
- * accesses the socket the ICMP is just dropped and for some paths there is no
- * check at all. A more general error queue to queue errors for later handling
- * is probably better.
- */
-static int dccp_v4_err(struct sk_buff *skb, u32 info)
-{
-	const struct iphdr *iph = (struct iphdr *)skb->data;
-	const u8 offset = iph->ihl << 2;
-	const struct dccp_hdr *dh;
-	struct dccp_sock *dp;
-	const int type = icmp_hdr(skb)->type;
-	const int code = icmp_hdr(skb)->code;
-	struct sock *sk;
-	__u64 seq;
-	int err;
-	struct net *net = dev_net(skb->dev);
-
-	if (!pskb_may_pull(skb, offset + sizeof(*dh)))
-		return -EINVAL;
-	dh = (struct dccp_hdr *)(skb->data + offset);
-	if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh)))
-		return -EINVAL;
-	iph = (struct iphdr *)skb->data;
-	dh = (struct dccp_hdr *)(skb->data + offset);
-
-	sk = __inet_lookup_established(net, &dccp_hashinfo,
-				       iph->daddr, dh->dccph_dport,
-				       iph->saddr, ntohs(dh->dccph_sport),
-				       inet_iif(skb), 0);
-	if (!sk) {
-		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-		return -ENOENT;
-	}
-
-	if (sk->sk_state == DCCP_TIME_WAIT) {
-		inet_twsk_put(inet_twsk(sk));
-		return 0;
-	}
-	seq = dccp_hdr_seq(dh);
-	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
-		dccp_req_err(sk, seq);
-		return 0;
-	}
-
-	bh_lock_sock(sk);
-	/* If too many ICMPs get dropped on busy
-	 * servers this needs to be solved differently.
-	 */
-	if (sock_owned_by_user(sk))
-		__NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
-
-	if (sk->sk_state == DCCP_CLOSED)
-		goto out;
-
-	dp = dccp_sk(sk);
-	if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
-	    !between48(seq, dp->dccps_awl, dp->dccps_awh)) {
-		__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
-		goto out;
-	}
-
-	switch (type) {
-	case ICMP_REDIRECT:
-		if (!sock_owned_by_user(sk))
-			dccp_do_redirect(skb, sk);
-		goto out;
-	case ICMP_SOURCE_QUENCH:
-		/* Just silently ignore these. */
-		goto out;
-	case ICMP_PARAMETERPROB:
-		err = EPROTO;
-		break;
-	case ICMP_DEST_UNREACH:
-		if (code > NR_ICMP_UNREACH)
-			goto out;
-
-		if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
-			if (!sock_owned_by_user(sk))
-				dccp_do_pmtu_discovery(sk, iph, info);
-			goto out;
-		}
-
-		err = icmp_err_convert[code].errno;
-		break;
-	case ICMP_TIME_EXCEEDED:
-		err = EHOSTUNREACH;
-		break;
-	default:
-		goto out;
-	}
-
-	switch (sk->sk_state) {
-	case DCCP_REQUESTING:
-	case DCCP_RESPOND:
-		if (!sock_owned_by_user(sk)) {
-			__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
-			sk->sk_err = err;
-
-			sk_error_report(sk);
-
-			dccp_done(sk);
-		} else {
-			WRITE_ONCE(sk->sk_err_soft, err);
-		}
-		goto out;
-	}
-
-	/* If we've already connected we will keep trying
-	 * until we time out, or the user gives up.
-	 *
-	 * rfc1122 4.2.3.9 allows to consider as hard errors
-	 * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too,
-	 * but it is obsoleted by pmtu discovery).
-	 *
-	 * Note, that in modern internet, where routing is unreliable
-	 * and in each dark corner broken firewalls sit, sending random
-	 * errors ordered by their masters even this two messages finally lose
-	 * their original sense (even Linux sends invalid PORT_UNREACHs)
-	 *
-	 * Now we are in compliance with RFCs.
-	 *							--ANK (980905)
-	 */
-
-	if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) {
-		sk->sk_err = err;
-		sk_error_report(sk);
-	} else { /* Only an error on timeout */
-		WRITE_ONCE(sk->sk_err_soft, err);
-	}
-out:
-	bh_unlock_sock(sk);
-	sock_put(sk);
-	return 0;
-}
-
-static inline __sum16 dccp_v4_csum_finish(struct sk_buff *skb,
-				      __be32 src, __be32 dst)
-{
-	return csum_tcpudp_magic(src, dst, skb->len, IPPROTO_DCCP, skb->csum);
-}
-
-void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb)
-{
-	const struct inet_sock *inet = inet_sk(sk);
-	struct dccp_hdr *dh = dccp_hdr(skb);
-
-	dccp_csum_outgoing(skb);
-	dh->dccph_checksum = dccp_v4_csum_finish(skb,
-						 inet->inet_saddr,
-						 inet->inet_daddr);
-}
-EXPORT_SYMBOL_GPL(dccp_v4_send_check);
-
-static inline u64 dccp_v4_init_sequence(const struct sk_buff *skb)
-{
-	return secure_dccp_sequence_number(ip_hdr(skb)->daddr,
-					   ip_hdr(skb)->saddr,
-					   dccp_hdr(skb)->dccph_dport,
-					   dccp_hdr(skb)->dccph_sport);
-}
-
-/*
- * The three way handshake has completed - we got a valid ACK or DATAACK -
- * now create the new socket.
- *
- * This is the equivalent of TCP's tcp_v4_syn_recv_sock
- */
-struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
-				       struct sk_buff *skb,
-				       struct request_sock *req,
-				       struct dst_entry *dst,
-				       struct request_sock *req_unhash,
-				       bool *own_req)
-{
-	struct inet_request_sock *ireq;
-	struct inet_sock *newinet;
-	struct sock *newsk;
-
-	if (sk_acceptq_is_full(sk))
-		goto exit_overflow;
-
-	newsk = dccp_create_openreq_child(sk, req, skb);
-	if (newsk == NULL)
-		goto exit_nonewsk;
-
-	newinet		   = inet_sk(newsk);
-	ireq		   = inet_rsk(req);
-	RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
-	newinet->mc_index  = inet_iif(skb);
-	newinet->mc_ttl	   = ip_hdr(skb)->ttl;
-	atomic_set(&newinet->inet_id, get_random_u16());
-
-	if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL)
-		goto put_and_exit;
-
-	sk_setup_caps(newsk, dst);
-
-	dccp_sync_mss(newsk, dst_mtu(dst));
-
-	if (__inet_inherit_port(sk, newsk) < 0)
-		goto put_and_exit;
-	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL);
-	if (*own_req)
-		ireq->ireq_opt = NULL;
-	else
-		newinet->inet_opt = NULL;
-	return newsk;
-
-exit_overflow:
-	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
-exit_nonewsk:
-	dst_release(dst);
-exit:
-	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
-	return NULL;
-put_and_exit:
-	newinet->inet_opt = NULL;
-	inet_csk_prepare_forced_close(newsk);
-	dccp_done(newsk);
-	goto exit;
-}
-EXPORT_SYMBOL_GPL(dccp_v4_request_recv_sock);
-
-static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
-					   struct sk_buff *skb)
-{
-	struct rtable *rt;
-	const struct iphdr *iph = ip_hdr(skb);
-	struct flowi4 fl4 = {
-		.flowi4_oif = inet_iif(skb),
-		.daddr = iph->saddr,
-		.saddr = iph->daddr,
-		.flowi4_tos = inet_dscp_to_dsfield(inet_sk_dscp(inet_sk(sk))),
-		.flowi4_scope = ip_sock_rt_scope(sk),
-		.flowi4_proto = sk->sk_protocol,
-		.fl4_sport = dccp_hdr(skb)->dccph_dport,
-		.fl4_dport = dccp_hdr(skb)->dccph_sport,
-	};
-
-	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
-	rt = ip_route_output_flow(net, &fl4, sk);
-	if (IS_ERR(rt)) {
-		IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
-		return NULL;
-	}
-
-	return &rt->dst;
-}
-
-static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req)
-{
-	int err = -1;
-	struct sk_buff *skb;
-	struct dst_entry *dst;
-	struct flowi4 fl4;
-
-	dst = inet_csk_route_req(sk, &fl4, req);
-	if (dst == NULL)
-		goto out;
-
-	skb = dccp_make_response(sk, dst, req);
-	if (skb != NULL) {
-		const struct inet_request_sock *ireq = inet_rsk(req);
-		struct dccp_hdr *dh = dccp_hdr(skb);
-
-		dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr,
-							      ireq->ir_rmt_addr);
-		rcu_read_lock();
-		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
-					    ireq->ir_rmt_addr,
-					    rcu_dereference(ireq->ireq_opt),
-					    READ_ONCE(inet_sk(sk)->tos));
-		rcu_read_unlock();
-		err = net_xmit_eval(err);
-	}
-
-out:
-	dst_release(dst);
-	return err;
-}
-
-static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb,
-				   enum sk_rst_reason reason)
-{
-	int err;
-	const struct iphdr *rxiph;
-	struct sk_buff *skb;
-	struct dst_entry *dst;
-	struct net *net = dev_net(skb_dst(rxskb)->dev);
-	struct dccp_v4_pernet *pn;
-	struct sock *ctl_sk;
-
-	/* Never send a reset in response to a reset. */
-	if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET)
-		return;
-
-	if (skb_rtable(rxskb)->rt_type != RTN_LOCAL)
-		return;
-
-	pn = net_generic(net, dccp_v4_pernet_id);
-	ctl_sk = pn->v4_ctl_sk;
-	dst = dccp_v4_route_skb(net, ctl_sk, rxskb);
-	if (dst == NULL)
-		return;
-
-	skb = dccp_ctl_make_reset(ctl_sk, rxskb);
-	if (skb == NULL)
-		goto out;
-
-	rxiph = ip_hdr(rxskb);
-	dccp_hdr(skb)->dccph_checksum = dccp_v4_csum_finish(skb, rxiph->saddr,
-								 rxiph->daddr);
-	skb_dst_set(skb, dst_clone(dst));
-
-	local_bh_disable();
-	bh_lock_sock(ctl_sk);
-	err = ip_build_and_send_pkt(skb, ctl_sk,
-				    rxiph->daddr, rxiph->saddr, NULL,
-				    inet_sk(ctl_sk)->tos);
-	bh_unlock_sock(ctl_sk);
-
-	if (net_xmit_eval(err) == 0) {
-		__DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
-		__DCCP_INC_STATS(DCCP_MIB_OUTRSTS);
-	}
-	local_bh_enable();
-out:
-	dst_release(dst);
-}
-
-static void dccp_v4_reqsk_destructor(struct request_sock *req)
-{
-	dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
-	kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
-}
-
-void dccp_syn_ack_timeout(const struct request_sock *req)
-{
-}
-EXPORT_SYMBOL(dccp_syn_ack_timeout);
-
-static struct request_sock_ops dccp_request_sock_ops __read_mostly = {
-	.family		= PF_INET,
-	.obj_size	= sizeof(struct dccp_request_sock),
-	.rtx_syn_ack	= dccp_v4_send_response,
-	.send_ack	= dccp_reqsk_send_ack,
-	.destructor	= dccp_v4_reqsk_destructor,
-	.send_reset	= dccp_v4_ctl_send_reset,
-	.syn_ack_timeout = dccp_syn_ack_timeout,
-};
-
-int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
-{
-	struct inet_request_sock *ireq;
-	struct request_sock *req;
-	struct dccp_request_sock *dreq;
-	const __be32 service = dccp_hdr_request(skb)->dccph_req_service;
-	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
-
-	/* Never answer to DCCP_PKT_REQUESTs send to broadcast or multicast */
-	if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
-		return 0;	/* discard, don't send a reset here */
-
-	if (dccp_bad_service_code(sk, service)) {
-		dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE;
-		goto drop;
-	}
-	/*
-	 * TW buckets are converted to open requests without
-	 * limitations, they conserve resources and peer is
-	 * evidently real one.
-	 */
-	dcb->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
-	if (inet_csk_reqsk_queue_is_full(sk))
-		goto drop;
-
-	if (sk_acceptq_is_full(sk))
-		goto drop;
-
-	req = inet_reqsk_alloc(&dccp_request_sock_ops, sk, true);
-	if (req == NULL)
-		goto drop;
-
-	if (dccp_reqsk_init(req, dccp_sk(sk), skb))
-		goto drop_and_free;
-
-	dreq = dccp_rsk(req);
-	if (dccp_parse_options(sk, dreq, skb))
-		goto drop_and_free;
-
-	ireq = inet_rsk(req);
-	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
-	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-	ireq->ir_mark = inet_request_mark(sk, skb);
-	ireq->ireq_family = AF_INET;
-	ireq->ir_iif = READ_ONCE(sk->sk_bound_dev_if);
-
-	if (security_inet_conn_request(sk, skb, req))
-		goto drop_and_free;
-
-	/*
-	 * Step 3: Process LISTEN state
-	 *
-	 * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie
-	 *
-	 * Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child().
-	 */
-	dreq->dreq_isr	   = dcb->dccpd_seq;
-	dreq->dreq_gsr	   = dreq->dreq_isr;
-	dreq->dreq_iss	   = dccp_v4_init_sequence(skb);
-	dreq->dreq_gss     = dreq->dreq_iss;
-	dreq->dreq_service = service;
-
-	if (dccp_v4_send_response(sk, req))
-		goto drop_and_free;
-
-	if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT)))
-		reqsk_free(req);
-	else
-		reqsk_put(req);
-
-	return 0;
-
-drop_and_free:
-	reqsk_free(req);
-drop:
-	__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
-	return -1;
-}
-EXPORT_SYMBOL_GPL(dccp_v4_conn_request);
-
-int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
-{
-	struct dccp_hdr *dh = dccp_hdr(skb);
-
-	if (sk->sk_state == DCCP_OPEN) { /* Fast path */
-		if (dccp_rcv_established(sk, skb, dh, skb->len))
-			goto reset;
-		return 0;
-	}
-
-	/*
-	 *  Step 3: Process LISTEN state
-	 *	 If P.type == Request or P contains a valid Init Cookie option,
-	 *	      (* Must scan the packet's options to check for Init
-	 *		 Cookies.  Only Init Cookies are processed here,
-	 *		 however; other options are processed in Step 8.  This
-	 *		 scan need only be performed if the endpoint uses Init
-	 *		 Cookies *)
-	 *	      (* Generate a new socket and switch to that socket *)
-	 *	      Set S := new socket for this port pair
-	 *	      S.state = RESPOND
-	 *	      Choose S.ISS (initial seqno) or set from Init Cookies
-	 *	      Initialize S.GAR := S.ISS
-	 *	      Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies
-	 *	      Continue with S.state == RESPOND
-	 *	      (* A Response packet will be generated in Step 11 *)
-	 *	 Otherwise,
-	 *	      Generate Reset(No Connection) unless P.type == Reset
-	 *	      Drop packet and return
-	 *
-	 * NOTE: the check for the packet types is done in
-	 *	 dccp_rcv_state_process
-	 */
-
-	if (dccp_rcv_state_process(sk, skb, dh, skb->len))
-		goto reset;
-	return 0;
-
-reset:
-	dccp_v4_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED);
-	kfree_skb(skb);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(dccp_v4_do_rcv);
-
-/**
- *	dccp_invalid_packet  -  check for malformed packets
- *	@skb: Packet to validate
- *
- *	Implements RFC 4340, 8.5:  Step 1: Check header basics
- *	Packets that fail these checks are ignored and do not receive Resets.
- */
-int dccp_invalid_packet(struct sk_buff *skb)
-{
-	const struct dccp_hdr *dh;
-	unsigned int cscov;
-	u8 dccph_doff;
-
-	if (skb->pkt_type != PACKET_HOST)
-		return 1;
-
-	/* If the packet is shorter than 12 bytes, drop packet and return */
-	if (!pskb_may_pull(skb, sizeof(struct dccp_hdr))) {
-		DCCP_WARN("pskb_may_pull failed\n");
-		return 1;
-	}
-
-	dh = dccp_hdr(skb);
-
-	/* If P.type is not understood, drop packet and return */
-	if (dh->dccph_type >= DCCP_PKT_INVALID) {
-		DCCP_WARN("invalid packet type\n");
-		return 1;
-	}
-
-	/*
-	 * If P.Data Offset is too small for packet type, drop packet and return
-	 */
-	dccph_doff = dh->dccph_doff;
-	if (dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) {
-		DCCP_WARN("P.Data Offset(%u) too small\n", dccph_doff);
-		return 1;
-	}
-	/*
-	 * If P.Data Offset is too large for packet, drop packet and return
-	 */
-	if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) {
-		DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff);
-		return 1;
-	}
-	dh = dccp_hdr(skb);
-	/*
-	 * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet
-	 * has short sequence numbers), drop packet and return
-	 */
-	if ((dh->dccph_type < DCCP_PKT_DATA    ||
-	    dh->dccph_type > DCCP_PKT_DATAACK) && dh->dccph_x == 0)  {
-		DCCP_WARN("P.type (%s) not Data || [Data]Ack, while P.X == 0\n",
-			  dccp_packet_name(dh->dccph_type));
-		return 1;
-	}
-
-	/*
-	 * If P.CsCov is too large for the packet size, drop packet and return.
-	 * This must come _before_ checksumming (not as RFC 4340 suggests).
-	 */
-	cscov = dccp_csum_coverage(skb);
-	if (cscov > skb->len) {
-		DCCP_WARN("P.CsCov %u exceeds packet length %d\n",
-			  dh->dccph_cscov, skb->len);
-		return 1;
-	}
-
-	/* If header checksum is incorrect, drop packet and return.
-	 * (This step is completed in the AF-dependent functions.) */
-	skb->csum = skb_checksum(skb, 0, cscov, 0);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(dccp_invalid_packet);
-
-/* this is called when real data arrives */
-static int dccp_v4_rcv(struct sk_buff *skb)
-{
-	const struct dccp_hdr *dh;
-	const struct iphdr *iph;
-	bool refcounted;
-	struct sock *sk;
-	int min_cov;
-
-	/* Step 1: Check header basics */
-
-	if (dccp_invalid_packet(skb))
-		goto discard_it;
-
-	iph = ip_hdr(skb);
-	/* Step 1: If header checksum is incorrect, drop packet and return */
-	if (dccp_v4_csum_finish(skb, iph->saddr, iph->daddr)) {
-		DCCP_WARN("dropped packet with invalid checksum\n");
-		goto discard_it;
-	}
-
-	dh = dccp_hdr(skb);
-
-	DCCP_SKB_CB(skb)->dccpd_seq  = dccp_hdr_seq(dh);
-	DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type;
-
-	dccp_pr_debug("%8.8s src=%pI4@%-5d dst=%pI4@%-5d seq=%llu",
-		      dccp_packet_name(dh->dccph_type),
-		      &iph->saddr, ntohs(dh->dccph_sport),
-		      &iph->daddr, ntohs(dh->dccph_dport),
-		      (unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq);
-
-	if (dccp_packet_without_ack(skb)) {
-		DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ;
-		dccp_pr_debug_cat("\n");
-	} else {
-		DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb);
-		dccp_pr_debug_cat(", ack=%llu\n", (unsigned long long)
-				  DCCP_SKB_CB(skb)->dccpd_ack_seq);
-	}
-
-lookup:
-	sk = __inet_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
-			       dh->dccph_sport, dh->dccph_dport, 0, &refcounted);
-	if (!sk) {
-		dccp_pr_debug("failed to look up flow ID in table and "
-			      "get corresponding socket\n");
-		goto no_dccp_socket;
-	}
-
-	/*
-	 * Step 2:
-	 *	... or S.state == TIMEWAIT,
-	 *		Generate Reset(No Connection) unless P.type == Reset
-	 *		Drop packet and return
-	 */
-	if (sk->sk_state == DCCP_TIME_WAIT) {
-		dccp_pr_debug("sk->sk_state == DCCP_TIME_WAIT: do_time_wait\n");
-		inet_twsk_put(inet_twsk(sk));
-		goto no_dccp_socket;
-	}
-
-	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
-		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk;
-
-		sk = req->rsk_listener;
-		if (unlikely(sk->sk_state != DCCP_LISTEN)) {
-			inet_csk_reqsk_queue_drop_and_put(sk, req);
-			goto lookup;
-		}
-		sock_hold(sk);
-		refcounted = true;
-		nsk = dccp_check_req(sk, skb, req);
-		if (!nsk) {
-			reqsk_put(req);
-			goto discard_and_relse;
-		}
-		if (nsk == sk) {
-			reqsk_put(req);
-		} else if (dccp_child_process(sk, nsk, skb)) {
-			dccp_v4_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED);
-			goto discard_and_relse;
-		} else {
-			sock_put(sk);
-			return 0;
-		}
-	}
-	/*
-	 * RFC 4340, sec. 9.2.1: Minimum Checksum Coverage
-	 *	o if MinCsCov = 0, only packets with CsCov = 0 are accepted
-	 *	o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov
-	 */
-	min_cov = dccp_sk(sk)->dccps_pcrlen;
-	if (dh->dccph_cscov && (min_cov == 0 || dh->dccph_cscov < min_cov))  {
-		dccp_pr_debug("Packet CsCov %d does not satisfy MinCsCov %d\n",
-			      dh->dccph_cscov, min_cov);
-		/* FIXME: "Such packets SHOULD be reported using Data Dropped
-		 *         options (Section 11.7) with Drop Code 0, Protocol
-		 *         Constraints."                                     */
-		goto discard_and_relse;
-	}
-
-	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
-		goto discard_and_relse;
-	nf_reset_ct(skb);
-
-	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted);
-
-no_dccp_socket:
-	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
-		goto discard_it;
-	/*
-	 * Step 2:
-	 *	If no socket ...
-	 *		Generate Reset(No Connection) unless P.type == Reset
-	 *		Drop packet and return
-	 */
-	if (dh->dccph_type != DCCP_PKT_RESET) {
-		DCCP_SKB_CB(skb)->dccpd_reset_code =
-					DCCP_RESET_CODE_NO_CONNECTION;
-		dccp_v4_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED);
-	}
-
-discard_it:
-	kfree_skb(skb);
-	return 0;
-
-discard_and_relse:
-	if (refcounted)
-		sock_put(sk);
-	goto discard_it;
-}
-
-static const struct inet_connection_sock_af_ops dccp_ipv4_af_ops = {
-	.queue_xmit	   = ip_queue_xmit,
-	.send_check	   = dccp_v4_send_check,
-	.rebuild_header	   = inet_sk_rebuild_header,
-	.conn_request	   = dccp_v4_conn_request,
-	.syn_recv_sock	   = dccp_v4_request_recv_sock,
-	.net_header_len	   = sizeof(struct iphdr),
-	.setsockopt	   = ip_setsockopt,
-	.getsockopt	   = ip_getsockopt,
-};
-
-static int dccp_v4_init_sock(struct sock *sk)
-{
-	static __u8 dccp_v4_ctl_sock_initialized;
-	int err = dccp_init_sock(sk, dccp_v4_ctl_sock_initialized);
-
-	if (err == 0) {
-		if (unlikely(!dccp_v4_ctl_sock_initialized))
-			dccp_v4_ctl_sock_initialized = 1;
-		inet_csk(sk)->icsk_af_ops = &dccp_ipv4_af_ops;
-	}
-
-	return err;
-}
-
-static struct timewait_sock_ops dccp_timewait_sock_ops = {
-	.twsk_obj_size	= sizeof(struct inet_timewait_sock),
-};
-
-static struct proto dccp_v4_prot = {
-	.name			= "DCCP",
-	.owner			= THIS_MODULE,
-	.close			= dccp_close,
-	.connect		= dccp_v4_connect,
-	.disconnect		= dccp_disconnect,
-	.ioctl			= dccp_ioctl,
-	.init			= dccp_v4_init_sock,
-	.setsockopt		= dccp_setsockopt,
-	.getsockopt		= dccp_getsockopt,
-	.sendmsg		= dccp_sendmsg,
-	.recvmsg		= dccp_recvmsg,
-	.backlog_rcv		= dccp_v4_do_rcv,
-	.hash			= inet_hash,
-	.unhash			= inet_unhash,
-	.accept			= inet_csk_accept,
-	.get_port		= inet_csk_get_port,
-	.shutdown		= dccp_shutdown,
-	.destroy		= dccp_destroy_sock,
-	.orphan_count		= &dccp_orphan_count,
-	.max_header		= MAX_DCCP_HEADER,
-	.obj_size		= sizeof(struct dccp_sock),
-	.slab_flags		= SLAB_TYPESAFE_BY_RCU,
-	.rsk_prot		= &dccp_request_sock_ops,
-	.twsk_prot		= &dccp_timewait_sock_ops,
-	.h.hashinfo		= &dccp_hashinfo,
-};
-
-static const struct net_protocol dccp_v4_protocol = {
-	.handler	= dccp_v4_rcv,
-	.err_handler	= dccp_v4_err,
-	.no_policy	= 1,
-	.icmp_strict_tag_validation = 1,
-};
-
-static const struct proto_ops inet_dccp_ops = {
-	.family		   = PF_INET,
-	.owner		   = THIS_MODULE,
-	.release	   = inet_release,
-	.bind		   = inet_bind,
-	.connect	   = inet_stream_connect,
-	.socketpair	   = sock_no_socketpair,
-	.accept		   = inet_accept,
-	.getname	   = inet_getname,
-	/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
-	.poll		   = dccp_poll,
-	.ioctl		   = inet_ioctl,
-	.gettstamp	   = sock_gettstamp,
-	/* FIXME: work on inet_listen to rename it to sock_common_listen */
-	.listen		   = inet_dccp_listen,
-	.shutdown	   = inet_shutdown,
-	.setsockopt	   = sock_common_setsockopt,
-	.getsockopt	   = sock_common_getsockopt,
-	.sendmsg	   = inet_sendmsg,
-	.recvmsg	   = sock_common_recvmsg,
-	.mmap		   = sock_no_mmap,
-};
-
-static struct inet_protosw dccp_v4_protosw = {
-	.type		= SOCK_DCCP,
-	.protocol	= IPPROTO_DCCP,
-	.prot		= &dccp_v4_prot,
-	.ops		= &inet_dccp_ops,
-	.flags		= INET_PROTOSW_ICSK,
-};
-
-static int __net_init dccp_v4_init_net(struct net *net)
-{
-	struct dccp_v4_pernet *pn = net_generic(net, dccp_v4_pernet_id);
-
-	if (dccp_hashinfo.bhash == NULL)
-		return -ESOCKTNOSUPPORT;
-
-	return inet_ctl_sock_create(&pn->v4_ctl_sk, PF_INET,
-				    SOCK_DCCP, IPPROTO_DCCP, net);
-}
-
-static void __net_exit dccp_v4_exit_net(struct net *net)
-{
-	struct dccp_v4_pernet *pn = net_generic(net, dccp_v4_pernet_id);
-
-	inet_ctl_sock_destroy(pn->v4_ctl_sk);
-}
-
-static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list)
-{
-	inet_twsk_purge(&dccp_hashinfo);
-}
-
-static struct pernet_operations dccp_v4_ops = {
-	.init	= dccp_v4_init_net,
-	.exit	= dccp_v4_exit_net,
-	.exit_batch = dccp_v4_exit_batch,
-	.id	= &dccp_v4_pernet_id,
-	.size   = sizeof(struct dccp_v4_pernet),
-};
-
-static int __init dccp_v4_init(void)
-{
-	int err = proto_register(&dccp_v4_prot, 1);
-
-	if (err)
-		goto out;
-
-	inet_register_protosw(&dccp_v4_protosw);
-
-	err = register_pernet_subsys(&dccp_v4_ops);
-	if (err)
-		goto out_destroy_ctl_sock;
-
-	err = inet_add_protocol(&dccp_v4_protocol, IPPROTO_DCCP);
-	if (err)
-		goto out_proto_unregister;
-
-out:
-	return err;
-out_proto_unregister:
-	unregister_pernet_subsys(&dccp_v4_ops);
-out_destroy_ctl_sock:
-	inet_unregister_protosw(&dccp_v4_protosw);
-	proto_unregister(&dccp_v4_prot);
-	goto out;
-}
-
-static void __exit dccp_v4_exit(void)
-{
-	inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP);
-	unregister_pernet_subsys(&dccp_v4_ops);
-	inet_unregister_protosw(&dccp_v4_protosw);
-	proto_unregister(&dccp_v4_prot);
-}
-
-module_init(dccp_v4_init);
-module_exit(dccp_v4_exit);
-
-/*
- * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33)
- * values directly, Also cover the case where the protocol is not specified,
- * i.e. net-pf-PF_INET-proto-0-type-SOCK_DCCP
- */
-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 33, 6);
-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 0, 6);
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>");
-MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol");
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
deleted file mode 100644
index e24dbffabfc1..000000000000
--- a/net/dccp/ipv6.c
+++ /dev/null
@@ -1,1174 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *	DCCP over IPv6
- *	Linux INET6 implementation
- *
- *	Based on net/dccp6/ipv6.c
- *
- *	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
- */
-
-#include <linux/module.h>
-#include <linux/random.h>
-#include <linux/slab.h>
-#include <linux/xfrm.h>
-#include <linux/string.h>
-
-#include <net/addrconf.h>
-#include <net/inet_common.h>
-#include <net/inet_hashtables.h>
-#include <net/inet_sock.h>
-#include <net/inet6_connection_sock.h>
-#include <net/inet6_hashtables.h>
-#include <net/ip6_route.h>
-#include <net/ipv6.h>
-#include <net/protocol.h>
-#include <net/transp_v6.h>
-#include <net/ip6_checksum.h>
-#include <net/xfrm.h>
-#include <net/secure_seq.h>
-#include <net/netns/generic.h>
-#include <net/sock.h>
-#include <net/rstreason.h>
-
-#include "dccp.h"
-#include "ipv6.h"
-#include "feat.h"
-
-struct dccp_v6_pernet {
-	struct sock *v6_ctl_sk;
-};
-
-static unsigned int dccp_v6_pernet_id __read_mostly;
-
-/* The per-net v6_ctl_sk is used for sending RSTs and ACKs */
-
-static const struct inet_connection_sock_af_ops dccp_ipv6_mapped;
-static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops;
-
-/* add pseudo-header to DCCP checksum stored in skb->csum */
-static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb,
-				      const struct in6_addr *saddr,
-				      const struct in6_addr *daddr)
-{
-	return csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_DCCP, skb->csum);
-}
-
-static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb)
-{
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct dccp_hdr *dh = dccp_hdr(skb);
-
-	dccp_csum_outgoing(skb);
-	dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &sk->sk_v6_daddr);
-}
-
-static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb)
-{
-	return secure_dccpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
-					     ipv6_hdr(skb)->saddr.s6_addr32,
-					     dccp_hdr(skb)->dccph_dport,
-					     dccp_hdr(skb)->dccph_sport     );
-
-}
-
-static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
-			u8 type, u8 code, int offset, __be32 info)
-{
-	const struct ipv6hdr *hdr;
-	const struct dccp_hdr *dh;
-	struct dccp_sock *dp;
-	struct ipv6_pinfo *np;
-	struct sock *sk;
-	int err;
-	__u64 seq;
-	struct net *net = dev_net(skb->dev);
-
-	if (!pskb_may_pull(skb, offset + sizeof(*dh)))
-		return -EINVAL;
-	dh = (struct dccp_hdr *)(skb->data + offset);
-	if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh)))
-		return -EINVAL;
-	hdr = (const struct ipv6hdr *)skb->data;
-	dh = (struct dccp_hdr *)(skb->data + offset);
-
-	sk = __inet6_lookup_established(net, &dccp_hashinfo,
-					&hdr->daddr, dh->dccph_dport,
-					&hdr->saddr, ntohs(dh->dccph_sport),
-					inet6_iif(skb), 0);
-
-	if (!sk) {
-		__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
-				  ICMP6_MIB_INERRORS);
-		return -ENOENT;
-	}
-
-	if (sk->sk_state == DCCP_TIME_WAIT) {
-		inet_twsk_put(inet_twsk(sk));
-		return 0;
-	}
-	seq = dccp_hdr_seq(dh);
-	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
-		dccp_req_err(sk, seq);
-		return 0;
-	}
-
-	bh_lock_sock(sk);
-	if (sock_owned_by_user(sk))
-		__NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
-
-	if (sk->sk_state == DCCP_CLOSED)
-		goto out;
-
-	dp = dccp_sk(sk);
-	if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
-	    !between48(seq, dp->dccps_awl, dp->dccps_awh)) {
-		__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
-		goto out;
-	}
-
-	np = inet6_sk(sk);
-
-	if (type == NDISC_REDIRECT) {
-		if (!sock_owned_by_user(sk)) {
-			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
-
-			if (dst)
-				dst->ops->redirect(dst, sk, skb);
-		}
-		goto out;
-	}
-
-	if (type == ICMPV6_PKT_TOOBIG) {
-		struct dst_entry *dst = NULL;
-
-		if (!ip6_sk_accept_pmtu(sk))
-			goto out;
-
-		if (sock_owned_by_user(sk))
-			goto out;
-		if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED))
-			goto out;
-
-		dst = inet6_csk_update_pmtu(sk, ntohl(info));
-		if (!dst)
-			goto out;
-
-		if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst))
-			dccp_sync_mss(sk, dst_mtu(dst));
-		goto out;
-	}
-
-	icmpv6_err_convert(type, code, &err);
-
-	/* Might be for an request_sock */
-	switch (sk->sk_state) {
-	case DCCP_REQUESTING:
-	case DCCP_RESPOND:  /* Cannot happen.
-			       It can, it SYNs are crossed. --ANK */
-		if (!sock_owned_by_user(sk)) {
-			__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
-			sk->sk_err = err;
-			/*
-			 * Wake people up to see the error
-			 * (see connect in sock.c)
-			 */
-			sk_error_report(sk);
-			dccp_done(sk);
-		} else {
-			WRITE_ONCE(sk->sk_err_soft, err);
-		}
-		goto out;
-	}
-
-	if (!sock_owned_by_user(sk) && inet6_test_bit(RECVERR6, sk)) {
-		sk->sk_err = err;
-		sk_error_report(sk);
-	} else {
-		WRITE_ONCE(sk->sk_err_soft, err);
-	}
-out:
-	bh_unlock_sock(sk);
-	sock_put(sk);
-	return 0;
-}
-
-
-static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req)
-{
-	struct inet_request_sock *ireq = inet_rsk(req);
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct sk_buff *skb;
-	struct in6_addr *final_p, final;
-	struct flowi6 fl6;
-	int err = -1;
-	struct dst_entry *dst;
-
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_DCCP;
-	fl6.daddr = ireq->ir_v6_rmt_addr;
-	fl6.saddr = ireq->ir_v6_loc_addr;
-	fl6.flowlabel = 0;
-	fl6.flowi6_oif = ireq->ir_iif;
-	fl6.fl6_dport = ireq->ir_rmt_port;
-	fl6.fl6_sport = htons(ireq->ir_num);
-	security_req_classify_flow(req, flowi6_to_flowi_common(&fl6));
-
-
-	rcu_read_lock();
-	final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
-	rcu_read_unlock();
-
-	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
-	if (IS_ERR(dst)) {
-		err = PTR_ERR(dst);
-		dst = NULL;
-		goto done;
-	}
-
-	skb = dccp_make_response(sk, dst, req);
-	if (skb != NULL) {
-		struct dccp_hdr *dh = dccp_hdr(skb);
-		struct ipv6_txoptions *opt;
-
-		dh->dccph_checksum = dccp_v6_csum_finish(skb,
-							 &ireq->ir_v6_loc_addr,
-							 &ireq->ir_v6_rmt_addr);
-		fl6.daddr = ireq->ir_v6_rmt_addr;
-		rcu_read_lock();
-		opt = ireq->ipv6_opt;
-		if (!opt)
-			opt = rcu_dereference(np->opt);
-		err = ip6_xmit(sk, skb, &fl6, READ_ONCE(sk->sk_mark), opt,
-			       np->tclass, READ_ONCE(sk->sk_priority));
-		rcu_read_unlock();
-		err = net_xmit_eval(err);
-	}
-
-done:
-	dst_release(dst);
-	return err;
-}
-
-static void dccp_v6_reqsk_destructor(struct request_sock *req)
-{
-	dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
-	kfree(inet_rsk(req)->ipv6_opt);
-	kfree_skb(inet_rsk(req)->pktopts);
-}
-
-static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb,
-				   enum sk_rst_reason reason)
-{
-	const struct ipv6hdr *rxip6h;
-	struct sk_buff *skb;
-	struct flowi6 fl6;
-	struct net *net = dev_net(skb_dst(rxskb)->dev);
-	struct dccp_v6_pernet *pn;
-	struct sock *ctl_sk;
-	struct dst_entry *dst;
-
-	if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET)
-		return;
-
-	if (!ipv6_unicast_destination(rxskb))
-		return;
-
-	pn = net_generic(net, dccp_v6_pernet_id);
-	ctl_sk = pn->v6_ctl_sk;
-	skb = dccp_ctl_make_reset(ctl_sk, rxskb);
-	if (skb == NULL)
-		return;
-
-	rxip6h = ipv6_hdr(rxskb);
-	dccp_hdr(skb)->dccph_checksum = dccp_v6_csum_finish(skb, &rxip6h->saddr,
-							    &rxip6h->daddr);
-
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.daddr = rxip6h->saddr;
-	fl6.saddr = rxip6h->daddr;
-
-	fl6.flowi6_proto = IPPROTO_DCCP;
-	fl6.flowi6_oif = inet6_iif(rxskb);
-	fl6.fl6_dport = dccp_hdr(skb)->dccph_dport;
-	fl6.fl6_sport = dccp_hdr(skb)->dccph_sport;
-	security_skb_classify_flow(rxskb, flowi6_to_flowi_common(&fl6));
-
-	/* sk = NULL, but it is safe for now. RST socket required. */
-	dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
-	if (!IS_ERR(dst)) {
-		skb_dst_set(skb, dst);
-		ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0, 0);
-		DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
-		DCCP_INC_STATS(DCCP_MIB_OUTRSTS);
-		return;
-	}
-
-	kfree_skb(skb);
-}
-
-static struct request_sock_ops dccp6_request_sock_ops = {
-	.family		= AF_INET6,
-	.obj_size	= sizeof(struct dccp6_request_sock),
-	.rtx_syn_ack	= dccp_v6_send_response,
-	.send_ack	= dccp_reqsk_send_ack,
-	.destructor	= dccp_v6_reqsk_destructor,
-	.send_reset	= dccp_v6_ctl_send_reset,
-	.syn_ack_timeout = dccp_syn_ack_timeout,
-};
-
-static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
-{
-	struct request_sock *req;
-	struct dccp_request_sock *dreq;
-	struct inet_request_sock *ireq;
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	const __be32 service = dccp_hdr_request(skb)->dccph_req_service;
-	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
-
-	if (skb->protocol == htons(ETH_P_IP))
-		return dccp_v4_conn_request(sk, skb);
-
-	if (!ipv6_unicast_destination(skb))
-		return 0;	/* discard, don't send a reset here */
-
-	if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
-		__IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
-		return 0;
-	}
-
-	if (dccp_bad_service_code(sk, service)) {
-		dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE;
-		goto drop;
-	}
-	/*
-	 * There are no SYN attacks on IPv6, yet...
-	 */
-	dcb->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
-	if (inet_csk_reqsk_queue_is_full(sk))
-		goto drop;
-
-	if (sk_acceptq_is_full(sk))
-		goto drop;
-
-	req = inet_reqsk_alloc(&dccp6_request_sock_ops, sk, true);
-	if (req == NULL)
-		goto drop;
-
-	if (dccp_reqsk_init(req, dccp_sk(sk), skb))
-		goto drop_and_free;
-
-	dreq = dccp_rsk(req);
-	if (dccp_parse_options(sk, dreq, skb))
-		goto drop_and_free;
-
-	ireq = inet_rsk(req);
-	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
-	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
-	ireq->ir_rmt_addr = LOOPBACK4_IPV6;
-	ireq->ir_loc_addr = LOOPBACK4_IPV6;
-
-	ireq->ireq_family = AF_INET6;
-	ireq->ir_mark = inet_request_mark(sk, skb);
-
-	if (security_inet_conn_request(sk, skb, req))
-		goto drop_and_free;
-
-	if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) ||
-	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
-	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
-		refcount_inc(&skb->users);
-		ireq->pktopts = skb;
-	}
-	ireq->ir_iif = READ_ONCE(sk->sk_bound_dev_if);
-
-	/* So that link locals have meaning */
-	if (!ireq->ir_iif &&
-	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
-		ireq->ir_iif = inet6_iif(skb);
-
-	/*
-	 * Step 3: Process LISTEN state
-	 *
-	 *   Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie
-	 *
-	 * Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child().
-	 */
-	dreq->dreq_isr	   = dcb->dccpd_seq;
-	dreq->dreq_gsr     = dreq->dreq_isr;
-	dreq->dreq_iss	   = dccp_v6_init_sequence(skb);
-	dreq->dreq_gss     = dreq->dreq_iss;
-	dreq->dreq_service = service;
-
-	if (dccp_v6_send_response(sk, req))
-		goto drop_and_free;
-
-	if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT)))
-		reqsk_free(req);
-	else
-		reqsk_put(req);
-
-	return 0;
-
-drop_and_free:
-	reqsk_free(req);
-drop:
-	__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
-	return -1;
-}
-
-static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
-					      struct sk_buff *skb,
-					      struct request_sock *req,
-					      struct dst_entry *dst,
-					      struct request_sock *req_unhash,
-					      bool *own_req)
-{
-	struct inet_request_sock *ireq = inet_rsk(req);
-	struct ipv6_pinfo *newnp;
-	const struct ipv6_pinfo *np = inet6_sk(sk);
-	struct ipv6_txoptions *opt;
-	struct inet_sock *newinet;
-	struct dccp6_sock *newdp6;
-	struct sock *newsk;
-
-	if (skb->protocol == htons(ETH_P_IP)) {
-		/*
-		 *	v6 mapped
-		 */
-		newsk = dccp_v4_request_recv_sock(sk, skb, req, dst,
-						  req_unhash, own_req);
-		if (newsk == NULL)
-			return NULL;
-
-		newdp6 = (struct dccp6_sock *)newsk;
-		newinet = inet_sk(newsk);
-		newinet->pinet6 = &newdp6->inet6;
-		newnp = inet6_sk(newsk);
-
-		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
-
-		newnp->saddr = newsk->sk_v6_rcv_saddr;
-
-		inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
-		newsk->sk_backlog_rcv = dccp_v4_do_rcv;
-		newnp->pktoptions  = NULL;
-		newnp->opt	   = NULL;
-		newnp->ipv6_mc_list = NULL;
-		newnp->ipv6_ac_list = NULL;
-		newnp->ipv6_fl_list = NULL;
-		newnp->mcast_oif   = inet_iif(skb);
-		newnp->mcast_hops  = ip_hdr(skb)->ttl;
-
-		/*
-		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
-		 * here, dccp_create_openreq_child now does this for us, see the comment in
-		 * that function for the gory details. -acme
-		 */
-
-		/* It is tricky place. Until this moment IPv4 tcp
-		   worked with IPv6 icsk.icsk_af_ops.
-		   Sync it now.
-		 */
-		dccp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
-
-		return newsk;
-	}
-
-
-	if (sk_acceptq_is_full(sk))
-		goto out_overflow;
-
-	if (!dst) {
-		struct flowi6 fl6;
-
-		dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_DCCP);
-		if (!dst)
-			goto out;
-	}
-
-	newsk = dccp_create_openreq_child(sk, req, skb);
-	if (newsk == NULL)
-		goto out_nonewsk;
-
-	/*
-	 * No need to charge this sock to the relevant IPv6 refcnt debug socks
-	 * count here, dccp_create_openreq_child now does this for us, see the
-	 * comment in that function for the gory details. -acme
-	 */
-
-	ip6_dst_store(newsk, dst, NULL, NULL);
-	newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM |
-						      NETIF_F_TSO);
-	newdp6 = (struct dccp6_sock *)newsk;
-	newinet = inet_sk(newsk);
-	newinet->pinet6 = &newdp6->inet6;
-	newnp = inet6_sk(newsk);
-
-	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
-
-	newnp->saddr		= ireq->ir_v6_loc_addr;
-
-	/* Now IPv6 options...
-
-	   First: no IPv4 options.
-	 */
-	newinet->inet_opt = NULL;
-
-	/* Clone RX bits */
-	newnp->rxopt.all = np->rxopt.all;
-
-	newnp->ipv6_mc_list = NULL;
-	newnp->ipv6_ac_list = NULL;
-	newnp->ipv6_fl_list = NULL;
-	newnp->pktoptions = NULL;
-	newnp->opt	  = NULL;
-	newnp->mcast_oif  = inet6_iif(skb);
-	newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
-
-	/*
-	 * Clone native IPv6 options from listening socket (if any)
-	 *
-	 * Yes, keeping reference count would be much more clever, but we make
-	 * one more one thing there: reattach optmem to newsk.
-	 */
-	opt = ireq->ipv6_opt;
-	if (!opt)
-		opt = rcu_dereference(np->opt);
-	if (opt) {
-		opt = ipv6_dup_options(newsk, opt);
-		RCU_INIT_POINTER(newnp->opt, opt);
-	}
-	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (opt)
-		inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
-						    opt->opt_flen;
-
-	dccp_sync_mss(newsk, dst_mtu(dst));
-
-	if (__inet_inherit_port(sk, newsk) < 0) {
-		inet_csk_prepare_forced_close(newsk);
-		dccp_done(newsk);
-		goto out;
-	}
-	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL);
-	/* Clone pktoptions received with SYN, if we own the req */
-	if (*own_req && ireq->pktopts) {
-		newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk);
-		consume_skb(ireq->pktopts);
-		ireq->pktopts = NULL;
-	}
-
-	return newsk;
-
-out_overflow:
-	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
-out_nonewsk:
-	dst_release(dst);
-out:
-	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
-	return NULL;
-}
-
-/* The socket must have it's spinlock held when we get
- * here.
- *
- * We have a potential double-lock case here, so even when
- * doing backlog processing we use the BH locking scheme.
- * This is because we cannot sleep with the original spinlock
- * held.
- */
-static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
-{
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct sk_buff *opt_skb = NULL;
-
-	/* Imagine: socket is IPv6. IPv4 packet arrives,
-	   goes to IPv4 receive handler and backlogged.
-	   From backlog it always goes here. Kerboom...
-	   Fortunately, dccp_rcv_established and rcv_established
-	   handle them correctly, but it is not case with
-	   dccp_v6_hnd_req and dccp_v6_ctl_send_reset().   --ANK
-	 */
-
-	if (skb->protocol == htons(ETH_P_IP))
-		return dccp_v4_do_rcv(sk, skb);
-
-	if (sk_filter(sk, skb))
-		goto discard;
-
-	/*
-	 * socket locking is here for SMP purposes as backlog rcv is currently
-	 * called with bh processing disabled.
-	 */
-
-	/* Do Stevens' IPV6_PKTOPTIONS.
-
-	   Yes, guys, it is the only place in our code, where we
-	   may make it not affecting IPv4.
-	   The rest of code is protocol independent,
-	   and I do not like idea to uglify IPv4.
-
-	   Actually, all the idea behind IPV6_PKTOPTIONS
-	   looks not very well thought. For now we latch
-	   options, received in the last packet, enqueued
-	   by tcp. Feel free to propose better solution.
-					       --ANK (980728)
-	 */
-	if (np->rxopt.all && sk->sk_state != DCCP_LISTEN)
-		opt_skb = skb_clone_and_charge_r(skb, sk);
-
-	if (sk->sk_state == DCCP_OPEN) { /* Fast path */
-		if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len))
-			goto reset;
-		if (opt_skb)
-			goto ipv6_pktoptions;
-		return 0;
-	}
-
-	/*
-	 *  Step 3: Process LISTEN state
-	 *     If S.state == LISTEN,
-	 *	 If P.type == Request or P contains a valid Init Cookie option,
-	 *	      (* Must scan the packet's options to check for Init
-	 *		 Cookies.  Only Init Cookies are processed here,
-	 *		 however; other options are processed in Step 8.  This
-	 *		 scan need only be performed if the endpoint uses Init
-	 *		 Cookies *)
-	 *	      (* Generate a new socket and switch to that socket *)
-	 *	      Set S := new socket for this port pair
-	 *	      S.state = RESPOND
-	 *	      Choose S.ISS (initial seqno) or set from Init Cookies
-	 *	      Initialize S.GAR := S.ISS
-	 *	      Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies
-	 *	      Continue with S.state == RESPOND
-	 *	      (* A Response packet will be generated in Step 11 *)
-	 *	 Otherwise,
-	 *	      Generate Reset(No Connection) unless P.type == Reset
-	 *	      Drop packet and return
-	 *
-	 * NOTE: the check for the packet types is done in
-	 *	 dccp_rcv_state_process
-	 */
-
-	if (dccp_rcv_state_process(sk, skb, dccp_hdr(skb), skb->len))
-		goto reset;
-	if (opt_skb)
-		goto ipv6_pktoptions;
-	return 0;
-
-reset:
-	dccp_v6_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED);
-discard:
-	if (opt_skb != NULL)
-		__kfree_skb(opt_skb);
-	kfree_skb(skb);
-	return 0;
-
-/* Handling IPV6_PKTOPTIONS skb the similar
- * way it's done for net/ipv6/tcp_ipv6.c
- */
-ipv6_pktoptions:
-	if (!((1 << sk->sk_state) & (DCCPF_CLOSED | DCCPF_LISTEN))) {
-		if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
-			WRITE_ONCE(np->mcast_oif, inet6_iif(opt_skb));
-		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
-			WRITE_ONCE(np->mcast_hops, ipv6_hdr(opt_skb)->hop_limit);
-		if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
-			np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
-		if (inet6_test_bit(REPFLOW, sk))
-			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
-		if (ipv6_opt_accepted(sk, opt_skb,
-				      &DCCP_SKB_CB(opt_skb)->header.h6)) {
-			memmove(IP6CB(opt_skb),
-				&DCCP_SKB_CB(opt_skb)->header.h6,
-				sizeof(struct inet6_skb_parm));
-			opt_skb = xchg(&np->pktoptions, opt_skb);
-		} else {
-			__kfree_skb(opt_skb);
-			opt_skb = xchg(&np->pktoptions, NULL);
-		}
-	}
-
-	kfree_skb(opt_skb);
-	return 0;
-}
-
-static int dccp_v6_rcv(struct sk_buff *skb)
-{
-	const struct dccp_hdr *dh;
-	bool refcounted;
-	struct sock *sk;
-	int min_cov;
-
-	/* Step 1: Check header basics */
-
-	if (dccp_invalid_packet(skb))
-		goto discard_it;
-
-	/* Step 1: If header checksum is incorrect, drop packet and return. */
-	if (dccp_v6_csum_finish(skb, &ipv6_hdr(skb)->saddr,
-				     &ipv6_hdr(skb)->daddr)) {
-		DCCP_WARN("dropped packet with invalid checksum\n");
-		goto discard_it;
-	}
-
-	dh = dccp_hdr(skb);
-
-	DCCP_SKB_CB(skb)->dccpd_seq  = dccp_hdr_seq(dh);
-	DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type;
-
-	if (dccp_packet_without_ack(skb))
-		DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ;
-	else
-		DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb);
-
-lookup:
-	sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
-			        dh->dccph_sport, dh->dccph_dport,
-				inet6_iif(skb), 0, &refcounted);
-	if (!sk) {
-		dccp_pr_debug("failed to look up flow ID in table and "
-			      "get corresponding socket\n");
-		goto no_dccp_socket;
-	}
-
-	/*
-	 * Step 2:
-	 *	... or S.state == TIMEWAIT,
-	 *		Generate Reset(No Connection) unless P.type == Reset
-	 *		Drop packet and return
-	 */
-	if (sk->sk_state == DCCP_TIME_WAIT) {
-		dccp_pr_debug("sk->sk_state == DCCP_TIME_WAIT: do_time_wait\n");
-		inet_twsk_put(inet_twsk(sk));
-		goto no_dccp_socket;
-	}
-
-	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
-		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk;
-
-		sk = req->rsk_listener;
-		if (unlikely(sk->sk_state != DCCP_LISTEN)) {
-			inet_csk_reqsk_queue_drop_and_put(sk, req);
-			goto lookup;
-		}
-		sock_hold(sk);
-		refcounted = true;
-		nsk = dccp_check_req(sk, skb, req);
-		if (!nsk) {
-			reqsk_put(req);
-			goto discard_and_relse;
-		}
-		if (nsk == sk) {
-			reqsk_put(req);
-		} else if (dccp_child_process(sk, nsk, skb)) {
-			dccp_v6_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED);
-			goto discard_and_relse;
-		} else {
-			sock_put(sk);
-			return 0;
-		}
-	}
-	/*
-	 * RFC 4340, sec. 9.2.1: Minimum Checksum Coverage
-	 *	o if MinCsCov = 0, only packets with CsCov = 0 are accepted
-	 *	o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov
-	 */
-	min_cov = dccp_sk(sk)->dccps_pcrlen;
-	if (dh->dccph_cscov  &&  (min_cov == 0 || dh->dccph_cscov < min_cov))  {
-		dccp_pr_debug("Packet CsCov %d does not satisfy MinCsCov %d\n",
-			      dh->dccph_cscov, min_cov);
-		/* FIXME: send Data Dropped option (see also dccp_v4_rcv) */
-		goto discard_and_relse;
-	}
-
-	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
-		goto discard_and_relse;
-	nf_reset_ct(skb);
-
-	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4,
-				refcounted) ? -1 : 0;
-
-no_dccp_socket:
-	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
-		goto discard_it;
-	/*
-	 * Step 2:
-	 *	If no socket ...
-	 *		Generate Reset(No Connection) unless P.type == Reset
-	 *		Drop packet and return
-	 */
-	if (dh->dccph_type != DCCP_PKT_RESET) {
-		DCCP_SKB_CB(skb)->dccpd_reset_code =
-					DCCP_RESET_CODE_NO_CONNECTION;
-		dccp_v6_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED);
-	}
-
-discard_it:
-	kfree_skb(skb);
-	return 0;
-
-discard_and_relse:
-	if (refcounted)
-		sock_put(sk);
-	goto discard_it;
-}
-
-static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
-			   int addr_len)
-{
-	struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr;
-	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct inet_sock *inet = inet_sk(sk);
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct in6_addr *saddr = NULL, *final_p, final;
-	struct ipv6_txoptions *opt;
-	struct flowi6 fl6;
-	struct dst_entry *dst;
-	int addr_type;
-	int err;
-
-	dp->dccps_role = DCCP_ROLE_CLIENT;
-
-	if (addr_len < SIN6_LEN_RFC2133)
-		return -EINVAL;
-
-	if (usin->sin6_family != AF_INET6)
-		return -EAFNOSUPPORT;
-
-	memset(&fl6, 0, sizeof(fl6));
-
-	if (inet6_test_bit(SNDFLOW, sk)) {
-		fl6.flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
-		IP6_ECN_flow_init(fl6.flowlabel);
-		if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) {
-			struct ip6_flowlabel *flowlabel;
-			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
-			if (IS_ERR(flowlabel))
-				return -EINVAL;
-			fl6_sock_release(flowlabel);
-		}
-	}
-	/*
-	 * connect() to INADDR_ANY means loopback (BSD'ism).
-	 */
-	if (ipv6_addr_any(&usin->sin6_addr))
-		usin->sin6_addr.s6_addr[15] = 1;
-
-	addr_type = ipv6_addr_type(&usin->sin6_addr);
-
-	if (addr_type & IPV6_ADDR_MULTICAST)
-		return -ENETUNREACH;
-
-	if (addr_type & IPV6_ADDR_LINKLOCAL) {
-		if (addr_len >= sizeof(struct sockaddr_in6) &&
-		    usin->sin6_scope_id) {
-			/* If interface is set while binding, indices
-			 * must coincide.
-			 */
-			if (sk->sk_bound_dev_if &&
-			    sk->sk_bound_dev_if != usin->sin6_scope_id)
-				return -EINVAL;
-
-			sk->sk_bound_dev_if = usin->sin6_scope_id;
-		}
-
-		/* Connect to link-local address requires an interface */
-		if (!sk->sk_bound_dev_if)
-			return -EINVAL;
-	}
-
-	sk->sk_v6_daddr = usin->sin6_addr;
-	np->flow_label = fl6.flowlabel;
-
-	/*
-	 * DCCP over IPv4
-	 */
-	if (addr_type == IPV6_ADDR_MAPPED) {
-		u32 exthdrlen = icsk->icsk_ext_hdr_len;
-		struct sockaddr_in sin;
-
-		net_dbg_ratelimited("connect: ipv4 mapped\n");
-
-		if (ipv6_only_sock(sk))
-			return -ENETUNREACH;
-
-		sin.sin_family = AF_INET;
-		sin.sin_port = usin->sin6_port;
-		sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
-
-		icsk->icsk_af_ops = &dccp_ipv6_mapped;
-		sk->sk_backlog_rcv = dccp_v4_do_rcv;
-
-		err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
-		if (err) {
-			icsk->icsk_ext_hdr_len = exthdrlen;
-			icsk->icsk_af_ops = &dccp_ipv6_af_ops;
-			sk->sk_backlog_rcv = dccp_v6_do_rcv;
-			goto failure;
-		}
-		np->saddr = sk->sk_v6_rcv_saddr;
-		return err;
-	}
-
-	if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
-		saddr = &sk->sk_v6_rcv_saddr;
-
-	fl6.flowi6_proto = IPPROTO_DCCP;
-	fl6.daddr = sk->sk_v6_daddr;
-	fl6.saddr = saddr ? *saddr : np->saddr;
-	fl6.flowi6_oif = sk->sk_bound_dev_if;
-	fl6.fl6_dport = usin->sin6_port;
-	fl6.fl6_sport = inet->inet_sport;
-	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
-
-	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
-	final_p = fl6_update_dst(&fl6, opt, &final);
-
-	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
-	if (IS_ERR(dst)) {
-		err = PTR_ERR(dst);
-		goto failure;
-	}
-
-	if (saddr == NULL) {
-		saddr = &fl6.saddr;
-
-		err = inet_bhash2_update_saddr(sk, saddr, AF_INET6);
-		if (err)
-			goto failure;
-	}
-
-	/* set the source address */
-	np->saddr = *saddr;
-	inet->inet_rcv_saddr = LOOPBACK4_IPV6;
-
-	ip6_dst_store(sk, dst, NULL, NULL);
-
-	icsk->icsk_ext_hdr_len = 0;
-	if (opt)
-		icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
-
-	inet->inet_dport = usin->sin6_port;
-
-	dccp_set_state(sk, DCCP_REQUESTING);
-	err = inet6_hash_connect(&dccp_death_row, sk);
-	if (err)
-		goto late_failure;
-
-	dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32,
-						      sk->sk_v6_daddr.s6_addr32,
-						      inet->inet_sport,
-						      inet->inet_dport);
-	err = dccp_connect(sk);
-	if (err)
-		goto late_failure;
-
-	return 0;
-
-late_failure:
-	dccp_set_state(sk, DCCP_CLOSED);
-	inet_bhash2_reset_saddr(sk);
-	__sk_dst_reset(sk);
-failure:
-	inet->inet_dport = 0;
-	sk->sk_route_caps = 0;
-	return err;
-}
-
-static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops = {
-	.queue_xmit	   = inet6_csk_xmit,
-	.send_check	   = dccp_v6_send_check,
-	.rebuild_header	   = inet6_sk_rebuild_header,
-	.conn_request	   = dccp_v6_conn_request,
-	.syn_recv_sock	   = dccp_v6_request_recv_sock,
-	.net_header_len	   = sizeof(struct ipv6hdr),
-	.setsockopt	   = ipv6_setsockopt,
-	.getsockopt	   = ipv6_getsockopt,
-};
-
-/*
- *	DCCP over IPv4 via INET6 API
- */
-static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = {
-	.queue_xmit	   = ip_queue_xmit,
-	.send_check	   = dccp_v4_send_check,
-	.rebuild_header	   = inet_sk_rebuild_header,
-	.conn_request	   = dccp_v6_conn_request,
-	.syn_recv_sock	   = dccp_v6_request_recv_sock,
-	.net_header_len	   = sizeof(struct iphdr),
-	.setsockopt	   = ipv6_setsockopt,
-	.getsockopt	   = ipv6_getsockopt,
-};
-
-static void dccp_v6_sk_destruct(struct sock *sk)
-{
-	dccp_destruct_common(sk);
-	inet6_sock_destruct(sk);
-}
-
-/* NOTE: A lot of things set to zero explicitly by call to
- *       sk_alloc() so need not be done here.
- */
-static int dccp_v6_init_sock(struct sock *sk)
-{
-	static __u8 dccp_v6_ctl_sock_initialized;
-	int err = dccp_init_sock(sk, dccp_v6_ctl_sock_initialized);
-
-	if (err == 0) {
-		if (unlikely(!dccp_v6_ctl_sock_initialized))
-			dccp_v6_ctl_sock_initialized = 1;
-		inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops;
-		sk->sk_destruct = dccp_v6_sk_destruct;
-	}
-
-	return err;
-}
-
-static struct timewait_sock_ops dccp6_timewait_sock_ops = {
-	.twsk_obj_size	= sizeof(struct dccp6_timewait_sock),
-};
-
-static struct proto dccp_v6_prot = {
-	.name		   = "DCCPv6",
-	.owner		   = THIS_MODULE,
-	.close		   = dccp_close,
-	.connect	   = dccp_v6_connect,
-	.disconnect	   = dccp_disconnect,
-	.ioctl		   = dccp_ioctl,
-	.init		   = dccp_v6_init_sock,
-	.setsockopt	   = dccp_setsockopt,
-	.getsockopt	   = dccp_getsockopt,
-	.sendmsg	   = dccp_sendmsg,
-	.recvmsg	   = dccp_recvmsg,
-	.backlog_rcv	   = dccp_v6_do_rcv,
-	.hash		   = inet6_hash,
-	.unhash		   = inet_unhash,
-	.accept		   = inet_csk_accept,
-	.get_port	   = inet_csk_get_port,
-	.shutdown	   = dccp_shutdown,
-	.destroy	   = dccp_destroy_sock,
-	.orphan_count	   = &dccp_orphan_count,
-	.max_header	   = MAX_DCCP_HEADER,
-	.obj_size	   = sizeof(struct dccp6_sock),
-	.ipv6_pinfo_offset = offsetof(struct dccp6_sock, inet6),
-	.slab_flags	   = SLAB_TYPESAFE_BY_RCU,
-	.rsk_prot	   = &dccp6_request_sock_ops,
-	.twsk_prot	   = &dccp6_timewait_sock_ops,
-	.h.hashinfo	   = &dccp_hashinfo,
-};
-
-static const struct inet6_protocol dccp_v6_protocol = {
-	.handler	= dccp_v6_rcv,
-	.err_handler	= dccp_v6_err,
-	.flags		= INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL,
-};
-
-static const struct proto_ops inet6_dccp_ops = {
-	.family		   = PF_INET6,
-	.owner		   = THIS_MODULE,
-	.release	   = inet6_release,
-	.bind		   = inet6_bind,
-	.connect	   = inet_stream_connect,
-	.socketpair	   = sock_no_socketpair,
-	.accept		   = inet_accept,
-	.getname	   = inet6_getname,
-	.poll		   = dccp_poll,
-	.ioctl		   = inet6_ioctl,
-	.gettstamp	   = sock_gettstamp,
-	.listen		   = inet_dccp_listen,
-	.shutdown	   = inet_shutdown,
-	.setsockopt	   = sock_common_setsockopt,
-	.getsockopt	   = sock_common_getsockopt,
-	.sendmsg	   = inet_sendmsg,
-	.recvmsg	   = sock_common_recvmsg,
-	.mmap		   = sock_no_mmap,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	   = inet6_compat_ioctl,
-#endif
-};
-
-static struct inet_protosw dccp_v6_protosw = {
-	.type		= SOCK_DCCP,
-	.protocol	= IPPROTO_DCCP,
-	.prot		= &dccp_v6_prot,
-	.ops		= &inet6_dccp_ops,
-	.flags		= INET_PROTOSW_ICSK,
-};
-
-static int __net_init dccp_v6_init_net(struct net *net)
-{
-	struct dccp_v6_pernet *pn = net_generic(net, dccp_v6_pernet_id);
-
-	if (dccp_hashinfo.bhash == NULL)
-		return -ESOCKTNOSUPPORT;
-
-	return inet_ctl_sock_create(&pn->v6_ctl_sk, PF_INET6,
-				    SOCK_DCCP, IPPROTO_DCCP, net);
-}
-
-static void __net_exit dccp_v6_exit_net(struct net *net)
-{
-	struct dccp_v6_pernet *pn = net_generic(net, dccp_v6_pernet_id);
-
-	inet_ctl_sock_destroy(pn->v6_ctl_sk);
-}
-
-static struct pernet_operations dccp_v6_ops = {
-	.init   = dccp_v6_init_net,
-	.exit   = dccp_v6_exit_net,
-	.id	= &dccp_v6_pernet_id,
-	.size   = sizeof(struct dccp_v6_pernet),
-};
-
-static int __init dccp_v6_init(void)
-{
-	int err = proto_register(&dccp_v6_prot, 1);
-
-	if (err)
-		goto out;
-
-	inet6_register_protosw(&dccp_v6_protosw);
-
-	err = register_pernet_subsys(&dccp_v6_ops);
-	if (err)
-		goto out_destroy_ctl_sock;
-
-	err = inet6_add_protocol(&dccp_v6_protocol, IPPROTO_DCCP);
-	if (err)
-		goto out_unregister_proto;
-
-out:
-	return err;
-out_unregister_proto:
-	unregister_pernet_subsys(&dccp_v6_ops);
-out_destroy_ctl_sock:
-	inet6_unregister_protosw(&dccp_v6_protosw);
-	proto_unregister(&dccp_v6_prot);
-	goto out;
-}
-
-static void __exit dccp_v6_exit(void)
-{
-	inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP);
-	unregister_pernet_subsys(&dccp_v6_ops);
-	inet6_unregister_protosw(&dccp_v6_protosw);
-	proto_unregister(&dccp_v6_prot);
-}
-
-module_init(dccp_v6_init);
-module_exit(dccp_v6_exit);
-
-/*
- * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33)
- * values directly, Also cover the case where the protocol is not specified,
- * i.e. net-pf-PF_INET6-proto-0-type-SOCK_DCCP
- */
-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 33, 6);
-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 0, 6);
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>");
-MODULE_DESCRIPTION("DCCPv6 - Datagram Congestion Controlled Protocol");
diff --git a/net/dccp/ipv6.h b/net/dccp/ipv6.h
deleted file mode 100644
index c5d14c48def1..000000000000
--- a/net/dccp/ipv6.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-#ifndef _DCCP_IPV6_H
-#define _DCCP_IPV6_H
-/*
- *  net/dccp/ipv6.h
- *
- *  An implementation of the DCCP protocol
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
- */
-
-#include <linux/dccp.h>
-#include <linux/ipv6.h>
-
-struct dccp6_sock {
-	struct dccp_sock  dccp;
-	struct ipv6_pinfo inet6;
-};
-
-struct dccp6_request_sock {
-	struct dccp_request_sock  dccp;
-};
-
-struct dccp6_timewait_sock {
-	struct inet_timewait_sock   inet;
-};
-
-#endif /* _DCCP_IPV6_H */
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
deleted file mode 100644
index fecc8190064f..000000000000
--- a/net/dccp/minisocks.c
+++ /dev/null
@@ -1,266 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  net/dccp/minisocks.c
- *
- *  An implementation of the DCCP protocol
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-
-#include <linux/dccp.h>
-#include <linux/gfp.h>
-#include <linux/kernel.h>
-#include <linux/skbuff.h>
-#include <linux/timer.h>
-
-#include <net/sock.h>
-#include <net/xfrm.h>
-#include <net/inet_timewait_sock.h>
-#include <net/rstreason.h>
-
-#include "ackvec.h"
-#include "ccid.h"
-#include "dccp.h"
-#include "feat.h"
-
-struct inet_timewait_death_row dccp_death_row = {
-	.tw_refcount = REFCOUNT_INIT(1),
-	.sysctl_max_tw_buckets = NR_FILE * 2,
-	.hashinfo	= &dccp_hashinfo,
-};
-
-EXPORT_SYMBOL_GPL(dccp_death_row);
-
-void dccp_time_wait(struct sock *sk, int state, int timeo)
-{
-	struct inet_timewait_sock *tw;
-
-	tw = inet_twsk_alloc(sk, &dccp_death_row, state);
-
-	if (tw != NULL) {
-		const struct inet_connection_sock *icsk = inet_csk(sk);
-		const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
-#if IS_ENABLED(CONFIG_IPV6)
-		if (tw->tw_family == PF_INET6) {
-			tw->tw_v6_daddr = sk->sk_v6_daddr;
-			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
-			tw->tw_ipv6only = sk->sk_ipv6only;
-		}
-#endif
-
-		/* Get the TIME_WAIT timeout firing. */
-		if (timeo < rto)
-			timeo = rto;
-
-		if (state == DCCP_TIME_WAIT)
-			timeo = DCCP_TIMEWAIT_LEN;
-
-		/* Linkage updates.
-		 * Note that access to tw after this point is illegal.
-		 */
-		inet_twsk_hashdance_schedule(tw, sk, &dccp_hashinfo, timeo);
-	} else {
-		/* Sorry, if we're out of memory, just CLOSE this
-		 * socket up.  We've got bigger problems than
-		 * non-graceful socket closings.
-		 */
-		DCCP_WARN("time wait bucket table overflow\n");
-	}
-
-	dccp_done(sk);
-}
-
-struct sock *dccp_create_openreq_child(const struct sock *sk,
-				       const struct request_sock *req,
-				       const struct sk_buff *skb)
-{
-	/*
-	 * Step 3: Process LISTEN state
-	 *
-	 *   (* Generate a new socket and switch to that socket *)
-	 *   Set S := new socket for this port pair
-	 */
-	struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
-
-	if (newsk != NULL) {
-		struct dccp_request_sock *dreq = dccp_rsk(req);
-		struct inet_connection_sock *newicsk = inet_csk(newsk);
-		struct dccp_sock *newdp = dccp_sk(newsk);
-
-		newdp->dccps_role	    = DCCP_ROLE_SERVER;
-		newdp->dccps_hc_rx_ackvec   = NULL;
-		newdp->dccps_service_list   = NULL;
-		newdp->dccps_hc_rx_ccid     = NULL;
-		newdp->dccps_hc_tx_ccid     = NULL;
-		newdp->dccps_service	    = dreq->dreq_service;
-		newdp->dccps_timestamp_echo = dreq->dreq_timestamp_echo;
-		newdp->dccps_timestamp_time = dreq->dreq_timestamp_time;
-		newicsk->icsk_rto	    = DCCP_TIMEOUT_INIT;
-
-		INIT_LIST_HEAD(&newdp->dccps_featneg);
-		/*
-		 * Step 3: Process LISTEN state
-		 *
-		 *    Choose S.ISS (initial seqno) or set from Init Cookies
-		 *    Initialize S.GAR := S.ISS
-		 *    Set S.ISR, S.GSR from packet (or Init Cookies)
-		 *
-		 *    Setting AWL/AWH and SWL/SWH happens as part of the feature
-		 *    activation below, as these windows all depend on the local
-		 *    and remote Sequence Window feature values (7.5.2).
-		 */
-		newdp->dccps_iss = dreq->dreq_iss;
-		newdp->dccps_gss = dreq->dreq_gss;
-		newdp->dccps_gar = newdp->dccps_iss;
-		newdp->dccps_isr = dreq->dreq_isr;
-		newdp->dccps_gsr = dreq->dreq_gsr;
-
-		/*
-		 * Activate features: initialise CCIDs, sequence windows etc.
-		 */
-		if (dccp_feat_activate_values(newsk, &dreq->dreq_featneg)) {
-			sk_free_unlock_clone(newsk);
-			return NULL;
-		}
-		dccp_init_xmit_timers(newsk);
-
-		__DCCP_INC_STATS(DCCP_MIB_PASSIVEOPENS);
-	}
-	return newsk;
-}
-
-EXPORT_SYMBOL_GPL(dccp_create_openreq_child);
-
-/*
- * Process an incoming packet for RESPOND sockets represented
- * as an request_sock.
- */
-struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
-			    struct request_sock *req)
-{
-	struct sock *child = NULL;
-	struct dccp_request_sock *dreq = dccp_rsk(req);
-	bool own_req;
-
-	/* TCP/DCCP listeners became lockless.
-	 * DCCP stores complex state in its request_sock, so we need
-	 * a protection for them, now this code runs without being protected
-	 * by the parent (listener) lock.
-	 */
-	spin_lock_bh(&dreq->dreq_lock);
-
-	/* Check for retransmitted REQUEST */
-	if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
-
-		if (after48(DCCP_SKB_CB(skb)->dccpd_seq, dreq->dreq_gsr)) {
-			dccp_pr_debug("Retransmitted REQUEST\n");
-			dreq->dreq_gsr = DCCP_SKB_CB(skb)->dccpd_seq;
-			/*
-			 * Send another RESPONSE packet
-			 * To protect against Request floods, increment retrans
-			 * counter (backoff, monitored by dccp_response_timer).
-			 */
-			inet_rtx_syn_ack(sk, req);
-		}
-		/* Network Duplicate, discard packet */
-		goto out;
-	}
-
-	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
-
-	if (dccp_hdr(skb)->dccph_type != DCCP_PKT_ACK &&
-	    dccp_hdr(skb)->dccph_type != DCCP_PKT_DATAACK)
-		goto drop;
-
-	/* Invalid ACK */
-	if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
-				dreq->dreq_iss, dreq->dreq_gss)) {
-		dccp_pr_debug("Invalid ACK number: ack_seq=%llu, "
-			      "dreq_iss=%llu, dreq_gss=%llu\n",
-			      (unsigned long long)
-			      DCCP_SKB_CB(skb)->dccpd_ack_seq,
-			      (unsigned long long) dreq->dreq_iss,
-			      (unsigned long long) dreq->dreq_gss);
-		goto drop;
-	}
-
-	if (dccp_parse_options(sk, dreq, skb))
-		 goto drop;
-
-	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
-							 req, &own_req);
-	if (child) {
-		child = inet_csk_complete_hashdance(sk, child, req, own_req);
-		goto out;
-	}
-
-	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
-drop:
-	if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
-		req->rsk_ops->send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED);
-
-	inet_csk_reqsk_queue_drop(sk, req);
-out:
-	spin_unlock_bh(&dreq->dreq_lock);
-	return child;
-}
-
-EXPORT_SYMBOL_GPL(dccp_check_req);
-
-/*
- *  Queue segment on the new socket if the new socket is active,
- *  otherwise we just shortcircuit this and continue with
- *  the new socket.
- */
-int dccp_child_process(struct sock *parent, struct sock *child,
-		       struct sk_buff *skb)
-	__releases(child)
-{
-	int ret = 0;
-	const int state = child->sk_state;
-
-	if (!sock_owned_by_user(child)) {
-		ret = dccp_rcv_state_process(child, skb, dccp_hdr(skb),
-					     skb->len);
-
-		/* Wakeup parent, send SIGIO */
-		if (state == DCCP_RESPOND && child->sk_state != state)
-			parent->sk_data_ready(parent);
-	} else {
-		/* Alas, it is possible again, because we do lookup
-		 * in main socket hash table and lock on listening
-		 * socket does not protect us more.
-		 */
-		__sk_add_backlog(child, skb);
-	}
-
-	bh_unlock_sock(child);
-	sock_put(child);
-	return ret;
-}
-
-EXPORT_SYMBOL_GPL(dccp_child_process);
-
-void dccp_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
-			 struct request_sock *rsk)
-{
-	DCCP_BUG("DCCP-ACK packets are never sent in LISTEN/RESPOND state");
-}
-
-EXPORT_SYMBOL_GPL(dccp_reqsk_send_ack);
-
-int dccp_reqsk_init(struct request_sock *req,
-		    struct dccp_sock const *dp, struct sk_buff const *skb)
-{
-	struct dccp_request_sock *dreq = dccp_rsk(req);
-
-	spin_lock_init(&dreq->dreq_lock);
-	inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
-	inet_rsk(req)->ir_num	   = ntohs(dccp_hdr(skb)->dccph_dport);
-	inet_rsk(req)->acked	   = 0;
-	dreq->dreq_timestamp_echo  = 0;
-
-	/* inherit feature negotiation options from listening socket */
-	return dccp_feat_clone_list(&dp->dccps_featneg, &dreq->dreq_featneg);
-}
-
-EXPORT_SYMBOL_GPL(dccp_reqsk_init);
diff --git a/net/dccp/options.c b/net/dccp/options.c
deleted file mode 100644
index db62d4767024..000000000000
--- a/net/dccp/options.c
+++ /dev/null
@@ -1,609 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  net/dccp/options.c
- *
- *  An implementation of the DCCP protocol
- *  Copyright (c) 2005 Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org>
- *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
- *  Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz>
- */
-#include <linux/dccp.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/unaligned.h>
-#include <linux/kernel.h>
-#include <linux/skbuff.h>
-
-#include "ackvec.h"
-#include "ccid.h"
-#include "dccp.h"
-#include "feat.h"
-
-u64 dccp_decode_value_var(const u8 *bf, const u8 len)
-{
-	u64 value = 0;
-
-	if (len >= DCCP_OPTVAL_MAXLEN)
-		value += ((u64)*bf++) << 40;
-	if (len > 4)
-		value += ((u64)*bf++) << 32;
-	if (len > 3)
-		value += ((u64)*bf++) << 24;
-	if (len > 2)
-		value += ((u64)*bf++) << 16;
-	if (len > 1)
-		value += ((u64)*bf++) << 8;
-	if (len > 0)
-		value += *bf;
-
-	return value;
-}
-
-/**
- * dccp_parse_options  -  Parse DCCP options present in @skb
- * @sk: client|server|listening dccp socket (when @dreq != NULL)
- * @dreq: request socket to use during connection setup, or NULL
- * @skb: frame to parse
- */
-int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
-		       struct sk_buff *skb)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	const struct dccp_hdr *dh = dccp_hdr(skb);
-	const u8 pkt_type = DCCP_SKB_CB(skb)->dccpd_type;
-	unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb);
-	unsigned char *opt_ptr = options;
-	const unsigned char *opt_end = (unsigned char *)dh +
-					(dh->dccph_doff * 4);
-	struct dccp_options_received *opt_recv = &dp->dccps_options_received;
-	unsigned char opt, len;
-	unsigned char *value;
-	u32 elapsed_time;
-	__be32 opt_val;
-	int rc;
-	int mandatory = 0;
-
-	memset(opt_recv, 0, sizeof(*opt_recv));
-
-	opt = len = 0;
-	while (opt_ptr != opt_end) {
-		opt   = *opt_ptr++;
-		len   = 0;
-		value = NULL;
-
-		/* Check if this isn't a single byte option */
-		if (opt > DCCPO_MAX_RESERVED) {
-			if (opt_ptr == opt_end)
-				goto out_nonsensical_length;
-
-			len = *opt_ptr++;
-			if (len < 2)
-				goto out_nonsensical_length;
-			/*
-			 * Remove the type and len fields, leaving
-			 * just the value size
-			 */
-			len	-= 2;
-			value	= opt_ptr;
-			opt_ptr += len;
-
-			if (opt_ptr > opt_end)
-				goto out_nonsensical_length;
-		}
-
-		/*
-		 * CCID-specific options are ignored during connection setup, as
-		 * negotiation may still be in progress (see RFC 4340, 10.3).
-		 * The same applies to Ack Vectors, as these depend on the CCID.
-		 */
-		if (dreq != NULL && (opt >= DCCPO_MIN_RX_CCID_SPECIFIC ||
-		    opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1))
-			goto ignore_option;
-
-		switch (opt) {
-		case DCCPO_PADDING:
-			break;
-		case DCCPO_MANDATORY:
-			if (mandatory)
-				goto out_invalid_option;
-			if (pkt_type != DCCP_PKT_DATA)
-				mandatory = 1;
-			break;
-		case DCCPO_NDP_COUNT:
-			if (len > 6)
-				goto out_invalid_option;
-
-			opt_recv->dccpor_ndp = dccp_decode_value_var(value, len);
-			dccp_pr_debug("%s opt: NDP count=%llu\n", dccp_role(sk),
-				      (unsigned long long)opt_recv->dccpor_ndp);
-			break;
-		case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R:
-			if (pkt_type == DCCP_PKT_DATA)      /* RFC 4340, 6 */
-				break;
-			if (len == 0)
-				goto out_invalid_option;
-			rc = dccp_feat_parse_options(sk, dreq, mandatory, opt,
-						    *value, value + 1, len - 1);
-			if (rc)
-				goto out_featneg_failed;
-			break;
-		case DCCPO_TIMESTAMP:
-			if (len != 4)
-				goto out_invalid_option;
-			/*
-			 * RFC 4340 13.1: "The precise time corresponding to
-			 * Timestamp Value zero is not specified". We use
-			 * zero to indicate absence of a meaningful timestamp.
-			 */
-			opt_val = get_unaligned((__be32 *)value);
-			if (unlikely(opt_val == 0)) {
-				DCCP_WARN("Timestamp with zero value\n");
-				break;
-			}
-
-			if (dreq != NULL) {
-				dreq->dreq_timestamp_echo = ntohl(opt_val);
-				dreq->dreq_timestamp_time = dccp_timestamp();
-			} else {
-				opt_recv->dccpor_timestamp =
-					dp->dccps_timestamp_echo = ntohl(opt_val);
-				dp->dccps_timestamp_time = dccp_timestamp();
-			}
-			dccp_pr_debug("%s rx opt: TIMESTAMP=%u, ackno=%llu\n",
-				      dccp_role(sk), ntohl(opt_val),
-				      (unsigned long long)
-				      DCCP_SKB_CB(skb)->dccpd_ack_seq);
-			/* schedule an Ack in case this sender is quiescent */
-			inet_csk_schedule_ack(sk);
-			break;
-		case DCCPO_TIMESTAMP_ECHO:
-			if (len != 4 && len != 6 && len != 8)
-				goto out_invalid_option;
-
-			opt_val = get_unaligned((__be32 *)value);
-			opt_recv->dccpor_timestamp_echo = ntohl(opt_val);
-
-			dccp_pr_debug("%s rx opt: TIMESTAMP_ECHO=%u, len=%d, "
-				      "ackno=%llu", dccp_role(sk),
-				      opt_recv->dccpor_timestamp_echo,
-				      len + 2,
-				      (unsigned long long)
-				      DCCP_SKB_CB(skb)->dccpd_ack_seq);
-
-			value += 4;
-
-			if (len == 4) {		/* no elapsed time included */
-				dccp_pr_debug_cat("\n");
-				break;
-			}
-
-			if (len == 6) {		/* 2-byte elapsed time */
-				__be16 opt_val2 = get_unaligned((__be16 *)value);
-				elapsed_time = ntohs(opt_val2);
-			} else {		/* 4-byte elapsed time */
-				opt_val = get_unaligned((__be32 *)value);
-				elapsed_time = ntohl(opt_val);
-			}
-
-			dccp_pr_debug_cat(", ELAPSED_TIME=%u\n", elapsed_time);
-
-			/* Give precedence to the biggest ELAPSED_TIME */
-			if (elapsed_time > opt_recv->dccpor_elapsed_time)
-				opt_recv->dccpor_elapsed_time = elapsed_time;
-			break;
-		case DCCPO_ELAPSED_TIME:
-			if (dccp_packet_without_ack(skb))   /* RFC 4340, 13.2 */
-				break;
-
-			if (len == 2) {
-				__be16 opt_val2 = get_unaligned((__be16 *)value);
-				elapsed_time = ntohs(opt_val2);
-			} else if (len == 4) {
-				opt_val = get_unaligned((__be32 *)value);
-				elapsed_time = ntohl(opt_val);
-			} else {
-				goto out_invalid_option;
-			}
-
-			if (elapsed_time > opt_recv->dccpor_elapsed_time)
-				opt_recv->dccpor_elapsed_time = elapsed_time;
-
-			dccp_pr_debug("%s rx opt: ELAPSED_TIME=%d\n",
-				      dccp_role(sk), elapsed_time);
-			break;
-		case DCCPO_MIN_RX_CCID_SPECIFIC ... DCCPO_MAX_RX_CCID_SPECIFIC:
-			if (ccid_hc_rx_parse_options(dp->dccps_hc_rx_ccid, sk,
-						     pkt_type, opt, value, len))
-				goto out_invalid_option;
-			break;
-		case DCCPO_ACK_VECTOR_0:
-		case DCCPO_ACK_VECTOR_1:
-			if (dccp_packet_without_ack(skb))   /* RFC 4340, 11.4 */
-				break;
-			/*
-			 * Ack vectors are processed by the TX CCID if it is
-			 * interested. The RX CCID need not parse Ack Vectors,
-			 * since it is only interested in clearing old state.
-			 */
-			fallthrough;
-		case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC:
-			if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk,
-						     pkt_type, opt, value, len))
-				goto out_invalid_option;
-			break;
-		default:
-			DCCP_CRIT("DCCP(%p): option %d(len=%d) not "
-				  "implemented, ignoring", sk, opt, len);
-			break;
-		}
-ignore_option:
-		if (opt != DCCPO_MANDATORY)
-			mandatory = 0;
-	}
-
-	/* mandatory was the last byte in option list -> reset connection */
-	if (mandatory)
-		goto out_invalid_option;
-
-out_nonsensical_length:
-	/* RFC 4340, 5.8: ignore option and all remaining option space */
-	return 0;
-
-out_invalid_option:
-	DCCP_INC_STATS(DCCP_MIB_INVALIDOPT);
-	rc = DCCP_RESET_CODE_OPTION_ERROR;
-out_featneg_failed:
-	DCCP_WARN("DCCP(%p): Option %d (len=%d) error=%u\n", sk, opt, len, rc);
-	DCCP_SKB_CB(skb)->dccpd_reset_code = rc;
-	DCCP_SKB_CB(skb)->dccpd_reset_data[0] = opt;
-	DCCP_SKB_CB(skb)->dccpd_reset_data[1] = len > 0 ? value[0] : 0;
-	DCCP_SKB_CB(skb)->dccpd_reset_data[2] = len > 1 ? value[1] : 0;
-	return -1;
-}
-
-EXPORT_SYMBOL_GPL(dccp_parse_options);
-
-void dccp_encode_value_var(const u64 value, u8 *to, const u8 len)
-{
-	if (len >= DCCP_OPTVAL_MAXLEN)
-		*to++ = (value & 0xFF0000000000ull) >> 40;
-	if (len > 4)
-		*to++ = (value & 0xFF00000000ull) >> 32;
-	if (len > 3)
-		*to++ = (value & 0xFF000000) >> 24;
-	if (len > 2)
-		*to++ = (value & 0xFF0000) >> 16;
-	if (len > 1)
-		*to++ = (value & 0xFF00) >> 8;
-	if (len > 0)
-		*to++ = (value & 0xFF);
-}
-
-static inline u8 dccp_ndp_len(const u64 ndp)
-{
-	if (likely(ndp <= 0xFF))
-		return 1;
-	return likely(ndp <= USHRT_MAX) ? 2 : (ndp <= UINT_MAX ? 4 : 6);
-}
-
-int dccp_insert_option(struct sk_buff *skb, const unsigned char option,
-		       const void *value, const unsigned char len)
-{
-	unsigned char *to;
-
-	if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 2 > DCCP_MAX_OPT_LEN)
-		return -1;
-
-	DCCP_SKB_CB(skb)->dccpd_opt_len += len + 2;
-
-	to    = skb_push(skb, len + 2);
-	*to++ = option;
-	*to++ = len + 2;
-
-	memcpy(to, value, len);
-	return 0;
-}
-
-EXPORT_SYMBOL_GPL(dccp_insert_option);
-
-static int dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	u64 ndp = dp->dccps_ndp_count;
-
-	if (dccp_non_data_packet(skb))
-		++dp->dccps_ndp_count;
-	else
-		dp->dccps_ndp_count = 0;
-
-	if (ndp > 0) {
-		unsigned char *ptr;
-		const int ndp_len = dccp_ndp_len(ndp);
-		const int len = ndp_len + 2;
-
-		if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN)
-			return -1;
-
-		DCCP_SKB_CB(skb)->dccpd_opt_len += len;
-
-		ptr = skb_push(skb, len);
-		*ptr++ = DCCPO_NDP_COUNT;
-		*ptr++ = len;
-		dccp_encode_value_var(ndp, ptr, ndp_len);
-	}
-
-	return 0;
-}
-
-static inline int dccp_elapsed_time_len(const u32 elapsed_time)
-{
-	return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4;
-}
-
-static int dccp_insert_option_timestamp(struct sk_buff *skb)
-{
-	__be32 now = htonl(dccp_timestamp());
-	/* yes this will overflow but that is the point as we want a
-	 * 10 usec 32 bit timer which mean it wraps every 11.9 hours */
-
-	return dccp_insert_option(skb, DCCPO_TIMESTAMP, &now, sizeof(now));
-}
-
-static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp,
-					     struct dccp_request_sock *dreq,
-					     struct sk_buff *skb)
-{
-	__be32 tstamp_echo;
-	unsigned char *to;
-	u32 elapsed_time, elapsed_time_len, len;
-
-	if (dreq != NULL) {
-		elapsed_time = dccp_timestamp() - dreq->dreq_timestamp_time;
-		tstamp_echo  = htonl(dreq->dreq_timestamp_echo);
-		dreq->dreq_timestamp_echo = 0;
-	} else {
-		elapsed_time = dccp_timestamp() - dp->dccps_timestamp_time;
-		tstamp_echo  = htonl(dp->dccps_timestamp_echo);
-		dp->dccps_timestamp_echo = 0;
-	}
-
-	elapsed_time_len = dccp_elapsed_time_len(elapsed_time);
-	len = 6 + elapsed_time_len;
-
-	if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN)
-		return -1;
-
-	DCCP_SKB_CB(skb)->dccpd_opt_len += len;
-
-	to    = skb_push(skb, len);
-	*to++ = DCCPO_TIMESTAMP_ECHO;
-	*to++ = len;
-
-	memcpy(to, &tstamp_echo, 4);
-	to += 4;
-
-	if (elapsed_time_len == 2) {
-		const __be16 var16 = htons((u16)elapsed_time);
-		memcpy(to, &var16, 2);
-	} else if (elapsed_time_len == 4) {
-		const __be32 var32 = htonl(elapsed_time);
-		memcpy(to, &var32, 4);
-	}
-
-	return 0;
-}
-
-static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec;
-	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
-	const u16 buflen = dccp_ackvec_buflen(av);
-	/* Figure out how many options do we need to represent the ackvec */
-	const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN);
-	u16 len = buflen + 2 * nr_opts;
-	u8 i, nonce = 0;
-	const unsigned char *tail, *from;
-	unsigned char *to;
-
-	if (dcb->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) {
-		DCCP_WARN("Lacking space for %u bytes on %s packet\n", len,
-			  dccp_packet_name(dcb->dccpd_type));
-		return -1;
-	}
-	/*
-	 * Since Ack Vectors are variable-length, we can not always predict
-	 * their size. To catch exception cases where the space is running out
-	 * on the skb, a separate Sync is scheduled to carry the Ack Vector.
-	 */
-	if (len > DCCPAV_MIN_OPTLEN &&
-	    len + dcb->dccpd_opt_len + skb->len > dp->dccps_mss_cache) {
-		DCCP_WARN("No space left for Ack Vector (%u) on skb (%u+%u), "
-			  "MPS=%u ==> reduce payload size?\n", len, skb->len,
-			  dcb->dccpd_opt_len, dp->dccps_mss_cache);
-		dp->dccps_sync_scheduled = 1;
-		return 0;
-	}
-	dcb->dccpd_opt_len += len;
-
-	to   = skb_push(skb, len);
-	len  = buflen;
-	from = av->av_buf + av->av_buf_head;
-	tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN;
-
-	for (i = 0; i < nr_opts; ++i) {
-		int copylen = len;
-
-		if (len > DCCP_SINGLE_OPT_MAXLEN)
-			copylen = DCCP_SINGLE_OPT_MAXLEN;
-
-		/*
-		 * RFC 4340, 12.2: Encode the Nonce Echo for this Ack Vector via
-		 * its type; ack_nonce is the sum of all individual buf_nonce's.
-		 */
-		nonce ^= av->av_buf_nonce[i];
-
-		*to++ = DCCPO_ACK_VECTOR_0 + av->av_buf_nonce[i];
-		*to++ = copylen + 2;
-
-		/* Check if buf_head wraps */
-		if (from + copylen > tail) {
-			const u16 tailsize = tail - from;
-
-			memcpy(to, from, tailsize);
-			to	+= tailsize;
-			len	-= tailsize;
-			copylen	-= tailsize;
-			from	= av->av_buf;
-		}
-
-		memcpy(to, from, copylen);
-		from += copylen;
-		to   += copylen;
-		len  -= copylen;
-	}
-	/*
-	 * Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340.
-	 */
-	if (dccp_ackvec_update_records(av, dcb->dccpd_seq, nonce))
-		return -ENOBUFS;
-	return 0;
-}
-
-/**
- * dccp_insert_option_mandatory  -  Mandatory option (5.8.2)
- * @skb: frame into which to insert option
- *
- * Note that since we are using skb_push, this function needs to be called
- * _after_ inserting the option it is supposed to influence (stack order).
- */
-int dccp_insert_option_mandatory(struct sk_buff *skb)
-{
-	if (DCCP_SKB_CB(skb)->dccpd_opt_len >= DCCP_MAX_OPT_LEN)
-		return -1;
-
-	DCCP_SKB_CB(skb)->dccpd_opt_len++;
-	*(u8 *)skb_push(skb, 1) = DCCPO_MANDATORY;
-	return 0;
-}
-
-/**
- * dccp_insert_fn_opt  -  Insert single Feature-Negotiation option into @skb
- * @skb: frame to insert feature negotiation option into
- * @type: %DCCPO_CHANGE_L, %DCCPO_CHANGE_R, %DCCPO_CONFIRM_L, %DCCPO_CONFIRM_R
- * @feat: one out of %dccp_feature_numbers
- * @val: NN value or SP array (preferred element first) to copy
- * @len: true length of @val in bytes (excluding first element repetition)
- * @repeat_first: whether to copy the first element of @val twice
- *
- * The last argument is used to construct Confirm options, where the preferred
- * value and the preference list appear separately (RFC 4340, 6.3.1). Preference
- * lists are kept such that the preferred entry is always first, so we only need
- * to copy twice, and avoid the overhead of cloning into a bigger array.
- */
-int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat,
-		       u8 *val, u8 len, bool repeat_first)
-{
-	u8 tot_len, *to;
-
-	/* take the `Feature' field and possible repetition into account */
-	if (len > (DCCP_SINGLE_OPT_MAXLEN - 2)) {
-		DCCP_WARN("length %u for feature %u too large\n", len, feat);
-		return -1;
-	}
-
-	if (unlikely(val == NULL || len == 0))
-		len = repeat_first = false;
-	tot_len = 3 + repeat_first + len;
-
-	if (DCCP_SKB_CB(skb)->dccpd_opt_len + tot_len > DCCP_MAX_OPT_LEN) {
-		DCCP_WARN("packet too small for feature %d option!\n", feat);
-		return -1;
-	}
-	DCCP_SKB_CB(skb)->dccpd_opt_len += tot_len;
-
-	to    = skb_push(skb, tot_len);
-	*to++ = type;
-	*to++ = tot_len;
-	*to++ = feat;
-
-	if (repeat_first)
-		*to++ = *val;
-	if (len)
-		memcpy(to, val, len);
-	return 0;
-}
-
-/* The length of all options needs to be a multiple of 4 (5.8) */
-static void dccp_insert_option_padding(struct sk_buff *skb)
-{
-	int padding = DCCP_SKB_CB(skb)->dccpd_opt_len % 4;
-
-	if (padding != 0) {
-		padding = 4 - padding;
-		memset(skb_push(skb, padding), 0, padding);
-		DCCP_SKB_CB(skb)->dccpd_opt_len += padding;
-	}
-}
-
-int dccp_insert_options(struct sock *sk, struct sk_buff *skb)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-
-	DCCP_SKB_CB(skb)->dccpd_opt_len = 0;
-
-	if (dp->dccps_send_ndp_count && dccp_insert_option_ndp(sk, skb))
-		return -1;
-
-	if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA) {
-
-		/* Feature Negotiation */
-		if (dccp_feat_insert_opts(dp, NULL, skb))
-			return -1;
-
-		if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_REQUEST) {
-			/*
-			 * Obtain RTT sample from Request/Response exchange.
-			 * This is currently used for TFRC initialisation.
-			 */
-			if (dccp_insert_option_timestamp(skb))
-				return -1;
-
-		} else if (dccp_ackvec_pending(sk) &&
-			   dccp_insert_option_ackvec(sk, skb)) {
-				return -1;
-		}
-	}
-
-	if (dp->dccps_hc_rx_insert_options) {
-		if (ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb))
-			return -1;
-		dp->dccps_hc_rx_insert_options = 0;
-	}
-
-	if (dp->dccps_timestamp_echo != 0 &&
-	    dccp_insert_option_timestamp_echo(dp, NULL, skb))
-		return -1;
-
-	dccp_insert_option_padding(skb);
-	return 0;
-}
-
-int dccp_insert_options_rsk(struct dccp_request_sock *dreq, struct sk_buff *skb)
-{
-	DCCP_SKB_CB(skb)->dccpd_opt_len = 0;
-
-	if (dccp_feat_insert_opts(NULL, dreq, skb))
-		return -1;
-
-	/* Obtain RTT sample from Response/Ack exchange (used by TFRC). */
-	if (dccp_insert_option_timestamp(skb))
-		return -1;
-
-	if (dreq->dreq_timestamp_echo != 0 &&
-	    dccp_insert_option_timestamp_echo(NULL, dreq, skb))
-		return -1;
-
-	dccp_insert_option_padding(skb);
-	return 0;
-}
diff --git a/net/dccp/output.c b/net/dccp/output.c
deleted file mode 100644
index 39cf3430177a..000000000000
--- a/net/dccp/output.c
+++ /dev/null
@@ -1,708 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  net/dccp/output.c
- *
- *  An implementation of the DCCP protocol
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-
-#include <linux/dccp.h>
-#include <linux/kernel.h>
-#include <linux/skbuff.h>
-#include <linux/slab.h>
-#include <linux/sched/signal.h>
-
-#include <net/inet_sock.h>
-#include <net/sock.h>
-
-#include "ackvec.h"
-#include "ccid.h"
-#include "dccp.h"
-
-static inline void dccp_event_ack_sent(struct sock *sk)
-{
-	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
-}
-
-/* enqueue @skb on sk_send_head for retransmission, return clone to send now */
-static struct sk_buff *dccp_skb_entail(struct sock *sk, struct sk_buff *skb)
-{
-	skb_set_owner_w(skb, sk);
-	WARN_ON(sk->sk_send_head);
-	sk->sk_send_head = skb;
-	return skb_clone(sk->sk_send_head, gfp_any());
-}
-
-/*
- * All SKB's seen here are completely headerless. It is our
- * job to build the DCCP header, and pass the packet down to
- * IP so it can do the same plus pass the packet off to the
- * device.
- */
-static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
-{
-	if (likely(skb != NULL)) {
-		struct inet_sock *inet = inet_sk(sk);
-		const struct inet_connection_sock *icsk = inet_csk(sk);
-		struct dccp_sock *dp = dccp_sk(sk);
-		struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
-		struct dccp_hdr *dh;
-		/* XXX For now we're using only 48 bits sequence numbers */
-		const u32 dccp_header_size = sizeof(*dh) +
-					     sizeof(struct dccp_hdr_ext) +
-					  dccp_packet_hdr_len(dcb->dccpd_type);
-		int err, set_ack = 1;
-		u64 ackno = dp->dccps_gsr;
-		/*
-		 * Increment GSS here already in case the option code needs it.
-		 * Update GSS for real only if option processing below succeeds.
-		 */
-		dcb->dccpd_seq = ADD48(dp->dccps_gss, 1);
-
-		switch (dcb->dccpd_type) {
-		case DCCP_PKT_DATA:
-			set_ack = 0;
-			fallthrough;
-		case DCCP_PKT_DATAACK:
-		case DCCP_PKT_RESET:
-			break;
-
-		case DCCP_PKT_REQUEST:
-			set_ack = 0;
-			/* Use ISS on the first (non-retransmitted) Request. */
-			if (icsk->icsk_retransmits == 0)
-				dcb->dccpd_seq = dp->dccps_iss;
-			fallthrough;
-
-		case DCCP_PKT_SYNC:
-		case DCCP_PKT_SYNCACK:
-			ackno = dcb->dccpd_ack_seq;
-			fallthrough;
-		default:
-			/*
-			 * Set owner/destructor: some skbs are allocated via
-			 * alloc_skb (e.g. when retransmission may happen).
-			 * Only Data, DataAck, and Reset packets should come
-			 * through here with skb->sk set.
-			 */
-			WARN_ON(skb->sk);
-			skb_set_owner_w(skb, sk);
-			break;
-		}
-
-		if (dccp_insert_options(sk, skb)) {
-			kfree_skb(skb);
-			return -EPROTO;
-		}
-
-
-		/* Build DCCP header and checksum it. */
-		dh = dccp_zeroed_hdr(skb, dccp_header_size);
-		dh->dccph_type	= dcb->dccpd_type;
-		dh->dccph_sport	= inet->inet_sport;
-		dh->dccph_dport	= inet->inet_dport;
-		dh->dccph_doff	= (dccp_header_size + dcb->dccpd_opt_len) / 4;
-		dh->dccph_ccval	= dcb->dccpd_ccval;
-		dh->dccph_cscov = dp->dccps_pcslen;
-		/* XXX For now we're using only 48 bits sequence numbers */
-		dh->dccph_x	= 1;
-
-		dccp_update_gss(sk, dcb->dccpd_seq);
-		dccp_hdr_set_seq(dh, dp->dccps_gss);
-		if (set_ack)
-			dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno);
-
-		switch (dcb->dccpd_type) {
-		case DCCP_PKT_REQUEST:
-			dccp_hdr_request(skb)->dccph_req_service =
-							dp->dccps_service;
-			/*
-			 * Limit Ack window to ISS <= P.ackno <= GSS, so that
-			 * only Responses to Requests we sent are considered.
-			 */
-			dp->dccps_awl = dp->dccps_iss;
-			break;
-		case DCCP_PKT_RESET:
-			dccp_hdr_reset(skb)->dccph_reset_code =
-							dcb->dccpd_reset_code;
-			break;
-		}
-
-		icsk->icsk_af_ops->send_check(sk, skb);
-
-		if (set_ack)
-			dccp_event_ack_sent(sk);
-
-		DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
-
-		err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
-		return net_xmit_eval(err);
-	}
-	return -ENOBUFS;
-}
-
-/**
- * dccp_determine_ccmps  -  Find out about CCID-specific packet-size limits
- * @dp: socket to find packet size limits of
- *
- * We only consider the HC-sender CCID for setting the CCMPS (RFC 4340, 14.),
- * since the RX CCID is restricted to feedback packets (Acks), which are small
- * in comparison with the data traffic. A value of 0 means "no current CCMPS".
- */
-static u32 dccp_determine_ccmps(const struct dccp_sock *dp)
-{
-	const struct ccid *tx_ccid = dp->dccps_hc_tx_ccid;
-
-	if (tx_ccid == NULL || tx_ccid->ccid_ops == NULL)
-		return 0;
-	return tx_ccid->ccid_ops->ccid_ccmps;
-}
-
-unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct dccp_sock *dp = dccp_sk(sk);
-	u32 ccmps = dccp_determine_ccmps(dp);
-	u32 cur_mps = ccmps ? min(pmtu, ccmps) : pmtu;
-
-	/* Account for header lengths and IPv4/v6 option overhead */
-	cur_mps -= (icsk->icsk_af_ops->net_header_len + icsk->icsk_ext_hdr_len +
-		    sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext));
-
-	/*
-	 * Leave enough headroom for common DCCP header options.
-	 * This only considers options which may appear on DCCP-Data packets, as
-	 * per table 3 in RFC 4340, 5.8. When running out of space for other
-	 * options (eg. Ack Vector which can take up to 255 bytes), it is better
-	 * to schedule a separate Ack. Thus we leave headroom for the following:
-	 *  - 1 byte for Slow Receiver (11.6)
-	 *  - 6 bytes for Timestamp (13.1)
-	 *  - 10 bytes for Timestamp Echo (13.3)
-	 *  - 8 bytes for NDP count (7.7, when activated)
-	 *  - 6 bytes for Data Checksum (9.3)
-	 *  - %DCCPAV_MIN_OPTLEN bytes for Ack Vector size (11.4, when enabled)
-	 */
-	cur_mps -= roundup(1 + 6 + 10 + dp->dccps_send_ndp_count * 8 + 6 +
-			   (dp->dccps_hc_rx_ackvec ? DCCPAV_MIN_OPTLEN : 0), 4);
-
-	/* And store cached results */
-	icsk->icsk_pmtu_cookie = pmtu;
-	WRITE_ONCE(dp->dccps_mss_cache, cur_mps);
-
-	return cur_mps;
-}
-
-EXPORT_SYMBOL_GPL(dccp_sync_mss);
-
-void dccp_write_space(struct sock *sk)
-{
-	struct socket_wq *wq;
-
-	rcu_read_lock();
-	wq = rcu_dereference(sk->sk_wq);
-	if (skwq_has_sleeper(wq))
-		wake_up_interruptible(&wq->wait);
-	/* Should agree with poll, otherwise some programs break */
-	if (sock_writeable(sk))
-		sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT);
-
-	rcu_read_unlock();
-}
-
-/**
- * dccp_wait_for_ccid  -  Await CCID send permission
- * @sk:    socket to wait for
- * @delay: timeout in jiffies
- *
- * This is used by CCIDs which need to delay the send time in process context.
- */
-static int dccp_wait_for_ccid(struct sock *sk, unsigned long delay)
-{
-	DEFINE_WAIT(wait);
-	long remaining;
-
-	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-	sk->sk_write_pending++;
-	release_sock(sk);
-
-	remaining = schedule_timeout(delay);
-
-	lock_sock(sk);
-	sk->sk_write_pending--;
-	finish_wait(sk_sleep(sk), &wait);
-
-	if (signal_pending(current) || sk->sk_err)
-		return -1;
-	return remaining;
-}
-
-/**
- * dccp_xmit_packet  -  Send data packet under control of CCID
- * @sk: socket to send data packet on
- *
- * Transmits next-queued payload and informs CCID to account for the packet.
- */
-static void dccp_xmit_packet(struct sock *sk)
-{
-	int err, len;
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct sk_buff *skb = dccp_qpolicy_pop(sk);
-
-	if (unlikely(skb == NULL))
-		return;
-	len = skb->len;
-
-	if (sk->sk_state == DCCP_PARTOPEN) {
-		const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD;
-		/*
-		 * See 8.1.5 - Handshake Completion.
-		 *
-		 * For robustness we resend Confirm options until the client has
-		 * entered OPEN. During the initial feature negotiation, the MPS
-		 * is smaller than usual, reduced by the Change/Confirm options.
-		 */
-		if (!list_empty(&dp->dccps_featneg) && len > cur_mps) {
-			DCCP_WARN("Payload too large (%d) for featneg.\n", len);
-			dccp_send_ack(sk);
-			dccp_feat_list_purge(&dp->dccps_featneg);
-		}
-
-		inet_csk_schedule_ack(sk);
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-					      inet_csk(sk)->icsk_rto,
-					      DCCP_RTO_MAX);
-		DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK;
-	} else if (dccp_ack_pending(sk)) {
-		DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK;
-	} else {
-		DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATA;
-	}
-
-	err = dccp_transmit_skb(sk, skb);
-	if (err)
-		dccp_pr_debug("transmit_skb() returned err=%d\n", err);
-	/*
-	 * Register this one as sent even if an error occurred. To the remote
-	 * end a local packet drop is indistinguishable from network loss, i.e.
-	 * any local drop will eventually be reported via receiver feedback.
-	 */
-	ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len);
-
-	/*
-	 * If the CCID needs to transfer additional header options out-of-band
-	 * (e.g. Ack Vectors or feature-negotiation options), it activates this
-	 * flag to schedule a Sync. The Sync will automatically incorporate all
-	 * currently pending header options, thus clearing the backlog.
-	 */
-	if (dp->dccps_sync_scheduled)
-		dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
-}
-
-/**
- * dccp_flush_write_queue  -  Drain queue at end of connection
- * @sk: socket to be drained
- * @time_budget: time allowed to drain the queue
- *
- * Since dccp_sendmsg queues packets without waiting for them to be sent, it may
- * happen that the TX queue is not empty at the end of a connection. We give the
- * HC-sender CCID a grace period of up to @time_budget jiffies. If this function
- * returns with a non-empty write queue, it will be purged later.
- */
-void dccp_flush_write_queue(struct sock *sk, long *time_budget)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct sk_buff *skb;
-	long delay, rc;
-
-	while (*time_budget > 0 && (skb = skb_peek(&sk->sk_write_queue))) {
-		rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
-
-		switch (ccid_packet_dequeue_eval(rc)) {
-		case CCID_PACKET_WILL_DEQUEUE_LATER:
-			/*
-			 * If the CCID determines when to send, the next sending
-			 * time is unknown or the CCID may not even send again
-			 * (e.g. remote host crashes or lost Ack packets).
-			 */
-			DCCP_WARN("CCID did not manage to send all packets\n");
-			return;
-		case CCID_PACKET_DELAY:
-			delay = msecs_to_jiffies(rc);
-			if (delay > *time_budget)
-				return;
-			rc = dccp_wait_for_ccid(sk, delay);
-			if (rc < 0)
-				return;
-			*time_budget -= (delay - rc);
-			/* check again if we can send now */
-			break;
-		case CCID_PACKET_SEND_AT_ONCE:
-			dccp_xmit_packet(sk);
-			break;
-		case CCID_PACKET_ERR:
-			skb_dequeue(&sk->sk_write_queue);
-			kfree_skb(skb);
-			dccp_pr_debug("packet discarded due to err=%ld\n", rc);
-		}
-	}
-}
-
-void dccp_write_xmit(struct sock *sk)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct sk_buff *skb;
-
-	while ((skb = dccp_qpolicy_top(sk))) {
-		int rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
-
-		switch (ccid_packet_dequeue_eval(rc)) {
-		case CCID_PACKET_WILL_DEQUEUE_LATER:
-			return;
-		case CCID_PACKET_DELAY:
-			sk_reset_timer(sk, &dp->dccps_xmit_timer,
-				       jiffies + msecs_to_jiffies(rc));
-			return;
-		case CCID_PACKET_SEND_AT_ONCE:
-			dccp_xmit_packet(sk);
-			break;
-		case CCID_PACKET_ERR:
-			dccp_qpolicy_drop(sk, skb);
-			dccp_pr_debug("packet discarded due to err=%d\n", rc);
-		}
-	}
-}
-
-/**
- * dccp_retransmit_skb  -  Retransmit Request, Close, or CloseReq packets
- * @sk: socket to perform retransmit on
- *
- * There are only four retransmittable packet types in DCCP:
- * - Request  in client-REQUEST  state (sec. 8.1.1),
- * - CloseReq in server-CLOSEREQ state (sec. 8.3),
- * - Close    in   node-CLOSING  state (sec. 8.3),
- * - Acks in client-PARTOPEN state (sec. 8.1.5, handled by dccp_delack_timer()).
- * This function expects sk->sk_send_head to contain the original skb.
- */
-int dccp_retransmit_skb(struct sock *sk)
-{
-	WARN_ON(sk->sk_send_head == NULL);
-
-	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk) != 0)
-		return -EHOSTUNREACH; /* Routing failure or similar. */
-
-	/* this count is used to distinguish original and retransmitted skb */
-	inet_csk(sk)->icsk_retransmits++;
-
-	return dccp_transmit_skb(sk, skb_clone(sk->sk_send_head, GFP_ATOMIC));
-}
-
-struct sk_buff *dccp_make_response(const struct sock *sk, struct dst_entry *dst,
-				   struct request_sock *req)
-{
-	struct dccp_hdr *dh;
-	struct dccp_request_sock *dreq;
-	const u32 dccp_header_size = sizeof(struct dccp_hdr) +
-				     sizeof(struct dccp_hdr_ext) +
-				     sizeof(struct dccp_hdr_response);
-	struct sk_buff *skb;
-
-	/* sk is marked const to clearly express we dont hold socket lock.
-	 * sock_wmalloc() will atomically change sk->sk_wmem_alloc,
-	 * it is safe to promote sk to non const.
-	 */
-	skb = sock_wmalloc((struct sock *)sk, MAX_DCCP_HEADER, 1,
-			   GFP_ATOMIC);
-	if (!skb)
-		return NULL;
-
-	skb_reserve(skb, MAX_DCCP_HEADER);
-
-	skb_dst_set(skb, dst_clone(dst));
-
-	dreq = dccp_rsk(req);
-	if (inet_rsk(req)->acked)	/* increase GSS upon retransmission */
-		dccp_inc_seqno(&dreq->dreq_gss);
-	DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESPONSE;
-	DCCP_SKB_CB(skb)->dccpd_seq  = dreq->dreq_gss;
-
-	/* Resolve feature dependencies resulting from choice of CCID */
-	if (dccp_feat_server_ccid_dependencies(dreq))
-		goto response_failed;
-
-	if (dccp_insert_options_rsk(dreq, skb))
-		goto response_failed;
-
-	/* Build and checksum header */
-	dh = dccp_zeroed_hdr(skb, dccp_header_size);
-
-	dh->dccph_sport	= htons(inet_rsk(req)->ir_num);
-	dh->dccph_dport	= inet_rsk(req)->ir_rmt_port;
-	dh->dccph_doff	= (dccp_header_size +
-			   DCCP_SKB_CB(skb)->dccpd_opt_len) / 4;
-	dh->dccph_type	= DCCP_PKT_RESPONSE;
-	dh->dccph_x	= 1;
-	dccp_hdr_set_seq(dh, dreq->dreq_gss);
-	dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dreq->dreq_gsr);
-	dccp_hdr_response(skb)->dccph_resp_service = dreq->dreq_service;
-
-	dccp_csum_outgoing(skb);
-
-	/* We use `acked' to remember that a Response was already sent. */
-	inet_rsk(req)->acked = 1;
-	DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
-	return skb;
-response_failed:
-	kfree_skb(skb);
-	return NULL;
-}
-
-EXPORT_SYMBOL_GPL(dccp_make_response);
-
-/* answer offending packet in @rcv_skb with Reset from control socket @ctl */
-struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *rcv_skb)
-{
-	struct dccp_hdr *rxdh = dccp_hdr(rcv_skb), *dh;
-	struct dccp_skb_cb *dcb = DCCP_SKB_CB(rcv_skb);
-	const u32 dccp_hdr_reset_len = sizeof(struct dccp_hdr) +
-				       sizeof(struct dccp_hdr_ext) +
-				       sizeof(struct dccp_hdr_reset);
-	struct dccp_hdr_reset *dhr;
-	struct sk_buff *skb;
-
-	skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC);
-	if (skb == NULL)
-		return NULL;
-
-	skb_reserve(skb, sk->sk_prot->max_header);
-
-	/* Swap the send and the receive. */
-	dh = dccp_zeroed_hdr(skb, dccp_hdr_reset_len);
-	dh->dccph_type	= DCCP_PKT_RESET;
-	dh->dccph_sport	= rxdh->dccph_dport;
-	dh->dccph_dport	= rxdh->dccph_sport;
-	dh->dccph_doff	= dccp_hdr_reset_len / 4;
-	dh->dccph_x	= 1;
-
-	dhr = dccp_hdr_reset(skb);
-	dhr->dccph_reset_code = dcb->dccpd_reset_code;
-
-	switch (dcb->dccpd_reset_code) {
-	case DCCP_RESET_CODE_PACKET_ERROR:
-		dhr->dccph_reset_data[0] = rxdh->dccph_type;
-		break;
-	case DCCP_RESET_CODE_OPTION_ERROR:
-	case DCCP_RESET_CODE_MANDATORY_ERROR:
-		memcpy(dhr->dccph_reset_data, dcb->dccpd_reset_data, 3);
-		break;
-	}
-	/*
-	 * From RFC 4340, 8.3.1:
-	 *   If P.ackno exists, set R.seqno := P.ackno + 1.
-	 *   Else set R.seqno := 0.
-	 */
-	if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
-		dccp_hdr_set_seq(dh, ADD48(dcb->dccpd_ack_seq, 1));
-	dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dcb->dccpd_seq);
-
-	dccp_csum_outgoing(skb);
-	return skb;
-}
-
-EXPORT_SYMBOL_GPL(dccp_ctl_make_reset);
-
-/* send Reset on established socket, to close or abort the connection */
-int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code)
-{
-	struct sk_buff *skb;
-	/*
-	 * FIXME: what if rebuild_header fails?
-	 * Should we be doing a rebuild_header here?
-	 */
-	int err = inet_csk(sk)->icsk_af_ops->rebuild_header(sk);
-
-	if (err != 0)
-		return err;
-
-	skb = sock_wmalloc(sk, sk->sk_prot->max_header, 1, GFP_ATOMIC);
-	if (skb == NULL)
-		return -ENOBUFS;
-
-	/* Reserve space for headers and prepare control bits. */
-	skb_reserve(skb, sk->sk_prot->max_header);
-	DCCP_SKB_CB(skb)->dccpd_type	   = DCCP_PKT_RESET;
-	DCCP_SKB_CB(skb)->dccpd_reset_code = code;
-
-	return dccp_transmit_skb(sk, skb);
-}
-
-/*
- * Do all connect socket setups that can be done AF independent.
- */
-int dccp_connect(struct sock *sk)
-{
-	struct sk_buff *skb;
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct dst_entry *dst = __sk_dst_get(sk);
-	struct inet_connection_sock *icsk = inet_csk(sk);
-
-	sk->sk_err = 0;
-	sock_reset_flag(sk, SOCK_DONE);
-
-	dccp_sync_mss(sk, dst_mtu(dst));
-
-	/* do not connect if feature negotiation setup fails */
-	if (dccp_feat_finalise_settings(dccp_sk(sk)))
-		return -EPROTO;
-
-	/* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */
-	dp->dccps_gar = dp->dccps_iss;
-
-	skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation);
-	if (unlikely(skb == NULL))
-		return -ENOBUFS;
-
-	/* Reserve space for headers. */
-	skb_reserve(skb, sk->sk_prot->max_header);
-
-	DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_REQUEST;
-
-	dccp_transmit_skb(sk, dccp_skb_entail(sk, skb));
-	DCCP_INC_STATS(DCCP_MIB_ACTIVEOPENS);
-
-	/* Timer for repeating the REQUEST until an answer. */
-	icsk->icsk_retransmits = 0;
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-				  icsk->icsk_rto, DCCP_RTO_MAX);
-	return 0;
-}
-
-EXPORT_SYMBOL_GPL(dccp_connect);
-
-void dccp_send_ack(struct sock *sk)
-{
-	/* If we have been reset, we may not send again. */
-	if (sk->sk_state != DCCP_CLOSED) {
-		struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header,
-						GFP_ATOMIC);
-
-		if (skb == NULL) {
-			inet_csk_schedule_ack(sk);
-			inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
-			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-						  TCP_DELACK_MAX,
-						  DCCP_RTO_MAX);
-			return;
-		}
-
-		/* Reserve space for headers */
-		skb_reserve(skb, sk->sk_prot->max_header);
-		DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_ACK;
-		dccp_transmit_skb(sk, skb);
-	}
-}
-
-EXPORT_SYMBOL_GPL(dccp_send_ack);
-
-#if 0
-/* FIXME: Is this still necessary (11.3) - currently nowhere used by DCCP. */
-void dccp_send_delayed_ack(struct sock *sk)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-	/*
-	 * FIXME: tune this timer. elapsed time fixes the skew, so no problem
-	 * with using 2s, and active senders also piggyback the ACK into a
-	 * DATAACK packet, so this is really for quiescent senders.
-	 */
-	unsigned long timeout = jiffies + 2 * HZ;
-
-	/* Use new timeout only if there wasn't a older one earlier. */
-	if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) {
-		/* If delack timer was blocked or is about to expire,
-		 * send ACK now.
-		 *
-		 * FIXME: check the "about to expire" part
-		 */
-		if (icsk->icsk_ack.blocked) {
-			dccp_send_ack(sk);
-			return;
-		}
-
-		if (!time_before(timeout, icsk_delack_timeout(icsk)))
-			timeout = icsk_delack_timeout(icsk);
-	}
-	icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
-	sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout);
-}
-#endif
-
-void dccp_send_sync(struct sock *sk, const u64 ackno,
-		    const enum dccp_pkt_type pkt_type)
-{
-	/*
-	 * We are not putting this on the write queue, so
-	 * dccp_transmit_skb() will set the ownership to this
-	 * sock.
-	 */
-	struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC);
-
-	if (skb == NULL) {
-		/* FIXME: how to make sure the sync is sent? */
-		DCCP_CRIT("could not send %s", dccp_packet_name(pkt_type));
-		return;
-	}
-
-	/* Reserve space for headers and prepare control bits. */
-	skb_reserve(skb, sk->sk_prot->max_header);
-	DCCP_SKB_CB(skb)->dccpd_type = pkt_type;
-	DCCP_SKB_CB(skb)->dccpd_ack_seq = ackno;
-
-	/*
-	 * Clear the flag in case the Sync was scheduled for out-of-band data,
-	 * such as carrying a long Ack Vector.
-	 */
-	dccp_sk(sk)->dccps_sync_scheduled = 0;
-
-	dccp_transmit_skb(sk, skb);
-}
-
-EXPORT_SYMBOL_GPL(dccp_send_sync);
-
-/*
- * Send a DCCP_PKT_CLOSE/CLOSEREQ. The caller locks the socket for us. This
- * cannot be allowed to fail queueing a DCCP_PKT_CLOSE/CLOSEREQ frame under
- * any circumstances.
- */
-void dccp_send_close(struct sock *sk, const int active)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct sk_buff *skb;
-	const gfp_t prio = active ? GFP_KERNEL : GFP_ATOMIC;
-
-	skb = alloc_skb(sk->sk_prot->max_header, prio);
-	if (skb == NULL)
-		return;
-
-	/* Reserve space for headers and prepare control bits. */
-	skb_reserve(skb, sk->sk_prot->max_header);
-	if (dp->dccps_role == DCCP_ROLE_SERVER && !dp->dccps_server_timewait)
-		DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSEREQ;
-	else
-		DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSE;
-
-	if (active) {
-		skb = dccp_skb_entail(sk, skb);
-		/*
-		 * Retransmission timer for active-close: RFC 4340, 8.3 requires
-		 * to retransmit the Close/CloseReq until the CLOSING/CLOSEREQ
-		 * state can be left. The initial timeout is 2 RTTs.
-		 * Since RTT measurement is done by the CCIDs, there is no easy
-		 * way to get an RTT sample. The fallback RTT from RFC 4340, 3.4
-		 * is too low (200ms); we use a high value to avoid unnecessary
-		 * retransmissions when the link RTT is > 0.2 seconds.
-		 * FIXME: Let main module sample RTTs and use that instead.
-		 */
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-					  DCCP_TIMEOUT_INIT, DCCP_RTO_MAX);
-	}
-	dccp_transmit_skb(sk, skb);
-}
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
deleted file mode 100644
index fcc5c9d64f46..000000000000
--- a/net/dccp/proto.c
+++ /dev/null
@@ -1,1293 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  net/dccp/proto.c
- *
- *  An implementation of the DCCP protocol
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-
-#include <linux/dccp.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <linux/in.h>
-#include <linux/if_arp.h>
-#include <linux/init.h>
-#include <linux/random.h>
-#include <linux/slab.h>
-#include <net/checksum.h>
-
-#include <net/inet_sock.h>
-#include <net/inet_common.h>
-#include <net/sock.h>
-#include <net/xfrm.h>
-
-#include <asm/ioctls.h>
-#include <linux/spinlock.h>
-#include <linux/timer.h>
-#include <linux/delay.h>
-#include <linux/poll.h>
-
-#include "ccid.h"
-#include "dccp.h"
-#include "feat.h"
-
-#define CREATE_TRACE_POINTS
-#include "trace.h"
-
-DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly;
-
-EXPORT_SYMBOL_GPL(dccp_statistics);
-
-DEFINE_PER_CPU(unsigned int, dccp_orphan_count);
-EXPORT_PER_CPU_SYMBOL_GPL(dccp_orphan_count);
-
-struct inet_hashinfo dccp_hashinfo;
-EXPORT_SYMBOL_GPL(dccp_hashinfo);
-
-/* the maximum queue length for tx in packets. 0 is no limit */
-int sysctl_dccp_tx_qlen __read_mostly = 5;
-
-#ifdef CONFIG_IP_DCCP_DEBUG
-static const char *dccp_state_name(const int state)
-{
-	static const char *const dccp_state_names[] = {
-	[DCCP_OPEN]		= "OPEN",
-	[DCCP_REQUESTING]	= "REQUESTING",
-	[DCCP_PARTOPEN]		= "PARTOPEN",
-	[DCCP_LISTEN]		= "LISTEN",
-	[DCCP_RESPOND]		= "RESPOND",
-	[DCCP_CLOSING]		= "CLOSING",
-	[DCCP_ACTIVE_CLOSEREQ]	= "CLOSEREQ",
-	[DCCP_PASSIVE_CLOSE]	= "PASSIVE_CLOSE",
-	[DCCP_PASSIVE_CLOSEREQ]	= "PASSIVE_CLOSEREQ",
-	[DCCP_TIME_WAIT]	= "TIME_WAIT",
-	[DCCP_CLOSED]		= "CLOSED",
-	};
-
-	if (state >= DCCP_MAX_STATES)
-		return "INVALID STATE!";
-	else
-		return dccp_state_names[state];
-}
-#endif
-
-void dccp_set_state(struct sock *sk, const int state)
-{
-	const int oldstate = sk->sk_state;
-
-	dccp_pr_debug("%s(%p)  %s  -->  %s\n", dccp_role(sk), sk,
-		      dccp_state_name(oldstate), dccp_state_name(state));
-	WARN_ON(state == oldstate);
-
-	switch (state) {
-	case DCCP_OPEN:
-		if (oldstate != DCCP_OPEN)
-			DCCP_INC_STATS(DCCP_MIB_CURRESTAB);
-		/* Client retransmits all Confirm options until entering OPEN */
-		if (oldstate == DCCP_PARTOPEN)
-			dccp_feat_list_purge(&dccp_sk(sk)->dccps_featneg);
-		break;
-
-	case DCCP_CLOSED:
-		if (oldstate == DCCP_OPEN || oldstate == DCCP_ACTIVE_CLOSEREQ ||
-		    oldstate == DCCP_CLOSING)
-			DCCP_INC_STATS(DCCP_MIB_ESTABRESETS);
-
-		sk->sk_prot->unhash(sk);
-		if (inet_csk(sk)->icsk_bind_hash != NULL &&
-		    !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
-			inet_put_port(sk);
-		fallthrough;
-	default:
-		if (oldstate == DCCP_OPEN)
-			DCCP_DEC_STATS(DCCP_MIB_CURRESTAB);
-	}
-
-	/* Change state AFTER socket is unhashed to avoid closed
-	 * socket sitting in hash tables.
-	 */
-	inet_sk_set_state(sk, state);
-}
-
-EXPORT_SYMBOL_GPL(dccp_set_state);
-
-static void dccp_finish_passive_close(struct sock *sk)
-{
-	switch (sk->sk_state) {
-	case DCCP_PASSIVE_CLOSE:
-		/* Node (client or server) has received Close packet. */
-		dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED);
-		dccp_set_state(sk, DCCP_CLOSED);
-		break;
-	case DCCP_PASSIVE_CLOSEREQ:
-		/*
-		 * Client received CloseReq. We set the `active' flag so that
-		 * dccp_send_close() retransmits the Close as per RFC 4340, 8.3.
-		 */
-		dccp_send_close(sk, 1);
-		dccp_set_state(sk, DCCP_CLOSING);
-	}
-}
-
-void dccp_done(struct sock *sk)
-{
-	dccp_set_state(sk, DCCP_CLOSED);
-	dccp_clear_xmit_timers(sk);
-
-	sk->sk_shutdown = SHUTDOWN_MASK;
-
-	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_state_change(sk);
-	else
-		inet_csk_destroy_sock(sk);
-}
-
-EXPORT_SYMBOL_GPL(dccp_done);
-
-const char *dccp_packet_name(const int type)
-{
-	static const char *const dccp_packet_names[] = {
-		[DCCP_PKT_REQUEST]  = "REQUEST",
-		[DCCP_PKT_RESPONSE] = "RESPONSE",
-		[DCCP_PKT_DATA]	    = "DATA",
-		[DCCP_PKT_ACK]	    = "ACK",
-		[DCCP_PKT_DATAACK]  = "DATAACK",
-		[DCCP_PKT_CLOSEREQ] = "CLOSEREQ",
-		[DCCP_PKT_CLOSE]    = "CLOSE",
-		[DCCP_PKT_RESET]    = "RESET",
-		[DCCP_PKT_SYNC]	    = "SYNC",
-		[DCCP_PKT_SYNCACK]  = "SYNCACK",
-	};
-
-	if (type >= DCCP_NR_PKT_TYPES)
-		return "INVALID";
-	else
-		return dccp_packet_names[type];
-}
-
-EXPORT_SYMBOL_GPL(dccp_packet_name);
-
-void dccp_destruct_common(struct sock *sk)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-
-	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
-	dp->dccps_hc_tx_ccid = NULL;
-}
-EXPORT_SYMBOL_GPL(dccp_destruct_common);
-
-static void dccp_sk_destruct(struct sock *sk)
-{
-	dccp_destruct_common(sk);
-	inet_sock_destruct(sk);
-}
-
-int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct inet_connection_sock *icsk = inet_csk(sk);
-
-	pr_warn_once("DCCP is deprecated and scheduled to be removed in 2025, "
-		     "please contact the netdev mailing list\n");
-
-	icsk->icsk_rto		= DCCP_TIMEOUT_INIT;
-	icsk->icsk_syn_retries	= sysctl_dccp_request_retries;
-	sk->sk_state		= DCCP_CLOSED;
-	sk->sk_write_space	= dccp_write_space;
-	sk->sk_destruct		= dccp_sk_destruct;
-	icsk->icsk_sync_mss	= dccp_sync_mss;
-	dp->dccps_mss_cache	= 536;
-	dp->dccps_rate_last	= jiffies;
-	dp->dccps_role		= DCCP_ROLE_UNDEFINED;
-	dp->dccps_service	= DCCP_SERVICE_CODE_IS_ABSENT;
-	dp->dccps_tx_qlen	= sysctl_dccp_tx_qlen;
-
-	dccp_init_xmit_timers(sk);
-
-	INIT_LIST_HEAD(&dp->dccps_featneg);
-	/* control socket doesn't need feat nego */
-	if (likely(ctl_sock_initialized))
-		return dccp_feat_init(sk);
-	return 0;
-}
-
-EXPORT_SYMBOL_GPL(dccp_init_sock);
-
-void dccp_destroy_sock(struct sock *sk)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-
-	__skb_queue_purge(&sk->sk_write_queue);
-	if (sk->sk_send_head != NULL) {
-		kfree_skb(sk->sk_send_head);
-		sk->sk_send_head = NULL;
-	}
-
-	/* Clean up a referenced DCCP bind bucket. */
-	if (inet_csk(sk)->icsk_bind_hash != NULL)
-		inet_put_port(sk);
-
-	kfree(dp->dccps_service_list);
-	dp->dccps_service_list = NULL;
-
-	if (dp->dccps_hc_rx_ackvec != NULL) {
-		dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
-		dp->dccps_hc_rx_ackvec = NULL;
-	}
-	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
-	dp->dccps_hc_rx_ccid = NULL;
-
-	/* clean up feature negotiation state */
-	dccp_feat_list_purge(&dp->dccps_featneg);
-}
-
-EXPORT_SYMBOL_GPL(dccp_destroy_sock);
-
-static inline int dccp_need_reset(int state)
-{
-	return state != DCCP_CLOSED && state != DCCP_LISTEN &&
-	       state != DCCP_REQUESTING;
-}
-
-int dccp_disconnect(struct sock *sk, int flags)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct inet_sock *inet = inet_sk(sk);
-	struct dccp_sock *dp = dccp_sk(sk);
-	const int old_state = sk->sk_state;
-
-	if (old_state != DCCP_CLOSED)
-		dccp_set_state(sk, DCCP_CLOSED);
-
-	/*
-	 * This corresponds to the ABORT function of RFC793, sec. 3.8
-	 * TCP uses a RST segment, DCCP a Reset packet with Code 2, "Aborted".
-	 */
-	if (old_state == DCCP_LISTEN) {
-		inet_csk_listen_stop(sk);
-	} else if (dccp_need_reset(old_state)) {
-		dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
-		sk->sk_err = ECONNRESET;
-	} else if (old_state == DCCP_REQUESTING)
-		sk->sk_err = ECONNRESET;
-
-	dccp_clear_xmit_timers(sk);
-	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
-	dp->dccps_hc_rx_ccid = NULL;
-
-	__skb_queue_purge(&sk->sk_receive_queue);
-	__skb_queue_purge(&sk->sk_write_queue);
-	if (sk->sk_send_head != NULL) {
-		__kfree_skb(sk->sk_send_head);
-		sk->sk_send_head = NULL;
-	}
-
-	inet->inet_dport = 0;
-
-	inet_bhash2_reset_saddr(sk);
-
-	sk->sk_shutdown = 0;
-	sock_reset_flag(sk, SOCK_DONE);
-
-	icsk->icsk_backoff = 0;
-	inet_csk_delack_init(sk);
-	__sk_dst_reset(sk);
-
-	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
-
-	sk_error_report(sk);
-	return 0;
-}
-
-EXPORT_SYMBOL_GPL(dccp_disconnect);
-
-/*
- *	Wait for a DCCP event.
- *
- *	Note that we don't need to lock the socket, as the upper poll layers
- *	take care of normal races (between the test and the event) and we don't
- *	go look at any of the socket buffers directly.
- */
-__poll_t dccp_poll(struct file *file, struct socket *sock,
-		       poll_table *wait)
-{
-	struct sock *sk = sock->sk;
-	__poll_t mask;
-	u8 shutdown;
-	int state;
-
-	sock_poll_wait(file, sock, wait);
-
-	state = inet_sk_state_load(sk);
-	if (state == DCCP_LISTEN)
-		return inet_csk_listen_poll(sk);
-
-	/* Socket is not locked. We are protected from async events
-	   by poll logic and correct handling of state changes
-	   made by another threads is impossible in any case.
-	 */
-
-	mask = 0;
-	if (READ_ONCE(sk->sk_err))
-		mask = EPOLLERR;
-	shutdown = READ_ONCE(sk->sk_shutdown);
-
-	if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED)
-		mask |= EPOLLHUP;
-	if (shutdown & RCV_SHUTDOWN)
-		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
-
-	/* Connected? */
-	if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
-		if (atomic_read(&sk->sk_rmem_alloc) > 0)
-			mask |= EPOLLIN | EPOLLRDNORM;
-
-		if (!(shutdown & SEND_SHUTDOWN)) {
-			if (sk_stream_is_writeable(sk)) {
-				mask |= EPOLLOUT | EPOLLWRNORM;
-			} else {  /* send SIGIO later */
-				sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
-				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-
-				/* Race breaker. If space is freed after
-				 * wspace test but before the flags are set,
-				 * IO signal will be lost.
-				 */
-				if (sk_stream_is_writeable(sk))
-					mask |= EPOLLOUT | EPOLLWRNORM;
-			}
-		}
-	}
-	return mask;
-}
-EXPORT_SYMBOL_GPL(dccp_poll);
-
-int dccp_ioctl(struct sock *sk, int cmd, int *karg)
-{
-	int rc = -ENOTCONN;
-
-	lock_sock(sk);
-
-	if (sk->sk_state == DCCP_LISTEN)
-		goto out;
-
-	switch (cmd) {
-	case SIOCOUTQ: {
-		*karg = sk_wmem_alloc_get(sk);
-		/* Using sk_wmem_alloc here because sk_wmem_queued is not used by DCCP and
-		 * always 0, comparably to UDP.
-		 */
-
-		rc = 0;
-	}
-		break;
-	case SIOCINQ: {
-		struct sk_buff *skb;
-		*karg = 0;
-
-		skb = skb_peek(&sk->sk_receive_queue);
-		if (skb != NULL) {
-			/*
-			 * We will only return the amount of this packet since
-			 * that is all that will be read.
-			 */
-			*karg = skb->len;
-		}
-		rc = 0;
-	}
-		break;
-	default:
-		rc = -ENOIOCTLCMD;
-		break;
-	}
-out:
-	release_sock(sk);
-	return rc;
-}
-
-EXPORT_SYMBOL_GPL(dccp_ioctl);
-
-static int dccp_setsockopt_service(struct sock *sk, const __be32 service,
-				   sockptr_t optval, unsigned int optlen)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct dccp_service_list *sl = NULL;
-
-	if (service == DCCP_SERVICE_INVALID_VALUE ||
-	    optlen > DCCP_SERVICE_LIST_MAX_LEN * sizeof(u32))
-		return -EINVAL;
-
-	if (optlen > sizeof(service)) {
-		sl = kmalloc(optlen, GFP_KERNEL);
-		if (sl == NULL)
-			return -ENOMEM;
-
-		sl->dccpsl_nr = optlen / sizeof(u32) - 1;
-		if (copy_from_sockptr_offset(sl->dccpsl_list, optval,
-				sizeof(service), optlen - sizeof(service)) ||
-		    dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) {
-			kfree(sl);
-			return -EFAULT;
-		}
-	}
-
-	lock_sock(sk);
-	dp->dccps_service = service;
-
-	kfree(dp->dccps_service_list);
-
-	dp->dccps_service_list = sl;
-	release_sock(sk);
-	return 0;
-}
-
-static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx)
-{
-	u8 *list, len;
-	int i, rc;
-
-	if (cscov < 0 || cscov > 15)
-		return -EINVAL;
-	/*
-	 * Populate a list of permissible values, in the range cscov...15. This
-	 * is necessary since feature negotiation of single values only works if
-	 * both sides incidentally choose the same value. Since the list starts
-	 * lowest-value first, negotiation will pick the smallest shared value.
-	 */
-	if (cscov == 0)
-		return 0;
-	len = 16 - cscov;
-
-	list = kmalloc(len, GFP_KERNEL);
-	if (list == NULL)
-		return -ENOBUFS;
-
-	for (i = 0; i < len; i++)
-		list[i] = cscov++;
-
-	rc = dccp_feat_register_sp(sk, DCCPF_MIN_CSUM_COVER, rx, list, len);
-
-	if (rc == 0) {
-		if (rx)
-			dccp_sk(sk)->dccps_pcrlen = cscov;
-		else
-			dccp_sk(sk)->dccps_pcslen = cscov;
-	}
-	kfree(list);
-	return rc;
-}
-
-static int dccp_setsockopt_ccid(struct sock *sk, int type,
-				sockptr_t optval, unsigned int optlen)
-{
-	u8 *val;
-	int rc = 0;
-
-	if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS)
-		return -EINVAL;
-
-	val = memdup_sockptr(optval, optlen);
-	if (IS_ERR(val))
-		return PTR_ERR(val);
-
-	lock_sock(sk);
-	if (type == DCCP_SOCKOPT_TX_CCID || type == DCCP_SOCKOPT_CCID)
-		rc = dccp_feat_register_sp(sk, DCCPF_CCID, 1, val, optlen);
-
-	if (!rc && (type == DCCP_SOCKOPT_RX_CCID || type == DCCP_SOCKOPT_CCID))
-		rc = dccp_feat_register_sp(sk, DCCPF_CCID, 0, val, optlen);
-	release_sock(sk);
-
-	kfree(val);
-	return rc;
-}
-
-static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
-		sockptr_t optval, unsigned int optlen)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	int val, err = 0;
-
-	switch (optname) {
-	case DCCP_SOCKOPT_PACKET_SIZE:
-		DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
-		return 0;
-	case DCCP_SOCKOPT_CHANGE_L:
-	case DCCP_SOCKOPT_CHANGE_R:
-		DCCP_WARN("sockopt(CHANGE_L/R) is deprecated: fix your app\n");
-		return 0;
-	case DCCP_SOCKOPT_CCID:
-	case DCCP_SOCKOPT_RX_CCID:
-	case DCCP_SOCKOPT_TX_CCID:
-		return dccp_setsockopt_ccid(sk, optname, optval, optlen);
-	}
-
-	if (optlen < (int)sizeof(int))
-		return -EINVAL;
-
-	if (copy_from_sockptr(&val, optval, sizeof(int)))
-		return -EFAULT;
-
-	if (optname == DCCP_SOCKOPT_SERVICE)
-		return dccp_setsockopt_service(sk, val, optval, optlen);
-
-	lock_sock(sk);
-	switch (optname) {
-	case DCCP_SOCKOPT_SERVER_TIMEWAIT:
-		if (dp->dccps_role != DCCP_ROLE_SERVER)
-			err = -EOPNOTSUPP;
-		else
-			dp->dccps_server_timewait = (val != 0);
-		break;
-	case DCCP_SOCKOPT_SEND_CSCOV:
-		err = dccp_setsockopt_cscov(sk, val, false);
-		break;
-	case DCCP_SOCKOPT_RECV_CSCOV:
-		err = dccp_setsockopt_cscov(sk, val, true);
-		break;
-	case DCCP_SOCKOPT_QPOLICY_ID:
-		if (sk->sk_state != DCCP_CLOSED)
-			err = -EISCONN;
-		else if (val < 0 || val >= DCCPQ_POLICY_MAX)
-			err = -EINVAL;
-		else
-			dp->dccps_qpolicy = val;
-		break;
-	case DCCP_SOCKOPT_QPOLICY_TXQLEN:
-		if (val < 0)
-			err = -EINVAL;
-		else
-			dp->dccps_tx_qlen = val;
-		break;
-	default:
-		err = -ENOPROTOOPT;
-		break;
-	}
-	release_sock(sk);
-
-	return err;
-}
-
-int dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
-		    unsigned int optlen)
-{
-	if (level != SOL_DCCP)
-		return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level,
-							     optname, optval,
-							     optlen);
-	return do_dccp_setsockopt(sk, level, optname, optval, optlen);
-}
-
-EXPORT_SYMBOL_GPL(dccp_setsockopt);
-
-static int dccp_getsockopt_service(struct sock *sk, int len,
-				   __be32 __user *optval,
-				   int __user *optlen)
-{
-	const struct dccp_sock *dp = dccp_sk(sk);
-	const struct dccp_service_list *sl;
-	int err = -ENOENT, slen = 0, total_len = sizeof(u32);
-
-	lock_sock(sk);
-	if ((sl = dp->dccps_service_list) != NULL) {
-		slen = sl->dccpsl_nr * sizeof(u32);
-		total_len += slen;
-	}
-
-	err = -EINVAL;
-	if (total_len > len)
-		goto out;
-
-	err = 0;
-	if (put_user(total_len, optlen) ||
-	    put_user(dp->dccps_service, optval) ||
-	    (sl != NULL && copy_to_user(optval + 1, sl->dccpsl_list, slen)))
-		err = -EFAULT;
-out:
-	release_sock(sk);
-	return err;
-}
-
-static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
-		    char __user *optval, int __user *optlen)
-{
-	struct dccp_sock *dp;
-	int val, len;
-
-	if (get_user(len, optlen))
-		return -EFAULT;
-
-	if (len < (int)sizeof(int))
-		return -EINVAL;
-
-	dp = dccp_sk(sk);
-
-	switch (optname) {
-	case DCCP_SOCKOPT_PACKET_SIZE:
-		DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
-		return 0;
-	case DCCP_SOCKOPT_SERVICE:
-		return dccp_getsockopt_service(sk, len,
-					       (__be32 __user *)optval, optlen);
-	case DCCP_SOCKOPT_GET_CUR_MPS:
-		val = READ_ONCE(dp->dccps_mss_cache);
-		break;
-	case DCCP_SOCKOPT_AVAILABLE_CCIDS:
-		return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen);
-	case DCCP_SOCKOPT_TX_CCID:
-		val = ccid_get_current_tx_ccid(dp);
-		if (val < 0)
-			return -ENOPROTOOPT;
-		break;
-	case DCCP_SOCKOPT_RX_CCID:
-		val = ccid_get_current_rx_ccid(dp);
-		if (val < 0)
-			return -ENOPROTOOPT;
-		break;
-	case DCCP_SOCKOPT_SERVER_TIMEWAIT:
-		val = dp->dccps_server_timewait;
-		break;
-	case DCCP_SOCKOPT_SEND_CSCOV:
-		val = dp->dccps_pcslen;
-		break;
-	case DCCP_SOCKOPT_RECV_CSCOV:
-		val = dp->dccps_pcrlen;
-		break;
-	case DCCP_SOCKOPT_QPOLICY_ID:
-		val = dp->dccps_qpolicy;
-		break;
-	case DCCP_SOCKOPT_QPOLICY_TXQLEN:
-		val = dp->dccps_tx_qlen;
-		break;
-	case 128 ... 191:
-		return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname,
-					     len, (u32 __user *)optval, optlen);
-	case 192 ... 255:
-		return ccid_hc_tx_getsockopt(dp->dccps_hc_tx_ccid, sk, optname,
-					     len, (u32 __user *)optval, optlen);
-	default:
-		return -ENOPROTOOPT;
-	}
-
-	len = sizeof(val);
-	if (put_user(len, optlen) || copy_to_user(optval, &val, len))
-		return -EFAULT;
-
-	return 0;
-}
-
-int dccp_getsockopt(struct sock *sk, int level, int optname,
-		    char __user *optval, int __user *optlen)
-{
-	if (level != SOL_DCCP)
-		return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level,
-							     optname, optval,
-							     optlen);
-	return do_dccp_getsockopt(sk, level, optname, optval, optlen);
-}
-
-EXPORT_SYMBOL_GPL(dccp_getsockopt);
-
-static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb)
-{
-	struct cmsghdr *cmsg;
-
-	/*
-	 * Assign an (opaque) qpolicy priority value to skb->priority.
-	 *
-	 * We are overloading this skb field for use with the qpolicy subystem.
-	 * The skb->priority is normally used for the SO_PRIORITY option, which
-	 * is initialised from sk_priority. Since the assignment of sk_priority
-	 * to skb->priority happens later (on layer 3), we overload this field
-	 * for use with queueing priorities as long as the skb is on layer 4.
-	 * The default priority value (if nothing is set) is 0.
-	 */
-	skb->priority = 0;
-
-	for_each_cmsghdr(cmsg, msg) {
-		if (!CMSG_OK(msg, cmsg))
-			return -EINVAL;
-
-		if (cmsg->cmsg_level != SOL_DCCP)
-			continue;
-
-		if (cmsg->cmsg_type <= DCCP_SCM_QPOLICY_MAX &&
-		    !dccp_qpolicy_param_ok(skb->sk, cmsg->cmsg_type))
-			return -EINVAL;
-
-		switch (cmsg->cmsg_type) {
-		case DCCP_SCM_PRIORITY:
-			if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u32)))
-				return -EINVAL;
-			skb->priority = *(__u32 *)CMSG_DATA(cmsg);
-			break;
-		default:
-			return -EINVAL;
-		}
-	}
-	return 0;
-}
-
-int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
-{
-	const struct dccp_sock *dp = dccp_sk(sk);
-	const int flags = msg->msg_flags;
-	const int noblock = flags & MSG_DONTWAIT;
-	struct sk_buff *skb;
-	int rc, size;
-	long timeo;
-
-	trace_dccp_probe(sk, len);
-
-	if (len > READ_ONCE(dp->dccps_mss_cache))
-		return -EMSGSIZE;
-
-	lock_sock(sk);
-
-	timeo = sock_sndtimeo(sk, noblock);
-
-	/*
-	 * We have to use sk_stream_wait_connect here to set sk_write_pending,
-	 * so that the trick in dccp_rcv_request_sent_state_process.
-	 */
-	/* Wait for a connection to finish. */
-	if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN))
-		if ((rc = sk_stream_wait_connect(sk, &timeo)) != 0)
-			goto out_release;
-
-	size = sk->sk_prot->max_header + len;
-	release_sock(sk);
-	skb = sock_alloc_send_skb(sk, size, noblock, &rc);
-	lock_sock(sk);
-	if (skb == NULL)
-		goto out_release;
-
-	if (dccp_qpolicy_full(sk)) {
-		rc = -EAGAIN;
-		goto out_discard;
-	}
-
-	if (sk->sk_state == DCCP_CLOSED) {
-		rc = -ENOTCONN;
-		goto out_discard;
-	}
-
-	/* We need to check dccps_mss_cache after socket is locked. */
-	if (len > dp->dccps_mss_cache) {
-		rc = -EMSGSIZE;
-		goto out_discard;
-	}
-
-	skb_reserve(skb, sk->sk_prot->max_header);
-	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
-	if (rc != 0)
-		goto out_discard;
-
-	rc = dccp_msghdr_parse(msg, skb);
-	if (rc != 0)
-		goto out_discard;
-
-	dccp_qpolicy_push(sk, skb);
-	/*
-	 * The xmit_timer is set if the TX CCID is rate-based and will expire
-	 * when congestion control permits to release further packets into the
-	 * network. Window-based CCIDs do not use this timer.
-	 */
-	if (!timer_pending(&dp->dccps_xmit_timer))
-		dccp_write_xmit(sk);
-out_release:
-	release_sock(sk);
-	return rc ? : len;
-out_discard:
-	kfree_skb(skb);
-	goto out_release;
-}
-
-EXPORT_SYMBOL_GPL(dccp_sendmsg);
-
-int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
-		 int *addr_len)
-{
-	const struct dccp_hdr *dh;
-	long timeo;
-
-	lock_sock(sk);
-
-	if (sk->sk_state == DCCP_LISTEN) {
-		len = -ENOTCONN;
-		goto out;
-	}
-
-	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
-
-	do {
-		struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
-
-		if (skb == NULL)
-			goto verify_sock_status;
-
-		dh = dccp_hdr(skb);
-
-		switch (dh->dccph_type) {
-		case DCCP_PKT_DATA:
-		case DCCP_PKT_DATAACK:
-			goto found_ok_skb;
-
-		case DCCP_PKT_CLOSE:
-		case DCCP_PKT_CLOSEREQ:
-			if (!(flags & MSG_PEEK))
-				dccp_finish_passive_close(sk);
-			fallthrough;
-		case DCCP_PKT_RESET:
-			dccp_pr_debug("found fin (%s) ok!\n",
-				      dccp_packet_name(dh->dccph_type));
-			len = 0;
-			goto found_fin_ok;
-		default:
-			dccp_pr_debug("packet_type=%s\n",
-				      dccp_packet_name(dh->dccph_type));
-			sk_eat_skb(sk, skb);
-		}
-verify_sock_status:
-		if (sock_flag(sk, SOCK_DONE)) {
-			len = 0;
-			break;
-		}
-
-		if (sk->sk_err) {
-			len = sock_error(sk);
-			break;
-		}
-
-		if (sk->sk_shutdown & RCV_SHUTDOWN) {
-			len = 0;
-			break;
-		}
-
-		if (sk->sk_state == DCCP_CLOSED) {
-			if (!sock_flag(sk, SOCK_DONE)) {
-				/* This occurs when user tries to read
-				 * from never connected socket.
-				 */
-				len = -ENOTCONN;
-				break;
-			}
-			len = 0;
-			break;
-		}
-
-		if (!timeo) {
-			len = -EAGAIN;
-			break;
-		}
-
-		if (signal_pending(current)) {
-			len = sock_intr_errno(timeo);
-			break;
-		}
-
-		sk_wait_data(sk, &timeo, NULL);
-		continue;
-	found_ok_skb:
-		if (len > skb->len)
-			len = skb->len;
-		else if (len < skb->len)
-			msg->msg_flags |= MSG_TRUNC;
-
-		if (skb_copy_datagram_msg(skb, 0, msg, len)) {
-			/* Exception. Bailout! */
-			len = -EFAULT;
-			break;
-		}
-		if (flags & MSG_TRUNC)
-			len = skb->len;
-	found_fin_ok:
-		if (!(flags & MSG_PEEK))
-			sk_eat_skb(sk, skb);
-		break;
-	} while (1);
-out:
-	release_sock(sk);
-	return len;
-}
-
-EXPORT_SYMBOL_GPL(dccp_recvmsg);
-
-int inet_dccp_listen(struct socket *sock, int backlog)
-{
-	struct sock *sk = sock->sk;
-	unsigned char old_state;
-	int err;
-
-	lock_sock(sk);
-
-	err = -EINVAL;
-	if (sock->state != SS_UNCONNECTED || sock->type != SOCK_DCCP)
-		goto out;
-
-	old_state = sk->sk_state;
-	if (!((1 << old_state) & (DCCPF_CLOSED | DCCPF_LISTEN)))
-		goto out;
-
-	WRITE_ONCE(sk->sk_max_ack_backlog, backlog);
-	/* Really, if the socket is already in listen state
-	 * we can only allow the backlog to be adjusted.
-	 */
-	if (old_state != DCCP_LISTEN) {
-		struct dccp_sock *dp = dccp_sk(sk);
-
-		dp->dccps_role = DCCP_ROLE_LISTEN;
-
-		/* do not start to listen if feature negotiation setup fails */
-		if (dccp_feat_finalise_settings(dp)) {
-			err = -EPROTO;
-			goto out;
-		}
-
-		err = inet_csk_listen_start(sk);
-		if (err)
-			goto out;
-	}
-	err = 0;
-
-out:
-	release_sock(sk);
-	return err;
-}
-
-EXPORT_SYMBOL_GPL(inet_dccp_listen);
-
-static void dccp_terminate_connection(struct sock *sk)
-{
-	u8 next_state = DCCP_CLOSED;
-
-	switch (sk->sk_state) {
-	case DCCP_PASSIVE_CLOSE:
-	case DCCP_PASSIVE_CLOSEREQ:
-		dccp_finish_passive_close(sk);
-		break;
-	case DCCP_PARTOPEN:
-		dccp_pr_debug("Stop PARTOPEN timer (%p)\n", sk);
-		inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
-		fallthrough;
-	case DCCP_OPEN:
-		dccp_send_close(sk, 1);
-
-		if (dccp_sk(sk)->dccps_role == DCCP_ROLE_SERVER &&
-		    !dccp_sk(sk)->dccps_server_timewait)
-			next_state = DCCP_ACTIVE_CLOSEREQ;
-		else
-			next_state = DCCP_CLOSING;
-		fallthrough;
-	default:
-		dccp_set_state(sk, next_state);
-	}
-}
-
-void dccp_close(struct sock *sk, long timeout)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct sk_buff *skb;
-	u32 data_was_unread = 0;
-	int state;
-
-	lock_sock(sk);
-
-	sk->sk_shutdown = SHUTDOWN_MASK;
-
-	if (sk->sk_state == DCCP_LISTEN) {
-		dccp_set_state(sk, DCCP_CLOSED);
-
-		/* Special case. */
-		inet_csk_listen_stop(sk);
-
-		goto adjudge_to_death;
-	}
-
-	sk_stop_timer(sk, &dp->dccps_xmit_timer);
-
-	/*
-	 * We need to flush the recv. buffs.  We do this only on the
-	 * descriptor close, not protocol-sourced closes, because the
-	  *reader process may not have drained the data yet!
-	 */
-	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
-		data_was_unread += skb->len;
-		__kfree_skb(skb);
-	}
-
-	/* If socket has been already reset kill it. */
-	if (sk->sk_state == DCCP_CLOSED)
-		goto adjudge_to_death;
-
-	if (data_was_unread) {
-		/* Unread data was tossed, send an appropriate Reset Code */
-		DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread);
-		dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
-		dccp_set_state(sk, DCCP_CLOSED);
-	} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
-		/* Check zero linger _after_ checking for unread data. */
-		sk->sk_prot->disconnect(sk, 0);
-	} else if (sk->sk_state != DCCP_CLOSED) {
-		/*
-		 * Normal connection termination. May need to wait if there are
-		 * still packets in the TX queue that are delayed by the CCID.
-		 */
-		dccp_flush_write_queue(sk, &timeout);
-		dccp_terminate_connection(sk);
-	}
-
-	/*
-	 * Flush write queue. This may be necessary in several cases:
-	 * - we have been closed by the peer but still have application data;
-	 * - abortive termination (unread data or zero linger time),
-	 * - normal termination but queue could not be flushed within time limit
-	 */
-	__skb_queue_purge(&sk->sk_write_queue);
-
-	sk_stream_wait_close(sk, timeout);
-
-adjudge_to_death:
-	state = sk->sk_state;
-	sock_hold(sk);
-	sock_orphan(sk);
-
-	/*
-	 * It is the last release_sock in its life. It will remove backlog.
-	 */
-	release_sock(sk);
-	/*
-	 * Now socket is owned by kernel and we acquire BH lock
-	 * to finish close. No need to check for user refs.
-	 */
-	local_bh_disable();
-	bh_lock_sock(sk);
-	WARN_ON(sock_owned_by_user(sk));
-
-	this_cpu_inc(dccp_orphan_count);
-
-	/* Have we already been destroyed by a softirq or backlog? */
-	if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
-		goto out;
-
-	if (sk->sk_state == DCCP_CLOSED)
-		inet_csk_destroy_sock(sk);
-
-	/* Otherwise, socket is reprieved until protocol close. */
-
-out:
-	bh_unlock_sock(sk);
-	local_bh_enable();
-	sock_put(sk);
-}
-
-EXPORT_SYMBOL_GPL(dccp_close);
-
-void dccp_shutdown(struct sock *sk, int how)
-{
-	dccp_pr_debug("called shutdown(%x)\n", how);
-}
-
-EXPORT_SYMBOL_GPL(dccp_shutdown);
-
-static inline int __init dccp_mib_init(void)
-{
-	dccp_statistics = alloc_percpu(struct dccp_mib);
-	if (!dccp_statistics)
-		return -ENOMEM;
-	return 0;
-}
-
-static inline void dccp_mib_exit(void)
-{
-	free_percpu(dccp_statistics);
-}
-
-static int thash_entries;
-module_param(thash_entries, int, 0444);
-MODULE_PARM_DESC(thash_entries, "Number of ehash buckets");
-
-#ifdef CONFIG_IP_DCCP_DEBUG
-bool dccp_debug;
-module_param(dccp_debug, bool, 0644);
-MODULE_PARM_DESC(dccp_debug, "Enable debug messages");
-
-EXPORT_SYMBOL_GPL(dccp_debug);
-#endif
-
-static int __init dccp_init(void)
-{
-	unsigned long goal;
-	unsigned long nr_pages = totalram_pages();
-	int ehash_order, bhash_order, i;
-	int rc;
-
-	BUILD_BUG_ON(sizeof(struct dccp_skb_cb) >
-		     sizeof_field(struct sk_buff, cb));
-	rc = inet_hashinfo2_init_mod(&dccp_hashinfo);
-	if (rc)
-		goto out_fail;
-	rc = -ENOBUFS;
-	dccp_hashinfo.bind_bucket_cachep =
-		kmem_cache_create("dccp_bind_bucket",
-				  sizeof(struct inet_bind_bucket), 0,
-				  SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL);
-	if (!dccp_hashinfo.bind_bucket_cachep)
-		goto out_free_hashinfo2;
-	dccp_hashinfo.bind2_bucket_cachep =
-		kmem_cache_create("dccp_bind2_bucket",
-				  sizeof(struct inet_bind2_bucket), 0,
-				  SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL);
-	if (!dccp_hashinfo.bind2_bucket_cachep)
-		goto out_free_bind_bucket_cachep;
-
-	/*
-	 * Size and allocate the main established and bind bucket
-	 * hash tables.
-	 *
-	 * The methodology is similar to that of the buffer cache.
-	 */
-	if (nr_pages >= (128 * 1024))
-		goal = nr_pages >> (21 - PAGE_SHIFT);
-	else
-		goal = nr_pages >> (23 - PAGE_SHIFT);
-
-	if (thash_entries)
-		goal = (thash_entries *
-			sizeof(struct inet_ehash_bucket)) >> PAGE_SHIFT;
-	for (ehash_order = 0; (1UL << ehash_order) < goal; ehash_order++)
-		;
-	do {
-		unsigned long hash_size = (1UL << ehash_order) * PAGE_SIZE /
-					sizeof(struct inet_ehash_bucket);
-
-		while (hash_size & (hash_size - 1))
-			hash_size--;
-		dccp_hashinfo.ehash_mask = hash_size - 1;
-		dccp_hashinfo.ehash = (struct inet_ehash_bucket *)
-			__get_free_pages(GFP_ATOMIC|__GFP_NOWARN, ehash_order);
-	} while (!dccp_hashinfo.ehash && --ehash_order > 0);
-
-	if (!dccp_hashinfo.ehash) {
-		DCCP_CRIT("Failed to allocate DCCP established hash table");
-		goto out_free_bind2_bucket_cachep;
-	}
-
-	for (i = 0; i <= dccp_hashinfo.ehash_mask; i++)
-		INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i);
-
-	if (inet_ehash_locks_alloc(&dccp_hashinfo))
-			goto out_free_dccp_ehash;
-
-	bhash_order = ehash_order;
-
-	do {
-		dccp_hashinfo.bhash_size = (1UL << bhash_order) * PAGE_SIZE /
-					sizeof(struct inet_bind_hashbucket);
-		if ((dccp_hashinfo.bhash_size > (64 * 1024)) &&
-		    bhash_order > 0)
-			continue;
-		dccp_hashinfo.bhash = (struct inet_bind_hashbucket *)
-			__get_free_pages(GFP_ATOMIC|__GFP_NOWARN, bhash_order);
-	} while (!dccp_hashinfo.bhash && --bhash_order >= 0);
-
-	if (!dccp_hashinfo.bhash) {
-		DCCP_CRIT("Failed to allocate DCCP bind hash table");
-		goto out_free_dccp_locks;
-	}
-
-	dccp_hashinfo.bhash2 = (struct inet_bind_hashbucket *)
-		__get_free_pages(GFP_ATOMIC | __GFP_NOWARN, bhash_order);
-
-	if (!dccp_hashinfo.bhash2) {
-		DCCP_CRIT("Failed to allocate DCCP bind2 hash table");
-		goto out_free_dccp_bhash;
-	}
-
-	for (i = 0; i < dccp_hashinfo.bhash_size; i++) {
-		spin_lock_init(&dccp_hashinfo.bhash[i].lock);
-		INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain);
-		spin_lock_init(&dccp_hashinfo.bhash2[i].lock);
-		INIT_HLIST_HEAD(&dccp_hashinfo.bhash2[i].chain);
-	}
-
-	dccp_hashinfo.pernet = false;
-
-	rc = dccp_mib_init();
-	if (rc)
-		goto out_free_dccp_bhash2;
-
-	rc = dccp_ackvec_init();
-	if (rc)
-		goto out_free_dccp_mib;
-
-	rc = dccp_sysctl_init();
-	if (rc)
-		goto out_ackvec_exit;
-
-	rc = ccid_initialize_builtins();
-	if (rc)
-		goto out_sysctl_exit;
-
-	dccp_timestamping_init();
-
-	return 0;
-
-out_sysctl_exit:
-	dccp_sysctl_exit();
-out_ackvec_exit:
-	dccp_ackvec_exit();
-out_free_dccp_mib:
-	dccp_mib_exit();
-out_free_dccp_bhash2:
-	free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order);
-out_free_dccp_bhash:
-	free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order);
-out_free_dccp_locks:
-	inet_ehash_locks_free(&dccp_hashinfo);
-out_free_dccp_ehash:
-	free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
-out_free_bind2_bucket_cachep:
-	kmem_cache_destroy(dccp_hashinfo.bind2_bucket_cachep);
-out_free_bind_bucket_cachep:
-	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
-out_free_hashinfo2:
-	inet_hashinfo2_free_mod(&dccp_hashinfo);
-out_fail:
-	dccp_hashinfo.bhash = NULL;
-	dccp_hashinfo.bhash2 = NULL;
-	dccp_hashinfo.ehash = NULL;
-	dccp_hashinfo.bind_bucket_cachep = NULL;
-	dccp_hashinfo.bind2_bucket_cachep = NULL;
-	return rc;
-}
-
-static void __exit dccp_fini(void)
-{
-	int bhash_order = get_order(dccp_hashinfo.bhash_size *
-				    sizeof(struct inet_bind_hashbucket));
-
-	ccid_cleanup_builtins();
-	dccp_mib_exit();
-	free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order);
-	free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order);
-	free_pages((unsigned long)dccp_hashinfo.ehash,
-		   get_order((dccp_hashinfo.ehash_mask + 1) *
-			     sizeof(struct inet_ehash_bucket)));
-	inet_ehash_locks_free(&dccp_hashinfo);
-	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
-	dccp_ackvec_exit();
-	dccp_sysctl_exit();
-	inet_hashinfo2_free_mod(&dccp_hashinfo);
-}
-
-module_init(dccp_init);
-module_exit(dccp_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@conectiva.com.br>");
-MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol");
diff --git a/net/dccp/qpolicy.c b/net/dccp/qpolicy.c
deleted file mode 100644
index 5ba204ec0aca..000000000000
--- a/net/dccp/qpolicy.c
+++ /dev/null
@@ -1,136 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  net/dccp/qpolicy.c
- *
- *  Policy-based packet dequeueing interface for DCCP.
- *
- *  Copyright (c) 2008 Tomasz Grobelny <tomasz@grobelny.oswiecenia.net>
- */
-#include "dccp.h"
-
-/*
- *	Simple Dequeueing Policy:
- *	If tx_qlen is different from 0, enqueue up to tx_qlen elements.
- */
-static void qpolicy_simple_push(struct sock *sk, struct sk_buff *skb)
-{
-	skb_queue_tail(&sk->sk_write_queue, skb);
-}
-
-static bool qpolicy_simple_full(struct sock *sk)
-{
-	return dccp_sk(sk)->dccps_tx_qlen &&
-	       sk->sk_write_queue.qlen >= dccp_sk(sk)->dccps_tx_qlen;
-}
-
-static struct sk_buff *qpolicy_simple_top(struct sock *sk)
-{
-	return skb_peek(&sk->sk_write_queue);
-}
-
-/*
- *	Priority-based Dequeueing Policy:
- *	If tx_qlen is different from 0 and the queue has reached its upper bound
- *	of tx_qlen elements, replace older packets lowest-priority-first.
- */
-static struct sk_buff *qpolicy_prio_best_skb(struct sock *sk)
-{
-	struct sk_buff *skb, *best = NULL;
-
-	skb_queue_walk(&sk->sk_write_queue, skb)
-		if (best == NULL || skb->priority > best->priority)
-			best = skb;
-	return best;
-}
-
-static struct sk_buff *qpolicy_prio_worst_skb(struct sock *sk)
-{
-	struct sk_buff *skb, *worst = NULL;
-
-	skb_queue_walk(&sk->sk_write_queue, skb)
-		if (worst == NULL || skb->priority < worst->priority)
-			worst = skb;
-	return worst;
-}
-
-static bool qpolicy_prio_full(struct sock *sk)
-{
-	if (qpolicy_simple_full(sk))
-		dccp_qpolicy_drop(sk, qpolicy_prio_worst_skb(sk));
-	return false;
-}
-
-/**
- * struct dccp_qpolicy_operations  -  TX Packet Dequeueing Interface
- * @push: add a new @skb to the write queue
- * @full: indicates that no more packets will be admitted
- * @top:  peeks at whatever the queueing policy defines as its `top'
- * @params: parameter passed to policy operation
- */
-struct dccp_qpolicy_operations {
-	void		(*push)	(struct sock *sk, struct sk_buff *skb);
-	bool		(*full) (struct sock *sk);
-	struct sk_buff*	(*top)  (struct sock *sk);
-	__be32		params;
-};
-
-static struct dccp_qpolicy_operations qpol_table[DCCPQ_POLICY_MAX] = {
-	[DCCPQ_POLICY_SIMPLE] = {
-		.push   = qpolicy_simple_push,
-		.full   = qpolicy_simple_full,
-		.top    = qpolicy_simple_top,
-		.params = 0,
-	},
-	[DCCPQ_POLICY_PRIO] = {
-		.push   = qpolicy_simple_push,
-		.full   = qpolicy_prio_full,
-		.top    = qpolicy_prio_best_skb,
-		.params = DCCP_SCM_PRIORITY,
-	},
-};
-
-/*
- *	Externally visible interface
- */
-void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb)
-{
-	qpol_table[dccp_sk(sk)->dccps_qpolicy].push(sk, skb);
-}
-
-bool dccp_qpolicy_full(struct sock *sk)
-{
-	return qpol_table[dccp_sk(sk)->dccps_qpolicy].full(sk);
-}
-
-void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb)
-{
-	if (skb != NULL) {
-		skb_unlink(skb, &sk->sk_write_queue);
-		kfree_skb(skb);
-	}
-}
-
-struct sk_buff *dccp_qpolicy_top(struct sock *sk)
-{
-	return qpol_table[dccp_sk(sk)->dccps_qpolicy].top(sk);
-}
-
-struct sk_buff *dccp_qpolicy_pop(struct sock *sk)
-{
-	struct sk_buff *skb = dccp_qpolicy_top(sk);
-
-	if (skb != NULL) {
-		/* Clear any skb fields that we used internally */
-		skb->priority = 0;
-		skb_unlink(skb, &sk->sk_write_queue);
-	}
-	return skb;
-}
-
-bool dccp_qpolicy_param_ok(struct sock *sk, __be32 param)
-{
-	/* check if exactly one bit is set */
-	if (!param || (param & (param - 1)))
-		return false;
-	return (qpol_table[dccp_sk(sk)->dccps_qpolicy].params & param) == param;
-}
diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c
deleted file mode 100644
index b15845fd6300..000000000000
--- a/net/dccp/sysctl.c
+++ /dev/null
@@ -1,107 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  net/dccp/sysctl.c
- *
- *  An implementation of the DCCP protocol
- *  Arnaldo Carvalho de Melo <acme@mandriva.com>
- */
-
-#include <linux/mm.h>
-#include <linux/sysctl.h>
-#include "dccp.h"
-#include "feat.h"
-
-/* Boundary values */
-static int		u8_max   = 0xFF;
-static unsigned long	seqw_min = DCCPF_SEQ_WMIN,
-			seqw_max = 0xFFFFFFFF;		/* maximum on 32 bit */
-
-static struct ctl_table dccp_default_table[] = {
-	{
-		.procname	= "seq_window",
-		.data		= &sysctl_dccp_sequence_window,
-		.maxlen		= sizeof(sysctl_dccp_sequence_window),
-		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_minmax,
-		.extra1		= &seqw_min,		/* RFC 4340, 7.5.2 */
-		.extra2		= &seqw_max,
-	},
-	{
-		.procname	= "rx_ccid",
-		.data		= &sysctl_dccp_rx_ccid,
-		.maxlen		= sizeof(sysctl_dccp_rx_ccid),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= &u8_max,		/* RFC 4340, 10. */
-	},
-	{
-		.procname	= "tx_ccid",
-		.data		= &sysctl_dccp_tx_ccid,
-		.maxlen		= sizeof(sysctl_dccp_tx_ccid),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= &u8_max,		/* RFC 4340, 10. */
-	},
-	{
-		.procname	= "request_retries",
-		.data		= &sysctl_dccp_request_retries,
-		.maxlen		= sizeof(sysctl_dccp_request_retries),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ONE,
-		.extra2		= &u8_max,
-	},
-	{
-		.procname	= "retries1",
-		.data		= &sysctl_dccp_retries1,
-		.maxlen		= sizeof(sysctl_dccp_retries1),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= &u8_max,
-	},
-	{
-		.procname	= "retries2",
-		.data		= &sysctl_dccp_retries2,
-		.maxlen		= sizeof(sysctl_dccp_retries2),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= &u8_max,
-	},
-	{
-		.procname	= "tx_qlen",
-		.data		= &sysctl_dccp_tx_qlen,
-		.maxlen		= sizeof(sysctl_dccp_tx_qlen),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-	},
-	{
-		.procname	= "sync_ratelimit",
-		.data		= &sysctl_dccp_sync_ratelimit,
-		.maxlen		= sizeof(sysctl_dccp_sync_ratelimit),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_ms_jiffies,
-	},
-};
-
-static struct ctl_table_header *dccp_table_header;
-
-int __init dccp_sysctl_init(void)
-{
-	dccp_table_header = register_net_sysctl(&init_net, "net/dccp/default",
-			dccp_default_table);
-
-	return dccp_table_header != NULL ? 0 : -ENOMEM;
-}
-
-void dccp_sysctl_exit(void)
-{
-	if (dccp_table_header != NULL) {
-		unregister_net_sysctl_table(dccp_table_header);
-		dccp_table_header = NULL;
-	}
-}
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
deleted file mode 100644
index 232ac4ae0a73..000000000000
--- a/net/dccp/timer.c
+++ /dev/null
@@ -1,272 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  net/dccp/timer.c
- *
- *  An implementation of the DCCP protocol
- *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- */
-
-#include <linux/dccp.h>
-#include <linux/skbuff.h>
-#include <linux/export.h>
-
-#include "dccp.h"
-
-/* sysctl variables governing numbers of retransmission attempts */
-int  sysctl_dccp_request_retries	__read_mostly = TCP_SYN_RETRIES;
-int  sysctl_dccp_retries1		__read_mostly = TCP_RETR1;
-int  sysctl_dccp_retries2		__read_mostly = TCP_RETR2;
-
-static void dccp_write_err(struct sock *sk)
-{
-	sk->sk_err = READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT;
-	sk_error_report(sk);
-
-	dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
-	dccp_done(sk);
-	__DCCP_INC_STATS(DCCP_MIB_ABORTONTIMEOUT);
-}
-
-/* A write timeout has occurred. Process the after effects. */
-static int dccp_write_timeout(struct sock *sk)
-{
-	const struct inet_connection_sock *icsk = inet_csk(sk);
-	int retry_until;
-
-	if (sk->sk_state == DCCP_REQUESTING || sk->sk_state == DCCP_PARTOPEN) {
-		if (icsk->icsk_retransmits != 0)
-			dst_negative_advice(sk);
-		retry_until = icsk->icsk_syn_retries ?
-			    : sysctl_dccp_request_retries;
-	} else {
-		if (icsk->icsk_retransmits >= sysctl_dccp_retries1) {
-			/* NOTE. draft-ietf-tcpimpl-pmtud-01.txt requires pmtu
-			   black hole detection. :-(
-
-			   It is place to make it. It is not made. I do not want
-			   to make it. It is disguisting. It does not work in any
-			   case. Let me to cite the same draft, which requires for
-			   us to implement this:
-
-   "The one security concern raised by this memo is that ICMP black holes
-   are often caused by over-zealous security administrators who block
-   all ICMP messages.  It is vitally important that those who design and
-   deploy security systems understand the impact of strict filtering on
-   upper-layer protocols.  The safest web site in the world is worthless
-   if most TCP implementations cannot transfer data from it.  It would
-   be far nicer to have all of the black holes fixed rather than fixing
-   all of the TCP implementations."
-
-			   Golden words :-).
-		   */
-
-			dst_negative_advice(sk);
-		}
-
-		retry_until = sysctl_dccp_retries2;
-		/*
-		 * FIXME: see tcp_write_timout and tcp_out_of_resources
-		 */
-	}
-
-	if (icsk->icsk_retransmits >= retry_until) {
-		/* Has it gone just too far? */
-		dccp_write_err(sk);
-		return 1;
-	}
-	return 0;
-}
-
-/*
- *	The DCCP retransmit timer.
- */
-static void dccp_retransmit_timer(struct sock *sk)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-
-	/*
-	 * More than 4MSL (8 minutes) has passed, a RESET(aborted) was
-	 * sent, no need to retransmit, this sock is dead.
-	 */
-	if (dccp_write_timeout(sk))
-		return;
-
-	/*
-	 * We want to know the number of packets retransmitted, not the
-	 * total number of retransmissions of clones of original packets.
-	 */
-	if (icsk->icsk_retransmits == 0)
-		__DCCP_INC_STATS(DCCP_MIB_TIMEOUTS);
-
-	if (dccp_retransmit_skb(sk) != 0) {
-		/*
-		 * Retransmission failed because of local congestion,
-		 * do not backoff.
-		 */
-		if (--icsk->icsk_retransmits == 0)
-			icsk->icsk_retransmits = 1;
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-					  min(icsk->icsk_rto,
-					      TCP_RESOURCE_PROBE_INTERVAL),
-					  DCCP_RTO_MAX);
-		return;
-	}
-
-	icsk->icsk_backoff++;
-
-	icsk->icsk_rto = min(icsk->icsk_rto << 1, DCCP_RTO_MAX);
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto,
-				  DCCP_RTO_MAX);
-	if (icsk->icsk_retransmits > sysctl_dccp_retries1)
-		__sk_dst_reset(sk);
-}
-
-static void dccp_write_timer(struct timer_list *t)
-{
-	struct inet_connection_sock *icsk =
-			from_timer(icsk, t, icsk_retransmit_timer);
-	struct sock *sk = &icsk->icsk_inet.sk;
-	int event = 0;
-
-	bh_lock_sock(sk);
-	if (sock_owned_by_user(sk)) {
-		/* Try again later */
-		sk_reset_timer(sk, &icsk->icsk_retransmit_timer,
-			       jiffies + (HZ / 20));
-		goto out;
-	}
-
-	if (sk->sk_state == DCCP_CLOSED || !icsk->icsk_pending)
-		goto out;
-
-	if (time_after(icsk_timeout(icsk), jiffies)) {
-		sk_reset_timer(sk, &icsk->icsk_retransmit_timer,
-			       icsk_timeout(icsk));
-		goto out;
-	}
-
-	event = icsk->icsk_pending;
-	icsk->icsk_pending = 0;
-
-	switch (event) {
-	case ICSK_TIME_RETRANS:
-		dccp_retransmit_timer(sk);
-		break;
-	}
-out:
-	bh_unlock_sock(sk);
-	sock_put(sk);
-}
-
-static void dccp_keepalive_timer(struct timer_list *t)
-{
-	struct sock *sk = from_timer(sk, t, sk_timer);
-
-	pr_err("dccp should not use a keepalive timer !\n");
-	sock_put(sk);
-}
-
-/* This is the same as tcp_delack_timer, sans prequeue & mem_reclaim stuff */
-static void dccp_delack_timer(struct timer_list *t)
-{
-	struct inet_connection_sock *icsk =
-			from_timer(icsk, t, icsk_delack_timer);
-	struct sock *sk = &icsk->icsk_inet.sk;
-
-	bh_lock_sock(sk);
-	if (sock_owned_by_user(sk)) {
-		/* Try again later. */
-		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
-		sk_reset_timer(sk, &icsk->icsk_delack_timer,
-			       jiffies + TCP_DELACK_MIN);
-		goto out;
-	}
-
-	if (sk->sk_state == DCCP_CLOSED ||
-	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
-		goto out;
-	if (time_after(icsk_delack_timeout(icsk), jiffies)) {
-		sk_reset_timer(sk, &icsk->icsk_delack_timer,
-			       icsk_delack_timeout(icsk));
-		goto out;
-	}
-
-	icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER;
-
-	if (inet_csk_ack_scheduled(sk)) {
-		if (!inet_csk_in_pingpong_mode(sk)) {
-			/* Delayed ACK missed: inflate ATO. */
-			icsk->icsk_ack.ato = min_t(u32, icsk->icsk_ack.ato << 1,
-						   icsk->icsk_rto);
-		} else {
-			/* Delayed ACK missed: leave pingpong mode and
-			 * deflate ATO.
-			 */
-			inet_csk_exit_pingpong_mode(sk);
-			icsk->icsk_ack.ato = TCP_ATO_MIN;
-		}
-		dccp_send_ack(sk);
-		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
-	}
-out:
-	bh_unlock_sock(sk);
-	sock_put(sk);
-}
-
-/**
- * dccp_write_xmitlet  -  Workhorse for CCID packet dequeueing interface
- * @t: pointer to the tasklet associated with this handler
- *
- * See the comments above %ccid_dequeueing_decision for supported modes.
- */
-static void dccp_write_xmitlet(struct tasklet_struct *t)
-{
-	struct dccp_sock *dp = from_tasklet(dp, t, dccps_xmitlet);
-	struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
-
-	bh_lock_sock(sk);
-	if (sock_owned_by_user(sk))
-		sk_reset_timer(sk, &dccp_sk(sk)->dccps_xmit_timer, jiffies + 1);
-	else
-		dccp_write_xmit(sk);
-	bh_unlock_sock(sk);
-	sock_put(sk);
-}
-
-static void dccp_write_xmit_timer(struct timer_list *t)
-{
-	struct dccp_sock *dp = from_timer(dp, t, dccps_xmit_timer);
-
-	dccp_write_xmitlet(&dp->dccps_xmitlet);
-}
-
-void dccp_init_xmit_timers(struct sock *sk)
-{
-	struct dccp_sock *dp = dccp_sk(sk);
-
-	tasklet_setup(&dp->dccps_xmitlet, dccp_write_xmitlet);
-	timer_setup(&dp->dccps_xmit_timer, dccp_write_xmit_timer, 0);
-	inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer,
-				  &dccp_keepalive_timer);
-}
-
-static ktime_t dccp_timestamp_seed;
-/**
- * dccp_timestamp  -  10s of microseconds time source
- * Returns the number of 10s of microseconds since loading DCCP. This is native
- * DCCP time difference format (RFC 4340, sec. 13).
- * Please note: This will wrap around about circa every 11.9 hours.
- */
-u32 dccp_timestamp(void)
-{
-	u64 delta = (u64)ktime_us_delta(ktime_get_real(), dccp_timestamp_seed);
-
-	do_div(delta, 10);
-	return delta;
-}
-EXPORT_SYMBOL_GPL(dccp_timestamp);
-
-void __init dccp_timestamping_init(void)
-{
-	dccp_timestamp_seed = ktime_get_real();
-}
diff --git a/net/dccp/trace.h b/net/dccp/trace.h
deleted file mode 100644
index 5a43b3508c7f..000000000000
--- a/net/dccp/trace.h
+++ /dev/null
@@ -1,82 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM dccp
-
-#if !defined(_TRACE_DCCP_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_DCCP_H
-
-#include <net/sock.h>
-#include "dccp.h"
-#include "ccids/ccid3.h"
-#include <linux/tracepoint.h>
-#include <trace/events/net_probe_common.h>
-
-TRACE_EVENT(dccp_probe,
-
-	TP_PROTO(struct sock *sk, size_t size),
-
-	TP_ARGS(sk, size),
-
-	TP_STRUCT__entry(
-		/* sockaddr_in6 is always bigger than sockaddr_in */
-		__array(__u8, saddr, sizeof(struct sockaddr_in6))
-		__array(__u8, daddr, sizeof(struct sockaddr_in6))
-		__field(__u16, sport)
-		__field(__u16, dport)
-		__field(__u16, size)
-		__field(__u16, tx_s)
-		__field(__u32, tx_rtt)
-		__field(__u32, tx_p)
-		__field(__u32, tx_x_calc)
-		__field(__u64, tx_x_recv)
-		__field(__u64, tx_x)
-		__field(__u32, tx_t_ipi)
-	),
-
-	TP_fast_assign(
-		const struct inet_sock *inet = inet_sk(sk);
-		struct ccid3_hc_tx_sock *hc = NULL;
-
-		if (ccid_get_current_tx_ccid(dccp_sk(sk)) == DCCPC_CCID3)
-			hc = ccid3_hc_tx_sk(sk);
-
-		memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
-		memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
-
-		TP_STORE_ADDR_PORTS(__entry, inet, sk);
-
-		/* For filtering use */
-		__entry->sport = ntohs(inet->inet_sport);
-		__entry->dport = ntohs(inet->inet_dport);
-
-		__entry->size = size;
-		if (hc) {
-			__entry->tx_s = hc->tx_s;
-			__entry->tx_rtt = hc->tx_rtt;
-			__entry->tx_p = hc->tx_p;
-			__entry->tx_x_calc = hc->tx_x_calc;
-			__entry->tx_x_recv = hc->tx_x_recv >> 6;
-			__entry->tx_x = hc->tx_x >> 6;
-			__entry->tx_t_ipi = hc->tx_t_ipi;
-		} else {
-			__entry->tx_s = 0;
-			memset_startat(__entry, 0, tx_rtt);
-		}
-	),
-
-	TP_printk("src=%pISpc dest=%pISpc size=%d tx_s=%d tx_rtt=%d "
-		  "tx_p=%d tx_x_calc=%u tx_x_recv=%llu tx_x=%llu tx_t_ipi=%d",
-		  __entry->saddr, __entry->daddr, __entry->size,
-		  __entry->tx_s, __entry->tx_rtt, __entry->tx_p,
-		  __entry->tx_x_calc, __entry->tx_x_recv, __entry->tx_x,
-		  __entry->tx_t_ipi)
-);
-
-#endif /* _TRACE_TCP_H */
-
-/* This part must be outside protection */
-#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH .
-#undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_FILE trace
-#include <trace/define_trace.h>
diff --git a/net/devlink/dev.c b/net/devlink/dev.c
index d6e3db300acb..02602704bdea 100644
--- a/net/devlink/dev.c
+++ b/net/devlink/dev.c
@@ -775,7 +775,7 @@ static int devlink_info_version_put(struct devlink_info_req *req, int attr,
 		req->version_cb(version_name, version_type,
 				req->version_cb_priv);
 
-	if (!req->msg)
+	if (!req->msg || !*version_value)
 		return 0;
 
 	nest = nla_nest_start_noflag(req->msg, attr);
diff --git a/net/devlink/health.c b/net/devlink/health.c
index 57db6799722a..b3ce8ecbb7fb 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -735,7 +735,7 @@ static void devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name)
 		return;
 	}
 
-	item->nla_type = NLA_NUL_STRING;
+	item->nla_type = DEVLINK_VAR_ATTR_TYPE_NUL_STRING;
 	item->len = strlen(name) + 1;
 	item->attrtype = DEVLINK_ATTR_FMSG_OBJ_NAME;
 	memcpy(&item->value, name, item->len);
@@ -822,32 +822,37 @@ static void devlink_fmsg_put_value(struct devlink_fmsg *fmsg,
 static void devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value)
 {
 	devlink_fmsg_err_if_binary(fmsg);
-	devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG);
+	devlink_fmsg_put_value(fmsg, &value, sizeof(value),
+			       DEVLINK_VAR_ATTR_TYPE_FLAG);
 }
 
 static void devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value)
 {
 	devlink_fmsg_err_if_binary(fmsg);
-	devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8);
+	devlink_fmsg_put_value(fmsg, &value, sizeof(value),
+			       DEVLINK_VAR_ATTR_TYPE_U8);
 }
 
 void devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value)
 {
 	devlink_fmsg_err_if_binary(fmsg);
-	devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32);
+	devlink_fmsg_put_value(fmsg, &value, sizeof(value),
+			       DEVLINK_VAR_ATTR_TYPE_U32);
 }
 EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put);
 
 static void devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value)
 {
 	devlink_fmsg_err_if_binary(fmsg);
-	devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64);
+	devlink_fmsg_put_value(fmsg, &value, sizeof(value),
+			       DEVLINK_VAR_ATTR_TYPE_U64);
 }
 
 void devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value)
 {
 	devlink_fmsg_err_if_binary(fmsg);
-	devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, NLA_NUL_STRING);
+	devlink_fmsg_put_value(fmsg, value, strlen(value) + 1,
+			       DEVLINK_VAR_ATTR_TYPE_NUL_STRING);
 }
 EXPORT_SYMBOL_GPL(devlink_fmsg_string_put);
 
@@ -857,7 +862,8 @@ void devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value,
 	if (!fmsg->err && !fmsg->putting_binary)
 		fmsg->err = -EINVAL;
 
-	devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY);
+	devlink_fmsg_put_value(fmsg, value, value_len,
+			       DEVLINK_VAR_ATTR_TYPE_BINARY);
 }
 EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put);
 
@@ -928,43 +934,26 @@ void devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name,
 EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put);
 
 static int
-devlink_fmsg_item_fill_type(struct devlink_fmsg_item *msg, struct sk_buff *skb)
-{
-	switch (msg->nla_type) {
-	case NLA_FLAG:
-	case NLA_U8:
-	case NLA_U32:
-	case NLA_U64:
-	case NLA_NUL_STRING:
-	case NLA_BINARY:
-		return nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE,
-				  msg->nla_type);
-	default:
-		return -EINVAL;
-	}
-}
-
-static int
 devlink_fmsg_item_fill_data(struct devlink_fmsg_item *msg, struct sk_buff *skb)
 {
 	int attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA;
 	u8 tmp;
 
 	switch (msg->nla_type) {
-	case NLA_FLAG:
+	case DEVLINK_VAR_ATTR_TYPE_FLAG:
 		/* Always provide flag data, regardless of its value */
 		tmp = *(bool *)msg->value;
 
 		return nla_put_u8(skb, attrtype, tmp);
-	case NLA_U8:
+	case DEVLINK_VAR_ATTR_TYPE_U8:
 		return nla_put_u8(skb, attrtype, *(u8 *)msg->value);
-	case NLA_U32:
+	case DEVLINK_VAR_ATTR_TYPE_U32:
 		return nla_put_u32(skb, attrtype, *(u32 *)msg->value);
-	case NLA_U64:
+	case DEVLINK_VAR_ATTR_TYPE_U64:
 		return devlink_nl_put_u64(skb, attrtype, *(u64 *)msg->value);
-	case NLA_NUL_STRING:
+	case DEVLINK_VAR_ATTR_TYPE_NUL_STRING:
 		return nla_put_string(skb, attrtype, (char *)&msg->value);
-	case NLA_BINARY:
+	case DEVLINK_VAR_ATTR_TYPE_BINARY:
 		return nla_put(skb, attrtype, msg->len, (void *)&msg->value);
 	default:
 		return -EINVAL;
@@ -998,7 +987,8 @@ devlink_fmsg_prepare_skb(struct devlink_fmsg *fmsg, struct sk_buff *skb,
 			err = nla_put_flag(skb, item->attrtype);
 			break;
 		case DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA:
-			err = devlink_fmsg_item_fill_type(item, skb);
+			err = nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE,
+					 item->nla_type);
 			if (err)
 				break;
 			err = devlink_fmsg_item_fill_data(item, skb);
diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c
index f9786d51f68f..e340d955cf3b 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -10,6 +10,33 @@
 
