| Age | Commit message (Collapse) | Author |
|---|
|
When conditions are met, schedule a delayed work in bond event handler
to perform bonding operation according to the bond state. In the case
of changing slave number or link state, re-set the netdev for the bond
ibdev after the modification is complete, since these two operations
may not call hns_roce_set_bond_netdev() in hns_roce_init().
The delayed work will be paused when there is a driver reset or exit
to avoid concurrency.
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20251112093510.3696363-7-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Implement hns_roce_slave_init() and hns_roce_slave_uninit() for device
init/uninit in bonding cases. The former is used to initialize a slave
ibdev (when the slave is unlinked from a bond) or a bond ibdev, while
the latter does the opposite. Most of the process is the same as
regular device init/uninit, while some bonding‑specific steps below are
also added.
In bond device init flow, choose one slave to re-initialize as the
main_hr_dev of the bond, and it will be the only device presented for
multiple slaves. During registration, set and active netdev to the
ibdev based on the link state of the slaves. When this main_hr_dev
slave is being unlinked while the bond is still valid, choose a new
slave from the rest and initialize it as the new bond device.
In uninit flow, add a bond cleanup process, restore all the other
slaves and clean up bond resource. This is only for the case where
the port of main_hr_dev is directly removed without unlinking it
from bond.
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20251112093510.3696363-6-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Add three bonding cmds to configure bonding settings to HW.
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20251112093510.3696363-5-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Register netdev notifier for two bonding events NETDEV_CHANGEUPPER
and NETDEV_CHANGELOWERSTATE.
In NETDEV_CHANGEUPPER event handler, check some rules about the HW
constraints when trying to link a new slave to the masteri, and
store some bonding information from the notifier. In unlinking case,
simply check the number of the rest slaves to decide whether the
bond is still supported.
In NETDEV_CHANGELOWERSTATE event handler, not much is done. It
simply sets the bond state when the bond is ready, which will be
used later.
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20251112093510.3696363-4-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Allocate bond_grp resources for each card when the first device in
this card is registered. Block the initialization of VF when its PF
is a bonded slave, as VF is not supported in this case due to HW
constraints.
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20251112093510.3696363-3-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Add helpers to obtain netdev and bus_num from hr_dev.
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20251112093510.3696363-2-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Initialize the firmware and hardware with HWRM command.
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Link: https://patch.msgid.link/20251117171136.128193-9-siva.kallam@broadcom.com
Reviewed-by: Usman Ansari <usman.ansari@broadcom.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Add basic debugfs infrastructure for Broadcom next generation
controller.
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Link: https://patch.msgid.link/20251117171136.128193-8-siva.kallam@broadcom.com
Reviewed-by: Usman Ansari <usman.ansari@broadcom.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Enable Firmware channel and query device attributes
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Link: https://patch.msgid.link/20251117171136.128193-7-siva.kallam@broadcom.com
Reviewed-by: Usman Ansari <usman.ansari@broadcom.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Add infrastructure for enabling Firmware channel.
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Link: https://patch.msgid.link/20251117171136.128193-6-siva.kallam@broadcom.com
Reviewed-by: Usman Ansari <usman.ansari@broadcom.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Allocate required memory resources for Firmware channel.
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Link: https://patch.msgid.link/20251117171136.128193-5-siva.kallam@broadcom.com
Reviewed-by: Usman Ansari <usman.ansari@broadcom.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Register and get the basic required resources from bnge driver.
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Link: https://patch.msgid.link/20251117171136.128193-4-siva.kallam@broadcom.com
Reviewed-by: Usman Ansari <usman.ansari@broadcom.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Add basic Auxiliary interface to the driver which supports
the BCM5770X NIC family.
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Link: https://patch.msgid.link/20251117171136.128193-3-siva.kallam@broadcom.com
Reviewed-by: Usman Ansari <usman.ansari@broadcom.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Add an auxiliary (aux) device to support RoCE. The base driver is
responsible for creating the auxiliary device and allocating the
required resources to it, which will be owned by the bnge RoCE
driver in future patches.
Signed-off-by: Vikas Gupta <vikas.gupta@broadcom.com>
Link: https://patch.msgid.link/20251117171136.128193-2-siva.kallam@broadcom.com
Reviewed-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Driver is not creating the debugfs hooks for CQ coalesc parameters
because of a wrong check. Fixed the condition check inside
bnxt_re_init_cq_coal_debugfs().