 #include <uapi/linux/devlink.h>
 
+/* Sparse enums validation callbacks */
+static int
+devlink_attr_param_type_validate(const struct nlattr *attr,
+				 struct netlink_ext_ack *extack)
+{
+	switch (nla_get_u8(attr)) {
+	case DEVLINK_VAR_ATTR_TYPE_U8:
+		fallthrough;
+	case DEVLINK_VAR_ATTR_TYPE_U16:
+		fallthrough;
+	case DEVLINK_VAR_ATTR_TYPE_U32:
+		fallthrough;
+	case DEVLINK_VAR_ATTR_TYPE_U64:
+		fallthrough;
+	case DEVLINK_VAR_ATTR_TYPE_STRING:
+		fallthrough;
+	case DEVLINK_VAR_ATTR_TYPE_FLAG:
+		fallthrough;
+	case DEVLINK_VAR_ATTR_TYPE_NUL_STRING:
+		fallthrough;
+	case DEVLINK_VAR_ATTR_TYPE_BINARY:
+		return 0;
+	}
+	NL_SET_ERR_MSG_ATTR(extack, attr, "invalid enum value");
+	return -EINVAL;
+}
+
 /* Common nested types */
 const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1] = {
 	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY, },
@@ -273,7 +300,7 @@ static const struct nla_policy devlink_param_set_nl_policy[DEVLINK_ATTR_PARAM_VA
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
 	[DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING, },
-	[DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8, },
+	[DEVLINK_ATTR_PARAM_TYPE] = NLA_POLICY_VALIDATE_FN(NLA_U8, &devlink_attr_param_type_validate),
 	[DEVLINK_ATTR_PARAM_VALUE_CMODE] = NLA_POLICY_MAX(NLA_U8, 2),
 };
 
diff --git a/net/devlink/param.c b/net/devlink/param.c
index dcf0d1ccebba..b29abf8d3ed4 100644
--- a/net/devlink/param.c
+++ b/net/devlink/param.c
@@ -167,25 +167,6 @@ static int devlink_param_set(struct devlink *devlink,
 }
 
 static int
-devlink_param_type_to_nla_type(enum devlink_param_type param_type)
-{
-	switch (param_type) {
-	case DEVLINK_PARAM_TYPE_U8:
-		return NLA_U8;
-	case DEVLINK_PARAM_TYPE_U16:
-		return NLA_U16;
-	case DEVLINK_PARAM_TYPE_U32:
-		return NLA_U32;
-	case DEVLINK_PARAM_TYPE_STRING:
-		return NLA_STRING;
-	case DEVLINK_PARAM_TYPE_BOOL:
-		return NLA_FLAG;
-	default:
-		return -EINVAL;
-	}
-}
-
-static int
 devlink_nl_param_value_fill_one(struct sk_buff *msg,
 				enum devlink_param_type type,
 				enum devlink_param_cmode cmode,
@@ -247,7 +228,6 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
 	struct devlink_param_gset_ctx ctx;
 	struct nlattr *param_values_list;
 	struct nlattr *param_attr;
-	int nla_type;
 	void *hdr;
 	int err;
 	int i;
@@ -293,11 +273,7 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
 		goto param_nest_cancel;
 	if (param->generic && nla_put_flag(msg, DEVLINK_ATTR_PARAM_GENERIC))
 		goto param_nest_cancel;
-
-	nla_type = devlink_param_type_to_nla_type(param->type);
-	if (nla_type < 0)
-		goto param_nest_cancel;
-	if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, nla_type))
+	if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, param->type))
 		goto param_nest_cancel;
 
 	param_values_list = nla_nest_start_noflag(msg,
@@ -419,25 +395,7 @@ devlink_param_type_get_from_info(struct genl_info *info,
 	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_TYPE))
 		return -EINVAL;
 
-	switch (nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_TYPE])) {
-	case NLA_U8:
-		*param_type = DEVLINK_PARAM_TYPE_U8;
-		break;
-	case NLA_U16:
-		*param_type = DEVLINK_PARAM_TYPE_U16;
-		break;
-	case NLA_U32:
-		*param_type = DEVLINK_PARAM_TYPE_U32;
-		break;
-	case NLA_STRING:
-		*param_type = DEVLINK_PARAM_TYPE_STRING;
-		break;
-	case NLA_FLAG:
-		*param_type = DEVLINK_PARAM_TYPE_BOOL;
-		break;
-	default:
-		return -EINVAL;
-	}
+	*param_type = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_TYPE]);
 
 	return 0;
 }
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index e827775baf2e..436a7e1b412a 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -862,6 +862,16 @@ static void dsa_tree_teardown_lags(struct dsa_switch_tree *dst)
 	kfree(dst->lags);
 }
 
+static void dsa_tree_teardown_routing_table(struct dsa_switch_tree *dst)
+{
+	struct dsa_link *dl, *next;
+
+	list_for_each_entry_safe(dl, next, &dst->rtable, list) {
+		list_del(&dl->list);
+		kfree(dl);
+	}
+}
+
 static int dsa_tree_setup(struct dsa_switch_tree *dst)
 {
 	bool complete;
@@ -879,7 +889,7 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst)
 
 	err = dsa_tree_setup_cpu_ports(dst);
 	if (err)
-		return err;
+		goto teardown_rtable;
 
 	err = dsa_tree_setup_switches(dst);
 	if (err)
@@ -911,14 +921,14 @@ teardown_switches:
 	dsa_tree_teardown_switches(dst);
 teardown_cpu_ports:
 	dsa_tree_teardown_cpu_ports(dst);
+teardown_rtable:
+	dsa_tree_teardown_routing_table(dst);
 
 	return err;
 }
 
 static void dsa_tree_teardown(struct dsa_switch_tree *dst)
 {
-	struct dsa_link *dl, *next;
-
 	if (!dst->setup)
 		return;
 
@@ -932,10 +942,7 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst)
 
 	dsa_tree_teardown_cpu_ports(dst);
 
-	list_for_each_entry_safe(dl, next, &dst->rtable, list) {
-		list_del(&dl->list);
-		kfree(dl);
-	}
+	dsa_tree_teardown_routing_table(dst);
 
 	pr_info("DSA: tree %d torn down\n", dst->index);
 
@@ -1478,12 +1485,44 @@ static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd)
 
 static void dsa_switch_release_ports(struct dsa_switch *ds)
 {
+	struct dsa_mac_addr *a, *tmp;
 	struct dsa_port *dp, *next;
+	struct dsa_vlan *v, *n;
 
 	dsa_switch_for_each_port_safe(dp, next, ds) {
-		WARN_ON(!list_empty(&dp->fdbs));
-		WARN_ON(!list_empty(&dp->mdbs));
-		WARN_ON(!list_empty(&dp->vlans));
+		/* These are either entries that upper layers lost track of
+		 * (probably due to bugs), or installed through interfaces
+		 * where one does not necessarily have to remove them, like
+		 * ndo_dflt_fdb_add().
+		 */
+		list_for_each_entry_safe(a, tmp, &dp->fdbs, list) {
+			dev_info(ds->dev,
+				 "Cleaning up unicast address %pM vid %u from port %d\n",
+				 a->addr, a->vid, dp->index);
+			list_del(&a->list);
+			kfree(a);
+		}
+
+		list_for_each_entry_safe(a, tmp, &dp->mdbs, list) {
+			dev_info(ds->dev,
+				 "Cleaning up multicast address %pM vid %u from port %d\n",
+				 a->addr, a->vid, dp->index);
+			list_del(&a->list);
+			kfree(a);
+		}
+
+		/* These are entries that upper layers have lost track of,
+		 * probably due to bugs, but also due to dsa_port_do_vlan_del()
+		 * having failed and the VLAN entry still lingering on.
+		 */
+		list_for_each_entry_safe(v, n, &dp->vlans, list) {
+			dev_info(ds->dev,
+				 "Cleaning up vid %u from port %d\n",
+				 v->vid, dp->index);
+			list_del(&v->list);
+			kfree(v);
+		}
+
 		list_del(&dp->list);
 		kfree(dp);
 	}
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 5c9d1798e830..082573ae6864 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -116,19 +116,15 @@ static bool dsa_port_can_configure_learning(struct dsa_port *dp)
 
 bool dsa_port_supports_hwtstamp(struct dsa_port *dp)
 {
+	struct kernel_hwtstamp_config config = {};
 	struct dsa_switch *ds = dp->ds;
-	struct ifreq ifr = {};
 	int err;
 
 	if (!ds->ops->port_hwtstamp_get || !ds->ops->port_hwtstamp_set)
 		return false;
 
-	/* "See through" shim implementations of the "get" method.
-	 * Since we can't cook up a complete ioctl request structure, this will
-	 * fail in copy_to_user() with -EFAULT, which hopefully is enough to
-	 * detect a valid implementation.
-	 */
-	err = ds->ops->port_hwtstamp_get(ds, dp->index, &ifr);
+	/* "See through" shim implementations of the "get" method. */
+	err = ds->ops->port_hwtstamp_get(ds, dp->index, &config);
 	return err != -EOPNOTSUPP;
 }
 
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 3ee53e28ec2e..53e03fd8071b 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -197,7 +197,7 @@ static int dsa_port_do_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid)
 
 	err = ds->ops->tag_8021q_vlan_del(ds, port, vid);
 	if (err) {
-		refcount_inc(&v->refcount);
+		refcount_set(&v->refcount, 1);
 		return err;
 	}
 
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index c33d4bf17929..0b7564b53790 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -140,7 +140,12 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev)
 {
-	u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
+	u8 *tag;
+
+	if (skb_linearize(skb))
+		return NULL;
+
+	tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
 
 	return ksz_common_rcv(skb, dev, tag[0] & KSZ8795_TAIL_TAG_EG_PORT_M,
 			      KSZ_EGRESS_TAG_LEN);
@@ -311,10 +316,16 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
 
 static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev)
 {
-	/* Tag decoding */
-	u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
-	unsigned int port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M;
 	unsigned int len = KSZ_EGRESS_TAG_LEN;
+	unsigned int port;
+	u8 *tag;
+
+	if (skb_linearize(skb))
+		return NULL;
+
+	/* Tag decoding */
+	tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
+	port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M;
 
 	/* Extra 4-bytes PTP timestamp */
 	if (tag[0] & KSZ9477_PTP_TAG_INDICATION) {
diff --git a/net/dsa/user.c b/net/dsa/user.c
index 804dc7dac4f2..e9334520c54a 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -578,20 +578,6 @@ dsa_user_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 static int dsa_user_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct dsa_user_priv *p = netdev_priv(dev);
-	struct dsa_switch *ds = p->dp->ds;
-	int port = p->dp->index;
-
-	/* Pass through to switch driver if it supports timestamping */
-	switch (cmd) {
-	case SIOCGHWTSTAMP:
-		if (ds->ops->port_hwtstamp_get)
-			return ds->ops->port_hwtstamp_get(ds, port, ifr);
-		break;
-	case SIOCSHWTSTAMP:
-		if (ds->ops->port_hwtstamp_set)
-			return ds->ops->port_hwtstamp_set(ds, port, ifr);
-		break;
-	}
 
 	return phylink_mii_ioctl(p->dp->pl, ifr, cmd);
 }
@@ -2574,6 +2560,31 @@ static int dsa_user_fill_forward_path(struct net_device_path_ctx *ctx,
 	return 0;
 }
 
+static int dsa_user_hwtstamp_get(struct net_device *dev,
+				 struct kernel_hwtstamp_config *cfg)
+{
+	struct dsa_port *dp = dsa_user_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
+
+	if (!ds->ops->port_hwtstamp_get)
+		return -EOPNOTSUPP;
+
+	return ds->ops->port_hwtstamp_get(ds, dp->index, cfg);
+}
+
+static int dsa_user_hwtstamp_set(struct net_device *dev,
+				 struct kernel_hwtstamp_config *cfg,
+				 struct netlink_ext_ack *extack)
+{
+	struct dsa_port *dp = dsa_user_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
+
+	if (!ds->ops->port_hwtstamp_set)
+		return -EOPNOTSUPP;
+
+	return ds->ops->port_hwtstamp_set(ds, dp->index, cfg, extack);
+}
+
 static const struct net_device_ops dsa_user_netdev_ops = {
 	.ndo_open		= dsa_user_open,
 	.ndo_stop		= dsa_user_close,
@@ -2595,6 +2606,8 @@ static const struct net_device_ops dsa_user_netdev_ops = {
 	.ndo_vlan_rx_kill_vid	= dsa_user_vlan_rx_kill_vid,
 	.ndo_change_mtu		= dsa_user_change_mtu,
 	.ndo_fill_forward_path	= dsa_user_fill_forward_path,
+	.ndo_hwtstamp_get	= dsa_user_hwtstamp_get,
+	.ndo_hwtstamp_set	= dsa_user_hwtstamp_set,
 };
 
 static const struct device_type dsa_type = {
diff --git a/net/ethtool/cmis_cdb.c b/net/ethtool/cmis_cdb.c
index 0e2691ccb0df..3057576bc81e 100644
--- a/net/ethtool/cmis_cdb.c
+++ b/net/ethtool/cmis_cdb.c
@@ -351,7 +351,7 @@ ethtool_cmis_module_poll(struct net_device *dev,
 	struct netlink_ext_ack extack = {};
 	int err;
 
-	ethtool_cmis_page_init(&page_data, 0, offset, sizeof(rpl));
+	ethtool_cmis_page_init(&page_data, 0, offset, sizeof(*rpl));
 	page_data.data = (u8 *)rpl;
 
 	err = ops->get_module_eeprom_by_page(dev, &page_data, &extack);
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 49bea6b45bd5..eb253e0fd61b 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -921,9 +921,18 @@ int ethtool_get_ts_info_by_phc(struct net_device *dev,
 
 		phy = ethtool_phy_get_ts_info_by_phc(dev, info, hwprov_desc);
 		if (IS_ERR(phy))
-			err = PTR_ERR(phy);
-		else
-			err = 0;
+			return PTR_ERR(phy);
+
+		/* Report the phc source only if we have a real
+		 * phc source with an index.
+		 */
+		if (info->phc_index >= 0) {
+			info->phc_source = HWTSTAMP_SOURCE_PHYLIB;
+			info->phc_phyindex = phy->phyindex;
+		}
+		err = 0;
+	} else if (!err && info->phc_index >= 0) {
+		info->phc_source = HWTSTAMP_SOURCE_NETDEV;
 	}
 
 	info->so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE |
@@ -947,10 +956,20 @@ int __ethtool_get_ts_info(struct net_device *dev,
 
 		ethtool_init_tsinfo(info);
 		if (phy_is_default_hwtstamp(phydev) &&
-		    phy_has_tsinfo(phydev))
+		    phy_has_tsinfo(phydev)) {
 			err = phy_ts_info(phydev, info);
-		else if (ops->get_ts_info)
+			/* Report the phc source only if we have a real
+			 * phc source with an index.
+			 */
+			if (!err && info->phc_index >= 0) {
+				info->phc_source = HWTSTAMP_SOURCE_PHYLIB;
+				info->phc_phyindex = phydev->phyindex;
+			}
+		} else if (ops->get_ts_info) {
 			err = ops->get_ts_info(dev, info);
+			if (!err && info->phc_index >= 0)
+				info->phc_source = HWTSTAMP_SOURCE_NETDEV;
+		}
 
 		info->so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE |
 					 SOF_TIMESTAMPING_SOFTWARE;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 8262cc10f98d..39ec920f5de7 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -978,6 +978,88 @@ static int ethtool_rxnfc_copy_to_user(void __user *useraddr,
 	return 0;
 }
 
+static bool flow_type_hashable(u32 flow_type)
+{
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case AH_ESP_V4_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case AH_ESP_V6_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case IPV4_FLOW:
+	case IPV6_FLOW:
+	case GTPU_V4_FLOW:
+	case GTPU_V6_FLOW:
+	case GTPC_V4_FLOW:
+	case GTPC_V6_FLOW:
+	case GTPC_TEID_V4_FLOW:
+	case GTPC_TEID_V6_FLOW:
+	case GTPU_EH_V4_FLOW:
+	case GTPU_EH_V6_FLOW:
+	case GTPU_UL_V4_FLOW:
+	case GTPU_UL_V6_FLOW:
+	case GTPU_DL_V4_FLOW:
+	case GTPU_DL_V6_FLOW:
+		return true;
+	}
+
+	return false;
+}
+
+/* When adding a new type, update the assert and, if it's hashable, add it to
+ * the flow_type_hashable switch case.
+ */
+static_assert(GTPU_DL_V6_FLOW + 1 == __FLOW_TYPE_COUNT);
+
+static int ethtool_check_xfrm_rxfh(u32 input_xfrm, u64 rxfh)
+{
+	/* Sanity check: if symmetric-xor/symmetric-or-xor is set, then:
+	 * 1 - no other fields besides IP src/dst and/or L4 src/dst are set
+	 * 2 - If src is set, dst must also be set
+	 */
+	if ((input_xfrm != RXH_XFRM_NO_CHANGE &&
+	     input_xfrm & (RXH_XFRM_SYM_XOR | RXH_XFRM_SYM_OR_XOR)) &&
+	    ((rxfh & ~(RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3)) ||
+	     (!!(rxfh & RXH_IP_SRC) ^ !!(rxfh & RXH_IP_DST)) ||
+	     (!!(rxfh & RXH_L4_B_0_1) ^ !!(rxfh & RXH_L4_B_2_3))))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ethtool_check_flow_types(struct net_device *dev, u32 input_xfrm)
+{
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rxnfc info = {
+		.cmd = ETHTOOL_GRXFH,
+	};
+	int err;
+	u32 i;
+
+	for (i = 0; i < __FLOW_TYPE_COUNT; i++) {
+		if (!flow_type_hashable(i))
+			continue;
+
+		info.flow_type = i;
+		err = ops->get_rxnfc(dev, &info, NULL);
+		if (err)
+			continue;
+
+		err = ethtool_check_xfrm_rxfh(input_xfrm, info.data);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 						u32 cmd, void __user *useraddr)
 {
@@ -1012,16 +1094,9 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 		if (rc)
 			return rc;
 
-		/* Sanity check: if symmetric-xor/symmetric-or-xor is set, then:
-		 * 1 - no other fields besides IP src/dst and/or L4 src/dst
-		 * 2 - If src is set, dst must also be set
-		 */
-		if ((rxfh.input_xfrm & (RXH_XFRM_SYM_XOR | RXH_XFRM_SYM_OR_XOR)) &&
-		    ((info.data & ~(RXH_IP_SRC | RXH_IP_DST |
-				    RXH_L4_B_0_1 | RXH_L4_B_2_3)) ||
-		     (!!(info.data & RXH_IP_SRC) ^ !!(info.data & RXH_IP_DST)) ||
-		     (!!(info.data & RXH_L4_B_0_1) ^ !!(info.data & RXH_L4_B_2_3))))
-			return -EINVAL;
+		rc = ethtool_check_xfrm_rxfh(rxfh.input_xfrm, info.data);
+		if (rc)
+			return rc;
 	}
 
 	rc = ops->set_rxnfc(dev, &info);
@@ -1413,6 +1488,10 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	     rxfh.input_xfrm == RXH_XFRM_NO_CHANGE))
 		return -EINVAL;
 
+	ret = ethtool_check_flow_types(dev, rxfh.input_xfrm);
+	if (ret)
+		return ret;
+
 	indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]);
 
 	/* Check settings which may be global rather than per RSS-context */
diff --git a/net/ethtool/mm.c b/net/ethtool/mm.c
index 2816bb23c3ad..ad9b40034003 100644
--- a/net/ethtool/mm.c
+++ b/net/ethtool/mm.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright 2022-2023 NXP
+ * Copyright 2022-2025 NXP
+ * Copyright 2024 Furong Xu <0x1207@gmail.com>
  */
 #include "common.h"
 #include "netlink.h"
@@ -282,3 +283,279 @@ bool ethtool_dev_mm_supported(struct net_device *dev)
 	return supported;
 }
 EXPORT_SYMBOL_GPL(ethtool_dev_mm_supported);
+
+static void ethtool_mmsv_configure_tx(struct ethtool_mmsv *mmsv,
+				      bool tx_active)
+{
+	if (mmsv->ops->configure_tx)
+		mmsv->ops->configure_tx(mmsv, tx_active);
+}
+
+static void ethtool_mmsv_configure_pmac(struct ethtool_mmsv *mmsv,
+					bool pmac_enabled)
+{
+	if (mmsv->ops->configure_pmac)
+		mmsv->ops->configure_pmac(mmsv, pmac_enabled);
+}
+
+static void ethtool_mmsv_send_mpacket(struct ethtool_mmsv *mmsv,
+				      enum ethtool_mpacket mpacket)
+{
+	if (mmsv->ops->send_mpacket)
+		mmsv->ops->send_mpacket(mmsv, mpacket);
+}
+
+/**
+ * ethtool_mmsv_verify_timer - Timer for MAC Merge verification
+ * @t: timer_list struct containing private info
+ *
+ * Verify the MAC Merge capability in the local TX direction, by
+ * transmitting Verify mPackets up to 3 times. Wait until link
+ * partner responds with a Response mPacket, otherwise fail.
+ */
+static void ethtool_mmsv_verify_timer(struct timer_list *t)
+{
+	struct ethtool_mmsv *mmsv = from_timer(mmsv, t, verify_timer);
+	unsigned long flags;
+	bool rearm = false;
+
+	spin_lock_irqsave(&mmsv->lock, flags);
+
+	switch (mmsv->status) {
+	case ETHTOOL_MM_VERIFY_STATUS_INITIAL:
+	case ETHTOOL_MM_VERIFY_STATUS_VERIFYING:
+		if (mmsv->verify_retries != 0) {
+			ethtool_mmsv_send_mpacket(mmsv, ETHTOOL_MPACKET_VERIFY);
+			rearm = true;
+		} else {
+			mmsv->status = ETHTOOL_MM_VERIFY_STATUS_FAILED;
+		}
+
+		mmsv->verify_retries--;
+		break;
+
+	case ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED:
+		ethtool_mmsv_configure_tx(mmsv, true);
+		break;
+
+	default:
+		break;
+	}
+
+	if (rearm) {
+		mod_timer(&mmsv->verify_timer,
+			  jiffies + msecs_to_jiffies(mmsv->verify_time));
+	}
+
+	spin_unlock_irqrestore(&mmsv->lock, flags);
+}
+
+static void ethtool_mmsv_verify_timer_arm(struct ethtool_mmsv *mmsv)
+{
+	if (mmsv->pmac_enabled && mmsv->tx_enabled && mmsv->verify_enabled &&
+	    mmsv->status != ETHTOOL_MM_VERIFY_STATUS_FAILED &&
+	    mmsv->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED) {
+		timer_setup(&mmsv->verify_timer, ethtool_mmsv_verify_timer, 0);
+		mod_timer(&mmsv->verify_timer, jiffies);
+	}
+}
+
+static void ethtool_mmsv_apply(struct ethtool_mmsv *mmsv)
+{
+	/* If verification is disabled, configure FPE right away.
+	 * Otherwise let the timer code do it.
+	 */
+	if (!mmsv->verify_enabled) {
+		ethtool_mmsv_configure_pmac(mmsv, mmsv->pmac_enabled);
+		ethtool_mmsv_configure_tx(mmsv, mmsv->tx_enabled);
+	} else {
+		mmsv->status = ETHTOOL_MM_VERIFY_STATUS_INITIAL;
+		mmsv->verify_retries = ETHTOOL_MM_MAX_VERIFY_RETRIES;
+
+		if (netif_running(mmsv->dev))
+			ethtool_mmsv_verify_timer_arm(mmsv);
+	}
+}
+
+/**
+ * ethtool_mmsv_stop() - Stop MAC Merge Software Verification
+ * @mmsv: MAC Merge Software Verification state
+ *
+ * Drivers should call this method in a state where the hardware is
+ * about to lose state, like ndo_stop() or suspend(), and turning off
+ * MAC Merge features would be superfluous. Otherwise, prefer
+ * ethtool_mmsv_link_state_handle() with up=false.
+ */
+void ethtool_mmsv_stop(struct ethtool_mmsv *mmsv)
+{
+	timer_shutdown_sync(&mmsv->verify_timer);
+}
+EXPORT_SYMBOL_GPL(ethtool_mmsv_stop);
+
+/**
+ * ethtool_mmsv_link_state_handle() - Inform MAC Merge Software Verification
+ *				      of link state changes
+ * @mmsv: MAC Merge Software Verification state
+ * @up: True if device carrier is up and able to pass verification packets
+ *
+ * Calling context is expected to be from a task, interrupts enabled.
+ */
+void ethtool_mmsv_link_state_handle(struct ethtool_mmsv *mmsv, bool up)
+{
+	unsigned long flags;
+
+	ethtool_mmsv_stop(mmsv);
+
+	spin_lock_irqsave(&mmsv->lock, flags);
+
+	if (up && mmsv->pmac_enabled) {
+		/* VERIFY process requires pMAC enabled when NIC comes up */
+		ethtool_mmsv_configure_pmac(mmsv, true);
+
+		/* New link => maybe new partner => new verification process */
+		ethtool_mmsv_apply(mmsv);
+	} else {
+		/* Reset the reported verification state while the link is down */
+		if (mmsv->verify_enabled)
+			mmsv->status = ETHTOOL_MM_VERIFY_STATUS_INITIAL;
+
+		/* No link or pMAC not enabled */
+		ethtool_mmsv_configure_pmac(mmsv, false);
+		ethtool_mmsv_configure_tx(mmsv, false);
+	}
+
+	spin_unlock_irqrestore(&mmsv->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ethtool_mmsv_link_state_handle);
+
+/**
+ * ethtool_mmsv_event_handle() - Inform MAC Merge Software Verification
+ *				 of interrupt-based events
+ * @mmsv: MAC Merge Software Verification state
+ * @event: Event which took place (packet transmission or reception)
+ *
+ * Calling context expects to have interrupts disabled.
+ */
+void ethtool_mmsv_event_handle(struct ethtool_mmsv *mmsv,
+			       enum ethtool_mmsv_event event)
+{
+	/* This is interrupt context, just spin_lock() */
+	spin_lock(&mmsv->lock);
+
+	if (!mmsv->pmac_enabled)
+		goto unlock;
+
+	switch (event) {
+	case ETHTOOL_MMSV_LP_SENT_VERIFY_MPACKET:
+		/* Link partner has sent verify mPacket */
+		ethtool_mmsv_send_mpacket(mmsv, ETHTOOL_MPACKET_RESPONSE);
+		break;
+	case ETHTOOL_MMSV_LD_SENT_VERIFY_MPACKET:
+		/* Local device has sent verify mPacket */
+		if (mmsv->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED)
+			mmsv->status = ETHTOOL_MM_VERIFY_STATUS_VERIFYING;
+		break;
+	case ETHTOOL_MMSV_LP_SENT_RESPONSE_MPACKET:
+		/* Link partner has sent response mPacket */
+		if (mmsv->status == ETHTOOL_MM_VERIFY_STATUS_VERIFYING)
+			mmsv->status = ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED;
+		break;
+	}
+
+unlock:
+	spin_unlock(&mmsv->lock);
+}
+EXPORT_SYMBOL_GPL(ethtool_mmsv_event_handle);
+
+static bool ethtool_mmsv_is_tx_active(struct ethtool_mmsv *mmsv)
+{
+	/* TX is active if administratively enabled, and verification either
+	 * succeeded, or was administratively disabled.
+	 */
+	return mmsv->tx_enabled &&
+	       (mmsv->status == ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED ||
+	       mmsv->status == ETHTOOL_MM_VERIFY_STATUS_DISABLED);
+}
+
+/**
+ * ethtool_mmsv_get_mm() - get_mm() hook for MAC Merge Software Verification
+ * @mmsv: MAC Merge Software Verification state
+ * @state: see struct ethtool_mm_state
+ *
+ * Drivers are expected to call this from their ethtool_ops :: get_mm()
+ * method.
+ */
+void ethtool_mmsv_get_mm(struct ethtool_mmsv *mmsv,
+			 struct ethtool_mm_state *state)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&mmsv->lock, flags);
+
+	state->max_verify_time = ETHTOOL_MM_MAX_VERIFY_TIME_MS;
+	state->verify_enabled = mmsv->verify_enabled;
+	state->pmac_enabled = mmsv->pmac_enabled;
+	state->verify_time = mmsv->verify_time;
+	state->tx_enabled = mmsv->tx_enabled;
+	state->verify_status = mmsv->status;
+	state->tx_active = ethtool_mmsv_is_tx_active(mmsv);
+
+	spin_unlock_irqrestore(&mmsv->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ethtool_mmsv_get_mm);
+
+/**
+ * ethtool_mmsv_set_mm() - set_mm() hook for MAC Merge Software Verification
+ * @mmsv: MAC Merge Software Verification state
+ * @cfg: see struct ethtool_mm_cfg
+ *
+ * Drivers are expected to call this from their ethtool_ops :: set_mm()
+ * method.
+ */
+void ethtool_mmsv_set_mm(struct ethtool_mmsv *mmsv, struct ethtool_mm_cfg *cfg)
+{
+	unsigned long flags;
+
+	/* Wait for the verification that's currently in progress to finish */
+	ethtool_mmsv_stop(mmsv);
+
+	spin_lock_irqsave(&mmsv->lock, flags);
+
+	mmsv->verify_enabled = cfg->verify_enabled;
+	mmsv->pmac_enabled = cfg->pmac_enabled;
+	mmsv->verify_time = cfg->verify_time;
+	mmsv->tx_enabled = cfg->tx_enabled;
+
+	if (!cfg->verify_enabled)
+		mmsv->status = ETHTOOL_MM_VERIFY_STATUS_DISABLED;
+
+	ethtool_mmsv_apply(mmsv);
+
+	spin_unlock_irqrestore(&mmsv->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ethtool_mmsv_set_mm);
+
+/**
+ * ethtool_mmsv_init() - Initialize MAC Merge Software Verification state
+ * @mmsv: MAC Merge Software Verification state
+ * @dev: Pointer to network interface
+ * @ops: Methods for implementing the generic functionality
+ *
+ * The MAC Merge Software Verification is a timer- and event-based state
+ * machine intended for network interfaces which lack a hardware-based
+ * TX verification process (as per IEEE 802.3 clause 99.4.3). The timer
+ * is managed by the core code, whereas events are supplied by the
+ * driver explicitly calling one of the other API functions.
+ */
+void ethtool_mmsv_init(struct ethtool_mmsv *mmsv, struct net_device *dev,
+		       const struct ethtool_mmsv_ops *ops)
+{
+	mmsv->ops = ops;
+	mmsv->dev = dev;
+	mmsv->verify_retries = ETHTOOL_MM_MAX_VERIFY_RETRIES;
+	mmsv->verify_time = ETHTOOL_MM_MAX_VERIFY_TIME_MS;
+	mmsv->status = ETHTOOL_MM_VERIFY_STATUS_DISABLED;
+	timer_setup(&mmsv->verify_timer, ethtool_mmsv_verify_timer, 0);
+	spin_lock_init(&mmsv->lock);
+}
+EXPORT_SYMBOL_GPL(ethtool_mmsv_init);
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 977beeaaa2f9..9de828df46cd 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -357,6 +357,18 @@ struct ethnl_dump_ctx {
 	unsigned long			pos_ifindex;
 };
 
+/**
+ * struct ethnl_perphy_dump_ctx - context for dumpit() PHY-aware callbacks
+ * @ethnl_ctx: generic ethnl context
+ * @ifindex: For Filtered DUMP requests, the ifindex of the targeted netdev
+ * @pos_phyindex: iterator position for multi-msg DUMP
+ */
+struct ethnl_perphy_dump_ctx {
+	struct ethnl_dump_ctx	ethnl_ctx;
+	unsigned int		ifindex;
+	unsigned long		pos_phyindex;
+};
+
 static const struct ethnl_request_ops *
 ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = {
 	[ETHTOOL_MSG_STRSET_GET]	= &ethnl_strset_request_ops,
@@ -400,6 +412,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = {
 	[ETHTOOL_MSG_MM_SET]		= &ethnl_mm_request_ops,
 	[ETHTOOL_MSG_TSCONFIG_GET]	= &ethnl_tsconfig_request_ops,
 	[ETHTOOL_MSG_TSCONFIG_SET]	= &ethnl_tsconfig_request_ops,
+	[ETHTOOL_MSG_PHY_GET]		= &ethnl_phy_request_ops,
 };
 
 static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
@@ -407,6 +420,12 @@ static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
 	return (struct ethnl_dump_ctx *)cb->ctx;
 }
 
+static struct ethnl_perphy_dump_ctx *
+ethnl_perphy_dump_context(struct netlink_callback *cb)
+{
+	return (struct ethnl_perphy_dump_ctx *)cb->ctx;
+}
+
 /**
  * ethnl_default_parse() - Parse request message
  * @req_info:    pointer to structure to put data into
@@ -584,18 +603,19 @@ static int ethnl_default_dumpit(struct sk_buff *skb,
 {
 	struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb);
 	struct net *net = sock_net(skb->sk);
+	netdevice_tracker dev_tracker;
 	struct net_device *dev;
 	int ret = 0;
 
 	rcu_read_lock();
 	for_each_netdev_dump(net, dev, ctx->pos_ifindex) {
-		dev_hold(dev);
+		netdev_hold(dev, &dev_tracker, GFP_ATOMIC);
 		rcu_read_unlock();
 
 		ret = ethnl_default_dump_one(skb, dev, ctx, genl_info_dump(cb));
 
 		rcu_read_lock();
-		dev_put(dev);
+		netdev_put(dev, &dev_tracker);
 
 		if (ret < 0 && ret != -EOPNOTSUPP) {
 			if (likely(skb->len))
@@ -662,6 +682,173 @@ free_req_info:
 	return ret;
 }
 
+/* per-PHY ->start() handler for GET requests */
+static int ethnl_perphy_start(struct netlink_callback *cb)
+{
+	struct ethnl_perphy_dump_ctx *phy_ctx = ethnl_perphy_dump_context(cb);
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	struct ethnl_dump_ctx *ctx = &phy_ctx->ethnl_ctx;
+	struct ethnl_reply_data *reply_data;
+	const struct ethnl_request_ops *ops;
+	struct ethnl_req_info *req_info;
+	struct genlmsghdr *ghdr;
+	int ret;
+
+	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
+
+	ghdr = nlmsg_data(cb->nlh);
+	ops = ethnl_default_requests[ghdr->cmd];
+	if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", ghdr->cmd))
+		return -EOPNOTSUPP;
+	req_info = kzalloc(ops->req_info_size, GFP_KERNEL);
+	if (!req_info)
+		return -ENOMEM;
+	reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL);
+	if (!reply_data) {
+		ret = -ENOMEM;
+		goto free_req_info;
+	}
+
+	/* Unlike per-dev dump, don't ignore dev. The dump handler
+	 * will notice it and dump PHYs from given dev. We only keep track of
+	 * the dev's ifindex, .dumpit() will grab and release the netdev itself.
+	 */
+	ret = ethnl_default_parse(req_info, &info->info, ops, false);
+	if (req_info->dev) {
+		phy_ctx->ifindex = req_info->dev->ifindex;
+		netdev_put(req_info->dev, &req_info->dev_tracker);
+		req_info->dev = NULL;
+	}
+	if (ret < 0)
+		goto free_reply_data;
+
+	ctx->ops = ops;
+	ctx->req_info = req_info;
+	ctx->reply_data = reply_data;
+	ctx->pos_ifindex = 0;
+
+	return 0;
+
+free_reply_data:
+	kfree(reply_data);
+free_req_info:
+	kfree(req_info);
+
+	return ret;
+}
+
+static int ethnl_perphy_dump_one_dev(struct sk_buff *skb,
+				     struct ethnl_perphy_dump_ctx *ctx,
+				     const struct genl_info *info)
+{
+	struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx;
+	struct net_device *dev = ethnl_ctx->req_info->dev;
+	struct phy_device_node *pdn;
+	int ret;
+
+	if (!dev->link_topo)
+		return 0;
+
+	xa_for_each_start(&dev->link_topo->phys, ctx->pos_phyindex, pdn,
+			  ctx->pos_phyindex) {
+		ethnl_ctx->req_info->phy_index = ctx->pos_phyindex;
+
+		/* We can re-use the original dump_one as ->prepare_data in
+		 * commands use ethnl_req_get_phydev(), which gets the PHY from
+		 * the req_info->phy_index
+		 */
+		ret = ethnl_default_dump_one(skb, dev, ethnl_ctx, info);
+		if (ret)
+			return ret;
+	}
+
+	ctx->pos_phyindex = 0;
+
+	return 0;
+}
+
+static int ethnl_perphy_dump_all_dev(struct sk_buff *skb,
+				     struct ethnl_perphy_dump_ctx *ctx,
+				     const struct genl_info *info)
+{
+	struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx;
+	struct net *net = sock_net(skb->sk);
+	netdevice_tracker dev_tracker;
+	struct net_device *dev;
+	int ret = 0;
+
+	rcu_read_lock();
+	for_each_netdev_dump(net, dev, ethnl_ctx->pos_ifindex) {
+		netdev_hold(dev, &dev_tracker, GFP_ATOMIC);
+		rcu_read_unlock();
+
+		/* per-PHY commands use ethnl_req_get_phydev(), which needs the
+		 * net_device in the req_info
+		 */
+		ethnl_ctx->req_info->dev = dev;
+		ret = ethnl_perphy_dump_one_dev(skb, ctx, info);
+
+		rcu_read_lock();
+		netdev_put(dev, &dev_tracker);
+		ethnl_ctx->req_info->dev = NULL;
+
+		if (ret < 0 && ret != -EOPNOTSUPP) {
+			if (likely(skb->len))
+				ret = skb->len;
+			break;
+		}
+		ret = 0;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/* per-PHY ->dumpit() handler for GET requests. */
+static int ethnl_perphy_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb)
+{
+	struct ethnl_perphy_dump_ctx *ctx = ethnl_perphy_dump_context(cb);
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx;
+	int ret = 0;
+
+	if (ctx->ifindex) {
+		netdevice_tracker dev_tracker;
+		struct net_device *dev;
+
+		dev = netdev_get_by_index(genl_info_net(&info->info),
+					  ctx->ifindex, &dev_tracker,
+					  GFP_KERNEL);
+		if (!dev)
+			return -ENODEV;
+
+		ethnl_ctx->req_info->dev = dev;
+		ret = ethnl_perphy_dump_one_dev(skb, ctx, genl_info_dump(cb));
+
+		if (ret < 0 && ret != -EOPNOTSUPP && likely(skb->len))
+			ret = skb->len;
+
+		netdev_put(dev, &dev_tracker);
+	} else {
+		ret = ethnl_perphy_dump_all_dev(skb, ctx, genl_info_dump(cb));
+	}
+
+	return ret;
+}
+
+/* per-PHY ->done() handler for GET requests */
+static int ethnl_perphy_done(struct netlink_callback *cb)
+{
+	struct ethnl_perphy_dump_ctx *ctx = ethnl_perphy_dump_context(cb);
+	struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx;
+
+	kfree(ethnl_ctx->reply_data);
+	kfree(ethnl_ctx->req_info);
+
+	return 0;
+}
+
 /* default ->done() handler for GET requests */
 static int ethnl_default_done(struct netlink_callback *cb)
 {
@@ -1200,9 +1387,9 @@ static const struct genl_ops ethtool_genl_ops[] = {
 	{
 		.cmd	= ETHTOOL_MSG_PSE_GET,
 		.doit	= ethnl_default_doit,
-		.start	= ethnl_default_start,
-		.dumpit	= ethnl_default_dumpit,
-		.done	= ethnl_default_done,
+		.start	= ethnl_perphy_start,
+		.dumpit	= ethnl_perphy_dumpit,
+		.done	= ethnl_perphy_done,
 		.policy = ethnl_pse_get_policy,
 		.maxattr = ARRAY_SIZE(ethnl_pse_get_policy) - 1,
 	},
@@ -1224,9 +1411,9 @@ static const struct genl_ops ethtool_genl_ops[] = {
 	{
 		.cmd	= ETHTOOL_MSG_PLCA_GET_CFG,
 		.doit	= ethnl_default_doit,
-		.start	= ethnl_default_start,
-		.dumpit	= ethnl_default_dumpit,
-		.done	= ethnl_default_done,
+		.start	= ethnl_perphy_start,
+		.dumpit	= ethnl_perphy_dumpit,
+		.done	= ethnl_perphy_done,
 		.policy = ethnl_plca_get_cfg_policy,
 		.maxattr = ARRAY_SIZE(ethnl_plca_get_cfg_policy) - 1,
 	},
@@ -1240,9 +1427,9 @@ static const struct genl_ops ethtool_genl_ops[] = {
 	{
 		.cmd	= ETHTOOL_MSG_PLCA_GET_STATUS,
 		.doit	= ethnl_default_doit,
-		.start	= ethnl_default_start,
-		.dumpit	= ethnl_default_dumpit,
-		.done	= ethnl_default_done,
+		.start	= ethnl_perphy_start,
+		.dumpit	= ethnl_perphy_dumpit,
+		.done	= ethnl_perphy_done,
 		.policy = ethnl_plca_get_status_policy,
 		.maxattr = ARRAY_SIZE(ethnl_plca_get_status_policy) - 1,
 	},
@@ -1271,10 +1458,10 @@ static const struct genl_ops ethtool_genl_ops[] = {
 	},
 	{
 		.cmd	= ETHTOOL_MSG_PHY_GET,
-		.doit	= ethnl_phy_doit,
-		.start	= ethnl_phy_start,
-		.dumpit	= ethnl_phy_dumpit,
-		.done	= ethnl_phy_done,
+		.doit	= ethnl_default_doit,
+		.start	= ethnl_perphy_start,
+		.dumpit	= ethnl_perphy_dumpit,
+		.done	= ethnl_perphy_done,
 		.policy = ethnl_phy_get_policy,
 		.maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1,
 	},
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index ec6ab5443a6f..91b953924af3 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -499,10 +499,6 @@ int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info);
 int ethnl_rss_dump_start(struct netlink_callback *cb);
 int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
-int ethnl_phy_start(struct netlink_callback *cb);
-int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info);
-int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
-int ethnl_phy_done(struct netlink_callback *cb);
 int ethnl_tsinfo_start(struct netlink_callback *cb);
 int ethnl_tsinfo_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int ethnl_tsinfo_done(struct netlink_callback *cb);
diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
index 1f590e8d75ed..68372bef4b2f 100644
--- a/net/ethtool/phy.c
+++ b/net/ethtool/phy.c
@@ -12,304 +12,154 @@
 #include <net/netdev_lock.h>
 
 struct phy_req_info {
-	struct ethnl_req_info		base;
-	struct phy_device_node		*pdn;
+	struct ethnl_req_info base;
 };
 
-#define PHY_REQINFO(__req_base) \
-	container_of(__req_base, struct phy_req_info, base)
+struct phy_reply_data {
+	struct ethnl_reply_data	base;
+	u32 phyindex;
+	char *drvname;
+	char *name;
+	unsigned int upstream_type;
+	char *upstream_sfp_name;
+	unsigned int upstream_index;
+	char *downstream_sfp_name;
+};
+
+#define PHY_REPDATA(__reply_base) \
+	container_of(__reply_base, struct phy_reply_data, base)
 
 const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = {
 	[ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
-/* Caller holds rtnl */
-static ssize_t
-ethnl_phy_reply_size(const struct ethnl_req_info *req_base,
-		     struct netlink_ext_ack *extack)
+static int phy_reply_size(const struct ethnl_req_info *req_info,
+			  const struct ethnl_reply_data *reply_data)
 {
-	struct phy_req_info *req_info = PHY_REQINFO(req_base);
-	struct phy_device_node *pdn = req_info->pdn;
-	struct phy_device *phydev = pdn->phy;
+	struct phy_reply_data *rep_data = PHY_REPDATA(reply_data);
 	size_t size = 0;
 
-	ASSERT_RTNL();
-
 	/* ETHTOOL_A_PHY_INDEX */
 	size += nla_total_size(sizeof(u32));
 
 	/* ETHTOOL_A_DRVNAME */
-	if (phydev->drv)
-		size += nla_total_size(strlen(phydev->drv->name) + 1);
+	if (rep_data->drvname)
+		size += nla_total_size(strlen(rep_data->drvname) + 1);
 
 	/* ETHTOOL_A_NAME */
-	size += nla_total_size(strlen(dev_name(&phydev->mdio.dev)) + 1);
+	size += nla_total_size(strlen(rep_data->name) + 1);
 
 	/* ETHTOOL_A_PHY_UPSTREAM_TYPE */
 	size += nla_total_size(sizeof(u32));
 
-	if (phy_on_sfp(phydev)) {
-		const char *upstream_sfp_name = sfp_get_name(pdn->parent_sfp_bus);
-
-		/* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */
-		if (upstream_sfp_name)
-			size += nla_total_size(strlen(upstream_sfp_name) + 1);
+	/* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */
+	if (rep_data->upstream_sfp_name)
+		size += nla_total_size(strlen(rep_data->upstream_sfp_name) + 1);
 
-		/* ETHTOOL_A_PHY_UPSTREAM_INDEX */
+	/* ETHTOOL_A_PHY_UPSTREAM_INDEX */
+	if (rep_data->upstream_index)
 		size += nla_total_size(sizeof(u32));
-	}
 
 	/* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */
-	if (phydev->sfp_bus) {
-		const char *sfp_name = sfp_get_name(phydev->sfp_bus);
-
-		if (sfp_name)
-			size += nla_total_size(strlen(sfp_name) + 1);
-	}
+	if (rep_data->downstream_sfp_name)
+		size += nla_total_size(strlen(rep_data->downstream_sfp_name) + 1);
 
 	return size;
 }
 
-static int
-ethnl_phy_fill_reply(const struct ethnl_req_info *req_base, struct sk_buff *skb)
+static int phy_prepare_data(const struct ethnl_req_info *req_info,
+			    struct ethnl_reply_data *reply_data,
+			    const struct genl_info *info)
 {
-	struct phy_req_info *req_info = PHY_REQINFO(req_base);
-	struct phy_device_node *pdn = req_info->pdn;
-	struct phy_device *phydev = pdn->phy;
-	enum phy_upstream ptype;
+	struct phy_link_topology *topo = reply_data->dev->link_topo;
+	struct phy_reply_data *rep_data = PHY_REPDATA(reply_data);
+	struct nlattr **tb = info->attrs;
+	struct phy_device_node *pdn;
+	struct phy_device *phydev;
 
-	ptype = pdn->upstream_type;
+	/* RTNL is held by the caller */
+	phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PHY_HEADER,
+				      info->extack);
+	if (IS_ERR_OR_NULL(phydev))
+		return -EOPNOTSUPP;
 
-	if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, phydev->phyindex) ||
-	    nla_put_string(skb, ETHTOOL_A_PHY_NAME, dev_name(&phydev->mdio.dev)) ||
-	    nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, ptype))
-		return -EMSGSIZE;
+	pdn = xa_load(&topo->phys, phydev->phyindex);
+	if (!pdn)
+		return -EOPNOTSUPP;
 
-	if (phydev->drv &&
-	    nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, phydev->drv->name))
-		return -EMSGSIZE;
+	rep_data->phyindex = phydev->phyindex;
+	rep_data->name = kstrdup(dev_name(&phydev->mdio.dev), GFP_KERNEL);
+	rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL);
+	rep_data->upstream_type = pdn->upstream_type;
 
-	if (ptype == PHY_UPSTREAM_PHY) {
+	if (pdn->upstream_type == PHY_UPSTREAM_PHY) {
 		struct phy_device *upstream = pdn->upstream.phydev;
-		const char *sfp_upstream_name;
-
-		/* Parent index */
-		if (nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, upstream->phyindex))
-			return -EMSGSIZE;
-
-		if (pdn->parent_sfp_bus) {
-			sfp_upstream_name = sfp_get_name(pdn->parent_sfp_bus);
-			if (sfp_upstream_name &&
-			    nla_put_string(skb, ETHTOOL_A_PHY_UPSTREAM_SFP_NAME,
-					   sfp_upstream_name))
-				return -EMSGSIZE;
-		}
-	}
-
-	if (phydev->sfp_bus) {
-		const char *sfp_name = sfp_get_name(phydev->sfp_bus);
-
-		if (sfp_name &&
-		    nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME,
-				   sfp_name))
-			return -EMSGSIZE;
+		rep_data->upstream_index = upstream->phyindex;
 	}
 
-	return 0;
-}
-
-static int ethnl_phy_parse_request(struct ethnl_req_info *req_base,
-				   struct nlattr **tb,
-				   struct netlink_ext_ack *extack)
-{
-	struct phy_link_topology *topo = req_base->dev->link_topo;
-	struct phy_req_info *req_info = PHY_REQINFO(req_base);
-	struct phy_device *phydev;
+	if (pdn->parent_sfp_bus)
+		rep_data->upstream_sfp_name = kstrdup(sfp_get_name(pdn->parent_sfp_bus),
+						      GFP_KERNEL);
 
-	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PHY_HEADER,
-				      extack);
-	if (!phydev)
-		return 0;
-
-	if (IS_ERR(phydev))
-		return PTR_ERR(phydev);
-
-	if (!topo)
-		return 0;
-
-	req_info->pdn = xa_load(&topo->phys, phydev->phyindex);
+	if (phydev->sfp_bus)
+		rep_data->downstream_sfp_name = kstrdup(sfp_get_name(phydev->sfp_bus),
+							GFP_KERNEL);
 
 	return 0;
 }
 
-int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info)
+static int phy_fill_reply(struct sk_buff *skb,
+			  const struct ethnl_req_info *req_info,
+			  const struct ethnl_reply_data *reply_data)
 {
-	struct phy_req_info req_info = {};
-	struct nlattr **tb = info->attrs;
-	struct sk_buff *rskb;
-	void *reply_payload;
-	int reply_len;
-	int ret;
-
-	ret = ethnl_parse_header_dev_get(&req_info.base,
-					 tb[ETHTOOL_A_PHY_HEADER],
-					 genl_info_net(info), info->extack,
-					 true);
-	if (ret < 0)
-		return ret;
-
-	rtnl_lock();
-	netdev_lock_ops(req_info.base.dev);
-
-	ret = ethnl_phy_parse_request(&req_info.base, tb, info->extack);
-	if (ret < 0)
-		goto err_unlock;
-
-	/* No PHY, return early */
-	if (!req_info.pdn)
-		goto err_unlock;
-
-	ret = ethnl_phy_reply_size(&req_info.base, info->extack);
-	if (ret < 0)
-		goto err_unlock;
-	reply_len = ret + ethnl_reply_header_size();
-
-	rskb = ethnl_reply_init(reply_len, req_info.base.dev,
-				ETHTOOL_MSG_PHY_GET_REPLY,
-				ETHTOOL_A_PHY_HEADER,
-				info, &reply_payload);
-	if (!rskb) {
-		ret = -ENOMEM;
-		goto err_unlock;
-	}
-
-	ret = ethnl_phy_fill_reply(&req_info.base, rskb);
-	if (ret)
-		goto err_free_msg;
+	struct phy_reply_data *rep_data = PHY_REPDATA(reply_data);
 
-	netdev_unlock_ops(req_info.base.dev);
-	rtnl_unlock();
-	ethnl_parse_header_dev_put(&req_info.base);
-	genlmsg_end(rskb, reply_payload);
-
-	return genlmsg_reply(rskb, info);
-
-err_free_msg:
-	nlmsg_free(rskb);
-err_unlock:
-	netdev_unlock_ops(req_info.base.dev);
-	rtnl_unlock();
-	ethnl_parse_header_dev_put(&req_info.base);
-	return ret;
-}
-
-struct ethnl_phy_dump_ctx {
-	struct phy_req_info	*phy_req_info;
-	unsigned long ifindex;
-	unsigned long phy_index;
-};
-
-int ethnl_phy_start(struct netlink_callback *cb)
-{
-	const struct genl_info *info = genl_info_dump(cb);
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
-	int ret;
-
-	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
-
-	ctx->phy_req_info = kzalloc(sizeof(*ctx->phy_req_info), GFP_KERNEL);
-	if (!ctx->phy_req_info)
-		return -ENOMEM;
-
-	ret = ethnl_parse_header_dev_get(&ctx->phy_req_info->base,
-					 info->attrs[ETHTOOL_A_PHY_HEADER],
-					 sock_net(cb->skb->sk), cb->extack,
-					 false);
-	ctx->ifindex = 0;
-	ctx->phy_index = 0;
-
-	if (ret)
-		kfree(ctx->phy_req_info);
+	if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, rep_data->phyindex) ||
+	    nla_put_string(skb, ETHTOOL_A_PHY_NAME, rep_data->name) ||
+	    nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, rep_data->upstream_type))
+		return -EMSGSIZE;
 
-	return ret;
-}
+	if (rep_data->drvname &&
+	    nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, rep_data->drvname))
+		return -EMSGSIZE;
 
-int ethnl_phy_done(struct netlink_callback *cb)
-{
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
+	if (rep_data->upstream_index &&
+	    nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX,
+			rep_data->upstream_index))
+		return -EMSGSIZE;
 
-	if (ctx->phy_req_info->base.dev)
-		ethnl_parse_header_dev_put(&ctx->phy_req_info->base);
+	if (rep_data->upstream_sfp_name &&
+	    nla_put_string(skb, ETHTOOL_A_PHY_UPSTREAM_SFP_NAME,
+			   rep_data->upstream_sfp_name))
+		return -EMSGSIZE;
 
-	kfree(ctx->phy_req_info);
+	if (rep_data->downstream_sfp_name &&
+	    nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME,
+			   rep_data->downstream_sfp_name))
+		return -EMSGSIZE;
 
 	return 0;
 }
 
-static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev,
-				  struct netlink_callback *cb)
+static void phy_cleanup_data(struct ethnl_reply_data *reply_data)
 {
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
-	struct phy_req_info *pri = ctx->phy_req_info;
-	struct phy_device_node *pdn;
-	int ret = 0;
-	void *ehdr;
-
-	if (!dev->link_topo)
-		return 0;
-
-	xa_for_each_start(&dev->link_topo->phys, ctx->phy_index, pdn, ctx->phy_index) {
-		ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_PHY_GET_REPLY);
-		if (!ehdr) {
-			ret = -EMSGSIZE;
-			break;
-		}
-
-		ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_PHY_HEADER);
-		if (ret < 0) {
-			genlmsg_cancel(skb, ehdr);
-			break;
-		}
-
-		pri->pdn = pdn;
-		ret = ethnl_phy_fill_reply(&pri->base, skb);
-		if (ret < 0) {
-			genlmsg_cancel(skb, ehdr);
-			break;
-		}
-
-		genlmsg_end(skb, ehdr);
-	}
+	struct phy_reply_data *rep_data = PHY_REPDATA(reply_data);
 
-	return ret;
+	kfree(rep_data->drvname);
+	kfree(rep_data->name);
+	kfree(rep_data->upstream_sfp_name);
+	kfree(rep_data->downstream_sfp_name);
 }
 
-int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
-{
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
-	struct net *net = sock_net(skb->sk);
-	struct net_device *dev;
-	int ret = 0;
-
-	rtnl_lock();
-
-	if (ctx->phy_req_info->base.dev) {
-		dev = ctx->phy_req_info->base.dev;
-		netdev_lock_ops(dev);
-		ret = ethnl_phy_dump_one_dev(skb, dev, cb);
-		netdev_unlock_ops(dev);
-	} else {
-		for_each_netdev_dump(net, dev, ctx->ifindex) {
-			netdev_lock_ops(dev);
-			ret = ethnl_phy_dump_one_dev(skb, dev, cb);
-			netdev_unlock_ops(dev);
-			if (ret)
-				break;
-
-			ctx->phy_index = 0;
-		}
-	}
-	rtnl_unlock();
-
-	return ret;
-}
+const struct ethnl_request_ops ethnl_phy_request_ops = {
+	.request_cmd		= ETHTOOL_MSG_PHY_GET,
+	.reply_cmd		= ETHTOOL_MSG_PHY_GET_REPLY,
+	.hdr_attr		= ETHTOOL_A_PHY_HEADER,
+	.req_info_size		= sizeof(struct phy_req_info),
+	.reply_data_size	= sizeof(struct phy_reply_data),
+
+	.prepare_data		= phy_prepare_data,
+	.reply_size		= phy_reply_size,
+	.fill_reply		= phy_fill_reply,
+	.cleanup_data		= phy_cleanup_data,
+};
diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c
index 8130b406ef10..8c654caa6805 100644
--- a/net/ethtool/tsinfo.c
+++ b/net/ethtool/tsinfo.c
@@ -160,6 +160,12 @@ static int tsinfo_reply_size(const struct ethnl_req_info *req_base,
 		/* _TSINFO_HWTSTAMP_PROVIDER */
 		len += nla_total_size(0) + 2 * nla_total_size(sizeof(u32));
 	}
+	if (ts_info->phc_source) {
+		len += nla_total_size(sizeof(u32));	/* _TSINFO_HWTSTAMP_SOURCE */
+		if (ts_info->phc_phyindex)
+			/* _TSINFO_HWTSTAMP_PHYINDEX */
+			len += nla_total_size(sizeof(u32));
+	}
 	if (req_base->flags & ETHTOOL_FLAG_STATS)
 		len += nla_total_size(0) + /* _TSINFO_STATS */
 		       nla_total_size_64bit(sizeof(u64)) * ETHTOOL_TS_STAT_CNT;
@@ -259,6 +265,16 @@ static int tsinfo_fill_reply(struct sk_buff *skb,
 
 		nla_nest_end(skb, nest);
 	}
+	if (ts_info->phc_source) {
+		if (nla_put_u32(skb, ETHTOOL_A_TSINFO_HWTSTAMP_SOURCE,
+				ts_info->phc_source))
+			return -EMSGSIZE;
+
+		if (ts_info->phc_phyindex &&
+		    nla_put_u32(skb, ETHTOOL_A_TSINFO_HWTSTAMP_PHYINDEX,
+				ts_info->phc_phyindex))
+			return -EMSGSIZE;
+	}
 	if (req_base->flags & ETHTOOL_FLAG_STATS &&
 	    tsinfo_put_stats(skb, &data->stats))
 		return -EMSGSIZE;
@@ -346,6 +362,11 @@ static int ethnl_tsinfo_dump_one_phydev(struct sk_buff *skb,
 	if (ret < 0)
 		goto err;
 
+	if (reply_data->ts_info.phc_index >= 0) {
+		reply_data->ts_info.phc_source = HWTSTAMP_SOURCE_PHYLIB;
+		reply_data->ts_info.phc_phyindex = phydev->phyindex;
+	}
+
 	ret = ethnl_tsinfo_end_dump(skb, dev, req_info, reply_data, ehdr);
 	if (ret < 0)
 		goto err;
@@ -389,6 +410,8 @@ static int ethnl_tsinfo_dump_one_netdev(struct sk_buff *skb,
 		if (ret < 0)
 			goto err;
 
+		if (reply_data->ts_info.phc_index >= 0)
+			reply_data->ts_info.phc_source = HWTSTAMP_SOURCE_NETDEV;
 		ret = ethnl_tsinfo_end_dump(skb, dev, req_info, reply_data,
 					    ehdr);
 		if (ret < 0)
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 1b1b700ec05e..0d1e56965af0 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -761,6 +761,11 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 	if (res)
 		goto err_unregister;
 
+	if (protocol_version == PRP_V1) {
+		eth_hw_addr_set(slave[1], slave[0]->dev_addr);
+		call_netdevice_notifiers(NETDEV_CHANGEADDR, slave[1]);
+	}
+
 	if (interlink) {
 		res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack);
 		if (res)
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index d7ae32473c41..192893c3f2ec 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -78,6 +78,15 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event,
 			eth_hw_addr_set(master->dev, dev->dev_addr);
 			call_netdevice_notifiers(NETDEV_CHANGEADDR,
 						 master->dev);
+
+			if (hsr->prot_version == PRP_V1) {
+				port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B);
+				if (port) {
+					eth_hw_addr_set(port->dev, dev->dev_addr);
+					call_netdevice_notifiers(NETDEV_CHANGEADDR,
+								 port->dev);
+				}
+			}
 		}
 
 		/* Make sure we recognize frames from ourselves in hsr_rcv() */
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index 1bc47b17a296..135ec5fce019 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -155,6 +155,7 @@ struct hsr_port {
 	struct hsr_priv		*hsr;
 	enum hsr_port_type	type;
 	struct rcu_head		rcu;
+	unsigned char		original_macaddress[ETH_ALEN];
 };
 
 struct hsr_frame_info;
diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index 2a802a5de2ac..b87b6a6fe070 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -196,6 +196,7 @@ int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev,
 	port->hsr = hsr;
 	port->dev = dev;
 	port->type = type;
+	ether_addr_copy(port->original_macaddress, dev->dev_addr);
 
 	if (type != HSR_PT_MASTER) {
 		res = hsr_portdev_setup(hsr, dev, port, extack);
@@ -232,6 +233,7 @@ void hsr_del_port(struct hsr_port *port)
 		if (!port->hsr->fwd_offloaded)
 			dev_set_promiscuity(port->dev, -1);
 		netdev_upper_dev_unlink(port->dev, master->dev);
+		eth_hw_addr_set(port->dev, port->original_macaddress);
 	}
 
 	kfree_rcu(port, rcu);
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 6d2c97f8e9ef..12850a277251 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -425,7 +425,7 @@ config INET_DIAG
 	tristate "INET: socket monitoring interface"
 	default y
 	help
-	  Support for INET (TCP, DCCP, etc) socket monitoring interface used by
+	  Support for INET (TCP, UDP, etc) socket monitoring interface used by
 	  native Linux tools such as ss. ss is included in iproute2, currently
 	  downloadable at:
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 5df1f1325259..76e38092cd8a 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1328,10 +1328,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 
 		/* Routing failed... */
 		sk->sk_route_caps = 0;
-		/*
-		 * Other protocols have to map its equivalent state to TCP_SYN_SENT.
-		 * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme
-		 */
+
 		if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) ||
 		    sk->sk_state != TCP_SYN_SENT ||
 		    (sk->sk_userlocks & SOCK_BINDADDR_LOCK) ||
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 77e5705ac799..c47d3828d4f6 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1792,12 +1792,12 @@ static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh,
 	struct ifaddrmsg *ifm;
 	int err, i;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+	ifm = nlmsg_payload(nlh, sizeof(*ifm));
+	if (!ifm) {
 		NL_SET_ERR_MSG(extack, "ipv4: Invalid header for address dump request");
 		return -EINVAL;
 	}
 
-	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
 		NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for address dump request");
 		return -EINVAL;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 0e4076866c0a..f14a41ee4aa1 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -120,47 +120,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 }
 
 #ifdef CONFIG_INET_ESPINTCP
-struct esp_tcp_sk {
-	struct sock *sk;
-	struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
-	struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
-	sock_put(esk->sk);
-	kfree(esk);
-}
-
 static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
 {
 	struct xfrm_encap_tmpl *encap = x->encap;
 	struct net *net = xs_net(x);
-	struct esp_tcp_sk *esk;
 	__be16 sport, dport;
-	struct sock *nsk;
 	struct sock *sk;
 
-	sk = rcu_dereference(x->encap_sk);
-	if (sk && sk->sk_state == TCP_ESTABLISHED)
-		return sk;
-
 	spin_lock_bh(&x->lock);
 	sport = encap->encap_sport;
 	dport = encap->encap_dport;
-	nsk = rcu_dereference_protected(x->encap_sk,
-					lockdep_is_held(&x->lock));
-	if (sk && sk == nsk) {
-		esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
-		if (!esk) {
-			spin_unlock_bh(&x->lock);
-			return ERR_PTR(-ENOMEM);
-		}
-		RCU_INIT_POINTER(x->encap_sk, NULL);
-		esk->sk = sk;
-		call_rcu(&esk->rcu, esp_free_tcp_sk);
-	}
 	spin_unlock_bh(&x->lock);
 
 	sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, x->id.daddr.a4,
@@ -173,20 +142,6 @@ static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
 		return ERR_PTR(-EINVAL);
 	}
 
-	spin_lock_bh(&x->lock);
-	nsk = rcu_dereference_protected(x->encap_sk,
-					lockdep_is_held(&x->lock));
-	if (encap->encap_sport != sport ||
-	    encap->encap_dport != dport) {
-		sock_put(sk);
-		sk = nsk ?: ERR_PTR(-EREMCHG);
-	} else if (sk == nsk) {
-		sock_put(sk);
-	} else {
-		rcu_assign_pointer(x->encap_sk, sk);
-	}
-	spin_unlock_bh(&x->lock);
-
 	return sk;
 }
 
@@ -199,8 +154,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
 
 	sk = esp_find_tcp_sk(x);
 	err = PTR_ERR_OR_ZERO(sk);
-	if (err)
+	if (err) {
+		kfree_skb(skb);
 		goto out;
+	}
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk))
@@ -209,6 +166,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
 		err = espintcp_push_skb(sk, skb);
 	bh_unlock_sock(sk);
 
+	sock_put(sk);
+
 out:
 	rcu_read_unlock();
 	return err;
@@ -392,6 +351,8 @@ static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
 	if (IS_ERR(sk))
 		return ERR_CAST(sk);
 
+	sock_put(sk);
+
 	*lenp = htons(len);
 	esph = (struct ip_esp_hdr *)(lenp + 1);
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 3f4e629998fa..fd1e1507a224 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -807,7 +807,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		case RTA_MULTIPATH:
 			err = lwtunnel_valid_encap_type_attr(nla_data(attr),
 							     nla_len(attr),
-							     extack, false);
+							     extack);
 			if (err < 0)
 				goto errout;
 			cfg->fc_mp = nla_data(attr);
@@ -825,7 +825,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		case RTA_ENCAP_TYPE:
 			cfg->fc_encap_type = nla_get_u16(attr);
 			err = lwtunnel_valid_encap_type(cfg->fc_encap_type,
-							extack, false);
+							extack);
 			if (err < 0)
 				goto errout;
 			break;
@@ -948,12 +948,12 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 	if (filter->rtnl_held)
 		ASSERT_RTNL();
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
+	rtm = nlmsg_payload(nlh, sizeof(*rtm));
+	if (!rtm) {
 		NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request");
 		return -EINVAL;
 	}
 
-	rtm = nlmsg_data(nlh);
 	if (rtm->rtm_dst_len || rtm->rtm_src_len  || rtm->rtm_tos   ||
 	    rtm->rtm_scope) {
 		NL_SET_ERR_MSG(extack, "Invalid values in header for FIB dump request");
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f68bb9e34c34..d643bd1a0d9d 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -365,7 +365,7 @@ static struct hlist_head *fib_info_laddrhash_bucket(const struct net *net,
 static struct hlist_head *fib_info_hash_alloc(unsigned int hash_bits)
 {
 	/* The second half is used for prefsrc */
-	return kvcalloc((1 << hash_bits) * 2, sizeof(struct hlist_head *),
+	return kvcalloc((1 << hash_bits) * 2, sizeof(struct hlist_head),
 			GFP_KERNEL);
 }
 
@@ -2168,34 +2168,52 @@ static bool fib_good_nh(const struct fib_nh *nh)
 	return !!(state & NUD_VALID);
 }
 
-void fib_select_multipath(struct fib_result *res, int hash)
+void fib_select_multipath(struct fib_result *res, int hash,
+			  const struct flowi4 *fl4)
 {
 	struct fib_info *fi = res->fi;
 	struct net *net = fi->fib_net;
-	bool first = false;
+	bool found = false;
+	bool use_neigh;
+	__be32 saddr;
 
 	if (unlikely(res->fi->nh)) {
 		nexthop_path_fib_result(res, hash);
 		return;
 	}
 
+	use_neigh = READ_ONCE(net->ipv4.sysctl_fib_multipath_use_neigh);
+	saddr = fl4 ? fl4->saddr : 0;
+
 	change_nexthops(fi) {
-		if (READ_ONCE(net->ipv4.sysctl_fib_multipath_use_neigh)) {
-			if (!fib_good_nh(nexthop_nh))
-				continue;
-			if (!first) {
-				res->nh_sel = nhsel;
-				res->nhc = &nexthop_nh->nh_common;
-				first = true;
-			}
+		int nh_upper_bound;
+
+		/* Nexthops without a carrier are assigned an upper bound of
+		 * minus one when "ignore_routes_with_linkdown" is set.
+		 */
+		nh_upper_bound = atomic_read(&nexthop_nh->fib_nh_upper_bound);
+		if (nh_upper_bound == -1 ||
+		    (use_neigh && !fib_good_nh(nexthop_nh)))
+			continue;
+
+		if (!found) {
+			res->nh_sel = nhsel;
+			res->nhc = &nexthop_nh->nh_common;
+			found = !saddr || nexthop_nh->nh_saddr == saddr;
 		}
 
-		if (hash > atomic_read(&nexthop_nh->fib_nh_upper_bound))
+		if (hash > nh_upper_bound)
 			continue;
 
-		res->nh_sel = nhsel;
-		res->nhc = &nexthop_nh->nh_common;
-		return;
+		if (!saddr || nexthop_nh->nh_saddr == saddr) {
+			res->nh_sel = nhsel;
+			res->nhc = &nexthop_nh->nh_common;
+			return;
+		}
+
+		if (found)
+			return;
+
 	} endfor_nexthops(fi);
 }
 #endif
@@ -2210,7 +2228,7 @@ void fib_select_path(struct net *net, struct fib_result *res,
 	if (fib_info_num_path(res->fi) > 1) {
 		int h = fib_multipath_hash(net, fl4, skb, NULL);
 
-		fib_select_multipath(res, h);
+		fib_select_multipath(res, h, fl4);
 	}
 	else
 #endif
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 6701a98d9a9f..dafd68f3436a 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -199,7 +199,7 @@ static const struct net_protocol net_gre_protocol = {
 
 static int __init gre_init(void)
 {
-	pr_info("GRE over IPv4 demultiplexor driver\n");
+	pr_info("GRE over IPv4 demultiplexer driver\n");
 
 	if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) {
 		pr_err("can't add protocol\n");
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index dd5cf8914a28..20915895bdaa 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -330,7 +330,7 @@ inet_csk_find_open_port(const struct sock *sk, struct inet_bind_bucket **tb_ret,
 			struct inet_bind2_bucket **tb2_ret,
 			struct inet_bind_hashbucket **head2_ret, int *port_ret)
 {
-	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
+	struct inet_hashinfo *hinfo = tcp_get_hashinfo(sk);
 	int i, low, high, attempt_half, port, l3mdev;
 	struct inet_bind_hashbucket *head, *head2;
 	struct net *net = sock_net(sk);
@@ -512,10 +512,10 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
  */
 int inet_csk_get_port(struct sock *sk, unsigned short snum)
 {
-	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
 	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
 	bool found_port = false, check_bind_conflict = true;
 	bool bhash_created = false, bhash2_created = false;
+	struct inet_hashinfo *hinfo = tcp_get_hashinfo(sk);
 	int ret = -EADDRINUSE, port = snum, l3mdev;
 	struct inet_bind_hashbucket *head, *head2;
 	struct inet_bind2_bucket *tb2 = NULL;
@@ -767,7 +767,6 @@ void inet_csk_init_xmit_timers(struct sock *sk,
 	timer_setup(&sk->sk_timer, keepalive_handler, 0);
 	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
 }
-EXPORT_SYMBOL(inet_csk_init_xmit_timers);
 
 void inet_csk_clear_xmit_timers(struct sock *sk)
 {
@@ -780,7 +779,6 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
 	sk_stop_timer(sk, &icsk->icsk_delack_timer);
 	sk_stop_timer(sk, &sk->sk_timer);
 }
-EXPORT_SYMBOL(inet_csk_clear_xmit_timers);
 
 void inet_csk_clear_xmit_timers_sync(struct sock *sk)
 {
@@ -831,7 +829,6 @@ no_route:
 	__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(inet_csk_route_req);
 
 struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 					    struct sock *newsk,
@@ -898,7 +895,6 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req)
 		req->num_retrans++;
 	return err;
 }
-EXPORT_SYMBOL(inet_rtx_syn_ack);
 
 static struct request_sock *
 reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener,
@@ -1026,9 +1022,10 @@ static bool reqsk_queue_unlink(struct request_sock *req)
 	bool found = false;
 
 	if (sk_hashed(sk)) {
-		struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
-		spinlock_t *lock = inet_ehash_lockp(hashinfo, req->rsk_hash);
+		struct inet_hashinfo *hashinfo = tcp_get_hashinfo(sk);
+		spinlock_t *lock;
 
+		lock = inet_ehash_lockp(hashinfo, req->rsk_hash);
 		spin_lock(lock);
 		found = __sk_nulls_del_node_init_rcu(sk);
 		spin_unlock(lock);
@@ -1058,14 +1055,13 @@ bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
 {
 	return __inet_csk_reqsk_queue_drop(sk, req, false);
 }
-EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
 
 void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req)
 {
 	inet_csk_reqsk_queue_drop(sk, req);
 	reqsk_put(req);
 }
-EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put);
+EXPORT_IPV6_MOD(inet_csk_reqsk_queue_drop_and_put);
 
 static void reqsk_timer_handler(struct timer_list *t)
 {
@@ -1209,7 +1205,6 @@ bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
 	inet_csk_reqsk_queue_added(sk);
 	return true;
 }
-EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
 
 static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk,
 			   const gfp_t priority)
@@ -1290,7 +1285,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 
 	return newsk;
 }
-EXPORT_SYMBOL_GPL(inet_csk_clone_lock);
 
 /*
  * At this point, there should be no process reference to this
@@ -1322,7 +1316,7 @@ void inet_csk_destroy_sock(struct sock *sk)
 EXPORT_SYMBOL(inet_csk_destroy_sock);
 
 /* This function allows to force a closure of a socket after the call to
- * tcp/dccp_create_openreq_child().
+ * tcp_create_openreq_child().
  */
 void inet_csk_prepare_forced_close(struct sock *sk)
 	__releases(&sk->sk_lock.slock)
@@ -1380,7 +1374,6 @@ int inet_csk_listen_start(struct sock *sk)
 	inet_sk_set_state(sk, TCP_CLOSE);
 	return err;
 }
-EXPORT_SYMBOL_GPL(inet_csk_listen_start);
 
 static void inet_child_forget(struct sock *sk, struct request_sock *req,
 			      struct sock *child)
@@ -1475,7 +1468,6 @@ child_put:
 	sock_put(child);
 	return NULL;
 }
-EXPORT_SYMBOL(inet_csk_complete_hashdance);
 
 /*
  *	This routine closes sockets which have been at least partially
@@ -1590,4 +1582,3 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
 out:
 	return dst;
 }
-EXPORT_SYMBOL_GPL(inet_csk_update_pmtu);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index c2bb91d9e9ff..1d1d6ad53f4c 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -160,7 +160,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	    ext & (1 << (INET_DIAG_TCLASS - 1))) {
 		u32 classid = 0;
 
-#ifdef CONFIG_SOCK_CGROUP_DATA
+#ifdef CONFIG_CGROUP_NET_CLASSID
 		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
 #endif
 		/* Fallback to socket priority if class id isn't set.
@@ -1369,8 +1369,6 @@ static int inet_diag_type2proto(int type)
 	switch (type) {
 	case TCPDIAG_GETSOCK:
 		return IPPROTO_TCP;
-	case DCCPDIAG_GETSOCK:
-		return IPPROTO_DCCP;
 	default:
 		return 0;
 	}
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 5bf163f756e9..77a0b52b2eab 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -23,11 +23,12 @@
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/inet6_hashtables.h>
 #endif
-#include <net/secure_seq.h>
 #include <net/hotdata.h>
 #include <net/ip.h>
-#include <net/tcp.h>
+#include <net/rps.h>
+#include <net/secure_seq.h>
 #include <net/sock_reuseport.h>
+#include <net/tcp.h>
 
 u32 inet_ehashfn(const struct net *net, const __be32 laddr,
 		 const __u16 lport, const __be32 faddr,
@@ -176,7 +177,7 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
  */
 static void __inet_put_port(struct sock *sk)
 {
-	struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
+	struct inet_hashinfo *hashinfo = tcp_get_hashinfo(sk);
 	struct inet_bind_hashbucket *head, *head2;
 	struct net *net = sock_net(sk);
 	struct inet_bind_bucket *tb;
@@ -215,7 +216,7 @@ EXPORT_SYMBOL(inet_put_port);
 
 int __inet_inherit_port(const struct sock *sk, struct sock *child)
 {
-	struct inet_hashinfo *table = tcp_or_dccp_get_hashinfo(sk);
+	struct inet_hashinfo *table = tcp_get_hashinfo(sk);
 	unsigned short port = inet_sk(child)->inet_num;
 	struct inet_bind_hashbucket *head, *head2;
 	bool created_inet_bind_bucket = false;
@@ -668,7 +669,7 @@ static bool inet_ehash_lookup_by_sk(struct sock *sk,
  */
 bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 {
-	struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
+	struct inet_hashinfo *hashinfo = tcp_get_hashinfo(sk);
 	struct inet_ehash_bucket *head;
 	struct hlist_nulls_head *list;
 	spinlock_t *lock;
@@ -713,7 +714,7 @@ bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 	}
 	return ok;
 }
-EXPORT_SYMBOL_GPL(inet_ehash_nolisten);
+EXPORT_IPV6_MOD(inet_ehash_nolisten);
 
 static int inet_reuseport_add_sock(struct sock *sk,
 				   struct inet_listen_hashbucket *ilb)
@@ -740,7 +741,7 @@ static int inet_reuseport_add_sock(struct sock *sk,
 
 int __inet_hash(struct sock *sk, struct sock *osk)
 {
-	struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
+	struct inet_hashinfo *hashinfo = tcp_get_hashinfo(sk);
 	struct inet_listen_hashbucket *ilb2;
 	int err = 0;
 
@@ -771,7 +772,7 @@ unlock:
 
 	return err;
 }
-EXPORT_SYMBOL(__inet_hash);
+EXPORT_IPV6_MOD(__inet_hash);
 
 int inet_hash(struct sock *sk)
 {
@@ -782,15 +783,15 @@ int inet_hash(struct sock *sk)
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(inet_hash);
 
 void inet_unhash(struct sock *sk)
 {
-	struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
+	struct inet_hashinfo *hashinfo = tcp_get_hashinfo(sk);
 
 	if (sk_unhashed(sk))
 		return;
 
+	sock_rps_delete_flow(sk);
 	if (sk->sk_state == TCP_LISTEN) {
 		struct inet_listen_hashbucket *ilb2;
 
@@ -823,7 +824,7 @@ void inet_unhash(struct sock *sk)
 		spin_unlock_bh(lock);
 	}
 }
-EXPORT_SYMBOL_GPL(inet_unhash);
+EXPORT_IPV6_MOD(inet_unhash);
 
 static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb,
 				    const struct net *net, unsigned short port,
@@ -874,7 +875,7 @@ inet_bind2_bucket_find(const struct inet_bind_hashbucket *head, const struct net
 struct inet_bind_hashbucket *
 inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port)
 {
-	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
+	struct inet_hashinfo *hinfo = tcp_get_hashinfo(sk);
 	u32 hash;
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -902,7 +903,7 @@ static void inet_update_saddr(struct sock *sk, void *saddr, int family)
 
 static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset)
 {
-	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
+	struct inet_hashinfo *hinfo = tcp_get_hashinfo(sk);
 	struct inet_bind_hashbucket *head, *head2;
 	struct inet_bind2_bucket *tb2, *new_tb2;
 	int l3mdev = inet_sk_bound_l3mdev(sk);
@@ -982,14 +983,14 @@ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
 {
 	return __inet_bhash2_update_saddr(sk, saddr, family, false);
 }
-EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr);
+EXPORT_IPV6_MOD(inet_bhash2_update_saddr);
 
 void inet_bhash2_reset_saddr(struct sock *sk)
 {
 	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
 		__inet_bhash2_update_saddr(sk, NULL, 0, true);
 }
-EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr);
+EXPORT_IPV6_MOD(inet_bhash2_reset_saddr);
 
 /* RFC 6056 3.3.4.  Algorithm 4: Double-Hash Port Selection Algorithm
  * Note that we use 32bit integers (vs RFC 'short integers')
@@ -1214,7 +1215,6 @@ int inet_hash_connect(struct inet_timewait_death_row *death_row,
 	return __inet_hash_connect(death_row, sk, port_offset, hash_port0,
 				   __inet_check_established);
 }
-EXPORT_SYMBOL_GPL(inet_hash_connect);
 
 static void init_hashinfo_lhash2(struct inet_hashinfo *h)
 {
@@ -1265,7 +1265,6 @@ int inet_hashinfo2_init_mod(struct inet_hashinfo *h)
 	init_hashinfo_lhash2(h);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(inet_hashinfo2_init_mod);
 
 int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
 {
@@ -1305,7 +1304,6 @@ set_mask:
 	hashinfo->ehash_locks_mask = nblocks - 1;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(inet_ehash_locks_alloc);
 
 struct inet_hashinfo *inet_pernet_hashinfo_alloc(struct inet_hashinfo *hashinfo,
 						 unsigned int ehash_entries)
@@ -1341,7 +1339,6 @@ free_hashinfo:
 err:
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_alloc);
 
 void inet_pernet_hashinfo_free(struct inet_hashinfo *hashinfo)
 {
@@ -1352,4 +1349,3 @@ void inet_pernet_hashinfo_free(struct inet_hashinfo *hashinfo)
 	vfree(hashinfo->ehash);
 	kfree(hashinfo);
 }
-EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_free);
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index aded4bf1bc16..67efe9501581 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -166,7 +166,6 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
 	spin_unlock(lock);
 	local_bh_enable();
 }
-EXPORT_SYMBOL_GPL(inet_twsk_hashdance_schedule);
 
 static void tw_timer_handler(struct timer_list *t)
 {
@@ -223,7 +222,6 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 
 	return tw;
 }
-EXPORT_SYMBOL_GPL(inet_twsk_alloc);
 
 /* These are always called from BH context.  See callers in
  * tcp_input.c to verify this.
@@ -306,7 +304,6 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
 		mod_timer_pending(&tw->tw_timer, jiffies + timeo);
 	}
 }
-EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
 
 /* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */
 void inet_twsk_purge(struct inet_hashinfo *hashinfo)
@@ -365,4 +362,3 @@ restart:
 		rcu_read_unlock();
 	}
 }
-EXPORT_SYMBOL_GPL(inet_twsk_purge);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 26d15f907551..f5b9004d6938 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1066,16 +1066,15 @@ static int __net_init ipgre_init_net(struct net *net)
 	return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL);
 }
 
-static void __net_exit ipgre_exit_batch_rtnl(struct list_head *list_net,
-					     struct list_head *dev_to_kill)
+static void __net_exit ipgre_exit_rtnl(struct net *net,
+				       struct list_head *dev_to_kill)
 {
-	ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops,
-			      dev_to_kill);
+	ip_tunnel_delete_net(net, ipgre_net_id, &ipgre_link_ops, dev_to_kill);
 }
 
 static struct pernet_operations ipgre_net_ops = {
 	.init = ipgre_init_net,
-	.exit_batch_rtnl = ipgre_exit_batch_rtnl,
+	.exit_rtnl = ipgre_exit_rtnl,
 	.id   = &ipgre_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
@@ -1752,16 +1751,15 @@ static int __net_init ipgre_tap_init_net(struct net *net)
 	return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0");
 }
 
-static void __net_exit ipgre_tap_exit_batch_rtnl(struct list_head *list_net,
-						 struct list_head *dev_to_kill)
+static void __net_exit ipgre_tap_exit_rtnl(struct net *net,
+					   struct list_head *dev_to_kill)
 {
-	ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops,
-			      dev_to_kill);
+	ip_tunnel_delete_net(net, gre_tap_net_id, &ipgre_tap_ops, dev_to_kill);
 }
 
 static struct pernet_operations ipgre_tap_net_ops = {
 	.init = ipgre_tap_init_net,
-	.exit_batch_rtnl = ipgre_tap_exit_batch_rtnl,
+	.exit_rtnl = ipgre_tap_exit_rtnl,
 	.id   = &gre_tap_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
@@ -1772,16 +1770,15 @@ static int __net_init erspan_init_net(struct net *net)
 				  &erspan_link_ops, "erspan0");
 }
 
-static void __net_exit erspan_exit_batch_rtnl(struct list_head *net_list,
-					      struct list_head *dev_to_kill)
+static void __net_exit erspan_exit_rtnl(struct net *net,
+					struct list_head *dev_to_kill)
 {
-	ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops,
-			      dev_to_kill);
+	ip_tunnel_delete_net(net, erspan_net_id, &erspan_link_ops, dev_to_kill);
 }
 
 static struct pernet_operations erspan_net_ops = {
 	.init = erspan_init_net,
-	.exit_batch_rtnl = erspan_exit_batch_rtnl,
+	.exit_rtnl = erspan_exit_rtnl,
 	.id   = &erspan_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 6e18d7ec5062..a2705d454fd6 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1014,7 +1014,8 @@ static int __ip_append_data(struct sock *sk,
 				uarg = msg->msg_ubuf;
 			}
 		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
-			uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
+			uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb),
+						    false);
 			if (!uarg)
 				return -ENOBUFS;
 			extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 1024f961ec9a..678b8f96e3e9 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -243,11 +243,11 @@ static struct net_device *__ip_tunnel_create(struct net *net,
 	if (parms->name[0]) {
 		if (!dev_valid_name(parms->name))
 			goto failed;
-		strscpy(name, parms->name, IFNAMSIZ);
+		strscpy(name, parms->name);
 	} else {
 		if (strlen(ops->kind) > (IFNAMSIZ - 3))
 			goto failed;
-		strcpy(name, ops->kind);
+		strscpy(name, ops->kind);
 		strcat(name, "%d");
 	}
 
@@ -1174,13 +1174,16 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_init_net);
 
-static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn,
-			      struct list_head *head,
-			      struct rtnl_link_ops *ops)
+void ip_tunnel_delete_net(struct net *net, unsigned int id,
+			  struct rtnl_link_ops *ops,
+			  struct list_head *head)
 {
+	struct ip_tunnel_net *itn = net_generic(net, id);
 	struct net_device *dev, *aux;
 	int h;
 
+	ASSERT_RTNL_NET(net);
+
 	for_each_netdev_safe(net, dev, aux)
 		if (dev->rtnl_link_ops == ops)
 			unregister_netdevice_queue(dev, head);
@@ -1198,21 +1201,7 @@ static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn,
 				unregister_netdevice_queue(t->dev, head);
 	}
 }
-
-void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id,
-			   struct rtnl_link_ops *ops,
-			   struct list_head *dev_to_kill)
-{
-	struct ip_tunnel_net *itn;
-	struct net *net;
-
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list) {
-		itn = net_generic(net, id);
-		ip_tunnel_destroy(net, itn, dev_to_kill, ops);
-	}
-}
-EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets);
+EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
 
 int ip_tunnel_newlink(struct net *net, struct net_device *dev,
 		      struct nlattr *tb[], struct ip_tunnel_parm_kern *p,
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 159b4473290e..686e4f3d83aa 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -523,16 +523,15 @@ static int __net_init vti_init_net(struct net *net)
 	return 0;
 }
 
-static void __net_exit vti_exit_batch_rtnl(struct list_head *list_net,
-					   struct list_head *dev_to_kill)
+static void __net_exit vti_exit_rtnl(struct net *net,
+				     struct list_head *dev_to_kill)
 {
-	ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops,
-			      dev_to_kill);
+	ip_tunnel_delete_net(net, vti_net_id, &vti_link_ops, dev_to_kill);
 }
 
 static struct pernet_operations vti_net_ops = {
 	.init = vti_init_net,
-	.exit_batch_rtnl = vti_exit_batch_rtnl,
+	.exit_rtnl = vti_exit_rtnl,
 	.id   = &vti_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index bab0bf90c908..3e03af073a1c 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -604,16 +604,15 @@ static int __net_init ipip_init_net(struct net *net)
 	return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
 }
 
-static void __net_exit ipip_exit_batch_rtnl(struct list_head *list_net,
-					    struct list_head *dev_to_kill)
+static void __net_exit ipip_exit_rtnl(struct net *net,
+				      struct list_head *dev_to_kill)
 {
-	ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops,
-			      dev_to_kill);
+	ip_tunnel_delete_net(net, ipip_net_id, &ipip_link_ops, dev_to_kill);
 }
 
 static struct pernet_operations ipip_net_ops = {
 	.init = ipip_init_net,
-	.exit_batch_rtnl = ipip_exit_batch_rtnl,
+	.exit_rtnl = ipip_exit_rtnl,
 	.id   = &ipip_net_id,
 	.size = sizeof(struct ip_tunnel_net),
 };
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index a8b04d4abcaa..2ff2f79c7351 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -120,11 +120,6 @@ static void ipmr_expire_process(struct timer_list *t);
 				lockdep_rtnl_is_held() ||		\
 				list_empty(&net->ipv4.mr_tables))
 
-static bool ipmr_can_free_table(struct net *net)
-{
-	return !check_net(net) || !net_initialized(net);
-}
-
 static struct mr_table *ipmr_mr_table_iter(struct net *net,
 					   struct mr_table *mrt)
 {
@@ -317,11 +312,6 @@ EXPORT_SYMBOL(ipmr_rule_default);
 #define ipmr_for_each_table(mrt, net) \
 	for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
 
-static bool ipmr_can_free_table(struct net *net)
-{
-	return !check_net(net);
-}
-
 static struct mr_table *ipmr_mr_table_iter(struct net *net,
 					   struct mr_table *mrt)
 {
@@ -437,7 +427,7 @@ static void ipmr_free_table(struct mr_table *mrt)
 {
 	struct net *net = read_pnet(&mrt->net);
 
-	WARN_ON_ONCE(!ipmr_can_free_table(net));
+	WARN_ON_ONCE(!mr_can_free_table(net));
 
 	timer_shutdown_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC |
@@ -2511,7 +2501,8 @@ static int ipmr_rtm_valid_getroute_req(struct sk_buff *skb,
 	struct rtmsg *rtm;
 	int i, err;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
+	rtm = nlmsg_payload(nlh, sizeof(*rtm));
+	if (!rtm) {
 		NL_SET_ERR_MSG(extack, "ipv4: Invalid header for multicast route get request");
 		return -EINVAL;
 	}
@@ -2520,7 +2511,6 @@ static int ipmr_rtm_valid_getroute_req(struct sk_buff *skb,
 		return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
 					      rtm_ipv4_policy, extack);
 
-	rtm = nlmsg_data(nlh);
 	if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) ||
 	    (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) ||
 	    rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol ||
@@ -2836,7 +2826,8 @@ static int ipmr_valid_dumplink(const struct nlmsghdr *nlh,
 {
 	struct ifinfomsg *ifm;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+	ifm = nlmsg_payload(nlh, sizeof(*ifm));
+	if (!ifm) {
 		NL_SET_ERR_MSG(extack, "ipv4: Invalid header for ipmr link dump");
 		return -EINVAL;
 	}
@@ -2846,7 +2837,6 @@ static int ipmr_valid_dumplink(const struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
-	ifm = nlmsg_data(nlh);
 	if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
 	    ifm->ifi_change || ifm->ifi_index) {
 		NL_SET_ERR_MSG(extack, "Invalid values in header for ipmr link dump request");
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 467151517023..4397e89d3123 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -541,6 +541,7 @@ static struct nexthop *nexthop_alloc(void)
 		INIT_LIST_HEAD(&nh->f6i_list);
 		INIT_LIST_HEAD(&nh->grp_list);
 		INIT_LIST_HEAD(&nh->fdb_list);
+		spin_lock_init(&nh->lock);
 	}
 	return nh;
 }
@@ -1555,12 +1556,12 @@ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
 	if (nh->is_group) {
 		struct nh_group *nhg;
 
-		nhg = rtnl_dereference(nh->nh_grp);
+		nhg = rcu_dereference_rtnl(nh->nh_grp);
 		if (nhg->has_v4)
 			goto no_v4_nh;
 		is_fdb_nh = nhg->fdb_nh;
 	} else {
-		nhi = rtnl_dereference(nh->nh_info);
+		nhi = rcu_dereference_rtnl(nh->nh_info);
 		if (nhi->family == AF_INET)
 			goto no_v4_nh;
 		is_fdb_nh = nhi->fdb_nh;
@@ -2118,7 +2119,7 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
 /* not called for nexthop replace */
 static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
 {
-	struct fib6_info *f6i, *tmp;
+	struct fib6_info *f6i;
 	bool do_flush = false;
 	struct fib_info *fi;
 
@@ -2129,13 +2130,24 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
 	if (do_flush)
 		fib_flush(net);
 
-	/* ip6_del_rt removes the entry from this list hence the _safe */
-	list_for_each_entry_safe(f6i, tmp, &nh->f6i_list, nh_list) {
+	spin_lock_bh(&nh->lock);
+
+	nh->dead = true;
+
+	while (!list_empty(&nh->f6i_list)) {
+		f6i = list_first_entry(&nh->f6i_list, typeof(*f6i), nh_list);
+
 		/* __ip6_del_rt does a release, so do a hold here */
 		fib6_info_hold(f6i);
+
+		spin_unlock_bh(&nh->lock);
 		ipv6_stub->ip6_del_rt(net, f6i,
 				      !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode));
+
+		spin_lock_bh(&nh->lock);
 	}
+
+	spin_unlock_bh(&nh->lock);
 }
 
 static void __remove_nexthop(struct net *net, struct nexthop *nh,
@@ -3168,8 +3180,7 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
 		}
 
 		cfg->nh_encap_type = nla_get_u16(tb[NHA_ENCAP_TYPE]);
-		err = lwtunnel_valid_encap_type(cfg->nh_encap_type,
-						extack, false);
+		err = lwtunnel_valid_encap_type(cfg->nh_encap_type, extack);
 		if (err < 0)
 			goto out;
 
@@ -4040,14 +4051,11 @@ out:
 }
 EXPORT_SYMBOL(nexthop_res_grp_activity_update);
 
-static void __net_exit nexthop_net_exit_batch_rtnl(struct list_head *net_list,
-						   struct list_head *dev_to_kill)
+static void __net_exit nexthop_net_exit_rtnl(struct net *net,
+					     struct list_head *dev_to_kill)
 {
-	struct net *net;
-
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list)
-		flush_all_nexthops(net);
+	ASSERT_RTNL_NET(net);
+	flush_all_nexthops(net);
 }
 
 static void __net_exit nexthop_net_exit(struct net *net)
@@ -4072,7 +4080,7 @@ static int __net_init nexthop_net_init(struct net *net)
 static struct pernet_operations nexthop_net_ops = {
 	.init = nexthop_net_init,
 	.exit = nexthop_net_exit,
-	.exit_batch_rtnl = nexthop_net_exit_batch_rtnl,
+	.exit_rtnl = nexthop_net_exit_rtnl,
 };
 
 static const struct rtnl_msg_handler nexthop_rtnl_msg_handlers[] __initconst = {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 22dfc971aab4..fccb05fb3a79 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -189,7 +189,11 @@ const __u8 ip_tos2prio[16] = {
 EXPORT_SYMBOL(ip_tos2prio);
 
 static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
+#ifndef CONFIG_PREEMPT_RT
 #define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field)
+#else
+#define RT_CACHE_STAT_INC(field) this_cpu_inc(rt_cache_stat.field)
+#endif
 
 #ifdef CONFIG_PROC_FS
 static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
@@ -2037,8 +2041,12 @@ static u32 fib_multipath_custom_hash_fl4(const struct net *net,
 		hash_keys.addrs.v4addrs.dst = fl4->daddr;
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
 		hash_keys.basic.ip_proto = fl4->flowi4_proto;
-	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
-		hash_keys.ports.src = fl4->fl4_sport;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) {
+		if (fl4->flowi4_flags & FLOWI_FLAG_ANY_SPORT)
+			hash_keys.ports.src = (__force __be16)get_random_u16();
+		else
+			hash_keys.ports.src = fl4->fl4_sport;
+	}
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
 		hash_keys.ports.dst = fl4->fl4_dport;
 
@@ -2093,7 +2101,10 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 			hash_keys.addrs.v4addrs.src = fl4->saddr;
 			hash_keys.addrs.v4addrs.dst = fl4->daddr;
-			hash_keys.ports.src = fl4->fl4_sport;
+			if (fl4->flowi4_flags & FLOWI_FLAG_ANY_SPORT)
+				hash_keys.ports.src = (__force __be16)get_random_u16();
+			else
+				hash_keys.ports.src = fl4->fl4_sport;
 			hash_keys.ports.dst = fl4->fl4_dport;
 			hash_keys.basic.ip_proto = fl4->flowi4_proto;
 		}
@@ -2154,7 +2165,7 @@ ip_mkroute_input(struct sk_buff *skb, struct fib_result *res,
 	if (res->fi && fib_info_num_path(res->fi) > 1) {
 		int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys);
 
-		fib_select_multipath(res, h);
+		fib_select_multipath(res, h, NULL);
 		IPCB(skb)->flags |= IPSKB_MULTIPATH;
 	}
 #endif
@@ -3205,7 +3216,8 @@ static int inet_rtm_valid_getroute_req(struct sk_buff *skb,
 	struct rtmsg *rtm;
 	int i, err;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
+	rtm = nlmsg_payload(nlh, sizeof(*rtm));
+	if (!rtm) {
 		NL_SET_ERR_MSG(extack,
 			       "ipv4: Invalid header for route get request");
 		return -EINVAL;
@@ -3215,7 +3227,6 @@ static int inet_rtm_valid_getroute_req(struct sk_buff *skb,
 		return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
 					      rtm_ipv4_policy, extack);
 
-	rtm = nlmsg_data(nlh);
 	if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) ||
 	    (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) ||
 	    rtm->rtm_table || rtm->rtm_protocol ||
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e0e96f8fd47c..b7b6ab41b496 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1059,6 +1059,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
 
 int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 {
+	struct net_devmem_dmabuf_binding *binding = NULL;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct ubuf_info *uarg = NULL;
 	struct sk_buff *skb;
@@ -1066,11 +1067,23 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	int flags, err, copied = 0;
 	int mss_now = 0, size_goal, copied_syn = 0;
 	int process_backlog = 0;
+	bool sockc_valid = true;
 	int zc = 0;
 	long timeo;
 
 	flags = msg->msg_flags;
 
+	sockc = (struct sockcm_cookie){ .tsflags = READ_ONCE(sk->sk_tsflags) };
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(sk, msg, &sockc);
+		if (unlikely(err))
+			/* Don't return error until MSG_FASTOPEN has been
+			 * processed; that may succeed even if the cmsg is
+			 * invalid.
+			 */
+			sockc_valid = false;
+	}
+
 	if ((flags & MSG_ZEROCOPY) && size) {
 		if (msg->msg_ubuf) {
 			uarg = msg->msg_ubuf;
@@ -1078,7 +1091,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 				zc = MSG_ZEROCOPY;
 		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
 			skb = tcp_write_queue_tail(sk);
-			uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb));
+			uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb),
+						    sockc_valid && !!sockc.dmabuf_id);
 			if (!uarg) {
 				err = -ENOBUFS;
 				goto out_err;
@@ -1087,12 +1101,27 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 				zc = MSG_ZEROCOPY;
 			else
 				uarg_to_msgzc(uarg)->zerocopy = 0;
+
+			if (sockc_valid && sockc.dmabuf_id) {
+				binding = net_devmem_get_binding(sk, sockc.dmabuf_id);
+				if (IS_ERR(binding)) {
+					err = PTR_ERR(binding);
+					binding = NULL;
+					goto out_err;
+				}
+			}
 		}
 	} else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) {
 		if (sk->sk_route_caps & NETIF_F_SG)
 			zc = MSG_SPLICE_PAGES;
 	}
 
+	if (sockc_valid && sockc.dmabuf_id &&
+	    (!(flags & MSG_ZEROCOPY) || !sock_flag(sk, SOCK_ZEROCOPY))) {
+		err = -EINVAL;
+		goto out_err;
+	}
+
 	if (unlikely(flags & MSG_FASTOPEN ||
 		     inet_test_bit(DEFER_CONNECT, sk)) &&
 	    !tp->repair) {
@@ -1131,13 +1160,10 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 		/* 'common' sending to sendq */
 	}
 
-	sockc = (struct sockcm_cookie) { .tsflags = READ_ONCE(sk->sk_tsflags)};
-	if (msg->msg_controllen) {
-		err = sock_cmsg_send(sk, msg, &sockc);
-		if (unlikely(err)) {
+	if (!sockc_valid) {
+		if (!err)
 			err = -EINVAL;
-			goto out_err;
-		}
+		goto out_err;
 	}
 
 	/* This should be in poll */
@@ -1258,7 +1284,8 @@ new_segment:
 					goto wait_for_space;
 			}
 
-			err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
+			err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg,
+						       binding);
 			if (err == -EMSGSIZE || err == -EEXIST) {
 				tcp_mark_push(tp, skb);
 				goto new_segment;
@@ -1339,6 +1366,8 @@ out_nopush:
 	/* msg->msg_ubuf is pinned by the caller so we don't take extra refs */
 	if (uarg && !msg->msg_ubuf)
 		net_zcopy_put(uarg);
+	if (binding)
+		net_devmem_dmabuf_binding_put(binding);
 	return copied + copied_syn;
 
 do_error:
@@ -1356,6 +1385,9 @@ out_err:
 		sk->sk_write_space(sk);
 		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
 	}
+	if (binding)
+		net_devmem_dmabuf_binding_put(binding);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(tcp_sendmsg_locked);
@@ -3409,6 +3441,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->rack.reo_wnd_persist = 0;
 	tp->rack.dsack_seen = 0;
 	tp->syn_data_acked = 0;
+	tp->syn_fastopen_child = 0;
 	tp->rx_opt.saw_tstamp = 0;
 	tp->rx_opt.dsack = 0;
 	tp->rx_opt.num_sacks = 0;
@@ -4164,6 +4197,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 		info->tcpi_options |= TCPI_OPT_SYN_DATA;
 	if (tp->tcp_usec_ts)
 		info->tcpi_options |= TCPI_OPT_USEC_TS;
+	if (tp->syn_fastopen_child)
+		info->tcpi_options |= TCPI_OPT_TFO_CHILD;
 
 	info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto);
 	info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato,
@@ -5196,7 +5231,7 @@ void __init tcp_init(void)
 	/* Set per-socket limits to no more than 1/128 the pressure threshold */
 	limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7);
 	max_wshare = min(4UL*1024*1024, limit);
-	max_rshare = min(6UL*1024*1024, limit);
+	max_rshare = min(32UL*1024*1024, limit);
 
 	init_net.ipv4.sysctl_tcp_wmem[0] = PAGE_SIZE;
 	init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 1a6b1bc54245..9b83d639b5ac 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -401,6 +401,7 @@ fastopen:
 				}
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPFASTOPENPASSIVE);
+				tcp_sk(child)->syn_fastopen_child = 1;
 				return child;
 			}
 			NET_INC_STATS(sock_net(sk),
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a35018e2d0ba..8ec92dec321a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -664,10 +664,12 @@ EXPORT_IPV6_MOD(tcp_initialize_rcv_mss);
  */
 static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
 {
-	u32 new_sample = tp->rcv_rtt_est.rtt_us;
-	long m = sample;
+	u32 new_sample, old_sample = tp->rcv_rtt_est.rtt_us;
+	long m = sample << 3;
 
-	if (new_sample != 0) {
+	if (old_sample == 0 || m < old_sample) {
+		new_sample = m;
+	} else {
 		/* If we sample in larger samples in the non-timestamp
 		 * case, we could grossly overestimate the RTT especially
 		 * with chatty applications or bulk transfer apps which
@@ -678,17 +680,12 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
 		 * else with timestamps disabled convergence takes too
 		 * long.
 		 */
-		if (!win_dep) {
-			m -= (new_sample >> 3);
-			new_sample += m;
-		} else {
-			m <<= 3;
-			if (m < new_sample)
-				new_sample = m;
-		}
-	} else {
-		/* No previous measure. */
-		new_sample = m << 3;
+		if (win_dep)
+			return;
+		/* Do not use this sample if receive queue is not empty. */
+		if (tp->rcv_nxt != tp->copied_seq)
+			return;
+		new_sample = old_sample - (old_sample >> 3) + sample;
 	}
 
 	tp->rcv_rtt_est.rtt_us = new_sample;
@@ -712,7 +709,7 @@ new_measure:
 	tp->rcv_rtt_est.time = tp->tcp_mstamp;
 }
 
-static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp)
+static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp, u32 min_delta)
 {
 	u32 delta, delta_us;
 
@@ -722,7 +719,7 @@ static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp)
 
 	if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
 		if (!delta)
-			delta = 1;
+			delta = min_delta;
 		delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
 		return delta_us;
 	}
@@ -740,13 +737,39 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 
 	if (TCP_SKB_CB(skb)->end_seq -
 	    TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) {
-		s32 delta = tcp_rtt_tsopt_us(tp);
+		s32 delta = tcp_rtt_tsopt_us(tp, 0);
 
-		if (delta >= 0)
+		if (delta > 0)
 			tcp_rcv_rtt_update(tp, delta, 0);
 	}
 }
 
+static void tcp_rcvbuf_grow(struct sock *sk)
+{
+	const struct net *net = sock_net(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	int rcvwin, rcvbuf, cap;
+
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) ||
+	    (sk->sk_userlocks & SOCK_RCVBUF_LOCK))
+		return;
+
+	/* slow start: allow the sender to double its rate. */
+	rcvwin = tp->rcvq_space.space << 1;
+
+	if (!RB_EMPTY_ROOT(&tp->out_of_order_queue))
+		rcvwin += TCP_SKB_CB(tp->ooo_last_skb)->end_seq - tp->rcv_nxt;
+
+	cap = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
+
+	rcvbuf = min_t(u32, tcp_space_from_win(sk, rcvwin), cap);
+	if (rcvbuf > sk->sk_rcvbuf) {
+		WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+		/* Make the window clamp follow along.  */
+		WRITE_ONCE(tp->window_clamp,
+			   tcp_win_from_space(sk, rcvbuf));
+	}
+}
 /*
  * This function should be called every time data is copied to user space.
  * It calculates the appropriate TCP receive buffer space.
@@ -754,8 +777,7 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 void tcp_rcv_space_adjust(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 copied;
-	int time;
+	int time, inq, copied;
 
 	trace_tcp_rcv_space_adjust(sk);
 
@@ -766,45 +788,18 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 	/* Number of bytes copied to user in last RTT */
 	copied = tp->copied_seq - tp->rcvq_space.seq;
+	/* Number of bytes in receive queue. */
+	inq = tp->rcv_nxt - tp->copied_seq;
+	copied -= inq;
 	if (copied <= tp->rcvq_space.space)
 		goto new_measure;
 
-	/* A bit of theory :
-	 * copied = bytes received in previous RTT, our base window
-	 * To cope with packet losses, we need a 2x factor
-	 * To cope with slow start, and sender growing its cwin by 100 %
-	 * every RTT, we need a 4x factor, because the ACK we are sending
-	 * now is for the next RTT, not the current one :
-	 * <prev RTT . ><current RTT .. ><next RTT .... >
-	 */
-
-	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
-	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
-		u64 rcvwin, grow;
-		int rcvbuf;
-
-		/* minimal window to cope with packet losses, assuming
-		 * steady state. Add some cushion because of small variations.
-		 */
-		rcvwin = ((u64)copied << 1) + 16 * tp->advmss;
+	trace_tcp_rcvbuf_grow(sk, time);
 
-		/* Accommodate for sender rate increase (eg. slow start) */
-		grow = rcvwin * (copied - tp->rcvq_space.space);
-		do_div(grow, tp->rcvq_space.space);
-		rcvwin += (grow << 1);
-
-		rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin),
-			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
-		if (rcvbuf > sk->sk_rcvbuf) {
-			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
-
-			/* Make the window clamp follow along.  */
-			WRITE_ONCE(tp->window_clamp,
-				   tcp_win_from_space(sk, rcvbuf));
-		}
-	}
 	tp->rcvq_space.space = copied;
 
+	tcp_rcvbuf_grow(sk);
+
 new_measure:
 	tp->rcvq_space.seq = tp->copied_seq;
 	tp->rcvq_space.time = tp->tcp_mstamp;
@@ -3226,7 +3221,7 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	 */
 	if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp &&
 	    tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED)
-		seq_rtt_us = ca_rtt_us = tcp_rtt_tsopt_us(tp);
+		seq_rtt_us = ca_rtt_us = tcp_rtt_tsopt_us(tp, 1);
 
 	rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */
 	if (seq_rtt_us < 0)
@@ -5173,6 +5168,7 @@ end:
 		skb_condense(skb);
 		skb_set_owner_r(skb, sk);
 	}
+	tcp_rcvbuf_grow(sk);
 }
 
 static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
@@ -6873,6 +6869,9 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (!tp->srtt_us)
 			tcp_synack_rtt_meas(sk, req);
 
+		if (tp->rx_opt.tstamp_ok)
+			tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
+
 		if (req) {
 			tcp_rcv_synrecv_state_fastopen(sk);
 		} else {
@@ -6898,9 +6897,6 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale;
 		tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
 
-		if (tp->rx_opt.tstamp_ok)
-			tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
-
 		if (!inet_csk(sk)->icsk_ca_ops->cong_control)
 			tcp_update_pacing_rate(sk);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d5b5c32115d2..6a14f9e6fef6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3495,8 +3495,8 @@ static int __net_init tcp_sk_init(struct net *net)
 	 * which are too large can cause TCP streams to be bursty.
 	 */
 	net->ipv4.sysctl_tcp_tso_win_divisor = 3;
-	/* Default TSQ limit of 16 TSO segments */
-	net->ipv4.sysctl_tcp_limit_output_bytes = 16 * 65536;
+	/* Default TSQ limit of 4 MB */
+	net->ipv4.sysctl_tcp_limit_output_bytes = 4 << 20;
 
 	/* rfc5961 challenge ack rate limiting, per net-ns, disabled by default. */
 	net->ipv4.sysctl_tcp_challenge_ack_limit = INT_MAX;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 934f777f29d3..d293087b426d 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -439,7 +439,7 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
 				       iif, sdif);
 	NAPI_GRO_CB(skb)->is_flist = !sk;
 	if (sk)
-		sock_put(sk);
+		sock_gen_put(sk);
 }
 
 INDIRECT_CALLABLE_SCOPE
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 13295a59d22e..3ac8d2d17e1f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2619,9 +2619,8 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 	limit = max_t(unsigned long,
 		      2 * skb->truesize,
 		      READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift));
-	if (sk->sk_pacing_status == SK_PACING_NONE)
-		limit = min_t(unsigned long, limit,
-			      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
+	limit = min_t(unsigned long, limit,
+		      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
 	limit <<= factor;
 
 	if (static_branch_unlikely(&tcp_tx_delay_enabled) &&
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8867fe687888..dde52b8050b8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -93,6 +93,7 @@
 #include <linux/inet.h>
 #include <linux/netdevice.h>
 #include <linux/slab.h>
+#include <linux/sock_diag.h>
 #include <net/tcp_states.h>
 #include <linux/skbuff.h>
 #include <linux/proc_fs.h>
@@ -119,6 +120,7 @@
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6_stubs.h>
 #endif
+#include <net/rps.h>
 
 struct udp_table udp_table __read_mostly;
 
@@ -2199,6 +2201,7 @@ void udp_lib_unhash(struct sock *sk)
 		struct udp_table *udptable = udp_get_table_prot(sk);
 		struct udp_hslot *hslot, *hslot2;
 
+		sock_rps_delete_flow(sk);
 		hslot  = udp_hashslot(udptable, sock_net(sk),
 				      udp_sk(sk)->udp_port_hash);
 		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
@@ -2904,15 +2907,33 @@ void udp_destroy_sock(struct sock *sk)
 	}
 }
 
+typedef struct sk_buff *(*udp_gro_receive_t)(struct sock *sk,
+					     struct list_head *head,
+					     struct sk_buff *skb);
+
 static void set_xfrm_gro_udp_encap_rcv(__u16 encap_type, unsigned short family,
 				       struct sock *sk)
 {
 #ifdef CONFIG_XFRM
+	udp_gro_receive_t new_gro_receive;
+
 	if (udp_test_bit(GRO_ENABLED, sk) && encap_type == UDP_ENCAP_ESPINUDP) {
-		if (family == AF_INET)
-			WRITE_ONCE(udp_sk(sk)->gro_receive, xfrm4_gro_udp_encap_rcv);
-		else if (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6)
-			WRITE_ONCE(udp_sk(sk)->gro_receive, ipv6_stub->xfrm6_gro_udp_encap_rcv);
+		if (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6)
+			new_gro_receive = ipv6_stub->xfrm6_gro_udp_encap_rcv;
+		else
+			new_gro_receive = xfrm4_gro_udp_encap_rcv;
+
+		if (udp_sk(sk)->gro_receive != new_gro_receive) {
+			/*
+			 * With IPV6_ADDRFORM the gro callback could change
+			 * after being set, unregister the old one, if valid.
+			 */
+			if (udp_sk(sk)->gro_receive)
+				udp_tunnel_update_gro_rcv(sk, false);
+
+			WRITE_ONCE(udp_sk(sk)->gro_receive, new_gro_receive);
+			udp_tunnel_update_gro_rcv(sk, true);
+		}
 	}
 #endif
 }
@@ -2962,6 +2983,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case UDP_ENCAP:
+		sockopt_lock_sock(sk);
 		switch (val) {
 		case 0:
 #ifdef CONFIG_XFRM
@@ -2985,6 +3007,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 			err = -ENOPROTOOPT;
 			break;
 		}
+		sockopt_release_sock(sk);
 		break;
 
 	case UDP_NO_CHECK6_TX:
@@ -3002,13 +3025,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case UDP_GRO:
-
+		sockopt_lock_sock(sk);
 		/* when enabling GRO, accept the related GSO packet type */
 		if (valbool)
 			udp_tunnel_encap_enable(sk);
 		udp_assign_bit(GRO_ENABLED, sk, valbool);
 		udp_assign_bit(ACCEPT_L4, sk, valbool);
 		set_xfrm_gro_udp_encap_rcv(up->encap_type, sk->sk_family, sk);
+		sockopt_release_sock(sk);
 		break;
 
 	/*
@@ -3392,34 +3416,55 @@ struct bpf_iter__udp {
 	int bucket __aligned(8);
 };
 
+union bpf_udp_iter_batch_item {
+	struct sock *sk;
+	__u64 cookie;
+};
+
 struct bpf_udp_iter_state {
 	struct udp_iter_state state;
 	unsigned int cur_sk;
 	unsigned int end_sk;
 	unsigned int max_sk;
-	int offset;
-	struct sock **batch;
-	bool st_bucket_done;
+	union bpf_udp_iter_batch_item *batch;
 };
 
 static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter,
-				      unsigned int new_batch_sz);
+				      unsigned int new_batch_sz, gfp_t flags);
+static struct sock *bpf_iter_udp_resume(struct sock *first_sk,
+					union bpf_udp_iter_batch_item *cookies,
+					int n_cookies)
+{
+	struct sock *sk = NULL;
+	int i;
+
+	for (i = 0; i < n_cookies; i++) {
+		sk = first_sk;
+		udp_portaddr_for_each_entry_from(sk)
+			if (cookies[i].cookie == atomic64_read(&sk->sk_cookie))
+				goto done;
+	}
+done:
+	return sk;
+}
+
 static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
 {
 	struct bpf_udp_iter_state *iter = seq->private;
 	struct udp_iter_state *state = &iter->state;
+	unsigned int find_cookie, end_cookie;
 	struct net *net = seq_file_net(seq);
-	int resume_bucket, resume_offset;
 	struct udp_table *udptable;
 	unsigned int batch_sks = 0;
-	bool resized = false;
+	int resume_bucket;
+	int resizes = 0;
 	struct sock *sk;
+	int err = 0;
 
 	resume_bucket = state->bucket;
-	resume_offset = iter->offset;
 
 	/* The current batch is done, so advance the bucket. */
-	if (iter->st_bucket_done)
+	if (iter->cur_sk == iter->end_sk)
 		state->bucket++;
 
 	udptable = udp_get_table_seq(seq, net);
@@ -3432,62 +3477,89 @@ again:
 	 * before releasing the bucket lock. This allows BPF programs that are
 	 * called in seq_show to acquire the bucket lock if needed.
 	 */
+	find_cookie = iter->cur_sk;
+	end_cookie = iter->end_sk;
 	iter->cur_sk = 0;
 	iter->end_sk = 0;
-	iter->st_bucket_done = false;
 	batch_sks = 0;
 
 	for (; state->bucket <= udptable->mask; state->bucket++) {
 		struct udp_hslot *hslot2 = &udptable->hash2[state->bucket].hslot;
 
 		if (hlist_empty(&hslot2->head))
-			continue;
+			goto next_bucket;
 
-		iter->offset = 0;
 		spin_lock_bh(&hslot2->lock);
-		udp_portaddr_for_each_entry(sk, &hslot2->head) {
+		sk = hlist_entry_safe(hslot2->head.first, struct sock,
+				      __sk_common.skc_portaddr_node);
+		/* Resume from the first (in iteration order) unseen socket from
+		 * the last batch that still exists in resume_bucket. Most of
+		 * the time this will just be where the last iteration left off
+		 * in resume_bucket unless that socket disappeared between
+		 * reads.
+		 */
+		if (state->bucket == resume_bucket)
+			sk = bpf_iter_udp_resume(sk, &iter->batch[find_cookie],
+						 end_cookie - find_cookie);
+fill_batch:
+		udp_portaddr_for_each_entry_from(sk) {
 			if (seq_sk_match(seq, sk)) {
-				/* Resume from the last iterated socket at the
-				 * offset in the bucket before iterator was stopped.
-				 */
-				if (state->bucket == resume_bucket &&
-				    iter->offset < resume_offset) {
-					++iter->offset;
-					continue;
-				}
 				if (iter->end_sk < iter->max_sk) {
 					sock_hold(sk);
-					iter->batch[iter->end_sk++] = sk;
+					iter->batch[iter->end_sk++].sk = sk;
 				}
 				batch_sks++;
 			}
 		}
+
+		/* Allocate a larger batch and try again. */
+		if (unlikely(resizes <= 1 && iter->end_sk &&
+			     iter->end_sk != batch_sks)) {
+			resizes++;
+
+			/* First, try with GFP_USER to maximize the chances of
+			 * grabbing more memory.
+			 */
+			if (resizes == 1) {
+				spin_unlock_bh(&hslot2->lock);
+				err = bpf_iter_udp_realloc_batch(iter,
+								 batch_sks * 3 / 2,
+								 GFP_USER);
+				if (err)
+					return ERR_PTR(err);
+				/* Start over. */
+				goto again;
+			}
+
+			/* Next, hold onto the lock, so the bucket doesn't
+			 * change while we get the rest of the sockets.
+			 */
+			err = bpf_iter_udp_realloc_batch(iter, batch_sks,
+							 GFP_NOWAIT);
+			if (err) {
+				spin_unlock_bh(&hslot2->lock);
+				return ERR_PTR(err);
+			}
+
+			/* Pick up where we left off. */
+			sk = iter->batch[iter->end_sk - 1].sk;
+			sk = hlist_entry_safe(sk->__sk_common.skc_portaddr_node.next,
+					      struct sock,
+					      __sk_common.skc_portaddr_node);
+			batch_sks = iter->end_sk;
+			goto fill_batch;
+		}
+
 		spin_unlock_bh(&hslot2->lock);
 
 		if (iter->end_sk)
 			break;
+next_bucket:
+		resizes = 0;
 	}
 
-	/* All done: no batch made. */
-	if (!iter->end_sk)
-		return NULL;
-
-	if (iter->end_sk == batch_sks) {
-		/* Batching is done for the current bucket; return the first
-		 * socket to be iterated from the batch.
-		 */
-		iter->st_bucket_done = true;
-		goto done;
-	}
-	if (!resized && !bpf_iter_udp_realloc_batch(iter, batch_sks * 3 / 2)) {
-		resized = true;
-		/* After allocating a larger batch, retry one more time to grab
-		 * the whole bucket.
-		 */
-		goto again;
-	}
-done:
-	return iter->batch[0];
+	WARN_ON_ONCE(iter->end_sk != batch_sks);
+	return iter->end_sk ? iter->batch[0].sk : NULL;
 }
 
 static void *bpf_iter_udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
@@ -3498,16 +3570,14 @@ static void *bpf_iter_udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	/* Whenever seq_next() is called, the iter->cur_sk is
 	 * done with seq_show(), so unref the iter->cur_sk.
 	 */
-	if (iter->cur_sk < iter->end_sk) {
-		sock_put(iter->batch[iter->cur_sk++]);
-		++iter->offset;
-	}
+	if (iter->cur_sk < iter->end_sk)
+		sock_put(iter->batch[iter->cur_sk++].sk);
 
 	/* After updating iter->cur_sk, check if there are more sockets
 	 * available in the current bucket batch.
 	 */
 	if (iter->cur_sk < iter->end_sk)
-		sk = iter->batch[iter->cur_sk];
+		sk = iter->batch[iter->cur_sk].sk;
 	else
 		/* Prepare a new batch. */
 		sk = bpf_iter_udp_batch(seq);
@@ -3571,8 +3641,19 @@ unlock:
 
 static void bpf_iter_udp_put_batch(struct bpf_udp_iter_state *iter)
 {
-	while (iter->cur_sk < iter->end_sk)
-		sock_put(iter->batch[iter->cur_sk++]);
+	union bpf_udp_iter_batch_item *item;
+	unsigned int cur_sk = iter->cur_sk;
+	__u64 cookie;
+
+	/* Remember the cookies of the sockets we haven't seen yet, so we can
+	 * pick up where we left off next time around.
+	 */
+	while (cur_sk < iter->end_sk) {
+		item = &iter->batch[cur_sk++];
+		cookie = sock_gen_cookie(item->sk);
+		sock_put(item->sk);
+		item->cookie = cookie;
+	}
 }
 
 static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v)
@@ -3588,10 +3669,8 @@ static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v)
 			(void)udp_prog_seq_show(prog, &meta, v, 0, 0);
 	}
 
-	if (iter->cur_sk < iter->end_sk) {
+	if (iter->cur_sk < iter->end_sk)
 		bpf_iter_udp_put_batch(iter);
-		iter->st_bucket_done = false;
-	}
 }
 
 static const struct seq_operations bpf_iter_udp_seq_ops = {
@@ -3842,16 +3921,19 @@ DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta,
 		     struct udp_sock *udp_sk, uid_t uid, int bucket)
 
 static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter,
-				      unsigned int new_batch_sz)
+				      unsigned int new_batch_sz, gfp_t flags)
 {
-	struct sock **new_batch;
+	union bpf_udp_iter_batch_item *new_batch;
 
 	new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch),
-				   GFP_USER | __GFP_NOWARN);
+				   flags | __GFP_NOWARN);
 	if (!new_batch)
 		return -ENOMEM;
 
-	bpf_iter_udp_put_batch(iter);
+	if (flags != GFP_NOWAIT)
+		bpf_iter_udp_put_batch(iter);
+
+	memcpy(new_batch, iter->batch, sizeof(*iter->batch) * iter->end_sk);
 	kvfree(iter->batch);
 	iter->batch = new_batch;
 	iter->max_sk = new_batch_sz;
@@ -3870,10 +3952,12 @@ static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux)
 	if (ret)
 		return ret;
 
-	ret = bpf_iter_udp_realloc_batch(iter, INIT_BATCH_SZ);
+	ret = bpf_iter_udp_realloc_batch(iter, INIT_BATCH_SZ, GFP_USER);
 	if (ret)
 		bpf_iter_fini_seq_net(priv_data);
 
+	iter->state.bucket = -1;
+
 	return ret;
 }
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 787b2947d3a0..9c775f8aa438 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -410,6 +410,62 @@ static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs)
 	return segs;
 }
 
+static void __udpv6_gso_segment_csum(struct sk_buff *seg,
+				     struct in6_addr *oldip,
+				     const struct in6_addr *newip,
+				     __be16 *oldport, __be16 newport)
+{
+	struct udphdr *uh = udp_hdr(seg);
+
+	if (ipv6_addr_equal(oldip, newip) && *oldport == newport)
+		return;
+
+	if (uh->check) {
+		inet_proto_csum_replace16(&uh->check, seg, oldip->s6_addr32,
+					  newip->s6_addr32, true);
+
+		inet_proto_csum_replace2(&uh->check, seg, *oldport, newport,
+					 false);
+		if (!uh->check)
+			uh->check = CSUM_MANGLED_0;
+	}
+
+	*oldip = *newip;
+	*oldport = newport;
+}
+
+static struct sk_buff *__udpv6_gso_segment_list_csum(struct sk_buff *segs)
+{
+	const struct ipv6hdr *iph;
+	const struct udphdr *uh;
+	struct ipv6hdr *iph2;
+	struct sk_buff *seg;
+	struct udphdr *uh2;
+
+	seg = segs;
+	uh = udp_hdr(seg);
+	iph = ipv6_hdr(seg);
+	uh2 = udp_hdr(seg->next);
+	iph2 = ipv6_hdr(seg->next);
+
+	if (!(*(const u32 *)&uh->source ^ *(const u32 *)&uh2->source) &&
+	    ipv6_addr_equal(&iph->saddr, &iph2->saddr) &&
+	    ipv6_addr_equal(&iph->daddr, &iph2->daddr))
+		return segs;
+
+	while ((seg = seg->next)) {
+		uh2 = udp_hdr(seg);
+		iph2 = ipv6_hdr(seg);
+
+		__udpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr,
+					 &uh2->source, uh->source);
+		__udpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr,
+					 &uh2->dest, uh->dest);
+	}
+
+	return segs;
+}
+
 static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
 					      netdev_features_t features,
 					      bool is_ipv6)
@@ -422,7 +478,10 @@ static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
 
 	udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss);
 
-	return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb);
+	if (is_ipv6)
+		return __udpv6_gso_segment_list_csum(skb);
+	else
+		return __udpv4_gso_segment_list_csum(skb);
 }
 
 struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index 3d1214e6df0e..2326548997d3 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -90,6 +90,8 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 
 	udp_tunnel_encap_enable(sk);
 
+	udp_tunnel_update_gro_rcv(sk, true);
+
 	if (!sk->sk_dport && !sk->sk_bound_dev_if && sk_saddr_any(sk) &&
 	    sk->sk_kern_sock)
 		udp_tunnel_update_gro_lookup(net, sk, true);
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index b5b06323cfd9..0d31a8c108d4 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -182,11 +182,15 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 	int offset = skb_gro_offset(skb);
 	const struct net_offload *ops;
 	struct sk_buff *pp = NULL;
-	int ret;
-
-	offset = offset - sizeof(struct udphdr);
+	int len, dlen;
+	__u8 *udpdata;
+	__be32 *udpdata32;
 
-	if (!pskb_pull(skb, offset))
+	len = skb->len - offset;
+	dlen = offset + min(len, 8);
+	udpdata = skb_gro_header(skb, dlen, offset);
+	udpdata32 = (__be32 *)udpdata;
+	if (unlikely(!udpdata))
 		return NULL;
 
 	rcu_read_lock();
@@ -194,11 +198,10 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 	if (!ops || !ops->callbacks.gro_receive)
 		goto out;
 
-	ret = __xfrm4_udp_encap_rcv(sk, skb, false);
-	if (ret)
+	/* check if it is a keepalive or IKE packet */
+	if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
 		goto out;
 
-	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
 
 	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
@@ -208,7 +211,6 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 
 out:
 	rcu_read_unlock();
-	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->same_flow = 0;
 	NAPI_GRO_CB(skb)->flush = 1;
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 9ba83f0c9928..43b19adfbf88 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3214,16 +3214,13 @@ static void add_v4_addrs(struct inet6_dev *idev)
 	struct in6_addr addr;
 	struct net_device *dev;
 	struct net *net = dev_net(idev->dev);
-	int scope, plen, offset = 0;
+	int scope, plen;
 	u32 pflags = 0;
 
 	ASSERT_RTNL();
 
 	memset(&addr, 0, sizeof(struct in6_addr));
-	/* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */
-	if (idev->dev->addr_len == sizeof(struct in6_addr))
-		offset = sizeof(struct in6_addr) - 4;
-	memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4);
+	memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4);
 
 	if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) {
 		scope = IPV6_ADDR_COMPATv4;
@@ -3534,7 +3531,13 @@ static void addrconf_gre_config(struct net_device *dev)
 		return;
 	}
 
-	if (dev->type == ARPHRD_ETHER) {
+	/* Generate the IPv6 link-local address using addrconf_addr_gen(),
+	 * unless we have an IPv4 GRE device not bound to an IP address and
+	 * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this
+	 * case). Such devices fall back to add_v4_addrs() instead.
+	 */
+	if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 &&
+	      idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) {
 		addrconf_addr_gen(idev, true);
 		return;
 	}
@@ -5346,12 +5349,12 @@ static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh,
 	struct ifaddrmsg *ifm;
 	int err, i;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+	ifm = nlmsg_payload(nlh, sizeof(*ifm));
+	if (!ifm) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid header for address dump request");
 		return -EINVAL;
 	}
 
-	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address dump request");
 		return -EINVAL;
@@ -5484,7 +5487,8 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb,
 	struct ifaddrmsg *ifm;
 	int i, err;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+	ifm = nlmsg_payload(nlh, sizeof(*ifm));
+	if (!ifm) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid header for get address request");
 		return -EINVAL;
 	}
@@ -5493,7 +5497,6 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb,
 		return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
 					      ifa_ipv6_policy, extack);
 
-	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request");
 		return -EINVAL;
@@ -6112,7 +6115,8 @@ static int inet6_valid_dump_ifinfo(const struct nlmsghdr *nlh,
 {
 	struct ifinfomsg *ifm;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+	ifm = nlmsg_payload(nlh, sizeof(*ifm));
+	if (!ifm) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid header for link dump request");
 		return -EINVAL;
 	}
@@ -6122,7 +6126,6 @@ static int inet6_valid_dump_ifinfo(const struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
-	ifm = nlmsg_data(nlh);
 	if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
 	    ifm->ifi_change || ifm->ifi_index) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for dump request");
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index ab054f329e12..fb63ffbcfc64 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -473,12 +473,12 @@ static int ip6addrlbl_valid_dump_req(const struct nlmsghdr *nlh,
 {
 	struct ifaddrlblmsg *ifal;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifal))) {
+	ifal = nlmsg_payload(nlh, sizeof(*ifal));
+	if (!ifal) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid header for address label dump request");
 		return -EINVAL;
 	}
 
-	ifal = nlmsg_data(nlh);
 	if (ifal->__ifal_reserved || ifal->ifal_prefixlen ||
 	    ifal->ifal_flags || ifal->ifal_index || ifal->ifal_seq) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address label dump request");
@@ -543,7 +543,8 @@ static int ip6addrlbl_valid_get_req(struct sk_buff *skb,
 	struct ifaddrlblmsg *ifal;
 	int i, err;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifal))) {
+	ifal = nlmsg_payload(nlh, sizeof(*ifal));
+	if (!ifal) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid header for addrlabel get request");
 		return -EINVAL;
 	}
@@ -552,7 +553,6 @@ static int ip6addrlbl_valid_get_req(struct sk_buff *skb,
 		return nlmsg_parse_deprecated(nlh, sizeof(*ifal), tb,
 					      IFAL_MAX, ifal_policy, extack);
 
-	ifal = nlmsg_data(nlh);
 	if (ifal->__ifal_reserved || ifal->ifal_flags || ifal->ifal_seq) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for addrlabel get request");
 		return -EINVAL;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index f60ec8b0f8ea..acaff1296783 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -715,6 +715,7 @@ const struct proto_ops inet6_stream_ops = {
 #endif
 	.set_rcvlowat	   = tcp_set_rcvlowat,
 };
+EXPORT_SYMBOL_GPL(inet6_stream_ops);
 
 const struct proto_ops inet6_dgram_ops = {
 	.family		   = PF_INET6,
@@ -881,7 +882,6 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
 	}
 	return false;
 }
-EXPORT_SYMBOL_GPL(ipv6_opt_accepted);
 
 static struct packet_type ipv6_packet_type __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IPV6),
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 9e73944e3b53..72adfc107b55 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -137,47 +137,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 }
 
 #ifdef CONFIG_INET6_ESPINTCP
-struct esp_tcp_sk {
-	struct sock *sk;
-	struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
-	struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
-	sock_put(esk->sk);
-	kfree(esk);
-}
-
 static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
 {
 	struct xfrm_encap_tmpl *encap = x->encap;
 	struct net *net = xs_net(x);
-	struct esp_tcp_sk *esk;
 	__be16 sport, dport;
-	struct sock *nsk;
 	struct sock *sk;
 
-	sk = rcu_dereference(x->encap_sk);
-	if (sk && sk->sk_state == TCP_ESTABLISHED)
-		return sk;
-
 	spin_lock_bh(&x->lock);
 	sport = encap->encap_sport;
 	dport = encap->encap_dport;
-	nsk = rcu_dereference_protected(x->encap_sk,
-					lockdep_is_held(&x->lock));
-	if (sk && sk == nsk) {
-		esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
-		if (!esk) {
-			spin_unlock_bh(&x->lock);
-			return ERR_PTR(-ENOMEM);
-		}
-		RCU_INIT_POINTER(x->encap_sk, NULL);
-		esk->sk = sk;
-		call_rcu(&esk->rcu, esp_free_tcp_sk);
-	}
 	spin_unlock_bh(&x->lock);
 
 	sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &x->id.daddr.in6,
@@ -190,20 +159,6 @@ static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
 		return ERR_PTR(-EINVAL);
 	}
 
-	spin_lock_bh(&x->lock);
-	nsk = rcu_dereference_protected(x->encap_sk,
-					lockdep_is_held(&x->lock));
-	if (encap->encap_sport != sport ||
-	    encap->encap_dport != dport) {
-		sock_put(sk);
-		sk = nsk ?: ERR_PTR(-EREMCHG);
-	} else if (sk == nsk) {
-		sock_put(sk);
-	} else {
-		rcu_assign_pointer(x->encap_sk, sk);
-	}
-	spin_unlock_bh(&x->lock);
-
 	return sk;
 }
 
@@ -216,8 +171,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
 
 	sk = esp6_find_tcp_sk(x);
 	err = PTR_ERR_OR_ZERO(sk);
-	if (err)
+	if (err) {
+		kfree_skb(skb);
 		goto out;
+	}
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk))
@@ -226,6 +183,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
 		err = espintcp_push_skb(sk, skb);
 	bh_unlock_sock(sk);
 
+	sock_put(sk);
+
 out:
 	rcu_read_unlock();
 	return err;
@@ -422,6 +381,8 @@ static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x,
 	if (IS_ERR(sk))
 		return ERR_CAST(sk);
 
+	sock_put(sk);
+
 	*lenp = htons(len);
 	esph = (struct ip_esp_hdr *)(lenp + 1);
 
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index dbcf556a35bb..8f500eaf33cf 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -54,7 +54,6 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
 
 	return dst;
 }
-EXPORT_SYMBOL(inet6_csk_route_req);
 
 static inline
 struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
@@ -137,4 +136,3 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu)
 	dst = inet6_csk_route_socket(sk, &fl6);
 	return IS_ERR(dst) ? NULL : dst;
 }
-EXPORT_SYMBOL_GPL(inet6_csk_update_pmtu);
diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index 09065187378e..40df8bdfaacd 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -38,6 +38,7 @@ struct ioam6_lwt_freq {
 };
 
 struct ioam6_lwt {
+	struct dst_entry null_dst;
 	struct dst_cache cache;
 	struct ioam6_lwt_freq freq;
 	atomic_t pkt_cnt;
@@ -177,6 +178,14 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla,
 	if (err)
 		goto free_lwt;
 
+	/* This "fake" dst_entry will be stored in a dst_cache, which will call
+	 * dst_hold() and dst_release() on it. We must ensure that dst_destroy()
+	 * will never be called. For that, its initial refcount is 1 and +1 when
+	 * it is stored in the cache. Then, +1/-1 each time we read the cache
+	 * and release it. Long story short, we're fine.
+	 */
+	dst_init(&ilwt->null_dst, NULL, NULL, DST_OBSOLETE_NONE, DST_NOCOUNT);
+
 	atomic_set(&ilwt->pkt_cnt, 0);
 	ilwt->freq.k = freq_k;
 	ilwt->freq.n = freq_n;
@@ -336,7 +345,8 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
 
 static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb), *cache_dst = NULL;
+	struct dst_entry *orig_dst = skb_dst(skb);
+	struct dst_entry *dst = NULL;
 	struct ioam6_lwt *ilwt;
 	int err = -EINVAL;
 	u32 pkt_cnt;
@@ -344,7 +354,7 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (skb->protocol != htons(ETH_P_IPV6))
 		goto drop;
 
-	ilwt = ioam6_lwt_state(dst->lwtstate);
+	ilwt = ioam6_lwt_state(orig_dst->lwtstate);
 
 	/* Check for insertion frequency (i.e., "k over n" insertions) */
 	pkt_cnt = atomic_fetch_inc(&ilwt->pkt_cnt);
@@ -352,9 +362,20 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 		goto out;
 
 	local_bh_disable();
-	cache_dst = dst_cache_get(&ilwt->cache);
+	dst = dst_cache_get(&ilwt->cache);
 	local_bh_enable();
 
+	/* This is how we notify that the destination does not change after
+	 * transformation and that we need to use orig_dst instead of the cache
+	 */
+	if (dst == &ilwt->null_dst) {
+		dst_release(dst);
+
+		dst = orig_dst;
+		/* keep refcount balance: dst_release() is called at the end */
+		dst_hold(dst);
+	}
+
 	switch (ilwt->mode) {
 	case IOAM6_IPTUNNEL_MODE_INLINE:
 do_inline:
@@ -362,7 +383,7 @@ do_inline:
 		if (ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP)
 			goto out;
 
-		err = ioam6_do_inline(net, skb, &ilwt->tuninfo, cache_dst);
+		err = ioam6_do_inline(net, skb, &ilwt->tuninfo, dst);
 		if (unlikely(err))
 			goto drop;
 
@@ -372,7 +393,7 @@ do_encap:
 		/* Encapsulation (ip6ip6) */
 		err = ioam6_do_encap(net, skb, &ilwt->tuninfo,
 				     ilwt->has_tunsrc, &ilwt->tunsrc,
-				     &ilwt->tundst, cache_dst);
+				     &ilwt->tundst, dst);
 		if (unlikely(err))
 			goto drop;
 
@@ -390,7 +411,7 @@ do_encap:
 		goto drop;
 	}
 
-	if (unlikely(!cache_dst)) {
+	if (unlikely(!dst)) {
 		struct ipv6hdr *hdr = ipv6_hdr(skb);
 		struct flowi6 fl6;
 
@@ -401,20 +422,27 @@ do_encap:
 		fl6.flowi6_mark = skb->mark;
 		fl6.flowi6_proto = hdr->nexthdr;
 
-		cache_dst = ip6_route_output(net, NULL, &fl6);
-		if (cache_dst->error) {
-			err = cache_dst->error;
+		dst = ip6_route_output(net, NULL, &fl6);
+		if (dst->error) {
+			err = dst->error;
 			goto drop;
 		}
 
-		/* cache only if we don't create a dst reference loop */
-		if (dst->lwtstate != cache_dst->lwtstate) {
-			local_bh_disable();
-			dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr);
-			local_bh_enable();
-		}
-
-		err = skb_cow_head(skb, LL_RESERVED_SPACE(cache_dst->dev));
+		/* If the destination is the same after transformation (which is
+		 * a valid use case for IOAM), then we don't want to add it to
+		 * the cache in order to avoid a reference loop. Instead, we add
+		 * our fake dst_entry to the cache as a way to detect this case.
+		 * Otherwise, we add the resolved destination to the cache.
+		 */
+		local_bh_disable();
+		if (orig_dst->lwtstate == dst->lwtstate)
+			dst_cache_set_ip6(&ilwt->cache,
+					  &ilwt->null_dst, &fl6.saddr);
+		else
+			dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr);
+		local_bh_enable();
+
+		err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
 		if (unlikely(err))
 			goto drop;
 	}
@@ -422,22 +450,26 @@ do_encap:
 	/* avoid lwtunnel_output() reentry loop when destination is the same
 	 * after transformation (e.g., with the inline mode)
 	 */
-	if (dst->lwtstate != cache_dst->lwtstate) {
+	if (orig_dst->lwtstate != dst->lwtstate) {
 		skb_dst_drop(skb);
-		skb_dst_set(skb, cache_dst);
+		skb_dst_set(skb, dst);
 		return dst_output(net, sk, skb);
 	}
 out:
-	dst_release(cache_dst);
-	return dst->lwtstate->orig_output(net, sk, skb);
+	dst_release(dst);
+	return orig_dst->lwtstate->orig_output(net, sk, skb);
 drop:
-	dst_release(cache_dst);
+	dst_release(dst);
 	kfree_skb(skb);
 	return err;
 }
 
 static void ioam6_destroy_state(struct lwtunnel_state *lwt)
 {
+	/* Since the refcount of per-cpu dst_entry caches will never be 0 (see
+	 * why above) when our "fake" dst_entry is used, it is not necessary to
+	 * remove them before calling dst_cache_destroy()
+	 */
 	dst_cache_destroy(&ioam6_lwt_state(lwt)->cache);
 }
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index bf727149fdec..7094d7708686 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -249,40 +249,52 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 
 struct fib6_table *fib6_new_table(struct net *net, u32 id)
 {
-	struct fib6_table *tb;
+	struct fib6_table *tb, *new_tb;
 
 	if (id == 0)
 		id = RT6_TABLE_MAIN;
+
 	tb = fib6_get_table(net, id);
 	if (tb)
 		return tb;
 
-	tb = fib6_alloc_table(net, id);
-	if (tb)
-		fib6_link_table(net, tb);
+	new_tb = fib6_alloc_table(net, id);
+	if (!new_tb)
+		return NULL;
+
+	spin_lock_bh(&net->ipv6.fib_table_hash_lock);
+
+	tb = fib6_get_table(net, id);
+	if (unlikely(tb)) {
+		spin_unlock_bh(&net->ipv6.fib_table_hash_lock);
+		kfree(new_tb);
+		return tb;
+	}
+
+	fib6_link_table(net, new_tb);
+
+	spin_unlock_bh(&net->ipv6.fib_table_hash_lock);
 
-	return tb;
+	return new_tb;
 }
 EXPORT_SYMBOL_GPL(fib6_new_table);
 
 struct fib6_table *fib6_get_table(struct net *net, u32 id)
 {
-	struct fib6_table *tb;
 	struct hlist_head *head;
-	unsigned int h;
+	struct fib6_table *tb;
 
-	if (id == 0)
+	if (!id)
 		id = RT6_TABLE_MAIN;
-	h = id & (FIB6_TABLE_HASHSZ - 1);
-	rcu_read_lock();
-	head = &net->ipv6.fib_table_hash[h];
-	hlist_for_each_entry_rcu(tb, head, tb6_hlist) {
-		if (tb->tb6_id == id) {
-			rcu_read_unlock();
+
+	head = &net->ipv6.fib_table_hash[id & (FIB6_TABLE_HASHSZ - 1)];
+
+	/* See comment in fib6_link_table().  RCU is not required,
+	 * but rcu_dereference_raw() is used to avoid data-race.
+	 */
+	hlist_for_each_entry_rcu(tb, head, tb6_hlist, true)
+		if (tb->tb6_id == id)
 			return tb;
-		}
-	}
-	rcu_read_unlock();
 
 	return NULL;
 }
@@ -1015,8 +1027,9 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 			.table = table
 		};
 
-		nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from,
-					 &arg);
+		rcu_read_lock();
+		nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, &arg);
+		rcu_read_unlock();
 	} else {
 		struct fib6_nh *fib6_nh;
 
@@ -1034,8 +1047,14 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 	rt6_flush_exceptions(rt);
 	fib6_drop_pcpu_from(rt, table);
 
-	if (rt->nh && !list_empty(&rt->nh_list))
-		list_del_init(&rt->nh_list);
+	if (rt->nh) {
+		spin_lock(&rt->nh->lock);
+
+		if (!list_empty(&rt->nh_list))
+			list_del_init(&rt->nh_list);
+
+		spin_unlock(&rt->nh->lock);
+	}
 
 	if (refcount_read(&rt->fib6_ref) != 1) {
 		/* This route is used as dummy address holder in some split
@@ -1069,8 +1088,8 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
  */
 
 static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
-			    struct nl_info *info,
-			    struct netlink_ext_ack *extack)
+			    struct nl_info *info, struct netlink_ext_ack *extack,
+			    struct list_head *purge_list)
 {
 	struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
 				    lockdep_is_held(&rt->fib6_table->tb6_lock));
@@ -1203,7 +1222,9 @@ next_iter:
 			fib6_nsiblings++;
 		}
 		BUG_ON(fib6_nsiblings != rt->fib6_nsiblings);
+		rcu_read_lock();
 		rt6_multipath_rebalance(temp_sibling);
+		rcu_read_unlock();
 	}
 
 	/*
@@ -1246,7 +1267,9 @@ add:
 					sibling->fib6_nsiblings--;
 				rt->fib6_nsiblings = 0;
 				list_del_rcu(&rt->fib6_siblings);
+				rcu_read_lock();
 				rt6_multipath_rebalance(next_sibling);
+				rcu_read_unlock();
 				return err;
 			}
 		}
@@ -1294,10 +1317,9 @@ add:
 		}
 		nsiblings = iter->fib6_nsiblings;
 		iter->fib6_node = NULL;
-		fib6_purge_rt(iter, fn, info->nl_net);
+		list_add(&iter->purge_link, purge_list);
 		if (rcu_access_pointer(fn->rr_ptr) == iter)
 			fn->rr_ptr = NULL;
-		fib6_info_release(iter);
 
 		if (nsiblings) {
 			/* Replacing an ECMP route, remove all siblings */
@@ -1310,10 +1332,9 @@ add:
 				if (rt6_qualify_for_ecmp(iter)) {
 					*ins = iter->fib6_next;
 					iter->fib6_node = NULL;
-					fib6_purge_rt(iter, fn, info->nl_net);
+					list_add(&iter->purge_link, purge_list);
 					if (rcu_access_pointer(fn->rr_ptr) == iter)
 						fn->rr_ptr = NULL;
-					fib6_info_release(iter);
 					nsiblings--;
 					info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
 				} else {
@@ -1329,6 +1350,28 @@ add:
 	return 0;
 }
 
+static int fib6_add_rt2node_nh(struct fib6_node *fn, struct fib6_info *rt,
+			       struct nl_info *info, struct netlink_ext_ack *extack,
+			       struct list_head *purge_list)
+{
+	int err;
+
+	spin_lock(&rt->nh->lock);
+
+	if (rt->nh->dead) {
+		NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+		err = -EINVAL;
+	} else {
+		err = fib6_add_rt2node(fn, rt, info, extack, purge_list);
+		if (!err)
+			list_add(&rt->nh_list, &rt->nh->f6i_list);
+	}
+
+	spin_unlock(&rt->nh->lock);
+
+	return err;
+}
+
 static void fib6_start_gc(struct net *net, struct fib6_info *rt)
 {
 	if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
@@ -1383,6 +1426,7 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 	     struct nl_info *info, struct netlink_ext_ack *extack)
 {
 	struct fib6_table *table = rt->fib6_table;
+	LIST_HEAD(purge_list);
 	struct fib6_node *fn;
 #ifdef CONFIG_IPV6_SUBTREES
 	struct fib6_node *pn = NULL;
@@ -1485,10 +1529,19 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 	}
 #endif
 
-	err = fib6_add_rt2node(fn, rt, info, extack);
+	if (rt->nh)
+		err = fib6_add_rt2node_nh(fn, rt, info, extack, &purge_list);
+	else
+		err = fib6_add_rt2node(fn, rt, info, extack, &purge_list);
 	if (!err) {
-		if (rt->nh)
-			list_add(&rt->nh_list, &rt->nh->f6i_list);
+		struct fib6_info *iter, *next;
+
+		list_for_each_entry_safe(iter, next, &purge_list, purge_link) {
+			list_del(&iter->purge_link);
+			fib6_purge_rt(iter, fn, info->nl_net);
+			fib6_info_release(iter);
+		}
+
 		__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
 
 		if (rt->fib6_flags & RTF_EXPIRES)
@@ -2423,6 +2476,8 @@ static int __net_init fib6_net_init(struct net *net)
 	if (!net->ipv6.fib_table_hash)
 		goto out_rt6_stats;
 
+	spin_lock_init(&net->ipv6.fib_table_hash_lock);
+
 	net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl),
 					  GFP_KERNEL);
 	if (!net->ipv6.fib6_main_tbl)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 957ca98fa70f..2dc9dcffe2ca 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1570,7 +1570,7 @@ static struct inet6_protocol ip6gre_protocol __read_mostly = {
 	.flags       = INET6_PROTO_FINAL,
 };
 
-static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
+static void __net_exit ip6gre_exit_rtnl_net(struct net *net, struct list_head *head)
 {
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 	struct net_device *dev, *aux;
@@ -1587,16 +1587,16 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
 		for (h = 0; h < IP6_GRE_HASH_SIZE; h++) {
 			struct ip6_tnl *t;
 
-			t = rtnl_dereference(ign->tunnels[prio][h]);
+			t = rtnl_net_dereference(net, ign->tunnels[prio][h]);
 
 			while (t) {
 				/* If dev is in the same netns, it has already
 				 * been added to the list by the previous loop.
 				 */
 				if (!net_eq(dev_net(t->dev), net))
-					unregister_netdevice_queue(t->dev,
-								   head);
-				t = rtnl_dereference(t->next);
+					unregister_netdevice_queue(t->dev, head);
+
+				t = rtnl_net_dereference(net, t->next);
 			}
 		}
 	}
@@ -1640,19 +1640,9 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit ip6gre_exit_batch_rtnl(struct list_head *net_list,
-					      struct list_head *dev_to_kill)
-{
-	struct net *net;
-
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list)
-		ip6gre_destroy_tunnels(net, dev_to_kill);
-}
-
 static struct pernet_operations ip6gre_net_ops = {
 	.init = ip6gre_init_net,
-	.exit_batch_rtnl = ip6gre_exit_batch_rtnl,
+	.exit_rtnl = ip6gre_exit_rtnl_net,
 	.id   = &ip6gre_net_id,
 	.size = sizeof(struct ip6gre_net),
 };
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 581bc6289081..7bd29a9ff0db 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -259,7 +259,7 @@ bool ip6_autoflowlabel(struct net *net, const struct sock *sk)
 }
 
 /*
- * xmit an sk_buff (used by TCP, SCTP and DCCP)
+ * xmit an sk_buff (used by TCP and SCTP)
  * Note : socket lock is not held for SYNACK packets, but might be modified
  * by calls to skb_set_owner_w() and ipv6_local_error(),
  * which are using proper atomic operations or spinlocks.
@@ -1524,7 +1524,8 @@ emsgsize:
 				uarg = msg->msg_ubuf;
 			}
 		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
-			uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
+			uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb),
+						    false);
 			if (!uarg)
 				return -ENOBUFS;
 			extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a04dd1bb4b19..894d3158a6f0 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2210,7 +2210,7 @@ static struct xfrm6_tunnel mplsip6_handler __read_mostly = {
 	.priority	=	1,
 };
 
-static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head *list)
+static void __net_exit ip6_tnl_exit_rtnl_net(struct net *net, struct list_head *list)
 {
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	struct net_device *dev, *aux;
@@ -2222,25 +2222,27 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head
 			unregister_netdevice_queue(dev, list);
 
 	for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) {
-		t = rtnl_dereference(ip6n->tnls_r_l[h]);
+		t = rtnl_net_dereference(net, ip6n->tnls_r_l[h]);
 		while (t) {
 			/* If dev is in the same netns, it has already
 			 * been added to the list by the previous loop.
 			 */
 			if (!net_eq(dev_net(t->dev), net))
 				unregister_netdevice_queue(t->dev, list);
-			t = rtnl_dereference(t->next);
+
+			t = rtnl_net_dereference(net, t->next);
 		}
 	}
 
-	t = rtnl_dereference(ip6n->tnls_wc[0]);
+	t = rtnl_net_dereference(net, ip6n->tnls_wc[0]);
 	while (t) {
 		/* If dev is in the same netns, it has already
 		 * been added to the list by the previous loop.
 		 */
 		if (!net_eq(dev_net(t->dev), net))
 			unregister_netdevice_queue(t->dev, list);
-		t = rtnl_dereference(t->next);
+
+		t = rtnl_net_dereference(net, t->next);
 	}
 }
 
@@ -2287,19 +2289,9 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit ip6_tnl_exit_batch_rtnl(struct list_head *net_list,
-					       struct list_head *dev_to_kill)
-{
-	struct net *net;
-
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list)
-		ip6_tnl_destroy_tunnels(net, dev_to_kill);
-}
-
 static struct pernet_operations ip6_tnl_net_ops = {
 	.init = ip6_tnl_init_net,
-	.exit_batch_rtnl = ip6_tnl_exit_batch_rtnl,
+	.exit_rtnl = ip6_tnl_exit_rtnl_net,
 	.id   = &ip6_tnl_net_id,
 	.size = sizeof(struct ip6_tnl_net),
 };
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 09ec4b0ad7dc..40464a88bca6 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1112,21 +1112,21 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = {
 	.get_link_net	= ip6_tnl_get_link_net,
 };
 
-static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n,
-					    struct list_head *list)
+static void __net_exit vti6_exit_rtnl_net(struct net *net, struct list_head *list)
 {
-	int h;
+	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
 	struct ip6_tnl *t;
+	int h;
 
 	for (h = 0; h < IP6_VTI_HASH_SIZE; h++) {
-		t = rtnl_dereference(ip6n->tnls_r_l[h]);
+		t = rtnl_net_dereference(net, ip6n->tnls_r_l[h]);
 		while (t) {
 			unregister_netdevice_queue(t->dev, list);
-			t = rtnl_dereference(t->next);
+			t = rtnl_net_dereference(net, t->next);
 		}
 	}
 
-	t = rtnl_dereference(ip6n->tnls_wc[0]);
+	t = rtnl_net_dereference(net, ip6n->tnls_wc[0]);
 	if (t)
 		unregister_netdevice_queue(t->dev, list);
 }
@@ -1170,22 +1170,9 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit vti6_exit_batch_rtnl(struct list_head *net_list,
-					    struct list_head *dev_to_kill)
-{
-	struct vti6_net *ip6n;
-	struct net *net;
-
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list) {
-		ip6n = net_generic(net, vti6_net_id);
-		vti6_destroy_tunnels(ip6n, dev_to_kill);
-	}
-}
-
 static struct pernet_operations vti6_net_ops = {
 	.init = vti6_init_net,
-	.exit_batch_rtnl = vti6_exit_batch_rtnl,
+	.exit_rtnl = vti6_exit_rtnl_net,
 	.id   = &vti6_net_id,
 	.size = sizeof(struct vti6_net),
 };
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index b413c9c8a21c..3276cde5ebd7 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -108,11 +108,6 @@ static void ipmr_expire_process(struct timer_list *t);
 				lockdep_rtnl_is_held() || \
 				list_empty(&net->ipv6.mr6_tables))
 
-static bool ip6mr_can_free_table(struct net *net)
-{
-	return !check_net(net) || !net_initialized(net);
-}
-
 static struct mr_table *ip6mr_mr_table_iter(struct net *net,
 					    struct mr_table *mrt)
 {
@@ -306,11 +301,6 @@ EXPORT_SYMBOL(ip6mr_rule_default);
 #define ip6mr_for_each_table(mrt, net) \
 	for (mrt = net->ipv6.mrt6; mrt; mrt = NULL)
 
-static bool ip6mr_can_free_table(struct net *net)
-{
-	return !check_net(net);
-}
-
 static struct mr_table *ip6mr_mr_table_iter(struct net *net,
 					    struct mr_table *mrt)
 {
@@ -416,7 +406,7 @@ static void ip6mr_free_table(struct mr_table *mrt)
 {
 	struct net *net = read_pnet(&mrt->net);
 
-	WARN_ON_ONCE(!ip6mr_can_free_table(net));
+	WARN_ON_ONCE(!mr_can_free_table(net));
 
 	timer_shutdown_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC |
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 581ce055bf52..4541836ee3da 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -164,20 +164,20 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		struct ip6_fraglist_iter iter;
 		struct sk_buff *frag2;
 
-		if (first_len - hlen > mtu ||
-		    skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
+		if (first_len - hlen > mtu)
 			goto blackhole;
 
-		if (skb_cloned(skb))
+		if (skb_cloned(skb) ||
+		    skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
 			goto slow_path;
 
 		skb_walk_frags(skb, frag2) {
-			if (frag2->len > mtu ||
-			    skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
+			if (frag2->len > mtu)
 				goto blackhole;
 
 			/* Partially cloned skb? */
-			if (skb_shared(frag2))
+			if (skb_shared(frag2) ||
+			    skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
 				goto slow_path;
 		}
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 210b84cecc24..0143262094b0 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1771,6 +1771,7 @@ out:
 	if (!err) {
 		spin_lock_bh(&f6i->fib6_table->tb6_lock);
 		fib6_update_sernum(net, f6i);
+		fib6_add_gc_list(f6i);
 		spin_unlock_bh(&f6i->fib6_table->tb6_lock);
 		fib6_force_start_gc(net);
 	}
@@ -1819,11 +1820,13 @@ static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg)
 
 void rt6_flush_exceptions(struct fib6_info *f6i)
 {
-	if (f6i->nh)
-		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions,
-					 f6i);
-	else
+	if (f6i->nh) {
+		rcu_read_lock();
+		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions, f6i);
+		rcu_read_unlock();
+	} else {
 		fib6_nh_flush_exceptions(f6i->fib6_nh, f6i);
+	}
 }
 
 /* Find cached rt in the hash table inside passed in rt
@@ -2491,8 +2494,12 @@ static u32 rt6_multipath_custom_hash_fl6(const struct net *net,
 		hash_keys.basic.ip_proto = fl6->flowi6_proto;
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL)
 		hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
-	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
-		hash_keys.ports.src = fl6->fl6_sport;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) {
+		if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT)
+			hash_keys.ports.src = (__force __be16)get_random_u16();
+		else
+			hash_keys.ports.src = fl6->fl6_sport;
+	}
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
 		hash_keys.ports.dst = fl6->fl6_dport;
 
@@ -2546,7 +2553,10 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 			hash_keys.addrs.v6addrs.src = fl6->saddr;
 			hash_keys.addrs.v6addrs.dst = fl6->daddr;
-			hash_keys.ports.src = fl6->fl6_sport;
+			if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT)
+				hash_keys.ports.src = (__force __be16)get_random_u16();
+			else
+				hash_keys.ports.src = fl6->fl6_sport;
 			hash_keys.ports.dst = fl6->fl6_dport;
 			hash_keys.basic.ip_proto = fl6->flowi6_proto;
 		}
@@ -3728,61 +3738,14 @@ void fib6_nh_release_dsts(struct fib6_nh *fib6_nh)
 }
 
 static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
-					      gfp_t gfp_flags,
-					      struct netlink_ext_ack *extack)
+					       gfp_t gfp_flags,
+					       struct netlink_ext_ack *extack)
 {
 	struct net *net = cfg->fc_nlinfo.nl_net;
-	struct fib6_info *rt = NULL;
-	struct nexthop *nh = NULL;
 	struct fib6_table *table;
-	struct fib6_nh *fib6_nh;
-	int err = -EINVAL;
-	int addr_type;
-
-	/* RTF_PCPU is an internal flag; can not be set by userspace */
-	if (cfg->fc_flags & RTF_PCPU) {
-		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU");
-		goto out;
-	}
-
-	/* RTF_CACHE is an internal flag; can not be set by userspace */
-	if (cfg->fc_flags & RTF_CACHE) {
-		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE");
-		goto out;
-	}
-
-	if (cfg->fc_type > RTN_MAX) {
-		NL_SET_ERR_MSG(extack, "Invalid route type");
-		goto out;
-	}
-
-	if (cfg->fc_dst_len > 128) {
-		NL_SET_ERR_MSG(extack, "Invalid prefix length");
-		goto out;
-	}
-	if (cfg->fc_src_len > 128) {
-		NL_SET_ERR_MSG(extack, "Invalid source address length");
-		goto out;
-	}
-#ifndef CONFIG_IPV6_SUBTREES
-	if (cfg->fc_src_len) {
-		NL_SET_ERR_MSG(extack,
-			       "Specifying source address requires IPV6_SUBTREES to be enabled");
-		goto out;
-	}
-#endif
-	if (cfg->fc_nh_id) {
-		nh = nexthop_find_by_id(net, cfg->fc_nh_id);
-		if (!nh) {
-			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
-			goto out;
-		}
-		err = fib6_check_nexthop(nh, cfg, extack);
-		if (err)
-			goto out;
-	}
+	struct fib6_info *rt;
+	int err;
 
-	err = -ENOBUFS;
 	if (cfg->fc_nlinfo.nlh &&
 	    !(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) {
 		table = fib6_get_table(net, cfg->fc_table);
@@ -3793,22 +3756,22 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	} else {
 		table = fib6_new_table(net, cfg->fc_table);
 	}
+	if (!table) {
+		err = -ENOBUFS;
+		goto err;
+	}
 
-	if (!table)
-		goto out;
-
-	err = -ENOMEM;
-	rt = fib6_info_alloc(gfp_flags, !nh);
-	if (!rt)
-		goto out;
+	rt = fib6_info_alloc(gfp_flags, !cfg->fc_nh_id);
+	if (!rt) {
+		err = -ENOMEM;
+		goto err;
+	}
 
 	rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len,
 					       extack);
 	if (IS_ERR(rt->fib6_metrics)) {
 		err = PTR_ERR(rt->fib6_metrics);
-		/* Do not leave garbage there. */
-		rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
-		goto out_free;
+		goto free;
 	}
 
 	if (cfg->fc_flags & RTF_ADDRCONF)
@@ -3816,12 +3779,12 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 
 	if (cfg->fc_flags & RTF_EXPIRES)
 		fib6_set_expires(rt, jiffies +
-				clock_t_to_jiffies(cfg->fc_expires));
+				 clock_t_to_jiffies(cfg->fc_expires));
 
 	if (cfg->fc_protocol == RTPROT_UNSPEC)
 		cfg->fc_protocol = RTPROT_BOOT;
-	rt->fib6_protocol = cfg->fc_protocol;
 
+	rt->fib6_protocol = cfg->fc_protocol;
 	rt->fib6_table = table;
 	rt->fib6_metric = cfg->fc_metric;
 	rt->fib6_type = cfg->fc_type ? : RTN_UNICAST;
@@ -3834,23 +3797,54 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len);
 	rt->fib6_src.plen = cfg->fc_src_len;
 #endif
-	if (nh) {
-		if (rt->fib6_src.plen) {
-			NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+	return rt;
+free:
+	kfree(rt);
+err:
+	return ERR_PTR(err);
+}
+
+static int ip6_route_info_create_nh(struct fib6_info *rt,
+				    struct fib6_config *cfg,
+				    gfp_t gfp_flags,
+				    struct netlink_ext_ack *extack)
+{
+	struct net *net = cfg->fc_nlinfo.nl_net;
+	struct fib6_nh *fib6_nh;
+	int err;
+
+	if (cfg->fc_nh_id) {
+		struct nexthop *nh;
+
+		rcu_read_lock();
+
+		nh = nexthop_find_by_id(net, cfg->fc_nh_id);
+		if (!nh) {
 			err = -EINVAL;
+			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
 			goto out_free;
 		}
+
+		err = fib6_check_nexthop(nh, cfg, extack);
+		if (err)
+			goto out_free;
+
 		if (!nexthop_get(nh)) {
 			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
 			err = -ENOENT;
 			goto out_free;
 		}
+
 		rt->nh = nh;
 		fib6_nh = nexthop_fib6_nh(rt->nh);
+
+		rcu_read_unlock();
 	} else {
+		int addr_type;
+
 		err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack);
 		if (err)
-			goto out;
+			goto out_release;
 
 		fib6_nh = rt->fib6_nh;
 
@@ -3869,21 +3863,21 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) {
 			NL_SET_ERR_MSG(extack, "Invalid source address");
 			err = -EINVAL;
-			goto out;
+			goto out_release;
 		}
 		rt->fib6_prefsrc.addr = cfg->fc_prefsrc;
 		rt->fib6_prefsrc.plen = 128;
-	} else
-		rt->fib6_prefsrc.plen = 0;
+	}
 
-	return rt;
-out:
+	return 0;
+out_release:
 	fib6_info_release(rt);
-	return ERR_PTR(err);
+	return err;
 out_free:
+	rcu_read_unlock();
 	ip_fib_metrics_put(rt->fib6_metrics);
 	kfree(rt);
-	return ERR_PTR(err);
+	return err;
 }
 
 int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
@@ -3896,6 +3890,10 @@ int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
+	err = ip6_route_info_create_nh(rt, cfg, gfp_flags, extack);
+	if (err)
+		return err;
+
 	err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack);
 	fib6_info_release(rt);
 
@@ -4124,9 +4122,9 @@ static int ip6_route_del(struct fib6_config *cfg,
 			if (rt->nh) {
 				if (!fib6_info_hold_safe(rt))
 					continue;
-				rcu_read_unlock();
 
-				return __ip6_del_rt(rt, &cfg->fc_nlinfo);
+				err =  __ip6_del_rt(rt, &cfg->fc_nlinfo);
+				break;
 			}
 			if (cfg->fc_nh_id)
 				continue;
@@ -4141,13 +4139,13 @@ static int ip6_route_del(struct fib6_config *cfg,
 				continue;
 			if (!fib6_info_hold_safe(rt))
 				continue;
-			rcu_read_unlock();
 
 			/* if gateway was specified only delete the one hop */
 			if (cfg->fc_flags & RTF_GATEWAY)
-				return __ip6_del_rt(rt, &cfg->fc_nlinfo);
-
-			return __ip6_del_rt_siblings(rt, cfg);
+				err = __ip6_del_rt(rt, &cfg->fc_nlinfo);
+			else
+				err = __ip6_del_rt_siblings(rt, cfg);
+			break;
 		}
 	}
 	rcu_read_unlock();
@@ -4481,6 +4479,53 @@ void rt6_purge_dflt_routers(struct net *net)
 	rcu_read_unlock();
 }
 
+static int fib6_config_validate(struct fib6_config *cfg,
+				struct netlink_ext_ack *extack)
+{
+	/* RTF_PCPU is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_PCPU) {
+		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU");
+		goto errout;
+	}
+
+	/* RTF_CACHE is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_CACHE) {
+		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE");
+		goto errout;
+	}
+
+	if (cfg->fc_type > RTN_MAX) {
+		NL_SET_ERR_MSG(extack, "Invalid route type");
+		goto errout;
+	}
+
+	if (cfg->fc_dst_len > 128) {
+		NL_SET_ERR_MSG(extack, "Invalid prefix length");
+		goto errout;
+	}
+
+#ifdef CONFIG_IPV6_SUBTREES
+	if (cfg->fc_src_len > 128) {
+		NL_SET_ERR_MSG(extack, "Invalid source address length");
+		goto errout;
+	}
+
+	if (cfg->fc_nh_id && cfg->fc_src_len) {
+		NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+		goto errout;
+	}
+#else
+	if (cfg->fc_src_len) {
+		NL_SET_ERR_MSG(extack,
+			       "Specifying source address requires IPV6_SUBTREES to be enabled");
+		goto errout;
+	}
+#endif
+	return 0;
+errout:
+	return -EINVAL;
+}
+
 static void rtmsg_to_fib6_config(struct net *net,
 				 struct in6_rtmsg *rtmsg,
 				 struct fib6_config *cfg)
@@ -4516,9 +4561,12 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg)
 
 	rtmsg_to_fib6_config(net, rtmsg, &cfg);
 
-	rtnl_lock();
 	switch (cmd) {
 	case SIOCADDRT:
+		err = fib6_config_validate(&cfg, NULL);
+		if (err)
+			break;
+
 		/* Only do the default setting of fc_metric in route adding */
 		if (cfg.fc_metric == 0)
 			cfg.fc_metric = IP6_RT_PRIO_USER;
@@ -4528,7 +4576,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg)
 		err = ip6_route_del(&cfg, NULL);
 		break;
 	}
-	rtnl_unlock();
+
 	return err;
 }
 
@@ -4618,6 +4666,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 		.fc_ignore_dev_down = true,
 	};
 	struct fib6_info *f6i;
+	int err;
 
 	if (anycast) {
 		cfg.fc_type = RTN_ANYCAST;
@@ -4628,14 +4677,19 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 	}
 
 	f6i = ip6_route_info_create(&cfg, gfp_flags, extack);
-	if (!IS_ERR(f6i)) {
-		f6i->dst_nocount = true;
+	if (IS_ERR(f6i))
+		return f6i;
 
-		if (!anycast &&
-		    (READ_ONCE(net->ipv6.devconf_all->disable_policy) ||
-		     READ_ONCE(idev->cnf.disable_policy)))
-			f6i->dst_nopolicy = true;
-	}
+	err = ip6_route_info_create_nh(f6i, &cfg, gfp_flags, extack);
+	if (err)
+		return ERR_PTR(err);
+
+	f6i->dst_nocount = true;
+
+	if (!anycast &&
+	    (READ_ONCE(net->ipv6.devconf_all->disable_policy) ||
+	     READ_ONCE(idev->cnf.disable_policy)))
+		f6i->dst_nopolicy = true;
 
 	return f6i;
 }
@@ -5050,12 +5104,60 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_FLOWLABEL]		= { .type = NLA_BE32 },
 };
 
+static int rtm_to_fib6_multipath_config(struct fib6_config *cfg,
+					struct netlink_ext_ack *extack,
+					bool newroute)
+{
+	struct rtnexthop *rtnh;
+	int remaining;
+
+	remaining = cfg->fc_mp_len;
+	rtnh = (struct rtnexthop *)cfg->fc_mp;
+
+	if (!rtnh_ok(rtnh, remaining)) {
+		NL_SET_ERR_MSG(extack, "Invalid nexthop configuration - no valid nexthops");
+		return -EINVAL;
+	}
+
+	do {
+		bool has_gateway = cfg->fc_flags & RTF_GATEWAY;
+		int attrlen = rtnh_attrlen(rtnh);
+
+		if (attrlen > 0) {
+			struct nlattr *nla, *attrs;
+
+			attrs = rtnh_attrs(rtnh);
+			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+			if (nla) {
+				if (nla_len(nla) < sizeof(cfg->fc_gateway)) {
+					NL_SET_ERR_MSG(extack,
+						       "Invalid IPv6 address in RTA_GATEWAY");
+					return -EINVAL;
+				}
+
+				has_gateway = true;
+			}
+		}
+
+		if (newroute && (cfg->fc_nh_id || !has_gateway)) {
+			NL_SET_ERR_MSG(extack,
+				       "Device only routes can not be added for IPv6 using the multipath API.");
+			return -EINVAL;
+		}
+
+		rtnh = rtnh_next(rtnh, &remaining);
+	} while (rtnh_ok(rtnh, remaining));
+
+	return lwtunnel_valid_encap_type_attr(cfg->fc_mp, cfg->fc_mp_len, extack);
+}
+
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 			      struct fib6_config *cfg,
 			      struct netlink_ext_ack *extack)
 {
-	struct rtmsg *rtm;
+	bool newroute = nlh->nlmsg_type == RTM_NEWROUTE;
 	struct nlattr *tb[RTA_MAX+1];
+	struct rtmsg *rtm;
 	unsigned int pref;
 	int err;
 
@@ -5164,9 +5266,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
 		cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
 
-		err = lwtunnel_valid_encap_type_attr(cfg->fc_mp,
-						     cfg->fc_mp_len,
-						     extack, true);
+		err = rtm_to_fib6_multipath_config(cfg, extack, newroute);
 		if (err < 0)
 			goto errout;
 	}
@@ -5185,8 +5285,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[RTA_ENCAP_TYPE]) {
 		cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
 
-		err = lwtunnel_valid_encap_type(cfg->fc_encap_type,
-						extack, true);
+		err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack);
 		if (err < 0)
 			goto errout;
 	}
@@ -5208,29 +5307,28 @@ errout:
 struct rt6_nh {
 	struct fib6_info *fib6_info;
 	struct fib6_config r_cfg;
-	struct list_head next;
+	struct list_head list;
 };
 
-static int ip6_route_info_append(struct net *net,
-				 struct list_head *rt6_nh_list,
+static int ip6_route_info_append(struct list_head *rt6_nh_list,
 				 struct fib6_info *rt,
 				 struct fib6_config *r_cfg)
 {
 	struct rt6_nh *nh;
-	int err = -EEXIST;
 
-	list_for_each_entry(nh, rt6_nh_list, next) {
+	list_for_each_entry(nh, rt6_nh_list, list) {
 		/* check if fib6_info already exists */
 		if (rt6_duplicate_nexthop(nh->fib6_info, rt))
-			return err;
+			return -EEXIST;
 	}
 
 	nh = kzalloc(sizeof(*nh), GFP_KERNEL);
 	if (!nh)
 		return -ENOMEM;
+
 	nh->fib6_info = rt;
 	memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg));
-	list_add_tail(&nh->next, rt6_nh_list);
+	list_add_tail(&nh->list, rt6_nh_list);
 
 	return 0;
 }
@@ -5286,37 +5384,26 @@ out:
 	return should_notify;
 }
 
-static int fib6_gw_from_attr(struct in6_addr *gw, struct nlattr *nla,
-			     struct netlink_ext_ack *extack)
-{
-	if (nla_len(nla) < sizeof(*gw)) {
-		NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY");
-		return -EINVAL;
-	}
-
-	*gw = nla_get_in6_addr(nla);
-
-	return 0;
-}
-
 static int ip6_route_multipath_add(struct fib6_config *cfg,
 				   struct netlink_ext_ack *extack)
 {
 	struct fib6_info *rt_notif = NULL, *rt_last = NULL;
 	struct nl_info *info = &cfg->fc_nlinfo;
+	struct rt6_nh *nh, *nh_safe;
 	struct fib6_config r_cfg;
 	struct rtnexthop *rtnh;
-	struct fib6_info *rt;
+	LIST_HEAD(rt6_nh_list);
 	struct rt6_nh *err_nh;
-	struct rt6_nh *nh, *nh_safe;
+	struct fib6_info *rt;
 	__u16 nlflags;
 	int remaining;
 	int attrlen;
-	int err = 1;
+	int replace;
 	int nhn = 0;
-	int replace = (cfg->fc_nlinfo.nlh &&
-		       (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
-	LIST_HEAD(rt6_nh_list);
+	int err;
+
+	replace = (cfg->fc_nlinfo.nlh &&
+		   (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
 
 	nlflags = replace ? NLM_F_REPLACE : NLM_F_CREATE;
 	if (info->nlh && info->nlh->nlmsg_flags & NLM_F_APPEND)
@@ -5339,18 +5426,11 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla) {
-				err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
-							extack);
-				if (err)
-					goto cleanup;
-
+				r_cfg.fc_gateway = nla_get_in6_addr(nla);
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
-			r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
 
-			/* RTA_ENCAP_TYPE length checked in
-			 * lwtunnel_valid_encap_type_attr
-			 */
+			r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
 			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 			if (nla)
 				r_cfg.fc_encap_type = nla_get_u16(nla);
@@ -5363,18 +5443,16 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 			rt = NULL;
 			goto cleanup;
 		}
-		if (!rt6_qualify_for_ecmp(rt)) {
-			err = -EINVAL;
-			NL_SET_ERR_MSG(extack,
-				       "Device only routes can not be added for IPv6 using the multipath API.");
-			fib6_info_release(rt);
+
+		err = ip6_route_info_create_nh(rt, &r_cfg, GFP_KERNEL, extack);
+		if (err) {
+			rt = NULL;
 			goto cleanup;
 		}
 
 		rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1;
 
-		err = ip6_route_info_append(info->nl_net, &rt6_nh_list,
-					    rt, &r_cfg);
+		err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
 		if (err) {
 			fib6_info_release(rt);
 			goto cleanup;
@@ -5383,12 +5461,6 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
-	if (list_empty(&rt6_nh_list)) {
-		NL_SET_ERR_MSG(extack,
-			       "Invalid nexthop configuration - no valid nexthops");
-		return -EINVAL;
-	}
-
 	/* for add and replace send one notification with all nexthops.
 	 * Skip the notification in fib6_add_rt2node and send one with
 	 * the full route when done
@@ -5401,7 +5473,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 	info->skip_notify_kernel = 1;
 
 	err_nh = NULL;
-	list_for_each_entry(nh, &rt6_nh_list, next) {
+	list_for_each_entry(nh, &rt6_nh_list, list) {
 		err = __ip6_ins_rt(nh->fib6_info, info, extack);
 
 		if (err) {
@@ -5469,16 +5541,16 @@ add_errout:
 		ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags);
 
 	/* Delete routes that were already added */
-	list_for_each_entry(nh, &rt6_nh_list, next) {
+	list_for_each_entry(nh, &rt6_nh_list, list) {
 		if (err_nh == nh)
 			break;
 		ip6_route_del(&nh->r_cfg, extack);
 	}
 
 cleanup:
-	list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
+	list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, list) {
 		fib6_info_release(nh->fib6_info);
-		list_del(&nh->next);
+		list_del(&nh->list);
 		kfree(nh);
 	}
 
@@ -5510,21 +5582,15 @@ static int ip6_route_multipath_del(struct fib6_config *cfg,
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla) {
-				err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
-							extack);
-				if (err) {
-					last_err = err;
-					goto next_rtnh;
-				}
-
+				r_cfg.fc_gateway = nla_get_in6_addr(nla);
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
 		}
+
 		err = ip6_route_del(&r_cfg, extack);
 		if (err)
 			last_err = err;
 
-next_rtnh:
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
@@ -5541,15 +5607,20 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		return err;
 
-	if (cfg.fc_nh_id &&
-	    !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id)) {
-		NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
-		return -EINVAL;
+	if (cfg.fc_nh_id) {
+		rcu_read_lock();
+		err = !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id);
+		rcu_read_unlock();
+
+		if (err) {
+			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+			return -EINVAL;
+		}
 	}
 
-	if (cfg.fc_mp)
+	if (cfg.fc_mp) {
 		return ip6_route_multipath_del(&cfg, extack);
-	else {
+	} else {
 		cfg.fc_delete_all_nh = 1;
 		return ip6_route_del(&cfg, extack);
 	}
@@ -5565,6 +5636,10 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		return err;
 
+	err = fib6_config_validate(&cfg, extack);
+	if (err)
+		return err;
+
 	if (cfg.fc_metric == 0)
 		cfg.fc_metric = IP6_RT_PRIO_USER;
 
@@ -6029,7 +6104,8 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
 	struct rtmsg *rtm;
 	int i, err;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
+	rtm = nlmsg_payload(nlh, sizeof(*rtm));
+	if (!rtm) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Invalid header for get route request");
 		return -EINVAL;
@@ -6039,7 +6115,6 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
 		return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
 					      rtm_ipv6_policy, extack);
 
-	rtm = nlmsg_data(nlh);
 	if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) ||
 	    (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) ||
 	    rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope ||
@@ -6254,6 +6329,8 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 	err = -ENOBUFS;
 	seq = info->nlh ? info->nlh->nlmsg_seq : 0;
 
+	rcu_read_lock();
+
 	skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC);
 	if (!skb)
 		goto errout;
@@ -6266,10 +6343,14 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		kfree_skb(skb);
 		goto errout;
 	}
+
+	rcu_read_unlock();
+
 	rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
 		    info->nlh, GFP_ATOMIC);
 	return;
 errout:
+	rcu_read_unlock();
 	rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
 }
 
@@ -6759,9 +6840,9 @@ static void bpf_iter_unregister(void)
 
 static const struct rtnl_msg_handler ip6_route_rtnl_msg_handlers[] __initconst_or_module = {
 	{.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWROUTE,
-	 .doit = inet6_rtm_newroute},
+	 .doit = inet6_rtm_newroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
 	{.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELROUTE,
-	 .doit = inet6_rtm_delroute},
+	 .doit = inet6_rtm_delroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
 	{.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE,
 	 .doit = inet6_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
 };
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index bbf5b84a70fc..f78ecb6ad838 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -40,7 +40,14 @@
 #include <net/seg6_hmac.h>
 #include <linux/random.h>
 
-static DEFINE_PER_CPU(char [SEG6_HMAC_RING_SIZE], hmac_ring);
+struct hmac_storage {
+	local_lock_t bh_lock;
+	char hmac_ring[SEG6_HMAC_RING_SIZE];
+};
+
+static DEFINE_PER_CPU(struct hmac_storage, hmac_storage) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 static int seg6_hmac_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
 {
@@ -187,7 +194,8 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
 	 */
 
 	local_bh_disable();
-	ring = this_cpu_ptr(hmac_ring);
+	local_lock_nested_bh(&hmac_storage.bh_lock);
+	ring = this_cpu_ptr(hmac_storage.hmac_ring);
 	off = ring;
 
 	/* source address */
@@ -212,6 +220,7 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
 
 	dgsize = __do_hmac(hinfo, ring, plen, tmp_out,
 			   SEG6_HMAC_MAX_DIGESTSIZE);
+	local_unlock_nested_bh(&hmac_storage.bh_lock);
 	local_bh_enable();
 
 	if (dgsize < 0)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 9a0f32acb750..a72dbca9e8fc 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1804,8 +1804,7 @@ static struct xfrm_tunnel mplsip_handler __read_mostly = {
 };
 #endif
 
-static void __net_exit sit_destroy_tunnels(struct net *net,
-					   struct list_head *head)
+static void __net_exit sit_exit_rtnl_net(struct net *net, struct list_head *head)
 {
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 	struct net_device *dev, *aux;
@@ -1820,15 +1819,15 @@ static void __net_exit sit_destroy_tunnels(struct net *net,
 		for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) {
 			struct ip_tunnel *t;
 
-			t = rtnl_dereference(sitn->tunnels[prio][h]);
+			t = rtnl_net_dereference(net, sitn->tunnels[prio][h]);
 			while (t) {
 				/* If dev is in the same netns, it has already
 				 * been added to the list by the previous loop.
 				 */
 				if (!net_eq(dev_net(t->dev), net))
-					unregister_netdevice_queue(t->dev,
-								   head);
-				t = rtnl_dereference(t->next);
+					unregister_netdevice_queue(t->dev, head);
+
+				t = rtnl_net_dereference(net, t->next);
 			}
 		}
 	}
@@ -1881,19 +1880,9 @@ err_alloc_dev:
 	return err;
 }
 
-static void __net_exit sit_exit_batch_rtnl(struct list_head *net_list,
-					   struct list_head *dev_to_kill)
-{
-	struct net *net;
-
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_list, exit_list)
-		sit_destroy_tunnels(net, dev_to_kill);
-}
-
 static struct pernet_operations sit_net_ops = {
 	.init = sit_init_net,
-	.exit_batch_rtnl = sit_exit_batch_rtnl,
+	.exit_rtnl = sit_exit_rtnl_net,
 	.id   = &sit_net_id,
 	.size = sizeof(struct sit_net),
 };
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7dcb33f879ee..e8e68a142649 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -267,6 +267,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
+	if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !fl6.fl6_sport)
+		fl6.flowi6_flags = FLOWI_FLAG_ANY_SPORT;
 	fl6.flowi6_uid = sk->sk_uid;
 
 	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index d9b11fe41bf0..a8a04f441e78 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -42,7 +42,7 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
 					iif, sdif);
 	NAPI_GRO_CB(skb)->is_flist = !sk;
 	if (sk)
-		sock_put(sk);
+		sock_gen_put(sk);
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 }
 
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 4abc5e9d6322..841c81abaaf4 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -179,14 +179,18 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 	int offset = skb_gro_offset(skb);
 	const struct net_offload *ops;
 	struct sk_buff *pp = NULL;
-	int ret;
+	int len, dlen;
+	__u8 *udpdata;
+	__be32 *udpdata32;
 
 	if (skb->protocol == htons(ETH_P_IP))
 		return xfrm4_gro_udp_encap_rcv(sk, head, skb);
 
-	offset = offset - sizeof(struct udphdr);
-
-	if (!pskb_pull(skb, offset))
+	len = skb->len - offset;
+	dlen = offset + min(len, 8);
+	udpdata = skb_gro_header(skb, dlen, offset);
+	udpdata32 = (__be32 *)udpdata;
+	if (unlikely(!udpdata))
 		return NULL;
 
 	rcu_read_lock();
@@ -194,11 +198,10 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 	if (!ops || !ops->callbacks.gro_receive)
 		goto out;
 
-	ret = __xfrm6_udp_encap_rcv(sk, skb, false);
-	if (ret)
+	/* check if it is a keepalive or IKE packet */
+	if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
 		goto out;
 
-	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
 
 	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
@@ -208,7 +211,6 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
 
 out:
 	rcu_read_unlock();
-	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->same_flow = 0;
 	NAPI_GRO_CB(skb)->flush = 1;
 
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index ca10916340b0..5432a5f2dfc8 100644
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -277,8 +277,10 @@ void l3mdev_update_flow(struct net *net, struct flowi *fl)
 	if (fl->flowi_oif) {
 		dev = dev_get_by_index_rcu(net, fl->flowi_oif);
 		if (dev) {
-			if (!fl->flowi_l3mdev)
+			if (!fl->flowi_l3mdev) {
 				fl->flowi_l3mdev = l3mdev_master_ifindex_rcu(dev);
+				fl->flowi_flags |= FLOWI_FLAG_L3MDEV_OIF;
+			}
 
 			/* oif set to L3mdev directs lookup to its table;
 			 * reset to avoid oif match in fib_lookup
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 0259cde394ba..cc77ec5769d8 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -887,15 +887,15 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		if (sk->sk_type != SOCK_STREAM)
 			goto copy_uaddr;
 
+		/* Partial read */
+		if (used + offset < skb_len)
+			continue;
+
 		if (!(flags & MSG_PEEK)) {
 			skb_unlink(skb, &sk->sk_receive_queue);
 			kfree_skb(skb);
 			*seq = 0;
 		}
-
-		/* Partial read */
-		if (used + offset < skb_len)
-			continue;
 	} while (len > 0);
 
 out:
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 9f683f838431..d9d88f2f2831 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -146,8 +146,8 @@ static int ieee80211_set_ap_mbssid_options(struct ieee80211_sub_if_data *sdata,
 					   struct ieee80211_bss_conf *link_conf)
 {
 	struct ieee80211_sub_if_data *tx_sdata;
+	struct ieee80211_bss_conf *old;
 
-	sdata->vif.mbssid_tx_vif = NULL;
 	link_conf->bssid_index = 0;
 	link_conf->nontransmitted = false;
 	link_conf->ema_ap = false;
@@ -156,14 +156,26 @@ static int ieee80211_set_ap_mbssid_options(struct ieee80211_sub_if_data *sdata,
 	if (sdata->vif.type != NL80211_IFTYPE_AP || !params->tx_wdev)
 		return -EINVAL;
 
+	old = sdata_dereference(link_conf->tx_bss_conf, sdata);
+	if (old)
+		return -EALREADY;
+
 	tx_sdata = IEEE80211_WDEV_TO_SUB_IF(params->tx_wdev);
 	if (!tx_sdata)
 		return -EINVAL;
 
 	if (tx_sdata == sdata) {
-		sdata->vif.mbssid_tx_vif = &sdata->vif;
+		rcu_assign_pointer(link_conf->tx_bss_conf, link_conf);
 	} else {
-		sdata->vif.mbssid_tx_vif = &tx_sdata->vif;
+		struct ieee80211_bss_conf *tx_bss_conf;
+
+		tx_bss_conf = sdata_dereference(tx_sdata->vif.link_conf[params->tx_link_id],
+						sdata);
+		if (rcu_access_pointer(tx_bss_conf->tx_bss_conf) != tx_bss_conf)
+			return -EINVAL;
+
+		rcu_assign_pointer(link_conf->tx_bss_conf, tx_bss_conf);
+
 		link_conf->nontransmitted = true;
 		link_conf->bssid_index = params->index;
 	}
@@ -1278,9 +1290,9 @@ static u8 ieee80211_num_beaconing_links(struct ieee80211_sub_if_data *sdata)
 	    sdata->vif.type != NL80211_IFTYPE_P2P_GO)
 		return num;
 
-	if (!sdata->vif.valid_links)
-		return num;
-
+	/* non-MLO mode of operation also uses link_id 0 in sdata so it is
+	 * safe to directly proceed with the below loop
+	 */
 	for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) {
 		link = sdata_dereference(sdata->link[link_id], sdata);
 		if (!link)
@@ -1409,6 +1421,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 				(IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ |
 				 IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ |
 				 IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ);
+		link_conf->eht_disable_mcs15 =
+			u8_get_bits(params->eht_oper->params,
+				    IEEE80211_EHT_OPER_MCS15_DISABLE);
 	} else {
 		link_conf->eht_su_beamformer = false;
 		link_conf->eht_su_beamformee = false;
@@ -1669,7 +1684,6 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev,
 	kfree(link_conf->ftmr_params);
 	link_conf->ftmr_params = NULL;
 
-	sdata->vif.mbssid_tx_vif = NULL;
 	link_conf->bssid_index = 0;
 	link_conf->nontransmitted = false;
 	link_conf->ema_ap = false;
@@ -1683,6 +1697,9 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev,
 		ieee80211_free_key_list(local, &keys);
 	}
 
+	ieee80211_stop_mbssid(sdata);
+	RCU_INIT_POINTER(link_conf->tx_bss_conf, NULL);
+
 	link_conf->enable_beacon = false;
 	sdata->beacon_rate_set = false;
 	sdata->vif.cfg.ssid_len = 0;
@@ -2066,6 +2083,9 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 	if (params->listen_interval >= 0)
 		sta->listen_interval = params->listen_interval;
 
+	if (params->eml_cap_present)
+		sta->sta.eml_cap = params->eml_cap;
+
 	ret = sta_link_apply_parameters(local, sta, STA_LINK_MODE_STA_MODIFY,
 					&params->link_sta_params);
 	if (ret)
@@ -2904,7 +2924,7 @@ static int ieee80211_scan(struct wiphy *wiphy,
 		 * the frames sent while scanning on other channel will be
 		 * lost)
 		 */
-		if (sdata->deflink.u.ap.beacon &&
+		if (ieee80211_num_beaconing_links(sdata) &&
 		    (!(wiphy->features & NL80211_FEATURE_AP_SCAN) ||
 		     !(req->flags & NL80211_SCAN_FLAG_AP)))
 			return -EOPNOTSUPP;
@@ -3700,6 +3720,7 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_bss_conf *tx_bss_conf;
 	struct ieee80211_link_data *link_data;
 
 	if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS))
@@ -3713,25 +3734,24 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id)
 		return;
 	}
 
-	/* TODO: MBSSID with MLO changes */
-	if (vif->mbssid_tx_vif == vif) {
+	tx_bss_conf = rcu_dereference(link_data->conf->tx_bss_conf);
+	if (tx_bss_conf == link_data->conf) {
 		/* Trigger ieee80211_csa_finish() on the non-transmitting
 		 * interfaces when channel switch is received on
 		 * transmitting interface
 		 */
-		struct ieee80211_sub_if_data *iter;
-
-		list_for_each_entry_rcu(iter, &local->interfaces, list) {
-			if (!ieee80211_sdata_running(iter))
-				continue;
+		struct ieee80211_link_data *iter;
 
-			if (iter == sdata || iter->vif.mbssid_tx_vif != vif)
+		for_each_sdata_link(local, iter) {
+			if (iter->sdata == sdata ||
+			    rcu_access_pointer(iter->conf->tx_bss_conf) != tx_bss_conf)
 				continue;
 
-			wiphy_work_queue(iter->local->hw.wiphy,
-					 &iter->deflink.csa.finalize_work);
+			wiphy_work_queue(iter->sdata->local->hw.wiphy,
+					 &iter->csa.finalize_work);
 		}
 	}
+
 	wiphy_work_queue(local->hw.wiphy, &link_data->csa.finalize_work);
 
 	rcu_read_unlock();
@@ -4833,17 +4853,19 @@ ieee80211_color_change_bss_config_notify(struct ieee80211_link_data *link,
 
 	ieee80211_link_info_change_notify(sdata, link, changed);
 
-	if (!sdata->vif.bss_conf.nontransmitted && sdata->vif.mbssid_tx_vif) {
-		struct ieee80211_sub_if_data *child;
+	if (!link->conf->nontransmitted &&
+	    rcu_access_pointer(link->conf->tx_bss_conf)) {
+		struct ieee80211_link_data *tmp;
 