Fixes: cf2749079011 ("RDMA/bnxt_re: Add a debugfs entry for CQE coalescing tuning")
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20251117061306.1140588-1-kalesh-anakkur.purayil@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
When a process exits with numerous large, pinned memory regions consisting
of 4KB pages, the cleanup of the memory region through __ib_umem_release()
may cause soft lockups. This is because unpin_user_page_range_dirty_lock()
is called in a tight loop for unpin and releasing page without yielding the
CPU.
watchdog: BUG: soft lockup - CPU#44 stuck for 26s! [python3:73464]
Kernel panic - not syncing: softlockup: hung tasks
CPU: 44 PID: 73464 Comm: python3 Tainted: G OEL
asm_sysvec_apic_timer_interrupt+0x1b/0x20
RIP: 0010:free_unref_page+0xff/0x190
? free_unref_page+0xe3/0x190
__put_page+0x77/0xe0
put_compound_head+0xed/0x100
unpin_user_page_range_dirty_lock+0xb2/0x180
__ib_umem_release+0x57/0xb0 [ib_core]
ib_umem_release+0x3f/0xd0 [ib_core]
mlx5_ib_dereg_mr+0x2e9/0x440 [mlx5_ib]
ib_dereg_mr_user+0x43/0xb0 [ib_core]
uverbs_free_mr+0x15/0x20 [ib_uverbs]
destroy_hw_idr_uobject+0x21/0x60 [ib_uverbs]
uverbs_destroy_uobject+0x38/0x1b0 [ib_uverbs]
__uverbs_cleanup_ufile+0xd1/0x150 [ib_uverbs]
uverbs_destroy_ufile_hw+0x3f/0x100 [ib_uverbs]
ib_uverbs_close+0x1f/0xb0 [ib_uverbs]
__fput+0x9c/0x280
____fput+0xe/0x20
task_work_run+0x6a/0xb0
do_exit+0x217/0x3c0
do_group_exit+0x3b/0xb0
get_signal+0x150/0x900
arch_do_signal_or_restart+0xde/0x100
exit_to_user_mode_loop+0xc4/0x160
exit_to_user_mode_prepare+0xa0/0xb0
syscall_exit_to_user_mode+0x27/0x50
do_syscall_64+0x63/0xb0
Fix soft lockup issues by incorporating cond_resched() calls within
__ib_umem_release(), and this SG entries are typically grouped in 2MB
chunks on x86_64, adding cond_resched() should has minimal performance
impact.
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Link: https://patch.msgid.link/20251113095317.2628-1-lirongqing@baidu.com
Acked-by: Junxian Huang <huangjunxian6@hisilicon.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Fix couple of occurrences of the misspelled word "reource"
in the comments with the correct spelling "resource".
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20251113105457.879903-1-kalesh-anakkur.purayil@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
The variable udata cannot be NULL because irdma_create_user_ah() always
receives it. Therefore, the if() check can be safely removed.
Signed-off-by: Tuo Li <islituo@gmail.com>
Link: https://patch.msgid.link/20251112120253.68945-1-islituo@gmail.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
In include/rdma/ib_cm.h:
Correct a typedef's kernel-doc notation by adding the 'typedef' keyword
to it to avoid a warning.
Add a leading " *" to a kernel-doc line to avoid a warning.
Warning: ib_cm.h:289 function parameter 'ib_cm_handler' not described
in 'int'
Warning: ib_cm.h:289 expecting prototype for ib_cm_handler(). Prototype
was for int() instead
Warning: ib_cm.h:484 bad line: connection message in case duplicates
are received.
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://patch.msgid.link/20251112062908.2711007-1-rdunlap@infradead.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Single patch to expose new link mode for 1600Gbps, utilizing 8 lanes at
200Gbps per lane.
Signed-off-by: Leon Romanovsky <leon@kernel.org>
* mlx5-next:
net/mlx5: Expose definition for 1600Gbps link mode
|
|
This patch exposes new link mode for 1600Gbps, utilizing 8 lanes at
200Gbps per lane.
Co-developed-by: Yael Chemla <ychemla@nvidia.com>
Reviewed-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1762863888-1092798-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
After device_initialize() is called, use put_device() to release the
device according to kernel device management rules. While direct
kfree() work in this case, using put_device() is more correct.
Found by code review.
Fixes: 9cb837480424 ("RDMA/rtrs: server: main functionality")
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
Link: https://patch.msgid.link/20251110005158.13394-1-make24@iscas.ac.cn
Acked-by: Jack Wang <jinpu.wang@ionos.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Currently if a user enqueues a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistency cannot be addressed without refactoring the API.
alloc_workqueue() treats all queues as per-CPU by default, while unbound
workqueues must opt-in via WQ_UNBOUND.
This default is suboptimal: most workloads benefit from unbound queues,
allowing the scheduler to place worker threads where they’re needed and
reducing noise when CPUs are isolated.
This continues the effort to refactor workqueue APIs, which began with
the introduction of new workqueues and a new alloc_workqueue flag in:
commit 128ea9f6ccfb ("workqueue: Add system_percpu_wq and system_dfl_wq")
commit 930c2ea566af ("workqueue: Add new WQ_PERCPU flag")
This change adds a new WQ_PERCPU flag to explicitly request
alloc_workqueue() to be per-cpu when WQ_UNBOUND has not been specified.
With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND),
any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND
must now use WQ_PERCPU.
Once migration is complete, WQ_UNBOUND can be removed and unbound will
become the implicit default.
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Link: https://patch.msgid.link/20251107133626.190952-1-marco.crivellari@suse.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Currently if a user enqueues a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistency cannot be addressed without refactoring the API.
alloc_workqueue() treats all queues as per-CPU by default, while unbound
workqueues must opt-in via WQ_UNBOUND.
This default is suboptimal: most workloads benefit from unbound queues,
allowing the scheduler to place worker threads where they’re needed and
reducing noise when CPUs are isolated.
This continues the effort to refactor workqueue APIs, which began with
the introduction of new workqueues and a new alloc_workqueue flag in:
commit 128ea9f6ccfb ("workqueue: Add system_percpu_wq and system_dfl_wq")
commit 930c2ea566af ("workqueue: Add new WQ_PERCPU flag")
This change adds a new WQ_PERCPU flag to explicitly request
alloc_workqueue() to be per-cpu when WQ_UNBOUND has not been specified.
With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND),
any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND
must now use WQ_PERCPU.
Once migration is complete, WQ_UNBOUND can be removed and unbound will
become the implicit default.
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Link: https://patch.msgid.link/20251107133306.187939-1-marco.crivellari@suse.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
The CQ registry was never actually used (ceq->reg_cq was always NULL),
so remove the dead code.
Signed-off-by: Jacob Moroni <jmoroni@google.com>
Link: https://patch.msgid.link/20251105162841.31786-1-jmoroni@google.com
Acked-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
|
|
Allows the creation of RDMA TRANSPORT tables over VFs/SFs that
belong to another eswitch manager. Which is only possible for PFs that
were connected via a create_lag PRM command.
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://patch.msgid.link/20251029-support-other-eswitch-v1-7-98bb707b5d57@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Refactor the _get_prio() function to remove redundant arguments by
reusing the existing flow table attributes struct instead of passing
attributes separately. This improves code clarity and maintainability.
In addition allows downstream patch to add new parameter without
needing to change __get_prio() arguments.
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://patch.msgid.link/20251029-support-other-eswitch-v1-6-98bb707b5d57@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
When building a devx object destruction command for steering objects add
consideration for other_eswitch argument to allow proper destruction for
objects that were created with it.
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://patch.msgid.link/20251029-support-other-eswitch-v1-5-98bb707b5d57@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
In case of a LAG configuration change the root namespace core device for
all of the LAG slaves to be the core device of the master device for
RDMA_TRANSPORT namespaces, in order to ensure all tables are created
through the master device.
Once the LAG is disabled revert back to the native core device.
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://patch.msgid.link/20251029-support-other-eswitch-v1-4-98bb707b5d57@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
When the device in switchdev mode, the RDMA device manages all the
vports which belong to its representors, which can lead to a situation
where the PF that is used to manage the RDMA device isn't the native PF
of some of the vports it manages.
Add infrastructure to allow the master PF to manage all the hardware
resources for the vports under its management.