-		list_for_each_entry(child, &sdata->local->interfaces, list) {
-			if (child != sdata && child->vif.mbssid_tx_vif == &sdata->vif) {
-				child->vif.bss_conf.he_bss_color.color = color;
-				child->vif.bss_conf.he_bss_color.enabled = enable;
-				ieee80211_link_info_change_notify(child,
-								  &child->deflink,
-								  BSS_CHANGED_HE_BSS_COLOR);
-			}
+		for_each_sdata_link(sdata->local, tmp) {
+			if (tmp->sdata == sdata ||
+			    rcu_access_pointer(tmp->conf->tx_bss_conf) != link->conf)
+				continue;
+
+			tmp->conf->he_bss_color.color = color;
+			tmp->conf->he_bss_color.enabled = enable;
+			ieee80211_link_info_change_notify(tmp->sdata, tmp,
+							  BSS_CHANGED_HE_BSS_COLOR);
 		}
 	}
 }
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index c3bfac58151f..3aaf5abf1acc 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -2131,6 +2131,9 @@ void ieee80211_link_release_channel(struct ieee80211_link_data *link)
 {
 	struct ieee80211_sub_if_data *sdata = link->sdata;
 
+	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+		return;
+
 	lockdep_assert_wiphy(sdata->local->hw.wiphy);
 
 	if (rcu_access_pointer(link->conf->chanctx_conf))
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index a8948f4d983e..49061bd4151b 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -152,12 +152,6 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf,
 
 	p += scnprintf(p,
 		       bufsz + buf - p,
-		       "target %uus interval %uus ecn %s\n",
-		       codel_time_to_us(sta->cparams.target),
-		       codel_time_to_us(sta->cparams.interval),
-		       sta->cparams.ecn ? "yes" : "no");
-	p += scnprintf(p,
-		       bufsz + buf - p,
 		       "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets flags\n");
 
 	for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 4246d168374f..a6e7b7ba6a01 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -48,7 +48,7 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_mgmt *mgmt;
 	u8 *pos;
 	struct ieee80211_supported_band *sband;
-	u32 rate_flags, rates = 0, rates_added = 0;
+	u32 rates = 0, rates_added = 0;
 	struct beacon_data *presp;
 	int frame_len;
 
@@ -90,14 +90,11 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata,
 	pos += ifibss->ssid_len;
 
 	sband = local->hw.wiphy->bands[chandef->chan->band];
-	rate_flags = ieee80211_chandef_rate_flags(chandef);
 	rates_n = 0;
 	if (have_higher_than_11mbit)
 		*have_higher_than_11mbit = false;
 
 	for (i = 0; i < sband->n_bitrates; i++) {
-		if ((rate_flags & sband->bitrates[i].flags) != rate_flags)
-			continue;
 		if (sband->bitrates[i].bitrate > 110 &&
 		    have_higher_than_11mbit)
 			*have_higher_than_11mbit = true;
@@ -395,7 +392,6 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	const struct cfg80211_bss_ies *ies;
 	enum nl80211_channel_type chan_type;
 	u64 tsf;
-	u32 rate_flags;
 
 	lockdep_assert_wiphy(sdata->local->hw.wiphy);
 
@@ -429,7 +425,6 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	}
 
 	sband = sdata->local->hw.wiphy->bands[cbss->channel->band];
-	rate_flags = ieee80211_chandef_rate_flags(&sdata->u.ibss.chandef);
 
 	basic_rates = 0;
 
@@ -439,9 +434,6 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 
 		for (j = 0; j < sband->n_bitrates; j++) {
 			int brate;
-			if ((rate_flags & sband->bitrates[j].flags)
-			    != rate_flags)
-				continue;
 
 			brate = DIV_ROUND_UP(sband->bitrates[j].bitrate, 5);
 			if (brate == rate) {
@@ -1717,12 +1709,9 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 			struct cfg80211_ibss_params *params)
 {
 	u64 changed = 0;
-	u32 rate_flags;
-	struct ieee80211_supported_band *sband;
 	enum ieee80211_chanctx_mode chanmode;
 	struct ieee80211_local *local = sdata->local;
 	int radar_detect_width = 0;
-	int i;
 	int ret;
 
 	lockdep_assert_wiphy(local->hw.wiphy);
@@ -1765,12 +1754,6 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 	sdata->u.ibss.last_scan_completed = jiffies;
 
 	/* fix basic_rates if channel does not support these rates */
-	rate_flags = ieee80211_chandef_rate_flags(&params->chandef);
-	sband = local->hw.wiphy->bands[params->chandef.chan->band];
-	for (i = 0; i < sband->n_bitrates; i++) {
-		if ((rate_flags & sband->bitrates[i].flags) != rate_flags)
-			sdata->u.ibss.basic_rates &= ~BIT(i);
-	}
 	memcpy(sdata->vif.bss_conf.mcast_rate, params->mcast_rate,
 	       sizeof(params->mcast_rate));
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index fb05f3cd37ec..30809f0b35f7 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1226,6 +1226,15 @@ struct ieee80211_sub_if_data *vif_to_sdata(struct ieee80211_vif *p)
 	if ((_link = wiphy_dereference((_local)->hw.wiphy,		\
 				       ___sdata->link[___link_id])))
 
+#define for_each_link_data(sdata, __link)					\
+	struct ieee80211_sub_if_data *__sdata = sdata;				\
+	for (int __link_id = 0;							\
+	     __link_id < ARRAY_SIZE((__sdata)->link); __link_id++)		\
+		if ((!(__sdata)->vif.valid_links ||				\
+		     (__sdata)->vif.valid_links & BIT(__link_id)) &&		\
+		    ((__link) = sdata_dereference((__sdata)->link[__link_id],	\
+						  (__sdata))))
+
 static inline int
 ieee80211_get_mbssid_beacon_len(struct cfg80211_mbssid_elems *elems,
 				struct cfg80211_rnr_elems *rnr_elems,
@@ -2078,6 +2087,9 @@ static inline void ieee80211_vif_clear_links(struct ieee80211_sub_if_data *sdata
 	ieee80211_vif_set_links(sdata, 0, 0);
 }
 
+void ieee80211_apvlan_link_setup(struct ieee80211_sub_if_data *sdata);
+void ieee80211_apvlan_link_clear(struct ieee80211_sub_if_data *sdata);
+
 /* tx handling */
 void ieee80211_clear_tx_pending(struct ieee80211_local *local);
 void ieee80211_tx_pending(struct tasklet_struct *t);
@@ -2613,7 +2625,7 @@ void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata,
 /* element building in SKBs */
 int ieee80211_put_srates_elem(struct sk_buff *skb,
 			      const struct ieee80211_supported_band *sband,
-			      u32 basic_rates, u32 rate_flags, u32 masked_rates,
+			      u32 basic_rates, u32 masked_rates,
 			      u8 element_id);
 int ieee80211_put_he_cap(struct sk_buff *skb,
 			 struct ieee80211_sub_if_data *sdata,
@@ -2795,6 +2807,8 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 
 void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata,
 				      struct ieee80211_mgmt *mgmt, size_t len);
+void ieee80211_stop_mbssid(struct ieee80211_sub_if_data *sdata);
+
 #if IS_ENABLED(CONFIG_MAC80211_KUNIT_TEST)
 #define EXPORT_SYMBOL_IF_MAC80211_KUNIT(sym) EXPORT_SYMBOL_IF_KUNIT(sym)
 #define VISIBLE_IF_MAC80211_KUNIT
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index f0f4a250b10e..7c27f3cd841c 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -485,6 +485,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 	case NL80211_IFTYPE_MONITOR:
 		list_del_rcu(&sdata->u.mntr.list);
 		break;
+	case NL80211_IFTYPE_AP_VLAN:
+		ieee80211_apvlan_link_clear(sdata);
+		break;
 	default:
 		break;
 	}
@@ -659,6 +662,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
 		ieee80211_txq_remove_vlan(local, sdata);
 
+	if (sdata->vif.txq)
+		ieee80211_txq_purge(sdata->local, to_txq_info(sdata->vif.txq));
+
 	sdata->bss = NULL;
 
 	if (local->open_count == 0)
@@ -726,30 +732,59 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 		ieee80211_add_virtual_monitor(local);
 }
 
-static void ieee80211_stop_mbssid(struct ieee80211_sub_if_data *sdata)
+void ieee80211_stop_mbssid(struct ieee80211_sub_if_data *sdata)
 {
-	struct ieee80211_sub_if_data *tx_sdata, *non_tx_sdata, *tmp_sdata;
-	struct ieee80211_vif *tx_vif = sdata->vif.mbssid_tx_vif;
+	struct ieee80211_sub_if_data *tx_sdata;
+	struct ieee80211_bss_conf *link_conf, *tx_bss_conf;
+	struct ieee80211_link_data *tx_link, *link;
+	unsigned int link_id;
 
-	if (!tx_vif)
-		return;
+	lockdep_assert_wiphy(sdata->local->hw.wiphy);
+
+	/* Check if any of the links of current sdata is an MBSSID. */
+	for_each_vif_active_link(&sdata->vif, link_conf, link_id) {
+		tx_bss_conf = sdata_dereference(link_conf->tx_bss_conf, sdata);
+		if (!tx_bss_conf)
+			continue;
+
+		tx_sdata = vif_to_sdata(tx_bss_conf->vif);
+		RCU_INIT_POINTER(link_conf->tx_bss_conf, NULL);
 
-	tx_sdata = vif_to_sdata(tx_vif);
-	sdata->vif.mbssid_tx_vif = NULL;
+		/* If we are not tx sdata reset tx sdata's tx_bss_conf to avoid recusrion
+		 * while closing tx sdata at the end of outer loop below.
+		 */
+		if (sdata != tx_sdata) {
+			tx_link = sdata_dereference(tx_sdata->link[tx_bss_conf->link_id],
+						    tx_sdata);
+			if (!tx_link)
+				continue;
 
-	list_for_each_entry_safe(non_tx_sdata, tmp_sdata,
-				 &tx_sdata->local->interfaces, list) {
-		if (non_tx_sdata != sdata && non_tx_sdata != tx_sdata &&
-		    non_tx_sdata->vif.mbssid_tx_vif == tx_vif &&
-		    ieee80211_sdata_running(non_tx_sdata)) {
-			non_tx_sdata->vif.mbssid_tx_vif = NULL;
-			dev_close(non_tx_sdata->wdev.netdev);
+			RCU_INIT_POINTER(tx_link->conf->tx_bss_conf, NULL);
 		}
-	}
 
-	if (sdata != tx_sdata && ieee80211_sdata_running(tx_sdata)) {
-		tx_sdata->vif.mbssid_tx_vif = NULL;
-		dev_close(tx_sdata->wdev.netdev);
+		/* loop through sdatas to find if any of their links
+		 * belong to same MBSSID set as the one getting deleted.
+		 */
+		for_each_sdata_link(tx_sdata->local, link) {
+			struct ieee80211_sub_if_data *link_sdata = link->sdata;
+
+			if (link_sdata == sdata || link_sdata == tx_sdata ||
+			    rcu_access_pointer(link->conf->tx_bss_conf) != tx_bss_conf)
+				continue;
+
+			RCU_INIT_POINTER(link->conf->tx_bss_conf, NULL);
+
+			/* Remove all links of matching MLD until dynamic link
+			 * removal can be supported.
+			 */
+			cfg80211_stop_iface(link_sdata->wdev.wiphy, &link_sdata->wdev,
+					    GFP_KERNEL);
+		}
+
+		/* If we are not tx sdata, remove links of tx sdata and proceed */
+		if (sdata != tx_sdata && ieee80211_sdata_running(tx_sdata))
+			cfg80211_stop_iface(tx_sdata->wdev.wiphy,
+					    &tx_sdata->wdev, GFP_KERNEL);
 	}
 }
 
@@ -757,21 +792,25 @@ static int ieee80211_stop(struct net_device *dev)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 
-	/* close dependent VLAN and MBSSID interfaces before locking wiphy */
+	/* close dependent VLAN interfaces before locking wiphy */
 	if (sdata->vif.type == NL80211_IFTYPE_AP) {
 		struct ieee80211_sub_if_data *vlan, *tmpsdata;
 
 		list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans,
 					 u.vlan.list)
 			dev_close(vlan->dev);
-
-		ieee80211_stop_mbssid(sdata);
 	}
 
 	guard(wiphy)(sdata->local->hw.wiphy);
 
 	wiphy_work_cancel(sdata->local->hw.wiphy, &sdata->activate_links_work);
 
+	/* Close the dependent MBSSID interfaces with wiphy lock as we may be
+	 * terminating its partner links too in case of MLD.
+	 */
+	if (sdata->vif.type == NL80211_IFTYPE_AP)
+		ieee80211_stop_mbssid(sdata);
+
 	ieee80211_do_stop(sdata, true);
 
 	return 0;
@@ -1265,6 +1304,8 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		sdata->crypto_tx_tailroom_needed_cnt +=
 			master->crypto_tx_tailroom_needed_cnt;
 
+		ieee80211_apvlan_link_setup(sdata);
+
 		break;
 		}
 	case NL80211_IFTYPE_AP:
@@ -1321,7 +1362,12 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 	case NL80211_IFTYPE_AP_VLAN:
 		/* no need to tell driver, but set carrier and chanctx */
 		if (sdata->bss->active) {
-			ieee80211_link_vlan_copy_chanctx(&sdata->deflink);
+			struct ieee80211_link_data *link;
+
+			for_each_link_data(sdata, link) {
+				ieee80211_link_vlan_copy_chanctx(link);
+			}
+
 			netif_carrier_on(dev);
 			ieee80211_set_vif_encap_ops(sdata);
 		} else {
diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index 58a76bcd6ae6..d40c2bd3b50b 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -12,6 +12,71 @@
 #include "key.h"
 #include "debugfs_netdev.h"
 
+static void ieee80211_update_apvlan_links(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_sub_if_data *vlan;
+	struct ieee80211_link_data *link;
+	u16 ap_bss_links = sdata->vif.valid_links;
+	u16 new_links, vlan_links;
+	unsigned long add;
+
+	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) {
+		int link_id;
+
+		if (!vlan)
+			continue;
+
+		/* No support for 4addr with MLO yet */
+		if (vlan->wdev.use_4addr)
+			return;
+
+		vlan_links = vlan->vif.valid_links;
+
+		new_links = ap_bss_links;
+
+		add = new_links & ~vlan_links;
+		if (!add)
+			continue;
+
+		ieee80211_vif_set_links(vlan, add, 0);
+
+		for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) {
+			link = sdata_dereference(vlan->link[link_id], vlan);
+			ieee80211_link_vlan_copy_chanctx(link);
+		}
+	}
+}
+
+void ieee80211_apvlan_link_setup(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_sub_if_data *ap_bss = container_of(sdata->bss,
+					    struct ieee80211_sub_if_data, u.ap);
+	u16 new_links = ap_bss->vif.valid_links;
+	unsigned long add;
+	int link_id;
+
+	if (!ap_bss->vif.valid_links)
+		return;
+
+	add = new_links;
+	for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) {
+		sdata->wdev.valid_links |= BIT(link_id);
+		ether_addr_copy(sdata->wdev.links[link_id].addr,
+				ap_bss->wdev.links[link_id].addr);
+	}
+
+	ieee80211_vif_set_links(sdata, new_links, 0);
+}
+
+void ieee80211_apvlan_link_clear(struct ieee80211_sub_if_data *sdata)
+{
+	if (!sdata->wdev.valid_links)
+		return;
+
+	sdata->wdev.valid_links = 0;
+	ieee80211_vif_clear_links(sdata);
+}
+
 void ieee80211_link_setup(struct ieee80211_link_data *link)
 {
 	if (link->sdata->vif.type == NL80211_IFTYPE_STATION)
@@ -31,6 +96,17 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata,
 	rcu_assign_pointer(sdata->vif.link_conf[link_id], link_conf);
 	rcu_assign_pointer(sdata->link[link_id], link);
 
+	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+		struct ieee80211_sub_if_data *ap_bss;
+		struct ieee80211_bss_conf *ap_bss_conf;
+
+		ap_bss = container_of(sdata->bss,
+				      struct ieee80211_sub_if_data, u.ap);
+		ap_bss_conf = sdata_dereference(ap_bss->vif.link_conf[link_id],
+						ap_bss);
+		memcpy(link_conf, ap_bss_conf, sizeof(*link_conf));
+	}
+
 	link->sdata = sdata;
 	link->link_id = link_id;
 	link->conf = link_conf;
@@ -54,6 +130,7 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata,
 	if (!deflink) {
 		switch (sdata->vif.type) {
 		case NL80211_IFTYPE_AP:
+		case NL80211_IFTYPE_AP_VLAN:
 			ether_addr_copy(link_conf->addr,
 					sdata->wdev.links[link_id].addr);
 			link_conf->bssid = link_conf->addr;
@@ -177,6 +254,7 @@ static void ieee80211_set_vif_links_bitmaps(struct ieee80211_sub_if_data *sdata,
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_AP_VLAN:
 		/* in an AP all links are always active */
 		sdata->vif.active_links = valid_links;
 
@@ -278,12 +356,16 @@ static int ieee80211_vif_update_links(struct ieee80211_sub_if_data *sdata,
 		ieee80211_set_vif_links_bitmaps(sdata, new_links, dormant_links);
 
 		/* tell the driver */
-		ret = drv_change_vif_links(sdata->local, sdata,
-					   old_links & old_active,
-					   new_links & sdata->vif.active_links,
-					   old);
+		if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN)
+			ret = drv_change_vif_links(sdata->local, sdata,
+						   old_links & old_active,
+						   new_links & sdata->vif.active_links,
+						   old);
 		if (!new_links)
 			ieee80211_debugfs_recreate_netdev(sdata, false);
+
+		if (sdata->vif.type == NL80211_IFTYPE_AP)
+			ieee80211_update_apvlan_links(sdata);
 	}
 
 	if (ret) {
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 741e6c7edcb7..6b6de43d9420 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1354,10 +1354,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	hw->wiphy->software_iftypes |= BIT(NL80211_IFTYPE_MONITOR);
 
 
-	local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) +
-				      sizeof(void *) * channels, GFP_KERNEL);
+	local->int_scan_req = kzalloc(struct_size(local->int_scan_req,
+						  channels, channels),
+				      GFP_KERNEL);
 	if (!local->int_scan_req)
 		return -ENOMEM;
+	local->int_scan_req->n_channels = channels;
 
 	eth_broadcast_addr(local->int_scan_req->bssid);
 
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 7257f5610af5..5cc56d578048 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -8,6 +8,7 @@
 
 #include <linux/slab.h>
 #include <linux/unaligned.h>
+#include <net/sock.h>
 #include "ieee80211_i.h"
 #include "mesh.h"
 #include "wme.h"
@@ -776,7 +777,7 @@ bool ieee80211_mesh_xmit_fast(struct ieee80211_sub_if_data *sdata,
 	if (ethertype < ETH_P_802_3_MIN)
 		return false;
 
-	if (skb->sk && skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)
+	if (sk_requests_wifi_status(skb->sk))
 		return false;
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -956,13 +957,10 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
 	u8 *pos;
 	struct ieee80211_sub_if_data *sdata;
 	int hdr_len = offsetofend(struct ieee80211_mgmt, u.beacon);
-	u32 rate_flags;
 
 	sdata = container_of(ifmsh, struct ieee80211_sub_if_data, u.mesh);
 
 	sband = ieee80211_get_sband(sdata);
-	rate_flags =
-		ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chanreq.oper);
 
 	ie_len_he_cap = ieee80211_ie_len_he_cap(sdata);
 	ie_len_eht_cap = ieee80211_ie_len_eht_cap(sdata);
@@ -1091,7 +1089,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
 
 	if (ieee80211_put_srates_elem(skb, sband,
 				      sdata->vif.bss_conf.basic_rates,
-				      rate_flags, 0, WLAN_EID_SUPP_RATES) ||
+				      0, WLAN_EID_SUPP_RATES) ||
 	    mesh_add_ds_params_ie(sdata, skb))
 		goto out_free;
 
@@ -1104,7 +1102,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
 
 	if (ieee80211_put_srates_elem(skb, sband,
 				      sdata->vif.bss_conf.basic_rates,
-				      rate_flags, 0, WLAN_EID_EXT_SUPP_RATES) ||
+				      0, WLAN_EID_EXT_SUPP_RATES) ||
 	    mesh_add_rsn_ie(sdata, skb) ||
 	    mesh_add_ht_cap_ie(sdata, skb) ||
 	    mesh_add_ht_oper_ie(sdata, skb) ||
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index c94a9c7ca960..91444301a84a 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -636,7 +636,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
 				mesh_path_add_gate(mpath);
 		}
 		rcu_read_unlock();
-	} else {
+	} else if (ifmsh->mshcfg.dot11MeshForwarding) {
 		rcu_read_lock();
 		mpath = mesh_path_lookup(sdata, target_addr);
 		if (mpath) {
@@ -654,6 +654,8 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
 			}
 		}
 		rcu_read_unlock();
+	} else {
+		forward = false;
 	}
 
 	if (reply) {
@@ -671,7 +673,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
-	if (forward && ifmsh->mshcfg.dot11MeshForwarding) {
+	if (forward) {
 		u32 preq_id;
 		u8 hopcount;
 
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index 9f9cb5af0a97..0319674be832 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -22,7 +22,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, struct mesh_path *mpath);
 static u32 mesh_table_hash(const void *addr, u32 len, u32 seed)
 {
 	/* Use last four bytes of hw addr as hash index */
-	return jhash_1word(__get_unaligned_cpu32((u8 *)addr + 2), seed);
+	return jhash_1word(get_unaligned((u32 *)((u8 *)addr + 2)), seed);
 }
 
 static const struct rhashtable_params mesh_rht_params = {
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 96e0a861886a..9c6a2b342170 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -264,7 +264,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata,
 
 	if (action != WLAN_SP_MESH_PEERING_CLOSE) {
 		struct ieee80211_supported_band *sband;
-		u32 rate_flags, basic_rates;
+		u32 basic_rates;
 
 		sband = ieee80211_get_sband(sdata);
 		if (!sband) {
@@ -280,16 +280,12 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata,
 			put_unaligned_le16(sta->sta.aid, pos);
 		}
 
-		rate_flags =
-			ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chanreq.oper);
 		basic_rates = sdata->vif.bss_conf.basic_rates;
 
 		if (ieee80211_put_srates_elem(skb, sband, basic_rates,
-					      rate_flags, 0,
-					      WLAN_EID_SUPP_RATES) ||
+					      0, WLAN_EID_SUPP_RATES) ||
 		    ieee80211_put_srates_elem(skb, sband, basic_rates,
-					      rate_flags, 0,
-					      WLAN_EID_EXT_SUPP_RATES) ||
+					      0, WLAN_EID_EXT_SUPP_RATES) ||
 		    mesh_add_rsn_ie(sdata, skb) ||
 		    mesh_add_meshid_ie(sdata, skb) ||
 		    mesh_add_meshconf_ie(sdata, skb))
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 5d1f2d6d09ad..b84150dbfe8c 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1525,9 +1525,9 @@ static void ieee80211_assoc_add_rates(struct ieee80211_local *local,
 		rates = ~0;
 	}
 
-	ieee80211_put_srates_elem(skb, sband, 0, 0, ~rates,
+	ieee80211_put_srates_elem(skb, sband, 0, ~rates,
 				  WLAN_EID_SUPP_RATES);
-	ieee80211_put_srates_elem(skb, sband, 0, 0, ~rates,
+	ieee80211_put_srates_elem(skb, sband, 0, ~rates,
 				  WLAN_EID_EXT_SUPP_RATES);
 }
 
@@ -7675,6 +7675,7 @@ ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata,
 	int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.ttlm_res);
 	int ttlm_max_len = 2 + 1 + sizeof(struct ieee80211_ttlm_elem) + 1 +
 		2 * 2 * IEEE80211_TTLM_NUM_TIDS;
+	u16 status_code;
 
 	skb = dev_alloc_skb(local->tx_headroom + hdr_len + ttlm_max_len);
 	if (!skb)
@@ -7697,19 +7698,18 @@ ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata,
 		WARN_ON(1);
 		fallthrough;
 	case NEG_TTLM_RES_REJECT:
-		mgmt->u.action.u.ttlm_res.status_code =
-			WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING;
+		status_code = WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING;
 		break;
 	case NEG_TTLM_RES_ACCEPT:
-		mgmt->u.action.u.ttlm_res.status_code = WLAN_STATUS_SUCCESS;
+		status_code = WLAN_STATUS_SUCCESS;
 		break;
 	case NEG_TTLM_RES_SUGGEST_PREFERRED:
-		mgmt->u.action.u.ttlm_res.status_code =
-			WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED;
+		status_code = WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED;
 		ieee80211_neg_ttlm_add_suggested_map(skb, neg_ttlm);
 		break;
 	}
 
+	mgmt->u.action.u.ttlm_res.status_code = cpu_to_le16(status_code);
 	ieee80211_tx_skb(sdata, skb);
 }
 
@@ -7875,7 +7875,7 @@ void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata,
 	 * This can be better implemented in the future, to handle request
 	 * rejections.
 	 */
-	if (mgmt->u.action.u.ttlm_res.status_code != WLAN_STATUS_SUCCESS)
+	if (le16_to_cpu(mgmt->u.action.u.ttlm_res.status_code) != WLAN_STATUS_SUCCESS)
 		__ieee80211_disconnect(sdata);
 }
 
diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c
index 6da39c864f45..96584b39215e 100644
--- a/net/mac80211/parse.c
+++ b/net/mac80211/parse.c
@@ -1101,7 +1101,6 @@ int ieee80211_parse_bitrates(enum nl80211_chan_width width,
 			     const struct ieee80211_supported_band *sband,
 			     const u8 *srates, int srates_len, u32 *rates)
 {
-	u32 rate_flags = ieee80211_chanwidth_rate_flags(width);
 	struct ieee80211_rate *br;
 	int brate, rate, i, j, count = 0;
 
@@ -1112,8 +1111,6 @@ int ieee80211_parse_bitrates(enum nl80211_chan_width width,
 
 		for (j = 0; j < sband->n_bitrates; j++) {
 			br = &sband->bitrates[j];
-			if ((rate_flags & br->flags) != rate_flags)
-				continue;
 
 			brate = DIV_ROUND_UP(br->bitrate, 5);
 			if (brate == rate) {
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 0d056db9f81e..3cb2ad6d0b28 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -368,9 +368,8 @@ static void __rate_control_send_low(struct ieee80211_hw *hw,
 				    struct ieee80211_tx_info *info,
 				    u32 rate_mask)
 {
+	u32 rate_flags = 0;
 	int i;
-	u32 rate_flags =
-		ieee80211_chandef_rate_flags(&hw->conf.chandef);
 
 	if (sband->band == NL80211_BAND_S1GHZ) {
 		info->control.rates[0].flags |= IEEE80211_TX_RC_S1G_MCS;
@@ -778,14 +777,9 @@ static bool rate_control_cap_mask(struct ieee80211_sub_if_data *sdata,
 				  u8 mcs_mask[IEEE80211_HT_MCS_MASK_LEN],
 				  u16 vht_mask[NL80211_VHT_NSS_MAX])
 {
-	u32 i, flags;
+	u32 i;
 
 	*mask = sdata->rc_rateidx_mask[sband->band];
-	flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chanreq.oper);
-	for (i = 0; i < sband->n_bitrates; i++) {
-		if ((flags & sband->bitrates[i].flags) != flags)
-			*mask &= ~BIT(i);
-	}
 
 	if (*mask == (1 << sband->n_bitrates) - 1 &&
 	    !sdata->rc_has_mcs_mask[sband->band] &&
@@ -990,8 +984,6 @@ int rate_control_set_rates(struct ieee80211_hw *hw,
 	if (sta->uploaded)
 		drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta);
 
-	ieee80211_sta_set_expected_throughput(pubsta, sta_get_expected_throughput(sta));
-
 	return 0;
 }
 EXPORT_SYMBOL(rate_control_set_rates);
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 706cbc99f718..f66910013218 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -1873,16 +1873,13 @@ minstrel_ht_free_sta(void *priv, struct ieee80211_sta *sta, void *priv_sta)
 
 static void
 minstrel_ht_fill_rate_array(u8 *dest, struct ieee80211_supported_band *sband,
-			    const s16 *bitrates, int n_rates, u32 rate_flags)
+			    const s16 *bitrates, int n_rates)
 {
 	int i, j;
 
 	for (i = 0; i < sband->n_bitrates; i++) {
 		struct ieee80211_rate *rate = &sband->bitrates[i];
 
-		if ((rate_flags & sband->bitrates[i].flags) != rate_flags)
-			continue;
-
 		for (j = 0; j < n_rates; j++) {
 			if (rate->bitrate != bitrates[j])
 				continue;
@@ -1898,7 +1895,6 @@ minstrel_ht_init_cck_rates(struct minstrel_priv *mp)
 {
 	static const s16 bitrates[4] = { 10, 20, 55, 110 };
 	struct ieee80211_supported_band *sband;
-	u32 rate_flags = ieee80211_chandef_rate_flags(&mp->hw->conf.chandef);
 
 	memset(mp->cck_rates, 0xff, sizeof(mp->cck_rates));
 	sband = mp->hw->wiphy->bands[NL80211_BAND_2GHZ];
@@ -1908,8 +1904,7 @@ minstrel_ht_init_cck_rates(struct minstrel_priv *mp)
 	BUILD_BUG_ON(ARRAY_SIZE(mp->cck_rates) != ARRAY_SIZE(bitrates));
 	minstrel_ht_fill_rate_array(mp->cck_rates, sband,
 				    minstrel_cck_bitrates,
-				    ARRAY_SIZE(minstrel_cck_bitrates),
-				    rate_flags);
+				    ARRAY_SIZE(minstrel_cck_bitrates));
 }
 
 static void
@@ -1917,7 +1912,6 @@ minstrel_ht_init_ofdm_rates(struct minstrel_priv *mp, enum nl80211_band band)
 {
 	static const s16 bitrates[8] = { 60, 90, 120, 180, 240, 360, 480, 540 };
 	struct ieee80211_supported_band *sband;
-	u32 rate_flags = ieee80211_chandef_rate_flags(&mp->hw->conf.chandef);
 
 	memset(mp->ofdm_rates[band], 0xff, sizeof(mp->ofdm_rates[band]));
 	sband = mp->hw->wiphy->bands[band];
@@ -1927,8 +1921,7 @@ minstrel_ht_init_ofdm_rates(struct minstrel_priv *mp, enum nl80211_band band)
 	BUILD_BUG_ON(ARRAY_SIZE(mp->ofdm_rates[band]) != ARRAY_SIZE(bitrates));
 	minstrel_ht_fill_rate_array(mp->ofdm_rates[band], sband,
 				    minstrel_ofdm_bitrates,
-				    ARRAY_SIZE(minstrel_ofdm_bitrates),
-				    rate_flags);
+				    ARRAY_SIZE(minstrel_ofdm_bitrates));
 }
 
 static void *
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index cb7079071885..7b8da40a912d 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -240,6 +240,9 @@ static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata,
 					struct ieee80211_channel *channel,
 					u32 scan_flags, const u8 *da)
 {
+	struct ieee80211_link_data *link_sdata;
+	u8 link_id;
+
 	if (!sdata)
 		return false;
 
@@ -251,7 +254,20 @@ static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata,
 
 	if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR)
 		return true;
-	return ether_addr_equal(da, sdata->vif.addr);
+
+	if (ether_addr_equal(da, sdata->vif.addr))
+		return true;
+
+	for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) {
+		link_sdata = rcu_dereference(sdata->link[link_id]);
+		if (!link_sdata)
+			continue;
+
+		if (ether_addr_equal(da, link_sdata->conf->addr))
+			return true;
+	}
+
+	return false;
 }
 
 void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c
index c6015cd00372..7422888d3640 100644
--- a/net/mac80211/spectmgmt.c
+++ b/net/mac80211/spectmgmt.c
@@ -147,14 +147,14 @@ validate_chandef_by_6ghz_he_eht_oper(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_local *local = sdata->local;
 	u32 control_freq, center_freq1, center_freq2;
 	enum nl80211_chan_width chan_width;
-	struct {
-		struct ieee80211_he_operation _oper;
-		struct ieee80211_he_6ghz_oper _6ghz_oper;
-	} __packed he;
-	struct {
-		struct ieee80211_eht_operation _oper;
-		struct ieee80211_eht_operation_info _oper_info;
-	} __packed eht;
+	DEFINE_RAW_FLEX(struct ieee80211_he_operation, he, optional,
+			sizeof(struct ieee80211_he_6ghz_oper));
+	struct ieee80211_he_6ghz_oper *_6ghz_oper =
+				(struct ieee80211_he_6ghz_oper *)he->optional;
+	DEFINE_RAW_FLEX(struct ieee80211_eht_operation, eht, optional,
+			sizeof(struct ieee80211_eht_operation_info));
+	struct ieee80211_eht_operation_info *_oper_info =
+			(struct ieee80211_eht_operation_info *)eht->optional;
 	const struct ieee80211_eht_operation *eht_oper;
 
 	if (conn->mode < IEEE80211_CONN_MODE_HE) {
@@ -167,38 +167,38 @@ validate_chandef_by_6ghz_he_eht_oper(struct ieee80211_sub_if_data *sdata,
 	center_freq2 = chandef->center_freq2;
 	chan_width = chandef->width;
 
-	he._oper.he_oper_params =
+	he->he_oper_params =
 		le32_encode_bits(1, IEEE80211_HE_OPERATION_6GHZ_OP_INFO);
-	he._6ghz_oper.primary =
+	_6ghz_oper->primary =
 		ieee80211_frequency_to_channel(control_freq);
-	he._6ghz_oper.ccfs0 = ieee80211_frequency_to_channel(center_freq1);
-	he._6ghz_oper.ccfs1 = center_freq2 ?
+	_6ghz_oper->ccfs0 = ieee80211_frequency_to_channel(center_freq1);
+	_6ghz_oper->ccfs1 = center_freq2 ?
 		ieee80211_frequency_to_channel(center_freq2) : 0;
 
 	switch (chan_width) {
 	case NL80211_CHAN_WIDTH_320:
-		he._6ghz_oper.ccfs1 = he._6ghz_oper.ccfs0;
-		he._6ghz_oper.ccfs0 += control_freq < center_freq1 ? -16 : 16;
-		he._6ghz_oper.control = IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ;
+		_6ghz_oper->ccfs1 = _6ghz_oper->ccfs0;
+		_6ghz_oper->ccfs0 += control_freq < center_freq1 ? -16 : 16;
+		_6ghz_oper->control = IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ;
 		break;
 	case NL80211_CHAN_WIDTH_160:
-		he._6ghz_oper.ccfs1 = he._6ghz_oper.ccfs0;
-		he._6ghz_oper.ccfs0 += control_freq < center_freq1 ? -8 : 8;
+		_6ghz_oper->ccfs1 = _6ghz_oper->ccfs0;
+		_6ghz_oper->ccfs0 += control_freq < center_freq1 ? -8 : 8;
 		fallthrough;
 	case NL80211_CHAN_WIDTH_80P80:
-		he._6ghz_oper.control =
+		_6ghz_oper->control =
 			IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ;
 		break;
 	case NL80211_CHAN_WIDTH_80:
-		he._6ghz_oper.control =
+		_6ghz_oper->control =
 			IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ;
 		break;
 	case NL80211_CHAN_WIDTH_40:
-		he._6ghz_oper.control =
+		_6ghz_oper->control =
 			IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ;
 		break;
 	default:
-		he._6ghz_oper.control =
+		_6ghz_oper->control =
 			IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ;
 		break;
 	}
@@ -206,15 +206,14 @@ validate_chandef_by_6ghz_he_eht_oper(struct ieee80211_sub_if_data *sdata,
 	if (conn->mode < IEEE80211_CONN_MODE_EHT) {
 		eht_oper = NULL;
 	} else {
-		eht._oper.params = IEEE80211_EHT_OPER_INFO_PRESENT;
-		eht._oper_info.control = he._6ghz_oper.control;
-		eht._oper_info.ccfs0 = he._6ghz_oper.ccfs0;
-		eht._oper_info.ccfs1 = he._6ghz_oper.ccfs1;
-		eht_oper = &eht._oper;
+		eht->params = IEEE80211_EHT_OPER_INFO_PRESENT;
+		_oper_info->control = _6ghz_oper->control;
+		_oper_info->ccfs0 = _6ghz_oper->ccfs0;
+		_oper_info->ccfs1 = _6ghz_oper->ccfs1;
+		eht_oper = eht;
 	}
 
-	if (!ieee80211_chandef_he_6ghz_oper(local, &he._oper,
-					    eht_oper, chandef))
+	if (!ieee80211_chandef_he_6ghz_oper(local, he, eht_oper, chandef))
 		chandef->chan = NULL;
 }
 
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 248e1f63bf73..84b18be1f0b1 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -18,7 +18,6 @@
 #include <linux/timer.h>
 #include <linux/rtnetlink.h>
 
-#include <net/codel.h>
 #include <net/mac80211.h>
 #include "ieee80211_i.h"
 #include "driver-ops.h"
@@ -701,12 +700,6 @@ __sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
-	sta->cparams.ce_threshold = CODEL_DISABLED_THRESHOLD;
-	sta->cparams.target = MS2TIME(20);
-	sta->cparams.interval = MS2TIME(100);
-	sta->cparams.ecn = true;
-	sta->cparams.ce_threshold_selector = 0;
-	sta->cparams.ce_threshold_mask = 0;
 
 	sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr);
 
@@ -2905,27 +2898,6 @@ unsigned long ieee80211_sta_last_active(struct sta_info *sta)
 	return sta->deflink.status_stats.last_ack;
 }
 
-static void sta_update_codel_params(struct sta_info *sta, u32 thr)
-{
-	if (thr && thr < STA_SLOW_THRESHOLD * sta->local->num_sta) {
-		sta->cparams.target = MS2TIME(50);
-		sta->cparams.interval = MS2TIME(300);
-		sta->cparams.ecn = false;
-	} else {
-		sta->cparams.target = MS2TIME(20);
-		sta->cparams.interval = MS2TIME(100);
-		sta->cparams.ecn = true;
-	}
-}
-
-void ieee80211_sta_set_expected_throughput(struct ieee80211_sta *pubsta,
-					   u32 thr)
-{
-	struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
-
-	sta_update_codel_params(sta, thr);
-}
-
 int ieee80211_sta_allocate_link(struct sta_info *sta, unsigned int link_id)
 {
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 07b7ec39a52f..7a95d8d34fca 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -466,14 +466,6 @@ struct ieee80211_fragment_cache {
 	unsigned int next;
 };
 
-/*
- * The bandwidth threshold below which the per-station CoDel parameters will be
- * scaled to be more lenient (to prevent starvation of slow stations). This
- * value will be scaled by the number of active stations when it is being
- * applied.
- */
-#define STA_SLOW_THRESHOLD 6000 /* 6 Mbps */
-
 /**
  * struct link_sta_info - Link STA information
  * All link specific sta info are stored here for reference. This can be
@@ -626,7 +618,6 @@ struct link_sta_info {
  * @sta: station information we share with the driver
  * @sta_state: duplicates information about station state (for debug)
  * @rcu_head: RCU head used for freeing this station struct
- * @cparams: CoDel parameters for this station.
  * @reserved_tid: reserved TID (if any, otherwise IEEE80211_TID_UNRESERVED)
  * @amsdu_mesh_control: track the mesh A-MSDU format used by the peer:
  *
@@ -717,8 +708,6 @@ struct sta_info {
 	struct dentry *debugfs_dir;
 #endif
 
-	struct codel_params cparams;
-
 	u8 reserved_tid;
 	s8 amsdu_mesh_control;
 
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index b17b3cc7fb90..a362254b310c 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -1085,7 +1085,13 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 
 	ieee80211_report_used_skb(local, skb, false, status->ack_hwtstamp);
 
-	if (status->free_list)
+	/*
+	 * This is a bit racy but we can avoid a lot of work
+	 * with this test...
+	 */
+	if (local->tx_mntrs)
+		ieee80211_tx_monitor(local, skb, retry_count, status);
+	else if (status->free_list)
 		list_add_tail(&skb->list, status->free_list);
 	else
 		dev_kfree_skb(skb);
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index 2f92e7c7f203..94714f8ffd22 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -382,8 +382,8 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_link_data *link,
 	if (WARN_ON_ONCE(!sband))
 		return;
 
-	ieee80211_put_srates_elem(skb, sband, 0, 0, 0, WLAN_EID_SUPP_RATES);
-	ieee80211_put_srates_elem(skb, sband, 0, 0, 0, WLAN_EID_EXT_SUPP_RATES);
+	ieee80211_put_srates_elem(skb, sband, 0, 0, WLAN_EID_SUPP_RATES);
+	ieee80211_put_srates_elem(skb, sband, 0, 0, WLAN_EID_EXT_SUPP_RATES);
 	ieee80211_tdls_add_supp_channels(sdata, skb);
 
 	/* add any custom IEs that go before Extended Capabilities */
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 20179db88c4a..d8d4f3d7d7f2 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -26,6 +26,7 @@
 #include <net/codel_impl.h>
 #include <linux/unaligned.h>
 #include <net/fq_impl.h>
+#include <net/sock.h>
 #include <net/gso.h>
 
 #include "ieee80211_i.h"
@@ -49,19 +50,11 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx,
 	struct ieee80211_supported_band *sband;
 	struct ieee80211_hdr *hdr;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_chanctx_conf *chanctx_conf;
-	u32 rate_flags = 0;
 
 	/* assume HW handles this */
 	if (tx->rate.flags & (IEEE80211_TX_RC_MCS | IEEE80211_TX_RC_VHT_MCS))
 		return 0;
 
-	rcu_read_lock();
-	chanctx_conf = rcu_dereference(tx->sdata->vif.bss_conf.chanctx_conf);
-	if (chanctx_conf)
-		rate_flags = ieee80211_chandef_rate_flags(&chanctx_conf->def);
-	rcu_read_unlock();
-
 	/* uh huh? */
 	if (WARN_ON_ONCE(tx->rate.idx < 0))
 		return 0;
@@ -138,9 +131,6 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx,
 		if (r->bitrate > txrate->bitrate)
 			break;
 
-		if ((rate_flags & r->flags) != rate_flags)
-			continue;
-
 		if (tx->sdata->vif.bss_conf.basic_rates & BIT(i))
 			rate = r->bitrate;
 
@@ -1402,16 +1392,9 @@ static struct sk_buff *fq_tin_dequeue_func(struct fq *fq,
 
 	local = container_of(fq, struct ieee80211_local, fq);
 	txqi = container_of(tin, struct txq_info, tin);
+	cparams = &local->cparams;
 	cstats = &txqi->cstats;
 
-	if (txqi->txq.sta) {
-		struct sta_info *sta = container_of(txqi->txq.sta,
-						    struct sta_info, sta);
-		cparams = &sta->cparams;
-	} else {
-		cparams = &local->cparams;
-	}
-
 	if (flow == &tin->default_flow)
 		cvars = &txqi->def_cvars;
 	else
@@ -2876,8 +2859,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (unlikely(!multicast &&
-		     ((skb->sk &&
-		       skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS) ||
+		     (sk_requests_wifi_status(skb->sk) ||
 		      ctrl_flags & IEEE80211_TX_CTL_REQ_TX_STATUS)))
 		info_id = ieee80211_store_ack_skb(local, skb, &info_flags,
 						  cookie);
@@ -3774,7 +3756,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
 		return false;
 
 	/* don't handle TX status request here either */
-	if (skb->sk && skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)
+	if (sk_requests_wifi_status(skb->sk))
 		return false;
 
 	if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) {
@@ -4526,8 +4508,10 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 						     IEEE80211_TX_CTRL_MLO_LINK_UNSPEC,
 						     NULL);
 	} else if (ieee80211_vif_is_mld(&sdata->vif) &&
-		   sdata->vif.type == NL80211_IFTYPE_AP &&
-		   !ieee80211_hw_check(&sdata->local->hw, MLO_MCAST_MULTI_LINK_TX)) {
+		   ((sdata->vif.type == NL80211_IFTYPE_AP &&
+		     !ieee80211_hw_check(&sdata->local->hw, MLO_MCAST_MULTI_LINK_TX)) ||
+		    (sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
+		     !sdata->wdev.use_4addr))) {
 		ieee80211_mlo_multicast_tx(dev, skb);
 	} else {
 normal:
@@ -4664,8 +4648,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
 			memcpy(IEEE80211_SKB_CB(seg), info, sizeof(*info));
 	}
 
-	if (unlikely(skb->sk &&
-		     skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) {
+	if (unlikely(sk_requests_wifi_status(skb->sk))) {
 		info->status_data = ieee80211_store_ack_skb(local, skb,
 							    &info->flags, NULL);
 		if (info->status_data)
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index dec6e16b8c7d..27d414efa3fd 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1204,7 +1204,6 @@ static int ieee80211_put_preq_ies_band(struct sk_buff *skb,
 	struct ieee80211_supported_band *sband;
 	int i, err;
 	size_t noffset;
-	u32 rate_flags;
 	bool have_80mhz = false;
 
 	*offset = 0;
@@ -1213,13 +1212,11 @@ static int ieee80211_put_preq_ies_band(struct sk_buff *skb,
 	if (WARN_ON_ONCE(!sband))
 		return 0;
 
-	rate_flags = ieee80211_chandef_rate_flags(chandef);
-
 	/* For direct scan add S1G IE and consider its override bits */
 	if (band == NL80211_BAND_S1GHZ)
 		return ieee80211_put_s1g_cap(skb, &sband->s1g_cap);
 
-	err = ieee80211_put_srates_elem(skb, sband, 0, rate_flags,
+	err = ieee80211_put_srates_elem(skb, sband, 0,
 					~rate_mask, WLAN_EID_SUPP_RATES);
 	if (err)
 		return err;
@@ -1241,7 +1238,7 @@ static int ieee80211_put_preq_ies_band(struct sk_buff *skb,
 		*offset = noffset;
 	}
 
-	err = ieee80211_put_srates_elem(skb, sband, 0, rate_flags,
+	err = ieee80211_put_srates_elem(skb, sband, 0,
 					~rate_mask, WLAN_EID_EXT_SUPP_RATES);
 	if (err)
 		return err;
@@ -1522,16 +1519,13 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_supported_band *sband;
 	size_t num_rates;
-	u32 supp_rates, rate_flags;
+	u32 supp_rates;
 	int i, j;
 
 	sband = sdata->local->hw.wiphy->bands[band];
 	if (WARN_ON(!sband))
 		return 1;
 
-	rate_flags =
-		ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chanreq.oper);
-
 	num_rates = sband->n_bitrates;
 	supp_rates = 0;
 	for (i = 0; i < elems->supp_rates_len +
@@ -1551,12 +1545,7 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata,
 			continue;
 
 		for (j = 0; j < num_rates; j++) {
-			int brate;
-			if ((rate_flags & sband->bitrates[j].flags)
-			    != rate_flags)
-				continue;
-
-			brate = sband->bitrates[j].bitrate;
+			int brate = sband->bitrates[j].bitrate;
 
 			if (brate == own_rate) {
 				supp_rates |= BIT(j);
@@ -3223,15 +3212,13 @@ bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper,
 
 int ieee80211_put_srates_elem(struct sk_buff *skb,
 			      const struct ieee80211_supported_band *sband,
-			      u32 basic_rates, u32 rate_flags, u32 masked_rates,
+			      u32 basic_rates, u32 masked_rates,
 			      u8 element_id)
 {
 	u8 i, rates, skip;
 
 	rates = 0;
 	for (i = 0; i < sband->n_bitrates; i++) {
-		if ((rate_flags & sband->bitrates[i].flags) != rate_flags)
-			continue;
 		if (masked_rates & BIT(i))
 			continue;
 		rates++;
@@ -3257,8 +3244,6 @@ int ieee80211_put_srates_elem(struct sk_buff *skb,
 		int rate;
 		u8 basic;
 
-		if ((rate_flags & sband->bitrates[i].flags) != rate_flags)
-			continue;
 		if (masked_rates & BIT(i))
 			continue;
 
diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index dd895617defd..9b12ca97f412 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -630,6 +630,9 @@ static int mctp_sk_hash(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
 
+	/* Bind lookup runs under RCU, remain live during that. */
+	sock_set_flag(sk, SOCK_RCU_FREE);
+
 	mutex_lock(&net->mctp.bind_lock);
 	sk_add_node_rcu(sk, &net->mctp.binds);
 	mutex_unlock(&net->mctp.bind_lock);
diff --git a/net/mctp/device.c b/net/mctp/device.c
index 8e0724c56723..4d404edd7446 100644
--- a/net/mctp/device.c
+++ b/net/mctp/device.c
@@ -117,11 +117,18 @@ static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	struct net_device *dev;
 	struct ifaddrmsg *hdr;
 	struct mctp_dev *mdev;
-	int ifindex, rc;
-
-	hdr = nlmsg_data(cb->nlh);
-	// filter by ifindex if requested
-	ifindex = hdr->ifa_index;
+	int ifindex = 0, rc;
+
+	/* Filter by ifindex if a header is provided */
+	hdr = nlmsg_payload(cb->nlh, sizeof(*hdr));
+	if (hdr) {
+		ifindex = hdr->ifa_index;
+	} else {
+		if (cb->strict_check) {
+			NL_SET_ERR_MSG(cb->extack, "mctp: Invalid header for addr dump request");
+			return -EINVAL;
+		}
+	}
 
 	rcu_read_lock();
 	for_each_netdev_dump(net, dev, mcb->ifindex) {
diff --git a/net/mctp/neigh.c b/net/mctp/neigh.c
index 590f642413e4..05b899f22d90 100644
--- a/net/mctp/neigh.c
+++ b/net/mctp/neigh.c
@@ -250,7 +250,10 @@ static int mctp_rtm_getneigh(struct sk_buff *skb, struct netlink_callback *cb)
 		int idx;
 	} *cbctx = (void *)cb->ctx;
 
-	ndmsg = nlmsg_data(cb->nlh);
+	ndmsg = nlmsg_payload(cb->nlh, sizeof(*ndmsg));
+	if (!ndmsg)
+		return -EINVAL;
+
 	req_ifindex = ndmsg->ndm_ifindex;
 
 	idx = 0;
diff --git a/net/mctp/route.c b/net/mctp/route.c
index 4c460160914f..d9c8e5a5f9ce 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -313,8 +313,10 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev)
 
 	key = flow->key;
 
-	if (WARN_ON(key->dev && key->dev != dev))
+	if (key->dev) {
+		WARN_ON(key->dev != dev);
 		return;
+	}
 
 	mctp_dev_set_key(dev, key);
 }
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 1f63b32d76d6..d536c97144e9 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -2095,12 +2095,12 @@ static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 	struct rtmsg *rtm;
 	int err, i;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
+	rtm = nlmsg_payload(nlh, sizeof(*rtm));
+	if (!rtm) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid header for FIB dump request");
 		return -EINVAL;
 	}
 
-	rtm = nlmsg_data(nlh);
 	if (rtm->rtm_dst_len || rtm->rtm_src_len  || rtm->rtm_tos   ||
 	    rtm->rtm_table   || rtm->rtm_scope    || rtm->rtm_type  ||
 	    rtm->rtm_flags) {
@@ -2288,7 +2288,8 @@ static int mpls_valid_getroute_req(struct sk_buff *skb,
 	struct rtmsg *rtm;
 	int i, err;
 
-	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
+	rtm = nlmsg_payload(nlh, sizeof(*rtm));
+	if (!rtm) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Invalid header for get route request");
 		return -EINVAL;
@@ -2298,7 +2299,6 @@ static int mpls_valid_getroute_req(struct sk_buff *skb,
 		return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
 					      rtm_mpls_policy, extack);
 
-	rtm = nlmsg_data(nlh);
 	if ((rtm->rtm_dst_len && rtm->rtm_dst_len != 20) ||
 	    rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_table ||
 	    rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) {
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index 19eb9292bd60..0c24545f0e8d 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -28,6 +28,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC),
 	SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX),
 	SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
+	SNMP_MIB_ITEM("MPJoinRejected", MPTCP_MIB_JOINREJECTED),
 	SNMP_MIB_ITEM("MPJoinSynTx", MPTCP_MIB_JOINSYNTX),
 	SNMP_MIB_ITEM("MPJoinSynTxCreatSkErr", MPTCP_MIB_JOINSYNTXCREATSKERR),
 	SNMP_MIB_ITEM("MPJoinSynTxBindErr", MPTCP_MIB_JOINSYNTXBINDERR),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 128282982843..250c6b77977e 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -23,6 +23,7 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_JOINSYNACKMAC,	/* HMAC was wrong on SYN/ACK + MP_JOIN */
 	MPTCP_MIB_JOINACKRX,		/* Received an ACK + MP_JOIN */
 	MPTCP_MIB_JOINACKMAC,		/* HMAC was wrong on ACK + MP_JOIN */
+	MPTCP_MIB_JOINREJECTED,		/* The PM rejected the JOIN request */
 	MPTCP_MIB_JOINSYNTX,		/* Sending a SYN + MP_JOIN */
 	MPTCP_MIB_JOINSYNTXCREATSKERR,	/* Not able to create a socket when sending a SYN + MP_JOIN */
 	MPTCP_MIB_JOINSYNTXBINDERR,	/* Not able to bind() the address when sending a SYN + MP_JOIN */
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 31747f974941..1306d4dc287b 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -151,10 +151,13 @@ bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk,
 				     const struct mptcp_addr_info *addr)
 {
 	struct mptcp_pm_add_entry *entry;
+	bool ret;
 
 	entry = mptcp_pm_del_add_timer(msk, addr, false);
+	ret = entry;
 	kfree(entry);
-	return entry;
+
+	return ret;
 }
 
 bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk)
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 2cb62f026b1f..a715dcbe0146 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -337,7 +337,11 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 
 	release_sock(sk);
 
-	sock_kfree_s(sk, match, sizeof(*match));
+	kfree_rcu_mightsleep(match);
+	/* Adjust sk_omem_alloc like sock_kfree_s() does, to match
+	 * with allocation of this memory by sock_kmemdup()
+	 */
+	atomic_sub(sizeof(*match), &sk->sk_omem_alloc);
 
 	err = 0;
 out:
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 44f7ab463d75..0749733ea897 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -46,7 +46,9 @@ static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_sm
 static void __mptcp_destroy_sock(struct sock *sk);
 static void mptcp_check_send_data_fin(struct sock *sk);
 
-DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
+DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 static struct net_device *mptcp_napi_dev;
 
 /* Returns end sequence number of the receiver's advertised window */
@@ -3142,9 +3144,9 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
 {
-	unsigned int offset = sizeof(struct mptcp6_sock) - sizeof(struct ipv6_pinfo);
+	struct mptcp6_sock *msk6 = container_of(mptcp_sk(sk), struct mptcp6_sock, msk);
 
-	return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
+	return &msk6->np;
 }
 
 static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk)
@@ -3527,8 +3529,10 @@ bool mptcp_finish_join(struct sock *ssk)
 		return true;
 	}
 
-	if (!mptcp_pm_allow_new_subflow(msk))
+	if (!mptcp_pm_allow_new_subflow(msk)) {
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_JOINREJECTED);
 		goto err_prohibited;
+	}
 
 	/* If we can't acquire msk socket lock here, let the release callback
 	 * handle it
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index d409586b5977..3dd11dd3ba16 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -479,6 +479,7 @@ mptcp_subflow_rsk(const struct request_sock *rsk)
 
 struct mptcp_delegated_action {
 	struct napi_struct napi;
+	local_lock_t bh_lock;
 	struct list_head head;
 };
 
@@ -670,9 +671,11 @@ static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow,
 		if (WARN_ON_ONCE(!list_empty(&subflow->delegated_node)))
 			return;
 
+		local_lock_nested_bh(&mptcp_delegated_actions.bh_lock);
 		delegated = this_cpu_ptr(&mptcp_delegated_actions);
 		schedule = list_empty(&delegated->head);
 		list_add_tail(&subflow->delegated_node, &delegated->head);
+		local_unlock_nested_bh(&mptcp_delegated_actions.bh_lock);
 		sock_hold(mptcp_subflow_tcp_sock(subflow));
 		if (schedule)
 			napi_schedule(&delegated->napi);
@@ -684,11 +687,15 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated)
 {
 	struct mptcp_subflow_context *ret;
 
-	if (list_empty(&delegated->head))
+	local_lock_nested_bh(&mptcp_delegated_actions.bh_lock);
+	if (list_empty(&delegated->head)) {
+		local_unlock_nested_bh(&mptcp_delegated_actions.bh_lock);
 		return NULL;
+	}
 
 	ret = list_first_entry(&delegated->head, struct mptcp_subflow_context, delegated_node);
 	list_del_init(&ret->delegated_node);
+	local_unlock_nested_bh(&mptcp_delegated_actions.bh_lock);
 	return ret;
 }
 
@@ -744,6 +751,7 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 			 struct sockaddr_storage *addr,
 			 unsigned short family);
 struct mptcp_sched_ops *mptcp_sched_find(const char *name);
+int mptcp_validate_scheduler(struct mptcp_sched_ops *sched);
 int mptcp_register_scheduler(struct mptcp_sched_ops *sched);
 void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
 void mptcp_sched_init(void);
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index c16c6fbd4ba2..1e59072d478c 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -16,8 +16,7 @@
 static DEFINE_SPINLOCK(mptcp_sched_list_lock);
 static LIST_HEAD(mptcp_sched_list);
 
-static int mptcp_sched_default_get_send(struct mptcp_sock *msk,
-					struct mptcp_sched_data *data)
+static int mptcp_sched_default_get_send(struct mptcp_sock *msk)
 {
 	struct sock *ssk;
 
@@ -29,8 +28,7 @@ static int mptcp_sched_default_get_send(struct mptcp_sock *msk,
 	return 0;
 }
 
-static int mptcp_sched_default_get_retrans(struct mptcp_sock *msk,
-					   struct mptcp_sched_data *data)
+static int mptcp_sched_default_get_retrans(struct mptcp_sock *msk)
 {
 	struct sock *ssk;
 
@@ -84,10 +82,23 @@ void mptcp_get_available_schedulers(char *buf, size_t maxlen)
 	rcu_read_unlock();
 }
 
-int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
+int mptcp_validate_scheduler(struct mptcp_sched_ops *sched)
 {
-	if (!sched->get_send)
+	if (!sched->get_send) {
+		pr_err("%s does not implement required ops\n", sched->name);
 		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
+{
+	int ret;
+
+	ret = mptcp_validate_scheduler(sched);
+	if (ret)
+		return ret;
 
 	spin_lock(&mptcp_sched_list_lock);
 	if (mptcp_sched_find(sched->name)) {
@@ -157,7 +168,6 @@ void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 int mptcp_sched_get_send(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
-	struct mptcp_sched_data *data = NULL;
 
 	msk_owned_by_me(msk);
 
@@ -178,14 +188,13 @@ int mptcp_sched_get_send(struct mptcp_sock *msk)
 	}
 
 	if (msk->sched == &mptcp_sched_default || !msk->sched)
-		return mptcp_sched_default_get_send(msk, data);
-	return msk->sched->get_send(msk, data);
+		return mptcp_sched_default_get_send(msk);
+	return msk->sched->get_send(msk);
 }
 
 int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
-	struct mptcp_sched_data *data = NULL;
 
 	msk_owned_by_me(msk);
 
@@ -199,8 +208,8 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 	}
 
 	if (msk->sched == &mptcp_sched_default || !msk->sched)
-		return mptcp_sched_default_get_retrans(msk, data);
+		return mptcp_sched_default_get_retrans(msk);
 	if (msk->sched->get_retrans)
-		return msk->sched->get_retrans(msk, data);
-	return msk->sched->get_send(msk, data);
+		return msk->sched->get_retrans(msk);
+	return msk->sched->get_send(msk);
 }
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 24c2de1891bd..15613d691bfe 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -247,6 +247,7 @@ again:
 
 		if (unlikely(req->syncookie)) {
 			if (!mptcp_can_accept_new_subflow(subflow_req->msk)) {
+				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINREJECTED);
 				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
 				return -EPERM;
 			}
@@ -745,15 +746,11 @@ struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *op
 EXPORT_SYMBOL(mptcp_subflow_reqsk_alloc);
 
 /* validate hmac received in third ACK */
-static bool subflow_hmac_valid(const struct request_sock *req,
+static bool subflow_hmac_valid(const struct mptcp_subflow_request_sock *subflow_req,
 			       const struct mptcp_options_received *mp_opt)
 {
-	const struct mptcp_subflow_request_sock *subflow_req;
+	struct mptcp_sock *msk = subflow_req->msk;
 	u8 hmac[SHA256_DIGEST_SIZE];
-	struct mptcp_sock *msk;
-
-	subflow_req = mptcp_subflow_rsk(req);
-	msk = subflow_req->msk;
 
 	subflow_generate_hmac(READ_ONCE(msk->remote_key),
 			      READ_ONCE(msk->local_key),
@@ -899,13 +896,14 @@ create_child:
 				goto dispose_child;
 			}
 
-			if (!subflow_hmac_valid(req, &mp_opt)) {
+			if (!subflow_hmac_valid(subflow_req, &mp_opt)) {
 				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
 				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
 				goto dispose_child;
 			}
 
 			if (!mptcp_can_accept_new_subflow(owner)) {
+				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINREJECTED);
 				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
 				goto dispose_child;
 			}
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index 4e0842df5234..2c260f33b55c 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -143,16 +143,15 @@ struct ncsi_channel_vlan_filter {
 };
 
 struct ncsi_channel_stats {
-	u32 hnc_cnt_hi;		/* Counter cleared            */
-	u32 hnc_cnt_lo;		/* Counter cleared            */
-	u32 hnc_rx_bytes;	/* Rx bytes                   */
-	u32 hnc_tx_bytes;	/* Tx bytes                   */
-	u32 hnc_rx_uc_pkts;	/* Rx UC packets              */
-	u32 hnc_rx_mc_pkts;     /* Rx MC packets              */
-	u32 hnc_rx_bc_pkts;	/* Rx BC packets              */
-	u32 hnc_tx_uc_pkts;	/* Tx UC packets              */
-	u32 hnc_tx_mc_pkts;	/* Tx MC packets              */
-	u32 hnc_tx_bc_pkts;	/* Tx BC packets              */
+	u64 hnc_cnt;		/* Counter cleared            */
+	u64 hnc_rx_bytes;	/* Rx bytes                   */
+	u64 hnc_tx_bytes;	/* Tx bytes                   */
+	u64 hnc_rx_uc_pkts;	/* Rx UC packets              */
+	u64 hnc_rx_mc_pkts;     /* Rx MC packets              */
+	u64 hnc_rx_bc_pkts;	/* Rx BC packets              */
+	u64 hnc_tx_uc_pkts;	/* Tx UC packets              */
+	u64 hnc_tx_mc_pkts;	/* Tx MC packets              */
+	u64 hnc_tx_bc_pkts;	/* Tx BC packets              */
 	u32 hnc_fcs_err;	/* FCS errors                 */
 	u32 hnc_align_err;	/* Alignment errors           */
 	u32 hnc_false_carrier;	/* False carrier detection    */
@@ -181,7 +180,7 @@ struct ncsi_channel_stats {
 	u32 hnc_tx_1023_frames;	/* Tx 512-1023 bytes frames   */
 	u32 hnc_tx_1522_frames;	/* Tx 1024-1522 bytes frames  */
 	u32 hnc_tx_9022_frames;	/* Tx 1523-9022 bytes frames  */
-	u32 hnc_rx_valid_bytes;	/* Rx valid bytes             */
+	u64 hnc_rx_valid_bytes;	/* Rx valid bytes             */
 	u32 hnc_rx_runt_pkts;	/* Rx error runt packets      */
 	u32 hnc_rx_jabber_pkts;	/* Rx error jabber packets    */
 	u32 ncsi_rx_cmds;	/* Rx NCSI commands           */
diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h
index f2f3b5c1b941..24edb2737972 100644
--- a/net/ncsi/ncsi-pkt.h
+++ b/net/ncsi/ncsi-pkt.h
@@ -252,16 +252,15 @@ struct ncsi_rsp_gp_pkt {
 /* Get Controller Packet Statistics */
 struct ncsi_rsp_gcps_pkt {
 	struct ncsi_rsp_pkt_hdr rsp;            /* Response header            */
-	__be32                  cnt_hi;         /* Counter cleared            */
-	__be32                  cnt_lo;         /* Counter cleared            */
-	__be32                  rx_bytes;       /* Rx bytes                   */
-	__be32                  tx_bytes;       /* Tx bytes                   */
-	__be32                  rx_uc_pkts;     /* Rx UC packets              */
-	__be32                  rx_mc_pkts;     /* Rx MC packets              */
-	__be32                  rx_bc_pkts;     /* Rx BC packets              */
-	__be32                  tx_uc_pkts;     /* Tx UC packets              */
-	__be32                  tx_mc_pkts;     /* Tx MC packets              */
-	__be32                  tx_bc_pkts;     /* Tx BC packets              */
+	__be64                  cnt;            /* Counter cleared            */
+	__be64                  rx_bytes;       /* Rx bytes                   */
+	__be64                  tx_bytes;       /* Tx bytes                   */
+	__be64                  rx_uc_pkts;     /* Rx UC packets              */
+	__be64                  rx_mc_pkts;     /* Rx MC packets              */
+	__be64                  rx_bc_pkts;     /* Rx BC packets              */
+	__be64                  tx_uc_pkts;     /* Tx UC packets              */
+	__be64                  tx_mc_pkts;     /* Tx MC packets              */
+	__be64                  tx_bc_pkts;     /* Tx BC packets              */
 	__be32                  fcs_err;        /* FCS errors                 */
 	__be32                  align_err;      /* Alignment errors           */
 	__be32                  false_carrier;  /* False carrier detection    */
@@ -290,11 +289,11 @@ struct ncsi_rsp_gcps_pkt {
 	__be32                  tx_1023_frames; /* Tx 512-1023 bytes frames   */
 	__be32                  tx_1522_frames; /* Tx 1024-1522 bytes frames  */
 	__be32                  tx_9022_frames; /* Tx 1523-9022 bytes frames  */
-	__be32                  rx_valid_bytes; /* Rx valid bytes             */
+	__be64                  rx_valid_bytes; /* Rx valid bytes             */
 	__be32                  rx_runt_pkts;   /* Rx error runt packets      */
 	__be32                  rx_jabber_pkts; /* Rx error jabber packets    */
 	__be32                  checksum;       /* Checksum                   */
-};
+}  __packed __aligned(4);
 
 /* Get NCSI Statistics */
 struct ncsi_rsp_gns_pkt {
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 4a8ce2949fae..8668888c5a2f 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -926,16 +926,15 @@ static int ncsi_rsp_handler_gcps(struct ncsi_request *nr)
 
 	/* Update HNC's statistics */
 	ncs = &nc->stats;
-	ncs->hnc_cnt_hi         = ntohl(rsp->cnt_hi);
-	ncs->hnc_cnt_lo         = ntohl(rsp->cnt_lo);
-	ncs->hnc_rx_bytes       = ntohl(rsp->rx_bytes);
-	ncs->hnc_tx_bytes       = ntohl(rsp->tx_bytes);
-	ncs->hnc_rx_uc_pkts     = ntohl(rsp->rx_uc_pkts);
-	ncs->hnc_rx_mc_pkts     = ntohl(rsp->rx_mc_pkts);
-	ncs->hnc_rx_bc_pkts     = ntohl(rsp->rx_bc_pkts);
-	ncs->hnc_tx_uc_pkts     = ntohl(rsp->tx_uc_pkts);
-	ncs->hnc_tx_mc_pkts     = ntohl(rsp->tx_mc_pkts);
-	ncs->hnc_tx_bc_pkts     = ntohl(rsp->tx_bc_pkts);
+	ncs->hnc_cnt            = be64_to_cpu(rsp->cnt);
+	ncs->hnc_rx_bytes       = be64_to_cpu(rsp->rx_bytes);
+	ncs->hnc_tx_bytes       = be64_to_cpu(rsp->tx_bytes);
+	ncs->hnc_rx_uc_pkts     = be64_to_cpu(rsp->rx_uc_pkts);
+	ncs->hnc_rx_mc_pkts     = be64_to_cpu(rsp->rx_mc_pkts);
+	ncs->hnc_rx_bc_pkts     = be64_to_cpu(rsp->rx_bc_pkts);
+	ncs->hnc_tx_uc_pkts     = be64_to_cpu(rsp->tx_uc_pkts);
+	ncs->hnc_tx_mc_pkts     = be64_to_cpu(rsp->tx_mc_pkts);
+	ncs->hnc_tx_bc_pkts     = be64_to_cpu(rsp->tx_bc_pkts);
 	ncs->hnc_fcs_err        = ntohl(rsp->fcs_err);
 	ncs->hnc_align_err      = ntohl(rsp->align_err);
 	ncs->hnc_false_carrier  = ntohl(rsp->false_carrier);
@@ -964,7 +963,7 @@ static int ncsi_rsp_handler_gcps(struct ncsi_request *nr)
 	ncs->hnc_tx_1023_frames = ntohl(rsp->tx_1023_frames);
 	ncs->hnc_tx_1522_frames = ntohl(rsp->tx_1522_frames);
 	ncs->hnc_tx_9022_frames = ntohl(rsp->tx_9022_frames);
-	ncs->hnc_rx_valid_bytes = ntohl(rsp->rx_valid_bytes);
+	ncs->hnc_rx_valid_bytes = be64_to_cpu(rsp->rx_valid_bytes);
 	ncs->hnc_rx_runt_pkts   = ntohl(rsp->rx_runt_pkts);
 	ncs->hnc_rx_jabber_pkts = ntohl(rsp->rx_jabber_pkts);
 
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 047ba81865ed..2560416218d0 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -212,7 +212,7 @@ config NF_CT_PROTO_SCTP
 	bool 'SCTP protocol connection tracking support'
 	depends on NETFILTER_ADVANCED
 	default y
-	select CRC32
+	select NET_CRC32C
 	help
 	  With this option enabled, the layer 3 independent connection
 	  tracking code will be able to do state tracking on SCTP connections.
@@ -475,7 +475,7 @@ endif # NF_CONNTRACK
 
 config NF_TABLES
 	select NETFILTER_NETLINK
-	select CRC32
+	select NET_CRC32C
 	tristate "Netfilter nf_tables support"
 	help
 	  nftables is the new packet classification framework that intends to
@@ -1180,7 +1180,7 @@ config NETFILTER_XT_MATCH_CGROUP
 	tristate '"control group" match support'
 	depends on NETFILTER_ADVANCED
 	depends on CGROUPS
-	select CGROUP_NET_CLASSID
+	select SOCK_CGROUP_DATA
 	help
 	Socket/process control group matching allows you to match locally
 	generated packets based on which net_cls control group processes
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index cf3ce72c3de6..5251524b96af 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -64,7 +64,7 @@ struct hbucket {
 #define ahash_sizeof_regions(htable_bits)		\
 	(ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region))
 #define ahash_region(n, htable_bits)		\
-	((n) % ahash_numof_locks(htable_bits))
+	((n) / jhash_size(HTABLE_REGION_BITS))
 #define ahash_bucket_start(h,  htable_bits)	\
 	((htable_bits) < HTABLE_REGION_BITS ? 0	\
 		: (h) * jhash_size(HTABLE_REGION_BITS))
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 8c5b1fe12d07..c203252e856d 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -105,7 +105,7 @@ config	IP_VS_PROTO_AH
 
 config  IP_VS_PROTO_SCTP
 	bool "SCTP load balancing support"
-	select CRC32
+	select NET_CRC32C
 	help
 	  This option enables support for load balancing SCTP transport
 	  protocol. Say Y if unsure.
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 3313bceb6cc9..014f07740369 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -119,13 +119,12 @@ __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu)
 	return false;
 }
 
-/* Get route to daddr, update *saddr, optionally bind route to saddr */
+/* Get route to daddr, optionally bind route to saddr */
 static struct rtable *do_output_route4(struct net *net, __be32 daddr,
-				       int rt_mode, __be32 *saddr)
+				       int rt_mode, __be32 *ret_saddr)
 {
 	struct flowi4 fl4;
 	struct rtable *rt;
-	bool loop = false;
 
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = daddr;
@@ -135,23 +134,17 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr,
 retry:
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt)) {
-		/* Invalid saddr ? */
-		if (PTR_ERR(rt) == -EINVAL && *saddr &&
-		    rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
-			*saddr = 0;
-			flowi4_update_output(&fl4, 0, daddr, 0);
-			goto retry;
-		}
 		IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
 		return NULL;
-	} else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
+	}
+	if (rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
 		ip_rt_put(rt);
-		*saddr = fl4.saddr;
 		flowi4_update_output(&fl4, 0, daddr, fl4.saddr);
-		loop = true;
+		rt_mode = 0;
 		goto retry;
 	}
-	*saddr = fl4.saddr;
+	if (ret_saddr)
+		*ret_saddr = fl4.saddr;
 	return rt;
 }
 
@@ -344,19 +337,15 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 		if (ret_saddr)
 			*ret_saddr = dest_dst->dst_saddr.ip;
 	} else {
-		__be32 saddr = htonl(INADDR_ANY);
-
 		noref = 0;
 
 		/* For such unconfigured boxes avoid many route lookups
 		 * for performance reasons because we do not remember saddr
 		 */
 		rt_mode &= ~IP_VS_RT_MODE_CONNECT;
-		rt = do_output_route4(net, daddr, rt_mode, &saddr);
+		rt = do_output_route4(net, daddr, rt_mode, ret_saddr);
 		if (!rt)
 			goto err_unreach;
-		if (ret_saddr)
-			*ret_saddr = saddr;
 	}
 
 	local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 7f8b245e287a..de8d50af9b5b 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -531,10 +531,8 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
 
 		p = tmpl;
 		tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p);
-		if (tmpl != p) {
-			tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p);
+		if (tmpl != p)
 			tmpl->proto.tmpl_padto = (char *)tmpl - (char *)p;
-		}
 	} else {
 		tmpl = kzalloc(sizeof(*tmpl), flags);
 		if (!tmpl)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 2f666751c7e7..6c4cff10357d 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -98,69 +98,87 @@ struct ct_iter_state {
 	struct seq_net_private p;
 	struct hlist_nulls_head *hash;
 	unsigned int htable_size;
+	unsigned int skip_elems;
 	unsigned int bucket;
 	u_int64_t time_now;
 };
 
-static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
+static struct nf_conntrack_tuple_hash *ct_get_next(const struct net *net,
+						   struct ct_iter_state *st)
 {
-	struct ct_iter_state *st = seq->private;
+	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
+	unsigned int i;
 
-	for (st->bucket = 0;
-	     st->bucket < st->htable_size;
-	     st->bucket++) {
-		n = rcu_dereference(
-			hlist_nulls_first_rcu(&st->hash[st->bucket]));
-		if (!is_a_nulls(n))
-			return n;
-	}
-	return NULL;
-}
+	for (i = st->bucket; i < st->htable_size; i++) {
+		unsigned int skip = 0;
 
-static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
-				      struct hlist_nulls_node *head)
-{
-	struct ct_iter_state *st = seq->private;
+restart:
+		hlist_nulls_for_each_entry_rcu(h, n, &st->hash[i], hnnode) {
+			struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+			struct hlist_nulls_node *tmp = n;
 
-	head = rcu_dereference(hlist_nulls_next_rcu(head));
-	while (is_a_nulls(head)) {
-		if (likely(get_nulls_value(head) == st->bucket)) {
-			if (++st->bucket >= st->htable_size)
-				return NULL;
+			if (!net_eq(net, nf_ct_net(ct)))
+				continue;
+
+			if (++skip <= st->skip_elems)
+				continue;
+
+			/* h should be returned, skip to nulls marker. */
+			while (!is_a_nulls(tmp))
+				tmp = rcu_dereference(hlist_nulls_next_rcu(tmp));
+
+			/* check if h is still linked to hash[i] */
+			if (get_nulls_value(tmp) != i) {
+				skip = 0;
+				goto restart;
+			}
+
+			st->skip_elems = skip;
+			st->bucket = i;
+			return h;
 		}
-		head = rcu_dereference(
-			hlist_nulls_first_rcu(&st->hash[st->bucket]));
-	}
-	return head;
-}
 
-static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos)
-{
-	struct hlist_nulls_node *head = ct_get_first(seq);
+		skip = 0;
+		if (get_nulls_value(n) != i)
+			goto restart;
+
+		st->skip_elems = 0;
+	}
 
-	if (head)
-		while (pos && (head = ct_get_next(seq, head)))
-			pos--;
-	return pos ? NULL : head;
+	st->bucket = i;
+	return NULL;
 }
 
 static void *ct_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(RCU)
 {
 	struct ct_iter_state *st = seq->private;
+	struct net *net = seq_file_net(seq);
 
 	st->time_now = ktime_get_real_ns();
 	rcu_read_lock();
 
 	nf_conntrack_get_ht(&st->hash, &st->htable_size);
-	return ct_get_idx(seq, *pos);
+
+	if (*pos == 0) {
+		st->skip_elems = 0;
+		st->bucket = 0;
+	} else if (st->skip_elems) {
+		/* resume from last dumped entry */
+		st->skip_elems--;
+	}
+
+	return ct_get_next(net, st);
 }
 
 static void *ct_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
+	struct ct_iter_state *st = s->private;
+	struct net *net = seq_file_net(s);
+
 	(*pos)++;
-	return ct_get_next(s, v);
+	return ct_get_next(net, st);
 }
 
 static void ct_seq_stop(struct seq_file *s, void *v)
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 9d8361526f82..9441ac3d8c1a 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -383,8 +383,8 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
 void flow_offload_teardown(struct flow_offload *flow)
 {
 	clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status);
-	set_bit(NF_FLOW_TEARDOWN, &flow->flags);
-	flow_offload_fixup_ct(flow);
+	if (!test_and_set_bit(NF_FLOW_TEARDOWN, &flow->flags))
+		flow_offload_fixup_ct(flow);
 }
 EXPORT_SYMBOL_GPL(flow_offload_teardown);
 
@@ -558,10 +558,12 @@ static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table,
 
 	if (nf_flow_has_expired(flow) ||
 	    nf_ct_is_dying(flow->ct) ||
-	    nf_flow_custom_gc(flow_table, flow))
+	    nf_flow_custom_gc(flow_table, flow)) {
 		flow_offload_teardown(flow);
-	else if (!teardown)
+		teardown = true;
+	} else if (!teardown) {
 		nf_flow_table_extend_ct_timeout(flow->ct);
+	}
 
 	if (teardown) {
 		if (test_bit(NF_FLOW_HW, &flow->flags)) {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a133e1c175ce..b28f6730e26d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4569,6 +4569,8 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
 	[NFTA_SET_HANDLE]		= { .type = NLA_U64 },
 	[NFTA_SET_EXPR]			= { .type = NLA_NESTED },
 	[NFTA_SET_EXPRESSIONS]		= NLA_POLICY_NESTED_ARRAY(nft_expr_policy),
+	[NFTA_SET_TYPE]			= { .type = NLA_REJECT },
+	[NFTA_SET_COUNT]		= { .type = NLA_REJECT },
 };
 
 static const struct nla_policy nft_concat_policy[NFTA_SET_FIELD_MAX + 1] = {
@@ -4763,6 +4765,27 @@ static u32 nft_set_userspace_size(const struct nft_set_ops *ops, u32 size)
 	return size;
 }
 
+static noinline_for_stack int
+nf_tables_fill_set_info(struct sk_buff *skb, const struct nft_set *set)
+{
+	unsigned int nelems;
+	char str[40];
+	int ret;
+
+	ret = snprintf(str, sizeof(str), "%ps", set->ops);
+
+	/* Not expected to happen and harmless: NFTA_SET_TYPE is dumped
+	 * to userspace purely for informational/debug purposes.
+	 */
+	DEBUG_NET_WARN_ON_ONCE(ret >= sizeof(str));
+
+	if (nla_put_string(skb, NFTA_SET_TYPE, str))
+		return -EMSGSIZE;
+
+	nelems = nft_set_userspace_size(set->ops, atomic_read(&set->nelems));
+	return nla_put_be32(skb, NFTA_SET_COUNT, htonl(nelems));
+}
+
 static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 			      const struct nft_set *set, u16 event, u16 flags)
 {
@@ -4843,6 +4866,9 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 
 	nla_nest_end(skb, nest);
 
+	if (nf_tables_fill_set_info(skb, set))
+		goto nla_put_failure;
+
 	if (set->num_exprs == 1) {
 		nest = nla_nest_start_noflag(skb, NFTA_SET_EXPR);
 		if (nf_tables_fill_expr_info(skb, set->exprs[0], false) < 0)
diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c
index 9b2d7463d3d3..df0798da2329 100644
--- a/net/netfilter/nft_quota.c
+++ b/net/netfilter/nft_quota.c
@@ -19,10 +19,16 @@ struct nft_quota {
 };
 
 static inline bool nft_overquota(struct nft_quota *priv,
-				 const struct sk_buff *skb)
+				 const struct sk_buff *skb,
+				 bool *report)
 {
-	return atomic64_add_return(skb->len, priv->consumed) >=
-	       atomic64_read(&priv->quota);
+	u64 consumed = atomic64_add_return(skb->len, priv->consumed);
+	u64 quota = atomic64_read(&priv->quota);
+
+	if (report)
+		*report = consumed >= quota;
+
+	return consumed > quota;
 }
 
 static inline bool nft_quota_invert(struct nft_quota *priv)
@@ -34,7 +40,7 @@ static inline void nft_quota_do_eval(struct nft_quota *priv,
 				     struct nft_regs *regs,
 				     const struct nft_pktinfo *pkt)
 {
-	if (nft_overquota(priv, pkt->skb) ^ nft_quota_invert(priv))
+	if (nft_overquota(priv, pkt->skb, NULL) ^ nft_quota_invert(priv))
 		regs->verdict.code = NFT_BREAK;
 }
 
@@ -51,13 +57,13 @@ static void nft_quota_obj_eval(struct nft_object *obj,
 			       const struct nft_pktinfo *pkt)
 {
 	struct nft_quota *priv = nft_obj_data(obj);
-	bool overquota;
+	bool overquota, report;
 
-	overquota = nft_overquota(priv, pkt->skb);
+	overquota = nft_overquota(priv, pkt->skb, &report);
 	if (overquota ^ nft_quota_invert(priv))
 		regs->verdict.code = NFT_BREAK;
 
-	if (overquota &&
+	if (report &&
 	    !test_and_set_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags))
 		nft_obj_notify(nft_net(pkt), obj->key.table, obj, 0, 0,
 			       NFT_MSG_NEWOBJ, 0, nft_pf(pkt), 0, GFP_ATOMIC);
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 7be342b495f5..c5855069bdab 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -663,6 +663,9 @@ static int pipapo_realloc_mt(struct nft_pipapo_field *f,
 	    check_add_overflow(rules, extra, &rules_alloc))
 		return -EOVERFLOW;
 
+	if (rules_alloc > (INT_MAX / sizeof(*new_mt)))
+		return -ENOMEM;
+
 	new_mt = kvmalloc_array(rules_alloc, sizeof(*new_mt), GFP_KERNEL_ACCOUNT);
 	if (!new_mt)
 		return -ENOMEM;
@@ -683,6 +686,30 @@ out_free:
 	return 0;
 }
 
+
+/**
+ * lt_calculate_size() - Get storage size for lookup table with overflow check
+ * @groups:	Amount of bit groups
+ * @bb:		Number of bits grouped together in lookup table buckets
+ * @bsize:	Size of each bucket in lookup table, in longs
+ *
+ * Return: allocation size including alignment overhead, negative on overflow
+ */
+static ssize_t lt_calculate_size(unsigned int groups, unsigned int bb,
+				 unsigned int bsize)
+{
+	ssize_t ret = groups * NFT_PIPAPO_BUCKETS(bb) * sizeof(long);
+
+	if (check_mul_overflow(ret, bsize, &ret))
+		return -1;
+	if (check_add_overflow(ret, NFT_PIPAPO_ALIGN_HEADROOM, &ret))
+		return -1;
+	if (ret > INT_MAX)
+		return -1;
+
+	return ret;
+}
+
 /**
  * pipapo_resize() - Resize lookup or mapping table, or both
  * @f:		Field containing lookup and mapping tables
@@ -701,6 +728,7 @@ static int pipapo_resize(struct nft_pipapo_field *f,
 	long *new_lt = NULL, *new_p, *old_lt = f->lt, *old_p;
 	unsigned int new_bucket_size, copy;
 	int group, bucket, err;
+	ssize_t lt_size;
 
 	if (rules >= NFT_PIPAPO_RULE0_MAX)
 		return -ENOSPC;
@@ -719,10 +747,11 @@ static int pipapo_resize(struct nft_pipapo_field *f,
 	else
 		copy = new_bucket_size;
 
-	new_lt = kvzalloc(f->groups * NFT_PIPAPO_BUCKETS(f->bb) *
-			  new_bucket_size * sizeof(*new_lt) +
-			  NFT_PIPAPO_ALIGN_HEADROOM,
-			  GFP_KERNEL);
+	lt_size = lt_calculate_size(f->groups, f->bb, new_bucket_size);
+	if (lt_size < 0)
+		return -ENOMEM;
+
+	new_lt = kvzalloc(lt_size, GFP_KERNEL_ACCOUNT);
 	if (!new_lt)
 		return -ENOMEM;
 
@@ -907,7 +936,7 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f)
 {
 	unsigned int groups, bb;
 	unsigned long *new_lt;
-	size_t lt_size;
+	ssize_t lt_size;
 
 	lt_size = f->groups * NFT_PIPAPO_BUCKETS(f->bb) * f->bsize *
 		  sizeof(*f->lt);
@@ -917,15 +946,17 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f)
 		groups = f->groups * 2;
 		bb = NFT_PIPAPO_GROUP_BITS_LARGE_SET;
 
-		lt_size = groups * NFT_PIPAPO_BUCKETS(bb) * f->bsize *
-			  sizeof(*f->lt);
+		lt_size = lt_calculate_size(groups, bb, f->bsize);
+		if (lt_size < 0)
+			return;
 	} else if (f->bb == NFT_PIPAPO_GROUP_BITS_LARGE_SET &&
 		   lt_size < NFT_PIPAPO_LT_SIZE_LOW) {
 		groups = f->groups / 2;
 		bb = NFT_PIPAPO_GROUP_BITS_SMALL_SET;
 
-		lt_size = groups * NFT_PIPAPO_BUCKETS(bb) * f->bsize *
-			  sizeof(*f->lt);
+		lt_size = lt_calculate_size(groups, bb, f->bsize);
+		if (lt_size < 0)
+			return;
 
 		/* Don't increase group width if the resulting lookup table size
 		 * would exceed the upper size threshold for a "small" set.
@@ -936,7 +967,7 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f)
 		return;
 	}
 
-	new_lt = kvzalloc(lt_size + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL_ACCOUNT);
+	new_lt = kvzalloc(lt_size, GFP_KERNEL_ACCOUNT);
 	if (!new_lt)
 		return;
 
@@ -1451,13 +1482,15 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 
 	for (i = 0; i < old->field_count; i++) {
 		unsigned long *new_lt;
+		ssize_t lt_size;
 
 		memcpy(dst, src, offsetof(struct nft_pipapo_field, lt));
 
-		new_lt = kvzalloc(src->groups * NFT_PIPAPO_BUCKETS(src->bb) *
-				  src->bsize * sizeof(*dst->lt) +
-				  NFT_PIPAPO_ALIGN_HEADROOM,
-				  GFP_KERNEL_ACCOUNT);
+		lt_size = lt_calculate_size(src->groups, src->bb, src->bsize);
+		if (lt_size < 0)
+			goto out_lt;
+
+		new_lt = kvzalloc(lt_size, GFP_KERNEL_ACCOUNT);
 		if (!new_lt)
 			goto out_lt;
 
@@ -1469,6 +1502,9 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 		       src->groups * NFT_PIPAPO_BUCKETS(src->bb));
 
 		if (src->rules > 0) {
+			if (src->rules_alloc > (INT_MAX / sizeof(*src->mt)))
+				goto out_mt;
+
 			dst->mt = kvmalloc_array(src->rules_alloc,
 						 sizeof(*src->mt),
 						 GFP_KERNEL_ACCOUNT);
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index 9f54819eb52c..9082155ee558 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -168,7 +168,7 @@ static int idletimer_tg_create(struct idletimer_tg_info *info)
 	INIT_WORK(&info->timer->work, idletimer_tg_work);
 
 	mod_timer(&info->timer->timer,
-		  msecs_to_jiffies(info->timeout * 1000) + jiffies);
+		  secs_to_jiffies(info->timeout) + jiffies);
 
 	return 0;
 
@@ -229,7 +229,7 @@ static int idletimer_tg_create_v1(struct idletimer_tg_info_v1 *info)
 	} else {
 		timer_setup(&info->timer->timer, idletimer_tg_expired, 0);
 		mod_timer(&info->timer->timer,
-				msecs_to_jiffies(info->timeout * 1000) + jiffies);
+				secs_to_jiffies(info->timeout) + jiffies);
 	}
 
 	return 0;
@@ -254,7 +254,7 @@ static unsigned int idletimer_tg_target(struct sk_buff *skb,
 		 info->label, info->timeout);
 
 	mod_timer(&info->timer->timer,
-		  msecs_to_jiffies(info->timeout * 1000) + jiffies);
+		  secs_to_jiffies(info->timeout) + jiffies);
 
 	return XT_CONTINUE;
 }
@@ -275,7 +275,7 @@ static unsigned int idletimer_tg_target_v1(struct sk_buff *skb,
 		alarm_start_relative(&info->timer->alarm, tout);
 	} else {
 		mod_timer(&info->timer->timer,
-				msecs_to_jiffies(info->timeout * 1000) + jiffies);
+				secs_to_jiffies(info->timeout) + jiffies);
 	}
 
 	return XT_CONTINUE;
@@ -320,7 +320,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
 	if (info->timer) {
 		info->timer->refcnt++;
 		mod_timer(&info->timer->timer,
-			  msecs_to_jiffies(info->timeout * 1000) + jiffies);
+			  secs_to_jiffies(info->timeout) + jiffies);
 
 		pr_debug("increased refcnt of timer %s to %u\n",
 			 info->label, info->timer->refcnt);
@@ -382,7 +382,7 @@ static int idletimer_tg_checkentry_v1(const struct xt_tgchk_param *par)
 			}
 		} else {
 				mod_timer(&info->timer->timer,
-					msecs_to_jiffies(info->timeout * 1000) + jiffies);
+					secs_to_jiffies(info->timeout) + jiffies);
 		}
 		pr_debug("increased refcnt of timer %s to %u\n",
 			 info->label, info->timer->refcnt);
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
index c0f5e9a4f3c6..c437fbd59ec1 100644
--- a/net/netfilter/xt_cgroup.c
+++ b/net/netfilter/xt_cgroup.c
@@ -23,6 +23,8 @@ MODULE_DESCRIPTION("Xtables: process control group matching");
 MODULE_ALIAS("ipt_cgroup");
 MODULE_ALIAS("ip6t_cgroup");
 
+#define NET_CLS_CLASSID_INVALID_MSG "xt_cgroup: classid invalid without net_cls cgroups\n"
+
 static int cgroup_mt_check_v0(const struct xt_mtchk_param *par)
 {
 	struct xt_cgroup_info_v0 *info = par->matchinfo;
@@ -30,6 +32,11 @@ static int cgroup_mt_check_v0(const struct xt_mtchk_param *par)
 	if (info->invert & ~1)
 		return -EINVAL;
 
+	if (!IS_ENABLED(CONFIG_CGROUP_NET_CLASSID)) {
+		pr_info(NET_CLS_CLASSID_INVALID_MSG);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -51,6 +58,11 @@ static int cgroup_mt_check_v1(const struct xt_mtchk_param *par)
 		return -EINVAL;
 	}
 
+	if (info->has_classid && !IS_ENABLED(CONFIG_CGROUP_NET_CLASSID)) {
+		pr_info(NET_CLS_CLASSID_INVALID_MSG);
+		return -EINVAL;
+	}
+
 	info->priv = NULL;
 	if (info->has_path) {
 		cgrp = cgroup_get_from_path(info->path);
@@ -83,6 +95,11 @@ static int cgroup_mt_check_v2(const struct xt_mtchk_param *par)
 		return -EINVAL;
 	}
 
+	if (info->has_classid && !IS_ENABLED(CONFIG_CGROUP_NET_CLASSID)) {
+		pr_info(NET_CLS_CLASSID_INVALID_MSG);
+		return -EINVAL;
+	}
+
 	info->priv = NULL;
 	if (info->has_path) {
 		cgrp = cgroup_get_from_path(info->path);
@@ -100,6 +117,7 @@ static int cgroup_mt_check_v2(const struct xt_mtchk_param *par)
 static bool
 cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par)
 {
+#ifdef CONFIG_CGROUP_NET_CLASSID
 	const struct xt_cgroup_info_v0 *info = par->matchinfo;
 	struct sock *sk = skb->sk;
 
@@ -108,6 +126,8 @@ cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par)
 
 	return (info->id == sock_cgroup_classid(&skb->sk->sk_cgrp_data)) ^
 		info->invert;
+#endif
+	return false;
 }
 
 static bool cgroup_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
@@ -123,9 +143,12 @@ static bool cgroup_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
 	if (ancestor)
 		return cgroup_is_descendant(sock_cgroup_ptr(skcd), ancestor) ^
 			info->invert_path;
+#ifdef CONFIG_CGROUP_NET_CLASSID
 	else
 		return (info->classid == sock_cgroup_classid(skcd)) ^
 			info->invert_classid;
+#endif
+	return false;
 }
 
 static bool cgroup_mt_v2(const struct sk_buff *skb, struct xt_action_param *par)
@@ -141,9 +164,12 @@ static bool cgroup_mt_v2(const struct sk_buff *skb, struct xt_action_param *par)
 	if (ancestor)
 		return cgroup_is_descendant(sock_cgroup_ptr(skcd), ancestor) ^
 			info->invert_path;
+#ifdef CONFIG_CGROUP_NET_CLASSID
 	else
 		return (info->classid == sock_cgroup_classid(skcd)) ^
 			info->invert_classid;
+#endif
+	return false;
 }
 
 static void cgroup_mt_destroy_v1(const struct xt_mtdtor_param *par)
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index 1f8909c16f14..99458da6be32 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -311,6 +311,8 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state,
 					      NL_POLICY_TYPE_ATTR_PAD))
 				goto nla_put_failure;
 			break;
+		} else if (pt->validation_type == NLA_VALIDATE_FUNCTION) {
+			break;
 		}
 
 		nla_get_range_unsigned(pt, &range);
@@ -340,6 +342,9 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state,
 		else
 			type = NL_ATTR_TYPE_SINT;
 
+		if (pt->validation_type == NLA_VALIDATE_FUNCTION)
+			break;
+
 		nla_get_range_signed(pt, &range);
 
 		if (nla_put_s64(skb, NL_POLICY_TYPE_ATTR_MIN_VALUE_S,
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index 5481bd561eb4..e6aaee92dba4 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -11,8 +11,8 @@ config OPENVSWITCH
 				     (!NF_NAT || NF_NAT) && \
 				     (!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT)))
 	depends on PSAMPLE || !PSAMPLE
-	select CRC32
 	select MPLS
+	select NET_CRC32C
 	select NET_MPLS_GSO
 	select DST_CACHE
 	select NET_NSH
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 61fea7baae5d..e7269a3eec79 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -39,56 +39,18 @@
 #include "flow_netlink.h"
 #include "openvswitch_trace.h"
 
-struct deferred_action {
-	struct sk_buff *skb;
-	const struct nlattr *actions;
-	int actions_len;
-
-	/* Store pkt_key clone when creating deferred action. */
-	struct sw_flow_key pkt_key;
-};
-
-#define MAX_L2_LEN	(VLAN_ETH_HLEN + 3 * MPLS_HLEN)
-struct ovs_frag_data {
-	unsigned long dst;
-	struct vport *vport;
-	struct ovs_skb_cb cb;
-	__be16 inner_protocol;
-	u16 network_offset;	/* valid only for MPLS */
-	u16 vlan_tci;
-	__be16 vlan_proto;
-	unsigned int l2_len;
-	u8 mac_proto;
-	u8 l2_data[MAX_L2_LEN];
-};
-
-static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage);
-
-#define DEFERRED_ACTION_FIFO_SIZE 10
-#define OVS_RECURSION_LIMIT 5
-#define OVS_DEFERRED_ACTION_THRESHOLD (OVS_RECURSION_LIMIT - 2)
-struct action_fifo {
-	int head;
-	int tail;
-	/* Deferred action fifo queue storage. */
-	struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
+DEFINE_PER_CPU(struct ovs_pcpu_storage, ovs_pcpu_storage) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
 };
 
-struct action_flow_keys {
-	struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD];
-};
-
-static struct action_fifo __percpu *action_fifos;
-static struct action_flow_keys __percpu *flow_keys;
-static DEFINE_PER_CPU(int, exec_actions_level);
-
 /* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys'
  * space. Return NULL if out of key spaces.
  */
 static struct sw_flow_key *clone_key(const struct sw_flow_key *key_)
 {
-	struct action_flow_keys *keys = this_cpu_ptr(flow_keys);
-	int level = this_cpu_read(exec_actions_level);
+	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(&ovs_pcpu_storage);
+	struct action_flow_keys *keys = &ovs_pcpu->flow_keys;
+	int level = ovs_pcpu->exec_level;
 	struct sw_flow_key *key = NULL;
 
 	if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
@@ -132,10 +94,9 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
 				    const struct nlattr *actions,
 				    const int actions_len)
 {
-	struct action_fifo *fifo;
+	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage.action_fifos);
 	struct deferred_action *da;
 
-	fifo = this_cpu_ptr(action_fifos);
 	da = action_fifo_put(fifo);
 	if (da) {
 		da->skb = skb;
@@ -794,7 +755,7 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 static int ovs_vport_output(struct net *net, struct sock *sk,
 			    struct sk_buff *skb)
 {
-	struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
+	struct ovs_frag_data *data = this_cpu_ptr(&ovs_pcpu_storage.frag_data);
 	struct vport *vport = data->vport;
 
 	if (skb_cow_head(skb, data->l2_len) < 0) {
@@ -846,7 +807,7 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb,
 	unsigned int hlen = skb_network_offset(skb);
 	struct ovs_frag_data *data;
 
-	data = this_cpu_ptr(&ovs_frag_data_storage);
+	data = this_cpu_ptr(&ovs_pcpu_storage.frag_data);
 	data->dst = skb->_skb_refdst;
 	data->vport = vport;
 	data->cb = *OVS_CB(skb);
@@ -975,8 +936,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 	upcall.cmd = OVS_PACKET_CMD_ACTION;
 	upcall.mru = OVS_CB(skb)->mru;
 
-	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
-	     a = nla_next(a, &rem)) {
+	nla_for_each_nested(a, attr, rem) {
 		switch (nla_type(a)) {
 		case OVS_USERSPACE_ATTR_USERDATA:
 			upcall.userdata = a;
@@ -1609,13 +1569,13 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
 
 		if (actions) { /* Sample action */
 			if (clone_flow_key)
-				__this_cpu_inc(exec_actions_level);
+				__this_cpu_inc(ovs_pcpu_storage.exec_level);
 
 			err = do_execute_actions(dp, skb, clone,
 						 actions, len);
 
 			if (clone_flow_key)
-				__this_cpu_dec(exec_actions_level);
+				__this_cpu_dec(ovs_pcpu_storage.exec_level);
 		} else { /* Recirc action */
 			clone->recirc_id = recirc_id;
 			ovs_dp_process_packet(skb, clone);
@@ -1651,7 +1611,7 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
 
 static void process_deferred_actions(struct datapath *dp)
 {
-	struct action_fifo *fifo = this_cpu_ptr(action_fifos);
+	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage.action_fifos);
 
 	/* Do not touch the FIFO in case there is no deferred actions. */
 	if (action_fifo_is_empty(fifo))
@@ -1682,7 +1642,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 {
 	int err, level;
 
-	level = __this_cpu_inc_return(exec_actions_level);
+	level = __this_cpu_inc_return(ovs_pcpu_storage.exec_level);
 	if (unlikely(level > OVS_RECURSION_LIMIT)) {
 		net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n",
 				     ovs_dp_name(dp));
@@ -1699,27 +1659,6 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 		process_deferred_actions(dp);
 
 out:
-	__this_cpu_dec(exec_actions_level);
+	__this_cpu_dec(ovs_pcpu_storage.exec_level);
 	return err;
 }
-
-int action_fifos_init(void)
-{
-	action_fifos = alloc_percpu(struct action_fifo);
-	if (!action_fifos)
-		return -ENOMEM;
-
-	flow_keys = alloc_percpu(struct action_flow_keys);
-	if (!flow_keys) {
-		free_percpu(action_fifos);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-void action_fifos_exit(void)
-{
-	free_percpu(action_fifos);
-	free_percpu(flow_keys);
-}
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 5d548eda742d..6a304ae2d959 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -244,11 +244,13 @@ void ovs_dp_detach_port(struct vport *p)
 /* Must be called with rcu_read_lock. */
 void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 {
+	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(&ovs_pcpu_storage);
 	const struct vport *p = OVS_CB(skb)->input_vport;
 	struct datapath *dp = p->dp;
 	struct sw_flow *flow;
 	struct sw_flow_actions *sf_acts;
 	struct dp_stats_percpu *stats;
+	bool ovs_pcpu_locked = false;
 	u64 *stats_counter;
 	u32 n_mask_hit;
 	u32 n_cache_hit;
@@ -290,10 +292,26 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 
 	ovs_flow_stats_update(flow, key->tp.flags, skb);
 	sf_acts = rcu_dereference(flow->sf_acts);
+	/* This path can be invoked recursively: Use the current task to
+	 * identify recursive invocation - the lock must be acquired only once.
+	 * Even with disabled bottom halves this can be preempted on PREEMPT_RT.
+	 * Limit the locking to RT to avoid assigning `owner' if it can be
+	 * avoided.
+	 */
+	if (IS_ENABLED(CONFIG_PREEMPT_RT) && ovs_pcpu->owner != current) {
+		local_lock_nested_bh(&ovs_pcpu_storage.bh_lock);
+		ovs_pcpu->owner = current;
+		ovs_pcpu_locked = true;
+	}
+
 	error = ovs_execute_actions(dp, skb, sf_acts, key);
 	if (unlikely(error))
 		net_dbg_ratelimited("ovs: action execution error on datapath %s: %d\n",
 				    ovs_dp_name(dp), error);
+	if (ovs_pcpu_locked) {
+		ovs_pcpu->owner = NULL;
+		local_unlock_nested_bh(&ovs_pcpu_storage.bh_lock);
+	}
 
 	stats_counter = &stats->n_hit;
 
@@ -671,7 +689,13 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	sf_acts = rcu_dereference(flow->sf_acts);
 
 	local_bh_disable();
+	local_lock_nested_bh(&ovs_pcpu_storage.bh_lock);
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		this_cpu_write(ovs_pcpu_storage.owner, current);
 	err = ovs_execute_actions(dp, packet, sf_acts, &flow->key);
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		this_cpu_write(ovs_pcpu_storage.owner, NULL);
+	local_unlock_nested_bh(&ovs_pcpu_storage.bh_lock);
 	local_bh_enable();
 	rcu_read_unlock();
 
@@ -2729,13 +2753,9 @@ static int __init dp_init(void)
 
 	pr_info("Open vSwitch switching datapath\n");
 
-	err = action_fifos_init();
-	if (err)
-		goto error;
-
 	err = ovs_internal_dev_rtnl_link_register();
 	if (err)
-		goto error_action_fifos_exit;
+		goto error;
 
 	err = ovs_flow_init();
 	if (err)
@@ -2778,8 +2798,6 @@ error_flow_exit:
 	ovs_flow_exit();
 error_unreg_rtnl_link:
 	ovs_internal_dev_rtnl_link_unregister();
-error_action_fifos_exit:
-	action_fifos_exit();
 error:
 	return err;
 }
@@ -2795,7 +2813,6 @@ static void dp_cleanup(void)
 	ovs_vport_exit();
 	ovs_flow_exit();
 	ovs_internal_dev_rtnl_link_unregister();
-	action_fifos_exit();
 }
 
 module_init(dp_init);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 384ca77f4e79..1b5348b0f559 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -13,6 +13,7 @@
 #include <linux/skbuff.h>
 #include <linux/u64_stats_sync.h>
 #include <net/ip_tunnels.h>
+#include <net/mpls.h>
 
 #include "conntrack.h"
 #include "flow.h"
@@ -173,6 +174,54 @@ struct ovs_net {
 	bool xt_label;
 };
 
+#define MAX_L2_LEN	(VLAN_ETH_HLEN + 3 * MPLS_HLEN)
+struct ovs_frag_data {
+	unsigned long dst;
+	struct vport *vport;
+	struct ovs_skb_cb cb;
+	__be16 inner_protocol;
+	u16 network_offset;	/* valid only for MPLS */
+	u16 vlan_tci;
+	__be16 vlan_proto;
+	unsigned int l2_len;
+	u8 mac_proto;
+	u8 l2_data[MAX_L2_LEN];
+};
+
+struct deferred_action {
+	struct sk_buff *skb;
+	const struct nlattr *actions;
+	int actions_len;
+
+	/* Store pkt_key clone when creating deferred action. */
+	struct sw_flow_key pkt_key;
+};
+
+#define DEFERRED_ACTION_FIFO_SIZE 10
+#define OVS_RECURSION_LIMIT 5
+#define OVS_DEFERRED_ACTION_THRESHOLD (OVS_RECURSION_LIMIT - 2)
+
+struct action_fifo {
+	int head;
+	int tail;
+	/* Deferred action fifo queue storage. */
+	struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
+};
+
+struct action_flow_keys {
+	struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD];
+};
+
+struct ovs_pcpu_storage {
+	struct action_fifo action_fifos;
+	struct action_flow_keys flow_keys;
+	struct ovs_frag_data frag_data;
+	int exec_level;
+	struct task_struct *owner;
+	local_lock_t bh_lock;
+};
+DECLARE_PER_CPU(struct ovs_pcpu_storage, ovs_pcpu_storage);
+
 /**
  * enum ovs_pkt_hash_types - hash info to include with a packet
  * to send to userspace.
@@ -281,9 +330,6 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 void ovs_dp_notify_wq(struct work_struct *work);
 
-int action_fifos_init(void);
-void action_fifos_exit(void);
-
 /* 'KEY' must not have any bits set outside of the 'MASK' */
 #define OVS_MASKED(OLD, KEY, MASK) ((KEY) | ((OLD) & ~(MASK)))
 #define OVS_SET_MASKED(OLD, KEY, MASK) ((OLD) = OVS_MASKED(OLD, KEY, MASK))
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 95e0dd14dc1a..ad64bb9ab5e2 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2876,7 +2876,8 @@ static int validate_set(const struct nlattr *a,
 	size_t key_len;
 
 	/* There can be only one key in a action */
-	if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
+	if (!nla_ok(ovs_key, nla_len(a)) ||
+	    nla_total_size(nla_len(ovs_key)) != nla_len(a))
 		return -EINVAL;
 
 	key_len = nla_len(ovs_key);
@@ -3048,7 +3049,8 @@ static int validate_userspace(const struct nlattr *attr)
 	struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
 	int error;
 
-	error = nla_parse_nested_deprecated(a, OVS_USERSPACE_ATTR_MAX, attr,
+	error = nla_parse_deprecated_strict(a, OVS_USERSPACE_ATTR_MAX,
+					    nla_data(attr), nla_len(attr),
 					    userspace_policy, NULL);
 	if (error)
 		return error;
diff --git a/net/rds/page.c b/net/rds/page.c
index 7cc57e098ddb..afb151eac271 100644
--- a/net/rds/page.c
+++ b/net/rds/page.c
@@ -40,10 +40,12 @@
 struct rds_page_remainder {
 	struct page	*r_page;
 	unsigned long	r_offset;
+	local_lock_t	bh_lock;
 };
 
-static
-DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 /**
  * rds_page_remainder_alloc - build up regions of a message.
@@ -69,7 +71,6 @@ int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
 			     gfp_t gfp)
 {
 	struct rds_page_remainder *rem;
-	unsigned long flags;
 	struct page *page;
 	int ret;
 
@@ -87,8 +88,9 @@ int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
 		goto out;
 	}
 
-	rem = &per_cpu(rds_page_remainders, get_cpu());
-	local_irq_save(flags);
+	local_bh_disable();
+	local_lock_nested_bh(&rds_page_remainders.bh_lock);
+	rem = this_cpu_ptr(&rds_page_remainders);
 
 	while (1) {
 		/* avoid a tiny region getting stuck by tossing it */
@@ -116,13 +118,14 @@ int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
 		}
 
 		/* alloc if there is nothing for us to use */
-		local_irq_restore(flags);
-		put_cpu();
+		local_unlock_nested_bh(&rds_page_remainders.bh_lock);
+		local_bh_enable();
 
 		page = alloc_page(gfp);
 
-		rem = &per_cpu(rds_page_remainders, get_cpu());
-		local_irq_save(flags);
+		local_bh_disable();
+		local_lock_nested_bh(&rds_page_remainders.bh_lock);
+		rem = this_cpu_ptr(&rds_page_remainders);
 
 		if (!page) {
 			ret = -ENOMEM;
@@ -140,8 +143,8 @@ int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
 		rem->r_offset = 0;
 	}
 
-	local_irq_restore(flags);
-	put_cpu();
+	local_unlock_nested_bh(&rds_page_remainders.bh_lock);
+	local_bh_enable();
 out:
 	rdsdebug("bytes %lu ret %d %p %u %u\n", bytes, ret,
 		 ret ? NULL : sg_page(scat), ret ? 0 : scat->offset,
diff --git a/net/rxrpc/Kconfig b/net/rxrpc/Kconfig
index a20986806fea..f60b81c66078 100644
--- a/net/rxrpc/Kconfig
+++ b/net/rxrpc/Kconfig
@@ -67,6 +67,29 @@ config RXKAD
 
 	  See Documentation/networking/rxrpc.rst.
 
+config RXGK
+	bool "RxRPC GSSAPI security"
+	select CRYPTO_KRB5
+	select CRYPTO_MANAGER
+	select CRYPTO_KRB5ENC
+	select CRYPTO_AUTHENC
+	select CRYPTO_SKCIPHER
+	select CRYPTO_HASH_INFO
+	select CRYPTO_HMAC
+	select CRYPTO_CMAC
+	select CRYPTO_SHA1
+	select CRYPTO_SHA256
+	select CRYPTO_SHA512
+	select CRYPTO_CBC
+	select CRYPTO_CTS
+	select CRYPTO_AES
+	select CRYPTO_CAMELLIA
+	help
+	  Provide the GSSAPI-based RxGK security class for AFS.  Keys are added
+	  with add_key().
+
+	  See Documentation/networking/rxrpc.rst.
+
 config RXPERF
 	tristate "RxRPC test service"
 	help
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile
index 210b75e3179e..c0542bae719e 100644
--- a/net/rxrpc/Makefile
+++ b/net/rxrpc/Makefile
@@ -24,6 +24,7 @@ rxrpc-y := \
 	local_object.o \
 	misc.o \
 	net_ns.o \
+	oob.o \
 	output.o \
 	peer_event.o \
 	peer_object.o \
@@ -39,6 +40,9 @@ rxrpc-y := \
 rxrpc-$(CONFIG_PROC_FS) += proc.o
 rxrpc-$(CONFIG_RXKAD) += rxkad.o
 rxrpc-$(CONFIG_SYSCTL) += sysctl.o
-
+rxrpc-$(CONFIG_RXGK) += \
+	rxgk.o \
+	rxgk_app.o \
+	rxgk_kdf.o
 
 obj-$(CONFIG_RXPERF) += rxperf.o
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 86873399f7d5..36df0274d7b7 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -265,7 +265,10 @@ static int rxrpc_listen(struct socket *sock, int backlog)
  * @gfp: Allocation flags
  *
  * Lookup or create a remote transport endpoint record for the specified
- * address and return it with a ref held.
+ * address.
+ *
+ * Return: The peer record found with a reference, %NULL if no record is found
+ * or a negative error code if the address is invalid or unsupported.
  */
 struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock,
 					    struct sockaddr_rxrpc *srx, gfp_t gfp)
@@ -283,9 +286,11 @@ EXPORT_SYMBOL(rxrpc_kernel_lookup_peer);
 
 /**
  * rxrpc_kernel_get_peer - Get a reference on a peer
- * @peer: The peer to get a reference on.
+ * @peer: The peer to get a reference on (may be NULL).
+ *
+ * Get a reference for a remote peer record (if not NULL).
  *
- * Get a record for the remote peer in a call.
+ * Return: The @peer argument.
  */
 struct rxrpc_peer *rxrpc_kernel_get_peer(struct rxrpc_peer *peer)
 {
@@ -296,6 +301,8 @@ EXPORT_SYMBOL(rxrpc_kernel_get_peer);
 /**
  * rxrpc_kernel_put_peer - Allow a kernel app to drop a peer reference
  * @peer: The peer to drop a ref on
+ *
+ * Drop a reference on a peer record.
  */
 void rxrpc_kernel_put_peer(struct rxrpc_peer *peer)
 {
@@ -320,10 +327,12 @@ EXPORT_SYMBOL(rxrpc_kernel_put_peer);
  *
  * Allow a kernel service to begin a call on the nominated socket.  This just
  * sets up all the internal tracking structures and allocates connection and
- * call IDs as appropriate.  The call to be used is returned.
+ * call IDs as appropriate.
  *
  * The default socket destination address and security may be overridden by
  * supplying @srx and @key.
+ *
+ * Return: The new call or an error code.
  */
 struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 					   struct rxrpc_peer *peer,
@@ -437,6 +446,8 @@ EXPORT_SYMBOL(rxrpc_kernel_put_call);
  *
  * Allow a kernel service to find out whether a call is still alive - whether
  * it has completed successfully and all received data has been consumed.
+ *
+ * Return: %true if the call is still ongoing and %false if it has completed.
  */
 bool rxrpc_kernel_check_life(const struct socket *sock,
 			     const struct rxrpc_call *call)
@@ -450,63 +461,20 @@ bool rxrpc_kernel_check_life(const struct socket *sock,
 EXPORT_SYMBOL(rxrpc_kernel_check_life);
 
 /**
- * rxrpc_kernel_get_epoch - Retrieve the epoch value from a call.
- * @sock: The socket the call is on
- * @call: The call to query
- *
- * Allow a kernel service to retrieve the epoch value from a service call to
- * see if the client at the other end rebooted.
- */
-u32 rxrpc_kernel_get_epoch(struct socket *sock, struct rxrpc_call *call)
-{
-	return call->conn->proto.epoch;
-}
-EXPORT_SYMBOL(rxrpc_kernel_get_epoch);
-
-/**
- * rxrpc_kernel_new_call_notification - Get notifications of new calls
- * @sock: The socket to intercept received messages on
- * @notify_new_call: Function to be called when new calls appear
- * @discard_new_call: Function to discard preallocated calls
+ * rxrpc_kernel_set_notifications - Set table of callback operations
+ * @sock: The socket to install table upon
+ * @app_ops: Callback operation table to set
  *
- * Allow a kernel service to be given notifications about new calls.
+ * Allow a kernel service to set a table of event notifications on a socket.
  */
-void rxrpc_kernel_new_call_notification(
-	struct socket *sock,
-	rxrpc_notify_new_call_t notify_new_call,
-	rxrpc_discard_new_call_t discard_new_call)
+void rxrpc_kernel_set_notifications(struct socket *sock,
+				    const struct rxrpc_kernel_ops *app_ops)
 {
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 
-	rx->notify_new_call = notify_new_call;
-	rx->discard_new_call = discard_new_call;
+	rx->app_ops = app_ops;
 }
-EXPORT_SYMBOL(rxrpc_kernel_new_call_notification);
-
-/**
- * rxrpc_kernel_set_max_life - Set maximum lifespan on a call
- * @sock: The socket the call is on
- * @call: The call to configure
- * @hard_timeout: The maximum lifespan of the call in ms
- *
- * Set the maximum lifespan of a call.  The call will end with ETIME or
- * ETIMEDOUT if it takes longer than this.
- */
-void rxrpc_kernel_set_max_life(struct socket *sock, struct rxrpc_call *call,
-			       unsigned long hard_timeout)
-{
-	ktime_t delay = ms_to_ktime(hard_timeout), expect_term_by;
-
-	mutex_lock(&call->user_mutex);
-
-	expect_term_by = ktime_add(ktime_get_real(), delay);
-	WRITE_ONCE(call->expect_term_by, expect_term_by);
-	trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard);
-	rxrpc_poke_call(call, rxrpc_call_poke_set_timeout);
-
-	mutex_unlock(&call->user_mutex);
-}
-EXPORT_SYMBOL(rxrpc_kernel_set_max_life);
+EXPORT_SYMBOL(rxrpc_kernel_set_notifications);
 
 /*
  * connect an RxRPC socket
@@ -624,7 +592,10 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 		fallthrough;
 	case RXRPC_SERVER_BOUND:
 	case RXRPC_SERVER_LISTENING:
-		ret = rxrpc_do_sendmsg(rx, m, len);
+		if (m->msg_flags & MSG_OOB)
+			ret = rxrpc_sendmsg_oob(rx, m, len);
+		else
+			ret = rxrpc_do_sendmsg(rx, m, len);
 		/* The socket has been unlocked */
 		goto out;
 	default:
@@ -659,7 +630,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			    sockptr_t optval, unsigned int optlen)
 {
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
-	unsigned int min_sec_level;
+	unsigned int min_sec_level, val;
 	u16 service_upgrade[2];
 	int ret;
 
@@ -740,6 +711,26 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			rx->service_upgrade.to = service_upgrade[1];
 			goto success;
 
+		case RXRPC_MANAGE_RESPONSE:
+			ret = -EINVAL;
+			if (optlen != sizeof(unsigned int))
+				goto error;
+			ret = -EISCONN;
+			if (rx->sk.sk_state != RXRPC_UNBOUND)
+				goto error;
+			ret = copy_safe_from_sockptr(&val, sizeof(val),
+						     optval, optlen);
+			if (ret)
+				goto error;
+			ret = -EINVAL;
+			if (val > 1)
+				goto error;
+			if (val)
+				set_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags);
+			else
+				clear_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags);
+			goto success;
+
 		default:
 			break;
 		}
@@ -846,6 +837,8 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol,
 	rx->calls = RB_ROOT;
 
 	spin_lock_init(&rx->incoming_lock);
+	skb_queue_head_init(&rx->recvmsg_oobq);
+	rx->pending_oobq = RB_ROOT;
 	INIT_LIST_HEAD(&rx->sock_calls);
 	INIT_LIST_HEAD(&rx->to_be_accepted);
 	INIT_LIST_HEAD(&rx->recvmsg_q);
@@ -879,8 +872,10 @@ static int rxrpc_shutdown(struct socket *sock, int flags)
 	lock_sock(sk);
 
 	if (sk->sk_state < RXRPC_CLOSE) {
+		spin_lock_irq(&rx->recvmsg_lock);
 		sk->sk_state = RXRPC_CLOSE;
 		sk->sk_shutdown = SHUTDOWN_MASK;
+		spin_unlock_irq(&rx->recvmsg_lock);
 	} else {
 		ret = -ESHUTDOWN;
 	}
@@ -892,12 +887,30 @@ static int rxrpc_shutdown(struct socket *sock, int flags)
 }
 
 /*
+ * Purge the out-of-band queue.
+ */
+static void rxrpc_purge_oob_queue(struct sock *sk)
+{
+	struct rxrpc_sock *rx = rxrpc_sk(sk);
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(&rx->recvmsg_oobq)))
+		rxrpc_kernel_free_oob(skb);
+	while (!RB_EMPTY_ROOT(&rx->pending_oobq)) {
+		skb = rb_entry(rx->pending_oobq.rb_node, struct sk_buff, rbnode);
+		rb_erase(&skb->rbnode, &rx->pending_oobq);
+		rxrpc_kernel_free_oob(skb);
+	}
+}
+
+/*
  * RxRPC socket destructor
  */
 static void rxrpc_sock_destructor(struct sock *sk)
 {
 	_enter("%p", sk);
 
+	rxrpc_purge_oob_queue(sk);
 	rxrpc_purge_queue(&sk->sk_receive_queue);
 
 	WARN_ON(refcount_read(&sk->sk_wmem_alloc));
@@ -936,7 +949,9 @@ static int rxrpc_release_sock(struct sock *sk)
 		break;
 	}
 
+	spin_lock_irq(&rx->recvmsg_lock);
 	sk->sk_state = RXRPC_CLOSE;
+	spin_unlock_irq(&rx->recvmsg_lock);
 
 	if (rx->local && rx->local->service == rx) {
 		write_lock(&rx->local->services_lock);
@@ -948,6 +963,7 @@ static int rxrpc_release_sock(struct sock *sk)
 	rxrpc_discard_prealloc(rx);
 	rxrpc_release_calls_on_socket(rx);
 	flush_workqueue(rxrpc_workqueue);
+	rxrpc_purge_oob_queue(sk);
 	rxrpc_purge_queue(&sk->sk_receive_queue);
 
 	rxrpc_unuse_local(rx->local, rxrpc_local_unuse_release_sock);
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 3cc3af15086f..5bd3922c310d 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -31,6 +31,7 @@ struct key_preparsed_payload;
 struct rxrpc_connection;
 struct rxrpc_txbuf;
 struct rxrpc_txqueue;
+struct rxgk_context;
 
 /*
  * Mark applied to socket buffers in skb->mark.  skb->priority is used
@@ -39,6 +40,7 @@ struct rxrpc_txqueue;
 enum rxrpc_skb_mark {
 	RXRPC_SKB_MARK_PACKET,		/* Received packet */
 	RXRPC_SKB_MARK_ERROR,		/* Error notification */
+	RXRPC_SKB_MARK_CHALLENGE,	/* Challenge notification */
 	RXRPC_SKB_MARK_SERVICE_CONN_SECURED, /* Service connection response has been verified */
 	RXRPC_SKB_MARK_REJECT_BUSY,	/* Reject with BUSY */
 	RXRPC_SKB_MARK_REJECT_ABORT,	/* Reject with ABORT (code in skb->priority) */
@@ -146,10 +148,12 @@ struct rxrpc_backlog {
 struct rxrpc_sock {
 	/* WARNING: sk has to be the first member */
 	struct sock		sk;
-	rxrpc_notify_new_call_t	notify_new_call; /* Func to notify of new call */
-	rxrpc_discard_new_call_t discard_new_call; /* Func to discard a new call */
+	const struct rxrpc_kernel_ops *app_ops;	/* Table of kernel app notification funcs */
 	struct rxrpc_local	*local;		/* local endpoint */
 	struct rxrpc_backlog	*backlog;	/* Preallocation for services */
+	struct sk_buff_head	recvmsg_oobq;	/* OOB messages for recvmsg to pick up */
+	struct rb_root		pending_oobq;	/* OOB messages awaiting userspace to respond to */
+	u64			oob_id_counter;	/* OOB message ID counter */
 	spinlock_t		incoming_lock;	/* Incoming call vs service shutdown lock */
 	struct list_head	sock_calls;	/* List of calls owned by this socket */
 	struct list_head	to_be_accepted;	/* calls awaiting acceptance */
@@ -160,6 +164,7 @@ struct rxrpc_sock {
 	struct rb_root		calls;		/* User ID -> call mapping */
 	unsigned long		flags;
 #define RXRPC_SOCK_CONNECTED		0	/* connect_srx is set */
+#define RXRPC_SOCK_MANAGE_RESPONSE	1	/* User wants to manage RESPONSE packets */
 	rwlock_t		call_lock;	/* lock for calls */
 	u32			min_sec_level;	/* minimum security level */
 #define RXRPC_SECURITY_MAX	RXRPC_SECURITY_ENCRYPT
@@ -203,7 +208,7 @@ struct rxrpc_host_header {
  */
 struct rxrpc_skb_priv {
 	union {
-		struct rxrpc_connection *conn;	/* Connection referred to (poke packet) */
+		struct rxrpc_connection *poke_conn;	/* Conn referred to (poke packet) */
 		struct {
 			u16		offset;		/* Offset of data */
 			u16		len;		/* Length of data */
@@ -217,6 +222,19 @@ struct rxrpc_skb_priv {
 			u16		nr_acks;	/* Number of acks+nacks */
 			u8		reason;		/* Reason for ack */
 		} ack;
+		struct {
+			struct rxrpc_connection *conn;	/* Connection referred to */
+			union {
+				u32 rxkad_nonce;
+			};
+		} chall;
+		struct {
+			rxrpc_serial_t	challenge_serial;
+			u32		kvno;
+			u32		version;
+			u16		len;
+			u16		ticket_len;
+		} resp;
 	};
 	struct rxrpc_host_header hdr;	/* RxRPC packet header from this packet */
 };
@@ -270,9 +288,24 @@ struct rxrpc_security {
 	/* issue a challenge */
 	int (*issue_challenge)(struct rxrpc_connection *);
 
+	/* Validate a challenge packet */
+	bool (*validate_challenge)(struct rxrpc_connection *conn,
+				   struct sk_buff *skb);
+
+	/* Fill out the cmsg for recvmsg() to pass on a challenge to userspace.
+	 * The security class gets to add additional information.
+	 */
+	int (*challenge_to_recvmsg)(struct rxrpc_connection *conn,
+				    struct sk_buff *challenge,
+				    struct msghdr *msg);
+
+	/* Parse sendmsg() control message and respond to challenge. */
+	int (*sendmsg_respond_to_challenge)(struct sk_buff *challenge,
+					    struct msghdr *msg);
+
 	/* respond to a challenge */
-	int (*respond_to_challenge)(struct rxrpc_connection *,
-				    struct sk_buff *);
+	int (*respond_to_challenge)(struct rxrpc_connection *conn,
+				    struct sk_buff *challenge);
 
 	/* verify a response */
 	int (*verify_response)(struct rxrpc_connection *,
@@ -280,6 +313,11 @@ struct rxrpc_security {
 
 	/* clear connection security */
 	void (*clear)(struct rxrpc_connection *);
+
+	/* Default ticket -> key decoder */
+	int (*default_decode_ticket)(struct rxrpc_connection *conn, struct sk_buff *skb,
+				     unsigned int ticket_offset, unsigned int ticket_len,
+				     struct key **_key);
 };
 
 /*
@@ -526,7 +564,17 @@ struct rxrpc_connection {
 			struct rxrpc_crypt csum_iv;	/* packet checksum base */
 			u32	nonce;		/* response re-use preventer */
 		} rxkad;
+		struct {
+			struct rxgk_context *keys[4]; /* (Re-)keying buffer */
+			u64	start_time;	/* The start time for TK derivation */
+			u8	nonce[20];	/* Response re-use preventer */
+			u32	enctype;	/* Kerberos 5 encoding type */
+			u32	key_number;	/* Current key number */
+		} rxgk;
 	};
+	rwlock_t		security_use_lock; /* Security use/modification lock */
+	struct sk_buff		*tx_response;	/* Response packet to be transmitted */
+
 	unsigned long		flags;
 	unsigned long		events;
 	unsigned long		idle_timestamp;	/* Time at which last became idle */
@@ -692,6 +740,7 @@ struct rxrpc_call {
 	u32			call_id;	/* call ID on connection  */
 	u32			cid;		/* connection ID plus channel index */
 	u32			security_level;	/* Security level selected */
+	u32			security_enctype; /* Security-specific encoding type (or 0) */
 	int			debug_id;	/* debug ID for printks */
 	unsigned short		rx_pkt_offset;	/* Current recvmsg packet offset */
 	unsigned short		rx_pkt_len;	/* Current recvmsg packet len */
@@ -867,6 +916,8 @@ struct rxrpc_txbuf {
 	unsigned short		len;		/* Amount of data in buffer */
 	unsigned short		space;		/* Remaining data space */
 	unsigned short		offset;		/* Offset of fill point */
+	unsigned short		crypto_header;	/* Size of crypto header */
+	unsigned short		sec_header;	/* Size of security header */
 	unsigned short		pkt_len;	/* Size of packet content */
 	unsigned short		alloc_size;	/* Amount of bufferage allocated */
 	unsigned int		flags;
@@ -1001,7 +1052,9 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t, unsigned int);
 struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *,
 					 struct rxrpc_conn_parameters *,
 					 struct rxrpc_call_params *, gfp_t,
-					 unsigned int);
+					 unsigned int)
+	__releases(&rx->sk.sk_lock)
+	__acquires(&call->user_mutex);
 void rxrpc_start_call_timer(struct rxrpc_call *call);
 void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *,
 			 struct sk_buff *);
@@ -1198,8 +1251,11 @@ void rxrpc_error_report(struct sock *);
 bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why,
 			s32 abort_code, int err);
 int rxrpc_io_thread(void *data);
+void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb);
 static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local)
 {
+	if (!local->io_thread)
+		return;
 	wake_up_process(READ_ONCE(local->io_thread));
 }
 
@@ -1289,8 +1345,16 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net)
 }
 
 /*
+ * out_of_band.c
+ */
+void rxrpc_notify_socket_oob(struct rxrpc_call *call, struct sk_buff *skb);
+void rxrpc_add_pending_oob(struct rxrpc_sock *rx, struct sk_buff *skb);
+int rxrpc_sendmsg_oob(struct rxrpc_sock *rx, struct msghdr *msg, size_t len);
+
+/*
  * output.c
  */
+ssize_t do_udp_sendmsg(struct socket *socket, struct msghdr *msg, size_t len);
 void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason,
 		    rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why);
 void rxrpc_send_probe_for_pmtud(struct rxrpc_call *call);
@@ -1299,6 +1363,7 @@ void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req
 void rxrpc_send_conn_abort(struct rxrpc_connection *conn);
 void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb);
 void rxrpc_send_keepalive(struct rxrpc_peer *);
+void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *skb);
 
 /*
  * peer_event.c
@@ -1363,6 +1428,11 @@ ktime_t rxrpc_get_rto_backoff(struct rxrpc_call *call, bool retrans);
 void rxrpc_call_init_rtt(struct rxrpc_call *call);
 
 /*
+ * rxgk.c
+ */
+extern const struct rxrpc_security rxgk_yfs;
+
+/*
  * rxkad.c
  */
 #ifdef CONFIG_RXKAD
@@ -1433,7 +1503,6 @@ static inline void rxrpc_sysctl_exit(void) {}
 extern atomic_t rxrpc_nr_txbuf;
 struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_size,
 					   size_t data_align, gfp_t gfp);
-void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what);
 void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what);
 void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what);
 
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index e685034ce4f7..a4b363b47cca 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -34,7 +34,6 @@ static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call,
 static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 				      struct rxrpc_backlog *b,
 				      rxrpc_notify_rx_t notify_rx,
-				      rxrpc_user_attach_call_t user_attach_call,
 				      unsigned long user_call_ID, gfp_t gfp,
 				      unsigned int debug_id)
 {
@@ -123,9 +122,10 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 
 	call->user_call_ID = user_call_ID;
 	call->notify_rx = notify_rx;
-	if (user_attach_call) {
+	if (rx->app_ops &&
+	    rx->app_ops->user_attach_call) {
 		rxrpc_get_call(call, rxrpc_call_get_kernel_service);
-		user_attach_call(call, user_call_ID);
+		rx->app_ops->user_attach_call(call, user_call_ID);
 	}
 
 	rxrpc_get_call(call, rxrpc_call_get_userid);
@@ -219,9 +219,10 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
 	while (CIRC_CNT(head, tail, size) > 0) {
 		struct rxrpc_call *call = b->call_backlog[tail];
 		rcu_assign_pointer(call->socket, rx);
-		if (rx->discard_new_call) {
+		if (rx->app_ops &&
+		    rx->app_ops->discard_new_call) {
 			_debug("discard %lx", call->user_call_ID);
-			rx->discard_new_call(call, call->user_call_ID);
+			rx->app_ops->discard_new_call(call, call->user_call_ID);
 			if (call->notify_rx)
 				call->notify_rx = rxrpc_dummy_notify;
 			rxrpc_put_call(call, rxrpc_call_put_kernel);
@@ -387,8 +388,9 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local,
 	rxrpc_incoming_call(rx, call, skb);
 	conn = call->conn;
 
-	if (rx->notify_new_call)
-		rx->notify_new_call(&rx->sk, call, call->user_call_ID);
+	if (rx->app_ops &&
+	    rx->app_ops->notify_new_call)
+		rx->app_ops->notify_new_call(&rx->sk, call, call->user_call_ID);
 
 	spin_lock(&conn->state_lock);
 	if (conn->state == RXRPC_CONN_SERVICE_UNSECURED) {
@@ -440,8 +442,7 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *rx, unsigned long user_call_ID)
 	if (rx->sk.sk_state == RXRPC_CLOSE)
 		return -ESHUTDOWN;
 
-	return rxrpc_service_prealloc_one(rx, b, NULL, NULL, user_call_ID,
-					  GFP_KERNEL,
+	return rxrpc_service_prealloc_one(rx, b, NULL, user_call_ID, GFP_KERNEL,
 					  atomic_inc_return(&rxrpc_debug_id));
 }
 
@@ -449,20 +450,18 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *rx, unsigned long user_call_ID)
  * rxrpc_kernel_charge_accept - Charge up socket with preallocated calls
  * @sock: The socket on which to preallocate
  * @notify_rx: Event notification function for the call
- * @user_attach_call: Func to attach call to user_call_ID
  * @user_call_ID: The tag to attach to the preallocated call
  * @gfp: The allocation conditions.
  * @debug_id: The tracing debug ID.
  *
- * Charge up the socket with preallocated calls, each with a user ID.  A
- * function should be provided to effect the attachment from the user's side.
- * The user is given a ref to hold on the call.
+ * Charge up the socket with preallocated calls, each with a user ID.  The
+ * ->user_attach_call() callback function should be provided to effect the
+ * attachment from the user's side.  The user is given a ref to hold on the
+ * call.
  *
  * Note that the call may be come connected before this function returns.
  */
-int rxrpc_kernel_charge_accept(struct socket *sock,
-			       rxrpc_notify_rx_t notify_rx,
-			       rxrpc_user_attach_call_t user_attach_call,
+int rxrpc_kernel_charge_accept(struct socket *sock, rxrpc_notify_rx_t notify_rx,
 			       unsigned long user_call_ID, gfp_t gfp,
 			       unsigned int debug_id)
 {
@@ -472,8 +471,7 @@ int rxrpc_kernel_charge_accept(struct socket *sock,
 	if (sock->sk->sk_state == RXRPC_CLOSE)
 		return -ESHUTDOWN;
 
-	return rxrpc_service_prealloc_one(rx, b, notify_rx,
-					  user_attach_call, user_call_ID,
+	return rxrpc_service_prealloc_one(rx, b, notify_rx, user_call_ID,
 					  gfp, debug_id);
 }
 EXPORT_SYMBOL(rxrpc_kernel_charge_accept);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index fce58be65e7c..e9e8f0ef3fd5 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -145,8 +145,8 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
 	INIT_LIST_HEAD(&call->recvmsg_link);
 	INIT_LIST_HEAD(&call->sock_link);
 	INIT_LIST_HEAD(&call->attend_link);
-	skb_queue_head_init(&call->rx_queue);
 	skb_queue_head_init(&call->recvmsg_queue);
+	skb_queue_head_init(&call->rx_queue);
 	skb_queue_head_init(&call->rx_oos_queue);
 	init_waitqueue_head(&call->waitq);
 	spin_lock_init(&call->notify_lock);
@@ -322,7 +322,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 					 struct rxrpc_call_params *p,
 					 gfp_t gfp,
 					 unsigned int debug_id)
-	__releases(&rx->sk.sk_lock.slock)
+	__releases(&rx->sk.sk_lock)
 	__acquires(&call->user_mutex)
 {
 	struct rxrpc_call *call, *xcall;
@@ -760,3 +760,23 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
 	atomic_dec(&rxnet->nr_calls);
 	wait_var_event(&rxnet->nr_calls, !atomic_read(&rxnet->nr_calls));
 }
+
+/**
+ * rxrpc_kernel_query_call_security - Query call's security parameters
+ * @call: The call to query
+ * @_service_id: Where to return the service ID
+ * @_enctype: Where to return the "encoding type"
+ *
+ * This queries the security parameters of a call, setting *@_service_id and
+ * *@_enctype and returning the security class.
+ *
+ * Return: The security class protocol number.
+ */
+u8 rxrpc_kernel_query_call_security(struct rxrpc_call *call,
+				    u16 *_service_id, u32 *_enctype)
+{
+	*_service_id = call->dest_srx.srx_service;
+	*_enctype = call->security_enctype;
+	return call->security_ix;
+}
+EXPORT_SYMBOL(rxrpc_kernel_query_call_security);
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 4d9c5e21ba78..232b6986da83 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -19,7 +19,7 @@
 /*
  * Set the completion state on an aborted connection.
  */
-static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff *skb,
+static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn,
 				   s32 abort_code, int err,
 				   enum rxrpc_call_completion compl)
 {
@@ -49,12 +49,20 @@ static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff
 int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb,
 		     s32 abort_code, int err, enum rxrpc_abort_reason why)
 {
-	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 
-	if (rxrpc_set_conn_aborted(conn, skb, abort_code, err,
+	u32 cid = conn->proto.cid, call = 0, seq = 0;
+
+	if (skb) {
+		struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+		cid  = sp->hdr.cid;
+		call = sp->hdr.callNumber;
+		seq  = sp->hdr.seq;
+	}
+
+	if (rxrpc_set_conn_aborted(conn, abort_code, err,
 				   RXRPC_CALL_LOCALLY_ABORTED)) {
-		trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber,
-				  sp->hdr.seq, abort_code, err);
+		trace_rxrpc_abort(0, why, cid, call, seq, abort_code, err);
 		rxrpc_poke_conn(conn, rxrpc_conn_get_poke_abort);
 	}
 	return -EPROTO;
@@ -67,7 +75,7 @@ static void rxrpc_input_conn_abort(struct rxrpc_connection *conn,
 				   struct sk_buff *skb)
 {
 	trace_rxrpc_rx_conn_abort(conn, skb);
-	rxrpc_set_conn_aborted(conn, skb, skb->priority, -ECONNABORTED,
+	rxrpc_set_conn_aborted(conn, skb->priority, -ECONNABORTED,
 			       RXRPC_CALL_REMOTELY_ABORTED);
 }
 
@@ -248,7 +256,10 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 
 	switch (sp->hdr.type) {
 	case RXRPC_PACKET_TYPE_CHALLENGE:
-		return conn->security->respond_to_challenge(conn, skb);
+		ret = conn->security->respond_to_challenge(conn, skb);
+		sp->chall.conn = NULL;
+		rxrpc_put_connection(conn, rxrpc_conn_put_challenge_input);
+		return ret;
 
 	case RXRPC_PACKET_TYPE_RESPONSE:
 		ret = conn->security->verify_response(conn, skb);
@@ -270,7 +281,8 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 			 * we've already received the packet, put it on the
 			 * front of the queue.
 			 */
-			sp->conn = rxrpc_get_connection(conn, rxrpc_conn_get_poke_secured);
+			sp->poke_conn = rxrpc_get_connection(
+				conn, rxrpc_conn_get_poke_secured);
 			skb->mark = RXRPC_SKB_MARK_SERVICE_CONN_SECURED;
 			rxrpc_get_skb(skb, rxrpc_skb_get_conn_secured);
 			skb_queue_head(&conn->local->rx_queue, skb);
@@ -392,6 +404,61 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn,
 }
 
 /*
+ * Post a CHALLENGE packet to the socket of one of a connection's calls so that
+ * it can get application data to include in the packet, possibly querying
+ * userspace.
+ */
+static bool rxrpc_post_challenge(struct rxrpc_connection *conn,
+				 struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rxrpc_call *call = NULL;
+	struct rxrpc_sock *rx;
+	bool respond = false;
+
+	sp->chall.conn =
+		rxrpc_get_connection(conn, rxrpc_conn_get_challenge_input);
+
+	if (!conn->security->challenge_to_recvmsg) {
+		rxrpc_post_packet_to_conn(conn, skb);
+		return true;
+	}
+
+	rcu_read_lock();
+
+	for (int i = 0; i < ARRAY_SIZE(conn->channels); i++) {
+		if (conn->channels[i].call) {
+			call = conn->channels[i].call;
+			rx = rcu_dereference(call->socket);
+			if (!rx) {
+				call = NULL;
+				continue;
+			}
+
+			respond = true;
+			if (test_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags))
+				break;
+			call = NULL;
+		}
+	}
+
+	if (!respond) {
+		rcu_read_unlock();
+		rxrpc_put_connection(conn, rxrpc_conn_put_challenge_input);
+		sp->chall.conn = NULL;
+		return false;
+	}
+
+	if (call)
+		rxrpc_notify_socket_oob(call, skb);
+	rcu_read_unlock();
+
+	if (!call)
+		rxrpc_post_packet_to_conn(conn, skb);
+	return true;
+}
+
+/*
  * Input a connection-level packet.
  */
 bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
@@ -411,6 +478,16 @@ bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
 		return true;
 
 	case RXRPC_PACKET_TYPE_CHALLENGE:
+		rxrpc_see_skb(skb, rxrpc_skb_see_oob_challenge);
+		if (rxrpc_is_conn_aborted(conn)) {
+			if (conn->completion == RXRPC_CALL_LOCALLY_ABORTED)
+				rxrpc_send_conn_abort(conn);
+			return true;
+		}
+		if (!conn->security->validate_challenge(conn, skb))
+			return false;
+		return rxrpc_post_challenge(conn, skb);
+
 	case RXRPC_PACKET_TYPE_RESPONSE:
 		if (rxrpc_is_conn_aborted(conn)) {
 			if (conn->completion == RXRPC_CALL_LOCALLY_ABORTED)
@@ -436,6 +513,19 @@ void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb)
 	if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events))
 		rxrpc_abort_calls(conn);
 
+	if (conn->tx_response) {
+		struct sk_buff *skb;
+
+		spin_lock_irq(&conn->local->lock);
+		skb = conn->tx_response;
+		conn->tx_response = NULL;
+		spin_unlock_irq(&conn->local->lock);
+
+		if (conn->state != RXRPC_CONN_ABORTED)
+			rxrpc_send_response(conn, skb);
+		rxrpc_free_skb(skb, rxrpc_skb_put_response);
+	}
+
 	if (skb) {
 		switch (skb->mark) {
 		case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
@@ -452,3 +542,31 @@ void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb)
 	if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
 		rxrpc_process_delayed_final_acks(conn, false);
 }
+
+/*
+ * Post a RESPONSE message to the I/O thread for transmission.
+ */
+void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rxrpc_local *local = conn->local;
+	struct sk_buff *old;
+
+	_enter("%x", sp->resp.challenge_serial);
+
+	spin_lock_irq(&local->lock);
+	old = conn->tx_response;
+	if (old) {
+		struct rxrpc_skb_priv *osp = rxrpc_skb(skb);
+
+		/* Always go with the response to the most recent challenge. */
+		if (after(sp->resp.challenge_serial, osp->resp.challenge_serial))
+			conn->tx_response = old;
+		else
+			old = skb;
+	} else {
+		conn->tx_response = skb;
+	}
+	spin_unlock_irq(&local->lock);
+	rxrpc_poke_conn(conn, rxrpc_conn_get_poke_response);
+}
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 8ac22dde8b39..37340becb224 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -73,6 +73,7 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet,
 		skb_queue_head_init(&conn->rx_queue);
 		conn->rxnet = rxnet;
 		conn->security = &rxrpc_no_security;
+		rwlock_init(&conn->security_use_lock);
 		spin_lock_init(&conn->state_lock);
 		conn->debug_id = atomic_inc_return(&rxrpc_debug_id);
 		conn->idle_timestamp = jiffies;
@@ -329,6 +330,7 @@ static void rxrpc_clean_up_connection(struct work_struct *work)
 	}
 
 	rxrpc_purge_queue(&conn->rx_queue);
+	rxrpc_free_skb(conn->tx_response, rxrpc_skb_put_response);
 
 	rxrpc_kill_client_conn(conn);
 
diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c
index e068f9b79d02..1f7c136d6d0e 100644
--- a/net/rxrpc/insecure.c
+++ b/net/rxrpc/insecure.c
@@ -42,13 +42,19 @@ static void none_free_call_crypto(struct rxrpc_call *call)
 {
 }
 
-static int none_respond_to_challenge(struct rxrpc_connection *conn,
-				     struct sk_buff *skb)
+static bool none_validate_challenge(struct rxrpc_connection *conn,
+				    struct sk_buff *skb)
 {
 	return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
 				rxrpc_eproto_rxnull_challenge);
 }
 
+static int none_sendmsg_respond_to_challenge(struct sk_buff *challenge,
+					     struct msghdr *msg)
+{
+	return -EINVAL;
+}
+
 static int none_verify_response(struct rxrpc_connection *conn,
 				struct sk_buff *skb)
 {
@@ -82,7 +88,8 @@ const struct rxrpc_security rxrpc_no_security = {
 	.alloc_txbuf			= none_alloc_txbuf,
 	.secure_packet			= none_secure_packet,
 	.verify_packet			= none_verify_packet,
-	.respond_to_challenge		= none_respond_to_challenge,
+	.validate_challenge		= none_validate_challenge,
+	.sendmsg_respond_to_challenge	= none_sendmsg_respond_to_challenge,
 	.verify_response		= none_verify_response,
 	.clear				= none_clear,
 };
diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c
index 64f8d77b8731..27b650d30f4d 100644
--- a/net/rxrpc/io_thread.c
+++ b/net/rxrpc/io_thread.c
@@ -489,8 +489,8 @@ int rxrpc_io_thread(void *data)
 				rxrpc_free_skb(skb, rxrpc_skb_put_error_report);
 				break;
 			case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
-				rxrpc_input_conn_event(sp->conn, skb);
-				rxrpc_put_connection(sp->conn, rxrpc_conn_put_poke);
+				rxrpc_input_conn_event(sp->poke_conn, skb);
+				rxrpc_put_connection(sp->poke_conn, rxrpc_conn_put_poke);
 				rxrpc_free_skb(skb, rxrpc_skb_put_conn_secured);
 				break;
 			default:
@@ -501,9 +501,11 @@ int rxrpc_io_thread(void *data)
 		}
 
 		/* Deal with connections that want immediate attention. */
-		spin_lock_irq(&local->lock);
-		list_splice_tail_init(&local->conn_attend_q, &conn_attend_q);
-		spin_unlock_irq(&local->lock);
+		if (!list_empty_careful(&local->conn_attend_q)) {
+			spin_lock_irq(&local->lock);
+			list_splice_tail_init(&local->conn_attend_q, &conn_attend_q);
+			spin_unlock_irq(&local->lock);
+		}
 
 		while ((conn = list_first_entry_or_null(&conn_attend_q,
 							struct rxrpc_connection,
diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 33e8302a79e3..9fdc1f031c9d 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -129,6 +129,160 @@ static int rxrpc_preparse_xdr_rxkad(struct key_preparsed_payload *prep,
 	return 0;
 }
 
+static u64 xdr_dec64(const __be32 *xdr)
+{
+	return (u64)ntohl(xdr[0]) << 32 | (u64)ntohl(xdr[1]);
+}
+
+static time64_t rxrpc_s64_to_time64(s64 time_in_100ns)
+{
+	bool neg = false;
+	u64 tmp = time_in_100ns;
+
+	if (time_in_100ns < 0) {
+		tmp = -time_in_100ns;
+		neg = true;
+	}
+	do_div(tmp, 10000000);
+	return neg ? -tmp : tmp;
+}
+
+/*
+ * Parse a YFS-RxGK type XDR format token
+ * - the caller guarantees we have at least 4 words
+ *
+ * struct token_rxgk {
+ *	opr_time begintime;
+ *	opr_time endtime;
+ *	afs_int64 level;
+ *	afs_int64 lifetime;
+ *	afs_int64 bytelife;
+ *	afs_int64 enctype;
+ *	opaque key<>;
+ *	opaque ticket<>;
+ * };
+ */
+static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep,
+				       size_t datalen,
+				       const __be32 *xdr, unsigned int toklen)
+{
+	struct rxrpc_key_token *token, **pptoken;
+	time64_t expiry;
+	size_t plen;
+	const __be32 *ticket, *key;
+	s64 tmp;
+	u32 tktlen, keylen;
+
+	_enter(",{%x,%x,%x,%x},%x",
+	       ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]),
+	       toklen);
+
+	if (6 * 2 + 2 > toklen / 4)
+		goto reject;
+
+	key = xdr + (6 * 2 + 1);
+	keylen = ntohl(key[-1]);
+	_debug("keylen: %x", keylen);
+	keylen = round_up(keylen, 4);
+	if ((6 * 2 + 2) * 4 + keylen > toklen)
+		goto reject;
+
+	ticket = xdr + (6 * 2 + 1 + (keylen / 4) + 1);
+	tktlen = ntohl(ticket[-1]);
+	_debug("tktlen: %x", tktlen);
+	tktlen = round_up(tktlen, 4);
+	if ((6 * 2 + 2) * 4 + keylen + tktlen != toklen) {
+		kleave(" = -EKEYREJECTED [%x!=%x, %x,%x]",
+		       (6 * 2 + 2) * 4 + keylen + tktlen, toklen,
+		       keylen, tktlen);
+		goto reject;
+	}
+
+	plen = sizeof(*token) + sizeof(*token->rxgk) + tktlen + keylen;
+	prep->quotalen = datalen + plen;
+
+	plen -= sizeof(*token);
+	token = kzalloc(sizeof(*token), GFP_KERNEL);
+	if (!token)
+		goto nomem;
+
+	token->rxgk = kzalloc(sizeof(*token->rxgk) + keylen, GFP_KERNEL);
+	if (!token->rxgk)
+		goto nomem_token;
+
+	token->security_index	= RXRPC_SECURITY_YFS_RXGK;
+	token->rxgk->begintime	= xdr_dec64(xdr + 0 * 2);
+	token->rxgk->endtime	= xdr_dec64(xdr + 1 * 2);
+	token->rxgk->level	= tmp = xdr_dec64(xdr + 2 * 2);
+	if (tmp < -1LL || tmp > RXRPC_SECURITY_ENCRYPT)
+		goto reject_token;
+	token->rxgk->lifetime	= xdr_dec64(xdr + 3 * 2);
+	token->rxgk->bytelife	= xdr_dec64(xdr + 4 * 2);
+	token->rxgk->enctype	= tmp = xdr_dec64(xdr + 5 * 2);
+	if (tmp < 0 || tmp > UINT_MAX)
+		goto reject_token;
+	token->rxgk->key.len	= ntohl(key[-1]);
+	token->rxgk->key.data	= token->rxgk->_key;
+	token->rxgk->ticket.len = ntohl(ticket[-1]);
+
+	if (token->rxgk->endtime != 0) {
+		expiry = rxrpc_s64_to_time64(token->rxgk->endtime);
+		if (expiry < 0)
+			goto expired;
+		if (expiry < prep->expiry)
+			prep->expiry = expiry;
+	}
+
+	memcpy(token->rxgk->key.data, key, token->rxgk->key.len);
+
+	/* Pad the ticket so that we can use it directly in XDR */
+	token->rxgk->ticket.data = kzalloc(round_up(token->rxgk->ticket.len, 4),
+					   GFP_KERNEL);
+	if (!token->rxgk->ticket.data)
+		goto nomem_yrxgk;
+	memcpy(token->rxgk->ticket.data, ticket, token->rxgk->ticket.len);
+
+	_debug("SCIX: %u",	token->security_index);
+	_debug("EXPY: %llx",	token->rxgk->endtime);
+	_debug("LIFE: %llx",	token->rxgk->lifetime);
+	_debug("BYTE: %llx",	token->rxgk->bytelife);
+	_debug("ENC : %u",	token->rxgk->enctype);
+	_debug("LEVL: %u",	token->rxgk->level);
+	_debug("KLEN: %u",	token->rxgk->key.len);
+	_debug("TLEN: %u",	token->rxgk->ticket.len);
+	_debug("KEY0: %*phN",	token->rxgk->key.len, token->rxgk->key.data);
+	_debug("TICK: %*phN",
+	       min_t(u32, token->rxgk->ticket.len, 32), token->rxgk->ticket.data);
+
+	/* count the number of tokens attached */
+	prep->payload.data[1] = (void *)((unsigned long)prep->payload.data[1] + 1);
+
+	/* attach the data */
+	for (pptoken = (struct rxrpc_key_token **)&prep->payload.data[0];
+	     *pptoken;
+	     pptoken = &(*pptoken)->next)
+		continue;
+	*pptoken = token;
+
+	_leave(" = 0");
+	return 0;
+
+nomem_yrxgk:
+	kfree(token->rxgk);
+nomem_token:
+	kfree(token);
+nomem:
+	return -ENOMEM;
+reject_token:
+	kfree(token);
+reject:
+	return -EKEYREJECTED;
+expired:
+	kfree(token->rxgk);
+	kfree(token);
+	return -EKEYEXPIRED;
+}
+
 /*
  * attempt to parse the data as the XDR format
  * - the caller guarantees we have more than 7 words
@@ -228,6 +382,9 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep)
 		case RXRPC_SECURITY_RXKAD:
 			ret2 = rxrpc_preparse_xdr_rxkad(prep, datalen, token, toklen);
 			break;
+		case RXRPC_SECURITY_YFS_RXGK:
+			ret2 = rxrpc_preparse_xdr_yfs_rxgk(prep, datalen, token, toklen);
+			break;
 		default:
 			ret2 = -EPROTONOSUPPORT;
 			break;
@@ -390,6 +547,10 @@ static void rxrpc_free_token_list(struct rxrpc_key_token *token)
 		case RXRPC_SECURITY_RXKAD:
 			kfree(token->kad);
 			break;
+		case RXRPC_SECURITY_YFS_RXGK:
+			kfree(token->rxgk->ticket.data);
+			kfree(token->rxgk);
+			break;
 		default:
 			pr_err("Unknown token type %x on rxrpc key\n",
 			       token->security_index);
@@ -433,6 +594,9 @@ static void rxrpc_describe(const struct key *key, struct seq_file *m)
 		case RXRPC_SECURITY_RXKAD:
 			seq_puts(m, "ka");
 			break;
+		case RXRPC_SECURITY_YFS_RXGK:
+			seq_puts(m, "ygk");
+			break;
 		default: /* we have a ticket we can't encode */
 			seq_printf(m, "%u", token->security_index);
 			break;
@@ -531,6 +695,8 @@ EXPORT_SYMBOL(rxrpc_get_server_data_key);
  *
  * Generate a null RxRPC key that can be used to indicate anonymous security is
  * required for a particular domain.
+ *
+ * Return: The new key or a negative error code.
  */
 struct key *rxrpc_get_null_key(const char *keyname)
 {
@@ -595,6 +761,13 @@ static long rxrpc_read(const struct key *key,
 				toksize += RND(token->kad->ticket_len);
 			break;
 
+		case RXRPC_SECURITY_YFS_RXGK:
+			toksize += 6 * 8 + 2 * 4;
+			if (!token->no_leak_key)
+				toksize += RND(token->rxgk->key.len);
+			toksize += RND(token->rxgk->ticket.len);
+			break;
+
 		default: /* we have a ticket we can't encode */
 			pr_err("Unsupported key token type (%u)\n",
 			       token->security_index);
@@ -674,6 +847,20 @@ static long rxrpc_read(const struct key *key,
 				ENCODE_DATA(token->kad->ticket_len, token->kad->ticket);
 			break;
 
+		case RXRPC_SECURITY_YFS_RXGK:
+			ENCODE64(token->rxgk->begintime);
+			ENCODE64(token->rxgk->endtime);
+			ENCODE64(token->rxgk->level);
+			ENCODE64(token->rxgk->lifetime);
+			ENCODE64(token->rxgk->bytelife);
+			ENCODE64(token->rxgk->enctype);
+			if (token->no_leak_key)
+				ENCODE(0);
+			else
+				ENCODE_DATA(token->rxgk->key.len, token->rxgk->key.data);
+			ENCODE_DATA(token->rxgk->ticket.len, token->rxgk->ticket.data);
+			break;
+
 		default:
 			pr_err("Unsupported key token type (%u)\n",
 			       token->security_index);
diff --git a/net/rxrpc/oob.c b/net/rxrpc/oob.c
new file mode 100644
index 000000000000..05ca9c1faa57
--- /dev/null
+++ b/net/rxrpc/oob.c
@@ -0,0 +1,379 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Out of band message handling (e.g. challenge-response)
+ *
+ * Copyright (C) 2025 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/net.h>
+#include <linux/gfp.h>
+#include <linux/skbuff.h>
+#include <linux/export.h>
+#include <linux/sched/signal.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+enum rxrpc_oob_command {
+	RXRPC_OOB_CMD_UNSET,
+	RXRPC_OOB_CMD_RESPOND,
+} __mode(byte);
+
+struct rxrpc_oob_params {
+	u64			oob_id;		/* ID number of message if reply */
+	s32			abort_code;
+	enum rxrpc_oob_command	command;
+	bool			have_oob_id:1;
+};
+
+/*
+ * Post an out-of-band message for attention by the socket or kernel service
+ * associated with a reference call.
+ */
+void rxrpc_notify_socket_oob(struct rxrpc_call *call, struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rxrpc_sock *rx;
+	struct sock *sk;
+
+	rcu_read_lock();
+
+	rx = rcu_dereference(call->socket);
+	if (rx) {
+		sk = &rx->sk;
+		spin_lock_irq(&rx->recvmsg_lock);
+
+		if (sk->sk_state < RXRPC_CLOSE) {
+			skb->skb_mstamp_ns = rx->oob_id_counter++;
+			rxrpc_get_skb(skb, rxrpc_skb_get_post_oob);
+			skb_queue_tail(&rx->recvmsg_oobq, skb);
+
+			trace_rxrpc_notify_socket(call->debug_id, sp->hdr.serial);
+			if (rx->app_ops)
+				rx->app_ops->notify_oob(sk, skb);
+		}
+
+		spin_unlock_irq(&rx->recvmsg_lock);
+		if (!rx->app_ops && !sock_flag(sk, SOCK_DEAD))
+			sk->sk_data_ready(sk);
+	}
+
+	rcu_read_unlock();
+}
+
+/*
+ * Locate the OOB message to respond to by its ID.
+ */
+static struct sk_buff *rxrpc_find_pending_oob(struct rxrpc_sock *rx, u64 oob_id)
+{
+	struct rb_node *p;
+	struct sk_buff *skb;
+
+	p = rx->pending_oobq.rb_node;
+	while (p) {
+		skb = rb_entry(p, struct sk_buff, rbnode);
+
+		if (oob_id < skb->skb_mstamp_ns)
+			p = p->rb_left;
+		else if (oob_id > skb->skb_mstamp_ns)
+			p = p->rb_right;
+		else
+			return skb;
+	}
+
+	return NULL;
+}
+
+/*
+ * Add an OOB message into the pending-response set.  We always assign the next
+ * value from a 64-bit counter to the oob_id, so just assume we're always going
+ * to be on the right-hand edge of the tree and that the counter won't wrap.
+ * The tree is also given a ref to the message.
+ */
+void rxrpc_add_pending_oob(struct rxrpc_sock *rx, struct sk_buff *skb)
+{
+	struct rb_node **pp = &rx->pending_oobq.rb_node, *p = NULL;
+
+	while (*pp) {
+		p = *pp;
+		pp = &(*pp)->rb_right;
+	}
+
+	rb_link_node(&skb->rbnode, p, pp);
+	rb_insert_color(&skb->rbnode, &rx->pending_oobq);
+}
+
+/*
+ * Extract control messages from the sendmsg() control buffer.
+ */
+static int rxrpc_sendmsg_oob_cmsg(struct msghdr *msg, struct rxrpc_oob_params *p)
+{
+	struct cmsghdr *cmsg;
+	int len;
+
+	if (msg->msg_controllen == 0)
+		return -EINVAL;
+
+	for_each_cmsghdr(cmsg, msg) {
+		if (!CMSG_OK(msg, cmsg))
+			return -EINVAL;
+
+		len = cmsg->cmsg_len - sizeof(struct cmsghdr);
+		_debug("CMSG %d, %d, %d",
+		       cmsg->cmsg_level, cmsg->cmsg_type, len);
+
+		if (cmsg->cmsg_level != SOL_RXRPC)
+			continue;
+
+		switch (cmsg->cmsg_type) {
+		case RXRPC_OOB_ID:
+			if (len != sizeof(p->oob_id) || p->have_oob_id)
+				return -EINVAL;
+			memcpy(&p->oob_id, CMSG_DATA(cmsg), sizeof(p->oob_id));
+			p->have_oob_id = true;
+			break;
+		case RXRPC_RESPOND:
+			if (p->command != RXRPC_OOB_CMD_UNSET)
+				return -EINVAL;
+			p->command = RXRPC_OOB_CMD_RESPOND;
+			break;
+		case RXRPC_ABORT:
+			if (len != sizeof(p->abort_code) || p->abort_code)
+				return -EINVAL;
+			memcpy(&p->abort_code, CMSG_DATA(cmsg), sizeof(p->abort_code));
+			if (p->abort_code == 0)
+				return -EINVAL;
+			break;
+		case RXRPC_RESP_RXGK_APPDATA:
+			if (p->command != RXRPC_OOB_CMD_RESPOND)
+				return -EINVAL;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	switch (p->command) {
+	case RXRPC_OOB_CMD_RESPOND:
+		if (!p->have_oob_id)
+			return -EBADSLT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Allow userspace to respond to an OOB using sendmsg().
+ */
+static int rxrpc_respond_to_oob(struct rxrpc_sock *rx,
+				struct rxrpc_oob_params *p,
+				struct msghdr *msg)
+{
+	struct rxrpc_connection *conn;
+	struct rxrpc_skb_priv *sp;
+	struct sk_buff *skb;
+	int ret;
+
+	skb = rxrpc_find_pending_oob(rx, p->oob_id);
+	if (skb)
+		rb_erase(&skb->rbnode, &rx->pending_oobq);
+	release_sock(&rx->sk);
+	if (!skb)
+		return -EBADSLT;
+
+	sp = rxrpc_skb(skb);
+
+	switch (p->command) {
+	case RXRPC_OOB_CMD_RESPOND:
+		ret = -EPROTO;
+		if (skb->mark != RXRPC_OOB_CHALLENGE)
+			break;
+		conn = sp->chall.conn;
+		ret = -EOPNOTSUPP;
+		if (!conn->security->sendmsg_respond_to_challenge)
+			break;
+		if (p->abort_code) {
+			rxrpc_abort_conn(conn, NULL, p->abort_code, -ECONNABORTED,
+					 rxrpc_abort_response_sendmsg);
+			ret = 0;
+		} else {
+			ret = conn->security->sendmsg_respond_to_challenge(skb, msg);
+		}
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	rxrpc_free_skb(skb, rxrpc_skb_put_oob);
+	return ret;
+}
+
+/*
+ * Send an out-of-band message or respond to a received out-of-band message.
+ * - caller gives us the socket lock
+ * - the socket may be either a client socket or a server socket
+ */
+int rxrpc_sendmsg_oob(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
+{
+	struct rxrpc_oob_params p = {};
+	int ret;
+
+	_enter("");
+
+	ret = rxrpc_sendmsg_oob_cmsg(msg, &p);
+	if (ret < 0)
+		goto error_release_sock;
+
+	if (p.have_oob_id)
+		return rxrpc_respond_to_oob(rx, &p, msg);
+
+	release_sock(&rx->sk);
+
+	switch (p.command) {
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+
+error_release_sock:
+	release_sock(&rx->sk);
+	return ret;
+}
+
+/**
+ * rxrpc_kernel_query_oob - Query the parameters of an out-of-band message
+ * @oob: The message to query
+ * @_peer: Where to return the peer record
+ * @_peer_appdata: The application data attached to a peer record
+ *
+ * Extract useful parameters from an out-of-band message.  The source peer
+ * parameters are returned through the argument list and the message type is
+ * returned.
+ *
+ * Return:
+ * * %RXRPC_OOB_CHALLENGE - Challenge wanting a response.
+ */
+enum rxrpc_oob_type rxrpc_kernel_query_oob(struct sk_buff *oob,
+					   struct rxrpc_peer **_peer,
+					   unsigned long *_peer_appdata)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(oob);
+	enum rxrpc_oob_type type = oob->mark;
+
+	switch (type) {
+	case RXRPC_OOB_CHALLENGE:
+		*_peer		= sp->chall.conn->peer;
+		*_peer_appdata	= sp->chall.conn->peer->app_data;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		*_peer		= NULL;
+		*_peer_appdata	= 0;
+		break;
+	}
+
+	return type;
+}
+EXPORT_SYMBOL(rxrpc_kernel_query_oob);
+
+/**
+ * rxrpc_kernel_dequeue_oob - Dequeue and return the front OOB message
+ * @sock: The socket to query
+ * @_type: Where to return the message type
+ *
+ * Dequeue the front OOB message, if there is one, and return it and
+ * its type.
+ *
+ * Return: The sk_buff representing the OOB message or %NULL if the queue was
+ * empty.
+ */
+struct sk_buff *rxrpc_kernel_dequeue_oob(struct socket *sock,
+					 enum rxrpc_oob_type *_type)
+{
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+	struct sk_buff *oob;
+
+	oob = skb_dequeue(&rx->recvmsg_oobq);
+	if (oob)
+		*_type = oob->mark;
+	return oob;
+}
+EXPORT_SYMBOL(rxrpc_kernel_dequeue_oob);
+
+/**
+ * rxrpc_kernel_free_oob - Free an out-of-band message
+ * @oob: The OOB message to free
+ *
+ * Free an OOB message along with any resources it holds.
+ */
+void rxrpc_kernel_free_oob(struct sk_buff *oob)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(oob);
+
+	switch (oob->mark) {
+	case RXRPC_OOB_CHALLENGE:
+		rxrpc_put_connection(sp->chall.conn, rxrpc_conn_put_oob);
+		break;
+	}
+
+	rxrpc_free_skb(oob, rxrpc_skb_put_purge_oob);
+}
+EXPORT_SYMBOL(rxrpc_kernel_free_oob);
+
+/**
+ * rxrpc_kernel_query_challenge - Query the parameters of a challenge
+ * @challenge: The challenge to query
+ * @_peer: Where to return the peer record
+ * @_peer_appdata: The application data attached to a peer record
+ * @_service_id: Where to return the connection service ID
+ * @_security_index: Where to return the connection security index
+ *
+ * Extract useful parameters from a CHALLENGE message.
+ */
+void rxrpc_kernel_query_challenge(struct sk_buff *challenge,
+				  struct rxrpc_peer **_peer,
+				  unsigned long *_peer_appdata,
+				  u16 *_service_id, u8 *_security_index)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(challenge);
+
+	*_peer		= sp->chall.conn->peer;
+	*_peer_appdata	= sp->chall.conn->peer->app_data;
+	*_service_id	= sp->hdr.serviceId;
+	*_security_index = sp->hdr.securityIndex;
+}
+EXPORT_SYMBOL(rxrpc_kernel_query_challenge);
+
+/**
+ * rxrpc_kernel_reject_challenge - Allow a kernel service to reject a challenge
+ * @challenge: The challenge to be rejected
+ * @abort_code: The abort code to stick into the ABORT packet
+ * @error: Local error value
+ * @why: Indication as to why.
+ *
+ * Allow a kernel service to reject a challenge by aborting the connection if
+ * it's still in an abortable state.  The error is returned so this function
+ * can be used with a return statement.
+ *
+ * Return: The %error parameter.
+ */
+int rxrpc_kernel_reject_challenge(struct sk_buff *challenge, u32 abort_code,
+				  int error, enum rxrpc_abort_reason why)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(challenge);
+
+	_enter("{%x},%d,%d,%u", sp->hdr.serial, abort_code, error, why);
+
+	rxrpc_abort_conn(sp->chall.conn, NULL, abort_code, error, why);
+	return error;
+}
+EXPORT_SYMBOL(rxrpc_kernel_reject_challenge);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 95905b85a8d7..0af19bcdc80a 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -18,7 +18,7 @@
 
 extern int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
 
-static ssize_t do_udp_sendmsg(struct socket *socket, struct msghdr *msg, size_t len)
+ssize_t do_udp_sendmsg(struct socket *socket, struct msghdr *msg, size_t len)
 {
 	struct sockaddr *sa = msg->msg_name;
 	struct sock *sk = socket->sk;
@@ -916,3 +916,61 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer)
 	peer->last_tx_at = ktime_get_seconds();
 	_leave("");
 }
+
+/*
+ * Send a RESPONSE message.
+ */
+void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(response);
+	struct scatterlist sg[16];
+	struct bio_vec bvec[16];
+	struct msghdr msg;
+	size_t len = sp->resp.len;
+	__be32 wserial;
+	u32 serial = 0;
+	int ret, nr_sg;
+
+	_enter("C=%x,%x", conn->debug_id, sp->resp.challenge_serial);
+
+	sg_init_table(sg, ARRAY_SIZE(sg));
+	ret = skb_to_sgvec(response, sg, 0, len);
+	if (ret < 0)
+		goto fail;
+	nr_sg = ret;
+
+	for (int i = 0; i < nr_sg; i++)
+		bvec_set_page(&bvec[i], sg_page(&sg[i]), sg[i].length, sg[i].offset);
+
+	iov_iter_bvec(&msg.msg_iter, WRITE, bvec, nr_sg, len);
+
+	msg.msg_name	= &conn->peer->srx.transport;
+	msg.msg_namelen	= conn->peer->srx.transport_len;
+	msg.msg_control	= NULL;
+	msg.msg_controllen = 0;
+	msg.msg_flags	= MSG_SPLICE_PAGES;
+
+	serial = rxrpc_get_next_serials(conn, 1);
+	wserial = htonl(serial);
+
+	trace_rxrpc_tx_response(conn, serial, sp);
+
+	ret = skb_store_bits(response, offsetof(struct rxrpc_wire_header, serial),
+			     &wserial, sizeof(wserial));
+	if (ret < 0)
+		goto fail;
+
+	rxrpc_local_dont_fragment(conn->local, false);
+
+	ret = do_udp_sendmsg(conn->local->socket, &msg, len);
+	if (ret < 0)
+		goto fail;
+
+	conn->peer->last_tx_at = ktime_get_seconds();
+	return;
+
+fail:
+	trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+			    rxrpc_tx_point_response);
+	kleave(" = %d", ret);
+}
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 71b6e07bf161..e2f35e6c04d6 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -475,6 +475,8 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet)
  * @call: The call to query
  *
  * Get a record for the remote peer in a call.
+ *
+ * Return: The call's peer record.
  */
 struct rxrpc_peer *rxrpc_kernel_get_call_peer(struct socket *sock, struct rxrpc_call *call)
 {
@@ -486,7 +488,9 @@ EXPORT_SYMBOL(rxrpc_kernel_get_call_peer);
  * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT
  * @peer: The peer to query
  *
- * Get the call's peer smoothed RTT in uS or UINT_MAX if we have no samples.
+ * Get the call's peer smoothed RTT.
+ *
+ * Return: The RTT in uS or %UINT_MAX if we have no samples.
  */
 unsigned int rxrpc_kernel_get_srtt(const struct rxrpc_peer *peer)
 {
@@ -499,7 +503,10 @@ EXPORT_SYMBOL(rxrpc_kernel_get_srtt);
  * @peer: The peer to query
  *
  * Get a pointer to the address from a peer record.  The caller is responsible
- * for making sure that the address is not deallocated.
+ * for making sure that the address is not deallocated.  A fake address will be
+ * substituted if %peer in NULL.
+ *
+ * Return: The rxrpc address record or a fake record.
  */
 const struct sockaddr_rxrpc *rxrpc_kernel_remote_srx(const struct rxrpc_peer *peer)
 {
@@ -512,7 +519,10 @@ EXPORT_SYMBOL(rxrpc_kernel_remote_srx);
  * @peer: The peer to query
  *
  * Get a pointer to the transport address from a peer record.  The caller is
- * responsible for making sure that the address is not deallocated.
+ * responsible for making sure that the address is not deallocated.  A fake
+ * address will be substituted if %peer in NULL.
+ *
+ * Return: The transport address record or a fake record.
  */
 const struct sockaddr *rxrpc_kernel_remote_addr(const struct rxrpc_peer *peer)
 {
@@ -527,7 +537,9 @@ EXPORT_SYMBOL(rxrpc_kernel_remote_addr);
  * @app_data: The data to set
  *
  * Set the app-specific data on a peer.  AF_RXRPC makes no effort to retain
- * anything the data might refer to.  The previous app_data is returned.
+ * anything the data might refer to.
+ *
+ * Return: The previous app_data.
  */
 unsigned long rxrpc_kernel_set_peer_data(struct rxrpc_peer *peer, unsigned long app_data)
 {
@@ -540,6 +552,8 @@ EXPORT_SYMBOL(rxrpc_kernel_set_peer_data);
  * @peer: The peer to query
  *
  * Retrieve the app-specific data from a peer.
+ *
+ * Return: The peer's app data.
  */
 unsigned long rxrpc_kernel_get_peer_data(const struct rxrpc_peer *peer)
 {
diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h
index 42f70e4636f8..f8bfec12bc7e 100644
--- a/net/rxrpc/protocol.h
+++ b/net/rxrpc/protocol.h
@@ -181,4 +181,24 @@ struct rxkad_response {
 	__be32		ticket_len;	/* Kerberos ticket length  */
 } __packed;
 
+/*
+ * GSSAPI security type-4 and type-6 data header.
+ */
+struct rxgk_header {
+	__be32	epoch;
+	__be32	cid;
+	__be32	call_number;
+	__be32	seq;
+	__be32	sec_index;
+	__be32	data_len;
+} __packed;
+
+/*
+ * GSSAPI security type-4 and type-6 response packet header.
+ */
+struct rxgk_response {
+	__be64	start_time;
+	__be32	token_len;
+} __packed;
+
 #endif /* _LINUX_RXRPC_PACKET_H */
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 32cd5f1d541d..86a27fb55a1c 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -155,6 +155,82 @@ static int rxrpc_verify_data(struct rxrpc_call *call, struct sk_buff *skb)
 }
 
 /*
+ * Transcribe a call's user ID to a control message.
+ */
+static int rxrpc_recvmsg_user_id(struct rxrpc_call *call, struct msghdr *msg,
+				 int flags)
+{
+	if (!test_bit(RXRPC_CALL_HAS_USERID, &call->flags))
+		return 0;
+
+	if (flags & MSG_CMSG_COMPAT) {
+		unsigned int id32 = call->user_call_ID;
+
+		return put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID,
+				sizeof(unsigned int), &id32);
+	} else {
+		unsigned long idl = call->user_call_ID;
+
+		return put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID,
+				sizeof(unsigned long), &idl);
+	}
+}
+
+/*
+ * Deal with a CHALLENGE packet.
+ */
+static int rxrpc_recvmsg_challenge(struct socket *sock, struct msghdr *msg,
+				   struct sk_buff *challenge, unsigned int flags)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(challenge);
+	struct rxrpc_connection *conn = sp->chall.conn;
+
+	return conn->security->challenge_to_recvmsg(conn, challenge, msg);
+}
+
+/*
+ * Process OOB packets.  Called with the socket locked.
+ */
+static int rxrpc_recvmsg_oob(struct socket *sock, struct msghdr *msg,
+			     unsigned int flags)
+{
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+	struct sk_buff *skb;
+	bool need_response = false;
+	int ret;
+
+	skb = skb_peek(&rx->recvmsg_oobq);
+	if (!skb)
+		return -EAGAIN;
+	rxrpc_see_skb(skb, rxrpc_skb_see_recvmsg);
+
+	ret = put_cmsg(msg, SOL_RXRPC, RXRPC_OOB_ID, sizeof(u64),
+		       &skb->skb_mstamp_ns);
+	if (ret < 0)
+		return ret;
+
+	switch ((enum rxrpc_oob_type)skb->mark) {
+	case RXRPC_OOB_CHALLENGE:
+		need_response = true;
+		ret = rxrpc_recvmsg_challenge(sock, msg, skb, flags);
+		break;
+	default:
+		WARN_ONCE(1, "recvmsg() can't process unknown OOB type %u\n",
+			  skb->mark);
+		ret = -EIO;
+		break;
+	}
+
+	if (!(flags & MSG_PEEK))
+		skb_unlink(skb, &rx->recvmsg_oobq);
+	if (need_response)
+		rxrpc_add_pending_oob(rx, skb);
+	else
+		rxrpc_free_skb(skb, rxrpc_skb_put_oob);
+	return ret;
+}
+
+/*
  * Deliver messages to a call.  This keeps processing packets until the buffer
  * is filled and we find either more DATA (returns 0) or the end of the DATA
  * (returns 1).  If more packets are required, it returns -EAGAIN and if the
@@ -165,6 +241,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 			      size_t len, int flags, size_t *_offset)
 {
 	struct rxrpc_skb_priv *sp;
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	struct sk_buff *skb;
 	rxrpc_seq_t seq = 0;
 	size_t remain;
@@ -207,7 +284,6 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 			trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq,
 					     sp->offset, sp->len, ret2);
 			if (ret2 < 0) {
-				kdebug("verify = %d", ret2);
 				ret = ret2;
 				goto out;
 			}
@@ -255,6 +331,13 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 
 		if (!(flags & MSG_PEEK))
 			rxrpc_rotate_rx_window(call);
+
+		if (!rx->app_ops &&
+		    !skb_queue_empty_lockless(&rx->recvmsg_oobq)) {
+			trace_rxrpc_recvdata(call, rxrpc_recvmsg_oobq, seq,
+					     rx_pkt_offset, rx_pkt_len, ret);
+			break;
+		}
 	}
 
 out:
@@ -262,6 +345,7 @@ out:
 		call->rx_pkt_offset = rx_pkt_offset;
 		call->rx_pkt_len = rx_pkt_len;
 	}
+
 done:
 	trace_rxrpc_recvdata(call, rxrpc_recvmsg_data_return, seq,
 			     rx_pkt_offset, rx_pkt_len, ret);
@@ -301,6 +385,7 @@ try_again:
 	/* Return immediately if a client socket has no outstanding calls */
 	if (RB_EMPTY_ROOT(&rx->calls) &&
 	    list_empty(&rx->recvmsg_q) &&
+	    skb_queue_empty_lockless(&rx->recvmsg_oobq) &&
 	    rx->sk.sk_state != RXRPC_SERVER_LISTENING) {
 		release_sock(&rx->sk);
 		return -EAGAIN;
@@ -322,7 +407,8 @@ try_again:
 		if (ret)
 			goto wait_error;
 
-		if (list_empty(&rx->recvmsg_q)) {
+		if (list_empty(&rx->recvmsg_q) &&
+		    skb_queue_empty_lockless(&rx->recvmsg_oobq)) {
 			if (signal_pending(current))
 				goto wait_interrupted;
 			trace_rxrpc_recvmsg(0, rxrpc_recvmsg_wait, 0);
@@ -332,6 +418,15 @@ try_again:
 		goto try_again;
 	}
 
+	/* Deal with OOB messages before we consider getting normal data. */
+	if (!skb_queue_empty_lockless(&rx->recvmsg_oobq)) {
+		ret = rxrpc_recvmsg_oob(sock, msg, flags);
+		release_sock(&rx->sk);
+		if (ret == -EAGAIN)
+			goto try_again;
+		goto error_no_call;
+	}
+
 	/* Find the next call and dequeue it if we're not just peeking.  If we
 	 * do dequeue it, that comes with a ref that we will need to release.
 	 * We also want to weed out calls that got requeued whilst we were
@@ -342,7 +437,8 @@ try_again:
 	call = list_entry(l, struct rxrpc_call, recvmsg_link);
 
 	if (!rxrpc_call_is_complete(call) &&
-	    skb_queue_empty(&call->recvmsg_queue)) {
+	    skb_queue_empty(&call->recvmsg_queue) &&
+	    skb_queue_empty(&rx->recvmsg_oobq)) {
 		list_del_init(&call->recvmsg_link);
 		spin_unlock_irq(&rx->recvmsg_lock);
 		release_sock(&rx->sk);
@@ -377,21 +473,9 @@ try_again:
 	if (test_bit(RXRPC_CALL_RELEASED, &call->flags))
 		BUG();
 