Whereas currently the only such resource is RDMA TRANSPORT steering
domains.
That is done by adding new FW argument other_eswitch which is passed by
the driver to the FW to allow the master PF to properly manage vports
belonging to other native PF.
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Add mlx5_fs_set_root_dev() function which swaps the root namespace
core device with another one for a given table_type.
It is intended for usage only by RDMA_TRANSPORT tables in case of LAG
configuration, to allow the creation of tables during LAG always
through the LAG master device, which is valid since during LAG the
master is allowed to manage the RDMA_TRANSPORT tables of its slaves.
In addition move the table_type enum to global include to allow its use
in a downstream patch in the RDMA driver.
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://patch.msgid.link/20251029-support-other-eswitch-v1-3-98bb707b5d57@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Add other_eswitch support which allows flow tables creation above vports
that reside on different esw managers.
The new flag MLX5_FLOW_TABLE_OTHER_ESWITCH indicates if the
esw_owner_vhca_id attribute is supported.
Note that this is only supported if the Advanced-RDMA cap-
rdma_transport_manager_other_eswitch is set.
And it is the caller responsibility to check that.
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://patch.msgid.link/20251029-support-other-eswitch-v1-2-98bb707b5d57@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Add OTHER_ESWITCH capabilities which includes other_eswitch and
eswitch_owner_vhca_id to all steering objects.
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://patch.msgid.link/20251029-support-other-eswitch-v1-1-98bb707b5d57@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Add support for direct ST mode where ST Table Location equals
PCI_TPH_LOC_NONE.
In that case, no steering table exists, the steering tag itself will be
used directly by the SW, FW, HW from the mkey.
This enables RDMA users to use the current exposed APIs to work in
direct mode.
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://patch.msgid.link/20251027-st-direct-mode-v1-2-e0ad953866b6@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Expose pcie_tph_get_st_table_loc() to be used by drivers as will be done
in the next patch from the series.
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://patch.msgid.link/20251027-st-direct-mode-v1-1-e0ad953866b6@nvidia.com
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
This patch adds debugfs interfaces that allows the user to
enable/disable the RoCE CQ coalescing and fine tune certain
CQ coalescing parameters which would be helpful during debug.
Signed-off-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Reviewed-by: Hongguang Gao <hongguang.gao@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20251103043425.234846-1-kalesh-anakkur.purayil@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Correct the kernel-doc comments format to avoid around 35 kernel-doc
warnings:
- use struct keyword to introduce struct kernel-doc comments
- use correct variable name for some struct members
- use correct function name in comments for some functions
- fix spelling in a few comments
- use a ':' instead of '-' to separate struct members from their
descriptions
- add a function name heading for rvt_div_mtu()
This leaves one struct member that is not described:
rdmavt_qp.h:206: warning: Function parameter or struct member 'wq'
not described in 'rvt_krwq'
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://patch.msgid.link/20251105045127.106822-1-rdunlap@infradead.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Currently if a user enqueue a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistentcy cannot be addressed without refactoring the API.
alloc_workqueue() treats all queues as per-CPU by default, while unbound
workqueues must opt-in via WQ_UNBOUND.
This default is suboptimal: most workloads benefit from unbound queues,
allowing the scheduler to place worker threads where they’re needed and
reducing noise when CPUs are isolated.
This change adds a new WQ_PERCPU flag to explicitly request
alloc_workqueue() to be per-cpu when WQ_UNBOUND has not been specified.
With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND),
any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND
must now use WQ_PERCPU.
Once migration is complete, WQ_UNBOUND can be removed and unbound will
become the implicit default.
CC: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Link: https://patch.msgid.link/20251101163121.78400-6-marco.crivellari@suse.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Currently if a user enqueue a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistentcy cannot be addressed without refactoring the API.
alloc_workqueue() treats all queues as per-CPU by default, while unbound
workqueues must opt-in via WQ_UNBOUND.
This default is suboptimal: most workloads benefit from unbound queues,
allowing the scheduler to place worker threads where they’re needed and
reducing noise when CPUs are isolated.
This change adds a new WQ_PERCPU flag to explicitly request
alloc_workqueue() to be per-cpu when WQ_UNBOUND has not been specified.