-	if (test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) {
-		if (flags & MSG_CMSG_COMPAT) {
-			unsigned int id32 = call->user_call_ID;
-
-			ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID,
-				       sizeof(unsigned int), &id32);
-		} else {
-			unsigned long idl = call->user_call_ID;
-
-			ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID,
-				       sizeof(unsigned long), &idl);
-		}
-		if (ret < 0)
-			goto error_unlock_call;
-	}
+	ret = rxrpc_recvmsg_user_id(call, msg, flags);
+	if (ret < 0)
+		goto error_unlock_call;
 
 	if (msg->msg_name && call->peer) {
 		size_t len = sizeof(call->dest_srx);
@@ -477,14 +561,14 @@ wait_error:
  * @_service: Where to store the actual service ID (may be upgraded)
  *
  * Allow a kernel service to receive data and pick up information about the
- * state of a call.  Returns 0 if got what was asked for and there's more
- * available, 1 if we got what was asked for and we're at the end of the data
- * and -EAGAIN if we need more data.
+ * state of a call.  Note that *@_abort should also be initialised to %0.
  *
- * Note that we may return -EAGAIN to drain empty packets at the end of the
- * data, even if we've already copied over the requested data.
+ * Note that we may return %-EAGAIN to drain empty packets at the end
+ * of the data, even if we've already copied over the requested data.
  *
- * *_abort should also be initialised to 0.
+ * Return: %0 if got what was asked for and there's more available, %1
+ * if we got what was asked for and we're at the end of the data and
+ * %-EAGAIN if we need more data.
  */
 int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 			   struct iov_iter *iter, size_t *_len,
diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c
new file mode 100644
index 000000000000..1e19c605bcc8
--- /dev/null
+++ b/net/rxrpc/rxgk.c
@@ -0,0 +1,1371 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* GSSAPI-based RxRPC security
+ *
+ * Copyright (C) 2025 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/key-type.h>
+#include "ar-internal.h"
+#include "rxgk_common.h"
+
+/*
+ * Parse the information from a server key
+ */
+static int rxgk_preparse_server_key(struct key_preparsed_payload *prep)
+{
+	const struct krb5_enctype *krb5;
+	struct krb5_buffer *server_key = (void *)&prep->payload.data[2];
+	unsigned int service, sec_class, kvno, enctype;
+	int n = 0;
+
+	_enter("%zu", prep->datalen);
+
+	if (sscanf(prep->orig_description, "%u:%u:%u:%u%n",
+		   &service, &sec_class, &kvno, &enctype, &n) != 4)
+		return -EINVAL;
+
+	if (prep->orig_description[n])
+		return -EINVAL;
+
+	krb5 = crypto_krb5_find_enctype(enctype);
+	if (!krb5)
+		return -ENOPKG;
+
+	prep->payload.data[0] = (struct krb5_enctype *)krb5;
+
+	if (prep->datalen != krb5->key_len)
+		return -EKEYREJECTED;
+
+	server_key->len = prep->datalen;
+	server_key->data = kmemdup(prep->data, prep->datalen, GFP_KERNEL);
+	if (!server_key->data)
+		return -ENOMEM;
+
+	_leave(" = 0");
+	return 0;
+}
+
+static void rxgk_free_server_key(union key_payload *payload)
+{
+	struct krb5_buffer *server_key = (void *)&payload->data[2];
+
+	kfree_sensitive(server_key->data);
+}
+
+static void rxgk_free_preparse_server_key(struct key_preparsed_payload *prep)
+{
+	rxgk_free_server_key(&prep->payload);
+}
+
+static void rxgk_destroy_server_key(struct key *key)
+{
+	rxgk_free_server_key(&key->payload);
+}
+
+static void rxgk_describe_server_key(const struct key *key, struct seq_file *m)
+{
+	const struct krb5_enctype *krb5 = key->payload.data[0];
+
+	if (krb5)
+		seq_printf(m, ": %s", krb5->name);
+}
+
+/*
+ * Handle rekeying the connection when we see our limits overrun or when the
+ * far side decided to rekey.
+ *
+ * Returns a ref on the context if successful or -ESTALE if the key is out of
+ * date.
+ */
+static struct rxgk_context *rxgk_rekey(struct rxrpc_connection *conn,
+				       const u16 *specific_key_number)
+{
+	struct rxgk_context *gk, *dead = NULL;
+	unsigned int key_number, current_key, mask = ARRAY_SIZE(conn->rxgk.keys) - 1;
+	bool crank = false;
+
+	_enter("%d", specific_key_number ? *specific_key_number : -1);
+
+	mutex_lock(&conn->security_lock);
+
+	current_key = conn->rxgk.key_number;
+	if (!specific_key_number) {
+		key_number = current_key;
+	} else {
+		if (*specific_key_number == (u16)current_key)
+			key_number = current_key;
+		else if (*specific_key_number == (u16)(current_key - 1))
+			key_number = current_key - 1;
+		else if (*specific_key_number == (u16)(current_key + 1))
+			goto crank_window;
+		else
+			goto bad_key;
+	}
+
+	gk = conn->rxgk.keys[key_number & mask];
+	if (!gk)
+		goto generate_key;
+	if (!specific_key_number &&
+	    test_bit(RXGK_TK_NEEDS_REKEY, &gk->flags))
+		goto crank_window;
+
+grab:
+	refcount_inc(&gk->usage);
+	mutex_unlock(&conn->security_lock);
+	rxgk_put(dead);
+	return gk;
+
+crank_window:
+	trace_rxrpc_rxgk_rekey(conn, current_key,
+			       specific_key_number ? *specific_key_number : -1);
+	if (current_key == UINT_MAX)
+		goto bad_key;
+	if (current_key + 1 == UINT_MAX)
+		set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
+
+	key_number = current_key + 1;
+	if (WARN_ON(conn->rxgk.keys[key_number & mask]))
+		goto bad_key;
+	crank = true;
+
+generate_key:
+	gk = conn->rxgk.keys[current_key & mask];
+	gk = rxgk_generate_transport_key(conn, gk->key, key_number, GFP_NOFS);
+	if (IS_ERR(gk)) {
+		mutex_unlock(&conn->security_lock);
+		return gk;
+	}
+
+	write_lock(&conn->security_use_lock);
+	if (crank) {
+		current_key++;
+		conn->rxgk.key_number = current_key;
+		dead = conn->rxgk.keys[(current_key - 2) & mask];
+		conn->rxgk.keys[(current_key - 2) & mask] = NULL;
+	}
+	conn->rxgk.keys[current_key & mask] = gk;
+	write_unlock(&conn->security_use_lock);
+	goto grab;
+
+bad_key:
+	mutex_unlock(&conn->security_lock);
+	return ERR_PTR(-ESTALE);
+}
+
+/*
+ * Get the specified keying context.
+ *
+ * Returns a ref on the context if successful or -ESTALE if the key is out of
+ * date.
+ */
+static struct rxgk_context *rxgk_get_key(struct rxrpc_connection *conn,
+					 const u16 *specific_key_number)
+{
+	struct rxgk_context *gk;
+	unsigned int key_number, current_key, mask = ARRAY_SIZE(conn->rxgk.keys) - 1;
+
+	_enter("{%u},%d",
+	       conn->rxgk.key_number, specific_key_number ? *specific_key_number : -1);
+
+	read_lock(&conn->security_use_lock);
+
+	current_key = conn->rxgk.key_number;
+	if (!specific_key_number) {
+		key_number = current_key;
+	} else {
+		/* Only the bottom 16 bits of the key number are exposed in the
+		 * header, so we try and keep the upper 16 bits in step.  The
+		 * whole 32 bits are used to generate the TK.
+		 */
+		if (*specific_key_number == (u16)current_key)
+			key_number = current_key;
+		else if (*specific_key_number == (u16)(current_key - 1))
+			key_number = current_key - 1;
+		else if (*specific_key_number == (u16)(current_key + 1))
+			goto rekey;
+		else
+			goto bad_key;
+	}
+
+	gk = conn->rxgk.keys[key_number & mask];
+	if (!gk)
+		goto slow_path;
+	if (!specific_key_number &&
+	    key_number < UINT_MAX) {
+		if (time_after(jiffies, gk->expiry) ||
+		    gk->bytes_remaining < 0) {
+			set_bit(RXGK_TK_NEEDS_REKEY, &gk->flags);
+			goto slow_path;
+		}
+
+		if (test_bit(RXGK_TK_NEEDS_REKEY, &gk->flags))
+			goto slow_path;
+	}
+
+	refcount_inc(&gk->usage);
+	read_unlock(&conn->security_use_lock);
+	return gk;
+
+rekey:
+	_debug("rekey");
+	if (current_key == UINT_MAX)
+		goto bad_key;
+	gk = conn->rxgk.keys[current_key & mask];
+	if (gk)
+		set_bit(RXGK_TK_NEEDS_REKEY, &gk->flags);
+slow_path:
+	read_unlock(&conn->security_use_lock);
+	return rxgk_rekey(conn, specific_key_number);
+bad_key:
+	read_unlock(&conn->security_use_lock);
+	return ERR_PTR(-ESTALE);
+}
+
+/*
+ * initialise connection security
+ */
+static int rxgk_init_connection_security(struct rxrpc_connection *conn,
+					 struct rxrpc_key_token *token)
+{
+	struct rxgk_context *gk;
+	int ret;
+
+	_enter("{%d,%u},{%x}",
+	       conn->debug_id, conn->rxgk.key_number, key_serial(conn->key));
+
+	conn->security_ix = token->security_index;
+	conn->security_level = token->rxgk->level;
+
+	if (rxrpc_conn_is_client(conn)) {
+		conn->rxgk.start_time = ktime_get();
+		do_div(conn->rxgk.start_time, 100);
+	}
+
+	gk = rxgk_generate_transport_key(conn, token->rxgk, conn->rxgk.key_number,
+					 GFP_NOFS);
+	if (IS_ERR(gk))
+		return PTR_ERR(gk);
+	conn->rxgk.enctype = gk->krb5->etype;
+	conn->rxgk.keys[gk->key_number & 3] = gk;
+
+	switch (conn->security_level) {
+	case RXRPC_SECURITY_PLAIN:
+	case RXRPC_SECURITY_AUTH:
+	case RXRPC_SECURITY_ENCRYPT:
+		break;
+	default:
+		ret = -EKEYREJECTED;
+		goto error;
+	}
+
+	ret = 0;
+error:
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Clean up the crypto on a call.
+ */
+static void rxgk_free_call_crypto(struct rxrpc_call *call)
+{
+}
+
+/*
+ * Work out how much data we can put in a packet.
+ */
+static struct rxrpc_txbuf *rxgk_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp)
+{
+	enum krb5_crypto_mode mode;
+	struct rxgk_context *gk;
+	struct rxrpc_txbuf *txb;
+	size_t shdr, alloc, limit, part, offset, gap;
+
+	switch (call->conn->security_level) {
+	default:
+		alloc = umin(remain, RXRPC_JUMBO_DATALEN);
+		return rxrpc_alloc_data_txbuf(call, alloc, 1, gfp);
+	case RXRPC_SECURITY_AUTH:
+		shdr = 0;
+		mode = KRB5_CHECKSUM_MODE;
+		break;
+	case RXRPC_SECURITY_ENCRYPT:
+		shdr = sizeof(struct rxgk_header);
+		mode = KRB5_ENCRYPT_MODE;
+		break;
+	}
+
+	gk = rxgk_get_key(call->conn, NULL);
+	if (IS_ERR(gk))
+		return NULL;
+
+	/* Work out the maximum amount of data that will fit. */
+	alloc = RXRPC_JUMBO_DATALEN;
+	limit = crypto_krb5_how_much_data(gk->krb5, mode, &alloc, &offset);
+
+	if (remain < limit - shdr) {
+		part = remain;
+		alloc = crypto_krb5_how_much_buffer(gk->krb5, mode,
+						    shdr + part, &offset);
+		gap = 0;
+	} else {
+		part = limit - shdr;
+		gap = RXRPC_JUMBO_DATALEN - alloc;
+		alloc = RXRPC_JUMBO_DATALEN;
+	}
+
+	rxgk_put(gk);
+
+	txb = rxrpc_alloc_data_txbuf(call, alloc, 16, gfp);
+	if (!txb)
+		return NULL;
+
+	txb->crypto_header	= offset;
+	txb->sec_header		= shdr;
+	txb->offset		+= offset + shdr;
+	txb->space		= part;
+
+	/* Clear excess space in the packet */
+	if (gap)
+		memset(txb->data + alloc - gap, 0, gap);
+	return txb;
+}
+
+/*
+ * Integrity mode (sign a packet - level 1 security)
+ */
+static int rxgk_secure_packet_integrity(const struct rxrpc_call *call,
+					struct rxgk_context *gk,
+					struct rxrpc_txbuf *txb)
+{
+	struct rxgk_header *hdr;
+	struct scatterlist sg[1];
+	struct krb5_buffer metadata;
+	int ret = -ENOMEM;
+
+	_enter("");
+
+	hdr = kzalloc(sizeof(*hdr), GFP_NOFS);
+	if (!hdr)
+		goto error_gk;
+
+	hdr->epoch	= htonl(call->conn->proto.epoch);
+	hdr->cid	= htonl(call->cid);
+	hdr->call_number = htonl(call->call_id);
+	hdr->seq	= htonl(txb->seq);
+	hdr->sec_index	= htonl(call->security_ix);
+	hdr->data_len	= htonl(txb->len);
+	metadata.len = sizeof(*hdr);
+	metadata.data = hdr;
+
+	sg_init_table(sg, 1);
+	sg_set_buf(&sg[0], txb->data, txb->alloc_size);
+
+	ret = crypto_krb5_get_mic(gk->krb5, gk->tx_Kc, &metadata,
+				  sg, 1, txb->alloc_size,
+				  txb->crypto_header, txb->sec_header + txb->len);
+	if (ret >= 0) {
+		txb->pkt_len = ret;
+		if (txb->alloc_size == RXRPC_JUMBO_DATALEN)
+			txb->jumboable = true;
+		gk->bytes_remaining -= ret;
+	}
+	kfree(hdr);
+error_gk:
+	rxgk_put(gk);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * wholly encrypt a packet (level 2 security)
+ */
+static int rxgk_secure_packet_encrypted(const struct rxrpc_call *call,
+					struct rxgk_context *gk,
+					struct rxrpc_txbuf *txb)
+{
+	struct rxgk_header *hdr;
+	struct scatterlist sg[1];
+	int ret;
+
+	_enter("%x", txb->len);
+
+	/* Insert the header into the buffer. */
+	hdr = txb->data + txb->crypto_header;
+	hdr->epoch	 = htonl(call->conn->proto.epoch);
+	hdr->cid	 = htonl(call->cid);
+	hdr->call_number = htonl(call->call_id);
+	hdr->seq	 = htonl(txb->seq);
+	hdr->sec_index	 = htonl(call->security_ix);
+	hdr->data_len	 = htonl(txb->len);
+
+	sg_init_table(sg, 1);
+	sg_set_buf(&sg[0], txb->data, txb->alloc_size);
+
+	ret = crypto_krb5_encrypt(gk->krb5, gk->tx_enc,
+				  sg, 1, txb->alloc_size,
+				  txb->crypto_header, txb->sec_header + txb->len,
+				  false);
+	if (ret >= 0) {
+		txb->pkt_len = ret;
+		if (txb->alloc_size == RXRPC_JUMBO_DATALEN)
+			txb->jumboable = true;
+		gk->bytes_remaining -= ret;
+	}
+
+	rxgk_put(gk);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * checksum an RxRPC packet header
+ */
+static int rxgk_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
+{
+	struct rxgk_context *gk;
+	int ret;
+
+	_enter("{%d{%x}},{#%u},%u,",
+	       call->debug_id, key_serial(call->conn->key), txb->seq, txb->len);
+
+	gk = rxgk_get_key(call->conn, NULL);
+	if (IS_ERR(gk))
+		return PTR_ERR(gk) == -ESTALE ? -EKEYREJECTED : PTR_ERR(gk);
+
+	ret = key_validate(call->conn->key);
+	if (ret < 0) {
+		rxgk_put(gk);
+		return ret;
+	}
+
+	call->security_enctype = gk->krb5->etype;
+	txb->cksum = htons(gk->key_number);
+
+	switch (call->conn->security_level) {
+	case RXRPC_SECURITY_PLAIN:
+		rxgk_put(gk);
+		txb->pkt_len = txb->len;
+		return 0;
+	case RXRPC_SECURITY_AUTH:
+		return rxgk_secure_packet_integrity(call, gk, txb);
+	case RXRPC_SECURITY_ENCRYPT:
+		return rxgk_secure_packet_encrypted(call, gk, txb);
+	default:
+		rxgk_put(gk);
+		return -EPERM;
+	}
+}
+
+/*
+ * Integrity mode (check the signature on a packet - level 1 security)
+ */
+static int rxgk_verify_packet_integrity(struct rxrpc_call *call,
+					struct rxgk_context *gk,
+					struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rxgk_header *hdr;
+	struct krb5_buffer metadata;
+	unsigned int offset = sp->offset, len = sp->len;
+	size_t data_offset = 0, data_len = len;
+	u32 ac;
+	int ret = -ENOMEM;
+
+	_enter("");
+
+	crypto_krb5_where_is_the_data(gk->krb5, KRB5_CHECKSUM_MODE,
+				      &data_offset, &data_len);
+
+	hdr = kzalloc(sizeof(*hdr), GFP_NOFS);
+	if (!hdr)
+		goto put_gk;
+
+	hdr->epoch	= htonl(call->conn->proto.epoch);
+	hdr->cid	= htonl(call->cid);
+	hdr->call_number = htonl(call->call_id);
+	hdr->seq	= htonl(sp->hdr.seq);
+	hdr->sec_index	= htonl(call->security_ix);
+	hdr->data_len	= htonl(data_len);
+
+	metadata.len = sizeof(*hdr);
+	metadata.data = hdr;
+	ret = rxgk_verify_mic_skb(gk->krb5, gk->rx_Kc, &metadata,
+				  skb, &offset, &len, &ac);
+	kfree(hdr);
+	if (ret == -EPROTO) {
+		rxrpc_abort_eproto(call, skb, ac,
+				   rxgk_abort_1_verify_mic_eproto);
+	} else {
+		sp->offset = offset;
+		sp->len = len;
+	}
+
+put_gk:
+	rxgk_put(gk);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Decrypt an encrypted packet (level 2 security).
+ */
+static int rxgk_verify_packet_encrypted(struct rxrpc_call *call,
+					struct rxgk_context *gk,
+					struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rxgk_header hdr;
+	unsigned int offset = sp->offset, len = sp->len;
+	int ret;
+	u32 ac;
+
+	_enter("");
+
+	ret = rxgk_decrypt_skb(gk->krb5, gk->rx_enc, skb, &offset, &len, &ac);
+	if (ret == -EPROTO)
+		rxrpc_abort_eproto(call, skb, ac, rxgk_abort_2_decrypt_eproto);
+	if (ret < 0)
+		goto error;
+
+	if (len < sizeof(hdr)) {
+		ret = rxrpc_abort_eproto(call, skb, RXGK_PACKETSHORT,
+					 rxgk_abort_2_short_header);
+		goto error;
+	}
+
+	/* Extract the header from the skb */
+	ret = skb_copy_bits(skb, offset, &hdr, sizeof(hdr));
+	if (ret < 0) {
+		ret = rxrpc_abort_eproto(call, skb, RXGK_PACKETSHORT,
+					 rxgk_abort_2_short_encdata);
+		goto error;
+	}
+	offset += sizeof(hdr);
+	len -= sizeof(hdr);
+
+	if (ntohl(hdr.epoch)		!= call->conn->proto.epoch ||
+	    ntohl(hdr.cid)		!= call->cid ||
+	    ntohl(hdr.call_number)	!= call->call_id ||
+	    ntohl(hdr.seq)		!= sp->hdr.seq ||
+	    ntohl(hdr.sec_index)	!= call->security_ix ||
+	    ntohl(hdr.data_len)		> len) {
+		ret = rxrpc_abort_eproto(call, skb, RXGK_SEALEDINCON,
+					 rxgk_abort_2_short_data);
+		goto error;
+	}
+
+	sp->offset = offset;
+	sp->len = ntohl(hdr.data_len);
+	ret = 0;
+error:
+	rxgk_put(gk);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Verify the security on a received packet or subpacket (if part of a
+ * jumbo packet).
+ */
+static int rxgk_verify_packet(struct rxrpc_call *call, struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rxgk_context *gk;
+	u16 key_number = sp->hdr.cksum;
+
+	_enter("{%d{%x}},{#%u}",
+	       call->debug_id, key_serial(call->conn->key), sp->hdr.seq);
+
+	gk = rxgk_get_key(call->conn, &key_number);
+	if (IS_ERR(gk)) {
+		switch (PTR_ERR(gk)) {
+		case -ESTALE:
+			return rxrpc_abort_eproto(call, skb, RXGK_BADKEYNO,
+						  rxgk_abort_bad_key_number);
+		default:
+			return PTR_ERR(gk);
+		}
+	}
+
+	call->security_enctype = gk->krb5->etype;
+	switch (call->conn->security_level) {
+	case RXRPC_SECURITY_PLAIN:
+		rxgk_put(gk);
+		return 0;
+	case RXRPC_SECURITY_AUTH:
+		return rxgk_verify_packet_integrity(call, gk, skb);
+	case RXRPC_SECURITY_ENCRYPT:
+		return rxgk_verify_packet_encrypted(call, gk, skb);
+	default:
+		rxgk_put(gk);
+		return -ENOANO;
+	}
+}
+
+/*
+ * Allocate memory to hold a challenge or a response packet.  We're not running
+ * in the io_thread, so we can't use ->tx_alloc.
+ */
+static struct page *rxgk_alloc_packet(size_t total_len)
+{
+	gfp_t gfp = GFP_NOFS;
+	int order;
+
+	order = get_order(total_len);
+	if (order > 0)
+		gfp |= __GFP_COMP;
+	return alloc_pages(gfp, order);
+}
+
+/*
+ * Issue a challenge.
+ */
+static int rxgk_issue_challenge(struct rxrpc_connection *conn)
+{
+	struct rxrpc_wire_header *whdr;
+	struct bio_vec bvec[1];
+	struct msghdr msg;
+	struct page *page;
+	size_t len = sizeof(*whdr) + sizeof(conn->rxgk.nonce);
+	u32 serial;
+	int ret;
+
+	_enter("{%d}", conn->debug_id);
+
+	get_random_bytes(&conn->rxgk.nonce, sizeof(conn->rxgk.nonce));
+
+	/* We can't use conn->tx_alloc without a lock */
+	page = rxgk_alloc_packet(sizeof(*whdr) + sizeof(conn->rxgk.nonce));
+	if (!page)
+		return -ENOMEM;
+
+	bvec_set_page(&bvec[0], page, len, 0);
+	iov_iter_bvec(&msg.msg_iter, WRITE, bvec, 1, len);
+
+	msg.msg_name	= &conn->peer->srx.transport;
+	msg.msg_namelen	= conn->peer->srx.transport_len;
+	msg.msg_control	= NULL;
+	msg.msg_controllen = 0;
+	msg.msg_flags	= MSG_SPLICE_PAGES;
+
+	whdr = page_address(page);
+	whdr->epoch	= htonl(conn->proto.epoch);
+	whdr->cid	= htonl(conn->proto.cid);
+	whdr->callNumber = 0;
+	whdr->seq	= 0;
+	whdr->type	= RXRPC_PACKET_TYPE_CHALLENGE;
+	whdr->flags	= conn->out_clientflag;
+	whdr->userStatus = 0;
+	whdr->securityIndex = conn->security_ix;
+	whdr->_rsvd	= 0;
+	whdr->serviceId	= htons(conn->service_id);
+
+	memcpy(whdr + 1, conn->rxgk.nonce, sizeof(conn->rxgk.nonce));
+
+	serial = rxrpc_get_next_serials(conn, 1);
+	whdr->serial = htonl(serial);
+
+	trace_rxrpc_tx_challenge(conn, serial, 0, *(u32 *)&conn->rxgk.nonce);
+
+	ret = do_udp_sendmsg(conn->local->socket, &msg, len);
+	if (ret > 0)
+		conn->peer->last_tx_at = ktime_get_seconds();
+	__free_page(page);
+
+	if (ret < 0) {
+		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+				    rxrpc_tx_point_rxgk_challenge);
+		return -EAGAIN;
+	}
+
+	trace_rxrpc_tx_packet(conn->debug_id, whdr,
+			      rxrpc_tx_point_rxgk_challenge);
+	_leave(" = 0");
+	return 0;
+}
+
+/*
+ * Validate a challenge packet.
+ */
+static bool rxgk_validate_challenge(struct rxrpc_connection *conn,
+				    struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	u8 nonce[20];
+
+	if (!conn->key) {
+		rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+				 rxgk_abort_chall_no_key);
+		return false;
+	}
+
+	if (key_validate(conn->key) < 0) {
+		rxrpc_abort_conn(conn, skb, RXGK_EXPIRED, -EPROTO,
+				 rxgk_abort_chall_key_expired);
+		return false;
+	}
+
+	if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
+			  nonce, sizeof(nonce)) < 0) {
+		rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO,
+				 rxgk_abort_chall_short);
+		return false;
+	}
+
+	trace_rxrpc_rx_challenge(conn, sp->hdr.serial, 0, *(u32 *)nonce, 0);
+	return true;
+}
+
+/**
+ * rxgk_kernel_query_challenge - Query RxGK-specific challenge parameters
+ * @challenge: The challenge packet to query
+ *
+ * Return: The Kerberos 5 encoding type for the challenged connection.
+ */
+u32 rxgk_kernel_query_challenge(struct sk_buff *challenge)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(challenge);
+
+	return sp->chall.conn->rxgk.enctype;
+}
+EXPORT_SYMBOL(rxgk_kernel_query_challenge);
+
+/*
+ * Fill out the control message to pass to userspace to inform about the
+ * challenge.
+ */
+static int rxgk_challenge_to_recvmsg(struct rxrpc_connection *conn,
+				     struct sk_buff *challenge,
+				     struct msghdr *msg)
+{
+	struct rxgk_challenge chall;
+
+	chall.base.service_id		= conn->service_id;
+	chall.base.security_index	= conn->security_ix;
+	chall.enctype			= conn->rxgk.enctype;
+
+	return put_cmsg(msg, SOL_RXRPC, RXRPC_CHALLENGED, sizeof(chall), &chall);
+}
+
+/*
+ * Insert the requisite amount of XDR padding for the length given.
+ */
+static int rxgk_pad_out(struct sk_buff *response, size_t len, size_t offset)
+{
+	__be32 zero = 0;
+	size_t pad = xdr_round_up(len) - len;
+	int ret;
+
+	if (!pad)
+		return 0;
+
+	ret = skb_store_bits(response, offset, &zero, pad);
+	if (ret < 0)
+		return ret;
+	return pad;
+}
+
+/*
+ * Insert the header into the response.
+ */
+static noinline ssize_t rxgk_insert_response_header(struct rxrpc_connection *conn,
+						    struct rxgk_context *gk,
+						    struct sk_buff *response,
+						    size_t offset)
+{
+	struct rxrpc_skb_priv *rsp = rxrpc_skb(response);
+
+	struct {
+		struct rxrpc_wire_header whdr;
+		__be32 start_time_msw;
+		__be32 start_time_lsw;
+		__be32 ticket_len;
+	} h;
+	int ret;
+
+	rsp->resp.kvno		= gk->key_number;
+	rsp->resp.version	= gk->krb5->etype;
+
+	h.whdr.epoch		= htonl(conn->proto.epoch);
+	h.whdr.cid		= htonl(conn->proto.cid);
+	h.whdr.callNumber	= 0;
+	h.whdr.serial		= 0;
+	h.whdr.seq		= 0;
+	h.whdr.type		= RXRPC_PACKET_TYPE_RESPONSE;
+	h.whdr.flags		= conn->out_clientflag;
+	h.whdr.userStatus	= 0;
+	h.whdr.securityIndex	= conn->security_ix;
+	h.whdr.cksum		= htons(gk->key_number);
+	h.whdr.serviceId	= htons(conn->service_id);
+	h.start_time_msw	= htonl(upper_32_bits(conn->rxgk.start_time));
+	h.start_time_lsw	= htonl(lower_32_bits(conn->rxgk.start_time));
+	h.ticket_len		= htonl(gk->key->ticket.len);
+
+	ret = skb_store_bits(response, offset, &h, sizeof(h));
+	return ret < 0 ? ret : sizeof(h);
+}
+
+/*
+ * Construct the authenticator to go in the response packet
+ *
+ * struct RXGK_Authenticator {
+ *	opaque nonce[20];
+ *	opaque appdata<>;
+ *	RXGK_Level level;
+ *	unsigned int epoch;
+ *	unsigned int cid;
+ *	unsigned int call_numbers<>;
+ * };
+ */
+static ssize_t rxgk_construct_authenticator(struct rxrpc_connection *conn,
+					    struct sk_buff *challenge,
+					    const struct krb5_buffer *appdata,
+					    struct sk_buff *response,
+					    size_t offset)
+{
+	struct {
+		u8	nonce[20];
+		__be32	appdata_len;
+	} a;
+	struct {
+		__be32	level;
+		__be32	epoch;
+		__be32	cid;
+		__be32	call_numbers_count;
+		__be32	call_numbers[4];
+	} b;
+	int ret;
+
+	ret = skb_copy_bits(challenge, sizeof(struct rxrpc_wire_header),
+			    a.nonce, sizeof(a.nonce));
+	if (ret < 0)
+		return -EPROTO;
+
+	a.appdata_len = htonl(appdata->len);
+
+	ret = skb_store_bits(response, offset, &a, sizeof(a));
+	if (ret < 0)
+		return ret;
+	offset += sizeof(a);
+
+	if (appdata->len) {
+		ret = skb_store_bits(response, offset, appdata->data, appdata->len);
+		if (ret < 0)
+			return ret;
+		offset += appdata->len;
+
+		ret = rxgk_pad_out(response, appdata->len, offset);
+		if (ret < 0)
+			return ret;
+		offset += ret;
+	}
+
+	b.level			= htonl(conn->security_level);
+	b.epoch			= htonl(conn->proto.epoch);
+	b.cid			= htonl(conn->proto.cid);
+	b.call_numbers_count	= htonl(4);
+	b.call_numbers[0]	= htonl(conn->channels[0].call_counter);
+	b.call_numbers[1]	= htonl(conn->channels[1].call_counter);
+	b.call_numbers[2]	= htonl(conn->channels[2].call_counter);
+	b.call_numbers[3]	= htonl(conn->channels[3].call_counter);
+
+	ret = skb_store_bits(response, offset, &b, sizeof(b));
+	if (ret < 0)
+		return ret;
+	return sizeof(a) + xdr_round_up(appdata->len) + sizeof(b);
+}
+
+static ssize_t rxgk_encrypt_authenticator(struct rxrpc_connection *conn,
+					  struct rxgk_context *gk,
+					  struct sk_buff *response,
+					  size_t offset,
+					  size_t alloc_len,
+					  size_t auth_offset,
+					  size_t auth_len)
+{
+	struct scatterlist sg[16];
+	int nr_sg;
+
+	sg_init_table(sg, ARRAY_SIZE(sg));
+	nr_sg = skb_to_sgvec(response, sg, offset, alloc_len);
+	if (unlikely(nr_sg < 0))
+		return nr_sg;
+	return crypto_krb5_encrypt(gk->krb5, gk->resp_enc, sg, nr_sg, alloc_len,
+				   auth_offset, auth_len, false);
+}
+
+/*
+ * Construct the response.
+ *
+ * struct RXGK_Response {
+ *	rxgkTime start_time;
+ *	RXGK_Data token;
+ *	opaque authenticator<RXGK_MAXAUTHENTICATOR>
+ * };
+ */
+static int rxgk_construct_response(struct rxrpc_connection *conn,
+				   struct sk_buff *challenge,
+				   struct krb5_buffer *appdata)
+{
+	struct rxrpc_skb_priv *csp, *rsp;
+	struct rxgk_context *gk;
+	struct sk_buff *response;
+	size_t len, auth_len, authx_len, offset, auth_offset, authx_offset;
+	__be32 tmp;
+	int ret;
+
+	gk = rxgk_get_key(conn, NULL);
+	if (IS_ERR(gk))
+		return PTR_ERR(gk);
+
+	auth_len = 20 + (4 + appdata->len) + 12 + (1 + 4) * 4;
+	authx_len = crypto_krb5_how_much_buffer(gk->krb5, KRB5_ENCRYPT_MODE,
+						auth_len, &auth_offset);
+	len = sizeof(struct rxrpc_wire_header) +
+		8 + (4 + xdr_round_up(gk->key->ticket.len)) + (4 + authx_len);
+
+	response = alloc_skb_with_frags(0, len, 0, &ret, GFP_NOFS);
+	if (!response)
+		goto error;
+	rxrpc_new_skb(response, rxrpc_skb_new_response_rxgk);
+	response->len = len;
+	response->data_len = len;
+
+	ret = rxgk_insert_response_header(conn, gk, response, 0);
+	if (ret < 0)
+		goto error;
+	offset = ret;
+
+	ret = skb_store_bits(response, offset, gk->key->ticket.data, gk->key->ticket.len);
+	if (ret < 0)
+		goto error;
+	offset += gk->key->ticket.len;
+	ret = rxgk_pad_out(response, gk->key->ticket.len, offset);
+	if (ret < 0)
+		goto error;
+
+	authx_offset = offset + ret + 4; /* Leave a gap for the length. */
+
+	ret = rxgk_construct_authenticator(conn, challenge, appdata, response,
+					   authx_offset + auth_offset);
+	if (ret < 0)
+		goto error;
+	auth_len = ret;
+
+	ret = rxgk_encrypt_authenticator(conn, gk, response,
+					 authx_offset, authx_len,
+					 auth_offset, auth_len);
+	if (ret < 0)
+		goto error;
+	authx_len = ret;
+
+	tmp = htonl(authx_len);
+	ret = skb_store_bits(response, authx_offset - 4, &tmp, 4);
+	if (ret < 0)
+		goto error;
+
+	ret = rxgk_pad_out(response, authx_len, authx_offset + authx_len);
+	if (ret < 0)
+		goto error;
+	len = authx_offset + authx_len + ret;
+
+	if (len != response->len) {
+		response->len = len;
+		response->data_len = len;
+	}
+
+	csp = rxrpc_skb(challenge);
+	rsp = rxrpc_skb(response);
+	rsp->resp.len = len;
+	rsp->resp.challenge_serial = csp->hdr.serial;
+	rxrpc_post_response(conn, response);
+	response = NULL;
+	ret = 0;
+
+error:
+	rxrpc_free_skb(response, rxrpc_skb_put_response);
+	rxgk_put(gk);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Respond to a challenge packet.
+ */
+static int rxgk_respond_to_challenge(struct rxrpc_connection *conn,
+				     struct sk_buff *challenge,
+				     struct krb5_buffer *appdata)
+{
+	_enter("{%d,%x}", conn->debug_id, key_serial(conn->key));
+
+	if (key_validate(conn->key) < 0)
+		return rxrpc_abort_conn(conn, NULL, RXGK_EXPIRED, -EPROTO,
+					rxgk_abort_chall_key_expired);
+
+	return rxgk_construct_response(conn, challenge, appdata);
+}
+
+static int rxgk_respond_to_challenge_no_appdata(struct rxrpc_connection *conn,
+						struct sk_buff *challenge)
+{
+	struct krb5_buffer appdata = {};
+
+	return rxgk_respond_to_challenge(conn, challenge, &appdata);
+}
+
+/**
+ * rxgk_kernel_respond_to_challenge - Respond to a challenge with appdata
+ * @challenge: The challenge to respond to
+ * @appdata: The application data to include in the RESPONSE authenticator
+ *
+ * Allow a kernel application to respond to a CHALLENGE with application data
+ * to be included in the RxGK RESPONSE Authenticator.
+ *
+ * Return: %0 if successful and a negative error code otherwise.
+ */
+int rxgk_kernel_respond_to_challenge(struct sk_buff *challenge,
+				     struct krb5_buffer *appdata)
+{
+	struct rxrpc_skb_priv *csp = rxrpc_skb(challenge);
+
+	return rxgk_respond_to_challenge(csp->chall.conn, challenge, appdata);
+}
+EXPORT_SYMBOL(rxgk_kernel_respond_to_challenge);
+
+/*
+ * Parse sendmsg() control message and respond to challenge.  We need to see if
+ * there's an appdata to fish out.
+ */
+static int rxgk_sendmsg_respond_to_challenge(struct sk_buff *challenge,
+					     struct msghdr *msg)
+{
+	struct krb5_buffer appdata = {};
+	struct cmsghdr *cmsg;
+
+	for_each_cmsghdr(cmsg, msg) {
+		if (cmsg->cmsg_level != SOL_RXRPC ||
+		    cmsg->cmsg_type != RXRPC_RESP_RXGK_APPDATA)
+			continue;
+		if (appdata.data)
+			return -EINVAL;
+		appdata.data = CMSG_DATA(cmsg);
+		appdata.len = cmsg->cmsg_len - sizeof(struct cmsghdr);
+	}
+
+	return rxgk_kernel_respond_to_challenge(challenge, &appdata);
+}
+
+/*
+ * Verify the authenticator.
+ *
+ * struct RXGK_Authenticator {
+ *	opaque nonce[20];
+ *	opaque appdata<>;
+ *	RXGK_Level level;
+ *	unsigned int epoch;
+ *	unsigned int cid;
+ *	unsigned int call_numbers<>;
+ * };
+ */
+static int rxgk_do_verify_authenticator(struct rxrpc_connection *conn,
+					const struct krb5_enctype *krb5,
+					struct sk_buff *skb,
+					__be32 *p, __be32 *end)
+{
+	u32 app_len, call_count, level, epoch, cid, i;
+
+	_enter("");
+
+	if (memcmp(p, conn->rxgk.nonce, 20) != 0)
+		return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
+					rxgk_abort_resp_bad_nonce);
+	p += 20 / sizeof(__be32);
+
+	app_len	= ntohl(*p++);
+	if (app_len > (end - p) * sizeof(__be32))
+		return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
+					rxgk_abort_resp_short_applen);
+
+	p += xdr_round_up(app_len) / sizeof(__be32);
+	if (end - p < 4)
+		return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
+					rxgk_abort_resp_short_applen);
+
+	level	= ntohl(*p++);
+	epoch	= ntohl(*p++);
+	cid	= ntohl(*p++);
+	call_count = ntohl(*p++);
+
+	if (level	!= conn->security_level ||
+	    epoch	!= conn->proto.epoch ||
+	    cid		!= conn->proto.cid ||
+	    call_count	> 4)
+		return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
+					rxgk_abort_resp_bad_param);
+
+	if (end - p < call_count)
+		return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
+					rxgk_abort_resp_short_call_list);
+
+	for (i = 0; i < call_count; i++) {
+		u32 call_id = ntohl(*p++);
+
+		if (call_id > INT_MAX)
+			return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
+						rxgk_abort_resp_bad_callid);
+
+		if (call_id < conn->channels[i].call_counter)
+			return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
+						rxgk_abort_resp_call_ctr);
+
+		if (call_id > conn->channels[i].call_counter) {
+			if (conn->channels[i].call)
+				return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
+							rxgk_abort_resp_call_state);
+
+			conn->channels[i].call_counter = call_id;
+		}
+	}
+
+	_leave(" = 0");
+	return 0;
+}
+
+/*
+ * Extract the authenticator and verify it.
+ */
+static int rxgk_verify_authenticator(struct rxrpc_connection *conn,
+				     const struct krb5_enctype *krb5,
+				     struct sk_buff *skb,
+				     unsigned int auth_offset, unsigned int auth_len)
+{
+	void *auth;
+	__be32 *p;
+	int ret;
+
+	auth = kmalloc(auth_len, GFP_NOFS);
+	if (!auth)
+		return -ENOMEM;
+
+	ret = skb_copy_bits(skb, auth_offset, auth, auth_len);
+	if (ret < 0) {
+		ret = rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
+				       rxgk_abort_resp_short_auth);
+		goto error;
+	}
+
+	p = auth;
+	ret = rxgk_do_verify_authenticator(conn, krb5, skb, p, p + auth_len);
+error:
+	kfree(auth);
+	return ret;
+}
+
+/*
+ * Verify a response.
+ *
+ * struct RXGK_Response {
+ *	rxgkTime	start_time;
+ *	RXGK_Data	token;
+ *	opaque		authenticator<RXGK_MAXAUTHENTICATOR>
+ * };
+ */
+static int rxgk_verify_response(struct rxrpc_connection *conn,
+				struct sk_buff *skb)
+{
+	const struct krb5_enctype *krb5;
+	struct rxrpc_key_token *token;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rxgk_response rhdr;
+	struct rxgk_context *gk;
+	struct key *key = NULL;
+	unsigned int offset = sizeof(struct rxrpc_wire_header);
+	unsigned int len = skb->len - sizeof(struct rxrpc_wire_header);
+	unsigned int token_offset, token_len;
+	unsigned int auth_offset, auth_len;
+	__be32 xauth_len;
+	int ret, ec;
+
+	_enter("{%d}", conn->debug_id);
+
+	/* Parse the RXGK_Response object */
+	if (sizeof(rhdr) + sizeof(__be32) > len)
+		goto short_packet;
+
+	if (skb_copy_bits(skb, offset, &rhdr, sizeof(rhdr)) < 0)
+		goto short_packet;
+	offset	+= sizeof(rhdr);
+	len	-= sizeof(rhdr);
+
+	token_offset	= offset;
+	token_len	= ntohl(rhdr.token_len);
+	if (xdr_round_up(token_len) + sizeof(__be32) > len)
+		goto short_packet;
+
+	trace_rxrpc_rx_response(conn, sp->hdr.serial, 0, sp->hdr.cksum, token_len);
+
+	offset	+= xdr_round_up(token_len);
+	len	-= xdr_round_up(token_len);
+
+	if (skb_copy_bits(skb, offset, &xauth_len, sizeof(xauth_len)) < 0)
+		goto short_packet;
+	offset	+= sizeof(xauth_len);
+	len	-= sizeof(xauth_len);
+
+	auth_offset	= offset;
+	auth_len	= ntohl(xauth_len);
+	if (auth_len < len)
+		goto short_packet;
+	if (auth_len & 3)
+		goto inconsistent;
+	if (auth_len < 20 + 9 * 4)
+		goto auth_too_short;
+
+	/* We need to extract and decrypt the token and instantiate a session
+	 * key for it.  This bit, however, is application-specific.  If
+	 * possible, we use a default parser, but we might end up bumping this
+	 * to the app to deal with - which might mean a round trip to
+	 * userspace.
+	 */
+	ret = rxgk_extract_token(conn, skb, token_offset, token_len, &key);
+	if (ret < 0)
+		goto out;
+
+	/* We now have a key instantiated from the decrypted ticket.  We can
+	 * pass this to the application so that they can parse the ticket
+	 * content and we can use the session key it contains to derive the
+	 * keys we need.
+	 *
+	 * Note that we have to switch enctype at this point as the enctype of
+	 * the ticket doesn't necessarily match that of the transport.
+	 */
+	token = key->payload.data[0];
+	conn->security_level = token->rxgk->level;
+	conn->rxgk.start_time = __be64_to_cpu(rhdr.start_time);
+
+	gk = rxgk_generate_transport_key(conn, token->rxgk, sp->hdr.cksum, GFP_NOFS);
+	if (IS_ERR(gk)) {
+		ret = PTR_ERR(gk);
+		goto cant_get_token;
+	}
+
+	krb5 = gk->krb5;
+
+	trace_rxrpc_rx_response(conn, sp->hdr.serial, krb5->etype, sp->hdr.cksum, token_len);
+
+	/* Decrypt, parse and verify the authenticator. */
+	ret = rxgk_decrypt_skb(krb5, gk->resp_enc, skb,
+			       &auth_offset, &auth_len, &ec);
+	if (ret < 0) {
+		rxrpc_abort_conn(conn, skb, RXGK_SEALEDINCON, ret,
+				 rxgk_abort_resp_auth_dec);
+		goto out;
+	}
+
+	ret = rxgk_verify_authenticator(conn, krb5, skb, auth_offset, auth_len);
+	if (ret < 0)
+		goto out;
+
+	conn->key = key;
+	key = NULL;
+	ret = 0;
+out:
+	key_put(key);
+	_leave(" = %d", ret);
+	return ret;
+
+inconsistent:
+	ret = rxrpc_abort_conn(conn, skb, RXGK_INCONSISTENCY, -EPROTO,
+			       rxgk_abort_resp_xdr_align);
+	goto out;
+auth_too_short:
+	ret = rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO,
+			       rxgk_abort_resp_short_auth);
+	goto out;
+short_packet:
+	ret = rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO,
+			       rxgk_abort_resp_short_packet);
+	goto out;
+
+cant_get_token:
+	switch (ret) {
+	case -ENOMEM:
+		goto temporary_error;
+	case -EINVAL:
+		ret = rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EKEYREJECTED,
+				       rxgk_abort_resp_internal_error);
+		goto out;
+	case -ENOPKG:
+		ret = rxrpc_abort_conn(conn, skb, KRB5_PROG_KEYTYPE_NOSUPP,
+				       -EKEYREJECTED, rxgk_abort_resp_nopkg);
+		goto out;
+	}
+
+temporary_error:
+	/* Ignore the response packet if we got a temporary error such as
+	 * ENOMEM.  We just want to send the challenge again.  Note that we
+	 * also come out this way if the ticket decryption fails.
+	 */
+	goto out;
+}
+
+/*
+ * clear the connection security
+ */
+static void rxgk_clear(struct rxrpc_connection *conn)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(conn->rxgk.keys); i++)
+		rxgk_put(conn->rxgk.keys[i]);
+}
+
+/*
+ * Initialise the RxGK security service.
+ */
+static int rxgk_init(void)
+{
+	return 0;
+}
+
+/*
+ * Clean up the RxGK security service.
+ */
+static void rxgk_exit(void)
+{
+}
+
+/*
+ * RxRPC YFS GSSAPI-based security
+ */
+const struct rxrpc_security rxgk_yfs = {
+	.name				= "yfs-rxgk",
+	.security_index			= RXRPC_SECURITY_YFS_RXGK,
+	.no_key_abort			= RXGK_NOTAUTH,
+	.init				= rxgk_init,
+	.exit				= rxgk_exit,
+	.preparse_server_key		= rxgk_preparse_server_key,
+	.free_preparse_server_key	= rxgk_free_preparse_server_key,
+	.destroy_server_key		= rxgk_destroy_server_key,
+	.describe_server_key		= rxgk_describe_server_key,
+	.init_connection_security	= rxgk_init_connection_security,
+	.alloc_txbuf			= rxgk_alloc_txbuf,
+	.secure_packet			= rxgk_secure_packet,
+	.verify_packet			= rxgk_verify_packet,
+	.free_call_crypto		= rxgk_free_call_crypto,
+	.issue_challenge		= rxgk_issue_challenge,
+	.validate_challenge		= rxgk_validate_challenge,
+	.challenge_to_recvmsg		= rxgk_challenge_to_recvmsg,
+	.sendmsg_respond_to_challenge	= rxgk_sendmsg_respond_to_challenge,
+	.respond_to_challenge		= rxgk_respond_to_challenge_no_appdata,
+	.verify_response		= rxgk_verify_response,
+	.clear				= rxgk_clear,
+	.default_decode_ticket		= rxgk_yfs_decode_ticket,
+};
diff --git a/net/rxrpc/rxgk_app.c b/net/rxrpc/rxgk_app.c
new file mode 100644
index 000000000000..b94b77a1c317
--- /dev/null
+++ b/net/rxrpc/rxgk_app.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Application-specific bits for GSSAPI-based RxRPC security
+ *
+ * Copyright (C) 2025 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/key-type.h>
+#include "ar-internal.h"
+#include "rxgk_common.h"
+
+/*
+ * Decode a default-style YFS ticket in a response and turn it into an
+ * rxrpc-type key.
+ *
+ * struct rxgk_key {
+ *	afs_uint32	enctype;
+ *	opaque		key<>;
+ * };
+ *
+ * struct RXGK_AuthName {
+ *	afs_int32	kind;
+ *	opaque		data<AUTHDATAMAX>;
+ *	opaque		display<AUTHPRINTABLEMAX>;
+ * };
+ *
+ * struct RXGK_Token {
+ *	rxgk_key		K0;
+ *	RXGK_Level		level;
+ *	rxgkTime		starttime;
+ *	afs_int32		lifetime;
+ *	afs_int32		bytelife;
+ *	rxgkTime		expirationtime;
+ *	struct RXGK_AuthName	identities<>;
+ * };
+ */
+int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb,
+			   unsigned int ticket_offset, unsigned int ticket_len,
+			   struct key **_key)
+{
+	struct rxrpc_key_token *token;
+	const struct cred *cred = current_cred(); // TODO - use socket creds
+	struct key *key;
+	size_t pre_ticket_len, payload_len;
+	unsigned int klen, enctype;
+	void *payload, *ticket;
+	__be32 *t, *p, *q, tmp[2];
+	int ret;
+
+	_enter("");
+
+	/* Get the session key length */
+	ret = skb_copy_bits(skb, ticket_offset, tmp, sizeof(tmp));
+	if (ret < 0)
+		return rxrpc_abort_conn(conn, skb, RXGK_INCONSISTENCY, -EPROTO,
+					rxgk_abort_resp_short_yfs_klen);
+	enctype = ntohl(tmp[0]);
+	klen = ntohl(tmp[1]);
+
+	if (klen > ticket_len - 10 * sizeof(__be32))
+		return rxrpc_abort_conn(conn, skb, RXGK_INCONSISTENCY, -EPROTO,
+					rxgk_abort_resp_short_yfs_key);
+
+	pre_ticket_len = ((5 + 14) * sizeof(__be32) +
+			  xdr_round_up(klen) +
+			  sizeof(__be32));
+	payload_len = pre_ticket_len + xdr_round_up(ticket_len);
+
+	payload = kzalloc(payload_len, GFP_NOFS);
+	if (!payload)
+		return -ENOMEM;
+
+	/* We need to fill out the XDR form for a key payload that we can pass
+	 * to add_key().  Start by copying in the ticket so that we can parse
+	 * it.
+	 */
+	ticket = payload + pre_ticket_len;
+	ret = skb_copy_bits(skb, ticket_offset, ticket, ticket_len);
+	if (ret < 0) {
+		ret = rxrpc_abort_conn(conn, skb, RXGK_INCONSISTENCY, -EPROTO,
+				       rxgk_abort_resp_short_yfs_tkt);
+		goto error;
+	}
+
+	/* Fill out the form header. */
+	p = payload;
+	p[0] = htonl(0); /* Flags */
+	p[1] = htonl(1); /* len(cellname) */
+	p[2] = htonl(0x20000000); /* Cellname " " */
+	p[3] = htonl(1); /* #tokens */
+	p[4] = htonl(15 * sizeof(__be32) + xdr_round_up(klen) +
+		     xdr_round_up(ticket_len)); /* Token len */
+
+	/* Now fill in the body.  Most of this we can just scrape directly from
+	 * the ticket.
+	 */
+	t = ticket + sizeof(__be32) * 2 + xdr_round_up(klen);
+	q = payload + 5 * sizeof(__be32);
+	q[0]  = htonl(RXRPC_SECURITY_YFS_RXGK);
+	q[1]  = t[1];		/* begintime - msw */
+	q[2]  = t[2];		/* - lsw */
+	q[3]  = t[5];		/* endtime - msw */
+	q[4]  = t[6];		/* - lsw */
+	q[5]  = 0;		/* level - msw */
+	q[6]  = t[0];		/* - lsw */
+	q[7]  = 0;		/* lifetime - msw */
+	q[8]  = t[3];		/* - lsw */
+	q[9]  = 0;		/* bytelife - msw */
+	q[10] = t[4];		/* - lsw */
+	q[11] = 0;		/* enctype - msw */
+	q[12] = htonl(enctype);	/* - lsw */
+	q[13] = htonl(klen);	/* Key length */
+
+	q += 14;
+
+	memcpy(q, ticket + sizeof(__be32) * 2, klen);
+	q += xdr_round_up(klen) / 4;
+	q[0] = htonl(ticket_len);
+	q++;
+	if (WARN_ON((unsigned long)q != (unsigned long)ticket)) {
+		ret = -EIO;
+		goto error;
+	}
+
+	/* Ticket read in with skb_copy_bits above */
+	q += xdr_round_up(ticket_len) / 4;
+	if (WARN_ON((unsigned long)q - (unsigned long)payload != payload_len)) {
+		ret = -EIO;
+		goto error;
+	}
+
+	/* Now turn that into a key. */
+	key = key_alloc(&key_type_rxrpc, "x",
+			GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred, // TODO: Use socket owner
+			KEY_USR_VIEW,
+			KEY_ALLOC_NOT_IN_QUOTA, NULL);
+	if (IS_ERR(key)) {
+		_leave(" = -ENOMEM [alloc %ld]", PTR_ERR(key));
+		ret = PTR_ERR(key);
+		goto error;
+	}
+
+	_debug("key %d", key_serial(key));
+
+	ret = key_instantiate_and_link(key, payload, payload_len, NULL, NULL);
+	if (ret < 0)
+		goto error_key;
+
+	token = key->payload.data[0];
+	token->no_leak_key = true;
+	*_key = key;
+	key = NULL;
+	ret = 0;
+	goto error;
+
+error_key:
+	key_put(key);
+error:
+	kfree_sensitive(payload);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Extract the token and set up a session key from the details.
+ *
+ * struct RXGK_TokenContainer {
+ *	afs_int32	kvno;
+ *	afs_int32	enctype;
+ *	opaque		encrypted_token<>;
+ * };
+ *
+ * [tools.ietf.org/html/draft-wilkinson-afs3-rxgk-afs-08 sec 6.1]
+ */
+int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb,
+		       unsigned int token_offset, unsigned int token_len,
+		       struct key **_key)
+{
+	const struct krb5_enctype *krb5;
+	const struct krb5_buffer *server_secret;
+	struct crypto_aead *token_enc = NULL;
+	struct key *server_key;
+	unsigned int ticket_offset, ticket_len;
+	u32 kvno, enctype;
+	int ret, ec;
+
+	struct {
+		__be32 kvno;
+		__be32 enctype;
+		__be32 token_len;
+	} container;
+
+	/* Decode the RXGK_TokenContainer object.  This tells us which server
+	 * key we should be using.  We can then fetch the key, get the secret
+	 * and set up the crypto to extract the token.
+	 */
+	if (skb_copy_bits(skb, token_offset, &container, sizeof(container)) < 0)
+		return rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO,
+					rxgk_abort_resp_tok_short);
+
+	kvno		= ntohl(container.kvno);
+	enctype		= ntohl(container.enctype);
+	ticket_len	= ntohl(container.token_len);
+	ticket_offset	= token_offset + sizeof(container);
+
+	if (xdr_round_up(ticket_len) > token_len - 3 * 4)
+		return rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO,
+					rxgk_abort_resp_tok_short);
+
+	_debug("KVNO %u", kvno);
+	_debug("ENC  %u", enctype);
+	_debug("TLEN %u", ticket_len);
+
+	server_key = rxrpc_look_up_server_security(conn, skb, kvno, enctype);
+	if (IS_ERR(server_key))
+		goto cant_get_server_key;
+
+	down_read(&server_key->sem);
+	server_secret = (const void *)&server_key->payload.data[2];
+	ret = rxgk_set_up_token_cipher(server_secret, &token_enc, enctype, &krb5, GFP_NOFS);
+	up_read(&server_key->sem);
+	key_put(server_key);
+	if (ret < 0)
+		goto cant_get_token;
+
+	/* We can now decrypt and parse the token/ticket.  This allows us to
+	 * gain access to K0, from which we can derive the transport key and
+	 * thence decode the authenticator.
+	 */
+	ret = rxgk_decrypt_skb(krb5, token_enc, skb,
+			       &ticket_offset, &ticket_len, &ec);
+	crypto_free_aead(token_enc);
+	token_enc = NULL;
+	if (ret < 0)
+		return rxrpc_abort_conn(conn, skb, ec, ret,
+					rxgk_abort_resp_tok_dec);
+
+	ret = conn->security->default_decode_ticket(conn, skb, ticket_offset,
+						    ticket_len, _key);
+	if (ret < 0)
+		goto cant_get_token;
+
+	_leave(" = 0");
+	return ret;
+
+cant_get_server_key:
+	ret = PTR_ERR(server_key);
+	switch (ret) {
+	case -ENOMEM:
+		goto temporary_error;
+	case -ENOKEY:
+	case -EKEYREJECTED:
+	case -EKEYEXPIRED:
+	case -EKEYREVOKED:
+	case -EPERM:
+		return rxrpc_abort_conn(conn, skb, RXGK_BADKEYNO, -EKEYREJECTED,
+					rxgk_abort_resp_tok_nokey);
+	default:
+		return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EKEYREJECTED,
+					rxgk_abort_resp_tok_keyerr);
+	}
+
+cant_get_token:
+	switch (ret) {
+	case -ENOMEM:
+		goto temporary_error;
+	case -EINVAL:
+		return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EKEYREJECTED,
+					rxgk_abort_resp_tok_internal_error);
+	case -ENOPKG:
+		return rxrpc_abort_conn(conn, skb, KRB5_PROG_KEYTYPE_NOSUPP,
+					-EKEYREJECTED, rxgk_abort_resp_tok_nopkg);
+	}
+
+temporary_error:
+	/* Ignore the response packet if we got a temporary error such as
+	 * ENOMEM.  We just want to send the challenge again.  Note that we
+	 * also come out this way if the ticket decryption fails.
+	 */
+	return ret;
+}
diff --git a/net/rxrpc/rxgk_common.h b/net/rxrpc/rxgk_common.h
new file mode 100644
index 000000000000..7370a5655985
--- /dev/null
+++ b/net/rxrpc/rxgk_common.h
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Common bits for GSSAPI-based RxRPC security.
+ *
+ * Copyright (C) 2025 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <crypto/krb5.h>
+#include <crypto/skcipher.h>
+#include <crypto/hash.h>
+
+/*
+ * Per-key number context.  This is replaced when the connection is rekeyed.
+ */
+struct rxgk_context {
+	refcount_t		usage;
+	unsigned int		key_number;	/* Rekeying number (goes in the rx header) */
+	unsigned long		flags;
+#define RXGK_TK_NEEDS_REKEY	0		/* Set if this needs rekeying */
+	unsigned long		expiry;		/* Expiration time of this key */
+	long long		bytes_remaining; /* Remaining Tx lifetime of this key */
+	const struct krb5_enctype *krb5;	/* RxGK encryption type */
+	const struct rxgk_key	*key;
+
+	/* We need up to 7 keys derived from the transport key, but we don't
+	 * actually need the transport key.  Each key is derived by
+	 * DK(TK,constant).
+	 */
+	struct crypto_aead	*tx_enc;	/* Transmission key */
+	struct crypto_aead	*rx_enc;	/* Reception key */
+	struct crypto_shash	*tx_Kc;		/* Transmission checksum key */
+	struct crypto_shash	*rx_Kc;		/* Reception checksum key */
+	struct crypto_aead	*resp_enc;	/* Response packet enc key */
+};
+
+#define xdr_round_up(x) (round_up((x), sizeof(__be32)))
+#define xdr_object_len(x) (4 + xdr_round_up(x))
+
+/*
+ * rxgk_app.c
+ */
+int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb,
+			   unsigned int ticket_offset, unsigned int ticket_len,
+			   struct key **_key);
+int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb,
+		       unsigned int token_offset, unsigned int token_len,
+		       struct key **_key);
+
+/*
+ * rxgk_kdf.c
+ */
+void rxgk_put(struct rxgk_context *gk);
+struct rxgk_context *rxgk_generate_transport_key(struct rxrpc_connection *conn,
+						 const struct rxgk_key *key,
+						 unsigned int key_number,
+						 gfp_t gfp);
+int rxgk_set_up_token_cipher(const struct krb5_buffer *server_key,
+			     struct crypto_aead **token_key,
+			     unsigned int enctype,
+			     const struct krb5_enctype **_krb5,
+			     gfp_t gfp);
+
+/*
+ * Apply decryption and checksumming functions to part of an skbuff.  The
+ * offset and length are updated to reflect the actual content of the encrypted
+ * region.
+ */
+static inline
+int rxgk_decrypt_skb(const struct krb5_enctype *krb5,
+		     struct crypto_aead *aead,
+		     struct sk_buff *skb,
+		     unsigned int *_offset, unsigned int *_len,
+		     int *_error_code)
+{
+	struct scatterlist sg[16];
+	size_t offset = 0, len = *_len;
+	int nr_sg, ret;
+
+	sg_init_table(sg, ARRAY_SIZE(sg));
+	nr_sg = skb_to_sgvec(skb, sg, *_offset, len);
+	if (unlikely(nr_sg < 0))
+		return nr_sg;
+
+	ret = crypto_krb5_decrypt(krb5, aead, sg, nr_sg,
+				  &offset, &len);
+	switch (ret) {
+	case 0:
+		*_offset += offset;
+		*_len = len;
+		break;
+	case -EPROTO:
+	case -EBADMSG:
+		*_error_code = RXGK_SEALEDINCON;
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * Check the MIC on a region of an skbuff.  The offset and length are updated
+ * to reflect the actual content of the secure region.
+ */
+static inline
+int rxgk_verify_mic_skb(const struct krb5_enctype *krb5,
+			struct crypto_shash *shash,
+			const struct krb5_buffer *metadata,
+			struct sk_buff *skb,
+			unsigned int *_offset, unsigned int *_len,
+			u32 *_error_code)
+{
+	struct scatterlist sg[16];
+	size_t offset = 0, len = *_len;
+	int nr_sg, ret;
+
+	sg_init_table(sg, ARRAY_SIZE(sg));
+	nr_sg = skb_to_sgvec(skb, sg, *_offset, len);
+	if (unlikely(nr_sg < 0))
+		return nr_sg;
+
+	ret = crypto_krb5_verify_mic(krb5, shash, metadata, sg, nr_sg,
+				     &offset, &len);
+	switch (ret) {
+	case 0:
+		*_offset += offset;
+		*_len = len;
+		break;
+	case -EPROTO:
+	case -EBADMSG:
+		*_error_code = RXGK_SEALEDINCON;
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
diff --git a/net/rxrpc/rxgk_kdf.c b/net/rxrpc/rxgk_kdf.c
new file mode 100644
index 000000000000..b4db5aa30e5b
--- /dev/null
+++ b/net/rxrpc/rxgk_kdf.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* RxGK transport key derivation.
+ *
+ * Copyright (C) 2025 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/key-type.h>
+#include <linux/slab.h>
+#include <keys/rxrpc-type.h>
+#include "ar-internal.h"
+#include "rxgk_common.h"
+
+#define round16(x) (((x) + 15) & ~15)
+
+/*
+ * Constants used to derive the keys and hmacs actually used for doing stuff.
+ */
+#define RXGK_CLIENT_ENC_PACKET		1026U // 0x402
+#define RXGK_CLIENT_MIC_PACKET          1027U // 0x403
+#define RXGK_SERVER_ENC_PACKET          1028U // 0x404
+#define RXGK_SERVER_MIC_PACKET          1029U // 0x405
+#define RXGK_CLIENT_ENC_RESPONSE        1030U // 0x406
+#define RXGK_SERVER_ENC_TOKEN           1036U // 0x40c
+
+static void rxgk_free(struct rxgk_context *gk)
+{
+	if (gk->tx_Kc)
+		crypto_free_shash(gk->tx_Kc);
+	if (gk->rx_Kc)
+		crypto_free_shash(gk->rx_Kc);
+	if (gk->tx_enc)
+		crypto_free_aead(gk->tx_enc);
+	if (gk->rx_enc)
+		crypto_free_aead(gk->rx_enc);
+	if (gk->resp_enc)
+		crypto_free_aead(gk->resp_enc);
+	kfree(gk);
+}
+
+void rxgk_put(struct rxgk_context *gk)
+{
+	if (gk && refcount_dec_and_test(&gk->usage))
+		rxgk_free(gk);
+}
+
+/*
+ * Transport key derivation function.
+ *
+ *      TK = random-to-key(PRF+(K0, L,
+ *                         epoch || cid || start_time || key_number))
+ *      [tools.ietf.org/html/draft-wilkinson-afs3-rxgk-11 sec 8.3]
+ */
+static int rxgk_derive_transport_key(struct rxrpc_connection *conn,
+				     struct rxgk_context *gk,
+				     const struct rxgk_key *rxgk,
+				     struct krb5_buffer *TK,
+				     gfp_t gfp)
+{
+	const struct krb5_enctype *krb5 = gk->krb5;
+	struct krb5_buffer conn_info;
+	unsigned int L = krb5->key_bytes;
+	__be32 *info;
+	u8 *buffer;
+	int ret;
+
+	_enter("");
+
+	conn_info.len = sizeof(__be32) * 5;
+
+	buffer = kzalloc(round16(conn_info.len), gfp);
+	if (!buffer)
+		return -ENOMEM;
+
+	conn_info.data = buffer;
+
+	info = (__be32 *)conn_info.data;
+	info[0] = htonl(conn->proto.epoch);
+	info[1] = htonl(conn->proto.cid);
+	info[2] = htonl(conn->rxgk.start_time >> 32);
+	info[3] = htonl(conn->rxgk.start_time >>  0);
+	info[4] = htonl(gk->key_number);
+
+	ret = crypto_krb5_calc_PRFplus(krb5, &rxgk->key, L, &conn_info, TK, gfp);
+	kfree_sensitive(buffer);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Set up the ciphers for the usage keys.
+ */
+static int rxgk_set_up_ciphers(struct rxrpc_connection *conn,
+			       struct rxgk_context *gk,
+			       const struct rxgk_key *rxgk,
+			       gfp_t gfp)
+{
+	const struct krb5_enctype *krb5 = gk->krb5;
+	struct crypto_shash *shash;
+	struct crypto_aead *aead;
+	struct krb5_buffer TK;
+	bool service = rxrpc_conn_is_service(conn);
+	int ret;
+	u8 *buffer;
+
+	buffer = kzalloc(krb5->key_bytes, gfp);
+	if (!buffer)
+		return -ENOMEM;
+
+	TK.len = krb5->key_bytes;
+	TK.data = buffer;
+
+	ret = rxgk_derive_transport_key(conn, gk, rxgk, &TK, gfp);
+	if (ret < 0)
+		goto out;
+
+	aead = crypto_krb5_prepare_encryption(krb5, &TK, RXGK_CLIENT_ENC_RESPONSE, gfp);
+	if (IS_ERR(aead))
+		goto aead_error;
+	gk->resp_enc = aead;
+
+	if (crypto_aead_blocksize(gk->resp_enc) != krb5->block_len ||
+	    crypto_aead_authsize(gk->resp_enc) != krb5->cksum_len) {
+		pr_notice("algo inconsistent with krb5 table %u!=%u or %u!=%u\n",
+			  crypto_aead_blocksize(gk->resp_enc), krb5->block_len,
+			  crypto_aead_authsize(gk->resp_enc), krb5->cksum_len);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (service) {
+		switch (conn->security_level) {
+		case RXRPC_SECURITY_AUTH:
+			shash = crypto_krb5_prepare_checksum(
+				krb5, &TK, RXGK_SERVER_MIC_PACKET, gfp);
+			if (IS_ERR(shash))
+				goto hash_error;
+			gk->tx_Kc = shash;
+			shash = crypto_krb5_prepare_checksum(
+				krb5, &TK, RXGK_CLIENT_MIC_PACKET, gfp);
+			if (IS_ERR(shash))
+				goto hash_error;
+			gk->rx_Kc = shash;
+			break;
+		case RXRPC_SECURITY_ENCRYPT:
+			aead = crypto_krb5_prepare_encryption(
+				krb5, &TK, RXGK_SERVER_ENC_PACKET, gfp);
+			if (IS_ERR(aead))
+				goto aead_error;
+			gk->tx_enc = aead;
+			aead = crypto_krb5_prepare_encryption(
+				krb5, &TK, RXGK_CLIENT_ENC_PACKET, gfp);
+			if (IS_ERR(aead))
+				goto aead_error;
+			gk->rx_enc = aead;
+			break;
+		}
+	} else {
+		switch (conn->security_level) {
+		case RXRPC_SECURITY_AUTH:
+			shash = crypto_krb5_prepare_checksum(
+				krb5, &TK, RXGK_CLIENT_MIC_PACKET, gfp);
+			if (IS_ERR(shash))
+				goto hash_error;
+			gk->tx_Kc = shash;
+			shash = crypto_krb5_prepare_checksum(
+				krb5, &TK, RXGK_SERVER_MIC_PACKET, gfp);
+			if (IS_ERR(shash))
+				goto hash_error;
+			gk->rx_Kc = shash;
+			break;
+		case RXRPC_SECURITY_ENCRYPT:
+			aead = crypto_krb5_prepare_encryption(
+				krb5, &TK, RXGK_CLIENT_ENC_PACKET, gfp);
+			if (IS_ERR(aead))
+				goto aead_error;
+			gk->tx_enc = aead;
+			aead = crypto_krb5_prepare_encryption(
+				krb5, &TK, RXGK_SERVER_ENC_PACKET, gfp);
+			if (IS_ERR(aead))
+				goto aead_error;
+			gk->rx_enc = aead;
+			break;
+		}
+	}
+
+	ret = 0;
+out:
+	kfree_sensitive(buffer);
+	return ret;
+aead_error:
+	ret = PTR_ERR(aead);
+	goto out;
+hash_error:
+	ret = PTR_ERR(shash);
+	goto out;
+}
+
+/*
+ * Derive a transport key for a connection and then derive a bunch of usage
+ * keys from it and set up ciphers using them.
+ */
+struct rxgk_context *rxgk_generate_transport_key(struct rxrpc_connection *conn,
+						 const struct rxgk_key *key,
+						 unsigned int key_number,
+						 gfp_t gfp)
+{
+	struct rxgk_context *gk;
+	unsigned long lifetime;
+	int ret = -ENOPKG;
+
+	_enter("");
+
+	gk = kzalloc(sizeof(*gk), GFP_KERNEL);
+	if (!gk)
+		return ERR_PTR(-ENOMEM);
+	refcount_set(&gk->usage, 1);
+	gk->key		= key;
+	gk->key_number	= key_number;
+
+	gk->krb5 = crypto_krb5_find_enctype(key->enctype);
+	if (!gk->krb5)
+		goto err_tk;
+
+	ret = rxgk_set_up_ciphers(conn, gk, key, gfp);
+	if (ret)
+		goto err_tk;
+
+	/* Set the remaining number of bytes encrypted with this key that may
+	 * be transmitted before rekeying.  Note that the spec has been
+	 * interpreted differently on this point...
+	 */
+	switch (key->bytelife) {
+	case 0:
+	case 63:
+		gk->bytes_remaining = LLONG_MAX;
+		break;
+	case 1 ... 62:
+		gk->bytes_remaining = 1LL << key->bytelife;
+		break;
+	default:
+		gk->bytes_remaining = key->bytelife;
+		break;
+	}
+
+	/* Set the time after which rekeying must occur */
+	if (key->lifetime) {
+		lifetime = min_t(u64, key->lifetime, INT_MAX / HZ);
+		lifetime *= HZ;
+	} else {
+		lifetime = MAX_JIFFY_OFFSET;
+	}
+	gk->expiry = jiffies + lifetime;
+	return gk;
+
+err_tk:
+	rxgk_put(gk);
+	_leave(" = %d", ret);
+	return ERR_PTR(ret);
+}
+
+/*
+ * Use the server secret key to set up the ciphers that will be used to extract
+ * the token from a response packet.
+ */
+int rxgk_set_up_token_cipher(const struct krb5_buffer *server_key,
+			     struct crypto_aead **token_aead,
+			     unsigned int enctype,
+			     const struct krb5_enctype **_krb5,
+			     gfp_t gfp)
+{
+	const struct krb5_enctype *krb5;
+	struct crypto_aead *aead;
+
+	krb5 = crypto_krb5_find_enctype(enctype);
+	if (!krb5)
+		return -ENOPKG;
+
+	aead = crypto_krb5_prepare_encryption(krb5, server_key, RXGK_SERVER_ENC_TOKEN, gfp);
+	if (IS_ERR(aead))
+		return PTR_ERR(aead);
+
+	*_krb5 = krb5;
+	*token_aead = aead;
+	return 0;
+}
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 6cb37b0eb77f..3657c0661cdc 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -177,8 +177,10 @@ static struct rxrpc_txbuf *rxkad_alloc_txbuf(struct rxrpc_call *call, size_t rem
 	if (!txb)
 		return NULL;
 
-	txb->offset += shdr;
-	txb->space = part;
+	txb->crypto_header	= 0;
+	txb->sec_header		= shdr;
+	txb->offset		+= shdr;
+	txb->space		= part;
 	return txb;
 }
 
@@ -683,6 +685,8 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 	serial = rxrpc_get_next_serial(conn);
 	whdr.serial = htonl(serial);
 
+	trace_rxrpc_tx_challenge(conn, serial, 0, conn->rxkad.nonce);
+
 	ret = kernel_sendmsg(conn->local->socket, &msg, iov, 2, len);
 	if (ret < 0) {
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
@@ -698,62 +702,6 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 }
 
 /*
- * send a Kerberos security response
- */
-static int rxkad_send_response(struct rxrpc_connection *conn,
-			       struct rxrpc_host_header *hdr,
-			       struct rxkad_response *resp,
-			       const struct rxkad_key *s2)
-{
-	struct rxrpc_wire_header whdr;
-	struct msghdr msg;
-	struct kvec iov[3];
-	size_t len;
-	u32 serial;
-	int ret;
-
-	_enter("");
-
-	msg.msg_name	= &conn->peer->srx.transport;
-	msg.msg_namelen	= conn->peer->srx.transport_len;
-	msg.msg_control	= NULL;
-	msg.msg_controllen = 0;
-	msg.msg_flags	= 0;
-
-	memset(&whdr, 0, sizeof(whdr));
-	whdr.epoch	= htonl(hdr->epoch);
-	whdr.cid	= htonl(hdr->cid);
-	whdr.type	= RXRPC_PACKET_TYPE_RESPONSE;
-	whdr.flags	= conn->out_clientflag;
-	whdr.securityIndex = hdr->securityIndex;
-	whdr.serviceId	= htons(hdr->serviceId);
-
-	iov[0].iov_base	= &whdr;
-	iov[0].iov_len	= sizeof(whdr);
-	iov[1].iov_base	= resp;
-	iov[1].iov_len	= sizeof(*resp);
-	iov[2].iov_base	= (void *)s2->ticket;
-	iov[2].iov_len	= s2->ticket_len;
-
-	len = iov[0].iov_len + iov[1].iov_len + iov[2].iov_len;
-
-	serial = rxrpc_get_next_serial(conn);
-	whdr.serial = htonl(serial);
-
-	rxrpc_local_dont_fragment(conn->local, false);
-	ret = kernel_sendmsg(conn->local->socket, &msg, iov, 3, len);
-	if (ret < 0) {
-		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
-				    rxrpc_tx_point_rxkad_response);
-		return -EAGAIN;
-	}
-
-	conn->peer->last_tx_at = ktime_get_seconds();
-	_leave(" = 0");
-	return 0;
-}
-
-/*
  * calculate the response checksum
  */
 static void rxkad_calc_response_checksum(struct rxkad_response *response)
@@ -772,12 +720,21 @@ static void rxkad_calc_response_checksum(struct rxkad_response *response)
  * encrypt the response packet
  */
 static int rxkad_encrypt_response(struct rxrpc_connection *conn,
-				  struct rxkad_response *resp,
+				  struct sk_buff *response,
 				  const struct rxkad_key *s2)
 {
 	struct skcipher_request *req;
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[1];
+	size_t encsize = sizeof(((struct rxkad_response *)0)->encrypted);
+	int ret;
+
+	sg_init_table(sg, ARRAY_SIZE(sg));
+	ret = skb_to_sgvec(response, sg,
+			   sizeof(struct rxrpc_wire_header) +
+			   offsetof(struct rxkad_response, encrypted), encsize);
+	if (ret < 0)
+		return ret;
 
 	req = skcipher_request_alloc(&conn->rxkad.cipher->base, GFP_NOFS);
 	if (!req)
@@ -786,89 +743,206 @@ static int rxkad_encrypt_response(struct rxrpc_connection *conn,
 	/* continue encrypting from where we left off */
 	memcpy(&iv, s2->session_key, sizeof(iv));
 
-	sg_init_table(sg, 1);
-	sg_set_buf(sg, &resp->encrypted, sizeof(resp->encrypted));
 	skcipher_request_set_sync_tfm(req, conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
-	skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x);
-	crypto_skcipher_encrypt(req);
+	skcipher_request_set_crypt(req, sg, sg, encsize, iv.x);
+	ret = crypto_skcipher_encrypt(req);
 	skcipher_request_free(req);
-	return 0;
+	return ret;
 }
 
 /*
- * respond to a challenge packet
+ * Validate a challenge packet.
  */
-static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
-				      struct sk_buff *skb)
+static bool rxkad_validate_challenge(struct rxrpc_connection *conn,
+				     struct sk_buff *skb)
 {
-	const struct rxrpc_key_token *token;
 	struct rxkad_challenge challenge;
-	struct rxkad_response *resp;
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-	u32 version, nonce, min_level;
-	int ret = -EPROTO;
+	u32 version, min_level;
+	int ret;
 
 	_enter("{%d,%x}", conn->debug_id, key_serial(conn->key));
 
-	if (!conn->key)
-		return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
-					rxkad_abort_chall_no_key);
+	if (!conn->key) {
+		rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+				 rxkad_abort_chall_no_key);
+		return false;
+	}
 
 	ret = key_validate(conn->key);
-	if (ret < 0)
-		return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret,
-					rxkad_abort_chall_key_expired);
+	if (ret < 0) {
+		rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret,
+				 rxkad_abort_chall_key_expired);
+		return false;
+	}
 
 	if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
-			  &challenge, sizeof(challenge)) < 0)
-		return rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO,
-					rxkad_abort_chall_short);
+			  &challenge, sizeof(challenge)) < 0) {
+		rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO,
+				 rxkad_abort_chall_short);
+		return false;
+	}
 
 	version = ntohl(challenge.version);
-	nonce = ntohl(challenge.nonce);
+	sp->chall.rxkad_nonce = ntohl(challenge.nonce);
 	min_level = ntohl(challenge.min_level);
 
-	trace_rxrpc_rx_challenge(conn, sp->hdr.serial, version, nonce, min_level);
+	trace_rxrpc_rx_challenge(conn, sp->hdr.serial, version,
+				 sp->chall.rxkad_nonce, min_level);
+
+	if (version != RXKAD_VERSION) {
+		rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO,
+				 rxkad_abort_chall_version);
+		return false;
+	}
 
-	if (version != RXKAD_VERSION)
-		return rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO,
-					rxkad_abort_chall_version);
+	if (conn->security_level < min_level) {
+		rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EACCES,
+				 rxkad_abort_chall_level);
+		return false;
+	}
+	return true;
+}
+
+/*
+ * Insert the header into the response.
+ */
+static noinline
+int rxkad_insert_response_header(struct rxrpc_connection *conn,
+				 const struct rxrpc_key_token *token,
+				 struct sk_buff *challenge,
+				 struct sk_buff *response,
+				 size_t *offset)
+{
+	struct rxrpc_skb_priv *csp = rxrpc_skb(challenge);
+	struct {
+		struct rxrpc_wire_header whdr;
+		struct rxkad_response	resp;
+	} h;
+	int ret;
 
-	if (conn->security_level < min_level)
-		return rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EACCES,
-					rxkad_abort_chall_level);
+	h.whdr.epoch			= htonl(conn->proto.epoch);
+	h.whdr.cid			= htonl(conn->proto.cid);
+	h.whdr.callNumber		= 0;
+	h.whdr.serial			= 0;
+	h.whdr.seq			= 0;
+	h.whdr.type			= RXRPC_PACKET_TYPE_RESPONSE;
+	h.whdr.flags			= conn->out_clientflag;
+	h.whdr.userStatus		= 0;
+	h.whdr.securityIndex		= conn->security_ix;
+	h.whdr.cksum			= 0;
+	h.whdr.serviceId		= htons(conn->service_id);
+	h.resp.version			= htonl(RXKAD_VERSION);
+	h.resp.__pad			= 0;
+	h.resp.encrypted.epoch		= htonl(conn->proto.epoch);
+	h.resp.encrypted.cid		= htonl(conn->proto.cid);
+	h.resp.encrypted.checksum	= 0;
+	h.resp.encrypted.securityIndex	= htonl(conn->security_ix);
+	h.resp.encrypted.call_id[0]	= htonl(conn->channels[0].call_counter);
+	h.resp.encrypted.call_id[1]	= htonl(conn->channels[1].call_counter);
+	h.resp.encrypted.call_id[2]	= htonl(conn->channels[2].call_counter);
+	h.resp.encrypted.call_id[3]	= htonl(conn->channels[3].call_counter);
+	h.resp.encrypted.inc_nonce	= htonl(csp->chall.rxkad_nonce + 1);
+	h.resp.encrypted.level		= htonl(conn->security_level);
+	h.resp.kvno			= htonl(token->kad->kvno);
+	h.resp.ticket_len		= htonl(token->kad->ticket_len);
+
+	rxkad_calc_response_checksum(&h.resp);
+
+	ret = skb_store_bits(response, *offset, &h, sizeof(h));
+	*offset += sizeof(h);
+	return ret;
+}
+
+/*
+ * respond to a challenge packet
+ */
+static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
+				      struct sk_buff *challenge)
+{
+	const struct rxrpc_key_token *token;
+	struct rxrpc_skb_priv *csp, *rsp;
+	struct sk_buff *response;
+	size_t len, offset = 0;
+	int ret = -EPROTO;
+
+	_enter("{%d,%x}", conn->debug_id, key_serial(conn->key));
+
+	ret = key_validate(conn->key);
+	if (ret < 0)
+		return rxrpc_abort_conn(conn, challenge, RXKADEXPIRED, ret,
+					rxkad_abort_chall_key_expired);
 
 	token = conn->key->payload.data[0];
 
 	/* build the response packet */
-	resp = kzalloc(sizeof(struct rxkad_response), GFP_NOFS);
-	if (!resp)
-		return -ENOMEM;
+	len = sizeof(struct rxrpc_wire_header) +
+		sizeof(struct rxkad_response) +
+		token->kad->ticket_len;
+
+	response = alloc_skb_with_frags(0, len, 0, &ret, GFP_NOFS);
+	if (!response)
+		goto error;
+	rxrpc_new_skb(response, rxrpc_skb_new_response_rxkad);
+	response->len = len;
+	response->data_len = len;
+
+	offset = 0;
+	ret = rxkad_insert_response_header(conn, token, challenge, response,
+					   &offset);
+	if (ret < 0)
+		goto error;
+
+	ret = rxkad_encrypt_response(conn, response, token->kad);
+	if (ret < 0)
+		goto error;
+
+	ret = skb_store_bits(response, offset, token->kad->ticket,
+			     token->kad->ticket_len);
+	if (ret < 0)
+		goto error;
 
-	resp->version			= htonl(RXKAD_VERSION);
-	resp->encrypted.epoch		= htonl(conn->proto.epoch);
-	resp->encrypted.cid		= htonl(conn->proto.cid);
-	resp->encrypted.securityIndex	= htonl(conn->security_ix);
-	resp->encrypted.inc_nonce	= htonl(nonce + 1);
-	resp->encrypted.level		= htonl(conn->security_level);
-	resp->kvno			= htonl(token->kad->kvno);
-	resp->ticket_len		= htonl(token->kad->ticket_len);
-	resp->encrypted.call_id[0]	= htonl(conn->channels[0].call_counter);
-	resp->encrypted.call_id[1]	= htonl(conn->channels[1].call_counter);
-	resp->encrypted.call_id[2]	= htonl(conn->channels[2].call_counter);
-	resp->encrypted.call_id[3]	= htonl(conn->channels[3].call_counter);
-
-	/* calculate the response checksum and then do the encryption */
-	rxkad_calc_response_checksum(resp);
-	ret = rxkad_encrypt_response(conn, resp, token->kad);
-	if (ret == 0)
-		ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad);
-	kfree(resp);
+	csp = rxrpc_skb(challenge);
+	rsp = rxrpc_skb(response);
+	rsp->resp.len = len;
+	rsp->resp.challenge_serial = csp->hdr.serial;
+	rxrpc_post_response(conn, response);
+	response = NULL;
+	ret = 0;
+
+error:
+	rxrpc_free_skb(response, rxrpc_skb_put_response);
 	return ret;
 }
 
 /*
+ * RxKAD does automatic response only as there's nothing to manage that isn't
+ * already in the key.
+ */
+static int rxkad_sendmsg_respond_to_challenge(struct sk_buff *challenge,
+					      struct msghdr *msg)
+{
+	return -EINVAL;
+}
+
+/**
+ * rxkad_kernel_respond_to_challenge - Respond to a challenge with appdata
+ * @challenge: The challenge to respond to
+ *
+ * Allow a kernel application to respond to a CHALLENGE.
+ *
+ * Return: %0 if successful and a negative error code otherwise.
+ */
+int rxkad_kernel_respond_to_challenge(struct sk_buff *challenge)
+{
+	struct rxrpc_skb_priv *csp = rxrpc_skb(challenge);
+
+	return rxkad_respond_to_challenge(csp->chall.conn, challenge);
+}
+EXPORT_SYMBOL(rxkad_kernel_respond_to_challenge);
+
+/*
  * decrypt the kerberos IV ticket in the response
  */
 static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
@@ -1276,6 +1350,8 @@ const struct rxrpc_security rxkad = {
 	.verify_packet			= rxkad_verify_packet,
 	.free_call_crypto		= rxkad_free_call_crypto,
 	.issue_challenge		= rxkad_issue_challenge,
+	.validate_challenge		= rxkad_validate_challenge,
+	.sendmsg_respond_to_challenge	= rxkad_sendmsg_respond_to_challenge,
 	.respond_to_challenge		= rxkad_respond_to_challenge,
 	.verify_response		= rxkad_verify_response,
 	.clear				= rxkad_clear,
diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c
index e848a4777b8c..0377301156b0 100644
--- a/net/rxrpc/rxperf.c
+++ b/net/rxrpc/rxperf.c
@@ -8,6 +8,7 @@
 #define pr_fmt(fmt) "rxperf: " fmt
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <crypto/krb5.h>
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #define RXRPC_TRACE_ONLY_DEFINE_ENUMS
@@ -136,6 +137,12 @@ static void rxperf_notify_end_reply_tx(struct sock *sock,
 			      RXPERF_CALL_SV_AWAIT_ACK);
 }
 
+static const struct rxrpc_kernel_ops rxperf_rxrpc_callback_ops = {
+	.notify_new_call	= rxperf_rx_new_call,
+	.discard_new_call	= rxperf_rx_discard_new_call,
+	.user_attach_call	= rxperf_rx_attach,
+};
+
 /*
  * Charge the incoming call preallocation.
  */
@@ -161,7 +168,6 @@ static void rxperf_charge_preallocation(struct work_struct *work)
 
 		if (rxrpc_kernel_charge_accept(rxperf_socket,
 					       rxperf_notify_rx,
-					       rxperf_rx_attach,
 					       (unsigned long)call,
 					       GFP_KERNEL,
 					       call->debug_id) < 0)
@@ -209,8 +215,7 @@ static int rxperf_open_socket(void)
 	if (ret < 0)
 		goto error_2;
 
-	rxrpc_kernel_new_call_notification(socket, rxperf_rx_new_call,
-					   rxperf_rx_discard_new_call);
+	rxrpc_kernel_set_notifications(socket, &rxperf_rxrpc_callback_ops);
 
 	ret = kernel_listen(socket, INT_MAX);
 	if (ret < 0)
@@ -546,9 +551,9 @@ static int rxperf_process_call(struct rxperf_call *call)
 }
 
 /*
- * Add a key to the security keyring.
+ * Add an rxkad key to the security keyring.
  */
-static int rxperf_add_key(struct key *keyring)
+static int rxperf_add_rxkad_key(struct key *keyring)
 {
 	key_ref_t kref;
 	int ret;
@@ -574,6 +579,47 @@ static int rxperf_add_key(struct key *keyring)
 	return ret;
 }
 
+#ifdef CONFIG_RXGK
+/*
+ * Add a yfs-rxgk key to the security keyring.
+ */
+static int rxperf_add_yfs_rxgk_key(struct key *keyring, u32 enctype)
+{
+	const struct krb5_enctype *krb5 = crypto_krb5_find_enctype(enctype);
+	key_ref_t kref;
+	char name[64];
+	int ret;
+	u8 key[32];
+
+	if (!krb5 || krb5->key_len > sizeof(key))
+		return 0;
+
+	/* The key is just { 0, 1, 2, 3, 4, ... } */
+	for (int i = 0; i < krb5->key_len; i++)
+		key[i] = i;
+
+	sprintf(name, "%u:6:1:%u", RX_PERF_SERVICE, enctype);
+
+	kref = key_create_or_update(make_key_ref(keyring, true),
+				    "rxrpc_s", name,
+				    key, krb5->key_len,
+				    KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH |
+				    KEY_USR_VIEW,
+				    KEY_ALLOC_NOT_IN_QUOTA);
+
+	if (IS_ERR(kref)) {
+		pr_err("Can't allocate rxperf server key: %ld\n", PTR_ERR(kref));
+		return PTR_ERR(kref);
+	}
+
+	ret = key_link(keyring, key_ref_to_ptr(kref));
+	if (ret < 0)
+		pr_err("Can't link rxperf server key: %d\n", ret);
+	key_ref_put(kref);
+	return ret;
+}
+#endif
+
 /*
  * Initialise the rxperf server.
  */
@@ -603,9 +649,29 @@ static int __init rxperf_init(void)
 		goto error_keyring;
 	}
 	rxperf_sec_keyring = keyring;
-	ret = rxperf_add_key(keyring);
+	ret = rxperf_add_rxkad_key(keyring);
+	if (ret < 0)
+		goto error_key;
+#ifdef CONFIG_RXGK
+	ret = rxperf_add_yfs_rxgk_key(keyring, KRB5_ENCTYPE_AES128_CTS_HMAC_SHA1_96);
+	if (ret < 0)
+		goto error_key;
+	ret = rxperf_add_yfs_rxgk_key(keyring, KRB5_ENCTYPE_AES256_CTS_HMAC_SHA1_96);
+	if (ret < 0)
+		goto error_key;
+	ret = rxperf_add_yfs_rxgk_key(keyring, KRB5_ENCTYPE_AES128_CTS_HMAC_SHA256_128);
+	if (ret < 0)
+		goto error_key;
+	ret = rxperf_add_yfs_rxgk_key(keyring, KRB5_ENCTYPE_AES256_CTS_HMAC_SHA384_192);
+	if (ret < 0)
+		goto error_key;
+	ret = rxperf_add_yfs_rxgk_key(keyring, KRB5_ENCTYPE_CAMELLIA128_CTS_CMAC);
+	if (ret < 0)
+		goto error_key;
+	ret = rxperf_add_yfs_rxgk_key(keyring, KRB5_ENCTYPE_CAMELLIA256_CTS_CMAC);
 	if (ret < 0)
 		goto error_key;
+#endif
 
 	ret = rxperf_open_socket();
 	if (ret < 0)
diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c
index 9784adc8f275..078d91a6b77f 100644
--- a/net/rxrpc/security.c
+++ b/net/rxrpc/security.c
@@ -20,6 +20,9 @@ static const struct rxrpc_security *rxrpc_security_types[] = {
 #ifdef CONFIG_RXKAD
 	[RXRPC_SECURITY_RXKAD]	= &rxkad,
 #endif
+#ifdef CONFIG_RXGK
+	[RXRPC_SECURITY_YFS_RXGK] = &rxgk_yfs,
+#endif
 };
 
 int __init rxrpc_init_security(void)
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 84dc6c94f23b..ebbb78b842de 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -607,7 +607,7 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p)
 static struct rxrpc_call *
 rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 				  struct rxrpc_send_params *p)
-	__releases(&rx->sk.sk_lock.slock)
+	__releases(&rx->sk.sk_lock)
 	__acquires(&call->user_mutex)
 {
 	struct rxrpc_conn_parameters cp;
@@ -657,7 +657,6 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
  * - the socket may be either a client socket or a server socket
  */
 int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
-	__releases(&rx->sk.sk_lock.slock)
 {
 	struct rxrpc_call *call;
 	bool dropped_lock = false;
@@ -759,14 +758,21 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 	if (rxrpc_call_is_complete(call)) {
 		/* it's too late for this call */
 		ret = -ESHUTDOWN;
-	} else if (p.command == RXRPC_CMD_SEND_ABORT) {
+		goto out_put_unlock;
+	}
+
+	switch (p.command) {
+	case RXRPC_CMD_SEND_ABORT:
 		rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED,
 				    rxrpc_abort_call_sendmsg);
 		ret = 0;
-	} else if (p.command != RXRPC_CMD_SEND_DATA) {
-		ret = -EINVAL;
-	} else {
+		break;
+	case RXRPC_CMD_SEND_DATA:
 		ret = rxrpc_send_data(rx, call, msg, len, NULL, &dropped_lock);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
 	}
 
 out_put_unlock:
@@ -794,6 +800,8 @@ error_release_sock:
  * appropriate to sending data.  No control data should be supplied in @msg,
  * nor should an address be supplied.  MSG_MORE should be flagged if there's
  * more data to come, otherwise this data will end the transmission phase.
+ *
+ * Return: %0 if successful and a negative error code otherwise.
  */
 int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
 			   struct msghdr *msg, size_t len,
@@ -829,8 +837,9 @@ EXPORT_SYMBOL(rxrpc_kernel_send_data);
  * @error: Local error value
  * @why: Indication as to why.
  *
- * Allow a kernel service to abort a call, if it's still in an abortable state
- * and return true if the call was aborted, false if it was already complete.
+ * Allow a kernel service to abort a call if it's still in an abortable state.
+ *
+ * Return: %true if the call was aborted, %false if it was already complete.
  */
 bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
 			     u32 abort_code, int error, enum rxrpc_abort_reason why)
diff --git a/net/rxrpc/server_key.c b/net/rxrpc/server_key.c
index e51940589ee5..36b05fd842a7 100644
--- a/net/rxrpc/server_key.c
+++ b/net/rxrpc/server_key.c
@@ -152,6 +152,8 @@ int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen)
  *
  * Set the server security keyring on an rxrpc socket.  This is used to provide
  * the encryption keys for a kernel service.
+ *
+ * Return: %0 if successful and a negative error code otherwise.
  */
 int rxrpc_sock_set_security_keyring(struct sock *sk, struct key *keyring)
 {
@@ -169,3 +171,43 @@ int rxrpc_sock_set_security_keyring(struct sock *sk, struct key *keyring)
 	return ret;
 }
 EXPORT_SYMBOL(rxrpc_sock_set_security_keyring);
+
+/**
+ * rxrpc_sock_set_manage_response - Set the manage-response flag for a kernel service
+ * @sk: The socket to set the keyring on
+ * @set: True to set, false to clear the flag
+ *
+ * Set the flag on an rxrpc socket to say that the caller wants to manage the
+ * RESPONSE packet and the user-defined data it may contain.  Setting this
+ * means that recvmsg() will return messages with RXRPC_CHALLENGED in the
+ * control message buffer containing information about the challenge.
+ *
+ * The user should respond to the challenge by passing RXRPC_RESPOND or
+ * RXRPC_RESPOND_ABORT control messages with sendmsg() to the same call.
+ * Supplementary control messages, such as RXRPC_RESP_RXGK_APPDATA, may be
+ * included to indicate the parts the user wants to supply.
+ *
+ * The server will be passed the response data with a RXRPC_RESPONDED control
+ * message when it gets the first data from each call.
+ *
+ * Note that this is only honoured by security classes that need auxiliary data
+ * (e.g. RxGK).  Those that don't offer the facility (e.g. RxKAD) respond
+ * without consulting userspace.
+ *
+ * Return: The previous setting.
+ */
+int rxrpc_sock_set_manage_response(struct sock *sk, bool set)
+{
+	struct rxrpc_sock *rx = rxrpc_sk(sk);
+	int ret;
+
+	lock_sock(sk);
+	ret = !!test_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags);
+	if (set)
+		set_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags);
+	else
+		clear_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags);
+	release_sock(sk);
+	return ret;
+}
+EXPORT_SYMBOL(rxrpc_sock_set_manage_response);
diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c
index c550991d48fa..29767038691a 100644
--- a/net/rxrpc/txbuf.c
+++ b/net/rxrpc/txbuf.c
@@ -60,14 +60,6 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_
 	return txb;
 }
 
-void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what)
-{
-	int r;
-
-	__refcount_inc(&txb->ref, &r);
-	trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r + 1, what);
-}
-
 void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what)
 {
 	int r = refcount_read(&txb->ref);
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index a800127effcd..ad914d2b2e22 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -403,6 +403,18 @@ config NET_SCH_ETS
 
 	  If unsure, say N.
 
+config NET_SCH_BPF
+	bool "BPF-based Qdisc"
+	depends on BPF_SYSCALL && BPF_JIT && DEBUG_INFO_BTF
+	help
+	  This option allows BPF-based queueing disiplines. With BPF struct_ops,
+	  users can implement supported operators in Qdisc_ops using BPF programs.
+	  The queue holding skb can be built with BPF maps or graphs.
+
+	  Say Y here if you want to use BPF-based Qdisc.
+
+	  If unsure, say N.
+
 menuconfig NET_SCH_DEFAULT
 	bool "Allow override default queue discipline"
 	help
@@ -784,7 +796,7 @@ config NET_ACT_SKBEDIT
 config NET_ACT_CSUM
 	tristate "Checksum Updating"
 	depends on NET_CLS_ACT && INET
-	select CRC32
+	select NET_CRC32C
 	help
 	  Say Y here to update some common checksum after some direct
 	  packet alterations.
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 82c3f78ca486..904d784902d1 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -62,6 +62,7 @@ obj-$(CONFIG_NET_SCH_FQ_PIE)	+= sch_fq_pie.o
 obj-$(CONFIG_NET_SCH_CBS)	+= sch_cbs.o
 obj-$(CONFIG_NET_SCH_ETF)	+= sch_etf.o
 obj-$(CONFIG_NET_SCH_TAPRIO)	+= sch_taprio.o
+obj-$(CONFIG_NET_SCH_BPF)	+= bpf_qdisc.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 839790043256..057e20cef375 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1461,17 +1461,29 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct netlink_ext_ack *extack)
 {
 	struct tc_action_ops *ops[TCA_ACT_MAX_PRIO] = {};
-	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
+	struct nlattr *tb[TCA_ACT_MAX_PRIO + 2];
 	struct tc_action *act;
 	size_t sz = 0;
 	int err;
 	int i;
 
-	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX_PRIO, nla, NULL,
+	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX_PRIO + 1, nla, NULL,
 					  extack);
 	if (err < 0)
 		return err;
 
+	/* The nested attributes are parsed as types, but they are really an
+	 * array of actions. So we parse one more than we can handle, and return
+	 * an error if the last one is set (as that indicates that the request
+	 * contained more than the maximum number of actions).
+	 */
+	if (tb[TCA_ACT_MAX_PRIO + 1]) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "Only %d actions supported per filter",
+				   TCA_ACT_MAX_PRIO);
+		return -EINVAL;
+	}
+
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
 		struct tc_action_ops *a_o;
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 5b3814365924..5f01f567c934 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -30,7 +30,29 @@ static LIST_HEAD(mirred_list);
 static DEFINE_SPINLOCK(mirred_list_lock);
 
 #define MIRRED_NEST_LIMIT    4
-static DEFINE_PER_CPU(unsigned int, mirred_nest_level);
+
+#ifndef CONFIG_PREEMPT_RT
+static u8 tcf_mirred_nest_level_inc_return(void)
+{
+	return __this_cpu_inc_return(softnet_data.xmit.sched_mirred_nest);
+}
+
+static void tcf_mirred_nest_level_dec(void)
+{
+	__this_cpu_dec(softnet_data.xmit.sched_mirred_nest);
+}
+
+#else
+static u8 tcf_mirred_nest_level_inc_return(void)
+{
+	return current->net_xmit.sched_mirred_nest++;
+}
+
+static void tcf_mirred_nest_level_dec(void)
+{
+	current->net_xmit.sched_mirred_nest--;
+}
+#endif
 
 static bool tcf_mirred_is_act_redirect(int action)
 {
@@ -423,7 +445,7 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 	int m_eaction;
 	u32 blockid;
 
-	nest_level = __this_cpu_inc_return(mirred_nest_level);
+	nest_level = tcf_mirred_nest_level_inc_return();
 	if (unlikely(nest_level > MIRRED_NEST_LIMIT)) {
 		net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n",
 				     netdev_name(skb->dev));
@@ -454,7 +476,7 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 				   retval);
 
 dec_nest_level:
-	__this_cpu_dec(mirred_nest_level);
+	tcf_mirred_nest_level_dec();
 
 	return retval;
 }
diff --git a/net/sched/bpf_qdisc.c b/net/sched/bpf_qdisc.c
new file mode 100644
index 000000000000..7ea8b54b2ab1
--- /dev/null
+++ b/net/sched/bpf_qdisc.c
@@ -0,0 +1,475 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/types.h>
+#include <linux/bpf_verifier.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/filter.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+
+#define QDISC_OP_IDX(op)	(offsetof(struct Qdisc_ops, op) / sizeof(void (*)(void)))
+#define QDISC_MOFF_IDX(moff)	(moff / sizeof(void (*)(void)))
+
+static struct bpf_struct_ops bpf_Qdisc_ops;
+
+struct bpf_sched_data {
+	struct qdisc_watchdog watchdog;
+};
+
+struct bpf_sk_buff_ptr {
+	struct sk_buff *skb;
+};
+
+static int bpf_qdisc_init(struct btf *btf)
+{
+	return 0;
+}
+
+BTF_ID_LIST_SINGLE(bpf_qdisc_ids, struct, Qdisc)
+BTF_ID_LIST_SINGLE(bpf_sk_buff_ids, struct, sk_buff)
+BTF_ID_LIST_SINGLE(bpf_sk_buff_ptr_ids, struct, bpf_sk_buff_ptr)
+
+static bool bpf_qdisc_is_valid_access(int off, int size,
+				      enum bpf_access_type type,
+				      const struct bpf_prog *prog,
+				      struct bpf_insn_access_aux *info)
+{
+	struct btf *btf = prog->aux->attach_btf;
+	u32 arg;
+
+	arg = btf_ctx_arg_idx(btf, prog->aux->attach_func_proto, off);
+	if (prog->aux->attach_st_ops_member_off == offsetof(struct Qdisc_ops, enqueue)) {
+		if (arg == 2 && type == BPF_READ) {
+			info->reg_type = PTR_TO_BTF_ID | PTR_TRUSTED;
+			info->btf = btf;
+			info->btf_id = bpf_sk_buff_ptr_ids[0];
+			return true;
+		}
+	}
+
+	return bpf_tracing_btf_ctx_access(off, size, type, prog, info);
+}
+
+static int bpf_qdisc_qdisc_access(struct bpf_verifier_log *log,
+				  const struct bpf_reg_state *reg,
+				  int off, size_t *end)
+{
+	switch (off) {
+	case offsetof(struct Qdisc, limit):
+		*end = offsetofend(struct Qdisc, limit);
+		break;
+	case offsetof(struct Qdisc, q) + offsetof(struct qdisc_skb_head, qlen):
+		*end = offsetof(struct Qdisc, q) + offsetofend(struct qdisc_skb_head, qlen);
+		break;
+	case offsetof(struct Qdisc, qstats) ... offsetofend(struct Qdisc, qstats) - 1:
+		*end = offsetofend(struct Qdisc, qstats);
+		break;
+	default:
+		return -EACCES;
+	}
+
+	return 0;
+}
+
+static int bpf_qdisc_sk_buff_access(struct bpf_verifier_log *log,
+				    const struct bpf_reg_state *reg,
+				    int off, size_t *end)
+{
+	switch (off) {
+	case offsetof(struct sk_buff, tstamp):
+		*end = offsetofend(struct sk_buff, tstamp);
+		break;
+	case offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data[0]) ...
+	     offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb,
+						     data[QDISC_CB_PRIV_LEN - 1]):
+		*end = offsetof(struct sk_buff, cb) +
+		       offsetofend(struct qdisc_skb_cb, data[QDISC_CB_PRIV_LEN - 1]);
+		break;
+	default:
+		return -EACCES;
+	}
+
+	return 0;
+}
+
+static int bpf_qdisc_btf_struct_access(struct bpf_verifier_log *log,
+				       const struct bpf_reg_state *reg,
+				       int off, int size)
+{
+	const struct btf_type *t, *skbt, *qdisct;
+	size_t end;
+	int err;
+
+	skbt = btf_type_by_id(reg->btf, bpf_sk_buff_ids[0]);
+	qdisct = btf_type_by_id(reg->btf, bpf_qdisc_ids[0]);
+	t = btf_type_by_id(reg->btf, reg->btf_id);
+
+	if (t == skbt) {
+		err = bpf_qdisc_sk_buff_access(log, reg, off, &end);
+	} else if (t == qdisct) {
+		err = bpf_qdisc_qdisc_access(log, reg, off, &end);
+	} else {
+		bpf_log(log, "only read is supported\n");
+		return -EACCES;
+	}
+
+	if (err) {
+		bpf_log(log, "no write support to %s at off %d\n",
+			btf_name_by_offset(reg->btf, t->name_off), off);
+		return -EACCES;
+	}
+
+	if (off + size > end) {
+		bpf_log(log,
+			"write access at off %d with size %d beyond the member of %s ended at %zu\n",
+			off, size, btf_name_by_offset(reg->btf, t->name_off), end);
+		return -EACCES;
+	}
+
+	return 0;
+}
+
+BTF_ID_LIST(bpf_qdisc_init_prologue_ids)
+BTF_ID(func, bpf_qdisc_init_prologue)
+
+static int bpf_qdisc_gen_prologue(struct bpf_insn *insn_buf, bool direct_write,
+				  const struct bpf_prog *prog)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	if (prog->aux->attach_st_ops_member_off != offsetof(struct Qdisc_ops, init))
+		return 0;
+
+	/* r6 = r1; // r6 will be "u64 *ctx". r1 is "u64 *ctx".
+	 * r2 = r1[16]; // r2 will be "struct netlink_ext_ack *extack"
+	 * r1 = r1[0]; // r1 will be "struct Qdisc *sch"
+	 * r0 = bpf_qdisc_init_prologue(r1, r2);
+	 * if r0 == 0 goto pc+1;
+	 * BPF_EXIT;
+	 * r1 = r6; // r1 will be "u64 *ctx".
+	 */
+	*insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 16);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0);
+	*insn++ = BPF_CALL_KFUNC(0, bpf_qdisc_init_prologue_ids[0]);
+	*insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1);
+	*insn++ = BPF_EXIT_INSN();
+	*insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
+	*insn++ = prog->insnsi[0];
+
+	return insn - insn_buf;
+}
+
+BTF_ID_LIST(bpf_qdisc_reset_destroy_epilogue_ids)
+BTF_ID(func, bpf_qdisc_reset_destroy_epilogue)
+
+static int bpf_qdisc_gen_epilogue(struct bpf_insn *insn_buf, const struct bpf_prog *prog,
+				  s16 ctx_stack_off)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	if (prog->aux->attach_st_ops_member_off != offsetof(struct Qdisc_ops, reset) &&
+	    prog->aux->attach_st_ops_member_off != offsetof(struct Qdisc_ops, destroy))
+		return 0;
+
+	/* r1 = stack[ctx_stack_off]; // r1 will be "u64 *ctx"
+	 * r1 = r1[0]; // r1 will be "struct Qdisc *sch"
+	 * r0 = bpf_qdisc_reset_destroy_epilogue(r1);
+	 * BPF_EXIT;
+	 */
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_FP, ctx_stack_off);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0);
+	*insn++ = BPF_CALL_KFUNC(0, bpf_qdisc_reset_destroy_epilogue_ids[0]);
+	*insn++ = BPF_EXIT_INSN();
+
+	return insn - insn_buf;
+}
+
+__bpf_kfunc_start_defs();
+
+/* bpf_skb_get_hash - Get the flow hash of an skb.
+ * @skb: The skb to get the flow hash from.
+ */
+__bpf_kfunc u32 bpf_skb_get_hash(struct sk_buff *skb)
+{
+	return skb_get_hash(skb);
+}
+
+/* bpf_kfree_skb - Release an skb's reference and drop it immediately.
+ * @skb: The skb whose reference to be released and dropped.
+ */
+__bpf_kfunc void bpf_kfree_skb(struct sk_buff *skb)
+{
+	kfree_skb(skb);
+}
+
+/* bpf_qdisc_skb_drop - Drop an skb by adding it to a deferred free list.
+ * @skb: The skb whose reference to be released and dropped.
+ * @to_free_list: The list of skbs to be dropped.
+ */
+__bpf_kfunc void bpf_qdisc_skb_drop(struct sk_buff *skb,
+				    struct bpf_sk_buff_ptr *to_free_list)
+{
+	__qdisc_drop(skb, (struct sk_buff **)to_free_list);
+}
+
+/* bpf_qdisc_watchdog_schedule - Schedule a qdisc to a later time using a timer.
+ * @sch: The qdisc to be scheduled.
+ * @expire: The expiry time of the timer.
+ * @delta_ns: The slack range of the timer.
+ */
+__bpf_kfunc void bpf_qdisc_watchdog_schedule(struct Qdisc *sch, u64 expire, u64 delta_ns)
+{
+	struct bpf_sched_data *q = qdisc_priv(sch);
+
+	qdisc_watchdog_schedule_range_ns(&q->watchdog, expire, delta_ns);
+}
+
+/* bpf_qdisc_init_prologue - Hidden kfunc called in prologue of .init. */
+__bpf_kfunc int bpf_qdisc_init_prologue(struct Qdisc *sch,
+					struct netlink_ext_ack *extack)
+{
+	struct bpf_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct Qdisc *p;
+
+	qdisc_watchdog_init(&q->watchdog, sch);
+
+	if (sch->parent != TC_H_ROOT) {
+		/* If qdisc_lookup() returns NULL, it means .init is called by
+		 * qdisc_create_dflt() in mq/mqprio_init and the parent qdisc
+		 * has not been added to qdisc_hash yet.
+		 */
+		p = qdisc_lookup(dev, TC_H_MAJ(sch->parent));
+		if (p && !(p->flags & TCQ_F_MQROOT)) {
+			NL_SET_ERR_MSG(extack, "BPF qdisc only supported on root or mq");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+/* bpf_qdisc_reset_destroy_epilogue - Hidden kfunc called in epilogue of .reset
+ * and .destroy
+ */
+__bpf_kfunc void bpf_qdisc_reset_destroy_epilogue(struct Qdisc *sch)
+{
+	struct bpf_sched_data *q = qdisc_priv(sch);
+
+	qdisc_watchdog_cancel(&q->watchdog);
+}
+
+/* bpf_qdisc_bstats_update - Update Qdisc basic statistics
+ * @sch: The qdisc from which an skb is dequeued.
+ * @skb: The skb to be dequeued.
+ */
+__bpf_kfunc void bpf_qdisc_bstats_update(struct Qdisc *sch, const struct sk_buff *skb)
+{
+	bstats_update(&sch->bstats, skb);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(qdisc_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_skb_get_hash, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfree_skb, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_qdisc_skb_drop, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_dynptr_from_skb, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_qdisc_watchdog_schedule, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_qdisc_init_prologue, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_qdisc_reset_destroy_epilogue, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_qdisc_bstats_update, KF_TRUSTED_ARGS)
+BTF_KFUNCS_END(qdisc_kfunc_ids)
+
+BTF_SET_START(qdisc_common_kfunc_set)
+BTF_ID(func, bpf_skb_get_hash)
+BTF_ID(func, bpf_kfree_skb)
+BTF_ID(func, bpf_dynptr_from_skb)
+BTF_SET_END(qdisc_common_kfunc_set)
+
+BTF_SET_START(qdisc_enqueue_kfunc_set)
+BTF_ID(func, bpf_qdisc_skb_drop)
+BTF_ID(func, bpf_qdisc_watchdog_schedule)
+BTF_SET_END(qdisc_enqueue_kfunc_set)
+
+BTF_SET_START(qdisc_dequeue_kfunc_set)
+BTF_ID(func, bpf_qdisc_watchdog_schedule)
+BTF_ID(func, bpf_qdisc_bstats_update)
+BTF_SET_END(qdisc_dequeue_kfunc_set)
+
+enum qdisc_ops_kf_flags {
+	QDISC_OPS_KF_COMMON		= 0,
+	QDISC_OPS_KF_ENQUEUE		= 1 << 0,
+	QDISC_OPS_KF_DEQUEUE		= 1 << 1,
+};
+
+static const u32 qdisc_ops_context_flags[] = {
+	[QDISC_OP_IDX(enqueue)]		= QDISC_OPS_KF_ENQUEUE,
+	[QDISC_OP_IDX(dequeue)]		= QDISC_OPS_KF_DEQUEUE,
+	[QDISC_OP_IDX(init)]		= QDISC_OPS_KF_COMMON,
+	[QDISC_OP_IDX(reset)]		= QDISC_OPS_KF_COMMON,
+	[QDISC_OP_IDX(destroy)]		= QDISC_OPS_KF_COMMON,
+};
+
+static int bpf_qdisc_kfunc_filter(const struct bpf_prog *prog, u32 kfunc_id)
+{
+	u32 moff, flags;
+
+	if (!btf_id_set8_contains(&qdisc_kfunc_ids, kfunc_id))
+		return 0;
+
+	if (prog->aux->st_ops != &bpf_Qdisc_ops)
+		return -EACCES;
+
+	moff = prog->aux->attach_st_ops_member_off;
+	flags = qdisc_ops_context_flags[QDISC_MOFF_IDX(moff)];
+
+	if ((flags & QDISC_OPS_KF_ENQUEUE) &&
+	    btf_id_set_contains(&qdisc_enqueue_kfunc_set, kfunc_id))
+		return 0;
+
+	if ((flags & QDISC_OPS_KF_DEQUEUE) &&
+	    btf_id_set_contains(&qdisc_dequeue_kfunc_set, kfunc_id))
+		return 0;
+
+	if (btf_id_set_contains(&qdisc_common_kfunc_set, kfunc_id))
+		return 0;
+
+	return -EACCES;
+}
+
+static const struct btf_kfunc_id_set bpf_qdisc_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &qdisc_kfunc_ids,
+	.filter = bpf_qdisc_kfunc_filter,
+};
+
+static const struct bpf_verifier_ops bpf_qdisc_verifier_ops = {
+	.get_func_proto		= bpf_base_func_proto,
+	.is_valid_access	= bpf_qdisc_is_valid_access,
+	.btf_struct_access	= bpf_qdisc_btf_struct_access,
+	.gen_prologue		= bpf_qdisc_gen_prologue,
+	.gen_epilogue		= bpf_qdisc_gen_epilogue,
+};
+
+static int bpf_qdisc_init_member(const struct btf_type *t,
+				 const struct btf_member *member,
+				 void *kdata, const void *udata)
+{
+	const struct Qdisc_ops *uqdisc_ops;
+	struct Qdisc_ops *qdisc_ops;
+	u32 moff;
+
+	uqdisc_ops = (const struct Qdisc_ops *)udata;
+	qdisc_ops = (struct Qdisc_ops *)kdata;
+
+	moff = __btf_member_bit_offset(t, member) / 8;
+	switch (moff) {
+	case offsetof(struct Qdisc_ops, priv_size):
+		if (uqdisc_ops->priv_size)
+			return -EINVAL;
+		qdisc_ops->priv_size = sizeof(struct bpf_sched_data);
+		return 1;
+	case offsetof(struct Qdisc_ops, peek):
+		qdisc_ops->peek = qdisc_peek_dequeued;
+		return 0;
+	case offsetof(struct Qdisc_ops, id):
+		if (bpf_obj_name_cpy(qdisc_ops->id, uqdisc_ops->id,
+				     sizeof(qdisc_ops->id)) <= 0)
+			return -EINVAL;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int bpf_qdisc_reg(void *kdata, struct bpf_link *link)
+{
+	return register_qdisc(kdata);
+}
+
+static void bpf_qdisc_unreg(void *kdata, struct bpf_link *link)
+{
+	return unregister_qdisc(kdata);
+}
+
+static int bpf_qdisc_validate(void *kdata)
+{
+	struct Qdisc_ops *ops = (struct Qdisc_ops *)kdata;
+
+	if (!ops->enqueue || !ops->dequeue || !ops->init ||
+	    !ops->reset || !ops->destroy)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int Qdisc_ops__enqueue(struct sk_buff *skb__ref, struct Qdisc *sch,
+			      struct sk_buff **to_free)
+{
+	return 0;
+}
+
+static struct sk_buff *Qdisc_ops__dequeue(struct Qdisc *sch)
+{
+	return NULL;
+}
+
+static int Qdisc_ops__init(struct Qdisc *sch, struct nlattr *arg,
+			   struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static void Qdisc_ops__reset(struct Qdisc *sch)
+{
+}
+
+static void Qdisc_ops__destroy(struct Qdisc *sch)
+{
+}
+
+static struct Qdisc_ops __bpf_ops_qdisc_ops = {
+	.enqueue = Qdisc_ops__enqueue,
+	.dequeue = Qdisc_ops__dequeue,
+	.init = Qdisc_ops__init,
+	.reset = Qdisc_ops__reset,
+	.destroy = Qdisc_ops__destroy,
+};
+
+static struct bpf_struct_ops bpf_Qdisc_ops = {
+	.verifier_ops = &bpf_qdisc_verifier_ops,
+	.reg = bpf_qdisc_reg,
+	.unreg = bpf_qdisc_unreg,
+	.validate = bpf_qdisc_validate,
+	.init_member = bpf_qdisc_init_member,
+	.init = bpf_qdisc_init,
+	.name = "Qdisc_ops",
+	.cfi_stubs = &__bpf_ops_qdisc_ops,
+	.owner = THIS_MODULE,
+};
+
+BTF_ID_LIST(bpf_sk_buff_dtor_ids)
+BTF_ID(func, bpf_kfree_skb)
+
+static int __init bpf_qdisc_kfunc_init(void)
+{
+	int ret;
+	const struct btf_id_dtor_kfunc skb_kfunc_dtors[] = {
+		{
+			.btf_id       = bpf_sk_buff_ids[0],
+			.kfunc_btf_id = bpf_sk_buff_dtor_ids[0]
+		},
+	};
+
+	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_qdisc_kfunc_set);
+	ret = ret ?: register_btf_id_dtor_kfuncs(skb_kfunc_dtors,
+						 ARRAY_SIZE(skb_kfunc_dtors),
+						 THIS_MODULE);
+	ret = ret ?: register_bpf_struct_ops(&bpf_Qdisc_ops, Qdisc_ops);
+
+	return ret;
+}
+late_initcall(bpf_qdisc_kfunc_init);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index f74a097f54ae..c5e3673aadbe 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -25,6 +25,7 @@
 #include <linux/hrtimer.h>
 #include <linux/slab.h>
 #include <linux/hashtable.h>
+#include <linux/bpf.h>
 
 #include <net/netdev_lock.h>
 #include <net/net_namespace.h>
@@ -207,7 +208,7 @@ static struct Qdisc_ops *qdisc_lookup_default(const char *name)
 
 	for (q = qdisc_base; q; q = q->next) {
 		if (!strcmp(name, q->id)) {
-			if (!try_module_get(q->owner))
+			if (!bpf_try_module_get(q, q->owner))
 				q = NULL;
 			break;
 		}
@@ -237,7 +238,7 @@ int qdisc_set_default(const char *name)
 
 	if (ops) {
 		/* Set new default */
-		module_put(default_qdisc_ops->owner);
+		bpf_module_put(default_qdisc_ops, default_qdisc_ops->owner);
 		default_qdisc_ops = ops;
 	}
 	write_unlock(&qdisc_mod_lock);
@@ -359,7 +360,7 @@ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind)
 		read_lock(&qdisc_mod_lock);
 		for (q = qdisc_base; q; q = q->next) {
 			if (nla_strcmp(kind, q->id) == 0) {
-				if (!try_module_get(q->owner))
+				if (!bpf_try_module_get(q, q->owner))
 					q = NULL;
 				break;
 			}
@@ -1370,7 +1371,7 @@ err_out3:
 	netdev_put(dev, &sch->dev_tracker);
 	qdisc_free(sch);
 err_out2:
-	module_put(ops->owner);
+	bpf_module_put(ops, ops->owner);
 err_out:
 	*errp = err;
 	return NULL;
@@ -1782,7 +1783,7 @@ static void request_qdisc_module(struct nlattr *kind)
 
 	ops = qdisc_lookup_ops(kind);
 	if (ops) {
-		module_put(ops->owner);
+		bpf_module_put(ops, ops->owner);
 		return;
 	}
 
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 12dd71139da3..c93761040c6e 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -144,7 +144,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt,
 
 	qlen = sch->q.qlen;
 	while (sch->q.qlen > sch->limit) {
-		struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
+		struct sk_buff *skb = qdisc_dequeue_internal(sch, true);
 
 		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index e0a81d313aa7..9b6d79bd8737 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -35,6 +35,11 @@ struct drr_sched {
 	struct Qdisc_class_hash		clhash;
 };
 
+static bool cl_is_active(struct drr_class *cl)
+{
+	return !list_empty(&cl->alist);
+}
+
 static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
 {
 	struct drr_sched *q = qdisc_priv(sch);
@@ -337,7 +342,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	struct drr_sched *q = qdisc_priv(sch);
 	struct drr_class *cl;
 	int err = 0;
-	bool first;
 
 	cl = drr_classify(skb, sch, &err);
 	if (cl == NULL) {
@@ -347,7 +351,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		return err;
 	}
 
-	first = !cl->qdisc->q.qlen;
 	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
@@ -357,7 +360,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		return err;
 	}
 
-	if (first) {
+	if (!cl_is_active(cl)) {
 		list_add_tail(&cl->alist, &q->active);
 		cl->deficit = cl->quantum;
 	}
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index c3bdeb14185b..2c069f0181c6 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -74,6 +74,11 @@ static const struct nla_policy ets_class_policy[TCA_ETS_MAX + 1] = {
 	[TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 },
 };
 
+static bool cl_is_active(struct ets_class *cl)
+{
+	return !list_empty(&cl->alist);
+}
+
 static int ets_quantum_parse(struct Qdisc *sch, const struct nlattr *attr,
 			     unsigned int *quantum,
 			     struct netlink_ext_ack *extack)
@@ -416,7 +421,6 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	struct ets_sched *q = qdisc_priv(sch);
 	struct ets_class *cl;
 	int err = 0;
-	bool first;
 
 	cl = ets_classify(skb, sch, &err);
 	if (!cl) {
@@ -426,7 +430,6 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		return err;
 	}
 
-	first = !cl->qdisc->q.qlen;
 	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
@@ -436,7 +439,7 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		return err;
 	}
 
-	if (first && !ets_class_is_strict(q, cl)) {
+	if (!cl_is_active(cl) && !ets_class_is_strict(q, cl)) {
 		list_add_tail(&cl->alist, &q->active);
 		cl->deficit = cl->quantum;
 	}
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 2ca5332cfcc5..902ff5470607 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -1136,7 +1136,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
 		sch_tree_lock(sch);
 	}
 	while (sch->q.qlen > sch->limit) {
-		struct sk_buff *skb = fq_dequeue(sch);
+		struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
 
 		if (!skb)
 			break;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 6c9029f71e88..2a0f3a513bfa 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -441,7 +441,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
 
 	while (sch->q.qlen > sch->limit ||
 	       q->memory_usage > q->memory_limit) {
-		struct sk_buff *skb = fq_codel_dequeue(sch);
+		struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
 
 		q->cstats.drop_len += qdisc_pkt_len(skb);
 		rtnl_kfree_skbs(skb, skb);
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index f3b8203d3e85..df7fac95ab15 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -366,7 +366,7 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
 
 	/* Drop excess packets if new limit is lower */
 	while (sch->q.qlen > sch->limit) {
-		struct sk_buff *skb = fq_pie_qdisc_dequeue(sch);
+		struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
 
 		len_dropped += qdisc_pkt_len(skb);
 		num_dropped += 1;
diff --git a/net/sched/sch_frag.c b/net/sched/sch_frag.c
index ce63414185fd..d1d87dce7f3f 100644
--- a/net/sched/sch_frag.c
+++ b/net/sched/sch_frag.c
@@ -16,14 +16,18 @@ struct sch_frag_data {
 	unsigned int l2_len;
 	u8 l2_data[VLAN_ETH_HLEN];
 	int (*xmit)(struct sk_buff *skb);
+	local_lock_t bh_lock;
 };
 
-static DEFINE_PER_CPU(struct sch_frag_data, sch_frag_data_storage);
+static DEFINE_PER_CPU(struct sch_frag_data, sch_frag_data_storage) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 static int sch_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct sch_frag_data *data = this_cpu_ptr(&sch_frag_data_storage);
 
+	lockdep_assert_held(&data->bh_lock);
 	if (skb_cow_head(skb, data->l2_len) < 0) {
 		kfree_skb(skb);
 		return -ENOMEM;
@@ -95,6 +99,7 @@ static int sch_fragment(struct net *net, struct sk_buff *skb,
 		struct rtable sch_frag_rt = { 0 };
 		unsigned long orig_dst;
 
+		local_lock_nested_bh(&sch_frag_data_storage.bh_lock);
 		sch_frag_prepare_frag(skb, xmit);
 		dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL,
 			 DST_OBSOLETE_NONE, DST_NOCOUNT);
@@ -105,11 +110,13 @@ static int sch_fragment(struct net *net, struct sk_buff *skb,
 		IPCB(skb)->frag_max_size = mru;
 
 		ret = ip_do_fragment(net, skb->sk, skb, sch_frag_xmit);
+		local_unlock_nested_bh(&sch_frag_data_storage.bh_lock);
 		refdst_drop(orig_dst);
 	} else if (skb_protocol(skb, true) == htons(ETH_P_IPV6)) {
 		unsigned long orig_dst;
 		struct rt6_info sch_frag_rt;
 
+		local_lock_nested_bh(&sch_frag_data_storage.bh_lock);
 		sch_frag_prepare_frag(skb, xmit);
 		memset(&sch_frag_rt, 0, sizeof(sch_frag_rt));
 		dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL,
@@ -122,6 +129,7 @@ static int sch_fragment(struct net *net, struct sk_buff *skb,
 
 		ret = ipv6_stub->ipv6_fragment(net, skb->sk, skb,
 					       sch_frag_xmit);
+		local_unlock_nested_bh(&sch_frag_data_storage.bh_lock);
 		refdst_drop(orig_dst);
 	} else {
 		net_warn_ratelimited("Fail frag %s: eth=%x, MRU=%d, MTU=%d\n",
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 514b1b6ac681..08e0e3aff976 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -24,6 +24,7 @@
 #include <linux/if_vlan.h>
 #include <linux/skb_array.h>
 #include <linux/if_macvlan.h>
+#include <linux/bpf.h>
 #include <net/sch_generic.h>
 #include <net/pkt_sched.h>
 #include <net/dst.h>
@@ -1001,14 +1002,14 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
 {
 	struct Qdisc *sch;
 
-	if (!try_module_get(ops->owner)) {
+	if (!bpf_try_module_get(ops, ops->owner)) {
 		NL_SET_ERR_MSG(extack, "Failed to increase module reference counter");
 		return NULL;
 	}
 
 	sch = qdisc_alloc(dev_queue, ops, extack);
 	if (IS_ERR(sch)) {
-		module_put(ops->owner);
+		bpf_module_put(ops, ops->owner);
 		return NULL;
 	}
 	sch->parent = parentid;
@@ -1078,7 +1079,7 @@ static void __qdisc_destroy(struct Qdisc *qdisc)
 		ops->destroy(qdisc);
 
 	lockdep_unregister_key(&qdisc->root_lock_key);
-	module_put(ops->owner);
+	bpf_module_put(ops, ops->owner);
 	netdev_put(dev, &qdisc->dev_tracker);
 
 	trace_qdisc_destroy(qdisc);
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index ce5045eea065..7986145a527c 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -961,6 +961,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 
 	if (cl != NULL) {
 		int old_flags;
+		int len = 0;
 
 		if (parentid) {
 			if (cl->cl_parent &&
@@ -991,9 +992,13 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		if (usc != NULL)
 			hfsc_change_usc(cl, usc, cur_time);
 
+		if (cl->qdisc->q.qlen != 0)
+			len = qdisc_peek_len(cl->qdisc);
+		/* Check queue length again since some qdisc implementations
+		 * (e.g., netem/codel) might empty the queue during the peek
+		 * operation.
+		 */
 		if (cl->qdisc->q.qlen != 0) {
-			int len = qdisc_peek_len(cl->qdisc);
-
 			if (cl->cl_flags & HFSC_RSC) {
 				if (old_flags & HFSC_RSC)
 					update_ed(cl, len);
@@ -1564,7 +1569,10 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 		return err;
 	}
 
-	if (first) {
+	sch->qstats.backlog += len;
+	sch->q.qlen++;
+
+	if (first && !cl->cl_nactive) {
 		if (cl->cl_flags & HFSC_RSC)
 			init_ed(cl, len);
 		if (cl->cl_flags & HFSC_FSC)
@@ -1579,9 +1587,6 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 
 	}
 
-	sch->qstats.backlog += len;
-	sch->q.qlen++;
-
 	return NET_XMIT_SUCCESS;
 }
 
@@ -1636,10 +1641,16 @@ hfsc_dequeue(struct Qdisc *sch)
 		if (cl->qdisc->q.qlen != 0) {
 			/* update ed */
 			next_len = qdisc_peek_len(cl->qdisc);
-			if (realtime)
-				update_ed(cl, next_len);
-			else
-				update_d(cl, next_len);
+			/* Check queue length again since some qdisc implementations
+			 * (e.g., netem/codel) might empty the queue during the peek
+			 * operation.
+			 */
+			if (cl->qdisc->q.qlen != 0) {
+				if (realtime)
+					update_ed(cl, next_len);
+				else
+					update_d(cl, next_len);
+			}
 		} else {
 			/* the class becomes passive */
 			eltree_remove(cl);
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 44d9efe1a96a..5aa434b46707 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -564,7 +564,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt,
 	qlen = sch->q.qlen;
 	prev_backlog = sch->qstats.backlog;
 	while (sch->q.qlen > sch->limit) {
-		struct sk_buff *skb = hhf_dequeue(sch);
+		struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
 
 		rtnl_kfree_skbs(skb, skb);
 	}
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 4b9a639b642e..14bf71f57057 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -348,7 +348,8 @@ static void htb_add_to_wait_tree(struct htb_sched *q,
  */
 static inline void htb_next_rb_node(struct rb_node **n)
 {
-	*n = rb_next(*n);
+	if (*n)
+		*n = rb_next(*n);
 }
 
 /**
@@ -609,8 +610,8 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl)
  */
 static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl)
 {
-	WARN_ON(!cl->prio_activity);
-
+	if (!cl->prio_activity)
+		return;
 	htb_deactivate_prios(q, cl);
 	cl->prio_activity = 0;
 }
@@ -1485,8 +1486,6 @@ static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg)
 {
 	struct htb_class *cl = (struct htb_class *)arg;
 
-	if (!cl->prio_activity)
-		return;
 	htb_deactivate(qdisc_priv(sch), cl);
 }
 
@@ -1740,8 +1739,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg,
 	if (cl->parent)
 		cl->parent->children--;
 
-	if (cl->prio_activity)
-		htb_deactivate(q, cl);
+	htb_deactivate(q, cl);
 
 	if (cl->cmode != HTB_CAN_SEND)
 		htb_safe_rb_erase(&cl->pq_node,
@@ -1949,8 +1947,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			/* turn parent into inner node */
 			qdisc_purge_queue(parent->leaf.q);
 			parent_qdisc = parent->leaf.q;
-			if (parent->prio_activity)
-				htb_deactivate(q, parent);
+			htb_deactivate(q, parent);
 
 			/* remove from evt list because of level change */
 			if (parent->cmode != HTB_CAN_SEND) {
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index 3771d000b30d..ff49a6c97033 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -195,7 +195,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt,
 	/* Drop excess packets if new limit is lower */
 	qlen = sch->q.qlen;
 	while (sch->q.qlen > sch->limit) {
-		struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
+		struct sk_buff *skb = qdisc_dequeue_internal(sch, true);
 
 		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 687a932eb9b2..bf1282cb22eb 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -202,6 +202,11 @@ struct qfq_sched {
  */
 enum update_reason {enqueue, requeue};
 
+static bool cl_is_active(struct qfq_class *cl)
+{
+	return !list_empty(&cl->alist);
+}
+
 static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
@@ -1215,7 +1220,6 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	struct qfq_class *cl;
 	struct qfq_aggregate *agg;
 	int err = 0;
-	bool first;
 
 	cl = qfq_classify(skb, sch, &err);
 	if (cl == NULL) {
@@ -1237,7 +1241,6 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	gso_segs = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
-	first = !cl->qdisc->q.qlen;
 	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		pr_debug("qfq_enqueue: enqueue failed %d\n", err);
@@ -1253,8 +1256,8 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	++sch->q.qlen;
 
 	agg = cl->agg;
-	/* if the queue was not empty, then done here */
-	if (!first) {
+	/* if the class is active, then done here */
+	if (cl_is_active(cl)) {
 		if (unlikely(skb == cl->qdisc->ops->peek(cl->qdisc)) &&
 		    list_first_entry(&agg->active, struct qfq_class, alist)
 		    == cl && cl->deficit < len)
diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig
index d18a72df3654..24d5a35ce894 100644
--- a/net/sctp/Kconfig
+++ b/net/sctp/Kconfig
@@ -7,10 +7,10 @@ menuconfig IP_SCTP
 	tristate "The SCTP Protocol"
 	depends on INET
 	depends on IPV6 || IPV6=n
-	select CRC32
 	select CRYPTO
 	select CRYPTO_HMAC
 	select CRYPTO_SHA1
+	select NET_CRC32C
 	select NET_UDP_TUNNEL
 	help
 	  Stream Control Transmission Protocol
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 760152e751c7..5793d71852b8 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -736,24 +736,6 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 	return peer;
 }
 
-/* Delete a transport address from an association.  */
-void sctp_assoc_del_peer(struct sctp_association *asoc,
-			 const union sctp_addr *addr)
-{
-	struct list_head	*pos;
-	struct list_head	*temp;
-	struct sctp_transport	*transport;
-
-	list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) {
-		transport = list_entry(pos, struct sctp_transport, transports);
-		if (sctp_cmp_addr_exact(addr, &transport->ipaddr)) {
-			/* Do book keeping for removing the peer and free it. */
-			sctp_assoc_rm_peer(asoc, transport);
-			break;
-		}
-	}
-}
-
 /* Lookup a transport by address. */
 struct sctp_transport *sctp_assoc_lookup_paddr(
 					const struct sctp_association *asoc,
diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index 502095173d88..e6f863c031b4 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -111,7 +111,6 @@ int __init sctp_offload_init(void)
 	if (ret)
 		goto ipv4;
 
-	crc32c_csum_stub = &sctp_csum_ops;
 	return ret;
 
 ipv4:
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index f80208edd6a5..3ead591c72fd 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -115,14 +115,6 @@ static void sctp_control_set_owner_w(struct sctp_chunk *chunk)
 	skb->destructor = sctp_control_release_owner;
 }
 
-/* What was the inbound interface for this chunk? */
-int sctp_chunk_iif(const struct sctp_chunk *chunk)
-{
-	struct sk_buff *skb = chunk->skb;
-
-	return SCTP_INPUT_CB(skb)->af->skb_iif(skb);
-}
-
 /* RFC 2960 3.3.2 Initiation (INIT) (1)
  *
  * Note 2: The ECN capable field is reserved for future use of
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 53725ee7ba06..90b75d4ec329 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -8321,7 +8321,7 @@ static int sctp_hash(struct sock *sk)
 
 static void sctp_unhash(struct sock *sk)
 {
-	/* STUB */
+	sock_rps_delete_flow(sk);
 }
 
 /* Check if port is acceptable.  Possibly find first available port.
@@ -9100,7 +9100,8 @@ static void __sctp_write_space(struct sctp_association *asoc)
 		wq = rcu_dereference(sk->sk_wq);
 		if (wq) {
 			if (waitqueue_active(&wq->wait))
-				wake_up_interruptible(&wq->wait);
+				wake_up_interruptible_poll(&wq->wait, EPOLLOUT |
+						EPOLLWRNORM | EPOLLWRBAND);
 
 			/* Note that we try to include the Async I/O support
 			 * here by modeling from the current TCP/UDP code.
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 3e6cb35baf25..3760131f1484 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -362,6 +362,9 @@ static void smc_destruct(struct sock *sk)
 		return;
 }
 
+static struct lock_class_key smc_key;
+static struct lock_class_key smc_slock_key;
+
 void smc_sk_init(struct net *net, struct sock *sk, int protocol)
 {
 	struct smc_sock *smc = smc_sk(sk);
@@ -375,6 +378,8 @@ void smc_sk_init(struct net *net, struct sock *sk, int protocol)
 	INIT_WORK(&smc->connect_work, smc_connect_work);
 	INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
 	INIT_LIST_HEAD(&smc->accept_q);
+	sock_lock_init_class_and_name(sk, "slock-AF_SMC", &smc_slock_key,
+				      "sk_lock-AF_SMC", &smc_key);
 	spin_lock_init(&smc->accept_q_lock);
 	spin_lock_init(&smc->conn.send_lock);
 	sk->sk_prot->hash(sk);
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 95696f42647e..d946bfb424c7 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -485,19 +485,6 @@ int strp_init(struct strparser *strp, struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(strp_init);
 
-/* Sock process lock held (lock_sock) */
-void __strp_unpause(struct strparser *strp)
-{
-	strp->paused = 0;
-
-	if (strp->need_bytes) {
-		if (strp_peek_len(strp) < strp->need_bytes)
-			return;
-	}
-	strp_read_sock(strp);
-}
-EXPORT_SYMBOL_GPL(__strp_unpause);
-
 void strp_unpause(struct strparser *strp)
 {
 	strp->paused = 0;
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 004cdb59f010..7ce5e28a6c03 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1536,13 +1536,9 @@ static ssize_t write_flush(struct file *file, const char __user *buf,
 	 * or by one second if it has already reached the current time.
 	 * Newly added cache entries will always have ->last_refresh greater
 	 * that ->flush_time, so they don't get flushed prematurely.
-	 *
-	 * If someone frequently calls the flush interface, we should
-	 * immediately clean the corresponding cache_detail instead of
-	 * continuously accumulating nextcheck.
 	 */
 
-	if (cd->flush_time >= now && cd->flush_time < (now + 5))
+	if (cd->flush_time >= now)
 		now = cd->flush_time + 1;
 
 	cd->flush_time = now;
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index c524421ec652..8584893b4785 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -817,12 +817,16 @@ static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb,
 		goto exit;
 	}
 
+	/* Get net to avoid freed tipc_crypto when delete namespace */
+	get_net(aead->crypto->net);
+
 	/* Now, do encrypt */
 	rc = crypto_aead_encrypt(req);
 	if (rc == -EINPROGRESS || rc == -EBUSY)
 		return rc;
 
 	tipc_bearer_put(b);
+	put_net(aead->crypto->net);
 
 exit:
 	kfree(ctx);
@@ -860,6 +864,7 @@ static void tipc_aead_encrypt_done(void *data, int err)
 	kfree(tx_ctx);
 	tipc_bearer_put(b);
 	tipc_aead_put(aead);
+	put_net(net);
 }
 
 /**
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 18be6ff4c3db..3ee44d731700 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -2228,7 +2228,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 			break;
 		if (msg_data_sz(hdr) < TIPC_MAX_IF_NAME)
 			break;
-		strncpy(if_name, data, TIPC_MAX_IF_NAME);
+		strscpy(if_name, data, TIPC_MAX_IF_NAME);
 
 		/* Update own tolerance if peer indicates a non-zero value */
 		if (tipc_in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) {
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index e2f19627e43d..b45c5b91bc7a 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -716,7 +716,8 @@ void tipc_mon_reinit_self(struct net *net)
 		if (!mon)
 			continue;
 		write_lock_bh(&mon->lock);
-		mon->self->addr = tipc_own_addr(net);
+		if (mon->self)
+			mon->self->addr = tipc_own_addr(net);
 		write_unlock_bh(&mon->lock);
 	}
 }
diff --git a/net/tipc/node.c b/net/tipc/node.c
index ccf5e427f43e..cb43f2016a70 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1581,7 +1581,7 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr,
 	tipc_node_read_lock(node);
 	link = node->links[bearer_id].link;
 	if (link) {
-		strncpy(linkname, tipc_link_name(link), len);
+		strscpy(linkname, tipc_link_name(link), len);
 		err = 0;
 	}
 	tipc_node_read_unlock(node);
diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c
index 77e33e1e340e..65b0da6fdf6a 100644
--- a/net/tls/tls_strp.c
+++ b/net/tls/tls_strp.c
@@ -396,7 +396,6 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort)
 		return 0;
 
 	shinfo = skb_shinfo(strp->anchor);
-	shinfo->frag_list = NULL;
 
 	/* If we don't know the length go max plus page for cipher overhead */
 	need_spc = strp->stm.full_len ?: TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE;
@@ -412,6 +411,8 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort)
 				   page, 0, 0);
 	}
 
+	shinfo->frag_list = NULL;
+
 	strp->copy_mode = 1;
 	strp->stm.offset = 0;
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 2ab20821d6bb..bd507f74e35e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -765,6 +765,11 @@ static void copy_peercred(struct sock *sk, struct sock *peersk)
 	spin_unlock(&sk->sk_peer_lock);
 }
 
+static bool unix_may_passcred(const struct sock *sk)
+{
+	return sk->sk_scm_credentials || sk->sk_scm_pidfd;
+}
+
 static int unix_listen(struct socket *sock, int backlog)
 {
 	int err;
@@ -1010,6 +1015,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
 
 	sock_init_data(sock, sk);
 
+	sk->sk_scm_rights	= 1;
 	sk->sk_hash		= unix_unbound_hash(sk);
 	sk->sk_allocation	= GFP_KERNEL_ACCOUNT;
 	sk->sk_write_space	= unix_write_space;
@@ -1411,9 +1417,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
 		if (err)
 			goto out;
 
-		if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
-		     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
-		    !READ_ONCE(unix_sk(sk)->addr)) {
+		if (unix_may_passcred(sk) && !READ_ONCE(unix_sk(sk)->addr)) {
 			err = unix_autobind(sk);
 			if (err)
 				goto out;
@@ -1531,9 +1535,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	if (err)
 		goto out;
 
-	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
-	     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
-	    !READ_ONCE(u->addr)) {
+	if (unix_may_passcred(sk) && !READ_ONCE(u->addr)) {
 		err = unix_autobind(sk);
 		if (err)
 			goto out;
@@ -1625,10 +1627,12 @@ restart:
 	/* The way is open! Fastly set all the necessary fields... */
 
 	sock_hold(sk);
-	unix_peer(newsk)	= sk;
-	newsk->sk_state		= TCP_ESTABLISHED;
-	newsk->sk_type		= sk->sk_type;
+	unix_peer(newsk) = sk;
+	newsk->sk_state = TCP_ESTABLISHED;
+	newsk->sk_type = sk->sk_type;
+	newsk->sk_scm_recv_flags = other->sk_scm_recv_flags;
 	init_peercred(newsk);
+
 	newu = unix_sk(newsk);
 	newu->listener = other;
 	RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
@@ -1709,17 +1713,6 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb)
 	return 0;
 }
 
-static void unix_sock_inherit_flags(const struct socket *old,
-				    struct socket *new)
-{
-	if (test_bit(SOCK_PASSCRED, &old->flags))
-		set_bit(SOCK_PASSCRED, &new->flags);
-	if (test_bit(SOCK_PASSPIDFD, &old->flags))
-		set_bit(SOCK_PASSPIDFD, &new->flags);
-	if (test_bit(SOCK_PASSSEC, &old->flags))
-		set_bit(SOCK_PASSSEC, &new->flags);
-}
-
 static int unix_accept(struct socket *sock, struct socket *newsock,
 		       struct proto_accept_arg *arg)
 {
@@ -1756,7 +1749,6 @@ static int unix_accept(struct socket *sock, struct socket *newsock,
 	unix_state_lock(tsk);
 	unix_update_edges(unix_sk(tsk));
 	newsock->state = SS_CONNECTED;
-	unix_sock_inherit_flags(sock, newsock);
 	sock_graft(tsk, newsock);
 	unix_state_unlock(tsk);
 	return 0;
@@ -1865,7 +1857,7 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
 {
 	int err = 0;
 
-	UNIXCB(skb).pid  = get_pid(scm->pid);
+	UNIXCB(skb).pid = get_pid(scm->pid);
 	UNIXCB(skb).uid = scm->creds.uid;
 	UNIXCB(skb).gid = scm->creds.gid;
 	UNIXCB(skb).fp = NULL;
@@ -1877,28 +1869,19 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
 	return err;
 }
 
-static bool unix_passcred_enabled(const struct socket *sock,
-				  const struct sock *other)
-{
-	return test_bit(SOCK_PASSCRED, &sock->flags) ||
-	       test_bit(SOCK_PASSPIDFD, &sock->flags) ||
-	       !other->sk_socket ||
-	       test_bit(SOCK_PASSCRED, &other->sk_socket->flags) ||
-	       test_bit(SOCK_PASSPIDFD, &other->sk_socket->flags);
-}
-
 /*
  * Some apps rely on write() giving SCM_CREDENTIALS
  * We include credentials if source or destination socket
  * asserted SOCK_PASSCRED.
  */
-static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
-			    const struct sock *other)
+static void unix_maybe_add_creds(struct sk_buff *skb, const struct sock *sk,
+				 const struct sock *other)
 {
 	if (UNIXCB(skb).pid)
 		return;
-	if (unix_passcred_enabled(sock, other)) {
-		UNIXCB(skb).pid  = get_pid(task_tgid(current));
+
+	if (unix_may_passcred(sk) || unix_may_passcred(other)) {
+		UNIXCB(skb).pid = get_pid(task_tgid(current));
 		current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
 	}
 }
@@ -1974,9 +1957,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 			goto out;
 	}
 
-	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
-	     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
-	    !READ_ONCE(u->addr)) {
+	if (unix_may_passcred(sk) && !READ_ONCE(u->addr)) {
 		err = unix_autobind(sk);
 		if (err)
 			goto out;
@@ -2093,6 +2074,11 @@ restart_locked:
 		goto out_unlock;
 	}
 
+	if (UNIXCB(skb).fp && !other->sk_scm_rights) {
+		err = -EPERM;
+		goto out_unlock;
+	}
+
 	if (sk->sk_type != SOCK_SEQPACKET) {
 		err = security_unix_may_send(sk->sk_socket, other->sk_socket);
 		if (err)
@@ -2139,7 +2125,8 @@ restart_locked:
 
 	if (sock_flag(other, SOCK_RCVTSTAMP))
 		__net_timestamp(skb);
-	maybe_add_creds(skb, sock, other);
+
+	unix_maybe_add_creds(skb, sk, other);
 	scm_stat_add(other, skb);
 	skb_queue_tail(&other->sk_receive_queue, skb);
 	unix_state_unlock(other);
@@ -2167,14 +2154,14 @@ out:
 #define UNIX_SKB_FRAGS_SZ (PAGE_SIZE << get_order(32768))
 
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
-static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other,
+static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other,
 		     struct scm_cookie *scm, bool fds_sent)
 {
 	struct unix_sock *ousk = unix_sk(other);
 	struct sk_buff *skb;
 	int err;
 
-	skb = sock_alloc_send_skb(sock->sk, 1, msg->msg_flags & MSG_DONTWAIT, &err);
+	skb = sock_alloc_send_skb(sk, 1, msg->msg_flags & MSG_DONTWAIT, &err);
 
 	if (!skb)
 		return err;
@@ -2193,12 +2180,16 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 
 	if (sock_flag(other, SOCK_DEAD) ||
 	    (other->sk_shutdown & RCV_SHUTDOWN)) {
-		unix_state_unlock(other);
 		err = -EPIPE;
-		goto out;
+		goto out_unlock;
+	}
+
+	if (UNIXCB(skb).fp && !other->sk_scm_rights) {
+		err = -EPERM;
+		goto out_unlock;
 	}
 
-	maybe_add_creds(skb, sock, other);
+	unix_maybe_add_creds(skb, sk, other);
 	scm_stat_add(other, skb);
 
 	spin_lock(&other->sk_receive_queue.lock);
@@ -2211,6 +2202,8 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 	other->sk_data_ready(other);
 
 	return 0;
+out_unlock:
+	unix_state_unlock(other);
 out:
 	consume_skb(skb);
 	return err;
@@ -2314,7 +2307,13 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		    (other->sk_shutdown & RCV_SHUTDOWN))
 			goto out_pipe_unlock;
 
-		maybe_add_creds(skb, sock, other);
+		if (UNIXCB(skb).fp && !other->sk_scm_rights) {
+			unix_state_unlock(other);
+			err = -EPERM;
+			goto out_free;
+		}
+
+		unix_maybe_add_creds(skb, sk, other);
 		scm_stat_add(other, skb);
 		skb_queue_tail(&other->sk_receive_queue, skb);
 		unix_state_unlock(other);
@@ -2324,7 +2323,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
 	if (msg->msg_flags & MSG_OOB) {
-		err = queue_oob(sock, msg, other, &scm, fds_sent);
+		err = queue_oob(sk, msg, other, &scm, fds_sent);
 		if (err)
 			goto out_err;
 		sent++;
@@ -2846,8 +2845,7 @@ unlock:
 			/* Never glue messages from different writers */
 			if (!unix_skb_scm_eq(skb, &scm))
 				break;
-		} else if (test_bit(SOCK_PASSCRED, &sock->flags) ||
-			   test_bit(SOCK_PASSPIDFD, &sock->flags)) {
+		} else if (unix_may_passcred(sk)) {
 			/* Copy credentials */
 			scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
 			unix_set_secdata(&scm, skb);
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 7f7de6d88096..6e7b727c781c 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -87,7 +87,7 @@ static int virtio_transport_init_zcopy_skb(struct vsock_sock *vsk,
 
 		uarg = msg_zerocopy_realloc(sk_vsock(vsk),
 					    iter->count,
-					    NULL);
+					    NULL, false);
 		if (!uarg)
 			return -1;
 
@@ -107,8 +107,7 @@ static int virtio_transport_fill_skb(struct sk_buff *skb,
 {
 	if (zcopy)
 		return __zerocopy_sg_from_iter(info->msg, NULL, skb,
-					       &info->msg->msg_iter,
-					       len);
+					       &info->msg->msg_iter, len, NULL);
 
 	return memcpy_from_msg(skb_put(skb, len), info->msg, len);
 }
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index f039a7d0d6f7..fd5f79266471 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -469,6 +469,8 @@ nl80211_mbssid_config_policy[NL80211_MBSSID_CONFIG_ATTR_MAX + 1] = {
 	[NL80211_MBSSID_CONFIG_ATTR_INDEX] = { .type = NLA_U8 },
 	[NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX] = { .type = NLA_U32 },
 	[NL80211_MBSSID_CONFIG_ATTR_EMA] = { .type = NLA_FLAG },
+	[NL80211_MBSSID_CONFIG_ATTR_TX_LINK_ID] =
+		NLA_POLICY_MAX(NLA_U8, IEEE80211_MLD_MAX_NUM_LINKS),
 };
 
 static const struct nla_policy
@@ -833,6 +835,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_MLD_ADDR] = NLA_POLICY_EXACT_LEN(ETH_ALEN),
 	[NL80211_ATTR_MLO_SUPPORT] = { .type = NLA_FLAG },
 	[NL80211_ATTR_MAX_NUM_AKM_SUITES] = { .type = NLA_REJECT },
+	[NL80211_ATTR_EML_CAPABILITY] = { .type = NLA_U16 },
 	[NL80211_ATTR_PUNCT_BITMAP] =
 		NLA_POLICY_FULL_RANGE(NLA_U32, &nl80211_punct_bitmap_range),
 
@@ -5523,11 +5526,13 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev,
 
 static int nl80211_parse_mbssid_config(struct wiphy *wiphy,
 				       struct net_device *dev,
+				       unsigned int link_id,
 				       struct nlattr *attrs,
 				       struct cfg80211_mbssid_config *config,
 				       u8 num_elems)
 {
 	struct nlattr *tb[NL80211_MBSSID_CONFIG_ATTR_MAX + 1];
+	int tx_link_id = -1;
 
 	if (!wiphy->mbssid_max_interfaces)
 		return -EOPNOTSUPP;
@@ -5551,6 +5556,9 @@ static int nl80211_parse_mbssid_config(struct wiphy *wiphy,
 	    (!config->index && !num_elems))
 		return -EINVAL;
 
+	if (tb[NL80211_MBSSID_CONFIG_ATTR_TX_LINK_ID])
+		tx_link_id = nla_get_u8(tb[NL80211_MBSSID_CONFIG_ATTR_TX_LINK_ID]);
+
 	if (tb[NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX]) {
 		u32 tx_ifindex =
 			nla_get_u32(tb[NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX]);
@@ -5572,10 +5580,25 @@ static int nl80211_parse_mbssid_config(struct wiphy *wiphy,
 			}
 
 			config->tx_wdev = tx_netdev->ieee80211_ptr;
+			/* Caller should call dev_put(config->tx_wdev) from this point */
+
+			if (config->tx_wdev->valid_links) {
+				if (tx_link_id == -1 ||
+				    !(config->tx_wdev->valid_links & BIT(tx_link_id)))
+					return -ENOLINK;
+
+				config->tx_link_id = tx_link_id;
+			}
 		} else {
+			if (tx_link_id >= 0 && tx_link_id != link_id)
+				return -EINVAL;
+
 			config->tx_wdev = dev->ieee80211_ptr;
 		}
 	} else if (!config->index) {
+		if (tx_link_id >= 0 && tx_link_id != link_id)
+			return -EINVAL;
+
 		config->tx_wdev = dev->ieee80211_ptr;
 	} else {
 		return -EINVAL;
@@ -6325,7 +6348,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (info->attrs[NL80211_ATTR_MBSSID_CONFIG]) {
-		err = nl80211_parse_mbssid_config(&rdev->wiphy, dev,
+		err = nl80211_parse_mbssid_config(&rdev->wiphy, dev, link_id,
 						  info->attrs[NL80211_ATTR_MBSSID_CONFIG],
 						  &params->mbssid_config,
 						  params->beacon.mbssid_ies ?
@@ -7118,6 +7141,11 @@ int cfg80211_check_station_change(struct wiphy *wiphy,
 			return -EINVAL;
 	}
 
+	/* Accept EMLSR capabilities only for AP client before association */
+	if (statype != CFG80211_STA_AP_CLIENT_UNASSOC &&
+	    params->eml_cap_present)
+		return -EINVAL;
+
 	switch (statype) {
 	case CFG80211_STA_AP_MLME_CLIENT:
 		/* Use this only for authorizing/unauthorizing a station */
@@ -7473,6 +7501,12 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info)
 		params.link_sta_params.he_6ghz_capa =
 			nla_data(info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]);
 
+	if (info->attrs[NL80211_ATTR_EML_CAPABILITY]) {
+		params.eml_cap_present = true;
+		params.eml_cap =
+			nla_get_u16(info->attrs[NL80211_ATTR_EML_CAPABILITY]);
+	}
+
 	if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT])
 		params.airtime_weight =
 			nla_get_u16(info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]);
@@ -7631,6 +7665,12 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
+	if (info->attrs[NL80211_ATTR_EML_CAPABILITY]) {
+		params.eml_cap_present = true;
+		params.eml_cap =
+			nla_get_u16(info->attrs[NL80211_ATTR_EML_CAPABILITY]);
+	}
+
 	if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY])
 		params.link_sta_params.he_6ghz_capa =
 			nla_data(info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]);
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 9865f305275d..ddd3a97f6609 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2681,7 +2681,7 @@ cfg80211_defrag_mle(const struct element *mle, const u8 *ie, size_t ielen,
 	/* Required length for first defragmentation */
 	buf_len = mle->datalen - 1;
 	for_each_element(elem, mle->data + mle->datalen,
-			 ielen - sizeof(*mle) + mle->datalen) {
+			 ie + ielen - mle->data - mle->datalen) {
 		if (elem->id != WLAN_EID_FRAGMENT)
 			break;
 
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5696af45bcf7..72c000c0ae5f 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -338,13 +338,14 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	u32 len = xdp_get_buff_len(xdp);
 	int err;
 
-	spin_lock_bh(&xs->rx_lock);
 	err = xsk_rcv_check(xs, xdp, len);
 	if (!err) {
+		spin_lock_bh(&xs->pool->rx_lock);
 		err = __xsk_rcv(xs, xdp, len);
 		xsk_flush(xs);
+		spin_unlock_bh(&xs->pool->rx_lock);
 	}
-	spin_unlock_bh(&xs->rx_lock);
+
 	return err;
 }
 
@@ -1303,7 +1304,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	xs->queue_id = qid;
 	xp_add_xsk(xs->pool, xs);
 
-	if (xs->zc && qid < dev->real_num_rx_queues) {
+	if (qid < dev->real_num_rx_queues) {
 		struct netdev_rx_queue *rxq;
 
 		rxq = __netif_get_rx_queue(dev, qid);
@@ -1734,7 +1735,6 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 	xs = xdp_sk(sk);
 	xs->state = XSK_READY;
 	mutex_init(&xs->mutex);
-	spin_lock_init(&xs->rx_lock);
 
 	INIT_LIST_HEAD(&xs->map_list);
 	spin_lock_init(&xs->map_list_lock);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index cbf2129e808b..aa9788f20d0d 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -89,6 +89,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	pool->addrs = umem->addrs;
 	pool->tx_metadata_len = umem->tx_metadata_len;
 	pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM;
+	spin_lock_init(&pool->rx_lock);
 	INIT_LIST_HEAD(&pool->free_list);
 	INIT_LIST_HEAD(&pool->xskb_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index fe82e2d07300..fc7a603b04f1 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -171,8 +171,10 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb)
 	struct espintcp_ctx *ctx = espintcp_getctx(sk);
 
 	if (skb_queue_len(&ctx->out_queue) >=
-	    READ_ONCE(net_hotdata.max_backlog))
+	    READ_ONCE(net_hotdata.max_backlog)) {
+		kfree_skb(skb);
 		return -ENOBUFS;
+	}
 
 	__skb_queue_tail(&ctx->out_queue, skb);
 
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index 622445f041d3..cb1e12740c87 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -952,32 +952,28 @@ static struct rtnl_link_ops xfrmi_link_ops __read_mostly = {
 	.get_link_net	= xfrmi_get_link_net,
 };
 
-static void __net_exit xfrmi_exit_batch_rtnl(struct list_head *net_exit_list,
-					     struct list_head *dev_to_kill)
+static void __net_exit xfrmi_exit_rtnl(struct net *net,
+				       struct list_head *dev_to_kill)
 {
-	struct net *net;
+	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+	struct xfrm_if __rcu **xip;
+	struct xfrm_if *xi;
+	int i;
 
-	ASSERT_RTNL();
-	list_for_each_entry(net, net_exit_list, exit_list) {
-		struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
-		struct xfrm_if __rcu **xip;
-		struct xfrm_if *xi;
-		int i;
-
-		for (i = 0; i < XFRMI_HASH_SIZE; i++) {
-			for (xip = &xfrmn->xfrmi[i];
-			     (xi = rtnl_dereference(*xip)) != NULL;
-			     xip = &xi->next)
-				unregister_netdevice_queue(xi->dev, dev_to_kill);
-		}
-		xi = rtnl_dereference(xfrmn->collect_md_xfrmi);
-		if (xi)
+	for (i = 0; i < XFRMI_HASH_SIZE; i++) {
+		for (xip = &xfrmn->xfrmi[i];
+		     (xi = rtnl_net_dereference(net, *xip)) != NULL;
+		     xip = &xi->next)
 			unregister_netdevice_queue(xi->dev, dev_to_kill);
 	}
+
+	xi = rtnl_net_dereference(net, xfrmn->collect_md_xfrmi);
+	if (xi)
+		unregister_netdevice_queue(xi->dev, dev_to_kill);
 }
 
 static struct pernet_operations xfrmi_net_ops = {
-	.exit_batch_rtnl = xfrmi_exit_batch_rtnl,
+	.exit_rtnl = xfrmi_exit_rtnl,
 	.id   = &xfrmi_net_id,
 	.size = sizeof(struct xfrmi_net),
 };
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index 0c1420534394..907c3ccb440d 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -48,7 +48,6 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen)
 {
 	struct acomp_req *req = ipcomp_cb(skb)->req;
 	struct ipcomp_req_extra *extra;
-	const int plen = skb->data_len;
 	struct scatterlist *dsg;
 	int len, dlen;
 
@@ -64,7 +63,7 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen)
 
 	/* Only update truesize on input. */
 	if (!hlen)
-		skb->truesize += dlen - plen;
+		skb->truesize += dlen;
 	skb->data_len = dlen;
 	skb->len += dlen;
 
diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c
index 82f0a301683f..ebf95d48e86c 100644
--- a/net/xfrm/xfrm_nat_keepalive.c
+++ b/net/xfrm/xfrm_nat_keepalive.c
@@ -9,9 +9,13 @@
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
 
-static DEFINE_PER_CPU(struct sock *, nat_keepalive_sk_ipv4);
+static DEFINE_PER_CPU(struct sock_bh_locked, nat_keepalive_sk_ipv4) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 #if IS_ENABLED(CONFIG_IPV6)
-static DEFINE_PER_CPU(struct sock *, nat_keepalive_sk_ipv6);
+static DEFINE_PER_CPU(struct sock_bh_locked, nat_keepalive_sk_ipv6) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 #endif
 
 struct nat_keepalive {
@@ -56,10 +60,12 @@ static int nat_keepalive_send_ipv4(struct sk_buff *skb,
 
 	skb_dst_set(skb, &rt->dst);
 
-	sk = *this_cpu_ptr(&nat_keepalive_sk_ipv4);
+	local_lock_nested_bh(&nat_keepalive_sk_ipv4.bh_lock);
+	sk = this_cpu_read(nat_keepalive_sk_ipv4.sock);
 	sock_net_set(sk, net);
 	err = ip_build_and_send_pkt(skb, sk, fl4.saddr, fl4.daddr, NULL, tos);
 	sock_net_set(sk, &init_net);
+	local_unlock_nested_bh(&nat_keepalive_sk_ipv4.bh_lock);
 	return err;
 }
 
@@ -89,15 +95,19 @@ static int nat_keepalive_send_ipv6(struct sk_buff *skb,
 	fl6.fl6_sport = ka->encap_sport;
 	fl6.fl6_dport = ka->encap_dport;
 
-	sk = *this_cpu_ptr(&nat_keepalive_sk_ipv6);
+	local_lock_nested_bh(&nat_keepalive_sk_ipv6.bh_lock);
+	sk = this_cpu_read(nat_keepalive_sk_ipv6.sock);
 	sock_net_set(sk, net);
 	dst = ipv6_stub->ipv6_dst_lookup_flow(net, sk, &fl6, NULL);
-	if (IS_ERR(dst))
+	if (IS_ERR(dst)) {
+		local_unlock_nested_bh(&nat_keepalive_sk_ipv6.bh_lock);
 		return PTR_ERR(dst);
+	}
 
 	skb_dst_set(skb, dst);
 	err = ipv6_stub->ip6_xmit(sk, skb, &fl6, skb->mark, NULL, 0, 0);
 	sock_net_set(sk, &init_net);
+	local_unlock_nested_bh(&nat_keepalive_sk_ipv6.bh_lock);
 	return err;
 }
 #endif
@@ -202,7 +212,7 @@ static void nat_keepalive_work(struct work_struct *work)
 				      (ctx.next_run - ctx.now) * HZ);
 }
 
-static int nat_keepalive_sk_init(struct sock * __percpu *socks,
+static int nat_keepalive_sk_init(struct sock_bh_locked __percpu *socks,
 				 unsigned short family)
 {
 	struct sock *sk;
@@ -214,22 +224,22 @@ static int nat_keepalive_sk_init(struct sock * __percpu *socks,
 		if (err < 0)
 			goto err;
 
-		*per_cpu_ptr(socks, i) = sk;
+		per_cpu_ptr(socks, i)->sock = sk;
 	}
 
 	return 0;
 err:
 	for_each_possible_cpu(i)
-		inet_ctl_sock_destroy(*per_cpu_ptr(socks, i));
+		inet_ctl_sock_destroy(per_cpu_ptr(socks, i)->sock);
 	return err;
 }
 
-static void nat_keepalive_sk_fini(struct sock * __percpu *socks)
+static void nat_keepalive_sk_fini(struct sock_bh_locked __percpu *socks)
 {
 	int i;
 
 	for_each_possible_cpu(i)
-		inet_ctl_sock_destroy(*per_cpu_ptr(socks, i));
+		inet_ctl_sock_destroy(per_cpu_ptr(socks, i)->sock);
 }
 
 void xfrm_nat_keepalive_state_updated(struct xfrm_state *x)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 7200ba8de936..d4134a18c658 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1581,6 +1581,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	struct xfrm_policy *delpol;
 	struct hlist_head *chain;
 
+	/* Sanitize mark before store */
+	policy->mark.v &= policy->mark.m;
+
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
 	if (chain)
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 5e1c736ea708..203b585c2ae2 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -838,9 +838,6 @@ int __xfrm_state_delete(struct xfrm_state *x)
 		xfrm_nat_keepalive_state_updated(x);
 		spin_unlock(&net->xfrm.xfrm_state_lock);
 
-		if (x->encap_sk)
-			sock_put(rcu_dereference_raw(x->encap_sk));
-
 		xfrm_dev_state_delete(x);
 
 		/* All xfrm_state objects are created by xfrm_state_alloc.
@@ -1721,6 +1718,9 @@ static void __xfrm_state_insert(struct xfrm_state *x)
 
 	list_add(&x->km.all, &net->xfrm.state_all);
 
+	/* Sanitize mark before store */
+	x->mark.v &= x->mark.m;
+
 	h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr,
 			  x->props.reqid, x->props.family);
 	XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,
diff --git a/rust/Makefile b/rust/Makefile
index fa0eea8a9eca..3aca903a7d08 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -368,7 +368,7 @@ $(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_extra = ;
 $(obj)/bindings/bindings_helpers_generated.rs: $(src)/helpers/helpers.c FORCE
 	$(call if_changed_dep,bindgen)
 
-rust_exports = $(NM) -p --defined-only $(1) | awk '$$2~/(T|R|D|B)/ && $$3!~/__cfi/ && $$3!~/__odr_asan/ { printf $(2),$$3 }'
+rust_exports = $(NM) -p --defined-only $(1) | awk '$$2~/(T|R|D|B)/ && $$3!~/__(pfx|cfi|odr_asan)/ { printf $(2),$$3 }'
 
 quiet_cmd_exports = EXPORTS $@
       cmd_exports = \
diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs
index 014af0d1fc70..a08eb5518cac 100644
--- a/rust/bindings/lib.rs
+++ b/rust/bindings/lib.rs
@@ -26,6 +26,7 @@
 
 #[allow(dead_code)]
 #[allow(clippy::undocumented_unsafe_blocks)]
+#[cfg_attr(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES, allow(unnecessary_transmutes))]
 mod bindings_raw {
     // Manual definition for blocklisted types.
     type __kernel_size_t = usize;
diff --git a/rust/helpers/dma.c b/rust/helpers/dma.c
new file mode 100644
index 000000000000..df8b8a77355a
--- /dev/null
+++ b/rust/helpers/dma.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/dma-mapping.h>
+
+void *rust_helper_dma_alloc_attrs(struct device *dev, size_t size,
+				  dma_addr_t *dma_handle, gfp_t flag,
+				  unsigned long attrs)
+{
+	return dma_alloc_attrs(dev, size, dma_handle, flag, attrs);
+}
+
+void rust_helper_dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+				dma_addr_t dma_handle, unsigned long attrs)
+{
+	dma_free_attrs(dev, size, cpu_addr, dma_handle, attrs);
+}
diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index e1c21eba9b15..1e7c84df7252 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -14,6 +14,7 @@
 #include "cpumask.c"
 #include "cred.c"
 #include "device.c"
+#include "dma.c"
 #include "err.c"
 #include "fs.c"
 #include "io.c"
diff --git a/rust/helpers/io.c b/rust/helpers/io.c
index 4c2401ccd720..15ea187c5466 100644
--- a/rust/helpers/io.c
+++ b/rust/helpers/io.c
@@ -7,94 +7,94 @@ void __iomem *rust_helper_ioremap(phys_addr_t offset, size_t size)
 	return ioremap(offset, size);
 }
 
-void rust_helper_iounmap(volatile void __iomem *addr)
+void rust_helper_iounmap(void __iomem *addr)
 {
 	iounmap(addr);
 }
 
-u8 rust_helper_readb(const volatile void __iomem *addr)
+u8 rust_helper_readb(const void __iomem *addr)
 {
 	return readb(addr);
 }
 
-u16 rust_helper_readw(const volatile void __iomem *addr)
+u16 rust_helper_readw(const void __iomem *addr)
 {
 	return readw(addr);
 }
 
-u32 rust_helper_readl(const volatile void __iomem *addr)
+u32 rust_helper_readl(const void __iomem *addr)
 {
 	return readl(addr);
 }
 
 #ifdef CONFIG_64BIT
-u64 rust_helper_readq(const volatile void __iomem *addr)
+u64 rust_helper_readq(const void __iomem *addr)
 {
 	return readq(addr);
 }
 #endif
 
-void rust_helper_writeb(u8 value, volatile void __iomem *addr)
+void rust_helper_writeb(u8 value, void __iomem *addr)
 {
 	writeb(value, addr);
 }
 
-void rust_helper_writew(u16 value, volatile void __iomem *addr)
+void rust_helper_writew(u16 value, void __iomem *addr)
 {
 	writew(value, addr);
 }
 
-void rust_helper_writel(u32 value, volatile void __iomem *addr)
+void rust_helper_writel(u32 value, void __iomem *addr)
 {
 	writel(value, addr);
 }
 
 #ifdef CONFIG_64BIT
-void rust_helper_writeq(u64 value, volatile void __iomem *addr)
+void rust_helper_writeq(u64 value, void __iomem *addr)
 {
 	writeq(value, addr);
 }
 #endif
 
-u8 rust_helper_readb_relaxed(const volatile void __iomem *addr)
+u8 rust_helper_readb_relaxed(const void __iomem *addr)
 {
 	return readb_relaxed(addr);
 }
 
-u16 rust_helper_readw_relaxed(const volatile void __iomem *addr)
+u16 rust_helper_readw_relaxed(const void __iomem *addr)
 {
 	return readw_relaxed(addr);
 }
 
-u32 rust_helper_readl_relaxed(const volatile void __iomem *addr)
+u32 rust_helper_readl_relaxed(const void __iomem *addr)
 {
 	return readl_relaxed(addr);
 }
 
 #ifdef CONFIG_64BIT
-u64 rust_helper_readq_relaxed(const volatile void __iomem *addr)
+u64 rust_helper_readq_relaxed(const void __iomem *addr)
 {
 	return readq_relaxed(addr);
 }
 #endif
 
-void rust_helper_writeb_relaxed(u8 value, volatile void __iomem *addr)
+void rust_helper_writeb_relaxed(u8 value, void __iomem *addr)
 {
 	writeb_relaxed(value, addr);
 }
 
-void rust_helper_writew_relaxed(u16 value, volatile void __iomem *addr)
+void rust_helper_writew_relaxed(u16 value, void __iomem *addr)
 {
 	writew_relaxed(value, addr);
 }
 
-void rust_helper_writel_relaxed(u32 value, volatile void __iomem *addr)
+void rust_helper_writel_relaxed(u32 value, void __iomem *addr)
 {
 	writel_relaxed(value, addr);
 }
 
 #ifdef CONFIG_64BIT
-void rust_helper_writeq_relaxed(u64 value, volatile void __iomem *addr)
+void rust_helper_writeq_relaxed(u64 value, void __iomem *addr)
 {
 	writeq_relaxed(value, addr);
 }
diff --git a/rust/kernel/alloc/kvec.rs b/rust/kernel/alloc/kvec.rs
index ae9d072741ce..87a71fd40c3c 100644
--- a/rust/kernel/alloc/kvec.rs
+++ b/rust/kernel/alloc/kvec.rs
@@ -2,6 +2,9 @@
 
 //! Implementation of [`Vec`].
 
+// May not be needed in Rust 1.87.0 (pending beta backport).
+#![allow(clippy::ptr_eq)]
+
 use super::{
     allocator::{KVmalloc, Kmalloc, Vmalloc},
     layout::ArrayLayout,
diff --git a/rust/kernel/firmware.rs b/rust/kernel/firmware.rs
index f04b058b09b2..2494c96e105f 100644
--- a/rust/kernel/firmware.rs
+++ b/rust/kernel/firmware.rs
@@ -4,7 +4,7 @@
 //!
 //! C header: [`include/linux/firmware.h`](srctree/include/linux/firmware.h)
 
-use crate::{bindings, device::Device, error::Error, error::Result, str::CStr};
+use crate::{bindings, device::Device, error::Error, error::Result, ffi, str::CStr};
 use core::ptr::NonNull;
 
 /// # Invariants
@@ -12,7 +12,11 @@ use core::ptr::NonNull;
 /// One of the following: `bindings::request_firmware`, `bindings::firmware_request_nowarn`,
 /// `bindings::firmware_request_platform`, `bindings::request_firmware_direct`.
 struct FwFunc(
-    unsafe extern "C" fn(*mut *const bindings::firmware, *const u8, *mut bindings::device) -> i32,
+    unsafe extern "C" fn(
+        *mut *const bindings::firmware,
+        *const ffi::c_char,
+        *mut bindings::device,
+    ) -> i32,
 );
 
 impl FwFunc {
diff --git a/rust/kernel/list.rs b/rust/kernel/list.rs
index a335c3b1ff5e..2054682c5724 100644
--- a/rust/kernel/list.rs
+++ b/rust/kernel/list.rs
@@ -4,6 +4,9 @@
 
 //! A linked list implementation.
 
+// May not be needed in Rust 1.87.0 (pending beta backport).
+#![allow(clippy::ptr_eq)]
+
 use crate::sync::ArcBorrow;
 use crate::types::Opaque;
 use core::iter::{DoubleEndedIterator, FusedIterator};
diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index a59469c785e3..32ea43ece646 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -421,6 +421,7 @@ impl<T: Driver> Adapter<T> {
     /// `phydev` must be passed by the corresponding callback in `phy_driver`.
     unsafe extern "C" fn match_phy_device_callback(
         phydev: *mut bindings::phy_device,
+        _phydrv: *const bindings::phy_driver,
     ) -> crate::ffi::c_int {
         // SAFETY: This callback is called only in contexts
         // where we hold `phy_device->lock`, so the accessors on
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index 878111cb77bc..fb61ce81ea28 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -73,7 +73,7 @@ impl fmt::Display for BStr {
                 b'\r' => f.write_str("\\r")?,
                 // Printable characters.
                 0x20..=0x7e => f.write_char(b as char)?,
-                _ => write!(f, "\\x{:02x}", b)?,
+                _ => write!(f, "\\x{b:02x}")?,
             }
         }
         Ok(())
@@ -109,7 +109,7 @@ impl fmt::Debug for BStr {
                 b'\\' => f.write_str("\\\\")?,
                 // Printable characters.
                 0x20..=0x7e => f.write_char(b as char)?,
-                _ => write!(f, "\\x{:02x}", b)?,
+                _ => write!(f, "\\x{b:02x}")?,
             }
         }
         f.write_char('"')
@@ -447,7 +447,7 @@ impl fmt::Display for CStr {
                 // Printable character.
                 f.write_char(c as char)?;
             } else {
-                write!(f, "\\x{:02x}", c)?;
+                write!(f, "\\x{c:02x}")?;
             }
         }
         Ok(())
@@ -479,7 +479,7 @@ impl fmt::Debug for CStr {
                 // Printable characters.
                 b'\"' => f.write_str("\\\"")?,
                 0x20..=0x7e => f.write_char(c as char)?,
-                _ => write!(f, "\\x{:02x}", c)?,
+                _ => write!(f, "\\x{c:02x}")?,
             }
         }
         f.write_str("\"")
@@ -641,13 +641,13 @@ mod tests {
     #[test]
     fn test_cstr_display() {
         let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap();
-        assert_eq!(format!("{}", hello_world), "hello, world!");
+        assert_eq!(format!("{hello_world}"), "hello, world!");
         let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap();
-        assert_eq!(format!("{}", non_printables), "\\x01\\x09\\x0a");
+        assert_eq!(format!("{non_printables}"), "\\x01\\x09\\x0a");
         let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap();
-        assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu");
+        assert_eq!(format!("{non_ascii}"), "d\\xe9j\\xe0 vu");
         let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap();
-        assert_eq!(format!("{}", good_bytes), "\\xf0\\x9f\\xa6\\x80");
+        assert_eq!(format!("{good_bytes}"), "\\xf0\\x9f\\xa6\\x80");
     }
 
     #[test]
@@ -658,47 +658,47 @@ mod tests {
             bytes[i as usize] = i.wrapping_add(1);
         }
         let cstr = CStr::from_bytes_with_nul(&bytes).unwrap();
-        assert_eq!(format!("{}", cstr), ALL_ASCII_CHARS);
+        assert_eq!(format!("{cstr}"), ALL_ASCII_CHARS);
     }
 
     #[test]
     fn test_cstr_debug() {
         let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap();
-        assert_eq!(format!("{:?}", hello_world), "\"hello, world!\"");
+        assert_eq!(format!("{hello_world:?}"), "\"hello, world!\"");
         let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap();
-        assert_eq!(format!("{:?}", non_printables), "\"\\x01\\x09\\x0a\"");
+        assert_eq!(format!("{non_printables:?}"), "\"\\x01\\x09\\x0a\"");
         let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap();
-        assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\"");
+        assert_eq!(format!("{non_ascii:?}"), "\"d\\xe9j\\xe0 vu\"");
         let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap();
-        assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\"");
+        assert_eq!(format!("{good_bytes:?}"), "\"\\xf0\\x9f\\xa6\\x80\"");
     }
 
     #[test]
     fn test_bstr_display() {
         let hello_world = BStr::from_bytes(b"hello, world!");
-        assert_eq!(format!("{}", hello_world), "hello, world!");
+        assert_eq!(format!("{hello_world}"), "hello, world!");
         let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_");
-        assert_eq!(format!("{}", escapes), "_\\t_\\n_\\r_\\_'_\"_");
+        assert_eq!(format!("{escapes}"), "_\\t_\\n_\\r_\\_'_\"_");
         let others = BStr::from_bytes(b"\x01");
-        assert_eq!(format!("{}", others), "\\x01");
+        assert_eq!(format!("{others}"), "\\x01");
         let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu");
-        assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu");
+        assert_eq!(format!("{non_ascii}"), "d\\xe9j\\xe0 vu");
         let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80");
-        assert_eq!(format!("{}", good_bytes), "\\xf0\\x9f\\xa6\\x80");
+        assert_eq!(format!("{good_bytes}"), "\\xf0\\x9f\\xa6\\x80");
     }
 
     #[test]
     fn test_bstr_debug() {
         let hello_world = BStr::from_bytes(b"hello, world!");
-        assert_eq!(format!("{:?}", hello_world), "\"hello, world!\"");
+        assert_eq!(format!("{hello_world:?}"), "\"hello, world!\"");
         let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_");
-        assert_eq!(format!("{:?}", escapes), "\"_\\t_\\n_\\r_\\\\_'_\\\"_\"");
+        assert_eq!(format!("{escapes:?}"), "\"_\\t_\\n_\\r_\\\\_'_\\\"_\"");
         let others = BStr::from_bytes(b"\x01");
-        assert_eq!(format!("{:?}", others), "\"\\x01\"");
+        assert_eq!(format!("{others:?}"), "\"\\x01\"");
         let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu");
-        assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\"");
+        assert_eq!(format!("{non_ascii:?}"), "\"d\\xe9j\\xe0 vu\"");
         let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80");
-        assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\"");
+        assert_eq!(format!("{good_bytes:?}"), "\"\\xf0\\x9f\\xa6\\x80\"");
     }
 }
 
diff --git a/rust/macros/kunit.rs b/rust/macros/kunit.rs
index 4f553ecf40c0..99ccac82edde 100644
--- a/rust/macros/kunit.rs
+++ b/rust/macros/kunit.rs
@@ -15,10 +15,7 @@ pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream {
     }
 
     if attr.len() > 255 {
-        panic!(
-            "The test suite name `{}` exceeds the maximum length of 255 bytes",
-            attr
-        )
+        panic!("The test suite name `{attr}` exceeds the maximum length of 255 bytes")
     }
 
     let mut tokens: Vec<_> = ts.into_iter().collect();
@@ -102,16 +99,14 @@ pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream {
     let mut kunit_macros = "".to_owned();
     let mut test_cases = "".to_owned();
     for test in &tests {
-        let kunit_wrapper_fn_name = format!("kunit_rust_wrapper_{}", test);
+        let kunit_wrapper_fn_name = format!("kunit_rust_wrapper_{test}");
         let kunit_wrapper = format!(
-            "unsafe extern \"C\" fn {}(_test: *mut kernel::bindings::kunit) {{ {}(); }}",
-            kunit_wrapper_fn_name, test
+            "unsafe extern \"C\" fn {kunit_wrapper_fn_name}(_test: *mut kernel::bindings::kunit) {{ {test}(); }}"
         );
         writeln!(kunit_macros, "{kunit_wrapper}").unwrap();
         writeln!(
             test_cases,
-            "    kernel::kunit::kunit_case(kernel::c_str!(\"{}\"), {}),",
-            test, kunit_wrapper_fn_name
+            "    kernel::kunit::kunit_case(kernel::c_str!(\"{test}\"), {kunit_wrapper_fn_name}),"
         )
         .unwrap();
     }
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index a9418fbc9b44..2f66107847f7 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -48,7 +48,7 @@ impl<'a> ModInfoBuilder<'a> {
             )
         } else {
             // Loadable modules' modinfo strings go as-is.
-            format!("{field}={content}\0", field = field, content = content)
+            format!("{field}={content}\0")
         };
 
         write!(
@@ -126,10 +126,7 @@ impl ModuleInfo {
             };
 
             if seen_keys.contains(&key) {
-                panic!(
-                    "Duplicated key \"{}\". Keys can only be specified once.",
-                    key
-                );
+                panic!("Duplicated key \"{key}\". Keys can only be specified once.");
             }
 
             assert_eq!(expect_punct(it), ':');
@@ -143,10 +140,7 @@ impl ModuleInfo {
                 "license" => info.license = expect_string_ascii(it),
                 "alias" => info.alias = Some(expect_string_array(it)),
                 "firmware" => info.firmware = Some(expect_string_array(it)),
-                _ => panic!(
-                    "Unknown key \"{}\". Valid keys are: {:?}.",
-                    key, EXPECTED_KEYS
-                ),
+                _ => panic!("Unknown key \"{key}\". Valid keys are: {EXPECTED_KEYS:?}."),
             }
 
             assert_eq!(expect_punct(it), ',');
@@ -158,7 +152,7 @@ impl ModuleInfo {
 
         for key in REQUIRED_KEYS {
             if !seen_keys.iter().any(|e| e == key) {
-                panic!("Missing required key \"{}\".", key);
+                panic!("Missing required key \"{key}\".");
             }
         }
 
@@ -170,10 +164,7 @@ impl ModuleInfo {
         }
 
         if seen_keys != ordered_keys {
-            panic!(
-                "Keys are not ordered as expected. Order them like: {:?}.",
-                ordered_keys
-            );
+            panic!("Keys are not ordered as expected. Order them like: {ordered_keys:?}.");
         }
 
         info
diff --git a/rust/macros/paste.rs b/rust/macros/paste.rs
index 6529a387673f..cce712d19855 100644
--- a/rust/macros/paste.rs
+++ b/rust/macros/paste.rs
@@ -50,7 +50,7 @@ fn concat_helper(tokens: &[TokenTree]) -> Vec<(String, Span)> {
                 let tokens = group.stream().into_iter().collect::<Vec<TokenTree>>();
                 segments.append(&mut concat_helper(tokens.as_slice()));
             }
-            token => panic!("unexpected token in paste segments: {:?}", token),
+            token => panic!("unexpected token in paste segments: {token:?}"),
         };
     }
 
diff --git a/rust/pin-init/examples/pthread_mutex.rs b/rust/pin-init/examples/pthread_mutex.rs
index 9164298c44c0..5ac22f1880d2 100644
--- a/rust/pin-init/examples/pthread_mutex.rs
+++ b/rust/pin-init/examples/pthread_mutex.rs
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: Apache-2.0 OR MIT
 
-// inspired by https://github.com/nbdd0121/pin-init/blob/trunk/examples/pthread_mutex.rs
+// inspired by <https://github.com/nbdd0121/pin-init/blob/trunk/examples/pthread_mutex.rs>
 #![allow(clippy::undocumented_unsafe_blocks)]
 #![cfg_attr(feature = "alloc", feature(allocator_api))]
 #[cfg(not(windows))]
diff --git a/rust/pin-init/internal/src/pinned_drop.rs b/rust/pin-init/internal/src/pinned_drop.rs
index c824dd8b436d..c4ca7a70b726 100644
--- a/rust/pin-init/internal/src/pinned_drop.rs
+++ b/rust/pin-init/internal/src/pinned_drop.rs
@@ -28,8 +28,7 @@ pub(crate) fn pinned_drop(_args: TokenStream, input: TokenStream) -> TokenStream
             // Found the end of the generics, this should be `PinnedDrop`.
             assert!(
                 matches!(tt, TokenTree::Ident(i) if i.to_string() == "PinnedDrop"),
-                "expected 'PinnedDrop', found: '{:?}'",
-                tt
+                "expected 'PinnedDrop', found: '{tt:?}'"
             );
             pinned_drop_idx = Some(i);
             break;
diff --git a/rust/pin-init/src/alloc.rs b/rust/pin-init/src/alloc.rs
index e16baa3b434e..5017f57442d8 100644
--- a/rust/pin-init/src/alloc.rs
+++ b/rust/pin-init/src/alloc.rs
@@ -17,11 +17,9 @@ use crate::{
 
 pub extern crate alloc;
 
-// SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee).
-//
-// In this case we are allowed to use `T: ?Sized`, since all zeros is the `None` variant and there
-// is no problem with a VTABLE pointer being null.
-unsafe impl<T: ?Sized> ZeroableOption for Box<T> {}
+// SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee:
+// <https://doc.rust-lang.org/stable/std/option/index.html#representation>).
+unsafe impl<T> ZeroableOption for Box<T> {}
 
 /// Smart pointer that can initialize memory in-place.
 pub trait InPlaceInit<T>: Sized {
diff --git a/rust/pin-init/src/lib.rs b/rust/pin-init/src/lib.rs
index 05c44514765e..0806c689f693 100644
--- a/rust/pin-init/src/lib.rs
+++ b/rust/pin-init/src/lib.rs
@@ -1447,7 +1447,7 @@ impl_zeroable! {
     {<T: ?Sized + Zeroable>} UnsafeCell<T>,
 
     // SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee:
-    // https://doc.rust-lang.org/stable/std/option/index.html#representation).
+    // <https://doc.rust-lang.org/stable/std/option/index.html#representation>).
     Option<NonZeroU8>, Option<NonZeroU16>, Option<NonZeroU32>, Option<NonZeroU64>,
     Option<NonZeroU128>, Option<NonZeroUsize>,
     Option<NonZeroI8>, Option<NonZeroI16>, Option<NonZeroI32>, Option<NonZeroI64>,
diff --git a/rust/uapi/lib.rs b/rust/uapi/lib.rs
index 13495910271f..c98d7a8cde77 100644
--- a/rust/uapi/lib.rs
+++ b/rust/uapi/lib.rs
@@ -24,6 +24,7 @@
     unreachable_pub,
     unsafe_op_in_unsafe_fn
 )]
+#![cfg_attr(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES, allow(unnecessary_transmutes))]
 
 // Manual definition of blocklisted types.
 type __kernel_size_t = usize;
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 5b632635e00d..95a4fa1f1e44 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -376,7 +376,7 @@ $(obj)/%.o: $(src)/%.c
 	@echo "  CLANG-bpf " $@
 	$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \
 		-I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \
-		-I$(LIBBPF_INCLUDE) \
+		-I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \
 		-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
 		-D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \
diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c
index b7997541f7ee..f93d9145ab8a 100644
--- a/samples/bpf/sockex2_kern.c
+++ b/samples/bpf/sockex2_kern.c
@@ -31,7 +31,6 @@ static inline int proto_ports_offset(__u64 proto)
 	switch (proto) {
 	case IPPROTO_TCP:
 	case IPPROTO_UDP:
-	case IPPROTO_DCCP:
 	case IPPROTO_ESP:
 	case IPPROTO_SCTP:
 	case IPPROTO_UDPLITE:
diff --git a/samples/ftrace/sample-trace-array.c b/samples/ftrace/sample-trace-array.c
index dac67c367457..4147616102f9 100644
--- a/samples/ftrace/sample-trace-array.c
+++ b/samples/ftrace/sample-trace-array.c
@@ -112,7 +112,7 @@ static int __init sample_trace_array_init(void)
 	/*
 	 * If context specific per-cpu buffers havent already been allocated.
 	 */
-	trace_printk_init_buffers();
+	trace_array_init_printk(tr);
 
 	simple_tsk = kthread_run(simple_thread, NULL, "sample-instance");
 	if (IS_ERR(simple_tsk)) {
diff --git a/samples/livepatch/livepatch-callbacks-busymod.c b/samples/livepatch/livepatch-callbacks-busymod.c
index 69105596e72e..fadc2a85cb35 100644
--- a/samples/livepatch/livepatch-callbacks-busymod.c
+++ b/samples/livepatch/livepatch-callbacks-busymod.c
@@ -56,4 +56,5 @@ static void livepatch_callbacks_mod_exit(void)
 
 module_init(livepatch_callbacks_mod_init);
 module_exit(livepatch_callbacks_mod_exit);
+MODULE_DESCRIPTION("Live patching demo for (un)patching callbacks, support module");
 MODULE_LICENSE("GPL");
diff --git a/samples/livepatch/livepatch-callbacks-demo.c b/samples/livepatch/livepatch-callbacks-demo.c
index 11c3f4357812..9e69d9caed25 100644
--- a/samples/livepatch/livepatch-callbacks-demo.c
+++ b/samples/livepatch/livepatch-callbacks-demo.c
@@ -192,5 +192,6 @@ static void livepatch_callbacks_demo_exit(void)
 
 module_init(livepatch_callbacks_demo_init);
 module_exit(livepatch_callbacks_demo_exit);
+MODULE_DESCRIPTION("Live patching demo for (un)patching callbacks");
 MODULE_LICENSE("GPL");
 MODULE_INFO(livepatch, "Y");
diff --git a/samples/livepatch/livepatch-callbacks-mod.c b/samples/livepatch/livepatch-callbacks-mod.c
index 2a074f422a51..d1851b471ad9 100644
--- a/samples/livepatch/livepatch-callbacks-mod.c
+++ b/samples/livepatch/livepatch-callbacks-mod.c
@@ -38,4 +38,5 @@ static void livepatch_callbacks_mod_exit(void)
 
 module_init(livepatch_callbacks_mod_init);
 module_exit(livepatch_callbacks_mod_exit);
+MODULE_DESCRIPTION("Live patching demo for (un)patching callbacks, support module");
 MODULE_LICENSE("GPL");
diff --git a/samples/livepatch/livepatch-sample.c b/samples/livepatch/livepatch-sample.c
index cd76d7ebe598..5263a2f31c48 100644
--- a/samples/livepatch/livepatch-sample.c
+++ b/samples/livepatch/livepatch-sample.c
@@ -66,5 +66,6 @@ static void livepatch_exit(void)
 
 module_init(livepatch_init);
 module_exit(livepatch_exit);
+MODULE_DESCRIPTION("Kernel Live Patching Sample Module");
 MODULE_LICENSE("GPL");
 MODULE_INFO(livepatch, "Y");
diff --git a/samples/livepatch/livepatch-shadow-fix1.c b/samples/livepatch/livepatch-shadow-fix1.c
index f3f153895d6c..cbf68ca40097 100644
--- a/samples/livepatch/livepatch-shadow-fix1.c
+++ b/samples/livepatch/livepatch-shadow-fix1.c
@@ -168,5 +168,6 @@ static void livepatch_shadow_fix1_exit(void)
 
 module_init(livepatch_shadow_fix1_init);
 module_exit(livepatch_shadow_fix1_exit);
+MODULE_DESCRIPTION("Live patching demo for shadow variables");
 MODULE_LICENSE("GPL");
 MODULE_INFO(livepatch, "Y");
diff --git a/samples/livepatch/livepatch-shadow-fix2.c b/samples/livepatch/livepatch-shadow-fix2.c
index 361046a4f10c..b99122cb221f 100644
--- a/samples/livepatch/livepatch-shadow-fix2.c
+++ b/samples/livepatch/livepatch-shadow-fix2.c
@@ -128,5 +128,6 @@ static void livepatch_shadow_fix2_exit(void)
 
 module_init(livepatch_shadow_fix2_init);
 module_exit(livepatch_shadow_fix2_exit);
+MODULE_DESCRIPTION("Live patching demo for shadow variables");
 MODULE_LICENSE("GPL");
 MODULE_INFO(livepatch, "Y");
diff --git a/scripts/Makefile.compiler b/scripts/Makefile.compiler
index 8956587b8547..f4fcc1eaaeae 100644
--- a/scripts/Makefile.compiler
+++ b/scripts/Makefile.compiler
@@ -79,8 +79,8 @@ ld-option = $(call try-run, $(LD) $(KBUILD_LDFLAGS) $(1) -v,$(1),$(2),$(3))
 # Usage: MY_RUSTFLAGS += $(call __rustc-option,$(RUSTC),$(MY_RUSTFLAGS),-Cinstrument-coverage,-Zinstrument-coverage)
 # TODO: remove RUSTC_BOOTSTRAP=1 when we raise the minimum GNU Make version to 4.4
 __rustc-option = $(call try-run,\
-	echo '#![allow(missing_docs)]#![feature(no_core)]#![no_core]' | RUSTC_BOOTSTRAP=1\
-	$(1) --sysroot=/dev/null $(filter-out --sysroot=/dev/null,$(2)) $(3)\
+	echo '$(pound)![allow(missing_docs)]$(pound)![feature(no_core)]$(pound)![no_core]' | RUSTC_BOOTSTRAP=1\
+	$(1) --sysroot=/dev/null $(filter-out --sysroot=/dev/null --target=%,$(2)) $(3)\
 	--crate-type=rlib --out-dir=$(TMPOUT) --emit=obj=- - >/dev/null,$(3),$(4))
 
 # rustc-option
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index d75897559d18..fd649c68e198 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -8,6 +8,7 @@
 
 # Default set of warnings, always enabled
 KBUILD_CFLAGS += -Wall
+KBUILD_CFLAGS += -Wextra
 KBUILD_CFLAGS += -Wundef
 KBUILD_CFLAGS += -Werror=implicit-function-declaration
 KBUILD_CFLAGS += -Werror=implicit-int
@@ -15,7 +16,7 @@ KBUILD_CFLAGS += -Werror=return-type
 KBUILD_CFLAGS += -Werror=strict-prototypes
 KBUILD_CFLAGS += -Wno-format-security
 KBUILD_CFLAGS += -Wno-trigraphs
-KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,)
+KBUILD_CFLAGS += $(call cc-disable-warning, frame-address)
 KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 KBUILD_CFLAGS += -Wmissing-declarations
 KBUILD_CFLAGS += -Wmissing-prototypes
@@ -36,6 +37,18 @@ KBUILD_CFLAGS += -Wno-gnu
 # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111219
 KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow-non-kprintf)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation-non-kprintf)
+
+# Clang may emit a warning when a const variable, such as the dummy variables
+# in typecheck(), or const member of an aggregate type are not initialized,
+# which can result in unexpected behavior. However, in many audited cases of
+# the "field" variant of the warning, this is intentional because the field is
+# never used within a particular call path, the field is within a union with
+# other non-const members, or the containing object is not const so the field
+# can be modified via memcpy() / memset(). While the variable warning also gets
+# disabled with this same switch, there should not be too much coverage lost
+# because -Wuninitialized will still flag when an uninitialized const variable
+# is used.
+KBUILD_CFLAGS += $(call cc-disable-warning, default-const-init-unsafe)
 else
 
 # gcc inanely warns about local variables called 'main'
@@ -56,6 +69,13 @@ KBUILD_CFLAGS += -Wno-pointer-sign
 # globally built with -Wcast-function-type.
 KBUILD_CFLAGS += $(call cc-option, -Wcast-function-type)
 
+# Currently, disable -Wstringop-overflow for GCC 11, globally.
+KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-disable-warning, stringop-overflow)
+KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
+
+# Currently, disable -Wunterminated-string-initialization as broken
+KBUILD_CFLAGS += $(call cc-disable-warning, unterminated-string-initialization)
+
 # The allocators already balk at large sizes, so silence the compiler
 # warnings for bounds checks involving those possible values. While
 # -Wno-alloc-size-larger-than would normally be used here, earlier versions
@@ -82,7 +102,6 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init)
 # Warn if there is an enum types mismatch
 KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion)
 
-KBUILD_CFLAGS += -Wextra
 KBUILD_CFLAGS += -Wunused
 
 #
diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
index b0a6cd5b818c..b64862dc6f08 100644
--- a/scripts/Makefile.vmlinux
+++ b/scripts/Makefile.vmlinux
@@ -13,7 +13,7 @@ ifdef CONFIG_ARCH_VMLINUX_NEEDS_RELOCS
 vmlinux-final := vmlinux.unstripped
 
 quiet_cmd_strip_relocs = RSTRIP  $@
-      cmd_strip_relocs = $(OBJCOPY) --remove-section='.rel*' $< $@
+      cmd_strip_relocs = $(OBJCOPY) --remove-section='.rel*' --remove-section=!'.rel*.dyn' $< $@
 
 vmlinux: $(vmlinux-final) FORCE
 	$(call if_changed,strip_relocs)
@@ -94,10 +94,10 @@ $(vmlinux-final): $(RESOLVE_BTFIDS)
 endif
 
 ifdef CONFIG_BUILDTIME_TABLE_SORT
-vmlinux: scripts/sorttable
+$(vmlinux-final): scripts/sorttable
 endif
 
-# module.builtin.ranges
+# modules.builtin.ranges
 # ---------------------------------------------------------------------------
 ifdef CONFIG_BUILTIN_MODULE_RANGES
 __default: modules.builtin.ranges
diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o
index 938c7457717e..b024ffb3e201 100644
--- a/scripts/Makefile.vmlinux_o
+++ b/scripts/Makefile.vmlinux_o
@@ -73,7 +73,7 @@ vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE
 
 targets += vmlinux.o
 
-# module.builtin.modinfo
+# modules.builtin.modinfo
 # ---------------------------------------------------------------------------
 
 OBJCOPYFLAGS_modules.builtin.modinfo := -j .modinfo -O binary
@@ -82,7 +82,7 @@ targets += modules.builtin.modinfo
 modules.builtin.modinfo: vmlinux.o FORCE
 	$(call if_changed,objcopy)
 
-# module.builtin
+# modules.builtin
 # ---------------------------------------------------------------------------
 
 # The second line aids cases where multiple modules share the same object.
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 3d22bf863eec..298c8f8d7719 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -4804,7 +4804,7 @@ sub process {
 		}
 
 # do not use BUG() or variants
-		if ($line =~ /\b(?!AA_|BUILD_|DCCP_|IDA_|KVM_|RWLOCK_|snd_|SPIN_)(?:[a-zA-Z_]*_)?BUG(?:_ON)?(?:_[A-Z_]+)?\s*\(/) {
+		if ($line =~ /\b(?!AA_|BUILD_|IDA_|KVM_|RWLOCK_|snd_|SPIN_)(?:[a-zA-Z_]*_)?BUG(?:_ON)?(?:_[A-Z_]+)?\s*\(/) {
 			my $msg_level = \&WARN;
 			$msg_level = \&CHK if ($file);
 			&{$msg_level}("AVOID_BUG",
diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py
index cd41bc906fbd..fe663dd0c43b 100755
--- a/scripts/generate_rust_analyzer.py
+++ b/scripts/generate_rust_analyzer.py
@@ -112,6 +112,12 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
         cfg=["kernel"],
     )
 
+    append_crate(
+        "ffi",
+        srctree / "rust" / "ffi.rs",
+        ["core", "compiler_builtins"],
+    )
+
     def append_crate_with_generated(
         display_name,
         deps,
@@ -131,9 +137,9 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
             "exclude_dirs": [],
         }
 
-    append_crate_with_generated("bindings", ["core"])
-    append_crate_with_generated("uapi", ["core"])
-    append_crate_with_generated("kernel", ["core", "macros", "build_error", "pin_init", "bindings", "uapi"])
+    append_crate_with_generated("bindings", ["core", "ffi"])
+    append_crate_with_generated("uapi", ["core", "ffi"])
+    append_crate_with_generated("kernel", ["core", "macros", "build_error", "pin_init", "ffi", "bindings", "uapi"])
 
     def is_root_crate(build_file, target):
         try:
diff --git a/scripts/genksyms/keywords.c b/scripts/genksyms/keywords.c
index b85e0979a00c..ee1499d27061 100644
--- a/scripts/genksyms/keywords.c
+++ b/scripts/genksyms/keywords.c
@@ -17,6 +17,8 @@ static struct resword {
 	{ "__signed__", SIGNED_KEYW },
 	{ "__typeof", TYPEOF_KEYW },
 	{ "__typeof__", TYPEOF_KEYW },
+	{ "__typeof_unqual", TYPEOF_KEYW },
+	{ "__typeof_unqual__", TYPEOF_KEYW },
 	{ "__volatile", VOLATILE_KEYW },
 	{ "__volatile__", VOLATILE_KEYW },
 	{ "__builtin_va_list", VA_LIST_KEYW },
@@ -40,6 +42,10 @@ static struct resword {
 	// KAO. },
 	// { "attribute", ATTRIBUTE_KEYW },
 
+	// X86 named address space qualifiers
+	{ "__seg_gs", X86_SEG_KEYW },
+	{ "__seg_fs", X86_SEG_KEYW },
+
 	{ "auto", AUTO_KEYW },
 	{ "char", CHAR_KEYW },
 	{ "const", CONST_KEYW },
@@ -57,6 +63,7 @@ static struct resword {
 	{ "struct", STRUCT_KEYW },
 	{ "typedef", TYPEDEF_KEYW },
 	{ "typeof", TYPEOF_KEYW },
+	{ "typeof_unqual", TYPEOF_KEYW },
 	{ "union", UNION_KEYW },
 	{ "unsigned", UNSIGNED_KEYW },
 	{ "void", VOID_KEYW },
diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y
index ee600a804fa1..efdcf07c4eb6 100644
--- a/scripts/genksyms/parse.y
+++ b/scripts/genksyms/parse.y
@@ -91,6 +91,8 @@ static void record_compound(struct string_list **keyw,
 %token TYPEOF_KEYW
 %token VA_LIST_KEYW
 