With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND),
any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND
must now use WQ_PERCPU.
Once migration is complete, WQ_UNBOUND can be removed and unbound will
become the implicit default.
CC: Yishai Hadas <yishaih@nvidia.com>
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Link: https://patch.msgid.link/20251101163121.78400-5-marco.crivellari@suse.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Currently if a user enqueue a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistentcy cannot be addressed without refactoring the API.
alloc_workqueue() treats all queues as per-CPU by default, while unbound
workqueues must opt-in via WQ_UNBOUND.
This default is suboptimal: most workloads benefit from unbound queues,
allowing the scheduler to place worker threads where they’re needed and
reducing noise when CPUs are isolated.
This change adds a new WQ_PERCPU flag to explicitly request
alloc_workqueue() to be per-cpu when WQ_UNBOUND has not been specified.
With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND),
any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND
must now use WQ_PERCPU.
Once migration is complete, WQ_UNBOUND can be removed and unbound will
become the implicit default.
CC: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Link: https://patch.msgid.link/20251101163121.78400-4-marco.crivellari@suse.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Currently if a user enqueue a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistentcy cannot be addressed without refactoring the API.
alloc_workqueue() treats all queues as per-CPU by default, while unbound
workqueues must opt-in via WQ_UNBOUND.
This default is suboptimal: most workloads benefit from unbound queues,
allowing the scheduler to place worker threads where they’re needed and
reducing noise when CPUs are isolated.
This change adds a new WQ_PERCPU flag to explicitly request
alloc_workqueue() to be per-cpu when WQ_UNBOUND has not been specified.
With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND),
any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND
must now use WQ_PERCPU.
Once migration is complete, WQ_UNBOUND can be removed and unbound will
become the implicit default.
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Link: https://patch.msgid.link/20251101163121.78400-3-marco.crivellari@suse.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Currently if a user enqueue a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistency cannot be addressed without refactoring the API.
system_unbound_wq should be the default workqueue so as not to enforce
locality constraints for random work whenever it's not required.
Adding system_dfl_wq to encourage its use when unbound work should be used.
The old system_unbound_wq will be kept for a few release cycles.
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Link: https://patch.msgid.link/20251101163121.78400-2-marco.crivellari@suse.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Need to take an SRQ lock in poll_cq before moving SRQ tail.
Signed-off-by: Jay Bhat <jay.bhat@intel.com>
Reviewed-by: Jacob Moroni <jmoroni@google.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Link: https://patch.msgid.link/20251031021726.1003-7-tatyana.e.nikolova@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
CQ shadow area should not be updated at the end of a page (once every
64th CQ entry), except when CQ has no more CQEs. SW must also increase
the requested CQ size by 1 and make sure the CQ is not exactly one page
in size. This is to address a quirk in the hardware.
Signed-off-by: Jay Bhat <jay.bhat@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Link: https://patch.msgid.link/20251031021726.1003-4-tatyana.e.nikolova@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
In case we get an unsignaled error completion, we silently consume the CQE by
pretending the QP does not exist. Without this, bookkeeping for signaled
completions does not work correctly.
Signed-off-by: Jay Bhat <jay.bhat@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Link: https://patch.msgid.link/20251031021726.1003-5-tatyana.e.nikolova@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Failure to initialize info.create field to false in certain cases
was resulting in incorrect status code going to rdma-core when dereg_mr
failed during reset. To fix this, memset entire cqp_request->info
in irdma_alloc_and_get_cqp_request() function, so that this is not spread
all over the code.
Signed-off-by: Bhat, Jay <jay.bhat@intel.com>
Reviewed-by: Jacob Moroni <jmoroni@google.com>
Signed-off-by: Krzysztof Czurylo <krzysztof.czurylo@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Link: https://patch.msgid.link/20251031021726.1003-2-tatyana.e.nikolova@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Enforce local fence for LOCAL_INV WRs to
avoid spurious FASTREG_VALID_MKEY async events
during heavy invalidation/registration activity.
Signed-off-by: Jacob Moroni <jmoroni@google.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Link: https://patch.msgid.link/20251031021726.1003-3-tatyana.e.nikolova@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
A NULL pointer dereference can occur in rxe_srq_chk_attr() when
ibv_modify_srq() is invoked twice in succession under certain error
conditions. The first call may fail in rxe_queue_resize(), which leads
rxe_srq_from_attr() to set srq->rq.queue = NULL. The second call then
triggers a crash (null deref) when accessing
srq->rq.queue->buf->index_mask.