+%token X86_SEG_KEYW
+
 %token EXPORT_SYMBOL_KEYW
 
 %token ASM_PHRASE
@@ -292,7 +294,8 @@ type_qualifier_seq:
 	;
 
 type_qualifier:
-	CONST_KEYW | VOLATILE_KEYW
+	X86_SEG_KEYW
+	| CONST_KEYW | VOLATILE_KEYW
 	| RESTRICT_KEYW
 		{ /* restrict has no effect in prototypes so ignore it */
 		  remove_node($1);
diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec
index 726f34e11960..98f206cb7c60 100644
--- a/scripts/package/kernel.spec
+++ b/scripts/package/kernel.spec
@@ -16,6 +16,7 @@ Source1: config
 Source2: diff.patch
 Provides: kernel-%{KERNELRELEASE}
 BuildRequires: bc binutils bison dwarves
+BuildRequires: (elfutils-devel or libdw-devel)
 BuildRequires: (elfutils-libelf-devel or libelf-devel) flex
 BuildRequires: gcc make openssl openssl-devel perl python3 rsync
 
diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 744ddba01d93..d4b007b38a47 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -210,7 +210,7 @@ Rules-Requires-Root: no
 Build-Depends: debhelper-compat (= 12)
 Build-Depends-Arch: bc, bison, flex,
  gcc-${host_gnu} <!pkg.${sourcename}.nokernelheaders>,
- kmod, libelf-dev:native,
+ kmod, libdw-dev:native, libelf-dev:native,
  libssl-dev:native, libssl-dev <!pkg.${sourcename}.nokernelheaders>,
  python3:native, rsync
 Homepage: https://www.kernel.org/
diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening
index c17366ce8224..3fe9d7b945c4 100644
--- a/security/Kconfig.hardening
+++ b/security/Kconfig.hardening
@@ -344,7 +344,7 @@ config CC_HAS_RANDSTRUCT
 
 choice
 	prompt "Randomize layout of sensitive kernel structures"
-	default RANDSTRUCT_FULL if COMPILE_TEST && (GCC_PLUGINS || CC_HAS_RANDSTRUCT)
+	default RANDSTRUCT_FULL if COMPILE_TEST && CC_HAS_RANDSTRUCT
 	default RANDSTRUCT_NONE
 	help
 	  If you enable this, the layouts of structures that are entirely
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index f3e7ac513db3..f99ab1a3b0f0 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -245,7 +245,9 @@ static int process_measurement(struct file *file, const struct cred *cred,
 				&allowed_algos);
 	violation_check = ((func == FILE_CHECK || func == MMAP_CHECK ||
 			    func == MMAP_CHECK_REQPROT) &&
-			   (ima_policy_flag & IMA_MEASURE));
+			   (ima_policy_flag & IMA_MEASURE) &&
+			   ((action & IMA_MEASURE) ||
+			    (file->f_mode & FMODE_WRITE)));
 	if (!action && !violation_check)
 		return 0;
 
diff --git a/security/landlock/audit.c b/security/landlock/audit.c
index 7e5e0ed0e4e5..c52d079cdb77 100644
--- a/security/landlock/audit.c
+++ b/security/landlock/audit.c
@@ -175,7 +175,7 @@ static void test_get_hierarchy(struct kunit *const test)
 	KUNIT_EXPECT_EQ(test, 10, get_hierarchy(&dom2, 0)->id);
 	KUNIT_EXPECT_EQ(test, 20, get_hierarchy(&dom2, 1)->id);
 	KUNIT_EXPECT_EQ(test, 30, get_hierarchy(&dom2, 2)->id);
-	KUNIT_EXPECT_EQ(test, 30, get_hierarchy(&dom2, -1)->id);
+	/* KUNIT_EXPECT_EQ(test, 30, get_hierarchy(&dom2, -1)->id); */
 }
 
 #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
@@ -437,7 +437,7 @@ void landlock_log_denial(const struct landlock_cred_security *const subject,
 		return;
 
 	/* Checks if the current exec was restricting itself. */
-	if (subject->domain_exec & (1 << youngest_layer)) {
+	if (subject->domain_exec & BIT(youngest_layer)) {
 		/* Ignores denials for the same execution. */
 		if (!youngest_denied->log_same_exec)
 			return;
diff --git a/security/landlock/domain.c b/security/landlock/domain.c
index bae2e9909013..a647b68e8d06 100644
--- a/security/landlock/domain.c
+++ b/security/landlock/domain.c
@@ -16,6 +16,7 @@
 #include <linux/path.h>
 #include <linux/pid.h>
 #include <linux/sched.h>
+#include <linux/signal.h>
 #include <linux/uidgid.h>
 
 #include "access.h"
@@ -99,8 +100,7 @@ static struct landlock_details *get_current_details(void)
 		return ERR_PTR(-ENOMEM);
 
 	memcpy(details->exe_path, path_str, path_size);
-	WARN_ON_ONCE(current_cred() != current_real_cred());
-	details->pid = get_pid(task_pid(current));
+	details->pid = get_pid(task_tgid(current));
 	details->uid = from_kuid(&init_user_ns, current_uid());
 	get_task_comm(details->comm, current);
 	return details;
diff --git a/security/landlock/domain.h b/security/landlock/domain.h
index ed0d348e214c..7fb70b25f85a 100644
--- a/security/landlock/domain.h
+++ b/security/landlock/domain.h
@@ -130,7 +130,7 @@ int landlock_init_hierarchy_log(struct landlock_hierarchy *const hierarchy);
 static inline void
 landlock_free_hierarchy_details(struct landlock_hierarchy *const hierarchy)
 {
-	if (WARN_ON_ONCE(!hierarchy || !hierarchy->details))
+	if (!hierarchy || !hierarchy->details)
 		return;
 
 	put_pid(hierarchy->details->pid);
diff --git a/security/landlock/id.c b/security/landlock/id.c
index 11fab9259c15..56f7cc0fc744 100644
--- a/security/landlock/id.c
+++ b/security/landlock/id.c
@@ -7,6 +7,7 @@
 
 #include <kunit/test.h>
 #include <linux/atomic.h>
+#include <linux/bitops.h>
 #include <linux/random.h>
 #include <linux/spinlock.h>
 
@@ -25,7 +26,7 @@ static void __init init_id(atomic64_t *const counter, const u32 random_32bits)
 	 * Ensures sure 64-bit values are always used by user space (or may
 	 * fail with -EOVERFLOW), and makes this testable.
 	 */
-	init = 1ULL << 32;
+	init = BIT_ULL(32);
 
 	/*
 	 * Makes a large (2^32) boot-time value to limit ID collision in logs
@@ -105,7 +106,7 @@ static u64 get_id_range(size_t number_of_ids, atomic64_t *const counter,
 	 * to get a new ID (e.g. a full landlock_restrict_self() call), and the
 	 * cost of draining all available IDs during the system's uptime.
 	 */
-	random_4bits = random_4bits % (1 << 4);
+	random_4bits &= 0b1111;
 	step = number_of_ids + random_4bits;
 
 	/* It is safe to cast a signed atomic to an unsigned value. */
@@ -144,6 +145,19 @@ static void test_range1_rand1(struct kunit *const test)
 		init + 2);
 }
 
+static void test_range1_rand15(struct kunit *const test)
+{
+	atomic64_t counter;
+	u64 init;
+
+	init = get_random_u32();
+	atomic64_set(&counter, init);
+	KUNIT_EXPECT_EQ(test, get_id_range(1, &counter, 15), init);
+	KUNIT_EXPECT_EQ(
+		test, get_id_range(get_random_u8(), &counter, get_random_u8()),
+		init + 16);
+}
+
 static void test_range1_rand16(struct kunit *const test)
 {
 	atomic64_t counter;
@@ -196,6 +210,19 @@ static void test_range2_rand2(struct kunit *const test)
 		init + 4);
 }
 
+static void test_range2_rand15(struct kunit *const test)
+{
+	atomic64_t counter;
+	u64 init;
+
+	init = get_random_u32();
+	atomic64_set(&counter, init);
+	KUNIT_EXPECT_EQ(test, get_id_range(2, &counter, 15), init);
+	KUNIT_EXPECT_EQ(
+		test, get_id_range(get_random_u8(), &counter, get_random_u8()),
+		init + 17);
+}
+
 static void test_range2_rand16(struct kunit *const test)
 {
 	atomic64_t counter;
@@ -232,10 +259,12 @@ static struct kunit_case __refdata test_cases[] = {
 	KUNIT_CASE(test_init_once),
 	KUNIT_CASE(test_range1_rand0),
 	KUNIT_CASE(test_range1_rand1),
+	KUNIT_CASE(test_range1_rand15),
 	KUNIT_CASE(test_range1_rand16),
 	KUNIT_CASE(test_range2_rand0),
 	KUNIT_CASE(test_range2_rand1),
 	KUNIT_CASE(test_range2_rand2),
+	KUNIT_CASE(test_range2_rand15),
 	KUNIT_CASE(test_range2_rand16),
 	{}
 	/* clang-format on */
diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c
index 54a9f29e6ebb..33eafb71e4f3 100644
--- a/security/landlock/syscalls.c
+++ b/security/landlock/syscalls.c
@@ -9,6 +9,7 @@
 
 #include <asm/current.h>
 #include <linux/anon_inodes.h>
+#include <linux/bitops.h>
 #include <linux/build_bug.h>
 #include <linux/capability.h>
 #include <linux/cleanup.h>
@@ -169,20 +170,16 @@ const int landlock_abi_version = 7;
  *        the new ruleset.
  * @size: Size of the pointed &struct landlock_ruleset_attr (needed for
  *        backward and forward compatibility).
- * @flags: Supported value:
+ * @flags: Supported values:
+ *
  *         - %LANDLOCK_CREATE_RULESET_VERSION
  *         - %LANDLOCK_CREATE_RULESET_ERRATA
  *
  * This system call enables to create a new Landlock ruleset, and returns the
  * related file descriptor on success.
  *
- * If @flags is %LANDLOCK_CREATE_RULESET_VERSION and @attr is NULL and @size is
- * 0, then the returned value is the highest supported Landlock ABI version
- * (starting at 1).
- *
- * If @flags is %LANDLOCK_CREATE_RULESET_ERRATA and @attr is NULL and @size is
- * 0, then the returned value is a bitmask of fixed issues for the current
- * Landlock ABI version.
+ * If %LANDLOCK_CREATE_RULESET_VERSION or %LANDLOCK_CREATE_RULESET_ERRATA is
+ * set, then @attr must be NULL and @size must be 0.
  *
  * Possible returned errors are:
  *
@@ -191,6 +188,9 @@ const int landlock_abi_version = 7;
  * - %E2BIG: @attr or @size inconsistencies;
  * - %EFAULT: @attr or @size inconsistencies;
  * - %ENOMSG: empty &landlock_ruleset_attr.handled_access_fs.
+ *
+ * .. kernel-doc:: include/uapi/linux/landlock.h
+ *     :identifiers: landlock_create_ruleset_flags
  */
 SYSCALL_DEFINE3(landlock_create_ruleset,
 		const struct landlock_ruleset_attr __user *const, attr,
@@ -452,18 +452,15 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd,
  * @ruleset_fd: File descriptor tied to the ruleset to merge with the target.
  * @flags: Supported values:
  *
- * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
- * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
- * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
+ *         - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
+ *         - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
+ *         - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
  *
  * This system call enables to enforce a Landlock ruleset on the current
  * thread.  Enforcing a ruleset requires that the task has %CAP_SYS_ADMIN in its
  * namespace or is running with no_new_privs.  This avoids scenarios where
  * unprivileged tasks can affect the behavior of privileged children.
  *
- * It is allowed to only pass the %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
- * flag with a @ruleset_fd value of -1.
- *
  * Possible returned errors are:
  *
  * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time;
@@ -475,6 +472,9 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd,
  *   %CAP_SYS_ADMIN in its namespace.
  * - %E2BIG: The maximum number of stacked rulesets is reached for the current
  *   thread.
+ *
+ * .. kernel-doc:: include/uapi/linux/landlock.h
+ *     :identifiers: landlock_restrict_self_flags
  */
 SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32,
 		flags)
@@ -564,7 +564,7 @@ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32,
 	new_llcred->domain = new_dom;
 
 #ifdef CONFIG_AUDIT
-	new_llcred->domain_exec |= 1 << (new_dom->num_layers - 1);
+	new_llcred->domain_exec |= BIT(new_dom->num_layers - 1);
 #endif /* CONFIG_AUDIT */
 
 	return commit_creds(new_cred);
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 1b942b4908a2..7d623b00495c 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -24,7 +24,6 @@
 #include <net/ipv6.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
-#include <linux/dccp.h>
 #include <linux/sctp.h>
 #include <linux/lsm_audit.h>
 #include <linux/security.h>
@@ -68,13 +67,6 @@ int ipv4_skb_to_auditdata(struct sk_buff *skb,
 		ad->u.net->dport = uh->dest;
 		break;
 	}
-	case IPPROTO_DCCP: {
-		struct dccp_hdr *dh = dccp_hdr(skb);
-
-		ad->u.net->sport = dh->dccph_sport;
-		ad->u.net->dport = dh->dccph_dport;
-		break;
-	}
 	case IPPROTO_SCTP: {
 		struct sctphdr *sh = sctp_hdr(skb);
 
@@ -140,17 +132,6 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb,
 		ad->u.net->dport = uh->dest;
 		break;
 	}
-	case IPPROTO_DCCP: {
-		struct dccp_hdr _dccph, *dh;
-
-		dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph);
-		if (dh == NULL)
-			break;
-
-		ad->u.net->sport = dh->dccph_sport;
-		ad->u.net->dport = dh->dccph_dport;
-		break;
-	}
 	case IPPROTO_SCTP: {
 		struct sctphdr _sctph, *sh;
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index e7a7dcab81db..b2695785610a 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -65,7 +65,6 @@
 #include <net/netlink.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
-#include <linux/dccp.h>
 #include <linux/sctp.h>
 #include <net/sctp/structs.h>
 #include <linux/quota.h>
@@ -1191,8 +1190,6 @@ static inline u16 socket_type_to_security_class(int family, int type, int protoc
 				return SECCLASS_ICMP_SOCKET;
 			else
 				return SECCLASS_RAWIP_SOCKET;
-		case SOCK_DCCP:
-			return SECCLASS_DCCP_SOCKET;
 		default:
 			return SECCLASS_RAWIP_SOCKET;
 		}
@@ -4392,22 +4389,6 @@ static int selinux_parse_skb_ipv4(struct sk_buff *skb,
 		break;
 	}
 
-	case IPPROTO_DCCP: {
-		struct dccp_hdr _dccph, *dh;
-
-		if (ntohs(ih->frag_off) & IP_OFFSET)
-			break;
-
-		offset += ihlen;
-		dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph);
-		if (dh == NULL)
-			break;
-
-		ad->u.net->sport = dh->dccph_sport;
-		ad->u.net->dport = dh->dccph_dport;
-		break;
-	}
-
 #if IS_ENABLED(CONFIG_IP_SCTP)
 	case IPPROTO_SCTP: {
 		struct sctphdr _sctph, *sh;
@@ -4486,18 +4467,6 @@ static int selinux_parse_skb_ipv6(struct sk_buff *skb,
 		break;
 	}
 
-	case IPPROTO_DCCP: {
-		struct dccp_hdr _dccph, *dh;
-
-		dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph);
-		if (dh == NULL)
-			break;
-
-		ad->u.net->sport = dh->dccph_sport;
-		ad->u.net->dport = dh->dccph_dport;
-		break;
-	}
-
 #if IS_ENABLED(CONFIG_IP_SCTP)
 	case IPPROTO_SCTP: {
 		struct sctphdr _sctph, *sh;
@@ -4849,10 +4818,6 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 			node_perm = UDP_SOCKET__NODE_BIND;
 			break;
 
-		case SECCLASS_DCCP_SOCKET:
-			node_perm = DCCP_SOCKET__NODE_BIND;
-			break;
-
 		case SECCLASS_SCTP_SOCKET:
 			node_perm = SCTP_SOCKET__NODE_BIND;
 			break;
@@ -4908,11 +4873,10 @@ static int selinux_socket_connect_helper(struct socket *sock,
 		return 0;
 
 	/*
-	 * If a TCP, DCCP or SCTP socket, check name_connect permission
+	 * If a TCP or SCTP socket, check name_connect permission
 	 * for the port.
 	 */
 	if (sksec->sclass == SECCLASS_TCP_SOCKET ||
-	    sksec->sclass == SECCLASS_DCCP_SOCKET ||
 	    sksec->sclass == SECCLASS_SCTP_SOCKET) {
 		struct common_audit_data ad;
 		struct lsm_network_audit net = {0,};
@@ -4957,9 +4921,6 @@ static int selinux_socket_connect_helper(struct socket *sock,
 		case SECCLASS_TCP_SOCKET:
 			perm = TCP_SOCKET__NAME_CONNECT;
 			break;
-		case SECCLASS_DCCP_SOCKET:
-			perm = DCCP_SOCKET__NAME_CONNECT;
-			break;
 		case SECCLASS_SCTP_SOCKET:
 			perm = SCTP_SOCKET__NAME_CONNECT;
 			break;
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index 04a9b480885e..5665aa5e7853 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -127,8 +127,6 @@ const struct security_class_mapping secclass_map[] = {
 	{ "key",
 	  { "view", "read", "write", "search", "link", "setattr", "create",
 	    NULL } },
-	{ "dccp_socket",
-	  { COMMON_SOCK_PERMS, "node_bind", "name_connect", NULL } },
 	{ "memprotect", { "mmap_zero", NULL } },
 	{ "peer", { "recv", NULL } },
 	{ "capability2", { COMMON_CAP2_PERMS, NULL } },
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 3a95986b134f..2c0b07f9fbbd 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -98,7 +98,6 @@ static const struct nlmsg_perm nlmsg_route_perms[] = {
 
 static const struct nlmsg_perm nlmsg_tcpdiag_perms[] = {
 	{ TCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
-	{ DCCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 	{ SOCK_DIAG_BY_FAMILY, NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 	{ SOCK_DESTROY, NETLINK_TCPDIAG_SOCKET__NLMSG_WRITE },
 };
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 99833168604e..fc340a6f0dde 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -24,7 +24,6 @@
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
-#include <linux/dccp.h>
 #include <linux/icmpv6.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
@@ -4061,7 +4060,6 @@ static int smk_skb_to_addr_ipv6(struct sk_buff *skb, struct sockaddr_in6 *sip)
 	__be16 frag_off;
 	struct tcphdr _tcph, *th;
 	struct udphdr _udph, *uh;
-	struct dccp_hdr _dccph, *dh;
 
 	sip->sin6_port = 0;
 
@@ -4090,11 +4088,6 @@ static int smk_skb_to_addr_ipv6(struct sk_buff *skb, struct sockaddr_in6 *sip)
 		if (uh != NULL)
 			sip->sin6_port = uh->source;
 		break;
-	case IPPROTO_DCCP:
-		dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph);
-		if (dh != NULL)
-			sip->sin6_port = dh->dccph_sport;
-		break;
 	}
 	return proto;
 }
@@ -4216,7 +4209,7 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	case PF_INET6:
 		proto = smk_skb_to_addr_ipv6(skb, &sadd);
 		if (proto != IPPROTO_UDP && proto != IPPROTO_UDPLITE &&
-		    proto != IPPROTO_TCP && proto != IPPROTO_DCCP)
+		    proto != IPPROTO_TCP)
 			break;
 #ifdef SMACK_IPV6_SECMARK_LABELING
 		skp = smack_from_skb(skb);
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index 4683b9139c56..4ecb17bd5436 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -1074,8 +1074,7 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream)
 	runtime->oss.params = 0;
 	runtime->oss.prepare = 1;
 	runtime->oss.buffer_used = 0;
-	if (runtime->dma_area)
-		snd_pcm_format_set_silence(runtime->format, runtime->dma_area, bytes_to_samples(runtime, runtime->dma_bytes));
+	snd_pcm_runtime_buffer_set_silence(runtime);
 
 	runtime->oss.period_frames = snd_pcm_alsa_frames(substream, oss_period_size);
 
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 6c2b6a62d9d2..853ac5bb33ff 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -723,6 +723,17 @@ static void snd_pcm_buffer_access_unlock(struct snd_pcm_runtime *runtime)
 	atomic_inc(&runtime->buffer_accessing);
 }
 
+/* fill the PCM buffer with the current silence format; called from pcm_oss.c */
+void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime)
+{
+	snd_pcm_buffer_access_lock(runtime);
+	if (runtime->dma_area)
+		snd_pcm_format_set_silence(runtime->format, runtime->dma_area,
+					   bytes_to_samples(runtime, runtime->dma_bytes));
+	snd_pcm_buffer_access_unlock(runtime);
+}
+EXPORT_SYMBOL_GPL(snd_pcm_runtime_buffer_set_silence);
+
 #if IS_ENABLED(CONFIG_SND_PCM_OSS)
 #define is_oss_stream(substream)	((substream)->oss.oss)
 #else
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 198c598a5393..880240924bfd 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -732,15 +732,21 @@ static int snd_seq_deliver_single_event(struct snd_seq_client *client,
  */
 static int __deliver_to_subscribers(struct snd_seq_client *client,
 				    struct snd_seq_event *event,
-				    struct snd_seq_client_port *src_port,
-				    int atomic, int hop)
+				    int port, int atomic, int hop)
 {
+	struct snd_seq_client_port *src_port;
 	struct snd_seq_subscribers *subs;
 	int err, result = 0, num_ev = 0;
 	union __snd_seq_event event_saved;
 	size_t saved_size;
 	struct snd_seq_port_subs_info *grp;
 
+	if (port < 0)
+		return 0;
+	src_port = snd_seq_port_use_ptr(client, port);
+	if (!src_port)
+		return 0;
+
 	/* save original event record */
 	saved_size = snd_seq_event_packet_size(event);
 	memcpy(&event_saved, event, saved_size);
@@ -775,6 +781,7 @@ static int __deliver_to_subscribers(struct snd_seq_client *client,
 		read_unlock(&grp->list_lock);
 	else
 		up_read(&grp->list_mutex);
+	snd_seq_port_unlock(src_port);
 	memcpy(event, &event_saved, saved_size);
 	return (result < 0) ? result : num_ev;
 }
@@ -783,25 +790,32 @@ static int deliver_to_subscribers(struct snd_seq_client *client,
 				  struct snd_seq_event *event,
 				  int atomic, int hop)
 {
-	struct snd_seq_client_port *src_port;
-	int ret = 0, ret2;
-
-	src_port = snd_seq_port_use_ptr(client, event->source.port);
-	if (src_port) {
-		ret = __deliver_to_subscribers(client, event, src_port, atomic, hop);
-		snd_seq_port_unlock(src_port);
-	}
-
-	if (client->ump_endpoint_port < 0 ||
-	    event->source.port == client->ump_endpoint_port)
-		return ret;
+	int ret;
+#if IS_ENABLED(CONFIG_SND_SEQ_UMP)
+	int ret2;
+#endif
 
-	src_port = snd_seq_port_use_ptr(client, client->ump_endpoint_port);
-	if (!src_port)
+	ret = __deliver_to_subscribers(client, event,
+				       event->source.port, atomic, hop);
+#if IS_ENABLED(CONFIG_SND_SEQ_UMP)
+	if (!snd_seq_client_is_ump(client) || client->ump_endpoint_port < 0)
 		return ret;
-	ret2 = __deliver_to_subscribers(client, event, src_port, atomic, hop);
-	snd_seq_port_unlock(src_port);
-	return ret2 < 0 ? ret2 : ret;
+	/* If it's an event from EP port (and with a UMP group),
+	 * deliver to subscribers of the corresponding UMP group port, too.
+	 * Or, if it's from non-EP port, deliver to subscribers of EP port, too.
+	 */
+	if (event->source.port == client->ump_endpoint_port)
+		ret2 = __deliver_to_subscribers(client, event,
+						snd_seq_ump_group_port(event),
+						atomic, hop);
+	else
+		ret2 = __deliver_to_subscribers(client, event,
+						client->ump_endpoint_port,
+						atomic, hop);
+	if (ret2 < 0)
+		return ret2;
+#endif
+	return ret;
 }
 
 /* deliver an event to the destination port(s).
diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c
index ff7e558b4d51..db2f169cae11 100644
--- a/sound/core/seq/seq_ump_convert.c
+++ b/sound/core/seq/seq_ump_convert.c
@@ -1285,3 +1285,21 @@ int snd_seq_deliver_to_ump(struct snd_seq_client *source,
 	else
 		return cvt_to_ump_midi1(dest, dest_port, event, atomic, hop);
 }
+
+/* return the UMP group-port number of the event;
+ * return -1 if groupless or non-UMP event
+ */
+int snd_seq_ump_group_port(const struct snd_seq_event *event)
+{
+	const struct snd_seq_ump_event *ump_ev =
+		(const struct snd_seq_ump_event *)event;
+	unsigned char type;
+
+	if (!snd_seq_ev_is_ump(event))
+		return -1;
+	type = ump_message_type(ump_ev->ump[0]);
+	if (ump_is_groupless_msg(type))
+		return -1;
+	/* group-port number starts from 1 */
+	return ump_message_group(ump_ev->ump[0]) + 1;
+}
diff --git a/sound/core/seq/seq_ump_convert.h b/sound/core/seq/seq_ump_convert.h
index 6c146d803280..4abf0a7637d7 100644
--- a/sound/core/seq/seq_ump_convert.h
+++ b/sound/core/seq/seq_ump_convert.h
@@ -18,5 +18,6 @@ int snd_seq_deliver_to_ump(struct snd_seq_client *source,
 			   struct snd_seq_client_port *dest_port,
 			   struct snd_seq_event *event,
 			   int atomic, int hop);
+int snd_seq_ump_group_port(const struct snd_seq_event *event);
 
 #endif /* __SEQ_UMP_CONVERT_H */
diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c
index 8686adaf4531..d3511135f7d3 100644
--- a/sound/hda/intel-sdw-acpi.c
+++ b/sound/hda/intel-sdw-acpi.c
@@ -177,7 +177,7 @@ static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level,
  * sdw_intel_startup() is required for creation of devices and bus
  * startup
  */
-int sdw_intel_acpi_scan(acpi_handle *parent_handle,
+int sdw_intel_acpi_scan(acpi_handle parent_handle,
 			struct sdw_intel_acpi_info *info)
 {
 	acpi_status status;
diff --git a/sound/isa/azt2320.c b/sound/isa/azt2320.c
index b937c9138d12..588b9f0831d3 100644
--- a/sound/isa/azt2320.c
+++ b/sound/isa/azt2320.c
@@ -189,8 +189,8 @@ static int snd_card_azt2320_probe(int dev,
 	if (error < 0)
 		return error;
 
-	strcpy(card->driver, "AZT2320");
-	strcpy(card->shortname, "Aztech AZT2320");
+	strscpy(card->driver, "AZT2320");
+	strscpy(card->shortname, "Aztech AZT2320");
 	sprintf(card->longname, "%s, WSS at 0x%lx, irq %i, dma %i&%i",
 		card->shortname, chip->port, irq[dev], dma1[dev], dma2[dev]);
 
diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c
index c6c018b40c69..4e0693f0ab0f 100644
--- a/sound/pci/es1968.c
+++ b/sound/pci/es1968.c
@@ -1561,7 +1561,7 @@ static int snd_es1968_capture_open(struct snd_pcm_substream *substream)
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct es1968 *chip = snd_pcm_substream_chip(substream);
 	struct esschan *es;
-	int apu1, apu2;
+	int err, apu1, apu2;
 
 	apu1 = snd_es1968_alloc_apu_pair(chip, ESM_APU_PCM_CAPTURE);
 	if (apu1 < 0)
@@ -1605,7 +1605,9 @@ static int snd_es1968_capture_open(struct snd_pcm_substream *substream)
 	runtime->hw = snd_es1968_capture;
 	runtime->hw.buffer_bytes_max = runtime->hw.period_bytes_max =
 		calc_available_memory_size(chip) - 1024; /* keep MIXBUF size */
-	snd_pcm_hw_constraint_pow2(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_BYTES);
+	err = snd_pcm_hw_constraint_pow2(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_BYTES);
+	if (err < 0)
+		return err;
 
 	spin_lock_irq(&chip->substream_lock);
 	list_add(&es->list, &chip->substream_list);
diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig
index fb955a205d50..9c427270ff4f 100644
--- a/sound/pci/hda/Kconfig
+++ b/sound/pci/hda/Kconfig
@@ -96,9 +96,7 @@ config SND_HDA_CIRRUS_SCODEC
 
 config SND_HDA_CIRRUS_SCODEC_KUNIT_TEST
 	tristate "KUnit test for Cirrus side-codec library" if !KUNIT_ALL_TESTS
-	select SND_HDA_CIRRUS_SCODEC
-	select GPIOLIB
-	depends on KUNIT
+	depends on SND_HDA_CIRRUS_SCODEC && GPIOLIB && KUNIT
 	default KUNIT_ALL_TESTS
 	help
 	  This builds KUnit tests for the cirrus side-codec library.
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 79004bc8107b..20ab1fb2195f 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -441,6 +441,10 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 		alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000);
 		fallthrough;
 	case 0x10ec0215:
+	case 0x10ec0236:
+	case 0x10ec0245:
+	case 0x10ec0256:
+	case 0x10ec0257:
 	case 0x10ec0285:
 	case 0x10ec0289:
 		alc_update_coef_idx(codec, 0x36, 1<<13, 0);
@@ -448,12 +452,8 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0230:
 	case 0x10ec0233:
 	case 0x10ec0235:
-	case 0x10ec0236:
-	case 0x10ec0245:
 	case 0x10ec0255:
-	case 0x10ec0256:
 	case 0x19e58326:
-	case 0x10ec0257:
 	case 0x10ec0282:
 	case 0x10ec0283:
 	case 0x10ec0286:
@@ -6742,6 +6742,25 @@ static void alc274_fixup_bind_dacs(struct hda_codec *codec,
 	codec->power_save_node = 0;
 }
 
+/* avoid DAC 0x06 for speaker switch 0x17; it has no volume control */
+static void alc274_fixup_hp_aio_bind_dacs(struct hda_codec *codec,
+				    const struct hda_fixup *fix, int action)
+{
+	static const hda_nid_t conn[] = { 0x02, 0x03 }; /* exclude 0x06 */
+	/* The speaker is routed to the Node 0x06 by a mistake, thus the
+	 * speaker's volume can't be adjusted since the node doesn't have
+	 * Amp-out capability. Assure the speaker and lineout pin to be
+	 * coupled with DAC NID 0x02.
+	 */
+	static const hda_nid_t preferred_pairs[] = {
+		0x16, 0x02, 0x17, 0x02, 0x21, 0x03, 0
+	};
+	struct alc_spec *spec = codec->spec;
+
+	snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+	spec->gen.preferred_dacs = preferred_pairs;
+}
+
 /* avoid DAC 0x06 for bass speaker 0x17; it has no volume control */
 static void alc289_fixup_asus_ga401(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
@@ -6811,7 +6830,10 @@ static void alc256_fixup_chromebook(struct hda_codec *codec,
 
 	switch (action) {
 	case HDA_FIXUP_ACT_PRE_PROBE:
-		spec->gen.suppress_auto_mute = 1;
+		if (codec->core.subsystem_id == 0x10280d76)
+			spec->gen.suppress_auto_mute = 0;
+		else
+			spec->gen.suppress_auto_mute = 1;
 		spec->gen.suppress_auto_mic = 1;
 		spec->en_3kpull_low = false;
 		break;
@@ -6963,6 +6985,41 @@ static void alc285_fixup_hp_spectre_x360_eb1(struct hda_codec *codec,
 	}
 }
 
+/* GPIO1 = amplifier on/off */
+static void alc285_fixup_hp_spectre_x360_df1(struct hda_codec *codec,
+					     const struct hda_fixup *fix,
+					     int action)
+{
+	struct alc_spec *spec = codec->spec;
+	static const hda_nid_t conn[] = { 0x02 };
+	static const struct hda_pintbl pincfgs[] = {
+		{ 0x14, 0x90170110 },  /* front/high speakers */
+		{ 0x17, 0x90170130 },  /* back/bass speakers */
+		{ }
+	};
+
+	// enable mute led
+	alc285_fixup_hp_mute_led_coefbit(codec, fix, action);
+
+	switch (action) {
+	case HDA_FIXUP_ACT_PRE_PROBE:
+		/* needed for amp of back speakers */
+		spec->gpio_mask |= 0x01;
+		spec->gpio_dir |= 0x01;
+		snd_hda_apply_pincfgs(codec, pincfgs);
+		/* share DAC to have unified volume control */
+		snd_hda_override_conn_list(codec, 0x14, ARRAY_SIZE(conn), conn);
+		snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+		break;
+	case HDA_FIXUP_ACT_INIT:
+		/* need to toggle GPIO to enable the amp of back speakers */
+		alc_update_gpio_data(codec, 0x01, true);
+		msleep(100);
+		alc_update_gpio_data(codec, 0x01, false);
+		break;
+	}
+}
+
 static void alc285_fixup_hp_spectre_x360(struct hda_codec *codec,
 					  const struct hda_fixup *fix, int action)
 {
@@ -7761,6 +7818,7 @@ enum {
 	ALC280_FIXUP_HP_9480M,
 	ALC245_FIXUP_HP_X360_AMP,
 	ALC285_FIXUP_HP_SPECTRE_X360_EB1,
+	ALC285_FIXUP_HP_SPECTRE_X360_DF1,
 	ALC285_FIXUP_HP_ENVY_X360,
 	ALC288_FIXUP_DELL_HEADSET_MODE,
 	ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -7969,6 +8027,8 @@ enum {
 	ALC233_FIXUP_MEDION_MTL_SPK,
 	ALC294_FIXUP_BASS_SPEAKER_15,
 	ALC283_FIXUP_DELL_HP_RESUME,
+	ALC294_FIXUP_ASUS_CS35L41_SPI_2,
+	ALC274_FIXUP_HP_AIO_BIND_DACS,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -9836,6 +9896,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc285_fixup_hp_spectre_x360_eb1
 	},
+	[ALC285_FIXUP_HP_SPECTRE_X360_DF1] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_hp_spectre_x360_df1
+	},
 	[ALC285_FIXUP_HP_ENVY_X360] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc285_fixup_hp_envy_x360,
@@ -10333,6 +10397,16 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc283_fixup_dell_hp_resume,
 	},
+	[ALC294_FIXUP_ASUS_CS35L41_SPI_2] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = cs35l41_fixup_spi_two,
+		.chained = true,
+		.chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC,
+	},
+	[ALC274_FIXUP_HP_AIO_BIND_DACS] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc274_fixup_hp_aio_bind_dacs,
+	},
 };
 
 static const struct hda_quirk alc269_fixup_tbl[] = {
@@ -10557,6 +10631,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x86c1, "HP Laptop 15-da3001TU", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
+	SND_PCI_QUIRK(0x103c, 0x863e, "HP Spectre x360 15-df1xxx", ALC285_FIXUP_HP_SPECTRE_X360_DF1),
 	SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
 	SND_PCI_QUIRK(0x103c, 0x86f9, "HP Spectre x360 13-aw0xxx", ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
@@ -10761,12 +10836,13 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8caf, "HP Elite mt645 G8 Mobile Thin Client", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8cbd, "HP Pavilion Aero Laptop 13-bg0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS),
-	SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
-	SND_PCI_QUIRK(0x103c, 0x8cde, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX),
+	SND_PCI_QUIRK(0x103c, 0x8cde, "HP OmniBook Ultra Flip Laptop 14t", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX),
 	SND_PCI_QUIRK(0x103c, 0x8cdf, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ce0, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8d01, "HP ZBook Power 14 G12", ALC285_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8d18, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS),
 	SND_PCI_QUIRK(0x103c, 0x8d84, "HP EliteBook X G1i", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8d85, "HP EliteBook 14 G12", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8d86, "HP Elite X360 14 G12", ALC285_FIXUP_HP_GPIO_LED),
@@ -10786,11 +10862,15 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8da1, "HP 16 Clipper OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8da7, "HP 14 Enstrom OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8da8, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x103c, 0x8dd4, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS),
 	SND_PCI_QUIRK(0x103c, 0x8de8, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2),
 	SND_PCI_QUIRK(0x103c, 0x8de9, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2),
 	SND_PCI_QUIRK(0x103c, 0x8dec, "HP EliteBook 640 G12", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8ded, "HP EliteBook 640 G12", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8dee, "HP EliteBook 660 G12", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8def, "HP EliteBook 660 G12", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8df0, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8df1, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8dfc, "HP EliteBook 645 G12", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8dfe, "HP EliteBook 665 G12", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8e11, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10805,9 +10885,12 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8e1a, "HP ZBook Firefly 14 G12A", ALC245_FIXUP_HP_ZBOOK_FIREFLY_G12A),
 	SND_PCI_QUIRK(0x103c, 0x8e1b, "HP EliteBook G12", ALC245_FIXUP_HP_ZBOOK_FIREFLY_G12A),
 	SND_PCI_QUIRK(0x103c, 0x8e1c, "HP EliteBook G12", ALC245_FIXUP_HP_ZBOOK_FIREFLY_G12A),
+	SND_PCI_QUIRK(0x103c, 0x8e1d, "HP ZBook X Gli 16 G12", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8e2c, "HP EliteBook 16 G12", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8e36, "HP 14 Enstrom OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e37, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x103c, 0x8e3a, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x103c, 0x8e3b, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e60, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e61, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e62, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10835,11 +10918,11 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x12a3, "Asus N7691ZM", ALC269_FIXUP_ASUS_N7601ZM),
 	SND_PCI_QUIRK(0x1043, 0x12af, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x12b4, "ASUS B3405CCA / P3405CCA", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC),
-	SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x12b4, "ASUS B3405CCA / P3405CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
 	SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1460, "Asus VivoBook 15", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
@@ -10893,7 +10976,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
-	SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1ccf, "ASUS G814JU/JV/JI", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1cdf, "ASUS G814JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1cef, "ASUS G834JY/JZ/JI/JG", ALC285_FIXUP_ASUS_HEADSET_MIC),
@@ -10925,14 +11008,14 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1fb3, "ASUS ROG Flow Z13 GZ302EA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3011, "ASUS B5605CVA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
-	SND_PCI_QUIRK(0x1043, 0x3061, "ASUS B3405CCA", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x3071, "ASUS B5405CCA", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x30c1, "ASUS B3605CCA / P3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x30d1, "ASUS B5405CCA", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x30e1, "ASUS B5605CCA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x3061, "ASUS B3405CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x3071, "ASUS B5405CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x30c1, "ASUS B3605CCA / P3605CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x30d1, "ASUS B5405CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x30e1, "ASUS B5605CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27),
-	SND_PCI_QUIRK(0x1043, 0x31e1, "ASUS B5605CCA", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x31f1, "ASUS B3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x31e1, "ASUS B5605CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x31f1, "ASUS B3605CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
@@ -11223,6 +11306,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x38fa, "Thinkbook 16P Gen5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
 	SND_PCI_QUIRK(0x17aa, 0x38fd, "ThinkBook plus Gen5 Hybrid", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
+	SND_PCI_QUIRK(0x17aa, 0x390d, "Lenovo Yoga Pro 7 14ASP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC),
 	SND_PCI_QUIRK(0x17aa, 0x391f, "Yoga S990-16 pro Quad YC Quad", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3920, "Yoga S990-16 pro Quad VECO Quad", ALC287_FIXUP_TAS2781_I2C),
@@ -11487,6 +11571,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC295_FIXUP_HP_OMEN, .name = "alc295-hp-omen"},
 	{.id = ALC285_FIXUP_HP_SPECTRE_X360, .name = "alc285-hp-spectre-x360"},
 	{.id = ALC285_FIXUP_HP_SPECTRE_X360_EB1, .name = "alc285-hp-spectre-x360-eb1"},
+	{.id = ALC285_FIXUP_HP_SPECTRE_X360_DF1, .name = "alc285-hp-spectre-x360-df1"},
 	{.id = ALC285_FIXUP_HP_ENVY_X360, .name = "alc285-hp-envy-x360"},
 	{.id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, .name = "alc287-ideapad-bass-spk-amp"},
 	{.id = ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN, .name = "alc287-yoga9-bass-spk-pin"},
diff --git a/sound/pci/hda/tas2781_hda_spi.c b/sound/pci/hda/tas2781_hda_spi.c
index 399f2e4c3b62..25175ff4b3aa 100644
--- a/sound/pci/hda/tas2781_hda_spi.c
+++ b/sound/pci/hda/tas2781_hda_spi.c
@@ -1003,8 +1003,7 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context)
 	 */
 
 out:
-	if (fmw)
-		release_firmware(fmw);
+	release_firmware(fmw);
 	pm_runtime_mark_last_busy(tas_hda->priv->dev);
 	pm_runtime_put_autosuspend(tas_hda->priv->dev);
 }
diff --git a/sound/sh/Kconfig b/sound/sh/Kconfig
index b75fbb3236a7..f5fa09d740b4 100644
--- a/sound/sh/Kconfig
+++ b/sound/sh/Kconfig
@@ -14,7 +14,7 @@ if SND_SUPERH
 
 config SND_AICA
 	tristate "Dreamcast Yamaha AICA sound"
-	depends on SH_DREAMCAST
+	depends on SH_DREAMCAST && SH_DMA_API
 	select SND_PCM
 	select G2_DMA
 	help
diff --git a/sound/soc/amd/acp/acp-i2s.c b/sound/soc/amd/acp/acp-i2s.c
index a38409dd1d34..70fa54d568ef 100644
--- a/sound/soc/amd/acp/acp-i2s.c
+++ b/sound/soc/amd/acp/acp-i2s.c
@@ -97,7 +97,7 @@ static int acp_i2s_set_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask, u32 rx_mas
 	struct acp_stream *stream;
 	int slot_len, no_of_slots;
 
-	chip = dev_get_platdata(dev);
+	chip = dev_get_drvdata(dev->parent);
 	switch (slot_width) {
 	case SLOT_WIDTH_8:
 		slot_len = 8;
diff --git a/sound/soc/amd/acp/acp-legacy-common.c b/sound/soc/amd/acp/acp-legacy-common.c
index b4d68484e06d..ba8db0851daa 100644
--- a/sound/soc/amd/acp/acp-legacy-common.c
+++ b/sound/soc/amd/acp/acp-legacy-common.c
@@ -450,7 +450,7 @@ int acp_machine_select(struct acp_chip_info *chip)
 	struct snd_soc_acpi_mach *mach;
 	int size, platform;
 
-	if (chip->flag == FLAG_AMD_LEGACY_ONLY_DMIC) {
+	if (chip->flag == FLAG_AMD_LEGACY_ONLY_DMIC && chip->is_pdm_dev) {
 		platform = chip->acp_rev;
 		chip->mach_dev = platform_device_register_data(chip->dev, "acp-pdm-mach",
 							       PLATFORM_DEVID_NONE, &platform,
diff --git a/sound/soc/amd/acp/acp-rembrandt.c b/sound/soc/amd/acp/acp-rembrandt.c
index 746b6ed72029..cccdd10c345e 100644
--- a/sound/soc/amd/acp/acp-rembrandt.c
+++ b/sound/soc/amd/acp/acp-rembrandt.c
@@ -199,7 +199,7 @@ static void rembrandt_audio_remove(struct platform_device *pdev)
 
 static int rmb_pcm_resume(struct device *dev)
 {
-	struct acp_chip_info *chip = dev_get_platdata(dev);
+	struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
 	struct acp_stream *stream;
 	struct snd_pcm_substream *substream;
 	snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/acp/acp-renoir.c b/sound/soc/amd/acp/acp-renoir.c
index ebf0106fc737..04f6d70b6a92 100644
--- a/sound/soc/amd/acp/acp-renoir.c
+++ b/sound/soc/amd/acp/acp-renoir.c
@@ -146,7 +146,7 @@ static void renoir_audio_remove(struct platform_device *pdev)
 
 static int rn_pcm_resume(struct device *dev)
 {
-	struct acp_chip_info *chip = dev_get_platdata(dev);
+	struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
 	struct acp_stream *stream;
 	struct snd_pcm_substream *substream;
 	snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/acp/acp63.c b/sound/soc/amd/acp/acp63.c
index 52d895e624c7..1f15c96a9b94 100644
--- a/sound/soc/amd/acp/acp63.c
+++ b/sound/soc/amd/acp/acp63.c
@@ -250,7 +250,7 @@ static void acp63_audio_remove(struct platform_device *pdev)
 
 static int acp63_pcm_resume(struct device *dev)
 {
-	struct acp_chip_info *chip = dev_get_platdata(dev);
+	struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
 	struct acp_stream *stream;
 	struct snd_pcm_substream *substream;
 	snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/acp/acp70.c b/sound/soc/amd/acp/acp70.c
index 6d5f5ade075c..217b717e9beb 100644
--- a/sound/soc/amd/acp/acp70.c
+++ b/sound/soc/amd/acp/acp70.c
@@ -182,7 +182,7 @@ static void acp_acp70_audio_remove(struct platform_device *pdev)
 
 static int acp70_pcm_resume(struct device *dev)
 {
-	struct acp_chip_info *chip = dev_get_platdata(dev);
+	struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
 	struct acp_stream *stream;
 	struct snd_pcm_substream *substream;
 	snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/ps/pci-ps.c b/sound/soc/amd/ps/pci-ps.c
index 8e57f31ef7f7..7936b3173632 100644
--- a/sound/soc/amd/ps/pci-ps.c
+++ b/sound/soc/amd/ps/pci-ps.c
@@ -193,6 +193,7 @@ static irqreturn_t acp63_irq_handler(int irq, void *dev_id)
 	struct amd_sdw_manager *amd_manager;
 	u32 ext_intr_stat, ext_intr_stat1;
 	u16 irq_flag = 0;
+	u16 wake_irq_flag = 0;
 	u16 sdw_dma_irq_flag = 0;
 
 	adata = dev_id;
@@ -231,7 +232,7 @@ static irqreturn_t acp63_irq_handler(int irq, void *dev_id)
 	}
 
 	if (adata->acp_rev >= ACP70_PCI_REV)
-		irq_flag = check_and_handle_acp70_sdw_wake_irq(adata);
+		wake_irq_flag = check_and_handle_acp70_sdw_wake_irq(adata);
 
 	if (ext_intr_stat & BIT(PDM_DMA_STAT)) {
 		ps_pdm_data = dev_get_drvdata(&adata->pdm_dev->dev);
@@ -245,7 +246,7 @@ static irqreturn_t acp63_irq_handler(int irq, void *dev_id)
 	if (sdw_dma_irq_flag)
 		return IRQ_WAKE_THREAD;
 
-	if (irq_flag)
+	if (irq_flag | wake_irq_flag)
 		return IRQ_HANDLED;
 	else
 		return IRQ_NONE;
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 40bb7a1d44bc..20f99cbee29b 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -776,10 +776,9 @@ config SND_SOC_CS_AMP_LIB
 	tristate
 
 config SND_SOC_CS_AMP_LIB_TEST
-	tristate "KUnit test for Cirrus Logic cs-amp-lib"
-	depends on KUNIT
+	tristate "KUnit test for Cirrus Logic cs-amp-lib" if !KUNIT_ALL_TESTS
+	depends on SND_SOC_CS_AMP_LIB && KUNIT
 	default KUNIT_ALL_TESTS
-	select SND_SOC_CS_AMP_LIB
 	help
 	  This builds KUnit tests for the Cirrus Logic common
 	  amplifier library.
diff --git a/sound/soc/codecs/aw88081.c b/sound/soc/codecs/aw88081.c
index ad16ab6812cd..3dd8428f08cc 100644
--- a/sound/soc/codecs/aw88081.c
+++ b/sound/soc/codecs/aw88081.c
@@ -1295,9 +1295,19 @@ static int aw88081_i2c_probe(struct i2c_client *i2c)
 			aw88081_dai, ARRAY_SIZE(aw88081_dai));
 }
 
+#if defined(CONFIG_OF)
+static const struct of_device_id aw88081_of_match[] = {
+	{ .compatible = "awinic,aw88081" },
+	{ .compatible = "awinic,aw88083" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, aw88081_of_match);
+#endif
+
 static struct i2c_driver aw88081_i2c_driver = {
 	.driver = {
 		.name = AW88081_I2C_NAME,
+		.of_match_table = of_match_ptr(aw88081_of_match),
 	},
 	.probe = aw88081_i2c_probe,
 	.id_table = aw88081_i2c_id,
diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c
index ac19a572fe70..6165ac16c3a9 100644
--- a/sound/soc/codecs/cs42l43-jack.c
+++ b/sound/soc/codecs/cs42l43-jack.c
@@ -654,6 +654,10 @@ static int cs42l43_run_type_detect(struct cs42l43_codec *priv)
 
 	reinit_completion(&priv->type_detect);
 
+	regmap_update_bits(cs42l43->regmap, CS42L43_STEREO_MIC_CLAMP_CTRL,
+			   CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_VAL_MASK,
+			   CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_VAL_MASK);
+
 	cs42l43_start_hs_bias(priv, true);
 	regmap_update_bits(cs42l43->regmap, CS42L43_HS2,
 			   CS42L43_HSDET_MODE_MASK, 0x3 << CS42L43_HSDET_MODE_SHIFT);
@@ -665,6 +669,9 @@ static int cs42l43_run_type_detect(struct cs42l43_codec *priv)
 			   CS42L43_HSDET_MODE_MASK, 0x2 << CS42L43_HSDET_MODE_SHIFT);
 	cs42l43_stop_hs_bias(priv);
 
+	regmap_update_bits(cs42l43->regmap, CS42L43_STEREO_MIC_CLAMP_CTRL,
+			   CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_VAL_MASK, 0);
+
 	if (!time_left)
 		return -ETIMEDOUT;
 
@@ -702,6 +709,9 @@ static void cs42l43_clear_jack(struct cs42l43_codec *priv)
 			   CS42L43_PGA_WIDESWING_MODE_EN_MASK, 0);
 	regmap_update_bits(cs42l43->regmap, CS42L43_STEREO_MIC_CTRL,
 			   CS42L43_JACK_STEREO_CONFIG_MASK, 0);
+	regmap_update_bits(cs42l43->regmap, CS42L43_STEREO_MIC_CLAMP_CTRL,
+			   CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_MASK,
+			   CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_MASK);
 	regmap_update_bits(cs42l43->regmap, CS42L43_HS2,
 			   CS42L43_HSDET_MODE_MASK | CS42L43_HSDET_MANUAL_MODE_MASK,
 			   0x2 << CS42L43_HSDET_MODE_SHIFT);
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index 17019b1d680b..bc01ff65bd6f 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -842,12 +842,28 @@ static void print_eld_info(struct snd_info_entry *entry,
 static int hdmi_dai_proc_new(struct hdmi_codec_priv *hcp,
 			     struct snd_soc_dai *dai)
 {
+	struct snd_soc_component *component = dai->component;
+	struct snd_soc_card *card = component->card;
+	struct snd_soc_dai *d;
+	struct snd_soc_pcm_runtime *rtd;
 	struct snd_info_entry *entry;
 	char name[32];
-	int err;
+	int err, i, id = 0;
 
-	snprintf(name, sizeof(name), "eld#%d", dai->id);
-	err = snd_card_proc_new(dai->component->card->snd_card, name, &entry);
+	/*
+	 * To avoid duplicate proc entry, find its rtd and use rtd->id
+	 * instead of dai->id
+	 */
+	for_each_card_rtds(card, rtd) {
+		for_each_rtd_dais(rtd, i, d)
+			if (d == dai) {
+				id = rtd->id;
+				goto found;
+			}
+	}
+found:
+	snprintf(name, sizeof(name), "eld#%d", id);
+	err = snd_card_proc_new(card->snd_card, name, &entry);
 	if (err < 0)
 		return err;
 
diff --git a/sound/soc/codecs/lpass-wsa-macro.c b/sound/soc/codecs/lpass-wsa-macro.c
index b261fa373e65..c1fb71cfb5d0 100644
--- a/sound/soc/codecs/lpass-wsa-macro.c
+++ b/sound/soc/codecs/lpass-wsa-macro.c
@@ -63,6 +63,10 @@
 #define CDC_WSA_TX_SPKR_PROT_CLK_DISABLE	0
 #define CDC_WSA_TX_SPKR_PROT_PCM_RATE_MASK	GENMASK(3, 0)
 #define CDC_WSA_TX_SPKR_PROT_PCM_RATE_8K	0
+#define CDC_WSA_TX_SPKR_PROT_PCM_RATE_16K	1
+#define CDC_WSA_TX_SPKR_PROT_PCM_RATE_24K	2
+#define CDC_WSA_TX_SPKR_PROT_PCM_RATE_32K	3
+#define CDC_WSA_TX_SPKR_PROT_PCM_RATE_48K	4
 #define CDC_WSA_TX0_SPKR_PROT_PATH_CFG0		(0x0248)
 #define CDC_WSA_TX1_SPKR_PROT_PATH_CTL		(0x0264)
 #define CDC_WSA_TX1_SPKR_PROT_PATH_CFG0		(0x0268)
@@ -407,6 +411,7 @@ struct wsa_macro {
 	int ear_spkr_gain;
 	int spkr_gain_offset;
 	int spkr_mode;
+	u32 pcm_rate_vi;
 	int is_softclip_on[WSA_MACRO_SOFTCLIP_MAX];
 	int softclip_clk_users[WSA_MACRO_SOFTCLIP_MAX];
 	struct regmap *regmap;
@@ -1280,6 +1285,7 @@ static int wsa_macro_hw_params(struct snd_pcm_substream *substream,
 			       struct snd_soc_dai *dai)
 {
 	struct snd_soc_component *component = dai->component;
+	struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
 	int ret;
 
 	switch (substream->stream) {
@@ -1292,6 +1298,11 @@ static int wsa_macro_hw_params(struct snd_pcm_substream *substream,
 			return ret;
 		}
 		break;
+	case SNDRV_PCM_STREAM_CAPTURE:
+		if (dai->id == WSA_MACRO_AIF_VI)
+			wsa->pcm_rate_vi = params_rate(params);
+
+		break;
 	default:
 		break;
 	}
@@ -1448,35 +1459,11 @@ static void wsa_macro_mclk_enable(struct wsa_macro *wsa, bool mclk_enable)
 	}
 }
 
-static int wsa_macro_mclk_event(struct snd_soc_dapm_widget *w,
-				struct snd_kcontrol *kcontrol, int event)
+static void wsa_macro_enable_disable_vi_sense(struct snd_soc_component *component, bool enable,
+						u32 tx_reg0, u32 tx_reg1, u32 val)
 {
-	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
-	struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
-
-	wsa_macro_mclk_enable(wsa, event == SND_SOC_DAPM_PRE_PMU);
-	return 0;
-}
-
-static int wsa_macro_enable_vi_feedback(struct snd_soc_dapm_widget *w,
-					struct snd_kcontrol *kcontrol,
-					int event)
-{
-	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
-	struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
-	u32 tx_reg0, tx_reg1;
-
-	if (test_bit(WSA_MACRO_TX0, &wsa->active_ch_mask[WSA_MACRO_AIF_VI])) {
-		tx_reg0 = CDC_WSA_TX0_SPKR_PROT_PATH_CTL;
-		tx_reg1 = CDC_WSA_TX1_SPKR_PROT_PATH_CTL;
-	} else if (test_bit(WSA_MACRO_TX1, &wsa->active_ch_mask[WSA_MACRO_AIF_VI])) {
-		tx_reg0 = CDC_WSA_TX2_SPKR_PROT_PATH_CTL;
-		tx_reg1 = CDC_WSA_TX3_SPKR_PROT_PATH_CTL;
-	}
-
-	switch (event) {
-	case SND_SOC_DAPM_POST_PMU:
-			/* Enable V&I sensing */
+	if (enable) {
+		/* Enable V&I sensing */
 		snd_soc_component_update_bits(component, tx_reg0,
 					      CDC_WSA_TX_SPKR_PROT_RESET_MASK,
 					      CDC_WSA_TX_SPKR_PROT_RESET);
@@ -1485,10 +1472,10 @@ static int wsa_macro_enable_vi_feedback(struct snd_soc_dapm_widget *w,
 					      CDC_WSA_TX_SPKR_PROT_RESET);
 		snd_soc_component_update_bits(component, tx_reg0,
 					      CDC_WSA_TX_SPKR_PROT_PCM_RATE_MASK,
-					      CDC_WSA_TX_SPKR_PROT_PCM_RATE_8K);
+					      val);
 		snd_soc_component_update_bits(component, tx_reg1,
 					      CDC_WSA_TX_SPKR_PROT_PCM_RATE_MASK,
-					      CDC_WSA_TX_SPKR_PROT_PCM_RATE_8K);
+					      val);
 		snd_soc_component_update_bits(component, tx_reg0,
 					      CDC_WSA_TX_SPKR_PROT_CLK_EN_MASK,
 					      CDC_WSA_TX_SPKR_PROT_CLK_ENABLE);
@@ -1501,9 +1488,7 @@ static int wsa_macro_enable_vi_feedback(struct snd_soc_dapm_widget *w,
 		snd_soc_component_update_bits(component, tx_reg1,
 					      CDC_WSA_TX_SPKR_PROT_RESET_MASK,
 					      CDC_WSA_TX_SPKR_PROT_NO_RESET);
-		break;
-	case SND_SOC_DAPM_POST_PMD:
-		/* Disable V&I sensing */
+	} else {
 		snd_soc_component_update_bits(component, tx_reg0,
 					      CDC_WSA_TX_SPKR_PROT_RESET_MASK,
 					      CDC_WSA_TX_SPKR_PROT_RESET);
@@ -1516,6 +1501,72 @@ static int wsa_macro_enable_vi_feedback(struct snd_soc_dapm_widget *w,
 		snd_soc_component_update_bits(component, tx_reg1,
 					      CDC_WSA_TX_SPKR_PROT_CLK_EN_MASK,
 					      CDC_WSA_TX_SPKR_PROT_CLK_DISABLE);
+	}
+}
+
+static void wsa_macro_enable_disable_vi_feedback(struct snd_soc_component *component,
+						 bool enable, u32 rate)
+{
+	struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
+
+	if (test_bit(WSA_MACRO_TX0, &wsa->active_ch_mask[WSA_MACRO_AIF_VI]))
+		wsa_macro_enable_disable_vi_sense(component, enable,
+				CDC_WSA_TX0_SPKR_PROT_PATH_CTL,
+				CDC_WSA_TX1_SPKR_PROT_PATH_CTL, rate);
+
+	if (test_bit(WSA_MACRO_TX1, &wsa->active_ch_mask[WSA_MACRO_AIF_VI]))
+		wsa_macro_enable_disable_vi_sense(component, enable,
+				CDC_WSA_TX2_SPKR_PROT_PATH_CTL,
+				CDC_WSA_TX3_SPKR_PROT_PATH_CTL, rate);
+}
+
+static int wsa_macro_mclk_event(struct snd_soc_dapm_widget *w,
+				struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
+
+	wsa_macro_mclk_enable(wsa, event == SND_SOC_DAPM_PRE_PMU);
+	return 0;
+}
+
+static int wsa_macro_enable_vi_feedback(struct snd_soc_dapm_widget *w,
+					struct snd_kcontrol *kcontrol,
+					int event)
+{
+	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
+	u32 rate_val;
+
+	switch (wsa->pcm_rate_vi) {
+	case 8000:
+		rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_8K;
+		break;
+	case 16000:
+		rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_16K;
+		break;
+	case 24000:
+		rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_24K;
+		break;
+	case 32000:
+		rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_32K;
+		break;
+	case 48000:
+		rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_48K;
+		break;
+	default:
+		rate_val = CDC_WSA_TX_SPKR_PROT_PCM_RATE_8K;
+		break;
+	}
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		/* Enable V&I sensing */
+		wsa_macro_enable_disable_vi_feedback(component, true, rate_val);
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		/* Disable V&I sensing */
+		wsa_macro_enable_disable_vi_feedback(component, false, rate_val);
 		break;
 	}
 
diff --git a/sound/soc/dwc/dwc-i2s.c b/sound/soc/dwc/dwc-i2s.c
index 4c4171bb3fbb..28001e9857d9 100644
--- a/sound/soc/dwc/dwc-i2s.c
+++ b/sound/soc/dwc/dwc-i2s.c
@@ -199,12 +199,10 @@ static void i2s_start(struct dw_i2s_dev *dev,
 	else
 		i2s_write_reg(dev->i2s_base, IRER, 1);
 
-	/* I2S needs to enable IRQ to make a handshake with DMAC on the JH7110 SoC */
-	if (dev->use_pio || dev->is_jh7110)
-		i2s_enable_irqs(dev, substream->stream, config->chan_nr);
-	else
+	if (!(dev->use_pio || dev->is_jh7110))
 		i2s_enable_dma(dev, substream->stream);
 
+	i2s_enable_irqs(dev, substream->stream, config->chan_nr);
 	i2s_write_reg(dev->i2s_base, CER, 1);
 }
 
@@ -218,11 +216,12 @@ static void i2s_stop(struct dw_i2s_dev *dev,
 	else
 		i2s_write_reg(dev->i2s_base, IRER, 0);
 
-	if (dev->use_pio || dev->is_jh7110)
-		i2s_disable_irqs(dev, substream->stream, 8);
-	else
+	if (!(dev->use_pio || dev->is_jh7110))
 		i2s_disable_dma(dev, substream->stream);
 
+	i2s_disable_irqs(dev, substream->stream, 8);
+
+
 	if (!dev->active) {
 		i2s_write_reg(dev->i2s_base, CER, 0);
 		i2s_write_reg(dev->i2s_base, IER, 0);
diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c
index f501f47242fb..1bba48318e2d 100644
--- a/sound/soc/fsl/fsl_asrc_dma.c
+++ b/sound/soc/fsl/fsl_asrc_dma.c
@@ -156,11 +156,24 @@ static int fsl_asrc_dma_hw_params(struct snd_soc_component *component,
 	for_each_dpcm_be(rtd, stream, dpcm) {
 		struct snd_soc_pcm_runtime *be = dpcm->be;
 		struct snd_pcm_substream *substream_be;
-		struct snd_soc_dai *dai = snd_soc_rtd_to_cpu(be, 0);
+		struct snd_soc_dai *dai_cpu = snd_soc_rtd_to_cpu(be, 0);
+		struct snd_soc_dai *dai_codec = snd_soc_rtd_to_codec(be, 0);
+		struct snd_soc_dai *dai;
 
 		if (dpcm->fe != rtd)
 			continue;
 
+		/*
+		 * With audio graph card, original cpu dai is changed to codec
+		 * device in backend, so if cpu dai is dummy device in backend,
+		 * get the codec dai device, which is the real hardware device
+		 * connected.
+		 */
+		if (!snd_soc_dai_is_dummy(dai_cpu))
+			dai = dai_cpu;
+		else
+			dai = dai_codec;
+
 		substream_be = snd_soc_dpcm_get_substream(be, stream);
 		dma_params_be = snd_soc_dai_get_dma_data(dai, substream_be);
 		dev_be = dai->dev;
diff --git a/sound/soc/fsl/fsl_qmc_audio.c b/sound/soc/fsl/fsl_qmc_audio.c
index b2979290c973..5614a8b909ed 100644
--- a/sound/soc/fsl/fsl_qmc_audio.c
+++ b/sound/soc/fsl/fsl_qmc_audio.c
@@ -250,6 +250,9 @@ static int qmc_audio_pcm_trigger(struct snd_soc_component *component,
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 		bitmap_zero(prtd->chans_pending, 64);
+		prtd->buffer_ended = 0;
+		prtd->ch_dma_addr_current = prtd->ch_dma_addr_start;
+
 		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 			for (i = 0; i < prtd->channels; i++)
 				prtd->qmc_dai->chans[i].prtd_tx = prtd;
diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c
index 3686d468506b..45e000f61ecc 100644
--- a/sound/soc/fsl/imx-card.c
+++ b/sound/soc/fsl/imx-card.c
@@ -544,7 +544,7 @@ static int imx_card_parse_of(struct imx_card_data *data)
 	if (!card->dai_link)
 		return -ENOMEM;
 
-	data->link_data = devm_kcalloc(dev, num_links, sizeof(*link), GFP_KERNEL);
+	data->link_data = devm_kcalloc(dev, num_links, sizeof(*link_data), GFP_KERNEL);
 	if (!data->link_data)
 		return -ENOMEM;
 
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index a1ccc300e68c..3ae2a212a2e3 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -1174,9 +1174,9 @@ void graph_util_parse_link_direction(struct device_node *np,
 	bool is_playback_only = of_property_read_bool(np, "playback-only");
 	bool is_capture_only  = of_property_read_bool(np, "capture-only");
 
-	if (is_playback_only)
+	if (playback_only)
 		*playback_only = is_playback_only;
-	if (is_capture_only)
+	if (capture_only)
 		*capture_only = is_capture_only;
 }
 EXPORT_SYMBOL_GPL(graph_util_parse_link_direction);
diff --git a/sound/soc/intel/avs/path.c b/sound/soc/intel/avs/path.c
index ef0c1d125d66..cafb8c6198be 100644
--- a/sound/soc/intel/avs/path.c
+++ b/sound/soc/intel/avs/path.c
@@ -115,6 +115,78 @@ avs_path_find_variant(struct avs_dev *adev,
 	return NULL;
 }
 
+static struct acpi_nhlt_config *
+avs_nhlt_config_or_default(struct avs_dev *adev, struct avs_tplg_module *t);
+
+int avs_path_set_constraint(struct avs_dev *adev, struct avs_tplg_path_template *template,
+			    struct snd_pcm_hw_constraint_list *rate_list,
+			    struct snd_pcm_hw_constraint_list *channels_list,
+			    struct snd_pcm_hw_constraint_list *sample_bits_list)
+{
+	struct avs_tplg_path *path_template;
+	unsigned int *rlist, *clist, *slist;
+	size_t i;
+
+	i = 0;
+	list_for_each_entry(path_template, &template->path_list, node)
+		i++;
+
+	rlist = kcalloc(i, sizeof(rlist), GFP_KERNEL);
+	clist = kcalloc(i, sizeof(clist), GFP_KERNEL);
+	slist = kcalloc(i, sizeof(slist), GFP_KERNEL);
+
+	i = 0;
+	list_for_each_entry(path_template, &template->path_list, node) {
+		struct avs_tplg_pipeline *pipeline_template;
+
+		list_for_each_entry(pipeline_template, &path_template->ppl_list, node) {
+			struct avs_tplg_module *module_template;
+
+			list_for_each_entry(module_template, &pipeline_template->mod_list, node) {
+				const guid_t *type = &module_template->cfg_ext->type;
+				struct acpi_nhlt_config *blob;
+
+				if (!guid_equal(type, &AVS_COPIER_MOD_UUID) &&
+				    !guid_equal(type, &AVS_WOVHOSTM_MOD_UUID))
+					continue;
+
+				switch (module_template->cfg_ext->copier.dma_type) {
+				case AVS_DMA_DMIC_LINK_INPUT:
+				case AVS_DMA_I2S_LINK_OUTPUT:
+				case AVS_DMA_I2S_LINK_INPUT:
+					break;
+				default:
+					continue;
+				}
+
+				blob = avs_nhlt_config_or_default(adev, module_template);
+				if (IS_ERR(blob))
+					continue;
+
+				rlist[i] = path_template->fe_fmt->sampling_freq;
+				clist[i] = path_template->fe_fmt->num_channels;
+				slist[i] = path_template->fe_fmt->bit_depth;
+				i++;
+			}
+		}
+	}
+
+	if (i) {
+		rate_list->count = i;
+		rate_list->list = rlist;
+		channels_list->count = i;
+		channels_list->list = clist;
+		sample_bits_list->count = i;
+		sample_bits_list->list = slist;
+	} else {
+		kfree(rlist);
+		kfree(clist);
+		kfree(slist);
+	}
+
+	return i;
+}
+
 static void avs_init_node_id(union avs_connector_node_id *node_id,
 			     struct avs_tplg_modcfg_ext *te, u32 dma_id)
 {
diff --git a/sound/soc/intel/avs/path.h b/sound/soc/intel/avs/path.h
index 7ed7e94e0a56..c65ed84aa853 100644
--- a/sound/soc/intel/avs/path.h
+++ b/sound/soc/intel/avs/path.h
@@ -69,6 +69,11 @@ int avs_path_reset(struct avs_path *path);
 int avs_path_pause(struct avs_path *path);
 int avs_path_run(struct avs_path *path, int trigger);
 
+int avs_path_set_constraint(struct avs_dev *adev, struct avs_tplg_path_template *template,
+			    struct snd_pcm_hw_constraint_list *rate_list,
+			    struct snd_pcm_hw_constraint_list *channels_list,
+			    struct snd_pcm_hw_constraint_list *sample_bits_list);
+
 int avs_peakvol_set_volume(struct avs_dev *adev, struct avs_path_module *mod,
 			   struct soc_mixer_control *mc, long *input);
 int avs_peakvol_set_mute(struct avs_dev *adev, struct avs_path_module *mod,
diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c
index dac463390da1..d83ef504643b 100644
--- a/sound/soc/intel/avs/pcm.c
+++ b/sound/soc/intel/avs/pcm.c
@@ -31,6 +31,10 @@ struct avs_dma_data {
 		struct hdac_ext_stream *host_stream;
 	};
 
+	struct snd_pcm_hw_constraint_list rate_list;
+	struct snd_pcm_hw_constraint_list channels_list;
+	struct snd_pcm_hw_constraint_list sample_bits_list;
+
 	struct work_struct period_elapsed_work;
 	struct snd_pcm_substream *substream;
 };
@@ -74,6 +78,45 @@ void avs_period_elapsed(struct snd_pcm_substream *substream)
 	schedule_work(&data->period_elapsed_work);
 }
 
+static int hw_rule_param_size(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule);
+static int avs_hw_constraints_init(struct snd_pcm_substream *substream, struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct snd_pcm_hw_constraint_list *r, *c, *s;
+	struct avs_tplg_path_template *template;
+	struct avs_dma_data *data;
+	int ret;
+
+	ret = snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS);
+	if (ret < 0)
+		return ret;
+
+	data = snd_soc_dai_get_dma_data(dai, substream);
+	r = &(data->rate_list);
+	c = &(data->channels_list);
+	s = &(data->sample_bits_list);
+
+	template = avs_dai_find_path_template(dai, !rtd->dai_link->no_pcm, substream->stream);
+	ret = avs_path_set_constraint(data->adev, template, r, c, s);
+	if (ret <= 0)
+		return ret;
+
+	ret = snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, r);
+	if (ret < 0)
+		return ret;
+
+	ret = snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS, c);
+	if (ret < 0)
+		return ret;
+
+	ret = snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_SAMPLE_BITS, s);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static int avs_dai_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
@@ -101,7 +144,7 @@ static int avs_dai_startup(struct snd_pcm_substream *substream, struct snd_soc_d
 	if (rtd->dai_link->ignore_suspend)
 		adev->num_lp_paths++;
 
-	return 0;
+	return avs_hw_constraints_init(substream, dai);
 }
 
 static void avs_dai_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *dai)
@@ -114,6 +157,10 @@ static void avs_dai_shutdown(struct snd_pcm_substream *substream, struct snd_soc
 	if (rtd->dai_link->ignore_suspend)
 		data->adev->num_lp_paths--;
 
+	kfree(data->rate_list.list);
+	kfree(data->channels_list.list);
+	kfree(data->sample_bits_list.list);
+
 	snd_soc_dai_set_dma_data(dai, substream, NULL);
 	kfree(data);
 }
@@ -927,7 +974,8 @@ static int avs_component_probe(struct snd_soc_component *component)
 		else
 			mach->tplg_filename = devm_kasprintf(adev->dev, GFP_KERNEL,
 							     "hda-generic-tplg.bin");
-
+		if (!mach->tplg_filename)
+			return -ENOMEM;
 		filename = kasprintf(GFP_KERNEL, "%s/%s", component->driver->topology_name_prefix,
 				     mach->tplg_filename);
 		if (!filename)
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 6446cda0f857..0f3b8f44e701 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -576,6 +576,19 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF2 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{       /* Acer Aspire SW3-013 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW3-013"),
+		},
+		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_DIFF_MIC |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 90dafa810b2e..095d08b3fc82 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -764,6 +764,7 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = {
 
 static const struct snd_pci_quirk sof_sdw_ssid_quirk_table[] = {
 	SND_PCI_QUIRK(0x1043, 0x1e13, "ASUS Zenbook S14", SOC_SDW_CODEC_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1f43, "ASUS Zenbook S16", SOC_SDW_CODEC_MIC),
 	{}
 };
 
diff --git a/sound/soc/intel/catpt/dsp.c b/sound/soc/intel/catpt/dsp.c
index 5993819cc58a..008a20a2acbd 100644
--- a/sound/soc/intel/catpt/dsp.c
+++ b/sound/soc/intel/catpt/dsp.c
@@ -156,7 +156,7 @@ static void catpt_dsp_set_srampge(struct catpt_dev *cdev, struct resource *sram,
 {
 	unsigned long old;
 	u32 off = sram->start;
-	u32 b = __ffs(mask);
+	unsigned long b = __ffs(mask);
 
 	old = catpt_readl_pci(cdev, VDRTCTL0) & mask;
 	dev_dbg(cdev->dev, "SRAMPGE [0x%08lx] 0x%08lx -> 0x%08lx",
diff --git a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c
index 6603d8de501c..c599eb43eeb1 100644
--- a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c
@@ -431,7 +431,8 @@ static const struct snd_soc_acpi_link_adr ptl_cs42l43_l3[] = {
 		.mask = BIT(3),
 		.num_adr = ARRAY_SIZE(cs42l43_3_adr),
 		.adr_d = cs42l43_3_adr,
-	}
+	},
+	{}
 };
 
 static const struct snd_soc_acpi_link_adr ptl_rt722_only[] = {
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 3033e2d3fe16..90e367586493 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -228,6 +228,7 @@ config SND_SOC_MT8188
 config SND_SOC_MT8188_MT6359
 	tristate "ASoC Audio driver for MT8188 with MT6359 and I2S codecs"
 	depends on SND_SOC_MT8188 && MTK_PMIC_WRAP
+	depends on SND_SOC_MT6359_ACCDET || !SND_SOC_MT6359_ACCDET
 	depends on I2C
 	select SND_SOC_MT6359
 	select SND_SOC_HDMI_CODEC
diff --git a/sound/soc/qcom/lpass.h b/sound/soc/qcom/lpass.h
index 27a2bf9a6613..de3ec6f594c1 100644
--- a/sound/soc/qcom/lpass.h
+++ b/sound/soc/qcom/lpass.h
@@ -13,10 +13,11 @@
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <dt-bindings/sound/qcom,lpass.h>
+#include <dt-bindings/sound/qcom,q6afe.h>
 #include "lpass-hdmi.h"
 
 #define LPASS_AHBIX_CLOCK_FREQUENCY		131072000
-#define LPASS_MAX_PORTS			(LPASS_CDC_DMA_VA_TX8 + 1)
+#define LPASS_MAX_PORTS			(DISPLAY_PORT_RX_7 + 1)
 #define LPASS_MAX_MI2S_PORTS			(8)
 #define LPASS_MAX_DMA_CHANNELS			(8)
 #define LPASS_MAX_HDMI_DMA_CHANNELS		(4)
diff --git a/sound/soc/renesas/rz-ssi.c b/sound/soc/renesas/rz-ssi.c
index 3a0af4ca7ab6..0f7458a43901 100644
--- a/sound/soc/renesas/rz-ssi.c
+++ b/sound/soc/renesas/rz-ssi.c
@@ -1244,7 +1244,7 @@ static int rz_ssi_runtime_resume(struct device *dev)
 
 static const struct dev_pm_ops rz_ssi_pm_ops = {
 	RUNTIME_PM_OPS(rz_ssi_runtime_suspend, rz_ssi_runtime_resume, NULL)
-	SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
 };
 
 static struct platform_driver rz_ssi_driver = {
diff --git a/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c b/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c
index 246e5c2e0af5..c7e55f443351 100644
--- a/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c
+++ b/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c
@@ -60,6 +60,10 @@ static int asoc_sdw_bridge_cs35l56_asp_init(struct snd_soc_pcm_runtime *rtd)
 
 	/* 4 x 16-bit sample slots and FSYNC=48000, BCLK=3.072 MHz */
 	for_each_rtd_codec_dais(rtd, i, codec_dai) {
+		ret = asoc_sdw_cs35l56_volume_limit(card, codec_dai->component->name_prefix);
+		if (ret)
+			return ret;
+
 		ret = snd_soc_dai_set_tdm_slot(codec_dai, tx_mask, rx_mask, 4, 16);
 		if (ret < 0)
 			return ret;
diff --git a/sound/soc/sdw_utils/soc_sdw_cs42l43.c b/sound/soc/sdw_utils/soc_sdw_cs42l43.c
index 668c9d28a1c1..b415d45d520d 100644
--- a/sound/soc/sdw_utils/soc_sdw_cs42l43.c
+++ b/sound/soc/sdw_utils/soc_sdw_cs42l43.c
@@ -20,6 +20,8 @@
 #include <sound/soc-dapm.h>
 #include <sound/soc_sdw_utils.h>
 
+#define CS42L43_SPK_VOLUME_0DB	128 /* 0dB Max */
+
 static const struct snd_soc_dapm_route cs42l43_hs_map[] = {
 	{ "Headphone", NULL, "cs42l43 AMP3_OUT" },
 	{ "Headphone", NULL, "cs42l43 AMP4_OUT" },
@@ -117,6 +119,14 @@ int asoc_sdw_cs42l43_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_so
 			return -ENOMEM;
 	}
 
+	ret = snd_soc_limit_volume(card, "cs42l43 Speaker Digital Volume",
+				   CS42L43_SPK_VOLUME_0DB);
+	if (ret)
+		dev_err(card->dev, "cs42l43 speaker volume limit failed: %d\n", ret);
+	else
+		dev_info(card->dev, "Setting CS42L43 Speaker volume limit to %d\n",
+			 CS42L43_SPK_VOLUME_0DB);
+
 	ret = snd_soc_dapm_add_routes(&card->dapm, cs42l43_spk_map,
 				      ARRAY_SIZE(cs42l43_spk_map));
 	if (ret)
diff --git a/sound/soc/sdw_utils/soc_sdw_cs_amp.c b/sound/soc/sdw_utils/soc_sdw_cs_amp.c
index 4b6181cf2971..35b550bcd4de 100644
--- a/sound/soc/sdw_utils/soc_sdw_cs_amp.c
+++ b/sound/soc/sdw_utils/soc_sdw_cs_amp.c
@@ -16,6 +16,25 @@
 
 #define CODEC_NAME_SIZE	8
 #define CS_AMP_CHANNELS_PER_AMP	4
+#define CS35L56_SPK_VOLUME_0DB 400 /* 0dB Max */
+
+int asoc_sdw_cs35l56_volume_limit(struct snd_soc_card *card, const char *name_prefix)
+{
+	char *volume_ctl_name;
+	int ret;
+
+	volume_ctl_name = kasprintf(GFP_KERNEL, "%s Speaker Volume", name_prefix);
+	if (!volume_ctl_name)
+		return -ENOMEM;
+
+	ret = snd_soc_limit_volume(card, volume_ctl_name, CS35L56_SPK_VOLUME_0DB);
+	if (ret)
+		dev_err(card->dev, "%s limit set failed: %d\n", volume_ctl_name, ret);
+
+	kfree(volume_ctl_name);
+	return ret;
+}
+EXPORT_SYMBOL_NS(asoc_sdw_cs35l56_volume_limit, "SND_SOC_SDW_UTILS");
 
 int asoc_sdw_cs_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai *dai)
 {
@@ -40,6 +59,11 @@ int asoc_sdw_cs_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai
 
 		snprintf(widget_name, sizeof(widget_name), "%s SPK",
 			 codec_dai->component->name_prefix);
+
+		ret = asoc_sdw_cs35l56_volume_limit(card, codec_dai->component->name_prefix);
+		if (ret)
+			return ret;
+
 		ret = snd_soc_dapm_add_routes(&card->dapm, &route, 1);
 		if (ret)
 			return ret;
diff --git a/sound/soc/sdw_utils/soc_sdw_rt_dmic.c b/sound/soc/sdw_utils/soc_sdw_rt_dmic.c
index 46d917a99c51..97be110a59b6 100644
--- a/sound/soc/sdw_utils/soc_sdw_rt_dmic.c
+++ b/sound/soc/sdw_utils/soc_sdw_rt_dmic.c
@@ -29,6 +29,8 @@ int asoc_sdw_rt_dmic_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_da
 		mic_name = devm_kasprintf(card->dev, GFP_KERNEL, "rt715-sdca");
 	else
 		mic_name = devm_kasprintf(card->dev, GFP_KERNEL, "%s", component->name_prefix);
+	if (!mic_name)
+		return -ENOMEM;
 
 	card->components = devm_kasprintf(card->dev, GFP_KERNEL,
 					  "%s mic:%s", card->components,
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 4308a6cbb2e6..43835197d1fe 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1584,10 +1584,13 @@ int dpcm_add_paths(struct snd_soc_pcm_runtime *fe, int stream,
 		/*
 		 * Filter for systems with 'component_chaining' enabled.
 		 * This helps to avoid unnecessary re-configuration of an
-		 * already active BE on such systems.
+		 * already active BE on such systems and ensures the BE DAI
+		 * widget is powered ON after hw_params() BE DAI callback.
 		 */
 		if (fe->card->component_chaining &&
 		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_NEW) &&
+		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_OPEN) &&
+		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_PARAMS) &&
 		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_CLOSE))
 			continue;
 
diff --git a/sound/soc/sof/intel/hda-bus.c b/sound/soc/sof/intel/hda-bus.c
index b1be03011d7e..6492e1cefbfb 100644
--- a/sound/soc/sof/intel/hda-bus.c
+++ b/sound/soc/sof/intel/hda-bus.c
@@ -76,7 +76,7 @@ void sof_hda_bus_init(struct snd_sof_dev *sdev, struct device *dev)
 
 	snd_hdac_ext_bus_init(bus, dev, &bus_core_ops, sof_hda_ext_ops);
 
-	if (chip && chip->hw_ip_version == SOF_INTEL_ACE_2_0)
+	if (chip && chip->hw_ip_version >= SOF_INTEL_ACE_2_0)
 		bus->use_pio_for_commands = true;
 #else
 	snd_hdac_ext_bus_init(bus, dev, NULL, NULL);
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index b34e5fdf10f1..6a3932d90b43 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -1049,7 +1049,21 @@ static void hda_generic_machine_select(struct snd_sof_dev *sdev,
 		if (!*mach && codec_num <= 2) {
 			bool tplg_fixup = false;
 
-			hda_mach = snd_soc_acpi_intel_hda_machines;
+			/*
+			 * make a local copy of the match array since we might
+			 * be modifying it
+			 */
+			hda_mach = devm_kmemdup_array(sdev->dev,
+					snd_soc_acpi_intel_hda_machines,
+					2, /* we have one entry + sentinel in the array */
+					sizeof(snd_soc_acpi_intel_hda_machines[0]),
+					GFP_KERNEL);
+			if (!hda_mach) {
+				dev_err(bus->dev,
+					"%s: failed to duplicate the HDA match table\n",
+					__func__);
+				return;
+			}
 
 			dev_info(bus->dev, "using HDA machine driver %s now\n",
 				 hda_mach->drv_name);
diff --git a/sound/soc/sof/ipc4-control.c b/sound/soc/sof/ipc4-control.c
index 576f407cd456..976a4794d610 100644
--- a/sound/soc/sof/ipc4-control.c
+++ b/sound/soc/sof/ipc4-control.c
@@ -531,6 +531,14 @@ static int sof_ipc4_bytes_ext_put(struct snd_sof_control *scontrol,
 		return -EINVAL;
 	}
 
+	/* Check header id */
+	if (header.numid != SOF_CTRL_CMD_BINARY) {
+		dev_err_ratelimited(scomp->dev,
+				    "Incorrect numid for bytes put %d\n",
+				    header.numid);
+		return -EINVAL;
+	}
+
 	/* Verify the ABI header first */
 	if (copy_from_user(&abi_hdr, tlvd->tlv, sizeof(abi_hdr)))
 		return -EFAULT;
@@ -613,7 +621,8 @@ static int _sof_ipc4_bytes_ext_get(struct snd_sof_control *scontrol,
 	if (data_size > size)
 		return -ENOSPC;
 
-	header.numid = scontrol->comp_id;
+	/* Set header id and length */
+	header.numid = SOF_CTRL_CMD_BINARY;
 	header.length = data_size;
 
 	if (copy_to_user(tlvd, &header, sizeof(struct snd_ctl_tlv)))
diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index 1a2841899ff5..c09b424ab863 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -798,7 +798,8 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm
 
 		spcm->stream[stream].private = stream_priv;
 
-		if (!support_info)
+		/* Delay reporting is only supported on playback */
+		if (!support_info || stream == SNDRV_PCM_STREAM_CAPTURE)
 			continue;
 
 		time_info = kzalloc(sizeof(*time_info), GFP_KERNEL);
diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c
index dc9cb8324067..14aa8ecc4bc4 100644
--- a/sound/soc/sof/topology.c
+++ b/sound/soc/sof/topology.c
@@ -1063,7 +1063,7 @@ static int sof_connect_dai_widget(struct snd_soc_component *scomp,
 				  struct snd_sof_dai *dai)
 {
 	struct snd_soc_card *card = scomp->card;
-	struct snd_soc_pcm_runtime *rtd;
+	struct snd_soc_pcm_runtime *rtd, *full, *partial;
 	struct snd_soc_dai *cpu_dai;
 	int stream;
 	int i;
@@ -1080,12 +1080,22 @@ static int sof_connect_dai_widget(struct snd_soc_component *scomp,
 	else
 		goto end;
 
+	full = NULL;
+	partial = NULL;
 	list_for_each_entry(rtd, &card->rtd_list, list) {
 		/* does stream match DAI link ? */
-		if (!rtd->dai_link->stream_name ||
-		    !strstr(rtd->dai_link->stream_name, w->sname))
-			continue;
+		if (rtd->dai_link->stream_name) {
+			if (!strcmp(rtd->dai_link->stream_name, w->sname)) {
+				full = rtd;
+				break;
+			} else if (strstr(rtd->dai_link->stream_name, w->sname)) {
+				partial = rtd;
+			}
+		}
+	}
 
+	rtd = full ? full : partial;
+	if (rtd) {
 		for_each_rtd_cpu_dais(rtd, i, cpu_dai) {
 			/*
 			 * Please create DAI widget in the right order
diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index e8c1abf1ae0a..bf5299ba11c3 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -409,11 +409,11 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
 				     unsigned int rate)
 {
 	struct platform_device *pdev = sai->pdev;
-	unsigned int sai_ck_rate, sai_ck_max_rate, sai_curr_rate, sai_new_rate;
+	unsigned int sai_ck_rate, sai_ck_max_rate, sai_ck_min_rate, sai_curr_rate, sai_new_rate;
 	int div, ret;
 
 	/*
-	 * Set maximum expected kernel clock frequency
+	 * Set minimum and maximum expected kernel clock frequency
 	 * - mclk on or spdif:
 	 *   f_sai_ck = MCKDIV * mclk-fs * fs
 	 *   Here typical 256 ratio is assumed for mclk-fs
@@ -423,13 +423,16 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
 	 *   Set constraint MCKDIV * FRL <= 256, to ensure MCKDIV is in available range
 	 *   f_sai_ck = sai_ck_max_rate * pow_of_two(FRL) / 256
 	 */
+	sai_ck_min_rate = rate * 256;
 	if (!(rate % SAI_RATE_11K))
 		sai_ck_max_rate = SAI_MAX_SAMPLE_RATE_11K * 256;
 	else
 		sai_ck_max_rate = SAI_MAX_SAMPLE_RATE_8K * 256;
 
-	if (!sai->sai_mclk && !STM_SAI_PROTOCOL_IS_SPDIF(sai))
+	if (!sai->sai_mclk && !STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
+		sai_ck_min_rate = rate * sai->fs_length;
 		sai_ck_max_rate /= DIV_ROUND_CLOSEST(256, roundup_pow_of_two(sai->fs_length));
+	}
 
 	/*
 	 * Request exclusivity, as the clock is shared by SAI sub-blocks and by
@@ -444,7 +447,10 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
 	 * return immediately.
 	 */
 	sai_curr_rate = clk_get_rate(sai->sai_ck);
-	if (stm32_sai_rate_accurate(sai_ck_max_rate, sai_curr_rate))
+	dev_dbg(&pdev->dev, "kernel clock rate: min [%u], max [%u], current [%u]",
+		sai_ck_min_rate, sai_ck_max_rate, sai_curr_rate);
+	if (stm32_sai_rate_accurate(sai_ck_max_rate, sai_curr_rate) &&
+	    sai_curr_rate >= sai_ck_min_rate)
 		return 0;
 
 	/*
@@ -472,7 +478,7 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
 		/* Try a lower frequency */
 		div++;
 		sai_ck_rate = sai_ck_max_rate / div;
-	} while (sai_ck_rate > rate);
+	} while (sai_ck_rate >= sai_ck_min_rate);
 
 	/* No accurate rate found */
 	dev_err(&pdev->dev, "Failed to find an accurate rate");
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index a29f28eb7d0c..f36ec98da460 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -926,6 +926,8 @@ static int endpoint_set_interface(struct snd_usb_audio *chip,
 {
 	int altset = set ? ep->altsetting : 0;
 	int err;
+	int retries = 0;
+	const int max_retries = 5;
 
 	if (ep->iface_ref->altset == altset)
 		return 0;
@@ -935,8 +937,13 @@ static int endpoint_set_interface(struct snd_usb_audio *chip,
 
 	usb_audio_dbg(chip, "Setting usb interface %d:%d for EP 0x%x\n",
 		      ep->iface, altset, ep->ep_num);
+retry:
 	err = usb_set_interface(chip->dev, ep->iface, altset);
 	if (err < 0) {
+		if (err == -EPROTO && ++retries <= max_retries) {
+			msleep(5 * (1 << (retries - 1)));
+			goto retry;
+		}
 		usb_audio_err_ratelimited(
 			chip, "%d:%d: usb_set_interface failed (%d)\n",
 			ep->iface, altset, err);
diff --git a/sound/usb/format.c b/sound/usb/format.c
index 9d32b21a5fbb..0ba4641a0eb1 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -260,7 +260,8 @@ static int parse_audio_format_rates_v1(struct snd_usb_audio *chip, struct audiof
 	}
 
 	/* Jabra Evolve 65 headset */
-	if (chip->usb_id == USB_ID(0x0b0e, 0x030b)) {
+	if (chip->usb_id == USB_ID(0x0b0e, 0x030b) ||
+	    chip->usb_id == USB_ID(0x0b0e, 0x030c)) {
 		/* only 48kHz for playback while keeping 16kHz for capture */
 		if (fp->nr_rates != 1)
 			return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000);
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index dcdd7e9e1ae9..cfed000f243a 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1885,10 +1885,18 @@ static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
 	}
 
 	port_info = find_port_info(umidi, number);
-	name_format = port_info ? port_info->name :
-		(jack_name != default_jack_name  ? "%s %s" : "%s %s %d");
-	snprintf(substream->name, sizeof(substream->name),
-		 name_format, umidi->card->shortname, jack_name, number + 1);
+	if (port_info || jack_name == default_jack_name ||
+	    strncmp(umidi->card->shortname, jack_name, strlen(umidi->card->shortname)) != 0) {
+		name_format = port_info ? port_info->name :
+			(jack_name != default_jack_name  ? "%s %s" : "%s %s %d");
+		snprintf(substream->name, sizeof(substream->name),
+			 name_format, umidi->card->shortname, jack_name, number + 1);
+	} else {
+		/* The manufacturer included the iProduct name in the jack
+		 * name, do not use both
+		 */
+		strscpy(substream->name, jack_name);
+	}
 
 	*rsubstream = substream;
 }
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 9112313a9dbc..dbbc9eb935a4 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2242,6 +2242,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x0c45, 0x6340, /* Sonix HD USB Camera */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x0c45, 0x636b, /* Microdia JP001 USB Camera */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x0d8c, 0x0014, /* USB Audio Device */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
@@ -2250,6 +2252,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_FIXED_RATE),
 	DEVICE_FLG(0x0fd9, 0x0008, /* Hauppauge HVR-950Q */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
+	DEVICE_FLG(0x1101, 0x0003, /* Audioengine D1 */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */
 		   QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_MIC_RES_16),
 	DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */
diff --git a/tools/Makefile b/tools/Makefile
index 5e1254eb66de..c31cbbd12c45 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -41,6 +41,7 @@ help:
 	@echo '  mm                     - misc mm tools'
 	@echo '  wmi			- WMI interface examples'
 	@echo '  x86_energy_perf_policy - Intel energy policy tool'
+	@echo '  ynl			- ynl headers, library, and python tool'
 	@echo ''
 	@echo 'You can do:'
 	@echo ' $$ make -C tools/ <tool>_install'
@@ -118,11 +119,14 @@ freefall: FORCE
 kvm_stat: FORCE
 	$(call descend,kvm/$@)
 
+ynl: FORCE
+	$(call descend,net/ynl)
+
 all: acpi counter cpupower gpio hv firewire \
 		perf selftests bootconfig spi turbostat usb \
 		virtio mm bpf x86_energy_perf_policy \
 		tmon freefall iio objtool kvm_stat wmi \
-		debugging tracing thermal thermometer thermal-engine
+		debugging tracing thermal thermometer thermal-engine ynl
 
 acpi_install:
 	$(call descend,power/$(@:_install=),install)
@@ -157,13 +161,16 @@ freefall_install:
 kvm_stat_install:
 	$(call descend,kvm/$(@:_install=),install)
 
+ynl_install:
+	$(call descend,net/$(@:_install=),install)
+
 install: acpi_install counter_install cpupower_install gpio_install \
 		hv_install firewire_install iio_install \
 		perf_install selftests_install turbostat_install usb_install \
 		virtio_install mm_install bpf_install x86_energy_perf_policy_install \
 		tmon_install freefall_install objtool_install kvm_stat_install \
 		wmi_install debugging_install intel-speed-select_install \
-		tracing_install thermometer_install thermal-engine_install
+		tracing_install thermometer_install thermal-engine_install ynl_install
 
 acpi_clean:
 	$(call descend,power/acpi,clean)
@@ -214,12 +221,15 @@ freefall_clean:
 build_clean:
 	$(call descend,build,clean)
 
+ynl_clean:
+	$(call descend,net/$(@:_clean=),clean)
+
 clean: acpi_clean counter_clean cpupower_clean hv_clean firewire_clean \
 		perf_clean selftests_clean turbostat_clean bootconfig_clean spi_clean usb_clean virtio_clean \
 		mm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
 		freefall_clean build_clean libbpf_clean libsubcmd_clean \
 		gpio_clean objtool_clean leds_clean wmi_clean firmware_clean debugging_clean \
 		intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean \
-		sched_ext_clean
+		sched_ext_clean ynl_clean
 
 .PHONY: FORCE
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 6d44f8c8a18f..af9d9acaf997 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -43,9 +43,6 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_DIRTY_LOG_PAGE_OFFSET 64
 
-#define KVM_REG_SIZE(id)						\
-	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
-
 struct kvm_regs {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
@@ -108,6 +105,7 @@ struct kvm_regs {
 #define KVM_ARM_VCPU_PTRAUTH_ADDRESS	5 /* VCPU uses address authentication */
 #define KVM_ARM_VCPU_PTRAUTH_GENERIC	6 /* VCPU uses generic authentication */
 #define KVM_ARM_VCPU_HAS_EL2		7 /* Support nested virtualization */
+#define KVM_ARM_VCPU_HAS_EL2_E2H0	8 /* Limit NV support to E2H RES0 */
 
 struct kvm_vcpu_init {
 	__u32 target;
@@ -418,6 +416,7 @@ enum {
 #define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
 #define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO  7
 #define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
+#define KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ  9
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT	10
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
 			(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index 9306726337fe..df36f23876e8 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -1,24 +1,2 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#define __ARCH_WANT_RENAMEAT
-#define __ARCH_WANT_NEW_STAT
-#define __ARCH_WANT_SET_GET_RLIMIT
-#define __ARCH_WANT_TIME32_SYSCALLS
-#define __ARCH_WANT_MEMFD_SECRET
-
-#include <asm-generic/unistd.h>
+#include <asm/unistd_64.h>
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 9e3fa7942e7d..6c2c152d8a67 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -75,8 +75,8 @@
 #define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */
 #define X86_FEATURE_K8			( 3*32+ 4) /* Opteron, Athlon64 */
 #define X86_FEATURE_ZEN5		( 3*32+ 5) /* CPU based on Zen5 microarchitecture */
-#define X86_FEATURE_P3			( 3*32+ 6) /* P3 */
-#define X86_FEATURE_P4			( 3*32+ 7) /* P4 */
+/* Free                                 ( 3*32+ 6) */
+/* Free                                 ( 3*32+ 7) */
 #define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */
 #define X86_FEATURE_UP			( 3*32+ 9) /* "up" SMP kernel running on UP */
 #define X86_FEATURE_ART			( 3*32+10) /* "art" Always running timer (ART) */
@@ -329,6 +329,7 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* "clzero" CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* "irperf" Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */
+#define X86_FEATURE_INVLPGB		(13*32+ 3) /* INVLPGB and TLBSYNC instructions supported */
 #define X86_FEATURE_RDPRU		(13*32+ 4) /* "rdpru" Read processor register at user level */
 #define X86_FEATURE_WBNOINVD		(13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
@@ -377,6 +378,7 @@
 #define X86_FEATURE_V_SPEC_CTRL		(15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */
 #define X86_FEATURE_VNMI		(15*32+25) /* "vnmi" Virtual NMI */
 #define X86_FEATURE_SVME_ADDR_CHK	(15*32+28) /* SVME addr check */
+#define X86_FEATURE_IDLE_HLT		(15*32+30) /* IDLE HLT intercept */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
 #define X86_FEATURE_AVX512VBMI		(16*32+ 1) /* "avx512vbmi" AVX512 Vector Bit Manipulation instructions*/
@@ -434,15 +436,18 @@
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* Speculative Store Bypass Disable */
 
 /* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */
-#define X86_FEATURE_SME			(19*32+ 0) /* "sme" AMD Secure Memory Encryption */
-#define X86_FEATURE_SEV			(19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */
+#define X86_FEATURE_SME			(19*32+ 0) /* "sme" Secure Memory Encryption */
+#define X86_FEATURE_SEV			(19*32+ 1) /* "sev" Secure Encrypted Virtualization */
 #define X86_FEATURE_VM_PAGE_FLUSH	(19*32+ 2) /* VM Page Flush MSR is supported */
-#define X86_FEATURE_SEV_ES		(19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */
-#define X86_FEATURE_SEV_SNP		(19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */
+#define X86_FEATURE_SEV_ES		(19*32+ 3) /* "sev_es" Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_SEV_SNP		(19*32+ 4) /* "sev_snp" Secure Encrypted Virtualization - Secure Nested Paging */
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* Virtual TSC_AUX */
-#define X86_FEATURE_SME_COHERENT	(19*32+10) /* AMD hardware-enforced cache coherency */
-#define X86_FEATURE_DEBUG_SWAP		(19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */
+#define X86_FEATURE_SME_COHERENT	(19*32+10) /* hardware-enforced cache coherency */
+#define X86_FEATURE_DEBUG_SWAP		(19*32+14) /* "debug_swap" SEV-ES full debug state swap support */
+#define X86_FEATURE_RMPREAD		(19*32+21) /* RMPREAD instruction */
+#define X86_FEATURE_SEGMENTED_RMP	(19*32+23) /* Segmented RMP support */
 #define X86_FEATURE_SVSM		(19*32+28) /* "svsm" SVSM present */
+#define X86_FEATURE_HV_INUSE_WR_ALLOWED	(19*32+30) /* Allow Write to in-use hypervisor-owned pages */
 
 /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* No Nested Data Breakpoints */
@@ -455,6 +460,11 @@
 #define X86_FEATURE_SBPB		(20*32+27) /* Selective Branch Prediction Barrier */
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
 #define X86_FEATURE_SRSO_NO		(20*32+29) /* CPU is not affected by SRSO */
+#define X86_FEATURE_SRSO_USER_KERNEL_NO	(20*32+30) /* CPU is not affected by SRSO across user/kernel boundaries */
+#define X86_FEATURE_SRSO_BP_SPEC_REDUCE	(20*32+31) /*
+						    * BP_CFG[BpSpecReduce] can be used to mitigate SRSO for VMs.
+						    * (SRSO_MSR_FIX in the official doc).
+						    */
 
 /*
  * Extended auxiliary flags: Linux defined - for features scattered in various
@@ -470,6 +480,7 @@
 #define X86_FEATURE_AMD_FAST_CPPC	(21*32 + 5) /* Fast CPPC */
 #define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */
 #define X86_FEATURE_AMD_WORKLOAD_CLASS	(21*32 + 7) /* Workload Classification */
+#define X86_FEATURE_PREFER_YMM		(21*32 + 8) /* Avoid ZMM registers due to downclocking */
 
 /*
  * BUG word(s)
@@ -521,4 +532,5 @@
 #define X86_BUG_RFDS			X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
 #define X86_BUG_BHI			X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
 #define X86_BUG_IBPB_NO_RET	   	X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
+#define X86_BUG_SPECTRE_V2_USER		X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index dc1c1057f26e..e6134ef2263d 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -397,7 +397,8 @@
 #define MSR_IA32_PASID_VALID		BIT_ULL(31)
 
 /* DEBUGCTLMSR bits (others vary by model): */
-#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_LBR_BIT		0	     /* last branch recording */
+#define DEBUGCTLMSR_LBR			(1UL <<  DEBUGCTLMSR_LBR_BIT)
 #define DEBUGCTLMSR_BTF_SHIFT		1
 #define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
 #define DEBUGCTLMSR_BUS_LOCK_DETECT	(1UL <<  2)
@@ -610,6 +611,7 @@
 #define MSR_AMD_PERF_CTL		0xc0010062
 #define MSR_AMD_PERF_STATUS		0xc0010063
 #define MSR_AMD_PSTATE_DEF_BASE		0xc0010064
+#define MSR_AMD64_GUEST_TSC_FREQ	0xc0010134
 #define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
 #define MSR_AMD_PPIN_CTL		0xc00102f0
@@ -646,6 +648,7 @@
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
 #define MSR_AMD64_SVM_AVIC_DOORBELL	0xc001011b
 #define MSR_AMD64_VM_PAGE_FLUSH		0xc001011e
+#define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 #define MSR_AMD64_SEV_ES_GHCB		0xc0010130
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0
@@ -684,11 +687,12 @@
 #define MSR_AMD64_SNP_SMT_PROT		BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT)
 #define MSR_AMD64_SNP_RESV_BIT		18
 #define MSR_AMD64_SNP_RESERVED_MASK	GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT)
-
-#define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
-
 #define MSR_AMD64_RMP_BASE		0xc0010132
 #define MSR_AMD64_RMP_END		0xc0010133
+#define MSR_AMD64_RMP_CFG		0xc0010136
+#define MSR_AMD64_SEG_RMP_ENABLED_BIT	0
+#define MSR_AMD64_SEG_RMP_ENABLED	BIT_ULL(MSR_AMD64_SEG_RMP_ENABLED_BIT)
+#define MSR_AMD64_RMP_SEGMENT_SHIFT(x)	(((x) & GENMASK_ULL(13, 8)) >> 8)
 
 #define MSR_SVSM_CAA			0xc001f000
 
@@ -699,15 +703,17 @@
 #define MSR_AMD_CPPC_REQ		0xc00102b3
 #define MSR_AMD_CPPC_STATUS		0xc00102b4
 
-#define AMD_CPPC_LOWEST_PERF(x)		(((x) >> 0) & 0xff)
-#define AMD_CPPC_LOWNONLIN_PERF(x)	(((x) >> 8) & 0xff)
-#define AMD_CPPC_NOMINAL_PERF(x)	(((x) >> 16) & 0xff)
-#define AMD_CPPC_HIGHEST_PERF(x)	(((x) >> 24) & 0xff)
+/* Masks for use with MSR_AMD_CPPC_CAP1 */
+#define AMD_CPPC_LOWEST_PERF_MASK	GENMASK(7, 0)
+#define AMD_CPPC_LOWNONLIN_PERF_MASK	GENMASK(15, 8)
+#define AMD_CPPC_NOMINAL_PERF_MASK	GENMASK(23, 16)
+#define AMD_CPPC_HIGHEST_PERF_MASK	GENMASK(31, 24)
 
-#define AMD_CPPC_MAX_PERF(x)		(((x) & 0xff) << 0)
-#define AMD_CPPC_MIN_PERF(x)		(((x) & 0xff) << 8)
-#define AMD_CPPC_DES_PERF(x)		(((x) & 0xff) << 16)
-#define AMD_CPPC_ENERGY_PERF_PREF(x)	(((x) & 0xff) << 24)
+/* Masks for use with MSR_AMD_CPPC_REQ */
+#define AMD_CPPC_MAX_PERF_MASK		GENMASK(7, 0)
+#define AMD_CPPC_MIN_PERF_MASK		GENMASK(15, 8)
+#define AMD_CPPC_DES_PERF_MASK		GENMASK(23, 16)
+#define AMD_CPPC_EPP_PERF_MASK		GENMASK(31, 24)
 
 /* AMD Performance Counter Global Status and Control MSRs */
 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS	0xc0000300
@@ -719,6 +725,7 @@
 
 /* Zen4 */
 #define MSR_ZEN4_BP_CFG                 0xc001102e
+#define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4
 #define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
 
 /* Fam 19h MSRs */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 88585c1de416..460306b35a4b 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -559,6 +559,9 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 #define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA	(1 << 8)
 
+#define KVM_XEN_MSR_MIN_INDEX			0x40000000u
+#define KVM_XEN_MSR_MAX_INDEX			0x4fffffffu
+
 struct kvm_xen_hvm_config {
 	__u32 flags;
 	__u32 msr;
@@ -925,5 +928,6 @@ struct kvm_hyperv_eventfd {
 #define KVM_X86_SEV_VM		2
 #define KVM_X86_SEV_ES_VM	3
 #define KVM_X86_SNP_VM		4
+#define KVM_X86_TDX_VM		5
 
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index 1814b413fd57..ec1321248dac 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -95,6 +95,7 @@
 #define SVM_EXIT_CR14_WRITE_TRAP		0x09e
 #define SVM_EXIT_CR15_WRITE_TRAP		0x09f
 #define SVM_EXIT_INVPCID       0x0a2
+#define SVM_EXIT_IDLE_HLT      0x0a6
 #define SVM_EXIT_NPF           0x400
 #define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS	0x402
@@ -224,6 +225,7 @@
 	{ SVM_EXIT_CR4_WRITE_TRAP,	"write_cr4_trap" }, \
 	{ SVM_EXIT_CR8_WRITE_TRAP,	"write_cr8_trap" }, \
 	{ SVM_EXIT_INVPCID,     "invpcid" }, \
+	{ SVM_EXIT_IDLE_HLT,     "idle-halt" }, \
 	{ SVM_EXIT_NPF,         "npf" }, \
 	{ SVM_EXIT_AVIC_INCOMPLETE_IPI,		"avic_incomplete_ipi" }, \
 	{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS,   "avic_unaccelerated_access" }, \
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 0199d56cb479..d66b710d628f 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -3,6 +3,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -28,7 +29,7 @@
  * only for the return value that is the same as the source input,
  * which the compiler could/should do much better anyway.
  */
-SYM_FUNC_START(__memset)
+SYM_TYPED_FUNC_START(__memset)
 	ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS
 
 	movq %rdi,%r9
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index caedb3ef6688..f5dd84eb55dc 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -996,8 +996,8 @@ AVXcode: 4
 83: Grp1 Ev,Ib (1A),(es)
 # CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
 #			     CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
 88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
 8f: POP2 Bq,Rq (000),(11B),(ev)
 a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 04ba035d67e9..b9ce3aab15fe 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -24,6 +24,7 @@
 
 #include <sys/poll.h>
 #include <sys/utsname.h>
+#include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -677,6 +678,88 @@ static void kvp_process_ipconfig_file(char *cmd,
 	pclose(file);
 }
 
+static bool kvp_verify_ip_address(const void *address_string)
+{
+	char verify_buf[sizeof(struct in6_addr)];
+
+	if (inet_pton(AF_INET, address_string, verify_buf) == 1)
+		return true;
+	if (inet_pton(AF_INET6, address_string, verify_buf) == 1)
+		return true;
+	return false;
+}
+
+static void kvp_extract_routes(const char *line, void **output, size_t *remaining)
+{
+	static const char needle[] = "via ";
+	const char *match, *haystack = line;
+
+	while ((match = strstr(haystack, needle))) {
+		const char *address, *next_char;
+
+		/* Address starts after needle. */
+		address = match + strlen(needle);
+
+		/* The char following address is a space or end of line. */
+		next_char = strpbrk(address, " \t\\");
+		if (!next_char)
+			next_char = address + strlen(address) + 1;
+
+		/* Enough room for address and semicolon. */
+		if (*remaining >= (next_char - address) + 1) {
+			memcpy(*output, address, next_char - address);
+			/* Terminate string for verification. */
+			memcpy(*output + (next_char - address), "", 1);
+			if (kvp_verify_ip_address(*output)) {
+				/* Advance output buffer. */
+				*output += next_char - address;
+				*remaining -= next_char - address;
+
+				/* Each address needs a trailing semicolon. */
+				memcpy(*output, ";", 1);
+				*output += 1;
+				*remaining -= 1;
+			}
+		}
+		haystack = next_char;
+	}
+}
+
+static void kvp_get_gateway(void *buffer, size_t buffer_len)
+{
+	static const char needle[] = "default ";
+	FILE *f;
+	void *output = buffer;
+	char *line = NULL;
+	size_t alloc_size = 0, remaining = buffer_len - 1;
+	ssize_t num_chars;
+
+	/* Show route information in a single line, for each address family */
+	f = popen("ip --oneline -4 route show;ip --oneline -6 route show", "r");
+	if (!f) {
+		/* Convert buffer into C-String. */
+		memcpy(output, "", 1);
+		return;
+	}
+	while ((num_chars = getline(&line, &alloc_size, f)) > 0) {
+		/* Skip short lines. */
+		if (num_chars <= strlen(needle))
+			continue;
+		/* Skip lines without default route. */
+		if (memcmp(line, needle, strlen(needle)))
+			continue;
+		/* Remove trailing newline to simplify further parsing. */
+		if (line[num_chars - 1] == '\n')
+			line[num_chars - 1] = '\0';
+		/* Search routes after match. */
+		kvp_extract_routes(line + strlen(needle), &output, &remaining);
+	}
+	/* Convert buffer into C-String. */
+	memcpy(output, "", 1);
+	free(line);
+	pclose(f);
+}
+
 static void kvp_get_ipconfig_info(char *if_name,
 				 struct hv_kvp_ipaddr_value *buffer)
 {
@@ -685,30 +768,7 @@ static void kvp_get_ipconfig_info(char *if_name,
 	char *p;
 	FILE *file;
 
-	/*
-	 * Get the address of default gateway (ipv4).
-	 */
-	sprintf(cmd, "%s %s", "ip route show dev", if_name);
-	strcat(cmd, " | awk '/default/ {print $3 }'");
-
-	/*
-	 * Execute the command to gather gateway info.
-	 */
-	kvp_process_ipconfig_file(cmd, (char *)buffer->gate_way,
-				(MAX_GATEWAY_SIZE * 2), INET_ADDRSTRLEN, 0);
-
-	/*
-	 * Get the address of default gateway (ipv6).
-	 */
-	sprintf(cmd, "%s %s", "ip -f inet6  route show dev", if_name);
-	strcat(cmd, " | awk '/default/ {print $3 }'");
-
-	/*
-	 * Execute the command to gather gateway info (ipv6).
-	 */
-	kvp_process_ipconfig_file(cmd, (char *)buffer->gate_way,
-				(MAX_GATEWAY_SIZE * 2), INET6_ADDRSTRLEN, 1);
-
+	kvp_get_gateway(buffer->gate_way, sizeof(buffer->gate_way));
 
 	/*
 	 * Gather the DNS state.
diff --git a/tools/include/linux/cfi_types.h b/tools/include/linux/cfi_types.h
new file mode 100644
index 000000000000..6b8713675765
--- /dev/null
+++ b/tools/include/linux/cfi_types.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Clang Control Flow Integrity (CFI) type definitions.
+ */
+#ifndef _LINUX_CFI_TYPES_H
+#define _LINUX_CFI_TYPES_H
+
+#ifdef __ASSEMBLY__
+#include <linux/linkage.h>
+
+#ifdef CONFIG_CFI_CLANG
+/*
+ * Use the __kcfi_typeid_<function> type identifier symbol to
+ * annotate indirectly called assembly functions. The compiler emits
+ * these symbols for all address-taken function declarations in C
+ * code.
+ */
+#ifndef __CFI_TYPE
+#define __CFI_TYPE(name)				\
+	.4byte __kcfi_typeid_##name
+#endif
+
+#define SYM_TYPED_ENTRY(name, linkage, align...)	\
+	linkage(name) ASM_NL				\
+	align ASM_NL					\
+	__CFI_TYPE(name) ASM_NL				\
+	name:
+
+#define SYM_TYPED_START(name, linkage, align...)	\
+	SYM_TYPED_ENTRY(name, linkage, align)
+
+#else /* CONFIG_CFI_CLANG */
+
+#define SYM_TYPED_START(name, linkage, align...)	\
+	SYM_START(name, linkage, align)
+
+#endif /* CONFIG_CFI_CLANG */
+
+#ifndef SYM_TYPED_FUNC_START
+#define SYM_TYPED_FUNC_START(name) 			\
+	SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* _LINUX_CFI_TYPES_H */
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 1ea2c4c33b86..ef1c27fa3c57 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -85,6 +85,7 @@
 /* compatibility flags */
 #define MAP_FILE	0
 
+#define PKEY_UNRESTRICTED	0x0
 #define PKEY_DISABLE_ACCESS	0x1
 #define PKEY_DISABLE_WRITE	0x2
 #define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\
diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h
index aa5016ff3d91..f333a0ac4ee4 100644
--- a/tools/include/uapi/asm-generic/socket.h
+++ b/tools/include/uapi/asm-generic/socket.h
@@ -145,6 +145,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 88dc393c2bca..2892a45023af 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -849,9 +849,11 @@ __SYSCALL(__NR_getxattrat, sys_getxattrat)
 __SYSCALL(__NR_listxattrat, sys_listxattrat)
 #define __NR_removexattrat 466
 __SYSCALL(__NR_removexattrat, sys_removexattrat)
+#define __NR_open_tree_attr 467
+__SYSCALL(__NR_open_tree_attr, sys_open_tree_attr)
 
 #undef __NR_syscalls
-#define __NR_syscalls 467
+#define __NR_syscalls 468
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 28705ae67784..fd404729b115 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4968,6 +4968,9 @@ union bpf_attr {
  * 		the netns switch takes place from ingress to ingress without
  * 		going through the CPU's backlog queue.
  *
+ * 		*skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during
+ * 		the netns switch.
+ *
  * 		The *flags* argument is reserved and must be 0. The helper is
  * 		currently only supported for tc BPF program types at the
  * 		ingress hook and for veth and netkit target device types. The
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 5d32d53508d9..ced0fc3c3aa5 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -79,6 +79,8 @@ enum {
 #define IPPROTO_MPLS		IPPROTO_MPLS
   IPPROTO_ETHERNET = 143,	/* Ethernet-within-IPv6 Encapsulation	*/
 #define IPPROTO_ETHERNET	IPPROTO_ETHERNET
+  IPPROTO_AGGFRAG = 144,	/* AGGFRAG in ESP (RFC 9347)		*/
+#define IPPROTO_AGGFRAG		IPPROTO_AGGFRAG
   IPPROTO_RAW = 255,		/* Raw IP packets			*/
 #define IPPROTO_RAW		IPPROTO_RAW
   IPPROTO_SMC = 256,		/* Shared Memory Communications		*/
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 502ea63b5d2e..b6ae8ad8934b 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -617,10 +617,6 @@ struct kvm_ioeventfd {
 #define KVM_X86_DISABLE_EXITS_HLT            (1 << 1)
 #define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
 #define KVM_X86_DISABLE_EXITS_CSTATE         (1 << 3)
-#define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
-                                              KVM_X86_DISABLE_EXITS_HLT | \
-                                              KVM_X86_DISABLE_EXITS_PAUSE | \
-                                              KVM_X86_DISABLE_EXITS_CSTATE)
 
 /* for KVM_ENABLE_CAP */
 struct kvm_enable_cap {
@@ -933,6 +929,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_PRE_FAULT_MEMORY 236
 #define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237
 #define KVM_CAP_X86_GUEST_MODE 238
+#define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
@@ -1070,6 +1067,10 @@ struct kvm_dirty_tlb {
 
 #define KVM_REG_SIZE_SHIFT	52
 #define KVM_REG_SIZE_MASK	0x00f0000000000000ULL
+
+#define KVM_REG_SIZE(id)		\
+	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
 #define KVM_REG_SIZE_U8		0x0000000000000000ULL
 #define KVM_REG_SIZE_U16	0x0010000000000000ULL
 #define KVM_REG_SIZE_U32	0x0020000000000000ULL
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 7600bf62dbdf..7eb9571786b8 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -219,6 +219,7 @@ enum {
 	NETDEV_CMD_QSTATS_GET,
 	NETDEV_CMD_BIND_RX,
 	NETDEV_CMD_NAPI_SET,
+	NETDEV_CMD_BIND_TX,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 0524d541d4e3..5fc753c23734 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -385,6 +385,8 @@ enum perf_event_read_format {
  *
  * @sample_max_stack: Max number of frame pointers in a callchain,
  *		      should be < /proc/sys/kernel/perf_event_max_stack
+ *		      Max number of entries of branch stack
+ *		      should be < hardware limit
  */
 struct perf_event_attr {
 
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 887a25286441..f78ee3670dd5 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -98,43 +98,93 @@ struct statx_timestamp {
  */
 struct statx {
 	/* 0x00 */
-	__u32	stx_mask;	/* What results were written [uncond] */
-	__u32	stx_blksize;	/* Preferred general I/O size [uncond] */
-	__u64	stx_attributes;	/* Flags conveying information about the file [uncond] */
+	/* What results were written [uncond] */
+	__u32	stx_mask;
+
+	/* Preferred general I/O size [uncond] */
+	__u32	stx_blksize;
+
+	/* Flags conveying information about the file [uncond] */
+	__u64	stx_attributes;
+
 	/* 0x10 */
-	__u32	stx_nlink;	/* Number of hard links */
-	__u32	stx_uid;	/* User ID of owner */
-	__u32	stx_gid;	/* Group ID of owner */
-	__u16	stx_mode;	/* File mode */
+	/* Number of hard links */
+	__u32	stx_nlink;
+
+	/* User ID of owner */
+	__u32	stx_uid;
+
+	/* Group ID of owner */
+	__u32	stx_gid;
+
+	/* File mode */
+	__u16	stx_mode;
 	__u16	__spare0[1];
+
 	/* 0x20 */
-	__u64	stx_ino;	/* Inode number */
-	__u64	stx_size;	/* File size */
-	__u64	stx_blocks;	/* Number of 512-byte blocks allocated */
-	__u64	stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
+	/* Inode number */
+	__u64	stx_ino;
+
+	/* File size */
+	__u64	stx_size;
+
+	/* Number of 512-byte blocks allocated */
+	__u64	stx_blocks;
+
+	/* Mask to show what's supported in stx_attributes */
+	__u64	stx_attributes_mask;
+
 	/* 0x40 */
-	struct statx_timestamp	stx_atime;	/* Last access time */
-	struct statx_timestamp	stx_btime;	/* File creation time */
-	struct statx_timestamp	stx_ctime;	/* Last attribute change time */
-	struct statx_timestamp	stx_mtime;	/* Last data modification time */
+	/* Last access time */
+	struct statx_timestamp	stx_atime;
+
+	/* File creation time */
+	struct statx_timestamp	stx_btime;
+
+	/* Last attribute change time */
+	struct statx_timestamp	stx_ctime;
+
+	/* Last data modification time */
+	struct statx_timestamp	stx_mtime;
+
 	/* 0x80 */
-	__u32	stx_rdev_major;	/* Device ID of special file [if bdev/cdev] */
+	/* Device ID of special file [if bdev/cdev] */
+	__u32	stx_rdev_major;
 	__u32	stx_rdev_minor;
-	__u32	stx_dev_major;	/* ID of device containing file [uncond] */
+
+	/* ID of device containing file [uncond] */
+	__u32	stx_dev_major;
 	__u32	stx_dev_minor;
+
 	/* 0x90 */
 	__u64	stx_mnt_id;
-	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
-	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
+
+	/* Memory buffer alignment for direct I/O */
+	__u32	stx_dio_mem_align;
+
+	/* File offset alignment for direct I/O */
+	__u32	stx_dio_offset_align;
+
 	/* 0xa0 */
-	__u64	stx_subvol;	/* Subvolume identifier */
-	__u32	stx_atomic_write_unit_min;	/* Min atomic write unit in bytes */
-	__u32	stx_atomic_write_unit_max;	/* Max atomic write unit in bytes */
+	/* Subvolume identifier */
+	__u64	stx_subvol;
+
+	/* Min atomic write unit in bytes */
+	__u32	stx_atomic_write_unit_min;
+
+	/* Max atomic write unit in bytes */
+	__u32	stx_atomic_write_unit_max;
+
 	/* 0xb0 */
-	__u32   stx_atomic_write_segments_max;	/* Max atomic write segment count */
-	__u32   __spare1[1];
+	/* Max atomic write segment count */
+	__u32   stx_atomic_write_segments_max;
+
+	/* File offset alignment for direct I/O reads */
+	__u32	stx_dio_read_offset_align;
+
 	/* 0xb8 */
 	__u64	__spare3[9];	/* Spare space for future expansion */
+
 	/* 0x100 */
 };
 
@@ -164,6 +214,7 @@ struct statx {
 #define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 #define STATX_SUBVOL		0x00008000U	/* Want/got stx_subvol */
 #define STATX_WRITE_ATOMIC	0x00010000U	/* Want/got atomic_write_* fields */
+#define STATX_DIO_READ_ALIGN	0x00020000U	/* Want/got dio read alignment info */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e0605403f977..fdcee6a71e0f 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1283,6 +1283,7 @@ enum bpf_tc_attach_point {
 	BPF_TC_INGRESS = 1 << 0,
 	BPF_TC_EGRESS  = 1 << 1,
 	BPF_TC_CUSTOM  = 1 << 2,
+	BPF_TC_QDISC   = 1 << 3,
 };
 
 #define BPF_TC_PARENT(a, b) 	\
@@ -1297,9 +1298,11 @@ struct bpf_tc_hook {
 	int ifindex;
 	enum bpf_tc_attach_point attach_point;
 	__u32 parent;
+	__u32 handle;
+	const char *qdisc;
 	size_t :0;
 };
-#define bpf_tc_hook__last_field parent
+#define bpf_tc_hook__last_field qdisc
 
 struct bpf_tc_opts {
 	size_t sz;
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 68a2def17175..c997e69d507f 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -529,9 +529,9 @@ int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id)
 }
 
 
-typedef int (*qdisc_config_t)(struct libbpf_nla_req *req);
+typedef int (*qdisc_config_t)(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook);
 
-static int clsact_config(struct libbpf_nla_req *req)
+static int clsact_config(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook)
 {
 	req->tc.tcm_parent = TC_H_CLSACT;
 	req->tc.tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0);
@@ -539,6 +539,16 @@ static int clsact_config(struct libbpf_nla_req *req)
 	return nlattr_add(req, TCA_KIND, "clsact", sizeof("clsact"));
 }
 
+static int qdisc_config(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook)
+{
+	const char *qdisc = OPTS_GET(hook, qdisc, NULL);
+
+	req->tc.tcm_parent = OPTS_GET(hook, parent, TC_H_ROOT);
+	req->tc.tcm_handle = OPTS_GET(hook, handle, 0);
+
+	return nlattr_add(req, TCA_KIND, qdisc, strlen(qdisc) + 1);
+}
+
 static int attach_point_to_config(struct bpf_tc_hook *hook,
 				  qdisc_config_t *config)
 {
@@ -552,6 +562,9 @@ static int attach_point_to_config(struct bpf_tc_hook *hook,
 		return 0;
 	case BPF_TC_CUSTOM:
 		return -EOPNOTSUPP;
+	case BPF_TC_QDISC:
+		*config = &qdisc_config;
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -596,7 +609,7 @@ static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags)
 	req.tc.tcm_family  = AF_UNSPEC;
 	req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0);
 
-	ret = config(&req);
+	ret = config(&req, hook);
 	if (ret < 0)
 		return ret;
 
@@ -639,6 +652,7 @@ int bpf_tc_hook_destroy(struct bpf_tc_hook *hook)
 	case BPF_TC_INGRESS:
 	case BPF_TC_EGRESS:
 		return libbpf_err(__bpf_tc_detach(hook, NULL, true));
+	case BPF_TC_QDISC:
 	case BPF_TC_INGRESS | BPF_TC_EGRESS:
 		return libbpf_err(tc_qdisc_delete(hook));
 	case BPF_TC_CUSTOM:
diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile
index ffcfd777c451..7fbb50b74c00 100644
--- a/tools/lib/perf/Makefile
+++ b/tools/lib/perf/Makefile
@@ -42,6 +42,7 @@ libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 TEST_ARGS := $(if $(V),-v)
 
 INCLUDES = \
+-I$(OUTPUT)arch/$(SRCARCH)/include/generated/uapi \
 -I$(srctree)/tools/lib/perf/include \
 -I$(srctree)/tools/lib/ \
 -I$(srctree)/tools/include \
@@ -99,7 +100,16 @@ $(LIBAPI)-clean:
 	$(call QUIET_CLEAN, libapi)
 	$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
 
-$(LIBPERF_IN): FORCE
+uapi-asm := $(OUTPUT)arch/$(SRCARCH)/include/generated/uapi/asm
+ifeq ($(SRCARCH),arm64)
+	syscall-y := $(uapi-asm)/unistd_64.h
+endif
+uapi-asm-generic:
+	$(if $(syscall-y),\
+		$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-headers obj=$(uapi-asm) \
+		generic=include/uapi/asm-generic $(syscall-y),)
+
+$(LIBPERF_IN): uapi-asm-generic FORCE
 	$(Q)$(MAKE) $(build)=libperf
 
 $(LIBPERF_A): $(LIBPERF_IN)
@@ -120,7 +130,7 @@ all: fixdep
 clean: $(LIBAPI)-clean
 	$(call QUIET_CLEAN, libperf) $(RM) $(LIBPERF_A) \
                 *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBPERF_VERSION) .*.d .*.cmd tests/*.o LIBPERF-CFLAGS $(LIBPERF_PC) \
-                $(TESTS_STATIC) $(TESTS_SHARED)
+                $(TESTS_STATIC) $(TESTS_SHARED) $(syscall-y)
 
 TESTS_IN = tests-in.o
 
diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps
index 385783489f84..90686e241157 100644
--- a/tools/net/ynl/Makefile.deps
+++ b/tools/net/ynl/Makefile.deps
@@ -20,15 +20,30 @@ CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \
 	$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) \
 	$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_GENERATED_H,ethtool_netlink_generated.h)
 CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h)
+CFLAGS_lockd_netlink:=$(call get_hdr_inc,_LINUX_LOCKD_NETLINK_H,lockd_netlink.h)
 CFLAGS_mptcp_pm:=$(call get_hdr_inc,_LINUX_MPTCP_PM_H,mptcp_pm.h)
 CFLAGS_net_shaper:=$(call get_hdr_inc,_LINUX_NET_SHAPER_H,net_shaper.h)
 CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h)
 CFLAGS_nl80211:=$(call get_hdr_inc,__LINUX_NL802121_H,nl80211.h)
 CFLAGS_nlctrl:=$(call get_hdr_inc,__LINUX_GENERIC_NETLINK_H,genetlink.h)
 CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h)
+CFLAGS_ovpn:=$(call get_hdr_inc,_LINUX_OVPN_H,ovpn.h)
 CFLAGS_ovs_datapath:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h)
 CFLAGS_ovs_flow:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h)
 CFLAGS_ovs_vport:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h)
-CFLAGS_rt-addr:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h)
+CFLAGS_rt-addr:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \
+	$(call get_hdr_inc,__LINUX_IF_ADDR_H,if_addr.h)
+CFLAGS_rt-link:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \
+	$(call get_hdr_inc,_LINUX_IF_LINK_H,if_link.h)
+CFLAGS_rt-neigh:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \
+	$(call get_hdr_inc,__LINUX_NEIGHBOUR_H,neighbour.h)
 CFLAGS_rt-route:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h)
+CFLAGS_rt-rule:=$(call get_hdr_inc,__LINUX_FIB_RULES_H,fib_rules.h)
+CFLAGS_tc:= $(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \
+	$(call get_hdr_inc,__LINUX_PKT_SCHED_H,pkt_sched.h) \
+	$(call get_hdr_inc,__LINUX_PKT_CLS_H,pkt_cls.h) \
+	$(call get_hdr_inc,_TC_CT_H,tc_act/tc_ct.h) \
+	$(call get_hdr_inc,_TC_MIRRED_H,tc_act/tc_mirred.h) \
+	$(call get_hdr_inc,_TC_SKBEDIT_H,tc_act/tc_skbedit.h) \
+	$(call get_hdr_inc,_TC_TUNNEL_KEY_H,tc_act/tc_tunnel_key.h)
 CFLAGS_tcp_metrics:=$(call get_hdr_inc,_LINUX_TCP_METRICS_H,tcp_metrics.h)
diff --git a/tools/net/ynl/generated/Makefile b/tools/net/ynl/generated/Makefile
index 6603ad8d4ce1..86e1e4a959a7 100644
--- a/tools/net/ynl/generated/Makefile
+++ b/tools/net/ynl/generated/Makefile
@@ -22,10 +22,9 @@ TOOL:=../pyynl/ynl_gen_c.py
 TOOL_RST:=../pyynl/ynl_gen_rst.py
 
 SPECS_DIR:=../../../../Documentation/netlink/specs
-GENS_PATHS=$(shell grep -nrI --files-without-match \
-		'protocol: netlink' \
-		$(SPECS_DIR))
-GENS=$(patsubst $(SPECS_DIR)/%.yaml,%,${GENS_PATHS}) rt-addr rt-route
+SPECS_PATHS=$(wildcard $(SPECS_DIR)/*.yaml)
+GENS_UNSUP=conntrack nftables
+GENS=$(filter-out ${GENS_UNSUP},$(patsubst $(SPECS_DIR)/%.yaml,%,${SPECS_PATHS}))
 SRCS=$(patsubst %,%-user.c,${GENS})
 HDRS=$(patsubst %,%-user.h,${GENS})
 OBJS=$(patsubst %,%-user.o,${GENS})
diff --git a/tools/net/ynl/lib/ynl-priv.h b/tools/net/ynl/lib/ynl-priv.h
index 634eb16548b9..824777d7e05e 100644
--- a/tools/net/ynl/lib/ynl-priv.h
+++ b/tools/net/ynl/lib/ynl-priv.h
@@ -25,6 +25,7 @@ enum ynl_policy_type {
 	YNL_PT_UINT,
 	YNL_PT_NUL_STR,
 	YNL_PT_BITFIELD32,
+	YNL_PT_SUBMSG,
 };
 
 enum ynl_parse_result {
@@ -42,7 +43,10 @@ typedef int (*ynl_parse_cb_t)(const struct nlmsghdr *nlh,
 			      struct ynl_parse_arg *yarg);
 
 struct ynl_policy_attr {
-	enum ynl_policy_type type;
+	enum ynl_policy_type type:8;
+	__u8 is_submsg:1;
+	__u8 is_selector:1;
+	__u16 selector_type;
 	unsigned int len;
 	const char *name;
 	const struct ynl_policy_nest *nest;
@@ -94,7 +98,7 @@ struct ynl_ntf_base_type {
 	unsigned char data[] __attribute__((aligned(8)));
 };
 
-struct nlmsghdr *ynl_msg_start_req(struct ynl_sock *ys, __u32 id);
+struct nlmsghdr *ynl_msg_start_req(struct ynl_sock *ys, __u32 id, __u16 flags);
 struct nlmsghdr *ynl_msg_start_dump(struct ynl_sock *ys, __u32 id);
 
 struct nlmsghdr *
@@ -103,6 +107,8 @@ struct nlmsghdr *
 ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version);
 
 int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr);
+int ynl_submsg_failed(struct ynl_parse_arg *yarg, const char *field_name,
+		      const char *sel_name);
 
 /* YNL specific helpers used by the auto-generated code */
 
@@ -207,11 +213,15 @@ static inline void *ynl_attr_data_end(const struct nlattr *attr)
 				     NLMSG_HDRLEN + fixed_hdr_sz); attr; \
 	     (attr) = ynl_attr_next(ynl_nlmsg_end_addr(nlh), attr))
 
-#define ynl_attr_for_each_nested(attr, outer)				\
+#define ynl_attr_for_each_nested_off(attr, outer, offset)		\
 	for ((attr) = ynl_attr_first(outer, outer->nla_len,		\
-				     sizeof(struct nlattr)); attr;	\
+				     sizeof(struct nlattr) + offset);	\
+	     attr;							\
 	     (attr) = ynl_attr_next(ynl_attr_data_end(outer), attr))
 
+#define ynl_attr_for_each_nested(attr, outer)				\
+	ynl_attr_for_each_nested_off(attr, outer, 0)
+
 #define ynl_attr_for_each_payload(start, len, attr)			\
 	for ((attr) = ynl_attr_first(start, len, 0); attr;		\
 	     (attr) = ynl_attr_next(start + len, attr))
diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index 70f899a54007..2a169c3c0797 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -45,8 +45,39 @@
 #define perr(_ys, _msg)			__yerr(&(_ys)->err, errno, _msg)
 
 /* -- Netlink boiler plate */
+static bool
+ynl_err_walk_is_sel(const struct ynl_policy_nest *policy,
+		    const struct nlattr *attr)
+{
+	unsigned int type = ynl_attr_type(attr);
+
+	return policy && type <= policy->max_attr &&
+		policy->table[type].is_selector;
+}
+
+static const struct ynl_policy_nest *
+ynl_err_walk_sel_policy(const struct ynl_policy_attr *policy_attr,
+			const struct nlattr *selector)
+{
+	const struct ynl_policy_nest *policy = policy_attr->nest;
+	const char *sel;
+	unsigned int i;
+
+	if (!policy_attr->is_submsg)
+		return policy;
+
+	sel = ynl_attr_get_str(selector);
+	for (i = 0; i <= policy->max_attr; i++) {
+		if (!strcmp(sel, policy->table[i].name))
+			return policy->table[i].nest;
+	}
+
+	return NULL;
+}
+
 static int
-ynl_err_walk_report_one(const struct ynl_policy_nest *policy, unsigned int type,
+ynl_err_walk_report_one(const struct ynl_policy_nest *policy,
+			const struct nlattr *selector, unsigned int type,
 			char *str, int str_sz, int *n)
 {
 	if (!policy) {
@@ -67,9 +98,34 @@ ynl_err_walk_report_one(const struct ynl_policy_nest *policy, unsigned int type,
 		return 1;
 	}
 
-	if (*n < str_sz)
-		*n += snprintf(str, str_sz - *n,
-			       ".%s", policy->table[type].name);
+	if (*n < str_sz) {
+		int sz;
+
+		sz = snprintf(str, str_sz - *n,
+			      ".%s", policy->table[type].name);
+		*n += sz;
+		str += sz;
+	}
+
+	if (policy->table[type].is_submsg) {
+		if (!selector) {
+			if (*n < str_sz)
+				*n += snprintf(str, str_sz, "(!selector)");
+			return 1;
+		}
+
+		if (ynl_attr_type(selector) !=
+		    policy->table[type].selector_type) {
+			if (*n < str_sz)
+				*n += snprintf(str, str_sz, "(!=selector)");
+			return 1;
+		}
+
+		if (*n < str_sz)
+			*n += snprintf(str, str_sz - *n, "(%s)",
+				       ynl_attr_get_str(selector));
+	}
+
 	return 0;
 }
 
@@ -78,6 +134,8 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off,
 	     const struct ynl_policy_nest *policy, char *str, int str_sz,
 	     const struct ynl_policy_nest **nest_pol)
 {
+	const struct ynl_policy_nest *next_pol;
+	const struct nlattr *selector = NULL;
 	unsigned int astart_off, aend_off;
 	const struct nlattr *attr;
 	unsigned int data_len;
@@ -96,6 +154,10 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off,
 	ynl_attr_for_each_payload(start, data_len, attr) {
 		astart_off = (char *)attr - (char *)start;
 		aend_off = (char *)ynl_attr_data_end(attr) - (char *)start;
+
+		if (ynl_err_walk_is_sel(policy, attr))
+			selector = attr;
+
 		if (aend_off <= off)
 			continue;
 
@@ -109,16 +171,20 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off,
 
 	type = ynl_attr_type(attr);
 
-	if (ynl_err_walk_report_one(policy, type, str, str_sz, &n))
+	if (ynl_err_walk_report_one(policy, selector, type, str, str_sz, &n))
+		return n;
+
+	next_pol = ynl_err_walk_sel_policy(&policy->table[type], selector);
+	if (!next_pol)
 		return n;
 
 	if (!off) {
 		if (nest_pol)
-			*nest_pol = policy->table[type].nest;
+			*nest_pol = next_pol;
 		return n;
 	}
 
-	if (!policy->table[type].nest) {
+	if (!next_pol) {
 		if (n < str_sz)
 			n += snprintf(str, str_sz, "!nest");
 		return n;
@@ -128,7 +194,7 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off,
 	start =  ynl_attr_data(attr);
 	end = start + ynl_attr_data_len(attr);
 
-	return n + ynl_err_walk(ys, start, end, off, policy->table[type].nest,
+	return n + ynl_err_walk(ys, start, end, off, next_pol,
 				&str[n], str_sz - n, nest_pol);
 }
 
@@ -191,12 +257,12 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh,
 		n = snprintf(bad_attr, sizeof(bad_attr), "%sbad attribute: ",
 			     str ? " (" : "");
 
-		start = ynl_nlmsg_data_offset(ys->nlh, ys->family->hdr_len);
+		start = ynl_nlmsg_data_offset(ys->nlh, ys->req_hdr_len);
 		end = ynl_nlmsg_end_addr(ys->nlh);
 
 		off = ys->err.attr_offs;
 		off -= sizeof(struct nlmsghdr);
-		off -= ys->family->hdr_len;
+		off -= ys->req_hdr_len;
 
 		n += ynl_err_walk(ys, start, end, off, ys->req_policy,
 				  &bad_attr[n], sizeof(bad_attr) - n, NULL);
@@ -216,14 +282,14 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh,
 		n = snprintf(miss_attr, sizeof(miss_attr), "%smissing attribute: ",
 			     bad_attr[0] ? ", " : (str ? " (" : ""));
 
-		start = ynl_nlmsg_data_offset(ys->nlh, ys->family->hdr_len);
+		start = ynl_nlmsg_data_offset(ys->nlh, ys->req_hdr_len);
 		end = ynl_nlmsg_end_addr(ys->nlh);
 
 		nest_pol = ys->req_policy;
 		if (tb[NLMSGERR_ATTR_MISS_NEST]) {
 			off = ynl_attr_get_u32(tb[NLMSGERR_ATTR_MISS_NEST]);
 			off -= sizeof(struct nlmsghdr);
-			off -= ys->family->hdr_len;
+			off -= ys->req_hdr_len;
 
 			n += ynl_err_walk(ys, start, end, off, ys->req_policy,
 					  &miss_attr[n], sizeof(miss_attr) - n,
@@ -231,7 +297,7 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh,
 		}
 
 		n2 = 0;
-		ynl_err_walk_report_one(nest_pol, type, &miss_attr[n],
+		ynl_err_walk_report_one(nest_pol, NULL, type, &miss_attr[n],
 					sizeof(miss_attr) - n, &n2);
 		n += n2;
 
@@ -364,7 +430,7 @@ int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr)
 		     "Invalid attribute (binary %s)", policy->name);
 		return -1;
 	case YNL_PT_NUL_STR:
-		if ((!policy->len || len <= policy->len) && !data[len - 1])
+		if (len && (!policy->len || len <= policy->len) && !data[len - 1])
 			break;
 		yerr(yarg->ys, YNL_ERROR_ATTR_INVALID,
 		     "Invalid attribute (string %s)", policy->name);
@@ -384,6 +450,15 @@ int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr)
 	return 0;
 }
 
+int ynl_submsg_failed(struct ynl_parse_arg *yarg, const char *field_name,
+		      const char *sel_name)
+{
+	yerr(yarg->ys, YNL_ERROR_SUBMSG_KEY,
+	     "Parsing error: Sub-message key not set (msg %s, key %s)",
+	     field_name, sel_name);
+	return YNL_PARSE_CB_ERROR;
+}
+
 /* Generic code */
 
 static void ynl_err_reset(struct ynl_sock *ys)
@@ -451,9 +526,9 @@ ynl_gemsg_start(struct ynl_sock *ys, __u32 id, __u16 flags,
 	return nlh;
 }
 
-struct nlmsghdr *ynl_msg_start_req(struct ynl_sock *ys, __u32 id)
+struct nlmsghdr *ynl_msg_start_req(struct ynl_sock *ys, __u32 id, __u16 flags)
 {
-	return ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK);
+	return ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK | flags);
 }
 
 struct nlmsghdr *ynl_msg_start_dump(struct ynl_sock *ys, __u32 id)
diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h
index 59256e258130..db7c0591a63f 100644
--- a/tools/net/ynl/lib/ynl.h
+++ b/tools/net/ynl/lib/ynl.h
@@ -23,6 +23,7 @@ enum ynl_error_code {
 	YNL_ERROR_INV_RESP,
 	YNL_ERROR_INPUT_INVALID,
 	YNL_ERROR_INPUT_TOO_BIG,
+	YNL_ERROR_SUBMSG_KEY,
 };
 
 /**
@@ -80,11 +81,25 @@ struct ynl_sock {
 
 	struct nlmsghdr *nlh;
 	const struct ynl_policy_nest *req_policy;
+	size_t req_hdr_len;
 	unsigned char *tx_buf;
 	unsigned char *rx_buf;
 	unsigned char raw_buf[];
 };
 
+/**
+ * struct ynl_string - parsed individual string
+ * @len: length of the string (excluding terminating character)
+ * @str: value of the string
+ *
+ * Parsed and nul-terminated string. This struct is only used for arrays of
+ * strings. Non-array string members are placed directly in respective types.
+ */
+struct ynl_string {
+	unsigned int len;
+	char str[];
+};
+
 struct ynl_sock *
 ynl_sock_create(const struct ynl_family *yf, struct ynl_error *e);
 void ynl_sock_destroy(struct ynl_sock *ys);
diff --git a/tools/net/ynl/pyynl/cli.py b/tools/net/ynl/pyynl/cli.py
index 794e3c7dcc65..33ccc5c1843b 100755
--- a/tools/net/ynl/pyynl/cli.py
+++ b/tools/net/ynl/pyynl/cli.py
@@ -144,16 +144,17 @@ def main():
             ops = [ (item[0], json.loads(item[1]), args.flags or []) for item in args.multi ]
             reply = ynl.do_multi(ops)
             output(reply)
-    except NlError as e:
-        print(e)
-        exit(1)
 
-    if args.ntf:
-        try:
+        if args.ntf:
             for msg in ynl.poll_ntf(duration=args.duration):
                 output(msg)
-        except KeyboardInterrupt:
-            pass
+    except NlError as e:
+        print(e)
+        exit(1)
+    except KeyboardInterrupt:
+        pass
+    except BrokenPipeError:
+        pass
 
 
 if __name__ == "__main__":
diff --git a/tools/net/ynl/pyynl/ethtool.py b/tools/net/ynl/pyynl/ethtool.py
index af7fddd7b085..cab6b576c876 100755
--- a/tools/net/ynl/pyynl/ethtool.py
+++ b/tools/net/ynl/pyynl/ethtool.py
@@ -338,16 +338,24 @@ def main():
         print('Capabilities:')
         [print(f'\t{v}') for v in bits_to_dict(tsinfo['timestamping'])]
 
-        print(f'PTP Hardware Clock: {tsinfo["phc-index"]}')
+        print(f'PTP Hardware Clock: {tsinfo.get("phc-index", "none")}')
 
-        print('Hardware Transmit Timestamp Modes:')
-        [print(f'\t{v}') for v in bits_to_dict(tsinfo['tx-types'])]
+        if 'tx-types' in tsinfo:
+            print('Hardware Transmit Timestamp Modes:')
+            [print(f'\t{v}') for v in bits_to_dict(tsinfo['tx-types'])]
+        else:
+            print('Hardware Transmit Timestamp Modes: none')
+
+        if 'rx-filters' in tsinfo:
+            print('Hardware Receive Filter Modes:')
+            [print(f'\t{v}') for v in bits_to_dict(tsinfo['rx-filters'])]
+        else:
+            print('Hardware Receive Filter Modes: none')
 
-        print('Hardware Receive Filter Modes:')
-        [print(f'\t{v}') for v in bits_to_dict(tsinfo['rx-filters'])]
+        if 'stats' in tsinfo and tsinfo['stats']:
+            print('Statistics:')
+            [print(f'\t{k}: {v}') for k, v in tsinfo['stats'].items()]
 
-        print('Statistics:')
-        [print(f'\t{k}: {v}') for k, v in tsinfo['stats'].items()]
         return
 
     print(f'Settings for {args.device}:')
diff --git a/tools/net/ynl/pyynl/lib/__init__.py b/tools/net/ynl/pyynl/lib/__init__.py
index 9137b83e580a..71518b9842ee 100644
--- a/tools/net/ynl/pyynl/lib/__init__.py
+++ b/tools/net/ynl/pyynl/lib/__init__.py
@@ -1,8 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 
 from .nlspec import SpecAttr, SpecAttrSet, SpecEnumEntry, SpecEnumSet, \
-    SpecFamily, SpecOperation
+    SpecFamily, SpecOperation, SpecSubMessage, SpecSubMessageFormat
 from .ynl import YnlFamily, Netlink, NlError
 
 __all__ = ["SpecAttr", "SpecAttrSet", "SpecEnumEntry", "SpecEnumSet",
-           "SpecFamily", "SpecOperation", "YnlFamily", "Netlink", "NlError"]
+           "SpecFamily", "SpecOperation", "SpecSubMessage", "SpecSubMessageFormat",
+           "YnlFamily", "Netlink", "NlError"]
diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index a9966ff2a143..76032e01c2e7 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -14,6 +14,7 @@ import yaml
 
 sys.path.append(pathlib.Path(__file__).resolve().parent.as_posix())
 from lib import SpecFamily, SpecAttrSet, SpecAttr, SpecOperation, SpecEnumSet, SpecEnumEntry
+from lib import SpecSubMessage, SpecSubMessageFormat
 
 
 def c_upper(name):
@@ -56,11 +57,20 @@ class Type(SpecAttr):
         self.request = False
         self.reply = False
 
+        self.is_selector = False
+
         if 'len' in attr:
             self.len = attr['len']
 
         if 'nested-attributes' in attr:
-            self.nested_attrs = attr['nested-attributes']
+            nested = attr['nested-attributes']
+        elif 'sub-message' in attr:
+            nested = attr['sub-message']
+        else:
+            nested = None
+
+        if nested:
+            self.nested_attrs = nested
             if self.nested_attrs == family.name:
                 self.nested_render_name = c_lower(f"{family.ident_name}")
             else:
@@ -119,7 +129,9 @@ class Type(SpecAttr):
         return c_upper(value)
 
     def resolve(self):
-        if 'name-prefix' in self.attr:
+        if 'parent-sub-message' in self.attr:
+            enum_name = self.attr['parent-sub-message'].enum_name
+        elif 'name-prefix' in self.attr:
             enum_name = f"{self.attr['name-prefix']}{self.name}"
         else:
             enum_name = f"{self.attr_set.name_prefix}{self.name}"
@@ -142,19 +154,19 @@ class Type(SpecAttr):
         return self.is_recursive() and not ri.op
 
     def presence_type(self):
-        return 'bit'
+        return 'present'
 
     def presence_member(self, space, type_filter):
         if self.presence_type() != type_filter:
             return
 
-        if self.presence_type() == 'bit':
+        if self.presence_type() == 'present':
             pfx = '__' if space == 'user' else ''
             return f"{pfx}u32 {self.c_name}:1;"
 
-        if self.presence_type() == 'len':
+        if self.presence_type() in {'len', 'count'}:
             pfx = '__' if space == 'user' else ''
-            return f"{pfx}u32 {self.c_name}_len;"
+            return f"{pfx}u32 {self.c_name};"
 
     def _complex_member_type(self, ri):
         return None
@@ -162,28 +174,34 @@ class Type(SpecAttr):
     def free_needs_iter(self):
         return False
 
+    def _free_lines(self, ri, var, ref):
+        if self.is_multi_val() or self.presence_type() in {'count', 'len'}:
+            return [f'free({var}->{ref}{self.c_name});']
+        return []
+
     def free(self, ri, var, ref):
-        if self.is_multi_val() or self.presence_type() == 'len':
-            ri.cw.p(f'free({var}->{ref}{self.c_name});')
+        lines = self._free_lines(ri, var, ref)
+        for line in lines:
+            ri.cw.p(line)
 
     def arg_member(self, ri):
         member = self._complex_member_type(ri)
         if member:
-            arg = [member + ' *' + self.c_name]
+            spc = ' ' if member[-1] != '*' else ''
+            arg = [member + spc + '*' + self.c_name]
             if self.presence_type() == 'count':
                 arg += ['unsigned int n_' + self.c_name]
             return arg
         raise Exception(f"Struct member not implemented for class type {self.type}")
 
     def struct_member(self, ri):
-        if self.is_multi_val():
-            ri.cw.p(f"unsigned int n_{self.c_name};")
         member = self._complex_member_type(ri)
         if member:
             ptr = '*' if self.is_multi_val() else ''
             if self.is_recursive_for_op(ri):
                 ptr = '*'
-            ri.cw.p(f"{member} {ptr}{self.c_name};")
+            spc = ' ' if member[-1] != '*' else ''
+            ri.cw.p(f"{member}{spc}{ptr}{self.c_name};")
             return
         members = self.arg_member(ri)
         for one in members:
@@ -209,10 +227,9 @@ class Type(SpecAttr):
         cw.p(f'[{self.enum_name}] = {"{"} .name = "{self.name}", {typol}{"}"},')
 
     def _attr_put_line(self, ri, var, line):
-        if self.presence_type() == 'bit':
-            ri.cw.p(f"if ({var}->_present.{self.c_name})")
-        elif self.presence_type() == 'len':
-            ri.cw.p(f"if ({var}->_present.{self.c_name}_len)")
+        presence = self.presence_type()
+        if presence in {'present', 'len'}:
+            ri.cw.p(f"if ({var}->_{presence}.{self.c_name})")
         ri.cw.p(f"{line};")
 
     def _attr_put_simple(self, ri, var, put_type):
@@ -242,7 +259,7 @@ class Type(SpecAttr):
         if not self.is_multi_val():
             ri.cw.p("if (ynl_attr_validate(yarg, attr))")
             ri.cw.p("return YNL_PARSE_CB_ERROR;")
-            if self.presence_type() == 'bit':
+            if self.presence_type() == 'present':
                 ri.cw.p(f"{var}->_present.{self.c_name} = 1;")
 
         if init_lines:
@@ -263,15 +280,24 @@ class Type(SpecAttr):
         var = "req"
         member = f"{var}->{'.'.join(ref)}"
 
+        local_vars = []
+        if self.free_needs_iter():
+            local_vars += ['unsigned int i;']
+
         code = []
         presence = ''
         for i in range(0, len(ref)):
             presence = f"{var}->{'.'.join(ref[:i] + [''])}_present.{ref[i]}"
             # Every layer below last is a nest, so we know it uses bit presence
             # last layer is "self" and may be a complex type
-            if i == len(ref) - 1 and self.presence_type() != 'bit':
+            if i == len(ref) - 1 and self.presence_type() != 'present':
+                presence = f"{var}->{'.'.join(ref[:i] + [''])}_{self.presence_type()}.{ref[i]}"
                 continue
             code.append(presence + ' = 1;')
+        ref_path = '.'.join(ref[:-1])
+        if ref_path:
+            ref_path += '.'
+        code += self._free_lines(ri, var, ref_path)
         code += self._setter_lines(ri, member, presence)
 
         func_name = f"{op_prefix(ri, direction, deref=deref)}_set_{'_'.join(ref)}"
@@ -279,7 +305,8 @@ class Type(SpecAttr):
         alloc = bool([x for x in code if 'alloc(' in x])
         if free and not alloc:
             func_name = '__' + func_name
-        ri.cw.write_func('static inline void', func_name, body=code,
+        ri.cw.write_func('static inline void', func_name, local_vars=local_vars,
+                         body=code,
                          args=[f'{type_name(ri, direction, deref=deref)} *{var}'] + self.arg_member(ri))
 
 
@@ -340,26 +367,10 @@ class TypeScalar(Type):
         if 'byte-order' in attr:
             self.byte_order_comment = f" /* {attr['byte-order']} */"
 
-        if 'enum' in self.attr:
-            enum = self.family.consts[self.attr['enum']]
-            low, high = enum.value_range()
-            if 'min' not in self.checks:
-                if low != 0 or self.type[0] == 's':
-                    self.checks['min'] = low
-            if 'max' not in self.checks:
-                self.checks['max'] = high
-
-        if 'min' in self.checks and 'max' in self.checks:
-            if self.get_limit('min') > self.get_limit('max'):
-                raise Exception(f'Invalid limit for "{self.name}" min: {self.get_limit("min")} max: {self.get_limit("max")}')
-            self.checks['range'] = True
-
-        low = min(self.get_limit('min', 0), self.get_limit('max', 0))
-        high = max(self.get_limit('min', 0), self.get_limit('max', 0))
-        if low < 0 and self.type[0] == 'u':
-            raise Exception(f'Invalid limit for "{self.name}" negative limit for unsigned type')
-        if low < -32768 or high > 32767:
-            self.checks['full-range'] = True
+        # Classic families have some funny enums, don't bother
+        # computing checks, since we only need them for kernel policies
+        if not family.is_classic():
+            self._init_checks()
 
         # Added by resolve():
         self.is_bitfield = None
@@ -384,6 +395,31 @@ class TypeScalar(Type):
         else:
             self.type_name = '__' + self.type
 
+    def _init_checks(self):
+        if 'enum' in self.attr:
+            enum = self.family.consts[self.attr['enum']]
+            low, high = enum.value_range()
+            if low == None and high == None:
+                self.checks['sparse'] = True
+            else:
+                if 'min' not in self.checks:
+                    if low != 0 or self.type[0] == 's':
+                        self.checks['min'] = low
+                if 'max' not in self.checks:
+                    self.checks['max'] = high
+
+        if 'min' in self.checks and 'max' in self.checks:
+            if self.get_limit('min') > self.get_limit('max'):
+                raise Exception(f'Invalid limit for "{self.name}" min: {self.get_limit("min")} max: {self.get_limit("max")}')
+            self.checks['range'] = True
+
+        low = min(self.get_limit('min', 0), self.get_limit('max', 0))
+        high = max(self.get_limit('min', 0), self.get_limit('max', 0))
+        if low < 0 and self.type[0] == 'u':
+            raise Exception(f'Invalid limit for "{self.name}" negative limit for unsigned type')
+        if low < -32768 or high > 32767:
+            self.checks['full-range'] = True
+
     def _attr_policy(self, policy):
         if 'flags-mask' in self.checks or self.is_bitfield:
             if self.is_bitfield:
@@ -402,6 +438,8 @@ class TypeScalar(Type):
             return f"NLA_POLICY_MIN({policy}, {self.get_limit_str('min')})"
         elif 'max' in self.checks:
             return f"NLA_POLICY_MAX({policy}, {self.get_limit_str('max')})"
+        elif 'sparse' in self.checks:
+            return f"NLA_POLICY_VALIDATE_FN({policy}, &{c_lower(self.enum_name)}_validate)"
         return super()._attr_policy(policy)
 
     def _attr_typol(self):
@@ -448,7 +486,10 @@ class TypeString(Type):
         ri.cw.p(f"char *{self.c_name};")
 
     def _attr_typol(self):
-        return f'.type = YNL_PT_NUL_STR, '
+        typol = f'.type = YNL_PT_NUL_STR, '
+        if self.is_selector:
+            typol += '.is_selector = 1, '
+        return typol
 
     def _attr_policy(self, policy):
         if 'exact-len' in self.checks:
@@ -473,7 +514,7 @@ class TypeString(Type):
         self._attr_put_simple(ri, var, 'str')
 
     def _attr_get(self, ri, var):
-        len_mem = var + '->_present.' + self.c_name + '_len'
+        len_mem = var + '->_len.' + self.c_name
         return [f"{len_mem} = len;",
                 f"{var}->{self.c_name} = malloc(len + 1);",
                 f"memcpy({var}->{self.c_name}, ynl_attr_get_str(attr), len);",
@@ -482,11 +523,10 @@ class TypeString(Type):
                ['unsigned int len;']
 
     def _setter_lines(self, ri, member, presence):
-        return [f"free({member});",
-                f"{presence}_len = strlen({self.c_name});",
-                f"{member} = malloc({presence}_len + 1);",
-                f'memcpy({member}, {self.c_name}, {presence}_len);',
-                f'{member}[{presence}_len] = 0;']
+        return [f"{presence} = strlen({self.c_name});",
+                f"{member} = malloc({presence} + 1);",
+                f'memcpy({member}, {self.c_name}, {presence});',
+                f'{member}[{presence}] = 0;']
 
 
 class TypeBinary(Type):
@@ -525,10 +565,10 @@ class TypeBinary(Type):
 
     def attr_put(self, ri, var):
         self._attr_put_line(ri, var, f"ynl_attr_put(nlh, {self.enum_name}, " +
-                            f"{var}->{self.c_name}, {var}->_present.{self.c_name}_len)")
+                            f"{var}->{self.c_name}, {var}->_len.{self.c_name})")
 
     def _attr_get(self, ri, var):
-        len_mem = var + '->_present.' + self.c_name + '_len'
+        len_mem = var + '->_len.' + self.c_name
         return [f"{len_mem} = len;",
                 f"{var}->{self.c_name} = malloc(len);",
                 f"memcpy({var}->{self.c_name}, ynl_attr_data(attr), len);"], \
@@ -536,10 +576,60 @@ class TypeBinary(Type):
                ['unsigned int len;']
 
     def _setter_lines(self, ri, member, presence):
-        return [f"free({member});",
-                f"{presence}_len = len;",
-                f"{member} = malloc({presence}_len);",
-                f'memcpy({member}, {self.c_name}, {presence}_len);']
+        return [f"{presence} = len;",
+                f"{member} = malloc({presence});",
+                f'memcpy({member}, {self.c_name}, {presence});']
+
+
+class TypeBinaryStruct(TypeBinary):
+    def struct_member(self, ri):
+        ri.cw.p(f'struct {c_lower(self.get("struct"))} *{self.c_name};')
+
+    def _attr_get(self, ri, var):
+        struct_sz = 'sizeof(struct ' + c_lower(self.get("struct")) + ')'
+        len_mem = var + '->_' + self.presence_type() + '.' + self.c_name
+        return [f"{len_mem} = len;",
+                f"if (len < {struct_sz})",
+                f"{var}->{self.c_name} = calloc(1, {struct_sz});",
+                "else",
+                f"{var}->{self.c_name} = malloc(len);",
+                f"memcpy({var}->{self.c_name}, ynl_attr_data(attr), len);"], \
+               ['len = ynl_attr_data_len(attr);'], \
+               ['unsigned int len;']
+
+
+class TypeBinaryScalarArray(TypeBinary):
+    def arg_member(self, ri):
+        return [f'__{self.get("sub-type")} *{self.c_name}', 'size_t count']
+
+    def presence_type(self):
+        return 'count'
+
+    def struct_member(self, ri):
+        ri.cw.p(f'__{self.get("sub-type")} *{self.c_name};')
+
+    def attr_put(self, ri, var):
+        presence = self.presence_type()
+        ri.cw.block_start(line=f"if ({var}->_{presence}.{self.c_name})")
+        ri.cw.p(f"i = {var}->_{presence}.{self.c_name} * sizeof(__{self.get('sub-type')});")
+        ri.cw.p(f"ynl_attr_put(nlh, {self.enum_name}, " +
+                f"{var}->{self.c_name}, i);")
+        ri.cw.block_end()
+
+    def _attr_get(self, ri, var):
+        len_mem = var + '->_count.' + self.c_name
+        return [f"{len_mem} = len / sizeof(__{self.get('sub-type')});",
+                f"len = {len_mem} * sizeof(__{self.get('sub-type')});",
+                f"{var}->{self.c_name} = malloc(len);",
+                f"memcpy({var}->{self.c_name}, ynl_attr_data(attr), len);"], \
+               ['len = ynl_attr_data_len(attr);'], \
+               ['unsigned int len;']
+
+    def _setter_lines(self, ri, member, presence):
+        return [f"{presence} = count;",
+                f"count *= sizeof(__{self.get('sub-type')});",
+                f"{member} = malloc(count);",
+                f'memcpy({member}, {self.c_name}, count);']
 
 
 class TypeBitfield32(Type):
@@ -574,12 +664,14 @@ class TypeNest(Type):
     def _complex_member_type(self, ri):
         return self.nested_struct_type
 
-    def free(self, ri, var, ref):
+    def _free_lines(self, ri, var, ref):
+        lines = []
         at = '&'
         if self.is_recursive_for_op(ri):
             at = ''
-            ri.cw.p(f'if ({var}->{ref}{self.c_name})')
-        ri.cw.p(f'{self.nested_render_name}_free({at}{var}->{ref}{self.c_name});')
+            lines += [f'if ({var}->{ref}{self.c_name})']
+        lines += [f'{self.nested_render_name}_free({at}{var}->{ref}{self.c_name});']
+        return lines
 
     def _attr_typol(self):
         return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, '
@@ -593,7 +685,11 @@ class TypeNest(Type):
                             f"{self.enum_name}, {at}{var}->{self.c_name})")
 
     def _attr_get(self, ri, var):
-        get_lines = [f"if ({self.nested_render_name}_parse(&parg, attr))",
+        pns = self.family.pure_nested_structs[self.nested_attrs]
+        args = ["&parg", "attr"]
+        for sel in pns.external_selectors():
+            args.append(f'{var}->{sel.name}')
+        get_lines = [f"if ({self.nested_render_name}_parse({', '.join(args)}))",
                      "return YNL_PARSE_CB_ERROR;"]
         init_lines = [f"parg.rsp_policy = &{self.nested_render_name}_nest;",
                       f"parg.data = &{var}->{self.c_name};"]
@@ -623,24 +719,46 @@ class TypeMultiAttr(Type):
     def _complex_member_type(self, ri):
         if 'type' not in self.attr or self.attr['type'] == 'nest':
             return self.nested_struct_type
+        elif self.attr['type'] == 'binary' and 'struct' in self.attr:
+            return None  # use arg_member()
+        elif self.attr['type'] == 'string':
+            return 'struct ynl_string *'
         elif self.attr['type'] in scalars:
             scalar_pfx = '__' if ri.ku_space == 'user' else ''
             return scalar_pfx + self.attr['type']
         else:
             raise Exception(f"Sub-type {self.attr['type']} not supported yet")
 
+    def arg_member(self, ri):
+        if self.type == 'binary' and 'struct' in self.attr:
+            return [f'struct {c_lower(self.attr["struct"])} *{self.c_name}',
+                    f'unsigned int n_{self.c_name}']
+        return super().arg_member(ri)
+
     def free_needs_iter(self):
-        return 'type' not in self.attr or self.attr['type'] == 'nest'
+        return self.attr['type'] in {'nest', 'string'}
 
-    def free(self, ri, var, ref):
+    def _free_lines(self, ri, var, ref):
+        lines = []
         if self.attr['type'] in scalars:
-            ri.cw.p(f"free({var}->{ref}{self.c_name});")
+            lines += [f"free({var}->{ref}{self.c_name});"]
+        elif self.attr['type'] == 'binary':
+            lines += [f"free({var}->{ref}{self.c_name});"]
+        elif self.attr['type'] == 'string':
+            lines += [
+                f"for (i = 0; i < {var}->{ref}_count.{self.c_name}; i++)",
+                f"free({var}->{ref}{self.c_name}[i]);",
+                f"free({var}->{ref}{self.c_name});",
+            ]
         elif 'type' not in self.attr or self.attr['type'] == 'nest':
-            ri.cw.p(f"for (i = 0; i < {var}->{ref}n_{self.c_name}; i++)")
-            ri.cw.p(f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name}[i]);')
-            ri.cw.p(f"free({var}->{ref}{self.c_name});")
+            lines += [
+                f"for (i = 0; i < {var}->{ref}_count.{self.c_name}; i++)",
+                f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name}[i]);',
+                f"free({var}->{ref}{self.c_name});",
+            ]
         else:
             raise Exception(f"Free of MultiAttr sub-type {self.attr['type']} not supported yet")
+        return lines
 
     def _attr_policy(self, policy):
         return self.base_type._attr_policy(policy)
@@ -654,20 +772,23 @@ class TypeMultiAttr(Type):
     def attr_put(self, ri, var):
         if self.attr['type'] in scalars:
             put_type = self.type
-            ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)")
+            ri.cw.p(f"for (i = 0; i < {var}->_count.{self.c_name}; i++)")
             ri.cw.p(f"ynl_attr_put_{put_type}(nlh, {self.enum_name}, {var}->{self.c_name}[i]);")
+        elif self.attr['type'] == 'binary' and 'struct' in self.attr:
+            ri.cw.p(f"for (i = 0; i < {var}->_count.{self.c_name}; i++)")
+            ri.cw.p(f"ynl_attr_put(nlh, {self.enum_name}, &{var}->{self.c_name}[i], sizeof(struct {c_lower(self.attr['struct'])}));")
+        elif self.attr['type'] == 'string':
+            ri.cw.p(f"for (i = 0; i < {var}->_count.{self.c_name}; i++)")
+            ri.cw.p(f"ynl_attr_put_str(nlh, {self.enum_name}, {var}->{self.c_name}[i]->str);")
         elif 'type' not in self.attr or self.attr['type'] == 'nest':
-            ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)")
+            ri.cw.p(f"for (i = 0; i < {var}->_count.{self.c_name}; i++)")
             self._attr_put_line(ri, var, f"{self.nested_render_name}_put(nlh, " +
                                 f"{self.enum_name}, &{var}->{self.c_name}[i])")
         else:
             raise Exception(f"Put of MultiAttr sub-type {self.attr['type']} not supported yet")
 
     def _setter_lines(self, ri, member, presence):
-        # For multi-attr we have a count, not presence, hack up the presence
-        presence = presence[:-(len('_present.') + len(self.c_name))] + "n_" + self.c_name
-        return [f"free({member});",
-                f"{member} = {self.c_name};",
+        return [f"{member} = {self.c_name};",
                 f"{presence} = n_{self.c_name};"]
 
 
@@ -684,22 +805,56 @@ class TypeArrayNest(Type):
         elif self.attr['sub-type'] in scalars:
             scalar_pfx = '__' if ri.ku_space == 'user' else ''
             return scalar_pfx + self.attr['sub-type']
+        elif self.attr['sub-type'] == 'binary' and 'exact-len' in self.checks:
+            return None  # use arg_member()
         else:
             raise Exception(f"Sub-type {self.attr['sub-type']} not supported yet")
 
+    def arg_member(self, ri):
+        if self.sub_type == 'binary' and 'exact-len' in self.checks:
+            return [f'unsigned char (*{self.c_name})[{self.checks["exact-len"]}]',
+                    f'unsigned int n_{self.c_name}']
+        return super().arg_member(ri)
+
     def _attr_typol(self):
         if self.attr['sub-type'] in scalars:
             return f'.type = YNL_PT_U{c_upper(self.sub_type[1:])}, '
+        elif self.attr['sub-type'] == 'binary' and 'exact-len' in self.checks:
+            return f'.type = YNL_PT_BINARY, .len = {self.checks["exact-len"]}, '
         else:
             return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, '
 
     def _attr_get(self, ri, var):
         local_vars = ['const struct nlattr *attr2;']
         get_lines = [f'attr_{self.c_name} = attr;',
-                     'ynl_attr_for_each_nested(attr2, attr)',
-                     f'\t{var}->n_{self.c_name}++;']
+                     'ynl_attr_for_each_nested(attr2, attr) {',
+                     '\tif (ynl_attr_validate(yarg, attr2))',
+                     '\t\treturn YNL_PARSE_CB_ERROR;',
+                     f'\t{var}->_count.{self.c_name}++;',
+                     '}']
         return get_lines, None, local_vars
 
+    def attr_put(self, ri, var):
+        ri.cw.p(f'array = ynl_attr_nest_start(nlh, {self.enum_name});')
+        if self.sub_type in scalars:
+            put_type = self.sub_type
+            ri.cw.block_start(line=f'for (i = 0; i < {var}->_count.{self.c_name}; i++)')
+            ri.cw.p(f"ynl_attr_put_{put_type}(nlh, i, {var}->{self.c_name}[i]);")
+            ri.cw.block_end()
+        elif self.sub_type == 'binary' and 'exact-len' in self.checks:
+            ri.cw.p(f'for (i = 0; i < {var}->_count.{self.c_name}; i++)')
+            ri.cw.p(f"ynl_attr_put(nlh, i, {var}->{self.c_name}[i], {self.checks['exact-len']});")
+        elif self.sub_type == 'nest':
+            ri.cw.p(f'for (i = 0; i < {var}->_count.{self.c_name}; i++)')
+            ri.cw.p(f"{self.nested_render_name}_put(nlh, i, &{var}->{self.c_name}[i]);")
+        else:
+            raise Exception(f"Put for ArrayNest sub-type {self.attr['sub-type']} not supported, yet")
+        ri.cw.p('ynl_attr_nest_end(nlh, array);')
+
+    def _setter_lines(self, ri, member, presence):
+        return [f"{member} = {self.c_name};",
+                f"{presence} = n_{self.c_name};"]
+
 
 class TypeNestTypeValue(Type):
     def _complex_member_type(self, ri):
@@ -731,14 +886,71 @@ class TypeNestTypeValue(Type):
         return get_lines, init_lines, local_vars
 
 
+class TypeSubMessage(TypeNest):
+    def __init__(self, family, attr_set, attr, value):
+        super().__init__(family, attr_set, attr, value)
+
+        self.selector = Selector(attr, attr_set)
+
+    def _attr_typol(self):
+        typol = f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, '
+        typol += '.is_submsg = 1, '
+        # Reverse-parsing of the policy (ynl_err_walk() in ynl.c) does not
+        # support external selectors. No family uses sub-messages with external
+        # selector for requests so this is fine for now.
+        if not self.selector.is_external():
+            typol += f'.selector_type = {self.attr_set[self["selector"]].value} '
+        return typol
+
+    def _attr_get(self, ri, var):
+        sel = c_lower(self['selector'])
+        if self.selector.is_external():
+            sel_var = f"_sel_{sel}"
+        else:
+            sel_var = f"{var}->{sel}"
+        get_lines = [f'if (!{sel_var})',
+                     f'return ynl_submsg_failed(yarg, "%s", "%s");' %
+                        (self.name, self['selector']),
+                    f"if ({self.nested_render_name}_parse(&parg, {sel_var}, attr))",
+                     "return YNL_PARSE_CB_ERROR;"]
+        init_lines = [f"parg.rsp_policy = &{self.nested_render_name}_nest;",
+                      f"parg.data = &{var}->{self.c_name};"]
+        return get_lines, init_lines, None
+
+
+class Selector:
+    def __init__(self, msg_attr, attr_set):
+        self.name = msg_attr["selector"]
+
+        if self.name in attr_set:
+            self.attr = attr_set[self.name]
+            self.attr.is_selector = True
+            self._external = False
+        else:
+            # The selector will need to get passed down thru the structs
+            self.attr = None
+            self._external = True
+
+    def set_attr(self, attr):
+        self.attr = attr
+
+    def is_external(self):
+        return self._external
+
+
 class Struct:
-    def __init__(self, family, space_name, type_list=None, inherited=None):
+    def __init__(self, family, space_name, type_list=None, fixed_header=None,
+                 inherited=None, submsg=None):
         self.family = family
         self.space_name = space_name
         self.attr_set = family.attr_sets[space_name]
         # Use list to catch comparisons with empty sets
         self._inherited = inherited if inherited is not None else []
         self.inherited = []
+        self.fixed_header = None
+        if fixed_header:
+            self.fixed_header = 'struct ' + c_lower(fixed_header)
+        self.submsg = submsg
 
         self.nested = type_list is None
         if family.name == c_lower(space_name):
@@ -755,6 +967,7 @@ class Struct:
         self.request = False
         self.reply = False
         self.recursive = False
+        self.in_multi_val = False  # used by a MultiAttr or and legacy arrays
 
         self.attr_list = []
         self.attrs = dict()
@@ -787,6 +1000,19 @@ class Struct:
             raise Exception("Inheriting different members not supported")
         self.inherited = [c_lower(x) for x in sorted(self._inherited)]
 
+    def external_selectors(self):
+        sels = []
+        for name, attr in self.attr_list:
+            if isinstance(attr, TypeSubMessage) and attr.selector.is_external():
+                sels.append(attr.selector)
+        return sels
+
+    def free_needs_iter(self):
+        for _, attr in self.attr_list:
+            if attr.free_needs_iter():
+                return True
+        return False
+
 
 class EnumEntry(SpecEnumEntry):
     def __init__(self, enum_set, yaml, prev, value_start):
@@ -840,7 +1066,7 @@ class EnumSet(SpecEnumSet):
         high = max([x.value for x in self.entries.values()])
 
         if high - low + 1 != len(self.entries):
-            raise Exception("Can't get value range for a noncontiguous enum")
+            return None, None
 
         return low, high
 
@@ -887,18 +1113,25 @@ class AttrSet(SpecAttrSet):
         elif elem['type'] == 'string':
             t = TypeString(self.family, self, elem, value)
         elif elem['type'] == 'binary':
-            t = TypeBinary(self.family, self, elem, value)
+            if 'struct' in elem:
+                t = TypeBinaryStruct(self.family, self, elem, value)
+            elif elem.get('sub-type') in scalars:
+                t = TypeBinaryScalarArray(self.family, self, elem, value)
+            else:
+                t = TypeBinary(self.family, self, elem, value)
         elif elem['type'] == 'bitfield32':
             t = TypeBitfield32(self.family, self, elem, value)
         elif elem['type'] == 'nest':
             t = TypeNest(self.family, self, elem, value)
         elif elem['type'] == 'indexed-array' and 'sub-type' in elem:
-            if elem["sub-type"] in ['nest', 'u32']:
+            if elem["sub-type"] in ['binary', 'nest', 'u32']:
                 t = TypeArrayNest(self.family, self, elem, value)
             else:
                 raise Exception(f'new_attr: unsupported sub-type {elem["sub-type"]}')
         elif elem['type'] == 'nest-type-value':
             t = TypeNestTypeValue(self.family, self, elem, value)
+        elif elem['type'] == 'sub-message':
+            t = TypeSubMessage(self.family, self, elem, value)
         else:
             raise Exception(f"No typed class for type {elem['type']}")
 
@@ -910,6 +1143,14 @@ class AttrSet(SpecAttrSet):
 
 class Operation(SpecOperation):
     def __init__(self, family, yaml, req_value, rsp_value):
+        # Fill in missing operation properties (for fixed hdr-only msgs)
+        for mode in ['do', 'dump', 'event']:
+            for direction in ['request', 'reply']:
+                try:
+                    yaml[mode][direction].setdefault('attributes', [])
+                except KeyError:
+                    pass
+
         super().__init__(family, yaml, req_value, rsp_value)
 
         self.render_name = c_lower(family.ident_name + '_' + self.name)
@@ -935,6 +1176,16 @@ class Operation(SpecOperation):
         self.has_ntf = True
 
 
+class SubMessage(SpecSubMessage):
+    def __init__(self, family, yaml):
+        super().__init__(family, yaml)
+
+        self.render_name = c_lower(family.ident_name + '-' + yaml['name'])
+
+    def resolve(self):
+        self.resolve_up(super())
+
+
 class Family(SpecFamily):
     def __init__(self, file_name, exclude_ops):
         # Added by resolve:
@@ -993,7 +1244,7 @@ class Family(SpecFamily):
 
         # dict space-name -> 'request': set(attrs), 'reply': set(attrs)
         self.root_sets = dict()
-        # dict space-name -> set('request', 'reply')
+        # dict space-name -> Struct
         self.pure_nested_structs = dict()
 
         self._mark_notify()
@@ -1002,6 +1253,7 @@ class Family(SpecFamily):
         self._load_root_sets()
         self._load_nested_sets()
         self._load_attr_use()
+        self._load_selector_passing()
         self._load_hooks()
 
         self.kernel_policy = self.yaml.get('kernel-policy', 'split')
@@ -1017,6 +1269,9 @@ class Family(SpecFamily):
     def new_operation(self, elem, req_value, rsp_value):
         return Operation(self, elem, req_value, rsp_value)
 
+    def new_sub_message(self, elem):
+        return SubMessage(self, elem)
+
     def is_classic(self):
         return self.proto == 'netlink-raw'
 
@@ -1069,20 +1324,85 @@ class Family(SpecFamily):
             for _, spec in self.attr_sets[name].items():
                 if 'nested-attributes' in spec:
                     nested = spec['nested-attributes']
-                    # If the unknown nest we hit is recursive it's fine, it'll be a pointer
-                    if self.pure_nested_structs[nested].recursive:
-                        continue
-                    if nested not in pns_key_seen:
-                        # Dicts are sorted, this will make struct last
-                        struct = self.pure_nested_structs.pop(name)
-                        self.pure_nested_structs[name] = struct
-                        finished = False
-                        break
+                elif 'sub-message' in spec:
+                    nested = spec.sub_message
+                else:
+                    continue
+
+                # If the unknown nest we hit is recursive it's fine, it'll be a pointer
+                if self.pure_nested_structs[nested].recursive:
+                    continue
+                if nested not in pns_key_seen:
+                    # Dicts are sorted, this will make struct last
+                    struct = self.pure_nested_structs.pop(name)
+                    self.pure_nested_structs[name] = struct
+                    finished = False
+                    break
             if finished:
                 pns_key_seen.add(name)
             else:
                 pns_key_list.append(name)
 
+    def _load_nested_set_nest(self, spec):
+        inherit = set()
+        nested = spec['nested-attributes']
+        if nested not in self.root_sets:
+            if nested not in self.pure_nested_structs:
+                self.pure_nested_structs[nested] = \
+                    Struct(self, nested, inherited=inherit,
+                           fixed_header=spec.get('fixed-header'))
+        else:
+            raise Exception(f'Using attr set as root and nested not supported - {nested}')
+
+        if 'type-value' in spec:
+            if nested in self.root_sets:
+                raise Exception("Inheriting members to a space used as root not supported")
+            inherit.update(set(spec['type-value']))
+        elif spec['type'] == 'indexed-array':
+            inherit.add('idx')
+        self.pure_nested_structs[nested].set_inherited(inherit)
+
+        return nested
+
+    def _load_nested_set_submsg(self, spec):
+        # Fake the struct type for the sub-message itself
+        # its not a attr_set but codegen wants attr_sets.
+        submsg = self.sub_msgs[spec["sub-message"]]
+        nested = submsg.name
+
+        attrs = []
+        for name, fmt in submsg.formats.items():
+            attr = {
+                "name": name,
+                "parent-sub-message": spec,
+            }
+            if 'attribute-set' in fmt:
+                attr |= {
+                    "type": "nest",
+                    "nested-attributes": fmt['attribute-set'],
+                }
+                if 'fixed-header' in fmt:
+                    attr |= { "fixed-header": fmt["fixed-header"] }
+            elif 'fixed-header' in fmt:
+                attr |= {
+                    "type": "binary",
+                    "struct": fmt["fixed-header"],
+                }
+            else:
+                attr["type"] = "flag"
+            attrs.append(attr)
+
+        self.attr_sets[nested] = AttrSet(self, {
+            "name": nested,
+            "name-pfx": self.name + '-' + spec.name + '-',
+            "attributes": attrs
+        })
+
+        if nested not in self.pure_nested_structs:
+            self.pure_nested_structs[nested] = Struct(self, nested, submsg=submsg)
+
+        return nested
+
     def _load_nested_sets(self):
         attr_set_queue = list(self.root_sets.keys())
         attr_set_seen = set(self.root_sets.keys())
@@ -1090,55 +1410,61 @@ class Family(SpecFamily):
         while len(attr_set_queue):
             a_set = attr_set_queue.pop(0)
             for attr, spec in self.attr_sets[a_set].items():
-                if 'nested-attributes' not in spec:
+                if 'nested-attributes' in spec:
+                    nested = self._load_nested_set_nest(spec)
+                elif 'sub-message' in spec:
+                    nested = self._load_nested_set_submsg(spec)
+                else:
                     continue
 
-                nested = spec['nested-attributes']
                 if nested not in attr_set_seen:
                     attr_set_queue.append(nested)
                     attr_set_seen.add(nested)
 
-                inherit = set()
-                if nested not in self.root_sets:
-                    if nested not in self.pure_nested_structs:
-                        self.pure_nested_structs[nested] = Struct(self, nested, inherited=inherit)
-                else:
-                    raise Exception(f'Using attr set as root and nested not supported - {nested}')
-
-                if 'type-value' in spec:
-                    if nested in self.root_sets:
-                        raise Exception("Inheriting members to a space used as root not supported")
-                    inherit.update(set(spec['type-value']))
-                elif spec['type'] == 'indexed-array':
-                    inherit.add('idx')
-                self.pure_nested_structs[nested].set_inherited(inherit)
-
         for root_set, rs_members in self.root_sets.items():
             for attr, spec in self.attr_sets[root_set].items():
                 if 'nested-attributes' in spec:
                     nested = spec['nested-attributes']
+                elif 'sub-message' in spec:
+                    nested = spec.sub_message
+                else:
+                    nested = None
+
+                if nested:
                     if attr in rs_members['request']:
                         self.pure_nested_structs[nested].request = True
                     if attr in rs_members['reply']:
                         self.pure_nested_structs[nested].reply = True
 
+                    if spec.is_multi_val():
+                        child = self.pure_nested_structs.get(nested)
+                        child.in_multi_val = True
+
         self._sort_pure_types()
 
         # Propagate the request / reply / recursive
         for attr_set, struct in reversed(self.pure_nested_structs.items()):
             for _, spec in self.attr_sets[attr_set].items():
-                if 'nested-attributes' in spec:
-                    child_name = spec['nested-attributes']
-                    struct.child_nests.add(child_name)
-                    child = self.pure_nested_structs.get(child_name)
-                    if child:
-                        if not child.recursive:
-                            struct.child_nests.update(child.child_nests)
-                        child.request |= struct.request
-                        child.reply |= struct.reply
                 if attr_set in struct.child_nests:
                     struct.recursive = True
 
+                if 'nested-attributes' in spec:
+                    child_name = spec['nested-attributes']
+                elif 'sub-message' in spec:
+                    child_name = spec.sub_message
+                else:
+                    continue
+
+                struct.child_nests.add(child_name)
+                child = self.pure_nested_structs.get(child_name)
+                if child:
+                    if not child.recursive:
+                        struct.child_nests.update(child.child_nests)
+                    child.request |= struct.request
+                    child.reply |= struct.reply
+                    if spec.is_multi_val():
+                        child.in_multi_val = True
+
         self._sort_pure_types()
 
     def _load_attr_use(self):
@@ -1157,6 +1483,30 @@ class Family(SpecFamily):
                 if attr in rs_members['reply']:
                     spec.set_reply()
 
+    def _load_selector_passing(self):
+        def all_structs():
+            for k, v in reversed(self.pure_nested_structs.items()):
+                yield k, v
+            for k, _ in self.root_sets.items():
+                yield k, None  # we don't have a struct, but it must be terminal
+
+        for attr_set, struct in all_structs():
+            for _, spec in self.attr_sets[attr_set].items():
+                if 'nested-attributes' in spec:
+                    child_name = spec['nested-attributes']
+                elif 'sub-message' in spec:
+                    child_name = spec.sub_message
+                else:
+                    continue
+
+                child = self.pure_nested_structs.get(child_name)
+                for selector in child.external_selectors():
+                    if selector.name in self.attr_sets[attr_set]:
+                        sel_attr = self.attr_sets[attr_set][selector.name]
+                        selector.set_attr(sel_attr)
+                    else:
+                        raise Exception("Passing selector thru more than one layer not supported")
+
     def _load_global_policy(self):
         global_set = set()
         attr_set_name = None
@@ -1206,9 +1556,15 @@ class RenderInfo:
         self.op_mode = op_mode
         self.op = op
 
-        self.fixed_hdr = None
+        fixed_hdr = op.fixed_header if op else None
+        self.fixed_hdr_len = 'ys->family->hdr_len'
         if op and op.fixed_header:
-            self.fixed_hdr = 'struct ' + c_lower(op.fixed_header)
+            if op.fixed_header != family.fixed_header:
+                if family.is_classic():
+                    self.fixed_hdr_len = f"sizeof(struct {c_lower(fixed_hdr)})"
+                else:
+                    raise Exception(f"Per-op fixed header not supported, yet")
+
 
         # 'do' and 'dump' response parsing is identical
         self.type_consistent = True
@@ -1239,18 +1595,26 @@ class RenderInfo:
 
         self.struct = dict()
         if op_mode == 'notify':
-            op_mode = 'do'
+            op_mode = 'do' if 'do' in op else 'dump'
         for op_dir in ['request', 'reply']:
             if op:
                 type_list = []
                 if op_dir in op[op_mode]:
                     type_list = op[op_mode][op_dir]['attributes']
-                self.struct[op_dir] = Struct(family, self.attr_set, type_list=type_list)
+                self.struct[op_dir] = Struct(family, self.attr_set,
+                                             fixed_header=fixed_hdr,
+                                             type_list=type_list)
         if op_mode == 'event':
-            self.struct['reply'] = Struct(family, self.attr_set, type_list=op['event']['attributes'])
+            self.struct['reply'] = Struct(family, self.attr_set,
+                                          fixed_header=fixed_hdr,
+                                          type_list=op['event']['attributes'])
 
     def type_empty(self, key):
-        return len(self.struct[key].attr_list) == 0 and self.fixed_hdr is None
+        return len(self.struct[key].attr_list) == 0 and \
+            self.struct['request'].fixed_header is None
+
+    def needs_nlflags(self, direction):
+        return self.op_mode == 'do' and direction == 'request' and self.family.is_classic()
 
 
 class CodeWriter:
@@ -1308,6 +1672,7 @@ class CodeWriter:
         if self._silent_block:
             ind += 1
         self._silent_block = line.endswith(')') and CodeWriter._is_cond(line)
+        self._silent_block |= line.strip() == 'else'
         if line[0] == '#':
             ind = 0
         if add_ind:
@@ -1404,9 +1769,9 @@ class CodeWriter:
 
     def write_func(self, qual_ret, name, body, args=None, local_vars=None):
         self.write_func_prot(qual_ret=qual_ret, name=name, args=args)
+        self.block_start()
         self.write_func_lvar(local_vars=local_vars)
 
-        self.block_start()
         for line in body:
             self.p(line)
         self.block_end()
@@ -1564,11 +1929,37 @@ def print_dump_prototype(ri):
     print_prototype(ri, "request")
 
 
+def put_typol_submsg(cw, struct):
+    cw.block_start(line=f'const struct ynl_policy_attr {struct.render_name}_policy[] =')
+
+    i = 0
+    for name, arg in struct.member_list():
+        nest = ""
+        if arg.type == 'nest':
+            nest = f" .nest = &{arg.nested_render_name}_nest,"
+        cw.p('[%d] = { .type = YNL_PT_SUBMSG, .name = "%s",%s },' %
+             (i, name, nest))
+        i += 1
+
+    cw.block_end(line=';')
+    cw.nl()
+
+    cw.block_start(line=f'const struct ynl_policy_nest {struct.render_name}_nest =')
+    cw.p(f'.max_attr = {i - 1},')
+    cw.p(f'.table = {struct.render_name}_policy,')
+    cw.block_end(line=';')
+    cw.nl()
+
+
 def put_typol_fwd(cw, struct):
     cw.p(f'extern const struct ynl_policy_nest {struct.render_name}_nest;')
 
 
 def put_typol(cw, struct):
+    if struct.submsg:
+        put_typol_submsg(cw, struct)
+        return
+
     type_max = struct.attr_set.max_name
     cw.block_start(line=f'const struct ynl_policy_attr {struct.render_name}_policy[{type_max} + 1] =')
 
@@ -1651,16 +2042,40 @@ def put_req_nested_prototype(ri, struct, suffix=';'):
 
 
 def put_req_nested(ri, struct):
+    local_vars = []
+    init_lines = []
+
+    if struct.submsg is None:
+        local_vars.append('struct nlattr *nest;')
+        init_lines.append("nest = ynl_attr_nest_start(nlh, attr_type);")
+    if struct.fixed_header:
+        local_vars.append('void *hdr;')
+        struct_sz = f'sizeof({struct.fixed_header})'
+        init_lines.append(f"hdr = ynl_nlmsg_put_extra_header(nlh, {struct_sz});")
+        init_lines.append(f"memcpy(hdr, &obj->_hdr, {struct_sz});")
+
+    has_anest = False
+    has_count = False
+    for _, arg in struct.member_list():
+        has_anest |= arg.type == 'indexed-array'
+        has_count |= arg.presence_type() == 'count'
+    if has_anest:
+        local_vars.append('struct nlattr *array;')
+    if has_count:
+        local_vars.append('unsigned int i;')
+
     put_req_nested_prototype(ri, struct, suffix='')
     ri.cw.block_start()
-    ri.cw.write_func_lvar('struct nlattr *nest;')
+    ri.cw.write_func_lvar(local_vars)
 
-    ri.cw.p("nest = ynl_attr_nest_start(nlh, attr_type);")
+    for line in init_lines:
+        ri.cw.p(line)
 
     for _, arg in struct.member_list():
         arg.attr_put(ri, "obj")
 
-    ri.cw.p("ynl_attr_nest_end(nlh, nest);")
+    if struct.submsg is None:
+        ri.cw.p("ynl_attr_nest_end(nlh, nest);")
 
     ri.cw.nl()
     ri.cw.p('return 0;')
@@ -1669,19 +2084,27 @@ def put_req_nested(ri, struct):
 
 
 def _multi_parse(ri, struct, init_lines, local_vars):
+    if struct.fixed_header:
+        local_vars += ['void *hdr;']
     if struct.nested:
-        iter_line = "ynl_attr_for_each_nested(attr, nested)"
+        if struct.fixed_header:
+            iter_line = f"ynl_attr_for_each_nested_off(attr, nested, sizeof({struct.fixed_header}))"
+        else:
+            iter_line = "ynl_attr_for_each_nested(attr, nested)"
     else:
-        if ri.fixed_hdr:
-            local_vars += ['void *hdr;']
         iter_line = "ynl_attr_for_each(attr, nlh, yarg->ys->family->hdr_len)"
+        if ri.op.fixed_header != ri.family.fixed_header:
+            if ri.family.is_classic():
+                iter_line = f"ynl_attr_for_each(attr, nlh, sizeof({struct.fixed_header}))"
+            else:
+                raise Exception(f"Per-op fixed header not supported, yet")
 
     array_nests = set()
     multi_attrs = set()
     needs_parg = False
     for arg, aspec in struct.member_list():
         if aspec['type'] == 'indexed-array' and 'sub-type' in aspec:
-            if aspec["sub-type"] == 'nest':
+            if aspec["sub-type"] in {'binary', 'nest'}:
                 local_vars.append(f'const struct nlattr *attr_{aspec.c_name};')
                 array_nests.add(arg)
             elif aspec['sub-type'] in scalars:
@@ -1692,6 +2115,7 @@ def _multi_parse(ri, struct, init_lines, local_vars):
         if 'multi-attr' in aspec:
             multi_attrs.add(arg)
         needs_parg |= 'nested-attributes' in aspec
+        needs_parg |= 'sub-message' in aspec
     if array_nests or multi_attrs:
         local_vars.append('int i;')
     if needs_parg:
@@ -1713,12 +2137,14 @@ def _multi_parse(ri, struct, init_lines, local_vars):
     for arg in struct.inherited:
         ri.cw.p(f'dst->{arg} = {arg};')
 
-    if ri.fixed_hdr:
-        if ri.family.is_classic():
+    if struct.fixed_header:
+        if struct.nested:
+            ri.cw.p('hdr = ynl_attr_data(nested);')
+        elif ri.family.is_classic():
             ri.cw.p('hdr = ynl_nlmsg_data(nlh);')
         else:
             ri.cw.p('hdr = ynl_nlmsg_data_offset(nlh, sizeof(struct genlmsghdr));')
-        ri.cw.p(f"memcpy(&dst->_hdr, hdr, sizeof({ri.fixed_hdr}));")
+        ri.cw.p(f"memcpy(&dst->_hdr, hdr, sizeof({struct.fixed_header}));")
     for anest in sorted(all_multi):
         aspec = struct[anest]
         ri.cw.p(f"if (dst->{aspec.c_name})")
@@ -1743,7 +2169,7 @@ def _multi_parse(ri, struct, init_lines, local_vars):
 
         ri.cw.block_start(line=f"if (n_{aspec.c_name})")
         ri.cw.p(f"dst->{aspec.c_name} = calloc(n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));")
-        ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};")
+        ri.cw.p(f"dst->_count.{aspec.c_name} = n_{aspec.c_name};")
         ri.cw.p('i = 0;')
         if 'nested-attributes' in aspec:
             ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;")
@@ -1754,6 +2180,9 @@ def _multi_parse(ri, struct, init_lines, local_vars):
             ri.cw.p('return YNL_PARSE_CB_ERROR;')
         elif aspec.sub_type in scalars:
             ri.cw.p(f"dst->{aspec.c_name}[i] = ynl_attr_get_{aspec.sub_type}(attr);")
+        elif aspec.sub_type == 'binary' and 'exact-len' in aspec.checks:
+            # Length is validated by typol
+            ri.cw.p(f'memcpy(dst->{aspec.c_name}[i], ynl_attr_data(attr), {aspec.checks["exact-len"]});')
         else:
             raise Exception(f"Nest parsing type not supported in {aspec['name']}")
         ri.cw.p('i++;')
@@ -1765,7 +2194,7 @@ def _multi_parse(ri, struct, init_lines, local_vars):
         aspec = struct[anest]
         ri.cw.block_start(line=f"if (n_{aspec.c_name})")
         ri.cw.p(f"dst->{aspec.c_name} = calloc(n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));")
-        ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};")
+        ri.cw.p(f"dst->_count.{aspec.c_name} = n_{aspec.c_name};")
         ri.cw.p('i = 0;')
         if 'nested-attributes' in aspec:
             ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;")
@@ -1777,8 +2206,22 @@ def _multi_parse(ri, struct, init_lines, local_vars):
             ri.cw.p('return YNL_PARSE_CB_ERROR;')
         elif aspec.type in scalars:
             ri.cw.p(f"dst->{aspec.c_name}[i] = ynl_attr_get_{aspec.type}(attr);")
+        elif aspec.type == 'binary' and 'struct' in aspec:
+            ri.cw.p('size_t len = ynl_attr_data_len(attr);')
+            ri.cw.nl()
+            ri.cw.p(f'if (len > sizeof(dst->{aspec.c_name}[0]))')
+            ri.cw.p(f'len = sizeof(dst->{aspec.c_name}[0]);')
+            ri.cw.p(f"memcpy(&dst->{aspec.c_name}[i], ynl_attr_data(attr), len);")
+        elif aspec.type == 'string':
+            ri.cw.p('unsigned int len;')
+            ri.cw.nl()
+            ri.cw.p('len = strnlen(ynl_attr_get_str(attr), ynl_attr_data_len(attr));')
+            ri.cw.p(f'dst->{aspec.c_name}[i] = malloc(sizeof(struct ynl_string) + len + 1);')
+            ri.cw.p(f"dst->{aspec.c_name}[i]->len = len;")
+            ri.cw.p(f"memcpy(dst->{aspec.c_name}[i]->str, ynl_attr_get_str(attr), len);")
+            ri.cw.p(f"dst->{aspec.c_name}[i]->str[len] = 0;")
         else:
-            raise Exception('Nest parsing type not supported yet')
+            raise Exception(f'Nest parsing of type {aspec.type} not supported yet')
         ri.cw.p('i++;')
         ri.cw.block_end()
         ri.cw.block_end()
@@ -1793,9 +2236,49 @@ def _multi_parse(ri, struct, init_lines, local_vars):
     ri.cw.nl()
 
 
+def parse_rsp_submsg(ri, struct):
+    parse_rsp_nested_prototype(ri, struct, suffix='')
+
+    var = 'dst'
+    local_vars = {'const struct nlattr *attr = nested;',
+                  f'{struct.ptr_name}{var} = yarg->data;',
+                  'struct ynl_parse_arg parg;'}
+
+    for _, arg in struct.member_list():
+        _, _, l_vars = arg._attr_get(ri, var)
+        local_vars |= set(l_vars) if l_vars else set()
+
+    ri.cw.block_start()
+    ri.cw.write_func_lvar(list(local_vars))
+    ri.cw.p('parg.ys = yarg->ys;')
+    ri.cw.nl()
+
+    first = True
+    for name, arg in struct.member_list():
+        kw = 'if' if first else 'else if'
+        first = False
+
+        ri.cw.block_start(line=f'{kw} (!strcmp(sel, "{name}"))')
+        get_lines, init_lines, _ = arg._attr_get(ri, var)
+        for line in init_lines or []:
+            ri.cw.p(line)
+        for line in get_lines:
+            ri.cw.p(line)
+        if arg.presence_type() == 'present':
+            ri.cw.p(f"{var}->_present.{arg.c_name} = 1;")
+        ri.cw.block_end()
+    ri.cw.p('return 0;')
+    ri.cw.block_end()
+    ri.cw.nl()
+
+
 def parse_rsp_nested_prototype(ri, struct, suffix=';'):
     func_args = ['struct ynl_parse_arg *yarg',
                  'const struct nlattr *nested']
+    for sel in struct.external_selectors():
+        func_args.append('const char *_sel_' + sel.name)
+    if struct.submsg:
+        func_args.insert(1, 'const char *sel')
     for arg in struct.inherited:
         func_args.append('__u32 ' + arg)
 
@@ -1804,6 +2287,9 @@ def parse_rsp_nested_prototype(ri, struct, suffix=';'):
 
 
 def parse_rsp_nested(ri, struct):
+    if struct.submsg:
+        return parse_rsp_submsg(ri, struct)
+
     parse_rsp_nested_prototype(ri, struct, suffix='')
 
     local_vars = ['const struct nlattr *attr;',
@@ -1856,25 +2342,31 @@ def print_req(ri):
         ret_err = 'NULL'
         local_vars += [f'{type_name(ri, rdir(direction))} *rsp;']
 
-    if ri.fixed_hdr:
+    if ri.struct["request"].fixed_header:
         local_vars += ['size_t hdr_len;',
                        'void *hdr;']
 
+    for _, attr in ri.struct["request"].member_list():
+        if attr.presence_type() == 'count':
+            local_vars += ['unsigned int i;']
+            break
+
     print_prototype(ri, direction, terminate=False)
     ri.cw.block_start()
     ri.cw.write_func_lvar(local_vars)
 
     if ri.family.is_classic():
-        ri.cw.p(f"nlh = ynl_msg_start_req(ys, {ri.op.enum_name});")
+        ri.cw.p(f"nlh = ynl_msg_start_req(ys, {ri.op.enum_name}, req->_nlmsg_flags);")
     else:
         ri.cw.p(f"nlh = ynl_gemsg_start_req(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);")
 
     ri.cw.p(f"ys->req_policy = &{ri.struct['request'].render_name}_nest;")
+    ri.cw.p(f"ys->req_hdr_len = {ri.fixed_hdr_len};")
     if 'reply' in ri.op[ri.op_mode]:
         ri.cw.p(f"yrs.yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;")
     ri.cw.nl()
 
-    if ri.fixed_hdr:
+    if ri.struct['request'].fixed_header:
         ri.cw.p("hdr_len = sizeof(req->_hdr);")
         ri.cw.p("hdr = ynl_nlmsg_put_extra_header(nlh, hdr_len);")
         ri.cw.p("memcpy(hdr, &req->_hdr, hdr_len);")
@@ -1920,7 +2412,7 @@ def print_dump(ri):
                   'struct nlmsghdr *nlh;',
                   'int err;']
 
-    if ri.fixed_hdr:
+    if ri.struct['request'].fixed_header:
         local_vars += ['size_t hdr_len;',
                        'void *hdr;']
 
@@ -1941,7 +2433,7 @@ def print_dump(ri):
     else:
         ri.cw.p(f"nlh = ynl_gemsg_start_dump(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);")
 
-    if ri.fixed_hdr:
+    if ri.struct['request'].fixed_header:
         ri.cw.p("hdr_len = sizeof(req->_hdr);")
         ri.cw.p("hdr = ynl_nlmsg_put_extra_header(nlh, hdr_len);")
         ri.cw.p("memcpy(hdr, &req->_hdr, hdr_len);")
@@ -1949,6 +2441,7 @@ def print_dump(ri):
 
     if "request" in ri.op[ri.op_mode]:
         ri.cw.p(f"ys->req_policy = &{ri.struct['request'].render_name}_nest;")
+        ri.cw.p(f"ys->req_hdr_len = {ri.fixed_hdr_len};")
         ri.cw.nl()
         for _, attr in ri.struct["request"].member_list():
             attr.attr_put(ri, "req")
@@ -1994,6 +2487,16 @@ def print_free_prototype(ri, direction, suffix=';'):
     ri.cw.write_func_prot('void', f"{name}_free", [f"struct {struct_name} *{arg}"], suffix=suffix)
 
 
+def print_nlflags_set(ri, direction):
+    name = op_prefix(ri, direction)
+    ri.cw.write_func_prot(f'static inline void', f"{name}_set_nlflags",
+                          [f"struct {name} *req", "__u16 nl_flags"])
+    ri.cw.block_start()
+    ri.cw.p('req->_nlmsg_flags = nl_flags;')
+    ri.cw.block_end()
+    ri.cw.nl()
+
+
 def _print_type(ri, direction, struct):
     suffix = f'_{ri.type_name}{direction_to_suffix[direction]}'
     if not direction and ri.type_name_conflict:
@@ -2004,22 +2507,25 @@ def _print_type(ri, direction, struct):
 
     ri.cw.block_start(line=f"struct {ri.family.c_name}{suffix}")
 
-    if ri.fixed_hdr:
-        ri.cw.p(ri.fixed_hdr + ' _hdr;')
+    if ri.needs_nlflags(direction):
+        ri.cw.p('__u16 _nlmsg_flags;')
+        ri.cw.nl()
+    if struct.fixed_header:
+        ri.cw.p(struct.fixed_header + ' _hdr;')
         ri.cw.nl()
 
-    meta_started = False
-    for _, attr in struct.member_list():
-        for type_filter in ['len', 'bit']:
+    for type_filter in ['present', 'len', 'count']:
+        meta_started = False
+        for _, attr in struct.member_list():
             line = attr.presence_member(ri.ku_space, type_filter)
             if line:
                 if not meta_started:
                     ri.cw.block_start(line=f"struct")
                     meta_started = True
                 ri.cw.p(line)
-    if meta_started:
-        ri.cw.block_end(line='_present;')
-        ri.cw.nl()
+        if meta_started:
+            ri.cw.block_end(line=f'_{type_filter};')
+    ri.cw.nl()
 
     for arg in struct.inherited:
         ri.cw.p(f"__u32 {arg};")
@@ -2043,6 +2549,9 @@ def print_type_helpers(ri, direction, deref=False):
     print_free_prototype(ri, direction)
     ri.cw.nl()
 
+    if ri.needs_nlflags(direction):
+        print_nlflags_set(ri, direction)
+
     if ri.ku_space == 'user' and direction == 'request':
         for _, attr in ri.struct[direction].member_list():
             attr.setter(ri, ri.attr_set, direction, deref=deref)
@@ -2111,11 +2620,9 @@ def print_wrapped_type(ri):
 
 
 def _free_type_members_iter(ri, struct):
-    for _, attr in struct.member_list():
-        if attr.free_needs_iter():
-            ri.cw.p('unsigned int i;')
-            ri.cw.nl()
-            break
+    if struct.free_needs_iter():
+        ri.cw.p('unsigned int i;')
+        ri.cw.nl()
 
 
 def _free_type_members(ri, var, struct, ref=''):
@@ -2252,6 +2759,46 @@ def print_kernel_policy_ranges(family, cw):
             cw.nl()
 
 
+def print_kernel_policy_sparse_enum_validates(family, cw):
+    first = True
+    for _, attr_set in family.attr_sets.items():
+        if attr_set.subset_of:
+            continue
+
+        for _, attr in attr_set.items():
+            if not attr.request:
+                continue
+            if not attr.enum_name:
+                continue
+            if 'sparse' not in attr.checks:
+                continue
+
+            if first:
+                cw.p('/* Sparse enums validation callbacks */')
+                first = False
+
+            sign = '' if attr.type[0] == 'u' else '_signed'
+            suffix = 'ULL' if attr.type[0] == 'u' else 'LL'
+            cw.write_func_prot('static int', f'{c_lower(attr.enum_name)}_validate',
+                               ['const struct nlattr *attr', 'struct netlink_ext_ack *extack'])
+            cw.block_start()
+            cw.block_start(line=f'switch (nla_get_{attr["type"]}(attr))')
+            enum = family.consts[attr['enum']]
+            first_entry = True
+            for entry in enum.entries.values():
+                if first_entry:
+                    first_entry = False
+                else:
+                    cw.p('fallthrough;')
+                cw.p(f'case {entry.c_name}:')
+            cw.p('return 0;')
+            cw.block_end()
+            cw.p('NL_SET_ERR_MSG_ATTR(extack, attr, "invalid enum value");')
+            cw.p('return -EINVAL;')
+            cw.block_end()
+            cw.nl()
+
+
 def print_kernel_op_table_fwd(family, cw, terminate):
     exported = not kernel_can_gen_family_struct(family)
 
@@ -2711,7 +3258,11 @@ def render_uapi(family, cw):
 
 
 def _render_user_ntf_entry(ri, op):
-    ri.cw.block_start(line=f"[{op.enum_name}] = ")
+    if not ri.family.is_classic():
+        ri.cw.block_start(line=f"[{op.enum_name}] = ")
+    else:
+        crud_op = ri.family.req_by_value[op.rsp_value]
+        ri.cw.block_start(line=f"[{crud_op.enum_name}] = ")
     ri.cw.p(f".alloc_sz\t= sizeof({type_name(ri, 'event')}),")
     ri.cw.p(f".cb\t\t= {op_prefix(ri, 'reply', deref=True)}_parse,")
     ri.cw.p(f".policy\t\t= &{ri.struct['reply'].render_name}_nest,")
@@ -2750,7 +3301,8 @@ def render_user_family(family, cw, prototype):
         cw.p(f'.is_classic\t= true,')
         cw.p(f'.classic_id\t= {family.get("protonum")},')
     if family.is_classic():
-        cw.p(f'.hdr_len\t= sizeof(struct {c_lower(family.fixed_header)}),')
+        if family.fixed_header:
+            cw.p(f'.hdr_len\t= sizeof(struct {c_lower(family.fixed_header)}),')
     elif family.fixed_header:
         cw.p(f'.hdr_len\t= sizeof(struct genlmsghdr) + sizeof(struct {c_lower(family.fixed_header)}),')
     else:
@@ -2864,7 +3416,7 @@ def main():
             cw.p(f'#include "{hdr_file}"')
             cw.p('#include "ynl.h"')
         headers = []
-    for definition in parsed['definitions']:
+    for definition in parsed['definitions'] + parsed['attribute-sets']:
         if 'header' in definition:
             headers.append(definition['header'])
     if args.mode == 'user':
@@ -2918,6 +3470,7 @@ def main():
             print_kernel_family_struct_hdr(parsed, cw)
         else:
             print_kernel_policy_ranges(parsed, cw)
+            print_kernel_policy_sparse_enum_validates(parsed, cw)
 
             for _, struct in sorted(parsed.pure_nested_structs.items()):
                 if struct.request:
@@ -2962,6 +3515,9 @@ def main():
             for attr_set, struct in parsed.pure_nested_structs.items():
                 ri = RenderInfo(cw, parsed, args.mode, "", "", attr_set)
                 print_type_full(ri, struct)
+                if struct.request and struct.in_multi_val:
+                    free_rsp_nested_prototype(ri)
+                    cw.nl()
 
             for op_name, op in parsed.ops.items():
                 cw.p(f"/* ============== {op.enum_name} ============== */")
@@ -3021,8 +3577,7 @@ def main():
                     has_recursive_nests = True
             if has_recursive_nests:
                 cw.nl()
-            for name in parsed.pure_nested_structs:
-                struct = Struct(parsed, name)
+            for struct in parsed.pure_nested_structs.values():
                 put_typol(cw, struct)
             for name in parsed.root_sets:
                 struct = Struct(parsed, name)
diff --git a/tools/net/ynl/pyynl/ynl_gen_rst.py b/tools/net/ynl/pyynl/ynl_gen_rst.py
index 6c56d0d726b4..0cb6348e28d3 100755
--- a/tools/net/ynl/pyynl/ynl_gen_rst.py
+++ b/tools/net/ynl/pyynl/ynl_gen_rst.py
@@ -392,7 +392,7 @@ def parse_arguments() -> argparse.Namespace:
 
 
 def parse_yaml_file(filename: str) -> str:
-    """Transform the YAML specified by filename into a rst-formmated string"""
+    """Transform the YAML specified by filename into an RST-formatted string"""
     with open(filename, "r", encoding="utf-8") as spec_file:
         yaml_data = yaml.safe_load(spec_file)
         content = parse_yaml(yaml_data)
diff --git a/tools/net/ynl/samples/.gitignore b/tools/net/ynl/samples/.gitignore
index 7f9781cf532f..7f5fca7682d7 100644
--- a/tools/net/ynl/samples/.gitignore
+++ b/tools/net/ynl/samples/.gitignore
@@ -4,4 +4,6 @@ netdev
 ovs
 page-pool
 rt-addr
+rt-link
 rt-route
+tc
diff --git a/tools/net/ynl/samples/devlink.c b/tools/net/ynl/samples/devlink.c
index d2611d7ebab4..ac9dfb01f280 100644
--- a/tools/net/ynl/samples/devlink.c
+++ b/tools/net/ynl/samples/devlink.c
@@ -22,6 +22,7 @@ int main(int argc, char **argv)
 	ynl_dump_foreach(devs, d) {
 		struct devlink_info_get_req *info_req;
 		struct devlink_info_get_rsp *info_rsp;
+		unsigned i;
 
 		printf("%s/%s:\n", d->bus_name, d->dev_name);
 
@@ -34,11 +35,11 @@ int main(int argc, char **argv)
 		if (!info_rsp)
 			goto err_free_devs;
 
-		if (info_rsp->_present.info_driver_name_len)
+		if (info_rsp->_len.info_driver_name)
 			printf("    driver: %s\n", info_rsp->info_driver_name);
-		if (info_rsp->n_info_version_running)
+		if (info_rsp->_count.info_version_running)
 			printf("    running fw:\n");
-		for (unsigned i = 0; i < info_rsp->n_info_version_running; i++)
+		for (i = 0; i < info_rsp->_count.info_version_running; i++)
 			printf("        %s: %s\n",
 			       info_rsp->info_version_running[i].info_version_name,
 			       info_rsp->info_version_running[i].info_version_value);
diff --git a/tools/net/ynl/samples/rt-addr.c b/tools/net/ynl/samples/rt-addr.c
index 0f4851b4ec57..2edde5c36b18 100644
--- a/tools/net/ynl/samples/rt-addr.c
+++ b/tools/net/ynl/samples/rt-addr.c
@@ -20,7 +20,7 @@ static void rt_addr_print(struct rt_addr_getaddr_rsp *a)
 	if (name)
 		printf("%16s: ", name);
 
-	switch (a->_present.address_len) {
+	switch (a->_len.address) {
 	case 4:
 		addr = inet_ntop(AF_INET, a->address,
 				 addr_str, sizeof(addr_str));
@@ -36,7 +36,7 @@ static void rt_addr_print(struct rt_addr_getaddr_rsp *a)
 	if (addr)
 		printf("%s", addr);
 	else
-		printf("[%d]", a->_present.address_len);
+		printf("[%d]", a->_len.address);
 
 	printf("\n");
 }
diff --git a/tools/net/ynl/samples/rt-link.c b/tools/net/ynl/samples/rt-link.c
new file mode 100644
index 000000000000..acdd4b4a0f74
--- /dev/null
+++ b/tools/net/ynl/samples/rt-link.c
@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <string.h>
+
+#include <ynl.h>
+
+#include <arpa/inet.h>
+#include <net/if.h>
+
+#include "rt-link-user.h"
+
+static void rt_link_print(struct rt_link_getlink_rsp *r)
+{
+	unsigned int i;
+
+	printf("%3d: ", r->_hdr.ifi_index);
+
+	if (r->_len.ifname)
+		printf("%16s: ", r->ifname);
+
+	if (r->_present.mtu)
+		printf("mtu %5d  ", r->mtu);
+
+	if (r->linkinfo._len.kind)
+		printf("kind %-8s  ", r->linkinfo.kind);
+	else
+		printf("     %8s  ", "");
+
+	if (r->prop_list._count.alt_ifname) {
+		printf("altname ");
+		for (i = 0; i < r->prop_list._count.alt_ifname; i++)
+			printf("%s ", r->prop_list.alt_ifname[i]->str);
+		printf(" ");
+	}
+
+	if (r->linkinfo._present.data && r->linkinfo.data._present.netkit) {
+		struct rt_link_linkinfo_netkit_attrs *netkit;
+		const char *name;
+
+		netkit = &r->linkinfo.data.netkit;
+		printf("primary %d  ", netkit->primary);
+
+		name = NULL;
+		if (netkit->_present.policy)
+			name = rt_link_netkit_policy_str(netkit->policy);
+		if (name)
+			printf("policy %s  ", name);
+	}
+
+	printf("\n");
+}
+
+static int rt_link_create_netkit(struct ynl_sock *ys)
+{
+	struct rt_link_getlink_ntf *ntf_gl;
+	struct rt_link_newlink_req *req;
+	struct ynl_ntf_base_type *ntf;
+	int ret;
+
+	req = rt_link_newlink_req_alloc();
+	if (!req) {
+		fprintf(stderr, "Can't alloc req\n");
+		return -1;
+	}
+
+	/* rtnetlink doesn't provide info about the created object.
+	 * It expects us to set the ECHO flag and the dig the info out
+	 * of the notifications...
+	 */
+	rt_link_newlink_req_set_nlflags(req, NLM_F_CREATE | NLM_F_ECHO);
+
+	rt_link_newlink_req_set_linkinfo_kind(req, "netkit");
+
+	/* Test error messages */
+	rt_link_newlink_req_set_linkinfo_data_netkit_policy(req, 10);
+	ret = rt_link_newlink(ys, req);
+	if (ret) {
+		printf("Testing error message for policy being bad:\n\t%s\n", ys->err.msg);
+	} else {
+		fprintf(stderr,	"Warning: unexpected success creating netkit with bad attrs\n");
+		goto created;
+	}
+
+	rt_link_newlink_req_set_linkinfo_data_netkit_policy(req, NETKIT_DROP);
+
+	ret = rt_link_newlink(ys, req);
+created:
+	rt_link_newlink_req_free(req);
+	if (ret) {
+		fprintf(stderr, "YNL: %s\n", ys->err.msg);
+		return -1;
+	}
+
+	if (!ynl_has_ntf(ys)) {
+		fprintf(stderr,
+			"Warning: interface created but received no notification, won't delete the interface\n");
+		return 0;
+	}
+
+	ntf = ynl_ntf_dequeue(ys);
+	if (ntf->cmd !=	RTM_NEWLINK) {
+		fprintf(stderr,
+			"Warning: unexpected notification type, won't delete the interface\n");
+		return 0;
+	}
+	ntf_gl = (void *)ntf;
+	ret = ntf_gl->obj._hdr.ifi_index;
+	ynl_ntf_free(ntf);
+
+	return ret;
+}
+
+static void rt_link_del(struct ynl_sock *ys, int ifindex)
+{
+	struct rt_link_dellink_req *req;
+
+	req = rt_link_dellink_req_alloc();
+	if (!req) {
+		fprintf(stderr, "Can't alloc req\n");
+		return;
+	}
+
+	req->_hdr.ifi_index = ifindex;
+	if (rt_link_dellink(ys, req))
+		fprintf(stderr, "YNL: %s\n", ys->err.msg);
+	else
+		fprintf(stderr,
+			"Trying to delete a Netkit interface (ifindex %d)\n",
+			ifindex);
+
+	rt_link_dellink_req_free(req);
+}
+
+int main(int argc, char **argv)
+{
+	struct rt_link_getlink_req_dump *req;
+	struct rt_link_getlink_list *rsp;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int created = 0;
+
+	ys = ynl_sock_create(&ynl_rt_link_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return 1;
+	}
+
+	if (argc > 1) {
+		fprintf(stderr, "Trying to create a Netkit interface\n");
+		created = rt_link_create_netkit(ys);
+		if (created < 0)
+			goto err_destroy;
+	}
+
+	req = rt_link_getlink_req_dump_alloc();
+	if (!req)
+		goto err_del_ifc;
+
+	rsp = rt_link_getlink_dump(ys, req);
+	rt_link_getlink_req_dump_free(req);
+	if (!rsp)
+		goto err_close;
+
+	if (ynl_dump_empty(rsp))
+		fprintf(stderr, "Error: no links reported\n");
+	ynl_dump_foreach(rsp, link)
+		rt_link_print(link);
+	rt_link_getlink_list_free(rsp);
+
+	if (created)
+		rt_link_del(ys, created);
+
+	ynl_sock_destroy(ys);
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL: %s\n", ys->err.msg);
+err_del_ifc:
+	if (created)
+		rt_link_del(ys, created);
+err_destroy:
+	ynl_sock_destroy(ys);
+	return 2;
+}
diff --git a/tools/net/ynl/samples/rt-route.c b/tools/net/ynl/samples/rt-route.c
index 9d9c868f8873..7427104a96df 100644
--- a/tools/net/ynl/samples/rt-route.c
+++ b/tools/net/ynl/samples/rt-route.c
@@ -26,13 +26,13 @@ static void rt_route_print(struct rt_route_getroute_rsp *r)
 			printf("oif: %-16s ", name);
 	}
 
-	if (r->_present.dst_len) {
+	if (r->_len.dst) {
 		route = inet_ntop(r->_hdr.rtm_family, r->dst,
 				  route_str, sizeof(route_str));
 		printf("dst: %s/%d", route, r->_hdr.rtm_dst_len);
 	}
 
-	if (r->_present.gateway_len) {
+	if (r->_len.gateway) {
 		route = inet_ntop(r->_hdr.rtm_family, r->gateway,
 				  route_str, sizeof(route_str));
 		printf("gateway: %s ", route);
diff --git a/tools/net/ynl/samples/tc.c b/tools/net/ynl/samples/tc.c
new file mode 100644
index 000000000000..0bfff0fdd792
--- /dev/null
+++ b/tools/net/ynl/samples/tc.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <string.h>
+
+#include <ynl.h>
+
+#include <net/if.h>
+
+#include "tc-user.h"
+
+static void tc_qdisc_print(struct tc_getqdisc_rsp *q)
+{
+	char ifname[IF_NAMESIZE];
+	const char *name;
+
+	name = if_indextoname(q->_hdr.tcm_ifindex, ifname);
+	if (name)
+		printf("%16s: ", name);
+
+	if (q->_len.kind) {
+		printf("%s  ", q->kind);
+
+		if (q->options._present.fq_codel) {
+			struct tc_fq_codel_attrs *fq_codel;
+			struct tc_fq_codel_xstats *stats;
+
+			fq_codel = &q->options.fq_codel;
+			stats = q->stats2.app.fq_codel;
+
+			if (fq_codel->_present.limit)
+				printf("limit: %dp ", fq_codel->limit);
+			if (fq_codel->_present.target)
+				printf("target: %dms ",
+				       (fq_codel->target + 500) / 1000);
+			if (q->stats2.app._len.fq_codel)
+				printf("new_flow_cnt: %d ",
+				       stats->qdisc_stats.new_flow_count);
+		}
+	}
+
+	printf("\n");
+}
+
+int main(int argc, char **argv)
+{
+	struct tc_getqdisc_req_dump *req;
+	struct tc_getqdisc_list *rsp;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+
+	ys = ynl_sock_create(&ynl_tc_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return 1;
+	}
+
+	req = tc_getqdisc_req_dump_alloc();
+	if (!req)
+		goto err_destroy;
+
+	rsp = tc_getqdisc_dump(ys, req);
+	tc_getqdisc_req_dump_free(req);
+	if (!rsp)
+		goto err_close;
+
+	if (ynl_dump_empty(rsp))
+		fprintf(stderr, "Error: no addresses reported\n");
+	ynl_dump_foreach(rsp, qdisc)
+		tc_qdisc_print(qdisc);
+	tc_getqdisc_list_free(rsp);
+
+	ynl_sock_destroy(ys);
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL: %s\n", ys->err.msg);
+err_destroy:
+	ynl_sock_destroy(ys);
+	return 2;
+}
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 33d861c04ebd..687c5eafb49a 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -189,6 +189,15 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 	op2 = ins.opcode.bytes[1];
 	op3 = ins.opcode.bytes[2];
 
+	/*
+	 * XXX hack, decoder is buggered and thinks 0xea is 7 bytes long.
+	 */
+	if (op1 == 0xea) {
+		insn->len = 1;
+		insn->type = INSN_BUG;
+		return 0;
+	}
+
 	if (ins.rex_prefix.nbytes) {
 		rex = ins.rex_prefix.bytes[0];
 		rex_w = X86_REX_W(rex) >> 3;
@@ -522,7 +531,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 			case INAT_PFX_REPNE:
 				if (modrm == 0xca)
 					/* eretu/erets */
-					insn->type = INSN_CONTEXT_SWITCH;
+					insn->type = INSN_SYSRET;
 				break;
 			default:
 				if (modrm == 0xca)
@@ -535,11 +544,15 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 
 			insn->type = INSN_JUMP_CONDITIONAL;
 
-		} else if (op2 == 0x05 || op2 == 0x07 || op2 == 0x34 ||
-			   op2 == 0x35) {
+		} else if (op2 == 0x05 || op2 == 0x34) {
+
+			/* syscall, sysenter */
+			insn->type = INSN_SYSCALL;
+
+		} else if (op2 == 0x07 || op2 == 0x35) {
 
-			/* sysenter, sysret */
-			insn->type = INSN_CONTEXT_SWITCH;
+			/* sysret, sysexit */
+			insn->type = INSN_SYSRET;
 
 		} else if (op2 == 0x0b || op2 == 0xb9) {
 
@@ -676,7 +689,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 
 	case 0xca: /* retf */
 	case 0xcb: /* retf */
-		insn->type = INSN_CONTEXT_SWITCH;
+		insn->type = INSN_SYSRET;
 		break;
 
 	case 0xe0: /* loopne */
@@ -721,7 +734,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 		} else if (modrm_reg == 5) {
 
 			/* jmpf */
-			insn->type = INSN_CONTEXT_SWITCH;
+			insn->type = INSN_SYSRET;
 
 		} else if (modrm_reg == 6) {
 
diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c
index 403e587676f1..06ca4a2659a4 100644
--- a/tools/objtool/arch/x86/special.c
+++ b/tools/objtool/arch/x86/special.c
@@ -126,7 +126,7 @@ struct reloc *arch_find_switch_table(struct objtool_file *file,
 	 * indicates a rare GCC quirk/bug which can leave dead
 	 * code behind.
 	 */
-	if (reloc_type(text_reloc) == R_X86_64_PC32) {
+	if (!file->ignore_unreachables && reloc_type(text_reloc) == R_X86_64_PC32) {
 		WARN_INSN(insn, "ignoring unreachables due to jump table quirk");
 		file->ignore_unreachables = true;
 	}
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 4a1f6c3169b3..b21b12ec88d9 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -225,7 +225,9 @@ static bool is_rust_noreturn(const struct symbol *func)
 	       str_ends_with(func->name, "_4core9panicking14panic_nounwind")				||
 	       str_ends_with(func->name, "_4core9panicking18panic_bounds_check")			||
 	       str_ends_with(func->name, "_4core9panicking19assert_failed_inner")			||
+	       str_ends_with(func->name, "_4core9panicking30panic_null_pointer_dereference")		||
 	       str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference")	||
+	       str_ends_with(func->name, "_7___rustc17rust_begin_unwind")				||
 	       strstr(func->name, "_4core9panicking13assert_failed")					||
 	       strstr(func->name, "_4core9panicking11panic_const24panic_const_")			||
 	       (strstr(func->name, "_4core5slice5index24slice_") &&
@@ -3505,6 +3507,34 @@ next_orig:
 	return next_insn_same_sec(file, alt_group->orig_group->last_insn);
 }
 
+static bool skip_alt_group(struct instruction *insn)
+{
+	struct instruction *alt_insn = insn->alts ? insn->alts->insn : NULL;
+
+	/* ANNOTATE_IGNORE_ALTERNATIVE */
+	if (insn->alt_group && insn->alt_group->ignore)
+		return true;
+
+	/*
+	 * For NOP patched with CLAC/STAC, only follow the latter to avoid
+	 * impossible code paths combining patched CLAC with unpatched STAC
+	 * or vice versa.
+	 *
+	 * ANNOTATE_IGNORE_ALTERNATIVE could have been used here, but Linus
+	 * requested not to do that to avoid hurting .s file readability
+	 * around CLAC/STAC alternative sites.
+	 */
+
+	if (!alt_insn)
+		return false;
+
+	/* Don't override ASM_{CLAC,STAC}_UNSAFE */
+	if (alt_insn->alt_group && alt_insn->alt_group->ignore)
+		return false;
+
+	return alt_insn->type == INSN_CLAC || alt_insn->type == INSN_STAC;
+}
+
 /*
  * Follow the branch starting at the given instruction, and recursively follow
  * any other branches (jumps).  Meanwhile, track the frame pointer state at
@@ -3625,7 +3655,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			}
 		}
 
-		if (insn->alt_group && insn->alt_group->ignore)
+		if (skip_alt_group(insn))
 			return 0;
 
 		if (handle_insn_ops(insn, next_insn, &state))
@@ -3684,14 +3714,20 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 
 			break;
 
-		case INSN_CONTEXT_SWITCH:
-			if (func) {
-				if (!next_insn || !next_insn->hint) {
-					WARN_INSN(insn, "unsupported instruction in callable function");
-					return 1;
-				}
-				break;
+		case INSN_SYSCALL:
+			if (func && (!next_insn || !next_insn->hint)) {
+				WARN_INSN(insn, "unsupported instruction in callable function");
+				return 1;
+			}
+
+			break;
+
+		case INSN_SYSRET:
+			if (func && (!next_insn || !next_insn->hint)) {
+				WARN_INSN(insn, "unsupported instruction in callable function");
+				return 1;
 			}
+
 			return 0;
 
 		case INSN_STAC:
@@ -3886,6 +3922,12 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn)
 			WARN_INSN(insn, "RET before UNTRAIN");
 			return 1;
 
+		case INSN_SYSCALL:
+			break;
+
+		case INSN_SYSRET:
+			return 0;
+
 		case INSN_NOP:
 			if (insn->retpoline_safe)
 				return 0;
@@ -3895,6 +3937,9 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn)
 			break;
 		}
 
+		if (insn->dead_end)
+			return 0;
+
 		if (!next) {
 			WARN_INSN(insn, "teh end!");
 			return 1;
diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h
index 089a1acc48a8..01ef6f415adf 100644
--- a/tools/objtool/include/objtool/arch.h
+++ b/tools/objtool/include/objtool/arch.h
@@ -19,7 +19,8 @@ enum insn_type {
 	INSN_CALL,
 	INSN_CALL_DYNAMIC,
 	INSN_RETURN,
-	INSN_CONTEXT_SWITCH,
+	INSN_SYSCALL,
+	INSN_SYSRET,
 	INSN_BUG,
 	INSN_NOP,
 	INSN_STAC,
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index eea95c6c0c71..b7769a22fe1a 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -29,6 +29,7 @@ include $(srctree)/tools/scripts/Makefile.arch
 $(call detected_var,SRCARCH)
 
 CFLAGS += -I$(OUTPUT)arch/$(SRCARCH)/include/generated
+CFLAGS += -I$(OUTPUT)libperf/arch/$(SRCARCH)/include/generated/uapi
 
 # Additional ARCH settings for ppc
 ifeq ($(SRCARCH),powerpc)
diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
index 49eeb2ad8dbd..27c1d5ebcd91 100644
--- a/tools/perf/arch/arm/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
@@ -481,3 +481,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index c844cd5cda62..1e8c44c7b614 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -381,3 +381,4 @@
 464	n64	getxattrat			sys_getxattrat
 465	n64	listxattrat			sys_listxattrat
 466	n64	removexattrat			sys_removexattrat
+467	n64	open_tree_attr			sys_open_tree_attr
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index d8b4ab78bef0..9a084bdb8926 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -557,3 +557,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index e9115b4d8b63..a4569b96ef06 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -469,3 +469,4 @@
 464  common	getxattrat		sys_getxattrat			sys_getxattrat
 465  common	listxattrat		sys_listxattrat			sys_listxattrat
 466  common	removexattrat		sys_removexattrat		sys_removexattrat
+467  common	open_tree_attr		sys_open_tree_attr		sys_open_tree_attr
diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
index c8cad33bf250..52a7652fcff6 100644
--- a/tools/perf/arch/sh/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
@@ -470,3 +470,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
index 727f99d333b3..83e45eb6c095 100644
--- a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
@@ -512,3 +512,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
index 4d0fb2fba7e2..ac007ea00979 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
@@ -396,7 +396,7 @@
 381	i386	pkey_alloc		sys_pkey_alloc
 382	i386	pkey_free		sys_pkey_free
 383	i386	statx			sys_statx
-384	i386	arch_prctl		sys_arch_prctl			compat_sys_arch_prctl
+384	i386	arch_prctl		sys_arch_prctl
 385	i386	io_pgetevents		sys_io_pgetevents_time32	compat_sys_io_pgetevents
 386	i386	rseq			sys_rseq
 393	i386	semget			sys_semget
@@ -472,3 +472,4 @@
 464	i386	getxattrat		sys_getxattrat
 465	i386	listxattrat		sys_listxattrat
 466	i386	removexattrat		sys_removexattrat
+467	i386	open_tree_attr		sys_open_tree_attr
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 5eb708bff1c7..cfb5ca41e30d 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -390,6 +390,7 @@
 464	common	getxattrat		sys_getxattrat
 465	common	listxattrat		sys_listxattrat
 466	common	removexattrat		sys_removexattrat
+467	common	open_tree_attr		sys_open_tree_attr
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
index 37effc1b134e..f657a77314f8 100644
--- a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
@@ -437,3 +437,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index a4499e5a6f9c..857f6646cc23 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -20,6 +20,7 @@ FILES=(
   "include/uapi/linux/stat.h"
   "include/linux/bits.h"
   "include/vdso/bits.h"
+  "include/linux/cfi_types.h"
   "include/linux/const.h"
   "include/vdso/const.h"
   "include/vdso/unaligned.h"
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index d18cc47e89bd..c3322eb3d686 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -392,6 +392,8 @@ struct ucred {
 
 extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
 extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
+extern int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len,
+			    void *data);
 
 struct timespec64;
 struct __kernel_timespec;
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
index 6e6907e63bfc..a15ac2fa4b20 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
@@ -155,4 +155,8 @@
 #define AT_HANDLE_MNT_ID_UNIQUE	0x001	/* Return the u64 unique mount ID. */
 #define AT_HANDLE_CONNECTABLE	0x002	/* Request a connectable file handle */
 
+/* Flags for execveat2(2). */
+#define AT_EXECVE_CHECK		0x10000	/* Only perform a check if execution
+					   would be allowed. */
+
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index 753971770733..e762e1af650c 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -40,6 +40,15 @@
 #define BLOCK_SIZE_BITS 10
 #define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
 
+/* flags for integrity meta */
+#define IO_INTEGRITY_CHK_GUARD		(1U << 0) /* enforce guard check */
+#define IO_INTEGRITY_CHK_REFTAG		(1U << 1) /* enforce ref check */
+#define IO_INTEGRITY_CHK_APPTAG		(1U << 2) /* enforce app check */
+
+#define IO_INTEGRITY_VALID_FLAGS (IO_INTEGRITY_CHK_GUARD | \
+				  IO_INTEGRITY_CHK_REFTAG | \
+				  IO_INTEGRITY_CHK_APPTAG)
+
 #define SEEK_SET	0	/* seek relative to beginning of file */
 #define SEEK_CUR	1	/* seek relative to current file position */
 #define SEEK_END	2	/* seek relative to end of file */
@@ -203,10 +212,8 @@ struct fsxattr {
 #define BLKROTATIONAL _IO(0x12,126)
 #define BLKZEROOUT _IO(0x12,127)
 #define BLKGETDISKSEQ _IOR(0x12,128,__u64)
-/*
- * A jump here: 130-136 are reserved for zoned block devices
- * (see uapi/linux/blkzoned.h)
- */
+/* 130-136 are used by zoned block device ioctls (uapi/linux/blkzoned.h) */
+/* 137-141 are used by blk-crypto ioctls (uapi/linux/blk-crypto.h) */
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
@@ -332,9 +339,13 @@ typedef int __bitwise __kernel_rwf_t;
 /* Atomic Write */
 #define RWF_ATOMIC	((__force __kernel_rwf_t)0x00000040)
 
+/* buffered IO that drops the cache after reading or writing data */
+#define RWF_DONTCACHE	((__force __kernel_rwf_t)0x00000080)
+
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
-			 RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC)
+			 RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\
+			 RWF_DONTCACHE)
 
 #define PROCFS_IOCTL_MAGIC 'f'
 
diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h
index c07008816aca..7fa67c2031a5 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/mount.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h
@@ -179,7 +179,12 @@ struct statmount {
 	__u32 opt_array;	/* [str] Array of nul terminated fs options */
 	__u32 opt_sec_num;	/* Number of security options */
 	__u32 opt_sec_array;	/* [str] Array of nul terminated security options */
-	__u64 __spare2[46];
+	__u64 supported_mask;	/* Mask flags that this kernel supports */
+	__u32 mnt_uidmap_num;	/* Number of uid mappings */
+	__u32 mnt_uidmap;	/* [str] Array of uid mappings (as seen from callers namespace) */
+	__u32 mnt_gidmap_num;	/* Number of gid mappings */
+	__u32 mnt_gidmap;	/* [str] Array of gid mappings (as seen from callers namespace) */
+	__u64 __spare2[43];
 	char str[];		/* Variable size part containing strings */
 };
 
@@ -217,6 +222,9 @@ struct mnt_id_req {
 #define STATMOUNT_SB_SOURCE		0x00000200U	/* Want/got sb_source */
 #define STATMOUNT_OPT_ARRAY		0x00000400U	/* Want/got opt_... */
 #define STATMOUNT_OPT_SEC_ARRAY		0x00000800U	/* Want/got opt_sec... */
+#define STATMOUNT_SUPPORTED_MASK	0x00001000U	/* Want/got supported mask flags */
+#define STATMOUNT_MNT_UIDMAP		0x00002000U	/* Want/got uidmap... */
+#define STATMOUNT_MNT_GIDMAP		0x00004000U	/* Want/got gidmap... */
 
 /*
  * Special @mnt_id values that can be passed to listmount
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 5c6080680cb2..15c18ef4eb11 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -353,4 +353,15 @@ struct prctl_mm_map {
  */
 #define PR_LOCK_SHADOW_STACK_STATUS      76
 
+/*
+ * Controls the mode of timer_create() for CRIU restore operations.
+ * Enabling this allows CRIU to restore timers with explicit IDs.
+ *
+ * Don't use for normal operations as the result might be undefined.
+ */
+#define PR_TIMER_CREATE_RESTORE_IDS		77
+# define PR_TIMER_CREATE_RESTORE_IDS_OFF	0
+# define PR_TIMER_CREATE_RESTORE_IDS_ON		1
+# define PR_TIMER_CREATE_RESTORE_IDS_GET	2
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h
index 887a25286441..f78ee3670dd5 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/stat.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h
@@ -98,43 +98,93 @@ struct statx_timestamp {
  */
 struct statx {
 	/* 0x00 */
-	__u32	stx_mask;	/* What results were written [uncond] */
-	__u32	stx_blksize;	/* Preferred general I/O size [uncond] */
-	__u64	stx_attributes;	/* Flags conveying information about the file [uncond] */
+	/* What results were written [uncond] */
+	__u32	stx_mask;
+
+	/* Preferred general I/O size [uncond] */
+	__u32	stx_blksize;
+
+	/* Flags conveying information about the file [uncond] */
+	__u64	stx_attributes;
+
 	/* 0x10 */
-	__u32	stx_nlink;	/* Number of hard links */
-	__u32	stx_uid;	/* User ID of owner */
-	__u32	stx_gid;	/* Group ID of owner */
-	__u16	stx_mode;	/* File mode */
+	/* Number of hard links */
+	__u32	stx_nlink;
+
+	/* User ID of owner */
+	__u32	stx_uid;
+
+	/* Group ID of owner */
+	__u32	stx_gid;
+
+	/* File mode */
+	__u16	stx_mode;
 	__u16	__spare0[1];
+
 	/* 0x20 */
-	__u64	stx_ino;	/* Inode number */
-	__u64	stx_size;	/* File size */
-	__u64	stx_blocks;	/* Number of 512-byte blocks allocated */
-	__u64	stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
+	/* Inode number */
+	__u64	stx_ino;
+
+	/* File size */
+	__u64	stx_size;
+
+	/* Number of 512-byte blocks allocated */
+	__u64	stx_blocks;
+
+	/* Mask to show what's supported in stx_attributes */
+	__u64	stx_attributes_mask;
+
 	/* 0x40 */
-	struct statx_timestamp	stx_atime;	/* Last access time */
-	struct statx_timestamp	stx_btime;	/* File creation time */
-	struct statx_timestamp	stx_ctime;	/* Last attribute change time */
-	struct statx_timestamp	stx_mtime;	/* Last data modification time */
+	/* Last access time */
+	struct statx_timestamp	stx_atime;
+
+	/* File creation time */
+	struct statx_timestamp	stx_btime;
+
+	/* Last attribute change time */
+	struct statx_timestamp	stx_ctime;
+
+	/* Last data modification time */
+	struct statx_timestamp	stx_mtime;
+
 	/* 0x80 */
-	__u32	stx_rdev_major;	/* Device ID of special file [if bdev/cdev] */
+	/* Device ID of special file [if bdev/cdev] */
+	__u32	stx_rdev_major;
 	__u32	stx_rdev_minor;
-	__u32	stx_dev_major;	/* ID of device containing file [uncond] */
+
+	/* ID of device containing file [uncond] */
+	__u32	stx_dev_major;
 	__u32	stx_dev_minor;
+
 	/* 0x90 */
 	__u64	stx_mnt_id;
-	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
-	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
+
+	/* Memory buffer alignment for direct I/O */
+	__u32	stx_dio_mem_align;
+
+	/* File offset alignment for direct I/O */
+	__u32	stx_dio_offset_align;
+
 	/* 0xa0 */
-	__u64	stx_subvol;	/* Subvolume identifier */
-	__u32	stx_atomic_write_unit_min;	/* Min atomic write unit in bytes */
-	__u32	stx_atomic_write_unit_max;	/* Max atomic write unit in bytes */
+	/* Subvolume identifier */
+	__u64	stx_subvol;
+
+	/* Min atomic write unit in bytes */
+	__u32	stx_atomic_write_unit_min;
+
+	/* Max atomic write unit in bytes */
+	__u32	stx_atomic_write_unit_max;
+
 	/* 0xb0 */
-	__u32   stx_atomic_write_segments_max;	/* Max atomic write segment count */
-	__u32   __spare1[1];
+	/* Max atomic write segment count */
+	__u32   stx_atomic_write_segments_max;
+
+	/* File offset alignment for direct I/O reads */
+	__u32	stx_dio_read_offset_align;
+
 	/* 0xb8 */
 	__u64	__spare3[9];	/* Spare space for future expansion */
+
 	/* 0x100 */
 };
 
@@ -164,6 +214,7 @@ struct statx {
 #define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 #define STATX_SUBVOL		0x00008000U	/* Want/got stx_subvol */
 #define STATX_WRITE_ATOMIC	0x00010000U	/* Want/got atomic_write_* fields */
+#define STATX_DIO_READ_ALIGN	0x00020000U	/* Want/got dio read alignment info */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
diff --git a/tools/perf/trace/beauty/include/uapi/sound/asound.h b/tools/perf/trace/beauty/include/uapi/sound/asound.h
index 4cd513215bcd..5a049eeaecce 100644
--- a/tools/perf/trace/beauty/include/uapi/sound/asound.h
+++ b/tools/perf/trace/beauty/include/uapi/sound/asound.h
@@ -716,7 +716,7 @@ enum {
  *  Raw MIDI section - /dev/snd/midi??
  */
 
-#define SNDRV_RAWMIDI_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 4)
+#define SNDRV_RAWMIDI_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 5)
 
 enum {
 	SNDRV_RAWMIDI_STREAM_OUTPUT = 0,
@@ -728,6 +728,9 @@ enum {
 #define SNDRV_RAWMIDI_INFO_INPUT		0x00000002
 #define SNDRV_RAWMIDI_INFO_DUPLEX		0x00000004
 #define SNDRV_RAWMIDI_INFO_UMP			0x00000008
+#define SNDRV_RAWMIDI_INFO_STREAM_INACTIVE	0x00000010
+
+#define SNDRV_RAWMIDI_DEVICE_UNKNOWN		0
 
 struct snd_rawmidi_info {
 	unsigned int device;		/* RO/WR (control): device number */
@@ -740,7 +743,8 @@ struct snd_rawmidi_info {
 	unsigned char subname[32];	/* name of active or selected subdevice */
 	unsigned int subdevices_count;
 	unsigned int subdevices_avail;
-	unsigned char reserved[64];	/* reserved for future use */
+	int tied_device;		/* R: tied rawmidi device (UMP/legacy) */
+	unsigned char reserved[60];	/* reserved for future use */
 };
 
 #define SNDRV_RAWMIDI_MODE_FRAMING_MASK		(7<<0)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1974395492d7..3c030da2e477 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2566,25 +2566,6 @@ check:
 	return false;
 }
 
-static bool evsel__handle_error_quirks(struct evsel *evsel, int error)
-{
-	/*
-	 * AMD core PMU tries to forward events with precise_ip to IBS PMU
-	 * implicitly.  But IBS PMU has more restrictions so it can fail with
-	 * supported event attributes.  Let's forward it back to the core PMU
-	 * by clearing precise_ip only if it's from precise_max (:P).
-	 */
-	if ((error == -EINVAL || error == -ENOENT) && x86__is_amd_cpu() &&
-	    evsel->core.attr.precise_ip && evsel->precise_max) {
-		evsel->core.attr.precise_ip = 0;
-		pr_debug2_peo("removing precise_ip on AMD\n");
-		display_attr(&evsel->core.attr);
-		return true;
-	}
-
-	return false;
-}
-
 static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 		struct perf_thread_map *threads,
 		int start_cpu_map_idx, int end_cpu_map_idx)
@@ -2730,9 +2711,6 @@ try_fallback:
 	if (evsel__precise_ip_fallback(evsel))
 		goto retry_open;
 
-	if (evsel__handle_error_quirks(evsel, err))
-		goto retry_open;
-
 out_close:
 	if (err)
 		threads->err_thread = thread;
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 9fb2c1343c7f..0b037e7389a0 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -371,7 +371,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 	 *    has to be pointed by symsrc_filename
 	 */
 	if (ofs == 0) {
-		if (dso__data_get_fd(dso, machine, &fd) {
+		if (dso__data_get_fd(dso, machine, &fd)) {
 			ofs = elf_section_offset(fd, ".debug_frame");
 			dso__data_put_fd(dso);
 		}
diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c
index 2c720e3ecad5..fdc7170639e6 100644
--- a/tools/sched_ext/scx_flatcg.bpf.c
+++ b/tools/sched_ext/scx_flatcg.bpf.c
@@ -950,5 +950,5 @@ SCX_OPS_DEFINE(flatcg_ops,
 	       .cgroup_move		= (void *)fcg_cgroup_move,
 	       .init			= (void *)fcg_init,
 	       .exit			= (void *)fcg_exit,
-	       .flags			= SCX_OPS_HAS_CGROUP_WEIGHT | SCX_OPS_ENQ_EXITING,
+	       .flags			= SCX_OPS_ENQ_EXITING,
 	       .name			= "flatcg");
diff --git a/tools/scripts/syscall.tbl b/tools/scripts/syscall.tbl
index ebbdb3c42e9f..580b4e246aec 100644
--- a/tools/scripts/syscall.tbl
+++ b/tools/scripts/syscall.tbl
@@ -407,3 +407,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index f2957a3e36fe..bf9caa908f89 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -1780,7 +1780,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
 	if (rc)
 		return rc;
 
-	rc = devm_cxl_setup_fwctl(cxlmd);
+	rc = devm_cxl_setup_fwctl(&pdev->dev, cxlmd);
 	if (rc)
 		dev_dbg(dev, "No CXL FWCTL setup\n");
 
diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config
index cdd9782f9646..422e186cf3cf 100644
--- a/tools/testing/kunit/configs/all_tests.config
+++ b/tools/testing/kunit/configs/all_tests.config
@@ -20,6 +20,7 @@ CONFIG_VFAT_FS=y
 
 CONFIG_PCI=y
 CONFIG_USB4=y
+CONFIG_I2C=y
 
 CONFIG_NET=y
 CONFIG_MCTP=y
@@ -43,6 +44,8 @@ CONFIG_REGMAP_BUILD=y
 
 CONFIG_AUDIT=y
 
+CONFIG_PRIME_NUMBERS=y
+
 CONFIG_SECURITY=y
 CONFIG_SECURITY_APPARMOR=y
 CONFIG_SECURITY_LANDLOCK=y
@@ -51,3 +54,4 @@ CONFIG_SOUND=y
 CONFIG_SND=y
 CONFIG_SND_SOC=y
 CONFIG_SND_SOC_TOPOLOGY_BUILD=y
+CONFIG_SND_SOC_CS35L56_I2C=y
diff --git a/tools/testing/kunit/qemu_configs/sh.py b/tools/testing/kunit/qemu_configs/sh.py
index 78a474a5b95f..f00cb89fdef6 100644
--- a/tools/testing/kunit/qemu_configs/sh.py
+++ b/tools/testing/kunit/qemu_configs/sh.py
@@ -7,7 +7,9 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 CONFIG_MEMORY_START=0x0c000000
 CONFIG_SH_RTS7751R2D=y
 CONFIG_RTS7751R2D_PLUS=y
-CONFIG_SERIAL_SH_SCI=y''',
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_CMDLINE_EXTEND=y
+''',
 			   qemu_arch='sh4',
 			   kernel_path='arch/sh/boot/zImage',
 			   kernel_command_line='console=ttySC1',
diff --git a/tools/testing/memblock/internal.h b/tools/testing/memblock/internal.h
index 1cf82acb2a3e..0ab4b53bb4f3 100644
--- a/tools/testing/memblock/internal.h
+++ b/tools/testing/memblock/internal.h
@@ -24,4 +24,10 @@ static inline void accept_memory(phys_addr_t start, unsigned long size)
 {
 }
 
+static inline unsigned long free_reserved_area(void *start, void *end,
+					       int poison, const char *s)
+{
+	return 0;
+}
+
 #endif
diff --git a/tools/testing/memblock/linux/mutex.h b/tools/testing/memblock/linux/mutex.h
new file mode 100644
index 000000000000..ae3f497165d6
--- /dev/null
+++ b/tools/testing/memblock/linux/mutex.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MUTEX_H
+#define _MUTEX_H
+
+#define DEFINE_MUTEX(name) int name
+
+static inline void dummy_mutex_guard(int *name)
+{
+}
+
+#define guard(mutex)	\
+	dummy_##mutex##_guard
+
+#endif /* _MUTEX_H */
\ No newline at end of file
diff --git a/tools/testing/memblock/tests/basic_api.c b/tools/testing/memblock/tests/basic_api.c
index 67503089e6a0..01e836fba488 100644
--- a/tools/testing/memblock/tests/basic_api.c
+++ b/tools/testing/memblock/tests/basic_api.c
@@ -2434,6 +2434,107 @@ static int memblock_overlaps_region_checks(void)
 	return 0;
 }
 
+#ifdef CONFIG_NUMA
+static int memblock_set_node_check(void)
+{
+	unsigned long i, max_reserved;
+	struct memblock_region *rgn;
+	void *orig_region;
+
+	PREFIX_PUSH();
+
+	reset_memblock_regions();
+	memblock_allow_resize();
+
+	dummy_physical_memory_init();
+	memblock_add(dummy_physical_memory_base(), MEM_SIZE);
+	orig_region = memblock.reserved.regions;
+
+	/* Equally Split range to node 0 and 1*/
+	memblock_set_node(memblock_start_of_DRAM(),
+			memblock_phys_mem_size() / 2, &memblock.memory, 0);
+	memblock_set_node(memblock_start_of_DRAM() + memblock_phys_mem_size() / 2,
+			memblock_phys_mem_size() / 2, &memblock.memory, 1);
+
+	ASSERT_EQ(memblock.memory.cnt, 2);
+	rgn = &memblock.memory.regions[0];
+	ASSERT_EQ(rgn->base, memblock_start_of_DRAM());
+	ASSERT_EQ(rgn->size, memblock_phys_mem_size() / 2);
+	ASSERT_EQ(memblock_get_region_node(rgn), 0);
+	rgn = &memblock.memory.regions[1];
+	ASSERT_EQ(rgn->base, memblock_start_of_DRAM() + memblock_phys_mem_size() / 2);
+	ASSERT_EQ(rgn->size, memblock_phys_mem_size() / 2);
+	ASSERT_EQ(memblock_get_region_node(rgn), 1);
+
+	/* Reserve 126 regions with the last one across node boundary */
+	for (i = 0; i < 125; i++)
+		memblock_reserve(memblock_start_of_DRAM() + SZ_16 * i, SZ_8);
+
+	memblock_reserve(memblock_start_of_DRAM() + memblock_phys_mem_size() / 2 - SZ_8,
+			SZ_16);
+
+	/*
+	 * Commit 61167ad5fecd ("mm: pass nid to reserve_bootmem_region()")
+	 * do following process to set nid to each memblock.reserved region.
+	 * But it may miss some region if memblock_set_node() double the
+	 * array.
+	 *
+	 * By checking 'max', we make sure all region nid is set properly.
+	 */
+repeat:
+	max_reserved = memblock.reserved.max;
+	for_each_mem_region(rgn) {
+		int nid = memblock_get_region_node(rgn);
+
+		memblock_set_node(rgn->base, rgn->size, &memblock.reserved, nid);
+	}
+	if (max_reserved != memblock.reserved.max)
+		goto repeat;
+
+	/* Confirm each region has valid node set */
+	for_each_reserved_mem_region(rgn) {
+		ASSERT_TRUE(numa_valid_node(memblock_get_region_node(rgn)));
+		if (rgn == (memblock.reserved.regions + memblock.reserved.cnt - 1))
+			ASSERT_EQ(1, memblock_get_region_node(rgn));
+		else
+			ASSERT_EQ(0, memblock_get_region_node(rgn));
+	}
+
+	dummy_physical_memory_cleanup();
+
+	/*
+	 * The current reserved.regions is occupying a range of memory that
+	 * allocated from dummy_physical_memory_init(). After free the memory,
+	 * we must not use it. So restore the origin memory region to make sure
+	 * the tests can run as normal and not affected by the double array.
+	 */
+	memblock.reserved.regions = orig_region;
+	memblock.reserved.cnt = INIT_MEMBLOCK_RESERVED_REGIONS;
+
+	test_pass_pop();
+
+	return 0;
+}
+
+static int memblock_set_node_checks(void)
+{
+	prefix_reset();
+	prefix_push("memblock_set_node");
+	test_print("Running memblock_set_node tests...\n");
+
+	memblock_set_node_check();
+
+	prefix_pop();
+
+	return 0;
+}
+#else
+static int memblock_set_node_checks(void)
+{
+	return 0;
+}
+#endif
+
 int memblock_basic_checks(void)
 {
 	memblock_initialization_check();
@@ -2444,6 +2545,7 @@ int memblock_basic_checks(void)
 	memblock_bottom_up_checks();
 	memblock_trim_memory_checks();
 	memblock_overlaps_region_checks();
+	memblock_set_node_checks();
 
 	return 0;
 }
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index c77c8c8e3d9b..a62bd8e3a52e 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -66,11 +66,13 @@ TARGETS += mseal_system_mappings
 TARGETS += nci
 TARGETS += net
 TARGETS += net/af_unix
+TARGETS += net/can
 TARGETS += net/forwarding
 TARGETS += net/hsr
 TARGETS += net/mptcp
 TARGETS += net/netfilter
 TARGETS += net/openvswitch
+TARGETS += net/ovpn
 TARGETS += net/packetdrill
 TARGETS += net/rds
 TARGETS += net/tcp_ao
@@ -121,6 +123,7 @@ TARGETS += user_events
 TARGETS += vDSO
 TARGETS += mm
 TARGETS += x86
+TARGETS += x86/bugs
 TARGETS += zram
 #Please keep the TARGETS list alphabetically sorted
 # Run "make quicktest=1 run_tests" or
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index c378d5d07e02..3201a962b3dc 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -71,8 +71,10 @@ CONFIG_NET_IPGRE=y
 CONFIG_NET_IPGRE_DEMUX=y
 CONFIG_NET_IPIP=y
 CONFIG_NET_MPLS_GSO=y
+CONFIG_NET_SCH_BPF=y
 CONFIG_NET_SCH_FQ=y
 CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_SCH_HTB=y
 CONFIG_NET_SCHED=y
 CONFIG_NETDEVSIM=y
 CONFIG_NETFILTER=y
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c
new file mode 100644
index 000000000000..730357cd0c9a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/pkt_sched.h>
+#include <linux/rtnetlink.h>
+#include <test_progs.h>
+
+#include "network_helpers.h"
+#include "bpf_qdisc_fifo.skel.h"
+#include "bpf_qdisc_fq.skel.h"
+#include "bpf_qdisc_fail__incompl_ops.skel.h"
+
+#define LO_IFINDEX 1
+
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+
+static void do_test(char *qdisc)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
+			    .attach_point = BPF_TC_QDISC,
+			    .parent = TC_H_ROOT,
+			    .handle = 0x8000000,
+			    .qdisc = qdisc);
+	int srv_fd = -1, cli_fd = -1;
+	int err;
+
+	err = bpf_tc_hook_create(&hook);
+	if (!ASSERT_OK(err, "attach qdisc"))
+		return;
+
+	srv_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_OK_FD(srv_fd, "start server"))
+		goto done;
+
+	cli_fd = connect_to_fd(srv_fd, 0);
+	if (!ASSERT_OK_FD(cli_fd, "connect to client"))
+		goto done;
+
+	err = send_recv_data(srv_fd, cli_fd, total_bytes);
+	ASSERT_OK(err, "send_recv_data");
+
+done:
+	if (srv_fd != -1)
+		close(srv_fd);
+	if (cli_fd != -1)
+		close(cli_fd);
+
+	bpf_tc_hook_destroy(&hook);
+}
+
+static void test_fifo(void)
+{
+	struct bpf_qdisc_fifo *fifo_skel;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	do_test("bpf_fifo");
+out:
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_fq(void)
+{
+	struct bpf_qdisc_fq *fq_skel;
+
+	fq_skel = bpf_qdisc_fq__open_and_load();
+	if (!ASSERT_OK_PTR(fq_skel, "bpf_qdisc_fq__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fq__attach(fq_skel), "bpf_qdisc_fq__attach"))
+		goto out;
+
+	do_test("bpf_fq");
+out:
+	bpf_qdisc_fq__destroy(fq_skel);
+}
+
+static void test_qdisc_attach_to_mq(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook,
+			    .attach_point = BPF_TC_QDISC,
+			    .parent = TC_H_MAKE(1 << 16, 1),
+			    .handle = 0x11 << 16,
+			    .qdisc = "bpf_fifo");
+	struct bpf_qdisc_fifo *fifo_skel;
+	int err;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	SYS(out, "ip link add veth0 type veth peer veth1");
+	hook.ifindex = if_nametoindex("veth0");
+	SYS(out, "tc qdisc add dev veth0 root handle 1: mq");
+
+	err = bpf_tc_hook_create(&hook);
+	ASSERT_OK(err, "attach qdisc");
+
+	bpf_tc_hook_destroy(&hook);
+
+	SYS(out, "tc qdisc delete dev veth0 root mq");
+out:
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_qdisc_attach_to_non_root(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
+			    .attach_point = BPF_TC_QDISC,
+			    .parent = TC_H_MAKE(1 << 16, 1),
+			    .handle = 0x11 << 16,
+			    .qdisc = "bpf_fifo");
+	struct bpf_qdisc_fifo *fifo_skel;
+	int err;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	SYS(out, "tc qdisc add dev lo root handle 1: htb");
+	SYS(out_del_htb, "tc class add dev lo parent 1: classid 1:1 htb rate 75Kbit");
+
+	err = bpf_tc_hook_create(&hook);
+	if (!ASSERT_ERR(err, "attach qdisc"))
+		bpf_tc_hook_destroy(&hook);
+
+out_del_htb:
+	SYS(out, "tc qdisc delete dev lo root htb");
+out:
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_incompl_ops(void)
+{
+	struct bpf_qdisc_fail__incompl_ops *skel;
+	struct bpf_link *link;
+
+	skel = bpf_qdisc_fail__incompl_ops__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.test);
+	if (!ASSERT_ERR_PTR(link, "bpf_map__attach_struct_ops"))
+		bpf_link__destroy(link);
+
+	bpf_qdisc_fail__incompl_ops__destroy(skel);
+}
+
+static int get_default_qdisc(char *qdisc_name)
+{
+	FILE *f;
+	int num;
+
+	f = fopen("/proc/sys/net/core/default_qdisc", "r");
+	if (!f)
+		return -errno;
+
+	num = fscanf(f, "%s", qdisc_name);
+	fclose(f);
+
+	return num == 1 ? 0 : -EFAULT;
+}
+
+static void test_default_qdisc_attach_to_mq(void)
+{
+	char default_qdisc[IFNAMSIZ] = {};
+	struct bpf_qdisc_fifo *fifo_skel;
+	struct netns_obj *netns = NULL;
+	int err;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	err = get_default_qdisc(default_qdisc);
+	if (!ASSERT_OK(err, "read sysctl net.core.default_qdisc"))
+		goto out;
+
+	err = write_sysctl("/proc/sys/net/core/default_qdisc", "bpf_fifo");
+	if (!ASSERT_OK(err, "write sysctl net.core.default_qdisc"))
+		goto out;
+
+	netns = netns_new("bpf_qdisc_ns", true);
+	if (!ASSERT_OK_PTR(netns, "netns_new"))
+		goto out;
+
+	SYS(out, "ip link add veth0 type veth peer veth1");
+	SYS(out, "tc qdisc add dev veth0 root handle 1: mq");
+
+	ASSERT_EQ(fifo_skel->bss->init_called, true, "init_called");
+
+	SYS(out, "tc qdisc delete dev veth0 root mq");
+out:
+	netns_free(netns);
+	if (default_qdisc[0])
+		write_sysctl("/proc/sys/net/core/default_qdisc", default_qdisc);
+
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+void test_ns_bpf_qdisc(void)
+{
+	if (test__start_subtest("fifo"))
+		test_fifo();
+	if (test__start_subtest("fq"))
+		test_fq();
+	if (test__start_subtest("attach to mq"))
+		test_qdisc_attach_to_mq();
+	if (test__start_subtest("attach to non root"))
+		test_qdisc_attach_to_non_root();
+	if (test__start_subtest("incompl_ops"))
+		test_incompl_ops();
+}
+
+void serial_test_bpf_qdisc_default(void)
+{
+	test_default_qdisc_attach_to_mq();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c
index 09f6487f58b9..5fea3209566e 100644
--- a/tools/testing/selftests/bpf/prog_tests/for_each.c
+++ b/tools/testing/selftests/bpf/prog_tests/for_each.c
@@ -6,6 +6,7 @@
 #include "for_each_array_map_elem.skel.h"
 #include "for_each_map_elem_write_key.skel.h"
 #include "for_each_multi_maps.skel.h"
+#include "for_each_hash_modify.skel.h"
 
 static unsigned int duration;
 
@@ -203,6 +204,40 @@ out:
 	for_each_multi_maps__destroy(skel);
 }
 
+static void test_hash_modify(void)
+{
+	struct for_each_hash_modify *skel;
+	int max_entries, i, err;
+	__u64 key, val;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1
+	);
+
+	skel = for_each_hash_modify__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "for_each_hash_modify__open_and_load"))
+		return;
+
+	max_entries = bpf_map__max_entries(skel->maps.hashmap);
+	for (i = 0; i < max_entries; i++) {
+		key = i;
+		val = i;
+		err = bpf_map__update_elem(skel->maps.hashmap, &key, sizeof(key),
+					   &val, sizeof(val), BPF_ANY);
+		if (!ASSERT_OK(err, "map_update"))
+			goto out;
+	}
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+	ASSERT_OK(topts.retval, "retval");
+
+out:
+	for_each_hash_modify__destroy(skel);
+}
+
 void test_for_each(void)
 {
 	if (test__start_subtest("hash_map"))
@@ -213,4 +248,6 @@ void test_for_each(void)
 		test_write_map_key();
 	if (test__start_subtest("multi_maps"))
 		test_multi_maps();
+	if (test__start_subtest("hash_modify"))
+		test_hash_modify();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
index 115287ba441b..0703e987df89 100644
--- a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
@@ -25,8 +25,11 @@ static void *spin_lock_thread(void *arg)
 
 	while (!READ_ONCE(skip)) {
 		err = bpf_prog_test_run_opts(prog_fd, &topts);
-		ASSERT_OK(err, "test_run");
-		ASSERT_OK(topts.retval, "test_run retval");
+		if (err || topts.retval) {
+			ASSERT_OK(err, "test_run");
+			ASSERT_OK(topts.retval, "test_run retval");
+			break;
+		}
 	}
 	pthread_exit(arg);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
index d56e18b25528..a4517bee34d5 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
@@ -7,14 +7,433 @@
 
 #define TEST_NS "sock_iter_batch_netns"
 
+static const int init_batch_size = 16;
 static const int nr_soreuse = 4;
 
+struct iter_out {
+	int idx;
+	__u64 cookie;
+} __packed;
+
+struct sock_count {
+	__u64 cookie;
+	int count;
+};
+
+static int insert(__u64 cookie, struct sock_count counts[], int counts_len)
+{
+	int insert = -1;
+	int i = 0;
+
+	for (; i < counts_len; i++) {
+		if (!counts[i].cookie) {
+			insert = i;
+		} else if (counts[i].cookie == cookie) {
+			insert = i;
+			break;
+		}
+	}
+	if (insert < 0)
+		return insert;
+
+	counts[insert].cookie = cookie;
+	counts[insert].count++;
+
+	return counts[insert].count;
+}
+
+static int read_n(int iter_fd, int n, struct sock_count counts[],
+		  int counts_len)
+{
+	struct iter_out out;
+	int nread = 1;
+	int i = 0;
+
+	for (; nread > 0 && (n < 0 || i < n); i++) {
+		nread = read(iter_fd, &out, sizeof(out));
+		if (!nread || !ASSERT_EQ(nread, sizeof(out), "nread"))
+			break;
+		ASSERT_GE(insert(out.cookie, counts, counts_len), 0, "insert");
+	}
+
+	ASSERT_TRUE(n < 0 || i == n, "n < 0 || i == n");
+
+	return i;
+}
+
+static __u64 socket_cookie(int fd)
+{
+	__u64 cookie;
+	socklen_t cookie_len = sizeof(cookie);
+
+	if (!ASSERT_OK(getsockopt(fd, SOL_SOCKET, SO_COOKIE, &cookie,
+				  &cookie_len), "getsockopt(SO_COOKIE)"))
+		return 0;
+	return cookie;
+}
+
+static bool was_seen(int fd, struct sock_count counts[], int counts_len)
+{
+	__u64 cookie = socket_cookie(fd);
+	int i = 0;
+
+	for (; cookie && i < counts_len; i++)
+		if (cookie == counts[i].cookie)
+			return true;
+
+	return false;
+}
+
+static int get_seen_socket(int *fds, struct sock_count counts[], int n)
+{
+	int i = 0;
+
+	for (; i < n; i++)
+		if (was_seen(fds[i], counts, n))
+			return i;
+	return -1;
+}
+
+static int get_nth_socket(int *fds, int fds_len, struct bpf_link *link, int n)
+{
+	int i, nread, iter_fd;
+	int nth_sock_idx = -1;
+	struct iter_out out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create"))
+		return -1;
+
+	for (; n >= 0; n--) {
+		nread = read(iter_fd, &out, sizeof(out));
+		if (!nread || !ASSERT_GE(nread, 1, "nread"))
+			goto done;
+	}
+
+	for (i = 0; i < fds_len && nth_sock_idx < 0; i++)
+		if (fds[i] >= 0 && socket_cookie(fds[i]) == out.cookie)
+			nth_sock_idx = i;
+done:
+	close(iter_fd);
+	return nth_sock_idx;
+}
+
+static int get_seen_count(int fd, struct sock_count counts[], int n)
+{
+	__u64 cookie = socket_cookie(fd);
+	int count = 0;
+	int i = 0;
+
+	for (; cookie && !count && i < n; i++)
+		if (cookie == counts[i].cookie)
+			count = counts[i].count;
+
+	return count;
+}
+
+static void check_n_were_seen_once(int *fds, int fds_len, int n,
+				   struct sock_count counts[], int counts_len)
+{
+	int seen_once = 0;
+	int seen_cnt;
+	int i = 0;
+
+	for (; i < fds_len; i++) {
+		/* Skip any sockets that were closed or that weren't seen
+		 * exactly once.
+		 */
+		if (fds[i] < 0)
+			continue;
+		seen_cnt = get_seen_count(fds[i], counts, counts_len);
+		if (seen_cnt && ASSERT_EQ(seen_cnt, 1, "seen_cnt"))
+			seen_once++;
+	}
+
+	ASSERT_EQ(seen_once, n, "seen_once");
+}
+
+static void remove_seen(int family, int sock_type, const char *addr, __u16 port,
+			int *socks, int socks_len, struct sock_count *counts,
+			int counts_len, struct bpf_link *link, int iter_fd)
+{
+	int close_idx;
+
+	/* Iterate through the first socks_len - 1 sockets. */
+	read_n(iter_fd, socks_len - 1, counts, counts_len);
+
+	/* Make sure we saw socks_len - 1 sockets exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+
+	/* Close a socket we've already seen to remove it from the bucket. */
+	close_idx = get_seen_socket(socks, counts, counts_len);
+	if (!ASSERT_GE(close_idx, 0, "close_idx"))
+		return;
+	close(socks[close_idx]);
+	socks[close_idx] = -1;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure the last socket wasn't skipped and that there were no
+	 * repeats.
+	 */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+}
+
+static void remove_unseen(int family, int sock_type, const char *addr,
+			  __u16 port, int *socks, int socks_len,
+			  struct sock_count *counts, int counts_len,
+			  struct bpf_link *link, int iter_fd)
+{
+	int close_idx;
+
+	/* Iterate through the first socket. */
+	read_n(iter_fd, 1, counts, counts_len);
+
+	/* Make sure we saw a socket from fds. */
+	check_n_were_seen_once(socks, socks_len, 1, counts, counts_len);
+
+	/* Close what would be the next socket in the bucket to exercise the
+	 * condition where we need to skip past the first cookie we remembered.
+	 */
+	close_idx = get_nth_socket(socks, socks_len, link, 1);
+	if (!ASSERT_GE(close_idx, 0, "close_idx"))
+		return;
+	close(socks[close_idx]);
+	socks[close_idx] = -1;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure the remaining sockets were seen exactly once and that we
+	 * didn't repeat the socket that was already seen.
+	 */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+}
+
+static void remove_all(int family, int sock_type, const char *addr,
+		       __u16 port, int *socks, int socks_len,
+		       struct sock_count *counts, int counts_len,
+		       struct bpf_link *link, int iter_fd)
+{
+	int close_idx, i;
+
+	/* Iterate through the first socket. */
+	read_n(iter_fd, 1, counts, counts_len);
+
+	/* Make sure we saw a socket from fds. */
+	check_n_were_seen_once(socks, socks_len, 1, counts, counts_len);
+
+	/* Close all remaining sockets to exhaust the list of saved cookies and
+	 * exit without putting any sockets into the batch on the next read.
+	 */
+	for (i = 0; i < socks_len - 1; i++) {
+		close_idx = get_nth_socket(socks, socks_len, link, 1);
+		if (!ASSERT_GE(close_idx, 0, "close_idx"))
+			return;
+		close(socks[close_idx]);
+		socks[close_idx] = -1;
+	}
+
+	/* Make sure there are no more sockets returned */
+	ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n");
+}
+
+static void add_some(int family, int sock_type, const char *addr, __u16 port,
+		     int *socks, int socks_len, struct sock_count *counts,
+		     int counts_len, struct bpf_link *link, int iter_fd)
+{
+	int *new_socks = NULL;
+
+	/* Iterate through the first socks_len - 1 sockets. */
+	read_n(iter_fd, socks_len - 1, counts, counts_len);
+
+	/* Make sure we saw socks_len - 1 sockets exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+
+	/* Double the number of sockets in the bucket. */
+	new_socks = start_reuseport_server(family, sock_type, addr, port, 0,
+					   socks_len);
+	if (!ASSERT_OK_PTR(new_socks, "start_reuseport_server"))
+		goto done;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure each of the original sockets was seen exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len, counts,
+			       counts_len);
+done:
+	free_fds(new_socks, socks_len);
+}
+
+static void force_realloc(int family, int sock_type, const char *addr,
+			  __u16 port, int *socks, int socks_len,
+			  struct sock_count *counts, int counts_len,
+			  struct bpf_link *link, int iter_fd)
+{
+	int *new_socks = NULL;
+
+	/* Iterate through the first socket just to initialize the batch. */
+	read_n(iter_fd, 1, counts, counts_len);
+
+	/* Double the number of sockets in the bucket to force a realloc on the
+	 * next read.
+	 */
+	new_socks = start_reuseport_server(family, sock_type, addr, port, 0,
+					   socks_len);
+	if (!ASSERT_OK_PTR(new_socks, "start_reuseport_server"))
+		goto done;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure each socket from the first set was seen exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len, counts,
+			       counts_len);
+done:
+	free_fds(new_socks, socks_len);
+}
+
+struct test_case {
+	void (*test)(int family, int sock_type, const char *addr, __u16 port,
+		     int *socks, int socks_len, struct sock_count *counts,
+		     int counts_len, struct bpf_link *link, int iter_fd);
+	const char *description;
+	int init_socks;
+	int max_socks;
+	int sock_type;
+	int family;
+};
+
+static struct test_case resume_tests[] = {
+	{
+		.description = "udp: resume after removing a seen socket",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		.family = AF_INET6,
+		.test = remove_seen,
+	},
+	{
+		.description = "udp: resume after removing one unseen socket",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		.family = AF_INET6,
+		.test = remove_unseen,
+	},
+	{
+		.description = "udp: resume after removing all unseen sockets",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		.family = AF_INET6,
+		.test = remove_all,
+	},
+	{
+		.description = "udp: resume after adding a few sockets",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		/* Use AF_INET so that new sockets are added to the head of the
+		 * bucket's list.
+		 */
+		.family = AF_INET,
+		.test = add_some,
+	},
+	{
+		.description = "udp: force a realloc to occur",
+		.init_socks = init_batch_size,
+		.max_socks = init_batch_size * 2,
+		.sock_type = SOCK_DGRAM,
+		/* Use AF_INET6 so that new sockets are added to the tail of the
+		 * bucket's list, needing to be added to the next batch to force
+		 * a realloc.
+		 */
+		.family = AF_INET6,
+		.test = force_realloc,
+	},
+};
+
+static void do_resume_test(struct test_case *tc)
+{
+	struct sock_iter_batch *skel = NULL;
+	static const __u16 port = 10001;
+	struct bpf_link *link = NULL;
+	struct sock_count *counts;
+	int err, iter_fd = -1;
+	const char *addr;
+	int *fds = NULL;
+	int local_port;
+
+	counts = calloc(tc->max_socks, sizeof(*counts));
+	if (!ASSERT_OK_PTR(counts, "counts"))
+		goto done;
+	skel = sock_iter_batch__open();
+	if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open"))
+		goto done;
+
+	/* Prepare a bucket of sockets in the kernel hashtable */
+	addr = tc->family == AF_INET6 ? "::1" : "127.0.0.1";
+	fds = start_reuseport_server(tc->family, tc->sock_type, addr, port, 0,
+				     tc->init_socks);
+	if (!ASSERT_OK_PTR(fds, "start_reuseport_server"))
+		goto done;
+	local_port = get_socket_local_port(*fds);
+	if (!ASSERT_GE(local_port, 0, "get_socket_local_port"))
+		goto done;
+	skel->rodata->ports[0] = ntohs(local_port);
+	skel->rodata->sf = tc->family;
+
+	err = sock_iter_batch__load(skel);
+	if (!ASSERT_OK(err, "sock_iter_batch__load"))
+		goto done;
+
+	link = bpf_program__attach_iter(tc->sock_type == SOCK_STREAM ?
+					skel->progs.iter_tcp_soreuse :
+					skel->progs.iter_udp_soreuse,
+					NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+		goto done;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create"))
+		goto done;
+
+	tc->test(tc->family, tc->sock_type, addr, port, fds, tc->init_socks,
+		 counts, tc->max_socks, link, iter_fd);
+done:
+	free(counts);
+	free_fds(fds, tc->init_socks);
+	if (iter_fd >= 0)
+		close(iter_fd);
+	bpf_link__destroy(link);
+	sock_iter_batch__destroy(skel);
+}
+
+static void do_resume_tests(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(resume_tests); i++) {
+		if (test__start_subtest(resume_tests[i].description)) {
+			do_resume_test(&resume_tests[i]);
+		}
+	}
+}
+
 static void do_test(int sock_type, bool onebyone)
 {
 	int err, i, nread, to_read, total_read, iter_fd = -1;
-	int first_idx, second_idx, indices[nr_soreuse];
+	struct iter_out outputs[nr_soreuse];
 	struct bpf_link *link = NULL;
 	struct sock_iter_batch *skel;
+	int first_idx, second_idx;
 	int *fds[2] = {};
 
 	skel = sock_iter_batch__open();
@@ -34,6 +453,7 @@ static void do_test(int sock_type, bool onebyone)
 			goto done;
 		skel->rodata->ports[i] = ntohs(local_port);
 	}
+	skel->rodata->sf = AF_INET6;
 
 	err = sock_iter_batch__load(skel);
 	if (!ASSERT_OK(err, "sock_iter_batch__load"))
@@ -55,38 +475,38 @@ static void do_test(int sock_type, bool onebyone)
 	 * from a bucket and leave one socket out from
 	 * that bucket on purpose.
 	 */
-	to_read = (nr_soreuse - 1) * sizeof(*indices);
+	to_read = (nr_soreuse - 1) * sizeof(*outputs);
 	total_read = 0;
 	first_idx = -1;
 	do {
-		nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
-		if (nread <= 0 || nread % sizeof(*indices))
+		nread = read(iter_fd, outputs, onebyone ? sizeof(*outputs) : to_read);
+		if (nread <= 0 || nread % sizeof(*outputs))
 			break;
 		total_read += nread;
 
 		if (first_idx == -1)
-			first_idx = indices[0];
-		for (i = 0; i < nread / sizeof(*indices); i++)
-			ASSERT_EQ(indices[i], first_idx, "first_idx");
+			first_idx = outputs[0].idx;
+		for (i = 0; i < nread / sizeof(*outputs); i++)
+			ASSERT_EQ(outputs[i].idx, first_idx, "first_idx");
 	} while (total_read < to_read);
-	ASSERT_EQ(nread, onebyone ? sizeof(*indices) : to_read, "nread");
+	ASSERT_EQ(nread, onebyone ? sizeof(*outputs) : to_read, "nread");
 	ASSERT_EQ(total_read, to_read, "total_read");
 
 	free_fds(fds[first_idx], nr_soreuse);
 	fds[first_idx] = NULL;
 
 	/* Read the "whole" second bucket */
-	to_read = nr_soreuse * sizeof(*indices);
+	to_read = nr_soreuse * sizeof(*outputs);
 	total_read = 0;
 	second_idx = !first_idx;
 	do {
-		nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
-		if (nread <= 0 || nread % sizeof(*indices))
+		nread = read(iter_fd, outputs, onebyone ? sizeof(*outputs) : to_read);
+		if (nread <= 0 || nread % sizeof(*outputs))
 			break;
 		total_read += nread;
 
-		for (i = 0; i < nread / sizeof(*indices); i++)
-			ASSERT_EQ(indices[i], second_idx, "second_idx");
+		for (i = 0; i < nread / sizeof(*outputs); i++)
+			ASSERT_EQ(outputs[i].idx, second_idx, "second_idx");
 	} while (total_read <= to_read);
 	ASSERT_EQ(nread, 0, "nread");
 	/* Both so_reuseport ports should be in different buckets, so
@@ -128,6 +548,7 @@ void test_sock_iter_batch(void)
 		do_test(SOCK_DGRAM, true);
 		do_test(SOCK_DGRAM, false);
 	}
+	do_resume_tests();
 	close_netns(nstoken);
 
 done:
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
index 2d0796314862..0a99fd404f6d 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
@@ -68,7 +68,6 @@ static void test_sockmap_ktls_disconnect_after_delete(int family, int map)
 		goto close_cli;
 
 	err = disconnect(cli);
-	ASSERT_OK(err, "disconnect");
 
 close_cli:
 	close(cli);
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 13a2e22f5465..863df7c0fdd0 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -221,7 +221,7 @@
 #define CAN_USE_GOTOL
 #endif
 
-#if _clang_major__ >= 18
+#if __clang_major__ >= 18
 #define CAN_USE_BPF_ST
 #endif
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h b/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h
new file mode 100644
index 000000000000..3754f581b328
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _BPF_QDISC_COMMON_H
+#define _BPF_QDISC_COMMON_H
+
+#define NET_XMIT_SUCCESS        0x00
+#define NET_XMIT_DROP           0x01    /* skb dropped                  */
+#define NET_XMIT_CN             0x02    /* congestion notification      */
+
+#define TC_PRIO_CONTROL  7
+#define TC_PRIO_MAX      15
+
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+
+struct bpf_sk_buff_ptr;
+
+static struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb)
+{
+	return (struct qdisc_skb_cb *)skb->cb;
+}
+
+static inline unsigned int qdisc_pkt_len(const struct sk_buff *skb)
+{
+	return qdisc_skb_cb(skb)->pkt_len;
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c
new file mode 100644
index 000000000000..f188062ed730
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "bpf_experimental.h"
+#include "bpf_qdisc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops")
+int BPF_PROG(bpf_qdisc_test_enqueue, struct sk_buff *skb, struct Qdisc *sch,
+	     struct bpf_sk_buff_ptr *to_free)
+{
+	bpf_qdisc_skb_drop(skb, to_free);
+	return NET_XMIT_DROP;
+}
+
+SEC("struct_ops")
+struct sk_buff *BPF_PROG(bpf_qdisc_test_dequeue, struct Qdisc *sch)
+{
+	return NULL;
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_qdisc_test_reset, struct Qdisc *sch)
+{
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_qdisc_test_destroy, struct Qdisc *sch)
+{
+}
+
+SEC(".struct_ops")
+struct Qdisc_ops test = {
+	.enqueue   = (void *)bpf_qdisc_test_enqueue,
+	.dequeue   = (void *)bpf_qdisc_test_dequeue,
+	.reset     = (void *)bpf_qdisc_test_reset,
+	.destroy   = (void *)bpf_qdisc_test_destroy,
+	.id        = "bpf_qdisc_test",
+};
+
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c
new file mode 100644
index 000000000000..1de2be3e370b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "bpf_experimental.h"
+#include "bpf_qdisc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct skb_node {
+	struct sk_buff __kptr * skb;
+	struct bpf_list_node node;
+};
+
+private(A) struct bpf_spin_lock q_fifo_lock;
+private(A) struct bpf_list_head q_fifo __contains(skb_node, node);
+
+bool init_called;
+
+SEC("struct_ops/bpf_fifo_enqueue")
+int BPF_PROG(bpf_fifo_enqueue, struct sk_buff *skb, struct Qdisc *sch,
+	     struct bpf_sk_buff_ptr *to_free)
+{
+	struct skb_node *skbn;
+	u32 pkt_len;
+
+	if (sch->q.qlen == sch->limit)
+		goto drop;
+
+	skbn = bpf_obj_new(typeof(*skbn));
+	if (!skbn)
+		goto drop;
+
+	pkt_len = qdisc_pkt_len(skb);
+
+	sch->q.qlen++;
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	if (skb)
+		bpf_qdisc_skb_drop(skb, to_free);
+
+	bpf_spin_lock(&q_fifo_lock);
+	bpf_list_push_back(&q_fifo, &skbn->node);
+	bpf_spin_unlock(&q_fifo_lock);
+
+	sch->qstats.backlog += pkt_len;
+	return NET_XMIT_SUCCESS;
+drop:
+	bpf_qdisc_skb_drop(skb, to_free);
+	return NET_XMIT_DROP;
+}
+
+SEC("struct_ops/bpf_fifo_dequeue")
+struct sk_buff *BPF_PROG(bpf_fifo_dequeue, struct Qdisc *sch)
+{
+	struct bpf_list_node *node;
+	struct sk_buff *skb = NULL;
+	struct skb_node *skbn;
+
+	bpf_spin_lock(&q_fifo_lock);
+	node = bpf_list_pop_front(&q_fifo);
+	bpf_spin_unlock(&q_fifo_lock);
+	if (!node)
+		return NULL;
+
+	skbn = container_of(node, struct skb_node, node);
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	bpf_obj_drop(skbn);
+	if (!skb)
+		return NULL;
+
+	sch->qstats.backlog -= qdisc_pkt_len(skb);
+	bpf_qdisc_bstats_update(sch, skb);
+	sch->q.qlen--;
+
+	return skb;
+}
+
+SEC("struct_ops/bpf_fifo_init")
+int BPF_PROG(bpf_fifo_init, struct Qdisc *sch, struct nlattr *opt,
+	     struct netlink_ext_ack *extack)
+{
+	sch->limit = 1000;
+	init_called = true;
+	return 0;
+}
+
+SEC("struct_ops/bpf_fifo_reset")
+void BPF_PROG(bpf_fifo_reset, struct Qdisc *sch)
+{
+	struct bpf_list_node *node;
+	struct skb_node *skbn;
+	int i;
+
+	bpf_for(i, 0, sch->q.qlen) {
+		struct sk_buff *skb = NULL;
+
+		bpf_spin_lock(&q_fifo_lock);
+		node = bpf_list_pop_front(&q_fifo);
+		bpf_spin_unlock(&q_fifo_lock);
+
+		if (!node)
+			break;
+
+		skbn = container_of(node, struct skb_node, node);
+		skb = bpf_kptr_xchg(&skbn->skb, skb);
+		if (skb)
+			bpf_kfree_skb(skb);
+		bpf_obj_drop(skbn);
+	}
+	sch->q.qlen = 0;
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_fifo_destroy, struct Qdisc *sch)
+{
+}
+
+SEC(".struct_ops")
+struct Qdisc_ops fifo = {
+	.enqueue   = (void *)bpf_fifo_enqueue,
+	.dequeue   = (void *)bpf_fifo_dequeue,
+	.init      = (void *)bpf_fifo_init,
+	.reset     = (void *)bpf_fifo_reset,
+	.destroy   = (void *)bpf_fifo_destroy,
+	.id        = "bpf_fifo",
+};
+
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c
new file mode 100644
index 000000000000..1a3233a275c7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c
@@ -0,0 +1,756 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* bpf_fq is intended for testing the bpf qdisc infrastructure and not a direct
+ * copy of sch_fq. bpf_fq implements the scheduling algorithm of sch_fq before
+ * 29f834aa326e ("net_sched: sch_fq: add 3 bands and WRR scheduling") was
+ * introduced. It gives each flow a fair chance to transmit packets in a
+ * round-robin fashion. Note that for flow pacing, bpf_fq currently only
+ * respects skb->tstamp but not skb->sk->sk_pacing_rate. In addition, if there
+ * are multiple bpf_fq instances, they will have a shared view of flows and
+ * configuration since some key data structure such as fq_prio_flows,
+ * fq_nonprio_flows, and fq_bpf_data are global.
+ *
+ * To use bpf_fq alone without running selftests, use the following commands.
+ *
+ * 1. Register bpf_fq to the kernel
+ *     bpftool struct_ops register bpf_qdisc_fq.bpf.o /sys/fs/bpf
+ * 2. Add bpf_fq to an interface
+ *     tc qdisc add dev <interface name> root handle <handle> bpf_fq
+ * 3. Delete bpf_fq attached to the interface
+ *     tc qdisc delete dev <interface name> root
+ * 4. Unregister bpf_fq
+ *     bpftool struct_ops unregister name fq
+ *
+ * The qdisc name, bpf_fq, used in tc commands is defined by Qdisc_ops.id.
+ * The struct_ops_map_name, fq, used in the bpftool command is the name of the
+ * Qdisc_ops.
+ *
+ * SEC(".struct_ops")
+ * struct Qdisc_ops fq = {
+ *         ...
+ *         .id        = "bpf_fq",
+ * };
+ */
+
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_experimental.h"
+#include "bpf_qdisc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define NSEC_PER_USEC 1000L
+#define NSEC_PER_SEC 1000000000L
+
+#define NUM_QUEUE (1 << 20)
+
+struct fq_bpf_data {
+	u32 quantum;
+	u32 initial_quantum;
+	u32 flow_refill_delay;
+	u32 flow_plimit;
+	u64 horizon;
+	u32 orphan_mask;
+	u32 timer_slack;
+	u64 time_next_delayed_flow;
+	u64 unthrottle_latency_ns;
+	u8 horizon_drop;
+	u32 new_flow_cnt;
+	u32 old_flow_cnt;
+	u64 ktime_cache;
+};
+
+enum {
+	CLS_RET_PRIO	= 0,
+	CLS_RET_NONPRIO = 1,
+	CLS_RET_ERR	= 2,
+};
+
+struct skb_node {
+	u64 tstamp;
+	struct sk_buff __kptr * skb;
+	struct bpf_rb_node node;
+};
+
+struct fq_flow_node {
+	int credit;
+	u32 qlen;
+	u64 age;
+	u64 time_next_packet;
+	struct bpf_list_node list_node;
+	struct bpf_rb_node rb_node;
+	struct bpf_rb_root queue __contains(skb_node, node);
+	struct bpf_spin_lock lock;
+	struct bpf_refcount refcount;
+};
+
+struct dequeue_nonprio_ctx {
+	bool stop_iter;
+	u64 expire;
+	u64 now;
+};
+
+struct remove_flows_ctx {
+	bool gc_only;
+	u32 reset_cnt;
+	u32 reset_max;
+};
+
+struct unset_throttled_flows_ctx {
+	bool unset_all;
+	u64 now;
+};
+
+struct fq_stashed_flow {
+	struct fq_flow_node __kptr * flow;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u64);
+	__type(value, struct fq_stashed_flow);
+	__uint(max_entries, NUM_QUEUE);
+} fq_nonprio_flows SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u64);
+	__type(value, struct fq_stashed_flow);
+	__uint(max_entries, 1);
+} fq_prio_flows SEC(".maps");
+
+private(A) struct bpf_spin_lock fq_delayed_lock;
+private(A) struct bpf_rb_root fq_delayed __contains(fq_flow_node, rb_node);
+
+private(B) struct bpf_spin_lock fq_new_flows_lock;
+private(B) struct bpf_list_head fq_new_flows __contains(fq_flow_node, list_node);
+
+private(C) struct bpf_spin_lock fq_old_flows_lock;
+private(C) struct bpf_list_head fq_old_flows __contains(fq_flow_node, list_node);
+
+private(D) struct fq_bpf_data q;
+
+/* Wrapper for bpf_kptr_xchg that expects NULL dst */
+static void bpf_kptr_xchg_back(void *map_val, void *ptr)
+{
+	void *ret;
+
+	ret = bpf_kptr_xchg(map_val, ptr);
+	if (ret)
+		bpf_obj_drop(ret);
+}
+
+static bool skbn_tstamp_less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct skb_node *skbn_a;
+	struct skb_node *skbn_b;
+
+	skbn_a = container_of(a, struct skb_node, node);
+	skbn_b = container_of(b, struct skb_node, node);
+
+	return skbn_a->tstamp < skbn_b->tstamp;
+}
+
+static bool fn_time_next_packet_less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct fq_flow_node *flow_a;
+	struct fq_flow_node *flow_b;
+
+	flow_a = container_of(a, struct fq_flow_node, rb_node);
+	flow_b = container_of(b, struct fq_flow_node, rb_node);
+
+	return flow_a->time_next_packet < flow_b->time_next_packet;
+}
+
+static void
+fq_flows_add_head(struct bpf_list_head *head, struct bpf_spin_lock *lock,
+		  struct fq_flow_node *flow, u32 *flow_cnt)
+{
+	bpf_spin_lock(lock);
+	bpf_list_push_front(head, &flow->list_node);
+	bpf_spin_unlock(lock);
+	*flow_cnt += 1;
+}
+
+static void
+fq_flows_add_tail(struct bpf_list_head *head, struct bpf_spin_lock *lock,
+		  struct fq_flow_node *flow, u32 *flow_cnt)
+{
+	bpf_spin_lock(lock);
+	bpf_list_push_back(head, &flow->list_node);
+	bpf_spin_unlock(lock);
+	*flow_cnt += 1;
+}
+
+static void
+fq_flows_remove_front(struct bpf_list_head *head, struct bpf_spin_lock *lock,
+		      struct bpf_list_node **node, u32 *flow_cnt)
+{
+	bpf_spin_lock(lock);
+	*node = bpf_list_pop_front(head);
+	bpf_spin_unlock(lock);
+	*flow_cnt -= 1;
+}
+
+static bool
+fq_flows_is_empty(struct bpf_list_head *head, struct bpf_spin_lock *lock)
+{
+	struct bpf_list_node *node;
+
+	bpf_spin_lock(lock);
+	node = bpf_list_pop_front(head);
+	if (node) {
+		bpf_list_push_front(head, node);
+		bpf_spin_unlock(lock);
+		return false;
+	}
+	bpf_spin_unlock(lock);
+
+	return true;
+}
+
+/* flow->age is used to denote the state of the flow (not-detached, detached, throttled)
+ * as well as the timestamp when the flow is detached.
+ *
+ * 0: not-detached
+ * 1 - (~0ULL-1): detached
+ * ~0ULL: throttled
+ */
+static void fq_flow_set_detached(struct fq_flow_node *flow)
+{
+	flow->age = bpf_jiffies64();
+}
+
+static bool fq_flow_is_detached(struct fq_flow_node *flow)
+{
+	return flow->age != 0 && flow->age != ~0ULL;
+}
+
+static bool sk_listener(struct sock *sk)
+{
+	return (1 << sk->__sk_common.skc_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV);
+}
+
+static void fq_gc(void);
+
+static int fq_new_flow(void *flow_map, struct fq_stashed_flow **sflow, u64 hash)
+{
+	struct fq_stashed_flow tmp = {};
+	struct fq_flow_node *flow;
+	int ret;
+
+	flow = bpf_obj_new(typeof(*flow));
+	if (!flow)
+		return -ENOMEM;
+
+	flow->credit = q.initial_quantum,
+	flow->qlen = 0,
+	flow->age = 1,
+	flow->time_next_packet = 0,
+
+	ret = bpf_map_update_elem(flow_map, &hash, &tmp, 0);
+	if (ret == -ENOMEM || ret == -E2BIG) {
+		fq_gc();
+		bpf_map_update_elem(&fq_nonprio_flows, &hash, &tmp, 0);
+	}
+
+	*sflow = bpf_map_lookup_elem(flow_map, &hash);
+	if (!*sflow) {
+		bpf_obj_drop(flow);
+		return -ENOMEM;
+	}
+
+	bpf_kptr_xchg_back(&(*sflow)->flow, flow);
+	return 0;
+}
+
+static int
+fq_classify(struct sk_buff *skb, struct fq_stashed_flow **sflow)
+{
+	struct sock *sk = skb->sk;
+	int ret = CLS_RET_NONPRIO;
+	u64 hash = 0;
+
+	if ((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL) {
+		*sflow = bpf_map_lookup_elem(&fq_prio_flows, &hash);
+		ret = CLS_RET_PRIO;
+	} else {
+		if (!sk || sk_listener(sk)) {
+			hash = bpf_skb_get_hash(skb) & q.orphan_mask;
+			/* Avoid collision with an existing flow hash, which
+			 * only uses the lower 32 bits of hash, by setting the
+			 * upper half of hash to 1.
+			 */
+			hash |= (1ULL << 32);
+		} else if (sk->__sk_common.skc_state == TCP_CLOSE) {
+			hash = bpf_skb_get_hash(skb) & q.orphan_mask;
+			hash |= (1ULL << 32);
+		} else {
+			hash = sk->__sk_common.skc_hash;
+		}
+		*sflow = bpf_map_lookup_elem(&fq_nonprio_flows, &hash);
+	}
+
+	if (!*sflow)
+		ret = fq_new_flow(&fq_nonprio_flows, sflow, hash) < 0 ?
+		      CLS_RET_ERR : CLS_RET_NONPRIO;
+
+	return ret;
+}
+
+static bool fq_packet_beyond_horizon(struct sk_buff *skb)
+{
+	return (s64)skb->tstamp > (s64)(q.ktime_cache + q.horizon);
+}
+
+SEC("struct_ops/bpf_fq_enqueue")
+int BPF_PROG(bpf_fq_enqueue, struct sk_buff *skb, struct Qdisc *sch,
+	     struct bpf_sk_buff_ptr *to_free)
+{
+	struct fq_flow_node *flow = NULL, *flow_copy;
+	struct fq_stashed_flow *sflow;
+	u64 time_to_send, jiffies;
+	struct skb_node *skbn;
+	int ret;
+
+	if (sch->q.qlen >= sch->limit)
+		goto drop;
+
+	if (!skb->tstamp) {
+		time_to_send = q.ktime_cache = bpf_ktime_get_ns();
+	} else {
+		if (fq_packet_beyond_horizon(skb)) {
+			q.ktime_cache = bpf_ktime_get_ns();
+			if (fq_packet_beyond_horizon(skb)) {
+				if (q.horizon_drop)
+					goto drop;
+
+				skb->tstamp = q.ktime_cache + q.horizon;
+			}
+		}
+		time_to_send = skb->tstamp;
+	}
+
+	ret = fq_classify(skb, &sflow);
+	if (ret == CLS_RET_ERR)
+		goto drop;
+
+	flow = bpf_kptr_xchg(&sflow->flow, flow);
+	if (!flow)
+		goto drop;
+
+	if (ret == CLS_RET_NONPRIO) {
+		if (flow->qlen >= q.flow_plimit) {
+			bpf_kptr_xchg_back(&sflow->flow, flow);
+			goto drop;
+		}
+
+		if (fq_flow_is_detached(flow)) {
+			flow_copy = bpf_refcount_acquire(flow);
+
+			jiffies = bpf_jiffies64();
+			if ((s64)(jiffies - (flow_copy->age + q.flow_refill_delay)) > 0) {
+				if (flow_copy->credit < q.quantum)
+					flow_copy->credit = q.quantum;
+			}
+			flow_copy->age = 0;
+			fq_flows_add_tail(&fq_new_flows, &fq_new_flows_lock, flow_copy,
+					  &q.new_flow_cnt);
+		}
+	}
+
+	skbn = bpf_obj_new(typeof(*skbn));
+	if (!skbn) {
+		bpf_kptr_xchg_back(&sflow->flow, flow);
+		goto drop;
+	}
+
+	skbn->tstamp = skb->tstamp = time_to_send;
+
+	sch->qstats.backlog += qdisc_pkt_len(skb);
+
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	if (skb)
+		bpf_qdisc_skb_drop(skb, to_free);
+
+	bpf_spin_lock(&flow->lock);
+	bpf_rbtree_add(&flow->queue, &skbn->node, skbn_tstamp_less);
+	bpf_spin_unlock(&flow->lock);
+
+	flow->qlen++;
+	bpf_kptr_xchg_back(&sflow->flow, flow);
+
+	sch->q.qlen++;
+	return NET_XMIT_SUCCESS;
+
+drop:
+	bpf_qdisc_skb_drop(skb, to_free);
+	sch->qstats.drops++;
+	return NET_XMIT_DROP;
+}
+
+static int fq_unset_throttled_flows(u32 index, struct unset_throttled_flows_ctx *ctx)
+{
+	struct bpf_rb_node *node = NULL;
+	struct fq_flow_node *flow;
+
+	bpf_spin_lock(&fq_delayed_lock);
+
+	node = bpf_rbtree_first(&fq_delayed);
+	if (!node) {
+		bpf_spin_unlock(&fq_delayed_lock);
+		return 1;
+	}
+
+	flow = container_of(node, struct fq_flow_node, rb_node);
+	if (!ctx->unset_all && flow->time_next_packet > ctx->now) {
+		q.time_next_delayed_flow = flow->time_next_packet;
+		bpf_spin_unlock(&fq_delayed_lock);
+		return 1;
+	}
+
+	node = bpf_rbtree_remove(&fq_delayed, &flow->rb_node);
+
+	bpf_spin_unlock(&fq_delayed_lock);
+
+	if (!node)
+		return 1;
+
+	flow = container_of(node, struct fq_flow_node, rb_node);
+	flow->age = 0;
+	fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt);
+
+	return 0;
+}
+
+static void fq_flow_set_throttled(struct fq_flow_node *flow)
+{
+	flow->age = ~0ULL;
+
+	if (q.time_next_delayed_flow > flow->time_next_packet)
+		q.time_next_delayed_flow = flow->time_next_packet;
+
+	bpf_spin_lock(&fq_delayed_lock);
+	bpf_rbtree_add(&fq_delayed, &flow->rb_node, fn_time_next_packet_less);
+	bpf_spin_unlock(&fq_delayed_lock);
+}
+
+static void fq_check_throttled(u64 now)
+{
+	struct unset_throttled_flows_ctx ctx = {
+		.unset_all = false,
+		.now = now,
+	};
+	unsigned long sample;
+
+	if (q.time_next_delayed_flow > now)
+		return;
+
+	sample = (unsigned long)(now - q.time_next_delayed_flow);
+	q.unthrottle_latency_ns -= q.unthrottle_latency_ns >> 3;
+	q.unthrottle_latency_ns += sample >> 3;
+
+	q.time_next_delayed_flow = ~0ULL;
+	bpf_loop(NUM_QUEUE, fq_unset_throttled_flows, &ctx, 0);
+}
+
+static struct sk_buff*
+fq_dequeue_nonprio_flows(u32 index, struct dequeue_nonprio_ctx *ctx)
+{
+	u64 time_next_packet, time_to_send;
+	struct bpf_rb_node *rb_node;
+	struct sk_buff *skb = NULL;
+	struct bpf_list_head *head;
+	struct bpf_list_node *node;
+	struct bpf_spin_lock *lock;
+	struct fq_flow_node *flow;
+	struct skb_node *skbn;
+	bool is_empty;
+	u32 *cnt;
+
+	if (q.new_flow_cnt) {
+		head = &fq_new_flows;
+		lock = &fq_new_flows_lock;
+		cnt = &q.new_flow_cnt;
+	} else if (q.old_flow_cnt) {
+		head = &fq_old_flows;
+		lock = &fq_old_flows_lock;
+		cnt = &q.old_flow_cnt;
+	} else {
+		if (q.time_next_delayed_flow != ~0ULL)
+			ctx->expire = q.time_next_delayed_flow;
+		goto break_loop;
+	}
+
+	fq_flows_remove_front(head, lock, &node, cnt);
+	if (!node)
+		goto break_loop;
+
+	flow = container_of(node, struct fq_flow_node, list_node);
+	if (flow->credit <= 0) {
+		flow->credit += q.quantum;
+		fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt);
+		return NULL;
+	}
+
+	bpf_spin_lock(&flow->lock);
+	rb_node = bpf_rbtree_first(&flow->queue);
+	if (!rb_node) {
+		bpf_spin_unlock(&flow->lock);
+		is_empty = fq_flows_is_empty(&fq_old_flows, &fq_old_flows_lock);
+		if (head == &fq_new_flows && !is_empty) {
+			fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt);
+		} else {
+			fq_flow_set_detached(flow);
+			bpf_obj_drop(flow);
+		}
+		return NULL;
+	}
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	time_to_send = skbn->tstamp;
+
+	time_next_packet = (time_to_send > flow->time_next_packet) ?
+		time_to_send : flow->time_next_packet;
+	if (ctx->now < time_next_packet) {
+		bpf_spin_unlock(&flow->lock);
+		flow->time_next_packet = time_next_packet;
+		fq_flow_set_throttled(flow);
+		return NULL;
+	}
+
+	rb_node = bpf_rbtree_remove(&flow->queue, rb_node);
+	bpf_spin_unlock(&flow->lock);
+
+	if (!rb_node)
+		goto add_flow_and_break;
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	bpf_obj_drop(skbn);
+
+	if (!skb)
+		goto add_flow_and_break;
+
+	flow->credit -= qdisc_skb_cb(skb)->pkt_len;
+	flow->qlen--;
+
+add_flow_and_break:
+	fq_flows_add_head(head, lock, flow, cnt);
+
+break_loop:
+	ctx->stop_iter = true;
+	return skb;
+}
+
+static struct sk_buff *fq_dequeue_prio(void)
+{
+	struct fq_flow_node *flow = NULL;
+	struct fq_stashed_flow *sflow;
+	struct bpf_rb_node *rb_node;
+	struct sk_buff *skb = NULL;
+	struct skb_node *skbn;
+	u64 hash = 0;
+
+	sflow = bpf_map_lookup_elem(&fq_prio_flows, &hash);
+	if (!sflow)
+		return NULL;
+
+	flow = bpf_kptr_xchg(&sflow->flow, flow);
+	if (!flow)
+		return NULL;
+
+	bpf_spin_lock(&flow->lock);
+	rb_node = bpf_rbtree_first(&flow->queue);
+	if (!rb_node) {
+		bpf_spin_unlock(&flow->lock);
+		goto out;
+	}
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	rb_node = bpf_rbtree_remove(&flow->queue, &skbn->node);
+	bpf_spin_unlock(&flow->lock);
+
+	if (!rb_node)
+		goto out;
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	bpf_obj_drop(skbn);
+
+out:
+	bpf_kptr_xchg_back(&sflow->flow, flow);
+
+	return skb;
+}
+
+SEC("struct_ops/bpf_fq_dequeue")
+struct sk_buff *BPF_PROG(bpf_fq_dequeue, struct Qdisc *sch)
+{
+	struct dequeue_nonprio_ctx cb_ctx = {};
+	struct sk_buff *skb = NULL;
+	int i;
+
+	if (!sch->q.qlen)
+		goto out;
+
+	skb = fq_dequeue_prio();
+	if (skb)
+		goto dequeue;
+
+	q.ktime_cache = cb_ctx.now = bpf_ktime_get_ns();
+	fq_check_throttled(q.ktime_cache);
+	bpf_for(i, 0, sch->limit) {
+		skb = fq_dequeue_nonprio_flows(i, &cb_ctx);
+		if (cb_ctx.stop_iter)
+			break;
+	};
+
+	if (skb) {
+dequeue:
+		sch->q.qlen--;
+		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		bpf_qdisc_bstats_update(sch, skb);
+		return skb;
+	}
+
+	if (cb_ctx.expire)
+		bpf_qdisc_watchdog_schedule(sch, cb_ctx.expire, q.timer_slack);
+out:
+	return NULL;
+}
+
+static int fq_remove_flows_in_list(u32 index, void *ctx)
+{
+	struct bpf_list_node *node;
+	struct fq_flow_node *flow;
+
+	bpf_spin_lock(&fq_new_flows_lock);
+	node = bpf_list_pop_front(&fq_new_flows);
+	bpf_spin_unlock(&fq_new_flows_lock);
+	if (!node) {
+		bpf_spin_lock(&fq_old_flows_lock);
+		node = bpf_list_pop_front(&fq_old_flows);
+		bpf_spin_unlock(&fq_old_flows_lock);
+		if (!node)
+			return 1;
+	}
+
+	flow = container_of(node, struct fq_flow_node, list_node);
+	bpf_obj_drop(flow);
+
+	return 0;
+}
+
+extern unsigned CONFIG_HZ __kconfig;
+
+/* limit number of collected flows per round */
+#define FQ_GC_MAX 8
+#define FQ_GC_AGE (3*CONFIG_HZ)
+
+static bool fq_gc_candidate(struct fq_flow_node *flow)
+{
+	u64 jiffies = bpf_jiffies64();
+
+	return fq_flow_is_detached(flow) &&
+	       ((s64)(jiffies - (flow->age + FQ_GC_AGE)) > 0);
+}
+
+static int
+fq_remove_flows(struct bpf_map *flow_map, u64 *hash,
+		struct fq_stashed_flow *sflow, struct remove_flows_ctx *ctx)
+{
+	if (sflow->flow &&
+	    (!ctx->gc_only || fq_gc_candidate(sflow->flow))) {
+		bpf_map_delete_elem(flow_map, hash);
+		ctx->reset_cnt++;
+	}
+
+	return ctx->reset_cnt < ctx->reset_max ? 0 : 1;
+}
+
+static void fq_gc(void)
+{
+	struct remove_flows_ctx cb_ctx = {
+		.gc_only = true,
+		.reset_cnt = 0,
+		.reset_max = FQ_GC_MAX,
+	};
+
+	bpf_for_each_map_elem(&fq_nonprio_flows, fq_remove_flows, &cb_ctx, 0);
+}
+
+SEC("struct_ops/bpf_fq_reset")
+void BPF_PROG(bpf_fq_reset, struct Qdisc *sch)
+{
+	struct unset_throttled_flows_ctx utf_ctx = {
+		.unset_all = true,
+	};
+	struct remove_flows_ctx rf_ctx = {
+		.gc_only = false,
+		.reset_cnt = 0,
+		.reset_max = NUM_QUEUE,
+	};
+	struct fq_stashed_flow *sflow;
+	u64 hash = 0;
+
+	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
+
+	bpf_for_each_map_elem(&fq_nonprio_flows, fq_remove_flows, &rf_ctx, 0);
+
+	rf_ctx.reset_cnt = 0;
+	bpf_for_each_map_elem(&fq_prio_flows, fq_remove_flows, &rf_ctx, 0);
+	fq_new_flow(&fq_prio_flows, &sflow, hash);
+
+	bpf_loop(NUM_QUEUE, fq_remove_flows_in_list, NULL, 0);
+	q.new_flow_cnt = 0;
+	q.old_flow_cnt = 0;
+
+	bpf_loop(NUM_QUEUE, fq_unset_throttled_flows, &utf_ctx, 0);
+}
+
+SEC("struct_ops/bpf_fq_init")
+int BPF_PROG(bpf_fq_init, struct Qdisc *sch, struct nlattr *opt,
+	     struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = sch->dev_queue->dev;
+	u32 psched_mtu = dev->mtu + dev->hard_header_len;
+	struct fq_stashed_flow *sflow;
+	u64 hash = 0;
+
+	if (fq_new_flow(&fq_prio_flows, &sflow, hash) < 0)
+		return -ENOMEM;
+
+	sch->limit = 10000;
+	q.initial_quantum = 10 * psched_mtu;
+	q.quantum = 2 * psched_mtu;
+	q.flow_refill_delay = 40;
+	q.flow_plimit = 100;
+	q.horizon = 10ULL * NSEC_PER_SEC;
+	q.horizon_drop = 1;
+	q.orphan_mask = 1024 - 1;
+	q.timer_slack = 10 * NSEC_PER_USEC;
+	q.time_next_delayed_flow = ~0ULL;
+	q.unthrottle_latency_ns = 0ULL;
+	q.new_flow_cnt = 0;
+	q.old_flow_cnt = 0;
+
+	return 0;
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_fq_destroy, struct Qdisc *sch)
+{
+}
+
+SEC(".struct_ops")
+struct Qdisc_ops fq = {
+	.enqueue   = (void *)bpf_fq_enqueue,
+	.dequeue   = (void *)bpf_fq_dequeue,
+	.reset     = (void *)bpf_fq_reset,
+	.init      = (void *)bpf_fq_init,
+	.destroy   = (void *)bpf_fq_destroy,
+	.id        = "bpf_fq",
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index 659694162739..17db400f0e0d 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -128,6 +128,7 @@
 #define sk_refcnt		__sk_common.skc_refcnt
 #define sk_state		__sk_common.skc_state
 #define sk_net			__sk_common.skc_net
+#define sk_rcv_saddr		__sk_common.skc_rcv_saddr
 #define sk_v6_daddr		__sk_common.skc_v6_daddr
 #define sk_v6_rcv_saddr		__sk_common.skc_v6_rcv_saddr
 #define sk_flags		__sk_common.skc_flags
diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_modify.c b/tools/testing/selftests/bpf/progs/for_each_hash_modify.c
new file mode 100644
index 000000000000..82307166f789
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/for_each_hash_modify.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Intel Corporation */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 128);
+	__type(key, __u64);
+	__type(value, __u64);
+} hashmap SEC(".maps");
+
+static int cb(struct bpf_map *map, __u64 *key, __u64 *val, void *arg)
+{
+	bpf_map_delete_elem(map, key);
+	bpf_map_update_elem(map, key, val, 0);
+	return 0;
+}
+
+SEC("tc")
+int test_pkt_access(struct __sk_buff *skb)
+{
+	(void)skb;
+
+	bpf_for_each_map_elem(&hashmap, cb, NULL, 0);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/res_spin_lock.c b/tools/testing/selftests/bpf/progs/res_spin_lock.c
index b33385dfbd35..22c4fb8b9266 100644
--- a/tools/testing/selftests/bpf/progs/res_spin_lock.c
+++ b/tools/testing/selftests/bpf/progs/res_spin_lock.c
@@ -38,13 +38,14 @@ int res_spin_lock_test(struct __sk_buff *ctx)
 	r = bpf_res_spin_lock(&elem1->lock);
 	if (r)
 		return r;
-	if (!bpf_res_spin_lock(&elem2->lock)) {
+	r = bpf_res_spin_lock(&elem2->lock);
+	if (!r) {
 		bpf_res_spin_unlock(&elem2->lock);
 		bpf_res_spin_unlock(&elem1->lock);
 		return -1;
 	}
 	bpf_res_spin_unlock(&elem1->lock);
-	return 0;
+	return r != -EDEADLK;
 }
 
 SEC("tc")
@@ -124,12 +125,15 @@ int res_spin_lock_test_held_lock_max(struct __sk_buff *ctx)
 	/* Trigger AA, after exhausting entries in the held lock table. This
 	 * time, only the timeout can save us, as AA detection won't succeed.
 	 */
-	if (!bpf_res_spin_lock(locks[34])) {
+	ret = bpf_res_spin_lock(locks[34]);
+	if (!ret) {
 		bpf_res_spin_unlock(locks[34]);
 		ret = 1;
 		goto end;
 	}
 
+	ret = ret != -ETIMEDOUT ? 2 : 0;
+
 end:
 	for (i = i - 1; i >= 0; i--)
 		bpf_res_spin_unlock(locks[i]);
diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c
index 0107a24b7522..d330b1511979 100644
--- a/tools/testing/selftests/bpf/progs/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c
@@ -83,6 +83,14 @@ struct loop_ctx {
 	struct sock *sk;
 };
 
+static bool sk_is_tcp(struct sock *sk)
+{
+	return (sk->__sk_common.skc_family == AF_INET ||
+		sk->__sk_common.skc_family == AF_INET6) &&
+		sk->sk_type == SOCK_STREAM &&
+		sk->sk_protocol == IPPROTO_TCP;
+}
+
 static int bpf_test_sockopt_flip(void *ctx, struct sock *sk,
 				 const struct sockopt_test *t,
 				 int level)
@@ -91,6 +99,9 @@ static int bpf_test_sockopt_flip(void *ctx, struct sock *sk,
 
 	opt = t->opt;
 
+	if (opt == SO_TXREHASH && !sk_is_tcp(sk))
+		return 0;
+
 	if (bpf_getsockopt(ctx, level, opt, &old, sizeof(old)))
 		return 1;
 	/* kernel initialized txrehash to 255 */
diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
index 96531b0d9d55..8f483337e103 100644
--- a/tools/testing/selftests/bpf/progs/sock_iter_batch.c
+++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
@@ -17,6 +17,12 @@ static bool ipv6_addr_loopback(const struct in6_addr *a)
 		a->s6_addr32[2] | (a->s6_addr32[3] ^ bpf_htonl(1))) == 0;
 }
 
+static bool ipv4_addr_loopback(__be32 a)
+{
+	return a == bpf_ntohl(0x7f000001);
+}
+
+volatile const unsigned int sf;
 volatile const __u16 ports[2];
 unsigned int bucket[2];
 
@@ -26,16 +32,20 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx)
 	struct sock *sk = (struct sock *)ctx->sk_common;
 	struct inet_hashinfo *hinfo;
 	unsigned int hash;
+	__u64 sock_cookie;
 	struct net *net;
 	int idx;
 
 	if (!sk)
 		return 0;
 
+	sock_cookie = bpf_get_socket_cookie(sk);
 	sk = bpf_core_cast(sk, struct sock);
-	if (sk->sk_family != AF_INET6 ||
+	if (sk->sk_family != sf ||
 	    sk->sk_state != TCP_LISTEN ||
-	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
+	    sk->sk_family == AF_INET6 ?
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) :
+	    !ipv4_addr_loopback(sk->sk_rcv_saddr))
 		return 0;
 
 	if (sk->sk_num == ports[0])
@@ -52,6 +62,7 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx)
 	hinfo = net->ipv4.tcp_death_row.hashinfo;
 	bucket[idx] = hash & hinfo->lhash2_mask;
 	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+	bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie));
 
 	return 0;
 }
@@ -63,14 +74,18 @@ int iter_udp_soreuse(struct bpf_iter__udp *ctx)
 {
 	struct sock *sk = (struct sock *)ctx->udp_sk;
 	struct udp_table *udptable;
+	__u64 sock_cookie;
 	int idx;
 
 	if (!sk)
 		return 0;
 
+	sock_cookie = bpf_get_socket_cookie(sk);
 	sk = bpf_core_cast(sk, struct sock);
-	if (sk->sk_family != AF_INET6 ||
-	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
+	if (sk->sk_family != sf ||
+	    sk->sk_family == AF_INET6 ?
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) :
+	    !ipv4_addr_loopback(sk->sk_rcv_saddr))
 		return 0;
 
 	if (sk->sk_num == ports[0])
@@ -84,6 +99,7 @@ int iter_udp_soreuse(struct bpf_iter__udp *ctx)
 	udptable = sk->sk_net.net->ipv4.udp_table;
 	bucket[idx] = udp_sk(sk)->udp_portaddr_hash & udptable->mask;
 	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+	bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie));
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
index ccde6a4c6319..683306db8594 100644
--- a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
+++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
@@ -4,6 +4,8 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/errno.h>
 #include "xsk_xdp_common.h"
 
 struct {
@@ -14,6 +16,7 @@ struct {
 } xsk SEC(".maps");
 
 static unsigned int idx;
+int adjust_value = 0;
 int count = 0;
 
 SEC("xdp.frags") int xsk_def_prog(struct xdp_md *xdp)
@@ -70,4 +73,51 @@ SEC("xdp") int xsk_xdp_shared_umem(struct xdp_md *xdp)
 	return bpf_redirect_map(&xsk, idx, XDP_DROP);
 }
 
+SEC("xdp.frags") int xsk_xdp_adjust_tail(struct xdp_md *xdp)
+{
+	__u32 buff_len, curr_buff_len;
+	int ret;
+
+	buff_len = bpf_xdp_get_buff_len(xdp);
+	if (buff_len == 0)
+		return XDP_DROP;
+
+	ret = bpf_xdp_adjust_tail(xdp, adjust_value);
+	if (ret < 0) {
+		/* Handle unsupported cases */
+		if (ret == -EOPNOTSUPP) {
+			/* Set adjust_value to -EOPNOTSUPP to indicate to userspace that this case
+			 * is unsupported
+			 */
+			adjust_value = -EOPNOTSUPP;
+			return bpf_redirect_map(&xsk, 0, XDP_DROP);
+		}
+
+		return XDP_DROP;
+	}
+
+	curr_buff_len = bpf_xdp_get_buff_len(xdp);
+	if (curr_buff_len != buff_len + adjust_value)
+		return XDP_DROP;
+
+	if (curr_buff_len > buff_len) {
+		__u32 *pkt_data = (void *)(long)xdp->data;
+		__u32 len, words_to_end, seq_num;
+
+		len = curr_buff_len - PKT_HDR_ALIGN;
+		words_to_end = len / sizeof(*pkt_data) - 1;
+		seq_num = words_to_end;
+
+		/* Convert sequence number to network byte order. Store this in the last 4 bytes of
+		 * the packet. Use 'adjust_value' to determine the position at the end of the
+		 * packet for storing the sequence number.
+		 */
+		seq_num = __constant_htonl(words_to_end);
+		bpf_xdp_store_bytes(xdp, curr_buff_len - sizeof(seq_num), &seq_num,
+				    sizeof(seq_num));
+	}
+
+	return bpf_redirect_map(&xsk, 0, XDP_DROP);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/xsk_xdp_common.h b/tools/testing/selftests/bpf/xsk_xdp_common.h
index 5a6f36f07383..45810ff552da 100644
--- a/tools/testing/selftests/bpf/xsk_xdp_common.h
+++ b/tools/testing/selftests/bpf/xsk_xdp_common.h
@@ -4,6 +4,7 @@
 #define XSK_XDP_COMMON_H_
 
 #define MAX_SOCKETS 2
+#define PKT_HDR_ALIGN (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */
 
 struct xdp_info {
 	__u64 count;
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 11f047b8af75..0ced4026ee44 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -524,6 +524,8 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 	test->nb_sockets = 1;
 	test->fail = false;
 	test->set_ring = false;
+	test->adjust_tail = false;
+	test->adjust_tail_support = false;
 	test->mtu = MAX_ETH_PKT_SIZE;
 	test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog;
 	test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk;
@@ -757,14 +759,15 @@ static struct pkt_stream *pkt_stream_clone(struct pkt_stream *pkt_stream)
 	return pkt_stream_generate(pkt_stream->nb_pkts, pkt_stream->pkts[0].len);
 }
 
-static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
+static void pkt_stream_replace_ifobject(struct ifobject *ifobj, u32 nb_pkts, u32 pkt_len)
 {
-	struct pkt_stream *pkt_stream;
+	ifobj->xsk->pkt_stream = pkt_stream_generate(nb_pkts, pkt_len);
+}
 
-	pkt_stream = pkt_stream_generate(nb_pkts, pkt_len);
-	test->ifobj_tx->xsk->pkt_stream = pkt_stream;
-	pkt_stream = pkt_stream_generate(nb_pkts, pkt_len);
-	test->ifobj_rx->xsk->pkt_stream = pkt_stream;
+static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
+{
+	pkt_stream_replace_ifobject(test->ifobj_tx, nb_pkts, pkt_len);
+	pkt_stream_replace_ifobject(test->ifobj_rx, nb_pkts, pkt_len);
 }
 
 static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len,
@@ -991,6 +994,31 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr)
 	return true;
 }
 
+static bool is_adjust_tail_supported(struct xsk_xdp_progs *skel_rx)
+{
+	struct bpf_map *data_map;
+	int adjust_value = 0;
+	int key = 0;
+	int ret;
+
+	data_map = bpf_object__find_map_by_name(skel_rx->obj, "xsk_xdp_.bss");
+	if (!data_map || !bpf_map__is_internal(data_map)) {
+		ksft_print_msg("Error: could not find bss section of XDP program\n");
+		exit_with_error(errno);
+	}
+
+	ret = bpf_map_lookup_elem(bpf_map__fd(data_map), &key, &adjust_value);
+	if (ret) {
+		ksft_print_msg("Error: bpf_map_lookup_elem failed with error %d\n", ret);
+		exit_with_error(errno);
+	}
+
+	/* Set the 'adjust_value' variable to -EOPNOTSUPP in the XDP program if the adjust_tail
+	 * helper is not supported. Skip the adjust_tail test case in this scenario.
+	 */
+	return adjust_value != -EOPNOTSUPP;
+}
+
 static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 expected_pkt_nb,
 			  u32 bytes_processed)
 {
@@ -1767,8 +1795,13 @@ static void *worker_testapp_validate_rx(void *arg)
 
 	if (!err && ifobject->validation_func)
 		err = ifobject->validation_func(ifobject);
-	if (err)
-		report_failure(test);
+
+	if (err) {
+		if (test->adjust_tail && !is_adjust_tail_supported(ifobject->xdp_progs))
+			test->adjust_tail_support = false;
+		else
+			report_failure(test);
+	}
 
 	pthread_exit(NULL);
 }
@@ -2515,6 +2548,71 @@ static int testapp_hw_sw_max_ring_size(struct test_spec *test)
 	return testapp_validate_traffic(test);
 }
 
+static int testapp_xdp_adjust_tail(struct test_spec *test, int adjust_value)
+{
+	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
+	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
+
+	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_adjust_tail,
+			       skel_tx->progs.xsk_xdp_adjust_tail,
+			       skel_rx->maps.xsk, skel_tx->maps.xsk);
+
+	skel_rx->bss->adjust_value = adjust_value;
+
+	return testapp_validate_traffic(test);
+}
+
+static int testapp_adjust_tail(struct test_spec *test, u32 value, u32 pkt_len)
+{
+	int ret;
+
+	test->adjust_tail_support = true;
+	test->adjust_tail = true;
+	test->total_steps = 1;
+
+	pkt_stream_replace_ifobject(test->ifobj_tx, DEFAULT_BATCH_SIZE, pkt_len);
+	pkt_stream_replace_ifobject(test->ifobj_rx, DEFAULT_BATCH_SIZE, pkt_len + value);
+
+	ret = testapp_xdp_adjust_tail(test, value);
+	if (ret)
+		return ret;
+
+	if (!test->adjust_tail_support) {
+		ksft_test_result_skip("%s %sResize pkt with bpf_xdp_adjust_tail() not supported\n",
+				      mode_string(test), busy_poll_string(test));
+		return TEST_SKIP;
+	}
+
+	return 0;
+}
+
+static int testapp_adjust_tail_shrink(struct test_spec *test)
+{
+	/* Shrink by 4 bytes for testing purpose */
+	return testapp_adjust_tail(test, -4, MIN_PKT_SIZE * 2);
+}
+
+static int testapp_adjust_tail_shrink_mb(struct test_spec *test)
+{
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	/* Shrink by the frag size */
+	return testapp_adjust_tail(test, -XSK_UMEM__MAX_FRAME_SIZE, XSK_UMEM__LARGE_FRAME_SIZE * 2);
+}
+
+static int testapp_adjust_tail_grow(struct test_spec *test)
+{
+	/* Grow by 4 bytes for testing purpose */
+	return testapp_adjust_tail(test, 4, MIN_PKT_SIZE * 2);
+}
+
+static int testapp_adjust_tail_grow_mb(struct test_spec *test)
+{
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	/* Grow by (frag_size - last_frag_Size) - 1 to stay inside the last fragment */
+	return testapp_adjust_tail(test, (XSK_UMEM__MAX_FRAME_SIZE / 2) - 1,
+				   XSK_UMEM__LARGE_FRAME_SIZE * 2);
+}
+
 static void run_pkt_test(struct test_spec *test)
 {
 	int ret;
@@ -2621,6 +2719,10 @@ static const struct test_spec tests[] = {
 	{.name = "TOO_MANY_FRAGS", .test_func = testapp_too_many_frags},
 	{.name = "HW_SW_MIN_RING_SIZE", .test_func = testapp_hw_sw_min_ring_size},
 	{.name = "HW_SW_MAX_RING_SIZE", .test_func = testapp_hw_sw_max_ring_size},
+	{.name = "XDP_ADJUST_TAIL_SHRINK", .test_func = testapp_adjust_tail_shrink},
+	{.name = "XDP_ADJUST_TAIL_SHRINK_MULTI_BUFF", .test_func = testapp_adjust_tail_shrink_mb},
+	{.name = "XDP_ADJUST_TAIL_GROW", .test_func = testapp_adjust_tail_grow},
+	{.name = "XDP_ADJUST_TAIL_GROW_MULTI_BUFF", .test_func = testapp_adjust_tail_grow_mb},
 	};
 
 static void print_tests(void)
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index e46e823f6a1a..67fc44b2813b 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -173,6 +173,8 @@ struct test_spec {
 	u16 nb_sockets;
 	bool fail;
 	bool set_ring;
+	bool adjust_tail;
+	bool adjust_tail_support;
 	enum test_mode mode;
 	char name[MAX_TEST_NAME_SIZE];
 };
diff --git a/tools/testing/selftests/drivers/net/.gitignore b/tools/testing/selftests/drivers/net/.gitignore
index ec746f374e85..d634d8395d90 100644
--- a/tools/testing/selftests/drivers/net/.gitignore
+++ b/tools/testing/selftests/drivers/net/.gitignore
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-xdp_helper
+napi_id_helper
diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
index 0c95bd944d56..17db31aa58c9 100644
--- a/tools/testing/selftests/drivers/net/Makefile
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -6,9 +6,12 @@ TEST_INCLUDES := $(wildcard lib/py/*.py) \
 		 ../../net/net_helper.sh \
 		 ../../net/lib.sh \
 
-TEST_GEN_FILES := xdp_helper
+TEST_GEN_FILES := \
+	napi_id_helper \
+# end of TEST_GEN_FILES
 
 TEST_PROGS := \
+	napi_id.py \
 	netcons_basic.sh \
 	netcons_fragmented_msg.sh \
 	netcons_overflow.sh \
diff --git a/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh b/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh
new file mode 120000
index 000000000000..d16a65e7595d
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh
@@ -0,0 +1 @@
+run_net_forwarding_test.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index 07cddb19ba35..df2c047ffa90 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -15,12 +15,11 @@ TEST_PROGS = \
 	iou-zcrx.py \
 	irq.py \
 	loopback.sh \
-	nic_link_layer.py \
-	nic_performance.py \
 	pp_alloc_fail.py \
 	rss_ctx.py \
 	rss_input_xfrm.py \
 	tso.py \
+	xsk_reconfig.py \
 	#
 
 TEST_FILES := \
diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py
index 3947e9157115..d7f6a76eb2b7 100755
--- a/tools/testing/selftests/drivers/net/hw/devmem.py
+++ b/tools/testing/selftests/drivers/net/hw/devmem.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0
 
+from os import path
 from lib.py import ksft_run, ksft_exit
 from lib.py import ksft_eq, KsftSkipEx
 from lib.py import NetDrvEpEnv
@@ -10,8 +11,7 @@ from lib.py import ksft_disruptive
 
 def require_devmem(cfg):
     if not hasattr(cfg, "_devmem_probed"):
-        port = rand_port()
-        probe_command = f"./ncdevmem -f {cfg.ifname}"
+        probe_command = f"{cfg.bin_local} -f {cfg.ifname}"
         cfg._devmem_supported = cmd(probe_command, fail=False, shell=True).ret == 0
         cfg._devmem_probed = True
 
@@ -25,7 +25,7 @@ def check_rx(cfg) -> None:
     require_devmem(cfg)
 
     port = rand_port()
-    listen_cmd = f"./ncdevmem -l -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port}"
+    listen_cmd = f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port}"
 
     with bkg(listen_cmd) as socat:
         wait_port_listen(port)
@@ -34,9 +34,42 @@ def check_rx(cfg) -> None:
     ksft_eq(socat.stdout.strip(), "hello\nworld")
 
 
+@ksft_disruptive
+def check_tx(cfg) -> None:
+    cfg.require_ipver("6")
+    require_devmem(cfg)
+
+    port = rand_port()
+    listen_cmd = f"socat -U - TCP6-LISTEN:{port}"
+
+    with bkg(listen_cmd, exit_wait=True) as socat:
+        wait_port_listen(port)
+        cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port}", host=cfg.remote, shell=True)
+
+    ksft_eq(socat.stdout.strip(), "hello\nworld")
+
+
+@ksft_disruptive
+def check_tx_chunks(cfg) -> None:
+    cfg.require_ipver("6")
+    require_devmem(cfg)
+
+    port = rand_port()
+    listen_cmd = f"socat -U - TCP6-LISTEN:{port}"
+
+    with bkg(listen_cmd, exit_wait=True) as socat:
+        wait_port_listen(port)
+        cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port} -z 3", host=cfg.remote, shell=True)
+
+    ksft_eq(socat.stdout.strip(), "hello\nworld")
+
+
 def main() -> None:
     with NetDrvEpEnv(__file__) as cfg:
-        ksft_run([check_rx],
+        cfg.bin_local = path.abspath(path.dirname(__file__) + "/ncdevmem")
+        cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+        ksft_run([check_rx, check_tx, check_tx_chunks],
                  args=(cfg, ))
     ksft_exit()
 
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
index c26b4180eddd..62456df947bc 100644
--- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
@@ -37,8 +37,8 @@
 
 #include <liburing.h>
 
-#define PAGE_SIZE (4096)
-#define AREA_SIZE (8192 * PAGE_SIZE)
+static long page_size;
+#define AREA_SIZE (8192 * page_size)
 #define SEND_SIZE (512 * 4096)
 #define min(a, b) \
 	({ \
@@ -66,7 +66,7 @@ static int cfg_oneshot_recvs;
 static int cfg_send_size = SEND_SIZE;
 static struct sockaddr_in6 cfg_addr;
 
-static char payload[SEND_SIZE] __attribute__((aligned(PAGE_SIZE)));
+static char *payload;
 static void *area_ptr;
 static void *ring_ptr;
 static size_t ring_size;
@@ -114,8 +114,8 @@ static inline size_t get_refill_ring_size(unsigned int rq_entries)
 
 	ring_size = rq_entries * sizeof(struct io_uring_zcrx_rqe);
 	/* add space for the header (head/tail/etc.) */
-	ring_size += PAGE_SIZE;
-	return ALIGN_UP(ring_size, 4096);
+	ring_size += page_size;
+	return ALIGN_UP(ring_size, page_size);
 }
 
 static void setup_zcrx(struct io_uring *ring)
@@ -219,7 +219,7 @@ static void process_accept(struct io_uring *ring, struct io_uring_cqe *cqe)
 
 	connfd = cqe->res;
 	if (cfg_oneshot)
-		add_recvzc_oneshot(ring, connfd, PAGE_SIZE);
+		add_recvzc_oneshot(ring, connfd, page_size);
 	else
 		add_recvzc(ring, connfd);
 }
@@ -245,7 +245,7 @@ static void process_recvzc(struct io_uring *ring, struct io_uring_cqe *cqe)
 
 	if (cfg_oneshot) {
 		if (cqe->res == 0 && cqe->flags == 0 && cfg_oneshot_recvs) {
-			add_recvzc_oneshot(ring, connfd, PAGE_SIZE);
+			add_recvzc_oneshot(ring, connfd, page_size);
 			cfg_oneshot_recvs--;
 		}
 	} else if (!(cqe->flags & IORING_CQE_F_MORE)) {
@@ -260,7 +260,7 @@ static void process_recvzc(struct io_uring *ring, struct io_uring_cqe *cqe)
 
 	for (i = 0; i < n; i++) {
 		if (*(data + i) != payload[(received + i)])
-			error(1, 0, "payload mismatch at ", i);
+			error(1, 0, "payload mismatch at %d", i);
 	}
 	received += n;
 
@@ -354,7 +354,7 @@ static void run_client(void)
 		chunk = min_t(ssize_t, cfg_payload_len, to_send);
 		res = send(fd, src, chunk, 0);
 		if (res < 0)
-			error(1, 0, "send(): %d", sent);
+			error(1, 0, "send(): %zd", sent);
 		sent += res;
 		to_send -= res;
 	}
@@ -370,7 +370,7 @@ static void usage(const char *filepath)
 
 static void parse_opts(int argc, char **argv)
 {
-	const int max_payload_len = sizeof(payload) -
+	const int max_payload_len = SEND_SIZE -
 				    sizeof(struct ipv6hdr) -
 				    sizeof(struct tcphdr) -
 				    40 /* max tcp options */;
@@ -443,6 +443,13 @@ int main(int argc, char **argv)
 	const char *cfg_test = argv[argc - 1];
 	int i;
 
+	page_size = sysconf(_SC_PAGESIZE);
+	if (page_size < 0)
+		return 1;
+
+	if (posix_memalign((void **)&payload, page_size, SEND_SIZE))
+		return 1;
+
 	parse_opts(argc, argv);
 
 	for (i = 0; i < SEND_SIZE; i++)
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
index 9f271ab6ec04..9c03fd777f3d 100755
--- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
@@ -5,13 +5,12 @@ import re
 from os import path
 from lib.py import ksft_run, ksft_exit
 from lib.py import NetDrvEpEnv
-from lib.py import bkg, cmd, ethtool, wait_port_listen
+from lib.py import bkg, cmd, defer, ethtool, rand_port, wait_port_listen
 
 
-def _get_rx_ring_entries(cfg):
-    output = ethtool(f"-g {cfg.ifname}", host=cfg.remote).stdout
-    values = re.findall(r'RX:\s+(\d+)', output)
-    return int(values[1])
+def _get_current_settings(cfg):
+    output = ethtool(f"-g {cfg.ifname}", json=True, host=cfg.remote)[0]
+    return (output['rx'], output['hds-thresh'])
 
 
 def _get_combined_channels(cfg):
@@ -20,8 +19,21 @@ def _get_combined_channels(cfg):
     return int(values[1])
 
 
-def _set_flow_rule(cfg, chan):
-    output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port 9999 action {chan}", host=cfg.remote).stdout
+def _create_rss_ctx(cfg, chan):
+    output = ethtool(f"-X {cfg.ifname} context new start {chan} equal 1", host=cfg.remote).stdout
+    values = re.search(r'New RSS context is (\d+)', output).group(1)
+    ctx_id = int(values)
+    return (ctx_id, defer(ethtool, f"-X {cfg.ifname} delete context {ctx_id}", host=cfg.remote))
+
+
+def _set_flow_rule(cfg, port, chan):
+    output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} action {chan}", host=cfg.remote).stdout
+    values = re.search(r'ID (\d+)', output).group(1)
+    return int(values)
+
+
+def _set_flow_rule_rss(cfg, port, ctx_id):
+    output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} context {ctx_id}", host=cfg.remote).stdout
     values = re.search(r'ID (\d+)', output).group(1)
     return int(values)
 
@@ -32,22 +44,29 @@ def test_zcrx(cfg) -> None:
     combined_chans = _get_combined_channels(cfg)
     if combined_chans < 2:
         raise KsftSkipEx('at least 2 combined channels required')
-    rx_ring = _get_rx_ring_entries(cfg)
+    (rx_ring, hds_thresh) = _get_current_settings(cfg)
+    port = rand_port()
+
+    ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
 
-    try:
-        ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
-        ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
-        flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
+    ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote)
 
-        rx_cmd = f"{cfg.bin_remote} -s -p 9999 -i {cfg.ifname} -q {combined_chans - 1}"
-        tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p 9999 -l 12840"
-        with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
-            wait_port_listen(9999, proto="tcp", host=cfg.remote)
-            cmd(tx_cmd)
-    finally:
-        ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
-        ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
-        ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+    ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+
+    ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
+    defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote)
+
+    flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
+
+    rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}"
+    tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 12840"
+    with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+        wait_port_listen(port, proto="tcp", host=cfg.remote)
+        cmd(tx_cmd)
 
 
 def test_zcrx_oneshot(cfg) -> None:
@@ -56,22 +75,61 @@ def test_zcrx_oneshot(cfg) -> None:
     combined_chans = _get_combined_channels(cfg)
     if combined_chans < 2:
         raise KsftSkipEx('at least 2 combined channels required')
-    rx_ring = _get_rx_ring_entries(cfg)
-
-    try:
-        ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
-        ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
-        flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
-
-        rx_cmd = f"{cfg.bin_remote} -s -p 9999 -i {cfg.ifname} -q {combined_chans - 1} -o 4"
-        tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p 9999 -l 4096 -z 16384"
-        with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
-            wait_port_listen(9999, proto="tcp", host=cfg.remote)
-            cmd(tx_cmd)
-    finally:
-        ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
-        ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
-        ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+    (rx_ring, hds_thresh) = _get_current_settings(cfg)
+    port = rand_port()
+
+    ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
+
+    ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote)
+
+    ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+
+    ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
+    defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote)
+
+    flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
+
+    rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1} -o 4"
+    tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 4096 -z 16384"
+    with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+        wait_port_listen(port, proto="tcp", host=cfg.remote)
+        cmd(tx_cmd)
+
+
+def test_zcrx_rss(cfg) -> None:
+    cfg.require_ipver('6')
+
+    combined_chans = _get_combined_channels(cfg)
+    if combined_chans < 2:
+        raise KsftSkipEx('at least 2 combined channels required')
+    (rx_ring, hds_thresh) = _get_current_settings(cfg)
+    port = rand_port()
+
+    ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
+
+    ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote)
+
+    ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+
+    ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
+    defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote)
+
+    (ctx_id, delete_ctx) = _create_rss_ctx(cfg, combined_chans - 1)
+    flow_rule_id = _set_flow_rule_rss(cfg, port, ctx_id)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
+
+    rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}"
+    tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 12840"
+    with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+        wait_port_listen(port, proto="tcp", host=cfg.remote)
+        cmd(tx_cmd)
 
 
 def main() -> None:
diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
index 399789a9676a..b582885786f5 100644
--- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
+++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
@@ -9,7 +9,6 @@ try:
     sys.path.append(KSFT_DIR.as_posix())
     from net.lib.py import *
     from drivers.net.lib.py import *
-    from .linkconfig import LinkConfig
 except ModuleNotFoundError as e:
     ksft_pr("Failed importing `net` library from kernel sources")
     ksft_pr(str(e))
diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py b/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
deleted file mode 100644
index 79fde603cbbc..000000000000
--- a/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
+++ /dev/null
@@ -1,222 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-from lib.py import cmd, ethtool, ip
-from lib.py import ksft_pr, ksft_eq, KsftSkipEx
-from typing import Optional
-import re
-import time
-import json
-
-#The LinkConfig class is implemented to handle the link layer configurations.
-#Required minimum ethtool version is 6.10
-
-class LinkConfig:
-    """Class for handling the link layer configurations"""
-    def __init__(self, cfg: object) -> None:
-        self.cfg = cfg
-        self.partner_netif = self.get_partner_netif_name()
-
-        """Get the initial link configuration of local interface"""
-        self.common_link_modes = self.get_common_link_modes()
-
-    def get_partner_netif_name(self) -> Optional[str]:
-        partner_netif = None
-        try:
-            if not self.verify_link_up():
-                return None
-            """Get partner interface name"""
-            partner_json_output = ip("addr show", json=True, host=self.cfg.remote)
-            for interface in partner_json_output:
-                for addr in interface.get('addr_info', []):
-                    if addr.get('local') == self.cfg.remote_addr:
-                        partner_netif = interface['ifname']
-                        ksft_pr(f"Partner Interface name: {partner_netif}")
-            if partner_netif is None:
-                ksft_pr("Unable to get the partner interface name")
-        except Exception as e:
-            print(f"Unexpected error occurred while getting partner interface name: {e}")
-        self.partner_netif = partner_netif
-        return partner_netif
-
-    def verify_link_up(self) -> bool:
-        """Verify whether the local interface link is up"""
-        with open(f"/sys/class/net/{self.cfg.ifname}/operstate", "r") as fp:
-            link_state = fp.read().strip()
-
-        if link_state == "down":
-            ksft_pr(f"Link state of interface {self.cfg.ifname} is DOWN")
-            return False
-        else:
-            return True
-
-    def reset_interface(self, local: bool = True, remote: bool = True) -> bool:
-        ksft_pr("Resetting interfaces in local and remote")
-        if remote:
-            if self.verify_link_up():
-                if self.partner_netif is not None:
-                    ifname = self.partner_netif
-                    link_up_cmd = f"ip link set up {ifname}"
-                    link_down_cmd = f"ip link set down {ifname}"
-                    reset_cmd = f"{link_down_cmd} && sleep 5 && {link_up_cmd}"
-                    try:
-                        cmd(reset_cmd, host=self.cfg.remote)
-                    except Exception as e:
-                        ksft_pr(f"Unexpected error occurred while resetting remote: {e}")
-                else:
-                    ksft_pr("Partner interface not available")
-        if local:
-            ifname = self.cfg.ifname
-            link_up_cmd = f"ip link set up {ifname}"
-            link_down_cmd = f"ip link set down {ifname}"
-            reset_cmd = f"{link_down_cmd} && sleep 5 && {link_up_cmd}"
-            try:
-                cmd(reset_cmd)
-            except Exception as e:
-                ksft_pr(f"Unexpected error occurred while resetting local: {e}")
-        time.sleep(10)
-        if self.verify_link_up() and self.get_ethtool_field("link-detected"):
-            ksft_pr("Local and remote interfaces reset to original state")
-            return True
-        else:
-            ksft_pr("Error occurred after resetting interfaces. Link is DOWN.")
-            return False
-
-    def set_speed_and_duplex(self, speed: str, duplex: str, autoneg: bool = True) -> bool:
-        """Set the speed and duplex state for the interface"""
-        autoneg_state = "on" if autoneg is True else "off"
-        process = None
-        try:
-            process = ethtool(f"--change {self.cfg.ifname} speed {speed} duplex {duplex} autoneg {autoneg_state}")
-        except Exception as e:
-            ksft_pr(f"Unexpected error occurred while setting speed/duplex: {e}")
-        if process is None or process.ret != 0:
-            return False
-        else:
-            ksft_pr(f"Speed: {speed} Mbps, Duplex: {duplex} set for Interface: {self.cfg.ifname}")
-            return True
-
-    def verify_speed_and_duplex(self, expected_speed: str, expected_duplex: str) -> bool:
-        if not self.verify_link_up():
-            return False
-        """Verifying the speed and duplex state for the interface"""
-        with open(f"/sys/class/net/{self.cfg.ifname}/speed", "r") as fp:
-            actual_speed = fp.read().strip()
-        with open(f"/sys/class/net/{self.cfg.ifname}/duplex", "r") as fp:
-            actual_duplex = fp.read().strip()
-
-        ksft_eq(actual_speed, expected_speed)
-        ksft_eq(actual_duplex, expected_duplex)
-        return True
-
-    def set_autonegotiation_state(self, state: str, remote: bool = False) -> bool:
-        common_link_modes = self.common_link_modes
-        speeds, duplex_modes = self.get_speed_duplex_values(self.common_link_modes)
-        speed = speeds[0]
-        duplex = duplex_modes[0]
-        if not speed or not duplex:
-            ksft_pr("No speed or duplex modes found")
-            return False
-
-        speed_duplex_cmd = f"speed {speed} duplex {duplex}" if state == "off" else ""
-        if remote:
-            if not self.verify_link_up():
-                return False
-            """Set the autonegotiation state for the partner"""
-            command = f"-s {self.partner_netif} {speed_duplex_cmd} autoneg {state}"
-            partner_autoneg_change = None
-            """Set autonegotiation state for interface in remote pc"""
-            try:
-                partner_autoneg_change = ethtool(command, host=self.cfg.remote)
-            except Exception as e:
-                ksft_pr(f"Unexpected error occurred while changing auto-neg in remote: {e}")
-            if partner_autoneg_change is None or partner_autoneg_change.ret != 0:
-                ksft_pr(f"Not able to set autoneg parameter for interface {self.partner_netif}.")
-                return False
-            ksft_pr(f"Autoneg set as {state} for {self.partner_netif}")
-        else:
-            """Set the autonegotiation state for the interface"""
-            try:
-                process = ethtool(f"-s {self.cfg.ifname} {speed_duplex_cmd} autoneg {state}")
-                if process.ret != 0:
-                    ksft_pr(f"Not able to set autoneg parameter for interface {self.cfg.ifname}")
-                    return False
-            except Exception as e:
-                ksft_pr(f"Unexpected error occurred while changing auto-neg in local: {e}")
-                return False
-            ksft_pr(f"Autoneg set as {state} for {self.cfg.ifname}")
-        return True
-
-    def check_autoneg_supported(self, remote: bool = False) -> bool:
-        if not remote:
-            local_autoneg = self.get_ethtool_field("supports-auto-negotiation")
-            if local_autoneg is None:
-                ksft_pr(f"Unable to fetch auto-negotiation status for interface {self.cfg.ifname}")
-            """Return autoneg status of the local interface"""
-            return local_autoneg
-        else:
-            if not self.verify_link_up():
-                raise KsftSkipEx("Link is DOWN")
-            """Check remote auto-negotiation support status"""
-            partner_autoneg = False
-            if self.partner_netif is not None:
-                partner_autoneg = self.get_ethtool_field("supports-auto-negotiation", remote=True)
-                if partner_autoneg is None:
-                    ksft_pr(f"Unable to fetch auto-negotiation status for interface {self.partner_netif}")
-            return partner_autoneg
-
-    def get_common_link_modes(self) -> set[str]:
-        common_link_modes = []
-        """Populate common link modes"""
-        link_modes = self.get_ethtool_field("supported-link-modes")
-        partner_link_modes = self.get_ethtool_field("link-partner-advertised-link-modes")
-        if link_modes is None:
-            raise KsftSkipEx(f"Link modes not available for {self.cfg.ifname}")
-        if partner_link_modes is None:
-            raise KsftSkipEx(f"Partner link modes not available for {self.cfg.ifname}")
-        common_link_modes = set(link_modes) and set(partner_link_modes)
-        return common_link_modes
-
-    def get_speed_duplex_values(self, link_modes: list[str]) -> tuple[list[str], list[str]]:
-        speed = []
-        duplex = []
-        """Check the link modes"""
-        for data in link_modes:
-            parts = data.split('/')
-            speed_value = re.match(r'\d+', parts[0])
-            if speed_value:
-                speed.append(speed_value.group())
-            else:
-                ksft_pr(f"No speed value found for interface {self.ifname}")
-                return None, None
-            duplex.append(parts[1].lower())
-        return speed, duplex
-
-    def get_ethtool_field(self, field: str, remote: bool = False) -> Optional[str]:
-        process = None
-        if not remote:
-            """Get the ethtool field value for the local interface"""
-            try:
-                process = ethtool(self.cfg.ifname, json=True)
-            except Exception as e:
-                ksft_pr("Required minimum ethtool version is 6.10")
-                ksft_pr(f"Unexpected error occurred while getting ethtool field in local: {e}")
-                return None
-        else:
-            if not self.verify_link_up():
-                return None
-            """Get the ethtool field value for the remote interface"""
-            self.cfg.require_cmd("ethtool", remote=True)
-            if self.partner_netif is None:
-                ksft_pr(f"Partner interface name is unavailable.")
-                return None
-            try:
-                process = ethtool(self.partner_netif, json=True, host=self.cfg.remote)
-            except Exception as e:
-                ksft_pr("Required minimum ethtool version is 6.10")
-                ksft_pr(f"Unexpected error occurred while getting ethtool field in remote: {e}")
-                return None
-        json_data = process[0]
-        """Check if the field exist in the json data"""
-        if field not in json_data:
-            raise KsftSkipEx(f'Field {field} does not exist in the output of interface {json_data["ifname"]}')
-        return json_data[field]
diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
index 2bf14ac2b8c6..fc7ba7d71502 100644
--- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -9,22 +9,31 @@
  *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201
  *
  *     On client:
- *     echo -n "hello\nworld" | nc -s <server IP> 5201 -p 5201
+ *     echo -n "hello\nworld" | \
+ *		ncdevmem -s <server IP> [-c <client IP>] -p 5201 -f eth1
  *
- * Test data validation:
+ * Note this is compatible with regular netcat. i.e. the sender or receiver can
+ * be replaced with regular netcat to test the RX or TX path in isolation.
+ *
+ * Test data validation (devmem TCP on RX only):
  *
  *     On server:
  *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201 -v 7
  *
  *     On client:
  *     yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \
- *             tr \\n \\0 | \
- *             head -c 5G | \
+ *             head -c 1G | \
  *             nc <server IP> 5201 -p 5201
  *
+ * Test data validation (devmem TCP on RX and TX, validation happens on RX):
  *
- * Note this is compatible with regular netcat. i.e. the sender or receiver can
- * be replaced with regular netcat to test the RX or TX path in isolation.
+ *	On server:
+ *	ncdevmem -s <server IP> [-c <client IP>] -l -p 5201 -v 8 -f eth1
+ *
+ *	On client:
+ *	yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06\\x07) | \
+ *		head -c 1M | \
+ *		ncdevmem -s <server IP> [-c <client IP>] -p 5201 -f eth1
  */
 #define _GNU_SOURCE
 #define __EXPORTED_HEADERS__
@@ -40,15 +49,18 @@
 #include <fcntl.h>
 #include <malloc.h>
 #include <error.h>
+#include <poll.h>
 
 #include <arpa/inet.h>
 #include <sys/socket.h>
 #include <sys/mman.h>
 #include <sys/ioctl.h>
 #include <sys/syscall.h>
+#include <sys/time.h>
 
 #include <linux/memfd.h>
 #include <linux/dma-buf.h>
+#include <linux/errqueue.h>
 #include <linux/udmabuf.h>
 #include <linux/types.h>
 #include <linux/netlink.h>
@@ -70,6 +82,9 @@
 #define MSG_SOCK_DEVMEM 0x2000000
 #endif
 
+#define MAX_IOV 1024
+
+static size_t max_chunk;
 static char *server_ip;
 static char *client_ip;
 static char *port;
@@ -79,6 +94,8 @@ static int num_queues = -1;
 static char *ifname;
 static unsigned int ifindex;
 static unsigned int dmabuf_id;
+static uint32_t tx_dmabuf_id;
+static int waittime_ms = 500;
 
 struct memory_buffer {
 	int fd;
@@ -92,6 +109,8 @@ struct memory_buffer {
 struct memory_provider {
 	struct memory_buffer *(*alloc)(size_t size);
 	void (*free)(struct memory_buffer *ctx);
+	void (*memcpy_to_device)(struct memory_buffer *dst, size_t off,
+				 void *src, int n);
 	void (*memcpy_from_device)(void *dst, struct memory_buffer *src,
 				   size_t off, int n);
 };
@@ -152,6 +171,20 @@ static void udmabuf_free(struct memory_buffer *ctx)
 	free(ctx);
 }
 
+static void udmabuf_memcpy_to_device(struct memory_buffer *dst, size_t off,
+				     void *src, int n)
+{
+	struct dma_buf_sync sync = {};
+
+	sync.flags = DMA_BUF_SYNC_START | DMA_BUF_SYNC_WRITE;
+	ioctl(dst->fd, DMA_BUF_IOCTL_SYNC, &sync);
+
+	memcpy(dst->buf_mem + off, src, n);
+
+	sync.flags = DMA_BUF_SYNC_END | DMA_BUF_SYNC_WRITE;
+	ioctl(dst->fd, DMA_BUF_IOCTL_SYNC, &sync);
+}
+
 static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src,
 				       size_t off, int n)
 {
@@ -169,6 +202,7 @@ static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src,
 static struct memory_provider udmabuf_memory_provider = {
 	.alloc = udmabuf_alloc,
 	.free = udmabuf_free,
+	.memcpy_to_device = udmabuf_memcpy_to_device,
 	.memcpy_from_device = udmabuf_memcpy_from_device,
 };
 
@@ -187,14 +221,16 @@ void validate_buffer(void *line, size_t size)
 {
 	static unsigned char seed = 1;
 	unsigned char *ptr = line;
-	int errors = 0;
+	unsigned char expected;
+	static int errors;
 	size_t i;
 
 	for (i = 0; i < size; i++) {
-		if (ptr[i] != seed) {
+		expected = seed ? seed : '\n';
+		if (ptr[i] != expected) {
 			fprintf(stderr,
 				"Failed validation: expected=%u, actual=%u, index=%lu\n",
-				seed, ptr[i], i);
+				expected, ptr[i], i);
 			errors++;
 			if (errors > 20)
 				error(1, 0, "validation failed.");
@@ -393,6 +429,49 @@ err_close:
 	return -1;
 }
 
+static int bind_tx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
+			 struct ynl_sock **ys)
+{
+	struct netdev_bind_tx_req *req = NULL;
+	struct netdev_bind_tx_rsp *rsp = NULL;
+	struct ynl_error yerr;
+
+	*ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+	if (!*ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = netdev_bind_tx_req_alloc();
+	netdev_bind_tx_req_set_ifindex(req, ifindex);
+	netdev_bind_tx_req_set_fd(req, dmabuf_fd);
+
+	rsp = netdev_bind_tx(*ys, req);
+	if (!rsp) {
+		perror("netdev_bind_tx");
+		goto err_close;
+	}
+
+	if (!rsp->_present.id) {
+		perror("id not present");
+		goto err_close;
+	}
+
+	fprintf(stderr, "got tx dmabuf id=%d\n", rsp->id);
+	tx_dmabuf_id = rsp->id;
+
+	netdev_bind_tx_req_free(req);
+	netdev_bind_tx_rsp_free(rsp);
+
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg);
+	netdev_bind_tx_req_free(req);
+	ynl_sock_destroy(*ys);
+	return -1;
+}
+
 static void enable_reuseaddr(int fd)
 {
 	int opt = 1;
@@ -431,7 +510,23 @@ static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
 	return 0;
 }
 
-int do_server(struct memory_buffer *mem)
+static struct netdev_queue_id *create_queues(void)
+{
+	struct netdev_queue_id *queues;
+	size_t i = 0;
+
+	queues = calloc(num_queues, sizeof(*queues));
+	for (i = 0; i < num_queues; i++) {
+		queues[i]._present.type = 1;
+		queues[i]._present.id = 1;
+		queues[i].type = NETDEV_QUEUE_TYPE_RX;
+		queues[i].id = start_queue + i;
+	}
+
+	return queues;
+}
+
+static int do_server(struct memory_buffer *mem)
 {
 	char ctrl_data[sizeof(int) * 20000];
 	struct netdev_queue_id *queues;
@@ -448,7 +543,6 @@ int do_server(struct memory_buffer *mem)
 	char buffer[256];
 	int socket_fd;
 	int client_fd;
-	size_t i = 0;
 	int ret;
 
 	ret = parse_address(server_ip, atoi(port), &server_sin);
@@ -471,16 +565,7 @@ int do_server(struct memory_buffer *mem)
 
 	sleep(1);
 
-	queues = malloc(sizeof(*queues) * num_queues);
-
-	for (i = 0; i < num_queues; i++) {
-		queues[i]._present.type = 1;
-		queues[i]._present.id = 1;
-		queues[i].type = NETDEV_QUEUE_TYPE_RX;
-		queues[i].id = start_queue + i;
-	}
-
-	if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+	if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
 		error(1, 0, "Failed to bind\n");
 
 	tmp_mem = malloc(mem->size);
@@ -545,7 +630,6 @@ int do_server(struct memory_buffer *mem)
 			goto cleanup;
 		}
 
-		i++;
 		for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
 			if (cm->cmsg_level != SOL_SOCKET ||
 			    (cm->cmsg_type != SCM_DEVMEM_DMABUF &&
@@ -630,10 +714,8 @@ cleanup:
 
 void run_devmem_tests(void)
 {
-	struct netdev_queue_id *queues;
 	struct memory_buffer *mem;
 	struct ynl_sock *ys;
-	size_t i = 0;
 
 	mem = provider->alloc(getpagesize() * NUM_PAGES);
 
@@ -641,38 +723,24 @@ void run_devmem_tests(void)
 	if (configure_rss())
 		error(1, 0, "rss error\n");
 
-	queues = calloc(num_queues, sizeof(*queues));
-
 	if (configure_headersplit(1))
 		error(1, 0, "Failed to configure header split\n");
 
-	if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+	if (!bind_rx_queue(ifindex, mem->fd,
+			   calloc(num_queues, sizeof(struct netdev_queue_id)),
+			   num_queues, &ys))
 		error(1, 0, "Binding empty queues array should have failed\n");
 
-	for (i = 0; i < num_queues; i++) {
-		queues[i]._present.type = 1;
-		queues[i]._present.id = 1;
-		queues[i].type = NETDEV_QUEUE_TYPE_RX;
-		queues[i].id = start_queue + i;
-	}
-
 	if (configure_headersplit(0))
 		error(1, 0, "Failed to configure header split\n");
 
-	if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+	if (!bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
 		error(1, 0, "Configure dmabuf with header split off should have failed\n");
 
 	if (configure_headersplit(1))
 		error(1, 0, "Failed to configure header split\n");
 
-	for (i = 0; i < num_queues; i++) {
-		queues[i]._present.type = 1;
-		queues[i]._present.id = 1;
-		queues[i].type = NETDEV_QUEUE_TYPE_RX;
-		queues[i].id = start_queue + i;
-	}
-
-	if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+	if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
 		error(1, 0, "Failed to bind\n");
 
 	/* Deactivating a bound queue should not be legal */
@@ -685,13 +753,216 @@ void run_devmem_tests(void)
 	provider->free(mem);
 }
 
+static uint64_t gettimeofday_ms(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000ULL) + (tv.tv_usec / 1000ULL);
+}
+
+static int do_poll(int fd)
+{
+	struct pollfd pfd;
+	int ret;
+
+	pfd.revents = 0;
+	pfd.fd = fd;
+
+	ret = poll(&pfd, 1, waittime_ms);
+	if (ret == -1)
+		error(1, errno, "poll");
+
+	return ret && (pfd.revents & POLLERR);
+}
+
+static void wait_compl(int fd)
+{
+	int64_t tstop = gettimeofday_ms() + waittime_ms;
+	char control[CMSG_SPACE(100)] = {};
+	struct sock_extended_err *serr;
+	struct msghdr msg = {};
+	struct cmsghdr *cm;
+	__u32 hi, lo;
+	int ret;
+
+	msg.msg_control = control;
+	msg.msg_controllen = sizeof(control);
+
+	while (gettimeofday_ms() < tstop) {
+		if (!do_poll(fd))
+			continue;
+
+		ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+		if (ret < 0) {
+			if (errno == EAGAIN)
+				continue;
+			error(1, errno, "recvmsg(MSG_ERRQUEUE)");
+			return;
+		}
+		if (msg.msg_flags & MSG_CTRUNC)
+			error(1, 0, "MSG_CTRUNC\n");
+
+		for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+			if (cm->cmsg_level != SOL_IP &&
+			    cm->cmsg_level != SOL_IPV6)
+				continue;
+			if (cm->cmsg_level == SOL_IP &&
+			    cm->cmsg_type != IP_RECVERR)
+				continue;
+			if (cm->cmsg_level == SOL_IPV6 &&
+			    cm->cmsg_type != IPV6_RECVERR)
+				continue;
+
+			serr = (void *)CMSG_DATA(cm);
+			if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY)
+				error(1, 0, "wrong origin %u", serr->ee_origin);
+			if (serr->ee_errno != 0)
+				error(1, 0, "wrong errno %d", serr->ee_errno);
+
+			hi = serr->ee_data;
+			lo = serr->ee_info;
+
+			fprintf(stderr, "tx complete [%d,%d]\n", lo, hi);
+			return;
+		}
+	}
+
+	error(1, 0, "did not receive tx completion");
+}
+
+static int do_client(struct memory_buffer *mem)
+{
+	char ctrl_data[CMSG_SPACE(sizeof(__u32))];
+	struct sockaddr_in6 server_sin;
+	struct sockaddr_in6 client_sin;
+	struct ynl_sock *ys = NULL;
+	struct iovec iov[MAX_IOV];
+	struct msghdr msg = {};
+	ssize_t line_size = 0;
+	struct cmsghdr *cmsg;
+	char *line = NULL;
+	unsigned long mid;
+	size_t len = 0;
+	int socket_fd;
+	__u32 ddmabuf;
+	int opt = 1;
+	int ret;
+
+	ret = parse_address(server_ip, atoi(port), &server_sin);
+	if (ret < 0)
+		error(1, 0, "parse server address");
+
+	socket_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (socket_fd < 0)
+		error(1, socket_fd, "create socket");
+
+	enable_reuseaddr(socket_fd);
+
+	ret = setsockopt(socket_fd, SOL_SOCKET, SO_BINDTODEVICE, ifname,
+			 strlen(ifname) + 1);
+	if (ret)
+		error(1, errno, "bindtodevice");
+
+	if (bind_tx_queue(ifindex, mem->fd, &ys))
+		error(1, 0, "Failed to bind\n");
+
+	if (client_ip) {
+		ret = parse_address(client_ip, atoi(port), &client_sin);
+		if (ret < 0)
+			error(1, 0, "parse client address");
+
+		ret = bind(socket_fd, &client_sin, sizeof(client_sin));
+		if (ret)
+			error(1, errno, "bind");
+	}
+
+	ret = setsockopt(socket_fd, SOL_SOCKET, SO_ZEROCOPY, &opt, sizeof(opt));
+	if (ret)
+		error(1, errno, "set sock opt");
+
+	fprintf(stderr, "Connect to %s %d (via %s)\n", server_ip,
+		ntohs(server_sin.sin6_port), ifname);
+
+	ret = connect(socket_fd, &server_sin, sizeof(server_sin));
+	if (ret)
+		error(1, errno, "connect");
+
+	while (1) {
+		free(line);
+		line = NULL;
+		line_size = getline(&line, &len, stdin);
+
+		if (line_size < 0)
+			break;
+
+		if (max_chunk) {
+			msg.msg_iovlen =
+				(line_size + max_chunk - 1) / max_chunk;
+			if (msg.msg_iovlen > MAX_IOV)
+				error(1, 0,
+				      "can't partition %zd bytes into maximum of %d chunks",
+				      line_size, MAX_IOV);
+
+			for (int i = 0; i < msg.msg_iovlen; i++) {
+				iov[i].iov_base = (void *)(i * max_chunk);
+				iov[i].iov_len = max_chunk;
+			}
+
+			iov[msg.msg_iovlen - 1].iov_len =
+				line_size - (msg.msg_iovlen - 1) * max_chunk;
+		} else {
+			iov[0].iov_base = 0;
+			iov[0].iov_len = line_size;
+			msg.msg_iovlen = 1;
+		}
+
+		msg.msg_iov = iov;
+		provider->memcpy_to_device(mem, 0, line, line_size);
+
+		msg.msg_control = ctrl_data;
+		msg.msg_controllen = sizeof(ctrl_data);
+
+		cmsg = CMSG_FIRSTHDR(&msg);
+		cmsg->cmsg_level = SOL_SOCKET;
+		cmsg->cmsg_type = SCM_DEVMEM_DMABUF;
+		cmsg->cmsg_len = CMSG_LEN(sizeof(__u32));
+
+		ddmabuf = tx_dmabuf_id;
+
+		*((__u32 *)CMSG_DATA(cmsg)) = ddmabuf;
+
+		ret = sendmsg(socket_fd, &msg, MSG_ZEROCOPY);
+		if (ret < 0)
+			error(1, errno, "Failed sendmsg");
+
+		fprintf(stderr, "sendmsg_ret=%d\n", ret);
+
+		if (ret != line_size)
+			error(1, errno, "Did not send all bytes %d vs %zd", ret,
+			      line_size);
+
+		wait_compl(socket_fd);
+	}
+
+	fprintf(stderr, "%s: tx ok\n", TEST_PREFIX);
+
+	free(line);
+	close(socket_fd);
+
+	if (ys)
+		ynl_sock_destroy(ys);
+
+	return 0;
+}
+
 int main(int argc, char *argv[])
 {
 	struct memory_buffer *mem;
 	int is_server = 0, opt;
 	int ret;
 
-	while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:")) != -1) {
+	while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:z:")) != -1) {
 		switch (opt) {
 		case 'l':
 			is_server = 1;
@@ -717,6 +988,9 @@ int main(int argc, char *argv[])
 		case 'f':
 			ifname = optarg;
 			break;
+		case 'z':
+			max_chunk = atoi(optarg);
+			break;
 		case '?':
 			fprintf(stderr, "unknown option: %c\n", optopt);
 			break;
@@ -728,6 +1002,8 @@ int main(int argc, char *argv[])
 
 	ifindex = if_nametoindex(ifname);
 
+	fprintf(stderr, "using ifindex=%u\n", ifindex);
+
 	if (!server_ip && !client_ip) {
 		if (start_queue < 0 && num_queues < 0) {
 			num_queues = rxq_num(ifindex);
@@ -778,7 +1054,7 @@ int main(int argc, char *argv[])
 		error(1, 0, "Missing -p argument\n");
 
 	mem = provider->alloc(getpagesize() * NUM_PAGES);
-	ret = is_server ? do_server(mem) : 1;
+	ret = is_server ? do_server(mem) : do_client(mem);
 	provider->free(mem);
 
 	return ret;
diff --git a/tools/testing/selftests/drivers/net/hw/nic_link_layer.py b/tools/testing/selftests/drivers/net/hw/nic_link_layer.py
deleted file mode 100644
index efd921180532..000000000000
--- a/tools/testing/selftests/drivers/net/hw/nic_link_layer.py
+++ /dev/null
@@ -1,113 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-License-Identifier: GPL-2.0
-
-#Introduction:
-#This file has basic link layer tests for generic NIC drivers.
-#The test comprises of auto-negotiation, speed and duplex checks.
-#
-#Setup:
-#Connect the DUT PC with NIC card to partner pc back via ethernet medium of your choice(RJ45, T1)
-#
-#        DUT PC                                              Partner PC
-#┌───────────────────────┐                         ┌──────────────────────────┐
-#│                       │                         │                          │
-#│                       │                         │                          │
-#│           ┌───────────┐                         │                          │
-#│           │DUT NIC    │         Eth             │                          │
-#│           │Interface ─┼─────────────────────────┼─    any eth Interface    │
-#│           └───────────┘                         │                          │
-#│                       │                         │                          │
-#│                       │                         │                          │
-#└───────────────────────┘                         └──────────────────────────┘
-#
-#Configurations:
-#Required minimum ethtool version is 6.10 (supports json)
-#Default values:
-#time_delay = 8 #time taken to wait for transitions to happen, in seconds.
-
-import time
-import argparse
-from lib.py import ksft_run, ksft_exit, ksft_pr, ksft_eq
-from lib.py import KsftFailEx, KsftSkipEx
-from lib.py import NetDrvEpEnv
-from lib.py import LinkConfig
-
-def _pre_test_checks(cfg: object, link_config: LinkConfig) -> None:
-    if link_config.partner_netif is None:
-        KsftSkipEx("Partner interface is not available")
-    if not link_config.check_autoneg_supported() or not link_config.check_autoneg_supported(remote=True):
-        KsftSkipEx(f"Auto-negotiation not supported for interface {cfg.ifname} or {link_config.partner_netif}")
-    if not link_config.verify_link_up():
-        raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-
-def verify_autonegotiation(cfg: object, expected_state: str, link_config: LinkConfig) -> None:
-    if not link_config.verify_link_up():
-        raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-    """Verifying the autonegotiation state in partner"""
-    partner_autoneg_output = link_config.get_ethtool_field("auto-negotiation", remote=True)
-    if partner_autoneg_output is None:
-        KsftSkipEx(f"Auto-negotiation state not available for interface {link_config.partner_netif}")
-    partner_autoneg_state = "on" if partner_autoneg_output is True else "off"
-
-    ksft_eq(partner_autoneg_state, expected_state)
-
-    """Verifying the autonegotiation state of local"""
-    autoneg_output = link_config.get_ethtool_field("auto-negotiation")
-    if autoneg_output is None:
-        KsftSkipEx(f"Auto-negotiation state not available for interface {cfg.ifname}")
-    actual_state = "on" if autoneg_output is True else "off"
-
-    ksft_eq(actual_state, expected_state)
-
-    """Verifying the link establishment"""
-    link_available = link_config.get_ethtool_field("link-detected")
-    if link_available is None:
-        KsftSkipEx(f"Link status not available for interface {cfg.ifname}")
-    if link_available != True:
-        raise KsftSkipEx("Link not established at interface {cfg.ifname} after changing auto-negotiation")
-
-def test_autonegotiation(cfg: object, link_config: LinkConfig, time_delay: int) -> None:
-    _pre_test_checks(cfg, link_config)
-    for state in ["off", "on"]:
-        if not link_config.set_autonegotiation_state(state, remote=True):
-            raise KsftSkipEx(f"Unable to set auto-negotiation state for interface {link_config.partner_netif}")
-        if not link_config.set_autonegotiation_state(state):
-            raise KsftSkipEx(f"Unable to set auto-negotiation state for interface {cfg.ifname}")
-        time.sleep(time_delay)
-        verify_autonegotiation(cfg, state, link_config)
-
-def test_network_speed(cfg: object, link_config: LinkConfig, time_delay: int) -> None:
-    _pre_test_checks(cfg, link_config)
-    common_link_modes = link_config.common_link_modes
-    if not common_link_modes:
-        KsftSkipEx("No common link modes exist")
-    speeds, duplex_modes = link_config.get_speed_duplex_values(common_link_modes)
-
-    if speeds and duplex_modes and len(speeds) == len(duplex_modes):
-        for idx in range(len(speeds)):
-            speed = speeds[idx]
-            duplex = duplex_modes[idx]
-            if not link_config.set_speed_and_duplex(speed, duplex):
-                raise KsftFailEx(f"Unable to set speed and duplex parameters for {cfg.ifname}")
-            time.sleep(time_delay)
-            if not link_config.verify_speed_and_duplex(speed, duplex):
-                raise KsftSkipEx(f"Error occurred while verifying speed and duplex states for interface {cfg.ifname}")
-    else:
-        if not speeds or not duplex_modes:
-            KsftSkipEx(f"No supported speeds or duplex modes found for interface {cfg.ifname}")
-        else:
-            KsftSkipEx("Mismatch in the number of speeds and duplex modes")
-
-def main() -> None:
-    parser = argparse.ArgumentParser(description="Run basic link layer tests for NIC driver")
-    parser.add_argument('--time-delay', type=int, default=8, help='Time taken to wait for transitions to happen(in seconds). Default is 8 seconds.')
-    args = parser.parse_args()
-    time_delay = args.time_delay
-    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
-        link_config = LinkConfig(cfg)
-        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, link_config, time_delay,))
-        link_config.reset_interface()
-    ksft_exit()
-
-if __name__ == "__main__":
-    main()
diff --git a/tools/testing/selftests/drivers/net/hw/nic_performance.py b/tools/testing/selftests/drivers/net/hw/nic_performance.py
deleted file mode 100644
index 201403b76ea3..000000000000
--- a/tools/testing/selftests/drivers/net/hw/nic_performance.py
+++ /dev/null
@@ -1,137 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-License-Identifier: GPL-2.0
-
-#Introduction:
-#This file has basic performance test for generic NIC drivers.
-#The test comprises of throughput check for TCP and UDP streams.
-#
-#Setup:
-#Connect the DUT PC with NIC card to partner pc back via ethernet medium of your choice(RJ45, T1)
-#
-#        DUT PC                                              Partner PC
-#┌───────────────────────┐                         ┌──────────────────────────┐
-#│                       │                         │                          │
-#│                       │                         │                          │
-#│           ┌───────────┐                         │                          │
-#│           │DUT NIC    │         Eth             │                          │
-#│           │Interface ─┼─────────────────────────┼─    any eth Interface    │
-#│           └───────────┘                         │                          │
-#│                       │                         │                          │
-#│                       │                         │                          │
-#└───────────────────────┘                         └──────────────────────────┘
-#
-#Configurations:
-#To prevent interruptions, Add ethtool, ip to the sudoers list in remote PC and get the ssh key from remote.
-#Required minimum ethtool version is 6.10
-#Change the below configuration based on your hw needs.
-# """Default values"""
-#time_delay = 8 #time taken to wait for transitions to happen, in seconds.
-#test_duration = 10  #performance test duration for the throughput check, in seconds.
-#send_throughput_threshold = 80 #percentage of send throughput required to pass the check
-#receive_throughput_threshold = 50 #percentage of receive throughput required to pass the check
-
-import time
-import json
-import argparse
-from lib.py import ksft_run, ksft_exit, ksft_pr, ksft_true
-from lib.py import KsftFailEx, KsftSkipEx, GenerateTraffic
-from lib.py import NetDrvEpEnv, bkg, wait_port_listen
-from lib.py import cmd
-from lib.py import LinkConfig
-
-class TestConfig:
-    def __init__(self, time_delay: int, test_duration: int, send_throughput_threshold: int, receive_throughput_threshold: int) -> None:
-        self.time_delay = time_delay
-        self.test_duration = test_duration
-        self.send_throughput_threshold = send_throughput_threshold
-        self.receive_throughput_threshold = receive_throughput_threshold
-
-def _pre_test_checks(cfg: object, link_config: LinkConfig) -> None:
-    if not link_config.verify_link_up():
-        KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-    common_link_modes = link_config.common_link_modes
-    if common_link_modes is None:
-        KsftSkipEx("No common link modes found")
-    if link_config.partner_netif == None:
-        KsftSkipEx("Partner interface is not available")
-    if link_config.check_autoneg_supported():
-        KsftSkipEx("Auto-negotiation not supported by local")
-    if link_config.check_autoneg_supported(remote=True):
-        KsftSkipEx("Auto-negotiation not supported by remote")
-    cfg.require_cmd("iperf3", remote=True)
-
-def check_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, protocol: str, traffic: GenerateTraffic) -> None:
-    common_link_modes = link_config.common_link_modes
-    speeds, duplex_modes = link_config.get_speed_duplex_values(common_link_modes)
-    """Test duration in seconds"""
-    duration = test_config.test_duration
-
-    ksft_pr(f"{protocol} test")
-    test_type = "-u" if protocol == "UDP" else ""
-
-    send_throughput = []
-    receive_throughput = []
-    for idx in range(0, len(speeds)):
-        if link_config.set_speed_and_duplex(speeds[idx], duplex_modes[idx]) == False:
-            raise KsftFailEx(f"Not able to set speed and duplex parameters for {cfg.ifname}")
-        time.sleep(test_config.time_delay)
-        if not link_config.verify_link_up():
-            raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-
-        send_command=f"{test_type} -b 0 -t {duration} --json"
-        receive_command=f"{test_type} -b 0 -t {duration} --reverse --json"
-
-        send_result = traffic.run_remote_test(cfg, command=send_command)
-        if send_result.ret != 0:
-            raise KsftSkipEx("Error occurred during data transmit: {send_result.stdout}")
-
-        send_output = send_result.stdout
-        send_data = json.loads(send_output)
-
-        """Convert throughput to Mbps"""
-        send_throughput.append(round(send_data['end']['sum_sent']['bits_per_second'] / 1e6, 2))
-        ksft_pr(f"{protocol}: Send throughput: {send_throughput[idx]} Mbps")
-
-        receive_result = traffic.run_remote_test(cfg, command=receive_command)
-        if receive_result.ret != 0:
-            raise KsftSkipEx("Error occurred during data receive: {receive_result.stdout}")
-
-        receive_output = receive_result.stdout
-        receive_data = json.loads(receive_output)
-
-        """Convert throughput to Mbps"""
-        receive_throughput.append(round(receive_data['end']['sum_received']['bits_per_second'] / 1e6, 2))
-        ksft_pr(f"{protocol}: Receive throughput: {receive_throughput[idx]} Mbps")
-
-    """Check whether throughput is not below the threshold (default values set at start)"""
-    for idx in range(0, len(speeds)):
-        send_threshold = float(speeds[idx]) * float(test_config.send_throughput_threshold / 100)
-        receive_threshold = float(speeds[idx]) * float(test_config.receive_throughput_threshold / 100)
-        ksft_true(send_throughput[idx] >= send_threshold, f"{protocol}: Send throughput is below threshold for {speeds[idx]} Mbps in {duplex_modes[idx]} duplex")
-        ksft_true(receive_throughput[idx] >= receive_threshold, f"{protocol}: Receive throughput is below threshold for {speeds[idx]} Mbps in {duplex_modes[idx]} duplex")
-
-def test_tcp_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, traffic: GenerateTraffic) -> None:
-    _pre_test_checks(cfg, link_config)
-    check_throughput(cfg, link_config, test_config, 'TCP', traffic)
-
-def test_udp_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, traffic: GenerateTraffic) -> None:
-    _pre_test_checks(cfg, link_config)
-    check_throughput(cfg, link_config, test_config, 'UDP', traffic)
-
-def main() -> None:
-    parser = argparse.ArgumentParser(description="Run basic performance test for NIC driver")
-    parser.add_argument('--time-delay', type=int, default=8, help='Time taken to wait for transitions to happen(in seconds). Default is 8 seconds.')
-    parser.add_argument('--test-duration', type=int, default=10, help='Performance test duration for the throughput check, in seconds. Default is 10 seconds.')
-    parser.add_argument('--stt', type=int, default=80, help='Send throughput Threshold: Percentage of send throughput upon actual throughput required to pass the throughput check (in percentage). Default is 80.')
-    parser.add_argument('--rtt', type=int, default=50, help='Receive throughput Threshold: Percentage of receive throughput upon actual throughput required to pass the throughput check (in percentage). Default is 50.')
-    args=parser.parse_args()
-    test_config = TestConfig(args.time_delay, args.test_duration, args.stt, args.rtt)
-    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
-        traffic = GenerateTraffic(cfg)
-        link_config = LinkConfig(cfg)
-        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, link_config, test_config, traffic,  ))
-        link_config.reset_interface()
-    ksft_exit()
-
-if __name__ == "__main__":
-    main()
diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
index 53bb08cc29ec..f439c434ba36 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
@@ -32,6 +32,11 @@ def test_rss_input_xfrm(cfg, ipver):
     if multiprocessing.cpu_count() < 2:
         raise KsftSkipEx("Need at least two CPUs to test symmetric RSS hash")
 
+    cfg.require_cmd("socat", remote=True)
+
+    if not hasattr(socket, "SO_INCOMING_CPU"):
+        raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11")
+
     input_xfrm = cfg.ethnl.rss_get(
         {'header': {'dev-name': cfg.ifname}}).get('input_xfrm')
 
diff --git a/tools/testing/selftests/drivers/net/hw/xsk_reconfig.py b/tools/testing/selftests/drivers/net/hw/xsk_reconfig.py
new file mode 100755
index 000000000000..d19d1d518208
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/xsk_reconfig.py
@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+# This is intended to be run on a virtio-net guest interface.
+# The test binds the XDP socket to the interface without setting
+# the fill ring to trigger delayed refill_work. This helps to
+# make it easier to reproduce the deadlock when XDP program,
+# XDP socket bind/unbind, rx ring resize race with refill_work on
+# the buggy kernel.
+#
+# The Qemu command to setup virtio-net
+# -netdev tap,id=hostnet1,vhost=on,script=no,downscript=no
+# -device virtio-net-pci,netdev=hostnet1,iommu_platform=on,disable-legacy=on
+
+from lib.py import ksft_exit, ksft_run
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import NetDrvEnv
+from lib.py import bkg, ip, cmd, ethtool
+import time
+
+def _get_rx_ring_entries(cfg):
+    output = ethtool(f"-g {cfg.ifname}", json=True)
+    return output[0]["rx"]
+
+def setup_xsk(cfg, xdp_queue_id = 0) -> bkg:
+    # Probe for support
+    xdp = cmd(f'{cfg.net_lib_dir / "xdp_helper"} - -', fail=False)
+    if xdp.ret == 255:
+        raise KsftSkipEx('AF_XDP unsupported')
+    elif xdp.ret > 0:
+        raise KsftFailEx('unable to create AF_XDP socket')
+
+    try:
+        return bkg(f'{cfg.net_lib_dir / "xdp_helper"} {cfg.ifindex} ' \
+                   '{xdp_queue_id} -z', ksft_wait=3)
+    except:
+        raise KsftSkipEx('Failed to bind XDP socket in zerocopy.\n' \
+                         'Please consider adding iommu_platform=on ' \
+                         'when setting up virtio-net-pci')
+
+def check_xdp_bind(cfg):
+    with setup_xsk(cfg):
+        ip(f"link set dev %s xdp obj %s sec xdp" %
+           (cfg.ifname, cfg.net_lib_dir / "xdp_dummy.bpf.o"))
+        ip(f"link set dev %s xdp off" % cfg.ifname)
+
+def check_rx_resize(cfg):
+    with setup_xsk(cfg):
+        rx_ring = _get_rx_ring_entries(cfg)
+        ethtool(f"-G %s rx %d" % (cfg.ifname, rx_ring // 2))
+        ethtool(f"-G %s rx %d" % (cfg.ifname, rx_ring))
+
+def main():
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        ksft_run([check_xdp_bind, check_rx_resize],
+                 args=(cfg, ))
+    ksft_exit()
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index ad5ff645183a..3bccddf8cbc5 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -12,7 +12,7 @@ from .remote import Remote
 
 class NetDrvEnvBase:
     """
-    Base class for a NIC / host envirnoments
+    Base class for a NIC / host environments
 
     Attributes:
       test_dir: Path to the source directory of the test
diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py
index da5af2c680fa..d9c10613ae67 100644
--- a/tools/testing/selftests/drivers/net/lib/py/load.py
+++ b/tools/testing/selftests/drivers/net/lib/py/load.py
@@ -2,7 +2,7 @@
 
 import time
 
-from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen, bkg
+from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen
 
 class GenerateTraffic:
     def __init__(self, env, port=None):
@@ -23,24 +23,6 @@ class GenerateTraffic:
             self.stop(verbose=True)
             raise Exception("iperf3 traffic did not ramp up")
 