Call Trace:
<TASK>
rxe_modify_srq+0x170/0x480 [rdma_rxe]
? __pfx_rxe_modify_srq+0x10/0x10 [rdma_rxe]
? uverbs_try_lock_object+0x4f/0xa0 [ib_uverbs]
? rdma_lookup_get_uobject+0x1f0/0x380 [ib_uverbs]
ib_uverbs_modify_srq+0x204/0x290 [ib_uverbs]
? __pfx_ib_uverbs_modify_srq+0x10/0x10 [ib_uverbs]
? tryinc_node_nr_active+0xe6/0x150
? uverbs_fill_udata+0xed/0x4f0 [ib_uverbs]
ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x2c0/0x470 [ib_uverbs]
? __pfx_ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x10/0x10 [ib_uverbs]
? uverbs_fill_udata+0xed/0x4f0 [ib_uverbs]
ib_uverbs_run_method+0x55a/0x6e0 [ib_uverbs]
? __pfx_ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x10/0x10 [ib_uverbs]
ib_uverbs_cmd_verbs+0x54d/0x800 [ib_uverbs]
? __pfx_ib_uverbs_cmd_verbs+0x10/0x10 [ib_uverbs]
? __pfx___raw_spin_lock_irqsave+0x10/0x10
? __pfx_do_vfs_ioctl+0x10/0x10
? ioctl_has_perm.constprop.0.isra.0+0x2c7/0x4c0
? __pfx_ioctl_has_perm.constprop.0.isra.0+0x10/0x10
ib_uverbs_ioctl+0x13e/0x220 [ib_uverbs]
? __pfx_ib_uverbs_ioctl+0x10/0x10 [ib_uverbs]
__x64_sys_ioctl+0x138/0x1c0
do_syscall_64+0x82/0x250
? fdget_pos+0x58/0x4c0
? ksys_write+0xf3/0x1c0
? __pfx_ksys_write+0x10/0x10
? do_syscall_64+0xc8/0x250
? __pfx_vm_mmap_pgoff+0x10/0x10
? fget+0x173/0x230
? fput+0x2a/0x80
? ksys_mmap_pgoff+0x224/0x4c0
? do_syscall_64+0xc8/0x250
? do_user_addr_fault+0x37b/0xfe0
? clear_bhb_loop+0x50/0xa0
? clear_bhb_loop+0x50/0xa0
? clear_bhb_loop+0x50/0xa0
entry_SYSCALL_64_after_hwframe+0x76/0x7e
Fixes: 8700e3e7c485 ("Soft RoCE driver")
Tested-by: Liu Yi <asatsuyu.liu@gmail.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Link: https://patch.msgid.link/20251027215203.1321-1-yanjun.zhu@linux.dev
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
When a GSI MAD packet is sent on the QP, it will potentially be
retried CMA_MAX_CM_RETRIES times with a timeout value of:
4.096usec * 2 ^ CMA_CM_RESPONSE_TIMEOUT
The above equates to ~64 seconds using the default CMA values.
The cm_id_priv's refcount will be incremented for this period.
Therefore, the timeout value waiting for a cm_id destruction must be
based on the effective timeout of MAD packets. To provide additional
leeway, we add 25% to this timeout and use that instead of the
constant 10 seconds timeout, which may result in false negatives.
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Link: https://patch.msgid.link/20251021132738.4179604-1-haakon.bugge@oracle.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
|
|
Before this patch during either switchdev or legacy mode enablement we
cleared the mac address of vports between changes. This change allows us
to preserve the vports mac address between eswitch mode changes.
Vports hold information for VFs/SFs such as the permanent mac address.
VF/SF mac can be set either by iproute vf interface or devlink function
interface. For no obvious reason we reset it to 0 on switchdev/legacy
mode changes, this patch is fixing that, to align with other vport
information that are never reset, e.g GUID,mtu,promisc mode, etc ..
Signed-off-by: Adithya Jayachandran <ajayachandra@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Acked-by: Leon Romanovsky <leon@kernel.org> # RDMA
|