-    def run_remote_test(self, env: object, port=None, command=None):
-        if port is None:
-            port = rand_port()
-        try:
-            server_cmd = f"iperf3 -s 1 -p {port} --one-off"
-            with bkg(server_cmd, host=env.remote):
-                #iperf3 opens TCP connection as default in server
-                #-u to be specified in client command for UDP
-                wait_port_listen(port, host=env.remote)
-        except Exception as e:
-            raise Exception(f"Unexpected error occurred while running server command: {e}")
-        try:
-            client_cmd = f"iperf3 -c {env.remote_addr} -p {port} {command}"
-            proc = cmd(client_cmd)
-            return proc
-        except Exception as e:
-            raise Exception(f"Unexpected error occurred while running client command: {e}")
-
     def _wait_pkts(self, pkt_cnt=None, pps=None):
         """
         Wait until we've seen pkt_cnt or until traffic ramps up to pps.
diff --git a/tools/testing/selftests/drivers/net/napi_id.py b/tools/testing/selftests/drivers/net/napi_id.py
new file mode 100755
index 000000000000..356bac46ba04
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/napi_id.py
@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_eq, NetDrvEpEnv
+from lib.py import bkg, cmd, rand_port, NetNSEnter
+
+def test_napi_id(cfg) -> None:
+    port = rand_port()
+    listen_cmd = f"{cfg.test_dir}/napi_id_helper {cfg.addr_v['4']} {port}"
+
+    with bkg(listen_cmd, ksft_wait=3) as server:
+        cmd(f"echo a | socat - TCP:{cfg.addr_v['4']}:{port}", host=cfg.remote, shell=True)
+
+    ksft_eq(0, server.ret)
+
+def main() -> None:
+    with NetDrvEpEnv(__file__) as cfg:
+        ksft_run([test_napi_id], args=(cfg,))
+    ksft_exit()
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/napi_id_helper.c b/tools/testing/selftests/drivers/net/napi_id_helper.c
new file mode 100644
index 000000000000..eecd610c2109
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/napi_id_helper.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <sys/socket.h>
+
+#include "../../net/lib/ksft.h"
+
+int main(int argc, char *argv[])
+{
+	struct sockaddr_in address;
+	unsigned int napi_id;
+	unsigned int port;
+	socklen_t optlen;
+	char buf[1024];
+	int opt = 1;
+	int server;
+	int client;
+	int ret;
+
+	server = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+	if (server < 0) {
+		perror("socket creation failed");
+		if (errno == EAFNOSUPPORT)
+			return -1;
+		return 1;
+	}
+
+	port = atoi(argv[2]);
+
+	if (setsockopt(server, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt))) {
+		perror("setsockopt");
+		return 1;
+	}
+
+	address.sin_family = AF_INET;
+	inet_pton(AF_INET, argv[1], &address.sin_addr);
+	address.sin_port = htons(port);
+
+	if (bind(server, (struct sockaddr *)&address, sizeof(address)) < 0) {
+		perror("bind failed");
+		return 1;
+	}
+
+	if (listen(server, 1) < 0) {
+		perror("listen");
+		return 1;
+	}
+
+	ksft_ready();
+
+	client = accept(server, NULL, 0);
+	if (client < 0) {
+		perror("accept");
+		return 1;
+	}
+
+	optlen = sizeof(napi_id);
+	ret = getsockopt(client, SOL_SOCKET, SO_INCOMING_NAPI_ID, &napi_id,
+			 &optlen);
+	if (ret != 0) {
+		perror("getsockopt");
+		return 1;
+	}
+
+	read(client, buf, 1024);
+
+	ksft_wait();
+
+	if (napi_id == 0) {
+		fprintf(stderr, "napi ID is 0\n");
+		return 1;
+	}
+
+	close(client);
+	close(server);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/drivers/net/ocelot/psfp.sh b/tools/testing/selftests/drivers/net/ocelot/psfp.sh
index bed748dde4b0..8972f42dfe03 100755
--- a/tools/testing/selftests/drivers/net/ocelot/psfp.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/psfp.sh
@@ -266,18 +266,14 @@ run_test()
 		"${base_time}" \
 		"${CYCLE_TIME_NS}" \
 		"${SHIFT_TIME_NS}" \
+		"${GATE_DURATION_NS}" \
 		"${NUM_PKTS}" \
 		"${STREAM_VID}" \
 		"${STREAM_PRIO}" \
 		"" \
 		"${isochron_dat}"
 
-	# Count all received packets by looking at the non-zero RX timestamps
-	received=$(isochron report \
-		--input-file "${isochron_dat}" \
-		--printf-format "%u\n" --printf-args "R" | \
-		grep -w -v '0' | wc -l)
-
+	received=$(isochron_report_num_received "${isochron_dat}")
 	if [ "${received}" = "${expected}" ]; then
 		RET=0
 	else
diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py
index 4b6822866066..e0f114612c1a 100755
--- a/tools/testing/selftests/drivers/net/ping.py
+++ b/tools/testing/selftests/drivers/net/ping.py
@@ -9,11 +9,11 @@ from lib.py import EthtoolFamily, NetDrvEpEnv
 from lib.py import bkg, cmd, wait_port_listen, rand_port
 from lib.py import defer, ethtool, ip
 
-remote_ifname=""
 no_sleep=False
 
 def _test_v4(cfg) -> None:
-    cfg.require_ipver("4")
+    if not cfg.addr_v["4"]:
+        return
 
     cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["4"])
     cmd("ping -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
@@ -21,7 +21,8 @@ def _test_v4(cfg) -> None:
     cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
 
 def _test_v6(cfg) -> None:
-    cfg.require_ipver("6")
+    if not cfg.addr_v["6"]:
+        return
 
     cmd("ping -c 1 -W5 " + cfg.remote_addr_v["6"])
     cmd("ping -c 1 -W5 " + cfg.addr_v["6"], host=cfg.remote)
@@ -49,6 +50,16 @@ def _test_tcp(cfg) -> None:
         cmd(f"echo {test_string} | socat -t 2 -u STDIN TCP:{cfg.remote_baddr}:{port}", shell=True)
     ksft_eq(nc.stdout.strip(), test_string)
 
+def _schedule_checksum_reset(cfg, netnl) -> None:
+    features = ethtool(f"-k {cfg.ifname}", json=True)
+    setting = ""
+    for side in ["tx", "rx"]:
+        f = features[0][side + "-checksumming"]
+        if not f["fixed"]:
+            setting += " " + side
+            setting += " " + ("on" if f["requested"] or f["active"] else "off")
+    defer(ethtool, f" -K {cfg.ifname} " + setting)
+
 def _set_offload_checksum(cfg, netnl, on) -> None:
     try:
         ethtool(f" -K {cfg.ifname} rx {on} tx {on} ")
@@ -57,7 +68,7 @@ def _set_offload_checksum(cfg, netnl, on) -> None:
 
 def _set_xdp_generic_sb_on(cfg) -> None:
     prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
-    cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
     cmd(f"ip link set dev {cfg.ifname} mtu 1500 xdpgeneric obj {prog} sec xdp", shell=True)
     defer(cmd, f"ip link set dev {cfg.ifname} xdpgeneric off")
 
@@ -66,8 +77,8 @@ def _set_xdp_generic_sb_on(cfg) -> None:
 
 def _set_xdp_generic_mb_on(cfg) -> None:
     prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
-    cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
-    defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+    defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
     ip("link set dev %s mtu 9000 xdpgeneric obj %s sec xdp.frags" % (cfg.ifname, prog))
     defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdpgeneric off")
 
@@ -76,7 +87,7 @@ def _set_xdp_generic_mb_on(cfg) -> None:
 
 def _set_xdp_native_sb_on(cfg) -> None:
     prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
-    cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
     cmd(f"ip -j link set dev {cfg.ifname} mtu 1500 xdp obj {prog} sec xdp", shell=True)
     defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
     xdp_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
@@ -93,8 +104,8 @@ def _set_xdp_native_sb_on(cfg) -> None:
 
 def _set_xdp_native_mb_on(cfg) -> None:
     prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
-    cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
-    defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+    defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
     try:
         cmd(f"ip link set dev {cfg.ifname} mtu 9000 xdp obj {prog} sec xdp.frags", shell=True)
         defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
@@ -112,18 +123,15 @@ def _set_xdp_offload_on(cfg) -> None:
     except Exception as e:
         raise KsftSkipEx('device does not support offloaded XDP')
     defer(ip, f"link set dev {cfg.ifname} xdpoffload off")
-    cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
 
     if no_sleep != True:
         time.sleep(10)
 
 def get_interface_info(cfg) -> None:
-    global remote_ifname
     global no_sleep
 
-    remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_addr_v['4']} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout
-    remote_ifname = remote_info.rstrip('\n')
-    if remote_ifname == "":
+    if cfg.remote_ifname == "":
         raise KsftFailEx('Can not get remote interface')
     local_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
     if 'parentbus' in local_info and local_info['parentbus'] == "netdevsim":
@@ -136,19 +144,32 @@ def set_interface_init(cfg) -> None:
     cmd(f"ip link set dev {cfg.ifname} xdp off ", shell=True)
     cmd(f"ip link set dev {cfg.ifname} xdpgeneric off ", shell=True)
     cmd(f"ip link set dev {cfg.ifname} xdpoffload off", shell=True)
-    cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+
+def test_default_v4(cfg, netnl) -> None:
+    cfg.require_ipver("4")
 
-def test_default(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
     _set_offload_checksum(cfg, netnl, "off")
     _test_v4(cfg)
-    _test_v6(cfg)
     _test_tcp(cfg)
     _set_offload_checksum(cfg, netnl, "on")
     _test_v4(cfg)
+    _test_tcp(cfg)
+
+def test_default_v6(cfg, netnl) -> None:
+    cfg.require_ipver("6")
+
+    _schedule_checksum_reset(cfg, netnl)
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
     _test_v6(cfg)
     _test_tcp(cfg)
 
 def test_xdp_generic_sb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
     _set_xdp_generic_sb_on(cfg)
     _set_offload_checksum(cfg, netnl, "off")
     _test_v4(cfg)
@@ -160,6 +181,7 @@ def test_xdp_generic_sb(cfg, netnl) -> None:
     _test_tcp(cfg)
 
 def test_xdp_generic_mb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
     _set_xdp_generic_mb_on(cfg)
     _set_offload_checksum(cfg, netnl, "off")
     _test_v4(cfg)
@@ -171,6 +193,7 @@ def test_xdp_generic_mb(cfg, netnl) -> None:
     _test_tcp(cfg)
 
 def test_xdp_native_sb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
     _set_xdp_native_sb_on(cfg)
     _set_offload_checksum(cfg, netnl, "off")
     _test_v4(cfg)
@@ -182,6 +205,7 @@ def test_xdp_native_sb(cfg, netnl) -> None:
     _test_tcp(cfg)
 
 def test_xdp_native_mb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
     _set_xdp_native_mb_on(cfg)
     _set_offload_checksum(cfg, netnl, "off")
     _test_v4(cfg)
@@ -202,7 +226,8 @@ def main() -> None:
     with NetDrvEpEnv(__file__) as cfg:
         get_interface_info(cfg)
         set_interface_init(cfg)
-        ksft_run([test_default,
+        ksft_run([test_default_v4,
+                  test_default_v6,
                   test_xdp_generic_sb,
                   test_xdp_generic_mb,
                   test_xdp_native_sb,
diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index 06abd3f233e1..236005290a33 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -26,13 +26,13 @@ def nl_get_queues(cfg, nl, qtype='rx'):
 
 def check_xsk(cfg, nl, xdp_queue_id=0) -> None:
     # Probe for support
-    xdp = cmd(f'{cfg.test_dir / "xdp_helper"} - -', fail=False)
+    xdp = cmd(f'{cfg.net_lib_dir / "xdp_helper"} - -', fail=False)
     if xdp.ret == 255:
         raise KsftSkipEx('AF_XDP unsupported')
     elif xdp.ret > 0:
         raise KsftFailEx('unable to create AF_XDP socket')
 
-    with bkg(f'{cfg.test_dir / "xdp_helper"} {cfg.ifindex} {xdp_queue_id}',
+    with bkg(f'{cfg.net_lib_dir / "xdp_helper"} {cfg.ifindex} {xdp_queue_id}',
              ksft_wait=3):
 
         rx = tx = False
diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile
index 2d5a76d99181..eaf6938f100e 100644
--- a/tools/testing/selftests/drivers/net/team/Makefile
+++ b/tools/testing/selftests/drivers/net/team/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for net selftests
 
-TEST_PROGS := dev_addr_lists.sh
+TEST_PROGS := dev_addr_lists.sh propagation.sh
 
 TEST_INCLUDES := \
 	../bonding/lag_lib.sh \
diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config
index b5e3a3aad4bf..636b3525b679 100644
--- a/tools/testing/selftests/drivers/net/team/config
+++ b/tools/testing/selftests/drivers/net/team/config
@@ -1,5 +1,6 @@
 CONFIG_DUMMY=y
 CONFIG_IPV6=y
 CONFIG_MACVLAN=y
+CONFIG_NETDEVSIM=m
 CONFIG_NET_TEAM=y
 CONFIG_NET_TEAM_MODE_LOADBALANCE=y
diff --git a/tools/testing/selftests/drivers/net/team/propagation.sh b/tools/testing/selftests/drivers/net/team/propagation.sh
new file mode 100755
index 000000000000..4bea75b79878
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/propagation.sh
@@ -0,0 +1,80 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+NSIM_LRO_ID=$((256 + RANDOM % 256))
+NSIM_LRO_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_LRO_ID
+
+NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device
+NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device
+
+cleanup()
+{
+	set +e
+	ip link del dummyteam &>/dev/null
+	ip link del team0 &>/dev/null
+	echo $NSIM_LRO_ID > $NSIM_DEV_SYS_DEL
+	modprobe -r netdevsim
+}
+
+# Trigger LRO propagation to the lower.
+# https://lore.kernel.org/netdev/aBvOpkIoxcr9PfDg@mini-arch/
+team_lro()
+{
+	# using netdevsim because it supports NETIF_F_LRO
+	NSIM_LRO_NAME=$(find $NSIM_LRO_SYS/net -maxdepth 1 -type d ! \
+		-path $NSIM_LRO_SYS/net -exec basename {} \;)
+
+	ip link add name team0 type team
+	ip link set $NSIM_LRO_NAME down
+	ip link set dev $NSIM_LRO_NAME master team0
+	ip link set team0 up
+	ethtool -K team0 large-receive-offload off
+
+	ip link del team0
+}
+
+# Trigger promisc propagation to the lower during IFLA_MASTER.
+# https://lore.kernel.org/netdev/20250506032328.3003050-1-sdf@fomichev.me/
+team_promisc()
+{
+	ip link add name dummyteam type dummy
+	ip link add name team0 type team
+	ip link set dummyteam down
+	ip link set team0 promisc on
+	ip link set dev dummyteam master team0
+	ip link set team0 up
+
+	ip link del team0
+	ip link del dummyteam
+}
+
+# Trigger promisc propagation to the lower via netif_change_flags (aka
+# ndo_change_rx_flags).
+# https://lore.kernel.org/netdev/20250514220319.3505158-1-stfomichev@gmail.com/
+team_change_flags()
+{
+	ip link add name dummyteam type dummy
+	ip link add name team0 type team
+	ip link set dummyteam down
+	ip link set dev dummyteam master team0
+	ip link set team0 up
+	ip link set team0 promisc on
+
+	# Make sure we can add more L2 addresses without any issues.
+	ip link add link team0 address 00:00:00:00:00:01 team0.1 type macvlan
+	ip link set team0.1 up
+
+	ip link del team0.1
+	ip link del team0
+	ip link del dummyteam
+}
+
+trap cleanup EXIT
+modprobe netdevsim || :
+echo $NSIM_LRO_ID > $NSIM_DEV_SYS_NEW
+udevadm settle
+team_lro
+team_promisc
+team_change_flags
diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
index 4a2d5c454fd1..59a71f22fb11 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
+++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
@@ -48,8 +48,16 @@ static uint64_t get_mnt_id(struct __test_metadata *const _metadata,
 
 static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
 
+static const int mark_cmds[] = {
+	FAN_MARK_ADD,
+	FAN_MARK_REMOVE,
+	FAN_MARK_FLUSH
+};
+
+#define NUM_FAN_FDS ARRAY_SIZE(mark_cmds)
+
 FIXTURE(fanotify) {
-	int fan_fd;
+	int fan_fd[NUM_FAN_FDS];
 	char buf[256];
 	unsigned int rem;
 	void *next;
@@ -61,7 +69,7 @@ FIXTURE(fanotify) {
 
 FIXTURE_SETUP(fanotify)
 {
-	int ret;
+	int i, ret;
 
 	ASSERT_EQ(unshare(CLONE_NEWNS), 0);
 
@@ -89,20 +97,34 @@ FIXTURE_SETUP(fanotify)
 	self->root_id = get_mnt_id(_metadata, "/");
 	ASSERT_NE(self->root_id, 0);
 
-	self->fan_fd = fanotify_init(FAN_REPORT_MNT, 0);
-	ASSERT_GE(self->fan_fd, 0);
-
-	ret = fanotify_mark(self->fan_fd, FAN_MARK_ADD | FAN_MARK_MNTNS,
-			    FAN_MNT_ATTACH | FAN_MNT_DETACH, self->ns_fd, NULL);
-	ASSERT_EQ(ret, 0);
+	for (i = 0; i < NUM_FAN_FDS; i++) {
+		self->fan_fd[i] = fanotify_init(FAN_REPORT_MNT | FAN_NONBLOCK,
+						0);
+		ASSERT_GE(self->fan_fd[i], 0);
+		ret = fanotify_mark(self->fan_fd[i], FAN_MARK_ADD |
+				    FAN_MARK_MNTNS,
+				    FAN_MNT_ATTACH | FAN_MNT_DETACH,
+				    self->ns_fd, NULL);
+		ASSERT_EQ(ret, 0);
+		// On fd[0] we do an extra ADD that changes nothing.
+		// On fd[1]/fd[2] we REMOVE/FLUSH which removes the mark.
+		ret = fanotify_mark(self->fan_fd[i], mark_cmds[i] |
+				    FAN_MARK_MNTNS,
+				    FAN_MNT_ATTACH | FAN_MNT_DETACH,
+				    self->ns_fd, NULL);
+		ASSERT_EQ(ret, 0);
+	}
 
 	self->rem = 0;
 }
 
 FIXTURE_TEARDOWN(fanotify)
 {
+	int i;
+
 	ASSERT_EQ(self->rem, 0);
-	close(self->fan_fd);
+	for (i = 0; i < NUM_FAN_FDS; i++)
+		close(self->fan_fd[i]);
 
 	ASSERT_EQ(fchdir(self->orig_root), 0);
 
@@ -123,8 +145,21 @@ static uint64_t expect_notify(struct __test_metadata *const _metadata,
 	unsigned int thislen;
 
 	if (!self->rem) {
-		ssize_t len = read(self->fan_fd, self->buf, sizeof(self->buf));
-		ASSERT_GT(len, 0);
+		ssize_t len;
+		int i;
+
+		for (i = NUM_FAN_FDS - 1; i >= 0; i--) {
+			len = read(self->fan_fd[i], self->buf,
+				   sizeof(self->buf));
+			if (i > 0) {
+				// Groups 1,2 should get EAGAIN
+				ASSERT_EQ(len, -1);
+				ASSERT_EQ(errno, EAGAIN);
+			} else {
+				// Group 0 should get events
+				ASSERT_GT(len, 0);
+			}
+		}
 
 		self->rem = len;
 		self->next = (void *) self->buf;
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc b/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
index 6b94b678741a..f656bccb1a14 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
@@ -7,11 +7,32 @@
 MAX_ARGS=128
 EXCEED_ARGS=$((MAX_ARGS + 1))
 
+# bash and dash evaluate variables differently.
+# dash will evaluate '\\' every time it is read whereas bash does not.
+#
+#   TEST_STRING="$TEST_STRING \\$i"
+#   echo $TEST_STRING
+#
+# With i=123
+# On bash, that will print "\123"
+# but on dash, that will print the escape sequence of \123 as the \ will
+# be interpreted again in the echo.
+#
+# Set a variable "bs" to save a double backslash, then echo that
+# to "ts" to see if $ts changed or not. If it changed, it's dash,
+# if not, it's bash, and then bs can equal a single backslash.
+bs='\\'
+ts=`echo $bs`
+if [ "$ts" = '\\' ]; then
+  # this is bash
+  bs='\'
+fi
+
 check_max_args() { # event_header
   TEST_STRING=$1
   # Acceptable
   for i in `seq 1 $MAX_ARGS`; do
-    TEST_STRING="$TEST_STRING \\$i"
+    TEST_STRING="$TEST_STRING $bs$i"
   done
   echo "$TEST_STRING" >> dynamic_events
   echo > dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
index 118247b8dd84..c62165fabd0c 100644
--- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
+++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
@@ -80,6 +80,26 @@ if [ $misscnt -gt 0 ]; then
 	exit_fail
 fi
 
+# Check strings too
+if [ -f events/syscalls/sys_enter_openat/filter ]; then
+	DIRNAME=`basename $TMPDIR`
+	echo "filename.ustring ~ \"*$DIRNAME*\"" > events/syscalls/sys_enter_openat/filter
+	echo 1 > events/syscalls/sys_enter_openat/enable
+	echo 1 > tracing_on
+	ls /bin/sh
+	nocnt=`grep openat trace | wc -l`
+	ls $TMPDIR
+	echo 0 > tracing_on
+	hitcnt=`grep openat trace | wc -l`;
+	echo 0 > events/syscalls/sys_enter_openat/enable
+	if [ $nocnt -gt 0 ]; then
+		exit_fail
+	fi
+	if [ $hitcnt -eq 0 ]; then
+		exit_fail
+	fi
+fi
+
 reset_events_filter
 
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-multi-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-multi-filter.tc
new file mode 100644
index 000000000000..b6d6a312ead5
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-multi-filter.tc
@@ -0,0 +1,177 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: ftrace - function graph filters
+# requires: set_ftrace_filter function_graph:tracer
+
+# Make sure that function graph filtering works
+
+INSTANCE1="instances/test1_$$"
+INSTANCE2="instances/test2_$$"
+
+WD=`pwd`
+
+do_reset() {
+    cd $WD
+    if [ -d $INSTANCE1 ]; then
+	echo nop > $INSTANCE1/current_tracer
+	rmdir $INSTANCE1
+    fi
+    if [ -d $INSTANCE2 ]; then
+	echo nop > $INSTANCE2/current_tracer
+	rmdir $INSTANCE2
+    fi
+}
+
+mkdir $INSTANCE1
+if ! grep -q function_graph $INSTANCE1/available_tracers; then
+    echo "function_graph not allowed with instances"
+    rmdir $INSTANCE1
+    exit_unsupported
+fi
+
+mkdir $INSTANCE2
+
+fail() { # msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+disable_tracing
+clear_trace
+
+function_count() {
+    search=$1
+    vsearch=$2
+
+    if [ -z "$search" ]; then
+	cat enabled_functions | wc -l
+    elif [ -z "$vsearch" ]; then
+	grep $search enabled_functions | wc -l
+    else
+	grep $search enabled_functions | grep $vsearch| wc -l
+    fi
+}
+
+set_fgraph() {
+    instance=$1
+    filter="$2"
+    notrace="$3"
+
+    echo "$filter" > $instance/set_ftrace_filter
+    echo "$notrace" > $instance/set_ftrace_notrace
+    echo function_graph > $instance/current_tracer
+}
+
+check_functions() {
+    orig_cnt=$1
+    test=$2
+
+    cnt=`function_count $test`
+    if [ $cnt -gt $orig_cnt ]; then
+	fail
+    fi
+}
+
+check_cnt() {
+    orig_cnt=$1
+    search=$2
+    vsearch=$3
+
+    cnt=`function_count $search $vsearch`
+    if [ $cnt -gt $orig_cnt ]; then
+	fail
+    fi
+}
+
+reset_graph() {
+    instance=$1
+    echo nop > $instance/current_tracer
+}
+
+# get any functions that were enabled before the test
+total_cnt=`function_count`
+sched_cnt=`function_count sched`
+lock_cnt=`function_count lock`
+time_cnt=`function_count time`
+clock_cnt=`function_count clock`
+locks_clock_cnt=`function_count locks clock`
+clock_locks_cnt=`function_count clock locks`
+
+# Trace functions with "sched" but not "time"
+set_fgraph $INSTANCE1 '*sched*' '*time*'
+
+# Make sure "time" isn't listed
+check_functions $time_cnt 'time'
+instance1_cnt=`function_count`
+
+# Trace functions with "lock" but not "clock"
+set_fgraph $INSTANCE2 '*lock*' '*clock*'
+instance1_2_cnt=`function_count`
+
+# Turn off the first instance
+reset_graph $INSTANCE1
+
+# The second instance doesn't trace "clock" functions
+check_functions $clock_cnt 'clock'
+instance2_cnt=`function_count`
+
+# Start from a clean slate
+reset_graph $INSTANCE2
+check_functions $total_cnt
+
+# Trace functions with "lock" but not "clock"
+set_fgraph $INSTANCE2 '*lock*' '*clock*'
+
+# This should match the last time instance 2 was by itself
+cnt=`function_count`
+if [ $instance2_cnt -ne $cnt ]; then
+    fail
+fi
+
+# And it should not be tracing "clock" functions
+check_functions $clock_cnt 'clock'
+
+# Trace functions with "sched" but not "time"
+set_fgraph $INSTANCE1 '*sched*' '*time*'
+
+# This should match the last time both instances were enabled
+cnt=`function_count`
+if [ $instance1_2_cnt -ne $cnt ]; then
+    fail
+fi
+
+# Turn off the second instance
+reset_graph $INSTANCE2
+
+# This should match the last time instance 1 was by itself
+cnt=`function_count`
+if [ $instance1_cnt -ne $cnt ]; then
+    fail
+fi
+
+# And it should not be tracing "time" functions
+check_functions $time_cnt 'time'
+
+# Start from a clean slate
+reset_graph $INSTANCE1
+check_functions $total_cnt
+
+# Enable all functions but those that have "locks"
+set_fgraph $INSTANCE1 '' '*locks*'
+
+# Enable all functions but those that have "clock"
+set_fgraph $INSTANCE2 '' '*clock*'
+
+# If a function has "locks" it should not have "clock"
+check_cnt $locks_clock_cnt locks clock
+
+# If a function has "clock" it should not have "locks"
+check_cnt $clock_locks_cnt clock locks
+
+reset_graph $INSTANCE1
+reset_graph $INSTANCE2
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c
index 322b9d3b0125..57708de2075d 100644
--- a/tools/testing/selftests/kvm/arm64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c
@@ -129,10 +129,10 @@ static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = {
 	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, DIT, 0),
 	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, SEL2, 0),
 	REG_FTR_BITS(FTR_EXACT, ID_AA64PFR0_EL1, GIC, 0),
-	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 0),
-	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 0),
-	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 0),
-	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 1),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 1),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 1),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 1),
 	REG_FTR_END,
 };
 
diff --git a/tools/testing/selftests/landlock/audit.h b/tools/testing/selftests/landlock/audit.h
index b9054086a0c9..18a6014920b5 100644
--- a/tools/testing/selftests/landlock/audit.h
+++ b/tools/testing/selftests/landlock/audit.h
@@ -300,15 +300,22 @@ out:
 	return err;
 }
 
-static int __maybe_unused matches_log_domain_allocated(int audit_fd,
+static int __maybe_unused matches_log_domain_allocated(int audit_fd, pid_t pid,
 						       __u64 *domain_id)
 {
-	return audit_match_record(
-		audit_fd, AUDIT_LANDLOCK_DOMAIN,
-		REGEX_LANDLOCK_PREFIX
-		" status=allocated mode=enforcing pid=[0-9]\\+ uid=[0-9]\\+"
-		" exe=\"[^\"]\\+\" comm=\".*_test\"$",
-		domain_id);
+	static const char log_template[] = REGEX_LANDLOCK_PREFIX
+		" status=allocated mode=enforcing pid=%d uid=[0-9]\\+"
+		" exe=\"[^\"]\\+\" comm=\".*_test\"$";
+	char log_match[sizeof(log_template) + 10];
+	int log_match_len;
+
+	log_match_len =
+		snprintf(log_match, sizeof(log_match), log_template, pid);
+	if (log_match_len > sizeof(log_match))
+		return -E2BIG;
+
+	return audit_match_record(audit_fd, AUDIT_LANDLOCK_DOMAIN, log_match,
+				  domain_id);
 }
 
 static int __maybe_unused matches_log_domain_deallocated(
diff --git a/tools/testing/selftests/landlock/audit_test.c b/tools/testing/selftests/landlock/audit_test.c
index a0643070c403..cfc571afd0eb 100644
--- a/tools/testing/selftests/landlock/audit_test.c
+++ b/tools/testing/selftests/landlock/audit_test.c
@@ -9,6 +9,7 @@
 #include <errno.h>
 #include <limits.h>
 #include <linux/landlock.h>
+#include <pthread.h>
 #include <stdlib.h>
 #include <sys/mount.h>
 #include <sys/prctl.h>
@@ -40,7 +41,6 @@ FIXTURE(audit)
 {
 	struct audit_filter audit_filter;
 	int audit_fd;
-	__u64(*domain_stack)[16];
 };
 
 FIXTURE_SETUP(audit)
@@ -60,18 +60,10 @@ FIXTURE_SETUP(audit)
 		TH_LOG("Failed to initialize audit: %s", error_msg);
 	}
 	clear_cap(_metadata, CAP_AUDIT_CONTROL);
-
-	self->domain_stack = mmap(NULL, sizeof(*self->domain_stack),
-				  PROT_READ | PROT_WRITE,
-				  MAP_SHARED | MAP_ANONYMOUS, -1, 0);
-	ASSERT_NE(MAP_FAILED, self->domain_stack);
-	memset(self->domain_stack, 0, sizeof(*self->domain_stack));
 }
 
 FIXTURE_TEARDOWN(audit)
 {
-	EXPECT_EQ(0, munmap(self->domain_stack, sizeof(*self->domain_stack)));
-
 	set_cap(_metadata, CAP_AUDIT_CONTROL);
 	EXPECT_EQ(0, audit_cleanup(self->audit_fd, &self->audit_filter));
 	clear_cap(_metadata, CAP_AUDIT_CONTROL);
@@ -83,9 +75,15 @@ TEST_F(audit, layers)
 		.scoped = LANDLOCK_SCOPE_SIGNAL,
 	};
 	int status, ruleset_fd, i;
+	__u64(*domain_stack)[16];
 	__u64 prev_dom = 3;
 	pid_t child;
 
+	domain_stack = mmap(NULL, sizeof(*domain_stack), PROT_READ | PROT_WRITE,
+			    MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(MAP_FAILED, domain_stack);
+	memset(domain_stack, 0, sizeof(*domain_stack));
+
 	ruleset_fd =
 		landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
 	ASSERT_LE(0, ruleset_fd);
@@ -94,7 +92,7 @@ TEST_F(audit, layers)
 	child = fork();
 	ASSERT_LE(0, child);
 	if (child == 0) {
-		for (i = 0; i < ARRAY_SIZE(*self->domain_stack); i++) {
+		for (i = 0; i < ARRAY_SIZE(*domain_stack); i++) {
 			__u64 denial_dom = 1;
 			__u64 allocated_dom = 2;
 
@@ -107,7 +105,8 @@ TEST_F(audit, layers)
 				  matches_log_signal(_metadata, self->audit_fd,
 						     getppid(), &denial_dom));
 			EXPECT_EQ(0, matches_log_domain_allocated(
-					     self->audit_fd, &allocated_dom));
+					     self->audit_fd, getpid(),
+					     &allocated_dom));
 			EXPECT_NE(denial_dom, 1);
 			EXPECT_NE(denial_dom, 0);
 			EXPECT_EQ(denial_dom, allocated_dom);
@@ -115,7 +114,7 @@ TEST_F(audit, layers)
 			/* Checks that the new domain is younger than the previous one. */
 			EXPECT_GT(allocated_dom, prev_dom);
 			prev_dom = allocated_dom;
-			(*self->domain_stack)[i] = allocated_dom;
+			(*domain_stack)[i] = allocated_dom;
 		}
 
 		/* Checks that we reached the maximum number of layers. */
@@ -142,23 +141,143 @@ TEST_F(audit, layers)
 	/* Purges log from deallocated domains. */
 	EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
 				&audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
-	for (i = ARRAY_SIZE(*self->domain_stack) - 1; i >= 0; i--) {
+	for (i = ARRAY_SIZE(*domain_stack) - 1; i >= 0; i--) {
 		__u64 deallocated_dom = 2;
 
 		EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
 							    &deallocated_dom));
-		EXPECT_EQ((*self->domain_stack)[i], deallocated_dom)
+		EXPECT_EQ((*domain_stack)[i], deallocated_dom)
 		{
 			TH_LOG("Failed to match domain %llx (#%d)",
-			       (*self->domain_stack)[i], i);
+			       (*domain_stack)[i], i);
 		}
 	}
+	EXPECT_EQ(0, munmap(domain_stack, sizeof(*domain_stack)));
 	EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
 				&audit_tv_default, sizeof(audit_tv_default)));
-
 	EXPECT_EQ(0, close(ruleset_fd));
 }
 
+struct thread_data {
+	pid_t parent_pid;
+	int ruleset_fd, pipe_child, pipe_parent;
+};
+
+static void *thread_audit_test(void *arg)
+{
+	const struct thread_data *data = (struct thread_data *)arg;
+	uintptr_t err = 0;
+	char buffer;
+
+	/* TGID and TID are different for a second thread. */
+	if (getpid() == gettid()) {
+		err = 1;
+		goto out;
+	}
+
+	if (landlock_restrict_self(data->ruleset_fd, 0)) {
+		err = 2;
+		goto out;
+	}
+
+	if (close(data->ruleset_fd)) {
+		err = 3;
+		goto out;
+	}
+
+	/* Creates a denial to get the domain ID. */
+	if (kill(data->parent_pid, 0) != -1) {
+		err = 4;
+		goto out;
+	}
+
+	if (EPERM != errno) {
+		err = 5;
+		goto out;
+	}
+
+	/* Signals the parent to read denial logs. */
+	if (write(data->pipe_child, ".", 1) != 1) {
+		err = 6;
+		goto out;
+	}
+
+	/* Waits for the parent to update audit filters. */
+	if (read(data->pipe_parent, &buffer, 1) != 1) {
+		err = 7;
+		goto out;
+	}
+
+out:
+	close(data->pipe_child);
+	close(data->pipe_parent);
+	return (void *)err;
+}
+
+/* Checks that the PID tied to a domain is not a TID but the TGID. */
+TEST_F(audit, thread)
+{
+	const struct landlock_ruleset_attr ruleset_attr = {
+		.scoped = LANDLOCK_SCOPE_SIGNAL,
+	};
+	__u64 denial_dom = 1;
+	__u64 allocated_dom = 2;
+	__u64 deallocated_dom = 3;
+	pthread_t thread;
+	int pipe_child[2], pipe_parent[2];
+	char buffer;
+	struct thread_data child_data;
+
+	child_data.parent_pid = getppid();
+	ASSERT_EQ(0, pipe2(pipe_child, O_CLOEXEC));
+	child_data.pipe_child = pipe_child[1];
+	ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC));
+	child_data.pipe_parent = pipe_parent[0];
+	child_data.ruleset_fd =
+		landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+	ASSERT_LE(0, child_data.ruleset_fd);
+
+	/* TGID and TID are the same for the initial thread . */
+	EXPECT_EQ(getpid(), gettid());
+	EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+	ASSERT_EQ(0, pthread_create(&thread, NULL, thread_audit_test,
+				    &child_data));
+
+	/* Waits for the child to generate a denial. */
+	ASSERT_EQ(1, read(pipe_child[0], &buffer, 1));
+	EXPECT_EQ(0, close(pipe_child[0]));
+
+	/* Matches the signal log to get the domain ID. */
+	EXPECT_EQ(0, matches_log_signal(_metadata, self->audit_fd,
+					child_data.parent_pid, &denial_dom));
+	EXPECT_NE(denial_dom, 1);
+	EXPECT_NE(denial_dom, 0);
+
+	EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, getpid(),
+						  &allocated_dom));
+	EXPECT_EQ(denial_dom, allocated_dom);
+
+	/* Updates filter rules to match the drop record. */
+	set_cap(_metadata, CAP_AUDIT_CONTROL);
+	EXPECT_EQ(0, audit_filter_drop(self->audit_fd, AUDIT_ADD_RULE));
+	EXPECT_EQ(0, audit_filter_exe(self->audit_fd, &self->audit_filter,
+				      AUDIT_DEL_RULE));
+	clear_cap(_metadata, CAP_AUDIT_CONTROL);
+
+	/* Signals the thread to exit, which will generate a domain deallocation. */
+	ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+	EXPECT_EQ(0, close(pipe_parent[1]));
+	ASSERT_EQ(0, pthread_join(thread, NULL));
+
+	EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+				&audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
+	EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
+						    &deallocated_dom));
+	EXPECT_EQ(denial_dom, deallocated_dom);
+	EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+				&audit_tv_default, sizeof(audit_tv_default)));
+}
+
 FIXTURE(audit_flags)
 {
 	struct audit_filter audit_filter;
@@ -273,7 +392,8 @@ TEST_F(audit_flags, signal)
 
 			/* Checks domain information records. */
 			EXPECT_EQ(0, matches_log_domain_allocated(
-					     self->audit_fd, &allocated_dom));
+					     self->audit_fd, getpid(),
+					     &allocated_dom));
 			EXPECT_NE(*self->domain_id, 1);
 			EXPECT_NE(*self->domain_id, 0);
 			EXPECT_EQ(*self->domain_id, allocated_dom);
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index f819011a8798..73729382d40f 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -5964,7 +5964,8 @@ TEST_F(audit_layout1, refer_handled)
 	EXPECT_EQ(EXDEV, errno);
 	EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
 				    dir_s1d1));
-	EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, NULL));
+	EXPECT_EQ(0,
+		  matches_log_domain_allocated(self->audit_fd, getpid(), NULL));
 	EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
 				    dir_s1d3));
 
diff --git a/tools/testing/selftests/lib/config b/tools/testing/selftests/lib/config
index 81a1f64a22e8..377b3699ff31 100644
--- a/tools/testing/selftests/lib/config
+++ b/tools/testing/selftests/lib/config
@@ -1,2 +1,3 @@
 CONFIG_TEST_BITMAP=m
+CONFIG_PRIME_NUMBERS=m
 CONFIG_TEST_BITOPS=m
diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c
index efabfcbe0b49..17ed3e9917ca 100644
--- a/tools/testing/selftests/mincore/mincore_selftest.c
+++ b/tools/testing/selftests/mincore/mincore_selftest.c
@@ -283,8 +283,7 @@ out_free:
 
 /*
  * Test mincore() behavior on a page backed by a tmpfs file.  This test
- * performs the same steps as the previous one. However, we don't expect
- * any readahead in this case.
+ * performs the same steps as the previous one.
  */
 TEST(check_tmpfs_mmap)
 {
@@ -295,7 +294,6 @@ TEST(check_tmpfs_mmap)
 	int page_size;
 	int fd;
 	int i;
-	int ra_pages = 0;
 
 	page_size = sysconf(_SC_PAGESIZE);
 	vec_size = FILE_SIZE / page_size;
@@ -338,8 +336,7 @@ TEST(check_tmpfs_mmap)
 	}
 
 	/*
-	 * Touch a page in the middle of the mapping. We expect only
-	 * that page to be fetched into memory.
+	 * Touch a page in the middle of the mapping.
 	 */
 	addr[FILE_SIZE / 2] = 1;
 	retval = mincore(addr, FILE_SIZE, vec);
@@ -348,15 +345,6 @@ TEST(check_tmpfs_mmap)
 		TH_LOG("Page not found in memory after use");
 	}
 
-	i = FILE_SIZE / 2 / page_size + 1;
-	while (i < vec_size && vec[i]) {
-		ra_pages++;
-		i++;
-	}
-	ASSERT_EQ(ra_pages, 0) {
-		TH_LOG("Read-ahead pages found in memory");
-	}
-
 	munmap(addr, FILE_SIZE);
 	close(fd);
 	free(vec);
diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
index 67df7b47087f..e1fe16bcbbe8 100755
--- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
+++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
@@ -29,7 +29,7 @@ fi
 if [[ $cgroup2 ]]; then
   cgroup_path=$(mount -t cgroup2 | head -1 | awk '{print $3}')
   if [[ -z "$cgroup_path" ]]; then
-    cgroup_path=/dev/cgroup/memory
+    cgroup_path=$(mktemp -d)
     mount -t cgroup2 none $cgroup_path
     do_umount=1
   fi
@@ -37,7 +37,7 @@ if [[ $cgroup2 ]]; then
 else
   cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}')
   if [[ -z "$cgroup_path" ]]; then
-    cgroup_path=/dev/cgroup/memory
+    cgroup_path=$(mktemp -d)
     mount -t cgroup memory,hugetlb $cgroup_path
     do_umount=1
   fi
diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c
index 2c3a0eb6b22d..9bc4591c7b16 100644
--- a/tools/testing/selftests/mm/compaction_test.c
+++ b/tools/testing/selftests/mm/compaction_test.c
@@ -90,6 +90,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
 	int compaction_index = 0;
 	char nr_hugepages[20] = {0};
 	char init_nr_hugepages[24] = {0};
+	char target_nr_hugepages[24] = {0};
+	int slen;
 
 	snprintf(init_nr_hugepages, sizeof(init_nr_hugepages),
 		 "%lu", initial_nr_hugepages);
@@ -106,11 +108,18 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
 		goto out;
 	}
 
-	/* Request a large number of huge pages. The Kernel will allocate
-	   as much as it can */
-	if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) {
-		ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n",
-			       strerror(errno));
+	/*
+	 * Request huge pages for about half of the free memory. The Kernel
+	 * will allocate as much as it can, and we expect it will get at least 1/3
+	 */
+	nr_hugepages_ul = mem_free / hugepage_size / 2;
+	snprintf(target_nr_hugepages, sizeof(target_nr_hugepages),
+		 "%lu", nr_hugepages_ul);
+
+	slen = strlen(target_nr_hugepages);
+	if (write(fd, target_nr_hugepages, slen) != slen) {
+		ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n",
+			       nr_hugepages_ul, strerror(errno));
 		goto close_fd;
 	}
 
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index f0cb14ea8608..b6cfe0a4b7df 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -293,7 +293,7 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size,
 		.iov_base = mem,
 		.iov_len = size,
 	};
-	ssize_t cur, total, transferred;
+	ssize_t cur, total, transferred = 0;
 	struct comm_pipes comm_pipes;
 	char *old, *new;
 	int ret, fds[2];
diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c
index b3d0e2771096..eba43ead13ae 100644
--- a/tools/testing/selftests/mm/guard-regions.c
+++ b/tools/testing/selftests/mm/guard-regions.c
@@ -271,12 +271,16 @@ FIXTURE_SETUP(guard_regions)
 	self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
 	setup_sighandler();
 
-	if (variant->backing == ANON_BACKED)
+	switch (variant->backing) {
+	case ANON_BACKED:
 		return;
-
-	self->fd = open_file(
-		variant->backing == SHMEM_BACKED ? "/tmp/" : "",
-		self->path);
+	case LOCAL_FILE_BACKED:
+		self->fd = open_file("", self->path);
+		break;
+	case SHMEM_BACKED:
+		self->fd = memfd_create(self->path, 0);
+		break;
+	}
 
 	/* We truncate file to at least 100 pages, tests can modify as needed. */
 	ASSERT_EQ(ftruncate(self->fd, 100 * self->page_size), 0);
@@ -1696,7 +1700,7 @@ TEST_F(guard_regions, readonly_file)
 	char *ptr;
 	int i;
 
-	if (variant->backing == ANON_BACKED)
+	if (variant->backing != LOCAL_FILE_BACKED)
 		SKIP(return, "Read-only test specific to file-backed");
 
 	/* Map shared so we can populate with pattern, populate it, unmap. */
diff --git a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
index 11f9bbe7dc22..0b0d4ba1af27 100755
--- a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
+++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
@@ -23,7 +23,7 @@ fi
 if [[ $cgroup2 ]]; then
   CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk '{print $3}')
   if [[ -z "$CGROUP_ROOT" ]]; then
-    CGROUP_ROOT=/dev/cgroup/memory
+    CGROUP_ROOT=$(mktemp -d)
     mount -t cgroup2 none $CGROUP_ROOT
     do_umount=1
   fi
diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h
index 1bad310d282a..17bf2d1b0192 100644
--- a/tools/testing/selftests/mm/pkey-powerpc.h
+++ b/tools/testing/selftests/mm/pkey-powerpc.h
@@ -3,6 +3,8 @@
 #ifndef _PKEYS_POWERPC_H
 #define _PKEYS_POWERPC_H
 
+#include <sys/stat.h>
+
 #ifndef SYS_pkey_alloc
 # define SYS_pkey_alloc		384
 # define SYS_pkey_free		385
@@ -102,8 +104,18 @@ static inline void expect_fault_on_read_execonly_key(void *p1, int pkey)
 	return;
 }
 
+#define REPEAT_8(s) s s s s s s s s
+#define REPEAT_64(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) \
+		     REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s)
+#define REPEAT_512(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) \
+		      REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s)
+#define REPEAT_4096(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) \
+		       REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s)
+#define REPEAT_16384(s) REPEAT_4096(s) REPEAT_4096(s) \
+			REPEAT_4096(s) REPEAT_4096(s)
+
 /* 4-byte instructions * 16384 = 64K page */
-#define __page_o_noops() asm(".rept 16384 ; nop; .endr")
+#define __page_o_noops() asm(REPEAT_16384("nop\n"))
 
 static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
 {
diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c
index ca4ad0d44ab2..255b332f7a08 100644
--- a/tools/testing/selftests/mm/pkey_util.c
+++ b/tools/testing/selftests/mm/pkey_util.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#define __SANE_USERSPACE_TYPES__
 #include <sys/syscall.h>
 #include <unistd.h>
 
diff --git a/tools/testing/selftests/nci/nci_dev.c b/tools/testing/selftests/nci/nci_dev.c
index 1562aa7d60b0..6dec59d64083 100644
--- a/tools/testing/selftests/nci/nci_dev.c
+++ b/tools/testing/selftests/nci/nci_dev.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2021 Samsung Electrnoics
+ * Copyright (C) 2021 Samsung Electronics
  * Bongsu Jeon <bongsu.jeon@samsung.com>
  *
  * Test code for nci
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 679542f565a4..532bb732bc6d 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -39,6 +39,7 @@ scm_rights
 sk_bind_sendto_listen
 sk_connect_zero_addr
 sk_so_peek_off
+skf_net_off
 socket
 so_incoming_cpu
 so_netns_cookie
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 6d718b478ed8..70a38f485d4d 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -31,6 +31,7 @@ TEST_PROGS += veth.sh
 TEST_PROGS += ioam6.sh
 TEST_PROGS += gro.sh
 TEST_PROGS += gre_gso.sh
+TEST_PROGS += gre_ipv6_lladdr.sh
 TEST_PROGS += cmsg_so_mark.sh
 TEST_PROGS += cmsg_so_priority.sh
 TEST_PROGS += test_so_rcv.sh
@@ -106,6 +107,8 @@ TEST_PROGS += ipv6_route_update_soft_lockup.sh
 TEST_PROGS += busy_poll_test.sh
 TEST_GEN_PROGS += proc_net_pktgen
 TEST_PROGS += lwt_dst_cache_ref_loop.sh
+TEST_PROGS += skf_net_off.sh
+TEST_GEN_FILES += skf_net_off
 
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := busy_poller netlink-dumps
diff --git a/tools/testing/selftests/net/af_unix/scm_rights.c b/tools/testing/selftests/net/af_unix/scm_rights.c
index d66336256580..8b015f16c03d 100644
--- a/tools/testing/selftests/net/af_unix/scm_rights.c
+++ b/tools/testing/selftests/net/af_unix/scm_rights.c
@@ -23,6 +23,7 @@ FIXTURE_VARIANT(scm_rights)
 	int type;
 	int flags;
 	bool test_listener;
+	bool disabled;
 };
 
 FIXTURE_VARIANT_ADD(scm_rights, dgram)
@@ -31,6 +32,16 @@ FIXTURE_VARIANT_ADD(scm_rights, dgram)
 	.type = SOCK_DGRAM,
 	.flags = 0,
 	.test_listener = false,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, dgram_disabled)
+{
+	.name = "UNIX ",
+	.type = SOCK_DGRAM,
+	.flags = 0,
+	.test_listener = false,
+	.disabled = true,
 };
 
 FIXTURE_VARIANT_ADD(scm_rights, stream)
@@ -39,6 +50,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream)
 	.type = SOCK_STREAM,
 	.flags = 0,
 	.test_listener = false,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = 0,
+	.test_listener = false,
+	.disabled = true,
 };
 
 FIXTURE_VARIANT_ADD(scm_rights, stream_oob)
@@ -47,6 +68,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream_oob)
 	.type = SOCK_STREAM,
 	.flags = MSG_OOB,
 	.test_listener = false,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_oob_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = MSG_OOB,
+	.test_listener = false,
+	.disabled = true,
 };
 
 FIXTURE_VARIANT_ADD(scm_rights, stream_listener)
@@ -55,6 +86,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream_listener)
 	.type = SOCK_STREAM,
 	.flags = 0,
 	.test_listener = true,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_listener_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = 0,
+	.test_listener = true,
+	.disabled = true,
 };
 
 FIXTURE_VARIANT_ADD(scm_rights, stream_listener_oob)
@@ -63,6 +104,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream_listener_oob)
 	.type = SOCK_STREAM,
 	.flags = MSG_OOB,
 	.test_listener = true,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_listener_oob_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = MSG_OOB,
+	.test_listener = true,
+	.disabled = true,
 };
 
 static int count_sockets(struct __test_metadata *_metadata,
@@ -105,6 +156,9 @@ FIXTURE_SETUP(scm_rights)
 	ret = unshare(CLONE_NEWNET);
 	ASSERT_EQ(0, ret);
 
+	if (variant->disabled)
+		return;
+
 	ret = count_sockets(_metadata, variant);
 	ASSERT_EQ(0, ret);
 }
@@ -113,6 +167,9 @@ FIXTURE_TEARDOWN(scm_rights)
 {
 	int ret;
 
+	if (variant->disabled)
+		return;
+
 	sleep(1);
 
 	ret = count_sockets(_metadata, variant);
@@ -121,6 +178,7 @@ FIXTURE_TEARDOWN(scm_rights)
 
 static void create_listeners(struct __test_metadata *_metadata,
 			     FIXTURE_DATA(scm_rights) *self,
+			     const FIXTURE_VARIANT(scm_rights) *variant,
 			     int n)
 {
 	struct sockaddr_un addr = {
@@ -140,6 +198,12 @@ static void create_listeners(struct __test_metadata *_metadata,
 		ret = listen(self->fd[i], -1);
 		ASSERT_EQ(0, ret);
 
+		if (variant->disabled) {
+			ret = setsockopt(self->fd[i], SOL_SOCKET, SO_PASSRIGHTS,
+					 &(int){0}, sizeof(int));
+			ASSERT_EQ(0, ret);
+		}
+
 		addrlen = sizeof(addr);
 		ret = getsockname(self->fd[i], (struct sockaddr *)&addr, &addrlen);
 		ASSERT_EQ(0, ret);
@@ -164,6 +228,12 @@ static void create_socketpairs(struct __test_metadata *_metadata,
 	for (i = 0; i < n * 2; i += 2) {
 		ret = socketpair(AF_UNIX, variant->type, 0, self->fd + i);
 		ASSERT_EQ(0, ret);
+
+		if (variant->disabled) {
+			ret = setsockopt(self->fd[i], SOL_SOCKET, SO_PASSRIGHTS,
+					 &(int){0}, sizeof(int));
+			ASSERT_EQ(0, ret);
+		}
 	}
 }
 
@@ -175,7 +245,7 @@ static void __create_sockets(struct __test_metadata *_metadata,
 	ASSERT_LE(n * 2, sizeof(self->fd) / sizeof(self->fd[0]));
 
 	if (variant->test_listener)
-		create_listeners(_metadata, self, n);
+		create_listeners(_metadata, self, variant, n);
 	else
 		create_socketpairs(_metadata, self, variant, n);
 }
@@ -230,7 +300,13 @@ void __send_fd(struct __test_metadata *_metadata,
 	int ret;
 
 	ret = sendmsg(self->fd[receiver * 2 + 1], &msg, variant->flags);
-	ASSERT_EQ(MSGLEN, ret);
+
+	if (variant->disabled) {
+		ASSERT_EQ(-1, ret);
+		ASSERT_EQ(-EPERM, -errno);
+	} else {
+		ASSERT_EQ(MSGLEN, ret);
+	}
 }
 
 #define create_sockets(n)					\
diff --git a/tools/testing/selftests/net/bareudp.sh b/tools/testing/selftests/net/bareudp.sh
index f366cadbc5e8..4046131e7888 100755
--- a/tools/testing/selftests/net/bareudp.sh
+++ b/tools/testing/selftests/net/bareudp.sh
@@ -106,26 +106,16 @@
 # |                                                                       |
 # +-----------------------------------------------------------------------+
 
+. ./lib.sh
+
 ERR=4 # Return 4 by default, which is the SKIP code for kselftest
 PING6="ping"
 PAUSE_ON_FAIL="no"
 
-readonly NS0=$(mktemp -u ns0-XXXXXXXX)
-readonly NS1=$(mktemp -u ns1-XXXXXXXX)
-readonly NS2=$(mktemp -u ns2-XXXXXXXX)
-readonly NS3=$(mktemp -u ns3-XXXXXXXX)
-
 # Exit the script after having removed the network namespaces it created
-#
-# Parameters:
-#
-#   * The list of network namespaces to delete before exiting.
-#
 exit_cleanup()
 {
-	for ns in "$@"; do
-		ip netns delete "${ns}" 2>/dev/null || true
-	done
+	cleanup_all_ns
 
 	if [ "${ERR}" -eq 4 ]; then
 		echo "Error: Setting up the testing environment failed." >&2
@@ -140,17 +130,7 @@ exit_cleanup()
 # namespaces created by this script are deleted.
 create_namespaces()
 {
-	ip netns add "${NS0}" || exit_cleanup
-	ip netns add "${NS1}" || exit_cleanup "${NS0}"
-	ip netns add "${NS2}" || exit_cleanup "${NS0}" "${NS1}"
-	ip netns add "${NS3}" || exit_cleanup "${NS0}" "${NS1}" "${NS2}"
-}
-
-# The trap function handler
-#
-exit_cleanup_all()
-{
-	exit_cleanup "${NS0}" "${NS1}" "${NS2}" "${NS3}"
+	setup_ns NS0 NS1 NS2 NS3 || exit_cleanup
 }
 
 # Configure a network interface using a host route
@@ -188,10 +168,6 @@ iface_config()
 #
 setup_underlay()
 {
-	for ns in "${NS0}" "${NS1}" "${NS2}" "${NS3}"; do
-		ip -netns "${ns}" link set dev lo up
-	done;
-
 	ip link add name veth01 netns "${NS0}" type veth peer name veth10 netns "${NS1}"
 	ip link add name veth12 netns "${NS1}" type veth peer name veth21 netns "${NS2}"
 	ip link add name veth23 netns "${NS2}" type veth peer name veth32 netns "${NS3}"
@@ -234,14 +210,6 @@ setup_overlay_ipv4()
 	ip netns exec "${NS2}" sysctl -qw net.ipv4.ip_forward=1
 	ip -netns "${NS1}" route add 192.0.2.100/32 via 192.0.2.10
 	ip -netns "${NS2}" route add 192.0.2.103/32 via 192.0.2.33
-
-	# The intermediate namespaces don't have routes for the reverse path,
-	# as it will be handled by tc. So we need to ensure that rp_filter is
-	# not going to block the traffic.
-	ip netns exec "${NS1}" sysctl -qw net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${NS2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${NS1}" sysctl -qw net.ipv4.conf.default.rp_filter=0
-	ip netns exec "${NS2}" sysctl -qw net.ipv4.conf.default.rp_filter=0
 }
 
 setup_overlay_ipv6()
@@ -521,13 +489,10 @@ done
 
 check_features
 
-# Create namespaces before setting up the exit trap.
-# Otherwise, exit_cleanup_all() could delete namespaces that were not created
-# by this script.
-create_namespaces
-
 set -e
-trap exit_cleanup_all EXIT
+trap exit_cleanup EXIT
+
+create_namespaces
 
 setup_underlay
 setup_overlay_ipv4
diff --git a/tools/testing/selftests/net/can/.gitignore b/tools/testing/selftests/net/can/.gitignore
new file mode 100644
index 000000000000..764a53fc837f
--- /dev/null
+++ b/tools/testing/selftests/net/can/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+test_raw_filter
diff --git a/tools/testing/selftests/net/can/Makefile b/tools/testing/selftests/net/can/Makefile
new file mode 100644
index 000000000000..5b82e60a03e7
--- /dev/null
+++ b/tools/testing/selftests/net/can/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+
+top_srcdir = ../../../../..
+
+CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
+
+TEST_PROGS := test_raw_filter.sh
+
+TEST_GEN_FILES := test_raw_filter
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/can/test_raw_filter.c b/tools/testing/selftests/net/can/test_raw_filter.c
new file mode 100644
index 000000000000..4101c36390fd
--- /dev/null
+++ b/tools/testing/selftests/net/can/test_raw_filter.c
@@ -0,0 +1,405 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (c) 2011 Volkswagen Group Electronic Research
+ * All rights reserved.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <net/if.h>
+#include <linux/if.h>
+
+#include <linux/can.h>
+#include <linux/can/raw.h>
+
+#include "../../kselftest_harness.h"
+
+#define ID 0x123
+
+char CANIF[IFNAMSIZ];
+
+static int send_can_frames(int sock, int testcase)
+{
+	struct can_frame frame;
+
+	frame.can_dlc = 1;
+	frame.data[0] = testcase;
+
+	frame.can_id = ID;
+	if (write(sock, &frame, sizeof(frame)) < 0)
+		goto write_err;
+
+	frame.can_id = (ID | CAN_RTR_FLAG);
+	if (write(sock, &frame, sizeof(frame)) < 0)
+		goto write_err;
+
+	frame.can_id = (ID | CAN_EFF_FLAG);
+	if (write(sock, &frame, sizeof(frame)) < 0)
+		goto write_err;
+
+	frame.can_id = (ID | CAN_EFF_FLAG | CAN_RTR_FLAG);
+	if (write(sock, &frame, sizeof(frame)) < 0)
+		goto write_err;
+
+	return 0;
+
+write_err:
+	perror("write");
+	return 1;
+}
+
+FIXTURE(can_filters) {
+	int sock;
+};
+
+FIXTURE_SETUP(can_filters)
+{
+	struct sockaddr_can addr;
+	struct ifreq ifr;
+	int recv_own_msgs = 1;
+	int s, ret;
+
+	s = socket(PF_CAN, SOCK_RAW, CAN_RAW);
+	ASSERT_GE(s, 0)
+		TH_LOG("failed to create CAN_RAW socket: %d", errno);
+
+	strncpy(ifr.ifr_name, CANIF, sizeof(ifr.ifr_name));
+	ret = ioctl(s, SIOCGIFINDEX, &ifr);
+	ASSERT_GE(ret, 0)
+		TH_LOG("failed SIOCGIFINDEX: %d", errno);
+
+	addr.can_family = AF_CAN;
+	addr.can_ifindex = ifr.ifr_ifindex;
+
+	setsockopt(s, SOL_CAN_RAW, CAN_RAW_RECV_OWN_MSGS,
+		   &recv_own_msgs, sizeof(recv_own_msgs));
+
+	ret = bind(s, (struct sockaddr *)&addr, sizeof(addr));
+	ASSERT_EQ(ret, 0)
+		TH_LOG("failed bind socket: %d", errno);
+
+	self->sock = s;
+}
+
+FIXTURE_TEARDOWN(can_filters)
+{
+	close(self->sock);
+}
+
+FIXTURE_VARIANT(can_filters) {
+	int testcase;
+	canid_t id;
+	canid_t mask;
+	int exp_num_rx;
+	canid_t exp_flags[];
+};
+
+/* Receive all frames when filtering for the ID in standard frame format */
+FIXTURE_VARIANT_ADD(can_filters, base) {
+	.testcase = 1,
+	.id = ID,
+	.mask = CAN_SFF_MASK,
+	.exp_num_rx = 4,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Ignore EFF flag in filter ID if not covered by filter mask */
+FIXTURE_VARIANT_ADD(can_filters, base_eff) {
+	.testcase = 2,
+	.id = ID | CAN_EFF_FLAG,
+	.mask = CAN_SFF_MASK,
+	.exp_num_rx = 4,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Ignore RTR flag in filter ID if not covered by filter mask */
+FIXTURE_VARIANT_ADD(can_filters, base_rtr) {
+	.testcase = 3,
+	.id = ID | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK,
+	.exp_num_rx = 4,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Ignore EFF and RTR flags in filter ID if not covered by filter mask */
+FIXTURE_VARIANT_ADD(can_filters, base_effrtr) {
+	.testcase = 4,
+	.id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK,
+	.exp_num_rx = 4,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only SFF frames when expecting no EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff) {
+	.testcase = 5,
+	.id = ID,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only EFF frames when filter id and filter mask include EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff_eff) {
+	.testcase = 6,
+	.id = ID | CAN_EFF_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only SFF frames when expecting no EFF flag, ignoring RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff_rtr) {
+	.testcase = 7,
+	.id = ID | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only EFF frames when filter id and filter mask include EFF flag,
+ * ignoring RTR flag
+ */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff_effrtr) {
+	.testcase = 8,
+	.id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive no remote frames when filtering for no RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr) {
+	.testcase = 9,
+	.id = ID,
+	.mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		0,
+		CAN_EFF_FLAG,
+	},
+};
+
+/* Receive no remote frames when filtering for no RTR flag, ignoring EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr_eff) {
+	.testcase = 10,
+	.id = ID | CAN_EFF_FLAG,
+	.mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		0,
+		CAN_EFF_FLAG,
+	},
+};
+
+/* Receive only remote frames when filter includes RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr_rtr) {
+	.testcase = 11,
+	.id = ID | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only remote frames when filter includes RTR flag, ignoring EFF
+ * flag
+ */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr_effrtr) {
+	.testcase = 12,
+	.id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only SFF data frame when filtering for no flags */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr) {
+	.testcase = 13,
+	.id = ID,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		0,
+	},
+};
+
+/* Receive only EFF data frame when filtering for EFF but no RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr_eff) {
+	.testcase = 14,
+	.id = ID | CAN_EFF_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		CAN_EFF_FLAG,
+	},
+};
+
+/* Receive only SFF remote frame when filtering for RTR but no EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr_rtr) {
+	.testcase = 15,
+	.id = ID | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only EFF remote frame when filtering for EFF and RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr_effrtr) {
+	.testcase = 16,
+	.id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only SFF data frame when filtering for no EFF flag and no RTR flag
+ * but based on EFF mask
+ */
+FIXTURE_VARIANT_ADD(can_filters, eff) {
+	.testcase = 17,
+	.id = ID,
+	.mask = CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		0,
+	},
+};
+
+/* Receive only EFF data frame when filtering for EFF flag and no RTR flag but
+ * based on EFF mask
+ */
+FIXTURE_VARIANT_ADD(can_filters, eff_eff) {
+	.testcase = 18,
+	.id = ID | CAN_EFF_FLAG,
+	.mask = CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		CAN_EFF_FLAG,
+	},
+};
+
+/* This test verifies that the raw CAN filters work, by checking if only frames
+ * with the expected set of flags are received. For each test case, the given
+ * filter (id and mask) is added and four CAN frames are sent with every
+ * combination of set/unset EFF/RTR flags.
+ */
+TEST_F(can_filters, test_filter)
+{
+	struct can_filter rfilter;
+	int ret;
+
+	rfilter.can_id = variant->id;
+	rfilter.can_mask = variant->mask;
+	setsockopt(self->sock, SOL_CAN_RAW, CAN_RAW_FILTER,
+		   &rfilter, sizeof(rfilter));
+
+	TH_LOG("filters: can_id = 0x%08X can_mask = 0x%08X",
+		rfilter.can_id, rfilter.can_mask);
+
+	ret = send_can_frames(self->sock, variant->testcase);
+	ASSERT_EQ(ret, 0)
+		TH_LOG("failed to send CAN frames");
+
+	for (int i = 0; i <= variant->exp_num_rx; i++) {
+		struct can_frame frame;
+		struct timeval tv = {
+			.tv_sec = 0,
+			.tv_usec = 50000, /* 50ms timeout */
+		};
+		fd_set rdfs;
+
+		FD_ZERO(&rdfs);
+		FD_SET(self->sock, &rdfs);
+
+		ret = select(self->sock + 1, &rdfs, NULL, NULL, &tv);
+		ASSERT_GE(ret, 0)
+			TH_LOG("failed select for frame %d, err: %d)", i, errno);
+
+		ret = FD_ISSET(self->sock, &rdfs);
+		if (i == variant->exp_num_rx) {
+			ASSERT_EQ(ret, 0)
+				TH_LOG("too many frames received");
+		} else {
+			ASSERT_NE(ret, 0)
+				TH_LOG("too few frames received");
+
+			ret = read(self->sock, &frame, sizeof(frame));
+			ASSERT_GE(ret, 0)
+				TH_LOG("failed to read frame %d, err: %d", i, errno);
+
+			TH_LOG("rx: can_id = 0x%08X rx = %d", frame.can_id, i);
+
+			ASSERT_EQ(ID, frame.can_id & CAN_SFF_MASK)
+				TH_LOG("received wrong can_id");
+			ASSERT_EQ(variant->testcase, frame.data[0])
+				TH_LOG("received wrong test case");
+
+			ASSERT_EQ(frame.can_id & ~CAN_ERR_MASK,
+				  variant->exp_flags[i])
+				TH_LOG("received unexpected flags");
+		}
+	}
+}
+
+int main(int argc, char **argv)
+{
+	char *ifname = getenv("CANIF");
+
+	if (!ifname) {
+		printf("CANIF environment variable must contain the test interface\n");
+		return KSFT_FAIL;
+	}
+
+	strncpy(CANIF, ifname, sizeof(CANIF) - 1);
+
+	return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/net/can/test_raw_filter.sh b/tools/testing/selftests/net/can/test_raw_filter.sh
new file mode 100755
index 000000000000..276d6c06ac95
--- /dev/null
+++ b/tools/testing/selftests/net/can/test_raw_filter.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	test_raw_filter
+"
+
+net_dir=$(dirname $0)/..
+source $net_dir/lib.sh
+
+export CANIF=${CANIF:-"vcan0"}
+BITRATE=${BITRATE:-500000}
+
+setup()
+{
+	if [[ $CANIF == vcan* ]]; then
+		ip link add name $CANIF type vcan || exit $ksft_skip
+	else
+		ip link set dev $CANIF type can bitrate $BITRATE || exit $ksft_skip
+	fi
+	ip link set dev $CANIF up
+	pwd
+}
+
+cleanup()
+{
+	ip link set dev $CANIF down
+	if [[ $CANIF == vcan* ]]; then
+		ip link delete $CANIF
+	fi
+}
+
+test_raw_filter()
+{
+	./test_raw_filter
+	check_err $?
+	log_test "test_raw_filter"
+}
+
+trap cleanup EXIT
+setup
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 130d532b7e67..3cfef5153823 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -33,7 +33,6 @@ CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NF_CONNTRACK=m
 CONFIG_IPV6_MROUTE=y
 CONFIG_IPV6_SIT=y
-CONFIG_IP_DCCP=m
 CONFIG_NF_NAT=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP_NF_IPTABLES=m
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index b866bab1d92a..5fbdd2a0b537 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -359,6 +359,23 @@ fib_rule6_test()
 			"$getnomatch" "iif flowlabel masked redirect to table" \
 			"iif flowlabel masked no redirect to table"
 	fi
+
+	$IP link show dev $DEV | grep -q vrf0
+	if [ $? -eq 0 ]; then
+		match="oif vrf0"
+		getmatch="oif $DEV"
+		getnomatch="oif lo"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "VRF oif redirect to table" \
+			"VRF oif no redirect to table"
+
+		match="from $SRC_IP6 iif vrf0"
+		getmatch="from $SRC_IP6 iif $DEV"
+		getnomatch="from $SRC_IP6 iif lo"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "VRF iif redirect to table" \
+			"VRF iif no redirect to table"
+	fi
 }
 
 fib_rule6_vrf_test()
@@ -499,10 +516,7 @@ fib_rule4_test()
 	fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \
 		"oif redirect to table" "oif no redirect to table"
 
-	# Enable forwarding and disable rp_filter as all the addresses are in
-	# the same subnet and egress device == ingress device.
 	ip netns exec $testns sysctl -qw net.ipv4.ip_forward=1
-	ip netns exec $testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0
 	match="from $SRC_IP iif $DEV"
 	getnomatch="from $SRC_IP iif lo"
 	fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \
@@ -635,6 +649,23 @@ fib_rule4_test()
 			"$getnomatch" "iif dscp masked redirect to table" \
 			"iif dscp masked no redirect to table"
 	fi
+
+	$IP link show dev $DEV | grep -q vrf0
+	if [ $? -eq 0 ]; then
+		match="oif vrf0"
+		getmatch="oif $DEV"
+		getnomatch="oif lo"
+		fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "VRF oif redirect to table" \
+			"VRF oif no redirect to table"
+
+		match="from $SRC_IP iif vrf0"
+		getmatch="from $SRC_IP iif $DEV"
+		getnomatch="from $SRC_IP iif lo"
+		fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "VRF iif redirect to table" \
+			"VRF iif no redirect to table"
+	fi
 }
 
 fib_rule4_vrf_test()
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 3ea6f886a210..a94b73a53f72 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -11,7 +11,7 @@ TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \
        ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \
        ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \
        ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test \
-       ipv4_mpath_list ipv6_mpath_list"
+       ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
@@ -1085,6 +1085,35 @@ route_setup()
 	set +e
 }
 
+forwarding_cleanup()
+{
+	cleanup_ns $ns3
+
+	route_cleanup
+}
+
+# extend route_setup with an ns3 reachable through ns2 over both devices
+forwarding_setup()
+{
+	forwarding_cleanup
+
+	route_setup
+
+	setup_ns ns3
+
+	ip link add veth5 netns $ns3 type veth peer name veth6 netns $ns2
+	ip -netns $ns3 link set veth5 up
+	ip -netns $ns2 link set veth6 up
+
+	ip -netns $ns3 -4 addr add dev veth5 172.16.105.1/24
+	ip -netns $ns2 -4 addr add dev veth6 172.16.105.2/24
+	ip -netns $ns3 -4 route add 172.16.100.0/22 via 172.16.105.2
+
+	ip -netns $ns3 -6 addr add dev veth5 2001:db8:105::1/64 nodad
+	ip -netns $ns2 -6 addr add dev veth6 2001:db8:105::2/64 nodad
+	ip -netns $ns3 -6 route add 2001:db8:101::/33 via 2001:db8:105::2
+}
+
 # assumption is that basic add of a single path route works
 # otherwise just adding an address on an interface is broken
 ipv6_rt_add()
@@ -2531,9 +2560,6 @@ ipv4_mpath_list_test()
 	run_cmd "ip -n $ns2 route add 203.0.113.0/24
 		nexthop via 172.16.201.2 nexthop via 172.16.202.2"
 	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.fib_multipath_hash_policy=1"
-	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.veth2.rp_filter=0"
-	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.all.rp_filter=0"
-	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.default.rp_filter=0"
 	set +e
 
 	local dmac=$(ip -n $ns2 -j link show dev veth2 | jq -r '.[]["address"]')
@@ -2600,6 +2626,93 @@ ipv6_mpath_list_test()
 	route_cleanup
 }
 
+tc_set_flower_counter__saddr_syn() {
+	tc_set_flower_counter $1 $2 $3 "src_ip $4 ip_proto tcp tcp_flags 0x2"
+}
+
+ip_mpath_balance_dep_check()
+{
+	if [ ! -x "$(command -v socat)" ]; then
+		echo "socat command not found. Skipping test"
+		return 1
+	fi
+
+	if [ ! -x "$(command -v jq)" ]; then
+		echo "jq command not found. Skipping test"
+		return 1
+	fi
+}
+
+ip_mpath_balance() {
+	local -r ipver=$1
+	local -r daddr=$2
+	local -r num_conn=20
+
+	for i in $(seq 1 $num_conn); do
+		ip netns exec $ns3 socat $ipver TCP-LISTEN:8000 STDIO >/dev/null &
+		sleep 0.02
+		echo -n a | ip netns exec $ns1 socat $ipver STDIO TCP:$daddr:8000
+	done
+
+	local -r syn0="$(tc_get_flower_counter $ns1 veth1)"
+	local -r syn1="$(tc_get_flower_counter $ns1 veth3)"
+	local -r syns=$((syn0+syn1))
+
+	[ "$VERBOSE" = "1" ] && echo "multipath: syns seen: ($syn0,$syn1)"
+
+	[[ $syns -ge $num_conn ]] && [[ $syn0 -gt 0 ]] && [[ $syn1 -gt 0 ]]
+}
+
+ipv4_mpath_balance_test()
+{
+	echo
+	echo "IPv4 multipath load balance test"
+
+	ip_mpath_balance_dep_check || return 1
+	forwarding_setup
+
+	$IP route add 172.16.105.1 \
+		nexthop via 172.16.101.2 \
+		nexthop via 172.16.103.2
+
+	ip netns exec $ns1 \
+		sysctl -q -w net.ipv4.fib_multipath_hash_policy=1
+
+	tc_set_flower_counter__saddr_syn $ns1 4 veth1 172.16.101.1
+	tc_set_flower_counter__saddr_syn $ns1 4 veth3 172.16.103.1
+
+	ip_mpath_balance -4 172.16.105.1
+
+	log_test $? 0 "IPv4 multipath loadbalance"
+
+	forwarding_cleanup
+}
+
+ipv6_mpath_balance_test()
+{
+	echo
+	echo "IPv6 multipath load balance test"
+
+	ip_mpath_balance_dep_check || return 1
+	forwarding_setup
+
+	$IP route add 2001:db8:105::1\
+		nexthop via 2001:db8:101::2 \
+		nexthop via 2001:db8:103::2
+
+	ip netns exec $ns1 \
+		sysctl -q -w net.ipv6.fib_multipath_hash_policy=1
+
+	tc_set_flower_counter__saddr_syn $ns1 6 veth1 2001:db8:101::1
+	tc_set_flower_counter__saddr_syn $ns1 6 veth3 2001:db8:103::1
+
+	ip_mpath_balance -6 "[2001:db8:105::1]"
+
+	log_test $? 0 "IPv6 multipath loadbalance"
+
+	forwarding_cleanup
+}
+
 ################################################################################
 # usage
 
@@ -2683,6 +2796,8 @@ do
 	fib6_gc_test|ipv6_gc)		fib6_gc_test;;
 	ipv4_mpath_list)		ipv4_mpath_list_test;;
 	ipv6_mpath_list)		ipv6_mpath_list_test;;
+	ipv4_mpath_balance)		ipv4_mpath_balance_test;;
+	ipv6_mpath_balance)		ipv6_mpath_balance_test;;
 
 	help) echo "Test names: $TESTS"; exit 0;;
 	esac
diff --git a/tools/testing/selftests/net/forwarding/bridge_igmp.sh b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
index e6a3e04fd83f..d4e7dd659354 100755
--- a/tools/testing/selftests/net/forwarding/bridge_igmp.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
@@ -1,10 +1,24 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="v2reportleave_test v3include_test v3inc_allow_test v3inc_is_include_test \
-	   v3inc_is_exclude_test v3inc_to_exclude_test v3exc_allow_test v3exc_is_include_test \
-	   v3exc_is_exclude_test v3exc_to_exclude_test v3inc_block_test v3exc_block_test \
-	   v3exc_timeout_test v3star_ex_auto_add_test"
+ALL_TESTS="
+	v2reportleave_test
+	v3include_test
+	v3inc_allow_test
+	v3inc_is_include_test
+	v3inc_is_exclude_test
+	v3inc_to_exclude_test
+	v3exc_allow_test
+	v3exc_is_include_test
+	v3exc_is_exclude_test
+	v3exc_to_exclude_test
+	v3inc_block_test
+	v3exc_block_test
+	v3exc_timeout_test
+	v3star_ex_auto_add_test
+	v2per_vlan_snooping_port_stp_test
+	v2per_vlan_snooping_vlan_stp_test
+"
 NUM_NETIFS=4
 CHECK_TC="yes"
 TEST_GROUP="239.10.10.10"
@@ -554,6 +568,64 @@ v3star_ex_auto_add_test()
 	v3cleanup $swp2 $TEST_GROUP
 }
 
+v2per_vlan_snooping_stp_test()
+{
+	local is_port=$1
+
+	local msg="port"
+	[[ $is_port -ne 1 ]] && msg="vlan"
+
+	ip link set br0 up type bridge vlan_filtering 1 \
+					mcast_igmp_version 2 \
+					mcast_snooping 1 \
+					mcast_vlan_snooping 1 \
+					mcast_querier 1 \
+					mcast_stats_enabled 1
+	bridge vlan global set vid 1 dev br0 \
+					mcast_snooping 1 \
+					mcast_querier 1 \
+					mcast_query_interval 100 \
+					mcast_startup_query_count 0
+	[[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 0
+	[[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 4
+	sleep 5
+	local tx_s=$(ip -j -p stats show dev $swp1 \
+			group xstats_slave subgroup bridge suite mcast \
+			| jq '.[]["multicast"]["igmp_queries"]["tx_v2"]')
+
+	[[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 3
+	[[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 3
+	sleep 5
+	local tx_e=$(ip -j -p stats show dev $swp1 \
+			group xstats_slave subgroup bridge suite mcast \
+			| jq '.[]["multicast"]["igmp_queries"]["tx_v2"]')
+
+	RET=0
+	local tx=$(expr $tx_e - $tx_s)
+	test $tx -gt 0
+	check_err $? "No IGMP queries after STP state becomes forwarding"
+	log_test "per vlan snooping with $msg stp state change"
+
+	# restore settings
+	bridge vlan global set vid 1 dev br0 \
+					mcast_querier 0 \
+					mcast_query_interval 12500 \
+					mcast_startup_query_count 2
+	ip link set br0 up type bridge vlan_filtering 0 \
+					mcast_vlan_snooping 0 \
+					mcast_stats_enabled 0
+}
+
+v2per_vlan_snooping_port_stp_test()
+{
+	v2per_vlan_snooping_stp_test 1
+}
+
+v2per_vlan_snooping_vlan_stp_test()
+{
+	v2per_vlan_snooping_stp_test 0
+}
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/bridge_mld.sh b/tools/testing/selftests/net/forwarding/bridge_mld.sh
index f84ab2e65754..4cacef5a813a 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mld.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mld.sh
@@ -1,10 +1,23 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="mldv2include_test mldv2inc_allow_test mldv2inc_is_include_test mldv2inc_is_exclude_test \
-	   mldv2inc_to_exclude_test mldv2exc_allow_test mldv2exc_is_include_test \
-	   mldv2exc_is_exclude_test mldv2exc_to_exclude_test mldv2inc_block_test \
-	   mldv2exc_block_test mldv2exc_timeout_test mldv2star_ex_auto_add_test"
+ALL_TESTS="
+	mldv2include_test
+	mldv2inc_allow_test
+	mldv2inc_is_include_test
+	mldv2inc_is_exclude_test
+	mldv2inc_to_exclude_test
+	mldv2exc_allow_test
+	mldv2exc_is_include_test
+	mldv2exc_is_exclude_test
+	mldv2exc_to_exclude_test
+	mldv2inc_block_test
+	mldv2exc_block_test
+	mldv2exc_timeout_test
+	mldv2star_ex_auto_add_test
+	mldv2per_vlan_snooping_port_stp_test
+	mldv2per_vlan_snooping_vlan_stp_test
+"
 NUM_NETIFS=4
 CHECK_TC="yes"
 TEST_GROUP="ff02::cc"
@@ -554,6 +567,66 @@ mldv2star_ex_auto_add_test()
 	mldv2cleanup $swp2
 }
 
+mldv2per_vlan_snooping_stp_test()
+{
+	local is_port=$1
+
+	local msg="port"
+	[[ $is_port -ne 1 ]] && msg="vlan"
+
+	ip link set br0 up type bridge vlan_filtering 1 \
+					mcast_mld_version 2 \
+					mcast_snooping 1 \
+					mcast_vlan_snooping 1 \
+					mcast_querier 1 \
+					mcast_stats_enabled 1
+	bridge vlan global set vid 1 dev br0 \
+					mcast_mld_version 2 \
+					mcast_snooping 1 \
+					mcast_querier 1 \
+					mcast_query_interval 100 \
+					mcast_startup_query_count 0
+
+	[[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 0
+	[[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 4
+	sleep 5
+	local tx_s=$(ip -j -p stats show dev $swp1 \
+			group xstats_slave subgroup bridge suite mcast \
+			| jq '.[]["multicast"]["mld_queries"]["tx_v2"]')
+	[[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 3
+	[[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 3
+	sleep 5
+	local tx_e=$(ip -j -p stats show dev $swp1 \
+			group xstats_slave subgroup bridge suite mcast \
+			| jq '.[]["multicast"]["mld_queries"]["tx_v2"]')
+
+	RET=0
+	local tx=$(expr $tx_e - $tx_s)
+	test $tx -gt 0
+	check_err $? "No MLD queries after STP state becomes forwarding"
+	log_test "per vlan snooping with $msg stp state change"
+
+	# restore settings
+	bridge vlan global set vid 1 dev br0 \
+					mcast_querier 0 \
+					mcast_query_interval 12500 \
+					mcast_startup_query_count 2 \
+					mcast_mld_version 1
+	ip link set br0 up type bridge vlan_filtering 0 \
+					mcast_vlan_snooping 0 \
+					mcast_stats_enabled 0
+}
+
+mldv2per_vlan_snooping_port_stp_test()
+{
+	mldv2per_vlan_snooping_stp_test 1
+}
+
+mldv2per_vlan_snooping_vlan_stp_test()
+{
+	mldv2per_vlan_snooping_stp_test 0
+}
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
index 90f8a244ea90..e59fba366a0a 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid"
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid 8021p drop_untagged"
 NUM_NETIFS=4
 CHECK_TC="yes"
 source lib.sh
@@ -194,6 +194,100 @@ other_tpid()
 	tc qdisc del dev $h2 clsact
 }
 
+8021p_do()
+{
+	local should_fail=$1; shift
+	local mac=de:ad:be:ef:13:37
+
+	tc filter add dev $h2 ingress protocol all pref 1 handle 101 \
+		flower dst_mac $mac action drop
+
+	$MZ -q $h1 -c 1 -b $mac -a own "81:00 00:00 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa"
+	sleep 1
+
+	tc -j -s filter show dev $h2 ingress \
+		| jq -e ".[] | select(.options.handle == 101) \
+		| select(.options.actions[0].stats.packets == 1)" &> /dev/null
+	check_err_fail $should_fail $? "802.1p-tagged reception"
+
+	tc filter del dev $h2 ingress pref 1
+}
+
+8021p()
+{
+	RET=0
+
+	tc qdisc add dev $h2 clsact
+	ip link set $h2 promisc on
+
+	# Test that with the default_pvid, 1, packets tagged with VID 0 are
+	# accepted.
+	8021p_do 0
+
+	# Test that packets tagged with VID 0 are still accepted after changing
+	# the default_pvid.
+	ip link set br0 type bridge vlan_default_pvid 10
+	8021p_do 0
+
+	log_test "Reception of 802.1p-tagged traffic"
+
+	ip link set $h2 promisc off
+	tc qdisc del dev $h2 clsact
+}
+
+send_untagged_and_8021p()
+{
+	ping_do $h1 192.0.2.2
+	check_fail $?
+
+	8021p_do 1
+}
+
+drop_untagged()
+{
+	RET=0
+
+	tc qdisc add dev $h2 clsact
+	ip link set $h2 promisc on
+
+	# Test that with no PVID, untagged and 802.1p-tagged traffic is
+	# dropped.
+	ip link set br0 type bridge vlan_default_pvid 1
+
+	# First we reconfigure the default_pvid, 1, as a non-PVID VLAN.
+	bridge vlan add dev $swp1 vid 1 untagged
+	send_untagged_and_8021p
+	bridge vlan add dev $swp1 vid 1 pvid untagged
+
+	# Next we try to delete VID 1 altogether
+	bridge vlan del dev $swp1 vid 1
+	send_untagged_and_8021p
+	bridge vlan add dev $swp1 vid 1 pvid untagged
+
+	# Set up the bridge without a default_pvid, then check that the 8021q
+	# module, when the bridge port goes down and then up again, does not
+	# accidentally re-enable untagged packet reception.
+	ip link set br0 type bridge vlan_default_pvid 0
+	ip link set $swp1 down
+	ip link set $swp1 up
+	setup_wait
+	send_untagged_and_8021p
+
+	# Remove swp1 as a bridge port and let it rejoin the bridge while it
+	# has no default_pvid.
+	ip link set $swp1 nomaster
+	ip link set $swp1 master br0
+	send_untagged_and_8021p
+
+	# Restore settings
+	ip link set br0 type bridge vlan_default_pvid 1
+
+	log_test "Dropping of untagged and 802.1p-tagged traffic with no PVID"
+
+	ip link set $h2 promisc off
+	tc qdisc del dev $h2 clsact
+}
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config
index 8d7a1a004b7c..18fd69d8d937 100644
--- a/tools/testing/selftests/net/forwarding/config
+++ b/tools/testing/selftests/net/forwarding/config
@@ -1,6 +1,7 @@
 CONFIG_BRIDGE=m
 CONFIG_VLAN_8021Q=m
 CONFIG_BRIDGE_VLAN_FILTERING=y
+CONFIG_BRIDGE_IGMP_SNOOPING=y
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_NET_VRF=m
diff --git a/tools/testing/selftests/net/forwarding/tc_taprio.sh b/tools/testing/selftests/net/forwarding/tc_taprio.sh
new file mode 100755
index 000000000000..8992aeabfe0b
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/tc_taprio.sh
@@ -0,0 +1,421 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS=" \
+	test_clock_jump_backward \
+	test_taprio_after_ptp \
+	test_max_sdu \
+	test_clock_jump_backward_forward \
+"
+NUM_NETIFS=4
+source tc_common.sh
+source lib.sh
+source tsn_lib.sh
+
+require_command python3
+
+# The test assumes the usual topology from the README, where h1 is connected to
+# swp1, h2 to swp2, and swp1 and swp2 are together in a bridge.
+# Additional assumption: h1 and h2 use the same PHC, and so do swp1 and swp2.
+# By synchronizing h1 to swp1 via PTP, h2 is also implicitly synchronized to
+# swp1 (and both to CLOCK_REALTIME).
+h1=${NETIFS[p1]}
+swp1=${NETIFS[p2]}
+swp2=${NETIFS[p3]}
+h2=${NETIFS[p4]}
+
+UDS_ADDRESS_H1="/var/run/ptp4l_h1"
+UDS_ADDRESS_SWP1="/var/run/ptp4l_swp1"
+
+H1_IPV4="192.0.2.1"
+H2_IPV4="192.0.2.2"
+H1_IPV6="2001:db8:1::1"
+H2_IPV6="2001:db8:1::2"
+
+# Tunables
+NUM_PKTS=100
+STREAM_VID=10
+STREAM_PRIO_1=6
+STREAM_PRIO_2=5
+STREAM_PRIO_3=4
+# PTP uses TC 0
+ALL_GATES=$((1 << 0 | 1 << STREAM_PRIO_1 | 1 << STREAM_PRIO_2))
+# Use a conservative cycle of 10 ms to allow the test to still pass when the
+# kernel has some extra overhead like lockdep etc
+CYCLE_TIME_NS=10000000
+# Create two Gate Control List entries, one OPEN and one CLOSE, of equal
+# durations
+GATE_DURATION_NS=$((CYCLE_TIME_NS / 2))
+# Give 2/3 of the cycle time to user space and 1/3 to the kernel
+FUDGE_FACTOR=$((CYCLE_TIME_NS / 3))
+# Shift the isochron base time by half the gate time, so that packets are
+# always received by swp1 close to the middle of the time slot, to minimize
+# inaccuracies due to network sync
+SHIFT_TIME_NS=$((GATE_DURATION_NS / 2))
+
+path_delay=
+
+h1_create()
+{
+	simple_if_init $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+h2_destroy()
+{
+	simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+switch_create()
+{
+	local h2_mac_addr=$(mac_get $h2)
+
+	ip link set $swp1 up
+	ip link set $swp2 up
+
+	ip link add br0 type bridge vlan_filtering 1
+	ip link set $swp1 master br0
+	ip link set $swp2 master br0
+	ip link set br0 up
+
+	bridge vlan add dev $swp2 vid $STREAM_VID
+	bridge vlan add dev $swp1 vid $STREAM_VID
+	bridge fdb add dev $swp2 \
+		$h2_mac_addr vlan $STREAM_VID static master
+}
+
+switch_destroy()
+{
+	ip link del br0
+}
+
+ptp_setup()
+{
+	# Set up swp1 as a master PHC for h1, synchronized to the local
+	# CLOCK_REALTIME.
+	phc2sys_start $UDS_ADDRESS_SWP1
+	ptp4l_start $h1 true $UDS_ADDRESS_H1
+	ptp4l_start $swp1 false $UDS_ADDRESS_SWP1
+}
+
+ptp_cleanup()
+{
+	ptp4l_stop $swp1
+	ptp4l_stop $h1
+	phc2sys_stop
+}
+
+txtime_setup()
+{
+	local if_name=$1
+
+	tc qdisc add dev $if_name clsact
+	# Classify PTP on TC 7 and isochron on TC 6
+	tc filter add dev $if_name egress protocol 0x88f7 \
+		flower action skbedit priority 7
+	tc filter add dev $if_name egress protocol 802.1Q \
+		flower vlan_ethtype 0xdead action skbedit priority 6
+	tc qdisc add dev $if_name handle 100: parent root mqprio num_tc 8 \
+		queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
+		map 0 1 2 3 4 5 6 7 \
+		hw 1
+	# Set up TC 5, 6, 7 for SO_TXTIME. tc-mqprio queues count from 1.
+	tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_1 + 1)) etf \
+		clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+	tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_2 + 1)) etf \
+		clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+	tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_3 + 1)) etf \
+		clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+}
+
+txtime_cleanup()
+{
+	local if_name=$1
+
+	tc qdisc del dev $if_name clsact
+	tc qdisc del dev $if_name root
+}
+
+taprio_replace()
+{
+	local if_name="$1"; shift
+	local extra_args="$1"; shift
+
+	# STREAM_PRIO_1 always has an open gate.
+	# STREAM_PRIO_2 has a gate open for GATE_DURATION_NS (half the cycle time)
+	# STREAM_PRIO_3 always has a closed gate.
+	tc qdisc replace dev $if_name root stab overhead 24 taprio num_tc 8 \
+		queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
+		map 0 1 2 3 4 5 6 7 \
+		sched-entry S $(printf "%x" $ALL_GATES) $GATE_DURATION_NS \
+		sched-entry S $(printf "%x" $((ALL_GATES & ~(1 << STREAM_PRIO_2)))) $GATE_DURATION_NS \
+		base-time 0 flags 0x2 $extra_args
+	taprio_wait_for_admin $if_name
+}
+
+taprio_cleanup()
+{
+	local if_name=$1
+
+	tc qdisc del dev $if_name root
+}
+
+probe_path_delay()
+{
+	local isochron_dat="$(mktemp)"
+	local received
+
+	log_info "Probing path delay"
+
+	isochron_do "$h1" "$h2" "$UDS_ADDRESS_H1" "" 0 \
+		"$CYCLE_TIME_NS" "" "" "$NUM_PKTS" \
+		"$STREAM_VID" "$STREAM_PRIO_1" "" "$isochron_dat"
+
+	received=$(isochron_report_num_received "$isochron_dat")
+	if [ "$received" != "$NUM_PKTS" ]; then
+		echo "Cannot establish basic data path between $h1 and $h2"
+		exit $ksft_fail
+	fi
+
+	printf "pdelay = {}\n" > isochron_data.py
+	isochron report --input-file "$isochron_dat" \
+		--printf-format "pdelay[%u] = %d - %d\n" \
+		--printf-args "qRT" \
+		>> isochron_data.py
+	cat <<-'EOF' > isochron_postprocess.py
+	#!/usr/bin/env python3
+
+	from isochron_data import pdelay
+	import numpy as np
+
+	w = np.array(list(pdelay.values()))
+	print("{}".format(np.max(w)))
+	EOF
+	path_delay=$(python3 ./isochron_postprocess.py)
+
+	log_info "Path delay from $h1 to $h2 estimated at $path_delay ns"
+
+	if [ "$path_delay" -gt "$GATE_DURATION_NS" ]; then
+		echo "Path delay larger than gate duration, aborting"
+		exit $ksft_fail
+	fi
+
+	rm -f ./isochron_data.py 2> /dev/null
+	rm -f ./isochron_postprocess.py 2> /dev/null
+	rm -f "$isochron_dat" 2> /dev/null
+}
+
+setup_prepare()
+{
+	vrf_prepare
+
+	h1_create
+	h2_create
+	switch_create
+
+	txtime_setup $h1
+
+	# Temporarily set up PTP just to probe the end-to-end path delay.
+	ptp_setup
+	probe_path_delay
+	ptp_cleanup
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	isochron_recv_stop
+	txtime_cleanup $h1
+
+	switch_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+run_test()
+{
+	local base_time=$1; shift
+	local stream_prio=$1; shift
+	local expected_delay=$1; shift
+	local should_fail=$1; shift
+	local test_name=$1; shift
+	local isochron_dat="$(mktemp)"
+	local received
+	local median_delay
+
+	RET=0
+
+	# Set the shift time equal to the cycle time, which effectively
+	# cancels the default advance time. Packets won't be sent early in
+	# software, which ensures that they won't prematurely enter through
+	# the open gate in __test_out_of_band(). Also, the gate is open for
+	# long enough that this won't cause a problem in __test_in_band().
+	isochron_do "$h1" "$h2" "$UDS_ADDRESS_H1" "" "$base_time" \
+		"$CYCLE_TIME_NS" "$SHIFT_TIME_NS" "$GATE_DURATION_NS" \
+		"$NUM_PKTS" "$STREAM_VID" "$stream_prio" "" "$isochron_dat"
+
+	received=$(isochron_report_num_received "$isochron_dat")
+	[ "$received" = "$NUM_PKTS" ]
+	check_err_fail $should_fail $? "Reception of $NUM_PKTS packets"
+
+	if [ $should_fail = 0 ] && [ "$received" = "$NUM_PKTS" ]; then
+		printf "pdelay = {}\n" > isochron_data.py
+		isochron report --input-file "$isochron_dat" \
+			--printf-format "pdelay[%u] = %d - %d\n" \
+			--printf-args "qRT" \
+			>> isochron_data.py
+		cat <<-'EOF' > isochron_postprocess.py
+		#!/usr/bin/env python3
+
+		from isochron_data import pdelay
+		import numpy as np
+
+		w = np.array(list(pdelay.values()))
+		print("{}".format(int(np.median(w))))
+		EOF
+		median_delay=$(python3 ./isochron_postprocess.py)
+
+		# If the condition below is true, packets were delayed by a closed gate
+		[ "$median_delay" -gt $((path_delay + expected_delay)) ]
+		check_fail $? "Median delay $median_delay is greater than expected delay $expected_delay plus path delay $path_delay"
+
+		# If the condition below is true, packets were sent expecting them to
+		# hit a closed gate in the switch, but were not delayed
+		[ "$expected_delay" -gt 0 ] && [ "$median_delay" -lt "$expected_delay" ]
+		check_fail $? "Median delay $median_delay is less than expected delay $expected_delay"
+	fi
+
+	log_test "$test_name"
+
+	rm -f ./isochron_data.py 2> /dev/null
+	rm -f ./isochron_postprocess.py 2> /dev/null
+	rm -f "$isochron_dat" 2> /dev/null
+}
+
+__test_always_open()
+{
+	run_test 0.000000000 $STREAM_PRIO_1 0 0 "Gate always open"
+}
+
+__test_always_closed()
+{
+	run_test 0.000000000 $STREAM_PRIO_3 0 1 "Gate always closed"
+}
+
+__test_in_band()
+{
+	# Send packets in-band with the OPEN gate entry
+	run_test 0.000000000 $STREAM_PRIO_2 0 0 "In band with gate"
+}
+
+__test_out_of_band()
+{
+	# Send packets in-band with the CLOSE gate entry
+	run_test 0.005000000 $STREAM_PRIO_2 \
+		$((GATE_DURATION_NS - SHIFT_TIME_NS)) 0 \
+		"Out of band with gate"
+}
+
+run_subtests()
+{
+	__test_always_open
+	__test_always_closed
+	__test_in_band
+	__test_out_of_band
+}
+
+test_taprio_after_ptp()
+{
+	log_info "Setting up taprio after PTP"
+	ptp_setup
+	taprio_replace $swp2
+	run_subtests
+	taprio_cleanup $swp2
+	ptp_cleanup
+}
+
+__test_under_max_sdu()
+{
+	# Limit max-sdu for STREAM_PRIO_1
+	taprio_replace "$swp2" "max-sdu 0 0 0 0 0 0 100 0"
+	run_test 0.000000000 $STREAM_PRIO_1 0 0 "Under maximum SDU"
+}
+
+__test_over_max_sdu()
+{
+	# Limit max-sdu for STREAM_PRIO_1
+	taprio_replace "$swp2" "max-sdu 0 0 0 0 0 0 20 0"
+	run_test 0.000000000 $STREAM_PRIO_1 0 1 "Over maximum SDU"
+}
+
+test_max_sdu()
+{
+	ptp_setup
+	__test_under_max_sdu
+	__test_over_max_sdu
+	taprio_cleanup $swp2
+	ptp_cleanup
+}
+
+# Perform a clock jump in the past without synchronization running, so that the
+# time base remains where it was set by phc_ctl.
+test_clock_jump_backward()
+{
+	# This is a more complex schedule specifically crafted in a way that
+	# has been problematic on NXP LS1028A. Not much to test with it other
+	# than the fact that it passes traffic.
+	tc qdisc replace dev $swp2 root stab overhead 24 taprio num_tc 8 \
+		queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 map 0 1 2 3 4 5 6 7 \
+		base-time 0 sched-entry S 20 300000 sched-entry S 10 200000 \
+		sched-entry S 20 300000 sched-entry S 48 200000 \
+		sched-entry S 20 300000 sched-entry S 83 200000 \
+		sched-entry S 40 300000 sched-entry S 00 200000 flags 2
+
+	log_info "Forcing a backward clock jump"
+	phc_ctl $swp1 set 0
+
+	ping_test $h1 192.0.2.2
+	taprio_cleanup $swp2
+}
+
+# Test that taprio tolerates clock jumps.
+# Since ptp4l and phc2sys are running, it is expected for the time to
+# eventually recover (through yet another clock jump). Isochron waits
+# until that is the case.
+test_clock_jump_backward_forward()
+{
+	log_info "Forcing a backward and a forward clock jump"
+	taprio_replace $swp2
+	phc_ctl $swp1 set 0
+	ptp_setup
+	ping_test $h1 192.0.2.2
+	run_subtests
+	ptp_cleanup
+	taprio_cleanup $swp2
+}
+
+tc_offload_check
+if [[ $? -ne 0 ]]; then
+	log_test_skip "Could not test offloaded functionality"
+	exit $EXIT_STATUS
+fi
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tsn_lib.sh b/tools/testing/selftests/net/forwarding/tsn_lib.sh
index b91bcd8008a9..08c044ff6689 100644
--- a/tools/testing/selftests/net/forwarding/tsn_lib.sh
+++ b/tools/testing/selftests/net/forwarding/tsn_lib.sh
@@ -2,6 +2,8 @@
 # SPDX-License-Identifier: GPL-2.0
 # Copyright 2021-2022 NXP
 
+tc_testing_scripts_dir=$(dirname $0)/../../tc-testing/scripts
+
 REQUIRE_ISOCHRON=${REQUIRE_ISOCHRON:=yes}
 REQUIRE_LINUXPTP=${REQUIRE_LINUXPTP:=yes}
 
@@ -18,6 +20,7 @@ fi
 if [[ "$REQUIRE_LINUXPTP" = "yes" ]]; then
 	require_command phc2sys
 	require_command ptp4l
+	require_command phc_ctl
 fi
 
 phc2sys_start()
@@ -182,6 +185,7 @@ isochron_do()
 	local base_time=$1; shift
 	local cycle_time=$1; shift
 	local shift_time=$1; shift
+	local window_size=$1; shift
 	local num_pkts=$1; shift
 	local vid=$1; shift
 	local priority=$1; shift
@@ -212,6 +216,10 @@ isochron_do()
 		extra_args="${extra_args} --shift-time=${shift_time}"
 	fi
 
+	if ! [ -z "${window_size}" ]; then
+		extra_args="${extra_args} --window-size=${window_size}"
+	fi
+
 	if [ "${use_l2}" = "true" ]; then
 		extra_args="${extra_args} --l2 --etype=0xdead ${vid}"
 		receiver_extra_args="--l2 --etype=0xdead"
@@ -247,3 +255,21 @@ isochron_do()
 
 	cpufreq_restore ${ISOCHRON_CPU}
 }
+
+isochron_report_num_received()
+{
+	local isochron_dat=$1; shift
+
+	# Count all received packets by looking at the non-zero RX timestamps
+	isochron report \
+		--input-file "${isochron_dat}" \
+		--printf-format "%u\n" --printf-args "R" | \
+		grep -w -v '0' | wc -l
+}
+
+taprio_wait_for_admin()
+{
+	local if_name="$1"; shift
+
+	"$tc_testing_scripts_dir/taprio_wait_for_admin.sh" "$(which tc)" "$if_name"
+}
diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
new file mode 100755
index 000000000000..5b34f6e1f831
--- /dev/null
+++ b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
@@ -0,0 +1,177 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./lib.sh
+
+PAUSE_ON_FAIL="no"
+
+# The trap function handler
+#
+exit_cleanup_all()
+{
+	cleanup_all_ns
+
+	exit "${EXIT_STATUS}"
+}
+
+# Add fake IPv4 and IPv6 networks on the loopback device, to be used as
+# underlay by future GRE devices.
+#
+setup_basenet()
+{
+	ip -netns "${NS0}" link set dev lo up
+	ip -netns "${NS0}" address add dev lo 192.0.2.10/24
+	ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad
+}
+
+# Check if network device has an IPv6 link-local address assigned.
+#
+# Parameters:
+#
+#   * $1: The network device to test
+#   * $2: An extra regular expression that should be matched (to verify the
+#         presence of extra attributes)
+#   * $3: The expected return code from grep (to allow checking the absence of
+#         a link-local address)
+#   * $4: The user visible name for the scenario being tested
+#
+check_ipv6_ll_addr()
+{
+	local DEV="$1"
+	local EXTRA_MATCH="$2"
+	local XRET="$3"
+	local MSG="$4"
+
+	RET=0
+	set +e
+	ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}"
+	check_err_fail "${XRET}" $? ""
+	log_test "${MSG}"
+	set -e
+}
+
+# Create a GRE device and verify that it gets an IPv6 link-local address as
+# expected.
+#
+# Parameters:
+#
+#   * $1: The device type (gre, ip6gre, gretap or ip6gretap)
+#   * $2: The local underlay IP address (can be an IPv4, an IPv6 or "any")
+#   * $3: The remote underlay IP address (can be an IPv4, an IPv6 or "any")
+#   * $4: The IPv6 interface identifier generation mode to use for the GRE
+#         device (eui64, none, stable-privacy or random).
+#
+test_gre_device()
+{
+	local GRE_TYPE="$1"
+	local LOCAL_IP="$2"
+	local REMOTE_IP="$3"
+	local MODE="$4"
+	local ADDR_GEN_MODE
+	local MATCH_REGEXP
+	local MSG
+
+	ip link add netns "${NS0}" name gretest type "${GRE_TYPE}" local "${LOCAL_IP}" remote "${REMOTE_IP}"
+
+	case "${MODE}" in
+	    "eui64")
+		ADDR_GEN_MODE=0
+		MATCH_REGEXP=""
+		MSG="${GRE_TYPE}, mode: 0 (EUI64), ${LOCAL_IP} -> ${REMOTE_IP}"
+		XRET=0
+		;;
+	    "none")
+		ADDR_GEN_MODE=1
+		MATCH_REGEXP=""
+		MSG="${GRE_TYPE}, mode: 1 (none), ${LOCAL_IP} -> ${REMOTE_IP}"
+		XRET=1 # No link-local address should be generated
+		;;
+	    "stable-privacy")
+		ADDR_GEN_MODE=2
+		MATCH_REGEXP="stable-privacy"
+		MSG="${GRE_TYPE}, mode: 2 (stable privacy), ${LOCAL_IP} -> ${REMOTE_IP}"
+		XRET=0
+		# Initialise stable_secret (required for stable-privacy mode)
+		ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.stable_secret="2001:db8::abcd"
+		;;
+	    "random")
+		ADDR_GEN_MODE=3
+		MATCH_REGEXP="stable-privacy"
+		MSG="${GRE_TYPE}, mode: 3 (random), ${LOCAL_IP} -> ${REMOTE_IP}"
+		XRET=0
+		;;
+	esac
+
+	# Check that IPv6 link-local address is generated when device goes up
+	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+	ip -netns "${NS0}" link set dev gretest up
+	check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}"
+
+	# Now disable link-local address generation
+	ip -netns "${NS0}" link set dev gretest down
+	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1
+	ip -netns "${NS0}" link set dev gretest up
+
+	# Check that link-local address generation works when re-enabled while
+	# the device is already up
+	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+	check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}"
+
+	ip -netns "${NS0}" link del dev gretest
+}
+
+test_gre4()
+{
+	local GRE_TYPE
+	local MODE
+
+	for GRE_TYPE in "gre" "gretap"; do
+		printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+		for MODE in "eui64" "none" "stable-privacy" "random"; do
+			test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}"
+			test_gre_device "${GRE_TYPE}" any 192.0.2.11 "${MODE}"
+			test_gre_device "${GRE_TYPE}" 192.0.2.10 any "${MODE}"
+		done
+	done
+}
+
+test_gre6()
+{
+	local GRE_TYPE
+	local MODE
+
+	for GRE_TYPE in "ip6gre" "ip6gretap"; do
+		printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+		for MODE in "eui64" "none" "stable-privacy" "random"; do
+			test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}"
+			test_gre_device "${GRE_TYPE}" any 2001:db8::11 "${MODE}"
+			test_gre_device "${GRE_TYPE}" 2001:db8::10 any "${MODE}"
+		done
+	done
+}
+
+usage()
+{
+	echo "Usage: $0 [-p]"
+	exit 1
+}
+
+while getopts :p o
+do
+	case $o in
+		p) PAUSE_ON_FAIL="yes";;
+		*) usage;;
+	esac
+done
+
+setup_ns NS0
+
+set -e
+trap exit_cleanup_all EXIT
+
+setup_basenet
+
+test_gre4
+test_gre6
diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh
index d6f0e449c029..b13c89a99ecb 100755
--- a/tools/testing/selftests/net/icmp_redirect.sh
+++ b/tools/testing/selftests/net/icmp_redirect.sh
@@ -178,8 +178,6 @@ setup()
 		else
 			ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
 			ip netns exec $ns sysctl -q -w net.ipv4.conf.all.send_redirects=1
-			ip netns exec $ns sysctl -q -w net.ipv4.conf.default.rp_filter=0
-			ip netns exec $ns sysctl -q -w net.ipv4.conf.all.rp_filter=0
 
 			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
 			ip netns exec $ns sysctl -q -w net.ipv6.route.mtu_expires=10
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 701905eeff66..7962da06f816 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -217,6 +217,8 @@ setup_ns()
 			return $ksft_skip
 		fi
 		ip -n "${!ns_name}" link set lo up
+		ip netns exec "${!ns_name}" sysctl -wq net.ipv4.conf.all.rp_filter=0
+		ip netns exec "${!ns_name}" sysctl -wq net.ipv4.conf.default.rp_filter=0
 		ns_list+=("${!ns_name}")
 	done
 	NS_LIST+=("${ns_list[@]}")
@@ -270,6 +272,30 @@ tc_rule_handle_stats_get()
 		  .options.actions[0].stats$selector"
 }
 
+# attach a qdisc with two children match/no-match and a flower filter to match
+tc_set_flower_counter() {
+	local -r ns=$1
+	local -r ipver=$2
+	local -r dev=$3
+	local -r flower_expr=$4
+
+	tc -n $ns qdisc add dev $dev root handle 1: prio bands 2 \
+			priomap 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
+
+	tc -n $ns qdisc add dev $dev parent 1:1 handle 11: pfifo
+	tc -n $ns qdisc add dev $dev parent 1:2 handle 12: pfifo
+
+	tc -n $ns filter add dev $dev parent 1: protocol ipv$ipver \
+			flower $flower_expr classid 1:2
+}
+
+tc_get_flower_counter() {
+	local -r ns=$1
+	local -r dev=$2
+
+	tc -n $ns -j -s qdisc show dev $dev handle 12: | jq .[0].packets
+}
+
 ret_set_ksft_status()
 {
 	local ksft_status=$1; shift
diff --git a/tools/testing/selftests/net/lib/.gitignore b/tools/testing/selftests/net/lib/.gitignore
index 1ebc6187f421..bbc97d6bf556 100644
--- a/tools/testing/selftests/net/lib/.gitignore
+++ b/tools/testing/selftests/net/lib/.gitignore
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 csum
+xdp_helper
diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile
index c22623b9a2a5..88c4bc461459 100644
--- a/tools/testing/selftests/net/lib/Makefile
+++ b/tools/testing/selftests/net/lib/Makefile
@@ -10,6 +10,7 @@ TEST_FILES += ../../../../net/ynl
 
 TEST_GEN_FILES += csum
 TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
+TEST_GEN_FILES += xdp_helper
 
 TEST_INCLUDES := $(wildcard py/*.py sh/*.sh)
 
diff --git a/tools/testing/selftests/net/lib/ksft.h b/tools/testing/selftests/net/lib/ksft.h
new file mode 100644
index 000000000000..17dc34a612c6
--- /dev/null
+++ b/tools/testing/selftests/net/lib/ksft.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if !defined(__NET_KSFT_H__)
+#define __NET_KSFT_H__
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+static inline void ksft_ready(void)
+{
+	const char msg[7] = "ready\n";
+	char *env_str;
+	int fd;
+
+	env_str = getenv("KSFT_READY_FD");
+	if (env_str) {
+		fd = atoi(env_str);
+		if (!fd) {
+			fprintf(stderr, "invalid KSFT_READY_FD = '%s'\n",
+				env_str);
+			return;
+		}
+	} else {
+		fd = STDOUT_FILENO;
+	}
+
+	write(fd, msg, sizeof(msg));
+	if (fd != STDOUT_FILENO)
+		close(fd);
+}
+
+static inline void ksft_wait(void)
+{
+	char *env_str;
+	char byte;
+	int fd;
+
+	env_str = getenv("KSFT_WAIT_FD");
+	if (env_str) {
+		fd = atoi(env_str);
+		if (!fd) {
+			fprintf(stderr, "invalid KSFT_WAIT_FD = '%s'\n",
+				env_str);
+			return;
+		}
+	} else {
+		/* Not running in KSFT env, wait for input from STDIN instead */
+		fd = STDIN_FILENO;
+	}
+
+	read(fd, &byte, sizeof(byte));
+	if (fd != STDIN_FILENO)
+		close(fd);
+}
+
+#endif
diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py
index 3cfad0fd4570..61287c203b6e 100644
--- a/tools/testing/selftests/net/lib/py/ksft.py
+++ b/tools/testing/selftests/net/lib/py/ksft.py
@@ -3,6 +3,7 @@
 import builtins
 import functools
 import inspect
+import signal
 import sys
 import time
 import traceback
@@ -26,6 +27,10 @@ class KsftXfailEx(Exception):
     pass
 
 
+class KsftTerminate(KeyboardInterrupt):
+    pass
+
+
 def ksft_pr(*objs, **kwargs):
     print("#", *objs, **kwargs)
 
@@ -193,6 +198,17 @@ def ksft_setup(env):
     return env
 
 
+def _ksft_intr(signum, frame):
+    # ksft runner.sh sends 2 SIGTERMs in a row on a timeout
+    # if we don't ignore the second one it will stop us from handling cleanup
+    global term_cnt
+    term_cnt += 1
+    if term_cnt == 1:
+        raise KsftTerminate()
+    else:
+        ksft_pr(f"Ignoring SIGTERM (cnt: {term_cnt}), already exiting...")
+
+
 def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
     cases = cases or []
 
@@ -205,6 +221,10 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
                     cases.append(value)
                     break
 
+    global term_cnt
+    term_cnt = 0
+    prev_sigterm = signal.signal(signal.SIGTERM, _ksft_intr)
+
     totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0}
 
     print("TAP version 13")
@@ -233,7 +253,7 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
             for line in tb.strip().split('\n'):
                 ksft_pr("Exception|", line)
             if stop:
-                ksft_pr("Stopping tests due to KeyboardInterrupt.")
+                ksft_pr(f"Stopping tests due to {type(e).__name__}.")
             KSFT_RESULT = False
             cnt_key = 'fail'
 
@@ -248,6 +268,8 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
         if stop:
             break
 
+    signal.signal(signal.SIGTERM, prev_sigterm)
+
     print(
         f"# Totals: pass:{totals['pass']} fail:{totals['fail']} xfail:{totals['xfail']} xpass:0 skip:{totals['skip']} error:0"
     )
diff --git a/tools/testing/selftests/drivers/net/xdp_helper.c b/tools/testing/selftests/net/lib/xdp_helper.c
index aeed25914104..eb025a9f35b1 100644
--- a/tools/testing/selftests/drivers/net/xdp_helper.c
+++ b/tools/testing/selftests/net/lib/xdp_helper.c
@@ -11,55 +11,16 @@
 #include <net/if.h>
 #include <inttypes.h>
 
+#include "ksft.h"
+
 #define UMEM_SZ (1U << 16)
 #define NUM_DESC (UMEM_SZ / 2048)
 
-/* Move this to a common header when reused! */
-static void ksft_ready(void)
-{
-	const char msg[7] = "ready\n";
-	char *env_str;
-	int fd;
-
-	env_str = getenv("KSFT_READY_FD");
-	if (env_str) {
-		fd = atoi(env_str);
-		if (!fd) {
-			fprintf(stderr, "invalid KSFT_READY_FD = '%s'\n",
-				env_str);
-			return;
-		}
-	} else {
-		fd = STDOUT_FILENO;
-	}
-
-	write(fd, msg, sizeof(msg));
-	if (fd != STDOUT_FILENO)
-		close(fd);
-}
 
-static void ksft_wait(void)
+static void print_usage(const char *bin)
 {
-	char *env_str;
-	char byte;
-	int fd;
-
-	env_str = getenv("KSFT_WAIT_FD");
-	if (env_str) {
-		fd = atoi(env_str);
-		if (!fd) {
-			fprintf(stderr, "invalid KSFT_WAIT_FD = '%s'\n",
-				env_str);
-			return;
-		}
-	} else {
-		/* Not running in KSFT env, wait for input from STDIN instead */
-		fd = STDIN_FILENO;
-	}
-
-	read(fd, &byte, sizeof(byte));
-	if (fd != STDIN_FILENO)
-		close(fd);
+	fprintf(stderr, "Usage: %s ifindex queue_id [-z]\n\n"
+		"where:\n\t-z: force zerocopy mode", bin);
 }
 
 /* this is a simple helper program that creates an XDP socket and does the
@@ -77,12 +38,13 @@ int main(int argc, char **argv)
 	struct sockaddr_xdp sxdp = { 0 };
 	int num_desc = NUM_DESC;
 	void *umem_area;
+	int retry = 0;
 	int ifindex;
 	int sock_fd;
 	int queue;
 
-	if (argc != 3) {
-		fprintf(stderr, "Usage: %s ifindex queue_id\n", argv[0]);
+	if (argc != 3 && argc != 4) {
+		print_usage(argv[0]);
 		return 1;
 	}
 
@@ -132,11 +94,29 @@ int main(int argc, char **argv)
 	sxdp.sxdp_queue_id = queue;
 	sxdp.sxdp_flags = 0;
 
-	if (bind(sock_fd, (struct sockaddr *)&sxdp, sizeof(sxdp)) != 0) {
-		munmap(umem_area, UMEM_SZ);
-		perror("bind failed");
-		close(sock_fd);
-		return 1;
+	if (argc > 3) {
+		if (!strcmp(argv[3], "-z")) {
+			sxdp.sxdp_flags = XDP_ZEROCOPY;
+		} else {
+			print_usage(argv[0]);
+			return 1;
+		}
+	}
+
+	while (1) {
+		if (bind(sock_fd, (struct sockaddr *)&sxdp, sizeof(sxdp)) == 0)
+			break;
+
+		if (errno == EBUSY && retry < 3) {
+			retry++;
+			sleep(1);
+			continue;
+		} else {
+			perror("bind failed");
+			munmap(umem_area, UMEM_SZ);
+			close(sock_fd);
+			return 1;
+		}
 	}
 
 	ksft_ready();
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 4f55477ffe08..7a3cb4c09e45 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -206,9 +206,8 @@ chk_dump_one()
 	local token
 	local msg
 
-	ss_token="$(ss -inmHMN $ns | grep 'token:' |\
-		    head -n 1 |\
-		    sed 's/.*token:\([0-9a-f]*\).*/\1/')"
+	ss_token="$(ss -inmHMN $ns |
+		    mptcp_lib_get_info_value "token" "token")"
 
 	token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\
 		 awk -F':[ \t]+' '/^token/ {print $2}')"
@@ -226,6 +225,37 @@ chk_dump_one()
 	fi
 }
 
+chk_dump_subflow()
+{
+	local inet_diag_token
+	local subflow_line
+	local ss_output
+	local ss_token
+	local msg
+
+	ss_output=$(ss -tniN $ns)
+
+	subflow_line=$(echo "$ss_output" | \
+		       grep -m1 -Eo '[0-9.]+:[0-9].+ +[0-9.]+:[0-9.]+')
+
+	ss_token=$(echo "$ss_output" | grep -m1 -Eo 'token:[^ ]+')
+
+	inet_diag_token=$(ip netns exec $ns ./mptcp_diag -s "$subflow_line" | \
+			  grep -Eo 'token:[^ ]+')
+
+	msg="....chk dump_subflow"
+
+	mptcp_lib_print_title "$msg"
+	if [ -n "$ss_token" ] && [ "$ss_token" = "$inet_diag_token" ]; then
+		mptcp_lib_pr_ok
+		mptcp_lib_result_pass "${msg}"
+	else
+		mptcp_lib_pr_fail "expected $ss_token found $inet_diag_token"
+		mptcp_lib_result_fail "${msg}"
+		ret=${KSFT_FAIL}
+	fi
+}
+
 msk_info_get_value()
 {
 	local port="${1}"
@@ -317,6 +347,7 @@ chk_msk_fallback_nr 0 "....chk no fallback"
 chk_msk_inuse 2
 chk_msk_cestab 2
 chk_dump_one
+chk_dump_subflow
 flush_pids
 
 chk_msk_inuse 0 "2->0"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index c83a8b47bbdf..ac1349c4b9e5 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -180,13 +180,26 @@ static void xgetnameinfo(const struct sockaddr *addr, socklen_t addrlen,
 }
 
 static void xgetaddrinfo(const char *node, const char *service,
-			 const struct addrinfo *hints,
+			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
+again:
 	int err = getaddrinfo(node, service, hints, res);
 
 	if (err) {
-		const char *errstr = getxinfo_strerr(err);
+		const char *errstr;
+
+		/* glibc starts to support MPTCP since v2.42.
+		 * For older versions, use IPPROTO_TCP to resolve,
+		 * and use TCP/MPTCP to create socket.
+		 * Link: https://sourceware.org/git/?p=glibc.git;a=commit;h=a8e9022e0f82
+		 */
+		if (err == EAI_SOCKTYPE) {
+			hints->ai_protocol = IPPROTO_TCP;
+			goto again;
+		}
+
+		errstr = getxinfo_strerr(err);
 
 		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
 			node ? node : "", service ? service : "", errstr);
@@ -292,7 +305,7 @@ static int sock_listen_mptcp(const char * const listenaddr,
 {
 	int sock = -1;
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
 	};
@@ -356,7 +369,7 @@ static int sock_connect_mptcp(const char * const remoteaddr,
 			      int infd, struct wstate *winfo)
 {
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 	};
 	struct addrinfo *a, *addr;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c
index 284286c524cf..e084796e804d 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_diag.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c
@@ -8,6 +8,7 @@
 #include <sys/socket.h>
 #include <netinet/in.h>
 #include <linux/tcp.h>
+#include <arpa/inet.h>
 
 #include <unistd.h>
 #include <stdlib.h>
@@ -19,6 +20,15 @@
 #define IPPROTO_MPTCP 262
 #endif
 
+#define parse_rtattr_nested(tb, max, rta) \
+	(parse_rtattr_flags((tb), (max), RTA_DATA(rta), RTA_PAYLOAD(rta), \
+			    NLA_F_NESTED))
+
+struct params {
+	__u32 target_token;
+	char subflow_addrs[1024];
+};
+
 struct mptcp_info {
 	__u8	mptcpi_subflows;
 	__u8	mptcpi_add_addr_signal;
@@ -46,6 +56,37 @@ struct mptcp_info {
 	__u32	mptcpi_last_ack_recv;
 };
 
+enum {
+	MPTCP_SUBFLOW_ATTR_UNSPEC,
+	MPTCP_SUBFLOW_ATTR_TOKEN_REM,
+	MPTCP_SUBFLOW_ATTR_TOKEN_LOC,
+	MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ,
+	MPTCP_SUBFLOW_ATTR_MAP_SEQ,
+	MPTCP_SUBFLOW_ATTR_MAP_SFSEQ,
+	MPTCP_SUBFLOW_ATTR_SSN_OFFSET,
+	MPTCP_SUBFLOW_ATTR_MAP_DATALEN,
+	MPTCP_SUBFLOW_ATTR_FLAGS,
+	MPTCP_SUBFLOW_ATTR_ID_REM,
+	MPTCP_SUBFLOW_ATTR_ID_LOC,
+	MPTCP_SUBFLOW_ATTR_PAD,
+
+	__MPTCP_SUBFLOW_ATTR_MAX
+};
+
+#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1)
+
+#define MPTCP_SUBFLOW_FLAG_MCAP_REM		_BITUL(0)
+#define MPTCP_SUBFLOW_FLAG_MCAP_LOC		_BITUL(1)
+#define MPTCP_SUBFLOW_FLAG_JOIN_REM		_BITUL(2)
+#define MPTCP_SUBFLOW_FLAG_JOIN_LOC		_BITUL(3)
+#define MPTCP_SUBFLOW_FLAG_BKUP_REM		_BITUL(4)
+#define MPTCP_SUBFLOW_FLAG_BKUP_LOC		_BITUL(5)
+#define MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED	_BITUL(6)
+#define MPTCP_SUBFLOW_FLAG_CONNECTED		_BITUL(7)
+#define MPTCP_SUBFLOW_FLAG_MAPVALID		_BITUL(8)
+
+#define rta_getattr(type, value)		(*(type *)RTA_DATA(value))
+
 static void die_perror(const char *msg)
 {
 	perror(msg);
@@ -54,11 +95,13 @@ static void die_perror(const char *msg)
 
 static void die_usage(int r)
 {
-	fprintf(stderr, "Usage: mptcp_diag -t\n");
+	fprintf(stderr, "Usage:\n"
+			"mptcp_diag -t <token>\n"
+			"mptcp_diag -s \"<saddr>:<sport> <daddr>:<dport>\"\n");
 	exit(r);
 }
 
-static void send_query(int fd, __u32 token)
+static void send_query(int fd, struct inet_diag_req_v2 *r, __u32 proto)
 {
 	struct sockaddr_nl nladdr = {
 		.nl_family = AF_NETLINK
@@ -72,31 +115,26 @@ static void send_query(int fd, __u32 token)
 			.nlmsg_type = SOCK_DIAG_BY_FAMILY,
 			.nlmsg_flags = NLM_F_REQUEST
 		},
-		.r = {
-			.sdiag_family = AF_INET,
-			/* Real proto is set via INET_DIAG_REQ_PROTOCOL */
-			.sdiag_protocol = IPPROTO_TCP,
-			.id.idiag_cookie[0] = token,
-		}
+		.r = *r
 	};
 	struct rtattr rta_proto;
 	struct iovec iov[6];
-	int iovlen = 1;
-	__u32 proto;
-
-	req.r.idiag_ext |= (1 << (INET_DIAG_INFO - 1));
-	proto = IPPROTO_MPTCP;
-	rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL;
-	rta_proto.rta_len = RTA_LENGTH(sizeof(proto));
+	int iovlen = 0;
 
-	iov[0] = (struct iovec) {
+	iov[iovlen++] = (struct iovec) {
 		.iov_base = &req,
 		.iov_len = sizeof(req)
 	};
-	iov[iovlen] = (struct iovec){ &rta_proto, sizeof(rta_proto)};
-	iov[iovlen + 1] = (struct iovec){ &proto, sizeof(proto)};
-	req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto));
-	iovlen += 2;
+
+	if (proto == IPPROTO_MPTCP) {
+		rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL;
+		rta_proto.rta_len = RTA_LENGTH(sizeof(proto));
+
+		iov[iovlen++] = (struct iovec){ &rta_proto, sizeof(rta_proto)};
+		iov[iovlen++] = (struct iovec){ &proto, sizeof(proto)};
+		req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto));
+	}
+
 	struct msghdr msg = {
 		.msg_name = &nladdr,
 		.msg_namelen = sizeof(nladdr),
@@ -160,7 +198,67 @@ static void print_info_msg(struct mptcp_info *info)
 	printf("bytes_acked:      %llu\n", info->mptcpi_bytes_acked);
 }
 
-static void parse_nlmsg(struct nlmsghdr *nlh)
+/*
+ * 'print_subflow_info' is from 'mptcp_subflow_info'
+ * which is a function in 'misc/ss.c' of iproute2.
+ */
+static void print_subflow_info(struct rtattr *tb[])
+{
+	u_int32_t flags = 0;
+
+	printf("It's a mptcp subflow, the subflow info:\n");
+	if (tb[MPTCP_SUBFLOW_ATTR_FLAGS]) {
+		char caps[32 + 1] = { 0 }, *cap = &caps[0];
+
+		flags = rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_FLAGS]);
+
+		if (flags & MPTCP_SUBFLOW_FLAG_MCAP_REM)
+			*cap++ = 'M';
+		if (flags & MPTCP_SUBFLOW_FLAG_MCAP_LOC)
+			*cap++ = 'm';
+		if (flags & MPTCP_SUBFLOW_FLAG_JOIN_REM)
+			*cap++ = 'J';
+		if (flags & MPTCP_SUBFLOW_FLAG_JOIN_LOC)
+			*cap++ = 'j';
+		if (flags & MPTCP_SUBFLOW_FLAG_BKUP_REM)
+			*cap++ = 'B';
+		if (flags & MPTCP_SUBFLOW_FLAG_BKUP_LOC)
+			*cap++ = 'b';
+		if (flags & MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED)
+			*cap++ = 'e';
+		if (flags & MPTCP_SUBFLOW_FLAG_CONNECTED)
+			*cap++ = 'c';
+		if (flags & MPTCP_SUBFLOW_FLAG_MAPVALID)
+			*cap++ = 'v';
+
+		if (flags)
+			printf(" flags:%s", caps);
+	}
+	if (tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM] &&
+	    tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC] &&
+	    tb[MPTCP_SUBFLOW_ATTR_ID_REM] &&
+	    tb[MPTCP_SUBFLOW_ATTR_ID_LOC])
+		printf(" token:%04x(id:%u)/%04x(id:%u)",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM]),
+		       rta_getattr(__u8, tb[MPTCP_SUBFLOW_ATTR_ID_REM]),
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC]),
+		       rta_getattr(__u8, tb[MPTCP_SUBFLOW_ATTR_ID_LOC]));
+	if (tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ])
+		printf(" seq:%llu",
+		       rta_getattr(__u64, tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ]));
+	if (tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ])
+		printf(" sfseq:%u",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ]));
+	if (tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET])
+		printf(" ssnoff:%u",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET]));
+	if (tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN])
+		printf(" maplen:%u",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN]));
+	printf("\n");
+}
+
+static void parse_nlmsg(struct nlmsghdr *nlh, __u32 proto)
 {
 	struct inet_diag_msg *r = NLMSG_DATA(nlh);
 	struct rtattr *tb[INET_DIAG_MAX + 1];
@@ -169,7 +267,7 @@ static void parse_nlmsg(struct nlmsghdr *nlh)
 			   nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)),
 			   NLA_F_NESTED);
 
-	if (tb[INET_DIAG_INFO]) {
+	if (proto == IPPROTO_MPTCP && tb[INET_DIAG_INFO]) {
 		int len = RTA_PAYLOAD(tb[INET_DIAG_INFO]);
 		struct mptcp_info *info;
 
@@ -183,11 +281,28 @@ static void parse_nlmsg(struct nlmsghdr *nlh)
 		}
 		print_info_msg(info);
 	}
+	if (proto == IPPROTO_TCP && tb[INET_DIAG_ULP_INFO]) {
+		struct rtattr *ulpinfo[INET_ULP_INFO_MAX + 1] = { 0 };
+
+		parse_rtattr_nested(ulpinfo, INET_ULP_INFO_MAX,
+				    tb[INET_DIAG_ULP_INFO]);
+
+		if (ulpinfo[INET_ULP_INFO_MPTCP]) {
+			struct rtattr *sfinfo[MPTCP_SUBFLOW_ATTR_MAX + 1] = { 0 };
+
+			parse_rtattr_nested(sfinfo, MPTCP_SUBFLOW_ATTR_MAX,
+					    ulpinfo[INET_ULP_INFO_MPTCP]);
+			print_subflow_info(sfinfo);
+		} else {
+			printf("It's a normal TCP!\n");
+		}
+	}
 }
 
-static void recv_nlmsg(int fd, struct nlmsghdr *nlh)
+static void recv_nlmsg(int fd, __u32 proto)
 {
 	char rcv_buff[8192];
+	struct nlmsghdr *nlh = (struct nlmsghdr *)rcv_buff;
 	struct sockaddr_nl rcv_nladdr = {
 		.nl_family = AF_NETLINK
 	};
@@ -204,7 +319,6 @@ static void recv_nlmsg(int fd, struct nlmsghdr *nlh)
 	int len;
 
 	len = recvmsg(fd, &rcv_msg, 0);
-	nlh = (struct nlmsghdr *)rcv_buff;
 
 	while (NLMSG_OK(nlh, len)) {
 		if (nlh->nlmsg_type == NLMSG_DONE) {
@@ -218,40 +332,84 @@ static void recv_nlmsg(int fd, struct nlmsghdr *nlh)
 			       -(err->error), strerror(-(err->error)));
 			break;
 		}
-		parse_nlmsg(nlh);
+		parse_nlmsg(nlh, proto);
 		nlh = NLMSG_NEXT(nlh, len);
 	}
 }
 
 static void get_mptcpinfo(__u32 token)
 {
-	struct nlmsghdr *nlh = NULL;
+	struct inet_diag_req_v2 r = {
+		.sdiag_family           = AF_INET,
+		/* Real proto is set via INET_DIAG_REQ_PROTOCOL */
+		.sdiag_protocol         = IPPROTO_TCP,
+		.idiag_ext              = 1 << (INET_DIAG_INFO - 1),
+		.id.idiag_cookie[0]     = token,
+	};
+	__u32 proto = IPPROTO_MPTCP;
 	int fd;
 
 	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
 	if (fd < 0)
 		die_perror("Netlink socket");
 
-	send_query(fd, token);
-	recv_nlmsg(fd, nlh);
+	send_query(fd, &r, proto);
+	recv_nlmsg(fd, proto);
 
 	close(fd);
 }
 
-static void parse_opts(int argc, char **argv, __u32 *target_token)
+static void get_subflow_info(char *subflow_addrs)
+{
+	struct inet_diag_req_v2 r = {
+		.sdiag_family           = AF_INET,
+		.sdiag_protocol         = IPPROTO_TCP,
+		.idiag_ext              = 1 << (INET_DIAG_INFO - 1),
+		.id.idiag_cookie[0]     = INET_DIAG_NOCOOKIE,
+		.id.idiag_cookie[1]     = INET_DIAG_NOCOOKIE,
+	};
+	char saddr[64], daddr[64];
+	int sport, dport;
+	int ret;
+	int fd;
+
+	ret = sscanf(subflow_addrs, "%[^:]:%d %[^:]:%d", saddr, &sport, daddr, &dport);
+	if (ret != 4)
+		die_perror("IP PORT Pairs has style problems!");
+
+	printf("%s:%d -> %s:%d\n", saddr, sport, daddr, dport);
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+	if (fd < 0)
+		die_perror("Netlink socket");
+
+	r.id.idiag_sport = htons(sport);
+	r.id.idiag_dport = htons(dport);
+
+	inet_pton(AF_INET, saddr, &r.id.idiag_src);
+	inet_pton(AF_INET, daddr, &r.id.idiag_dst);
+	send_query(fd, &r, IPPROTO_TCP);
+	recv_nlmsg(fd, IPPROTO_TCP);
+}
+
+static void parse_opts(int argc, char **argv, struct params *p)
 {
 	int c;
 
 	if (argc < 2)
 		die_usage(1);
 
-	while ((c = getopt(argc, argv, "ht:")) != -1) {
+	while ((c = getopt(argc, argv, "ht:s:")) != -1) {
 		switch (c) {
 		case 'h':
 			die_usage(0);
 			break;
 		case 't':
-			sscanf(optarg, "%x", target_token);
+			sscanf(optarg, "%x", &p->target_token);
+			break;
+		case 's':
+			strncpy(p->subflow_addrs, optarg,
+				sizeof(p->subflow_addrs) - 1);
 			break;
 		default:
 			die_usage(1);
@@ -262,10 +420,15 @@ static void parse_opts(int argc, char **argv, __u32 *target_token)
 
 int main(int argc, char *argv[])
 {
-	__u32 target_token;
+	struct params p = { 0 };
+
+	parse_opts(argc, argv, &p);
+
+	if (p.target_token)
+		get_mptcpinfo(p.target_token);
 
-	parse_opts(argc, argv, &target_token);
-	get_mptcpinfo(target_token);
+	if (p.subflow_addrs[0] != '\0')
+		get_subflow_info(p.subflow_addrs);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
index 218aac467321..3cf1e2a612ce 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -72,13 +72,21 @@ static const char *getxinfo_strerr(int err)
 }
 
 static void xgetaddrinfo(const char *node, const char *service,
-			 const struct addrinfo *hints,
+			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
+again:
 	int err = getaddrinfo(node, service, hints, res);
 
 	if (err) {
-		const char *errstr = getxinfo_strerr(err);
+		const char *errstr;
+
+		if (err == EAI_SOCKTYPE) {
+			hints->ai_protocol = IPPROTO_TCP;
+			goto again;
+		}
+
+		errstr = getxinfo_strerr(err);
 
 		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
 			node ? node : "", service ? service : "", errstr);
@@ -91,7 +99,7 @@ static int sock_listen_mptcp(const char * const listenaddr,
 {
 	int sock = -1;
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
 	};
@@ -136,7 +144,7 @@ static int sock_connect_mptcp(const char * const remoteaddr,
 			      const char * const port, int proto)
 {
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 	};
 	struct addrinfo *a, *addr;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index befa66f5a366..b8af65373b3a 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -62,6 +62,7 @@ unset sflags
 unset fastclose
 unset fullmesh
 unset speed
+unset join_syn_rej
 unset join_csum_ns1
 unset join_csum_ns2
 unset join_fail_nr
@@ -1403,6 +1404,7 @@ chk_join_nr()
 	local syn_nr=$1
 	local syn_ack_nr=$2
 	local ack_nr=$3
+	local syn_rej=${join_syn_rej:-0}
 	local csum_ns1=${join_csum_ns1:-0}
 	local csum_ns2=${join_csum_ns2:-0}
 	local fail_nr=${join_fail_nr:-0}
@@ -1468,6 +1470,15 @@ chk_join_nr()
 		fail_test "got $count JOIN[s] ack HMAC failure expected 0"
 	fi
 
+	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinRejected")
+	if [ -z "$count" ]; then
+		rc=${KSFT_SKIP}
+	elif [ "$count" != "$syn_rej" ]; then
+		rc=${KSFT_FAIL}
+		print_check "syn rejected"
+		fail_test "got $count JOIN[s] syn rejected expected $syn_rej"
+	fi
+
 	print_results "join Rx" ${rc}
 
 	join_syn_tx="${join_syn_tx:-${syn_nr}}" \
@@ -1963,7 +1974,8 @@ subflows_tests()
 		pm_nl_set_limits $ns2 0 1
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 0
+		join_syn_rej=1 \
+			chk_join_nr 1 1 0
 	fi
 
 	# subflow
@@ -1992,7 +2004,8 @@ subflows_tests()
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
 		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 2 2 1
+		join_syn_rej=1 \
+			chk_join_nr 2 2 1
 	fi
 
 	# single subflow, dev
@@ -3061,7 +3074,8 @@ syncookies_tests()
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
 		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 2 1 1
+		join_syn_rej=1 \
+			chk_join_nr 2 1 1
 	fi
 
 	# test signal address with cookies
@@ -3545,7 +3559,8 @@ userspace_tests()
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 0
+		join_syn_rej=1 \
+			chk_join_nr 1 1 0
 	fi
 
 	# userspace pm type does not send join
@@ -3568,7 +3583,8 @@ userspace_tests()
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		sflags=backup speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 0
+		join_syn_rej=1 \
+			chk_join_nr 1 1 0
 		chk_prio_nr 0 0 0 0
 	fi
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 051e289d7967..55212188871e 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -331,12 +331,15 @@ mptcp_lib_result_print_all_tap() {
 
 # get the value of keyword $1 in the line marked by keyword $2
 mptcp_lib_get_info_value() {
-	grep "${2}" | sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q'
+	grep "${2}" 2>/dev/null |
+		sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q'
+		# the ';q' at the end limits to the first matched entry.
 }
 
 # $1: info name ; $2: evts_ns ; [$3: event type; [$4: addr]]
 mptcp_lib_evts_get_info() {
-	grep "${4:-}" "${2}" | mptcp_lib_get_info_value "${1}" "^type:${3:-1},"
+	grep "${4:-}" "${2}" 2>/dev/null |
+		mptcp_lib_get_info_value "${1}" "^type:${3:-1},"
 }
 
 # $1: PID
@@ -476,8 +479,6 @@ mptcp_lib_ns_init() {
 	local netns
 	for netns in "${@}"; do
 		ip netns exec "${!netns}" sysctl -q net.mptcp.enabled=1
-		ip netns exec "${!netns}" sysctl -q net.ipv4.conf.all.rp_filter=0
-		ip netns exec "${!netns}" sysctl -q net.ipv4.conf.default.rp_filter=0
 	done
 }
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index 926b0be87c99..9934a68df237 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -159,13 +159,21 @@ static const char *getxinfo_strerr(int err)
 }
 
 static void xgetaddrinfo(const char *node, const char *service,
-			 const struct addrinfo *hints,
+			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
+again:
 	int err = getaddrinfo(node, service, hints, res);
 
 	if (err) {
-		const char *errstr = getxinfo_strerr(err);
+		const char *errstr;
+
+		if (err == EAI_SOCKTYPE) {
+			hints->ai_protocol = IPPROTO_TCP;
+			goto again;
+		}
+
+		errstr = getxinfo_strerr(err);
 
 		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
 			node ? node : "", service ? service : "", errstr);
@@ -178,7 +186,7 @@ static int sock_listen_mptcp(const char * const listenaddr,
 {
 	int sock = -1;
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
 	};
@@ -223,7 +231,7 @@ static int sock_connect_mptcp(const char * const remoteaddr,
 			      const char * const port, int proto)
 {
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 	};
 	struct addrinfo *a, *addr;
diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile
index ffe161fac8b5..3bdcbbdba925 100644
--- a/tools/testing/selftests/net/netfilter/Makefile
+++ b/tools/testing/selftests/net/netfilter/Makefile
@@ -12,6 +12,7 @@ TEST_PROGS += conntrack_dump_flush.sh
 TEST_PROGS += conntrack_icmp_related.sh
 TEST_PROGS += conntrack_ipip_mtu.sh
 TEST_PROGS += conntrack_tcp_unreplied.sh
+TEST_PROGS += conntrack_resize.sh
 TEST_PROGS += conntrack_sctp_collision.sh
 TEST_PROGS += conntrack_vrf.sh
 TEST_PROGS += conntrack_reverse_clash.sh
diff --git a/tools/testing/selftests/net/netfilter/br_netfilter.sh b/tools/testing/selftests/net/netfilter/br_netfilter.sh
index 1559ba275105..011de8763094 100755
--- a/tools/testing/selftests/net/netfilter/br_netfilter.sh
+++ b/tools/testing/selftests/net/netfilter/br_netfilter.sh
@@ -60,9 +60,6 @@ bcast_ping()
 	done
 }
 
-ip netns exec "$ns0" sysctl -q net.ipv4.conf.all.rp_filter=0
-ip netns exec "$ns0" sysctl -q net.ipv4.conf.default.rp_filter=0
-
 if ! ip link add veth1 netns "$ns0" type veth peer name eth0 netns "$ns1"; then
 	echo "SKIP: Can't create veth device"
 	exit $ksft_skip
diff --git a/tools/testing/selftests/net/netfilter/bridge_brouter.sh b/tools/testing/selftests/net/netfilter/bridge_brouter.sh
index 2549b6590693..ea76f2bc2f59 100755
--- a/tools/testing/selftests/net/netfilter/bridge_brouter.sh
+++ b/tools/testing/selftests/net/netfilter/bridge_brouter.sh
@@ -22,8 +22,6 @@ trap cleanup EXIT
 
 setup_ns nsbr ns1 ns2
 
-ip netns exec "$nsbr" sysctl -q net.ipv4.conf.default.rp_filter=0
-ip netns exec "$nsbr" sysctl -q net.ipv4.conf.all.rp_filter=0
 if ! ip link add veth0 netns "$nsbr" type veth peer name eth0 netns "$ns1"; then
 	echo "SKIP: Can't create veth device"
 	exit $ksft_skip
diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config
index 43d8b500d391..363646f4fefe 100644
--- a/tools/testing/selftests/net/netfilter/config
+++ b/tools/testing/selftests/net/netfilter/config
@@ -46,6 +46,7 @@ CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
 CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_PROCFS=y
 CONFIG_NF_CONNTRACK_EVENTS=y
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_MARK=y
diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
new file mode 100755
index 000000000000..9e033e80219e
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
@@ -0,0 +1,427 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+checktool "conntrack --version" "run test without conntrack"
+checktool "nft --version" "run test without nft tool"
+
+init_net_max=0
+ct_buckets=0
+tmpfile=""
+tmpfile_proc=""
+tmpfile_uniq=""
+ret=0
+
+insert_count=2000
+[ "$KSFT_MACHINE_SLOW" = "yes" ] && insert_count=400
+
+modprobe -q nf_conntrack
+if ! sysctl -q net.netfilter.nf_conntrack_max >/dev/null;then
+	echo "SKIP: conntrack sysctls not available"
+	exit $KSFT_SKIP
+fi
+
+init_net_max=$(sysctl -n net.netfilter.nf_conntrack_max) || exit 1
+ct_buckets=$(sysctl -n net.netfilter.nf_conntrack_buckets) || exit 1
+
+cleanup() {
+	cleanup_all_ns
+
+	rm -f "$tmpfile" "$tmpfile_proc" "$tmpfile_uniq"
+
+	# restore original sysctl setting
+	sysctl -q net.netfilter.nf_conntrack_max=$init_net_max
+	sysctl -q net.netfilter.nf_conntrack_buckets=$ct_buckets
+}
+trap cleanup EXIT
+
+check_max_alias()
+{
+	local expected="$1"
+	# old name, expected to alias to the first, i.e. changing one
+	# changes the other as well.
+	local lv=$(sysctl -n net.nf_conntrack_max)
+
+	if [ $expected -ne "$lv" ];then
+		echo "nf_conntrack_max sysctls should have identical values"
+		exit 1
+	fi
+}
+
+insert_ctnetlink() {
+	local ns="$1"
+	local count="$2"
+	local i=0
+	local bulk=16
+
+	while [ $i -lt $count ] ;do
+		ip netns exec "$ns" bash -c "for i in \$(seq 1 $bulk); do \
+			if ! conntrack -I -s \$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%255+1)) \
+					  -d \$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%255+1)) \
+					  --protonum 17 --timeout 3600 --status ASSURED,SEEN_REPLY --sport \$RANDOM --dport 53; then \
+					  return;\
+			fi & \
+		done ; wait" 2>/dev/null
+
+		i=$((i+bulk))
+	done
+}
+
+check_ctcount() {
+	local ns="$1"
+	local count="$2"
+	local msg="$3"
+
+	local now=$(ip netns exec "$ns" conntrack -C)
+
+	if [ $now -ne "$count" ] ;then
+		echo "expected $count entries in $ns, not $now: $msg"
+		exit 1
+	fi
+
+	echo "PASS: got $count connections: $msg"
+}
+
+ctresize() {
+	local duration="$1"
+	local now=$(date +%s)
+	local end=$((now + duration))
+
+	while [ $now -lt $end ]; do
+		sysctl -q net.netfilter.nf_conntrack_buckets=$RANDOM
+		now=$(date +%s)
+	done
+}
+
+do_rsleep() {
+	local limit="$1"
+	local r=$RANDOM
+
+	r=$((r%limit))
+	sleep "$r"
+}
+
+ct_flush_once() {
+	local ns="$1"
+
+	ip netns exec "$ns" conntrack -F 2>/dev/null
+}
+
+ctflush() {
+	local ns="$1"
+	local duration="$2"
+	local now=$(date +%s)
+	local end=$((now + duration))
+
+	do_rsleep "$duration"
+
+        while [ $now -lt $end ]; do
+		ct_flush_once "$ns"
+		do_rsleep "$duration"
+		now=$(date +%s)
+        done
+}
+
+ctflood()
+{
+	local ns="$1"
+	local duration="$2"
+	local msg="$3"
+	local now=$(date +%s)
+	local end=$((now + duration))
+	local j=0
+	local k=0
+
+        while [ $now -lt $end ]; do
+		j=$((j%256))
+		k=$((k%256))
+
+		ip netns exec "$ns" bash -c \
+			"j=$j k=$k; for i in \$(seq 1 254); do ping -q -c 1 127.\$k.\$j.\$i & done; wait" >/dev/null 2>&1
+
+		j=$((j+1))
+
+		if [ $j -eq 256 ];then
+			k=$((k+1))
+		fi
+
+		now=$(date +%s)
+	done
+
+	wait
+}
+
+# dump to /dev/null.  We don't want dumps to cause infinite loops
+# or use-after-free even when conntrack table is altered while dumps
+# are in progress.
+ct_nulldump()
+{
+	local ns="$1"
+
+	ip netns exec "$ns" conntrack -L > /dev/null 2>&1 &
+
+	# Don't require /proc support in conntrack
+	if [ -r /proc/self/net/nf_conntrack ] ; then
+		ip netns exec "$ns" bash -c "wc -l < /proc/self/net/nf_conntrack" > /dev/null &
+	fi
+
+	wait
+}
+
+check_taint()
+{
+	local tainted_then="$1"
+	local msg="$2"
+
+	local tainted_now=0
+
+	if [ "$tainted_then" -ne 0 ];then
+		return
+	fi
+
+	read tainted_now < /proc/sys/kernel/tainted
+
+	if [ "$tainted_now" -eq 0 ];then
+		echo "PASS: $msg"
+	else
+		echo "TAINT: $msg"
+		dmesg
+		exit 1
+	fi
+}
+
+insert_flood()
+{
+	local n="$1"
+	local r=0
+
+	r=$((RANDOM%$insert_count))
+
+	ctflood "$n" "$timeout" "floodresize" &
+	insert_ctnetlink "$n" "$r" &
+	ctflush "$n" "$timeout" &
+	ct_nulldump "$n" &
+
+	wait
+}
+
+test_floodresize_all()
+{
+	local timeout=20
+	local n=""
+	local tainted_then=""
+
+	read tainted_then < /proc/sys/kernel/tainted
+
+	for n in "$nsclient1" "$nsclient2";do
+		insert_flood "$n" &
+	done
+
+	# resize table constantly while flood/insert/dump/flushs
+	# are happening in parallel.
+	ctresize "$timeout"
+
+	# wait for subshells to complete, everything is limited
+	# by $timeout.
+	wait
+
+	check_taint "$tainted_then" "resize+flood"
+}
+
+check_dump()
+{
+	local ns="$1"
+	local protoname="$2"
+	local c=0
+	local proto=0
+	local proc=0
+	local unique=""
+	local lret=0
+
+	# NOTE: assumes timeouts are large enough to not have
+	# expirations in all following tests.
+	l=$(ip netns exec "$ns" conntrack -L 2>/dev/null | sort | tee "$tmpfile" | wc -l)
+	c=$(ip netns exec "$ns" conntrack -C)
+
+	if [ "$c" -eq 0 ]; then
+		echo "FAIL: conntrack count for $ns is 0"
+		lret=1
+	fi
+
+	if [ "$c" -ne "$l" ]; then
+		echo "FAIL: conntrack count inconsistency for $ns -L: $c != $l"
+		lret=1
+	fi
+
+	# check the dump we retrieved is free of duplicated entries.
+	unique=$(uniq "$tmpfile" | tee "$tmpfile_uniq" | wc -l)
+	if [ "$l" -ne "$unique" ]; then
+		echo "FAIL: listing contained redundant entries for $ns: $l != $unique"
+		diff -u "$tmpfile" "$tmpfile_uniq"
+		lret=1
+	fi
+
+	# we either inserted icmp or only udp, hence, --proto should return same entry count as without filter.
+	proto=$(ip netns exec "$ns" conntrack -L --proto $protoname 2>/dev/null | sort | uniq | tee "$tmpfile_uniq" | wc -l)
+	if [ "$l" -ne "$proto" ]; then
+		echo "FAIL: dump inconsistency for $ns -L --proto $protoname: $l != $proto"
+		diff -u "$tmpfile" "$tmpfile_uniq"
+		lret=1
+	fi
+
+	if [ -r /proc/self/net/nf_conntrack ] ; then
+		proc=$(ip netns exec "$ns" bash -c "sort < /proc/self/net/nf_conntrack | tee \"$tmpfile_proc\" | wc -l")
+
+		if [ "$l" -ne "$proc" ]; then
+			echo "FAIL: proc inconsistency for $ns: $l != $proc"
+			lret=1
+		fi
+
+		proc=$(uniq "$tmpfile_proc" | tee "$tmpfile_uniq" | wc -l)
+		if [ "$l" -ne "$proc" ]; then
+			echo "FAIL: proc inconsistency after uniq filter for $ns: $l != $proc"
+			diff -u "$tmpfile_proc" "$tmpfile_uniq"
+			lret=1
+		fi
+	fi
+
+	if [ $lret -eq 0 ];then
+		echo "PASS: dump in netns $ns had same entry count (-C $c, -L $l, -p $proto, /proc $proc)"
+	else
+		echo "FAIL: dump in netns $ns had different entry count (-C $c, -L $l, -p $proto, /proc $proc)"
+		ret=1
+	fi
+}
+
+test_dump_all()
+{
+	local timeout=3
+	local tainted_then=""
+
+	read tainted_then < /proc/sys/kernel/tainted
+
+	ct_flush_once "$nsclient1"
+	ct_flush_once "$nsclient2"
+
+	ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=3600
+
+	ctflood "$nsclient1" $timeout "dumpall" &
+	insert_ctnetlink "$nsclient2" $insert_count
+
+	wait
+
+	check_dump "$nsclient1" "icmp"
+	check_dump "$nsclient2" "udp"
+
+	check_taint "$tainted_then" "test parallel conntrack dumps"
+}
+
+check_sysctl_immutable()
+{
+	local ns="$1"
+	local name="$2"
+	local failhard="$3"
+	local o=0
+	local n=0
+
+	o=$(ip netns exec "$ns" sysctl -n "$name" 2>/dev/null)
+	n=$((o+1))
+
+	# return value isn't reliable, need to read it back
+	ip netns exec "$ns" sysctl -q "$name"=$n 2>/dev/null >/dev/null
+
+	n=$(ip netns exec "$ns" sysctl -n "$name" 2>/dev/null)
+
+	[ -z "$n" ] && return 1
+
+	if [ $o -ne $n ]; then
+		if [ $failhard -gt 0 ] ;then
+			echo "FAIL: net.$name should not be changeable from namespace (now $n)"
+			ret=1
+		fi
+		return 0
+	fi
+
+	return 1
+}
+
+test_conntrack_max_limit()
+{
+	sysctl -q net.netfilter.nf_conntrack_max=100
+	insert_ctnetlink "$nsclient1" 101
+
+	# check netns is clamped by init_net, i.e., either netns follows
+	# init_net value, or a higher pernet limit (compared to init_net) is ignored.
+	check_ctcount "$nsclient1" 100 "netns conntrack_max is init_net bound"
+
+	sysctl -q net.netfilter.nf_conntrack_max=$init_net_max
+}
+
+test_conntrack_disable()
+{
+	local timeout=2
+
+	# disable conntrack pickups
+	ip netns exec "$nsclient1" nft flush table ip test_ct
+
+	ct_flush_once "$nsclient1"
+	ct_flush_once "$nsclient2"
+
+	ctflood "$nsclient1" "$timeout" "conntrack disable"
+	ip netns exec "$nsclient2" ping -q -c 1 127.0.0.1 >/dev/null 2>&1
+
+	# Disabled, should not have picked up any connection.
+	check_ctcount "$nsclient1" 0 "conntrack disabled"
+
+	# This one is still active, expect 1 connection.
+	check_ctcount "$nsclient2" 1 "conntrack enabled"
+}
+
+init_net_max=$(sysctl -n net.netfilter.nf_conntrack_max)
+
+check_max_alias $init_net_max
+
+sysctl -q net.netfilter.nf_conntrack_max="262000"
+check_max_alias 262000
+
+setup_ns nsclient1 nsclient2
+
+# check this only works from init_net
+for n in netfilter.nf_conntrack_buckets netfilter.nf_conntrack_expect_max net.nf_conntrack_max;do
+	check_sysctl_immutable "$nsclient1" "net.$n" 1
+done
+
+# won't work on older kernels. If it works, check that the netns obeys the limit
+if check_sysctl_immutable "$nsclient1" net.netfilter.nf_conntrack_max 0;then
+	# subtest: if pernet is changeable, check that reducing it in pernet
+	# limits the pernet entries.  Inverse, pernet clamped by a lower init_net
+	# setting, is already checked by "test_conntrack_max_limit" test.
+
+	ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_max=1
+	insert_ctnetlink "$nsclient1" 2
+	check_ctcount "$nsclient1" 1 "netns conntrack_max is pernet bound"
+	ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_max=$init_net_max
+fi
+
+for n in "$nsclient1" "$nsclient2";do
+# enable conntrack in both namespaces
+ip netns exec "$n" nft -f - <<EOF
+table ip test_ct {
+	chain input {
+		type filter hook input priority 0
+		ct state new counter
+	}
+}
+EOF
+done
+
+tmpfile=$(mktemp)
+tmpfile_proc=$(mktemp)
+tmpfile_uniq=$(mktemp)
+test_conntrack_max_limit
+test_dump_all
+test_floodresize_all
+test_conntrack_disable
+
+exit $ret
diff --git a/tools/testing/selftests/net/netfilter/conntrack_vrf.sh b/tools/testing/selftests/net/netfilter/conntrack_vrf.sh
index e95ecb37c2b1..025b58f2ae91 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_vrf.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_vrf.sh
@@ -52,9 +52,6 @@ trap cleanup EXIT
 
 setup_ns ns0 ns1
 
-ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.default.rp_filter=0
-ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.all.rp_filter=0
-ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.all.rp_filter=0
 ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.all.forwarding=1
 
 if ! ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1; then
diff --git a/tools/testing/selftests/net/netfilter/ipvs.sh b/tools/testing/selftests/net/netfilter/ipvs.sh
index d3edb16cd4b3..6af2ea3ad6b8 100755
--- a/tools/testing/selftests/net/netfilter/ipvs.sh
+++ b/tools/testing/selftests/net/netfilter/ipvs.sh
@@ -129,9 +129,6 @@ test_dr() {
 	# avoid incorrect arp response
 	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_ignore=1
 	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_announce=2
-	# avoid reverse route lookup
-	ip netns exec "${ns2}" sysctl -qw  net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${ns2}" sysctl -qw  net.ipv4.conf.veth21.rp_filter=0
 	ip netns exec "${ns2}" ip addr add "${vip_v4}/32" dev lo:1
 
 	test_service
@@ -167,9 +164,6 @@ test_tun() {
 	ip netns exec "${ns2}" ip link set tunl0 up
 	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_ignore=1
 	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_announce=2
-	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.tunl0.rp_filter=0
-	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.veth21.rp_filter=0
 	ip netns exec "${ns2}" ip addr add "${vip_v4}/32" dev lo:1
 
 	test_service
diff --git a/tools/testing/selftests/net/netfilter/nft_fib.sh b/tools/testing/selftests/net/netfilter/nft_fib.sh
index ce1451c275fd..82780b39277c 100755
--- a/tools/testing/selftests/net/netfilter/nft_fib.sh
+++ b/tools/testing/selftests/net/netfilter/nft_fib.sh
@@ -45,6 +45,19 @@ table inet filter {
 EOF
 }
 
+load_input_ruleset() {
+	local netns=$1
+
+ip netns exec "$netns" nft -f /dev/stdin <<EOF
+table inet filter {
+	chain input {
+		type filter hook input priority 0; policy accept;
+	        fib saddr . iif oif missing counter log prefix "$netns nft_rpfilter: " drop
+	}
+}
+EOF
+}
+
 load_pbr_ruleset() {
 	local netns=$1
 
@@ -154,8 +167,6 @@ test_ping() {
 ip netns exec "$nsrouter" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
 ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
 ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
-ip netns exec "$nsrouter" sysctl net.ipv4.conf.all.rp_filter=0 > /dev/null
-ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth0.rp_filter=0 > /dev/null
 
 test_ping 10.0.2.1 dead:2::1 || exit 1
 check_drops || exit 1
@@ -165,6 +176,16 @@ check_drops || exit 1
 
 echo "PASS: fib expression did not cause unwanted packet drops"
 
+load_input_ruleset "$ns1"
+
+test_ping 127.0.0.1 ::1 || exit 1
+check_drops || exit 1
+
+test_ping 10.0.1.99 dead:1::99 || exit 1
+check_drops || exit 1
+
+echo "PASS: fib expression did not discard loopback packets"
+
 ip netns exec "$nsrouter" nft flush table inet filter
 
 ip -net "$ns1" route del default
diff --git a/tools/testing/selftests/net/netfilter/nft_nat_zones.sh b/tools/testing/selftests/net/netfilter/nft_nat_zones.sh
index 3b81d88bdde3..9f200f80253a 100755
--- a/tools/testing/selftests/net/netfilter/nft_nat_zones.sh
+++ b/tools/testing/selftests/net/netfilter/nft_nat_zones.sh
@@ -88,7 +88,6 @@ for i in $(seq 1 "$maxclients");do
   echo netns exec "$cl" sysctl -q net.ipv4.tcp_syn_retries=2
   echo netns exec "$gw" ip link set "veth$i" up
   echo netns exec "$gw" sysctl -q net.ipv4.conf.veth"$i".arp_ignore=2
-  echo netns exec "$gw" sysctl -q net.ipv4.conf.veth"$i".rp_filter=0
 
   # clients have same IP addresses.
   echo netns exec "$cl" ip addr add 10.1.0.3/24 dev eth0
@@ -178,7 +177,6 @@ fi
 
 ip netns exec "$gw" sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
 ip netns exec "$gw" sysctl -q net.ipv6.conf.all.forwarding=1 > /dev/null
-ip netns exec "$gw" sysctl -q net.ipv4.conf.all.rp_filter=0 >/dev/null
 
 # useful for debugging: allows to use 'ping' from clients to gateway.
 ip netns exec "$gw" sysctl -q net.ipv4.fwmark_reflect=1 > /dev/null
diff --git a/tools/testing/selftests/net/netfilter/rpath.sh b/tools/testing/selftests/net/netfilter/rpath.sh
index 86ec4e68594d..24ad41d526d9 100755
--- a/tools/testing/selftests/net/netfilter/rpath.sh
+++ b/tools/testing/selftests/net/netfilter/rpath.sh
@@ -1,8 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-# return code to signal skipped test
-ksft_skip=4
+source lib.sh
 
 # search for legacy iptables (it uses the xtables extensions
 if iptables-legacy --version >/dev/null 2>&1; then
@@ -32,17 +31,10 @@ if [ -z "$iptables$ip6tables$nft" ]; then
 	exit $ksft_skip
 fi
 
-sfx=$(mktemp -u "XXXXXXXX")
-ns1="ns1-$sfx"
-ns2="ns2-$sfx"
-trap "ip netns del $ns1; ip netns del $ns2" EXIT
-
-# create two netns, disable rp_filter in ns2 and
-# keep IPv6 address when moving into VRF
-ip netns add "$ns1"
-ip netns add "$ns2"
-ip netns exec "$ns2" sysctl -q net.ipv4.conf.all.rp_filter=0
-ip netns exec "$ns2" sysctl -q net.ipv4.conf.default.rp_filter=0
+trap cleanup_all_ns EXIT
+
+# create two netns, keep IPv6 address when moving into VRF
+setup_ns ns1 ns2
 ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.keep_addr_on_down=1
 
 # a standard connection between the netns, should not trigger rp filter
diff --git a/tools/testing/selftests/net/ovpn/.gitignore b/tools/testing/selftests/net/ovpn/.gitignore
new file mode 100644
index 000000000000..ee44c081ca7c
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0+
+ovpn-cli
diff --git a/tools/testing/selftests/net/ovpn/Makefile b/tools/testing/selftests/net/ovpn/Makefile
new file mode 100644
index 000000000000..e0926d76b4c8
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/Makefile
@@ -0,0 +1,32 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+CFLAGS = -pedantic -Wextra -Wall -Wl,--no-as-needed -g -O0 -ggdb $(KHDR_INCLUDES)
+VAR_CFLAGS = $(shell pkg-config --cflags libnl-3.0 libnl-genl-3.0 2>/dev/null)
+ifeq ($(VAR_CFLAGS),)
+VAR_CFLAGS = -I/usr/include/libnl3
+endif
+CFLAGS += $(VAR_CFLAGS)
+
+
+LDLIBS = -lmbedtls -lmbedcrypto
+VAR_LDLIBS = $(shell pkg-config --libs libnl-3.0 libnl-genl-3.0 2>/dev/null)
+ifeq ($(VAR_LDLIBS),)
+VAR_LDLIBS = -lnl-genl-3 -lnl-3
+endif
+LDLIBS += $(VAR_LDLIBS)
+
+
+TEST_FILES = common.sh
+
+TEST_PROGS = test.sh \
+	test-large-mtu.sh \
+	test-chachapoly.sh \
+	test-tcp.sh \
+	test-float.sh \
+	test-close-socket.sh \
+	test-close-socket-tcp.sh
+
+TEST_GEN_FILES := ovpn-cli
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/ovpn/common.sh b/tools/testing/selftests/net/ovpn/common.sh
new file mode 100644
index 000000000000..88869c675d03
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/common.sh
@@ -0,0 +1,108 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+UDP_PEERS_FILE=${UDP_PEERS_FILE:-udp_peers.txt}
+TCP_PEERS_FILE=${TCP_PEERS_FILE:-tcp_peers.txt}
+OVPN_CLI=${OVPN_CLI:-./ovpn-cli}
+ALG=${ALG:-aes}
+PROTO=${PROTO:-UDP}
+FLOAT=${FLOAT:-0}
+
+LAN_IP="11.11.11.11"
+
+create_ns() {
+	ip netns add peer${1}
+}
+
+setup_ns() {
+	MODE="P2P"
+
+	if [ ${1} -eq 0 ]; then
+		MODE="MP"
+		for p in $(seq 1 ${NUM_PEERS}); do
+			ip link add veth${p} netns peer0 type veth peer name veth${p} netns peer${p}
+
+			ip -n peer0 addr add 10.10.${p}.1/24 dev veth${p}
+			ip -n peer0 addr add fd00:0:0:${p}::1/64 dev veth${p}
+			ip -n peer0 link set veth${p} up
+
+			ip -n peer${p} addr add 10.10.${p}.2/24 dev veth${p}
+			ip -n peer${p} addr add fd00:0:0:${p}::2/64 dev veth${p}
+			ip -n peer${p} link set veth${p} up
+		done
+	fi
+
+	ip netns exec peer${1} ${OVPN_CLI} new_iface tun${1} $MODE
+	ip -n peer${1} addr add ${2} dev tun${1}
+	# add a secondary IP to peer 1, to test a LAN behind a client
+	if [ ${1} -eq 1 -a -n "${LAN_IP}" ]; then
+		ip -n peer${1} addr add ${LAN_IP} dev tun${1}
+		ip -n peer0 route add ${LAN_IP} via $(echo ${2} |sed -e s'!/.*!!') dev tun0
+	fi
+	if [ -n "${3}" ]; then
+		ip -n peer${1} link set mtu ${3} dev tun${1}
+	fi
+	ip -n peer${1} link set tun${1} up
+}
+
+add_peer() {
+	if [ "${PROTO}" == "UDP" ]; then
+		if [ ${1} -eq 0 ]; then
+			ip netns exec peer0 ${OVPN_CLI} new_multi_peer tun0 1 ${UDP_PEERS_FILE}
+
+			for p in $(seq 1 ${NUM_PEERS}); do
+				ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 1 0 ${ALG} 0 \
+					data64.key
+			done
+		else
+			RADDR=$(awk "NR == ${1} {print \$2}" ${UDP_PEERS_FILE})
+			RPORT=$(awk "NR == ${1} {print \$3}" ${UDP_PEERS_FILE})
+			LPORT=$(awk "NR == ${1} {print \$5}" ${UDP_PEERS_FILE})
+			ip netns exec peer${1} ${OVPN_CLI} new_peer tun${1} ${1} ${LPORT} \
+				${RADDR} ${RPORT}
+			ip netns exec peer${1} ${OVPN_CLI} new_key tun${1} ${1} 1 0 ${ALG} 1 \
+				data64.key
+		fi
+	else
+		if [ ${1} -eq 0 ]; then
+			(ip netns exec peer0 ${OVPN_CLI} listen tun0 1 ${TCP_PEERS_FILE} && {
+				for p in $(seq 1 ${NUM_PEERS}); do
+					ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 1 0 \
+						${ALG} 0 data64.key
+				done
+			}) &
+			sleep 5
+		else
+			ip netns exec peer${1} ${OVPN_CLI} connect tun${1} ${1} 10.10.${1}.1 1 \
+				data64.key
+		fi
+	fi
+}
+
+cleanup() {
+	# some ovpn-cli processes sleep in background so they need manual poking
+	killall $(basename ${OVPN_CLI}) 2>/dev/null || true
+
+	# netns peer0 is deleted without erasing ifaces first
+	for p in $(seq 1 10); do
+		ip -n peer${p} link set tun${p} down 2>/dev/null || true
+		ip netns exec peer${p} ${OVPN_CLI} del_iface tun${p} 2>/dev/null || true
+	done
+	for p in $(seq 1 10); do
+		ip -n peer0 link del veth${p} 2>/dev/null || true
+	done
+	for p in $(seq 0 10); do
+		ip netns del peer${p} 2>/dev/null || true
+	done
+}
+
+if [ "${PROTO}" == "UDP" ]; then
+	NUM_PEERS=${NUM_PEERS:-$(wc -l ${UDP_PEERS_FILE} | awk '{print $1}')}
+else
+	NUM_PEERS=${NUM_PEERS:-$(wc -l ${TCP_PEERS_FILE} | awk '{print $1}')}
+fi
+
+
diff --git a/tools/testing/selftests/net/ovpn/config b/tools/testing/selftests/net/ovpn/config
new file mode 100644
index 000000000000..71946ba9fa17
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/config
@@ -0,0 +1,10 @@
+CONFIG_NET=y
+CONFIG_INET=y
+CONFIG_STREAM_PARSER=y
+CONFIG_NET_UDP_TUNNEL=y
+CONFIG_DST_CACHE=y
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_AES=y
+CONFIG_CRYPTO_GCM=y
+CONFIG_CRYPTO_CHACHA20POLY1305=y
+CONFIG_OVPN=m
diff --git a/tools/testing/selftests/net/ovpn/data64.key b/tools/testing/selftests/net/ovpn/data64.key
new file mode 100644
index 000000000000..a99e88c4e290
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/data64.key
@@ -0,0 +1,5 @@
+jRqMACN7d7/aFQNT8S7jkrBD8uwrgHbG5OQZP2eu4R1Y7tfpS2bf5RHv06Vi163CGoaIiTX99R3B
+ia9ycAH8Wz1+9PWv51dnBLur9jbShlgZ2QHLtUc4a/gfT7zZwULXuuxdLnvR21DDeMBaTbkgbai9
+uvAa7ne1liIgGFzbv+Bas4HDVrygxIxuAnP5Qgc3648IJkZ0QEXPF+O9f0n5+QIvGCxkAUVx+5K6
+KIs+SoeWXnAopELmoGSjUpFtJbagXK82HfdqpuUxT2Tnuef0/14SzVE/vNleBNu2ZbyrSAaah8tE
+BofkPJUBFY+YQcfZNM5Dgrw3i+Bpmpq/gpdg5w==
diff --git a/tools/testing/selftests/net/ovpn/ovpn-cli.c b/tools/testing/selftests/net/ovpn/ovpn-cli.c
new file mode 100644
index 000000000000..de9c26f98b2e
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c
@@ -0,0 +1,2383 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel accelerator
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <stdio.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <time.h>
+
+#include <linux/ovpn.h>
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+#include <netlink/socket.h>
+#include <netlink/netlink.h>
+#include <netlink/genl/genl.h>
+#include <netlink/genl/family.h>
+#include <netlink/genl/ctrl.h>
+
+#include <mbedtls/base64.h>
+#include <mbedtls/error.h>
+
+#include <sys/socket.h>
+
+/* defines to make checkpatch happy */
+#define strscpy strncpy
+#define __always_unused __attribute__((__unused__))
+
+/* libnl < 3.5.0 does not set the NLA_F_NESTED on its own, therefore we
+ * have to explicitly do it to prevent the kernel from failing upon
+ * parsing of the message
+ */
+#define nla_nest_start(_msg, _type) \
+	nla_nest_start(_msg, (_type) | NLA_F_NESTED)
+
+/* libnl < 3.11.0 does not implement nla_get_uint() */
+uint64_t ovpn_nla_get_uint(struct nlattr *attr)
+{
+	if (nla_len(attr) == sizeof(uint32_t))
+		return nla_get_u32(attr);
+	else
+		return nla_get_u64(attr);
+}
+
+typedef int (*ovpn_nl_cb)(struct nl_msg *msg, void *arg);
+
+enum ovpn_key_direction {
+	KEY_DIR_IN = 0,
+	KEY_DIR_OUT,
+};
+
+#define KEY_LEN (256 / 8)
+#define NONCE_LEN 8
+
+#define PEER_ID_UNDEF 0x00FFFFFF
+#define MAX_PEERS 10
+
+struct nl_ctx {
+	struct nl_sock *nl_sock;
+	struct nl_msg *nl_msg;
+	struct nl_cb *nl_cb;
+
+	int ovpn_dco_id;
+};
+
+enum ovpn_cmd {
+	CMD_INVALID,
+	CMD_NEW_IFACE,
+	CMD_DEL_IFACE,
+	CMD_LISTEN,
+	CMD_CONNECT,
+	CMD_NEW_PEER,
+	CMD_NEW_MULTI_PEER,
+	CMD_SET_PEER,
+	CMD_DEL_PEER,
+	CMD_GET_PEER,
+	CMD_NEW_KEY,
+	CMD_DEL_KEY,
+	CMD_GET_KEY,
+	CMD_SWAP_KEYS,
+	CMD_LISTEN_MCAST,
+};
+
+struct ovpn_ctx {
+	enum ovpn_cmd cmd;
+
+	__u8 key_enc[KEY_LEN];
+	__u8 key_dec[KEY_LEN];
+	__u8 nonce[NONCE_LEN];
+
+	enum ovpn_cipher_alg cipher;
+
+	sa_family_t sa_family;
+
+	unsigned long peer_id;
+	unsigned long lport;
+
+	union {
+		struct sockaddr_in in4;
+		struct sockaddr_in6 in6;
+	} remote;
+
+	union {
+		struct sockaddr_in in4;
+		struct sockaddr_in6 in6;
+	} peer_ip;
+
+	bool peer_ip_set;
+
+	unsigned int ifindex;
+	char ifname[IFNAMSIZ];
+	enum ovpn_mode mode;
+	bool mode_set;
+
+	int socket;
+	int cli_sockets[MAX_PEERS];
+
+	__u32 keepalive_interval;
+	__u32 keepalive_timeout;
+
+	enum ovpn_key_direction key_dir;
+	enum ovpn_key_slot key_slot;
+	int key_id;
+
+	const char *peers_file;
+};
+
+static int ovpn_nl_recvmsgs(struct nl_ctx *ctx)
+{
+	int ret;
+
+	ret = nl_recvmsgs(ctx->nl_sock, ctx->nl_cb);
+
+	switch (ret) {
+	case -NLE_INTR:
+		fprintf(stderr,
+			"netlink received interrupt due to signal - ignoring\n");
+		break;
+	case -NLE_NOMEM:
+		fprintf(stderr, "netlink out of memory error\n");
+		break;
+	case -NLE_AGAIN:
+		fprintf(stderr,
+			"netlink reports blocking read - aborting wait\n");
+		break;
+	default:
+		if (ret)
+			fprintf(stderr, "netlink reports error (%d): %s\n",
+				ret, nl_geterror(-ret));
+		break;
+	}
+
+	return ret;
+}
+
+static struct nl_ctx *nl_ctx_alloc_flags(struct ovpn_ctx *ovpn, int cmd,
+					 int flags)
+{
+	struct nl_ctx *ctx;
+	int err, ret;
+
+	ctx = calloc(1, sizeof(*ctx));
+	if (!ctx)
+		return NULL;
+
+	ctx->nl_sock = nl_socket_alloc();
+	if (!ctx->nl_sock) {
+		fprintf(stderr, "cannot allocate netlink socket\n");
+		goto err_free;
+	}
+
+	nl_socket_set_buffer_size(ctx->nl_sock, 8192, 8192);
+
+	ret = genl_connect(ctx->nl_sock);
+	if (ret) {
+		fprintf(stderr, "cannot connect to generic netlink: %s\n",
+			nl_geterror(ret));
+		goto err_sock;
+	}
+
+	/* enable Extended ACK for detailed error reporting */
+	err = 1;
+	setsockopt(nl_socket_get_fd(ctx->nl_sock), SOL_NETLINK, NETLINK_EXT_ACK,
+		   &err, sizeof(err));
+
+	ctx->ovpn_dco_id = genl_ctrl_resolve(ctx->nl_sock, OVPN_FAMILY_NAME);
+	if (ctx->ovpn_dco_id < 0) {
+		fprintf(stderr, "cannot find ovpn_dco netlink component: %d\n",
+			ctx->ovpn_dco_id);
+		goto err_free;
+	}
+
+	ctx->nl_msg = nlmsg_alloc();
+	if (!ctx->nl_msg) {
+		fprintf(stderr, "cannot allocate netlink message\n");
+		goto err_sock;
+	}
+
+	ctx->nl_cb = nl_cb_alloc(NL_CB_DEFAULT);
+	if (!ctx->nl_cb) {
+		fprintf(stderr, "failed to allocate netlink callback\n");
+		goto err_msg;
+	}
+
+	nl_socket_set_cb(ctx->nl_sock, ctx->nl_cb);
+
+	genlmsg_put(ctx->nl_msg, 0, 0, ctx->ovpn_dco_id, 0, flags, cmd, 0);
+
+	if (ovpn->ifindex > 0)
+		NLA_PUT_U32(ctx->nl_msg, OVPN_A_IFINDEX, ovpn->ifindex);
+
+	return ctx;
+nla_put_failure:
+err_msg:
+	nlmsg_free(ctx->nl_msg);
+err_sock:
+	nl_socket_free(ctx->nl_sock);
+err_free:
+	free(ctx);
+	return NULL;
+}
+
+static struct nl_ctx *nl_ctx_alloc(struct ovpn_ctx *ovpn, int cmd)
+{
+	return nl_ctx_alloc_flags(ovpn, cmd, 0);
+}
+
+static void nl_ctx_free(struct nl_ctx *ctx)
+{
+	if (!ctx)
+		return;
+
+	nl_socket_free(ctx->nl_sock);
+	nlmsg_free(ctx->nl_msg);
+	nl_cb_put(ctx->nl_cb);
+	free(ctx);
+}
+
+static int ovpn_nl_cb_error(struct sockaddr_nl (*nla)__always_unused,
+			    struct nlmsgerr *err, void *arg)
+{
+	struct nlmsghdr *nlh = (struct nlmsghdr *)err - 1;
+	struct nlattr *tb_msg[NLMSGERR_ATTR_MAX + 1];
+	int len = nlh->nlmsg_len;
+	struct nlattr *attrs;
+	int *ret = arg;
+	int ack_len = sizeof(*nlh) + sizeof(int) + sizeof(*nlh);
+
+	*ret = err->error;
+
+	if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS))
+		return NL_STOP;
+
+	if (!(nlh->nlmsg_flags & NLM_F_CAPPED))
+		ack_len += err->msg.nlmsg_len - sizeof(*nlh);
+
+	if (len <= ack_len)
+		return NL_STOP;
+
+	attrs = (void *)((uint8_t *)nlh + ack_len);
+	len -= ack_len;
+
+	nla_parse(tb_msg, NLMSGERR_ATTR_MAX, attrs, len, NULL);
+	if (tb_msg[NLMSGERR_ATTR_MSG]) {
+		len = strnlen((char *)nla_data(tb_msg[NLMSGERR_ATTR_MSG]),
+			      nla_len(tb_msg[NLMSGERR_ATTR_MSG]));
+		fprintf(stderr, "kernel error: %*s\n", len,
+			(char *)nla_data(tb_msg[NLMSGERR_ATTR_MSG]));
+	}
+
+	if (tb_msg[NLMSGERR_ATTR_MISS_NEST]) {
+		fprintf(stderr, "missing required nesting type %u\n",
+			nla_get_u32(tb_msg[NLMSGERR_ATTR_MISS_NEST]));
+	}
+
+	if (tb_msg[NLMSGERR_ATTR_MISS_TYPE]) {
+		fprintf(stderr, "missing required attribute type %u\n",
+			nla_get_u32(tb_msg[NLMSGERR_ATTR_MISS_TYPE]));
+	}
+
+	return NL_STOP;
+}
+
+static int ovpn_nl_cb_finish(struct nl_msg (*msg)__always_unused,
+			     void *arg)
+{
+	int *status = arg;
+
+	*status = 0;
+	return NL_SKIP;
+}
+
+static int ovpn_nl_cb_ack(struct nl_msg (*msg)__always_unused,
+			  void *arg)
+{
+	int *status = arg;
+
+	*status = 0;
+	return NL_STOP;
+}
+
+static int ovpn_nl_msg_send(struct nl_ctx *ctx, ovpn_nl_cb cb)
+{
+	int status = 1;
+
+	nl_cb_err(ctx->nl_cb, NL_CB_CUSTOM, ovpn_nl_cb_error, &status);
+	nl_cb_set(ctx->nl_cb, NL_CB_FINISH, NL_CB_CUSTOM, ovpn_nl_cb_finish,
+		  &status);
+	nl_cb_set(ctx->nl_cb, NL_CB_ACK, NL_CB_CUSTOM, ovpn_nl_cb_ack, &status);
+
+	if (cb)
+		nl_cb_set(ctx->nl_cb, NL_CB_VALID, NL_CB_CUSTOM, cb, ctx);
+
+	nl_send_auto_complete(ctx->nl_sock, ctx->nl_msg);
+
+	while (status == 1)
+		ovpn_nl_recvmsgs(ctx);
+
+	if (status < 0)
+		fprintf(stderr, "failed to send netlink message: %s (%d)\n",
+			strerror(-status), status);
+
+	return status;
+}
+
+static int ovpn_parse_key(const char *file, struct ovpn_ctx *ctx)
+{
+	int idx_enc, idx_dec, ret = -1;
+	unsigned char *ckey = NULL;
+	__u8 *bkey = NULL;
+	size_t olen = 0;
+	long ckey_len;
+	FILE *fp;
+
+	fp = fopen(file, "r");
+	if (!fp) {
+		fprintf(stderr, "cannot open: %s\n", file);
+		return -1;
+	}
+
+	/* get file size */
+	fseek(fp, 0L, SEEK_END);
+	ckey_len = ftell(fp);
+	rewind(fp);
+
+	/* if the file is longer, let's just read a portion */
+	if (ckey_len > 256)
+		ckey_len = 256;
+
+	ckey = malloc(ckey_len);
+	if (!ckey)
+		goto err;
+
+	ret = fread(ckey, 1, ckey_len, fp);
+	if (ret != ckey_len) {
+		fprintf(stderr,
+			"couldn't read enough data from key file: %dbytes read\n",
+			ret);
+		goto err;
+	}
+
+	olen = 0;
+	ret = mbedtls_base64_decode(NULL, 0, &olen, ckey, ckey_len);
+	if (ret != MBEDTLS_ERR_BASE64_BUFFER_TOO_SMALL) {
+		char buf[256];
+
+		mbedtls_strerror(ret, buf, sizeof(buf));
+		fprintf(stderr, "unexpected base64 error1: %s (%d)\n", buf,
+			ret);
+
+		goto err;
+	}
+
+	bkey = malloc(olen);
+	if (!bkey) {
+		fprintf(stderr, "cannot allocate binary key buffer\n");
+		goto err;
+	}
+
+	ret = mbedtls_base64_decode(bkey, olen, &olen, ckey, ckey_len);
+	if (ret) {
+		char buf[256];
+
+		mbedtls_strerror(ret, buf, sizeof(buf));
+		fprintf(stderr, "unexpected base64 error2: %s (%d)\n", buf,
+			ret);
+
+		goto err;
+	}
+
+	if (olen < 2 * KEY_LEN + NONCE_LEN) {
+		fprintf(stderr,
+			"not enough data in key file, found %zdB but needs %dB\n",
+			olen, 2 * KEY_LEN + NONCE_LEN);
+		goto err;
+	}
+
+	switch (ctx->key_dir) {
+	case KEY_DIR_IN:
+		idx_enc = 0;
+		idx_dec = 1;
+		break;
+	case KEY_DIR_OUT:
+		idx_enc = 1;
+		idx_dec = 0;
+		break;
+	default:
+		goto err;
+	}
+
+	memcpy(ctx->key_enc, bkey + KEY_LEN * idx_enc, KEY_LEN);
+	memcpy(ctx->key_dec, bkey + KEY_LEN * idx_dec, KEY_LEN);
+	memcpy(ctx->nonce, bkey + 2 * KEY_LEN, NONCE_LEN);
+
+	ret = 0;
+
+err:
+	fclose(fp);
+	free(bkey);
+	free(ckey);
+
+	return ret;
+}
+
+static int ovpn_parse_cipher(const char *cipher, struct ovpn_ctx *ctx)
+{
+	if (strcmp(cipher, "aes") == 0)
+		ctx->cipher = OVPN_CIPHER_ALG_AES_GCM;
+	else if (strcmp(cipher, "chachapoly") == 0)
+		ctx->cipher = OVPN_CIPHER_ALG_CHACHA20_POLY1305;
+	else if (strcmp(cipher, "none") == 0)
+		ctx->cipher = OVPN_CIPHER_ALG_NONE;
+	else
+		return -ENOTSUP;
+
+	return 0;
+}
+
+static int ovpn_parse_key_direction(const char *dir, struct ovpn_ctx *ctx)
+{
+	int in_dir;
+
+	in_dir = strtoll(dir, NULL, 10);
+	switch (in_dir) {
+	case KEY_DIR_IN:
+	case KEY_DIR_OUT:
+		ctx->key_dir = in_dir;
+		break;
+	default:
+		fprintf(stderr,
+			"invalid key direction provided. Can be 0 or 1 only\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int ovpn_socket(struct ovpn_ctx *ctx, sa_family_t family, int proto)
+{
+	struct sockaddr_storage local_sock = { 0 };
+	struct sockaddr_in6 *in6;
+	struct sockaddr_in *in;
+	int ret, s, sock_type;
+	size_t sock_len;
+
+	if (proto == IPPROTO_UDP)
+		sock_type = SOCK_DGRAM;
+	else if (proto == IPPROTO_TCP)
+		sock_type = SOCK_STREAM;
+	else
+		return -EINVAL;
+
+	s = socket(family, sock_type, 0);
+	if (s < 0) {
+		perror("cannot create socket");
+		return -1;
+	}
+
+	switch (family) {
+	case AF_INET:
+		in = (struct sockaddr_in *)&local_sock;
+		in->sin_family = family;
+		in->sin_port = htons(ctx->lport);
+		in->sin_addr.s_addr = htonl(INADDR_ANY);
+		sock_len = sizeof(*in);
+		break;
+	case AF_INET6:
+		in6 = (struct sockaddr_in6 *)&local_sock;
+		in6->sin6_family = family;
+		in6->sin6_port = htons(ctx->lport);
+		in6->sin6_addr = in6addr_any;
+		sock_len = sizeof(*in6);
+		break;
+	default:
+		return -1;
+	}
+
+	int opt = 1;
+
+	ret = setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
+
+	if (ret < 0) {
+		perror("setsockopt for SO_REUSEADDR");
+		return ret;
+	}
+
+	ret = setsockopt(s, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt));
+	if (ret < 0) {
+		perror("setsockopt for SO_REUSEPORT");
+		return ret;
+	}
+
+	if (family == AF_INET6) {
+		opt = 0;
+		if (setsockopt(s, IPPROTO_IPV6, IPV6_V6ONLY, &opt,
+			       sizeof(opt))) {
+			perror("failed to set IPV6_V6ONLY");
+			return -1;
+		}
+	}
+
+	ret = bind(s, (struct sockaddr *)&local_sock, sock_len);
+	if (ret < 0) {
+		perror("cannot bind socket");
+		goto err_socket;
+	}
+
+	ctx->socket = s;
+	ctx->sa_family = family;
+	return 0;
+
+err_socket:
+	close(s);
+	return -1;
+}
+
+static int ovpn_udp_socket(struct ovpn_ctx *ctx, sa_family_t family)
+{
+	return ovpn_socket(ctx, family, IPPROTO_UDP);
+}
+
+static int ovpn_listen(struct ovpn_ctx *ctx, sa_family_t family)
+{
+	int ret;
+
+	ret = ovpn_socket(ctx, family, IPPROTO_TCP);
+	if (ret < 0)
+		return ret;
+
+	ret = listen(ctx->socket, 10);
+	if (ret < 0) {
+		perror("listen");
+		close(ctx->socket);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int ovpn_accept(struct ovpn_ctx *ctx)
+{
+	socklen_t socklen;
+	int ret;
+
+	socklen = sizeof(ctx->remote);
+	ret = accept(ctx->socket, (struct sockaddr *)&ctx->remote, &socklen);
+	if (ret < 0) {
+		perror("accept");
+		goto err;
+	}
+
+	fprintf(stderr, "Connection received!\n");
+
+	switch (socklen) {
+	case sizeof(struct sockaddr_in):
+	case sizeof(struct sockaddr_in6):
+		break;
+	default:
+		fprintf(stderr, "error: expecting IPv4 or IPv6 connection\n");
+		close(ret);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	return ret;
+err:
+	close(ctx->socket);
+	return ret;
+}
+
+static int ovpn_connect(struct ovpn_ctx *ovpn)
+{
+	socklen_t socklen;
+	int s, ret;
+
+	s = socket(ovpn->remote.in4.sin_family, SOCK_STREAM, 0);
+	if (s < 0) {
+		perror("cannot create socket");
+		return -1;
+	}
+
+	switch (ovpn->remote.in4.sin_family) {
+	case AF_INET:
+		socklen = sizeof(struct sockaddr_in);
+		break;
+	case AF_INET6:
+		socklen = sizeof(struct sockaddr_in6);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	ret = connect(s, (struct sockaddr *)&ovpn->remote, socklen);
+	if (ret < 0) {
+		perror("connect");
+		goto err;
+	}
+
+	fprintf(stderr, "connected\n");
+
+	ovpn->socket = s;
+
+	return 0;
+err:
+	close(s);
+	return ret;
+}
+
+static int ovpn_new_peer(struct ovpn_ctx *ovpn, bool is_tcp)
+{
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_NEW);
+	if (!ctx)
+		return -ENOMEM;
+
+	attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_SOCKET, ovpn->socket);
+
+	if (!is_tcp) {
+		switch (ovpn->remote.in4.sin_family) {
+		case AF_INET:
+			NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_REMOTE_IPV4,
+				    ovpn->remote.in4.sin_addr.s_addr);
+			NLA_PUT_U16(ctx->nl_msg, OVPN_A_PEER_REMOTE_PORT,
+				    ovpn->remote.in4.sin_port);
+			break;
+		case AF_INET6:
+			NLA_PUT(ctx->nl_msg, OVPN_A_PEER_REMOTE_IPV6,
+				sizeof(ovpn->remote.in6.sin6_addr),
+				&ovpn->remote.in6.sin6_addr);
+			NLA_PUT_U32(ctx->nl_msg,
+				    OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID,
+				    ovpn->remote.in6.sin6_scope_id);
+			NLA_PUT_U16(ctx->nl_msg, OVPN_A_PEER_REMOTE_PORT,
+				    ovpn->remote.in6.sin6_port);
+			break;
+		default:
+			fprintf(stderr,
+				"Invalid family for remote socket address\n");
+			goto nla_put_failure;
+		}
+	}
+
+	if (ovpn->peer_ip_set) {
+		switch (ovpn->peer_ip.in4.sin_family) {
+		case AF_INET:
+			NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_VPN_IPV4,
+				    ovpn->peer_ip.in4.sin_addr.s_addr);
+			break;
+		case AF_INET6:
+			NLA_PUT(ctx->nl_msg, OVPN_A_PEER_VPN_IPV6,
+				sizeof(struct in6_addr),
+				&ovpn->peer_ip.in6.sin6_addr);
+			break;
+		default:
+			fprintf(stderr, "Invalid family for peer address\n");
+			goto nla_put_failure;
+		}
+	}
+
+	nla_nest_end(ctx->nl_msg, attr);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_set_peer(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_SET);
+	if (!ctx)
+		return -ENOMEM;
+
+	attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_KEEPALIVE_INTERVAL,
+		    ovpn->keepalive_interval);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_KEEPALIVE_TIMEOUT,
+		    ovpn->keepalive_timeout);
+	nla_nest_end(ctx->nl_msg, attr);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_del_peer(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_DEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+	nla_nest_end(ctx->nl_msg, attr);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_handle_peer(struct nl_msg *msg, void (*arg)__always_unused)
+{
+	struct nlattr *pattrs[OVPN_A_PEER_MAX + 1];
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *attrs[OVPN_A_MAX + 1];
+	__u16 rport = 0, lport = 0;
+
+	nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+		  genlmsg_attrlen(gnlh, 0), NULL);
+
+	if (!attrs[OVPN_A_PEER]) {
+		fprintf(stderr, "no packet content in netlink message\n");
+		return NL_SKIP;
+	}
+
+	nla_parse(pattrs, OVPN_A_PEER_MAX, nla_data(attrs[OVPN_A_PEER]),
+		  nla_len(attrs[OVPN_A_PEER]), NULL);
+
+	if (pattrs[OVPN_A_PEER_ID])
+		fprintf(stderr, "* Peer %u\n",
+			nla_get_u32(pattrs[OVPN_A_PEER_ID]));
+
+	if (pattrs[OVPN_A_PEER_SOCKET_NETNSID])
+		fprintf(stderr, "\tsocket NetNS ID: %d\n",
+			nla_get_s32(pattrs[OVPN_A_PEER_SOCKET_NETNSID]));
+
+	if (pattrs[OVPN_A_PEER_VPN_IPV4]) {
+		char buf[INET_ADDRSTRLEN];
+
+		inet_ntop(AF_INET, nla_data(pattrs[OVPN_A_PEER_VPN_IPV4]),
+			  buf, sizeof(buf));
+		fprintf(stderr, "\tVPN IPv4: %s\n", buf);
+	}
+
+	if (pattrs[OVPN_A_PEER_VPN_IPV6]) {
+		char buf[INET6_ADDRSTRLEN];
+
+		inet_ntop(AF_INET6, nla_data(pattrs[OVPN_A_PEER_VPN_IPV6]),
+			  buf, sizeof(buf));
+		fprintf(stderr, "\tVPN IPv6: %s\n", buf);
+	}
+
+	if (pattrs[OVPN_A_PEER_LOCAL_PORT])
+		lport = ntohs(nla_get_u16(pattrs[OVPN_A_PEER_LOCAL_PORT]));
+
+	if (pattrs[OVPN_A_PEER_REMOTE_PORT])
+		rport = ntohs(nla_get_u16(pattrs[OVPN_A_PEER_REMOTE_PORT]));
+
+	if (pattrs[OVPN_A_PEER_REMOTE_IPV6]) {
+		void *ip = pattrs[OVPN_A_PEER_REMOTE_IPV6];
+		char buf[INET6_ADDRSTRLEN];
+		int scope_id = -1;
+
+		if (pattrs[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID]) {
+			void *p = pattrs[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID];
+
+			scope_id = nla_get_u32(p);
+		}
+
+		inet_ntop(AF_INET6, nla_data(ip), buf, sizeof(buf));
+		fprintf(stderr, "\tRemote: %s:%hu (scope-id: %u)\n", buf, rport,
+			scope_id);
+
+		if (pattrs[OVPN_A_PEER_LOCAL_IPV6]) {
+			void *ip = pattrs[OVPN_A_PEER_LOCAL_IPV6];
+
+			inet_ntop(AF_INET6, nla_data(ip), buf, sizeof(buf));
+			fprintf(stderr, "\tLocal: %s:%hu\n", buf, lport);
+		}
+	}
+
+	if (pattrs[OVPN_A_PEER_REMOTE_IPV4]) {
+		void *ip = pattrs[OVPN_A_PEER_REMOTE_IPV4];
+		char buf[INET_ADDRSTRLEN];
+
+		inet_ntop(AF_INET, nla_data(ip), buf, sizeof(buf));
+		fprintf(stderr, "\tRemote: %s:%hu\n", buf, rport);
+
+		if (pattrs[OVPN_A_PEER_LOCAL_IPV4]) {
+			void *p = pattrs[OVPN_A_PEER_LOCAL_IPV4];
+
+			inet_ntop(AF_INET, nla_data(p), buf, sizeof(buf));
+			fprintf(stderr, "\tLocal: %s:%hu\n", buf, lport);
+		}
+	}
+
+	if (pattrs[OVPN_A_PEER_KEEPALIVE_INTERVAL]) {
+		void *p = pattrs[OVPN_A_PEER_KEEPALIVE_INTERVAL];
+
+		fprintf(stderr, "\tKeepalive interval: %u sec\n",
+			nla_get_u32(p));
+	}
+
+	if (pattrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT])
+		fprintf(stderr, "\tKeepalive timeout: %u sec\n",
+			nla_get_u32(pattrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]));
+
+	if (pattrs[OVPN_A_PEER_VPN_RX_BYTES])
+		fprintf(stderr, "\tVPN RX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_RX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_VPN_TX_BYTES])
+		fprintf(stderr, "\tVPN TX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_TX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_VPN_RX_PACKETS])
+		fprintf(stderr, "\tVPN RX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_RX_PACKETS]));
+
+	if (pattrs[OVPN_A_PEER_VPN_TX_PACKETS])
+		fprintf(stderr, "\tVPN TX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_TX_PACKETS]));
+
+	if (pattrs[OVPN_A_PEER_LINK_RX_BYTES])
+		fprintf(stderr, "\tLINK RX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_RX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_LINK_TX_BYTES])
+		fprintf(stderr, "\tLINK TX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_TX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_LINK_RX_PACKETS])
+		fprintf(stderr, "\tLINK RX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_RX_PACKETS]));
+
+	if (pattrs[OVPN_A_PEER_LINK_TX_PACKETS])
+		fprintf(stderr, "\tLINK TX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_TX_PACKETS]));
+
+	return NL_SKIP;
+}
+
+static int ovpn_get_peer(struct ovpn_ctx *ovpn)
+{
+	int flags = 0, ret = -1;
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+
+	if (ovpn->peer_id == PEER_ID_UNDEF)
+		flags = NLM_F_DUMP;
+
+	ctx = nl_ctx_alloc_flags(ovpn, OVPN_CMD_PEER_GET, flags);
+	if (!ctx)
+		return -ENOMEM;
+
+	if (ovpn->peer_id != PEER_ID_UNDEF) {
+		attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+		NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+		nla_nest_end(ctx->nl_msg, attr);
+	}
+
+	ret = ovpn_nl_msg_send(ctx, ovpn_handle_peer);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_new_key(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *keyconf, *key_dir;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_NEW);
+	if (!ctx)
+		return -ENOMEM;
+
+	keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_KEY_ID, ovpn->key_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_CIPHER_ALG, ovpn->cipher);
+
+	key_dir = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF_ENCRYPT_DIR);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_CIPHER_KEY, KEY_LEN, ovpn->key_enc);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_NONCE_TAIL, NONCE_LEN, ovpn->nonce);
+	nla_nest_end(ctx->nl_msg, key_dir);
+
+	key_dir = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF_DECRYPT_DIR);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_CIPHER_KEY, KEY_LEN, ovpn->key_dec);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_NONCE_TAIL, NONCE_LEN, ovpn->nonce);
+	nla_nest_end(ctx->nl_msg, key_dir);
+
+	nla_nest_end(ctx->nl_msg, keyconf);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_del_key(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *keyconf;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_DEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+	nla_nest_end(ctx->nl_msg, keyconf);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_handle_key(struct nl_msg *msg, void (*arg)__always_unused)
+{
+	struct nlattr *kattrs[OVPN_A_KEYCONF_MAX + 1];
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *attrs[OVPN_A_MAX + 1];
+
+	nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+		  genlmsg_attrlen(gnlh, 0), NULL);
+
+	if (!attrs[OVPN_A_KEYCONF]) {
+		fprintf(stderr, "no packet content in netlink message\n");
+		return NL_SKIP;
+	}
+
+	nla_parse(kattrs, OVPN_A_KEYCONF_MAX, nla_data(attrs[OVPN_A_KEYCONF]),
+		  nla_len(attrs[OVPN_A_KEYCONF]), NULL);
+
+	if (kattrs[OVPN_A_KEYCONF_PEER_ID])
+		fprintf(stderr, "* Peer %u\n",
+			nla_get_u32(kattrs[OVPN_A_KEYCONF_PEER_ID]));
+	if (kattrs[OVPN_A_KEYCONF_SLOT]) {
+		fprintf(stderr, "\t- Slot: ");
+		switch (nla_get_u32(kattrs[OVPN_A_KEYCONF_SLOT])) {
+		case OVPN_KEY_SLOT_PRIMARY:
+			fprintf(stderr, "primary\n");
+			break;
+		case OVPN_KEY_SLOT_SECONDARY:
+			fprintf(stderr, "secondary\n");
+			break;
+		default:
+			fprintf(stderr, "invalid (%u)\n",
+				nla_get_u32(kattrs[OVPN_A_KEYCONF_SLOT]));
+			break;
+		}
+	}
+	if (kattrs[OVPN_A_KEYCONF_KEY_ID])
+		fprintf(stderr, "\t- Key ID: %u\n",
+			nla_get_u32(kattrs[OVPN_A_KEYCONF_KEY_ID]));
+	if (kattrs[OVPN_A_KEYCONF_CIPHER_ALG]) {
+		fprintf(stderr, "\t- Cipher: ");
+		switch (nla_get_u32(kattrs[OVPN_A_KEYCONF_CIPHER_ALG])) {
+		case OVPN_CIPHER_ALG_NONE:
+			fprintf(stderr, "none\n");
+			break;
+		case OVPN_CIPHER_ALG_AES_GCM:
+			fprintf(stderr, "aes-gcm\n");
+			break;
+		case OVPN_CIPHER_ALG_CHACHA20_POLY1305:
+			fprintf(stderr, "chacha20poly1305\n");
+			break;
+		default:
+			fprintf(stderr, "invalid (%u)\n",
+				nla_get_u32(kattrs[OVPN_A_KEYCONF_CIPHER_ALG]));
+			break;
+		}
+	}
+
+	return NL_SKIP;
+}
+
+static int ovpn_get_key(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *keyconf;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_GET);
+	if (!ctx)
+		return -ENOMEM;
+
+	keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+	nla_nest_end(ctx->nl_msg, keyconf);
+
+	ret = ovpn_nl_msg_send(ctx, ovpn_handle_key);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_swap_keys(struct ovpn_ctx *ovpn)
+{
+	struct nl_ctx *ctx;
+	struct nlattr *kc;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_SWAP);
+	if (!ctx)
+		return -ENOMEM;
+
+	kc = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	nla_nest_end(ctx->nl_msg, kc);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+/* Helper function used to easily add attributes to a rtnl message */
+static int ovpn_addattr(struct nlmsghdr *n, int maxlen, int type,
+			const void *data, int alen)
+{
+	int len = RTA_LENGTH(alen);
+	struct rtattr *rta;
+
+	if ((int)(NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len)) > maxlen)	{
+		fprintf(stderr, "%s: rtnl: message exceeded bound of %d\n",
+			__func__, maxlen);
+		return -EMSGSIZE;
+	}
+
+	rta = nlmsg_tail(n);
+	rta->rta_type = type;
+	rta->rta_len = len;
+
+	if (!data)
+		memset(RTA_DATA(rta), 0, alen);
+	else
+		memcpy(RTA_DATA(rta), data, alen);
+
+	n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len);
+
+	return 0;
+}
+
+static struct rtattr *ovpn_nest_start(struct nlmsghdr *msg, size_t max_size,
+				      int attr)
+{
+	struct rtattr *nest = nlmsg_tail(msg);
+
+	if (ovpn_addattr(msg, max_size, attr, NULL, 0) < 0)
+		return NULL;
+
+	return nest;
+}
+
+static void ovpn_nest_end(struct nlmsghdr *msg, struct rtattr *nest)
+{
+	nest->rta_len = (uint8_t *)nlmsg_tail(msg) - (uint8_t *)nest;
+}
+
+#define RT_SNDBUF_SIZE (1024 * 2)
+#define RT_RCVBUF_SIZE (1024 * 4)
+
+/* Open RTNL socket */
+static int ovpn_rt_socket(void)
+{
+	int sndbuf = RT_SNDBUF_SIZE, rcvbuf = RT_RCVBUF_SIZE, fd;
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (fd < 0) {
+		fprintf(stderr, "%s: cannot open netlink socket\n", __func__);
+		return fd;
+	}
+
+	if (setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &sndbuf,
+		       sizeof(sndbuf)) < 0) {
+		fprintf(stderr, "%s: SO_SNDBUF\n", __func__);
+		close(fd);
+		return -1;
+	}
+
+	if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &rcvbuf,
+		       sizeof(rcvbuf)) < 0) {
+		fprintf(stderr, "%s: SO_RCVBUF\n", __func__);
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
+/* Bind socket to Netlink subsystem */
+static int ovpn_rt_bind(int fd, uint32_t groups)
+{
+	struct sockaddr_nl local = { 0 };
+	socklen_t addr_len;
+
+	local.nl_family = AF_NETLINK;
+	local.nl_groups = groups;
+
+	if (bind(fd, (struct sockaddr *)&local, sizeof(local)) < 0) {
+		fprintf(stderr, "%s: cannot bind netlink socket: %d\n",
+			__func__, errno);
+		return -errno;
+	}
+
+	addr_len = sizeof(local);
+	if (getsockname(fd, (struct sockaddr *)&local, &addr_len) < 0) {
+		fprintf(stderr, "%s: cannot getsockname: %d\n", __func__,
+			errno);
+		return -errno;
+	}
+
+	if (addr_len != sizeof(local)) {
+		fprintf(stderr, "%s: wrong address length %d\n", __func__,
+			addr_len);
+		return -EINVAL;
+	}
+
+	if (local.nl_family != AF_NETLINK) {
+		fprintf(stderr, "%s: wrong address family %d\n", __func__,
+			local.nl_family);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+typedef int (*ovpn_parse_reply_cb)(struct nlmsghdr *msg, void *arg);
+
+/* Send Netlink message and run callback on reply (if specified) */
+static int ovpn_rt_send(struct nlmsghdr *payload, pid_t peer,
+			unsigned int groups, ovpn_parse_reply_cb cb,
+			void *arg_cb)
+{
+	int len, rem_len, fd, ret, rcv_len;
+	struct sockaddr_nl nladdr = { 0 };
+	struct nlmsgerr *err;
+	struct nlmsghdr *h;
+	char buf[1024 * 16];
+	struct iovec iov = {
+		.iov_base = payload,
+		.iov_len = payload->nlmsg_len,
+	};
+	struct msghdr nlmsg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+
+	nladdr.nl_family = AF_NETLINK;
+	nladdr.nl_pid = peer;
+	nladdr.nl_groups = groups;
+
+	payload->nlmsg_seq = time(NULL);
+
+	/* no need to send reply */
+	if (!cb)
+		payload->nlmsg_flags |= NLM_F_ACK;
+
+	fd = ovpn_rt_socket();
+	if (fd < 0) {
+		fprintf(stderr, "%s: can't open rtnl socket\n", __func__);
+		return -errno;
+	}
+
+	ret = ovpn_rt_bind(fd, 0);
+	if (ret < 0) {
+		fprintf(stderr, "%s: can't bind rtnl socket\n", __func__);
+		ret = -errno;
+		goto out;
+	}
+
+	ret = sendmsg(fd, &nlmsg, 0);
+	if (ret < 0) {
+		fprintf(stderr, "%s: rtnl: error on sendmsg()\n", __func__);
+		ret = -errno;
+		goto out;
+	}
+
+	/* prepare buffer to store RTNL replies */
+	memset(buf, 0, sizeof(buf));
+	iov.iov_base = buf;
+
+	while (1) {
+		/*
+		 * iov_len is modified by recvmsg(), therefore has to be initialized before
+		 * using it again
+		 */
+		iov.iov_len = sizeof(buf);
+		rcv_len = recvmsg(fd, &nlmsg, 0);
+		if (rcv_len < 0) {
+			if (errno == EINTR || errno == EAGAIN) {
+				fprintf(stderr, "%s: interrupted call\n",
+					__func__);
+				continue;
+			}
+			fprintf(stderr, "%s: rtnl: error on recvmsg()\n",
+				__func__);
+			ret = -errno;
+			goto out;
+		}
+
+		if (rcv_len == 0) {
+			fprintf(stderr,
+				"%s: rtnl: socket reached unexpected EOF\n",
+				__func__);
+			ret = -EIO;
+			goto out;
+		}
+
+		if (nlmsg.msg_namelen != sizeof(nladdr)) {
+			fprintf(stderr,
+				"%s: sender address length: %u (expected %zu)\n",
+				__func__, nlmsg.msg_namelen, sizeof(nladdr));
+			ret = -EIO;
+			goto out;
+		}
+
+		h = (struct nlmsghdr *)buf;
+		while (rcv_len >= (int)sizeof(*h)) {
+			len = h->nlmsg_len;
+			rem_len = len - sizeof(*h);
+
+			if (rem_len < 0 || len > rcv_len) {
+				if (nlmsg.msg_flags & MSG_TRUNC) {
+					fprintf(stderr, "%s: truncated message\n",
+						__func__);
+					ret = -EIO;
+					goto out;
+				}
+				fprintf(stderr, "%s: malformed message: len=%d\n",
+					__func__, len);
+				ret = -EIO;
+				goto out;
+			}
+
+			if (h->nlmsg_type == NLMSG_DONE) {
+				ret = 0;
+				goto out;
+			}
+
+			if (h->nlmsg_type == NLMSG_ERROR) {
+				err = (struct nlmsgerr *)NLMSG_DATA(h);
+				if (rem_len < (int)sizeof(struct nlmsgerr)) {
+					fprintf(stderr, "%s: ERROR truncated\n",
+						__func__);
+					ret = -EIO;
+					goto out;
+				}
+
+				if (err->error) {
+					fprintf(stderr, "%s: (%d) %s\n",
+						__func__, err->error,
+						strerror(-err->error));
+					ret = err->error;
+					goto out;
+				}
+
+				ret = 0;
+				if (cb)	{
+					int r = cb(h, arg_cb);
+
+					if (r <= 0)
+						ret = r;
+				}
+				goto out;
+			}
+
+			if (cb) {
+				int r = cb(h, arg_cb);
+
+				if (r <= 0) {
+					ret = r;
+					goto out;
+				}
+			} else {
+				fprintf(stderr, "%s: RTNL: unexpected reply\n",
+					__func__);
+			}
+
+			rcv_len -= NLMSG_ALIGN(len);
+			h = (struct nlmsghdr *)((uint8_t *)h +
+						NLMSG_ALIGN(len));
+		}
+
+		if (nlmsg.msg_flags & MSG_TRUNC) {
+			fprintf(stderr, "%s: message truncated\n", __func__);
+			continue;
+		}
+
+		if (rcv_len) {
+			fprintf(stderr, "%s: rtnl: %d not parsed bytes\n",
+				__func__, rcv_len);
+			ret = -1;
+			goto out;
+		}
+	}
+out:
+	close(fd);
+
+	return ret;
+}
+
+struct ovpn_link_req {
+	struct nlmsghdr n;
+	struct ifinfomsg i;
+	char buf[256];
+};
+
+static int ovpn_new_iface(struct ovpn_ctx *ovpn)
+{
+	struct rtattr *linkinfo, *data;
+	struct ovpn_link_req req = { 0 };
+	int ret = -1;
+
+	fprintf(stdout, "Creating interface %s with mode %u\n", ovpn->ifname,
+		ovpn->mode);
+
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.i));
+	req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
+	req.n.nlmsg_type = RTM_NEWLINK;
+
+	if (ovpn_addattr(&req.n, sizeof(req), IFLA_IFNAME, ovpn->ifname,
+			 strlen(ovpn->ifname) + 1) < 0)
+		goto err;
+
+	linkinfo = ovpn_nest_start(&req.n, sizeof(req), IFLA_LINKINFO);
+	if (!linkinfo)
+		goto err;
+
+	if (ovpn_addattr(&req.n, sizeof(req), IFLA_INFO_KIND, OVPN_FAMILY_NAME,
+			 strlen(OVPN_FAMILY_NAME) + 1) < 0)
+		goto err;
+
+	if (ovpn->mode_set) {
+		data = ovpn_nest_start(&req.n, sizeof(req), IFLA_INFO_DATA);
+		if (!data)
+			goto err;
+
+		if (ovpn_addattr(&req.n, sizeof(req), IFLA_OVPN_MODE,
+				 &ovpn->mode, sizeof(uint8_t)) < 0)
+			goto err;
+
+		ovpn_nest_end(&req.n, data);
+	}
+
+	ovpn_nest_end(&req.n, linkinfo);
+
+	req.i.ifi_family = AF_PACKET;
+
+	ret = ovpn_rt_send(&req.n, 0, 0, NULL, NULL);
+err:
+	return ret;
+}
+
+static int ovpn_del_iface(struct ovpn_ctx *ovpn)
+{
+	struct ovpn_link_req req = { 0 };
+
+	fprintf(stdout, "Deleting interface %s ifindex %u\n", ovpn->ifname,
+		ovpn->ifindex);
+
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.i));
+	req.n.nlmsg_flags = NLM_F_REQUEST;
+	req.n.nlmsg_type = RTM_DELLINK;
+
+	req.i.ifi_family = AF_PACKET;
+	req.i.ifi_index = ovpn->ifindex;
+
+	return ovpn_rt_send(&req.n, 0, 0, NULL, NULL);
+}
+
+static int nl_seq_check(struct nl_msg (*msg)__always_unused,
+			void (*arg)__always_unused)
+{
+	return NL_OK;
+}
+
+struct mcast_handler_args {
+	const char *group;
+	int id;
+};
+
+static int mcast_family_handler(struct nl_msg *msg, void *arg)
+{
+	struct mcast_handler_args *grp = arg;
+	struct nlattr *tb[CTRL_ATTR_MAX + 1];
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *mcgrp;
+	int rem_mcgrp;
+
+	nla_parse(tb, CTRL_ATTR_MAX, genlmsg_attrdata(gnlh, 0),
+		  genlmsg_attrlen(gnlh, 0), NULL);
+
+	if (!tb[CTRL_ATTR_MCAST_GROUPS])
+		return NL_SKIP;
+
+	nla_for_each_nested(mcgrp, tb[CTRL_ATTR_MCAST_GROUPS], rem_mcgrp) {
+		struct nlattr *tb_mcgrp[CTRL_ATTR_MCAST_GRP_MAX + 1];
+
+		nla_parse(tb_mcgrp, CTRL_ATTR_MCAST_GRP_MAX,
+			  nla_data(mcgrp), nla_len(mcgrp), NULL);
+
+		if (!tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME] ||
+		    !tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID])
+			continue;
+		if (strncmp(nla_data(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME]),
+			    grp->group, nla_len(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME])))
+			continue;
+		grp->id = nla_get_u32(tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID]);
+		break;
+	}
+
+	return NL_SKIP;
+}
+
+static int mcast_error_handler(struct sockaddr_nl (*nla)__always_unused,
+			       struct nlmsgerr *err, void *arg)
+{
+	int *ret = arg;
+
+	*ret = err->error;
+	return NL_STOP;
+}
+
+static int mcast_ack_handler(struct nl_msg (*msg)__always_unused, void *arg)
+{
+	int *ret = arg;
+
+	*ret = 0;
+	return NL_STOP;
+}
+
+static int ovpn_handle_msg(struct nl_msg *msg, void *arg)
+{
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *attrs[OVPN_A_MAX + 1];
+	struct nlmsghdr *nlh = nlmsg_hdr(msg);
+	char ifname[IF_NAMESIZE];
+	int *ret = arg;
+	__u32 ifindex;
+
+	fprintf(stderr, "received message from ovpn-dco\n");
+
+	*ret = -1;
+
+	if (!genlmsg_valid_hdr(nlh, 0)) {
+		fprintf(stderr, "invalid header\n");
+		return NL_STOP;
+	}
+
+	if (nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+		      genlmsg_attrlen(gnlh, 0), NULL)) {
+		fprintf(stderr, "received bogus data from ovpn-dco\n");
+		return NL_STOP;
+	}
+
+	if (!attrs[OVPN_A_IFINDEX]) {
+		fprintf(stderr, "no ifindex in this message\n");
+		return NL_STOP;
+	}
+
+	ifindex = nla_get_u32(attrs[OVPN_A_IFINDEX]);
+	if (!if_indextoname(ifindex, ifname)) {
+		fprintf(stderr, "cannot resolve ifname for ifindex: %u\n",
+			ifindex);
+		return NL_STOP;
+	}
+
+	switch (gnlh->cmd) {
+	case OVPN_CMD_PEER_DEL_NTF:
+		fprintf(stdout, "received CMD_PEER_DEL_NTF\n");
+		break;
+	case OVPN_CMD_KEY_SWAP_NTF:
+		fprintf(stdout, "received CMD_KEY_SWAP_NTF\n");
+		break;
+	default:
+		fprintf(stderr, "received unknown command: %d\n", gnlh->cmd);
+		return NL_STOP;
+	}
+
+	*ret = 0;
+	return NL_OK;
+}
+
+static int ovpn_get_mcast_id(struct nl_sock *sock, const char *family,
+			     const char *group)
+{
+	struct nl_msg *msg;
+	struct nl_cb *cb;
+	int ret, ctrlid;
+	struct mcast_handler_args grp = {
+		.group = group,
+		.id = -ENOENT,
+	};
+
+	msg = nlmsg_alloc();
+	if (!msg)
+		return -ENOMEM;
+
+	cb = nl_cb_alloc(NL_CB_DEFAULT);
+	if (!cb) {
+		ret = -ENOMEM;
+		goto out_fail_cb;
+	}
+
+	ctrlid = genl_ctrl_resolve(sock, "nlctrl");
+
+	genlmsg_put(msg, 0, 0, ctrlid, 0, 0, CTRL_CMD_GETFAMILY, 0);
+
+	ret = -ENOBUFS;
+	NLA_PUT_STRING(msg, CTRL_ATTR_FAMILY_NAME, family);
+
+	ret = nl_send_auto_complete(sock, msg);
+	if (ret < 0)
+		goto nla_put_failure;
+
+	ret = 1;
+
+	nl_cb_err(cb, NL_CB_CUSTOM, mcast_error_handler, &ret);
+	nl_cb_set(cb, NL_CB_ACK, NL_CB_CUSTOM, mcast_ack_handler, &ret);
+	nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, mcast_family_handler, &grp);
+
+	while (ret > 0)
+		nl_recvmsgs(sock, cb);
+
+	if (ret == 0)
+		ret = grp.id;
+ nla_put_failure:
+	nl_cb_put(cb);
+ out_fail_cb:
+	nlmsg_free(msg);
+	return ret;
+}
+
+static int ovpn_listen_mcast(void)
+{
+	struct nl_sock *sock;
+	struct nl_cb *cb;
+	int mcid, ret;
+
+	sock = nl_socket_alloc();
+	if (!sock) {
+		fprintf(stderr, "cannot allocate netlink socket\n");
+		goto err_free;
+	}
+
+	nl_socket_set_buffer_size(sock, 8192, 8192);
+
+	ret = genl_connect(sock);
+	if (ret < 0) {
+		fprintf(stderr, "cannot connect to generic netlink: %s\n",
+			nl_geterror(ret));
+		goto err_free;
+	}
+
+	mcid = ovpn_get_mcast_id(sock, OVPN_FAMILY_NAME, OVPN_MCGRP_PEERS);
+	if (mcid < 0) {
+		fprintf(stderr, "cannot get mcast group: %s\n",
+			nl_geterror(mcid));
+		goto err_free;
+	}
+
+	ret = nl_socket_add_membership(sock, mcid);
+	if (ret) {
+		fprintf(stderr, "failed to join mcast group: %d\n", ret);
+		goto err_free;
+	}
+
+	ret = 1;
+	cb = nl_cb_alloc(NL_CB_DEFAULT);
+	nl_cb_set(cb, NL_CB_SEQ_CHECK, NL_CB_CUSTOM, nl_seq_check, NULL);
+	nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, ovpn_handle_msg, &ret);
+	nl_cb_err(cb, NL_CB_CUSTOM, ovpn_nl_cb_error, &ret);
+
+	while (ret == 1) {
+		int err = nl_recvmsgs(sock, cb);
+
+		if (err < 0) {
+			fprintf(stderr,
+				"cannot receive netlink message: (%d) %s\n",
+				err, nl_geterror(-err));
+			ret = -1;
+			break;
+		}
+	}
+
+	nl_cb_put(cb);
+err_free:
+	nl_socket_free(sock);
+	return ret;
+}
+
+static void usage(const char *cmd)
+{
+	fprintf(stderr,
+		"Usage %s <command> <iface> [arguments..]\n",
+		cmd);
+	fprintf(stderr, "where <command> can be one of the following\n\n");
+
+	fprintf(stderr, "* new_iface <iface> [mode]: create new ovpn interface\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tmode:\n");
+	fprintf(stderr, "\t\t- P2P for peer-to-peer mode (i.e. client)\n");
+	fprintf(stderr, "\t\t- MP for multi-peer mode (i.e. server)\n");
+
+	fprintf(stderr, "* del_iface <iface>: delete ovpn interface\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+
+	fprintf(stderr,
+		"* listen <iface> <lport> <peers_file> [ipv6]: listen for incoming peer TCP connections\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tlport: TCP port to listen to\n");
+	fprintf(stderr,
+		"\tpeers_file: file containing one peer per line: Line format:\n");
+	fprintf(stderr, "\t\t<peer_id> <vpnaddr>\n");
+	fprintf(stderr,
+		"\tipv6: whether the socket should listen to the IPv6 wildcard address\n");
+
+	fprintf(stderr,
+		"* connect <iface> <peer_id> <raddr> <rport> [key_file]: start connecting peer of TCP-based VPN session\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the connecting peer\n");
+	fprintf(stderr, "\traddr: peer IP address to connect to\n");
+	fprintf(stderr, "\trport: peer TCP port to connect to\n");
+	fprintf(stderr,
+		"\tkey_file: file containing the symmetric key for encryption\n");
+
+	fprintf(stderr,
+		"* new_peer <iface> <peer_id> <lport> <raddr> <rport> [vpnaddr]: add new peer\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tlport: local UDP port to bind to\n");
+	fprintf(stderr,
+		"\tpeer_id: peer ID to be used in data packets to/from this peer\n");
+	fprintf(stderr, "\traddr: peer IP address\n");
+	fprintf(stderr, "\trport: peer UDP port\n");
+	fprintf(stderr, "\tvpnaddr: peer VPN IP\n");
+
+	fprintf(stderr,
+		"* new_multi_peer <iface> <lport> <peers_file>: add multiple peers as listed in the file\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tlport: local UDP port to bind to\n");
+	fprintf(stderr,
+		"\tpeers_file: text file containing one peer per line. Line format:\n");
+	fprintf(stderr, "\t\t<peer_id> <raddr> <rport> <vpnaddr>\n");
+
+	fprintf(stderr,
+		"* set_peer <iface> <peer_id> <keepalive_interval> <keepalive_timeout>: set peer attributes\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+	fprintf(stderr,
+		"\tkeepalive_interval: interval for sending ping messages\n");
+	fprintf(stderr,
+		"\tkeepalive_timeout: time after which a peer is timed out\n");
+
+	fprintf(stderr, "* del_peer <iface> <peer_id>: delete peer\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to delete\n");
+
+	fprintf(stderr, "* get_peer <iface> [peer_id]: retrieve peer(s) status\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr,
+		"\tpeer_id: peer ID of the peer to query. All peers are returned if omitted\n");
+
+	fprintf(stderr,
+		"* new_key <iface> <peer_id> <slot> <key_id> <cipher> <key_dir> <key_file>: set data channel key\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr,
+		"\tpeer_id: peer ID of the peer to configure the key for\n");
+	fprintf(stderr, "\tslot: either 1 (primary) or 2 (secondary)\n");
+	fprintf(stderr, "\tkey_id: an ID from 0 to 7\n");
+	fprintf(stderr,
+		"\tcipher: cipher to use, supported: aes (AES-GCM), chachapoly (CHACHA20POLY1305)\n");
+	fprintf(stderr,
+		"\tkey_dir: key direction, must 0 on one host and 1 on the other\n");
+	fprintf(stderr, "\tkey_file: file containing the pre-shared key\n");
+
+	fprintf(stderr,
+		"* del_key <iface> <peer_id> [slot]: erase existing data channel key\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+	fprintf(stderr, "\tslot: slot to erase. PRIMARY if omitted\n");
+
+	fprintf(stderr,
+		"* get_key <iface> <peer_id> <slot>: retrieve non sensible key data\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to query\n");
+	fprintf(stderr, "\tslot: either 1 (primary) or 2 (secondary)\n");
+
+	fprintf(stderr,
+		"* swap_keys <iface> <peer_id>: swap content of primary and secondary key slots\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+
+	fprintf(stderr,
+		"* listen_mcast: listen to ovpn netlink multicast messages\n");
+}
+
+static int ovpn_parse_remote(struct ovpn_ctx *ovpn, const char *host,
+			     const char *service, const char *vpnip)
+{
+	int ret;
+	struct addrinfo *result;
+	struct addrinfo hints = {
+		.ai_family = ovpn->sa_family,
+		.ai_socktype = SOCK_DGRAM,
+		.ai_protocol = IPPROTO_UDP
+	};
+
+	if (host) {
+		ret = getaddrinfo(host, service, &hints, &result);
+		if (ret) {
+			fprintf(stderr, "getaddrinfo on remote error: %s\n",
+				gai_strerror(ret));
+			return -1;
+		}
+
+		if (!(result->ai_family == AF_INET &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in)) &&
+		    !(result->ai_family == AF_INET6 &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in6))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		memcpy(&ovpn->remote, result->ai_addr, result->ai_addrlen);
+	}
+
+	if (vpnip) {
+		ret = getaddrinfo(vpnip, NULL, &hints, &result);
+		if (ret) {
+			fprintf(stderr, "getaddrinfo on vpnip error: %s\n",
+				gai_strerror(ret));
+			return -1;
+		}
+
+		if (!(result->ai_family == AF_INET &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in)) &&
+		    !(result->ai_family == AF_INET6 &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in6))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		memcpy(&ovpn->peer_ip, result->ai_addr, result->ai_addrlen);
+		ovpn->sa_family = result->ai_family;
+
+		ovpn->peer_ip_set = true;
+	}
+
+	ret = 0;
+out:
+	freeaddrinfo(result);
+	return ret;
+}
+
+static int ovpn_parse_new_peer(struct ovpn_ctx *ovpn, const char *peer_id,
+			       const char *raddr, const char *rport,
+			       const char *vpnip)
+{
+	ovpn->peer_id = strtoul(peer_id, NULL, 10);
+	if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+		fprintf(stderr, "peer ID value out of range\n");
+		return -1;
+	}
+
+	return ovpn_parse_remote(ovpn, raddr, rport, vpnip);
+}
+
+static int ovpn_parse_key_slot(const char *arg, struct ovpn_ctx *ovpn)
+{
+	int slot = strtoul(arg, NULL, 10);
+
+	if (errno == ERANGE || slot < 1 || slot > 2) {
+		fprintf(stderr, "key slot out of range\n");
+		return -1;
+	}
+
+	switch (slot) {
+	case 1:
+		ovpn->key_slot = OVPN_KEY_SLOT_PRIMARY;
+		break;
+	case 2:
+		ovpn->key_slot = OVPN_KEY_SLOT_SECONDARY;
+		break;
+	}
+
+	return 0;
+}
+
+static int ovpn_send_tcp_data(int socket)
+{
+	uint16_t len = htons(1000);
+	uint8_t buf[1002];
+	int ret;
+
+	memcpy(buf, &len, sizeof(len));
+	memset(buf + sizeof(len), 0x86, sizeof(buf) - sizeof(len));
+
+	ret = send(socket, buf, sizeof(buf), MSG_NOSIGNAL);
+
+	fprintf(stdout, "Sent %u bytes over TCP socket\n", ret);
+
+	return ret > 0 ? 0 : ret;
+}
+
+static int ovpn_recv_tcp_data(int socket)
+{
+	uint8_t buf[1002];
+	uint16_t len;
+	int ret;
+
+	ret = recv(socket, buf, sizeof(buf), MSG_NOSIGNAL);
+
+	if (ret < 2) {
+		fprintf(stderr, ">>>> Error while reading TCP data: %d\n", ret);
+		return ret;
+	}
+
+	memcpy(&len, buf, sizeof(len));
+	len = ntohs(len);
+
+	fprintf(stdout, ">>>> Received %u bytes over TCP socket, header: %u\n",
+		ret, len);
+
+	return 0;
+}
+
+static enum ovpn_cmd ovpn_parse_cmd(const char *cmd)
+{
+	if (!strcmp(cmd, "new_iface"))
+		return CMD_NEW_IFACE;
+
+	if (!strcmp(cmd, "del_iface"))
+		return CMD_DEL_IFACE;
+
+	if (!strcmp(cmd, "listen"))
+		return CMD_LISTEN;
+
+	if (!strcmp(cmd, "connect"))
+		return CMD_CONNECT;
+
+	if (!strcmp(cmd, "new_peer"))
+		return CMD_NEW_PEER;
+
+	if (!strcmp(cmd, "new_multi_peer"))
+		return CMD_NEW_MULTI_PEER;
+
+	if (!strcmp(cmd, "set_peer"))
+		return CMD_SET_PEER;
+
+	if (!strcmp(cmd, "del_peer"))
+		return CMD_DEL_PEER;
+
+	if (!strcmp(cmd, "get_peer"))
+		return CMD_GET_PEER;
+
+	if (!strcmp(cmd, "new_key"))
+		return CMD_NEW_KEY;
+
+	if (!strcmp(cmd, "del_key"))
+		return CMD_DEL_KEY;
+
+	if (!strcmp(cmd, "get_key"))
+		return CMD_GET_KEY;
+
+	if (!strcmp(cmd, "swap_keys"))
+		return CMD_SWAP_KEYS;
+
+	if (!strcmp(cmd, "listen_mcast"))
+		return CMD_LISTEN_MCAST;
+
+	return CMD_INVALID;
+}
+
+/* Send process to background and waits for signal.
+ *
+ * This helper is called at the end of commands
+ * creating sockets, so that the latter stay alive
+ * along with the process that created them.
+ *
+ * A signal is expected to be delivered in order to
+ * terminate the waiting processes
+ */
+static void ovpn_waitbg(void)
+{
+	daemon(1, 1);
+	pause();
+}
+
+static int ovpn_run_cmd(struct ovpn_ctx *ovpn)
+{
+	char peer_id[10], vpnip[INET6_ADDRSTRLEN], laddr[128], lport[10];
+	char raddr[128], rport[10];
+	int n, ret;
+	FILE *fp;
+
+	switch (ovpn->cmd) {
+	case CMD_NEW_IFACE:
+		ret = ovpn_new_iface(ovpn);
+		break;
+	case CMD_DEL_IFACE:
+		ret = ovpn_del_iface(ovpn);
+		break;
+	case CMD_LISTEN:
+		ret = ovpn_listen(ovpn, ovpn->sa_family);
+		if (ret < 0) {
+			fprintf(stderr, "cannot listen on TCP socket\n");
+			return ret;
+		}
+
+		fp = fopen(ovpn->peers_file, "r");
+		if (!fp) {
+			fprintf(stderr, "cannot open file: %s\n",
+				ovpn->peers_file);
+			return -1;
+		}
+
+		int num_peers = 0;
+
+		while ((n = fscanf(fp, "%s %s\n", peer_id, vpnip)) == 2) {
+			struct ovpn_ctx peer_ctx = { 0 };
+
+			if (num_peers == MAX_PEERS) {
+				fprintf(stderr, "max peers reached!\n");
+				return -E2BIG;
+			}
+
+			peer_ctx.ifindex = ovpn->ifindex;
+			peer_ctx.sa_family = ovpn->sa_family;
+
+			peer_ctx.socket = ovpn_accept(ovpn);
+			if (peer_ctx.socket < 0) {
+				fprintf(stderr, "cannot accept connection!\n");
+				return -1;
+			}
+
+			/* store peer sockets to test TCP I/O */
+			ovpn->cli_sockets[num_peers] = peer_ctx.socket;
+
+			ret = ovpn_parse_new_peer(&peer_ctx, peer_id, NULL,
+						  NULL, vpnip);
+			if (ret < 0) {
+				fprintf(stderr, "error while parsing line\n");
+				return -1;
+			}
+
+			ret = ovpn_new_peer(&peer_ctx, true);
+			if (ret < 0) {
+				fprintf(stderr,
+					"cannot add peer to VPN: %s %s\n",
+					peer_id, vpnip);
+				return ret;
+			}
+			num_peers++;
+		}
+
+		for (int i = 0; i < num_peers; i++) {
+			ret = ovpn_recv_tcp_data(ovpn->cli_sockets[i]);
+			if (ret < 0)
+				break;
+		}
+		ovpn_waitbg();
+		break;
+	case CMD_CONNECT:
+		ret = ovpn_connect(ovpn);
+		if (ret < 0) {
+			fprintf(stderr, "cannot connect TCP socket\n");
+			return ret;
+		}
+
+		ret = ovpn_new_peer(ovpn, true);
+		if (ret < 0) {
+			fprintf(stderr, "cannot add peer to VPN\n");
+			close(ovpn->socket);
+			return ret;
+		}
+
+		if (ovpn->cipher != OVPN_CIPHER_ALG_NONE) {
+			ret = ovpn_new_key(ovpn);
+			if (ret < 0) {
+				fprintf(stderr, "cannot set key\n");
+				return ret;
+			}
+		}
+
+		ret = ovpn_send_tcp_data(ovpn->socket);
+		ovpn_waitbg();
+		break;
+	case CMD_NEW_PEER:
+		ret = ovpn_udp_socket(ovpn, AF_INET6);
+		if (ret < 0)
+			return ret;
+
+		ret = ovpn_new_peer(ovpn, false);
+		ovpn_waitbg();
+		break;
+	case CMD_NEW_MULTI_PEER:
+		ret = ovpn_udp_socket(ovpn, AF_INET6);
+		if (ret < 0)
+			return ret;
+
+		fp = fopen(ovpn->peers_file, "r");
+		if (!fp) {
+			fprintf(stderr, "cannot open file: %s\n",
+				ovpn->peers_file);
+			return -1;
+		}
+
+		while ((n = fscanf(fp, "%s %s %s %s %s %s\n", peer_id, laddr,
+				   lport, raddr, rport, vpnip)) == 6) {
+			struct ovpn_ctx peer_ctx = { 0 };
+
+			peer_ctx.ifindex = ovpn->ifindex;
+			peer_ctx.socket = ovpn->socket;
+			peer_ctx.sa_family = AF_UNSPEC;
+
+			ret = ovpn_parse_new_peer(&peer_ctx, peer_id, raddr,
+						  rport, vpnip);
+			if (ret < 0) {
+				fprintf(stderr, "error while parsing line\n");
+				return -1;
+			}
+
+			ret = ovpn_new_peer(&peer_ctx, false);
+			if (ret < 0) {
+				fprintf(stderr,
+					"cannot add peer to VPN: %s %s %s %s\n",
+					peer_id, raddr, rport, vpnip);
+				return ret;
+			}
+		}
+		ovpn_waitbg();
+		break;
+	case CMD_SET_PEER:
+		ret = ovpn_set_peer(ovpn);
+		break;
+	case CMD_DEL_PEER:
+		ret = ovpn_del_peer(ovpn);
+		break;
+	case CMD_GET_PEER:
+		if (ovpn->peer_id == PEER_ID_UNDEF)
+			fprintf(stderr, "List of peers connected to: %s\n",
+				ovpn->ifname);
+
+		ret = ovpn_get_peer(ovpn);
+		break;
+	case CMD_NEW_KEY:
+		ret = ovpn_new_key(ovpn);
+		break;
+	case CMD_DEL_KEY:
+		ret = ovpn_del_key(ovpn);
+		break;
+	case CMD_GET_KEY:
+		ret = ovpn_get_key(ovpn);
+		break;
+	case CMD_SWAP_KEYS:
+		ret = ovpn_swap_keys(ovpn);
+		break;
+	case CMD_LISTEN_MCAST:
+		ret = ovpn_listen_mcast();
+		break;
+	case CMD_INVALID:
+		break;
+	}
+
+	return ret;
+}
+
+static int ovpn_parse_cmd_args(struct ovpn_ctx *ovpn, int argc, char *argv[])
+{
+	int ret;
+
+	/* no args required for LISTEN_MCAST */
+	if (ovpn->cmd == CMD_LISTEN_MCAST)
+		return 0;
+
+	/* all commands need an ifname */
+	if (argc < 3)
+		return -EINVAL;
+
+	strscpy(ovpn->ifname, argv[2], IFNAMSIZ - 1);
+	ovpn->ifname[IFNAMSIZ - 1] = '\0';
+
+	/* all commands, except NEW_IFNAME, needs an ifindex */
+	if (ovpn->cmd != CMD_NEW_IFACE) {
+		ovpn->ifindex = if_nametoindex(ovpn->ifname);
+		if (!ovpn->ifindex) {
+			fprintf(stderr, "cannot find interface: %s\n",
+				strerror(errno));
+			return -1;
+		}
+	}
+
+	switch (ovpn->cmd) {
+	case CMD_NEW_IFACE:
+		if (argc < 4)
+			break;
+
+		if (!strcmp(argv[3], "P2P")) {
+			ovpn->mode = OVPN_MODE_P2P;
+		} else if (!strcmp(argv[3], "MP")) {
+			ovpn->mode = OVPN_MODE_MP;
+		} else {
+			fprintf(stderr, "Cannot parse iface mode: %s\n",
+				argv[3]);
+			return -1;
+		}
+		ovpn->mode_set = true;
+		break;
+	case CMD_DEL_IFACE:
+		break;
+	case CMD_LISTEN:
+		if (argc < 5)
+			return -EINVAL;
+
+		ovpn->lport = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->lport > 65535) {
+			fprintf(stderr, "lport value out of range\n");
+			return -1;
+		}
+
+		ovpn->peers_file = argv[4];
+
+		if (argc > 5 && !strcmp(argv[5], "ipv6"))
+			ovpn->sa_family = AF_INET6;
+		break;
+	case CMD_CONNECT:
+		if (argc < 6)
+			return -EINVAL;
+
+		ovpn->sa_family = AF_INET;
+
+		ret = ovpn_parse_new_peer(ovpn, argv[3], argv[4], argv[5],
+					  NULL);
+		if (ret < 0) {
+			fprintf(stderr, "Cannot parse remote peer data\n");
+			return -1;
+		}
+
+		if (argc > 6) {
+			ovpn->key_slot = OVPN_KEY_SLOT_PRIMARY;
+			ovpn->key_id = 0;
+			ovpn->cipher = OVPN_CIPHER_ALG_AES_GCM;
+			ovpn->key_dir = KEY_DIR_OUT;
+
+			ret = ovpn_parse_key(argv[6], ovpn);
+			if (ret)
+				return -1;
+		}
+		break;
+	case CMD_NEW_PEER:
+		if (argc < 7)
+			return -EINVAL;
+
+		ovpn->lport = strtoul(argv[4], NULL, 10);
+		if (errno == ERANGE || ovpn->lport > 65535) {
+			fprintf(stderr, "lport value out of range\n");
+			return -1;
+		}
+
+		const char *vpnip = (argc > 7) ? argv[7] : NULL;
+
+		ret = ovpn_parse_new_peer(ovpn, argv[3], argv[5], argv[6],
+					  vpnip);
+		if (ret < 0)
+			return -1;
+		break;
+	case CMD_NEW_MULTI_PEER:
+		if (argc < 5)
+			return -EINVAL;
+
+		ovpn->lport = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->lport > 65535) {
+			fprintf(stderr, "lport value out of range\n");
+			return -1;
+		}
+
+		ovpn->peers_file = argv[4];
+		break;
+	case CMD_SET_PEER:
+		if (argc < 6)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ovpn->keepalive_interval = strtoul(argv[4], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr,
+				"keepalive interval value out of range\n");
+			return -1;
+		}
+
+		ovpn->keepalive_timeout = strtoul(argv[5], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr,
+				"keepalive interval value out of range\n");
+			return -1;
+		}
+		break;
+	case CMD_DEL_PEER:
+		if (argc < 4)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+		break;
+	case CMD_GET_PEER:
+		ovpn->peer_id = PEER_ID_UNDEF;
+		if (argc > 3) {
+			ovpn->peer_id = strtoul(argv[3], NULL, 10);
+			if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+				fprintf(stderr, "peer ID value out of range\n");
+				return -1;
+			}
+		}
+		break;
+	case CMD_NEW_KEY:
+		if (argc < 9)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_key_slot(argv[4], ovpn);
+		if (ret)
+			return -1;
+
+		ovpn->key_id = strtoul(argv[5], NULL, 10);
+		if (errno == ERANGE || ovpn->key_id > 2) {
+			fprintf(stderr, "key ID out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_cipher(argv[6], ovpn);
+		if (ret < 0)
+			return -1;
+
+		ret = ovpn_parse_key_direction(argv[7], ovpn);
+		if (ret < 0)
+			return -1;
+
+		ret = ovpn_parse_key(argv[8], ovpn);
+		if (ret)
+			return -1;
+		break;
+	case CMD_DEL_KEY:
+		if (argc < 4)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_key_slot(argv[4], ovpn);
+		if (ret)
+			return ret;
+		break;
+	case CMD_GET_KEY:
+		if (argc < 5)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_key_slot(argv[4], ovpn);
+		if (ret)
+			return ret;
+		break;
+	case CMD_SWAP_KEYS:
+		if (argc < 4)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+		break;
+	case CMD_LISTEN_MCAST:
+		break;
+	case CMD_INVALID:
+		break;
+	}
+
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	struct ovpn_ctx ovpn;
+	int ret;
+
+	if (argc < 2) {
+		usage(argv[0]);
+		return -1;
+	}
+
+	memset(&ovpn, 0, sizeof(ovpn));
+	ovpn.sa_family = AF_UNSPEC;
+	ovpn.cipher = OVPN_CIPHER_ALG_NONE;
+
+	ovpn.cmd = ovpn_parse_cmd(argv[1]);
+	if (ovpn.cmd == CMD_INVALID) {
+		fprintf(stderr, "Error: unknown command.\n\n");
+		usage(argv[0]);
+		return -1;
+	}
+
+	ret = ovpn_parse_cmd_args(&ovpn, argc, argv);
+	if (ret < 0) {
+		fprintf(stderr, "Error: invalid arguments.\n\n");
+		if (ret == -EINVAL)
+			usage(argv[0]);
+		return ret;
+	}
+
+	ret = ovpn_run_cmd(&ovpn);
+	if (ret)
+		fprintf(stderr, "Cannot execute command: %s (%d)\n",
+			strerror(-ret), ret);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/net/ovpn/tcp_peers.txt b/tools/testing/selftests/net/ovpn/tcp_peers.txt
new file mode 100644
index 000000000000..d753eebe8716
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/tcp_peers.txt
@@ -0,0 +1,5 @@
+1 5.5.5.2
+2 5.5.5.3
+3 5.5.5.4
+4 5.5.5.5
+5 5.5.5.6
diff --git a/tools/testing/selftests/net/ovpn/test-chachapoly.sh b/tools/testing/selftests/net/ovpn/test-chachapoly.sh
new file mode 100755
index 000000000000..32504079a2b8
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-chachapoly.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+ALG="chachapoly"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh b/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh
new file mode 100755
index 000000000000..093d44772ffd
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+PROTO="TCP"
+
+source test-close-socket.sh
diff --git a/tools/testing/selftests/net/ovpn/test-close-socket.sh b/tools/testing/selftests/net/ovpn/test-close-socket.sh
new file mode 100755
index 000000000000..5e48a8b67928
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-close-socket.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+#set -x
+set -e
+
+source ./common.sh
+
+cleanup
+
+modprobe -q ovpn || true
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	create_ns ${p}
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	setup_ns ${p} 5.5.5.$((${p} + 1))/24
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	add_peer ${p}
+done
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 60 120
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 60 120
+done
+
+sleep 1
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ping -qfc 500 -w 3 5.5.5.$((${p} + 1))
+done
+
+ip netns exec peer0 iperf3 -1 -s &
+sleep 1
+ip netns exec peer1 iperf3 -Z -t 3 -c 5.5.5.1
+
+cleanup
+
+modprobe -r ovpn || true
diff --git a/tools/testing/selftests/net/ovpn/test-float.sh b/tools/testing/selftests/net/ovpn/test-float.sh
new file mode 100755
index 000000000000..ba5d725e18b0
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-float.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+FLOAT="1"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test-tcp.sh b/tools/testing/selftests/net/ovpn/test-tcp.sh
new file mode 100755
index 000000000000..ba3f1f315a34
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-tcp.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+PROTO="TCP"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test.sh b/tools/testing/selftests/net/ovpn/test.sh
new file mode 100755
index 000000000000..e8acdc303307
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test.sh
@@ -0,0 +1,117 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+#set -x
+set -e
+
+source ./common.sh
+
+cleanup
+
+modprobe -q ovpn || true
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	create_ns ${p}
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	setup_ns ${p} 5.5.5.$((${p} + 1))/24 ${MTU}
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	add_peer ${p}
+done
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 60 120
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 60 120
+done
+
+sleep 1
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ping -qfc 500 -w 3 5.5.5.$((${p} + 1))
+	ip netns exec peer0 ping -qfc 500 -s 3000 -w 3 5.5.5.$((${p} + 1))
+done
+
+# ping LAN behind client 1
+ip netns exec peer0 ping -qfc 500 -w 3 ${LAN_IP}
+
+if [ "$FLOAT" == "1" ]; then
+	# make clients float..
+	for p in $(seq 1 ${NUM_PEERS}); do
+		ip -n peer${p} addr del 10.10.${p}.2/24 dev veth${p}
+		ip -n peer${p} addr add 10.10.${p}.3/24 dev veth${p}
+	done
+	for p in $(seq 1 ${NUM_PEERS}); do
+		ip netns exec peer${p} ping -qfc 500 -w 3 5.5.5.1
+	done
+fi
+
+ip netns exec peer0 iperf3 -1 -s &
+sleep 1
+ip netns exec peer1 iperf3 -Z -t 3 -c 5.5.5.1
+
+echo "Adding secondary key and then swap:"
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 2 1 ${ALG} 0 data64.key
+	ip netns exec peer${p} ${OVPN_CLI} new_key tun${p} ${p} 2 1 ${ALG} 1 data64.key
+	ip netns exec peer${p} ${OVPN_CLI} swap_keys tun${p} ${p}
+done
+
+sleep 1
+
+echo "Querying all peers:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0
+ip netns exec peer1 ${OVPN_CLI} get_peer tun1
+
+echo "Querying peer 1:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0 1
+
+echo "Querying non-existent peer 10:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0 10 || true
+
+echo "Deleting peer 1:"
+ip netns exec peer0 ${OVPN_CLI} del_peer tun0 1
+ip netns exec peer1 ${OVPN_CLI} del_peer tun1 1
+
+echo "Querying keys:"
+for p in $(seq 2 ${NUM_PEERS}); do
+	ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} ${p} 1
+	ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} ${p} 2
+done
+
+echo "Deleting peer while sending traffic:"
+(ip netns exec peer2 ping -qf -w 4 5.5.5.1)&
+sleep 2
+ip netns exec peer0 ${OVPN_CLI} del_peer tun0 2
+# following command fails in TCP mode
+# (both ends get conn reset when one peer disconnects)
+ip netns exec peer2 ${OVPN_CLI} del_peer tun2 2 || true
+
+echo "Deleting keys:"
+for p in $(seq 3 ${NUM_PEERS}); do
+	ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} ${p} 1
+	ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} ${p} 2
+done
+
+echo "Setting timeout to 3s MP:"
+for p in $(seq 3 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 3 3 || true
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 0 0
+done
+# wait for peers to timeout
+sleep 5
+
+echo "Setting timeout to 3s P2P:"
+for p in $(seq 3 ${NUM_PEERS}); do
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 3 3
+done
+sleep 5
+
+cleanup
+
+modprobe -r ovpn || true
diff --git a/tools/testing/selftests/net/ovpn/udp_peers.txt b/tools/testing/selftests/net/ovpn/udp_peers.txt
new file mode 100644
index 000000000000..e9773ddf875c
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/udp_peers.txt
@@ -0,0 +1,6 @@
+1 10.10.1.1 1 10.10.1.2 1 5.5.5.2
+2 10.10.2.1 1 10.10.2.2 1 5.5.5.3
+3 10.10.3.1 1 10.10.3.2 1 5.5.5.4
+4 fd00:0:0:4::1 1 fd00:0:0:4::2 1 5.5.5.5
+5 fd00:0:0:5::1 1 fd00:0:0:5::2 1 5.5.5.6
+6 fd00:0:0:6::1 1 fd00:0:0:6::2 1 5.5.5.7
diff --git a/tools/testing/selftests/net/reuseport_addr_any.c b/tools/testing/selftests/net/reuseport_addr_any.c
index b8475cb29be7..1c43401a1c80 100644
--- a/tools/testing/selftests/net/reuseport_addr_any.c
+++ b/tools/testing/selftests/net/reuseport_addr_any.c
@@ -9,7 +9,6 @@
 #include <arpa/inet.h>
 #include <errno.h>
 #include <error.h>
-#include <linux/dccp.h>
 #include <linux/in.h>
 #include <linux/unistd.h>
 #include <stdbool.h>
@@ -21,10 +20,6 @@
 #include <sys/socket.h>
 #include <unistd.h>
 
-#ifndef SOL_DCCP
-#define SOL_DCCP 269
-#endif
-
 static const char *IP4_ADDR = "127.0.0.1";
 static const char *IP6_ADDR = "::1";
 static const char *IP4_MAPPED6 = "::ffff:127.0.0.1";
@@ -86,15 +81,6 @@ static void build_rcv_fd(int family, int proto, int *rcv_fds, int count,
 
 		if (proto == SOCK_STREAM && listen(rcv_fds[i], 10))
 			error(1, errno, "tcp: failed to listen on receive port");
-		else if (proto == SOCK_DCCP) {
-			if (setsockopt(rcv_fds[i], SOL_DCCP,
-					DCCP_SOCKOPT_SERVICE,
-					&(int) {htonl(42)}, sizeof(int)))
-				error(1, errno, "failed to setsockopt");
-
-			if (listen(rcv_fds[i], 10))
-				error(1, errno, "dccp: failed to listen on receive port");
-		}
 	}
 }
 
@@ -148,11 +134,6 @@ static int connect_and_send(int family, int proto)
 	if (fd < 0)
 		error(1, errno, "failed to create send socket");
 
-	if (proto == SOCK_DCCP &&
-		setsockopt(fd, SOL_DCCP, DCCP_SOCKOPT_SERVICE,
-				&(int){htonl(42)}, sizeof(int)))
-		error(1, errno, "failed to setsockopt");
-
 	if (bind(fd, saddr, sz))
 		error(1, errno, "failed to bind send socket");
 
@@ -175,7 +156,7 @@ static int receive_once(int epfd, int proto)
 	if (i < 0)
 		error(1, errno, "epoll_wait failed");
 
-	if (proto == SOCK_STREAM || proto == SOCK_DCCP) {
+	if (proto == SOCK_STREAM) {
 		fd = accept(ev.data.fd, NULL, NULL);
 		if (fd < 0)
 			error(1, errno, "failed to accept");
@@ -243,20 +224,6 @@ static void run_one_test(int fam_send, int fam_rcv, int proto,
 
 static void test_proto(int proto, const char *proto_str)
 {
-	if (proto == SOCK_DCCP) {
-		int test_fd;
-
-		test_fd = socket(AF_INET, proto, 0);
-		if (test_fd < 0) {
-			if (errno == ESOCKTNOSUPPORT) {
-				fprintf(stderr, "DCCP not supported: skipping DCCP tests\n");
-				return;
-			} else
-				error(1, errno, "failed to create a DCCP socket");
-		}
-		close(test_fd);
-	}
-
 	fprintf(stderr, "%s IPv4 ... ", proto_str);
 	run_one_test(AF_INET, AF_INET, proto, IP4_ADDR);
 
@@ -271,7 +238,6 @@ int main(void)
 {
 	test_proto(SOCK_DGRAM, "UDP");
 	test_proto(SOCK_STREAM, "TCP");
-	test_proto(SOCK_DCCP, "DCCP");
 
 	fprintf(stderr, "SUCCESS\n");
 	return 0;
diff --git a/tools/testing/selftests/net/skf_net_off.c b/tools/testing/selftests/net/skf_net_off.c
new file mode 100644
index 000000000000..1fdf61d6cd7f
--- /dev/null
+++ b/tools/testing/selftests/net/skf_net_off.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Open a tun device.
+ *
+ * [modifications: use IFF_NAPI_FRAGS, add sk filter]
+ *
+ * Expects the device to have been configured previously, e.g.:
+ *   sudo ip tuntap add name tap1 mode tap
+ *   sudo ip link set tap1 up
+ *   sudo ip link set dev tap1 addr 02:00:00:00:00:01
+ *   sudo ip -6 addr add fdab::1 peer fdab::2 dev tap1 nodad
+ *
+ * And to avoid premature pskb_may_pull:
+ *
+ *   sudo ethtool -K tap1 gro off
+ *   sudo bash -c 'echo 0 > /proc/sys/net/ipv4/ip_early_demux'
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <linux/filter.h>
+#include <linux/if.h>
+#include <linux/if_packet.h>
+#include <linux/if_tun.h>
+#include <linux/ipv6.h>
+#include <netinet/if_ether.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/poll.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <unistd.h>
+
+static bool cfg_do_filter;
+static bool cfg_do_frags;
+static int cfg_dst_port = 8000;
+static char *cfg_ifname;
+
+static int tun_open(const char *tun_name)
+{
+	struct ifreq ifr = {0};
+	int fd, ret;
+
+	fd = open("/dev/net/tun", O_RDWR);
+	if (fd == -1)
+		error(1, errno, "open /dev/net/tun");
+
+	ifr.ifr_flags = IFF_TAP;
+	if (cfg_do_frags)
+		ifr.ifr_flags |= IFF_NAPI | IFF_NAPI_FRAGS;
+
+	strncpy(ifr.ifr_name, tun_name, IFNAMSIZ - 1);
+
+	ret = ioctl(fd, TUNSETIFF, &ifr);
+	if (ret)
+		error(1, ret, "ioctl TUNSETIFF");
+
+	return fd;
+}
+
+static void sk_set_filter(int fd)
+{
+	const int offset_proto = offsetof(struct ip6_hdr, ip6_nxt);
+	const int offset_dport = sizeof(struct ip6_hdr) + offsetof(struct udphdr, dest);
+
+	/* Filter UDP packets with destination port cfg_dst_port */
+	struct sock_filter filter_code[] = {
+		BPF_STMT(BPF_LD  + BPF_B   + BPF_ABS, SKF_AD_OFF + SKF_AD_PKTTYPE),
+		BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, PACKET_HOST, 0, 4),
+		BPF_STMT(BPF_LD  + BPF_B   + BPF_ABS, SKF_NET_OFF + offset_proto),
+		BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_UDP, 0, 2),
+		BPF_STMT(BPF_LD  + BPF_H   + BPF_ABS, SKF_NET_OFF + offset_dport),
+		BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, cfg_dst_port, 1, 0),
+		BPF_STMT(BPF_RET + BPF_K, 0),
+		BPF_STMT(BPF_RET + BPF_K, 0xFFFF),
+	};
+
+	struct sock_fprog filter = {
+		sizeof(filter_code) / sizeof(filter_code[0]),
+		filter_code,
+	};
+
+	if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &filter, sizeof(filter)))
+		error(1, errno, "setsockopt attach filter");
+}
+
+static int raw_open(void)
+{
+	int fd;
+
+	fd = socket(PF_INET6, SOCK_RAW, IPPROTO_UDP);
+	if (fd == -1)
+		error(1, errno, "socket raw (udp)");
+
+	if (cfg_do_filter)
+		sk_set_filter(fd);
+
+	return fd;
+}
+
+static void tun_write(int fd)
+{
+	const char eth_src[] = { 0x02, 0x00, 0x00, 0x00, 0x00, 0x02 };
+	const char eth_dst[] = { 0x02, 0x00, 0x00, 0x00, 0x00, 0x01 };
+	struct tun_pi pi = {0};
+	struct ipv6hdr ip6h = {0};
+	struct udphdr uh = {0};
+	struct ethhdr eth = {0};
+	uint32_t payload;
+	struct iovec iov[5];
+	int ret;
+
+	pi.proto = htons(ETH_P_IPV6);
+
+	memcpy(eth.h_source, eth_src, sizeof(eth_src));
+	memcpy(eth.h_dest, eth_dst, sizeof(eth_dst));
+	eth.h_proto = htons(ETH_P_IPV6);
+
+	ip6h.version = 6;
+	ip6h.payload_len = htons(sizeof(uh) + sizeof(uint32_t));
+	ip6h.nexthdr = IPPROTO_UDP;
+	ip6h.hop_limit = 8;
+	if (inet_pton(AF_INET6, "fdab::2", &ip6h.saddr) != 1)
+		error(1, errno, "inet_pton src");
+	if (inet_pton(AF_INET6, "fdab::1", &ip6h.daddr) != 1)
+		error(1, errno, "inet_pton src");
+
+	uh.source = htons(8000);
+	uh.dest = htons(cfg_dst_port);
+	uh.len = ip6h.payload_len;
+	uh.check = 0;
+
+	payload = htonl(0xABABABAB);		/* Covered in IPv6 length */
+
+	iov[0].iov_base = &pi;
+	iov[0].iov_len  = sizeof(pi);
+	iov[1].iov_base = &eth;
+	iov[1].iov_len  = sizeof(eth);
+	iov[2].iov_base = &ip6h;
+	iov[2].iov_len  = sizeof(ip6h);
+	iov[3].iov_base = &uh;
+	iov[3].iov_len  = sizeof(uh);
+	iov[4].iov_base = &payload;
+	iov[4].iov_len  = sizeof(payload);
+
+	ret = writev(fd, iov, sizeof(iov) / sizeof(iov[0]));
+	if (ret <= 0)
+		error(1, errno, "writev");
+}
+
+static void raw_read(int fd)
+{
+	struct timeval tv = { .tv_usec = 100 * 1000 };
+	struct msghdr msg = {0};
+	struct iovec iov[2];
+	struct udphdr uh;
+	uint32_t payload[2];
+	int ret;
+
+	if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+		error(1, errno, "setsockopt rcvtimeo udp");
+
+	iov[0].iov_base = &uh;
+	iov[0].iov_len = sizeof(uh);
+
+	iov[1].iov_base = payload;
+	iov[1].iov_len = sizeof(payload);
+
+	msg.msg_iov = iov;
+	msg.msg_iovlen = sizeof(iov) / sizeof(iov[0]);
+
+	ret = recvmsg(fd, &msg, 0);
+	if (ret <= 0)
+		error(1, errno, "read raw");
+	if (ret != sizeof(uh) + sizeof(payload[0]))
+		error(1, errno, "read raw: len=%d\n", ret);
+
+	fprintf(stderr, "raw recv: 0x%x\n", payload[0]);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "fFi:")) != -1) {
+		switch (c) {
+		case 'f':
+			cfg_do_filter = true;
+			printf("bpf filter enabled\n");
+			break;
+		case 'F':
+			cfg_do_frags = true;
+			printf("napi frags mode enabled\n");
+			break;
+		case 'i':
+			cfg_ifname = optarg;
+			break;
+		default:
+			error(1, 0, "unknown option %c", optopt);
+			break;
+		}
+	}
+
+	if (!cfg_ifname)
+		error(1, 0, "must specify tap interface name (-i)");
+}
+
+int main(int argc, char **argv)
+{
+	int fdt, fdr;
+
+	parse_opts(argc, argv);
+
+	fdr = raw_open();
+	fdt = tun_open(cfg_ifname);
+
+	tun_write(fdt);
+	raw_read(fdr);
+
+	if (close(fdt))
+		error(1, errno, "close tun");
+	if (close(fdr))
+		error(1, errno, "close udp");
+
+	fprintf(stderr, "OK\n");
+	return 0;
+}
+
diff --git a/tools/testing/selftests/net/skf_net_off.sh b/tools/testing/selftests/net/skf_net_off.sh
new file mode 100755
index 000000000000..5da5066fb465
--- /dev/null
+++ b/tools/testing/selftests/net/skf_net_off.sh
@@ -0,0 +1,30 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+readonly NS="ns-$(mktemp -u XXXXXX)"
+
+cleanup() {
+	ip netns del $NS
+}
+
+ip netns add $NS
+trap cleanup EXIT
+
+ip -netns $NS link set lo up
+ip -netns $NS tuntap add name tap1 mode tap
+ip -netns $NS link set tap1 up
+ip -netns $NS link set dev tap1 addr 02:00:00:00:00:01
+ip -netns $NS -6 addr add fdab::1 peer fdab::2 dev tap1 nodad
+ip netns exec $NS ethtool -K tap1 gro off
+
+# disable early demux, else udp_v6_early_demux pulls udp header into linear
+ip netns exec $NS sysctl -w net.ipv4.ip_early_demux=0
+
+echo "no filter"
+ip netns exec $NS ./skf_net_off -i tap1
+
+echo "filter, linear skb (-f)"
+ip netns exec $NS ./skf_net_off -i tap1 -f
+
+echo "filter, fragmented skb (-f) (-F)"
+ip netns exec $NS ./skf_net_off -i tap1 -f -F
diff --git a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
index 02d617040793..a5e959a080bb 100755
--- a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
@@ -285,11 +285,6 @@ setup_hs()
 	ip netns exec ${hsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec ${hsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
 
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0
-
 	ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
 	ip -netns ${hsname} link set ${rtveth} netns ${rtname}
 	ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hid}/64 dev veth0 nodad
diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
index 79fb81e63c59..a649dba3cb77 100755
--- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
@@ -250,11 +250,6 @@ setup_hs()
 	eval local rtname=\${rt_${rid}}
 	local rtveth=veth-t${tid}
 
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0
-
 	ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
 	ip -netns ${hsname} link set ${rtveth} netns ${rtname}
 	ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hid}/24 dev veth0
diff --git a/tools/testing/selftests/net/srv6_end_flavors_test.sh b/tools/testing/selftests/net/srv6_end_flavors_test.sh
index 50563443a4ad..318487eda671 100755
--- a/tools/testing/selftests/net/srv6_end_flavors_test.sh
+++ b/tools/testing/selftests/net/srv6_end_flavors_test.sh
@@ -399,7 +399,7 @@ __get_srv6_rtcfg_id()
 
 # Given the description of a router <id:op> as an input, the function returns
 # the <op> token which represents the operation (e.g. End behavior with or
-# withouth flavors) configured for the node.
+# without flavors) configured for the node.
 
 # Note that when the operation represents an End behavior with a list of
 # flavors, the output is the ordered version of that list.
@@ -480,7 +480,7 @@ setup_rt_local_sids()
 
 
 	# all SIDs start with a common locator. Routes and SRv6 Endpoint
-	# behavior instaces are grouped together in the 'localsid' table.
+	# behavior instances are grouped together in the 'localsid' table.
 	ip -netns "${nsname}" -6 rule \
 		add to "${LOCATOR_SERVICE}::/16" \
 		lookup "${LOCALSID_TABLE_ID}" prio 999
diff --git a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
index 87e414cc417c..ba730655a7bf 100755
--- a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
@@ -245,10 +245,8 @@
 # that adopted in the use cases already examined (of course, it is necessary to
 # consider the different SIDs/C-SIDs).
 
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
 
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
 readonly DUMMY_DEVNAME="dum0"
 readonly VRF_TID=100
 readonly VRF_DEVNAME="vrf-${VRF_TID}"
@@ -376,32 +374,18 @@ test_command_or_ksft_skip()
 	fi
 }
 
-get_nodename()
-{
-	local name="$1"
-
-	echo "${name}-${RDMSUFF}"
-}
-
 get_rtname()
 {
 	local rtid="$1"
 
-	get_nodename "rt-${rtid}"
+	echo "rt_${rtid}"
 }
 
 get_hsname()
 {
 	local hsid="$1"
 
-	get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
-	local name="$1"
-
-	ip netns add "${name}"
+	echo "hs_${hsid}"
 }
 
 create_router()
@@ -410,8 +394,7 @@ create_router()
 	local nsname
 
 	nsname="$(get_rtname "${rtid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 create_host()
@@ -420,28 +403,12 @@ create_host()
 	local nsname
 
 	nsname="$(get_hsname "${hsid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 cleanup()
 {
-	local nsname
-	local i
-
-	# destroy routers
-	for i in ${ROUTERS}; do
-		nsname="$(get_rtname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
-	# destroy hosts
-	for i in ${HOSTS}; do
-		nsname="$(get_hsname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
+	cleanup_all_ns
 
 	# check whether the setup phase was completed successfully or not. In
 	# case of an error during the setup phase of the testing environment,
@@ -462,10 +429,10 @@ add_link_rt_pairs()
 	local nsname
 	local neigh_nsname
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
-		neigh_nsname="$(get_rtname "${neigh}")"
+		eval neigh_nsname=\${$(get_rtname "${neigh}")}
 
 		ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
 			type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -497,7 +464,7 @@ setup_rt_networking()
 	local devname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -518,9 +485,6 @@ setup_rt_networking()
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
 }
 
@@ -596,7 +560,7 @@ setup_rt_local_sids()
 	local lcnode_func_prefix
 	local lcblock_prefix
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -668,8 +632,8 @@ __setup_l3vpn()
 	local rtsrc_nsname
 	local rtdst_nsname
 
-	rtsrc_nsname="$(get_rtname "${src}")"
-	rtdst_nsname="$(get_rtname "${dst}")"
+	eval rtsrc_nsname=\${$(get_rtname "${src}")}
+	eval rtdst_nsname=\${$(get_rtname "${dst}")}
 
 	container="${LCBLOCK_ADDR}"
 
@@ -744,8 +708,8 @@ setup_hs()
 	local hsname
 	local rtname
 
-	hsname="$(get_hsname "${hs}")"
-	rtname="$(get_rtname "${rt}")"
+	eval hsname=\${$(get_hsname "${hs}")}
+	eval rtname=\${$(get_rtname "${rt}")}
 
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -791,11 +755,6 @@ setup_hs()
 	ip netns exec "${rtname}" \
 		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1
 
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec "${rtname}" \
-		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
-
 	ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
 }
 
@@ -880,7 +839,7 @@ check_rt_connectivity()
 	local prefix
 	local rtsrc_nsname
 
-	rtsrc_nsname="$(get_rtname "${rtsrc}")"
+	eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
 
 	prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
 
@@ -903,7 +862,7 @@ check_hs_ipv6_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -915,7 +874,7 @@ check_hs_ipv4_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
@@ -1025,7 +984,7 @@ rt_x_nextcsid_end_behavior_test()
 	local nsname
 	local ret
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	__nextcsid_end_behavior_test "${nsname}" "add" "${blen}" "${flen}"
 	ret="$?"
diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
index c79cb8ede17f..4b86040c58c6 100755
--- a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
@@ -287,10 +287,8 @@
 # packet using the SRv6 End.DT46 behavior (associated with the SID fcff:1::d46)
 # and sends it to the host hs-1.
 
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
 
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
 readonly DUMMY_DEVNAME="dum0"
 readonly VRF_TID=100
 readonly VRF_DEVNAME="vrf-${VRF_TID}"
@@ -418,32 +416,18 @@ test_command_or_ksft_skip()
 	fi
 }
 
-get_nodename()
-{
-	local name="$1"
-
-	echo "${name}-${RDMSUFF}"
-}
-
 get_rtname()
 {
 	local rtid="$1"
 
-	get_nodename "rt-${rtid}"
+	echo "rt_${rtid}"
 }
 
 get_hsname()
 {
 	local hsid="$1"
 
-	get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
-	local name="$1"
-
-	ip netns add "${name}"
+	echo "hs_${hsid}"
 }
 
 create_router()
@@ -452,15 +436,12 @@ create_router()
 	local nsname
 
 	nsname="$(get_rtname "${rtid}")"
+	setup_ns "${nsname}"
 
-	__create_namespace "${nsname}"
-
+	eval nsname=\${$(get_rtname "${rtid}")}
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
 }
 
@@ -470,29 +451,12 @@ create_host()
 	local nsname
 
 	nsname="$(get_hsname "${hsid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 cleanup()
 {
-	local nsname
-	local i
-
-	# destroy routers
-	for i in ${ROUTERS}; do
-		nsname="$(get_rtname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
-	# destroy hosts
-	for i in ${HOSTS}; do
-		nsname="$(get_hsname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
+	cleanup_all_ns
 	# check whether the setup phase was completed successfully or not. In
 	# case of an error during the setup phase of the testing environment,
 	# the selftest is considered as "skipped".
@@ -512,10 +476,10 @@ add_link_rt_pairs()
 	local nsname
 	local neigh_nsname
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
-		neigh_nsname="$(get_rtname "${neigh}")"
+		eval neigh_nsname=\${$(get_rtname "${neigh}")}
 
 		ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
 			type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -547,7 +511,7 @@ setup_rt_networking()
 	local devname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -631,7 +595,7 @@ set_end_x_nextcsid()
 	local rt="$1"
 	local adj="$2"
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 	net_prefix="$(get_network_prefix "${rt}" "${adj}")"
 	lcnode_func_prefix="$(build_lcnode_func_prefix "${rt}")"
 
@@ -650,7 +614,7 @@ set_underlay_sids_reachability()
 	local rt="$1"
 	local rt_neighs="$2"
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -685,7 +649,7 @@ setup_rt_local_sids()
 	local lcnode_func_prefix
 	local lcblock_prefix
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
         set_underlay_sids_reachability "${rt}" "${rt_neighs}"
 
@@ -728,8 +692,8 @@ __setup_l3vpn()
 	local rtsrc_nsname
 	local rtdst_nsname
 
-	rtsrc_nsname="$(get_rtname "${src}")"
-	rtdst_nsname="$(get_rtname "${dst}")"
+	eval rtsrc_nsname=\${$(get_rtname "${src}")}
+	eval rtdst_nsname=\${$(get_rtname "${dst}")}
 
 	container="${LCBLOCK_ADDR}"
 
@@ -804,8 +768,8 @@ setup_hs()
 	local hsname
 	local rtname
 
-	hsname="$(get_hsname "${hs}")"
-	rtname="$(get_rtname "${rt}")"
+	eval hsname=\${$(get_hsname "${hs}")}
+	eval rtname=\${$(get_rtname "${rt}")}
 
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -851,11 +815,6 @@ setup_hs()
 	ip netns exec "${rtname}" \
 		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1
 
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec "${rtname}" \
-		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
-
 	ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
 }
 
@@ -947,7 +906,7 @@ check_rt_connectivity()
 	local prefix
 	local rtsrc_nsname
 
-	rtsrc_nsname="$(get_rtname "${rtsrc}")"
+	eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
 
 	prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
 
@@ -970,7 +929,7 @@ check_hs_ipv6_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -982,7 +941,7 @@ check_hs_ipv4_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
@@ -1093,7 +1052,7 @@ rt_x_nextcsid_end_x_behavior_test()
 	local nsname
 	local ret
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	__nextcsid_end_x_behavior_test "${nsname}" "add" "${blen}" "${flen}"
 	ret="$?"
diff --git a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
index 28a775654b92..3efce1718c5f 100755
--- a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
@@ -166,10 +166,8 @@
 #  hs-4->hs-3 |IPv6 DA=fcff:1::e|SRH SIDs=fcff:3::d46|IPv6|...| (i.d)
 #
 
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
 
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
 readonly VRF_TID=100
 readonly VRF_DEVNAME="vrf-${VRF_TID}"
 readonly RT2HS_DEVNAME="veth-t${VRF_TID}"
@@ -248,32 +246,18 @@ test_command_or_ksft_skip()
 	fi
 }
 
-get_nodename()
-{
-	local name="$1"
-
-	echo "${name}-${RDMSUFF}"
-}
-
 get_rtname()
 {
 	local rtid="$1"
 
-	get_nodename "rt-${rtid}"
+	echo "rt_${rtid}"
 }
 
 get_hsname()
 {
 	local hsid="$1"
 
-	get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
-	local name="$1"
-
-	ip netns add "${name}"
+	echo "hs_${hsid}"
 }
 
 create_router()
@@ -282,8 +266,7 @@ create_router()
 	local nsname
 
 	nsname="$(get_rtname "${rtid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 create_host()
@@ -292,29 +275,12 @@ create_host()
 	local nsname
 
 	nsname="$(get_hsname "${hsid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 cleanup()
 {
-	local nsname
-	local i
-
-	# destroy routers
-	for i in ${ROUTERS}; do
-		nsname="$(get_rtname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
-	# destroy hosts
-	for i in ${HOSTS}; do
-		nsname="$(get_hsname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
+	cleanup_all_ns
 	# check whether the setup phase was completed successfully or not. In
 	# case of an error during the setup phase of the testing environment,
 	# the selftest is considered as "skipped".
@@ -334,10 +300,10 @@ add_link_rt_pairs()
 	local nsname
 	local neigh_nsname
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
-		neigh_nsname="$(get_rtname "${neigh}")"
+		eval neigh_nsname=\${$(get_rtname "${neigh}")}
 
 		ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
 			type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -369,7 +335,7 @@ setup_rt_networking()
 	local devname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -387,9 +353,6 @@ setup_rt_networking()
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
 }
 
@@ -403,7 +366,7 @@ setup_rt_local_sids()
 	local nsname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -469,7 +432,7 @@ __setup_rt_policy()
 	local policy=''
 	local n
 
-	nsname="$(get_rtname "${encap_rt}")"
+	eval nsname=\${$(get_rtname "${encap_rt}")}
 
 	for n in ${end_rts}; do
 		policy="${policy}${VPN_LOCATOR_SERVICE}:${n}::${END_FUNC},"
@@ -516,8 +479,8 @@ setup_hs()
 	local hsname
 	local rtname
 
-	hsname="$(get_hsname "${hs}")"
-	rtname="$(get_rtname "${rt}")"
+	eval hsname=\${$(get_hsname "${hs}")}
+	eval rtname=\${$(get_rtname "${rt}")}
 
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -555,11 +518,6 @@ setup_hs()
 	ip netns exec "${rtname}" \
 		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1
 
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec "${rtname}" \
-		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
-
 	ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
 }
 
@@ -656,7 +614,7 @@ check_rt_connectivity()
 	local prefix
 	local rtsrc_nsname
 
-	rtsrc_nsname="$(get_rtname "${rtsrc}")"
+	eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
 
 	prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
 
@@ -679,7 +637,7 @@ check_hs_ipv6_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -691,7 +649,7 @@ check_hs_ipv4_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
diff --git a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
index cb4177d41b21..cabc70538ffe 100755
--- a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
@@ -116,10 +116,8 @@
 #  hs-2->hs-1 |IPv6 DA=fcff:4::e|SRH SIDs=fcff:3::e,fcff:1::d2|eth|...| (i.b)
 #
 
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
 
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
 readonly DUMMY_DEVNAME="dum0"
 readonly RT2HS_DEVNAME="veth-hs"
 readonly HS_VETH_NAME="veth0"
@@ -199,32 +197,18 @@ test_command_or_ksft_skip()
 	fi
 }
 
-get_nodename()
-{
-	local name="$1"
-
-	echo "${name}-${RDMSUFF}"
-}
-
 get_rtname()
 {
 	local rtid="$1"
 
-	get_nodename "rt-${rtid}"
+	echo "rt_${rtid}"
 }
 
 get_hsname()
 {
 	local hsid="$1"
 
-	get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
-	local name="$1"
-
-	ip netns add "${name}"
+	echo "hs_${hsid}"
 }
 
 create_router()
@@ -233,8 +217,7 @@ create_router()
 	local nsname
 
 	nsname="$(get_rtname "${rtid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 create_host()
@@ -243,28 +226,12 @@ create_host()
 	local nsname
 
 	nsname="$(get_hsname "${hsid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 cleanup()
 {
-	local nsname
-	local i
-
-	# destroy routers
-	for i in ${ROUTERS}; do
-		nsname="$(get_rtname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
-	# destroy hosts
-	for i in ${HOSTS}; do
-		nsname="$(get_hsname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
+	cleanup_all_ns
 
 	# check whether the setup phase was completed successfully or not. In
 	# case of an error during the setup phase of the testing environment,
@@ -285,10 +252,10 @@ add_link_rt_pairs()
 	local nsname
 	local neigh_nsname
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
-		neigh_nsname="$(get_rtname "${neigh}")"
+		eval neigh_nsname=\${$(get_rtname "${neigh}")}
 
 		ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
 			type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -320,7 +287,7 @@ setup_rt_networking()
 	local devname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -341,9 +308,6 @@ setup_rt_networking()
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
 }
 
@@ -357,7 +321,7 @@ setup_rt_local_sids()
 	local nsname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -407,7 +371,7 @@ __setup_rt_policy()
 	local policy=''
 	local n
 
-	nsname="$(get_rtname "${encap_rt}")"
+	eval nsname=\${$(get_rtname "${encap_rt}")}
 
 	for n in ${end_rts}; do
 		policy="${policy}${VPN_LOCATOR_SERVICE}:${n}::${END_FUNC},"
@@ -446,7 +410,7 @@ setup_decap()
 	local rt="$1"
 	local nsname
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	# Local End.DX2 behavior
 	ip -netns "${nsname}" -6 route \
@@ -463,8 +427,8 @@ setup_hs()
 	local hsname
 	local rtname
 
-	hsname="$(get_hsname "${hs}")"
-	rtname="$(get_rtname "${rt}")"
+	eval hsname=\${$(get_hsname "${hs}")}
+	eval rtname=\${$(get_rtname "${rt}")}
 
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -486,11 +450,6 @@ setup_hs()
 		add "${IPv4_HS_NETWORK}.254/24" dev "${RT2HS_DEVNAME}"
 
 	ip -netns "${rtname}" link set "${RT2HS_DEVNAME}" up
-
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec "${rtname}" \
-		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
 }
 
 # set an auto-generated mac address
@@ -508,7 +467,7 @@ set_mac_address()
 	local ifname="$4"
 	local nsname
 
-	nsname=$(get_nodename "${nodename}")
+	eval nsname=\${${nodename}}
 
 	ip -netns "${nsname}" link set dev "${ifname}" down
 
@@ -532,7 +491,7 @@ set_host_l2peer()
 	local hssrc_name
 	local ipaddr
 
-	hssrc_name="$(get_hsname "${hssrc}")"
+	eval hssrc_name=\${$(get_hsname "${hssrc}")}
 
 	if [ "${proto}" -eq 6 ]; then
 		ipaddr="${ipprefix}::${hsdst}"
@@ -562,7 +521,7 @@ setup_l2vpn()
 	local rtdst="${hsdst}"
 
 	# set fixed mac for source node and the neigh MAC address
-	set_mac_address "hs-${hssrc}" "${hssrc}" "${hssrc}" "${HS_VETH_NAME}"
+	set_mac_address "hs_${hssrc}" "${hssrc}" "${hssrc}" "${HS_VETH_NAME}"
 	set_host_l2peer "${hssrc}" "${hsdst}" "${IPv6_HS_NETWORK}" 6
 	set_host_l2peer "${hssrc}" "${hsdst}" "${IPv4_HS_NETWORK}" 4
 
@@ -570,7 +529,7 @@ setup_l2vpn()
 	# to the mac address of the remote peer (L2 VPN destination host).
 	# Otherwise, traffic coming from the source host is dropped at the
 	# ingress router.
-	set_mac_address "rt-${rtsrc}" "${hsdst}" 254 "${RT2HS_DEVNAME}"
+	set_mac_address "rt_${rtsrc}" "${hsdst}" 254 "${RT2HS_DEVNAME}"
 
 	# set the SRv6 Policies at the ingress router
 	setup_rt_policy_ipv6 "${hsdst}" "${rtsrc}" "${end_rts}" "${rtdst}" \
@@ -647,7 +606,7 @@ check_rt_connectivity()
 	local prefix
 	local rtsrc_nsname
 
-	rtsrc_nsname="$(get_rtname "${rtsrc}")"
+	eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
 
 	prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
 
@@ -670,7 +629,7 @@ check_hs_ipv6_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -682,7 +641,7 @@ check_hs_ipv4_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
diff --git a/tools/testing/selftests/pcie_bwctrl/Makefile b/tools/testing/selftests/pcie_bwctrl/Makefile
index 48ec048f47af..277f92f9d753 100644
--- a/tools/testing/selftests/pcie_bwctrl/Makefile
+++ b/tools/testing/selftests/pcie_bwctrl/Makefile
@@ -1,2 +1,3 @@
-TEST_PROGS = set_pcie_cooling_state.sh set_pcie_speed.sh
+TEST_PROGS = set_pcie_cooling_state.sh
+TEST_FILES = set_pcie_speed.sh
 include ../lib.mk
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json b/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
index 1ba96c467754..d9fc62ab476c 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
@@ -412,5 +412,27 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY ingress"
         ]
+    },
+    {
+        "id": "33f4",
+        "name": "Check echo of big filter command",
+        "category": [
+            "infra",
+            "u32"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DUMMY parent root handle 10: fq_codel"
+        ],
+        "cmdUnderTest": "bash -c '$TC -echo filter add dev $DUMMY parent 10: u32 match u32 0 0 $(for i in $(seq 32); do echo action pedit munge ip dport set 22; done) | grep \"added filter\"'",
+        "verifyCmd": "",
+        "expExitCode": "0",
+        "matchCount": "0",
+        "matchPattern": "",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY parent root fq_codel"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index d4ea9cd845a3..ddc97ecd8b39 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -313,5 +313,292 @@
             "$TC qdisc del dev $DUMMY handle 1: root",
             "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
         ]
+    },
+    {
+        "id": "a4c3",
+        "name": "Test HFSC with netem/blackhole - queue emptying during peek operation",
+        "category": [
+            "qdisc",
+            "hfsc",
+            "netem",
+            "blackhole"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+            "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr",
+            "$TC class add dev $DUMMY parent 1:0 classid 1:2 drr",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 plug limit 1024",
+            "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 hfsc default 1",
+            "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+            "$TC qdisc add dev $DUMMY parent 3:1 handle 4:0 netem delay 1ms",
+            "$TC qdisc add dev $DUMMY parent 4:1 handle 5:0 blackhole",
+            "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true",
+            "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+            "$TC class del dev $DUMMY parent 3:0 classid 3:1",
+            "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+            "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true"
+        ],
+        "cmdUnderTest": "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "qdisc hfsc 3:.*parent 1:2.*default 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1:0 root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
+    },
+    {
+        "id": "90ec",
+        "name": "Test DRR's enqueue reentrant behaviour with netem",
+        "category": [
+            "qdisc",
+            "drr"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+            "$TC class replace dev $DUMMY parent 1:0 classid 1:1 drr",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+            "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+        ],
+        "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+        "matchJSON": [
+            {
+                "kind": "drr",
+                "handle": "1:",
+                "bytes": 196,
+                "packets": 2
+            }
+        ],
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1:0 root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
+    },
+    {
+        "id": "1f1f",
+        "name": "Test ETS's enqueue reentrant behaviour with netem",
+        "category": [
+            "qdisc",
+            "ets"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1:0 root ets bands 2",
+            "$TC class replace dev $DUMMY parent 1:0 classid 1:1 ets quantum 1500",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+            "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+        ],
+        "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j -s class show dev $DUMMY",
+        "matchJSON": [
+            {
+                "class": "ets",
+                "handle": "1:1",
+                "stats": {
+                    "bytes": 196,
+                    "packets": 2
+                }
+            }
+        ],
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1:0 root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
+    },
+    {
+        "id": "5e6d",
+        "name": "Test QFQ's enqueue reentrant behaviour with netem",
+        "category": [
+            "qdisc",
+            "qfq"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1:0 root qfq",
+            "$TC class replace dev $DUMMY parent 1:0 classid 1:1 qfq weight 100 maxpkt 1500",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+            "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+        ],
+        "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+        "matchJSON": [
+            {
+                "kind": "qfq",
+                "handle": "1:",
+                "bytes": 196,
+                "packets": 2
+            }
+        ],
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1:0 root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
+    },
+    {
+        "id": "bf1d",
+        "name": "Test HFSC's enqueue reentrant behaviour with netem",
+        "category": [
+            "qdisc",
+            "hfsc"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1:0 root hfsc",
+            "$TC class add dev $DUMMY parent 1:0 classid 1:1 hfsc ls m2 10Mbit",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+            "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip dst 10.10.10.1/32 flowid 1:1",
+            "$TC class add dev $DUMMY parent 1:0 classid 1:2 hfsc ls m2 10Mbit",
+            "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 netem duplicate 100%",
+            "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 2 u32 match ip dst 10.10.10.2/32 flowid 1:2",
+            "ping -c 1 10.10.10.1 -I$DUMMY > /dev/null || true",
+            "$TC filter del dev $DUMMY parent 1:0 protocol ip prio 1",
+            "$TC class del dev $DUMMY classid 1:1"
+        ],
+        "cmdUnderTest": "ping -c 1 10.10.10.2 -I$DUMMY > /dev/null || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+        "matchJSON": [
+            {
+                "kind": "hfsc",
+                "handle": "1:",
+                "bytes": 392,
+                "packets": 4
+            }
+        ],
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1:0 root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
+    },
+    {
+        "id": "7c3b",
+        "name": "Test nested DRR's enqueue reentrant behaviour with netem",
+        "category": [
+            "qdisc",
+            "drr"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+            "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr",
+            "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1",
+            "$TC qdisc add dev $DUMMY handle 2:0 parent 1:1 drr",
+            "$TC class add dev $DUMMY classid 2:1 parent 2:0 drr",
+            "$TC filter add dev $DUMMY parent 2:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 2:1",
+            "$TC qdisc add dev $DUMMY parent 2:1 handle 3:0 netem duplicate 100%"
+        ],
+        "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+        "matchJSON": [
+            {
+                "kind": "drr",
+                "handle": "1:",
+                "bytes": 196,
+                "packets": 2
+            }
+        ],
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1:0 root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
+    },
+    {
+        "id": "62c4",
+        "name": "Test HTB with FQ_CODEL - basic functionality",
+        "category": [
+            "qdisc",
+            "htb",
+            "fq_codel"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin",
+                "scapyPlugin"
+            ]
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 root handle 1: htb default 11",
+            "$TC class add dev $DEV1 parent 1: classid 1:1 htb rate 10kbit",
+            "$TC class add dev $DEV1 parent 1:1 classid 1:11 htb rate 10kbit prio 0 quantum 1486",
+            "$TC qdisc add dev $DEV1 parent 1:11 fq_codel quantum 300 noecn",
+            "sleep 0.5"
+        ],
+        "scapy": {
+            "iface": "$DEV0",
+            "count": 5,
+            "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/TCP(sport=12345, dport=80)"
+        },
+        "cmdUnderTest": "$TC -s qdisc show dev $DEV1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DEV1 | grep -A 5 'qdisc fq_codel'",
+        "matchPattern": "Sent [0-9]+ bytes [0-9]+ pkt",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 handle 1: root"
+        ]
+    },
+    {
+        "id": "831d",
+        "name": "Test HFSC qlen accounting with DRR/NETEM/BLACKHOLE chain",
+        "category": ["qdisc", "hfsc", "drr", "netem", "blackhole"],
+        "plugins": { "requires": ["nsPlugin", "scapyPlugin"] },
+        "setup": [
+            "$IP link set dev $DEV1 up || true",
+            "$TC qdisc add dev $DEV1 root handle 1: drr",
+            "$TC filter add dev $DEV1 parent 1: basic classid 1:1",
+            "$TC class add dev $DEV1 parent 1: classid 1:1 drr",
+            "$TC qdisc add dev $DEV1 parent 1:1 handle 2: hfsc def 1",
+            "$TC class add dev $DEV1 parent 2: classid 2:1 hfsc rt m1 8 d 1 m2 0",
+            "$TC qdisc add dev $DEV1 parent 2:1 handle 3: netem",
+            "$TC qdisc add dev $DEV1 parent 3:1 handle 4: blackhole"
+        ],
+        "scapy": {
+            "iface": "$DEV0",
+            "count": 5,
+            "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()"
+        },
+        "cmdUnderTest": "$TC -s qdisc show dev $DEV1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DEV1",
+        "matchPattern": "qdisc hfsc",
+        "matchCount": "1",
+        "teardown": ["$TC qdisc del dev $DEV1 root handle 1: drr"]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
index e9469ee71e6f..6d515d0e5ed6 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
@@ -189,5 +189,29 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY handle 1: root"
         ]
+    },
+    {
+        "id": "deb1",
+        "name": "CODEL test qdisc limit trimming",
+        "category": ["qdisc", "codel"],
+        "plugins": {
+            "requires": ["nsPlugin", "scapyPlugin"]
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 handle 1: root codel limit 10"
+        ],
+        "scapy": [
+            {
+                "iface": "$DEV0",
+                "count": 10,
+                "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+            }
+        ],
+        "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root codel limit 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DEV1",
+        "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 1p target 5ms interval 100ms",
+        "matchCount": "1",
+        "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
index 3a537b2ec4c9..24faf4e12dfa 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
@@ -377,5 +377,27 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY handle 1: root"
         ]
+    },
+    {
+        "id": "9479",
+        "name": "FQ test qdisc limit trimming",
+        "category": ["qdisc", "fq"],
+        "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+        "setup": [
+            "$TC qdisc add dev $DEV1 handle 1: root fq limit 10"
+        ],
+        "scapy": [
+            {
+                "iface": "$DEV0",
+                "count": 10,
+                "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+            }
+        ],
+        "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq limit 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DEV1",
+        "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 1p",
+        "matchCount": "1",
+        "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
index 9774b1e8801b..4ce62b857fd7 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
@@ -294,5 +294,27 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY handle 1: root"
         ]
+    },
+    {
+        "id": "0436",
+        "name": "FQ_CODEL test qdisc limit trimming",
+        "category": ["qdisc", "fq_codel"],
+        "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+        "setup": [
+            "$TC qdisc add dev $DEV1 handle 1: root fq_codel limit 10"
+        ],
+        "scapy": [
+            {
+                "iface": "$DEV0",
+                "count": 10,
+                "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+            }
+        ],
+        "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq_codel limit 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DEV1",
+        "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 1p flows 1024 quantum.*target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64",
+        "matchCount": "1",
+        "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
index d012d88d67fe..229fe1bf4a90 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
@@ -18,5 +18,27 @@
         "matchCount": "1",
         "teardown": [
         ]
+    },
+    {
+        "id": "83bf",
+        "name": "FQ_PIE test qdisc limit trimming",
+        "category": ["qdisc", "fq_pie"],
+        "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+        "setup": [
+            "$TC qdisc add dev $DEV1 handle 1: root fq_pie limit 10"
+        ],
+        "scapy": [
+            {
+                "iface": "$DEV0",
+                "count": 10,
+                "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+            }
+        ],
+        "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq_pie limit 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DEV1",
+        "matchPattern": "qdisc fq_pie 1: root refcnt [0-9]+ limit 1p",
+        "matchCount": "1",
+        "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
index dbef5474b26b..0ca19fac54a5 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
@@ -188,5 +188,27 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY handle 1: root"
         ]
+    },
+    {
+        "id": "385f",
+        "name": "HHF test qdisc limit trimming",
+        "category": ["qdisc", "hhf"],
+        "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+        "setup": [
+            "$TC qdisc add dev $DEV1 handle 1: root hhf limit 10"
+        ],
+        "scapy": [
+            {
+                "iface": "$DEV0",
+                "count": 10,
+                "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+            }
+        ],
+        "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root hhf limit 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DEV1",
+        "matchPattern": "qdisc hhf 1: root refcnt [0-9]+ limit 1p.*hh_limit 2048 reset_timeout 40ms admit_bytes 128Kb evict_timeout 1s non_hh_weight 2",
+        "matchCount": "1",
+        "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json
new file mode 100644
index 000000000000..1a98b66e8030
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json
@@ -0,0 +1,24 @@
+[
+    {
+        "id": "6158",
+        "name": "PIE test qdisc limit trimming",
+        "category": ["qdisc", "pie"],
+        "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+        "setup": [
+            "$TC qdisc add dev $DEV1 handle 1: root pie limit 10"
+        ],
+        "scapy": [
+            {
+                "iface": "$DEV0",
+                "count": 10,
+                "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+            }
+        ],
+        "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root pie limit 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DEV1",
+        "matchPattern": "qdisc pie 1: root refcnt [0-9]+ limit 1p",
+        "matchCount": "1",
+        "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
+    }
+]
diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile
index c7781efea0f3..f34ac0bac696 100644
--- a/tools/testing/selftests/ublk/Makefile
+++ b/tools/testing/selftests/ublk/Makefile
@@ -6,6 +6,10 @@ LDLIBS += -lpthread -lm -luring
 TEST_PROGS := test_generic_01.sh
 TEST_PROGS += test_generic_02.sh
 TEST_PROGS += test_generic_03.sh
+TEST_PROGS += test_generic_04.sh
+TEST_PROGS += test_generic_05.sh
+TEST_PROGS += test_generic_06.sh
+TEST_PROGS += test_generic_07.sh
 
 TEST_PROGS += test_null_01.sh
 TEST_PROGS += test_null_02.sh
@@ -21,12 +25,16 @@ TEST_PROGS += test_stripe_04.sh
 
 TEST_PROGS += test_stress_01.sh
 TEST_PROGS += test_stress_02.sh
+TEST_PROGS += test_stress_03.sh
+TEST_PROGS += test_stress_04.sh
+TEST_PROGS += test_stress_05.sh
 
 TEST_GEN_PROGS_EXTENDED = kublk
 
 include ../lib.mk
 
-$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c
+$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c \
+	fault_inject.c
 
 check:
 	shellcheck -x -f gcc *.sh
diff --git a/tools/testing/selftests/ublk/fault_inject.c b/tools/testing/selftests/ublk/fault_inject.c
new file mode 100644
index 000000000000..94a8e729ba4c
--- /dev/null
+++ b/tools/testing/selftests/ublk/fault_inject.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Fault injection ublk target. Hack this up however you like for
+ * testing specific behaviors of ublk_drv. Currently is a null target
+ * with a configurable delay before completing each I/O. This delay can
+ * be used to test ublk_drv's handling of I/O outstanding to the ublk
+ * server when it dies.
+ */
+
+#include "kublk.h"
+
+static int ublk_fault_inject_tgt_init(const struct dev_ctx *ctx,
+				      struct ublk_dev *dev)
+{
+	const struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
+	unsigned long dev_size = 250UL << 30;
+
+	dev->tgt.dev_size = dev_size;
+	dev->tgt.params = (struct ublk_params) {
+		.types = UBLK_PARAM_TYPE_BASIC,
+		.basic = {
+			.logical_bs_shift	= 9,
+			.physical_bs_shift	= 12,
+			.io_opt_shift		= 12,
+			.io_min_shift		= 9,
+			.max_sectors		= info->max_io_buf_bytes >> 9,
+			.dev_sectors		= dev_size >> 9,
+		},
+	};
+
+	dev->private_data = (void *)(unsigned long)(ctx->fault_inject.delay_us * 1000);
+	return 0;
+}
+
+static int ublk_fault_inject_queue_io(struct ublk_queue *q, int tag)
+{
+	const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+	struct io_uring_sqe *sqe;
+	struct __kernel_timespec ts = {
+		.tv_nsec = (long long)q->dev->private_data,
+	};
+
+	ublk_queue_alloc_sqes(q, &sqe, 1);
+	io_uring_prep_timeout(sqe, &ts, 1, 0);
+	sqe->user_data = build_user_data(tag, ublksrv_get_op(iod), 0, 1);
+
+	ublk_queued_tgt_io(q, tag, 1);
+
+	return 0;
+}
+
+static void ublk_fault_inject_tgt_io_done(struct ublk_queue *q, int tag,
+					  const struct io_uring_cqe *cqe)
+{
+	const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+
+	if (cqe->res != -ETIME)
+		ublk_err("%s: unexpected cqe res %d\n", __func__, cqe->res);
+
+	if (ublk_completed_tgt_io(q, tag))
+		ublk_complete_io(q, tag, iod->nr_sectors << 9);
+	else
+		ublk_err("%s: io not complete after 1 cqe\n", __func__);
+}
+
+static void ublk_fault_inject_cmd_line(struct dev_ctx *ctx, int argc, char *argv[])
+{
+	static const struct option longopts[] = {
+		{ "delay_us", 	1,	NULL,  0  },
+		{ 0, 0, 0, 0 }
+	};
+	int option_idx, opt;
+
+	ctx->fault_inject.delay_us = 0;
+	while ((opt = getopt_long(argc, argv, "",
+				  longopts, &option_idx)) != -1) {
+		switch (opt) {
+		case 0:
+			if (!strcmp(longopts[option_idx].name, "delay_us"))
+				ctx->fault_inject.delay_us = strtoll(optarg, NULL, 10);
+		}
+	}
+}
+
+static void ublk_fault_inject_usage(const struct ublk_tgt_ops *ops)
+{
+	printf("\tfault_inject: [--delay_us us (default 0)]\n");
+}
+
+const struct ublk_tgt_ops fault_inject_tgt_ops = {
+	.name = "fault_inject",
+	.init_tgt = ublk_fault_inject_tgt_init,
+	.queue_io = ublk_fault_inject_queue_io,
+	.tgt_io_done = ublk_fault_inject_tgt_io_done,
+	.parse_cmd_line = ublk_fault_inject_cmd_line,
+	.usage = ublk_fault_inject_usage,
+};
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index 91c282bc7674..842b40736a9b 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -5,22 +5,24 @@
 
 #include "kublk.h"
 
+#define MAX_NR_TGT_ARG 	64
+
 unsigned int ublk_dbg_mask = UBLK_LOG;
 static const struct ublk_tgt_ops *tgt_ops_list[] = {
 	&null_tgt_ops,
 	&loop_tgt_ops,
 	&stripe_tgt_ops,
+	&fault_inject_tgt_ops,
 };
 
 static const struct ublk_tgt_ops *ublk_find_tgt(const char *name)
 {
-	const struct ublk_tgt_ops *ops;
 	int i;
 
 	if (name == NULL)
 		return NULL;
 
-	for (i = 0; sizeof(tgt_ops_list) / sizeof(ops); i++)
+	for (i = 0; i < ARRAY_SIZE(tgt_ops_list); i++)
 		if (strcmp(tgt_ops_list[i]->name, name) == 0)
 			return tgt_ops_list[i];
 	return NULL;
@@ -118,6 +120,27 @@ static int ublk_ctrl_start_dev(struct ublk_dev *dev,
 	return __ublk_ctrl_cmd(dev, &data);
 }
 
+static int ublk_ctrl_start_user_recovery(struct ublk_dev *dev)
+{
+	struct ublk_ctrl_cmd_data data = {
+		.cmd_op	= UBLK_U_CMD_START_USER_RECOVERY,
+	};
+
+	return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_end_user_recovery(struct ublk_dev *dev, int daemon_pid)
+{
+	struct ublk_ctrl_cmd_data data = {
+		.cmd_op	= UBLK_U_CMD_END_USER_RECOVERY,
+		.flags	= CTRL_CMD_HAS_DATA,
+	};
+
+	dev->dev_info.ublksrv_pid = data.data[0] = daemon_pid;
+
+	return __ublk_ctrl_cmd(dev, &data);
+}
+
 static int ublk_ctrl_add_dev(struct ublk_dev *dev)
 {
 	struct ublk_ctrl_cmd_data data = {
@@ -207,10 +230,73 @@ static const char *ublk_dev_state_desc(struct ublk_dev *dev)
 	};
 }
 
+static void ublk_print_cpu_set(const cpu_set_t *set, char *buf, unsigned len)
+{
+	unsigned done = 0;
+	int i;
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (CPU_ISSET(i, set))
+			done += snprintf(&buf[done], len - done, "%d ", i);
+	}
+}
+
+static void ublk_adjust_affinity(cpu_set_t *set)
+{
+	int j, updated = 0;
+
+	/*
+	 * Just keep the 1st CPU now.
+	 *
+	 * In future, auto affinity selection can be tried.
+	 */
+	for (j = 0; j < CPU_SETSIZE; j++) {
+		if (CPU_ISSET(j, set)) {
+			if (!updated) {
+				updated = 1;
+				continue;
+			}
+			CPU_CLR(j, set);
+		}
+	}
+}
+
+/* Caller must free the allocated buffer */
+static int ublk_ctrl_get_affinity(struct ublk_dev *ctrl_dev, cpu_set_t **ptr_buf)
+{
+	struct ublk_ctrl_cmd_data data = {
+		.cmd_op	= UBLK_U_CMD_GET_QUEUE_AFFINITY,
+		.flags	= CTRL_CMD_HAS_DATA | CTRL_CMD_HAS_BUF,
+	};
+	cpu_set_t *buf;
+	int i, ret;
+
+	buf = malloc(sizeof(cpu_set_t) * ctrl_dev->dev_info.nr_hw_queues);
+	if (!buf)
+		return -ENOMEM;
+
+	for (i = 0; i < ctrl_dev->dev_info.nr_hw_queues; i++) {
+		data.data[0] = i;
+		data.len = sizeof(cpu_set_t);
+		data.addr = (__u64)&buf[i];
+
+		ret = __ublk_ctrl_cmd(ctrl_dev, &data);
+		if (ret < 0) {
+			free(buf);
+			return ret;
+		}
+		ublk_adjust_affinity(&buf[i]);
+	}
+
+	*ptr_buf = buf;
+	return 0;
+}
+
 static void ublk_ctrl_dump(struct ublk_dev *dev)
 {
 	struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
 	struct ublk_params p;
+	cpu_set_t *affinity;
 	int ret;
 
 	ret = ublk_ctrl_get_params(dev, &p);
@@ -219,12 +305,31 @@ static void ublk_ctrl_dump(struct ublk_dev *dev)
 		return;
 	}
 
+	ret = ublk_ctrl_get_affinity(dev, &affinity);
+	if (ret < 0) {
+		ublk_err("failed to get affinity %m\n");
+		return;
+	}
+
 	ublk_log("dev id %d: nr_hw_queues %d queue_depth %d block size %d dev_capacity %lld\n",
 			info->dev_id, info->nr_hw_queues, info->queue_depth,
 			1 << p.basic.logical_bs_shift, p.basic.dev_sectors);
 	ublk_log("\tmax rq size %d daemon pid %d flags 0x%llx state %s\n",
 			info->max_io_buf_bytes, info->ublksrv_pid, info->flags,
 			ublk_dev_state_desc(dev));
+
+	if (affinity) {
+		char buf[512];
+		int i;
+
+		for (i = 0; i < info->nr_hw_queues; i++) {
+			ublk_print_cpu_set(&affinity[i], buf, sizeof(buf));
+			printf("\tqueue %u: tid %d affinity(%s)\n",
+					i, dev->q[i].tid, buf);
+		}
+		free(affinity);
+	}
+
 	fflush(stdout);
 }
 
@@ -347,7 +452,9 @@ static int ublk_queue_init(struct ublk_queue *q)
 	}
 
 	ret = ublk_setup_ring(&q->ring, ring_depth, cq_depth,
-			IORING_SETUP_COOP_TASKRUN);
+			IORING_SETUP_COOP_TASKRUN |
+			IORING_SETUP_SINGLE_ISSUER |
+			IORING_SETUP_DEFER_TASKRUN);
 	if (ret < 0) {
 		ublk_err("ublk dev %d queue %d setup io_uring failed %d\n",
 				q->dev->dev_info.dev_id, q->q_id, ret);
@@ -429,12 +536,17 @@ int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
 	if (!(io->flags & UBLKSRV_IO_FREE))
 		return 0;
 
-	/* we issue because we need either fetching or committing */
+	/*
+	 * we issue because we need either fetching or committing or
+	 * getting data
+	 */
 	if (!(io->flags &
-		(UBLKSRV_NEED_FETCH_RQ | UBLKSRV_NEED_COMMIT_RQ_COMP)))
+		(UBLKSRV_NEED_FETCH_RQ | UBLKSRV_NEED_COMMIT_RQ_COMP | UBLKSRV_NEED_GET_DATA)))
 		return 0;
 
-	if (io->flags & UBLKSRV_NEED_COMMIT_RQ_COMP)
+	if (io->flags & UBLKSRV_NEED_GET_DATA)
+		cmd_op = UBLK_U_IO_NEED_GET_DATA;
+	else if (io->flags & UBLKSRV_NEED_COMMIT_RQ_COMP)
 		cmd_op = UBLK_U_IO_COMMIT_AND_FETCH_REQ;
 	else if (io->flags & UBLKSRV_NEED_FETCH_RQ)
 		cmd_op = UBLK_U_IO_FETCH_REQ;
@@ -551,6 +663,9 @@ static void ublk_handle_cqe(struct io_uring *r,
 		assert(tag < q->q_depth);
 		if (q->tgt_ops->queue_io)
 			q->tgt_ops->queue_io(q, tag);
+	} else if (cqe->res == UBLK_IO_RES_NEED_GET_DATA) {
+		io->flags |= UBLKSRV_NEED_GET_DATA | UBLKSRV_IO_FREE;
+		ublk_queue_io_cmd(q, io, tag);
 	} else {
 		/*
 		 * COMMIT_REQ will be completed immediately since no fetching
@@ -602,9 +717,24 @@ static int ublk_process_io(struct ublk_queue *q)
 	return reapped;
 }
 
+static void ublk_queue_set_sched_affinity(const struct ublk_queue *q,
+		cpu_set_t *cpuset)
+{
+        if (sched_setaffinity(0, sizeof(*cpuset), cpuset) < 0)
+                ublk_err("ublk dev %u queue %u set affinity failed",
+                                q->dev->dev_info.dev_id, q->q_id);
+}
+
+struct ublk_queue_info {
+	struct ublk_queue 	*q;
+	sem_t 			*queue_sem;
+	cpu_set_t 		*affinity;
+};
+
 static void *ublk_io_handler_fn(void *data)
 {
-	struct ublk_queue *q = data;
+	struct ublk_queue_info *info = data;
+	struct ublk_queue *q = info->q;
 	int dev_id = q->dev->dev_info.dev_id;
 	int ret;
 
@@ -614,6 +744,10 @@ static void *ublk_io_handler_fn(void *data)
 				dev_id, q->q_id);
 		return NULL;
 	}
+	/* IO perf is sensitive with queue pthread affinity on NUMA machine*/
+	ublk_queue_set_sched_affinity(q, info->affinity);
+	sem_post(info->queue_sem);
+
 	ublk_dbg(UBLK_DBG_QUEUE, "tid %d: ublk dev %d queue %d started\n",
 			q->tid, dev_id, q->q_id);
 
@@ -639,7 +773,7 @@ static void ublk_set_parameters(struct ublk_dev *dev)
 				dev->dev_info.dev_id, ret);
 }
 
-static int ublk_send_dev_event(const struct dev_ctx *ctx, int dev_id)
+static int ublk_send_dev_event(const struct dev_ctx *ctx, struct ublk_dev *dev, int dev_id)
 {
 	uint64_t id;
 	int evtfd = ctx->_evtfd;
@@ -652,36 +786,68 @@ static int ublk_send_dev_event(const struct dev_ctx *ctx, int dev_id)
 	else
 		id = ERROR_EVTFD_DEVID;
 
+	if (dev && ctx->shadow_dev)
+		memcpy(&ctx->shadow_dev->q, &dev->q, sizeof(dev->q));
+
 	if (write(evtfd, &id, sizeof(id)) != sizeof(id))
 		return -EINVAL;
 
+	close(evtfd);
+	shmdt(ctx->shadow_dev);
+
 	return 0;
 }
 
 
 static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 {
-	int ret, i;
-	void *thread_ret;
 	const struct ublksrv_ctrl_dev_info *dinfo = &dev->dev_info;
+	struct ublk_queue_info *qinfo;
+	cpu_set_t *affinity_buf;
+	void *thread_ret;
+	sem_t queue_sem;
+	int ret, i;
 
 	ublk_dbg(UBLK_DBG_DEV, "%s enter\n", __func__);
 
+	qinfo = (struct ublk_queue_info *)calloc(sizeof(struct ublk_queue_info),
+			dinfo->nr_hw_queues);
+	if (!qinfo)
+		return -ENOMEM;
+
+	sem_init(&queue_sem, 0, 0);
 	ret = ublk_dev_prep(ctx, dev);
 	if (ret)
 		return ret;
 
+	ret = ublk_ctrl_get_affinity(dev, &affinity_buf);
+	if (ret)
+		return ret;
+
 	for (i = 0; i < dinfo->nr_hw_queues; i++) {
 		dev->q[i].dev = dev;
 		dev->q[i].q_id = i;
+
+		qinfo[i].q = &dev->q[i];
+		qinfo[i].queue_sem = &queue_sem;
+		qinfo[i].affinity = &affinity_buf[i];
 		pthread_create(&dev->q[i].thread, NULL,
 				ublk_io_handler_fn,
-				&dev->q[i]);
+				&qinfo[i]);
 	}
 
+	for (i = 0; i < dinfo->nr_hw_queues; i++)
+		sem_wait(&queue_sem);
+	free(qinfo);
+	free(affinity_buf);
+
 	/* everything is fine now, start us */
-	ublk_set_parameters(dev);
-	ret = ublk_ctrl_start_dev(dev, getpid());
+	if (ctx->recovery)
+		ret = ublk_ctrl_end_user_recovery(dev, getpid());
+	else {
+		ublk_set_parameters(dev);
+		ret = ublk_ctrl_start_dev(dev, getpid());
+	}
 	if (ret < 0) {
 		ublk_err("%s: ublk_ctrl_start_dev failed: %d\n", __func__, ret);
 		goto fail;
@@ -691,7 +857,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 	if (ctx->fg)
 		ublk_ctrl_dump(dev);
 	else
-		ublk_send_dev_event(ctx, dev->dev_info.dev_id);
+		ublk_send_dev_event(ctx, dev, dev->dev_info.dev_id);
 
 	/* wait until we are terminated */
 	for (i = 0; i < dinfo->nr_hw_queues; i++)
@@ -856,7 +1022,10 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
 		}
 	}
 
-	ret = ublk_ctrl_add_dev(dev);
+	if (ctx->recovery)
+		ret = ublk_ctrl_start_user_recovery(dev);
+	else
+		ret = ublk_ctrl_add_dev(dev);
 	if (ret < 0) {
 		ublk_err("%s: can't add dev id %d, type %s ret %d\n",
 				__func__, dev_id, tgt_type, ret);
@@ -870,7 +1039,7 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
 
 fail:
 	if (ret < 0)
-		ublk_send_dev_event(ctx, -1);
+		ublk_send_dev_event(ctx, dev, -1);
 	ublk_ctrl_deinit(dev);
 	return ret;
 }
@@ -884,30 +1053,58 @@ static int cmd_dev_add(struct dev_ctx *ctx)
 	if (ctx->fg)
 		goto run;
 
+	ctx->_shmid = shmget(IPC_PRIVATE, sizeof(struct ublk_dev), IPC_CREAT | 0666);
+	if (ctx->_shmid < 0) {
+		ublk_err("%s: failed to shmget %s\n", __func__, strerror(errno));
+		exit(-1);
+	}
+	ctx->shadow_dev = (struct ublk_dev *)shmat(ctx->_shmid, NULL, 0);
+	if (ctx->shadow_dev == (struct ublk_dev *)-1) {
+		ublk_err("%s: failed to shmat %s\n", __func__, strerror(errno));
+		exit(-1);
+	}
 	ctx->_evtfd = eventfd(0, 0);
 	if (ctx->_evtfd < 0) {
 		ublk_err("%s: failed to create eventfd %s\n", __func__, strerror(errno));
 		exit(-1);
 	}
 
-	setsid();
 	res = fork();
 	if (res == 0) {
+		int res2;
+
+		setsid();
+		res2 = fork();
+		if (res2 == 0) {
+			/* prepare for detaching */
+			close(STDIN_FILENO);
+			close(STDOUT_FILENO);
+			close(STDERR_FILENO);
 run:
-		res = __cmd_dev_add(ctx);
-		return res;
+			res = __cmd_dev_add(ctx);
+			return res;
+		} else {
+			/* detached from the foreground task */
+			exit(EXIT_SUCCESS);
+		}
 	} else if (res > 0) {
 		uint64_t id;
+		int exit_code = EXIT_FAILURE;
 
 		res = read(ctx->_evtfd, &id, sizeof(id));
 		close(ctx->_evtfd);
 		if (res == sizeof(id) && id != ERROR_EVTFD_DEVID) {
 			ctx->dev_id = id - 1;
-			return __cmd_dev_list(ctx);
+			if (__cmd_dev_list(ctx) >= 0)
+				exit_code = EXIT_SUCCESS;
 		}
-		exit(EXIT_FAILURE);
+		shmdt(ctx->shadow_dev);
+		shmctl(ctx->_shmid, IPC_RMID, NULL);
+		/* wait for child and detach from it */
+		wait(NULL);
+		exit(exit_code);
 	} else {
-		return res;
+		exit(EXIT_FAILURE);
 	}
 }
 
@@ -969,6 +1166,9 @@ static int __cmd_dev_list(struct dev_ctx *ctx)
 			ublk_err("%s: can't get dev info from %d: %d\n",
 					__func__, ctx->dev_id, ret);
 	} else {
+		if (ctx->shadow_dev)
+			memcpy(&dev->q, ctx->shadow_dev->q, sizeof(dev->q));
+
 		ublk_ctrl_dump(dev);
 	}
 
@@ -1039,14 +1239,47 @@ static int cmd_dev_get_features(void)
 	return ret;
 }
 
+static void __cmd_create_help(char *exe, bool recovery)
+{
+	int i;
+
+	printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n",
+			exe, recovery ? "recover" : "add");
+	printf("\t[--foreground] [--quiet] [-z] [--debug_mask mask] [-r 0|1 ] [-g]\n");
+	printf("\t[-e 0|1 ] [-i 0|1]\n");
+	printf("\t[target options] [backfile1] [backfile2] ...\n");
+	printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
+
+	for (i = 0; i < sizeof(tgt_ops_list) / sizeof(tgt_ops_list[0]); i++) {
+		const struct ublk_tgt_ops *ops = tgt_ops_list[i];
+
+		if (ops->usage)
+			ops->usage(ops);
+	}
+}
+
+static void cmd_add_help(char *exe)
+{
+	__cmd_create_help(exe, false);
+	printf("\n");
+}
+
+static void cmd_recover_help(char *exe)
+{
+	__cmd_create_help(exe, true);
+	printf("\tPlease provide exact command line for creating this device with real dev_id\n");
+	printf("\n");
+}
+
 static int cmd_dev_help(char *exe)
 {
-	printf("%s add -t [null|loop] [-q nr_queues] [-d depth] [-n dev_id] [backfile1] [backfile2] ...\n", exe);
-	printf("\t default: nr_queues=2(max 4), depth=128(max 128), dev_id=-1(auto allocation)\n");
+	cmd_add_help(exe);
+	cmd_recover_help(exe);
+
 	printf("%s del [-n dev_id] -a \n", exe);
-	printf("\t -a delete all devices -n delete specified device\n");
+	printf("\t -a delete all devices -n delete specified device\n\n");
 	printf("%s list [-n dev_id] -a \n", exe);
-	printf("\t -a list all devices, -n list specified device, default -a \n");
+	printf("\t -a list all devices, -n list specified device, default -a \n\n");
 	printf("%s features\n", exe);
 	return 0;
 }
@@ -1063,9 +1296,13 @@ int main(int argc, char *argv[])
 		{ "quiet",		0,	NULL,  0  },
 		{ "zero_copy",          0,      NULL, 'z' },
 		{ "foreground",		0,	NULL,  0  },
-		{ "chunk_size", 	1,	NULL,  0  },
+		{ "recovery", 		1,      NULL, 'r' },
+		{ "recovery_fail_io",	1,	NULL, 'e'},
+		{ "recovery_reissue",	1,	NULL, 'i'},
+		{ "get_data",		1,	NULL, 'g'},
 		{ 0, 0, 0, 0 }
 	};
+	const struct ublk_tgt_ops *ops = NULL;
 	int option_idx, opt;
 	const char *cmd = argv[1];
 	struct dev_ctx ctx = {
@@ -1073,15 +1310,18 @@ int main(int argc, char *argv[])
 		.nr_hw_queues	=	2,
 		.dev_id		=	-1,
 		.tgt_type	=	"unknown",
-		.chunk_size 	= 	65536, 	/* def chunk size is 64K */
 	};
 	int ret = -EINVAL, i;
+	int tgt_argc = 1;
+	char *tgt_argv[MAX_NR_TGT_ARG] = { NULL };
+	int value;
 
 	if (argc == 1)
 		return ret;
 
+	opterr = 0;
 	optind = 2;
-	while ((opt = getopt_long(argc, argv, "t:n:d:q:az",
+	while ((opt = getopt_long(argc, argv, "t:n:d:q:r:e:i:gaz",
 				  longopts, &option_idx)) != -1) {
 		switch (opt) {
 		case 'a':
@@ -1103,6 +1343,24 @@ int main(int argc, char *argv[])
 		case 'z':
 			ctx.flags |= UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_USER_COPY;
 			break;
+		case 'r':
+			value = strtol(optarg, NULL, 10);
+			if (value)
+				ctx.flags |= UBLK_F_USER_RECOVERY;
+			break;
+		case 'e':
+			value = strtol(optarg, NULL, 10);
+			if (value)
+				ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_FAIL_IO;
+			break;
+		case 'i':
+			value = strtol(optarg, NULL, 10);
+			if (value)
+				ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_REISSUE;
+			break;
+		case 'g':
+			ctx.flags |= UBLK_F_NEED_GET_DATA;
+			break;
 		case 0:
 			if (!strcmp(longopts[option_idx].name, "debug_mask"))
 				ublk_dbg_mask = strtol(optarg, NULL, 16);
@@ -1110,8 +1368,26 @@ int main(int argc, char *argv[])
 				ublk_dbg_mask = 0;
 			if (!strcmp(longopts[option_idx].name, "foreground"))
 				ctx.fg = 1;
-			if (!strcmp(longopts[option_idx].name, "chunk_size"))
-				ctx.chunk_size = strtol(optarg, NULL, 10);
+			break;
+		case '?':
+			/*
+			 * target requires every option must have argument
+			 */
+			if (argv[optind][0] == '-' || argv[optind - 1][0] != '-') {
+				fprintf(stderr, "every target option requires argument: %s %s\n",
+						argv[optind - 1], argv[optind]);
+				exit(EXIT_FAILURE);
+			}
+
+			if (tgt_argc < (MAX_NR_TGT_ARG - 1) / 2) {
+				tgt_argv[tgt_argc++] = argv[optind - 1];
+				tgt_argv[tgt_argc++] = argv[optind];
+			} else {
+				fprintf(stderr, "too many target options\n");
+				exit(EXIT_FAILURE);
+			}
+			optind += 1;
+			break;
 		}
 	}
 
@@ -1120,9 +1396,25 @@ int main(int argc, char *argv[])
 		ctx.files[ctx.nr_files++] = argv[i++];
 	}
 
+	ops = ublk_find_tgt(ctx.tgt_type);
+	if (ops && ops->parse_cmd_line) {
+		optind = 0;
+
+		tgt_argv[0] = ctx.tgt_type;
+		ops->parse_cmd_line(&ctx, tgt_argc, tgt_argv);
+	}
+
 	if (!strcmp(cmd, "add"))
 		ret = cmd_dev_add(&ctx);
-	else if (!strcmp(cmd, "del"))
+	else if (!strcmp(cmd, "recover")) {
+		if (ctx.dev_id < 0) {
+			fprintf(stderr, "device id isn't provided for recovering\n");
+			ret = -EINVAL;
+		} else {
+			ctx.recovery = 1;
+			ret = cmd_dev_add(&ctx);
+		}
+	} else if (!strcmp(cmd, "del"))
 		ret = cmd_dev_del(&ctx);
 	else if (!strcmp(cmd, "list")) {
 		ctx.all = 1;
diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h
index 760ff8ffb810..44ee1e4ac55b 100644
--- a/tools/testing/selftests/ublk/kublk.h
+++ b/tools/testing/selftests/ublk/kublk.h
@@ -20,9 +20,15 @@
 #include <sys/wait.h>
 #include <sys/eventfd.h>
 #include <sys/uio.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include <linux/io_uring.h>
 #include <liburing.h>
-#include <linux/ublk_cmd.h>
+#include <semaphore.h>
+
+/* allow ublk_dep.h to override ublk_cmd.h */
 #include "ublk_dep.h"
+#include <linux/ublk_cmd.h>
 
 #define __maybe_unused __attribute__((unused))
 #define MAX_BACK_FILES   4
@@ -30,6 +36,8 @@
 #define min(a, b) ((a) < (b) ? (a) : (b))
 #endif
 
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0]))
+
 /****************** part 1: libublk ********************/
 
 #define CTRL_DEV		"/dev/ublk-control"
@@ -42,8 +50,8 @@
 #define UBLKSRV_IO_IDLE_SECS		20
 
 #define UBLK_IO_MAX_BYTES               (1 << 20)
-#define UBLK_MAX_QUEUES                 4
-#define UBLK_QUEUE_DEPTH                128
+#define UBLK_MAX_QUEUES                 32
+#define UBLK_QUEUE_DEPTH                1024
 
 #define UBLK_DBG_DEV            (1U << 0)
 #define UBLK_DBG_QUEUE          (1U << 1)
@@ -55,6 +63,16 @@
 struct ublk_dev;
 struct ublk_queue;
 
+struct stripe_ctx {
+	/* stripe */
+	unsigned int    chunk_size;
+};
+
+struct fault_inject_ctx {
+	/* fault_inject */
+	unsigned long   delay_us;
+};
+
 struct dev_ctx {
 	char tgt_type[16];
 	unsigned long flags;
@@ -66,11 +84,18 @@ struct dev_ctx {
 	unsigned int	logging:1;
 	unsigned int	all:1;
 	unsigned int	fg:1;
-
-	/* stripe */
-	unsigned int    chunk_size;
+	unsigned int	recovery:1;
 
 	int _evtfd;
+	int _shmid;
+
+	/* built from shmem, only for ublk_dump_dev() */
+	struct ublk_dev *shadow_dev;
+
+	union {
+		struct stripe_ctx 	stripe;
+		struct fault_inject_ctx fault_inject;
+	};
 };
 
 struct ublk_ctrl_cmd_data {
@@ -90,6 +115,7 @@ struct ublk_io {
 #define UBLKSRV_NEED_FETCH_RQ		(1UL << 0)
 #define UBLKSRV_NEED_COMMIT_RQ_COMP	(1UL << 1)
 #define UBLKSRV_IO_FREE			(1UL << 2)
+#define UBLKSRV_NEED_GET_DATA           (1UL << 3)
 	unsigned short flags;
 	unsigned short refs;		/* used by target code only */
 
@@ -107,6 +133,14 @@ struct ublk_tgt_ops {
 	int (*queue_io)(struct ublk_queue *, int tag);
 	void (*tgt_io_done)(struct ublk_queue *,
 			int tag, const struct io_uring_cqe *);
+
+	/*
+	 * Target specific command line handling
+	 *
+	 * each option requires argument for target command line
+	 */
+	void (*parse_cmd_line)(struct dev_ctx *ctx, int argc, char *argv[]);
+	void (*usage)(const struct ublk_tgt_ops *ops);
 };
 
 struct ublk_tgt {
@@ -357,6 +391,7 @@ static inline int ublk_queue_use_zc(const struct ublk_queue *q)
 extern const struct ublk_tgt_ops null_tgt_ops;
 extern const struct ublk_tgt_ops loop_tgt_ops;
 extern const struct ublk_tgt_ops stripe_tgt_ops;
+extern const struct ublk_tgt_ops fault_inject_tgt_ops;
 
 void backing_file_tgt_deinit(struct ublk_dev *dev);
 int backing_file_tgt_init(struct ublk_dev *dev);
diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c
index 179731c3dd6f..5dbd6392d83d 100644
--- a/tools/testing/selftests/ublk/stripe.c
+++ b/tools/testing/selftests/ublk/stripe.c
@@ -281,7 +281,7 @@ static int ublk_stripe_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
 			.max_sectors = dev->dev_info.max_io_buf_bytes >> 9,
 		},
 	};
-	unsigned chunk_size = ctx->chunk_size;
+	unsigned chunk_size = ctx->stripe.chunk_size;
 	struct stripe_conf *conf;
 	unsigned chunk_shift;
 	loff_t bytes = 0;
@@ -344,10 +344,36 @@ static void ublk_stripe_tgt_deinit(struct ublk_dev *dev)
 	backing_file_tgt_deinit(dev);
 }
 
+static void ublk_stripe_cmd_line(struct dev_ctx *ctx, int argc, char *argv[])
+{
+	static const struct option longopts[] = {
+		{ "chunk_size", 	1,	NULL,  0  },
+		{ 0, 0, 0, 0 }
+	};
+	int option_idx, opt;
+
+	ctx->stripe.chunk_size = 65536;
+	while ((opt = getopt_long(argc, argv, "",
+				  longopts, &option_idx)) != -1) {
+		switch (opt) {
+		case 0:
+			if (!strcmp(longopts[option_idx].name, "chunk_size"))
+				ctx->stripe.chunk_size = strtol(optarg, NULL, 10);
+		}
+	}
+}
+
+static void ublk_stripe_usage(const struct ublk_tgt_ops *ops)
+{
+	printf("\tstripe: [--chunk_size chunk_size (default 65536)]\n");
+}
+
 const struct ublk_tgt_ops stripe_tgt_ops = {
 	.name = "stripe",
 	.init_tgt = ublk_stripe_tgt_init,
 	.deinit_tgt = ublk_stripe_tgt_deinit,
 	.queue_io = ublk_stripe_queue_io,
 	.tgt_io_done = ublk_stripe_io_done,
+	.parse_cmd_line = ublk_stripe_cmd_line,
+	.usage = ublk_stripe_usage,
 };
diff --git a/tools/testing/selftests/ublk/test_common.sh b/tools/testing/selftests/ublk/test_common.sh
index a88b35943227..a81210ca3e99 100755
--- a/tools/testing/selftests/ublk/test_common.sh
+++ b/tools/testing/selftests/ublk/test_common.sh
@@ -17,8 +17,8 @@ _get_disk_dev_t() {
 	local minor
 
 	dev=/dev/ublkb"${dev_id}"
-	major=$(stat -c '%Hr' "$dev")
-	minor=$(stat -c '%Lr' "$dev")
+	major="0x"$(stat -c '%t' "$dev")
+	minor="0x"$(stat -c '%T' "$dev")
 
 	echo $(( (major & 0xfff) << 20 | (minor & 0xfffff) ))
 }
@@ -30,18 +30,26 @@ _run_fio_verify_io() {
 }
 
 _create_backfile() {
-	local my_size=$1
-	local my_file
+	local index=$1
+	local new_size=$2
+	local old_file
+	local new_file
 
-	my_file=$(mktemp ublk_file_"${my_size}"_XXXXX)
-	truncate -s "${my_size}" "${my_file}"
-	echo "$my_file"
+	old_file="${UBLK_BACKFILES[$index]}"
+	[ -f "$old_file" ] && rm -f "$old_file"
+
+	new_file=$(mktemp ublk_file_"${new_size}"_XXXXX)
+	truncate -s "${new_size}" "${new_file}"
+	UBLK_BACKFILES["$index"]="$new_file"
 }
 
-_remove_backfile() {
-	local file=$1
+_remove_files() {
+	local file
 
-	[ -f "$file" ] && rm -f "$file"
+	for file in "${UBLK_BACKFILES[@]}"; do
+		[ -f "$file" ] && rm -f "$file"
+	done
+	[ -f "$UBLK_TMP" ] && rm -f "$UBLK_TMP"
 }
 
 _create_tmp_dir() {
@@ -106,6 +114,7 @@ _prep_test() {
 	local type=$1
 	shift 1
 	modprobe ublk_drv > /dev/null 2>&1
+	UBLK_TMP=$(mktemp ublk_test_XXXXX)
 	[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "ublk $type: $*"
 }
 
@@ -129,7 +138,10 @@ _show_result()
 			echo "$1 : [FAIL]"
 		fi
 	fi
-	[ "$2" -ne 0 ] && exit "$2"
+	if [ "$2" -ne 0 ]; then
+		_remove_files
+		exit "$2"
+	fi
 	return 0
 }
 
@@ -138,16 +150,16 @@ _check_add_dev()
 {
 	local tid=$1
 	local code=$2
-	shift 2
+
 	if [ "${code}" -ne 0 ]; then
-		_remove_test_files "$@"
 		_show_result "${tid}" "${code}"
 	fi
 }
 
 _cleanup_test() {
 	"${UBLK_PROG}" del -a
-	rm -f "$UBLK_TMP"
+
+	_remove_files
 }
 
 _have_feature()
@@ -158,9 +170,11 @@ _have_feature()
 	return 1
 }
 
-_add_ublk_dev() {
-	local kublk_temp;
+_create_ublk_dev() {
 	local dev_id;
+	local cmd=$1
+
+	shift 1
 
 	if [ ! -c /dev/ublk-control ]; then
 		return ${UBLK_SKIP_CODE}
@@ -171,17 +185,34 @@ _add_ublk_dev() {
 		fi
 	fi
 
-	kublk_temp=$(mktemp /tmp/kublk-XXXXXX)
-	if ! "${UBLK_PROG}" add "$@" > "${kublk_temp}" 2>&1; then
+	if ! dev_id=$("${UBLK_PROG}" "$cmd" "$@" | grep "dev id" | awk -F '[ :]' '{print $3}'); then
 		echo "fail to add ublk dev $*"
-		rm -f "${kublk_temp}"
 		return 255
 	fi
-
-	dev_id=$(grep "dev id" "${kublk_temp}" | awk -F '[ :]' '{print $3}')
 	udevadm settle
-	rm -f "${kublk_temp}"
-	echo "${dev_id}"
+
+	if [[ "$dev_id" =~ ^[0-9]+$ ]]; then
+		echo "${dev_id}"
+	else
+		return 255
+	fi
+}
+
+_add_ublk_dev() {
+	_create_ublk_dev "add" "$@"
+}
+
+_recover_ublk_dev() {
+	local dev_id
+	local state
+
+	dev_id=$(_create_ublk_dev "recover" "$@")
+	for ((j=0;j<20;j++)); do
+		state=$(_get_ublk_dev_state "${dev_id}")
+		[ "$state" == "LIVE" ] && break
+		sleep 1
+	done
+	echo "$state"
 }
 
 # kill the ublk daemon and return ublk device state
@@ -220,7 +251,7 @@ __run_io_and_remove()
 	local kill_server=$3
 
 	fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
-		--rw=readwrite --iodepth=64 --size="${size}" --numjobs=4 \
+		--rw=readwrite --iodepth=256 --size="${size}" --numjobs=4 \
 		--runtime=20 --time_based > /dev/null 2>&1 &
 	sleep 2
 	if [ "${kill_server}" = "yes" ]; then
@@ -238,15 +269,80 @@ __run_io_and_remove()
 	wait
 }
 
+run_io_and_remove()
+{
+	local size=$1
+	local dev_id
+	shift 1
+
+	dev_id=$(_add_ublk_dev "$@")
+	_check_add_dev "$TID" $?
+
+	[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
+	if ! __run_io_and_remove "$dev_id" "${size}" "no"; then
+		echo "/dev/ublkc$dev_id isn't removed"
+		exit 255
+	fi
+}
+
+run_io_and_kill_daemon()
+{
+	local size=$1
+	local dev_id
+	shift 1
+
+	dev_id=$(_add_ublk_dev "$@")
+	_check_add_dev "$TID" $?
+
+	[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs kill ublk server(ublk add $*)"
+	if ! __run_io_and_remove "$dev_id" "${size}" "yes"; then
+		echo "/dev/ublkc$dev_id isn't removed res ${res}"
+		exit 255
+	fi
+}
+
+run_io_and_recover()
+{
+	local state
+	local dev_id
+
+	dev_id=$(_add_ublk_dev "$@")
+	_check_add_dev "$TID" $?
+
+	fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
+		--rw=readwrite --iodepth=256 --size="${size}" --numjobs=4 \
+		--runtime=20 --time_based > /dev/null 2>&1 &
+	sleep 4
+
+	state=$(__ublk_kill_daemon "${dev_id}" "QUIESCED")
+	if [ "$state" != "QUIESCED" ]; then
+		echo "device isn't quiesced($state) after killing daemon"
+		return 255
+	fi
+
+	state=$(_recover_ublk_dev -n "$dev_id" "$@")
+	if [ "$state" != "LIVE" ]; then
+		echo "faile to recover to LIVE($state)"
+		return 255
+	fi
+
+	if ! __remove_ublk_dev_return "${dev_id}"; then
+		echo "delete dev ${dev_id} failed"
+		return 255
+	fi
+	wait
+}
+
+
 _ublk_test_top_dir()
 {
 	cd "$(dirname "$0")" && pwd
 }
 
-UBLK_TMP=$(mktemp ublk_test_XXXXX)
 UBLK_PROG=$(_ublk_test_top_dir)/kublk
 UBLK_TEST_QUIET=1
 UBLK_TEST_SHOW_RESULT=1
+UBLK_BACKFILES=()
 export UBLK_PROG
 export UBLK_TEST_QUIET
 export UBLK_TEST_SHOW_RESULT
diff --git a/tools/testing/selftests/ublk/test_generic_04.sh b/tools/testing/selftests/ublk/test_generic_04.sh
new file mode 100755
index 000000000000..8a3bc080c577
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_04.sh
@@ -0,0 +1,40 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_04"
+ERR_CODE=0
+
+ublk_run_recover_test()
+{
+	run_io_and_recover "$@"
+	ERR_CODE=$?
+	if [ ${ERR_CODE} -ne 0 ]; then
+		echo "$TID failure: $*"
+		_show_result $TID $ERR_CODE
+	fi
+}
+
+if ! _have_program fio; then
+	exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "recover" "basic recover function verification"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_run_recover_test -t null -q 2 -r 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+ublk_run_recover_test -t null -q 2 -r 1 -i 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 -i 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "recover"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_05.sh b/tools/testing/selftests/ublk/test_generic_05.sh
new file mode 100755
index 000000000000..3bb00a347402
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_05.sh
@@ -0,0 +1,44 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_05"
+ERR_CODE=0
+
+ublk_run_recover_test()
+{
+	run_io_and_recover "$@"
+	ERR_CODE=$?
+	if [ ${ERR_CODE} -ne 0 ]; then
+		echo "$TID failure: $*"
+		_show_result $TID $ERR_CODE
+	fi
+}
+
+if ! _have_program fio; then
+	exit "$UBLK_SKIP_CODE"
+fi
+
+if ! _have_feature "ZERO_COPY"; then
+	exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "recover" "basic recover function verification (zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_run_recover_test -t null -q 2 -r 1 -z &
+ublk_run_recover_test -t loop -q 2 -r 1 -z "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+ublk_run_recover_test -t null -q 2 -r 1 -z -i 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 -z -i 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -z -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "recover"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_06.sh b/tools/testing/selftests/ublk/test_generic_06.sh
new file mode 100755
index 000000000000..b67230c42c84
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_06.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_06"
+ERR_CODE=0
+
+_prep_test "fault_inject" "fast cleanup when all I/Os of one hctx are in server"
+
+# configure ublk server to sleep 2s before completing each I/O
+dev_id=$(_add_ublk_dev -t fault_inject -q 2 -d 1 --delay_us 2000000)
+_check_add_dev $TID $?
+
+STARTTIME=${SECONDS}
+
+dd if=/dev/urandom of=/dev/ublkb${dev_id} oflag=direct bs=4k count=1 status=none > /dev/null 2>&1 &
+dd_pid=$!
+
+__ublk_kill_daemon ${dev_id} "DEAD"
+
+wait $dd_pid
+dd_exitcode=$?
+
+ENDTIME=${SECONDS}
+ELAPSED=$(($ENDTIME - $STARTTIME))
+
+# assert that dd sees an error and exits quickly after ublk server is
+# killed. previously this relied on seeing an I/O timeout and so would
+# take ~30s
+if [ $dd_exitcode -eq 0 ]; then
+        echo "dd unexpectedly exited successfully!"
+        ERR_CODE=255
+fi
+if [ $ELAPSED -ge 5 ]; then
+        echo "dd took $ELAPSED seconds to exit (>= 5s tolerance)!"
+        ERR_CODE=255
+fi
+
+_cleanup_test "fault_inject"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_07.sh b/tools/testing/selftests/ublk/test_generic_07.sh
new file mode 100755
index 000000000000..cba86451fa5e
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_07.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_07"
+ERR_CODE=0
+
+if ! _have_program fio; then
+	exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "generic" "test UBLK_F_NEED_GET_DATA"
+
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop -q 2 -g "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
+
+# run fio over the ublk disk
+_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
+ERR_CODE=$?
+if [ "$ERR_CODE" -eq 0 ]; then
+	_mkfs_mount_test /dev/ublkb"${dev_id}"
+	ERR_CODE=$?
+fi
+
+_cleanup_test "generic"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_01.sh b/tools/testing/selftests/ublk/test_loop_01.sh
index 1ef8b6044777..833fa0dbc700 100755
--- a/tools/testing/selftests/ublk/test_loop_01.sh
+++ b/tools/testing/selftests/ublk/test_loop_01.sh
@@ -12,10 +12,10 @@ fi
 
 _prep_test "loop" "write and verify test"
 
-backfile_0=$(_create_backfile 256M)
+_create_backfile 0 256M
 
-dev_id=$(_add_ublk_dev -t loop "$backfile_0")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
 
 # run fio over the ublk disk
 _run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
@@ -23,6 +23,4 @@ ERR_CODE=$?
 
 _cleanup_test "loop"
 
-_remove_backfile "$backfile_0"
-
 _show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_02.sh b/tools/testing/selftests/ublk/test_loop_02.sh
index 03863d825e07..874568b3646b 100755
--- a/tools/testing/selftests/ublk/test_loop_02.sh
+++ b/tools/testing/selftests/ublk/test_loop_02.sh
@@ -8,15 +8,13 @@ ERR_CODE=0
 
 _prep_test "loop" "mkfs & mount & umount"
 
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
 
 _mkfs_mount_test /dev/ublkb"${dev_id}"
 ERR_CODE=$?
 
 _cleanup_test "loop"
 
-_remove_backfile "$backfile_0"
-
 _show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_03.sh b/tools/testing/selftests/ublk/test_loop_03.sh
index e9ca744de8b1..c30f797c6429 100755
--- a/tools/testing/selftests/ublk/test_loop_03.sh
+++ b/tools/testing/selftests/ublk/test_loop_03.sh
@@ -12,9 +12,9 @@ fi
 
 _prep_test "loop" "write and verify over zero copy"
 
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop -z "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop -z "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
 
 # run fio over the ublk disk
 _run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
@@ -22,6 +22,4 @@ ERR_CODE=$?
 
 _cleanup_test "loop"
 
-_remove_backfile "$backfile_0"
-
 _show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_04.sh b/tools/testing/selftests/ublk/test_loop_04.sh
index 1435422c38ec..b01d75b3214d 100755
--- a/tools/testing/selftests/ublk/test_loop_04.sh
+++ b/tools/testing/selftests/ublk/test_loop_04.sh
@@ -8,15 +8,14 @@ ERR_CODE=0
 
 _prep_test "loop" "mkfs & mount & umount with zero copy"
 
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop -z "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+
+dev_id=$(_add_ublk_dev -t loop -z "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
 
 _mkfs_mount_test /dev/ublkb"${dev_id}"
 ERR_CODE=$?
 
 _cleanup_test "loop"
 
-_remove_backfile "$backfile_0"
-
 _show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_05.sh b/tools/testing/selftests/ublk/test_loop_05.sh
index 2e6e2e6978fc..de2141533074 100755
--- a/tools/testing/selftests/ublk/test_loop_05.sh
+++ b/tools/testing/selftests/ublk/test_loop_05.sh
@@ -12,10 +12,10 @@ fi
 
 _prep_test "loop" "write and verify test"
 
-backfile_0=$(_create_backfile 256M)
+_create_backfile 0 256M
 
-dev_id=$(_add_ublk_dev -q 2 -t loop "$backfile_0")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -q 2 -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
 
 # run fio over the ublk disk
 _run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
@@ -23,6 +23,4 @@ ERR_CODE=$?
 
 _cleanup_test "loop"
 
-_remove_backfile "$backfile_0"
-
 _show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_01.sh b/tools/testing/selftests/ublk/test_stress_01.sh
index a8be24532b24..7d3150f057d4 100755
--- a/tools/testing/selftests/ublk/test_stress_01.sh
+++ b/tools/testing/selftests/ublk/test_stress_01.sh
@@ -4,44 +4,31 @@
 . "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
 TID="stress_01"
 ERR_CODE=0
-DEV_ID=-1
 
 ublk_io_and_remove()
 {
-	local size=$1
-	shift 1
-	local backfile=""
-	if echo "$@" | grep -q "loop"; then
-		backfile=${*: -1}
-	fi
-	DEV_ID=$(_add_ublk_dev "$@")
-	_check_add_dev $TID $? "${backfile}"
-
-	[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
-	if ! __run_io_and_remove "${DEV_ID}" "${size}" "no"; then
-		echo "/dev/ublkc${DEV_ID} isn't removed"
-		_remove_backfile "${backfile}"
-		exit 255
+	run_io_and_remove "$@"
+	ERR_CODE=$?
+	if [ ${ERR_CODE} -ne 0 ]; then
+		echo "$TID failure: $*"
+		_show_result $TID $ERR_CODE
 	fi
 }
 
+if ! _have_program fio; then
+	exit "$UBLK_SKIP_CODE"
+fi
+
 _prep_test "stress" "run IO and remove device"
 
-ublk_io_and_remove 8G -t null -q 4
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
-	_show_result $TID $ERR_CODE
-fi
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
 
-BACK_FILE=$(_create_backfile 256M)
-ublk_io_and_remove 256M -t loop -q 4 "${BACK_FILE}"
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
-	_show_result $TID $ERR_CODE
-fi
+ublk_io_and_remove 8G -t null -q 4 &
+ublk_io_and_remove 256M -t loop -q 4 "${UBLK_BACKFILES[0]}" &
+ublk_io_and_remove 256M -t stripe -q 4 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
 
-ublk_io_and_remove 256M -t loop -q 4 -z "${BACK_FILE}"
-ERR_CODE=$?
 _cleanup_test "stress"
-_remove_backfile "${BACK_FILE}"
 _show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_02.sh b/tools/testing/selftests/ublk/test_stress_02.sh
index 2159e4cc8140..1a9065125ae1 100755
--- a/tools/testing/selftests/ublk/test_stress_02.sh
+++ b/tools/testing/selftests/ublk/test_stress_02.sh
@@ -4,44 +4,31 @@
 . "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
 TID="stress_02"
 ERR_CODE=0
-DEV_ID=-1
+
+if ! _have_program fio; then
+	exit "$UBLK_SKIP_CODE"
+fi
 
 ublk_io_and_kill_daemon()
 {
-	local size=$1
-	shift 1
-	local backfile=""
-	if echo "$@" | grep -q "loop"; then
-		backfile=${*: -1}
-	fi
-	DEV_ID=$(_add_ublk_dev "$@")
-	_check_add_dev $TID $? "${backfile}"
-
-	[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs kill ublk server(ublk add $*)"
-	if ! __run_io_and_remove "${DEV_ID}" "${size}" "yes"; then
-		echo "/dev/ublkc${DEV_ID} isn't removed res ${res}"
-		_remove_backfile "${backfile}"
-		exit 255
+	run_io_and_kill_daemon "$@"
+	ERR_CODE=$?
+	if [ ${ERR_CODE} -ne 0 ]; then
+		echo "$TID failure: $*"
+		_show_result $TID $ERR_CODE
 	fi
 }
 
 _prep_test "stress" "run IO and kill ublk server"
 
-ublk_io_and_kill_daemon 8G -t null -q 4
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
-	_show_result $TID $ERR_CODE
-fi
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
 
-BACK_FILE=$(_create_backfile 256M)
-ublk_io_and_kill_daemon 256M -t loop -q 4 "${BACK_FILE}"
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
-	_show_result $TID $ERR_CODE
-fi
+ublk_io_and_kill_daemon 8G -t null -q 4 &
+ublk_io_and_kill_daemon 256M -t loop -q 4 "${UBLK_BACKFILES[0]}" &
+ublk_io_and_kill_daemon 256M -t stripe -q 4 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
 
-ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${BACK_FILE}"
-ERR_CODE=$?
 _cleanup_test "stress"
-_remove_backfile "${BACK_FILE}"
 _show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_03.sh b/tools/testing/selftests/ublk/test_stress_03.sh
new file mode 100755
index 000000000000..e0854f71d35b
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_03.sh
@@ -0,0 +1,38 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_03"
+ERR_CODE=0
+
+ublk_io_and_remove()
+{
+	run_io_and_remove "$@"
+	ERR_CODE=$?
+	if [ ${ERR_CODE} -ne 0 ]; then
+		echo "$TID failure: $*"
+		_show_result $TID $ERR_CODE
+	fi
+}
+
+if ! _have_program fio; then
+	exit "$UBLK_SKIP_CODE"
+fi
+
+if ! _have_feature "ZERO_COPY"; then
+	exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "stress" "run IO and remove device(zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_io_and_remove 8G -t null -q 4 -z &
+ublk_io_and_remove 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
+ublk_io_and_remove 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_04.sh b/tools/testing/selftests/ublk/test_stress_04.sh
new file mode 100755
index 000000000000..1798a98387e8
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_04.sh
@@ -0,0 +1,37 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_04"
+ERR_CODE=0
+
+ublk_io_and_kill_daemon()
+{
+	run_io_and_kill_daemon "$@"
+	ERR_CODE=$?
+	if [ ${ERR_CODE} -ne 0 ]; then
+		echo "$TID failure: $*"
+		_show_result $TID $ERR_CODE
+	fi
+}
+
+if ! _have_program fio; then
+	exit "$UBLK_SKIP_CODE"
+fi
+if ! _have_feature "ZERO_COPY"; then
+	exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "stress" "run IO and kill ublk server(zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_io_and_kill_daemon 8G -t null -q 4 -z &
+ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
+ublk_io_and_kill_daemon 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_05.sh b/tools/testing/selftests/ublk/test_stress_05.sh
new file mode 100755
index 000000000000..88601b48f1cd
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_05.sh
@@ -0,0 +1,64 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_05"
+ERR_CODE=0
+
+run_io_and_remove()
+{
+	local size=$1
+	local dev_id
+	local dev_pid
+	shift 1
+
+	dev_id=$(_add_ublk_dev "$@")
+	_check_add_dev $TID $?
+
+	[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
+
+	fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
+		--rw=readwrite --iodepth=128 --size="${size}" --numjobs=4 \
+		--runtime=40 --time_based > /dev/null 2>&1 &
+	sleep 4
+
+	dev_pid=$(_get_ublk_daemon_pid "$dev_id")
+	kill -9 "$dev_pid"
+
+	if ! __remove_ublk_dev_return "${dev_id}"; then
+		echo "delete dev ${dev_id} failed"
+		return 255
+	fi
+}
+
+ublk_io_and_remove()
+{
+	run_io_and_remove "$@"
+	ERR_CODE=$?
+	if [ ${ERR_CODE} -ne 0 ]; then
+		echo "$TID failure: $*"
+		_show_result $TID $ERR_CODE
+	fi
+}
+
+_prep_test "stress" "run IO and remove device with recovery enabled"
+
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+for reissue in $(seq 0 1); do
+	ublk_io_and_remove 8G -t null -q 4 -g -r 1 -i "$reissue" &
+	ublk_io_and_remove 256M -t loop -q 4 -g -r 1 -i "$reissue" "${UBLK_BACKFILES[0]}" &
+	wait
+done
+
+if _have_feature "ZERO_COPY"; then
+	for reissue in $(seq 0 1); do
+		ublk_io_and_remove 8G -t null -q 4 -g -z -r 1 -i "$reissue" &
+		ublk_io_and_remove 256M -t loop -q 4 -g -z -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" &
+		wait
+	done
+fi
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_01.sh b/tools/testing/selftests/ublk/test_stripe_01.sh
index 7e387ef656ea..4e4f0fdf3c9b 100755
--- a/tools/testing/selftests/ublk/test_stripe_01.sh
+++ b/tools/testing/selftests/ublk/test_stripe_01.sh
@@ -12,19 +12,15 @@ fi
 
 _prep_test "stripe" "write and verify test"
 
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
+_create_backfile 0 256M
+_create_backfile 1 256M
 
-dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
 
 # run fio over the ublk disk
 _run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=512M
 ERR_CODE=$?
 
 _cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
 _show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_02.sh b/tools/testing/selftests/ublk/test_stripe_02.sh
index e8a45fa82dde..5820ab2efba4 100755
--- a/tools/testing/selftests/ublk/test_stripe_02.sh
+++ b/tools/testing/selftests/ublk/test_stripe_02.sh
@@ -8,17 +8,14 @@ ERR_CODE=0
 
 _prep_test "stripe" "mkfs & mount & umount"
 
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "$backfile_0" "$backfile_1"
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+dev_id=$(_add_ublk_dev -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
 
 _mkfs_mount_test /dev/ublkb"${dev_id}"
 ERR_CODE=$?
 
 _cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
 _show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_03.sh b/tools/testing/selftests/ublk/test_stripe_03.sh
index c1b34af36145..20b977e27814 100755
--- a/tools/testing/selftests/ublk/test_stripe_03.sh
+++ b/tools/testing/selftests/ublk/test_stripe_03.sh
@@ -12,19 +12,15 @@ fi
 
 _prep_test "stripe" "write and verify test"
 
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
+_create_backfile 0 256M
+_create_backfile 1 256M
 
-dev_id=$(_add_ublk_dev -q 2 -t stripe "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -q 2 -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
 
 # run fio over the ublk disk
 _run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=512M
 ERR_CODE=$?
 
 _cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
 _show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_04.sh b/tools/testing/selftests/ublk/test_stripe_04.sh
index 1f2b642381d1..1b51ed2f1d84 100755
--- a/tools/testing/selftests/ublk/test_stripe_04.sh
+++ b/tools/testing/selftests/ublk/test_stripe_04.sh
@@ -8,17 +8,14 @@ ERR_CODE=0
 
 _prep_test "stripe" "mkfs & mount & umount on zero copy"
 
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t stripe -z -q 2 "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "$backfile_0" "$backfile_1"
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+dev_id=$(_add_ublk_dev -t stripe -z -q 2 "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
 
 _mkfs_mount_test /dev/ublkb"${dev_id}"
 ERR_CODE=$?
 
 _cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
 _show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/x86/bugs/Makefile b/tools/testing/selftests/x86/bugs/Makefile
new file mode 100644
index 000000000000..8ff2d7226c7f
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/Makefile
@@ -0,0 +1,3 @@
+TEST_PROGS := its_sysfs.py its_permutations.py its_indirect_alignment.py its_ret_alignment.py
+TEST_FILES := common.py
+include ../../lib.mk
diff --git a/tools/testing/selftests/x86/bugs/common.py b/tools/testing/selftests/x86/bugs/common.py
new file mode 100755
index 000000000000..2f9664a80617
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/common.py
@@ -0,0 +1,164 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# This contains kselftest framework adapted common functions for testing
+# mitigation for x86 bugs.
+
+import os, sys, re, shutil
+
+sys.path.insert(0, '../../kselftest')
+import ksft
+
+def read_file(path):
+    if not os.path.exists(path):
+        return None
+    with open(path, 'r') as file:
+        return file.read().strip()
+
+def cpuinfo_has(arg):
+    cpuinfo = read_file('/proc/cpuinfo')
+    if arg in cpuinfo:
+        return True
+    return False
+
+def cmdline_has(arg):
+    cmdline = read_file('/proc/cmdline')
+    if arg in cmdline:
+        return True
+    return False
+
+def cmdline_has_either(args):
+    cmdline = read_file('/proc/cmdline')
+    for arg in args:
+        if arg in cmdline:
+            return True
+    return False
+
+def cmdline_has_none(args):
+    return not cmdline_has_either(args)
+
+def cmdline_has_all(args):
+    cmdline = read_file('/proc/cmdline')
+    for arg in args:
+        if arg not in cmdline:
+            return False
+    return True
+
+def get_sysfs(bug):
+    return read_file("/sys/devices/system/cpu/vulnerabilities/" + bug)
+
+def sysfs_has(bug, mitigation):
+    status = get_sysfs(bug)
+    if mitigation in status:
+        return True
+    return False
+
+def sysfs_has_either(bugs, mitigations):
+    for bug in bugs:
+        for mitigation in mitigations:
+            if sysfs_has(bug, mitigation):
+                return True
+    return False
+
+def sysfs_has_none(bugs, mitigations):
+    return not sysfs_has_either(bugs, mitigations)
+
+def sysfs_has_all(bugs, mitigations):
+    for bug in bugs:
+        for mitigation in mitigations:
+            if not sysfs_has(bug, mitigation):
+                return False
+    return True
+
+def bug_check_pass(bug, found):
+    ksft.print_msg(f"\nFound: {found}")
+    # ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}")
+    ksft.test_result_pass(f'{bug}: {found}')
+
+def bug_check_fail(bug, found, expected):
+    ksft.print_msg(f'\nFound:\t {found}')
+    ksft.print_msg(f'Expected:\t {expected}')
+    ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}")
+    ksft.test_result_fail(f'{bug}: {found}')
+
+def bug_status_unknown(bug, found):
+    ksft.print_msg(f'\nUnknown status: {found}')
+    ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}")
+    ksft.test_result_fail(f'{bug}: {found}')
+
+def basic_checks_sufficient(bug, mitigation):
+    if not mitigation:
+        bug_status_unknown(bug, "None")
+        return True
+    elif mitigation == "Not affected":
+        ksft.test_result_pass(bug)
+        return True
+    elif mitigation == "Vulnerable":
+        if cmdline_has_either([f'{bug}=off', 'mitigations=off']):
+            bug_check_pass(bug, mitigation)
+            return True
+    return False
+
+def get_section_info(vmlinux, section_name):
+    from elftools.elf.elffile import ELFFile
+    with open(vmlinux, 'rb') as f:
+        elffile = ELFFile(f)
+        section = elffile.get_section_by_name(section_name)
+        if section is None:
+            ksft.print_msg("Available sections in vmlinux:")
+            for sec in elffile.iter_sections():
+                ksft.print_msg(sec.name)
+            raise ValueError(f"Section {section_name} not found in {vmlinux}")
+        return section['sh_addr'], section['sh_offset'], section['sh_size']
+
+def get_patch_sites(vmlinux, offset, size):
+    import struct
+    output = []
+    with open(vmlinux, 'rb') as f:
+        f.seek(offset)
+        i = 0
+        while i < size:
+            data = f.read(4)  # s32
+            if not data:
+                break
+            sym_offset = struct.unpack('<i', data)[0] + i
+            i += 4
+            output.append(sym_offset)
+    return output
+
+def get_instruction_from_vmlinux(elffile, section, virtual_address, target_address):
+    from capstone import Cs, CS_ARCH_X86, CS_MODE_64
+    section_start = section['sh_addr']
+    section_end = section_start + section['sh_size']
+
+    if not (section_start <= target_address < section_end):
+        return None
+
+    offset = target_address - section_start
+    code = section.data()[offset:offset + 16]
+
+    cap = init_capstone()
+    for instruction in cap.disasm(code, target_address):
+        if instruction.address == target_address:
+            return instruction
+    return None
+
+def init_capstone():
+    from capstone import Cs, CS_ARCH_X86, CS_MODE_64, CS_OPT_SYNTAX_ATT
+    cap = Cs(CS_ARCH_X86, CS_MODE_64)
+    cap.syntax = CS_OPT_SYNTAX_ATT
+    return cap
+
+def get_runtime_kernel():
+    import drgn
+    return drgn.program_from_kernel()
+
+def check_dependencies_or_skip(modules, script_name="unknown test"):
+    for mod in modules:
+        try:
+            __import__(mod)
+        except ImportError:
+            ksft.test_result_skip(f"Skipping {script_name}: missing module '{mod}'")
+            ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_indirect_alignment.py b/tools/testing/selftests/x86/bugs/its_indirect_alignment.py
new file mode 100755
index 000000000000..cdc33ae6a91c
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_indirect_alignment.py
@@ -0,0 +1,150 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for indirect target selection (ITS) mitigation.
+#
+# Test if indirect CALL/JMP are correctly patched by evaluating
+# the vmlinux .retpoline_sites in /proc/kcore.
+
+# Install dependencies
+# add-apt-repository ppa:michel-slm/kernel-utils
+# apt update
+# apt install -y python3-drgn python3-pyelftools python3-capstone
+#
+# Best to copy the vmlinux at a standard location:
+# mkdir -p /usr/lib/debug/lib/modules/$(uname -r)
+# cp $VMLINUX /usr/lib/debug/lib/modules/$(uname -r)/vmlinux
+#
+# Usage: ./its_indirect_alignment.py [vmlinux]
+
+import os, sys, argparse
+from pathlib import Path
+
+this_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, this_dir + '/../../kselftest')
+import ksft
+import common as c
+
+bug = "indirect_target_selection"
+
+mitigation = c.get_sysfs(bug)
+if not mitigation or "Aligned branch/return thunks" not in mitigation:
+    ksft.test_result_skip("Skipping its_indirect_alignment.py: Aligned branch/return thunks not enabled")
+    ksft.finished()
+
+if c.sysfs_has("spectre_v2", "Retpolines"):
+    ksft.test_result_skip("Skipping its_indirect_alignment.py: Retpolines deployed")
+    ksft.finished()
+
+c.check_dependencies_or_skip(['drgn', 'elftools', 'capstone'], script_name="its_indirect_alignment.py")
+
+from elftools.elf.elffile import ELFFile
+from drgn.helpers.common.memory import identify_address
+
+cap = c.init_capstone()
+
+if len(os.sys.argv) > 1:
+    arg_vmlinux = os.sys.argv[1]
+    if not os.path.exists(arg_vmlinux):
+        ksft.test_result_fail(f"its_indirect_alignment.py: vmlinux not found at argument path: {arg_vmlinux}")
+        ksft.exit_fail()
+    os.makedirs(f"/usr/lib/debug/lib/modules/{os.uname().release}", exist_ok=True)
+    os.system(f'cp {arg_vmlinux} /usr/lib/debug/lib/modules/$(uname -r)/vmlinux')
+
+vmlinux = f"/usr/lib/debug/lib/modules/{os.uname().release}/vmlinux"
+if not os.path.exists(vmlinux):
+    ksft.test_result_fail(f"its_indirect_alignment.py: vmlinux not found at {vmlinux}")
+    ksft.exit_fail()
+
+ksft.print_msg(f"Using vmlinux: {vmlinux}")
+
+retpolines_start_vmlinux, retpolines_sec_offset, size = c.get_section_info(vmlinux, '.retpoline_sites')
+ksft.print_msg(f"vmlinux: Section .retpoline_sites (0x{retpolines_start_vmlinux:x}) found at 0x{retpolines_sec_offset:x} with size 0x{size:x}")
+
+sites_offset = c.get_patch_sites(vmlinux, retpolines_sec_offset, size)
+total_retpoline_tests = len(sites_offset)
+ksft.print_msg(f"Found {total_retpoline_tests} retpoline sites")
+
+prog = c.get_runtime_kernel()
+retpolines_start_kcore = prog.symbol('__retpoline_sites').address
+ksft.print_msg(f'kcore: __retpoline_sites: 0x{retpolines_start_kcore:x}')
+
+x86_indirect_its_thunk_r15 = prog.symbol('__x86_indirect_its_thunk_r15').address
+ksft.print_msg(f'kcore: __x86_indirect_its_thunk_r15: 0x{x86_indirect_its_thunk_r15:x}')
+
+tests_passed = 0
+tests_failed = 0
+tests_unknown = 0
+
+with open(vmlinux, 'rb') as f:
+    elffile = ELFFile(f)
+    text_section = elffile.get_section_by_name('.text')
+
+    for i in range(0, len(sites_offset)):
+        site = retpolines_start_kcore + sites_offset[i]
+        vmlinux_site = retpolines_start_vmlinux + sites_offset[i]
+        passed = unknown = failed = False
+        try:
+            vmlinux_insn = c.get_instruction_from_vmlinux(elffile, text_section, text_section['sh_addr'], vmlinux_site)
+            kcore_insn = list(cap.disasm(prog.read(site, 16), site))[0]
+            operand = kcore_insn.op_str
+            insn_end = site + kcore_insn.size - 1 # TODO handle Jcc.32 __x86_indirect_thunk_\reg
+            safe_site = insn_end & 0x20
+            site_status = "" if safe_site else "(unsafe)"
+
+            ksft.print_msg(f"\nSite {i}: {identify_address(prog, site)} <0x{site:x}> {site_status}")
+            ksft.print_msg(f"\tvmlinux: 0x{vmlinux_insn.address:x}:\t{vmlinux_insn.mnemonic}\t{vmlinux_insn.op_str}")
+            ksft.print_msg(f"\tkcore:   0x{kcore_insn.address:x}:\t{kcore_insn.mnemonic}\t{kcore_insn.op_str}")
+
+            if (site & 0x20) ^ (insn_end & 0x20):
+                ksft.print_msg(f"\tSite at safe/unsafe boundary: {str(kcore_insn.bytes)} {kcore_insn.mnemonic} {operand}")
+            if safe_site:
+                tests_passed += 1
+                passed = True
+                ksft.print_msg(f"\tPASSED: At safe address")
+                continue
+
+            if operand.startswith('0xffffffff'):
+                thunk = int(operand, 16)
+                if thunk > x86_indirect_its_thunk_r15:
+                    insn_at_thunk = list(cap.disasm(prog.read(thunk, 16), thunk))[0]
+                    operand += ' -> ' + insn_at_thunk.mnemonic + ' ' + insn_at_thunk.op_str + ' <dynamic-thunk?>'
+                    if 'jmp' in insn_at_thunk.mnemonic and thunk & 0x20:
+                        ksft.print_msg(f"\tPASSED: Found {operand} at safe address")
+                        passed = True
+                if not passed:
+                    if kcore_insn.operands[0].type == capstone.CS_OP_IMM:
+                        operand += ' <' + prog.symbol(int(operand, 16)) + '>'
+                        if '__x86_indirect_its_thunk_' in operand:
+                            ksft.print_msg(f"\tPASSED: Found {operand}")
+                        else:
+                            ksft.print_msg(f"\tPASSED: Found direct branch: {kcore_insn}, ITS thunk not required.")
+                        passed = True
+                    else:
+                        unknown = True
+            if passed:
+                tests_passed += 1
+            elif unknown:
+                ksft.print_msg(f"UNKNOWN: unexpected operand: {kcore_insn}")
+                tests_unknown += 1
+            else:
+                ksft.print_msg(f'\t************* FAILED *************')
+                ksft.print_msg(f"\tFound {kcore_insn.bytes} {kcore_insn.mnemonic} {operand}")
+                ksft.print_msg(f'\t**********************************')
+                tests_failed += 1
+        except Exception as e:
+            ksft.print_msg(f"UNKNOWN: An unexpected error occurred: {e}")
+            tests_unknown += 1
+
+ksft.print_msg(f"\n\nSummary:")
+ksft.print_msg(f"PASS:    \t{tests_passed} \t/ {total_retpoline_tests}")
+ksft.print_msg(f"FAIL:    \t{tests_failed} \t/ {total_retpoline_tests}")
+ksft.print_msg(f"UNKNOWN: \t{tests_unknown} \t/ {total_retpoline_tests}")
+
+if tests_failed == 0:
+    ksft.test_result_pass("All ITS return thunk sites passed")
+else:
+    ksft.test_result_fail(f"{tests_failed} ITS return thunk sites failed")
+ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_permutations.py b/tools/testing/selftests/x86/bugs/its_permutations.py
new file mode 100755
index 000000000000..3204f4728c62
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_permutations.py
@@ -0,0 +1,109 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for indirect target selection (ITS) cmdline permutations with other bugs
+# like spectre_v2 and retbleed.
+
+import os, sys, subprocess, itertools, re, shutil
+
+test_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, test_dir + '/../../kselftest')
+import ksft
+import common as c
+
+bug = "indirect_target_selection"
+mitigation = c.get_sysfs(bug)
+
+if not mitigation or "Not affected" in mitigation:
+    ksft.test_result_skip("Skipping its_permutations.py: not applicable")
+    ksft.finished()
+
+if shutil.which('vng') is None:
+    ksft.test_result_skip("Skipping its_permutations.py: virtme-ng ('vng') not found in PATH.")
+    ksft.finished()
+
+TEST = f"{test_dir}/its_sysfs.py"
+default_kparam = ['clearcpuid=hypervisor', 'panic=5', 'panic_on_warn=1', 'oops=panic', 'nmi_watchdog=1', 'hung_task_panic=1']
+
+DEBUG = " -v "
+
+# Install dependencies
+# https://github.com/arighi/virtme-ng
+# apt install virtme-ng
+BOOT_CMD = f"vng --run {test_dir}/../../../../../arch/x86/boot/bzImage "
+#BOOT_CMD += DEBUG
+
+bug = "indirect_target_selection"
+
+input_options = {
+    'indirect_target_selection'     : ['off', 'on', 'stuff', 'vmexit'],
+    'retbleed'                      : ['off', 'stuff', 'auto'],
+    'spectre_v2'                    : ['off', 'on', 'eibrs', 'retpoline', 'ibrs', 'eibrs,retpoline'],
+}
+
+def pretty_print(output):
+    OKBLUE = '\033[94m'
+    OKGREEN = '\033[92m'
+    WARNING = '\033[93m'
+    FAIL = '\033[91m'
+    ENDC = '\033[0m'
+    BOLD = '\033[1m'
+
+    # Define patterns and their corresponding colors
+    patterns = {
+        r"^ok \d+": OKGREEN,
+        r"^not ok \d+": FAIL,
+        r"^# Testing .*": OKBLUE,
+        r"^# Found: .*": WARNING,
+        r"^# Totals: .*": BOLD,
+        r"pass:([1-9]\d*)": OKGREEN,
+        r"fail:([1-9]\d*)": FAIL,
+        r"skip:([1-9]\d*)": WARNING,
+    }
+
+    # Apply colors based on patterns
+    for pattern, color in patterns.items():
+        output = re.sub(pattern, lambda match: f"{color}{match.group(0)}{ENDC}", output, flags=re.MULTILINE)
+
+    print(output)
+
+combinations = list(itertools.product(*input_options.values()))
+ksft.print_header()
+ksft.set_plan(len(combinations))
+
+logs = ""
+
+for combination in combinations:
+    append = ""
+    log = ""
+    for p in default_kparam:
+        append += f' --append={p}'
+    command = BOOT_CMD + append
+    test_params = ""
+    for i, key in enumerate(input_options.keys()):
+        param = f'{key}={combination[i]}'
+        test_params += f' {param}'
+        command += f" --append={param}"
+    command += f" -- {TEST}"
+    test_name = f"{bug} {test_params}"
+    pretty_print(f'# Testing {test_name}')
+    t =  subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+    t.wait()
+    output, _ = t.communicate()
+    if t.returncode == 0:
+        ksft.test_result_pass(test_name)
+    else:
+        ksft.test_result_fail(test_name)
+    output = output.decode()
+    log += f" {output}"
+    pretty_print(log)
+    logs += output + "\n"
+
+# Optionally use tappy to parse the output
+# apt install python3-tappy
+with open("logs.txt", "w") as f:
+    f.write(logs)
+
+ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_ret_alignment.py b/tools/testing/selftests/x86/bugs/its_ret_alignment.py
new file mode 100755
index 000000000000..f40078d9f6ff
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_ret_alignment.py
@@ -0,0 +1,139 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for indirect target selection (ITS) mitigation.
+#
+# Tests if the RETs are correctly patched by evaluating the
+# vmlinux .return_sites in /proc/kcore.
+#
+# Install dependencies
+# add-apt-repository ppa:michel-slm/kernel-utils
+# apt update
+# apt install -y python3-drgn python3-pyelftools python3-capstone
+#
+# Run on target machine
+# mkdir -p /usr/lib/debug/lib/modules/$(uname -r)
+# cp $VMLINUX /usr/lib/debug/lib/modules/$(uname -r)/vmlinux
+#
+# Usage: ./its_ret_alignment.py
+
+import os, sys, argparse
+from pathlib import Path
+
+this_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, this_dir + '/../../kselftest')
+import ksft
+import common as c
+
+bug = "indirect_target_selection"
+mitigation = c.get_sysfs(bug)
+if not mitigation or "Aligned branch/return thunks" not in mitigation:
+    ksft.test_result_skip("Skipping its_ret_alignment.py: Aligned branch/return thunks not enabled")
+    ksft.finished()
+
+c.check_dependencies_or_skip(['drgn', 'elftools', 'capstone'], script_name="its_ret_alignment.py")
+
+from elftools.elf.elffile import ELFFile
+from drgn.helpers.common.memory import identify_address
+
+cap = c.init_capstone()
+
+if len(os.sys.argv) > 1:
+    arg_vmlinux = os.sys.argv[1]
+    if not os.path.exists(arg_vmlinux):
+        ksft.test_result_fail(f"its_ret_alignment.py: vmlinux not found at user-supplied path: {arg_vmlinux}")
+        ksft.exit_fail()
+    os.makedirs(f"/usr/lib/debug/lib/modules/{os.uname().release}", exist_ok=True)
+    os.system(f'cp {arg_vmlinux} /usr/lib/debug/lib/modules/$(uname -r)/vmlinux')
+
+vmlinux = f"/usr/lib/debug/lib/modules/{os.uname().release}/vmlinux"
+if not os.path.exists(vmlinux):
+    ksft.test_result_fail(f"its_ret_alignment.py: vmlinux not found at {vmlinux}")
+    ksft.exit_fail()
+
+ksft.print_msg(f"Using vmlinux: {vmlinux}")
+
+rethunks_start_vmlinux, rethunks_sec_offset, size = c.get_section_info(vmlinux, '.return_sites')
+ksft.print_msg(f"vmlinux: Section .return_sites (0x{rethunks_start_vmlinux:x}) found at 0x{rethunks_sec_offset:x} with size 0x{size:x}")
+
+sites_offset = c.get_patch_sites(vmlinux, rethunks_sec_offset, size)
+total_rethunk_tests = len(sites_offset)
+ksft.print_msg(f"Found {total_rethunk_tests} rethunk sites")
+
+prog = c.get_runtime_kernel()
+rethunks_start_kcore = prog.symbol('__return_sites').address
+ksft.print_msg(f'kcore: __rethunk_sites: 0x{rethunks_start_kcore:x}')
+
+its_return_thunk = prog.symbol('its_return_thunk').address
+ksft.print_msg(f'kcore: its_return_thunk: 0x{its_return_thunk:x}')
+
+tests_passed = 0
+tests_failed = 0
+tests_unknown = 0
+tests_skipped = 0
+
+with open(vmlinux, 'rb') as f:
+    elffile = ELFFile(f)
+    text_section = elffile.get_section_by_name('.text')
+
+    for i in range(len(sites_offset)):
+        site = rethunks_start_kcore + sites_offset[i]
+        vmlinux_site = rethunks_start_vmlinux + sites_offset[i]
+        try:
+            passed = unknown = failed = skipped = False
+
+            symbol = identify_address(prog, site)
+            vmlinux_insn = c.get_instruction_from_vmlinux(elffile, text_section, text_section['sh_addr'], vmlinux_site)
+            kcore_insn = list(cap.disasm(prog.read(site, 16), site))[0]
+
+            insn_end = site + kcore_insn.size - 1
+
+            safe_site = insn_end & 0x20
+            site_status = "" if safe_site else "(unsafe)"
+
+            ksft.print_msg(f"\nSite {i}: {symbol} <0x{site:x}> {site_status}")
+            ksft.print_msg(f"\tvmlinux: 0x{vmlinux_insn.address:x}:\t{vmlinux_insn.mnemonic}\t{vmlinux_insn.op_str}")
+            ksft.print_msg(f"\tkcore:   0x{kcore_insn.address:x}:\t{kcore_insn.mnemonic}\t{kcore_insn.op_str}")
+
+            if safe_site:
+                tests_passed += 1
+                passed = True
+                ksft.print_msg(f"\tPASSED: At safe address")
+                continue
+
+            if "jmp" in kcore_insn.mnemonic:
+                passed = True
+            elif "ret" not in kcore_insn.mnemonic:
+                skipped = True
+
+            if passed:
+                ksft.print_msg(f"\tPASSED: Found {kcore_insn.mnemonic} {kcore_insn.op_str}")
+                tests_passed += 1
+            elif skipped:
+                ksft.print_msg(f"\tSKIPPED: Found '{kcore_insn.mnemonic}'")
+                tests_skipped += 1
+            elif unknown:
+                ksft.print_msg(f"UNKNOWN: An unknown instruction: {kcore_insn}")
+                tests_unknown += 1
+            else:
+                ksft.print_msg(f'\t************* FAILED *************')
+                ksft.print_msg(f"\tFound {kcore_insn.mnemonic} {kcore_insn.op_str}")
+                ksft.print_msg(f'\t**********************************')
+                tests_failed += 1
+        except Exception as e:
+            ksft.print_msg(f"UNKNOWN: An unexpected error occurred: {e}")
+            tests_unknown += 1
+
+ksft.print_msg(f"\n\nSummary:")
+ksft.print_msg(f"PASSED: \t{tests_passed} \t/ {total_rethunk_tests}")
+ksft.print_msg(f"FAILED: \t{tests_failed} \t/ {total_rethunk_tests}")
+ksft.print_msg(f"SKIPPED: \t{tests_skipped} \t/ {total_rethunk_tests}")
+ksft.print_msg(f"UNKNOWN: \t{tests_unknown} \t/ {total_rethunk_tests}")
+
+if tests_failed == 0:
+    ksft.test_result_pass("All ITS return thunk sites passed.")
+else:
+    ksft.test_result_fail(f"{tests_failed} failed sites need ITS return thunks.")
+ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_sysfs.py b/tools/testing/selftests/x86/bugs/its_sysfs.py
new file mode 100755
index 000000000000..7bca81f2f606
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_sysfs.py
@@ -0,0 +1,65 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for Indirect Target Selection(ITS) mitigation sysfs status.
+
+import sys, os, re
+this_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, this_dir + '/../../kselftest')
+import ksft
+
+from common import *
+
+bug = "indirect_target_selection"
+mitigation = get_sysfs(bug)
+
+ITS_MITIGATION_ALIGNED_THUNKS	= "Mitigation: Aligned branch/return thunks"
+ITS_MITIGATION_RETPOLINE_STUFF	= "Mitigation: Retpolines, Stuffing RSB"
+ITS_MITIGATION_VMEXIT_ONLY		= "Mitigation: Vulnerable, KVM: Not affected"
+ITS_MITIGATION_VULNERABLE       = "Vulnerable"
+
+def check_mitigation():
+    if mitigation == ITS_MITIGATION_ALIGNED_THUNKS:
+        if cmdline_has(f'{bug}=stuff') and sysfs_has("spectre_v2", "Retpolines"):
+            bug_check_fail(bug, ITS_MITIGATION_ALIGNED_THUNKS, ITS_MITIGATION_RETPOLINE_STUFF)
+            return
+        if cmdline_has(f'{bug}=vmexit') and cpuinfo_has('its_native_only'):
+            bug_check_fail(bug, ITS_MITIGATION_ALIGNED_THUNKS, ITS_MITIGATION_VMEXIT_ONLY)
+            return
+        bug_check_pass(bug, ITS_MITIGATION_ALIGNED_THUNKS)
+        return
+
+    if mitigation == ITS_MITIGATION_RETPOLINE_STUFF:
+        if cmdline_has(f'{bug}=stuff') and sysfs_has("spectre_v2", "Retpolines"):
+            bug_check_pass(bug, ITS_MITIGATION_RETPOLINE_STUFF)
+            return
+        if sysfs_has('retbleed', 'Stuffing'):
+            bug_check_pass(bug, ITS_MITIGATION_RETPOLINE_STUFF)
+            return
+        bug_check_fail(bug, ITS_MITIGATION_RETPOLINE_STUFF, ITS_MITIGATION_ALIGNED_THUNKS)
+
+    if mitigation == ITS_MITIGATION_VMEXIT_ONLY:
+        if cmdline_has(f'{bug}=vmexit') and cpuinfo_has('its_native_only'):
+            bug_check_pass(bug, ITS_MITIGATION_VMEXIT_ONLY)
+            return
+        bug_check_fail(bug, ITS_MITIGATION_VMEXIT_ONLY, ITS_MITIGATION_ALIGNED_THUNKS)
+
+    if mitigation == ITS_MITIGATION_VULNERABLE:
+        if sysfs_has("spectre_v2", "Vulnerable"):
+            bug_check_pass(bug, ITS_MITIGATION_VULNERABLE)
+        else:
+            bug_check_fail(bug, "Mitigation", ITS_MITIGATION_VULNERABLE)
+
+    bug_status_unknown(bug, mitigation)
+    return
+
+ksft.print_header()
+ksft.set_plan(1)
+ksft.print_msg(f'{bug}: {mitigation} ...')
+
+if not basic_checks_sufficient(bug, mitigation):
+    check_mitigation()
+
+ksft.finished()
diff --git a/tools/testing/shared/linux.c b/tools/testing/shared/linux.c
index 66dbb362385f..0f97fb0d19e1 100644
--- a/tools/testing/shared/linux.c
+++ b/tools/testing/shared/linux.c
@@ -150,7 +150,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list)
 {
 	if (kmalloc_verbose)
-		pr_debug("Bulk free %p[0-%lu]\n", list, size - 1);
+		pr_debug("Bulk free %p[0-%zu]\n", list, size - 1);
 
 	pthread_mutex_lock(&cachep->lock);
 	for (int i = 0; i < size; i++)
@@ -168,7 +168,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
 	size_t i;
 
 	if (kmalloc_verbose)
-		pr_debug("Bulk alloc %lu\n", size);
+		pr_debug("Bulk alloc %zu\n", size);
 
 	pthread_mutex_lock(&cachep->lock);
 	if (cachep->nr_objs >= size) {
diff --git a/tools/testing/shared/linux/cleanup.h b/tools/testing/shared/linux/cleanup.h
new file mode 100644
index 000000000000..ea3081426ee9
--- /dev/null
+++ b/tools/testing/shared/linux/cleanup.h
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "../../../../include/linux/cleanup.h"
diff --git a/tools/testing/vsock/timeout.c b/tools/testing/vsock/timeout.c
index 44aee49b6cee..1453d38e08bb 100644
--- a/tools/testing/vsock/timeout.c
+++ b/tools/testing/vsock/timeout.c
@@ -21,6 +21,7 @@
 #include <stdbool.h>
 #include <unistd.h>
 #include <stdio.h>
+#include <time.h>
 #include "timeout.h"
 
 static volatile bool timeout;
@@ -28,6 +29,8 @@ static volatile bool timeout;
 /* SIGALRM handler function.  Do not use sleep(2), alarm(2), or
  * setitimer(2) while using this API - they may interfere with each
  * other.
+ *
+ * If you need to sleep, please use timeout_sleep() provided by this API.
  */
 void sigalrm(int signo)
 {
@@ -58,3 +61,18 @@ void timeout_end(void)
 	alarm(0);
 	timeout = false;
 }
+
+/* Sleep in a timeout section.
+ *
+ * nanosleep(2) can be used with this API since POSIX.1 explicitly
+ * specifies that it does not interact with signals.
+ */
+int timeout_usleep(useconds_t usec)
+{
+	struct timespec ts = {
+		.tv_sec = usec / 1000000,
+		.tv_nsec = (usec % 1000000) * 1000,
+	};
+
+	return nanosleep(&ts, NULL);
+}
diff --git a/tools/testing/vsock/timeout.h b/tools/testing/vsock/timeout.h
index ecb7c840e65a..1c3fcad87a49 100644
--- a/tools/testing/vsock/timeout.h
+++ b/tools/testing/vsock/timeout.h
@@ -11,5 +11,6 @@ void sigalrm(int signo);
 void timeout_begin(unsigned int seconds);
 void timeout_check(const char *operation);
 void timeout_end(void);
+int timeout_usleep(useconds_t usec);
 
 #endif /* TIMEOUT_H */
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index d0f6d253ac72..9ea33b78b9fc 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -1058,18 +1058,39 @@ static void sigpipe(int signo)
 	have_sigpipe = 1;
 }
 
+#define SEND_SLEEP_USEC (10 * 1000)
+
 static void test_stream_check_sigpipe(int fd)
 {
 	ssize_t res;
 
 	have_sigpipe = 0;
 
-	res = send(fd, "A", 1, 0);
-	if (res != -1) {
-		fprintf(stderr, "expected send(2) failure, got %zi\n", res);
-		exit(EXIT_FAILURE);
+	/* When the other peer calls shutdown(SHUT_RD), there is a chance that
+	 * the send() call could occur before the message carrying the close
+	 * information arrives over the transport. In such cases, the send()
+	 * might still succeed. To avoid this race, let's retry the send() call
+	 * a few times, ensuring the test is more reliable.
+	 */
+	timeout_begin(TIMEOUT);
+	while(1) {
+		res = send(fd, "A", 1, 0);
+		if (res == -1 && errno != EINTR)
+			break;
+
+		/* Sleep a little before trying again to avoid flooding the
+		 * other peer and filling its receive buffer, causing
+		 * false-negative.
+		 */
+		timeout_usleep(SEND_SLEEP_USEC);
+		timeout_check("send");
 	}
+	timeout_end();
 
+	if (errno != EPIPE) {
+		fprintf(stderr, "unexpected send(2) errno %d\n", errno);
+		exit(EXIT_FAILURE);
+	}
 	if (!have_sigpipe) {
 		fprintf(stderr, "SIGPIPE expected\n");
 		exit(EXIT_FAILURE);
@@ -1077,12 +1098,21 @@ static void test_stream_check_sigpipe(int fd)
 
 	have_sigpipe = 0;
 
-	res = send(fd, "A", 1, MSG_NOSIGNAL);
-	if (res != -1) {
-		fprintf(stderr, "expected send(2) failure, got %zi\n", res);
-		exit(EXIT_FAILURE);
+	timeout_begin(TIMEOUT);
+	while(1) {
+		res = send(fd, "A", 1, MSG_NOSIGNAL);
+		if (res == -1 && errno != EINTR)
+			break;
+
+		timeout_usleep(SEND_SLEEP_USEC);
+		timeout_check("send");
 	}
+	timeout_end();
 
+	if (errno != EPIPE) {
+		fprintf(stderr, "unexpected send(2) errno %d\n", errno);
+		exit(EXIT_FAILURE);
+	}
 	if (have_sigpipe) {
 		fprintf(stderr, "SIGPIPE not expected\n");
 		exit(EXIT_FAILURE);
@@ -1264,21 +1294,25 @@ static void test_unsent_bytes_client(const struct test_opts *opts, int type)
 	send_buf(fd, buf, sizeof(buf), 0, sizeof(buf));
 	control_expectln("RECEIVED");
 
-	ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
-	if (ret < 0) {
-		if (errno == EOPNOTSUPP) {
-			fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n");
-		} else {
+	/* SIOCOUTQ isn't guaranteed to instantly track sent data. Even though
+	 * the "RECEIVED" message means that the other side has received the
+	 * data, there can be a delay in our kernel before updating the "unsent
+	 * bytes" counter. Repeat SIOCOUTQ until it returns 0.
+	 */
+	timeout_begin(TIMEOUT);
+	do {
+		ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
+		if (ret < 0) {
+			if (errno == EOPNOTSUPP) {
+				fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n");
+				break;
+			}
 			perror("ioctl");
 			exit(EXIT_FAILURE);
 		}
-	} else if (ret == 0 && sock_bytes_unsent != 0) {
-		fprintf(stderr,
-			"Unexpected 'SIOCOUTQ' value, expected 0, got %i\n",
-			sock_bytes_unsent);
-		exit(EXIT_FAILURE);
-	}
-
+		timeout_check("SIOCOUTQ");
+	} while (sock_bytes_unsent != 0);
+	timeout_end();
 	close(fd);
 }
 
diff --git a/usr/include/Makefile b/usr/include/Makefile
index e3d6b03527fe..f02f41941b60 100644
--- a/usr/include/Makefile
+++ b/usr/include/Makefile
@@ -59,6 +59,10 @@ ifeq ($(SRCARCH),arc)
 no-header-test += linux/bpf_perf_event.h
 endif
 
+ifeq ($(SRCARCH),openrisc)
+no-header-test += linux/bpf_perf_event.h
+endif
+
 ifeq ($(SRCARCH),powerpc)
 no-header-test += linux/bpf_perf_event.h
 endif